linux/net/ipv4/fib_semantics.c

1790 lines
42 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: semantics.
*
* 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/uaccess.h>
#include <linux/bitops.h>
#include <linux/types.h>
#include <linux/kernel.h>
#include <linux/jiffies.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_arp.h>
#include <linux/proc_fs.h>
#include <linux/skbuff.h>
#include <linux/init.h>
include cleanup: Update gfp.h and slab.h includes to prepare for breaking implicit slab.h inclusion from percpu.h percpu.h is included by sched.h and module.h and thus ends up being included when building most .c files. percpu.h includes slab.h which in turn includes gfp.h making everything defined by the two files universally available and complicating inclusion dependencies. percpu.h -> slab.h dependency is about to be removed. Prepare for this change by updating users of gfp and slab facilities include those headers directly instead of assuming availability. As this conversion needs to touch large number of source files, the following script is used as the basis of conversion. http://userweb.kernel.org/~tj/misc/slabh-sweep.py The script does the followings. * Scan files for gfp and slab usages and update includes such that only the necessary includes are there. ie. if only gfp is used, gfp.h, if slab is used, slab.h. * When the script inserts a new include, it looks at the include blocks and try to put the new include such that its order conforms to its surrounding. It's put in the include block which contains core kernel includes, in the same order that the rest are ordered - alphabetical, Christmas tree, rev-Xmas-tree or at the end if there doesn't seem to be any matching order. * If the script can't find a place to put a new include (mostly because the file doesn't have fitting include block), it prints out an error message indicating which .h file needs to be added to the file. The conversion was done in the following steps. 1. The initial automatic conversion of all .c files updated slightly over 4000 files, deleting around 700 includes and adding ~480 gfp.h and ~3000 slab.h inclusions. The script emitted errors for ~400 files. 2. Each error was manually checked. Some didn't need the inclusion, some needed manual addition while adding it to implementation .h or embedding .c file was more appropriate for others. This step added inclusions to around 150 files. 3. The script was run again and the output was compared to the edits from #2 to make sure no file was left behind. 4. Several build tests were done and a couple of problems were fixed. e.g. lib/decompress_*.c used malloc/free() wrappers around slab APIs requiring slab.h to be added manually. 5. The script was run on all .h files but without automatically editing them as sprinkling gfp.h and slab.h inclusions around .h files could easily lead to inclusion dependency hell. Most gfp.h inclusion directives were ignored as stuff from gfp.h was usually wildly available and often used in preprocessor macros. Each slab.h inclusion directive was examined and added manually as necessary. 6. percpu.h was updated not to include slab.h. 7. Build test were done on the following configurations and failures were fixed. CONFIG_GCOV_KERNEL was turned off for all tests (as my distributed build env didn't work with gcov compiles) and a few more options had to be turned off depending on archs to make things build (like ipr on powerpc/64 which failed due to missing writeq). * x86 and x86_64 UP and SMP allmodconfig and a custom test config. * powerpc and powerpc64 SMP allmodconfig * sparc and sparc64 SMP allmodconfig * ia64 SMP allmodconfig * s390 SMP allmodconfig * alpha SMP allmodconfig * um on x86_64 SMP allmodconfig 8. percpu.h modifications were reverted so that it could be applied as a separate patch and serve as bisection point. Given the fact that I had only a couple of failures from tests on step 6, I'm fairly confident about the coverage of this conversion patch. If there is a breakage, it's likely to be something in one of the arch headers which should be easily discoverable easily on most builds of the specific arch. Signed-off-by: Tejun Heo <tj@kernel.org> Guess-its-ok-by: Christoph Lameter <cl@linux-foundation.org> Cc: Ingo Molnar <mingo@redhat.com> Cc: Lee Schermerhorn <Lee.Schermerhorn@hp.com>
2010-03-24 08:04:11 +00:00
#include <linux/slab.h>
#include <linux/netlink.h>
#include <net/arp.h>
#include <net/ip.h>
#include <net/protocol.h>
#include <net/route.h>
#include <net/tcp.h>
#include <net/sock.h>
#include <net/ip_fib.h>
#include <net/netlink.h>
#include <net/nexthop.h>
#include <net/lwtunnel.h>
#include <net/fib_notifier.h>
#include "fib_lookup.h"
static DEFINE_SPINLOCK(fib_info_lock);
static struct hlist_head *fib_info_hash;
static struct hlist_head *fib_info_laddrhash;
static unsigned int fib_info_hash_size;
static unsigned int fib_info_cnt;
#define DEVINDEX_HASHBITS 8
#define DEVINDEX_HASHSIZE (1U << DEVINDEX_HASHBITS)
static struct hlist_head fib_info_devhash[DEVINDEX_HASHSIZE];
#ifdef CONFIG_IP_ROUTE_MULTIPATH
#define for_nexthops(fi) { \
int nhsel; const struct fib_nh *nh; \
for (nhsel = 0, nh = (fi)->fib_nh; \
nhsel < (fi)->fib_nhs; \
nh++, nhsel++)
#define change_nexthops(fi) { \
int nhsel; struct fib_nh *nexthop_nh; \
for (nhsel = 0, nexthop_nh = (struct fib_nh *)((fi)->fib_nh); \
nhsel < (fi)->fib_nhs; \
nexthop_nh++, nhsel++)
#else /* CONFIG_IP_ROUTE_MULTIPATH */
/* Hope, that gcc will optimize it to get rid of dummy loop */
#define for_nexthops(fi) { \
int nhsel; const struct fib_nh *nh = (fi)->fib_nh; \
for (nhsel = 0; nhsel < 1; nhsel++)
#define change_nexthops(fi) { \
int nhsel; \
struct fib_nh *nexthop_nh = (struct fib_nh *)((fi)->fib_nh); \
for (nhsel = 0; nhsel < 1; nhsel++)
#endif /* CONFIG_IP_ROUTE_MULTIPATH */
#define endfor_nexthops(fi) }
const struct fib_prop fib_props[RTN_MAX + 1] = {
[RTN_UNSPEC] = {
.error = 0,
.scope = RT_SCOPE_NOWHERE,
},
[RTN_UNICAST] = {
.error = 0,
.scope = RT_SCOPE_UNIVERSE,
},
[RTN_LOCAL] = {
.error = 0,
.scope = RT_SCOPE_HOST,
},
[RTN_BROADCAST] = {
.error = 0,
.scope = RT_SCOPE_LINK,
},
[RTN_ANYCAST] = {
.error = 0,
.scope = RT_SCOPE_LINK,
},
[RTN_MULTICAST] = {
.error = 0,
.scope = RT_SCOPE_UNIVERSE,
},
[RTN_BLACKHOLE] = {
.error = -EINVAL,
.scope = RT_SCOPE_UNIVERSE,
},
[RTN_UNREACHABLE] = {
.error = -EHOSTUNREACH,
.scope = RT_SCOPE_UNIVERSE,
},
[RTN_PROHIBIT] = {
.error = -EACCES,
.scope = RT_SCOPE_UNIVERSE,
},
[RTN_THROW] = {
.error = -EAGAIN,
.scope = RT_SCOPE_UNIVERSE,
},
[RTN_NAT] = {
.error = -EINVAL,
.scope = RT_SCOPE_NOWHERE,
},
[RTN_XRESOLVE] = {
.error = -EINVAL,
.scope = RT_SCOPE_NOWHERE,
},
};
static void rt_fibinfo_free(struct rtable __rcu **rtp)
{
struct rtable *rt = rcu_dereference_protected(*rtp, 1);
if (!rt)
return;
/* Not even needed : RCU_INIT_POINTER(*rtp, NULL);
* because we waited an RCU grace period before calling
* free_fib_info_rcu()
*/
dst_dev_put(&rt->dst);
dst_release_immediate(&rt->dst);
}
static void free_nh_exceptions(struct fib_nh *nh)
{
struct fnhe_hash_bucket *hash;
int i;
hash = rcu_dereference_protected(nh->nh_exceptions, 1);
if (!hash)
return;
for (i = 0; i < FNHE_HASH_SIZE; i++) {
struct fib_nh_exception *fnhe;
fnhe = rcu_dereference_protected(hash[i].chain, 1);
while (fnhe) {
struct fib_nh_exception *next;
next = rcu_dereference_protected(fnhe->fnhe_next, 1);
rt_fibinfo_free(&fnhe->fnhe_rth_input);
rt_fibinfo_free(&fnhe->fnhe_rth_output);
kfree(fnhe);
fnhe = next;
}
}
kfree(hash);
}
static void rt_fibinfo_free_cpus(struct rtable __rcu * __percpu *rtp)
{
int cpu;
if (!rtp)
return;
for_each_possible_cpu(cpu) {
struct rtable *rt;
rt = rcu_dereference_protected(*per_cpu_ptr(rtp, cpu), 1);
if (rt) {
dst_dev_put(&rt->dst);
dst_release_immediate(&rt->dst);
}
}
free_percpu(rtp);
}
/* Release a nexthop info record */
static void free_fib_info_rcu(struct rcu_head *head)
{
struct fib_info *fi = container_of(head, struct fib_info, rcu);
ipv4: fix the rcu race between free_fib_info and ip_route_output_slow We hit a kernel OOPS. <3>[23898.789643] BUG: sleeping function called from invalid context at /data/buildbot/workdir/ics/hardware/intel/linux-2.6/arch/x86/mm/fault.c:1103 <3>[23898.862215] in_atomic(): 0, irqs_disabled(): 0, pid: 10526, name: Thread-6683 <4>[23898.967805] HSU serial 0000:00:05.1: 0000:00:05.2:HSU serial prevented me to suspend... <4>[23899.258526] Pid: 10526, comm: Thread-6683 Tainted: G W 3.0.8-137685-ge7742f9 #1 <4>[23899.357404] HSU serial 0000:00:05.1: 0000:00:05.2:HSU serial prevented me to suspend... <4>[23899.904225] Call Trace: <4>[23899.989209] [<c1227f50>] ? pgtable_bad+0x130/0x130 <4>[23900.000416] [<c1238c2a>] __might_sleep+0x10a/0x110 <4>[23900.007357] [<c1228021>] do_page_fault+0xd1/0x3c0 <4>[23900.013764] [<c18e9ba9>] ? restore_all+0xf/0xf <4>[23900.024024] [<c17c007b>] ? napi_complete+0x8b/0x690 <4>[23900.029297] [<c1227f50>] ? pgtable_bad+0x130/0x130 <4>[23900.123739] [<c1227f50>] ? pgtable_bad+0x130/0x130 <4>[23900.128955] [<c18ea0c3>] error_code+0x5f/0x64 <4>[23900.133466] [<c1227f50>] ? pgtable_bad+0x130/0x130 <4>[23900.138450] [<c17f6298>] ? __ip_route_output_key+0x698/0x7c0 <4>[23900.144312] [<c17f5f8d>] ? __ip_route_output_key+0x38d/0x7c0 <4>[23900.150730] [<c17f63df>] ip_route_output_flow+0x1f/0x60 <4>[23900.156261] [<c181de58>] ip4_datagram_connect+0x188/0x2b0 <4>[23900.161960] [<c18e981f>] ? _raw_spin_unlock_bh+0x1f/0x30 <4>[23900.167834] [<c18298d6>] inet_dgram_connect+0x36/0x80 <4>[23900.173224] [<c14f9e88>] ? _copy_from_user+0x48/0x140 <4>[23900.178817] [<c17ab9da>] sys_connect+0x9a/0xd0 <4>[23900.183538] [<c132e93c>] ? alloc_file+0xdc/0x240 <4>[23900.189111] [<c123925d>] ? sub_preempt_count+0x3d/0x50 Function free_fib_info resets nexthop_nh->nh_dev to NULL before releasing fi. Other cpu might be accessing fi. Fixing it by delaying the releasing. With the patch, we ran MTBF testing on Android mobile for 12 hours and didn't trigger the issue. Thank Eric for very detailed review/checking the issue. Signed-off-by: Yanmin Zhang <yanmin_zhang@linux.intel.com> Signed-off-by: Kun Jiang <kunx.jiang@intel.com> Acked-by: Eric Dumazet <edumazet@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2012-05-23 15:39:45 +00:00
change_nexthops(fi) {
if (nexthop_nh->nh_dev)
dev_put(nexthop_nh->nh_dev);
lwtstate_put(nexthop_nh->nh_lwtstate);
free_nh_exceptions(nexthop_nh);
rt_fibinfo_free_cpus(nexthop_nh->nh_pcpu_rth_output);
rt_fibinfo_free(&nexthop_nh->nh_rth_input);
