linux/net/ipv6/ip6_fib.c

2281 lines
49 KiB
C
Raw Normal View History

/*
* Linux INET6 implementation
* Forwarding Information Database
*
* Authors:
* Pedro Roque <roque@di.fc.ul.pt>
*
* This program is free software; you can redistribute it and/or
* modify it under the terms of the GNU General Public License
* as published by the Free Software Foundation; either version
* 2 of the License, or (at your option) any later version.
*
* Changes:
* Yuji SEKIYA @USAGI: Support default route on router node;
* remove ip6_null_entry from the top of
* routing table.
* Ville Nuorvala: Fixed routing subtrees.
*/
#define pr_fmt(fmt) "IPv6: " fmt
#include <linux/errno.h>
#include <linux/types.h>
#include <linux/net.h>
#include <linux/route.h>
#include <linux/netdevice.h>
#include <linux/in6.h>
#include <linux/init.h>
#include <linux/list.h>
include cleanup: Update gfp.h and slab.h includes to prepare for breaking implicit slab.h inclusion from percpu.h percpu.h is included by sched.h and module.h and thus ends up being included when building most .c files. percpu.h includes slab.h which in turn includes gfp.h making everything defined by the two files universally available and complicating inclusion dependencies. percpu.h -> slab.h dependency is about to be removed. Prepare for this change by updating users of gfp and slab facilities include those headers directly instead of assuming availability. As this conversion needs to touch large number of source files, the following script is used as the basis of conversion. http://userweb.kernel.org/~tj/misc/slabh-sweep.py The script does the followings. * Scan files for gfp and slab usages and update includes such that only the necessary includes are there. ie. if only gfp is used, gfp.h, if slab is used, slab.h. * When the script inserts a new include, it looks at the include blocks and try to put the new include such that its order conforms to its surrounding. It's put in the include block which contains core kernel includes, in the same order that the rest are ordered - alphabetical, Christmas tree, rev-Xmas-tree or at the end if there doesn't seem to be any matching order. * If the script can't find a place to put a new include (mostly because the file doesn't have fitting include block), it prints out an error message indicating which .h file needs to be added to the file. The conversion was done in the following steps. 1. The initial automatic conversion of all .c files updated slightly over 4000 files, deleting around 700 includes and adding ~480 gfp.h and ~3000 slab.h inclusions. The script emitted errors for ~400 files. 2. Each error was manually checked. Some didn't need the inclusion, some needed manual addition while adding it to implementation .h or embedding .c file was more appropriate for others. This step added inclusions to around 150 files. 3. The script was run again and the output was compared to the edits from #2 to make sure no file was left behind. 4. Several build tests were done and a couple of problems were fixed. e.g. lib/decompress_*.c used malloc/free() wrappers around slab APIs requiring slab.h to be added manually. 5. The script was run on all .h files but without automatically editing them as sprinkling gfp.h and slab.h inclusions around .h files could easily lead to inclusion dependency hell. Most gfp.h inclusion directives were ignored as stuff from gfp.h was usually wildly available and often used in preprocessor macros. Each slab.h inclusion directive was examined and added manually as necessary. 6. percpu.h was updated not to include slab.h. 7. Build test were done on the following configurations and failures were fixed. CONFIG_GCOV_KERNEL was turned off for all tests (as my distributed build env didn't work with gcov compiles) and a few more options had to be turned off depending on archs to make things build (like ipr on powerpc/64 which failed due to missing writeq). * x86 and x86_64 UP and SMP allmodconfig and a custom test config. * powerpc and powerpc64 SMP allmodconfig * sparc and sparc64 SMP allmodconfig * ia64 SMP allmodconfig * s390 SMP allmodconfig * alpha SMP allmodconfig * um on x86_64 SMP allmodconfig 8. percpu.h modifications were reverted so that it could be applied as a separate patch and serve as bisection point. Given the fact that I had only a couple of failures from tests on step 6, I'm fairly confident about the coverage of this conversion patch. If there is a breakage, it's likely to be something in one of the arch headers which should be easily discoverable easily on most builds of the specific arch. Signed-off-by: Tejun Heo <tj@kernel.org> Guess-its-ok-by: Christoph Lameter <cl@linux-foundation.org> Cc: Ingo Molnar <mingo@redhat.com> Cc: Lee Schermerhorn <Lee.Schermerhorn@hp.com>
2010-03-24 08:04:11 +00:00
#include <linux/slab.h>
#include <net/ipv6.h>
#include <net/ndisc.h>
#include <net/addrconf.h>
#include <net/lwtunnel.h>
#include <net/fib_notifier.h>
#include <net/ip6_fib.h>
#include <net/ip6_route.h>
#define RT6_DEBUG 2
#if RT6_DEBUG >= 3
#define RT6_TRACE(x...) pr_debug(x)
#else
#define RT6_TRACE(x...) do { ; } while (0)
#endif
static struct kmem_cache *fib6_node_kmem __read_mostly;
struct fib6_cleaner {
struct fib6_walker w;
struct net *net;
int (*func)(struct rt6_info *, void *arg);
int sernum;
void *arg;
};
#ifdef CONFIG_IPV6_SUBTREES
#define FWS_INIT FWS_S
#else
#define FWS_INIT FWS_L
#endif
static void fib6_prune_clones(struct net *net, struct fib6_node *fn);
static struct rt6_info *fib6_find_prefix(struct net *net, struct fib6_node *fn);
static struct fib6_node *fib6_repair_tree(struct net *net, struct fib6_node *fn);
static int fib6_walk(struct net *net, struct fib6_walker *w);
static int fib6_walk_continue(struct fib6_walker *w);
/*
* A routing update causes an increase of the serial number on the
* affected subtree. This allows for cached routes to be asynchronously
* tested when modifications are made to the destination cache as a
* result of redirects, path MTU changes, etc.
*/
static void fib6_gc_timer_cb(unsigned long arg);
#define FOR_WALKERS(net, w) \
list_for_each_entry(w, &(net)->ipv6.fib6_walkers, lh)
static void fib6_walker_link(struct net *net, struct fib6_walker *w)
{
write_lock_bh(&net->ipv6.fib6_walker_lock);
list_add(&w->lh, &net->ipv6.fib6_walkers);
write_unlock_bh(&net->ipv6.fib6_walker_lock);
}
static void fib6_walker_unlink(struct net *net, struct fib6_walker *w)
{
write_lock_bh(&net->ipv6.fib6_walker_lock);
list_del(&w->lh);
write_unlock_bh(&net->ipv6.fib6_walker_lock);
}
static int fib6_new_sernum(struct net *net)
{
int new, old;
do {
old = atomic_read(&net->ipv6.fib6_sernum);
new = old < INT_MAX ? old + 1 : 1;
} while (atomic_cmpxchg(&net->ipv6.fib6_sernum,
old, new) != old);
return new;
}
enum {
FIB6_NO_SERNUM_CHANGE = 0,
};
/*
* Auxiliary address test functions for the radix tree.
*
* These assume a 32bit processor (although it will work on
* 64bit processors)
*/
/*
* test bit
*/
#if defined(__LITTLE_ENDIAN)
# define BITOP_BE32_SWIZZLE (0x1F & ~7)
#else
# define BITOP_BE32_SWIZZLE 0
#endif
static __be32 addr_bit_set(const void *token, int fn_bit)
{
const __be32 *addr = token;
/*
* Here,
* 1 << ((~fn_bit ^ BITOP_BE32_SWIZZLE) & 0x1f)
* is optimized version of
* htonl(1 << ((~fn_bit)&0x1F))
* See include/asm-generic/bitops/le.h.
*/
return (__force __be32)(1 << ((~fn_bit ^ BITOP_BE32_SWIZZLE) & 0x1f)) &
addr[fn_bit >> 5];
}
static struct fib6_node *node_alloc(void)
{
struct fib6_node *fn;
fn = kmem_cache_zalloc(fib6_node_kmem, GFP_ATOMIC);
return fn;
}
static void node_free_immediate(struct fib6_node *fn)
{
kmem_cache_free(fib6_node_kmem, fn);
}
static void node_free_rcu(struct rcu_head *head)
{
struct fib6_node *fn = container_of(head, struct fib6_node, rcu);
kmem_cache_free(fib6_node_kmem, fn);
}
static void node_free(struct fib6_node *fn)
{
call_rcu(&fn->rcu, node_free_rcu);
}
void rt6_free_pcpu(struct rt6_info *non_pcpu_rt)
{
int cpu;
if (!non_pcpu_rt->rt6i_pcpu)
return;
for_each_possible_cpu(cpu) {
struct rt6_info **ppcpu_rt;
struct rt6_info *pcpu_rt;
ppcpu_rt = per_cpu_ptr(non_pcpu_rt->rt6i_pcpu, cpu);
pcpu_rt = *ppcpu_rt;
if (pcpu_rt) {
dst_dev_put(&pcpu_rt->dst);
dst_release(&pcpu_rt->dst);
*ppcpu_rt = NULL;
}
}
ipv6: Fix a potential deadlock when creating pcpu rt rt6_make_pcpu_route() is called under read_lock(&table->tb6_lock). rt6_make_pcpu_route() calls ip6_rt_pcpu_alloc(rt) which then calls dst_alloc(). dst_alloc() _may_ call ip6_dst_gc() which takes the write_lock(&tabl->tb6_lock). A visualized version: read_lock(&table->tb6_lock); rt6_make_pcpu_route(); => ip6_rt_pcpu_alloc(); => dst_alloc(); => ip6_dst_gc(); => write_lock(&table->tb6_lock); /* oops */ The fix is to do a read_unlock first before calling ip6_rt_pcpu_alloc(). A reported stack: [141625.537638] INFO: rcu_sched self-detected stall on CPU { 27} (t=60000 jiffies g=4159086 c=4159085 q=2139) [141625.547469] Task dump for CPU 27: [141625.550881] mtr R running task 0 22121 22081 0x00000008 [141625.558069] 0000000000000000 ffff88103f363d98 ffffffff8106e488 000000000000001b [141625.565641] ffffffff81684900 ffff88103f363db8 ffffffff810702b0 0000000008000000 [141625.573220] ffffffff81684900 ffff88103f363de8 ffffffff8108df9f ffff88103f375a00 [141625.580803] Call Trace: [141625.583345] <IRQ> [<ffffffff8106e488>] sched_show_task+0xc1/0xc6 [141625.589650] [<ffffffff810702b0>] dump_cpu_task+0x35/0x39 [141625.595144] [<ffffffff8108df9f>] rcu_dump_cpu_stacks+0x6a/0x8c [141625.601320] [<ffffffff81090606>] rcu_check_callbacks+0x1f6/0x5d4 [141625.607669] [<ffffffff810940c8>] update_process_times+0x2a/0x4f [141625.613925] [<ffffffff8109fbee>] tick_sched_handle+0x32/0x3e [141625.619923] [<ffffffff8109fc2f>] tick_sched_timer+0x35/0x5c [141625.625830] [<ffffffff81094a1f>] __hrtimer_run_queues+0x8f/0x18d [141625.632171] [<ffffffff81094c9e>] hrtimer_interrupt+0xa0/0x166 [141625.638258] [<ffffffff8102bf2a>] local_apic_timer_interrupt+0x4e/0x52 [141625.645036] [<ffffffff8102c36f>] smp_apic_timer_interrupt+0x39/0x4a [141625.651643] [<ffffffff8140b9e8>] apic_timer_interrupt+0x68/0x70 [141625.657895] <EOI> [<ffffffff81346ee8>] ? dst_destroy+0x7c/0xb5 [141625.664188] [<ffffffff813d45b5>] ? fib6_flush_trees+0x20/0x20 [141625.670272] [<ffffffff81082b45>] ? queue_write_lock_slowpath+0x60/0x6f [141625.677140] [<ffffffff8140aa33>] _raw_write_lock_bh+0x23/0x25 [141625.683218] [<ffffffff813d4553>] __fib6_clean_all+0x40/0x82 [141625.689124] [<ffffffff813d45b5>] ? fib6_flush_trees+0x20/0x20 [141625.695207] [<ffffffff813d6058>] fib6_clean_all+0xe/0x10 [141625.700854] [<ffffffff813d60d3>] fib6_run_gc+0x79/0xc8 [141625.706329] [<ffffffff813d0510>] ip6_dst_gc+0x85/0xf9 [141625.711718] [<ffffffff81346d68>] dst_alloc+0x55/0x159 [141625.717105] [<ffffffff813d09b5>] __ip6_dst_alloc.isra.32+0x19/0x63 [141625.723620] [<ffffffff813d1830>] ip6_pol_route+0x36a/0x3e8 [141625.729441] [<ffffffff813d18d6>] ip6_pol_route_output+0x11/0x13 [141625.735700] [<ffffffff813f02c8>] fib6_rule_action+0xa7/0x1bf [141625.741698] [<ffffffff813d18c5>] ? ip6_pol_route_input+0x17/0x17 [141625.748043] [<ffffffff81357c48>] fib_rules_lookup+0xb5/0x12a [141625.754050] [<ffffffff81141628>] ? poll_select_copy_remaining+0xf9/0xf9 [141625.761002] [<ffffffff813f0535>] fib6_rule_lookup+0x37/0x5c [141625.766914] [<ffffffff813d18c5>] ? ip6_pol_route_input+0x17/0x17 [141625.773260] [<ffffffff813d008c>] ip6_route_output+0x7a/0x82 [141625.779177] [<ffffffff813c44c8>] ip6_dst_lookup_tail+0x53/0x112 [141625.785437] [<ffffffff813c45c3>] ip6_dst_lookup_flow+0x2a/0x6b [141625.791604] [<ffffffff813ddaab>] rawv6_sendmsg+0x407/0x9b6 [141625.797423] [<ffffffff813d7914>] ? do_ipv6_setsockopt.isra.8+0xd87/0xde2 [141625.804464] [<ffffffff8139d4b4>] inet_sendmsg+0x57/0x8e [141625.810028] [<ffffffff81329ba3>] sock_sendmsg+0x2e/0x3c [141625.815588] [<ffffffff8132be57>] SyS_sendto+0xfe/0x143 [141625.821063] [<ffffffff813dd551>] ? rawv6_setsockopt+0x5e/0x67 [141625.827146] [<ffffffff8132c9f8>] ? sock_common_setsockopt+0xf/0x11 [141625.833660] [<ffffffff8132c08c>] ? SyS_setsockopt+0x81/0xa2 [141625.839565] [<ffffffff8140ac17>] entry_SYSCALL_64_fastpath+0x12/0x6a Fixes: d52d3997f843 ("pv6: Create percpu rt6_info") Signed-off-by: Martin KaFai Lau <kafai@fb.com> CC: Hannes Frederic Sowa <hannes@stressinduktion.org> Reported-by: Steinar H. Gunderson <sgunderson@bigfoot.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2015-08-14 18:05:54 +00:00
free_percpu(non_pcpu_rt->rt6i_pcpu);
ipv6: Fix a potential deadlock when creating pcpu rt rt6_make_pcpu_route() is called under read_lock(&table->tb6_lock). rt6_make_pcpu_route() calls ip6_rt_pcpu_alloc(rt) which then calls dst_alloc(). dst_alloc() _may_ call ip6_dst_gc() which takes the write_lock(&tabl->tb6_lock). A visualized version: read_lock(&table->tb6_lock); rt6_make_pcpu_route(); => ip6_rt_pcpu_alloc(); => dst_alloc(); => ip6_dst_gc(); => write_lock(&table->tb6_lock); /* oops */ The fix is to do a read_unlock first before calling ip6_rt_pcpu_alloc(). A reported stack: [141625.537638] INFO: rcu_sched self-detected stall on CPU { 27} (t=60000 jiffies g=4159086 c=4159085 q=2139) [141625.547469] Task dump for CPU 27: [141625.550881] mtr R running task 0 22121 22081 0x00000008 [141625.558069] 0000000000000000 ffff88103f363d98 ffffffff8106e488 000000000000001b [141625.565641] ffffffff81684900 ffff88103f363db8 ffffffff810702b0 0000000008000000 [141625.573220] ffffffff81684900 ffff88103f363de8 ffffffff8108df9f ffff88103f375a00 [141625.580803] Call Trace: [141625.583345] <IRQ> [<ffffffff8106e488>] sched_show_task+0xc1/0xc6 [141625.589650] [<ffffffff810702b0>] dump_cpu_task+0x35/0x39 [141625.595144] [<ffffffff8108df9f>] rcu_dump_cpu_stacks+0x6a/0x8c [141625.601320] [<ffffffff81090606>] rcu_check_callbacks+0x1f6/0x5d4 [141625.607669] [<ffffffff810940c8>] update_process_times+0x2a/0x4f [141625.613925] [<ffffffff8109fbee>] tick_sched_handle+0x32/0x3e [141625.619923] [<ffffffff8109fc2f>] tick_sched_timer+0x35/0x5c [141625.625830] [<ffffffff81094a1f>] __hrtimer_run_queues+0x8f/0x18d [141625.632171] [<ffffffff81094c9e>] hrtimer_interrupt+0xa0/0x166 [141625.638258] [<ffffffff8102bf2a>] local_apic_timer_interrupt+0x4e/0x52 [141625.645036] [<ffffffff8102c36f>] smp_apic_timer_interrupt+0x39/0x4a [141625.651643] [<ffffffff8140b9e8>] apic_timer_interrupt+0x68/0x70 [141625.657895] <EOI> [<ffffffff81346ee8>] ? dst_destroy+0x7c/0xb5 [141625.664188] [<ffffffff813d45b5>] ? fib6_flush_trees+0x20/0x20 [141625.670272] [<ffffffff81082b45>] ? queue_write_lock_slowpath+0x60/0x6f [141625.677140] [<ffffffff8140aa33>] _raw_write_lock_bh+0x23/0x25 [141625.683218] [<ffffffff813d4553>] __fib6_clean_all+0x40/0x82 [141625.689124] [<ffffffff813d45b5>] ? fib6_flush_trees+0x20/0x20 [141625.695207] [<ffffffff813d6058>] fib6_clean_all+0xe/0x10 [141625.700854] [<ffffffff813d60d3>] fib6_run_gc+0x79/0xc8 [141625.706329] [<ffffffff813d0510>] ip6_dst_gc+0x85/0xf9 [141625.711718] [<ffffffff81346d68>] dst_alloc+0x55/0x159 [141625.717105] [<ffffffff813d09b5>] __ip6_dst_alloc.isra.32+0x19/0x63 [141625.723620] [<ffffffff813d1830>] ip6_pol_route+0x36a/0x3e8 [141625.729441] [<ffffffff813d18d6>] ip6_pol_route_output+0x11/0x13 [141625.735700] [<ffffffff813f02c8>] fib6_rule_action+0xa7/0x1bf [141625.741698] [<ffffffff813d18c5>] ? ip6_pol_route_input+0x17/0x17 [141625.748043] [<ffffffff81357c48>] fib_rules_lookup+0xb5/0x12a [141625.754050] [<ffffffff81141628>] ? poll_select_copy_remaining+0xf9/0xf9 [141625.761002] [<ffffffff813f0535>] fib6_rule_lookup+0x37/0x5c [141625.766914] [<ffffffff813d18c5>] ? ip6_pol_route_input+0x17/0x17 [141625.773260] [<ffffffff813d008c>] ip6_route_output+0x7a/0x82 [141625.779177] [<ffffffff813c44c8>] ip6_dst_lookup_tail+0x53/0x112 [141625.785437] [<ffffffff813c45c3>] ip6_dst_lookup_flow+0x2a/0x6b [141625.791604] [<ffffffff813ddaab>] rawv6_sendmsg+0x407/0x9b6 [141625.797423] [<ffffffff813d7914>] ? do_ipv6_setsockopt.isra.8+0xd87/0xde2 [141625.804464] [<ffffffff8139d4b4>] inet_sendmsg+0x57/0x8e [141625.810028] [<ffffffff81329ba3>] sock_sendmsg+0x2e/0x3c [141625.815588] [<ffffffff8132be57>] SyS_sendto+0xfe/0x143 [141625.821063] [<ffffffff813dd551>] ? rawv6_setsockopt+0x5e/0x67 [141625.827146] [<ffffffff8132c9f8>] ? sock_common_setsockopt+0xf/0x11 [141625.833660] [<ffffffff8132c08c>] ? SyS_setsockopt+0x81/0xa2 [141625.839565] [<ffffffff8140ac17>] entry_SYSCALL_64_fastpath+0x12/0x6a Fixes: d52d3997f843 ("pv6: Create percpu rt6_info") Signed-off-by: Martin KaFai Lau <kafai@fb.com> CC: Hannes Frederic Sowa <hannes@stressinduktion.org> Reported-by: Steinar H. Gunderson <sgunderson@bigfoot.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2015-08-14 18:05:54 +00:00
non_pcpu_rt->rt6i_pcpu = NULL;
}
EXPORT_SYMBOL_GPL(rt6_free_pcpu);
static void fib6_free_table(struct fib6_table *table)
{
inetpeer_invalidate_tree(&table->tb6_peers);
kfree(table);
}
static void fib6_link_table(struct net *net, struct fib6_table *tb)
{
unsigned int h;
/*
* Initialize table lock at a single place to give lockdep a key,
* tables aren't visible prior to being linked to the list.
