1 files changed, 145 insertions, 682 deletions

diff --git a/fs/xfs/xfs_mount.c b/fs/xfs/xfs_mount.c
index d06afbc3540..3507cd0ec40 100644
--- a/fs/xfs/xfs_mount.c
+++ b/fs/xfs/xfs_mount.c
@@ -17,31 +17,31 @@
  */
 #include "xfs.h"
 #include "xfs_fs.h"
-#include "xfs_types.h"
+#include "xfs_shared.h"
+#include "xfs_format.h"
+#include "xfs_log_format.h"
+#include "xfs_trans_resv.h"
 #include "xfs_bit.h"
-#include "xfs_log.h"
 #include "xfs_inum.h"
-#include "xfs_trans.h"
 #include "xfs_sb.h"
 #include "xfs_ag.h"
-#include "xfs_dir2.h"
 #include "xfs_mount.h"
-#include "xfs_bmap_btree.h"
-#include "xfs_alloc_btree.h"
-#include "xfs_ialloc_btree.h"
-#include "xfs_dinode.h"
+#include "xfs_da_format.h"
 #include "xfs_inode.h"
-#include "xfs_btree.h"
+#include "xfs_dir2.h"
 #include "xfs_ialloc.h"
 #include "xfs_alloc.h"
 #include "xfs_rtalloc.h"
 #include "xfs_bmap.h"
+#include "xfs_trans.h"
+#include "xfs_trans_priv.h"
+#include "xfs_log.h"
 #include "xfs_error.h"
-#include "xfs_rw.h"
 #include "xfs_quota.h"
 #include "xfs_fsops.h"
-#include "xfs_utils.h"
 #include "xfs_trace.h"
+#include "xfs_icache.h"
+#include "xfs_dinode.h"
 
 
 #ifdef HAVE_PERCPU_SB
@@ -56,61 +56,6 @@ STATIC void	xfs_icsb_disable_counter(xfs_mount_t *, xfs_sb_field_t);
 #define xfs_icsb_balance_counter_locked(mp, a, b)	do { } while (0)
 #endif
 
-static const struct {
-	short offset;
-	short type;	/* 0 = integer
-			 * 1 = binary / string (no translation)
-			 */
-} xfs_sb_info[] = {
-    { offsetof(xfs_sb_t, sb_magicnum),   0 },
-    { offsetof(xfs_sb_t, sb_blocksize),  0 },
-    { offsetof(xfs_sb_t, sb_dblocks),    0 },
-    { offsetof(xfs_sb_t, sb_rblocks),    0 },
-    { offsetof(xfs_sb_t, sb_rextents),   0 },
-    { offsetof(xfs_sb_t, sb_uuid),       1 },
-    { offsetof(xfs_sb_t, sb_logstart),   0 },
-    { offsetof(xfs_sb_t, sb_rootino),    0 },
-    { offsetof(xfs_sb_t, sb_rbmino),     0 },
-    { offsetof(xfs_sb_t, sb_rsumino),    0 },
-    { offsetof(xfs_sb_t, sb_rextsize),   0 },
-    { offsetof(xfs_sb_t, sb_agblocks),   0 },
-    { offsetof(xfs_sb_t, sb_agcount),    0 },
-    { offsetof(xfs_sb_t, sb_rbmblocks),  0 },
-    { offsetof(xfs_sb_t, sb_logblocks),  0 },
-    { offsetof(xfs_sb_t, sb_versionnum), 0 },
-    { offsetof(xfs_sb_t, sb_sectsize),   0 },
-    { offsetof(xfs_sb_t, sb_inodesize),  0 },
-    { offsetof(xfs_sb_t, sb_inopblock),  0 },
-    { offsetof(xfs_sb_t, sb_fname[0]),   1 },
-    { offsetof(xfs_sb_t, sb_blocklog),   0 },
-    { offsetof(xfs_sb_t, sb_sectlog),    0 },
-    { offsetof(xfs_sb_t, sb_inodelog),   0 },
-    { offsetof(xfs_sb_t, sb_inopblog),   0 },
-    { offsetof(xfs_sb_t, sb_agblklog),   0 },
-    { offsetof(xfs_sb_t, sb_rextslog),   0 },
-    { offsetof(xfs_sb_t, sb_inprogress), 0 },
-    { offsetof(xfs_sb_t, sb_imax_pct),   0 },
-    { offsetof(xfs_sb_t, sb_icount),     0 },
-    { offsetof(xfs_sb_t, sb_ifree),      0 },
-    { offsetof(xfs_sb_t, sb_fdblocks),   0 },
-    { offsetof(xfs_sb_t, sb_frextents),  0 },
-    { offsetof(xfs_sb_t, sb_uquotino),   0 },
-    { offsetof(xfs_sb_t, sb_gquotino),   0 },
-    { offsetof(xfs_sb_t, sb_qflags),     0 },
-    { offsetof(xfs_sb_t, sb_flags),      0 },
-    { offsetof(xfs_sb_t, sb_shared_vn),  0 },
-    { offsetof(xfs_sb_t, sb_inoalignmt), 0 },
-    { offsetof(xfs_sb_t, sb_unit),	 0 },
-    { offsetof(xfs_sb_t, sb_width),	 0 },
-    { offsetof(xfs_sb_t, sb_dirblklog),	 0 },
-    { offsetof(xfs_sb_t, sb_logsectlog), 0 },
-    { offsetof(xfs_sb_t, sb_logsectsize),0 },
-    { offsetof(xfs_sb_t, sb_logsunit),	 0 },
-    { offsetof(xfs_sb_t, sb_features2),	 0 },
-    { offsetof(xfs_sb_t, sb_bad_features2), 0 },
-    { sizeof(xfs_sb_t),			 0 }
-};
-
 static DEFINE_MUTEX(xfs_uuid_table_mutex);
 static int xfs_uuid_table_size;
 static uuid_t *xfs_uuid_table;
@@ -158,7 +103,7 @@ xfs_uuid_mount(
 
  out_duplicate:
 	mutex_unlock(&xfs_uuid_table_mutex);
-	xfs_warn(mp, "Filesystem has duplicate UUID - can't mount");
+	xfs_warn(mp, "Filesystem has duplicate UUID %pU - can't mount", uuid);
 	return XFS_ERROR(EINVAL);
 }
 
