29c4afc4e9
There is NULL pointer dereference possible during statistics update if the route used for OOTB responce is removed at unfortunate time. If the route exists when we receive OOTB packet and we finally jump into sctp_packet_transmit() to send ABORT, but in the meantime route is removed under our feet, we take "no_route" path and try to update stats with IP_INC_STATS(sock_net(asoc->base.sk), ...). But sctp_ootb_pkt_new() used to prepare responce packet doesn't call sctp_transport_set_owner() and therefore there is no asoc associated with this packet. Probably temporary asoc just for OOTB responces is overkill, so just introduce a check like in all other places in sctp_packet_transmit(), where "asoc" is dereferenced. To reproduce this, one needs to 0. ensure that sctp module is loaded (otherwise ABORT is not generated) 1. remove default route on the machine 2. while true; do ip route del [interface-specific route] ip route add [interface-specific route] done 3. send enough OOTB packets (i.e. HB REQs) from another host to trigger ABORT responce On x86_64 the crash looks like this: BUG: unable to handle kernel NULL pointer dereference at 0000000000000020 IP: [<ffffffffa05ec9ac>] sctp_packet_transmit+0x63c/0x730 [sctp] PGD 0 Oops: 0000 [#1] PREEMPT SMP Modules linked in: ... CPU: 0 PID: 0 Comm: swapper/0 Tainted: G O 4.0.5-1-ARCH #1 Hardware name: ... task: ffffffff818124c0 ti: ffffffff81800000 task.ti: ffffffff81800000 RIP: 0010:[<ffffffffa05ec9ac>] [<ffffffffa05ec9ac>] sctp_packet_transmit+0x63c/0x730 [sctp] RSP: 0018:ffff880127c037b8 EFLAGS: 00010296 RAX: 0000000000000000 RBX: 0000000000000000 RCX: 00000015ff66b480 RDX: 00000015ff66b400 RSI: ffff880127c17200 RDI: ffff880123403700 RBP: ffff880127c03888 R08: 0000000000017200 R09: ffffffff814625af R10: ffffea00047e4680 R11: 00000000ffffff80 R12: ffff8800b0d38a28 R13: ffff8800b0d38a28 R14: ffff8800b3e88000 R15: ffffffffa05f24e0 FS: 0000000000000000(0000) GS:ffff880127c00000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 000000008005003b CR2: 0000000000000020 CR3: 00000000c855b000 CR4: 00000000000007f0 Stack: ffff880127c03910 ffff8800b0d38a28 ffffffff8189d240 ffff88011f91b400 ffff880127c03828 ffffffffa05c94c5 0000000000000000 ffff8800baa1c520 0000000000000000 0000000000000001 0000000000000000 0000000000000000 Call Trace: <IRQ> [<ffffffffa05c94c5>] ? sctp_sf_tabort_8_4_8.isra.20+0x85/0x140 [sctp] [<ffffffffa05d6b42>] ? sctp_transport_put+0x52/0x80 [sctp] [<ffffffffa05d0bfc>] sctp_do_sm+0xb8c/0x19a0 [sctp] [<ffffffff810b0e00>] ? trigger_load_balance+0x90/0x210 [<ffffffff810e0329>] ? update_process_times+0x59/0x60 [<ffffffff812c7a40>] ? timerqueue_add+0x60/0xb0 [<ffffffff810e0549>] ? enqueue_hrtimer+0x29/0xa0 [<ffffffff8101f599>] ? read_tsc+0x9/0x10 [<ffffffff8116d4b5>] ? put_page+0x55/0x60 [<ffffffff810ee1ad>] ? clockevents_program_event+0x6d/0x100 [<ffffffff81462b68>] ? skb_free_head+0x58/0x80 [<ffffffffa029a10b>] ? chksum_update+0x1b/0x27 [crc32c_generic] [<ffffffff81283f3e>] ? crypto_shash_update+0xce/0xf0 [<ffffffffa05d3993>] sctp_endpoint_bh_rcv+0x113/0x280 [sctp] [<ffffffffa05dd4e6>] sctp_inq_push+0x46/0x60 [sctp] [<ffffffffa05ed7a0>] sctp_rcv+0x880/0x910 [sctp] [<ffffffffa05ecb50>] ? sctp_packet_transmit_chunk+0xb0/0xb0 [sctp] [<ffffffffa05ecb70>] ? sctp_csum_update+0x20/0x20 [sctp] [<ffffffff814b05a5>] ? ip_route_input_noref+0x235/0xd30 [<ffffffff81051d6b>] ? ack_ioapic_level+0x7b/0x150 [<ffffffff814b27be>] ip_local_deliver_finish+0xae/0x210 [<ffffffff814b2e15>] ip_local_deliver+0x35/0x90 [<ffffffff814b2a15>] ip_rcv_finish+0xf5/0x370 [<ffffffff814b3128>] ip_rcv+0x2b8/0x3a0 [<ffffffff81474193>] __netif_receive_skb_core+0x763/0xa50 [<ffffffff81476c28>] __netif_receive_skb+0x18/0x60 [<ffffffff81476cb0>] netif_receive_skb_internal+0x40/0xd0 [<ffffffff814776c8>] napi_gro_receive+0xe8/0x120 [<ffffffffa03946aa>] rtl8169_poll+0x2da/0x660 [r8169] [<ffffffff8147896a>] net_rx_action+0x21a/0x360 [<ffffffff81078dc1>] __do_softirq+0xe1/0x2d0 [<ffffffff8107912d>] irq_exit+0xad/0xb0 [<ffffffff8157d158>] do_IRQ+0x58/0xf0 [<ffffffff8157b06d>] common_interrupt+0x6d/0x6d <EOI> [<ffffffff810e1218>] ? hrtimer_start+0x18/0x20 [<ffffffffa05d65f9>] ? sctp_transport_destroy_rcu+0x29/0x30 [sctp] [<ffffffff81020c50>] ? mwait_idle+0x60/0xa0 [<ffffffff810216ef>] arch_cpu_idle+0xf/0x20 [<ffffffff810b731c>] cpu_startup_entry+0x3ec/0x480 [<ffffffff8156b365>] rest_init+0x85/0x90 [<ffffffff818eb035>] start_kernel+0x48b/0x4ac [<ffffffff818ea120>] ? early_idt_handlers+0x120/0x120 [<ffffffff818ea339>] x86_64_start_reservations+0x2a/0x2c [<ffffffff818ea49c>] x86_64_start_kernel+0x161/0x184 Code: 90 48 8b 80 b8 00 00 00 48 89 85 70 ff ff ff 48 83 bd 70 ff ff ff 00 0f 85 cd fa ff ff 48 89 df 31 db e8 18 63 e7 e0 48 8b 45 80 <48> 8b 40 20 48 8b 40 30 48 8b 80 68 01 00 00 65 48 ff 40 78 e9 RIP [<ffffffffa05ec9ac>] sctp_packet_transmit+0x63c/0x730 [sctp] RSP <ffff880127c037b8> CR2: 0000000000000020 ---[ end trace 5aec7fd2dc983574 ]--- Kernel panic - not syncing: Fatal exception in interrupt Kernel Offset: 0x0 from 0xffffffff81000000 (relocation range: 0xffffffff80000000-0xffffffff9fffffff) drm_kms_helper: panic occurred, switching back to text console ---[ end Kernel panic - not syncing: Fatal exception in interrupt Signed-off-by: Alexander Sverdlin <alexander.sverdlin@nokia.com> Acked-by: Neil Horman <nhorman@tuxdriver.com> Acked-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com> Acked-by: Vlad Yasevich <vyasevich@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
789 lines
22 KiB
C
789 lines
22 KiB
C
/* SCTP kernel implementation
|
|
* (C) Copyright IBM Corp. 2001, 2004
|
|
* Copyright (c) 1999-2000 Cisco, Inc.
|
|
* Copyright (c) 1999-2001 Motorola, Inc.
|
|
*
|
|
* This file is part of the SCTP kernel implementation
|
|
*
|
|
* These functions handle output processing.
|
|
*
|
|
* This SCTP implementation 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, or (at your option)
|
|
* any later version.
|
|
*
|
|
* This SCTP implementation 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.
|
|
*
|
|
* You should have received a copy of the GNU General Public License
|
|
* along with GNU CC; see the file COPYING. If not, see
|
|
* <http://www.gnu.org/licenses/>.
