aboutsummaryrefslogtreecommitdiffstats
path: root/net/unix
Commit message (Collapse)AuthorAge
...
* [UNIX]: Extend unix_sysctl_(un)register prototypesPavel Emelyanov2008-01-28
| | | | | | | | | | | | | Add the struct net * argument to both of them to use in the future. Also make the register one return an error code. It is useless right now, but will make the future patches much simpler. Signed-off-by: Pavel Emelyanov <xemul@openvz.org> Acked-by: Eric W. Biederman <ebiederm@xmission.com> Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au> Signed-off-by: David S. Miller <davem@davemloft.net>
* [NET]: Name magic constants in sock_wake_async()Pavel Emelyanov2008-01-28
| | | | | | | | | | | | | | | | | | The sock_wake_async() performs a bit different actions depending on "how" argument. Unfortunately this argument ony has numerical magic values. I propose to give names to their constants to help people reading this function callers understand what's going on without looking into this function all the time. I suppose this is 2.6.25 material, but if it's not (or the naming seems poor/bad/awful), I can rework it against the current net-2.6 tree. Signed-off-by: Pavel Emelyanov <xemul@openvz.org> Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au> Signed-off-by: David S. Miller <davem@davemloft.net>
* [UNIX] Move the unix sock iterators in to proper placePavel Emelyanov2008-01-28
| | | | | | | | | | | | | | The first_unix_socket() and next_unix_sockets() are now used in proc file and in forall_unix_socets macro only. The forall_unix_sockets is not used in this file at all so remove it. After this move the helpers to where they really belong, i.e. closer to proc code under the #ifdef CONFIG_PROC_FS option. Signed-off-by: Pavel Emelyanov <xemul@openvz.org> Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au> Signed-off-by: David S. Miller <davem@davemloft.net>
* [NET]: Consolidate net namespace related proc files creation.Denis V. Lunev2008-01-28
| | | | | | Signed-off-by: Denis V. Lunev <den@openvz.org> Signed-off-by: Pavel Emelyanov <xemul@openvz.org> Signed-off-by: David S. Miller <davem@davemloft.net>
* [NET]: Make AF_UNIX per network namespace safe [v2]Denis V. Lunev2008-01-28
| | | | | | | | | | | | | | | | | | Because of the global nature of garbage collection, and because of the cost of per namespace hash tables unix_socket_table has been kept global. With a filter added on lookups so we don't see sockets from the wrong namespace. Currently I don't fold the namesapce into the hash so multiple namespaces using the same socket name will be guaranteed a hash collision. Changes from v1: - fixed unix_seq_open Signed-off-by: Denis V. Lunev <den@openvz.org> Signed-off-by: Eric W. Biederman <ebiederm@xmission.com> Signed-off-by: David S. Miller <davem@davemloft.net>
* [UNIX]: EOF on non-blocking SOCK_SEQPACKETFlorian Zumbiehl2007-11-29
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | I am not absolutely sure whether this actually is a bug (as in: I've got no clue what the standards say or what other implementations do), but at least I was pretty surprised when I noticed that a recv() on a non-blocking unix domain socket of type SOCK_SEQPACKET (which is connection oriented, after all) where the remote end has closed the connection returned -1 (EAGAIN) rather than 0 to indicate end of file. This is a test case: | #include <sys/types.h> | #include <unistd.h> | #include <sys/socket.h> | #include <sys/un.h> | #include <fcntl.h> | #include <string.h> | #include <stdlib.h> | | int main(){ | int sock; | struct sockaddr_un addr; | char buf[4096]; | int pfds[2]; | | pipe(pfds); | sock=socket(PF_UNIX,SOCK_SEQPACKET,0); | addr.sun_family=AF_UNIX; | strcpy(addr.sun_path,"/tmp/foobar_testsock"); | bind(sock,(struct sockaddr *)&addr,sizeof(addr)); | listen(sock,1); | if(fork()){ | close(sock); | sock=socket(PF_UNIX,SOCK_SEQPACKET,0); | connect(sock,(struct sockaddr *)&addr,sizeof(addr)); | fcntl(sock,F_SETFL,fcntl(sock,F_GETFL)|O_NONBLOCK); | close(pfds[1]); | read(pfds[0],buf,sizeof(buf)); | recv(sock,buf,sizeof(buf),0); // <-- this one | }else accept(sock,NULL,NULL); | exit(0); | } If you try it, make sure /tmp/foobar_testsock doesn't exist. The marked recv() returns -1 (EAGAIN) on 2.6.23.9. Below you find a patch that fixes that. Signed-off-by: Florian Zumbiehl <florz@florz.de> Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
* [UNIX]: The unix_nr_socks limit can be exceededPavel Emelyanov2007-11-11
| | | | | | | | | | | | | | | The unix_nr_socks value is limited with the 2 * get_max_files() value, as seen from the unix_create1(). However, the check and the actual increment are separated with the GFP_KERNEL allocation, so this limit can be exceeded under a memory pressure - task may go to sleep freeing the pages and some other task will be allowed to allocate a new sock and so on and so forth. So make the increment before the check (similar thing is done in the sock_kmalloc) and go to kmalloc after this. Signed-off-by: Pavel Emelyanov <xemul@openvz.org> Signed-off-by: David S. Miller <davem@davemloft.net>
* [AF_UNIX]: Convert socks to unix_socks in scan_inflight, not in callbacksPavel Emelyanov2007-11-11
| | | | | | | | | | | | The scan_inflight() routine scans through the unix sockets and calls some passed callback. The fact is that all these callbacks work with the unix_sock objects, not the sock ones, so make this conversion in the scan_inflight() before calling the callbacks. This removes one unneeded variable from the inc_inflight_move_tail(). Signed-off-by: Pavel Emelyanov <xemul@openvz.org> Signed-off-by: David S. Miller <davem@davemloft.net>
* [AF_UNIX]: Make unix_tot_inflight counter non-atomicPavel Emelyanov2007-11-11
| | | | | | | | This counter is _always_ modified under the unix_gc_lock spinlock, so its atomicity can be provided w/o additional efforts. Signed-off-by: Pavel Emelyanov <xemul@openvz.org> Signed-off-by: David S. Miller <davem@davemloft.net>
* [NET]: Forget the zero_it argument of sk_alloc()Pavel Emelyanov2007-11-01
| | | | | | | | | | | | | | | Finally, the zero_it argument can be completely removed from the callers and from the function prototype. Besides, fix the checkpatch.pl warnings about using the assignments inside if-s. This patch is rather big, and it is a part of the previous one. I splitted it wishing to make the patches more readable. Hope this particular split helped. Signed-off-by: Pavel Emelyanov <xemul@openvz.org> Signed-off-by: David S. Miller <davem@davemloft.net>
* pid namespaces: changes to show virtual ids to userPavel Emelyanov2007-10-19
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | This is the largest patch in the set. Make all (I hope) the places where the pid is shown to or get from user operate on the virtual pids. The idea is: - all in-kernel data structures must store either struct pid itself or the pid's global nr, obtained with pid_nr() call; - when seeking the task from kernel code with the stored id one should use find_task_by_pid() call that works with global pids; - when showing pid's numerical value to the user the virtual one should be used, but however when one shows task's pid outside this task's namespace the global one is to be used; - when getting the pid from userspace one need to consider this as the virtual one and use appropriate task/pid-searching functions. [akpm@linux-foundation.org: build fix] [akpm@linux-foundation.org: nuther build fix] [akpm@linux-foundation.org: yet nuther build fix] [akpm@linux-foundation.org: remove unneeded casts] Signed-off-by: Pavel Emelyanov <xemul@openvz.org> Signed-off-by: Alexey Dobriyan <adobriyan@openvz.org> Cc: Sukadev Bhattiprolu <sukadev@us.ibm.com> Cc: Oleg Nesterov <oleg@tv-sign.ru> Cc: Paul Menage <menage@google.com> Cc: "Eric W. Biederman" <ebiederm@xmission.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
* sched: affine sync wakeupsIngo Molnar2007-10-15
| | | | | | | | make sync wakeups affine for cache-cold tasks: if a cache-cold task is woken up by a sync wakeup then use the opportunity to migrate it straight away. (the two tasks are 'related' because they communicate) Signed-off-by: Ingo Molnar <mingo@elte.hu>
* [NET]: Make core networking code use seq_open_privatePavel Emelyanov2007-10-10
| | | | | | | | | | | This concerns the ipv4 and ipv6 code mostly, but also the netlink and unix sockets. The netlink code is an example of how to use the __seq_open_private() call - it saves the net namespace on this private. Signed-off-by: Pavel Emelyanov <xemul@openvz.org> Signed-off-by: David S. Miller <davem@davemloft.net>
* [NET]: Make socket creation namespace safe.Eric W. Biederman2007-10-10
| | | | | | | | | | | | | | | | | | | | | | | This patch passes in the namespace a new socket should be created in and has the socket code do the appropriate reference counting. By virtue of this all socket create methods are touched. In addition the socket create methods are modified so that they will fail if you attempt to create a socket in a non-default network namespace. Failing if we attempt to create a socket outside of the default network namespace ensures that as we incrementally make the network stack network namespace aware we will not export functionality that someone has not audited and made certain is network namespace safe. Allowing us to partially enable network namespaces before all of the exotic protocols are supported. Any protocol layers I have missed will fail to compile because I now pass an extra parameter into the socket creation code. [ Integrated AF_IUCV build fixes from Andrew Morton... -DaveM ] Signed-off-by: Eric W. Biederman <ebiederm@xmission.com> Signed-off-by: David S. Miller <davem@davemloft.net>
* [NET]: Make /proc/net per network namespaceEric W. Biederman2007-10-10
| | | | | | | | | | | | | | | | | | This patch makes /proc/net per network namespace. It modifies the global variables proc_net and proc_net_stat to be per network namespace. The proc_net file helpers are modified to take a network namespace argument, and all of their callers are fixed to pass &init_net for that argument. This ensures that all of the /proc/net files are only visible and usable in the initial network namespace until the code behind them has been updated to be handle multiple network namespaces. Making /proc/net per namespace is necessary as at least some files in /proc/net depend upon the set of network devices which is per network namespace, and even more files in /proc/net have contents that are relevant to a single network namespace. Signed-off-by: Eric W. Biederman <ebiederm@xmission.com> Signed-off-by: David S. Miller <davem@davemloft.net>
* [AF_UNIX]: Make code static.Adrian Bunk2007-07-31
| | | | | | | | | The following code can now become static: - struct unix_socket_table - unix_table_lock Signed-off-by: Adrian Bunk <bunk@stusta.de> Signed-off-by: David S. Miller <davem@davemloft.net>
* [AF_UNIX]: Rewrite garbage collector, fixes race.Miklos Szeredi2007-07-11
