/*
* Select an allocation group to look for a free inode in, based on the parent
* inode and then mode. Return the allocation group buffer.
*/
STATIC xfs_buf_t * /* allocation group buffer */
xfs_ialloc_ag_select(
xfs_trans_t *tp, /* transaction pointer */
xfs_ino_t parent, /* parent directory inode number */
mode_t mode, /* bits set to indicate file type */
int okalloc) /* ok to allocate more space */
{
xfs_buf_t *agbp; /* allocation group header buffer */
xfs_agnumber_t agcount; /* number of ag's in the filesystem */
xfs_agnumber_t agno; /* current ag number */
int flags; /* alloc buffer locking flags */
xfs_extlen_t ineed; /* blocks needed for inode allocation */
xfs_extlen_t longest = 0; /* longest extent available */
xfs_mount_t *mp; /* mount point structure */
int needspace; /* file mode implies space allocated */
xfs_perag_t *pag; /* per allocation group data */
xfs_agnumber_t pagno; /* parent (starting) ag number */
/*
* Files of these types need at least one block if length > 0
* (and they won't fit in the inode, but that's hard to figure out).
*/
needspace = S_ISDIR(mode) || S_ISREG(mode) || S_ISLNK(mode);
mp = tp->t_mountp;
agcount = mp->m_maxagi;
if (S_ISDIR(mode))
pagno = xfs_ialloc_next_ag(mp);
else {
pagno = XFS_INO_TO_AGNO(mp, parent);
if (pagno >= agcount)
pagno = 0;
}
ASSERT(pagno < agcount);
/*
* Loop through allocation groups, looking for one with a little
* free space in it. Note we don't look for free inodes, exactly.
* Instead, we include whether there is a need to allocate inodes
* to mean that blocks must be allocated for them,
* if none are currently free.
*/
agno = pagno;
flags = XFS_ALLOC_FLAG_TRYLOCK;
down_read(&mp->m_peraglock);
for (;;) {
pag = &mp->m_perag[agno];
if (!pag->pagi_init) {
if (xfs_ialloc_read_agi(mp, tp, agno, &agbp)) {
agbp = NULL;
goto nextag;
}
} else
agbp = NULL;
if (!pag->pagi_inodeok) {
xfs_ialloc_next_ag(mp);
goto unlock_nextag;
}
/*
* Is there enough free space for the file plus a block
* of inodes (if we need to allocate some)?
*/
ineed = pag->pagi_freecount ? 0 : XFS_IALLOC_BLOCKS(mp);
if (ineed && !pag->pagf_init) {
if (agbp == NULL &&
xfs_ialloc_read_agi(mp, tp, agno, &agbp)) {
agbp = NULL;
goto nextag;
}
(void)xfs_alloc_pagf_init(mp, tp, agno, flags);
}
if (!ineed || pag->pagf_init) {
if (ineed && !(longest = pag->pagf_longest))
longest = pag->pagf_flcount > 0;
if (!ineed ||
(pag->pagf_freeblks >= needspace + ineed &&
longest >= ineed &&
okalloc)) {
if (agbp == NULL &&
xfs_ialloc_read_agi(mp, tp, agno, &agbp)) {
agbp = NULL;
goto nextag;
}
up_read(&mp->m_peraglock);
return agbp;
}
}
unlock_nextag:
if (agbp)
xfs_trans_brelse(tp, agbp);
nextag:
/*
* No point in iterating over the rest, if we're shutting
* down.
*/
if (XFS_FORCED_SHUTDOWN(mp)) {
up_read(&mp->m_peraglock);
return NULL;
}
agno++;
if (agno >= agcount)
agno = 0;
if (agno == pagno) {
if (flags == 0) {
up_read(&mp->m_peraglock);
return NULL;
}
flags = 0;
}
}
}
/*
* Allocate an inode on disk.
*
* Mode is used to tell whether the new inode will need space, and whether it
* is a directory.
*
* This function is designed to be called twice if it has to do an allocation
* to make more free inodes. On the first call, *IO_agbp should be set to NULL.
