linux/net/ipv6/route.c

3253 lines
77 KiB
C
Raw Normal View History

/*
* Linux INET6 implementation
* FIB front-end.
*
* Authors:
* Pedro Roque <roque@di.fc.ul.pt>
*
* 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:
*
* YOSHIFUJI Hideaki @USAGI
* reworked default router selection.
* - respect outgoing interface
* - select from (probably) reachable routers (i.e.
* routers in REACHABLE, STALE, DELAY or PROBE states).
* - always select the same router if it is (probably)
* reachable. otherwise, round-robin the list.
* Ville Nuorvala
* Fixed routing subtrees.
*/
#define pr_fmt(fmt) "IPv6: " fmt
#include <linux/capability.h>
#include <linux/errno.h>
#include <linux/export.h>
#include <linux/types.h>
#include <linux/times.h>
#include <linux/socket.h>
#include <linux/sockios.h>
#include <linux/net.h>
#include <linux/route.h>
#include <linux/netdevice.h>
#include <linux/in6.h>
#include <linux/mroute6.h>
#include <linux/init.h>
#include <linux/if_arp.h>
#include <linux/proc_fs.h>
#include <linux/seq_file.h>
#include <linux/nsproxy.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 08:04:11 +00:00
#include <linux/slab.h>
#include <net/net_namespace.h>
#include <net/snmp.h>
#include <net/ipv6.h>
#include <net/ip6_fib.h>
#include <net/ip6_route.h>
#include <net/ndisc.h>
#include <net/addrconf.h>
#include <net/tcp.h>
#include <linux/rtnetlink.h>
#include <net/dst.h>
#include <net/xfrm.h>
#include <net/netevent.h>
#include <net/netlink.h>
#include <net/nexthop.h>
#include <asm/uaccess.h>
#ifdef CONFIG_SYSCTL
#include <linux/sysctl.h>
#endif
static struct rt6_info *ip6_rt_copy(struct rt6_info *ort,
const struct in6_addr *dest);
static struct dst_entry *ip6_dst_check(struct dst_entry *dst, u32 cookie);
static unsigned int ip6_default_advmss(const struct dst_entry *dst);
static unsigned int ip6_mtu(const struct dst_entry *dst);
static struct dst_entry *ip6_negative_advice(struct dst_entry *);
static void ip6_dst_destroy(struct dst_entry *);
static void ip6_dst_ifdown(struct dst_entry *,
struct net_device *dev, int how);
static int ip6_dst_gc(struct dst_ops *ops);
static int ip6_pkt_discard(struct sk_buff *skb);
static int ip6_pkt_discard_out(struct sk_buff *skb);
static void ip6_link_failure(struct sk_buff *skb);
static void ip6_rt_update_pmtu(struct dst_entry *dst, struct sock *sk,
struct sk_buff *skb, u32 mtu);
static void rt6_do_redirect(struct dst_entry *dst, struct sock *sk,
struct sk_buff *skb);
#ifdef CONFIG_IPV6_ROUTE_INFO
static struct rt6_info *rt6_add_route_info(struct net *net,
const struct in6_addr *prefix, int prefixlen,
const struct in6_addr *gwaddr, int ifindex,
unsigned int pref);
static struct rt6_info *rt6_get_route_info(struct net *net,
const struct in6_addr *prefix, int prefixlen,
const struct in6_addr *gwaddr, int ifindex);
#endif
static u32 *ipv6_cow_metrics(struct dst_entry *dst, unsigned long old)
{
struct rt6_info *rt = (struct rt6_info *) dst;
struct inet_peer *peer;
u32 *p = NULL;
if (!(rt->dst.flags & DST_HOST))
return NULL;
peer = rt6_get_peer_create(rt);
if (peer) {
u32 *old_p = __DST_METRICS_PTR(old);
unsigned long prev, new;
p = peer->metrics;
if (inet_metrics_new(peer))
memcpy(p, old_p, sizeof(u32) * RTAX_MAX);
new = (unsigned long) p;
prev = cmpxchg(&dst->_metrics, old, new);
if (prev != old) {
p = __DST_METRICS_PTR(prev);
if (prev & DST_METRICS_READ_ONLY)
p = NULL;
}
}
return p;
}
static inline const void *choose_neigh_daddr(struct rt6_info *rt,
struct sk_buff *skb,
const void *daddr)
{
struct in6_addr *p = &rt->rt6i_gateway;
if (!ipv6_addr_any(p))
return (const void *) p;
else if (skb)
return &ipv6_hdr(skb)->daddr;
return daddr;
}
static struct neighbour *ip6_neigh_lookup(const struct dst_entry *dst,
struct sk_buff *skb,
const void *daddr)
{
struct rt6_info *rt = (struct rt6_info *) dst;
struct neighbour *n;
daddr = choose_neigh_daddr(rt, skb, daddr);
n = __ipv6_neigh_lookup(&nd_tbl, dst->dev, daddr);
if (n)
return n;
return neigh_create(&nd_tbl, daddr, dst->dev);
}
static int rt6_bind_neighbour(struct rt6_info *rt, struct net_device *dev)
{
struct neighbour *n = __ipv6_neigh_lookup(&nd_tbl, dev, &rt->rt6i_gateway);
if (!n) {
n = neigh_create(&nd_tbl, &rt->rt6i_gateway, dev);
if (IS_ERR(n))
return PTR_ERR(n);
}
rt->n = n;
return 0;
}
static struct dst_ops ip6_dst_ops_template = {
.family = AF_INET6,
.protocol = cpu_to_be16(ETH_P_IPV6),
.gc = ip6_dst_gc,
.gc_thresh = 1024,
.check = ip6_dst_check,
.default_advmss = ip6_default_advmss,
.mtu = ip6_mtu,
.cow_metrics = ipv6_cow_metrics,
.destroy = ip6_dst_destroy,
.ifdown = ip6_dst_ifdown,
.negative_advice = ip6_negative_advice,
.link_failure = ip6_link_failure,
.update_pmtu = ip6_rt_update_pmtu,
.redirect = rt6_do_redirect,
.local_out = __ip6_local_out,
.neigh_lookup = ip6_neigh_lookup,
};
static unsigned int ip6_blackhole_mtu(const struct dst_entry *dst)
{
unsigned int mtu = dst_metric_raw(dst, RTAX_MTU);
return mtu ? : dst->dev->mtu;
}
static void ip6_rt_blackhole_update_pmtu(struct dst_entry *dst, struct sock *sk,
struct sk_buff *skb, u32 mtu)
{
}
static void ip6_rt_blackhole_redirect(struct dst_entry *dst, struct sock *sk,
struct sk_buff *skb)
{
}
net: provide cow_metrics() methods to blackhole dst_ops Since commit 62fa8a846d7d (net: Implement read-only protection and COW'ing of metrics.) the kernel throws an oops. [ 101.620985] BUG: unable to handle kernel NULL pointer dereference at (null) [ 101.621050] IP: [< (null)>] (null) [ 101.621084] PGD 6e53c067 PUD 3dd6a067 PMD 0 [ 101.621122] Oops: 0010 [#1] SMP [ 101.621153] last sysfs file: /sys/devices/virtual/ppp/ppp/uevent [ 101.621192] CPU 2 [ 101.621206] Modules linked in: l2tp_ppp pppox ppp_generic slhc l2tp_netlink l2tp_core deflate zlib_deflate twofish_x86_64 twofish_common des_generic cbc ecb sha1_generic hmac af_key iptable_filter snd_pcm_oss snd_mixer_oss snd_seq snd_seq_device loop snd_hda_codec_hdmi snd_hda_codec_realtek snd_hda_intel snd_hda_codec snd_pcm snd_timer snd i2c_i801 iTCO_wdt psmouse soundcore snd_page_alloc evdev uhci_hcd ehci_hcd thermal [ 101.621552] [ 101.621567] Pid: 5129, comm: openl2tpd Not tainted 2.6.39-rc4-Quad #3 Gigabyte Technology Co., Ltd. G33-DS3R/G33-DS3R [ 101.621637] RIP: 0010:[<0000000000000000>] [< (null)>] (null) [ 101.621684] RSP: 0018:ffff88003ddeba60 EFLAGS: 00010202 [ 101.621716] RAX: ffff88003ddb5600 RBX: ffff88003ddb5600 RCX: 0000000000000020 [ 101.621758] RDX: ffffffff81a69a00 RSI: ffffffff81b7ee61 RDI: ffff88003ddb5600 [ 101.621800] RBP: ffff8800537cd900 R08: 0000000000000000 R09: ffff88003ddb5600 [ 101.621840] R10: 0000000000000005 R11: 0000000000014b38 R12: ffff88003ddb5600 [ 101.621881] R13: ffffffff81b7e480 R14: ffffffff81b7e8b8 R15: ffff88003ddebad8 [ 101.621924] FS: 00007f06e4182700(0000) GS:ffff88007fd00000(0000) knlGS:0000000000000000 [ 101.621971] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 101.622005] CR2: 0000000000000000 CR3: 0000000045274000 CR4: 00000000000006e0 [ 101.622046] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 [ 101.622087] DR3: 0000000000000000 DR6: 00000000ffff0ff0 DR7: 0000000000000400 [ 101.622129] Process openl2tpd (pid: 5129, threadinfo ffff88003ddea000, task ffff88003de9a280) [ 101.622177] Stack: [ 101.622191] ffffffff81447efa ffff88007d3ded80 ffff88003de9a280 ffff88007d3ded80 [ 101.622245] 0000000000000001 ffff88003ddebbb8 ffffffff8148d5a7 0000000000000212 [ 101.622299] ffff88003dcea000 ffff88003dcea188 ffffffff00000001 ffffffff81b7e480 [ 101.622353] Call Trace: [ 101.622374] [<ffffffff81447efa>] ? ipv4_blackhole_route+0x1ba/0x210 [ 101.622415] [<ffffffff8148d5a7>] ? xfrm_lookup+0x417/0x510 [ 101.622450] [<ffffffff8127672a>] ? extract_buf+0x9a/0x140 [ 101.622485] [<ffffffff8144c6a0>] ? __ip_flush_pending_frames+0x70/0x70 [ 101.622526] [<ffffffff8146fbbf>] ? udp_sendmsg+0x62f/0x810 [ 101.622562] [<ffffffff813f98a6>] ? sock_sendmsg+0x116/0x130 [ 101.622599] [<ffffffff8109df58>] ? find_get_page+0x18/0x90 [ 101.622633] [<ffffffff8109fd6a>] ? filemap_fault+0x12a/0x4b0 [ 101.622668] [<ffffffff813fb5c4>] ? move_addr_to_kernel+0x64/0x90 [ 101.622706] [<ffffffff81405d5a>] ? verify_iovec+0x7a/0xf0 [ 101.622739] [<ffffffff813fc772>] ? sys_sendmsg+0x292/0x420 [ 101.622774] [<ffffffff810b994a>] ? handle_pte_fault+0x8a/0x7c0 [ 101.622810] [<ffffffff810b76fe>] ? __pte_alloc+0xae/0x130 [ 101.622844] [<ffffffff810ba2f8>] ? handle_mm_fault+0x138/0x380 [ 101.622880] [<ffffffff81024af9>] ? do_page_fault+0x189/0x410 [ 101.622915] [<ffffffff813fbe03>] ? sys_getsockname+0xf3/0x110 [ 101.622952] [<ffffffff81450c4d>] ? ip_setsockopt+0x4d/0xa0 [ 101.622986] [<ffffffff813f9932>] ? sockfd_lookup_light+0x22/0x90 [ 101.623024] [<ffffffff814b61fb>] ? system_call_fastpath+0x16/0x1b [ 101.623060] Code: Bad RIP value. [ 101.623090] RIP [< (null)>] (null) [ 101.623125] RSP <ffff88003ddeba60> [ 101.623146] CR2: 0000000000000000 [ 101.650871] ---[ end trace ca3856a7d8e8dad4 ]--- [ 101.651011] __sk_free: optmem leakage (160 bytes) detected. The oops happens in dst_metrics_write_ptr() include/net/dst.h:124: return dst->ops->cow_metrics(dst, p); dst->ops->cow_metrics is NULL and causes the oops. Provide cow_metrics() methods, like we did in commit 214f45c91bb (net: provide default_advmss() methods to blackhole dst_ops) Signed-off-by: Held Bernhard <berny156@gmx.de> Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2011-04-24 22:07:32 +00:00
static u32 *ip6_rt_blackhole_cow_metrics(struct dst_entry *dst,
unsigned long old)
{
return NULL;
}
static struct dst_ops ip6_dst_blackhole_ops = {
.family = AF_INET6,
.protocol = cpu_to_be16(ETH_P_IPV6),
.destroy = ip6_dst_destroy,
.check = ip6_dst_check,
.mtu = ip6_blackhole_mtu,
.default_advmss = ip6_default_advmss,
.update_pmtu = ip6_rt_blackhole_update_pmtu,
.redirect = ip6_rt_blackhole_redirect,
net: provide cow_metrics() methods to blackhole dst_ops Since commit 62fa8a846d7d (net: Implement read-only protection and COW'ing of metrics.) the kernel throws an oops. [ 101.620985] BUG: unable to handle kernel NULL pointer dereference at (null) [ 101.621050] IP: [< (null)>] (null) [ 101.621084] PGD 6e53c067 PUD 3dd6a067 PMD 0 [ 101.621122] Oops: 0010 [#1] SMP [ 101.621153] last sysfs file: /sys/devices/virtual/ppp/ppp/uevent [ 101.621192] CPU 2 [ 101.621206] Modules linked in: l2tp_ppp pppox ppp_generic slhc l2tp_netlink l2tp_core deflate zlib_deflate twofish_x86_64 twofish_common des_generic cbc ecb sha1_generic hmac af_key iptable_filter snd_pcm_oss snd_mixer_oss snd_seq snd_seq_device loop snd_hda_codec_hdmi snd_hda_codec_realtek snd_hda_intel snd_hda_codec snd_pcm snd_timer snd i2c_i801 iTCO_wdt psmouse soundcore snd_page_alloc evdev uhci_hcd ehci_hcd thermal [ 101.621552] [ 101.621567] Pid: 5129, comm: openl2tpd Not tainted 2.6.39-rc4-Quad #3 Gigabyte Technology Co., Ltd. G33-DS3R/G33-DS3R [ 101.621637] RIP: 0010:[<0000000000000000>] [< (null)>] (null) [ 101.621684] RSP: 0018:ffff88003ddeba60 EFLAGS: 00010202 [ 101.621716] RAX: ffff88003ddb5600 RBX: ffff88003ddb5600 RCX: 0000000000000020 [ 101.621758] RDX: ffffffff81a69a00 RSI: ffffffff81b7ee61 RDI: ffff88003ddb5600 [ 101.621800] RBP: ffff8800537cd900 R08: 0000000000000000 R09: ffff88003ddb5600 [ 101.621840] R10: 0000000000000005 R11: 0000000000014b38 R12: ffff88003ddb5600 [ 101.621881] R13: ffffffff81b7e480 R14: ffffffff81b7e8b8 R15: ffff88003ddebad8 [ 101.621924] FS: 00007f06e4182700(0000) GS:ffff88007fd00000(0000) knlGS:0000000000000000 [ 101.621971] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 101.622005] CR2: 0000000000000000 CR3: 0000000045274000 CR4: 00000000000006e0 [ 101.622046] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 [ 101.622087] DR3: 0000000000000000 DR6: 00000000ffff0ff0 DR7: 0000000000000400 [ 101.622129] Process openl2tpd (pid: 5129, threadinfo ffff88003ddea000, task ffff88003de9a280) [ 101.622177] Stack: [ 101.622191] ffffffff81447efa ffff88007d3ded80 ffff88003de9a280 ffff88007d3ded80 [ 101.622245] 0000000000000001 ffff88003ddebbb8 ffffffff8148d5a7 0000000000000212 [ 101.622299] ffff88003dcea000 ffff88003dcea188 ffffffff00000001 ffffffff81b7e480 [ 101.622353] Call Trace: [ 101.622374] [<ffffffff81447efa>] ? ipv4_blackhole_route+0x1ba/0x210 [ 101.622415] [<ffffffff8148d5a7>] ? xfrm_lookup+0x417/0x510 [ 101.622450] [<ffffffff8127672a>] ? extract_buf+0x9a/0x140 [ 101.622485] [<ffffffff8144c6a0>] ? __ip_flush_pending_frames+0x70/0x70 [ 101.622526] [<ffffffff8146fbbf>] ? udp_sendmsg+0x62f/0x810 [ 101.622562] [<ffffffff813f98a6>] ? sock_sendmsg+0x116/0x130 [ 101.622599] [<ffffffff8109df58>] ? find_get_page+0x18/0x90 [ 101.622633] [<ffffffff8109fd6a>] ? filemap_fault+0x12a/0x4b0 [ 101.622668] [<ffffffff813fb5c4>] ? move_addr_to_kernel+0x64/0x90 [ 101.622706] [<ffffffff81405d5a>] ? verify_iovec+0x7a/0xf0 [ 101.622739] [<ffffffff813fc772>] ? sys_sendmsg+0x292/0x420 [ 101.622774] [<ffffffff810b994a>] ? handle_pte_fault+0x8a/0x7c0 [ 101.622810] [<ffffffff810b76fe>] ? __pte_alloc+0xae/0x130 [ 101.622844] [<ffffffff810ba2f8>] ? handle_mm_fault+0x138/0x380 [ 101.622880] [<ffffffff81024af9>] ? do_page_fault+0x189/0x410 [ 101.622915] [<ffffffff813fbe03>] ? sys_getsockname+0xf3/0x110 [ 101.622952] [<ffffffff81450c4d>] ? ip_setsockopt+0x4d/0xa0 [ 101.622986] [<ffffffff813f9932>] ? sockfd_lookup_light+0x22/0x90 [ 101.623024] [<ffffffff814b61fb>] ? system_call_fastpath+0x16/0x1b [ 101.623060] Code: Bad RIP value. [ 101.623090] RIP [< (null)>] (null) [ 101.623125] RSP <ffff88003ddeba60> [ 101.623146] CR2: 0000000000000000 [ 101.650871] ---[ end trace ca3856a7d8e8dad4 ]--- [ 101.651011] __sk_free: optmem leakage (160 bytes) detected. The oops happens in dst_metrics_write_ptr() include/net/dst.h:124: return dst->ops->cow_metrics(dst, p); dst->ops->cow_metrics is NULL and causes the oops. Provide cow_metrics() methods, like we did in commit 214f45c91bb (net: provide default_advmss() methods to blackhole dst_ops) Signed-off-by: Held Bernhard <berny156@gmx.de> Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2011-04-24 22:07:32 +00:00
.cow_metrics = ip6_rt_blackhole_cow_metrics,
.neigh_lookup = ip6_neigh_lookup,
};
net: Implement read-only protection and COW'ing of metrics. Routing metrics are now copy-on-write. Initially a route entry points it's metrics at a read-only location. If a routing table entry exists, it will point there. Else it will point at the all zero metric place-holder called 'dst_default_metrics'. The writeability state of the metrics is stored in the low bits of the metrics pointer, we have two bits left to spare if we want to store more states. For the initial implementation, COW is implemented simply via kmalloc. However future enhancements will change this to place the writable metrics somewhere else, in order to increase sharing. Very likely this "somewhere else" will be the inetpeer cache. Note also that this means that metrics updates may transiently fail if we cannot COW the metrics successfully. But even by itself, this patch should decrease memory usage and increase cache locality especially for routing workloads. In those cases the read-only metric copies stay in place and never get written to. TCP workloads where metrics get updated, and those rare cases where PMTU triggers occur, will take a very slight performance hit. But that hit will be alleviated when the long-term writable metrics move to a more sharable location. Since the metrics storage went from a u32 array of RTAX_MAX entries to what is essentially a pointer, some retooling of the dst_entry layout was necessary. Most importantly, we need to preserve the alignment of the reference count so that it doesn't share cache lines with the read-mostly state, as per Eric Dumazet's alignment assertion checks. The only non-trivial bit here is the move of the 'flags' member into the writeable cacheline. This is OK since we are always accessing the flags around the same moment when we made a modification to the reference count. Signed-off-by: David S. Miller <davem@davemloft.net>
2011-01-27 04:51:05 +00:00
static const u32 ip6_template_metrics[RTAX_MAX] = {
[RTAX_HOPLIMIT - 1] = 255,
};
static const struct rt6_info ip6_null_entry_template = {
.dst = {
.__refcnt = ATOMIC_INIT(1),
.__use = 1,
.obsolete = DST_OBSOLETE_FORCE_CHK,
.error = -ENETUNREACH,
.input = ip6_pkt_discard,
.output = ip6_pkt_discard_out,
},
.rt6i_flags = (RTF_REJECT | RTF_NONEXTHOP),
.rt6i_protocol = RTPROT_KERNEL,
.rt6i_metric = ~(u32) 0,
.rt6i_ref = ATOMIC_INIT(1),
};
#ifdef CONFIG_IPV6_MULTIPLE_TABLES
static int ip6_pkt_prohibit(struct sk_buff *skb);
static int ip6_pkt_prohibit_out(struct sk_buff *skb);
static const struct rt6_info ip6_prohibit_entry_template = {
.dst = {
.__refcnt = ATOMIC_INIT(1),
.__use = 1,
.obsolete = DST_OBSOLETE_FORCE_CHK,
.error = -EACCES,
.input = ip6_pkt_prohibit,
.output = ip6_pkt_prohibit_out,
},
.rt6i_flags = (RTF_REJECT | RTF_NONEXTHOP),
.rt6i_protocol = RTPROT_KERNEL,
.rt6i_metric = ~(u32) 0,
.rt6i_ref = ATOMIC_INIT(1),
};
static const struct rt6_info ip6_blk_hole_entry_template = {
.dst = {
.__refcnt = ATOMIC_INIT(1),
.__use = 1,
.obsolete = DST_OBSOLETE_FORCE_CHK,
.error = -EINVAL,
.input = dst_discard,
.output = dst_discard,
},
.rt6i_flags = (RTF_REJECT | RTF_NONEXTHOP),
.rt6i_protocol = RTPROT_KERNEL,
.rt6i_metric = ~(u32) 0,
.rt6i_ref = ATOMIC_INIT(1),
};
#endif
/* allocate dst with ip6_dst_ops */
static inline struct rt6_info *ip6_dst_alloc(struct net *net,
struct net_device *dev,
int flags,
struct fib6_table *table)
{
struct rt6_info *rt = dst_alloc(&net->ipv6.ip6_dst_ops, dev,
0, DST_OBSOLETE_FORCE_CHK, flags);
if (rt) {
struct dst_entry *dst = &rt->dst;
memset(dst + 1, 0, sizeof(*rt) - sizeof(*dst));
rt6_init_peer(rt, table ? &table->tb6_peers : net->ipv6.peers);
rt->rt6i_genid = rt_genid(net);
INIT_LIST_HEAD(&rt->rt6i_siblings);
rt->rt6i_nsiblings = 0;
}
return rt;
}
static void ip6_dst_destroy(struct dst_entry *dst)
{
struct rt6_info *rt = (struct rt6_info *)dst;
struct inet6_dev *idev = rt->rt6i_idev;
if (rt->n)
neigh_release(rt->n);
if (!(rt->dst.flags & DST_HOST))
dst_destroy_metrics_generic(dst);
if (idev) {
rt->rt6i_idev = NULL;
