xfs: introduce xfs_inode_buf.c for inode buffer operations

The only thing remaining in xfs_inode.[ch] are the operations that
read, write or verify physical inodes in their underlying buffers.
Move all this code to xfs_inode_buf.[ch] and so we can stop sharing
xfs_inode.[ch] with userspace.

Signed-off-by: Dave Chinner <dchinner@redhat.com>
Reviewed-by: Brian Foster <bfoster@redhat.com>
Reviewed-by: Mark Tinguely <tinguely@sgi.com>
Signed-off-by: Ben Myers <bpm@sgi.com>

5 files changed, 514 insertions, 454 deletions

diff --git a/fs/xfs/Makefile b/fs/xfs/Makefile
index ce0b87e6e4f3..7f2319d3554d 100644
--- a/fs/xfs/Makefile
+++ b/fs/xfs/Makefile
@@ -75,6 +75,7 @@ xfs-y				+= xfs_alloc.o \
                                    xfs_icreate_item.o \
                                    xfs_inode.o \
                                    xfs_inode_fork.o \
+                                   xfs_inode_buf.o \
                                    xfs_log_recover.o \
                                    xfs_mount.o \
                                    xfs_symlink.o \
diff --git a/fs/xfs/xfs_inode.c b/fs/xfs/xfs_inode.c
index 18308aceebc1..fcda5b39cc17 100644
--- a/fs/xfs/xfs_inode.c
+++ b/fs/xfs/xfs_inode.c
@@ -322,236 +322,6 @@ __xfs_iflock(
         finish_wait(wq, &wait.wait);
 }
 
-/*
- * Check that none of the inode's in the buffer have a next
- * unlinked field of 0.
- */
-#if defined(DEBUG)
-void
-xfs_inobp_check(
-        xfs_mount_t     *mp,
-        xfs_buf_t       *bp)
-{
-        int             i;
-        int             j;
-        xfs_dinode_t    *dip;
-
-        j = mp->m_inode_cluster_size >> mp->m_sb.sb_inodelog;
-
-        for (i = 0; i < j; i++) {
-                dip = (xfs_dinode_t *)xfs_buf_offset(bp,
-                                        i * mp->m_sb.sb_inodesize);
-                if (!dip->di_next_unlinked)  {
-                        xfs_alert(mp,
-        "Detected bogus zero next_unlinked field in incore inode buffer 0x%p.",
-                                bp);
-                        ASSERT(dip->di_next_unlinked);
-                }
-        }
-}
-#endif
-
-static void
-xfs_inode_buf_verify(
-        struct xfs_buf  *bp)
-{
-        struct xfs_mount *mp = bp->b_target->bt_mount;
-        int             i;
-        int             ni;
-
-        /*
-         * Validate the magic number and version of every inode in the buffer
-         */
-        ni = XFS_BB_TO_FSB(mp, bp->b_length) * mp->m_sb.sb_inopblock;
-        for (i = 0; i < ni; i++) {
-                int             di_ok;
-                xfs_dinode_t    *dip;
-
-                dip = (struct xfs_dinode *)xfs_buf_offset(bp,
-                                        (i << mp->m_sb.sb_inodelog));
-                di_ok = dip->di_magic == cpu_to_be16(XFS_DINODE_MAGIC) &&
-                            XFS_DINODE_GOOD_VERSION(dip->di_version);
-                if (unlikely(XFS_TEST_ERROR(!di_ok, mp,
-                                                XFS_ERRTAG_ITOBP_INOTOBP,
-                                                XFS_RANDOM_ITOBP_INOTOBP))) {
-                        xfs_buf_ioerror(bp, EFSCORRUPTED);
-                        XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_HIGH,
-                                             mp, dip);
-#ifdef DEBUG
-                        xfs_emerg(mp,
-                                "bad inode magic/vsn daddr %lld #%d (magic=%x)",
-                                (unsigned long long)bp->b_bn, i,
-                                be16_to_cpu(dip->di_magic));
-                        ASSERT(0);
-#endif
-                }
-        }
-        xfs_inobp_check(mp, bp);
-}
-
-
-static void
-xfs_inode_buf_read_verify(
-        struct xfs_buf  *bp)
-{
-        xfs_inode_buf_verify(bp);
-}
-
-static void
-xfs_inode_buf_write_verify(
-        struct xfs_buf  *bp)
-{
-        xfs_inode_buf_verify(bp);
-}
-
-const struct xfs_buf_ops xfs_inode_buf_ops = {
-        .verify_read = xfs_inode_buf_read_verify,
-        .verify_write = xfs_inode_buf_write_verify,
-};
-
-
-/*
- * This routine is called to map an inode to the buffer containing the on-disk
- * version of the inode.  It returns a pointer to the buffer containing the
- * on-disk inode in the bpp parameter, and in the dipp parameter it returns a
- * pointer to the on-disk inode within that buffer.
- *
- * If a non-zero error is returned, then the contents of bpp and dipp are
- * undefined.
