proc: Allow proc_free_inum to be called from any context
authorEric W. Biederman <ebiederm@xmission.com>
Sat, 22 Dec 2012 04:38:00 +0000 (20:38 -0800)
committerEric W. Biederman <ebiederm@xmission.com>
Wed, 26 Dec 2012 00:23:12 +0000 (16:23 -0800)
While testing the pid namespace code I hit this nasty warning.

[  176.262617] ------------[ cut here ]------------
[  176.263388] WARNING: at /home/eric/projects/linux/linux-userns-devel/kernel/softirq.c:160 local_bh_enable_ip+0x7a/0xa0()
[  176.265145] Hardware name: Bochs
[  176.265677] Modules linked in:
[  176.266341] Pid: 742, comm: bash Not tainted 3.7.0userns+ #18
[  176.266564] Call Trace:
[  176.266564]  [<ffffffff810a539f>] warn_slowpath_common+0x7f/0xc0
[  176.266564]  [<ffffffff810a53fa>] warn_slowpath_null+0x1a/0x20
[  176.266564]  [<ffffffff810ad9ea>] local_bh_enable_ip+0x7a/0xa0
[  176.266564]  [<ffffffff819308c9>] _raw_spin_unlock_bh+0x19/0x20
[  176.266564]  [<ffffffff8123dbda>] proc_free_inum+0x3a/0x50
[  176.266564]  [<ffffffff8111d0dc>] free_pid_ns+0x1c/0x80
[  176.266564]  [<ffffffff8111d195>] put_pid_ns+0x35/0x50
[  176.266564]  [<ffffffff810c608a>] put_pid+0x4a/0x60
[  176.266564]  [<ffffffff8146b177>] tty_ioctl+0x717/0xc10
[  176.266564]  [<ffffffff810aa4d5>] ? wait_consider_task+0x855/0xb90
[  176.266564]  [<ffffffff81086bf9>] ? default_spin_lock_flags+0x9/0x10
[  176.266564]  [<ffffffff810cab0a>] ? remove_wait_queue+0x5a/0x70
[  176.266564]  [<ffffffff811e37e8>] do_vfs_ioctl+0x98/0x550
[  176.266564]  [<ffffffff810b8a0f>] ? recalc_sigpending+0x1f/0x60
[  176.266564]  [<ffffffff810b9127>] ? __set_task_blocked+0x37/0x80
[  176.266564]  [<ffffffff810ab95b>] ? sys_wait4+0xab/0xf0
[  176.266564]  [<ffffffff811e3d31>] sys_ioctl+0x91/0xb0
[  176.266564]  [<ffffffff810a95f0>] ? task_stopped_code+0x50/0x50
[  176.266564]  [<ffffffff81939199>] system_call_fastpath+0x16/0x1b
[  176.266564] ---[ end trace 387af88219ad6143 ]---

It turns out that spin_unlock_bh(proc_inum_lock) is not safe when
put_pid is called with another spinlock held and irqs disabled.

For now take the easy path and use spin_lock_irqsave(proc_inum_lock)
in proc_free_inum and spin_loc_irq in proc_alloc_inum(proc_inum_lock).

Signed-off-by: "Eric W. Biederman" <ebiederm@xmission.com>
fs/proc/generic.c

index e064f562b1f75daf2225d02ad031cd88a560cd95..76ddae83daa58e2b086dd286c847c47de71f1124 100644 (file)
@@ -352,18 +352,18 @@ retry:
        if (!ida_pre_get(&proc_inum_ida, GFP_KERNEL))
                return -ENOMEM;
 
-       spin_lock_bh(&proc_inum_lock);
+       spin_lock_irq(&proc_inum_lock);
        error = ida_get_new(&proc_inum_ida, &i);
-       spin_unlock_bh(&proc_inum_lock);
+       spin_unlock_irq(&proc_inum_lock);
        if (error == -EAGAIN)
                goto retry;
        else if (error)
                return error;
 
        if (i > UINT_MAX - PROC_DYNAMIC_FIRST) {
-               spin_lock_bh(&proc_inum_lock);
+               spin_lock_irq(&proc_inum_lock);
                ida_remove(&proc_inum_ida, i);
-               spin_unlock_bh(&proc_inum_lock);
+               spin_unlock_irq(&proc_inum_lock);
                return -ENOSPC;
        }
        *inum = PROC_DYNAMIC_FIRST + i;
@@ -372,9 +372,10 @@ retry:
 
 void proc_free_inum(unsigned int inum)
 {
-       spin_lock_bh(&proc_inum_lock);
+       unsigned long flags;
+       spin_lock_irqsave(&proc_inum_lock, flags);
        ida_remove(&proc_inum_ida, inum - PROC_DYNAMIC_FIRST);
-       spin_unlock_bh(&proc_inum_lock);
+       spin_unlock_irqrestore(&proc_inum_lock, flags);
 }
 
 static void *proc_follow_link(struct dentry *dentry, struct nameidata *nd)