From 0eb71a9da5796851fa87ddc1a534066c0fe54055 Mon Sep 17 00:00:00 2001 From: NeilBrown Date: Mon, 18 Jun 2018 12:52:50 +1000 Subject: rhashtable: split rhashtable.h Due to the use of rhashtables in net namespaces, rhashtable.h is included in lots of the kernel, so a small changes can required a large recompilation. This makes development painful. This patch splits out rhashtable-types.h which just includes the major type declarations, and does not include (non-trivial) inline code. rhashtable.h is no longer included by anything in the include/ directory. Common include files only include rhashtable-types.h so a large recompilation is only triggered when that changes. Acked-by: Herbert Xu Signed-off-by: NeilBrown Signed-off-by: David S. Miller --- net/sctp/input.c | 1 + net/sctp/socket.c | 1 + 2 files changed, 2 insertions(+) (limited to 'net/sctp') diff --git a/net/sctp/input.c b/net/sctp/input.c index ba8a6e6c36fa..9bbc5f92c941 100644 --- a/net/sctp/input.c +++ b/net/sctp/input.c @@ -56,6 +56,7 @@ #include #include #include +#include /* Forward declarations for internal helpers. */ static int sctp_rcv_ootb(struct sk_buff *); diff --git a/net/sctp/socket.c b/net/sctp/socket.c index d20f7addee19..0e91e83eea5a 100644 --- a/net/sctp/socket.c +++ b/net/sctp/socket.c @@ -66,6 +66,7 @@ #include #include #include +#include #include #include -- cgit v1.2.3 From b0e9a2fe3ff971950833bc0ffc383babd9443bc4 Mon Sep 17 00:00:00 2001 From: Xin Long Date: Thu, 28 Jun 2018 15:31:00 +0800 Subject: sctp: add support for SCTP_REUSE_PORT sockopt This feature is actually already supported by sk->sk_reuse which can be set by socket level opt SO_REUSEADDR. But it's not working exactly as RFC6458 demands in section 8.1.27, like: - This option only supports one-to-one style SCTP sockets - This socket option must not be used after calling bind() or sctp_bindx(). Besides, SCTP_REUSE_PORT sockopt should be provided for user's programs. Otherwise, the programs with SCTP_REUSE_PORT from other systems will not work in linux. To separate it from the socket level version, this patch adds 'reuse' in sctp_sock and it works pretty much as sk->sk_reuse, but with some extra setup limitations that are needed when it is being enabled. "It should be noted that the behavior of the socket-level socket option to reuse ports and/or addresses for SCTP sockets is unspecified", so it leaves SO_REUSEADDR as is for the compatibility. Note that the name SCTP_REUSE_PORT is somewhat confusing, as its functionality is nearly identical to SO_REUSEADDR, but with some extra restrictions. Here it uses 'reuse' in sctp_sock instead of 'reuseport'. As for sk->sk_reuseport support for SCTP, it will be added in another patch. Thanks to Neil to make this clear. v1->v2: - add sctp_sk->reuse to separate it from the socket level version. v2->v3: - improve changelog according to Marcelo's suggestion. Acked-by: Neil Horman Signed-off-by: Xin Long Signed-off-by: David S. Miller --- include/net/sctp/structs.h | 1 + include/uapi/linux/sctp.h | 1 + net/sctp/socket.c | 62 ++++++++++++++++++++++++++++++++++++++++------ 3 files changed, 57 insertions(+), 7 deletions(-) (limited to 'net/sctp') diff --git a/include/net/sctp/structs.h b/include/net/sctp/structs.h index e0f962d27386..701a51736fa5 100644 --- a/include/net/sctp/structs.h +++ b/include/net/sctp/structs.h @@ -220,6 +220,7 @@ struct sctp_sock { __u32 adaptation_ind; __u32 pd_point; __u16 nodelay:1, + reuse:1, disable_fragments:1, v4mapped:1, frag_interleave:1, diff --git a/include/uapi/linux/sctp.h b/include/uapi/linux/sctp.h index b64d583bf053..c02986a284db 100644 --- a/include/uapi/linux/sctp.h +++ b/include/uapi/linux/sctp.h @@ -100,6 +100,7 @@ typedef __s32 sctp_assoc_t; #define SCTP_RECVNXTINFO 33 #define SCTP_DEFAULT_SNDINFO 34 #define SCTP_AUTH_DEACTIVATE_KEY 35 +#define SCTP_REUSE_PORT 36 /* Internal Socket Options. Some of the sctp library functions are * implemented using these socket options. diff --git a/net/sctp/socket.c b/net/sctp/socket.c index 0e91e83eea5a..bf11f9cacb63 100644 --- a/net/sctp/socket.c +++ b/net/sctp/socket.c @@ -4170,6 +4170,28 @@ out: return retval; } +static int sctp_setsockopt_reuse_port(struct sock *sk, char __user *optval, + unsigned int optlen) +{ + int val; + + if (!sctp_style(sk, TCP)) + return -EOPNOTSUPP; + + if (sctp_sk(sk)->ep->base.bind_addr.port) + return -EFAULT; + + if (optlen < sizeof(int)) + return -EINVAL; + + if (get_user(val, (int __user *)optval)) + return -EFAULT; + + sctp_sk(sk)->reuse = !!val; + + return 0; +} + /* API 6.2 setsockopt(), getsockopt() * * Applications use setsockopt() and getsockopt() to set or retrieve @@ -4364,6 +4386,9 @@ static int sctp_setsockopt(struct sock *sk, int level, int optname, retval = sctp_setsockopt_interleaving_supported(sk, optval, optlen); break; + case SCTP_REUSE_PORT: + retval = sctp_setsockopt_reuse_port(sk, optval, optlen); + break; default: retval = -ENOPROTOOPT; break; @@ -7197,6 +7222,26 @@ out: return retval; } +static int sctp_getsockopt_reuse_port(struct sock *sk, int len, + char __user *optval, + int __user *optlen) +{ + int val; + + if (len < sizeof(int)) + return -EINVAL; + + len = sizeof(int); + val = sctp_sk(sk)->reuse; + if (put_user(len, optlen)) + return -EFAULT; + + if (copy_to_user(optval, &val, len)) + return -EFAULT; + + return 0; +} + static int sctp_getsockopt(struct sock *sk, int level, int optname, char __user *optval, int __user *optlen) { @@ -7392,6 +7437,9 @@ static int sctp_getsockopt(struct sock *sk, int level, int optname, retval = sctp_getsockopt_interleaving_supported(sk, len, optval, optlen); break; + case SCTP_REUSE_PORT: + retval = sctp_getsockopt_reuse_port(sk, len, optval, optlen); + break; default: retval = -ENOPROTOOPT; break; @@ -7429,6 +7477,7 @@ static struct sctp_bind_bucket *sctp_bucket_create( static long sctp_get_port_local(struct sock *sk, union sctp_addr *addr) { + bool reuse = (sk->sk_reuse || sctp_sk(sk)->reuse); struct sctp_bind_hashbucket *head; /* hash list */ struct sctp_bind_bucket *pp; unsigned short snum; @@ -7501,13 +7550,11 @@ pp_found: * used by other socket (pp->owner not empty); that other * socket is going to be sk2. */ - int reuse = sk->sk_reuse; struct sock *sk2; pr_debug("%s: found a possible match\n", __func__); - if (pp->fastreuse && sk->sk_reuse && - sk->sk_state != SCTP_SS_LISTENING) + if (pp->fastreuse && reuse && sk->sk_state != SCTP_SS_LISTENING) goto success; /* Run through the list of sockets bound to the port @@ -7525,7 +7572,7 @@ pp_found: ep2 = sctp_sk(sk2)->ep; if (sk == sk2 || - (reuse && sk2->sk_reuse && + (reuse && (sk2->sk_reuse || sctp_sk(sk2)->reuse) && sk2->sk_state != SCTP_SS_LISTENING)) continue; @@ -7549,12 +7596,12 @@ pp_not_found: * SO_REUSEADDR on this socket -sk-). */ if (hlist_empty(&pp->owner)) { - if (sk->sk_reuse && sk->sk_state != SCTP_SS_LISTENING) + if (reuse && sk->sk_state != SCTP_SS_LISTENING) pp->fastreuse = 1; else pp->fastreuse = 0; } else if (pp->fastreuse && - (!sk->sk_reuse || sk->sk_state == SCTP_SS_LISTENING)) + (!reuse || sk->sk_state == SCTP_SS_LISTENING)) pp->fastreuse = 0; /* We are set, so fill up all the data in the hash table @@ -7685,7 +7732,7 @@ int sctp_inet_listen(struct socket *sock, int backlog) err = 