OpenCloudOS-Kernel/net/sctp/ipv6.c

1174 lines
30 KiB
C
Raw Permalink Normal View History

// SPDX-License-Identifier: GPL-2.0-or-later
/* SCTP kernel implementation
* (C) Copyright IBM Corp. 2002, 2004
* Copyright (c) 2001 Nokia, Inc.
* Copyright (c) 2001 La Monte H.P. Yarroll
* Copyright (c) 2002-2003 Intel Corp.
*
* This file is part of the SCTP kernel implementation
*
* SCTP over IPv6.
*
* 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:
* Le Yanqun <yanqun.le@nokia.com>
* Hui Huang <hui.huang@nokia.com>
* La Monte H.P. Yarroll <piggy@acm.org>
* Sridhar Samudrala <sri@us.ibm.com>
* Jon Grimm <jgrimm@us.ibm.com>
* Ardelle Fan <ardelle.fan@intel.com>
*
* Based on:
* linux/net/ipv6/tcp_ipv6.c
*/
#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
#include <linux/module.h>
#include <linux/errno.h>
#include <linux/types.h>
#include <linux/socket.h>
#include <linux/sockios.h>
#include <linux/net.h>
#include <linux/in.h>
#include <linux/in6.h>
#include <linux/netdevice.h>
#include <linux/init.h>
#include <linux/ipsec.h>
include cleanup: Update gfp.h and slab.h includes to prepare for breaking implicit slab.h inclusion from percpu.h percpu.h is included by sched.h and module.h and thus ends up being included when building most .c files. percpu.h includes slab.h which in turn includes gfp.h making everything defined by the two files universally available and complicating inclusion dependencies. percpu.h -> slab.h dependency is about to be removed. Prepare for this change by updating users of gfp and slab facilities include those headers directly instead of assuming availability. As this conversion needs to touch large number of source files, the following script is used as the basis of conversion. http://userweb.kernel.org/~tj/misc/slabh-sweep.py The script does the followings. * Scan files for gfp and slab usages and update includes such that only the necessary includes are there. ie. if only gfp is used, gfp.h, if slab is used, slab.h. * When the script inserts a new include, it looks at the include blocks and try to put the new include such that its order conforms to its surrounding. It's put in the include block which contains core kernel includes, in the same order that the rest are ordered - alphabetical, Christmas tree, rev-Xmas-tree or at the end if there doesn't seem to be any matching order. * If the script can't find a place to put a new include (mostly because the file doesn't have fitting include block), it prints out an error message indicating which .h file needs to be added to the file. The conversion was done in the following steps. 1. The initial automatic conversion of all .c files updated slightly over 4000 files, deleting around 700 includes and adding ~480 gfp.h and ~3000 slab.h inclusions. The script emitted errors for ~400 files. 2. Each error was manually checked. Some didn't need the inclusion, some needed manual addition while adding it to implementation .h or embedding .c file was more appropriate for others. This step added inclusions to around 150 files. 3. The script was run again and the output was compared to the edits from #2 to make sure no file was left behind. 4. Several build tests were done and a couple of problems were fixed. e.g. lib/decompress_*.c used malloc/free() wrappers around slab APIs requiring slab.h to be added manually. 5. The script was run on all .h files but without automatically editing them as sprinkling gfp.h and slab.h inclusions around .h files could easily lead to inclusion dependency hell. Most gfp.h inclusion directives were ignored as stuff from gfp.h was usually wildly available and often used in preprocessor macros. Each slab.h inclusion directive was examined and added manually as necessary. 6. percpu.h was updated not to include slab.h. 7. Build test were done on the following configurations and failures were fixed. CONFIG_GCOV_KERNEL was turned off for all tests (as my distributed build env didn't work with gcov compiles) and a few more options had to be turned off depending on archs to make things build (like ipr on powerpc/64 which failed due to missing writeq). * x86 and x86_64 UP and SMP allmodconfig and a custom test config. * powerpc and powerpc64 SMP allmodconfig * sparc and sparc64 SMP allmodconfig * ia64 SMP allmodconfig * s390 SMP allmodconfig * alpha SMP allmodconfig * um on x86_64 SMP allmodconfig 8. percpu.h modifications were reverted so that it could be applied as a separate patch and serve as bisection point. Given the fact that I had only a couple of failures from tests on step 6, I'm fairly confident about the coverage of this conversion patch. If there is a breakage, it's likely to be something in one of the arch headers which should be easily discoverable easily on most builds of the specific arch. Signed-off-by: Tejun Heo <tj@kernel.org> Guess-its-ok-by: Christoph Lameter <cl@linux-foundation.org> Cc: Ingo Molnar <mingo@redhat.com> Cc: Lee Schermerhorn <Lee.Schermerhorn@hp.com>
2010-03-24 16:04:11 +08:00
#include <linux/slab.h>
#include <linux/ipv6.h>
#include <linux/icmpv6.h>
#include <linux/random.h>
#include <linux/seq_file.h>
#include <net/protocol.h>
#include <net/ndisc.h>
#include <net/ip.h>
#include <net/ipv6.h>
#include <net/transp_v6.h>
#include <net/addrconf.h>
#include <net/ip6_route.h>
#include <net/inet_common.h>
#include <net/inet_ecn.h>
#include <net/sctp/sctp.h>
#include <linux/uaccess.h>
static inline int sctp_v6_addr_match_len(union sctp_addr *s1,
union sctp_addr *s2);
static void sctp_v6_to_addr(union sctp_addr *addr, struct in6_addr *saddr,
__be16 port);
static int sctp_v6_cmp_addr(const union sctp_addr *addr1,
const union sctp_addr *addr2);
/* Event handler for inet6 address addition/deletion events.
* The sctp_local_addr_list needs to be protocted by a spin lock since
* multiple notifiers (say IPv4 and IPv6) may be running at the same
* time and thus corrupt the list.
* The reader side is protected with RCU.
*/
static int sctp_inet6addr_event(struct notifier_block *this, unsigned long ev,
void *ptr)
{
struct inet6_ifaddr *ifa = (struct inet6_ifaddr *)ptr;
struct sctp_sockaddr_entry *addr = NULL;
struct sctp_sockaddr_entry *temp;
struct net *net = dev_net(ifa->idev->dev);
int found = 0;
switch (ev) {
case NETDEV_UP:
addr = kzalloc(sizeof(*addr), GFP_ATOMIC);
if (addr) {
addr->a.v6.sin6_family = AF_INET6;
addr->a.v6.sin6_addr = ifa->addr;
addr->a.v6.sin6_scope_id = ifa->idev->dev->ifindex;
addr->valid = 1;
spin_lock_bh(&net->sctp.local_addr_lock);
list_add_tail_rcu(&addr->list, &net->sctp.local_addr_list);
sctp_addr_wq_mgmt(net, addr, SCTP_ADDR_NEW);
spin_unlock_bh(&net->sctp.local_addr_lock);
}
break;
case NETDEV_DOWN:
spin_lock_bh(&net->sctp.local_addr_lock);
list_for_each_entry_safe(addr, temp,
&net->sctp.local_addr_list, list) {
if (addr->a.sa.sa_family == AF_INET6 &&
ipv6_addr_equal(&addr->a.v6.sin6_addr,
&ifa->addr)) {
sctp_addr_wq_mgmt(net, addr, SCTP_ADDR_DEL);
found = 1;
addr->valid = 0;
list_del_rcu(&addr->list);
break;
}
}
spin_unlock_bh(&net->sctp.local_addr_lock);
if (found)
kfree_rcu(addr, rcu);
break;
}
return NOTIFY_DONE;
}
static struct notifier_block sctp_inet6addr_notifier = {
.notifier_call = sctp_inet6addr_event,
};
/* ICMP error handler. */
static int sctp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
u8 type, u8 code, int offset, __be32 info)
{
struct inet6_dev *idev;
struct sock *sk;
struct sctp_association *asoc;
struct sctp_transport *transport;
struct ipv6_pinfo *np;
__u16 saveip, savesctp;
int err, ret = 0;
struct net *net = dev_net(skb->dev);
idev = in6_dev_get(skb->dev);
/* Fix up skb to look at the embedded net header. */
saveip = skb->network_header;
savesctp = skb->transport_header;
skb_reset_network_header(skb);
skb_set_transport_header(skb, offset);
sk = sctp_err_lookup(net, AF_INET6, skb, sctp_hdr(skb), &asoc, &transport);
/* Put back, the original pointers. */
skb->network_header = saveip;
skb->transport_header = savesctp;
if (!sk) {
__ICMP6_INC_STATS(net, idev, ICMP6_MIB_INERRORS);
ret = -ENOENT;
goto out;
}
/* Warning: The sock lock is held. Remember to call
* sctp_err_finish!
*/
switch (type) {
case ICMPV6_PKT_TOOBIG:
if (ip6_sk_accept_pmtu(sk))
sctp_icmp_frag_needed(sk, asoc, transport, ntohl(info));
goto out_unlock;
case ICMPV6_PARAMPROB:
if (ICMPV6_UNK_NEXTHDR == code) {
sctp_icmp_proto_unreachable(sk, asoc, transport);
goto out_unlock;
}
break;
case NDISC_REDIRECT:
sctp_icmp_redirect(sk, transport, skb);
goto out_unlock;
default:
break;
}
np = inet6_sk(sk);
icmpv6_err_convert(type, code, &err);
if (!sock_owned_by_user(sk) && np->recverr) {
sk->sk_err = err;
sk->sk_error_report(sk);
} else { /* Only an error on timeout */
sk->sk_err_soft = err;
}
out_unlock:
sctp_err_finish(sk, transport);
out:
if (likely(idev != NULL))
in6_dev_put(idev);
return ret;
}
static int sctp_v6_xmit(struct sk_buff *skb, struct sctp_transport *transport)
{
struct sock *sk = skb->sk;
struct ipv6_pinfo *np = inet6_sk(sk);
net: sctp: fix ipv6 ipsec encryption bug in sctp_v6_xmit Alan Chester reported an issue with IPv6 on SCTP that IPsec traffic is not being encrypted, whereas on IPv4 it is. Setting up an AH + ESP transport does not seem to have the desired effect: SCTP + IPv4: 22:14:20.809645 IP (tos 0x2,ECT(0), ttl 64, id 0, offset 0, flags [DF], proto AH (51), length 116) 192.168.0.2 > 192.168.0.5: AH(spi=0x00000042,sumlen=16,seq=0x1): ESP(spi=0x00000044,seq=0x1), length 72 22:14:20.813270 IP (tos 0x2,ECT(0), ttl 64, id 0, offset 0, flags [DF], proto AH (51), length 340) 192.168.0.5 > 192.168.0.2: AH(spi=0x00000043,sumlen=16,seq=0x1): SCTP + IPv6: 22:31:19.215029 IP6 (class 0x02, hlim 64, next-header SCTP (132) payload length: 364) fe80::222:15ff:fe87:7fc.3333 > fe80::92e6:baff:fe0d:5a54.36767: sctp 1) [INIT ACK] [init tag: 747759530] [rwnd: 62464] [OS: 10] [MIS: 10] Moreover, Alan says: This problem was seen with both Racoon and Racoon2. Other people have seen this with OpenSwan. When IPsec is configured to encrypt all upper layer protocols the SCTP connection does not initialize. After using Wireshark to follow packets, this is because the SCTP packet leaves Box A unencrypted and Box B believes all upper layer protocols are to be encrypted so it drops this packet, causing the SCTP connection to fail to initialize. When IPsec is configured to encrypt just SCTP, the SCTP packets are observed unencrypted. In fact, using `socat sctp6-listen:3333 -` on one end and transferring "plaintext" string on the other end, results in cleartext on the wire where SCTP eventually does not report any errors, thus in the latter case that Alan reports, the non-paranoid user might think he's communicating over an encrypted transport on SCTP although he's not (tcpdump ... -X): ... 0x0030: 5d70 8e1a 0003 001a 177d eb6c 0000 0000 ]p.......}.l.... 0x0040: 0000 0000 706c 6169 6e74 6578 740a 0000 ....plaintext... Only in /proc/net/xfrm_stat we can see XfrmInTmplMismatch increasing on the receiver side. Initial follow-up analysis from Alan's bug report was done by Alexey Dobriyan. Also thanks to Vlad Yasevich for feedback on this. SCTP has its own implementation of sctp_v6_xmit() not calling inet6_csk_xmit(). This has the implication that it probably never really got updated along with changes in inet6_csk_xmit() and therefore does not seem to invoke xfrm handlers. SCTP's IPv4 xmit however, properly calls ip_queue_xmit() to do the work. Since a call to inet6_csk_xmit() would solve this problem, but result in unecessary route lookups, let us just use the cached flowi6 instead that we got through sctp_v6_get_dst(). Since all SCTP packets are being sent through sctp_packet_transmit(), we do the route lookup / flow caching in sctp_transport_route(), hold it in tp->dst and skb_dst_set() right after that. If we would alter fl6->daddr in sctp_v6_xmit() to np->opt->srcrt, we possibly could run into the same effect of not having xfrm layer pick it up, hence, use fl6_update_dst() in sctp_v6_get_dst() instead to get the correct source routed dst entry, which we assign to the skb. Also source address routing example from 625034113 ("sctp: fix sctp to work with ipv6 source address routing") still works with this patch! Nevertheless, in RFC5095 it is actually 'recommended' to not use that anyway due to traffic amplification [1]. So it seems we're not supposed to do that anyway in sctp_v6_xmit(). Moreover, if we overwrite the flow destination here, the lower IPv6 layer will be unable to put the correct destination address into IP header, as routing header is added in ipv6_push_nfrag_opts() but then probably with wrong final destination. Things aside, result of this patch is that we do not have any XfrmInTmplMismatch increase plus on the wire with this patch it now looks like: SCTP + IPv6: 08:17:47.074080 IP6 2620:52:0:102f:7a2b:cbff:fe27:1b0a > 2620:52:0:102f:213:72ff:fe32:7eba: AH(spi=0x00005fb4,seq=0x1): ESP(spi=0x00005fb5,seq=0x1), length 72 08:17:47.074264 IP6 2620:52:0:102f:213:72ff:fe32:7eba > 2620:52:0:102f:7a2b:cbff:fe27:1b0a: AH(spi=0x00003d54,seq=0x1): ESP(spi=0x00003d55,seq=0x1), length 296 This fixes Kernel Bugzilla 24412. This security issue seems to be present since 2.6.18 kernels. Lets just hope some big passive adversary in the wild didn't have its fun with that. lksctp-tools IPv6 regression test suite passes as well with this patch. [1] http://www.secdev.org/conf/IPv6_RH_security-csw07.pdf Reported-by: Alan Chester <alan.chester@tekelec.com> Reported-by: Alexey Dobriyan <adobriyan@gmail.com> Signed-off-by: Daniel Borkmann <dborkman@redhat.com> Cc: Steffen Klassert <steffen.klassert@secunet.com> Cc: Hannes Frederic Sowa <hannes@stressinduktion.org> Acked-by: Vlad Yasevich <vyasevich@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2013-09-11 22:58:36 +08:00
struct flowi6 *fl6 = &transport->fl.u.ip6;
__u8 tclass = np->tclass;
int res;
net: sctp: rework debugging framework to use pr_debug and friends We should get rid of all own SCTP debug printk macros and use the ones that the kernel offers anyway instead. This makes the code more readable and conform to the kernel code, and offers all the features of dynamic debbuging that pr_debug() et al has, such as only turning on/off portions of debug messages at runtime through debugfs. The runtime cost of having CONFIG_DYNAMIC_DEBUG enabled, but none of the debug statements printing, is negligible [1]. If kernel debugging is completly turned off, then these statements will also compile into "empty" functions. While we're at it, we also need to change the Kconfig option as it /now/ only refers to the ifdef'ed code portions in outqueue.c that enable further debugging/tracing of SCTP transaction fields. Also, since SCTP_ASSERT code was enabled with this Kconfig option and has now been removed, we transform those code parts into WARNs resp. where appropriate BUG_ONs so that those bugs can be more easily detected as probably not many people have SCTP debugging permanently turned on. To turn on all SCTP debugging, the following steps are needed: # mount -t debugfs none /sys/kernel/debug # echo -n 'module sctp +p' > /sys/kernel/debug/dynamic_debug/control This can be done more fine-grained on a per file, per line basis and others as described in [2]. [1] https://www.kernel.org/doc/ols/2009/ols2009-pages-39-46.pdf [2] Documentation/dynamic-debug-howto.txt Signed-off-by: Daniel Borkmann <dborkman@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2013-06-29 01:49:40 +08:00
pr_debug("%s: skb:%p, len:%d, src:%pI6 dst:%pI6\n", __func__, skb,
net: sctp: fix ipv6 ipsec encryption bug in sctp_v6_xmit Alan Chester reported an issue with IPv6 on SCTP that IPsec traffic is not being encrypted, whereas on IPv4 it is. Setting up an AH + ESP transport does not seem to have the desired effect: SCTP + IPv4: 22:14:20.809645 IP (tos 0x2,ECT(0), ttl 64, id 0, offset 0, flags [DF], proto AH (51), length 116) 192.168.0.2 > 192.168.0.5: AH(spi=0x00000042,sumlen=16,seq=0x1): ESP(spi=0x00000044,seq=0x1), length 72 22:14:20.813270 IP (tos 0x2,ECT(0), ttl 64, id 0, offset 0, flags [DF], proto AH (51), length 340) 192.168.0.5 > 192.168.0.2: AH(spi=0x00000043,sumlen=16,seq=0x1): SCTP + IPv6: 22:31:19.215029 IP6 (class 0x02, hlim 64, next-header SCTP (132) payload length: 364) fe80::222:15ff:fe87:7fc.3333 > fe80::92e6:baff:fe0d:5a54.36767: sctp 1) [INIT ACK] [init tag: 747759530] [rwnd: 62464] [OS: 10] [MIS: 10] Moreover, Alan says: This problem was seen with both Racoon and Racoon2. Other people have seen this with OpenSwan. When IPsec is configured to encrypt all upper layer protocols the SCTP connection does not initialize. After using Wireshark to follow packets, this is because the SCTP packet leaves Box A unencrypted and Box B believes all upper layer protocols are to be encrypted so it drops this packet, causing the SCTP connection to fail to initialize. When IPsec is configured to encrypt just SCTP, the SCTP packets are observed unencrypted. In fact, using `socat sctp6-listen:3333 -` on one end and transferring "plaintext" string on the other end, results in cleartext on the wire where SCTP eventually does not report any errors, thus in the latter case that Alan reports, the non-paranoid user might think he's communicating over an encrypted transport on SCTP although he's not (tcpdump ... -X): ... 0x0030: 5d70 8e1a 0003 001a 177d eb6c 0000 0000 ]p.......}.l.... 0x0040: 0000 0000 706c 6169 6e74 6578 740a 0000 ....plaintext... Only in /proc/net/xfrm_stat we can see XfrmInTmplMismatch increasing on the receiver side. Initial follow-up analysis from Alan's bug report was done by Alexey Dobriyan. Also thanks to Vlad Yasevich for feedback on this. SCTP has its own implementation of sctp_v6_xmit() not calling inet6_csk_xmit(). This has the implication that it probably never really got updated along with changes in inet6_csk_xmit() and therefore does not seem to invoke xfrm handlers. SCTP's IPv4 xmit however, properly calls ip_queue_xmit() to do the work. Since a call to inet6_csk_xmit() would solve this problem, but result in unecessary route lookups, let us just use the cached flowi6 instead that we got through sctp_v6_get_dst(). Since all SCTP packets are being sent through sctp_packet_transmit(), we do the route lookup / flow caching in sctp_transport_route(), hold it in tp->dst and skb_dst_set() right after that. If we would alter fl6->daddr in sctp_v6_xmit() to np->opt->srcrt, we possibly could run into the same effect of not having xfrm layer pick it up, hence, use fl6_update_dst() in sctp_v6_get_dst() instead to get the correct source routed dst entry, which we assign to the skb. Also source address routing example from 625034113 ("sctp: fix sctp to work with ipv6 source address routing") still works with this patch! Nevertheless, in RFC5095 it is actually 'recommended' to not use that anyway due to traffic amplification [1]. So it seems we're not supposed to do that anyway in sctp_v6_xmit(). Moreover, if we overwrite the flow destination here, the lower IPv6 layer will be unable to put the correct destination address into IP header, as routing header is added in ipv6_push_nfrag_opts() but then probably with wrong final destination. Things aside, result of this patch is that we do not have any XfrmInTmplMismatch increase plus on the wire with this patch it now looks like: SCTP + IPv6: 08:17:47.074080 IP6 2620:52:0:102f:7a2b:cbff:fe27:1b0a > 2620:52:0:102f:213:72ff:fe32:7eba: AH(spi=0x00005fb4,seq=0x1): ESP(spi=0x00005fb5,seq=0x1), length 72 08:17:47.074264 IP6 2620:52:0:102f:213:72ff:fe32:7eba > 2620:52:0:102f:7a2b:cbff:fe27:1b0a: AH(spi=0x00003d54,seq=0x1): ESP(spi=0x00003d55,seq=0x1), length 296 This fixes Kernel Bugzilla 24412. This security issue seems to be present since 2.6.18 kernels. Lets just hope some big passive adversary in the wild didn't have its fun with that. lksctp-tools IPv6 regression test suite passes as well with this patch. [1] http://www.secdev.org/conf/IPv6_RH_security-csw07.pdf Reported-by: Alan Chester <alan.chester@tekelec.com> Reported-by: Alexey Dobriyan <adobriyan@gmail.com> Signed-off-by: Daniel Borkmann <dborkman@redhat.com> Cc: Steffen Klassert <steffen.klassert@secunet.com> Cc: Hannes Frederic Sowa <hannes@stressinduktion.org> Acked-by: Vlad Yasevich <vyasevich@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2013-09-11 22:58:36 +08:00
