--- zzzz-none-000/linux-3.10.107/fs/xfs/xfs_mount.c	2017-06-27 09:49:32.000000000 +0000
+++ scorpion-7490-727/linux-3.10.107/fs/xfs/xfs_mount.c	2021-02-04 17:41:59.000000000 +0000
@@ -17,115 +17,46 @@
  */
 #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_trans_priv.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_da_btree.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_quota.h"
 #include "xfs_fsops.h"
-#include "xfs_utils.h"
 #include "xfs_trace.h"
 #include "xfs_icache.h"
-#include "xfs_cksum.h"
-#include "xfs_buf_item.h"
+#include "xfs_sysfs.h"
 
 
-#ifdef HAVE_PERCPU_SB
-STATIC void	xfs_icsb_balance_counter(xfs_mount_t *, xfs_sb_field_t,
-						int);
-STATIC void	xfs_icsb_balance_counter_locked(xfs_mount_t *, xfs_sb_field_t,
-						int);
-STATIC void	xfs_icsb_disable_counter(xfs_mount_t *, xfs_sb_field_t);
-#else
-
-#define xfs_icsb_balance_counter(mp, a, b)		do { } while (0)
-#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 },
-    { offsetof(xfs_sb_t, sb_features_compat), 0 },
-    { offsetof(xfs_sb_t, sb_features_ro_compat), 0 },
-    { offsetof(xfs_sb_t, sb_features_incompat), 0 },
-    { offsetof(xfs_sb_t, sb_features_log_incompat), 0 },
-    { offsetof(xfs_sb_t, sb_crc),	 0 },
-    { offsetof(xfs_sb_t, sb_pad),	 0 },
-    { offsetof(xfs_sb_t, sb_pquotino),	 0 },
-    { offsetof(xfs_sb_t, sb_lsn),	 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;
 
+void
+xfs_uuid_table_free(void)
+{
+	if (xfs_uuid_table_size == 0)
+		return;
+	kmem_free(xfs_uuid_table);
+	xfs_uuid_table = NULL;
+	xfs_uuid_table_size = 0;
+}
+
 /*
  * See if the UUID is unique among mounted XFS filesystems.
  * Mount fails if UUID is nil or a FS with the same UUID is already mounted.
@@ -142,7 +73,7 @@
 
 	if (uuid_is_nil(uuid)) {
 		xfs_warn(mp, "Filesystem has nil UUID - can't mount");
-		return XFS_ERROR(EINVAL);
+		return -EINVAL;
 	}
 
 	mutex_lock(&xfs_uuid_table_mutex);
@@ -170,7 +101,7 @@
  out_duplicate:
 	mutex_unlock(&xfs_uuid_table_mutex);
 	xfs_warn(mp, "Filesystem has duplicate UUID %pU - can't mount", uuid);
-	return XFS_ERROR(EINVAL);
+	return -EINVAL;
 }
 
 STATIC void
@@ -197,64 +128,6 @@
 }
 
 
-/*
- * 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)
@@ -297,183 +170,9 @@
 	ASSERT(PAGE_SHIFT >= sbp->sb_blocklog);
 	ASSERT(sbp->sb_blocklog >= BBSHIFT);
 
-#if XFS_BIG_BLKNOS     /* Limited by ULONG_MAX of page cache index */
+	/* Limited by ULONG_MAX of page cache index */
 	if (nblocks >> (PAGE_CACHE_SHIFT - sbp->sb_blocklog) > ULONG_MAX)
-		return EFBIG;
-#else                  /* Limited by UINT_MAX of sectors */
-	if (nblocks << (sbp->sb_blocklog - BBSHIFT) > UINT_MAX)
-		return EFBIG;
-#endif
-	return 0;
-}
-
-/*
- * Check the validity of the SB found.
- */
-STATIC int
-xfs_mount_validate_sb(
-	xfs_mount_t	*mp,
-	xfs_sb_t	*sbp,
-	bool		check_inprogress,
-	bool		check_version)
-{
-
-	/*
-	 * 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) {
-		xfs_warn(mp, "bad magic number");
-		return XFS_ERROR(EWRONGFS);
-	}
-
-
-	if (!xfs_sb_good_version(sbp)) {
-		xfs_warn(mp, "bad version");
-		return XFS_ERROR(EWRONGFS);
-	}
-
-	/*
-	 * Version 5 superblock feature mask validation. Reject combinations the
-	 * kernel cannot support up front before checking anything else. For
-	 * write validation, we don't need to check feature masks.
-	 */
-	if (check_version && XFS_SB_VERSION_NUM(sbp) == XFS_SB_VERSION_5) {
-		xfs_alert(mp,
-"Version 5 superblock detected. This kernel has EXPERIMENTAL support enabled!\n"
-"Use of these features in this kernel is at your own risk!");
-
-		if (xfs_sb_has_compat_feature(sbp,
-					XFS_SB_FEAT_COMPAT_UNKNOWN)) {
-			xfs_warn(mp,
-"Superblock has unknown compatible features (0x%x) enabled.\n"
-"Using a more recent kernel is recommended.",
-				(sbp->sb_features_compat &
-						XFS_SB_FEAT_COMPAT_UNKNOWN));
-		}
-
-		if (xfs_sb_has_ro_compat_feature(sbp,
-					XFS_SB_FEAT_RO_COMPAT_UNKNOWN)) {
-			xfs_alert(mp,
-"Superblock has unknown read-only compatible features (0x%x) enabled.",
-				(sbp->sb_features_ro_compat &
-						XFS_SB_FEAT_RO_COMPAT_UNKNOWN));
-			if (!(mp->m_flags & XFS_MOUNT_RDONLY)) {
-				xfs_warn(mp,
-"Attempted to mount read-only compatible filesystem read-write.\n"
-"Filesystem can only be safely mounted read only.");
-				return XFS_ERROR(EINVAL);
-			}
-		}
-		if (xfs_sb_has_incompat_feature(sbp,
-					XFS_SB_FEAT_INCOMPAT_UNKNOWN)) {
-			xfs_warn(mp,
-"Superblock has unknown incompatible features (0x%x) enabled.\n"
-"Filesystem can not be safely mounted by this kernel.",
-				(sbp->sb_features_incompat &
-						XFS_SB_FEAT_INCOMPAT_UNKNOWN));
-			return XFS_ERROR(EINVAL);
-		}
-	}
-
-	if (unlikely(
-	    sbp->sb_logstart == 0 && mp->m_logdev_targp == mp->m_ddev_targp)) {
-		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)) {
-		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))) {
-		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)) {
-		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:
-		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)) {
-		xfs_warn(mp,
-		"file system too large to be mounted on this system.");
-		return XFS_ERROR(EFBIG);
-	}
-
-	if (check_inprogress && sbp->sb_inprogress) {
-		xfs_warn(mp, "Offline file system operation in progress!");
-		return XFS_ERROR(EFSCORRUPTED);
-	}
-
-	/*
-	 * Version 1 directory format has never worked on Linux.
-	 */
-	if (unlikely(!xfs_sb_version_hasdirv2(sbp))) {
-		xfs_warn(mp, "file system using version 1 directory format");
-		return XFS_ERROR(ENOSYS);
-	}
-
+		return -EFBIG;
 	return 0;
 }
 
