1 files changed, 84 insertions, 140 deletions

diff --git a/fs/xfs/xfs_inode.c b/fs/xfs/xfs_inode.c
index b210224..a59eea0 100644
--- a/fs/xfs/xfs_inode.c
+++ b/fs/xfs/xfs_inode.c
@@ -20,7 +20,6 @@
 #include "xfs.h"
 #include "xfs_fs.h"
 #include "xfs_types.h"
-#include "xfs_bit.h"
 #include "xfs_log.h"
 #include "xfs_inum.h"
 #include "xfs_trans.h"
@@ -61,6 +60,20 @@ STATIC int xfs_iformat_local(xfs_inode_t *, xfs_dinode_t *, int, int);
 STATIC int xfs_iformat_extents(xfs_inode_t *, xfs_dinode_t *, int);
 STATIC int xfs_iformat_btree(xfs_inode_t *, xfs_dinode_t *, int);
 
+/*
+ * helper function to extract extent size hint from inode
+ */
+xfs_extlen_t
+xfs_get_extsz_hint(
+	struct xfs_inode	*ip)
+{
+	if ((ip->i_d.di_flags & XFS_DIFLAG_EXTSIZE) && ip->i_d.di_extsize)
+		return ip->i_d.di_extsize;
+	if (XFS_IS_REALTIME_INODE(ip))
+		return ip->i_mount->m_sb.sb_rextsize;
+	return 0;
+}
+
 #ifdef DEBUG
 /*
  * Make sure that the extents in the given memory buffer
@@ -137,6 +150,7 @@ xfs_imap_to_bp(
 	int		ni;
 	xfs_buf_t	*bp;
 
+	buf_flags |= XBF_UNMAPPED;
 	error = xfs_trans_read_buf(mp, tp, mp->m_ddev_targp, imap->im_blkno,
 				   (int)imap->im_len, buf_flags, &bp);
 	if (error) {
@@ -226,7 +240,7 @@ xfs_inotobp(
 	if (error)
 		return error;
 
-	error = xfs_imap_to_bp(mp, tp, &imap, &bp, XBF_LOCK, imap_flags);
+	error = xfs_imap_to_bp(mp, tp, &imap, &bp, 0, imap_flags);
 	if (error)
 		return error;
 
@@ -782,8 +796,7 @@ xfs_iread(
 	/*
 	 * Get pointers to the on-disk inode and the buffer containing it.
 	 */
-	error = xfs_imap_to_bp(mp, tp, &ip->i_imap, &bp,
-			       XBF_LOCK, iget_flags);
+	error = xfs_imap_to_bp(mp, tp, &ip->i_imap, &bp, 0, iget_flags);
 	if (error)
 		return error;
 	dip = (xfs_dinode_t *)xfs_buf_offset(bp, ip->i_imap.im_boffset);
@@ -1342,7 +1355,7 @@ xfs_iunlink(
 		 * Here we put the head pointer into our next pointer,
 		 * and then we fall through to point the head at us.
 		 */
-		error = xfs_itobp(mp, tp, ip, &dip, &ibp, XBF_LOCK);
+		error = xfs_itobp(mp, tp, ip, &dip, &ibp, 0);
 		if (error)
 			return error;
 
@@ -1423,7 +1436,7 @@ xfs_iunlink_remove(
 		 * of dealing with the buffer when there is no need to
 		 * change it.
 		 */
-		error = xfs_itobp(mp, tp, ip, &dip, &ibp, XBF_LOCK);
+		error = xfs_itobp(mp, tp, ip, &dip, &ibp, 0);
 		if (error) {
 			xfs_warn(mp, "%s: xfs_itobp() returned error %d.",
 				__func__, error);
@@ -1484,7 +1497,7 @@ xfs_iunlink_remove(
 		 * Now last_ibp points to the buffer previous to us on
 		 * the unlinked list.  Pull us from the list.
 		 */
-		error = xfs_itobp(mp, tp, ip, &dip, &ibp, XBF_LOCK);
+		error = xfs_itobp(mp, tp, ip, &dip, &ibp, 0);
 		if (error) {
 			xfs_warn(mp, "%s: xfs_itobp(2) returned error %d.",
 				__func__, error);
@@ -1566,8 +1579,7 @@ xfs_ifree_cluster(
 		 * to mark all the active inodes on the buffer stale.
 		 */
 		bp = xfs_trans_get_buf(tp, mp->m_ddev_targp, blkno,
-					mp->m_bsize * blks_per_cluster,
-					XBF_LOCK);
+					mp->m_bsize * blks_per_cluster, 0);
 
