From: Dave Chinner <dchinner@xxxxxxxxxx>
This patch explicitly separates free inode chunk allocation and
inode allocation into two individual high level operations.
Reviewed-by: Darrick J. Wong <darrick.wong@xxxxxxxxxx>
Reviewed-by: Christoph Hellwig <hch@xxxxxx>
Signed-off-by: Dave Chinner <dchinner@xxxxxxxxxx>
Signed-off-by: Gao Xiang <hsiangkao@xxxxxxxxxx>
---
fs/xfs/libxfs/xfs_ialloc.c | 54 +++++++++++++++++---------------------
fs/xfs/libxfs/xfs_ialloc.h | 20 ++++++++++----
fs/xfs/xfs_inode.c | 18 ++++++++-----
3 files changed, 51 insertions(+), 41 deletions(-)
diff --git a/fs/xfs/libxfs/xfs_ialloc.c b/fs/xfs/libxfs/xfs_ialloc.c
index 074c2d83de77..dcb076d5c390 100644
--- a/fs/xfs/libxfs/xfs_ialloc.c
+++ b/fs/xfs/libxfs/xfs_ialloc.c
@@ -1570,7 +1570,7 @@ xfs_dialloc_ag_update_inobt(
* The caller selected an AG for us, and made sure that free inodes are
* available.
*/
-STATIC int
+int
xfs_dialloc_ag(
struct xfs_trans *tp,
struct xfs_buf *agbp,
@@ -1726,21 +1726,22 @@ xfs_dialloc_roll(
}
/*
- * Allocate an inode on disk.
+ * Select and prepare an AG for inode allocation.
*
- * Mode is used to tell whether the new inode will need space, and whether it
- * is a directory.
+ * Mode is used to tell whether the new inode is a directory and hence where to
+ * locate it.
*
- * 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.
+ * This function will ensure that the selected AG has free inodes available to
+ * allocate from. The selected AGI will be returned locked to the caller, and it
+ * will allocate more free inodes if required. If no free inodes are found or
+ * can be allocated, no AGI will be returned.
*/
int
-xfs_dialloc(
+xfs_dialloc_select_ag(
struct xfs_trans **tpp,
xfs_ino_t parent,
umode_t mode,
- xfs_ino_t *inop)
+ struct xfs_buf **IO_agbp)
{
struct xfs_mount *mp = (*tpp)->t_mountp;
struct xfs_buf *agbp;
@@ -1753,15 +1754,15 @@ xfs_dialloc(
struct xfs_ino_geometry *igeo = M_IGEO(mp);
bool okalloc = true;
+ *IO_agbp = NULL;
+
/*
* We do not have an agbp, so select an initial allocation
* group for inode allocation.
*/
start_agno = xfs_ialloc_ag_select(*tpp, parent, mode);
- if (start_agno == NULLAGNUMBER) {
- *inop = NULLFSINO;
+ if (start_agno == NULLAGNUMBER)
return 0;
- }
/*
* If we have already hit the ceiling of inode blocks then clear
@@ -1794,7 +1795,7 @@ xfs_dialloc(
if (!pag->pagi_init) {
error = xfs_ialloc_pagi_init(mp, *tpp, agno);
if (error)
- goto out_error;
+ break;
}
/*
@@ -1809,11 +1810,11 @@ xfs_dialloc(
*/
error = xfs_ialloc_read_agi(mp, *tpp, agno, &agbp);
if (error)
- goto out_error;
+ break;
if (pag->pagi_freecount) {
xfs_perag_put(pag);
- goto out_alloc;
+ goto found_ag;
}
if (!okalloc)
@@ -1824,12 +1825,9 @@ xfs_dialloc(
if (error) {
xfs_trans_brelse(*tpp, agbp);
- if (error != -ENOSPC)
- goto out_error;
-
- xfs_perag_put(pag);
- *inop = NULLFSINO;
- return 0;
+ if (error == -ENOSPC)
+ error = 0;
+ break;