| | | | | | | | | | | | | | | | | | | | | | | | | Throw out the old mark & sweep garbage collector and put in a refcounting cycle detecting one. The old one had a race with recvmsg, that resulted in false positives and hence data loss. The old algorithm operated on all unix sockets in the system, so any additional locking would have meant performance problems for all users of these. The new algorithm instead only operates on "in flight" sockets, which are very rare, and the additional locking for these doesn't negatively impact the vast majority of users. In fact it's probable, that there weren't *any* heavy senders of sockets over sockets, otherwise the above race would have been discovered long ago. The patch works OK with the app that exposed the race with the old code. The garbage collection has also been verified to work in a few simple cases. Signed-off-by: Miklos Szeredi <mszeredi@suse.cz> Signed-off-by: David S. Miller <davem@davemloft.net>
* [NET]: Make all initialized struct seq_operations const.Philippe De Muyter2007-07-11
| | | | | | | Make all initialized struct seq_operations in net/ const Signed-off-by: Philippe De Muyter <phdm@macqel.be> Signed-off-by: David S. Miller <davem@davemloft.net>
* [AF_UNIX]: Fix stream recvmsg() race.Miklos Szeredi2007-06-07
| | | | | | | | | | | | | | | | | | | | | | | A recv() on an AF_UNIX, SOCK_STREAM socket can race with a send()+close() on the peer, causing recv() to return zero, even though the sent data should be received. This happens if the send() and the close() is performed between skb_dequeue() and checking sk->sk_shutdown in unix_stream_recvmsg(): process A skb_dequeue() returns NULL, there's no data in the socket queue process B new data is inserted onto the queue by unix_stream_sendmsg() process B sk->sk_shutdown is set to SHUTDOWN_MASK by unix_release_sock() process A sk->sk_shutdown is checked, unix_release_sock() returns zero I'm surprised nobody noticed this, it's not hard to trigger. Maybe it's just (un)luck with the timing. It's possible to work around this bug in userspace, by retrying the recv() once in case of a zero return value. Signed-off-by: Miklos Szeredi <mszeredi@suse.cz> Signed-off-by: David S. Miller <davem@davemloft.net>
* [AF_UNIX]: Fix datagram connect race causing an OOPS.David S. Miller2007-06-03
| | | | | | | | | | | | | | | | | | | | | | | | Based upon an excellent bug report and initial patch by Frederik Deweerdt. The UNIX datagram connect code blindly dereferences other->sk_socket via the call down to the security_unix_may_send() function. Without locking 'other' that pointer can go NULL via unix_release_sock() which does sock_orphan() which also marks the socket SOCK_DEAD. So we have to lock both 'sk' and 'other' yet avoid all kinds of potential deadlocks (connect to self is OK for datagram sockets and it is possible for two datagram sockets to perform a simultaneous connect to each other). So what we do is have a "double lock" function similar to how we handle this situation in other areas of the kernel. We take the lock of the socket pointer with the smallest address first in order to avoid ABBA style deadlocks. Once we have them both locked, we check to see if SOCK_DEAD is set for 'other' and if so, drop everything and retry the lookup. Signed-off-by: David S. Miller <davem@davemloft.net>
* [AF_UNIX]: Make socket locking much less confusing.David S. Miller2007-06-03
| | | | | | | | | | | The unix_state_*() locking macros imply that there is some rwlock kind of thing going on, but the implementation is actually a spinlock which makes the code more confusing than it needs to be. So use plain unix_state_lock and unix_state_unlock. Signed-off-by: David S. Miller <davem@davemloft.net>
* header cleaning: don't include smp_lock.h when not usedRandy Dunlap2007-05-08
| | | | | | | | | | | | Remove includes of <linux/smp_lock.h> where it is not used/needed. Suggested by Al Viro. Builds cleanly on x86_64, i386, alpha, ia64, powerpc, sparc, sparc64, and arm (all 59 defconfigs). Signed-off-by: Randy Dunlap <randy.dunlap@oracle.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
* [SK_BUFF]: Introduce skb_reset_transport_header(skb)Arnaldo Carvalho de Melo2007-04-26
| | | | | | | | | | | | | | | | For the common, open coded 'skb->h.raw = skb->data' operation, so that we can later turn skb->h.raw into a offset, reducing the size of struct sk_buff in 64bit land while possibly keeping it as a pointer on 32bit. This one touches just the most simple cases: skb->h.raw = skb->data; skb->h.raw = {skb_push|[__]skb_pull}() The next ones will handle the slightly more "complex" cases. Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
* [NET]: Revert incorrect accept queue backlog changes.David S. Miller2007-03-06
| | | | | | | | | | | | | | | This reverts two changes: 8488df894d05d6fa41c2bd298c335f944bb0e401 248f06726e866942b3d8ca8f411f9067713b7ff8 A backlog value of N really does mean allow "N + 1" connections to queue to a listening socket. This allows one to specify "0" as the backlog and still get 1 connection. Noticed by Gerrit Renker and Rick Jones. Signed-off-by: David S. Miller <davem@davemloft.net>
* [AF_UNIX]: Test against sk_max_ack_backlog properly.David S. Miller2007-03-02
| | | | | | | This brings things inline with the sk_acceptq_is_full() bug fix. The limit test should be x >= sk_max_ack_backlog. Signed-off-by: David S. Miller <davem@davemloft.net>
* [PATCH] sysctl: remove insert_at_head from register_sysctlEric W. Biederman2007-02-14
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | The semantic effect of insert_at_head is that it would allow new registered sysctl entries to override existing sysctl entries of the same name. Which is pain for caching and the proc interface never implemented. I have done an audit and discovered that none of the current users of register_sysctl care as (excpet for directories) they do not register duplicate sysctl entries. So this patch simply removes the support for overriding existing entries in the sys_sysctl interface since no one uses it or cares and it makes future enhancments harder. Signed-off-by: Eric W. Biederman <ebiederm@xmission.com> Acked-by: Ralf Baechle <ralf@linux-mips.org> Acked-by: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: Russell King <rmk@arm.linux.org.uk> Cc: David Howells <dhowells@redhat.com> Cc: "Luck, Tony" <tony.luck@intel.com> Cc: Ralf Baechle <ralf@linux-mips.org> Cc: Paul Mackerras <paulus@samba.org> Cc: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: Andi Kleen <ak@muc.de> Cc: Jens Axboe <axboe@kernel.dk> Cc: Corey Minyard <minyard@acm.org> Cc: Neil Brown <neilb@suse.de> Cc: "John W. Linville" <linville@tuxdriver.com> Cc: James Bottomley <James.Bottomley@steeleye.com> Cc: Jan Kara <jack@ucw.cz> Cc: Trond Myklebust <trond.myklebust@fys.uio.no> Cc: Mark Fasheh <mark.fasheh@oracle.com> Cc: David Chinner <dgc@sgi.com> Cc: "David S. Miller" <davem@davemloft.net> Cc: Patrick McHardy <kaber@trash.net> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
* [PATCH] remove many unneeded #includes of sched.hTim Schmielau2007-02-14
| | | | | | | | | | | | | | | | | | | | | | | | After Al Viro (finally) succeeded in removing the sched.h #include in module.h recently, it makes sense again to remove other superfluous sched.h includes. There are quite a lot of files which include it but don't actually need anything defined in there. Presumably these includes were once needed for macros that used to live in sched.h, but moved to other header files in the course of cleaning it up. To ease the pain, this time I did not fiddle with any header files and only removed #includes from .c-files, which tend to cause less trouble. Compile tested against 2.6.20-rc2 and 2.6.20-rc2-mm2 (with offsets) on alpha, arm, i386, ia64, mips, powerpc, and x86_64 with allnoconfig, defconfig, allmodconfig, and allyesconfig as well as a few randconfigs on x86_64 and all configs in arch/arm/configs on arm. I also checked that no new warnings were introduced by the patch (actually, some warnings are removed that were emitted by unnecessarily included header files). Signed-off-by: Tim Schmielau <tim@physik3.uni-rostock.de> Acked-by: Russell King <rmk+kernel@arm.linux.org.uk> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
* [PATCH] mark struct file_operations const 8Arjan van de Ven2007-02-12
| | | | | | | | | | | Many struct file_operations in the kernel can be "const". Marking them const moves these to the .rodata section, which avoids false sharing with potential dirty data. In addition it'll catch accidental writes at compile time to these shared resources. Signed-off-by: Arjan van de Ven <arjan@linux.intel.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
* [NET] UNIX: Fix whitespace errors.YOSHIFUJI Hideaki2007-02-11
| | | | | Signed-off-by: YOSHIFUJI Hideaki <yoshfuji@linux-ipv6.org> Signed-off-by: David S. Miller <davem@davemloft.net>
* [PATCH] struct path: convert unixJosef Sipek2006-12-08
| | | | | | Signed-off-by: Josef Sipek <jsipek@fsl.cs.sunysb.edu> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
* [NET]: Annotate csum_partial() callers in net/*Al Viro2006-12-03
| | | | | Signed-off-by: Al Viro <viro@zeniv.linux.org.uk> Signed-off-by: David S. Miller <davem@davemloft.net>
* [AF_UNIX]: Change max_dgram_qlen sysctl to __read_mostlyBrian Haley2006-09-22
| | | | | Signed-off-by: Brian Haley <brian.haley@hp.com> Signed-off-by: David S. Miller <davem@davemloft.net>
* [NET]: Use BUILD_BUG_ON() for checking size of skb->cb.YOSHIFUJI Hideaki2006-09-22
| | | | | Signed-off-by: YOSHIFUJI Hideaki <yoshfuji@linux-ipv6.org> Signed-off-by: David S. Miller <davem@davemloft.net>
* [AF_UNIX]: Kernel memory leak fix for af_unix datagram getpeersec patchCatherine Zhang2006-08-02
| | | | | | | | | | | | | | | | | | | | From: Catherine Zhang <cxzhang@watson.ibm.com> This patch implements a cleaner fix for the memory leak problem of the original unix datagram getpeersec patch. Instead of creating a security context each time a unix datagram is sent, we only create the security context when the receiver requests it. This new design requires modification of the current unix_getsecpeer_dgram LSM hook and addition of two new hooks, namely, secid_to_secctx and release_secctx. The former retrieves the security context and the latter releases it. A hook is required for releasing the security context because it is up to the security module to decide how that's done. In the case of Selinux, it's a simple kfree operation. Acked-by: Stephen Smalley <sds@tycho.nsa.gov> Signed-off-by: David S. Miller <davem@davemloft.net>
* [NET]: Conversions from kmalloc+memset to k(z|c)alloc.Panagiotis Issaris2006-07-21
| | | | | | Signed-off-by: Panagiotis Issaris <takis@issaris.org> Signed-off-by: David S. Miller <davem@davemloft.net>
* [AF_UNIX]: datagram getpeersec fixAndrew Morton2006-07-03
| | | | | | | | The unix_get_peersec_dgram() stub should have been inlined so that it disappears. Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: David S. Miller <davem@davemloft.net>
* [PATCH] lockdep: annotate af_unix lockingIngo Molnar2006-07-03
| | | | | | | | | | | | Teach special (recursive) locking code to the lock validator. Also splits af_unix's sk_receive_queue.lock class from the other networking skb-queue locks. Has no effect on non-lockdep kernels. Signed-off-by: Ingo Molnar <mingo@elte.hu> Signed-off-by: Arjan van de Ven <arjan@linux.intel.com> Cc: "David S. Miller" <davem@davemloft.net> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
* Remove obsolete #include <linux/config.h>Jörn Engel2006-06-30
