linux_dsm_epyc7002/include/net/ip6_fib.h

549 lines
13 KiB
C
Raw Normal View History

/*
* Linux INET6 implementation
*
* 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.
*/
#ifndef _IP6_FIB_H
#define _IP6_FIB_H
#include <linux/ipv6_route.h>
#include <linux/rtnetlink.h>
#include <linux/spinlock.h>
#include <linux/notifier.h>
#include <net/dst.h>
#include <net/flow.h>
#include <net/ip_fib.h>
#include <net/netlink.h>
#include <net/inetpeer.h>
#include <net/fib_notifier.h>
#ifdef CONFIG_IPV6_MULTIPLE_TABLES
#define FIB6_TABLE_HASHSZ 256
#else
#define FIB6_TABLE_HASHSZ 1
#endif
#define RT6_DEBUG 2
#if RT6_DEBUG >= 3
#define RT6_TRACE(x...) pr_debug(x)
#else
#define RT6_TRACE(x...) do { ; } while (0)
#endif
struct rt6_info;
struct fib6_info;
struct fib6_config {
u32 fc_table;
u32 fc_metric;
int fc_dst_len;
int fc_src_len;
int fc_ifindex;
u32 fc_flags;
u32 fc_protocol;
net: ipv6: Allow shorthand delete of all nexthops in multipath route IPv4 allows multipath routes to be deleted using just the prefix and length. For example: $ ip ro ls vrf red unreachable default metric 8192 1.1.1.0/24 nexthop via 10.100.1.254 dev eth1 weight 1 nexthop via 10.11.200.2 dev eth11.200 weight 1 10.11.200.0/24 dev eth11.200 proto kernel scope link src 10.11.200.3 10.100.1.0/24 dev eth1 proto kernel scope link src 10.100.1.3 $ ip ro del 1.1.1.0/24 vrf red $ ip ro ls vrf red unreachable default metric 8192 10.11.200.0/24 dev eth11.200 proto kernel scope link src 10.11.200.3 10.100.1.0/24 dev eth1 proto kernel scope link src 10.100.1.3 The same notation does not work with IPv6 because of how multipath routes are implemented for IPv6. For IPv6 only the first nexthop of a multipath route is deleted if the request contains only a prefix and length. This leads to unnecessary complexity in userspace dealing with IPv6 multipath routes. This patch allows all nexthops to be deleted without specifying each one in the delete request. Internally, this is done by walking the sibling list of the route matching the specifications given (prefix, length, metric, protocol, etc). $ ip -6 ro ls vrf red 2001:db8:1::/120 dev eth1 proto kernel metric 256 pref medium 2001:db8:2::/120 dev eth2 proto kernel metric 256 pref medium 2001:db8:200::/120 via 2001:db8:1::2 dev eth1 metric 1024 pref medium 2001:db8:200::/120 via 2001:db8:2::2 dev eth2 metric 1024 pref medium ... $ ip -6 ro del vrf red 2001:db8:200::/120 $ ip -6 ro ls vrf red 2001:db8:1::/120 dev eth1 proto kernel metric 256 pref medium 2001:db8:2::/120 dev eth2 proto kernel metric 256 pref medium ... Because IPv6 allows individual nexthops to be deleted without deleting the entire route, the ip6_route_multipath_del and non-multipath code path (ip6_route_del) have to be discriminated so that all nexthops are only deleted for the latter case. This is done by making the existing fc_type in fib6_config a u16 and then adding a new u16 field with fc_delete_all_nh as the first bit. Suggested-by: Dinesh Dutt <ddutt@cumulusnetworks.com> Signed-off-by: David Ahern <dsa@cumulusnetworks.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-02-03 03:37:08 +07:00
u16 fc_type; /* only 8 bits are used */
u16 fc_delete_all_nh : 1,
fc_ignore_dev_down:1,
__unused : 14;
struct in6_addr fc_dst;
struct in6_addr fc_src;
struct in6_addr fc_prefsrc;
struct in6_addr fc_gateway;
unsigned long fc_expires;
struct nlattr *fc_mx;
int fc_mx_len;
int fc_mp_len;
struct nlattr *fc_mp;
struct nl_info fc_nlinfo;
struct nlattr *fc_encap;
u16 fc_encap_type;
};
struct fib6_node {
ipv6: replace rwlock with rcu and spinlock in fib6_table With all the preparation work before, we are now ready to replace rwlock with rcu and spinlock in fib6_table. That means now all fib6_node in fib6_table are protected by rcu. And when freeing fib6_node, call_rcu() is used to wait for the rcu grace period before releasing the memory. When accessing fib6_node, corresponding rcu APIs need to be used. And all previous sessions protected by the write lock will now be protected by the spin lock per table. All previous sessions protected by read lock will now be protected by rcu_read_lock(). A couple of things to note here: 1. As part of the work of replacing rwlock with rcu, the linked list of fn->leaf now has to be rcu protected as well. So both fn->leaf and rt->dst.rt6_next are now __rcu tagged and corresponding rcu APIs are used when manipulating them. 2. For fn->rr_ptr, first of all, it also needs to be rcu protected now and is tagged with __rcu and rcu APIs are used in corresponding places. Secondly, fn->rr_ptr is changed in rt6_select() which is a reader thread. This makes the issue a bit complicated. We think a valid solution for it is to let rt6_select() grab the tb6_lock if it decides to change it. As it is not in the normal operation and only happens when there is no valid neighbor cache for the route, we think the performance impact should be low. 3. fib6_walk_continue() has to be called with tb6_lock held even in the route dumping related functions, e.g. inet6_dump_fib(), fib6_tables_dump() and ipv6_route_seq_ops. It is because fib6_walk_continue() makes modifications to the walker structure, and so are fib6_repair_tree() and fib6_del_route(). In order to do proper syncing between them, we need to let fib6_walk_continue() hold the lock. We may be able to do further improvement on the way we do the tree walk to get rid of the need for holding the spin lock. But not for now. 4. When fib6_del_route() removes a route from the tree, we no longer mark rt->dst.rt6_next to NULL to make simultaneous reader be able to further traverse the list with rcu. However, rt->dst.rt6_next is only valid within this same rcu period. No one should access it later. 5. All the operation of atomic_inc(rt->rt6i_ref) is changed to be performed before we publish this route (either by linking it to fn->leaf or insert it in the list pointed by fn->leaf) just to be safe because as soon as we publish the route, some read thread will be able to access it. Signed-off-by: Wei Wang <weiwan@google.com> Signed-off-by: Martin KaFai Lau <kafai@fb.com> Signed-off-by: Eric Dumazet <edumazet@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-10-07 02:06:10 +07:00
struct fib6_node __rcu *parent;
struct fib6_node __rcu *left;
struct fib6_node __rcu *right;
#ifdef CONFIG_IPV6_SUBTREES
ipv6: replace rwlock with rcu and spinlock in fib6_table With all the preparation work before, we are now ready to replace rwlock with rcu and spinlock in fib6_table. That means now all fib6_node in fib6_table are protected by rcu. And when freeing fib6_node, call_rcu() is used to wait for the rcu grace period before releasing the memory. When accessing fib6_node, corresponding rcu APIs need to be used. And all previous sessions protected by the write lock will now be protected by the spin lock per table. All previous sessions protected by read lock will now be protected by rcu_read_lock(). A couple of things to note here: 1. As part of the work of replacing rwlock with rcu, the linked list of fn->leaf now has to be rcu protected as well. So both fn->leaf and rt->dst.rt6_next are now __rcu tagged and corresponding rcu APIs are used when manipulating them. 2. For fn->rr_ptr, first of all, it also needs to be rcu protected now and is tagged with __rcu and rcu APIs are used in corresponding places. Secondly, fn->rr_ptr is changed in rt6_select() which is a reader thread. This makes the issue a bit complicated. We think a valid solution for it is to let rt6_select() grab the tb6_lock if it decides to change it. As it is not in the normal operation and only happens when there is no valid neighbor cache for the route, we think the performance impact should be low. 3. fib6_walk_continue() has to be called with tb6_lock held even in the route dumping related functions, e.g. inet6_dump_fib(), fib6_tables_dump() and ipv6_route_seq_ops. It is because fib6_walk_continue() makes modifications to the walker structure, and so are fib6_repair_tree() and fib6_del_route(). In order to do proper syncing between them, we need to let fib6_walk_continue() hold the lock. We may be able to do further improvement on the way we do the tree walk to get rid of the need for holding the spin lock. But not for now. 4. When fib6_del_route() removes a route from the tree, we no longer mark rt->dst.rt6_next to NULL to make simultaneous reader be able to further traverse the list with rcu. However, rt->dst.rt6_next is only valid within this same rcu period. No one should access it later. 5. All the operation of atomic_inc(rt->rt6i_ref) is changed to be performed before we publish this route (either by linking it to fn->leaf or insert it in the list pointed by fn->leaf) just to be safe because as soon as we publish the route, some read thread will be able to access it. Signed-off-by: Wei Wang <weiwan@google.com> Signed-off-by: Martin KaFai Lau <kafai@fb.com> Signed-off-by: Eric Dumazet <edumazet@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-10-07 02:06:10 +07:00