in6_dev_put(idev);
}
if (!(rt->rt6i_flags & RTF_EXPIRES) && dst->from)
dst_release(dst->from);
if (rt6_has_peer(rt)) {
struct inet_peer *peer = rt6_peer_ptr(rt);
inet_putpeer(peer);
}
}
inet: Create a mechanism for upward inetpeer propagation into routes. If we didn't have a routing cache, we would not be able to properly propagate certain kinds of dynamic path attributes, for example PMTU information and redirects. The reason is that if we didn't have a routing cache, then there would be no way to lookup all of the active cached routes hanging off of sockets, tunnels, IPSEC bundles, etc. Consider the case where we created a cached route, but no inetpeer entry existed and also we were not asked to pre-COW the route metrics and therefore did not force the creation a new inetpeer entry. If we later get a PMTU message, or a redirect, and store this information in a new inetpeer entry, there is no way to teach that cached route about the newly existing inetpeer entry. The facilities implemented here handle this problem. First we create a generation ID. When we create a cached route of any kind, we remember the generation ID at the time of attachment. Any time we force-create an inetpeer entry in response to new path information, we bump that generation ID. The dst_ops->check() callback is where the knowledge of this event is propagated. If the global generation ID does not equal the one stored in the cached route, and the cached route has not attached to an inetpeer yet, we look it up and attach if one is found. Now that we've updated the cached route's information, we update the route's generation ID too. This clears the way for implementing PMTU and redirects directly in the inetpeer cache. There is absolutely no need to consult cached route information in order to maintain this information. At this point nothing bumps the inetpeer genids, that comes in the later changes which handle PMTUs and redirects using inetpeers. Signed-off-by: David S. Miller <davem@davemloft.net>
2011-02-08 04:38:06 +00:00
static atomic_t __rt6_peer_genid = ATOMIC_INIT(0);
static u32 rt6_peer_genid(void)
{
return atomic_read(&__rt6_peer_genid);
}
void rt6_bind_peer(struct rt6_info *rt, int create)
{
struct inet_peer_base *base;
struct inet_peer *peer;
base = inetpeer_base_ptr(rt->_rt6i_peer);
if (!base)
return;
peer = inet_getpeer_v6(base, &rt->rt6i_dst.addr, create);
if (peer) {
if (!rt6_set_peer(rt, peer))
inet_putpeer(peer);
else
rt->rt6i_peer_genid = rt6_peer_genid();
}
}
static void ip6_dst_ifdown(struct dst_entry *dst, struct net_device *dev,
int how)
{
struct rt6_info *rt = (struct rt6_info *)dst;
struct inet6_dev *idev = rt->rt6i_idev;
struct net_device *loopback_dev =
dev_net(dev)->loopback_dev;
if (dev != loopback_dev) {
if (idev && idev->dev == dev) {
struct inet6_dev *loopback_idev =
in6_dev_get(loopback_dev);
if (loopback_idev) {
rt->rt6i_idev = loopback_idev;
in6_dev_put(idev);
}
}
if (rt->n && rt->n->dev == dev) {
rt->n->dev = loopback_dev;
dev_hold(loopback_dev);
dev_put(dev);
}
}
}
static bool rt6_check_expired(const struct rt6_info *rt)
{
if (rt->rt6i_flags & RTF_EXPIRES) {
if (time_after(jiffies, rt->dst.expires))
return true;
} else if (rt->dst.from) {
return rt6_check_expired((struct rt6_info *) rt->dst.from);
}
return false;
}
static bool rt6_need_strict(const struct in6_addr *daddr)
{
return ipv6_addr_type(daddr) &
(IPV6_ADDR_MULTICAST | IPV6_ADDR_LINKLOCAL | IPV6_ADDR_LOOPBACK);
}
/* Multipath route selection:
* Hash based function using packet header and flowlabel.
* Adapted from fib_info_hashfn()
*/
static int rt6_info_hash_nhsfn(unsigned int candidate_count,
const struct flowi6 *fl6)
{
unsigned int val = fl6->flowi6_proto;
val ^= (__force u32)fl6->daddr.s6_addr32[0];
val ^= (__force u32)fl6->daddr.s6_addr32[1];
val ^= (__force u32)fl6->daddr.s6_addr32[2];
val ^= (__force u32)fl6->daddr.s6_addr32[3];
val ^= (__force u32)fl6->saddr.s6_addr32[0];
val ^= (__force u32)fl6->saddr.s6_addr32[1];
val ^= (__force u32)fl6->saddr.s6_addr32[2];
val ^= (__force u32)fl6->saddr.s6_addr32[3];
/* Work only if this not encapsulated */
switch (fl6->flowi6_proto) {
case IPPROTO_UDP:
case IPPROTO_TCP:
case IPPROTO_SCTP:
val ^= (__force u16)fl6->fl6_sport;
val ^= (__force u16)fl6->fl6_dport;
break;
case IPPROTO_ICMPV6:
val ^= (__force u16)fl6->fl6_icmp_type;
val ^= (__force u16)fl6->fl6_icmp_code;
break;
}
/* RFC6438 recommands to use flowlabel */
val ^= (__force u32)fl6->flowlabel;
/* Perhaps, we need to tune, this function? */
val = val ^ (val >> 7) ^ (val >> 12);
return val % candidate_count;
}
static struct rt6_info *rt6_multipath_select(struct rt6_info *match,
struct flowi6 *fl6)
{
struct rt6_info *sibling, *next_sibling;
int route_choosen;
route_choosen = rt6_info_hash_nhsfn(match->rt6i_nsiblings + 1, fl6);
/* Don't change the route, if route_choosen == 0
* (siblings does not include ourself)
*/
if (route_choosen)
list_for_each_entry_safe(sibling, next_sibling,
&match->rt6i_siblings, rt6i_siblings) {
route_choosen--;
if (route_choosen == 0) {
match = sibling;
break;
}
}
return match;
}
/*
* Route lookup. Any table->tb6_lock is implied.
*/
static inline struct rt6_info *rt6_device_match(struct net *net,
struct rt6_info *rt,
const struct in6_addr *saddr,
int oif,
int flags)
{
struct rt6_info *local = NULL;
struct rt6_info *sprt;
if (!oif && ipv6_addr_any(saddr))
goto out;
for (sprt = rt; sprt; sprt = sprt->dst.rt6_next) {
struct net_device *dev = sprt->dst.dev;
if (oif) {
if (dev->ifindex == oif)
return sprt;
if (dev->flags & IFF_LOOPBACK) {
if (!sprt->rt6i_idev ||
sprt->rt6i_idev->dev->ifindex != oif) {
if (flags & RT6_LOOKUP_F_IFACE && oif)
continue;
if (local && (!oif ||
local->rt6i_idev->dev->ifindex == oif))
continue;
}
local = sprt;
}
} else {
if (ipv6_chk_addr(net, saddr, dev,
flags & RT6_LOOKUP_F_IFACE))
return sprt;
}
}
if (oif) {
if (local)
return local;
if (flags & RT6_LOOKUP_F_IFACE)
return net->ipv6.ip6_null_entry;
}
out:
return rt;
}
#ifdef CONFIG_IPV6_ROUTER_PREF
static void rt6_probe(struct rt6_info *rt)
{
struct neighbour *neigh;
/*
* Okay, this does not seem to be appropriate
* for now, however, we need to check if it
* is really so; aka Router Reachability Probing.
*
* Router Reachability Probe MUST be rate-limited
* to no more than one per minute.
*/
neigh = rt ? rt->n : NULL;
if (!neigh || (neigh->nud_state & NUD_VALID))
return;
read_lock_bh(&neigh->lock);
if (!(neigh->nud_state & NUD_VALID) &&
time_after(jiffies, neigh->updated + rt->rt6i_idev->cnf.rtr_probe_interval)) {
struct in6_addr mcaddr;
struct in6_addr *target;
neigh->updated = jiffies;
read_unlock_bh(&neigh->lock);
target = (struct in6_addr *)&neigh->primary_key;
addrconf_addr_solict_mult(target, &mcaddr);
ndisc_send_ns(rt->dst.dev, NULL, target, &mcaddr, NULL);
} else {
read_unlock_bh(&neigh->lock);
}
}
#else
static inline void rt6_probe(struct rt6_info *rt)
{
}
#endif
/*
* Default Router Selection (RFC 2461 6.3.6)
*/
static inline int rt6_check_dev(struct rt6_info *rt, int oif)
{
struct net_device *dev = rt->dst.dev;
if (!oif || dev->ifindex == oif)
return 2;
if ((dev->flags & IFF_LOOPBACK) &&
rt->rt6i_idev && rt->rt6i_idev->dev->ifindex == oif)
return 1;
return 0;
}
static inline int rt6_check_neigh(struct rt6_info *rt)
{
struct neighbour *neigh;
int m;
neigh = rt->n;
if (rt->rt6i_flags & RTF_NONEXTHOP ||
!(rt->rt6i_flags & RTF_GATEWAY))
m = 1;
else if (neigh) {
read_lock_bh(&neigh->lock);
if (neigh->nud_state & NUD_VALID)
m = 2;
#ifdef CONFIG_IPV6_ROUTER_PREF
else if (neigh->nud_state & NUD_FAILED)
m = 0;
#endif
else
m = 1;
read_unlock_bh(&neigh->lock);
} else
m = 0;
return m;
}
static int rt6_score_route(struct rt6_info *rt, int oif,
int strict)
{
int m, n;
m = rt6_check_dev(rt, oif);
if (!m && (strict & RT6_LOOKUP_F_IFACE))
return -1;
#ifdef CONFIG_IPV6_ROUTER_PREF
m |= IPV6_DECODE_PREF(IPV6_EXTRACT_PREF(rt->rt6i_flags)) << 2;
#endif
n = rt6_check_neigh(rt);
if (!n && (strict & RT6_LOOKUP_F_REACHABLE))
return -1;
return m;
}
[IPV6]: Fix routing round-robin locking. As per RFC2461, section 6.3.6, item #2, when no routers on the matching list are known to be reachable or probably reachable we do round robin on those available routes so that we make sure to probe as many of them as possible to detect when one becomes reachable faster. Each routing table has a rwlock protecting the tree and the linked list of routes at each leaf. The round robin code executes during lookup and thus with the rwlock taken as a reader. A small local spinlock tries to provide protection but this does not work at all for two reasons: 1) The round-robin list manipulation, as coded, goes like this (with read lock held): walk routes finding head and tail spin_lock(); rotate list using head and tail spin_unlock(); While one thread is rotating the list, another thread can end up with stale values of head and tail and then proceed to corrupt the list when it gets the lock. This ends up causing the OOPS in fib6_add() later onthat many people have been hitting. 2) All the other code paths that run with the rwlock held as a reader do not expect the list to change on them, they expect it to remain completely fixed while they hold the lock in that way. So, simply stated, it is impossible to implement this correctly using a manipulation of the list without violating the rwlock locking semantics. Reimplement using a per-fib6_node round-robin pointer. This way we don't need to manipulate the list at all, and since the round-robin pointer can only ever point to real existing entries we don't need to perform any locking on the changing of the round-robin pointer itself. We only need to reset the round-robin pointer to NULL when the entry it is pointing to is removed. The idea is from Thomas Graf and it is very similar to how this was implemented before the advanced router selection code when in. Signed-off-by: David S. Miller <davem@davemloft.net>
2007-03-25 03:36:25 +00:00
static struct rt6_info *find_match(struct rt6_info *rt, int oif, int strict,
int *mpri, struct rt6_info *match)
{
[IPV6]: Fix routing round-robin locking. As per RFC2461, section 6.3.6, item #2, when no routers on the matching list are known to be reachable or probably reachable we do round robin on those available routes so that we make sure to probe as many of them as possible to detect when one becomes reachable faster. Each routing table has a rwlock protecting the tree and the linked list of routes at each leaf. The round robin code executes during lookup and thus with the rwlock taken as a reader. A small local spinlock tries to provide protection but this does not work at all for two reasons: 1) The round-robin list manipulation, as coded, goes like this (with read lock held): walk routes finding head and tail spin_lock(); rotate list using head and tail spin_unlock(); While one thread is rotating the list, another thread can end up with stale values of head and tail and then proceed to corrupt the list when it gets the lock. This ends up causing the OOPS in fib6_add() later onthat many people have been hitting. 2) All the other code paths that run with the rwlock held as a reader do not expect the list to change on them, they expect it to remain completely fixed while they hold the lock in that way. So, simply stated, it is impossible to implement this correctly using a manipulation of the list without violating the rwlock locking semantics. Reimplement using a per-fib6_node round-robin pointer. This way we don't need to manipulate the list at all, and since the round-robin pointer can only ever point to real existing entries we don't need to perform any locking on the changing of the round-robin pointer itself. We only need to reset the round-robin pointer to NULL when the entry it is pointing to is removed. The idea is from Thomas Graf and it is very similar to how this was implemented before the advanced router selection code when in. Signed-off-by: David S. Miller <davem@davemloft.net>
2007-03-25 03:36:25 +00:00
int m;
if (rt6_check_expired(rt))
goto out;
m = rt6_score_route(rt, oif, strict);
if (m < 0)
goto out;
if (m > *mpri) {
if (strict & RT6_LOOKUP_F_REACHABLE)
rt6_probe(match);
*mpri = m;
match = rt;
} else if (strict & RT6_LOOKUP_F_REACHABLE) {
rt6_probe(rt);
}
out:
return match;
}
static struct rt6_info *find_rr_leaf(struct fib6_node *fn,
struct rt6_info *rr_head,
u32 metric, int oif, int strict)
{
struct rt6_info *rt, *match;
int mpri = -1;
[IPV6]: Fix routing round-robin locking. As per RFC2461, section 6.3.6, item #2, when no routers on the matching list are known to be reachable or probably reachable we do round robin on those available routes so that we make sure to probe as many of them as possible to detect when one becomes reachable faster. Each routing table has a rwlock protecting the tree and the linked list of routes at each leaf. The round robin code executes during lookup and thus with the rwlock taken as a reader. A small local spinlock tries to provide protection but this does not work at all for two reasons: 1) The round-robin list manipulation, as coded, goes like this (with read lock held): walk routes finding head and tail spin_lock(); rotate list using head and tail spin_unlock(); While one thread is rotating the list, another thread can end up with stale values of head and tail and then proceed to corrupt the list when it gets the lock. This ends up causing the OOPS in fib6_add() later onthat many people have been hitting. 2) All the other code paths that run with the rwlock held as a reader do not expect the list to change on them, they expect it to remain completely fixed while they hold the lock in that way. So, simply stated, it is impossible to implement this correctly using a manipulation of the list without violating the rwlock locking semantics. Reimplement using a per-fib6_node round-robin pointer. This way we don't need to manipulate the list at all, and since the round-robin pointer can only ever point to real existing entries we don't need to perform any locking on the changing of the round-robin pointer itself. We only need to reset the round-robin pointer to NULL when the entry it is pointing to is removed. The idea is from Thomas Graf and it is very similar to how this was implemented before the advanced router selection code when in. Signed-off-by: David S. Miller <davem@davemloft.net>
2007-03-25 03:36:25 +00:00
match = NULL;
for (rt = rr_head; rt && rt->rt6i_metric == metric;
rt = rt->dst.rt6_next)
[IPV6]: Fix routing round-robin locking. As per RFC2461, section 6.3.6, item #2, when no routers on the matching list are known to be reachable or probably reachable we do round robin on those available routes so that we make sure to probe as many of them as possible to detect when one becomes reachable faster. Each routing table has a rwlock protecting the tree and the linked list of routes at each leaf. The round robin code executes during lookup and thus with the rwlock taken as a reader. A small local spinlock tries to provide protection but this does not work at all for two reasons: 1) The round-robin list manipulation, as coded, goes like this (with read lock held): walk routes finding head and tail spin_lock(); rotate list using head and tail spin_unlock(); While one thread is rotating the list, another thread can end up with stale values of head and tail and then proceed to corrupt the list when it gets the lock. This ends up causing the OOPS in fib6_add() later onthat many people have been hitting. 2) All the other code paths that run with the rwlock held as a reader do not expect the list to change on them, they expect it to remain completely fixed while they hold the lock in that way. So, simply stated, it is impossible to implement this correctly using a manipulation of the list without violating the rwlock locking semantics. Reimplement using a per-fib6_node round-robin pointer. This way we don't need to manipulate the list at all, and since the round-robin pointer can only ever point to real existing entries we don't need to perform any locking on the changing of the round-robin pointer itself. We only need to reset the round-robin pointer to NULL when the entry it is pointing to is removed. The idea is from Thomas Graf and it is very similar to how this was implemented before the advanced router selection code when in. Signed-off-by: David S. Miller <davem@davemloft.net>
2007-03-25 03:36:25 +00:00
match = find_match(rt, oif, strict, &mpri, match);
for (rt = fn->leaf; rt && rt != rr_head && rt->rt6i_metric == metric;
rt = rt->dst.rt6_next)
[IPV6]: Fix routing round-robin locking. As per RFC2461, section 6.3.6, item #2, when no routers on the matching list are known to be reachable or probably reachable we do round robin on those available routes so that we make sure to probe as many of them as possible to detect when one becomes reachable faster. Each routing table has a rwlock protecting the tree and the linked list of routes at each leaf. The round robin code executes during lookup and thus with the rwlock taken as a reader. A small local spinlock tries to provide protection but this does not work at all for two reasons: 1) The round-robin list manipulation, as coded, goes like this (with read lock held): walk routes finding head and tail spin_lock(); rotate list using head and tail spin_unlock(); While one thread is rotating the list, another thread can end up with stale values of head and tail and then proceed to corrupt the list when it gets the lock. This ends up causing the OOPS in fib6_add() later onthat many people have been hitting. 2) All the other code paths that run with the rwlock held as a reader do not expect the list to change on them, they expect it to remain completely fixed while they hold the lock in that way. So, simply stated, it is impossible to implement this correctly using a manipulation of the list without violating the rwlock locking semantics. Reimplement using a per-fib6_node round-robin pointer. This way we don't need to manipulate the list at all, and since the round-robin pointer can only ever point to real existing entries we don't need to perform any locking on the changing of the round-robin pointer itself. We only need to reset the round-robin pointer to NULL when the entry it is pointing to is removed. The idea is from Thomas Graf and it is very similar to how this was implemented before the advanced router selection code when in. Signed-off-by: David S. Miller <davem@davemloft.net>