| | | | | Signed-off-by: Jörn Engel <joern@wohnheim.fh-wedel.de> Signed-off-by: Adrian Bunk <bunk@stusta.de>
* [AF_UNIX]: Datagram getpeersecCatherine Zhang2006-06-29
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | This patch implements an API whereby an application can determine the label of its peer's Unix datagram sockets via the auxiliary data mechanism of recvmsg. Patch purpose: This patch enables a security-aware application to retrieve the security context of the peer of a Unix datagram socket. The application can then use this security context to determine the security context for processing on behalf of the peer who sent the packet. Patch design and implementation: The design and implementation is very similar to the UDP case for INET sockets. Basically we build upon the existing Unix domain socket API for retrieving user credentials. Linux offers the API for obtaining user credentials via ancillary messages (i.e., out of band/control messages that are bundled together with a normal message). To retrieve the security context, the application first indicates to the kernel such desire by setting the SO_PASSSEC option via getsockopt. Then the application retrieves the security context using the auxiliary data mechanism. An example server application for Unix datagram socket should look like this: toggle = 1; toggle_len = sizeof(toggle); setsockopt(sockfd, SOL_SOCKET, SO_PASSSEC, &toggle, &toggle_len); recvmsg(sockfd, &msg_hdr, 0); if (msg_hdr.msg_controllen > sizeof(struct cmsghdr)) { cmsg_hdr = CMSG_FIRSTHDR(&msg_hdr); if (cmsg_hdr->cmsg_len <= CMSG_LEN(sizeof(scontext)) && cmsg_hdr->cmsg_level == SOL_SOCKET && cmsg_hdr->cmsg_type == SCM_SECURITY) { memcpy(&scontext, CMSG_DATA(cmsg_hdr), sizeof(scontext)); } } sock_setsockopt is enhanced with a new socket option SOCK_PASSSEC to allow a server socket to receive security context of the peer. Testing: We have tested the patch by setting up Unix datagram client and server applications. We verified that the server can retrieve the security context using the auxiliary data mechanism of recvmsg. Signed-off-by: Catherine Zhang <cxzhang@watson.ibm.com> Acked-by: Acked-by: James Morris <jmorris@namei.org> Signed-off-by: David S. Miller <davem@davemloft.net>
* [PATCH] POLLRDHUP/EPOLLRDHUP handling for half-closed devices notificationsDavide Libenzi2006-03-25
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Implement the half-closed devices notifiation, by adding a new POLLRDHUP (and its alias EPOLLRDHUP) bit to the existing poll/select sets. Since the existing POLLHUP handling, that does not report correctly half-closed devices, was feared to be changed, this implementation leaves the current POLLHUP reporting unchanged and simply add a new bit that is set in the few places where it makes sense. The same thing was discussed and conceptually agreed quite some time ago: http://lkml.org/lkml/2003/7/12/116 Since this new event bit is added to the existing Linux poll infrastruture, even the existing poll/select system calls will be able to use it. As far as the existing POLLHUP handling, the patch leaves it as is. The pollrdhup-2.6.16.rc5-0.10.diff defines the POLLRDHUP for all the existing archs and sets the bit in the six relevant files. The other attached diff is the simple change required to sys/epoll.h to add the EPOLLRDHUP definition. There is "a stupid program" to test POLLRDHUP delivery here: http://www.xmailserver.org/pollrdhup-test.c It tests poll(2), but since the delivery is same epoll(2) will work equally. Signed-off-by: Davide Libenzi <davidel@xmailserver.org> Cc: "David S. Miller" <davem@davemloft.net> Cc: Michael Kerrisk <mtk-manpages@gmx.net> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
* [NET]: sem2mutex part 2Ingo Molnar2006-03-21
| | | | | | | | | | | Semaphore to mutex conversion. The conversion was generated via scripts, and the result was validated automatically via a script as well. Signed-off-by: Ingo Molnar <mingo@elte.hu> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: David S. Miller <davem@davemloft.net>
* [NET] sem2mutex: net/Arjan van de Ven2006-03-21
| | | | | | | | | | | | Semaphore to mutex conversion. The conversion was generated via scripts, and the result was validated automatically via a script as well. Signed-off-by: Arjan van de Ven <arjan@infradead.org> Signed-off-by: Ingo Molnar <mingo@elte.hu> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: David S. Miller <davem@davemloft.net>
* [AF_UNIX]: use shift instead of integer divisionBenjamin LaHaise2006-03-21
| | | | | | | | | | The patch below replaces a divide by 2 with a shift -- sk_sndbuf is an integer, so gcc emits an idiv, which takes 10x longer than a shift by 1. This improves af_unix bandwidth by ~6-10K/s. Also, tidy up the comment to fit in 80 columns while we're at it. Signed-off-by: Benjamin LaHaise <benjamin.c.lahaise@intel.com> Signed-off-by: David S. Miller <davem@davemloft.net>
* [PATCH] fix file countingDipankar Sarma2006-03-08
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | I have benchmarked this on an x86_64 NUMA system and see no significant performance difference on kernbench. Tested on both x86_64 and powerpc. The way we do file struct accounting is not very suitable for batched freeing. For scalability reasons, file accounting was constructor/destructor based. This meant that nr_files was decremented only when the object was removed from the slab cache. This is susceptible to slab fragmentation. With RCU based file structure, consequent batched freeing and a test program like Serge's, we just speed this up and end up with a very fragmented slab - llm22:~ # cat /proc/sys/fs/file-nr 587730 0 758844 At the same time, I see only a 2000+ objects in filp cache. The following patch I fixes this problem. This patch changes the file counting by removing the filp_count_lock. Instead we use a separate percpu counter, nr_files, for now and all accesses to it are through get_nr_files() api. In the sysctl handler for nr_files, we populate files_stat.nr_files before returning to user. Counting files as an when they are created and destroyed (as opposed to inside slab) allows us to correctly count open files with RCU. Signed-off-by: Dipankar Sarma <dipankar@in.ibm.com> Cc: "Paul E. McKenney" <paulmck@us.ibm.com> Cc: "David S. Miller" <davem@davemloft.net> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
* [PATCH] mutex subsystem, semaphore to mutex: VFS, ->i_semJes Sorensen2006-01-09
| | | | | | | | | | | | | This patch converts the inode semaphore to a mutex. I have tested it on XFS and compiled as much as one can consider on an ia64. Anyway your luck with it might be different. Modified-by: Ingo Molnar <mingo@elte.hu> (finished the conversion) Signed-off-by: Jes Sorensen <jes@sgi.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
* [NET]: Add a dev_ioctl() fallback to sock_ioctl()Christoph Hellwig2006-01-03
| | | | | | | | | | | Currently all network protocols need to call dev_ioctl as the default fallback in their ioctl implementations. This patch adds a fallback to dev_ioctl to sock_ioctl if the protocol returned -ENOIOCTLCMD. This way all the procotol ioctl handlers can be simplified and we don't need to export dev_ioctl. Signed-off-by: Christoph Hellwig <hch@lst.de> Signed-off-by: David S. Miller <davem@davemloft.net>
* [AF_UNIX]: Convert to use a spinlock instead of rwlockBenjamin LaHaise2006-01-03
| | | | | | | | | | From: Benjamin LaHaise <bcrl@kvack.org> In af_unix, a rwlock is used to protect internal state. At least on my P4 with HT it is faster to use a spinlock due to the simpler memory barrier used to unlock. This patch raises bw_unix to ~690K/s. Signed-off-by: David S. Miller <davem@davemloft.net>
* [NET]: move struct proto_ops to constEric Dumazet2006-01-03
| | | | | | | | | | | | | | | | | | | | | | I noticed that some of 'struct proto_ops' used in the kernel may share a cache line used by locks or other heavily modified data. (default linker alignement is 32 bytes, and L1_CACHE_LINE is 64 or 128 at least) This patch makes sure a 'struct proto_ops' can be declared as const, so that all cpus can share all parts of it without false sharing. This is not mandatory : a driver can still use a read/write structure if it needs to (and eventually a __read_mostly) I made a global stubstitute to change all existing occurences to make them const. This should reduce the possibility of false sharing on SMP, and speedup some socket system calls. Signed-off-by: Eric Dumazet <dada1@cosmosbay.com> Signed-off-by: David S. Miller <davem@davemloft.net>
* [AF_UNIX]: Use spinlock for unix_table_lockDavid S. Miller2006-01-03
| | | | | | | | This lock is actually taken mostly as a writer, so using a rwlock actually just makes performance worse especially on chips like the Intel P4. Signed-off-by: David S. Miller <davem@davemloft.net>
* [AF_UNIX]: Remove superfluous reference counting in unix_stream_sendmsgBenjamin LaHaise2006-01-03
| | | | | | | | | | | | | AF_UNIX stream socket performance on P4 CPUs tends to suffer due to a lot of pipeline flushes from atomic operations. The patch below removes the sock_hold() and sock_put() in unix_stream_sendmsg(). This should be safe as the socket still holds a reference to its peer which is only released after the file descriptor's final user invokes unix_release_sock(). The only consideration is that we must add a memory barrier before setting the peer initially. Signed-off-by: Benjamin LaHaise <benjamin.c.lahaise@intel.com> Signed-off-by: David S. Miller <davem@davemloft.net>
generated by cgit v1.2.2 (git 2.25.0) at 2025-07-24 01:10:33 -0400
ef='#n2146'>2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 2516 2517 2518 2519 2520 2521 2522 2523 2524 2525 2526 2527 2528 2529 2530 2531 2532 2533 2534 2535 2536 2537 2538 2539 2540 2541 2542 2543 2544 2545 2546 2547 2548 2549 2550 2551 2552 2553 2554 2555 2556 2557 2558 2559 2560 2561 2562 2563 2564 2565 2566 2567 2568 2569 2570 2571 2572 2573 2574 2575 2576 2577 2578 2579 2580 2581 2582 2583 2584 2585 2586 2587 2588 2589 2590 2591 2592 2593 2594 2595 2596 2597 2598 2599 2600 2601 2602 2603 2604 2605 2606 2607 2608 2609 2610 2611 2612 2613 2614 2615 2616 2617 2618 2619 2620 2621 2622 2623 2624 2625 2626 2627 2628 2629 2630 2631 2632 2633 2634 2635 2636 2637 2638 2639 2640 2641 2642 2643 2644 2645 2646 2647 2648 2649 2650 2651 2652 2653 2654 2655 2656 2657 2658 2659 2660 2661 2662 2663 2664 2665 2666 2667 2668 2669 2670 2671 2672 2673 2674 2675 2676 2677 2678 2679 2680 2681 2682 2683 2684 2685 2686 2687 2688 2689 2690 2691 2692 2693 2694 2695 2696 2697 2698 2699 2700 2701 2702 2703 2704 2705 2706 2707 2708 2709 2710 2711 2712 2713 2714 2715 2716 2717 2718 2719 2720 2721 2722 2723 2724 2725 2726 2727 2728 2729 2730 2731 2732 2733 2734 2735 2736 2737 2738 2739 2740 2741 2742 2743 2744 2745 2746 2747 2748 2749 2750 2751 2752 2753 2754 2755 2756 2757 2758 2759 2760 2761 2762 2763 2764 2765 2766 2767 2768 2769 2770 2771 2772 2773 2774 2775 2776 2777 2778 2779 2780 2781 2782 2783 2784 2785 2786 2787 2788 2789 2790 2791 2792 2793 2794 2795 2796 2797 2798 2799 2800 2801 2802 2803 2804 2805 2806 2807 2808 2809 2810 2811 2812 2813 2814 2815 2816 2817 2818 2819 2820 2821 2822 2823 2824 
/*
 *	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.
 */

