linux/net/ipv4/fib_frontend.c

1320 lines
31 KiB
C
Raw Normal View History

/*
* INET An implementation of the TCP/IP protocol suite for the LINUX
* operating system. INET is implemented using the BSD Socket
* interface as the means of communication with the user level.
*
* IPv4 Forwarding Information Base: FIB frontend.
*
* Authors: Alexey Kuznetsov, <kuznet@ms2.inr.ac.ru>
*
* 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.
*/
#include <linux/module.h>
#include <asm/uaccess.h>
#include <linux/bitops.h>
#include <linux/capability.h>
#include <linux/types.h>
#include <linux/kernel.h>
#include <linux/mm.h>
#include <linux/string.h>
#include <linux/socket.h>
#include <linux/sockios.h>
#include <linux/errno.h>
#include <linux/in.h>
#include <linux/inet.h>
#include <linux/inetdevice.h>
#include <linux/netdevice.h>
#include <linux/if_addr.h>
#include <linux/if_arp.h>
#include <linux/skbuff.h>
#include <linux/cache.h>
#include <linux/init.h>
#include <linux/list.h>
include cleanup: Update gfp.h and slab.h includes to prepare for breaking implicit slab.h inclusion from percpu.h percpu.h is included by sched.h and module.h and thus ends up being included when building most .c files. percpu.h includes slab.h which in turn includes gfp.h making everything defined by the two files universally available and complicating inclusion dependencies. percpu.h -> slab.h dependency is about to be removed. Prepare for this change by updating users of gfp and slab facilities include those headers directly instead of assuming availability. As this conversion needs to touch large number of source files, the following script is used as the basis of conversion. http://userweb.kernel.org/~tj/misc/slabh-sweep.py The script does the followings. * Scan files for gfp and slab usages and update includes such that only the necessary includes are there. ie. if only gfp is used, gfp.h, if slab is used, slab.h. * When the script inserts a new include, it looks at the include blocks and try to put the new include such that its order conforms to its surrounding. It's put in the include block which contains core kernel includes, in the same order that the rest are ordered - alphabetical, Christmas tree, rev-Xmas-tree or at the end if there doesn't seem to be any matching order. * If the script can't find a place to put a new include (mostly because the file doesn't have fitting include block), it prints out an error message indicating which .h file needs to be added to the file. The conversion was done in the following steps. 1. The initial automatic conversion of all .c files updated slightly over 4000 files, deleting around 700 includes and adding ~480 gfp.h and ~3000 slab.h inclusions. The script emitted errors for ~400 files. 2. Each error was manually checked. Some didn't need the inclusion, some needed manual addition while adding it to implementation .h or embedding .c file was more appropriate for others. This step added inclusions to around 150 files. 3. The script was run again and the output was compared to the edits from #2 to make sure no file was left behind. 4. Several build tests were done and a couple of problems were fixed. e.g. lib/decompress_*.c used malloc/free() wrappers around slab APIs requiring slab.h to be added manually. 5. The script was run on all .h files but without automatically editing them as sprinkling gfp.h and slab.h inclusions around .h files could easily lead to inclusion dependency hell. Most gfp.h inclusion directives were ignored as stuff from gfp.h was usually wildly available and often used in preprocessor macros. Each slab.h inclusion directive was examined and added manually as necessary. 6. percpu.h was updated not to include slab.h. 7. Build test were done on the following configurations and failures were fixed. CONFIG_GCOV_KERNEL was turned off for all tests (as my distributed build env didn't work with gcov compiles) and a few more options had to be turned off depending on archs to make things build (like ipr on powerpc/64 which failed due to missing writeq). * x86 and x86_64 UP and SMP allmodconfig and a custom test config. * powerpc and powerpc64 SMP allmodconfig * sparc and sparc64 SMP allmodconfig * ia64 SMP allmodconfig * s390 SMP allmodconfig * alpha SMP allmodconfig * um on x86_64 SMP allmodconfig 8. percpu.h modifications were reverted so that it could be applied as a separate patch and serve as bisection point. Given the fact that I had only a couple of failures from tests on step 6, I'm fairly confident about the coverage of this conversion patch. If there is a breakage, it's likely to be something in one of the arch headers which should be easily discoverable easily on most builds of the specific arch. Signed-off-by: Tejun Heo <tj@kernel.org> Guess-its-ok-by: Christoph Lameter <cl@linux-foundation.org> Cc: Ingo Molnar <mingo@redhat.com> Cc: Lee Schermerhorn <Lee.Schermerhorn@hp.com>
2010-03-24 16:04:11 +08:00
#include <linux/slab.h>
#include <net/ip.h>
#include <net/protocol.h>
#include <net/route.h>
#include <net/tcp.h>
#include <net/sock.h>
#include <net/arp.h>
#include <net/ip_fib.h>
#include <net/rtnetlink.h>
#include <net/xfrm.h>
#include <net/l3mdev.h>
#include <trace/events/fib.h>
#ifndef CONFIG_IP_MULTIPLE_TABLES
static int __net_init fib4_rules_init(struct net *net)
{
struct fib_table *local_table, *main_table;
main_table = fib_trie_table(RT_TABLE_MAIN, NULL);
if (!main_table)
return -ENOMEM;
local_table = fib_trie_table(RT_TABLE_LOCAL, main_table);
if (!local_table)
goto fail;
hlist_add_head_rcu(&local_table->tb_hlist,
&net->ipv4.fib_table_hash[TABLE_LOCAL_INDEX]);
hlist_add_head_rcu(&main_table->tb_hlist,
&net->ipv4.fib_table_hash[TABLE_MAIN_INDEX]);
return 0;
fail:
fib_free_table(main_table);
return -ENOMEM;
}
#else
struct fib_table *fib_new_table(struct net *net, u32 id)
{
struct fib_table *tb, *alias = NULL;
unsigned int h;
if (id == 0)
id = RT_TABLE_MAIN;
tb = fib_get_table(net, id);
if (tb)
return tb;
if (id == RT_TABLE_LOCAL)
alias = fib_new_table(net, RT_TABLE_MAIN);
tb = fib_trie_table(id, alias);
if (!tb)
return NULL;
switch (id) {
case RT_TABLE_LOCAL:
rcu_assign_pointer(net->ipv4.fib_local, tb);
break;
case RT_TABLE_MAIN:
rcu_assign_pointer(net->ipv4.fib_main, tb);
break;
case RT_TABLE_DEFAULT:
rcu_assign_pointer(net->ipv4.fib_default, tb);
break;
default:
break;
}
h = id & (FIB_TABLE_HASHSZ - 1);
hlist_add_head_rcu(&tb->tb_hlist, &net->ipv4.fib_table_hash[h]);
return tb;
}
/* caller must hold either rtnl or rcu read lock */
struct fib_table *fib_get_table(struct net *net, u32 id)
{
struct fib_table *tb;
struct hlist_head *head;
unsigned int h;
if (id == 0)
id = RT_TABLE_MAIN;
h = id & (FIB_TABLE_HASHSZ - 1);
head = &net->ipv4.fib_table_hash[h];
hlist: drop the node parameter from iterators I'm not sure why, but the hlist for each entry iterators were conceived list_for_each_entry(pos, head, member) The hlist ones were greedy and wanted an extra parameter: hlist_for_each_entry(tpos, pos, head, member) Why did they need an extra pos parameter? I'm not quite sure. Not only they don't really need it, it also prevents the iterator from looking exactly like the list iterator, which is unfortunate. Besides the semantic patch, there was some manual work required: - Fix up the actual hlist iterators in linux/list.h - Fix up the declaration of other iterators based on the hlist ones. - A very small amount of places were using the 'node' parameter, this was modified to use 'obj->member' instead. - Coccinelle didn't handle the hlist_for_each_entry_safe iterator properly, so those had to be fixed up manually. The semantic patch which is mostly the work of Peter Senna Tschudin is here: @@ iterator name hlist_for_each_entry, hlist_for_each_entry_continue, hlist_for_each_entry_from, hlist_for_each_entry_rcu, hlist_for_each_entry_rcu_bh, hlist_for_each_entry_continue_rcu_bh, for_each_busy_worker, ax25_uid_for_each, ax25_for_each, inet_bind_bucket_for_each, sctp_for_each_hentry, sk_for_each, sk_for_each_rcu, sk_for_each_from, sk_for_each_safe, sk_for_each_bound, hlist_for_each_entry_safe, hlist_for_each_entry_continue_rcu, nr_neigh_for_each, nr_neigh_for_each_safe, nr_node_for_each, nr_node_for_each_safe, for_each_gfn_indirect_valid_sp, for_each_gfn_sp, for_each_host; type T; expression a,c,d,e; identifier b; statement S; @@ -T b; <+... when != b ( hlist_for_each_entry(a, - b, c, d) S | hlist_for_each_entry_continue(a, - b, c) S | hlist_for_each_entry_from(a, - b, c) S | hlist_for_each_entry_rcu(a, - b, c, d) S | hlist_for_each_entry_rcu_bh(a, - b, c, d) S | hlist_for_each_entry_continue_rcu_bh(a, - b, c) S | for_each_busy_worker(a, c, - b, d) S | ax25_uid_for_each(a, - b, c) S | ax25_for_each(a, - b, c) S | inet_bind_bucket_for_each(a, - b, c) S | sctp_for_each_hentry(a, - b, c) S | sk_for_each(a, - b, c) S | sk_for_each_rcu(a, - b, c) S | sk_for_each_from -(a, b) +(a) S + sk_for_each_from(a) S | sk_for_each_safe(a, - b, c, d) S | sk_for_each_bound(a, - b, c) S | hlist_for_each_entry_safe(a, - b, c, d, e) S | hlist_for_each_entry_continue_rcu(a, - b, c) S | nr_neigh_for_each(a, - b, c) S | nr_neigh_for_each_safe(a, - b, c, d) S | nr_node_for_each(a, - b, c) S | nr_node_for_each_safe(a, - b, c, d) S | - for_each_gfn_sp(a, c, d, b) S + for_each_gfn_sp(a, c, d) S | - for_each_gfn_indirect_valid_sp(a, c, d, b) S + for_each_gfn_indirect_valid_sp(a, c, d) S | for_each_host(a, - b, c) S | for_each_host_safe(a, - b, c, d) S | for_each_mesh_entry(a, - b, c, d) S ) ...+> [akpm@linux-foundation.org: drop bogus change from net/ipv4/raw.c] [akpm@linux-foundation.org: drop bogus hunk from net/ipv6/raw.c] [akpm@linux-foundation.org: checkpatch fixes] [akpm@linux-foundation.org: fix warnings] [akpm@linux-foudnation.org: redo intrusive kvm changes] Tested-by: Peter Senna Tschudin <peter.senna@gmail.com> Acked-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Signed-off-by: Sasha Levin <sasha.levin@oracle.com> Cc: Wu Fengguang <fengguang.wu@intel.com> Cc: Marcelo Tosatti <mtosatti@redhat.com> Cc: Gleb Natapov <gleb@redhat.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2013-02-28 09:06:00 +08:00