skb->len, &fl6->saddr, &fl6->daddr);
if (transport->dscp & SCTP_DSCP_SET_MASK)
tclass = transport->dscp & SCTP_DSCP_VAL_MASK;
if (INET_ECN_is_capable(tclass))
IP6_ECN_flow_xmit(sk, fl6->flowlabel);
if (!(transport->param_flags & SPP_PMTUD_ENABLE))
skb->ignore_df = 1;
net: sctp: fix ipv6 ipsec encryption bug in sctp_v6_xmit Alan Chester reported an issue with IPv6 on SCTP that IPsec traffic is not being encrypted, whereas on IPv4 it is. Setting up an AH + ESP transport does not seem to have the desired effect: SCTP + IPv4: 22:14:20.809645 IP (tos 0x2,ECT(0), ttl 64, id 0, offset 0, flags [DF], proto AH (51), length 116) 192.168.0.2 > 192.168.0.5: AH(spi=0x00000042,sumlen=16,seq=0x1): ESP(spi=0x00000044,seq=0x1), length 72 22:14:20.813270 IP (tos 0x2,ECT(0), ttl 64, id 0, offset 0, flags [DF], proto AH (51), length 340) 192.168.0.5 > 192.168.0.2: AH(spi=0x00000043,sumlen=16,seq=0x1): SCTP + IPv6: 22:31:19.215029 IP6 (class 0x02, hlim 64, next-header SCTP (132) payload length: 364) fe80::222:15ff:fe87:7fc.3333 > fe80::92e6:baff:fe0d:5a54.36767: sctp 1) [INIT ACK] [init tag: 747759530] [rwnd: 62464] [OS: 10] [MIS: 10] Moreover, Alan says: This problem was seen with both Racoon and Racoon2. Other people have seen this with OpenSwan. When IPsec is configured to encrypt all upper layer protocols the SCTP connection does not initialize. After using Wireshark to follow packets, this is because the SCTP packet leaves Box A unencrypted and Box B believes all upper layer protocols are to be encrypted so it drops this packet, causing the SCTP connection to fail to initialize. When IPsec is configured to encrypt just SCTP, the SCTP packets are observed unencrypted. In fact, using `socat sctp6-listen:3333 -` on one end and transferring "plaintext" string on the other end, results in cleartext on the wire where SCTP eventually does not report any errors, thus in the latter case that Alan reports, the non-paranoid user might think he's communicating over an encrypted transport on SCTP although he's not (tcpdump ... -X): ... 0x0030: 5d70 8e1a 0003 001a 177d eb6c 0000 0000 ]p.......}.l.... 0x0040: 0000 0000 706c 6169 6e74 6578 740a 0000 ....plaintext... Only in /proc/net/xfrm_stat we can see XfrmInTmplMismatch increasing on the receiver side. Initial follow-up analysis from Alan's bug report was done by Alexey Dobriyan. Also thanks to Vlad Yasevich for feedback on this. SCTP has its own implementation of sctp_v6_xmit() not calling inet6_csk_xmit(). This has the implication that it probably never really got updated along with changes in inet6_csk_xmit() and therefore does not seem to invoke xfrm handlers. SCTP's IPv4 xmit however, properly calls ip_queue_xmit() to do the work. Since a call to inet6_csk_xmit() would solve this problem, but result in unecessary route lookups, let us just use the cached flowi6 instead that we got through sctp_v6_get_dst(). Since all SCTP packets are being sent through sctp_packet_transmit(), we do the route lookup / flow caching in sctp_transport_route(), hold it in tp->dst and skb_dst_set() right after that. If we would alter fl6->daddr in sctp_v6_xmit() to np->opt->srcrt, we possibly could run into the same effect of not having xfrm layer pick it up, hence, use fl6_update_dst() in sctp_v6_get_dst() instead to get the correct source routed dst entry, which we assign to the skb. Also source address routing example from 625034113 ("sctp: fix sctp to work with ipv6 source address routing") still works with this patch! Nevertheless, in RFC5095 it is actually 'recommended' to not use that anyway due to traffic amplification [1]. So it seems we're not supposed to do that anyway in sctp_v6_xmit(). Moreover, if we overwrite the flow destination here, the lower IPv6 layer will be unable to put the correct destination address into IP header, as routing header is added in ipv6_push_nfrag_opts() but then probably with wrong final destination. Things aside, result of this patch is that we do not have any XfrmInTmplMismatch increase plus on the wire with this patch it now looks like: SCTP + IPv6: 08:17:47.074080 IP6 2620:52:0:102f:7a2b:cbff:fe27:1b0a > 2620:52:0:102f:213:72ff:fe32:7eba: AH(spi=0x00005fb4,seq=0x1): ESP(spi=0x00005fb5,seq=0x1), length 72 08:17:47.074264 IP6 2620:52:0:102f:213:72ff:fe32:7eba > 2620:52:0:102f:7a2b:cbff:fe27:1b0a: AH(spi=0x00003d54,seq=0x1): ESP(spi=0x00003d55,seq=0x1), length 296 This fixes Kernel Bugzilla 24412. This security issue seems to be present since 2.6.18 kernels. Lets just hope some big passive adversary in the wild didn't have its fun with that. lksctp-tools IPv6 regression test suite passes as well with this patch. [1] http://www.secdev.org/conf/IPv6_RH_security-csw07.pdf Reported-by: Alan Chester <alan.chester@tekelec.com> Reported-by: Alexey Dobriyan <adobriyan@gmail.com> Signed-off-by: Daniel Borkmann <dborkman@redhat.com> Cc: Steffen Klassert <steffen.klassert@secunet.com> Cc: Hannes Frederic Sowa <hannes@stressinduktion.org> Acked-by: Vlad Yasevich <vyasevich@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2013-09-11 22:58:36 +08:00
SCTP_INC_STATS(sock_net(sk), SCTP_MIB_OUTSCTPPACKS);
rcu_read_lock();
res = ip6_xmit(sk, skb, fl6, sk->sk_mark, rcu_dereference(np->opt),
tclass, sk->sk_priority);
rcu_read_unlock();
return res;
}
/* Returns the dst cache entry for the given source and destination ip
* addresses.
*/
static void sctp_v6_get_dst(struct sctp_transport *t, union sctp_addr *saddr,
struct flowi *fl, struct sock *sk)
{
struct sctp_association *asoc = t->asoc;
struct dst_entry *dst = NULL;
struct flowi _fl;
struct flowi6 *fl6 = &_fl.u.ip6;
struct sctp_bind_addr *bp;
net: sctp: fix ipv6 ipsec encryption bug in sctp_v6_xmit Alan Chester reported an issue with IPv6 on SCTP that IPsec traffic is not being encrypted, whereas on IPv4 it is. Setting up an AH + ESP transport does not seem to have the desired effect: SCTP + IPv4: 22:14:20.809645 IP (tos 0x2,ECT(0), ttl 64, id 0, offset 0, flags [DF], proto AH (51), length 116) 192.168.0.2 > 192.168.0.5: AH(spi=0x00000042,sumlen=16,seq=0x1): ESP(spi=0x00000044,seq=0x1), length 72 22:14:20.813270 IP (tos 0x2,ECT(0), ttl 64, id 0, offset 0, flags [DF], proto AH (51), length 340) 192.168.0.5 > 192.168.0.2: AH(spi=0x00000043,sumlen=16,seq=0x1): SCTP + IPv6: 22:31:19.215029 IP6 (class 0x02, hlim 64, next-header SCTP (132) payload length: 364) fe80::222:15ff:fe87:7fc.3333 > fe80::92e6:baff:fe0d:5a54.36767: sctp 1) [INIT ACK] [init tag: 747759530] [rwnd: 62464] [OS: 10] [MIS: 10] Moreover, Alan says: This problem was seen with both Racoon and Racoon2. Other people have seen this with OpenSwan. When IPsec is configured to encrypt all upper layer protocols the SCTP connection does not initialize. After using Wireshark to follow packets, this is because the SCTP packet leaves Box A unencrypted and Box B believes all upper layer protocols are to be encrypted so it drops this packet, causing the SCTP connection to fail to initialize. When IPsec is configured to encrypt just SCTP, the SCTP packets are observed unencrypted. In fact, using `socat sctp6-listen:3333 -` on one end and transferring "plaintext" string on the other end, results in cleartext on the wire where SCTP eventually does not report any errors, thus in the latter case that Alan reports, the non-paranoid user might think he's communicating over an encrypted transport on SCTP although he's not (tcpdump ... -X): ... 0x0030: 5d70 8e1a 0003 001a 177d eb6c 0000 0000 ]p.......}.l.... 0x0040: 0000 0000 706c 6169 6e74 6578 740a 0000 ....plaintext... Only in /proc/net/xfrm_stat we can see XfrmInTmplMismatch increasing on the receiver side. Initial follow-up analysis from Alan's bug report was done by Alexey Dobriyan. Also thanks to Vlad Yasevich for feedback on this. SCTP has its own implementation of sctp_v6_xmit() not calling inet6_csk_xmit(). This has the implication that it probably never really got updated along with changes in inet6_csk_xmit() and therefore does not seem to invoke xfrm handlers. SCTP's IPv4 xmit however, properly calls ip_queue_xmit() to do the work. Since a call to inet6_csk_xmit() would solve this problem, but result in unecessary route lookups, let us just use the cached flowi6 instead that we got through sctp_v6_get_dst(). Since all SCTP packets are being sent through sctp_packet_transmit(), we do the route lookup / flow caching in sctp_transport_route(), hold it in tp->dst and skb_dst_set() right after that. If we would alter fl6->daddr in sctp_v6_xmit() to np->opt->srcrt, we possibly could run into the same effect of not having xfrm layer pick it up, hence, use fl6_update_dst() in sctp_v6_get_dst() instead to get the correct source routed dst entry, which we assign to the skb. Also source address routing example from 625034113 ("sctp: fix sctp to work with ipv6 source address routing") still works with this patch! Nevertheless, in RFC5095 it is actually 'recommended' to not use that anyway due to traffic amplification [1]. So it seems we're not supposed to do that anyway in sctp_v6_xmit(). Moreover, if we overwrite the flow destination here, the lower IPv6 layer will be unable to put the correct destination address into IP header, as routing header is added in ipv6_push_nfrag_opts() but then probably with wrong final destination. Things aside, result of this patch is that we do not have any XfrmInTmplMismatch increase plus on the wire with this patch it now looks like: SCTP + IPv6: 08:17:47.074080 IP6 2620:52:0:102f:7a2b:cbff:fe27:1b0a > 2620:52:0:102f:213:72ff:fe32:7eba: AH(spi=0x00005fb4,seq=0x1): ESP(spi=0x00005fb5,seq=0x1), length 72 08:17:47.074264 IP6 2620:52:0:102f:213:72ff:fe32:7eba > 2620:52:0:102f:7a2b:cbff:fe27:1b0a: AH(spi=0x00003d54,seq=0x1): ESP(spi=0x00003d55,seq=0x1), length 296 This fixes Kernel Bugzilla 24412. This security issue seems to be present since 2.6.18 kernels. Lets just hope some big passive adversary in the wild didn't have its fun with that. lksctp-tools IPv6 regression test suite passes as well with this patch. [1] http://www.secdev.org/conf/IPv6_RH_security-csw07.pdf Reported-by: Alan Chester <alan.chester@tekelec.com> Reported-by: Alexey Dobriyan <adobriyan@gmail.com> Signed-off-by: Daniel Borkmann <dborkman@redhat.com> Cc: Steffen Klassert <steffen.klassert@secunet.com> Cc: Hannes Frederic Sowa <hannes@stressinduktion.org> Acked-by: Vlad Yasevich <vyasevich@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2013-09-11 22:58:36 +08:00
struct ipv6_pinfo *np = inet6_sk(sk);
struct sctp_sockaddr_entry *laddr;
union sctp_addr *daddr = &t->ipaddr;
union sctp_addr dst_saddr;
net: sctp: fix ipv6 ipsec encryption bug in sctp_v6_xmit Alan Chester reported an issue with IPv6 on SCTP that IPsec traffic is not being encrypted, whereas on IPv4 it is. Setting up an AH + ESP transport does not seem to have the desired effect: SCTP + IPv4: 22:14:20.809645 IP (tos 0x2,ECT(0), ttl 64, id 0, offset 0, flags [DF], proto AH (51), length 116) 192.168.0.2 > 192.168.0.5: AH(spi=0x00000042,sumlen=16,seq=0x1): ESP(spi=0x00000044,seq=0x1), length 72 22:14:20.813270 IP (tos 0x2,ECT(0), ttl 64, id 0, offset 0, flags [DF], proto AH (51), length 340) 192.168.0.5 > 192.168.0.2: AH(spi=0x00000043,sumlen=16,seq=0x1): SCTP + IPv6: 22:31:19.215029 IP6 (class 0x02, hlim 64, next-header SCTP (132) payload length: 364) fe80::222:15ff:fe87:7fc.3333 > fe80::92e6:baff:fe0d:5a54.36767: sctp 1) [INIT ACK] [init tag: 747759530] [rwnd: 62464] [OS: 10] [MIS: 10] Moreover, Alan says: This problem was seen with both Racoon and Racoon2. Other people have seen this with OpenSwan. When IPsec is configured to encrypt all upper layer protocols the SCTP connection does not initialize. After using Wireshark to follow packets, this is because the SCTP packet leaves Box A unencrypted and Box B believes all upper layer protocols are to be encrypted so it drops this packet, causing the SCTP connection to fail to initialize. When IPsec is configured to encrypt just SCTP, the SCTP packets are observed unencrypted. In fact, using `socat sctp6-listen:3333 -` on one end and transferring "plaintext" string on the other end, results in cleartext on the wire where SCTP eventually does not report any errors, thus in the latter case that Alan reports, the non-paranoid user might think he's communicating over an encrypted transport on SCTP although he's not (tcpdump ... -X): ... 0x0030: 5d70 8e1a 0003 001a 177d eb6c 0000 0000 ]p.......}.l.... 0x0040: 0000 0000 706c 6169 6e74 6578 740a 0000 ....plaintext... Only in /proc/net/xfrm_stat we can see XfrmInTmplMismatch increasing on the receiver side. Initial follow-up analysis from Alan's bug report was done by Alexey Dobriyan. Also thanks to Vlad Yasevich for feedback on this. SCTP has its own implementation of sctp_v6_xmit() not calling inet6_csk_xmit(). This has the implication that it probably never really got updated along with changes in inet6_csk_xmit() and therefore does not seem to invoke xfrm handlers. SCTP's IPv4 xmit however, properly calls ip_queue_xmit() to do the work. Since a call to inet6_csk_xmit() would solve this problem, but result in unecessary route lookups, let us just use the cached flowi6 instead that we got through sctp_v6_get_dst(). Since all SCTP packets are being sent through sctp_packet_transmit(), we do the route lookup / flow caching in sctp_transport_route(), hold it in tp->dst and skb_dst_set() right after that. If we would alter fl6->daddr in sctp_v6_xmit() to np->opt->srcrt, we possibly could run into the same effect of not having xfrm layer pick it up, hence, use fl6_update_dst() in sctp_v6_get_dst() instead to get the correct source routed dst entry, which we assign to the skb. Also source address routing example from 625034113 ("sctp: fix sctp to work with ipv6 source address routing") still works with this patch! Nevertheless, in RFC5095 it is actually 'recommended' to not use that anyway due to traffic amplification [1]. So it seems we're not supposed to do that anyway in sctp_v6_xmit(). Moreover, if we overwrite the flow destination here, the lower IPv6 layer will be unable to put the correct destination address into IP header, as routing header is added in ipv6_push_nfrag_opts() but then probably with wrong final destination. Things aside, result of this patch is that we do not have any XfrmInTmplMismatch increase plus on the wire with this patch it now looks like: SCTP + IPv6: 08:17:47.074080 IP6 2620:52:0:102f:7a2b:cbff:fe27:1b0a > 2620:52:0:102f:213:72ff:fe32:7eba: AH(spi=0x00005fb4,seq=0x1): ESP(spi=0x00005fb5,seq=0x1), length 72 08:17:47.074264 IP6 2620:52:0:102f:213:72ff:fe32:7eba > 2620:52:0:102f:7a2b:cbff:fe27:1b0a: AH(spi=0x00003d54,seq=0x1): ESP(spi=0x00003d55,seq=0x1), length 296 This fixes Kernel Bugzilla 24412. This security issue seems to be present since 2.6.18 kernels. Lets just hope some big passive adversary in the wild didn't have its fun with that. lksctp-tools IPv6 regression test suite passes as well with this patch. [1] http://www.secdev.org/conf/IPv6_RH_security-csw07.pdf Reported-by: Alan Chester <alan.chester@tekelec.com> Reported-by: Alexey Dobriyan <adobriyan@gmail.com> Signed-off-by: Daniel Borkmann <dborkman@redhat.com> Cc: Steffen Klassert <steffen.klassert@secunet.com> Cc: Hannes Frederic Sowa <hannes@stressinduktion.org> Acked-by: Vlad Yasevich <vyasevich@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2013-09-11 22:58:36 +08:00
struct in6_addr *final_p, final;
enum sctp_scope scope;
__u8 matchlen = 0;
memset(&_fl, 0, sizeof(_fl));
fl6->daddr = daddr->v6.sin6_addr;
fl6->fl6_dport = daddr->v6.sin6_port;
fl6->flowi6_proto = IPPROTO_SCTP;
if (ipv6_addr_type(&daddr->v6.sin6_addr) & IPV6_ADDR_LINKLOCAL)
fl6->flowi6_oif = daddr->v6.sin6_scope_id;
else if (asoc)
fl6->flowi6_oif = asoc->base.sk->sk_bound_dev_if;
if (t->flowlabel & SCTP_FLOWLABEL_SET_MASK)
fl6->flowlabel = htonl(t->flowlabel & SCTP_FLOWLABEL_VAL_MASK);
if (np->sndflow && (fl6->flowlabel & IPV6_FLOWLABEL_MASK)) {
struct ip6_flowlabel *flowlabel;
flowlabel = fl6_sock_lookup(sk, fl6->flowlabel);
if (IS_ERR(flowlabel))
goto out;
fl6_sock_release(flowlabel);
}
net: sctp: rework debugging framework to use pr_debug and friends We should get rid of all own SCTP debug printk macros and use the ones that the kernel offers anyway instead. This makes the code more readable and conform to the kernel code, and offers all the features of dynamic debbuging that pr_debug() et al has, such as only turning on/off portions of debug messages at runtime through debugfs. The runtime cost of having CONFIG_DYNAMIC_DEBUG enabled, but none of the debug statements printing, is negligible [1]. If kernel debugging is completly turned off, then these statements will also compile into "empty" functions. While we're at it, we also need to change the Kconfig option as it /now/ only refers to the ifdef'ed code portions in outqueue.c that enable further debugging/tracing of SCTP transaction fields. Also, since SCTP_ASSERT code was enabled with this Kconfig option and has now been removed, we transform those code parts into WARNs resp. where appropriate BUG_ONs so that those bugs can be more easily detected as probably not many people have SCTP debugging permanently turned on. To turn on all SCTP debugging, the following steps are needed: # mount -t debugfs none /sys/kernel/debug # echo -n 'module sctp +p' > /sys/kernel/debug/dynamic_debug/control This can be done more fine-grained on a per file, per line basis and others as described in [2]. [1] https://www.kernel.org/doc/ols/2009/ols2009-pages-39-46.pdf [2] Documentation/dynamic-debug-howto.txt Signed-off-by: Daniel Borkmann <dborkman@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2013-06-29 01:49:40 +08:00
pr_debug("%s: dst=%pI6 ", __func__, &fl6->daddr);
if (asoc)
fl6->fl6_sport = htons(asoc->base.bind_addr.port);
if (saddr) {
fl6->saddr = saddr->v6.sin6_addr;
if (!fl6->fl6_sport)
fl6->fl6_sport = saddr->v6.sin6_port;
net: sctp: rework debugging framework to use pr_debug and friends We should get rid of all own SCTP debug printk macros and use the ones that the kernel offers anyway instead. This makes the code more readable and conform to the kernel code, and offers all the features of dynamic debbuging that pr_debug() et al has, such as only turning on/off portions of debug messages at runtime through debugfs. The runtime cost of having CONFIG_DYNAMIC_DEBUG enabled, but none of the debug statements printing, is negligible [1]. If kernel debugging is completly turned off, then these statements will also compile into "empty" functions. While we're at it, we also need to change the Kconfig option as it /now/ only refers to the ifdef'ed code portions in outqueue.c that enable further debugging/tracing of SCTP transaction fields. Also, since SCTP_ASSERT code was enabled with this Kconfig option and has now been removed, we transform those code parts into WARNs resp. where appropriate BUG_ONs so that those bugs can be more easily detected as probably not many people have SCTP debugging permanently turned on. To turn on all SCTP debugging, the following steps are needed: # mount -t debugfs none /sys/kernel/debug # echo -n 'module sctp +p' > /sys/kernel/debug/dynamic_debug/control This can be done more fine-grained on a per file, per line basis and others as described in [2]. [1] https://www.kernel.org/doc/ols/2009/ols2009-pages-39-46.pdf [2] Documentation/dynamic-debug-howto.txt Signed-off-by: Daniel Borkmann <dborkman@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2013-06-29 01:49:40 +08:00
pr_debug("src=%pI6 - ", &fl6->saddr);
}
rcu_read_lock();
final_p = fl6_update_dst(fl6, rcu_dereference(np->opt), &final);
rcu_read_unlock();
dst = ip6_dst_lookup_flow(sock_net(sk), sk, fl6, final_p);
if (!asoc || saddr) {
t->dst = dst;
memcpy(fl, &_fl, sizeof(_fl));
goto out;
}
bp = &asoc->base.bind_addr;
scope = sctp_scope(daddr);
/* ip6_dst_lookup has filled in the fl6->saddr for us. Check
* to see if we can use it.