@@ -186,64 +131,6 @@ xfs_uuid_unmount(
 }
 
 
-/*
- * Reference counting access wrappers to the perag structures.
- * Because we never free per-ag structures, the only thing we
- * have to protect against changes is the tree structure itself.
- */
-struct xfs_perag *
-xfs_perag_get(struct xfs_mount *mp, xfs_agnumber_t agno)
-{
-	struct xfs_perag	*pag;
-	int			ref = 0;
-
-	rcu_read_lock();
-	pag = radix_tree_lookup(&mp->m_perag_tree, agno);
-	if (pag) {
-		ASSERT(atomic_read(&pag->pag_ref) >= 0);
-		ref = atomic_inc_return(&pag->pag_ref);
-	}
-	rcu_read_unlock();
-	trace_xfs_perag_get(mp, agno, ref, _RET_IP_);
-	return pag;
-}
-
-/*
- * search from @first to find the next perag with the given tag set.
- */
-struct xfs_perag *
-xfs_perag_get_tag(
-	struct xfs_mount	*mp,
-	xfs_agnumber_t		first,
-	int			tag)
-{
-	struct xfs_perag	*pag;
-	int			found;
-	int			ref;
-
-	rcu_read_lock();
-	found = radix_tree_gang_lookup_tag(&mp->m_perag_tree,
-					(void **)&pag, first, 1, tag);
-	if (found <= 0) {
-		rcu_read_unlock();
-		return NULL;
-	}
-	ref = atomic_inc_return(&pag->pag_ref);
-	rcu_read_unlock();
-	trace_xfs_perag_get_tag(mp, pag->pag_agno, ref, _RET_IP_);
-	return pag;
-}
-
-void
-xfs_perag_put(struct xfs_perag *pag)
-{
-	int	ref;
-
-	ASSERT(atomic_read(&pag->pag_ref) > 0);
-	ref = atomic_dec_return(&pag->pag_ref);
-	trace_xfs_perag_put(pag->pag_mount, pag->pag_agno, ref, _RET_IP_);
-}
-
 STATIC void
 __xfs_free_perag(
 	struct rcu_head	*head)
@@ -296,151 +183,13 @@ xfs_sb_validate_fsb_count(
 	return 0;
 }
 
-/*
- * Check the validity of the SB found.
- */
-STATIC int
-xfs_mount_validate_sb(
-	xfs_mount_t	*mp,
-	xfs_sb_t	*sbp,
-	int		flags)
-{
-	int		loud = !(flags & XFS_MFSI_QUIET);
-
-	/*
-	 * If the log device and data device have the
-	 * same device number, the log is internal.
-	 * Consequently, the sb_logstart should be non-zero.  If
-	 * we have a zero sb_logstart in this case, we may be trying to mount
-	 * a volume filesystem in a non-volume manner.
-	 */
-	if (sbp->sb_magicnum != XFS_SB_MAGIC) {
-		if (loud)
-			xfs_warn(mp, "bad magic number");
-		return XFS_ERROR(EWRONGFS);
-	}
-
-	if (!xfs_sb_good_version(sbp)) {
-		if (loud)
-			xfs_warn(mp, "bad version");
-		return XFS_ERROR(EWRONGFS);
-	}
-
-	if (unlikely(
-	    sbp->sb_logstart == 0 && mp->m_logdev_targp == mp->m_ddev_targp)) {
-		if (loud)
-			xfs_warn(mp,
-		"filesystem is marked as having an external log; "
-		"specify logdev on the mount command line.");
-		return XFS_ERROR(EINVAL);
-	}
-
-	if (unlikely(
-	    sbp->sb_logstart != 0 && mp->m_logdev_targp != mp->m_ddev_targp)) {
-		if (loud)
-			xfs_warn(mp,
-		"filesystem is marked as having an internal log; "
-		"do not specify logdev on the mount command line.");
-		return XFS_ERROR(EINVAL);
-	}
-
-	/*
-	 * More sanity checking.  Most of these were stolen directly from
-	 * xfs_repair.
-	 */
-	if (unlikely(
-	    sbp->sb_agcount <= 0					||
-	    sbp->sb_sectsize < XFS_MIN_SECTORSIZE			||
-	    sbp->sb_sectsize > XFS_MAX_SECTORSIZE			||
-	    sbp->sb_sectlog < XFS_MIN_SECTORSIZE_LOG			||
-	    sbp->sb_sectlog > XFS_MAX_SECTORSIZE_LOG			||
-	    sbp->sb_sectsize != (1 << sbp->sb_sectlog)			||
-	    sbp->sb_blocksize < XFS_MIN_BLOCKSIZE			||
-	    sbp->sb_blocksize > XFS_MAX_BLOCKSIZE			||
-	    sbp->sb_blocklog < XFS_MIN_BLOCKSIZE_LOG			||
-	    sbp->sb_blocklog > XFS_MAX_BLOCKSIZE_LOG			||
-	    sbp->sb_blocksize != (1 << sbp->sb_blocklog)		||
-	    sbp->sb_inodesize < XFS_DINODE_MIN_SIZE			||
-	    sbp->sb_inodesize > XFS_DINODE_MAX_SIZE			||
-	    sbp->sb_inodelog < XFS_DINODE_MIN_LOG			||
-	    sbp->sb_inodelog > XFS_DINODE_MAX_LOG			||
-	    sbp->sb_inodesize != (1 << sbp->sb_inodelog)		||
-	    (sbp->sb_blocklog - sbp->sb_inodelog != sbp->sb_inopblog)	||
-	    (sbp->sb_rextsize * sbp->sb_blocksize > XFS_MAX_RTEXTSIZE)	||
-	    (sbp->sb_rextsize * sbp->sb_blocksize < XFS_MIN_RTEXTSIZE)	||
-	    (sbp->sb_imax_pct > 100 /* zero sb_imax_pct is valid */)	||
-	    sbp->sb_dblocks == 0					||
-	    sbp->sb_dblocks > XFS_MAX_DBLOCKS(sbp)			||
-	    sbp->sb_dblocks < XFS_MIN_DBLOCKS(sbp))) {
-		if (loud)
-			XFS_CORRUPTION_ERROR("SB sanity check failed",
-				XFS_ERRLEVEL_LOW, mp, sbp);
-		return XFS_ERROR(EFSCORRUPTED);
-	}
-
-	/*
-	 * Until this is fixed only page-sized or smaller data blocks work.
-	 */
-	if (unlikely(sbp->sb_blocksize > PAGE_SIZE)) {
-		if (loud) {
-			xfs_warn(mp,
-		"File system with blocksize %d bytes. "
-		"Only pagesize (%ld) or less will currently work.",
-				sbp->sb_blocksize, PAGE_SIZE);
-		}
-		return XFS_ERROR(ENOSYS);
-	}
-
-	/*
-	 * Currently only very few inode sizes are supported.
-	 */
-	switch (sbp->sb_inodesize) {
-	case 256:
-	case 512:
-	case 1024:
-	case 2048:
-		break;
-	default:
-		if (loud)
-			xfs_warn(mp, "inode size of %d bytes not supported",
-				sbp->sb_inodesize);
-		return XFS_ERROR(ENOSYS);
-	}
-
-	if (xfs_sb_validate_fsb_count(sbp, sbp->sb_dblocks) ||
-	    xfs_sb_validate_fsb_count(sbp, sbp->sb_rblocks)) {
-		if (loud)
-			xfs_warn(mp,
-		"file system too large to be mounted on this system.");
-		return XFS_ERROR(EFBIG);
-	}
-
-	if (unlikely(sbp->sb_inprogress)) {
-		if (loud)
-			xfs_warn(mp, "file system busy");
-		return XFS_ERROR(EFSCORRUPTED);
-	}
-
-	/*
-	 * Version 1 directory format has never worked on Linux.
-	 */
-	if (unlikely(!xfs_sb_version_hasdirv2(sbp))) {
-		if (loud)
-			xfs_warn(mp,
-				"file system using version 1 directory format");
-		return XFS_ERROR(ENOSYS);
-	}
-
-	return 0;
-}
-
 int
 xfs_initialize_perag(
 	xfs_mount_t	*mp,
 	xfs_agnumber_t	agcount,
 	xfs_agnumber_t	*maxagi)
 {
-	xfs_agnumber_t	index, max_metadata;
+	xfs_agnumber_t	index;
 	xfs_agnumber_t	first_initialised = 0;
 	xfs_perag_t	*pag;
 	xfs_agino_t	agino;
@@ -500,43 +249,10 @@ xfs_initialize_perag(
 	else
 		mp->m_flags &= ~XFS_MOUNT_32BITINODES;
 