struct fib6_node __rcu *subtree;
#endif
struct fib6_info __rcu *leaf;
__u16 fn_bit; /* bit key */
__u16 fn_flags;
int fn_sernum;
struct fib6_info __rcu *rr_ptr;
struct rcu_head rcu;
};
struct fib6_gc_args {
int timeout;
int more;
};
#ifndef CONFIG_IPV6_SUBTREES
#define FIB6_SUBTREE(fn) NULL
#else
ipv6: replace rwlock with rcu and spinlock in fib6_table With all the preparation work before, we are now ready to replace rwlock with rcu and spinlock in fib6_table. That means now all fib6_node in fib6_table are protected by rcu. And when freeing fib6_node, call_rcu() is used to wait for the rcu grace period before releasing the memory. When accessing fib6_node, corresponding rcu APIs need to be used. And all previous sessions protected by the write lock will now be protected by the spin lock per table. All previous sessions protected by read lock will now be protected by rcu_read_lock(). A couple of things to note here: 1. As part of the work of replacing rwlock with rcu, the linked list of fn->leaf now has to be rcu protected as well. So both fn->leaf and rt->dst.rt6_next are now __rcu tagged and corresponding rcu APIs are used when manipulating them. 2. For fn->rr_ptr, first of all, it also needs to be rcu protected now and is tagged with __rcu and rcu APIs are used in corresponding places. Secondly, fn->rr_ptr is changed in rt6_select() which is a reader thread. This makes the issue a bit complicated. We think a valid solution for it is to let rt6_select() grab the tb6_lock if it decides to change it. As it is not in the normal operation and only happens when there is no valid neighbor cache for the route, we think the performance impact should be low. 3. fib6_walk_continue() has to be called with tb6_lock held even in the route dumping related functions, e.g. inet6_dump_fib(), fib6_tables_dump() and ipv6_route_seq_ops. It is because fib6_walk_continue() makes modifications to the walker structure, and so are fib6_repair_tree() and fib6_del_route(). In order to do proper syncing between them, we need to let fib6_walk_continue() hold the lock. We may be able to do further improvement on the way we do the tree walk to get rid of the need for holding the spin lock. But not for now. 4. When fib6_del_route() removes a route from the tree, we no longer mark rt->dst.rt6_next to NULL to make simultaneous reader be able to further traverse the list with rcu. However, rt->dst.rt6_next is only valid within this same rcu period. No one should access it later. 5. All the operation of atomic_inc(rt->rt6i_ref) is changed to be performed before we publish this route (either by linking it to fn->leaf or insert it in the list pointed by fn->leaf) just to be safe because as soon as we publish the route, some read thread will be able to access it. Signed-off-by: Wei Wang <weiwan@google.com> Signed-off-by: Martin KaFai Lau <kafai@fb.com> Signed-off-by: Eric Dumazet <edumazet@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-10-07 02:06:10 +07:00
#define FIB6_SUBTREE(fn) (rcu_dereference_protected((fn)->subtree, 1))
#endif
/*
* routing information
*
*/
struct rt6key {
struct in6_addr addr;
int plen;
};
struct fib6_table;
struct rt6_exception_bucket {
struct hlist_head chain;
int depth;
};
struct rt6_exception {
struct hlist_node hlist;
struct rt6_info *rt6i;
unsigned long stamp;
struct rcu_head rcu;
};
#define FIB6_EXCEPTION_BUCKET_SIZE_SHIFT 10
#define FIB6_EXCEPTION_BUCKET_SIZE (1 << FIB6_EXCEPTION_BUCKET_SIZE_SHIFT)
#define FIB6_MAX_DEPTH 5
struct fib6_nh {
struct fib_nh_common nh_common;
#ifdef CONFIG_IPV6_ROUTER_PREF
unsigned long last_probe;
#endif
};
struct fib6_info {
struct fib6_table *fib6_table;
struct fib6_info __rcu *fib6_next;
struct fib6_node __rcu *fib6_node;
/* Multipath routes:
* siblings is a list of fib6_info that have the the same metric/weight,
* destination, but not the same gateway. nsiblings is just a cache
* to speed up lookup.
*/
struct list_head fib6_siblings;
unsigned int fib6_nsiblings;
refcount_t fib6_ref;
unsigned long expires;
struct dst_metrics *fib6_metrics;
#define fib6_pmtu fib6_metrics->metrics[RTAX_MTU-1]
struct rt6key fib6_dst;
u32 fib6_flags;
struct rt6key fib6_src;
struct rt6key fib6_prefsrc;
struct rt6_info * __percpu *rt6i_pcpu;
struct rt6_exception_bucket __rcu *rt6i_exception_bucket;
u32 fib6_metric;
u8 fib6_protocol;
u8 fib6_type;
u8 exception_bucket_flushed:1,
should_flush:1,
dst_nocount:1,
dst_nopolicy:1,
dst_host:1,
fib6_destroying:1,
unused:2;
struct fib6_nh fib6_nh;
net/ipv6: respect rcu grace period before freeing fib6_info syzbot reported use after free that is caused by fib6_info being freed without a proper RCU grace period. CPU: 0 PID: 1407 Comm: udevd Not tainted 4.17.0+ #39 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 Call Trace: <IRQ> __dump_stack lib/dump_stack.c:77 [inline] dump_stack+0x1b9/0x294 lib/dump_stack.c:113 print_address_description+0x6c/0x20b mm/kasan/report.c:256 kasan_report_error mm/kasan/report.c:354 [inline] kasan_report.cold.7+0x242/0x2fe mm/kasan/report.c:412 __asan_report_load8_noabort+0x14/0x20 mm/kasan/report.c:433 __read_once_size include/linux/compiler.h:188 [inline] find_rr_leaf net/ipv6/route.c:705 [inline] rt6_select net/ipv6/route.c:761 [inline] fib6_table_lookup+0x12b7/0x14d0 net/ipv6/route.c:1823 ip6_pol_route+0x1c2/0x1020 net/ipv6/route.c:1856 ip6_pol_route_output+0x54/0x70 net/ipv6/route.c:2082 fib6_rule_lookup+0x211/0x6d0 net/ipv6/fib6_rules.c:122 ip6_route_output_flags+0x2c5/0x350 net/ipv6/route.c:2110 ip6_route_output include/net/ip6_route.h:82 [inline] icmpv6_xrlim_allow net/ipv6/icmp.c:211 [inline] icmp6_send+0x147c/0x2da0 net/ipv6/icmp.c:535 icmpv6_send+0x17a/0x300 net/ipv6/ip6_icmp.c:43 ip6_link_failure+0xa5/0x790 net/ipv6/route.c:2244 dst_link_failure include/net/dst.h:427 [inline] ndisc_error_report+0xd1/0x1c0 net/ipv6/ndisc.c:695 neigh_invalidate+0x246/0x550 net/core/neighbour.c:892 neigh_timer_handler+0xaf9/0xde0 net/core/neighbour.c:978 call_timer_fn+0x230/0x940 kernel/time/timer.c:1326 expire_timers kernel/time/timer.c:1363 [inline] __run_timers+0x79e/0xc50 kernel/time/timer.c:1666 run_timer_softirq+0x4c/0x70 kernel/time/timer.c:1692 __do_softirq+0x2e0/0xaf5 kernel/softirq.c:284 invoke_softirq kernel/softirq.c:364 [inline] irq_exit+0x1d1/0x200 kernel/softirq.c:404 exiting_irq arch/x86/include/asm/apic.h:527 [inline] smp_apic_timer_interrupt+0x17e/0x710 arch/x86/kernel/apic/apic.c:1052 apic_timer_interrupt+0xf/0x20 arch/x86/entry/entry_64.S:863 </IRQ> RIP: 0010:strlen+0x5e/0xa0 lib/string.c:482 Code: 24 00 74 3b 48 bb 00 00 00 00 00 fc ff df 4c 89 e0 48 83 c0 01 48 89 c2 48 89 c1 48 c1 ea 03 83 e1 07 0f b6 14 1a 38 ca 7f 04 <84> d2 75 23 80 38 00 75 de 48 83 c4 08 4c 29 e0 5b 41 5c 5d c3 48 RSP: 0018:ffff8801af117850 EFLAGS: 00000246 ORIG_RAX: ffffffffffffff13 RAX: ffff880197f53bd0 RBX: dffffc0000000000 RCX: 0000000000000000 RDX: 0000000000000000 RSI: ffffffff81c5b06c RDI: ffff880197f53bc0 RBP: ffff8801af117868 R08: ffff88019a976540 R09: 0000000000000000 R10: ffff88019a976540 R11: 0000000000000000 R12: ffff880197f53bc0 R13: ffff880197f53bc0 R14: ffffffff899e4e90 R15: ffff8801d91c6a00 strlen include/linux/string.h:267 [inline] getname_kernel+0x24/0x370 fs/namei.c:218 open_exec+0x17/0x70 fs/exec.c:882 load_elf_binary+0x968/0x5610 fs/binfmt_elf.c:780 search_binary_handler+0x17d/0x570 fs/exec.c:1653 exec_binprm fs/exec.c:1695 [inline] __do_execve_file.isra.35+0x16fe/0x2710 fs/exec.c:1819 do_execveat_common fs/exec.c:1866 [inline] do_execve fs/exec.c:1883 [inline] __do_sys_execve fs/exec.c:1964 [inline] __se_sys_execve fs/exec.c:1959 [inline] __x64_sys_execve+0x8f/0xc0 fs/exec.c:1959 do_syscall_64+0x1b1/0x800 arch/x86/entry/common.c:290 entry_SYSCALL_64_after_hwframe+0x49/0xbe RIP: 0033:0x7f1576a46207 Code: 77 19 f4 48 89 d7 44 89 c0 0f 05 48 3d 00 f0 ff ff 76 e0 f7 d8 64 41 89 01 eb d8 f7 d8 64 41 89 01 eb df b8 3b 00 00 00 0f 05 <48> 3d 00 f0 ff ff 77 02 f3 c3 48 8b 15 00 8c 2d 00 f7 d8 64 89 02 RSP: 002b:00007ffff2784568 EFLAGS: 00000202 ORIG_RAX: 000000000000003b RAX: ffffffffffffffda RBX: 00000000ffffffff RCX: 00007f1576a46207 RDX: 0000000001215b10 RSI: 00007ffff2784660 RDI: 00007ffff2785670 RBP: 0000000000625500 R08: 000000000000589c R09: 000000000000589c R10: 0000000000000000 R11: 0000000000000202 R12: 0000000001215b10 R13: 0000000000000007 R14: 0000000001204250 R15: 0000000000000005 Allocated by task 12188: save_stack+0x43/0xd0 mm/kasan/kasan.c:448 set_track mm/kasan/kasan.c:460 [inline] kasan_kmalloc+0xc4/0xe0 mm/kasan/kasan.c:553 kmem_cache_alloc_trace+0x152/0x780 mm/slab.c:3620 kmalloc include/linux/slab.h:513 [inline] kzalloc include/linux/slab.h:706 [inline] fib6_info_alloc+0xbb/0x280 net/ipv6/ip6_fib.c:152 ip6_route_info_create+0x782/0x2b50 net/ipv6/route.c:3013 ip6_route_add+0x23/0xb0 net/ipv6/route.c:3154 ipv6_route_ioctl+0x5a5/0x760 net/ipv6/route.c:3660 inet6_ioctl+0x100/0x1f0 net/ipv6/af_inet6.c:546 sock_do_ioctl+0xe4/0x3e0 net/socket.c:973 sock_ioctl+0x30d/0x680 net/socket.c:1097 vfs_ioctl fs/ioctl.c:46 [inline] file_ioctl fs/ioctl.c:500 [inline] do_vfs_ioctl+0x1cf/0x16f0 fs/ioctl.c:684 ksys_ioctl+0xa9/0xd0 fs/ioctl.c:701 __do_sys_ioctl fs/ioctl.c:708 [inline] __se_sys_ioctl fs/ioctl.c:706 [inline] __x64_sys_ioctl+0x73/0xb0 fs/ioctl.c:706 do_syscall_64+0x1b1/0x800 arch/x86/entry/common.c:290 entry_SYSCALL_64_after_hwframe+0x49/0xbe Freed by task 1402: save_stack+0x43/0xd0 mm/kasan/kasan.c:448 set_track mm/kasan/kasan.c:460 [inline] __kasan_slab_free+0x11a/0x170 mm/kasan/kasan.c:521 kasan_slab_free+0xe/0x10 mm/kasan/kasan.c:528 __cache_free mm/slab.c:3498 [inline] kfree+0xd9/0x260 mm/slab.c:3813 fib6_info_destroy+0x29b/0x350 net/ipv6/ip6_fib.c:207 fib6_info_release include/net/ip6_fib.h:286 [inline] __ip6_del_rt_siblings net/ipv6/route.c:3235 [inline] ip6_route_del+0x11c4/0x13b0 net/ipv6/route.c:3316 ipv6_route_ioctl+0x616/0x760 net/ipv6/route.c:3663 inet6_ioctl+0x100/0x1f0 net/ipv6/af_inet6.c:546 sock_do_ioctl+0xe4/0x3e0 net/socket.c:973 sock_ioctl+0x30d/0x680 net/socket.c:1097 vfs_ioctl fs/ioctl.c:46 [inline] file_ioctl fs/ioctl.c:500 [inline] do_vfs_ioctl+0x1cf/0x16f0 fs/ioctl.c:684 ksys_ioctl+0xa9/0xd0 fs/ioctl.c:701 __do_sys_ioctl fs/ioctl.c:708 [inline] __se_sys_ioctl fs/ioctl.c:706 [inline] __x64_sys_ioctl+0x73/0xb0 fs/ioctl.c:706 do_syscall_64+0x1b1/0x800 arch/x86/entry/common.c:290 entry_SYSCALL_64_after_hwframe+0x49/0xbe The buggy address belongs to the object at ffff8801b5df2580 which belongs to the cache kmalloc-256 of size 256 The buggy address is located 8 bytes inside of 256-byte region [ffff8801b5df2580, ffff8801b5df2680) The buggy address belongs to the page: page:ffffea0006d77c80 count:1 mapcount:0 mapping:ffff8801da8007c0 index:0xffff8801b5df2e40 flags: 0x2fffc0000000100(slab) raw: 02fffc0000000100 ffffea0006c5cc48 ffffea0007363308 ffff8801da8007c0 raw: ffff8801b5df2e40 ffff8801b5df2080 0000000100000006 0000000000000000 page dumped because: kasan: bad access detected Memory state around the buggy address: ffff8801b5df2480: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb ffff8801b5df2500: fb fb fb fb fb fb fb fb fc fc fc fc fc fc fc fc > ffff8801b5df2580: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb ^ ffff8801b5df2600: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb ffff8801b5df2680: fc fc fc fc fc fc fc fc fb fb fb fb fb fb fb fb Fixes: a64efe142f5e ("net/ipv6: introduce fib6_info struct and helpers") Signed-off-by: Eric Dumazet <edumazet@google.com> Cc: David Ahern <dsahern@gmail.com> Reported-by: syzbot+9e6d75e3edef427ee888@syzkaller.appspotmail.com Acked-by: David Ahern <dsahern@gmail.com> Tested-by: David Ahern <dsahern@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-06-18 19:24:31 +07:00
struct rcu_head rcu;
};
struct rt6_info {
struct dst_entry dst;
struct fib6_info __rcu *from;
struct rt6key rt6i_dst;
struct rt6key rt6i_src;
struct in6_addr rt6i_gateway;
struct inet6_dev *rt6i_idev;
u32 rt6i_flags;
struct list_head rt6i_uncached;
struct uncached_list *rt6i_uncached_list;
/* more non-fragment space at head required */
unsigned short rt6i_nfheader_len;
};
struct fib6_result {
struct fib6_nh *nh;
struct fib6_info *f6i;
u32 fib6_flags;
u8 fib6_type;
struct rt6_info *rt6;
};
ipv6: replace rwlock with rcu and spinlock in fib6_table With all the preparation work before, we are now ready to replace rwlock with rcu and spinlock in fib6_table. That means now all fib6_node in fib6_table are protected by rcu. And when freeing fib6_node, call_rcu() is used to wait for the rcu grace period before releasing the memory. When accessing fib6_node, corresponding rcu APIs need to be used. And all previous sessions protected by the write lock will now be protected by the spin lock per table. All previous sessions protected by read lock will now be protected by rcu_read_lock(). A couple of things to note here: 1. As part of the work of replacing rwlock with rcu, the linked list of fn->leaf now has to be rcu protected as well. So both fn->leaf and rt->dst.rt6_next are now __rcu tagged and corresponding rcu APIs are used when manipulating them. 2. For fn->rr_ptr, first of all, it also needs to be rcu protected now and is tagged with __rcu and rcu APIs are used in corresponding places. Secondly, fn->rr_ptr is changed in rt6_select() which is a reader thread. This makes the issue a bit complicated. We think a valid solution for it is to let rt6_select() grab the tb6_lock if it decides to change it. As it is not in the normal operation and only happens when there is no valid neighbor cache for the route, we think the performance impact should be low. 3. fib6_walk_continue() has to be called with tb6_lock held even in the route dumping related functions, e.g. inet6_dump_fib(), fib6_tables_dump() and ipv6_route_seq_ops. It is because fib6_walk_continue() makes modifications to the walker structure, and so are fib6_repair_tree() and fib6_del_route(). In order to do proper syncing between them, we need to let fib6_walk_continue() hold the lock. We may be able to do further improvement on the way we do the tree walk to get rid of the need for holding the spin lock. But not for now. 4. When fib6_del_route() removes a route from the tree, we no longer mark rt->dst.rt6_next to NULL to make simultaneous reader be able to further traverse the list with rcu. However, rt->dst.rt6_next is only valid within this same rcu period. No one should access it later. 5. All the operation of atomic_inc(rt->rt6i_ref) is changed to be performed before we publish this route (either by linking it to fn->leaf or insert it in the list pointed by fn->leaf) just to be safe because as soon as we publish the route, some read thread will be able to access it. Signed-off-by: Wei Wang <weiwan@google.com> Signed-off-by: Martin KaFai Lau <kafai@fb.com> Signed-off-by: Eric Dumazet <edumazet@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-10-07 02:06:10 +07:00
#define for_each_fib6_node_rt_rcu(fn) \
for (rt = rcu_dereference((fn)->leaf); rt; \
rt = rcu_dereference(rt->fib6_next))
