1 files changed, 565 insertions, 65 deletions

diff --git a/fs/ext4/super.c b/fs/ext4/super.c
index 7f47c366bf15..61182fe6254e 100644
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -26,7 +26,6 @@
 #include <linux/init.h>
 #include <linux/blkdev.h>
 #include <linux/parser.h>
-#include <linux/smp_lock.h>
 #include <linux/buffer_head.h>
 #include <linux/exportfs.h>
 #include <linux/vfs.h>
@@ -41,6 +40,9 @@
 #include <linux/crc16.h>
 #include <asm/uaccess.h>
 
+#include <linux/kthread.h>
+#include <linux/freezer.h>
+
 #include "ext4.h"
 #include "ext4_jbd2.h"
 #include "xattr.h"
@@ -50,8 +52,11 @@
 #define CREATE_TRACE_POINTS
 #include <trace/events/ext4.h>
 
-struct proc_dir_entry *ext4_proc_root;
+static struct proc_dir_entry *ext4_proc_root;
 static struct kset *ext4_kset;
+struct ext4_lazy_init *ext4_li_info;
+struct mutex ext4_li_mtx;
+struct ext4_features *ext4_feat;
 
 static int ext4_load_journal(struct super_block *, struct ext4_super_block *,
                              unsigned long journal_devnum);
@@ -68,14 +73,16 @@ static int ext4_statfs(struct dentry *dentry, struct kstatfs *buf);
 static int ext4_unfreeze(struct super_block *sb);
 static void ext4_write_super(struct super_block *sb);
 static int ext4_freeze(struct super_block *sb);
-static int ext4_get_sb(struct file_system_type *fs_type, int flags,
-                       const char *dev_name, void *data, struct vfsmount *mnt);
+static struct dentry *ext4_mount(struct file_system_type *fs_type, int flags,
+                       const char *dev_name, void *data);
+static void ext4_destroy_lazyinit_thread(void);
+static void ext4_unregister_li_request(struct super_block *sb);
 
 #if !defined(CONFIG_EXT3_FS) && !defined(CONFIG_EXT3_FS_MODULE) && defined(CONFIG_EXT4_USE_FOR_EXT23)
 static struct file_system_type ext3_fs_type = {
         .owner          = THIS_MODULE,
         .name           = "ext3",
-        .get_sb         = ext4_get_sb,
+        .mount          = ext4_mount,
         .kill_sb        = kill_block_super,
         .fs_flags       = FS_REQUIRES_DEV,
 };
@@ -702,13 +709,13 @@ static void ext4_put_super(struct super_block *sb)
         struct ext4_super_block *es = sbi->s_es;
         int i, err;
 
+        ext4_unregister_li_request(sb);
         dquot_disable(sb, -1, DQUOT_USAGE_ENABLED | DQUOT_LIMITS_ENABLED);
 
         flush_workqueue(sbi->dio_unwritten_wq);
         destroy_workqueue(sbi->dio_unwritten_wq);
 
         lock_super(sb);
-        lock_kernel();
         if (sb->s_dirt)
                 ext4_commit_super(sb, 1);
 
@@ -719,6 +726,7 @@ static void ext4_put_super(struct super_block *sb)
                         ext4_abort(sb, "Couldn't clean up the journal");
         }
 
+        del_timer(&sbi->s_err_report);
         ext4_release_system_zone(sb);
         ext4_mb_release(sb);
         ext4_ext_release(sb);
@@ -775,7 +783,6 @@ static void ext4_put_super(struct super_block *sb)
          * Now that we are completely done shutting down the
          * superblock, we need to actually destroy the kobject.
          */
-        unlock_kernel();
         unlock_super(sb);
         kobject_put(&sbi->s_kobj);
         wait_for_completion(&sbi->s_kobj_unregister);
@@ -821,12 +828,22 @@ static struct inode *ext4_alloc_inode(struct super_block *sb)
         ei->cur_aio_dio = NULL;
         ei->i_sync_tid = 0;
         ei->i_datasync_tid = 0;
+        atomic_set(&ei->i_ioend_count, 0);
 
         return &ei->vfs_inode;
 }
 
+static int ext4_drop_inode(struct inode *inode)
+{
+        int drop = generic_drop_inode(inode);
+
+        trace_ext4_drop_inode(inode, drop);
+        return drop;
+}
+
 static void ext4_destroy_inode(struct inode *inode)
 {
+        ext4_ioend_wait(inode);
         if (!list_empty(&(EXT4_I(inode)->i_orphan))) {
                 ext4_msg(inode->i_sb, KERN_ERR,
                          "Inode %lu (%p): orphan list check failed!",
@@ -1045,6 +1062,12 @@ static int ext4_show_options(struct seq_file *seq, struct vfsmount *vfs)
             !(def_mount_opts & EXT4_DEFM_BLOCK_VALIDITY))
                 seq_puts(seq, ",block_validity");
 