#include <linux/capability.h>
#include <linux/errno.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 <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 <asm/uaccess.h>

#ifdef CONFIG_SYSCTL
#include <linux/sysctl.h>
#endif

/* Set to 3 to get tracing. */
#define RT6_DEBUG 2

#if RT6_DEBUG >= 3
#define RDBG(x) printk x
#define RT6_TRACE(x...) printk(KERN_DEBUG x)
#else
#define RDBG(x)
#define RT6_TRACE(x...) do { ; } while (0)
#endif

#define CLONE_OFFLINK_ROUTE 0

static struct rt6_info * ip6_rt_copy(struct rt6_info *ort);
static struct dst_entry	*ip6_dst_check(struct dst_entry *dst, u32 cookie);
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, u32 mtu);

#ifdef CONFIG_IPV6_ROUTE_INFO
static struct rt6_info *rt6_add_route_info(struct net *net,
					   struct in6_addr *prefix, int prefixlen,
					   struct in6_addr *gwaddr, int ifindex,
					   unsigned pref);
static struct rt6_info *rt6_get_route_info(struct net *net,
					   struct in6_addr *prefix, int prefixlen,
					   struct in6_addr *gwaddr, int ifindex);
#endif

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,
	.destroy		=	ip6_dst_destroy,
	.ifdown			=	ip6_dst_ifdown,
	.negative_advice	=	ip6_negative_advice,
	.link_failure		=	ip6_link_failure,
	.update_pmtu		=	ip6_rt_update_pmtu,
	.local_out		=	__ip6_local_out,
	.entries		=	ATOMIC_INIT(0),
};

static void ip6_rt_blackhole_update_pmtu(struct dst_entry *dst, u32 mtu)
{
}

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,
	.update_pmtu		=	ip6_rt_blackhole_update_pmtu,
	.entries		=	ATOMIC_INIT(0),
};

static struct rt6_info ip6_null_entry_template = {
	.u = {
		.dst = {
			.__refcnt	= ATOMIC_INIT(1),
			.__use		= 1,
			.obsolete	= -1,
			.error		= -ENETUNREACH,
			.metrics	= { [RTAX_HOPLIMIT - 1] = 255, },
			.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 struct rt6_info ip6_prohibit_entry_template = {
	.u = {
		.dst = {
			.__refcnt	= ATOMIC_INIT(1),
			.__use		= 1,
			.obsolete	= -1,
			.error		= -EACCES,
			.metrics	= { [RTAX_HOPLIMIT - 1] = 255, },
			.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 struct rt6_info ip6_blk_hole_entry_template = {
	.u = {
		.dst = {
			.__refcnt	= ATOMIC_INIT(1),
			.__use		= 1,
			.obsolete	= -1,
			.error		= -EINVAL,
			.metrics	= { [RTAX_HOPLIMIT - 1] = 255, },
			.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 dst_ops *ops)
{
	return (struct rt6_info *)dst_alloc(ops);
}

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 (idev != NULL) {
		rt->rt6i_idev = NULL;
		in6_dev_put(idev);
	}
}

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 && idev != NULL && idev->dev == dev) {
		struct inet6_dev *loopback_idev =
			in6_dev_get(loopback_dev);
		if (loopback_idev != NULL) {
			rt->rt6i_idev = loopback_idev;
			in6_dev_put(idev);
		}
	}
}

static __inline__ int rt6_check_expired(const struct rt6_info *rt)
{
	return (rt->rt6i_flags & RTF_EXPIRES &&
		time_after(jiffies, rt->rt6i_expires));
}

static inline int rt6_need_strict(struct in6_addr *daddr)
{
	return (ipv6_addr_type(daddr) &
		(IPV6_ADDR_MULTICAST | IPV6_ADDR_LINKLOCAL | IPV6_ADDR_LOOPBACK));
}

/*
 *	Route lookup. Any table->tb6_lock is implied.
 */

static inline struct rt6_info *rt6_device_match(struct net *net,
						    struct rt6_info *rt,
						    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->u.dst.rt6_next) {
		struct net_device *dev = sprt->rt6i_dev;

		if (oif) {
			if (dev->ifindex == oif)
				return sprt;
			if (dev->flags & IFF_LOOPBACK) {
				if (sprt->rt6i_idev == NULL ||
				    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 = rt ? rt->rt6i_nexthop : NULL;
	/*
	 * 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.
	 */
	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->rt6i_dev, NULL, target, &mcaddr, NULL);
	} else
		read_unlock_bh(&neigh->lock);
}
#else
static inline void rt6_probe(struct rt6_info *rt)
{
	return;
}
#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->rt6i_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 = rt->rt6i_nexthop;
	int m;
	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;
}

static struct rt6_info *find_match(struct rt6_info *rt, int oif, int strict,
				   int *mpri, struct rt6_info *match)
{
	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;

	match = NULL;
	for (rt = rr_head; rt && rt->rt6i_metric == metric;
	     rt = rt->u.dst.rt6_next)
		match = find_match(rt, oif, strict, &mpri, match);
	for (rt = fn->leaf; rt && rt != rr_head && rt->rt6i_metric == metric;
	     rt = rt->u.dst.rt6_next)
		match = find_match(rt, oif, strict, &mpri, match);

	return match;
}

static struct rt6_info *rt6_select(struct fib6_node *fn, int oif, int strict)
{
	struct rt6_info *match, *rt0;
	struct net *net;

	RT6_TRACE("%s(fn->leaf=%p, oif=%d)\n",
		  __func__, fn->leaf, oif);

	rt0 = fn->rr_ptr;
	if (!rt0)
		fn->rr_ptr = rt0 = fn->leaf;

	match = find_rr_leaf(fn, rt0, rt0->rt6i_metric, oif, strict);

	if (!match &&
	    (strict & RT6_LOOKUP_F_REACHABLE)) {
		struct rt6_info *next = rt0->u.dst.rt6_next;

		/* no entries matched; do round-robin */
		if (!next || next->rt6i_metric != rt0->rt6i_metric)
			next = fn->leaf;

		if (next != rt0)
			fn->rr_ptr = next;
	}

	RT6_TRACE("%s() => %p\n",
		  __func__, match);

	net = dev_net(rt0->rt6i_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,
		  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)
		pref = ICMPV6_ROUTER_PREF_MEDIUM;

	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)) {
			rt->rt6i_flags &= ~RTF_EXPIRES;
		} else {
			rt->rt6i_expires = jiffies + HZ * lifetime;
			rt->rt6i_flags |= RTF_EXPIRES;
		}
		dst_release(&rt->u.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 flowi *fl, int flags)
{
	struct fib6_node *fn;
	struct rt6_info *rt;

	read_lock_bh(&table->tb6_lock);
	fn = fib6_lookup(&table->tb6_root, &fl->fl6_dst, &fl->fl6_src);
restart:
	rt = fn->leaf;
	rt = rt6_device_match(net, rt, &fl->fl6_src, fl->oif, flags);
	BACKTRACK(net, &fl->fl6_src);
out:
	dst_use(&rt->u.dst, jiffies);
	read_unlock_bh(&table->tb6_lock);
	return rt;

}

struct rt6_info *rt6_lookup(struct net *net, const struct in6_addr *daddr,
			    const struct in6_addr *saddr, int oif, int strict)
{
	struct flowi fl = {
		.oif = oif,
		.nl_u = {
			.ip6_u = {
				.daddr = *daddr,
			},
		},
	};
	struct dst_entry *dst;
	int flags = strict ? RT6_LOOKUP_F_IFACE : 0;

	if (saddr) {
		memcpy(&fl.fl6_src, saddr, sizeof(*saddr));
		flags |= RT6_LOOKUP_F_HAS_SADDR;
	}

	dst = fib6_rule_lookup(net, &fl, 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->rt6i_dev),
	};
	return __ip6_ins_rt(rt, &info);
}

static struct rt6_info *rt6_alloc_cow(struct rt6_info *ort, struct in6_addr *daddr,
				      struct in6_addr *saddr)
{
	struct rt6_info *rt;

	/*
	 *	Clone the route.
	 */

	rt = ip6_rt_copy(ort);

	if (rt) {
		struct neighbour *neigh;
		int attempts = !in_softirq();

		if (!(rt->rt6i_flags&RTF_GATEWAY)) {
			if (rt->rt6i_dst.plen != 128 &&
			    ipv6_addr_equal(&rt->rt6i_dst.addr, daddr))
				rt->rt6i_flags |= RTF_ANYCAST;
			ipv6_addr_copy(&rt->rt6i_gateway, daddr);
		}

		ipv6_addr_copy(&rt->rt6i_dst.addr, daddr);
		rt->rt6i_dst.plen = 128;
		rt->rt6i_flags |= RTF_CACHE;
		rt->u.dst.flags |= DST_HOST;

