ocfs2: Add a mount option "coherency=*" to handle cluster coherency for O_DIRECT...

[GitHub/mt8127/android_kernel_alcatel_ttab.git] / fs / ocfs2 / super.c

diff --git a/fs/ocfs2/super.c b/fs/ocfs2/super.c
index 03a799fdd7402abb631ddd6575d250a5bd7a3a2d..9122d59f8127c6768d14ffe7c1ab48fa2a9e056a 100644 (file)
--- a/fs/ocfs2/super.c
+++ b/fs/ocfs2/super.c
@@ -145,8 +145,7 @@ static const struct super_operations ocfs2_sops = {
        .alloc_inode    = ocfs2_alloc_inode,
        .destroy_inode  = ocfs2_destroy_inode,
        .drop_inode     = ocfs2_drop_inode,
-       .clear_inode    = ocfs2_clear_inode,
-       .delete_inode   = ocfs2_delete_inode,
+       .evict_inode    = ocfs2_evict_inode,
        .sync_fs        = ocfs2_sync_fs,
        .put_super      = ocfs2_put_super,
        .remount_fs     = ocfs2_remount,
@@ -178,6 +177,8 @@ enum {
        Opt_noacl,
        Opt_usrquota,
        Opt_grpquota,
+       Opt_coherency_buffered,
+       Opt_coherency_full,
        Opt_resv_level,
        Opt_dir_resv_level,
        Opt_err,
@@ -206,6 +207,8 @@ static const match_table_t tokens = {
        {Opt_noacl, "noacl"},
        {Opt_usrquota, "usrquota"},
        {Opt_grpquota, "grpquota"},
+       {Opt_coherency_buffered, "coherency=buffered"},
+       {Opt_coherency_full, "coherency=full"},
        {Opt_resv_level, "resv_level=%u"},
        {Opt_dir_resv_level, "dir_resv_level=%u"},
        {Opt_err, NULL}
@@ -515,11 +518,11 @@ static void ocfs2_release_system_inodes(struct ocfs2_super *osb)
 
        mlog_entry_void();
 
-       for (i = 0; i < NUM_SYSTEM_INODES; i++) {
-               inode = osb->system_inodes[i];
+       for (i = 0; i < NUM_GLOBAL_SYSTEM_INODES; i++) {
+               inode = osb->global_system_inodes[i];
                if (inode) {
                        iput(inode);
-                       osb->system_inodes[i] = NULL;
+                       osb->global_system_inodes[i] = NULL;
                }
        }
 
@@ -535,6 +538,20 @@ static void ocfs2_release_system_inodes(struct ocfs2_super *osb)
                osb->root_inode = NULL;
        }
 
+       if (!osb->local_system_inodes)
+               goto out;
+
+       for (i = 0; i < NUM_LOCAL_SYSTEM_INODES * osb->max_slots; i++) {
+               if (osb->local_system_inodes[i]) {
+                       iput(osb->local_system_inodes[i]);
+                       osb->local_system_inodes[i] = NULL;
+               }
+       }
+
+       kfree(osb->local_system_inodes);
+       osb->local_system_inodes = NULL;
+
+out:
        mlog_exit(0);
 }
 
@@ -1439,6 +1456,12 @@ static int ocfs2_parse_options(struct super_block *sb,
                case Opt_grpquota:
                        mopt->mount_opt |= OCFS2_MOUNT_GRPQUOTA;
                        break;
+               case Opt_coherency_buffered:
+                       mopt->mount_opt |= OCFS2_MOUNT_COHERENCY_BUFFERED;
+                       break;
+               case Opt_coherency_full:
+                       mopt->mount_opt &= ~OCFS2_MOUNT_COHERENCY_BUFFERED;
+                       break;
                case Opt_acl:
                        mopt->mount_opt |= OCFS2_MOUNT_POSIX_ACL;
                        mopt->mount_opt &= ~OCFS2_MOUNT_NO_POSIX_ACL;
@@ -1537,6 +1560,11 @@ static int ocfs2_show_options(struct seq_file *s, struct vfsmount *mnt)
        if (opts & OCFS2_MOUNT_GRPQUOTA)
                seq_printf(s, ",grpquota");
 
+       if (opts & OCFS2_MOUNT_COHERENCY_BUFFERED)
+               seq_printf(s, ",coherency=buffered");
+       else
+               seq_printf(s, ",coherency=full");
+
        if (opts & OCFS2_MOUNT_NOUSERXATTR)
                seq_printf(s, ",nouser_xattr");
        else
@@ -1991,6 +2019,36 @@ static int ocfs2_setup_osb_uuid(struct ocfs2_super *osb, const unsigned char *uu
        return 0;
 }
 
