diff options
author | Linus Torvalds <torvalds@linux-foundation.org> | 2016-07-27 12:03:20 -0700 |
---|---|---|
committer | Linus Torvalds <torvalds@linux-foundation.org> | 2016-07-27 12:03:20 -0700 |
commit | 468fc7ed5537615efe671d94248446ac24679773 (patch) | |
tree | 27bc9de792e863d6ec1630927b77ac9e7dabb38a /net/sctp | |
parent | 08fd8c17686c6b09fa410a26d516548dd80ff147 (diff) | |
parent | 36232012344b8db67052432742deaf17f82e70e6 (diff) | |
download | lwn-468fc7ed5537615efe671d94248446ac24679773.tar.gz lwn-468fc7ed5537615efe671d94248446ac24679773.zip |
Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next
Pull networking updates from David Miller:
1) Unified UDP encapsulation offload methods for drivers, from
Alexander Duyck.
2) Make DSA binding more sane, from Andrew Lunn.
3) Support QCA9888 chips in ath10k, from Anilkumar Kolli.
4) Several workqueue usage cleanups, from Bhaktipriya Shridhar.
5) Add XDP (eXpress Data Path), essentially running BPF programs on RX
packets as soon as the device sees them, with the option to mirror
the packet on TX via the same interface. From Brenden Blanco and
others.
6) Allow qdisc/class stats dumps to run lockless, from Eric Dumazet.
7) Add VLAN support to b53 and bcm_sf2, from Florian Fainelli.
8) Simplify netlink conntrack entry layout, from Florian Westphal.
9) Add ipv4 forwarding support to mlxsw spectrum driver, from Ido
Schimmel, Yotam Gigi, and Jiri Pirko.
10) Add SKB array infrastructure and convert tun and macvtap over to it.
From Michael S Tsirkin and Jason Wang.
11) Support qdisc packet injection in pktgen, from John Fastabend.
12) Add neighbour monitoring framework to TIPC, from Jon Paul Maloy.
13) Add NV congestion control support to TCP, from Lawrence Brakmo.
14) Add GSO support to SCTP, from Marcelo Ricardo Leitner.
15) Allow GRO and RPS to function on macsec devices, from Paolo Abeni.
16) Support MPLS over IPV4, from Simon Horman.
* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (1622 commits)
xgene: Fix build warning with ACPI disabled.
be2net: perform temperature query in adapter regardless of its interface state
l2tp: Correctly return -EBADF from pppol2tp_getname.
net/mlx5_core/health: Remove deprecated create_singlethread_workqueue
net: ipmr/ip6mr: update lastuse on entry change
macsec: ensure rx_sa is set when validation is disabled
tipc: dump monitor attributes
tipc: add a function to get the bearer name
tipc: get monitor threshold for the cluster
tipc: make cluster size threshold for monitoring configurable
tipc: introduce constants for tipc address validation
net: neigh: disallow transition to NUD_STALE if lladdr is unchanged in neigh_update()
MAINTAINERS: xgene: Add driver and documentation path
Documentation: dtb: xgene: Add MDIO node
dtb: xgene: Add MDIO node
drivers: net: xgene: ethtool: Use phy_ethtool_gset and sset
drivers: net: xgene: Use exported functions
drivers: net: xgene: Enable MDIO driver
drivers: net: xgene: Add backward compatibility
drivers: net: phy: xgene: Add MDIO driver
...
Diffstat (limited to 'net/sctp')
-rw-r--r-- | net/sctp/Makefile | 3 | ||||
-rw-r--r-- | net/sctp/associola.c | 1 | ||||
-rw-r--r-- | net/sctp/chunk.c | 25 | ||||
-rw-r--r-- | net/sctp/endpointola.c | 1 | ||||
-rw-r--r-- | net/sctp/input.c | 68 | ||||
-rw-r--r-- | net/sctp/inqueue.c | 85 | ||||
-rw-r--r-- | net/sctp/ipv6.c | 15 | ||||
-rw-r--r-- | net/sctp/offload.c | 119 | ||||
-rw-r--r-- | net/sctp/output.c | 378 | ||||
-rw-r--r-- | net/sctp/outqueue.c | 99 | ||||
-rw-r--r-- | net/sctp/protocol.c | 9 | ||||
-rw-r--r-- | net/sctp/sm_make_chunk.c | 47 | ||||
-rw-r--r-- | net/sctp/sm_sideeffect.c | 4 | ||||
-rw-r--r-- | net/sctp/sm_statefuns.c | 9 | ||||
-rw-r--r-- | net/sctp/socket.c | 293 | ||||
-rw-r--r-- | net/sctp/ulpevent.c | 17 |
16 files changed, 944 insertions, 229 deletions
diff --git a/net/sctp/Makefile b/net/sctp/Makefile index 0fca5824ad0e..6c4f7496cec6 100644 --- a/net/sctp/Makefile +++ b/net/sctp/Makefile @@ -11,7 +11,8 @@ sctp-y := sm_statetable.o sm_statefuns.o sm_sideeffect.o \ transport.o chunk.o sm_make_chunk.o ulpevent.o \ inqueue.o outqueue.o ulpqueue.o \ tsnmap.o bind_addr.o socket.o primitive.o \ - output.o input.o debug.o ssnmap.o auth.o + output.o input.o debug.o ssnmap.o auth.o \ + offload.o sctp_probe-y := probe.o diff --git a/net/sctp/associola.c b/net/sctp/associola.c index e1849f3714ad..1c23060c41a6 100644 --- a/net/sctp/associola.c +++ b/net/sctp/associola.c @@ -268,6 +268,7 @@ static struct sctp_association *sctp_association_init(struct sctp_association *a goto fail_init; asoc->active_key_id = ep->active_key_id; + asoc->prsctp_enable = ep->prsctp_enable; /* Save the hmacs and chunks list into this association */ if (ep->auth_hmacs_list) diff --git a/net/sctp/chunk.c b/net/sctp/chunk.c index 1eb94bf18ef4..a55e54738b81 100644 --- a/net/sctp/chunk.c +++ b/net/sctp/chunk.c @@ -335,13 +335,32 @@ errout: /* Check whether this message has expired. */ int sctp_chunk_abandoned(struct sctp_chunk *chunk) { - struct sctp_datamsg *msg = chunk->msg; + if (!chunk->asoc->prsctp_enable || + !SCTP_PR_POLICY(chunk->sinfo.sinfo_flags)) { + struct sctp_datamsg *msg = chunk->msg; + + if (!msg->can_abandon) + return 0; + + if (time_after(jiffies, msg->expires_at)) + return 1; - if (!msg->can_abandon) return 0; + } - if (time_after(jiffies, msg->expires_at)) + if (SCTP_PR_TTL_ENABLED(chunk->sinfo.sinfo_flags) && + time_after(jiffies, chunk->prsctp_param)) { + if (chunk->sent_count) + chunk->asoc->abandoned_sent[SCTP_PR_INDEX(TTL)]++; + else + chunk->asoc->abandoned_unsent[SCTP_PR_INDEX(TTL)]++; + return 1; + } else if (SCTP_PR_RTX_ENABLED(chunk->sinfo.sinfo_flags) && + chunk->sent_count > chunk->prsctp_param) { + chunk->asoc->abandoned_sent[SCTP_PR_INDEX(RTX)]++; return 1; + } + /* PRIO policy is processed by sendmsg, not here */ return 0; } diff --git a/net/sctp/endpointola.c b/net/sctp/endpointola.c index 9d494e35e7f9..1f03065686fe 100644 --- a/net/sctp/endpointola.c +++ b/net/sctp/endpointola.c @@ -163,6 +163,7 @@ static struct sctp_endpoint *sctp_endpoint_init(struct sctp_endpoint *ep, */ ep->auth_hmacs_list = auth_hmacs; ep->auth_chunk_list = auth_chunks; + ep->prsctp_enable = net->sctp.prsctp_enable; return ep; diff --git a/net/sctp/input.c b/net/sctp/input.c index 47cf4604d19c..c182db7d691f 100644 --- a/net/sctp/input.c +++ b/net/sctp/input.c @@ -90,17 +90,6 @@ static inline int sctp_rcv_checksum(struct net *net, struct sk_buff *skb) return 0; } -struct sctp_input_cb { - union { - struct inet_skb_parm h4; -#if IS_ENABLED(CONFIG_IPV6) - struct inet6_skb_parm h6; -#endif - } header; - struct sctp_chunk *chunk; -}; -#define SCTP_INPUT_CB(__skb) ((struct sctp_input_cb *)&((__skb)->cb[0])) - /* * This is the routine which IP calls when receiving an SCTP packet. */ @@ -123,31 +112,35 @@ int sctp_rcv(struct sk_buff *skb) __SCTP_INC_STATS(net, SCTP_MIB_INSCTPPACKS); - if (skb_linearize(skb)) + /* If packet is too small to contain a single chunk, let's not + * waste time on it anymore. + */ + if (skb->len < sizeof(struct sctphdr) + sizeof(struct sctp_chunkhdr) + + skb_transport_offset(skb)) goto discard_it; - /* Pull up the IP and SCTP headers. */ - __skb_pull(skb, skb_transport_offset(skb)); - if (skb->len < sizeof(struct sctphdr)) + if (!pskb_may_pull(skb, sizeof(struct sctphdr))) goto discard_it; + /* Pull up the IP header. */ + __skb_pull(skb, skb_transport_offset(skb)); + skb->csum_valid = 0; /* Previous value not applicable */ if (skb_csum_unnecessary(skb)) __skb_decr_checksum_unnecessary(skb); - else if (!sctp_checksum_disable && sctp_rcv_checksum(net, skb) < 0) + else if (!sctp_checksum_disable && + !