Merge branch 'xfs-misc-fixes-3.17-2' into for-next

16 files changed, 175 insertions, 161 deletions

diff --git a/fs/xfs/libxfs/xfs_sb.c b/fs/xfs/libxfs/xfs_sb.c
index 6e93b5ef0a6b..ad525a5623a4 100644
--- a/fs/xfs/libxfs/xfs_sb.c
+++ b/fs/xfs/libxfs/xfs_sb.c
@@ -386,10 +386,11 @@ xfs_sb_quota_from_disk(struct xfs_sb *sbp)
 	}
 }
 
-void
-xfs_sb_from_disk(
+static void
+__xfs_sb_from_disk(
 	struct xfs_sb	*to,
-	xfs_dsb_t	*from)
+	xfs_dsb_t	*from,
+	bool		convert_xquota)
 {
 	to->sb_magicnum = be32_to_cpu(from->sb_magicnum);
 	to->sb_blocksize = be32_to_cpu(from->sb_blocksize);
@@ -445,6 +446,17 @@ xfs_sb_from_disk(
 	to->sb_pad = 0;
 	to->sb_pquotino = be64_to_cpu(from->sb_pquotino);
 	to->sb_lsn = be64_to_cpu(from->sb_lsn);
+	/* Convert on-disk flags to in-memory flags? */
+	if (convert_xquota)
+		xfs_sb_quota_from_disk(to);
+}
+
+void
+xfs_sb_from_disk(
+	struct xfs_sb	*to,
+	xfs_dsb_t	*from)
+{
+	__xfs_sb_from_disk(to, from, true);
 }
 
 static inline void
@@ -577,7 +589,11 @@ xfs_sb_verify(
 	struct xfs_mount *mp = bp->b_target->bt_mount;
 	struct xfs_sb	sb;
 
-	xfs_sb_from_disk(&sb, XFS_BUF_TO_SBP(bp));
+	/*
+	 * Use call variant which doesn't convert quota flags from disk 
+	 * format, because xfs_mount_validate_sb checks the on-disk flags.
+	 */
+	__xfs_sb_from_disk(&sb, XFS_BUF_TO_SBP(bp), false);
 
 	/*
 	 * Only check the in progress field for the primary superblock as
diff --git a/fs/xfs/xfs_bmap_util.c b/fs/xfs/xfs_bmap_util.c
index d32889af1777..2f1e30d39a35 100644
--- a/fs/xfs/xfs_bmap_util.c
+++ b/fs/xfs/xfs_bmap_util.c
@@ -809,7 +809,7 @@ xfs_can_free_eofblocks(struct xfs_inode *ip, bool force)
 	 * have speculative prealloc/delalloc blocks to remove.
 	 */
 	if (VFS_I(ip)->i_size == 0 &&
-	    VN_CACHED(VFS_I(ip)) == 0 &&
+	    VFS_I(ip)->i_mapping->nrpages == 0 &&
 	    ip->i_delayed_blks == 0)
 		return false;
 
@@ -1619,6 +1619,30 @@ xfs_swap_extents_check_format(
 }
 
 int
+xfs_swap_extent_flush(
+	struct xfs_inode	*ip)
+{
+	int	error;
+
+	error = filemap_write_and_wait(VFS_I(ip)->i_mapping);
+	if (error)
+		return error;
+	truncate_pagecache_range(VFS_I(ip), 0, -1);
+
+	/* Verify O_DIRECT for ftmp */
+	if (VFS_I(ip)->i_mapping->nrpages)
+		return -EINVAL;
+
+	/*
+	 * Don't try to swap extents on mmap()d files because we can't lock
+	 * out races against page faults safely.
+	 */
+	if (mapping_mapped(VFS_I(ip)->i_mapping))
+		return -EBUSY;
+	return 0;
+}
+
+int
 xfs_swap_extents(
 	xfs_inode_t	*ip,	/* target inode */
 	xfs_inode_t	*tip,	/* tmp inode */
@@ -1633,6 +1657,7 @@ xfs_swap_extents(
 	int		aforkblks = 0;
 	int		taforkblks = 0;
 	__uint64_t	tmp;
+	int		lock_flags;
 
 	tempifp = kmem_alloc(sizeof(xfs_ifork_t), KM_MAYFAIL);
 	if (!tempifp) {
@@ -1641,13 +1666,13 @@ xfs_swap_extents(
 	}
 