 		if (!bp)
 			return ENOMEM;
@@ -1656,14 +1668,13 @@ retry:
 			iip = ip->i_itemp;
 			if (!iip || xfs_inode_clean(ip)) {
 				ASSERT(ip != free_ip);
-				ip->i_update_core = 0;
 				xfs_ifunlock(ip);
 				xfs_iunlock(ip, XFS_ILOCK_EXCL);
 				continue;
 			}
 
-			iip->ili_last_fields = iip->ili_format.ilf_fields;
-			iip->ili_format.ilf_fields = 0;
+			iip->ili_last_fields = iip->ili_fields;
+			iip->ili_fields = 0;
 			iip->ili_logged = 1;
 			xfs_trans_ail_copy_lsn(mp->m_ail, &iip->ili_flush_lsn,
 						&iip->ili_item.li_lsn);
@@ -1738,7 +1749,7 @@ xfs_ifree(
 
 	xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);
 
-	error = xfs_itobp(ip->i_mount, tp, ip, &dip, &ibp, XBF_LOCK);
+	error = xfs_itobp(ip->i_mount, tp, ip, &dip, &ibp, 0);
 	if (error)
 		return error;
 
@@ -2177,7 +2188,7 @@ xfs_iflush_fork(
 	mp = ip->i_mount;
 	switch (XFS_IFORK_FORMAT(ip, whichfork)) {
 	case XFS_DINODE_FMT_LOCAL:
-		if ((iip->ili_format.ilf_fields & dataflag[whichfork]) &&
+		if ((iip->ili_fields & dataflag[whichfork]) &&
 		    (ifp->if_bytes > 0)) {
 			ASSERT(ifp->if_u1.if_data != NULL);
 			ASSERT(ifp->if_bytes <= XFS_IFORK_SIZE(ip, whichfork));
@@ -2187,8 +2198,8 @@ xfs_iflush_fork(
 
 	case XFS_DINODE_FMT_EXTENTS:
 		ASSERT((ifp->if_flags & XFS_IFEXTENTS) ||
-		       !(iip->ili_format.ilf_fields & extflag[whichfork]));
-		if ((iip->ili_format.ilf_fields & extflag[whichfork]) &&
+		       !(iip->ili_fields & extflag[whichfork]));
+		if ((iip->ili_fields & extflag[whichfork]) &&
 		    (ifp->if_bytes > 0)) {
 			ASSERT(xfs_iext_get_ext(ifp, 0));
 			ASSERT(XFS_IFORK_NEXTENTS(ip, whichfork) > 0);
@@ -2198,7 +2209,7 @@ xfs_iflush_fork(
 		break;
 
 	case XFS_DINODE_FMT_BTREE:
-		if ((iip->ili_format.ilf_fields & brootflag[whichfork]) &&
+		if ((iip->ili_fields & brootflag[whichfork]) &&
 		    (ifp->if_broot_bytes > 0)) {
 			ASSERT(ifp->if_broot != NULL);
 			ASSERT(ifp->if_broot_bytes <=
@@ -2211,14 +2222,14 @@ xfs_iflush_fork(
 		break;
 
 	case XFS_DINODE_FMT_DEV:
-		if (iip->ili_format.ilf_fields & XFS_ILOG_DEV) {
+		if (iip->ili_fields & XFS_ILOG_DEV) {
 			ASSERT(whichfork == XFS_DATA_FORK);
 			xfs_dinode_put_rdev(dip, ip->i_df.if_u2.if_rdev);
 		}
 		break;
 
