linux_dsm_epyc7002/net/ipv6/icmp.c

1134 lines
26 KiB
C
Raw Normal View History

/*
* Internet Control Message Protocol (ICMPv6)
* Linux INET6 implementation
*
* Authors:
* Pedro Roque <roque@di.fc.ul.pt>
*
* Based on net/ipv4/icmp.c
*
* RFC 1885
*
* This program is free software; you can redistribute it and/or
* modify it under the terms of the GNU General Public License
* as published by the Free Software Foundation; either version
* 2 of the License, or (at your option) any later version.
*/
/*
* Changes:
*
* Andi Kleen : exception handling
* Andi Kleen add rate limits. never reply to a icmp.
* add more length checks and other fixes.
* yoshfuji : ensure to sent parameter problem for
* fragments.
* YOSHIFUJI Hideaki @USAGI: added sysctl for icmp rate limit.
* Randy Dunlap and
* YOSHIFUJI Hideaki @USAGI: Per-interface statistics support
* Kazunori MIYAZAWA @USAGI: change output process to use ip6_append_data
*/
#define pr_fmt(fmt) "IPv6: " fmt
#include <linux/module.h>
#include <linux/errno.h>
#include <linux/types.h>
#include <linux/socket.h>
#include <linux/in.h>
#include <linux/kernel.h>
#include <linux/sockios.h>
#include <linux/net.h>
#include <linux/skbuff.h>
#include <linux/init.h>
#include <linux/netfilter.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 15:04:11 +07:00
#include <linux/slab.h>
#ifdef CONFIG_SYSCTL
#include <linux/sysctl.h>
#endif
#include <linux/inet.h>
#include <linux/netdevice.h>
#include <linux/icmpv6.h>
#include <net/ip.h>
#include <net/sock.h>
#include <net/ipv6.h>
#include <net/ip6_checksum.h>
#include <net/ping.h>
#include <net/protocol.h>
#include <net/raw.h>
#include <net/rawv6.h>
#include <net/transp_v6.h>
#include <net/ip6_route.h>
#include <net/addrconf.h>
#include <net/icmp.h>
#include <net/xfrm.h>
#include <net/inet_common.h>
#include <net/dsfield.h>
#include <net/l3mdev.h>
#include <linux/uaccess.h>
/*
* The ICMP socket(s). This is the most convenient way to flow control
* our ICMP output as well as maintain a clean interface throughout
* all layers. All Socketless IP sends will soon be gone.
*
* On SMP we have one ICMP socket per-cpu.
*/
static inline struct sock *icmpv6_sk(struct net *net)
{
return net->ipv6.icmp_sk[smp_processor_id()];
}
static void icmpv6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
u8 type, u8 code, int offset, __be32 info)
{
/* icmpv6_notify checks 8 bytes can be pulled, icmp6hdr is 8 bytes */
struct icmp6hdr *icmp6 = (struct icmp6hdr *) (skb->data + offset);
struct net *net = dev_net(skb->dev);
if (type == ICMPV6_PKT_TOOBIG)
ip6_update_pmtu(skb, net, info, skb->dev->ifindex, 0, sock_net_uid(net, NULL));
else if (type == NDISC_REDIRECT)
ip6_redirect(skb, net, skb->dev->ifindex, 0,
sock_net_uid(net, NULL));
if (!(type & ICMPV6_INFOMSG_MASK))
if (icmp6->icmp6_type == ICMPV6_ECHO_REQUEST)
ping_err(skb, offset, ntohl(info));
}
static int icmpv6_rcv(struct sk_buff *skb);
static const struct inet6_protocol icmpv6_protocol = {
.handler = icmpv6_rcv,
.err_handler = icmpv6_err,
.flags = INET6_PROTO_NOPOLICY|INET6_PROTO_FINAL,
};
/* Called with BH disabled */
icmp: icmp_sk() should not use smp_processor_id() in preemptible code Pass namespace into icmp_xmit_lock, obtain socket inside and return it as a result for caller. Thanks Alexey Dobryan for this report: Steps to reproduce: CONFIG_PREEMPT=y CONFIG_DEBUG_PREEMPT=y tracepath <something> BUG: using smp_processor_id() in preemptible [00000000] code: tracepath/3205 caller is icmp_sk+0x15/0x30 Pid: 3205, comm: tracepath Not tainted 2.6.27-rc4 #1 Call Trace: [<ffffffff8031af14>] debug_smp_processor_id+0xe4/0xf0 [<ffffffff80409405>] icmp_sk+0x15/0x30 [<ffffffff8040a17b>] icmp_send+0x4b/0x3f0 [<ffffffff8025a415>] ? trace_hardirqs_on_caller+0xd5/0x160 [<ffffffff8025a4ad>] ? trace_hardirqs_on+0xd/0x10 [<ffffffff8023a475>] ? local_bh_enable_ip+0x95/0x110 [<ffffffff804285b9>] ? _spin_unlock_bh+0x39/0x40 [<ffffffff8025a26c>] ? mark_held_locks+0x4c/0x90 [<ffffffff8025a4ad>] ? trace_hardirqs_on+0xd/0x10 [<ffffffff8025a415>] ? trace_hardirqs_on_caller+0xd5/0x160 [<ffffffff803e91b4>] ip_fragment+0x8d4/0x900 [<ffffffff803e7030>] ? ip_finish_output2+0x0/0x290 [<ffffffff803e91e0>] ? ip_finish_output+0x0/0x60 [<ffffffff803e6650>] ? dst_output+0x0/0x10 [<ffffffff803e922c>] ip_finish_output+0x4c/0x60 [<ffffffff803e92e3>] ip_output+0xa3/0xf0 [<ffffffff803e68d0>] ip_local_out+0x20/0x30 [<ffffffff803e753f>] ip_push_pending_frames+0x27f/0x400 [<ffffffff80406313>] udp_push_pending_frames+0x233/0x3d0 [<ffffffff804067d1>] udp_sendmsg+0x321/0x6f0 [<ffffffff8040d155>] inet_sendmsg+0x45/0x80 [<ffffffff803b967f>] sock_sendmsg+0xdf/0x110 [<ffffffff8024a100>] ? autoremove_wake_function+0x0/0x40 [<ffffffff80257ce5>] ? validate_chain+0x415/0x1010 [<ffffffff8027dc10>] ? __do_fault+0x140/0x450 [<ffffffff802597d0>] ? __lock_acquire+0x260/0x590 [<ffffffff803b9e55>] ? sockfd_lookup_light+0x45/0x80 [<ffffffff803ba50a>] sys_sendto+0xea/0x120 [<ffffffff80428e42>] ? _spin_unlock_irqrestore+0x42/0x80 [<ffffffff803134bc>] ? __up_read+0x4c/0xb0 [<ffffffff8024e0c6>] ? up_read+0x26/0x30 [<ffffffff8020b8bb>] system_call_fastpath+0x16/0x1b icmp6_sk() is similar. Signed-off-by: Denis V. Lunev <den@openvz.org> Signed-off-by: David S. Miller <davem@davemloft.net>
2008-08-23 18:43:33 +07:00
static __inline__ struct sock *icmpv6_xmit_lock(struct net *net)
{
icmp: icmp_sk() should not use smp_processor_id() in preemptible code Pass namespace into icmp_xmit_lock, obtain socket inside and return it as a result for caller. Thanks Alexey Dobryan for this report: Steps to reproduce: CONFIG_PREEMPT=y CONFIG_DEBUG_PREEMPT=y tracepath <something> BUG: using smp_processor_id() in preemptible [00000000] code: tracepath/3205 caller is icmp_sk+0x15/0x30 Pid: 3205, comm: tracepath Not tainted 2.6.27-rc4 #1 Call Trace: [<ffffffff8031af14>] debug_smp_processor_id+0xe4/0xf0 [<ffffffff80409405>] icmp_sk+0x15/0x30 [<ffffffff8040a17b>] icmp_send+0x4b/0x3f0 [<ffffffff8025a415>] ? trace_hardirqs_on_caller+0xd5/0x160 [<ffffffff8025a4ad>] ? trace_hardirqs_on+0xd/0x10 [<ffffffff8023a475>] ? local_bh_enable_ip+0x95/0x110 [<ffffffff804285b9>] ? _spin_unlock_bh+0x39/0x40 [<ffffffff8025a26c>] ? mark_held_locks+0x4c/0x90 [<ffffffff8025a4ad>] ? trace_hardirqs_on+0xd/0x10 [<ffffffff8025a415>] ? trace_hardirqs_on_caller+0xd5/0x160 [<ffffffff803e91b4>] ip_fragment+0x8d4/0x900 [<ffffffff803e7030>] ? ip_finish_output2+0x0/0x290 [<ffffffff803e91e0>] ? ip_finish_output+0x0/0x60 [<ffffffff803e6650>] ? dst_output+0x0/0x10 [<ffffffff803e922c>] ip_finish_output+0x4c/0x60 [<ffffffff803e92e3>] ip_output+0xa3/0xf0 [<ffffffff803e68d0>] ip_local_out+0x20/0x30 [<ffffffff803e753f>] ip_push_pending_frames+0x27f/0x400 [<ffffffff80406313>] udp_push_pending_frames+0x233/0x3d0 [<ffffffff804067d1>] udp_sendmsg+0x321/0x6f0 [<ffffffff8040d155>] inet_sendmsg+0x45/0x80 [<ffffffff803b967f>] sock_sendmsg+0xdf/0x110 [<ffffffff8024a100>] ? autoremove_wake_function+0x0/0x40 [<ffffffff80257ce5>] ? validate_chain+0x415/0x1010 [<ffffffff8027dc10>] ? __do_fault+0x140/0x450 [<ffffffff802597d0>] ? __lock_acquire+0x260/0x590 [<ffffffff803b9e55>] ? sockfd_lookup_light+0x45/0x80 [<ffffffff803ba50a>] sys_sendto+0xea/0x120 [<ffffffff80428e42>] ? _spin_unlock_irqrestore+0x42/0x80 [<ffffffff803134bc>] ? __up_read+0x4c/0xb0 [<ffffffff8024e0c6>] ? up_read+0x26/0x30 [<ffffffff8020b8bb>] system_call_fastpath+0x16/0x1b icmp6_sk() is similar. Signed-off-by: Denis V. Lunev <den@openvz.org> Signed-off-by: David S. Miller <davem@davemloft.net>
2008-08-23 18:43:33 +07:00
struct sock *sk;
sk = icmpv6_sk(net);
if (unlikely(!spin_trylock(&sk->sk_lock.slock))) {
/* This can happen if the output path (f.e. SIT or
* ip6ip6 tunnel) signals dst_link_failure() for an
* outgoing ICMP6 packet.
