Merge branch 'server-cluster-locking-api' of git://linux-nfs.org/~bfields/linux

* 'server-cluster-locking-api' of git://linux-nfs.org/~bfields/linux: gfs2: nfs lock support for gfs2 lockd: add code to handle deferred lock requests lockd: always preallocate block in nlmsvc_lock() lockd: handle test_lock deferrals lockd: pass cookie in nlmsvc_testlock lockd: handle fl_grant callbacks lockd: save lock state on deferral locks: add fl_grant callback for asynchronous lock return nfsd4: Convert NFSv4 to new lock interface locks: add lock cancel command locks: allow {vfs,posix}_lock_file to return conflicting lock locks: factor out generic/filesystem switch from setlock code locks: factor out generic/filesystem switch from test_lock locks: give posix_test_lock same interface as ->lock locks: make ->lock release private data before returning in GETLK case locks: create posix-to-flock helper functions locks: trivial removal of unnecessary parentheses
2007-05-07 12:34:24 -07:00
parent 0f9008ef38 586759f03e
commit 2d56d3c43c
15 changed files with 546 additions and 205 deletions
--- a/fs/locks.c
+++ b/fs/locks.c
@@ -665,11 +665,11 @@ static int locks_block_on_timeout(struct file_lock *blocker, struct file_lock *w
 }

 int
-posix_test_lock(struct file *filp, struct file_lock *fl,
-		struct file_lock *conflock)
+posix_test_lock(struct file *filp, struct file_lock *fl)
 {
 	struct file_lock *cfl;

+	fl->fl_type = F_UNLCK;
 	lock_kernel();
 	for (cfl = filp->f_path.dentry->d_inode->i_flock; cfl; cfl = cfl->fl_next) {
 		if (!IS_POSIX(cfl))
@@ -678,7 +678,7 @@ posix_test_lock(struct file *filp, struct file_lock *fl,
 			break;
 	}
 	if (cfl) {
-		__locks_copy_lock(conflock, cfl);
+		__locks_copy_lock(fl, cfl);
 		unlock_kernel();
 		return 1;
 	}
@@ -800,7 +800,7 @@ out:
 	return error;
 }

-static int __posix_lock_file_conf(struct inode *inode, struct file_lock *request, struct file_lock *conflock)
+static int __posix_lock_file(struct inode *inode, struct file_lock *request, struct file_lock *conflock)
 {
 	struct file_lock *fl;
 	struct file_lock *new_fl = NULL;
@@ -1006,6 +1006,7 @@ static int __posix_lock_file_conf(struct inode *inode, struct file_lock *request
 * posix_lock_file - Apply a POSIX-style lock to a file
 * @filp: The file to apply the lock to
 * @fl: The lock to be applied
+ * @conflock: Place to return a copy of the conflicting lock, if found.
 *
 * Add a POSIX style lock to a file.
 * We merge adjacent & overlapping locks whenever possible.
@@ -1015,26 +1016,12 @@ static int __posix_lock_file_conf(struct inode *inode, struct file_lock *request
 * whether or not a lock was successfully freed by testing the return
 * value for -ENOENT.
 */
-int posix_lock_file(struct file *filp, struct file_lock *fl)
-{
-	return __posix_lock_file_conf(filp->f_path.dentry->d_inode, fl, NULL);
-}
-EXPORT_SYMBOL(posix_lock_file);
-
-/**
- * posix_lock_file_conf - Apply a POSIX-style lock to a file
- * @filp: The file to apply the lock to
- * @fl: The lock to be applied
- * @conflock: Place to return a copy of the conflicting lock, if found.
- *
- * Except for the conflock parameter, acts just like posix_lock_file.
- */
-int posix_lock_file_conf(struct file *filp, struct file_lock *fl,
+int posix_lock_file(struct file *filp, struct file_lock *fl,
 			struct file_lock *conflock)
 {
-	return __posix_lock_file_conf(filp->f_path.dentry->d_inode, fl, conflock);
+	return __posix_lock_file(filp->f_path.dentry->d_inode, fl, conflock);
 }
-EXPORT_SYMBOL(posix_lock_file_conf);
+EXPORT_SYMBOL(posix_lock_file);