(skb_shinfo(skb)->gso_type & SKB_GSO_SCTP) && + sctp_rcv_checksum(net, skb) < 0) goto discard_it; skb->csum_valid = 1; - skb_pull(skb, sizeof(struct sctphdr)); - - /* Make sure we at least have chunk headers worth of data left. */ - if (skb->len < sizeof(struct sctp_chunkhdr)) - goto discard_it; + __skb_pull(skb, sizeof(struct sctphdr)); family = ipver2af(ip_hdr(skb)->version); af = sctp_get_af_specific(family); if (unlikely(!af)) goto discard_it; + SCTP_INPUT_CB(skb)->af = af; /* Initialize local addresses for lookups. */ af->from_skb(&src, skb, 1); @@ -328,6 +321,7 @@ int sctp_backlog_rcv(struct sock *sk, struct sk_buff *skb) */ sk = rcvr->sk; + local_bh_disable(); bh_lock_sock(sk); if (sock_owned_by_user(sk)) { @@ -339,6 +333,7 @@ int sctp_backlog_rcv(struct sock *sk, struct sk_buff *skb) sctp_inq_push(inqueue, chunk); bh_unlock_sock(sk); + local_bh_enable(); /* If the chunk was backloged again, don't drop refs */ if (backloged) @@ -657,19 +652,23 @@ out_unlock: */ static int sctp_rcv_ootb(struct sk_buff *skb) { - sctp_chunkhdr_t *ch; - __u8 *ch_end; - - ch = (sctp_chunkhdr_t *) skb->data; + sctp_chunkhdr_t *ch, _ch; + int ch_end, offset = 0; /* Scan through all the chunks in the packet. */ do { + /* Make sure we have at least the header there */ + if (offset + sizeof(sctp_chunkhdr_t) > skb->len) + break; + + ch = skb_header_pointer(skb, offset, sizeof(*ch), &_ch); + /* Break out if chunk length is less then minimal. */ if (ntohs(ch->length) < sizeof(sctp_chunkhdr_t)) break; - ch_end = ((__u8 *)ch) + WORD_ROUND(ntohs(ch->length)); - if (ch_end > skb_tail_pointer(skb)) + ch_end = offset + WORD_ROUND(ntohs(ch->length)); + if (ch_end > skb->len) break; /* RFC 8.4, 2) If the OOTB packet contains an ABORT chunk, the @@ -694,8 +693,8 @@ static int sctp_rcv_ootb(struct sk_buff *skb) if (SCTP_CID_INIT == ch->type && (void *)ch != skb->data) goto discard; - ch = (sctp_chunkhdr_t *) ch_end; - } while (ch_end < skb_tail_pointer(skb)); + offset = ch_end; + } while (ch_end < skb->len); return 0; @@ -1170,6 +1169,17 @@ static struct sctp_association *__sctp_rcv_lookup_harder(struct net *net, { sctp_chunkhdr_t *ch; + /* We do not allow GSO frames here as we need to linearize and + * then cannot guarantee frame boundaries. This shouldn't be an + * issue as packets hitting this are mostly INIT or INIT-ACK and + * those cannot be on GSO-style anyway. + */ + if ((skb_shinfo(skb)->gso_type & SKB_GSO_SCTP) == SKB_GSO_SCTP) + return NULL; + + if (skb_linearize(skb)) + return NULL; + ch = (sctp_chunkhdr_t *) skb->data; /* The code below will attempt to walk the chunk and extract diff --git a/net/sctp/inqueue.c b/net/sctp/inqueue.c index 9d87bba0ff1d..c30ddb0f3190 100644 --- a/net/sctp/inqueue.c +++ b/net/sctp/inqueue.c @@ -89,12 +89,10 @@ void sctp_inq_push(struct sctp_inq *q, struct sctp_chunk *chunk) * Eventually, we should clean up inqueue to not rely * on the BH related data structures. */ - local_bh_disable(); list_add_tail(&chunk->list, &q->in_chunk_list); if (chunk->asoc) chunk->asoc->stats.ipackets++; q->immediate.func(&q->immediate); - local_bh_enable(); } /* Peek at the next chunk on the inqeue. */ @@ -130,13 +128,25 @@ struct sctp_chunk *sctp_inq_pop(struct sctp_inq *queue) * at this time. */ - if ((chunk = queue->in_progress)) { + chunk = queue->in_progress; + if (chunk) { /* There is a packet that we have been working on. * Any post processing work to do before we move on? */ if (chunk->singleton || chunk->end_of_packet || chunk->pdiscard) { + if (chunk->head_skb == chunk->skb) { + chunk->skb = skb_shinfo(chunk->skb)->frag_list; + goto new_skb; + } + if (chunk->skb->next) { + chunk->skb = chunk->skb->next; + goto new_skb; + } + + if (chunk->head_skb) + chunk->skb = chunk->head_skb; sctp_chunk_free(chunk); chunk = queue->in_progress = NULL; } else { @@ -152,34 +162,71 @@ struct sctp_chunk *sctp_inq_pop(struct sctp_inq *queue) if (!chunk) { struct list_head *entry; +next_chunk: /* Is the queue empty? */ - if (list_empty(&queue->in_chunk_list)) + entry = sctp_list_dequeue(&queue->in_chunk_list); + if (!entry) return NULL; - entry = queue->in_chunk_list.next; - chunk = queue->in_progress = - list_entry(entry, struct sctp_chunk, list); - list_del_init(entry); + chunk = list_entry(entry, struct sctp_chunk, list); + + /* Linearize if it's not GSO */ + if ((skb_shinfo(chunk->skb)->gso_type & SKB_GSO_SCTP) != SKB_GSO_SCTP && + skb_is_nonlinear(chunk->skb)) { + if (skb_linearize(chunk->skb)) { + __SCTP_INC_STATS(dev_net(chunk->skb->dev), SCTP_MIB_IN_PKT_DISCARDS); + sctp_chunk_free(chunk); + goto next_chunk; + } + + /* Update sctp_hdr as it probably changed */ + chunk->sctp_hdr = sctp_hdr(chunk->skb); + } + + if ((skb_shinfo(chunk->skb)->gso_type & SKB_GSO_SCTP) == SKB_GSO_SCTP) { + /* GSO-marked skbs but without frags, handle + * them normally + */ + if (skb_shinfo(chunk->skb)->frag_list) + chunk->head_skb = chunk->skb; + + /* skbs with "cover letter" */ + if (chunk->head_skb && chunk->skb->data_len == chunk->skb->len) + chunk->skb = skb_shinfo(chunk->skb)->frag_list; + + if (WARN_ON(!chunk->skb)) { + __SCTP_INC_STATS(dev_net(chunk->skb->dev), SCTP_MIB_IN_PKT_DISCARDS); + sctp_chunk_free(chunk); + goto next_chunk; + } + } + + if (chunk->asoc) + sock_rps_save_rxhash(chunk->asoc->base.sk, chunk->skb); + + queue->in_progress = chunk; +new_skb: /* This is the first chunk in the packet. */ - chunk->singleton = 1; ch = (sctp_chunkhdr_t *) chunk->skb->data; + chunk->singleton = 1; chunk->data_accepted = 0; + chunk->pdiscard = 0; + chunk->auth = 0; + chunk->has_asconf = 0; + chunk->end_of_packet = 0; + if (chunk->head_skb) { + struct sctp_input_cb + *cb = SCTP_INPUT_CB(chunk->skb), + *head_cb = SCTP_INPUT_CB(chunk->head_skb); - if (chunk->asoc) - sock_rps_save_rxhash(chunk->asoc->base.sk, chunk->skb); + cb->chunk = head_cb->chunk; + cb->af = head_cb->af; + } } chunk->chunk_hdr = ch; chunk->chunk_end = ((__u8 *)ch) + WORD_ROUND(ntohs(ch->length)); - /* In the unlikely case of an IP reassembly, the skb could be - * non-linear. If so, update chunk_end so that it doesn't go past - * the skb->tail. - */ - if (unlikely(skb_is_nonlinear(chunk->skb))) { - 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. */ diff --git a/net/sctp/ipv6.c b/net/sctp/ipv6.c index 0657d18a85bf..f473779e8b1c 100644 --- a/net/sctp/ipv6.c +++ b/net/sctp/ipv6.c @@ -420,6 +420,7 @@ 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; + /* Always called on head skb, so this is safe */ sh = sctp_hdr(skb); if (is_saddr) { *port = sh->source; @@ -559,6 +560,7 @@ static int sctp_v6_is_any(const union sctp_addr *addr) static int sctp_v6_available(union sctp_addr *addr, struct sctp_sock *sp) { int type; + struct net *net = sock_net(&sp->inet.sk); const struct in6_addr *in6 = (const struct in6_addr *)&addr->v6.sin6_addr; type = ipv6_addr_type(in6); @@ -573,7 +575,8 @@ static int sctp_v6_available(union sctp_addr *addr, struct sctp_sock *sp) if (!