+        if (!test_opt(sb, INIT_INODE_TABLE))
+                seq_puts(seq, ",noinit_inode_table");
+        else if (sbi->s_li_wait_mult)
+                seq_printf(seq, ",init_inode_table=%u",
+                           (unsigned) sbi->s_li_wait_mult);
+
         ext4_show_quota_options(seq, sb);
 
         return 0;
@@ -1160,6 +1183,7 @@ static const struct super_operations ext4_sops = {
         .destroy_inode  = ext4_destroy_inode,
         .write_inode    = ext4_write_inode,
         .dirty_inode    = ext4_dirty_inode,
+        .drop_inode     = ext4_drop_inode,
         .evict_inode    = ext4_evict_inode,
         .put_super      = ext4_put_super,
         .sync_fs        = ext4_sync_fs,
@@ -1173,6 +1197,7 @@ static const struct super_operations ext4_sops = {
         .quota_write    = ext4_quota_write,
 #endif
         .bdev_try_to_free_page = bdev_try_to_free_page,
+        .trim_fs        = ext4_trim_fs
 };
 
 static const struct super_operations ext4_nojournal_sops = {
@@ -1180,6 +1205,7 @@ static const struct super_operations ext4_nojournal_sops = {
         .destroy_inode  = ext4_destroy_inode,
         .write_inode    = ext4_write_inode,
         .dirty_inode    = ext4_dirty_inode,
+        .drop_inode     = ext4_drop_inode,
         .evict_inode    = ext4_evict_inode,
         .write_super    = ext4_write_super,
         .put_super      = ext4_put_super,
@@ -1219,6 +1245,7 @@ enum {
         Opt_inode_readahead_blks, Opt_journal_ioprio,
         Opt_dioread_nolock, Opt_dioread_lock,
         Opt_discard, Opt_nodiscard,
+        Opt_init_inode_table, Opt_noinit_inode_table,
 };
 
 static const match_table_t tokens = {
@@ -1289,6 +1316,9 @@ static const match_table_t tokens = {
         {Opt_dioread_lock, "dioread_lock"},
         {Opt_discard, "discard"},
         {Opt_nodiscard, "nodiscard"},
+        {Opt_init_inode_table, "init_itable=%u"},
+        {Opt_init_inode_table, "init_itable"},
+        {Opt_noinit_inode_table, "noinit_itable"},
         {Opt_err, NULL},
 };
 
@@ -1759,6 +1789,20 @@ set_qf_format:
                 case Opt_dioread_lock:
                         clear_opt(sbi->s_mount_opt, DIOREAD_NOLOCK);
                         break;
+                case Opt_init_inode_table:
+                        set_opt(sbi->s_mount_opt, INIT_INODE_TABLE);
+                        if (args[0].from) {
+                                if (match_int(&args[0], &option))
+                                        return 0;
+                        } else
+                                option = EXT4_DEF_LI_WAIT_MULT;
+                        if (option < 0)
+                                return 0;
+                        sbi->s_li_wait_mult = option;
+                        break;
+                case Opt_noinit_inode_table:
+                        clear_opt(sbi->s_mount_opt, INIT_INODE_TABLE);
+                        break;
                 default:
                         ext4_msg(sb, KERN_ERR,
                                "Unrecognized mount option \"%s\" "
@@ -1942,7 +1986,8 @@ int ext4_group_desc_csum_verify(struct ext4_sb_info *sbi, __u32 block_group,
 }
 
 /* Called at mount-time, super-block is locked */
-static int ext4_check_descriptors(struct super_block *sb)
+static int ext4_check_descriptors(struct super_block *sb,
+                                  ext4_group_t *first_not_zeroed)
 {
         struct ext4_sb_info *sbi = EXT4_SB(sb);
         ext4_fsblk_t first_block = le32_to_cpu(sbi->s_es->s_first_data_block);
@@ -1951,7 +1996,7 @@ static int ext4_check_descriptors(struct super_block *sb)
         ext4_fsblk_t inode_bitmap;
         ext4_fsblk_t inode_table;
         int flexbg_flag = 0;
-        ext4_group_t i;
+        ext4_group_t i, grp = sbi->s_groups_count;
 
         if (EXT4_HAS_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_FLEX_BG))
                 flexbg_flag = 1;
@@ -1967,6 +2012,10 @@ static int ext4_check_descriptors(struct super_block *sb)
                         last_block = first_block +
                                 (EXT4_BLOCKS_PER_GROUP(sb) - 1);
 