ipv6: replace rwlock with rcu and spinlock in fib6_table With all the preparation work before, we are now ready to replace rwlock with rcu and spinlock in fib6_table. That means now all fib6_node in fib6_table are protected by rcu. And when freeing fib6_node, call_rcu() is used to wait for the rcu grace period before releasing the memory. When accessing fib6_node, corresponding rcu APIs need to be used. And all previous sessions protected by the write lock will now be protected by the spin lock per table. All previous sessions protected by read lock will now be protected by rcu_read_lock(). A couple of things to note here: 1. As part of the work of replacing rwlock with rcu, the linked list of fn->leaf now has to be rcu protected as well. So both fn->leaf and rt->dst.rt6_next are now __rcu tagged and corresponding rcu APIs are used when manipulating them. 2. For fn->rr_ptr, first of all, it also needs to be rcu protected now and is tagged with __rcu and rcu APIs are used in corresponding places. Secondly, fn->rr_ptr is changed in rt6_select() which is a reader thread. This makes the issue a bit complicated. We think a valid solution for it is to let rt6_select() grab the tb6_lock if it decides to change it. As it is not in the normal operation and only happens when there is no valid neighbor cache for the route, we think the performance impact should be low. 3. fib6_walk_continue() has to be called with tb6_lock held even in the route dumping related functions, e.g. inet6_dump_fib(), fib6_tables_dump() and ipv6_route_seq_ops. It is because fib6_walk_continue() makes modifications to the walker structure, and so are fib6_repair_tree() and fib6_del_route(). In order to do proper syncing between them, we need to let fib6_walk_continue() hold the lock. We may be able to do further improvement on the way we do the tree walk to get rid of the need for holding the spin lock. But not for now. 4. When fib6_del_route() removes a route from the tree, we no longer mark rt->dst.rt6_next to NULL to make simultaneous reader be able to further traverse the list with rcu. However, rt->dst.rt6_next is only valid within this same rcu period. No one should access it later. 5. All the operation of atomic_inc(rt->rt6i_ref) is changed to be performed before we publish this route (either by linking it to fn->leaf or insert it in the list pointed by fn->leaf) just to be safe because as soon as we publish the route, some read thread will be able to access it. Signed-off-by: Wei Wang <weiwan@google.com> Signed-off-by: Martin KaFai Lau <kafai@fb.com> Signed-off-by: Eric Dumazet <edumazet@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-10-07 02:06:10 +07:00
#define for_each_fib6_walker_rt(w) \
for (rt = (w)->leaf; rt; \
rt = rcu_dereference_protected(rt->fib6_next, 1))
ipv6: replace rwlock with rcu and spinlock in fib6_table With all the preparation work before, we are now ready to replace rwlock with rcu and spinlock in fib6_table. That means now all fib6_node in fib6_table are protected by rcu. And when freeing fib6_node, call_rcu() is used to wait for the rcu grace period before releasing the memory. When accessing fib6_node, corresponding rcu APIs need to be used. And all previous sessions protected by the write lock will now be protected by the spin lock per table. All previous sessions protected by read lock will now be protected by rcu_read_lock(). A couple of things to note here: 1. As part of the work of replacing rwlock with rcu, the linked list of fn->leaf now has to be rcu protected as well. So both fn->leaf and rt->dst.rt6_next are now __rcu tagged and corresponding rcu APIs are used when manipulating them. 2. For fn->rr_ptr, first of all, it also needs to be rcu protected now and is tagged with __rcu and rcu APIs are used in corresponding places. Secondly, fn->rr_ptr is changed in rt6_select() which is a reader thread. This makes the issue a bit complicated. We think a valid solution for it is to let rt6_select() grab the tb6_lock if it decides to change it. As it is not in the normal operation and only happens when there is no valid neighbor cache for the route, we think the performance impact should be low. 3. fib6_walk_continue() has to be called with tb6_lock held even in the route dumping related functions, e.g. inet6_dump_fib(), fib6_tables_dump() and ipv6_route_seq_ops. It is because fib6_walk_continue() makes modifications to the walker structure, and so are fib6_repair_tree() and fib6_del_route(). In order to do proper syncing between them, we need to let fib6_walk_continue() hold the lock. We may be able to do further improvement on the way we do the tree walk to get rid of the need for holding the spin lock. But not for now. 4. When fib6_del_route() removes a route from the tree, we no longer mark rt->dst.rt6_next to NULL to make simultaneous reader be able to further traverse the list with rcu. However, rt->dst.rt6_next is only valid within this same rcu period. No one should access it later. 5. All the operation of atomic_inc(rt->rt6i_ref) is changed to be performed before we publish this route (either by linking it to fn->leaf or insert it in the list pointed by fn->leaf) just to be safe because as soon as we publish the route, some read thread will be able to access it. Signed-off-by: Wei Wang <weiwan@google.com> Signed-off-by: Martin KaFai Lau <kafai@fb.com> Signed-off-by: Eric Dumazet <edumazet@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-10-07 02:06:10 +07:00
static inline struct inet6_dev *ip6_dst_idev(struct dst_entry *dst)
{
return ((struct rt6_info *)dst)->rt6i_idev;
}
static inline void fib6_clean_expires(struct fib6_info *f6i)
{
f6i->fib6_flags &= ~RTF_EXPIRES;
f6i->expires = 0;
}
static inline void fib6_set_expires(struct fib6_info *f6i,
unsigned long expires)
{
f6i->expires = expires;
f6i->fib6_flags |= RTF_EXPIRES;
}
static inline bool fib6_check_expired(const struct fib6_info *f6i)
{
if (f6i->fib6_flags & RTF_EXPIRES)
return time_after(jiffies, f6i->expires);
return false;
}
/* Function to safely get fn->sernum for passed in rt
* and store result in passed in cookie.
* Return true if we can get cookie safely
* Return false if not
*/
static inline bool fib6_get_cookie_safe(const struct fib6_info *f6i,
u32 *cookie)
{
struct fib6_node *fn;
bool status = false;
fn = rcu_dereference(f6i->fib6_node);
if (fn) {
*cookie = fn->fn_sernum;
ipv6: update fn_sernum after route is inserted to tree fib6_add() logic currently calls fib6_add_1() to figure out what node should be used for the newly added route and then call fib6_add_rt2node() to insert the route to the node. And during the call of fib6_add_1(), fn_sernum is updated for all nodes that share the same prefix as the new route. This does not have issue in the current code because reader thread will not be able to access the tree while writer thread is inserting new route to it. However, it is not the case once we transition to use RCU. Reader thread could potentially see the new fn_sernum before the new route is inserted. As a result, reader thread's route lookup will return a stale route with the new fn_sernum. In order to solve this issue, we remove all the update of fn_sernum in fib6_add_1(), and instead, introduce a new function that updates fn_sernum for all related nodes and call this functions once the route is successfully inserted to the tree. Also, smp_wmb() is used after a route is successfully inserted into the fib tree and right before the updated of fn->sernum. And smp_rmb() is used right after fn->sernum is accessed in rt6_get_cookie_safe(). This is to guarantee that when the reader thread sees the new fn->sernum, the new route is already inserted in the tree in memory. Signed-off-by: Wei Wang <weiwan@google.com> Signed-off-by: Martin KaFai Lau <kafai@fb.com> Signed-off-by: Eric Dumazet <edumazet@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-10-07 02:06:07 +07:00
/* pairs with smp_wmb() in fib6_update_sernum_upto_root() */
smp_rmb();
status = true;
}
return status;
}
static inline u32 rt6_get_cookie(const struct rt6_info *rt)
{
struct fib6_info *from;
u32 cookie = 0;
rcu_read_lock();
from = rcu_dereference(rt->from);
if (from && (rt->rt6i_flags & RTF_PCPU ||
unlikely(!list_empty(&rt->rt6i_uncached))))
fib6_get_cookie_safe(from, &cookie);
rcu_read_unlock();
return cookie;
}
static inline void ip6_rt_put(struct rt6_info *rt)