2007-03-25 03:36:25 +00:00
match = find_match(rt, oif, strict, &mpri, match);
[IPV6]: Fix routing round-robin locking. As per RFC2461, section 6.3.6, item #2, when no routers on the matching list are known to be reachable or probably reachable we do round robin on those available routes so that we make sure to probe as many of them as possible to detect when one becomes reachable faster. Each routing table has a rwlock protecting the tree and the linked list of routes at each leaf. The round robin code executes during lookup and thus with the rwlock taken as a reader. A small local spinlock tries to provide protection but this does not work at all for two reasons: 1) The round-robin list manipulation, as coded, goes like this (with read lock held): walk routes finding head and tail spin_lock(); rotate list using head and tail spin_unlock(); While one thread is rotating the list, another thread can end up with stale values of head and tail and then proceed to corrupt the list when it gets the lock. This ends up causing the OOPS in fib6_add() later onthat many people have been hitting. 2) All the other code paths that run with the rwlock held as a reader do not expect the list to change on them, they expect it to remain completely fixed while they hold the lock in that way. So, simply stated, it is impossible to implement this correctly using a manipulation of the list without violating the rwlock locking semantics. Reimplement using a per-fib6_node round-robin pointer. This way we don't need to manipulate the list at all, and since the round-robin pointer can only ever point to real existing entries we don't need to perform any locking on the changing of the round-robin pointer itself. We only need to reset the round-robin pointer to NULL when the entry it is pointing to is removed. The idea is from Thomas Graf and it is very similar to how this was implemented before the advanced router selection code when in. Signed-off-by: David S. Miller <davem@davemloft.net>
2007-03-25 03:36:25 +00:00
return match;
}
[IPV6]: Fix routing round-robin locking. As per RFC2461, section 6.3.6, item #2, when no routers on the matching list are known to be reachable or probably reachable we do round robin on those available routes so that we make sure to probe as many of them as possible to detect when one becomes reachable faster. Each routing table has a rwlock protecting the tree and the linked list of routes at each leaf. The round robin code executes during lookup and thus with the rwlock taken as a reader. A small local spinlock tries to provide protection but this does not work at all for two reasons: 1) The round-robin list manipulation, as coded, goes like this (with read lock held): walk routes finding head and tail spin_lock(); rotate list using head and tail spin_unlock(); While one thread is rotating the list, another thread can end up with stale values of head and tail and then proceed to corrupt the list when it gets the lock. This ends up causing the OOPS in fib6_add() later onthat many people have been hitting. 2) All the other code paths that run with the rwlock held as a reader do not expect the list to change on them, they expect it to remain completely fixed while they hold the lock in that way. So, simply stated, it is impossible to implement this correctly using a manipulation of the list without violating the rwlock locking semantics. Reimplement using a per-fib6_node round-robin pointer. This way we don't need to manipulate the list at all, and since the round-robin pointer can only ever point to real existing entries we don't need to perform any locking on the changing of the round-robin pointer itself. We only need to reset the round-robin pointer to NULL when the entry it is pointing to is removed. The idea is from Thomas Graf and it is very similar to how this was implemented before the advanced router selection code when in. Signed-off-by: David S. Miller <davem@davemloft.net>
2007-03-25 03:36:25 +00:00
static struct rt6_info *rt6_select(struct fib6_node *fn, int oif, int strict)
{
struct rt6_info *match, *rt0;
struct net *net;
[IPV6]: Fix routing round-robin locking. As per RFC2461, section 6.3.6, item #2, when no routers on the matching list are known to be reachable or probably reachable we do round robin on those available routes so that we make sure to probe as many of them as possible to detect when one becomes reachable faster. Each routing table has a rwlock protecting the tree and the linked list of routes at each leaf. The round robin code executes during lookup and thus with the rwlock taken as a reader. A small local spinlock tries to provide protection but this does not work at all for two reasons: 1) The round-robin list manipulation, as coded, goes like this (with read lock held): walk routes finding head and tail spin_lock(); rotate list using head and tail spin_unlock(); While one thread is rotating the list, another thread can end up with stale values of head and tail and then proceed to corrupt the list when it gets the lock. This ends up causing the OOPS in fib6_add() later onthat many people have been hitting. 2) All the other code paths that run with the rwlock held as a reader do not expect the list to change on them, they expect it to remain completely fixed while they hold the lock in that way. So, simply stated, it is impossible to implement this correctly using a manipulation of the list without violating the rwlock locking semantics. Reimplement using a per-fib6_node round-robin pointer. This way we don't need to manipulate the list at all, and since the round-robin pointer can only ever point to real existing entries we don't need to perform any locking on the changing of the round-robin pointer itself. We only need to reset the round-robin pointer to NULL when the entry it is pointing to is removed. The idea is from Thomas Graf and it is very similar to how this was implemented before the advanced router selection code when in. Signed-off-by: David S. Miller <davem@davemloft.net>
2007-03-25 03:36:25 +00:00
rt0 = fn->rr_ptr;
if (!rt0)
fn->rr_ptr = rt0 = fn->leaf;
[IPV6]: Fix routing round-robin locking. As per RFC2461, section 6.3.6, item #2, when no routers on the matching list are known to be reachable or probably reachable we do round robin on those available routes so that we make sure to probe as many of them as possible to detect when one becomes reachable faster. Each routing table has a rwlock protecting the tree and the linked list of routes at each leaf. The round robin code executes during lookup and thus with the rwlock taken as a reader. A small local spinlock tries to provide protection but this does not work at all for two reasons: 1) The round-robin list manipulation, as coded, goes like this (with read lock held): walk routes finding head and tail spin_lock(); rotate list using head and tail spin_unlock(); While one thread is rotating the list, another thread can end up with stale values of head and tail and then proceed to corrupt the list when it gets the lock. This ends up causing the OOPS in fib6_add() later onthat many people have been hitting. 2) All the other code paths that run with the rwlock held as a reader do not expect the list to change on them, they expect it to remain completely fixed while they hold the lock in that way. So, simply stated, it is impossible to implement this correctly using a manipulation of the list without violating the rwlock locking semantics. Reimplement using a per-fib6_node round-robin pointer. This way we don't need to manipulate the list at all, and since the round-robin pointer can only ever point to real existing entries we don't need to perform any locking on the changing of the round-robin pointer itself. We only need to reset the round-robin pointer to NULL when the entry it is pointing to is removed. The idea is from Thomas Graf and it is very similar to how this was implemented before the advanced router selection code when in. Signed-off-by: David S. Miller <davem@davemloft.net>
2007-03-25 03:36:25 +00:00
match = find_rr_leaf(fn, rt0, rt0->rt6i_metric, oif, strict);
if (!match &&
[IPV6]: Fix routing round-robin locking. As per RFC2461, section 6.3.6, item #2, when no routers on the matching list are known to be reachable or probably reachable we do round robin on those available routes so that we make sure to probe as many of them as possible to detect when one becomes reachable faster. Each routing table has a rwlock protecting the tree and the linked list of routes at each leaf. The round robin code executes during lookup and thus with the rwlock taken as a reader. A small local spinlock tries to provide protection but this does not work at all for two reasons: 1) The round-robin list manipulation, as coded, goes like this (with read lock held): walk routes finding head and tail spin_lock(); rotate list using head and tail spin_unlock(); While one thread is rotating the list, another thread can end up with stale values of head and tail and then proceed to corrupt the list when it gets the lock. This ends up causing the OOPS in fib6_add() later onthat many people have been hitting. 2) All the other code paths that run with the rwlock held as a reader do not expect the list to change on them, they expect it to remain completely fixed while they hold the lock in that way. So, simply stated, it is impossible to implement this correctly using a manipulation of the list without violating the rwlock locking semantics. Reimplement using a per-fib6_node round-robin pointer. This way we don't need to manipulate the list at all, and since the round-robin pointer can only ever point to real existing entries we don't need to perform any locking on the changing of the round-robin pointer itself. We only need to reset the round-robin pointer to NULL when the entry it is pointing to is removed. The idea is from Thomas Graf and it is very similar to how this was implemented before the advanced router selection code when in. Signed-off-by: David S. Miller <davem@davemloft.net>
2007-03-25 03:36:25 +00:00
(strict & RT6_LOOKUP_F_REACHABLE)) {
struct rt6_info *next = rt0->dst.rt6_next;
[IPV6]: Fix routing round-robin locking. As per RFC2461, section 6.3.6, item #2, when no routers on the matching list are known to be reachable or probably reachable we do round robin on those available routes so that we make sure to probe as many of them as possible to detect when one becomes reachable faster. Each routing table has a rwlock protecting the tree and the linked list of routes at each leaf. The round robin code executes during lookup and thus with the rwlock taken as a reader. A small local spinlock tries to provide protection but this does not work at all for two reasons: 1) The round-robin list manipulation, as coded, goes like this (with read lock held): walk routes finding head and tail spin_lock(); rotate list using head and tail spin_unlock(); While one thread is rotating the list, another thread can end up with stale values of head and tail and then proceed to corrupt the list when it gets the lock. This ends up causing the OOPS in fib6_add() later onthat many people have been hitting. 2) All the other code paths that run with the rwlock held as a reader do not expect the list to change on them, they expect it to remain completely fixed while they hold the lock in that way. So, simply stated, it is impossible to implement this correctly using a manipulation of the list without violating the rwlock locking semantics. Reimplement using a per-fib6_node round-robin pointer. This way we don't need to manipulate the list at all, and since the round-robin pointer can only ever point to real existing entries we don't need to perform any locking on the changing of the round-robin pointer itself. We only need to reset the round-robin pointer to NULL when the entry it is pointing to is removed. The idea is from Thomas Graf and it is very similar to how this was implemented before the advanced router selection code when in. Signed-off-by: David S. Miller <davem@davemloft.net>
2007-03-25 03:36:25 +00:00
/* no entries matched; do round-robin */
[IPV6]: Fix routing round-robin locking. As per RFC2461, section 6.3.6, item #2, when no routers on the matching list are known to be reachable or probably reachable we do round robin on those available routes so that we make sure to probe as many of them as possible to detect when one becomes reachable faster. Each routing table has a rwlock protecting the tree and the linked list of routes at each leaf. The round robin code executes during lookup and thus with the rwlock taken as a reader. A small local spinlock tries to provide protection but this does not work at all for two reasons: 1) The round-robin list manipulation, as coded, goes like this (with read lock held): walk routes finding head and tail spin_lock(); rotate list using head and tail spin_unlock(); While one thread is rotating the list, another thread can end up with stale values of head and tail and then proceed to corrupt the list when it gets the lock. This ends up causing the OOPS in fib6_add() later onthat many people have been hitting. 2) All the other code paths that run with the rwlock held as a reader do not expect the list to change on them, they expect it to remain completely fixed while they hold the lock in that way. So, simply stated, it is impossible to implement this correctly using a manipulation of the list without violating the rwlock locking semantics. Reimplement using a per-fib6_node round-robin pointer. This way we don't need to manipulate the list at all, and since the round-robin pointer can only ever point to real existing entries we don't need to perform any locking on the changing of the round-robin pointer itself. We only need to reset the round-robin pointer to NULL when the entry it is pointing to is removed. The idea is from Thomas Graf and it is very similar to how this was implemented before the advanced router selection code when in. Signed-off-by: David S. Miller <davem@davemloft.net>
2007-03-25 03:36:25 +00:00
if (!next || next->rt6i_metric != rt0->rt6i_metric)
next = fn->leaf;
if (next != rt0)
fn->rr_ptr = next;
}
net = dev_net(rt0->dst.dev);
return match ? match : net->ipv6.ip6_null_entry;
}
#ifdef CONFIG_IPV6_ROUTE_INFO
int rt6_route_rcv(struct net_device *dev, u8 *opt, int len,
const struct in6_addr *gwaddr)
{
struct net *net = dev_net(dev);
struct route_info *rinfo = (struct route_info *) opt;
struct in6_addr prefix_buf, *prefix;
unsigned int pref;
unsigned long lifetime;
struct rt6_info *rt;
if (len < sizeof(struct route_info)) {
return -EINVAL;
}
/* Sanity check for prefix_len and length */
if (rinfo->length > 3) {
return -EINVAL;
} else if (rinfo->prefix_len > 128) {
return -EINVAL;
} else if (rinfo->prefix_len > 64) {
if (rinfo->length < 2) {
return -EINVAL;
}
} else if (rinfo->prefix_len > 0) {
if (rinfo->length < 1) {
return -EINVAL;
}
}
pref = rinfo->route_pref;
if (pref == ICMPV6_ROUTER_PREF_INVALID)
return -EINVAL;
lifetime = addrconf_timeout_fixup(ntohl(rinfo->lifetime), HZ);
if (rinfo->length == 3)
prefix = (struct in6_addr *)rinfo->prefix;
else {
/* this function is safe */
ipv6_addr_prefix(&prefix_buf,
(struct in6_addr *)rinfo->prefix,
rinfo->prefix_len);
prefix = &prefix_buf;
}
rt = rt6_get_route_info(net, prefix, rinfo->prefix_len, gwaddr,
dev->ifindex);
if (rt && !lifetime) {
ip6_del_rt(rt);
rt = NULL;
}
if (!rt && lifetime)
rt = rt6_add_route_info(net, prefix, rinfo->prefix_len, gwaddr, dev->ifindex,
pref);
else if (rt)
rt->rt6i_flags = RTF_ROUTEINFO |
(rt->rt6i_flags & ~RTF_PREF_MASK) | RTF_PREF(pref);
if (rt) {
if (!addrconf_finite_timeout(lifetime))
rt6_clean_expires(rt);
else
rt6_set_expires(rt, jiffies + HZ * lifetime);
dst_release(&rt->dst);
}
return 0;
}
#endif
#define BACKTRACK(__net, saddr) \
do { \
if (rt == __net->ipv6.ip6_null_entry) { \
struct fib6_node *pn; \
while (1) { \
if (fn->fn_flags & RTN_TL_ROOT) \
goto out; \
pn = fn->parent; \
if (FIB6_SUBTREE(pn) && FIB6_SUBTREE(pn) != fn) \
fn = fib6_lookup(FIB6_SUBTREE(pn), NULL, saddr); \
else \
fn = pn; \
if (fn->fn_flags & RTN_RTINFO) \
goto restart; \
} \
} \
} while (0)
static struct rt6_info *ip6_pol_route_lookup(struct net *net,
struct fib6_table *table,
struct flowi6 *fl6, int flags)
{
struct fib6_node *fn;
struct rt6_info *rt;
read_lock_bh(&table->tb6_lock);
fn = fib6_lookup(&table->tb6_root, &fl6->daddr, &fl6->saddr);
restart:
rt = fn->leaf;
rt = rt6_device_match(net, rt, &fl6->saddr, fl6->flowi6_oif, flags);
if (rt->rt6i_nsiblings && fl6->flowi6_oif == 0)
rt = rt6_multipath_select(rt, fl6);
BACKTRACK(net, &fl6->saddr);
out:
dst_use(&rt->dst, jiffies);
read_unlock_bh(&table->tb6_lock);
return rt;
}
struct dst_entry * ip6_route_lookup(struct net *net, struct flowi6 *fl6,
int flags)
{
return fib6_rule_lookup(net, fl6, flags, ip6_pol_route_lookup);
}
EXPORT_SYMBOL_GPL(ip6_route_lookup);
struct rt6_info *rt6_lookup(struct net *net, const struct in6_addr *daddr,
const struct in6_addr *saddr, int oif, int strict)
{
struct flowi6 fl6 = {
.flowi6_oif = oif,
.daddr = *daddr,
};
struct dst_entry *dst;
int flags = strict ? RT6_LOOKUP_F_IFACE : 0;
if (saddr) {
memcpy(&fl6.saddr, saddr, sizeof(*saddr));
flags |= RT6_LOOKUP_F_HAS_SADDR;
}
dst = fib6_rule_lookup(net, &fl6, flags, ip6_pol_route_lookup);
if (dst->error == 0)
return (struct rt6_info *) dst;
dst_release(dst);
return NULL;
}
EXPORT_SYMBOL(rt6_lookup);
/* ip6_ins_rt is called with FREE table->tb6_lock.