(type & IPV6_ADDR_UNICAST)) return 0; - return ipv6_chk_addr(sock_net(&sp->inet.sk), in6, NULL, 0); + return sp->inet.freebind || net->ipv6.sysctl.ip_nonlocal_bind || + ipv6_chk_addr(net, in6, NULL, 0); } /* This function checks if the address is a valid address to be used for @@ -710,8 +713,7 @@ static int sctp_v6_addr_to_user(struct sctp_sock *sp, union sctp_addr *addr) /* Where did this skb come from? */ static int sctp_v6_skb_iif(const struct sk_buff *skb) { - struct inet6_skb_parm *opt = (struct inet6_skb_parm *) skb->cb; - return opt->iif; + return IP6CB(skb)->iif; } /* Was this packet marked by Explicit Congestion Notification? */ @@ -780,15 +782,14 @@ static void sctp_inet6_skb_msgname(struct sk_buff *skb, char *msgname, if (ip_hdr(skb)->version == 4) { addr->v4.sin_family = AF_INET; addr->v4.sin_port = sh->source; - addr->v4.sin_addr.s_addr = ip_hdr(skb)->saddr; + addr->v4.sin_addr.s_addr = ip_hdr(skb)->saddr; } else { addr->v6.sin6_family = AF_INET6; addr->v6.sin6_flowinfo = 0; addr->v6.sin6_port = sh->source; addr->v6.sin6_addr = ipv6_hdr(skb)->saddr; if (ipv6_addr_type(&addr->v6.sin6_addr) & IPV6_ADDR_LINKLOCAL) { - struct sctp_ulpevent *ev = sctp_skb2event(skb); - addr->v6.sin6_scope_id = ev->iif; + addr->v6.sin6_scope_id = sctp_v6_skb_iif(skb); } } @@ -955,7 +956,7 @@ static const struct proto_ops inet6_seqpacket_ops = { .setsockopt = sock_common_setsockopt, .getsockopt = sock_common_getsockopt, .sendmsg = inet_sendmsg, - .recvmsg = sock_common_recvmsg, + .recvmsg = inet_recvmsg, .mmap = sock_no_mmap, #ifdef CONFIG_COMPAT .compat_setsockopt = compat_sock_common_setsockopt, diff --git a/net/sctp/offload.c b/net/sctp/offload.c new file mode 100644 index 000000000000..7e869d0cca69 --- /dev/null +++ b/net/sctp/offload.c @@ -0,0 +1,119 @@ +/* + * sctp_offload - GRO/GSO Offloading for SCTP + * + * Copyright (C) 2015, Marcelo Ricardo Leitner <marcelo.leitner@gmail.com> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + */ + +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + +#include <linux/kernel.h> +#include <linux/kprobes.h> +#include <linux/socket.h> +#include <linux/sctp.h> +#include <linux/proc_fs.h> +#include <linux/vmalloc.h> +#include <linux/module.h> +#include <linux/kfifo.h> +#include <linux/time.h> +#include <net/net_namespace.h> + +#include <linux/skbuff.h> +#include <net/sctp/sctp.h> +#include <net/sctp/checksum.h> +#include <net/protocol.h> + +static __le32 sctp_gso_make_checksum(struct sk_buff *skb) +{ + skb->ip_summed = CHECKSUM_NONE; + return sctp_compute_cksum(skb, skb_transport_offset(skb)); +} + +static struct sk_buff *sctp_gso_segment(struct sk_buff *skb, + netdev_features_t features) +{ + struct sk_buff *segs = ERR_PTR(-EINVAL); + struct sctphdr *sh; + + sh = sctp_hdr(skb); + if (!pskb_may_pull(skb, sizeof(*sh))) + goto out; + + __skb_pull(skb, sizeof(*sh)); + + if (skb_gso_ok(skb, features | NETIF_F_GSO_ROBUST)) { + /* Packet is from an untrusted source, reset gso_segs. */ + struct skb_shared_info *pinfo = skb_shinfo(skb); + struct sk_buff *frag_iter; + + pinfo->gso_segs = 0; + if (skb->len != skb->data_len) { + /* Means we have chunks in here too */ + pinfo->gso_segs++; + } + + skb_walk_frags(skb, frag_iter) + pinfo->gso_segs++; + + segs = NULL; + goto out; + } + + segs = skb_segment(skb, features | NETIF_F_HW_CSUM); + if (IS_ERR(segs)) + goto out; + + /* All that is left is update SCTP CRC if necessary */ + if (!(features & NETIF_F_SCTP_CRC)) { + for (skb = segs; skb; skb = skb->next) { + if (skb->ip_summed == CHECKSUM_PARTIAL) { + sh = sctp_hdr(skb); + sh->checksum = sctp_gso_make_checksum(skb); + } + } + } + +out: + return segs; +} + +static const struct net_offload sctp_offload = { + .callbacks = { + .gso_segment = sctp_gso_segment, + }, +}; + +static const struct net_offload sctp6_offload = { + .callbacks = { + .gso_segment = sctp_gso_segment, + }, +}; + +int __init sctp_offload_init(void) +{ + int ret; + + ret = inet_add_offload(&sctp_offload, IPPROTO_SCTP); + if (ret) + goto out; + + ret = inet6_add_offload(&sctp6_offload, IPPROTO_SCTP); + if (ret) + goto ipv4; + + return ret; + +ipv4: + inet_del_offload(&sctp_offload, IPPROTO_SCTP); +out: + return ret; +} diff --git a/net/sctp/output.c b/net/sctp/output.c index 9844fe573029..7425f6c23888 100644 --- a/net/sctp/output.c +++ b/net/sctp/output.c @@ -84,18 +84,42 @@ static void sctp_packet_reset(struct sctp_packet *packet) struct sctp_packet *sctp_packet_config(struct sctp_packet *packet, __u32 vtag, int ecn_capable) { - struct sctp_chunk *chunk = NULL; + struct sctp_transport *tp = packet->transport; + struct sctp_association *asoc = tp->asoc; pr_debug("%s: packet:%p vtag:0x%x\n", __func__, packet, vtag); packet->vtag = vtag; + if (asoc && tp->dst) { + struct sock *sk = asoc->base.sk; + + rcu_read_lock(); + if (__sk_dst_get(sk) != tp->dst) { + dst_hold(tp->dst); + sk_setup_caps(sk, tp->dst); + } + + if (sk_can_gso(sk)) { + struct net_device *dev = tp->dst->dev; + + packet->max_size = dev->gso_max_size; + } else { + packet->max_size = asoc->pathmtu; + } + rcu_read_unlock(); + + } else { + packet->max_size = tp->pathmtu; + } + if (ecn_capable && sctp_packet_empty(packet)) { - chunk = sctp_get_ecne_prepend(packet->transport->asoc); + struct sctp_chunk *chunk; /* If there a is a prepend chunk stick it on the list before * any other chunks get appended. */ + chunk = sctp_get_ecne_prepend(asoc); if (chunk) sctp_packet_append_chunk(packet, chunk); } @@ -158,7 +182,8 @@ sctp_xmit_t sctp_packet_transmit_chunk(struct sctp_packet *packet, sctp_xmit_t retval; int error = 0; - pr_debug("%s: packet:%p chunk:%p\n", __func__, packet, chunk); + pr_debug("%s: packet:%p size:%Zu chunk:%p size:%d\n", __func__, + packet, packet->size, chunk, chunk->skb ? chunk->skb->len : -1); switch ((retval = (sctp_packet_append_chunk(packet, chunk)))) { case SCTP_XMIT_PMTU_FULL: @@ -291,6 +316,8 @@ static sctp_xmit_t __sctp_packet_append_chunk(struct sctp_packet *packet, packet->has_data = 1; /* timestamp the chunk for rtx purposes */ chunk->sent_at = jiffies; + /* Mainly used for prsctp RTX policy */ + chunk->sent_count++; break; case SCTP_CID_COOKIE_ECHO: packet->has_cookie_echo = 1; @@ -381,12 +408,15 @@ int sctp_packet_transmit(struct sctp_packet *packet, gfp_t gfp) struct sctp_transport *tp = packet->transport; struct sctp_association *asoc = tp->asoc; struct sctphdr *sh; - struct sk_buff *nskb; + struct sk_buff *nskb = NULL, *head = NULL; struct sctp_chunk *chunk, *tmp; struct sock *sk; int err = 0; int padding; /* How much padding do we need? */ + int pkt_size; __u8 has_data = 0; + int gso = 0; + int pktcount = 0; struct dst_entry *dst; unsigned char *auth = NULL; /* pointer to auth in skb data */ @@ -400,18 +430,37 @@ int sctp_packet_transmit(struct sctp_packet *packet, gfp_t gfp) chunk = list_entry(packet->chunk_list.next, struct sctp_chunk, list); sk = chunk->skb->sk; - /* Allocate the new skb. */ - nskb = alloc_skb(packet->size + MAX_HEADER, gfp); - if (!nskb) + /* Allocate the head skb, or main one if not in GSO */ + if (packet->size > tp->pathmtu && !packet->ipfragok) { + if (sk_can_gso(sk)) { + gso = 1; + pkt_size = packet->overhead; + } else { + /* If this happens, we trash this packet and try + * to build a new one, hopefully correct this + * time. Application may notice this error. + */ + pr_err_once("Trying to GSO but underlying