-	if (mp->m_flags & XFS_MOUNT_32BITINODES) {
-		/*
-		 * Calculate how much should be reserved for inodes to meet
-		 * the max inode percentage.
-		 */
-		if (mp->m_maxicount) {
-			__uint64_t	icount;
-
-			icount = sbp->sb_dblocks * sbp->sb_imax_pct;
-			do_div(icount, 100);
-			icount += sbp->sb_agblocks - 1;
-			do_div(icount, sbp->sb_agblocks);
-			max_metadata = icount;
-		} else {
-			max_metadata = agcount;
-		}
-
-		for (index = 0; index < agcount; index++) {
-			ino = XFS_AGINO_TO_INO(mp, index, agino);
-			if (ino > XFS_MAXINUMBER_32) {
-				index++;
-				break;
-			}
-
-			pag = xfs_perag_get(mp, index);
-			pag->pagi_inodeok = 1;
-			if (index < max_metadata)
-				pag->pagf_metadata = 1;
-			xfs_perag_put(pag);
-		}
-	} else {
-		for (index = 0; index < agcount; index++) {
-			pag = xfs_perag_get(mp, index);
-			pag->pagi_inodeok = 1;
-			xfs_perag_put(pag);
-		}
-	}
+	if (mp->m_flags & XFS_MOUNT_32BITINODES)
+		index = xfs_set_inode32(mp);
+	else
+		index = xfs_set_inode64(mp);
 
 	if (maxagi)
 		*maxagi = index;
@@ -551,180 +267,104 @@ out_unwind:
 	return error;
 }
 