It takes new route entry, the addition fails by any reason the
route is freed. In any case, if caller does not hold it, it may
be destroyed.
*/
static int __ip6_ins_rt(struct rt6_info *rt, struct nl_info *info)
{
int err;
struct fib6_table *table;
table = rt->rt6i_table;
write_lock_bh(&table->tb6_lock);
err = fib6_add(&table->tb6_root, rt, info);
write_unlock_bh(&table->tb6_lock);
return err;
}
int ip6_ins_rt(struct rt6_info *rt)
{
struct nl_info info = {
.nl_net = dev_net(rt->dst.dev),
};
return __ip6_ins_rt(rt, &info);
}
static struct rt6_info *rt6_alloc_cow(struct rt6_info *ort,
const struct in6_addr *daddr,
const struct in6_addr *saddr)
{
struct rt6_info *rt;
/*
* Clone the route.
*/
rt = ip6_rt_copy(ort, daddr);
if (rt) {
int attempts = !in_softirq();
if (!(rt->rt6i_flags & RTF_GATEWAY)) {
if (ort->rt6i_dst.plen != 128 &&
ipv6_addr_equal(&ort->rt6i_dst.addr, daddr))
rt->rt6i_flags |= RTF_ANYCAST;
rt->rt6i_gateway = *daddr;
}
rt->rt6i_flags |= RTF_CACHE;
#ifdef CONFIG_IPV6_SUBTREES
if (rt->rt6i_src.plen && saddr) {
rt->rt6i_src.addr = *saddr;
rt->rt6i_src.plen = 128;
}
#endif
retry:
if (rt6_bind_neighbour(rt, rt->dst.dev)) {
struct net *net = dev_net(rt->dst.dev);
int saved_rt_min_interval =
net->ipv6.sysctl.ip6_rt_gc_min_interval;
int saved_rt_elasticity =
net->ipv6.sysctl.ip6_rt_gc_elasticity;
if (attempts-- > 0) {
net->ipv6.sysctl.ip6_rt_gc_elasticity = 1;
net->ipv6.sysctl.ip6_rt_gc_min_interval = 0;
ip6_dst_gc(&net->ipv6.ip6_dst_ops);
net->ipv6.sysctl.ip6_rt_gc_elasticity =
saved_rt_elasticity;
net->ipv6.sysctl.ip6_rt_gc_min_interval =
saved_rt_min_interval;
goto retry;
}
net_warn_ratelimited("Neighbour table overflow\n");
dst_free(&rt->dst);
return NULL;
}
}
return rt;
}
static struct rt6_info *rt6_alloc_clone(struct rt6_info *ort,
const struct in6_addr *daddr)
{
struct rt6_info *rt = ip6_rt_copy(ort, daddr);
if (rt) {
rt->rt6i_flags |= RTF_CACHE;
rt->n = neigh_clone(ort->n);
}
return rt;
}
static struct rt6_info *ip6_pol_route(struct net *net, struct fib6_table *table, int oif,
struct flowi6 *fl6, int flags)
{
struct fib6_node *fn;
struct rt6_info *rt, *nrt;
int strict = 0;
int attempts = 3;
int err;
int reachable = net->ipv6.devconf_all->forwarding ? 0 : RT6_LOOKUP_F_REACHABLE;
strict |= flags & RT6_LOOKUP_F_IFACE;
relookup:
read_lock_bh(&table->tb6_lock);
restart_2:
fn = fib6_lookup(&table->tb6_root, &fl6->daddr, &fl6->saddr);
restart:
rt = rt6_select(fn, oif, strict | reachable);
if (rt->rt6i_nsiblings && oif == 0)
rt = rt6_multipath_select(rt, fl6);
BACKTRACK(net, &fl6->saddr);
if (rt == net->ipv6.ip6_null_entry ||
rt->rt6i_flags & RTF_CACHE)
goto out;
dst_hold(&rt->dst);
read_unlock_bh(&table->tb6_lock);
if (!rt->n && !(rt->rt6i_flags & RTF_NONEXTHOP))
nrt = rt6_alloc_cow(rt, &fl6->daddr, &fl6->saddr);
else if (!(rt->dst.flags & DST_HOST))
nrt = rt6_alloc_clone(rt, &fl6->daddr);
else
goto out2;
dst_release(&rt->dst);
rt = nrt ? : net->ipv6.ip6_null_entry;
dst_hold(&rt->dst);
if (nrt) {
err = ip6_ins_rt(nrt);
if (!err)
goto out2;
}
if (--attempts <= 0)
goto out2;
/*
* Race condition! In the gap, when table->tb6_lock was
* released someone could insert this route. Relookup.
*/
dst_release(&rt->dst);
goto relookup;
out:
if (reachable) {
reachable = 0;
goto restart_2;
}
dst_hold(&rt->dst);
read_unlock_bh(&table->tb6_lock);
out2:
rt->dst.lastuse = jiffies;
rt->dst.__use++;
return rt;
}
static struct rt6_info *ip6_pol_route_input(struct net *net, struct fib6_table *table,
struct flowi6 *fl6, int flags)
{
return ip6_pol_route(net, table, fl6->flowi6_iif, fl6, flags);
}
static struct dst_entry *ip6_route_input_lookup(struct net *net,
struct net_device *dev,
struct flowi6 *fl6, int flags)
{
if (rt6_need_strict(&fl6->daddr) && dev->type != ARPHRD_PIMREG)
flags |= RT6_LOOKUP_F_IFACE;
return fib6_rule_lookup(net, fl6, flags, ip6_pol_route_input);
}
void ip6_route_input(struct sk_buff *skb)
{
const struct ipv6hdr *iph = ipv6_hdr(skb);
struct net *net = dev_net(skb->dev);
int flags = RT6_LOOKUP_F_HAS_SADDR;
struct flowi6 fl6 = {
.flowi6_iif = skb->dev->ifindex,
.daddr = iph->daddr,
.saddr = iph->saddr,
.flowlabel = (* (__be32 *) iph) & IPV6_FLOWINFO_MASK,
.flowi6_mark = skb->mark,
.flowi6_proto = iph->nexthdr,
};
skb_dst_set(skb, ip6_route_input_lookup(net, skb->dev, &fl6, flags));
}
static struct rt6_info *ip6_pol_route_output(struct net *net, struct fib6_table *table,
struct flowi6 *fl6, int flags)
{
return ip6_pol_route(net, table, fl6->flowi6_oif, fl6, flags);
}
struct dst_entry * ip6_route_output(struct net *net, const struct sock *sk,
struct flowi6 *fl6)
{
int flags = 0;
fl6->flowi6_iif = LOOPBACK_IFINDEX;
if ((sk && sk->sk_bound_dev_if) || rt6_need_strict(&fl6->daddr))
flags |= RT6_LOOKUP_F_IFACE;
if (!ipv6_addr_any(&fl6->saddr))
flags |= RT6_LOOKUP_F_HAS_SADDR;
else if (sk)
flags |= rt6_srcprefs2flags(inet6_sk(sk)->srcprefs);
return fib6_rule_lookup(net, fl6, flags, ip6_pol_route_output);
}
EXPORT_SYMBOL(ip6_route_output);
struct dst_entry *ip6_blackhole_route(struct net *net, struct dst_entry *dst_orig)
{
struct rt6_info *rt, *ort = (struct rt6_info *) dst_orig;
struct dst_entry *new = NULL;
rt = dst_alloc(&ip6_dst_blackhole_ops, ort->dst.dev, 1, DST_OBSOLETE_NONE, 0);
if (rt) {
new = &rt->dst;
memset(new + 1, 0, sizeof(*rt) - sizeof(*new));
rt6_init_peer(rt, net->ipv6.peers);
new->__use = 1;
new->input = dst_discard;
new->output = dst_discard;
if (dst_metrics_read_only(&ort->dst))
new->_metrics = ort->dst._metrics;
else
dst_copy_metrics(new, &ort->dst);
rt->rt6i_idev = ort->rt6i_idev;
if (rt->rt6i_idev)
in6_dev_hold(rt->rt6i_idev);
rt->rt6i_gateway = ort->rt6i_gateway;
rt->rt6i_flags = ort->rt6i_flags;
rt6_clean_expires(rt);
rt->rt6i_metric = 0;
memcpy(&rt->rt6i_dst, &ort->rt6i_dst, sizeof(struct rt6key));
#ifdef CONFIG_IPV6_SUBTREES
memcpy(&rt->rt6i_src, &ort->rt6i_src, sizeof(struct rt6key));
#endif
dst_free(new);
}
dst_release(dst_orig);
return new ? new : ERR_PTR(-ENOMEM);
}
/*
* Destination cache support functions
*/
static struct dst_entry *ip6_dst_check(struct dst_entry *dst, u32 cookie)
{
struct rt6_info *rt;
rt = (struct rt6_info *) dst;
/* All IPV6 dsts are created with ->obsolete set to the value
* DST_OBSOLETE_FORCE_CHK which forces validation calls down
* into this function always.
*/
if (rt->rt6i_genid != rt_genid(dev_net(rt->dst.dev)))
return NULL;
inet: Create a mechanism for upward inetpeer propagation into routes. If we didn't have a routing cache, we would not be able to properly propagate certain kinds of dynamic path attributes, for example PMTU information and redirects. The reason is that if we didn't have a routing cache, then there would be no way to lookup all of the active cached routes hanging off of sockets, tunnels, IPSEC bundles, etc. Consider the case where we created a cached route, but no inetpeer entry existed and also we were not asked to pre-COW the route metrics and therefore did not force the creation a new inetpeer entry. If we later get a PMTU message, or a redirect, and store this information in a new inetpeer entry, there is no way to teach that cached route about the newly existing inetpeer entry. The facilities implemented here handle this problem. First we create a generation ID. When we create a cached route of any kind, we remember the generation ID at the time of attachment. Any time we force-create an inetpeer entry in response to new path information, we bump that generation ID. The dst_ops->check() callback is where the knowledge of this event is propagated. If the global generation ID does not equal the one stored in the cached route, and the cached route has not attached to an inetpeer yet, we look it up and attach if one is found. Now that we've updated the cached route's information, we update the route's generation ID too. This clears the way for implementing PMTU and redirects directly in the inetpeer cache. There is absolutely no need to consult cached route information in order to maintain this information. At this point nothing bumps the inetpeer genids, that comes in the later changes which handle PMTUs and redirects using inetpeers. Signed-off-by: David S. Miller <davem@davemloft.net>
2011-02-08 04:38:06 +00:00
if (rt->rt6i_node && (rt->rt6i_node->fn_sernum == cookie)) {
if (rt->rt6i_peer_genid != rt6_peer_genid()) {
if (!rt6_has_peer(rt))
inet: Create a mechanism for upward inetpeer propagation into routes. If we didn't have a routing cache, we would not be able to properly propagate certain kinds of dynamic path attributes, for example PMTU information and redirects. The reason is that if we didn't have a routing cache, then there would be no way to lookup all of the active cached routes hanging off of sockets, tunnels, IPSEC bundles, etc. Consider the case where we created a cached route, but no inetpeer entry existed and also we were not asked to pre-COW the route metrics and therefore did not force the creation a new inetpeer entry. If we later get a PMTU message, or a redirect, and store this information in a new inetpeer entry, there is no way to teach that cached route about the newly existing inetpeer entry. The facilities implemented here handle this problem. First we create a generation ID. When we create a cached route of any kind, we remember the generation ID at the time of attachment. Any time we force-create an inetpeer entry in response to new path information, we bump that generation ID. The dst_ops->check() callback is where the knowledge of this event is propagated. If the global generation ID does not equal the one stored in the cached route, and the cached route has not attached to an inetpeer yet, we look it up and attach if one is found. Now that we've updated the cached route's information, we update the route's generation ID too. This clears the way for implementing PMTU and redirects directly in the inetpeer cache. There is absolutely no need to consult cached route information in order to maintain this information. At this point nothing bumps the inetpeer genids, that comes in the later changes which handle PMTUs and redirects using inetpeers. Signed-off-by: David S. Miller <davem@davemloft.net>
2011-02-08 04:38:06 +00:00
rt6_bind_peer(rt, 0);
rt->rt6i_peer_genid = rt6_peer_genid();
}
return dst;
inet: Create a mechanism for upward inetpeer propagation into routes. If we didn't have a routing cache, we would not be able to properly propagate certain kinds of dynamic path attributes, for example PMTU information and redirects. The reason is that if we didn't have a routing cache, then there would be no way to lookup all of the active cached routes hanging off of sockets, tunnels, IPSEC bundles, etc. Consider the case where we created a cached route, but no inetpeer entry existed and also we were not asked to pre-COW the route metrics and therefore did not force the creation a new inetpeer entry. If we later get a PMTU message, or a redirect, and store this information in a new inetpeer entry, there is no way to teach that cached route about the newly existing inetpeer entry. The facilities implemented here handle this problem. First we create a generation ID. When we create a cached route of any kind, we remember the generation ID at the time of attachment. Any time we force-create an inetpeer entry in response to new path information, we bump that generation ID. The dst_ops->check() callback is where the knowledge of this event is propagated. If the global generation ID does not equal the one stored in the cached route, and the cached route has not attached to an inetpeer yet, we look it up and attach if one is found. Now that we've updated the cached route's information, we update the route's generation ID too. This clears the way for implementing PMTU and redirects directly in the inetpeer cache. There is absolutely no need to consult cached route information in order to maintain this information. At this point nothing bumps the inetpeer genids, that comes in the later changes which handle PMTUs and redirects using inetpeers. Signed-off-by: David S. Miller <davem@davemloft.net>
2011-02-08 04:38:06 +00:00
}
return NULL;
}
static struct dst_entry *ip6_negative_advice(struct dst_entry *dst)
{
struct rt6_info *rt = (struct rt6_info *) dst;
if (rt) {
if (rt->rt6i_flags & RTF_CACHE) {
if (rt6_check_expired(rt)) {
ip6_del_rt(rt);
dst = NULL;
}
} else {
dst_release(dst);
dst = NULL;
}
}
return dst;
}
static void ip6_link_failure(struct sk_buff *skb)
{
struct rt6_info *rt;
icmpv6_send(skb, ICMPV6_DEST_UNREACH, ICMPV6_ADDR_UNREACH, 0);
rt = (struct rt6_info *) skb_dst(skb);
if (rt) {
if (rt->rt6i_flags & RTF_CACHE)
rt6_update_expires(rt, 0);
else if (rt->rt6i_node && (rt->rt6i_flags & RTF_DEFAULT))
rt->rt6i_node->fn_sernum = -1;
}
}
static void ip6_rt_update_pmtu(struct dst_entry *dst, struct sock *sk,
struct sk_buff *skb, u32 mtu)
{
struct rt6_info *rt6 = (struct rt6_info*)dst;
dst_confirm(dst);
if (mtu < dst_mtu(dst) && rt6->rt6i_dst.plen == 128) {
struct net *net = dev_net(dst->dev);
rt6->rt6i_flags |= RTF_MODIFIED;
if (mtu < IPV6_MIN_MTU) {
u32 features = dst_metric(dst, RTAX_FEATURES);
mtu = IPV6_MIN_MTU;
features |= RTAX_FEATURE_ALLFRAG;
dst_metric_set(dst, RTAX_FEATURES, features);
}
dst_metric_set(dst, RTAX_MTU, mtu);
rt6_update_expires(rt6, net->ipv6.sysctl.ip6_rt_mtu_expires);
}
}
void ip6_update_pmtu(struct sk_buff *skb, struct net *net, __be32 mtu,
int oif, u32 mark)
{
const struct ipv6hdr *iph = (struct ipv6hdr *) skb->data;
struct dst_entry *dst;
struct flowi6 fl6;
memset(&fl6, 0, sizeof(fl6));
fl6.flowi6_oif = oif;
fl6.flowi6_mark = mark;
fl6.flowi6_flags = 0;
fl6.daddr = iph->daddr;
fl6.saddr = iph->saddr;
fl6.flowlabel = (*(__be32 *) iph) & IPV6_FLOWINFO_MASK;
dst = ip6_route_output(net, NULL, &fl6);
if (!dst->error)
ip6_rt_update_pmtu(dst, NULL, skb, ntohl(mtu));
dst_release(dst);
}
EXPORT_SYMBOL_GPL(ip6_update_pmtu);
void ip6_sk_update_pmtu(struct sk_buff *skb, struct sock *sk, __be32 mtu)
{
ip6_update_pmtu(skb, sock_net(sk), mtu,
sk->sk_bound_dev_if, sk->sk_mark);
}
EXPORT_SYMBOL_GPL(ip6_sk_update_pmtu);
void ip6_redirect(struct sk_buff *skb, struct net *net, int oif, u32 mark)
{
const struct ipv6hdr *iph = (struct ipv6hdr *) skb->data;
struct dst_entry *dst;
struct flowi6 fl6;
memset(&fl6, 0, sizeof(fl6));
fl6.flowi6_oif = oif;
fl6.flowi6_mark = mark;
fl6.flowi6_flags = 0;
fl6.daddr = iph->daddr;
fl6.saddr = iph->saddr;
fl6.flowlabel = (*(__be32 *) iph) & IPV6_FLOWINFO_MASK;
dst = ip6_route_output(net, NULL, &fl6);
if (!dst->error)
rt6_do_redirect(dst, NULL, skb);
dst_release(dst);
}
EXPORT_SYMBOL_GPL(ip6_redirect);
void ip6_sk_redirect(struct sk_buff *skb, struct sock *sk)
{
ip6_redirect(skb, sock_net(sk), sk->sk_bound_dev_if, sk->sk_mark);
}
EXPORT_SYMBOL_GPL(ip6_sk_redirect);
static unsigned int ip6_default_advmss(const struct dst_entry *dst)
{
struct net_device *dev = dst->dev;
unsigned int mtu = dst_mtu(dst);
struct net *net = dev_net(dev);
mtu -= sizeof(struct ipv6hdr) + sizeof(struct tcphdr);
if (mtu < net->ipv6.sysctl.ip6_rt_min_advmss)
mtu = net->ipv6.sysctl.ip6_rt_min_advmss;
/*
* Maximal non-jumbo IPv6 payload is IPV6_MAXPLEN and
* corresponding MSS is IPV6_MAXPLEN - tcp_header_size.