 	/*
-	 * we have to do two separate lock calls here to keep lockdep
-	 * happy. If we try to get all the locks in one call, lock will
-	 * report false positives when we drop the ILOCK and regain them
-	 * below.
+	 * Lock up the inodes against other IO and truncate to begin with.
+	 * Then we can ensure the inodes are flushed and have no page cache
+	 * safely. Once we have done this we can take the ilocks and do the rest
+	 * of the checks.
 	 */
+	lock_flags = XFS_IOLOCK_EXCL;
 	xfs_lock_two_inodes(ip, tip, XFS_IOLOCK_EXCL);
-	xfs_lock_two_inodes(ip, tip, XFS_ILOCK_EXCL);
 
 	/* Verify that both files have the same format */
 	if ((ip->i_d.di_mode & S_IFMT) != (tip->i_d.di_mode & S_IFMT)) {
@@ -1661,23 +1686,28 @@ xfs_swap_extents(
 		goto out_unlock;
 	}
 
-	error = filemap_write_and_wait(VFS_I(tip)->i_mapping);
+	error = xfs_swap_extent_flush(ip);
+	if (error)
+		goto out_unlock;
+	error = xfs_swap_extent_flush(tip);
 	if (error)
 		goto out_unlock;
-	truncate_pagecache_range(VFS_I(tip), 0, -1);
 
-	/* Verify O_DIRECT for ftmp */
-	if (VN_CACHED(VFS_I(tip)) != 0) {
-		error = -EINVAL;
+	tp = xfs_trans_alloc(mp, XFS_TRANS_SWAPEXT);
+	error = xfs_trans_reserve(tp, &M_RES(mp)->tr_ichange, 0, 0);
+	if (error) {
+		xfs_trans_cancel(tp, 0);
 		goto out_unlock;
 	}
+	xfs_lock_two_inodes(ip, tip, XFS_ILOCK_EXCL);
+	lock_flags |= XFS_ILOCK_EXCL;
 
 	/* Verify all data are being swapped */
 	if (sxp->sx_offset != 0 ||
 	    sxp->sx_length != ip->i_d.di_size ||
 	    sxp->sx_length != tip->i_d.di_size) {
 		error = -EFAULT;
-		goto out_unlock;
+		goto out_trans_cancel;
 	}
 
 	trace_xfs_swap_extent_before(ip, 0);
@@ -1689,7 +1719,7 @@ xfs_swap_extents(
 		xfs_notice(mp,
 		    "%s: inode 0x%llx format is incompatible for exchanging.",
 				__func__, ip->i_ino);
-		goto out_unlock;
+		goto out_trans_cancel;
 	}
 
 	/*
@@ -1704,42 +1734,8 @@ xfs_swap_extents(
 	    (sbp->bs_mtime.tv_sec != VFS_I(ip)->i_mtime.tv_sec) ||
 	    (sbp->bs_mtime.tv_nsec != VFS_I(ip)->i_mtime.tv_nsec)) {
 		error = -EBUSY;
-		goto out_unlock;
-	}
-
-	/* We need to fail if the file is memory mapped.  Once we have tossed
-	 * all existing pages, the page fault will have no option
-	 * but to go to the filesystem for pages. By making the page fault call
-	 * vop_read (or write in the case of autogrow) they block on the iolock
-	 * until we have switched the extents.
-	 */
-	if (VN_MAPPED(VFS_I(ip))) {
-		error = -EBUSY;
-		goto out_unlock;
-	}
-
-	xfs_iunlock(ip, XFS_ILOCK_EXCL);
-	xfs_iunlock(tip, XFS_ILOCK_EXCL);
-
-	/*
-	 * There is a race condition here since we gave up the
-	 * ilock.  However, the data fork will not change since
-	 * we have the iolock (locked for truncation too) so we
-	 * are safe.  We don't really care if non-io related
-	 * fields change.
-	 */
-	truncate_pagecache_range(VFS_I(ip), 0, -1);
-
-	tp = xfs_trans_alloc(mp, XFS_TRANS_SWAPEXT);
-	error = xfs_trans_reserve(tp, &M_RES(mp)->tr_ichange, 0, 0);
-	if (error) {
-		xfs_iunlock(ip,  XFS_IOLOCK_EXCL);
-		xfs_iunlock(tip, XFS_IOLOCK_EXCL);
-		xfs_trans_cancel(tp, 0);
-		goto out;
+		goto out_trans_cancel;
 	}
-	xfs_lock_two_inodes(ip, tip, XFS_ILOCK_EXCL);
-
 	/*
 	 * Count the number of extended attribute blocks
 	 */
@@ -1757,8 +1753,8 @@ xfs_swap_extents(
 			goto out_trans_cancel;
 	}
 