- */
-int
-xfs_imap_to_bp(
-        struct xfs_mount        *mp,
-        struct xfs_trans        *tp,
-        struct xfs_imap         *imap,
-        struct xfs_dinode       **dipp,
-        struct xfs_buf          **bpp,
-        uint                    buf_flags,
-        uint                    iget_flags)
-{
-        struct xfs_buf          *bp;
-        int                     error;
-
-        buf_flags |= XBF_UNMAPPED;
-        error = xfs_trans_read_buf(mp, tp, mp->m_ddev_targp, imap->im_blkno,
-                                   (int)imap->im_len, buf_flags, &bp,
-                                   &xfs_inode_buf_ops);
-        if (error) {
-                if (error == EAGAIN) {
-                        ASSERT(buf_flags & XBF_TRYLOCK);
-                        return error;
-                }
-
-                if (error == EFSCORRUPTED &&
-                    (iget_flags & XFS_IGET_UNTRUSTED))
-                        return XFS_ERROR(EINVAL);
-
-                xfs_warn(mp, "%s: xfs_trans_read_buf() returned error %d.",
-                        __func__, error);
-                return error;
-        }
-
-        *bpp = bp;
-        *dipp = (struct xfs_dinode *)xfs_buf_offset(bp, imap->im_boffset);
-        return 0;
-}
-
-STATIC void
-xfs_dinode_from_disk(
-        xfs_icdinode_t          *to,
-        xfs_dinode_t            *from)
-{
-        to->di_magic = be16_to_cpu(from->di_magic);
-        to->di_mode = be16_to_cpu(from->di_mode);
-        to->di_version = from ->di_version;
-        to->di_format = from->di_format;
-        to->di_onlink = be16_to_cpu(from->di_onlink);
-        to->di_uid = be32_to_cpu(from->di_uid);
-        to->di_gid = be32_to_cpu(from->di_gid);
-        to->di_nlink = be32_to_cpu(from->di_nlink);
-        to->di_projid_lo = be16_to_cpu(from->di_projid_lo);
-        to->di_projid_hi = be16_to_cpu(from->di_projid_hi);
-        memcpy(to->di_pad, from->di_pad, sizeof(to->di_pad));
-        to->di_flushiter = be16_to_cpu(from->di_flushiter);
-        to->di_atime.t_sec = be32_to_cpu(from->di_atime.t_sec);
-        to->di_atime.t_nsec = be32_to_cpu(from->di_atime.t_nsec);
-        to->di_mtime.t_sec = be32_to_cpu(from->di_mtime.t_sec);
-        to->di_mtime.t_nsec = be32_to_cpu(from->di_mtime.t_nsec);
-        to->di_ctime.t_sec = be32_to_cpu(from->di_ctime.t_sec);
-        to->di_ctime.t_nsec = be32_to_cpu(from->di_ctime.t_nsec);
-        to->di_size = be64_to_cpu(from->di_size);
-        to->di_nblocks = be64_to_cpu(from->di_nblocks);
-        to->di_extsize = be32_to_cpu(from->di_extsize);
-        to->di_nextents = be32_to_cpu(from->di_nextents);
-        to->di_anextents = be16_to_cpu(from->di_anextents);
-        to->di_forkoff = from->di_forkoff;
-        to->di_aformat  = from->di_aformat;
-        to->di_dmevmask = be32_to_cpu(from->di_dmevmask);
-        to->di_dmstate  = be16_to_cpu(from->di_dmstate);
-        to->di_flags    = be16_to_cpu(from->di_flags);
-        to->di_gen      = be32_to_cpu(from->di_gen);
-
-        if (to->di_version == 3) {
-                to->di_changecount = be64_to_cpu(from->di_changecount);
-                to->di_crtime.t_sec = be32_to_cpu(from->di_crtime.t_sec);
-                to->di_crtime.t_nsec = be32_to_cpu(from->di_crtime.t_nsec);
-                to->di_flags2 = be64_to_cpu(from->di_flags2);
-                to->di_ino = be64_to_cpu(from->di_ino);
-                to->di_lsn = be64_to_cpu(from->di_lsn);
-                memcpy(to->di_pad2, from->di_pad2, sizeof(to->di_pad2));
-                uuid_copy(&to->di_uuid, &from->di_uuid);
-        }
-}
-
-void
-xfs_dinode_to_disk(
-        xfs_dinode_t            *to,
-        xfs_icdinode_t          *from)
-{
-        to->di_magic = cpu_to_be16(from->di_magic);
-        to->di_mode = cpu_to_be16(from->di_mode);
-        to->di_version = from ->di_version;
-        to->di_format = from->di_format;
-        to->di_onlink = cpu_to_be16(from->di_onlink);
-        to->di_uid = cpu_to_be32(from->di_uid);
-        to->di_gid = cpu_to_be32(from->di_gid);
-        to->di_nlink = cpu_to_be32(from->di_nlink);
-        to->di_projid_lo = cpu_to_be16(from->di_projid_lo);
-        to->di_projid_hi = cpu_to_be16(from->di_projid_hi);
-        memcpy(to->di_pad, from->di_pad, sizeof(to->di_pad));
-        to->di_atime.t_sec = cpu_to_be32(from->di_atime.t_sec);
-        to->di_atime.t_nsec = cpu_to_be32(from->di_atime.t_nsec);
-        to->di_mtime.t_sec = cpu_to_be32(from->di_mtime.t_sec);
-        to->di_mtime.t_nsec = cpu_to_be32(from->di_mtime.t_nsec);
-        to->di_ctime.t_sec = cpu_to_be32(from->di_ctime.t_sec);
-        to->di_ctime.t_nsec = cpu_to_be32(from->di_ctime.t_nsec);
-        to->di_size = cpu_to_be64(from->di_size);
-        to->di_nblocks = cpu_to_be64(from->di_nblocks);
-        to->di_extsize = cpu_to_be32(from->di_extsize);
-        to->di_nextents = cpu_to_be32(from->di_nextents);
-        to->di_anextents = cpu_to_be16(from->di_anextents);
-        to->di_forkoff = from->di_forkoff;
-        to->di_aformat = from->di_aformat;
