fs/lock: add 2 callbacks to lock_manager_operations to resolve conflict

Add 2 new callbacks, lm_lock_expirable and lm_expire_lock, to
lock_manager_operations to allow the lock manager to take appropriate
action to resolve the lock conflict if possible.

A new field, lm_mod_owner, is also added to lock_manager_operations.
The lm_mod_owner is used by the fs/lock code to make sure the lock
manager module such as nfsd, is not freed while lock conflict is being
resolved.

lm_lock_expirable checks and returns true to indicate that the lock
conflict can be resolved else return false. This callback must be
called with the flc_lock held so it can not block.

lm_expire_lock is called to resolve the lock conflict if the returned
value from lm_lock_expirable is true. This callback is called without
the flc_lock held since it's allowed to block. Upon returning from
this callback, the lock conflict should be resolved and the caller is
expected to restart the conflict check from the beginnning of the list.

Lock manager, such as NFSv4 courteous server, uses this callback to
resolve conflict by destroying lock owner, or the NFSv4 courtesy client
(client that has expired but allowed to maintains its states) that owns
the lock.

Reviewed-by: J. Bruce Fields <bfields@fieldses.org>
Signed-off-by: Dai Ngo <dai.ngo@oracle.com>
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
Reviewed-by: Jeff Layton <jlayton@kernel.org>

1 files changed, 30 insertions, 3 deletions

diff --git a/fs/locks.c b/fs/locks.c
index c369841ef7d1..ca28e0e50e56 100644
--- a/fs/locks.c
+++ b/fs/locks.c
@@ -902,6 +902,8 @@ posix_test_lock(struct file *filp, struct file_lock *fl)
 	struct file_lock *cfl;
 	struct file_lock_context *ctx;
 	struct inode *inode = locks_inode(filp);
+	void *owner;
+	void (*func)(void);
 
 	ctx = smp_load_acquire(&inode->i_flctx);
 	if (!ctx || list_empty_careful(&ctx->flc_posix)) {
@@ -909,12 +911,23 @@ posix_test_lock(struct file *filp, struct file_lock *fl)
 		return;
 	}
 
+retry:
 	spin_lock(&ctx->flc_lock);
 	list_for_each_entry(cfl, &ctx->flc_posix, fl_list) {
-		if (posix_locks_conflict(fl, cfl)) {
-			locks_copy_conflock(fl, cfl);
-			goto out;
+		if (!posix_locks_conflict(fl, cfl))
+			continue;
+		if (cfl->fl_lmops && cfl->fl_lmops->lm_lock_expirable
+			&& (*cfl->fl_lmops->lm_lock_expirable)(cfl)) {
+			owner = cfl->fl_lmops->lm_mod_owner;
+			func = cfl->fl_lmops->lm_expire_lock;
+			__module_get(owner);
+			spin_unlock(&ctx->flc_lock);
+			(*func)();
+			module_put(owner);
+			goto retry;
 		}
+		locks_copy_conflock(fl, cfl);
+		goto out;
 	}
 	fl->fl_type = F_UNLCK;
 out:
@@ -1088,6 +1101,8 @@ static int posix_lock_inode(struct inode *inode, struct file_lock *request,
 	int error;
 	bool added = false;
 	LIST_HEAD(dispose);
+	void *owner;
+	void (*func)(void);
 
 	ctx = locks_get_lock_context(inode, request->fl_type);
 	if (!ctx)
@@ -1106,6 +1121,7 @@ static int posix_lock_inode(struct inode *inode, struct file_lock *request,
 		new_fl2 = locks_alloc_lock();
 	}
 
+retry:
 	percpu_down_read(&file_rwsem);
 	spin_lock(&ctx->flc_lock);
 	/*
@@ -1117,6 +1133,17 @@ static int posix_lock_inode(struct inode *inode, struct file_lock *request,
 		list_for_each_entry(fl, &ctx->flc_posix, fl_list) {
 			if (!posix_locks_conflict(request, fl))
 				continue;
+			if (fl->fl_lmops && fl->fl_lmops->lm_lock_expirable
+				&& (*fl->fl_lmops->lm_lock_expirable)(fl)) {
+				owner = fl->fl_lmops->lm_mod_owner;
+				func = fl->fl_lmops->lm_expire_lock;
+				__module_get(owner);
+				spin_unlock(&ctx->flc_lock);
+				percpu_up_read(&file_rwsem);
+				(*func)();
+				module_put(owner);
+				goto retry;
+			}
 			if (conflock)
 				locks_copy_conflock(conflock, fl);
 			error = -EAGAIN;