ipv4: fix the rcu race between free_fib_info and ip_route_output_slow We hit a kernel OOPS. <3>[23898.789643] BUG: sleeping function called from invalid context at /data/buildbot/workdir/ics/hardware/intel/linux-2.6/arch/x86/mm/fault.c:1103 <3>[23898.862215] in_atomic(): 0, irqs_disabled(): 0, pid: 10526, name: Thread-6683 <4>[23898.967805] HSU serial 0000:00:05.1: 0000:00:05.2:HSU serial prevented me to suspend... <4>[23899.258526] Pid: 10526, comm: Thread-6683 Tainted: G W 3.0.8-137685-ge7742f9 #1 <4>[23899.357404] HSU serial 0000:00:05.1: 0000:00:05.2:HSU serial prevented me to suspend... <4>[23899.904225] Call Trace: <4>[23899.989209] [<c1227f50>] ? pgtable_bad+0x130/0x130 <4>[23900.000416] [<c1238c2a>] __might_sleep+0x10a/0x110 <4>[23900.007357] [<c1228021>] do_page_fault+0xd1/0x3c0 <4>[23900.013764] [<c18e9ba9>] ? restore_all+0xf/0xf <4>[23900.024024] [<c17c007b>] ? napi_complete+0x8b/0x690 <4>[23900.029297] [<c1227f50>] ? pgtable_bad+0x130/0x130 <4>[23900.123739] [<c1227f50>] ? pgtable_bad+0x130/0x130 <4>[23900.128955] [<c18ea0c3>] error_code+0x5f/0x64 <4>[23900.133466] [<c1227f50>] ? pgtable_bad+0x130/0x130 <4>[23900.138450] [<c17f6298>] ? __ip_route_output_key+0x698/0x7c0 <4>[23900.144312] [<c17f5f8d>] ? __ip_route_output_key+0x38d/0x7c0 <4>[23900.150730] [<c17f63df>] ip_route_output_flow+0x1f/0x60 <4>[23900.156261] [<c181de58>] ip4_datagram_connect+0x188/0x2b0 <4>[23900.161960] [<c18e981f>] ? _raw_spin_unlock_bh+0x1f/0x30 <4>[23900.167834] [<c18298d6>] inet_dgram_connect+0x36/0x80 <4>[23900.173224] [<c14f9e88>] ? _copy_from_user+0x48/0x140 <4>[23900.178817] [<c17ab9da>] sys_connect+0x9a/0xd0 <4>[23900.183538] [<c132e93c>] ? alloc_file+0xdc/0x240 <4>[23900.189111] [<c123925d>] ? sub_preempt_count+0x3d/0x50 Function free_fib_info resets nexthop_nh->nh_dev to NULL before releasing fi. Other cpu might be accessing fi. Fixing it by delaying the releasing. With the patch, we ran MTBF testing on Android mobile for 12 hours and didn't trigger the issue. Thank Eric for very detailed review/checking the issue. Signed-off-by: Yanmin Zhang <yanmin_zhang@linux.intel.com> Signed-off-by: Kun Jiang <kunx.jiang@intel.com> Acked-by: Eric Dumazet <edumazet@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2012-05-23 15:39:45 +00:00
} endfor_nexthops(fi);
ip_fib_metrics_put(fi->fib_metrics);
kfree(fi);
}
void free_fib_info(struct fib_info *fi)
{
if (fi->fib_dead == 0) {
pr_warn("Freeing alive fib_info %p\n", fi);
return;
}
fib_info_cnt--;
#ifdef CONFIG_IP_ROUTE_CLASSID
change_nexthops(fi) {
if (nexthop_nh->nh_tclassid)
fi->fib_net->ipv4.fib_num_tclassid_users--;
} endfor_nexthops(fi);
#endif
call_rcu(&fi->rcu, free_fib_info_rcu);
}
EXPORT_SYMBOL_GPL(free_fib_info);
void fib_release_info(struct fib_info *fi)
{
spin_lock_bh(&fib_info_lock);
if (fi && --fi->fib_treeref == 0) {
hlist_del(&fi->fib_hash);
if (fi->fib_prefsrc)
hlist_del(&fi->fib_lhash);
change_nexthops(fi) {
if (!nexthop_nh->nh_dev)
continue;
hlist_del(&nexthop_nh->nh_hash);
} endfor_nexthops(fi)
fi->fib_dead = 1;
fib_info_put(fi);
}
spin_unlock_bh(&fib_info_lock);
}
static inline int nh_comp(const struct fib_info *fi, const struct fib_info *ofi)
{
const struct fib_nh *onh = ofi->fib_nh;
for_nexthops(fi) {
if (nh->nh_oif != onh->nh_oif ||
nh->nh_gw != onh->nh_gw ||
nh->nh_scope != onh->nh_scope ||
#ifdef CONFIG_IP_ROUTE_MULTIPATH
nh->nh_weight != onh->nh_weight ||
#endif
#ifdef CONFIG_IP_ROUTE_CLASSID
nh->nh_tclassid != onh->nh_tclassid ||
#endif
lwtunnel_cmp_encap(nh->nh_lwtstate, onh->nh_lwtstate) ||
((nh->nh_flags ^ onh->nh_flags) & ~RTNH_COMPARE_MASK))
return -1;
onh++;
} endfor_nexthops(fi);
return 0;
}
static inline unsigned int fib_devindex_hashfn(unsigned int val)
{
unsigned int mask = DEVINDEX_HASHSIZE - 1;
return (val ^
(val >> DEVINDEX_HASHBITS) ^
(val >> (DEVINDEX_HASHBITS * 2))) & mask;
}
static inline unsigned int fib_info_hashfn(const struct fib_info *fi)
{
unsigned int mask = (fib_info_hash_size - 1);
unsigned int val = fi->fib_nhs;
val ^= (fi->fib_protocol << 8) | fi->fib_scope;
val ^= (__force u32)fi->fib_prefsrc;
val ^= fi->fib_priority;
for_nexthops(fi) {
val ^= fib_devindex_hashfn(nh->nh_oif);
} endfor_nexthops(fi)
return (val ^ (val >> 7) ^ (val >> 12)) & mask;
}
static struct fib_info *fib_find_info(const struct fib_info *nfi)
{
struct hlist_head *head;
struct fib_info *fi;
unsigned int hash;
hash = fib_info_hashfn(nfi);
head = &fib_info_hash[hash];
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 01:06:00 +00:00
hlist_for_each_entry(fi, head, fib_hash) {
if (!net_eq(fi->fib_net, nfi->fib_net))
continue;
if (fi->fib_nhs != nfi->fib_nhs)
continue;
if (nfi->fib_protocol == fi->fib_protocol &&
nfi->fib_scope == fi->fib_scope &&
nfi->fib_prefsrc == fi->fib_prefsrc &&
nfi->fib_priority == fi->fib_priority &&
ipv4: add a fib_type to fib_info commit d2d68ba9fe8 (ipv4: Cache input routes in fib_info nexthops.) introduced a regression for forwarding. This was hard to reproduce but the symptom was that packets were delivered to local host instead of being forwarded. David suggested to add fib_type to fib_info so that we dont inadvertently share same fib_info for different purposes. With help from Julian Anastasov who provided very helpful hints, reproduced here : <quote> Can it be a problem related to fib_info reuse from different routes. For example, when local IP address is created for subnet we have: broadcast 192.168.0.255 dev DEV proto kernel scope link src 192.168.0.1 192.168.0.0/24 dev DEV proto kernel scope link src 192.168.0.1 local 192.168.0.1 dev DEV proto kernel scope host src 192.168.0.1 The "dev DEV proto kernel scope link src 192.168.0.1" is a reused fib_info structure where we put cached routes. The result can be same fib_info for 192.168.0.255 and 192.168.0.0/24. RTN_BROADCAST is cached only for input routes. Incoming broadcast to 192.168.0.255 can be cached and can cause problems for traffic forwarded to 192.168.0.0/24. So, this patch should solve the problem because it separates the broadcast from unicast traffic. And the ip_route_input_slow caching will work for local and broadcast input routes (above routes 1 and 3) just because they differ in scope and use different fib_info. </quote> Many thanks to Chris Clayton for his patience and help. Reported-by: Chris Clayton <chris2553@googlemail.com> Bisected-by: Chris Clayton <chris2553@googlemail.com> Reported-by: Dave Jones <davej@redhat.com> Signed-off-by: Eric Dumazet <edumazet@google.com> Cc: Julian Anastasov <ja@ssi.bg> Tested-by: Chris Clayton <chris2553@googlemail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2012-10-04 01:25:26 +00:00
nfi->fib_type == fi->fib_type &&
memcmp(nfi->fib_metrics, fi->fib_metrics,
sizeof(u32) * RTAX_MAX) == 0 &&
!((nfi->fib_flags ^ fi->fib_flags) & ~RTNH_COMPARE_MASK) &&
(nfi->fib_nhs == 0 || nh_comp(fi, nfi) == 0))
return fi;
}
return NULL;
}
/* Check, that the gateway is already configured.
* Used only by redirect accept routine.
*/
int ip_fib_check_default(__be32 gw, struct net_device *dev)
{
struct hlist_head *head;
struct fib_nh *nh;
unsigned int hash;
spin_lock(&fib_info_lock);
hash = fib_devindex_hashfn(dev->ifindex);
head = &fib_info_devhash[hash];
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 01:06:00 +00:00
hlist_for_each_entry(nh, head, nh_hash) {
if (nh->nh_dev == dev &&
nh->nh_gw == gw &&
!(nh->nh_flags & RTNH_F_DEAD)) {
spin_unlock(&fib_info_lock);
return 0;
}
}
spin_unlock(&fib_info_lock);
return -1;
}
static inline size_t fib_nlmsg_size(struct fib_info *fi)
{
size_t payload = NLMSG_ALIGN(sizeof(struct rtmsg))
+ nla_total_size(4) /* RTA_TABLE */
+ nla_total_size(4) /* RTA_DST */
+ nla_total_size(4) /* RTA_PRIORITY */
+ nla_total_size(4) /* RTA_PREFSRC */
+ nla_total_size(TCP_CA_NAME_MAX); /* RTAX_CC_ALGO */
/* space for nested metrics */
payload += nla_total_size((RTAX_MAX * nla_total_size(4)));
if (fi->fib_nhs) {
size_t nh_encapsize = 0;
/* Also handles the special case fib_nhs == 1 */
/* each nexthop is packed in an attribute */
size_t nhsize = nla_total_size(sizeof(struct rtnexthop));
/* may contain flow and gateway attribute */
nhsize += 2 * nla_total_size(4);
/* grab encap info */
for_nexthops(fi) {
if (nh->nh_lwtstate) {
/* RTA_ENCAP_TYPE */
nh_encapsize += lwtunnel_get_encap_size(
nh->nh_lwtstate);
/* RTA_ENCAP */
nh_encapsize += nla_total_size(2);
}
} endfor_nexthops(fi);
/* all nexthops are packed in a nested attribute */
payload += nla_total_size((fi->fib_nhs * nhsize) +
nh_encapsize);
}
return payload;
}
void rtmsg_fib(int event, __be32 key, struct fib_alias *fa,
int dst_len, u32 tb_id, const struct nl_info *info,
unsigned int nlm_flags)
{
struct sk_buff *skb;
u32 seq = info->nlh ? info->nlh->nlmsg_seq : 0;
int err = -ENOBUFS;
skb = nlmsg_new(fib_nlmsg_size(fa->fa_info), GFP_KERNEL);
if (!skb)
goto errout;
err = fib_dump_info(skb, info->portid, seq, event, tb_id,
fa->fa_type, key, dst_len,
fa->fa_tos, fa->fa_info, nlm_flags);
if (err < 0) {
/* -EMSGSIZE implies BUG in fib_nlmsg_size() */
WARN_ON(err == -EMSGSIZE);
kfree_skb(skb);
goto errout;
}
rtnl_notify(skb, info->nl_net, info->portid, RTNLGRP_IPV4_ROUTE,
2009-02-25 07:18:28 +00:00
info->nlh, GFP_KERNEL);
return;
errout:
if (err < 0)
rtnl_set_sk_err(info->nl_net, RTNLGRP_IPV4_ROUTE, err);
}
static int fib_detect_death(struct fib_info *fi, int order,
struct fib_info **last_resort, int *last_idx,
int dflt)
{
struct neighbour *n;
int state = NUD_NONE;
n = neigh_lookup(&arp_tbl, &fi->fib_nh[0].nh_gw, fi->fib_dev);
if (n) {
state = n->nud_state;
neigh_release(n);
} else {
return 0;
}
if (state == NUD_REACHABLE)
return 0;
if ((state & NUD_VALID) && order != dflt)
return 0;
if ((state & NUD_VALID) ||
(*last_idx < 0 && order > dflt && state != NUD_INCOMPLETE)) {
*last_resort = fi;
*last_idx = order;
}
return 1;
}
#ifdef CONFIG_IP_ROUTE_MULTIPATH
static int fib_count_nexthops(struct rtnexthop *rtnh, int remaining,
struct netlink_ext_ack *extack)
{
int nhs = 0;
while (rtnh_ok(rtnh, remaining)) {
nhs++;
rtnh = rtnh_next(rtnh, &remaining);
}
/* leftover implies invalid nexthop configuration, discard it */
if (remaining > 0) {
NL_SET_ERR_MSG(extack,
"Invalid nexthop configuration - extra data after nexthops");
nhs = 0;
}
return nhs;
}
static int fib_get_nhs(struct fib_info *fi, struct rtnexthop *rtnh,
int remaining, struct fib_config *cfg,
struct netlink_ext_ack *extack)
{
int ret;
change_nexthops(fi) {
int attrlen;
if (!rtnh_ok(rtnh, remaining)) {
NL_SET_ERR_MSG(extack,
"Invalid nexthop configuration - extra data after nexthop");
return -EINVAL;
}
if (rtnh->rtnh_flags & (RTNH_F_DEAD | RTNH_F_LINKDOWN)) {
NL_SET_ERR_MSG(extack,
"Invalid flags for nexthop - can not contain DEAD or LINKDOWN");
