aboutsummaryrefslogtreecommitdiff
path: root/net/sctp
diff options
context:
space:
mode:
authorLinus Torvalds2021-06-30 15:51:09 -0700
committerLinus Torvalds2021-06-30 15:51:09 -0700
commitdbe69e43372212527abf48609aba7fc39a6daa27 (patch)
tree96cfafdf70f5325ceeac1054daf7deca339c9730 /net/sctp
parenta6eaf3850cb171c328a8b0db6d3c79286a1eba9d (diff)
parentb6df00789e2831fff7a2c65aa7164b2a4dcbe599 (diff)
Merge tag 'net-next-5.14' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next
Pull networking updates from Jakub Kicinski: "Core: - BPF: - add syscall program type and libbpf support for generating instructions and bindings for in-kernel BPF loaders (BPF loaders for BPF), this is a stepping stone for signed BPF programs - infrastructure to migrate TCP child sockets from one listener to another in the same reuseport group/map to improve flexibility of service hand-off/restart - add broadcast support to XDP redirect - allow bypass of the lockless qdisc to improving performance (for pktgen: +23% with one thread, +44% with 2 threads) - add a simpler version of "DO_ONCE()" which does not require jump labels, intended for slow-path usage - virtio/vsock: introduce SOCK_SEQPACKET support - add getsocketopt to retrieve netns cookie - ip: treat lowest address of a IPv4 subnet as ordinary unicast address allowing reclaiming of precious IPv4 addresses - ipv6: use prandom_u32() for ID generation - ip: add support for more flexible field selection for hashing across multi-path routes (w/ offload to mlxsw) - icmp: add support for extended RFC 8335 PROBE (ping) - seg6: add support for SRv6 End.DT46 behavior - mptcp: - DSS checksum support (RFC 8684) to detect middlebox meddling - support Connection-time 'C' flag - time stamping support - sctp: packetization Layer Path MTU Discovery (RFC 8899) - xfrm: speed up state addition with seq set - WiFi: - hidden AP discovery on 6 GHz and other HE 6 GHz improvements - aggregation handling improvements for some drivers - minstrel improvements for no-ack frames - deferred rate control for TXQs to improve reaction times - switch from round robin to virtual time-based airtime scheduler - add trace points: - tcp checksum errors - openvswitch - action execution, upcalls - socket errors via sk_error_report Device APIs: - devlink: add rate API for hierarchical control of max egress rate of virtual devices (VFs, SFs etc.) - don't require RCU read lock to be held around BPF hooks in NAPI context - page_pool: generic buffer recycling New hardware/drivers: - mobile: - iosm: PCIe Driver for Intel M.2 Modem - support for Qualcomm MSM8998 (ipa) - WiFi: Qualcomm QCN9074 and WCN6855 PCI devices - sparx5: Microchip SparX-5 family of Enterprise Ethernet switches - Mellanox BlueField Gigabit Ethernet (control NIC of the DPU) - NXP SJA1110 Automotive Ethernet 10-port switch - Qualcomm QCA8327 switch support (qca8k) - Mikrotik 10/25G NIC (atl1c) Driver changes: - ACPI support for some MDIO, MAC and PHY devices from Marvell and NXP (our first foray into MAC/PHY description via ACPI) - HW timestamping (PTP) support: bnxt_en, ice, sja1105, hns3, tja11xx - Mellanox/Nvidia NIC (mlx5) - NIC VF offload of L2 bridging - support IRQ distribution to Sub-functions - Marvell (prestera): - add flower and match all - devlink trap - link aggregation - Netronome (nfp): connection tracking offload - Intel 1GE (igc): add AF_XDP support - Marvell DPU (octeontx2): ingress ratelimit offload - Google vNIC (gve): new ring/descriptor format support - Qualcomm mobile (rmnet & ipa): inline checksum offload support - MediaTek WiFi (mt76) - mt7915 MSI support - mt7915 Tx status reporting - mt7915 thermal sensors support - mt7921 decapsulation offload - mt7921 enable runtime pm and deep sleep - Realtek WiFi (rtw88) - beacon filter support - Tx antenna path diversity support - firmware crash information via devcoredump - Qualcomm WiFi (wcn36xx) - Wake-on-WLAN support with magic packets and GTK rekeying - Micrel PHY (ksz886x/ksz8081): add cable test support" * tag 'net-next-5.14' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next: (2168 commits) tcp: change ICSK_CA_PRIV_SIZE definition tcp_yeah: check struct yeah size at compile time gve: DQO: Fix off by one in gve_rx_dqo() stmmac: intel: set PCI_D3hot in suspend stmmac: intel: Enable PHY WOL option in EHL net: stmmac: option to enable PHY WOL with PMT enabled net: say "local" instead of "static" addresses in ndo_dflt_fdb_{add,del} net: use netdev_info in ndo_dflt_fdb_{add,del} ptp: Set lookup cookie when creating a PTP PPS source. net: sock: add trace for socket errors net: sock: introduce sk_error_report net: dsa: replay the local bridge FDB entries pointing to the bridge dev too net: dsa: ensure during dsa_fdb_offload_notify that dev_hold and dev_put are on the same dev net: dsa: include fdb entries pointing to bridge in the host fdb list net: dsa: include bridge addresses which are local in the host fdb list net: dsa: sync static FDB entries on foreign interfaces to hardware net: dsa: install the host MDB and FDB entries in the master's RX filter net: dsa: reference count the FDB addresses at the cross-chip notifier level net: dsa: introduce a separate cross-chip notifier type for host FDBs net: dsa: reference count the MDB entries at the cross-chip notifier level ...
Diffstat (limited to 'net/sctp')
-rw-r--r--net/sctp/associola.c6
-rw-r--r--net/sctp/bind_addr.c19
-rw-r--r--net/sctp/debug.c1
-rw-r--r--net/sctp/input.c144
-rw-r--r--net/sctp/ipv6.c121
-rw-r--r--net/sctp/output.c33
-rw-r--r--net/sctp/outqueue.c13
-rw-r--r--net/sctp/protocol.c29
-rw-r--r--net/sctp/sm_make_chunk.c73
-rw-r--r--net/sctp/sm_sideeffect.c37
-rw-r--r--net/sctp/sm_statefuns.c70
-rw-r--r--net/sctp/sm_statetable.c43
-rw-r--r--net/sctp/socket.c123
-rw-r--r--net/sctp/sysctl.c35
-rw-r--r--net/sctp/transport.c150
15 files changed, 728 insertions, 169 deletions
diff --git a/net/sctp/associola.c b/net/sctp/associola.c
index 336df4b36655..be29da09cc7a 100644
--- a/net/sctp/associola.c
+++ b/net/sctp/associola.c
@@ -98,6 +98,7 @@ static struct sctp_association *sctp_association_init(
* sock configured value.
*/
asoc->hbinterval = msecs_to_jiffies(sp->hbinterval);
+ asoc->probe_interval = msecs_to_jiffies(sp->probe_interval);
asoc->encap_port = sp->encap_port;
@@ -625,6 +626,7 @@ struct sctp_transport *sctp_assoc_add_peer(struct sctp_association *asoc,
* association configured value.