+                if ((grp == sbi->s_groups_count) &&
+                   !(gdp->bg_flags & cpu_to_le16(EXT4_BG_INODE_ZEROED)))
+                        grp = i;
+
                 block_bitmap = ext4_block_bitmap(sb, gdp);
                 if (block_bitmap < first_block || block_bitmap > last_block) {
                         ext4_msg(sb, KERN_ERR, "ext4_check_descriptors: "
@@ -2004,6 +2053,8 @@ static int ext4_check_descriptors(struct super_block *sb)
                 if (!flexbg_flag)
                         first_block += EXT4_BLOCKS_PER_GROUP(sb);
         }
+        if (NULL != first_not_zeroed)
+                *first_not_zeroed = grp;
 
         ext4_free_blocks_count_set(sbi->s_es, ext4_count_free_blocks(sb));
         sbi->s_es->s_free_inodes_count =cpu_to_le32(ext4_count_free_inodes(sb));
@@ -2376,6 +2427,7 @@ static struct ext4_attr ext4_attr_##_name = {			\
 #define EXT4_ATTR(name, mode, show, store) \
 static struct ext4_attr ext4_attr_##name = __ATTR(name, mode, show, store)
 
+#define EXT4_INFO_ATTR(name) EXT4_ATTR(name, 0444, NULL, NULL)
 #define EXT4_RO_ATTR(name) EXT4_ATTR(name, 0444, name##_show, NULL)
 #define EXT4_RW_ATTR(name) EXT4_ATTR(name, 0644, name##_show, name##_store)
 #define EXT4_RW_ATTR_SBI_UI(name, elname)       \
@@ -2412,6 +2464,16 @@ static struct attribute *ext4_attrs[] = {
         NULL,
 };
 
+/* Features this copy of ext4 supports */
+EXT4_INFO_ATTR(lazy_itable_init);
+EXT4_INFO_ATTR(batched_discard);
+
+static struct attribute *ext4_feat_attrs[] = {
+        ATTR_LIST(lazy_itable_init),
+        ATTR_LIST(batched_discard),
+        NULL,
+};
+
 static ssize_t ext4_attr_show(struct kobject *kobj,
                               struct attribute *attr, char *buf)
 {
@@ -2440,7 +2502,6 @@ static void ext4_sb_release(struct kobject *kobj)
         complete(&sbi->s_kobj_unregister);
 }
 
-
 static const struct sysfs_ops ext4_attr_ops = {
         .show   = ext4_attr_show,
         .store  = ext4_attr_store,
@@ -2452,6 +2513,17 @@ static struct kobj_type ext4_ktype = {
         .release        = ext4_sb_release,
 };
 
+static void ext4_feat_release(struct kobject *kobj)
+{
+        complete(&ext4_feat->f_kobj_unregister);
+}
+
+static struct kobj_type ext4_feat_ktype = {
+        .default_attrs  = ext4_feat_attrs,
+        .sysfs_ops      = &ext4_attr_ops,
+        .release        = ext4_feat_release,
+};
+
 /*
  * Check whether this filesystem can be mounted based on
  * the features present and the RDONLY/RDWR mount requested.
@@ -2542,6 +2614,371 @@ static void print_daily_error_info(unsigned long arg)
         mod_timer(&sbi->s_err_report, jiffies + 24*60*60*HZ);  /* Once a day */
 }
 