ipv4: reject RTNH_F_DEAD and RTNH_F_LINKDOWN from user space Vegard Nossum is reporting for a crash in fib_dump_info when nh_dev = NULL and fib_nhs == 1: Pid: 50, comm: netlink.exe Not tainted 4.7.0-rc5+ RIP: 0033:[<00000000602b3d18>] RSP: 0000000062623890 EFLAGS: 00010202 RAX: 0000000000000000 RBX: 000000006261b800 RCX: 0000000000000000 RDX: 0000000000000000 RSI: 0000000000000024 RDI: 000000006245ba00 RBP: 00000000626238f0 R08: 000000000000029c R09: 0000000000000000 R10: 0000000062468038 R11: 000000006245ba00 R12: 000000006245ba00 R13: 00000000625f96c0 R14: 00000000601e16f0 R15: 0000000000000000 Kernel panic - not syncing: Kernel mode fault at addr 0x2e0, ip 0x602b3d18 CPU: 0 PID: 50 Comm: netlink.exe Not tainted 4.7.0-rc5+ #581 Stack: 626238f0 960226a02 00000400 000000fe 62623910 600afca7 62623970 62623a48 62468038 00000018 00000000 00000000 Call Trace: [<602b3e93>] rtmsg_fib+0xd3/0x190 [<602b6680>] fib_table_insert+0x260/0x500 [<602b0e5d>] inet_rtm_newroute+0x4d/0x60 [<60250def>] rtnetlink_rcv_msg+0x8f/0x270 [<60267079>] netlink_rcv_skb+0xc9/0xe0 [<60250d4b>] rtnetlink_rcv+0x3b/0x50 [<60265400>] netlink_unicast+0x1a0/0x2c0 [<60265e47>] netlink_sendmsg+0x3f7/0x470 [<6021dc9a>] sock_sendmsg+0x3a/0x90 [<6021e0d0>] ___sys_sendmsg+0x300/0x360 [<6021fa64>] __sys_sendmsg+0x54/0xa0 [<6021fac0>] SyS_sendmsg+0x10/0x20 [<6001ea68>] handle_syscall+0x88/0x90 [<600295fd>] userspace+0x3fd/0x500 [<6001ac55>] fork_handler+0x85/0x90 $ addr2line -e vmlinux -i 0x602b3d18 include/linux/inetdevice.h:222 net/ipv4/fib_semantics.c:1264 Problem happens when RTNH_F_LINKDOWN is provided from user space when creating routes that do not use the flag, catched with netlink fuzzer. Currently, the kernel allows user space to set both flags to nh_flags and fib_flags but this is not intentional, the assumption was that they are not set. Fix this by rejecting both flags with EINVAL. Reported-by: Vegard Nossum <vegard.nossum@oracle.com> Fixes: 0eeb075fad73 ("net: ipv4 sysctl option to ignore routes when nexthop link is down") Signed-off-by: Julian Anastasov <ja@ssi.bg> Cc: Andy Gospodarek <gospo@cumulusnetworks.com> Cc: Dinesh Dutt <ddutt@cumulusnetworks.com> Cc: Scott Feldman <sfeldma@gmail.com> Reviewed-by: Andy Gospodarek <gospo@cumulusnetworks.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-07-10 18:11:55 +00:00
return -EINVAL;
}
ipv4: reject RTNH_F_DEAD and RTNH_F_LINKDOWN from user space Vegard Nossum is reporting for a crash in fib_dump_info when nh_dev = NULL and fib_nhs == 1: Pid: 50, comm: netlink.exe Not tainted 4.7.0-rc5+ RIP: 0033:[<00000000602b3d18>] RSP: 0000000062623890 EFLAGS: 00010202 RAX: 0000000000000000 RBX: 000000006261b800 RCX: 0000000000000000 RDX: 0000000000000000 RSI: 0000000000000024 RDI: 000000006245ba00 RBP: 00000000626238f0 R08: 000000000000029c R09: 0000000000000000 R10: 0000000062468038 R11: 000000006245ba00 R12: 000000006245ba00 R13: 00000000625f96c0 R14: 00000000601e16f0 R15: 0000000000000000 Kernel panic - not syncing: Kernel mode fault at addr 0x2e0, ip 0x602b3d18 CPU: 0 PID: 50 Comm: netlink.exe Not tainted 4.7.0-rc5+ #581 Stack: 626238f0 960226a02 00000400 000000fe 62623910 600afca7 62623970 62623a48 62468038 00000018 00000000 00000000 Call Trace: [<602b3e93>] rtmsg_fib+0xd3/0x190 [<602b6680>] fib_table_insert+0x260/0x500 [<602b0e5d>] inet_rtm_newroute+0x4d/0x60 [<60250def>] rtnetlink_rcv_msg+0x8f/0x270 [<60267079>] netlink_rcv_skb+0xc9/0xe0 [<60250d4b>] rtnetlink_rcv+0x3b/0x50 [<60265400>] netlink_unicast+0x1a0/0x2c0 [<60265e47>] netlink_sendmsg+0x3f7/0x470 [<6021dc9a>] sock_sendmsg+0x3a/0x90 [<6021e0d0>] ___sys_sendmsg+0x300/0x360 [<6021fa64>] __sys_sendmsg+0x54/0xa0 [<6021fac0>] SyS_sendmsg+0x10/0x20 [<6001ea68>] handle_syscall+0x88/0x90 [<600295fd>] userspace+0x3fd/0x500 [<6001ac55>] fork_handler+0x85/0x90 $ addr2line -e vmlinux -i 0x602b3d18 include/linux/inetdevice.h:222 net/ipv4/fib_semantics.c:1264 Problem happens when RTNH_F_LINKDOWN is provided from user space when creating routes that do not use the flag, catched with netlink fuzzer. Currently, the kernel allows user space to set both flags to nh_flags and fib_flags but this is not intentional, the assumption was that they are not set. Fix this by rejecting both flags with EINVAL. Reported-by: Vegard Nossum <vegard.nossum@oracle.com> Fixes: 0eeb075fad73 ("net: ipv4 sysctl option to ignore routes when nexthop link is down") Signed-off-by: Julian Anastasov <ja@ssi.bg> Cc: Andy Gospodarek <gospo@cumulusnetworks.com> Cc: Dinesh Dutt <ddutt@cumulusnetworks.com> Cc: Scott Feldman <sfeldma@gmail.com> Reviewed-by: Andy Gospodarek <gospo@cumulusnetworks.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-07-10 18:11:55 +00:00
nexthop_nh->nh_flags =
(cfg->fc_flags & ~0xFF) | rtnh->rtnh_flags;
nexthop_nh->nh_oif = rtnh->rtnh_ifindex;
nexthop_nh->nh_weight = rtnh->rtnh_hops + 1;
attrlen = rtnh_attrlen(rtnh);
if (attrlen > 0) {
struct nlattr *nla, *attrs = rtnh_attrs(rtnh);
nla = nla_find(attrs, attrlen, RTA_GATEWAY);
nexthop_nh->nh_gw = nla ? nla_get_in_addr(nla) : 0;
#ifdef CONFIG_IP_ROUTE_CLASSID
nla = nla_find(attrs, attrlen, RTA_FLOW);
nexthop_nh->nh_tclassid = nla ? nla_get_u32(nla) : 0;
if (nexthop_nh->nh_tclassid)
fi->fib_net->ipv4.fib_num_tclassid_users++;
#endif
nla = nla_find(attrs, attrlen, RTA_ENCAP);
if (nla) {
struct lwtunnel_state *lwtstate;
struct nlattr *nla_entype;
nla_entype = nla_find(attrs, attrlen,
RTA_ENCAP_TYPE);
if (!nla_entype) {
NL_SET_BAD_ATTR(extack, nla);
NL_SET_ERR_MSG(extack,
"Encap type is missing");
goto err_inval;
}
ret = lwtunnel_build_state(nla_get_u16(
nla_entype),
nla, AF_INET, cfg,
&lwtstate, extack);
if (ret)
goto errout;
nexthop_nh->nh_lwtstate =
lwtstate_get(lwtstate);
}
}
rtnh = rtnh_next(rtnh, &remaining);
} endfor_nexthops(fi);
return 0;
err_inval:
ret = -EINVAL;
errout:
return ret;
}
static void fib_rebalance(struct fib_info *fi)
{
int total;
int w;
struct in_device *in_dev;
if (fi->fib_nhs < 2)
return;
total = 0;
for_nexthops(fi) {
if (nh->nh_flags & RTNH_F_DEAD)
continue;
net: Fix suspicious RCU usage in fib_rebalance This command: ip route add 192.168.1.0/24 nexthop via 10.2.1.5 dev eth1 nexthop via 10.2.2.5 dev eth2 generated this suspicious RCU usage message: [ 63.249262] [ 63.249939] =============================== [ 63.251571] [ INFO: suspicious RCU usage. ] [ 63.253250] 4.3.0-rc3+ #298 Not tainted [ 63.254724] ------------------------------- [ 63.256401] ../include/linux/inetdevice.h:205 suspicious rcu_dereference_check() usage! [ 63.259450] [ 63.259450] other info that might help us debug this: [ 63.259450] [ 63.262297] [ 63.262297] rcu_scheduler_active = 1, debug_locks = 1 [ 63.264647] 1 lock held by ip/2870: [ 63.265896] #0: (rtnl_mutex){+.+.+.}, at: [<ffffffff813ebfb7>] rtnl_lock+0x12/0x14 [ 63.268858] [ 63.268858] stack backtrace: [ 63.270409] CPU: 4 PID: 2870 Comm: ip Not tainted 4.3.0-rc3+ #298 [ 63.272478] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.7.5-20140531_083030-gandalf 04/01/2014 [ 63.275745] 0000000000000001 ffff8800b8c9f8b8 ffffffff8125f73c ffff88013afcf301 [ 63.278185] ffff8800bab7a380 ffff8800b8c9f8e8 ffffffff8107bf30 ffff8800bb728000 [ 63.280634] ffff880139fe9a60 0000000000000000 ffff880139fe9a00 ffff8800b8c9f908 [ 63.283177] Call Trace: [ 63.283959] [<ffffffff8125f73c>] dump_stack+0x4c/0x68 [ 63.285593] [<ffffffff8107bf30>] lockdep_rcu_suspicious+0xfa/0x103 [ 63.287500] [<ffffffff8144d752>] __in_dev_get_rcu+0x48/0x4f [ 63.289169] [<ffffffff8144d797>] fib_rebalance+0x3e/0x127 [ 63.290753] [<ffffffff8144d986>] ? rcu_read_unlock+0x3e/0x5f [ 63.292442] [<ffffffff8144ea45>] fib_create_info+0xaf9/0xdcc [ 63.294093] [<ffffffff8106c12f>] ? sched_clock_local+0x12/0x75 [ 63.295791] [<ffffffff8145236a>] fib_table_insert+0x8c/0x451 [ 63.297493] [<ffffffff8144bf9c>] ? fib_get_table+0x36/0x43 [ 63.299109] [<ffffffff8144c3ca>] inet_rtm_newroute+0x43/0x51 [ 63.300709] [<ffffffff813ef684>] rtnetlink_rcv_msg+0x182/0x195 [ 63.302334] [<ffffffff8107d04c>] ? trace_hardirqs_on+0xd/0xf [ 63.303888] [<ffffffff813ebfb7>] ? rtnl_lock+0x12/0x14 [ 63.305346] [<ffffffff813ef502>] ? __rtnl_unlock+0x12/0x12 [ 63.306878] [<ffffffff81407c4c>] netlink_rcv_skb+0x3d/0x90 [ 63.308437] [<ffffffff813ec00e>] rtnetlink_rcv+0x21/0x28 [ 63.309916] [<ffffffff81407742>] netlink_unicast+0xfa/0x17f [ 63.311447] [<ffffffff81407a5e>] netlink_sendmsg+0x297/0x2dc [ 63.313029] [<ffffffff813c6cd4>] sock_sendmsg_nosec+0x12/0x1d [ 63.314597] [<ffffffff813c835b>] ___sys_sendmsg+0x196/0x21b [ 63.316125] [<ffffffff8100bf9f>] ? native_sched_clock+0x1f/0x3c [ 63.317671] [<ffffffff8106c12f>] ? sched_clock_local+0x12/0x75 [ 63.319185] [<ffffffff8106c397>] ? sched_clock_cpu+0x9d/0xb6 [ 63.320693] [<ffffffff8107e2d7>] ? __lock_is_held+0x32/0x54 [ 63.322145] [<ffffffff81159fcb>] ? __fget_light+0x4b/0x77 [ 63.323541] [<ffffffff813c8726>] __sys_sendmsg+0x3d/0x5b [ 63.324947] [<ffffffff813c8751>] SyS_sendmsg+0xd/0x19 [ 63.326274] [<ffffffff814c8f57>] entry_SYSCALL_64_fastpath+0x12/0x6f It looks like all of the code paths to fib_rebalance are under rtnl. Fixes: 0e884c78ee19 ("ipv4: L3 hash-based multipath") Cc: Peter Nørlund <pch@ordbogen.com> Signed-off-by: David Ahern <dsa@cumulusnetworks.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2015-10-14 23:44:00 +00:00
in_dev = __in_dev_get_rtnl(nh->nh_dev);
if (in_dev &&
IN_DEV_IGNORE_ROUTES_WITH_LINKDOWN(in_dev) &&
nh->nh_flags & RTNH_F_LINKDOWN)
continue;
total += nh->nh_weight;
} endfor_nexthops(fi);
w = 0;
change_nexthops(fi) {
int upper_bound;
net: Fix suspicious RCU usage in fib_rebalance This command: ip route add 192.168.1.0/24 nexthop via 10.2.1.5 dev eth1 nexthop via 10.2.2.5 dev eth2 generated this suspicious RCU usage message: [ 63.249262] [ 63.249939] =============================== [ 63.251571] [ INFO: suspicious RCU usage. ] [ 63.253250] 4.3.0-rc3+ #298 Not tainted [ 63.254724] ------------------------------- [ 63.256401] ../include/linux/inetdevice.h:205 suspicious rcu_dereference_check() usage! [ 63.259450] [ 63.259450] other info that might help us debug this: [ 63.259450] [ 63.262297] [ 63.262297] rcu_scheduler_active = 1, debug_locks = 1 [ 63.264647] 1 lock held by ip/2870: [ 63.265896] #0: (rtnl_mutex){+.+.+.}, at: [<ffffffff813ebfb7>] rtnl_lock+0x12/0x14 [ 63.268858] [ 63.268858] stack backtrace: [ 63.270409] CPU: 4 PID: 2870 Comm: ip Not tainted 4.3.0-rc3+ #298 [ 63.272478] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.7.5-20140531_083030-gandalf 04/01/2014 [ 63.275745] 0000000000000001 ffff8800b8c9f8b8 ffffffff8125f73c ffff88013afcf301 [ 63.278185] ffff8800bab7a380 ffff8800b8c9f8e8 ffffffff8107bf30 ffff8800bb728000 [ 63.280634] ffff880139fe9a60 0000000000000000 ffff880139fe9a00 ffff8800b8c9f908 [ 63.283177] Call Trace: [ 63.283959] [<ffffffff8125f73c>] dump_stack+0x4c/0x68 [ 63.285593] [<ffffffff8107bf30>] lockdep_rcu_suspicious+0xfa/0x103 [ 63.287500] [<ffffffff8144d752>] __in_dev_get_rcu+0x48/0x4f [ 63.289169] [<ffffffff8144d797>] fib_rebalance+0x3e/0x127 [ 63.290753] [<ffffffff8144d986>] ? rcu_read_unlock+0x3e/0x5f [ 63.292442] [<ffffffff8144ea45>] fib_create_info+0xaf9/0xdcc [ 63.294093] [<ffffffff8106c12f>] ? sched_clock_local+0x12/0x75 [ 63.295791] [<ffffffff8145236a>] fib_table_insert+0x8c/0x451 [ 63.297493] [<ffffffff8144bf9c>] ? fib_get_table+0x36/0x43 [ 63.299109] [<ffffffff8144c3ca>] inet_rtm_newroute+0x43/0x51 [ 63.300709] [<ffffffff813ef684>] rtnetlink_rcv_msg+0x182/0x195 [ 63.302334] [<ffffffff8107d04c>] ? trace_hardirqs_on+0xd/0xf [ 63.303888] [<ffffffff813ebfb7>] ? rtnl_lock+0x12/0x14 [ 63.305346] [<ffffffff813ef502>] ? __rtnl_unlock+0x12/0x12 [ 63.306878] [<ffffffff81407c4c>] netlink_rcv_skb+0x3d/0x90 [ 63.308437] [<ffffffff813ec00e>] rtnetlink_rcv+0x21/0x28 [ 63.309916] [<ffffffff81407742>] netlink_unicast+0xfa/0x17f [ 63.311447] [<ffffffff81407a5e>] netlink_sendmsg+0x297/0x2dc [ 63.313029] [<ffffffff813c6cd4>] sock_sendmsg_nosec+0x12/0x1d [ 63.314597] [<ffffffff813c835b>] ___sys_sendmsg+0x196/0x21b [ 63.316125] [<ffffffff8100bf9f>] ? native_sched_clock+0x1f/0x3c [ 63.317671] [<ffffffff8106c12f>] ? sched_clock_local+0x12/0x75 [ 63.319185] [<ffffffff8106c397>] ? sched_clock_cpu+0x9d/0xb6 [ 63.320693] [<ffffffff8107e2d7>] ? __lock_is_held+0x32/0x54 [ 63.322145] [<ffffffff81159fcb>] ? __fget_light+0x4b/0x77 [ 63.323541] [<ffffffff813c8726>] __sys_sendmsg+0x3d/0x5b [ 63.324947] [<ffffffff813c8751>] SyS_sendmsg+0xd/0x19 [ 63.326274] [<ffffffff814c8f57>] entry_SYSCALL_64_fastpath+0x12/0x6f It looks like all of the code paths to fib_rebalance are under rtnl. Fixes: 0e884c78ee19 ("ipv4: L3 hash-based multipath") Cc: Peter Nørlund <pch@ordbogen.com> Signed-off-by: David Ahern <dsa@cumulusnetworks.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2015-10-14 23:44:00 +00:00