hlist_for_each_entry_rcu(tb, head, tb_hlist) {
if (tb->tb_id == id)
return tb;
}
return NULL;
}
#endif /* CONFIG_IP_MULTIPLE_TABLES */
static void fib_replace_table(struct net *net, struct fib_table *old,
struct fib_table *new)
{
#ifdef CONFIG_IP_MULTIPLE_TABLES
switch (new->tb_id) {
case RT_TABLE_LOCAL:
rcu_assign_pointer(net->ipv4.fib_local, new);
break;
case RT_TABLE_MAIN:
rcu_assign_pointer(net->ipv4.fib_main, new);
break;
case RT_TABLE_DEFAULT:
rcu_assign_pointer(net->ipv4.fib_default, new);
break;
default:
break;
}
#endif
/* replace the old table in the hlist */
hlist_replace_rcu(&old->tb_hlist, &new->tb_hlist);
}
int fib_unmerge(struct net *net)
{
struct fib_table *old, *new;
/* attempt to fetch local table if it has been allocated */
old = fib_get_table(net, RT_TABLE_LOCAL);
if (!old)
return 0;
new = fib_trie_unmerge(old);
if (!new)
return -ENOMEM;
/* replace merged table with clean table */
if (new != old) {
fib_replace_table(net, old, new);
fib_free_table(old);
}
return 0;
}
static void fib_flush(struct net *net)
{
int flushed = 0;
unsigned int h;
for (h = 0; h < FIB_TABLE_HASHSZ; h++) {
struct hlist_head *head = &net->ipv4.fib_table_hash[h];
struct hlist_node *tmp;
struct fib_table *tb;
hlist_for_each_entry_safe(tb, tmp, head, tb_hlist)
flushed += fib_table_flush(tb);
}
if (flushed)
rt_cache_flush(net);
}
void fib_flush_external(struct net *net)
{
struct fib_table *tb;
struct hlist_head *head;
unsigned int h;
for (h = 0; h < FIB_TABLE_HASHSZ; h++) {
head = &net->ipv4.fib_table_hash[h];
hlist_for_each_entry(tb, head, tb_hlist)
fib_table_flush_external(tb);
}
}
/*
* Find address type as if only "dev" was present in the system. If
* on_dev is NULL then all interfaces are taken into consideration.
*/
static inline unsigned int __inet_dev_addr_type(struct net *net,
const struct net_device *dev,
__be32 addr, u32 tb_id)
{
struct flowi4 fl4 = { .daddr = addr };
struct fib_result res;
unsigned int ret = RTN_BROADCAST;
struct fib_table *table;
if (ipv4_is_zeronet(addr) || ipv4_is_lbcast(addr))
return RTN_BROADCAST;
if (ipv4_is_multicast(addr))
return RTN_MULTICAST;
rcu_read_lock();
table = fib_get_table(net, tb_id);
if (table) {
ret = RTN_UNICAST;
if (!fib_table_lookup(table, &fl4, &res, FIB_LOOKUP_NOREF)) {
if (!dev || dev == res.fi->fib_dev)
ret = res.type;
}
}
rcu_read_unlock();
return ret;
}
unsigned int inet_addr_type_table(struct net *net, __be32 addr, u32 tb_id)
{
return __inet_dev_addr_type(net, NULL, addr, tb_id);
}
EXPORT_SYMBOL(inet_addr_type_table);
unsigned int inet_addr_type(struct net *net, __be32 addr)
{
return __inet_dev_addr_type(net, NULL, addr, RT_TABLE_LOCAL);
}
EXPORT_SYMBOL(inet_addr_type);
unsigned int inet_dev_addr_type(struct net *net, const struct net_device *dev,
__be32 addr)
{
u32 rt_table = l3mdev_fib_table(dev) ? : RT_TABLE_LOCAL;
return __inet_dev_addr_type(net, dev, addr, rt_table);
}
EXPORT_SYMBOL(inet_dev_addr_type);
/* inet_addr_type with dev == NULL but using the table from a dev
* if one is associated
*/
unsigned int inet_addr_type_dev_table(struct net *net,
const struct net_device *dev,
__be32 addr)
{
u32 rt_table = l3mdev_fib_table(dev) ? : RT_TABLE_LOCAL;
return __inet_dev_addr_type(net, NULL, addr, rt_table);
}
EXPORT_SYMBOL(inet_addr_type_dev_table);
__be32 fib_compute_spec_dst(struct sk_buff *skb)
{
struct net_device *dev = skb->dev;
struct in_device *in_dev;
struct fib_result res;
struct rtable *rt;
struct net *net;
int scope;
rt = skb_rtable(skb);
if ((rt->rt_flags & (RTCF_BROADCAST | RTCF_MULTICAST | RTCF_LOCAL)) ==
RTCF_LOCAL)
return ip_hdr(skb)->daddr;
in_dev = __in_dev_get_rcu(dev);
BUG_ON(!in_dev);
net = dev_net(dev);
scope = RT_SCOPE_UNIVERSE;
if (!ipv4_is_zeronet(ip_hdr(skb)->saddr)) {
struct flowi4 fl4 = {
.flowi4_iif = LOOPBACK_IFINDEX,
.daddr = ip_hdr(skb)->saddr,
.flowi4_tos = RT_TOS(ip_hdr(skb)->tos),
.flowi4_scope = scope,
.flowi4_mark = IN_DEV_SRC_VMARK(in_dev) ? skb->mark : 0,
};
net: ipv4 sysctl option to ignore routes when nexthop link is down This feature is only enabled with the new per-interface or ipv4 global sysctls called 'ignore_routes_with_linkdown'. net.ipv4.conf.all.ignore_routes_with_linkdown = 0 net.ipv4.conf.default.ignore_routes_with_linkdown = 0 net.ipv4.conf.lo.ignore_routes_with_linkdown = 0 ... When the above sysctls are set, will report to userspace that a route is dead and will no longer resolve to this nexthop when performing a fib lookup. This will signal to userspace that the route will not be selected. The signalling of a RTNH_F_DEAD is only passed to userspace if the sysctl is enabled and link is down. This was done as without it the netlink listeners would have no idea whether or not a nexthop would be selected. The kernel only sets RTNH_F_DEAD internally if the interface has IFF_UP cleared. With the new sysctl set, the following behavior can be observed (interface p8p1 is link-down): default via 10.0.5.2 dev p9p1 10.0.5.0/24 dev p9p1 proto kernel scope link src 10.0.5.15 70.0.0.0/24 dev p7p1 proto kernel scope link src 70.0.0.1 80.0.0.0/24 dev p8p1 proto kernel scope link src 80.0.0.1 dead linkdown 90.0.0.0/24 via 80.0.0.2 dev p8p1 metric 1 dead linkdown 90.0.0.0/24 via 70.0.0.2 dev p7p1 metric 2 90.0.0.1 via 70.0.0.2 dev p7p1 src 70.0.0.1 cache local 80.0.0.1 dev lo src 80.0.0.1 cache <local> 80.0.0.2 via 10.0.5.2 dev p9p1 src 10.0.5.15 cache While the route does remain in the table (so it can be modified if needed rather than being wiped away as it would be if IFF_UP was cleared), the proper next-hop is chosen automatically when the link is down. Now interface p8p1 is linked-up: default via 10.0.5.2 dev p9p1 10.0.5.0/24 dev p9p1 proto kernel scope link src 10.0.5.15 70.0.0.0/24 dev p7p1 proto kernel scope link src 70.0.0.1 80.0.0.0/24 dev p8p1 proto kernel scope link src 80.0.0.1 90.0.0.0/24 via 80.0.0.2 dev p8p1 metric 1 90.0.0.0/24 via 70.0.0.2 dev p7p1 metric 2 192.168.56.0/24 dev p2p1 proto kernel scope link src 192.168.56.2 90.0.0.1 via 80.0.0.2 dev p8p1 src 80.0.0.1 cache local 80.0.0.1 dev lo src 80.0.0.1 cache <local> 80.0.0.2 dev p8p1 src 80.0.0.1 cache and the output changes to what one would expect. If the sysctl is not set, the following output would be expected when p8p1 is down: default via 10.0.5.2 dev p9p1 10.0.5.0/24 dev p9p1 proto kernel scope link src 10.0.5.15 70.0.0.0/24 dev p7p1 proto kernel scope link src 70.0.0.1 80.0.0.0/24 dev p8p1 proto kernel scope link src 80.0.0.1 linkdown 90.0.0.0/24 via 80.0.0.2 dev p8p1 metric 1 linkdown 90.0.0.0/24 via 70.0.0.2 dev p7p1 metric 2 Since the dead flag does not appear, there should be no expectation that the kernel would skip using this route due to link being down. v2: Split kernel changes into 2 patches, this actually makes a behavioral change if the sysctl is set. Also took suggestion from Alex to simplify code by only checking sysctl during fib lookup and suggestion from Scott to add a per-interface sysctl. v3: Code clean-ups to make it more readable and efficient as well as a reverse path check fix. v4: Drop binary sysctl v5: Whitespace fixups from Dave v6: Style changes from Dave and checkpatch suggestions v7: One more checkpatch fixup Signed-off-by: Andy Gospodarek <gospo@cumulusnetworks.com> Signed-off-by: Dinesh Dutt <ddutt@cumulusnetworks.com> Acked-by: Scott Feldman <sfeldma@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2015-06-24 01:45:37 +08:00
if (!fib_lookup(net, &fl4, &res, 0))
return FIB_RES_PREFSRC(net, res);
} else {
scope = RT_SCOPE_LINK;
}
return inet_select_addr(dev, ip_hdr(skb)->saddr, scope);
}
/* Given (packet source, input interface) and optional (dst, oif, tos):
* - (main) check, that source is valid i.e. not broadcast or our local
* address.