 	case XFS_DINODE_FMT_UUID:
-		if (iip->ili_format.ilf_fields & XFS_ILOG_UUID) {
+		if (iip->ili_fields & XFS_ILOG_UUID) {
 			ASSERT(whichfork == XFS_DATA_FORK);
 			memcpy(XFS_DFORK_DPTR(dip),
 			       &ip->i_df.if_u2.if_uuid,
@@ -2348,11 +2359,11 @@ cluster_corrupt_out:
 	 */
 	rcu_read_unlock();
 	/*
-	 * Clean up the buffer.  If it was B_DELWRI, just release it --
+	 * Clean up the buffer.  If it was delwri, just release it --
 	 * brelse can handle it with no problems.  If not, shut down the
 	 * filesystem before releasing the buffer.
 	 */
-	bufwasdelwri = XFS_BUF_ISDELAYWRITE(bp);
+	bufwasdelwri = (bp->b_flags & _XBF_DELWRI_Q);
 	if (bufwasdelwri)
 		xfs_buf_relse(bp);
 
@@ -2378,30 +2389,29 @@ cluster_corrupt_out:
 	/*
 	 * Unlocks the flush lock
 	 */
-	xfs_iflush_abort(iq);
+	xfs_iflush_abort(iq, false);
 	kmem_free(ilist);
 	xfs_perag_put(pag);
 	return XFS_ERROR(EFSCORRUPTED);
 }
 
 /*
- * xfs_iflush() will write a modified inode's changes out to the
- * inode's on disk home.  The caller must have the inode lock held
- * in at least shared mode and the inode flush completion must be
- * active as well.  The inode lock will still be held upon return from
- * the call and the caller is free to unlock it.
- * The inode flush will be completed when the inode reaches the disk.
- * The flags indicate how the inode's buffer should be written out.
+ * Flush dirty inode metadata into the backing buffer.
+ *
+ * The caller must have the inode lock and the inode flush lock held.  The
+ * inode lock will still be held upon return to the caller, and the inode
+ * flush lock will be released after the inode has reached the disk.
+ *
+ * The caller must write out the buffer returned in *bpp and release it.
  */
 int
 xfs_iflush(
-	xfs_inode_t		*ip,
-	uint			flags)
+	struct xfs_inode	*ip,
+	struct xfs_buf		**bpp)
 {
-	xfs_inode_log_item_t	*iip;
-	xfs_buf_t		*bp;
-	xfs_dinode_t		*dip;
-	xfs_mount_t		*mp;
+	struct xfs_mount	*mp = ip->i_mount;
+	struct xfs_buf		*bp;
+	struct xfs_dinode	*dip;
 	int			error;
 
 	XFS_STATS_INC(xs_iflush_count);
@@ -2411,25 +2421,8 @@ xfs_iflush(
 	ASSERT(ip->i_d.di_format != XFS_DINODE_FMT_BTREE ||
 	       ip->i_d.di_nextents > XFS_IFORK_MAXEXT(ip, XFS_DATA_FORK));
 
-	iip = ip->i_itemp;
-	mp = ip->i_mount;
+	*bpp = NULL;
 
-	/*
-	 * We can't flush the inode until it is unpinned, so wait for it if we
-	 * are allowed to block.  We know no one new can pin it, because we are
-	 * holding the inode lock shared and you need to hold it exclusively to
-	 * pin the inode.
-	 *
-	 * If we are not allowed to block, force the log out asynchronously so
-	 * that when we come back the inode will be unpinned. If other inodes
-	 * in the same cluster are dirty, they will probably write the inode
-	 * out for us if they occur after the log force completes.
-	 */
-	if (!(flags & SYNC_WAIT) && xfs_ipincount(ip)) {
-		xfs_iunpin(ip);
-		xfs_ifunlock(ip);
-		return EAGAIN;
-	}
 	xfs_iunpin_wait(ip);
 