{
/* dst_release() accepts a NULL parameter.
* We rely on dst being first structure in struct rt6_info
*/
BUILD_BUG_ON(offsetof(struct rt6_info, dst) != 0);
dst_release(&rt->dst);
}
struct fib6_info *fib6_info_alloc(gfp_t gfp_flags);
net/ipv6: respect rcu grace period before freeing fib6_info syzbot reported use after free that is caused by fib6_info being freed without a proper RCU grace period. CPU: 0 PID: 1407 Comm: udevd Not tainted 4.17.0+ #39 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 Call Trace: <IRQ> __dump_stack lib/dump_stack.c:77 [inline] dump_stack+0x1b9/0x294 lib/dump_stack.c:113 print_address_description+0x6c/0x20b mm/kasan/report.c:256 kasan_report_error mm/kasan/report.c:354 [inline] kasan_report.cold.7+0x242/0x2fe mm/kasan/report.c:412 __asan_report_load8_noabort+0x14/0x20 mm/kasan/report.c:433 __read_once_size include/linux/compiler.h:188 [inline] find_rr_leaf net/ipv6/route.c:705 [inline] rt6_select net/ipv6/route.c:761 [inline] fib6_table_lookup+0x12b7/0x14d0 net/ipv6/route.c:1823 ip6_pol_route+0x1c2/0x1020 net/ipv6/route.c:1856 ip6_pol_route_output+0x54/0x70 net/ipv6/route.c:2082 fib6_rule_lookup+0x211/0x6d0 net/ipv6/fib6_rules.c:122 ip6_route_output_flags+0x2c5/0x350 net/ipv6/route.c:2110 ip6_route_output include/net/ip6_route.h:82 [inline] icmpv6_xrlim_allow net/ipv6/icmp.c:211 [inline] icmp6_send+0x147c/0x2da0 net/ipv6/icmp.c:535 icmpv6_send+0x17a/0x300 net/ipv6/ip6_icmp.c:43 ip6_link_failure+0xa5/0x790 net/ipv6/route.c:2244 dst_link_failure include/net/dst.h:427 [inline] ndisc_error_report+0xd1/0x1c0 net/ipv6/ndisc.c:695 neigh_invalidate+0x246/0x550 net/core/neighbour.c:892 neigh_timer_handler+0xaf9/0xde0 net/core/neighbour.c:978 call_timer_fn+0x230/0x940 kernel/time/timer.c:1326 expire_timers kernel/time/timer.c:1363 [inline] __run_timers+0x79e/0xc50 kernel/time/timer.c:1666 run_timer_softirq+0x4c/0x70 kernel/time/timer.c:1692 __do_softirq+0x2e0/0xaf5 kernel/softirq.c:284 invoke_softirq kernel/softirq.c:364 [inline] irq_exit+0x1d1/0x200 kernel/softirq.c:404 exiting_irq arch/x86/include/asm/apic.h:527 [inline] smp_apic_timer_interrupt+0x17e/0x710 arch/x86/kernel/apic/apic.c:1052 apic_timer_interrupt+0xf/0x20 arch/x86/entry/entry_64.S:863 </IRQ> RIP: 0010:strlen+0x5e/0xa0 lib/string.c:482 Code: 24 00 74 3b 48 bb 00 00 00 00 00 fc ff df 4c 89 e0 48 83 c0 01 48 89 c2 48 89 c1 48 c1 ea 03 83 e1 07 0f b6 14 1a 38 ca 7f 04 <84> d2 75 23 80 38 00 75 de 48 83 c4 08 4c 29 e0 5b 41 5c 5d c3 48 RSP: 0018:ffff8801af117850 EFLAGS: 00000246 ORIG_RAX: ffffffffffffff13 RAX: ffff880197f53bd0 RBX: dffffc0000000000 RCX: 0000000000000000 RDX: 0000000000000000 RSI: ffffffff81c5b06c RDI: ffff880197f53bc0 RBP: ffff8801af117868 R08: ffff88019a976540 R09: 0000000000000000 R10: ffff88019a976540 R11: 0000000000000000 R12: ffff880197f53bc0 R13: ffff880197f53bc0 R14: ffffffff899e4e90 R15: ffff8801d91c6a00 strlen include/linux/string.h:267 [inline] getname_kernel+0x24/0x370 fs/namei.c:218 open_exec+0x17/0x70 fs/exec.c:882 load_elf_binary+0x968/0x5610 fs/binfmt_elf.c:780 search_binary_handler+0x17d/0x570 fs/exec.c:1653 exec_binprm fs/exec.c:1695 [inline] __do_execve_file.isra.35+0x16fe/0x2710 fs/exec.c:1819 do_execveat_common fs/exec.c:1866 [inline] do_execve fs/exec.c:1883 [inline] __do_sys_execve fs/exec.c:1964 [inline] __se_sys_execve fs/exec.c:1959 [inline] __x64_sys_execve+0x8f/0xc0 fs/exec.c:1959 do_syscall_64+0x1b1/0x800 arch/x86/entry/common.c:290 entry_SYSCALL_64_after_hwframe+0x49/0xbe RIP: 0033:0x7f1576a46207 Code: 77 19 f4 48 89 d7 44 89 c0 0f 05 48 3d 00 f0 ff ff 76 e0 f7 d8 64 41 89 01 eb d8 f7 d8 64 41 89 01 eb df b8 3b 00 00 00 0f 05 <48> 3d 00 f0 ff ff 77 02 f3 c3 48 8b 15 00 8c 2d 00 f7 d8 64 89 02 RSP: 002b:00007ffff2784568 EFLAGS: 00000202 ORIG_RAX: 000000000000003b RAX: ffffffffffffffda RBX: 00000000ffffffff RCX: 00007f1576a46207 RDX: 0000000001215b10 RSI: 00007ffff2784660 RDI: 00007ffff2785670 RBP: 0000000000625500 R08: 000000000000589c R09: 000000000000589c R10: 0000000000000000 R11: 0000000000000202 R12: 0000000001215b10 R13: 0000000000000007 R14: 0000000001204250 R15: 0000000000000005 Allocated by task 12188: save_stack+0x43/0xd0 mm/kasan/kasan.c:448 set_track mm/kasan/kasan.c:460 [inline] kasan_kmalloc+0xc4/0xe0 mm/kasan/kasan.c:553 kmem_cache_alloc_trace+0x152/0x780 mm/slab.c:3620 kmalloc include/linux/slab.h:513 [inline] kzalloc include/linux/slab.h:706 [inline] fib6_info_alloc+0xbb/0x280 net/ipv6/ip6_fib.c:152 ip6_route_info_create+0x782/0x2b50 net/ipv6/route.c:3013 ip6_route_add+0x23/0xb0 net/ipv6/route.c:3154 ipv6_route_ioctl+0x5a5/0x760 net/ipv6/route.c:3660 inet6_ioctl+0x100/0x1f0 net/ipv6/af_inet6.c:546 sock_do_ioctl+0xe4/0x3e0 net/socket.c:973 sock_ioctl+0x30d/0x680 net/socket.c:1097 vfs_ioctl fs/ioctl.c:46 [inline] file_ioctl fs/ioctl.c:500 [inline] do_vfs_ioctl+0x1cf/0x16f0 fs/ioctl.c:684 ksys_ioctl+0xa9/0xd0 fs/ioctl.c:701 __do_sys_ioctl fs/ioctl.c:708 [inline] __se_sys_ioctl fs/ioctl.c:706 [inline] __x64_sys_ioctl+0x73/0xb0 fs/ioctl.c:706 do_syscall_64+0x1b1/0x800 arch/x86/entry/common.c:290 entry_SYSCALL_64_after_hwframe+0x49/0xbe Freed by task 1402: save_stack+0x43/0xd0 mm/kasan/kasan.c:448 set_track mm/kasan/kasan.c:460 [inline] __kasan_slab_free+0x11a/0x170 mm/kasan/kasan.c:521 kasan_slab_free+0xe/0x10 mm/kasan/kasan.c:528 __cache_free mm/slab.c:3498 [inline] kfree+0xd9/0x260 mm/slab.c:3813 fib6_info_destroy+0x29b/0x350 net/ipv6/ip6_fib.c:207 fib6_info_release include/net/ip6_fib.h:286 [inline] __ip6_del_rt_siblings net/ipv6/route.c:3235 [inline] ip6_route_del+0x11c4/0x13b0 net/ipv6/route.c:3316 ipv6_route_ioctl+0x616/0x760 net/ipv6/route.c:3663 inet6_ioctl+0x100/0x1f0 net/ipv6/af_inet6.c:546 sock_do_ioctl+0xe4/0x3e0 net/socket.c:973 sock_ioctl+0x30d/0x680 net/socket.c:1097 vfs_ioctl fs/ioctl.c:46 [inline] file_ioctl fs/ioctl.c:500 [inline] do_vfs_ioctl+0x1cf/0x16f0 fs/ioctl.c:684 ksys_ioctl+0xa9/0xd0 fs/ioctl.c:701 __do_sys_ioctl fs/ioctl.c:708 [inline] __se_sys_ioctl fs/ioctl.c:706 [inline] __x64_sys_ioctl+0x73/0xb0 fs/ioctl.c:706 do_syscall_64+0x1b1/0x800 arch/x86/entry/common.c:290 entry_SYSCALL_64_after_hwframe+0x49/0xbe The buggy address belongs to the object at ffff8801b5df2580 which belongs to the cache kmalloc-256 of size 256 The buggy address is located 8 bytes inside of 256-byte region [ffff8801b5df2580, ffff8801b5df2680) The buggy address belongs to the page: page:ffffea0006d77c80 count:1 mapcount:0 mapping:ffff8801da8007c0 index:0xffff8801b5df2e40 flags: 0x2fffc0000000100(slab) raw: 02fffc0000000100 ffffea0006c5cc48 ffffea0007363308 ffff8801da8007c0 raw: ffff8801b5df2e40 ffff8801b5df2080 0000000100000006 0000000000000000 page dumped because: kasan: bad access detected Memory state around the buggy address: ffff8801b5df2480: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb ffff8801b5df2500: fb fb fb fb fb fb fb fb fc fc fc fc fc fc fc fc > ffff8801b5df2580: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb ^ ffff8801b5df2600: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb ffff8801b5df2680: fc fc fc fc fc fc fc fc fb fb fb fb fb fb fb fb Fixes: a64efe142f5e ("net/ipv6: introduce fib6_info struct and helpers") Signed-off-by: Eric Dumazet <edumazet@google.com> Cc: David Ahern <dsahern@gmail.com> Reported-by: syzbot+9e6d75e3edef427ee888@syzkaller.appspotmail.com Acked-by: David Ahern <dsahern@gmail.com> Tested-by: David Ahern <dsahern@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-06-18 19:24:31 +07:00
void fib6_info_destroy_rcu(struct rcu_head *head);
static inline void fib6_info_hold(struct fib6_info *f6i)
{
refcount_inc(&f6i->fib6_ref);
}