 /**
 * posix_lock_file_wait - Apply a POSIX-style lock to a file
@@ -1050,7 +1037,7 @@ int posix_lock_file_wait(struct file *filp, struct file_lock *fl)
 	int error;
 	might_sleep ();
 	for (;;) {
-		error = posix_lock_file(filp, fl);
+		error = posix_lock_file(filp, fl, NULL);
 		if ((error != -EAGAIN) || !(fl->fl_flags & FL_SLEEP))
 			break;
 		error = wait_event_interruptible(fl->fl_wait, !fl->fl_next);
@@ -1122,7 +1109,7 @@ int locks_mandatory_area(int read_write, struct inode *inode,
 	fl.fl_end = offset + count - 1;

 	for (;;) {
-		error = __posix_lock_file_conf(inode, &fl, NULL);
+		error = __posix_lock_file(inode, &fl, NULL);
 		if (error != -EAGAIN)
 			break;
 		if (!(fl.fl_flags & FL_SLEEP))
@@ -1610,12 +1597,62 @@ asmlinkage long sys_flock(unsigned int fd, unsigned int cmd)
 	return error;
 }

+/**
+ * vfs_test_lock - test file byte range lock
+ * @filp: The file to test lock for
+ * @fl: The lock to test
+ * @conf: Place to return a copy of the conflicting lock, if found
+ *
+ * Returns -ERRNO on failure.  Indicates presence of conflicting lock by
+ * setting conf->fl_type to something other than F_UNLCK.
+ */
+int vfs_test_lock(struct file *filp, struct file_lock *fl)
+{
+	if (filp->f_op && filp->f_op->lock)
+		return filp->f_op->lock(filp, F_GETLK, fl);
+	posix_test_lock(filp, fl);
+	return 0;
+}
+EXPORT_SYMBOL_GPL(vfs_test_lock);
+
+static int posix_lock_to_flock(struct flock *flock, struct file_lock *fl)
+{
+	flock->l_pid = fl->fl_pid;
+#if BITS_PER_LONG == 32
+	/*
+	 * Make sure we can represent the posix lock via
+	 * legacy 32bit flock.
+	 */
+	if (fl->fl_start > OFFT_OFFSET_MAX)
+		return -EOVERFLOW;
+	if (fl->fl_end != OFFSET_MAX && fl->fl_end > OFFT_OFFSET_MAX)
+		return -EOVERFLOW;
+#endif
+	flock->l_start = fl->fl_start;
+	flock->l_len = fl->fl_end == OFFSET_MAX ? 0 :
+		fl->fl_end - fl->fl_start + 1;
+	flock->l_whence = 0;
+	return 0;
+}
+
+#if BITS_PER_LONG == 32
+static void posix_lock_to_flock64(struct flock64 *flock, struct file_lock *fl)
+{
+	flock->l_pid = fl->fl_pid;
+	flock->l_start = fl->fl_start;
+	flock->l_len = fl->fl_end == OFFSET_MAX ? 0 :
+		fl->fl_end - fl->fl_start + 1;
+	flock->l_whence = 0;
+	flock->l_type = fl->fl_type;
+}
+#endif
+
 /* Report the first existing lock that would conflict with l.
 * This implements the F_GETLK command of fcntl().
 */
 int fcntl_getlk(struct file *filp, struct flock __user *l)
 {
-	struct file_lock *fl, cfl, file_lock;
+	struct file_lock file_lock;
 	struct flock flock;
 	int error;

@@ -1630,38 +1667,15 @@ int fcntl_getlk(struct file *filp, struct flock __user *l)
 	if (error)
 		goto out;

-	if (filp->f_op && filp->f_op->lock) {
-		error = filp->f_op->lock(filp, F_GETLK, &file_lock);
-		if (file_lock.fl_ops && file_lock.fl_ops->fl_release_private)
-			file_lock.fl_ops->fl_release_private(&file_lock);
-		if (error < 0)
-			goto out;
-		else
-		  fl = (file_lock.fl_type == F_UNLCK ? NULL : &file_lock);
-	} else {
-		fl = (posix_test_lock(filp, &file_lock, &cfl) ? &cfl : NULL);
-	}
+	error = vfs_test_lock(filp, &file_lock);
+	if (error)
+		goto out;
 