*/
icmp: icmp_sk() should not use smp_processor_id() in preemptible code Pass namespace into icmp_xmit_lock, obtain socket inside and return it as a result for caller. Thanks Alexey Dobryan for this report: Steps to reproduce: CONFIG_PREEMPT=y CONFIG_DEBUG_PREEMPT=y tracepath <something> BUG: using smp_processor_id() in preemptible [00000000] code: tracepath/3205 caller is icmp_sk+0x15/0x30 Pid: 3205, comm: tracepath Not tainted 2.6.27-rc4 #1 Call Trace: [<ffffffff8031af14>] debug_smp_processor_id+0xe4/0xf0 [<ffffffff80409405>] icmp_sk+0x15/0x30 [<ffffffff8040a17b>] icmp_send+0x4b/0x3f0 [<ffffffff8025a415>] ? trace_hardirqs_on_caller+0xd5/0x160 [<ffffffff8025a4ad>] ? trace_hardirqs_on+0xd/0x10 [<ffffffff8023a475>] ? local_bh_enable_ip+0x95/0x110 [<ffffffff804285b9>] ? _spin_unlock_bh+0x39/0x40 [<ffffffff8025a26c>] ? mark_held_locks+0x4c/0x90 [<ffffffff8025a4ad>] ? trace_hardirqs_on+0xd/0x10 [<ffffffff8025a415>] ? trace_hardirqs_on_caller+0xd5/0x160 [<ffffffff803e91b4>] ip_fragment+0x8d4/0x900 [<ffffffff803e7030>] ? ip_finish_output2+0x0/0x290 [<ffffffff803e91e0>] ? ip_finish_output+0x0/0x60 [<ffffffff803e6650>] ? dst_output+0x0/0x10 [<ffffffff803e922c>] ip_finish_output+0x4c/0x60 [<ffffffff803e92e3>] ip_output+0xa3/0xf0 [<ffffffff803e68d0>] ip_local_out+0x20/0x30 [<ffffffff803e753f>] ip_push_pending_frames+0x27f/0x400 [<ffffffff80406313>] udp_push_pending_frames+0x233/0x3d0 [<ffffffff804067d1>] udp_sendmsg+0x321/0x6f0 [<ffffffff8040d155>] inet_sendmsg+0x45/0x80 [<ffffffff803b967f>] sock_sendmsg+0xdf/0x110 [<ffffffff8024a100>] ? autoremove_wake_function+0x0/0x40 [<ffffffff80257ce5>] ? validate_chain+0x415/0x1010 [<ffffffff8027dc10>] ? __do_fault+0x140/0x450 [<ffffffff802597d0>] ? __lock_acquire+0x260/0x590 [<ffffffff803b9e55>] ? sockfd_lookup_light+0x45/0x80 [<ffffffff803ba50a>] sys_sendto+0xea/0x120 [<ffffffff80428e42>] ? _spin_unlock_irqrestore+0x42/0x80 [<ffffffff803134bc>] ? __up_read+0x4c/0xb0 [<ffffffff8024e0c6>] ? up_read+0x26/0x30 [<ffffffff8020b8bb>] system_call_fastpath+0x16/0x1b icmp6_sk() is similar. Signed-off-by: Denis V. Lunev <den@openvz.org> Signed-off-by: David S. Miller <davem@davemloft.net>
2008-08-23 18:43:33 +07:00
return NULL;
}
icmp: icmp_sk() should not use smp_processor_id() in preemptible code Pass namespace into icmp_xmit_lock, obtain socket inside and return it as a result for caller. Thanks Alexey Dobryan for this report: Steps to reproduce: CONFIG_PREEMPT=y CONFIG_DEBUG_PREEMPT=y tracepath <something> BUG: using smp_processor_id() in preemptible [00000000] code: tracepath/3205 caller is icmp_sk+0x15/0x30 Pid: 3205, comm: tracepath Not tainted 2.6.27-rc4 #1 Call Trace: [<ffffffff8031af14>] debug_smp_processor_id+0xe4/0xf0 [<ffffffff80409405>] icmp_sk+0x15/0x30 [<ffffffff8040a17b>] icmp_send+0x4b/0x3f0 [<ffffffff8025a415>] ? trace_hardirqs_on_caller+0xd5/0x160 [<ffffffff8025a4ad>] ? trace_hardirqs_on+0xd/0x10 [<ffffffff8023a475>] ? local_bh_enable_ip+0x95/0x110 [<ffffffff804285b9>] ? _spin_unlock_bh+0x39/0x40 [<ffffffff8025a26c>] ? mark_held_locks+0x4c/0x90 [<ffffffff8025a4ad>] ? trace_hardirqs_on+0xd/0x10 [<ffffffff8025a415>] ? trace_hardirqs_on_caller+0xd5/0x160 [<ffffffff803e91b4>] ip_fragment+0x8d4/0x900 [<ffffffff803e7030>] ? ip_finish_output2+0x0/0x290 [<ffffffff803e91e0>] ? ip_finish_output+0x0/0x60 [<ffffffff803e6650>] ? dst_output+0x0/0x10 [<ffffffff803e922c>] ip_finish_output+0x4c/0x60 [<ffffffff803e92e3>] ip_output+0xa3/0xf0 [<ffffffff803e68d0>] ip_local_out+0x20/0x30 [<ffffffff803e753f>] ip_push_pending_frames+0x27f/0x400 [<ffffffff80406313>] udp_push_pending_frames+0x233/0x3d0 [<ffffffff804067d1>] udp_sendmsg+0x321/0x6f0 [<ffffffff8040d155>] inet_sendmsg+0x45/0x80 [<ffffffff803b967f>] sock_sendmsg+0xdf/0x110 [<ffffffff8024a100>] ? autoremove_wake_function+0x0/0x40 [<ffffffff80257ce5>] ? validate_chain+0x415/0x1010 [<ffffffff8027dc10>] ? __do_fault+0x140/0x450 [<ffffffff802597d0>] ? __lock_acquire+0x260/0x590 [<ffffffff803b9e55>] ? sockfd_lookup_light+0x45/0x80 [<ffffffff803ba50a>] sys_sendto+0xea/0x120 [<ffffffff80428e42>] ? _spin_unlock_irqrestore+0x42/0x80 [<ffffffff803134bc>] ? __up_read+0x4c/0xb0 [<ffffffff8024e0c6>] ? up_read+0x26/0x30 [<ffffffff8020b8bb>] system_call_fastpath+0x16/0x1b icmp6_sk() is similar. Signed-off-by: Denis V. Lunev <den@openvz.org> Signed-off-by: David S. Miller <davem@davemloft.net>
2008-08-23 18:43:33 +07:00
return sk;
}
static __inline__ void icmpv6_xmit_unlock(struct sock *sk)
{
spin_unlock(&sk->sk_lock.slock);
}
/*
* Figure out, may we reply to this packet with icmp error.
*
* We do not reply, if:
* - it was icmp error message.