*/
rwlock_init(&tb->tb6_lock);
h = tb->tb6_id & (FIB6_TABLE_HASHSZ - 1);
/*
* No protection necessary, this is the only list mutatation
* operation, tables never disappear once they exist.
*/
hlist_add_head_rcu(&tb->tb6_hlist, &net->ipv6.fib_table_hash[h]);
}
#ifdef CONFIG_IPV6_MULTIPLE_TABLES
static struct fib6_table *fib6_alloc_table(struct net *net, u32 id)
{
struct fib6_table *table;
table = kzalloc(sizeof(*table), GFP_ATOMIC);
if (table) {
table->tb6_id = id;
table->tb6_root.leaf = net->ipv6.ip6_null_entry;
table->tb6_root.fn_flags = RTN_ROOT | RTN_TL_ROOT | RTN_RTINFO;
inet_peer_base_init(&table->tb6_peers);
}
return table;
}
struct fib6_table *fib6_new_table(struct net *net, u32 id)
{
struct fib6_table *tb;
if (id == 0)
id = RT6_TABLE_MAIN;
tb = fib6_get_table(net, id);
if (tb)
return tb;
tb = fib6_alloc_table(net, id);
if (tb)
fib6_link_table(net, tb);
return tb;
}
EXPORT_SYMBOL_GPL(fib6_new_table);
struct fib6_table *fib6_get_table(struct net *net, u32 id)
{
struct fib6_table *tb;
struct hlist_head *head;
unsigned int h;
if (id == 0)
id = RT6_TABLE_MAIN;
h = id & (FIB6_TABLE_HASHSZ - 1);
rcu_read_lock();
head = &net->ipv6.fib_table_hash[h];
hlist: drop the node parameter from iterators I'm not sure why, but the hlist for each entry iterators were conceived list_for_each_entry(pos, head, member) The hlist ones were greedy and wanted an extra parameter: hlist_for_each_entry(tpos, pos, head, member) Why did they need an extra pos parameter? I'm not quite sure. Not only they don't really need it, it also prevents the iterator from looking exactly like the list iterator, which is unfortunate. Besides the semantic patch, there was some manual work required: - Fix up the actual hlist iterators in linux/list.h - Fix up the declaration of other iterators based on the hlist ones. - A very small amount of places were using the 'node' parameter, this was modified to use 'obj->member' instead. - Coccinelle didn't handle the hlist_for_each_entry_safe iterator properly, so those had to be fixed up manually. The semantic patch which is mostly the work of Peter Senna Tschudin is here: @@ iterator name hlist_for_each_entry, hlist_for_each_entry_continue, hlist_for_each_entry_from, hlist_for_each_entry_rcu, hlist_for_each_entry_rcu_bh, hlist_for_each_entry_continue_rcu_bh, for_each_busy_worker, ax25_uid_for_each, ax25_for_each, inet_bind_bucket_for_each, sctp_for_each_hentry, sk_for_each, sk_for_each_rcu, sk_for_each_from, sk_for_each_safe, sk_for_each_bound, hlist_for_each_entry_safe, hlist_for_each_entry_continue_rcu, nr_neigh_for_each, nr_neigh_for_each_safe, nr_node_for_each, nr_node_for_each_safe, for_each_gfn_indirect_valid_sp, for_each_gfn_sp, for_each_host; type T; expression a,c,d,e; identifier b; statement S; @@ -T b; <+... when != b ( hlist_for_each_entry(a, - b, c, d) S | hlist_for_each_entry_continue(a, - b, c) S | hlist_for_each_entry_from(a, - b, c) S | hlist_for_each_entry_rcu(a, - b, c, d) S | hlist_for_each_entry_rcu_bh(a, - b, c, d) S | hlist_for_each_entry_continue_rcu_bh(a, - b, c) S | for_each_busy_worker(a, c, - b, d) S | ax25_uid_for_each(a, - b, c) S | ax25_for_each(a, - b, c) S | inet_bind_bucket_for_each(a, - b, c) S | sctp_for_each_hentry(a, - b, c) S | sk_for_each(a, - b, c) S | sk_for_each_rcu(a, - b, c) S | sk_for_each_from -(a, b) +(a) S + sk_for_each_from(a) S | sk_for_each_safe(a, - b, c, d) S | sk_for_each_bound(a, - b, c) S | hlist_for_each_entry_safe(a, - b, c, d, e) S | hlist_for_each_entry_continue_rcu(a, - b, c) S | nr_neigh_for_each(a, - b, c) S | nr_neigh_for_each_safe(a, - b, c, d) S | nr_node_for_each(a, - b, c) S | nr_node_for_each_safe(a, - b, c, d) S | - for_each_gfn_sp(a, c, d, b) S + for_each_gfn_sp(a, c, d) S | - for_each_gfn_indirect_valid_sp(a, c, d, b) S + for_each_gfn_indirect_valid_sp(a, c, d) S | for_each_host(a, - b, c) S | for_each_host_safe(a, - b, c, d) S | for_each_mesh_entry(a, - b, c, d) S ) ...+> [akpm@linux-foundation.org: drop bogus change from net/ipv4/raw.c] [akpm@linux-foundation.org: drop bogus hunk from net/ipv6/raw.c] [akpm@linux-foundation.org: checkpatch fixes] [akpm@linux-foundation.org: fix warnings] [akpm@linux-foudnation.org: redo intrusive kvm changes] Tested-by: Peter Senna Tschudin <peter.senna@gmail.com> Acked-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Signed-off-by: Sasha Levin <sasha.levin@oracle.com> Cc: Wu Fengguang <fengguang.wu@intel.com> Cc: Marcelo Tosatti <mtosatti@redhat.com> Cc: Gleb Natapov <gleb@redhat.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2013-02-28 01:06:00 +00:00
hlist_for_each_entry_rcu(tb, head, tb6_hlist) {
if (tb->tb6_id == id) {
rcu_read_unlock();
return tb;
}
}
rcu_read_unlock();
return NULL;
}
EXPORT_SYMBOL_GPL(fib6_get_table);
static void __net_init fib6_tables_init(struct net *net)
{
fib6_link_table(net, net->ipv6.fib6_main_tbl);
fib6_link_table(net, net->ipv6.fib6_local_tbl);
}
#else
struct fib6_table *fib6_new_table(struct net *net, u32 id)
{
return fib6_get_table(net, id);
}
struct fib6_table *fib6_get_table(struct net *net, u32 id)
{
return net->ipv6.fib6_main_tbl;
}
struct dst_entry *fib6_rule_lookup(struct net *net, struct flowi6 *fl6,
int flags, pol_lookup_t lookup)
{
struct rt6_info *rt;
rt = lookup(net, net->ipv6.fib6_main_tbl, fl6, flags);
if (rt->dst.error == -EAGAIN) {
ip6_rt_put(rt);
rt = net->ipv6.ip6_null_entry;
dst_hold(&rt->dst);
}
return &rt->dst;
}
static void __net_init fib6_tables_init(struct net *net)
{
fib6_link_table(net, net->ipv6.fib6_main_tbl);
}
#endif
unsigned int fib6_tables_seq_read(struct net *net)
{
unsigned int h, fib_seq = 0;
rcu_read_lock();
for (h = 0; h < FIB6_TABLE_HASHSZ; h++) {
struct hlist_head *head = &net->ipv6.fib_table_hash[h];
struct fib6_table *tb;
hlist_for_each_entry_rcu(tb, head, tb6_hlist) {
read_lock_bh(&tb->tb6_lock);
fib_seq += tb->fib_seq;
read_unlock_bh(&tb->tb6_lock);
}
}
rcu_read_unlock();
return fib_seq;
}
static int call_fib6_entry_notifier(struct notifier_block *nb, struct net *net,
enum fib_event_type event_type,
struct rt6_info *rt)
{
struct fib6_entry_notifier_info info = {
.rt = rt,
};
return call_fib6_notifier(nb, net, event_type, &info.info);
}
static int call_fib6_entry_notifiers(struct net *net,
enum fib_event_type event_type,
struct rt6_info *rt)
{
struct fib6_entry_notifier_info info = {
.rt = rt,
};
rt->rt6i_table->fib_seq++;
return call_fib6_notifiers(net, event_type, &info.info);
}
struct fib6_dump_arg {
struct net *net;
struct notifier_block *nb;
};
static void fib6_rt_dump(struct rt6_info *rt, struct fib6_dump_arg *arg)
{
if (rt == arg->net->ipv6.ip6_null_entry)
return;
call_fib6_entry_notifier(arg->nb, arg->net, FIB_EVENT_ENTRY_ADD, rt);
}
static int fib6_node_dump(struct fib6_walker *w)
{
struct rt6_info *rt;
for (rt = w->leaf; rt; rt = rt->dst.rt6_next)
fib6_rt_dump(rt, w->args);
w->leaf = NULL;
return 0;
}
static void fib6_table_dump(struct net *net, struct fib6_table *tb,
struct fib6_walker *w)
{
w->root = &tb->tb6_root;
read_lock_bh(&tb->tb6_lock);
fib6_walk(net, w);
read_unlock_bh(&tb->tb6_lock);
}
/* Called with rcu_read_lock() */
int fib6_tables_dump(struct net *net, struct notifier_block *nb)
{
struct fib6_dump_arg arg;
struct fib6_walker *w;
unsigned int h;
w = kzalloc(sizeof(*w), GFP_ATOMIC);
if (!w)
return -ENOMEM;
w->func = fib6_node_dump;
arg.net = net;
arg.nb = nb;
w->args = &arg;
for (h = 0; h < FIB6_TABLE_HASHSZ; h++) {
struct hlist_head *head = &net->ipv6.fib_table_hash[h];
struct fib6_table *tb;
hlist_for_each_entry_rcu(tb, head, tb6_hlist)
fib6_table_dump(net, tb, w);
}
kfree(w);
return 0;
}
static int fib6_dump_node(struct fib6_walker *w)
{
int res;
struct rt6_info *rt;
for (rt = w->leaf; rt; rt = rt->dst.rt6_next) {
res = rt6_dump_route(rt, w->args);
if (res < 0) {
/* Frame is full, suspend walking */
w->leaf = rt;
return 1;
}
/* Multipath routes are dumped in one route with the
* RTA_MULTIPATH attribute. Jump 'rt' to point to the
* last sibling of this route (no need to dump the
* sibling routes again)
*/
if (rt->rt6i_nsiblings)
rt = list_last_entry(&rt->rt6i_siblings,
struct rt6_info,
rt6i_siblings);
}
w->leaf = NULL;
return 0;
}
static void fib6_dump_end(struct netlink_callback *cb)
{
struct net *net = sock_net(cb->skb->sk);
struct fib6_walker *w = (void *)cb->args[2];
if (w) {
if (cb->args[4]) {
cb->args[4] = 0;
fib6_walker_unlink(net, w);
}
cb->args[2] = 0;
kfree(w);
}
cb->done = (void *)cb->args[3];
cb->args[1] = 3;
}
static int fib6_dump_done(struct netlink_callback *cb)
{
fib6_dump_end(cb);
return cb->done ? cb->done(cb) : 0;
}
static int fib6_dump_table(struct fib6_table *table, struct sk_buff *skb,
struct netlink_callback *cb)
{
struct net *net = sock_net(skb->sk);
struct fib6_walker *w;
int res;
w = (void *)cb->args[2];
w->root = &table->tb6_root;
if (cb->args[4] == 0) {
ipv6: fib: fix crash when changing large fib while dumping it When the fib size exceeds what can be dumped in a single skb, the dump is suspended and resumed once the last skb has been received by userspace. When the fib is changed while the dump is suspended, the walker might contain stale pointers, causing a crash when the dump is resumed. BUG: unable to handle kernel NULL pointer dereference at 0000000000000018 IP: [<ffffffffa01bce04>] fib6_walk_continue+0xbb/0x124 [ipv6] PGD 5347a067 PUD 65c7067 PMD 0 Oops: 0000 [#1] PREEMPT SMP ... RIP: 0010:[<ffffffffa01bce04>] [<ffffffffa01bce04>] fib6_walk_continue+0xbb/0x124 [ipv6] ... Call Trace: [<ffffffff8104aca3>] ? mutex_spin_on_owner+0x59/0x71 [<ffffffffa01bd105>] inet6_dump_fib+0x11b/0x1b9 [ipv6] [<ffffffff81371af4>] netlink_dump+0x5b/0x19e [<ffffffff8134f288>] ? consume_skb+0x28/0x2a [<ffffffff81373b69>] netlink_recvmsg+0x1ab/0x2c6 [<ffffffff81372781>] ? netlink_unicast+0xfa/0x151 [<ffffffff813483e0>] __sock_recvmsg+0x6d/0x79 [<ffffffff81348a53>] sock_recvmsg+0xca/0xe3 [<ffffffff81066d4b>] ? autoremove_wake_function+0x0/0x38 [<ffffffff811ed1f8>] ? radix_tree_lookup_slot+0xe/0x10 [<ffffffff810b3ed7>] ? find_get_page+0x90/0xa5 [<ffffffff810b5dc5>] ? filemap_fault+0x201/0x34f [<ffffffff810ef152>] ? fget_light+0x2f/0xac [<ffffffff813519e7>] ? verify_iovec+0x4f/0x94 [<ffffffff81349a65>] sys_recvmsg+0x14d/0x223 Store the serial number when beginning to walk the fib and reload pointers when continuing to walk after a change occured. Similar to other dumping functions, this might cause unrelated entries to be missed when entries are deleted. Tested-by: Ben Greear <greearb@candelatech.com> Signed-off-by: Patrick McHardy <kaber@trash.net> Signed-off-by: David S. Miller <davem@davemloft.net>
2010-02-08 05:19:03 +00:00
w->count = 0;
w->skip = 0;
read_lock_bh(&table->tb6_lock);
res = fib6_walk(net, w);
read_unlock_bh(&table->tb6_lock);
ipv6: fib: fix crash when changing large fib while dumping it When the fib size exceeds what can be dumped in a single skb, the dump is suspended and resumed once the last skb has been received by userspace. When the fib is changed while the dump is suspended, the walker might contain stale pointers, causing a crash when the dump is resumed. BUG: unable to handle kernel NULL pointer dereference at 0000000000000018 IP: [<ffffffffa01bce04>] fib6_walk_continue+0xbb/0x124 [ipv6] PGD 5347a067 PUD 65c7067 PMD 0 Oops: 0000 [#1] PREEMPT SMP ... RIP: 0010:[<ffffffffa01bce04>] [<ffffffffa01bce04>] fib6_walk_continue+0xbb/0x124 [ipv6] ... Call Trace: [<ffffffff8104aca3>] ? mutex_spin_on_owner+0x59/0x71 [<ffffffffa01bd105>] inet6_dump_fib+0x11b/0x1b9 [ipv6] [<ffffffff81371af4>] netlink_dump+0x5b/0x19e [<ffffffff8134f288>] ? consume_skb+0x28/0x2a [<ffffffff81373b69>] netlink_recvmsg+0x1ab/0x2c6 [<ffffffff81372781>] ? netlink_unicast+0xfa/0x151 [<ffffffff813483e0>] __sock_recvmsg+0x6d/0x79 [<ffffffff81348a53>] sock_recvmsg+0xca/0xe3 [<ffffffff81066d4b>] ? autoremove_wake_function+0x0/0x38 [<ffffffff811ed1f8>] ? radix_tree_lookup_slot+0xe/0x10 [<ffffffff810b3ed7>] ? find_get_page+0x90/0xa5 [<ffffffff810b5dc5>] ? filemap_fault+0x201/0x34f [<ffffffff810ef152>] ? fget_light+0x2f/0xac [<ffffffff813519e7>] ? verify_iovec+0x4f/0x94 [<ffffffff81349a65>] sys_recvmsg+0x14d/0x223 Store the serial number when beginning to walk the fib and reload pointers when continuing to walk after a change occured. Similar to other dumping functions, this might cause unrelated entries to be missed when entries are deleted. Tested-by: Ben Greear <greearb@candelatech.com> Signed-off-by: Patrick McHardy <kaber@trash.net> Signed-off-by: David S. Miller <davem@davemloft.net>
2010-02-08 05:19:03 +00:00
if (res > 0) {
cb->args[4] = 1;
ipv6: fib: fix crash when changing large fib while dumping it When the fib size exceeds what can be dumped in a single skb, the dump is suspended and resumed once the last skb has been received by userspace. When the fib is changed while the dump is suspended, the walker might contain stale pointers, causing a crash when the dump is resumed. BUG: unable to handle kernel NULL pointer dereference at 0000000000000018 IP: [<ffffffffa01bce04>] fib6_walk_continue+0xbb/0x124 [ipv6] PGD 5347a067 PUD 65c7067 PMD 0 Oops: 0000 [#1] PREEMPT SMP ... RIP: 0010:[<ffffffffa01bce04>] [<ffffffffa01bce04>] fib6_walk_continue+0xbb/0x124 [ipv6] ... Call Trace: [<ffffffff8104aca3>] ? mutex_spin_on_owner+0x59/0x71 [<ffffffffa01bd105>] inet6_dump_fib+0x11b/0x1b9 [ipv6] [<ffffffff81371af4>] netlink_dump+0x5b/0x19e [<ffffffff8134f288>] ? consume_skb+0x28/0x2a [<ffffffff81373b69>] netlink_recvmsg+0x1ab/0x2c6 [<ffffffff81372781>] ? netlink_unicast+0xfa/0x151 [<ffffffff813483e0>] __sock_recvmsg+0x6d/0x79 [<ffffffff81348a53>] sock_recvmsg+0xca/0xe3 [<ffffffff81066d4b>] ? autoremove_wake_function+0x0/0x38 [<ffffffff811ed1f8>] ? radix_tree_lookup_slot+0xe/0x10 [<ffffffff810b3ed7>] ? find_get_page+0x90/0xa5 [<ffffffff810b5dc5>] ? filemap_fault+0x201/0x34f [<ffffffff810ef152>] ? fget_light+0x2f/0xac [<ffffffff813519e7>] ? verify_iovec+0x4f/0x94 [<ffffffff81349a65>] sys_recvmsg+0x14d/0x223 Store the serial number when beginning to walk the fib and reload pointers when continuing to walk after a change occured. Similar to other dumping functions, this might cause unrelated entries to be missed when entries are deleted. Tested-by: Ben Greear <greearb@candelatech.com> Signed-off-by: Patrick McHardy <kaber@trash.net> Signed-off-by: David S. Miller <davem@davemloft.net>
2010-02-08 05:19:03 +00:00
cb->args[5] = w->root->fn_sernum;
}
} else {
ipv6: fib: fix crash when changing large fib while dumping it When the fib size exceeds what can be dumped in a single skb, the dump is suspended and resumed once the last skb has been received by userspace. When the fib is changed while the dump is suspended, the walker might contain stale pointers, causing a crash when the dump is resumed. BUG: unable to handle kernel NULL pointer dereference at 0000000000000018 IP: [<ffffffffa01bce04>] fib6_walk_continue+0xbb/0x124 [ipv6] PGD 5347a067 PUD 65c7067 PMD 0 Oops: 0000 [#1] PREEMPT SMP ... RIP: 0010:[<ffffffffa01bce04>] [<ffffffffa01bce04>] fib6_walk_continue+0xbb/0x124 [ipv6] ... Call Trace: [<ffffffff8104aca3>] ? mutex_spin_on_owner+0x59/0x71 [<ffffffffa01bd105>] inet6_dump_fib+0x11b/0x1b9 [ipv6] [<ffffffff81371af4>] netlink_dump+0x5b/0x19e [<ffffffff8134f288>] ? consume_skb+0x28/0x2a [<ffffffff81373b69>] netlink_recvmsg+0x1ab/0x2c6 [<ffffffff81372781>] ? netlink_unicast+0xfa/0x151 [<ffffffff813483e0>] __sock_recvmsg+0x6d/0x79 [<ffffffff81348a53>] sock_recvmsg+0xca/0xe3 [<ffffffff81066d4b>] ? autoremove_wake_function+0x0/0x38 [<ffffffff811ed1f8>] ? radix_tree_lookup_slot+0xe/0x10 [<ffffffff810b3ed7>] ? find_get_page+0x90/0xa5 [<ffffffff810b5dc5>] ? filemap_fault+0x201/0x34f [<ffffffff810ef152>] ? fget_light+0x2f/0xac [<ffffffff813519e7>] ? verify_iovec+0x4f/0x94 [<ffffffff81349a65>] sys_recvmsg+0x14d/0x223 Store the serial number when beginning to walk the fib and reload pointers when continuing to walk after a change occured. Similar to other dumping functions, this might cause unrelated entries to be missed when entries are deleted. Tested-by: Ben Greear <greearb@candelatech.com> Signed-off-by: Patrick McHardy <kaber@trash.net> Signed-off-by: David S. Miller <davem@davemloft.net>
2010-02-08 05:19:03 +00:00
if (cb->args[5] != w->root->fn_sernum) {
/* Begin at the root if the tree changed */
cb->args[5] = w->root->fn_sernum;
w->state = FWS_INIT;
w->node = w->root;
w->skip = w->count;
} else
w->skip = 0;
read_lock_bh(&table->tb6_lock);
res = fib6_walk_continue(w);
read_unlock_bh(&table->tb6_lock);
if (res <= 0) {
fib6_walker_unlink(net, w);
cb->args[4] = 0;
}
}
return res;
}
static int inet6_dump_fib(struct sk_buff *skb, struct netlink_callback *cb)
{
struct net *net = sock_net(skb->sk);
unsigned int h, s_h;
unsigned int e = 0, s_e;
struct rt6_rtnl_dump_arg arg;
struct fib6_walker *w;
struct fib6_table *tb;
struct hlist_head *head;
int res = 0;
s_h = cb->args[0];
s_e = cb->args[1];
w = (void *)cb->args[2];
if (!w) {
/* New dump:
*
* 1. hook callback destructor.
