summaryrefslogtreecommitdiffstats
path: root/net/sctp
diff options
context:
space:
mode:
Diffstat (limited to 'net/sctp')
-rw-r--r--net/sctp/associola.c43
-rw-r--r--net/sctp/debug.c5
-rw-r--r--net/sctp/input.c51
-rw-r--r--net/sctp/inqueue.c8
-rw-r--r--net/sctp/ipv6.c85
-rw-r--r--net/sctp/output.c2
-rw-r--r--net/sctp/outqueue.c12
-rw-r--r--net/sctp/protocol.c101
-rw-r--r--net/sctp/sm_make_chunk.c27
-rw-r--r--net/sctp/sm_sideeffect.c51
-rw-r--r--net/sctp/sm_statefuns.c57
-rw-r--r--net/sctp/sm_statetable.c2
-rw-r--r--net/sctp/socket.c457
-rw-r--r--net/sctp/transport.c2
-rw-r--r--net/sctp/ulpevent.c49
-rw-r--r--net/sctp/ulpqueue.c166
16 files changed, 824 insertions, 294 deletions
diff --git a/net/sctp/associola.c b/net/sctp/associola.c
index 78d2ddb5ca1..df94e3cdfba 100644
--- a/net/sctp/associola.c
+++ b/net/sctp/associola.c
@@ -143,7 +143,7 @@ static struct sctp_association *sctp_association_init(struct sctp_association *a
/* Initialize the maximum mumber of new data packets that can be sent
* in a burst.
*/
- asoc->max_burst = sctp_max_burst;
+ asoc->max_burst = sp->max_burst;
/* initialize association timers */
asoc->timeouts[SCTP_EVENT_TIMEOUT_NONE] = 0;
@@ -714,8 +714,16 @@ void sctp_assoc_control_transport(struct sctp_association *asoc,
/* Record the transition on the transport. */
switch (command) {
case SCTP_TRANSPORT_UP:
+ /* If we are moving from UNCONFIRMED state due
+ * to heartbeat success, report the SCTP_ADDR_CONFIRMED
+ * state to the user, otherwise report SCTP_ADDR_AVAILABLE.
+ */
+ if (SCTP_UNCONFIRMED == transport->state &&
+ SCTP_HEARTBEAT_SUCCESS == error)
+ spc_state = SCTP_ADDR_CONFIRMED;
+ else
+ spc_state = SCTP_ADDR_AVAILABLE;
transport->state = SCTP_ACTIVE;
- spc_state = SCTP_ADDR_AVAILABLE;
break;
case SCTP_TRANSPORT_DOWN:
@@ -725,7 +733,7 @@ void sctp_assoc_control_transport(struct sctp_association *asoc,
default:
return;
- };
+ }
/* Generate and send a SCTP_PEER_ADDR_CHANGE notification to the
* user.
@@ -1095,6 +1103,13 @@ void sctp_assoc_update(struct sctp_association *asoc,
asoc->ssnmap = new->ssnmap;
new->ssnmap = NULL;
}
+
+ if (!asoc->assoc_id) {
+ /* get a new association id since we don't have one
+ * yet.
+ */
+ sctp_assoc_set_id(asoc, GFP_ATOMIC);
+ }
}
}
@@ -1367,3 +1382,25 @@ out:
sctp_read_unlock(&asoc->base.addr_lock);
return found;
}
+
+/* Set an association id for a given association */
+int sctp_assoc_set_id(struct sctp_association *asoc, gfp_t gfp)
+{
+ int assoc_id;
+ int error = 0;
+retry:
+ if (unlikely(!idr_pre_get(&sctp_assocs_id, gfp)))
+ return -ENOMEM;
+
+ spin_lock_bh(&sctp_assocs_id_lock);
+ error = idr_get_new_above(&sctp_assocs_id, (void *)asoc,
+ 1, &assoc_id);
+ spin_unlock_bh(&sctp_assocs_id_lock);
+ if (error == -EAGAIN)
+ goto retry;
+ else if (error)
+ return error;
+
+ asoc->assoc_id = (sctp_assoc_t) assoc_id;
+ return error;
+}
diff --git a/net/sctp/debug.c b/net/sctp/debug.c
index 5f5ab28977c..e8c0f7435d7 100644
--- a/net/sctp/debug.c
+++ b/net/sctp/debug.c
@@ -93,8 +93,9 @@ const char *sctp_cname(const sctp_subtype_t cid)
return "FWD_TSN";
default:
- return "unknown chunk";
- };
+ break;
+ }
+
return "unknown chunk";
}
diff --git a/net/sctp/input.c b/net/sctp/input.c
index 71db6687369..885109fb3dd 100644
--- a/net/sctp/input.c
+++ b/net/sctp/input.c
@@ -79,14 +79,10 @@ static void sctp_add_backlog(struct sock *sk, struct sk_buff *skb);
/* Calculate the SCTP checksum of an SCTP packet. */
static inline int sctp_rcv_checksum(struct sk_buff *skb)
{
- struct sctphdr *sh;
- __u32 cmp, val;
struct sk_buff *list = skb_shinfo(skb)->frag_list;
-
- sh = (struct sctphdr *) skb->h.raw;
- cmp = ntohl(sh->checksum);
-
- val = sctp_start_cksum((__u8 *)sh, skb_headlen(skb));
+ struct sctphdr *sh = sctp_hdr(skb);
+ __u32 cmp = ntohl(sh->checksum);
+ __u32 val = sctp_start_cksum((__u8 *)sh, skb_headlen(skb));
for (; list; list = list->next)
val = sctp_update_cksum((__u8 *)list->data, skb_headlen(list),
@@ -138,14 +134,13 @@ int sctp_rcv(struct sk_buff *skb)
if (skb_linearize(skb))
goto discard_it;
- sh = (struct sctphdr *) skb->h.raw;
+ sh = sctp_hdr(skb);
/* Pull up the IP and SCTP headers. */
- __skb_pull(skb, skb->h.raw - skb->data);
+ __skb_pull(skb, skb_transport_offset(skb));
if (skb->len < sizeof(struct sctphdr))
goto discard_it;
- if ((skb->ip_summed != CHECKSUM_UNNECESSARY) &&
- (sctp_rcv_checksum(skb) < 0))
+ if (!skb_csum_unnecessary(skb) && sctp_rcv_checksum(skb) < 0)
goto discard_it;
skb_pull(skb, sizeof(struct sctphdr));
@@ -154,7 +149,7 @@ int sctp_rcv(struct sk_buff *skb)
if (skb->len < sizeof(struct sctp_chunkhdr))
goto discard_it;
- family = ipver2af(skb->nh.iph->version);
+ family = ipver2af(ip_hdr(skb)->version);
af = sctp_get_af_specific(family);
if (unlikely(!af))
goto discard_it;
@@ -510,30 +505,30 @@ void sctp_err_finish(struct sock *sk, struct sctp_association *asoc)
void sctp_v4_err(struct sk_buff *skb, __u32 info)
{
struct iphdr *iph = (struct iphdr *)skb->data;
- struct sctphdr *sh = (struct sctphdr *)(skb->data + (iph->ihl <<2));
- int type = skb->h.icmph->type;
- int code = skb->h.icmph->code;
+ 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 sctp_transport *transport;
struct inet_sock *inet;
- char *saveip, *savesctp;
+ sk_buff_data_t saveip, savesctp;
int err;
- if (skb->len < ((iph->ihl << 2) + 8)) {
+ if (skb->len < ihlen + 8) {
ICMP_INC_STATS_BH(ICMP_MIB_INERRORS);
return;
}
/* Fix up skb to look at the embedded net header. */
- saveip = skb->nh.raw;
- savesctp = skb->h.raw;
- skb->nh.iph = iph;
- skb->h.raw = (char *)sh;
- sk = sctp_err_lookup(AF_INET, skb, sh, &asoc, &transport);
- /* Put back, the original pointers. */
- skb->nh.raw = saveip;
- skb->h.raw = savesctp;
+ saveip = skb->network_header;
+ savesctp = skb->transport_header;
+ skb_reset_network_header(skb);
+ skb_set_transport_header(skb, ihlen);
+ sk = sctp_err_lookup(AF_INET, skb, sctp_hdr(skb), &asoc, &transport);
+ /* Put back, the original values. */
+ skb->network_header = saveip;
+ skb->transport_header = savesctp;
if (!sk) {
ICMP_INC_STATS_BH(ICMP_MIB_INERRORS);
return;
@@ -616,7 +611,7 @@ int sctp_rcv_ootb(struct sk_buff *skb)
break;
ch_end = ((__u8 *)ch) + WORD_ROUND(ntohs(ch->length));
- if (ch_end > skb->tail)
+ if (ch_end > skb_tail_pointer(skb))
break;
/* RFC 8.4, 2) If the OOTB packet contains an ABORT chunk, the
@@ -648,7 +643,7 @@ int sctp_rcv_ootb(struct sk_buff *skb)
}
ch = (sctp_chunkhdr_t *) ch_end;
- } while (ch_end < skb->tail);
+ } while (ch_end < skb_tail_pointer(skb));
return 0;
@@ -905,7 +900,7 @@ static struct sctp_association *__sctp_rcv_init_lookup(struct sk_buff *skb,
struct sctp_association *asoc;
union sctp_addr addr;
union sctp_addr *paddr = &addr;
- struct sctphdr *sh = (struct sctphdr *) skb->h.raw;
+ struct sctphdr *sh = sctp_hdr(skb);
sctp_chunkhdr_t *ch;
union sctp_params params;
sctp_init_chunk_t *init;
diff --git a/net/sctp/inqueue.c b/net/sctp/inqueue.c
index c30629e1778..88aa2240754 100644
--- a/net/sctp/inqueue.c
+++ b/net/sctp/inqueue.c
@@ -159,16 +159,16 @@ struct sctp_chunk *sctp_inq_pop(struct sctp_inq *queue)
* the skb->tail.