* - it is truncated, so that it is known, that protocol is ICMPV6
* (i.e. in the middle of some exthdr)
*
* --ANK (980726)
*/
static bool is_ineligible(const struct sk_buff *skb)
{
int ptr = (u8 *)(ipv6_hdr(skb) + 1) - skb->data;
int len = skb->len - ptr;
__u8 nexthdr = ipv6_hdr(skb)->nexthdr;
__be16 frag_off;
if (len < 0)
return true;
ptr = ipv6_skip_exthdr(skb, ptr, &nexthdr, &frag_off);
if (ptr < 0)
return false;
if (nexthdr == IPPROTO_ICMPV6) {
u8 _type, *tp;
tp = skb_header_pointer(skb,
ptr+offsetof(struct icmp6hdr, icmp6_type),
sizeof(_type), &_type);
if (!tp || !(*tp & ICMPV6_INFOMSG_MASK))
return true;
}
return false;
}
static bool icmpv6_mask_allow(int type)
{
/* Informational messages are not limited. */
if (type & ICMPV6_INFOMSG_MASK)
return true;
/* Do not limit pmtu discovery, it would break it. */
if (type == ICMPV6_PKT_TOOBIG)
return true;
return false;
}
static bool icmpv6_global_allow(int type)
{
if (icmpv6_mask_allow(type))
return true;
if (icmp_global_allow())
return true;
return false;
}
/*
* Check the ICMP output rate limit
*/
static bool icmpv6_xrlim_allow(struct sock *sk, u8 type,
struct flowi6 *fl6)
{
struct net *net = sock_net(sk);
struct dst_entry *dst;
bool res = false;
if (icmpv6_mask_allow(type))
return true;
/*
* Look up the output route.
* XXX: perhaps the expire for routing entries cloned by
* this lookup should be more aggressive (not longer than timeout).
*/
dst = ip6_route_output(net, sk, fl6);
if (dst->error) {
IP6_INC_STATS(net, ip6_dst_idev(dst),
IPSTATS_MIB_OUTNOROUTES);
} else if (dst->dev && (dst->dev->flags&IFF_LOOPBACK)) {
res = true;
} else {
struct rt6_info *rt = (struct rt6_info *)dst;
int tmo = net->ipv6.sysctl.icmpv6_time;
struct inet_peer *peer;
/* Give more bandwidth to wider prefixes. */
if (rt->rt6i_dst.plen < 128)
tmo >>= ((128 - rt->rt6i_dst.plen)>>5);
peer = inet_getpeer_v6(net->ipv6.peers, &fl6->daddr, 1);
res = inet_peer_xrlim_allow(peer, tmo);
if (peer)
inet_putpeer(peer);
}
dst_release(dst);
return res;
}
/*
* an inline helper for the "simple" if statement below
* checks if parameter problem report is caused by an
* unrecognized IPv6 option that has the Option Type
* highest-order two bits set to 10
*/
static bool opt_unrec(struct sk_buff *skb, __u32 offset)
{
u8 _optval, *op;
offset += skb_network_offset(skb);
op = skb_header_pointer(skb, offset, sizeof(_optval), &_optval);
if (!op)
return true;
return (*op & 0xC0) == 0x80;
}
void icmpv6_push_pending_frames(struct sock *sk, struct flowi6 *fl6,
struct icmp6hdr *thdr, int len)
{
struct sk_buff *skb;
struct icmp6hdr *icmp6h;
skb = skb_peek(&sk->sk_write_queue);
if (!skb)
return;
icmp6h = icmp6_hdr(skb);
memcpy(icmp6h, thdr, sizeof(struct icmp6hdr));
icmp6h->icmp6_cksum = 0;
if (skb_queue_len(&sk->sk_write_queue) == 1) {
skb->csum = csum_partial(icmp6h,
sizeof(struct icmp6hdr), skb->csum);
icmp6h->icmp6_cksum = csum_ipv6_magic(&fl6->saddr,
&fl6->daddr,
len, fl6->flowi6_proto,
skb->csum);
} else {
__wsum tmp_csum = 0;
skb_queue_walk(&sk->sk_write_queue, skb) {
tmp_csum = csum_add(tmp_csum, skb->csum);
}
tmp_csum = csum_partial(icmp6h,
sizeof(struct icmp6hdr), tmp_csum);
icmp6h->icmp6_cksum = csum_ipv6_magic(&fl6->saddr,
&fl6->daddr,
len, fl6->flowi6_proto,
tmp_csum);
}
ip6_push_pending_frames(sk);
}
struct icmpv6_msg {
struct sk_buff *skb;
int offset;
uint8_t type;
};
static int icmpv6_getfrag(void *from, char *to, int offset, int len, int odd, struct sk_buff *skb)
{
struct icmpv6_msg *msg = (struct icmpv6_msg *) from;
struct sk_buff *org_skb = msg->skb;
__wsum csum = 0;
csum = skb_copy_and_csum_bits(org_skb, msg->offset + offset,
to, len, csum);
skb->csum = csum_block_add(skb->csum, csum, odd);
if (!(msg->type & ICMPV6_INFOMSG_MASK))
nf_ct_attach(skb, org_skb);
return 0;
}
#if IS_ENABLED(CONFIG_IPV6_MIP6)
static void mip6_addr_swap(struct sk_buff *skb)
{
struct ipv6hdr *iph = ipv6_hdr(skb);
struct inet6_skb_parm *opt = IP6CB(skb);
struct ipv6_destopt_hao *hao;
struct in6_addr tmp;
int off;
if (opt->dsthao) {
off = ipv6_find_tlv(skb, opt->dsthao, IPV6_TLV_HAO);
if (likely(off >= 0)) {
hao = (struct ipv6_destopt_hao *)
(skb_network_header(skb) + off);
tmp = iph->saddr;
iph->saddr = hao->addr;
hao->addr = tmp;
}
}
}
#else
static inline void mip6_addr_swap(struct sk_buff *skb) {}
#endif
static struct dst_entry *icmpv6_route_lookup(struct net *net,
struct sk_buff *skb,
struct sock *sk,
struct flowi6 *fl6)
{
struct dst_entry *dst, *dst2;
struct flowi6 fl2;
int err;
err = ip6_dst_lookup(net, sk, &dst, fl6);
if (err)
return ERR_PTR(err);
/*
* We won't send icmp if the destination is known
* anycast.
*/
if (ipv6_anycast_destination(dst, &fl6->daddr)) {
net_dbg_ratelimited("icmp6_send: acast source\n");
dst_release(dst);
return ERR_PTR(-EINVAL);
}
/* No need to clone since we're just using its address. */
dst2 = dst;
dst = xfrm_lookup(net, dst, flowi6_to_flowi(fl6), sk, 0);
if (!IS_ERR(dst)) {
if (dst != dst2)
return dst;
} else {
if (PTR_ERR(dst) == -EPERM)
dst = NULL;
else
return dst;
}
err = xfrm_decode_session_reverse(skb, flowi6_to_flowi(&fl2), AF_INET6);
if (err)
goto relookup_failed;
err = ip6_dst_lookup(net, sk, &dst2, &fl2);
if (err)
goto relookup_failed;
dst2 = xfrm_lookup(net, dst2, flowi6_to_flowi(&fl2), sk, XFRM_LOOKUP_ICMP);
if (!IS_ERR(dst2)) {
dst_release(dst);
dst = dst2;
} else {
err = PTR_ERR(dst2);
if (err == -EPERM) {
dst_release(dst);
return dst2;
} else
goto relookup_failed;
}
relookup_failed:
if (dst)
return dst;
return ERR_PTR(err);
}
static int icmp6_iif(const struct sk_buff *skb)
{
int iif = skb->dev->ifindex;
/* for local traffic to local address, skb dev is the loopback
* device. Check if there is a dst attached to the skb and if so
* get the real device index. Same is needed for replies to a link
* local address on a device enslaved to an L3 master device
*/
if (unlikely(iif == LOOPBACK_IFINDEX || netif_is_l3_master(skb->dev))) {
const struct rt6_info *rt6 = skb_rt6_info(skb);
if (rt6)
iif = rt6->rt6i_idev->dev->ifindex;
}
return iif;
}
/*
* Send an ICMP message in response to a packet in error
*/
static void icmp6_send(struct sk_buff *skb, u8 type, u8 code, __u32 info,
const struct in6_addr *force_saddr)
{
struct net *net = dev_net(skb->dev);
struct inet6_dev *idev = NULL;
struct ipv6hdr *hdr = ipv6_hdr(skb);
struct sock *sk;
struct ipv6_pinfo *np;
const struct in6_addr *saddr = NULL;
struct dst_entry *dst;
struct icmp6hdr tmp_hdr;
struct flowi6 fl6;
struct icmpv6_msg msg;
struct ipcm6_cookie ipc6;
int iif = 0;
int addr_type = 0;
int len;
u32 mark = IP6_REPLY_MARK(net, skb->mark);
if ((u8 *)hdr < skb->head ||
(skb_network_header(skb) + sizeof(*hdr)) > skb_tail_pointer(skb))
return;
/*
* Make sure we respect the rules
* i.e. RFC 1885 2.4(e)
* Rule (e.1) is enforced by not using icmp6_send
* in any code that processes icmp errors.
