linux/include/net/ip6_fib.h

655 lines
16 KiB
C
Raw Normal View History

/* SPDX-License-Identifier: GPL-2.0-or-later */
/*
* Linux INET6 implementation
*
* Authors:
* Pedro Roque <roque@di.fc.ul.pt>
*/
#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>
ipv6: fib6: avoid indirect calls from fib6_rule_lookup It was reported that a considerable amount of cycles were spent on the expensive indirect calls on fib6_rule_lookup. This patch introduces an inline helper called pol_route_func that uses the indirect_call_wrappers to avoid the indirect calls. This patch saves around 50ns per call. Performance was measured on the receiver by checking the amount of syncookies that server was able to generate under a synflood load. Traffic was generated using trafgen[1] which was pushing around 1Mpps on a single queue. Receiver was using only one rx queue which help to create a bottle neck and make the experiment rx-bounded. These are the syncookies generated over 10s from the different runs: Whithout the patch: TcpExtSyncookiesSent 3553749 0.0 TcpExtSyncookiesSent 3550895 0.0 TcpExtSyncookiesSent 3553845 0.0 TcpExtSyncookiesSent 3541050 0.0 TcpExtSyncookiesSent 3539921 0.0 TcpExtSyncookiesSent 3557659 0.0 TcpExtSyncookiesSent 3526812 0.0 TcpExtSyncookiesSent 3536121 0.0 TcpExtSyncookiesSent 3529963 0.0 TcpExtSyncookiesSent 3536319 0.0 With the patch: TcpExtSyncookiesSent 3611786 0.0 TcpExtSyncookiesSent 3596682 0.0 TcpExtSyncookiesSent 3606878 0.0 TcpExtSyncookiesSent 3599564 0.0 TcpExtSyncookiesSent 3601304 0.0 TcpExtSyncookiesSent 3609249 0.0 TcpExtSyncookiesSent 3617437 0.0 TcpExtSyncookiesSent 3608765 0.0 TcpExtSyncookiesSent 3620205 0.0 TcpExtSyncookiesSent 3601895 0.0 Without the patch the average is 354263 pkt/s or 2822 ns/pkt and with the patch the average is 360738 pkt/s or 2772 ns/pkt which gives an estimate of 50 ns per packet. [1] http://netsniff-ng.org/ Changelog since v1: - Change ordering in the ICW (Paolo Abeni) Cc: Luigi Rizzo <lrizzo@google.com> Cc: Paolo Abeni <pabeni@redhat.com> Reported-by: Eric Dumazet <edumazet@google.com> Signed-off-by: Brian Vazquez <brianvv@google.com> Acked-by: Paolo Abeni <pabeni@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2020-06-23 16:42:32 +00:00
#include <linux/indirect_call_wrapper.h>
#include <uapi/linux/bpf.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>
2017-02-02 20:37:08 +00:00
u16 fc_type; /* only 8 bits are used */
u16 fc_delete_all_nh : 1,
fc_ignore_dev_down:1,
__unused : 14;
u32 fc_nh_id;
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;
bool fc_is_fdb;
};
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>
2017-10-06 19:06:10 +00:00
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>
2017-10-06 19:06:10 +00:00
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
static inline bool fib6_routes_require_src(const struct net *net)
{
return false;
}
static inline void fib6_routes_require_src_inc(struct net *net) {}
static inline void fib6_routes_require_src_dec(struct net *net) {}
#else
static inline bool fib6_routes_require_src(const struct net *net)
{
return net->ipv6.fib6_routes_require_src > 0;
}
static inline void fib6_routes_require_src_inc(struct net *net)
{
net->ipv6.fib6_routes_require_src++;
}
static inline void fib6_routes_require_src_dec(struct net *net)
{
net->ipv6.fib6_routes_require_src--;
}
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>
2017-10-06 19:06:10 +00:00
#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 rt6_info * __percpu *rt6i_pcpu;
struct rt6_exception_bucket __rcu *rt6i_exception_bucket;
};
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 same metric/weight,
* destination, but not the same gateway. nsiblings is just a cache
* to speed up lookup.