*/
if (unlikely(skb_is_nonlinear(chunk->skb))) {
- if (chunk->chunk_end > chunk->skb->tail)
- chunk->chunk_end = chunk->skb->tail;
+ if (chunk->chunk_end > skb_tail_pointer(chunk->skb))
+ chunk->chunk_end = skb_tail_pointer(chunk->skb);
}
skb_pull(chunk->skb, sizeof(sctp_chunkhdr_t));
chunk->subh.v = NULL; /* Subheader is no longer valid. */
- if (chunk->chunk_end < chunk->skb->tail) {
+ if (chunk->chunk_end < skb_tail_pointer(chunk->skb)) {
/* This is not a singleton */
chunk->singleton = 0;
- } else if (chunk->chunk_end > chunk->skb->tail) {
+ } else if (chunk->chunk_end > skb_tail_pointer(chunk->skb)) {
/* RFC 2960, Section 6.10 Bundling
*
* Partial chunks MUST NOT be placed in an SCTP packet.
diff --git a/net/sctp/ipv6.c b/net/sctp/ipv6.c
index 0b9c49b3a10..84cd53635fe 100644
--- a/net/sctp/ipv6.c
+++ b/net/sctp/ipv6.c
@@ -122,26 +122,24 @@ SCTP_STATIC void sctp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
int type, int code, int offset, __be32 info)
{
struct inet6_dev *idev;
- struct ipv6hdr *iph = (struct ipv6hdr *)skb->data;
- struct sctphdr *sh = (struct sctphdr *)(skb->data + offset);
struct sock *sk;
struct sctp_association *asoc;
struct sctp_transport *transport;
struct ipv6_pinfo *np;
- char *saveip, *savesctp;
+ sk_buff_data_t saveip, savesctp;
int err;
idev = in6_dev_get(skb->dev);
/* Fix up skb to look at the embedded net header. */
- saveip = skb->nh.raw;
- savesctp = skb->h.raw;
- skb->nh.ipv6h = iph;
- skb->h.raw = (char *)sh;
- sk = sctp_err_lookup(AF_INET6, skb, sh, &asoc, &transport);
+ saveip = skb->network_header;
+ savesctp = skb->transport_header;
+ skb_reset_network_header(skb);
+ skb_set_transport_header(skb, offset);
+ sk = sctp_err_lookup(AF_INET6, skb, sctp_hdr(skb), &asoc, &transport);
/* Put back, the original pointers. */
- skb->nh.raw = saveip;
- skb->h.raw = savesctp;
+ skb->network_header = saveip;
+ skb->transport_header = savesctp;
if (!sk) {
ICMP6_INC_STATS_BH(idev, ICMP6_MIB_INERRORS);
goto out;
@@ -391,13 +389,13 @@ static void sctp_v6_from_skb(union sctp_addr *addr,struct sk_buff *skb,
addr->v6.sin6_flowinfo = 0; /* FIXME */
addr->v6.sin6_scope_id = ((struct inet6_skb_parm *)skb->cb)->iif;
- sh = (struct sctphdr *) skb->h.raw;
+ sh = sctp_hdr(skb);
if (is_saddr) {
*port = sh->source;
- from = &skb->nh.ipv6h->saddr;
+ from = &ipv6_hdr(skb)->saddr;
} else {
*port = sh->dest;
- from = &skb->nh.ipv6h->daddr;
+ from = &ipv6_hdr(skb)->daddr;
}
ipv6_addr_copy(&addr->v6.sin6_addr, from);
}
@@ -606,7 +604,7 @@ static sctp_scope_t sctp_v6_scope(union sctp_addr *addr)
default:
retval = SCTP_SCOPE_GLOBAL;
break;
- };
+ }
return retval;
}
@@ -699,7 +697,7 @@ static int sctp_v6_skb_iif(const struct sk_buff *skb)
/* Was this packet marked by Explicit Congestion Notification? */
static int sctp_v6_is_ce(const struct sk_buff *skb)
{
- return *((__u32 *)(skb->nh.ipv6h)) & htonl(1<<20);
+ return *((__u32 *)(ipv6_hdr(skb))) & htonl(1 << 20);
}
/* Dump the v6 addr to the seq file. */
@@ -766,19 +764,19 @@ static void sctp_inet6_skb_msgname(struct sk_buff *skb, char *msgname,
if (msgname) {
sctp_inet6_msgname(msgname, addr_len);
sin6 = (struct sockaddr_in6 *)msgname;
- sh = (struct sctphdr *)skb->h.raw;
+ sh = sctp_hdr(skb);
sin6->sin6_port = sh->source;
/* Map ipv4 address into v4-mapped-on-v6 address. */
if (sctp_sk(skb->sk)->v4mapped &&
- skb->nh.iph->version == 4) {
+ ip_hdr(skb)->version == 4) {
sctp_v4_map_v6((union sctp_addr *)sin6);
- sin6->sin6_addr.s6_addr32[3] = skb->nh.iph->saddr;
+ sin6->sin6_addr.s6_addr32[3] = ip_hdr(skb)->saddr;
return;
}
/* Otherwise, just copy the v6 address. */
- ipv6_addr_copy(&sin6->sin6_addr, &skb->nh.ipv6h->saddr);
+ ipv6_addr_copy(&sin6->sin6_addr, &ipv6_hdr(skb)->saddr);
if (ipv6_addr_type(&sin6->sin6_addr) & IPV6_ADDR_LINKLOCAL) {
struct sctp_ulpevent *ev = sctp_skb2event(skb);
sin6->sin6_scope_id = ev->iif;
@@ -994,45 +992,52 @@ static struct sctp_pf sctp_pf_inet6_specific = {
.af = &sctp_ipv6_specific,
};
-/* Initialize IPv6 support and register with inet6 stack. */
+/* Initialize IPv6 support and register with socket layer. */
int sctp_v6_init(void)
{
- int rc = proto_register(&sctpv6_prot, 1);
+ int rc;
+
+ /* Register the SCTP specific PF_INET6 functions. */
+ sctp_register_pf(&sctp_pf_inet6_specific, PF_INET6);
+ /* Register the SCTP specific AF_INET6 functions. */
+ sctp_register_af(&sctp_ipv6_specific);
+
+ rc = proto_register(&sctpv6_prot, 1);
if (rc)
- goto out;
- /* Register inet6 protocol. */
- rc = -EAGAIN;
- if (inet6_add_protocol(&sctpv6_protocol, IPPROTO_SCTP) < 0)
- goto out_unregister_sctp_proto;
+ return rc;
/* Add SCTPv6(UDP and TCP style) to inetsw6 linked list. */
inet6_register_protosw(&sctpv6_seqpacket_protosw);
inet6_register_protosw(&sctpv6_stream_protosw);
- /* Register the SCTP specific PF_INET6 functions. */
- sctp_register_pf(&sctp_pf_inet6_specific, PF_INET6);
-
- /* Register the SCTP specific AF_INET6 functions. */
- sctp_register_af(&sctp_ipv6_specific);
+ return 0;
+}
+/* Register with inet6 layer. */
+int sctp_v6_add_protocol(void)
+{
/* Register notifier for inet6 address additions/deletions. */
register_inet6addr_notifier(&sctp_inet6addr_notifier);
- rc = 0;
-out:
- return rc;
-out_unregister_sctp_proto:
- proto_unregister(&sctpv6_prot);
- goto out;
+
+ if (inet6_add_protocol(&sctpv6_protocol, IPPROTO_SCTP) < 0)
+ return -EAGAIN;
+
+ return 0;
}
/* IPv6 specific exit support. */
void sctp_v6_exit(void)
{
- list_del(&sctp_ipv6_specific.list);
- inet6_del_protocol(&sctpv6_protocol, IPPROTO_SCTP);
inet6_unregister_protosw(&sctpv6_seqpacket_protosw);
inet6_unregister_protosw(&sctpv6_stream_protosw);
- unregister_inet6addr_notifier(&sctp_inet6addr_notifier);
proto_unregister(&sctpv6_prot);
+ list_del(&sctp_ipv6_specific.list);
+}
+
+/* Unregister with inet6 layer. */
+void sctp_v6_del_protocol(void)
+{
+ inet6_del_protocol(&sctpv6_protocol, IPPROTO_SCTP);
+ unregister_inet6addr_notifier(&sctp_inet6addr_notifier);
}
diff --git a/net/sctp/output.c b/net/sctp/output.c
index f875fc3ced5..d85543def75 100644
--- a/net/sctp/output.c
+++ b/net/sctp/output.c
@@ -176,7 +176,7 @@ sctp_xmit_t sctp_packet_transmit_chunk(struct sctp_packet *packet,
case SCTP_XMIT_OK:
case SCTP_XMIT_NAGLE_DELAY:
break;
- };
+ }
return retval;
}
diff --git a/net/sctp/outqueue.c b/net/sctp/outqueue.c
index 41abfd17627..992f361084b 100644
--- a/net/sctp/outqueue.c
+++ b/net/sctp/outqueue.c
@@ -338,7 +338,7 @@ int sctp_outq_tail(struct sctp_outq *q, struct sctp_chunk *chunk)
SCTP_INC_STATS(SCTP_MIB_OUTORDERCHUNKS);
q->empty = 0;
break;
- };
+ }
} else {
list_add_tail(&chunk->list, &q->control_chunk_list);
SCTP_INC_STATS(SCTP_MIB_OUTCTRLCHUNKS);
@@ -630,7 +630,7 @@ static int sctp_outq_flush_rtx(struct sctp_outq *q, struct sctp_packet *pkt,
/* Retrieve a new chunk to bundle. */
lchunk = sctp_list_dequeue(lqueue);
break;
- };
+ }
/* If we are here due to a retransmit timeout or a fast
* retransmit and if there are any chunks left in the retransmit
@@ -779,7 +779,7 @@ int sctp_outq_flush(struct sctp_outq *q, int rtx_timeout)
default:
/* We built a chunk with an illegal type! */
BUG();
- };
+ }
}
/* Is it OK to send data chunks? */
@@ -1397,7 +1397,7 @@ static void sctp_check_transmitted(struct sctp_outq *q,
SCTP_DEBUG_PRINTK("ACKed: %08x", tsn);
dbg_prt_state = 0;
dbg_ack_tsn = tsn;
- };
+ }
dbg_last_ack_tsn = tsn;
#endif /* SCTP_DEBUG */
@@ -1452,7 +1452,7 @@ static void sctp_check_transmitted(struct sctp_outq *q,
SCTP_DEBUG_PRINTK("KEPT: %08x",tsn);
dbg_prt_state = 1;
dbg_kept_tsn = tsn;
- };
+ }
dbg_last_kept_tsn = tsn;
#endif /* SCTP_DEBUG */
@@ -1476,7 +1476,7 @@ static void sctp_check_transmitted(struct sctp_outq *q,
} else {
SCTP_DEBUG_PRINTK("\n");
}
- };
+ }
#endif /* SCTP_DEBUG */
if (transport) {
if (bytes_acked) {
diff --git a/net/sctp/protocol.c b/net/sctp/protocol.c
index e17a823ca90..34bab36637a 100644
--- a/net/sctp/protocol.c
+++ b/net/sctp/protocol.c
@@ -170,7 +170,7 @@ static void sctp_get_local_addr_list(void)
struct sctp_af *af;