*/
if (!IS_ERR(dst)) {
/* Walk through the bind address list and look for a bind
* address that matches the source address of the returned dst.
*/
sctp_v6_to_addr(&dst_saddr, &fl6->saddr, htons(bp->port));
rcu_read_lock();
list_for_each_entry_rcu(laddr, &bp->address_list, list) {
if (!laddr->valid || laddr->state == SCTP_ADDR_DEL ||
(laddr->state != SCTP_ADDR_SRC &&
!asoc->src_out_of_asoc_ok))
continue;
/* Do not compare against v4 addrs */
if ((laddr->a.sa.sa_family == AF_INET6) &&
(sctp_v6_cmp_addr(&dst_saddr, &laddr->a))) {
rcu_read_unlock();
t->dst = dst;
memcpy(fl, &_fl, sizeof(_fl));
goto out;
}
}
rcu_read_unlock();
/* None of the bound addresses match the source address of the
* dst. So release it.
*/
dst_release(dst);
dst = NULL;
}
/* Walk through the bind address list and try to get the
* best source address for a given destination.
*/
rcu_read_lock();
list_for_each_entry_rcu(laddr, &bp->address_list, list) {
struct dst_entry *bdst;
__u8 bmatchlen;
if (!laddr->valid ||
laddr->state != SCTP_ADDR_SRC ||
laddr->a.sa.sa_family != AF_INET6 ||
scope > sctp_scope(&laddr->a))
continue;
fl6->saddr = laddr->a.v6.sin6_addr;
fl6->fl6_sport = laddr->a.v6.sin6_port;
final_p = fl6_update_dst(fl6, rcu_dereference(np->opt), &final);
bdst = ip6_dst_lookup_flow(sock_net(sk), sk, fl6, final_p);
if (IS_ERR(bdst))
continue;
if (ipv6_chk_addr(dev_net(bdst->dev),
&laddr->a.v6.sin6_addr, bdst->dev, 1)) {
if (!IS_ERR_OR_NULL(dst))
dst_release(dst);
dst = bdst;
t->dst = dst;
memcpy(fl, &_fl, sizeof(_fl));
break;
}
bmatchlen = sctp_v6_addr_match_len(daddr, &laddr->a);
if (matchlen > bmatchlen) {
dst_release(bdst);
continue;
}
if (!IS_ERR_OR_NULL(dst))
dst_release(dst);
dst = bdst;
matchlen = bmatchlen;
t->dst = dst;
memcpy(fl, &_fl, sizeof(_fl));
}
rcu_read_unlock();
out:
sctp: fix CONFIG_SCTP_DBG_MSG=y null pointer dereference in sctp_v6_get_dst() Trinity (the syscall fuzzer) triggered the following BUG, reproducible only when the kernel is configured with CONFIG_SCTP_DBG_MSG=y. When CONFIG_SCTP_DBG_MSG is not set, the null pointer is never dereferenced. ---[ end trace a4de0bfcb38a3642 ]--- BUG: unable to handle kernel NULL pointer dereference at 0000000000000100 IP: [<ffffffff8136796e>] ip6_string+0x1e/0xa0 PGD 4eead067 PUD 4e472067 PMD 0 Oops: 0000 [#1] PREEMPT SMP Modules linked in: CPU 3 Pid: 21324, comm: trinity-child11 Tainted: G W 3.7.0-rc7+ #61 ASUSTeK Computer INC. EB1012/EB1012 RIP: 0010:[<ffffffff8136796e>] [<ffffffff8136796e>] ip6_string+0x1e/0xa0 RSP: 0018:ffff88004e4637a0 EFLAGS: 00010046 RAX: ffff88004e4637da RBX: ffff88004e4637da RCX: 0000000000000000 RDX: ffffffff8246e92a RSI: 0000000000000100 RDI: ffff88004e4637da RBP: ffff88004e4637a8 R08: 000000000000ffff R09: 000000000000ffff R10: 0000000000000000 R11: 0000000000000000 R12: ffffffff8289d600 R13: ffffffff8289d230 R14: ffffffff8246e928 R15: ffffffff8289d600 FS: 00007fed95153700(0000) GS:ffff88005fd80000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 0000000000000100 CR3: 000000004eeac000 CR4: 00000000000007e0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000ffff0ff0 DR7: 0000000000000400 Process trinity-child11 (pid: 21324, threadinfo ffff88004e462000, task ffff8800524b0000) Stack: ffff88004e4637da ffff88004e463828 ffffffff81368eee 000000004e4637d8 ffffffff0000ffff ffff88000000ffff 0000000000000000 000000004e4637f8 ffffffff826285d8 ffff88004e4637f8 0000000000000000 ffff8800524b06b0 Call Trace: [<ffffffff81368eee>] ip6_addr_string.isra.11+0x3e/0xa0 [<ffffffff81369183>] pointer.isra.12+0x233/0x2d0 [<ffffffff810a413a>] ? vprintk_emit+0x1ba/0x450 [<ffffffff8110953d>] ? trace_hardirqs_on_caller+0x10d/0x1a0 [<ffffffff81369757>] vsnprintf+0x187/0x5d0 [<ffffffff81369c62>] vscnprintf+0x12/0x30 [<ffffffff810a4028>] vprintk_emit+0xa8/0x450 [<ffffffff81e5cb00>] printk+0x49/0x4b [<ffffffff81d17221>] sctp_v6_get_dst+0x731/0x780 [<ffffffff81d16e15>] ? sctp_v6_get_dst+0x325/0x780 [<ffffffff81d00a96>] sctp_transport_route+0x46/0x120 [<ffffffff81cff0f1>] sctp_assoc_add_peer+0x161/0x350 [<ffffffff81d0fd8d>] sctp_sendmsg+0x6cd/0xcb0 [<ffffffff81b55bf0>] ? inet_create+0x670/0x670 [<ffffffff81b55cfb>] inet_sendmsg+0x10b/0x220 [<ffffffff81b55bf0>] ? inet_create+0x670/0x670 [<ffffffff81a72a64>] ? sock_update_classid+0xa4/0x2b0 [<ffffffff81a72ab0>] ? sock_update_classid+0xf0/0x2b0 [<ffffffff81a6ac1c>] sock_sendmsg+0xdc/0xf0 [<ffffffff8118e9e5>] ? might_fault+0x85/0x90 [<ffffffff8118e99c>] ? might_fault+0x3c/0x90 [<ffffffff81a6e12a>] sys_sendto+0xfa/0x130 [<ffffffff810a9887>] ? do_setitimer+0x197/0x380 [<ffffffff81e960d5>] ? sysret_check+0x22/0x5d [<ffffffff81e960a9>] system_call_fastpath+0x16/0x1b Code: 01 eb 89 66 2e 0f 1f 84 00 00 00 00 00 55 48 89 f8 31 c9 48 89 e5 53 eb 12 0f 1f 40 00 48 83 c1 01 48 83 c0 04 48 83 f9 08 74 70 <0f> b6 3c 4e 89 fb 83 e7 0f c0 eb 04 41 89 d8 41 83 e0 0f 0f b6 RIP [<ffffffff8136796e>] ip6_string+0x1e/0xa0 RSP <ffff88004e4637a0> CR2: 0000000000000100 ---[ end trace a4de0bfcb38a3643 ]--- Signed-off-by: Tommi Rantala <tt.rantala@gmail.com> Acked-by: Vlad Yasevich <vyasevich@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2012-11-30 07:17:42 +08:00
if (!IS_ERR_OR_NULL(dst)) {
struct rt6_info *rt;
net: sctp: rework debugging framework to use pr_debug and friends We should get rid of all own SCTP debug printk macros and use the ones that the kernel offers anyway instead. This makes the code more readable and conform to the kernel code, and offers all the features of dynamic debbuging that pr_debug() et al has, such as only turning on/off portions of debug messages at runtime through debugfs. The runtime cost of having CONFIG_DYNAMIC_DEBUG enabled, but none of the debug statements printing, is negligible [1]. If kernel debugging is completly turned off, then these statements will also compile into "empty" functions. While we're at it, we also need to change the Kconfig option as it /now/ only refers to the ifdef'ed code portions in outqueue.c that enable further debugging/tracing of SCTP transaction fields. Also, since SCTP_ASSERT code was enabled with this Kconfig option and has now been removed, we transform those code parts into WARNs resp. where appropriate BUG_ONs so that those bugs can be more easily detected as probably not many people have SCTP debugging permanently turned on. To turn on all SCTP debugging, the following steps are needed: # mount -t debugfs none /sys/kernel/debug # echo -n 'module sctp +p' > /sys/kernel/debug/dynamic_debug/control This can be done more fine-grained on a per file, per line basis and others as described in [2]. [1] https://www.kernel.org/doc/ols/2009/ols2009-pages-39-46.pdf [2] Documentation/dynamic-debug-howto.txt Signed-off-by: Daniel Borkmann <dborkman@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2013-06-29 01:49:40 +08:00
rt = (struct rt6_info *)dst;
t->dst_cookie = rt6_get_cookie(rt);
pr_debug("rt6_dst:%pI6/%d rt6_src:%pI6\n",
&rt->rt6i_dst.addr, rt->rt6i_dst.plen,
&fl->u.ip6.saddr);
} else {
t->dst = NULL;
net: sctp: rework debugging framework to use pr_debug and friends We should get rid of all own SCTP debug printk macros and use the ones that the kernel offers anyway instead. This makes the code more readable and conform to the kernel code, and offers all the features of dynamic debbuging that pr_debug() et al has, such as only turning on/off portions of debug messages at runtime through debugfs. The runtime cost of having CONFIG_DYNAMIC_DEBUG enabled, but none of the debug statements printing, is negligible [1]. If kernel debugging is completly turned off, then these statements will also compile into "empty" functions. While we're at it, we also need to change the Kconfig option as it /now/ only refers to the ifdef'ed code portions in outqueue.c that enable further debugging/tracing of SCTP transaction fields. Also, since SCTP_ASSERT code was enabled with this Kconfig option and has now been removed, we transform those code parts into WARNs resp. where appropriate BUG_ONs so that those bugs can be more easily detected as probably not many people have SCTP debugging permanently turned on. To turn on all SCTP debugging, the following steps are needed: # mount -t debugfs none /sys/kernel/debug # echo -n 'module sctp +p' > /sys/kernel/debug/dynamic_debug/control This can be done more fine-grained on a per file, per line basis and others as described in [2]. [1] https://www.kernel.org/doc/ols/2009/ols2009-pages-39-46.pdf [2] Documentation/dynamic-debug-howto.txt Signed-off-by: Daniel Borkmann <dborkman@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2013-06-29 01:49:40 +08:00
pr_debug("no route\n");
}
}
/* Returns the number of consecutive initial bits that match in the 2 ipv6
* addresses.
*/
static inline int sctp_v6_addr_match_len(union sctp_addr *s1,
union sctp_addr *s2)
{
return ipv6_addr_diff(&s1->v6.sin6_addr, &s2->v6.sin6_addr);
}
/* Fills in the source address(saddr) based on the destination address(daddr)
* and asoc's bind address list.