in_dev = __in_dev_get_rtnl(nexthop_nh->nh_dev);
if (nexthop_nh->nh_flags & RTNH_F_DEAD) {
upper_bound = -1;
} else if (in_dev &&
IN_DEV_IGNORE_ROUTES_WITH_LINKDOWN(in_dev) &&
nexthop_nh->nh_flags & RTNH_F_LINKDOWN) {
upper_bound = -1;
} else {
w += nexthop_nh->nh_weight;
upper_bound = DIV_ROUND_CLOSEST_ULL((u64)w << 31,
total) - 1;
}
atomic_set(&nexthop_nh->nh_upper_bound, upper_bound);
} endfor_nexthops(fi);
}
#else /* CONFIG_IP_ROUTE_MULTIPATH */
#define fib_rebalance(fi) do { } while (0)
#endif /* CONFIG_IP_ROUTE_MULTIPATH */
static int fib_encap_match(u16 encap_type,
struct nlattr *encap,
const struct fib_nh *nh,
const struct fib_config *cfg,
struct netlink_ext_ack *extack)
{
struct lwtunnel_state *lwtstate;
int ret, result = 0;
if (encap_type == LWTUNNEL_ENCAP_NONE)
return 0;
ret = lwtunnel_build_state(encap_type, encap, AF_INET,
cfg, &lwtstate, extack);
if (!ret) {
result = lwtunnel_cmp_encap(lwtstate, nh->nh_lwtstate);
lwtstate_free(lwtstate);
}
return result;
}
int fib_nh_match(struct fib_config *cfg, struct fib_info *fi,
struct netlink_ext_ack *extack)
{
#ifdef CONFIG_IP_ROUTE_MULTIPATH
struct rtnexthop *rtnh;
int remaining;
#endif
if (cfg->fc_priority && cfg->fc_priority != fi->fib_priority)
return 1;
if (cfg->fc_oif || cfg->fc_gw) {
if (cfg->fc_encap) {
if (fib_encap_match(cfg->fc_encap_type, cfg->fc_encap,
fi->fib_nh, cfg, extack))
return 1;
}
fib_semantics: Don't match route with mismatching tclassid In fib_nh_match(), if output interface or gateway are passed in the FIB configuration, we don't have to check next hops of multipath routes to conclude whether we have a match or not. However, we might still have routes with different realms matching the same output interface and gateway configuration, and this needs to cause the match to fail. Otherwise the first route inserted in the FIB will match, regardless of the realms: # ip route add 1.1.1.1 dev eth0 table 1234 realms 1/2 # ip route append 1.1.1.1 dev eth0 table 1234 realms 3/4 # ip route list table 1234 1.1.1.1 dev eth0 scope link realms 1/2 1.1.1.1 dev eth0 scope link realms 3/4 # ip route del 1.1.1.1 dev ens3 table 1234 realms 3/4 # ip route list table 1234 1.1.1.1 dev ens3 scope link realms 3/4 whereas route with realms 3/4 should have been deleted instead. Explicitly check for fc_flow passed in the FIB configuration (this comes from RTA_FLOW extracted by rtm_to_fib_config()) and fail matching if it differs from nh_tclassid. The handling of RTA_FLOW for multipath routes later in fib_nh_match() is still needed, as we can have multiple RTA_FLOW attributes that need to be matched against the tclassid of each next hop. v2: Check that fc_flow is set before discarding the match, so that the user can still select the first matching rule by not specifying any realm, as suggested by David Ahern. Reported-by: Jianlin Shi <jishi@redhat.com> Signed-off-by: Stefano Brivio <sbrivio@redhat.com> Acked-by: David Ahern <dsahern@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-02-15 08:46:03 +00:00
#ifdef CONFIG_IP_ROUTE_CLASSID
if (cfg->fc_flow &&
cfg->fc_flow != fi->fib_nh->nh_tclassid)
return 1;
#endif
if ((!cfg->fc_oif || cfg->fc_oif == fi->fib_nh->nh_oif) &&
(!cfg->fc_gw || cfg->fc_gw == fi->fib_nh->nh_gw))
return 0;
return 1;
}
#ifdef CONFIG_IP_ROUTE_MULTIPATH
if (!cfg->fc_mp)
return 0;
rtnh = cfg->fc_mp;
remaining = cfg->fc_mp_len;
for_nexthops(fi) {
int attrlen;
if (!rtnh_ok(rtnh, remaining))
return -EINVAL;
if (rtnh->rtnh_ifindex && rtnh->rtnh_ifindex != nh->nh_oif)
return 1;
attrlen = rtnh_attrlen(rtnh);
if (attrlen > 0) {
struct nlattr *nla, *attrs = rtnh_attrs(rtnh);
nla = nla_find(attrs, attrlen, RTA_GATEWAY);
if (nla && nla_get_in_addr(nla) != nh->nh_gw)
return 1;
#ifdef CONFIG_IP_ROUTE_CLASSID
nla = nla_find(attrs, attrlen, RTA_FLOW);
if (nla && nla_get_u32(nla) != nh->nh_tclassid)
return 1;
#endif
}
rtnh = rtnh_next(rtnh, &remaining);
} endfor_nexthops(fi);
#endif
return 0;
}
bool fib_metrics_match(struct fib_config *cfg, struct fib_info *fi)
{
struct nlattr *nla;
int remaining;
if (!cfg->fc_mx)
return true;
nla_for_each_attr(nla, cfg->fc_mx, cfg->fc_mx_len, remaining) {
int type = nla_type(nla);
u32 fi_val, val;
if (!type)
continue;
if (type > RTAX_MAX)
return false;
if (type == RTAX_CC_ALGO) {
char tmp[TCP_CA_NAME_MAX];
bool ecn_ca = false;
nla_strlcpy(tmp, nla, sizeof(tmp));
val = tcp_ca_get_key_by_name(fi->fib_net, tmp, &ecn_ca);
} else {
net: metrics: add proper netlink validation Before using nla_get_u32(), better make sure the attribute is of the proper size. Code recently was changed, but bug has been there from beginning of git. BUG: KMSAN: uninit-value in rtnetlink_put_metrics+0x553/0x960 net/core/rtnetlink.c:746 CPU: 1 PID: 14139 Comm: syz-executor6 Not tainted 4.17.0-rc5+ #103 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 Call Trace: __dump_stack lib/dump_stack.c:77 [inline] dump_stack+0x185/0x1d0 lib/dump_stack.c:113 kmsan_report+0x149/0x260 mm/kmsan/kmsan.c:1084 __msan_warning_32+0x6e/0xc0 mm/kmsan/kmsan_instr.c:686 rtnetlink_put_metrics+0x553/0x960 net/core/rtnetlink.c:746 fib_dump_info+0xc42/0x2190 net/ipv4/fib_semantics.c:1361 rtmsg_fib+0x65f/0x8c0 net/ipv4/fib_semantics.c:419 fib_table_insert+0x2314/0x2b50 net/ipv4/fib_trie.c:1287 inet_rtm_newroute+0x210/0x340 net/ipv4/fib_frontend.c:779 rtnetlink_rcv_msg+0xa32/0x1560 net/core/rtnetlink.c:4646 netlink_rcv_skb+0x378/0x600 net/netlink/af_netlink.c:2448 rtnetlink_rcv+0x50/0x60 net/core/rtnetlink.c:4664 netlink_unicast_kernel net/netlink/af_netlink.c:1310 [inline] netlink_unicast+0x1678/0x1750 net/netlink/af_netlink.c:1336 netlink_sendmsg+0x104f/0x1350 net/netlink/af_netlink.c:1901 sock_sendmsg_nosec net/socket.c:629 [inline] sock_sendmsg net/socket.c:639 [inline] ___sys_sendmsg+0xec0/0x1310 net/socket.c:2117 __sys_sendmsg net/socket.c:2155 [inline] __do_sys_sendmsg net/socket.c:2164 [inline] __se_sys_sendmsg net/socket.c:2162 [inline] __x64_sys_sendmsg+0x331/0x460 net/socket.c:2162 do_syscall_64+0x152/0x230 arch/x86/entry/common.c:287 entry_SYSCALL_64_after_hwframe+0x44/0xa9 RIP: 0033:0x455a09 RSP: 002b:00007faae5fd8c68 EFLAGS: 00000246 ORIG_RAX: 000000000000002e RAX: ffffffffffffffda RBX: 00007faae5fd96d4 RCX: 0000000000455a09 RDX: 0000000000000000 RSI: 0000000020000000 RDI: 0000000000000013 RBP: 000000000072bea0 R08: 0000000000000000 R09: 0000000000000000 R10: 0000000000000000 R11: 0000000000000246 R12: 00000000ffffffff R13: 00000000000005d0 R14: 00000000006fdc20 R15: 0000000000000000 Uninit was stored to memory at: kmsan_save_stack_with_flags mm/kmsan/kmsan.c:279 [inline] kmsan_save_stack mm/kmsan/kmsan.c:294 [inline] kmsan_internal_chain_origin+0x12b/0x210 mm/kmsan/kmsan.c:685 __msan_chain_origin+0x69/0xc0 mm/kmsan/kmsan_instr.c:529 fib_convert_metrics net/ipv4/fib_semantics.c:1056 [inline] fib_create_info+0x2d46/0x9dc0 net/ipv4/fib_semantics.c:1150 fib_table_insert+0x3e4/0x2b50 net/ipv4/fib_trie.c:1146 inet_rtm_newroute+0x210/0x340 net/ipv4/fib_frontend.c:779 rtnetlink_rcv_msg+0xa32/0x1560 net/core/rtnetlink.c:4646 netlink_rcv_skb+0x378/0x600 net/netlink/af_netlink.c:2448 rtnetlink_rcv+0x50/0x60 net/core/rtnetlink.c:4664 netlink_unicast_kernel net/netlink/af_netlink.c:1310 [inline] netlink_unicast+0x1678/0x1750 net/netlink/af_netlink.c:1336 netlink_sendmsg+0x104f/0x1350 net/netlink/af_netlink.c:1901 sock_sendmsg_nosec net/socket.c:629 [inline] sock_sendmsg net/socket.c:639 [inline] ___sys_sendmsg+0xec0/0x1310 net/socket.c:2117 __sys_sendmsg net/socket.c:2155 [inline] __do_sys_sendmsg net/socket.c:2164 [inline] __se_sys_sendmsg net/socket.c:2162 [inline] __x64_sys_sendmsg+0x331/0x460 net/socket.c:2162 do_syscall_64+0x152/0x230 arch/x86/entry/common.c:287 entry_SYSCALL_64_after_hwframe+0x44/0xa9 Uninit was created at: kmsan_save_stack_with_flags mm/kmsan/kmsan.c:279 [inline] kmsan_internal_poison_shadow+0xb8/0x1b0 mm/kmsan/kmsan.c:189 kmsan_kmalloc+0x94/0x100 mm/kmsan/kmsan.c:315 kmsan_slab_alloc+0x10/0x20 mm/kmsan/kmsan.c:322 slab_post_alloc_hook mm/slab.h:446 [inline] slab_alloc_node mm/slub.c:2753 [inline] __kmalloc_node_track_caller+0xb32/0x11b0 mm/slub.c:4395 __kmalloc_reserve net/core/skbuff.c:138 [inline] __alloc_skb+0x2cb/0x9e0 net/core/skbuff.c:206 alloc_skb include/linux/skbuff.h:988 [inline] netlink_alloc_large_skb net/netlink/af_netlink.c:1182 [inline] netlink_sendmsg+0x76e/0x1350 net/netlink/af_netlink.c:1876 sock_sendmsg_nosec net/socket.c:629 [inline] sock_sendmsg net/socket.c:639 [inline] ___sys_sendmsg+0xec0/0x1310 net/socket.c:2117 __sys_sendmsg net/socket.c:2155 [inline] __do_sys_sendmsg net/socket.c:2164 [inline] __se_sys_sendmsg net/socket.c:2162 [inline] __x64_sys_sendmsg+0x331/0x460 net/socket.c:2162 do_syscall_64+0x152/0x230 arch/x86/entry/common.c:287 entry_SYSCALL_64_after_hwframe+0x44/0xa9 Fixes: a919525ad832 ("net: Move fib_convert_metrics to metrics file") Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Signed-off-by: Eric Dumazet <edumazet@google.com> Reported-by: syzbot <syzkaller@googlegroups.com> Cc: David Ahern <dsahern@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-06-05 13:06:19 +00:00
if (nla_len(nla) != sizeof(u32))
return false;
val = nla_get_u32(nla);
}
fi_val = fi->fib_metrics->metrics[type - 1];
if (type == RTAX_FEATURES)
fi_val &= ~DST_FEATURE_ECN_CA;
if (fi_val != val)
return false;
}
return true;
}
/*
* Picture
* -------
*
* Semantics of nexthop is very messy by historical reasons.