* - figure out what "logical" interface this packet arrived
* and calculate "specific destination" address.
* - check, that packet arrived from expected physical interface.
fib: RCU conversion of fib_lookup() fib_lookup() converted to be called in RCU protected context, no reference taken and released on a contended cache line (fib_clntref) fib_table_lookup() and fib_semantic_match() get an additional parameter. struct fib_info gets an rcu_head field, and is freed after an rcu grace period. Stress test : (Sending 160.000.000 UDP frames on same neighbour, IP route cache disabled, dual E5540 @2.53GHz, 32bit kernel, FIB_HASH) (about same results for FIB_TRIE) Before patch : real 1m31.199s user 0m13.761s sys 23m24.780s After patch: real 1m5.375s user 0m14.997s sys 15m50.115s Before patch Profile : 13044.00 15.4% __ip_route_output_key vmlinux 8438.00 10.0% dst_destroy vmlinux 5983.00 7.1% fib_semantic_match vmlinux 5410.00 6.4% fib_rules_lookup vmlinux 4803.00 5.7% neigh_lookup vmlinux 4420.00 5.2% _raw_spin_lock vmlinux 3883.00 4.6% rt_set_nexthop vmlinux 3261.00 3.9% _raw_read_lock vmlinux 2794.00 3.3% fib_table_lookup vmlinux 2374.00 2.8% neigh_resolve_output vmlinux 2153.00 2.5% dst_alloc vmlinux 1502.00 1.8% _raw_read_lock_bh vmlinux 1484.00 1.8% kmem_cache_alloc vmlinux 1407.00 1.7% eth_header vmlinux 1406.00 1.7% ipv4_dst_destroy vmlinux 1298.00 1.5% __copy_from_user_ll vmlinux 1174.00 1.4% dev_queue_xmit vmlinux 1000.00 1.2% ip_output vmlinux After patch Profile : 13712.00 15.8% dst_destroy vmlinux 8548.00 9.9% __ip_route_output_key vmlinux 7017.00 8.1% neigh_lookup vmlinux 4554.00 5.3% fib_semantic_match vmlinux 4067.00 4.7% _raw_read_lock vmlinux 3491.00 4.0% dst_alloc vmlinux 3186.00 3.7% neigh_resolve_output vmlinux 3103.00 3.6% fib_table_lookup vmlinux 2098.00 2.4% _raw_read_lock_bh vmlinux 2081.00 2.4% kmem_cache_alloc vmlinux 2013.00 2.3% _raw_spin_lock vmlinux 1763.00 2.0% __copy_from_user_ll vmlinux 1763.00 2.0% ip_output vmlinux 1761.00 2.0% ipv4_dst_destroy vmlinux 1631.00 1.9% eth_header vmlinux 1440.00 1.7% _raw_read_unlock_bh vmlinux Reference results, if IP route cache is enabled : real 0m29.718s user 0m10.845s sys 7m37.341s 25213.00 29.5% __ip_route_output_key vmlinux 9011.00 10.5% dst_release vmlinux 4817.00 5.6% ip_push_pending_frames vmlinux 4232.00 5.0% ip_finish_output vmlinux 3940.00 4.6% udp_sendmsg vmlinux 3730.00 4.4% __copy_from_user_ll vmlinux 3716.00 4.4% ip_route_output_flow vmlinux 2451.00 2.9% __xfrm_lookup vmlinux 2221.00 2.6% ip_append_data vmlinux 1718.00 2.0% _raw_spin_lock_bh vmlinux 1655.00 1.9% __alloc_skb vmlinux 1572.00 1.8% sock_wfree vmlinux 1345.00 1.6% kfree vmlinux Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2010-10-05 18:41:36 +08:00
* called with rcu_read_lock()
*/
static int __fib_validate_source(struct sk_buff *skb, __be32 src, __be32 dst,
u8 tos, int oif, struct net_device *dev,
int rpf, struct in_device *idev, u32 *itag)
{
int ret, no_addr;
struct fib_result res;
struct flowi4 fl4;
struct net *net;
bool dev_match;
fl4.flowi4_oif = 0;
fl4.flowi4_iif = l3mdev_master_ifindex_rcu(dev);
if (!fl4.flowi4_iif)
fl4.flowi4_iif = oif ? : LOOPBACK_IFINDEX;
fl4.daddr = src;
fl4.saddr = dst;
fl4.flowi4_tos = tos;
fl4.flowi4_scope = RT_SCOPE_UNIVERSE;
fl4.flowi4_tun_key.tun_id = 0;
fl4.flowi4_flags = 0;
no_addr = idev->ifa_list == NULL;
fl4.flowi4_mark = IN_DEV_SRC_VMARK(idev) ? skb->mark : 0;
trace_fib_validate_source(dev, &fl4);
net = dev_net(dev);
net: ipv4 sysctl option to ignore routes when nexthop link is down This feature is only enabled with the new per-interface or ipv4 global sysctls called 'ignore_routes_with_linkdown'. net.ipv4.conf.all.ignore_routes_with_linkdown = 0 net.ipv4.conf.default.ignore_routes_with_linkdown = 0 net.ipv4.conf.lo.ignore_routes_with_linkdown = 0 ... When the above sysctls are set, will report to userspace that a route is dead and will no longer resolve to this nexthop when performing a fib lookup. This will signal to userspace that the route will not be selected. The signalling of a RTNH_F_DEAD is only passed to userspace if the sysctl is enabled and link is down. This was done as without it the netlink listeners would have no idea whether or not a nexthop would be selected. The kernel only sets RTNH_F_DEAD internally if the interface has IFF_UP cleared. With the new sysctl set, the following behavior can be observed (interface p8p1 is link-down): default via 10.0.5.2 dev p9p1 10.0.5.0/24 dev p9p1 proto kernel scope link src 10.0.5.15 70.0.0.0/24 dev p7p1 proto kernel scope link src 70.0.0.1 80.0.0.0/24 dev p8p1 proto kernel scope link src 80.0.0.1 dead linkdown 90.0.0.0/24 via 80.0.0.2 dev p8p1 metric 1 dead linkdown 90.0.0.0/24 via 70.0.0.2 dev p7p1 metric 2 90.0.0.1 via 70.0.0.2 dev p7p1 src 70.0.0.1 cache local 80.0.0.1 dev lo src 80.0.0.1 cache <local> 80.0.0.2 via 10.0.5.2 dev p9p1 src 10.0.5.15 cache While the route does remain in the table (so it can be modified if needed rather than being wiped away as it would be if IFF_UP was cleared), the proper next-hop is chosen automatically when the link is down. Now interface p8p1 is linked-up: default via 10.0.5.2 dev p9p1 10.0.5.0/24 dev p9p1 proto kernel scope link src 10.0.5.15 70.0.0.0/24 dev p7p1 proto kernel scope link src 70.0.0.1 80.0.0.0/24 dev p8p1 proto kernel scope link src 80.0.0.1 90.0.0.0/24 via 80.0.0.2 dev p8p1 metric 1 90.0.0.0/24 via 70.0.0.2 dev p7p1 metric 2 192.168.56.0/24 dev p2p1 proto kernel scope link src 192.168.56.2 90.0.0.1 via 80.0.0.2 dev p8p1 src 80.0.0.1 cache local 80.0.0.1 dev lo src 80.0.0.1 cache <local> 80.0.0.2 dev p8p1 src 80.0.0.1 cache and the output changes to what one would expect. If the sysctl is not set, the following output would be expected when p8p1 is down: default via 10.0.5.2 dev p9p1 10.0.5.0/24 dev p9p1 proto kernel scope link src 10.0.5.15 70.0.0.0/24 dev p7p1 proto kernel scope link src 70.0.0.1 80.0.0.0/24 dev p8p1 proto kernel scope link src 80.0.0.1 linkdown 90.0.0.0/24 via 80.0.0.2 dev p8p1 metric 1 linkdown 90.0.0.0/24 via 70.0.0.2 dev p7p1 metric 2 Since the dead flag does not appear, there should be no expectation that the kernel would skip using this route due to link being down. v2: Split kernel changes into 2 patches, this actually makes a behavioral change if the sysctl is set. Also took suggestion from Alex to simplify code by only checking sysctl during fib lookup and suggestion from Scott to add a per-interface sysctl. v3: Code clean-ups to make it more readable and efficient as well as a reverse path check fix. v4: Drop binary sysctl v5: Whitespace fixups from Dave v6: Style changes from Dave and checkpatch suggestions v7: One more checkpatch fixup Signed-off-by: Andy Gospodarek <gospo@cumulusnetworks.com> Signed-off-by: Dinesh Dutt <ddutt@cumulusnetworks.com> Acked-by: Scott Feldman <sfeldma@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2015-06-24 01:45:37 +08:00
if (fib_lookup(net, &fl4, &res, 0))
goto last_resort;
if (res.type != RTN_UNICAST &&
(res.type != RTN_LOCAL || !IN_DEV_ACCEPT_LOCAL(idev)))
goto e_inval;
if (!rpf && !fib_num_tclassid_users(dev_net(dev)) &&
(dev->ifindex != oif || !IN_DEV_TX_REDIRECTS(idev)))
goto last_resort;
fib_combine_itag(itag, &res);
dev_match = false;
#ifdef CONFIG_IP_ROUTE_MULTIPATH
for (ret = 0; ret < res.fi->fib_nhs; ret++) {
struct fib_nh *nh = &res.fi->fib_nh[ret];
if (nh->nh_dev == dev) {
dev_match = true;
break;
} else if (l3mdev_master_ifindex_rcu(nh->nh_dev) == dev->ifindex) {
dev_match = true;
break;
}
}
#else
if (FIB_RES_DEV(res) == dev)