*/
static void sctp_v6_get_saddr(struct sctp_sock *sk,
struct sctp_transport *t,
struct flowi *fl)
{
struct flowi6 *fl6 = &fl->u.ip6;
union sctp_addr *saddr = &t->saddr;
net: sctp: rework debugging framework to use pr_debug and friends We should get rid of all own SCTP debug printk macros and use the ones that the kernel offers anyway instead. This makes the code more readable and conform to the kernel code, and offers all the features of dynamic debbuging that pr_debug() et al has, such as only turning on/off portions of debug messages at runtime through debugfs. The runtime cost of having CONFIG_DYNAMIC_DEBUG enabled, but none of the debug statements printing, is negligible [1]. If kernel debugging is completly turned off, then these statements will also compile into "empty" functions. While we're at it, we also need to change the Kconfig option as it /now/ only refers to the ifdef'ed code portions in outqueue.c that enable further debugging/tracing of SCTP transaction fields. Also, since SCTP_ASSERT code was enabled with this Kconfig option and has now been removed, we transform those code parts into WARNs resp. where appropriate BUG_ONs so that those bugs can be more easily detected as probably not many people have SCTP debugging permanently turned on. To turn on all SCTP debugging, the following steps are needed: # mount -t debugfs none /sys/kernel/debug # echo -n 'module sctp +p' > /sys/kernel/debug/dynamic_debug/control This can be done more fine-grained on a per file, per line basis and others as described in [2]. [1] https://www.kernel.org/doc/ols/2009/ols2009-pages-39-46.pdf [2] Documentation/dynamic-debug-howto.txt Signed-off-by: Daniel Borkmann <dborkman@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2013-06-29 01:49:40 +08:00
pr_debug("%s: asoc:%p dst:%p\n", __func__, t->asoc, t->dst);
if (t->dst) {
saddr->v6.sin6_family = AF_INET6;
saddr->v6.sin6_addr = fl6->saddr;
}
}
/* Make a copy of all potential local addresses. */
static void sctp_v6_copy_addrlist(struct list_head *addrlist,
struct net_device *dev)
{
struct inet6_dev *in6_dev;
struct inet6_ifaddr *ifp;
struct sctp_sockaddr_entry *addr;
rcu_read_lock();
if ((in6_dev = __in6_dev_get(dev)) == NULL) {
rcu_read_unlock();
return;
}
read_lock_bh(&in6_dev->lock);
list_for_each_entry(ifp, &in6_dev->addr_list, if_list) {
/* Add the address to the local list. */
addr = kzalloc(sizeof(*addr), GFP_ATOMIC);
if (addr) {
addr->a.v6.sin6_family = AF_INET6;
addr->a.v6.sin6_addr = ifp->addr;
addr->a.v6.sin6_scope_id = dev->ifindex;
addr->valid = 1;
INIT_LIST_HEAD(&addr->list);
list_add_tail(&addr->list, addrlist);
}
}
read_unlock_bh(&in6_dev->lock);
rcu_read_unlock();
}
/* Copy over any ip options */
static void sctp_v6_copy_ip_options(struct sock *sk, struct sock *newsk)
{
struct ipv6_pinfo *newnp, *np = inet6_sk(sk);
struct ipv6_txoptions *opt;
newnp = inet6_sk(newsk);
rcu_read_lock();
opt = rcu_dereference(np->opt);
if (opt) {
opt = ipv6_dup_options(newsk, opt);
if (!opt)
pr_err("%s: Failed to copy ip options\n", __func__);
}
RCU_INIT_POINTER(newnp->opt, opt);
rcu_read_unlock();
}
/* Account for the IP options */
static int sctp_v6_ip_options_len(struct sock *sk)
{
struct ipv6_pinfo *np = inet6_sk(sk);
struct ipv6_txoptions *opt;
int len = 0;
rcu_read_lock();
opt = rcu_dereference(np->opt);
if (opt)
len = opt->opt_flen + opt->opt_nflen;
rcu_read_unlock();
return len;
}
/* Initialize a sockaddr_storage from in incoming skb. */
static void sctp_v6_from_skb(union sctp_addr *addr, struct sk_buff *skb,
int is_saddr)
{
/* Always called on head skb, so this is safe */
struct sctphdr *sh = sctp_hdr(skb);
struct sockaddr_in6 *sa = &addr->v6;
addr->v6.sin6_family = AF_INET6;
addr->v6.sin6_flowinfo = 0; /* FIXME */
addr->v6.sin6_scope_id = ((struct inet6_skb_parm *)skb->cb)->iif;
if (is_saddr) {
sa->sin6_port = sh->source;
sa->sin6_addr = ipv6_hdr(skb)->saddr;
} else {
sa->sin6_port = sh->dest;
sa->sin6_addr = ipv6_hdr(skb)->daddr;
}
}
/* Initialize an sctp_addr from a socket. */
static void sctp_v6_from_sk(union sctp_addr *addr, struct sock *sk)
{
addr->v6.sin6_family = AF_INET6;
addr->v6.sin6_port = 0;
addr->v6.sin6_addr = sk->sk_v6_rcv_saddr;
}
/* Initialize sk->sk_rcv_saddr from sctp_addr. */
static void sctp_v6_to_sk_saddr(union sctp_addr *addr, struct sock *sk)
{
sctp: Fixup v4mapped behaviour to comply with Sock API The SCTP socket extensions API document describes the v4mapping option as follows: 8.1.15. Set/Clear IPv4 Mapped Addresses (SCTP_I_WANT_MAPPED_V4_ADDR) This socket option is a Boolean flag which turns on or off the mapping of IPv4 addresses. If this option is turned on, then IPv4 addresses will be mapped to V6 representation. If this option is turned off, then no mapping will be done of V4 addresses and a user will receive both PF_INET6 and PF_INET type addresses on the socket. See [RFC3542] for more details on mapped V6 addresses. This description isn't really in line with what the code does though. Introduce addr_to_user (renamed addr_v4map), which should be called before any sockaddr is passed back to user space. The new function places the sockaddr into the correct format depending on the SCTP_I_WANT_MAPPED_V4_ADDR option. Audit all places that touched v4mapped and either sanely construct a v4 or v6 address then call addr_to_user, or drop the unnecessary v4mapped check entirely. Audit all places that call addr_to_user and verify they are on a sycall return path. Add a custom getname that formats the address properly. Several bugs are addressed: - SCTP_I_WANT_MAPPED_V4_ADDR=0 often returned garbage for addresses to user space - The addr_len returned from recvmsg was not correct when returning AF_INET on a v6 socket - flowlabel and scope_id were not zerod when promoting a v4 to v6 - Some syscalls like bind and connect behaved differently depending on v4mapped Tested bind, getpeername, getsockname, connect, and recvmsg for proper behaviour in v4mapped = 1 and 0 cases. Signed-off-by: Neil Horman <nhorman@tuxdriver.com> Tested-by: Jason Gunthorpe <jgunthorpe@obsidianresearch.com> Signed-off-by: Jason Gunthorpe <jgunthorpe@obsidianresearch.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2014-07-31 02:40:53 +08:00
if (addr->sa.sa_family == AF_INET) {
sk->sk_v6_rcv_saddr.s6_addr32[0] = 0;
sk->sk_v6_rcv_saddr.s6_addr32[1] = 0;
sk->sk_v6_rcv_saddr.s6_addr32[2] = htonl(0x0000ffff);
sk->sk_v6_rcv_saddr.s6_addr32[3] =
addr->v4.sin_addr.s_addr;
} else {
sk->sk_v6_rcv_saddr = addr->v6.sin6_addr;
}
}
/* Initialize sk->sk_daddr from sctp_addr. */
static void sctp_v6_to_sk_daddr(union sctp_addr *addr, struct sock *sk)
{
sctp: Fixup v4mapped behaviour to comply with Sock API The SCTP socket extensions API document describes the v4mapping option as follows: 8.1.15. Set/Clear IPv4 Mapped Addresses (SCTP_I_WANT_MAPPED_V4_ADDR) This socket option is a Boolean flag which turns on or off the mapping of IPv4 addresses. If this option is turned on, then IPv4 addresses will be mapped to V6 representation. If this option is turned off, then no mapping will be done of V4 addresses and a user will receive both PF_INET6 and PF_INET type addresses on the socket. See [RFC3542] for more details on mapped V6 addresses. This description isn't really in line with what the code does though. Introduce addr_to_user (renamed addr_v4map), which should be called before any sockaddr is passed back to user space. The new function places the sockaddr into the correct format depending on the SCTP_I_WANT_MAPPED_V4_ADDR option. Audit all places that touched v4mapped and either sanely construct a v4 or v6 address then call addr_to_user, or drop the unnecessary v4mapped check entirely. Audit all places that call addr_to_user and verify they are on a sycall return path. Add a custom getname that formats the address properly. Several bugs are addressed: - SCTP_I_WANT_MAPPED_V4_ADDR=0 often returned garbage for addresses to user space - The addr_len returned from recvmsg was not correct when returning AF_INET on a v6 socket - flowlabel and scope_id were not zerod when promoting a v4 to v6 - Some syscalls like bind and connect behaved differently depending on v4mapped Tested bind, getpeername, getsockname, connect, and recvmsg for proper behaviour in v4mapped = 1 and 0 cases. Signed-off-by: Neil Horman <nhorman@tuxdriver.com> Tested-by: Jason Gunthorpe <jgunthorpe@obsidianresearch.com> Signed-off-by: Jason Gunthorpe <jgunthorpe@obsidianresearch.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2014-07-31 02:40:53 +08:00
if (addr->sa.sa_family == AF_INET) {
sk->sk_v6_daddr.s6_addr32[0] = 0;
sk->sk_v6_daddr.s6_addr32[1] = 0;
sk->sk_v6_daddr.s6_addr32[2] = htonl(0x0000ffff);
sk->sk_v6_daddr.s6_addr32[3] = addr->v4.sin_addr.s_addr;
} else {
sk->sk_v6_daddr = addr->v6.sin6_addr;
}
}
/* Initialize a sctp_addr from an address parameter. */
static bool sctp_v6_from_addr_param(union sctp_addr *addr,
union sctp_addr_param *param,
__be16 port, int iif)
{
if (ntohs(param->v6.param_hdr.length) < sizeof(struct sctp_ipv6addr_param))
return false;
addr->v6.sin6_family = AF_INET6;
addr->v6.sin6_port = port;
addr->v6.sin6_flowinfo = 0; /* BUG */
addr->v6.sin6_addr = param->v6.addr;
addr->v6.sin6_scope_id = iif;
return true;
}
/* Initialize an address parameter from a sctp_addr and return the length
* of the address parameter.
*/
static int sctp_v6_to_addr_param(const union sctp_addr *addr,
union sctp_addr_param *param)
{
int length = sizeof(struct sctp_ipv6addr_param);
param->v6.param_hdr.type = SCTP_PARAM_IPV6_ADDRESS;
param->v6.param_hdr.length = htons(length);
param->v6.addr = addr->v6.sin6_addr;
return length;
}
/* Initialize a sctp_addr from struct in6_addr. */
static void sctp_v6_to_addr(union sctp_addr *addr, struct in6_addr *saddr,
__be16 port)
{
addr->sa.sa_family = AF_INET6;
addr->v6.sin6_port = port;
sctp: fully initialize the IPv6 address in sctp_v6_to_addr() KMSAN reported use of uninitialized sctp_addr->v4.sin_addr.s_addr and sctp_addr->v6.sin6_scope_id in sctp_v6_cmp_addr() (see below). Make sure all fields of an IPv6 address are initialized, which guarantees that the IPv4 fields are also initialized. ================================================================== BUG: KMSAN: use of uninitialized memory in sctp_v6_cmp_addr+0x8d4/0x9f0 net/sctp/ipv6.c:517 CPU: 2 PID: 31056 Comm: syz-executor1 Not tainted 4.11.0-rc5+ #2944 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS Bochs 01/01/2011 Call Trace: dump_stack+0x172/0x1c0 lib/dump_stack.c:42 is_logbuf_locked mm/kmsan/kmsan.c:59 [inline] kmsan_report+0x12a/0x180 mm/kmsan/kmsan.c:938 native_save_fl arch/x86/include/asm/irqflags.h:18 [inline] arch_local_save_flags arch/x86/include/asm/irqflags.h:72 [inline] arch_local_irq_save arch/x86/include/asm/irqflags.h:113 [inline] __msan_warning_32+0x61/0xb0 mm/kmsan/kmsan_instr.c:467 sctp_v6_cmp_addr+0x8d4/0x9f0 net/sctp/ipv6.c:517 sctp_v6_get_dst+0x8c7/0x1630 net/sctp/ipv6.c:290 sctp_transport_route+0x101/0x570 net/sctp/transport.c:292 sctp_assoc_add_peer+0x66d/0x16f0 net/sctp/associola.c:651 sctp_sendmsg+0x35a5/0x4f90 net/sctp/socket.c:1871 inet_sendmsg+0x498/0x670 net/ipv4/af_inet.c:762 sock_sendmsg_nosec net/socket.c:633 [inline] sock_sendmsg net/socket.c:643 [inline] SYSC_sendto+0x608/0x710 net/socket.c:1696 SyS_sendto+0x8a/0xb0 net/socket.c:1664 entry_SYSCALL_64_fastpath+0x13/0x94 RIP: 0033:0x44b479 RSP: 002b:00007f6213f21c08 EFLAGS: 00000286 ORIG_RAX: 000000000000002c RAX: ffffffffffffffda RBX: 0000000020000000 RCX: 000000000044b479 RDX: 0000000000000041 RSI: 0000000020edd000 RDI: 0000000000000006 RBP: 00000000007080a8 R08: 0000000020b85fe4 R09: 000000000000001c R10: 0000000000040005 R11: 0000000000000286 R12: 00000000ffffffff R13: 0000000000003760 R14: 00000000006e5820 R15: 0000000000ff8000 origin description: ----dst_saddr@sctp_v6_get_dst local variable created at: sk_fullsock include/net/sock.h:2321 [inline] inet6_sk include/linux/ipv6.h:309 [inline] sctp_v6_get_dst+0x91/0x1630 net/sctp/ipv6.c:241 sctp_transport_route+0x101/0x570 net/sctp/transport.c:292 ================================================================== BUG: KMSAN: use of uninitialized memory in sctp_v6_cmp_addr+0x8d4/0x9f0 net/sctp/ipv6.c:517 CPU: 2 PID: 31056 Comm: syz-executor1 Not tainted 4.11.0-rc5+ #2944 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS Bochs 01/01/2011 Call Trace: dump_stack+0x172/0x1c0 lib/dump_stack.c:42 is_logbuf_locked mm/kmsan/kmsan.c:59 [inline] kmsan_report+0x12a/0x180 mm/kmsan/kmsan.c:938 native_save_fl arch/x86/include/asm/irqflags.h:18 [inline] arch_local_save_flags arch/x86/include/asm/irqflags.h:72 [inline] arch_local_irq_save arch/x86/include/asm/irqflags.h:113 [inline] __msan_warning_32+0x61/0xb0 mm/kmsan/kmsan_instr.c:467 sctp_v6_cmp_addr+0x8d4/0x9f0 net/sctp/ipv6.c:517 sctp_v6_get_dst+0x8c7/0x1630 net/sctp/ipv6.c:290 sctp_transport_route+0x101/0x570 net/sctp/transport.c:292 sctp_assoc_add_peer+0x66d/0x16f0 net/sctp/associola.c:651 sctp_sendmsg+0x35a5/0x4f90 net/sctp/socket.c:1871 inet_sendmsg+0x498/0x670 net/ipv4/af_inet.c:762 sock_sendmsg_nosec net/socket.c:633 [inline] sock_sendmsg net/socket.c:643 [inline] SYSC_sendto+0x608/0x710 net/socket.c:1696 SyS_sendto+0x8a/0xb0 net/socket.c:1664 entry_SYSCALL_64_fastpath+0x13/0x94 RIP: 0033:0x44b479 RSP: 002b:00007f6213f21c08 EFLAGS: 00000286 ORIG_RAX: 000000000000002c RAX: ffffffffffffffda RBX: 0000000020000000 RCX: 000000000044b479 RDX: 0000000000000041 RSI: 0000000020edd000 RDI: 0000000000000006 RBP: 00000000007080a8 R08: 0000000020b85fe4 R09: 000000000000001c R10: 0000000000040005 R11: 0000000000000286 R12: 00000000ffffffff R13: 0000000000003760 R14: 00000000006e5820 R15: 0000000000ff8000 origin description: ----dst_saddr@sctp_v6_get_dst local variable created at: sk_fullsock include/net/sock.h:2321 [inline] inet6_sk include/linux/ipv6.h:309 [inline] sctp_v6_get_dst+0x91/0x1630 net/sctp/ipv6.c:241 sctp_transport_route+0x101/0x570 net/sctp/transport.c:292 ================================================================== Signed-off-by: Alexander Potapenko <glider@google.com> Reviewed-by: Xin Long <lucien.xin@gmail.com> Acked-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-08-17 02:16:40 +08:00
addr->v6.sin6_flowinfo = 0;
addr->v6.sin6_addr = *saddr;
sctp: fully initialize the IPv6 address in sctp_v6_to_addr() KMSAN reported use of uninitialized sctp_addr->v4.sin_addr.s_addr and sctp_addr->v6.sin6_scope_id in sctp_v6_cmp_addr() (see below). Make sure all fields of an IPv6 address are initialized, which guarantees that the IPv4 fields are also initialized. ================================================================== BUG: KMSAN: use of uninitialized memory in sctp_v6_cmp_addr+0x8d4/0x9f0 net/sctp/ipv6.c:517 CPU: 2 PID: 31056 Comm: syz-executor1 Not tainted 4.11.0-rc5+ #2944 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS Bochs 01/01/2011 Call Trace: dump_stack+0x172/0x1c0 lib/dump_stack.c:42 is_logbuf_locked mm/kmsan/kmsan.c:59 [inline] kmsan_report+0x12a/0x180 mm/kmsan/kmsan.c:938 native_save_fl arch/x86/include/asm/irqflags.h:18 [inline] arch_local_save_flags arch/x86/include/asm/irqflags.h:72 [inline] arch_local_irq_save arch/x86/include/asm/irqflags.h:113 [inline] __msan_warning_32+0x61/0xb0 mm/kmsan/kmsan_instr.c:467 sctp_v6_cmp_addr+0x8d4/0x9f0 net/sctp/ipv6.c:517 sctp_v6_get_dst+0x8c7/0x1630 net/sctp/ipv6.c:290 sctp_transport_route+0x101/0x570 net/sctp/transport.c:292 sctp_assoc_add_peer+0x66d/0x16f0 net/sctp/associola.c:651 sctp_sendmsg+0x35a5/0x4f90 net/sctp/socket.c:1871 inet_sendmsg+0x498/0x670 net/ipv4/af_inet.c:762 sock_sendmsg_nosec net/socket.c:633 [inline] sock_sendmsg net/socket.c:643 [inline] SYSC_sendto+0x608/0x710 net/socket.c:1696 SyS_sendto+0x8a/0xb0 net/socket.c:1664 entry_SYSCALL_64_fastpath+0x13/0x94 RIP: 0033:0x44b479 RSP: 002b:00007f6213f21c08 EFLAGS: 00000286 ORIG_RAX: 000000000000002c RAX: ffffffffffffffda RBX: 0000000020000000 RCX: 000000000044b479 RDX: 0000000000000041 RSI: 0000000020edd000 RDI: 0000000000000006 RBP: 00000000007080a8 R08: 0000000020b85fe4 R09: 000000000000001c R10: 0000000000040005 R11: 0000000000000286 R12: 00000000ffffffff R13: 0000000000003760 R14: 00000000006e5820 R15: 0000000000ff8000 origin description: ----dst_saddr@sctp_v6_get_dst local variable created at: sk_fullsock include/net/sock.h:2321 [inline] inet6_sk include/linux/ipv6.h:309 [inline] sctp_v6_get_dst+0x91/0x1630 net/sctp/ipv6.c:241 sctp_transport_route+0x101/0x570 net/sctp/transport.c:292 ================================================================== BUG: KMSAN: use of uninitialized memory in sctp_v6_cmp_addr+0x8d4/0x9f0 net/sctp/ipv6.c:517 CPU: 2 PID: 31056 Comm: syz-executor1 Not tainted 4.11.0-rc5+ #2944 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS Bochs 01/01/2011 Call Trace: dump_stack+0x172/0x1c0 lib/dump_stack.c:42 is_logbuf_locked mm/kmsan/kmsan.c:59 [inline] kmsan_report+0x12a/0x180 mm/kmsan/kmsan.c:938 native_save_fl arch/x86/include/asm/irqflags.h:18 [inline] arch_local_save_flags arch/x86/include/asm/irqflags.h:72 [inline] arch_local_irq_save arch/x86/include/asm/irqflags.h:113 [inline] __msan_warning_32+0x61/0xb0 mm/kmsan/kmsan_instr.c:467 sctp_v6_cmp_addr+0x8d4/0x9f0 net/sctp/ipv6.c:517 sctp_v6_get_dst+0x8c7/0x1630 net/sctp/ipv6.c:290 sctp_transport_route+0x101/0x570 net/sctp/transport.c:292 sctp_assoc_add_peer+0x66d/0x16f0 net/sctp/associola.c:651 sctp_sendmsg+0x35a5/0x4f90 net/sctp/socket.c:1871 inet_sendmsg+0x498/0x670 net/ipv4/af_inet.c:762 sock_sendmsg_nosec net/socket.c:633 [inline] sock_sendmsg net/socket.c:643 [inline] SYSC_sendto+0x608/0x710 net/socket.c:1696 SyS_sendto+0x8a/0xb0 net/socket.c:1664 entry_SYSCALL_64_fastpath+0x13/0x94 RIP: 0033:0x44b479 RSP: 002b:00007f6213f21c08 EFLAGS: 00000286 ORIG_RAX: 000000000000002c RAX: ffffffffffffffda RBX: 0000000020000000 RCX: 000000000044b479 RDX: 0000000000000041 RSI: 0000000020edd000 RDI: 0000000000000006 RBP: 00000000007080a8 R08: 0000000020b85fe4 R09: 000000000000001c R10: 0000000000040005 R11: 0000000000000286 R12: 00000000ffffffff R13: 0000000000003760 R14: 00000000006e5820 R15: 0000000000ff8000 origin description: ----dst_saddr@sctp_v6_get_dst local variable created at: sk_fullsock include/net/sock.h:2321 [inline] inet6_sk include/linux/ipv6.h:309 [inline] sctp_v6_get_dst+0x91/0x1630 net/sctp/ipv6.c:241 sctp_transport_route+0x101/0x570 net/sctp/transport.c:292 ================================================================== Signed-off-by: Alexander Potapenko <glider@google.com> Reviewed-by: Xin Long <lucien.xin@gmail.com> Acked-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-08-17 02:16:40 +08:00
addr->v6.sin6_scope_id = 0;
}
static int __sctp_v6_cmp_addr(const union sctp_addr *addr1,
const union sctp_addr *addr2)
{
if (addr1->sa.sa_family != addr2->sa.sa_family) {
if (addr1->sa.sa_family == AF_INET &&
addr2->sa.sa_family == AF_INET6 &&
ipv6_addr_v4mapped(&addr2->v6.sin6_addr) &&
addr2->v6.sin6_addr.s6_addr32[3] ==
addr1->v4.sin_addr.s_addr)
return 1;
if (addr2->sa.sa_family == AF_INET &&
addr1->sa.sa_family == AF_INET6 &&
ipv6_addr_v4mapped(&addr1->v6.sin6_addr) &&
addr1->v6.sin6_addr.s6_addr32[3] ==
addr2->v4.sin_addr.s_addr)
return 1;
return 0;
}
if (!ipv6_addr_equal(&addr1->v6.sin6_addr, &addr2->v6.sin6_addr))
return 0;
/* If this is a linklocal address, compare the scope_id. */
if ((ipv6_addr_type(&addr1->v6.sin6_addr) & IPV6_ADDR_LINKLOCAL) &&
addr1->v6.sin6_scope_id && addr2->v6.sin6_scope_id &&
addr1->v6.sin6_scope_id != addr2->v6.sin6_scope_id)
return 0;
return 1;
}
/* Compare addresses exactly.