|
|
*
|
|
* Please send any bug reports or fixes you make to the
|
|
* email address(es):
|
|
* lksctp developers <linux-sctp@vger.kernel.org>
|
|
*
|
|
* Written or modified by:
|
|
* La Monte H.P. Yarroll <piggy@acm.org>
|
|
* Karl Knutson <karl@athena.chicago.il.us>
|
|
* Jon Grimm <jgrimm@austin.ibm.com>
|
|
* Sridhar Samudrala <sri@us.ibm.com>
|
|
*/
|
|
|
|
#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
|
|
|
|
#include <linux/types.h>
|
|
#include <linux/kernel.h>
|
|
#include <linux/wait.h>
|
|
#include <linux/time.h>
|
|
#include <linux/ip.h>
|
|
#include <linux/ipv6.h>
|
|
#include <linux/init.h>
|
|
#include <linux/slab.h>
|
|
#include <net/inet_ecn.h>
|
|
#include <net/ip.h>
|
|
#include <net/icmp.h>
|
|
#include <net/net_namespace.h>
|
|
|
|
#include <linux/socket.h> /* for sa_family_t */
|
|
#include <net/sock.h>
|
|
|
|
#include <net/sctp/sctp.h>
|
|
#include <net/sctp/sm.h>
|
|
#include <net/sctp/checksum.h>
|
|
|
|
/* Forward declarations for private helpers. */
|
|
static sctp_xmit_t __sctp_packet_append_chunk(struct sctp_packet *packet,
|
|
struct sctp_chunk *chunk);
|
|
static sctp_xmit_t sctp_packet_can_append_data(struct sctp_packet *packet,
|
|
struct sctp_chunk *chunk);
|
|
static void sctp_packet_append_data(struct sctp_packet *packet,
|
|
struct sctp_chunk *chunk);
|
|
static sctp_xmit_t sctp_packet_will_fit(struct sctp_packet *packet,
|
|
struct sctp_chunk *chunk,
|
|
u16 chunk_len);
|
|
|
|
static void sctp_packet_reset(struct sctp_packet *packet)
|
|
{
|
|
packet->size = packet->overhead;
|
|
packet->has_cookie_echo = 0;
|
|
packet->has_sack = 0;
|
|
packet->has_data = 0;
|
|
packet->has_auth = 0;
|
|
packet->ipfragok = 0;
|
|
packet->auth = NULL;
|
|
}
|
|
|
|
/* Config a packet.
|
|
* This appears to be a followup set of initializations.
|
|
*/
|
|
struct sctp_packet *sctp_packet_config(struct sctp_packet *packet,
|
|
__u32 vtag, int ecn_capable)
|
|
{
|
|
struct sctp_chunk *chunk = NULL;
|
|
|
|
pr_debug("%s: packet:%p vtag:0x%x\n", __func__, packet, vtag);
|
|
|
|
packet->vtag = vtag;
|
|
|
|
if (ecn_capable && sctp_packet_empty(packet)) {
|
|
chunk = sctp_get_ecne_prepend(packet->transport->asoc);
|
|
|
|
/* If there a is a prepend chunk stick it on the list before
|
|
* any other chunks get appended.
|
|
*/
|
|
if (chunk)
|
|
sctp_packet_append_chunk(packet, chunk);
|
|
}
|
|
|
|
return packet;
|
|
}
|
|
|
|
/* Initialize the packet structure. */
|
|
struct sctp_packet *sctp_packet_init(struct sctp_packet *packet,
|
|
struct sctp_transport *transport,
|
|
__u16 sport, __u16 dport)
|
|
{
|
|
struct sctp_association *asoc = transport->asoc;
|
|
size_t overhead;
|
|
|
|
pr_debug("%s: packet:%p transport:%p\n", __func__, packet, transport);
|
|
|
|
packet->transport = transport;
|
|
packet->source_port = sport;
|
|
packet->destination_port = dport;
|
|
INIT_LIST_HEAD(&packet->chunk_list);
|
|
if (asoc) {
|
|
struct sctp_sock *sp = sctp_sk(asoc->base.sk);
|
|
overhead = sp->pf->af->net_header_len;
|
|
} else {
|
|
overhead = sizeof(struct ipv6hdr);
|
|
}
|
|
overhead += sizeof(struct sctphdr);
|
|
packet->overhead = overhead;
|
|
sctp_packet_reset(packet);
|
|
packet->vtag = 0;
|
|
|
|
return packet;
|
|
}
|
|
|
|
/* Free a packet. */
|
|
void sctp_packet_free(struct sctp_packet *packet)
|
|
{
|
|
struct sctp_chunk *chunk, *tmp;
|
|
|
|
pr_debug("%s: packet:%p\n", __func__, packet);
|
|
|
|
list_for_each_entry_safe(chunk, tmp, &packet->chunk_list, list) {
|
|
list_del_init(&chunk->list);
|
|
sctp_chunk_free(chunk);
|
|
}
|
|
}
|
|
|
|
/* This routine tries to append the chunk to the offered packet. If adding
|
|
* the chunk causes the packet to exceed the path MTU and COOKIE_ECHO chunk
|
|
* is not present in the packet, it transmits the input packet.