dev_match = true;
#endif
if (dev_match) {
ret = FIB_RES_NH(res).nh_scope >= RT_SCOPE_HOST;
return ret;
}
if (no_addr)
goto last_resort;
if (rpf == 1)
goto e_rpf;
fl4.flowi4_oif = dev->ifindex;
ret = 0;
net: ipv4 sysctl option to ignore routes when nexthop link is down This feature is only enabled with the new per-interface or ipv4 global sysctls called 'ignore_routes_with_linkdown'. net.ipv4.conf.all.ignore_routes_with_linkdown = 0 net.ipv4.conf.default.ignore_routes_with_linkdown = 0 net.ipv4.conf.lo.ignore_routes_with_linkdown = 0 ... When the above sysctls are set, will report to userspace that a route is dead and will no longer resolve to this nexthop when performing a fib lookup. This will signal to userspace that the route will not be selected. The signalling of a RTNH_F_DEAD is only passed to userspace if the sysctl is enabled and link is down. This was done as without it the netlink listeners would have no idea whether or not a nexthop would be selected. The kernel only sets RTNH_F_DEAD internally if the interface has IFF_UP cleared. With the new sysctl set, the following behavior can be observed (interface p8p1 is link-down): default via 10.0.5.2 dev p9p1 10.0.5.0/24 dev p9p1 proto kernel scope link src 10.0.5.15 70.0.0.0/24 dev p7p1 proto kernel scope link src 70.0.0.1 80.0.0.0/24 dev p8p1 proto kernel scope link src 80.0.0.1 dead linkdown 90.0.0.0/24 via 80.0.0.2 dev p8p1 metric 1 dead linkdown 90.0.0.0/24 via 70.0.0.2 dev p7p1 metric 2 90.0.0.1 via 70.0.0.2 dev p7p1 src 70.0.0.1 cache local 80.0.0.1 dev lo src 80.0.0.1 cache <local> 80.0.0.2 via 10.0.5.2 dev p9p1 src 10.0.5.15 cache While the route does remain in the table (so it can be modified if needed rather than being wiped away as it would be if IFF_UP was cleared), the proper next-hop is chosen automatically when the link is down. Now interface p8p1 is linked-up: default via 10.0.5.2 dev p9p1 10.0.5.0/24 dev p9p1 proto kernel scope link src 10.0.5.15 70.0.0.0/24 dev p7p1 proto kernel scope link src 70.0.0.1 80.0.0.0/24 dev p8p1 proto kernel scope link src 80.0.0.1 90.0.0.0/24 via 80.0.0.2 dev p8p1 metric 1 90.0.0.0/24 via 70.0.0.2 dev p7p1 metric 2 192.168.56.0/24 dev p2p1 proto kernel scope link src 192.168.56.2 90.0.0.1 via 80.0.0.2 dev p8p1 src 80.0.0.1 cache local 80.0.0.1 dev lo src 80.0.0.1 cache <local> 80.0.0.2 dev p8p1 src 80.0.0.1 cache and the output changes to what one would expect. If the sysctl is not set, the following output would be expected when p8p1 is down: default via 10.0.5.2 dev p9p1 10.0.5.0/24 dev p9p1 proto kernel scope link src 10.0.5.15 70.0.0.0/24 dev p7p1 proto kernel scope link src 70.0.0.1 80.0.0.0/24 dev p8p1 proto kernel scope link src 80.0.0.1 linkdown 90.0.0.0/24 via 80.0.0.2 dev p8p1 metric 1 linkdown 90.0.0.0/24 via 70.0.0.2 dev p7p1 metric 2 Since the dead flag does not appear, there should be no expectation that the kernel would skip using this route due to link being down. v2: Split kernel changes into 2 patches, this actually makes a behavioral change if the sysctl is set. Also took suggestion from Alex to simplify code by only checking sysctl during fib lookup and suggestion from Scott to add a per-interface sysctl. v3: Code clean-ups to make it more readable and efficient as well as a reverse path check fix. v4: Drop binary sysctl v5: Whitespace fixups from Dave v6: Style changes from Dave and checkpatch suggestions v7: One more checkpatch fixup Signed-off-by: Andy Gospodarek <gospo@cumulusnetworks.com> Signed-off-by: Dinesh Dutt <ddutt@cumulusnetworks.com> Acked-by: Scott Feldman <sfeldma@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2015-06-24 01:45:37 +08:00
if (fib_lookup(net, &fl4, &res, FIB_LOOKUP_IGNORE_LINKSTATE) == 0) {
if (res.type == RTN_UNICAST)
ret = FIB_RES_NH(res).nh_scope >= RT_SCOPE_HOST;
}
return ret;
last_resort:
if (rpf)
goto e_rpf;
*itag = 0;
return 0;
e_inval:
return -EINVAL;
e_rpf:
return -EXDEV;
}
/* Ignore rp_filter for packets protected by IPsec. */
int fib_validate_source(struct sk_buff *skb, __be32 src, __be32 dst,
u8 tos, int oif, struct net_device *dev,
struct in_device *idev, u32 *itag)
{
int r = secpath_exists(skb) ? 0 : IN_DEV_RPFILTER(idev);
if (!r && !fib_num_tclassid_users(dev_net(dev)) &&
IN_DEV_ACCEPT_LOCAL(idev) &&
(dev->ifindex != oif || !IN_DEV_TX_REDIRECTS(idev))) {
*itag = 0;
return 0;
}
return __fib_validate_source(skb, src, dst, tos, oif, dev, r, idev, itag);
}
static inline __be32 sk_extract_addr(struct sockaddr *addr)
{
return ((struct sockaddr_in *) addr)->sin_addr.s_addr;
}
static int put_rtax(struct nlattr *mx, int len, int type, u32 value)
{
struct nlattr *nla;
nla = (struct nlattr *) ((char *) mx + len);
nla->nla_type = type;
nla->nla_len = nla_attr_size(4);
*(u32 *) nla_data(nla) = value;
return len + nla_total_size(4);
}
static int rtentry_to_fib_config(struct net *net, int cmd, struct rtentry *rt,
struct fib_config *cfg)
{
__be32 addr;
int plen;
memset(cfg, 0, sizeof(*cfg));
cfg->fc_nlinfo.nl_net = net;
if (rt->rt_dst.sa_family != AF_INET)
return -EAFNOSUPPORT;
/*
* Check mask for validity:
* a) it must be contiguous.
* b) destination must have all host bits clear.
* c) if application forgot to set correct family (AF_INET),
* reject request unless it is absolutely clear i.e.
* both family and mask are zero.
*/
plen = 32;
addr = sk_extract_addr(&rt->rt_dst);
if (!(rt->rt_flags & RTF_HOST)) {
__be32 mask = sk_extract_addr(&rt->rt_genmask);
if (rt->rt_genmask.sa_family != AF_INET) {
if (mask || rt->rt_genmask.sa_family)
return -EAFNOSUPPORT;
}
if (bad_mask(mask, addr))
return -EINVAL;
plen = inet_mask_len(mask);
}
cfg->fc_dst_len = plen;
cfg->fc_dst = addr;
if (cmd != SIOCDELRT) {
cfg->fc_nlflags = NLM_F_CREATE;
cfg->fc_protocol = RTPROT_BOOT;
}
if (rt->rt_metric)
cfg->fc_priority = rt->rt_metric - 1;
if (rt->rt_flags & RTF_REJECT) {
cfg->fc_scope = RT_SCOPE_HOST;
cfg->fc_type = RTN_UNREACHABLE;
return 0;
}
cfg->fc_scope = RT_SCOPE_NOWHERE;
cfg->fc_type = RTN_UNICAST;
if (rt->rt_dev) {
char *colon;
struct net_device *dev;
char devname[IFNAMSIZ];
if (copy_from_user(devname, rt->rt_dev, IFNAMSIZ-1))
return -EFAULT;
devname[IFNAMSIZ-1] = 0;
colon = strchr(devname, ':');
if (colon)
*colon = 0;
dev = __dev_get_by_name(net, devname);
if (!dev)
return -ENODEV;
cfg->fc_oif = dev->ifindex;
if (colon) {
struct in_ifaddr *ifa;
struct in_device *in_dev = __in_dev_get_rtnl(dev);
if (!in_dev)
return -ENODEV;
*colon = ':';
for (ifa = in_dev->ifa_list; ifa; ifa = ifa->ifa_next)
if (strcmp(ifa->ifa_label, devname) == 0)
break;
if (!ifa)
return -ENODEV;
cfg->fc_prefsrc = ifa->ifa_local;
}
}
addr = sk_extract_addr(&rt->rt_gateway);
if (rt->rt_gateway.sa_family == AF_INET && addr) {
unsigned int addr_type;
cfg->fc_gw = addr;
addr_type = inet_addr_type_table(net, addr, cfg->fc_table);
if (rt->rt_flags & RTF_GATEWAY &&
addr_type == RTN_UNICAST)
cfg->fc_scope = RT_SCOPE_UNIVERSE;
}
if (cmd == SIOCDELRT)
return 0;
if (rt->rt_flags & RTF_GATEWAY && !cfg->fc_gw)
return -EINVAL;
if (cfg->fc_scope == RT_SCOPE_NOWHERE)
cfg->fc_scope = RT_SCOPE_LINK;
if (rt->rt_flags & (RTF_MTU | RTF_WINDOW | RTF_IRTT)) {
struct nlattr *mx;
int len = 0;
mx = kzalloc(3 * nla_total_size(4), GFP_KERNEL);
if (!mx)
return -ENOMEM;
if (rt->rt_flags & RTF_MTU)
len = put_rtax(mx, len, RTAX_ADVMSS, rt->rt_mtu - 40);
if (rt->rt_flags & RTF_WINDOW)
len = put_rtax(mx, len, RTAX_WINDOW, rt->rt_window);
if (rt->rt_flags & RTF_IRTT)
len = put_rtax(mx, len, RTAX_RTT, rt->rt_irtt << 3);
cfg->fc_mx = mx;
cfg->fc_mx_len = len;
}
return 0;
}
/*
* Handle IP routing ioctl calls.