* We have to take into account, that:
* a) gateway can be actually local interface address,
* so that gatewayed route is direct.
* b) gateway must be on-link address, possibly
* described not by an ifaddr, but also by a direct route.
* c) If both gateway and interface are specified, they should not
* contradict.
* d) If we use tunnel routes, gateway could be not on-link.
*
* Attempt to reconcile all of these (alas, self-contradictory) conditions
* results in pretty ugly and hairy code with obscure logic.
*
* I chose to generalized it instead, so that the size
* of code does not increase practically, but it becomes
* much more general.
* Every prefix is assigned a "scope" value: "host" is local address,
* "link" is direct route,
* [ ... "site" ... "interior" ... ]
* and "universe" is true gateway route with global meaning.
*
* Every prefix refers to a set of "nexthop"s (gw, oif),
* where gw must have narrower scope. This recursion stops
* when gw has LOCAL scope or if "nexthop" is declared ONLINK,
* which means that gw is forced to be on link.
*
* Code is still hairy, but now it is apparently logically
* consistent and very flexible. F.e. as by-product it allows
* to co-exists in peace independent exterior and interior
* routing processes.
*
* Normally it looks as following.
*
* {universe prefix} -> (gw, oif) [scope link]
* |
* |-> {link prefix} -> (gw, oif) [scope local]
* |
* |-> {local prefix} (terminal node)
*/
static int fib_check_nh(struct fib_config *cfg, struct fib_nh *nh,
struct netlink_ext_ack *extack)
{
int err = 0;
struct net *net;
struct net_device *dev;
net = cfg->fc_nlinfo.nl_net;
if (nh->nh_gw) {
struct fib_result res;
if (nh->nh_flags & RTNH_F_ONLINK) {
unsigned int addr_type;
if (cfg->fc_scope >= RT_SCOPE_LINK) {
NL_SET_ERR_MSG(extack,
"Nexthop has invalid scope");
return -EINVAL;
}
dev = __dev_get_by_index(net, nh->nh_oif);
if (!dev) {
NL_SET_ERR_MSG(extack, "Nexthop device required for onlink");
return -ENODEV;
}
if (!(dev->flags & IFF_UP)) {
NL_SET_ERR_MSG(extack,
"Nexthop device is not up");
return -ENETDOWN;
}
addr_type = inet_addr_type_dev_table(net, dev, nh->nh_gw);
if (addr_type != RTN_UNICAST) {
NL_SET_ERR_MSG(extack,
"Nexthop has invalid gateway");
return -EINVAL;
}
if (!netif_carrier_ok(dev))
nh->nh_flags |= RTNH_F_LINKDOWN;
nh->nh_dev = dev;
dev_hold(dev);
nh->nh_scope = RT_SCOPE_LINK;
return 0;
}
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 10:41:36 +00:00
rcu_read_lock();
{
struct fib_table *tbl = NULL;
struct flowi4 fl4 = {
.daddr = nh->nh_gw,
.flowi4_scope = cfg->fc_scope + 1,
.flowi4_oif = nh->nh_oif,
.flowi4_iif = LOOPBACK_IFINDEX,
};
/* It is not necessary, but requires a bit of thinking */
if (fl4.flowi4_scope < RT_SCOPE_LINK)
fl4.flowi4_scope = RT_SCOPE_LINK;
if (cfg->fc_table)
tbl = fib_get_table(net, cfg->fc_table);
if (tbl)
err = fib_table_lookup(tbl, &fl4, &res,
FIB_LOOKUP_IGNORE_LINKSTATE |
FIB_LOOKUP_NOREF);
/* on error or if no table given do full lookup. This
* is needed for example when nexthops are in the local
* table rather than the given table
*/
if (!tbl || err) {
err = fib_lookup(net, &fl4, &res,
FIB_LOOKUP_IGNORE_LINKSTATE);
}
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 10:41:36 +00:00
if (err) {
NL_SET_ERR_MSG(extack,
"Nexthop has invalid gateway");
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 10:41:36 +00:00
rcu_read_unlock();
return err;
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 10:41:36 +00:00
}
}
err = -EINVAL;
if (res.type != RTN_UNICAST && res.type != RTN_LOCAL) {
NL_SET_ERR_MSG(extack, "Nexthop has invalid gateway");
goto out;
}
nh->nh_scope = res.scope;
nh->nh_oif = FIB_RES_OIF(res);
nh->nh_dev = dev = FIB_RES_DEV(res);
if (!dev) {
NL_SET_ERR_MSG(extack,
"No egress device for nexthop gateway");
goto out;
}
dev_hold(dev);
if (!netif_carrier_ok(dev))
nh->nh_flags |= RTNH_F_LINKDOWN;
err = (dev->flags & IFF_UP) ? 0 : -ENETDOWN;
} else {
struct in_device *in_dev;
if (nh->nh_flags & (RTNH_F_PERVASIVE | RTNH_F_ONLINK)) {
NL_SET_ERR_MSG(extack,
"Invalid flags for nexthop - PERVASIVE and ONLINK can not be set");
return -EINVAL;
}
rcu_read_lock();
err = -ENODEV;
in_dev = inetdev_by_index(net, nh->nh_oif);
if (!in_dev)
goto out;
err = -ENETDOWN;
if (!(in_dev->dev->flags & IFF_UP)) {
NL_SET_ERR_MSG(extack, "Device for nexthop is not up");
goto out;
}
nh->nh_dev = in_dev->dev;
dev_hold(nh->nh_dev);
nh->nh_scope = RT_SCOPE_HOST;
if (!netif_carrier_ok(nh->nh_dev))
nh->nh_flags |= RTNH_F_LINKDOWN;
err = 0;
}
out:
rcu_read_unlock();
return err;
}
static inline unsigned int fib_laddr_hashfn(__be32 val)
{
unsigned int mask = (fib_info_hash_size - 1);
return ((__force u32)val ^
((__force u32)val >> 7) ^
((__force u32)val >> 14)) & mask;
}
static struct hlist_head *fib_info_hash_alloc(int bytes)
{
if (bytes <= PAGE_SIZE)
return kzalloc(bytes, GFP_KERNEL);
else
return (struct hlist_head *)
__get_free_pages(GFP_KERNEL | __GFP_ZERO,
get_order(bytes));
}
static void fib_info_hash_free(struct hlist_head *hash, int bytes)
{
if (!hash)
return;
if (bytes <= PAGE_SIZE)
kfree(hash);
else
free_pages((unsigned long) hash, get_order(bytes));
}
static void fib_info_hash_move(struct hlist_head *new_info_hash,
struct hlist_head *new_laddrhash,
unsigned int new_size)
{
struct hlist_head *old_info_hash, *old_laddrhash;
unsigned int old_size = fib_info_hash_size;
unsigned int i, bytes;
spin_lock_bh(&fib_info_lock);
old_info_hash = fib_info_hash;
old_laddrhash = fib_info_laddrhash;
fib_info_hash_size = new_size;
for (i = 0; i < old_size; i++) {
struct hlist_head *head = &fib_info_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 01:06:00 +00:00
struct hlist_node *n;
struct fib_info *fi;
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 01:06:00 +00:00
hlist_for_each_entry_safe(fi, n, head, fib_hash) {
struct hlist_head *dest;
unsigned int new_hash;
new_hash = fib_info_hashfn(fi);
dest = &new_info_hash[new_hash];
hlist_add_head(&fi->fib_hash, dest);
}
}
fib_info_hash = new_info_hash;
for (i = 0; i < old_size; i++) {
struct hlist_head *lhead = &fib_info_laddrhash[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 01:06:00 +00:00
struct hlist_node *n;
struct fib_info *fi;
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 01:06:00 +00:00
hlist_for_each_entry_safe(fi, n, lhead, fib_lhash) {
struct hlist_head *ldest;
unsigned int new_hash;
new_hash = fib_laddr_hashfn(fi->fib_prefsrc);
ldest = &new_laddrhash[new_hash];
hlist_add_head(&fi->fib_lhash, ldest);
}
}
fib_info_laddrhash = new_laddrhash;
spin_unlock_bh(&fib_info_lock);
bytes = old_size * sizeof(struct hlist_head *);
fib_info_hash_free(old_info_hash, bytes);
fib_info_hash_free(old_laddrhash, bytes);
}
__be32 fib_info_update_nh_saddr(struct net *net, struct fib_nh *nh)
{
nh->nh_saddr = inet_select_addr(nh->nh_dev,
nh->nh_gw,
nh->nh_parent->fib_scope);
nh->nh_saddr_genid = atomic_read(&net->ipv4.dev_addr_genid);
return nh->nh_saddr;
}
static bool fib_valid_prefsrc(struct fib_config *cfg, __be32 fib_prefsrc)
{
if (cfg->fc_type != RTN_LOCAL || !cfg->fc_dst ||
fib_prefsrc != cfg->fc_dst) {
u32 tb_id = cfg->fc_table;
int rc;
if (tb_id == RT_TABLE_MAIN)
tb_id = RT_TABLE_LOCAL;
rc = inet_addr_type_table(cfg->fc_nlinfo.nl_net,
fib_prefsrc, tb_id);
if (rc != RTN_LOCAL && tb_id != RT_TABLE_LOCAL) {
rc = inet_addr_type_table(cfg->fc_nlinfo.nl_net,
fib_prefsrc, RT_TABLE_LOCAL);
}
if (rc != RTN_LOCAL)
return false;
}
return true;
}
struct fib_info *fib_create_info(struct fib_config *cfg,
struct netlink_ext_ack *extack)
{
int err;
struct fib_info *fi = NULL;
struct fib_info *ofi;
int nhs = 1;
struct net *net = cfg->fc_nlinfo.nl_net;
if (cfg->fc_type > RTN_MAX)
goto err_inval;
/* Fast check to catch the most weird cases */
if (fib_props[cfg->fc_type].scope > cfg->fc_scope) {
NL_SET_ERR_MSG(extack, "Invalid scope");
goto err_inval;
}
if (cfg->fc_flags & (RTNH_F_DEAD | RTNH_F_LINKDOWN)) {
NL_SET_ERR_MSG(extack,
"Invalid rtm_flags - can not contain DEAD or LINKDOWN");
ipv4: reject RTNH_F_DEAD and RTNH_F_LINKDOWN from user space Vegard Nossum is reporting for a crash in fib_dump_info when nh_dev = NULL and fib_nhs == 1: Pid: 50, comm: netlink.exe Not tainted 4.7.0-rc5+ RIP: 0033:[<00000000602b3d18>] RSP: 0000000062623890 EFLAGS: 00010202 RAX: 0000000000000000 RBX: 000000006261b800 RCX: 0000000000000000 RDX: 0000000000000000 RSI: 0000000000000024 RDI: 000000006245ba00 RBP: 00000000626238f0 R08: 000000000000029c R09: 0000000000000000 R10: 0000000062468038 R11: 000000006245ba00 R12: 000000006245ba00 R13: 00000000625f96c0 R14: 00000000601e16f0 R15: 0000000000000000 Kernel panic - not syncing: Kernel mode fault at addr 0x2e0, ip 0x602b3d18 CPU: 0 PID: 50 Comm: netlink.exe Not tainted 4.7.0-rc5+ #581 Stack: 626238f0 960226a02 00000400 000000fe 62623910 600afca7 62623970 62623a48 62468038 00000018 00000000 00000000 Call Trace: [<602b3e93>] rtmsg_fib+0xd3/0x190 [<602b6680>] fib_table_insert+0x260/0x500 [<602b0e5d>] inet_rtm_newroute+0x4d/0x60 [<60250def>] rtnetlink_rcv_msg+0x8f/0x270 [<60267079>] netlink_rcv_skb+0xc9/0xe0 [<60250d4b>] rtnetlink_rcv+0x3b/0x50 [<60265400>] netlink_unicast+0x1a0/0x2c0 [<60265e47>] netlink_sendmsg+0x3f7/0x470 [<6021dc9a>] sock_sendmsg+0x3a/0x90 [<6021e0d0>] ___sys_sendmsg+0x300/0x360 [<6021fa64>] __sys_sendmsg+0x54/0xa0 [<6021fac0>] SyS_sendmsg+0x10/0x20 [<6001ea68>] handle_syscall+0x88/0x90 [<600295fd>] userspace+0x3fd/0x500 [<6001ac55>] fork_handler+0x85/0x90 $ addr2line -e vmlinux -i 0x602b3d18 include/linux/inetdevice.h:222 net/ipv4/fib_semantics.c:1264 Problem happens when RTNH_F_LINKDOWN is provided from user space when creating routes that do not use the flag, catched with netlink fuzzer. Currently, the kernel allows user space to set both flags to nh_flags and fib_flags but this is not intentional, the assumption was that they are not set. Fix this by rejecting both flags with EINVAL. Reported-by: Vegard Nossum <vegard.nossum@oracle.com> Fixes: 0eeb075fad73 ("net: ipv4 sysctl option to ignore routes when nexthop link is down") Signed-off-by: Julian Anastasov <ja@ssi.bg> Cc: Andy Gospodarek <gospo@cumulusnetworks.com> Cc: Dinesh Dutt <ddutt@cumulusnetworks.com> Cc: Scott Feldman <sfeldma@gmail.com> Reviewed-by: Andy Gospodarek <gospo@cumulusnetworks.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-07-10 18:11:55 +00:00