read_lock(&dev_base_lock);
- for (dev = dev_base; dev; dev = dev->next) {
+ for_each_netdev(dev) {
__list_for_each(pos, &sctp_address_families) {
af = list_entry(pos, struct sctp_af, list);
af->copy_addrlist(&sctp_local_addr_list, dev);
@@ -235,13 +235,13 @@ static void sctp_v4_from_skb(union sctp_addr *addr, struct sk_buff *skb,
port = &addr->v4.sin_port;
addr->v4.sin_family = AF_INET;
- sh = (struct sctphdr *) skb->h.raw;
+ sh = sctp_hdr(skb);
if (is_saddr) {
*port = sh->source;
- from = &skb->nh.iph->saddr;
+ from = &ip_hdr(skb)->saddr;
} else {
*port = sh->dest;
- from = &skb->nh.iph->daddr;
+ from = &ip_hdr(skb)->daddr;
}
memcpy(&addr->v4.sin_addr.s_addr, from, sizeof(struct in_addr));
}
@@ -530,7 +530,7 @@ static int sctp_v4_skb_iif(const struct sk_buff *skb)
/* Was this packet marked by Explicit Congestion Notification? */
static int sctp_v4_is_ce(const struct sk_buff *skb)
{
- return INET_ECN_is_ce(skb->nh.iph->tos);
+ return INET_ECN_is_ce(ip_hdr(skb)->tos);
}
/* Create and initialize a new sk for the socket returned by accept(). */
@@ -731,15 +731,13 @@ static void sctp_inet_event_msgname(struct sctp_ulpevent *event, char *msgname,
/* Initialize and copy out a msgname from an inbound skb. */
static void sctp_inet_skb_msgname(struct sk_buff *skb, char *msgname, int *len)
{
- struct sctphdr *sh;
- struct sockaddr_in *sin;
-
if (msgname) {
+ struct sctphdr *sh = sctp_hdr(skb);
+ struct sockaddr_in *sin = (struct sockaddr_in *)msgname;
+
sctp_inet_msgname(msgname, len);
- sin = (struct sockaddr_in *)msgname;
- sh = (struct sctphdr *)skb->h.raw;
sin->sin_port = sh->source;
- sin->sin_addr.s_addr = skb->nh.iph->saddr;
+ sin->sin_addr.s_addr = ip_hdr(skb)->saddr;
}
}
@@ -977,28 +975,14 @@ SCTP_STATIC __init int sctp_init(void)
if (!sctp_sanity_check())
goto out;
- status = proto_register(&sctp_prot, 1);
- if (status)
- goto out;
-
- /* Add SCTP to inet_protos hash table. */
- status = -EAGAIN;
- if (inet_add_protocol(&sctp_protocol, IPPROTO_SCTP) < 0)
- goto err_add_protocol;
-
- /* Add SCTP(TCP and UDP style) to inetsw linked list. */
- inet_register_protosw(&sctp_seqpacket_protosw);
- inet_register_protosw(&sctp_stream_protosw);
-
- /* Allocate a cache pools. */
+ /* Allocate bind_bucket and chunk caches. */
status = -ENOBUFS;
sctp_bucket_cachep = kmem_cache_create("sctp_bind_bucket",
sizeof(struct sctp_bind_bucket),
0, SLAB_HWCACHE_ALIGN,
NULL, NULL);
-
if (!sctp_bucket_cachep)
- goto err_bucket_cachep;
+ goto out;
sctp_chunk_cachep = kmem_cache_create("sctp_chunk",
sizeof(struct sctp_chunk),
@@ -1044,7 +1028,7 @@ SCTP_STATIC __init int sctp_init(void)
sctp_cookie_preserve_enable = 1;
/* Max.Burst - 4 */
- sctp_max_burst = SCTP_MAX_BURST;
+ sctp_max_burst = SCTP_DEFAULT_MAX_BURST;
/* Association.Max.Retrans - 10 attempts
* Path.Max.Retrans - 5 attempts (per destination address)
@@ -1155,6 +1139,14 @@ SCTP_STATIC __init int sctp_init(void)
INIT_LIST_HEAD(&sctp_address_families);
sctp_register_af(&sctp_ipv4_specific);
+ status = proto_register(&sctp_prot, 1);
+ if (status)
+ goto err_proto_register;
+
+ /* Register SCTP(UDP and TCP style) with socket layer. */
+ inet_register_protosw(&sctp_seqpacket_protosw);
+ inet_register_protosw(&sctp_stream_protosw);
+
status = sctp_v6_init();
if (status)
goto err_v6_init;
@@ -1168,19 +1160,39 @@ SCTP_STATIC __init int sctp_init(void)
/* Initialize the local address list. */
INIT_LIST_HEAD(&sctp_local_addr_list);
-
sctp_get_local_addr_list();
/* Register notifier for inet address additions/deletions. */
register_inetaddr_notifier(&sctp_inetaddr_notifier);
+ /* Register SCTP with inet layer. */
+ if (inet_add_protocol(&sctp_protocol, IPPROTO_SCTP) < 0) {
+ status = -EAGAIN;
+ goto err_add_protocol;
+ }
+
+ /* Register SCTP with inet6 layer. */
+ status = sctp_v6_add_protocol();
+ if (status)
+ goto err_v6_add_protocol;
+
__unsafe(THIS_MODULE);
status = 0;
out:
return status;
+err_v6_add_protocol:
+ inet_del_protocol(&sctp_protocol, IPPROTO_SCTP);
+ unregister_inetaddr_notifier(&sctp_inetaddr_notifier);
+err_add_protocol:
+ sctp_free_local_addr_list();
+ sock_release(sctp_ctl_socket);
err_ctl_sock_init:
sctp_v6_exit();
err_v6_init:
+ inet_unregister_protosw(&sctp_stream_protosw);
+ inet_unregister_protosw(&sctp_seqpacket_protosw);
+ proto_unregister(&sctp_prot);
+err_proto_register:
sctp_sysctl_unregister();
list_del(&sctp_ipv4_specific.list);
free_pages((unsigned long)sctp_port_hashtable,
@@ -1194,19 +1206,13 @@ err_ehash_alloc:
sizeof(struct sctp_hashbucket)));
err_ahash_alloc:
sctp_dbg_objcnt_exit();
-err_init_proc:
sctp_proc_exit();
+err_init_proc:
cleanup_sctp_mibs();
err_init_mibs:
kmem_cache_destroy(sctp_chunk_cachep);
err_chunk_cachep:
kmem_cache_destroy(sctp_bucket_cachep);
-err_bucket_cachep:
- inet_del_protocol(&sctp_protocol, IPPROTO_SCTP);
- inet_unregister_protosw(&sctp_seqpacket_protosw);
- inet_unregister_protosw(&sctp_stream_protosw);
-err_add_protocol:
- proto_unregister(&sctp_prot);
goto out;
}
@@ -1217,8 +1223,9 @@ SCTP_STATIC __exit void sctp_exit(void)
* up all the remaining associations and all that memory.
*/
- /* Unregister notifier for inet address additions/deletions. */
- unregister_inetaddr_notifier(&sctp_inetaddr_notifier);
+ /* Unregister with inet6/inet layers. */
+ sctp_v6_del_protocol();
+ inet_del_protocol(&sctp_protocol, IPPROTO_SCTP);
/* Free the local address list. */
sctp_free_local_addr_list();
@@ -1226,7 +1233,16 @@ SCTP_STATIC __exit void sctp_exit(void)
/* Free the control endpoint. */
sock_release(sctp_ctl_socket);
+ /* Cleanup v6 initializations. */
sctp_v6_exit();
+
+ /* Unregister with socket layer. */
+ inet_unregister_protosw(&sctp_stream_protosw);
+ inet_unregister_protosw(&sctp_seqpacket_protosw);
+
+ /* Unregister notifier for inet address additions/deletions. */
+ unregister_inetaddr_notifier(&sctp_inetaddr_notifier);
+
sctp_sysctl_unregister();
list_del(&sctp_ipv4_specific.list);
@@ -1238,16 +1254,13 @@ SCTP_STATIC __exit void sctp_exit(void)
get_order(sctp_port_hashsize *
sizeof(struct sctp_bind_hashbucket)));
- kmem_cache_destroy(sctp_chunk_cachep);
- kmem_cache_destroy(sctp_bucket_cachep);
-
sctp_dbg_objcnt_exit();
sctp_proc_exit();
cleanup_sctp_mibs();
- inet_del_protocol(&sctp_protocol, IPPROTO_SCTP);
- inet_unregister_protosw(&sctp_seqpacket_protosw);
- inet_unregister_protosw(&sctp_stream_protosw);
+ kmem_cache_destroy(sctp_chunk_cachep);
+ kmem_cache_destroy(sctp_bucket_cachep);
+
proto_unregister(&sctp_prot);
}
diff --git a/net/sctp/sm_make_chunk.c b/net/sctp/sm_make_chunk.c
index f7fb29d5a0c..8d18f570c2e 100644
--- a/net/sctp/sm_make_chunk.c
+++ b/net/sctp/sm_make_chunk.c
@@ -86,7 +86,7 @@ int sctp_chunk_iif(const struct sctp_chunk *chunk)
struct sctp_af *af;
int iif = 0;
- af = sctp_get_af_specific(ipver2af(chunk->skb->nh.iph->version));
+ af = sctp_get_af_specific(ipver2af(ip_hdr(chunk->skb)->version));
if (af)
iif = af->skb_iif(chunk->skb);
@@ -1143,7 +1143,7 @@ void *sctp_addto_chunk(struct sctp_chunk *chunk, int len, const void *data)
/* Adjust the chunk length field. */
chunk->chunk_hdr->length = htons(chunklen + padlen + len);
- chunk->chunk_end = chunk->skb->tail;
+ chunk->chunk_end = skb_tail_pointer(chunk->skb);
return target;
}
@@ -1168,7 +1168,7 @@ int sctp_user_addto_chunk(struct sctp_chunk *chunk, int off, int len,
/* Adjust the chunk length field. */
chunk->chunk_hdr->length =
htons(ntohs(chunk->chunk_hdr->length) + len);
- chunk->chunk_end = chunk->skb->tail;
+ chunk->chunk_end = skb_tail_pointer(chunk->skb);
out:
return err;
@@ -1233,7 +1233,7 @@ struct sctp_association *sctp_make_temp_asoc(const struct sctp_endpoint *ep,
asoc->temp = 1;
skb = chunk->skb;
/* Create an entry for the source address of the packet. */
- af = sctp_get_af_specific(ipver2af(skb->nh.iph->version));
+ af = sctp_get_af_specific(ipver2af(ip_hdr(skb)->version));
if (unlikely(!af))
goto fail;
af->from_skb(&asoc->c.peer_addr, skb, 1);
@@ -1939,7 +1939,6 @@ int sctp_process_init(struct sctp_association *asoc, sctp_cid_t cid,
* association.