* These are used to manipulate the routing tables
*/
int ip_rt_ioctl(struct net *net, unsigned int cmd, void __user *arg)
{
struct fib_config cfg;
struct rtentry rt;
int err;
switch (cmd) {
case SIOCADDRT: /* Add a route */
case SIOCDELRT: /* Delete a route */
net: Allow userns root to control ipv4 Allow an unpriviled user who has created a user namespace, and then created a network namespace to effectively use the new network namespace, by reducing capable(CAP_NET_ADMIN) and capable(CAP_NET_RAW) calls to be ns_capable(net->user_ns, CAP_NET_ADMIN), or capable(net->user_ns, CAP_NET_RAW) calls. Settings that merely control a single network device are allowed. Either the network device is a logical network device where restrictions make no difference or the network device is hardware NIC that has been explicity moved from the initial network namespace. In general policy and network stack state changes are allowed while resource control is left unchanged. Allow creating raw sockets. Allow the SIOCSARP ioctl to control the arp cache. Allow the SIOCSIFFLAG ioctl to allow setting network device flags. Allow the SIOCSIFADDR ioctl to allow setting a netdevice ipv4 address. Allow the SIOCSIFBRDADDR ioctl to allow setting a netdevice ipv4 broadcast address. Allow the SIOCSIFDSTADDR ioctl to allow setting a netdevice ipv4 destination address. Allow the SIOCSIFNETMASK ioctl to allow setting a netdevice ipv4 netmask. Allow the SIOCADDRT and SIOCDELRT ioctls to allow adding and deleting ipv4 routes. Allow the SIOCADDTUNNEL, SIOCCHGTUNNEL and SIOCDELTUNNEL ioctls for adding, changing and deleting gre tunnels. Allow the SIOCADDTUNNEL, SIOCCHGTUNNEL and SIOCDELTUNNEL ioctls for adding, changing and deleting ipip tunnels. Allow the SIOCADDTUNNEL, SIOCCHGTUNNEL and SIOCDELTUNNEL ioctls for adding, changing and deleting ipsec virtual tunnel interfaces. Allow setting the MRT_INIT, MRT_DONE, MRT_ADD_VIF, MRT_DEL_VIF, MRT_ADD_MFC, MRT_DEL_MFC, MRT_ASSERT, MRT_PIM, MRT_TABLE socket options on multicast routing sockets. Allow setting and receiving IPOPT_CIPSO, IP_OPT_SEC, IP_OPT_SID and arbitrary ip options. Allow setting IP_SEC_POLICY/IP_XFRM_POLICY ipv4 socket option. Allow setting the IP_TRANSPARENT ipv4 socket option. Allow setting the TCP_REPAIR socket option. Allow setting the TCP_CONGESTION socket option. Signed-off-by: "Eric W. Biederman" <ebiederm@xmission.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2012-11-16 11:03:05 +08:00
if (!ns_capable(net->user_ns, CAP_NET_ADMIN))
return -EPERM;
if (copy_from_user(&rt, arg, sizeof(rt)))
return -EFAULT;
rtnl_lock();
err = rtentry_to_fib_config(net, cmd, &rt, &cfg);
if (err == 0) {
struct fib_table *tb;
if (cmd == SIOCDELRT) {
tb = fib_get_table(net, cfg.fc_table);
if (tb)
err = fib_table_delete(tb, &cfg);
else
err = -ESRCH;
} else {
tb = fib_new_table(net, cfg.fc_table);
if (tb)
err = fib_table_insert(tb, &cfg);
else
err = -ENOBUFS;
}
/* allocated by rtentry_to_fib_config() */
kfree(cfg.fc_mx);
}
rtnl_unlock();
return err;
}
return -EINVAL;
}
const struct nla_policy rtm_ipv4_policy[RTA_MAX + 1] = {
[RTA_DST] = { .type = NLA_U32 },
[RTA_SRC] = { .type = NLA_U32 },
[RTA_IIF] = { .type = NLA_U32 },
[RTA_OIF] = { .type = NLA_U32 },
[RTA_GATEWAY] = { .type = NLA_U32 },
[RTA_PRIORITY] = { .type = NLA_U32 },
[RTA_PREFSRC] = { .type = NLA_U32 },
[RTA_METRICS] = { .type = NLA_NESTED },
[RTA_MULTIPATH] = { .len = sizeof(struct rtnexthop) },
[RTA_FLOW] = { .type = NLA_U32 },
[RTA_ENCAP_TYPE] = { .type = NLA_U16 },
[RTA_ENCAP] = { .type = NLA_NESTED },
};
static int rtm_to_fib_config(struct net *net, struct sk_buff *skb,
struct nlmsghdr *nlh, struct fib_config *cfg)
{
struct nlattr *attr;
int err, remaining;
struct rtmsg *rtm;
err = nlmsg_validate(nlh, sizeof(*rtm), RTA_MAX, rtm_ipv4_policy);
if (err < 0)
goto errout;
memset(cfg, 0, sizeof(*cfg));
rtm = nlmsg_data(nlh);
cfg->fc_dst_len = rtm->rtm_dst_len;
cfg->fc_tos = rtm->rtm_tos;
cfg->fc_table = rtm->rtm_table;
cfg->fc_protocol = rtm->rtm_protocol;
cfg->fc_scope = rtm->rtm_scope;
cfg->fc_type = rtm->rtm_type;
cfg->fc_flags = rtm->rtm_flags;
cfg->fc_nlflags = nlh->nlmsg_flags;
cfg->fc_nlinfo.portid = NETLINK_CB(skb).portid;
cfg->fc_nlinfo.nlh = nlh;
cfg->fc_nlinfo.nl_net = net;
if (cfg->fc_type > RTN_MAX) {
err = -EINVAL;
goto errout;
}
nlmsg_for_each_attr(attr, nlh, sizeof(struct rtmsg), remaining) {
switch (nla_type(attr)) {
case RTA_DST:
cfg->fc_dst = nla_get_be32(attr);
break;
case RTA_OIF:
cfg->fc_oif = nla_get_u32(attr);
break;
case RTA_GATEWAY:
cfg->fc_gw = nla_get_be32(attr);
break;
case RTA_PRIORITY:
cfg->fc_priority = nla_get_u32(attr);
break;
case RTA_PREFSRC:
cfg->fc_prefsrc = nla_get_be32(attr);
break;
case RTA_METRICS:
cfg->fc_mx = nla_data(attr);
cfg->fc_mx_len = nla_len(attr);
break;
case RTA_MULTIPATH:
cfg->fc_mp = nla_data(attr);
cfg->fc_mp_len = nla_len(attr);
break;
case RTA_FLOW:
cfg->fc_flow = nla_get_u32(attr);
break;
case RTA_TABLE:
cfg->fc_table = nla_get_u32(attr);
break;
case RTA_ENCAP:
cfg->fc_encap = attr;
break;
case RTA_ENCAP_TYPE:
cfg->fc_encap_type = nla_get_u16(attr);
break;
}
}
return 0;
errout:
return err;
}
static int inet_rtm_delroute(struct sk_buff *skb, struct nlmsghdr *nlh)
{
struct net *net = sock_net(skb->sk);
struct fib_config cfg;
struct fib_table *tb;
int err;
err = rtm_to_fib_config(net, skb, nlh, &cfg);
if (err < 0)
goto errout;
tb = fib_get_table(net, cfg.fc_table);
if (!tb) {
err = -ESRCH;
goto errout;
}
err = fib_table_delete(tb, &cfg);
errout:
return err;
}
static int inet_rtm_newroute(struct sk_buff *skb, struct nlmsghdr *nlh)
{
struct net *net = sock_net(skb->sk);
struct fib_config cfg;
struct fib_table *tb;
int err;
err = rtm_to_fib_config(net, skb, nlh, &cfg);
if (err < 0)
goto errout;
tb = fib_new_table(net, cfg.fc_table);
if (!tb) {
err = -ENOBUFS;
goto errout;
}
err = fib_table_insert(tb, &cfg);
errout:
return err;
}
static int inet_dump_fib(struct sk_buff *skb, struct netlink_callback *cb)
{
struct net *net = sock_net(skb->sk);
unsigned int h, s_h;
unsigned int e = 0, s_e;
struct fib_table *tb;
struct hlist_head *head;
int dumped = 0;
if (nlmsg_len(cb->nlh) >= sizeof(struct rtmsg) &&
((struct rtmsg *) nlmsg_data(cb->nlh))->rtm_flags & RTM_F_CLONED)
return skb->len;
s_h = cb->args[0];
s_e = cb->args[1];
rcu_read_lock();
for (h = s_h; h < FIB_TABLE_HASHSZ; h++, s_e = 0) {
e = 0;
head = &net->ipv4.fib_table_hash[h];
hlist_for_each_entry_rcu(tb, head, tb_hlist) {
if (e < s_e)
goto next;
if (dumped)
memset(&cb->args[2], 0, sizeof(cb->args) -
2 * sizeof(cb->args[0]));
if (fib_table_dump(tb, skb, cb) < 0)
goto out;
dumped = 1;
next:
e++;
}
}
out:
rcu_read_unlock();
cb->args[1] = e;
cb->args[0] = h;
return skb->len;
}
/* Prepare and feed intra-kernel routing request.
* Really, it should be netlink message, but :-( netlink
* can be not configured, so that we feed it directly
* to fib engine. It is legal, because all events occur
* only when netlink is already locked.
