@@ -439,6 +439,8 @@ lm_grant: no no no
lm_break: yes no no
lm_change yes no no
lm_breaker_owns_lease: yes no no
+lm_lock_expirable yes no no
+lm_expire_lock no no yes
====================== ============= ================= =========
buffer_head
@@ -896,6 +896,36 @@ static bool flock_locks_conflict(struct file_lock *caller_fl,
return locks_conflict(caller_fl, sys_fl);
}
+static bool
+resolve_lock_conflict_locked(struct file_lock_context *ctx,
+ struct file_lock *cfl, bool rwsem)
+{
+ void *ret, *owner;
+ void (*func)(void *priv);
+
+ if (cfl->fl_lmops && cfl->fl_lmops->lm_lock_expirable &&
+ cfl->fl_lmops->lm_expire_lock) {
+ ret = (*cfl->fl_lmops->lm_lock_expirable)(cfl);
+ if (!ret)
+ return false;
+ owner = cfl->fl_lmops->lm_mod_owner;
+ if (!owner)
+ return false;
+ func = cfl->fl_lmops->lm_expire_lock;
+ __module_get(owner);
+ if (rwsem)
+ percpu_up_read(&file_rwsem);
+ spin_unlock(&ctx->flc_lock);
+ (*func)(ret);
+ module_put(owner);
+ if (rwsem)
+ percpu_down_read(&file_rwsem);
+ spin_lock(&ctx->flc_lock);
+ return true;
+ }
+ return false;
+}
+
void
posix_test_lock(struct file *filp, struct file_lock *fl)
{
@@ -910,11 +940,14 @@ 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 (resolve_lock_conflict_locked(ctx, cfl, false))
+ goto retry;
+ locks_copy_conflock(fl, cfl);
+ goto out;
}
fl->fl_type = F_UNLCK;
out:
@@ -1108,6 +1141,7 @@ static int posix_lock_inode(struct inode *inode, struct file_lock *request,
percpu_down_read(&file_rwsem);
spin_lock(&ctx->flc_lock);
+retry:
/*
* New lock request. Walk all POSIX locks and look for conflicts. If
* there are any, either return error or put the request on the
@@ -1117,6 +1151,8 @@ 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 (resolve_lock_conflict_locked(ctx, fl, true))
+ goto retry;
if (conflock)
locks_copy_conflock(conflock, fl);
error = -EAGAIN;
@@ -1029,6 +1029,7 @@ struct file_lock_operations {
};
struct lock_manager_operations {
+ void *lm_mod_owner;
fl_owner_t (*lm_get_owner)(fl_owner_t);
void (*lm_put_owner)(fl_owner_t);
void (*lm_notify)(struct file_lock *); /* unblock callback */
@@ -1037,6 +1038,8 @@ 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_lock_expirable)(struct file_lock *cfl);
+ void (*lm_expire_lock)(void *data);
};
struct lock_manager {
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 a pointer to an opaque data if the lock conflict can be resolved otherwise returns NULL. This callback must be called with the flc_lock held so it can not block. lm_expire_lock is called with the returned value from lm_lock_expirable to resolve the conflict. 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. Signed-off-by: Dai Ngo <dai.ngo@oracle.com> --- Documentation/filesystems/locking.rst | 2 ++ fs/locks.c | 44 +++++++++++++++++++++++++++++++---- include/linux/fs.h | 3 +++ 3 files changed, 45 insertions(+), 4 deletions(-)