+static void ext4_lazyinode_timeout(unsigned long data)
+{
+        struct task_struct *p = (struct task_struct *)data;
+        wake_up_process(p);
+}
+
+/* Find next suitable group and run ext4_init_inode_table */
+static int ext4_run_li_request(struct ext4_li_request *elr)
+{
+        struct ext4_group_desc *gdp = NULL;
+        ext4_group_t group, ngroups;
+        struct super_block *sb;
+        unsigned long timeout = 0;
+        int ret = 0;
+
+        sb = elr->lr_super;
+        ngroups = EXT4_SB(sb)->s_groups_count;
+
+        for (group = elr->lr_next_group; group < ngroups; group++) {
+                gdp = ext4_get_group_desc(sb, group, NULL);
+                if (!gdp) {
+                        ret = 1;
+                        break;
+                }
+
+                if (!(gdp->bg_flags & cpu_to_le16(EXT4_BG_INODE_ZEROED)))
+                        break;
+        }
+
+        if (group == ngroups)
+                ret = 1;
+
+        if (!ret) {
+                timeout = jiffies;
+                ret = ext4_init_inode_table(sb, group,
+                                            elr->lr_timeout ? 0 : 1);
+                if (elr->lr_timeout == 0) {
+                        timeout = jiffies - timeout;
+                        if (elr->lr_sbi->s_li_wait_mult)
+                                timeout *= elr->lr_sbi->s_li_wait_mult;
+                        else
+                                timeout *= 20;
+                        elr->lr_timeout = timeout;
+                }
+                elr->lr_next_sched = jiffies + elr->lr_timeout;
+                elr->lr_next_group = group + 1;
+        }
+
+        return ret;
+}
+
+/*
+ * Remove lr_request from the list_request and free the
+ * request tructure. Should be called with li_list_mtx held
+ */
+static void ext4_remove_li_request(struct ext4_li_request *elr)
+{
+        struct ext4_sb_info *sbi;
+
+        if (!elr)
+                return;
+
+        sbi = elr->lr_sbi;
+
+        list_del(&elr->lr_request);
+        sbi->s_li_request = NULL;
+        kfree(elr);
+}
+
+static void ext4_unregister_li_request(struct super_block *sb)
+{
+        struct ext4_li_request *elr = EXT4_SB(sb)->s_li_request;
+
+        if (!ext4_li_info)
+                return;
+
+        mutex_lock(&ext4_li_info->li_list_mtx);
+        ext4_remove_li_request(elr);
+        mutex_unlock(&ext4_li_info->li_list_mtx);
+}
+
+/*
+ * This is the function where ext4lazyinit thread lives. It walks
+ * through the request list searching for next scheduled filesystem.
+ * When such a fs is found, run the lazy initialization request
+ * (ext4_rn_li_request) and keep track of the time spend in this
+ * function. Based on that time we compute next schedule time of
+ * the request. When walking through the list is complete, compute
+ * next waking time and put itself into sleep.
+ */
+static int ext4_lazyinit_thread(void *arg)
+{
+        struct ext4_lazy_init *eli = (struct ext4_lazy_init *)arg;
+        struct list_head *pos, *n;
+        struct ext4_li_request *elr;
+        unsigned long next_wakeup;
+        DEFINE_WAIT(wait);
+
+        BUG_ON(NULL == eli);
+
+        eli->li_timer.data = (unsigned long)current;
+        eli->li_timer.function = ext4_lazyinode_timeout;
+
+        eli->li_task = current;
+        wake_up(&eli->li_wait_task);
+
+cont_thread:
+        while (true) {
+                next_wakeup = MAX_JIFFY_OFFSET;
+
+                mutex_lock(&eli->li_list_mtx);
+                if (list_empty(&eli->li_request_list)) {
+                        mutex_unlock(&eli->li_list_mtx);
+                        goto exit_thread;
+                }
+
+                list_for_each_safe(pos, n, &eli->li_request_list) {
+                        elr = list_entry(pos, struct ext4_li_request,
+                                         lr_request);
+
+                        if (time_after_eq(jiffies, elr->lr_next_sched)) {
+                                if (ext4_run_li_request(elr) != 0) {
+                                        /* error, remove the lazy_init job */
+                                        ext4_remove_li_request(elr);
+                                        continue;
+                                }
+                        }
+
+                        if (time_before(elr->lr_next_sched, next_wakeup))
+                                next_wakeup = elr->lr_next_sched;
+                }
+                mutex_unlock(&eli->li_list_mtx);
+
+                if (freezing(current))
+                        refrigerator();
+
+                if ((time_after_eq(jiffies, next_wakeup)) ||
+                    (MAX_JIFFY_OFFSET == next_wakeup)) {
+                        cond_resched();
+                        continue;
+                }
+
+                eli->li_timer.expires = next_wakeup;
+                add_timer(&eli->li_timer);
+                prepare_to_wait(&eli->li_wait_daemon, &wait,
+                                TASK_INTERRUPTIBLE);
+                if (time_before(jiffies, next_wakeup))
+                        schedule();
+                finish_wait(&eli->li_wait_daemon, &wait);
+        }
+
+exit_thread:
+        /*
+         * It looks like the request list is empty, but we need
+         * to check it under the li_list_mtx lock, to prevent any
+         * additions into it, and of course we should lock ext4_li_mtx
+         * to atomically free the list and ext4_li_info, because at
+         * this point another ext4 filesystem could be registering
+         * new one.
+         */
+        mutex_lock(&ext4_li_mtx);
+        mutex_lock(&eli->li_list_mtx);
+        if (!list_empty(&eli->li_request_list)) {
+                mutex_unlock(&eli->li_list_mtx);
+                mutex_unlock(&ext4_li_mtx);
+                goto cont_thread;
+        }
+        mutex_unlock(&eli->li_list_mtx);
+        del_timer_sync(&ext4_li_info->li_timer);
+        eli->li_task = NULL;
+        wake_up(&eli->li_wait_task);
+
+        kfree(ext4_li_info);
+        ext4_li_info = NULL;