*/
static void fib_magic(int cmd, int type, __be32 dst, int dst_len, struct in_ifaddr *ifa)
{
struct net *net = dev_net(ifa->ifa_dev->dev);
u32 tb_id = l3mdev_fib_table(ifa->ifa_dev->dev);
struct fib_table *tb;
struct fib_config cfg = {
.fc_protocol = RTPROT_KERNEL,
.fc_type = type,
.fc_dst = dst,
.fc_dst_len = dst_len,
.fc_prefsrc = ifa->ifa_local,
.fc_oif = ifa->ifa_dev->dev->ifindex,
.fc_nlflags = NLM_F_CREATE | NLM_F_APPEND,
.fc_nlinfo = {
.nl_net = net,
},
};
if (!tb_id)
tb_id = (type == RTN_UNICAST) ? RT_TABLE_MAIN : RT_TABLE_LOCAL;
tb = fib_new_table(net, tb_id);
if (!tb)
return;
cfg.fc_table = tb->tb_id;
if (type != RTN_LOCAL)
cfg.fc_scope = RT_SCOPE_LINK;
else
cfg.fc_scope = RT_SCOPE_HOST;
if (cmd == RTM_NEWROUTE)
fib_table_insert(tb, &cfg);
else
fib_table_delete(tb, &cfg);
}
void fib_add_ifaddr(struct in_ifaddr *ifa)
{
struct in_device *in_dev = ifa->ifa_dev;
struct net_device *dev = in_dev->dev;
struct in_ifaddr *prim = ifa;
__be32 mask = ifa->ifa_mask;
__be32 addr = ifa->ifa_local;
__be32 prefix = ifa->ifa_address & mask;
if (ifa->ifa_flags & IFA_F_SECONDARY) {
prim = inet_ifa_byprefix(in_dev, prefix, mask);
if (!prim) {
pr_warn("%s: bug: prim == NULL\n", __func__);
return;
}
}
fib_magic(RTM_NEWROUTE, RTN_LOCAL, addr, 32, prim);
if (!(dev->flags & IFF_UP))
return;
/* Add broadcast address, if it is explicitly assigned. */
if (ifa->ifa_broadcast && ifa->ifa_broadcast != htonl(0xFFFFFFFF))
fib_magic(RTM_NEWROUTE, RTN_BROADCAST, ifa->ifa_broadcast, 32, prim);
if (!ipv4_is_zeronet(prefix) && !(ifa->ifa_flags & IFA_F_SECONDARY) &&
(prefix != addr || ifa->ifa_prefixlen < 32)) {
if (!(ifa->ifa_flags & IFA_F_NOPREFIXROUTE))
fib_magic(RTM_NEWROUTE,
dev->flags & IFF_LOOPBACK ? RTN_LOCAL : RTN_UNICAST,
prefix, ifa->ifa_prefixlen, prim);
/* Add network specific broadcasts, when it takes a sense */
if (ifa->ifa_prefixlen < 31) {
fib_magic(RTM_NEWROUTE, RTN_BROADCAST, prefix, 32, prim);
fib_magic(RTM_NEWROUTE, RTN_BROADCAST, prefix | ~mask,
32, prim);
}
}
}
/* Delete primary or secondary address.
* Optionally, on secondary address promotion consider the addresses
* from subnet iprim as deleted, even if they are in device list.
* In this case the secondary ifa can be in device list.
*/
void fib_del_ifaddr(struct in_ifaddr *ifa, struct in_ifaddr *iprim)
{
struct in_device *in_dev = ifa->ifa_dev;
struct net_device *dev = in_dev->dev;
struct in_ifaddr *ifa1;
struct in_ifaddr *prim = ifa, *prim1 = NULL;
__be32 brd = ifa->ifa_address | ~ifa->ifa_mask;
__be32 any = ifa->ifa_address & ifa->ifa_mask;
#define LOCAL_OK 1
#define BRD_OK 2
#define BRD0_OK 4
#define BRD1_OK 8
unsigned int ok = 0;
int subnet = 0; /* Primary network */
int gone = 1; /* Address is missing */
int same_prefsrc = 0; /* Another primary with same IP */
if (ifa->ifa_flags & IFA_F_SECONDARY) {
prim = inet_ifa_byprefix(in_dev, any, ifa->ifa_mask);
if (!prim) {
pr_warn("%s: bug: prim == NULL\n", __func__);
return;
}
if (iprim && iprim != prim) {
pr_warn("%s: bug: iprim != prim\n", __func__);
return;
}
} else if (!ipv4_is_zeronet(any) &&
(any != ifa->ifa_local || ifa->ifa_prefixlen < 32)) {
if (!(ifa->ifa_flags & IFA_F_NOPREFIXROUTE))
fib_magic(RTM_DELROUTE,
dev->flags & IFF_LOOPBACK ? RTN_LOCAL : RTN_UNICAST,
any, ifa->ifa_prefixlen, prim);
subnet = 1;
}
if (in_dev->dead)
goto no_promotions;
/* Deletion is more complicated than add.
* We should take care of not to delete too much :-)
*
* Scan address list to be sure that addresses are really gone.
*/
for (ifa1 = in_dev->ifa_list; ifa1; ifa1 = ifa1->ifa_next) {
if (ifa1 == ifa) {
/* promotion, keep the IP */
gone = 0;
continue;
}
/* Ignore IFAs from our subnet */
if (iprim && ifa1->ifa_mask == iprim->ifa_mask &&
inet_ifa_match(ifa1->ifa_address, iprim))
continue;
/* Ignore ifa1 if it uses different primary IP (prefsrc) */
if (ifa1->ifa_flags & IFA_F_SECONDARY) {
/* Another address from our subnet? */
if (ifa1->ifa_mask == prim->ifa_mask &&
inet_ifa_match(ifa1->ifa_address, prim))
prim1 = prim;
else {
/* We reached the secondaries, so
* same_prefsrc should be determined.
*/
if (!same_prefsrc)
continue;
/* Search new prim1 if ifa1 is not
* using the current prim1
*/
if (!prim1 ||
ifa1->ifa_mask != prim1->ifa_mask ||
!inet_ifa_match(ifa1->ifa_address, prim1))
prim1 = inet_ifa_byprefix(in_dev,
ifa1->ifa_address,
ifa1->ifa_mask);
if (!prim1)
continue;
if (prim1->ifa_local != prim->ifa_local)
continue;
}
} else {
if (prim->ifa_local != ifa1->ifa_local)
continue;
prim1 = ifa1;
if (prim != prim1)
same_prefsrc = 1;
}
if (ifa->ifa_local == ifa1->ifa_local)
ok |= LOCAL_OK;
if (ifa->ifa_broadcast == ifa1->ifa_broadcast)
ok |= BRD_OK;
if (brd == ifa1->ifa_broadcast)
ok |= BRD1_OK;
if (any == ifa1->ifa_broadcast)
ok |= BRD0_OK;
/* primary has network specific broadcasts */
if (prim1 == ifa1 && ifa1->ifa_prefixlen < 31) {
__be32 brd1 = ifa1->ifa_address | ~ifa1->ifa_mask;
__be32 any1 = ifa1->ifa_address & ifa1->ifa_mask;
if (!ipv4_is_zeronet(any1)) {
if (ifa->ifa_broadcast == brd1 ||
ifa->ifa_broadcast == any1)
ok |= BRD_OK;
if (brd == brd1 || brd == any1)
ok |= BRD1_OK;
if (any == brd1 || any == any1)
ok |= BRD0_OK;
}
}
}
no_promotions:
if (!(ok & BRD_OK))
fib_magic(RTM_DELROUTE, RTN_BROADCAST, ifa->ifa_broadcast, 32, prim);
if (subnet && ifa->ifa_prefixlen < 31) {
if (!(ok & BRD1_OK))
fib_magic(RTM_DELROUTE, RTN_BROADCAST, brd, 32, prim);
if (!(ok & BRD0_OK))
fib_magic(RTM_DELROUTE, RTN_BROADCAST, any, 32, prim);
}
if (!(ok & LOCAL_OK)) {
unsigned int addr_type;
fib_magic(RTM_DELROUTE, RTN_LOCAL, ifa->ifa_local, 32, prim);
/* Check, that this local address finally disappeared. */
addr_type = inet_addr_type_dev_table(dev_net(dev), dev,
ifa->ifa_local);
if (gone && addr_type != RTN_LOCAL) {
/* And the last, but not the least thing.
* We must flush stray FIB entries.
*
* First of all, we scan fib_info list searching
* for stray nexthop entries, then ignite fib_flush.
