tcp/rds: Fix use-after-free around kernel TCP reqsk.
Subsystems (4)
v4 cover tcp/rds: Fix use-after-free around kernel TCP reqsk.
syzkaller reported an warning of netns ref tracker for RDS TCP listener, which commit 740ea3c4a0b2 ("tcp: Clean up kernel listener's reqsk in inet_twsk_purge()") fixed for per-netns ehash.
This series fixes the bug in the partial fix and fixes the reported bug in the global ehash.
Changes:
v4:
* Add sk_family/refcnt check in inet_twsk_purge().
v3: https://lore.kernel.org/netdev/[email protected]/
* Drop patch 2, 3, 5
* Fix uaf by iterating ehash and purging reqsk during netns dismantle.
v2: https://lore.kernel.org/netdev/[email protected]/
* Add patch 1, 3, 5
* Use __sock_create() instead of converting socket
* Drop Sowmini from CC as it's bounced (patchwork may complain)
v1: https://lore.kernel.org/netdev/[email protected]/
Kuniyuki Iwashima (2):
tcp: Fix use-after-free in inet_twsk_purge().
rds: tcp: Fix use-after-free of net in reqsk_timer_handler().
net/ipv4/inet_timewait_sock.c | 24 +++++++++++++++++++----- net/ipv4/tcp_minisocks.c | 4 ---- 2 files changed, 19 insertions(+), 9 deletions(-)
Signature · 1 line
2.30.2
PATCH v4 1/2 tcp: Fix use-after-free in inet_twsk_purge().
Commit 740ea3c4a0b2 ("tcp: Clean up kernel listener's reqsk in inet_twsk_purge()") added changes in inet_twsk_purge() to purge reqsk in per-netns ehash during netns dismantle.
inet_csk_reqsk_queue_drop_and_put() will remove reqsk from per-netns ehash, but the iteration uses sk_nulls_for_each_rcu(), which is not safe. After removing reqsk, we need to restart iteration.
Also, we need to use refcount_inc_not_zero() to check if reqsk is freed by its timer.
--- net/ipv4/inet_timewait_sock.c | 24 +++++++++++++++++++----- 1 file changed, 19 insertions(+), 5 deletions(-)
net/ipv4/inet_timewait_sock.c +19 -5
@@ -278,18 +278,32 @@ void inet_twsk_purge(struct inet_hashinfo *hashinfo, int family) restart:sk_nulls_for_each_rcu (sk, node, &head->chain) {if (sk->sk_state !=TCP_TIME_WAIT ) { +struct request_sock *req; + +if (likely (sk->sk_state !=TCP_NEW_SYN_RECV )) +continue ; +/* A kernel listener socket might not hold refcnt for net, * so reqsk_timer_handler() could be fired after net is * freed. Userspace listener and reqsk never exist here. */ -if (unlikely (sk->sk_state ==TCP_NEW_SYN_RECV && - hashinfo->pernet)) { -struct request_sock *req =inet_reqsk (sk); -inet_csk_reqsk_queue_drop_and_put (req->rsk_listener, req); +if (sk->sk_family != family || +refcount_read (&sock_net (sk)->ns.count)) +continue ; + + req =inet_reqsk (sk); +if (unlikely (!refcount_inc_not_zero (&req->rsk_refcnt))) +continue ; + +if (unlikely (sk->sk_family != family || +refcount_read (&sock_net (sk)->ns.count))) { +reqsk_put (req); +continue ; } -continue ; +inet_csk_reqsk_queue_drop_and_put (req->rsk_listener, req); + goto restart; } tw =inet_twsk (sk);
Signature · 1 line
2.30.2
Re: [PATCH v4 net 1/2] tcp: Fix use-after-free in inet_twsk_purge().