@@ -544,9 +243,9 @@
 		mp->m_flags &= ~XFS_MOUNT_32BITINODES;
 
 	if (mp->m_flags & XFS_MOUNT_32BITINODES)
-		index = xfs_set_inode32(mp);
+		index = xfs_set_inode32(mp, agcount);
 	else
-		index = xfs_set_inode64(mp);
+		index = xfs_set_inode64(mp, agcount);
 
 	if (maxagi)
 		*maxagi = index;
@@ -561,280 +260,68 @@
 	return error;
 }
 
-void
-xfs_sb_from_disk(
-	struct xfs_sb	*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);
-	to->sb_features_compat = be32_to_cpu(from->sb_features_compat);
-	to->sb_features_ro_compat = be32_to_cpu(from->sb_features_ro_compat);
-	to->sb_features_incompat = be32_to_cpu(from->sb_features_incompat);
-	to->sb_features_log_incompat =
-				be32_to_cpu(from->sb_features_log_incompat);
-	to->sb_pad = 0;
-	to->sb_pquotino = be64_to_cpu(from->sb_pquotino);
-	to->sb_lsn = be64_to_cpu(from->sb_lsn);
-}
-
-/*
- * 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);
-	}
-}
-
-static int
-xfs_sb_verify(
-	struct xfs_buf	*bp,
-	bool		check_version)
-{
-	struct xfs_mount *mp = bp->b_target->bt_mount;
-	struct xfs_sb	sb;
-
-	xfs_sb_from_disk(&sb, XFS_BUF_TO_SBP(bp));
-
-	/*
-	 * Only check the in progress field for the primary superblock as
-	 * mkfs.xfs doesn't clear it from secondary superblocks.
-	 */
-	return xfs_mount_validate_sb(mp, &sb,
-				     bp->b_maps[0].bm_bn == XFS_SB_DADDR,
-				     check_version);
-}
-
-/*
- * If the superblock has the CRC feature bit set or the CRC field is non-null,
- * check that the CRC is valid.  We check the CRC field is non-null because a
- * single bit error could clear the feature bit and unused parts of the
- * superblock are supposed to be zero. Hence a non-null crc field indicates that
- * we've potentially lost a feature bit and we should check it anyway.
- */
-static void
-xfs_sb_read_verify(
-	struct xfs_buf	*bp)
-{
-	struct xfs_mount *mp = bp->b_target->bt_mount;
-	struct xfs_dsb	*dsb = XFS_BUF_TO_SBP(bp);
-	int		error;
-
-	/*
-	 * open code the version check to avoid needing to convert the entire
-	 * superblock from disk order just to check the version number
-	 */
-	if (dsb->sb_magicnum == cpu_to_be32(XFS_SB_MAGIC) &&
-	    (((be16_to_cpu(dsb->sb_versionnum) & XFS_SB_VERSION_NUMBITS) ==
-						XFS_SB_VERSION_5) ||
-	     dsb->sb_crc != 0)) {
-
-		if (!xfs_verify_cksum(bp->b_addr, be16_to_cpu(dsb->sb_sectsize),
-				      offsetof(struct xfs_sb, sb_crc))) {
-			error = EFSCORRUPTED;
-			goto out_error;
-		}
-	}
-	error = xfs_sb_verify(bp, true);
-
-out_error:
-	if (error) {
-		XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_LOW, mp, bp->b_addr);
-		xfs_buf_ioerror(bp, error);
-	}
-}
-
-/*
- * We may be probed for a filesystem match, so we may not want to emit
- * messages when the superblock buffer is not actually an XFS superblock.
- * If we find an XFS superblock, the run a normal, noisy mount because we are
- * really going to mount it and want to know about errors.
- */
-static void
-xfs_sb_quiet_read_verify(
-	struct xfs_buf	*bp)
-{
-	struct xfs_dsb	*dsb = XFS_BUF_TO_SBP(bp);
-
-
-	if (dsb->sb_magicnum == cpu_to_be32(XFS_SB_MAGIC)) {
-		/* XFS filesystem, verify noisily! */
-		xfs_sb_read_verify(bp);
-		return;
-	}
-	/* quietly fail */
-	xfs_buf_ioerror(bp, EWRONGFS);
-}
-
-static void
-xfs_sb_write_verify(
-	struct xfs_buf		*bp)
-{
-	struct xfs_mount	*mp = bp->b_target->bt_mount;
-	struct xfs_buf_log_item	*bip = bp->b_fspriv;
-	int			error;
-
-	error = xfs_sb_verify(bp, false);
-	if (error) {
-		XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_LOW, mp, bp->b_addr);
-		xfs_buf_ioerror(bp, error);
-		return;
-	}
-
-	if (!xfs_sb_version_hascrc(&mp->m_sb))
-		return;
-
-	if (bip)
-		XFS_BUF_TO_SBP(bp)->sb_lsn = cpu_to_be64(bip->bli_item.li_lsn);
-
-	xfs_update_cksum(bp->b_addr, BBTOB(bp->b_length),
-			 offsetof(struct xfs_sb, sb_crc));
-}
-
-const struct xfs_buf_ops xfs_sb_buf_ops = {
-	.verify_read = xfs_sb_read_verify,
-	.verify_write = xfs_sb_write_verify,
-};
-
-static const struct xfs_buf_ops xfs_sb_quiet_buf_ops = {
-	.verify_read = xfs_sb_quiet_read_verify,
-	.verify_write = xfs_sb_write_verify,
-};
-
 /*
  * 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;
 	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->m_ddev_targp, XFS_SB_DADDR,
-				   BTOBB(sector_size), 0,
-				   loud ? &xfs_sb_buf_ops
-				        : &xfs_sb_quiet_buf_ops);
-	if (!bp) {
-		if (loud)
-			xfs_warn(mp, "SB buffer read failed");
-		return EIO;
-	}
-	if (bp->b_error) {
-		error = bp->b_error;
+	error = xfs_buf_read_uncached(mp->m_ddev_targp, XFS_SB_DADDR,
+				   BTOBB(sector_size), 0, &bp, buf_ops);
+	if (error) {
 		if (loud)
 			xfs_warn(mp, "SB validate failed with error %d.", error);
-		goto release_buf;
+		/* bad CRC means corrupted metadata */
+		if (error == -EFSBADCRC)
+			error = -EFSCORRUPTED;
+		return error;
 	}
 
 	/*
 	 * Initialize the mount structure from the superblock.
 	 */
-	xfs_sb_from_disk(&mp->m_sb, XFS_BUF_TO_SBP(bp));
+	xfs_sb_from_disk(sbp, XFS_BUF_TO_SBP(bp));
+
+	/*
+	 * 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, "Invalid superblock magic number");
+		error = -EINVAL;
+		goto release_buf;
+	}
 
 	/*
 	 * We must be able to do sector-sized and sector-aligned IO.
@@ -843,22 +330,22 @@
 		if (loud)
 			xfs_warn(mp, "device supports %u byte sectors (not %u)",
 				sector_size, sbp->sb_sectsize);
-		error = ENOSYS;
+		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 < sbp->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 = 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);
+	xfs_reinit_percpu_counters(mp);
 
 	/* no need to be quiet anymore, so reset the buf ops */
 	bp->b_ops = &xfs_sb_buf_ops;
@@ -872,107 +359,6 @@
 	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
  */
@@ -988,42 +374,27 @@
 		 */
 		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 -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 -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 -EINVAL;
 			}
 		}
 
@@ -1034,12 +405,16 @@
 		if (xfs_sb_version_hasdalign(sbp)) {
 			if (sbp->sb_unit != mp->m_dalign) {
 				sbp->sb_unit = mp->m_dalign;
-				mp->m_update_flags |= XFS_SB_UNIT;
+				mp->m_update_sb = true;
 			}
 			if (sbp->sb_width != mp->m_swidth) {
 				sbp->sb_width = mp->m_swidth;
-				mp->m_update_flags |= XFS_SB_WIDTH;
+				mp->m_update_sb = true;
 			}
+		} else {
+			xfs_warn(mp,
+	"cannot change alignment: superblock does not support data alignment");
+			return -EINVAL;
 		}
 	} else if ((mp->m_flags & XFS_MOUNT_NOALIGN) != XFS_MOUNT_NOALIGN &&
 		    xfs_sb_version_hasdalign(&mp->m_sb)) {
@@ -1155,43 +530,46 @@
 }
 
 /*
- * 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)
+xfs_check_sizes(
+	struct xfs_mount *mp)
 {
-	xfs_buf_t	*bp;
+	struct xfs_buf	*bp;
 	xfs_daddr_t	d;
+	int		error;
 
 	d = (xfs_daddr_t)XFS_FSB_TO_BB(mp, mp->m_sb.sb_dblocks);
 	if (XFS_BB_TO_FSB(mp, d) != mp->m_sb.sb_dblocks) {
 		xfs_warn(mp, "filesystem size mismatch detected");
-		return XFS_ERROR(EFBIG);
+		return -EFBIG;
 	}
-	bp = xfs_buf_read_uncached(mp->m_ddev_targp,
+	error = xfs_buf_read_uncached(mp->m_ddev_targp,
 					d - XFS_FSS_TO_BB(mp, 1),
-					XFS_FSS_TO_BB(mp, 1), 0, NULL);
-	if (!bp) {
+					XFS_FSS_TO_BB(mp, 1), 0, &bp, NULL);
+	if (error) {
 		xfs_warn(mp, "last sector read failed");
-		return EIO;
+		return error;
 	}
 	xfs_buf_relse(bp);
 