*/
addr_type = ipv6_addr_type(&hdr->daddr);
if (ipv6_chk_addr(net, &hdr->daddr, skb->dev, 0) ||
ipv6_chk_acast_addr_src(net, skb->dev, &hdr->daddr))
saddr = &hdr->daddr;
/*
* Dest addr check
*/
if (addr_type & IPV6_ADDR_MULTICAST || skb->pkt_type != PACKET_HOST) {
if (type != ICMPV6_PKT_TOOBIG &&
!(type == ICMPV6_PARAMPROB &&
code == ICMPV6_UNK_OPTION &&
(opt_unrec(skb, info))))
return;
saddr = NULL;
}
addr_type = ipv6_addr_type(&hdr->saddr);
/*
* Source addr check
*/
if (__ipv6_addr_needs_scope_id(addr_type)) {
iif = icmp6_iif(skb);
} else {
net: handle no dst on skb in icmp6_send Andrey reported the following while fuzzing the kernel with syzkaller: kasan: CONFIG_KASAN_INLINE enabled kasan: GPF could be caused by NULL-ptr deref or user memory access general protection fault: 0000 [#1] SMP KASAN Modules linked in: CPU: 0 PID: 3859 Comm: a.out Not tainted 4.9.0-rc6+ #429 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS Bochs 01/01/2011 task: ffff8800666d4200 task.stack: ffff880067348000 RIP: 0010:[<ffffffff833617ec>] [<ffffffff833617ec>] icmp6_send+0x5fc/0x1e30 net/ipv6/icmp.c:451 RSP: 0018:ffff88006734f2c0 EFLAGS: 00010206 RAX: ffff8800666d4200 RBX: 0000000000000000 RCX: 0000000000000000 RDX: 0000000000000000 RSI: dffffc0000000000 RDI: 0000000000000018 RBP: ffff88006734f630 R08: ffff880064138418 R09: 0000000000000003 R10: dffffc0000000000 R11: 0000000000000005 R12: 0000000000000000 R13: ffffffff84e7e200 R14: ffff880064138484 R15: ffff8800641383c0 FS: 00007fb3887a07c0(0000) GS:ffff88006cc00000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 0000000020000000 CR3: 000000006b040000 CR4: 00000000000006f0 Stack: ffff8800666d4200 ffff8800666d49f8 ffff8800666d4200 ffffffff84c02460 ffff8800666d4a1a 1ffff1000ccdaa2f ffff88006734f498 0000000000000046 ffff88006734f440 ffffffff832f4269 ffff880064ba7456 0000000000000000 Call Trace: [<ffffffff83364ddc>] icmpv6_param_prob+0x2c/0x40 net/ipv6/icmp.c:557 [< inline >] ip6_tlvopt_unknown net/ipv6/exthdrs.c:88 [<ffffffff83394405>] ip6_parse_tlv+0x555/0x670 net/ipv6/exthdrs.c:157 [<ffffffff8339a759>] ipv6_parse_hopopts+0x199/0x460 net/ipv6/exthdrs.c:663 [<ffffffff832ee773>] ipv6_rcv+0xfa3/0x1dc0 net/ipv6/ip6_input.c:191 ... icmp6_send / icmpv6_send is invoked for both rx and tx paths. In both cases the dst->dev should be preferred for determining the L3 domain if the dst has been set on the skb. Fallback to the skb->dev if it has not. This covers the case reported here where icmp6_send is invoked on Rx before the route lookup. Fixes: 5d41ce29e ("net: icmp6_send should use dst dev to determine L3 domain") Reported-by: Andrey Konovalov <andreyknvl@google.com> Signed-off-by: David Ahern <dsa@cumulusnetworks.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-11-28 09:52:53 +07:00
dst = skb_dst(skb);
iif = l3mdev_master_ifindex(dst ? dst->dev : skb->dev);
}
/*
* Must not send error if the source does not uniquely
* identify a single node (RFC2463 Section 2.4).
* We check unspecified / multicast addresses here,
* and anycast addresses will be checked later.
*/
if ((addr_type == IPV6_ADDR_ANY) || (addr_type & IPV6_ADDR_MULTICAST)) {
net_dbg_ratelimited("icmp6_send: addr_any/mcast source [%pI6c > %pI6c]\n",
&hdr->saddr, &hdr->daddr);
return;
}
/*
* Never answer to a ICMP packet.
*/
if (is_ineligible(skb)) {
net_dbg_ratelimited("icmp6_send: no reply to icmp error [%pI6c > %pI6c]\n",
&hdr->saddr, &hdr->daddr);
return;
}
/* Needed by both icmp_global_allow and icmpv6_xmit_lock */
local_bh_disable();
/* Check global sysctl_icmp_msgs_per_sec ratelimit */
if (!(skb->dev->flags&IFF_LOOPBACK) && !icmpv6_global_allow(type))
goto out_bh_enable;
mip6_addr_swap(skb);
memset(&fl6, 0, sizeof(fl6));
fl6.flowi6_proto = IPPROTO_ICMPV6;
fl6.daddr = hdr->saddr;
if (force_saddr)
saddr = force_saddr;
if (saddr)
fl6.saddr = *saddr;
fl6.flowi6_mark = mark;
fl6.flowi6_oif = iif;
fl6.fl6_icmp_type = type;
fl6.fl6_icmp_code = code;
fl6.flowi6_uid = sock_net_uid(net, NULL);
fl6.mp_hash = rt6_multipath_hash(net, &fl6, skb, NULL);
security_skb_classify_flow(skb, flowi6_to_flowi(&fl6));
icmp: icmp_sk() should not use smp_processor_id() in preemptible code Pass namespace into icmp_xmit_lock, obtain socket inside and return it as a result for caller. Thanks Alexey Dobryan for this report: Steps to reproduce: CONFIG_PREEMPT=y CONFIG_DEBUG_PREEMPT=y tracepath <something> BUG: using smp_processor_id() in preemptible [00000000] code: tracepath/3205 caller is icmp_sk+0x15/0x30 Pid: 3205, comm: tracepath Not tainted 2.6.27-rc4 #1 Call Trace: [<ffffffff8031af14>] debug_smp_processor_id+0xe4/0xf0 [<ffffffff80409405>] icmp_sk+0x15/0x30 [<ffffffff8040a17b>] icmp_send+0x4b/0x3f0 [<ffffffff8025a415>] ? trace_hardirqs_on_caller+0xd5/0x160 [<ffffffff8025a4ad>] ? trace_hardirqs_on+0xd/0x10 [<ffffffff8023a475>] ? local_bh_enable_ip+0x95/0x110 [<ffffffff804285b9>] ? _spin_unlock_bh+0x39/0x40 [<ffffffff8025a26c>] ? mark_held_locks+0x4c/0x90 [<ffffffff8025a4ad>] ? trace_hardirqs_on+0xd/0x10 [<ffffffff8025a415>] ? trace_hardirqs_on_caller+0xd5/0x160 [<ffffffff803e91b4>] ip_fragment+0x8d4/0x900 [<ffffffff803e7030>] ? ip_finish_output2+0x0/0x290 [<ffffffff803e91e0>] ? ip_finish_output+0x0/0x60 [<ffffffff803e6650>] ? dst_output+0x0/0x10 [<ffffffff803e922c>] ip_finish_output+0x4c/0x60 [<ffffffff803e92e3>] ip_output+0xa3/0xf0 [<ffffffff803e68d0>] ip_local_out+0x20/0x30 [<ffffffff803e753f>] ip_push_pending_frames+0x27f/0x400 [<ffffffff80406313>] udp_push_pending_frames+0x233/0x3d0 [<ffffffff804067d1>] udp_sendmsg+0x321/0x6f0 [<ffffffff8040d155>] inet_sendmsg+0x45/0x80 [<ffffffff803b967f>] sock_sendmsg+0xdf/0x110 [<ffffffff8024a100>] ? autoremove_wake_function+0x0/0x40 [<ffffffff80257ce5>] ? validate_chain+0x415/0x1010 [<ffffffff8027dc10>] ? __do_fault+0x140/0x450 [<ffffffff802597d0>] ? __lock_acquire+0x260/0x590 [<ffffffff803b9e55>] ? sockfd_lookup_light+0x45/0x80 [<ffffffff803ba50a>] sys_sendto+0xea/0x120 [<ffffffff80428e42>] ? _spin_unlock_irqrestore+0x42/0x80 [<ffffffff803134bc>] ? __up_read+0x4c/0xb0 [<ffffffff8024e0c6>] ? up_read+0x26/0x30 [<ffffffff8020b8bb>] system_call_fastpath+0x16/0x1b icmp6_sk() is similar. Signed-off-by: Denis V. Lunev <den@openvz.org> Signed-off-by: David S. Miller <davem@davemloft.net>
2008-08-23 18:43:33 +07:00
sk = icmpv6_xmit_lock(net);
if (!sk)
goto out_bh_enable;