-void
-xfs_sb_from_disk(
-	xfs_sb_t	*to,
-	xfs_dsb_t	*from)
-{
-	to->sb_magicnum = be32_to_cpu(from->sb_magicnum);
-	to->sb_blocksize = be32_to_cpu(from->sb_blocksize);
-	to->sb_dblocks = be64_to_cpu(from->sb_dblocks);
-	to->sb_rblocks = be64_to_cpu(from->sb_rblocks);
-	to->sb_rextents = be64_to_cpu(from->sb_rextents);
-	memcpy(&to->sb_uuid, &from->sb_uuid, sizeof(to->sb_uuid));
-	to->sb_logstart = be64_to_cpu(from->sb_logstart);
-	to->sb_rootino = be64_to_cpu(from->sb_rootino);
-	to->sb_rbmino = be64_to_cpu(from->sb_rbmino);
-	to->sb_rsumino = be64_to_cpu(from->sb_rsumino);
-	to->sb_rextsize = be32_to_cpu(from->sb_rextsize);
-	to->sb_agblocks = be32_to_cpu(from->sb_agblocks);
-	to->sb_agcount = be32_to_cpu(from->sb_agcount);
-	to->sb_rbmblocks = be32_to_cpu(from->sb_rbmblocks);
-	to->sb_logblocks = be32_to_cpu(from->sb_logblocks);
-	to->sb_versionnum = be16_to_cpu(from->sb_versionnum);
-	to->sb_sectsize = be16_to_cpu(from->sb_sectsize);
-	to->sb_inodesize = be16_to_cpu(from->sb_inodesize);
-	to->sb_inopblock = be16_to_cpu(from->sb_inopblock);
-	memcpy(&to->sb_fname, &from->sb_fname, sizeof(to->sb_fname));
-	to->sb_blocklog = from->sb_blocklog;
-	to->sb_sectlog = from->sb_sectlog;
-	to->sb_inodelog = from->sb_inodelog;
-	to->sb_inopblog = from->sb_inopblog;
-	to->sb_agblklog = from->sb_agblklog;
-	to->sb_rextslog = from->sb_rextslog;
-	to->sb_inprogress = from->sb_inprogress;
-	to->sb_imax_pct = from->sb_imax_pct;
-	to->sb_icount = be64_to_cpu(from->sb_icount);
-	to->sb_ifree = be64_to_cpu(from->sb_ifree);
-	to->sb_fdblocks = be64_to_cpu(from->sb_fdblocks);
-	to->sb_frextents = be64_to_cpu(from->sb_frextents);
-	to->sb_uquotino = be64_to_cpu(from->sb_uquotino);
-	to->sb_gquotino = be64_to_cpu(from->sb_gquotino);
-	to->sb_qflags = be16_to_cpu(from->sb_qflags);
-	to->sb_flags = from->sb_flags;
-	to->sb_shared_vn = from->sb_shared_vn;
-	to->sb_inoalignmt = be32_to_cpu(from->sb_inoalignmt);
-	to->sb_unit = be32_to_cpu(from->sb_unit);
-	to->sb_width = be32_to_cpu(from->sb_width);
-	to->sb_dirblklog = from->sb_dirblklog;
-	to->sb_logsectlog = from->sb_logsectlog;
-	to->sb_logsectsize = be16_to_cpu(from->sb_logsectsize);
-	to->sb_logsunit = be32_to_cpu(from->sb_logsunit);
-	to->sb_features2 = be32_to_cpu(from->sb_features2);
-	to->sb_bad_features2 = be32_to_cpu(from->sb_bad_features2);
-}
-
-/*
- * Copy in core superblock to ondisk one.
- *
- * The fields argument is mask of superblock fields to copy.
- */
-void
-xfs_sb_to_disk(
-	xfs_dsb_t	*to,
-	xfs_sb_t	*from,
-	__int64_t	fields)
-{
-	xfs_caddr_t	to_ptr = (xfs_caddr_t)to;
-	xfs_caddr_t	from_ptr = (xfs_caddr_t)from;
-	xfs_sb_field_t	f;
-	int		first;
-	int		size;
-
-	ASSERT(fields);
-	if (!fields)
-		return;
-
-	while (fields) {
-		f = (xfs_sb_field_t)xfs_lowbit64((__uint64_t)fields);
-		first = xfs_sb_info[f].offset;
-		size = xfs_sb_info[f + 1].offset - first;
-
-		ASSERT(xfs_sb_info[f].type == 0 || xfs_sb_info[f].type == 1);
-
-		if (size == 1 || xfs_sb_info[f].type == 1) {
-			memcpy(to_ptr + first, from_ptr + first, size);
-		} else {
-			switch (size) {
-			case 2:
-				*(__be16 *)(to_ptr + first) =
-					cpu_to_be16(*(__u16 *)(from_ptr + first));
-				break;
-			case 4:
-				*(__be32 *)(to_ptr + first) =
-					cpu_to_be32(*(__u32 *)(from_ptr + first));
-				break;
-			case 8:
-				*(__be64 *)(to_ptr + first) =
-					cpu_to_be64(*(__u64 *)(from_ptr + first));
-				break;
-			default:
-				ASSERT(0);
-			}
-		}
-
-		fields &= ~(1LL << f);
-	}
-}
-
 /*
  * xfs_readsb
  *
  * Does the initial read of the superblock.
  */
 int
-xfs_readsb(xfs_mount_t *mp, int flags)
+xfs_readsb(
+	struct xfs_mount *mp,
+	int		flags)
 {
 	unsigned int	sector_size;
-	xfs_buf_t	*bp;
+	struct xfs_buf	*bp;
+	struct xfs_sb	*sbp = &mp->m_sb;
 	int		error;
 	int		loud = !(flags & XFS_MFSI_QUIET);
+	const struct xfs_buf_ops *buf_ops;
 
 	ASSERT(mp->m_sb_bp == NULL);
 	ASSERT(mp->m_ddev_targp != NULL);
 
 	/*
+	 * For the initial read, we must guess at the sector
+	 * size based on the block device.  It's enough to
+	 * get the sb_sectsize out of the superblock and
+	 * then reread with the proper length.
+	 * We don't verify it yet, because it may not be complete.
+	 */
+	sector_size = xfs_getsize_buftarg(mp->m_ddev_targp);
+	buf_ops = NULL;
+
+	/*
 	 * Allocate a (locked) buffer to hold the superblock.
 	 * This will be kept around at all times to optimize
 	 * access to the superblock.
 	 */
-	sector_size = xfs_getsize_buftarg(mp->m_ddev_targp);
-
 reread:
-	bp = xfs_buf_read_uncached(mp, mp->m_ddev_targp,
-					XFS_SB_DADDR, sector_size, 0);
+	bp = xfs_buf_read_uncached(mp->m_ddev_targp, XFS_SB_DADDR,
+				   BTOBB(sector_size), 0, buf_ops);
 	if (!bp) {
 		if (loud)
 			xfs_warn(mp, "SB buffer read failed");
 		return EIO;
 	}
+	if (bp->b_error) {
+		error = bp->b_error;
+		if (loud)
+			xfs_warn(mp, "SB validate failed with error %d.", error);
+		/* bad CRC means corrupted metadata */
+		if (error == EFSBADCRC)
+			error = EFSCORRUPTED;
+		goto release_buf;
+	}
 
 	/*
 	 * Initialize the mount structure from the superblock.
-	 * But first do some basic consistency checking.
 	 */
-	xfs_sb_from_disk(&mp->m_sb, XFS_BUF_TO_SBP(bp));
-	error = xfs_mount_validate_sb(mp, &(mp->m_sb), flags);
-	if (error) {
+	xfs_sb_from_disk(sbp, XFS_BUF_TO_SBP(bp));
+	xfs_sb_quota_from_disk(sbp);
+
+	/*
+	 * If we haven't validated the superblock, do so now before we try
+	 * to check the sector size and reread the superblock appropriately.
+	 */
+	if (sbp->sb_magicnum != XFS_SB_MAGIC) {
 		if (loud)
-			xfs_warn(mp, "SB validate failed");
+			xfs_warn(mp, "Invalid superblock magic number");
+		error = EINVAL;
 		goto release_buf;
 	}
 
 	/*
 	 * We must be able to do sector-sized and sector-aligned IO.
 	 */
-	if (sector_size > mp->m_sb.sb_sectsize) {
+	if (sector_size > sbp->sb_sectsize) {
 		if (loud)
 			xfs_warn(mp, "device supports %u byte sectors (not %u)",
-				sector_size, mp->m_sb.sb_sectsize);
+				sector_size, sbp->sb_sectsize);
 		error = ENOSYS;
 		goto release_buf;
 	}
 