-	xfs_trans_ijoin(tp, ip, XFS_ILOCK_EXCL | XFS_IOLOCK_EXCL);
-	xfs_trans_ijoin(tp, tip, XFS_ILOCK_EXCL | XFS_IOLOCK_EXCL);
+	xfs_trans_ijoin(tp, ip, lock_flags);
+	xfs_trans_ijoin(tp, tip, lock_flags);
 
 	/*
 	 * Before we've swapped the forks, lets set the owners of the forks
@@ -1887,8 +1883,8 @@ out:
 	return error;
 
 out_unlock:
-	xfs_iunlock(ip,  XFS_ILOCK_EXCL | XFS_IOLOCK_EXCL);
-	xfs_iunlock(tip, XFS_ILOCK_EXCL | XFS_IOLOCK_EXCL);
+	xfs_iunlock(ip, lock_flags);
+	xfs_iunlock(tip, lock_flags);
 	goto out;
 
 out_trans_cancel:
diff --git a/fs/xfs/xfs_buf.c b/fs/xfs/xfs_buf.c
index a6dc83e70ece..cd7b8ca9b064 100644
--- a/fs/xfs/xfs_buf.c
+++ b/fs/xfs/xfs_buf.c
@@ -1330,6 +1330,20 @@ _xfs_buf_ioapply(
 						   SHUTDOWN_CORRUPT_INCORE);
 				return;
 			}
+		} else if (bp->b_bn != XFS_BUF_DADDR_NULL) {
+			struct xfs_mount *mp = bp->b_target->bt_mount;
+
+			/*
+			 * non-crc filesystems don't attach verifiers during
+			 * log recovery, so don't warn for such filesystems.
+			 */
+			if (xfs_sb_version_hascrc(&mp->m_sb)) {
+				xfs_warn(mp,
+					"%s: no ops on block 0x%llx/0x%x",
+					__func__, bp->b_bn, bp->b_length);
+				xfs_hex_dump(bp->b_addr, 64);
+				dump_stack();
+			}
 		}
 	} else if (bp->b_flags & XBF_READ_AHEAD) {
 		rw = READA;
diff --git a/fs/xfs/xfs_dquot.c b/fs/xfs/xfs_dquot.c
index 8a44a79f49af..63c2de49f61d 100644
--- a/fs/xfs/xfs_dquot.c
+++ b/fs/xfs/xfs_dquot.c
@@ -974,7 +974,8 @@ xfs_qm_dqflush(
 	 * Get the buffer containing the on-disk dquot
 	 */
 	error = xfs_trans_read_buf(mp, NULL, mp->m_ddev_targp, dqp->q_blkno,
-				   mp->m_quotainfo->qi_dqchunklen, 0, &bp, NULL);
+				   mp->m_quotainfo->qi_dqchunklen, 0, &bp,
+				   &xfs_dquot_buf_ops);
 	if (error)
 		goto out_unlock;
 
diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c
index fcf91a22f5d8..076b1708d134 100644
--- a/fs/xfs/xfs_file.c
+++ b/fs/xfs/xfs_file.c
@@ -247,11 +247,11 @@ xfs_file_read_iter(
 	XFS_STATS_INC(xs_read_calls);
 
 	if (unlikely(file->f_flags & O_DIRECT))
-		ioflags |= IO_ISDIRECT;
+		ioflags |= XFS_IO_ISDIRECT;
 	if (file->f_mode & FMODE_NOCMTIME)
-		ioflags |= IO_INVIS;
+		ioflags |= XFS_IO_INVIS;
 
