[PATCH] fix SMP ordering hole in fcntl_setlk()

fcntl_setlk()/close() race prevention has a subtle hole - we need to
make sure that if we *do* have an fcntl/close race on SMP box, the
access to descriptor table and inode->i_flock won't get reordered.

As it is, we get STORE inode->i_flock, LOAD descriptor table entry vs.
STORE descriptor table entry, LOAD inode->i_flock with not a single
lock in common on both sides.  We do have BKL around the first STORE,
but check in locks_remove_posix() is outside of BKL and for a good
reason - we don't want BKL on common path of close(2).

Solution is to hold ->file_lock around fcheck() in there; that orders
us wrt removal from descriptor table that preceded locks_remove_posix()
on close path and we either come first (in which case eviction will be
handled by the close side) or we'll see the effect of close and do
eviction ourselves.  Note that even though it's read-only access,
we do need ->file_lock here - rcu_read_lock() won't be enough to
order the things.

Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>

diff --git a/fs/locks.c b/fs/locks.c
index 663c069b59b3d6490fd2fa9046d4d0bc3620a581..0ac6b92cb0b6365a19a7d4c337362a97b320a0a6 100644 (file)
--- a/fs/locks.c
+++ b/fs/locks.c
@@ -1753,6 +1753,7 @@ int fcntl_setlk(unsigned int fd, struct file *filp, unsigned int cmd,
        struct file_lock *file_lock = locks_alloc_lock();
        struct flock flock;
        struct inode *inode;
+       struct file *f;
        int error;
 
        if (file_lock == NULL)
@@ -1825,7 +1826,15 @@ again:
         * Attempt to detect a close/fcntl race and recover by
         * releasing the lock that was just acquired.
         */
-       if (!error && fcheck(fd) != filp && flock.l_type != F_UNLCK) {
+       /*
+        * we need that spin_lock here - it prevents reordering between
+        * update of inode->i_flock and check for it done in close().
+        * rcu_read_lock() wouldn't do.
+        */
+       spin_lock(&current->files->file_lock);
+       f = fcheck(fd);
+       spin_unlock(&current->files->file_lock);
+       if (!error && f != filp && flock.l_type != F_UNLCK) {
                flock.l_type = F_UNLCK;
                goto again;
        }
@@ -1881,6 +1890,7 @@ int fcntl_setlk64(unsigned int fd, struct file *filp, unsigned int cmd,
        struct file_lock *file_lock = locks_alloc_lock();
        struct flock64 flock;
        struct inode *inode;
+       struct file *f;
        int error;
 
        if (file_lock == NULL)
@@ -1953,7 +1963,10 @@ again:
         * Attempt to detect a close/fcntl race and recover by
         * releasing the lock that was just acquired.
         */
-       if (!error && fcheck(fd) != filp && flock.l_type != F_UNLCK) {
+       spin_lock(&current->files->file_lock);
+       f = fcheck(fd);
+       spin_unlock(&current->files->file_lock);
+       if (!error && f != filp && flock.l_type != F_UNLCK) {
                flock.l_type = F_UNLCK;
                goto again;
        }