device doesn't support it."); + goto nomem; + } + } else { + pkt_size = packet->size; + } + head = alloc_skb(pkt_size + MAX_HEADER, gfp); + if (!head) goto nomem; + if (gso) { + NAPI_GRO_CB(head)->last = head; + skb_shinfo(head)->gso_type = sk->sk_gso_type; + } /* Make sure the outbound skb has enough header room reserved. */ - skb_reserve(nskb, packet->overhead + MAX_HEADER); + skb_reserve(head, packet->overhead + MAX_HEADER); /* Set the owning socket so that we know where to get the * destination IP address. */ - sctp_packet_set_owner_w(nskb, sk); + sctp_packet_set_owner_w(head, sk); if (!sctp_transport_dst_check(tp)) { sctp_transport_route(tp, NULL, sctp_sk(sk)); @@ -422,11 +471,11 @@ int sctp_packet_transmit(struct sctp_packet *packet, gfp_t gfp) dst = dst_clone(tp->dst); if (!dst) goto no_route; - skb_dst_set(nskb, dst); + skb_dst_set(head, dst); /* Build the SCTP header. */ - sh = (struct sctphdr *)skb_push(nskb, sizeof(struct sctphdr)); - skb_reset_transport_header(nskb); + sh = (struct sctphdr *)skb_push(head, sizeof(struct sctphdr)); + skb_reset_transport_header(head); sh->source = htons(packet->source_port); sh->dest = htons(packet->destination_port); @@ -441,90 +490,143 @@ int sctp_packet_transmit(struct sctp_packet *packet, gfp_t gfp) sh->vtag = htonl(packet->vtag); sh->checksum = 0; - /** - * 6.10 Bundling - * - * An endpoint bundles chunks by simply including multiple - * chunks in one outbound SCTP packet. ... - */ - - /** - * 3.2 Chunk Field Descriptions - * - * The total length of a chunk (including Type, Length and - * Value fields) MUST be a multiple of 4 bytes. If the length - * of the chunk is not a multiple of 4 bytes, the sender MUST - * pad the chunk with all zero bytes and this padding is not - * included in the chunk length field. The sender should - * never pad with more than 3 bytes. - * - * [This whole comment explains WORD_ROUND() below.] - */ - pr_debug("***sctp_transmit_packet***\n"); - list_for_each_entry_safe(chunk, tmp, &packet->chunk_list, list) { - list_del_init(&chunk->list); - if (sctp_chunk_is_data(chunk)) { - /* 6.3.1 C4) When data is in flight and when allowed - * by rule C5, a new RTT measurement MUST be made each - * round trip. Furthermore, new RTT measurements - * SHOULD be made no more than once per round-trip - * for a given destination transport address. - */ + do { + /* Set up convenience variables... */ + chunk = list_entry(packet->chunk_list.next, struct sctp_chunk, list); + pktcount++; - if (!chunk->resent && !tp->rto_pending) { - chunk->rtt_in_progress = 1; - tp->rto_pending = 1; + /* Calculate packet size, so it fits in PMTU. Leave + * other chunks for the next packets. + */ + if (gso) { + pkt_size = packet->overhead; + list_for_each_entry(chunk, &packet->chunk_list, list) { + int padded = WORD_ROUND(chunk->skb->len); + + if (pkt_size + padded > tp->pathmtu) + break; + pkt_size += padded; } - has_data = 1; - } + /* Allocate a new skb. */ + nskb = alloc_skb(pkt_size + MAX_HEADER, gfp); + if (!nskb) + goto nomem; - padding = WORD_ROUND(chunk->skb->len) - chunk->skb->len; - if (padding) - memset(skb_put(chunk->skb, padding), 0, padding); + /* Make sure the outbound skb has enough header + * room reserved. + */ + skb_reserve(nskb, packet->overhead + MAX_HEADER); + } else { + nskb = head; + } - /* if this is the auth chunk that we are adding, - * store pointer where it will be added and put - * the auth into the packet. + /** + * 3.2 Chunk Field Descriptions + * + * The total length of a chunk (including Type, Length and + * Value fields) MUST be a multiple of 4 bytes. If the length + * of the chunk is not a multiple of 4 bytes, the sender MUST + * pad the chunk with all zero bytes and this padding is not + * included in the chunk length field. The sender should + * never pad with more than 3 bytes. + * + * [This whole comment explains WORD_ROUND() below.] */ - if (chunk == packet->auth) - auth = skb_tail_pointer(nskb); - memcpy(skb_put(nskb, chunk->skb->len), + pkt_size -= packet->overhead; + list_for_each_entry_safe(chunk, tmp, &packet->chunk_list, list) { + list_del_init(&chunk->list); + if (sctp_chunk_is_data(chunk)) { + /* 6.3.1 C4) When data is in flight and when allowed + * by rule C5, a new RTT measurement MUST be made each + * round trip. Furthermore, new RTT measurements + * SHOULD be made no more than once per round-trip + * for a given destination transport address. + */ + + if (!chunk->resent && !tp->rto_pending) { + chunk->rtt_in_progress = 1; + tp->rto_pending = 1; + } + + has_data = 1; + } + + padding = WORD_ROUND(chunk->skb->len) - chunk->skb->len; + if (padding) + memset(skb_put(chunk->skb, padding), 0, padding); + + /* if this is the auth chunk that we are adding, + * store pointer where it will be added and put + * the auth into the packet. + */ + if (chunk == packet->auth) + auth = skb_tail_pointer(nskb); + + memcpy(skb_put(nskb, chunk->skb->len), chunk->skb->data, chunk->skb->len); - pr_debug("*** Chunk:%p[%s] %s 0x%x, length:%d, chunk->skb->len:%d, " - "rtt_in_progress:%d\n", chunk, - sctp_cname(SCTP_ST_CHUNK(chunk->chunk_hdr->type)), - chunk->has_tsn ? "TSN" : "No TSN", - chunk->has_tsn ? ntohl(chunk->subh.data_hdr->tsn) : 0, - ntohs(chunk->chunk_hdr->length), chunk->skb->len, - chunk->rtt_in_progress); - - /* - * If this is a control chunk, this is our last - * reference. Free data chunks after they've been - * acknowledged or have failed. + pr_debug("*** Chunk:%p[%s] %s 0x%x, length:%d, chunk->skb->len:%d, rtt_in_progress:%d\n", + chunk, + sctp_cname(SCTP_ST_CHUNK(chunk->chunk_hdr->type)), + chunk->has_tsn ? "TSN" : "No TSN", + chunk->has_tsn ? ntohl(chunk->subh.data_hdr->tsn) : 0, + ntohs(chunk->chunk_hdr->length), chunk->skb->len, + chunk->rtt_in_progress); + + /* If this is a control chunk, this is our last + * reference. Free data chunks after they've been + * acknowledged or have failed. + * Re-queue auth chunks if needed. + */ + pkt_size -= WORD_ROUND(chunk->skb->len); + + if (!sctp_chunk_is_data(chunk) && chunk != packet->auth) + sctp_chunk_free(chunk); + + if (!pkt_size) + break; + } + + /* SCTP-AUTH, Section 6.2 + * The sender MUST calculate the MAC as described in RFC2104 [2] + * using the hash function H as described by the MAC Identifier and + * the shared association key K based on the endpoint pair shared key + * described by the shared key identifier. The 'data' used for the + * computation of the AUTH-chunk is given by the AUTH chunk with its + * HMAC field set to zero (as shown in Figure 6) followed by all + * chunks that are placed after the AUTH chunk in the SCTP packet. */ - if (!sctp_chunk_is_data(chunk)) - sctp_chunk_free(chunk); - } + if (auth) + sctp_auth_calculate_hmac(asoc, nskb, + (struct sctp_auth_chunk *)auth, + gfp); + + if (packet->auth) { + if (!list_empty(&packet->chunk_list)) { + /* We will generate more packets, so re-queue + * auth chunk. + */ + list_add(&chunk->list, &packet->chunk_list); + } else { + sctp_chunk_free(packet->auth); + packet->auth = NULL; + } + } - /* SCTP-AUTH, Section 6.2 - * The sender MUST calculate the MAC as described in RFC2104 [2] - * using the hash function H as described by the MAC Identifier and - * the shared association key K based on the endpoint pair shared key - * described by the shared key identifier. The 'data' used for the - * computation of the AUTH-chunk is given by the AUTH chunk with its - * HMAC field set to zero (as shown in Figure 6) followed by all - * chunks that are placed after the AUTH chunk in the SCTP packet. - */ - if (auth) - sctp_auth_calculate_hmac(asoc, nskb, - (struct sctp_auth_chunk *)auth, - gfp); + if (!gso) + break; + + if (skb_gro_receive(&head, nskb)) + goto nomem; + nskb = NULL; + if (WARN_ON_ONCE(skb_shinfo(head)->gso_segs >= + sk->sk_gso_max_segs)) + goto nomem; + } while (!list_empty(&packet->chunk_list)); /* 2) Calculate the Adler-32 checksum of the whole packet, * including the SCTP common header and all the @@ -532,16 +634,18 @@ int sctp_packet_transmit(struct sctp_packet *packet, gfp_t gfp) * * Note: Adler-32 is no longer applicable, as has been replaced * by CRC32-C as described in <draft-ietf-tsvwg-sctpcsum-02.txt>. + * + * If it's a GSO packet, it's postponed to sctp_skb_segment. */ - if (!sctp_checksum_disable) { - if (!