*/
ipv6: Plumb support for nexthop object in a fib6_info Add struct nexthop and nh_list list_head to fib6_info. nh_list is the fib6_info side of the nexthop <-> fib_info relationship. Since a fib6_info referencing a nexthop object can not have 'sibling' entries (the old way of doing multipath routes), the nh_list is a union with fib6_siblings. Add f6i_list list_head to 'struct nexthop' to track fib6_info entries using a nexthop instance. Update __remove_nexthop_fib to walk f6_list and delete fib entries using the nexthop. Add a few nexthop helpers for use when a nexthop is added to fib6_info: - nexthop_fib6_nh - return first fib6_nh in a nexthop object - fib6_info_nh_dev moved to nexthop.h and updated to use nexthop_fib6_nh if the fib6_info references a nexthop object - nexthop_path_fib6_result - similar to ipv4, select a path within a multipath nexthop object. If the nexthop is a blackhole, set fib6_result type to RTN_BLACKHOLE, and set the REJECT flag Update the fib6_info references to check for nh and take a different path as needed: - rt6_qualify_for_ecmp - if a fib entry uses a nexthop object it can NOT be coalesced with other fib entries into a multipath route - rt6_duplicate_nexthop - use nexthop_cmp if either fib6_info references a nexthop - addrconf (host routes), RA's and info entries (anything configured via ndisc) does not use nexthop objects - fib6_info_destroy_rcu - put reference to nexthop object - fib6_purge_rt - drop fib6_info from f6i_list - fib6_select_path - update to use the new nexthop_path_fib6_result when fib entry uses a nexthop object - rt6_device_match - update to catch use of nexthop object as a blackhole and set fib6_type and flags. - ip6_route_info_create - don't add space for fib6_nh if fib entry is going to reference a nexthop object, take a reference to nexthop object, disallow use of source routing - rt6_nlmsg_size - add space for RTA_NH_ID - add rt6_fill_node_nexthop to add nexthop data on a dump As with ipv4, most of the changes push existing code into the else branch of whether the fib entry uses a nexthop object. Update the nexthop code to walk f6i_list on a nexthop deleted to remove fib entries referencing it. Signed-off-by: David Ahern <dsahern@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-06-04 03:19:52 +00:00
union {
struct list_head fib6_siblings;
struct list_head nh_list;
};
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;
u32 fib6_metric;
u8 fib6_protocol;
u8 fib6_type;
ipv6: fix data-race in fib6_info_hw_flags_set / fib6_purge_rt Because fib6_info_hw_flags_set() is called without any synchronization, all accesses to gi6->offload, fi->trap and fi->offload_failed need some basic protection like READ_ONCE()/WRITE_ONCE(). BUG: KCSAN: data-race in fib6_info_hw_flags_set / fib6_purge_rt read to 0xffff8881087d5886 of 1 bytes by task 13953 on cpu 0: fib6_drop_pcpu_from net/ipv6/ip6_fib.c:1007 [inline] fib6_purge_rt+0x4f/0x580 net/ipv6/ip6_fib.c:1033 fib6_del_route net/ipv6/ip6_fib.c:1983 [inline] fib6_del+0x696/0x890 net/ipv6/ip6_fib.c:2028 __ip6_del_rt net/ipv6/route.c:3876 [inline] ip6_del_rt+0x83/0x140 net/ipv6/route.c:3891 __ipv6_dev_ac_dec+0x2b5/0x370 net/ipv6/anycast.c:374 ipv6_dev_ac_dec net/ipv6/anycast.c:387 [inline] __ipv6_sock_ac_close+0x141/0x200 net/ipv6/anycast.c:207 ipv6_sock_ac_close+0x79/0x90 net/ipv6/anycast.c:220 inet6_release+0x32/0x50 net/ipv6/af_inet6.c:476 __sock_release net/socket.c:650 [inline] sock_close+0x6c/0x150 net/socket.c:1318 __fput+0x295/0x520 fs/file_table.c:280 ____fput+0x11/0x20 fs/file_table.c:313 task_work_run+0x8e/0x110 kernel/task_work.c:164 tracehook_notify_resume include/linux/tracehook.h:189 [inline] exit_to_user_mode_loop kernel/entry/common.c:175 [inline] exit_to_user_mode_prepare+0x160/0x190 kernel/entry/common.c:207 __syscall_exit_to_user_mode_work kernel/entry/common.c:289 [inline] syscall_exit_to_user_mode+0x20/0x40 kernel/entry/common.c:300 do_syscall_64+0x50/0xd0 arch/x86/entry/common.c:86 entry_SYSCALL_64_after_hwframe+0x44/0xae write to 0xffff8881087d5886 of 1 bytes by task 1912 on cpu 1: fib6_info_hw_flags_set+0x155/0x3b0 net/ipv6/route.c:6230 nsim_fib6_rt_hw_flags_set drivers/net/netdevsim/fib.c:668 [inline] nsim_fib6_rt_add drivers/net/netdevsim/fib.c:691 [inline] nsim_fib6_rt_insert drivers/net/netdevsim/fib.c:756 [inline] nsim_fib6_event drivers/net/netdevsim/fib.c:853 [inline] nsim_fib_event drivers/net/netdevsim/fib.c:886 [inline] nsim_fib_event_work+0x284f/0x2cf0 drivers/net/netdevsim/fib.c:1477 process_one_work+0x3f6/0x960 kernel/workqueue.c:2307 worker_thread+0x616/0xa70 kernel/workqueue.c:2454 kthread+0x2c7/0x2e0 kernel/kthread.c:327 ret_from_fork+0x1f/0x30 value changed: 0x22 -> 0x2a Reported by Kernel Concurrency Sanitizer on: CPU: 1 PID: 1912 Comm: kworker/1:3 Not tainted 5.16.0-syzkaller #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 Workqueue: events nsim_fib_event_work Fixes: 0c5fcf9e249e ("IPv6: Add "offload failed" indication to routes") Fixes: bb3c4ab93e44 ("ipv6: Add "offload" and "trap" indications to routes") Signed-off-by: Eric Dumazet <edumazet@google.com> Cc: Amit Cohen <amcohen@nvidia.com> Cc: Ido Schimmel <idosch@nvidia.com> Reported-by: syzbot <syzkaller@googlegroups.com> Link: https://lore.kernel.org/r/20220216173217.3792411-2-eric.dumazet@gmail.com Signed-off-by: Jakub Kicinski <kuba@kernel.org>