-        to->di_dmevmask = cpu_to_be32(from->di_dmevmask);
-        to->di_dmstate = cpu_to_be16(from->di_dmstate);
-        to->di_flags = cpu_to_be16(from->di_flags);
-        to->di_gen = cpu_to_be32(from->di_gen);
-
-        if (from->di_version == 3) {
-                to->di_changecount = cpu_to_be64(from->di_changecount);
-                to->di_crtime.t_sec = cpu_to_be32(from->di_crtime.t_sec);
-                to->di_crtime.t_nsec = cpu_to_be32(from->di_crtime.t_nsec);
-                to->di_flags2 = cpu_to_be64(from->di_flags2);
-                to->di_ino = cpu_to_be64(from->di_ino);
-                to->di_lsn = cpu_to_be64(from->di_lsn);
-                memcpy(to->di_pad2, from->di_pad2, sizeof(to->di_pad2));
-                uuid_copy(&to->di_uuid, &from->di_uuid);
-                to->di_flushiter = 0;
-        } else {
-                to->di_flushiter = cpu_to_be16(from->di_flushiter);
-        }
-}
-
 STATIC uint
 _xfs_dic2xflags(
         __uint16_t              di_flags)
@@ -610,196 +380,6 @@ xfs_dic2xflags(
                                 (XFS_DFORK_Q(dip) ? XFS_XFLAG_HASATTR : 0);
 }
 
-static bool
-xfs_dinode_verify(
-        struct xfs_mount        *mp,
-        struct xfs_inode        *ip,
-        struct xfs_dinode       *dip)
-{
-        if (dip->di_magic != cpu_to_be16(XFS_DINODE_MAGIC))
-                return false;
-
-        /* only version 3 or greater inodes are extensively verified here */
-        if (dip->di_version < 3)
-                return true;
-
-        if (!xfs_sb_version_hascrc(&mp->m_sb))
-                return false;
-        if (!xfs_verify_cksum((char *)dip, mp->m_sb.sb_inodesize,
-                              offsetof(struct xfs_dinode, di_crc)))
-                return false;
-        if (be64_to_cpu(dip->di_ino) != ip->i_ino)
-                return false;
-        if (!uuid_equal(&dip->di_uuid, &mp->m_sb.sb_uuid))
-                return false;
-        return true;
-}
-
-void
-xfs_dinode_calc_crc(
-        struct xfs_mount        *mp,
-        struct xfs_dinode       *dip)
-{
-        __uint32_t              crc;
-
-        if (dip->di_version < 3)
-                return;
-
-        ASSERT(xfs_sb_version_hascrc(&mp->m_sb));
-        crc = xfs_start_cksum((char *)dip, mp->m_sb.sb_inodesize,
-                              offsetof(struct xfs_dinode, di_crc));
-        dip->di_crc = xfs_end_cksum(crc);
-}
-
-/*
- * Read the disk inode attributes into the in-core inode structure.
- *
- * For version 5 superblocks, if we are initialising a new inode and we are not
- * utilising the XFS_MOUNT_IKEEP inode cluster mode, we can simple build the new
- * inode core with a random generation number. If we are keeping inodes around,
- * we need to read the inode cluster to get the existing generation number off
- * disk. Further, if we are using version 4 superblocks (i.e. v1/v2 inode
- * format) then log recovery is dependent on the di_flushiter field being
- * initialised from the current on-disk value and hence we must also read the
- * inode off disk.
- */
-int
-xfs_iread(
-        xfs_mount_t     *mp,
-        xfs_trans_t     *tp,
-        xfs_inode_t     *ip,
-        uint            iget_flags)
-{
-        xfs_buf_t       *bp;
-        xfs_dinode_t    *dip;
-        int             error;
-
-        /*
-         * Fill in the location information in the in-core inode.
-         */
-        error = xfs_imap(mp, tp, ip->i_ino, &ip->i_imap, iget_flags);
-        if (error)
-                return error;
-
-        /* shortcut IO on inode allocation if possible */
-        if ((iget_flags & XFS_IGET_CREATE) &&
-            xfs_sb_version_hascrc(&mp->m_sb) &&
-            !(mp->m_flags & XFS_MOUNT_IKEEP)) {
-                /* initialise the on-disk inode core */
-                memset(&ip->i_d, 0, sizeof(ip->i_d));
-                ip->i_d.di_magic = XFS_DINODE_MAGIC;
-                ip->i_d.di_gen = prandom_u32();
-                if (xfs_sb_version_hascrc(&mp->m_sb)) {
-                        ip->i_d.di_version = 3;
-                        ip->i_d.di_ino = ip->i_ino;
-                        uuid_copy(&ip->i_d.di_uuid, &mp->m_sb.sb_uuid);
-                } else
-                        ip->i_d.di_version = 2;
-                return 0;
-        }
-
-        /*
-         * Get pointers to the on-disk inode and the buffer containing it.
-         */
-        error = xfs_imap_to_bp(mp, tp, &ip->i_imap, &dip, &bp, 0, iget_flags);
-        if (error)
-                return error;
-
-        /* even unallocated inodes are verified */
-        if (!xfs_dinode_verify(mp, ip, dip)) {
-                xfs_alert(mp, "%s: validation failed for inode %lld failed",
-                                __func__, ip->i_ino);
-
-                XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_LOW, mp, dip);
-                error = XFS_ERROR(EFSCORRUPTED);
-                goto out_brelse;
-        }
-
-        /*
-         * If the on-disk inode is already linked to a directory
-         * entry, copy all of the inode into the in-core inode.