*/
cb->args[3] = (long)cb->done;
cb->done = fib6_dump_done;
/*
* 2. allocate and initialize walker.
*/
w = kzalloc(sizeof(*w), GFP_ATOMIC);
if (!w)
return -ENOMEM;
w->func = fib6_dump_node;
cb->args[2] = (long)w;
}
arg.skb = skb;
arg.cb = cb;
arg.net = net;
w->args = &arg;
rcu_read_lock();
for (h = s_h; h < FIB6_TABLE_HASHSZ; h++, s_e = 0) {
e = 0;
head = &net->ipv6.fib_table_hash[h];
hlist: drop the node parameter from iterators I'm not sure why, but the hlist for each entry iterators were conceived list_for_each_entry(pos, head, member) The hlist ones were greedy and wanted an extra parameter: hlist_for_each_entry(tpos, pos, head, member) Why did they need an extra pos parameter? I'm not quite sure. Not only they don't really need it, it also prevents the iterator from looking exactly like the list iterator, which is unfortunate. Besides the semantic patch, there was some manual work required: - Fix up the actual hlist iterators in linux/list.h - Fix up the declaration of other iterators based on the hlist ones. - A very small amount of places were using the 'node' parameter, this was modified to use 'obj->member' instead. - Coccinelle didn't handle the hlist_for_each_entry_safe iterator properly, so those had to be fixed up manually. The semantic patch which is mostly the work of Peter Senna Tschudin is here: @@ iterator name hlist_for_each_entry, hlist_for_each_entry_continue, hlist_for_each_entry_from, hlist_for_each_entry_rcu, hlist_for_each_entry_rcu_bh, hlist_for_each_entry_continue_rcu_bh, for_each_busy_worker, ax25_uid_for_each, ax25_for_each, inet_bind_bucket_for_each, sctp_for_each_hentry, sk_for_each, sk_for_each_rcu, sk_for_each_from, sk_for_each_safe, sk_for_each_bound, hlist_for_each_entry_safe, hlist_for_each_entry_continue_rcu, nr_neigh_for_each, nr_neigh_for_each_safe, nr_node_for_each, nr_node_for_each_safe, for_each_gfn_indirect_valid_sp, for_each_gfn_sp, for_each_host; type T; expression a,c,d,e; identifier b; statement S; @@ -T b; <+... when != b ( hlist_for_each_entry(a, - b, c, d) S | hlist_for_each_entry_continue(a, - b, c) S | hlist_for_each_entry_from(a, - b, c) S | hlist_for_each_entry_rcu(a, - b, c, d) S | hlist_for_each_entry_rcu_bh(a, - b, c, d) S | hlist_for_each_entry_continue_rcu_bh(a, - b, c) S | for_each_busy_worker(a, c, - b, d) S | ax25_uid_for_each(a, - b, c) S | ax25_for_each(a, - b, c) S | inet_bind_bucket_for_each(a, - b, c) S | sctp_for_each_hentry(a, - b, c) S | sk_for_each(a, - b, c) S | sk_for_each_rcu(a, - b, c) S | sk_for_each_from -(a, b) +(a) S + sk_for_each_from(a) S | sk_for_each_safe(a, - b, c, d) S | sk_for_each_bound(a, - b, c) S | hlist_for_each_entry_safe(a, - b, c, d, e) S | hlist_for_each_entry_continue_rcu(a, - b, c) S | nr_neigh_for_each(a, - b, c) S | nr_neigh_for_each_safe(a, - b, c, d) S | nr_node_for_each(a, - b, c) S | nr_node_for_each_safe(a, - b, c, d) S | - for_each_gfn_sp(a, c, d, b) S + for_each_gfn_sp(a, c, d) S | - for_each_gfn_indirect_valid_sp(a, c, d, b) S + for_each_gfn_indirect_valid_sp(a, c, d) S | for_each_host(a, - b, c) S | for_each_host_safe(a, - b, c, d) S | for_each_mesh_entry(a, - b, c, d) S ) ...+> [akpm@linux-foundation.org: drop bogus change from net/ipv4/raw.c] [akpm@linux-foundation.org: drop bogus hunk from net/ipv6/raw.c] [akpm@linux-foundation.org: checkpatch fixes] [akpm@linux-foundation.org: fix warnings] [akpm@linux-foudnation.org: redo intrusive kvm changes] Tested-by: Peter Senna Tschudin <peter.senna@gmail.com> Acked-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Signed-off-by: Sasha Levin <sasha.levin@oracle.com> Cc: Wu Fengguang <fengguang.wu@intel.com> Cc: Marcelo Tosatti <mtosatti@redhat.com> Cc: Gleb Natapov <gleb@redhat.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2013-02-28 01:06:00 +00:00
hlist_for_each_entry_rcu(tb, head, tb6_hlist) {
if (e < s_e)
goto next;
res = fib6_dump_table(tb, skb, cb);
if (res != 0)
goto out;
next:
e++;
}
}
out:
rcu_read_unlock();
cb->args[1] = e;
cb->args[0] = h;
res = res < 0 ? res : skb->len;
if (res <= 0)
fib6_dump_end(cb);
return res;
}
/*
* Routing Table
*
* return the appropriate node for a routing tree "add" operation
* by either creating and inserting or by returning an existing
* node.
*/
static struct fib6_node *fib6_add_1(struct fib6_node *root,
struct in6_addr *addr, int plen,
int offset, int allow_create,
int replace_required, int sernum,
struct netlink_ext_ack *extack)
{
struct fib6_node *fn, *in, *ln;
struct fib6_node *pn = NULL;
struct rt6key *key;
int bit;
__be32 dir = 0;
RT6_TRACE("fib6_add_1\n");
/* insert node in tree */
fn = root;
do {
key = (struct rt6key *)((u8 *)fn->leaf + offset);
/*
* Prefix match
*/
if (plen < fn->fn_bit ||
!ipv6_prefix_equal(&key->addr, addr, fn->fn_bit)) {
if (!allow_create) {
if (replace_required) {
NL_SET_ERR_MSG(extack,
"Can not replace route - no match found");
pr_warn("Can't replace route, no match found\n");
return ERR_PTR(-ENOENT);
}
pr_warn("NLM_F_CREATE should be set when creating new route\n");
}
goto insert_above;
}
/*
* Exact match ?
*/
if (plen == fn->fn_bit) {
/* clean up an intermediate node */
if (!(fn->fn_flags & RTN_RTINFO)) {
rt6_release(fn->leaf);
fn->leaf = NULL;
}
fn->fn_sernum = sernum;
return fn;
}
/*
* We have more bits to go
*/
/* Try to walk down on tree. */
fn->fn_sernum = sernum;
dir = addr_bit_set(addr, fn->fn_bit);
pn = fn;
fn = dir ? fn->right : fn->left;
} while (fn);
if (!allow_create) {
/* We should not create new node because
* NLM_F_REPLACE was specified without NLM_F_CREATE
* I assume it is safe to require NLM_F_CREATE when
* REPLACE flag is used! Later we may want to remove the
* check for replace_required, because according
* to netlink specification, NLM_F_CREATE
* MUST be specified if new route is created.
* That would keep IPv6 consistent with IPv4
*/
if (replace_required) {
NL_SET_ERR_MSG(extack,
"Can not replace route - no match found");
pr_warn("Can't replace route, no match found\n");
return ERR_PTR(-ENOENT);
}
pr_warn("NLM_F_CREATE should be set when creating new route\n");
}
/*
* We walked to the bottom of tree.
* Create new leaf node without children.
*/
ln = node_alloc();
if (!ln)
return ERR_PTR(-ENOMEM);
ln->fn_bit = plen;
ln->parent = pn;
ln->fn_sernum = sernum;
if (dir)
pn->right = ln;
else
pn->left = ln;
return ln;
insert_above:
/*
* split since we don't have a common prefix anymore or
* we have a less significant route.
* we've to insert an intermediate node on the list
* this new node will point to the one we need to create
* and the current
*/
pn = fn->parent;
/* find 1st bit in difference between the 2 addrs.
See comment in __ipv6_addr_diff: bit may be an invalid value,
but if it is >= plen, the value is ignored in any case.
*/
bit = __ipv6_addr_diff(addr, &key->addr, sizeof(*addr));
/*
* (intermediate)[in]
* / \
* (new leaf node)[ln] (old node)[fn]
*/
if (plen > bit) {
in = node_alloc();
ln = node_alloc();
if (!in || !ln) {
if (in)
node_free_immediate(in);
if (ln)
node_free_immediate(ln);
return ERR_PTR(-ENOMEM);
}
/*
* new intermediate node.
* RTN_RTINFO will
* be off since that an address that chooses one of
* the branches would not match less specific routes
* in the other branch
*/
in->fn_bit = bit;
in->parent = pn;
in->leaf = fn->leaf;
atomic_inc(&in->leaf->rt6i_ref);
in->fn_sernum = sernum;
/* update parent pointer */
if (dir)
pn->right = in;
else
pn->left = in;
ln->fn_bit = plen;
ln->parent = in;
fn->parent = in;
ln->fn_sernum = sernum;
if (addr_bit_set(addr, bit)) {
in->right = ln;
in->left = fn;
} else {
in->left = ln;
in->right = fn;
}
} else { /* plen <= bit */
/*
* (new leaf node)[ln]
* / \
* (old node)[fn] NULL
*/
ln = node_alloc();
if (!ln)
return ERR_PTR(-ENOMEM);
ln->fn_bit = plen;
ln->parent = pn;
ln->fn_sernum = sernum;
if (dir)
pn->right = ln;
else
pn->left = ln;
if (addr_bit_set(&key->addr, plen))
ln->right = fn;
else
ln->left = fn;
fn->parent = ln;
}
return ln;
}
static bool rt6_qualify_for_ecmp(struct rt6_info *rt)
{
return (rt->rt6i_flags & (RTF_GATEWAY|RTF_ADDRCONF|RTF_DYNAMIC)) ==
RTF_GATEWAY;
}
static void fib6_copy_metrics(u32 *mp, const struct mx6_config *mxc)
ipv6: do not overwrite inetpeer metrics prematurely If an IPv6 host route with metrics exists, an attempt to add a new route for the same target with different metrics fails but rewrites the metrics anyway: 12sp0:~ # ip route add fec0::1 dev eth0 rto_min 1000 12sp0:~ # ip -6 route show fe80::/64 dev eth0 proto kernel metric 256 fec0::1 dev eth0 metric 1024 rto_min lock 1s 12sp0:~ # ip route add fec0::1 dev eth0 rto_min 1500 RTNETLINK answers: File exists 12sp0:~ # ip -6 route show fe80::/64 dev eth0 proto kernel metric 256 fec0::1 dev eth0 metric 1024 rto_min lock 1.5s This is caused by all IPv6 host routes using the metrics in their inetpeer (or the shared default). This also holds for the new route created in ip6_route_add() which shares the metrics with the already existing route and thus ip6_route_add() rewrites the metrics even if the new route ends up not being used at all. Another problem is that old metrics in inetpeer can reappear unexpectedly for a new route, e.g. 12sp0:~ # ip route add fec0::1 dev eth0 rto_min 1000 12sp0:~ # ip route del fec0::1 12sp0:~ # ip route add fec0::1 dev eth0 12sp0:~ # ip route change fec0::1 dev eth0 hoplimit 10 12sp0:~ # ip -6 route show fe80::/64 dev eth0 proto kernel metric 256 fec0::1 dev eth0 metric 1024 hoplimit 10 rto_min lock 1s Resolve the first problem by moving the setting of metrics down into fib6_add_rt2node() to the point we are sure we are inserting the new route into the tree. Second problem is addressed by introducing new flag DST_METRICS_FORCE_OVERWRITE which is set for a new host route in ip6_route_add() and makes ipv6_cow_metrics() always overwrite the metrics in inetpeer (even if they are not "new"); it is reset after that. v5: use a flag in _metrics member rather than one in flags v4: fix a typo making a condition always true (thanks to Hannes Frederic Sowa) v3: rewritten based on David Miller's idea to move setting the metrics (and allocation in non-host case) down to the point we already know the route is to be inserted. Also rebased to net-next as it is quite late in the cycle. Signed-off-by: Michal Kubecek <mkubecek@suse.cz> Acked-by: Hannes Frederic Sowa <hannes@stressinduktion.org> Signed-off-by: David S. Miller <davem@davemloft.net>
2014-03-27 12:04:08 +00:00
{
int i;
for (i = 0; i < RTAX_MAX; i++) {
if (test_bit(i, mxc->mx_valid))
mp[i] = mxc->mx[i];
}
}
static int fib6_commit_metrics(struct dst_entry *dst, struct mx6_config *mxc)
{
if (!mxc->mx)
return 0;
if (dst->flags & DST_HOST) {
u32 *mp = dst_metrics_write_ptr(dst);
if (unlikely(!mp))
return -ENOMEM;
fib6_copy_metrics(mp, mxc);
} else {
dst_init_metrics(dst, mxc->mx, false);
/* We've stolen mx now. */
mxc->mx = NULL;
ipv6: do not overwrite inetpeer metrics prematurely If an IPv6 host route with metrics exists, an attempt to add a new route for the same target with different metrics fails but rewrites the metrics anyway: 12sp0:~ # ip route add fec0::1 dev eth0 rto_min 1000 12sp0:~ # ip -6 route show fe80::/64 dev eth0 proto kernel metric 256 fec0::1 dev eth0 metric 1024 rto_min lock 1s 12sp0:~ # ip route add fec0::1 dev eth0 rto_min 1500 RTNETLINK answers: File exists 12sp0:~ # ip -6 route show fe80::/64 dev eth0 proto kernel metric 256 fec0::1 dev eth0 metric 1024 rto_min lock 1.5s This is caused by all IPv6 host routes using the metrics in their inetpeer (or the shared default). This also holds for the new route created in ip6_route_add() which shares the metrics with the already existing route and thus ip6_route_add() rewrites the metrics even if the new route ends up not being used at all. Another problem is that old metrics in inetpeer can reappear unexpectedly for a new route, e.g. 12sp0:~ # ip route add fec0::1 dev eth0 rto_min 1000 12sp0:~ # ip route del fec0::1 12sp0:~ # ip route add fec0::1 dev eth0 12sp0:~ # ip route change fec0::1 dev eth0 hoplimit 10 12sp0:~ # ip -6 route show fe80::/64 dev eth0 proto kernel metric 256 fec0::1 dev eth0 metric 1024 hoplimit 10 rto_min lock 1s Resolve the first problem by moving the setting of metrics down into fib6_add_rt2node() to the point we are sure we are inserting the new route into the tree. Second problem is addressed by introducing new flag DST_METRICS_FORCE_OVERWRITE which is set for a new host route in ip6_route_add() and makes ipv6_cow_metrics() always overwrite the metrics in inetpeer (even if they are not "new"); it is reset after that. v5: use a flag in _metrics member rather than one in flags v4: fix a typo making a condition always true (thanks to Hannes Frederic Sowa) v3: rewritten based on David Miller's idea to move setting the metrics (and allocation in non-host case) down to the point we already know the route is to be inserted. Also rebased to net-next as it is quite late in the cycle. Signed-off-by: Michal Kubecek <mkubecek@suse.cz> Acked-by: Hannes Frederic Sowa <hannes@stressinduktion.org> Signed-off-by: David S. Miller <davem@davemloft.net>
2014-03-27 12:04:08 +00:00
}
ipv6: do not overwrite inetpeer metrics prematurely If an IPv6 host route with metrics exists, an attempt to add a new route for the same target with different metrics fails but rewrites the metrics anyway: 12sp0:~ # ip route add fec0::1 dev eth0 rto_min 1000 12sp0:~ # ip -6 route show fe80::/64 dev eth0 proto kernel metric 256 fec0::1 dev eth0 metric 1024 rto_min lock 1s 12sp0:~ # ip route add fec0::1 dev eth0 rto_min 1500 RTNETLINK answers: File exists 12sp0:~ # ip -6 route show fe80::/64 dev eth0 proto kernel metric 256 fec0::1 dev eth0 metric 1024 rto_min lock 1.5s This is caused by all IPv6 host routes using the metrics in their inetpeer (or the shared default). This also holds for the new route created in ip6_route_add() which shares the metrics with the already existing route and thus ip6_route_add() rewrites the metrics even if the new route ends up not being used at all. Another problem is that old metrics in inetpeer can reappear unexpectedly for a new route, e.g. 12sp0:~ # ip route add fec0::1 dev eth0 rto_min 1000 12sp0:~ # ip route del fec0::1 12sp0:~ # ip route add fec0::1 dev eth0 12sp0:~ # ip route change fec0::1 dev eth0 hoplimit 10 12sp0:~ # ip -6 route show fe80::/64 dev eth0 proto kernel metric 256 fec0::1 dev eth0 metric 1024 hoplimit 10 rto_min lock 1s Resolve the first problem by moving the setting of metrics down into fib6_add_rt2node() to the point we are sure we are inserting the new route into the tree. Second problem is addressed by introducing new flag DST_METRICS_FORCE_OVERWRITE which is set for a new host route in ip6_route_add() and makes ipv6_cow_metrics() always overwrite the metrics in inetpeer (even if they are not "new"); it is reset after that. v5: use a flag in _metrics member rather than one in flags v4: fix a typo making a condition always true (thanks to Hannes Frederic Sowa) v3: rewritten based on David Miller's idea to move setting the metrics (and allocation in non-host case) down to the point we already know the route is to be inserted. Also rebased to net-next as it is quite late in the cycle. Signed-off-by: Michal Kubecek <mkubecek@suse.cz> Acked-by: Hannes Frederic Sowa <hannes@stressinduktion.org> Signed-off-by: David S. Miller <davem@davemloft.net>
2014-03-27 12:04:08 +00:00
return 0;
}
static void fib6_purge_rt(struct rt6_info *rt, struct fib6_node *fn,
struct net *net)
{
if (atomic_read(&rt->rt6i_ref) != 1) {
/* This route is used as dummy address holder in some split
* nodes. It is not leaked, but it still holds other resources,
* which must be released in time. So, scan ascendant nodes
* and replace dummy references to this route with references
* to still alive ones.