*/
if (fib_sync_down_addr(dev_net(dev), ifa->ifa_local))
fib_flush(dev_net(dev));
}
}
#undef LOCAL_OK
#undef BRD_OK
#undef BRD0_OK
#undef BRD1_OK
}
static void nl_fib_lookup(struct net *net, struct fib_result_nl *frn)
{
struct fib_result res;
struct flowi4 fl4 = {
.flowi4_mark = frn->fl_mark,
.daddr = frn->fl_addr,
.flowi4_tos = frn->fl_tos,
.flowi4_scope = frn->fl_scope,
};
struct fib_table *tb;
rcu_read_lock();
tb = fib_get_table(net, frn->tb_id_in);
frn->err = -ENOENT;
if (tb) {
local_bh_disable();
frn->tb_id = tb->tb_id;
frn->err = fib_table_lookup(tb, &fl4, &res, FIB_LOOKUP_NOREF);
if (!frn->err) {
frn->prefixlen = res.prefixlen;
frn->nh_sel = res.nh_sel;
frn->type = res.type;
frn->scope = res.scope;
}
local_bh_enable();
}
rcu_read_unlock();
}
static void nl_fib_input(struct sk_buff *skb)
{
struct net *net;
struct fib_result_nl *frn;
struct nlmsghdr *nlh;
u32 portid;
net = sock_net(skb->sk);
nlh = nlmsg_hdr(skb);
if (skb->len < NLMSG_HDRLEN || skb->len < nlh->nlmsg_len ||
nlmsg_len(nlh) < sizeof(*frn))
return;
netlink: fix splat in skb_clone with large messages Since (c05cdb1 netlink: allow large data transfers from user-space), netlink splats if it invokes skb_clone on large netlink skbs since: * skb_shared_info was not correctly initialized. * skb->destructor is not set in the cloned skb. This was spotted by trinity: [ 894.990671] BUG: unable to handle kernel paging request at ffffc9000047b001 [ 894.991034] IP: [<ffffffff81a212c4>] skb_clone+0x24/0xc0 [...] [ 894.991034] Call Trace: [ 894.991034] [<ffffffff81ad299a>] nl_fib_input+0x6a/0x240 [ 894.991034] [<ffffffff81c3b7e6>] ? _raw_read_unlock+0x26/0x40 [ 894.991034] [<ffffffff81a5f189>] netlink_unicast+0x169/0x1e0 [ 894.991034] [<ffffffff81a601e1>] netlink_sendmsg+0x251/0x3d0 Fix it by: 1) introducing a new netlink_skb_clone function that is used in nl_fib_input, that sets our special skb->destructor in the cloned skb. Moreover, handle the release of the large cloned skb head area in the destructor path. 2) not allowing large skbuffs in the netlink broadcast path. I cannot find any reasonable use of the large data transfer using netlink in that path, moreover this helps to skip extra skb_clone handling. I found two more netlink clients that are cloning the skbs, but they are not in the sendmsg path. Therefore, the sole client cloning that I found seems to be the fib frontend. Thanks to Eric Dumazet for helping to address this issue. Reported-by: Fengguang Wu <fengguang.wu@intel.com> Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org> Signed-off-by: David S. Miller <davem@davemloft.net>
2013-06-28 09:04:23 +08:00
skb = netlink_skb_clone(skb, GFP_KERNEL);
if (!skb)
return;
nlh = nlmsg_hdr(skb);
frn = (struct fib_result_nl *) nlmsg_data(nlh);
nl_fib_lookup(net, frn);
portid = NETLINK_CB(skb).portid; /* netlink portid */
NETLINK_CB(skb).portid = 0; /* from kernel */
NETLINK_CB(skb).dst_group = 0; /* unicast */
netlink_unicast(net->ipv4.fibnl, skb, portid, MSG_DONTWAIT);
}
static int __net_init nl_fib_lookup_init(struct net *net)
{
struct sock *sk;
struct netlink_kernel_cfg cfg = {
.input = nl_fib_input,
};
sk = netlink_kernel_create(net, NETLINK_FIB_LOOKUP, &cfg);
if (!sk)
return -EAFNOSUPPORT;
net->ipv4.fibnl = sk;
return 0;
}
static void nl_fib_lookup_exit(struct net *net)
{
netlink_kernel_release(net->ipv4.fibnl);
net->ipv4.fibnl = NULL;
}
static void fib_disable_ip(struct net_device *dev, unsigned long event,
bool force)
{
if (fib_sync_down_dev(dev, event, force))
fib_flush(dev_net(dev));
rt_cache_flush(dev_net(dev));
arp_ifdown(dev);
}
static int fib_inetaddr_event(struct notifier_block *this, unsigned long event, void *ptr)
{
struct in_ifaddr *ifa = (struct in_ifaddr *)ptr;
struct net_device *dev = ifa->ifa_dev->dev;
struct net *net = dev_net(dev);
switch (event) {
case NETDEV_UP:
fib_add_ifaddr(ifa);
#ifdef CONFIG_IP_ROUTE_MULTIPATH
fib_sync_up(dev, RTNH_F_DEAD);
#endif
atomic_inc(&net->ipv4.dev_addr_genid);
rt_cache_flush(dev_net(dev));
break;
case NETDEV_DOWN:
fib_del_ifaddr(ifa, NULL);
atomic_inc(&net->ipv4.dev_addr_genid);
if (!ifa->ifa_dev->ifa_list) {
/* Last address was deleted from this interface.
* Disable IP.
*/
fib_disable_ip(dev, event, true);
} else {
rt_cache_flush(dev_net(dev));
}
break;
}
return NOTIFY_DONE;
}
static int fib_netdev_event(struct notifier_block *this, unsigned long event, void *ptr)
{
struct net_device *dev = netdev_notifier_info_to_dev(ptr);
struct netdev_notifier_changeupper_info *info;
struct in_device *in_dev;
struct net *net = dev_net(dev);
unsigned int flags;
if (event == NETDEV_UNREGISTER) {
fib_disable_ip(dev, event, true);
rt_flush_dev(dev);
return NOTIFY_DONE;
}
in_dev = __in_dev_get_rtnl(dev);
if (!in_dev)
return NOTIFY_DONE;
switch (event) {
case NETDEV_UP:
for_ifa(in_dev) {
fib_add_ifaddr(ifa);
} endfor_ifa(in_dev);
#ifdef CONFIG_IP_ROUTE_MULTIPATH
fib_sync_up(dev, RTNH_F_DEAD);
#endif
atomic_inc(&net->ipv4.dev_addr_genid);
rt_cache_flush(net);
break;
case NETDEV_DOWN:
fib_disable_ip(dev, event, false);
break;
case NETDEV_CHANGE:
flags = dev_get_flags(dev);
if (flags & (IFF_RUNNING | IFF_LOWER_UP))
fib_sync_up(dev, RTNH_F_LINKDOWN);
else
fib_sync_down_dev(dev, event, false);
/* fall through */
case NETDEV_CHANGEMTU:
rt_cache_flush(net);
break;
case NETDEV_CHANGEUPPER:
info = ptr;
/* flush all routes if dev is linked to or unlinked from
* an L3 master device (e.g., VRF)
*/
if (info->upper_dev && netif_is_l3_master(info->upper_dev))
fib_disable_ip(dev, NETDEV_DOWN, true);
break;
}
return NOTIFY_DONE;
}
static struct notifier_block fib_inetaddr_notifier = {
.notifier_call = fib_inetaddr_event,
};
static struct notifier_block fib_netdev_notifier = {
.notifier_call = fib_netdev_event,
};
static int __net_init ip_fib_net_init(struct net *net)
{
int err;
size_t size = sizeof(struct hlist_head) * FIB_TABLE_HASHSZ;
/* Avoid false sharing : Use at least a full cache line */
size = max_t(size_t, size, L1_CACHE_BYTES);
net->ipv4.fib_table_hash = kzalloc(size, GFP_KERNEL);
if (!net->ipv4.fib_table_hash)
return -ENOMEM;
err = fib4_rules_init(net);
if (err < 0)
goto fail;
return 0;
fail:
kfree(net->ipv4.fib_table_hash);
return err;
}
static void ip_fib_net_exit(struct net *net)
{
unsigned int i;
rtnl_lock();
#ifdef CONFIG_IP_MULTIPLE_TABLES
RCU_INIT_POINTER(net->ipv4.fib_local, NULL);
RCU_INIT_POINTER(net->ipv4.fib_main, NULL);
RCU_INIT_POINTER(net->ipv4.fib_default, NULL);
#endif
for (i = 0; i < FIB_TABLE_HASHSZ; i++) {
struct hlist_head *head = &net->ipv4.fib_table_hash[i];
hlist: drop the node parameter from iterators I'm not sure why, but the hlist for each entry iterators were conceived list_for_each_entry(pos, head, member) The hlist ones were greedy and wanted an extra parameter: hlist_for_each_entry(tpos, pos, head, member) Why did they need an extra pos parameter? I'm not quite sure. Not only they don't really need it, it also prevents the iterator from looking exactly like the list iterator, which is unfortunate. Besides the semantic patch, there was some manual work required: - Fix up the actual hlist iterators in linux/list.h - Fix up the declaration of other iterators based on the hlist ones. - A very small amount of places were using the 'node' parameter, this was modified to use 'obj->member' instead. - Coccinelle didn't handle the hlist_for_each_entry_safe iterator properly, so those had to be fixed up manually. The semantic patch which is mostly the work of Peter Senna Tschudin is here: @@ iterator name hlist_for_each_entry, hlist_for_each_entry_continue, hlist_for_each_entry_from, hlist_for_each_entry_rcu, hlist_for_each_entry_rcu_bh, hlist_for_each_entry_continue_rcu_bh, for_each_busy_worker, ax25_uid_for_each, ax25_for_each, inet_bind_bucket_for_each, sctp_for_each_hentry, sk_for_each, sk_for_each_rcu, sk_for_each_from, sk_for_each_safe, sk_for_each_bound, hlist_for_each_entry_safe, hlist_for_each_entry_continue_rcu, nr_neigh_for_each, nr_neigh_for_each_safe, nr_node_for_each, nr_node_for_each_safe, for_each_gfn_indirect_valid_sp, for_each_gfn_sp, for_each_host; type T; expression a,c,d,e; identifier b; statement S; @@ -T b; <+... when != b ( hlist_for_each_entry(a, - b, c, d) S | hlist_for_each_entry_continue(a, - b, c) S | hlist_for_each_entry_from(a, - b, c) S | hlist_for_each_entry_rcu(a, - b, c, d) S | hlist_for_each_entry_rcu_bh(a, - b, c, d) S | hlist_for_each_entry_continue_rcu_bh(a, - b, c) S | for_each_busy_worker(a, c, - b, d) S | ax25_uid_for_each(a, - b, c) S | ax25_for_each(a, - b, c) S | inet_bind_bucket_for_each(a, - b, c) S | sctp_for_each_hentry(a, - b, c) S | sk_for_each(a, - b, c) S | sk_for_each_rcu(a, - b, c) S | sk_for_each_from -(a, b) +(a) S + sk_for_each_from(a) S | sk_for_each_safe(a, - b, c, d) S | sk_for_each_bound(a, - b, c) S | hlist_for_each_entry_safe(a, - b, c, d, e) S | hlist_for_each_entry_continue_rcu(a, - b, c) S | nr_neigh_for_each(a, - b, c) S | nr_neigh_for_each_safe(a, - b, c, d) S | nr_node_for_each(a, - b, c) S | nr_node_for_each_safe(a, - b, c, d) S | - for_each_gfn_sp(a, c, d, b) S + for_each_gfn_sp(a, c, d) S | - for_each_gfn_indirect_valid_sp(a, c, d, b) S + for_each_gfn_indirect_valid_sp(a, c, d) S | for_each_host(a, - b, c) S | for_each_host_safe(a, - b, c, d) S | for_each_mesh_entry(a, - b, c, d) S ) ...