* v4-mapped-v6 is also in consideration.
*/
static int sctp_v6_cmp_addr(const union sctp_addr *addr1,
const union sctp_addr *addr2)
{
return __sctp_v6_cmp_addr(addr1, addr2) &&
addr1->v6.sin6_port == addr2->v6.sin6_port;
}
/* Initialize addr struct to INADDR_ANY. */
static void sctp_v6_inaddr_any(union sctp_addr *addr, __be16 port)
{
memset(addr, 0x00, sizeof(union sctp_addr));
addr->v6.sin6_family = AF_INET6;
addr->v6.sin6_port = port;
}
/* Is this a wildcard address? */
static int sctp_v6_is_any(const union sctp_addr *addr)
{
return ipv6_addr_any(&addr->v6.sin6_addr);
}
/* Should this be available for binding? */
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);
if (IPV6_ADDR_ANY == type)
return 1;
if (type == IPV6_ADDR_MAPPED) {
if (sp && ipv6_only_sock(sctp_opt2sk(sp)))
return 0;
sctp_v6_map_v4(addr);
return sctp_get_af_specific(AF_INET)->available(addr, sp);
}
if (!(type & IPV6_ADDR_UNICAST))
return 0;
return ipv6_can_nonlocal_bind(net, &sp->inet) ||
ipv6_chk_addr(net, in6, NULL, 0);
}
/* This function checks if the address is a valid address to be used for
* SCTP.
*
* Output:
* Return 0 - If the address is a non-unicast or an illegal address.
* Return 1 - If the address is a unicast.
*/
static int sctp_v6_addr_valid(union sctp_addr *addr,
struct sctp_sock *sp,
const struct sk_buff *skb)
{
int ret = ipv6_addr_type(&addr->v6.sin6_addr);
/* Support v4-mapped-v6 address. */
if (ret == IPV6_ADDR_MAPPED) {
/* Note: This routine is used in input, so v4-mapped-v6
* are disallowed here when there is no sctp_sock.
*/
if (sp && ipv6_only_sock(sctp_opt2sk(sp)))
return 0;
sctp_v6_map_v4(addr);
return sctp_get_af_specific(AF_INET)->addr_valid(addr, sp, skb);
}
/* Is this a non-unicast address */
if (!(ret & IPV6_ADDR_UNICAST))
return 0;
return 1;
}
/* What is the scope of 'addr'? */
static enum sctp_scope sctp_v6_scope(union sctp_addr *addr)
{
enum sctp_scope retval;
int v6scope;
/* The IPv6 scope is really a set of bit fields.
* See IFA_* in <net/if_inet6.h>. Map to a generic SCTP scope.
*/
v6scope = ipv6_addr_scope(&addr->v6.sin6_addr);
switch (v6scope) {
case IFA_HOST:
retval = SCTP_SCOPE_LOOPBACK;
break;
case IFA_LINK:
retval = SCTP_SCOPE_LINK;
break;
case IFA_SITE:
retval = SCTP_SCOPE_PRIVATE;
break;
default:
retval = SCTP_SCOPE_GLOBAL;
break;
}
return retval;
}
/* Create and initialize a new sk for the socket to be returned by accept(). */
static struct sock *sctp_v6_create_accept_sk(struct sock *sk,
net: Work around lockdep limitation in sockets that use sockets Lockdep issues a circular dependency warning when AFS issues an operation through AF_RXRPC from a context in which the VFS/VM holds the mmap_sem. The theory lockdep comes up with is as follows: (1) If the pagefault handler decides it needs to read pages from AFS, it calls AFS with mmap_sem held and AFS begins an AF_RXRPC call, but creating a call requires the socket lock: mmap_sem must be taken before sk_lock-AF_RXRPC (2) afs_open_socket() opens an AF_RXRPC socket and binds it. rxrpc_bind() binds the underlying UDP socket whilst holding its socket lock. inet_bind() takes its own socket lock: sk_lock-AF_RXRPC must be taken before sk_lock-AF_INET (3) Reading from a TCP socket into a userspace buffer might cause a fault and thus cause the kernel to take the mmap_sem, but the TCP socket is locked whilst doing this: sk_lock-AF_INET must be taken before mmap_sem However, lockdep's theory is wrong in this instance because it deals only with lock classes and not individual locks. The AF_INET lock in (2) isn't really equivalent to the AF_INET lock in (3) as the former deals with a socket entirely internal to the kernel that never sees userspace. This is a limitation in the design of lockdep. Fix the general case by: (1) Double up all the locking keys used in sockets so that one set are used if the socket is created by userspace and the other set is used if the socket is created by the kernel. (2) Store the kern parameter passed to sk_alloc() in a variable in the sock struct (sk_kern_sock). This informs sock_lock_init(), sock_init_data() and sk_clone_lock() as to the lock keys to be used. Note that the child created by sk_clone_lock() inherits the parent's kern setting. (3) Add a 'kern' parameter to ->accept() that is analogous to the one passed in to ->create() that distinguishes whether kernel_accept() or sys_accept4() was the caller and can be passed to sk_alloc(). Note that a lot of accept functions merely dequeue an already allocated socket. I haven't touched these as the new socket already exists before we get the parameter. Note also that there are a couple of places where I've made the accepted socket unconditionally kernel-based: irda_accept() rds_rcp_accept_one() tcp_accept_from_sock() because they follow a sock_create_kern() and accept off of that. Whilst creating this, I noticed that lustre and ocfs don't create sockets through sock_create_kern() and thus they aren't marked as for-kernel, though they appear to be internal. I wonder if these should do that so that they use the new set of lock keys. Signed-off-by: David Howells <dhowells@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-03-09 16:09:05 +08:00
struct sctp_association *asoc,
bool kern)
{
struct sock *newsk;
struct ipv6_pinfo *newnp, *np = inet6_sk(sk);
struct sctp6_sock *newsctp6sk;
net: Work around lockdep limitation in sockets that use sockets Lockdep issues a circular dependency warning when AFS issues an operation through AF_RXRPC from a context in which the VFS/VM holds the mmap_sem. The theory lockdep comes up with is as follows: (1) If the pagefault handler decides it needs to read pages from AFS, it calls AFS with mmap_sem held and AFS begins an AF_RXRPC call, but creating a call requires the socket lock: mmap_sem must be taken before sk_lock-AF_RXRPC (2) afs_open_socket() opens an AF_RXRPC socket and binds it. rxrpc_bind() binds the underlying UDP socket whilst holding its socket lock. inet_bind() takes its own socket lock: sk_lock-AF_RXRPC must be taken before sk_lock-AF_INET (3) Reading from a TCP socket into a userspace buffer might cause a fault and thus cause the kernel to take the mmap_sem, but the TCP socket is locked whilst doing this: sk_lock-AF_INET must be taken before mmap_sem However, lockdep's theory is wrong in this instance because it deals only with lock classes and not individual locks. The AF_INET lock in (2) isn't really equivalent to the AF_INET lock in (3) as the former deals with a socket entirely internal to the kernel that never sees userspace. This is a limitation in the design of lockdep. Fix the general case by: (1) Double up all the locking keys used in sockets so that one set are used if the socket is created by userspace and the other set is used if the socket is created by the kernel. (2) Store the kern parameter passed to sk_alloc() in a variable in the sock struct (sk_kern_sock). This informs sock_lock_init(), sock_init_data() and sk_clone_lock() as to the lock keys to be used. Note that the child created by sk_clone_lock() inherits the parent's kern setting. (3) Add a 'kern' parameter to ->accept() that is analogous to the one passed in to ->create() that distinguishes whether kernel_accept() or sys_accept4() was the caller and can be passed to sk_alloc(). Note that a lot of accept functions merely dequeue an already allocated socket. I haven't touched these as the new socket already exists before we get the parameter. Note also that there are a couple of places where I've made the accepted socket unconditionally kernel-based: irda_accept() rds_rcp_accept_one() tcp_accept_from_sock() because they follow a sock_create_kern() and accept off of that. Whilst creating this, I noticed that lustre and ocfs don't create sockets through sock_create_kern() and thus they aren't marked as for-kernel, though they appear to be internal. I wonder if these should do that so that they use the new set of lock keys. Signed-off-by: David Howells <dhowells@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-03-09 16:09:05 +08:00
newsk = sk_alloc(sock_net(sk), PF_INET6, GFP_KERNEL, sk->sk_prot, kern);
if (!newsk)
goto out;
sock_init_data(NULL, newsk);
sctp_copy_sock(newsk, sk, asoc);
sock_reset_flag(sk, SOCK_ZAPPED);
newsctp6sk = (struct sctp6_sock *)newsk;
inet_sk(newsk)->pinet6 = &newsctp6sk->inet6;
sctp_sk(newsk)->v4mapped = sctp_sk(sk)->v4mapped;
newnp = inet6_sk(newsk);
memcpy(newnp, np, sizeof(struct ipv6_pinfo));
newnp->ipv6_mc_list = NULL;
newnp->ipv6_ac_list = NULL;
newnp->ipv6_fl_list = NULL;
sctp_v6_copy_ip_options(sk, newsk);
/* Initialize sk's sport, dport, rcv_saddr and daddr for getsockname()
* and getpeername().
*/
sctp_v6_to_sk_daddr(&asoc->peer.primary_addr, newsk);
newsk->sk_v6_rcv_saddr = sk->sk_v6_rcv_saddr;
sk_refcnt_debug_inc(newsk);
if (newsk->sk_prot->init(newsk)) {
sk_common_release(newsk);
newsk = NULL;
}
out:
return newsk;
}
sctp: Fixup v4mapped behaviour to comply with Sock API The SCTP socket extensions API document describes the v4mapping option as follows: 8.1.15. Set/Clear IPv4 Mapped Addresses (SCTP_I_WANT_MAPPED_V4_ADDR) This socket option is a Boolean flag which turns on or off the mapping of IPv4 addresses. If this option is turned on, then IPv4 addresses will be mapped to V6 representation. If this option is turned off, then no mapping will be done of V4 addresses and a user will receive both PF_INET6 and PF_INET type addresses on the socket. See [RFC3542] for more details on mapped V6 addresses. This description isn't really in line with what the code does though. Introduce addr_to_user (renamed addr_v4map), which should be called before any sockaddr is passed back to user space. The new function places the sockaddr into the correct format depending on the SCTP_I_WANT_MAPPED_V4_ADDR option. Audit all places that touched v4mapped and either sanely construct a v4 or v6 address then call addr_to_user, or drop the unnecessary v4mapped check entirely. Audit all places that call addr_to_user and verify they are on a sycall return path. Add a custom getname that formats the address properly. Several bugs are addressed: - SCTP_I_WANT_MAPPED_V4_ADDR=0 often returned garbage for addresses to user space - The addr_len returned from recvmsg was not correct when returning AF_INET on a v6 socket - flowlabel and scope_id were not zerod when promoting a v4 to v6 - Some syscalls like bind and connect behaved differently depending on v4mapped Tested bind, getpeername, getsockname, connect, and recvmsg for proper behaviour in v4mapped = 1 and 0 cases. Signed-off-by: Neil Horman <nhorman@tuxdriver.com> Tested-by: Jason Gunthorpe <jgunthorpe@obsidianresearch.com> Signed-off-by: Jason Gunthorpe <jgunthorpe@obsidianresearch.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2014-07-31 02:40:53 +08:00
/* Format a sockaddr for return to user space. This makes sure the return is
* AF_INET or AF_INET6 depending on the SCTP_I_WANT_MAPPED_V4_ADDR option.
*/
static int sctp_v6_addr_to_user(struct sctp_sock *sp, union sctp_addr *addr)
{
sctp: Fixup v4mapped behaviour to comply with Sock API The SCTP socket extensions API document describes the v4mapping option as follows: 8.1.15. Set/Clear IPv4 Mapped Addresses (SCTP_I_WANT_MAPPED_V4_ADDR) This socket option is a Boolean flag which turns on or off the mapping of IPv4 addresses. If this option is turned on, then IPv4 addresses will be mapped to V6 representation. If this option is turned off, then no mapping will be done of V4 addresses and a user will receive both PF_INET6 and PF_INET type addresses on the socket. See [RFC3542] for more details on mapped V6 addresses. This description isn't really in line with what the code does though. Introduce addr_to_user (renamed addr_v4map), which should be called before any sockaddr is passed back to user space. The new function places the sockaddr into the correct format depending on the SCTP_I_WANT_MAPPED_V4_ADDR option. Audit all places that touched v4mapped and either sanely construct a v4 or v6 address then call addr_to_user, or drop the unnecessary v4mapped check entirely. Audit all places that call addr_to_user and verify they are on a sycall return path. Add a custom getname that formats the address properly. Several bugs are addressed: - SCTP_I_WANT_MAPPED_V4_ADDR=0 often returned garbage for addresses to user space - The addr_len returned from recvmsg was not correct when returning AF_INET on a v6 socket - flowlabel and scope_id were not zerod when promoting a v4 to v6 - Some syscalls like bind and connect behaved differently depending on v4mapped Tested bind, getpeername, getsockname, connect, and recvmsg for proper behaviour in v4mapped = 1 and 0 cases. Signed-off-by: Neil Horman <nhorman@tuxdriver.com> Tested-by: Jason Gunthorpe <jgunthorpe@obsidianresearch.com> Signed-off-by: Jason Gunthorpe <jgunthorpe@obsidianresearch.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2014-07-31 02:40:53 +08:00
if (sp->v4mapped) {
if (addr->sa.sa_family == AF_INET)
sctp_v4_map_v6(addr);
} else {
if (addr->sa.sa_family == AF_INET6 &&
ipv6_addr_v4mapped(&addr->v6.sin6_addr))
sctp_v6_map_v4(addr);
}
sctp: do not leak kernel memory to user space syzbot produced a nice report [1] Issue here is that a recvmmsg() managed to leak 8 bytes of kernel memory to user space, because sin_zero (padding field) was not properly cleared. [1] BUG: KMSAN: uninit-value in copy_to_user include/linux/uaccess.h:184 [inline] BUG: KMSAN: uninit-value in move_addr_to_user+0x32e/0x530 net/socket.c:227 CPU: 1 PID: 3586 Comm: syzkaller481044 Not tainted 4.16.0+ #82 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 Call Trace: __dump_stack lib/dump_stack.c:17 [inline] dump_stack+0x185/0x1d0 lib/dump_stack.c:53 kmsan_report+0x142/0x240 mm/kmsan/kmsan.c:1067 kmsan_internal_check_memory+0x164/0x1d0 mm/kmsan/kmsan.c:1176 kmsan_copy_to_user+0x69/0x160 mm/kmsan/kmsan.c:1199 copy_to_user include/linux/uaccess.h:184 [inline] move_addr_to_user+0x32e/0x530 net/socket.c:227 ___sys_recvmsg+0x4e2/0x810 net/socket.c:2211 __sys_recvmmsg+0x54e/0xdb0 net/socket.c:2313 SYSC_recvmmsg+0x29b/0x3e0 net/socket.c:2394 SyS_recvmmsg+0x76/0xa0 net/socket.c:2378 do_syscall_64+0x309/0x430 arch/x86/entry/common.c:287 entry_SYSCALL_64_after_hwframe+0x3d/0xa2 RIP: 0033:0x4401c9 RSP: 002b:00007ffc56f73098 EFLAGS: 00000217 ORIG_RAX: 000000000000012b RAX: ffffffffffffffda RBX: 00000000004002c8 RCX: 00000000004401c9 RDX: 0000000000000001 RSI: 0000000020003ac0 RDI: 0000000000000003 RBP: 00000000006ca018 R08: 0000000020003bc0 R09: 0000000000000010 R10: 0000000000000000 R11: 0000000000000217 R12: 0000000000401af0 R13: 0000000000401b80 R14: 0000000000000000 R15: 0000000000000000 Local variable description: ----addr@___sys_recvmsg Variable was created at: ___sys_recvmsg+0xd5/0x810 net/socket.c:2172 __sys_recvmmsg+0x54e/0xdb0 net/socket.c:2313 Bytes 8-15 of 16 are uninitialized ================================================================== Kernel panic - not syncing: panic_on_warn set ... CPU: 1 PID: 3586 Comm: syzkaller481044 Tainted: G B 4.16.0+ #82 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 Call Trace: __dump_stack lib/dump_stack.c:17 [inline] dump_stack+0x185/0x1d0 lib/dump_stack.c:53 panic+0x39d/0x940 kernel/panic.c:183 kmsan_report+0x238/0x240 mm/kmsan/kmsan.c:1083 kmsan_internal_check_memory+0x164/0x1d0 mm/kmsan/kmsan.c:1176 kmsan_copy_to_user+0x69/0x160 mm/kmsan/kmsan.c:1199 copy_to_user include/linux/uaccess.h:184 [inline] move_addr_to_user+0x32e/0x530 net/socket.c:227 ___sys_recvmsg+0x4e2/0x810 net/socket.c:2211 __sys_recvmmsg+0x54e/0xdb0 net/socket.c:2313 SYSC_recvmmsg+0x29b/0x3e0 net/socket.c:2394 SyS_recvmmsg+0x76/0xa0 net/socket.c:2378 do_syscall_64+0x309/0x430 arch/x86/entry/common.c:287 entry_SYSCALL_64_after_hwframe+0x3d/0xa2 Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Signed-off-by: Eric Dumazet <edumazet@google.com> Cc: Vlad Yasevich <vyasevich@gmail.com> Cc: Neil Horman <nhorman@tuxdriver.com> Reported-by: syzbot <syzkaller@googlegroups.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-04-08 08:15:22 +08:00
if (addr->sa.sa_family == AF_INET) {
memset(addr->v4.sin_zero, 0, sizeof(addr->v4.sin_zero));
sctp: Fixup v4mapped behaviour to comply with Sock API The SCTP socket extensions API document describes the v4mapping option as follows: 8.1.15. Set/Clear IPv4 Mapped Addresses (SCTP_I_WANT_MAPPED_V4_ADDR) This socket option is a Boolean flag which turns on or off the mapping of IPv4 addresses. If this option is turned on, then IPv4 addresses will be mapped to V6 representation. If this option is turned off, then no mapping will be done of V4 addresses and a user will receive both PF_INET6 and PF_INET type addresses on the socket. See [RFC3542] for more details on mapped V6 addresses. This description isn't really in line with what the code does though. Introduce addr_to_user (renamed addr_v4map), which should be called before any sockaddr is passed back to user space. The new function places the sockaddr into the correct format depending on the SCTP_I_WANT_MAPPED_V4_ADDR option. Audit all places that touched v4mapped and either sanely construct a v4 or v6 address then call addr_to_user, or drop the unnecessary v4mapped check entirely. Audit all places that call addr_to_user and verify they are on a sycall return path. Add a custom getname that formats the address properly. Several bugs are addressed: - SCTP_I_WANT_MAPPED_V4_ADDR=0 often returned garbage for addresses to user space - The addr_len returned from recvmsg was not correct when returning AF_INET on a v6 socket - flowlabel and scope_id were not zerod when promoting a v4 to v6 - Some syscalls like bind and connect behaved differently depending on v4mapped Tested bind, getpeername, getsockname, connect, and recvmsg for proper behaviour in v4mapped = 1 and 0 cases. Signed-off-by: Neil Horman <nhorman@tuxdriver.com> Tested-by: Jason Gunthorpe <jgunthorpe@obsidianresearch.com> Signed-off-by: Jason Gunthorpe <jgunthorpe@obsidianresearch.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2014-07-31 02:40:53 +08:00
return sizeof(struct sockaddr_in);