-	if (mp->m_logdev_targp != mp->m_ddev_targp) {
-		d = (xfs_daddr_t)XFS_FSB_TO_BB(mp, mp->m_sb.sb_logblocks);
-		if (XFS_BB_TO_FSB(mp, d) != mp->m_sb.sb_logblocks) {
-			xfs_warn(mp, "log size mismatch detected");
-			return XFS_ERROR(EFBIG);
-		}
-		bp = xfs_buf_read_uncached(mp->m_logdev_targp,
+	if (mp->m_logdev_targp == mp->m_ddev_targp)
+		return 0;
+
+	d = (xfs_daddr_t)XFS_FSB_TO_BB(mp, mp->m_sb.sb_logblocks);
+	if (XFS_BB_TO_FSB(mp, d) != mp->m_sb.sb_logblocks) {
+		xfs_warn(mp, "log size mismatch detected");
+		return -EFBIG;
+	}
+	error = xfs_buf_read_uncached(mp->m_logdev_targp,
 					d - XFS_FSB_TO_BB(mp, 1),
-					XFS_FSB_TO_BB(mp, 1), 0, NULL);
-		if (!bp) {
-			xfs_warn(mp, "log device read failed");
-			return EIO;
-		}
-		xfs_buf_relse(bp);
+					XFS_FSB_TO_BB(mp, 1), 0, &bp, NULL);
+	if (error) {
+		xfs_warn(mp, "log device read failed");
+		return error;
 	}
+	xfs_buf_relse(bp);
 	return 0;
 }
 
@@ -1202,39 +580,19 @@
 xfs_mount_reset_sbqflags(
 	struct xfs_mount	*mp)
 {
-	int			error;
-	struct xfs_trans	*tp;
-
 	mp->m_qflags = 0;
 
-	/*
-	 * It is OK to look at sb_qflags here in mount path,
-	 * without m_sb_lock.
-	 */
+	/* It is OK to look at sb_qflags in the mount path without m_sb_lock. */
 	if (mp->m_sb.sb_qflags == 0)
 		return 0;
 	spin_lock(&mp->m_sb_lock);
 	mp->m_sb.sb_qflags = 0;
 	spin_unlock(&mp->m_sb_lock);
 
-	/*
-	 * If the fs is readonly, let the incore superblock run
-	 * with quotas off but don't flush the update out to disk
-	 */
-	if (mp->m_flags & XFS_MOUNT_RDONLY)
+	if (!xfs_fs_writable(mp, SB_FREEZE_WRITE))
 		return 0;
 
-	tp = xfs_trans_alloc(mp, XFS_TRANS_QM_SBCHANGE);
-	error = xfs_trans_reserve(tp, 0, XFS_QM_SBCHANGE_LOG_RES(mp),
-				  0, 0, XFS_DEFAULT_LOG_COUNT);
-	if (error) {
-		xfs_trans_cancel(tp, 0);
-		xfs_alert(mp, "%s: Superblock update failed!", __func__);
-		return error;
-	}
-
-	xfs_mod_sb(tp, XFS_SB_QFLAGS);
-	return xfs_trans_commit(tp, 0);
+	return xfs_sync_sb(mp, false);
 }
 
 __uint64_t
@@ -1267,38 +625,37 @@
  */
 int
 xfs_mountfs(
-	xfs_mount_t	*mp)
+	struct xfs_mount	*mp)
 {
-	xfs_sb_t	*sbp = &(mp->m_sb);
-	xfs_inode_t	*rip;
-	__uint64_t	resblks;
-	uint		quotamount = 0;
-	uint		quotaflags = 0;
-	int		error = 0;
-
-	xfs_mount_common(mp, sbp);
+	struct xfs_sb		*sbp = &(mp->m_sb);
+	struct xfs_inode	*rip;
+	__uint64_t		resblks;
+	uint			quotamount = 0;
+	uint			quotaflags = 0;
+	int			error = 0;
+
+	xfs_sb_mount_common(mp, sbp);
 
 	/*
-	 * Check for a mismatched features2 values.  Older kernels
-	 * read & wrote into the wrong sb offset for sb_features2
-	 * on some platforms due to xfs_sb_t not being 64bit size aligned
-	 * when sb_features2 was added, which made older superblock
-	 * reading/writing routines swap it as a 64-bit value.
+	 * Check for a mismatched features2 values.  Older kernels read & wrote
+	 * into the wrong sb offset for sb_features2 on some platforms due to
+	 * xfs_sb_t not being 64bit size aligned when sb_features2 was added,
+	 * which made older superblock reading/writing routines swap it as a
+	 * 64-bit value.
 	 *
 	 * For backwards compatibility, we make both slots equal.
 	 *
-	 * If we detect a mismatched field, we OR the set bits into the
-	 * existing features2 field in case it has already been modified; we
-	 * don't want to lose any features.  We then update the bad location
-	 * with the ORed value so that older kernels will see any features2
-	 * flags, and mark the two fields as needing updates once the
-	 * transaction subsystem is online.
+	 * If we detect a mismatched field, we OR the set bits into the existing
+	 * features2 field in case it has already been modified; we don't want
+	 * to lose any features.  We then update the bad location with the ORed
+	 * value so that older kernels will see any features2 flags. The
+	 * superblock writeback code ensures the new sb_features2 is copied to
+	 * sb_bad_features2 before it is logged or written to disk.
 	 */
 	if (xfs_sb_has_mismatched_features2(sbp)) {
 		xfs_warn(mp, "correcting sb_features alignment problem");
 		sbp->sb_features2 |= sbp->sb_bad_features2;
-		sbp->sb_bad_features2 = sbp->sb_features2;
-		mp->m_update_flags |= XFS_SB_FEATURES2 | XFS_SB_BAD_FEATURES2;
+		mp->m_update_sb = true;
 
 		/*
 		 * Re-check for ATTR2 in case it was found in bad_features2
@@ -1312,11 +669,17 @@
 	if (xfs_sb_version_hasattr2(&mp->m_sb) &&
 	   (mp->m_flags & XFS_MOUNT_NOATTR2)) {
 		xfs_sb_version_removeattr2(&mp->m_sb);
-		mp->m_update_flags |= XFS_SB_FEATURES2;
+		mp->m_update_sb = true;
 
 		/* update sb_versionnum for the clearing of the morebits */
 		if (!sbp->sb_features2)
-			mp->m_update_flags |= XFS_SB_VERSIONNUM;
+			mp->m_update_sb = true;
+	}
+
+	/* 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_sb = true;
 	}
 
 	/*
@@ -1336,10 +699,19 @@
 
 	xfs_set_maxicount(mp);
 
-	error = xfs_uuid_mount(mp);
+	error = xfs_sysfs_init(&mp->m_kobj, &xfs_mp_ktype, NULL, mp->m_fsname);
 	if (error)
 		goto out;
 
+	error = xfs_sysfs_init(&mp->m_stats.xs_kobj, &xfs_stats_ktype,
+			       &mp->m_kobj, "stats");
+	if (error)
+		goto out_remove_sysfs;
+
+	error = xfs_uuid_mount(mp);
+	if (error)
+		goto out_del_stats;
+
 	/*
 	 * Set the minimum read and write sizes
 	 */
@@ -1352,8 +724,36 @@
 	 * 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;
+	}
+
+	/*
+	 * If enabled, sparse inode chunk alignment is expected to match the
+	 * cluster size. Full inode chunk alignment must match the chunk size,
+	 * but that is checked on sb read verification...
+	 */
+	if (xfs_sb_version_hassparseinodes(&mp->m_sb) &&
+	    mp->m_sb.sb_spino_align !=
+			XFS_B_TO_FSBT(mp, mp->m_inode_cluster_size)) {
+		xfs_warn(mp,
+	"Sparse inode block alignment (%u) must match cluster size (%llu).",
+			 mp->m_sb.sb_spino_align,
+			 XFS_B_TO_FSBT(mp, mp->m_inode_cluster_size));
+		error = -EINVAL;
+		goto out_remove_uuid;
+	}
 
 	/*
 	 * Set inode alignment fields
@@ -1361,7 +761,7 @@
 	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)
@@ -1384,12 +784,11 @@
 
 	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.
@@ -1404,18 +803,20 @@
 	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) {
 		xfs_warn(mp, "no log defined");
 		XFS_ERROR_REPORT("xfs_mountfs", XFS_ERRLEVEL_LOW, mp);
-		error = XFS_ERROR(EFSCORRUPTED);
+		error = -EFSCORRUPTED;
 		goto out_free_perag;
 	}
 