* IPV6_MAXPLEN is also valid and means: "any MSS,
* rely only on pmtu discovery"
*/
if (mtu > IPV6_MAXPLEN - sizeof(struct tcphdr))
mtu = IPV6_MAXPLEN;
return mtu;
}
static unsigned int ip6_mtu(const struct dst_entry *dst)
{
struct inet6_dev *idev;
unsigned int mtu = dst_metric_raw(dst, RTAX_MTU);
if (mtu)
return mtu;
mtu = IPV6_MIN_MTU;
rcu_read_lock();
idev = __in6_dev_get(dst->dev);
if (idev)
mtu = idev->cnf.mtu6;
rcu_read_unlock();
return mtu;
}
static struct dst_entry *icmp6_dst_gc_list;
static DEFINE_SPINLOCK(icmp6_dst_lock);
struct dst_entry *icmp6_dst_alloc(struct net_device *dev,
struct neighbour *neigh,
struct flowi6 *fl6)
{
struct dst_entry *dst;
struct rt6_info *rt;
struct inet6_dev *idev = in6_dev_get(dev);
struct net *net = dev_net(dev);
if (unlikely(!idev))
return ERR_PTR(-ENODEV);
rt = ip6_dst_alloc(net, dev, 0, NULL);
if (unlikely(!rt)) {
in6_dev_put(idev);
dst = ERR_PTR(-ENOMEM);
goto out;
}
if (neigh)
neigh_hold(neigh);
else {
neigh = ip6_neigh_lookup(&rt->dst, NULL, &fl6->daddr);
if (IS_ERR(neigh)) {
in6_dev_put(idev);
dst_free(&rt->dst);
return ERR_CAST(neigh);
}
}
rt->dst.flags |= DST_HOST;
rt->dst.output = ip6_output;
rt->n = neigh;
atomic_set(&rt->dst.__refcnt, 1);
rt->rt6i_dst.addr = fl6->daddr;
rt->rt6i_dst.plen = 128;
rt->rt6i_idev = idev;
dst_metric_set(&rt->dst, RTAX_HOPLIMIT, 255);
spin_lock_bh(&icmp6_dst_lock);
rt->dst.next = icmp6_dst_gc_list;
icmp6_dst_gc_list = &rt->dst;
spin_unlock_bh(&icmp6_dst_lock);
fib6_force_start_gc(net);
dst = xfrm_lookup(net, &rt->dst, flowi6_to_flowi(fl6), NULL, 0);
out:
return dst;
}
int icmp6_dst_gc(void)
{
struct dst_entry *dst, **pprev;
int more = 0;
spin_lock_bh(&icmp6_dst_lock);
pprev = &icmp6_dst_gc_list;
while ((dst = *pprev) != NULL) {
if (!atomic_read(&dst->__refcnt)) {
*pprev = dst->next;
dst_free(dst);
} else {
pprev = &dst->next;
++more;
}
}
spin_unlock_bh(&icmp6_dst_lock);
return more;
}
static void icmp6_clean_all(int (*func)(struct rt6_info *rt, void *arg),
void *arg)
{
struct dst_entry *dst, **pprev;
spin_lock_bh(&icmp6_dst_lock);
pprev = &icmp6_dst_gc_list;
while ((dst = *pprev) != NULL) {
struct rt6_info *rt = (struct rt6_info *) dst;
if (func(rt, arg)) {
*pprev = dst->next;
dst_free(dst);
} else {
pprev = &dst->next;
}
}
spin_unlock_bh(&icmp6_dst_lock);
}
static int ip6_dst_gc(struct dst_ops *ops)
{
unsigned long now = jiffies;
struct net *net = container_of(ops, struct net, ipv6.ip6_dst_ops);
int rt_min_interval = net->ipv6.sysctl.ip6_rt_gc_min_interval;
int rt_max_size = net->ipv6.sysctl.ip6_rt_max_size;
int rt_elasticity = net->ipv6.sysctl.ip6_rt_gc_elasticity;
int rt_gc_timeout = net->ipv6.sysctl.ip6_rt_gc_timeout;
unsigned long rt_last_gc = net->ipv6.ip6_rt_last_gc;
int entries;
entries = dst_entries_get_fast(ops);
if (time_after(rt_last_gc + rt_min_interval, now) &&
entries <= rt_max_size)
goto out;
net->ipv6.ip6_rt_gc_expire++;
fib6_run_gc(net->ipv6.ip6_rt_gc_expire, net);
net->ipv6.ip6_rt_last_gc = now;
entries = dst_entries_get_slow(ops);
if (entries < ops->gc_thresh)
net->ipv6.ip6_rt_gc_expire = rt_gc_timeout>>1;
out:
net->ipv6.ip6_rt_gc_expire -= net->ipv6.ip6_rt_gc_expire>>rt_elasticity;
return entries > rt_max_size;
}
/* Clean host part of a prefix. Not necessary in radix tree,
but results in cleaner routing tables.
Remove it only when all the things will work!
*/
int ip6_dst_hoplimit(struct dst_entry *dst)
{
int hoplimit = dst_metric_raw(dst, RTAX_HOPLIMIT);
if (hoplimit == 0) {
struct net_device *dev = dst->dev;
struct inet6_dev *idev;
rcu_read_lock();
idev = __in6_dev_get(dev);
if (idev)
hoplimit = idev->cnf.hop_limit;
else
hoplimit = dev_net(dev)->ipv6.devconf_all->hop_limit;
rcu_read_unlock();
}
return hoplimit;
}
EXPORT_SYMBOL(ip6_dst_hoplimit);
/*
*
*/
int ip6_route_add(struct fib6_config *cfg)
{
int err;
struct net *net = cfg->fc_nlinfo.nl_net;
struct rt6_info *rt = NULL;
struct net_device *dev = NULL;
struct inet6_dev *idev = NULL;
struct fib6_table *table;
int addr_type;
if (cfg->fc_dst_len > 128 || cfg->fc_src_len > 128)
return -EINVAL;
#ifndef CONFIG_IPV6_SUBTREES
if (cfg->fc_src_len)
return -EINVAL;
#endif
if (cfg->fc_ifindex) {
err = -ENODEV;
dev = dev_get_by_index(net, cfg->fc_ifindex);
if (!dev)
goto out;
idev = in6_dev_get(dev);
if (!idev)
goto out;
}
if (cfg->fc_metric == 0)
cfg->fc_metric = IP6_RT_PRIO_USER;
err = -ENOBUFS;
if (cfg->fc_nlinfo.nlh &&
!(cfg->fc_nlinfo.nlh->nlmsg_flags & NLM_F_CREATE)) {
table = fib6_get_table(net, cfg->fc_table);
if (!table) {
pr_warn("NLM_F_CREATE should be specified when creating new route\n");
table = fib6_new_table(net, cfg->fc_table);
}
} else {
table = fib6_new_table(net, cfg->fc_table);
}
if (!table)
goto out;
rt = ip6_dst_alloc(net, NULL, DST_NOCOUNT, table);
if (!rt) {
err = -ENOMEM;
goto out;
}
if (cfg->fc_flags & RTF_EXPIRES)
rt6_set_expires(rt, jiffies +
clock_t_to_jiffies(cfg->fc_expires));
else
rt6_clean_expires(rt);
if (cfg->fc_protocol == RTPROT_UNSPEC)
cfg->fc_protocol = RTPROT_BOOT;
rt->rt6i_protocol = cfg->fc_protocol;
addr_type = ipv6_addr_type(&cfg->fc_dst);
if (addr_type & IPV6_ADDR_MULTICAST)
rt->dst.input = ip6_mc_input;
else if (cfg->fc_flags & RTF_LOCAL)
rt->dst.input = ip6_input;
else
rt->dst.input = ip6_forward;
rt->dst.output = ip6_output;
ipv6_addr_prefix(&rt->rt6i_dst.addr, &cfg->fc_dst, cfg->fc_dst_len);
rt->rt6i_dst.plen = cfg->fc_dst_len;
if (rt->rt6i_dst.plen == 128)
rt->dst.flags |= DST_HOST;
if (!(rt->dst.flags & DST_HOST) && cfg->fc_mx) {
u32 *metrics = kzalloc(sizeof(u32) * RTAX_MAX, GFP_KERNEL);
if (!metrics) {
err = -ENOMEM;
goto out;
}
dst_init_metrics(&rt->dst, metrics, 0);
}
#ifdef CONFIG_IPV6_SUBTREES
ipv6_addr_prefix(&rt->rt6i_src.addr, &cfg->fc_src, cfg->fc_src_len);
rt->rt6i_src.plen = cfg->fc_src_len;
#endif
rt->rt6i_metric = cfg->fc_metric;
/* We cannot add true routes via loopback here,
they would result in kernel looping; promote them to reject routes
*/
if ((cfg->fc_flags & RTF_REJECT) ||
(dev && (dev->flags & IFF_LOOPBACK) &&
!(addr_type & IPV6_ADDR_LOOPBACK) &&
!(cfg->fc_flags & RTF_LOCAL))) {
/* hold loopback dev/idev if we haven't done so. */
if (dev != net->loopback_dev) {
if (dev) {
dev_put(dev);
in6_dev_put(idev);
}
dev = net->loopback_dev;
dev_hold(dev);
idev = in6_dev_get(dev);
if (!idev) {
err = -ENODEV;
goto out;
}
}
rt->dst.output = ip6_pkt_discard_out;
rt->dst.input = ip6_pkt_discard;
rt->rt6i_flags = RTF_REJECT|RTF_NONEXTHOP;
switch (cfg->fc_type) {
case RTN_BLACKHOLE:
rt->dst.error = -EINVAL;
break;
case RTN_PROHIBIT:
rt->dst.error = -EACCES;
break;
case RTN_THROW:
rt->dst.error = -EAGAIN;
break;
default:
rt->dst.error = -ENETUNREACH;
break;
}
goto install_route;
}
if (cfg->fc_flags & RTF_GATEWAY) {
const struct in6_addr *gw_addr;
int gwa_type;
gw_addr = &cfg->fc_gateway;
rt->rt6i_gateway = *gw_addr;
gwa_type = ipv6_addr_type(gw_addr);
if (gwa_type != (IPV6_ADDR_LINKLOCAL|IPV6_ADDR_UNICAST)) {
struct rt6_info *grt;
/* IPv6 strictly inhibits using not link-local
addresses as nexthop address.
Otherwise, router will not able to send redirects.
It is very good, but in some (rare!) circumstances
(SIT, PtP, NBMA NOARP links) it is handy to allow
some exceptions. --ANK
*/
err = -EINVAL;
if (!(gwa_type & IPV6_ADDR_UNICAST))
goto out;
grt = rt6_lookup(net, gw_addr, NULL, cfg->fc_ifindex, 1);
err = -EHOSTUNREACH;
if (!grt)
goto out;
if (dev) {
if (dev != grt->dst.dev) {
dst_release(&grt->dst);
goto out;
}
} else {
dev = grt->dst.dev;
idev = grt->rt6i_idev;
dev_hold(dev);
in6_dev_hold(grt->rt6i_idev);
}
if (!(grt->rt6i_flags & RTF_GATEWAY))
err = 0;
dst_release(&grt->dst);
if (err)
goto out;
}
err = -EINVAL;
if (!dev || (dev->flags & IFF_LOOPBACK))
goto out;
}
err = -ENODEV;
if (!dev)
goto out;
if (!ipv6_addr_any(&cfg->fc_prefsrc)) {
if (!ipv6_chk_addr(net, &cfg->fc_prefsrc, dev, 0)) {
err = -EINVAL;
goto out;
}
rt->rt6i_prefsrc.addr = cfg->fc_prefsrc;
rt->rt6i_prefsrc.plen = 128;
} else
rt->rt6i_prefsrc.plen = 0;
if (cfg->fc_flags & (RTF_GATEWAY | RTF_NONEXTHOP)) {
err = rt6_bind_neighbour(rt, dev);
if (err)
goto out;
}
rt->rt6i_flags = cfg->fc_flags;
install_route:
if (cfg->fc_mx) {
struct nlattr *nla;
int remaining;
nla_for_each_attr(nla, cfg->fc_mx, cfg->fc_mx_len, remaining) {
int type = nla_type(nla);
if (type) {
if (type > RTAX_MAX) {
err = -EINVAL;
goto out;
}
dst_metric_set(&rt->dst, type, nla_get_u32(nla));
}
}
}
rt->dst.dev = dev;
rt->rt6i_idev = idev;
rt->rt6i_table = table;
cfg->fc_nlinfo.nl_net = dev_net(dev);
return __ip6_ins_rt(rt, &cfg->fc_nlinfo);
out:
if (dev)
dev_put(dev);
if (idev)
in6_dev_put(idev);
if (rt)
dst_free(&rt->dst);
return err;
}
static int __ip6_del_rt(struct rt6_info *rt, struct nl_info *info)
{
int err;
struct fib6_table *table;
struct net *net = dev_net(rt->dst.dev);
if (rt == net->ipv6.ip6_null_entry) {
err = -ENOENT;
goto out;
}
table = rt->rt6i_table;
write_lock_bh(&table->tb6_lock);
err = fib6_del(rt, info);
write_unlock_bh(&table->tb6_lock);
out:
dst_release(&rt->dst);
return err;
}
int ip6_del_rt(struct rt6_info *rt)
{
struct nl_info info = {
.nl_net = dev_net(rt->dst.dev),
};
return __ip6_del_rt(rt, &info);
}
static int ip6_route_del(struct fib6_config *cfg)
{
struct fib6_table *table;
struct fib6_node *fn;
struct rt6_info *rt;
int err = -ESRCH;
table = fib6_get_table(cfg->fc_nlinfo.nl_net, cfg->fc_table);
if (!table)
return err;
read_lock_bh(&table->tb6_lock);
fn = fib6_locate(&table->tb6_root,
&cfg->fc_dst, cfg->fc_dst_len,
&cfg->fc_src, cfg->fc_src_len);
if (fn) {
for (rt = fn->leaf; rt; rt = rt->dst.rt6_next) {
if (cfg->fc_ifindex &&
(!rt->dst.dev ||
rt->dst.dev->ifindex != cfg->fc_ifindex))
continue;
if (cfg->fc_flags & RTF_GATEWAY &&
!ipv6_addr_equal(&cfg->fc_gateway, &rt->rt6i_gateway))
continue;
if (cfg->fc_metric && cfg->fc_metric != rt->rt6i_metric)
continue;
dst_hold(&rt->dst);
read_unlock_bh(&table->tb6_lock);
return __ip6_del_rt(rt, &cfg->fc_nlinfo);
}
}
read_unlock_bh(&table->tb6_lock);
return err;
}
static void rt6_do_redirect(struct dst_entry *dst, struct sock *sk, struct sk_buff *skb)
{
struct net *net = dev_net(skb->dev);
struct netevent_redirect netevent;
struct rt6_info *rt, *nrt = NULL;
const struct in6_addr *target;
struct ndisc_options ndopts;
const struct in6_addr *dest;
struct neighbour *old_neigh;
struct inet6_dev *in6_dev;
struct neighbour *neigh;
struct icmp6hdr *icmph;
int optlen, on_link;
u8 *lladdr;
optlen = skb->tail - skb->transport_header;
optlen -= sizeof(struct icmp6hdr) + 2 * sizeof(struct in6_addr);
if (optlen < 0) {
net_dbg_ratelimited("rt6_do_redirect: packet too short\n");
return;
}
icmph = icmp6_hdr(skb);
target = (const struct in6_addr *) (icmph + 1);
dest = target + 1;
if (ipv6_addr_is_multicast(dest)) {
net_dbg_ratelimited("rt6_do_redirect: destination address is multicast\n");
return;
}
on_link = 0;
if (ipv6_addr_equal(dest, target)) {
on_link = 1;
} else if (ipv6_addr_type(target) !=
(IPV6_ADDR_UNICAST|IPV6_ADDR_LINKLOCAL)) {
net_dbg_ratelimited("rt6_do_redirect: target address is not link-local unicast\n");
return;
}
in6_dev = __in6_dev_get(skb->dev);
if (!in6_dev)
return;
if (in6_dev->cnf.forwarding || !in6_dev->cnf.accept_redirects)
return;
/* RFC2461 8.1:
* The IP source address of the Redirect MUST be the same as the current
* first-hop router for the specified ICMP Destination Address.
*/
if (!ndisc_parse_options((u8*)(dest + 1), optlen, &ndopts)) {
net_dbg_ratelimited("rt6_redirect: invalid ND options\n");
return;
}
lladdr = NULL;
if (ndopts.nd_opts_tgt_lladdr) {
lladdr = ndisc_opt_addr_data(ndopts.nd_opts_tgt_lladdr,
skb->dev);
if (!lladdr) {
net_dbg_ratelimited("rt6_redirect: invalid link-layer address length\n");
return;
}
}
rt = (struct rt6_info *) dst;
if (rt == net->ipv6.ip6_null_entry) {
net_dbg_ratelimited("rt6_redirect: source isn't a valid nexthop for redirect target\n");
return;
}
/* Redirect received -> path was valid.
* Look, redirects are sent only in response to data packets,
* so that this nexthop apparently is reachable. --ANK
*/
dst_confirm(&rt->dst);
neigh = __neigh_lookup(&nd_tbl, target, skb->dev, 1);
if (!neigh)
return;
/* Duplicate redirect: silently ignore. */
old_neigh = rt->n;
if (neigh == old_neigh)
goto out;
/*
* We have finally decided to accept it.