2022-02-16 17:32:17 +00:00
u8 offload;
u8 trap;
u8 offload_failed;
u8 should_flush:1,
dst_nocount:1,
dst_nopolicy:1,
fib6_destroying:1,
ipv6: fix data-race in fib6_info_hw_flags_set / fib6_purge_rt Because fib6_info_hw_flags_set() is called without any synchronization, all accesses to gi6->offload, fi->trap and fi->offload_failed need some basic protection like READ_ONCE()/WRITE_ONCE(). BUG: KCSAN: data-race in fib6_info_hw_flags_set / fib6_purge_rt read to 0xffff8881087d5886 of 1 bytes by task 13953 on cpu 0: fib6_drop_pcpu_from net/ipv6/ip6_fib.c:1007 [inline] fib6_purge_rt+0x4f/0x580 net/ipv6/ip6_fib.c:1033 fib6_del_route net/ipv6/ip6_fib.c:1983 [inline] fib6_del+0x696/0x890 net/ipv6/ip6_fib.c:2028 __ip6_del_rt net/ipv6/route.c:3876 [inline] ip6_del_rt+0x83/0x140 net/ipv6/route.c:3891 __ipv6_dev_ac_dec+0x2b5/0x370 net/ipv6/anycast.c:374 ipv6_dev_ac_dec net/ipv6/anycast.c:387 [inline] __ipv6_sock_ac_close+0x141/0x200 net/ipv6/anycast.c:207 ipv6_sock_ac_close+0x79/0x90 net/ipv6/anycast.c:220 inet6_release+0x32/0x50 net/ipv6/af_inet6.c:476 __sock_release net/socket.c:650 [inline] sock_close+0x6c/0x150 net/socket.c:1318 __fput+0x295/0x520 fs/file_table.c:280 ____fput+0x11/0x20 fs/file_table.c:313 task_work_run+0x8e/0x110 kernel/task_work.c:164 tracehook_notify_resume include/linux/tracehook.h:189 [inline] exit_to_user_mode_loop kernel/entry/common.c:175 [inline] exit_to_user_mode_prepare+0x160/0x190 kernel/entry/common.c:207 __syscall_exit_to_user_mode_work kernel/entry/common.c:289 [inline] syscall_exit_to_user_mode+0x20/0x40 kernel/entry/common.c:300 do_syscall_64+0x50/0xd0 arch/x86/entry/common.c:86 entry_SYSCALL_64_after_hwframe+0x44/0xae write to 0xffff8881087d5886 of 1 bytes by task 1912 on cpu 1: fib6_info_hw_flags_set+0x155/0x3b0 net/ipv6/route.c:6230 nsim_fib6_rt_hw_flags_set drivers/net/netdevsim/fib.c:668 [inline] nsim_fib6_rt_add drivers/net/netdevsim/fib.c:691 [inline] nsim_fib6_rt_insert drivers/net/netdevsim/fib.c:756 [inline] nsim_fib6_event drivers/net/netdevsim/fib.c:853 [inline] nsim_fib_event drivers/net/netdevsim/fib.c:886 [inline] nsim_fib_event_work+0x284f/0x2cf0 drivers/net/netdevsim/fib.c:1477 process_one_work+0x3f6/0x960 kernel/workqueue.c:2307 worker_thread+0x616/0xa70 kernel/workqueue.c:2454 kthread+0x2c7/0x2e0 kernel/kthread.c:327 ret_from_fork+0x1f/0x30 value changed: 0x22 -> 0x2a Reported by Kernel Concurrency Sanitizer on: CPU: 1 PID: 1912 Comm: kworker/1:3 Not tainted 5.16.0-syzkaller #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 Workqueue: events nsim_fib_event_work Fixes: 0c5fcf9e249e ("IPv6: Add "offload failed" indication to routes") Fixes: bb3c4ab93e44 ("ipv6: Add "offload" and "trap" indications to routes") Signed-off-by: Eric Dumazet <edumazet@google.com> Cc: Amit Cohen <amcohen@nvidia.com> Cc: Ido Schimmel <idosch@nvidia.com> Reported-by: syzbot <syzkaller@googlegroups.com> Link: https://lore.kernel.org/r/20220216173217.3792411-2-eric.dumazet@gmail.com Signed-off-by: Jakub Kicinski <kuba@kernel.org>
2022-02-16 17:32:17 +00:00
unused:4;
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 12:24:31 +00:00
struct rcu_head rcu;
ipv6: Plumb support for nexthop object in a fib6_info Add struct nexthop and nh_list list_head to fib6_info. nh_list is the fib6_info side of the nexthop <-> fib_info relationship. Since a fib6_info referencing a nexthop object can not have 'sibling' entries (the old way of doing multipath routes), the nh_list is a union with fib6_siblings. Add f6i_list list_head to 'struct nexthop' to track fib6_info entries using a nexthop instance. Update __remove_nexthop_fib to walk f6_list and delete fib entries using the nexthop. Add a few nexthop helpers for use when a nexthop is added to fib6_info: - nexthop_fib6_nh - return first fib6_nh in a nexthop object - fib6_info_nh_dev moved to nexthop.h and updated to use nexthop_fib6_nh if the fib6_info references a nexthop object - nexthop_path_fib6_result - similar to ipv4, select a path within a multipath nexthop object. If the nexthop is a blackhole, set fib6_result type to RTN_BLACKHOLE, and set the REJECT flag Update the fib6_info references to check for nh and take a different path as needed: - rt6_qualify_for_ecmp - if a fib entry uses a nexthop object it can NOT be coalesced with other fib entries into a multipath route - rt6_duplicate_nexthop - use nexthop_cmp if either fib6_info references a nexthop - addrconf (host routes), RA's and info entries (anything configured via ndisc) does not use nexthop objects - fib6_info_destroy_rcu - put reference to nexthop object - fib6_purge_rt - drop fib6_info from f6i_list - fib6_select_path - update to use the new nexthop_path_fib6_result when fib entry uses a nexthop object - rt6_device_match - update to catch use of nexthop object as a blackhole and set fib6_type and flags. - ip6_route_info_create - don't add space for fib6_nh if fib entry is going to reference a nexthop object, take a reference to nexthop object, disallow use of source routing - rt6_nlmsg_size - add space for RTA_NH_ID - add rt6_fill_node_nexthop to add nexthop data on a dump As with ipv4, most of the changes push existing code into the else branch of whether the fib entry uses a nexthop object. Update the nexthop code to walk f6i_list on a nexthop deleted to remove fib entries referencing it. Signed-off-by: David Ahern <dsahern@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-06-04 03:19:52 +00:00
struct nexthop *nh;
struct fib6_nh fib6_nh[];
};
struct rt6_info {
struct dst_entry dst;
struct fib6_info __rcu *from;
ipv6: Use global sernum for dst validation with nexthop objects Nik reported a bug with pcpu dst cache when nexthop objects are used illustrated by the following: $ ip netns add foo $ ip -netns foo li set lo up $ ip -netns foo addr add 2001:db8:11::1/128 dev lo $ ip netns exec foo sysctl net.ipv6.conf.all.forwarding=1 $ ip li add veth1 type veth peer name veth2 $ ip li set veth1 up $ ip addr add 2001:db8:10::1/64 dev veth1 $ ip li set dev veth2 netns foo $ ip -netns foo li set veth2 up $ ip -netns foo addr add 2001:db8:10::2/64 dev veth2 $ ip -6 nexthop add id 100 via 2001:db8:10::2 dev veth1 $ ip -6 route add 2001:db8:11::1/128 nhid 100 Create a pcpu entry on cpu 0: $ taskset -a -c 0 ip -6 route get 2001:db8:11::1 Re-add the route entry: $ ip -6 ro del 2001:db8:11::1 $ ip -6 route add 2001:db8:11::1/128 nhid 100 Route get on cpu 0 returns the stale pcpu: $ taskset -a -c 0 ip -6 route get 2001:db8:11::1 RTNETLINK answers: Network is unreachable While cpu 1 works: $ taskset -a -c 1 ip -6 route get 2001:db8:11::1 2001:db8:11::1 from :: via 2001:db8:10::2 dev veth1 src 2001:db8:10::1 metric 1024 pref medium Conversion of FIB entries to work with external nexthop objects missed an important difference between IPv4 and IPv6 - how dst entries are invalidated when the FIB changes. IPv4 has a per-network namespace generation id (rt_genid) that is bumped on changes to the FIB. Checking if a dst_entry is still valid means comparing rt_genid in the rtable to the current value of rt_genid for the namespace. IPv6 also has a per network namespace counter, fib6_sernum, but the count is saved per fib6_node. With the per-node counter only dst_entries based on fib entries under the node are invalidated when changes are made to the routes - limiting the scope of invalidations. IPv6 uses a reference in the rt6_info, 'from', to track the corresponding fib entry used to create the dst_entry. When validating a dst_entry, the 'from' is used to backtrack to the fib6_node and check the sernum of it to the cookie passed to the dst_check operation. With the inline format (nexthop definition inline with the fib6_info), dst_entries cached in the fib6_nh have a 1:1 correlation between fib entries, nexthop data and dst_entries. With external nexthops, IPv6 looks more like IPv4 which means multiple fib entries across disparate fib6_nodes can all reference the same fib6_nh. That means validation of dst_entries based on external nexthops needs to use the IPv4 format - the per-network namespace counter. Add sernum to rt6_info and set it when creating a pcpu dst entry. Update rt6_get_cookie to return sernum if it is set and update dst_check for IPv6 to look for sernum set and based the check on it if so. Finally, rt6_get_pcpu_route needs to validate the cached entry before returning a pcpu entry (similar to the rt_cache_valid calls in __mkroute_input and __mkroute_output for IPv4). This problem only affects routes using the new, external nexthops. Thanks to the kbuild test robot for catching the IS_ENABLED needed around rt_genid_ipv6 before I sent this out. Fixes: 5b98324ebe29 ("ipv6: Allow routes to use nexthop objects") Reported-by: Nikolay Aleksandrov <nikolay@cumulusnetworks.com> Signed-off-by: David Ahern <dsahern@kernel.org> Reviewed-by: Nikolay Aleksandrov <nikolay@cumulusnetworks.com> Tested-by: Nikolay Aleksandrov <nikolay@cumulusnetworks.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2020-05-01 14:53:08 +00:00
int sernum;
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>
2017-10-06 19:06:10 +00:00
#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>
2017-10-06 19:06:10 +00:00
#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>
2017-10-06 19:06:10 +00:00
static inline struct inet6_dev *ip6_dst_idev(struct dst_entry *dst)
{