-	/*
-	 * If device sector size is smaller than the superblock size,
-	 * re-read the superblock so the buffer is correctly sized.
-	 */
-	if (sector_size < mp->m_sb.sb_sectsize) {
+	if (buf_ops == NULL) {
+		/*
+		 * Re-read the superblock so the buffer is correctly sized,
+		 * and properly verified.
+		 */
 		xfs_buf_relse(bp);
-		sector_size = mp->m_sb.sb_sectsize;
+		sector_size = sbp->sb_sectsize;
+		buf_ops = loud ? &xfs_sb_buf_ops : &xfs_sb_quiet_buf_ops;
 		goto reread;
 	}
 
 	/* Initialize per-cpu counters */
 	xfs_icsb_reinit_counters(mp);
 
+	/* no need to be quiet anymore, so reset the buf ops */
+	bp->b_ops = &xfs_sb_buf_ops;
+
 	mp->m_sb_bp = bp;
 	xfs_buf_unlock(bp);
 	return 0;
@@ -734,107 +374,6 @@ release_buf:
 	return error;
 }
 
-
-/*
- * xfs_mount_common
- *
- * Mount initialization code establishing various mount
- * fields from the superblock associated with the given
- * mount structure
- */
-STATIC void
-xfs_mount_common(xfs_mount_t *mp, xfs_sb_t *sbp)
-{
-	mp->m_agfrotor = mp->m_agirotor = 0;
-	spin_lock_init(&mp->m_agirotor_lock);
-	mp->m_maxagi = mp->m_sb.sb_agcount;
-	mp->m_blkbit_log = sbp->sb_blocklog + XFS_NBBYLOG;
-	mp->m_blkbb_log = sbp->sb_blocklog - BBSHIFT;
-	mp->m_sectbb_log = sbp->sb_sectlog - BBSHIFT;
-	mp->m_agno_log = xfs_highbit32(sbp->sb_agcount - 1) + 1;
-	mp->m_agino_log = sbp->sb_inopblog + sbp->sb_agblklog;
-	mp->m_blockmask = sbp->sb_blocksize - 1;
-	mp->m_blockwsize = sbp->sb_blocksize >> XFS_WORDLOG;
-	mp->m_blockwmask = mp->m_blockwsize - 1;
-
-	mp->m_alloc_mxr[0] = xfs_allocbt_maxrecs(mp, sbp->sb_blocksize, 1);
-	mp->m_alloc_mxr[1] = xfs_allocbt_maxrecs(mp, sbp->sb_blocksize, 0);
-	mp->m_alloc_mnr[0] = mp->m_alloc_mxr[0] / 2;
-	mp->m_alloc_mnr[1] = mp->m_alloc_mxr[1] / 2;
-
-	mp->m_inobt_mxr[0] = xfs_inobt_maxrecs(mp, sbp->sb_blocksize, 1);
-	mp->m_inobt_mxr[1] = xfs_inobt_maxrecs(mp, sbp->sb_blocksize, 0);
-	mp->m_inobt_mnr[0] = mp->m_inobt_mxr[0] / 2;
-	mp->m_inobt_mnr[1] = mp->m_inobt_mxr[1] / 2;
-
-	mp->m_bmap_dmxr[0] = xfs_bmbt_maxrecs(mp, sbp->sb_blocksize, 1);
-	mp->m_bmap_dmxr[1] = xfs_bmbt_maxrecs(mp, sbp->sb_blocksize, 0);
-	mp->m_bmap_dmnr[0] = mp->m_bmap_dmxr[0] / 2;
-	mp->m_bmap_dmnr[1] = mp->m_bmap_dmxr[1] / 2;
-
-	mp->m_bsize = XFS_FSB_TO_BB(mp, 1);
-	mp->m_ialloc_inos = (int)MAX((__uint16_t)XFS_INODES_PER_CHUNK,
-					sbp->sb_inopblock);
-	mp->m_ialloc_blks = mp->m_ialloc_inos >> sbp->sb_inopblog;
-}
-
-/*
- * xfs_initialize_perag_data
- *
- * Read in each per-ag structure so we can count up the number of
- * allocated inodes, free inodes and used filesystem blocks as this
- * information is no longer persistent in the superblock. Once we have
- * this information, write it into the in-core superblock structure.
- */
-STATIC int
-xfs_initialize_perag_data(xfs_mount_t *mp, xfs_agnumber_t agcount)
-{
-	xfs_agnumber_t	index;
-	xfs_perag_t	*pag;
-	xfs_sb_t	*sbp = &mp->m_sb;
-	uint64_t	ifree = 0;
-	uint64_t	ialloc = 0;
-	uint64_t	bfree = 0;
-	uint64_t	bfreelst = 0;
-	uint64_t	btree = 0;
-	int		error;
-
-	for (index = 0; index < agcount; index++) {
-		/*
-		 * read the agf, then the agi. This gets us
-		 * all the information we need and populates the
-		 * per-ag structures for us.
-		 */
-		error = xfs_alloc_pagf_init(mp, NULL, index, 0);
-		if (error)
-			return error;
-
-		error = xfs_ialloc_pagi_init(mp, NULL, index);
-		if (error)
-			return error;
-		pag = xfs_perag_get(mp, index);
-		ifree += pag->pagi_freecount;
-		ialloc += pag->pagi_count;
-		bfree += pag->pagf_freeblks;
-		bfreelst += pag->pagf_flcount;
-		btree += pag->pagf_btreeblks;
-		xfs_perag_put(pag);
-	}
-	/*
-	 * Overwrite incore superblock counters with just-read data
-	 */
-	spin_lock(&mp->m_sb_lock);
-	sbp->sb_ifree = ifree;
-	sbp->sb_icount = ialloc;
-	sbp->sb_fdblocks = bfree + bfreelst + btree;
-	spin_unlock(&mp->m_sb_lock);
-
-	/* Fixup the per-cpu counters as well. */
-	xfs_icsb_reinit_counters(mp);
-
-	return 0;
-}
-
 /*
  * Update alignment values based on mount options and sb values
  */
@@ -850,42 +389,27 @@ xfs_update_alignment(xfs_mount_t *mp)
 		 */
 		if ((BBTOB(mp->m_dalign) & mp->m_blockmask) ||
 		    (BBTOB(mp->m_swidth) & mp->m_blockmask)) {
-			if (mp->m_flags & XFS_MOUNT_RETERR) {
-				xfs_warn(mp, "alignment check failed: "
-					 "(sunit/swidth vs. blocksize)");
-				return XFS_ERROR(EINVAL);
-			}
-			mp->m_dalign = mp->m_swidth = 0;
+			xfs_warn(mp,
+		"alignment check failed: sunit/swidth vs. blocksize(%d)",
+				sbp->sb_blocksize);
+			return XFS_ERROR(EINVAL);
 		} else {
 			/*
 			 * Convert the stripe unit and width to FSBs.
 			 */
 			mp->m_dalign = XFS_BB_TO_FSBT(mp, mp->m_dalign);
 			if (mp->m_dalign && (sbp->sb_agblocks % mp->m_dalign)) {
-				if (mp->m_flags & XFS_MOUNT_RETERR) {
-					xfs_warn(mp, "alignment check failed: "
-						 "(sunit/swidth vs. ag size)");
-					return XFS_ERROR(EINVAL);
-				}
 				xfs_warn(mp,
-		"stripe alignment turned off: sunit(%d)/swidth(%d) "
-		"incompatible with agsize(%d)",
-					mp->m_dalign, mp->m_swidth,
-					sbp->sb_agblocks);
-
-				mp->m_dalign = 0;
-				mp->m_swidth = 0;
+			"alignment check failed: sunit/swidth vs. agsize(%d)",
+					 sbp->sb_agblocks);
+				return XFS_ERROR(EINVAL);
 			} else if (mp->m_dalign) {
 				mp->m_swidth = XFS_BB_TO_FSBT(mp, mp->m_swidth);
 			} else {
-				if (mp->m_flags & XFS_MOUNT_RETERR) {
-					xfs_warn(mp, "alignment check failed: "
-						"sunit(%d) less than bsize(%d)",
-						mp->m_dalign,
-						mp->m_blockmask +1);
-					return XFS_ERROR(EINVAL);
-				}
-				mp->m_swidth = 0;
+				xfs_warn(mp,
+			"alignment check failed: sunit(%d) less than bsize(%d)",
+					 mp->m_dalign, sbp->sb_blocksize);
+				return XFS_ERROR(EINVAL);
 			}
 		}
 