-	if (unlikely(ioflags & IO_ISDIRECT)) {
+	if (unlikely(ioflags & XFS_IO_ISDIRECT)) {
 		xfs_buftarg_t	*target =
 			XFS_IS_REALTIME_INODE(ip) ?
 				mp->m_rtdev_targp : mp->m_ddev_targp;
@@ -284,7 +284,7 @@ xfs_file_read_iter(
 	 * proceeed concurrently without serialisation.
 	 */
 	xfs_rw_ilock(ip, XFS_IOLOCK_SHARED);
-	if ((ioflags & IO_ISDIRECT) && inode->i_mapping->nrpages) {
+	if ((ioflags & XFS_IO_ISDIRECT) && inode->i_mapping->nrpages) {
 		xfs_rw_iunlock(ip, XFS_IOLOCK_SHARED);
 		xfs_rw_ilock(ip, XFS_IOLOCK_EXCL);
 
@@ -326,7 +326,7 @@ xfs_file_splice_read(
 	XFS_STATS_INC(xs_read_calls);
 
 	if (infilp->f_mode & FMODE_NOCMTIME)
-		ioflags |= IO_INVIS;
+		ioflags |= XFS_IO_INVIS;
 
 	if (XFS_FORCED_SHUTDOWN(ip->i_mount))
 		return -EIO;
diff --git a/fs/xfs/xfs_inode.c b/fs/xfs/xfs_inode.c
index 1a5e068bc420..fea3c92fb3f0 100644
--- a/fs/xfs/xfs_inode.c
+++ b/fs/xfs/xfs_inode.c
@@ -1635,7 +1635,7 @@ xfs_release(
 		truncated = xfs_iflags_test_and_clear(ip, XFS_ITRUNCATED);
 		if (truncated) {
 			xfs_iflags_clear(ip, XFS_IDIRTY_RELEASE);
-			if (VN_DIRTY(VFS_I(ip)) && ip->i_delayed_blks > 0) {
+			if (ip->i_delayed_blks > 0) {
 				error = filemap_flush(VFS_I(ip)->i_mapping);
 				if (error)
 					return error;
diff --git a/fs/xfs/xfs_inode.h b/fs/xfs/xfs_inode.h
index f72bffa67266..c10e3fadd9af 100644
--- a/fs/xfs/xfs_inode.h
+++ b/fs/xfs/xfs_inode.h
@@ -398,4 +398,14 @@ do { \
 
 extern struct kmem_zone	*xfs_inode_zone;
 
+/*
+ * Flags for read/write calls
+ */
+#define XFS_IO_ISDIRECT	0x00001		/* bypass page cache */
+#define XFS_IO_INVIS	0x00002		/* don't update inode timestamps */
+
+#define XFS_IO_FLAGS \
+	{ XFS_IO_ISDIRECT,	"DIRECT" }, \
+	{ XFS_IO_INVIS,		"INVIS"}
+
 #endif	/* __XFS_INODE_H__ */
diff --git a/fs/xfs/xfs_ioctl.c b/fs/xfs/xfs_ioctl.c
index 494237ed4a65..3799695b9249 100644
--- a/fs/xfs/xfs_ioctl.c
+++ b/fs/xfs/xfs_ioctl.c
@@ -736,7 +736,7 @@ xfs_ioc_space(
 	xfs_ilock(ip, XFS_ILOCK_EXCL);
 	xfs_trans_ijoin(tp, ip, XFS_ILOCK_EXCL);
 