+> [akpm@linux-foundation.org: drop bogus change from net/ipv4/raw.c] [akpm@linux-foundation.org: drop bogus hunk from net/ipv6/raw.c] [akpm@linux-foundation.org: checkpatch fixes] [akpm@linux-foundation.org: fix warnings] [akpm@linux-foudnation.org: redo intrusive kvm changes] Tested-by: Peter Senna Tschudin <peter.senna@gmail.com> Acked-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Signed-off-by: Sasha Levin <sasha.levin@oracle.com> Cc: Wu Fengguang <fengguang.wu@intel.com> Cc: Marcelo Tosatti <mtosatti@redhat.com> Cc: Gleb Natapov <gleb@redhat.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2013-02-28 09:06:00 +08:00
struct hlist_node *tmp;
struct fib_table *tb;
hlist: drop the node parameter from iterators I'm not sure why, but the hlist for each entry iterators were conceived list_for_each_entry(pos, head, member) The hlist ones were greedy and wanted an extra parameter: hlist_for_each_entry(tpos, pos, head, member) Why did they need an extra pos parameter? I'm not quite sure. Not only they don't really need it, it also prevents the iterator from looking exactly like the list iterator, which is unfortunate. Besides the semantic patch, there was some manual work required: - Fix up the actual hlist iterators in linux/list.h - Fix up the declaration of other iterators based on the hlist ones. - A very small amount of places were using the 'node' parameter, this was modified to use 'obj->member' instead. - Coccinelle didn't handle the hlist_for_each_entry_safe iterator properly, so those had to be fixed up manually. The semantic patch which is mostly the work of Peter Senna Tschudin is here: @@ iterator name hlist_for_each_entry, hlist_for_each_entry_continue, hlist_for_each_entry_from, hlist_for_each_entry_rcu, hlist_for_each_entry_rcu_bh, hlist_for_each_entry_continue_rcu_bh, for_each_busy_worker, ax25_uid_for_each, ax25_for_each, inet_bind_bucket_for_each, sctp_for_each_hentry, sk_for_each, sk_for_each_rcu, sk_for_each_from, sk_for_each_safe, sk_for_each_bound, hlist_for_each_entry_safe, hlist_for_each_entry_continue_rcu, nr_neigh_for_each, nr_neigh_for_each_safe, nr_node_for_each, nr_node_for_each_safe, for_each_gfn_indirect_valid_sp, for_each_gfn_sp, for_each_host; type T; expression a,c,d,e; identifier b; statement S; @@ -T b; <+... when != b ( hlist_for_each_entry(a, - b, c, d) S | hlist_for_each_entry_continue(a, - b, c) S | hlist_for_each_entry_from(a, - b, c) S | hlist_for_each_entry_rcu(a, - b, c, d) S | hlist_for_each_entry_rcu_bh(a, - b, c, d) S | hlist_for_each_entry_continue_rcu_bh(a, - b, c) S | for_each_busy_worker(a, c, - b, d) S | ax25_uid_for_each(a, - b, c) S | ax25_for_each(a, - b, c) S | inet_bind_bucket_for_each(a, - b, c) S | sctp_for_each_hentry(a, - b, c) S | sk_for_each(a, - b, c) S | sk_for_each_rcu(a, - b, c) S | sk_for_each_from -(a, b) +(a) S + sk_for_each_from(a) S | sk_for_each_safe(a, - b, c, d) S | sk_for_each_bound(a, - b, c) S | hlist_for_each_entry_safe(a, - b, c, d, e) S | hlist_for_each_entry_continue_rcu(a, - b, c) S | nr_neigh_for_each(a, - b, c) S | nr_neigh_for_each_safe(a, - b, c, d) S | nr_node_for_each(a, - b, c) S | nr_node_for_each_safe(a, - b, c, d) S | - for_each_gfn_sp(a, c, d, b) S + for_each_gfn_sp(a, c, d) S | - for_each_gfn_indirect_valid_sp(a, c, d, b) S + for_each_gfn_indirect_valid_sp(a, c, d) S | for_each_host(a, - b, c) S | for_each_host_safe(a, - b, c, d) S | for_each_mesh_entry(a, - b, c, d) S ) ...+> [akpm@linux-foundation.org: drop bogus change from net/ipv4/raw.c] [akpm@linux-foundation.org: drop bogus hunk from net/ipv6/raw.c] [akpm@linux-foundation.org: checkpatch fixes] [akpm@linux-foundation.org: fix warnings] [akpm@linux-foudnation.org: redo intrusive kvm changes] Tested-by: Peter Senna Tschudin <peter.senna@gmail.com> Acked-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Signed-off-by: Sasha Levin <sasha.levin@oracle.com> Cc: Wu Fengguang <fengguang.wu@intel.com> Cc: Marcelo Tosatti <mtosatti@redhat.com> Cc: Gleb Natapov <gleb@redhat.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2013-02-28 09:06:00 +08:00
hlist_for_each_entry_safe(tb, tmp, head, tb_hlist) {
hlist_del(&tb->tb_hlist);
fib_table_flush(tb);
fib_free_table(tb);
}
}
fib_trie: Fix warning on fib4_rules_exit This fixes the following warning: BUG: sleeping function called from invalid context at mm/slub.c:1268 in_atomic(): 1, irqs_disabled(): 0, pid: 6, name: kworker/u8:0 INFO: lockdep is turned off. CPU: 3 PID: 6 Comm: kworker/u8:0 Tainted: G W 4.0.0-rc5+ #895 Hardware name: Bochs Bochs, BIOS Bochs 01/01/2011 Workqueue: netns cleanup_net 0000000000000006 ffff88011953fa68 ffffffff81a203b6 000000002c3a2c39 ffff88011952a680 ffff88011953fa98 ffffffff8109daf0 ffff8801186c6aa8 ffffffff81fbc9e5 00000000000004f4 0000000000000000 ffff88011953fac8 Call Trace: [<ffffffff81a203b6>] dump_stack+0x4c/0x65 [<ffffffff8109daf0>] ___might_sleep+0x1c3/0x1cb [<ffffffff8109db70>] __might_sleep+0x78/0x80 [<ffffffff8117a60e>] slab_pre_alloc_hook+0x31/0x8f [<ffffffff8117d4f6>] __kmalloc+0x69/0x14e [<ffffffff818ed0e1>] ? kzalloc.constprop.20+0xe/0x10 [<ffffffff818ed0e1>] kzalloc.constprop.20+0xe/0x10 [<ffffffff818ef622>] fib_trie_table+0x27/0x8b [<ffffffff818ef6bd>] fib_trie_unmerge+0x37/0x2a6 [<ffffffff810b06e1>] ? arch_local_irq_save+0x9/0xc [<ffffffff818e9793>] fib_unmerge+0x2d/0xb3 [<ffffffff818f5f56>] fib4_rule_delete+0x1f/0x52 [<ffffffff817f1c3f>] ? fib_rules_unregister+0x30/0xb2 [<ffffffff817f1c8b>] fib_rules_unregister+0x7c/0xb2 [<ffffffff818f64a1>] fib4_rules_exit+0x15/0x18 [<ffffffff818e8c0a>] ip_fib_net_exit+0x23/0xf2 [<ffffffff818e91f8>] fib_net_exit+0x32/0x36 [<ffffffff817c8352>] ops_exit_list+0x45/0x57 [<ffffffff817c8d3d>] cleanup_net+0x13c/0x1cd [<ffffffff8108b05d>] process_one_work+0x255/0x4ad [<ffffffff8108af69>] ? process_one_work+0x161/0x4ad [<ffffffff8108b4b1>] worker_thread+0x1cd/0x2ab [<ffffffff8108b2e4>] ? process_scheduled_works+0x2f/0x2f [<ffffffff81090686>] kthread+0xd4/0xdc [<ffffffff8109ec8f>] ? local_clock+0x19/0x22 [<ffffffff810905b2>] ? __kthread_parkme+0x83/0x83 [<ffffffff81a2c0c8>] ret_from_fork+0x58/0x90 [<ffffffff810905b2>] ? __kthread_parkme+0x83/0x83 The issue was that as a part of exiting the default rules were being deleted which resulted in the local trie being unmerged. By moving the freeing of the FIB tables up we can avoid the unmerge since there is no local table left when we call the fib4_rules_exit function. Fixes: 0ddcf43d5d4a ("ipv4: FIB Local/MAIN table collapse") Reported-by: Cong Wang <xiyou.wangcong@gmail.com> Signed-off-by: Alexander Duyck <alexander.h.duyck@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2015-03-28 05:14:16 +08:00
#ifdef CONFIG_IP_MULTIPLE_TABLES
fib4_rules_exit(net);
#endif
rtnl_unlock();
kfree(net->ipv4.fib_table_hash);
}
static int __net_init fib_net_init(struct net *net)
{
int error;
#ifdef CONFIG_IP_ROUTE_CLASSID
net->ipv4.fib_num_tclassid_users = 0;
#endif
error = ip_fib_net_init(net);
if (error < 0)
goto out;
error = nl_fib_lookup_init(net);
if (error < 0)
goto out_nlfl;
error = fib_proc_init(net);
if (error < 0)
goto out_proc;
out:
return error;
out_proc:
nl_fib_lookup_exit(net);
out_nlfl:
ip_fib_net_exit(net);
goto out;
}
static void __net_exit fib_net_exit(struct net *net)
{
fib_proc_exit(net);
nl_fib_lookup_exit(net);
ip_fib_net_exit(net);
}
static struct pernet_operations fib_net_ops = {
.init = fib_net_init,
.exit = fib_net_exit,
};
void __init ip_fib_init(void)
{
rtnl_register(PF_INET, RTM_NEWROUTE, inet_rtm_newroute, NULL, NULL);
rtnl_register(PF_INET, RTM_DELROUTE, inet_rtm_delroute, NULL, NULL);
rtnl_register(PF_INET, RTM_GETROUTE, NULL, inet_dump_fib, NULL);
register_pernet_subsys(&fib_net_ops);
register_netdevice_notifier(&fib_netdev_notifier);
register_inetaddr_notifier(&fib_inetaddr_notifier);
fib_trie_init();
}