+/* Make sure entire volume is addressable by our journal.  Requires
+   osb_clusters_at_boot to be valid and for the journal to have been
+   initialized by ocfs2_journal_init(). */
+static int ocfs2_journal_addressable(struct ocfs2_super *osb)
+{
+       int status = 0;
+       u64 max_block =
+               ocfs2_clusters_to_blocks(osb->sb,
+                                        osb->osb_clusters_at_boot) - 1;
+
+       /* 32-bit block number is always OK. */
+       if (max_block <= (u32)~0ULL)
+               goto out;
+
+       /* Volume is "huge", so see if our journal is new enough to
+          support it. */
+       if (!(OCFS2_HAS_COMPAT_FEATURE(osb->sb,
+                                      OCFS2_FEATURE_COMPAT_JBD2_SB) &&
+             jbd2_journal_check_used_features(osb->journal->j_journal, 0, 0,
+                                              JBD2_FEATURE_INCOMPAT_64BIT))) {
+               mlog(ML_ERROR, "The journal cannot address the entire volume. "
+                    "Enable the 'block64' journal option with tunefs.ocfs2");
+               status = -EFBIG;
+               goto out;
+       }
+
+ out:
+       return status;
+}
+
 static int ocfs2_initialize_super(struct super_block *sb,
                                  struct buffer_head *bh,
                                  int sector_size,
@@ -2003,6 +2061,7 @@ static int ocfs2_initialize_super(struct super_block *sb,
        struct ocfs2_journal *journal;
        __le32 uuid_net_key;
        struct ocfs2_super *osb;
+       u64 total_blocks;
 
        mlog_entry_void();
 
@@ -2061,6 +2120,15 @@ static int ocfs2_initialize_super(struct super_block *sb,
        snprintf(osb->dev_str, sizeof(osb->dev_str), "%u,%u",
                 MAJOR(osb->sb->s_dev), MINOR(osb->sb->s_dev));
 
+       osb->max_slots = le16_to_cpu(di->id2.i_super.s_max_slots);
+       if (osb->max_slots > OCFS2_MAX_SLOTS || osb->max_slots == 0) {
+               mlog(ML_ERROR, "Invalid number of node slots (%u)\n",
+                    osb->max_slots);
+               status = -EINVAL;
+               goto bail;
+       }
+       mlog(0, "max_slots for this device: %u\n", osb->max_slots);
+
        ocfs2_orphan_scan_init(osb);
 
        status = ocfs2_recovery_init(osb);
@@ -2099,15 +2167,6 @@ static int ocfs2_initialize_super(struct super_block *sb,
                goto bail;
        }
 
-       osb->max_slots = le16_to_cpu(di->id2.i_super.s_max_slots);
-       if (osb->max_slots > OCFS2_MAX_SLOTS || osb->max_slots == 0) {
-               mlog(ML_ERROR, "Invalid number of node slots (%u)\n",
-                    osb->max_slots);
-               status = -EINVAL;
-               goto bail;
-       }
-       mlog(0, "max_slots for this device: %u\n", osb->max_slots);
-
        osb->slot_recovery_generations =
                kcalloc(osb->max_slots, sizeof(*osb->slot_recovery_generations),
                        GFP_KERNEL);
@@ -2215,11 +2274,15 @@ static int ocfs2_initialize_super(struct super_block *sb,
                goto bail;
        }
 
-       if (ocfs2_clusters_to_blocks(osb->sb, le32_to_cpu(di->i_clusters) - 1)
-           > (u32)~0UL) {
-               mlog(ML_ERROR, "Volume might try to write to blocks beyond "
-                    "what jbd can address in 32 bits.\n");
-               status = -EINVAL;
+       total_blocks = ocfs2_clusters_to_blocks(osb->sb,
+                                               le32_to_cpu(di->i_clusters));
+
+       status = generic_check_addressable(osb->sb->s_blocksize_bits,
+                                          total_blocks);
+       if (status) {
+               mlog(ML_ERROR, "Volume too large "
+                    "to mount safely on this system");
+               status = -EFBIG;
                goto bail;
        }
 
@@ -2381,6 +2444,12 @@ static int ocfs2_check_volume(struct ocfs2_super *osb)
                goto finally;
        }
 
+       /* Now that journal has been initialized, check to make sure
+          entire volume is addressable. */
+       status = ocfs2_journal_addressable(osb);
+       if (status)
+               goto finally;
+
        /* If the journal was unmounted cleanly then we don't want to
         * recover anything. Otherwise, journal_load will do that
         * dirty work for us :) */