*/
if (!asoc->temp) {
- int assoc_id;
int error;
asoc->ssnmap = sctp_ssnmap_new(asoc->c.sinit_max_instreams,
@@ -1947,19 +1946,9 @@ int sctp_process_init(struct sctp_association *asoc, sctp_cid_t cid,
if (!asoc->ssnmap)
goto clean_up;
- retry:
- if (unlikely(!idr_pre_get(&sctp_assocs_id, gfp)))
+ error = sctp_assoc_set_id(asoc, gfp);
+ if (error)
goto clean_up;
- spin_lock_bh(&sctp_assocs_id_lock);
- error = idr_get_new_above(&sctp_assocs_id, (void *)asoc, 1,
- &assoc_id);
- spin_unlock_bh(&sctp_assocs_id_lock);
- if (error == -EAGAIN)
- goto retry;
- else if (error)
- goto clean_up;
-
- asoc->assoc_id = (sctp_assoc_t) assoc_id;
}
/* ADDIP Section 4.1 ASCONF Chunk Procedures
@@ -2077,7 +2066,7 @@ static int sctp_process_param(struct sctp_association *asoc,
default: /* Just ignore anything else. */
break;
- };
+ }
}
break;
@@ -2118,7 +2107,7 @@ static int sctp_process_param(struct sctp_association *asoc,
SCTP_DEBUG_PRINTK("Ignoring param: %d for association %p.\n",
ntohs(param.p->type), asoc);
break;
- };
+ }
return retval;
}
diff --git a/net/sctp/sm_sideeffect.c b/net/sctp/sm_sideeffect.c
index 13556749311..d9fad4f6ffc 100644
--- a/net/sctp/sm_sideeffect.c
+++ b/net/sctp/sm_sideeffect.c
@@ -464,7 +464,7 @@ static void sctp_cmd_init_failed(sctp_cmd_seq_t *commands,
struct sctp_ulpevent *event;
event = sctp_ulpevent_make_assoc_change(asoc,0, SCTP_CANT_STR_ASSOC,
- (__u16)error, 0, 0,
+ (__u16)error, 0, 0, NULL,
GFP_ATOMIC);
if (event)
@@ -492,8 +492,13 @@ static void sctp_cmd_assoc_failed(sctp_cmd_seq_t *commands,
/* Cancel any partial delivery in progress. */
sctp_ulpq_abort_pd(&asoc->ulpq, GFP_ATOMIC);
- event = sctp_ulpevent_make_assoc_change(asoc, 0, SCTP_COMM_LOST,
- (__u16)error, 0, 0,
+ if (event_type == SCTP_EVENT_T_CHUNK && subtype.chunk == SCTP_CID_ABORT)
+ event = sctp_ulpevent_make_assoc_change(asoc, 0, SCTP_COMM_LOST,
+ (__u16)error, 0, 0, chunk,
+ GFP_ATOMIC);
+ else
+ event = sctp_ulpevent_make_assoc_change(asoc, 0, SCTP_COMM_LOST,
+ (__u16)error, 0, 0, NULL,
GFP_ATOMIC);
if (event)
sctp_add_cmd_sf(commands, SCTP_CMD_EVENT_ULP,
@@ -857,6 +862,33 @@ static void sctp_cmd_set_sk_err(struct sctp_association *asoc, int error)
sk->sk_err = error;
}
+/* Helper function to generate an association change event */
+static void sctp_cmd_assoc_change(sctp_cmd_seq_t *commands,
+ struct sctp_association *asoc,
+ u8 state)
+{
+ struct sctp_ulpevent *ev;
+
+ ev = sctp_ulpevent_make_assoc_change(asoc, 0, state, 0,
+ asoc->c.sinit_num_ostreams,
+ asoc->c.sinit_max_instreams,
+ NULL, GFP_ATOMIC);
+ if (ev)
+ sctp_ulpq_tail_event(&asoc->ulpq, ev);
+}
+
+/* Helper function to generate an adaptation indication event */
+static void sctp_cmd_adaptation_ind(sctp_cmd_seq_t *commands,
+ struct sctp_association *asoc)
+{
+ struct sctp_ulpevent *ev;
+
+ ev = sctp_ulpevent_make_adaptation_indication(asoc, GFP_ATOMIC);
+
+ if (ev)
+ sctp_ulpq_tail_event(&asoc->ulpq, ev);
+}
+
/* These three macros allow us to pull the debugging code out of the
* main flow of sctp_do_sm() to keep attention focused on the real
* functionality there.
@@ -1004,7 +1036,7 @@ static int sctp_side_effects(sctp_event_t event_type, sctp_subtype_t subtype,
status, state, event_type, subtype.chunk);
BUG();
break;
- };
+ }
bail:
return error;
@@ -1480,11 +1512,20 @@ static int sctp_cmd_interpreter(sctp_event_t event_type,
case SCTP_CMD_SET_SK_ERR:
sctp_cmd_set_sk_err(asoc, cmd->obj.error);
break;
+ case SCTP_CMD_ASSOC_CHANGE:
+ sctp_cmd_assoc_change(commands, asoc,
+ cmd->obj.u8);
+ break;
+ case SCTP_CMD_ADAPTATION_IND:
+ sctp_cmd_adaptation_ind(commands, asoc);
+ break;
+
default:
printk(KERN_WARNING "Impossible command: %u, %p\n",
cmd->verb, cmd->obj.ptr);
break;
- };
+ }
+
if (error)
break;
}
diff --git a/net/sctp/sm_statefuns.c b/net/sctp/sm_statefuns.c
index e9097cf614b..f02ce3dddb7 100644
--- a/net/sctp/sm_statefuns.c
+++ b/net/sctp/sm_statefuns.c
@@ -186,7 +186,7 @@ sctp_disposition_t sctp_sf_do_4_C(const struct sctp_endpoint *ep,
* notification is passed to the upper layer.
*/
ev = sctp_ulpevent_make_assoc_change(asoc, 0, SCTP_SHUTDOWN_COMP,
- 0, 0, 0, GFP_ATOMIC);
+ 0, 0, 0, NULL, GFP_ATOMIC);
if (ev)
sctp_add_cmd_sf(commands, SCTP_CMD_EVENT_ULP,
SCTP_ULPEVENT(ev));
@@ -629,7 +629,7 @@ sctp_disposition_t sctp_sf_do_5_1D_ce(const struct sctp_endpoint *ep,
case -SCTP_IERROR_BAD_SIG:
default:
return sctp_sf_pdiscard(ep, asoc, type, arg, commands);
- };
+ }
}
@@ -661,7 +661,7 @@ sctp_disposition_t sctp_sf_do_5_1D_ce(const struct sctp_endpoint *ep,
ev = sctp_ulpevent_make_assoc_change(new_asoc, 0, SCTP_COMM_UP, 0,
new_asoc->c.sinit_num_ostreams,
new_asoc->c.sinit_max_instreams,
- GFP_ATOMIC);
+ NULL, GFP_ATOMIC);
if (!ev)
goto nomem_ev;
@@ -790,7 +790,7 @@ sctp_disposition_t sctp_sf_do_5_1E_ca(const struct sctp_endpoint *ep,
ev = sctp_ulpevent_make_assoc_change(asoc, 0, SCTP_COMM_UP,
0, asoc->c.sinit_num_ostreams,
asoc->c.sinit_max_instreams,
- GFP_ATOMIC);
+ NULL, GFP_ATOMIC);
if (!ev)
goto nomem;
@@ -1195,7 +1195,7 @@ static void sctp_tietags_populate(struct sctp_association *new_asoc,
new_asoc->c.my_ttag = asoc->c.my_vtag;
new_asoc->c.peer_ttag = asoc->c.peer_vtag;
break;
- };
+ }
/* Other parameters for the endpoint SHOULD be copied from the
* existing parameters of the association (e.g. number of
@@ -1625,7 +1625,7 @@ static sctp_disposition_t sctp_sf_do_dupcook_a(const struct sctp_endpoint *ep,
ev = sctp_ulpevent_make_assoc_change(asoc, 0, SCTP_RESTART, 0,
new_asoc->c.sinit_num_ostreams,
new_asoc->c.sinit_max_instreams,
- GFP_ATOMIC);
+ NULL, GFP_ATOMIC);
if (!ev)
goto nomem_ev;
@@ -1656,7 +1656,6 @@ static sctp_disposition_t sctp_sf_do_dupcook_b(const struct sctp_endpoint *ep,
struct sctp_association *new_asoc)
{
sctp_init_chunk_t *peer_init;
- struct sctp_ulpevent *ev;
struct sctp_chunk *repl;
/* new_asoc is a brand-new association, so these are not yet
@@ -1687,34 +1686,28 @@ static sctp_disposition_t sctp_sf_do_dupcook_b(const struct sctp_endpoint *ep,
* D) IMPLEMENTATION NOTE: An implementation may choose to
* send the Communication Up notification to the SCTP user
* upon reception of a valid COOKIE ECHO chunk.
+ *
+ * Sadly, this needs to be implemented as a side-effect, because
+ * we are not guaranteed to have set the association id of the real
+ * association and so these notifications need to be delayed until
+ * the association id is allocated.
*/
- ev = sctp_ulpevent_make_assoc_change(asoc, 0, SCTP_COMM_UP, 0,
- new_asoc->c.sinit_num_ostreams,
- new_asoc->c.sinit_max_instreams,
- GFP_ATOMIC);
- if (!ev)
- goto nomem_ev;
- sctp_add_cmd_sf(commands, SCTP_CMD_EVENT_ULP, SCTP_ULPEVENT(ev));
+ sctp_add_cmd_sf(commands, SCTP_CMD_ASSOC_CHANGE, SCTP_U8(SCTP_COMM_UP));
/* Sockets API Draft Section 5.3.1.6
* When a peer sends a Adaptation Layer Indication parameter , SCTP
* delivers this notification to inform the application that of the
* peers requested adaptation layer.
+ *
+ * This also needs to be done as a side effect for the same reason as
+ * above.
*/
- if (asoc->peer.adaptation_ind) {
- ev = sctp_ulpevent_make_adaptation_indication(asoc, GFP_ATOMIC);
- if (!ev)
- goto nomem_ev;
-
- sctp_add_cmd_sf(commands, SCTP_CMD_EVENT_ULP,
- SCTP_ULPEVENT(ev));
- }
+ if (asoc->peer.adaptation_ind)
+ sctp_add_cmd_sf(commands, SCTP_CMD_ADAPTATION_IND, SCTP_NULL());
return SCTP_DISPOSITION_CONSUME;
-nomem_ev:
- sctp_chunk_free(repl);
nomem:
return SCTP_DISPOSITION_NOMEM;
}
@@ -1786,7 +1779,7 @@ static sctp_disposition_t sctp_sf_do_dupcook_d(const struct sctp_endpoint *ep,
SCTP_COMM_UP, 0,
asoc->c.sinit_num_ostreams,
asoc->c.sinit_max_instreams,
- GFP_ATOMIC);
+ NULL, GFP_ATOMIC);
if (!ev)
goto nomem;
@@ -1904,7 +1897,7 @@ sctp_disposition_t sctp_sf_do_5_2_4_dupcook(const struct sctp_endpoint *ep,
case -SCTP_IERROR_BAD_SIG:
default:
return sctp_sf_pdiscard(ep, asoc, type, arg, commands);
- };
+ }
}
/* Compare the tie_tag in cookie with the verification tag of
@@ -1936,7 +1929,7 @@ sctp_disposition_t sctp_sf_do_5_2_4_dupcook(const struct sctp_endpoint *ep,
default: /* Discard packet for all others. */
retval = sctp_sf_pdiscard(ep, asoc, type, arg, commands);
break;
- };
+ }
/* Delete the tempory new association. */
sctp_add_cmd_sf(commands, SCTP_CMD_NEW_ASOC, SCTP_ASOC(new_asoc));
@@ -3035,7 +3028,7 @@ sctp_disposition_t sctp_sf_do_9_2_final(const struct sctp_endpoint *ep,
* notification is passed to the upper layer.