+        mutex_unlock(&ext4_li_mtx);
+
+        return 0;
+}
+
+static void ext4_clear_request_list(void)
+{
+        struct list_head *pos, *n;
+        struct ext4_li_request *elr;
+
+        mutex_lock(&ext4_li_info->li_list_mtx);
+        if (list_empty(&ext4_li_info->li_request_list))
+                return;
+
+        list_for_each_safe(pos, n, &ext4_li_info->li_request_list) {
+                elr = list_entry(pos, struct ext4_li_request,
+                                 lr_request);
+                ext4_remove_li_request(elr);
+        }
+        mutex_unlock(&ext4_li_info->li_list_mtx);
+}
+
+static int ext4_run_lazyinit_thread(void)
+{
+        struct task_struct *t;
+
+        t = kthread_run(ext4_lazyinit_thread, ext4_li_info, "ext4lazyinit");
+        if (IS_ERR(t)) {
+                int err = PTR_ERR(t);
+                ext4_clear_request_list();
+                del_timer_sync(&ext4_li_info->li_timer);
+                kfree(ext4_li_info);
+                ext4_li_info = NULL;
+                printk(KERN_CRIT "EXT4: error %d creating inode table "
+                                 "initialization thread\n",
+                                 err);
+                return err;
+        }
+        ext4_li_info->li_state |= EXT4_LAZYINIT_RUNNING;
+
+        wait_event(ext4_li_info->li_wait_task, ext4_li_info->li_task != NULL);
+        return 0;
+}
+
+/*
+ * Check whether it make sense to run itable init. thread or not.
+ * If there is at least one uninitialized inode table, return
+ * corresponding group number, else the loop goes through all
+ * groups and return total number of groups.
+ */
+static ext4_group_t ext4_has_uninit_itable(struct super_block *sb)
+{
+        ext4_group_t group, ngroups = EXT4_SB(sb)->s_groups_count;
+        struct ext4_group_desc *gdp = NULL;
+
+        for (group = 0; group < ngroups; group++) {
+                gdp = ext4_get_group_desc(sb, group, NULL);
+                if (!gdp)
+                        continue;
+
+                if (!(gdp->bg_flags & cpu_to_le16(EXT4_BG_INODE_ZEROED)))
+                        break;
+        }
+
+        return group;
+}
+
+static int ext4_li_info_new(void)
+{
+        struct ext4_lazy_init *eli = NULL;
+
+        eli = kzalloc(sizeof(*eli), GFP_KERNEL);
+        if (!eli)
+                return -ENOMEM;
+
+        eli->li_task = NULL;
+        INIT_LIST_HEAD(&eli->li_request_list);
+        mutex_init(&eli->li_list_mtx);
+
+        init_waitqueue_head(&eli->li_wait_daemon);
+        init_waitqueue_head(&eli->li_wait_task);
+        init_timer(&eli->li_timer);
+        eli->li_state |= EXT4_LAZYINIT_QUIT;
+
+        ext4_li_info = eli;
+
+        return 0;
+}
+
+static struct ext4_li_request *ext4_li_request_new(struct super_block *sb,
+                                            ext4_group_t start)
+{
+        struct ext4_sb_info *sbi = EXT4_SB(sb);
+        struct ext4_li_request *elr;
+        unsigned long rnd;
+
+        elr = kzalloc(sizeof(*elr), GFP_KERNEL);
+        if (!elr)
+                return NULL;
+
+        elr->lr_super = sb;
+        elr->lr_sbi = sbi;
+        elr->lr_next_group = start;
+
+        /*
+         * Randomize first schedule time of the request to
+         * spread the inode table initialization requests
+         * better.
+         */
+        get_random_bytes(&rnd, sizeof(rnd));
+        elr->lr_next_sched = jiffies + (unsigned long)rnd %
+                             (EXT4_DEF_LI_MAX_START_DELAY * HZ);
+
+        return elr;
+}
+
+static int ext4_register_li_request(struct super_block *sb,
+                                    ext4_group_t first_not_zeroed)
+{
+        struct ext4_sb_info *sbi = EXT4_SB(sb);
+        struct ext4_li_request *elr;
+        ext4_group_t ngroups = EXT4_SB(sb)->s_groups_count;
+        int ret;
+
+        if (sbi->s_li_request != NULL)
+                return 0;
+
+        if (first_not_zeroed == ngroups ||
+            (sb->s_flags & MS_RDONLY) ||
+            !test_opt(sb, INIT_INODE_TABLE)) {
+                sbi->s_li_request = NULL;
+                return 0;
+        }
+
+        if (first_not_zeroed == ngroups) {
+                sbi->s_li_request = NULL;
+                return 0;
+        }
+
+        elr = ext4_li_request_new(sb, first_not_zeroed);
+        if (!elr)
+                return -ENOMEM;
+
+        mutex_lock(&ext4_li_mtx);
+
+        if (NULL == ext4_li_info) {
+                ret = ext4_li_info_new();
+                if (ret)
+                        goto out;
+        }
+
+        mutex_lock(&ext4_li_info->li_list_mtx);
+        list_add(&elr->lr_request, &ext4_li_info->li_request_list);
+        mutex_unlock(&ext4_li_info->li_list_mtx);
+
+        sbi->s_li_request = elr;
+
+        if (!(ext4_li_info->li_state & EXT4_LAZYINIT_RUNNING)) {
+                ret = ext4_run_lazyinit_thread();
+                if (ret)
+                        goto out;
+        }
+out:
+        mutex_unlock(&ext4_li_mtx);
+        if (ret)
+                kfree(elr);
+        return ret;
+}
+
+/*
+ * We do not need to lock anything since this is called on
+ * module unload.
+ */
+static void ext4_destroy_lazyinit_thread(void)
+{
+        /*
+         * If thread exited earlier
+         * there's nothing to be done.
+         */
+        if (!ext4_li_info)
+                return;
+
+        ext4_clear_request_list();
+
+        while (ext4_li_info->li_task) {
+                wake_up(&ext4_li_info->li_wait_daemon);
+                wait_event(ext4_li_info->li_wait_task,
+                           ext4_li_info->li_task == NULL);
+        }
+}
+
 static int ext4_fill_super(struct super_block *sb, void *data, int silent)
                                 __releases(kernel_lock)
                                 __acquires(kernel_lock)
@@ -2567,6 +3004,7 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
         __u64 blocks_count;
         int err;
         unsigned int journal_ioprio = DEFAULT_JOURNAL_IOPRIO;
+        ext4_group_t first_not_zeroed;
 