-         * xfs_iformat_fork() handles copying in the inode format
-         * specific information.
-         * Otherwise, just get the truly permanent information.
-         */
-        if (dip->di_mode) {
-                xfs_dinode_from_disk(&ip->i_d, dip);
-                error = xfs_iformat_fork(ip, dip);
-                if (error)  {
-#ifdef DEBUG
-                        xfs_alert(mp, "%s: xfs_iformat() returned error %d",
-                                __func__, error);
-#endif /* DEBUG */
-                        goto out_brelse;
-                }
-        } else {
-                /*
-                 * Partial initialisation of the in-core inode. Just the bits
-                 * that xfs_ialloc won't overwrite or relies on being correct.
-                 */
-                ip->i_d.di_magic = be16_to_cpu(dip->di_magic);
-                ip->i_d.di_version = dip->di_version;
-                ip->i_d.di_gen = be32_to_cpu(dip->di_gen);
-                ip->i_d.di_flushiter = be16_to_cpu(dip->di_flushiter);
-
-                if (dip->di_version == 3) {
-                        ip->i_d.di_ino = be64_to_cpu(dip->di_ino);
-                        uuid_copy(&ip->i_d.di_uuid, &dip->di_uuid);
-                }
-
-                /*
-                 * Make sure to pull in the mode here as well in
-                 * case the inode is released without being used.
-                 * This ensures that xfs_inactive() will see that
-                 * the inode is already free and not try to mess
-                 * with the uninitialized part of it.
-                 */
-                ip->i_d.di_mode = 0;
-        }
-
-        /*
-         * The inode format changed when we moved the link count and
-         * made it 32 bits long.  If this is an old format inode,
-         * convert it in memory to look like a new one.  If it gets
-         * flushed to disk we will convert back before flushing or
-         * logging it.  We zero out the new projid field and the old link
-         * count field.  We'll handle clearing the pad field (the remains
-         * of the old uuid field) when we actually convert the inode to
-         * the new format. We don't change the version number so that we
-         * can distinguish this from a real new format inode.
-         */
-        if (ip->i_d.di_version == 1) {
-                ip->i_d.di_nlink = ip->i_d.di_onlink;
-                ip->i_d.di_onlink = 0;
-                xfs_set_projid(ip, 0);
-        }
-
-        ip->i_delayed_blks = 0;
-
-        /*
-         * Mark the buffer containing the inode as something to keep
-         * around for a while.  This helps to keep recently accessed
-         * meta-data in-core longer.
-         */
-        xfs_buf_set_ref(bp, XFS_INO_REF);
-
-        /*
-         * Use xfs_trans_brelse() to release the buffer containing the on-disk
-         * inode, because it was acquired with xfs_trans_read_buf() in
-         * xfs_imap_to_bp() above.  If tp is NULL, this is just a normal
-         * brelse().  If we're within a transaction, then xfs_trans_brelse()
-         * will only release the buffer if it is not dirty within the
-         * transaction.  It will be OK to release the buffer in this case,
-         * because inodes on disk are never destroyed and we will be locking the
-         * new in-core inode before putting it in the cache where other
-         * processes can find it.  Thus we don't have to worry about the inode
-         * being changed just because we released the buffer.
-         */
- out_brelse:
-        xfs_trans_brelse(tp, bp);
-        return error;
-}
-
 /*
  * Allocate an inode on disk and return a copy of its in-core version.
  * The in-core inode is locked exclusively.  Set mode, nlink, and rdev
diff --git a/fs/xfs/xfs_inode.h b/fs/xfs/xfs_inode.h
index 0bd034ac8f82..8f775ed722a9 100644
--- a/fs/xfs/xfs_inode.h
+++ b/fs/xfs/xfs_inode.h
@@ -18,24 +18,15 @@
 #ifndef __XFS_INODE_H__
 #define __XFS_INODE_H__
 
-struct posix_acl;
-struct xfs_dinode;
-struct xfs_inode;
-
+#include "xfs_inode_buf.h"
 #include "xfs_inode_fork.h"
 
 /*
- * Inode location information.  Stored in the inode and passed to
- * xfs_imap_to_bp() to get a buffer and dinode for a given inode.