*/
ev = sctp_ulpevent_make_assoc_change(asoc, 0, SCTP_SHUTDOWN_COMP,
- 0, 0, 0, GFP_ATOMIC);
+ 0, 0, 0, NULL, GFP_ATOMIC);
if (!ev)
goto nomem;
@@ -3115,7 +3108,7 @@ sctp_disposition_t sctp_sf_ootb(const struct sctp_endpoint *ep,
break;
ch_end = ((__u8 *)ch) + WORD_ROUND(ntohs(ch->length));
- if (ch_end > skb->tail)
+ if (ch_end > skb_tail_pointer(skb))
break;
if (SCTP_CID_SHUTDOWN_ACK == ch->type)
@@ -3130,7 +3123,7 @@ sctp_disposition_t sctp_sf_ootb(const struct sctp_endpoint *ep,
return sctp_sf_pdiscard(ep, asoc, type, arg, commands);
ch = (sctp_chunkhdr_t *) ch_end;
- } while (ch_end < skb->tail);
+ } while (ch_end < skb_tail_pointer(skb));
if (ootb_shut_ack)
sctp_sf_shut_8_4_5(ep, asoc, type, arg, commands);
@@ -4816,7 +4809,7 @@ sctp_disposition_t sctp_sf_t2_timer_expire(const struct sctp_endpoint *ep,
default:
BUG();
break;
- };
+ }
if (!reply)
goto nomem;
@@ -5286,7 +5279,7 @@ static int sctp_eat_data(const struct sctp_association *asoc,
chunk->ecn_ce_done = 1;
af = sctp_get_af_specific(
- ipver2af(chunk->skb->nh.iph->version));
+ ipver2af(ip_hdr(chunk->skb)->version));
if (af && af->is_ce(chunk->skb) && asoc->peer.ecn_capable) {
/* Do real work as sideffect. */
diff --git a/net/sctp/sm_statetable.c b/net/sctp/sm_statetable.c
index 5e54b17377f..523071c7902 100644
--- a/net/sctp/sm_statetable.c
+++ b/net/sctp/sm_statetable.c
@@ -101,7 +101,7 @@ const sctp_sm_table_entry_t *sctp_sm_lookup_event(sctp_event_t event_type,
default:
/* Yikes! We got an illegal event type. */
return &bug;
- };
+ }
}
#define TYPE_SCTP_FUNC(func) {.fn = func, .name = #func}
diff --git a/net/sctp/socket.c b/net/sctp/socket.c
index 536298c2eda..9f1a908776d 100644
--- a/net/sctp/socket.c
+++ b/net/sctp/socket.c
@@ -627,6 +627,12 @@ int sctp_bindx_rem(struct sock *sk, struct sockaddr *addrs, int addrcnt)
retval = -EINVAL;
goto err_bindx_rem;
}
+
+ if (!af->addr_valid(sa_addr, sp, NULL)) {
+ retval = -EADDRNOTAVAIL;
+ goto err_bindx_rem;
+ }
+
if (sa_addr->v4.sin_port != htons(bp->port)) {
retval = -EINVAL;
goto err_bindx_rem;
@@ -935,7 +941,7 @@ SCTP_STATIC int sctp_setsockopt_bindx(struct sock* sk,
default:
err = -EINVAL;
break;
- };
+ }
out:
kfree(kaddrs);
@@ -966,6 +972,7 @@ static int __sctp_connect(struct sock* sk,
int walk_size = 0;
union sctp_addr *sa_addr;
void *addr_buf;
+ unsigned short port;
sp = sctp_sk(sk);
ep = sp->ep;
@@ -986,6 +993,7 @@ static int __sctp_connect(struct sock* sk,
while (walk_size < addrs_size) {
sa_addr = (union sctp_addr *)addr_buf;
af = sctp_get_af_specific(sa_addr->sa.sa_family);
+ port = ntohs(sa_addr->v4.sin_port);
/* If the address family is not supported or if this address
* causes the address buffer to overflow return EINVAL.
@@ -999,6 +1007,12 @@ static int __sctp_connect(struct sock* sk,
if (err)
goto out_free;
+ /* Make sure the destination port is correctly set
+ * in all addresses.
+ */
+ if (asoc && asoc->peer.port && asoc->peer.port != port)
+ goto out_free;
+
memcpy(&to, sa_addr, af->sockaddr_len);
/* Check if there already is a matching association on the
@@ -2033,6 +2047,10 @@ static int sctp_setsockopt_autoclose(struct sock *sk, char __user *optval,
* SPP_HB_DEMAND - Request a user initiated heartbeat
* to be made immediately.
*
+ * SPP_HB_TIME_IS_ZERO - Specify's that the time for
+ * heartbeat delayis to be set to the value of 0
+ * milliseconds.
+ *
* SPP_PMTUD_ENABLE - This field will enable PMTU
* discovery upon the specified address. Note that
* if the address feild is empty then all addresses
@@ -2075,13 +2093,30 @@ static int sctp_apply_peer_addr_params(struct sctp_paddrparams *params,
return error;
}
- if (params->spp_hbinterval) {
- if (trans) {
- trans->hbinterval = msecs_to_jiffies(params->spp_hbinterval);
- } else if (asoc) {
- asoc->hbinterval = msecs_to_jiffies(params->spp_hbinterval);
- } else {
- sp->hbinterval = params->spp_hbinterval;
+ /* Note that unless the spp_flag is set to SPP_HB_ENABLE the value of
+ * this field is ignored. Note also that a value of zero indicates
+ * the current setting should be left unchanged.
+ */
+ if (params->spp_flags & SPP_HB_ENABLE) {
+
+ /* Re-zero the interval if the SPP_HB_TIME_IS_ZERO is
+ * set. This lets us use 0 value when this flag
+ * is set.
+ */
+ if (params->spp_flags & SPP_HB_TIME_IS_ZERO)
+ params->spp_hbinterval = 0;
+
+ if (params->spp_hbinterval ||
+ (params->spp_flags & SPP_HB_TIME_IS_ZERO)) {
+ if (trans) {
+ trans->hbinterval =
+ msecs_to_jiffies(params->spp_hbinterval);
+ } else if (asoc) {
+ asoc->hbinterval =
+ msecs_to_jiffies(params->spp_hbinterval);
+ } else {
+ sp->hbinterval = params->spp_hbinterval;
+ }
}
}
@@ -2098,7 +2133,12 @@ static int sctp_apply_peer_addr_params(struct sctp_paddrparams *params,
}
}
- if (params->spp_pathmtu) {
+ /* When Path MTU discovery is disabled the value specified here will
+ * be the "fixed" path mtu (i.e. the value of the spp_flags field must
+ * include the flag SPP_PMTUD_DISABLE for this field to have any
+ * effect).
+ */
+ if ((params->spp_flags & SPP_PMTUD_DISABLE) && params->spp_pathmtu) {
if (trans) {
trans->pathmtu = params->spp_pathmtu;
sctp_assoc_sync_pmtu(asoc);
@@ -2129,7 +2169,11 @@ static int sctp_apply_peer_addr_params(struct sctp_paddrparams *params,
}
}
- if (params->spp_sackdelay) {
+ /* Note that unless the spp_flag is set to SPP_SACKDELAY_ENABLE the
+ * value of this field is ignored. Note also that a value of zero
+ * indicates the current setting should be left unchanged.
+ */
+ if ((params->spp_flags & SPP_SACKDELAY_ENABLE) && params->spp_sackdelay) {
if (trans) {
trans->sackdelay =
msecs_to_jiffies(params->spp_sackdelay);
@@ -2157,7 +2201,11 @@ static int sctp_apply_peer_addr_params(struct sctp_paddrparams *params,
}
}
- if (params->spp_pathmaxrxt) {
+ /* Note that unless the spp_flag is set to SPP_PMTUD_ENABLE the value
+ * of this field is ignored. Note also that a value of zero
+ * indicates the current setting should be left unchanged.
+ */
+ if ((params->spp_flags & SPP_PMTUD_ENABLE) && params->spp_pathmaxrxt) {
if (trans) {
trans->pathmaxrxt = params->spp_pathmaxrxt;
} else if (asoc) {
@@ -2249,7 +2297,7 @@ static int sctp_setsockopt_peer_addr_params(struct sock *sk,
return 0;
}
-/* 7.1.24. Delayed Ack Timer (SCTP_DELAYED_ACK_TIME)
+/* 7.1.23. Delayed Ack Timer (SCTP_DELAYED_ACK_TIME)
*
* This options will get or set the delayed ack timer. The time is set
* in milliseconds. If the assoc_id is 0, then this sets or gets the
@@ -2786,6 +2834,102 @@ static int sctp_setsockopt_context(struct sock *sk, char __user *optval,
return 0;
}
+/*
+ * 7.1.24. Get or set fragmented interleave (SCTP_FRAGMENT_INTERLEAVE)
+ *
+ * This options will at a minimum specify if the implementation is doing
+ * fragmented interleave. Fragmented interleave, for a one to many
+ * socket, is when subsequent calls to receive a message may return
+ * parts of messages from different associations. Some implementations
+ * may allow you to turn this value on or off. If so, when turned off,
+ * no fragment interleave will occur (which will cause a head of line
+ * blocking amongst multiple associations sharing the same one to many
+ * socket). When this option is turned on, then each receive call may
+ * come from a different association (thus the user must receive data
+ * with the extended calls (e.g. sctp_recvmsg) to keep track of which
+ * association each receive belongs to.
+ *
+ * This option takes a boolean value. A non-zero value indicates that
+ * fragmented interleave is on. A value of zero indicates that
+ * fragmented interleave is off.
+ *
+ * Note that it is important that an implementation that allows this
+ * option to be turned on, have it off by default. Otherwise an unaware
+ * application using the one to many model may become confused and act
+ * incorrectly.
+ */
+static int sctp_setsockopt_fragment_interleave(struct sock *sk,
+ char __user *optval,
+ int optlen)
+{
+ int val;
+
+ if (optlen != sizeof(int))
+ return -EINVAL;
+ if (get_user(val, (int __user *)optval))
+ return -EFAULT;
+
+ sctp_sk(sk)->frag_interleave = (val == 0) ? 0 : 1;
+
+ return 0;
+}
+
+/*
+ * 7.1.25. Set or Get the sctp partial delivery point
+ * (SCTP_PARTIAL_DELIVERY_POINT)
+ * This option will set or get the SCTP partial delivery point. This
+ * point is the size of a message where the partial delivery API will be
+ * invoked to help free up rwnd space for the peer. Setting this to a
+ * lower value will cause partial delivery's to happen more often. The
+ * calls argument is an integer that sets or gets the partial delivery
+ * point.
+ */
+static int sctp_setsockopt_partial_delivery_point(struct sock *sk,
+ char __user *optval,
+ int optlen)
+{
+ u32 val;
+
+ if (optlen != sizeof(u32))
+ return -EINVAL;
+ if (get_user(val, (int __user *)optval))
+ return -EFAULT;
+
+ sctp_sk(sk)->pd_point = val;
+
+ return 0; /* is this the right error code? */
+}
+
+/*
+ * 7.1.28. Set or Get the maximum burst (SCTP_MAX_BURST)
+ *
+ * This option will allow a user to change the maximum burst of packets
+ * that can be emitted by this association. Note that the default value
+ * is 4, and some implementations may restrict this setting so that it
+ * can only be lowered.
+ *
+ * NOTE: This text doesn't seem right. Do this on a socket basis with
+ * future associations inheriting the socket value.