         sbi = kzalloc(sizeof(*sbi), GFP_KERNEL);
         if (!sbi)
@@ -2588,8 +3026,6 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
                 sbi->s_sectors_written_start =
                         part_stat_read(sb->s_bdev->bd_part, sectors[1]);
 
-        unlock_kernel();
-
         /* Cleanup superblock name */
         for (cp = sb->s_id; (cp = strchr(cp, '/'));)
                 *cp = '!';
@@ -2629,6 +3065,7 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
 
         /* Set defaults before we parse the mount options */
         def_mount_opts = le32_to_cpu(es->s_default_mount_opts);
+        set_opt(sbi->s_mount_opt, INIT_INODE_TABLE);
         if (def_mount_opts & EXT4_DEFM_DEBUG)
                 set_opt(sbi->s_mount_opt, DEBUG);
         if (def_mount_opts & EXT4_DEFM_BSDGROUPS) {
@@ -2906,7 +3343,7 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
                         goto failed_mount2;
                 }
         }
-        if (!ext4_check_descriptors(sb)) {
+        if (!ext4_check_descriptors(sb, &first_not_zeroed)) {
                 ext4_msg(sb, KERN_ERR, "group descriptors corrupted!");
                 goto failed_mount2;
         }
@@ -2922,6 +3359,24 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
         get_random_bytes(&sbi->s_next_generation, sizeof(u32));
         spin_lock_init(&sbi->s_next_gen_lock);
 
+        err = percpu_counter_init(&sbi->s_freeblocks_counter,
+                        ext4_count_free_blocks(sb));
+        if (!err) {
+                err = percpu_counter_init(&sbi->s_freeinodes_counter,
+                                ext4_count_free_inodes(sb));
+        }
+        if (!err) {
+                err = percpu_counter_init(&sbi->s_dirs_counter,
+                                ext4_count_dirs(sb));
+        }
+        if (!err) {
+                err = percpu_counter_init(&sbi->s_dirtyblocks_counter, 0);
+        }
+        if (err) {
+                ext4_msg(sb, KERN_ERR, "insufficient memory");
+                goto failed_mount3;
+        }
+
         sbi->s_stripe = ext4_get_stripe_size(sbi);
         sbi->s_max_writeback_mb_bump = 128;
 
@@ -3020,22 +3475,19 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
         }
         set_task_ioprio(sbi->s_journal->j_task, journal_ioprio);
 