+ * Kernel only inode definitions
  */
-struct xfs_imap {
-        xfs_daddr_t     im_blkno;       /* starting BB of inode chunk */
-        ushort          im_len;         /* length in BBs of inode chunk */
-        ushort          im_boffset;     /* inode offset in block in bytes */
-};
-
-#ifdef __KERNEL__
 
+struct xfs_dinode;
+struct xfs_inode;
 struct xfs_buf;
 struct xfs_bmap_free;
 struct xfs_bmbt_irec;
@@ -347,7 +338,10 @@ int		xfs_itruncate_extents(struct xfs_trans **, struct xfs_inode *,
 int             xfs_iunlink(struct xfs_trans *, xfs_inode_t *);
 
 void            xfs_iext_realloc(xfs_inode_t *, int, int);
+
 void            xfs_iunpin_wait(xfs_inode_t *);
+#define xfs_ipincount(ip)       ((unsigned int) atomic_read(&ip->i_pincount))
+
 int             xfs_iflush(struct xfs_inode *, struct xfs_buf **);
 void            xfs_lock_inodes(xfs_inode_t **, int, uint);
 void            xfs_lock_two_inodes(xfs_inode_t *, xfs_inode_t *, uint);
@@ -367,27 +361,6 @@ do { \
         iput(VFS_I(ip)); \
 } while (0)
 
-#endif /* __KERNEL__ */
-
-int             xfs_imap_to_bp(struct xfs_mount *, struct xfs_trans *,
-                               struct xfs_imap *, struct xfs_dinode **,
-                               struct xfs_buf **, uint, uint);
-int             xfs_iread(struct xfs_mount *, struct xfs_trans *,
-                          struct xfs_inode *, uint);
-void            xfs_dinode_calc_crc(struct xfs_mount *, struct xfs_dinode *);
-void            xfs_dinode_to_disk(struct xfs_dinode *,
-                                   struct xfs_icdinode *);
-bool            xfs_can_free_eofblocks(struct xfs_inode *, bool);
-
-#define xfs_ipincount(ip)       ((unsigned int) atomic_read(&ip->i_pincount))
-
-#if defined(DEBUG)
-void            xfs_inobp_check(struct xfs_mount *, struct xfs_buf *);
-#else
-#define xfs_inobp_check(mp, bp)
-#endif /* DEBUG */
-
 extern struct kmem_zone *xfs_inode_zone;
-extern const struct xfs_buf_ops xfs_inode_buf_ops;
 
 #endif  /* __XFS_INODE_H__ */
diff --git a/fs/xfs/xfs_inode_buf.c b/fs/xfs/xfs_inode_buf.c
new file mode 100644
index 000000000000..38fe509827dd
--- /dev/null
+++ b/fs/xfs/xfs_inode_buf.c
@@ -0,0 +1,453 @@
+/*
+ * Copyright (c) 2000-2006 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
+ */
+#include "xfs.h"
+#include "xfs_fs.h"
+#include "xfs_format.h"
+#include "xfs_log.h"
+#include "xfs_trans.h"
+#include "xfs_sb.h"
+#include "xfs_ag.h"
+#include "xfs_mount.h"
+#include "xfs_bmap_btree.h"
+#include "xfs_ialloc_btree.h"
+#include "xfs_dinode.h"
+#include "xfs_inode.h"
+#include "xfs_error.h"
+#include "xfs_cksum.h"
+#include "xfs_icache.h"
+#include "xfs_ialloc.h"
+
+/*
+ * Check that none of the inode's in the buffer have a next
+ * unlinked field of 0.
+ */
+#if defined(DEBUG)
+void
+xfs_inobp_check(
+        xfs_mount_t     *mp,
+        xfs_buf_t       *bp)
+{
+        int             i;
+        int             j;
+        xfs_dinode_t    *dip;
+
+        j = mp->m_inode_cluster_size >> mp->m_sb.sb_inodelog;
+
+        for (i = 0; i < j; i++) {
+                dip = (xfs_dinode_t *)xfs_buf_offset(bp,
+                                        i * mp->m_sb.sb_inodesize);
+                if (!dip->di_next_unlinked)  {
+                        xfs_alert(mp,
+        "Detected bogus zero next_unlinked field in incore inode buffer 0x%p.",
+                                bp);
+                        ASSERT(dip->di_next_unlinked);
+                }
+        }
+}
+#endif
+
+static void
+xfs_inode_buf_verify(
+        struct xfs_buf  *bp)
+{
+        struct xfs_mount *mp = bp->b_target->bt_mount;
+        int             i;
+        int             ni;
+
+        /*
+         * Validate the magic number and version of every inode in the buffer
+         */
+        ni = XFS_BB_TO_FSB(mp, bp->b_length) * mp->m_sb.sb_inopblock;
+        for (i = 0; i < ni; i++) {
+                int             di_ok;
+                xfs_dinode_t    *dip;
+
+                dip = (struct xfs_dinode *)xfs_buf_offset(bp,
+                                        (i << mp->m_sb.sb_inodelog));
+                di_ok = dip->di_magic == cpu_to_be16(XFS_DINODE_MAGIC) &&
+                            XFS_DINODE_GOOD_VERSION(dip->di_version);
+                if (unlikely(XFS_TEST_ERROR(!di_ok, mp,
+                                                XFS_ERRTAG_ITOBP_INOTOBP,
+                                                XFS_RANDOM_ITOBP_INOTOBP))) {
+                        xfs_buf_ioerror(bp, EFSCORRUPTED);
+                        XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_HIGH,
+                                             mp, dip);
+#ifdef DEBUG
+                        xfs_emerg(mp,
+                                "bad inode magic/vsn daddr %lld #%d (magic=%x)",
+                                (unsigned long long)bp->b_bn, i,
+                                be16_to_cpu(dip->di_magic));
+                        ASSERT(0);
+#endif
+                }
+        }
+        xfs_inobp_check(mp, bp);
+}
+
+
+static void
+xfs_inode_buf_read_verify(
+        struct xfs_buf  *bp)
+{
+        xfs_inode_buf_verify(bp);
+}
+
+static void
+xfs_inode_buf_write_verify(
+        struct xfs_buf  *bp)
+{
+        xfs_inode_buf_verify(bp);
+}
+
+const struct xfs_buf_ops xfs_inode_buf_ops = {
+        .verify_read = xfs_inode_buf_read_verify,
+        .verify_write = xfs_inode_buf_write_verify,
+};
+
+
+/*
+ * This routine is called to map an inode to the buffer containing the on-disk
+ * version of the inode.  It returns a pointer to the buffer containing the
+ * on-disk inode in the bpp parameter, and in the dipp parameter it returns a
+ * pointer to the on-disk inode within that buffer.
+ *
+ * If a non-zero error is returned, then the contents of bpp and dipp are
+ * undefined.