#ifdef CONFIG_IPV6_SUBTREES
		if (rt->rt6i_src.plen && saddr) {
			ipv6_addr_copy(&rt->rt6i_src.addr, saddr);
			rt->rt6i_src.plen = 128;
		}
#endif

	retry:
		neigh = ndisc_get_neigh(rt->rt6i_dev, &rt->rt6i_gateway);
		if (IS_ERR(neigh)) {
			struct net *net = dev_net(rt->rt6i_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;
			}

			if (net_ratelimit())
				printk(KERN_WARNING
				       "Neighbour table overflow.\n");
			dst_free(&rt->u.dst);
			return NULL;
		}
		rt->rt6i_nexthop = neigh;

	}

	return rt;
}

static struct rt6_info *rt6_alloc_clone(struct rt6_info *ort, struct in6_addr *daddr)
{
	struct rt6_info *rt = ip6_rt_copy(ort);
	if (rt) {
		ipv6_addr_copy(&rt->rt6i_dst.addr, daddr);
		rt->rt6i_dst.plen = 128;
		rt->rt6i_flags |= RTF_CACHE;
		rt->u.dst.flags |= DST_HOST;
		rt->rt6i_nexthop = neigh_clone(ort->rt6i_nexthop);
	}
	return rt;
}

static struct rt6_info *ip6_pol_route(struct net *net, struct fib6_table *table, int oif,
				      struct flowi *fl, 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, &fl->fl6_dst, &fl->fl6_src);

restart:
	rt = rt6_select(fn, oif, strict | reachable);

	BACKTRACK(net, &fl->fl6_src);
	if (rt == net->ipv6.ip6_null_entry ||
	    rt->rt6i_flags & RTF_CACHE)
		goto out;

	dst_hold(&rt->u.dst);
	read_unlock_bh(&table->tb6_lock);

	if (!rt->rt6i_nexthop && !(rt->rt6i_flags & RTF_NONEXTHOP))
		nrt = rt6_alloc_cow(rt, &fl->fl6_dst, &fl->fl6_src);
	else {
#if CLONE_OFFLINK_ROUTE
		nrt = rt6_alloc_clone(rt, &fl->fl6_dst);
#else
		goto out2;
#endif
	}

	dst_release(&rt->u.dst);
	rt = nrt ? : net->ipv6.ip6_null_entry;

	dst_hold(&rt->u.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->u.dst);
	goto relookup;

out:
	if (reachable) {
		reachable = 0;
		goto restart_2;
	}
	dst_hold(&rt->u.dst);
	read_unlock_bh(&table->tb6_lock);
out2:
	rt->u.dst.lastuse = jiffies;
	rt->u.dst.__use++;

	return rt;
}

static struct rt6_info *ip6_pol_route_input(struct net *net, struct fib6_table *table,
					    struct flowi *fl, int flags)
{
	return ip6_pol_route(net, table, fl->iif, fl, flags);
}

void ip6_route_input(struct sk_buff *skb)
{
	struct ipv6hdr *iph = ipv6_hdr(skb);
	struct net *net = dev_net(skb->dev);
	int flags = RT6_LOOKUP_F_HAS_SADDR;
	struct flowi fl = {
		.iif = skb->dev->ifindex,
		.nl_u = {
			.ip6_u = {
				.daddr = iph->daddr,
				.saddr = iph->saddr,
				.flowlabel = (* (__be32 *) iph)&IPV6_FLOWINFO_MASK,
			},
		},
		.mark = skb->mark,
		.proto = iph->nexthdr,
	};

	if (rt6_need_strict(&iph->daddr) && skb->dev->type != ARPHRD_PIMREG)
		flags |= RT6_LOOKUP_F_IFACE;

	skb_dst_set(skb, fib6_rule_lookup(net, &fl, flags, ip6_pol_route_input));
}

static struct rt6_info *ip6_pol_route_output(struct net *net, struct fib6_table *table,
					     struct flowi *fl, int flags)
{
	return ip6_pol_route(net, table, fl->oif, fl, flags);
}

struct dst_entry * ip6_route_output(struct net *net, struct sock *sk,
				    struct flowi *fl)
{
	int flags = 0;

	if (rt6_need_strict(&fl->fl6_dst))
		flags |= RT6_LOOKUP_F_IFACE;

	if (!ipv6_addr_any(&fl->fl6_src))
		flags |= RT6_LOOKUP_F_HAS_SADDR;
	else if (sk) {
		unsigned int prefs = inet6_sk(sk)->srcprefs;
		if (prefs & IPV6_PREFER_SRC_TMP)
			flags |= RT6_LOOKUP_F_SRCPREF_TMP;
		if (prefs & IPV6_PREFER_SRC_PUBLIC)
			flags |= RT6_LOOKUP_F_SRCPREF_PUBLIC;
		if (prefs & IPV6_PREFER_SRC_COA)
			flags |= RT6_LOOKUP_F_SRCPREF_COA;
	}

	return fib6_rule_lookup(net, fl, flags, ip6_pol_route_output);
}

EXPORT_SYMBOL(ip6_route_output);

int ip6_dst_blackhole(struct sock *sk, struct dst_entry **dstp, struct flowi *fl)
{
	struct rt6_info *ort = (struct rt6_info *) *dstp;
	struct rt6_info *rt = (struct rt6_info *)
		dst_alloc(&ip6_dst_blackhole_ops);
	struct dst_entry *new = NULL;

	if (rt) {
		new = &rt->u.dst;

		atomic_set(&new->__refcnt, 1);
		new->__use = 1;
		new->input = dst_discard;
		new->output = dst_discard;

		memcpy(new->metrics, ort->u.dst.metrics, RTAX_MAX*sizeof(u32));
		new->dev = ort->u.dst.dev;
		if (new->dev)
			dev_hold(new->dev);
		rt->rt6i_idev = ort->rt6i_idev;
		if (rt->rt6i_idev)
			in6_dev_hold(rt->rt6i_idev);
		rt->rt6i_expires = 0;

		ipv6_addr_copy(&rt->rt6i_gateway, &ort->rt6i_gateway);
		rt->rt6i_flags = ort->rt6i_flags & ~RTF_EXPIRES;
		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(*dstp);
	*dstp = new;
	return (new ? 0 : -ENOMEM);
}
EXPORT_SYMBOL_GPL(ip6_dst_blackhole);

/*
 *	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;

	if (rt && rt->rt6i_node && (rt->rt6i_node->fn_sernum == cookie))
		return dst;

	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)
			ip6_del_rt(rt);
		else
			dst_release(dst);
	}
	return NULL;
}

static void ip6_link_failure(struct sk_buff *skb)
{
	struct rt6_info *rt;

	icmpv6_send(skb, ICMPV6_DEST_UNREACH, ICMPV6_ADDR_UNREACH, 0, skb->dev);

	rt = (struct rt6_info *) skb_dst(skb);
	if (rt) {
		if (rt->rt6i_flags&RTF_CACHE) {
			dst_set_expires(&rt->u.dst, 0);
			rt->rt6i_flags |= RTF_EXPIRES;
		} 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, u32 mtu)
{
	struct rt6_info *rt6 = (struct rt6_info*)dst;

	if (mtu < dst_mtu(dst) && rt6->rt6i_dst.plen == 128) {
		rt6->rt6i_flags |= RTF_MODIFIED;
		if (mtu < IPV6_MIN_MTU) {
			mtu = IPV6_MIN_MTU;
			dst->metrics[RTAX_FEATURES-1] |= RTAX_FEATURE_ALLFRAG;
		}
		dst->metrics[RTAX_MTU-1] = mtu;
		call_netevent_notifiers(NETEVENT_PMTU_UPDATE, dst);
	}
}

static int ipv6_get_mtu(struct net_device *dev);

static inline unsigned int ipv6_advmss(struct net *net, unsigned int mtu)
{
	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 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,
				  const struct in6_addr *addr)
{
	struct rt6_info *rt;
	struct inet6_dev *idev = in6_dev_get(dev);
	struct net *net = dev_net(dev);

	if (unlikely(idev == NULL))
		return NULL;

	rt = ip6_dst_alloc(net->ipv6.ip6_dst_ops);
	if (unlikely(rt == NULL)) {
		in6_dev_put(idev);
		goto out;
	}

	dev_hold(dev);
	if (neigh)
		neigh_hold(neigh);
	else {
		neigh = ndisc_get_neigh(dev, addr);
		if (IS_ERR(neigh))
			neigh = NULL;
	}

	rt->rt6i_dev	  = dev;
	rt->rt6i_idev     = idev;
	rt->rt6i_nexthop  = neigh;
	atomic_set(&rt->u.dst.__refcnt, 1);
	rt->u.dst.metrics[RTAX_HOPLIMIT-1] = 255;
	rt->u.dst.metrics[RTAX_MTU-1] = ipv6_get_mtu(rt->rt6i_dev);
	rt->u.dst.metrics[RTAX_ADVMSS-1] = ipv6_advmss(net, dst_mtu(&rt->u.dst));
	rt->u.dst.output  = ip6_output;

#if 0	/* there's no chance to use these for ndisc */
	rt->u.dst.flags   = ipv6_addr_type(addr) & IPV6_ADDR_UNICAST
				? DST_HOST
				: 0;
	ipv6_addr_copy(&rt->rt6i_dst.addr, addr);
	rt->rt6i_dst.plen = 128;
#endif

	spin_lock_bh(&icmp6_dst_lock);
	rt->u.dst.next = icmp6_dst_gc_list;
	icmp6_dst_gc_list = &rt->u.dst;
	spin_unlock_bh(&icmp6_dst_lock);

	fib6_force_start_gc(net);

out:
	return &rt->u.dst;
}

int icmp6_dst_gc(void)
{
	struct dst_entry *dst, *next, **pprev;
	int more = 0;

	next = NULL;