return ((struct rt6_info *)dst)->rt6i_idev;
}
static inline bool fib6_requires_src(const struct fib6_info *rt)
{
return rt->fib6_src.plen > 0;
}
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->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) {
ipv6: annotate accesses to fn->fn_sernum struct fib6_node's fn_sernum field can be read while other threads change it. Add READ_ONCE()/WRITE_ONCE() annotations. Do not change existing smp barriers in fib6_get_cookie_safe() and __fib6_update_sernum_upto_root() syzbot reported: BUG: KCSAN: data-race in fib6_clean_node / inet6_csk_route_socket write to 0xffff88813df62e2c of 4 bytes by task 1920 on cpu 1: fib6_clean_node+0xc2/0x260 net/ipv6/ip6_fib.c:2178 fib6_walk_continue+0x38e/0x430 net/ipv6/ip6_fib.c:2112 fib6_walk net/ipv6/ip6_fib.c:2160 [inline] fib6_clean_tree net/ipv6/ip6_fib.c:2240 [inline] __fib6_clean_all+0x1a9/0x2e0 net/ipv6/ip6_fib.c:2256 fib6_flush_trees+0x6c/0x80 net/ipv6/ip6_fib.c:2281 rt_genid_bump_ipv6 include/net/net_namespace.h:488 [inline] addrconf_dad_completed+0x57f/0x870 net/ipv6/addrconf.c:4230 addrconf_dad_work+0x908/0x1170 process_one_work+0x3f6/0x960 kernel/workqueue.c:2307 worker_thread+0x616/0xa70 kernel/workqueue.c:2454 kthread+0x1bf/0x1e0 kernel/kthread.c:359 ret_from_fork+0x1f/0x30 read to 0xffff88813df62e2c of 4 bytes by task 15701 on cpu 0: fib6_get_cookie_safe include/net/ip6_fib.h:285 [inline] rt6_get_cookie include/net/ip6_fib.h:306 [inline] ip6_dst_store include/net/ip6_route.h:234 [inline] inet6_csk_route_socket+0x352/0x3c0 net/ipv6/inet6_connection_sock.c:109 inet6_csk_xmit+0x91/0x1e0 net/ipv6/inet6_connection_sock.c:121 __tcp_transmit_skb+0x1323/0x1840 net/ipv4/tcp_output.c:1402 tcp_transmit_skb net/ipv4/tcp_output.c:1420 [inline] tcp_write_xmit+0x1450/0x4460 net/ipv4/tcp_output.c:2680 __tcp_push_pending_frames+0x68/0x1c0 net/ipv4/tcp_output.c:2864 tcp_push+0x2d9/0x2f0 net/ipv4/tcp.c:725 mptcp_push_release net/mptcp/protocol.c:1491 [inline] __mptcp_push_pending+0x46c/0x490 net/mptcp/protocol.c:1578 mptcp_sendmsg+0x9ec/0xa50 net/mptcp/protocol.c:1764 inet6_sendmsg+0x5f/0x80 net/ipv6/af_inet6.c:643 sock_sendmsg_nosec net/socket.c:705 [inline] sock_sendmsg net/socket.c:725 [inline] kernel_sendmsg+0x97/0xd0 net/socket.c:745 sock_no_sendpage+0x84/0xb0 net/core/sock.c:3086 inet_sendpage+0x9d/0xc0 net/ipv4/af_inet.c:834 kernel_sendpage+0x187/0x200 net/socket.c:3492 sock_sendpage+0x5a/0x70 net/socket.c:1007 pipe_to_sendpage+0x128/0x160 fs/splice.c:364 splice_from_pipe_feed fs/splice.c:418 [inline] __splice_from_pipe+0x207/0x500 fs/splice.c:562 splice_from_pipe fs/splice.c:597 [inline] generic_splice_sendpage+0x94/0xd0 fs/splice.c:746 do_splice_from fs/splice.c:767 [inline] direct_splice_actor+0x80/0xa0 fs/splice.c:936 splice_direct_to_actor+0x345/0x650 fs/splice.c:891 do_splice_direct+0x106/0x190 fs/splice.c:979 do_sendfile+0x675/0xc40 fs/read_write.c:1245 __do_sys_sendfile64 fs/read_write.c:1310 [inline] __se_sys_sendfile64 fs/read_write.c:1296 [inline] __x64_sys_sendfile64+0x102/0x140 fs/read_write.c:1296 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x44/0xd0 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x44/0xae value changed: 0x0000026f -> 0x00000271 Reported by Kernel Concurrency Sanitizer on: CPU: 0 PID: 15701 Comm: syz-executor.2 Not tainted 5.16.0-syzkaller #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 The Fixes tag I chose is probably arbitrary, I do not think we need to backport this patch to older kernels. Fixes: c5cff8561d2d ("ipv6: add rcu grace period before freeing fib6_node") Signed-off-by: Eric Dumazet <edumazet@google.com> Reported-by: syzbot <syzkaller@googlegroups.com> Link: https://lore.kernel.org/r/20220120174112.1126644-1-eric.dumazet@gmail.com Signed-off-by: Jakub Kicinski <kuba@kernel.org>
2022-01-20 17:41:12 +00:00
*cookie = READ_ONCE(fn->fn_sernum);
/* pairs with smp_wmb() in __fib6_update_sernum_upto_root() */
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>
2017-10-06 19:06:07 +00:00
smp_rmb();
status = true;
}
return status;
}
static inline u32 rt6_get_cookie(const struct rt6_info *rt)
{
struct fib6_info *from;
u32 cookie = 0;
ipv6: Use global sernum for dst validation with nexthop objects Nik reported a bug with pcpu dst cache when nexthop objects are used illustrated by the following: $ ip netns add foo $ ip -netns foo li set lo up $ ip -netns foo addr add 2001:db8:11::1/128 dev lo $ ip netns exec foo sysctl net.ipv6.conf.all.forwarding=1 $ ip li add veth1 type veth peer name veth2 $ ip li set veth1 up $ ip addr add 2001:db8:10::1/64 dev veth1 $ ip li set dev veth2 netns foo $ ip -netns foo li set veth2 up $ ip -netns foo addr add 2001:db8:10::2/64 dev veth2 $ ip -6 nexthop add id 100 via 2001:db8:10::2 dev veth1 $ ip -6 route add 2001:db8:11::1/128 nhid 100 Create a pcpu entry on cpu 0: $ taskset -a -c 0 ip -6 route get 2001:db8:11::1 Re-add the route entry: $ ip -6 ro