ipv6: use fib6_info_hold_safe() when necessary In the code path where only rcu read lock is held, e.g. in the route lookup code path, it is not safe to directly call fib6_info_hold() because the fib6_info may already have been deleted but still exists in the rcu grace period. Holding reference to it could cause double free and crash the kernel. This patch adds a new function fib6_info_hold_safe() and replace fib6_info_hold() in all necessary places. Syzbot reported 3 crash traces because of this. One of them is: 8021q: adding VLAN 0 to HW filter on device team0 IPv6: ADDRCONF(NETDEV_CHANGE): team0: link becomes ready dst_release: dst:(____ptrval____) refcnt:-1 dst_release: dst:(____ptrval____) refcnt:-2 WARNING: CPU: 1 PID: 4845 at include/net/dst.h:239 dst_hold include/net/dst.h:239 [inline] WARNING: CPU: 1 PID: 4845 at include/net/dst.h:239 ip6_setup_cork+0xd66/0x1830 net/ipv6/ip6_output.c:1204 dst_release: dst:(____ptrval____) refcnt:-1 Kernel panic - not syncing: panic_on_warn set ... CPU: 1 PID: 4845 Comm: syz-executor493 Not tainted 4.18.0-rc3+ #10 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 Call Trace: __dump_stack lib/dump_stack.c:77 [inline] dump_stack+0x1c9/0x2b4 lib/dump_stack.c:113 panic+0x238/0x4e7 kernel/panic.c:184 dst_release: dst:(____ptrval____) refcnt:-2 dst_release: dst:(____ptrval____) refcnt:-3 __warn.cold.8+0x163/0x1ba kernel/panic.c:536 dst_release: dst:(____ptrval____) refcnt:-4 report_bug+0x252/0x2d0 lib/bug.c:186 fixup_bug arch/x86/kernel/traps.c:178 [inline] do_error_trap+0x1fc/0x4d0 arch/x86/kernel/traps.c:296 dst_release: dst:(____ptrval____) refcnt:-5 do_invalid_op+0x1b/0x20 arch/x86/kernel/traps.c:316 invalid_op+0x14/0x20 arch/x86/entry/entry_64.S:992 RIP: 0010:dst_hold include/net/dst.h:239 [inline] RIP: 0010:ip6_setup_cork+0xd66/0x1830 net/ipv6/ip6_output.c:1204 Code: c1 ed 03 89 9d 18 ff ff ff 48 b8 00 00 00 00 00 fc ff df 41 c6 44 05 00 f8 e9 2d 01 00 00 4c 8b a5 c8 fe ff ff e8 1a f6 e6 fa <0f> 0b e9 6a fc ff ff e8 0e f6 e6 fa 48 8b 85 d0 fe ff ff 48 8d 78 RSP: 0018:ffff8801a8fcf178 EFLAGS: 00010293 RAX: ffff8801a8eba5c0 RBX: 0000000000000000 RCX: ffffffff869511e6 RDX: 0000000000000000 RSI: ffffffff869515b6 RDI: 0000000000000005 RBP: ffff8801a8fcf2c8 R08: ffff8801a8eba5c0 R09: ffffed0035ac8338 R10: ffffed0035ac8338 R11: ffff8801ad6419c3 R12: ffff8801a8fcf720 R13: ffff8801a8fcf6a0 R14: ffff8801ad6419c0 R15: ffff8801ad641980 ip6_make_skb+0x2c8/0x600 net/ipv6/ip6_output.c:1768 udpv6_sendmsg+0x2c90/0x35f0 net/ipv6/udp.c:1376 inet_sendmsg+0x1a1/0x690 net/ipv4/af_inet.c:798 sock_sendmsg_nosec net/socket.c:641 [inline] sock_sendmsg+0xd5/0x120 net/socket.c:651 ___sys_sendmsg+0x51d/0x930 net/socket.c:2125 __sys_sendmmsg+0x240/0x6f0 net/socket.c:2220 __do_sys_sendmmsg net/socket.c:2249 [inline] __se_sys_sendmmsg net/socket.c:2246 [inline] __x64_sys_sendmmsg+0x9d/0x100 net/socket.c:2246 do_syscall_64+0x1b9/0x820 arch/x86/entry/common.c:290 entry_SYSCALL_64_after_hwframe+0x49/0xbe RIP: 0033:0x446ba9 Code: e8 cc bb 02 00 48 83 c4 18 c3 0f 1f 80 00 00 00 00 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 0f 83 eb 08 fc ff c3 66 2e 0f 1f 84 00 00 00 00 RSP: 002b:00007fb39a469da8 EFLAGS: 00000246 ORIG_RAX: 0000000000000133 RAX: ffffffffffffffda RBX: 00000000006dcc54 RCX: 0000000000446ba9 RDX: 00000000000000b8 RSI: 0000000020001b00 RDI: 0000000000000003 RBP: 00000000006dcc50 R08: 00007fb39a46a700 R09: 0000000000000000 R10: 0000000000000000 R11: 0000000000000246 R12: 45c828efc7a64843 R13: e6eeb815b9d8a477 R14: 5068caf6f713c6fc R15: 0000000000000001 Dumping ftrace buffer: (ftrace buffer empty) Kernel Offset: disabled Rebooting in 86400 seconds.. Fixes: 93531c674315 ("net/ipv6: separate handling of FIB entries from dst based routes") Reported-by: syzbot+902e2a1bcd4f7808cef5@syzkaller.appspotmail.com Reported-by: syzbot+8ae62d67f647abeeceb9@syzkaller.appspotmail.com Reported-by: syzbot+3f08feb14086930677d0@syzkaller.appspotmail.com Signed-off-by: Wei Wang <weiwan@google.com> Acked-by: Eric Dumazet <edumazet@google.com> Reviewed-by: David Ahern <dsahern@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-07-22 10:56:32 +07:00
static inline bool fib6_info_hold_safe(struct fib6_info *f6i)
{
return refcount_inc_not_zero(&f6i->fib6_ref);
ipv6: use fib6_info_hold_safe() when necessary In the code path where only rcu read lock is held, e.g. in the route lookup code path, it is not safe to directly call fib6_info_hold() because the fib6_info may already have been deleted but still exists in the rcu grace period. Holding reference to it could cause double free and crash the kernel. This patch adds a new function fib6_info_hold_safe() and replace fib6_info_hold() in all necessary places. Syzbot reported 3 crash traces because of this. One of them is: 8021q: adding VLAN 0 to HW filter on device team0 IPv6: ADDRCONF(NETDEV_CHANGE): team0: link becomes ready dst_release: dst:(____ptrval____) refcnt:-1 dst_release: dst:(____ptrval____) refcnt:-2 WARNING: CPU: 1 PID: 4845 at include/net/dst.h:239 dst_hold include/net/dst.h:239 [inline] WARNING: CPU: 1 PID: 4845 at include/net/dst.h:239 ip6_setup_cork+0xd66/0x1830 net/ipv6/ip6_output.c:1204 dst_release: dst:(____ptrval____) refcnt:-1 Kernel panic - not syncing: panic_on_warn set ... CPU: 1 PID: 4845 Comm: syz-executor493 Not tainted 4.18.0-rc3+ #10 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 Call Trace: __dump_stack lib/dump_stack.c:77 [inline] dump_stack+0x1c9/0x2b4 lib/dump_stack.c:113 panic+0x238/0x4e7 kernel/panic.c:184 dst_release: dst:(____ptrval____) refcnt:-2 dst_release: dst:(____ptrval____) refcnt:-3 __warn.cold.8+0x163/0x1ba kernel/panic.c:536 dst_release: dst:(____ptrval____) refcnt:-4 report_bug+0x252/0x2d0 lib/bug.c:186 fixup_bug arch/x86/kernel/traps.c:178 [inline] do_error_trap+0x1fc/0x4d0 arch/x86/kernel/traps.c:296 dst_release: dst:(____ptrval____) refcnt:-5 do_invalid_op+0x1b/0x20 arch/x86/kernel/traps.c:316 invalid_op+0x14/0x20 arch/x86/entry/entry_64.S:992 RIP: 0010:dst_hold include/net/dst.h:239 [inline] RIP: 0010:ip6_setup_cork+0xd66/0x1830 net/ipv6/ip6_output.c:1204 Code: c1 ed 03 89 9d 18 ff ff ff 48 b8 00 00 00 00 00 fc ff df 41 c6 44 05 00 f8 e9 2d 01 00 00 4c 8b a5 c8 fe ff ff e8 1a f6 e6 fa <0f> 0b e9 6a fc ff ff e8 0e f6 e6 fa 48 8b 85 d0 fe ff ff 48 8d 78 RSP: 0018:ffff8801a8fcf178 EFLAGS: 00010293 RAX: ffff8801a8eba5c0 RBX: 0000000000000000 RCX: ffffffff869511e6 RDX: 0000000000000000 RSI: ffffffff869515b6 RDI: 0000000000000005 RBP: ffff8801a8fcf2c8 R08: ffff8801a8eba5c0 R09: ffffed0035ac8338 R10: ffffed0035ac8338 R11: ffff8801ad6419c3 R12: ffff8801a8fcf720 R13: ffff8801a8fcf6a0 R14: ffff8801ad6419c0 R15: ffff8801ad641980 ip6_make_skb+0x2c8/0x600 net/ipv6/ip6_output.c:1768 udpv6_sendmsg+0x2c90/0x35f0 net/ipv6/udp.c:1376 inet_sendmsg+0x1a1/0x690 net/ipv4/af_inet.c:798 sock_sendmsg_nosec net/socket.c:641 [inline] sock_sendmsg+0xd5/0x120 net/socket.c:651 ___sys_sendmsg+0x51d/0x930 net/socket.c:2125 __sys_sendmmsg+0x240/0x6f0 net/socket.c:2220 __do_sys_sendmmsg net/socket.c:2249 [inline] __se_sys_sendmmsg net/socket.c:2246 [inline] __x64_sys_sendmmsg+0x9d/0x100 net/socket.c:2246 do_syscall_64+0x1b9/0x820 arch/x86/entry/common.c:290 entry_SYSCALL_64_after_hwframe+0x49/0xbe RIP: 0033:0x446ba9 Code: e8 cc bb 02 00 48 83 c4 18 c3 0f 1f 80 00 00 00 00 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 0f 83 eb 08 fc ff c3 66 2e 0f 1f 84 00 00 00 00 RSP: 002b:00007fb39a469da8 EFLAGS: 00000246 ORIG_RAX: 0000000000000133 RAX: ffffffffffffffda RBX: 00000000006dcc54 RCX: 0000000000446ba9 RDX: 00000000000000b8 RSI: 0000000020001b00 RDI: 0000000000000003 RBP: 00000000006dcc50 R08: 00007fb39a46a700 R09: 0000000000000000 R10: 0000000000000000 R11: 0000000000000246 R12: 45c828efc7a64843 R13: e6eeb815b9d8a477 R14: 5068caf6f713c6fc R15: 0000000000000001 Dumping ftrace buffer: (ftrace buffer empty) Kernel Offset: disabled Rebooting in 86400 seconds.. Fixes: 93531c674315 ("net/ipv6: separate handling of FIB entries from dst based routes") Reported-by: syzbot+902e2a1bcd4f7808cef5@syzkaller.appspotmail.com Reported-by: syzbot+8ae62d67f647abeeceb9@syzkaller.appspotmail.com Reported-by: syzbot+3f08feb14086930677d0@syzkaller.appspotmail.com Signed-off-by: Wei Wang <weiwan@google.com> Acked-by: Eric Dumazet <edumazet@google.com> Reviewed-by: David Ahern <dsahern@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-07-22 10:56:32 +07:00
}
static inline void fib6_info_release(struct fib6_info *f6i)
{
if (f6i && refcount_dec_and_test(&f6i->fib6_ref))