	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 = ops->dst_net;
	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;

	if (time_after(rt_last_gc + rt_min_interval, now) &&
	    atomic_read(&ops->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;
	if (atomic_read(&ops->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 (atomic_read(&ops->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!
 */

static int ipv6_get_mtu(struct net_device *dev)
{
	int mtu = IPV6_MIN_MTU;
	struct inet6_dev *idev;

	idev = in6_dev_get(dev);
	if (idev) {
		mtu = idev->cnf.mtu6;
		in6_dev_put(idev);
	}
	return mtu;
}

int ip6_dst_hoplimit(struct dst_entry *dst)
{
	int hoplimit = dst_metric(dst, RTAX_HOPLIMIT);
	if (hoplimit < 0) {
		struct net_device *dev = dst->dev;
		struct inet6_dev *idev = in6_dev_get(dev);
		if (idev) {
			hoplimit = idev->cnf.hop_limit;
			in6_dev_put(idev);
		} else
			hoplimit = dev_net(dev)->ipv6.devconf_all->hop_limit;
	}
	return 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;

	table = fib6_new_table(net, cfg->fc_table);
	if (table == NULL) {
		err = -ENOBUFS;
		goto out;
	}

	rt = ip6_dst_alloc(net->ipv6.ip6_dst_ops);

	if (rt == NULL) {
		err = -ENOMEM;
		goto out;
	}

	rt->u.dst.obsolete = -1;
	rt->rt6i_expires = (cfg->fc_flags & RTF_EXPIRES) ?
				jiffies + clock_t_to_jiffies(cfg->fc_expires) :
				0;

	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->u.dst.input = ip6_mc_input;
	else
		rt->u.dst.input = ip6_forward;

	rt->u.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->u.dst.flags = DST_HOST;

#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))) {
		/* 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->u.dst.output = ip6_pkt_discard_out;
		rt->u.dst.input = ip6_pkt_discard;
		rt->u.dst.error = -ENETUNREACH;
		rt->rt6i_flags = RTF_REJECT|RTF_NONEXTHOP;
		goto install_route;
	}

	if (cfg->fc_flags & RTF_GATEWAY) {
		struct in6_addr *gw_addr;
		int gwa_type;

		gw_addr = &cfg->fc_gateway;
		ipv6_addr_copy(&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 == NULL)
				goto out;
			if (dev) {
				if (dev != grt->rt6i_dev) {
					dst_release(&grt->u.dst);
					goto out;
				}
			} else {
				dev = grt->rt6i_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->u.dst);

			if (err)
				goto out;
		}
		err = -EINVAL;
		if (dev == NULL || (dev->flags&IFF_LOOPBACK))
			goto out;
	}

	err = -ENODEV;
	if (dev == NULL)
		goto out;

	if (cfg->fc_flags & (RTF_GATEWAY | RTF_NONEXTHOP)) {
		rt->rt6i_nexthop = __neigh_lookup_errno(&nd_tbl, &rt->rt6i_gateway, dev);
		if (IS_ERR(rt->rt6i_nexthop)) {
			err = PTR_ERR(rt->rt6i_nexthop);
			rt->rt6i_nexthop = NULL;
			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;
				}

				rt->u.dst.metrics[type - 1] = nla_get_u32(nla);
			}
		}
	}

	if (dst_metric(&rt->u.dst, RTAX_HOPLIMIT) == 0)
		rt->u.dst.metrics[RTAX_HOPLIMIT-1] = -1;
	if (!dst_mtu(&rt->u.dst))
		rt->u.dst.metrics[RTAX_MTU-1] = ipv6_get_mtu(dev);
	if (!dst_metric(&rt->u.dst, RTAX_ADVMSS))
		rt->u.dst.metrics[RTAX_ADVMSS-1] = ipv6_advmss(net, dst_mtu(&rt->u.dst));
	rt->u.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->u.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->rt6i_dev);

	if (rt == net->ipv6.ip6_null_entry)
		return -ENOENT;

	table = rt->rt6i_table;
	write_lock_bh(&table->tb6_lock);

	err = fib6_del(rt, info);
	dst_release(&rt->u.dst);

	write_unlock_bh(&table->tb6_lock);

	return err;
}

int ip6_del_rt(struct rt6_info *rt)
{
	struct nl_info info = {
		.nl_net = dev_net(rt->rt6i_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 == NULL)
		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->u.dst.rt6_next) {
			if (cfg->fc_ifindex &&
			    (rt->rt6i_dev == NULL ||
			     rt->rt6i_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->u.dst);
			read_unlock_bh(&table->tb6_lock);

			return __ip6_del_rt(rt, &cfg->fc_nlinfo);
		}
	}
	read_unlock_bh(&table->tb6_lock);

	return err;
}

/*
 *	Handle redirects
 */
struct ip6rd_flowi {
	struct flowi fl;
	struct in6_addr gateway;
};

static struct rt6_info *__ip6_route_redirect(struct net *net,
					     struct fib6_table *table,
					     struct flowi *fl,
					     int flags)
{
	struct ip6rd_flowi *rdfl = (struct ip6rd_flowi *)fl;
	struct rt6_info *rt;
	struct fib6_node *fn;

	/*
	 * Get the "current" route for this destination and
	 * check if the redirect has come from approriate router.
	 *
	 * RFC 2461 specifies that redirects should only be
	 * accepted if they come from the nexthop to the target.
	 * Due to the way the routes are chosen, this notion
	 * is a bit fuzzy and one might need to check all possible
	 * routes.
	 */

	read_lock_bh(&table->tb6_lock);
	fn = fib6_lookup(&table->tb6_root, &fl->fl6_dst, &fl->fl6_src);
restart:
	for (rt = fn->leaf; rt; rt = rt->u.dst.rt6_next) {
		/*
		 * Current route is on-link; redirect is always invalid.
		 *
		 * Seems, previous statement is not true. It could
		 * be node, which looks for us as on-link (f.e. proxy ndisc)
		 * But then router serving it might decide, that we should
		 * know truth 8)8) --ANK (980726).
		 */
		if (rt6_check_expired(rt))
			continue;
		if (!(rt->rt6i_flags & RTF_GATEWAY))
			continue;
		if (fl->oif != rt->rt6i_dev->ifindex)
			continue;
		if (!ipv6_addr_equal(&rdfl->gateway, &rt->rt6i_gateway))
			continue;
		break;
	}

	if (!rt)
		rt = net->ipv6.ip6_null_entry;
	BACKTRACK(net, &fl->fl6_src);
out:
	dst_hold(&rt->u.dst);

	read_unlock_bh(&table->tb6_lock);

	return rt;
};

static struct rt6_info *ip6_route_redirect(struct in6_addr *dest,
					   struct in6_addr *src,
					   struct in6_addr *gateway,
					   struct net_device *dev)
{
	int flags = RT6_LOOKUP_F_HAS_SADDR;
	struct net *net = dev_net(dev);
	struct ip6rd_flowi rdfl = {
		.fl = {
			.oif = dev->ifindex,
			.nl_u = {
				.ip6_u = {
					.daddr = *dest,
					.saddr = *src,
				},
			},
		},
		.gateway = *gateway,
	};

	if (rt6_need_strict(dest))
		flags |= RT6_LOOKUP_F_IFACE;

	return (struct rt6_info *)fib6_rule_lookup(net, (struct flowi *)&rdfl,
						   flags, __ip6_route_redirect);
}

void rt6_redirect(struct in6_addr *dest, struct in6_addr *src,
		  struct in6_addr *saddr,
		  struct neighbour *neigh, u8 *lladdr, int on_link)
{
	struct rt6_info *rt, *nrt = NULL;
	struct netevent_redirect netevent;
	struct net *net = dev_net(neigh->dev);

	rt = ip6_route_redirect(dest, src, saddr, neigh->dev);

	if (rt == net->ipv6.ip6_null_entry) {
		if (net_ratelimit())
			printk(KERN_DEBUG "rt6_redirect: source isn't a valid nexthop "
			       "for redirect target\n");
		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))
		     );

	/*
	 * 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->u.dst);

	/* Duplicate redirect: silently ignore. */
	if (neigh == rt->u.dst.neighbour)
		goto out;

	nrt = ip6_rt_copy(rt);
	if (nrt == NULL)
		goto out;

	nrt->rt6i_flags = RTF_GATEWAY|RTF_UP|RTF_DYNAMIC|RTF_CACHE;
	if (on_link)
		nrt->rt6i_flags &= ~RTF_GATEWAY;

	ipv6_addr_copy(&nrt->rt6i_dst.addr, dest);
	nrt->rt6i_dst.plen = 128;
	nrt->u.dst.flags |= DST_HOST;

	ipv6_addr_copy(&nrt->rt6i_gateway, (struct in6_addr*)neigh->primary_key);
	nrt->rt6i_nexthop = neigh_clone(neigh);
	/* Reset pmtu, it may be better */
	nrt->u.dst.metrics[RTAX_MTU-1] = ipv6_get_mtu(neigh->dev);
	nrt->u.dst.metrics[RTAX_ADVMSS-1] = ipv6_advmss(dev_net(neigh->dev),
							dst_mtu(&nrt->u.dst));

	if (ip6_ins_rt(nrt))
		goto out;

	netevent.old = &rt->u.dst;
	netevent.new = &nrt->u.dst;
	call_netevent_notifiers(NETEVENT_REDIRECT, &netevent);

	if (rt->rt6i_flags&RTF_CACHE) {
		ip6_del_rt(rt);
		return;
	}

out:
	dst_release(&rt->u.dst);
	return;
}

/*
 *	Handle ICMP "packet too big" messages
 *	i.e. Path MTU discovery
 */

void rt6_pmtu_discovery(struct in6_addr *daddr, struct in6_addr *saddr,
			struct net_device *dev, u32 pmtu)
{
	struct rt6_info *rt, *nrt;
	struct net *net = dev_net(dev);
	int allfrag = 0;

	rt = rt6_lookup(net, daddr, saddr, dev->ifindex, 0);
	if (rt == NULL)
		return;

	if (pmtu >= dst_mtu(&rt->u.dst))
		goto out;

	if (pmtu < IPV6_MIN_MTU) {
		/*
		 * According to RFC2460, PMTU is set to the IPv6 Minimum Link
		 * MTU (1280) and a fragment header should always be included
		 * after a node receiving Too Big message reporting PMTU is
		 * less than the IPv6 Minimum Link MTU.
		 */
		pmtu = IPV6_MIN_MTU;
		allfrag = 1;
	}

	/* New mtu received -> path was valid.
	   They are sent only in response to data packets,
	   so that this nexthop apparently is reachable. --ANK
	 */
	dst_confirm(&rt->u.dst);

	/* Host route. If it is static, it would be better
	   not to override it, but add new one, so that
	   when cache entry will expire old pmtu
	   would return automatically.
	 */
	if (rt->rt6i_flags & RTF_CACHE) {
		rt->u.dst.metrics[RTAX_MTU-1] = pmtu;
		if (allfrag)
			rt->u.dst.metrics[RTAX_FEATURES-1] |= RTAX_FEATURE_ALLFRAG;
		dst_set_expires(&rt->u.dst, net->ipv6.sysctl.ip6_rt_mtu_expires);
		rt->rt6i_flags |= RTF_MODIFIED|RTF_EXPIRES;
		goto out;
	}