@@ -902,6 +426,10 @@ xfs_update_alignment(xfs_mount_t *mp)
 				sbp->sb_width = mp->m_swidth;
 				mp->m_update_flags |= XFS_SB_WIDTH;
 			}
+		} else {
+			xfs_warn(mp,
+	"cannot change alignment: superblock does not support data alignment");
+			return XFS_ERROR(EINVAL);
 		}
 	} else if ((mp->m_flags & XFS_MOUNT_NOALIGN) != XFS_MOUNT_NOALIGN &&
 		    xfs_sb_version_hasdalign(&mp->m_sb)) {
@@ -1017,7 +545,7 @@ xfs_set_inoalignment(xfs_mount_t *mp)
 }
 
 /*
- * Check that the data (and log if separate) are an ok size.
+ * Check that the data (and log if separate) is an ok size.
  */
 STATIC int
 xfs_check_sizes(xfs_mount_t *mp)
@@ -1030,9 +558,9 @@ xfs_check_sizes(xfs_mount_t *mp)
 		xfs_warn(mp, "filesystem size mismatch detected");
 		return XFS_ERROR(EFBIG);
 	}
-	bp = xfs_buf_read_uncached(mp, mp->m_ddev_targp,
+	bp = xfs_buf_read_uncached(mp->m_ddev_targp,
 					d - XFS_FSS_TO_BB(mp, 1),
-					BBTOB(XFS_FSS_TO_BB(mp, 1)), 0);
+					XFS_FSS_TO_BB(mp, 1), 0, NULL);
 	if (!bp) {
 		xfs_warn(mp, "last sector read failed");
 		return EIO;
@@ -1045,9 +573,9 @@ xfs_check_sizes(xfs_mount_t *mp)
 			xfs_warn(mp, "log size mismatch detected");
 			return XFS_ERROR(EFBIG);
 		}
-		bp = xfs_buf_read_uncached(mp, mp->m_logdev_targp,
+		bp = xfs_buf_read_uncached(mp->m_logdev_targp,
 					d - XFS_FSB_TO_BB(mp, 1),
-					XFS_FSB_TO_B(mp, 1), 0);
+					XFS_FSB_TO_BB(mp, 1), 0, NULL);
 		if (!bp) {
 			xfs_warn(mp, "log device read failed");
 			return EIO;
@@ -1087,8 +615,7 @@ xfs_mount_reset_sbqflags(
 		return 0;
 
 	tp = xfs_trans_alloc(mp, XFS_TRANS_QM_SBCHANGE);
-	error = xfs_trans_reserve(tp, 0, mp->m_sb.sb_sectsize + 128, 0, 0,
-				      XFS_DEFAULT_LOG_COUNT);
+	error = xfs_trans_reserve(tp, &M_RES(mp)->tr_qm_sbchange, 0, 0);
 	if (error) {
 		xfs_trans_cancel(tp, 0);
 		xfs_alert(mp, "%s: Superblock update failed!", __func__);
@@ -1138,7 +665,7 @@ xfs_mountfs(
 	uint		quotaflags = 0;
 	int		error = 0;
 
-	xfs_mount_common(mp, sbp);
+	xfs_sb_mount_common(mp, sbp);
 
 	/*
 	 * Check for a mismatched features2 values.  Older kernels
@@ -1181,6 +708,12 @@ xfs_mountfs(
 			mp->m_update_flags |= XFS_SB_VERSIONNUM;
 	}
 
+	/* always use v2 inodes by default now */
+	if (!(mp->m_sb.sb_versionnum & XFS_SB_VERSION_NLINKBIT)) {
+		mp->m_sb.sb_versionnum |= XFS_SB_VERSION_NLINKBIT;
+		mp->m_update_flags |= XFS_SB_VERSIONNUM;
+	}
+
 	/*
 	 * Check if sb_agblocks is aligned at stripe boundary
 	 * If sb_agblocks is NOT aligned turn off m_dalign since
@@ -1198,8 +731,6 @@ xfs_mountfs(
 
 	xfs_set_maxicount(mp);
 