-	flock.l_type = F_UNLCK;
-	if (fl != NULL) {
-		flock.l_pid = fl->fl_pid;
-#if BITS_PER_LONG == 32
-		/*
-		 * Make sure we can represent the posix lock via
-		 * legacy 32bit flock.
-		 */
-		error = -EOVERFLOW;
-		if (fl->fl_start > OFFT_OFFSET_MAX)
+	flock.l_type = file_lock.fl_type;
+	if (file_lock.fl_type != F_UNLCK) {
+		error = posix_lock_to_flock(&flock, &file_lock);
+		if (error)
 			goto out;
-		if ((fl->fl_end != OFFSET_MAX)
-		    && (fl->fl_end > OFFT_OFFSET_MAX))
-			goto out;
-#endif
-		flock.l_start = fl->fl_start;
-		flock.l_len = fl->fl_end == OFFSET_MAX ? 0 :
-			fl->fl_end - fl->fl_start + 1;
-		flock.l_whence = 0;
-		flock.l_type = fl->fl_type;
 	}
 	error = -EFAULT;
 	if (!copy_to_user(l, &flock, sizeof(flock)))
@@ -1670,6 +1684,48 @@ out:
 	return error;
 }

+/**
+ * vfs_lock_file - file byte range lock
+ * @filp: The file to apply the lock to
+ * @cmd: type of locking operation (F_SETLK, F_GETLK, etc.)
+ * @fl: The lock to be applied
+ * @conf: Place to return a copy of the conflicting lock, if found.
+ *
+ * A caller that doesn't care about the conflicting lock may pass NULL
+ * as the final argument.
+ *
+ * If the filesystem defines a private ->lock() method, then @conf will
+ * be left unchanged; so a caller that cares should initialize it to
+ * some acceptable default.
+ *
+ * To avoid blocking kernel daemons, such as lockd, that need to acquire POSIX
+ * locks, the ->lock() interface may return asynchronously, before the lock has
+ * been granted or denied by the underlying filesystem, if (and only if)
+ * fl_grant is set. Callers expecting ->lock() to return asynchronously
+ * will only use F_SETLK, not F_SETLKW; they will set FL_SLEEP if (and only if)
+ * the request is for a blocking lock. When ->lock() does return asynchronously,
+ * it must return -EINPROGRESS, and call ->fl_grant() when the lock
+ * request completes.
+ * If the request is for non-blocking lock the file system should return
+ * -EINPROGRESS then try to get the lock and call the callback routine with
+ * the result. If the request timed out the callback routine will return a
+ * nonzero return code and the file system should release the lock. The file
+ * system is also responsible to keep a corresponding posix lock when it
+ * grants a lock so the VFS can find out which locks are locally held and do
+ * the correct lock cleanup when required.
+ * The underlying filesystem must not drop the kernel lock or call
+ * ->fl_grant() before returning to the caller with a -EINPROGRESS
+ * return code.
+ */
+int vfs_lock_file(struct file *filp, unsigned int cmd, struct file_lock *fl, struct file_lock *conf)
+{
+	if (filp->f_op && filp->f_op->lock)
+		return filp->f_op->lock(filp, cmd, fl);
+	else
+		return posix_lock_file(filp, fl, conf);
+}
+EXPORT_SYMBOL_GPL(vfs_lock_file);
+
 /* Apply the lock described by l to an open file descriptor.
 * This implements both the F_SETLK and F_SETLKW commands of fcntl().
 */
@@ -1732,21 +1788,17 @@ again:
 	if (error)
 		goto out;

-	if (filp->f_op && filp->f_op->lock != NULL)
-		error = filp->f_op->lock(filp, cmd, file_lock);
-	else {
-		for (;;) {
-			error = posix_lock_file(filp, file_lock);
-			if ((error != -EAGAIN) || (cmd == F_SETLK))
-				break;
-			error = wait_event_interruptible(file_lock->fl_wait,
-					!file_lock->fl_next);
-			if (!error)
-				continue;
-
-			locks_delete_block(file_lock);
+	for (;;) {
+		error = vfs_lock_file(filp, cmd, file_lock, NULL);
+		if (error != -EAGAIN || cmd == F_SETLK)
 			break;
-		}
+		error = wait_event_interruptible(file_lock->fl_wait,
+				!file_lock->fl_next);
+		if (!error)
+			continue;
+
+		locks_delete_block(file_lock);
+		break;
 	}