*/
peer->hbinterval = asoc->hbinterval;
+ peer->probe_interval = asoc->probe_interval;
peer->encap_port = asoc->encap_port;
@@ -714,6 +716,8 @@ struct sctp_transport *sctp_assoc_add_peer(struct sctp_association *asoc,
return NULL;
}
+ sctp_transport_pl_reset(peer);
+
/* Attach the remote transport to our asoc. */
list_add_tail_rcu(&peer->transports, &asoc->peer.transport_addr_list);
asoc->peer.transport_count++;
@@ -812,6 +816,7 @@ void sctp_assoc_control_transport(struct sctp_association *asoc,
spc_state = SCTP_ADDR_CONFIRMED;
transport->state = SCTP_ACTIVE;
+ sctp_transport_pl_reset(transport);
break;
case SCTP_TRANSPORT_DOWN:
@@ -821,6 +826,7 @@ void sctp_assoc_control_transport(struct sctp_association *asoc,
*/
if (transport->state != SCTP_UNCONFIRMED) {
transport->state = SCTP_INACTIVE;
+ sctp_transport_pl_reset(transport);
spc_state = SCTP_ADDR_UNREACHABLE;
} else {
sctp_transport_dst_release(transport);
diff --git a/net/sctp/bind_addr.c b/net/sctp/bind_addr.c
index 53e5ed79f63f..59e653b528b1 100644
--- a/net/sctp/bind_addr.c
+++ b/net/sctp/bind_addr.c
@@ -270,22 +270,19 @@ int sctp_raw_to_bind_addrs(struct sctp_bind_addr *bp, __u8 *raw_addr_list,
rawaddr = (union sctp_addr_param *)raw_addr_list;
af = sctp_get_af_specific(param_type2af(param->type));
- if (unlikely(!af)) {
+ if (unlikely(!af) ||
+ !af->from_addr_param(&addr, rawaddr, htons(port), 0)) {
retval = -EINVAL;
- sctp_bind_addr_clean(bp);
- break;
+ goto out_err;
}
- af->from_addr_param(&addr, rawaddr, htons(port), 0);
if (sctp_bind_addr_state(bp, &addr) != -1)
goto next;
retval = sctp_add_bind_addr(bp, &addr, sizeof(addr),
SCTP_ADDR_SRC, gfp);
- if (retval) {
+ if (retval)
/* Can't finish building the list, clean up. */
- sctp_bind_addr_clean(bp);
- break;
- }
+ goto out_err;
next:
len = ntohs(param->length);
@@ -294,6 +291,12 @@ next:
}
return retval;
+
+out_err:
+ if (retval)
+ sctp_bind_addr_clean(bp);
+
+ return retval;
}
/********************************************************************
diff --git a/net/sctp/debug.c b/net/sctp/debug.c
index c4d9c7feffb9..ccd773e4c371 100644
--- a/net/sctp/debug.c
+++ b/net/sctp/debug.c
@@ -154,6 +154,7 @@ static const char *const sctp_timer_tbl[] = {
"TIMEOUT_T5_SHUTDOWN_GUARD",
"TIMEOUT_HEARTBEAT",
"TIMEOUT_RECONF",
+ "TIMEOUT_PROBE",
"TIMEOUT_SACK",
"TIMEOUT_AUTOCLOSE",
};
diff --git a/net/sctp/input.c b/net/sctp/input.c
index 5ceaf75105ba..eb3c2a34a31c 100644
--- a/net/sctp/input.c
+++ b/net/sctp/input.c
@@ -385,7 +385,9 @@ static int sctp_add_backlog(struct sock *sk, struct sk_buff *skb)
void sctp_icmp_frag_needed(struct sock *sk, struct sctp_association *asoc,
struct sctp_transport *t, __u32 pmtu)
{
- if (!t || (t->pathmtu <= pmtu))
+ if (!t ||
+ (t->pathmtu <= pmtu &&
+ t->pl.probe_size + sctp_transport_pl_hlen(t) <= pmtu))
return;
if (sock_owned_by_user(sk)) {
@@ -554,6 +556,50 @@ void sctp_err_finish(struct sock *sk, struct sctp_transport *t)
sctp_transport_put(t);
}
+static void sctp_v4_err_handle(struct sctp_transport *t, struct sk_buff *skb,
+ __u8 type, __u8 code, __u32 info)
+{
+ struct sctp_association *asoc = t->asoc;
+ struct sock *sk = asoc->base.sk;
+ int err = 0;
+
+ switch (type) {
+ case ICMP_PARAMETERPROB:
+ err = EPROTO;
+ break;
+ case ICMP_DEST_UNREACH:
+ if (code > NR_ICMP_UNREACH)
+ return;
+ if (code == ICMP_FRAG_NEEDED) {
+ sctp_icmp_frag_needed(sk, asoc, t, SCTP_TRUNC4(info));
+ return;
+ }
+ if (code == ICMP_PROT_UNREACH) {
+ sctp_icmp_proto_unreachable(sk, asoc, t);
+ return;
+ }
+ err = icmp_err_convert[code].errno;
+ break;
+ case ICMP_TIME_EXCEEDED:
+ if (code == ICMP_EXC_FRAGTIME)
+ return;
+
+ err = EHOSTUNREACH;
+ break;
+ case ICMP_REDIRECT:
+ sctp_icmp_redirect(sk, t, skb);
+ return;
+ default:
+ return;
+ }
+ if (!sock_owned_by_user(sk) && inet_sk(sk)->recverr) {
+ sk->sk_err = err;
+ sk_error_report(sk);
+ } else { /* Only an error on timeout */
+ sk->sk_err_soft = err;
+ }
+}
+
/*
* This routine is called by the ICMP module when it gets some
* sort of error condition. If err < 0 then the socket should
@@ -572,22 +618,19 @@ void sctp_err_finish(struct sock *sk, struct sctp_transport *t)
int sctp_v4_err(struct sk_buff *skb, __u32 info)
{
const struct iphdr *iph = (const struct iphdr *)skb->data;
- const int ihlen = iph->ihl * 4;
const int type = icmp_hdr(skb)->type;
const int code = icmp_hdr(skb)->code;
- struct sock *sk;
- struct sctp_association *asoc = NULL;
+ struct net *net = dev_net(skb->dev);
struct sctp_transport *transport;
- struct inet_sock *inet;
+ struct sctp_association *asoc;
__u16 saveip, savesctp;
- int err;
- struct net *net = dev_net(skb->dev);
+ struct sock *sk;
/* Fix up skb to look at the embedded net header. */
saveip = skb->network_header;
savesctp = skb->transport_header;
skb_reset_network_header(skb);
- skb_set_transport_header(skb, ihlen);
+ skb_set_transport_header(skb, iph->ihl * 4);
sk = sctp_err_lookup(net, AF_INET, skb, sctp_hdr(skb), &asoc, &transport);
/* Put back, the original values. */
skb->network_header = saveip;
@@ -596,59 +639,41 @@ int sctp_v4_err(struct sk_buff *skb, __u32 info)
__ICMP_INC_STATS(net, ICMP_MIB_INERRORS);
return -ENOENT;
}
- /* Warning: The sock lock is held. Remember to call
- * sctp_err_finish!
- */
- switch (type) {
- case ICMP_PARAMETERPROB:
- err = EPROTO;
- break;
- case ICMP_DEST_UNREACH:
- if (code > NR_ICMP_UNREACH)
- goto out_unlock;
+ sctp_v4_err_handle(transport, skb, type, code, info);
+ sctp_err_finish(sk, transport);
- /* PMTU discovery (RFC1191) */
- if (ICMP_FRAG_NEEDED == code) {
- sctp_icmp_frag_needed(sk, asoc, transport,
- SCTP_TRUNC4(info));
- goto out_unlock;
- } else {
- if (ICMP_PROT_UNREACH == code) {
- sctp_icmp_proto_unreachable(sk, asoc,
- transport);
- goto out_unlock;
- }
- }
- err = icmp_err_convert[code].errno;
- break;
- case ICMP_TIME_EXCEEDED:
- /* Ignore any time exceeded errors due to fragment reassembly
- * timeouts.
- */
- if (ICMP_EXC_FRAGTIME == code)
- goto out_unlock;
+ return 0;
+}
- err = EHOSTUNREACH;
- break;
- case ICMP_REDIRECT:
- sctp_icmp_redirect(sk, transport, skb);
- goto out_unlock;
- default:
- goto out_unlock;
+int sctp_udp_v4_err(struct sock *sk, struct sk_buff *skb)
+{
+ struct net *net = dev_net(skb->dev);
+ struct sctp_association *asoc;
+ struct sctp_transport *t;
+ struct icmphdr *hdr;
+ __u32 info = 0;
+
+ skb->transport_header += sizeof(struct udphdr);
+ sk = sctp_err_lookup(net, AF_INET, skb, sctp_hdr(skb), &asoc, &t);
+ if (!sk) {
+ __ICMP_INC_STATS(net, ICMP_MIB_INERRORS);
+ return -ENOENT;
}
- inet = inet_sk(sk);
- if (!sock_owned_by_user(sk) && inet->recverr) {
- sk->sk_err = err;
- sk->sk_error_report(sk);
- } else { /* Only an error on timeout */
- sk->sk_err_soft = err;
+ skb->transport_header -= sizeof(struct udphdr);
+ hdr = (struct icmphdr *)(skb_network_header(skb) - sizeof(struct icmphdr));
+ if (hdr->type == ICMP_REDIRECT) {
+ /* can't be handled without outer iphdr known, leave it to udp_err */
+ sctp_err_finish(sk, t);
+ return 0;
}
+ if (hdr->type == ICMP_DEST_UNREACH && hdr->code == ICMP_FRAG_NEEDED)
+ info = ntohs(hdr->un.frag.mtu);
+ sctp_v4_err_handle(t, skb, hdr->type, hdr->code, info);
-out_unlock:
- sctp_err_finish(sk, transport);
- return 0;
+ sctp_err_finish(sk, t);
+ return 1;
}
/*
@@ -1131,7 +1156,8 @@ static struct sctp_association *__sctp_rcv_init_lookup(struct net *net,
if (!af)
continue;
- af->from_addr_param(paddr, params.addr, sh->source, 0);
+ if (!af->from_addr_param(paddr, params.addr, sh->source, 0))
+ continue;
asoc = __sctp_lookup_association(net, laddr, paddr, transportp);
if (asoc)
@@ -1167,6 +1193,9 @@ static struct sctp_association *__sctp_rcv_asconf_lookup(
union sctp_addr_param *param;
union sctp_addr paddr;
+ if (ntohs(ch->length) < sizeof(*asconf) + sizeof(struct sctp_paramhdr))
+ return NULL;
+
/* Skip over the ADDIP header and find the Address parameter */
param = (union sctp_addr_param *)(asconf + 1);
@@ -1174,7 +1203,8 @@ static struct sctp_association *__sctp_rcv_asconf_lookup(
if (unlikely(!af))
return NULL;
- af->from_addr_param(&paddr, param, peer_port, 0);
+ if (af->from_addr_param(&paddr, param, peer_port, 0))
+ return NULL;
return __sctp_lookup_association(net, laddr, &paddr, transportp);
}
@@ -1246,7 +1276,7 @@ static struct sctp_association *__sctp_rcv_walk_lookup(struct net *net,
ch = (struct sctp_chunkhdr *)ch_end;
chunk_num++;
- } while (ch_end < skb_tail_pointer(skb));
+ } while (ch_end + sizeof(*ch) < skb_tail_pointer(skb));
return asoc;
}
diff --git a/net/sctp/ipv6.c b/net/sctp/ipv6.c
index bd08807c9e44..e48dd909dee5 100644
--- a/net/sctp/ipv6.c
+++ b/net/sctp/ipv6.c
@@ -122,54 +122,28 @@ static struct notifier_block sctp_inet6addr_notifier = {
.notifier_call = sctp_inet6addr_event,
};
-/* ICMP error handler. */
-static int sctp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
- u8 type, u8 code, int offset, __be32 info)
+static void sctp_v6_err_handle(struct sctp_transport *t, struct sk_buff *skb,
+ __u8 type, __u8 code, __u32 info)
{
- struct inet6_dev *idev;
- struct sock *sk;
- struct sctp_association *asoc;
- struct sctp_transport *transport;
+ struct sctp_association *asoc = t->asoc;
+ struct sock *sk = asoc->base.sk;
struct ipv6_pinfo *np;
- __u16 saveip, savesctp;
- int err, ret = 0;
- struct net *net = dev_net(skb->dev);
-
- idev = in6_dev_get(skb->dev);
-
- /* Fix up skb to look at the embedded net header. */
- saveip = skb->network_header;
- savesctp = skb->transport_header;
- skb_reset_network_header(skb);
- skb_set_transport_header(skb, offset);
- sk = sctp_err_lookup(net, AF_INET6, skb, sctp_hdr(skb), &asoc, &transport);
- /* Put back, the original pointers. */
- skb->network_header = saveip;
- skb->transport_header = savesctp;
- if (!sk) {
- __ICMP6_INC_STATS(net, idev, ICMP6_MIB_INERRORS);
- ret = -ENOENT;
- goto out;
- }
-
- /* Warning: The sock lock is held. Remember to call
- * sctp_err_finish!