-no_journal:
-        err = percpu_counter_init(&sbi->s_freeblocks_counter,
-                                  ext4_count_free_blocks(sb));
-        if (!err)
-                err = percpu_counter_init(&sbi->s_freeinodes_counter,
-                                          ext4_count_free_inodes(sb));
-        if (!err)
-                err = percpu_counter_init(&sbi->s_dirs_counter,
-                                          ext4_count_dirs(sb));
-        if (!err)
-                err = percpu_counter_init(&sbi->s_dirtyblocks_counter, 0);
-        if (err) {
-                ext4_msg(sb, KERN_ERR, "insufficient memory");
-                goto failed_mount_wq;
-        }
+        /*
+         * The journal may have updated the bg summary counts, so we
+         * need to update the global counters.
+         */
+        percpu_counter_set(&sbi->s_freeblocks_counter,
+                           ext4_count_free_blocks(sb));
+        percpu_counter_set(&sbi->s_freeinodes_counter,
+                           ext4_count_free_inodes(sb));
+        percpu_counter_set(&sbi->s_dirs_counter,
+                           ext4_count_dirs(sb));
+        percpu_counter_set(&sbi->s_dirtyblocks_counter, 0);
 
+no_journal:
         EXT4_SB(sb)->dio_unwritten_wq = create_workqueue("ext4-dio-unwritten");
         if (!EXT4_SB(sb)->dio_unwritten_wq) {
                 printk(KERN_ERR "EXT4-fs: failed to create DIO workqueue\n");
@@ -3127,6 +3579,10 @@ no_journal:
                 goto failed_mount4;
         }
 
+        err = ext4_register_li_request(sb, first_not_zeroed);
+        if (err)
+                goto failed_mount4;
+
         sbi->s_kobj.kset = ext4_kset;
         init_completion(&sbi->s_kobj_unregister);
         err = kobject_init_and_add(&sbi->s_kobj, &ext4_ktype, NULL,
@@ -3164,7 +3620,6 @@ no_journal:
         if (es->s_error_count)
                 mod_timer(&sbi->s_err_report, jiffies + 300*HZ); /* 5 minutes */
 
-        lock_kernel();
         kfree(orig_data);
         return 0;
 
@@ -3182,10 +3637,6 @@ failed_mount_wq:
                 jbd2_journal_destroy(sbi->s_journal);
                 sbi->s_journal = NULL;
         }
-        percpu_counter_destroy(&sbi->s_freeblocks_counter);
-        percpu_counter_destroy(&sbi->s_freeinodes_counter);
-        percpu_counter_destroy(&sbi->s_dirs_counter);
-        percpu_counter_destroy(&sbi->s_dirtyblocks_counter);
 failed_mount3:
         if (sbi->s_flex_groups) {
                 if (is_vmalloc_addr(sbi->s_flex_groups))
@@ -3193,6 +3644,10 @@ failed_mount3:
                 else
                         kfree(sbi->s_flex_groups);
         }
+        percpu_counter_destroy(&sbi->s_freeblocks_counter);
+        percpu_counter_destroy(&sbi->s_freeinodes_counter);
+        percpu_counter_destroy(&sbi->s_dirs_counter);
+        percpu_counter_destroy(&sbi->s_dirtyblocks_counter);
 failed_mount2:
         for (i = 0; i < db_count; i++)
                 brelse(sbi->s_group_desc[i]);
@@ -3211,7 +3666,6 @@ out_fail:
         sb->s_fs_info = NULL;
         kfree(sbi->s_blockgroup_lock);
         kfree(sbi);
-        lock_kernel();
 out_free_orig:
         kfree(orig_data);
         return ret;
@@ -3468,7 +3922,7 @@ static int ext4_load_journal(struct super_block *sb,
         EXT4_SB(sb)->s_journal = journal;
         ext4_clear_journal_err(sb, es);
 
-        if (journal_devnum &&
+        if (!really_read_only && journal_devnum &&
             journal_devnum != le32_to_cpu(es->s_journal_dev)) {
                 es->s_journal_dev = cpu_to_le32(journal_devnum);
 
@@ -3522,9 +3976,10 @@ static int ext4_commit_super(struct super_block *sb, int sync)
                 es->s_kbytes_written =
                         cpu_to_le64(EXT4_SB(sb)->s_kbytes_written);
         ext4_free_blocks_count_set(es, percpu_counter_sum_positive(
-                                        &EXT4_SB(sb)->s_freeblocks_counter));
-        es->s_free_inodes_count = cpu_to_le32(percpu_counter_sum_positive(
-                                        &EXT4_SB(sb)->s_freeinodes_counter));
+                                           &EXT4_SB(sb)->s_freeblocks_counter));
+        es->s_free_inodes_count =
+                cpu_to_le32(percpu_counter_sum_positive(
+                                &EXT4_SB(sb)->s_freeinodes_counter));
         sb->s_dirt = 0;
         BUFFER_TRACE(sbh, "marking dirty");
         mark_buffer_dirty(sbh);
@@ -3720,8 +4175,6 @@ static int ext4_remount(struct super_block *sb, int *flags, char *data)
 #endif
         char *orig_data = kstrdup(data, GFP_KERNEL);
 