sctp: do not leak kernel memory to user space syzbot produced a nice report [1] Issue here is that a recvmmsg() managed to leak 8 bytes of kernel memory to user space, because sin_zero (padding field) was not properly cleared. [1] BUG: KMSAN: uninit-value in copy_to_user include/linux/uaccess.h:184 [inline] BUG: KMSAN: uninit-value in move_addr_to_user+0x32e/0x530 net/socket.c:227 CPU: 1 PID: 3586 Comm: syzkaller481044 Not tainted 4.16.0+ #82 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 Call Trace: __dump_stack lib/dump_stack.c:17 [inline] dump_stack+0x185/0x1d0 lib/dump_stack.c:53 kmsan_report+0x142/0x240 mm/kmsan/kmsan.c:1067 kmsan_internal_check_memory+0x164/0x1d0 mm/kmsan/kmsan.c:1176 kmsan_copy_to_user+0x69/0x160 mm/kmsan/kmsan.c:1199 copy_to_user include/linux/uaccess.h:184 [inline] move_addr_to_user+0x32e/0x530 net/socket.c:227 ___sys_recvmsg+0x4e2/0x810 net/socket.c:2211 __sys_recvmmsg+0x54e/0xdb0 net/socket.c:2313 SYSC_recvmmsg+0x29b/0x3e0 net/socket.c:2394 SyS_recvmmsg+0x76/0xa0 net/socket.c:2378 do_syscall_64+0x309/0x430 arch/x86/entry/common.c:287 entry_SYSCALL_64_after_hwframe+0x3d/0xa2 RIP: 0033:0x4401c9 RSP: 002b:00007ffc56f73098 EFLAGS: 00000217 ORIG_RAX: 000000000000012b RAX: ffffffffffffffda RBX: 00000000004002c8 RCX: 00000000004401c9 RDX: 0000000000000001 RSI: 0000000020003ac0 RDI: 0000000000000003 RBP: 00000000006ca018 R08: 0000000020003bc0 R09: 0000000000000010 R10: 0000000000000000 R11: 0000000000000217 R12: 0000000000401af0 R13: 0000000000401b80 R14: 0000000000000000 R15: 0000000000000000 Local variable description: ----addr@___sys_recvmsg Variable was created at: ___sys_recvmsg+0xd5/0x810 net/socket.c:2172 __sys_recvmmsg+0x54e/0xdb0 net/socket.c:2313 Bytes 8-15 of 16 are uninitialized ================================================================== Kernel panic - not syncing: panic_on_warn set ... CPU: 1 PID: 3586 Comm: syzkaller481044 Tainted: G B 4.16.0+ #82 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 Call Trace: __dump_stack lib/dump_stack.c:17 [inline] dump_stack+0x185/0x1d0 lib/dump_stack.c:53 panic+0x39d/0x940 kernel/panic.c:183 kmsan_report+0x238/0x240 mm/kmsan/kmsan.c:1083 kmsan_internal_check_memory+0x164/0x1d0 mm/kmsan/kmsan.c:1176 kmsan_copy_to_user+0x69/0x160 mm/kmsan/kmsan.c:1199 copy_to_user include/linux/uaccess.h:184 [inline] move_addr_to_user+0x32e/0x530 net/socket.c:227 ___sys_recvmsg+0x4e2/0x810 net/socket.c:2211 __sys_recvmmsg+0x54e/0xdb0 net/socket.c:2313 SYSC_recvmmsg+0x29b/0x3e0 net/socket.c:2394 SyS_recvmmsg+0x76/0xa0 net/socket.c:2378 do_syscall_64+0x309/0x430 arch/x86/entry/common.c:287 entry_SYSCALL_64_after_hwframe+0x3d/0xa2 Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Signed-off-by: Eric Dumazet <edumazet@google.com> Cc: Vlad Yasevich <vyasevich@gmail.com> Cc: Neil Horman <nhorman@tuxdriver.com> Reported-by: syzbot <syzkaller@googlegroups.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-04-08 08:15:22 +08:00
}
sctp: Fixup v4mapped behaviour to comply with Sock API The SCTP socket extensions API document describes the v4mapping option as follows: 8.1.15. Set/Clear IPv4 Mapped Addresses (SCTP_I_WANT_MAPPED_V4_ADDR) This socket option is a Boolean flag which turns on or off the mapping of IPv4 addresses. If this option is turned on, then IPv4 addresses will be mapped to V6 representation. If this option is turned off, then no mapping will be done of V4 addresses and a user will receive both PF_INET6 and PF_INET type addresses on the socket. See [RFC3542] for more details on mapped V6 addresses. This description isn't really in line with what the code does though. Introduce addr_to_user (renamed addr_v4map), which should be called before any sockaddr is passed back to user space. The new function places the sockaddr into the correct format depending on the SCTP_I_WANT_MAPPED_V4_ADDR option. Audit all places that touched v4mapped and either sanely construct a v4 or v6 address then call addr_to_user, or drop the unnecessary v4mapped check entirely. Audit all places that call addr_to_user and verify they are on a sycall return path. Add a custom getname that formats the address properly. Several bugs are addressed: - SCTP_I_WANT_MAPPED_V4_ADDR=0 often returned garbage for addresses to user space - The addr_len returned from recvmsg was not correct when returning AF_INET on a v6 socket - flowlabel and scope_id were not zerod when promoting a v4 to v6 - Some syscalls like bind and connect behaved differently depending on v4mapped Tested bind, getpeername, getsockname, connect, and recvmsg for proper behaviour in v4mapped = 1 and 0 cases. Signed-off-by: Neil Horman <nhorman@tuxdriver.com> Tested-by: Jason Gunthorpe <jgunthorpe@obsidianresearch.com> Signed-off-by: Jason Gunthorpe <jgunthorpe@obsidianresearch.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2014-07-31 02:40:53 +08:00
return sizeof(struct sockaddr_in6);
}
/* Where did this skb come from? */
static int sctp_v6_skb_iif(const struct sk_buff *skb)
{
sctp: allow GSO frags to access the chunk too SCTP will try to access original IP headers on sctp_recvmsg in order to copy the addresses used. There are also other places that do similar access to IP or even SCTP headers. But after 90017accff61 ("sctp: Add GSO support") they aren't always there because they are only present in the header skb. SCTP handles the queueing of incoming data by cloning the incoming skb and limiting to only the relevant payload. This clone has its cb updated to something different and it's then queued on socket rx queue. Thus we need to fix this in two moments. For rx path, not related to socket queue yet, this patch uses a partially copied sctp_input_cb to such GSO frags. This restores the ability to access the headers for this part of the code. Regarding the socket rx queue, it removes iif member from sctp_event and also add a chunk pointer on it. With these changes we're always able to reach the headers again. The biggest change here is that now the sctp_chunk struct and the original skb are only freed after the application consumed the buffer. Note however that the original payload was already like this due to the skb cloning. For iif, SCTP's IPv4 code doesn't use it, so no change is necessary. IPv6 now can fetch it directly from original's IPv6 CB as the original skb is still accessible. In the future we probably can simplify sctp_v*_skb_iif() stuff, as sctp_v4_skb_iif() was called but it's return value not used, and now it's not even called, but such cleanup is out of scope for this change. Fixes: 90017accff61 ("sctp: Add GSO support") Signed-off-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-07-14 02:08:57 +08:00
return IP6CB(skb)->iif;
}
/* Was this packet marked by Explicit Congestion Notification? */
static int sctp_v6_is_ce(const struct sk_buff *skb)
{
return *((__u32 *)(ipv6_hdr(skb))) & (__force __u32)htonl(1 << 20);
}
/* Dump the v6 addr to the seq file. */
static void sctp_v6_seq_dump_addr(struct seq_file *seq, union sctp_addr *addr)
{
seq_printf(seq, "%pI6 ", &addr->v6.sin6_addr);
}
static void sctp_v6_ecn_capable(struct sock *sk)
{
inet6_sk(sk)->tclass |= INET_ECN_ECT_0;
}
/* Initialize a PF_INET msgname from a ulpevent. */
static void sctp_inet6_event_msgname(struct sctp_ulpevent *event,
char *msgname, int *addrlen)
{
sctp: Fixup v4mapped behaviour to comply with Sock API The SCTP socket extensions API document describes the v4mapping option as follows: 8.1.15. Set/Clear IPv4 Mapped Addresses (SCTP_I_WANT_MAPPED_V4_ADDR) This socket option is a Boolean flag which turns on or off the mapping of IPv4 addresses. If this option is turned on, then IPv4 addresses will be mapped to V6 representation. If this option is turned off, then no mapping will be done of V4 addresses and a user will receive both PF_INET6 and PF_INET type addresses on the socket. See [RFC3542] for more details on mapped V6 addresses. This description isn't really in line with what the code does though. Introduce addr_to_user (renamed addr_v4map), which should be called before any sockaddr is passed back to user space. The new function places the sockaddr into the correct format depending on the SCTP_I_WANT_MAPPED_V4_ADDR option. Audit all places that touched v4mapped and either sanely construct a v4 or v6 address then call addr_to_user, or drop the unnecessary v4mapped check entirely. Audit all places that call addr_to_user and verify they are on a sycall return path. Add a custom getname that formats the address properly. Several bugs are addressed: - SCTP_I_WANT_MAPPED_V4_ADDR=0 often returned garbage for addresses to user space - The addr_len returned from recvmsg was not correct when returning AF_INET on a v6 socket - flowlabel and scope_id were not zerod when promoting a v4 to v6 - Some syscalls like bind and connect behaved differently depending on v4mapped Tested bind, getpeername, getsockname, connect, and recvmsg for proper behaviour in v4mapped = 1 and 0 cases. Signed-off-by: Neil Horman <nhorman@tuxdriver.com> Tested-by: Jason Gunthorpe <jgunthorpe@obsidianresearch.com> Signed-off-by: Jason Gunthorpe <jgunthorpe@obsidianresearch.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2014-07-31 02:40:53 +08:00
union sctp_addr *addr;
struct sctp_association *asoc;
union sctp_addr *paddr;
sctp: Fixup v4mapped behaviour to comply with Sock API The SCTP socket extensions API document describes the v4mapping option as follows: 8.1.15. Set/Clear IPv4 Mapped Addresses (SCTP_I_WANT_MAPPED_V4_ADDR) This socket option is a Boolean flag which turns on or off the mapping of IPv4 addresses. If this option is turned on, then IPv4 addresses will be mapped to V6 representation. If this option is turned off, then no mapping will be done of V4 addresses and a user will receive both PF_INET6 and PF_INET type addresses on the socket. See [RFC3542] for more details on mapped V6 addresses. This description isn't really in line with what the code does though. Introduce addr_to_user (renamed addr_v4map), which should be called before any sockaddr is passed back to user space. The new function places the sockaddr into the correct format depending on the SCTP_I_WANT_MAPPED_V4_ADDR option. Audit all places that touched v4mapped and either sanely construct a v4 or v6 address then call addr_to_user, or drop the unnecessary v4mapped check entirely. Audit all places that call addr_to_user and verify they are on a sycall return path. Add a custom getname that formats the address properly. Several bugs are addressed: - SCTP_I_WANT_MAPPED_V4_ADDR=0 often returned garbage for addresses to user space - The addr_len returned from recvmsg was not correct when returning AF_INET on a v6 socket - flowlabel and scope_id were not zerod when promoting a v4 to v6 - Some syscalls like bind and connect behaved differently depending on v4mapped Tested bind, getpeername, getsockname, connect, and recvmsg for proper behaviour in v4mapped = 1 and 0 cases. Signed-off-by: Neil Horman <nhorman@tuxdriver.com> Tested-by: Jason Gunthorpe <jgunthorpe@obsidianresearch.com> Signed-off-by: Jason Gunthorpe <jgunthorpe@obsidianresearch.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2014-07-31 02:40:53 +08:00
if (!msgname)
return;
sctp: Fixup v4mapped behaviour to comply with Sock API The SCTP socket extensions API document describes the v4mapping option as follows: 8.1.15. Set/Clear IPv4 Mapped Addresses (SCTP_I_WANT_MAPPED_V4_ADDR) This socket option is a Boolean flag which turns on or off the mapping of IPv4 addresses. If this option is turned on, then IPv4 addresses will be mapped to V6 representation. If this option is turned off, then no mapping will be done of V4 addresses and a user will receive both PF_INET6 and PF_INET type addresses on the socket. See [RFC3542] for more details on mapped V6 addresses. This description isn't really in line with what the code does though. Introduce addr_to_user (renamed addr_v4map), which should be called before any sockaddr is passed back to user space. The new function places the sockaddr into the correct format depending on the SCTP_I_WANT_MAPPED_V4_ADDR option. Audit all places that touched v4mapped and either sanely construct a v4 or v6 address then call addr_to_user, or drop the unnecessary v4mapped check entirely. Audit all places that call addr_to_user and verify they are on a sycall return path. Add a custom getname that formats the address properly. Several bugs are addressed: - SCTP_I_WANT_MAPPED_V4_ADDR=0 often returned garbage for addresses to user space - The addr_len returned from recvmsg was not correct when returning AF_INET on a v6 socket - flowlabel and scope_id were not zerod when promoting a v4 to v6 - Some syscalls like bind and connect behaved differently depending on v4mapped Tested bind, getpeername, getsockname, connect, and recvmsg for proper behaviour in v4mapped = 1 and 0 cases. Signed-off-by: Neil Horman <nhorman@tuxdriver.com> Tested-by: Jason Gunthorpe <jgunthorpe@obsidianresearch.com> Signed-off-by: Jason Gunthorpe <jgunthorpe@obsidianresearch.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2014-07-31 02:40:53 +08:00
addr = (union sctp_addr *)msgname;
asoc = event->asoc;
paddr = &asoc->peer.primary_addr;
sctp: Fixup v4mapped behaviour to comply with Sock API The SCTP socket extensions API document describes the v4mapping option as follows: 8.1.15. Set/Clear IPv4 Mapped Addresses (SCTP_I_WANT_MAPPED_V4_ADDR) This socket option is a Boolean flag which turns on or off the mapping of IPv4 addresses. If this option is turned on, then IPv4 addresses will be mapped to V6 representation. If this option is turned off, then no mapping will be done of V4 addresses and a user will receive both PF_INET6 and PF_INET type addresses on the socket. See [RFC3542] for more details on mapped V6 addresses. This description isn't really in line with what the code does though. Introduce addr_to_user (renamed addr_v4map), which should be called before any sockaddr is passed back to user space. The new function places the sockaddr into the correct format depending on the SCTP_I_WANT_MAPPED_V4_ADDR option. Audit all places that touched v4mapped and either sanely construct a v4 or v6 address then call addr_to_user, or drop the unnecessary v4mapped check entirely. Audit all places that call addr_to_user and verify they are on a sycall return path. Add a custom getname that formats the address properly. Several bugs are addressed: - SCTP_I_WANT_MAPPED_V4_ADDR=0 often returned garbage for addresses to user space - The addr_len returned from recvmsg was not correct when returning AF_INET on a v6 socket - flowlabel and scope_id were not zerod when promoting a v4 to v6 - Some syscalls like bind and connect behaved differently depending on v4mapped Tested bind, getpeername, getsockname, connect, and recvmsg for proper behaviour in v4mapped = 1 and 0 cases. Signed-off-by: Neil Horman <nhorman@tuxdriver.com> Tested-by: Jason Gunthorpe <jgunthorpe@obsidianresearch.com> Signed-off-by: Jason Gunthorpe <jgunthorpe@obsidianresearch.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2014-07-31 02:40:53 +08:00
if (paddr->sa.sa_family == AF_INET) {
addr->v4.sin_family = AF_INET;
addr->v4.sin_port = htons(asoc->peer.port);
addr->v4.sin_addr = paddr->v4.sin_addr;
} else {
addr->v6.sin6_family = AF_INET6;
addr->v6.sin6_flowinfo = 0;
if (ipv6_addr_type(&paddr->v6.sin6_addr) & IPV6_ADDR_LINKLOCAL)
addr->v6.sin6_scope_id = paddr->v6.sin6_scope_id;
else
addr->v6.sin6_scope_id = 0;
addr->v6.sin6_port = htons(asoc->peer.port);
addr->v6.sin6_addr = paddr->v6.sin6_addr;
}
sctp: Fixup v4mapped behaviour to comply with Sock API The SCTP socket extensions API document describes the v4mapping option as follows: 8.1.15. Set/Clear IPv4 Mapped Addresses (SCTP_I_WANT_MAPPED_V4_ADDR) This socket option is a Boolean flag which turns on or off the mapping of IPv4 addresses. If this option is turned on, then IPv4 addresses will be mapped to V6 representation. If this option is turned off, then no mapping will be done of V4 addresses and a user will receive both PF_INET6 and PF_INET type addresses on the socket. See [RFC3542] for more details on mapped V6 addresses. This description isn't really in line with what the code does though. Introduce addr_to_user (renamed addr_v4map), which should be called before any sockaddr is passed back to user space. The new function places the sockaddr into the correct format depending on the SCTP_I_WANT_MAPPED_V4_ADDR option. Audit all places that touched v4mapped and either sanely construct a v4 or v6 address then call addr_to_user, or drop the unnecessary v4mapped check entirely. Audit all places that call addr_to_user and verify they are on a sycall return path. Add a custom getname that formats the address properly. Several bugs are addressed: - SCTP_I_WANT_MAPPED_V4_ADDR=0 often returned garbage for addresses to user space - The addr_len returned from recvmsg was not correct when returning AF_INET on a v6 socket - flowlabel and scope_id were not zerod when promoting a v4 to v6 - Some syscalls like bind and connect behaved differently depending on v4mapped Tested bind, getpeername, getsockname, connect, and recvmsg for proper behaviour in v4mapped = 1 and 0 cases. Signed-off-by: Neil Horman <nhorman@tuxdriver.com> Tested-by: Jason Gunthorpe <jgunthorpe@obsidianresearch.com> Signed-off-by: Jason Gunthorpe <jgunthorpe@obsidianresearch.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2014-07-31 02:40:53 +08:00
*addrlen = sctp_v6_addr_to_user(sctp_sk(asoc->base.sk), addr);
}
/* Initialize a msg_name from an inbound skb. */
static void sctp_inet6_skb_msgname(struct sk_buff *skb, char *msgname,
int *addr_len)
{
sctp: Fixup v4mapped behaviour to comply with Sock API The SCTP socket extensions API document describes the v4mapping option as follows: 8.1.15. Set/Clear IPv4 Mapped Addresses (SCTP_I_WANT_MAPPED_V4_ADDR) This socket option is a Boolean flag which turns on or off the mapping of IPv4 addresses. If this option is turned on, then IPv4 addresses will be mapped to V6 representation. If this option is turned off, then no mapping will be done of V4 addresses and a user will receive both PF_INET6 and PF_INET type addresses on the socket. See [RFC3542] for more details on mapped V6 addresses. This description isn't really in line with what the code does though. Introduce addr_to_user (renamed addr_v4map), which should be called before any sockaddr is passed back to user space. The new function places the sockaddr into the correct format depending on the SCTP_I_WANT_MAPPED_V4_ADDR option. Audit all places that touched v4mapped and either sanely construct a v4 or v6 address then call addr_to_user, or drop the unnecessary v4mapped check entirely. Audit all places that call addr_to_user and verify they are on a sycall return path. Add a custom getname that formats the address properly. Several bugs are addressed: - SCTP_I_WANT_MAPPED_V4_ADDR=0 often returned garbage for addresses to user space - The addr_len returned from recvmsg was not correct when returning AF_INET on a v6 socket - flowlabel and scope_id were not zerod when promoting a v4 to v6 - Some syscalls like bind and connect behaved differently depending on v4mapped Tested bind, getpeername, getsockname, connect, and recvmsg for proper behaviour in v4mapped = 1 and 0 cases. Signed-off-by: Neil Horman <nhorman@tuxdriver.com> Tested-by: Jason Gunthorpe <jgunthorpe@obsidianresearch.com> Signed-off-by: Jason Gunthorpe <jgunthorpe@obsidianresearch.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2014-07-31 02:40:53 +08:00