net/ipv6: respect rcu grace period before freeing fib6_info syzbot reported use after free that is caused by fib6_info being freed without a proper RCU grace period. CPU: 0 PID: 1407 Comm: udevd Not tainted 4.17.0+ #39 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 Call Trace: <IRQ> __dump_stack lib/dump_stack.c:77 [inline] dump_stack+0x1b9/0x294 lib/dump_stack.c:113 print_address_description+0x6c/0x20b mm/kasan/report.c:256 kasan_report_error mm/kasan/report.c:354 [inline] kasan_report.cold.7+0x242/0x2fe mm/kasan/report.c:412 __asan_report_load8_noabort+0x14/0x20 mm/kasan/report.c:433 __read_once_size include/linux/compiler.h:188 [inline] find_rr_leaf net/ipv6/route.c:705 [inline] rt6_select net/ipv6/route.c:761 [inline] fib6_table_lookup+0x12b7/0x14d0 net/ipv6/route.c:1823 ip6_pol_route+0x1c2/0x1020 net/ipv6/route.c:1856 ip6_pol_route_output+0x54/0x70 net/ipv6/route.c:2082 fib6_rule_lookup+0x211/0x6d0 net/ipv6/fib6_rules.c:122 ip6_route_output_flags+0x2c5/0x350 net/ipv6/route.c:2110 ip6_route_output include/net/ip6_route.h:82 [inline] icmpv6_xrlim_allow net/ipv6/icmp.c:211 [inline] icmp6_send+0x147c/0x2da0 net/ipv6/icmp.c:535 icmpv6_send+0x17a/0x300 net/ipv6/ip6_icmp.c:43 ip6_link_failure+0xa5/0x790 net/ipv6/route.c:2244 dst_link_failure include/net/dst.h:427 [inline] ndisc_error_report+0xd1/0x1c0 net/ipv6/ndisc.c:695 neigh_invalidate+0x246/0x550 net/core/neighbour.c:892 neigh_timer_handler+0xaf9/0xde0 net/core/neighbour.c:978 call_timer_fn+0x230/0x940 kernel/time/timer.c:1326 expire_timers kernel/time/timer.c:1363 [inline] __run_timers+0x79e/0xc50 kernel/time/timer.c:1666 run_timer_softirq+0x4c/0x70 kernel/time/timer.c:1692 __do_softirq+0x2e0/0xaf5 kernel/softirq.c:284 invoke_softirq kernel/softirq.c:364 [inline] irq_exit+0x1d1/0x200 kernel/softirq.c:404 exiting_irq arch/x86/include/asm/apic.h:527 [inline] smp_apic_timer_interrupt+0x17e/0x710 arch/x86/kernel/apic/apic.c:1052 apic_timer_interrupt+0xf/0x20 arch/x86/entry/entry_64.S:863 </IRQ> RIP: 0010:strlen+0x5e/0xa0 lib/string.c:482 Code: 24 00 74 3b 48 bb 00 00 00 00 00 fc ff df 4c 89 e0 48 83 c0 01 48 89 c2 48 89 c1 48 c1 ea 03 83 e1 07 0f b6 14 1a 38 ca 7f 04 <84> d2 75 23 80 38 00 75 de 48 83 c4 08 4c 29 e0 5b 41 5c 5d c3 48 RSP: 0018:ffff8801af117850 EFLAGS: 00000246 ORIG_RAX: ffffffffffffff13 RAX: ffff880197f53bd0 RBX: dffffc0000000000 RCX: 0000000000000000 RDX: 0000000000000000 RSI: ffffffff81c5b06c RDI: ffff880197f53bc0 RBP: ffff8801af117868 R08: ffff88019a976540 R09: 0000000000000000 R10: ffff88019a976540 R11: 0000000000000000 R12: ffff880197f53bc0 R13: ffff880197f53bc0 R14: ffffffff899e4e90 R15: ffff8801d91c6a00 strlen include/linux/string.h:267 [inline] getname_kernel+0x24/0x370 fs/namei.c:218 open_exec+0x17/0x70 fs/exec.c:882 load_elf_binary+0x968/0x5610 fs/binfmt_elf.c:780 search_binary_handler+0x17d/0x570 fs/exec.c:1653 exec_binprm fs/exec.c:1695 [inline] __do_execve_file.isra.35+0x16fe/0x2710 fs/exec.c:1819 do_execveat_common fs/exec.c:1866 [inline] do_execve fs/exec.c:1883 [inline] __do_sys_execve fs/exec.c:1964 [inline] __se_sys_execve fs/exec.c:1959 [inline] __x64_sys_execve+0x8f/0xc0 fs/exec.c:1959 do_syscall_64+0x1b1/0x800 arch/x86/entry/common.c:290 entry_SYSCALL_64_after_hwframe+0x49/0xbe RIP: 0033:0x7f1576a46207 Code: 77 19 f4 48 89 d7 44 89 c0 0f 05 48 3d 00 f0 ff ff 76 e0 f7 d8 64 41 89 01 eb d8 f7 d8 64 41 89 01 eb df b8 3b 00 00 00 0f 05 <48> 3d 00 f0 ff ff 77 02 f3 c3 48 8b 15 00 8c 2d 00 f7 d8 64 89 02 RSP: 002b:00007ffff2784568 EFLAGS: 00000202 ORIG_RAX: 000000000000003b RAX: ffffffffffffffda RBX: 00000000ffffffff RCX: 00007f1576a46207 RDX: 0000000001215b10 RSI: 00007ffff2784660 RDI: 00007ffff2785670 RBP: 0000000000625500 R08: 000000000000589c R09: 000000000000589c R10: 0000000000000000 R11: 0000000000000202 R12: 0000000001215b10 R13: 0000000000000007 R14: 0000000001204250 R15: 0000000000000005 Allocated by task 12188: save_stack+0x43/0xd0 mm/kasan/kasan.c:448 set_track mm/kasan/kasan.c:460 [inline] kasan_kmalloc+0xc4/0xe0 mm/kasan/kasan.c:553 kmem_cache_alloc_trace+0x152/0x780 mm/slab.c:3620 kmalloc include/linux/slab.h:513 [inline] kzalloc include/linux/slab.h:706 [inline] fib6_info_alloc+0xbb/0x280 net/ipv6/ip6_fib.c:152 ip6_route_info_create+0x782/0x2b50 net/ipv6/route.c:3013 ip6_route_add+0x23/0xb0 net/ipv6/route.c:3154 ipv6_route_ioctl+0x5a5/0x760 net/ipv6/route.c:3660 inet6_ioctl+0x100/0x1f0 net/ipv6/af_inet6.c:546 sock_do_ioctl+0xe4/0x3e0 net/socket.c:973 sock_ioctl+0x30d/0x680 net/socket.c:1097 vfs_ioctl fs/ioctl.c:46 [inline] file_ioctl fs/ioctl.c:500 [inline] do_vfs_ioctl+0x1cf/0x16f0 fs/ioctl.c:684 ksys_ioctl+0xa9/0xd0 fs/ioctl.c:701 __do_sys_ioctl fs/ioctl.c:708 [inline] __se_sys_ioctl fs/ioctl.c:706 [inline] __x64_sys_ioctl+0x73/0xb0 fs/ioctl.c:706 do_syscall_64+0x1b1/0x800 arch/x86/entry/common.c:290 entry_SYSCALL_64_after_hwframe+0x49/0xbe Freed by task 1402: save_stack+0x43/0xd0 mm/kasan/kasan.c:448 set_track mm/kasan/kasan.c:460 [inline] __kasan_slab_free+0x11a/0x170 mm/kasan/kasan.c:521 kasan_slab_free+0xe/0x10 mm/kasan/kasan.c:528 __cache_free mm/slab.c:3498 [inline] kfree+0xd9/0x260 mm/slab.c:3813 fib6_info_destroy+0x29b/0x350 net/ipv6/ip6_fib.c:207 fib6_info_release include/net/ip6_fib.h:286 [inline] __ip6_del_rt_siblings net/ipv6/route.c:3235 [inline] ip6_route_del+0x11c4/0x13b0 net/ipv6/route.c:3316 ipv6_route_ioctl+0x616/0x760 net/ipv6/route.c:3663 inet6_ioctl+0x100/0x1f0 net/ipv6/af_inet6.c:546 sock_do_ioctl+0xe4/0x3e0 net/socket.c:973 sock_ioctl+0x30d/0x680 net/socket.c:1097 vfs_ioctl fs/ioctl.c:46 [inline] file_ioctl fs/ioctl.c:500 [inline] do_vfs_ioctl+0x1cf/0x16f0 fs/ioctl.c:684 ksys_ioctl+0xa9/0xd0 fs/ioctl.c:701 __do_sys_ioctl fs/ioctl.c:708 [inline] __se_sys_ioctl fs/ioctl.c:706 [inline] __x64_sys_ioctl+0x73/0xb0 fs/ioctl.c:706 do_syscall_64+0x1b1/0x800 arch/x86/entry/common.c:290 entry_SYSCALL_64_after_hwframe+0x49/0xbe The buggy address belongs to the object at ffff8801b5df2580 which belongs to the cache kmalloc-256 of size 256 The buggy address is located 8 bytes inside of 256-byte region [ffff8801b5df2580, ffff8801b5df2680) The buggy address belongs to the page: page:ffffea0006d77c80 count:1 mapcount:0 mapping:ffff8801da8007c0 index:0xffff8801b5df2e40 flags: 0x2fffc0000000100(slab) raw: 02fffc0000000100 ffffea0006c5cc48 ffffea0007363308 ffff8801da8007c0 raw: ffff8801b5df2e40 ffff8801b5df2080 0000000100000006 0000000000000000 page dumped because: kasan: bad access detected Memory state around the buggy address: ffff8801b5df2480: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb ffff8801b5df2500: fb fb fb fb fb fb fb fb fc fc fc fc fc fc fc fc > ffff8801b5df2580: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb ^ ffff8801b5df2600: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb ffff8801b5df2680: fc fc fc fc fc fc fc fc fb fb fb fb fb fb fb fb Fixes: a64efe142f5e ("net/ipv6: introduce fib6_info struct and helpers") Signed-off-by: Eric Dumazet <edumazet@google.com> Cc: David Ahern <dsahern@gmail.com> Reported-by: syzbot+9e6d75e3edef427ee888@syzkaller.appspotmail.com Acked-by: David Ahern <dsahern@gmail.com> Tested-by: David Ahern <dsahern@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-06-18 19:24:31 +07:00
call_rcu(&f6i->rcu, fib6_info_destroy_rcu);
}
enum fib6_walk_state {
#ifdef CONFIG_IPV6_SUBTREES
FWS_S,
#endif
FWS_L,
FWS_R,
FWS_C,
FWS_U
};
struct fib6_walker {
struct list_head lh;
struct fib6_node *root, *node;
struct fib6_info *leaf;
enum fib6_walk_state state;
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 12:19:03 +07:00
unsigned int skip;
unsigned int count;
int (*func)(struct fib6_walker *);
void *args;
};
struct rt6_statistics {
__u32 fib_nodes; /* all fib6 nodes */
__u32 fib_route_nodes; /* intermediate nodes */
__u32 fib_rt_entries; /* rt entries in fib table */
__u32 fib_rt_cache; /* cached rt entries in exception table */
__u32 fib_discarded_routes; /* total number of routes delete */
/* The following stats are not protected by any lock */
atomic_t fib_rt_alloc; /* total number of routes alloced */
atomic_t fib_rt_uncache; /* rt entries in uncached list */
};
#define RTN_TL_ROOT 0x0001
#define RTN_ROOT 0x0002 /* tree root node */
