ceph: preallocate flock state without locks held
When the lock_kernel() turns into lock_flocks() and a spinlock, we won't be able to do allocations with the lock held. Preallocate space without the lock, and retry if the lock state changes out from underneath us. Signed-off-by: Greg Farnum <gregf@hq.newdream.net> Signed-off-by: Sage Weil <sage@newdream.net>
This commit is contained in:
parent
ac0b74d8a1
commit
fca4451acf
|
@ -181,8 +181,9 @@ void ceph_count_locks(struct inode *inode, int *fcntl_count, int *flock_count)
|
|||
* Encode the flock and fcntl locks for the given inode into the pagelist.
|
||||
* Format is: #fcntl locks, sequential fcntl locks, #flock locks,
|
||||
* sequential flock locks.
|
||||
* Must be called with BLK already held, and the lock numbers should have
|
||||
* been gathered under the same lock holding window.
|
||||
* Must be called with lock_flocks() already held.
|
||||
* If we encounter more of a specific lock type than expected,
|
||||
* we return the value 1.
|
||||
*/
|
||||
int ceph_encode_locks(struct inode *inode, struct ceph_pagelist *pagelist,
|
||||
int num_fcntl_locks, int num_flock_locks)
|
||||
|
@ -190,6 +191,8 @@ int ceph_encode_locks(struct inode *inode, struct ceph_pagelist *pagelist,
|
|||
struct file_lock *lock;
|
||||
struct ceph_filelock cephlock;
|
||||
int err = 0;
|
||||
int seen_fcntl = 0;
|
||||
int seen_flock = 0;
|
||||
|
||||
dout("encoding %d flock and %d fcntl locks", num_flock_locks,
|
||||
num_fcntl_locks);
|
||||
|
@ -198,6 +201,11 @@ int ceph_encode_locks(struct inode *inode, struct ceph_pagelist *pagelist,
|
|||
goto fail;
|
||||
for (lock = inode->i_flock; lock != NULL; lock = lock->fl_next) {
|
||||
if (lock->fl_flags & FL_POSIX) {
|
||||
++seen_fcntl;
|
||||
if (seen_fcntl > num_fcntl_locks) {
|
||||
err = -ENOSPC;
|
||||
goto fail;
|
||||
}
|
||||
err = lock_to_ceph_filelock(lock, &cephlock);
|
||||
if (err)
|
||||
goto fail;
|
||||
|
@ -213,6 +221,11 @@ int ceph_encode_locks(struct inode *inode, struct ceph_pagelist *pagelist,
|
|||
goto fail;
|
||||
for (lock = inode->i_flock; lock != NULL; lock = lock->fl_next) {
|
||||
if (lock->fl_flags & FL_FLOCK) {
|
||||
++seen_flock;
|
||||
if (seen_flock > num_flock_locks) {
|
||||
err = -ENOSPC;
|
||||
goto fail;
|
||||
}
|
||||
err = lock_to_ceph_filelock(lock, &cephlock);
|
||||
if (err)
|
||||
goto fail;
|
||||
|
|
|
@ -2365,19 +2365,35 @@ static int encode_caps_cb(struct inode *inode, struct ceph_cap *cap,
|
|||
|
||||
if (recon_state->flock) {
|
||||
int num_fcntl_locks, num_flock_locks;
|
||||
struct ceph_pagelist_cursor trunc_point;
|
||||
|
||||
lock_kernel();
|
||||
ceph_count_locks(inode, &num_fcntl_locks, &num_flock_locks);
|
||||
rec.v2.flock_len = (2*sizeof(u32) +
|
||||
(num_fcntl_locks+num_flock_locks) *
|
||||
sizeof(struct ceph_filelock));
|
||||
ceph_pagelist_set_cursor(pagelist, &trunc_point);
|
||||
do {
|
||||
lock_kernel();
|
||||
ceph_count_locks(inode, &num_fcntl_locks,
|
||||
&num_flock_locks);
|
||||
rec.v2.flock_len = (2*sizeof(u32) +
|
||||
(num_fcntl_locks+num_flock_locks) *
|
||||
sizeof(struct ceph_filelock));
|
||||
unlock_kernel();
|
||||
|
||||
err = ceph_pagelist_append(pagelist, &rec, reclen);
|
||||
if (!err)
|
||||
err = ceph_encode_locks(inode, pagelist,
|
||||
num_fcntl_locks,
|
||||
num_flock_locks);
|
||||
unlock_kernel();
|
||||
/* pre-alloc pagelist */
|
||||
ceph_pagelist_truncate(pagelist, &trunc_point);
|
||||
err = ceph_pagelist_append(pagelist, &rec, reclen);
|
||||
if (!err)
|
||||
err = ceph_pagelist_reserve(pagelist,
|
||||
rec.v2.flock_len);
|
||||
|
||||
/* encode locks */
|
||||
if (!err) {
|
||||
lock_kernel();
|
||||
err = ceph_encode_locks(inode,
|
||||
pagelist,
|
||||
num_fcntl_locks,
|
||||
num_flock_locks);
|
||||
unlock_kernel();
|
||||
}
|
||||
} while (err == -ENOSPC);
|
||||
} else {
|
||||
err = ceph_pagelist_append(pagelist, &rec, reclen);
|
||||
}
|
||||
|
|
Loading…
Reference in New Issue