sk->sk_mark = mark;
icmp: icmp_sk() should not use smp_processor_id() in preemptible code Pass namespace into icmp_xmit_lock, obtain socket inside and return it as a result for caller. Thanks Alexey Dobryan for this report: Steps to reproduce: CONFIG_PREEMPT=y CONFIG_DEBUG_PREEMPT=y tracepath <something> BUG: using smp_processor_id() in preemptible [00000000] code: tracepath/3205 caller is icmp_sk+0x15/0x30 Pid: 3205, comm: tracepath Not tainted 2.6.27-rc4 #1 Call Trace: [<ffffffff8031af14>] debug_smp_processor_id+0xe4/0xf0 [<ffffffff80409405>] icmp_sk+0x15/0x30 [<ffffffff8040a17b>] icmp_send+0x4b/0x3f0 [<ffffffff8025a415>] ? trace_hardirqs_on_caller+0xd5/0x160 [<ffffffff8025a4ad>] ? trace_hardirqs_on+0xd/0x10 [<ffffffff8023a475>] ? local_bh_enable_ip+0x95/0x110 [<ffffffff804285b9>] ? _spin_unlock_bh+0x39/0x40 [<ffffffff8025a26c>] ? mark_held_locks+0x4c/0x90 [<ffffffff8025a4ad>] ? trace_hardirqs_on+0xd/0x10 [<ffffffff8025a415>] ? trace_hardirqs_on_caller+0xd5/0x160 [<ffffffff803e91b4>] ip_fragment+0x8d4/0x900 [<ffffffff803e7030>] ? ip_finish_output2+0x0/0x290 [<ffffffff803e91e0>] ? ip_finish_output+0x0/0x60 [<ffffffff803e6650>] ? dst_output+0x0/0x10 [<ffffffff803e922c>] ip_finish_output+0x4c/0x60 [<ffffffff803e92e3>] ip_output+0xa3/0xf0 [<ffffffff803e68d0>] ip_local_out+0x20/0x30 [<ffffffff803e753f>] ip_push_pending_frames+0x27f/0x400 [<ffffffff80406313>] udp_push_pending_frames+0x233/0x3d0 [<ffffffff804067d1>] udp_sendmsg+0x321/0x6f0 [<ffffffff8040d155>] inet_sendmsg+0x45/0x80 [<ffffffff803b967f>] sock_sendmsg+0xdf/0x110 [<ffffffff8024a100>] ? autoremove_wake_function+0x0/0x40 [<ffffffff80257ce5>] ? validate_chain+0x415/0x1010 [<ffffffff8027dc10>] ? __do_fault+0x140/0x450 [<ffffffff802597d0>] ? __lock_acquire+0x260/0x590 [<ffffffff803b9e55>] ? sockfd_lookup_light+0x45/0x80 [<ffffffff803ba50a>] sys_sendto+0xea/0x120 [<ffffffff80428e42>] ? _spin_unlock_irqrestore+0x42/0x80 [<ffffffff803134bc>] ? __up_read+0x4c/0xb0 [<ffffffff8024e0c6>] ? up_read+0x26/0x30 [<ffffffff8020b8bb>] system_call_fastpath+0x16/0x1b icmp6_sk() is similar. Signed-off-by: Denis V. Lunev <den@openvz.org> Signed-off-by: David S. Miller <davem@davemloft.net>
2008-08-23 18:43:33 +07:00
np = inet6_sk(sk);
if (!icmpv6_xrlim_allow(sk, type, &fl6))
goto out;
tmp_hdr.icmp6_type = type;
tmp_hdr.icmp6_code = code;
tmp_hdr.icmp6_cksum = 0;
tmp_hdr.icmp6_pointer = htonl(info);
if (!fl6.flowi6_oif && ipv6_addr_is_multicast(&fl6.daddr))
fl6.flowi6_oif = np->mcast_oif;
else if (!fl6.flowi6_oif)
fl6.flowi6_oif = np->ucast_oif;
ipcm6_init_sk(&ipc6, np);
fl6.flowlabel = ip6_make_flowinfo(ipc6.tclass, fl6.flowlabel);
dst = icmpv6_route_lookup(net, skb, sk, &fl6);
if (IS_ERR(dst))
goto out;
ipc6.hlimit = ip6_sk_dst_hoplimit(np, &fl6, dst);
msg.skb = skb;
msg.offset = skb_network_offset(skb);
msg.type = type;
len = skb->len - msg.offset;
len = min_t(unsigned int, len, IPV6_MIN_MTU - sizeof(struct ipv6hdr) - sizeof(struct icmp6hdr));
if (len < 0) {
net_dbg_ratelimited("icmp: len problem [%pI6c > %pI6c]\n",
&hdr->saddr, &hdr->daddr);
goto out_dst_release;
}
rcu_read_lock();
idev = __in6_dev_get(skb->dev);
if (ip6_append_data(sk, icmpv6_getfrag, &msg,
len + sizeof(struct icmp6hdr),
sizeof(struct icmp6hdr),
&ipc6, &fl6, (struct rt6_info *)dst,
MSG_DONTWAIT)) {
ICMP6_INC_STATS(net, idev, ICMP6_MIB_OUTERRORS);
ip6_flush_pending_frames(sk);
} else {
icmpv6_push_pending_frames(sk, &fl6, &tmp_hdr,
len + sizeof(struct icmp6hdr));
}
rcu_read_unlock();
out_dst_release:
dst_release(dst);
out:
icmpv6_xmit_unlock(sk);
out_bh_enable:
local_bh_enable();
}
/* Slightly more convenient version of icmp6_send.
*/
void icmpv6_param_prob(struct sk_buff *skb, u8 code, int pos)
{
icmp6_send(skb, ICMPV6_PARAMPROB, code, pos, NULL);
kfree_skb(skb);
}
/* Generate icmpv6 with type/code ICMPV6_DEST_UNREACH/ICMPV6_ADDR_UNREACH
* if sufficient data bytes are available
* @nhs is the size of the tunnel header(s) :
* Either an IPv4 header for SIT encap
* an IPv4 header + GRE header for GRE encap
*/
int ip6_err_gen_icmpv6_unreach(struct sk_buff *skb, int nhs, int type,
unsigned int data_len)
{
struct in6_addr temp_saddr;
struct rt6_info *rt;
struct sk_buff *skb2;
u32 info = 0;
if (!pskb_may_pull(skb, nhs + sizeof(struct ipv6hdr) + 8))
return 1;
/* RFC 4884 (partial) support for ICMP extensions */
if (data_len < 128 || (data_len & 7) || skb->len < data_len)
data_len = 0;
skb2 = data_len ? skb_copy(skb, GFP_ATOMIC) : skb_clone(skb, GFP_ATOMIC);
if (!skb2)
return 1;
skb_dst_drop(skb2);
skb_pull(skb2, nhs);
skb_reset_network_header(skb2);
rt = rt6_lookup(dev_net(skb->dev), &ipv6_hdr(skb2)->saddr, NULL, 0,
skb, 0);
if (rt && rt->dst.dev)
skb2->dev = rt->dst.dev;
ipv6_addr_set_v4mapped(ip_hdr(skb)->saddr, &temp_saddr);
if (data_len) {
/* RFC 4884 (partial) support :
* insert 0 padding at the end, before the extensions
*/
__skb_push(skb2, nhs);
skb_reset_network_header(skb2);
memmove(skb2->data, skb2->data + nhs, data_len - nhs);
memset(skb2->data + data_len - nhs, 0, nhs);
/* RFC 4884 4.5 : Length is measured in 64-bit words,
* and stored in reserved[0]
*/
info = (data_len/8) << 24;
}
if (type == ICMP_TIME_EXCEEDED)
icmp6_send(skb2, ICMPV6_TIME_EXCEED, ICMPV6_EXC_HOPLIMIT,
info, &temp_saddr);
else
icmp6_send(skb2, ICMPV6_DEST_UNREACH, ICMPV6_ADDR_UNREACH,
info, &temp_saddr);
if (rt)
ip6_rt_put(rt);
kfree_skb(skb2);
return 0;
}
EXPORT_SYMBOL(ip6_err_gen_icmpv6_unreach);
static void icmpv6_echo_reply(struct sk_buff *skb)
{
struct net *net = dev_net(skb->dev);
struct sock *sk;
struct inet6_dev *idev;
struct ipv6_pinfo *np;
const struct in6_addr *saddr = NULL;
struct icmp6hdr *icmph = icmp6_hdr(skb);
struct icmp6hdr tmp_hdr;
struct flowi6 fl6;
struct icmpv6_msg msg;
struct dst_entry *dst;
struct ipcm6_cookie ipc6;
u32 mark = IP6_REPLY_MARK(net, skb->mark);
saddr = &ipv6_hdr(skb)->daddr;
if (!ipv6_unicast_destination(skb) &&
!(net->ipv6.sysctl.anycast_src_echo_reply &&
ipv6_anycast_destination(skb_dst(skb), saddr)))
saddr = NULL;
memcpy(&tmp_hdr, icmph, sizeof(tmp_hdr));
tmp_hdr.icmp6_type = ICMPV6_ECHO_REPLY;
memset(&fl6, 0, sizeof(fl6));
fl6.flowi6_proto = IPPROTO_ICMPV6;
fl6.daddr = ipv6_hdr(skb)->saddr;
if (saddr)
fl6.saddr = *saddr;
fl6.flowi6_oif = icmp6_iif(skb);
fl6.fl6_icmp_type = ICMPV6_ECHO_REPLY;
fl6.flowi6_mark = mark;
fl6.flowi6_uid = sock_net_uid(net, NULL);
