From b9d6631395a1e25b210ce112b1bc10f3c665ea20 Mon Sep 17 00:00:00 2001 From: Zhou Chengming Date: Fri, 6 Jan 2017 09:32:32 +0800 Subject: sysctl: Drop reference added by grab_header in proc_sys_readdir commit 93362fa47fe98b62e4a34ab408c4a418432e7939 upstream. Fixes CVE-2016-9191, proc_sys_readdir doesn't drop reference added by grab_header when return from !dir_emit_dots path. It can cause any path called unregister_sysctl_table will wait forever. The calltrace of CVE-2016-9191: [ 5535.960522] Call Trace: [ 5535.963265] [] schedule+0x3f/0xa0 [ 5535.968817] [] schedule_timeout+0x3db/0x6f0 [ 5535.975346] [] ? wait_for_completion+0x45/0x130 [ 5535.982256] [] wait_for_completion+0xc3/0x130 [ 5535.988972] [] ? wake_up_q+0x80/0x80 [ 5535.994804] [] drop_sysctl_table+0xc4/0xe0 [ 5536.001227] [] drop_sysctl_table+0x77/0xe0 [ 5536.007648] [] unregister_sysctl_table+0x4d/0xa0 [ 5536.014654] [] unregister_sysctl_table+0x7f/0xa0 [ 5536.021657] [] unregister_sched_domain_sysctl+0x15/0x40 [ 5536.029344] [] partition_sched_domains+0x44/0x450 [ 5536.036447] [] ? __mutex_unlock_slowpath+0x111/0x1f0 [ 5536.043844] [] rebuild_sched_domains_locked+0x64/0xb0 [ 5536.051336] [] update_flag+0x11d/0x210 [ 5536.057373] [] ? mutex_lock_nested+0x2df/0x450 [ 5536.064186] [] ? cpuset_css_offline+0x1b/0x60 [ 5536.070899] [] ? trace_hardirqs_on+0xd/0x10 [ 5536.077420] [] ? mutex_lock_nested+0x2df/0x450 [ 5536.084234] [] ? css_killed_work_fn+0x25/0x220 [ 5536.091049] [] cpuset_css_offline+0x35/0x60 [ 5536.097571] [] css_killed_work_fn+0x5c/0x220 [ 5536.104207] [] process_one_work+0x1df/0x710 [ 5536.110736] [] ? process_one_work+0x160/0x710 [ 5536.117461] [] worker_thread+0x12b/0x4a0 [ 5536.123697] [] ? process_one_work+0x710/0x710 [ 5536.130426] [] kthread+0xfe/0x120 [ 5536.135991] [] ret_from_fork+0x1f/0x40 [ 5536.142041] [] ? kthread_create_on_node+0x230/0x230 One cgroup maintainer mentioned that "cgroup is trying to offline a cpuset css, which takes place under cgroup_mutex. The offlining ends up trying to drain active usages of a sysctl table which apprently is not happening." The real reason is that proc_sys_readdir doesn't drop reference added by grab_header when return from !dir_emit_dots path. So this cpuset offline path will wait here forever. See here for details: http://www.openwall.com/lists/oss-security/2016/11/04/13 Fixes: f0c3b5093add ("[readdir] convert procfs") Reported-by: CAI Qian Tested-by: Yang Shukui Signed-off-by: Zhou Chengming Acked-by: Al Viro Signed-off-by: Eric W. Biederman Signed-off-by: Greg Kroah-Hartman --- fs/proc/proc_sysctl.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'fs/proc') diff --git a/fs/proc/proc_sysctl.c b/fs/proc/proc_sysctl.c index fe5b6e6c4671..4dbe1e2daeca 100644 --- a/fs/proc/proc_sysctl.c +++ b/fs/proc/proc_sysctl.c @@ -703,7 +703,7 @@ static int proc_sys_readdir(struct file *file, struct dir_context *ctx) ctl_dir = container_of(head, struct ctl_dir, header); if (!dir_emit_dots(file, ctx)) - return 0; + goto out; pos = 2; @@ -713,6 +713,7 @@ static int proc_sys_readdir(struct file *file, struct dir_context *ctx) break; } } +out: sysctl_head_finish(head); return 0; } -- cgit v1.2.3