- */
+ int err = 0;
switch (type) {
case ICMPV6_PKT_TOOBIG:
if (ip6_sk_accept_pmtu(sk))
- sctp_icmp_frag_needed(sk, asoc, transport, ntohl(info));
- goto out_unlock;
+ sctp_icmp_frag_needed(sk, asoc, t, info);
+ return;
case ICMPV6_PARAMPROB:
if (ICMPV6_UNK_NEXTHDR == code) {
- sctp_icmp_proto_unreachable(sk, asoc, transport);
- goto out_unlock;
+ sctp_icmp_proto_unreachable(sk, asoc, t);
+ return;
}
break;
case NDISC_REDIRECT:
- sctp_icmp_redirect(sk, transport, skb);
- goto out_unlock;
+ sctp_icmp_redirect(sk, t, skb);
+ return;
default:
break;
}
@@ -178,18 +152,70 @@ static int sctp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
icmpv6_err_convert(type, code, &err);
if (!sock_owned_by_user(sk) && np->recverr) {
sk->sk_err = err;
- sk->sk_error_report(sk);
- } else { /* Only an error on timeout */
+ sk_error_report(sk);
+ } else {
sk->sk_err_soft = err;
}
+}
+
+/* ICMP error handler. */
+static int sctp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
+ u8 type, u8 code, int offset, __be32 info)
+{
+ struct net *net = dev_net(skb->dev);
+ struct sctp_transport *transport;
+ struct sctp_association *asoc;
+ __u16 saveip, savesctp;
+ struct sock *sk;
+
+ /* Fix up skb to look at the embedded net header. */
+ saveip = skb->network_header;
+ savesctp = skb->transport_header;
+ skb_reset_network_header(skb);
+ skb_set_transport_header(skb, offset);
+ sk = sctp_err_lookup(net, AF_INET6, skb, sctp_hdr(skb), &asoc, &transport);
+ /* Put back, the original pointers. */
+ skb->network_header = saveip;
+ skb->transport_header = savesctp;
+ if (!sk) {
+ __ICMP6_INC_STATS(net, __in6_dev_get(skb->dev), ICMP6_MIB_INERRORS);
+ return -ENOENT;
+ }
-out_unlock:
+ sctp_v6_err_handle(transport, skb, type, code, ntohl(info));
sctp_err_finish(sk, transport);
-out:
- if (likely(idev != NULL))
- in6_dev_put(idev);
- return ret;
+ return 0;
+}
+
+int sctp_udp_v6_err(struct sock *sk, struct sk_buff *skb)
+{
+ struct net *net = dev_net(skb->dev);
+ struct sctp_association *asoc;
+ struct sctp_transport *t;
+ struct icmp6hdr *hdr;
+ __u32 info = 0;
+
+ skb->transport_header += sizeof(struct udphdr);
+ sk = sctp_err_lookup(net, AF_INET6, skb, sctp_hdr(skb), &asoc, &t);
+ if (!sk) {
+ __ICMP6_INC_STATS(net, __in6_dev_get(skb->dev), ICMP6_MIB_INERRORS);
+ return -ENOENT;
+ }
+
+ skb->transport_header -= sizeof(struct udphdr);
+ hdr = (struct icmp6hdr *)(skb_network_header(skb) - sizeof(struct icmp6hdr));
+ if (hdr->icmp6_type == NDISC_REDIRECT) {
+ /* can't be handled without outer ip6hdr known, leave it to udpv6_err */
+ sctp_err_finish(sk, t);
+ return 0;
+ }
+ if (hdr->icmp6_type == ICMPV6_PKT_TOOBIG)
+ info = ntohl(hdr->icmp6_mtu);
+ sctp_v6_err_handle(t, skb, hdr->icmp6_type, hdr->icmp6_code, info);
+
+ sctp_err_finish(sk, t);
+ return 1;
}
static int sctp_v6_xmit(struct sk_buff *skb, struct sctp_transport *t)
@@ -551,15 +577,20 @@ static void sctp_v6_to_sk_daddr(union sctp_addr *addr, struct sock *sk)
}
/* Initialize a sctp_addr from an address parameter. */
-static void sctp_v6_from_addr_param(union sctp_addr *addr,
+static bool sctp_v6_from_addr_param(union sctp_addr *addr,
union sctp_addr_param *param,
__be16 port, int iif)
{
+ if (ntohs(param->v6.param_hdr.length) < sizeof(struct sctp_ipv6addr_param))
+ return false;
+
addr->v6.sin6_family = AF_INET6;
addr->v6.sin6_port = port;
addr->v6.sin6_flowinfo = 0; /* BUG */
addr->v6.sin6_addr = param->v6.addr;
addr->v6.sin6_scope_id = iif;
+
+ return true;
}
/* Initialize an address parameter from a sctp_addr and return the length
diff --git a/net/sctp/output.c b/net/sctp/output.c
index a6aa17df09ef..9032ce60d50e 100644
--- a/net/sctp/output.c
+++ b/net/sctp/output.c
@@ -103,7 +103,8 @@ void sctp_packet_config(struct sctp_packet *packet, __u32 vtag,
sctp_transport_route(tp, NULL, sp);
if (asoc->param_flags & SPP_PMTUD_ENABLE)
sctp_assoc_sync_pmtu(asoc);
- } else if (!sctp_transport_pmtu_check(tp)) {
+ } else if (!sctp_transport_pl_enabled(tp) &&
+ !sctp_transport_pmtu_check(tp)) {
if (asoc->param_flags & SPP_PMTUD_ENABLE)
sctp_assoc_sync_pmtu(asoc);
}
@@ -211,6 +212,30 @@ enum sctp_xmit sctp_packet_transmit_chunk(struct sctp_packet *packet,
return retval;
}
+/* Try to bundle a pad chunk into a packet with a heartbeat chunk for PLPMTUTD probe */
+static enum sctp_xmit sctp_packet_bundle_pad(struct sctp_packet *pkt, struct sctp_chunk *chunk)
+{
+ struct sctp_transport *t = pkt->transport;
+ struct sctp_chunk *pad;
+ int overhead = 0;
+
+ if (!chunk->pmtu_probe)
+ return SCTP_XMIT_OK;
+
+ /* calculate the Padding Data size for the pad chunk */
+ overhead += sizeof(struct sctphdr) + sizeof(struct sctp_chunkhdr);
+ overhead += sizeof(struct sctp_sender_hb_info) + sizeof(struct sctp_pad_chunk);
+ pad = sctp_make_pad(t->asoc, t->pl.probe_size - overhead);
+ if (!pad)
+ return SCTP_XMIT_DELAY;
+
+ list_add_tail(&pad->list, &pkt->chunk_list);
+ pkt->size += SCTP_PAD4(ntohs(pad->chunk_hdr->length));
+ chunk->transport = t;
+
+ return SCTP_XMIT_OK;
+}
+
/* Try to bundle an auth chunk into the packet. */
static enum sctp_xmit sctp_packet_bundle_auth(struct sctp_packet *pkt,
struct sctp_chunk *chunk)
@@ -382,6 +407,10 @@ enum sctp_xmit sctp_packet_append_chunk(struct sctp_packet *packet,
goto finish;
retval = __sctp_packet_append_chunk(packet, chunk);
+ if (retval != SCTP_XMIT_OK)
+ goto finish;
+
+ retval = sctp_packet_bundle_pad(packet, chunk);
finish:
return retval;
@@ -553,7 +582,7 @@ int sctp_packet_transmit(struct sctp_packet *packet, gfp_t gfp)