-	if (!(ioflags & IO_INVIS)) {
+	if (!(ioflags & XFS_IO_INVIS)) {
 		ip->i_d.di_mode &= ~S_ISUID;
 		if (ip->i_d.di_mode & S_IXGRP)
 			ip->i_d.di_mode &= ~S_ISGID;
@@ -1376,7 +1376,7 @@ xfs_ioc_getbmap(
 		return -EINVAL;
 
 	bmx.bmv_iflags = (cmd == XFS_IOC_GETBMAPA ? BMV_IF_ATTRFORK : 0);
-	if (ioflags & IO_INVIS)
+	if (ioflags & XFS_IO_INVIS)
 		bmx.bmv_iflags |= BMV_IF_NO_DMAPI_READ;
 
 	error = xfs_getbmap(ip, &bmx, xfs_getbmap_format,
@@ -1520,7 +1520,7 @@ xfs_file_ioctl(
 	int			error;
 
 	if (filp->f_mode & FMODE_NOCMTIME)
-		ioflags |= IO_INVIS;
+		ioflags |= XFS_IO_INVIS;
 
 	trace_xfs_file_ioctl(ip);
 
diff --git a/fs/xfs/xfs_ioctl32.c b/fs/xfs/xfs_ioctl32.c
index cf63418bf05f..a554646ff141 100644
--- a/fs/xfs/xfs_ioctl32.c
+++ b/fs/xfs/xfs_ioctl32.c
@@ -28,7 +28,6 @@
 #include "xfs_sb.h"
 #include "xfs_ag.h"
 #include "xfs_mount.h"
-#include "xfs_vnode.h"
 #include "xfs_inode.h"
 #include "xfs_itable.h"
 #include "xfs_error.h"
@@ -537,7 +536,7 @@ xfs_file_compat_ioctl(
 	int			error;
 
 	if (filp->f_mode & FMODE_NOCMTIME)
-		ioflags |= IO_INVIS;
+		ioflags |= XFS_IO_INVIS;
 
 	trace_xfs_file_compat_ioctl(ip);
 
diff --git a/fs/xfs/xfs_iops.c b/fs/xfs/xfs_iops.c
index d75621ae3e36..72129493e9d3 100644
--- a/fs/xfs/xfs_iops.c
+++ b/fs/xfs/xfs_iops.c
@@ -1055,12 +1055,12 @@ xfs_vn_fiemap(
 		return error;
 
 	/* Set up bmap header for xfs internal routine */
-	bm.bmv_offset = BTOBB(start);
+	bm.bmv_offset = BTOBBT(start);
 	/* Special case for whole file */
 	if (length == FIEMAP_MAX_OFFSET)
 		bm.bmv_length = -1LL;
 	else
-		bm.bmv_length = BTOBB(length);
+		bm.bmv_length = BTOBB(start + length) - bm.bmv_offset;
 
 	/* We add one because in getbmap world count includes the header */
 	bm.bmv_count = !fieinfo->fi_extents_max ? MAXEXTNUM :
diff --git a/fs/xfs/xfs_linux.h b/fs/xfs/xfs_linux.h
index d3ef6de475bb..d10dc8f397c9 100644
--- a/fs/xfs/xfs_linux.h
+++ b/fs/xfs/xfs_linux.h
@@ -101,7 +101,7 @@ typedef __uint64_t __psunsigned_t;
 #include <asm/byteorder.h>
 #include <asm/unaligned.h>
 
-#include "xfs_vnode.h"
+#include "xfs_fs.h"
 #include "xfs_stats.h"
 #include "xfs_sysctl.h"
 #include "xfs_iops.h"
diff --git a/fs/xfs/xfs_log.c b/fs/xfs/xfs_log.c
index 149a4a575a09..ca4fd5bd8522 100644
--- a/fs/xfs/xfs_log.c
+++ b/fs/xfs/xfs_log.c
@@ -1378,8 +1378,14 @@ xlog_alloc_log(
 
 	xlog_get_iclog_buffer_size(mp, log);
 