+ */
+static int sctp_setsockopt_maxburst(struct sock *sk,
+ char __user *optval,
+ int optlen)
+{
+ int val;
+
+ if (optlen != sizeof(int))
+ return -EINVAL;
+ if (get_user(val, (int __user *)optval))
+ return -EFAULT;
+
+ if (val < 0)
+ return -EINVAL;
+
+ sctp_sk(sk)->max_burst = val;
+
+ return 0;
+}
+
/* API 6.2 setsockopt(), getsockopt()
*
* Applications use setsockopt() and getsockopt() to set or retrieve
@@ -2865,6 +3009,9 @@ SCTP_STATIC int sctp_setsockopt(struct sock *sk, int level, int optname,
case SCTP_DELAYED_ACK_TIME:
retval = sctp_setsockopt_delayed_ack_time(sk, optval, optlen);
break;
+ case SCTP_PARTIAL_DELIVERY_POINT:
+ retval = sctp_setsockopt_partial_delivery_point(sk, optval, optlen);
+ break;
case SCTP_INITMSG:
retval = sctp_setsockopt_initmsg(sk, optval, optlen);
@@ -2900,11 +3047,16 @@ SCTP_STATIC int sctp_setsockopt(struct sock *sk, int level, int optname,
case SCTP_CONTEXT:
retval = sctp_setsockopt_context(sk, optval, optlen);
break;
-
+ case SCTP_FRAGMENT_INTERLEAVE:
+ retval = sctp_setsockopt_fragment_interleave(sk, optval, optlen);
+ break;
+ case SCTP_MAX_BURST:
+ retval = sctp_setsockopt_maxburst(sk, optval, optlen);
+ break;
default:
retval = -ENOPROTOOPT;
break;
- };
+ }
sctp_release_sock(sk);
@@ -3060,6 +3212,7 @@ SCTP_STATIC int sctp_init_sock(struct sock *sk)
sp->default_timetolive = 0;
sp->default_rcv_context = 0;
+ sp->max_burst = sctp_max_burst;
/* Initialize default setup parameters. These parameters
* can be modified with the SCTP_INITMSG socket option or
@@ -3128,8 +3281,9 @@ SCTP_STATIC int sctp_init_sock(struct sock *sk)
sp->pf = sctp_get_pf_specific(sk->sk_family);
/* Control variables for partial data delivery. */
- sp->pd_mode = 0;
+ atomic_set(&sp->pd_mode, 0);
skb_queue_head_init(&sp->pd_lobby);
+ sp->frag_interleave = 0;
/* Create a per socket endpoint structure. Even if we
* change the data structure relationships, this may still
@@ -3636,7 +3790,7 @@ static int sctp_getsockopt_peer_addr_params(struct sock *sk, int len,
return 0;
}
-/* 7.1.24. Delayed Ack Timer (SCTP_DELAYED_ACK_TIME)
+/* 7.1.23. Delayed Ack Timer (SCTP_DELAYED_ACK_TIME)
*
* This options will get or set the delayed ack timer. The time is set
* in milliseconds. If the assoc_id is 0, then this sets or gets the
@@ -3841,7 +3995,7 @@ static int sctp_getsockopt_peer_addrs(struct sock *sk, int len,
memcpy(&temp, &from->ipaddr, sizeof(temp));
sctp_get_pf_specific(sk->sk_family)->addr_v4map(sp, &temp);
addrlen = sctp_get_af_specific(sk->sk_family)->sockaddr_len;
- if(space_left < addrlen)
+ if (space_left < addrlen)
return -ENOMEM;
if (copy_to_user(to, &temp, addrlen))
return -EFAULT;
@@ -3930,8 +4084,9 @@ done:
/* Helper function that copies local addresses to user and returns the number
* of addresses copied.
*/
-static int sctp_copy_laddrs_to_user_old(struct sock *sk, __u16 port, int max_addrs,
- void __user *to)
+static int sctp_copy_laddrs_old(struct sock *sk, __u16 port,
+ int max_addrs, void *to,
+ int *bytes_copied)
{
struct list_head *pos, *next;
struct sctp_sockaddr_entry *addr;
@@ -3948,10 +4103,10 @@ static int sctp_copy_laddrs_to_user_old(struct sock *sk, __u16 port, int max_add
sctp_get_pf_specific(sk->sk_family)->addr_v4map(sctp_sk(sk),
&temp);
addrlen = sctp_get_af_specific(temp.sa.sa_family)->sockaddr_len;
- if (copy_to_user(to, &temp, addrlen))
- return -EFAULT;
+ memcpy(to, &temp, addrlen);
to += addrlen;
+ *bytes_copied += addrlen;
cnt ++;
if (cnt >= max_addrs) break;
}
@@ -3959,8 +4114,8 @@ static int sctp_copy_laddrs_to_user_old(struct sock *sk, __u16 port, int max_add
return cnt;
}
-static int sctp_copy_laddrs_to_user(struct sock *sk, __u16 port,
- void __user **to, size_t space_left)
+static int sctp_copy_laddrs(struct sock *sk, __u16 port, void *to,
+ size_t space_left, int *bytes_copied)
{
struct list_head *pos, *next;
struct sctp_sockaddr_entry *addr;
@@ -3977,14 +4132,14 @@ static int sctp_copy_laddrs_to_user(struct sock *sk, __u16 port,
sctp_get_pf_specific(sk->sk_family)->addr_v4map(sctp_sk(sk),
&temp);
addrlen = sctp_get_af_specific(temp.sa.sa_family)->sockaddr_len;
- if(space_left<addrlen)
+ if (space_left < addrlen)
return -ENOMEM;
- if (copy_to_user(*to, &temp, addrlen))
- return -EFAULT;
+ memcpy(to, &temp, addrlen);
- *to += addrlen;
+ to += addrlen;
cnt ++;
space_left -= addrlen;
+ bytes_copied += addrlen;
}
return cnt;
@@ -4008,6 +4163,8 @@ static int sctp_getsockopt_local_addrs_old(struct sock *sk, int len,
int addrlen;
rwlock_t *addr_lock;
int err = 0;
+ void *addrs;
+ int bytes_copied = 0;
if (len != sizeof(struct sctp_getaddrs_old))
return -EINVAL;
@@ -4035,6 +4192,15 @@ static int sctp_getsockopt_local_addrs_old(struct sock *sk, int len,
to = getaddrs.addrs;
+ /* Allocate space for a local instance of packed array to hold all
+ * the data. We store addresses here first and then put write them
+ * to the user in one shot.
+ */
+ addrs = kmalloc(sizeof(union sctp_addr) * getaddrs.addr_num,
+ GFP_KERNEL);
+ if (!addrs)
+ return -ENOMEM;
+
sctp_read_lock(addr_lock);
/* If the endpoint is bound to 0.0.0.0 or ::0, get the valid
@@ -4044,13 +4210,9 @@ static int sctp_getsockopt_local_addrs_old(struct sock *sk, int len,
addr = list_entry(bp->address_list.next,
struct sctp_sockaddr_entry, list);
if (sctp_is_any(&addr->a)) {
- cnt = sctp_copy_laddrs_to_user_old(sk, bp->port,
- getaddrs.addr_num,
- to);
- if (cnt < 0) {
- err = cnt;
- goto unlock;
- }
+ cnt = sctp_copy_laddrs_old(sk, bp->port,
+ getaddrs.addr_num,
+ addrs, &bytes_copied);
goto copy_getaddrs;
}
}
@@ -4060,22 +4222,29 @@ static int sctp_getsockopt_local_addrs_old(struct sock *sk, int len,
memcpy(&temp, &addr->a, sizeof(temp));
sctp_get_pf_specific(sk->sk_family)->addr_v4map(sp, &temp);
addrlen = sctp_get_af_specific(temp.sa.sa_family)->sockaddr_len;
- if (copy_to_user(to, &temp, addrlen)) {
- err = -EFAULT;
- goto unlock;
- }
+ memcpy(addrs, &temp, addrlen);
to += addrlen;
+ bytes_copied += addrlen;
cnt ++;
if (cnt >= getaddrs.addr_num) break;
}
copy_getaddrs:
+ sctp_read_unlock(addr_lock);
+
+ /* copy the entire address list into the user provided space */
+ if (copy_to_user(to, addrs, bytes_copied)) {
+ err = -EFAULT;
+ goto error;
+ }
+
+ /* copy the leading structure back to user */
getaddrs.addr_num = cnt;
if (copy_to_user(optval, &getaddrs, sizeof(struct sctp_getaddrs_old)))
err = -EFAULT;
-unlock:
- sctp_read_unlock(addr_lock);
+error:
+ kfree(addrs);
return err;
}
@@ -4095,7 +4264,8 @@ static int sctp_getsockopt_local_addrs(struct sock *sk, int len,
rwlock_t *addr_lock;
int err = 0;
size_t space_left;
- int bytes_copied;
+ int bytes_copied = 0;
+ void *addrs;
if (len <= sizeof(struct sctp_getaddrs))
return -EINVAL;
@@ -4123,6 +4293,9 @@ static int sctp_getsockopt_local_addrs(struct sock *sk, int len,
to = optval + offsetof(struct sctp_getaddrs,addrs);
space_left = len - sizeof(struct sctp_getaddrs) -
offsetof(struct sctp_getaddrs,addrs);
+ addrs = kmalloc(space_left, GFP_KERNEL);
+ if (!addrs)
+ return -ENOMEM;
sctp_read_lock(addr_lock);
@@ -4133,11 +4306,11 @@ static int sctp_getsockopt_local_addrs(struct sock *sk, int len,
addr = list_entry(bp->address_list.next,
struct sctp_sockaddr_entry, list);
if (sctp_is_any(&addr->a)) {
- cnt = sctp_copy_laddrs_to_user(sk, bp->port,
- &to, space_left);
+ cnt = sctp_copy_laddrs(sk, bp->port, addrs,
+ space_left, &bytes_copied);
if (cnt < 0) {
err = cnt;
- goto unlock;
+ goto error;
}
goto copy_getaddrs;
}
@@ -4148,26 +4321,31 @@ static int sctp_getsockopt_local_addrs(struct sock *sk, int len,
memcpy(&temp, &addr->a, sizeof(temp));
sctp_get_pf_specific(sk->sk_family)->addr_v4map(sp, &temp);
addrlen = sctp_get_af_specific(temp.sa.sa_family)->sockaddr_len;
- if(space_left < addrlen)
- return -ENOMEM; /*fixme: right error?*/
- if (copy_to_user(to, &temp, addrlen)) {
- err = -EFAULT;
- goto unlock;
+ if (space_left < addrlen) {
+ err = -ENOMEM; /*fixme: right error?*/
+ goto error;
}
+ memcpy(addrs, &temp, addrlen);
to += addrlen;
+ bytes_copied += addrlen;
cnt ++;
space_left -= addrlen;
}
copy_getaddrs:
+ sctp_read_unlock(addr_lock);
+
+ if (copy_to_user(to, addrs, bytes_copied)) {
+ err = -EFAULT;
+ goto error;
+ }
if (put_user(cnt, &((struct sctp_getaddrs __user *)optval)->addr_num))
return -EFAULT;
- bytes_copied = ((char __user *)to) - optval;
if (put_user(bytes_copied, optlen))
return -EFAULT;
-unlock:
- sctp_read_unlock(addr_lock);
+error:
+ kfree(addrs);
return err;
}
@@ -4530,6 +4708,77 @@ static int sctp_getsockopt_maxseg(struct sock *sk, int len,
return 0;
}
+/*
+ * 7.1.24. Get or set fragmented interleave (SCTP_FRAGMENT_INTERLEAVE)
+ * (chapter and verse is quoted at sctp_setsockopt_fragment_interleave())
+ */
+static int sctp_getsockopt_fragment_interleave(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)->frag_interleave;
+ if (put_user(len, optlen))
+ return -EFAULT;
+ if (copy_to_user(optval, &val, len))
+ return -EFAULT;
+
+ return 0;
+}
+
+/*
+ * 7.1.25. Set or Get the sctp partial delivery point
+ * (chapter and verse is quoted at sctp_setsockopt_partial_delivery_point())
+ */
+static int sctp_getsockopt_partial_delivery_point(struct sock *sk, int len,
+ char __user *optval,
+ int __user *optlen)
+{
+ u32 val;
+
+ if (len < sizeof(u32))
+ return -EINVAL;
+
+ len = sizeof(u32);
+
+ val = sctp_sk(sk)->pd_point;
+ if (put_user(len, optlen))
+ return -EFAULT;
+ if (copy_to_user(optval, &val, len))
+ return -EFAULT;
+
+ return -ENOTSUPP;
+}
+
+/*
+ * 7.1.28. Set or Get the maximum burst (SCTP_MAX_BURST)
+ * (chapter and verse is quoted at sctp_setsockopt_maxburst())
+ */
+static int sctp_getsockopt_maxburst(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)->max_burst;
+ if (put_user(len, optlen))
+ return -EFAULT;
+ if (copy_to_user(optval, &val, len))
+ return -EFAULT;
+
+ return -ENOTSUPP;
+}
+
SCTP_STATIC int sctp_getsockopt(struct sock *sk, int level, int optname,
char __user *optval, int __user *optlen)
{
@@ -4642,10 +4891,21 @@ SCTP_STATIC int sctp_getsockopt(struct sock *sk, int level, int optname,
case SCTP_CONTEXT:
retval = sctp_getsockopt_context(sk, len, optval, optlen);
break;
+ case SCTP_FRAGMENT_INTERLEAVE:
+ retval = sctp_getsockopt_fragment_interleave(sk, len, optval,
+ optlen);
+ break;
+ case SCTP_PARTIAL_DELIVERY_POINT:
+ retval = sctp_getsockopt_partial_delivery_point(sk, len, optval,
+ optlen);
+ break;
+ case SCTP_MAX_BURST:
+ retval = sctp_getsockopt_maxburst(sk, len, optval, optlen);
+ break;
default:
retval = -ENOPROTOOPT;
break;
- };
+ }
sctp_release_sock(sk);
return retval;
@@ -4760,7 +5020,8 @@ pp_found:
struct hlist_node *node;
SCTP_DEBUG_PRINTK("sctp_get_port() found a possible match\n");
- if (pp->fastreuse && sk->sk_reuse)
+ if (pp->fastreuse && sk->sk_reuse &&
+ sk->sk_state != SCTP_SS_LISTENING)
goto success;
/* Run through the list of sockets bound to the port
@@ -4777,7 +5038,8 @@ pp_found:
struct sctp_endpoint *ep2;
ep2 = sctp_sk(sk2)->ep;
- if (reuse && sk2->sk_reuse)
+ if (reuse && sk2->sk_reuse &&
+ sk2->sk_state != SCTP_SS_LISTENING)
continue;
if (sctp_bind_addr_match(&ep2->base.bind_addr, addr,
@@ -4798,9 +5060,13 @@ pp_not_found:
* if sk->sk_reuse is too (that is, if the caller requested
* SO_REUSEADDR on this socket -sk-).
