#include "xfs_buf_item.h"
#include "xfs_inode_item.h"
#include "xfs_btree.h"
+#include "xfs_btree_trace.h"
#include "xfs_alloc.h"
#include "xfs_ialloc.h"
#include "xfs_bmap.h"
}
/*
+ * Allocate and initialise an xfs_inode.
+ */
+struct xfs_inode *
+xfs_inode_alloc(
+ struct xfs_mount *mp,
+ xfs_ino_t ino)
+{
+ struct xfs_inode *ip;
+
+ /*
+ * if this didn't occur in transactions, we could use
+ * KM_MAYFAIL and return NULL here on ENOMEM. Set the
+ * code up to do this anyway.
+ */
+ ip = kmem_zone_alloc(xfs_inode_zone, KM_SLEEP);
+ if (!ip)
+ return NULL;
+
+ ASSERT(atomic_read(&ip->i_iocount) == 0);
+ ASSERT(atomic_read(&ip->i_pincount) == 0);
+ ASSERT(!spin_is_locked(&ip->i_flags_lock));
+ ASSERT(list_empty(&ip->i_reclaim));
+
+ ip->i_ino = ino;
+ ip->i_mount = mp;
+ ip->i_blkno = 0;
+ ip->i_len = 0;
+ ip->i_boffset =0;
+ ip->i_afp = NULL;
+ memset(&ip->i_df, 0, sizeof(xfs_ifork_t));
+ ip->i_flags = 0;
+ ip->i_update_core = 0;
+ ip->i_update_size = 0;
+ ip->i_delayed_blks = 0;
+ memset(&ip->i_d, 0, sizeof(xfs_icdinode_t));
+ ip->i_size = 0;
+ ip->i_new_size = 0;
+
+ /*
+ * Initialize inode's trace buffers.
+ */
+#ifdef XFS_INODE_TRACE
+ ip->i_trace = ktrace_alloc(INODE_TRACE_SIZE, KM_NOFS);
+#endif
+#ifdef XFS_BMAP_TRACE
+ ip->i_xtrace = ktrace_alloc(XFS_BMAP_KTRACE_SIZE, KM_NOFS);
+#endif
+#ifdef XFS_BTREE_TRACE
+ ip->i_btrace = ktrace_alloc(XFS_BMBT_KTRACE_SIZE, KM_NOFS);
+#endif
+#ifdef XFS_RW_TRACE
+ ip->i_rwtrace = ktrace_alloc(XFS_RW_KTRACE_SIZE, KM_NOFS);
+#endif
+#ifdef XFS_ILOCK_TRACE
+ ip->i_lock_trace = ktrace_alloc(XFS_ILOCK_KTRACE_SIZE, KM_NOFS);
+#endif
+#ifdef XFS_DIR2_TRACE
+ ip->i_dir_trace = ktrace_alloc(XFS_DIR2_KTRACE_SIZE, KM_NOFS);
+#endif
+
+ return ip;
+}
+
+/*
* Given a mount structure and an inode number, return a pointer
* to a newly allocated in-core inode corresponding to the given
* inode number.
xfs_inode_t *ip;
int error;
- ASSERT(xfs_inode_zone != NULL);
-
- ip = kmem_zone_zalloc(xfs_inode_zone, KM_SLEEP);
- ip->i_ino = ino;
- ip->i_mount = mp;
- atomic_set(&ip->i_iocount, 0);
- spin_lock_init(&ip->i_flags_lock);
+ ip = xfs_inode_alloc(mp, ino);
+ if (!ip)
+ return ENOMEM;
/*
* Get pointer's to the on-disk inode and the buffer containing it.
*/
error = xfs_itobp(mp, tp, ip, &dip, &bp, bno, imap_flags, XFS_BUF_LOCK);
if (error) {
- kmem_zone_free(xfs_inode_zone, ip);
+ xfs_idestroy(ip);
return error;
}
/*
- * Initialize inode's trace buffers.
- * Do this before xfs_iformat in case it adds entries.