0; sctp_unhash_endpoint(ep); sk->sk_state = SCTP_SS_CLOSED; - if (sk->sk_reuse) + if (sk->sk_reuse || sctp_sk(sk)->reuse) sctp_sk(sk)->bind_hash->fastreuse = 1; goto out; } @@ -8550,6 +8597,7 @@ void sctp_copy_sock(struct sock *newsk, struct sock *sk, 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 = sctp_destruct_sock; -- cgit v1.2.3 From 8a9c58d28d0f66569737a3295116710ed24573cd Mon Sep 17 00:00:00 2001 From: Xin Long Date: Mon, 2 Jul 2018 18:21:12 +0800 Subject: sctp: add support for dscp and flowlabel per transport Like some other per transport params, flowlabel and dscp are added in transport, asoc and sctp_sock. By default, transport sets its value from asoc's, and asoc does it from sctp_sock. flowlabel only works for ipv6 transport. Other than that they need to be passed down in sctp_xmit, flow4/6 also needs to set them before looking up route in get_dst. Note that it uses '& 0x100000' to check if flowlabel is set and '& 0x1' (tos 1st bit is unused) to check if dscp is set by users, so that they could be set to 0 by sockopt in next patch. Signed-off-by: Xin Long Signed-off-by: David S. Miller --- include/linux/sctp.h | 7 +++++++ include/net/sctp/structs.h | 9 +++++++++ net/sctp/associola.c | 7 +++++++ net/sctp/ipv6.c | 11 +++++++++-- net/sctp/protocol.c | 16 ++++++++++++---- 5 files changed, 44 insertions(+), 6 deletions(-) (limited to 'net/sctp') diff --git a/include/linux/sctp.h b/include/linux/sctp.h index b36c76635f18..83d94341e003 100644 --- a/include/linux/sctp.h +++ b/include/linux/sctp.h @@ -801,4 +801,11 @@ struct sctp_strreset_resptsn { __be32 receivers_next_tsn; }; +enum { + SCTP_DSCP_SET_MASK = 0x1, + SCTP_DSCP_VAL_MASK = 0xfc, + SCTP_FLOWLABEL_SET_MASK = 0x100000, + SCTP_FLOWLABEL_VAL_MASK = 0xfffff +}; + #endif /* __LINUX_SCTP_H__ */ diff --git a/include/net/sctp/structs.h b/include/net/sctp/structs.h index 701a51736fa5..ab869e0d8326 100644 --- a/include/net/sctp/structs.h +++ b/include/net/sctp/structs.h @@ -193,6 +193,9 @@ struct sctp_sock { /* This is the max_retrans value for new associations. */ __u16 pathmaxrxt; + __u32 flowlabel; + __u8 dscp; + /* The initial Path MTU to use for new associations. */ __u32 pathmtu; @@ -895,6 +898,9 @@ struct sctp_transport { */ __u16 pathmaxrxt; + __u32 flowlabel; + __u8 dscp; + /* This is the partially failed retrans value for the transport * and will be initialized from the assocs value. This can be changed * using the SCTP_PEER_ADDR_THLDS socket option @@ -1772,6 +1778,9 @@ struct sctp_association { */ __u16 pathmaxrxt; + __u32 flowlabel; + __u8 dscp; + /* Flag that path mtu update is pending */ __u8 pmtu_pending; diff --git a/net/sctp/associola.c b/net/sctp/associola.c index 5d5a16204d50..16ecfbc95614 100644 --- a/net/sctp/associola.c +++ b/net/sctp/associola.c @@ -115,6 +115,9 @@ static struct sctp_association *sctp_association_init( /* Initialize path max retrans value. */ asoc->pathmaxrxt = sp->pathmaxrxt; + asoc->flowlabel = sp->flowlabel; + asoc->dscp = sp->dscp; + /* Initialize default path MTU. */ asoc->pathmtu = sp->pathmtu; @@ -647,6 +650,10 @@ struct sctp_transport *sctp_assoc_add_peer(struct sctp_association *asoc, peer->sackdelay = asoc->sackdelay; peer->sackfreq = asoc->sackfreq; + if (addr->sa.sa_family == AF_INET6) + peer->flowlabel = asoc->flowlabel; + peer->dscp = asoc->dscp; + /* Enable/disable heartbeat, SACK delay, and path MTU discovery * based on association setting. */ diff --git a/net/sctp/ipv6.c b/net/sctp/ipv6.c index 0cd2e764f47f..38102bf7f13e 100644 --- a/net/sctp/ipv6.c +++ b/net/sctp/ipv6.c @@ -209,12 +209,17 @@ static int sctp_v6_xmit(struct sk_buff *skb, struct sctp_transport *transport) struct sock *sk = skb->sk; struct ipv6_pinfo *np = inet6_sk(sk); struct flowi6 *fl6 = &transport->fl.u.ip6; + __u8 tclass = np->tclass; int res; pr_debug("%s: skb:%p, len:%d, src:%pI6 dst:%pI6\n", __func__, skb, skb->len, &fl6->saddr, &fl6->daddr); - IP6_ECN_flow_xmit(sk, fl6->flowlabel); + if (transport->dscp & SCTP_DSCP_SET_MASK) + tclass = transport->dscp & SCTP_DSCP_VAL_MASK; + + if (INET_ECN_is_capable(tclass)) + IP6_ECN_flow_xmit(sk, fl6->flowlabel); if (!(transport->param_flags & SPP_PMTUD_ENABLE)) skb->ignore_df = 1; @@ -223,7 +228,7 @@ static int sctp_v6_xmit(struct sk_buff *skb, struct sctp_transport *transport) rcu_read_lock(); res = ip6_xmit(sk, skb, fl6, sk->sk_mark, rcu_dereference(np->opt), - np->tclass); + tclass); rcu_read_unlock(); return res; } @@ -254,6 +259,8 @@ static void sctp_v6_get_dst(struct sctp_transport *t, union sctp_addr *saddr, fl6->flowi6_oif = daddr->v6.sin6_scope_id; else if (asoc) fl6->flowi6_oif = asoc->base.sk->sk_bound_dev_if; + if (t->flowlabel & SCTP_FLOWLABEL_SET_MASK) + fl6->flowlabel = htonl(t->flowlabel & SCTP_FLOWLABEL_VAL_MASK); pr_debug("%s: dst=%pI6 ", __func__, &fl6->daddr); diff --git a/net/sctp/protocol.c b/net/sctp/protocol.c index 67f73d3a1356..e948db29ab53 100644 --- a/net/sctp/protocol.c +++ b/net/sctp/protocol.c @@ -426,13 +426,16 @@ 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; + if (t->dscp & SCTP_DSCP_SET_MASK) + tos = t->dscp & SCTP_DSCP_VAL_MASK; memset(fl4, 0x0, sizeof(struct flowi4)); 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(asoc->base.sk); + fl4->flowi4_tos = RT_CONN_FLAGS_TOS(asoc->base.sk, tos); fl4->flowi4_oif = asoc->base.sk->sk_bound_dev_if; fl4->fl4_sport = htons(asoc->base.bind_addr.port); } @@ -495,7 +498,7 @@ static void sctp_v4_get_dst(struct sctp_transport *t, union sctp_addr *saddr, fl4->fl4_sport = laddr->a.v4.sin_port; flowi4_update_output(fl4, asoc->base.sk->sk_bound_dev_if, - RT_CONN_FLAGS(asoc->base.sk), + RT_CONN_FLAGS_TOS(asoc->base.sk, tos), daddr->v4.sin_addr.s_addr, laddr->a.v4.sin_addr.s_addr); @@ -971,16 +974,21 @@ static inline int sctp_v4_xmit(struct sk_buff *skb, struct sctp_transport *transport) { struct inet_sock *inet = inet_sk(skb->sk); + __u8 dscp = inet->tos; pr_debug("%s: skb:%p, len:%d, src:%pI4, dst:%pI4\n", __func__, skb, - skb->len, &transport->fl.u.ip4.saddr, &transport->fl.u.ip4.daddr); + skb->len, &transport->fl.u.ip4.saddr, + &transport->fl.u.ip4.daddr); + + if (transport->dscp & SCTP_DSCP_SET_MASK) + dscp = transport->dscp & SCTP_DSCP_VAL_MASK; inet->pmtudisc = transport->param_flags & SPP_PMTUD_ENABLE ? IP_PMTUDISC_DO : IP_PMTUDISC_DONT; SCTP_INC_STATS(sock_net(&inet->sk), SCTP_MIB_OUTSCTPPACKS); - return ip_queue_xmit(&inet->sk, skb, &transport->fl); + return __ip_queue_xmit(&inet->sk, skb, &transport->fl, dscp); } static struct sctp_af sctp_af_inet; -- cgit v1.2.3 From 0b0dce7a36fb9f1a9dd8245ea82d3a268c6943fe Mon Sep 17 00:00:00 2001 From: Xin Long Date: Mon, 2 Jul 2018 18:21:13 +0800 Subject: sctp: add spp_ipv6_flowlabel and spp_dscp for sctp_paddrparams spp_ipv6_flowlabel and spp_dscp are added in sctp_paddrparams in this patch so that users could set sctp_sock/asoc/transport dscp and flowlabel with spp_flags SPP_IPV6_FLOWLABEL or SPP_DSCP by SCTP_PEER_ADDR_PARAMS , as described section 8.1.12 in RFC6458. As said in last patch, it uses '| 0x100000' or '|0x1' to mark flowlabel or dscp is set, so that their values could be set to 0. Note that to guarantee that an old app built with old kernel headers could work on the newer kernel, the param's check in sctp_g/setsockopt_peer_addr_params() is also