*/
neigh_update(neigh, lladdr, NUD_STALE,
NEIGH_UPDATE_F_WEAK_OVERRIDE|
NEIGH_UPDATE_F_OVERRIDE|
(on_link ? 0 : (NEIGH_UPDATE_F_OVERRIDE_ISROUTER|
NEIGH_UPDATE_F_ISROUTER))
);
nrt = ip6_rt_copy(rt, dest);
if (!nrt)
goto out;
nrt->rt6i_flags = RTF_GATEWAY|RTF_UP|RTF_DYNAMIC|RTF_CACHE;
if (on_link)
nrt->rt6i_flags &= ~RTF_GATEWAY;
nrt->rt6i_gateway = *(struct in6_addr *)neigh->primary_key;
nrt->n = neigh_clone(neigh);
if (ip6_ins_rt(nrt))
goto out;
netevent.old = &rt->dst;
netevent.old_neigh = old_neigh;
netevent.new = &nrt->dst;
netevent.new_neigh = neigh;
netevent.daddr = dest;
call_netevent_notifiers(NETEVENT_REDIRECT, &netevent);
if (rt->rt6i_flags & RTF_CACHE) {
rt = (struct rt6_info *) dst_clone(&rt->dst);
ip6_del_rt(rt);
}
out:
neigh_release(neigh);
}
/*
* Misc support functions
*/
static struct rt6_info *ip6_rt_copy(struct rt6_info *ort,
const struct in6_addr *dest)
{
struct net *net = dev_net(ort->dst.dev);
struct rt6_info *rt = ip6_dst_alloc(net, ort->dst.dev, 0,
ort->rt6i_table);
if (rt) {
rt->dst.input = ort->dst.input;
rt->dst.output = ort->dst.output;
rt->dst.flags |= DST_HOST;
rt->rt6i_dst.addr = *dest;
rt->rt6i_dst.plen = 128;
dst_copy_metrics(&rt->dst, &ort->dst);
rt->dst.error = ort->dst.error;
rt->rt6i_idev = ort->rt6i_idev;
if (rt->rt6i_idev)
in6_dev_hold(rt->rt6i_idev);
rt->dst.lastuse = jiffies;
rt->rt6i_gateway = ort->rt6i_gateway;
rt->rt6i_flags = ort->rt6i_flags;
if ((ort->rt6i_flags & (RTF_DEFAULT | RTF_ADDRCONF)) ==
(RTF_DEFAULT | RTF_ADDRCONF))
rt6_set_from(rt, ort);
else
rt6_clean_expires(rt);
rt->rt6i_metric = 0;
#ifdef CONFIG_IPV6_SUBTREES
memcpy(&rt->rt6i_src, &ort->rt6i_src, sizeof(struct rt6key));
#endif
memcpy(&rt->rt6i_prefsrc, &ort->rt6i_prefsrc, sizeof(struct rt6key));
rt->rt6i_table = ort->rt6i_table;
}
return rt;
}
#ifdef CONFIG_IPV6_ROUTE_INFO
static struct rt6_info *rt6_get_route_info(struct net *net,
const struct in6_addr *prefix, int prefixlen,
const struct in6_addr *gwaddr, int ifindex)
{
struct fib6_node *fn;
struct rt6_info *rt = NULL;
struct fib6_table *table;
table = fib6_get_table(net, RT6_TABLE_INFO);
if (!table)
return NULL;
read_lock_bh(&table->tb6_lock);
fn = fib6_locate(&table->tb6_root, prefix ,prefixlen, NULL, 0);
if (!fn)
goto out;
for (rt = fn->leaf; rt; rt = rt->dst.rt6_next) {
if (rt->dst.dev->ifindex != ifindex)
continue;
if ((rt->rt6i_flags & (RTF_ROUTEINFO|RTF_GATEWAY)) != (RTF_ROUTEINFO|RTF_GATEWAY))
continue;
if (!ipv6_addr_equal(&rt->rt6i_gateway, gwaddr))
continue;
dst_hold(&rt->dst);
break;
}
out:
read_unlock_bh(&table->tb6_lock);
return rt;
}
static struct rt6_info *rt6_add_route_info(struct net *net,
const struct in6_addr *prefix, int prefixlen,
const struct in6_addr *gwaddr, int ifindex,
unsigned int pref)
{
struct fib6_config cfg = {
.fc_table = RT6_TABLE_INFO,
.fc_metric = IP6_RT_PRIO_USER,
.fc_ifindex = ifindex,
.fc_dst_len = prefixlen,
.fc_flags = RTF_GATEWAY | RTF_ADDRCONF | RTF_ROUTEINFO |
RTF_UP | RTF_PREF(pref),
.fc_nlinfo.portid = 0,
.fc_nlinfo.nlh = NULL,
.fc_nlinfo.nl_net = net,
};
cfg.fc_dst = *prefix;
cfg.fc_gateway = *gwaddr;
/* We should treat it as a default route if prefix length is 0. */
if (!prefixlen)
cfg.fc_flags |= RTF_DEFAULT;
ip6_route_add(&cfg);
return rt6_get_route_info(net, prefix, prefixlen, gwaddr, ifindex);
}
#endif
struct rt6_info *rt6_get_dflt_router(const struct in6_addr *addr, struct net_device *dev)
{
struct rt6_info *rt;
struct fib6_table *table;
table = fib6_get_table(dev_net(dev), RT6_TABLE_DFLT);
if (!table)
return NULL;
read_lock_bh(&table->tb6_lock);
for (rt = table->tb6_root.leaf; rt; rt=rt->dst.rt6_next) {
if (dev == rt->dst.dev &&
((rt->rt6i_flags & (RTF_ADDRCONF | RTF_DEFAULT)) == (RTF_ADDRCONF | RTF_DEFAULT)) &&
ipv6_addr_equal(&rt->rt6i_gateway, addr))
break;
}
if (rt)
dst_hold(&rt->dst);
read_unlock_bh(&table->tb6_lock);
return rt;
}
struct rt6_info *rt6_add_dflt_router(const struct in6_addr *gwaddr,
struct net_device *dev,
unsigned int pref)
{
struct fib6_config cfg = {
.fc_table = RT6_TABLE_DFLT,
.fc_metric = IP6_RT_PRIO_USER,
.fc_ifindex = dev->ifindex,
.fc_flags = RTF_GATEWAY | RTF_ADDRCONF | RTF_DEFAULT |
RTF_UP | RTF_EXPIRES | RTF_PREF(pref),
.fc_nlinfo.portid = 0,
.fc_nlinfo.nlh = NULL,
.fc_nlinfo.nl_net = dev_net(dev),
};
cfg.fc_gateway = *gwaddr;
ip6_route_add(&cfg);
return rt6_get_dflt_router(gwaddr, dev);
}
void rt6_purge_dflt_routers(struct net *net)
{
struct rt6_info *rt;
struct fib6_table *table;
/* NOTE: Keep consistent with rt6_get_dflt_router */
table = fib6_get_table(net, RT6_TABLE_DFLT);
if (!table)
return;
restart:
read_lock_bh(&table->tb6_lock);
for (rt = table->tb6_root.leaf; rt; rt = rt->dst.rt6_next) {
if (rt->rt6i_flags & (RTF_DEFAULT | RTF_ADDRCONF)) {
dst_hold(&rt->dst);
read_unlock_bh(&table->tb6_lock);
ip6_del_rt(rt);
goto restart;
}
}
read_unlock_bh(&table->tb6_lock);
}
static void rtmsg_to_fib6_config(struct net *net,
struct in6_rtmsg *rtmsg,
struct fib6_config *cfg)
{
memset(cfg, 0, sizeof(*cfg));
cfg->fc_table = RT6_TABLE_MAIN;
cfg->fc_ifindex = rtmsg->rtmsg_ifindex;
cfg->fc_metric = rtmsg->rtmsg_metric;
cfg->fc_expires = rtmsg->rtmsg_info;
cfg->fc_dst_len = rtmsg->rtmsg_dst_len;
cfg->fc_src_len = rtmsg->rtmsg_src_len;
cfg->fc_flags = rtmsg->rtmsg_flags;
cfg->fc_nlinfo.nl_net = net;
cfg->fc_dst = rtmsg->rtmsg_dst;
cfg->fc_src = rtmsg->rtmsg_src;
cfg->fc_gateway = rtmsg->rtmsg_gateway;
}
int ipv6_route_ioctl(struct net *net, unsigned int cmd, void __user *arg)
{
struct fib6_config cfg;
struct in6_rtmsg rtmsg;
int err;
switch(cmd) {
case SIOCADDRT: /* Add a route */
case SIOCDELRT: /* Delete a route */
if (!capable(CAP_NET_ADMIN))
return -EPERM;
err = copy_from_user(&rtmsg, arg,
sizeof(struct in6_rtmsg));
if (err)
return -EFAULT;
rtmsg_to_fib6_config(net, &rtmsg, &cfg);
rtnl_lock();
switch (cmd) {
case SIOCADDRT:
err = ip6_route_add(&cfg);
break;
case SIOCDELRT:
err = ip6_route_del(&cfg);
break;
default:
err = -EINVAL;
}
rtnl_unlock();
return err;
}
return -EINVAL;
}
/*
* Drop the packet on the floor
*/
static int ip6_pkt_drop(struct sk_buff *skb, u8 code, int ipstats_mib_noroutes)
{
int type;
struct dst_entry *dst = skb_dst(skb);
switch (ipstats_mib_noroutes) {
case IPSTATS_MIB_INNOROUTES:
type = ipv6_addr_type(&ipv6_hdr(skb)->daddr);
if (type == IPV6_ADDR_ANY) {
IP6_INC_STATS(dev_net(dst->dev), ip6_dst_idev(dst),
IPSTATS_MIB_INADDRERRORS);
break;
}
/* FALLTHROUGH */
case IPSTATS_MIB_OUTNOROUTES:
IP6_INC_STATS(dev_net(dst->dev), ip6_dst_idev(dst),
ipstats_mib_noroutes);
break;
}
icmpv6_send(skb, ICMPV6_DEST_UNREACH, code, 0);
kfree_skb(skb);
return 0;
}
static int ip6_pkt_discard(struct sk_buff *skb)
{
return ip6_pkt_drop(skb, ICMPV6_NOROUTE, IPSTATS_MIB_INNOROUTES);
}
static int ip6_pkt_discard_out(struct sk_buff *skb)
{
skb->dev = skb_dst(skb)->dev;
return ip6_pkt_drop(skb, ICMPV6_NOROUTE, IPSTATS_MIB_OUTNOROUTES);
}
#ifdef CONFIG_IPV6_MULTIPLE_TABLES
static int ip6_pkt_prohibit(struct sk_buff *skb)
{
return ip6_pkt_drop(skb, ICMPV6_ADM_PROHIBITED, IPSTATS_MIB_INNOROUTES);
}
static int ip6_pkt_prohibit_out(struct sk_buff *skb)
{
skb->dev = skb_dst(skb)->dev;
return ip6_pkt_drop(skb, ICMPV6_ADM_PROHIBITED, IPSTATS_MIB_OUTNOROUTES);
}
#endif
/*
* Allocate a dst for local (unicast / anycast) address.
*/
struct rt6_info *addrconf_dst_alloc(struct inet6_dev *idev,
const struct in6_addr *addr,
bool anycast)
{
struct net *net = dev_net(idev->dev);
struct rt6_info *rt = ip6_dst_alloc(net, net->loopback_dev, 0, NULL);
int err;
if (!rt) {
net_warn_ratelimited("Maximum number of routes reached, consider increasing route/max_size\n");
return ERR_PTR(-ENOMEM);
}
in6_dev_hold(idev);
rt->dst.flags |= DST_HOST;
rt->dst.input = ip6_input;
rt->dst.output = ip6_output;
rt->rt6i_idev = idev;
rt->rt6i_flags = RTF_UP | RTF_NONEXTHOP;
if (anycast)
rt->rt6i_flags |= RTF_ANYCAST;
else
rt->rt6i_flags |= RTF_LOCAL;
err = rt6_bind_neighbour(rt, rt->dst.dev);
if (err) {
dst_free(&rt->dst);
return ERR_PTR(err);
}
rt->rt6i_dst.addr = *addr;
rt->rt6i_dst.plen = 128;
rt->rt6i_table = fib6_get_table(net, RT6_TABLE_LOCAL);
atomic_set(&rt->dst.__refcnt, 1);
return rt;
}
int ip6_route_get_saddr(struct net *net,
struct rt6_info *rt,
const struct in6_addr *daddr,
unsigned int prefs,
struct in6_addr *saddr)
{
struct inet6_dev *idev = ip6_dst_idev((struct dst_entry*)rt);
int err = 0;
if (rt->rt6i_prefsrc.plen)
*saddr = rt->rt6i_prefsrc.addr;
else
err = ipv6_dev_get_saddr(net, idev ? idev->dev : NULL,
daddr, prefs, saddr);
return err;
}
/* remove deleted ip from prefsrc entries */
struct arg_dev_net_ip {
struct net_device *dev;
struct net *net;
struct in6_addr *addr;
};
static int fib6_remove_prefsrc(struct rt6_info *rt, void *arg)
{
struct net_device *dev = ((struct arg_dev_net_ip *)arg)->dev;
struct net *net = ((struct arg_dev_net_ip *)arg)->net;
struct in6_addr *addr = ((struct arg_dev_net_ip *)arg)->addr;
if (((void *)rt->dst.dev == dev || !dev) &&
rt != net->ipv6.ip6_null_entry &&
ipv6_addr_equal(addr, &rt->rt6i_prefsrc.addr)) {
/* remove prefsrc entry */
rt->rt6i_prefsrc.plen = 0;
}
return 0;
}
void rt6_remove_prefsrc(struct inet6_ifaddr *ifp)
{
struct net *net = dev_net(ifp->idev->dev);
struct arg_dev_net_ip adni = {
.dev = ifp->idev->dev,
.net = net,
.addr = &ifp->addr,
};
fib6_clean_all(net, fib6_remove_prefsrc, 0, &adni);
}
struct arg_dev_net {
struct net_device *dev;
struct net *net;
};
static int fib6_ifdown(struct rt6_info *rt, void *arg)
{
const struct arg_dev_net *adn = arg;
const struct net_device *dev = adn->dev;
if ((rt->dst.dev == dev || !dev) &&
rt != adn->net->ipv6.ip6_null_entry)
return -1;
return 0;
}
void rt6_ifdown(struct net *net, struct net_device *dev)
{
struct arg_dev_net adn = {
.dev = dev,
.net = net,
};
fib6_clean_all(net, fib6_ifdown, 0, &adn);
icmp6_clean_all(fib6_ifdown, &adn);
}
struct rt6_mtu_change_arg {
struct net_device *dev;
unsigned int mtu;
};
static int rt6_mtu_change_route(struct rt6_info *rt, void *p_arg)
{
struct rt6_mtu_change_arg *arg = (struct rt6_mtu_change_arg *) p_arg;
struct inet6_dev *idev;
/* In IPv6 pmtu discovery is not optional,
so that RTAX_MTU lock cannot disable it.
We still use this lock to block changes
caused by addrconf/ndisc.
*/
idev = __in6_dev_get(arg->dev);
if (!idev)
return 0;
/* For administrative MTU increase, there is no way to discover
IPv6 PMTU increase, so PMTU increase should be updated here.
Since RFC 1981 doesn't include administrative MTU increase
update PMTU increase is a MUST. (i.e. jumbo frame)
*/
/*
If new MTU is less than route PMTU, this new MTU will be the
lowest MTU in the path, update the route PMTU to reflect PMTU
decreases; if new MTU is greater than route PMTU, and the
old MTU is the lowest MTU in the path, update the route PMTU
to reflect the increase. In this case if the other nodes' MTU
also have the lowest MTU, TOO BIG MESSAGE will be lead to
PMTU discouvery.
*/
if (rt->dst.dev == arg->dev &&
!dst_metric_locked(&rt->dst, RTAX_MTU) &&
(dst_mtu(&rt->dst) >= arg->mtu ||
(dst_mtu(&rt->dst) < arg->mtu &&
dst_mtu(&rt->dst) == idev->cnf.mtu6))) {
dst_metric_set(&rt->dst, RTAX_MTU, arg->mtu);
}
return 0;
}
void rt6_mtu_change(struct net_device *dev, unsigned int mtu)
{
struct rt6_mtu_change_arg arg = {
.dev = dev,
.mtu = mtu,
};
fib6_clean_all(dev_net(dev), rt6_mtu_change_route, 0, &arg);
}
static const struct nla_policy rtm_ipv6_policy[RTA_MAX+1] = {
[RTA_GATEWAY] = { .len = sizeof(struct in6_addr) },
[RTA_OIF] = { .type = NLA_U32 },
[RTA_IIF] = { .type = NLA_U32 },
[RTA_PRIORITY] = { .type = NLA_U32 },
[RTA_METRICS] = { .type = NLA_NESTED },
[RTA_MULTIPATH] = { .len = sizeof(struct rtnexthop) },
};
static int rtm_to_fib6_config(struct sk_buff *skb, struct nlmsghdr *nlh,
struct fib6_config *cfg)
{
struct rtmsg *rtm;
struct nlattr *tb[RTA_MAX+1];
int err;
err = nlmsg_parse(nlh, sizeof(*rtm), tb, RTA_MAX, rtm_ipv6_policy);
if (err < 0)
goto errout;
err = -EINVAL;
rtm = nlmsg_data(nlh);
memset(cfg, 0, sizeof(*cfg));
cfg->fc_table = rtm->rtm_table;
cfg->fc_dst_len = rtm->rtm_dst_len;
cfg->fc_src_len = rtm->rtm_src_len;
cfg->fc_flags = RTF_UP;
cfg->fc_protocol = rtm->rtm_protocol;
cfg->fc_type = rtm->rtm_type;
if (rtm->rtm_type == RTN_UNREACHABLE ||
rtm->rtm_type == RTN_BLACKHOLE ||
rtm->rtm_type == RTN_PROHIBIT ||
rtm->rtm_type == RTN_THROW)
cfg->fc_flags |= RTF_REJECT;
if (rtm->rtm_type == RTN_LOCAL)
cfg->fc_flags |= RTF_LOCAL;
cfg->fc_nlinfo.portid = NETLINK_CB(skb).portid;
cfg->fc_nlinfo.nlh = nlh;
cfg->fc_nlinfo.nl_net = sock_net(skb->sk);
if (tb[RTA_GATEWAY]) {
nla_memcpy(&cfg->fc_gateway, tb[RTA_GATEWAY], 16);
cfg->fc_flags |= RTF_GATEWAY;
}
if (tb[RTA_DST]) {
int plen = (rtm->rtm_dst_len + 7) >> 3;
if (nla_len(tb[RTA_DST]) < plen)
goto errout;
nla_memcpy(&cfg->fc_dst, tb[RTA_DST], plen);
}
if (tb[RTA_SRC]) {
int plen = (rtm->rtm_src_len + 7) >> 3;
if (nla_len(tb[RTA_SRC]) < plen)
goto errout;
nla_memcpy(&cfg->fc_src, tb[RTA_SRC], plen);
}
if (tb[RTA_PREFSRC])
nla_memcpy(&cfg->fc_prefsrc, tb[RTA_PREFSRC], 16);
if (tb[RTA_OIF])
cfg->fc_ifindex = nla_get_u32(tb[RTA_OIF]);
if (tb[RTA_PRIORITY])
cfg->fc_metric = nla_get_u32(tb[RTA_PRIORITY]);
if (tb[RTA_METRICS]) {
cfg->fc_mx = nla_data(tb[RTA_METRICS]);
cfg->fc_mx_len = nla_len(tb[RTA_METRICS]);
}
if (tb[RTA_TABLE])
cfg->fc_table = nla_get_u32(tb[RTA_TABLE]);
if (tb[RTA_MULTIPATH]) {
cfg->fc_mp = nla_data(tb[RTA_MULTIPATH]);
cfg->fc_mp_len = nla_len(tb[RTA_MULTIPATH]);
}
err = 0;
errout:
return err;
}
static int ip6_route_multipath(struct fib6_config *cfg, int add)
{
struct fib6_config r_cfg;
struct rtnexthop *rtnh;
int remaining;
int attrlen;
int err = 0, last_err = 0;
beginning:
rtnh = (struct rtnexthop *)cfg->fc_mp;
remaining = cfg->fc_mp_len;
/* Parse a Multipath Entry */
while (rtnh_ok(rtnh, remaining)) {
memcpy(&r_cfg, cfg, sizeof(*cfg));
if (rtnh->rtnh_ifindex)
r_cfg.fc_ifindex = rtnh->rtnh_ifindex;
attrlen = rtnh_attrlen(rtnh);
if (attrlen > 0) {
struct nlattr *nla, *attrs = rtnh_attrs(rtnh);
nla = nla_find(attrs, attrlen, RTA_GATEWAY);
if (nla) {
nla_memcpy(&r_cfg.fc_gateway, nla, 16);
r_cfg.fc_flags |= RTF_GATEWAY;
}
}
err = add ? ip6_route_add(&r_cfg) : ip6_route_del(&r_cfg);
if (err) {
last_err = err;
/* If we are trying to remove a route, do not stop the
* loop when ip6_route_del() fails (because next hop is
* already gone), we should try to remove all next hops.