union sctp_addr *addr;
struct sctphdr *sh;
sctp: Fixup v4mapped behaviour to comply with Sock API The SCTP socket extensions API document describes the v4mapping option as follows: 8.1.15. Set/Clear IPv4 Mapped Addresses (SCTP_I_WANT_MAPPED_V4_ADDR) This socket option is a Boolean flag which turns on or off the mapping of IPv4 addresses. If this option is turned on, then IPv4 addresses will be mapped to V6 representation. If this option is turned off, then no mapping will be done of V4 addresses and a user will receive both PF_INET6 and PF_INET type addresses on the socket. See [RFC3542] for more details on mapped V6 addresses. This description isn't really in line with what the code does though. Introduce addr_to_user (renamed addr_v4map), which should be called before any sockaddr is passed back to user space. The new function places the sockaddr into the correct format depending on the SCTP_I_WANT_MAPPED_V4_ADDR option. Audit all places that touched v4mapped and either sanely construct a v4 or v6 address then call addr_to_user, or drop the unnecessary v4mapped check entirely. Audit all places that call addr_to_user and verify they are on a sycall return path. Add a custom getname that formats the address properly. Several bugs are addressed: - SCTP_I_WANT_MAPPED_V4_ADDR=0 often returned garbage for addresses to user space - The addr_len returned from recvmsg was not correct when returning AF_INET on a v6 socket - flowlabel and scope_id were not zerod when promoting a v4 to v6 - Some syscalls like bind and connect behaved differently depending on v4mapped Tested bind, getpeername, getsockname, connect, and recvmsg for proper behaviour in v4mapped = 1 and 0 cases. Signed-off-by: Neil Horman <nhorman@tuxdriver.com> Tested-by: Jason Gunthorpe <jgunthorpe@obsidianresearch.com> Signed-off-by: Jason Gunthorpe <jgunthorpe@obsidianresearch.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2014-07-31 02:40:53 +08:00
if (!msgname)
return;
addr = (union sctp_addr *)msgname;
sh = sctp_hdr(skb);
if (ip_hdr(skb)->version == 4) {
addr->v4.sin_family = AF_INET;
addr->v4.sin_port = sh->source;
sctp: allow GSO frags to access the chunk too SCTP will try to access original IP headers on sctp_recvmsg in order to copy the addresses used. There are also other places that do similar access to IP or even SCTP headers. But after 90017accff61 ("sctp: Add GSO support") they aren't always there because they are only present in the header skb. SCTP handles the queueing of incoming data by cloning the incoming skb and limiting to only the relevant payload. This clone has its cb updated to something different and it's then queued on socket rx queue. Thus we need to fix this in two moments. For rx path, not related to socket queue yet, this patch uses a partially copied sctp_input_cb to such GSO frags. This restores the ability to access the headers for this part of the code. Regarding the socket rx queue, it removes iif member from sctp_event and also add a chunk pointer on it. With these changes we're always able to reach the headers again. The biggest change here is that now the sctp_chunk struct and the original skb are only freed after the application consumed the buffer. Note however that the original payload was already like this due to the skb cloning. For iif, SCTP's IPv4 code doesn't use it, so no change is necessary. IPv6 now can fetch it directly from original's IPv6 CB as the original skb is still accessible. In the future we probably can simplify sctp_v*_skb_iif() stuff, as sctp_v4_skb_iif() was called but it's return value not used, and now it's not even called, but such cleanup is out of scope for this change. Fixes: 90017accff61 ("sctp: Add GSO support") Signed-off-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-07-14 02:08:57 +08:00
addr->v4.sin_addr.s_addr = ip_hdr(skb)->saddr;
sctp: Fixup v4mapped behaviour to comply with Sock API The SCTP socket extensions API document describes the v4mapping option as follows: 8.1.15. Set/Clear IPv4 Mapped Addresses (SCTP_I_WANT_MAPPED_V4_ADDR) This socket option is a Boolean flag which turns on or off the mapping of IPv4 addresses. If this option is turned on, then IPv4 addresses will be mapped to V6 representation. If this option is turned off, then no mapping will be done of V4 addresses and a user will receive both PF_INET6 and PF_INET type addresses on the socket. See [RFC3542] for more details on mapped V6 addresses. This description isn't really in line with what the code does though. Introduce addr_to_user (renamed addr_v4map), which should be called before any sockaddr is passed back to user space. The new function places the sockaddr into the correct format depending on the SCTP_I_WANT_MAPPED_V4_ADDR option. Audit all places that touched v4mapped and either sanely construct a v4 or v6 address then call addr_to_user, or drop the unnecessary v4mapped check entirely. Audit all places that call addr_to_user and verify they are on a sycall return path. Add a custom getname that formats the address properly. Several bugs are addressed: - SCTP_I_WANT_MAPPED_V4_ADDR=0 often returned garbage for addresses to user space - The addr_len returned from recvmsg was not correct when returning AF_INET on a v6 socket - flowlabel and scope_id were not zerod when promoting a v4 to v6 - Some syscalls like bind and connect behaved differently depending on v4mapped Tested bind, getpeername, getsockname, connect, and recvmsg for proper behaviour in v4mapped = 1 and 0 cases. Signed-off-by: Neil Horman <nhorman@tuxdriver.com> Tested-by: Jason Gunthorpe <jgunthorpe@obsidianresearch.com> Signed-off-by: Jason Gunthorpe <jgunthorpe@obsidianresearch.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2014-07-31 02:40:53 +08:00
} 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)
sctp: allow GSO frags to access the chunk too SCTP will try to access original IP headers on sctp_recvmsg in order to copy the addresses used. There are also other places that do similar access to IP or even SCTP headers. But after 90017accff61 ("sctp: Add GSO support") they aren't always there because they are only present in the header skb. SCTP handles the queueing of incoming data by cloning the incoming skb and limiting to only the relevant payload. This clone has its cb updated to something different and it's then queued on socket rx queue. Thus we need to fix this in two moments. For rx path, not related to socket queue yet, this patch uses a partially copied sctp_input_cb to such GSO frags. This restores the ability to access the headers for this part of the code. Regarding the socket rx queue, it removes iif member from sctp_event and also add a chunk pointer on it. With these changes we're always able to reach the headers again. The biggest change here is that now the sctp_chunk struct and the original skb are only freed after the application consumed the buffer. Note however that the original payload was already like this due to the skb cloning. For iif, SCTP's IPv4 code doesn't use it, so no change is necessary. IPv6 now can fetch it directly from original's IPv6 CB as the original skb is still accessible. In the future we probably can simplify sctp_v*_skb_iif() stuff, as sctp_v4_skb_iif() was called but it's return value not used, and now it's not even called, but such cleanup is out of scope for this change. Fixes: 90017accff61 ("sctp: Add GSO support") Signed-off-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-07-14 02:08:57 +08:00
addr->v6.sin6_scope_id = sctp_v6_skb_iif(skb);
else
addr->v6.sin6_scope_id = 0;
}
sctp: Fixup v4mapped behaviour to comply with Sock API The SCTP socket extensions API document describes the v4mapping option as follows: 8.1.15. Set/Clear IPv4 Mapped Addresses (SCTP_I_WANT_MAPPED_V4_ADDR) This socket option is a Boolean flag which turns on or off the mapping of IPv4 addresses. If this option is turned on, then IPv4 addresses will be mapped to V6 representation. If this option is turned off, then no mapping will be done of V4 addresses and a user will receive both PF_INET6 and PF_INET type addresses on the socket. See [RFC3542] for more details on mapped V6 addresses. This description isn't really in line with what the code does though. Introduce addr_to_user (renamed addr_v4map), which should be called before any sockaddr is passed back to user space. The new function places the sockaddr into the correct format depending on the SCTP_I_WANT_MAPPED_V4_ADDR option. Audit all places that touched v4mapped and either sanely construct a v4 or v6 address then call addr_to_user, or drop the unnecessary v4mapped check entirely. Audit all places that call addr_to_user and verify they are on a sycall return path. Add a custom getname that formats the address properly. Several bugs are addressed: - SCTP_I_WANT_MAPPED_V4_ADDR=0 often returned garbage for addresses to user space - The addr_len returned from recvmsg was not correct when returning AF_INET on a v6 socket - flowlabel and scope_id were not zerod when promoting a v4 to v6 - Some syscalls like bind and connect behaved differently depending on v4mapped Tested bind, getpeername, getsockname, connect, and recvmsg for proper behaviour in v4mapped = 1 and 0 cases. Signed-off-by: Neil Horman <nhorman@tuxdriver.com> Tested-by: Jason Gunthorpe <jgunthorpe@obsidianresearch.com> Signed-off-by: Jason Gunthorpe <jgunthorpe@obsidianresearch.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2014-07-31 02:40:53 +08:00
*addr_len = sctp_v6_addr_to_user(sctp_sk(skb->sk), addr);
}
/* Do we support this AF? */
static int sctp_inet6_af_supported(sa_family_t family, struct sctp_sock *sp)
{
switch (family) {
case AF_INET6:
return 1;
/* v4-mapped-v6 addresses */
case AF_INET:
if (!__ipv6_only_sock(sctp_opt2sk(sp)))
return 1;
/* fallthru */
default:
return 0;
}
}
/* Address matching with wildcards allowed. This extra level
* of indirection lets us choose whether a PF_INET6 should
* disallow any v4 addresses if we so choose.
*/
static int sctp_inet6_cmp_addr(const union sctp_addr *addr1,
const union sctp_addr *addr2,
struct sctp_sock *opt)
{
struct sock *sk = sctp_opt2sk(opt);
struct sctp_af *af1, *af2;
af1 = sctp_get_af_specific(addr1->sa.sa_family);
af2 = sctp_get_af_specific(addr2->sa.sa_family);
if (!af1 || !af2)
return 0;
/* If the socket is IPv6 only, v4 addrs will not match */
if (__ipv6_only_sock(sk) && af1 != af2)
return 0;
/* Today, wildcard AF_INET/AF_INET6. */
if (sctp_is_any(sk, addr1) || sctp_is_any(sk, addr2))
return 1;
if (addr1->sa.sa_family == AF_INET && addr2->sa.sa_family == AF_INET)
return addr1->v4.sin_addr.s_addr == addr2->v4.sin_addr.s_addr;
return __sctp_v6_cmp_addr(addr1, addr2);
}
/* Verify that the provided sockaddr looks bindable. Common verification,
* has already been taken care of.
*/
static int sctp_inet6_bind_verify(struct sctp_sock *opt, union sctp_addr *addr)
{
struct sctp_af *af;
/* ASSERT: address family has already been verified. */
if (addr->sa.sa_family != AF_INET6)
af = sctp_get_af_specific(addr->sa.sa_family);
else {
int type = ipv6_addr_type(&addr->v6.sin6_addr);
struct net_device *dev;
if (type & IPV6_ADDR_LINKLOCAL) {
struct net *net;
if (!addr->v6.sin6_scope_id)
return 0;
net = sock_net(&opt->inet.sk);
rcu_read_lock();
dev = dev_get_by_index_rcu(net, addr->v6.sin6_scope_id);
if (!dev || !(ipv6_can_nonlocal_bind(net, &opt->inet) ||
ipv6_chk_addr(net, &addr->v6.sin6_addr,
dev, 0))) {
rcu_read_unlock();
return 0;
}
rcu_read_unlock();
}
af = opt->pf->af;
}
return af->available(addr, opt);
}
/* Verify that the provided sockaddr looks sendable. Common verification,
* has already been taken care of.
*/
static int sctp_inet6_send_verify(struct sctp_sock *opt, union sctp_addr *addr)
{
struct sctp_af *af = NULL;
/* ASSERT: address family has already been verified. */
if (addr->sa.sa_family != AF_INET6)
af = sctp_get_af_specific(addr->sa.sa_family);
else {
int type = ipv6_addr_type(&addr->v6.sin6_addr);
struct net_device *dev;
if (type & IPV6_ADDR_LINKLOCAL) {
if (!addr->v6.sin6_scope_id)
return 0;
rcu_read_lock();
dev = dev_get_by_index_rcu(sock_net(&opt->inet.sk),
addr->v6.sin6_scope_id);
rcu_read_unlock();
if (!dev)
return 0;
}
af = opt->pf->af;
}
return af != NULL;
}
/* Fill in Supported Address Type information for INIT and INIT-ACK
* chunks. Note: In the future, we may want to look at sock options
* to determine whether a PF_INET6 socket really wants to have IPV4
* addresses.
* Returns number of addresses supported.
*/
static int sctp_inet6_supported_addrs(const struct sctp_sock *opt,
__be16 *types)
{
types[0] = SCTP_PARAM_IPV6_ADDRESS;
if (!opt || !ipv6_only_sock(sctp_opt2sk(opt))) {
types[1] = SCTP_PARAM_IPV4_ADDRESS;
return 2;
}
return 1;
}
sctp: Fixup v4mapped behaviour to comply with Sock API The SCTP socket extensions API document describes the v4mapping option as follows: 8.1.15. Set/Clear IPv4 Mapped Addresses (SCTP_I_WANT_MAPPED_V4_ADDR) This socket option is a Boolean flag which turns on or off the mapping of IPv4 addresses. If this option is turned on, then IPv4 addresses will be mapped to V6 representation. If this option is turned off, then no mapping will be done of V4 addresses and a user will receive both PF_INET6 and PF_INET type addresses on the socket. See [RFC3542] for more details on mapped V6 addresses. This description isn't really in line with what the code does though. Introduce addr_to_user (renamed addr_v4map), which should be called before any sockaddr is passed back to user space. The new function places the sockaddr into the correct format depending on the SCTP_I_WANT_MAPPED_V4_ADDR option. Audit all places that touched v4mapped and either sanely construct a v4 or v6 address then call addr_to_user, or drop the unnecessary v4mapped check entirely. Audit all places that call addr_to_user and verify they are on a sycall return path. Add a custom getname that formats the address properly. Several bugs are addressed: - SCTP_I_WANT_MAPPED_V4_ADDR=0 often returned garbage for addresses to user space - The addr_len returned from recvmsg was not correct when returning AF_INET on a v6 socket - flowlabel and scope_id were not zerod when promoting a v4 to v6 - Some syscalls like bind and connect behaved differently depending on v4mapped Tested bind, getpeername, getsockname, connect, and recvmsg for proper behaviour in v4mapped = 1 and 0 cases. Signed-off-by: Neil Horman <nhorman@tuxdriver.com> Tested-by: Jason Gunthorpe <jgunthorpe@obsidianresearch.com> Signed-off-by: Jason Gunthorpe <jgunthorpe@obsidianresearch.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2014-07-31 02:40:53 +08:00
/* Handle SCTP_I_WANT_MAPPED_V4_ADDR for getpeername() and getsockname() */
static int sctp_getname(struct socket *sock, struct sockaddr *uaddr,
net: make getname() functions return length rather than use int* parameter Changes since v1: Added changes in these files: drivers/infiniband/hw/usnic/usnic_transport.c drivers/staging/lustre/lnet/lnet/lib-socket.c drivers/target/iscsi/iscsi_target_login.c drivers/vhost/net.c fs/dlm/lowcomms.c fs/ocfs2/cluster/tcp.c security/tomoyo/network.c Before: All these functions either return a negative error indicator, or store length of sockaddr into "int *socklen" parameter and return zero on success. "int *socklen" parameter is awkward. For example, if caller does not care, it still needs to provide on-stack storage for the value it does not need. None of the many FOO_getname() functions of various protocols ever used old value of *socklen. They always just overwrite it. This change drops this parameter, and makes all these functions, on success, return length of sockaddr. It's always >= 0 and can be differentiated from an error. Tests in callers are changed from "if (err)" to "if (err < 0)", where needed. rpc_sockname() lost "int buflen" parameter, since its only use was to be passed to kernel_getsockname() as &buflen and subsequently not used in any way. Userspace API is not changed. text data bss dec hex filename 30108430 2633624 873672 33615726 200ef6e vmlinux.before.o 30108109 2633612 873672 33615393 200ee21 vmlinux.o Signed-off-by: Denys Vlasenko <dvlasenk@redhat.com> CC: David S. Miller <davem@davemloft.net> CC: linux-kernel@vger.kernel.org CC: netdev@vger.kernel.org CC: linux-bluetooth@vger.kernel.org CC: linux-decnet-user@lists.sourceforge.net CC: linux-wireless@vger.kernel.org CC: linux-rdma@vger.kernel.org CC: linux-sctp@vger.kernel.org CC: linux-nfs@vger.kernel.org CC: linux-x25@vger.kernel.org Signed-off-by: David S. Miller <davem@davemloft.net>
2018-02-13 03:00:20 +08:00
int peer)
sctp: Fixup v4mapped behaviour to comply with Sock API The SCTP socket extensions API document describes the v4mapping option as follows: 8.1.15. Set/Clear IPv4 Mapped Addresses (SCTP_I_WANT_MAPPED_V4_ADDR) This socket option is a Boolean flag which turns on or off the mapping of IPv4 addresses. If this option is turned on, then IPv4 addresses will be mapped to V6 representation. If this option is turned off, then no mapping will be done of V4 addresses and a user will receive both PF_INET6 and PF_INET type addresses on the socket. See [RFC3542] for more details on mapped V6 addresses. This description isn't really in line with what the code does though. Introduce addr_to_user (renamed addr_v4map), which should be called before any sockaddr is passed back to user space. The new function places the sockaddr into the correct format depending on the SCTP_I_WANT_MAPPED_V4_ADDR option. Audit all places that touched v4mapped and either sanely construct a v4 or v6 address then call addr_to_user, or drop the unnecessary v4mapped check entirely. Audit all places that call addr_to_user and verify they are on a sycall return path. Add a custom getname that formats the address properly. Several bugs are addressed: - SCTP_I_WANT_MAPPED_V4_ADDR=0 often returned garbage for addresses to user space - The addr_len returned from recvmsg was not correct when returning AF_INET on a v6 socket - flowlabel and scope_id were not zerod when promoting a v4 to v6 - Some syscalls like bind and connect behaved differently depending on v4mapped Tested bind, getpeername, getsockname, connect, and recvmsg for proper behaviour in v4mapped = 1 and 0 cases. Signed-off-by: Neil Horman <nhorman@tuxdriver.com> Tested-by: Jason Gunthorpe <jgunthorpe@obsidianresearch.com> Signed-off-by: Jason Gunthorpe <jgunthorpe@obsidianresearch.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2014-07-31 02:40:53 +08:00
{
int rc;