del 2001:db8:11::1 $ ip -6 route add 2001:db8:11::1/128 nhid 100 Route get on cpu 0 returns the stale pcpu: $ taskset -a -c 0 ip -6 route get 2001:db8:11::1 RTNETLINK answers: Network is unreachable While cpu 1 works: $ taskset -a -c 1 ip -6 route get 2001:db8:11::1 2001:db8:11::1 from :: via 2001:db8:10::2 dev veth1 src 2001:db8:10::1 metric 1024 pref medium Conversion of FIB entries to work with external nexthop objects missed an important difference between IPv4 and IPv6 - how dst entries are invalidated when the FIB changes. IPv4 has a per-network namespace generation id (rt_genid) that is bumped on changes to the FIB. Checking if a dst_entry is still valid means comparing rt_genid in the rtable to the current value of rt_genid for the namespace. IPv6 also has a per network namespace counter, fib6_sernum, but the count is saved per fib6_node. With the per-node counter only dst_entries based on fib entries under the node are invalidated when changes are made to the routes - limiting the scope of invalidations. IPv6 uses a reference in the rt6_info, 'from', to track the corresponding fib entry used to create the dst_entry. When validating a dst_entry, the 'from' is used to backtrack to the fib6_node and check the sernum of it to the cookie passed to the dst_check operation. With the inline format (nexthop definition inline with the fib6_info), dst_entries cached in the fib6_nh have a 1:1 correlation between fib entries, nexthop data and dst_entries. With external nexthops, IPv6 looks more like IPv4 which means multiple fib entries across disparate fib6_nodes can all reference the same fib6_nh. That means validation of dst_entries based on external nexthops needs to use the IPv4 format - the per-network namespace counter. Add sernum to rt6_info and set it when creating a pcpu dst entry. Update rt6_get_cookie to return sernum if it is set and update dst_check for IPv6 to look for sernum set and based the check on it if so. Finally, rt6_get_pcpu_route needs to validate the cached entry before returning a pcpu entry (similar to the rt_cache_valid calls in __mkroute_input and __mkroute_output for IPv4). This problem only affects routes using the new, external nexthops. Thanks to the kbuild test robot for catching the IS_ENABLED needed around rt_genid_ipv6 before I sent this out. Fixes: 5b98324ebe29 ("ipv6: Allow routes to use nexthop objects") Reported-by: Nikolay Aleksandrov <nikolay@cumulusnetworks.com> Signed-off-by: David Ahern <dsahern@kernel.org> Reviewed-by: Nikolay Aleksandrov <nikolay@cumulusnetworks.com> Tested-by: Nikolay Aleksandrov <nikolay@cumulusnetworks.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2020-05-01 14:53:08 +00:00
if (rt->sernum)
return rt->sernum;
rcu_read_lock();
from = rcu_dereference(rt->from);
if (from)
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, bool with_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 12:24:31 +00:00
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 03:56:32 +00:00
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 03:56:32 +00:00
}
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 12:24:31 +00:00
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 05:19:03 +00:00
unsigned int skip;
unsigned int count;
ipv6: Dump route exceptions if requested Since commit 2b760fcf5cfb ("ipv6: hook up exception table to store dst cache"), route exceptions reside in a separate hash table, and won't be found by walking the FIB, so they won't be dumped to userspace on a RTM_GETROUTE message. This causes 'ip -6 route list cache' and 'ip -6 route flush cache' to have no function anymore: # ip -6 route get fc00:3::1 fc00:3::1 via fc00:1::2 dev veth_A-R1 src fc00:1::1 metric 1024 expires 539sec mtu 1400 pref medium # ip -6 route get fc00:4::1 fc00:4::1 via fc00:2::2 dev veth_A-R2 src fc00:2::1 metric 1024 expires 536sec mtu 1500 pref medium # ip -6 route list cache # ip -6 route flush cache # ip -6 route get fc00:3::1 fc00:3::1 via fc00:1::2 dev veth_A-R1 src fc00:1::1 metric 1024 expires 520sec mtu 1400 pref medium # ip -6 route get fc00:4::1 fc00:4::1 via fc00:2::2 dev veth_A-R2 src fc00:2::1 metric 1024 expires 519sec mtu 1500 pref medium because iproute2 lists cached routes using RTM_GETROUTE, and flushes them by listing all the routes, and deleting them with RTM_DELROUTE one by one. If cached routes are requested using the RTM_F_CLONED flag together with strict checking, or if no strict checking is requested (and hence we can't consistently apply filters), look up exceptions in the hash table associated with the current fib6_info in rt6_dump_route(), and, if present and not expired, add them to the dump. We might be unable to dump all the entries for a given node in a single message, so keep track of how many entries were handled for the current node in fib6_walker, and skip that amount in case we start from the same partially dumped