*/
- if (hlist_empty(&pp->owner))
- pp->fastreuse = sk->sk_reuse ? 1 : 0;
- else if (pp->fastreuse && !sk->sk_reuse)
+ if (hlist_empty(&pp->owner)) {
+ if (sk->sk_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))
pp->fastreuse = 0;
/* We are set, so fill up all the data in the hash table
@@ -4808,8 +5074,8 @@ pp_not_found:
* sockets FIXME: Blurry, NPI (ipg).
*/
success:
- inet_sk(sk)->num = snum;
if (!sctp_sk(sk)->bind_hash) {
+ inet_sk(sk)->num = snum;
sk_add_bind_node(sk, &pp->owner);
sctp_sk(sk)->bind_hash = pp;
}
@@ -4882,12 +5148,16 @@ SCTP_STATIC int sctp_seqpacket_listen(struct sock *sk, int backlog)
* This is not currently spelled out in the SCTP sockets
* extensions draft, but follows the practice as seen in TCP
* sockets.
+ *
+ * Additionally, turn off fastreuse flag since we are not listening
*/
+ sk->sk_state = SCTP_SS_LISTENING;
if (!ep->base.bind_addr.port) {
if (sctp_autobind(sk))
return -EAGAIN;
- }
- sk->sk_state = SCTP_SS_LISTENING;
+ } else
+ sctp_sk(sk)->bind_hash->fastreuse = 0;
+
sctp_hash_endpoint(ep);
return 0;
}
@@ -4925,11 +5195,13 @@ SCTP_STATIC int sctp_stream_listen(struct sock *sk, int backlog)
* extensions draft, but follows the practice as seen in TCP
* sockets.
*/
+ sk->sk_state = SCTP_SS_LISTENING;
if (!ep->base.bind_addr.port) {
if (sctp_autobind(sk))
return -EAGAIN;
- }
- sk->sk_state = SCTP_SS_LISTENING;
+ } else
+ sctp_sk(sk)->bind_hash->fastreuse = 0;
+
sk->sk_max_ack_backlog = backlog;
sctp_hash_endpoint(ep);
return 0;
@@ -4970,7 +5242,8 @@ int sctp_inet_listen(struct socket *sock, int backlog)
break;
default:
break;
- };
+ }
+
if (err)
goto cleanup;
@@ -5233,7 +5506,7 @@ SCTP_STATIC int sctp_msghdr_parse(const struct msghdr *msg,
default:
return -EINVAL;
- };
+ }
}
return 0;
}
@@ -5638,6 +5911,36 @@ void sctp_wait_for_close(struct sock *sk, long timeout)
finish_wait(sk->sk_sleep, &wait);
}
+static void sctp_sock_rfree_frag(struct sk_buff *skb)
+{
+ struct sk_buff *frag;
+
+ if (!skb->data_len)
+ goto done;
+
+ /* Don't forget the fragments. */
+ for (frag = skb_shinfo(skb)->frag_list; frag; frag = frag->next)
+ sctp_sock_rfree_frag(frag);
+
+done:
+ sctp_sock_rfree(skb);
+}
+
+static void sctp_skb_set_owner_r_frag(struct sk_buff *skb, struct sock *sk)
+{
+ struct sk_buff *frag;
+
+ if (!skb->data_len)
+ goto done;
+
+ /* Don't forget the fragments. */
+ for (frag = skb_shinfo(skb)->frag_list; frag; frag = frag->next)
+ sctp_skb_set_owner_r_frag(frag, sk);
+
+done:
+ sctp_skb_set_owner_r(skb, sk);
+}
+
/* Populate the fields of the newsk from the oldsk and migrate the assoc
* and its messages to the newsk.
*/
@@ -5692,10 +5995,10 @@ static void sctp_sock_migrate(struct sock *oldsk, struct sock *newsk,
sctp_skb_for_each(skb, &oldsk->sk_receive_queue, tmp) {
event = sctp_skb2event(skb);
if (event->asoc == assoc) {
- sctp_sock_rfree(skb);
+ sctp_sock_rfree_frag(skb);
__skb_unlink(skb, &oldsk->sk_receive_queue);
__skb_queue_tail(&newsk->sk_receive_queue, skb);
- sctp_skb_set_owner_r(skb, newsk);
+ sctp_skb_set_owner_r_frag(skb, newsk);
}
}
@@ -5706,9 +6009,9 @@ static void sctp_sock_migrate(struct sock *oldsk, struct sock *newsk,
* 3) Peeling off non-partial delivery; move pd_lobby to receive_queue.
*/
skb_queue_head_init(&newsp->pd_lobby);
- sctp_sk(newsk)->pd_mode = assoc->ulpq.pd_mode;
+ atomic_set(&sctp_sk(newsk)->pd_mode, assoc->ulpq.pd_mode);
- if (sctp_sk(oldsk)->pd_mode) {
+ if (atomic_read(&sctp_sk(oldsk)->pd_mode)) {
struct sk_buff_head *queue;
/* Decide which queue to move pd_lobby skbs to. */
@@ -5723,10 +6026,10 @@ static void sctp_sock_migrate(struct sock *oldsk, struct sock *newsk,
sctp_skb_for_each(skb, &oldsp->pd_lobby, tmp) {
event = sctp_skb2event(skb);
if (event->asoc == assoc) {
- sctp_sock_rfree(skb);
+ sctp_sock_rfree_frag(skb);
__skb_unlink(skb, &oldsp->pd_lobby);
__skb_queue_tail(queue, skb);
- sctp_skb_set_owner_r(skb, newsk);
+ sctp_skb_set_owner_r_frag(skb, newsk);
}
}
@@ -5734,8 +6037,18 @@ static void sctp_sock_migrate(struct sock *oldsk, struct sock *newsk,
* delivery to finish.
*/
if (assoc->ulpq.pd_mode)
- sctp_clear_pd(oldsk);
+ sctp_clear_pd(oldsk, NULL);
+
+ }
+
+ sctp_skb_for_each(skb, &assoc->ulpq.reasm, tmp) {
+ sctp_sock_rfree_frag(skb);
+ sctp_skb_set_owner_r_frag(skb, newsk);
+ }
+ sctp_skb_for_each(skb, &assoc->ulpq.lobby, tmp) {
+ sctp_sock_rfree_frag(skb);
+ sctp_skb_set_owner_r_frag(skb, newsk);
}
/* Set the type of socket to indicate that it is peeled off from the
diff --git a/net/sctp/transport.c b/net/sctp/transport.c
index 4d8c2ab864f..961df275d5b 100644
--- a/net/sctp/transport.c
+++ b/net/sctp/transport.c
@@ -507,7 +507,7 @@ void sctp_transport_lower_cwnd(struct sctp_transport *transport,
transport->cwnd = max(transport->cwnd/2,
4*transport->asoc->pathmtu);
break;
- };
+ }
transport->partial_bytes_acked = 0;
SCTP_DEBUG_PRINTK("%s: transport: %p reason: %d cwnd: "
diff --git a/net/sctp/ulpevent.c b/net/sctp/ulpevent.c
index 2e11bc8d5d3..661ea2dd78b 100644
--- a/net/sctp/ulpevent.c
+++ b/net/sctp/ulpevent.c
@@ -131,19 +131,54 @@ static inline void sctp_ulpevent_release_owner(struct sctp_ulpevent *event)
struct sctp_ulpevent *sctp_ulpevent_make_assoc_change(
const struct sctp_association *asoc,
__u16 flags, __u16 state, __u16 error, __u16 outbound,
- __u16 inbound, gfp_t gfp)
+ __u16 inbound, struct sctp_chunk *chunk, gfp_t gfp)
{
struct sctp_ulpevent *event;
struct sctp_assoc_change *sac;
struct sk_buff *skb;
- event = sctp_ulpevent_new(sizeof(struct sctp_assoc_change),
+ /* If the lower layer passed in the chunk, it will be
+ * an ABORT, so we need to include it in the sac_info.
+ */
+ if (chunk) {
+ /* sctp_inqu_pop() has allready pulled off the chunk
+ * header. We need to put it back temporarily
+ */
+ skb_push(chunk->skb, sizeof(sctp_chunkhdr_t));
+
+ /* Copy the chunk data to a new skb and reserve enough
+ * head room to use as notification.