 	/*
-	 * log's mount-time initialization. Perform 1st part recovery if needed
+	 * Log's mount-time initialization. The first part of recovery can place
+	 * some items on the AIL, to be handled when recovery is finished or
+	 * cancelled.
 	 */
 	error = xfs_log_mount(mp, mp->m_logdev_targp,
 			      XFS_FSB_TO_DADDR(mp, sbp->sb_logstart),
@@ -1449,7 +850,7 @@
 	     !mp->m_sb.sb_inprogress) {
 		error = xfs_initialize_perag_data(mp, sbp->sb_agcount);
 		if (error)
-			goto out_fail_wait;
+			goto out_log_dealloc;
 	}
 
 	/*
@@ -1470,7 +871,7 @@
 		xfs_iunlock(rip, XFS_ILOCK_EXCL);
 		XFS_ERROR_REPORT("xfs_mountfs_int(2)", XFS_ERRLEVEL_LOW,
 				 mp);
-		error = XFS_ERROR(EFSCORRUPTED);
+		error = -EFSCORRUPTED;
 		goto out_rele_rip;
 	}
 	mp->m_rootip = rip;	/* save it */
@@ -1494,8 +895,8 @@
 	 * the next remount into writeable mode.  Otherwise we would never
 	 * perform the update e.g. for the root filesystem.
 	 */
-	if (mp->m_update_flags && !(mp->m_flags & XFS_MOUNT_RDONLY)) {
-		error = xfs_mount_log_sb(mp, mp->m_update_flags);
+	if (mp->m_update_sb && !(mp->m_flags & XFS_MOUNT_RDONLY)) {
+		error = xfs_sync_sb(mp, false);
 		if (error) {
 			xfs_warn(mp, "failed to write sb changes");
 			goto out_rtunmount;
@@ -1521,14 +922,14 @@
 			xfs_notice(mp, "resetting quota flags");
 			error = xfs_mount_reset_sbqflags(mp);
 			if (error)
-				return error;
+				goto out_rtunmount;
 		}
 	}
 
 	/*
-	 * Finish recovering the file system.  This part needed to be
-	 * delayed until after the root and real-time bitmap inodes
-	 * were consistently read in.
+	 * Finish recovering the file system.  This part needed to be delayed
+	 * until after the root and real-time bitmap inodes were consistently
+	 * read in.
 	 */
 	error = xfs_log_mount_finish(mp);
 	if (error) {
@@ -1571,16 +972,24 @@
 	xfs_rtunmount_inodes(mp);
  out_rele_rip:
 	IRELE(rip);
+	cancel_delayed_work_sync(&mp->m_reclaim_work);
+	xfs_reclaim_inodes(mp, SYNC_WAIT);
  out_log_dealloc:
-	xfs_log_unmount(mp);
+	xfs_log_mount_cancel(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_del_stats:
+	xfs_sysfs_del(&mp->m_stats.xs_kobj);
+ out_remove_sysfs:
+	xfs_sysfs_del(&mp->m_kobj);
  out:
 	return error;
 }
@@ -1655,20 +1064,37 @@
 		xfs_warn(mp, "Unable to update superblock counters. "
 				"Freespace may not be correct on next mount.");
 
+
 	xfs_log_unmount(mp);
+	xfs_da_unmount(mp);
 	xfs_uuid_unmount(mp);
 
 #if defined(DEBUG)
 	xfs_errortag_clearall(mp, 0);
 #endif
 	xfs_free_perag(mp);
+
+	xfs_sysfs_del(&mp->m_stats.xs_kobj);
+	xfs_sysfs_del(&mp->m_kobj);
 }
 
-int
-xfs_fs_writable(xfs_mount_t *mp)
+/*
+ * Determine whether modifications can proceed. The caller specifies the minimum
+ * freeze level for which modifications should not be allowed. This allows
+ * certain operations to proceed while the freeze sequence is in progress, if
+ * necessary.
+ */
+bool
+xfs_fs_writable(
+	struct xfs_mount	*mp,
+	int			level)
 {
-	return !(mp->m_super->s_writers.frozen || XFS_FORCED_SHUTDOWN(mp) ||
-		(mp->m_flags & XFS_MOUNT_RDONLY));
+	ASSERT(level > SB_UNFROZEN);
+	if ((mp->m_super->s_writers.frozen >= level) ||
+	    XFS_FORCED_SHUTDOWN(mp) || (mp->m_flags & XFS_MOUNT_RDONLY))
+		return false;
+
+	return true;
 }
 
 /*
@@ -1676,21 +1102,17 @@
  *
  * Sync the superblock counters to disk.
  *
- * Note this code can be called during the process of freezing, so
- * we may need to use the transaction allocator which does not
- * block when the transaction subsystem is in its frozen state.
+ * Note this code can be called during the process of freezing, so we use the
+ * transaction allocator that does not block when the transaction subsystem is
+ * in its frozen state.
  */
 int
 xfs_log_sbcount(xfs_mount_t *mp)
 {
-	xfs_trans_t	*tp;
-	int		error;
-
-	if (!xfs_fs_writable(mp))
+	/* allow this to proceed during the freeze sequence... */
+	if (!xfs_fs_writable(mp, SB_FREEZE_COMPLETE))
 		return 0;
 
-	xfs_icsb_sync_counters(mp, 0);
-
 	/*
 	 * we don't need to do this if we are updating the superblock
 	 * counters on every modification.
@@ -1698,309 +1120,145 @@
 	if (!xfs_sb_version_haslazysbcount(&mp->m_sb))
 		return 0;
 
-	tp = _xfs_trans_alloc(mp, XFS_TRANS_SB_COUNT, KM_SLEEP);
-	error = xfs_trans_reserve(tp, 0, XFS_SB_LOG_RES(mp), 0, 0,
-				  XFS_DEFAULT_LOG_COUNT);
-	if (error) {
-		xfs_trans_cancel(tp, 0);
-		return error;
-	}
-
-	xfs_mod_sb(tp, XFS_SB_IFREE | XFS_SB_ICOUNT | XFS_SB_FDBLOCKS);
-	xfs_trans_set_sync(tp);
-	error = xfs_trans_commit(tp, 0);
-	return error;
+	return xfs_sync_sb(mp, true);
 }
 
 /*
- * 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.
+ * Deltas for the inode count are +/-64, hence we use a large batch size
+ * of 128 so we don't need to take the counter lock on every update.
  */
-void
-xfs_mod_sb(xfs_trans_t *tp, __int64_t fields)
+#define XFS_ICOUNT_BATCH	128
+int
+xfs_mod_icount(
+	struct xfs_mount	*mp,
+	int64_t			delta)
 {
-	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_buf_set_type(tp, bp, XFS_BLFT_SB_BUF);
-	xfs_trans_log_buf(tp, bp, first, last);
+	__percpu_counter_add(&mp->m_icount, delta, XFS_ICOUNT_BATCH);
+	if (__percpu_counter_compare(&mp->m_icount, 0, XFS_ICOUNT_BATCH) < 0) {
+		ASSERT(0);
+		percpu_counter_add(&mp->m_icount, -delta);
+		return -EINVAL;
+	}
+	return 0;
 }
 