}
if (ialloced) {
@@ -1846,9 +1844,7 @@ xfs_dialloc(
xfs_buf_relse(agbp);
return error;
}
-
- *inop = NULLFSINO;
- goto out_alloc;
+ goto found_ag;
}
nextag_relse_buffer:
@@ -1857,17 +1853,15 @@ xfs_dialloc(
xfs_perag_put(pag);
if (++agno == mp->m_sb.sb_agcount)
agno = 0;
- if (agno == start_agno) {
- *inop = NULLFSINO;
+ if (agno == start_agno)
return noroom ? -ENOSPC : 0;
- }
}
-out_alloc:
- return xfs_dialloc_ag(*tpp, agbp, parent, inop);
-out_error:
xfs_perag_put(pag);
return error;
+found_ag:
+ *IO_agbp = agbp;
+ return 0;
}
/*
diff --git a/fs/xfs/libxfs/xfs_ialloc.h b/fs/xfs/libxfs/xfs_ialloc.h
index 13810ffe4af9..3511086a7ae1 100644
--- a/fs/xfs/libxfs/xfs_ialloc.h
+++ b/fs/xfs/libxfs/xfs_ialloc.h
@@ -37,16 +37,26 @@ xfs_make_iptr(struct xfs_mount *mp, struct xfs_buf *b, int o)
* Mode is used to tell whether the new inode will need space, and whether
* it is a directory.
*
- * 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.
+ * There are two phases to inode allocation: selecting an AG and ensuring
+ * that it contains free inodes, followed by allocating one of the free
+ * inodes. xfs_dialloc_select_ag() does the former and returns a locked AGI
+ * to the caller, ensuring that followup call to xfs_dialloc_ag() will
+ * have free inodes to allocate from. xfs_dialloc_ag() will return the inode
+ * number of the free inode we allocated.
*/
int /* error */
-xfs_dialloc(
+xfs_dialloc_select_ag(
struct xfs_trans **tpp, /* double pointer of transaction */
xfs_ino_t parent, /* parent inode (directory) */
umode_t mode, /* mode bits for new inode */
- xfs_ino_t *inop); /* inode number allocated */
+ struct xfs_buf **IO_agbp);
+
+int
+xfs_dialloc_ag(
+ struct xfs_trans *tp,
+ struct xfs_buf *agbp,
+ xfs_ino_t parent,
+ xfs_ino_t *inop);
/*
* Free disk inode. Carefully avoids touching the incore inode, all
diff --git a/fs/xfs/xfs_inode.c b/fs/xfs/xfs_inode.c
index 860979fe18c3..3bbd3f5a57b1 100644
--- a/fs/xfs/xfs_inode.c
+++ b/fs/xfs/xfs_inode.c
@@ -906,10 +906,10 @@ xfs_dir_ialloc(
dev_t rdev,
prid_t prid) /* project id */
{
- xfs_inode_t *ip;
- xfs_ino_t parent_ino = dp ? dp->i_ino : 0;
- xfs_ino_t ino;
- int error;
+ struct xfs_buf *agibp;
+ xfs_ino_t parent_ino = dp ? dp->i_ino : 0;
+ xfs_ino_t ino;
+ int error;
ASSERT((*tpp)->t_flags & XFS_TRANS_PERM_LOG_RES);
@@ -917,13 +917,19 @@ xfs_dir_ialloc(
* Call the space management code to pick the on-disk inode to be
* allocated.
*/
- error = xfs_dialloc(tpp, parent_ino, mode, &ino);
+ error = xfs_dialloc_select_ag(tpp, parent_ino, mode, &agibp);
if (error)
return ERR_PTR(error);
- if (ino == NULLFSINO)
+ if (!agibp)
return ERR_PTR(-ENOSPC);
+ /* Allocate an inode from the selected AG */
+ error = xfs_dialloc_ag(*tpp, agibp, parent_ino, &ino);
+ if (error)
+ return ERR_PTR(error);
+ ASSERT(ino != NULLFSINO);
+
return xfs_init_new_inode(*tpp, dp, ino, mode, nlink, rdev, prid);
}
--
2.27.0
