ocfs2: Add the 'inode64' mount option.

Now that ocfs2 limits inode numbers to 32bits, add a mount option to
disable the limit.  This parallels XFS.  64bit systems can handle the
larger inode numbers.

[ Added description of inode64 mount option in ocfs2.txt. --Mark ]

Signed-off-by: Joel Becker <joel.becker@oracle.com>
Signed-off-by: Mark Fasheh <mfasheh@suse.com>

4 files changed, 25 insertions, 2 deletions

diff --git a/Documentation/filesystems/ocfs2.txt b/Documentation/filesystems/ocfs2.txt
index c318a8bbb1ef..6acf1b4f2466 100644
--- a/Documentation/filesystems/ocfs2.txt
+++ b/Documentation/filesystems/ocfs2.txt
@@ -76,3 +76,7 @@ localalloc=8(*)		Allows custom localalloc size in MB. If the value is too
                         large, the fs will silently revert it to the default.
                         Localalloc is not enabled for local mounts.
 localflocks             This disables cluster aware flock.
+inode64                 Indicates that Ocfs2 is allowed to create inodes at
+                        any location in the filesystem, including those which
+                        will result in inode numbers occupying more than 32
+                        bits of significance.
diff --git a/fs/ocfs2/ocfs2.h b/fs/ocfs2/ocfs2.h
index 6d3c10ddf489..78ae4f87e6b0 100644
--- a/fs/ocfs2/ocfs2.h
+++ b/fs/ocfs2/ocfs2.h
@@ -189,6 +189,7 @@ enum ocfs2_mount_options
         OCFS2_MOUNT_DATA_WRITEBACK = 1 << 4, /* No data ordering */
         OCFS2_MOUNT_LOCALFLOCKS = 1 << 5, /* No cluster aware user file locks */
         OCFS2_MOUNT_NOUSERXATTR = 1 << 6, /* No user xattr */
+        OCFS2_MOUNT_INODE64 = 1 << 7,   /* Allow inode numbers > 2^32 */
 };
 
 #define OCFS2_OSB_SOFT_RO       0x0001
diff --git a/fs/ocfs2/suballoc.c b/fs/ocfs2/suballoc.c
index 213bdca16fe4..d7a6f928c317 100644
--- a/fs/ocfs2/suballoc.c
+++ b/fs/ocfs2/suballoc.c
@@ -601,9 +601,10 @@ int ocfs2_reserve_new_inode(struct ocfs2_super *osb,
         /*
          * stat(2) can't handle i_ino > 32bits, so we tell the
          * lower levels not to allocate us a block group past that
-         * limit.
+         * limit.  The 'inode64' mount option avoids this behavior.
          */
-        (*ac)->ac_max_block = (u32)~0U;
+        if (!(osb->s_mount_opt & OCFS2_MOUNT_INODE64))
+                (*ac)->ac_max_block = (u32)~0U;
 
         /*
          * slot is set when we successfully steal inode from other nodes.
diff --git a/fs/ocfs2/super.c b/fs/ocfs2/super.c
index c85e525950a9..1a51c8c53bef 100644
--- a/fs/ocfs2/super.c
+++ b/fs/ocfs2/super.c
@@ -157,6 +157,7 @@ enum {
         Opt_stack,
         Opt_user_xattr,
         Opt_nouser_xattr,
+        Opt_inode64,
         Opt_err,
 };
 
@@ -178,6 +179,7 @@ static const match_table_t tokens = {
         {Opt_stack, "cluster_stack=%s"},
         {Opt_user_xattr, "user_xattr"},
         {Opt_nouser_xattr, "nouser_xattr"},
+        {Opt_inode64, "inode64"},
         {Opt_err, NULL}
 };
 
@@ -411,6 +413,15 @@ static int ocfs2_remount(struct super_block *sb, int *flags, char *data)
                 goto out;
         }
 
+        /* Probably don't want this on remount; it might
+         * mess with other nodes */
+        if (!(osb->s_mount_opt & OCFS2_MOUNT_INODE64) &&
+            (parsed_options.mount_opt & OCFS2_MOUNT_INODE64)) {
+                ret = -EINVAL;
+                mlog(ML_ERROR, "Cannot enable inode64 on remount\n");
+                goto out;
+        }
+
         /* We're going to/from readonly mode. */
         if ((*flags & MS_RDONLY) != (sb->s_flags & MS_RDONLY)) {
                 /* Lock here so the check of HARD_RO and the potential
@@ -930,6 +941,9 @@ static int ocfs2_parse_options(struct super_block *sb,
                                OCFS2_STACK_LABEL_LEN);
                         mopt->cluster_stack[OCFS2_STACK_LABEL_LEN] = '\0';
                         break;
+                case Opt_inode64:
+                        mopt->mount_opt |= OCFS2_MOUNT_INODE64;
+                        break;
                 default:
                         mlog(ML_ERROR,
                              "Unrecognized mount option \"%s\" "
@@ -994,6 +1008,9 @@ static int ocfs2_show_options(struct seq_file *s, struct vfsmount *mnt)
                 seq_printf(s, ",cluster_stack=%.*s", OCFS2_STACK_LABEL_LEN,
                            osb->osb_cluster_stack);
 
+        if (opts & OCFS2_MOUNT_INODE64)
+                seq_printf(s, ",inode64");
+
         return 0;
 }