*/
while (fn) {
if (!(fn->fn_flags & RTN_RTINFO) && fn->leaf == rt) {
fn->leaf = fib6_find_prefix(net, fn);
atomic_inc(&fn->leaf->rt6i_ref);
rt6_release(rt);
}
fn = fn->parent;
}
}
}
/*
* Insert routing information in a node.
*/
static int fib6_add_rt2node(struct fib6_node *fn, struct rt6_info *rt,
struct nl_info *info, struct mx6_config *mxc)
{
struct rt6_info *iter = NULL;
struct rt6_info **ins;
struct rt6_info **fallback_ins = NULL;
int replace = (info->nlh &&
(info->nlh->nlmsg_flags & NLM_F_REPLACE));
int add = (!info->nlh ||
(info->nlh->nlmsg_flags & NLM_F_CREATE));
int found = 0;
bool rt_can_ecmp = rt6_qualify_for_ecmp(rt);
u16 nlflags = NLM_F_EXCL;
ipv6: do not overwrite inetpeer metrics prematurely If an IPv6 host route with metrics exists, an attempt to add a new route for the same target with different metrics fails but rewrites the metrics anyway: 12sp0:~ # ip route add fec0::1 dev eth0 rto_min 1000 12sp0:~ # ip -6 route show fe80::/64 dev eth0 proto kernel metric 256 fec0::1 dev eth0 metric 1024 rto_min lock 1s 12sp0:~ # ip route add fec0::1 dev eth0 rto_min 1500 RTNETLINK answers: File exists 12sp0:~ # ip -6 route show fe80::/64 dev eth0 proto kernel metric 256 fec0::1 dev eth0 metric 1024 rto_min lock 1.5s This is caused by all IPv6 host routes using the metrics in their inetpeer (or the shared default). This also holds for the new route created in ip6_route_add() which shares the metrics with the already existing route and thus ip6_route_add() rewrites the metrics even if the new route ends up not being used at all. Another problem is that old metrics in inetpeer can reappear unexpectedly for a new route, e.g. 12sp0:~ # ip route add fec0::1 dev eth0 rto_min 1000 12sp0:~ # ip route del fec0::1 12sp0:~ # ip route add fec0::1 dev eth0 12sp0:~ # ip route change fec0::1 dev eth0 hoplimit 10 12sp0:~ # ip -6 route show fe80::/64 dev eth0 proto kernel metric 256 fec0::1 dev eth0 metric 1024 hoplimit 10 rto_min lock 1s Resolve the first problem by moving the setting of metrics down into fib6_add_rt2node() to the point we are sure we are inserting the new route into the tree. Second problem is addressed by introducing new flag DST_METRICS_FORCE_OVERWRITE which is set for a new host route in ip6_route_add() and makes ipv6_cow_metrics() always overwrite the metrics in inetpeer (even if they are not "new"); it is reset after that. v5: use a flag in _metrics member rather than one in flags v4: fix a typo making a condition always true (thanks to Hannes Frederic Sowa) v3: rewritten based on David Miller's idea to move setting the metrics (and allocation in non-host case) down to the point we already know the route is to be inserted. Also rebased to net-next as it is quite late in the cycle. Signed-off-by: Michal Kubecek <mkubecek@suse.cz> Acked-by: Hannes Frederic Sowa <hannes@stressinduktion.org> Signed-off-by: David S. Miller <davem@davemloft.net>
2014-03-27 12:04:08 +00:00
int err;
if (info->nlh && (info->nlh->nlmsg_flags & NLM_F_APPEND))
nlflags |= NLM_F_APPEND;
ins = &fn->leaf;
for (iter = fn->leaf; iter; iter = iter->dst.rt6_next) {
/*
* Search for duplicates
*/
if (iter->rt6i_metric == rt->rt6i_metric) {
/*
* Same priority level
*/
if (info->nlh &&
(info->nlh->nlmsg_flags & NLM_F_EXCL))
return -EEXIST;
nlflags &= ~NLM_F_EXCL;
if (replace) {
if (rt_can_ecmp == rt6_qualify_for_ecmp(iter)) {
found++;
break;
}
if (rt_can_ecmp)
fallback_ins = fallback_ins ?: ins;
goto next_iter;
}
if (rt6_duplicate_nexthop(iter, rt)) {
if (rt->rt6i_nsiblings)
rt->rt6i_nsiblings = 0;
if (!(iter->rt6i_flags & RTF_EXPIRES))
return -EEXIST;
if (!(rt->rt6i_flags & RTF_EXPIRES))
rt6_clean_expires(iter);
else
rt6_set_expires(iter, rt->dst.expires);
iter->rt6i_pmtu = rt->rt6i_pmtu;
return -EEXIST;
}
/* If we have the same destination and the same metric,
* but not the same gateway, then the route we try to
* add is sibling to this route, increment our counter
* of siblings, and later we will add our route to the
* list.
* Only static routes (which don't have flag
* RTF_EXPIRES) are used for ECMPv6.
*
* To avoid long list, we only had siblings if the
* route have a gateway.
*/
if (rt_can_ecmp &&
rt6_qualify_for_ecmp(iter))
rt->rt6i_nsiblings++;
}
if (iter->rt6i_metric > rt->rt6i_metric)
break;
next_iter:
ins = &iter->dst.rt6_next;
}
if (fallback_ins && !found) {
/* No ECMP-able route found, replace first non-ECMP one */
ins = fallback_ins;
iter = *ins;
found++;
}
[IPV6]: Fix routing round-robin locking. As per RFC2461, section 6.3.6, item #2, when no routers on the matching list are known to be reachable or probably reachable we do round robin on those available routes so that we make sure to probe as many of them as possible to detect when one becomes reachable faster. Each routing table has a rwlock protecting the tree and the linked list of routes at each leaf. The round robin code executes during lookup and thus with the rwlock taken as a reader. A small local spinlock tries to provide protection but this does not work at all for two reasons: 1) The round-robin list manipulation, as coded, goes like this (with read lock held): walk routes finding head and tail spin_lock(); rotate list using head and tail spin_unlock(); While one thread is rotating the list, another thread can end up with stale values of head and tail and then proceed to corrupt the list when it gets the lock. This ends up causing the OOPS in fib6_add() later onthat many people have been hitting. 2) All the other code paths that run with the rwlock held as a reader do not expect the list to change on them, they expect it to remain completely fixed while they hold the lock in that way. So, simply stated, it is impossible to implement this correctly using a manipulation of the list without violating the rwlock locking semantics. Reimplement using a per-fib6_node round-robin pointer. This way we don't need to manipulate the list at all, and since the round-robin pointer can only ever point to real existing entries we don't need to perform any locking on the changing of the round-robin pointer itself. We only need to reset the round-robin pointer to NULL when the entry it is pointing to is removed. The idea is from Thomas Graf and it is very similar to how this was implemented before the advanced router selection code when in. Signed-off-by: David S. Miller <davem@davemloft.net>
2007-03-25 03:36:25 +00:00
/* Reset round-robin state, if necessary */
if (ins == &fn->leaf)
fn->rr_ptr = NULL;
/* Link this route to others same route. */
if (rt->rt6i_nsiblings) {
unsigned int rt6i_nsiblings;
struct rt6_info *sibling, *temp_sibling;
/* Find the first route that have the same metric */
sibling = fn->leaf;
while (sibling) {
if (sibling->rt6i_metric == rt->rt6i_metric &&
rt6_qualify_for_ecmp(sibling)) {
list_add_tail(&rt->rt6i_siblings,
&sibling->rt6i_siblings);
break;
}
sibling = sibling->dst.rt6_next;
}
/* For each sibling in the list, increment the counter of
* siblings. BUG() if counters does not match, list of siblings
* is broken!
*/
rt6i_nsiblings = 0;
list_for_each_entry_safe(sibling, temp_sibling,
&rt->rt6i_siblings, rt6i_siblings) {
sibling->rt6i_nsiblings++;
BUG_ON(sibling->rt6i_nsiblings != rt->rt6i_nsiblings);
rt6i_nsiblings++;
}
BUG_ON(rt6i_nsiblings != rt->rt6i_nsiblings);
}
/*
* insert node
*/
if (!replace) {
if (!add)
pr_warn("NLM_F_CREATE should be set when creating new route\n");
add:
nlflags |= NLM_F_CREATE;
err = fib6_commit_metrics(&rt->dst, mxc);
if (err)
return err;
rt->dst.rt6_next = iter;
*ins = rt;
rcu_assign_pointer(rt->rt6i_node, fn);
atomic_inc(&rt->rt6i_ref);
call_fib6_entry_notifiers(info->nl_net, FIB_EVENT_ENTRY_ADD,
rt);
if (!info->skip_notify)
inet6_rt_notify(RTM_NEWROUTE, rt, info, nlflags);
info->nl_net->ipv6.rt6_stats->fib_rt_entries++;
if (!(fn->fn_flags & RTN_RTINFO)) {
info->nl_net->ipv6.rt6_stats->fib_route_nodes++;
fn->fn_flags |= RTN_RTINFO;
}
} else {
int nsiblings;
if (!found) {
if (add)
goto add;
pr_warn("NLM_F_REPLACE set, but no existing node found!\n");
return -ENOENT;
}
err = fib6_commit_metrics(&rt->dst, mxc);
if (err)
return err;
*ins = rt;
rcu_assign_pointer(rt->rt6i_node, fn);
rt->dst.rt6_next = iter->dst.rt6_next;
atomic_inc(&rt->rt6i_ref);
call_fib6_entry_notifiers(info->nl_net, FIB_EVENT_ENTRY_REPLACE,
rt);
if (!info->skip_notify)
inet6_rt_notify(RTM_NEWROUTE, rt, info, NLM_F_REPLACE);
if (!(fn->fn_flags & RTN_RTINFO)) {
info->nl_net->ipv6.rt6_stats->fib_route_nodes++;
fn->fn_flags |= RTN_RTINFO;
}
nsiblings = iter->rt6i_nsiblings;
iter->rt6i_node = NULL;
fib6_purge_rt(iter, fn, info->nl_net);
ipv6: reset fn->rr_ptr when replacing route syzcaller reported the following use-after-free issue in rt6_select(): BUG: KASAN: use-after-free in rt6_select net/ipv6/route.c:755 [inline] at addr ffff8800bc6994e8 BUG: KASAN: use-after-free in ip6_pol_route.isra.46+0x1429/0x1470 net/ipv6/route.c:1084 at addr ffff8800bc6994e8 Read of size 4 by task syz-executor1/439628 CPU: 0 PID: 439628 Comm: syz-executor1 Not tainted 4.3.5+ #8 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 0000000000000000 ffff88018fe435b0 ffffffff81ca384d ffff8801d3588c00 ffff8800bc699380 ffff8800bc699500 dffffc0000000000 ffff8801d40a47c0 ffff88018fe435d8 ffffffff81735751 ffff88018fe43660 ffff8800bc699380 Call Trace: [<ffffffff81ca384d>] __dump_stack lib/dump_stack.c:15 [inline] [<ffffffff81ca384d>] dump_stack+0xc1/0x124 lib/dump_stack.c:51 sctp: [Deprecated]: syz-executor0 (pid 439615) Use of struct sctp_assoc_value in delayed_ack socket option. Use struct sctp_sack_info instead [<ffffffff81735751>] kasan_object_err+0x21/0x70 mm/kasan/report.c:158 [<ffffffff817359c4>] print_address_description mm/kasan/report.c:196 [inline] [<ffffffff817359c4>] kasan_report_error+0x1b4/0x4a0 mm/kasan/report.c:285 [<ffffffff81735d93>] kasan_report mm/kasan/report.c:305 [inline] [<ffffffff81735d93>] __asan_report_load4_noabort+0x43/0x50 mm/kasan/report.c:325 [<ffffffff82a28e39>] rt6_select net/ipv6/route.c:755 [inline] [<ffffffff82a28e39>] ip6_pol_route.isra.46+0x1429/0x1470 net/ipv6/route.c:1084 [<ffffffff82a28fb1>] ip6_pol_route_output+0x81/0xb0 net/ipv6/route.c:1203 [<ffffffff82ab0a50>] fib6_rule_action+0x1f0/0x680 net/ipv6/fib6_rules.c:95 [<ffffffff8265cbb6>] fib_rules_lookup+0x2a6/0x7a0 net/core/fib_rules.c:223 [<ffffffff82ab1430>] fib6_rule_lookup+0xd0/0x250 net/ipv6/fib6_rules.c:41 [<ffffffff82a22006>] ip6_route_output+0x1d6/0x2c0 net/ipv6/route.c:1224 [<ffffffff829e83d2>] ip6_dst_lookup_tail+0x4d2/0x890 net/ipv6/ip6_output.c:943 [<ffffffff829e889a>] ip6_dst_lookup_flow+0x9a/0x250 net/ipv6/ip6_output.c:1079 [<ffffffff82a9f7d8>] ip6_datagram_dst_update+0x538/0xd40 net/ipv6/datagram.c:91 [<ffffffff82aa0978>] __ip6_datagram_connect net/ipv6/datagram.c:251 [inline] [<ffffffff82aa0978>] ip6_datagram_connect+0x518/0xe50 net/ipv6/datagram.c:272 [<ffffffff82aa1313>] ip6_datagram_connect_v6_only+0x63/0x90 net/ipv6/datagram.c:284 [<ffffffff8292f790>] inet_dgram_connect+0x170/0x1f0 net/ipv4/af_inet.c:564 [<ffffffff82565547>] SYSC_connect+0x1a7/0x2f0 net/socket.c:1582 [<ffffffff8256a649>] SyS_connect+0x29/0x30 net/socket.c:1563 [<ffffffff82c72032>] entry_SYSCALL_64_fastpath+0x12/0x17 Object at ffff8800bc699380, in cache ip6_dst_cache size: 384 The root cause of it is that in fib6_add_rt2node(), when it replaces an existing route with the new one, it does not update fn->rr_ptr. This commit resets fn->rr_ptr to NULL when it points to a route which is replaced in fib6_add_rt2node(). Fixes: 27596472473a ("ipv6: fix ECMP route replacement") Signed-off-by: Wei Wang <weiwan@google.com> Acked-by: Eric Dumazet <edumazet@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-08-16 18:18:09 +00:00
if (fn->rr_ptr == iter)
fn->rr_ptr = NULL;
rt6_release(iter);
if (nsiblings) {
/* Replacing an ECMP route, remove all siblings */
ins = &rt->dst.rt6_next;
iter = *ins;
while (iter) {
ipv6: make ECMP route replacement less greedy Commit 27596472473a ("ipv6: fix ECMP route replacement") introduced a loop that removes all siblings of an ECMP route that is being replaced. However, this loop doesn't stop when it has replaced siblings, and keeps removing other routes with a higher metric. We also end up triggering the WARN_ON after the loop, because after this nsiblings < 0. Instead, stop the loop when we have taken care of all routes with the same metric as the route being replaced. Reproducer: =========== #!/bin/sh ip netns add ns1 ip netns add ns2 ip -net ns1 link set lo up for x in 0 1 2 ; do ip link add veth$x netns ns2 type veth peer name eth$x netns ns1 ip -net ns1 link set eth$x up ip -net ns2 link set veth$x up done ip -net ns1 -6 r a 2000::/64 nexthop via fe80::0 dev eth0 \ nexthop via fe80::1 dev eth1 nexthop via fe80::2 dev eth2 ip -net ns1 -6 r a 2000::/64 via fe80::42 dev eth0 metric 256 ip -net ns1 -6 r a 2000::/64 via fe80::43 dev eth0 metric 2048 echo "before replace, 3 routes" ip -net ns1 -6 r | grep -v '^fe80\|^ff00' echo ip -net ns1 -6 r c 2000::/64 nexthop via fe80::4 dev eth0 \ nexthop via fe80::5 dev eth1 nexthop via fe80::6 dev eth2 echo "after replace, only 2 routes, metric 2048 is gone" ip -net ns1 -6 r | grep -v '^fe80\|^ff00' Fixes: 27596472473a ("ipv6: fix ECMP route replacement") Signed-off-by: Sabrina Dubroca <sd@queasysnail.net> Acked-by: Nicolas Dichtel <nicolas.dichtel@6wind.com> Reviewed-by: Xin Long <lucien.xin@gmail.com> Reviewed-by: Michal Kubecek <mkubecek@suse.cz> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-03-13 12:28:09 +00:00
if (iter->rt6i_metric > rt->rt6i_metric)
break;
if (rt6_qualify_for_ecmp(iter)) {
*ins = iter->dst.rt6_next;
iter->rt6i_node = NULL;
fib6_purge_rt(iter, fn, info->nl_net);
ipv6: reset fn->rr_ptr when replacing route syzcaller reported the following use-after-free issue in rt6_select(): BUG: KASAN: use-after-free in rt6_select net/ipv6/route.c:755 [inline] at addr ffff8800bc6994e8 BUG: KASAN: use-after-free in ip6_pol_route.isra.46+0x1429/0x1470 net/ipv6/route.c:1084 at addr ffff8800bc6994e8 Read of size 4 by task syz-executor1/439628 CPU: 0 PID: 439628 Comm: syz-executor1 Not tainted 4.3.5+ #8 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 0000000000000000 ffff88018fe435b0 ffffffff81ca384d ffff8801d3588c00 ffff8800bc699380 ffff8800bc699500 dffffc0000000000 ffff8801d40a47c0 ffff88018fe435d8 ffffffff81735751 ffff88018fe43660 ffff8800bc699380 Call Trace: [<ffffffff81ca384d>] __dump_stack lib/dump_stack.c:15 [inline] [<ffffffff81ca384d>] dump_stack+0xc1/0x124 lib/dump_stack.c:51 sctp: [Deprecated]: syz-executor0 (pid 439615) Use of struct sctp_assoc_value in delayed_ack socket option. Use struct sctp_sack_info instead [<ffffffff81735751>] kasan_object_err+0x21/0x70 mm/kasan/report.c:158 [<ffffffff817359c4>] print_address_description mm/kasan/report.c:196 [inline] [<ffffffff817359c4>] kasan_report_error+0x1b4/0x4a0 mm/kasan/report.c:285 [<ffffffff81735d93>] kasan_report mm/kasan/report.c:305 [inline] [<ffffffff81735d93>] __asan_report_load4_noabort+0x43/0x50 mm/kasan/report.c:325 [<ffffffff82a28e39>] rt6_select net/ipv6/route.c:755 [inline] [<ffffffff82a28e39>] ip6_pol_route.isra.46+0x1429/0x1470 net/ipv6/route.c:1084 [<ffffffff82a28fb1>] ip6_pol_route_output+0x81/0xb0 net/ipv6/route.c:1203 [<ffffffff82ab0a50>] fib6_rule_action+0x1f0/0x680 net/ipv6/fib6_rules.c:95 [<ffffffff8265cbb6>] fib_rules_lookup+0x2a6/0x7a0 net/core/fib_rules.c:223 [<ffffffff82ab1430>] fib6_rule_lookup+0xd0/0x250 net/ipv6/fib6_rules.c:41 [<ffffffff82a22006>] ip6_route_output+0x1d6/0x2c0 net/ipv6/route.c:1224 [<ffffffff829e83d2>] ip6_dst_lookup_tail+0x4d2/0x890 net/ipv6/ip6_output.c:943 [<ffffffff829e889a>] ip6_dst_lookup_flow+0x9a/0x250 net/ipv6/ip6_output.c:1079 [<ffffffff82a9f7d8>] ip6_datagram_dst_update+0x538/0xd40 net/ipv6/datagram.c:91 [<ffffffff82aa0978>] __ip6_datagram_connect net/ipv6/datagram.c:251 [inline] [<ffffffff82aa0978>] ip6_datagram_connect+0x518/0xe50 net/ipv6/datagram.c:272 [<ffffffff82aa1313>] ip6_datagram_connect_v6_only+0x63/0x90 net/ipv6/datagram.c:284 [<ffffffff8292f790>] inet_dgram_connect+0x170/0x1f0 net/ipv4/af_inet.c:564 [<ffffffff82565547>] SYSC_connect+0x1a7/0x2f0 net/socket.c:1582 [<ffffffff8256a649>] SyS_connect+0x29/0x30 net/socket.c:1563 [<ffffffff82c72032>] entry_SYSCALL_64_fastpath+0x12/0x17 Object at ffff8800bc699380, in cache ip6_dst_cache size: 384 The root cause of it is that in fib6_add_rt2node(), when it replaces an existing route with the new one, it does not update fn->rr_ptr. This commit resets fn->rr_ptr to NULL when it points to a route which is replaced in fib6_add_rt2node(). Fixes: 27596472473a ("ipv6: fix ECMP route replacement") Signed-off-by: Wei Wang <weiwan@google.com> Acked-by: Eric Dumazet <edumazet@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-08-16 18:18:09 +00:00
if (fn->rr_ptr == iter)
fn->rr_ptr = NULL;
rt6_release(iter);
nsiblings--;
} else {
ins = &iter->dst.rt6_next;
}
iter = *ins;
}
WARN_ON(nsiblings != 0);
}
}
return 0;
}
static void fib6_start_gc(struct net *net, struct rt6_info *rt)
{
if (!timer_pending(&net->ipv6.ip6_fib_timer) &&
(rt->rt6i_flags & (RTF_EXPIRES | RTF_CACHE)))
mod_timer(&net->ipv6.ip6_fib_timer,
jiffies + net->ipv6.sysctl.ip6_rt_gc_interval);
}
void fib6_force_start_gc(struct net *net)
{
if (!timer_pending(&net->ipv6.ip6_fib_timer))
mod_timer(&net->ipv6.ip6_fib_timer,
jiffies + net->ipv6.sysctl.ip6_rt_gc_interval);
}
/*
* Add routing information to the routing tree.