+ */
+int
+xfs_imap_to_bp(
+        struct xfs_mount        *mp,
+        struct xfs_trans        *tp,
+        struct xfs_imap         *imap,
+        struct xfs_dinode       **dipp,
+        struct xfs_buf          **bpp,
+        uint                    buf_flags,
+        uint                    iget_flags)
+{
+        struct xfs_buf          *bp;
+        int                     error;
+
+        buf_flags |= XBF_UNMAPPED;
+        error = xfs_trans_read_buf(mp, tp, mp->m_ddev_targp, imap->im_blkno,
+                                   (int)imap->im_len, buf_flags, &bp,
+                                   &xfs_inode_buf_ops);
+        if (error) {
+                if (error == EAGAIN) {
+                        ASSERT(buf_flags & XBF_TRYLOCK);
+                        return error;
+                }
+
+                if (error == EFSCORRUPTED &&
+                    (iget_flags & XFS_IGET_UNTRUSTED))
+                        return XFS_ERROR(EINVAL);
+
+                xfs_warn(mp, "%s: xfs_trans_read_buf() returned error %d.",
+                        __func__, error);
+                return error;
+        }
+
+        *bpp = bp;
+        *dipp = (struct xfs_dinode *)xfs_buf_offset(bp, imap->im_boffset);
+        return 0;
+}
+
+STATIC void
+xfs_dinode_from_disk(
+        xfs_icdinode_t          *to,
+        xfs_dinode_t            *from)
+{
+        to->di_magic = be16_to_cpu(from->di_magic);
+        to->di_mode = be16_to_cpu(from->di_mode);
+        to->di_version = from ->di_version;
+        to->di_format = from->di_format;
+        to->di_onlink = be16_to_cpu(from->di_onlink);
+        to->di_uid = be32_to_cpu(from->di_uid);
+        to->di_gid = be32_to_cpu(from->di_gid);
+        to->di_nlink = be32_to_cpu(from->di_nlink);
+        to->di_projid_lo = be16_to_cpu(from->di_projid_lo);
+        to->di_projid_hi = be16_to_cpu(from->di_projid_hi);
+        memcpy(to->di_pad, from->di_pad, sizeof(to->di_pad));
+        to->di_flushiter = be16_to_cpu(from->di_flushiter);
+        to->di_atime.t_sec = be32_to_cpu(from->di_atime.t_sec);
+        to->di_atime.t_nsec = be32_to_cpu(from->di_atime.t_nsec);
+        to->di_mtime.t_sec = be32_to_cpu(from->di_mtime.t_sec);
+        to->di_mtime.t_nsec = be32_to_cpu(from->di_mtime.t_nsec);
+        to->di_ctime.t_sec = be32_to_cpu(from->di_ctime.t_sec);
+        to->di_ctime.t_nsec = be32_to_cpu(from->di_ctime.t_nsec);
+        to->di_size = be64_to_cpu(from->di_size);
+        to->di_nblocks = be64_to_cpu(from->di_nblocks);
+        to->di_extsize = be32_to_cpu(from->di_extsize);
+        to->di_nextents = be32_to_cpu(from->di_nextents);
+        to->di_anextents = be16_to_cpu(from->di_anextents);
+        to->di_forkoff = from->di_forkoff;
+        to->di_aformat  = from->di_aformat;
+        to->di_dmevmask = be32_to_cpu(from->di_dmevmask);
+        to->di_dmstate  = be16_to_cpu(from->di_dmstate);
+        to->di_flags    = be16_to_cpu(from->di_flags);
+        to->di_gen      = be32_to_cpu(from->di_gen);
+
+        if (to->di_version == 3) {
+                to->di_changecount = be64_to_cpu(from->di_changecount);
+                to->di_crtime.t_sec = be32_to_cpu(from->di_crtime.t_sec);
+                to->di_crtime.t_nsec = be32_to_cpu(from->di_crtime.t_nsec);
+                to->di_flags2 = be64_to_cpu(from->di_flags2);
+                to->di_ino = be64_to_cpu(from->di_ino);
+                to->di_lsn = be64_to_cpu(from->di_lsn);
+                memcpy(to->di_pad2, from->di_pad2, sizeof(to->di_pad2));
+                uuid_copy(&to->di_uuid, &from->di_uuid);
+        }
+}
+
+void
+xfs_dinode_to_disk(
+        xfs_dinode_t            *to,
+        xfs_icdinode_t          *from)
+{
+        to->di_magic = cpu_to_be16(from->di_magic);
+        to->di_mode = cpu_to_be16(from->di_mode);
+        to->di_version = from ->di_version;
+        to->di_format = from->di_format;
+        to->di_onlink = cpu_to_be16(from->di_onlink);
+        to->di_uid = cpu_to_be32(from->di_uid);
+        to->di_gid = cpu_to_be32(from->di_gid);
+        to->di_nlink = cpu_to_be32(from->di_nlink);
+        to->di_projid_lo = cpu_to_be16(from->di_projid_lo);
+        to->di_projid_hi = cpu_to_be16(from->di_projid_hi);
+        memcpy(to->di_pad, from->di_pad, sizeof(to->di_pad));
+        to->di_atime.t_sec = cpu_to_be32(from->di_atime.t_sec);
+        to->di_atime.t_nsec = cpu_to_be32(from->di_atime.t_nsec);
+        to->di_mtime.t_sec = cpu_to_be32(from->di_mtime.t_sec);
+        to->di_mtime.t_nsec = cpu_to_be32(from->di_mtime.t_nsec);
+        to->di_ctime.t_sec = cpu_to_be32(from->di_ctime.t_sec);
+        to->di_ctime.t_nsec = cpu_to_be32(from->di_ctime.t_nsec);
+        to->di_size = cpu_to_be64(from->di_size);
+        to->di_nblocks = cpu_to_be64(from->di_nblocks);
+        to->di_extsize = cpu_to_be32(from->di_extsize);
+        to->di_nextents = cpu_to_be32(from->di_nextents);
+        to->di_anextents = cpu_to_be16(from->di_anextents);