- */
-#ifdef XFS_INODE_TRACE
- ip->i_trace = ktrace_alloc(INODE_TRACE_SIZE, KM_NOFS);
-#endif
-#ifdef XFS_BMAP_TRACE
- ip->i_xtrace = ktrace_alloc(XFS_BMAP_KTRACE_SIZE, KM_NOFS);
-#endif
-#ifdef XFS_BMBT_TRACE
- ip->i_btrace = ktrace_alloc(XFS_BMBT_KTRACE_SIZE, KM_NOFS);
-#endif
-#ifdef XFS_RW_TRACE
- ip->i_rwtrace = ktrace_alloc(XFS_RW_KTRACE_SIZE, KM_NOFS);
-#endif
-#ifdef XFS_ILOCK_TRACE
- ip->i_lock_trace = ktrace_alloc(XFS_ILOCK_KTRACE_SIZE, KM_NOFS);
-#endif
-#ifdef XFS_DIR2_TRACE
- ip->i_dir_trace = ktrace_alloc(XFS_DIR2_KTRACE_SIZE, KM_NOFS);
-#endif
-
- /*
* If we got something that isn't an inode it means someone
* (nfs or dmi) has a stale handle.
*/
if (be16_to_cpu(dip->di_core.di_magic) != XFS_DINODE_MAGIC) {
- kmem_zone_free(xfs_inode_zone, ip);
+ xfs_idestroy(ip);
xfs_trans_brelse(tp, bp);
#ifdef DEBUG
xfs_fs_cmn_err(CE_ALERT, mp, "xfs_iread: "
xfs_dinode_from_disk(&ip->i_d, &dip->di_core);
error = xfs_iformat(ip, dip);
if (error) {
- kmem_zone_free(xfs_inode_zone, ip);
+ xfs_idestroy(ip);
xfs_trans_brelse(tp, bp);
#ifdef DEBUG
xfs_fs_cmn_err(CE_ALERT, mp, "xfs_iread: "
XFS_IFORK_DSIZE(ip) / (uint)sizeof(xfs_bmbt_rec_t);
}
- INIT_LIST_HEAD(&ip->i_reclaim);
-
/*
* The inode format changed when we moved the link count and
* made it 32 bits long. If this is an old format inode,
}
if (ip->i_afp)
xfs_idestroy_fork(ip, XFS_ATTR_FORK);
- mrfree(&ip->i_lock);
- mrfree(&ip->i_iolock);
#ifdef XFS_INODE_TRACE
ktrace_free(ip->i_trace);
#ifdef XFS_BMAP_TRACE
ktrace_free(ip->i_xtrace);
#endif
-#ifdef XFS_BMBT_TRACE
+#ifdef XFS_BTREE_TRACE
ktrace_free(ip->i_btrace);
#endif
#ifdef XFS_RW_TRACE
spin_unlock(&mp->m_ail_lock);
}
xfs_inode_item_destroy(ip);
+ ip->i_itemp = NULL;
}
+ /* asserts to verify all state is correct here */
+ ASSERT(atomic_read(&ip->i_iocount) == 0);
+ ASSERT(atomic_read(&ip->i_pincount) == 0);
+ ASSERT(!spin_is_locked(&ip->i_flags_lock));
+ ASSERT(list_empty(&ip->i_reclaim));
kmem_zone_free(xfs_inode_zone, ip);
}
ASSERT(nextents <= XFS_LINEAR_EXTS);
size = nextents * sizeof(xfs_bmbt_rec_t);
- xfs_iext_irec_compact_full(ifp);
+ xfs_iext_irec_compact_pages(ifp);
ASSERT(ifp->if_real_bytes == XFS_IEXT_BUFSZ);
ep = ifp->if_u1.if_ext_irec->er_extbuf;
* compaction policy is as follows:
*
* Full Compaction: Extents fit into a single page (or inline buffer)
- * Full Compaction: Extents occupy less than 10% of allocated space
- * Partial Compaction: Extents occupy > 10% and < 50% of allocated space
+ * Partial Compaction: Extents occupy less than 50% of allocated space
* No Compaction: Extents occupy at least 50% of allocated space
*/
void
xfs_iext_direct_to_inline(ifp, nextents);
} else if (nextents <= XFS_LINEAR_EXTS) {
xfs_iext_indirect_to_direct(ifp);
- } else if (nextents < (nlists * XFS_LINEAR_EXTS) >> 3) {
- xfs_iext_irec_compact_full(ifp);
} else if (nextents < (nlists * XFS_LINEAR_EXTS) >> 1) {
xfs_iext_irec_compact_pages(ifp);
}
erp_next = erp + 1;
if (erp_next->er_extcount <=
(XFS_LINEAR_EXTS - erp->er_extcount)) {
- memmove(&erp->er_extbuf[erp->er_extcount],
+ memcpy(&erp->er_extbuf[erp->er_extcount],
erp_next->er_extbuf, erp_next->er_extcount *
sizeof(xfs_bmbt_rec_t));
erp->er_extcount += erp_next->er_extcount;
}
/*
- * Fully compact the extent records managed by the indirection array.