	/* Network route.
	   Two cases are possible:
	   1. It is connected route. Action: COW
	   2. It is gatewayed route or NONEXTHOP route. Action: clone it.
	 */
	if (!rt->rt6i_nexthop && !(rt->rt6i_flags & RTF_NONEXTHOP))
		nrt = rt6_alloc_cow(rt, daddr, saddr);
	else
		nrt = rt6_alloc_clone(rt, daddr);

	if (nrt) {
		nrt->u.dst.metrics[RTAX_MTU-1] = pmtu;
		if (allfrag)
			nrt->u.dst.metrics[RTAX_FEATURES-1] |= RTAX_FEATURE_ALLFRAG;

		/* According to RFC 1981, detecting PMTU increase shouldn't be
		 * happened within 5 mins, the recommended timer is 10 mins.
		 * Here this route expiration time is set to ip6_rt_mtu_expires
		 * which is 10 mins. After 10 mins the decreased pmtu is expired
		 * and detecting PMTU increase will be automatically happened.
		 */
		dst_set_expires(&nrt->u.dst, net->ipv6.sysctl.ip6_rt_mtu_expires);
		nrt->rt6i_flags |= RTF_DYNAMIC|RTF_EXPIRES;

		ip6_ins_rt(nrt);
	}
out:
	dst_release(&rt->u.dst);
}

/*
 *	Misc support functions
 */

static struct rt6_info * ip6_rt_copy(struct rt6_info *ort)
{
	struct net *net = dev_net(ort->rt6i_dev);
	struct rt6_info *rt = ip6_dst_alloc(net->ipv6.ip6_dst_ops);

	if (rt) {
		rt->u.dst.input = ort->u.dst.input;
		rt->u.dst.output = ort->u.dst.output;

		memcpy(rt->u.dst.metrics, ort->u.dst.metrics, RTAX_MAX*sizeof(u32));
		rt->u.dst.error = ort->u.dst.error;
		rt->u.dst.dev = ort->u.dst.dev;
		if (rt->u.dst.dev)
			dev_hold(rt->u.dst.dev);
		rt->rt6i_idev = ort->rt6i_idev;
		if (rt->rt6i_idev)
			in6_dev_hold(rt->rt6i_idev);
		rt->u.dst.lastuse = jiffies;
		rt->rt6i_expires = 0;

		ipv6_addr_copy(&rt->rt6i_gateway, &ort->rt6i_gateway);
		rt->rt6i_flags = ort->rt6i_flags & ~RTF_EXPIRES;
		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
		rt->rt6i_table = ort->rt6i_table;
	}
	return rt;
}

#ifdef CONFIG_IPV6_ROUTE_INFO
static struct rt6_info *rt6_get_route_info(struct net *net,
					   struct in6_addr *prefix, int prefixlen,
					   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 == NULL)
		return NULL;

	write_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->u.dst.rt6_next) {
		if (rt->rt6i_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->u.dst);
		break;
	}
out:
	write_unlock_bh(&table->tb6_lock);
	return rt;
}

static struct rt6_info *rt6_add_route_info(struct net *net,
					   struct in6_addr *prefix, int prefixlen,
					   struct in6_addr *gwaddr, int ifindex,
					   unsigned 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.pid = 0,
		.fc_nlinfo.nlh = NULL,
		.fc_nlinfo.nl_net = net,
	};

	ipv6_addr_copy(&cfg.fc_dst, prefix);
	ipv6_addr_copy(&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(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 == NULL)
		return NULL;

	write_lock_bh(&table->tb6_lock);
	for (rt = table->tb6_root.leaf; rt; rt=rt->u.dst.rt6_next) {
		if (dev == rt->rt6i_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->u.dst);
	write_unlock_bh(&table->tb6_lock);
	return rt;
}

struct rt6_info *rt6_add_dflt_router(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.pid = 0,
		.fc_nlinfo.nlh = NULL,
		.fc_nlinfo.nl_net = dev_net(dev),
	};

	ipv6_addr_copy(&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 == NULL)
		return;

restart:
	read_lock_bh(&table->tb6_lock);
	for (rt = table->tb6_root.leaf; rt; rt = rt->u.dst.rt6_next) {
		if (rt->rt6i_flags & (RTF_DEFAULT | RTF_ADDRCONF)) {
			dst_hold(&rt->u.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;

	ipv6_addr_copy(&cfg->fc_dst, &rtmsg->rtmsg_dst);
	ipv6_addr_copy(&cfg->fc_src, &rtmsg->rtmsg_src);
	ipv6_addr_copy(&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, int 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 || type == IPV6_ADDR_RESERVED) {
			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, skb->dev);
	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,
				    int anycast)
{
	struct net *net = dev_net(idev->dev);
	struct rt6_info *rt = ip6_dst_alloc(net->ipv6.ip6_dst_ops);
	struct neighbour *neigh;

	if (rt == NULL)
		return ERR_PTR(-ENOMEM);

	dev_hold(net->loopback_dev);
	in6_dev_hold(idev);

	rt->u.dst.flags = DST_HOST;
	rt->u.dst.input = ip6_input;
	rt->u.dst.output = ip6_output;
	rt->rt6i_dev = net->loopback_dev;
	rt->rt6i_idev = idev;
	rt->u.dst.metrics[RTAX_MTU-1] = ipv6_get_mtu(rt->rt6i_dev);
	rt->u.dst.metrics[RTAX_ADVMSS-1] = ipv6_advmss(net, dst_mtu(&rt->u.dst));
	rt->u.dst.metrics[RTAX_HOPLIMIT-1] = -1;
	rt->u.dst.obsolete = -1;

	rt->rt6i_flags = RTF_UP | RTF_NONEXTHOP;
	if (anycast)
		rt->rt6i_flags |= RTF_ANYCAST;
	else
		rt->rt6i_flags |= RTF_LOCAL;
	neigh = ndisc_get_neigh(rt->rt6i_dev, &rt->rt6i_gateway);
	if (IS_ERR(neigh)) {
		dst_free(&rt->u.dst);

		/* We are casting this because that is the return
		 * value type.  But an errno encoded pointer is the
		 * same regardless of the underlying pointer type,
		 * and that's what we are returning.  So this is OK.
		 */
		return (struct rt6_info *) neigh;
	}
	rt->rt6i_nexthop = neigh;

	ipv6_addr_copy(&rt->rt6i_dst.addr, addr);
	rt->rt6i_dst.plen = 128;
	rt->rt6i_table = fib6_get_table(net, RT6_TABLE_LOCAL);

	atomic_set(&rt->u.dst.__refcnt, 1);

	return rt;
}

struct arg_dev_net {
	struct net_device *dev;
	struct net *net;
};

static int fib6_ifdown(struct rt6_info *rt, void *arg)
{
	struct net_device *dev = ((struct arg_dev_net *)arg)->dev;
	struct net *net = ((struct arg_dev_net *)arg)->net;

	if (((void *)rt->rt6i_dev == dev || dev == NULL) &&
	    rt != net->ipv6.ip6_null_entry) {
		RT6_TRACE("deleted by ifdown %p\n", rt);
		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 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;
	struct net *net = dev_net(arg->dev);

	/* 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 == NULL)
		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->rt6i_dev == arg->dev &&
	    !dst_metric_locked(&rt->u.dst, RTAX_MTU) &&
	    (dst_mtu(&rt->u.dst) >= arg->mtu ||
	     (dst_mtu(&rt->u.dst) < arg->mtu &&
	      dst_mtu(&rt->u.dst) == idev->cnf.mtu6))) {
		rt->u.dst.metrics[RTAX_MTU-1] = arg->mtu;
		rt->u.dst.metrics[RTAX_ADVMSS-1] = ipv6_advmss(net, arg->mtu);
	}
	return 0;
}

void rt6_mtu_change(struct net_device *dev, unsigned 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 },
};

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;

	if (rtm->rtm_type == RTN_UNREACHABLE)
		cfg->fc_flags |= RTF_REJECT;

	cfg->fc_nlinfo.pid = NETLINK_CB(skb).pid;
	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_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]);

	err = 0;
errout:
	return 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;

	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;

	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 pid, u32 seq,
			 int prefix, int nowait, unsigned int flags)
{
	struct rtmsg *rtm;
	struct nlmsghdr *nlh;
	long expires;
	u32 table;

	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, pid, seq, type, sizeof(*rtm), flags);
	if (nlh == NULL)
		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;
	NLA_PUT_U32(skb, RTA_TABLE, table);
	if (rt->rt6i_flags&RTF_REJECT)
		rtm->rtm_type = RTN_UNREACHABLE;
	else if (rt->rt6i_dev && (rt->rt6i_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)
		rtm->rtm_protocol = RTPROT_KERNEL;
	else if (rt->rt6i_flags&RTF_DEFAULT)
		rtm->rtm_protocol = RTPROT_RA;

	if (rt->rt6i_flags&RTF_CACHE)
		rtm->rtm_flags |= RTM_F_CLONED;

	if (dst) {
		NLA_PUT(skb, RTA_DST, 16, dst);
		rtm->rtm_dst_len = 128;
	} else if (rtm->rtm_dst_len)
		NLA_PUT(skb, RTA_DST, 16, &rt->rt6i_dst.addr);
#ifdef CONFIG_IPV6_SUBTREES
	if (src) {
		NLA_PUT(skb, RTA_SRC, 16, src);
		rtm->rtm_src_len = 128;
	} else if (rtm->rtm_src_len)
		NLA_PUT(skb, RTA_SRC, 16, &rt->rt6i_src.addr);
#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
			NLA_PUT_U32(skb, RTA_IIF, iif);
	} else if (dst) {
		struct inet6_dev *idev = ip6_dst_idev(&rt->u.dst);
		struct in6_addr saddr_buf;
		if (ipv6_dev_get_saddr(net, idev ? idev->dev : NULL,
				       dst, 0, &saddr_buf) == 0)
			NLA_PUT(skb, RTA_PREFSRC, 16, &saddr_buf);
	}

	if (rtnetlink_put_metrics(skb, rt->u.dst.metrics) < 0)
		goto nla_put_failure;

	if (rt->u.dst.neighbour)
		NLA_PUT(skb, RTA_GATEWAY, 16, &rt->u.dst.neighbour->primary_key);

	if (rt->u.dst.dev)
		NLA_PUT_U32(skb, RTA_OIF, rt->rt6i_dev->ifindex);