goto err_inval;
}
ipv4: reject RTNH_F_DEAD and RTNH_F_LINKDOWN from user space Vegard Nossum is reporting for a crash in fib_dump_info when nh_dev = NULL and fib_nhs == 1: Pid: 50, comm: netlink.exe Not tainted 4.7.0-rc5+ RIP: 0033:[<00000000602b3d18>] RSP: 0000000062623890 EFLAGS: 00010202 RAX: 0000000000000000 RBX: 000000006261b800 RCX: 0000000000000000 RDX: 0000000000000000 RSI: 0000000000000024 RDI: 000000006245ba00 RBP: 00000000626238f0 R08: 000000000000029c R09: 0000000000000000 R10: 0000000062468038 R11: 000000006245ba00 R12: 000000006245ba00 R13: 00000000625f96c0 R14: 00000000601e16f0 R15: 0000000000000000 Kernel panic - not syncing: Kernel mode fault at addr 0x2e0, ip 0x602b3d18 CPU: 0 PID: 50 Comm: netlink.exe Not tainted 4.7.0-rc5+ #581 Stack: 626238f0 960226a02 00000400 000000fe 62623910 600afca7 62623970 62623a48 62468038 00000018 00000000 00000000 Call Trace: [<602b3e93>] rtmsg_fib+0xd3/0x190 [<602b6680>] fib_table_insert+0x260/0x500 [<602b0e5d>] inet_rtm_newroute+0x4d/0x60 [<60250def>] rtnetlink_rcv_msg+0x8f/0x270 [<60267079>] netlink_rcv_skb+0xc9/0xe0 [<60250d4b>] rtnetlink_rcv+0x3b/0x50 [<60265400>] netlink_unicast+0x1a0/0x2c0 [<60265e47>] netlink_sendmsg+0x3f7/0x470 [<6021dc9a>] sock_sendmsg+0x3a/0x90 [<6021e0d0>] ___sys_sendmsg+0x300/0x360 [<6021fa64>] __sys_sendmsg+0x54/0xa0 [<6021fac0>] SyS_sendmsg+0x10/0x20 [<6001ea68>] handle_syscall+0x88/0x90 [<600295fd>] userspace+0x3fd/0x500 [<6001ac55>] fork_handler+0x85/0x90 $ addr2line -e vmlinux -i 0x602b3d18 include/linux/inetdevice.h:222 net/ipv4/fib_semantics.c:1264 Problem happens when RTNH_F_LINKDOWN is provided from user space when creating routes that do not use the flag, catched with netlink fuzzer. Currently, the kernel allows user space to set both flags to nh_flags and fib_flags but this is not intentional, the assumption was that they are not set. Fix this by rejecting both flags with EINVAL. Reported-by: Vegard Nossum <vegard.nossum@oracle.com> Fixes: 0eeb075fad73 ("net: ipv4 sysctl option to ignore routes when nexthop link is down") Signed-off-by: Julian Anastasov <ja@ssi.bg> Cc: Andy Gospodarek <gospo@cumulusnetworks.com> Cc: Dinesh Dutt <ddutt@cumulusnetworks.com> Cc: Scott Feldman <sfeldma@gmail.com> Reviewed-by: Andy Gospodarek <gospo@cumulusnetworks.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-07-10 18:11:55 +00:00
#ifdef CONFIG_IP_ROUTE_MULTIPATH
if (cfg->fc_mp) {
nhs = fib_count_nexthops(cfg->fc_mp, cfg->fc_mp_len, extack);
if (nhs == 0)
goto err_inval;
}
#endif
err = -ENOBUFS;
if (fib_info_cnt >= fib_info_hash_size) {
unsigned int new_size = fib_info_hash_size << 1;
struct hlist_head *new_info_hash;
struct hlist_head *new_laddrhash;
unsigned int bytes;
if (!new_size)
new_size = 16;
bytes = new_size * sizeof(struct hlist_head *);
new_info_hash = fib_info_hash_alloc(bytes);
new_laddrhash = fib_info_hash_alloc(bytes);
if (!new_info_hash || !new_laddrhash) {
fib_info_hash_free(new_info_hash, bytes);
fib_info_hash_free(new_laddrhash, bytes);
} else
fib_info_hash_move(new_info_hash, new_laddrhash, new_size);
if (!fib_info_hash_size)
goto failure;
}
fi = kzalloc(sizeof(*fi)+nhs*sizeof(struct fib_nh), GFP_KERNEL);
if (!fi)
goto failure;
fi->fib_metrics = ip_fib_metrics_init(fi->fib_net, cfg->fc_mx,
cfg->fc_mx_len, extack);
if (unlikely(IS_ERR(fi->fib_metrics))) {
err = PTR_ERR(fi->fib_metrics);
kfree(fi);
return ERR_PTR(err);
}
fib_info_cnt++;
fi->fib_net = net;
fi->fib_protocol = cfg->fc_protocol;
fi->fib_scope = cfg->fc_scope;
fi->fib_flags = cfg->fc_flags;
fi->fib_priority = cfg->fc_priority;
fi->fib_prefsrc = cfg->fc_prefsrc;
ipv4: add a fib_type to fib_info commit d2d68ba9fe8 (ipv4: Cache input routes in fib_info nexthops.) introduced a regression for forwarding. This was hard to reproduce but the symptom was that packets were delivered to local host instead of being forwarded. David suggested to add fib_type to fib_info so that we dont inadvertently share same fib_info for different purposes. With help from Julian Anastasov who provided very helpful hints, reproduced here : <quote> Can it be a problem related to fib_info reuse from different routes. For example, when local IP address is created for subnet we have: broadcast 192.168.0.255 dev DEV proto kernel scope link src 192.168.0.1 192.168.0.0/24 dev DEV proto kernel scope link src 192.168.0.1 local 192.168.0.1 dev DEV proto kernel scope host src 192.168.0.1 The "dev DEV proto kernel scope link src 192.168.0.1" is a reused fib_info structure where we put cached routes. The result can be same fib_info for 192.168.0.255 and 192.168.0.0/24. RTN_BROADCAST is cached only for input routes. Incoming broadcast to 192.168.0.255 can be cached and can cause problems for traffic forwarded to 192.168.0.0/24. So, this patch should solve the problem because it separates the broadcast from unicast traffic. And the ip_route_input_slow caching will work for local and broadcast input routes (above routes 1 and 3) just because they differ in scope and use different fib_info. </quote> Many thanks to Chris Clayton for his patience and help. Reported-by: Chris Clayton <chris2553@googlemail.com> Bisected-by: Chris Clayton <chris2553@googlemail.com> Reported-by: Dave Jones <davej@redhat.com> Signed-off-by: Eric Dumazet <edumazet@google.com> Cc: Julian Anastasov <ja@ssi.bg> Tested-by: Chris Clayton <chris2553@googlemail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2012-10-04 01:25:26 +00:00
fi->fib_type = cfg->fc_type;
fi->fib_tb_id = cfg->fc_table;
fi->fib_nhs = nhs;
change_nexthops(fi) {
nexthop_nh->nh_parent = fi;
nexthop_nh->nh_pcpu_rth_output = alloc_percpu(struct rtable __rcu *);
if (!nexthop_nh->nh_pcpu_rth_output)
goto failure;
} endfor_nexthops(fi)
if (cfg->fc_mp) {
#ifdef CONFIG_IP_ROUTE_MULTIPATH
err = fib_get_nhs(fi, cfg->fc_mp, cfg->fc_mp_len, cfg, extack);
if (err != 0)
goto failure;
if (cfg->fc_oif && fi->fib_nh->nh_oif != cfg->fc_oif) {
NL_SET_ERR_MSG(extack,
"Nexthop device index does not match RTA_OIF");
goto err_inval;
}
if (cfg->fc_gw && fi->fib_nh->nh_gw != cfg->fc_gw) {
NL_SET_ERR_MSG(extack,
"Nexthop gateway does not match RTA_GATEWAY");
goto err_inval;
}
#ifdef CONFIG_IP_ROUTE_CLASSID
if (cfg->fc_flow && fi->fib_nh->nh_tclassid != cfg->fc_flow) {
NL_SET_ERR_MSG(extack,
"Nexthop class id does not match RTA_FLOW");
goto err_inval;
}
#endif
#else
NL_SET_ERR_MSG(extack,
"Multipath support not enabled in kernel");
goto err_inval;
#endif
} else {
struct fib_nh *nh = fi->fib_nh;
if (cfg->fc_encap) {
struct lwtunnel_state *lwtstate;
if (cfg->fc_encap_type == LWTUNNEL_ENCAP_NONE) {
NL_SET_ERR_MSG(extack,
"LWT encap type not specified");
goto err_inval;
}
err = lwtunnel_build_state(cfg->fc_encap_type,
cfg->fc_encap, AF_INET, cfg,
&lwtstate, extack);
if (err)
goto failure;
nh->nh_lwtstate = lwtstate_get(lwtstate);
}
nh->nh_oif = cfg->fc_oif;
nh->nh_gw = cfg->fc_gw;
nh->nh_flags = cfg->fc_flags;
#ifdef CONFIG_IP_ROUTE_CLASSID
nh->nh_tclassid = cfg->fc_flow;
if (nh->nh_tclassid)
fi->fib_net->ipv4.fib_num_tclassid_users++;
#endif
#ifdef CONFIG_IP_ROUTE_MULTIPATH
nh->nh_weight = 1;
#endif
}
if (fib_props[cfg->fc_type].error) {
if (cfg->fc_gw || cfg->fc_oif || cfg->fc_mp) {
NL_SET_ERR_MSG(extack,
"Gateway, device and multipath can not be specified for this route type");
goto err_inval;
}
goto link_it;
} else {
switch (cfg->fc_type) {
case RTN_UNICAST:
case RTN_LOCAL:
case RTN_BROADCAST:
case RTN_ANYCAST:
case RTN_MULTICAST:
break;
default:
NL_SET_ERR_MSG(extack, "Invalid route type");
goto err_inval;
}
}
if (cfg->fc_scope > RT_SCOPE_HOST) {
NL_SET_ERR_MSG(extack, "Invalid scope");
goto err_inval;
}
if (cfg->fc_scope == RT_SCOPE_HOST) {
struct fib_nh *nh = fi->fib_nh;
/* Local address is added. */
if (nhs != 1) {
NL_SET_ERR_MSG(extack,
"Route with host scope can not have multiple nexthops");
goto err_inval;
}
if (nh->nh_gw) {
NL_SET_ERR_MSG(extack,
"Route with host scope can not have a gateway");
goto err_inval;
}
nh->nh_scope = RT_SCOPE_NOWHERE;
nh->nh_dev = dev_get_by_index(net, fi->fib_nh->nh_oif);
err = -ENODEV;
if (!nh->nh_dev)
goto failure;
} else {
int linkdown = 0;
change_nexthops(fi) {
err = fib_check_nh(cfg, nexthop_nh, extack);
if (err != 0)
goto failure;
if (nexthop_nh->nh_flags & RTNH_F_LINKDOWN)
linkdown++;
} endfor_nexthops(fi)
if (linkdown == fi->fib_nhs)
fi->fib_flags |= RTNH_F_LINKDOWN;
}
if (fi->fib_prefsrc && !fib_valid_prefsrc(cfg, fi->fib_prefsrc)) {
NL_SET_ERR_MSG(extack, "Invalid prefsrc address");
goto err_inval;
}
change_nexthops(fi) {
fib_info_update_nh_saddr(net, nexthop_nh);
} endfor_nexthops(fi)
fib_rebalance(fi);
link_it:
ofi = fib_find_info(fi);
if (ofi) {
fi->fib_dead = 1;
free_fib_info(fi);
ofi->fib_treeref++;
return ofi;
}
fi->fib_treeref++;
refcount_set(&fi->fib_clntref, 1);
spin_lock_bh(&fib_info_lock);
hlist_add_head(&fi->fib_hash,
&fib_info_hash[fib_info_hashfn(fi)]);
if (fi->fib_prefsrc) {
struct hlist_head *head;
head = &fib_info_laddrhash[fib_laddr_hashfn(fi->fib_prefsrc)];
hlist_add_head(&fi->fib_lhash, head);
}
change_nexthops(fi) {
struct hlist_head *head;
unsigned int hash;
if (!nexthop_nh->nh_dev)
continue;
hash = fib_devindex_hashfn(nexthop_nh->nh_dev->ifindex);
head = &fib_info_devhash[hash];
hlist_add_head(&nexthop_nh->nh_hash, head);