|
|
* Data can be bundled with a packet containing a COOKIE_ECHO chunk as long
|
|
* as it can fit in the packet, but any more data that does not fit in this
|
|
* packet can be sent only after receiving the COOKIE_ACK.
|
|
*/
|
|
sctp_xmit_t sctp_packet_transmit_chunk(struct sctp_packet *packet,
|
|
struct sctp_chunk *chunk,
|
|
int one_packet)
|
|
{
|
|
sctp_xmit_t retval;
|
|
int error = 0;
|
|
|
|
pr_debug("%s: packet:%p chunk:%p\n", __func__, packet, chunk);
|
|
|
|
switch ((retval = (sctp_packet_append_chunk(packet, chunk)))) {
|
|
case SCTP_XMIT_PMTU_FULL:
|
|
if (!packet->has_cookie_echo) {
|
|
error = sctp_packet_transmit(packet);
|
|
if (error < 0)
|
|
chunk->skb->sk->sk_err = -error;
|
|
|
|
/* If we have an empty packet, then we can NOT ever
|
|
* return PMTU_FULL.
|
|
*/
|
|
if (!one_packet)
|
|
retval = sctp_packet_append_chunk(packet,
|
|
chunk);
|
|
}
|
|
break;
|
|
|
|
case SCTP_XMIT_RWND_FULL:
|
|
case SCTP_XMIT_OK:
|
|
case SCTP_XMIT_DELAY:
|
|
break;
|
|
}
|
|
|
|
return retval;
|
|
}
|
|
|
|
/* Try to bundle an auth chunk into the packet. */
|
|
static sctp_xmit_t sctp_packet_bundle_auth(struct sctp_packet *pkt,
|
|
struct sctp_chunk *chunk)
|
|
{
|
|
struct sctp_association *asoc = pkt->transport->asoc;
|
|
struct sctp_chunk *auth;
|
|
sctp_xmit_t retval = SCTP_XMIT_OK;
|
|
|
|
/* if we don't have an association, we can't do authentication */
|
|
if (!asoc)
|
|
return retval;
|
|
|
|
/* See if this is an auth chunk we are bundling or if
|
|
* auth is already bundled.
|
|
*/
|
|
if (chunk->chunk_hdr->type == SCTP_CID_AUTH || pkt->has_auth)
|
|
return retval;
|
|
|
|
/* if the peer did not request this chunk to be authenticated,
|
|
* don't do it
|
|
*/
|
|
if (!chunk->auth)
|
|
return retval;
|
|
|
|
auth = sctp_make_auth(asoc);
|
|
if (!auth)
|
|
return retval;
|
|
|
|
retval = __sctp_packet_append_chunk(pkt, auth);
|
|
|
|
if (retval != SCTP_XMIT_OK)
|
|
sctp_chunk_free(auth);
|
|
|
|
return retval;
|
|
}
|
|
|
|
/* Try to bundle a SACK with the packet. */
|
|
static sctp_xmit_t sctp_packet_bundle_sack(struct sctp_packet *pkt,
|
|
struct sctp_chunk *chunk)
|
|
{
|
|
sctp_xmit_t retval = SCTP_XMIT_OK;
|
|
|
|
/* If sending DATA and haven't aleady bundled a SACK, try to
|
|
* bundle one in to the packet.