Quoted 62 lines · Kuniyuki Iwashima
Commit
740ea3c4a0b2("tcp: Clean up kernel listener's reqsk ininet_twsk_purge()") added changes ininet_twsk_purge()to purge reqsk in per-netns ehash during netns dismantle.
inet_csk_reqsk_queue_drop_and_put()will remove reqsk from per-netns ehash, but the iteration usessk_nulls_for_each_rcu(), which is not safe. After removing reqsk, we need to restart iteration.Also, we need to use
refcount_inc_not_zero()to check if reqsk is freed by its timer.Fixes 740ea3c4a0b2 ("tcp: Clean up kernel listener's reqsk in inet_twsk_purge()")Reported-by Eric Dumazet <[email protected]>Signed-off-by Kuniyuki Iwashima <[email protected]>--- net/ipv4/inet_timewait_sock.c | 24 +++++++++++++++++++----- 1 file changed, 19 insertions(+), 5 deletions(-)net/ipv4/inet_timewait_sock.c +19
-5@@ -278,18 +278,32 @@ void inet_twsk_purge(struct inet_hashinfo *hashinfo, int family) restart:sk_nulls_for_each_rcu (sk, node, &head->chain) {if (sk->sk_state !=TCP_TIME_WAIT ) { +struct request_sock *req; + +if (likely (sk->sk_state !=TCP_NEW_SYN_RECV )) +continue ; +/* A kernel listener socket might not hold refcnt for net, * so reqsk_timer_handler() could be fired after net is * freed. Userspace listener and reqsk never exist here. */ -if (unlikely (sk->sk_state ==TCP_NEW_SYN_RECV && - hashinfo->pernet)) { -struct request_sock *req =inet_reqsk (sk); -inet_csk_reqsk_queue_drop_and_put (req->rsk_listener, req); +if (sk->sk_family != family || +refcount_read (&sock_net (sk)->ns.count)) +continue ; + + req =inet_reqsk (sk); +if (unlikely (!refcount_inc_not_zero (&req->rsk_refcnt))) +continue ; + +if (unlikely (sk->sk_family != family || +refcount_read (&sock_net (sk)->ns.count))) { +reqsk_put (req); +continue ; } -continue ; +inet_csk_reqsk_queue_drop_and_put (req->rsk_listener, req); + goto restart; }tw = inet_twsk(sk);
Quoted 3 lines
--
2.30.2
Unfortunately inet_csk_reqsk_queue_drop_and_put() also needs the local_bh_disable() part.
Presumably this code never met LOCKDEP :/
What about factoring the code like this ?
(Untested patch, only compiled)
net/ipv4/inet_timewait_sock.c +0 -0
100644
net/ipv4/inet_timewait_sock.c +1 -2
@@ -265,10 +265,9 @@ EXPORT_SYMBOL_GPL(__inet_twsk_schedule);void inet_twsk_purge (struct inet_hashinfo *hashinfo,int family) { -struct inet_timewait_sock *tw; -struct sock *sk;struct hlist_nulls_node *node;unsigned int slot; +struct sock *sk;for (slot =0 ; slot <= hashinfo->ehash_mask; slot++) {struct inet_ehash_bucket *head = &hashinfo->ehash[slot];
@@ -277,38 +276,35 @@ void inet_twsk_purge(struct inet_hashinfo
*hashinfo, int family)
rcu_read_lock();
restart:
sk_nulls_for_each_rcu(sk, node, &head->chain) {- if (sk->sk_state != TCP_TIME_WAIT) {
- /* A kernel listener socket might not
hold refcnt for net,
- * so reqsk_timer_handler() could be
fired after net is
- * freed. Userspace listener and
reqsk never exist here.
- */
- if (unlikely(sk->sk_state == TCP_NEW_SYN_RECV &&
- hashinfo->pernet)) {
- struct request_sock *req =inet_reqsk(sk);
-
- inet_csk_reqsk_queue_drop_and_put(req->rsk_listener, req);
- }
+ int state = inet_sk_state_load(sk);
+ if ((1 << state) & ~(TCPF_TIME_WAIT |
+ TCPF_NEW_SYN_RECV))
continue;
- }
- tw = inet_twsk(sk);
- if ((tw->tw_family != family) ||
- refcount_read(&twsk_net(tw)->ns.count))
+ if ((sk->sk_family != family) ||
+ refcount_read(&sock_net(sk)->ns.count))
continue;
- if (unlikely(!refcount_inc_not_zero(&tw->tw_refcnt)))
+ if (unlikely(!refcount_inc_not_zero(&sk->sk_refcnt)))
continue;
- if (unlikely((tw->tw_family != family) ||
- refcount_read(&twsk_net(tw)->ns.count))) {
- inet_twsk_put(tw);
+ if (unlikely((sk->sk_family != family) ||
+ refcount_read(&sock_net(sk)->ns.count))) {
+ sock_gen_put(sk);
goto restart;
}
rcu_read_unlock();
local_bh_disable();- inet_twsk_deschedule_put(tw);
+ if (state == TCP_TIME_WAIT) {
+ inet_twsk_deschedule_put(inet_twsk(sk));
+ } else {
+ struct request_sock *req = inet_reqsk(sk);
+
+ inet_csk_reqsk_queue_drop_and_put(req->rsk_listener,
+ req);
+ }
local_bh_enable();
goto restart_rcu;
}PATCH v4 2/2 rds: tcp: Fix use-after-free of net in reqsk_timer_handler().