} endfor_nexthops(fi)
spin_unlock_bh(&fib_info_lock);
return fi;
err_inval:
err = -EINVAL;
failure:
if (fi) {
fi->fib_dead = 1;
free_fib_info(fi);
}
return ERR_PTR(err);
}
int fib_dump_info(struct sk_buff *skb, u32 portid, u32 seq, int event,
u32 tb_id, u8 type, __be32 dst, int dst_len, u8 tos,
struct fib_info *fi, unsigned int flags)
{
struct nlmsghdr *nlh;
struct rtmsg *rtm;
nlh = nlmsg_put(skb, portid, seq, event, sizeof(*rtm), flags);
if (!nlh)
return -EMSGSIZE;
rtm = nlmsg_data(nlh);
rtm->rtm_family = AF_INET;
rtm->rtm_dst_len = dst_len;
rtm->rtm_src_len = 0;
rtm->rtm_tos = tos;
if (tb_id < 256)
rtm->rtm_table = tb_id;
else
rtm->rtm_table = RT_TABLE_COMPAT;
if (nla_put_u32(skb, RTA_TABLE, tb_id))
goto nla_put_failure;
rtm->rtm_type = type;
rtm->rtm_flags = fi->fib_flags;
rtm->rtm_scope = fi->fib_scope;
rtm->rtm_protocol = fi->fib_protocol;
if (rtm->rtm_dst_len &&
nla_put_in_addr(skb, RTA_DST, dst))
goto nla_put_failure;
if (fi->fib_priority &&
nla_put_u32(skb, RTA_PRIORITY, fi->fib_priority))
goto nla_put_failure;
if (rtnetlink_put_metrics(skb, fi->fib_metrics->metrics) < 0)
goto nla_put_failure;
if (fi->fib_prefsrc &&
nla_put_in_addr(skb, RTA_PREFSRC, fi->fib_prefsrc))
goto nla_put_failure;
if (fi->fib_nhs == 1) {
if (fi->fib_nh->nh_gw &&
nla_put_in_addr(skb, RTA_GATEWAY, fi->fib_nh->nh_gw))
goto nla_put_failure;
if (fi->fib_nh->nh_oif &&
nla_put_u32(skb, RTA_OIF, fi->fib_nh->nh_oif))
goto nla_put_failure;
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>
2015-06-23 17:45:37 +00:00
if (fi->fib_nh->nh_flags & RTNH_F_LINKDOWN) {
struct in_device *in_dev;
rcu_read_lock();
in_dev = __in_dev_get_rcu(fi->fib_nh->nh_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>
2015-06-23 17:45:37 +00:00
if (in_dev &&
IN_DEV_IGNORE_ROUTES_WITH_LINKDOWN(in_dev))
rtm->rtm_flags |= RTNH_F_DEAD;
rcu_read_unlock();
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>
2015-06-23 17:45:37 +00:00
}
if (fi->fib_nh->nh_flags & RTNH_F_OFFLOAD)
rtm->rtm_flags |= RTNH_F_OFFLOAD;
#ifdef CONFIG_IP_ROUTE_CLASSID
if (fi->fib_nh[0].nh_tclassid &&
nla_put_u32(skb, RTA_FLOW, fi->fib_nh[0].nh_tclassid))
goto nla_put_failure;
#endif
if (fi->fib_nh->nh_lwtstate &&
lwtunnel_fill_encap(skb, fi->fib_nh->nh_lwtstate) < 0)
goto nla_put_failure;
}
#ifdef CONFIG_IP_ROUTE_MULTIPATH
if (fi->fib_nhs > 1) {
struct rtnexthop *rtnh;
struct nlattr *mp;
mp = nla_nest_start(skb, RTA_MULTIPATH);
if (!mp)
goto nla_put_failure;
for_nexthops(fi) {
rtnh = nla_reserve_nohdr(skb, sizeof(*rtnh));
if (!rtnh)
goto nla_put_failure;
rtnh->rtnh_flags = nh->nh_flags & 0xFF;
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>
2015-06-23 17:45:37 +00:00
if (nh->nh_flags & RTNH_F_LINKDOWN) {
struct in_device *in_dev;
rcu_read_lock();
in_dev = __in_dev_get_rcu(nh->nh_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>
2015-06-23 17:45:37 +00:00
if (in_dev &&
IN_DEV_IGNORE_ROUTES_WITH_LINKDOWN(in_dev))
rtnh->rtnh_flags |= RTNH_F_DEAD;
rcu_read_unlock();
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>
2015-06-23 17:45:37 +00:00
}
rtnh->rtnh_hops = nh->nh_weight - 1;
rtnh->rtnh_ifindex = nh->nh_oif;
if (nh->nh_gw &&
nla_put_in_addr(skb, RTA_GATEWAY, nh->nh_gw))
goto nla_put_failure;
#ifdef CONFIG_IP_ROUTE_CLASSID
if (nh->nh_tclassid &&
nla_put_u32(skb, RTA_FLOW, nh->nh_tclassid))
goto nla_put_failure;
#endif
if (nh->nh_lwtstate &&
lwtunnel_fill_encap(skb, nh->nh_lwtstate) < 0)
goto nla_put_failure;
/* length of rtnetlink header + attributes */
rtnh->rtnh_len = nlmsg_get_pos(skb) - (void *) rtnh;
} endfor_nexthops(fi);
nla_nest_end(skb, mp);
}
#endif
netlink: make nlmsg_end() and genlmsg_end() void Contrary to common expectations for an "int" return, these functions return only a positive value -- if used correctly they cannot even return 0 because the message header will necessarily be in the skb. This makes the very common pattern of if (genlmsg_end(...) < 0) { ... } be a whole bunch of dead code. Many places also simply do return nlmsg_end(...); and the caller is expected to deal with it. This also commonly (at least for me) causes errors, because it is very common to write if (my_function(...)) /* error condition */ and if my_function() does "return nlmsg_end()" this is of course wrong. Additionally, there's not a single place in the kernel that actually needs the message length returned, and if anyone needs it later then it'll be very easy to just use skb->len there. Remove this, and make the functions void. This removes a bunch of dead code as described above. The patch adds lines because I did - return nlmsg_end(...); + nlmsg_end(...); + return 0; I could have preserved all the function's return values by returning skb->len, but instead I've audited all the places calling the affected functions and found that none cared. A few places actually compared the return value with <= 0 in dump functionality, but that could just be changed to < 0 with no change in behaviour, so I opted for the more efficient version. One instance of the error I've made numerous times now is also present in net/phonet/pn_netlink.c in the route_dumpit() function - it didn't check for <0 or <=0 and thus broke out of the loop every single time. I've preserved this since it will (I think) have caused the messages to userspace to be formatted differently with just a single message for every SKB returned to userspace. It's possible that this isn't needed for the tools that actually use this, but I don't even know what they are so couldn't test that changing this behaviour would be acceptable. Signed-off-by: Johannes Berg <johannes.berg@intel.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2015-01-16 21:09:00 +00:00
nlmsg_end(skb, nlh);
return 0;
nla_put_failure:
nlmsg_cancel(skb, nlh);
return -EMSGSIZE;
}
/*
* Update FIB if:
* - local address disappeared -> we must delete all the entries
* referring to it.
* - device went down -> we must shutdown all nexthops going via it.
*/
int fib_sync_down_addr(struct net_device *dev, __be32 local)
{
int ret = 0;
unsigned int hash = fib_laddr_hashfn(local);
struct hlist_head *head = &fib_info_laddrhash[hash];
struct net *net = dev_net(dev);
int tb_id = l3mdev_fib_table(dev);
struct fib_info *fi;
if (!fib_info_laddrhash || local == 0)
return 0;
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 01:06:00 +00:00
hlist_for_each_entry(fi, head, fib_lhash) {
if (!net_eq(fi->fib_net, net) ||
fi->fib_tb_id != tb_id)
continue;
if (fi->fib_prefsrc == local) {
fi->fib_flags |= RTNH_F_DEAD;
ret++;
}
}
return ret;
}
static int call_fib_nh_notifiers(struct fib_nh *fib_nh,
enum fib_event_type event_type)
{
struct in_device *in_dev = __in_dev_get_rtnl(fib_nh->nh_dev);
struct fib_nh_notifier_info info = {
.fib_nh = fib_nh,
};
switch (event_type) {
case FIB_EVENT_NH_ADD:
if (fib_nh->nh_flags & RTNH_F_DEAD)
break;
if (IN_DEV_IGNORE_ROUTES_WITH_LINKDOWN(in_dev) &&
fib_nh->nh_flags & RTNH_F_LINKDOWN)
break;
return call_fib4_notifiers(dev_net(fib_nh->nh_dev), event_type,
&info.info);
case FIB_EVENT_NH_DEL:
if ((in_dev && IN_DEV_IGNORE_ROUTES_WITH_LINKDOWN(in_dev) &&
fib_nh->nh_flags & RTNH_F_LINKDOWN) ||
(fib_nh->nh_flags & RTNH_F_DEAD))
return call_fib4_notifiers(dev_net(fib_nh->nh_dev),
event_type, &info.info);
default:
break;
}
return NOTIFY_DONE;
}
2018-10-09 15:48:14 +00:00
/* Update the PMTU of exceptions when:
* - the new MTU of the first hop becomes smaller than the PMTU
* - the old MTU was the same as the PMTU, and it limited discovery of
* larger MTUs on the path. With that limit raised, we can now
* discover larger MTUs
* A special case is locked exceptions, for which the PMTU is smaller
* than the minimal accepted PMTU:
* - if the new MTU is greater than the PMTU, don't make any change
* - otherwise, unlock and set PMTU
*/
static void nh_update_mtu(struct fib_nh *nh, u32 new, u32 orig)
{
struct fnhe_hash_bucket *bucket;
int i;
bucket = rcu_dereference_protected(nh->nh_exceptions, 1);
if (!bucket)
return;
for (i = 0; i < FNHE_HASH_SIZE; i++) {
struct fib_nh_exception *fnhe;
for (fnhe = rcu_dereference_protected(bucket[i].chain, 1);
fnhe;
fnhe = rcu_dereference_protected(fnhe->fnhe_next, 1)) {
if (fnhe->fnhe_mtu_locked) {
if (new <= fnhe->fnhe_pmtu) {
fnhe->fnhe_pmtu = new;
fnhe->fnhe_mtu_locked = false;
}
} else if (new < fnhe->fnhe_pmtu ||
orig == fnhe->fnhe_pmtu) {
fnhe->fnhe_pmtu = new;
}
}
}
}
void fib_sync_mtu(struct net_device *dev, u32 orig_mtu)
{
unsigned int hash = fib_devindex_hashfn(dev->ifindex);
struct hlist_head *head = &fib_info_devhash[hash];
struct fib_nh *nh;
hlist_for_each_entry(nh, head, nh_hash) {
if (nh->nh_dev == dev)
nh_update_mtu(nh, dev->mtu, orig_mtu);
}
}
/* Event force Flags Description
* NETDEV_CHANGE 0 LINKDOWN Carrier OFF, not for scope host
* NETDEV_DOWN 0 LINKDOWN|DEAD Link down, not for scope host
* NETDEV_DOWN 1 LINKDOWN|DEAD Last address removed
* NETDEV_UNREGISTER 1 LINKDOWN|DEAD Device removed
*/
int fib_sync_down_dev(struct net_device *dev, unsigned long event, bool force)
{
int ret = 0;
int scope = RT_SCOPE_NOWHERE;
struct fib_info *prev_fi = NULL;
unsigned int hash = fib_devindex_hashfn(dev->ifindex);
struct hlist_head *head = &fib_info_devhash[hash];
struct fib_nh *nh;
if (force)
scope = -1;
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 01:06:00 +00:00
hlist_for_each_entry(nh, head, nh_hash) {
struct fib_info *fi = nh->nh_parent;
int dead;
BUG_ON(!fi->fib_nhs);
if (nh->nh_dev != dev || fi == prev_fi)
continue;
prev_fi = fi;
dead = 0;
change_nexthops(fi) {
if (nexthop_nh->nh_flags & RTNH_F_DEAD)
dead++;
else if (nexthop_nh->nh_dev == dev &&
nexthop_nh->nh_scope != scope) {
switch (event) {
case NETDEV_DOWN:
case NETDEV_UNREGISTER:
nexthop_nh->nh_flags |= RTNH_F_DEAD;
/* fall through */
case NETDEV_CHANGE:
nexthop_nh->nh_flags |= RTNH_F_LINKDOWN;
break;
}
call_fib_nh_notifiers(nexthop_nh,
FIB_EVENT_NH_DEL);
dead++;
}
#ifdef CONFIG_IP_ROUTE_MULTIPATH
if (event == NETDEV_UNREGISTER &&
nexthop_nh->nh_dev == dev) {
dead = fi->fib_nhs;
break;
}
#endif
} endfor_nexthops(fi)
if (dead == fi->fib_nhs) {
switch (event) {
case NETDEV_DOWN:
case NETDEV_UNREGISTER:
fi->fib_flags |= RTNH_F_DEAD;
/* fall through */
case NETDEV_CHANGE:
fi->fib_flags |= RTNH_F_LINKDOWN;
break;
}
ret++;
}
fib_rebalance(fi);
}
return ret;
}
/* Must be invoked inside of an RCU protected region. */
static void fib_select_default(const struct flowi4 *flp, struct fib_result *res)
{
struct fib_info *fi = NULL, *last_resort = NULL;
struct hlist_head *fa_head = res->fa_head;
struct fib_table *tb = res->table;
u8 slen = 32 - res->prefixlen;
int order = -1, last_idx = -1;
struct fib_alias *fa, *fa1 = NULL;
u32 last_prio = res->fi->fib_priority;
u8 last_tos = 0;
hlist_for_each_entry_rcu(fa, fa_head, fa_list) {
struct fib_info *next_fi = fa->fa_info;
if (fa->fa_slen != slen)
continue;
if (fa->fa_tos && fa->fa_tos != flp->flowi4_tos)
continue;
if (fa->tb_id != tb->tb_id)
continue;
if (next_fi->fib_priority > last_prio &&
fa->fa_tos == last_tos) {
if (last_tos)
continue;
break;
}
if (next_fi->fib_flags & RTNH_F_DEAD)
continue;
last_tos = fa->fa_tos;
last_prio = next_fi->fib_priority;
if (next_fi->fib_scope != res->scope ||
fa->fa_type != RTN_UNICAST)
continue;
if (!next_fi->fib_nh[0].nh_gw ||
next_fi->fib_nh[0].nh_scope != RT_SCOPE_LINK)
continue;
fib_alias_accessed(fa);
if (!fi) {
if (next_fi != res->fi)
break;
fa1 = fa;
} else if (!fib_detect_death(fi, order, &last_resort,
&last_idx, fa1->fa_default)) {
fib_result_assign(res, fi);
fa1->fa_default = order;
goto out;
}
fi = next_fi;
order++;
}
if (order <= 0 || !fi) {
if (fa1)
fa1->fa_default = -1;
goto out;
}
if (!fib_detect_death(fi, order, &last_resort, &last_idx,
fa1->fa_default)) {
fib_result_assign(res, fi);
fa1->fa_default = order;
goto out;
}
if (last_idx >= 0)
fib_result_assign(res, last_resort);
fa1->fa_default = last_idx;
out:
return;
}
/*
* Dead device goes up. We wake up dead nexthops.
* It takes sense only on multipath routes.
*/
int fib_sync_up(struct net_device *dev, unsigned int nh_flags)
{
struct fib_info *prev_fi;
unsigned int hash;
struct hlist_head *head;
struct fib_nh *nh;
int ret;
if (!(dev->flags & IFF_UP))
return 0;
if (nh_flags & RTNH_F_DEAD) {
unsigned int flags = dev_get_flags(dev);
if (flags & (IFF_RUNNING | IFF_LOWER_UP))
nh_flags |= RTNH_F_LINKDOWN;
}
prev_fi = NULL;
hash = fib_devindex_hashfn(dev->ifindex);
head = &fib_info_devhash[hash];
ret = 0;
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 01:06:00 +00:00
hlist_for_each_entry(nh, head, nh_hash) {
struct fib_info *fi = nh->nh_parent;
int alive;
BUG_ON(!fi->fib_nhs);
if (nh->nh_dev != dev || fi == prev_fi)
continue;
prev_fi = fi;
alive = 0;
change_nexthops(fi) {
if (!(nexthop_nh->nh_flags & nh_flags)) {
alive++;
continue;
}
if (!nexthop_nh->nh_dev ||
!(nexthop_nh->nh_dev->flags & IFF_UP))
continue;
if (nexthop_nh->nh_dev != dev ||
!__in_dev_get_rtnl(dev))
continue;
alive++;
nexthop_nh->nh_flags &= ~nh_flags;
call_fib_nh_notifiers(nexthop_nh, FIB_EVENT_NH_ADD);
} endfor_nexthops(fi)
if (alive > 0) {
fi->fib_flags &= ~nh_flags;
ret++;
}
fib_rebalance(fi);
}
return ret;
}
#ifdef CONFIG_IP_ROUTE_MULTIPATH
net: ipv4: Consider failed nexthops in multipath routes Multipath route lookups should consider knowledge about next hops and not select a hop that is known to be failed. Example: [h2] [h3] 15.0.0.5 | | 3| 3| [SP1] [SP2]--+ 1 2 1 2 | | /-------------+ | | \ / | | X | | / \ | | / \---------------\ | 1 2 1 2 12.0.0.2 [TOR1] 3-----------------3 [TOR2] 12.0.0.3 4 4 \ / \ / \ / -------| |-----/ 1 2 [TOR3] 3| | [h1] 12.0.0.1 host h1 with IP 12.0.0.1 has 2 paths to host h3 at 15.0.0.5: root@h1:~# ip ro ls ... 12.0.0.0/24 dev swp1 proto kernel scope link src 12.0.0.1 15.0.0.0/16 nexthop via 12.0.0.2 dev swp1 weight 1 nexthop via 12.0.0.3 dev swp1 weight 1 ... If the link between tor3 and tor1 is down and the link between tor1 and tor2 then tor1 is effectively cut-off from h1. Yet the route lookups in h1 are alternating between the 2 routes: ping 15.0.0.5 gets one and ssh 15.0.0.5 gets the other. Connections that attempt to use the 12.0.0.2 nexthop fail since that neighbor is not reachable: root@h1:~# ip neigh show ... 12.0.0.3 dev swp1 lladdr 00:02:00:00:00:1b REACHABLE 12.0.0.2 dev swp1 FAILED ... The failed path can be avoided by considering known neighbor information when selecting next hops. If the neighbor lookup fails we have no knowledge about the nexthop, so give it a shot. If there is an entry then only select the nexthop if the state is sane. This is similar to what fib_detect_death does. To maintain backward compatibility use of the neighbor information is based on a new sysctl, fib_multipath_use_neigh. Signed-off-by: David Ahern <dsa@cumulusnetworks.com> Reviewed-by: Julian Anastasov <ja@ssi.bg> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-04-07 14:21:00 +00:00
static bool fib_good_nh(const struct fib_nh *nh)
{
int state = NUD_REACHABLE;
if (nh->nh_scope == RT_SCOPE_LINK) {
struct neighbour *n;
rcu_read_lock_bh();
n = __ipv4_neigh_lookup_noref(nh->nh_dev,
(__force u32)nh->nh_gw);
net: ipv4: Consider failed nexthops in multipath routes Multipath route lookups should consider knowledge about next hops and not select a hop that is known to be failed. Example: [h2] [h3] 15.0.0.5 | | 3| 3| [SP1] [SP2]--+ 1 2 1 2 | | /-------------+ | | \ / | | X | | / \ | | / \---------------\ | 1 2 1 2 12.0.0.2 [TOR1] 3-----------------3 [TOR2] 12.0.0.3 4 4 \ / \ / \ / -------| |-----/ 1 2 [TOR3] 3| | [h1] 12.0.0.1 host h1 with IP 12.0.0.1 has 2 paths to host h3 at 15.0.0.5: root@h1:~# ip ro ls ... 12.0.0.0/24 dev swp1 proto kernel scope link src 12.0.0.1 15.0.0.0/16 nexthop via 12.0.0.2 dev swp1 weight 1 nexthop via 12.0.0.3 dev swp1 weight 1 ... If the link between tor3 and tor1 is down and the link between tor1 and tor2 then tor1 is effectively cut-off from h1. Yet the route lookups in h1 are alternating between the 2 routes: ping 15.0.0.5 gets one and ssh 15.0.0.5 gets the other. Connections that attempt to use the 12.0.0.2 nexthop fail since that neighbor is not reachable: root@h1:~# ip neigh show ... 12.0.0.3 dev swp1 lladdr 00:02:00:00:00:1b REACHABLE 12.0.0.2 dev swp1 FAILED ... The failed path can be avoided by considering known neighbor information when selecting next hops. If the neighbor lookup fails we have no knowledge about the nexthop, so give it a shot. If there is an entry then only select the nexthop if the state is sane. This is similar to what fib_detect_death does. To maintain backward compatibility use of the neighbor information is based on a new sysctl, fib_multipath_use_neigh. Signed-off-by: David Ahern <dsa@cumulusnetworks.com> Reviewed-by: Julian Anastasov <ja@ssi.bg> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-04-07 14:21:00 +00:00
if (n)
state = n->nud_state;
rcu_read_unlock_bh();
}
return !!(state & NUD_VALID);
}
void fib_select_multipath(struct fib_result *res, int hash)
{
struct fib_info *fi = res->fi;
net: ipv4: Consider failed nexthops in multipath routes Multipath route lookups should consider knowledge about next hops and not select a hop that is known to be failed. Example: [h2] [h3] 15.0.0.5 | | 3| 3| [SP1] [SP2]--+ 1 2 1 2 | | /-------------+ | | \ / | | X | | / \ | | / \---------------\ | 1 2 1 2 12.0.0.2 [TOR1] 3-----------------3 [TOR2] 12.0.0.3 4 4 \ / \ / \ / -------| |-----/ 1 2 [TOR3] 3| | [h1] 12.0.0.1 host h1 with IP 12.0.0.1 has 2 paths to host h3 at 15.0.0.5: root@h1:~# ip ro ls ... 12.0.0.0/24 dev swp1 proto kernel scope link src 12.0.0.1 15.0.0.0/16 nexthop via 12.0.0.2 dev swp1 weight 1 nexthop via 12.0.0.3 dev swp1 weight 1 ... If the link between tor3 and tor1 is down and the link between tor1 and tor2 then tor1 is effectively cut-off from h1. Yet the route lookups in h1 are alternating between the 2 routes: ping 15.0.0.5 gets one and ssh 15.0.0.5 gets the other. Connections that attempt to use the 12.0.0.2 nexthop fail since that neighbor is not reachable: root@h1:~# ip neigh show ... 12.0.0.3 dev swp1 lladdr 00:02:00:00:00:1b REACHABLE 12.0.0.2 dev swp1 FAILED ... The failed path can be avoided by considering known neighbor information when selecting next hops. If the neighbor lookup fails we have no knowledge about the nexthop, so give it a shot. If there is an entry then only select the nexthop if the state is sane. This is similar to what fib_detect_death does. To maintain backward compatibility use of the neighbor information is based on a new sysctl, fib_multipath_use_neigh. Signed-off-by: David Ahern <dsa@cumulusnetworks.com> Reviewed-by: Julian Anastasov <ja@ssi.bg> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-04-07 14:21:00 +00:00
struct net *net = fi->fib_net;
bool first = false;
for_nexthops(fi) {
if (net->ipv4.sysctl_fib_multipath_use_neigh) {
if (!fib_good_nh(nh))
continue;
if (!first) {
res->nh_sel = nhsel;
first = true;
}
}
if (hash > atomic_read(&nh->nh_upper_bound))
continue;
res->nh_sel = nhsel;
return;
} endfor_nexthops(fi);
}
#endif
void fib_select_path(struct net *net, struct fib_result *res,
struct flowi4 *fl4, const struct sk_buff *skb)
{
if (fl4->flowi4_oif && !(fl4->flowi4_flags & FLOWI_FLAG_SKIP_NH_OIF))
goto check_saddr;
#ifdef CONFIG_IP_ROUTE_MULTIPATH
if (res->fi->fib_nhs > 1) {
int h = fib_multipath_hash(net, fl4, skb, NULL);
fib_select_multipath(res, h);
}
else
#endif
if (!res->prefixlen &&
res->table->tb_num_default > 1 &&
res->type == RTN_UNICAST)
fib_select_default(fl4, res);
check_saddr:
if (!fl4->saddr)
fl4->saddr = FIB_RES_PREFSRC(net, *res);
}