+	/*
+	 * Use a NULL block for the extra log buffer used during splits so that
+	 * it will trigger errors if we ever try to do IO on it without first
+	 * having set it up properly.
+	 */
 	error = -ENOMEM;
-	bp = xfs_buf_alloc(mp->m_logdev_targp, 0, BTOBB(log->l_iclog_size), 0);
+	bp = xfs_buf_alloc(mp->m_logdev_targp, XFS_BUF_DADDR_NULL,
+			   BTOBB(log->l_iclog_size), 0);
 	if (!bp)
 		goto out_free_log;
 
diff --git a/fs/xfs/xfs_log_recover.c b/fs/xfs/xfs_log_recover.c
index fbc2362d13e3..1fd5787add99 100644
--- a/fs/xfs/xfs_log_recover.c
+++ b/fs/xfs/xfs_log_recover.c
@@ -2126,6 +2126,17 @@ xlog_recover_validate_buf_type(
 	__uint16_t		magic16;
 	__uint16_t		magicda;
 
+	/*
+	 * We can only do post recovery validation on items on CRC enabled
+	 * fielsystems as we need to know when the buffer was written to be able
+	 * to determine if we should have replayed the item. If we replay old
+	 * metadata over a newer buffer, then it will enter a temporarily
+	 * inconsistent state resulting in verification failures. Hence for now
+	 * just avoid the verification stage for non-crc filesystems
+	 */
+	if (!xfs_sb_version_hascrc(&mp->m_sb))
+		return;
+
 	magic32 = be32_to_cpu(*(__be32 *)bp->b_addr);
 	magic16 = be16_to_cpu(*(__be16*)bp->b_addr);
 	magicda = be16_to_cpu(info->magic);
@@ -2163,8 +2174,6 @@ xlog_recover_validate_buf_type(
 		bp->b_ops = &xfs_agf_buf_ops;
 		break;
 	case XFS_BLFT_AGFL_BUF:
-		if (!xfs_sb_version_hascrc(&mp->m_sb))
-			break;
 		if (magic32 != XFS_AGFL_MAGIC) {
 			xfs_warn(mp, "Bad AGFL block magic!");
 			ASSERT(0);
@@ -2197,10 +2206,6 @@ xlog_recover_validate_buf_type(
 #endif
 		break;
 	case XFS_BLFT_DINO_BUF:
-		/*
-		 * we get here with inode allocation buffers, not buffers that
-		 * track unlinked list changes.
-		 */
 		if (magic16 != XFS_DINODE_MAGIC) {
 			xfs_warn(mp, "Bad INODE block magic!");
 			ASSERT(0);
@@ -2280,8 +2285,6 @@ xlog_recover_validate_buf_type(
 		bp->b_ops = &xfs_attr3_leaf_buf_ops;
 		break;
 	case XFS_BLFT_ATTR_RMT_BUF:
-		if (!xfs_sb_version_hascrc(&mp->m_sb))
-			break;
 		if (magic32 != XFS_ATTR3_RMT_MAGIC) {
 			xfs_warn(mp, "Bad attr remote magic!");
 			ASSERT(0);
@@ -2388,16 +2391,7 @@ xlog_recover_do_reg_buffer(
 	/* Shouldn't be any more regions */
 	ASSERT(i == item->ri_total);
 
-	/*
-	 * We can only do post recovery validation on items on CRC enabled
-	 * fielsystems as we need to know when the buffer was written to be able
-	 * to determine if we should have replayed the item. If we replay old
-	 * metadata over a newer buffer, then it will enter a temporarily
-	 * inconsistent state resulting in verification failures. Hence for now
-	 * just avoid the verification stage for non-crc filesystems
-	 */
-	if (xfs_sb_version_hascrc(&mp->m_sb))
-		xlog_recover_validate_buf_type(mp, bp, buf_f);
+	xlog_recover_validate_buf_type(mp, bp, buf_f);
 }
 