#define RTN_RTINFO 0x0004 /* node with valid routing info */
/*
* priority levels (or metrics)
*
*/
struct fib6_table {
struct hlist_node tb6_hlist;
u32 tb6_id;
ipv6: replace rwlock with rcu and spinlock in fib6_table With all the preparation work before, we are now ready to replace rwlock with rcu and spinlock in fib6_table. That means now all fib6_node in fib6_table are protected by rcu. And when freeing fib6_node, call_rcu() is used to wait for the rcu grace period before releasing the memory. When accessing fib6_node, corresponding rcu APIs need to be used. And all previous sessions protected by the write lock will now be protected by the spin lock per table. All previous sessions protected by read lock will now be protected by rcu_read_lock(). A couple of things to note here: 1. As part of the work of replacing rwlock with rcu, the linked list of fn->leaf now has to be rcu protected as well. So both fn->leaf and rt->dst.rt6_next are now __rcu tagged and corresponding rcu APIs are used when manipulating them. 2. For fn->rr_ptr, first of all, it also needs to be rcu protected now and is tagged with __rcu and rcu APIs are used in corresponding places. Secondly, fn->rr_ptr is changed in rt6_select() which is a reader thread. This makes the issue a bit complicated. We think a valid solution for it is to let rt6_select() grab the tb6_lock if it decides to change it. As it is not in the normal operation and only happens when there is no valid neighbor cache for the route, we think the performance impact should be low. 3. fib6_walk_continue() has to be called with tb6_lock held even in the route dumping related functions, e.g. inet6_dump_fib(), fib6_tables_dump() and ipv6_route_seq_ops. It is because fib6_walk_continue() makes modifications to the walker structure, and so are fib6_repair_tree() and fib6_del_route(). In order to do proper syncing between them, we need to let fib6_walk_continue() hold the lock. We may be able to do further improvement on the way we do the tree walk to get rid of the need for holding the spin lock. But not for now. 4. When fib6_del_route() removes a route from the tree, we no longer mark rt->dst.rt6_next to NULL to make simultaneous reader be able to further traverse the list with rcu. However, rt->dst.rt6_next is only valid within this same rcu period. No one should access it later. 5. All the operation of atomic_inc(rt->rt6i_ref) is changed to be performed before we publish this route (either by linking it to fn->leaf or insert it in the list pointed by fn->leaf) just to be safe because as soon as we publish the route, some read thread will be able to access it. Signed-off-by: Wei Wang <weiwan@google.com> Signed-off-by: Martin KaFai Lau <kafai@fb.com> Signed-off-by: Eric Dumazet <edumazet@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-10-07 02:06:10 +07:00
spinlock_t tb6_lock;
struct fib6_node tb6_root;
struct inet_peer_base tb6_peers;
unsigned int flags;
unsigned int fib_seq;
#define RT6_TABLE_HAS_DFLT_ROUTER BIT(0)
};
#define RT6_TABLE_UNSPEC RT_TABLE_UNSPEC
#define RT6_TABLE_MAIN RT_TABLE_MAIN
#define RT6_TABLE_DFLT RT6_TABLE_MAIN
#define RT6_TABLE_INFO RT6_TABLE_MAIN
#define RT6_TABLE_PREFIX RT6_TABLE_MAIN
#ifdef CONFIG_IPV6_MULTIPLE_TABLES
#define FIB6_TABLE_MIN 1
#define FIB6_TABLE_MAX RT_TABLE_MAX
#define RT6_TABLE_LOCAL RT_TABLE_LOCAL
#else
#define FIB6_TABLE_MIN RT_TABLE_MAIN
#define FIB6_TABLE_MAX FIB6_TABLE_MIN
#define RT6_TABLE_LOCAL RT6_TABLE_MAIN
#endif
typedef struct rt6_info *(*pol_lookup_t)(struct net *,
struct fib6_table *,
struct flowi6 *,
const struct sk_buff *, int);
struct fib6_entry_notifier_info {
struct fib_notifier_info info; /* must be first */
struct fib6_info *rt;
};
/*
* exported functions
*/
struct fib6_table *fib6_get_table(struct net *net, u32 id);
struct fib6_table *fib6_new_table(struct net *net, u32 id);
struct dst_entry *fib6_rule_lookup(struct net *net, struct flowi6 *fl6,
const struct sk_buff *skb,
int flags, pol_lookup_t lookup);
/* called with rcu lock held; can return error pointer
* caller needs to select path
*/
int fib6_lookup(struct net *net, int oif, struct flowi6 *fl6,
struct fib6_result *res, int flags);
/* called with rcu lock held; caller needs to select path */
int fib6_table_lookup(struct net *net, struct fib6_table *table,
int oif, struct flowi6 *fl6, struct fib6_result *res,
int strict);
void fib6_select_path(const struct net *net, struct fib6_result *res,
struct flowi6 *fl6, int oif, bool have_oif_match,
const struct sk_buff *skb, int strict);
struct fib6_node *fib6_node_lookup(struct fib6_node *root,
const struct in6_addr *daddr,
const struct in6_addr *saddr);
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,
bool exact_match);
void fib6_clean_all(struct net *net, int (*func)(struct fib6_info *, void *arg),
void *arg);
void fib6_clean_all_skip_notify(struct net *net,
int (*func)(struct fib6_info *, void *arg),
void *arg);
int fib6_add(struct fib6_node *root, struct fib6_info *rt,
struct nl_info *info, struct netlink_ext_ack *extack);
int fib6_del(struct fib6_info *rt, struct nl_info *info);
static inline
void rt6_get_prefsrc(const struct rt6_info *rt, struct in6_addr *addr)
{
const struct fib6_info *from;
rcu_read_lock();
from = rcu_dereference(rt->from);
if (from) {
*addr = from->fib6_prefsrc.addr;
} else {
struct in6_addr in6_zero = {};
*addr = in6_zero;
}
rcu_read_unlock();
}
static inline struct net_device *fib6_info_nh_dev(const struct fib6_info *f6i)
{
return f6i->fib6_nh.fib_nh_dev;
}
int fib6_nh_init(struct net *net, struct fib6_nh *fib6_nh,
struct fib6_config *cfg, gfp_t gfp_flags,
struct netlink_ext_ack *extack);
void fib6_nh_release(struct fib6_nh *fib6_nh);
void inet6_rt_notify(int event, struct fib6_info *rt, struct nl_info *info,
unsigned int flags);
void fib6_run_gc(unsigned long expires, struct net *net, bool force);
void fib6_gc_cleanup(void);
int fib6_init(void);
struct ipv6_route_iter {
struct seq_net_private p;
struct fib6_walker w;
loff_t skip;
struct fib6_table *tbl;
int sernum;
};
extern const struct seq_operations ipv6_route_seq_ops;
int call_fib6_notifier(struct notifier_block *nb, struct net *net,
enum fib_event_type event_type,
struct fib_notifier_info *info);
int call_fib6_notifiers(struct net *net, enum fib_event_type event_type,
struct fib_notifier_info *info);
int __net_init fib6_notifier_init(struct net *net);
void __net_exit fib6_notifier_exit(struct net *net);
unsigned int fib6_tables_seq_read(struct net *net);
int fib6_tables_dump(struct net *net, struct notifier_block *nb);
void fib6_update_sernum(struct net *net, struct fib6_info *rt);
void fib6_update_sernum_upto_root(struct net *net, struct fib6_info *rt);
void fib6_metric_set(struct fib6_info *f6i, int metric, u32 val);
static inline bool fib6_metric_locked(struct fib6_info *f6i, int metric)
{
return !!(f6i->fib6_metrics->metrics[RTAX_LOCK - 1] & (1 << metric));
}
#ifdef CONFIG_IPV6_MULTIPLE_TABLES
int fib6_rules_init(void);
void fib6_rules_cleanup(void);
bool fib6_rule_default(const struct fib_rule *rule);
int fib6_rules_dump(struct net *net, struct notifier_block *nb);
unsigned int fib6_rules_seq_read(struct net *net);
static inline bool fib6_rules_early_flow_dissect(struct net *net,
struct sk_buff *skb,
struct flowi6 *fl6,
struct flow_keys *flkeys)
{
unsigned int flag = FLOW_DISSECTOR_F_STOP_AT_ENCAP;
if (!net->ipv6.fib6_rules_require_fldissect)
return false;
skb_flow_dissect_flow_keys(skb, flkeys, flag);
fl6->fl6_sport = flkeys->ports.src;
fl6->fl6_dport = flkeys->ports.dst;
fl6->flowi6_proto = flkeys->basic.ip_proto;
return true;
}
#else
static inline int fib6_rules_init(void)
{
return 0;
}
static inline void fib6_rules_cleanup(void)
{
return ;
}
static inline bool fib6_rule_default(const struct fib_rule *rule)
{
return true;
}
static inline int fib6_rules_dump(struct net *net, struct notifier_block *nb)
{
return 0;
}
static inline unsigned int fib6_rules_seq_read(struct net *net)
{
return 0;
}
static inline bool fib6_rules_early_flow_dissect(struct net *net,
struct sk_buff *skb,
struct flowi6 *fl6,
struct flow_keys *flkeys)
{
return false;
}
#endif
#endif