In reply to Kuniyuki Iwashimasyzkaller reported a warning of netns tracker [0] followed by KASAN splat [1] and another ref tracker warning [1].
syzkaller could not find a repro, but in the log, the only suspicious sequence was as follows:
18:26:22 executing program 1:
r0 = socket$inet6_mptcp(0xa, 0x1, 0x106)
...
connect$inet6(r0, &(0x7f0000000080)={0xa, 0x4001, 0x0, @loopback}, 0x1c) (async)
The notable thing here is 0x4001 in connect(), which is RDS_TCP_PORT.
So, the scenario would be:
1. unshare(CLONE_NEWNET) creates a per netns tcp listener in
rds_tcp_listen_init().
2. syz-executor connect()s to it and creates a reqsk.
3. syz-executor exit()s immediately.
4. netns is dismantled. [0]
5. reqsk timer is fired, and UAF happens while freeing reqsk. [1]
6. listener is freed after RCU grace period. [2]
Basically, reqsk assumes that the listener guarantees netns safety until all reqsk timers are expired by holding the listener's refcount. However, this was not the case for kernel sockets.
Commit 740ea3c4a0b2 ("tcp: Clean up kernel listener's reqsk in inet_twsk_purge()") fixed this issue only for per-netns ehash.
Let's apply the same fix for the global ehash.
[0]:ref_tracker: net notrefcnt@0000000065449cc3 has 1/1 users at
sk_alloc (./include/net/net_namespace.h:337 net/core/sock.c:2146)
inet6_create (net/ipv6/af_inet6.c:192 net/ipv6/af_inet6.c:119)
__sock_create (net/socket.c:1572)
rds_tcp_listen_init (net/rds/tcp_listen.c:279)
rds_tcp_init_net (net/rds/tcp.c:577)
ops_init (net/core/net_namespace.c:137)
setup_net (net/core/net_namespace.c:340)
copy_net_ns (net/core/net_namespace.c:497)
create_new_namespaces (kernel/nsproxy.c:110)
unshare_nsproxy_namespaces (kernel/nsproxy.c:228 (discriminator 4))
ksys_unshare (kernel/fork.c:3429)
__x64_sys_unshare (kernel/fork.c:3496)
do_syscall_64 (arch/x86/entry/common.c:52 arch/x86/entry/common.c:83)
entry_SYSCALL_64_after_hwframe (arch/x86/entry/entry_64.S:129)
...
WARNING: CPU: 0 PID: 27 at lib/ref_tracker.c:179 ref_tracker_dir_exit (lib/ref_tracker.c:179)[1]:
BUG: KASAN: slab-use-after-free in inet_csk_reqsk_queue_drop (./include/net/inet_hashtables.h:180 net/ipv4/inet_connection_sock.c:952 net/ipv4/inet_connection_sock.c:966) Read of size 8 at addr ffff88801b370400 by task swapper/0/0 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.16.0-0-gd239552ce722-prebuilt.qemu.org 04/01/2014 Call Trace: <IRQ> dump_stack_lvl (lib/dump_stack.c:107 (discriminator 1)) print_report (mm/kasan/report.c:378 mm/kasan/report.c:488) kasan_report (mm/kasan/report.c:603) inet_csk_reqsk_queue_drop (./include/net/inet_hashtables.h:180 net/ipv4/inet_connection_sock.c:952 net/ipv4/inet_connection_sock.c:966) reqsk_timer_handler (net/ipv4/inet_connection_sock.c:979 net/ipv4/inet_connection_sock.c:1092) call_timer_fn (./arch/x86/include/asm/jump_label.h:27 ./include/linux/jump_label.h:207 ./include/trace/events/timer.h:127 kernel/time/timer.c:1701) __run_timers.part.0 (kernel/time/timer.c:1752 kernel/time/timer.c:2038) run_timer_softirq (kernel/time/timer.c:2053) __do_softirq (./arch/x86/include/asm/jump_label.h:27 ./include/linux/jump_label.h:207 ./include/trace/events/irq.h:142 kernel/softirq.c:554) irq_exit_rcu (kernel/softirq.c:427 kernel/softirq.c:632 kernel/softirq.c:644) sysvec_apic_timer_interrupt (arch/x86/kernel/apic/apic.c:1076 (discriminator 14)) </IRQ> Allocated by task 258 on cpu 0 at 83.612050s: kasan_save_stack (mm/kasan/common.c:48) kasan_save_track (mm/kasan/common.c:68) __kasan_slab_alloc (mm/kasan/common.c:343) kmem_cache_alloc (mm/slub.c:3813 mm/slub.c:3860 mm/slub.c:3867) copy_net_ns (./include/linux/slab.h:701 net/core/net_namespace.c:421 net/core/net_namespace.c:480) create_new_namespaces (kernel/nsproxy.c:110) unshare_nsproxy_namespaces (kernel/nsproxy.c:228 (discriminator 4)) ksys_unshare (kernel/fork.c:3429) __x64_sys_unshare (kernel/fork.c:3496) do_syscall_64 (arch/x86/entry/common.c:52 arch/x86/entry/common.c:83) entry_SYSCALL_64_after_hwframe (arch/x86/entry/entry_64.S:129) Freed by task 27 on cpu 0 at 329.158864s: kasan_save_stack (mm/kasan/common.c:48) kasan_save_track (mm/kasan/common.c:68) kasan_save_free_info (mm/kasan/generic.c:643) __kasan_slab_free (mm/kasan/common.c:265) kmem_cache_free (mm/slub.c:4299 mm/slub.c:4363) cleanup_net (net/core/net_namespace.c:456 net/core/net_namespace.c:446 net/core/net_namespace.c:639) process_one_work (kernel/workqueue.c:2638) worker_thread (kernel/workqueue.c:2700 kernel/workqueue.c:2787) kthread (kernel/kthread.c:388) ret_from_fork (arch/x86/kernel/process.c:153) ret_from_fork_asm (arch/x86/entry/entry_64.S:250) The buggy address belongs to the object at ffff88801b370000 which belongs to the cache net_namespace of size 4352
The buggy address is located 1024 bytes inside of
freed 4352-byte region [ffff88801b370000, ffff88801b371100)
[2]:
WARNING: CPU: 0 PID: 95 at lib/ref_tracker.c:228 ref_tracker_free (lib/ref_tracker.c:228 (discriminator 1)) Modules linked in: Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.16.0-0-gd239552ce722-prebuilt.qemu.org 04/01/2014 RIP: 0010:ref_tracker_free (lib/ref_tracker.c:228 (discriminator 1)) ... Call Trace: <IRQ> __sk_destruct (./include/net/net_namespace.h:353 net/core/sock.c:2204) rcu_core (./arch/x86/include/asm/preempt.h:26 kernel/rcu/tree.c:2165 kernel/rcu/tree.c:2433) __do_softirq (./arch/x86/include/asm/jump_label.h:27 ./include/linux/jump_label.h:207 ./include/trace/events/irq.h:142 kernel/softirq.c:554) irq_exit_rcu (kernel/softirq.c:427 kernel/softirq.c:632 kernel/softirq.c:644) sysvec_apic_timer_interrupt (arch/x86/kernel/apic/apic.c:1076 (discriminator 14)) </IRQ>
--- net/ipv4/tcp_minisocks.c | 4 ---- 1 file changed, 4 deletions(-)
net/ipv4/tcp_minisocks.c +0 -4
@@ -398,10 +398,6 @@ void tcp_twsk_purge(struct list_head *net_exit_list, int family)/* Even if tw_refcount == 1, we must clean up kernel reqsk */ inet_twsk_purge (net->ipv4.tcp_death_row.hashinfo, family); }else if (!purged_once) { -/* The last refcount is decremented in tcp_sk_exit_batch() */ -if (refcount_read (&net->ipv4.tcp_death_row.tw_refcount) ==1 ) -continue ; -inet_twsk_purge (&tcp_hashinfo, family); purged_once = true; }
Signature · 1 line
2.30.2