+ */
+ skb = skb_copy_expand(chunk->skb,
+ sizeof(struct sctp_assoc_change), 0, gfp);
+
+ if (!skb)
+ goto fail;
+
+ /* put back the chunk header now that we have a copy */
+ skb_pull(chunk->skb, sizeof(sctp_chunkhdr_t));
+
+ /* Embed the event fields inside the cloned skb. */
+ event = sctp_skb2event(skb);
+ sctp_ulpevent_init(event, MSG_NOTIFICATION, skb->truesize);
+
+ /* Include the notification structure */
+ sac = (struct sctp_assoc_change *)
+ skb_push(skb, sizeof(struct sctp_assoc_change));
+
+ /* Trim the buffer to the right length. */
+ skb_trim(skb, sizeof(struct sctp_assoc_change) +
+ ntohs(chunk->chunk_hdr->length));
+ } else {
+ event = sctp_ulpevent_new(sizeof(struct sctp_assoc_change),
MSG_NOTIFICATION, gfp);
- if (!event)
- goto fail;
- skb = sctp_event2skb(event);
- sac = (struct sctp_assoc_change *)
- skb_put(skb, sizeof(struct sctp_assoc_change));
+ if (!event)
+ goto fail;
+
+ skb = sctp_event2skb(event);
+ sac = (struct sctp_assoc_change *) skb_put(skb,
+ sizeof(struct sctp_assoc_change));
+ }
/* Socket Extensions for SCTP
* 5.3.1.1 SCTP_ASSOC_CHANGE
diff --git a/net/sctp/ulpqueue.c b/net/sctp/ulpqueue.c
index bfb197e37da..34eb977a204 100644
--- a/net/sctp/ulpqueue.c
+++ b/net/sctp/ulpqueue.c
@@ -138,26 +138,59 @@ int sctp_ulpq_tail_data(struct sctp_ulpq *ulpq, struct sctp_chunk *chunk,
/* Clear the partial delivery mode for this socket. Note: This
* assumes that no association is currently in partial delivery mode.
*/
-int sctp_clear_pd(struct sock *sk)
+int sctp_clear_pd(struct sock *sk, struct sctp_association *asoc)
{
struct sctp_sock *sp = sctp_sk(sk);
- sp->pd_mode = 0;
- if (!skb_queue_empty(&sp->pd_lobby)) {
- struct list_head *list;
- sctp_skb_list_tail(&sp->pd_lobby, &sk->sk_receive_queue);
- list = (struct list_head *)&sctp_sk(sk)->pd_lobby;
- INIT_LIST_HEAD(list);
- return 1;
+ if (atomic_dec_and_test(&sp->pd_mode)) {
+ /* This means there are no other associations in PD, so
+ * we can go ahead and clear out the lobby in one shot
+ */
+ if (!skb_queue_empty(&sp->pd_lobby)) {
+ struct list_head *list;
+ sctp_skb_list_tail(&sp->pd_lobby, &sk->sk_receive_queue);
+ list = (struct list_head *)&sctp_sk(sk)->pd_lobby;
+ INIT_LIST_HEAD(list);
+ return 1;
+ }
+ } else {
+ /* There are other associations in PD, so we only need to
+ * pull stuff out of the lobby that belongs to the
+ * associations that is exiting PD (all of its notifications
+ * are posted here).
+ */
+ if (!skb_queue_empty(&sp->pd_lobby) && asoc) {
+ struct sk_buff *skb, *tmp;
+ struct sctp_ulpevent *event;
+
+ sctp_skb_for_each(skb, &sp->pd_lobby, tmp) {
+ event = sctp_skb2event(skb);
+ if (event->asoc == asoc) {
+ __skb_unlink(skb, &sp->pd_lobby);
+ __skb_queue_tail(&sk->sk_receive_queue,
+ skb);
+ }
+ }
+ }
}
+
return 0;
}
+/* Set the pd_mode on the socket and ulpq */
+static void sctp_ulpq_set_pd(struct sctp_ulpq *ulpq)
+{
+ struct sctp_sock *sp = sctp_sk(ulpq->asoc->base.sk);
+
+ atomic_inc(&sp->pd_mode);
+ ulpq->pd_mode = 1;
+}
+
/* Clear the pd_mode and restart any pending messages waiting for delivery. */
static int sctp_ulpq_clear_pd(struct sctp_ulpq *ulpq)
{
ulpq->pd_mode = 0;
- return sctp_clear_pd(ulpq->asoc->base.sk);
+ return sctp_clear_pd(ulpq->asoc->base.sk, ulpq->asoc);
}
/* If the SKB of 'event' is on a list, it is the first such member
@@ -187,18 +220,35 @@ int sctp_ulpq_tail_event(struct sctp_ulpq *ulpq, struct sctp_ulpevent *event)
* the association the cause of the partial delivery.
*/
- if (!sctp_sk(sk)->pd_mode) {
+ if (atomic_read(&sctp_sk(sk)->pd_mode) == 0) {
queue = &sk->sk_receive_queue;
- } else if (ulpq->pd_mode) {
- if (event->msg_flags & MSG_NOTIFICATION)
- queue = &sctp_sk(sk)->pd_lobby;
- else {
- clear_pd = event->msg_flags & MSG_EOR;
- queue = &sk->sk_receive_queue;
+ } else {
+ if (ulpq->pd_mode) {
+ /* If the association is in partial delivery, we
+ * need to finish delivering the partially processed
+ * packet before passing any other data. This is
+ * because we don't truly support stream interleaving.
+ */
+ if ((event->msg_flags & MSG_NOTIFICATION) ||
+ (SCTP_DATA_NOT_FRAG ==
+ (event->msg_flags & SCTP_DATA_FRAG_MASK)))
+ queue = &sctp_sk(sk)->pd_lobby;
+ else {
+ clear_pd = event->msg_flags & MSG_EOR;
+ queue = &sk->sk_receive_queue;
+ }
+ } else {
+ /*
+ * If fragment interleave is enabled, we
+ * can queue this to the recieve queue instead
+ * of the lobby.
+ */
+ if (sctp_sk(sk)->frag_interleave)
+ queue = &sk->sk_receive_queue;
+ else
+ queue = &sctp_sk(sk)->pd_lobby;
}
- } else
- queue = &sctp_sk(sk)->pd_lobby;
-
+ }
/* If we are harvesting multiple skbs they will be
* collected on a list.
@@ -341,7 +391,7 @@ static struct sctp_ulpevent *sctp_make_reassembled_event(struct sk_buff_head *qu
break;
pos->next = pnext;
pos = pnext;
- };
+ }
event = sctp_skb2event(f_frag);
SCTP_INC_STATS(SCTP_MIB_REASMUSRMSGS);
@@ -360,6 +410,11 @@ static inline struct sctp_ulpevent *sctp_ulpq_retrieve_reassembled(struct sctp_u
struct sk_buff *first_frag = NULL;
__u32 ctsn, next_tsn;
struct sctp_ulpevent *retval = NULL;
+ struct sk_buff *pd_first = NULL;
+ struct sk_buff *pd_last = NULL;
+ size_t pd_len = 0;
+ struct sctp_association *asoc;
+ u32 pd_point;
/* Initialized to 0 just to avoid compiler warning message. Will
* never be used with this value. It is referenced only after it
@@ -375,6 +430,10 @@ static inline struct sctp_ulpevent *sctp_ulpq_retrieve_reassembled(struct sctp_u
* we expect to find the remaining middle fragments and the last
* fragment in order. If not, first_frag is reset to NULL and we
* start the next pass when we find another first fragment.
+ *
+ * There is a potential to do partial delivery if user sets
+ * SCTP_PARTIAL_DELIVERY_POINT option. Lets count some things here
+ * to see if can do PD.
*/
skb_queue_walk(&ulpq->reasm, pos) {
cevent = sctp_skb2event(pos);
@@ -382,14 +441,32 @@ static inline struct sctp_ulpevent *sctp_ulpq_retrieve_reassembled(struct sctp_u
switch (cevent->msg_flags & SCTP_DATA_FRAG_MASK) {
case SCTP_DATA_FIRST_FRAG:
+ /* If this "FIRST_FRAG" is the first
+ * element in the queue, then count it towards
+ * possible PD.
+ */
+ if (pos == ulpq->reasm.next) {
+ pd_first = pos;
+ pd_last = pos;
+ pd_len = pos->len;
+ } else {
+ pd_first = NULL;
+ pd_last = NULL;
+ pd_len = 0;
+ }
+
first_frag = pos;
next_tsn = ctsn + 1;
break;
case SCTP_DATA_MIDDLE_FRAG:
- if ((first_frag) && (ctsn == next_tsn))
+ if ((first_frag) && (ctsn == next_tsn)) {
next_tsn++;
- else
+ if (pd_first) {
+ pd_last = pos;
+ pd_len += pos->len;
+ }
+ } else
first_frag = NULL;
break;
@@ -399,8 +476,29 @@ static inline struct sctp_ulpevent *sctp_ulpq_retrieve_reassembled(struct sctp_u
else
first_frag = NULL;
break;
- };
+ }
+ }
+ asoc = ulpq->asoc;
+ if (pd_first) {
+ /* Make sure we can enter partial deliver.
+ * We can trigger partial delivery only if framgent
+ * interleave is set, or the socket is not already
+ * in partial delivery.
+ */
+ if (!sctp_sk(asoc->base.sk)->frag_interleave &&
+ atomic_read(&sctp_sk(asoc->base.sk)->pd_mode))
+ goto done;
+
+ cevent = sctp_skb2event(pd_first);
+ pd_point = sctp_sk(asoc->base.sk)->pd_point;
+ if (pd_point && pd_point <= pd_len) {
+ retval = sctp_make_reassembled_event(&ulpq->reasm,
+ pd_first,
+ pd_last);
+ if (retval)
+ sctp_ulpq_set_pd(ulpq);
+ }
}
done:
return retval;
@@ -458,7 +556,7 @@ static inline struct sctp_ulpevent *sctp_ulpq_retrieve_partial(struct sctp_ulpq
goto done;
default:
return NULL;
- };
+ }
}
/* We have the reassembled event. There is no need to look
@@ -550,7 +648,7 @@ static inline struct sctp_ulpevent *sctp_ulpq_retrieve_first(struct sctp_ulpq *u
break;
default:
return NULL;
- };
+ }
}
/* We have the reassembled event. There is no need to look
@@ -819,19 +917,29 @@ void sctp_ulpq_partial_delivery(struct sctp_ulpq *ulpq,
{
struct sctp_ulpevent *event;
struct sctp_association *asoc;
+ struct sctp_sock *sp;
asoc = ulpq->asoc;
+ sp = sctp_sk(asoc->base.sk);
- /* Are we already in partial delivery mode? */
- if (!sctp_sk(asoc->base.sk)->pd_mode) {
+ /* If the association is already in Partial Delivery mode
+ * we have noting to do.
+ */
+ if (ulpq->pd_mode)
+ return;
+ /* If the user enabled fragment interleave socket option,
+ * multiple associations can enter partial delivery.
+ * Otherwise, we can only enter partial delivery if the
+ * socket is not in partial deliver mode.
+ */
+ if (sp->frag_interleave || atomic_read(&sp->pd_mode) == 0) {
/* Is partial delivery possible? */
event = sctp_ulpq_retrieve_first(ulpq);
/* Send event to the ULP. */
if (event) {
sctp_ulpq_tail_event(ulpq, event);
- sctp_sk(asoc->base.sk)->pd_mode = 1;
- ulpq->pd_mode = 1;
+ sctp_ulpq_set_pd(ulpq);
return;
}
}
generated by cgit v1.2.3-70-g09d2 (git 2.46.0) at 2024-10-01 15:34:17 +0000