* <destination addr>/<source addr>
* with source addr info in sub-trees
*/
int fib6_add(struct fib6_node *root, struct rt6_info *rt,
struct nl_info *info, struct mx6_config *mxc,
struct netlink_ext_ack *extack)
{
struct fib6_node *fn, *pn = NULL;
int err = -ENOMEM;
int allow_create = 1;
int replace_required = 0;
int sernum = fib6_new_sernum(info->nl_net);
if (WARN_ON_ONCE(!atomic_read(&rt->dst.__refcnt)))
return -EINVAL;
if (info->nlh) {
if (!(info->nlh->nlmsg_flags & NLM_F_CREATE))
allow_create = 0;
if (info->nlh->nlmsg_flags & NLM_F_REPLACE)
replace_required = 1;
}
if (!allow_create && !replace_required)
pr_warn("RTM_NEWROUTE with no NLM_F_CREATE or NLM_F_REPLACE\n");
fn = fib6_add_1(root, &rt->rt6i_dst.addr, rt->rt6i_dst.plen,
offsetof(struct rt6_info, rt6i_dst), allow_create,
replace_required, sernum, extack);
if (IS_ERR(fn)) {
err = PTR_ERR(fn);
fn = NULL;
goto out;
}
pn = fn;
#ifdef CONFIG_IPV6_SUBTREES
if (rt->rt6i_src.plen) {
struct fib6_node *sn;
if (!fn->subtree) {
struct fib6_node *sfn;
/*
* Create subtree.
*
* fn[main tree]
* |
* sfn[subtree root]
* \
* sn[new leaf node]
*/
/* Create subtree root node */
sfn = node_alloc();
if (!sfn)
ipv6: repair fib6 tree in failure case In fib6_add(), it is possible that fib6_add_1() picks an intermediate node and sets the node's fn->leaf to NULL in order to add this new route. However, if fib6_add_rt2node() fails to add the new route for some reason, fn->leaf will be left as NULL and could potentially cause crash when fn->leaf is accessed in fib6_locate(). This patch makes sure fib6_repair_tree() is called to properly repair fn->leaf in the above failure case. Here is the syzkaller reported general protection fault in fib6_locate: kasan: CONFIG_KASAN_INLINE enabled kasan: GPF could be caused by NULL-ptr deref or user memory access general protection fault: 0000 [#1] SMP KASAN Modules linked in: CPU: 0 PID: 40937 Comm: syz-executor3 Not tainted Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 task: ffff8801d7d64100 ti: ffff8801d01a0000 task.ti: ffff8801d01a0000 RIP: 0010:[<ffffffff82a3e0e1>] [<ffffffff82a3e0e1>] __ipv6_prefix_equal64_half include/net/ipv6.h:475 [inline] RIP: 0010:[<ffffffff82a3e0e1>] [<ffffffff82a3e0e1>] ipv6_prefix_equal include/net/ipv6.h:492 [inline] RIP: 0010:[<ffffffff82a3e0e1>] [<ffffffff82a3e0e1>] fib6_locate_1 net/ipv6/ip6_fib.c:1210 [inline] RIP: 0010:[<ffffffff82a3e0e1>] [<ffffffff82a3e0e1>] fib6_locate+0x281/0x3c0 net/ipv6/ip6_fib.c:1233 RSP: 0018:ffff8801d01a36a8 EFLAGS: 00010202 RAX: 0000000000000020 RBX: ffff8801bc790e00 RCX: ffffc90002983000 RDX: 0000000000001219 RSI: ffff8801d01a37a0 RDI: 0000000000000100 RBP: ffff8801d01a36f0 R08: 00000000000000ff R09: 0000000000000000 R10: 0000000000000003 R11: 0000000000000000 R12: 0000000000000001 R13: dffffc0000000000 R14: ffff8801d01a37a0 R15: 0000000000000000 FS: 00007f6afd68c700(0000) GS:ffff8801db400000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 00000000004c6340 CR3: 00000000ba41f000 CR4: 00000000001426f0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 Stack: ffff8801d01a37a8 ffff8801d01a3780 ffffed003a0346f5 0000000c82a23ea0 ffff8800b7bd7700 ffff8801d01a3780 ffff8800b6a1c940 ffffffff82a23ea0 ffff8801d01a3920 ffff8801d01a3748 ffffffff82a223d6 ffff8801d7d64988 Call Trace: [<ffffffff82a223d6>] ip6_route_del+0x106/0x570 net/ipv6/route.c:2109 [<ffffffff82a23f9d>] inet6_rtm_delroute+0xfd/0x100 net/ipv6/route.c:3075 [<ffffffff82621359>] rtnetlink_rcv_msg+0x549/0x7a0 net/core/rtnetlink.c:3450 [<ffffffff8274c1d1>] netlink_rcv_skb+0x141/0x370 net/netlink/af_netlink.c:2281 [<ffffffff82613ddf>] rtnetlink_rcv+0x2f/0x40 net/core/rtnetlink.c:3456 [<ffffffff8274ad38>] netlink_unicast_kernel net/netlink/af_netlink.c:1206 [inline] [<ffffffff8274ad38>] netlink_unicast+0x518/0x750 net/netlink/af_netlink.c:1232 [<ffffffff8274b83e>] netlink_sendmsg+0x8ce/0xc30 net/netlink/af_netlink.c:1778 [<ffffffff82564aff>] sock_sendmsg_nosec net/socket.c:609 [inline] [<ffffffff82564aff>] sock_sendmsg+0xcf/0x110 net/socket.c:619 [<ffffffff82564d62>] sock_write_iter+0x222/0x3a0 net/socket.c:834 [<ffffffff8178523d>] new_sync_write+0x1dd/0x2b0 fs/read_write.c:478 [<ffffffff817853f4>] __vfs_write+0xe4/0x110 fs/read_write.c:491 [<ffffffff81786c38>] vfs_write+0x178/0x4b0 fs/read_write.c:538 [<ffffffff817892a9>] SYSC_write fs/read_write.c:585 [inline] [<ffffffff817892a9>] SyS_write+0xd9/0x1b0 fs/read_write.c:577 [<ffffffff82c71e32>] entry_SYSCALL_64_fastpath+0x12/0x17 Note: there is no "Fixes" tag as this seems to be a bug introduced very early. Signed-off-by: Wei Wang <weiwan@google.com> Acked-by: Eric Dumazet <edumazet@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-08-19 00:14:49 +00:00
goto failure;
sfn->leaf = info->nl_net->ipv6.ip6_null_entry;
atomic_inc(&info->nl_net->ipv6.ip6_null_entry->rt6i_ref);
sfn->fn_flags = RTN_ROOT;
sfn->fn_sernum = sernum;
/* Now add the first leaf node to new subtree */
sn = fib6_add_1(sfn, &rt->rt6i_src.addr,
rt->rt6i_src.plen,
offsetof(struct rt6_info, rt6i_src),
allow_create, replace_required, sernum,
extack);
if (IS_ERR(sn)) {
/* If it is failed, discard just allocated
ipv6: repair fib6 tree in failure case In fib6_add(), it is possible that fib6_add_1() picks an intermediate node and sets the node's fn->leaf to NULL in order to add this new route. However, if fib6_add_rt2node() fails to add the new route for some reason, fn->leaf will be left as NULL and could potentially cause crash when fn->leaf is accessed in fib6_locate(). This patch makes sure fib6_repair_tree() is called to properly repair fn->leaf in the above failure case. Here is the syzkaller reported general protection fault in fib6_locate: kasan: CONFIG_KASAN_INLINE enabled kasan: GPF could be caused by NULL-ptr deref or user memory access general protection fault: 0000 [#1] SMP KASAN Modules linked in: CPU: 0 PID: 40937 Comm: syz-executor3 Not tainted Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 task: ffff8801d7d64100 ti: ffff8801d01a0000 task.ti: ffff8801d01a0000 RIP: 0010:[<ffffffff82a3e0e1>] [<ffffffff82a3e0e1>] __ipv6_prefix_equal64_half include/net/ipv6.h:475 [inline] RIP: 0010:[<ffffffff82a3e0e1>] [<ffffffff82a3e0e1>] ipv6_prefix_equal include/net/ipv6.h:492 [inline] RIP: 0010:[<ffffffff82a3e0e1>] [<ffffffff82a3e0e1>] fib6_locate_1 net/ipv6/ip6_fib.c:1210 [inline] RIP: 0010:[<ffffffff82a3e0e1>] [<ffffffff82a3e0e1>] fib6_locate+0x281/0x3c0 net/ipv6/ip6_fib.c:1233 RSP: 0018:ffff8801d01a36a8 EFLAGS: 00010202 RAX: 0000000000000020 RBX: ffff8801bc790e00 RCX: ffffc90002983000 RDX: 0000000000001219 RSI: ffff8801d01a37a0 RDI: 0000000000000100 RBP: ffff8801d01a36f0 R08: 00000000000000ff R09: 0000000000000000 R10: 0000000000000003 R11: 0000000000000000 R12: 0000000000000001 R13: dffffc0000000000 R14: ffff8801d01a37a0 R15: 0000000000000000 FS: 00007f6afd68c700(0000) GS:ffff8801db400000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 00000000004c6340 CR3: 00000000ba41f000 CR4: 00000000001426f0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 Stack: ffff8801d01a37a8 ffff8801d01a3780 ffffed003a0346f5 0000000c82a23ea0 ffff8800b7bd7700 ffff8801d01a3780 ffff8800b6a1c940 ffffffff82a23ea0 ffff8801d01a3920 ffff8801d01a3748 ffffffff82a223d6 ffff8801d7d64988 Call Trace: [<ffffffff82a223d6>] ip6_route_del+0x106/0x570 net/ipv6/route.c:2109 [<ffffffff82a23f9d>] inet6_rtm_delroute+0xfd/0x100 net/ipv6/route.c:3075 [<ffffffff82621359>] rtnetlink_rcv_msg+0x549/0x7a0 net/core/rtnetlink.c:3450 [<ffffffff8274c1d1>] netlink_rcv_skb+0x141/0x370 net/netlink/af_netlink.c:2281 [<ffffffff82613ddf>] rtnetlink_rcv+0x2f/0x40 net/core/rtnetlink.c:3456 [<ffffffff8274ad38>] netlink_unicast_kernel net/netlink/af_netlink.c:1206 [inline] [<ffffffff8274ad38>] netlink_unicast+0x518/0x750 net/netlink/af_netlink.c:1232 [<ffffffff8274b83e>] netlink_sendmsg+0x8ce/0xc30 net/netlink/af_netlink.c:1778 [<ffffffff82564aff>] sock_sendmsg_nosec net/socket.c:609 [inline] [<ffffffff82564aff>] sock_sendmsg+0xcf/0x110 net/socket.c:619 [<ffffffff82564d62>] sock_write_iter+0x222/0x3a0 net/socket.c:834 [<ffffffff8178523d>] new_sync_write+0x1dd/0x2b0 fs/read_write.c:478 [<ffffffff817853f4>] __vfs_write+0xe4/0x110 fs/read_write.c:491 [<ffffffff81786c38>] vfs_write+0x178/0x4b0 fs/read_write.c:538 [<ffffffff817892a9>] SYSC_write fs/read_write.c:585 [inline] [<ffffffff817892a9>] SyS_write+0xd9/0x1b0 fs/read_write.c:577 [<ffffffff82c71e32>] entry_SYSCALL_64_fastpath+0x12/0x17 Note: there is no "Fixes" tag as this seems to be a bug introduced very early. Signed-off-by: Wei Wang <weiwan@google.com> Acked-by: Eric Dumazet <edumazet@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-08-19 00:14:49 +00:00
root, and then (in failure) stale node
in main tree.