node. When a partial dump restarts, as the starting node might change when 'sernum' changes, we have no guarantee that we need to skip the same amount of in-node entries. Therefore, we need two counters, and we need to zero the in-node counter if the node from which the dump is resumed differs. Note that, with the current version of iproute2, this only fixes the 'ip -6 route list cache': on a flush command, iproute2 doesn't pass RTM_F_CLONED and, due to this inconsistency, 'ip -6 route flush cache' is still unable to fetch the routes to be flushed. This will be addressed in a patch for iproute2. To flush cached routes, a procfs entry could be introduced instead: that's how it works for IPv4. We already have a rt6_flush_exception() function ready to be wired to it. However, this would not solve the issue for listing. Versions of iproute2 and kernel tested: iproute2 kernel 4.14.0 4.15.0 4.19.0 5.0.0 5.1.0 5.1.0, patched 3.18 list + + + + + + flush + + + + + + 4.4 list + + + + + + flush + + + + + + 4.9 list + + + + + + flush + + + + + + 4.14 list + + + + + + flush + + + + + + 4.15 list flush 4.19 list flush 5.0 list flush 5.1 list flush with list + + + + + + fix flush + + + + v7: - Explain usage of "skip" counters in commit message (suggested by David Ahern) v6: - Rebase onto net-next, use recently introduced nexthop walker - Make rt6_nh_dump_exceptions() a separate function (suggested by David Ahern) v5: - Use dump_routes and dump_exceptions from filter, ignore NLM_F_MATCH, update test results (flushing works with iproute2 < 5.0.0 now) v4: - Split NLM_F_MATCH and strict check handling in separate patches - Filter routes using RTM_F_CLONED: if it's not set, only return non-cached routes, and if it's set, only return cached routes: change requested by David Ahern and Martin Lau. This implies that iproute2 needs a separate patch to be able to flush IPv6 cached routes. This is not ideal because we can't fix the breakage caused by 2b760fcf5cfb entirely in kernel. However, two years have passed since then, and this makes it more tolerable v3: - More descriptive comment about expired exceptions in rt6_dump_route() - Swap return values of rt6_dump_route() (suggested by Martin Lau) - Don't zero skip_in_node in case we don't dump anything in a given pass (also suggested by Martin Lau) - Remove check on RTM_F_CLONED altogether: in the current UAPI semantic, it's just a flag to indicate the route was cloned, not to filter on routes v2: Add tracking of number of entries to be skipped in current node after a partial dump. As we restart from the same node, if not all the exceptions for a given node fit in a single message, the dump will not terminate, as suggested by Martin Lau. This is a concrete possibility, setting up a big number of exceptions for the same route actually causes the issue, suggested by David Ahern. Reported-by: Jianlin Shi <jishi@redhat.com> Fixes: 2b760fcf5cfb ("ipv6: hook up exception table to store dst cache") Signed-off-by: Stefano Brivio <sbrivio@redhat.com> Reviewed-by: David Ahern <dsahern@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-06-21 15:45:27 +00:00
unsigned int skip_in_node;
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 stat is not protected by any lock */
atomic_t fib_rt_alloc; /* total number of routes alloced */
};
#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>
2017-10-06 19:06:10 +00:00
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;
unsigned int nsiblings;
};
/*
* 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();
}
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 fib6_nh_release_dsts(struct fib6_nh *fib6_nh);
int call_fib6_entry_notifiers(struct net *net,
enum fib_event_type event_type,
struct fib6_info *rt,
struct netlink_ext_ack *extack);
int call_fib6_multipath_entry_notifiers(struct net *net,
enum fib_event_type event_type,
struct fib6_info *rt,
unsigned int nsiblings,
struct netlink_ext_ack *extack);
int call_fib6_entry_notifiers_replace(struct net *net, struct fib6_info *rt);
void fib6_rt_update(struct net *net, struct fib6_info *rt,
struct nl_info *info);
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,
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,
struct netlink_ext_ack *extack);
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_update_sernum_stub(struct net *net, struct fib6_info *f6i);
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));
}