-
-/*
- * xfs_mod_incore_sb_unlocked() is a utility routine common 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
- * do this do not apply it and return EINVAL.
- *
- * The m_sb_lock must be held when this routine is called.
- */
-STATIC int
-xfs_mod_incore_sb_unlocked(
-	xfs_mount_t	*mp,
-	xfs_sb_field_t	field,
-	int64_t		delta,
-	int		rsvd)
-{
-	int		scounter;	/* short counter for 32 bit fields */
-	long long	lcounter;	/* long counter for 64 bit fields */
-	long long	res_used, rem;
-
-	/*
-	 * With the in-core superblock spin lock held, switch
-	 * on the indicated field.  Apply the delta to the
-	 * proper field.  If the fields value would dip below
-	 * 0, then do not apply the delta and return EINVAL.
-	 */
-	switch (field) {
-	case XFS_SBS_ICOUNT:
-		lcounter = (long long)mp->m_sb.sb_icount;
-		lcounter += delta;
-		if (lcounter < 0) {
-			ASSERT(0);
-			return XFS_ERROR(EINVAL);
-		}
-		mp->m_sb.sb_icount = lcounter;
-		return 0;
-	case XFS_SBS_IFREE:
-		lcounter = (long long)mp->m_sb.sb_ifree;
-		lcounter += delta;
-		if (lcounter < 0) {
-			ASSERT(0);
-			return XFS_ERROR(EINVAL);
-		}
-		mp->m_sb.sb_ifree = lcounter;
-		return 0;
-	case XFS_SBS_FDBLOCKS:
-		lcounter = (long long)
-			mp->m_sb.sb_fdblocks - XFS_ALLOC_SET_ASIDE(mp);
-		res_used = (long long)(mp->m_resblks - mp->m_resblks_avail);
-
-		if (delta > 0) {		/* Putting blocks back */
-			if (res_used > delta) {
-				mp->m_resblks_avail += delta;
-			} else {
-				rem = delta - res_used;
-				mp->m_resblks_avail = mp->m_resblks;
-				lcounter += rem;
-			}
-		} else {				/* Taking blocks away */
-			lcounter += delta;
-			if (lcounter >= 0) {
-				mp->m_sb.sb_fdblocks = lcounter +
-							XFS_ALLOC_SET_ASIDE(mp);
-				return 0;
-			}
-
-			/*
-			 * We are out of blocks, use any available reserved
-			 * blocks if were allowed to.
-			 */
-			if (!rsvd)
-				return XFS_ERROR(ENOSPC);
-
-			lcounter = (long long)mp->m_resblks_avail + delta;
-			if (lcounter >= 0) {
-				mp->m_resblks_avail = lcounter;
-				return 0;
-			}
-			printk_once(KERN_WARNING
-				"Filesystem \"%s\": reserve blocks depleted! "
-				"Consider increasing reserve pool size.",
-				mp->m_fsname);
-			return XFS_ERROR(ENOSPC);
-		}
-
-		mp->m_sb.sb_fdblocks = lcounter + XFS_ALLOC_SET_ASIDE(mp);
-		return 0;
-	case XFS_SBS_FREXTENTS:
-		lcounter = (long long)mp->m_sb.sb_frextents;
-		lcounter += delta;
-		if (lcounter < 0) {
-			return XFS_ERROR(ENOSPC);
-		}
-		mp->m_sb.sb_frextents = lcounter;
-		return 0;
-	case XFS_SBS_DBLOCKS:
-		lcounter = (long long)mp->m_sb.sb_dblocks;
-		lcounter += delta;
-		if (lcounter < 0) {
-			ASSERT(0);
-			return XFS_ERROR(EINVAL);
-		}
-		mp->m_sb.sb_dblocks = lcounter;
-		return 0;
-	case XFS_SBS_AGCOUNT:
-		scounter = mp->m_sb.sb_agcount;
-		scounter += delta;
-		if (scounter < 0) {
-			ASSERT(0);
-			return XFS_ERROR(EINVAL);
-		}
-		mp->m_sb.sb_agcount = scounter;
-		return 0;
-	case XFS_SBS_IMAX_PCT:
-		scounter = mp->m_sb.sb_imax_pct;
-		scounter += delta;
-		if (scounter < 0) {
-			ASSERT(0);
-			return XFS_ERROR(EINVAL);
-		}
-		mp->m_sb.sb_imax_pct = scounter;
-		return 0;
-	case XFS_SBS_REXTSIZE:
-		scounter = mp->m_sb.sb_rextsize;
-		scounter += delta;
-		if (scounter < 0) {
-			ASSERT(0);
-			return XFS_ERROR(EINVAL);
-		}
-		mp->m_sb.sb_rextsize = scounter;
-		return 0;
-	case XFS_SBS_RBMBLOCKS:
-		scounter = mp->m_sb.sb_rbmblocks;
-		scounter += delta;
-		if (scounter < 0) {
-			ASSERT(0);
-			return XFS_ERROR(EINVAL);
-		}
-		mp->m_sb.sb_rbmblocks = scounter;
-		return 0;
-	case XFS_SBS_RBLOCKS:
-		lcounter = (long long)mp->m_sb.sb_rblocks;
-		lcounter += delta;
-		if (lcounter < 0) {
-			ASSERT(0);
-			return XFS_ERROR(EINVAL);
-		}
-		mp->m_sb.sb_rblocks = lcounter;
-		return 0;
-	case XFS_SBS_REXTENTS:
-		lcounter = (long long)mp->m_sb.sb_rextents;
-		lcounter += delta;
-		if (lcounter < 0) {
-			ASSERT(0);
-			return XFS_ERROR(EINVAL);
-		}
-		mp->m_sb.sb_rextents = lcounter;
-		return 0;
-	case XFS_SBS_REXTSLOG:
-		scounter = mp->m_sb.sb_rextslog;
-		scounter += delta;
-		if (scounter < 0) {
-			ASSERT(0);
-			return XFS_ERROR(EINVAL);
-		}
-		mp->m_sb.sb_rextslog = scounter;
-		return 0;
-	default:
+int
+xfs_mod_ifree(
+	struct xfs_mount	*mp,
+	int64_t			delta)
+{
+	percpu_counter_add(&mp->m_ifree, delta);
+	if (percpu_counter_compare(&mp->m_ifree, 0) < 0) {
 		ASSERT(0);
-		return XFS_ERROR(EINVAL);
+		percpu_counter_add(&mp->m_ifree, -delta);
+		return -EINVAL;
 	}
+	return 0;
 }
 
 /*
- * xfs_mod_incore_sb() is used to change a field in the in-core
- * superblock structure by the specified delta.  This modification
- * is protected by the m_sb_lock.  Just use the xfs_mod_incore_sb_unlocked()
- * routine to do the work.
+ * Deltas for the block count can vary from 1 to very large, but lock contention
+ * only occurs on frequent small block count updates such as in the delayed
+ * allocation path for buffered writes (page a time updates). Hence we set
+ * a large batch count (1024) to minimise global counter updates except when
+ * we get near to ENOSPC and we have to be very accurate with our updates.
  */
+#define XFS_FDBLOCKS_BATCH	1024
 int
-xfs_mod_incore_sb(
+xfs_mod_fdblocks(
 	struct xfs_mount	*mp,
-	xfs_sb_field_t		field,
 	int64_t			delta,
-	int			rsvd)
+	bool			rsvd)
 {
-	int			status;
+	int64_t			lcounter;
+	long long		res_used;
+	s32			batch;
 
-#ifdef HAVE_PERCPU_SB
-	ASSERT(field < XFS_SBS_ICOUNT || field > XFS_SBS_FDBLOCKS);
-#endif
-	spin_lock(&mp->m_sb_lock);
-	status = xfs_mod_incore_sb_unlocked(mp, field, delta, rsvd);
-	spin_unlock(&mp->m_sb_lock);
+	if (delta > 0) {
+		/*
+		 * If the reserve pool is depleted, put blocks back into it
+		 * first. Most of the time the pool is full.
+		 */
+		if (likely(mp->m_resblks == mp->m_resblks_avail)) {
+			percpu_counter_add(&mp->m_fdblocks, delta);
+			return 0;
+		}
 
-	return status;
-}
+		spin_lock(&mp->m_sb_lock);
+		res_used = (long long)(mp->m_resblks - mp->m_resblks_avail);
 
-/*
- * Change more than one field in the in-core superblock structure at a time.
- *
- * The fields and changes to those fields are specified in the array of
- * xfs_mod_sb structures passed in.  Either all of the specified deltas
- * will be applied or none of them will.  If any modified field dips below 0,
- * then all modifications will be backed out and EINVAL will be returned.
- *
- * Note that this function may not be used for the superblock values that
- * are tracked with the in-memory per-cpu counters - a direct call to
- * xfs_icsb_modify_counters is required for these.
- */
-int
-xfs_mod_incore_sb_batch(
-	struct xfs_mount	*mp,
-	xfs_mod_sb_t		*msb,
-	uint			nmsb,
-	int			rsvd)
-{
-	xfs_mod_sb_t		*msbp;
-	int			error = 0;
+		if (res_used > delta) {
+			mp->m_resblks_avail += delta;
+		} else {
+			delta -= res_used;
+			mp->m_resblks_avail = mp->m_resblks;
+			percpu_counter_add(&mp->m_fdblocks, delta);
+		}
+		spin_unlock(&mp->m_sb_lock);
+		return 0;
+	}
 