 	/*
@@ -1769,7 +1821,7 @@ out:
 */
 int fcntl_getlk64(struct file *filp, struct flock64 __user *l)
 {
-	struct file_lock *fl, cfl, file_lock;
+	struct file_lock file_lock;
 	struct flock64 flock;
 	int error;

@@ -1784,27 +1836,14 @@ int fcntl_getlk64(struct file *filp, struct flock64 __user *l)
 	if (error)
 		goto out;

-	if (filp->f_op && filp->f_op->lock) {
-		error = filp->f_op->lock(filp, F_GETLK, &file_lock);
-		if (file_lock.fl_ops && file_lock.fl_ops->fl_release_private)
-			file_lock.fl_ops->fl_release_private(&file_lock);
-		if (error < 0)
-			goto out;
-		else
-		  fl = (file_lock.fl_type == F_UNLCK ? NULL : &file_lock);
-	} else {
-		fl = (posix_test_lock(filp, &file_lock, &cfl) ? &cfl : NULL);
-	}
- 
-	flock.l_type = F_UNLCK;
-	if (fl != NULL) {
-		flock.l_pid = fl->fl_pid;
-		flock.l_start = fl->fl_start;
-		flock.l_len = fl->fl_end == OFFSET_MAX ? 0 :
-			fl->fl_end - fl->fl_start + 1;
-		flock.l_whence = 0;
-		flock.l_type = fl->fl_type;
-	}
+	error = vfs_test_lock(filp, &file_lock);
+	if (error)
+		goto out;
+
+	flock.l_type = file_lock.fl_type;
+	if (file_lock.fl_type != F_UNLCK)
+		posix_lock_to_flock64(&flock, &file_lock);
+
 	error = -EFAULT;
 	if (!copy_to_user(l, &flock, sizeof(flock)))
 		error = 0;
@@ -1875,21 +1914,17 @@ again:
 	if (error)
 		goto out;

-	if (filp->f_op && filp->f_op->lock != NULL)
-		error = filp->f_op->lock(filp, cmd, file_lock);
-	else {
-		for (;;) {
-			error = posix_lock_file(filp, file_lock);
-			if ((error != -EAGAIN) || (cmd == F_SETLK64))
-				break;
-			error = wait_event_interruptible(file_lock->fl_wait,
-					!file_lock->fl_next);
-			if (!error)
-				continue;
-
-			locks_delete_block(file_lock);
+	for (;;) {
+		error = vfs_lock_file(filp, cmd, file_lock, NULL);
+		if (error != -EAGAIN || cmd == F_SETLK64)
 			break;
-		}
+		error = wait_event_interruptible(file_lock->fl_wait,
+				!file_lock->fl_next);
+		if (!error)
+			continue;
+
+		locks_delete_block(file_lock);
+		break;
 	}

 	/*
@@ -1934,10 +1969,7 @@ void locks_remove_posix(struct file *filp, fl_owner_t owner)
 	lock.fl_ops = NULL;
 	lock.fl_lmops = NULL;

-	if (filp->f_op && filp->f_op->lock != NULL)
-		filp->f_op->lock(filp, F_SETLK, &lock);
-	else
-		posix_lock_file(filp, &lock);
+	vfs_lock_file(filp, F_SETLK, &lock, NULL);

 	if (lock.fl_ops && lock.fl_ops->fl_release_private)
 		lock.fl_ops->fl_release_private(&lock);
@@ -2014,6 +2046,22 @@ posix_unblock_lock(struct file *filp, struct file_lock *waiter)

 EXPORT_SYMBOL(posix_unblock_lock);

+/**
+ * vfs_cancel_lock - file byte range unblock lock
+ * @filp: The file to apply the unblock to
+ * @fl: The lock to be unblocked
+ *
+ * Used by lock managers to cancel blocked requests
+ */
+int vfs_cancel_lock(struct file *filp, struct file_lock *fl)
+{
+	if (filp->f_op && filp->f_op->lock)
+		return filp->f_op->lock(filp, F_CANCELLK, fl);
+	return 0;
+}
+
+EXPORT_SYMBOL_GPL(vfs_cancel_lock);
+
 static void lock_get_status(char* out, struct file_lock *fl, int id, char *pfx)
 {
 	struct inode *inode = NULL;