|
|
*/
|
|
if (sctp_chunk_is_data(chunk) && !pkt->has_sack &&
|
|
!pkt->has_cookie_echo) {
|
|
struct sctp_association *asoc;
|
|
struct timer_list *timer;
|
|
asoc = pkt->transport->asoc;
|
|
timer = &asoc->timers[SCTP_EVENT_TIMEOUT_SACK];
|
|
|
|
/* If the SACK timer is running, we have a pending SACK */
|
|
if (timer_pending(timer)) {
|
|
struct sctp_chunk *sack;
|
|
|
|
if (pkt->transport->sack_generation !=
|
|
pkt->transport->asoc->peer.sack_generation)
|
|
return retval;
|
|
|
|
asoc->a_rwnd = asoc->rwnd;
|
|
sack = sctp_make_sack(asoc);
|
|
if (sack) {
|
|
retval = __sctp_packet_append_chunk(pkt, sack);
|
|
if (retval != SCTP_XMIT_OK) {
|
|
sctp_chunk_free(sack);
|
|
goto out;
|
|
}
|
|
asoc->peer.sack_needed = 0;
|
|
if (del_timer(timer))
|
|
sctp_association_put(asoc);
|
|
}
|
|
}
|
|
}
|
|
out:
|
|
return retval;
|
|
}
|
|
|
|
|
|
/* Append a chunk to the offered packet reporting back any inability to do
|
|
* so.
|
|
*/
|
|
static sctp_xmit_t __sctp_packet_append_chunk(struct sctp_packet *packet,
|
|
struct sctp_chunk *chunk)
|
|
{
|
|
sctp_xmit_t retval = SCTP_XMIT_OK;
|
|
__u16 chunk_len = WORD_ROUND(ntohs(chunk->chunk_hdr->length));
|
|
|
|
/* Check to see if this chunk will fit into the packet */
|
|
retval = sctp_packet_will_fit(packet, chunk, chunk_len);
|
|
if (retval != SCTP_XMIT_OK)
|
|
goto finish;
|
|
|
|
/* We believe that this chunk is OK to add to the packet */
|
|
switch (chunk->chunk_hdr->type) {
|
|
case SCTP_CID_DATA:
|
|
/* Account for the data being in the packet */
|
|
sctp_packet_append_data(packet, chunk);
|
|
/* Disallow SACK bundling after DATA. */
|
|
packet->has_sack = 1;
|
|
/* Disallow AUTH bundling after DATA */
|
|
packet->has_auth = 1;
|
|
/* Let it be knows that packet has DATA in it */
|
|
packet->has_data = 1;
|
|
/* timestamp the chunk for rtx purposes */
|
|
chunk->sent_at = jiffies;
|
|
break;
|
|
case SCTP_CID_COOKIE_ECHO:
|
|
packet->has_cookie_echo = 1;
|
|
break;
|
|
|
|
case SCTP_CID_SACK:
|
|
packet->has_sack = 1;
|
|
if (chunk->asoc)
|
|
chunk->asoc->stats.osacks++;
|
|
break;
|
|
|
|
case SCTP_CID_AUTH:
|
|
packet->has_auth = 1;
|
|
packet->auth = chunk;
|
|
break;
|
|
}
|
|
|
|
/* It is OK to send this chunk. */
|
|
list_add_tail(&chunk->list, &packet->chunk_list);
|
|
packet->size += chunk_len;
|
|
chunk->transport = packet->transport;
|
|
finish:
|
|
return retval;
|
|
}
|
|
|
|
/* Append a chunk to the offered packet reporting back any inability to do
|
|
* so.
|
|
*/
|
|
sctp_xmit_t sctp_packet_append_chunk(struct sctp_packet *packet,
|
|
struct sctp_chunk *chunk)
|
|
{
|
|
sctp_xmit_t retval = SCTP_XMIT_OK;
|
|
|
|
pr_debug("%s: packet:%p chunk:%p\n", __func__, packet, chunk);
|
|
|
|
/* Data chunks are special. Before seeing what else we can
|
|
* bundle into this packet, check to see if we are allowed to
|
|
* send this DATA.
|
|
*/
|
|
if (sctp_chunk_is_data(chunk)) {
|
|
retval = sctp_packet_can_append_data(packet, chunk);
|
|
if (retval != SCTP_XMIT_OK)
|
|
goto finish;
|
|
}
|
|
|
|
/* Try to bundle AUTH chunk */
|
|
retval = sctp_packet_bundle_auth(packet, chunk);
|
|
if (retval != SCTP_XMIT_OK)
|
|
goto finish;
|
|
|
|
/* Try to bundle SACK chunk */
|
|
retval = sctp_packet_bundle_sack(packet, chunk);
|
|
if (retval != SCTP_XMIT_OK)
|
|
goto finish;
|
|
|
|
retval = __sctp_packet_append_chunk(packet, chunk);
|
|
|
|
finish:
|
|
return retval;
|
|
}
|
|
|
|
static void sctp_packet_release_owner(struct sk_buff *skb)
|
|
{
|
|
sk_free(skb->sk);
|
|
}
|
|
|
|
static void sctp_packet_set_owner_w(struct sk_buff *skb, struct sock *sk)
|
|
{
|
|
skb_orphan(skb);
|
|
skb->sk = sk;
|
|
skb->destructor = sctp_packet_release_owner;
|
|
|
|
/*
|
|
* The data chunks have already been accounted for in sctp_sendmsg(),
|
|
* therefore only reserve a single byte to keep socket around until
|
|
* the packet has been transmitted.