*/
if (add) {
/* If add fails, we should try to delete all
* next hops that have been already added.
*/
add = 0;
goto beginning;
}
}
/* Because each route is added like a single route we remove
* this flag after the first nexthop (if there is a collision,
* we have already fail to add the first nexthop:
* fib6_add_rt2node() has reject it).
*/
cfg->fc_nlinfo.nlh->nlmsg_flags &= ~NLM_F_EXCL;
rtnh = rtnh_next(rtnh, &remaining);
}
return last_err;
}
static int inet6_rtm_delroute(struct sk_buff *skb, struct nlmsghdr* nlh, void *arg)
{
struct fib6_config cfg;
int err;
err = rtm_to_fib6_config(skb, nlh, &cfg);
if (err < 0)
return err;
if (cfg.fc_mp)
return ip6_route_multipath(&cfg, 0);
else
return ip6_route_del(&cfg);
}
static int inet6_rtm_newroute(struct sk_buff *skb, struct nlmsghdr* nlh, void *arg)
{
struct fib6_config cfg;
int err;
err = rtm_to_fib6_config(skb, nlh, &cfg);
if (err < 0)
return err;
if (cfg.fc_mp)
return ip6_route_multipath(&cfg, 1);
else
return ip6_route_add(&cfg);
}
static inline size_t rt6_nlmsg_size(void)
{
return NLMSG_ALIGN(sizeof(struct rtmsg))
+ nla_total_size(16) /* RTA_SRC */
+ nla_total_size(16) /* RTA_DST */
+ nla_total_size(16) /* RTA_GATEWAY */
+ nla_total_size(16) /* RTA_PREFSRC */
+ nla_total_size(4) /* RTA_TABLE */
+ nla_total_size(4) /* RTA_IIF */
+ nla_total_size(4) /* RTA_OIF */
+ nla_total_size(4) /* RTA_PRIORITY */
+ RTAX_MAX * nla_total_size(4) /* RTA_METRICS */
+ nla_total_size(sizeof(struct rta_cacheinfo));
}
static int rt6_fill_node(struct net *net,
struct sk_buff *skb, struct rt6_info *rt,
struct in6_addr *dst, struct in6_addr *src,
int iif, int type, u32 portid, u32 seq,
int prefix, int nowait, unsigned int flags)
{
struct rtmsg *rtm;
struct nlmsghdr *nlh;
long expires;
u32 table;
struct neighbour *n;
if (prefix) { /* user wants prefix routes only */
if (!(rt->rt6i_flags & RTF_PREFIX_RT)) {
/* success since this is not a prefix route */
return 1;
}
}
nlh = nlmsg_put(skb, portid, seq, type, sizeof(*rtm), flags);
if (!nlh)
return -EMSGSIZE;
rtm = nlmsg_data(nlh);
rtm->rtm_family = AF_INET6;
rtm->rtm_dst_len = rt->rt6i_dst.plen;
rtm->rtm_src_len = rt->rt6i_src.plen;
rtm->rtm_tos = 0;
if (rt->rt6i_table)
table = rt->rt6i_table->tb6_id;
else
table = RT6_TABLE_UNSPEC;
rtm->rtm_table = table;
if (nla_put_u32(skb, RTA_TABLE, table))
goto nla_put_failure;
if (rt->rt6i_flags & RTF_REJECT) {
switch (rt->dst.error) {
case -EINVAL:
rtm->rtm_type = RTN_BLACKHOLE;
break;
case -EACCES:
rtm->rtm_type = RTN_PROHIBIT;
break;
case -EAGAIN:
rtm->rtm_type = RTN_THROW;
break;
default:
rtm->rtm_type = RTN_UNREACHABLE;
break;
}
}
else if (rt->rt6i_flags & RTF_LOCAL)
rtm->rtm_type = RTN_LOCAL;
else if (rt->dst.dev && (rt->dst.dev->flags & IFF_LOOPBACK))
rtm->rtm_type = RTN_LOCAL;
else
rtm->rtm_type = RTN_UNICAST;
rtm->rtm_flags = 0;
rtm->rtm_scope = RT_SCOPE_UNIVERSE;
rtm->rtm_protocol = rt->rt6i_protocol;
if (rt->rt6i_flags & RTF_DYNAMIC)
rtm->rtm_protocol = RTPROT_REDIRECT;
else if (rt->rt6i_flags & RTF_ADDRCONF) {
if (rt->rt6i_flags & (RTF_DEFAULT | RTF_ROUTEINFO))
rtm->rtm_protocol = RTPROT_RA;
else
rtm->rtm_protocol = RTPROT_KERNEL;
}
if (rt->rt6i_flags & RTF_CACHE)
rtm->rtm_flags |= RTM_F_CLONED;
if (dst) {
if (nla_put(skb, RTA_DST, 16, dst))
goto nla_put_failure;
rtm->rtm_dst_len = 128;
} else if (rtm->rtm_dst_len)
if (nla_put(skb, RTA_DST, 16, &rt->rt6i_dst.addr))
goto nla_put_failure;
#ifdef CONFIG_IPV6_SUBTREES
if (src) {
if (nla_put(skb, RTA_SRC, 16, src))
goto nla_put_failure;
rtm->rtm_src_len = 128;
} else if (rtm->rtm_src_len &&
nla_put(skb, RTA_SRC, 16, &rt->rt6i_src.addr))
goto nla_put_failure;
#endif
if (iif) {
#ifdef CONFIG_IPV6_MROUTE
if (ipv6_addr_is_multicast(&rt->rt6i_dst.addr)) {
int err = ip6mr_get_route(net, skb, rtm, nowait);
if (err <= 0) {
if (!nowait) {
if (err == 0)
return 0;
goto nla_put_failure;
} else {
if (err == -EMSGSIZE)
goto nla_put_failure;
}
}
} else
#endif
if (nla_put_u32(skb, RTA_IIF, iif))
goto nla_put_failure;
} else if (dst) {
struct in6_addr saddr_buf;
if (ip6_route_get_saddr(net, rt, dst, 0, &saddr_buf) == 0 &&
nla_put(skb, RTA_PREFSRC, 16, &saddr_buf))
goto nla_put_failure;
}
if (rt->rt6i_prefsrc.plen) {
struct in6_addr saddr_buf;
saddr_buf = rt->rt6i_prefsrc.addr;
if (nla_put(skb, RTA_PREFSRC, 16, &saddr_buf))
goto nla_put_failure;
}
if (rtnetlink_put_metrics(skb, dst_metrics_ptr(&rt->dst)) < 0)
goto nla_put_failure;
n = rt->n;
if (n) {
if (nla_put(skb, RTA_GATEWAY, 16, &n->primary_key) < 0)
goto nla_put_failure;
}
if (rt->dst.dev &&
nla_put_u32(skb, RTA_OIF, rt->dst.dev->ifindex))
goto nla_put_failure;
if (nla_put_u32(skb, RTA_PRIORITY, rt->rt6i_metric))
goto nla_put_failure;
expires = (rt->rt6i_flags & RTF_EXPIRES) ? rt->dst.expires - jiffies : 0;
if (rtnl_put_cacheinfo(skb, &rt->dst, 0, expires, rt->dst.error) < 0)
goto nla_put_failure;
return nlmsg_end(skb, nlh);
nla_put_failure:
nlmsg_cancel(skb, nlh);
return -EMSGSIZE;
}
int rt6_dump_route(struct rt6_info *rt, void *p_arg)
{
struct rt6_rtnl_dump_arg *arg = (struct rt6_rtnl_dump_arg *) p_arg;
int prefix;
if (nlmsg_len(arg->cb->nlh) >= sizeof(struct rtmsg)) {
struct rtmsg *rtm = nlmsg_data(arg->cb->nlh);
prefix = (rtm->rtm_flags & RTM_F_PREFIX) != 0;
} else
prefix = 0;
return rt6_fill_node(arg->net,
arg->skb, rt, NULL, NULL, 0, RTM_NEWROUTE,
NETLINK_CB(arg->cb->skb).portid, arg->cb->nlh->nlmsg_seq,
prefix, 0, NLM_F_MULTI);
}
static int inet6_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr* nlh, void *arg)
{
struct net *net = sock_net(in_skb->sk);
struct nlattr *tb[RTA_MAX+1];
struct rt6_info *rt;
struct sk_buff *skb;
struct rtmsg *rtm;
struct flowi6 fl6;
int err, iif = 0, oif = 0;
err = nlmsg_parse(nlh, sizeof(*rtm), tb, RTA_MAX, rtm_ipv6_policy);
if (err < 0)
goto errout;
err = -EINVAL;
memset(&fl6, 0, sizeof(fl6));
if (tb[RTA_SRC]) {
if (nla_len(tb[RTA_SRC]) < sizeof(struct in6_addr))
goto errout;
fl6.saddr = *(struct in6_addr *)nla_data(tb[RTA_SRC]);
}
if (tb[RTA_DST]) {
if (nla_len(tb[RTA_DST]) < sizeof(struct in6_addr))
goto errout;
fl6.daddr = *(struct in6_addr *)nla_data(tb[RTA_DST]);
}
if (tb[RTA_IIF])
iif = nla_get_u32(tb[RTA_IIF]);
if (tb[RTA_OIF])
oif = nla_get_u32(tb[RTA_OIF]);
if (iif) {
struct net_device *dev;
int flags = 0;
dev = __dev_get_by_index(net, iif);
if (!dev) {
err = -ENODEV;
goto errout;
}
fl6.flowi6_iif = iif;
if (!ipv6_addr_any(&fl6.saddr))
flags |= RT6_LOOKUP_F_HAS_SADDR;
rt = (struct rt6_info *)ip6_route_input_lookup(net, dev, &fl6,
flags);
} else {
fl6.flowi6_oif = oif;
rt = (struct rt6_info *)ip6_route_output(net, NULL, &fl6);
}
skb = alloc_skb(NLMSG_GOODSIZE, GFP_KERNEL);
if (!skb) {
dst_release(&rt->dst);
err = -ENOBUFS;
goto errout;
}
/* Reserve room for dummy headers, this skb can pass
through good chunk of routing engine.
*/
skb_reset_mac_header(skb);
skb_reserve(skb, MAX_HEADER + sizeof(struct ipv6hdr));
skb_dst_set(skb, &rt->dst);
err = rt6_fill_node(net, skb, rt, &fl6.daddr, &fl6.saddr, iif,
RTM_NEWROUTE, NETLINK_CB(in_skb).portid,
nlh->nlmsg_seq, 0, 0, 0);
if (err < 0) {
kfree_skb(skb);
goto errout;
}
err = rtnl_unicast(skb, net, NETLINK_CB(in_skb).portid);
errout:
return err;
}
void inet6_rt_notify(int event, struct rt6_info *rt, struct nl_info *info)
{
struct sk_buff *skb;
struct net *net = info->nl_net;
u32 seq;
int err;
err = -ENOBUFS;
seq = info->nlh ? info->nlh->nlmsg_seq : 0;
skb = nlmsg_new(rt6_nlmsg_size(), gfp_any());
if (!skb)
goto errout;
err = rt6_fill_node(net, skb, rt, NULL, NULL, 0,
event, info->portid, seq, 0, 0, 0);
if (err < 0) {
/* -EMSGSIZE implies BUG in rt6_nlmsg_size() */
WARN_ON(err == -EMSGSIZE);
kfree_skb(skb);
goto errout;
}
rtnl_notify(skb, net, info->portid, RTNLGRP_IPV6_ROUTE,
2009-02-25 07:18:28 +00:00
info->nlh, gfp_any());
return;
errout:
if (err < 0)
rtnl_set_sk_err(net, RTNLGRP_IPV6_ROUTE, err);
}
static int ip6_route_dev_notify(struct notifier_block *this,
unsigned long event, void *data)
{
struct net_device *dev = (struct net_device *)data;
struct net *net = dev_net(dev);
if (event == NETDEV_REGISTER && (dev->flags & IFF_LOOPBACK)) {
net->ipv6.ip6_null_entry->dst.dev = dev;
net->ipv6.ip6_null_entry->rt6i_idev = in6_dev_get(dev);
#ifdef CONFIG_IPV6_MULTIPLE_TABLES
net->ipv6.ip6_prohibit_entry->dst.dev = dev;
net->ipv6.ip6_prohibit_entry->rt6i_idev = in6_dev_get(dev);
net->ipv6.ip6_blk_hole_entry->dst.dev = dev;
net->ipv6.ip6_blk_hole_entry->rt6i_idev = in6_dev_get(dev);
#endif
}
return NOTIFY_OK;
}
/*
* /proc
*/
#ifdef CONFIG_PROC_FS
struct rt6_proc_arg
{
char *buffer;
int offset;
int length;
int skip;
int len;
};
static int rt6_info_route(struct rt6_info *rt, void *p_arg)
{
struct seq_file *m = p_arg;
struct neighbour *n;
seq_printf(m, "%pi6 %02x ", &rt->rt6i_dst.addr, rt->rt6i_dst.plen);
#ifdef CONFIG_IPV6_SUBTREES
seq_printf(m, "%pi6 %02x ", &rt->rt6i_src.addr, rt->rt6i_src.plen);
#else
seq_puts(m, "00000000000000000000000000000000 00 ");
#endif
n = rt->n;
if (n) {
seq_printf(m, "%pi6", n->primary_key);
} else {
seq_puts(m, "00000000000000000000000000000000");
}
seq_printf(m, " %08x %08x %08x %08x %8s\n",
rt->rt6i_metric, atomic_read(&rt->dst.__refcnt),
rt->dst.__use, rt->rt6i_flags,
rt->dst.dev ? rt->dst.dev->name : "");
return 0;
}
static int ipv6_route_show(struct seq_file *m, void *v)
{
struct net *net = (struct net *)m->private;
IPv6: Avoid taking write lock for /proc/net/ipv6_route During some debugging I needed to look into how /proc/net/ipv6_route operated and in my digging I found its calling fib6_clean_all() which uses "write_lock_bh(&table->tb6_lock)" before doing the walk of the table. I found this on 2.6.32, but reading the code I believe the same basic idea exists currently. Looking at the rtnetlink code they are only calling "read_lock_bh(&table->tb6_lock);" via fib6_dump_table(). While I realize reading from proc isn't the recommended way of fetching the ipv6 route table; taking a write lock seems unnecessary and would probably cause network performance issues. To verify this I loaded up the ipv6 route table and then ran iperf in 3 cases: * doing nothing * reading ipv6 route table via proc (while :; do cat /proc/net/ipv6_route > /dev/null; done) * reading ipv6 route table via rtnetlink (while :; do ip -6 route show table all > /dev/null; done) * Load the ipv6 route table up with: * for ((i = 0;i < 4000;i++)); do ip route add unreachable 2000::$i; done * iperf commands: * client: iperf -i 1 -V -c <ipv6 addr> * server: iperf -V -s * iperf results - 3 runs each (in Mbits/sec) * nothing: client: 927,927,927 server: 927,927,927 * proc: client: 179,97,96,113 server: 142,112,133 * iproute: client: 928,927,928 server: 927,927,927 lock_stat shows taking the write lock is causing the slowdown. Using this info I decided to write a version of fib6_clean_all() which replaces write_lock_bh(&table->tb6_lock) with read_lock_bh(&table->tb6_lock). With this new function I see the same results as with my rtnetlink iperf test. Signed-off-by: Josh Hunt <joshhunt00@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2011-12-28 13:23:07 +00:00
fib6_clean_all_ro(net, rt6_info_route, 0, m);
return 0;
}
static int ipv6_route_open(struct inode *inode, struct file *file)
{
return single_open_net(inode, file, ipv6_route_show);
}
static const struct file_operations ipv6_route_proc_fops = {
.owner = THIS_MODULE,
.open = ipv6_route_open,
.read = seq_read,
.llseek = seq_lseek,
.release = single_release_net,
};
static int rt6_stats_seq_show(struct seq_file *seq, void *v)
{
struct net *net = (struct net *)seq->private;
seq_printf(seq, "%04x %04x %04x %04x %04x %04x %04x\n",
net->ipv6.rt6_stats->fib_nodes,
net->ipv6.rt6_stats->fib_route_nodes,
net->ipv6.rt6_stats->fib_rt_alloc,
net->ipv6.rt6_stats->fib_rt_entries,
net->ipv6.rt6_stats->fib_rt_cache,
dst_entries_get_slow(&net->ipv6.ip6_dst_ops),
net->ipv6.rt6_stats->fib_discarded_routes);
return 0;
}
static int rt6_stats_seq_open(struct inode *inode, struct file *file)
{
return single_open_net(inode, file, rt6_stats_seq_show);
}
static const struct file_operations rt6_stats_seq_fops = {
.owner = THIS_MODULE,
.open = rt6_stats_seq_open,
.read = seq_read,
.llseek = seq_lseek,
.release = single_release_net,
};
#endif /* CONFIG_PROC_FS */
#ifdef CONFIG_SYSCTL
static
int ipv6_sysctl_rtcache_flush(ctl_table *ctl, int write,
void __user *buffer, size_t *lenp, loff_t *ppos)
{
struct net *net;
int delay;
if (!write)
return -EINVAL;
net = (struct net *)ctl->extra1;
delay = net->ipv6.sysctl.flush_delay;
proc_dointvec(ctl, write, buffer, lenp, ppos);
fib6_run_gc(delay <= 0 ? ~0UL : (unsigned long)delay, net);
return 0;
}
ctl_table ipv6_route_table_template[] = {
{
.procname = "flush",
.data = &init_net.ipv6.sysctl.flush_delay,
.maxlen = sizeof(int),
.mode = 0200,
.proc_handler = ipv6_sysctl_rtcache_flush
},
{
.procname = "gc_thresh",
.data = &ip6_dst_ops_template.gc_thresh,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec,
},
{
.procname = "max_size",
.data = &init_net.ipv6.sysctl.ip6_rt_max_size,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec,
},
{
.procname = "gc_min_interval",
.data = &init_net.ipv6.sysctl.ip6_rt_gc_min_interval,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec_jiffies,
},
{
.procname = "gc_timeout",
.data = &init_net.ipv6.sysctl.ip6_rt_gc_timeout,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec_jiffies,
},
{
.procname = "gc_interval",
.data = &init_net.ipv6.sysctl.ip6_rt_gc_interval,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec_jiffies,
},
{
.procname = "gc_elasticity",
.data = &init_net.ipv6.sysctl.ip6_rt_gc_elasticity,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec,
},
{
.procname = "mtu_expires",
.data = &init_net.ipv6.sysctl.ip6_rt_mtu_expires,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec_jiffies,
},
{
.procname = "min_adv_mss",
.data = &init_net.ipv6.sysctl.ip6_rt_min_advmss,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec,
},
{
.procname = "gc_min_interval_ms",
.data = &init_net.ipv6.sysctl.ip6_rt_gc_min_interval,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec_ms_jiffies,
},
{ }
};
struct ctl_table * __net_init ipv6_route_sysctl_init(struct net *net)
{
struct ctl_table *table;
table = kmemdup(ipv6_route_table_template,
sizeof(ipv6_route_table_template),
GFP_KERNEL);
if (table) {
table[0].data = &net->ipv6.sysctl.flush_delay;
table[0].extra1 = net;
table[1].data = &net->ipv6.ip6_dst_ops.gc_thresh;
table[2].data = &net->ipv6.sysctl.ip6_rt_max_size;
table[3].data = &net->ipv6.sysctl.ip6_rt_gc_min_interval;
table[4].data = &net->ipv6.sysctl.ip6_rt_gc_timeout;
table[5].data = &net->ipv6.sysctl.ip6_rt_gc_interval;
table[6].data = &net->ipv6.sysctl.ip6_rt_gc_elasticity;
table[7].data = &net->ipv6.sysctl.ip6_rt_mtu_expires;
table[8].data = &net->ipv6.sysctl.ip6_rt_min_advmss;
table[9].data = &net->ipv6.sysctl.ip6_rt_gc_min_interval;
}