net: ipv6: Emit notification when fib hardware flags are changed After installing a route to the kernel, user space receives an acknowledgment, which means the route was installed in the kernel, but not necessarily in hardware. The asynchronous nature of route installation in hardware can lead to a routing daemon advertising a route before it was actually installed in hardware. This can result in packet loss or mis-routed packets until the route is installed in hardware. It is also possible for a route already installed in hardware to change its action and therefore its flags. For example, a host route that is trapping packets can be "promoted" to perform decapsulation following the installation of an IPinIP/VXLAN tunnel. Emit RTM_NEWROUTE notifications whenever RTM_F_OFFLOAD/RTM_F_TRAP flags are changed. The aim is to provide an indication to user-space (e.g., routing daemons) about the state of the route in hardware. Introduce a sysctl that controls this behavior. Keep the default value at 0 (i.e., do not emit notifications) for several reasons: - Multiple RTM_NEWROUTE notification per-route might confuse existing routing daemons. - Convergence reasons in routing daemons. - The extra notifications will negatively impact the insertion rate. - Not all users are interested in these notifications. Move fib6_info_hw_flags_set() to C file because it is no longer a short function. Signed-off-by: Amit Cohen <amcohen@nvidia.com> Signed-off-by: Ido Schimmel <idosch@nvidia.com> Reviewed-by: David Ahern <dsahern@kernel.org> Signed-off-by: Jakub Kicinski <kuba@kernel.org>
2021-02-01 19:47:55 +00:00
void fib6_info_hw_flags_set(struct net *net, struct fib6_info *f6i,
bool offload, bool trap, bool offload_failed);
#if IS_BUILTIN(CONFIG_IPV6) && defined(CONFIG_BPF_SYSCALL)
struct bpf_iter__ipv6_route {
__bpf_md_ptr(struct bpf_iter_meta *, meta);
__bpf_md_ptr(struct fib6_info *, rt);
};
#endif
ipv6: fib6: avoid indirect calls from fib6_rule_lookup It was reported that a considerable amount of cycles were spent on the expensive indirect calls on fib6_rule_lookup. This patch introduces an inline helper called pol_route_func that uses the indirect_call_wrappers to avoid the indirect calls. This patch saves around 50ns per call. Performance was measured on the receiver by checking the amount of syncookies that server was able to generate under a synflood load. Traffic was generated using trafgen[1] which was pushing around 1Mpps on a single queue. Receiver was using only one rx queue which help to create a bottle neck and make the experiment rx-bounded. These are the syncookies generated over 10s from the different runs: Whithout the patch: TcpExtSyncookiesSent 3553749 0.0 TcpExtSyncookiesSent 3550895 0.0 TcpExtSyncookiesSent 3553845 0.0 TcpExtSyncookiesSent 3541050 0.0 TcpExtSyncookiesSent 3539921 0.0 TcpExtSyncookiesSent 3557659 0.0 TcpExtSyncookiesSent 3526812 0.0 TcpExtSyncookiesSent 3536121 0.0 TcpExtSyncookiesSent 3529963 0.0 TcpExtSyncookiesSent 3536319 0.0 With the patch: TcpExtSyncookiesSent 3611786 0.0 TcpExtSyncookiesSent 3596682 0.0 TcpExtSyncookiesSent 3606878 0.0 TcpExtSyncookiesSent 3599564 0.0 TcpExtSyncookiesSent 3601304 0.0 TcpExtSyncookiesSent 3609249 0.0 TcpExtSyncookiesSent 3617437 0.0 TcpExtSyncookiesSent 3608765 0.0 TcpExtSyncookiesSent 3620205 0.0 TcpExtSyncookiesSent 3601895 0.0 Without the patch the average is 354263 pkt/s or 2822 ns/pkt and with the patch the average is 360738 pkt/s or 2772 ns/pkt which gives an estimate of 50 ns per packet. [1] http://netsniff-ng.org/ Changelog since v1: - Change ordering in the ICW (Paolo Abeni) Cc: Luigi Rizzo <lrizzo@google.com> Cc: Paolo Abeni <pabeni@redhat.com> Reported-by: Eric Dumazet <edumazet@google.com> Signed-off-by: Brian Vazquez <brianvv@google.com> Acked-by: Paolo Abeni <pabeni@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2020-06-23 16:42:32 +00:00
INDIRECT_CALLABLE_DECLARE(struct rt6_info *ip6_pol_route_output(struct net *net,
struct fib6_table *table,
struct flowi6 *fl6,
const struct sk_buff *skb,
int flags));
INDIRECT_CALLABLE_DECLARE(struct rt6_info *ip6_pol_route_input(struct net *net,
struct fib6_table *table,
struct flowi6 *fl6,
const struct sk_buff *skb,
int flags));
INDIRECT_CALLABLE_DECLARE(struct rt6_info *__ip6_route_redirect(struct net *net,
struct fib6_table *table,
struct flowi6 *fl6,
const struct sk_buff *skb,
int flags));
INDIRECT_CALLABLE_DECLARE(struct rt6_info *ip6_pol_route_lookup(struct net *net,
struct fib6_table *table,
struct flowi6 *fl6,
const struct sk_buff *skb,
int flags));
static inline struct rt6_info *pol_lookup_func(pol_lookup_t lookup,
struct net *net,
struct fib6_table *table,
struct flowi6 *fl6,
const struct sk_buff *skb,
int flags)
{
return INDIRECT_CALL_4(lookup,
ip6_pol_route_output,
ip6_pol_route_input,
ip6_pol_route_lookup,
__ip6_route_redirect,
net, table, fl6, skb, flags);
}
#ifdef CONFIG_IPV6_MULTIPLE_TABLES
static inline bool fib6_has_custom_rules(const struct net *net)
{
return net->ipv6.fib6_has_custom_rules;
}
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,
struct netlink_ext_ack *extack);
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 bool fib6_has_custom_rules(const struct net *net)
{
return false;
}
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,
struct netlink_ext_ack *extack)
{
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