*/
node_free_immediate(sfn);
err = PTR_ERR(sn);
ipv6: repair fib6 tree in failure case In fib6_add(), it is possible that fib6_add_1() picks an intermediate node and sets the node's fn->leaf to NULL in order to add this new route. However, if fib6_add_rt2node() fails to add the new route for some reason, fn->leaf will be left as NULL and could potentially cause crash when fn->leaf is accessed in fib6_locate(). This patch makes sure fib6_repair_tree() is called to properly repair fn->leaf in the above failure case. Here is the syzkaller reported general protection fault in fib6_locate: kasan: CONFIG_KASAN_INLINE enabled kasan: GPF could be caused by NULL-ptr deref or user memory access general protection fault: 0000 [#1] SMP KASAN Modules linked in: CPU: 0 PID: 40937 Comm: syz-executor3 Not tainted Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 task: ffff8801d7d64100 ti: ffff8801d01a0000 task.ti: ffff8801d01a0000 RIP: 0010:[<ffffffff82a3e0e1>] [<ffffffff82a3e0e1>] __ipv6_prefix_equal64_half include/net/ipv6.h:475 [inline] RIP: 0010:[<ffffffff82a3e0e1>] [<ffffffff82a3e0e1>] ipv6_prefix_equal include/net/ipv6.h:492 [inline] RIP: 0010:[<ffffffff82a3e0e1>] [<ffffffff82a3e0e1>] fib6_locate_1 net/ipv6/ip6_fib.c:1210 [inline] RIP: 0010:[<ffffffff82a3e0e1>] [<ffffffff82a3e0e1>] fib6_locate+0x281/0x3c0 net/ipv6/ip6_fib.c:1233 RSP: 0018:ffff8801d01a36a8 EFLAGS: 00010202 RAX: 0000000000000020 RBX: ffff8801bc790e00 RCX: ffffc90002983000 RDX: 0000000000001219 RSI: ffff8801d01a37a0 RDI: 0000000000000100 RBP: ffff8801d01a36f0 R08: 00000000000000ff R09: 0000000000000000 R10: 0000000000000003 R11: 0000000000000000 R12: 0000000000000001 R13: dffffc0000000000 R14: ffff8801d01a37a0 R15: 0000000000000000 FS: 00007f6afd68c700(0000) GS:ffff8801db400000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 00000000004c6340 CR3: 00000000ba41f000 CR4: 00000000001426f0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 Stack: ffff8801d01a37a8 ffff8801d01a3780 ffffed003a0346f5 0000000c82a23ea0 ffff8800b7bd7700 ffff8801d01a3780 ffff8800b6a1c940 ffffffff82a23ea0 ffff8801d01a3920 ffff8801d01a3748 ffffffff82a223d6 ffff8801d7d64988 Call Trace: [<ffffffff82a223d6>] ip6_route_del+0x106/0x570 net/ipv6/route.c:2109 [<ffffffff82a23f9d>] inet6_rtm_delroute+0xfd/0x100 net/ipv6/route.c:3075 [<ffffffff82621359>] rtnetlink_rcv_msg+0x549/0x7a0 net/core/rtnetlink.c:3450 [<ffffffff8274c1d1>] netlink_rcv_skb+0x141/0x370 net/netlink/af_netlink.c:2281 [<ffffffff82613ddf>] rtnetlink_rcv+0x2f/0x40 net/core/rtnetlink.c:3456 [<ffffffff8274ad38>] netlink_unicast_kernel net/netlink/af_netlink.c:1206 [inline] [<ffffffff8274ad38>] netlink_unicast+0x518/0x750 net/netlink/af_netlink.c:1232 [<ffffffff8274b83e>] netlink_sendmsg+0x8ce/0xc30 net/netlink/af_netlink.c:1778 [<ffffffff82564aff>] sock_sendmsg_nosec net/socket.c:609 [inline] [<ffffffff82564aff>] sock_sendmsg+0xcf/0x110 net/socket.c:619 [<ffffffff82564d62>] sock_write_iter+0x222/0x3a0 net/socket.c:834 [<ffffffff8178523d>] new_sync_write+0x1dd/0x2b0 fs/read_write.c:478 [<ffffffff817853f4>] __vfs_write+0xe4/0x110 fs/read_write.c:491 [<ffffffff81786c38>] vfs_write+0x178/0x4b0 fs/read_write.c:538 [<ffffffff817892a9>] SYSC_write fs/read_write.c:585 [inline] [<ffffffff817892a9>] SyS_write+0xd9/0x1b0 fs/read_write.c:577 [<ffffffff82c71e32>] entry_SYSCALL_64_fastpath+0x12/0x17 Note: there is no "Fixes" tag as this seems to be a bug introduced very early. Signed-off-by: Wei Wang <weiwan@google.com> Acked-by: Eric Dumazet <edumazet@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-08-19 00:14:49 +00:00
goto failure;
}
/* Now link new subtree to main tree */
sfn->parent = fn;
fn->subtree = sfn;
} else {
sn = fib6_add_1(fn->subtree, &rt->rt6i_src.addr,
rt->rt6i_src.plen,
offsetof(struct rt6_info, rt6i_src),
allow_create, replace_required, sernum,
extack);
if (IS_ERR(sn)) {
err = PTR_ERR(sn);
ipv6: repair fib6 tree in failure case In fib6_add(), it is possible that fib6_add_1() picks an intermediate node and sets the node's fn->leaf to NULL in order to add this new route. However, if fib6_add_rt2node() fails to add the new route for some reason, fn->leaf will be left as NULL and could potentially cause crash when fn->leaf is accessed in fib6_locate(). This patch makes sure fib6_repair_tree() is called to properly repair fn->leaf in the above failure case. Here is the syzkaller reported general protection fault in fib6_locate: kasan: CONFIG_KASAN_INLINE enabled kasan: GPF could be caused by NULL-ptr deref or user memory access general protection fault: 0000 [#1] SMP KASAN Modules linked in: CPU: 0 PID: 40937 Comm: syz-executor3 Not tainted Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 task: ffff8801d7d64100 ti: ffff8801d01a0000 task.ti: ffff8801d01a0000 RIP: 0010:[<ffffffff82a3e0e1>] [<ffffffff82a3e0e1>] __ipv6_prefix_equal64_half include/net/ipv6.h:475 [inline] RIP: 0010:[<ffffffff82a3e0e1>] [<ffffffff82a3e0e1>] ipv6_prefix_equal include/net/ipv6.h:492 [inline] RIP: 0010:[<ffffffff82a3e0e1>] [<ffffffff82a3e0e1>] fib6_locate_1 net/ipv6/ip6_fib.c:1210 [inline] RIP: 0010:[<ffffffff82a3e0e1>] [<ffffffff82a3e0e1>] fib6_locate+0x281/0x3c0 net/ipv6/ip6_fib.c:1233 RSP: 0018:ffff8801d01a36a8 EFLAGS: 00010202 RAX: 0000000000000020 RBX: ffff8801bc790e00 RCX: ffffc90002983000 RDX: 0000000000001219 RSI: ffff8801d01a37a0 RDI: 0000000000000100 RBP: ffff8801d01a36f0 R08: 00000000000000ff R09: 0000000000000000 R10: 0000000000000003 R11: 0000000000000000 R12: 0000000000000001 R13: dffffc0000000000 R14: ffff8801d01a37a0 R15: 0000000000000000 FS: 00007f6afd68c700(0000) GS:ffff8801db400000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 00000000004c6340 CR3: 00000000ba41f000 CR4: 00000000001426f0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 Stack: ffff8801d01a37a8 ffff8801d01a3780 ffffed003a0346f5 0000000c82a23ea0 ffff8800b7bd7700 ffff8801d01a3780 ffff8800b6a1c940 ffffffff82a23ea0 ffff8801d01a3920 ffff8801d01a3748 ffffffff82a223d6 ffff8801d7d64988 Call Trace: [<ffffffff82a223d6>] ip6_route_del+0x106/0x570 net/ipv6/route.c:2109 [<ffffffff82a23f9d>] inet6_rtm_delroute+0xfd/0x100 net/ipv6/route.c:3075 [<ffffffff82621359>] rtnetlink_rcv_msg+0x549/0x7a0 net/core/rtnetlink.c:3450 [<ffffffff8274c1d1>] netlink_rcv_skb+0x141/0x370 net/netlink/af_netlink.c:2281 [<ffffffff82613ddf>] rtnetlink_rcv+0x2f/0x40 net/core/rtnetlink.c:3456 [<ffffffff8274ad38>] netlink_unicast_kernel net/netlink/af_netlink.c:1206 [inline] [<ffffffff8274ad38>] netlink_unicast+0x518/0x750 net/netlink/af_netlink.c:1232 [<ffffffff8274b83e>] netlink_sendmsg+0x8ce/0xc30 net/netlink/af_netlink.c:1778 [<ffffffff82564aff>] sock_sendmsg_nosec net/socket.c:609 [inline] [<ffffffff82564aff>] sock_sendmsg+0xcf/0x110 net/socket.c:619 [<ffffffff82564d62>] sock_write_iter+0x222/0x3a0 net/socket.c:834 [<ffffffff8178523d>] new_sync_write+0x1dd/0x2b0 fs/read_write.c:478 [<ffffffff817853f4>] __vfs_write+0xe4/0x110 fs/read_write.c:491 [<ffffffff81786c38>] vfs_write+0x178/0x4b0 fs/read_write.c:538 [<ffffffff817892a9>] SYSC_write fs/read_write.c:585 [inline] [<ffffffff817892a9>] SyS_write+0xd9/0x1b0 fs/read_write.c:577 [<ffffffff82c71e32>] entry_SYSCALL_64_fastpath+0x12/0x17 Note: there is no "Fixes" tag as this seems to be a bug introduced very early. Signed-off-by: Wei Wang <weiwan@google.com> Acked-by: Eric Dumazet <edumazet@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-08-19 00:14:49 +00:00
goto failure;
}
}
if (!fn->leaf) {
fn->leaf = rt;
atomic_inc(&rt->rt6i_ref);
}
fn = sn;
}
#endif
err = fib6_add_rt2node(fn, rt, info, mxc);
if (!err) {
fib6_start_gc(info->nl_net, rt);
if (!(rt->rt6i_flags & RTF_CACHE))
fib6_prune_clones(info->nl_net, pn);
}
out:
if (err) {
#ifdef CONFIG_IPV6_SUBTREES
/*
* If fib6_add_1 has cleared the old leaf pointer in the
* super-tree leaf node we have to find a new one for it.
*/
if (pn != fn && pn->leaf == rt) {
pn->leaf = NULL;
atomic_dec(&rt->rt6i_ref);
}
if (pn != fn && !pn->leaf && !(pn->fn_flags & RTN_RTINFO)) {
pn->leaf = fib6_find_prefix(info->nl_net, pn);
#if RT6_DEBUG >= 2
if (!pn->leaf) {
WARN_ON(pn->leaf == NULL);
pn->leaf = info->nl_net->ipv6.ip6_null_entry;
}
#endif
atomic_inc(&pn->leaf->rt6i_ref);
}
#endif
ipv6: repair fib6 tree in failure case In fib6_add(), it is possible that fib6_add_1() picks an intermediate node and sets the node's fn->leaf to NULL in order to add this new route. However, if fib6_add_rt2node() fails to add the new route for some reason, fn->leaf will be left as NULL and could potentially cause crash when fn->leaf is accessed in fib6_locate(). This patch makes sure fib6_repair_tree() is called to properly repair fn->leaf in the above failure case. Here is the syzkaller reported general protection fault in fib6_locate: kasan: CONFIG_KASAN_INLINE enabled kasan: GPF could be caused by NULL-ptr deref or user memory access general protection fault: 0000 [#1] SMP KASAN Modules linked in: CPU: 0 PID: 40937 Comm: syz-executor3 Not tainted Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 task: ffff8801d7d64100 ti: ffff8801d01a0000 task.ti: ffff8801d01a0000 RIP: 0010:[<ffffffff82a3e0e1>] [<ffffffff82a3e0e1>] __ipv6_prefix_equal64_half include/net/ipv6.h:475 [inline] RIP: 0010:[<ffffffff82a3e0e1>] [<ffffffff82a3e0e1>] ipv6_prefix_equal include/net/ipv6.h:492 [inline] RIP: 0010:[<ffffffff82a3e0e1>] [<ffffffff82a3e0e1>] fib6_locate_1 net/ipv6/ip6_fib.c:1210 [inline] RIP: 0010:[<ffffffff82a3e0e1>] [<ffffffff82a3e0e1>] fib6_locate+0x281/0x3c0 net/ipv6/ip6_fib.c:1233 RSP: 0018:ffff8801d01a36a8 EFLAGS: 00010202 RAX: 0000000000000020 RBX: ffff8801bc790e00 RCX: ffffc90002983000 RDX: 0000000000001219 RSI: ffff8801d01a37a0 RDI: 0000000000000100 RBP: ffff8801d01a36f0 R08: 00000000000000ff R09: 0000000000000000 R10: 0000000000000003 R11: 0000000000000000 R12: 0000000000000001 R13: dffffc0000000000 R14: ffff8801d01a37a0 R15: 0000000000000000 FS: 00007f6afd68c700(0000) GS:ffff8801db400000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 00000000004c6340 CR3: 00000000ba41f000 CR4: 00000000001426f0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 Stack: ffff8801d01a37a8 ffff8801d01a3780 ffffed003a0346f5 0000000c82a23ea0 ffff8800b7bd7700 ffff8801d01a3780 ffff8800b6a1c940 ffffffff82a23ea0 ffff8801d01a3920 ffff8801d01a3748 ffffffff82a223d6 ffff8801d7d64988 Call Trace: [<ffffffff82a223d6>] ip6_route_del+0x106/0x570 net/ipv6/route.c:2109 [<ffffffff82a23f9d>] inet6_rtm_delroute+0xfd/0x100 net/ipv6/route.c:3075 [<ffffffff82621359>] rtnetlink_rcv_msg+0x549/0x7a0 net/core/rtnetlink.c:3450 [<ffffffff8274c1d1>] netlink_rcv_skb+0x141/0x370 net/netlink/af_netlink.c:2281 [<ffffffff82613ddf>] rtnetlink_rcv+0x2f/0x40 net/core/rtnetlink.c:3456 [<ffffffff8274ad38>] netlink_unicast_kernel net/netlink/af_netlink.c:1206 [inline] [<ffffffff8274ad38>] netlink_unicast+0x518/0x750 net/netlink/af_netlink.c:1232 [<ffffffff8274b83e>] netlink_sendmsg+0x8ce/0xc30 net/netlink/af_netlink.c:1778 [<ffffffff82564aff>] sock_sendmsg_nosec net/socket.c:609 [inline] [<ffffffff82564aff>] sock_sendmsg+0xcf/0x110 net/socket.c:619 [<ffffffff82564d62>] sock_write_iter+0x222/0x3a0 net/socket.c:834 [<ffffffff8178523d>] new_sync_write+0x1dd/0x2b0 fs/read_write.c:478 [<ffffffff817853f4>] __vfs_write+0xe4/0x110 fs/read_write.c:491 [<ffffffff81786c38>] vfs_write+0x178/0x4b0 fs/read_write.c:538 [<ffffffff817892a9>] SYSC_write fs/read_write.c:585 [inline] [<ffffffff817892a9>] SyS_write+0xd9/0x1b0 fs/read_write.c:577 [<ffffffff82c71e32>] entry_SYSCALL_64_fastpath+0x12/0x17 Note: there is no "Fixes" tag as this seems to be a bug introduced very early. Signed-off-by: Wei Wang <weiwan@google.com> Acked-by: Eric Dumazet <edumazet@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-08-19 00:14:49 +00:00
goto failure;
}
return err;
ipv6: repair fib6 tree in failure case In fib6_add(), it is possible that fib6_add_1() picks an intermediate node and sets the node's fn->leaf to NULL in order to add this new route. However, if fib6_add_rt2node() fails to add the new route for some reason, fn->leaf will be left as NULL and could potentially cause crash when fn->leaf is accessed in fib6_locate(). This patch makes sure fib6_repair_tree() is called to properly repair fn->leaf in the above failure case. Here is the syzkaller reported general protection fault in fib6_locate: kasan: CONFIG_KASAN_INLINE enabled kasan: GPF could be caused by NULL-ptr deref or user memory access general protection fault: 0000 [#1] SMP KASAN Modules linked in: CPU: 0 PID: 40937 Comm: syz-executor3 Not tainted Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 task: ffff8801d7d64100 ti: ffff8801d01a0000 task.ti: ffff8801d01a0000 RIP: 0010:[<ffffffff82a3e0e1>] [<ffffffff82a3e0e1>] __ipv6_prefix_equal64_half include/net/ipv6.h:475 [inline] RIP: 0010:[<ffffffff82a3e0e1>] [<ffffffff82a3e0e1>] ipv6_prefix_equal include/net/ipv6.h:492 [inline] RIP: 0010:[<ffffffff82a3e0e1>] [<ffffffff82a3e0e1>] fib6_locate_1 net/ipv6/ip6_fib.c:1210 [inline] RIP: 0010:[<ffffffff82a3e0e1>] [<ffffffff82a3e0e1>] fib6_locate+0x281/0x3c0 net/ipv6/ip6_fib.c:1233 RSP: 0018:ffff8801d01a36a8 EFLAGS: 00010202 RAX: 0000000000000020 RBX: ffff8801bc790e00 RCX: ffffc90002983000 RDX: 0000000000001219 RSI: ffff8801d01a37a0 RDI: 0000000000000100 RBP: ffff8801d01a36f0 R08: 00000000000000ff R09: 0000000000000000 R10: 0000000000000003 R11: 0000000000000000 R12: 0000000000000001 R13: dffffc0000000000 R14: ffff8801d01a37a0 R15: 0000000000000000 FS: 00007f6afd68c700(0000) GS:ffff8801db400000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 00000000004c6340 CR3: 00000000ba41f000 CR4: 00000000001426f0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 Stack: ffff8801d01a37a8 ffff8801d01a3780 ffffed003a0346f5 0000000c82a23ea0 ffff8800b7bd7700 ffff8801d01a3780 ffff8800b6a1c940 ffffffff82a23ea0 ffff8801d01a3920 ffff8801d01a3748 ffffffff82a223d6 ffff8801d7d64988 Call Trace: [<ffffffff82a223d6>] ip6_route_del+0x106/0x570 net/ipv6/route.c:2109 [<ffffffff82a23f9d>] inet6_rtm_delroute+0xfd/0x100 net/ipv6/route.c:3075 [<ffffffff82621359>] rtnetlink_rcv_msg+0x549/0x7a0 net/core/rtnetlink.c:3450 [<ffffffff8274c1d1>] netlink_rcv_skb+0x141/0x370 net/netlink/af_netlink.c:2281 [<ffffffff82613ddf>] rtnetlink_rcv+0x2f/0x40 net/core/rtnetlink.c:3456 [<ffffffff8274ad38>] netlink_unicast_kernel net/netlink/af_netlink.c:1206 [inline] [<ffffffff8274ad38>] netlink_unicast+0x518/0x750 net/netlink/af_netlink.c:1232 [<ffffffff8274b83e>] netlink_sendmsg+0x8ce/0xc30 net/netlink/af_netlink.c:1778 [<ffffffff82564aff>] sock_sendmsg_nosec net/socket.c:609 [inline] [<ffffffff82564aff>] sock_sendmsg+0xcf/0x110 net/socket.c:619 [<ffffffff82564d62>] sock_write_iter+0x222/0x3a0 net/socket.c:834 [<ffffffff8178523d>] new_sync_write+0x1dd/0x2b0 fs/read_write.c:478 [<ffffffff817853f4>] __vfs_write+0xe4/0x110 fs/read_write.c:491 [<ffffffff81786c38>] vfs_write+0x178/0x4b0 fs/read_write.c:538 [<ffffffff817892a9>] SYSC_write fs/read_write.c:585 [inline] [<ffffffff817892a9>] SyS_write+0xd9/0x1b0 fs/read_write.c:577 [<ffffffff82c71e32>] entry_SYSCALL_64_fastpath+0x12/0x17 Note: there is no "Fixes" tag as this seems to be a bug introduced very early. Signed-off-by: Wei Wang <weiwan@google.com> Acked-by: Eric Dumazet <edumazet@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-08-19 00:14:49 +00:00
failure:
/* fn->leaf could be NULL if fn is an intermediate node and we
* failed to add the new route to it in both subtree creation
* failure and fib6_add_rt2node() failure case.
* In both cases, fib6_repair_tree() should be called to fix
* fn->leaf.
*/
if (fn && !(fn->fn_flags & (RTN_RTINFO|RTN_ROOT)))
fib6_repair_tree(info->nl_net, fn);
/* Always release dst as dst->__refcnt is guaranteed
* to be taken before entering this function
*/
dst_release_immediate(&rt->dst);
return err;
}
/*
* Routing tree lookup
*
*/
struct lookup_args {
int offset; /* key offset on rt6_info */
const struct in6_addr *addr; /* search key */
};
static struct fib6_node *fib6_lookup_1(struct fib6_node *root,
struct lookup_args *args)
{
struct fib6_node *fn;
__be32 dir;
if (unlikely(args->offset == 0))
return NULL;
/*
* Descend on a tree
*/
fn = root;
for (;;) {
struct fib6_node *next;
dir = addr_bit_set(args->addr, fn->fn_bit);
next = dir ? fn->right : fn->left;
if (next) {
fn = next;
continue;
}
break;
}
while (fn) {
if (FIB6_SUBTREE(fn) || fn->fn_flags & RTN_RTINFO) {
struct rt6key *key;
key = (struct rt6key *) ((u8 *) fn->leaf +
args->offset);
if (ipv6_prefix_equal(&key->addr, args->addr, key->plen)) {
#ifdef CONFIG_IPV6_SUBTREES
if (fn->subtree) {
struct fib6_node *sfn;
sfn = fib6_lookup_1(fn->subtree,
args + 1);
if (!sfn)
goto backtrack;
fn = sfn;
}
#endif
if (fn->fn_flags & RTN_RTINFO)
return fn;
}
}
#ifdef CONFIG_IPV6_SUBTREES
backtrack:
#endif
if (fn->fn_flags & RTN_ROOT)
break;
fn = fn->parent;
}
return NULL;
}
struct fib6_node *fib6_lookup(struct fib6_node *root, const struct in6_addr *daddr,
const struct in6_addr *saddr)
{
struct fib6_node *fn;
struct lookup_args args[] = {
{
.offset = offsetof(struct rt6_info, rt6i_dst),
.addr = daddr,
},
#ifdef CONFIG_IPV6_SUBTREES
{
.offset = offsetof(struct rt6_info, rt6i_src),
.addr = saddr,
},
#endif
{
.offset = 0, /* sentinel */
}
};
fn = fib6_lookup_1(root, daddr ? args : args + 1);
if (!fn || fn->fn_flags & RTN_TL_ROOT)
fn = root;
return fn;
}
/*
* Get node with specified destination prefix (and source prefix,
* if subtrees are used)
*/
static struct fib6_node *fib6_locate_1(struct fib6_node *root,
const struct in6_addr *addr,
int plen, int offset)
{
struct fib6_node *fn;
for (fn = root; fn ; ) {
struct rt6key *key = (struct rt6key *)((u8 *)fn->leaf + offset);
/*
* Prefix match
*/
if (plen < fn->fn_bit ||
!ipv6_prefix_equal(&key->addr, addr, fn->fn_bit))
return NULL;
if (plen == fn->fn_bit)
return fn;
/*
* We have more bits to go
*/
if (addr_bit_set(addr, fn->fn_bit))
fn = fn->right;
else
fn = fn->left;
}
return NULL;
}
struct fib6_node *fib6_locate(struct fib6_node *root,
const struct in6_addr *daddr, int dst_len,
const struct in6_addr *saddr, int src_len)
{
struct fib6_node *fn;
fn = fib6_locate_1(root, daddr, dst_len,
offsetof(struct rt6_info, rt6i_dst));
#ifdef CONFIG_IPV6_SUBTREES
if (src_len) {
WARN_ON(saddr == NULL);
if (fn && fn->subtree)
fn = fib6_locate_1(fn->subtree, saddr, src_len,
offsetof(struct rt6_info, rt6i_src));
}
#endif
if (fn && fn->fn_flags & RTN_RTINFO)
return fn;
return NULL;
}
/*
* Deletion
*
*/
static struct rt6_info *fib6_find_prefix(struct net *net, struct fib6_node *fn)
{
if (fn->fn_flags & RTN_ROOT)
return net->ipv6.ip6_null_entry;
while (fn) {
if (fn->left)
return fn->left->leaf;
if (fn->right)
return fn->right->leaf;
fn = FIB6_SUBTREE(fn);
}
return NULL;
}
/*
* Called to trim the tree of intermediate nodes when possible. "fn"
* is the node we want to try and remove.