sk = chunk->skb->sk;
/* check gso */
- if (packet->size > tp->pathmtu && !packet->ipfragok) {
+ if (packet->size > tp->pathmtu && !packet->ipfragok && !chunk->pmtu_probe) {
if (!sk_can_gso(sk)) {
pr_err_once("Trying to GSO but underlying device doesn't support it.");
goto out;
diff --git a/net/sctp/outqueue.c b/net/sctp/outqueue.c
index 5cb1aa5f067b..ff47091c385e 100644
--- a/net/sctp/outqueue.c
+++ b/net/sctp/outqueue.c
@@ -769,7 +769,11 @@ static int sctp_packet_singleton(struct sctp_transport *transport,
sctp_packet_init(&singleton, transport, sport, dport);
sctp_packet_config(&singleton, vtag, 0);
- sctp_packet_append_chunk(&singleton, chunk);
+ if (sctp_packet_append_chunk(&singleton, chunk) != SCTP_XMIT_OK) {
+ list_del_init(&chunk->list);
+ sctp_chunk_free(chunk);
+ return -ENOMEM;
+ }
return sctp_packet_transmit(&singleton, gfp);
}
@@ -929,8 +933,13 @@ static void sctp_outq_flush_ctrl(struct sctp_flush_ctx *ctx)
one_packet = 1;
fallthrough;
- case SCTP_CID_SACK:
case SCTP_CID_HEARTBEAT:
+ if (chunk->pmtu_probe) {
+ sctp_packet_singleton(ctx->transport, chunk, ctx->gfp);
+ break;
+ }
+ fallthrough;
+ case SCTP_CID_SACK:
case SCTP_CID_SHUTDOWN:
case SCTP_CID_ECN_ECNE:
case SCTP_CID_ASCONF:
diff --git a/net/sctp/protocol.c b/net/sctp/protocol.c
index 6f2bbfeec3a4..3c1fbf38f4f7 100644
--- a/net/sctp/protocol.c
+++ b/net/sctp/protocol.c
@@ -254,14 +254,19 @@ static void sctp_v4_to_sk_daddr(union sctp_addr *addr, struct sock *sk)
}
/* Initialize a sctp_addr from an address parameter. */
-static void sctp_v4_from_addr_param(union sctp_addr *addr,
+static bool sctp_v4_from_addr_param(union sctp_addr *addr,
union sctp_addr_param *param,
__be16 port, int iif)
{
+ if (ntohs(param->v4.param_hdr.length) < sizeof(struct sctp_ipv4addr_param))
+ return false;
+
addr->v4.sin_family = AF_INET;
addr->v4.sin_port = port;
addr->v4.sin_addr.s_addr = param->v4.addr.s_addr;
memset(addr->v4.sin_zero, 0, sizeof(addr->v4.sin_zero));
+
+ return true;
}
/* Initialize an address parameter from a sctp_addr and return the length
@@ -850,23 +855,6 @@ static int sctp_udp_rcv(struct sock *sk, struct sk_buff *skb)
return 0;
}
-static int sctp_udp_err_lookup(struct sock *sk, struct sk_buff *skb)
-{
- struct sctp_association *asoc;
- struct sctp_transport *t;
- int family;
-
- skb->transport_header += sizeof(struct udphdr);
- family = (ip_hdr(skb)->version == 4) ? AF_INET : AF_INET6;
- sk = sctp_err_lookup(dev_net(skb->dev), family, skb, sctp_hdr(skb),
- &asoc, &t);
- if (!sk)
- return -ENOENT;
-
- sctp_err_finish(sk, t);
- return 0;
-}
-
int sctp_udp_sock_start(struct net *net)
{
struct udp_tunnel_sock_cfg tuncfg = {NULL};
@@ -885,7 +873,7 @@ int sctp_udp_sock_start(struct net *net)
tuncfg.encap_type = 1;
tuncfg.encap_rcv = sctp_udp_rcv;
- tuncfg.encap_err_lookup = sctp_udp_err_lookup;
+ tuncfg.encap_err_lookup = sctp_udp_v4_err;
setup_udp_tunnel_sock(net, sock, &tuncfg);
net->sctp.udp4_sock = sock->sk;
@@ -907,7 +895,7 @@ int sctp_udp_sock_start(struct net *net)
tuncfg.encap_type = 1;
tuncfg.encap_rcv = sctp_udp_rcv;
- tuncfg.encap_err_lookup = sctp_udp_err_lookup;
+ tuncfg.encap_err_lookup = sctp_udp_v6_err;
setup_udp_tunnel_sock(net, sock, &tuncfg);
net->sctp.udp6_sock = sock->sk;
#endif
@@ -1171,7 +1159,6 @@ static const struct net_protocol sctp_protocol = {
.handler = sctp4_rcv,
.err_handler = sctp_v4_err,
.no_policy = 1,
- .netns_ok = 1,
.icmp_strict_tag_validation = 1,
};
diff --git a/net/sctp/sm_make_chunk.c b/net/sctp/sm_make_chunk.c
index 5b44d228b6ca..6c08e5048d38 100644
--- a/net/sctp/sm_make_chunk.c
+++ b/net/sctp/sm_make_chunk.c
@@ -1160,7 +1160,8 @@ nodata:
/* Make a HEARTBEAT chunk. */
struct sctp_chunk *sctp_make_heartbeat(const struct sctp_association *asoc,
- const struct sctp_transport *transport)
+ const struct sctp_transport *transport,
+ __u32 probe_size)
{
struct sctp_sender_hb_info hbinfo;
struct sctp_chunk *retval;
@@ -1176,6 +1177,7 @@ struct sctp_chunk *sctp_make_heartbeat(const struct sctp_association *asoc,
hbinfo.daddr = transport->ipaddr;
hbinfo.sent_at = jiffies;
hbinfo.hb_nonce = transport->hb_nonce;
+ hbinfo.probe_size = probe_size;
/* Cast away the 'const', as this is just telling the chunk
* what transport it belongs to.
@@ -1183,6 +1185,7 @@ struct sctp_chunk *sctp_make_heartbeat(const struct sctp_association *asoc,
retval->transport = (struct sctp_transport *) transport;
retval->subh.hbs_hdr = sctp_addto_chunk(retval, sizeof(hbinfo),
&hbinfo);
+ retval->pmtu_probe = !!probe_size;
nodata:
return retval;
@@ -1218,6 +1221,32 @@ nodata:
return retval;
}
+/* RFC4820 3. Padding Chunk (PAD)
+ * 0 1 2 3
+ * 0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9 0 1
+ * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
+ * | Type = 0x84 | Flags=0 | Length |
+ * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
+ * | |
+ * \ Padding Data /
+ * / \
+ * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
+ */
+struct sctp_chunk *sctp_make_pad(const struct sctp_association *asoc, int len)
+{
+ struct sctp_chunk *retval;
+
+ retval = sctp_make_control(asoc, SCTP_CID_PAD, 0, len, GFP_ATOMIC);
+ if (!retval)
+ return NULL;
+
+ skb_put_zero(retval->skb, len);
+ retval->chunk_hdr->length = htons(ntohs(retval->chunk_hdr->length) + len);
+ retval->chunk_end = skb_tail_pointer(retval->skb);
+
+ return retval;
+}
+
/* Create an Operation Error chunk with the specified space reserved.
* This routine can be used for containing multiple causes in the chunk.
