summaryrefslogtreecommitdiffstats
path: root/fs
diff options
context:
space:
mode:
authorPeter Staubach <staubach@redhat.com>2005-07-27 11:45:09 -0700
committerLinus Torvalds <torvalds@g5.osdl.org>2005-07-27 16:26:06 -0700
commitc293621bbf678a3d85e3ed721c3921c8a670610d (patch)
treec72fc522cf3fd2d12f7fd716b7eb4db8d7fcaf52 /fs
parent3e5ea098446e19175fdee4c2c4ec9366b0217db4 (diff)
[PATCH] stale POSIX lock handling
I believe that there is a problem with the handling of POSIX locks, which the attached patch should address. The problem appears to be a race between fcntl(2) and close(2). A multithreaded application could close a file descriptor at the same time as it is trying to acquire a lock using the same file descriptor. I would suggest that that multithreaded application is not providing the proper synchronization for itself, but the OS should still behave correctly. SUS3 (Single UNIX Specification Version 3, read: POSIX) indicates that when a file descriptor is closed, that all POSIX locks on the file, owned by the process which closed the file descriptor, should be released. The trick here is when those locks are released. The current code releases all locks which exist when close is processing, but any locks in progress are handled when the last reference to the open file is released. There are three cases to consider. One is the simple case, a multithreaded (mt) process has a file open and races to close it and acquire a lock on it. In this case, the close will release one reference to the open file and when the fcntl is done, it will release the other reference. For this situation, no locks should exist on the file when both the close and fcntl operations are done. The current system will handle this case because the last reference to the open file is being released. The second case is when the mt process has dup(2)'d the file descriptor. The close will release one reference to the file and the fcntl, when done, will release another, but there will still be at least one more reference to the open file. One could argue that the existence of a lock on the file after the close has completed is okay, because it was acquired after the close operation and there is still a way for the application to release the lock on the file, using an existing file descriptor. The third case is when the mt process has forked, after opening the file and either before or after becoming an mt process. In this case, each process would hold a reference to the open file. For each process, this degenerates to first case above. However, the lock continues to exist until both processes have released their references to the open file. This lock could block other lock requests. The changes to release the lock when the last reference to the open file aren't quite right because they would allow the lock to exist as long as there was a reference to the open file. This is too long. The new proposed solution is to add support in the fcntl code path to detect a race with close and then to release the lock which was just acquired when such as race is detected. This causes locks to be released in a timely fashion and for the system to conform to the POSIX semantic specification. This was tested by instrumenting a kernel to detect the handling locks and then running a program which generates case #3 above. A dangling lock could be reliably generated. When the changes to detect the close/fcntl race were added, a dangling lock could no longer be generated. Cc: Matthew Wilcox <willy@debian.org> Cc: Trond Myklebust <trond.myklebust@fys.uio.no> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
Diffstat (limited to 'fs')
-rw-r--r--fs/fcntl.c5
-rw-r--r--fs/locks.c81
2 files changed, 51 insertions, 35 deletions
diff --git a/fs/fcntl.c b/fs/fcntl.c
index 286a9f8f3d4..6fbc9d8fcc3 100644
--- a/fs/fcntl.c
+++ b/fs/fcntl.c
@@ -288,7 +288,7 @@ static long do_fcntl(int fd, unsigned int cmd, unsigned long arg,
break;
case F_SETLK:
case F_SETLKW:
- err = fcntl_setlk(filp, cmd, (struct flock __user *) arg);
+ err = fcntl_setlk(fd, filp, cmd, (struct flock __user *) arg);
break;
case F_GETOWN:
/*
@@ -376,7 +376,8 @@ asmlinkage long sys_fcntl64(unsigned int fd, unsigned int cmd, unsigned long arg
break;
case F_SETLK64:
case F_SETLKW64:
- err = fcntl_setlk64(filp, cmd, (struct flock64 __user *) arg);
+ err = fcntl_setlk64(fd, filp, cmd,
+ (struct flock64 __user *) arg);
break;
default:
err = do_fcntl(fd, cmd, arg, filp);
diff --git a/fs/locks.c b/fs/locks.c
index 29fa5da6c11..11956b6179f 100644
--- a/fs/locks.c
+++ b/fs/locks.c
@@ -1591,7 +1591,8 @@ out:
/* Apply the lock described by l to an open file descriptor.