 	/*
-	 * Loop through the array of mod structures and apply each individually.
-	 * If any fail, then back out all those which have already been applied.
-	 * Do all of this within the scope of the m_sb_lock so that all of the
-	 * changes will be atomic.
+	 * Taking blocks away, need to be more accurate the closer we
+	 * are to zero.
+	 *
+	 * If the counter has a value of less than 2 * max batch size,
+	 * then make everything serialise as we are real close to
+	 * ENOSPC.
+	 */
+	if (__percpu_counter_compare(&mp->m_fdblocks, 2 * XFS_FDBLOCKS_BATCH,
+				     XFS_FDBLOCKS_BATCH) < 0)
+		batch = 1;
+	else
+		batch = XFS_FDBLOCKS_BATCH;
+
+	__percpu_counter_add(&mp->m_fdblocks, delta, batch);
+	if (__percpu_counter_compare(&mp->m_fdblocks, XFS_ALLOC_SET_ASIDE(mp),
+				     XFS_FDBLOCKS_BATCH) >= 0) {
+		/* we had space! */
+		return 0;
+	}
+
+	/*
+	 * lock up the sb for dipping into reserves before releasing the space
+	 * that took us to ENOSPC.
 	 */
 	spin_lock(&mp->m_sb_lock);
-	for (msbp = msb; msbp < (msb + nmsb); msbp++) {
-		ASSERT(msbp->msb_field < XFS_SBS_ICOUNT ||
-		       msbp->msb_field > XFS_SBS_FDBLOCKS);
-
-		error = xfs_mod_incore_sb_unlocked(mp, msbp->msb_field,
-						   msbp->msb_delta, rsvd);
-		if (error)
-			goto unwind;
+	percpu_counter_add(&mp->m_fdblocks, -delta);
+	if (!rsvd)
+		goto fdblocks_enospc;
+
+	lcounter = (long long)mp->m_resblks_avail + delta;
+	if (lcounter >= 0) {
+		mp->m_resblks_avail = lcounter;
+		spin_unlock(&mp->m_sb_lock);
+		return 0;
 	}
+	printk_once(KERN_WARNING
+		"Filesystem \"%s\": reserve blocks depleted! "
+		"Consider increasing reserve pool size.",
+		mp->m_fsname);
+fdblocks_enospc:
 	spin_unlock(&mp->m_sb_lock);
-	return 0;
+	return -ENOSPC;
+}
 
-unwind:
-	while (--msbp >= msb) {
-		error = xfs_mod_incore_sb_unlocked(mp, msbp->msb_field,
-						   -msbp->msb_delta, rsvd);
-		ASSERT(error == 0);
-	}
+int
+xfs_mod_frextents(
+	struct xfs_mount	*mp,
+	int64_t			delta)
+{
+	int64_t			lcounter;
+	int			ret = 0;
+
+	spin_lock(&mp->m_sb_lock);
+	lcounter = mp->m_sb.sb_frextents + delta;
+	if (lcounter < 0)
+		ret = -ENOSPC;
+	else
+		mp->m_sb.sb_frextents = lcounter;
 	spin_unlock(&mp->m_sb_lock);
-	return error;
+	return ret;
 }
 
