fasync: Fix deadlock between task-context and interrupt-context kill_fasync()

I observed the following deadlock between them:

[task 1]                          [task 2]                         [task 3]
kill_fasync()                     mm_update_next_owner()           copy_process()
 spin_lock_irqsave(&fa->fa_lock)   read_lock(&tasklist_lock)        write_lock_irq(&tasklist_lock)
  send_sigio()                    <IRQ>                             ...
   read_lock(&fown->lock)         kill_fasync()                     ...
    read_lock(&tasklist_lock)      spin_lock_irqsave(&fa->fa_lock)  ...

Task 1 can't acquire read locked tasklist_lock, since there is
already task 3 expressed its wish to take the lock exclusive.
Task 2 holds the read locked lock, but it can't take the spin lock.

Also, there is possible another deadlock (which I haven't observed):

[task 1]                            [task 2]
f_getown()                          kill_fasync()
 read_lock(&f_own->lock)             spin_lock_irqsave(&fa->fa_lock,)
 <IRQ>                               send_sigio()                     write_lock_irq(&f_own->lock)
  kill_fasync()                       read_lock(&fown->lock)
   spin_lock_irqsave(&fa->fa_lock,)

Actually, we do not need exclusive fa->fa_lock in kill_fasync_rcu(),
as it guarantees fa->fa_file->f_owner integrity only. It may seem,
that it used to give a task a small possibility to receive two sequential
signals, if there are two parallel kill_fasync() callers, and task
handles the first signal fastly, but the behaviour won't become
different, since there is exclusive sighand lock in do_send_sig_info().

The patch converts fa_lock into rwlock_t, and this fixes two above
deadlocks, as rwlock is allowed to be taken from interrupt handler
by qrwlock design.

Signed-off-by: Kirill Tkhai <ktkhai@virtuozzo.com>
Signed-off-by: Jeff Layton <jlayton@redhat.com>

1 files changed, 7 insertions, 8 deletions

diff --git a/fs/fcntl.c b/fs/fcntl.c
index d737ff082472..c42169459298 100644
--- a/fs/fcntl.c
+++ b/fs/fcntl.c
@@ -871,9 +871,9 @@ int fasync_remove_entry(struct file *filp, struct fasync_struct **fapp)
                 if (fa->fa_file != filp)
                         continue;
 
-                spin_lock_irq(&fa->fa_lock);
+                write_lock_irq(&fa->fa_lock);
                 fa->fa_file = NULL;
-                spin_unlock_irq(&fa->fa_lock);
+                write_unlock_irq(&fa->fa_lock);
 
                 *fp = fa->fa_next;
                 call_rcu(&fa->fa_rcu, fasync_free_rcu);
@@ -918,13 +918,13 @@ struct fasync_struct *fasync_insert_entry(int fd, struct file *filp, struct fasy
                 if (fa->fa_file != filp)
                         continue;
 
-                spin_lock_irq(&fa->fa_lock);
+                write_lock_irq(&fa->fa_lock);
                 fa->fa_fd = fd;
-                spin_unlock_irq(&fa->fa_lock);
+                write_unlock_irq(&fa->fa_lock);
                 goto out;
         }
 
-        spin_lock_init(&new->fa_lock);
+        rwlock_init(&new->fa_lock);
         new->magic = FASYNC_MAGIC;
         new->fa_file = filp;
         new->fa_fd = fd;
@@ -987,14 +987,13 @@ static void kill_fasync_rcu(struct fasync_struct *fa, int sig, int band)
 {
         while (fa) {
                 struct fown_struct *fown;
-                unsigned long flags;
 
                 if (fa->magic != FASYNC_MAGIC) {
                         printk(KERN_ERR "kill_fasync: bad magic number in "
                                "fasync_struct!\n");
                         return;
                 }
-                spin_lock_irqsave(&fa->fa_lock, flags);
+                read_lock(&fa->fa_lock);
                 if (fa->fa_file) {
                         fown = &fa->fa_file->f_owner;
                         /* Don't send SIGURG to processes which have not set a
@@ -1003,7 +1002,7 @@ static void kill_fasync_rcu(struct fasync_struct *fa, int sig, int band)
                         if (!(sig == SIGURG && fown->signum == 0))
                                 send_sigio(fown, fa->fa_fd, band);
                 }
-                spin_unlock_irqrestore(&fa->fa_lock, flags);
+                read_unlock(&fa->fa_lock);
                 fa = rcu_dereference(fa->fa_next);
         }
 }