-	mp->m_maxioffset = xfs_max_file_offset(sbp->sb_blocklog);
-
 	error = xfs_uuid_mount(mp);
 	if (error)
 		goto out;
@@ -1216,8 +747,20 @@ xfs_mountfs(
 	 * Set the inode cluster size.
 	 * This may still be overridden by the file system
 	 * block size if it is larger than the chosen cluster size.
+	 *
+	 * For v5 filesystems, scale the cluster size with the inode size to
+	 * keep a constant ratio of inode per cluster buffer, but only if mkfs
+	 * has set the inode alignment value appropriately for larger cluster
+	 * sizes.
 	 */
 	mp->m_inode_cluster_size = XFS_INODE_BIG_CLUSTER_SIZE;
+	if (xfs_sb_version_hascrc(&mp->m_sb)) {
+		int	new_size = mp->m_inode_cluster_size;
+
+		new_size *= mp->m_sb.sb_inodesize / XFS_DINODE_MIN_SIZE;
+		if (mp->m_sb.sb_inoalignmt >= XFS_B_TO_FSBT(mp, new_size))
+			mp->m_inode_cluster_size = new_size;
+	}
 
 	/*
 	 * Set inode alignment fields
@@ -1225,7 +768,7 @@ xfs_mountfs(
 	xfs_set_inoalignment(mp);
 
 	/*
-	 * Check that the data (and log if separate) are an ok size.
+	 * Check that the data (and log if separate) is an ok size.
 	 */
 	error = xfs_check_sizes(mp);
 	if (error)
@@ -1248,12 +791,11 @@ xfs_mountfs(
 
 	mp->m_dmevmask = 0;	/* not persistent; set after each mount */
 
-	xfs_dir_mount(mp);
-
-	/*
-	 * Initialize the attribute manager's entries.
-	 */
-	mp->m_attr_magicpct = (mp->m_sb.sb_blocksize * 37) / 100;
+	error = xfs_da_mount(mp);
+	if (error) {
+		xfs_warn(mp, "Failed dir/attr init: %d", error);
+		goto out_remove_uuid;
+	}
 
 	/*
 	 * Initialize the precomputed transaction reservations values.
@@ -1268,7 +810,7 @@ xfs_mountfs(
 	error = xfs_initialize_perag(mp, sbp->sb_agcount, &mp->m_maxagi);
 	if (error) {
 		xfs_warn(mp, "Failed per-ag init: %d", error);
-		goto out_remove_uuid;
+		goto out_free_dir;
 	}
 
 	if (!sbp->sb_logblocks) {
@@ -1286,7 +828,7 @@ xfs_mountfs(
 			      XFS_FSB_TO_BB(mp, sbp->sb_logblocks));
 	if (error) {
 		xfs_warn(mp, "log mount failed");
-		goto out_free_perag;
+		goto out_fail_wait;
 	}
 
 	/*
@@ -1313,7 +855,7 @@ xfs_mountfs(
 	     !mp->m_sb.sb_inprogress) {
 		error = xfs_initialize_perag_data(mp, sbp->sb_agcount);
 		if (error)
-			goto out_free_perag;
+			goto out_fail_wait;
 	}
 
 	/*
@@ -1437,8 +979,14 @@ xfs_mountfs(
 	IRELE(rip);
  out_log_dealloc:
 	xfs_log_unmount(mp);
+ out_fail_wait:
+	if (mp->m_logdev_targp && mp->m_logdev_targp != mp->m_ddev_targp)
+		xfs_wait_buftarg(mp->m_logdev_targp);
+	xfs_wait_buftarg(mp->m_ddev_targp);
  out_free_perag:
 	xfs_free_perag(mp);
+ out_free_dir:
+	xfs_da_unmount(mp);
  out_remove_uuid:
 	xfs_uuid_unmount(mp);
  out:
@@ -1456,6 +1004,8 @@ xfs_unmountfs(
 	__uint64_t		resblks;
 	int			error;
 
+	cancel_delayed_work_sync(&mp->m_eofblocks_work);
+
 	xfs_qm_unmount_quotas(mp);
 	xfs_rtunmount_inodes(mp);
 	IRELE(mp->m_rootip);
@@ -1473,25 +1023,20 @@ xfs_unmountfs(
 	xfs_log_force(mp, XFS_LOG_SYNC);
 
 	/*
-	 * Do a delwri reclaim pass first so that as many dirty inodes are
-	 * queued up for IO as possible. Then flush the buffers before making
-	 * a synchronous path to catch all the remaining inodes are reclaimed.
-	 * This makes the reclaim process as quick as possible by avoiding
-	 * synchronous writeout and blocking on inodes already in the delwri
-	 * state as much as possible.
+	 * Flush all pending changes from the AIL.
 	 */
-	xfs_reclaim_inodes(mp, 0);
-	xfs_flush_buftarg(mp->m_ddev_targp, 1);
-	xfs_reclaim_inodes(mp, SYNC_WAIT);
-
-	xfs_qm_unmount(mp);
+	xfs_ail_push_all_sync(mp->m_ail);
 
 	/*
-	 * Flush out the log synchronously so that we know for sure
-	 * that nothing is pinned.  This is important because bflush()
-	 * will skip pinned buffers.
+	 * And reclaim all inodes.  At this point there should be no dirty
+	 * inodes and none should be pinned or locked, but use synchronous
+	 * reclaim just to be sure. We can stop background inode reclaim
+	 * here as well if it is still running.
 	 */
-	xfs_log_force(mp, XFS_LOG_SYNC);
+	cancel_delayed_work_sync(&mp->m_reclaim_work);
+	xfs_reclaim_inodes(mp, SYNC_WAIT);
+
+	xfs_qm_unmount(mp);
 
 	/*
 	 * Unreserve any blocks we have so that when we unmount we don't account
@@ -1517,19 +1062,9 @@ xfs_unmountfs(
 	if (error)
 		xfs_warn(mp, "Unable to update superblock counters. "
 				"Freespace may not be correct on next mount.");
-	xfs_unmountfs_writesb(mp);
-
-	/*
-	 * Make sure all buffers have been flushed and completed before
-	 * unmounting the log.
-	 */
-	error = xfs_flush_buftarg(mp->m_ddev_targp, 1);
-	if (error)
-		xfs_warn(mp, "%d busy buffers during unmount.", error);
-	xfs_wait_buftarg(mp->m_ddev_targp);
 