	NLA_PUT_U32(skb, RTA_PRIORITY, rt->rt6i_metric);

	if (!(rt->rt6i_flags & RTF_EXPIRES))
		expires = 0;
	else if (rt->rt6i_expires - jiffies < INT_MAX)
		expires = rt->rt6i_expires - jiffies;
	else
		expires = INT_MAX;

	if (rtnl_put_cacheinfo(skb, &rt->u.dst, 0, 0, 0,
			       expires, rt->u.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).pid, 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 flowi fl;
	int err, iif = 0;

	err = nlmsg_parse(nlh, sizeof(*rtm), tb, RTA_MAX, rtm_ipv6_policy);
	if (err < 0)
		goto errout;

	err = -EINVAL;
	memset(&fl, 0, sizeof(fl));

	if (tb[RTA_SRC]) {
		if (nla_len(tb[RTA_SRC]) < sizeof(struct in6_addr))
			goto errout;

		ipv6_addr_copy(&fl.fl6_src, nla_data(tb[RTA_SRC]));
	}

	if (tb[RTA_DST]) {
		if (nla_len(tb[RTA_DST]) < sizeof(struct in6_addr))
			goto errout;

		ipv6_addr_copy(&fl.fl6_dst, nla_data(tb[RTA_DST]));
	}

	if (tb[RTA_IIF])
		iif = nla_get_u32(tb[RTA_IIF]);

	if (tb[RTA_OIF])
		fl.oif = nla_get_u32(tb[RTA_OIF]);

	if (iif) {
		struct net_device *dev;
		dev = __dev_get_by_index(net, iif);
		if (!dev) {
			err = -ENODEV;
			goto errout;
		}
	}

	skb = alloc_skb(NLMSG_GOODSIZE, GFP_KERNEL);
	if (skb == NULL) {
		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));

	rt = (struct rt6_info*) ip6_route_output(net, NULL, &fl);
	skb_dst_set(skb, &rt->u.dst);

	err = rt6_fill_node(net, skb, rt, &fl.fl6_dst, &fl.fl6_src, iif,
			    RTM_NEWROUTE, NETLINK_CB(in_skb).pid,
			    nlh->nlmsg_seq, 0, 0, 0);
	if (err < 0) {
		kfree_skb(skb);
		goto errout;
	}

	err = rtnl_unicast(skb, net, NETLINK_CB(in_skb).pid);
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 != NULL ? info->nlh->nlmsg_seq : 0;

	skb = nlmsg_new(rt6_nlmsg_size(), gfp_any());
	if (skb == NULL)
		goto errout;

	err = rt6_fill_node(net, skb, rt, NULL, NULL, 0,
				event, info->pid, 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->pid, RTNLGRP_IPV6_ROUTE,
		    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->u.dst.dev = dev;
		net->ipv6.ip6_null_entry->rt6i_idev = in6_dev_get(dev);
#ifdef CONFIG_IPV6_MULTIPLE_TABLES
		net->ipv6.ip6_prohibit_entry->u.dst.dev = dev;
		net->ipv6.ip6_prohibit_entry->rt6i_idev = in6_dev_get(dev);
		net->ipv6.ip6_blk_hole_entry->u.dst.dev = dev;
		net->ipv6.ip6_blk_hole_entry->rt6i_idev = in6_dev_get(dev);
#endif
	}

	return NOTIFY_OK;
}

/*
 *	/proc
 */

#ifdef CONFIG_PROC_FS

#define RT6_INFO_LEN (32 + 4 + 32 + 4 + 32 + 40 + 5 + 1)

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;

	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

	if (rt->rt6i_nexthop) {
		seq_printf(m, "%pi6", rt->rt6i_nexthop->primary_key);
	} else {
		seq_puts(m, "00000000000000000000000000000000");
	}
	seq_printf(m, " %08x %08x %08x %08x %8s\n",
		   rt->rt6i_metric, atomic_read(&rt->u.dst.__refcnt),
		   rt->u.dst.__use, rt->rt6i_flags,
		   rt->rt6i_dev ? rt->rt6i_dev->name : "");
	return 0;
}

static int ipv6_route_show(struct seq_file *m, void *v)
{
	struct net *net = (struct net *)m->private;
	fib6_clean_all(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,
		   atomic_read(&net->ipv6.ip6_dst_ops->entries),
		   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, struct file * filp,
			      void __user *buffer, size_t *lenp, loff_t *ppos)
{
	struct net *net = current->nsproxy->net_ns;
	int delay = net->ipv6.sysctl.flush_delay;
	if (write) {
		proc_dointvec(ctl, write, filp, buffer, lenp, ppos);
		fib6_run_gc(delay <= 0 ? ~0UL : (unsigned long)delay, net);
		return 0;
	} else
		return -EINVAL;
}

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
	},
	{
		.ctl_name	=	NET_IPV6_ROUTE_GC_THRESH,
		.procname	=	"gc_thresh",
		.data		=	&ip6_dst_ops_template.gc_thresh,
		.maxlen		=	sizeof(int),
		.mode		=	0644,
		.proc_handler	=	proc_dointvec,
	},
	{
		.ctl_name	=	NET_IPV6_ROUTE_MAX_SIZE,
		.procname	=	"max_size",
		.data		=	&init_net.ipv6.sysctl.ip6_rt_max_size,
		.maxlen		=	sizeof(int),
		.mode		=	0644,
		.proc_handler	=	proc_dointvec,
	},
	{
		.ctl_name	=	NET_IPV6_ROUTE_GC_MIN_INTERVAL,
		.procname	=	"gc_min_interval",
		.data		=	&init_net.ipv6.sysctl.ip6_rt_gc_min_interval,
		.maxlen		=	sizeof(int),
		.mode		=	0644,
		.proc_handler	=	proc_dointvec_jiffies,
		.strategy	=	sysctl_jiffies,
	},
	{
		.ctl_name	=	NET_IPV6_ROUTE_GC_TIMEOUT,
		.procname	=	"gc_timeout",
		.data		=	&init_net.ipv6.sysctl.ip6_rt_gc_timeout,
		.maxlen		=	sizeof(int),
		.mode		=	0644,
		.proc_handler	=	proc_dointvec_jiffies,
		.strategy	=	sysctl_jiffies,
	},
	{
		.ctl_name	=	NET_IPV6_ROUTE_GC_INTERVAL,
		.procname	=	"gc_interval",
		.data		=	&init_net.ipv6.sysctl.ip6_rt_gc_interval,
		.maxlen		=	sizeof(int),
		.mode		=	0644,
		.proc_handler	=	proc_dointvec_jiffies,
		.strategy	=	sysctl_jiffies,
	},
	{
		.ctl_name	=	NET_IPV6_ROUTE_GC_ELASTICITY,
		.procname	=	"gc_elasticity",
		.data		=	&init_net.ipv6.sysctl.ip6_rt_gc_elasticity,
		.maxlen		=	sizeof(int),
		.mode		=	0644,
		.proc_handler	=	proc_dointvec_jiffies,
		.strategy	=	sysctl_jiffies,
	},
	{
		.ctl_name	=	NET_IPV6_ROUTE_MTU_EXPIRES,
		.procname	=	"mtu_expires",
		.data		=	&init_net.ipv6.sysctl.ip6_rt_mtu_expires,
		.maxlen		=	sizeof(int),
		.mode		=	0644,
		.proc_handler	=	proc_dointvec_jiffies,
		.strategy	=	sysctl_jiffies,
	},
	{
		.ctl_name	=	NET_IPV6_ROUTE_MIN_ADVMSS,
		.procname	=	"min_adv_mss",
		.data		=	&init_net.ipv6.sysctl.ip6_rt_min_advmss,
		.maxlen		=	sizeof(int),
		.mode		=	0644,
		.proc_handler	=	proc_dointvec_jiffies,
		.strategy	=	sysctl_jiffies,
	},
	{
		.ctl_name	=	NET_IPV6_ROUTE_GC_MIN_INTERVAL_MS,
		.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,
		.strategy	=	sysctl_ms_jiffies,
	},
	{ .ctl_name = 0 }
};

struct ctl_table *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[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;
	}

	return table;
}
#endif

static int ip6_route_net_init(struct net *net)
{
	int ret = -ENOMEM;

	net->ipv6.ip6_dst_ops = kmemdup(&ip6_dst_ops_template,
					sizeof(*net->ipv6.ip6_dst_ops),
					GFP_KERNEL);
	if (!net->ipv6.ip6_dst_ops)
		goto out;
	net->ipv6.ip6_dst_ops->dst_net = hold_net(net);

	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_ops;
	net->ipv6.ip6_null_entry->u.dst.path =
		(struct dst_entry *)net->ipv6.ip6_null_entry;
	net->ipv6.ip6_null_entry->u.dst.ops = net->ipv6.ip6_dst_ops;

#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->u.dst.path =
		(struct dst_entry *)net->ipv6.ip6_prohibit_entry;
	net->ipv6.ip6_prohibit_entry->u.dst.ops = net->ipv6.ip6_dst_ops;

	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->u.dst.path =
		(struct dst_entry *)net->ipv6.ip6_blk_hole_entry;
	net->ipv6.ip6_blk_hole_entry->u.dst.ops = net->ipv6.ip6_dst_ops;
#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;

#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
	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_ops:
	release_net(net->ipv6.ip6_dst_ops->dst_net);
	kfree(net->ipv6.ip6_dst_ops);
	goto out;
}

static void ip6_route_net_exit(struct net *net)
{
#ifdef CONFIG_PROC_FS
	proc_net_remove(net, "ipv6_route");
	proc_net_remove(net, "rt6_stats");
#endif
	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
	release_net(net->ipv6.ip6_dst_ops->dst_net);
	kfree(net->ipv6.ip6_dst_ops);
}

static struct pernet_operations ip6_route_net_ops = {
	.init = ip6_route_net_init,
	.exit = ip6_route_net_exit,
};

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 = register_pernet_subsys(&ip6_route_net_ops);
	if (ret)
		goto out_kmem_cache;

	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->u.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->u.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->u.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 = -ENOBUFS;
	if (__rtnl_register(PF_INET6, RTM_NEWROUTE, inet6_rtm_newroute, NULL) ||
	    __rtnl_register(PF_INET6, RTM_DELROUTE, inet6_rtm_delroute, NULL) ||
	    __rtnl_register(PF_INET6, RTM_GETROUTE, inet6_rtm_getroute, NULL))
		goto fib6_rules_init;

	ret = register_netdevice_notifier(&ip6_route_dev_notifier);
	if (ret)
		goto fib6_rules_init;

out:
	return ret;

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_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);
	fib6_rules_cleanup();
	xfrm6_fini();
	fib6_gc_cleanup();
	unregister_pernet_subsys(&ip6_route_net_ops);
	kmem_cache_destroy(ip6_dst_ops_template.kmem_cachep);
}
generated by cgit v1.2.2 (git 2.25.0) at 2025-07-24 01:10:32 -0400