On Dec 13, 2021, at 12:24 PM, Dai Ngo [off-list ref] wrote:

Add new callback, lm_expire_lock, to lock_manager_operations to allow
the lock manager to take appropriate action to resolve the lock conflict
if possible. The callback takes 2 arguments, file_lock of the blocker
and a testonly flag:

testonly = 1  check and return lock manager's private data if lock conflict
             can be resolved else return NULL.
testonly = 0  resolve the conflict if possible, return true if conflict
             was resolved esle return false.

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.

Signed-off-by: Dai Ngo <dai.ngo@oracle.com>
---
fs/locks.c         | 40 +++++++++++++++++++++++++++++++++++++---
include/linux/fs.h |  1 +
2 files changed, 38 insertions(+), 3 deletions(-)

diff --git a/fs/locks.c b/fs/locks.c
index 3d6fb4ae847b..5f3ea40ce2aa 100644
--- a/fs/locks.c
+++ b/fs/locks.c

@@ -952,8 +952,11 @@ void

posix_test_lock(struct file *filp, struct file_lock *fl)
{
	struct file_lock *cfl;
+	struct file_lock *checked_cfl = NULL;
	struct file_lock_context *ctx;
	struct inode *inode = locks_inode(filp);
+	void *res_data;
+	void *(*func)(void *priv, bool testonly);

	ctx = smp_load_acquire(&inode->i_flctx);
	if (!ctx || list_empty_careful(&ctx->flc_posix)) {

@@ -962,11 +965,24 @@ posix_test_lock(struct file *filp, struct file_lock *fl)

	}

	spin_lock(&ctx->flc_lock);
+retry:
	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 (checked_cfl != cfl && cfl->fl_lmops &&
+				cfl->fl_lmops->lm_expire_lock) {
+			res_data = cfl->fl_lmops->lm_expire_lock(cfl, true);
+			if (res_data) {
+				func = cfl->fl_lmops->lm_expire_lock;
+				spin_unlock(&ctx->flc_lock);
+				func(res_data, false);
+				spin_lock(&ctx->flc_lock);
+				checked_cfl = cfl;
+				goto retry;
+			}
		}

+		locks_copy_conflock(fl, cfl);
+		goto out;
	}
	fl->fl_type = F_UNLCK;
out:

@@ -1136,10 +1152,13 @@ static int posix_lock_inode(struct inode *inode, struct file_lock *request,

	struct file_lock *new_fl2 = NULL;
	struct file_lock *left = NULL;
	struct file_lock *right = NULL;
+	struct file_lock *checked_fl = NULL;
	struct file_lock_context *ctx;
	int error;
	bool added = false;
	LIST_HEAD(dispose);
+	void *res_data;
+	void *(*func)(void *priv, bool testonly);

	ctx = locks_get_lock_context(inode, request->fl_type);
	if (!ctx)

@@ -1166,9 +1185,24 @@ static int posix_lock_inode(struct inode *inode, struct file_lock *request,

	 * blocker's list of waiters and the global blocked_hash.
	 */
	if (request->fl_type != F_UNLCK) {
+retry:
		list_for_each_entry(fl, &ctx->flc_posix, fl_list) {
			if (!posix_locks_conflict(request, fl))
				continue;
+			if (checked_fl != fl && fl->fl_lmops &&
+					fl->fl_lmops->lm_expire_lock) {
+				res_data = fl->fl_lmops->lm_expire_lock(fl, true);
+				if (res_data) {
+					func = fl->fl_lmops->lm_expire_lock;
+					spin_unlock(&ctx->flc_lock);
+					percpu_up_read(&file_rwsem);
+					func(res_data, false);
+					percpu_down_read(&file_rwsem);
+					spin_lock(&ctx->flc_lock);
+					checked_fl = fl;
+					goto retry;
+				}
+			}
			if (conflock)
				locks_copy_conflock(conflock, fl);
			error = -EAGAIN;

diff --git a/include/linux/fs.h b/include/linux/fs.h
index e7a633353fd2..8cb910c3a394 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h

@@ -1071,6 +1071,7 @@ struct lock_manager_operations {

	int (*lm_change)(struct file_lock *, int, struct list_head *);
	void (*lm_setup)(struct file_lock *, void **);
	bool (*lm_breaker_owns_lease)(struct file_lock *);
+	void *(*lm_expire_lock)(void *priv, bool testonly);
};

struct lock_manager {
-- 
2.9.5