 /*
@@ -2405,8 +2399,11 @@ xlog_recover_do_reg_buffer(
  * Simple algorithm: if we have found a QUOTAOFF log item of the same type
  * (ie. USR or GRP), then just toss this buffer away; don't recover it.
  * Else, treat it as a regular buffer and do recovery.
+ *
+ * Return false if the buffer was tossed and true if we recovered the buffer to
+ * indicate to the caller if the buffer needs writing.
  */
-STATIC void
+STATIC bool
 xlog_recover_do_dquot_buffer(
 	struct xfs_mount		*mp,
 	struct xlog			*log,
@@ -2421,9 +2418,8 @@ xlog_recover_do_dquot_buffer(
 	/*
 	 * Filesystems are required to send in quota flags at mount time.
 	 */
-	if (mp->m_qflags == 0) {
-		return;
-	}
+	if (!mp->m_qflags)
+		return false;
 
 	type = 0;
 	if (buf_f->blf_flags & XFS_BLF_UDQUOT_BUF)
@@ -2436,9 +2432,10 @@ xlog_recover_do_dquot_buffer(
 	 * This type of quotas was turned off, so ignore this buffer
 	 */
 	if (log->l_quotaoffs_flag & type)
-		return;
+		return false;
 
 	xlog_recover_do_reg_buffer(mp, item, bp, buf_f);
+	return true;
 }
 
 /*
@@ -2505,23 +2502,44 @@ xlog_recover_buffer_pass2(
 	}
 
 	/*
-	 * recover the buffer only if we get an LSN from it and it's less than
+	 * Recover the buffer only if we get an LSN from it and it's less than
 	 * the lsn of the transaction we are replaying.
+	 *
+	 * Note that we have to be extremely careful of readahead here.
+	 * Readahead does not attach verfiers to the buffers so if we don't
+	 * actually do any replay after readahead because of the LSN we found
+	 * in the buffer if more recent than that current transaction then we
+	 * need to attach the verifier directly. Failure to do so can lead to
+	 * future recovery actions (e.g. EFI and unlinked list recovery) can
+	 * operate on the buffers and they won't get the verifier attached. This
+	 * can lead to blocks on disk having the correct content but a stale
+	 * CRC.
+	 *
+	 * It is safe to assume these clean buffers are currently up to date.
+	 * If the buffer is dirtied by a later transaction being replayed, then
+	 * the verifier will be reset to match whatever recover turns that
+	 * buffer into.
 	 */
 	lsn = xlog_recover_get_buf_lsn(mp, bp);
-	if (lsn && lsn != -1 && XFS_LSN_CMP(lsn, current_lsn) >= 0)
+	if (lsn && lsn != -1 && XFS_LSN_CMP(lsn, current_lsn) >= 0) {
+		xlog_recover_validate_buf_type(mp, bp, buf_f);
 		goto out_release;
+	}
 
 	if (buf_f->blf_flags & XFS_BLF_INODE_BUF) {
 		error = xlog_recover_do_inode_buffer(mp, item, bp, buf_f);
+		if (error)
+			goto out_release;
 	} else if (buf_f->blf_flags &
 		  (XFS_BLF_UDQUOT_BUF|XFS_BLF_PDQUOT_BUF|XFS_BLF_GDQUOT_BUF)) {
-		xlog_recover_do_dquot_buffer(mp, log, item, bp, buf_f);
+		bool	dirty;
+
+		dirty = xlog_recover_do_dquot_buffer(mp, log, item, bp, buf_f);
+		if (!dirty)
+			goto out_release;
 	} else {
 		xlog_recover_do_reg_buffer(mp, item, bp, buf_f);
 	}
-	if (error)
-		goto out_release;
 
 	/*
 	 * Perform delayed write on the buffer.  Asynchronous writes will be
@@ -3011,9 +3029,16 @@ xlog_recover_dquot_pass2(
 		return -EIO;
 	ASSERT(dq_f->qlf_len == 1);
 
+	/*
+	 * At this point we are assuming that the dquots have been allocated
+	 * and hence the buffer has valid dquots stamped in it. It should,
+	 * therefore, pass verifier validation. If the dquot is bad, then the
+	 * we'll return an error here, so we don't need to specifically check
+	 * the dquot in the buffer after the verifier has run.
+	 */
 	error = xfs_trans_read_buf(mp, NULL, mp->m_ddev_targp, dq_f->qlf_blkno,
 				   XFS_FSB_TO_BB(mp, dq_f->qlf_len), 0, &bp,
-				   NULL);
+				   &xfs_dquot_buf_ops);
 	if (error)
 		return error;
 