(dst->dev->features & NETIF_F_SCTP_CRC) || - (dst_xfrm(dst) != NULL) || packet->ipfragok) { - sh->checksum = sctp_compute_cksum(nskb, 0); + if (!sctp_checksum_disable || gso) { + if (!gso && (!(dst->dev->features & NETIF_F_SCTP_CRC) || + dst_xfrm(dst) || packet->ipfragok)) { + sh->checksum = sctp_compute_cksum(head, 0); } else { /* no need to seed pseudo checksum for SCTP */ - nskb->ip_summed = CHECKSUM_PARTIAL; - nskb->csum_start = skb_transport_header(nskb) - nskb->head; - nskb->csum_offset = offsetof(struct sctphdr, checksum); + head->ip_summed = CHECKSUM_PARTIAL; + head->csum_start = skb_transport_header(head) - head->head; + head->csum_offset = offsetof(struct sctphdr, checksum); } } @@ -557,7 +661,7 @@ int sctp_packet_transmit(struct sctp_packet *packet, gfp_t gfp) * Note: The works for IPv6 layer checks this bit too later * in transmission. See IP6_ECN_flow_xmit(). */ - tp->af_specific->ecn_capable(nskb->sk); + tp->af_specific->ecn_capable(sk); /* Set up the IP options. */ /* BUG: not implemented @@ -566,7 +670,7 @@ int sctp_packet_transmit(struct sctp_packet *packet, gfp_t gfp) /* Dump that on IP! */ if (asoc) { - asoc->stats.opackets++; + asoc->stats.opackets += pktcount; if (asoc->peer.last_sent_to != tp) /* Considering the multiple CPU scenario, this is a * "correcter" place for last_sent_to. --xguo @@ -589,16 +693,36 @@ int sctp_packet_transmit(struct sctp_packet *packet, gfp_t gfp) } } - pr_debug("***sctp_transmit_packet*** skb->len:%d\n", nskb->len); + pr_debug("***sctp_transmit_packet*** skb->len:%d\n", head->len); + + if (gso) { + /* Cleanup our debris for IP stacks */ + memset(head->cb, 0, max(sizeof(struct inet_skb_parm), + sizeof(struct inet6_skb_parm))); - nskb->ignore_df = packet->ipfragok; - tp->af_specific->sctp_xmit(nskb, tp); + skb_shinfo(head)->gso_segs = pktcount; + skb_shinfo(head)->gso_size = GSO_BY_FRAGS; + + /* We have to refresh this in case we are xmiting to + * more than one transport at a time + */ + rcu_read_lock(); + if (__sk_dst_get(sk) != tp->dst) { + dst_hold(tp->dst); + sk_setup_caps(sk, tp->dst); + } + rcu_read_unlock(); + } + head->ignore_df = packet->ipfragok; + tp->af_specific->sctp_xmit(head, tp); out: sctp_packet_reset(packet); return err; no_route: - kfree_skb(nskb); + kfree_skb(head); + if (nskb != head) + kfree_skb(nskb); if (asoc) IP_INC_STATS(sock_net(asoc->base.sk), IPSTATS_MIB_OUTNOROUTES); @@ -623,6 +747,8 @@ err: } goto out; nomem: + if (packet->auth && list_empty(&packet->auth->list)) + sctp_chunk_free(packet->auth); err = -ENOMEM; goto err; } @@ -751,39 +877,63 @@ static sctp_xmit_t sctp_packet_will_fit(struct sctp_packet *packet, struct sctp_chunk *chunk, u16 chunk_len) { - size_t psize; - size_t pmtu; - int too_big; + size_t psize, pmtu; sctp_xmit_t retval = SCTP_XMIT_OK; psize = packet->size; - pmtu = ((packet->transport->asoc) ? - (packet->transport->asoc->pathmtu) : - (packet->transport->pathmtu)); - - too_big = (psize + chunk_len > pmtu); + if (packet->transport->asoc) + pmtu = packet->transport->asoc->pathmtu; + else + pmtu = packet->transport->pathmtu; /* Decide if we need to fragment or resubmit later. */ - if (too_big) { - /* It's OK to fragmet at IP level if any one of the following + if (psize + chunk_len > pmtu) { + /* It's OK to fragment at IP level if any one of the following * is true: - * 1. The packet is empty (meaning this chunk is greater - * the MTU) - * 2. The chunk we are adding is a control chunk - * 3. The packet doesn't have any data in it yet and data - * requires authentication. + * 1. The packet is empty (meaning this chunk is greater + * the MTU) + * 2. The packet doesn't have any data in it yet and data + * requires authentication. */ - if (sctp_packet_empty(packet) || !sctp_chunk_is_data(chunk) || + if (sctp_packet_empty(packet) || (!packet->has_data && chunk->auth)) { /* We no longer do re-fragmentation. * Just fragment at the IP layer, if we * actually hit this condition */ packet->ipfragok = 1; - } else { - retval = SCTP_XMIT_PMTU_FULL; + goto out; } + + /* It is also okay to fragment if the chunk we are + * adding is a control chunk, but only if current packet + * is not a GSO one otherwise it causes fragmentation of + * a large frame. So in this case we allow the + * fragmentation by forcing it to be in a new packet. + */ + if (!sctp_chunk_is_data(chunk) && packet->has_data) + retval = SCTP_XMIT_PMTU_FULL; + + if (psize + chunk_len > packet->max_size) + /* Hit GSO/PMTU limit, gotta flush */ + retval = SCTP_XMIT_PMTU_FULL; + + if (!packet->transport->burst_limited && + psize + chunk_len > (packet->transport->cwnd >> 1)) + /* Do not allow a single GSO packet to use more + * than half of cwnd. + */ + retval = SCTP_XMIT_PMTU_FULL; + + if (packet->transport->burst_limited && + psize + chunk_len > (packet->transport->burst_limited >> 1)) + /* Do not allow a single GSO packet to use more + * than half of original cwnd. + */ + retval = SCTP_XMIT_PMTU_FULL; + /* Otherwise it will fit in the GSO packet */ } +out: return retval; } diff --git a/net/sctp/outqueue.c b/net/sctp/outqueue.c index 084718f9b3da..72e54a416af6 100644 --- a/net/sctp/outqueue.c +++ b/net/sctp/outqueue.c @@ -326,6 +326,9 @@ int sctp_outq_tail(struct sctp_outq *q, struct sctp_chunk *chunk, gfp_t gfp) sctp_chunk_hold(chunk); sctp_outq_tail_data(q, chunk); + if (chunk->asoc->prsctp_enable && + SCTP_PR_PRIO_ENABLED(chunk->sinfo.sinfo_flags)) + chunk->asoc->sent_cnt_removable++; if (chunk->chunk_hdr->flags & SCTP_DATA_UNORDERED) SCTP_INC_STATS(net, SCTP_MIB_OUTUNORDERCHUNKS); else @@ -372,6 +375,96 @@ static void sctp_insert_list(struct list_head *head, struct list_head *new) list_add_tail(new, head); } +static int sctp_prsctp_prune_sent(struct sctp_association *asoc, + struct sctp_sndrcvinfo *sinfo, + struct list_head *queue, int msg_len) +{ + struct sctp_chunk *chk, *temp; + + list_for_each_entry_safe(chk, temp, queue, transmitted_list) { + if (!SCTP_PR_PRIO_ENABLED(chk->sinfo.sinfo_flags) || + chk->prsctp_param <= sinfo->sinfo_timetolive) + continue; + + list_del_init(&chk->transmitted_list); + sctp_insert_list(&asoc->outqueue.abandoned, + &chk->transmitted_list); + + asoc->sent_cnt_removable--; + asoc->abandoned_sent[SCTP_PR_INDEX(PRIO)]++; + + if (!chk->tsn_gap_acked) { + if (chk->transport) + chk->transport->flight_size -= + sctp_data_size(chk); + asoc->outqueue.outstanding_bytes -= sctp_data_size(chk); + } + + msg_len -= SCTP_DATA_SNDSIZE(chk) + + sizeof(struct sk_buff) + + sizeof(struct sctp_chunk); + if (msg_len <= 0) + break; + } + + return msg_len; +} + +static int sctp_prsctp_prune_unsent(struct sctp_association *asoc, + struct sctp_sndrcvinfo *sinfo, + struct list_head *queue, int msg_len) +{ + struct sctp_chunk *chk, *temp; + + list_for_each_entry_safe(chk, temp, queue, list) { + if (!SCTP_PR_PRIO_ENABLED(chk->sinfo.sinfo_flags) || + chk->prsctp_param <= sinfo->sinfo_timetolive) + continue; + + list_del_init(&chk->list); + asoc->sent_cnt_removable--; + asoc->abandoned_unsent[SCTP_PR_INDEX(PRIO)]++; + + msg_len -= SCTP_DATA_SNDSIZE(chk) + + sizeof(struct sk_buff) + + sizeof(struct sctp_chunk); + sctp_chunk_free(chk); + if (msg_len <= 0) + break; + } + + return msg_len; +} + +/* Abandon the chunks according their priorities */ +void sctp_prsctp_prune(struct sctp_association *asoc, + struct sctp_sndrcvinfo *sinfo, int msg_len) +{ + struct sctp_transport *transport; + + if (!asoc->prsctp_enable || !asoc->sent_cnt_removable) + return; + + msg_len = sctp_prsctp_prune_sent(asoc, sinfo, + &asoc->outqueue.retransmit, + msg_len); + if (msg_len <= 0) + return; + + list_for_each_entry(transport, &asoc->peer.transport_addr_list, + transports) { + msg_len = sctp_prsctp_prune_sent(asoc, sinfo, + &transport->transmitted, + msg_len); + if (msg_len <= 0) + return; + } + + sctp_prsctp_prune_unsent(asoc, sinfo, + &asoc->outqueue.out_chunk_list, + msg_len); +} + /* Mark all the eligible packets on a transport for retransmission. */ void sctp_retransmit_mark(struct sctp_outq *q, struct sctp_transport *transport, @@ -962,6 +1055,9 @@ static int sctp_outq_flush(struct sctp_outq *q, int rtx_timeout, gfp_t gfp) /* Mark as failed send. */ sctp_chunk_fail(chunk, SCTP_ERROR_INV_STRM); + if (asoc->prsctp_enable && + SCTP_PR_PRIO_ENABLED(chunk->sinfo.sinfo_flags)) + asoc->sent_cnt_removable--; sctp_chunk_free(chunk); continue; } @@ -1251,6 +1347,9 @@ int sctp_outq_sack(struct sctp_outq *q, struct sctp_chunk *chunk) tsn = ntohl(tchunk->subh.data_hdr->tsn); if (TSN_lte(tsn, ctsn)) { list_del_init(&tchunk->transmitted_list); + if (asoc->prsctp_enable && + SCTP_PR_PRIO_ENABLED(chunk->sinfo.sinfo_flags)) + asoc->sent_cnt_removable--; sctp_chunk_free(tchunk); } } diff --git a/net/sctp/protocol.c b/net/sctp/protocol.c index d3d50daa248b..7b523e3f551f 100644 --- a/net/sctp/protocol.c +++ b/net/sctp/protocol.c @@ -240,6 +240,7 @@ 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; + /* Always called on head skb, so this is safe */ sh = sctp_hdr(skb); if (is_saddr) { *port = sh->source; @@ -1027,7 +1028,7 @@ static const struct proto_ops inet_seqpacket_ops = { .setsockopt = sock_common_setsockopt, /* IP_SOL IP_OPTION is a problem */ .getsockopt = sock_common_getsockopt, .sendmsg = inet_sendmsg, - .recvmsg = sock_common_recvmsg, + .recvmsg = inet_recvmsg, .mmap = sock_no_mmap, .sendpage = sock_no_sendpage, #ifdef CONFIG_COMPAT @@ -1479,7 +1480,8 @@ static __init int sctp_init(void) INIT_HLIST_HEAD(&sctp_port_hashtable[i].chain); } - if (sctp_transport_hashtable_init()) + status = sctp_transport_hashtable_init(); + if (status) goto err_thash_alloc; pr_info("Hash tables configured (bind %d/%d)\n", sctp_port_hashsize, @@ -1516,6 +1518,9 @@ static __init int sctp_init(void) if (status) goto err_v6_add_protocol; + if (sctp_offload_init() < 0) + pr_crit("%s: Cannot add SCTP protocol offload\n", __func__); + out: return status; err_v6_add_protocol: diff --git a/net/sctp/sm_make_chunk.c b/net/sctp/sm_make_chunk.c index 56f364d8f932..8c77b87a8565 100644 --- a/net/sctp/sm_make_chunk.c +++ b/net/sctp/sm_make_chunk.c @@ -108,14 +108,9 @@ static void sctp_control_set_owner_w(struct sctp_chunk *chunk) /* What was the inbound interface for this chunk? */ int sctp_chunk_iif(const struct sctp_chunk *chunk) { - struct sctp_af *af; - int iif = 0; - - af = sctp_get_af_specific(ipver2af(ip_hdr(chunk->skb)->version)); - if (af) - iif = af->skb_iif(chunk->skb); + struct sk_buff *skb = chunk->skb; - return iif; + return SCTP_INPUT_CB(skb)->af->skb_iif(skb); } /* RFC 2960 3.3.2 Initiation (INIT) (1) @@ -261,7 +256,7 @@ struct sctp_chunk *sctp_make_init(const struct sctp_association *asoc, chunksize += WORD_ROUND(SCTP_SAT_LEN(num_types)); chunksize += sizeof(ecap_param); - if (net->sctp.prsctp_enable) + if (asoc->prsctp_enable) chunksize += sizeof(prsctp_param); /* ADDIP: Section 4.2.7: @@ -355,7 +350,7 @@ struct sctp_chunk *sctp_make_init(const struct sctp_association *asoc, sctp_addto_param(retval, num_ext, extensions); } - if (net->sctp.prsctp_enable) + if (asoc->prsctp_enable) sctp_addto_chunk(retval, sizeof(prsctp_param), &prsctp_param); if (sp->adaptation_ind) { @@ -711,6 +706,20 @@ nodata: return retval; } +static void sctp_set_prsctp_policy(struct sctp_chunk *chunk, + const struct sctp_sndrcvinfo *sinfo) +{ + if (!chunk->asoc->prsctp_enable) + return; + + if (SCTP_PR_TTL_ENABLED(sinfo->sinfo_flags)) + chunk->prsctp_param = + jiffies + msecs_to_jiffies(sinfo->sinfo_timetolive); + else if (SCTP_PR_RTX_ENABLED(sinfo->sinfo_flags) || + SCTP_PR_PRIO_ENABLED(sinfo->sinfo_flags)) + chunk->prsctp_param = sinfo->sinfo_timetolive; +} + /* Make a DATA chunk for the given association from the provided * parameters. However, do not populate the data payload. */ @@ -744,6 +753,7 @@ struct sctp_chunk *sctp_make_datafrag_empty(struct sctp_association *asoc, retval->subh.data_hdr = sctp_addto_chunk(retval, sizeof(dp), &dp); memcpy(&retval->sinfo, sinfo, sizeof(struct sctp_sndrcvinfo)); + sctp_set_prsctp_policy(retval, sinfo); nodata: return retval; @@ -1585,7 +1595,6 @@ struct sctp_association *sctp_make_temp_asoc(const struct sctp_endpoint *ep, struct sctp_association *asoc; struct sk_buff *skb; sctp_scope_t scope; - struct sctp_af *af; /* Create the bare association. */ scope = sctp_scope(sctp_source(chunk)); @@ -1595,16 +1604,10 @@ 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(ip_hdr(skb)->version)); - if (unlikely(!af)) - goto fail; - af->from_skb(&asoc->c.peer_addr, skb, 1); + SCTP_INPUT_CB(skb)->af->from_skb(&asoc->c.peer_addr, skb, 1); + nodata: return asoc; - -fail: - sctp_association_free(asoc); - return NULL; } /* Build a cookie representing asoc. @@ -2024,8 +2027,8 @@ static void sctp_process_ext_param(struct sctp_association *asoc, for (i = 0; i < num_ext; i++) { switch (param.ext->chunks[i]) { case SCTP_CID_FWD_TSN: - if (net->sctp.prsctp_enable && !asoc->peer.prsctp_capable) - asoc->peer.prsctp_capable = 1; + if (asoc->prsctp_enable && !asoc->peer.prsctp_capable) + asoc->peer.prsctp_capable = 1; break; case SCTP_CID_AUTH: /* if the peer reports AUTH, assume that he @@ -2169,7 +2172,7 @@ static sctp_ierror_t sctp_verify_param(struct net *net, break; case SCTP_PARAM_FWD_TSN_SUPPORT: - if (net->sctp.prsctp_enable) + if (ep->prsctp_enable) break; goto fallthrough; @@ -2653,7 +2656,7 @@ do_addr_param: break; case SCTP_PARAM_FWD_TSN_SUPPORT: - if (net->sctp.prsctp_enable) { + if (asoc->prsctp_enable) { asoc->peer.prsctp_capable = 1; break; } diff --git a/net/sctp/sm_sideeffect.c b/net/sctp/sm_sideeffect.c index aa3712259368..12d45193357c 100644 --- a/net/sctp/sm_sideeffect.c +++ b/net/sctp/sm_sideeffect.c @@ -806,8 +806,10 @@ static void sctp_cmd_new_state(sctp_cmd_seq_t *cmds, /* Set the RCV_SHUTDOWN flag when a SHUTDOWN is received. */ if (sctp_state(asoc, SHUTDOWN_RECEIVED) && - sctp_sstate(sk, ESTABLISHED)) + sctp_sstate(sk, ESTABLISHED)) { + sk->sk_state = SCTP_SS_CLOSING; sk->sk_shutdown |= RCV_SHUTDOWN; + } } if (sctp_state(asoc, COOKIE_WAIT)) { diff --git a/net/sctp/sm_statefuns.c b/net/sctp/sm_statefuns.c index f1f08c8f277b..d88bb2b0b699 100644 --- a/net/sctp/sm_statefuns.c +++ b/net/sctp/sm_statefuns.c @@ -6118,14 +6118,11 @@ static int sctp_eat_data(const struct sctp_association *asoc, * chunk later. */ - if (!chunk->ecn_ce_done) { - struct sctp_af *af; + if (asoc->peer.ecn_capable && !chunk->ecn_ce_done) { + struct sctp_af *af = SCTP_INPUT_CB(chunk->skb)->af; chunk->ecn_ce_done = 1; - af = sctp_get_af_specific( - ipver2af(ip_hdr(chunk->skb)->version)); - - if (af && af->is_ce(chunk->skb) && asoc->peer.ecn_capable) { + if (af->is_ce(sctp_gso_headskb(chunk->skb))) { /* Do real work as sideffect. */ sctp_add_cmd_sf(commands, SCTP_CMD_ECN_CE, SCTP_U32(tsn)); diff --git a/net/sctp/socket.c b/net/sctp/socket.c index 67154b848aa9..8812e1bf6c1c 100644 --- a/net/sctp/socket.c +++ b/net/sctp/socket.c @@ -202,7 +202,7 @@ struct sctp_association *sctp_id2assoc(struct sock *sk, sctp_assoc_t id) * could be a TCP-style listening socket or a socket which * hasn't yet called connect() to establish an association. */ - if (!sctp_sstate(sk, ESTABLISHED)) + if (!sctp_sstate(sk, ESTABLISHED) && !sctp_sstate(sk, CLOSING)) return NULL; /* Get the first and the only association from the list. */ @@ -1068,7 +1068,7 @@ static int __sctp_connect(struct sock *sk, * is already connected. * It cannot be done even on a TCP-style listening socket. */ - if (sctp_sstate(sk, ESTABLISHED) || + if (sctp_sstate(sk, ESTABLISHED) || sctp_sstate(sk, CLOSING) || (sctp_style(sk, TCP) && sctp_sstate(sk, LISTENING))) { err = -EISCONN; goto out_free; @@ -1705,18 +1705,19 @@ static int sctp_sendmsg(struct sock *sk, struct msghdr *msg, size_t msg_len) if (msg_name) { /* Look for a matching association on the endpoint. */ asoc = sctp_endpoint_lookup_assoc(ep, &to, &transport); - if (!asoc) { - /* If we could not find a matching association on the - * endpoint, make sure that it is not a TCP-style - * socket that already has an association or there is - * no peeled-off association on another socket. - */ - if ((sctp_style(sk, TCP) && - sctp_sstate(sk, ESTABLISHED)) || - sctp_endpoint_is_peeled_off(ep, &to)) { - err = -EADDRNOTAVAIL; - goto out_unlock; - } + + /* If we could not find a matching association on the + * endpoint, make sure that it is not a TCP-style + * socket that already has an association or there is + * no peeled-off association on another socket. + */ + if (!asoc && + ((sctp_style(sk, TCP) && + (sctp_sstate(sk, ESTABLISHED) || + sctp_sstate(sk, CLOSING))) || + sctp_endpoint_is_peeled_off(ep, &to))) { + err = -EADDRNOTAVAIL; + goto out_unlock; } } else { asoc = sctp_id2assoc(sk, associd); @@ -1914,6 +1915,9 @@ static int sctp_sendmsg(struct sock *sk, struct msghdr *msg, size_t msg_len) goto out_free; } + if (sctp_wspace(asoc) < msg_len) + sctp_prsctp_prune(asoc, sinfo, msg_len - sctp_wspace(asoc)); + timeo = sock_sndtimeo(sk, msg->msg_flags & MSG_DONTWAIT); if (!sctp_wspace(asoc)) { err = sctp_wait_for_sndbuf(asoc, &timeo, msg_len); @@ -2063,7 +2067,7 @@ static int sctp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, { struct sctp_ulpevent *event = NULL; struct sctp_sock *sp = sctp_sk(sk); - struct sk_buff *skb; + struct sk_buff *skb, *head_skb; int copied; int err = 0; int skb_len; @@ -2074,7 +2078,8 @@ static int sctp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, lock_sock(sk); - if (sctp_style(sk, TCP) && !sctp_sstate(sk, ESTABLISHED)) { + if (sctp_style(sk, TCP) && !sctp_sstate(sk, ESTABLISHED) && + !sctp_sstate(sk, CLOSING)) { err = -ENOTCONN; goto out; } @@ -2099,12 +2104,16 @@ static int sctp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, if (err) goto out_free; - sock_recv_ts_and_drops(msg, sk, skb); + if (event->chunk && event->chunk->head_skb) + head_skb = event->chunk->head_skb; + else + head_skb = skb; + sock_recv_ts_and_drops(msg, sk, head_skb); if (sctp_ulpevent_is_notification(event)) { msg->msg_flags |= MSG_NOTIFICATION; sp->pf->event_msgname(event, msg->msg_name, addr_len); } else { - sp->pf->skb_msgname(skb, msg->msg_name, addr_len); + sp->pf->skb_msgname(head_skb, msg->msg_name, addr_len); } /* Check if we allow SCTP_NXTINFO. */ @@ -3661,6 +3670,80 @@ static int sctp_setsockopt_recvnxtinfo(struct sock *sk, return 0; } +static int sctp_setsockopt_pr_supported(struct sock *sk, + char __user *optval, + unsigned int optlen) +{ + struct sctp_assoc_value params; + struct sctp_association *asoc; + int retval = -EINVAL; + + if (optlen != sizeof(params)) + goto out; + + if (copy_from_user(¶ms, optval, optlen)) { + retval = -EFAULT; + goto out; + } + + asoc = sctp_id2assoc(sk, params.assoc_id); + if (asoc) { + asoc->prsctp_enable = !!params.assoc_value; + } else if (!params.assoc_id) { + struct sctp_sock *sp = sctp_sk(sk); + + sp->ep->prsctp_enable = !!params.assoc_value; + } else { + goto out; + } + + retval = 0; + +out: + return retval; +} + +static int sctp_setsockopt_default_prinfo(struct sock *sk, + char __user *optval, + unsigned int optlen) +{ + struct sctp_default_prinfo info; + struct sctp_association *asoc; + int retval = -EINVAL; + + if (optlen != sizeof(info)) + goto out; + + if (copy_from_user(&info, optval, sizeof(info))) { + retval = -EFAULT; + goto out; + } + + if (info.pr_policy & ~SCTP_PR_SCTP_MASK) + goto out; + + if (info.pr_policy == SCTP_PR_SCTP_NONE) + info.pr_value = 0; + + asoc = sctp_id2assoc(sk, info.pr_assoc_id); + if (asoc) { + SCTP_PR_SET_POLICY(asoc->default_flags, info.pr_policy); + asoc->default_timetolive = info.pr_value; + } else if (!info.pr_assoc_id) { + struct sctp_sock *sp = sctp_sk(sk); + + SCTP_PR_SET_POLICY(sp->default_flags, info.pr_policy); + sp->default_timetolive = info.pr_value; + } else { + goto out; + } + + retval = 0; + +out: + return retval; +} + /* API 6.2 setsockopt(), getsockopt() * * Applications use setsockopt() and getsockopt() to set or retrieve @@ -3821,6 +3904,12 @@ static int sctp_setsockopt(struct sock *sk, int level, int optname, case SCTP_RECVNXTINFO: retval = sctp_setsockopt_recvnxtinfo(sk, optval, optlen); break; + case SCTP_PR_SUPPORTED: + retval = sctp_setsockopt_pr_supported(sk, optval, optlen); + break; + case SCTP_DEFAULT_PRINFO: + retval = sctp_setsockopt_default_prinfo(sk, optval, optlen); + break; default: retval = -ENOPROTOOPT; break; @@ -4003,6 +4092,8 @@ static int sctp_init_sock(struct sock *sk) return -ESOCKTNOSUPPORT; } + sk->sk_gso_type = SKB_GSO_SCTP; + /* Initialize default send parameters. These parameters can be * modified with the SCTP_DEFAULT_SEND_PARAM socket option. */ @@ -4193,6 +4284,7 @@ static void sctp_shutdown(struct sock *sk, int how) return; if (how & SEND_SHUTDOWN) { + sk->sk_state = SCTP_SS_CLOSING; ep = sctp_sk(sk)->ep; if (!list_empty(&ep->asocs)) { asoc = list_entry(ep->asocs.next, @@ -4301,6 +4393,7 @@ int sctp_transport_walk_start(struct rhashtable_iter *iter) err = rhashtable_walk_start(iter); if (err && err != -EAGAIN) { + rhashtable_walk_stop(iter); rhashtable_walk_exit(iter); return err; } @@ -6163,6 +6256,148 @@ static int sctp_getsockopt_recvnxtinfo(struct sock *sk, int len, return 0; } +static int sctp_getsockopt_pr_supported(struct sock *sk, int len, + char __user *optval, + int __user *optlen) +{ + struct sctp_assoc_value params; + struct sctp_association *asoc; + int retval = -EFAULT; + + if (len < sizeof(params)) { + retval = -EINVAL; + goto out; + } + + len = sizeof(params); + if (copy_from_user(¶ms, optval, len)) + goto out; + + asoc = sctp_id2assoc(sk, params.assoc_id); + if (asoc) { + params.assoc_value = asoc->prsctp_enable; + } else if (!params.assoc_id) { + struct sctp_sock *sp = sctp_sk(sk); + + params.assoc_value = sp->ep->prsctp_enable; + } else { + retval = -EINVAL; + goto out; + } + + if (put_user(len, optlen)) + goto out; + + if (copy_to_user(optval, ¶ms, len)) + goto out; + + retval = 0; + +out: + return retval; +} + +static int sctp_getsockopt_default_prinfo(struct sock *sk, int len, + char __user *optval, + int __user *optlen) +{ + struct sctp_default_prinfo info; + struct sctp_association *asoc; + int retval = -EFAULT; + + if (len < sizeof(info)) { + retval = -EINVAL; + goto out; + } + + len = sizeof(info); + if (copy_from_user(&info, optval, len)) + goto out; + + asoc = sctp_id2assoc(sk, info.pr_assoc_id); + if (asoc) { + info.pr_policy = SCTP_PR_POLICY(asoc->default_flags); + info.pr_value = asoc->default_timetolive; + } else if (!info.pr_assoc_id) { + struct sctp_sock *sp = sctp_sk(sk); + + info.pr_policy = SCTP_PR_POLICY(sp->default_flags); + info.pr_value = sp->default_timetolive; + } else { + retval = -EINVAL; + goto out; + } + + if (put_user(len, optlen)) + goto out; + + if (copy_to_user(optval, &info, len)) + goto out; + + retval = 0; + +out: + return retval; +} + +static int sctp_getsockopt_pr_assocstatus(struct sock *sk, int len, + char __user *optval, + int __user *optlen) +{ + struct sctp_prstatus params; + struct sctp_association *asoc; + int policy; + int retval = -EINVAL; + + if (len < sizeof(params)) + goto out; + + len = sizeof(params); + if (copy_from_user(¶ms, optval, len)) { + retval = -EFAULT; + goto out; + } + + policy = params.sprstat_policy; + if (policy & ~SCTP_PR_SCTP_MASK) + goto out; + + asoc = sctp_id2assoc(sk, params.sprstat_assoc_id); + if (!asoc) + goto out; + + if (policy == SCTP_PR_SCTP_NONE) { + params.sprstat_abandoned_unsent = 0; + params.sprstat_abandoned_sent = 0; + for (policy = 0; policy <= SCTP_PR_INDEX(MAX); policy++) { + params.sprstat_abandoned_unsent += + asoc->abandoned_unsent[policy]; + params.sprstat_abandoned_sent += + asoc->abandoned_sent[policy]; + } + } else { + params.sprstat_abandoned_unsent = + asoc->abandoned_unsent[__SCTP_PR_INDEX(policy)]; + params.sprstat_abandoned_sent = + asoc->abandoned_sent[__SCTP_PR_INDEX(policy)]; + } + + if (put_user(len, optlen)) { + retval = -EFAULT; + goto out; + } + + if (copy_to_user(optval, ¶ms, len)) { + retval = -EFAULT; + goto out; + } + + retval = 0; + +out: + return retval; +} + static int sctp_getsockopt(struct sock *sk, int level, int optname, char __user *optval, int __user *optlen) { @@ -6316,6 +6551,17 @@ static int sctp_getsockopt(struct sock *sk, int level, int optname, case SCTP_RECVNXTINFO: retval = sctp_getsockopt_recvnxtinfo(sk, len, optval, optlen); break; + case SCTP_PR_SUPPORTED: + retval = sctp_getsockopt_pr_supported(sk, len, optval, optlen); + break; + case SCTP_DEFAULT_PRINFO: + retval = sctp_getsockopt_default_prinfo(sk, len, optval, + optlen); + break; + case SCTP_PR_ASSOC_STATUS: + retval = sctp_getsockopt_pr_assocstatus(sk, len, optval, + optlen); + break; default: retval = -ENOPROTOOPT; break; @@ -6863,7 +7109,7 @@ static int sctp_msghdr_parse(const struct msghdr *msg, sctp_cmsgs_t *cmsgs) if (cmsgs->srinfo->sinfo_flags & ~(SCTP_UNORDERED | SCTP_ADDR_OVER | - SCTP_SACK_IMMEDIATELY | + SCTP_SACK_IMMEDIATELY | SCTP_PR_SCTP_MASK | SCTP_ABORT | SCTP_EOF)) return -EINVAL; break; @@ -6887,7 +7133,7 @@ static int sctp_msghdr_parse(const struct msghdr *msg, sctp_cmsgs_t *cmsgs) if (cmsgs->sinfo->snd_flags & ~(SCTP_UNORDERED | SCTP_ADDR_OVER | - SCTP_SACK_IMMEDIATELY | + SCTP_SACK_IMMEDIATELY | SCTP_PR_SCTP_MASK | SCTP_ABORT | SCTP_EOF)) return -EINVAL; break; @@ -7564,10 +7810,13 @@ static void sctp_sock_migrate(struct sock *oldsk, struct sock *newsk, /* If the association on the newsk is already closed before accept() * is called, set RCV_SHUTDOWN flag. */ - if (sctp_state(assoc, CLOSED) && sctp_style(newsk, TCP)) + if (sctp_state(assoc, CLOSED) && sctp_style(newsk, TCP)) { + newsk->sk_state = SCTP_SS_CLOSED; newsk->sk_shutdown |= RCV_SHUTDOWN; + } else { + newsk->sk_state = SCTP_SS_ESTABLISHED; + } - newsk->sk_state = SCTP_SS_ESTABLISHED; release_sock(newsk); } diff --git a/net/sctp/ulpevent.c b/net/sctp/ulpevent.c index d1e38308f615..1bc4f71aaba8 100644 --- a/net/sctp/ulpevent.c +++ b/net/sctp/ulpevent.c @@ -51,7 +51,7 @@ static void sctp_ulpevent_release_frag_data(struct sctp_ulpevent *event); /* Initialize an ULP event from an given skb. */ static void sctp_ulpevent_init(struct sctp_ulpevent *event, - int msg_flags, + __u16 msg_flags, unsigned int len) { memset(event, 0, sizeof(struct sctp_ulpevent)); @@ -60,7 +60,7 @@ static void sctp_ulpevent_init(struct sctp_ulpevent *event, } /* Create a new sctp_ulpevent. */ -static struct sctp_ulpevent *sctp_ulpevent_new(int size, int msg_flags, +static struct sctp_ulpevent *sctp_ulpevent_new(int size, __u16 msg_flags, gfp_t gfp) { struct sctp_ulpevent *event; @@ -91,6 +91,7 @@ int sctp_ulpevent_is_notification(const struct sctp_ulpevent *event) static inline void sctp_ulpevent_set_owner(struct sctp_ulpevent *event, const struct sctp_association *asoc) { + struct sctp_chunk *chunk = event->chunk; struct sk_buff *skb; /* Cast away the const, as we are just wanting to @@ -101,6 +102,8 @@ static inline void sctp_ulpevent_set_owner(struct sctp_ulpevent *event, event->asoc = (struct sctp_association *)asoc; atomic_add(event->rmem_len, &event->asoc->rmem_alloc); sctp_skb_set_owner_r(skb, asoc->base.sk); + if (chunk && chunk->head_skb && !chunk->head_skb->sk) + chunk->head_skb->sk = asoc->base.sk; } /* A simple destructor to give up the reference to the association. */ @@ -701,6 +704,12 @@ struct sctp_ulpevent *sctp_ulpevent_make_rcvmsg(struct sctp_association *asoc, sctp_ulpevent_receive_data(event, asoc); + /* And hold the chunk as we need it for getting the IP headers + * later in recvmsg + */ + sctp_chunk_hold(chunk); + event->chunk = chunk; + event->stream = ntohs(chunk->subh.data_hdr->stream); event->ssn = ntohs(chunk->subh.data_hdr->ssn); event->ppid = chunk->subh.data_hdr->ppid; @@ -710,11 +719,11 @@ struct sctp_ulpevent *sctp_ulpevent_make_rcvmsg(struct sctp_association *asoc, } event->tsn = ntohl(chunk->subh.data_hdr->tsn); event->msg_flags |= chunk->chunk_hdr->flags; - event->iif = sctp_chunk_iif(chunk); return event; fail_mark: + sctp_chunk_put(chunk); kfree_skb(skb); fail: return NULL; @@ -1007,6 +1016,7 @@ static void sctp_ulpevent_release_data(struct sctp_ulpevent *event) done: sctp_assoc_rwnd_increase(event->asoc, len); + sctp_chunk_put(event->chunk); sctp_ulpevent_release_owner(event); } @@ -1029,6 +1039,7 @@ static void sctp_ulpevent_release_frag_data(struct sctp_ulpevent *event) } done: + sctp_chunk_put(event->chunk); sctp_ulpevent_release_owner(event); } |