+        to->di_forkoff = from->di_forkoff;
+        to->di_aformat = from->di_aformat;
+        to->di_dmevmask = cpu_to_be32(from->di_dmevmask);
+        to->di_dmstate = cpu_to_be16(from->di_dmstate);
+        to->di_flags = cpu_to_be16(from->di_flags);
+        to->di_gen = cpu_to_be32(from->di_gen);
+
+        if (from->di_version == 3) {
+                to->di_changecount = cpu_to_be64(from->di_changecount);
+                to->di_crtime.t_sec = cpu_to_be32(from->di_crtime.t_sec);
+                to->di_crtime.t_nsec = cpu_to_be32(from->di_crtime.t_nsec);
+                to->di_flags2 = cpu_to_be64(from->di_flags2);
+                to->di_ino = cpu_to_be64(from->di_ino);
+                to->di_lsn = cpu_to_be64(from->di_lsn);
+                memcpy(to->di_pad2, from->di_pad2, sizeof(to->di_pad2));
+                uuid_copy(&to->di_uuid, &from->di_uuid);
+                to->di_flushiter = 0;
+        } else {
+                to->di_flushiter = cpu_to_be16(from->di_flushiter);
+        }
+}
+
+static bool
+xfs_dinode_verify(
+        struct xfs_mount        *mp,
+        struct xfs_inode        *ip,
+        struct xfs_dinode       *dip)
+{
+        if (dip->di_magic != cpu_to_be16(XFS_DINODE_MAGIC))
+                return false;
+
+        /* only version 3 or greater inodes are extensively verified here */
+        if (dip->di_version < 3)
+                return true;
+
+        if (!xfs_sb_version_hascrc(&mp->m_sb))
+                return false;
+        if (!xfs_verify_cksum((char *)dip, mp->m_sb.sb_inodesize,
+                              offsetof(struct xfs_dinode, di_crc)))
+                return false;
+        if (be64_to_cpu(dip->di_ino) != ip->i_ino)
+                return false;
+        if (!uuid_equal(&dip->di_uuid, &mp->m_sb.sb_uuid))
+                return false;
+        return true;
+}
+
+void
+xfs_dinode_calc_crc(
+        struct xfs_mount        *mp,
+        struct xfs_dinode       *dip)
+{
+        __uint32_t              crc;
+
+        if (dip->di_version < 3)
+                return;
+
+        ASSERT(xfs_sb_version_hascrc(&mp->m_sb));
+        crc = xfs_start_cksum((char *)dip, mp->m_sb.sb_inodesize,
+                              offsetof(struct xfs_dinode, di_crc));
+        dip->di_crc = xfs_end_cksum(crc);
+}
+
+/*
+ * Read the disk inode attributes into the in-core inode structure.
+ *
+ * For version 5 superblocks, if we are initialising a new inode and we are not
+ * utilising the XFS_MOUNT_IKEEP inode cluster mode, we can simple build the new
+ * inode core with a random generation number. If we are keeping inodes around,
+ * we need to read the inode cluster to get the existing generation number off
+ * disk. Further, if we are using version 4 superblocks (i.e. v1/v2 inode
+ * format) then log recovery is dependent on the di_flushiter field being
+ * initialised from the current on-disk value and hence we must also read the
+ * inode off disk.
+ */
+int
+xfs_iread(
+        xfs_mount_t     *mp,
+        xfs_trans_t     *tp,
+        xfs_inode_t     *ip,
+        uint            iget_flags)
+{
+        xfs_buf_t       *bp;
+        xfs_dinode_t    *dip;
+        int             error;
+
+        /*
+         * Fill in the location information in the in-core inode.
+         */
+        error = xfs_imap(mp, tp, ip->i_ino, &ip->i_imap, iget_flags);
+        if (error)
+                return error;
+
+        /* shortcut IO on inode allocation if possible */
+        if ((iget_flags & XFS_IGET_CREATE) &&
+            xfs_sb_version_hascrc(&mp->m_sb) &&
+            !(mp->m_flags & XFS_MOUNT_IKEEP)) {
+                /* initialise the on-disk inode core */
+                memset(&ip->i_d, 0, sizeof(ip->i_d));
+                ip->i_d.di_magic = XFS_DINODE_MAGIC;
+                ip->i_d.di_gen = prandom_u32();
+                if (xfs_sb_version_hascrc(&mp->m_sb)) {
+                        ip->i_d.di_version = 3;
+                        ip->i_d.di_ino = ip->i_ino;
+                        uuid_copy(&ip->i_d.di_uuid, &mp->m_sb.sb_uuid);
+                } else
+                        ip->i_d.di_version = 2;
+                return 0;
+        }
+
+        /*
+         * Get pointers to the on-disk inode and the buffer containing it.
+         */
+        error = xfs_imap_to_bp(mp, tp, &ip->i_imap, &dip, &bp, 0, iget_flags);
+        if (error)
+                return error;
+
+        /* even unallocated inodes are verified */
+        if (!xfs_dinode_verify(mp, ip, dip)) {
+                xfs_alert(mp, "%s: validation failed for inode %lld failed",
+                                __func__, ip->i_ino);
+
+                XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_LOW, mp, dip);
+                error = XFS_ERROR(EFSCORRUPTED);
+                goto out_brelse;
+        }
+
+        /*
+         * If the on-disk inode is already linked to a directory
+         * entry, copy all of the inode into the in-core inode.