security_skb_classify_flow(skb, flowi6_to_flowi(&fl6));
local_bh_disable();
icmp: icmp_sk() should not use smp_processor_id() in preemptible code Pass namespace into icmp_xmit_lock, obtain socket inside and return it as a result for caller. Thanks Alexey Dobryan for this report: Steps to reproduce: CONFIG_PREEMPT=y CONFIG_DEBUG_PREEMPT=y tracepath <something> BUG: using smp_processor_id() in preemptible [00000000] code: tracepath/3205 caller is icmp_sk+0x15/0x30 Pid: 3205, comm: tracepath Not tainted 2.6.27-rc4 #1 Call Trace: [<ffffffff8031af14>] debug_smp_processor_id+0xe4/0xf0 [<ffffffff80409405>] icmp_sk+0x15/0x30 [<ffffffff8040a17b>] icmp_send+0x4b/0x3f0 [<ffffffff8025a415>] ? trace_hardirqs_on_caller+0xd5/0x160 [<ffffffff8025a4ad>] ? trace_hardirqs_on+0xd/0x10 [<ffffffff8023a475>] ? local_bh_enable_ip+0x95/0x110 [<ffffffff804285b9>] ? _spin_unlock_bh+0x39/0x40 [<ffffffff8025a26c>] ? mark_held_locks+0x4c/0x90 [<ffffffff8025a4ad>] ? trace_hardirqs_on+0xd/0x10 [<ffffffff8025a415>] ? trace_hardirqs_on_caller+0xd5/0x160 [<ffffffff803e91b4>] ip_fragment+0x8d4/0x900 [<ffffffff803e7030>] ? ip_finish_output2+0x0/0x290 [<ffffffff803e91e0>] ? ip_finish_output+0x0/0x60 [<ffffffff803e6650>] ? dst_output+0x0/0x10 [<ffffffff803e922c>] ip_finish_output+0x4c/0x60 [<ffffffff803e92e3>] ip_output+0xa3/0xf0 [<ffffffff803e68d0>] ip_local_out+0x20/0x30 [<ffffffff803e753f>] ip_push_pending_frames+0x27f/0x400 [<ffffffff80406313>] udp_push_pending_frames+0x233/0x3d0 [<ffffffff804067d1>] udp_sendmsg+0x321/0x6f0 [<ffffffff8040d155>] inet_sendmsg+0x45/0x80 [<ffffffff803b967f>] sock_sendmsg+0xdf/0x110 [<ffffffff8024a100>] ? autoremove_wake_function+0x0/0x40 [<ffffffff80257ce5>] ? validate_chain+0x415/0x1010 [<ffffffff8027dc10>] ? __do_fault+0x140/0x450 [<ffffffff802597d0>] ? __lock_acquire+0x260/0x590 [<ffffffff803b9e55>] ? sockfd_lookup_light+0x45/0x80 [<ffffffff803ba50a>] sys_sendto+0xea/0x120 [<ffffffff80428e42>] ? _spin_unlock_irqrestore+0x42/0x80 [<ffffffff803134bc>] ? __up_read+0x4c/0xb0 [<ffffffff8024e0c6>] ? up_read+0x26/0x30 [<ffffffff8020b8bb>] system_call_fastpath+0x16/0x1b icmp6_sk() is similar. Signed-off-by: Denis V. Lunev <den@openvz.org> Signed-off-by: David S. Miller <davem@davemloft.net>
2008-08-23 18:43:33 +07:00
sk = icmpv6_xmit_lock(net);
if (!sk)
goto out_bh_enable;
sk->sk_mark = mark;
icmp: icmp_sk() should not use smp_processor_id() in preemptible code Pass namespace into icmp_xmit_lock, obtain socket inside and return it as a result for caller. Thanks Alexey Dobryan for this report: Steps to reproduce: CONFIG_PREEMPT=y CONFIG_DEBUG_PREEMPT=y tracepath <something> BUG: using smp_processor_id() in preemptible [00000000] code: tracepath/3205 caller is icmp_sk+0x15/0x30 Pid: 3205, comm: tracepath Not tainted 2.6.27-rc4 #1 Call Trace: [<ffffffff8031af14>] debug_smp_processor_id+0xe4/0xf0 [<ffffffff80409405>] icmp_sk+0x15/0x30 [<ffffffff8040a17b>] icmp_send+0x4b/0x3f0 [<ffffffff8025a415>] ? trace_hardirqs_on_caller+0xd5/0x160 [<ffffffff8025a4ad>] ? trace_hardirqs_on+0xd/0x10 [<ffffffff8023a475>] ? local_bh_enable_ip+0x95/0x110 [<ffffffff804285b9>] ? _spin_unlock_bh+0x39/0x40 [<ffffffff8025a26c>] ? mark_held_locks+0x4c/0x90 [<ffffffff8025a4ad>] ? trace_hardirqs_on+0xd/0x10 [<ffffffff8025a415>] ? trace_hardirqs_on_caller+0xd5/0x160 [<ffffffff803e91b4>] ip_fragment+0x8d4/0x900 [<ffffffff803e7030>] ? ip_finish_output2+0x0/0x290 [<ffffffff803e91e0>] ? ip_finish_output+0x0/0x60 [<ffffffff803e6650>] ? dst_output+0x0/0x10 [<ffffffff803e922c>] ip_finish_output+0x4c/0x60 [<ffffffff803e92e3>] ip_output+0xa3/0xf0 [<ffffffff803e68d0>] ip_local_out+0x20/0x30 [<ffffffff803e753f>] ip_push_pending_frames+0x27f/0x400 [<ffffffff80406313>] udp_push_pending_frames+0x233/0x3d0 [<ffffffff804067d1>] udp_sendmsg+0x321/0x6f0 [<ffffffff8040d155>] inet_sendmsg+0x45/0x80 [<ffffffff803b967f>] sock_sendmsg+0xdf/0x110 [<ffffffff8024a100>] ? autoremove_wake_function+0x0/0x40 [<ffffffff80257ce5>] ? validate_chain+0x415/0x1010 [<ffffffff8027dc10>] ? __do_fault+0x140/0x450 [<ffffffff802597d0>] ? __lock_acquire+0x260/0x590 [<ffffffff803b9e55>] ? sockfd_lookup_light+0x45/0x80 [<ffffffff803ba50a>] sys_sendto+0xea/0x120 [<ffffffff80428e42>] ? _spin_unlock_irqrestore+0x42/0x80 [<ffffffff803134bc>] ? __up_read+0x4c/0xb0 [<ffffffff8024e0c6>] ? up_read+0x26/0x30 [<ffffffff8020b8bb>] system_call_fastpath+0x16/0x1b icmp6_sk() is similar. Signed-off-by: Denis V. Lunev <den@openvz.org> Signed-off-by: David S. Miller <davem@davemloft.net>
2008-08-23 18:43:33 +07:00
np = inet6_sk(sk);
if (!fl6.flowi6_oif && ipv6_addr_is_multicast(&fl6.daddr))
fl6.flowi6_oif = np->mcast_oif;
else if (!fl6.flowi6_oif)
fl6.flowi6_oif = np->ucast_oif;
if (ip6_dst_lookup(net, sk, &dst, &fl6))
goto out;
dst = xfrm_lookup(net, dst, flowi6_to_flowi(&fl6), sk, 0);
if (IS_ERR(dst))
goto out;
idev = __in6_dev_get(skb->dev);
msg.skb = skb;
msg.offset = 0;
msg.type = ICMPV6_ECHO_REPLY;
ipcm6_init_sk(&ipc6, np);
ipc6.hlimit = ip6_sk_dst_hoplimit(np, &fl6, dst);
ipc6.tclass = ipv6_get_dsfield(ipv6_hdr(skb));
if (ip6_append_data(sk, icmpv6_getfrag, &msg,
skb->len + sizeof(struct icmp6hdr),
sizeof(struct icmp6hdr), &ipc6, &fl6,
(struct rt6_info *)dst, MSG_DONTWAIT)) {
__ICMP6_INC_STATS(net, idev, ICMP6_MIB_OUTERRORS);
ip6_flush_pending_frames(sk);
} else {
icmpv6_push_pending_frames(sk, &fl6, &tmp_hdr,
skb->len + sizeof(struct icmp6hdr));
}
dst_release(dst);
out:
icmpv6_xmit_unlock(sk);
out_bh_enable:
local_bh_enable();
}
void icmpv6_notify(struct sk_buff *skb, u8 type, u8 code, __be32 info)
{
const struct inet6_protocol *ipprot;
int inner_offset;
__be16 frag_off;
u8 nexthdr;
struct net *net = dev_net(skb->dev);
if (!pskb_may_pull(skb, sizeof(struct ipv6hdr)))
goto out;
nexthdr = ((struct ipv6hdr *)skb->data)->nexthdr;
if (ipv6_ext_hdr(nexthdr)) {
/* now skip over extension headers */
inner_offset = ipv6_skip_exthdr(skb, sizeof(struct ipv6hdr),
&nexthdr, &frag_off);
if (inner_offset < 0)
goto out;
} else {
inner_offset = sizeof(struct ipv6hdr);
}
/* Checkin header including 8 bytes of inner protocol header. */
if (!pskb_may_pull(skb, inner_offset+8))
goto out;
/* BUGGG_FUTURE: we should try to parse exthdrs in this packet.
Without this we will not able f.e. to make source routed
pmtu discovery.
Corresponding argument (opt) to notifiers is already added.