|
|
*/
|
|
atomic_inc(&sk->sk_wmem_alloc);
|
|
}
|
|
|
|
/* All packets are sent to the network through this function from
|
|
* sctp_outq_tail().
|
|
*
|
|
* The return value is a normal kernel error return value.
|
|
*/
|
|
int sctp_packet_transmit(struct sctp_packet *packet)
|
|
{
|
|
struct sctp_transport *tp = packet->transport;
|
|
struct sctp_association *asoc = tp->asoc;
|
|
struct sctphdr *sh;
|
|
struct sk_buff *nskb;
|
|
struct sctp_chunk *chunk, *tmp;
|
|
struct sock *sk;
|
|
int err = 0;
|
|
int padding; /* How much padding do we need? */
|
|
__u8 has_data = 0;
|
|
struct dst_entry *dst;
|
|
unsigned char *auth = NULL; /* pointer to auth in skb data */
|
|
|
|
pr_debug("%s: packet:%p\n", __func__, packet);
|
|
|
|
/* Do NOT generate a chunkless packet. */
|
|
if (list_empty(&packet->chunk_list))
|
|
return err;
|
|
|
|
/* Set up convenience variables... */
|
|
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_ATOMIC);
|
|
if (!nskb)
|
|
goto nomem;
|
|
|
|
/* Make sure the outbound skb has enough header room reserved. */
|
|
skb_reserve(nskb, 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);
|
|
|
|
if (!sctp_transport_dst_check(tp)) {
|
|
sctp_transport_route(tp, NULL, sctp_sk(sk));
|
|
if (asoc && (asoc->param_flags & SPP_PMTUD_ENABLE)) {
|
|
sctp_assoc_sync_pmtu(sk, asoc);
|
|
}
|
|
}
|
|
dst = dst_clone(tp->dst);
|
|
if (!dst)
|
|
goto no_route;
|
|
skb_dst_set(nskb, dst);
|
|
|
|
/* Build the SCTP header. */
|
|
sh = (struct sctphdr *)skb_push(nskb, sizeof(struct sctphdr));
|
|
skb_reset_transport_header(nskb);
|
|
sh->source = htons(packet->source_port);
|
|
sh->dest = htons(packet->destination_port);
|
|
|
|
/* From 6.8 Adler-32 Checksum Calculation:
|
|
* After the packet is constructed (containing the SCTP common
|
|
* header and one or more control or DATA chunks), the
|
|
* transmitter shall:
|
|
*
|
|
* 1) Fill in the proper Verification Tag in the SCTP common
|
|
* header and initialize the checksum field to 0's.
|
|
*/
|
|
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.
|
|
*/
|
|
|
|
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.
|
|
*/
|
|
if (!sctp_chunk_is_data(chunk))
|
|
sctp_chunk_free(chunk);
|
|
}
|
|
|
|
/* 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_ATOMIC);
|
|
|
|
/* 2) Calculate the Adler-32 checksum of the whole packet,
|
|
* including the SCTP common header and all the
|
|
* chunks.
|
|
*
|
|
* Note: Adler-32 is no longer applicable, as has been replaced
|
|
* by CRC32-C as described in <draft-ietf-tsvwg-sctpcsum-02.txt>.
|
|
*/
|
|
if (!sctp_checksum_disable) {
|
|
if (!(dst->dev->features & NETIF_F_SCTP_CSUM) ||
|
|
(dst_xfrm(dst) != NULL) || packet->ipfragok) {
|
|
sh->checksum = sctp_compute_cksum(nskb, 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);
|
|
}
|
|
}
|
|
|
|
/* IP layer ECN support
|
|
* From RFC 2481
|
|
* "The ECN-Capable Transport (ECT) bit would be set by the
|
|
* data sender to indicate that the end-points of the
|
|
* transport protocol are ECN-capable."