 	/*
@@ -2448,21 +2441,20 @@ xfs_iflush(
 	/*
 	 * This may have been unpinned because the filesystem is shutting
 	 * down forcibly. If that's the case we must not write this inode
-	 * to disk, because the log record didn't make it to disk!
+	 * to disk, because the log record didn't make it to disk.
+	 *
+	 * We also have to remove the log item from the AIL in this case,
+	 * as we wait for an empty AIL as part of the unmount process.
 	 */
 	if (XFS_FORCED_SHUTDOWN(mp)) {
-		ip->i_update_core = 0;
-		if (iip)
-			iip->ili_format.ilf_fields = 0;
-		xfs_ifunlock(ip);
-		return XFS_ERROR(EIO);
+		error = XFS_ERROR(EIO);
+		goto abort_out;
 	}
 
 	/*
 	 * Get the buffer containing the on-disk inode.
 	 */
-	error = xfs_itobp(mp, NULL, ip, &dip, &bp,
-				(flags & SYNC_TRYLOCK) ? XBF_TRYLOCK : XBF_LOCK);
+	error = xfs_itobp(mp, NULL, ip, &dip, &bp, XBF_TRYLOCK);
 	if (error || !bp) {
 		xfs_ifunlock(ip);
 		return error;
@@ -2490,23 +2482,20 @@ xfs_iflush(
 	if (error)
 		goto cluster_corrupt_out;
 
-	if (flags & SYNC_WAIT)
-		error = xfs_bwrite(bp);
-	else
-		xfs_buf_delwri_queue(bp);
-
-	xfs_buf_relse(bp);
-	return error;
+	*bpp = bp;
+	return 0;
 
 corrupt_out:
 	xfs_buf_relse(bp);
 	xfs_force_shutdown(mp, SHUTDOWN_CORRUPT_INCORE);
 cluster_corrupt_out:
+	error = XFS_ERROR(EFSCORRUPTED);
+abort_out:
 	/*
 	 * Unlocks the flush lock
 	 */
-	xfs_iflush_abort(ip);
-	return XFS_ERROR(EFSCORRUPTED);
+	xfs_iflush_abort(ip, false);
+	return error;
 }
 
 
@@ -2533,26 +2522,6 @@ xfs_iflush_int(
 	/* set *dip = inode's place in the buffer */
 	dip = (xfs_dinode_t *)xfs_buf_offset(bp, ip->i_imap.im_boffset);
 
-	/*
-	 * Clear i_update_core before copying out the data.
-	 * This is for coordination with our timestamp updates
-	 * that don't hold the inode lock. They will always
-	 * update the timestamps BEFORE setting i_update_core,
-	 * so if we clear i_update_core after they set it we
-	 * are guaranteed to see their updates to the timestamps.
-	 * I believe that this depends on strongly ordered memory
-	 * semantics, but we have that.  We use the SYNCHRONIZE
-	 * macro to make sure that the compiler does not reorder
-	 * the i_update_core access below the data copy below.
-	 */
-	ip->i_update_core = 0;
-	SYNCHRONIZE();
-
-	/*
-	 * Make sure to get the latest timestamps from the Linux inode.
-	 */
-	xfs_synchronize_times(ip);
-
 	if (XFS_TEST_ERROR(dip->di_magic != cpu_to_be16(XFS_DINODE_MAGIC),
 			       mp, XFS_ERRTAG_IFLUSH_1, XFS_RANDOM_IFLUSH_1)) {
 		xfs_alert_tag(mp, XFS_PTAG_IFLUSH,
@@ -2663,36 +2632,33 @@ xfs_iflush_int(
 	xfs_inobp_check(mp, bp);
 