--ANK (980726)
*/
ipprot = rcu_dereference(inet6_protos[nexthdr]);
if (ipprot && ipprot->err_handler)
ipprot->err_handler(skb, NULL, type, code, inner_offset, info);
raw6_icmp_error(skb, nexthdr, type, code, inner_offset, info);
return;
out:
__ICMP6_INC_STATS(net, __in6_dev_get(skb->dev), ICMP6_MIB_INERRORS);
}
/*
* Handle icmp messages
*/
static int icmpv6_rcv(struct sk_buff *skb)
{
struct net *net = dev_net(skb->dev);
struct net_device *dev = skb->dev;
struct inet6_dev *idev = __in6_dev_get(dev);
const struct in6_addr *saddr, *daddr;
struct icmp6hdr *hdr;
u8 type;
bool success = false;
if (!xfrm6_policy_check(NULL, XFRM_POLICY_IN, skb)) {
struct sec_path *sp = skb_sec_path(skb);
int nh;
if (!(sp && sp->xvec[sp->len - 1]->props.flags &
XFRM_STATE_ICMP))
goto drop_no_count;
if (!pskb_may_pull(skb, sizeof(*hdr) + sizeof(struct ipv6hdr)))
goto drop_no_count;
nh = skb_network_offset(skb);
skb_set_network_header(skb, sizeof(*hdr));
if (!xfrm6_policy_check_reverse(NULL, XFRM_POLICY_IN, skb))
goto drop_no_count;
skb_set_network_header(skb, nh);
}
__ICMP6_INC_STATS(dev_net(dev), idev, ICMP6_MIB_INMSGS);
saddr = &ipv6_hdr(skb)->saddr;
daddr = &ipv6_hdr(skb)->daddr;
if (skb_checksum_validate(skb, IPPROTO_ICMPV6, ip6_compute_pseudo)) {
net_dbg_ratelimited("ICMPv6 checksum failed [%pI6c > %pI6c]\n",
saddr, daddr);
goto csum_error;
}
if (!pskb_pull(skb, sizeof(*hdr)))
goto discard_it;
hdr = icmp6_hdr(skb);
type = hdr->icmp6_type;
ICMP6MSGIN_INC_STATS(dev_net(dev), idev, type);
switch (type) {
case ICMPV6_ECHO_REQUEST:
if (!net->ipv6.sysctl.icmpv6_echo_ignore_all)
icmpv6_echo_reply(skb);
break;
case ICMPV6_ECHO_REPLY:
success = ping_rcv(skb);
break;
case ICMPV6_PKT_TOOBIG:
/* BUGGG_FUTURE: if packet contains rthdr, we cannot update
standard destination cache. Seems, only "advanced"
destination cache will allow to solve this problem
--ANK (980726)
*/
if (!pskb_may_pull(skb, sizeof(struct ipv6hdr)))
goto discard_it;
hdr = icmp6_hdr(skb);
/* to notify */
/* fall through */
case ICMPV6_DEST_UNREACH:
case ICMPV6_TIME_EXCEED:
case ICMPV6_PARAMPROB:
icmpv6_notify(skb, type, hdr->icmp6_code, hdr->icmp6_mtu);
break;
case NDISC_ROUTER_SOLICITATION:
case NDISC_ROUTER_ADVERTISEMENT:
case NDISC_NEIGHBOUR_SOLICITATION:
case NDISC_NEIGHBOUR_ADVERTISEMENT:
case NDISC_REDIRECT:
ndisc_rcv(skb);
break;
case ICMPV6_MGM_QUERY:
igmp6_event_query(skb);
break;
case ICMPV6_MGM_REPORT:
igmp6_event_report(skb);
break;
case ICMPV6_MGM_REDUCTION:
case ICMPV6_NI_QUERY:
case ICMPV6_NI_REPLY:
case ICMPV6_MLD2_REPORT:
case ICMPV6_DHAAD_REQUEST:
case ICMPV6_DHAAD_REPLY:
case ICMPV6_MOBILE_PREFIX_SOL:
case ICMPV6_MOBILE_PREFIX_ADV:
break;
default:
/* informational */
if (type & ICMPV6_INFOMSG_MASK)
break;
net_dbg_ratelimited("icmpv6: msg of unknown type [%pI6c > %pI6c]\n",
saddr, daddr);
/*
* error of unknown type.
* must pass to upper level
*/
icmpv6_notify(skb, type, hdr->icmp6_code, hdr->icmp6_mtu);
}
/* until the v6 path can be better sorted assume failure and
* preserve the status quo behaviour for the rest of the paths to here
*/
if (success)
consume_skb(skb);
else
kfree_skb(skb);
return 0;
csum_error:
__ICMP6_INC_STATS(dev_net(dev), idev, ICMP6_MIB_CSUMERRORS);
discard_it:
__ICMP6_INC_STATS(dev_net(dev), idev, ICMP6_MIB_INERRORS);
drop_no_count:
kfree_skb(skb);
return 0;
}
void icmpv6_flow_init(struct sock *sk, struct flowi6 *fl6,
u8 type,
const struct in6_addr *saddr,
const struct in6_addr *daddr,
int oif)
{
memset(fl6, 0, sizeof(*fl6));
fl6->saddr = *saddr;
fl6->daddr = *daddr;
fl6->flowi6_proto = IPPROTO_ICMPV6;
fl6->fl6_icmp_type = type;
fl6->fl6_icmp_code = 0;
fl6->flowi6_oif = oif;
security_sk_classify_flow(sk, flowi6_to_flowi(fl6));
}
static int __net_init icmpv6_sk_init(struct net *net)
{
struct sock *sk;
int err, i, j;
net->ipv6.icmp_sk =
treewide: kzalloc() -> kcalloc() The kzalloc() function has a 2-factor argument form, kcalloc(). This patch replaces cases of: kzalloc(a * b, gfp) with: kcalloc(a * b, gfp) as well as handling cases of: kzalloc(a * b * c, gfp) with: kzalloc(array3_size(a, b, c), gfp) as it's slightly less ugly than: kzalloc_array(array_size(a, b), c, gfp) This does, however, attempt to ignore constant size factors like: kzalloc(4 * 1024, gfp) though any constants defined via macros get caught up in the conversion. Any factors with a sizeof() of "unsigned char", "char", and "u8" were dropped, since they're redundant. The Coccinelle script used for this was: // Fix redundant parens around sizeof(). @@ type TYPE; expression THING, E; @@ ( kzalloc( - (sizeof(TYPE)) * E + sizeof(TYPE) * E , ...) | kzalloc( - (sizeof(THING)) * E + sizeof(THING) * E , ...) ) // Drop single-byte sizes and redundant parens. @@ expression COUNT; typedef u8; typedef __u8; @@ ( kzalloc( - sizeof(u8) * (COUNT) + COUNT , ...) | kzalloc( - sizeof(__u8) * (COUNT) + COUNT , ...) | kzalloc( - sizeof(char) * (COUNT) + COUNT , ...) | kzalloc( - sizeof(unsigned char) * (COUNT) + COUNT , ...) | kzalloc( - sizeof(u8) * COUNT + COUNT , ...) | kzalloc( - sizeof(__u8) * COUNT + COUNT , ...) | kzalloc( - sizeof(char) * COUNT + COUNT , ...) | kzalloc( - sizeof(unsigned char) * COUNT + COUNT , ...) ) // 2-factor product with sizeof(type/expression) and identifier or constant. @@ type TYPE; expression THING; identifier COUNT_ID; constant COUNT_CONST; @@ ( - kzalloc + kcalloc ( - sizeof(TYPE) * (COUNT_ID) + COUNT_ID, sizeof(TYPE) , ...) | - kzalloc + kcalloc ( - sizeof(TYPE) * COUNT_ID + COUNT_ID, sizeof(TYPE) , ...) | - kzalloc + kcalloc ( - sizeof(TYPE) * (COUNT_CONST) + COUNT_CONST, sizeof(TYPE) , ...) | - kzalloc + kcalloc ( - sizeof(TYPE) * COUNT_CONST + COUNT_CONST, sizeof(TYPE) , ...) | - kzalloc + kcalloc ( - sizeof(THING) * (COUNT_ID) + COUNT_ID, sizeof(THING) , ...) | - kzalloc + kcalloc ( - sizeof(THING) * COUNT_ID + COUNT_ID, sizeof(THING) , ...) | - kzalloc + kcalloc ( - sizeof(THING) * (COUNT_CONST) + COUNT_CONST, sizeof(THING) , ...) | - kzalloc + kcalloc ( - sizeof(THING) * COUNT_CONST + COUNT_CONST, sizeof(THING) , ...) ) // 2-factor product, only identifiers. @@ identifier SIZE, COUNT; @@ - kzalloc + kcalloc ( - SIZE * COUNT + COUNT, SIZE , ...) // 3-factor product with 1 sizeof(type) or sizeof(expression), with // redundant parens removed. @@ expression THING; identifier STRIDE, COUNT; type TYPE; @@ ( kzalloc( - sizeof(TYPE) * (COUNT) * (STRIDE) + array3_size(COUNT, STRIDE, sizeof(TYPE)) , ...) | kzalloc( - sizeof(TYPE) * (COUNT) * STRIDE + array3_size(COUNT, STRIDE, sizeof(TYPE)) , ...) | kzalloc( - sizeof(TYPE) * COUNT * (STRIDE) + array3_size(COUNT, STRIDE, sizeof(TYPE)) , ...) | kzalloc( - sizeof(TYPE) * COUNT * STRIDE + array3_size(COUNT, STRIDE, sizeof(TYPE)) , ...) | kzalloc( - sizeof(THING) * (COUNT) * (STRIDE) + array3_size(COUNT, STRIDE, sizeof(THING)) , ...) | kzalloc( - sizeof(THING) * (COUNT) * STRIDE + array3_size(COUNT, STRIDE, sizeof(THING)) , ...) | kzalloc( - sizeof(THING) * COUNT * (STRIDE) + array3_size(COUNT, STRIDE, sizeof(THING)) , ...) | kzalloc( - sizeof(THING) * COUNT * STRIDE + array3_size(COUNT, STRIDE, sizeof(THING)) , ...) ) // 3-factor product with 2 sizeof(variable), with redundant parens removed. @@ expression THING1, THING2; identifier COUNT; type TYPE1, TYPE2; @@ ( kzalloc( - sizeof(TYPE1) * sizeof(TYPE2) * COUNT + array3_size(COUNT, sizeof(TYPE1), sizeof(TYPE2)) , ...) | kzalloc( - sizeof(TYPE1) * sizeof(THING2) * (COUNT) + array3_size(COUNT, sizeof(TYPE1), sizeof(TYPE2)) , ...) | kzalloc( - sizeof(THING1) * sizeof(THING2) * COUNT + array3_size(COUNT, sizeof(THING1), sizeof(THING2)) , ...) | kzalloc( - sizeof(THING1) * sizeof(THING2) * (COUNT) + array3_size(COUNT, sizeof(THING1), sizeof(THING2)) , ...) | kzalloc( - sizeof(TYPE1) * sizeof(THING2) * COUNT + array3_size(COUNT, sizeof(TYPE1), sizeof(THING2)) , ...) | kzalloc( - sizeof(TYPE1) * sizeof(THING2) * (COUNT) + array3_size(COUNT, sizeof(TYPE1), sizeof(THING2)) , ...) ) // 3-factor product, only identifiers, with redundant parens removed. @@ identifier STRIDE, SIZE, COUNT; @@ ( kzalloc( - (COUNT) * STRIDE * SIZE + array3_size(COUNT, STRIDE, SIZE) , ...) | kzalloc( - COUNT * (STRIDE) * SIZE + array3_size(COUNT, STRIDE, SIZE) , ...) | kzalloc( - COUNT * STRIDE * (SIZE) + array3_size(COUNT, STRIDE, SIZE) , ...) | kzalloc( - (COUNT) * (STRIDE) * SIZE + array3_size(COUNT, STRIDE, SIZE) , ...) | kzalloc( - COUNT * (STRIDE) * (SIZE) + array3_size(COUNT, STRIDE, SIZE) , ...) | kzalloc( - (COUNT) * STRIDE * (SIZE) + array3_size(COUNT, STRIDE, SIZE) , ...) | kzalloc( - (COUNT) * (STRIDE) * (SIZE) + array3_size(COUNT, STRIDE, SIZE) , ...) | kzalloc( - COUNT * STRIDE * SIZE + array3_size(COUNT, STRIDE, SIZE) , ...) ) // Any remaining multi-factor products, first at least 3-factor products, // when they're not all constants... @@ expression E1, E2, E3; constant C1, C2, C3; @@ ( kzalloc(C1 * C2 * C3, ...) | kzalloc( - (E1) * E2 * E3 + array3_size(E1, E2, E3) , ...) | kzalloc( - (E1) * (E2) * E3 + array3_size(E1, E2, E3) , ...) | kzalloc( - (E1) * (E2) * (E3) + array3_size(E1, E2, E3) , ...) | kzalloc( - E1 * E2 * E3 + array3_size(E1, E2, E3) , ...) ) // And then all remaining 2 factors products when they're not all constants, // keeping sizeof() as the second factor argument. @@ expression THING, E1, E2; type TYPE; constant C1, C2, C3; @@ ( kzalloc(sizeof(THING) * C2, ...) | kzalloc(sizeof(TYPE) * C2, ...) | kzalloc(C1 * C2 * C3, ...) | kzalloc(C1 * C2, ...) | - kzalloc + kcalloc ( - sizeof(TYPE) * (E2) + E2, sizeof(TYPE) , ...) | - kzalloc + kcalloc ( - sizeof(TYPE) * E2 + E2, sizeof(TYPE) , ...) | - kzalloc + kcalloc ( - sizeof(THING) * (E2) + E2, sizeof(THING) , ...) | - kzalloc + kcalloc ( - sizeof(THING) * E2 + E2, sizeof(THING) , ...) | - kzalloc + kcalloc ( - (E1) * E2 + E1, E2 , ...) | - kzalloc + kcalloc ( - (E1) * (E2) + E1, E2 , ...) | - kzalloc + kcalloc ( - E1 * E2 + E1, E2 , ...) ) Signed-off-by: Kees Cook <keescook@chromium.org>
2018-06-13 04:03:40 +07:00
kcalloc(nr_cpu_ids, sizeof(struct sock *), GFP_KERNEL);
if (!net->ipv6.icmp_sk)
return -ENOMEM;
for_each_possible_cpu(i) {
err = inet_ctl_sock_create(&sk, PF_INET6,
SOCK_RAW, IPPROTO_ICMPV6, net);
if (err < 0) {
pr_err("Failed to initialize the ICMP6 control socket (err %d)\n",
err);
goto fail;
}
net->ipv6.icmp_sk[i] = sk;
/* Enough space for 2 64K ICMP packets, including
* sk_buff struct overhead.
*/
sk->sk_sndbuf = 2 * SKB_TRUESIZE(64 * 1024);
}
return 0;
fail:
for (j = 0; j < i; j++)
inet_ctl_sock_destroy(net->ipv6.icmp_sk[j]);
kfree(net->ipv6.icmp_sk);
return err;
}
static void __net_exit icmpv6_sk_exit(struct net *net)
{
int i;
for_each_possible_cpu(i) {
inet_ctl_sock_destroy(net->ipv6.icmp_sk[i]);
}
kfree(net->ipv6.icmp_sk);
}
static struct pernet_operations icmpv6_sk_ops = {
.init = icmpv6_sk_init,
.exit = icmpv6_sk_exit,
};
int __init icmpv6_init(void)
{
int err;
err = register_pernet_subsys(&icmpv6_sk_ops);
if (err < 0)
return err;
err = -EAGAIN;
if (inet6_add_protocol(&icmpv6_protocol, IPPROTO_ICMPV6) < 0)
goto fail;
err = inet6_register_icmp_sender(icmp6_send);
if (err)
goto sender_reg_err;
return 0;
sender_reg_err:
inet6_del_protocol(&icmpv6_protocol, IPPROTO_ICMPV6);
fail:
pr_err("Failed to register ICMP6 protocol\n");
unregister_pernet_subsys(&icmpv6_sk_ops);
return err;
}
void icmpv6_cleanup(void)
{
inet6_unregister_icmp_sender(icmp6_send);
unregister_pernet_subsys(&icmpv6_sk_ops);
inet6_del_protocol(&icmpv6_protocol, IPPROTO_ICMPV6);
}
static const struct icmp6_err {
int err;
int fatal;
} tab_unreach[] = {
{ /* NOROUTE */
.err = ENETUNREACH,
.fatal = 0,
},
{ /* ADM_PROHIBITED */
.err = EACCES,
.fatal = 1,
},
{ /* Was NOT_NEIGHBOUR, now reserved */
.err = EHOSTUNREACH,
.fatal = 0,
},
{ /* ADDR_UNREACH */
.err = EHOSTUNREACH,
.fatal = 0,
},
{ /* PORT_UNREACH */
.err = ECONNREFUSED,
.fatal = 1,
},
{ /* POLICY_FAIL */
.err = EACCES,
.fatal = 1,
},
{ /* REJECT_ROUTE */
.err = EACCES,
.fatal = 1,
},
};
int icmpv6_err_convert(u8 type, u8 code, int *err)
{
int fatal = 0;
*err = EPROTO;
switch (type) {
case ICMPV6_DEST_UNREACH:
fatal = 1;
if (code < ARRAY_SIZE(tab_unreach)) {
*err = tab_unreach[code].err;
fatal = tab_unreach[code].fatal;
}
break;
case ICMPV6_PKT_TOOBIG:
*err = EMSGSIZE;
break;
case ICMPV6_PARAMPROB:
*err = EPROTO;
fatal = 1;
break;
case ICMPV6_TIME_EXCEED:
*err = EHOSTUNREACH;
break;
}
return fatal;
}
EXPORT_SYMBOL(icmpv6_err_convert);
#ifdef CONFIG_SYSCTL
static struct ctl_table ipv6_icmp_table_template[] = {
{
.procname = "ratelimit",
.data = &init_net.ipv6.sysctl.icmpv6_time,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec_ms_jiffies,
},
{
.procname = "echo_ignore_all",
.data = &init_net.ipv6.sysctl.icmpv6_echo_ignore_all,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec,
},
{ },
};
struct ctl_table * __net_init ipv6_icmp_sysctl_init(struct net *net)
{
struct ctl_table *table;
table = kmemdup(ipv6_icmp_table_template,
sizeof(ipv6_icmp_table_template),
GFP_KERNEL);
if (table) {
table[0].data = &net->ipv6.sysctl.icmpv6_time;
table[1].data = &net->ipv6.sysctl.icmpv6_echo_ignore_all;
}
return table;
}
#endif