*/
static struct fib6_node *fib6_repair_tree(struct net *net,
struct fib6_node *fn)
{
int children;
int nstate;
struct fib6_node *child, *pn;
struct fib6_walker *w;
int iter = 0;
for (;;) {
RT6_TRACE("fixing tree: plen=%d iter=%d\n", fn->fn_bit, iter);
iter++;
WARN_ON(fn->fn_flags & RTN_RTINFO);
WARN_ON(fn->fn_flags & RTN_TL_ROOT);
WARN_ON(fn->leaf);
children = 0;
child = NULL;
if (fn->right)
child = fn->right, children |= 1;
if (fn->left)
child = fn->left, children |= 2;
if (children == 3 || FIB6_SUBTREE(fn)
#ifdef CONFIG_IPV6_SUBTREES
/* Subtree root (i.e. fn) may have one child */
|| (children && fn->fn_flags & RTN_ROOT)
#endif
) {
fn->leaf = fib6_find_prefix(net, fn);
#if RT6_DEBUG >= 2
if (!fn->leaf) {
WARN_ON(!fn->leaf);
fn->leaf = net->ipv6.ip6_null_entry;
}
#endif
atomic_inc(&fn->leaf->rt6i_ref);
return fn->parent;
}
pn = fn->parent;
#ifdef CONFIG_IPV6_SUBTREES
if (FIB6_SUBTREE(pn) == fn) {
WARN_ON(!(fn->fn_flags & RTN_ROOT));
FIB6_SUBTREE(pn) = NULL;
nstate = FWS_L;
} else {
WARN_ON(fn->fn_flags & RTN_ROOT);
#endif
if (pn->right == fn)
pn->right = child;
else if (pn->left == fn)
pn->left = child;
#if RT6_DEBUG >= 2
else
WARN_ON(1);
#endif
if (child)
child->parent = pn;
nstate = FWS_R;
#ifdef CONFIG_IPV6_SUBTREES
}
#endif
read_lock(&net->ipv6.fib6_walker_lock);
FOR_WALKERS(net, w) {
if (!child) {
if (w->root == fn) {
w->root = w->node = NULL;
RT6_TRACE("W %p adjusted by delroot 1\n", w);
} else if (w->node == fn) {
RT6_TRACE("W %p adjusted by delnode 1, s=%d/%d\n", w, w->state, nstate);
w->node = pn;
w->state = nstate;
}
} else {
if (w->root == fn) {
w->root = child;
RT6_TRACE("W %p adjusted by delroot 2\n", w);
}
if (w->node == fn) {
w->node = child;
if (children&2) {
RT6_TRACE("W %p adjusted by delnode 2, s=%d\n", w, w->state);
w->state = w->state >= FWS_R ? FWS_U : FWS_INIT;
} else {
RT6_TRACE("W %p adjusted by delnode 2, s=%d\n", w, w->state);
w->state = w->state >= FWS_C ? FWS_U : FWS_INIT;
}
}
}
}
read_unlock(&net->ipv6.fib6_walker_lock);
node_free(fn);
if (pn->fn_flags & RTN_RTINFO || FIB6_SUBTREE(pn))
return pn;
rt6_release(pn->leaf);
pn->leaf = NULL;
fn = pn;
}
}
static void fib6_del_route(struct fib6_node *fn, struct rt6_info **rtp,
struct nl_info *info)
{
struct fib6_walker *w;
struct rt6_info *rt = *rtp;
struct net *net = info->nl_net;
RT6_TRACE("fib6_del_route\n");
/* Unlink it */
*rtp = rt->dst.rt6_next;
rt->rt6i_node = NULL;
net->ipv6.rt6_stats->fib_rt_entries--;
net->ipv6.rt6_stats->fib_discarded_routes++;
[IPV6]: Fix routing round-robin locking. As per RFC2461, section 6.3.6, item #2, when no routers on the matching list are known to be reachable or probably reachable we do round robin on those available routes so that we make sure to probe as many of them as possible to detect when one becomes reachable faster. Each routing table has a rwlock protecting the tree and the linked list of routes at each leaf. The round robin code executes during lookup and thus with the rwlock taken as a reader. A small local spinlock tries to provide protection but this does not work at all for two reasons: 1) The round-robin list manipulation, as coded, goes like this (with read lock held): walk routes finding head and tail spin_lock(); rotate list using head and tail spin_unlock(); While one thread is rotating the list, another thread can end up with stale values of head and tail and then proceed to corrupt the list when it gets the lock. This ends up causing the OOPS in fib6_add() later onthat many people have been hitting. 2) All the other code paths that run with the rwlock held as a reader do not expect the list to change on them, they expect it to remain completely fixed while they hold the lock in that way. So, simply stated, it is impossible to implement this correctly using a manipulation of the list without violating the rwlock locking semantics. Reimplement using a per-fib6_node round-robin pointer. This way we don't need to manipulate the list at all, and since the round-robin pointer can only ever point to real existing entries we don't need to perform any locking on the changing of the round-robin pointer itself. We only need to reset the round-robin pointer to NULL when the entry it is pointing to is removed. The idea is from Thomas Graf and it is very similar to how this was implemented before the advanced router selection code when in. Signed-off-by: David S. Miller <davem@davemloft.net>
2007-03-25 03:36:25 +00:00
/* Reset round-robin state, if necessary */
if (fn->rr_ptr == rt)
fn->rr_ptr = NULL;
/* Remove this entry from other siblings */
if (rt->rt6i_nsiblings) {
struct rt6_info *sibling, *next_sibling;
list_for_each_entry_safe(sibling, next_sibling,
&rt->rt6i_siblings, rt6i_siblings)
sibling->rt6i_nsiblings--;
rt->rt6i_nsiblings = 0;
list_del_init(&rt->rt6i_siblings);
}
/* Adjust walkers */
read_lock(&net->ipv6.fib6_walker_lock);
FOR_WALKERS(net, w) {
if (w->state == FWS_C && w->leaf == rt) {
RT6_TRACE("walker %p adjusted by delroute\n", w);
w->leaf = rt->dst.rt6_next;
if (!w->leaf)
w->state = FWS_U;
}
}
read_unlock(&net->ipv6.fib6_walker_lock);
rt->dst.rt6_next = NULL;
/* If it was last route, expunge its radix tree node */
if (!fn->leaf) {
fn->fn_flags &= ~RTN_RTINFO;
net->ipv6.rt6_stats->fib_route_nodes--;
fn = fib6_repair_tree(net, fn);
}
fib6_purge_rt(rt, fn, net);
call_fib6_entry_notifiers(net, FIB_EVENT_ENTRY_DEL, rt);
if (!info->skip_notify)
inet6_rt_notify(RTM_DELROUTE, rt, info, 0);
rt6_release(rt);
}
int fib6_del(struct rt6_info *rt, struct nl_info *info)
{
struct fib6_node *fn = rcu_dereference_protected(rt->rt6i_node,
lockdep_is_held(&rt->rt6i_table->tb6_lock));
struct net *net = info->nl_net;
struct rt6_info **rtp;
#if RT6_DEBUG >= 2
if (rt->dst.obsolete > 0) {
WARN_ON(fn);
return -ENOENT;
}
#endif
if (!fn || rt == net->ipv6.ip6_null_entry)
return -ENOENT;
WARN_ON(!(fn->fn_flags & RTN_RTINFO));
if (!(rt->rt6i_flags & RTF_CACHE)) {
struct fib6_node *pn = fn;
#ifdef CONFIG_IPV6_SUBTREES
/* clones of this route might be in another subtree */
if (rt->rt6i_src.plen) {
while (!(pn->fn_flags & RTN_ROOT))
pn = pn->parent;
pn = pn->parent;
}
#endif
fib6_prune_clones(info->nl_net, pn);
}
/*
* Walk the leaf entries looking for ourself
*/
for (rtp = &fn->leaf; *rtp; rtp = &(*rtp)->dst.rt6_next) {
if (*rtp == rt) {
fib6_del_route(fn, rtp, info);
return 0;
}
}
return -ENOENT;
}
/*
* Tree traversal function.
*
* Certainly, it is not interrupt safe.
* However, it is internally reenterable wrt itself and fib6_add/fib6_del.
* It means, that we can modify tree during walking
* and use this function for garbage collection, clone pruning,
* cleaning tree when a device goes down etc. etc.
*
* It guarantees that every node will be traversed,
* and that it will be traversed only once.
*
* Callback function w->func may return:
* 0 -> continue walking.
* positive value -> walking is suspended (used by tree dumps,
* and probably by gc, if it will be split to several slices)
* negative value -> terminate walking.
*
* The function itself returns:
* 0 -> walk is complete.
* >0 -> walk is incomplete (i.e. suspended)
* <0 -> walk is terminated by an error.
*/
static int fib6_walk_continue(struct fib6_walker *w)
{
struct fib6_node *fn, *pn;
for (;;) {
fn = w->node;
if (!fn)
return 0;
if (w->prune && fn != w->root &&
fn->fn_flags & RTN_RTINFO && w->state < FWS_C) {
w->state = FWS_C;
w->leaf = fn->leaf;
}
switch (w->state) {
#ifdef CONFIG_IPV6_SUBTREES
case FWS_S:
if (FIB6_SUBTREE(fn)) {
w->node = FIB6_SUBTREE(fn);
continue;
}
w->state = FWS_L;
#endif
case FWS_L:
if (fn->left) {
w->node = fn->left;
w->state = FWS_INIT;
continue;
}
w->state = FWS_R;
case FWS_R:
if (fn->right) {
w->node = fn->right;
w->state = FWS_INIT;
continue;
}
w->state = FWS_C;
w->leaf = fn->leaf;
case FWS_C:
if (w->leaf && fn->fn_flags & RTN_RTINFO) {
ipv6: fib: fix crash when changing large fib while dumping it When the fib size exceeds what can be dumped in a single skb, the dump is suspended and resumed once the last skb has been received by userspace. When the fib is changed while the dump is suspended, the walker might contain stale pointers, causing a crash when the dump is resumed. BUG: unable to handle kernel NULL pointer dereference at 0000000000000018 IP: [<ffffffffa01bce04>] fib6_walk_continue+0xbb/0x124 [ipv6] PGD 5347a067 PUD 65c7067 PMD 0 Oops: 0000 [#1] PREEMPT SMP ... RIP: 0010:[<ffffffffa01bce04>] [<ffffffffa01bce04>] fib6_walk_continue+0xbb/0x124 [ipv6] ... Call Trace: [<ffffffff8104aca3>] ? mutex_spin_on_owner+0x59/0x71 [<ffffffffa01bd105>] inet6_dump_fib+0x11b/0x1b9 [ipv6] [<ffffffff81371af4>] netlink_dump+0x5b/0x19e [<ffffffff8134f288>] ? consume_skb+0x28/0x2a [<ffffffff81373b69>] netlink_recvmsg+0x1ab/0x2c6 [<ffffffff81372781>] ? netlink_unicast+0xfa/0x151 [<ffffffff813483e0>] __sock_recvmsg+0x6d/0x79 [<ffffffff81348a53>] sock_recvmsg+0xca/0xe3 [<ffffffff81066d4b>] ? autoremove_wake_function+0x0/0x38 [<ffffffff811ed1f8>] ? radix_tree_lookup_slot+0xe/0x10 [<ffffffff810b3ed7>] ? find_get_page+0x90/0xa5 [<ffffffff810b5dc5>] ? filemap_fault+0x201/0x34f [<ffffffff810ef152>] ? fget_light+0x2f/0xac [<ffffffff813519e7>] ? verify_iovec+0x4f/0x94 [<ffffffff81349a65>] sys_recvmsg+0x14d/0x223 Store the serial number when beginning to walk the fib and reload pointers when continuing to walk after a change occured. Similar to other dumping functions, this might cause unrelated entries to be missed when entries are deleted. Tested-by: Ben Greear <greearb@candelatech.com> Signed-off-by: Patrick McHardy <kaber@trash.net> Signed-off-by: David S. Miller <davem@davemloft.net>
2010-02-08 05:19:03 +00:00
int err;
if (w->skip) {
w->skip--;
goto skip;
ipv6: fib: fix crash when changing large fib while dumping it When the fib size exceeds what can be dumped in a single skb, the dump is suspended and resumed once the last skb has been received by userspace. When the fib is changed while the dump is suspended, the walker might contain stale pointers, causing a crash when the dump is resumed. BUG: unable to handle kernel NULL pointer dereference at 0000000000000018 IP: [<ffffffffa01bce04>] fib6_walk_continue+0xbb/0x124 [ipv6] PGD 5347a067 PUD 65c7067 PMD 0 Oops: 0000 [#1] PREEMPT SMP ... RIP: 0010:[<ffffffffa01bce04>] [<ffffffffa01bce04>] fib6_walk_continue+0xbb/0x124 [ipv6] ... Call Trace: [<ffffffff8104aca3>] ? mutex_spin_on_owner+0x59/0x71 [<ffffffffa01bd105>] inet6_dump_fib+0x11b/0x1b9 [ipv6] [<ffffffff81371af4>] netlink_dump+0x5b/0x19e [<ffffffff8134f288>] ? consume_skb+0x28/0x2a [<ffffffff81373b69>] netlink_recvmsg+0x1ab/0x2c6 [<ffffffff81372781>] ? netlink_unicast+0xfa/0x151 [<ffffffff813483e0>] __sock_recvmsg+0x6d/0x79 [<ffffffff81348a53>] sock_recvmsg+0xca/0xe3 [<ffffffff81066d4b>] ? autoremove_wake_function+0x0/0x38 [<ffffffff811ed1f8>] ? radix_tree_lookup_slot+0xe/0x10 [<ffffffff810b3ed7>] ? find_get_page+0x90/0xa5 [<ffffffff810b5dc5>] ? filemap_fault+0x201/0x34f [<ffffffff810ef152>] ? fget_light+0x2f/0xac [<ffffffff813519e7>] ? verify_iovec+0x4f/0x94 [<ffffffff81349a65>] sys_recvmsg+0x14d/0x223 Store the serial number when beginning to walk the fib and reload pointers when continuing to walk after a change occured. Similar to other dumping functions, this might cause unrelated entries to be missed when entries are deleted. Tested-by: Ben Greear <greearb@candelatech.com> Signed-off-by: Patrick McHardy <kaber@trash.net> Signed-off-by: David S. Miller <davem@davemloft.net>
2010-02-08 05:19:03 +00:00
}
err = w->func(w);
if (err)
return err;
ipv6: fib: fix crash when changing large fib while dumping it When the fib size exceeds what can be dumped in a single skb, the dump is suspended and resumed once the last skb has been received by userspace. When the fib is changed while the dump is suspended, the walker might contain stale pointers, causing a crash when the dump is resumed. BUG: unable to handle kernel NULL pointer dereference at 0000000000000018 IP: [<ffffffffa01bce04>] fib6_walk_continue+0xbb/0x124 [ipv6] PGD 5347a067 PUD 65c7067 PMD 0 Oops: 0000 [#1] PREEMPT SMP ... RIP: 0010:[<ffffffffa01bce04>] [<ffffffffa01bce04>] fib6_walk_continue+0xbb/0x124 [ipv6] ... Call Trace: [<ffffffff8104aca3>] ? mutex_spin_on_owner+0x59/0x71 [<ffffffffa01bd105>] inet6_dump_fib+0x11b/0x1b9 [ipv6] [<ffffffff81371af4>] netlink_dump+0x5b/0x19e [<ffffffff8134f288>] ? consume_skb+0x28/0x2a [<ffffffff81373b69>] netlink_recvmsg+0x1ab/0x2c6 [<ffffffff81372781>] ? netlink_unicast+0xfa/0x151 [<ffffffff813483e0>] __sock_recvmsg+0x6d/0x79 [<ffffffff81348a53>] sock_recvmsg+0xca/0xe3 [<ffffffff81066d4b>] ? autoremove_wake_function+0x0/0x38 [<ffffffff811ed1f8>] ? radix_tree_lookup_slot+0xe/0x10 [<ffffffff810b3ed7>] ? find_get_page+0x90/0xa5 [<ffffffff810b5dc5>] ? filemap_fault+0x201/0x34f [<ffffffff810ef152>] ? fget_light+0x2f/0xac [<ffffffff813519e7>] ? verify_iovec+0x4f/0x94 [<ffffffff81349a65>] sys_recvmsg+0x14d/0x223 Store the serial number when beginning to walk the fib and reload pointers when continuing to walk after a change occured. Similar to other dumping functions, this might cause unrelated entries to be missed when entries are deleted. Tested-by: Ben Greear <greearb@candelatech.com> Signed-off-by: Patrick McHardy <kaber@trash.net> Signed-off-by: David S. Miller <davem@davemloft.net>
2010-02-08 05:19:03 +00:00
w->count++;
continue;
}
skip:
w->state = FWS_U;
case FWS_U:
if (fn == w->root)
return 0;
pn = fn->parent;
w->node = pn;
#ifdef CONFIG_IPV6_SUBTREES
if (FIB6_SUBTREE(pn) == fn) {
WARN_ON(!(fn->fn_flags & RTN_ROOT));
w->state = FWS_L;
continue;
}
#endif
if (pn->left == fn) {
w->state = FWS_R;
continue;
}
if (pn->right == fn) {
w->state = FWS_C;
w->leaf = w->node->leaf;
continue;
}
#if RT6_DEBUG >= 2
WARN_ON(1);
#endif
}
}
}
static int fib6_walk(struct net *net, struct fib6_walker *w)
{
int res;
w->state = FWS_INIT;
w->node = w->root;
fib6_walker_link(net, w);
res = fib6_walk_continue(w);
if (res <= 0)
fib6_walker_unlink(net, w);
return res;
}
static int fib6_clean_node(struct fib6_walker *w)
{
int res;
struct rt6_info *rt;
struct fib6_cleaner *c = container_of(w, struct fib6_cleaner, w);
struct nl_info info = {
.nl_net = c->net,
};
if (c->sernum != FIB6_NO_SERNUM_CHANGE &&
w->node->fn_sernum != c->sernum)
w->node->fn_sernum = c->sernum;
if (!c->func) {
WARN_ON_ONCE(c->sernum == FIB6_NO_SERNUM_CHANGE);
w->leaf = NULL;
return 0;
}
for (rt = w->leaf; rt; rt = rt->dst.rt6_next) {
res = c->func(rt, c->arg);
if (res < 0) {
w->leaf = rt;
res = fib6_del(rt, &info);
if (res) {
#if RT6_DEBUG >= 2
pr_debug("%s: del failed: rt=%p@%p err=%d\n",
__func__, rt,
rcu_access_pointer(rt->rt6i_node),
res);
#endif
continue;
}
return 0;
}
WARN_ON(res != 0);
}
w->leaf = rt;
return 0;
}
/*
* Convenient frontend to tree walker.
*
* func is called on each route.
* It may return -1 -> delete this route.
* 0 -> continue walking
*
* prune==1 -> only immediate children of node (certainly,
* ignoring pure split nodes) will be scanned.