net: make getname() functions return length rather than use int* parameter Changes since v1: Added changes in these files: drivers/infiniband/hw/usnic/usnic_transport.c drivers/staging/lustre/lnet/lnet/lib-socket.c drivers/target/iscsi/iscsi_target_login.c drivers/vhost/net.c fs/dlm/lowcomms.c fs/ocfs2/cluster/tcp.c security/tomoyo/network.c Before: All these functions either return a negative error indicator, or store length of sockaddr into "int *socklen" parameter and return zero on success. "int *socklen" parameter is awkward. For example, if caller does not care, it still needs to provide on-stack storage for the value it does not need. None of the many FOO_getname() functions of various protocols ever used old value of *socklen. They always just overwrite it. This change drops this parameter, and makes all these functions, on success, return length of sockaddr. It's always >= 0 and can be differentiated from an error. Tests in callers are changed from "if (err)" to "if (err < 0)", where needed. rpc_sockname() lost "int buflen" parameter, since its only use was to be passed to kernel_getsockname() as &buflen and subsequently not used in any way. Userspace API is not changed. text data bss dec hex filename 30108430 2633624 873672 33615726 200ef6e vmlinux.before.o 30108109 2633612 873672 33615393 200ee21 vmlinux.o Signed-off-by: Denys Vlasenko <dvlasenk@redhat.com> CC: David S. Miller <davem@davemloft.net> CC: linux-kernel@vger.kernel.org CC: netdev@vger.kernel.org CC: linux-bluetooth@vger.kernel.org CC: linux-decnet-user@lists.sourceforge.net CC: linux-wireless@vger.kernel.org CC: linux-rdma@vger.kernel.org CC: linux-sctp@vger.kernel.org CC: linux-nfs@vger.kernel.org CC: linux-x25@vger.kernel.org Signed-off-by: David S. Miller <davem@davemloft.net>
2018-02-13 03:00:20 +08:00
rc = inet6_getname(sock, uaddr, peer);
sctp: Fixup v4mapped behaviour to comply with Sock API The SCTP socket extensions API document describes the v4mapping option as follows: 8.1.15. Set/Clear IPv4 Mapped Addresses (SCTP_I_WANT_MAPPED_V4_ADDR) This socket option is a Boolean flag which turns on or off the mapping of IPv4 addresses. If this option is turned on, then IPv4 addresses will be mapped to V6 representation. If this option is turned off, then no mapping will be done of V4 addresses and a user will receive both PF_INET6 and PF_INET type addresses on the socket. See [RFC3542] for more details on mapped V6 addresses. This description isn't really in line with what the code does though. Introduce addr_to_user (renamed addr_v4map), which should be called before any sockaddr is passed back to user space. The new function places the sockaddr into the correct format depending on the SCTP_I_WANT_MAPPED_V4_ADDR option. Audit all places that touched v4mapped and either sanely construct a v4 or v6 address then call addr_to_user, or drop the unnecessary v4mapped check entirely. Audit all places that call addr_to_user and verify they are on a sycall return path. Add a custom getname that formats the address properly. Several bugs are addressed: - SCTP_I_WANT_MAPPED_V4_ADDR=0 often returned garbage for addresses to user space - The addr_len returned from recvmsg was not correct when returning AF_INET on a v6 socket - flowlabel and scope_id were not zerod when promoting a v4 to v6 - Some syscalls like bind and connect behaved differently depending on v4mapped Tested bind, getpeername, getsockname, connect, and recvmsg for proper behaviour in v4mapped = 1 and 0 cases. Signed-off-by: Neil Horman <nhorman@tuxdriver.com> Tested-by: Jason Gunthorpe <jgunthorpe@obsidianresearch.com> Signed-off-by: Jason Gunthorpe <jgunthorpe@obsidianresearch.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2014-07-31 02:40:53 +08:00
net: make getname() functions return length rather than use int* parameter Changes since v1: Added changes in these files: drivers/infiniband/hw/usnic/usnic_transport.c drivers/staging/lustre/lnet/lnet/lib-socket.c drivers/target/iscsi/iscsi_target_login.c drivers/vhost/net.c fs/dlm/lowcomms.c fs/ocfs2/cluster/tcp.c security/tomoyo/network.c Before: All these functions either return a negative error indicator, or store length of sockaddr into "int *socklen" parameter and return zero on success. "int *socklen" parameter is awkward. For example, if caller does not care, it still needs to provide on-stack storage for the value it does not need. None of the many FOO_getname() functions of various protocols ever used old value of *socklen. They always just overwrite it. This change drops this parameter, and makes all these functions, on success, return length of sockaddr. It's always >= 0 and can be differentiated from an error. Tests in callers are changed from "if (err)" to "if (err < 0)", where needed. rpc_sockname() lost "int buflen" parameter, since its only use was to be passed to kernel_getsockname() as &buflen and subsequently not used in any way. Userspace API is not changed. text data bss dec hex filename 30108430 2633624 873672 33615726 200ef6e vmlinux.before.o 30108109 2633612 873672 33615393 200ee21 vmlinux.o Signed-off-by: Denys Vlasenko <dvlasenk@redhat.com> CC: David S. Miller <davem@davemloft.net> CC: linux-kernel@vger.kernel.org CC: netdev@vger.kernel.org CC: linux-bluetooth@vger.kernel.org CC: linux-decnet-user@lists.sourceforge.net CC: linux-wireless@vger.kernel.org CC: linux-rdma@vger.kernel.org CC: linux-sctp@vger.kernel.org CC: linux-nfs@vger.kernel.org CC: linux-x25@vger.kernel.org Signed-off-by: David S. Miller <davem@davemloft.net>
2018-02-13 03:00:20 +08:00
if (rc < 0)
sctp: Fixup v4mapped behaviour to comply with Sock API The SCTP socket extensions API document describes the v4mapping option as follows: 8.1.15. Set/Clear IPv4 Mapped Addresses (SCTP_I_WANT_MAPPED_V4_ADDR) This socket option is a Boolean flag which turns on or off the mapping of IPv4 addresses. If this option is turned on, then IPv4 addresses will be mapped to V6 representation. If this option is turned off, then no mapping will be done of V4 addresses and a user will receive both PF_INET6 and PF_INET type addresses on the socket. See [RFC3542] for more details on mapped V6 addresses. This description isn't really in line with what the code does though. Introduce addr_to_user (renamed addr_v4map), which should be called before any sockaddr is passed back to user space. The new function places the sockaddr into the correct format depending on the SCTP_I_WANT_MAPPED_V4_ADDR option. Audit all places that touched v4mapped and either sanely construct a v4 or v6 address then call addr_to_user, or drop the unnecessary v4mapped check entirely. Audit all places that call addr_to_user and verify they are on a sycall return path. Add a custom getname that formats the address properly. Several bugs are addressed: - SCTP_I_WANT_MAPPED_V4_ADDR=0 often returned garbage for addresses to user space - The addr_len returned from recvmsg was not correct when returning AF_INET on a v6 socket - flowlabel and scope_id were not zerod when promoting a v4 to v6 - Some syscalls like bind and connect behaved differently depending on v4mapped Tested bind, getpeername, getsockname, connect, and recvmsg for proper behaviour in v4mapped = 1 and 0 cases. Signed-off-by: Neil Horman <nhorman@tuxdriver.com> Tested-by: Jason Gunthorpe <jgunthorpe@obsidianresearch.com> Signed-off-by: Jason Gunthorpe <jgunthorpe@obsidianresearch.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2014-07-31 02:40:53 +08:00
return rc;
net: make getname() functions return length rather than use int* parameter Changes since v1: Added changes in these files: drivers/infiniband/hw/usnic/usnic_transport.c drivers/staging/lustre/lnet/lnet/lib-socket.c drivers/target/iscsi/iscsi_target_login.c drivers/vhost/net.c fs/dlm/lowcomms.c fs/ocfs2/cluster/tcp.c security/tomoyo/network.c Before: All these functions either return a negative error indicator, or store length of sockaddr into "int *socklen" parameter and return zero on success. "int *socklen" parameter is awkward. For example, if caller does not care, it still needs to provide on-stack storage for the value it does not need. None of the many FOO_getname() functions of various protocols ever used old value of *socklen. They always just overwrite it. This change drops this parameter, and makes all these functions, on success, return length of sockaddr. It's always >= 0 and can be differentiated from an error. Tests in callers are changed from "if (err)" to "if (err < 0)", where needed. rpc_sockname() lost "int buflen" parameter, since its only use was to be passed to kernel_getsockname() as &buflen and subsequently not used in any way. Userspace API is not changed. text data bss dec hex filename 30108430 2633624 873672 33615726 200ef6e vmlinux.before.o 30108109 2633612 873672 33615393 200ee21 vmlinux.o Signed-off-by: Denys Vlasenko <dvlasenk@redhat.com> CC: David S. Miller <davem@davemloft.net> CC: linux-kernel@vger.kernel.org CC: netdev@vger.kernel.org CC: linux-bluetooth@vger.kernel.org CC: linux-decnet-user@lists.sourceforge.net CC: linux-wireless@vger.kernel.org CC: linux-rdma@vger.kernel.org CC: linux-sctp@vger.kernel.org CC: linux-nfs@vger.kernel.org CC: linux-x25@vger.kernel.org Signed-off-by: David S. Miller <davem@davemloft.net>
2018-02-13 03:00:20 +08:00
rc = sctp_v6_addr_to_user(sctp_sk(sock->sk),
sctp: Fixup v4mapped behaviour to comply with Sock API The SCTP socket extensions API document describes the v4mapping option as follows: 8.1.15. Set/Clear IPv4 Mapped Addresses (SCTP_I_WANT_MAPPED_V4_ADDR) This socket option is a Boolean flag which turns on or off the mapping of IPv4 addresses. If this option is turned on, then IPv4 addresses will be mapped to V6 representation. If this option is turned off, then no mapping will be done of V4 addresses and a user will receive both PF_INET6 and PF_INET type addresses on the socket. See [RFC3542] for more details on mapped V6 addresses. This description isn't really in line with what the code does though. Introduce addr_to_user (renamed addr_v4map), which should be called before any sockaddr is passed back to user space. The new function places the sockaddr into the correct format depending on the SCTP_I_WANT_MAPPED_V4_ADDR option. Audit all places that touched v4mapped and either sanely construct a v4 or v6 address then call addr_to_user, or drop the unnecessary v4mapped check entirely. Audit all places that call addr_to_user and verify they are on a sycall return path. Add a custom getname that formats the address properly. Several bugs are addressed: - SCTP_I_WANT_MAPPED_V4_ADDR=0 often returned garbage for addresses to user space - The addr_len returned from recvmsg was not correct when returning AF_INET on a v6 socket - flowlabel and scope_id were not zerod when promoting a v4 to v6 - Some syscalls like bind and connect behaved differently depending on v4mapped Tested bind, getpeername, getsockname, connect, and recvmsg for proper behaviour in v4mapped = 1 and 0 cases. Signed-off-by: Neil Horman <nhorman@tuxdriver.com> Tested-by: Jason Gunthorpe <jgunthorpe@obsidianresearch.com> Signed-off-by: Jason Gunthorpe <jgunthorpe@obsidianresearch.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2014-07-31 02:40:53 +08:00
(union sctp_addr *)uaddr);
return rc;
}
static const struct proto_ops inet6_seqpacket_ops = {
.family = PF_INET6,
.owner = THIS_MODULE,
.release = inet6_release,
.bind = inet6_bind,
.connect = sctp_inet_connect,
.socketpair = sock_no_socketpair,
.accept = inet_accept,
sctp: Fixup v4mapped behaviour to comply with Sock API The SCTP socket extensions API document describes the v4mapping option as follows: 8.1.15. Set/Clear IPv4 Mapped Addresses (SCTP_I_WANT_MAPPED_V4_ADDR) This socket option is a Boolean flag which turns on or off the mapping of IPv4 addresses. If this option is turned on, then IPv4 addresses will be mapped to V6 representation. If this option is turned off, then no mapping will be done of V4 addresses and a user will receive both PF_INET6 and PF_INET type addresses on the socket. See [RFC3542] for more details on mapped V6 addresses. This description isn't really in line with what the code does though. Introduce addr_to_user (renamed addr_v4map), which should be called before any sockaddr is passed back to user space. The new function places the sockaddr into the correct format depending on the SCTP_I_WANT_MAPPED_V4_ADDR option. Audit all places that touched v4mapped and either sanely construct a v4 or v6 address then call addr_to_user, or drop the unnecessary v4mapped check entirely. Audit all places that call addr_to_user and verify they are on a sycall return path. Add a custom getname that formats the address properly. Several bugs are addressed: - SCTP_I_WANT_MAPPED_V4_ADDR=0 often returned garbage for addresses to user space - The addr_len returned from recvmsg was not correct when returning AF_INET on a v6 socket - flowlabel and scope_id were not zerod when promoting a v4 to v6 - Some syscalls like bind and connect behaved differently depending on v4mapped Tested bind, getpeername, getsockname, connect, and recvmsg for proper behaviour in v4mapped = 1 and 0 cases. Signed-off-by: Neil Horman <nhorman@tuxdriver.com> Tested-by: Jason Gunthorpe <jgunthorpe@obsidianresearch.com> Signed-off-by: Jason Gunthorpe <jgunthorpe@obsidianresearch.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2014-07-31 02:40:53 +08:00
.getname = sctp_getname,
.poll = sctp_poll,
.ioctl = inet6_ioctl,
.gettstamp = sock_gettstamp,
.listen = sctp_inet_listen,
.shutdown = inet_shutdown,
.setsockopt = sock_common_setsockopt,
.getsockopt = sock_common_getsockopt,
.sendmsg = inet_sendmsg,
.recvmsg = inet_recvmsg,
.mmap = sock_no_mmap,
#ifdef CONFIG_COMPAT
.compat_setsockopt = compat_sock_common_setsockopt,
.compat_getsockopt = compat_sock_common_getsockopt,
#endif
};
static struct inet_protosw sctpv6_seqpacket_protosw = {
.type = SOCK_SEQPACKET,
.protocol = IPPROTO_SCTP,
.prot = &sctpv6_prot,
.ops = &inet6_seqpacket_ops,
.flags = SCTP_PROTOSW_FLAG
};
static struct inet_protosw sctpv6_stream_protosw = {
.type = SOCK_STREAM,
.protocol = IPPROTO_SCTP,
.prot = &sctpv6_prot,
.ops = &inet6_seqpacket_ops,
.flags = SCTP_PROTOSW_FLAG,
};
static int sctp6_rcv(struct sk_buff *skb)
{
return sctp_rcv(skb) ? -1 : 0;
}
static const struct inet6_protocol sctpv6_protocol = {
.handler = sctp6_rcv,
.err_handler = sctp_v6_err,
.flags = INET6_PROTO_NOPOLICY | INET6_PROTO_FINAL,
};
static struct sctp_af sctp_af_inet6 = {
.sa_family = AF_INET6,
.sctp_xmit = sctp_v6_xmit,
.setsockopt = ipv6_setsockopt,
.getsockopt = ipv6_getsockopt,
.get_dst = sctp_v6_get_dst,
.get_saddr = sctp_v6_get_saddr,
.copy_addrlist = sctp_v6_copy_addrlist,
.from_skb = sctp_v6_from_skb,
.from_sk = sctp_v6_from_sk,
.from_addr_param = sctp_v6_from_addr_param,
.to_addr_param = sctp_v6_to_addr_param,
.cmp_addr = sctp_v6_cmp_addr,
.scope = sctp_v6_scope,
.addr_valid = sctp_v6_addr_valid,
.inaddr_any = sctp_v6_inaddr_any,
.is_any = sctp_v6_is_any,
.available = sctp_v6_available,
.skb_iif = sctp_v6_skb_iif,
.is_ce = sctp_v6_is_ce,
.seq_dump_addr = sctp_v6_seq_dump_addr,
.ecn_capable = sctp_v6_ecn_capable,
.net_header_len = sizeof(struct ipv6hdr),
.sockaddr_len = sizeof(struct sockaddr_in6),
.ip_options_len = sctp_v6_ip_options_len,
#ifdef CONFIG_COMPAT
.compat_setsockopt = compat_ipv6_setsockopt,
.compat_getsockopt = compat_ipv6_getsockopt,
#endif
};
static struct sctp_pf sctp_pf_inet6 = {
.event_msgname = sctp_inet6_event_msgname,
.skb_msgname = sctp_inet6_skb_msgname,
.af_supported = sctp_inet6_af_supported,
.cmp_addr = sctp_inet6_cmp_addr,
.bind_verify = sctp_inet6_bind_verify,
.send_verify = sctp_inet6_send_verify,
.supported_addrs = sctp_inet6_supported_addrs,
.create_accept_sk = sctp_v6_create_accept_sk,
sctp: Fixup v4mapped behaviour to comply with Sock API The SCTP socket extensions API document describes the v4mapping option as follows: 8.1.15. Set/Clear IPv4 Mapped Addresses (SCTP_I_WANT_MAPPED_V4_ADDR) This socket option is a Boolean flag which turns on or off the mapping of IPv4 addresses. If this option is turned on, then IPv4 addresses will be mapped to V6 representation. If this option is turned off, then no mapping will be done of V4 addresses and a user will receive both PF_INET6 and PF_INET type addresses on the socket. See [RFC3542] for more details on mapped V6 addresses. This description isn't really in line with what the code does though. Introduce addr_to_user (renamed addr_v4map), which should be called before any sockaddr is passed back to user space. The new function places the sockaddr into the correct format depending on the SCTP_I_WANT_MAPPED_V4_ADDR option. Audit all places that touched v4mapped and either sanely construct a v4 or v6 address then call addr_to_user, or drop the unnecessary v4mapped check entirely. Audit all places that call addr_to_user and verify they are on a sycall return path. Add a custom getname that formats the address properly. Several bugs are addressed: - SCTP_I_WANT_MAPPED_V4_ADDR=0 often returned garbage for addresses to user space - The addr_len returned from recvmsg was not correct when returning AF_INET on a v6 socket - flowlabel and scope_id were not zerod when promoting a v4 to v6 - Some syscalls like bind and connect behaved differently depending on v4mapped Tested bind, getpeername, getsockname, connect, and recvmsg for proper behaviour in v4mapped = 1 and 0 cases. Signed-off-by: Neil Horman <nhorman@tuxdriver.com> Tested-by: Jason Gunthorpe <jgunthorpe@obsidianresearch.com> Signed-off-by: Jason Gunthorpe <jgunthorpe@obsidianresearch.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2014-07-31 02:40:53 +08:00
.addr_to_user = sctp_v6_addr_to_user,
.to_sk_saddr = sctp_v6_to_sk_saddr,
.to_sk_daddr = sctp_v6_to_sk_daddr,
.copy_ip_options = sctp_v6_copy_ip_options,
.af = &sctp_af_inet6,
};
/* Initialize IPv6 support and register with socket layer. */
void sctp_v6_pf_init(void)
{
/* Register the SCTP specific PF_INET6 functions. */
sctp_register_pf(&sctp_pf_inet6, PF_INET6);
/* Register the SCTP specific AF_INET6 functions. */
sctp_register_af(&sctp_af_inet6);
}
void sctp_v6_pf_exit(void)
{
list_del(&sctp_af_inet6.list);
}
/* Initialize IPv6 support and register with socket layer. */
int sctp_v6_protosw_init(void)
{
int rc;
rc = proto_register(&sctpv6_prot, 1);
if (rc)
return rc;
/* Add SCTPv6(UDP and TCP style) to inetsw6 linked list. */
inet6_register_protosw(&sctpv6_seqpacket_protosw);
inet6_register_protosw(&sctpv6_stream_protosw);
return 0;
}
void sctp_v6_protosw_exit(void)
{
inet6_unregister_protosw(&sctpv6_seqpacket_protosw);
inet6_unregister_protosw(&sctpv6_stream_protosw);
proto_unregister(&sctpv6_prot);
}
/* Register with inet6 layer. */
int sctp_v6_add_protocol(void)
{
/* Register notifier for inet6 address additions/deletions. */
register_inet6addr_notifier(&sctp_inet6addr_notifier);
if (inet6_add_protocol(&sctpv6_protocol, IPPROTO_SCTP) < 0)
return -EAGAIN;
return 0;
}
/* Unregister with inet6 layer. */
void sctp_v6_del_protocol(void)
{
inet6_del_protocol(&sctpv6_protocol, IPPROTO_SCTP);
unregister_inet6addr_notifier(&sctp_inet6addr_notifier);
}