*/
@@ -2166,9 +2195,16 @@ static enum sctp_ierror sctp_verify_param(struct net *net,
break;
case SCTP_PARAM_SET_PRIMARY:
- if (ep->asconf_enable)
- break;
- goto unhandled;
+ if (!ep->asconf_enable)
+ goto unhandled;
+
+ if (ntohs(param.p->length) < sizeof(struct sctp_addip_param) +
+ sizeof(struct sctp_paramhdr)) {
+ sctp_process_inv_paramlength(asoc, param.p,
+ chunk, err_chunk);
+ retval = SCTP_IERROR_ABORT;
+ }
+ break;
case SCTP_PARAM_HOST_NAME_ADDRESS:
/* Tell the peer, we won't support this param. */
@@ -2346,11 +2382,13 @@ int sctp_process_init(struct sctp_association *asoc, struct sctp_chunk *chunk,
/* Process the initialization parameters. */
sctp_walk_params(param, peer_init, init_hdr.params) {
- if (!src_match && (param.p->type == SCTP_PARAM_IPV4_ADDRESS ||
- param.p->type == SCTP_PARAM_IPV6_ADDRESS)) {
+ if (!src_match &&
+ (param.p->type == SCTP_PARAM_IPV4_ADDRESS ||
+ param.p->type == SCTP_PARAM_IPV6_ADDRESS)) {
af = sctp_get_af_specific(param_type2af(param.p->type));
- af->from_addr_param(&addr, param.addr,
- chunk->sctp_hdr->source, 0);
+ if (!af->from_addr_param(&addr, param.addr,
+ chunk->sctp_hdr->source, 0))
+ continue;
if (sctp_cmp_addr_exact(sctp_source(chunk), &addr))
src_match = 1;
}
@@ -2531,7 +2569,8 @@ static int sctp_process_param(struct sctp_association *asoc,
break;
do_addr_param:
af = sctp_get_af_specific(param_type2af(param.p->type));
- af->from_addr_param(&addr, param.addr, htons(asoc->peer.port), 0);
+ if (!af->from_addr_param(&addr, param.addr, htons(asoc->peer.port), 0))
+ break;
scope = sctp_scope(peer_addr);
if (sctp_in_scope(net, &addr, scope))
if (!sctp_assoc_add_peer(asoc, &addr, gfp, SCTP_UNCONFIRMED))
@@ -2632,15 +2671,13 @@ do_addr_param:
addr_param = param.v + sizeof(struct sctp_addip_param);
af = sctp_get_af_specific(param_type2af(addr_param->p.type));
- if (af == NULL)
+ if (!af)
break;
- af->from_addr_param(&addr, addr_param,
- htons(asoc->peer.port), 0);
+ if (!af->from_addr_param(&addr, addr_param,
+ htons(asoc->peer.port), 0))
+ break;
- /* if the address is invalid, we can't process it.
- * XXX: see spec for what to do.
- */
if (!af->addr_valid(&addr, NULL, NULL))
break;
@@ -3054,7 +3091,8 @@ static __be16 sctp_process_asconf_param(struct sctp_association *asoc,
if (unlikely(!af))
return SCTP_ERROR_DNS_FAILED;
- af->from_addr_param(&addr, addr_param, htons(asoc->peer.port), 0);
+ if (!af->from_addr_param(&addr, addr_param, htons(asoc->peer.port), 0))
+ return SCTP_ERROR_DNS_FAILED;
/* ADDIP 4.2.1 This parameter MUST NOT contain a broadcast
* or multicast address.
@@ -3331,7 +3369,8 @@ static void sctp_asconf_param_success(struct sctp_association *asoc,
/* We have checked the packet before, so we do not check again. */
af = sctp_get_af_specific(param_type2af(addr_param->p.type));
- af->from_addr_param(&addr, addr_param, htons(bp->port), 0);
+ if (!af->from_addr_param(&addr, addr_param, htons(bp->port), 0))
+ return;
switch (asconf_param->param_hdr.type) {
case SCTP_PARAM_ADD_IP:
diff --git a/net/sctp/sm_sideeffect.c b/net/sctp/sm_sideeffect.c
index ce15d590a615..b3815b568e8e 100644
--- a/net/sctp/sm_sideeffect.c
+++ b/net/sctp/sm_sideeffect.c
@@ -471,6 +471,38 @@ out_unlock:
sctp_transport_put(transport);
}
+/* 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_association *asoc = transport->asoc;
+ struct sock *sk = asoc->base.sk;
+ struct net *net = sock_net(sk);
+ int error = 0;
+
+ bh_lock_sock(sk);
+ if (sock_owned_by_user(sk)) {
+ pr_debug("%s: sock is busy\n", __func__);
+
+ /* Try again later. */
+ if (!mod_timer(&transport->probe_timer, jiffies + (HZ / 20)))
+ sctp_transport_hold(transport);
+ goto out_unlock;
+ }
+
+ error = sctp_do_sm(net, SCTP_EVENT_T_TIMEOUT,
+ SCTP_ST_TIMEOUT(SCTP_EVENT_TIMEOUT_PROBE),
+ asoc->state, asoc->ep, asoc,
+ transport, GFP_ATOMIC);
+
+ if (error)
+ sk->sk_err = -error;
+
+out_unlock:
+ bh_unlock_sock(sk);
+ sctp_transport_put(transport);
+}
+
/* Inject a SACK Timeout event into the state machine. */
static void sctp_generate_sack_event(struct timer_list *t)
{
@@ -1641,6 +1673,11 @@ static int sctp_cmd_interpreter(enum sctp_event_type event_type,
sctp_cmd_hb_timers_stop(commands, asoc);
break;
+ case SCTP_CMD_PROBE_TIMER_UPDATE:
+ t = cmd->obj.transport;
+ sctp_transport_reset_probe_timer(t);
+ break;
+
case SCTP_CMD_REPORT_ERROR:
error = cmd->obj.error;
break;
diff --git a/net/sctp/sm_statefuns.c b/net/sctp/sm_statefuns.c
index fd1e319eda00..09a8f23ec709 100644
--- a/net/sctp/sm_statefuns.c
+++ b/net/sctp/sm_statefuns.c
@@ -361,7 +361,7 @@ enum sctp_disposition sctp_sf_do_5_1B_init(struct net *net,
/* If the INIT is coming toward a closing socket, we'll send back
* and ABORT. Essentially, this catches the race of INIT being
- * backloged to the socket at the same time as the user isses close().
+ * backloged to the socket at the same time as the user issues close().
* Since the socket and all its associations are going away, we
* can treat this OOTB
*/
@@ -608,8 +608,8 @@ enum sctp_disposition sctp_sf_do_5_1C_ack(struct net *net,
sctp_add_cmd_sf(commands, SCTP_CMD_NEW_STATE,
SCTP_STATE(SCTP_STATE_COOKIE_ECHOED));
- /* SCTP-AUTH: genereate the assocition shared keys so that
- * we can potentially signe the COOKIE-ECHO.
+ /* SCTP-AUTH: generate the association shared keys so that
+ * we can potentially sign the COOKIE-ECHO.
*/
sctp_add_cmd_sf(commands, SCTP_CMD_ASSOC_SHKEY, SCTP_NULL());
@@ -787,7 +787,7 @@ enum sctp_disposition sctp_sf_do_5_1D_ce(struct net *net,
goto nomem_init;
/* SCTP-AUTH: Now that we've populate required fields in
- * sctp_process_init, set up the assocaition shared keys as
+ * sctp_process_init, set up the association shared keys as
* necessary so that we can potentially authenticate the ACK
*/
error = sctp_auth_asoc_init_active_key(new_asoc, GFP_ATOMIC);
@@ -838,7 +838,7 @@ enum sctp_disposition sctp_sf_do_5_1D_ce(struct net *net,
/* Add all the state machine commands now since we've created
* everything. This way we don't introduce memory corruptions
- * during side-effect processing and correclty count established
+ * during side-effect processing and correctly count established
* associations.
*/
sctp_add_cmd_sf(commands, SCTP_CMD_NEW_ASOC, SCTP_ASOC(new_asoc));
@@ -923,7 +923,7 @@ enum sctp_disposition sctp_sf_do_5_1E_ca(struct net *net,
commands);
/* Reset init error count upon receipt of COOKIE-ACK,
- * to avoid problems with the managemement of this
+ * to avoid problems with the management of this
* counter in stale cookie situations when a transition back
* from the COOKIE-ECHOED state to the COOKIE-WAIT
* state is performed.
@@ -1004,7 +1004,7 @@ static enum sctp_disposition sctp_sf_heartbeat(
struct sctp_chunk *reply;
/* Send a heartbeat to our peer. */
- reply = sctp_make_heartbeat(asoc, transport);
+ reply = sctp_make_heartbeat(asoc, transport, 0);
if (!reply)
return SCTP_DISPOSITION_NOMEM;
@@ -1095,6 +1095,32 @@ enum sctp_disposition sctp_sf_send_reconf(struct net *net,
return SCTP_DISPOSITION_CONSUME;
}
+/* send hb chunk with padding for PLPMUTD. */
+enum sctp_disposition sctp_sf_send_probe(struct net *net,
+ const struct sctp_endpoint *ep,
+ const struct sctp_association *asoc,
+ const union sctp_subtype type,
+ void *arg,
+ struct sctp_cmd_seq *commands)
+{
+ struct sctp_transport *transport = (struct sctp_transport *)arg;
+ struct sctp_chunk *reply;
+
+ if (!sctp_transport_pl_enabled(transport))
+ return SCTP_DISPOSITION_CONSUME;
+
+ sctp_transport_pl_send(transport);
+
+ reply = sctp_make_heartbeat(asoc, transport, transport->pl.probe_size);
+ if (!reply)
+ return SCTP_DISPOSITION_NOMEM;
+ sctp_add_cmd_sf(commands, SCTP_CMD_REPLY, SCTP_CHUNK(reply));
+ sctp_add_cmd_sf(commands, SCTP_CMD_PROBE_TIMER_UPDATE,
+ SCTP_TRANSPORT(transport));
+
+ return SCTP_DISPOSITION_CONSUME;
+}
+
/*
* Process an heartbeat request.