-	xfs_log_unmount_write(mp);
 	xfs_log_unmount(mp);
+	xfs_da_unmount(mp);
 	xfs_uuid_unmount(mp);
 
 #if defined(DEBUG)
@@ -1541,7 +1076,7 @@ xfs_unmountfs(
 int
 xfs_fs_writable(xfs_mount_t *mp)
 {
-	return !(xfs_test_for_freeze(mp) || XFS_FORCED_SHUTDOWN(mp) ||
+	return !(mp->m_super->s_writers.frozen || XFS_FORCED_SHUTDOWN(mp) ||
 		(mp->m_flags & XFS_MOUNT_RDONLY));
 }
 
@@ -1573,8 +1108,7 @@ xfs_log_sbcount(xfs_mount_t *mp)
 		return 0;
 
 	tp = _xfs_trans_alloc(mp, XFS_TRANS_SB_COUNT, KM_SLEEP);
-	error = xfs_trans_reserve(tp, 0, mp->m_sb.sb_sectsize + 128, 0, 0,
-					XFS_DEFAULT_LOG_COUNT);
+	error = xfs_trans_reserve(tp, &M_RES(mp)->tr_sb, 0, 0);
 	if (error) {
 		xfs_trans_cancel(tp, 0);
 		return error;
@@ -1586,79 +1120,8 @@ xfs_log_sbcount(xfs_mount_t *mp)
 	return error;
 }
 
-int
-xfs_unmountfs_writesb(xfs_mount_t *mp)
-{
-	xfs_buf_t	*sbp;
-	int		error = 0;
-
-	/*
-	 * skip superblock write if fs is read-only, or
-	 * if we are doing a forced umount.
-	 */
-	if (!((mp->m_flags & XFS_MOUNT_RDONLY) ||
-		XFS_FORCED_SHUTDOWN(mp))) {
-
-		sbp = xfs_getsb(mp, 0);
-
-		XFS_BUF_UNDONE(sbp);
-		XFS_BUF_UNREAD(sbp);
-		xfs_buf_delwri_dequeue(sbp);
-		XFS_BUF_WRITE(sbp);
-		XFS_BUF_UNASYNC(sbp);
-		ASSERT(sbp->b_target == mp->m_ddev_targp);
-		xfsbdstrat(mp, sbp);
-		error = xfs_buf_iowait(sbp);
-		if (error)
-			xfs_buf_ioerror_alert(sbp, __func__);
-		xfs_buf_relse(sbp);
-	}
-	return error;
-}
-
-/*
- * xfs_mod_sb() can be used to copy arbitrary changes to the
- * in-core superblock into the superblock buffer to be logged.
- * It does not provide the higher level of locking that is
- * needed to protect the in-core superblock from concurrent
- * access.
- */
-void
-xfs_mod_sb(xfs_trans_t *tp, __int64_t fields)
-{
-	xfs_buf_t	*bp;
-	int		first;
-	int		last;
-	xfs_mount_t	*mp;
-	xfs_sb_field_t	f;
-
-	ASSERT(fields);
-	if (!fields)
-		return;
-	mp = tp->t_mountp;
-	bp = xfs_trans_getsb(tp, mp, 0);
-	first = sizeof(xfs_sb_t);
-	last = 0;
-
-	/* translate/copy */
-
-	xfs_sb_to_disk(XFS_BUF_TO_SBP(bp), &mp->m_sb, fields);
-
-	/* find modified range */
-	f = (xfs_sb_field_t)xfs_highbit64((__uint64_t)fields);
-	ASSERT((1LL << f) & XFS_SB_MOD_BITS);
-	last = xfs_sb_info[f + 1].offset - 1;
-
-	f = (xfs_sb_field_t)xfs_lowbit64((__uint64_t)fields);
-	ASSERT((1LL << f) & XFS_SB_MOD_BITS);
-	first = xfs_sb_info[f].offset;
-
-	xfs_trans_log_buf(tp, bp, first, last);
-}
-
-
 /*
- * xfs_mod_incore_sb_unlocked() is a utility routine common used to apply
+ * xfs_mod_incore_sb_unlocked() is a utility routine commonly used to apply
  * a delta to a specified field in the in-core superblock.  Simply
  * switch on the field indicated and apply the delta to that field.
  * Fields are not allowed to dip below zero, so if the delta would
@@ -1965,8 +1428,7 @@ xfs_mount_log_sb(
 			 XFS_SB_VERSIONNUM));
 
 	tp = xfs_trans_alloc(mp, XFS_TRANS_SB_UNIT);
-	error = xfs_trans_reserve(tp, 0, mp->m_sb.sb_sectsize + 128, 0, 0,
-				XFS_DEFAULT_LOG_COUNT);
+	error = xfs_trans_reserve(tp, &M_RES(mp)->tr_sb, 0, 0);
 	if (error) {
 		xfs_trans_cancel(tp, 0);
 		return error;
@@ -2124,12 +1586,6 @@ xfs_icsb_init_counters(
 	if (mp->m_sb_cnts == NULL)
 		return -ENOMEM;
 
-#ifdef CONFIG_HOTPLUG_CPU
-	mp->m_icsb_notifier.notifier_call = xfs_icsb_cpu_notify;
-	mp->m_icsb_notifier.priority = 0;
-	register_hotcpu_notifier(&mp->m_icsb_notifier);
-#endif /* CONFIG_HOTPLUG_CPU */
-
 	for_each_online_cpu(i) {
 		cntp = (xfs_icsb_cnts_t *)per_cpu_ptr(mp->m_sb_cnts, i);
 		memset(cntp, 0, sizeof(xfs_icsb_cnts_t));
@@ -2142,6 +1598,13 @@ xfs_icsb_init_counters(
 	 * initial balance kicks us off correctly
 	 */
 	mp->m_icsb_counters = -1;
+
+#ifdef CONFIG_HOTPLUG_CPU
+	mp->m_icsb_notifier.notifier_call = xfs_icsb_cpu_notify;
+	mp->m_icsb_notifier.priority = 0;
+	register_hotcpu_notifier(&mp->m_icsb_notifier);
+#endif /* CONFIG_HOTPLUG_CPU */
+
 	return 0;
 }