|
|
*
|
|
* Now setting the ECT bit all the time, as it should not cause
|
|
* any problems protocol-wise even if our peer ignores it.
|
|
*
|
|
* 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);
|
|
|
|
/* Set up the IP options. */
|
|
/* BUG: not implemented
|
|
* For v4 this all lives somewhere in sk->sk_opt...
|
|
*/
|
|
|
|
/* Dump that on IP! */
|
|
if (asoc) {
|
|
asoc->stats.opackets++;
|
|
if (asoc->peer.last_sent_to != tp)
|
|
/* Considering the multiple CPU scenario, this is a
|
|
* "correcter" place for last_sent_to. --xguo
|
|
*/
|
|
asoc->peer.last_sent_to = tp;
|
|
}
|
|
|
|
if (has_data) {
|
|
struct timer_list *timer;
|
|
unsigned long timeout;
|
|
|
|
/* Restart the AUTOCLOSE timer when sending data. */
|
|
if (sctp_state(asoc, ESTABLISHED) &&
|
|
asoc->timeouts[SCTP_EVENT_TIMEOUT_AUTOCLOSE]) {
|
|
timer = &asoc->timers[SCTP_EVENT_TIMEOUT_AUTOCLOSE];
|
|
timeout = asoc->timeouts[SCTP_EVENT_TIMEOUT_AUTOCLOSE];
|
|
|
|
if (!mod_timer(timer, jiffies + timeout))
|
|
sctp_association_hold(asoc);
|
|
}
|
|
}
|
|
|
|
pr_debug("***sctp_transmit_packet*** skb->len:%d\n", nskb->len);
|
|
|
|
nskb->ignore_df = packet->ipfragok;
|
|
tp->af_specific->sctp_xmit(nskb, tp);
|
|
|
|
out:
|
|
sctp_packet_reset(packet);
|
|
return err;
|
|
no_route:
|
|
kfree_skb(nskb);
|
|
|
|
if (asoc)
|
|
IP_INC_STATS(sock_net(asoc->base.sk), IPSTATS_MIB_OUTNOROUTES);
|
|
|
|
/* FIXME: Returning the 'err' will effect all the associations
|
|
* associated with a socket, although only one of the paths of the
|
|
* association is unreachable.
|
|
* The real failure of a transport or association can be passed on
|
|
* to the user via notifications. So setting this error may not be
|
|
* required.
|
|
*/
|
|
/* err = -EHOSTUNREACH; */
|
|
err:
|
|
/* Control chunks are unreliable so just drop them. DATA chunks
|
|
* will get resent or dropped later.
|
|
*/
|
|
|
|
list_for_each_entry_safe(chunk, tmp, &packet->chunk_list, list) {
|
|
list_del_init(&chunk->list);
|
|
if (!sctp_chunk_is_data(chunk))
|
|
sctp_chunk_free(chunk);
|
|
}
|
|
goto out;
|
|
nomem:
|
|
err = -ENOMEM;
|
|
goto err;
|
|
}
|
|
|
|
/********************************************************************
|
|
* 2nd Level Abstractions
|
|
********************************************************************/
|
|
|
|
/* This private function check to see if a chunk can be added */
|
|
static sctp_xmit_t sctp_packet_can_append_data(struct sctp_packet *packet,
|
|
struct sctp_chunk *chunk)
|
|
{
|
|
size_t datasize, rwnd, inflight, flight_size;
|
|
struct sctp_transport *transport = packet->transport;
|
|
struct sctp_association *asoc = transport->asoc;
|
|
struct sctp_outq *q = &asoc->outqueue;
|
|
|
|
/* RFC 2960 6.1 Transmission of DATA Chunks
|
|
*
|
|
* A) At any given time, the data sender MUST NOT transmit new data to
|
|
* any destination transport address if its peer's rwnd indicates
|
|
* that the peer has no buffer space (i.e. rwnd is 0, see Section
|
|
* 6.2.1). However, regardless of the value of rwnd (including if it
|
|
* is 0), the data sender can always have one DATA chunk in flight to
|
|
* the receiver if allowed by cwnd (see rule B below). This rule
|
|
* allows the sender to probe for a change in rwnd that the sender
|
|
* missed due to the SACK having been lost in transit from the data
|
|
* receiver to the data sender.