*
@@ -1243,6 +1269,18 @@ enum sctp_disposition sctp_sf_backbeat_8_3(struct net *net,
if (hbinfo->hb_nonce != link->hb_nonce)
return SCTP_DISPOSITION_DISCARD;
+ if (hbinfo->probe_size) {
+ if (hbinfo->probe_size != link->pl.probe_size ||
+ !sctp_transport_pl_enabled(link))
+ return SCTP_DISPOSITION_DISCARD;
+
+ sctp_transport_pl_recv(link);
+ if (link->pl.state == SCTP_PL_COMPLETE)
+ return SCTP_DISPOSITION_CONSUME;
+
+ return sctp_sf_send_probe(net, ep, asoc, type, link, commands);
+ }
+
max_interval = link->hbinterval + link->rto;
/* Check if the timestamp looks valid. */
@@ -2950,7 +2988,7 @@ enum sctp_disposition sctp_sf_do_9_2_reshutack(
commands);
/* Since we are not going to really process this INIT, there
- * is no point in verifying chunk boundries. Just generate
+ * is no point in verifying chunk boundaries. Just generate
* the SHUTDOWN ACK.
*/
reply = sctp_make_shutdown_ack(asoc, chunk);
@@ -3560,7 +3598,7 @@ enum sctp_disposition sctp_sf_do_9_2_final(struct net *net,
goto nomem_chunk;
/* Do all the commands now (after allocation), so that we
- * have consistent state if memory allocation failes
+ * have consistent state if memory allocation fails
*/
sctp_add_cmd_sf(commands, SCTP_CMD_EVENT_ULP, SCTP_ULPEVENT(ev));
@@ -3747,7 +3785,7 @@ static enum sctp_disposition sctp_sf_shut_8_4_5(
return sctp_sf_pdiscard(net, ep, asoc, type, arg, commands);
/* We need to discard the rest of the packet to prevent
- * potential bomming attacks from additional bundled chunks.
+ * potential boomming attacks from additional bundled chunks.
* This is documented in SCTP Threats ID.
*/
return sctp_sf_pdiscard(net, ep, asoc, type, arg, commands);
@@ -4257,7 +4295,7 @@ gen_shutdown:
}
/*
- * SCTP-AUTH Section 6.3 Receiving authenticated chukns
+ * SCTP-AUTH Section 6.3 Receiving authenticated chunks
*
* The receiver MUST use the HMAC algorithm indicated in the HMAC
* Identifier field. If this algorithm was not specified by the
@@ -4812,7 +4850,7 @@ static enum sctp_disposition sctp_sf_violation_ctsn(
/* Handle protocol violation of an invalid chunk bundling. For example,
* when we have an association and we receive bundled INIT-ACK, or
- * SHUDOWN-COMPLETE, our peer is clearly violationg the "MUST NOT bundle"
+ * SHUTDOWN-COMPLETE, our peer is clearly violating the "MUST NOT bundle"
* statement from the specs. Additionally, there might be an attacker
* on the path and we may not want to continue this communication.
*/
@@ -5208,7 +5246,7 @@ enum sctp_disposition sctp_sf_cookie_wait_prm_shutdown(
* Inputs
* (endpoint, asoc)
*
- * The RFC does not explcitly address this issue, but is the route through the
+ * The RFC does not explicitly address this issue, but is the route through the
* state table when someone issues a shutdown while in COOKIE_ECHOED state.
*
* Outputs
@@ -5932,7 +5970,7 @@ enum sctp_disposition sctp_sf_t1_cookie_timer_expire(
/* RFC2960 9.2 If the timer expires, the endpoint must re-send the SHUTDOWN
* with the updated last sequential TSN received from its peer.
*
- * An endpoint should limit the number of retransmissions of the
+ * An endpoint should limit the number of retransmission of the
* SHUTDOWN chunk to the protocol parameter 'Association.Max.Retrans'.
* If this threshold is exceeded the endpoint should destroy the TCB and
* MUST report the peer endpoint unreachable to the upper layer (and
@@ -6010,7 +6048,7 @@ nomem:
}
/*
- * ADDIP Section 4.1 ASCONF CHunk Procedures
+ * ADDIP Section 4.1 ASCONF Chunk Procedures
* If the T4 RTO timer expires the endpoint should do B1 to B5
*/
enum sctp_disposition sctp_sf_t4_timer_expire(
@@ -6441,7 +6479,7 @@ static int sctp_eat_data(const struct sctp_association *asoc,
chunk->ecn_ce_done = 1;
if (af->is_ce(sctp_gso_headskb(chunk->skb))) {
- /* Do real work as sideffect. */
+ /* Do real work as side effect. */
sctp_add_cmd_sf(commands, SCTP_CMD_ECN_CE,
SCTP_U32(tsn));
}
diff --git a/net/sctp/sm_statetable.c b/net/sctp/sm_statetable.c
index 88ea87f4f0e7..1816a4410b2b 100644
--- a/net/sctp/sm_statetable.c
+++ b/net/sctp/sm_statetable.c
@@ -527,6 +527,26 @@ auth_chunk_event_table[SCTP_NUM_AUTH_CHUNK_TYPES][SCTP_STATE_NUM_STATES] = {
}; /*state_fn_t auth_chunk_event_table[][] */
static const struct sctp_sm_table_entry
+pad_chunk_event_table[SCTP_STATE_NUM_STATES] = {
+ /* SCTP_STATE_CLOSED */
+ TYPE_SCTP_FUNC(sctp_sf_discard_chunk),
+ /* SCTP_STATE_COOKIE_WAIT */
+ TYPE_SCTP_FUNC(sctp_sf_discard_chunk),
+ /* SCTP_STATE_COOKIE_ECHOED */
+ TYPE_SCTP_FUNC(sctp_sf_discard_chunk),
+ /* SCTP_STATE_ESTABLISHED */
+ TYPE_SCTP_FUNC(sctp_sf_discard_chunk),
+ /* SCTP_STATE_SHUTDOWN_PENDING */
+ TYPE_SCTP_FUNC(sctp_sf_discard_chunk),
+ /* SCTP_STATE_SHUTDOWN_SENT */
+ TYPE_SCTP_FUNC(sctp_sf_discard_chunk),
+ /* SCTP_STATE_SHUTDOWN_RECEIVED */
+ TYPE_SCTP_FUNC(sctp_sf_discard_chunk),
+ /* SCTP_STATE_SHUTDOWN_ACK_SENT */
+ TYPE_SCTP_FUNC(sctp_sf_discard_chunk),
+}; /* chunk pad */
+
+static const struct sctp_sm_table_entry
chunk_event_table_unknown[SCTP_STATE_NUM_STATES] = {
/* SCTP_STATE_CLOSED */
TYPE_SCTP_FUNC(sctp_sf_ootb),
@@ -947,6 +967,25 @@ other_event_table[SCTP_NUM_OTHER_TYPES][SCTP_STATE_NUM_STATES] = {
TYPE_SCTP_FUNC(sctp_sf_timer_ignore), \
}
+#define TYPE_SCTP_EVENT_TIMEOUT_PROBE { \
+ /* SCTP_STATE_CLOSED */ \
+ TYPE_SCTP_FUNC(sctp_sf_timer_ignore), \
+ /* SCTP_STATE_COOKIE_WAIT */ \
+ TYPE_SCTP_FUNC(sctp_sf_timer_ignore), \
+ /* SCTP_STATE_COOKIE_ECHOED */ \
+ TYPE_SCTP_FUNC(sctp_sf_timer_ignore), \
+ /* SCTP_STATE_ESTABLISHED */ \
+ TYPE_SCTP_FUNC(sctp_sf_send_probe), \
+ /* SCTP_STATE_SHUTDOWN_PENDING */ \
+ TYPE_SCTP_FUNC(sctp_sf_timer_ignore), \
+ /* SCTP_STATE_SHUTDOWN_SENT */ \
+ TYPE_SCTP_FUNC(sctp_sf_timer_ignore), \
+ /* SCTP_STATE_SHUTDOWN_RECEIVED */ \
+ TYPE_SCTP_FUNC(sctp_sf_timer_ignore), \
+ /* SCTP_STATE_SHUTDOWN_ACK_SENT */ \
+ TYPE_SCTP_FUNC(sctp_sf_timer_ignore), \
+}
+
static const struct sctp_sm_table_entry
timeout_event_table[SCTP_NUM_TIMEOUT_TYPES][SCTP_STATE_NUM_STATES] = {
TYPE_SCTP_EVENT_TIMEOUT_NONE,
@@ -958,6 +997,7 @@ timeout_event_table[SCTP_NUM_TIMEOUT_TYPES][SCTP_STATE_NUM_STATES] = {
TYPE_SCTP_EVENT_TIMEOUT_T5_SHUTDOWN_GUARD,
TYPE_SCTP_EVENT_TIMEOUT_HEARTBEAT,
TYPE_SCTP_EVENT_TIMEOUT_RECONF,
+ TYPE_SCTP_EVENT_TIMEOUT_PROBE,
TYPE_SCTP_EVENT_TIMEOUT_SACK,
TYPE_SCTP_EVENT_TIMEOUT_AUTOCLOSE,
};
@@ -992,6 +1032,9 @@ static const struct sctp_sm_table_entry *sctp_chunk_event_lookup(
case SCTP_CID_AUTH:
return &auth_chunk_event_table[0][state];
+
+ case SCTP_CID_PAD:
+ return &pad_chunk_event_table[state];
}
return &chunk_event_table_unknown[state];
diff --git a/net/sctp/socket.c b/net/sctp/socket.c
index a79d193ff872..e64e01f61b11 100644
--- a/net/sctp/socket.c
+++ b/net/sctp/socket.c
@@ -2496,6 +2496,7 @@ static int sctp_apply_peer_addr_params(struct sctp_paddrparams *params,
sctp_transport_pmtu(trans, sctp_opt2sk(sp));
sctp_assoc_sync_pmtu(asoc);
}
+ sctp_transport_pl_reset(trans);
} else if (asoc) {
asoc->param_flags =
(asoc->param_flags & ~SPP_PMTUD) | pmtud_change;
@@ -4481,6 +4482,61 @@ static int sctp_setsockopt_encap_port(struct sock *sk,
return 0;
}
+static int sctp_setsockopt_probe_interval(struct sock *sk,
+ struct sctp_probeinterval *params,
+ unsigned int optlen)
+{
+ struct sctp_association *asoc;
+ struct sctp_transport *t;
+ __u32 probe_interval;
+
+ if (optlen != sizeof(*params))
+ return -EINVAL;
+
+ probe_interval = params->spi_interval;
+ if (probe_interval && probe_interval < SCTP_PROBE_TIMER_MIN)
+ return -EINVAL;
+
+ /* If an address other than INADDR_ANY is specified, and
+ * no transport is found, then the request is invalid.