improved, which follows the way that sctp_g/setsockopt_delayed_ack() or some other sockopts' process that accept two types of params does. Signed-off-by: Xin Long Signed-off-by: David S. Miller --- include/uapi/linux/sctp.h | 4 ++ net/sctp/socket.c | 177 ++++++++++++++++++++++++++++++++++++++++++++-- 2 files changed, 175 insertions(+), 6 deletions(-) (limited to 'net/sctp') diff --git a/include/uapi/linux/sctp.h b/include/uapi/linux/sctp.h index c02986a284db..b479db5c71d9 100644 --- a/include/uapi/linux/sctp.h +++ b/include/uapi/linux/sctp.h @@ -763,6 +763,8 @@ enum sctp_spp_flags { SPP_SACKDELAY_DISABLE = 1<<6, /*Disable SACK*/ SPP_SACKDELAY = SPP_SACKDELAY_ENABLE | SPP_SACKDELAY_DISABLE, SPP_HB_TIME_IS_ZERO = 1<<7, /* Set HB delay to 0 */ + SPP_IPV6_FLOWLABEL = 1<<8, + SPP_DSCP = 1<<9, }; struct sctp_paddrparams { @@ -773,6 +775,8 @@ struct sctp_paddrparams { __u32 spp_pathmtu; __u32 spp_sackdelay; __u32 spp_flags; + __u32 spp_ipv6_flowlabel; + __u8 spp_dscp; } __attribute__((packed, aligned(4))); /* diff --git a/net/sctp/socket.c b/net/sctp/socket.c index 0e4c8332771a..50b7ef975b42 100644 --- a/net/sctp/socket.c +++ b/net/sctp/socket.c @@ -2393,6 +2393,8 @@ static int sctp_setsockopt_autoclose(struct sock *sk, char __user *optval, * uint32_t spp_pathmtu; * uint32_t spp_sackdelay; * uint32_t spp_flags; + * uint32_t spp_ipv6_flowlabel; + * uint8_t spp_dscp; * }; * * spp_assoc_id - (one-to-many style socket) This is filled in the @@ -2472,6 +2474,45 @@ static int sctp_setsockopt_autoclose(struct sock *sk, char __user *optval, * also that this field is mutually exclusive to * SPP_SACKDELAY_ENABLE, setting both will have undefined * results. + * + * SPP_IPV6_FLOWLABEL: Setting this flag enables the + * setting of the IPV6 flow label value. The value is + * contained in the spp_ipv6_flowlabel field. + * Upon retrieval, this flag will be set to indicate that + * the spp_ipv6_flowlabel field has a valid value returned. + * If a specific destination address is set (in the + * spp_address field), then the value returned is that of + * the address. If just an association is specified (and + * no address), then the association's default flow label + * is returned. If neither an association nor a destination + * is specified, then the socket's default flow label is + * returned. For non-IPv6 sockets, this flag will be left + * cleared. + * + * SPP_DSCP: Setting this flag enables the setting of the + * Differentiated Services Code Point (DSCP) value + * associated with either the association or a specific + * address. The value is obtained in the spp_dscp field. + * Upon retrieval, this flag will be set to indicate that + * the spp_dscp field has a valid value returned. If a + * specific destination address is set when called (in the + * spp_address field), then that specific destination + * address's DSCP value is returned. If just an association + * is specified, then the association's default DSCP is + * returned. If neither an association nor a destination is + * specified, then the socket's default DSCP is returned. + * + * spp_ipv6_flowlabel + * - This field is used in conjunction with the + * SPP_IPV6_FLOWLABEL flag and contains the IPv6 flow label. + * The 20 least significant bits are used for the flow + * label. This setting has precedence over any IPv6-layer + * setting. + * + * spp_dscp - This field is used in conjunction with the SPP_DSCP flag + * and contains the DSCP. The 6 most significant bits are + * used for the DSCP. This setting has precedence over any + * IPv4- or IPv6- layer setting. */ static int sctp_apply_peer_addr_params(struct sctp_paddrparams *params, struct sctp_transport *trans, @@ -2611,6 +2652,51 @@ static int sctp_apply_peer_addr_params(struct sctp_paddrparams *params, } } + if (params->spp_flags & SPP_IPV6_FLOWLABEL) { + if (trans && trans->ipaddr.sa.sa_family == AF_INET6) { + trans->flowlabel = params->spp_ipv6_flowlabel & + SCTP_FLOWLABEL_VAL_MASK; + trans->flowlabel |= SCTP_FLOWLABEL_SET_MASK; + } else if (asoc) { + list_for_each_entry(trans, + &asoc->peer.transport_addr_list, + transports) { + if (trans->ipaddr.sa.sa_family != AF_INET6) + continue; + trans->flowlabel = params->spp_ipv6_flowlabel & + SCTP_FLOWLABEL_VAL_MASK; + trans->flowlabel |= SCTP_FLOWLABEL_SET_MASK; + } + asoc->flowlabel = params->spp_ipv6_flowlabel & + SCTP_FLOWLABEL_VAL_MASK; + asoc->flowlabel |= SCTP_FLOWLABEL_SET_MASK; + } else if (sctp_opt2sk(sp)->sk_family == AF_INET6) { + sp->flowlabel = params->spp_ipv6_flowlabel & + SCTP_FLOWLABEL_VAL_MASK; + sp->flowlabel |= SCTP_FLOWLABEL_SET_MASK; + } + } + + if (params->spp_flags & SPP_DSCP) { + if (trans) { + trans->dscp = params->spp_dscp & SCTP_DSCP_VAL_MASK; + trans->dscp |= SCTP_DSCP_SET_MASK; + } else if (asoc) { + list_for_each_entry(trans, + &asoc->peer.transport_addr_list, + transports) { + trans->dscp = params->spp_dscp & + SCTP_DSCP_VAL_MASK; + trans->dscp |= SCTP_DSCP_SET_MASK; + } + asoc->dscp = params->spp_dscp & SCTP_DSCP_VAL_MASK; + asoc->dscp |= SCTP_DSCP_SET_MASK; + } else { + sp->dscp = params->spp_dscp & SCTP_DSCP_VAL_MASK; + sp->dscp |= SCTP_DSCP_SET_MASK; + } + } + return 0; } @@ -2625,11 +2711,18 @@ static int sctp_setsockopt_peer_addr_params(struct sock *sk, int error; int hb_change, pmtud_change, sackdelay_change; - if (optlen != sizeof(struct sctp_paddrparams)) + if (optlen == sizeof(params)) { + if (copy_from_user(¶ms, optval, optlen)) + return -EFAULT; + } else if (optlen == ALIGN(offsetof(struct sctp_paddrparams, + spp_ipv6_flowlabel), 4)) { + if (copy_from_user(¶ms, optval, optlen)) + return -EFAULT; + if (params.spp_flags & (SPP_DSCP | SPP_IPV6_FLOWLABEL)) + return -EINVAL; + } else { return -EINVAL; - - if (copy_from_user(¶ms, optval, optlen)) - return -EFAULT; + } /* Validate flags and value parameters. */ hb_change = params.spp_flags & SPP_HB; @@ -5453,6 +5546,45 @@ out: * also that this field is mutually exclusive to * SPP_SACKDELAY_ENABLE, setting both will have undefined * results. + * + * SPP_IPV6_FLOWLABEL: Setting this flag enables the + * setting of the IPV6 flow label value. The value is + * contained in the spp_ipv6_flowlabel field. + * Upon retrieval, this flag will be set to indicate that + * the spp_ipv6_flowlabel field has a valid value returned. + * If a specific destination address is set (in the + * spp_address field), then the value returned is that of + * the address. If just an association is specified (and + * no address), then the association's default flow label + * is returned. If neither an association nor a destination + * is specified, then the socket's default flow label is + * returned. For non-IPv6 sockets, this flag will be left + * cleared. + * + * SPP_DSCP: Setting this flag enables the setting of the + * Differentiated Services Code Point (DSCP) value + * associated with either the association or a specific + * address. The value is obtained in the spp_dscp field. + * Upon retrieval, this flag will be set to indicate that + * the spp_dscp field has a valid value returned. If a + * specific destination address is set when called (in the + * spp_address field), then that specific destination + * address's DSCP value is returned. If just an association + * is specified, then the association's default DSCP