/*
* Grab the exclusive iolock for a data copy from src to dest, making
* sure to abide vfs locking order (lowest pointer value goes first) and
* breaking the pnfs layout leases on dest before proceeding. The loop
* is needed because we cannot call the blocking break_layout() with the
* src iolock held, and therefore have to back out both locks.
*/
static int
xfs_iolock_two_inodes_and_break_layout(
struct inode *src,
struct inode *dest)
{
int error;
retry:
if (src < dest) {
inode_lock_shared(src);
inode_lock_nested(dest, I_MUTEX_NONDIR2);
} else {
/* src >= dest */
inode_lock(dest);
}
error = break_layout(dest, false);
if (error == -EWOULDBLOCK) {
inode_unlock(dest);
if (src < dest)
inode_unlock_shared(src);
error = break_layout(dest, true);
if (error)
return error;
goto retry;
}
if (error) {
inode_unlock(dest);
if (src < dest)
inode_unlock_shared(src);
return error;
}
if (src > dest)
inode_lock_shared_nested(src, I_MUTEX_NONDIR2);
return 0;
}
/*
* Ensure that we do not have any outstanding pNFS layouts that can be used by
* clients to directly read from or write to this inode. This must be called
* before every operation that can remove blocks from the extent map.
* Additionally we call it during the write operation, where aren't concerned
* about exposing unallocated blocks but just want to provide basic
* synchronization between a local writer and pNFS clients. mmap writes would
* also benefit from this sort of synchronization, but due to the tricky locking
* rules in the page fault path we don't bother.
*/
int
xfs_break_layouts(
struct inode *inode,
uint *iolock,
bool with_imutex)
{
struct xfs_inode *ip = XFS_I(inode);
int error;
ASSERT(xfs_isilocked(ip, XFS_IOLOCK_SHARED|XFS_IOLOCK_EXCL));
while ((error = break_layout(inode, false) == -EWOULDBLOCK)) {
xfs_iunlock(ip, *iolock);
if (with_imutex && (*iolock & XFS_IOLOCK_EXCL))
inode_unlock(inode);
error = break_layout(inode, true);
*iolock = XFS_IOLOCK_EXCL;
if (with_imutex)
inode_lock(inode);
xfs_ilock(ip, *iolock);
}
return error;
}