+ */
+ if (!sctp_is_any(sk, (union sctp_addr *)&params->spi_address)) {
+ t = sctp_addr_id2transport(sk, &params->spi_address,
+ params->spi_assoc_id);
+ if (!t)
+ return -EINVAL;
+
+ t->probe_interval = msecs_to_jiffies(probe_interval);
+ sctp_transport_pl_reset(t);
+ return 0;
+ }
+
+ /* Get association, if assoc_id != SCTP_FUTURE_ASSOC and the
+ * socket is a one to many style socket, and an association
+ * was not found, then the id was invalid.
+ */
+ asoc = sctp_id2assoc(sk, params->spi_assoc_id);
+ if (!asoc && params->spi_assoc_id != SCTP_FUTURE_ASSOC &&
+ sctp_style(sk, UDP))
+ return -EINVAL;
+
+ /* If changes are for association, also apply probe_interval to
+ * each transport.
+ */
+ if (asoc) {
+ list_for_each_entry(t, &asoc->peer.transport_addr_list, transports) {
+ t->probe_interval = msecs_to_jiffies(probe_interval);
+ sctp_transport_pl_reset(t);
+ }
+
+ asoc->probe_interval = msecs_to_jiffies(probe_interval);
+ return 0;
+ }
+
+ sctp_sk(sk)->probe_interval = probe_interval;
+ return 0;
+}
+
/* API 6.2 setsockopt(), getsockopt()
*
* Applications use setsockopt() and getsockopt() to set or retrieve
@@ -4703,6 +4759,9 @@ static int sctp_setsockopt(struct sock *sk, int level, int optname,
case SCTP_REMOTE_UDP_ENCAPS_PORT:
retval = sctp_setsockopt_encap_port(sk, kopt, optlen);
break;
+ case SCTP_PLPMTUD_PROBE_INTERVAL:
+ retval = sctp_setsockopt_probe_interval(sk, kopt, optlen);
+ break;
default:
retval = -ENOPROTOOPT;
break;
@@ -4989,6 +5048,7 @@ static int sctp_init_sock(struct sock *sk)
atomic_set(&sp->pd_mode, 0);
skb_queue_head_init(&sp->pd_lobby);
sp->frag_interleave = 0;
+ sp->probe_interval = net->sctp.probe_interval;
/* Create a per socket endpoint structure. Even if we
* change the data structure relationships, this may still
@@ -7905,6 +7965,66 @@ out:
return 0;
}
+static int sctp_getsockopt_probe_interval(struct sock *sk, int len,
+ char __user *optval,
+ int __user *optlen)
+{
+ struct sctp_probeinterval params;
+ struct sctp_association *asoc;
+ struct sctp_transport *t;
+ __u32 probe_interval;
+
+ if (len < sizeof(params))
+ return -EINVAL;
+
+ len = sizeof(params);
+ if (copy_from_user(&params, optval, len))
+ return -EFAULT;
+
+ /* If an address other than INADDR_ANY is specified, and
+ * no transport is found, then the request is invalid.
+ */
+ if (!sctp_is_any(sk, (union sctp_addr *)&params.spi_address)) {
+ t = sctp_addr_id2transport(sk, &params.spi_address,
+ params.spi_assoc_id);
+ if (!t) {
+ pr_debug("%s: failed no transport\n", __func__);
+ return -EINVAL;
+ }
+
+ probe_interval = jiffies_to_msecs(t->probe_interval);
+ goto out;
+ }
+
+ /* Get association, if assoc_id != SCTP_FUTURE_ASSOC and the
+ * socket is a one to many style socket, and an association
+ * was not found, then the id was invalid.
+ */
+ asoc = sctp_id2assoc(sk, params.spi_assoc_id);
+ if (!asoc && params.spi_assoc_id != SCTP_FUTURE_ASSOC &&
+ sctp_style(sk, UDP)) {
+ pr_debug("%s: failed no association\n", __func__);
+ return -EINVAL;
+ }
+
+ if (asoc) {
+ probe_interval = jiffies_to_msecs(asoc->probe_interval);
+ goto out;
+ }
+
+ probe_interval = sctp_sk(sk)->probe_interval;
+
+out:
+ params.spi_interval = probe_interval;
+ if (copy_to_user(optval, &params, len))
+ return -EFAULT;
+
+ if (put_user(len, optlen))
+ return -EFAULT;
+
+ return 0;
+}
+
static int sctp_getsockopt(struct sock *sk, int level, int optname,
char __user *optval, int __user *optlen)
{
@@ -8128,6 +8248,9 @@ static int sctp_getsockopt(struct sock *sk, int level, int optname,
case SCTP_REMOTE_UDP_ENCAPS_PORT:
retval = sctp_getsockopt_encap_port(sk, len, optval, optlen);
break;
+ case SCTP_PLPMTUD_PROBE_INTERVAL:
+ retval = sctp_getsockopt_probe_interval(sk, len, optval, optlen);
+ break;
default:
retval = -ENOPROTOOPT;
break;
diff --git a/net/sctp/sysctl.c b/net/sctp/sysctl.c
index 55871b277f47..b46a416787ec 100644
--- a/net/sctp/sysctl.c
+++ b/net/sctp/sysctl.c
@@ -55,6 +55,8 @@ static int proc_sctp_do_alpha_beta(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,
void *buffer, size_t *lenp, loff_t *ppos);
+static int proc_sctp_do_probe_interval(struct ctl_table *ctl, int write,
+ void *buffer, size_t *lenp, loff_t *ppos);
static struct ctl_table sctp_table[] = {
{
@@ -294,6 +296,13 @@ static struct ctl_table sctp_net_table[] = {
.proc_handler = proc_dointvec,
},
{
+ .procname = "plpmtud_probe_interval",
+ .data = &init_net.sctp.probe_interval,
+ .maxlen = sizeof(int),
+ .mode = 0644,
+ .proc_handler = proc_sctp_do_probe_interval,
+ },
+ {
.procname = "udp_port",
.data = &init_net.sctp.udp_port,
.maxlen = sizeof(int),
@@ -539,6 +548,32 @@ static int proc_sctp_do_udp_port(struct ctl_table *ctl, int write,
return ret;
}
+static int proc_sctp_do_probe_interval(struct ctl_table *ctl, int write,
+ void *buffer, size_t *lenp, loff_t *ppos)
+{
+ struct net *net = current->nsproxy->net_ns;
+ struct ctl_table tbl;
+ int ret, new_value;
+
+ memset(&tbl, 0, sizeof(struct ctl_table));
+ tbl.maxlen = sizeof(unsigned int);
+
+ if (write)
+ tbl.data = &new_value;
+ else
+ tbl.data = &net->sctp.probe_interval;
+
+ ret = proc_dointvec(&tbl, write, buffer, lenp, ppos);
+ if (write && ret == 0) {
+ if (new_value && new_value < SCTP_PROBE_TIMER_MIN)
+ return -EINVAL;
+
+ net->sctp.probe_interval = new_value;
+ }
+
+ return ret;
+}
+
int sctp_sysctl_net_register(struct net *net)
{
struct ctl_table *table;
diff --git a/net/sctp/transport.c b/net/sctp/transport.c
index bf0ac467e757..5f23804f21c7 100644
--- a/net/sctp/transport.c
+++ b/net/sctp/transport.c
@@ -75,6 +75,7 @@ static struct sctp_transport *sctp_transport_init(struct net *net,
timer_setup(&peer->T3_rtx_timer, sctp_generate_t3_rtx_event, 0);
timer_setup(&peer->hb_timer, sctp_generate_heartbeat_event, 0);
timer_setup(&peer->reconf_timer, sctp_generate_reconf_event, 0);
+ timer_setup(&peer->probe_timer, sctp_generate_probe_event, 0);
timer_setup(&peer->proto_unreach_timer,
sctp_generate_proto_unreach_event, 0);
@@ -131,6 +132,9 @@ void sctp_transport_free(struct sctp_transport *transport)
if (del_timer(&transport->reconf_timer))
sctp_transport_put(transport);
+ if (del_timer(&transport->probe_timer))
+ sctp_transport_put(transport);
+
/* Delete the ICMP proto unreachable timer if it's active. */
if (del_timer(&transport->proto_unreach_timer))
sctp_transport_put(transport);
@@ -207,6 +211,15 @@ void sctp_transport_reset_reconf_timer(struct sctp_transport *transport)
sctp_transport_hold(transport);
}
+void sctp_transport_reset_probe_timer(struct sctp_transport *transport)
+{
+ if (timer_pending(&transport->probe_timer))
+ return;
+ if (!mod_timer(&transport->probe_timer,
+ jiffies + transport->probe_interval))
+ sctp_transport_hold(transport);
+}
+
/* This transport has been assigned to an association.
