From: Marc Eshel <eshel@xxxxxxxxxxxxxxx> - unquoted
Acquiring a lock on a cluster filesystem may require communication with remote
hosts, and to avoid blocking lockd or nfsd threads during such communication,
we allow the results to be returned asynchronously.
When a ->lock() call needs to block, the file system will return -EINPROGRESS,
and then later return the results with a call to the routine in the fl_notify
field of the lock_manager_operations struct.
Note that this is different from the ->lock() call discovering that there is a
conflict which would cause the caller to block; this is still handled in the
same way as before. In fact, we don't currently handle "blocking" locks at
all; those are less urgent, because the filesystem can always just return an
immediate -EAGAIN without denying the lock.
So this asynchronous interface is only used in the case of a non-blocking lock,
where we must know whether to allow or deny the lock now.
We're using fl_notify to asynchronously return the result of a lock
request. So we want fl_notify to be able to return a status and, if
appropriate, a conflicting lock.
This only current caller of fl_notify is in the blocked case, in which case
we don't use these extra arguments.
We also allow fl_notify to return an error. (Also ignored for now.)
Signed-off-by: J. Bruce Fields <bfields@xxxxxxxxxxxxxx>
---
fs/lockd/svclock.c | 7 ++++---
fs/locks.c | 21 ++++++++++++++++++++-
include/linux/fs.h | 2 +-
3 files changed, 25 insertions(+), 5 deletions(-)
diff --git a/fs/lockd/svclock.c b/fs/lockd/svclock.c
index 3b0e7a4..8c5c74f 100644
--- a/fs/lockd/svclock.c
+++ b/fs/lockd/svclock.c
@@ -509,12 +509,13 @@ nlmsvc_cancel_blocked(struct nlm_file *file, struct nlm_lock *lock)
* This function doesn't grant the blocked lock instantly, but rather moves
* the block to the head of nlm_blocked where it can be picked up by lockd.
*/
-static void
-nlmsvc_notify_blocked(struct file_lock *fl)
+static int
+nlmsvc_notify_blocked(struct file_lock *fl, struct file_lock *conf, int result)
{
struct nlm_block *block;
- dprintk("lockd: VFS unblock notification for block %p\n", fl);
+ dprintk("lockd: nlmsvc_notify_blocked lock %p conf %p result %d\n",
+ fl, conf, result);
list_for_each_entry(block, &nlm_blocked, b_list) {
if (nlm_compare_locks(&block->b_call->a_args.lock.fl, fl)) {
nlmsvc_insert_block(block, 0);
diff --git a/fs/locks.c b/fs/locks.c
index 62aea08..485b38a 100644
--- a/fs/locks.c
+++ b/fs/locks.c
@@ -544,7 +544,7 @@ static void locks_wake_up_blocks(struct file_lock *blocker)
struct file_lock, fl_block);
__locks_delete_block(waiter);
if (waiter->fl_lmops && waiter->fl_lmops->fl_notify)
- waiter->fl_lmops->fl_notify(waiter);
+ waiter->fl_lmops->fl_notify(waiter, NULL, -EAGAIN);
else
wake_up(&waiter->fl_wait);
}
@@ -1692,6 +1692,25 @@ out:
* @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.
+ *
+ * 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_notify 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_notify() 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_notify() 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)
{
diff --git a/include/linux/fs.h b/include/linux/fs.h
index c92d0bd..bec1dbe 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -784,7 +784,7 @@ struct file_lock_operations {
struct lock_manager_operations {
int (*fl_compare_owner)(struct file_lock *, struct file_lock *);
- void (*fl_notify)(struct file_lock *); /* unblock callback */
+ int (*fl_notify)(struct file_lock *, struct file_lock *, int);
void (*fl_copy_lock)(struct file_lock *, struct file_lock *);
void (*fl_release_private)(struct file_lock *);
void (*fl_break)(struct file_lock *);
--
1.5.0.rc1.gf4b6c
-
To unsubscribe from this list: send the line "unsubscribe linux-fsdevel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