is + * returned. If neither an association nor a destination is + * specified, then the socket's default DSCP is returned. + * + * spp_ipv6_flowlabel + * - This field is used in conjunction with the + * SPP_IPV6_FLOWLABEL flag and contains the IPv6 flow label. + * The 20 least significant bits are used for the flow + * label. This setting has precedence over any IPv6-layer + * setting. + * + * spp_dscp - This field is used in conjunction with the SPP_DSCP flag + * and contains the DSCP. The 6 most significant bits are + * used for the DSCP. This setting has precedence over any + * IPv4- or IPv6- layer setting. */ static int sctp_getsockopt_peer_addr_params(struct sock *sk, int len, char __user *optval, int __user *optlen) @@ -5462,9 +5594,15 @@ static int sctp_getsockopt_peer_addr_params(struct sock *sk, int len, struct sctp_association *asoc = NULL; struct sctp_sock *sp = sctp_sk(sk); - if (len < sizeof(struct sctp_paddrparams)) + if (len >= sizeof(params)) + len = sizeof(params); + else if (len >= ALIGN(offsetof(struct sctp_paddrparams, + spp_ipv6_flowlabel), 4)) + len = ALIGN(offsetof(struct sctp_paddrparams, + spp_ipv6_flowlabel), 4); + else return -EINVAL; - len = sizeof(struct sctp_paddrparams); + if (copy_from_user(¶ms, optval, len)) return -EFAULT; @@ -5499,6 +5637,15 @@ static int sctp_getsockopt_peer_addr_params(struct sock *sk, int len, /*draft-11 doesn't say what to return in spp_flags*/ params.spp_flags = trans->param_flags; + if (trans->flowlabel & SCTP_FLOWLABEL_SET_MASK) { + params.spp_ipv6_flowlabel = trans->flowlabel & + SCTP_FLOWLABEL_VAL_MASK; + params.spp_flags |= SPP_IPV6_FLOWLABEL; + } + if (trans->dscp & SCTP_DSCP_SET_MASK) { + params.spp_dscp = trans->dscp & SCTP_DSCP_VAL_MASK; + params.spp_flags |= SPP_DSCP; + } } else if (asoc) { /* Fetch association values. */ params.spp_hbinterval = jiffies_to_msecs(asoc->hbinterval); @@ -5508,6 +5655,15 @@ static int sctp_getsockopt_peer_addr_params(struct sock *sk, int len, /*draft-11 doesn't say what to return in spp_flags*/ params.spp_flags = asoc->param_flags; + if (asoc->flowlabel & SCTP_FLOWLABEL_SET_MASK) { + params.spp_ipv6_flowlabel = asoc->flowlabel & + SCTP_FLOWLABEL_VAL_MASK; + params.spp_flags |= SPP_IPV6_FLOWLABEL; + } + if (asoc->dscp & SCTP_DSCP_SET_MASK) { + params.spp_dscp = asoc->dscp & SCTP_DSCP_VAL_MASK; + params.spp_flags |= SPP_DSCP; + } } else { /* Fetch socket values. */ params.spp_hbinterval = sp->hbinterval; @@ -5517,6 +5673,15 @@ static int sctp_getsockopt_peer_addr_params(struct sock *sk, int len, /*draft-11 doesn't say what to return in spp_flags*/ params.spp_flags = sp->param_flags; + if (sp->flowlabel & SCTP_FLOWLABEL_SET_MASK) { + params.spp_ipv6_flowlabel = sp->flowlabel & + SCTP_FLOWLABEL_VAL_MASK; + params.spp_flags |= SPP_IPV6_FLOWLABEL; + } + if (sp->dscp & SCTP_DSCP_SET_MASK) { + params.spp_dscp = sp->dscp & SCTP_DSCP_VAL_MASK; + params.spp_flags |= SPP_DSCP; + } } if (copy_to_user(optval, ¶ms, len)) -- cgit v1.2.3 From 4be4139f7d0dc74e5a0932c7c7ddf0eb65da9e3a Mon Sep 17 00:00:00 2001 From: Xin Long Date: Mon, 2 Jul 2018 18:21:14 +0800 Subject: sctp: add support for setting flowlabel when adding a transport Struct sockaddr_in6 has the member sin6_flowinfo that includes the ipv6 flowlabel, it should also support for setting flowlabel when adding a transport whose ipaddr is from userspace. Note that addrinfo in sctp_sendmsg is using struct in6_addr for the secondary addrs, which doesn't contain sin6_flowinfo, and it needs to copy sin6_flowinfo from the primary addr. Signed-off-by: Xin Long Signed-off-by: David S. Miller --- net/sctp/associola.c | 12 ++++++++++-- net/sctp/socket.c | 5 +++++ 2 files changed, 15 insertions(+), 2 deletions(-) (limited to 'net/sctp') diff --git a/net/sctp/associola.c b/net/sctp/associola.c index 16ecfbc95614..297d9cf960b9 100644 --- a/net/sctp/associola.c +++ b/net/sctp/associola.c @@ -650,8 +650,16 @@ struct sctp_transport *sctp_assoc_add_peer(struct sctp_association *asoc, peer->sackdelay = asoc->sackdelay; peer->sackfreq = asoc->sackfreq; - if (addr->sa.sa_family == AF_INET6) - peer->flowlabel = asoc->flowlabel; + if (addr->sa.sa_family == AF_INET6) { + __be32 info = addr->v6.sin6_flowinfo; + + if (info) { + peer->flowlabel = ntohl(info & IPV6_FLOWLABEL_MASK); + peer->flowlabel |= SCTP_FLOWLABEL_SET_MASK; + } else { + peer->flowlabel = asoc->flowlabel; + } + } peer->dscp = asoc->dscp; /* Enable/disable heartbeat, SACK delay, and path MTU discovery diff --git a/net/sctp/socket.c b/net/sctp/socket.c index 50b7ef975b42..502c0d7cb105 100644 --- a/net/sctp/socket.c +++ b/net/sctp/socket.c @@ -1697,6 +1697,7 @@ static int sctp_sendmsg_new_asoc(struct sock *sk, __u16 sflags, struct sctp_association *asoc; enum sctp_scope scope; struct cmsghdr *cmsg; + __be32 flowinfo = 0; struct sctp_af *af; int err; @@ -1781,6 +1782,9 @@ static int sctp_sendmsg_new_asoc(struct sock *sk, __u16 sflags, if (!cmsgs->addrs_msg) return 0; + if (daddr->sa.sa_family == AF_INET6) + flowinfo = daddr->v6.sin6_flowinfo; + /* sendv addr list parse */ for_each_cmsghdr(cmsg, cmsgs->addrs_msg) { struct sctp_transport *transport; @@ -1813,6 +1817,7 @@ static int sctp_sendmsg_new_asoc(struct sock *sk, __u16 sflags, } dlen = sizeof(struct in6_addr); + daddr->v6.sin6_flowinfo = flowinfo; daddr->v6.sin6_family = AF_INET6; daddr->v6.sin6_port = htons(asoc->peer.port); memcpy(&daddr->v6.sin6_addr, CMSG_DATA(cmsg), dlen); -- cgit v1.2.3 From 0999f021c988770a37edfb266027db9c413901fd Mon Sep 17 00:00:00 2001 From: Xin Long Date: Mon, 2 Jul 2018 18:21:15 +0800 Subject: sctp: check for ipv6_pinfo legal sndflow with flowlabel in sctp_v6_get_dst The transport with illegal flowlabel should not be allowed to send packets. Other transport protocols already denies this. Signed-off-by: Xin Long Signed-off-by: David S. Miller --- net/sctp/ipv6.c | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'net/sctp') diff --git a/net/sctp/ipv6.c b/net/sctp/ipv6.c index 38102bf7f13e..fc6c5e4bffa5 100644 --- a/net/sctp/ipv6.c +++ b/net/sctp/ipv6.c @@ -262,6 +262,15 @@ 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)) { + struct ip6_flowlabel *flowlabel; + + flowlabel = fl6_sock_lookup(sk, fl6->flowlabel); + if (!flowlabel) + goto out; + fl6_sock_release(flowlabel); + } + pr_debug("%s: dst=%pI6 ", __func__, &fl6->daddr); if (asoc) -- cgit v1.2.3 From aa46225235efc687d971351a309b734549ca5718 Mon Sep 17 00:00:00 2001 From: Stephen Hemminger Date: Tue, 24 Jul 2018 12:29:08 -0700 Subject: sctp: whitespace fixes Remove blank line at EOF and trailing whitespace. Signed-off-by: Stephen Hemminger Signed-off-by: David S. Miller --- net/sctp/Kconfig | 4 ++-- net/sctp/sm_sideeffect.c | 1 - 2 files changed, 2 insertions(+), 3 deletions(-) (limited to 'net/sctp') diff --git a/net/sctp/Kconfig b/net/sctp/Kconfig index c740b189d4ba..950ecf6e7439 100644 --- a/net/sctp/Kconfig +++ b/net/sctp/Kconfig @@ -41,8 +41,8 @@ config SCTP_DBG_OBJCNT bool "SCTP: Debug object counts" depends on PROC_FS help - If you say Y, this will enable debugging support for counting the - type of objects that are currently allocated. This is useful for + If you say Y, this will enable debugging support for counting the + type of objects that are currently allocated. This is useful