 /*
@@ -2045,35 +1303,6 @@
 }
 
 /*
- * Used to log changes to the superblock unit and width fields which could
- * be altered by the mount options, as well as any potential sb_features2
- * fixup. Only the first superblock is updated.
- */
-int
-xfs_mount_log_sb(
-	xfs_mount_t	*mp,
-	__int64_t	fields)
-{
-	xfs_trans_t	*tp;
-	int		error;
-
-	ASSERT(fields & (XFS_SB_UNIT | XFS_SB_WIDTH | XFS_SB_UUID |
-			 XFS_SB_FEATURES2 | XFS_SB_BAD_FEATURES2 |
-			 XFS_SB_VERSIONNUM));
-
-	tp = xfs_trans_alloc(mp, XFS_TRANS_SB_UNIT);
-	error = xfs_trans_reserve(tp, 0, XFS_SB_LOG_RES(mp), 0, 0,
-				  XFS_DEFAULT_LOG_COUNT);
-	if (error) {
-		xfs_trans_cancel(tp, 0);
-		return error;
-	}
-	xfs_mod_sb(tp, fields);
-	error = xfs_trans_commit(tp, 0);
-	return error;
-}
-
-/*
  * If the underlying (data/log/rt) device is readonly, there are some
  * operations that cannot proceed.
  */
@@ -2087,576 +1316,7 @@
 	    (mp->m_rtdev_targp && xfs_readonly_buftarg(mp->m_rtdev_targp))) {
 		xfs_notice(mp, "%s required on read-only device.", message);
 		xfs_notice(mp, "write access unavailable, cannot proceed.");
-		return EROFS;
-	}
-	return 0;
-}
-
-#ifdef HAVE_PERCPU_SB
-/*
- * Per-cpu incore superblock counters
- *
- * Simple concept, difficult implementation
- *
- * Basically, replace the incore superblock counters with a distributed per cpu
- * counter for contended fields (e.g.  free block count).
- *
- * Difficulties arise in that the incore sb is used for ENOSPC checking, and
- * hence needs to be accurately read when we are running low on space. Hence
- * there is a method to enable and disable the per-cpu counters based on how
- * much "stuff" is available in them.
- *
- * Basically, a counter is enabled if there is enough free resource to justify
- * running a per-cpu fast-path. If the per-cpu counter runs out (i.e. a local
- * ENOSPC), then we disable the counters to synchronise all callers and
- * re-distribute the available resources.
- *
- * If, once we redistributed the available resources, we still get a failure,
- * we disable the per-cpu counter and go through the slow path.
- *
- * The slow path is the current xfs_mod_incore_sb() function.  This means that
- * when we disable a per-cpu counter, we need to drain its resources back to
- * the global superblock. We do this after disabling the counter to prevent
- * more threads from queueing up on the counter.
- *
- * Essentially, this means that we still need a lock in the fast path to enable
- * synchronisation between the global counters and the per-cpu counters. This
- * is not a problem because the lock will be local to a CPU almost all the time
- * and have little contention except when we get to ENOSPC conditions.
- *
- * Basically, this lock becomes a barrier that enables us to lock out the fast
- * path while we do things like enabling and disabling counters and
- * synchronising the counters.
- *
- * Locking rules:
- *
- * 	1. m_sb_lock before picking up per-cpu locks
- * 	2. per-cpu locks always picked up via for_each_online_cpu() order
- * 	3. accurate counter sync requires m_sb_lock + per cpu locks
- * 	4. modifying per-cpu counters requires holding per-cpu lock
- * 	5. modifying global counters requires holding m_sb_lock
- *	6. enabling or disabling a counter requires holding the m_sb_lock 
- *	   and _none_ of the per-cpu locks.
- *
- * Disabled counters are only ever re-enabled by a balance operation
- * that results in more free resources per CPU than a given threshold.
- * To ensure counters don't remain disabled, they are rebalanced when
- * the global resource goes above a higher threshold (i.e. some hysteresis
- * is present to prevent thrashing).
- */
-
-#ifdef CONFIG_HOTPLUG_CPU
-/*
- * hot-plug CPU notifier support.
- *
- * We need a notifier per filesystem as we need to be able to identify
- * the filesystem to balance the counters out. This is achieved by
- * having a notifier block embedded in the xfs_mount_t and doing pointer
- * magic to get the mount pointer from the notifier block address.
- */
-STATIC int
-xfs_icsb_cpu_notify(
-	struct notifier_block *nfb,
-	unsigned long action,
-	void *hcpu)
-{
-	xfs_icsb_cnts_t *cntp;
-	xfs_mount_t	*mp;
-
-	mp = (xfs_mount_t *)container_of(nfb, xfs_mount_t, m_icsb_notifier);
-	cntp = (xfs_icsb_cnts_t *)
-			per_cpu_ptr(mp->m_sb_cnts, (unsigned long)hcpu);
-	switch (action) {
-	case CPU_UP_PREPARE:
-	case CPU_UP_PREPARE_FROZEN:
-		/* Easy Case - initialize the area and locks, and
-		 * then rebalance when online does everything else for us. */
-		memset(cntp, 0, sizeof(xfs_icsb_cnts_t));
-		break;
-	case CPU_ONLINE:
-	case CPU_ONLINE_FROZEN:
-		xfs_icsb_lock(mp);
-		xfs_icsb_balance_counter(mp, XFS_SBS_ICOUNT, 0);
-		xfs_icsb_balance_counter(mp, XFS_SBS_IFREE, 0);
-		xfs_icsb_balance_counter(mp, XFS_SBS_FDBLOCKS, 0);
-		xfs_icsb_unlock(mp);
-		break;
-	case CPU_DEAD:
-	case CPU_DEAD_FROZEN:
-		/* Disable all the counters, then fold the dead cpu's
-		 * count into the total on the global superblock and
-		 * re-enable the counters. */
-		xfs_icsb_lock(mp);
-		spin_lock(&mp->m_sb_lock);
-		xfs_icsb_disable_counter(mp, XFS_SBS_ICOUNT);
-		xfs_icsb_disable_counter(mp, XFS_SBS_IFREE);
-		xfs_icsb_disable_counter(mp, XFS_SBS_FDBLOCKS);
-
-		mp->m_sb.sb_icount += cntp->icsb_icount;
-		mp->m_sb.sb_ifree += cntp->icsb_ifree;
-		mp->m_sb.sb_fdblocks += cntp->icsb_fdblocks;
-
-		memset(cntp, 0, sizeof(xfs_icsb_cnts_t));
-
-		xfs_icsb_balance_counter_locked(mp, XFS_SBS_ICOUNT, 0);
-		xfs_icsb_balance_counter_locked(mp, XFS_SBS_IFREE, 0);
-		xfs_icsb_balance_counter_locked(mp, XFS_SBS_FDBLOCKS, 0);
-		spin_unlock(&mp->m_sb_lock);
-		xfs_icsb_unlock(mp);
-		break;
-	}
-
-	return NOTIFY_OK;
-}
-#endif /* CONFIG_HOTPLUG_CPU */
-
-int
-xfs_icsb_init_counters(
-	xfs_mount_t	*mp)
-{
-	xfs_icsb_cnts_t *cntp;
-	int		i;
-
-	mp->m_sb_cnts = alloc_percpu(xfs_icsb_cnts_t);
-	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));
-	}
-
-	mutex_init(&mp->m_icsb_mutex);
-
-	/*
-	 * start with all counters disabled so that the
-	 * initial balance kicks us off correctly
-	 */
-	mp->m_icsb_counters = -1;
-	return 0;
-}
-
-void
-xfs_icsb_reinit_counters(
-	xfs_mount_t	*mp)
-{
-	xfs_icsb_lock(mp);
-	/*
-	 * start with all counters disabled so that the
-	 * initial balance kicks us off correctly
-	 */
-	mp->m_icsb_counters = -1;
-	xfs_icsb_balance_counter(mp, XFS_SBS_ICOUNT, 0);
-	xfs_icsb_balance_counter(mp, XFS_SBS_IFREE, 0);
-	xfs_icsb_balance_counter(mp, XFS_SBS_FDBLOCKS, 0);
-	xfs_icsb_unlock(mp);
-}
-
-void
-xfs_icsb_destroy_counters(
-	xfs_mount_t	*mp)
-{
-	if (mp->m_sb_cnts) {
-		unregister_hotcpu_notifier(&mp->m_icsb_notifier);
-		free_percpu(mp->m_sb_cnts);
-	}
-	mutex_destroy(&mp->m_icsb_mutex);
-}
-
-STATIC void
-xfs_icsb_lock_cntr(
-	xfs_icsb_cnts_t	*icsbp)
-{
-	while (test_and_set_bit(XFS_ICSB_FLAG_LOCK, &icsbp->icsb_flags)) {
-		ndelay(1000);
-	}
-}
-
-STATIC void
-xfs_icsb_unlock_cntr(
-	xfs_icsb_cnts_t	*icsbp)
-{
-	clear_bit(XFS_ICSB_FLAG_LOCK, &icsbp->icsb_flags);
-}
-
-
-STATIC void
-xfs_icsb_lock_all_counters(
-	xfs_mount_t	*mp)
-{
-	xfs_icsb_cnts_t *cntp;
-	int		i;
-
-	for_each_online_cpu(i) {
-		cntp = (xfs_icsb_cnts_t *)per_cpu_ptr(mp->m_sb_cnts, i);
-		xfs_icsb_lock_cntr(cntp);
+		return -EROFS;
 	}
-}
-
-STATIC void
-xfs_icsb_unlock_all_counters(
-	xfs_mount_t	*mp)
-{
-	xfs_icsb_cnts_t *cntp;
-	int		i;
-
-	for_each_online_cpu(i) {
-		cntp = (xfs_icsb_cnts_t *)per_cpu_ptr(mp->m_sb_cnts, i);
-		xfs_icsb_unlock_cntr(cntp);
-	}
-}
-
-STATIC void
-xfs_icsb_count(
-	xfs_mount_t	*mp,
-	xfs_icsb_cnts_t	*cnt,
-	int		flags)
-{
-	xfs_icsb_cnts_t *cntp;
-	int		i;
-
-	memset(cnt, 0, sizeof(xfs_icsb_cnts_t));
-
-	if (!(flags & XFS_ICSB_LAZY_COUNT))
-		xfs_icsb_lock_all_counters(mp);
-
-	for_each_online_cpu(i) {
-		cntp = (xfs_icsb_cnts_t *)per_cpu_ptr(mp->m_sb_cnts, i);
-		cnt->icsb_icount += cntp->icsb_icount;
-		cnt->icsb_ifree += cntp->icsb_ifree;
-		cnt->icsb_fdblocks += cntp->icsb_fdblocks;
-	}
-
-	if (!(flags & XFS_ICSB_LAZY_COUNT))
-		xfs_icsb_unlock_all_counters(mp);
-}
-
-STATIC int
-xfs_icsb_counter_disabled(
-	xfs_mount_t	*mp,
-	xfs_sb_field_t	field)
-{
-	ASSERT((field >= XFS_SBS_ICOUNT) && (field <= XFS_SBS_FDBLOCKS));