@@ -3021,18 +3046,6 @@ xlog_recover_dquot_pass2(
 	ddq = (xfs_disk_dquot_t *)xfs_buf_offset(bp, dq_f->qlf_boffset);
 
 	/*
-	 * At least the magic num portion should be on disk because this
-	 * was among a chunk of dquots created earlier, and we did some
-	 * minimal initialization then.
-	 */
-	error = xfs_dqcheck(mp, ddq, dq_f->qlf_id, 0, XFS_QMOPT_DOWARN,
-			   "xlog_recover_dquot_pass2");
-	if (error) {
-		xfs_buf_relse(bp);
-		return -EIO;
-	}
-
-	/*
 	 * If the dquot has an LSN in it, recover the dquot only if it's less
 	 * than the lsn of the transaction we are replaying.
 	 */
diff --git a/fs/xfs/xfs_mount.c b/fs/xfs/xfs_mount.c
index 5b639df0413e..fbf0384a466f 100644
--- a/fs/xfs/xfs_mount.c
+++ b/fs/xfs/xfs_mount.c
@@ -323,7 +323,6 @@ reread:
 	 * Initialize the mount structure from the superblock.
 	 */
 	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
diff --git a/fs/xfs/xfs_qm.c b/fs/xfs/xfs_qm.c
index 7e1a80b45f87..10232102b4a6 100644
--- a/fs/xfs/xfs_qm.c
+++ b/fs/xfs/xfs_qm.c
@@ -911,6 +911,12 @@ xfs_qm_dqiter_bufs(
 		if (error)
 			break;
 
+		/*
+		 * A corrupt buffer might not have a verifier attached, so
+		 * make sure we have the correct one attached before writeback
+		 * occurs.
+		 */
+		bp->b_ops = &xfs_dquot_buf_ops;
 		xfs_qm_reset_dqcounts(mp, bp, firstid, type);
 		xfs_buf_delwri_queue(bp, buffer_list);
 		xfs_buf_relse(bp);
@@ -996,7 +1002,7 @@ xfs_qm_dqiterate(
 					xfs_buf_readahead(mp->m_ddev_targp,
 					       XFS_FSB_TO_DADDR(mp, rablkno),
 					       mp->m_quotainfo->qi_dqchunklen,
-					       NULL);
+					       &xfs_dquot_buf_ops);
 					rablkno++;
 				}
 			}
diff --git a/fs/xfs/xfs_vnode.h b/fs/xfs/xfs_vnode.h
deleted file mode 100644
index e8a77383c0d5..000000000000
--- a/fs/xfs/xfs_vnode.h
+++ /dev/null
@@ -1,46 +0,0 @@
-/*
- * Copyright (c) 2000-2005 Silicon Graphics, Inc.
- * All Rights Reserved.
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License as
- * published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it would be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write the Free Software Foundation,
- * Inc.,  51 Franklin St, Fifth Floor, Boston, MA  02110-1301  USA
- */
-#ifndef __XFS_VNODE_H__
-#define __XFS_VNODE_H__
-
-#include "xfs_fs.h"
-
-struct file;
-struct xfs_inode;
-struct attrlist_cursor_kern;
-
-/*
- * Flags for read/write calls - same values as IRIX
- */
-#define IO_ISDIRECT	0x00004		/* bypass page cache */
-#define IO_INVIS	0x00020		/* don't update inode timestamps */
-
-#define XFS_IO_FLAGS \
-	{ IO_ISDIRECT,	"DIRECT" }, \
-	{ IO_INVIS,	"INVIS"}
-
-/*
- * Some useful predicates.
- */
-#define VN_MAPPED(vp)	mapping_mapped(vp->i_mapping)
-#define VN_CACHED(vp)	(vp->i_mapping->nrpages)
-#define VN_DIRTY(vp)	mapping_tagged(vp->i_mapping, \
-					PAGECACHE_TAG_DIRTY)
-
-
-#endif	/* __XFS_VNODE_H__ */