for identifying memory leaks. This debug information can be viewed by 'cat /proc/net/sctp/sctp_dbg_objcnt' diff --git a/net/sctp/sm_sideeffect.c b/net/sctp/sm_sideeffect.c index 298112ca8c06..85d393090238 100644 --- a/net/sctp/sm_sideeffect.c +++ b/net/sctp/sm_sideeffect.c @@ -1827,4 +1827,3 @@ nomem: error = -ENOMEM; goto out; } - -- cgit v1.2.3 From 05364ca03cfd419caecb292fede20eb39667eaae Mon Sep 17 00:00:00 2001 From: Konstantin Khorenko Date: Fri, 10 Aug 2018 20:11:42 +0300 Subject: net/sctp: Make wrappers for accessing in/out streams This patch introduces wrappers for accessing in/out streams indirectly. This will enable to replace physically contiguous memory arrays of streams with flexible arrays (or maybe any other appropriate mechanism) which do memory allocation on a per-page basis. Signed-off-by: Oleg Babin Signed-off-by: Konstantin Khorenko Signed-off-by: David S. Miller --- include/net/sctp/structs.h | 35 +++++++++++++++++------- net/sctp/chunk.c | 6 ++-- net/sctp/outqueue.c | 11 ++++---- net/sctp/socket.c | 4 +-- net/sctp/stream.c | 65 +++++++++++++++++++++++--------------------- net/sctp/stream_interleave.c | 20 +++++++------- net/sctp/stream_sched.c | 13 +++++---- net/sctp/stream_sched_prio.c | 22 +++++++-------- net/sctp/stream_sched_rr.c | 8 +++--- 9 files changed, 103 insertions(+), 81 deletions(-) (limited to 'net/sctp') diff --git a/include/net/sctp/structs.h b/include/net/sctp/structs.h index ab869e0d8326..6b2b8df8a1d2 100644 --- a/include/net/sctp/structs.h +++ b/include/net/sctp/structs.h @@ -398,37 +398,35 @@ void sctp_stream_update(struct sctp_stream *stream, struct sctp_stream *new); /* What is the current SSN number for this stream? */ #define sctp_ssn_peek(stream, type, sid) \ - ((stream)->type[sid].ssn) + (sctp_stream_##type((stream), (sid))->ssn) /* Return the next SSN number for this stream. */ #define sctp_ssn_next(stream, type, sid) \ - ((stream)->type[sid].ssn++) + (sctp_stream_##type((stream), (sid))->ssn++) /* Skip over this ssn and all below. */ #define sctp_ssn_skip(stream, type, sid, ssn) \ - ((stream)->type[sid].ssn = ssn + 1) + (sctp_stream_##type((stream), (sid))->ssn = ssn + 1) /* What is the current MID number for this stream? */ #define sctp_mid_peek(stream, type, sid) \ - ((stream)->type[sid].mid) + (sctp_stream_##type((stream), (sid))->mid) /* Return the next MID number for this stream. */ #define sctp_mid_next(stream, type, sid) \ - ((stream)->type[sid].mid++) + (sctp_stream_##type((stream), (sid))->mid++) /* Skip over this mid and all below. */ #define sctp_mid_skip(stream, type, sid, mid) \ - ((stream)->type[sid].mid = mid + 1) - -#define sctp_stream_in(asoc, sid) (&(asoc)->stream.in[sid]) + (sctp_stream_##type((stream), (sid))->mid = mid + 1) /* What is the current MID_uo number for this stream? */ #define sctp_mid_uo_peek(stream, type, sid) \ - ((stream)->type[sid].mid_uo) + (sctp_stream_##type((stream), (sid))->mid_uo) /* Return the next MID_uo number for this stream. */ #define sctp_mid_uo_next(stream, type, sid) \ - ((stream)->type[sid].mid_uo++) + (sctp_stream_##type((stream), (sid))->mid_uo++) /* * Pointers to address related SCTP functions. @@ -1463,6 +1461,23 @@ struct sctp_stream { struct sctp_stream_interleave *si; }; +static inline struct sctp_stream_out *sctp_stream_out( + const struct sctp_stream *stream, + __u16 sid) +{ + return ((struct sctp_stream_out *)(stream->out)) + sid; +} + +static inline struct sctp_stream_in *sctp_stream_in( + const struct sctp_stream *stream, + __u16 sid) +{ + return ((struct sctp_stream_in *)(stream->in)) + sid; +} + +#define SCTP_SO(s, i) sctp_stream_out((s), (i)) +#define SCTP_SI(s, i) sctp_stream_in((s), (i)) + #define SCTP_STREAM_CLOSED 0x00 #define SCTP_STREAM_OPEN 0x01 diff --git a/net/sctp/chunk.c b/net/sctp/chunk.c index bfb9f812e2ef..ce8087846f05 100644 --- a/net/sctp/chunk.c +++ b/net/sctp/chunk.c @@ -325,7 +325,8 @@ int sctp_chunk_abandoned(struct sctp_chunk *chunk) if (SCTP_PR_TTL_ENABLED(chunk->sinfo.sinfo_flags) && time_after(jiffies, chunk->msg->expires_at)) { struct sctp_stream_out *streamout = - &chunk->asoc->stream.out[chunk->sinfo.sinfo_stream]; + SCTP_SO(&chunk->asoc->stream, + chunk->sinfo.sinfo_stream); if (chunk->sent_count) { chunk->asoc->abandoned_sent[SCTP_PR_INDEX(TTL)]++; @@ -339,7 +340,8 @@ int sctp_chunk_abandoned(struct sctp_chunk *chunk) } else if (SCTP_PR_RTX_ENABLED(chunk->sinfo.sinfo_flags) && chunk->sent_count > chunk->sinfo.sinfo_timetolive) { struct sctp_stream_out *streamout = - &chunk->asoc->stream.out[chunk->sinfo.sinfo_stream]; + SCTP_SO(&chunk->asoc->stream, + chunk->sinfo.sinfo_stream); chunk->asoc->abandoned_sent[SCTP_PR_INDEX(RTX)]++; streamout->ext->abandoned_sent[SCTP_PR_INDEX(RTX)]++; diff --git a/net/sctp/outqueue.c b/net/sctp/outqueue.c index d68aa33485a9..d74d00b29942 100644 --- a/net/sctp/outqueue.c +++ b/net/sctp/outqueue.c @@ -80,7 +80,7 @@ static inline void sctp_outq_head_data(struct sctp_outq *q, q->out_qlen += ch->skb->len; stream = sctp_chunk_stream_no(ch); - oute = q->asoc->stream.out[stream].ext; + oute = SCTP_SO(&q->asoc->stream, stream)->ext; list_add(&ch->stream_list, &oute->outq); } @@ -101,7 +101,7 @@ static inline void sctp_outq_tail_data(struct sctp_outq *q, q->out_qlen += ch->skb->len; stream = sctp_chunk_stream_no(ch); - oute = q->asoc->stream.out[stream].ext; + oute = SCTP_SO(&q->asoc->stream, stream)->ext; list_add_tail(&ch->stream_list, &oute->outq); } @@ -372,7 +372,7 @@ static int sctp_prsctp_prune_sent(struct sctp_association *asoc, sctp_insert_list(&asoc->outqueue.abandoned, &chk->transmitted_list); - streamout = &asoc->stream.out[chk->sinfo.sinfo_stream]; + streamout = SCTP_SO(&asoc->stream, chk->sinfo.sinfo_stream); asoc->sent_cnt_removable--; asoc->abandoned_sent[SCTP_PR_INDEX(PRIO)]++; streamout->ext->abandoned_sent[SCTP_PR_INDEX(PRIO)]++; @@ -416,7 +416,7 @@ static int sctp_prsctp_prune_unsent(struct sctp_association *asoc, asoc->abandoned_unsent[SCTP_PR_INDEX(PRIO)]++; if (chk->sinfo.sinfo_stream < asoc->stream.outcnt) { struct sctp_stream_out *streamout = - &asoc->stream.out[chk->sinfo.sinfo_stream]; + SCTP_SO(&asoc->stream, chk->sinfo.sinfo_stream); streamout->ext->abandoned_unsent[SCTP_PR_INDEX(PRIO)]++; } @@ -1082,6 +1082,7 @@ static void sctp_outq_flush_data(struct sctp_flush_ctx *ctx, /* Finally, transmit new packets. */ while ((chunk = sctp_outq_dequeue_data(ctx->q)) != NULL) { __u32 sid = ntohs(chunk->subh.data_hdr->stream); + __u8 stream_state = SCTP_SO(&ctx->asoc->stream, sid)->state; /* Has this chunk expired? */ if (sctp_chunk_abandoned(chunk)) { @@ -1091,7 +1092,7 @@ static void sctp_outq_flush_data(struct sctp_flush_ctx *ctx, continue; } - if (ctx->asoc->stream.out[sid].state == SCTP_STREAM_CLOSED) { + if (stream_state == SCTP_STREAM_CLOSED) { sctp_outq_head_data(ctx->q, chunk); break; } diff --git a/net/sctp/socket.c b/net/sctp/socket.c index 502c0d7cb105..e96b15a66aba 100644 --- a/net/sctp/socket.c +++ b/net/sctp/socket.c @@ -1911,7 +1911,7 @@ static int sctp_sendmsg_to_asoc(struct sctp_association *asoc, goto err; } - if (unlikely(!asoc->stream.out[sinfo->sinfo_stream].ext)) { + if (unlikely(!SCTP_SO(&asoc->stream, sinfo->sinfo_stream)->ext)) { err = sctp_stream_init_ext(&asoc->stream, sinfo->sinfo_stream); if (err) goto err; @@ -7154,7 +7154,7 @@ static int sctp_getsockopt_pr_streamstatus(struct sock *sk, int len, if (!asoc || params.sprstat_sid >= asoc->stream.outcnt) goto out; - streamoute = asoc->stream.out[params.sprstat_sid].ext; + streamoute = SCTP_SO(&asoc->stream, params.sprstat_sid)->ext; if (!streamoute) { /* Not allocated yet, means all stats are 0 */ params.sprstat_abandoned_unsent = 0; diff --git a/net/sctp/stream.c b/net/sctp/stream.c index f1f1d1b232ba..7ca6fe4e7882 100644 --- a/net/sctp/stream.c +++ b/net/sctp/stream.c @@ -162,7 +162,7 @@ int sctp_stream_init(struct sctp_stream *stream, __u16 outcnt, __u16 incnt, stream->outcnt = outcnt; for (i = 0; i < stream->outcnt; i++) - stream->out[i].state = SCTP_STREAM_OPEN; + SCTP_SO(stream, i)->state = SCTP_STREAM_OPEN; sched->init(stream); @@ -193,7 +193,7 @@ int sctp_stream_init_ext(struct sctp_stream *stream, __u16 sid) soute = kzalloc(sizeof(*soute), GFP_KERNEL); if (!soute) return -ENOMEM; - stream->out[sid].ext = soute; + SCTP_SO(stream, sid)->ext = soute; return sctp_sched_init_sid(stream, sid, GFP_KERNEL); } @@ -205,7 +205,7 @@ void sctp_stream_free(struct sctp_stream *stream) sched->free(stream); for (i = 0; i < stream->outcnt; i++) - kfree(stream->out[i].ext); + kfree(SCTP_SO(stream, i)->ext); kfree(stream->out); kfree(stream->in); } @@ -215,12 +215,12 @@ void sctp_stream_clear(struct sctp_stream *stream) int i; for (i = 0; i < stream->outcnt; i++) { - stream->out[i].mid = 0; - stream->out[i].mid_uo = 0; + SCTP_SO(stream, i)->mid = 0; + SCTP_SO(stream, i)->mid_uo = 0; } for (i = 0; i < stream->incnt; i++) - stream->in[i].mid = 0; + SCTP_SI(stream, i)->mid = 0; } void sctp_stream_update(struct sctp_stream *stream, struct sctp_stream *new) @@ -273,8 +273,8 @@ static bool sctp_stream_outq_is_empty(struct sctp_stream *stream, for (i = 0; i < str_nums; i++) { __u16 sid = ntohs(str_list[i]); - if (stream->out[sid].ext && - !list_empty(&stream->out[sid].ext->outq)) + if (SCTP_SO(stream, sid)->ext && + !list_empty(&SCTP_SO(stream, sid)->ext->outq)) return false; } @@ -361,11 +361,11 @@ int sctp_send_reset_streams(struct sctp_association *asoc, if (out) { if (str_nums) for (i = 0; i < str_nums; i++) - stream->out[str_list[i]].state = + SCTP_SO(stream, str_list[i])->state = SCTP_STREAM_CLOSED; else for (i = 0; i < stream->outcnt; i++) - stream->out[i].state = SCTP_STREAM_CLOSED; + SCTP_SO(stream, i)->state = SCTP_STREAM_CLOSED; } asoc->strreset_chunk = chunk; @@ -380,11 +380,11 @@ int sctp_send_reset_streams(struct sctp_association *asoc, if (str_nums) for (i = 0; i < str_nums; i++) - stream->out[str_list[i]].state = + SCTP_SO(stream, str_list[i])->state = SCTP_STREAM_OPEN; else for (i = 0; i < stream->outcnt; i++) - stream->out[i].state = SCTP_STREAM_OPEN; + SCTP_SO(stream, i)->state = SCTP_STREAM_OPEN; goto out; } @@ -418,7 +418,7 @@ int sctp_send_reset_assoc(struct sctp_association *asoc) /* Block further xmit of data until this request is completed */ for (i = 0; i < stream->outcnt; i++) - stream->out[i].state = SCTP_STREAM_CLOSED; + SCTP_SO(stream, i)->state = SCTP_STREAM_CLOSED; asoc->strreset_chunk = chunk; sctp_chunk_hold(asoc->strreset_chunk); @@ -429,7 +429,7 @@ int sctp_send_reset_assoc(struct sctp_association *asoc) asoc->strreset_chunk = NULL; for (i = 0; i < stream->outcnt; i++) - stream->out[i].state = SCTP_STREAM_OPEN; + SCTP_SO(stream, i)->state = SCTP_STREAM_OPEN; return retval; } @@ -609,10 +609,10 @@ struct sctp_chunk *sctp_process_strreset_outreq( } for (i = 0; i < nums; i++) - stream->in[ntohs(str_p[i])].mid = 0; + SCTP_SI(stream, ntohs(str_p[i]))->mid = 0; } else { for (i = 0; i < stream->incnt; i++) - stream->in[i].mid = 0; + SCTP_SI(stream, i)->mid = 0; } result = SCTP_STRRESET_PERFORMED; @@ -683,11 +683,11 @@ struct sctp_chunk *sctp_process_strreset_inreq( if (nums) for (i = 0; i < nums; i++) - stream->out[ntohs(str_p[i])].state = + SCTP_SO(stream, ntohs(str_p[i]))->state = SCTP_STREAM_CLOSED; else for (i = 0; i < stream->outcnt; i++) - stream->out[i].state = SCTP_STREAM_CLOSED; + SCTP_SO(stream, i)->state = SCTP_STREAM_CLOSED; asoc->strreset_chunk = chunk; asoc->strreset_outstanding = 1; @@ -786,11 +786,11 @@ struct sctp_chunk *sctp_process_strreset_tsnreq( * incoming and outgoing streams. */ for (i = 0; i < stream->outcnt; i++) { - stream->out[i].mid = 0; - stream->out[i].mid_uo = 0; + SCTP_SO(stream, i)->mid = 0; + SCTP_SO(stream, i)->mid_uo = 0; } for (i = 0; i < stream->incnt; i++) - stream->in[i].mid = 0; + SCTP_SI(stream, i)->mid = 0; result = SCTP_STRRESET_PERFORMED; @@ -979,15 +979,18 @@ struct sctp_chunk *sctp_process_strreset_resp( sizeof(__u16); if (result == SCTP_STRRESET_PERFORMED) { + struct sctp_stream_out *sout; if (nums) { for (i = 0; i < nums; i++) { - stream->out[ntohs(str_p[i])].mid = 0; - stream->out[ntohs(str_p[i])].mid_uo = 0; + sout = SCTP_SO(stream, ntohs(str_p[i])); + sout->mid = 0; + sout->mid_uo = 0; } } else { for (i = 0; i < stream->outcnt; i++) { - stream->out[i].mid = 0; - stream->out[i].mid_uo = 0; + sout = SCTP_SO(stream, i); + sout->mid = 0; + sout->mid_uo = 0; } } @@ -995,7 +998,7 @@ struct sctp_chunk *sctp_process_strreset_resp( } for (i = 0; i < stream->outcnt; i++) - stream->out[i].state = SCTP_STREAM_OPEN; + SCTP_SO(stream, i)->state = SCTP_STREAM_OPEN; *evp = sctp_ulpevent_make_stream_reset_event(asoc, flags, nums, str_p, GFP_ATOMIC); @@ -1050,15 +1053,15 @@ struct sctp_chunk *sctp_process_strreset_resp( asoc->adv_peer_ack_point = asoc->ctsn_ack_point; for (i = 0; i < stream->outcnt; i++) { - stream->out[i].mid = 0; - stream->out[i].mid_uo = 0; + SCTP_SO(stream, i)->mid = 0; + SCTP_SO(stream, i)->mid_uo = 0; } for (i = 0; i < stream->incnt; i++) - stream->in[i].mid = 0; + SCTP_SI(stream, i)->mid = 0; } for (i = 0; i < stream->outcnt; i++) - stream->out[i].state = SCTP_STREAM_OPEN; + SCTP_SO(stream, i)->state = SCTP_STREAM_OPEN; *evp = sctp_ulpevent_make_assoc_reset_event(asoc, flags, stsn, rtsn, GFP_ATOMIC); @@ -1072,7 +1075,7 @@ struct sctp_chunk *sctp_process_strreset_resp( if (result == SCTP_STRRESET_PERFORMED) for (i = number; i < stream->outcnt; i++) - stream->out[i].state = SCTP_STREAM_OPEN; + SCTP_SO(stream, i)->state = SCTP_STREAM_OPEN; else stream->outcnt = number; diff --git a/net/sctp/stream_interleave.c b/net/sctp/stream_interleave.c index d3764c181299..0a78cdf86463 100644 --- a/net/sctp/stream_interleave.c +++ b/net/sctp/stream_interleave.c @@ -197,7 +197,7 @@ static struct sctp_ulpevent *sctp_intl_retrieve_partial( __u32 next_fsn = 0; int is_last = 0; - sin = sctp_stream_in(ulpq->asoc, event->stream); + sin = sctp_stream_in(&ulpq->asoc->stream, event->stream); skb_queue_walk(&ulpq->reasm, pos) { struct sctp_ulpevent *cevent = sctp_skb2event(pos); @@ -278,7 +278,7 @@ static struct sctp_ulpevent *sctp_intl_retrieve_reassembled( __u32 pd_len = 0; __u32 mid = 0; - sin = sctp_stream_in(ulpq->asoc, event->stream); + sin = sctp_stream_in(&ulpq->asoc->stream, event->stream); skb_queue_walk(&ulpq->reasm, pos) { struct sctp_ulpevent *cevent = sctp_skb2event(pos); @@ -368,7 +368,7 @@ static struct sctp_ulpevent *sctp_intl_reasm(struct sctp_ulpq *ulpq, sctp_intl_store_reasm(ulpq, event); - sin = sctp_stream_in(ulpq->asoc, event->stream); + sin = sctp_stream_in(&ulpq->asoc->stream, event->stream); if (sin->pd_mode && event->mid == sin->mid && event->fsn == sin->fsn) retval = sctp_intl_retrieve_partial(ulpq, event); @@ -575,7 +575,7 @@ static struct sctp_ulpevent *sctp_intl_retrieve_partial_uo( __u32 next_fsn = 0; int is_last = 0; - sin = sctp_stream_in(ulpq->asoc, event->stream); + sin = sctp_stream_in(&ulpq->asoc->stream, event->stream); skb_queue_walk(&ulpq->reasm_uo, pos) { struct sctp_ulpevent *cevent = sctp_skb2event(pos); @@ -659,7 +659,7 @@ static struct sctp_ulpevent *sctp_intl_retrieve_reassembled_uo( __u32 pd_len = 0; __u32 mid = 0; - sin = sctp_stream_in(ulpq->asoc, event->stream); + sin = sctp_stream_in(&ulpq->asoc->stream, event->stream); skb_queue_walk(&ulpq->reasm_uo, pos) { struct sctp_ulpevent *cevent = sctp_skb2event(pos); @@ -750,7 +750,7 @@ static struct sctp_ulpevent *sctp_intl_reasm_uo(struct sctp_ulpq *ulpq, sctp_intl_store_reasm_uo(ulpq, event); - sin = sctp_stream_in(ulpq->asoc, event->stream); + sin = sctp_stream_in(&ulpq->asoc->stream, event->stream); if (sin->pd_mode_uo && event->mid == sin->mid_uo && event->fsn == sin->fsn_uo) retval = sctp_intl_retrieve_partial_uo(ulpq, event); @@ -774,7 +774,7 @@ static struct sctp_ulpevent *sctp_intl_retrieve_first_uo(struct sctp_ulpq *ulpq) skb_queue_walk(&ulpq->reasm_uo, pos) { struct sctp_ulpevent *cevent = sctp_skb2event(pos); - csin = sctp_stream_in(ulpq->asoc, cevent->stream); + csin = sctp_stream_in(&ulpq->asoc->stream, cevent->stream); if (csin->pd_mode_uo) continue; @@ -875,7 +875,7 @@ static struct sctp_ulpevent *sctp_intl_retrieve_first(struct sctp_ulpq *ulpq) skb_queue_walk(&ulpq->reasm, pos) { struct sctp_ulpevent *cevent = sctp_skb2event(pos); - csin = sctp_stream_in(ulpq->asoc, cevent->stream); + csin = sctp_stream_in(&ulpq->asoc->stream, cevent->stream); if (csin->pd_mode) continue; @@ -1053,7 +1053,7 @@ static void sctp_intl_abort_pd(struct sctp_ulpq *ulpq, gfp_t gfp) __u16 sid; for (sid = 0; sid < stream->incnt; sid++) { - struct sctp_stream_in *sin = &stream->in[sid]; + struct sctp_stream_in *sin = SCTP_SI(stream, sid); __u32 mid; if (sin->pd_mode_uo) { @@ -1247,7 +1247,7 @@ static void sctp_handle_fwdtsn(struct sctp_ulpq *ulpq, struct sctp_chunk *chunk) static void sctp_intl_skip(struct sctp_ulpq *ulpq, __u16 sid, __u32 mid, __u8 flags) { - struct sctp_stream_in *sin = sctp_stream_in(ulpq->asoc, sid); + struct sctp_stream_in *sin = sctp_stream_in(&ulpq->asoc->stream, sid); struct sctp_stream *stream = &ulpq->asoc->stream; if (flags & SCTP_FTSN_U_BIT) { diff --git a/net/sctp/stream_sched.c b/net/sctp/stream_sched.c index f5fcd425232a..a6c04a94b08f 100644 --- a/net/sctp/stream_sched.c +++ b/net/sctp/stream_sched.c @@ -161,7 +161,7 @@ int sctp_sched_set_sched(struct sctp_association *asoc, /* Give the next scheduler a clean slate. */ for (i = 0; i < asoc->stream.outcnt; i++) { - void *p = asoc->stream.out[i].ext; + void *p = SCTP_SO(&asoc->stream, i)->ext; if (!p) continue; @@ -175,7 +175,7 @@ int sctp_sched_set_sched(struct sctp_association *asoc, asoc->outqueue.sched = n; n->init(&asoc->stream); for (i = 0; i < asoc->stream.outcnt; i++) { - if (!asoc->stream.out[i].ext) + if (!SCTP_SO(&asoc->stream, i)->ext) continue; ret = n->init_sid(&asoc->stream, i, GFP_KERNEL); @@ -217,7 +217,7 @@ int sctp_sched_set_value(struct sctp_association *asoc, __u16 sid, if (sid >= asoc->stream.outcnt) return -EINVAL; - if (!asoc->stream.out[sid].ext) { + if (!SCTP_SO(&asoc->stream, sid)->ext) { int ret; ret = sctp_stream_init_ext(&asoc->stream, sid); @@ -234,7 +234,7 @@ int sctp_sched_get_value(struct sctp_association *asoc, __u16 sid, if (sid >= asoc->stream.outcnt) return -EINVAL; - if (!asoc->stream.out[sid].ext) + if (!SCTP_SO(&asoc->stream, sid)->ext) return 0; return asoc->outqueue.sched->get(&asoc->stream, sid, value); @@ -252,7 +252,7 @@ void sctp_sched_dequeue_done(struct sctp_outq *q, struct sctp_chunk *ch) * priority stream comes in. */ sid = sctp_chunk_stream_no(ch); - sout = &q->asoc->stream.out[sid]; + sout = SCTP_SO(&q->asoc->stream, sid); q->asoc->stream.out_curr = sout; return; } @@ -272,8 +272,9 @@ 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); + struct sctp_stream_out_ext *ext = SCTP_SO(stream, sid)->ext; - INIT_LIST_HEAD(&stream->out[sid].ext->outq); + INIT_LIST_HEAD(&ext->outq); return sched->init_sid(stream, sid, gfp); } diff --git a/net/sctp/stream_sched_prio.c b/net/sctp/stream_sched_prio.c index 7997d35dd0fd..2245083a98f2 100644 --- a/net/sctp/stream_sched_prio.c +++ b/net/sctp/stream_sched_prio.c @@ -75,10 +75,10 @@ static struct sctp_stream_priorities *sctp_sched_prio_get_head( /* No luck. So we search on all streams now. */ for (i = 0; i < stream->outcnt; i++) { - if (!stream->out[i].ext) + if (!SCTP_SO(stream, i)->ext) continue; - p = stream->out[i].ext->prio_head; + p = SCTP_SO(stream, i)->ext->prio_head; if (!p) /* Means all other streams won't be initialized * as well. @@ -165,7 +165,7 @@ static void sctp_sched_prio_sched(struct sctp_stream *stream, static int sctp_sched_prio_set(struct sctp_stream *stream, __u16 sid, __u16 prio, gfp_t gfp) { - struct sctp_stream_out *sout = &stream->out[sid]; + struct sctp_stream_out *sout = SCTP_SO(stream, sid); struct sctp_stream_out_ext *soute = sout->ext; struct sctp_stream_priorities *prio_head, *old; bool reschedule = false; @@ -186,7 +186,7 @@ static int sctp_sched_prio_set(struct sctp_stream *stream, __u16 sid, return 0; for (i = 0; i < stream->outcnt; i++) { - soute = stream->out[i].ext; + soute = SCTP_SO(stream, i)->ext; if (soute && soute->prio_head == old) /* It's still in use, nothing else to do here. */ return 0; @@ -201,7 +201,7 @@ static int sctp_sched_prio_set(struct sctp_stream *stream, __u16 sid, static int sctp_sched_prio_get(struct sctp_stream *stream, __u16 sid, __u16 *value) { - *value = stream->out[sid].ext->prio_head->prio; + *value = SCTP_SO(stream, sid)->ext->prio_head->prio; return 0; } @@ -215,7 +215,7 @@ static int sctp_sched_prio_init(struct sctp_stream *stream) static int sctp_sched_prio_init_sid(struct sctp_stream *stream, __u16 sid, gfp_t gfp) { - INIT_LIST_HEAD(&stream->out[sid].ext->prio_list); + INIT_LIST_HEAD(&SCTP_SO(stream, sid)->ext->prio_list); return sctp_sched_prio_set(stream, sid, 0, gfp); } @@ -233,9 +233,9 @@ static void sctp_sched_prio_free(struct sctp_stream *stream) */ sctp_sched_prio_unsched_all(stream); for (i = 0; i < stream->outcnt; i++) { - if (!stream->out[i].ext) + if (!SCTP_SO(stream, i)->ext) continue; - prio = stream->out[i].ext->prio_head; + prio = SCTP_SO(stream, i)->ext->prio_head; if (prio && list_empty(&prio->prio_sched)) list_add(&prio->prio_sched, &list); } @@ -255,7 +255,7 @@ static void sctp_sched_prio_enqueue(struct sctp_outq *q, ch = list_first_entry(&msg->chunks, struct sctp_chunk, frag_list); sid = sctp_chunk_stream_no(ch); stream = &q->asoc->stream; - sctp_sched_prio_sched(stream, stream->out[sid].ext); + sctp_sched_prio_sched(stream, SCTP_SO(stream, sid)->ext); } static struct sctp_chunk *sctp_sched_prio_dequeue(struct sctp_outq *q) @@ -297,7 +297,7 @@ static void sctp_sched_prio_dequeue_done(struct sctp_outq *q, * this priority. */ sid = sctp_chunk_stream_no(ch); - soute = q->asoc->stream.out[sid].ext; + soute = SCTP_SO(&q->asoc->stream, sid)->ext; prio = soute->prio_head; sctp_sched_prio_next_stream(prio); @@ -317,7 +317,7 @@ static void sctp_sched_prio_sched_all(struct sctp_stream *stream) __u16 sid; sid = sctp_chunk_stream_no(ch); - sout = &stream->out[sid]; + sout = SCTP_SO(stream, sid); if (sout->ext) sctp_sched_prio_sched(stream, sout->ext); } diff --git a/net/sctp/stream_sched_rr.c b/net/sctp/stream_sched_rr.c index 1155692448f1..52ba743fa7a7 100644 --- a/net/sctp/stream_sched_rr.c +++ b/net/sctp/stream_sched_rr.c @@ -100,7 +100,7 @@ static int sctp_sched_rr_init(struct sctp_stream *stream) static int sctp_sched_rr_init_sid(struct sctp_stream *stream, __u16 sid, gfp_t gfp) { - INIT_LIST_HEAD(&stream->out[sid].ext->rr_list); + INIT_LIST_HEAD(&SCTP_SO(stream, sid)->ext->rr_list); return 0; } @@ -120,7 +120,7 @@ static void sctp_sched_rr_enqueue(struct sctp_outq *q, ch = list_first_entry(&msg->chunks, struct sctp_chunk, frag_list); sid = sctp_chunk_stream_no(ch); stream = &q->asoc->stream; - sctp_sched_rr_sched(stream, stream->out[sid].ext); + sctp_sched_rr_sched(stream, SCTP_SO(stream, sid)->ext); } static struct sctp_chunk *sctp_sched_rr_dequeue(struct sctp_outq *q) @@ -154,7 +154,7 @@ static void sctp_sched_rr_dequeue_done(struct sctp_outq *q, /* Last chunk on that msg, move to the next stream */ sid = sctp_chunk_stream_no(ch); - soute = q->asoc->stream.out[sid].ext; + soute = SCTP_SO(&q->asoc->stream, sid)->ext; sctp_sched_rr_next_stream(&q->asoc->stream); @@ -173,7 +173,7 @@ static void sctp_sched_rr_sched_all(struct sctp_stream *stream) __u16 sid; sid = sctp_chunk_stream_no(ch); - soute = stream->out[sid].ext; + soute = SCTP_SO(stream, sid)->ext; if (soute) sctp_sched_rr_sched(stream, soute); } -- cgit v1.2.3 From 0d493b4d0be352b5e361e4fa0bc3efe952d8b10e Mon Sep 17 00:00:00 2001 From: Konstantin Khorenko Date: Fri, 10 Aug 2018 20:11:43 +0300 Subject: net/sctp: Replace in/out stream arrays with flex_array This path replaces physically contiguous memory arrays allocated using kmalloc_array() with flexible arrays. This enables to avoid memory allocation failures on the systems under a memory stress. Signed-off-by: Oleg Babin Signed-off-by: Konstantin Khorenko Signed-off-by: David S. Miller --- include/net/sctp/structs.h | 9 ++--- net/sctp/stream.c | 88 ++++++++++++++++++++++++++++++++++------------ 2 files changed, 71 insertions(+), 26 deletions(-) (limited to 'net/sctp') diff --git a/include/net/sctp/structs.h b/include/net/sctp/structs.h index 6b2b8df8a1d2..28a7c8e44636 100644 --- a/include/net/sctp/structs.h +++ b/include/net/sctp/structs.h @@ -57,6 +57,7 @@ #include /* This gets us atomic counters. */ #include /* We need sk_buff_head. */ #include /* We need tq_struct. */ +#include /* We need flex_array. */ #include /* We need sctp* header structs. */ #include /* We need auth specific structs */ #include /* For inet_skb_parm */ @@ -1438,8 +1439,8 @@ struct sctp_stream_in { }; struct sctp_stream { - struct sctp_stream_out *out; - struct sctp_stream_in *in; + struct flex_array *out; + struct flex_array *in; __u16 outcnt; __u16 incnt; /* Current stream being sent, if any */ @@ -1465,14 +1466,14 @@ static inline struct sctp_stream_out *sctp_stream_out( const struct sctp_stream *stream, __u16 sid) { - return ((struct sctp_stream_out *)(stream->out)) + sid; + return flex_array_get(stream->out, sid); } static inline struct sctp_stream_in *sctp_stream_in( const struct sctp_stream *stream, __u16 sid) { - return ((struct sctp_stream_in *)(stream->in)) + sid; + return flex_array_get(stream->in, sid); } #define SCTP_SO(s, i) sctp_stream_out((s), (i)) diff --git a/net/sctp/stream.c b/net/sctp/stream.c index 7ca6fe4e7882..ffb940d3b57c 100644 --- a/net/sctp/stream.c +++ b/net/sctp/stream.c @@ -37,6 +37,53 @@ #include #include +static struct flex_array *fa_alloc(size_t elem_size, size_t elem_count, + gfp_t gfp) +{ + struct flex_array *result; + int err; + + result = flex_array_alloc(elem_size, elem_count, gfp); + if (result) { + err = flex_array_prealloc(result, 0, elem_count, gfp); + if (err) { + flex_array_free(result); + result = NULL; + } + } + + return result; +} + +static void fa_free(struct flex_array *fa) +{ + if (fa) + flex_array_free(fa); +} + +static void fa_copy(struct flex_array *fa, struct flex_array *from, + size_t index, size_t count) +{ + void *elem; + + while (count--) { + elem = flex_array_get(from, index); + flex_array_put(fa, index, elem, 0); + index++; + } +} + +static void fa_zero(struct flex_array *fa, size_t index, size_t count) +{ + void *elem; + + while (count--) { + elem = flex_array_get(fa, index); + memset(elem, 0, fa->element_size); + index++; + } +} + /* Migrates chunks from stream queues to new stream queues if needed, * but not across associations. Also, removes those chunks to streams * higher than the new max. @@ -78,34 +125,33 @@ static void sctp_stream_outq_migrate(struct sctp_stream *stream, * sctp_stream_update will swap ->out pointers. */ for (i = 0; i < outcnt; i++) { - kfree(new->out[i].ext); - new->out[i].ext = stream->out[i].ext; - stream->out[i].ext = NULL; + kfree(SCTP_SO(new, i)->ext); + SCTP_SO(new, i)->ext = SCTP_SO(stream, i)->ext; + SCTP_SO(stream, i)->ext = NULL; } } for (i = outcnt; i < stream->outcnt; i++) - kfree(stream->out[i].ext); + kfree(SCTP_SO(stream, i)->ext); } static int sctp_stream_alloc_out(struct sctp_stream *stream, __u16 outcnt, gfp_t gfp) { - struct sctp_stream_out *out; + struct flex_array *out; + size_t elem_size = sizeof(struct sctp_stream_out); - out = kmalloc_array(outcnt, sizeof(*out), gfp); + out = fa_alloc(elem_size, outcnt, gfp); if (!out) return -ENOMEM; if (stream->out) { - memcpy(out, stream->out, min(outcnt, stream->outcnt) * - sizeof(*out)); - kfree(stream->out); + fa_copy(out, stream->out, 0, min(outcnt, stream->outcnt)); + fa_free(stream->out); } if (outcnt > stream->outcnt) - memset(out + stream->outcnt, 0, - (outcnt - stream->outcnt) * sizeof(*out)); + fa_zero(out, stream->outcnt, (outcnt - stream->outcnt)); stream->out = out; @@ -115,22 +161,20 @@ static int sctp_stream_alloc_out(struct sctp_stream *stream, __u16 outcnt, static int sctp_stream_alloc_in(struct sctp_stream *stream, __u16 incnt, gfp_t gfp) { - struct sctp_stream_in *in; - - in = kmalloc_array(incnt, sizeof(*stream->in), gfp); + struct flex_array *in; + size_t elem_size = sizeof(struct sctp_stream_in); + in = fa_alloc(elem_size, incnt, gfp); if (!in) return -ENOMEM; if (stream->in) { - memcpy(in, stream->in, min(incnt, stream->incnt) * - sizeof(*in)); - kfree(stream->in); + fa_copy(in, stream->in, 0, min(incnt, stream->incnt)); + fa_free(stream->in); } if (incnt > stream->incnt) - memset(in + stream->incnt, 0, - (incnt - stream->incnt) * sizeof(*in)); + fa_zero(in, stream->incnt, (incnt - stream->incnt)); stream->in = in; @@ -174,7 +218,7 @@ in: ret = sctp_stream_alloc_in(stream, incnt, gfp); if (ret) { sched->free(stream); - kfree(stream->out); + fa_free(stream->out); stream->out = NULL; stream->outcnt = 0; goto out; @@ -206,8 +250,8 @@ void sctp_stream_free(struct sctp_stream *stream) sched->free(stream); for (i = 0; i < stream->outcnt; i++) kfree(SCTP_SO(stream, i)->ext); - kfree(stream->out); - kfree(stream->in); + fa_free(stream->out); + fa_free(stream->in); } void sctp_stream_clear(struct sctp_stream *stream) -- cgit v1.2.3