return table;
}
#endif
static int __net_init ip6_route_net_init(struct net *net)
{
int ret = -ENOMEM;
memcpy(&net->ipv6.ip6_dst_ops, &ip6_dst_ops_template,
sizeof(net->ipv6.ip6_dst_ops));
if (dst_entries_init(&net->ipv6.ip6_dst_ops) < 0)
goto out_ip6_dst_ops;
net->ipv6.ip6_null_entry = kmemdup(&ip6_null_entry_template,
sizeof(*net->ipv6.ip6_null_entry),
GFP_KERNEL);
if (!net->ipv6.ip6_null_entry)
goto out_ip6_dst_entries;
net->ipv6.ip6_null_entry->dst.path =
(struct dst_entry *)net->ipv6.ip6_null_entry;
net->ipv6.ip6_null_entry->dst.ops = &net->ipv6.ip6_dst_ops;
net: Implement read-only protection and COW'ing of metrics. Routing metrics are now copy-on-write. Initially a route entry points it's metrics at a read-only location. If a routing table entry exists, it will point there. Else it will point at the all zero metric place-holder called 'dst_default_metrics'. The writeability state of the metrics is stored in the low bits of the metrics pointer, we have two bits left to spare if we want to store more states. For the initial implementation, COW is implemented simply via kmalloc. However future enhancements will change this to place the writable metrics somewhere else, in order to increase sharing. Very likely this "somewhere else" will be the inetpeer cache. Note also that this means that metrics updates may transiently fail if we cannot COW the metrics successfully. But even by itself, this patch should decrease memory usage and increase cache locality especially for routing workloads. In those cases the read-only metric copies stay in place and never get written to. TCP workloads where metrics get updated, and those rare cases where PMTU triggers occur, will take a very slight performance hit. But that hit will be alleviated when the long-term writable metrics move to a more sharable location. Since the metrics storage went from a u32 array of RTAX_MAX entries to what is essentially a pointer, some retooling of the dst_entry layout was necessary. Most importantly, we need to preserve the alignment of the reference count so that it doesn't share cache lines with the read-mostly state, as per Eric Dumazet's alignment assertion checks. The only non-trivial bit here is the move of the 'flags' member into the writeable cacheline. This is OK since we are always accessing the flags around the same moment when we made a modification to the reference count. Signed-off-by: David S. Miller <davem@davemloft.net>
2011-01-27 04:51:05 +00:00
dst_init_metrics(&net->ipv6.ip6_null_entry->dst,
ip6_template_metrics, true);
#ifdef CONFIG_IPV6_MULTIPLE_TABLES
net->ipv6.ip6_prohibit_entry = kmemdup(&ip6_prohibit_entry_template,
sizeof(*net->ipv6.ip6_prohibit_entry),
GFP_KERNEL);
if (!net->ipv6.ip6_prohibit_entry)
goto out_ip6_null_entry;
net->ipv6.ip6_prohibit_entry->dst.path =
(struct dst_entry *)net->ipv6.ip6_prohibit_entry;
net->ipv6.ip6_prohibit_entry->dst.ops = &net->ipv6.ip6_dst_ops;
net: Implement read-only protection and COW'ing of metrics. Routing metrics are now copy-on-write. Initially a route entry points it's metrics at a read-only location. If a routing table entry exists, it will point there. Else it will point at the all zero metric place-holder called 'dst_default_metrics'. The writeability state of the metrics is stored in the low bits of the metrics pointer, we have two bits left to spare if we want to store more states. For the initial implementation, COW is implemented simply via kmalloc. However future enhancements will change this to place the writable metrics somewhere else, in order to increase sharing. Very likely this "somewhere else" will be the inetpeer cache. Note also that this means that metrics updates may transiently fail if we cannot COW the metrics successfully. But even by itself, this patch should decrease memory usage and increase cache locality especially for routing workloads. In those cases the read-only metric copies stay in place and never get written to. TCP workloads where metrics get updated, and those rare cases where PMTU triggers occur, will take a very slight performance hit. But that hit will be alleviated when the long-term writable metrics move to a more sharable location. Since the metrics storage went from a u32 array of RTAX_MAX entries to what is essentially a pointer, some retooling of the dst_entry layout was necessary. Most importantly, we need to preserve the alignment of the reference count so that it doesn't share cache lines with the read-mostly state, as per Eric Dumazet's alignment assertion checks. The only non-trivial bit here is the move of the 'flags' member into the writeable cacheline. This is OK since we are always accessing the flags around the same moment when we made a modification to the reference count. Signed-off-by: David S. Miller <davem@davemloft.net>
2011-01-27 04:51:05 +00:00
dst_init_metrics(&net->ipv6.ip6_prohibit_entry->dst,
ip6_template_metrics, true);
net->ipv6.ip6_blk_hole_entry = kmemdup(&ip6_blk_hole_entry_template,
sizeof(*net->ipv6.ip6_blk_hole_entry),
GFP_KERNEL);
if (!net->ipv6.ip6_blk_hole_entry)
goto out_ip6_prohibit_entry;
net->ipv6.ip6_blk_hole_entry->dst.path =
(struct dst_entry *)net->ipv6.ip6_blk_hole_entry;
net->ipv6.ip6_blk_hole_entry->dst.ops = &net->ipv6.ip6_dst_ops;
net: Implement read-only protection and COW'ing of metrics. Routing metrics are now copy-on-write. Initially a route entry points it's metrics at a read-only location. If a routing table entry exists, it will point there. Else it will point at the all zero metric place-holder called 'dst_default_metrics'. The writeability state of the metrics is stored in the low bits of the metrics pointer, we have two bits left to spare if we want to store more states. For the initial implementation, COW is implemented simply via kmalloc. However future enhancements will change this to place the writable metrics somewhere else, in order to increase sharing. Very likely this "somewhere else" will be the inetpeer cache. Note also that this means that metrics updates may transiently fail if we cannot COW the metrics successfully. But even by itself, this patch should decrease memory usage and increase cache locality especially for routing workloads. In those cases the read-only metric copies stay in place and never get written to. TCP workloads where metrics get updated, and those rare cases where PMTU triggers occur, will take a very slight performance hit. But that hit will be alleviated when the long-term writable metrics move to a more sharable location. Since the metrics storage went from a u32 array of RTAX_MAX entries to what is essentially a pointer, some retooling of the dst_entry layout was necessary. Most importantly, we need to preserve the alignment of the reference count so that it doesn't share cache lines with the read-mostly state, as per Eric Dumazet's alignment assertion checks. The only non-trivial bit here is the move of the 'flags' member into the writeable cacheline. This is OK since we are always accessing the flags around the same moment when we made a modification to the reference count. Signed-off-by: David S. Miller <davem@davemloft.net>
2011-01-27 04:51:05 +00:00
dst_init_metrics(&net->ipv6.ip6_blk_hole_entry->dst,
ip6_template_metrics, true);
#endif
net->ipv6.sysctl.flush_delay = 0;
net->ipv6.sysctl.ip6_rt_max_size = 4096;
net->ipv6.sysctl.ip6_rt_gc_min_interval = HZ / 2;
net->ipv6.sysctl.ip6_rt_gc_timeout = 60*HZ;
net->ipv6.sysctl.ip6_rt_gc_interval = 30*HZ;
net->ipv6.sysctl.ip6_rt_gc_elasticity = 9;
net->ipv6.sysctl.ip6_rt_mtu_expires = 10*60*HZ;
net->ipv6.sysctl.ip6_rt_min_advmss = IPV6_MIN_MTU - 20 - 40;
net->ipv6.ip6_rt_gc_expire = 30*HZ;
ret = 0;
out:
return ret;
#ifdef CONFIG_IPV6_MULTIPLE_TABLES
out_ip6_prohibit_entry:
kfree(net->ipv6.ip6_prohibit_entry);
out_ip6_null_entry:
kfree(net->ipv6.ip6_null_entry);
#endif
out_ip6_dst_entries:
dst_entries_destroy(&net->ipv6.ip6_dst_ops);
out_ip6_dst_ops:
goto out;
}
static void __net_exit ip6_route_net_exit(struct net *net)
{
kfree(net->ipv6.ip6_null_entry);
#ifdef CONFIG_IPV6_MULTIPLE_TABLES
kfree(net->ipv6.ip6_prohibit_entry);
kfree(net->ipv6.ip6_blk_hole_entry);
#endif
dst_entries_destroy(&net->ipv6.ip6_dst_ops);
}
static int __net_init ip6_route_net_init_late(struct net *net)
{
#ifdef CONFIG_PROC_FS
proc_net_fops_create(net, "ipv6_route", 0, &ipv6_route_proc_fops);
proc_net_fops_create(net, "rt6_stats", S_IRUGO, &rt6_stats_seq_fops);
#endif
return 0;
}
static void __net_exit ip6_route_net_exit_late(struct net *net)
{
#ifdef CONFIG_PROC_FS
proc_net_remove(net, "ipv6_route");
proc_net_remove(net, "rt6_stats");
#endif
}
static struct pernet_operations ip6_route_net_ops = {
.init = ip6_route_net_init,
.exit = ip6_route_net_exit,
};
static int __net_init ipv6_inetpeer_init(struct net *net)
{
struct inet_peer_base *bp = kmalloc(sizeof(*bp), GFP_KERNEL);
if (!bp)
return -ENOMEM;
inet_peer_base_init(bp);
net->ipv6.peers = bp;
return 0;
}
static void __net_exit ipv6_inetpeer_exit(struct net *net)
{
struct inet_peer_base *bp = net->ipv6.peers;
net->ipv6.peers = NULL;
inetpeer_invalidate_tree(bp);
kfree(bp);
}
static struct pernet_operations ipv6_inetpeer_ops = {
.init = ipv6_inetpeer_init,
.exit = ipv6_inetpeer_exit,
};
static struct pernet_operations ip6_route_net_late_ops = {
.init = ip6_route_net_init_late,
.exit = ip6_route_net_exit_late,
};
static struct notifier_block ip6_route_dev_notifier = {
.notifier_call = ip6_route_dev_notify,
.priority = 0,
};
int __init ip6_route_init(void)
{
int ret;
ret = -ENOMEM;
ip6_dst_ops_template.kmem_cachep =
kmem_cache_create("ip6_dst_cache", sizeof(struct rt6_info), 0,
SLAB_HWCACHE_ALIGN, NULL);
if (!ip6_dst_ops_template.kmem_cachep)
goto out;
ret = dst_entries_init(&ip6_dst_blackhole_ops);
if (ret)
goto out_kmem_cache;
ret = register_pernet_subsys(&ipv6_inetpeer_ops);
if (ret)
goto out_dst_entries;
ret = register_pernet_subsys(&ip6_route_net_ops);
if (ret)
goto out_register_inetpeer;
XFRM,IPv6: initialize ip6_dst_blackhole_ops.kmem_cachep ip6_dst_blackhole_ops.kmem_cachep is not expected to be NULL (i.e. to be initialized) when dst_alloc() is called from ip6_dst_blackhole(). Otherwise, it results in the following (xfrm_larval_drop is now set to 1 by default): [ 78.697642] Unable to handle kernel paging request for data at address 0x0000004c [ 78.703449] Faulting instruction address: 0xc0097f54 [ 78.786896] Oops: Kernel access of bad area, sig: 11 [#1] [ 78.792791] PowerMac [ 78.798383] Modules linked in: btusb usbhid bluetooth b43 mac80211 cfg80211 ehci_hcd ohci_hcd sungem sungem_phy usbcore ssb [ 78.804263] NIP: c0097f54 LR: c0334a28 CTR: c002d430 [ 78.809997] REGS: eef19ad0 TRAP: 0300 Not tainted (2.6.27-rc5) [ 78.815743] MSR: 00001032 <ME,IR,DR> CR: 22242482 XER: 20000000 [ 78.821550] DAR: 0000004c, DSISR: 40000000 [ 78.827278] TASK = eef0df40[3035] 'mip6d' THREAD: eef18000 [ 78.827408] GPR00: 00001032 eef19b80 eef0df40 00000000 00008020 eef19c30 00000001 00000000 [ 78.833249] GPR08: eee5101c c05a5c10 ef9ad500 00000000 24242422 1005787c 00000000 1004f960 [ 78.839151] GPR16: 00000000 10024e90 10050040 48030018 0fe44150 00000000 00000000 eef19c30 [ 78.845046] GPR24: eef19e44 00000000 eef19bf8 efb37c14 eef19bf8 00008020 00009032 c0596064 [ 78.856671] NIP [c0097f54] kmem_cache_alloc+0x20/0x94 [ 78.862581] LR [c0334a28] dst_alloc+0x40/0xc4 [ 78.868451] Call Trace: [ 78.874252] [eef19b80] [c03c1810] ip6_dst_lookup_tail+0x1c8/0x1dc (unreliable) [ 78.880222] [eef19ba0] [c0334a28] dst_alloc+0x40/0xc4 [ 78.886164] [eef19bb0] [c03cd698] ip6_dst_blackhole+0x28/0x1cc [ 78.892090] [eef19be0] [c03d9be8] rawv6_sendmsg+0x75c/0xc88 [ 78.897999] [eef19cb0] [c038bca4] inet_sendmsg+0x4c/0x78 [ 78.903907] [eef19cd0] [c03207c8] sock_sendmsg+0xac/0xe4 [ 78.909734] [eef19db0] [c03209e4] sys_sendmsg+0x1e4/0x2a0 [ 78.915540] [eef19f00] [c03220a8] sys_socketcall+0xfc/0x210 [ 78.921406] [eef19f40] [c0014b3c] ret_from_syscall+0x0/0x38 [ 78.927295] --- Exception: c01 at 0xfe2d730 [ 78.927297] LR = 0xfe2d71c [ 78.939019] Instruction dump: [ 78.944835] 91640018 9144001c 900a0000 4bffff44 9421ffe0 7c0802a6 bf810010 7c9d2378 [ 78.950694] 90010024 7fc000a6 57c0045e 7c000124 <83e3004c> 8383005c 2f9f0000 419e0050 [ 78.956464] ---[ end trace 05fa1ed7972487a1 ]--- As commented by Benjamin Thery, the bug was introduced by f2fc6a54585a1be6669613a31fbaba2ecbadcd36, while adding network namespaces support to ipv6 routes. Signed-off-by: Arnaud Ebalard <arno@natisbad.org> Acked-by: Benjamin Thery <benjamin.thery@bull.net> Signed-off-by: David S. Miller <davem@davemloft.net>
2008-10-01 09:37:56 +00:00
ip6_dst_blackhole_ops.kmem_cachep = ip6_dst_ops_template.kmem_cachep;
/* Registering of the loopback is done before this portion of code,
* the loopback reference in rt6_info will not be taken, do it
* manually for init_net */
init_net.ipv6.ip6_null_entry->dst.dev = init_net.loopback_dev;
init_net.ipv6.ip6_null_entry->rt6i_idev = in6_dev_get(init_net.loopback_dev);
#ifdef CONFIG_IPV6_MULTIPLE_TABLES
init_net.ipv6.ip6_prohibit_entry->dst.dev = init_net.loopback_dev;
init_net.ipv6.ip6_prohibit_entry->rt6i_idev = in6_dev_get(init_net.loopback_dev);
init_net.ipv6.ip6_blk_hole_entry->dst.dev = init_net.loopback_dev;
init_net.ipv6.ip6_blk_hole_entry->rt6i_idev = in6_dev_get(init_net.loopback_dev);
#endif
ret = fib6_init();
if (ret)
goto out_register_subsys;
ret = xfrm6_init();
if (ret)
goto out_fib6_init;
ret = fib6_rules_init();
if (ret)
goto xfrm6_init;
ret = register_pernet_subsys(&ip6_route_net_late_ops);
if (ret)
goto fib6_rules_init;
ret = -ENOBUFS;
if (__rtnl_register(PF_INET6, RTM_NEWROUTE, inet6_rtm_newroute, NULL, NULL) ||
__rtnl_register(PF_INET6, RTM_DELROUTE, inet6_rtm_delroute, NULL, NULL) ||
__rtnl_register(PF_INET6, RTM_GETROUTE, inet6_rtm_getroute, NULL, NULL))
goto out_register_late_subsys;
ret = register_netdevice_notifier(&ip6_route_dev_notifier);
if (ret)
goto out_register_late_subsys;
out:
return ret;
out_register_late_subsys:
unregister_pernet_subsys(&ip6_route_net_late_ops);
fib6_rules_init:
fib6_rules_cleanup();
xfrm6_init:
xfrm6_fini();
out_fib6_init:
fib6_gc_cleanup();
out_register_subsys:
unregister_pernet_subsys(&ip6_route_net_ops);
out_register_inetpeer:
unregister_pernet_subsys(&ipv6_inetpeer_ops);
out_dst_entries:
dst_entries_destroy(&ip6_dst_blackhole_ops);
out_kmem_cache:
kmem_cache_destroy(ip6_dst_ops_template.kmem_cachep);
goto out;
}
void ip6_route_cleanup(void)
{
unregister_netdevice_notifier(&ip6_route_dev_notifier);
unregister_pernet_subsys(&ip6_route_net_late_ops);
fib6_rules_cleanup();
xfrm6_fini();
fib6_gc_cleanup();
unregister_pernet_subsys(&ipv6_inetpeer_ops);
unregister_pernet_subsys(&ip6_route_net_ops);
dst_entries_destroy(&ip6_dst_blackhole_ops);
kmem_cache_destroy(ip6_dst_ops_template.kmem_cachep);
}