|
|
*/
|
|
|
|
rwnd = asoc->peer.rwnd;
|
|
inflight = q->outstanding_bytes;
|
|
flight_size = transport->flight_size;
|
|
|
|
datasize = sctp_data_size(chunk);
|
|
|
|
if (datasize > rwnd && inflight > 0)
|
|
/* We have (at least) one data chunk in flight,
|
|
* so we can't fall back to rule 6.1 B).
|
|
*/
|
|
return SCTP_XMIT_RWND_FULL;
|
|
|
|
/* RFC 2960 6.1 Transmission of DATA Chunks
|
|
*
|
|
* B) At any given time, the sender MUST NOT transmit new data
|
|
* to a given transport address if it has cwnd or more bytes
|
|
* of data outstanding to that transport address.
|
|
*/
|
|
/* RFC 7.2.4 & the Implementers Guide 2.8.
|
|
*
|
|
* 3) ...
|
|
* When a Fast Retransmit is being performed the sender SHOULD
|
|
* ignore the value of cwnd and SHOULD NOT delay retransmission.
|
|
*/
|
|
if (chunk->fast_retransmit != SCTP_NEED_FRTX &&
|
|
flight_size >= transport->cwnd)
|
|
return SCTP_XMIT_RWND_FULL;
|
|
|
|
/* Nagle's algorithm to solve small-packet problem:
|
|
* Inhibit the sending of new chunks when new outgoing data arrives
|
|
* if any previously transmitted data on the connection remains
|
|
* unacknowledged.
|
|
*/
|
|
|
|
if (sctp_sk(asoc->base.sk)->nodelay)
|
|
/* Nagle disabled */
|
|
return SCTP_XMIT_OK;
|
|
|
|
if (!sctp_packet_empty(packet))
|
|
/* Append to packet */
|
|
return SCTP_XMIT_OK;
|
|
|
|
if (inflight == 0)
|
|
/* Nothing unacked */
|
|
return SCTP_XMIT_OK;
|
|
|
|
if (!sctp_state(asoc, ESTABLISHED))
|
|
return SCTP_XMIT_OK;
|
|
|
|
/* Check whether this chunk and all the rest of pending data will fit
|
|
* or delay in hopes of bundling a full sized packet.
|
|
*/
|
|
if (chunk->skb->len + q->out_qlen >= transport->pathmtu - packet->overhead)
|
|
/* Enough data queued to fill a packet */
|
|
return SCTP_XMIT_OK;
|
|
|
|
/* Don't delay large message writes that may have been fragmented */
|
|
if (!chunk->msg->can_delay)
|
|
return SCTP_XMIT_OK;
|
|
|
|
/* Defer until all data acked or packet full */
|
|
return SCTP_XMIT_DELAY;
|
|
}
|
|
|
|
/* This private function does management things when adding DATA chunk */
|
|
static void sctp_packet_append_data(struct sctp_packet *packet,
|
|
struct sctp_chunk *chunk)
|
|
{
|
|
struct sctp_transport *transport = packet->transport;
|
|
size_t datasize = sctp_data_size(chunk);
|
|
struct sctp_association *asoc = transport->asoc;
|
|
u32 rwnd = asoc->peer.rwnd;
|
|
|
|
/* Keep track of how many bytes are in flight over this transport. */
|
|
transport->flight_size += datasize;
|
|
|
|
/* Keep track of how many bytes are in flight to the receiver. */
|
|
asoc->outqueue.outstanding_bytes += datasize;
|
|
|
|
/* Update our view of the receiver's rwnd. */
|
|
if (datasize < rwnd)
|
|
rwnd -= datasize;
|
|
else
|
|
rwnd = 0;
|
|
|
|
asoc->peer.rwnd = rwnd;
|
|
/* Has been accepted for transmission. */
|
|
if (!asoc->peer.prsctp_capable)
|
|
chunk->msg->can_abandon = 0;
|
|
sctp_chunk_assign_tsn(chunk);
|
|
sctp_chunk_assign_ssn(chunk);
|
|
}
|
|
|
|
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;
|
|
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);
|
|
|
|
/* 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
|
|
* 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.
|
|
*/
|
|
if (sctp_packet_empty(packet) || !sctp_chunk_is_data(chunk) ||
|
|
(!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;
|
|
}
|
|
}
|
|
|
|
return retval;
|
|
}
|