* Initialize fields from the association or from the sock itself.
* Register the reference count in the association.
@@ -241,12 +254,143 @@ void sctp_transport_pmtu(struct sctp_transport *transport, struct sock *sk)
transport->pathmtu = sctp_dst_mtu(transport->dst);
else
transport->pathmtu = SCTP_DEFAULT_MAXSEGMENT;
+
+ sctp_transport_pl_update(transport);
+}
+
+void sctp_transport_pl_send(struct sctp_transport *t)
+{
+ pr_debug("%s: PLPMTUD: transport: %p, state: %d, pmtu: %d, size: %d, high: %d\n",
+ __func__, t, t->pl.state, t->pl.pmtu, t->pl.probe_size, t->pl.probe_high);
+
+ if (t->pl.probe_count < SCTP_MAX_PROBES) {
+ t->pl.probe_count++;
+ return;
+ }
+
+ if (t->pl.state == SCTP_PL_BASE) {
+ if (t->pl.probe_size == SCTP_BASE_PLPMTU) { /* BASE_PLPMTU Confirmation Failed */
+ t->pl.state = SCTP_PL_ERROR; /* Base -> Error */
+
+ t->pl.pmtu = SCTP_MIN_PLPMTU;
+ t->pathmtu = t->pl.pmtu + sctp_transport_pl_hlen(t);
+ sctp_assoc_sync_pmtu(t->asoc);
+ }
+ } else if (t->pl.state == SCTP_PL_SEARCH) {
+ if (t->pl.pmtu == t->pl.probe_size) { /* Black Hole Detected */
+ t->pl.state = SCTP_PL_BASE; /* Search -> Base */
+ t->pl.probe_size = SCTP_BASE_PLPMTU;
+ t->pl.probe_high = 0;
+
+ t->pl.pmtu = SCTP_BASE_PLPMTU;
+ t->pathmtu = t->pl.pmtu + sctp_transport_pl_hlen(t);
+ sctp_assoc_sync_pmtu(t->asoc);
+ } else { /* Normal probe failure. */
+ t->pl.probe_high = t->pl.probe_size;
+ t->pl.probe_size = t->pl.pmtu;
+ }
+ } else if (t->pl.state == SCTP_PL_COMPLETE) {
+ if (t->pl.pmtu == t->pl.probe_size) { /* Black Hole Detected */
+ t->pl.state = SCTP_PL_BASE; /* Search Complete -> Base */
+ t->pl.probe_size = SCTP_BASE_PLPMTU;
+
+ t->pl.pmtu = SCTP_BASE_PLPMTU;
+ t->pathmtu = t->pl.pmtu + sctp_transport_pl_hlen(t);
+ sctp_assoc_sync_pmtu(t->asoc);
+ }
+ }
+ t->pl.probe_count = 1;
+}
+
+void sctp_transport_pl_recv(struct sctp_transport *t)
+{
+ pr_debug("%s: PLPMTUD: transport: %p, state: %d, pmtu: %d, size: %d, high: %d\n",
+ __func__, t, t->pl.state, t->pl.pmtu, t->pl.probe_size, t->pl.probe_high);
+
+ t->pl.pmtu = t->pl.probe_size;
+ t->pl.probe_count = 0;
+ if (t->pl.state == SCTP_PL_BASE) {
+ t->pl.state = SCTP_PL_SEARCH; /* Base -> Search */
+ t->pl.probe_size += SCTP_PL_BIG_STEP;
+ } else if (t->pl.state == SCTP_PL_ERROR) {
+ t->pl.state = SCTP_PL_SEARCH; /* Error -> Search */
+
+ t->pl.pmtu = t->pl.probe_size;
+ t->pathmtu = t->pl.pmtu + sctp_transport_pl_hlen(t);
+ sctp_assoc_sync_pmtu(t->asoc);
+ 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;
+ }
+ t->pl.probe_size += SCTP_PL_MIN_STEP;
+ if (t->pl.probe_size >= t->pl.probe_high) {
+ t->pl.probe_high = 0;
+ t->pl.raise_count = 0;
+ t->pl.state = SCTP_PL_COMPLETE; /* Search -> Search Complete */
+
+ t->pl.probe_size = t->pl.pmtu;
+ t->pathmtu = t->pl.pmtu + sctp_transport_pl_hlen(t);
+ sctp_assoc_sync_pmtu(t->asoc);
+ }
+ } else if (t->pl.state == SCTP_PL_COMPLETE && ++t->pl.raise_count == 30) {
+ /* 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;
+ }
+}
+
+static bool sctp_transport_pl_toobig(struct sctp_transport *t, u32 pmtu)
+{
+ pr_debug("%s: PLPMTUD: transport: %p, state: %d, pmtu: %d, size: %d, ptb: %d\n",
+ __func__, t, t->pl.state, t->pl.pmtu, t->pl.probe_size, pmtu);
+
+ if (pmtu < SCTP_MIN_PLPMTU || pmtu >= t->pl.probe_size)
+ return false;
+
+ if (t->pl.state == SCTP_PL_BASE) {
+ if (pmtu >= SCTP_MIN_PLPMTU && pmtu < SCTP_BASE_PLPMTU) {
+ t->pl.state = SCTP_PL_ERROR; /* Base -> Error */
+
+ t->pl.pmtu = SCTP_MIN_PLPMTU;
+ t->pathmtu = t->pl.pmtu + sctp_transport_pl_hlen(t);
+ }
+ } else if (t->pl.state == SCTP_PL_SEARCH) {
+ if (pmtu >= SCTP_BASE_PLPMTU && pmtu < t->pl.pmtu) {
+ t->pl.state = SCTP_PL_BASE; /* Search -> Base */
+ t->pl.probe_size = SCTP_BASE_PLPMTU;
+ t->pl.probe_count = 0;
+
+ t->pl.probe_high = 0;
+ t->pl.pmtu = SCTP_BASE_PLPMTU;
+ t->pathmtu = t->pl.pmtu + sctp_transport_pl_hlen(t);
+ } else if (pmtu > t->pl.pmtu && pmtu < t->pl.probe_size) {
+ t->pl.probe_size = pmtu;
+ t->pl.probe_count = 0;
+
+ return false;
+ }
+ } else if (t->pl.state == SCTP_PL_COMPLETE) {
+ if (pmtu >= SCTP_BASE_PLPMTU && pmtu < t->pl.pmtu) {
+ t->pl.state = SCTP_PL_BASE; /* Complete -> Base */
+ t->pl.probe_size = SCTP_BASE_PLPMTU;
+ t->pl.probe_count = 0;
+
+ t->pl.probe_high = 0;
+ t->pl.pmtu = SCTP_BASE_PLPMTU;
+ t->pathmtu = t->pl.pmtu + sctp_transport_pl_hlen(t);
+ }
+ }
+
+ return true;
}
bool sctp_transport_update_pmtu(struct sctp_transport *t, u32 pmtu)
{
- struct dst_entry *dst = sctp_transport_dst_check(t);
struct sock *sk = t->asoc->base.sk;
+ struct dst_entry *dst;
bool change = true;
if (unlikely(pmtu < SCTP_DEFAULT_MINSEGMENT)) {
@@ -257,6 +401,10 @@ bool sctp_transport_update_pmtu(struct sctp_transport *t, u32 pmtu)
}
pmtu = SCTP_TRUNC4(pmtu);
+ if (sctp_transport_pl_enabled(t))
+ return sctp_transport_pl_toobig(t, pmtu - sctp_transport_pl_hlen(t));
+
+ dst = sctp_transport_dst_check(t);
if (dst) {
struct sctp_pf *pf = sctp_get_pf_specific(dst->ops->family);
union sctp_addr addr;