*/
static void fib6_clean_tree(struct net *net, struct fib6_node *root,
int (*func)(struct rt6_info *, void *arg),
bool prune, int sernum, void *arg)
{
struct fib6_cleaner c;
c.w.root = root;
c.w.func = fib6_clean_node;
c.w.prune = prune;
ipv6: fib: fix crash when changing large fib while dumping it When the fib size exceeds what can be dumped in a single skb, the dump is suspended and resumed once the last skb has been received by userspace. When the fib is changed while the dump is suspended, the walker might contain stale pointers, causing a crash when the dump is resumed. BUG: unable to handle kernel NULL pointer dereference at 0000000000000018 IP: [<ffffffffa01bce04>] fib6_walk_continue+0xbb/0x124 [ipv6] PGD 5347a067 PUD 65c7067 PMD 0 Oops: 0000 [#1] PREEMPT SMP ... RIP: 0010:[<ffffffffa01bce04>] [<ffffffffa01bce04>] fib6_walk_continue+0xbb/0x124 [ipv6] ... Call Trace: [<ffffffff8104aca3>] ? mutex_spin_on_owner+0x59/0x71 [<ffffffffa01bd105>] inet6_dump_fib+0x11b/0x1b9 [ipv6] [<ffffffff81371af4>] netlink_dump+0x5b/0x19e [<ffffffff8134f288>] ? consume_skb+0x28/0x2a [<ffffffff81373b69>] netlink_recvmsg+0x1ab/0x2c6 [<ffffffff81372781>] ? netlink_unicast+0xfa/0x151 [<ffffffff813483e0>] __sock_recvmsg+0x6d/0x79 [<ffffffff81348a53>] sock_recvmsg+0xca/0xe3 [<ffffffff81066d4b>] ? autoremove_wake_function+0x0/0x38 [<ffffffff811ed1f8>] ? radix_tree_lookup_slot+0xe/0x10 [<ffffffff810b3ed7>] ? find_get_page+0x90/0xa5 [<ffffffff810b5dc5>] ? filemap_fault+0x201/0x34f [<ffffffff810ef152>] ? fget_light+0x2f/0xac [<ffffffff813519e7>] ? verify_iovec+0x4f/0x94 [<ffffffff81349a65>] sys_recvmsg+0x14d/0x223 Store the serial number when beginning to walk the fib and reload pointers when continuing to walk after a change occured. Similar to other dumping functions, this might cause unrelated entries to be missed when entries are deleted. Tested-by: Ben Greear <greearb@candelatech.com> Signed-off-by: Patrick McHardy <kaber@trash.net> Signed-off-by: David S. Miller <davem@davemloft.net>
2010-02-08 05:19:03 +00:00
c.w.count = 0;
c.w.skip = 0;
c.func = func;
c.sernum = sernum;
c.arg = arg;
c.net = net;
fib6_walk(net, &c.w);
}
static void __fib6_clean_all(struct net *net,
int (*func)(struct rt6_info *, void *),
int sernum, void *arg)
{
struct fib6_table *table;
struct hlist_head *head;
unsigned int h;
rcu_read_lock();
for (h = 0; h < FIB6_TABLE_HASHSZ; h++) {
head = &net->ipv6.fib_table_hash[h];
hlist: drop the node parameter from iterators I'm not sure why, but the hlist for each entry iterators were conceived list_for_each_entry(pos, head, member) The hlist ones were greedy and wanted an extra parameter: hlist_for_each_entry(tpos, pos, head, member) Why did they need an extra pos parameter? I'm not quite sure. Not only they don't really need it, it also prevents the iterator from looking exactly like the list iterator, which is unfortunate. Besides the semantic patch, there was some manual work required: - Fix up the actual hlist iterators in linux/list.h - Fix up the declaration of other iterators based on the hlist ones. - A very small amount of places were using the 'node' parameter, this was modified to use 'obj->member' instead. - Coccinelle didn't handle the hlist_for_each_entry_safe iterator properly, so those had to be fixed up manually. The semantic patch which is mostly the work of Peter Senna Tschudin is here: @@ iterator name hlist_for_each_entry, hlist_for_each_entry_continue, hlist_for_each_entry_from, hlist_for_each_entry_rcu, hlist_for_each_entry_rcu_bh, hlist_for_each_entry_continue_rcu_bh, for_each_busy_worker, ax25_uid_for_each, ax25_for_each, inet_bind_bucket_for_each, sctp_for_each_hentry, sk_for_each, sk_for_each_rcu, sk_for_each_from, sk_for_each_safe, sk_for_each_bound, hlist_for_each_entry_safe, hlist_for_each_entry_continue_rcu, nr_neigh_for_each, nr_neigh_for_each_safe, nr_node_for_each, nr_node_for_each_safe, for_each_gfn_indirect_valid_sp, for_each_gfn_sp, for_each_host; type T; expression a,c,d,e; identifier b; statement S; @@ -T b; <+... when != b ( hlist_for_each_entry(a, - b, c, d) S | hlist_for_each_entry_continue(a, - b, c) S | hlist_for_each_entry_from(a, - b, c) S | hlist_for_each_entry_rcu(a, - b, c, d) S | hlist_for_each_entry_rcu_bh(a, - b, c, d) S | hlist_for_each_entry_continue_rcu_bh(a, - b, c) S | for_each_busy_worker(a, c, - b, d) S | ax25_uid_for_each(a, - b, c) S | ax25_for_each(a, - b, c) S | inet_bind_bucket_for_each(a, - b, c) S | sctp_for_each_hentry(a, - b, c) S | sk_for_each(a, - b, c) S | sk_for_each_rcu(a, - b, c) S | sk_for_each_from -(a, b) +(a) S + sk_for_each_from(a) S | sk_for_each_safe(a, - b, c, d) S | sk_for_each_bound(a, - b, c) S | hlist_for_each_entry_safe(a, - b, c, d, e) S | hlist_for_each_entry_continue_rcu(a, - b, c) S | nr_neigh_for_each(a, - b, c) S | nr_neigh_for_each_safe(a, - b, c, d) S | nr_node_for_each(a, - b, c) S | nr_node_for_each_safe(a, - b, c, d) S | - for_each_gfn_sp(a, c, d, b) S + for_each_gfn_sp(a, c, d) S | - for_each_gfn_indirect_valid_sp(a, c, d, b) S + for_each_gfn_indirect_valid_sp(a, c, d) S | for_each_host(a, - b, c) S | for_each_host_safe(a, - b, c, d) S | for_each_mesh_entry(a, - b, c, d) S ) ...+> [akpm@linux-foundation.org: drop bogus change from net/ipv4/raw.c] [akpm@linux-foundation.org: drop bogus hunk from net/ipv6/raw.c] [akpm@linux-foundation.org: checkpatch fixes] [akpm@linux-foundation.org: fix warnings] [akpm@linux-foudnation.org: redo intrusive kvm changes] Tested-by: Peter Senna Tschudin <peter.senna@gmail.com> Acked-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Signed-off-by: Sasha Levin <sasha.levin@oracle.com> Cc: Wu Fengguang <fengguang.wu@intel.com> Cc: Marcelo Tosatti <mtosatti@redhat.com> Cc: Gleb Natapov <gleb@redhat.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2013-02-28 01:06:00 +00:00
hlist_for_each_entry_rcu(table, head, tb6_hlist) {
write_lock_bh(&table->tb6_lock);
fib6_clean_tree(net, &table->tb6_root,
func, false, sernum, arg);
write_unlock_bh(&table->tb6_lock);
}
}
rcu_read_unlock();
}
void fib6_clean_all(struct net *net, int (*func)(struct rt6_info *, void *),
void *arg)
{
__fib6_clean_all(net, func, FIB6_NO_SERNUM_CHANGE, arg);
}
static int fib6_prune_clone(struct rt6_info *rt, void *arg)
{
if (rt->rt6i_flags & RTF_CACHE) {
RT6_TRACE("pruning clone %p\n", rt);
return -1;
}
return 0;
}
static void fib6_prune_clones(struct net *net, struct fib6_node *fn)
{
fib6_clean_tree(net, fn, fib6_prune_clone, true,
FIB6_NO_SERNUM_CHANGE, NULL);
}
static void fib6_flush_trees(struct net *net)
{
int new_sernum = fib6_new_sernum(net);
__fib6_clean_all(net, NULL, new_sernum, NULL);
}
/*
* Garbage collection
*/
struct fib6_gc_args
{
int timeout;
int more;
};
static int fib6_age(struct rt6_info *rt, void *arg)
{
struct fib6_gc_args *gc_args = arg;
unsigned long now = jiffies;
/*
* check addrconf expiration here.
* Routes are expired even if they are in use.
*
* Also age clones. Note, that clones are aged out
* only if they are not in use now.
*/
if (rt->rt6i_flags & RTF_EXPIRES && rt->dst.expires) {
if (time_after(now, rt->dst.expires)) {
RT6_TRACE("expiring %p\n", rt);
return -1;
}
gc_args->more++;
} else if (rt->rt6i_flags & RTF_CACHE) {
if (time_after_eq(now, rt->dst.lastuse + gc_args->timeout))
rt->dst.obsolete = DST_OBSOLETE_KILL;
if (atomic_read(&rt->dst.__refcnt) == 1 &&
rt->dst.obsolete == DST_OBSOLETE_KILL) {
RT6_TRACE("aging clone %p\n", rt);
return -1;
} else if (rt->rt6i_flags & RTF_GATEWAY) {
struct neighbour *neigh;
__u8 neigh_flags = 0;
neigh = dst_neigh_lookup(&rt->dst, &rt->rt6i_gateway);
if (neigh) {
neigh_flags = neigh->flags;
neigh_release(neigh);
}
if (!(neigh_flags & NTF_ROUTER)) {
RT6_TRACE("purging route %p via non-router but gateway\n",
rt);
return -1;
}
}
gc_args->more++;
}
return 0;
}
void fib6_run_gc(unsigned long expires, struct net *net, bool force)
{
struct fib6_gc_args gc_args;
unsigned long now;
if (force) {
spin_lock_bh(&net->ipv6.fib6_gc_lock);
} else if (!spin_trylock_bh(&net->ipv6.fib6_gc_lock)) {
mod_timer(&net->ipv6.ip6_fib_timer, jiffies + HZ);
return;
}
gc_args.timeout = expires ? (int)expires :
net->ipv6.sysctl.ip6_rt_gc_interval;
gc_args.more = 0;
fib6_clean_all(net, fib6_age, &gc_args);
now = jiffies;
net->ipv6.ip6_rt_last_gc = now;
if (gc_args.more)
mod_timer(&net->ipv6.ip6_fib_timer,
round_jiffies(now
+ net->ipv6.sysctl.ip6_rt_gc_interval));
else
del_timer(&net->ipv6.ip6_fib_timer);
spin_unlock_bh(&net->ipv6.fib6_gc_lock);
}
static void fib6_gc_timer_cb(unsigned long arg)
{
fib6_run_gc(0, (struct net *)arg, true);
}
static int __net_init fib6_net_init(struct net *net)
{
size_t size = sizeof(struct hlist_head) * FIB6_TABLE_HASHSZ;
int err;
err = fib6_notifier_init(net);
if (err)
return err;
spin_lock_init(&net->ipv6.fib6_gc_lock);
rwlock_init(&net->ipv6.fib6_walker_lock);
INIT_LIST_HEAD(&net->ipv6.fib6_walkers);
setup_timer(&net->ipv6.ip6_fib_timer, fib6_gc_timer_cb, (unsigned long)net);
net->ipv6.rt6_stats = kzalloc(sizeof(*net->ipv6.rt6_stats), GFP_KERNEL);
if (!net->ipv6.rt6_stats)
goto out_timer;
/* Avoid false sharing : Use at least a full cache line */
size = max_t(size_t, size, L1_CACHE_BYTES);
net->ipv6.fib_table_hash = kzalloc(size, GFP_KERNEL);
if (!net->ipv6.fib_table_hash)
goto out_rt6_stats;
net->ipv6.fib6_main_tbl = kzalloc(sizeof(*net->ipv6.fib6_main_tbl),
GFP_KERNEL);
if (!net->ipv6.fib6_main_tbl)
goto out_fib_table_hash;
net->ipv6.fib6_main_tbl->tb6_id = RT6_TABLE_MAIN;
net->ipv6.fib6_main_tbl->tb6_root.leaf = net->ipv6.ip6_null_entry;
net->ipv6.fib6_main_tbl->tb6_root.fn_flags =
RTN_ROOT | RTN_TL_ROOT | RTN_RTINFO;
inet_peer_base_init(&net->ipv6.fib6_main_tbl->tb6_peers);
#ifdef CONFIG_IPV6_MULTIPLE_TABLES
net->ipv6.fib6_local_tbl = kzalloc(sizeof(*net->ipv6.fib6_local_tbl),
GFP_KERNEL);
if (!net->ipv6.fib6_local_tbl)
goto out_fib6_main_tbl;
net->ipv6.fib6_local_tbl->tb6_id = RT6_TABLE_LOCAL;
net->ipv6.fib6_local_tbl->tb6_root.leaf = net->ipv6.ip6_null_entry;
net->ipv6.fib6_local_tbl->tb6_root.fn_flags =
RTN_ROOT | RTN_TL_ROOT | RTN_RTINFO;
inet_peer_base_init(&net->ipv6.fib6_local_tbl->tb6_peers);
#endif
fib6_tables_init(net);
return 0;
#ifdef CONFIG_IPV6_MULTIPLE_TABLES
out_fib6_main_tbl:
kfree(net->ipv6.fib6_main_tbl);
#endif
out_fib_table_hash:
kfree(net->ipv6.fib_table_hash);
out_rt6_stats:
kfree(net->ipv6.rt6_stats);
out_timer:
fib6_notifier_exit(net);
return -ENOMEM;
}
static void fib6_net_exit(struct net *net)
{
unsigned int i;
rt6_ifdown(net, NULL);
del_timer_sync(&net->ipv6.ip6_fib_timer);
for (i = 0; i < FIB6_TABLE_HASHSZ; i++) {
struct hlist_head *head = &net->ipv6.fib_table_hash[i];
struct hlist_node *tmp;
struct fib6_table *tb;
hlist_for_each_entry_safe(tb, tmp, head, tb6_hlist) {
hlist_del(&tb->tb6_hlist);
fib6_free_table(tb);
}
}
kfree(net->ipv6.fib_table_hash);
kfree(net->ipv6.rt6_stats);
fib6_notifier_exit(net);
}
static struct pernet_operations fib6_net_ops = {
.init = fib6_net_init,
.exit = fib6_net_exit,
};
int __init fib6_init(void)
{
int ret = -ENOMEM;
fib6_node_kmem = kmem_cache_create("fib6_nodes",
sizeof(struct fib6_node),
0, SLAB_HWCACHE_ALIGN,
NULL);
if (!fib6_node_kmem)
goto out;
ret = register_pernet_subsys(&fib6_net_ops);
if (ret)
goto out_kmem_cache_create;
ret = __rtnl_register(PF_INET6, RTM_GETROUTE, NULL, inet6_dump_fib,
0);
if (ret)
goto out_unregister_subsys;
__fib6_flush_trees = fib6_flush_trees;
out:
return ret;
out_unregister_subsys:
unregister_pernet_subsys(&fib6_net_ops);
out_kmem_cache_create:
kmem_cache_destroy(fib6_node_kmem);
goto out;
}
void fib6_gc_cleanup(void)
{
unregister_pernet_subsys(&fib6_net_ops);
kmem_cache_destroy(fib6_node_kmem);
}
#ifdef CONFIG_PROC_FS
struct ipv6_route_iter {
struct seq_net_private p;
struct fib6_walker w;
loff_t skip;
struct fib6_table *tbl;
int sernum;
};
static int ipv6_route_seq_show(struct seq_file *seq, void *v)
{
struct rt6_info *rt = v;
struct ipv6_route_iter *iter = seq->private;
seq_printf(seq, "%pi6 %02x ", &rt->rt6i_dst.addr, rt->rt6i_dst.plen);
#ifdef CONFIG_IPV6_SUBTREES
seq_printf(seq, "%pi6 %02x ", &rt->rt6i_src.addr, rt->rt6i_src.plen);
#else
seq_puts(seq, "00000000000000000000000000000000 00 ");
#endif
if (rt->rt6i_flags & RTF_GATEWAY)
seq_printf(seq, "%pi6", &rt->rt6i_gateway);
else
seq_puts(seq, "00000000000000000000000000000000");
seq_printf(seq, " %08x %08x %08x %08x %8s\n",
rt->rt6i_metric, atomic_read(&rt->dst.__refcnt),
rt->dst.__use, rt->rt6i_flags,
rt->dst.dev ? rt->dst.dev->name : "");
iter->w.leaf = NULL;
return 0;
}
static int ipv6_route_yield(struct fib6_walker *w)
{
struct ipv6_route_iter *iter = w->args;
if (!iter->skip)
return 1;
do {
iter->w.leaf = iter->w.leaf->dst.rt6_next;
iter->skip--;
if (!iter->skip && iter->w.leaf)
return 1;
} while (iter->w.leaf);
return 0;
}
static void ipv6_route_seq_setup_walk(struct ipv6_route_iter *iter,
struct net *net)
{
memset(&iter->w, 0, sizeof(iter->w));
iter->w.func = ipv6_route_yield;
iter->w.root = &iter->tbl->tb6_root;
iter->w.state = FWS_INIT;
iter->w.node = iter->w.root;
iter->w.args = iter;
iter->sernum = iter->w.root->fn_sernum;
INIT_LIST_HEAD(&iter->w.lh);
fib6_walker_link(net, &iter->w);
}
static struct fib6_table *ipv6_route_seq_next_table(struct fib6_table *tbl,
struct net *net)
{
unsigned int h;
struct hlist_node *node;
if (tbl) {
h = (tbl->tb6_id & (FIB6_TABLE_HASHSZ - 1)) + 1;
node = rcu_dereference_bh(hlist_next_rcu(&tbl->tb6_hlist));
} else {
h = 0;
node = NULL;
}
while (!node && h < FIB6_TABLE_HASHSZ) {
node = rcu_dereference_bh(
hlist_first_rcu(&net->ipv6.fib_table_hash[h++]));
}
return hlist_entry_safe(node, struct fib6_table, tb6_hlist);
}
static void ipv6_route_check_sernum(struct ipv6_route_iter *iter)
{
if (iter->sernum != iter->w.root->fn_sernum) {
iter->sernum = iter->w.root->fn_sernum;
iter->w.state = FWS_INIT;
iter->w.node = iter->w.root;
WARN_ON(iter->w.skip);
iter->w.skip = iter->w.count;
}
}
static void *ipv6_route_seq_next(struct seq_file *seq, void *v, loff_t *pos)
{
int r;
struct rt6_info *n;
struct net *net = seq_file_net(seq);
struct ipv6_route_iter *iter = seq->private;
if (!v)
goto iter_table;
n = ((struct rt6_info *)v)->dst.rt6_next;
if (n) {
++*pos;
return n;
}
iter_table:
ipv6_route_check_sernum(iter);
read_lock(&iter->tbl->tb6_lock);
r = fib6_walk_continue(&iter->w);
read_unlock(&iter->tbl->tb6_lock);
if (r > 0) {
if (v)
++*pos;
return iter->w.leaf;
} else if (r < 0) {
fib6_walker_unlink(net, &iter->w);
return NULL;
}
fib6_walker_unlink(net, &iter->w);
iter->tbl = ipv6_route_seq_next_table(iter->tbl, net);
if (!iter->tbl)
return NULL;
ipv6_route_seq_setup_walk(iter, net);
goto iter_table;
}
static void *ipv6_route_seq_start(struct seq_file *seq, loff_t *pos)
__acquires(RCU_BH)
{
struct net *net = seq_file_net(seq);
struct ipv6_route_iter *iter = seq->private;
rcu_read_lock_bh();
iter->tbl = ipv6_route_seq_next_table(NULL, net);
iter->skip = *pos;
if (iter->tbl) {
ipv6_route_seq_setup_walk(iter, net);
return ipv6_route_seq_next(seq, NULL, pos);
} else {
return NULL;
}
}
static bool ipv6_route_iter_active(struct ipv6_route_iter *iter)
{
struct fib6_walker *w = &iter->w;
return w->node && !(w->state == FWS_U && w->node == w->root);
}
static void ipv6_route_seq_stop(struct seq_file *seq, void *v)
__releases(RCU_BH)
{
struct net *net = seq_file_net(seq);
struct ipv6_route_iter *iter = seq->private;
if (ipv6_route_iter_active(iter))
fib6_walker_unlink(net, &iter->w);
rcu_read_unlock_bh();
}
static const struct seq_operations ipv6_route_seq_ops = {
.start = ipv6_route_seq_start,
.next = ipv6_route_seq_next,
.stop = ipv6_route_seq_stop,
.show = ipv6_route_seq_show
};
int ipv6_route_open(struct inode *inode, struct file *file)
{
return seq_open_net(inode, file, &ipv6_route_seq_ops,
sizeof(struct ipv6_route_iter));
}
#endif /* CONFIG_PROC_FS */