+         * xfs_iformat_fork() handles copying in the inode format
+         * specific information.
+         * Otherwise, just get the truly permanent information.
+         */
+        if (dip->di_mode) {
+                xfs_dinode_from_disk(&ip->i_d, dip);
+                error = xfs_iformat_fork(ip, dip);
+                if (error)  {
+#ifdef DEBUG
+                        xfs_alert(mp, "%s: xfs_iformat() returned error %d",
+                                __func__, error);
+#endif /* DEBUG */
+                        goto out_brelse;
+                }
+        } else {
+                /*
+                 * Partial initialisation of the in-core inode. Just the bits
+                 * that xfs_ialloc won't overwrite or relies on being correct.
+                 */
+                ip->i_d.di_magic = be16_to_cpu(dip->di_magic);
+                ip->i_d.di_version = dip->di_version;
+                ip->i_d.di_gen = be32_to_cpu(dip->di_gen);
+                ip->i_d.di_flushiter = be16_to_cpu(dip->di_flushiter);
+
+                if (dip->di_version == 3) {
+                        ip->i_d.di_ino = be64_to_cpu(dip->di_ino);
+                        uuid_copy(&ip->i_d.di_uuid, &dip->di_uuid);
+                }
+
+                /*
+                 * Make sure to pull in the mode here as well in
+                 * case the inode is released without being used.
+                 * This ensures that xfs_inactive() will see that
+                 * the inode is already free and not try to mess
+                 * with the uninitialized part of it.
+                 */
+                ip->i_d.di_mode = 0;
+        }
+
+        /*
+         * The inode format changed when we moved the link count and
+         * made it 32 bits long.  If this is an old format inode,
+         * convert it in memory to look like a new one.  If it gets
+         * flushed to disk we will convert back before flushing or
+         * logging it.  We zero out the new projid field and the old link
+         * count field.  We'll handle clearing the pad field (the remains
+         * of the old uuid field) when we actually convert the inode to
+         * the new format. We don't change the version number so that we
+         * can distinguish this from a real new format inode.
+         */
+        if (ip->i_d.di_version == 1) {
+                ip->i_d.di_nlink = ip->i_d.di_onlink;
+                ip->i_d.di_onlink = 0;
+                xfs_set_projid(ip, 0);
+        }
+
+        ip->i_delayed_blks = 0;
+
+        /*
+         * Mark the buffer containing the inode as something to keep
+         * around for a while.  This helps to keep recently accessed
+         * meta-data in-core longer.
+         */
+        xfs_buf_set_ref(bp, XFS_INO_REF);
+
+        /*
+         * Use xfs_trans_brelse() to release the buffer containing the on-disk
+         * inode, because it was acquired with xfs_trans_read_buf() in
+         * xfs_imap_to_bp() above.  If tp is NULL, this is just a normal
+         * brelse().  If we're within a transaction, then xfs_trans_brelse()
+         * will only release the buffer if it is not dirty within the
+         * transaction.  It will be OK to release the buffer in this case,
+         * because inodes on disk are never destroyed and we will be locking the
+         * new in-core inode before putting it in the cache where other
+         * processes can find it.  Thus we don't have to worry about the inode
+         * being changed just because we released the buffer.
+         */
+ out_brelse:
+        xfs_trans_brelse(tp, bp);
+        return error;
+}
diff --git a/fs/xfs/xfs_inode_buf.h b/fs/xfs/xfs_inode_buf.h
new file mode 100644
index 000000000000..b5f1e22bf44e
--- /dev/null
+++ b/fs/xfs/xfs_inode_buf.h
@@ -0,0 +1,53 @@
+/*
+ * Copyright (c) 2000-2003,2005 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_INODE_BUF_H__
+#define __XFS_INODE_BUF_H__
+
+struct xfs_inode;
+struct xfs_dinode;
+struct xfs_icdinode;
+
+/*
+ * Inode location information.  Stored in the inode and passed to
+ * xfs_imap_to_bp() to get a buffer and dinode for a given inode.
+ */
+struct xfs_imap {
+        xfs_daddr_t     im_blkno;       /* starting BB of inode chunk */
+        ushort          im_len;         /* length in BBs of inode chunk */
+        ushort          im_boffset;     /* inode offset in block in bytes */
+};
+
+int             xfs_imap_to_bp(struct xfs_mount *, struct xfs_trans *,
+                               struct xfs_imap *, struct xfs_dinode **,
+                               struct xfs_buf **, uint, uint);
+int             xfs_iread(struct xfs_mount *, struct xfs_trans *,
+                          struct xfs_inode *, uint);
+void            xfs_dinode_calc_crc(struct xfs_mount *, struct xfs_dinode *);
+void            xfs_dinode_to_disk(struct xfs_dinode *,
+                                   struct xfs_icdinode *);
+bool            xfs_can_free_eofblocks(struct xfs_inode *, bool);
+
+#if defined(DEBUG)
+void            xfs_inobp_check(struct xfs_mount *, struct xfs_buf *);
+#else
+#define xfs_inobp_check(mp, bp)
+#endif /* DEBUG */
+
+extern const struct xfs_buf_ops xfs_inode_buf_ops;
+
+#endif  /* __XFS_INODE_BUF_H__ */