- */
-void
-xfs_iext_irec_compact_full(
- xfs_ifork_t *ifp) /* inode fork pointer */
-{
- xfs_bmbt_rec_host_t *ep, *ep_next; /* extent record pointers */
- xfs_ext_irec_t *erp, *erp_next; /* extent irec pointers */
- int erp_idx = 0; /* extent irec index */
- int ext_avail; /* empty entries in ex list */
- int ext_diff; /* number of exts to add */
- int nlists; /* number of irec's (ex lists) */
-
- ASSERT(ifp->if_flags & XFS_IFEXTIREC);
-
- nlists = ifp->if_real_bytes / XFS_IEXT_BUFSZ;
- erp = ifp->if_u1.if_ext_irec;
- ep = &erp->er_extbuf[erp->er_extcount];
- erp_next = erp + 1;
- ep_next = erp_next->er_extbuf;
-
- while (erp_idx < nlists - 1) {
- /*
- * Check how many extent records are available in this irec.
- * If there is none skip the whole exercise.
- */
- ext_avail = XFS_LINEAR_EXTS - erp->er_extcount;
- if (ext_avail) {
-
- /*
- * Copy over as many as possible extent records into
- * the previous page.
- */
- ext_diff = MIN(ext_avail, erp_next->er_extcount);
- memcpy(ep, ep_next, ext_diff * sizeof(xfs_bmbt_rec_t));
- erp->er_extcount += ext_diff;
- erp_next->er_extcount -= ext_diff;
-
- /*
- * If the next irec is empty now we can simply
- * remove it.
- */
- if (erp_next->er_extcount == 0) {
- /*
- * Free page before removing extent record
- * so er_extoffs don't get modified in
- * xfs_iext_irec_remove.
- */
- kmem_free(erp_next->er_extbuf);
- erp_next->er_extbuf = NULL;
- xfs_iext_irec_remove(ifp, erp_idx + 1);
- erp = &ifp->if_u1.if_ext_irec[erp_idx];
- nlists = ifp->if_real_bytes / XFS_IEXT_BUFSZ;
-
- /*
- * If the next irec is not empty move up the content
- * that has not been copied to the previous page to
- * the beggining of this one.
- */
- } else {
- memmove(erp_next->er_extbuf, &ep_next[ext_diff],
- erp_next->er_extcount *
- sizeof(xfs_bmbt_rec_t));
- ep_next = erp_next->er_extbuf;
- memset(&ep_next[erp_next->er_extcount], 0,
- (XFS_LINEAR_EXTS -
- erp_next->er_extcount) *
- sizeof(xfs_bmbt_rec_t));
- erp_next->er_extoff += ext_diff;
- }
- }
-
- if (erp->er_extcount == XFS_LINEAR_EXTS) {
- erp_idx++;
- if (erp_idx < nlists)
- erp = &ifp->if_u1.if_ext_irec[erp_idx];
- else
- break;
- }
- ep = &erp->er_extbuf[erp->er_extcount];
- erp_next = erp + 1;
- ep_next = erp_next->er_extbuf;
- }
-}
-
-/*
* This is called to update the er_extoff field in the indirection
* array when extents have been added or removed from one of the
* extent lists. erp_idx contains the irec index to begin updating