* If an inode is available without having to performn an allocation, an inode
* number is returned. In this case, *IO_agbp is set to NULL. If an allocation
* needs to be done, xfs_dialloc returns the current AGI buffer in *IO_agbp.
* The caller should then commit the current transaction, allocate a
* new transaction, and call xfs_dialloc() again, passing in the previous value
* of *IO_agbp. IO_agbp should be held across the transactions. Since the AGI
* buffer is locked across the two calls, the second call is guaranteed to have
* a free inode available.
*
* Once we successfully pick an inode its number is returned and the on-disk
* data structures are updated. The inode itself is not read in, since doing so
* would break ordering constraints with xfs_reclaim.
*/
int
xfs_dialloc(
struct xfs_trans *tp,
xfs_ino_t parent,
umode_t mode,
int okalloc,
struct xfs_buf **IO_agbp,
xfs_ino_t *inop)
{
struct xfs_mount *mp = tp->t_mountp;
struct xfs_buf *agbp;
xfs_agnumber_t agno;
int error;
int ialloced;
int noroom = 0;
xfs_agnumber_t start_agno;
struct xfs_perag *pag;
if (*IO_agbp) {
/*
* If the caller passes in a pointer to the AGI buffer,
* continue where we left off before. In this case, we
* know that the allocation group has free inodes.
*/
agbp = *IO_agbp;
goto out_alloc;
}
/*
* We do not have an agbp, so select an initial allocation
* group for inode allocation.
*/
start_agno = xfs_ialloc_ag_select(tp, parent, mode, okalloc);
if (start_agno == NULLAGNUMBER) {
*inop = NULLFSINO;
return 0;
}
/*
* If we have already hit the ceiling of inode blocks then clear
* okalloc so we scan all available agi structures for a free
* inode.
*/
if (mp->m_maxicount &&
mp->m_sb.sb_icount + XFS_IALLOC_INODES(mp) > mp->m_maxicount) {
noroom = 1;
okalloc = 0;
}
/*
* Loop until we find an allocation group that either has free inodes
* or in which we can allocate some inodes. Iterate through the
* allocation groups upward, wrapping at the end.
*/
agno = start_agno;
for (;;) {
pag = xfs_perag_get(mp, agno);
if (!pag->pagi_inodeok) {
xfs_ialloc_next_ag(mp);
goto nextag;
}
if (!pag->pagi_init) {
error = xfs_ialloc_pagi_init(mp, tp, agno);
if (error)
goto out_error;
}
/*
* Do a first racy fast path check if this AG is usable.
*/
if (!pag->pagi_freecount && !okalloc)
goto nextag;
/*
* Then read in the AGI buffer and recheck with the AGI buffer
* lock held.
*/
error = xfs_ialloc_read_agi(mp, tp, agno, &agbp);
if (error)
goto out_error;
if (pag->pagi_freecount) {
xfs_perag_put(pag);
goto out_alloc;
}
if (!okalloc)
goto nextag_relse_buffer;
error = xfs_ialloc_ag_alloc(tp, agbp, &ialloced);
if (error) {
xfs_trans_brelse(tp, agbp);
if (error != ENOSPC)
goto out_error;
xfs_perag_put(pag);
*inop = NULLFSINO;
return 0;
}
if (ialloced) {
/*
* We successfully allocated some inodes, return
* the current context to the caller so that it
* can commit the current transaction and call
* us again where we left off.
*/
ASSERT(pag->pagi_freecount > 0);
xfs_perag_put(pag);
*IO_agbp = agbp;
*inop = NULLFSINO;
return 0;
}
nextag_relse_buffer:
xfs_trans_brelse(tp, agbp);
nextag:
xfs_perag_put(pag);
if (++agno == mp->m_sb.sb_agcount)
agno = 0;
if (agno == start_agno) {
*inop = NULLFSINO;
return noroom ? ENOSPC : 0;
}
}
out_alloc:
*IO_agbp = NULL;
return xfs_dialloc_ag(tp, agbp, parent, inop);
out_error:
xfs_perag_put(pag);
return XFS_ERROR(error);
}