 	/*
-	 * We've recorded everything logged in the inode, so we'd
-	 * like to clear the ilf_fields bits so we don't log and
-	 * flush things unnecessarily.  However, we can't stop
-	 * logging all this information until the data we've copied
-	 * into the disk buffer is written to disk.  If we did we might
-	 * overwrite the copy of the inode in the log with all the
-	 * data after re-logging only part of it, and in the face of
-	 * a crash we wouldn't have all the data we need to recover.
+	 * We've recorded everything logged in the inode, so we'd like to clear
+	 * the ili_fields bits so we don't log and flush things unnecessarily.
+	 * However, we can't stop logging all this information until the data
+	 * we've copied into the disk buffer is written to disk.  If we did we
+	 * might overwrite the copy of the inode in the log with all the data
+	 * after re-logging only part of it, and in the face of a crash we
+	 * wouldn't have all the data we need to recover.
 	 *
-	 * What we do is move the bits to the ili_last_fields field.
-	 * When logging the inode, these bits are moved back to the
-	 * ilf_fields field.  In the xfs_iflush_done() routine we
-	 * clear ili_last_fields, since we know that the information
-	 * those bits represent is permanently on disk.  As long as
-	 * the flush completes before the inode is logged again, then
-	 * both ilf_fields and ili_last_fields will be cleared.
+	 * What we do is move the bits to the ili_last_fields field.  When
+	 * logging the inode, these bits are moved back to the ili_fields field.
+	 * In the xfs_iflush_done() routine we clear ili_last_fields, since we
+	 * know that the information those bits represent is permanently on
+	 * disk.  As long as the flush completes before the inode is logged
+	 * again, then both ili_fields and ili_last_fields will be cleared.
 	 *
-	 * We can play with the ilf_fields bits here, because the inode
-	 * lock must be held exclusively in order to set bits there
-	 * and the flush lock protects the ili_last_fields bits.
-	 * Set ili_logged so the flush done
-	 * routine can tell whether or not to look in the AIL.
-	 * Also, store the current LSN of the inode so that we can tell
-	 * whether the item has moved in the AIL from xfs_iflush_done().
-	 * In order to read the lsn we need the AIL lock, because
-	 * it is a 64 bit value that cannot be read atomically.
+	 * We can play with the ili_fields bits here, because the inode lock
+	 * must be held exclusively in order to set bits there and the flush
+	 * lock protects the ili_last_fields bits.  Set ili_logged so the flush
+	 * done routine can tell whether or not to look in the AIL.  Also, store
+	 * the current LSN of the inode so that we can tell whether the item has
+	 * moved in the AIL from xfs_iflush_done().  In order to read the lsn we
+	 * need the AIL lock, because it is a 64 bit value that cannot be read
+	 * atomically.
 	 */
-	if (iip != NULL && iip->ili_format.ilf_fields != 0) {
-		iip->ili_last_fields = iip->ili_format.ilf_fields;
-		iip->ili_format.ilf_fields = 0;
+	if (iip != NULL && iip->ili_fields != 0) {
+		iip->ili_last_fields = iip->ili_fields;
+		iip->ili_fields = 0;
 		iip->ili_logged = 1;
 
 		xfs_trans_ail_copy_lsn(mp->m_ail, &iip->ili_flush_lsn,
@@ -2711,8 +2677,7 @@ xfs_iflush_int(
 	} else {
 		/*
 		 * We're flushing an inode which is not in the AIL and has
-		 * not been logged but has i_update_core set.  For this
-		 * case we can use a B_DELWRI flush and immediately drop
+		 * not been logged.  For this case we can immediately drop
 		 * the inode flush lock because we can avoid the whole
 		 * AIL state thing.  It's OK to drop the flush lock now,
 		 * because we've already locked the buffer and to do anything
@@ -2732,27 +2697,6 @@ corrupt_out:
 	return XFS_ERROR(EFSCORRUPTED);
 }
 
-void
-xfs_promote_inode(
-	struct xfs_inode	*ip)
-{
-	struct xfs_buf		*bp;
-
-	ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL|XFS_ILOCK_SHARED));
-
-	bp = xfs_incore(ip->i_mount->m_ddev_targp, ip->i_imap.im_blkno,
-			ip->i_imap.im_len, XBF_TRYLOCK);
-	if (!bp)
-		return;
-
-	if (XFS_BUF_ISDELAYWRITE(bp)) {
-		xfs_buf_delwri_promote(bp);
-		wake_up_process(ip->i_mount->m_ddev_targp->bt_task);
-	}
-
-	xfs_buf_relse(bp);
-}
-
 /*
  * Return a pointer to the extent record at file index idx.
  */