* This implements both the F_SETLK and F_SETLKW commands of fcntl().
*/
-int fcntl_setlk(struct file *filp, unsigned int cmd, struct flock __user *l)
+int fcntl_setlk(unsigned int fd, struct file *filp, unsigned int cmd,
+ struct flock __user *l)
{
struct file_lock *file_lock = locks_alloc_lock();
struct flock flock;
@@ -1620,6 +1621,7 @@ int fcntl_setlk(struct file *filp, unsigned int cmd, struct flock __user *l)
goto out;
}
+again:
error = flock_to_posix_lock(filp, file_lock, &flock);
if (error)
goto out;
@@ -1648,25 +1650,33 @@ int fcntl_setlk(struct file *filp, unsigned int cmd, struct flock __user *l)
if (error)
goto out;
- if (filp->f_op && filp->f_op->lock != NULL) {
+ if (filp->f_op && filp->f_op->lock != NULL)
error = filp->f_op->lock(filp, cmd, file_lock);
- goto out;
- }
+ else {
+ for (;;) {
+ error = __posix_lock_file(inode, file_lock);
+ if ((error != -EAGAIN) || (cmd == F_SETLK))
+ break;
+ error = wait_event_interruptible(file_lock->fl_wait,
+ !file_lock->fl_next);
+ if (!error)
+ continue;
- for (;;) {
- error = __posix_lock_file(inode, file_lock);
- if ((error != -EAGAIN) || (cmd == F_SETLK))
+ locks_delete_block(file_lock);
break;
- error = wait_event_interruptible(file_lock->fl_wait,
- !file_lock->fl_next);
- if (!error)
- continue;
+ }
+ }
- locks_delete_block(file_lock);
- break;
+ /*
+ * 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) {
+ flock.l_type = F_UNLCK;
+ goto again;
}
- out:
+out:
locks_free_lock(file_lock);
return error;
}
@@ -1724,7 +1734,8 @@ out:
/* Apply the lock described by l to an open file descriptor.
* This implements both the F_SETLK and F_SETLKW commands of fcntl().
*/
-int fcntl_setlk64(struct file *filp, unsigned int cmd, struct flock64 __user *l)
+int fcntl_setlk64(unsigned int fd, struct file *filp, unsigned int cmd,
+ struct flock64 __user *l)
{
struct file_lock *file_lock = locks_alloc_lock();
struct flock64 flock;
@@ -1753,6 +1764,7 @@ int fcntl_setlk64(struct file *filp, unsigned int cmd, struct flock64 __user *l)
goto out;
}
+again:
error = flock64_to_posix_lock(filp, file_lock, &flock);
if (error)
goto out;
@@ -1781,22 +1793,30 @@ int fcntl_setlk64(struct file *filp, unsigned int cmd, struct flock64 __user *l)
if (error)
goto out;
- if (filp->f_op && filp->f_op->lock != NULL) {
+ if (filp->f_op && filp->f_op->lock != NULL)
error = filp->f_op->lock(filp, cmd, file_lock);
- goto out;
- }
+ else {
+ for (;;) {
+ error = __posix_lock_file(inode, file_lock);
+ if ((error != -EAGAIN) || (cmd == F_SETLK64))
+ break;
+ error = wait_event_interruptible(file_lock->fl_wait,
+ !file_lock->fl_next);
+ if (!error)
+ continue;
- for (;;) {
- error = __posix_lock_file(inode, file_lock);
- if ((error != -EAGAIN) || (cmd == F_SETLK64))
+ locks_delete_block(file_lock);
break;
- error = wait_event_interruptible(file_lock->fl_wait,
- !file_lock->fl_next);
- if (!error)
- continue;
+ }
+ }
- locks_delete_block(file_lock);
- break;
+ /*
+ * 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) {
+ flock.l_type = F_UNLCK;
+ goto again;
}
out:
@@ -1888,12 +1908,7 @@ void locks_remove_flock(struct file *filp)
while ((fl = *before) != NULL) {
if (fl->fl_file == filp) {
- /*
- * We might have a POSIX lock that was created at the same time
- * the filp was closed for the last time. Just remove that too,
- * regardless of ownership, since nobody can own it.
- */
- if (IS_FLOCK(fl) || IS_POSIX(fl)) {
+ if (IS_FLOCK(fl)) {
locks_delete_lock(before);
continue;
}