-	return test_bit(field, &mp->m_icsb_counters);
-}
-
-STATIC void
-xfs_icsb_disable_counter(
-	xfs_mount_t	*mp,
-	xfs_sb_field_t	field)
-{
-	xfs_icsb_cnts_t	cnt;
-
-	ASSERT((field >= XFS_SBS_ICOUNT) && (field <= XFS_SBS_FDBLOCKS));
-
-	/*
-	 * If we are already disabled, then there is nothing to do
-	 * here. We check before locking all the counters to avoid
-	 * the expensive lock operation when being called in the
-	 * slow path and the counter is already disabled. This is
-	 * safe because the only time we set or clear this state is under
-	 * the m_icsb_mutex.
-	 */
-	if (xfs_icsb_counter_disabled(mp, field))
-		return;
-
-	xfs_icsb_lock_all_counters(mp);
-	if (!test_and_set_bit(field, &mp->m_icsb_counters)) {
-		/* drain back to superblock */
-
-		xfs_icsb_count(mp, &cnt, XFS_ICSB_LAZY_COUNT);
-		switch(field) {
-		case XFS_SBS_ICOUNT:
-			mp->m_sb.sb_icount = cnt.icsb_icount;
-			break;
-		case XFS_SBS_IFREE:
-			mp->m_sb.sb_ifree = cnt.icsb_ifree;
-			break;
-		case XFS_SBS_FDBLOCKS:
-			mp->m_sb.sb_fdblocks = cnt.icsb_fdblocks;
-			break;
-		default:
-			BUG();
-		}
-	}
-
-	xfs_icsb_unlock_all_counters(mp);
-}
-
-STATIC void
-xfs_icsb_enable_counter(
-	xfs_mount_t	*mp,
-	xfs_sb_field_t	field,
-	uint64_t	count,
-	uint64_t	resid)
-{
-	xfs_icsb_cnts_t	*cntp;
-	int		i;
-
-	ASSERT((field >= XFS_SBS_ICOUNT) && (field <= XFS_SBS_FDBLOCKS));
-
-	xfs_icsb_lock_all_counters(mp);
-	for_each_online_cpu(i) {
-		cntp = per_cpu_ptr(mp->m_sb_cnts, i);
-		switch (field) {
-		case XFS_SBS_ICOUNT:
-			cntp->icsb_icount = count + resid;
-			break;
-		case XFS_SBS_IFREE:
-			cntp->icsb_ifree = count + resid;
-			break;
-		case XFS_SBS_FDBLOCKS:
-			cntp->icsb_fdblocks = count + resid;
-			break;
-		default:
-			BUG();
-			break;
-		}
-		resid = 0;
-	}
-	clear_bit(field, &mp->m_icsb_counters);
-	xfs_icsb_unlock_all_counters(mp);
-}
-
-void
-xfs_icsb_sync_counters_locked(
-	xfs_mount_t	*mp,
-	int		flags)
-{
-	xfs_icsb_cnts_t	cnt;
-
-	xfs_icsb_count(mp, &cnt, flags);
-
-	if (!xfs_icsb_counter_disabled(mp, XFS_SBS_ICOUNT))
-		mp->m_sb.sb_icount = cnt.icsb_icount;
-	if (!xfs_icsb_counter_disabled(mp, XFS_SBS_IFREE))
-		mp->m_sb.sb_ifree = cnt.icsb_ifree;
-	if (!xfs_icsb_counter_disabled(mp, XFS_SBS_FDBLOCKS))
-		mp->m_sb.sb_fdblocks = cnt.icsb_fdblocks;
-}
-
-/*
- * Accurate update of per-cpu counters to incore superblock
- */
-void
-xfs_icsb_sync_counters(
-	xfs_mount_t	*mp,
-	int		flags)
-{
-	spin_lock(&mp->m_sb_lock);
-	xfs_icsb_sync_counters_locked(mp, flags);
-	spin_unlock(&mp->m_sb_lock);
-}
-
-/*
- * Balance and enable/disable counters as necessary.
- *
- * Thresholds for re-enabling counters are somewhat magic.  inode counts are
- * chosen to be the same number as single on disk allocation chunk per CPU, and
- * free blocks is something far enough zero that we aren't going thrash when we
- * get near ENOSPC. We also need to supply a minimum we require per cpu to
- * prevent looping endlessly when xfs_alloc_space asks for more than will
- * be distributed to a single CPU but each CPU has enough blocks to be
- * reenabled.
- *
- * Note that we can be called when counters are already disabled.
- * xfs_icsb_disable_counter() optimises the counter locking in this case to
- * prevent locking every per-cpu counter needlessly.
- */
-
-#define XFS_ICSB_INO_CNTR_REENABLE	(uint64_t)64
-#define XFS_ICSB_FDBLK_CNTR_REENABLE(mp) \
-		(uint64_t)(512 + XFS_ALLOC_SET_ASIDE(mp))
-STATIC void
-xfs_icsb_balance_counter_locked(
-	xfs_mount_t	*mp,
-	xfs_sb_field_t  field,
-	int		min_per_cpu)
-{
-	uint64_t	count, resid;
-	int		weight = num_online_cpus();
-	uint64_t	min = (uint64_t)min_per_cpu;
-
-	/* disable counter and sync counter */
-	xfs_icsb_disable_counter(mp, field);
-
-	/* update counters  - first CPU gets residual*/
-	switch (field) {
-	case XFS_SBS_ICOUNT:
-		count = mp->m_sb.sb_icount;
-		resid = do_div(count, weight);
-		if (count < max(min, XFS_ICSB_INO_CNTR_REENABLE))
-			return;
-		break;
-	case XFS_SBS_IFREE:
-		count = mp->m_sb.sb_ifree;
-		resid = do_div(count, weight);
-		if (count < max(min, XFS_ICSB_INO_CNTR_REENABLE))
-			return;
-		break;
-	case XFS_SBS_FDBLOCKS:
-		count = mp->m_sb.sb_fdblocks;
-		resid = do_div(count, weight);
-		if (count < max(min, XFS_ICSB_FDBLK_CNTR_REENABLE(mp)))
-			return;
-		break;
-	default:
-		BUG();
-		count = resid = 0;	/* quiet, gcc */
-		break;
-	}
-
-	xfs_icsb_enable_counter(mp, field, count, resid);
-}
-
-STATIC void
-xfs_icsb_balance_counter(
-	xfs_mount_t	*mp,
-	xfs_sb_field_t  fields,
-	int		min_per_cpu)
-{
-	spin_lock(&mp->m_sb_lock);
-	xfs_icsb_balance_counter_locked(mp, fields, min_per_cpu);
-	spin_unlock(&mp->m_sb_lock);
-}
-
-int
-xfs_icsb_modify_counters(
-	xfs_mount_t	*mp,
-	xfs_sb_field_t	field,
-	int64_t		delta,
-	int		rsvd)
-{
-	xfs_icsb_cnts_t	*icsbp;
-	long long	lcounter;	/* long counter for 64 bit fields */
-	int		ret = 0;
-
-	might_sleep();
-again:
-	preempt_disable();
-	icsbp = this_cpu_ptr(mp->m_sb_cnts);
-
-	/*
-	 * if the counter is disabled, go to slow path
-	 */
-	if (unlikely(xfs_icsb_counter_disabled(mp, field)))
-		goto slow_path;
-	xfs_icsb_lock_cntr(icsbp);
-	if (unlikely(xfs_icsb_counter_disabled(mp, field))) {
-		xfs_icsb_unlock_cntr(icsbp);
-		goto slow_path;
-	}
-
-	switch (field) {
-	case XFS_SBS_ICOUNT:
-		lcounter = icsbp->icsb_icount;
-		lcounter += delta;
-		if (unlikely(lcounter < 0))
-			goto balance_counter;
-		icsbp->icsb_icount = lcounter;
-		break;
-
-	case XFS_SBS_IFREE:
-		lcounter = icsbp->icsb_ifree;
-		lcounter += delta;
-		if (unlikely(lcounter < 0))
-			goto balance_counter;
-		icsbp->icsb_ifree = lcounter;
-		break;
-
-	case XFS_SBS_FDBLOCKS:
-		BUG_ON((mp->m_resblks - mp->m_resblks_avail) != 0);
-
-		lcounter = icsbp->icsb_fdblocks - XFS_ALLOC_SET_ASIDE(mp);
-		lcounter += delta;
-		if (unlikely(lcounter < 0))
-			goto balance_counter;
-		icsbp->icsb_fdblocks = lcounter + XFS_ALLOC_SET_ASIDE(mp);
-		break;
-	default:
-		BUG();
-		break;
-	}
-	xfs_icsb_unlock_cntr(icsbp);
-	preempt_enable();
 	return 0;
-
-slow_path:
-	preempt_enable();
-
-	/*
-	 * serialise with a mutex so we don't burn lots of cpu on
-	 * the superblock lock. We still need to hold the superblock
-	 * lock, however, when we modify the global structures.
-	 */
-	xfs_icsb_lock(mp);
-
-	/*
-	 * Now running atomically.
-	 *
-	 * If the counter is enabled, someone has beaten us to rebalancing.
-	 * Drop the lock and try again in the fast path....
-	 */
-	if (!(xfs_icsb_counter_disabled(mp, field))) {
-		xfs_icsb_unlock(mp);
-		goto again;
-	}
-
-	/*
-	 * The counter is currently disabled. Because we are
-	 * running atomically here, we know a rebalance cannot
-	 * be in progress. Hence we can go straight to operating
-	 * on the global superblock. We do not call xfs_mod_incore_sb()
-	 * here even though we need to get the m_sb_lock. Doing so
-	 * will cause us to re-enter this function and deadlock.
-	 * Hence we get the m_sb_lock ourselves and then call
-	 * xfs_mod_incore_sb_unlocked() as the unlocked path operates
-	 * directly on the global counters.
-	 */
-	spin_lock(&mp->m_sb_lock);
-	ret = xfs_mod_incore_sb_unlocked(mp, field, delta, rsvd);
-	spin_unlock(&mp->m_sb_lock);
-
-	/*
-	 * Now that we've modified the global superblock, we
-	 * may be able to re-enable the distributed counters
-	 * (e.g. lots of space just got freed). After that
-	 * we are done.
-	 */
-	if (ret != ENOSPC)
-		xfs_icsb_balance_counter(mp, field, 0);
-	xfs_icsb_unlock(mp);
-	return ret;
-
-balance_counter:
-	xfs_icsb_unlock_cntr(icsbp);
-	preempt_enable();
-
-	/*
-	 * We may have multiple threads here if multiple per-cpu
-	 * counters run dry at the same time. This will mean we can
-	 * do more balances than strictly necessary but it is not
-	 * the common slowpath case.
-	 */
-	xfs_icsb_lock(mp);
-
-	/*
-	 * running atomically.
-	 *
-	 * This will leave the counter in the correct state for future
-	 * accesses. After the rebalance, we simply try again and our retry
-	 * will either succeed through the fast path or slow path without
-	 * another balance operation being required.
-	 */
-	xfs_icsb_balance_counter(mp, field, delta);
-	xfs_icsb_unlock(mp);
-	goto again;
 }
-
-#endif