-        lock_kernel();
-
         /* Store the original options */
         lock_super(sb);
         old_sb_flags = sb->s_flags;
@@ -3844,6 +4297,19 @@ static int ext4_remount(struct super_block *sb, int *flags, char *data)
                         enable_quota = 1;
                 }
         }
+
+        /*
+         * Reinitialize lazy itable initialization thread based on
+         * current settings
+         */
+        if ((sb->s_flags & MS_RDONLY) || !test_opt(sb, INIT_INODE_TABLE))
+                ext4_unregister_li_request(sb);
+        else {
+                ext4_group_t first_not_zeroed;
+                first_not_zeroed = ext4_has_uninit_itable(sb);
+                ext4_register_li_request(sb, first_not_zeroed);
+        }
+
         ext4_setup_system_zone(sb);
         if (sbi->s_journal == NULL)
                 ext4_commit_super(sb, 1);
@@ -3856,7 +4322,6 @@ static int ext4_remount(struct super_block *sb, int *flags, char *data)
                         kfree(old_opts.s_qf_names[i]);
 #endif
         unlock_super(sb);
-        unlock_kernel();
         if (enable_quota)
                 dquot_resume(sb, -1);
 
@@ -3882,7 +4347,6 @@ restore_opts:
         }
 #endif
         unlock_super(sb);
-        unlock_kernel();
         kfree(orig_data);
         return err;
 }
@@ -4116,12 +4580,10 @@ static int ext4_quota_on(struct super_block *sb, int type, int format_id,
 
 static int ext4_quota_off(struct super_block *sb, int type)
 {
-        /* Force all delayed allocation blocks to be allocated */
-        if (test_opt(sb, DELALLOC)) {
-                down_read(&sb->s_umount);
+        /* Force all delayed allocation blocks to be allocated.
+         * Caller already holds s_umount sem */
+        if (test_opt(sb, DELALLOC))
                 sync_filesystem(sb);
-                up_read(&sb->s_umount);
-        }
 
         return dquot_quota_off(sb, type);
 }
@@ -4227,17 +4689,17 @@ out:
 
 #endif
 
-static int ext4_get_sb(struct file_system_type *fs_type, int flags,
-                       const char *dev_name, void *data, struct vfsmount *mnt)
+static struct dentry *ext4_mount(struct file_system_type *fs_type, int flags,
+                       const char *dev_name, void *data)
 {
-        return get_sb_bdev(fs_type, flags, dev_name, data, ext4_fill_super,mnt);
+        return mount_bdev(fs_type, flags, dev_name, data, ext4_fill_super);
 }
 
 #if !defined(CONFIG_EXT2_FS) && !defined(CONFIG_EXT2_FS_MODULE) && defined(CONFIG_EXT4_USE_FOR_EXT23)
 static struct file_system_type ext2_fs_type = {
         .owner          = THIS_MODULE,
         .name           = "ext2",
-        .get_sb         = ext4_get_sb,
+        .mount          = ext4_mount,
         .kill_sb        = kill_block_super,
         .fs_flags       = FS_REQUIRES_DEV,
 };
@@ -4282,28 +4744,58 @@ static inline void unregister_as_ext3(void) { }
 static struct file_system_type ext4_fs_type = {
         .owner          = THIS_MODULE,
         .name           = "ext4",
-        .get_sb         = ext4_get_sb,
+        .mount          = ext4_mount,
         .kill_sb        = kill_block_super,
         .fs_flags       = FS_REQUIRES_DEV,
 };
 
-static int __init init_ext4_fs(void)
+int __init ext4_init_feat_adverts(void)
+{
+        struct ext4_features *ef;
+        int ret = -ENOMEM;
+
+        ef = kzalloc(sizeof(struct ext4_features), GFP_KERNEL);
+        if (!ef)
+                goto out;
+
+        ef->f_kobj.kset = ext4_kset;
+        init_completion(&ef->f_kobj_unregister);
+        ret = kobject_init_and_add(&ef->f_kobj, &ext4_feat_ktype, NULL,
+                                   "features");
+        if (ret) {
+                kfree(ef);
+                goto out;
+        }
+
+        ext4_feat = ef;
+        ret = 0;
+out:
+        return ret;
+}
+
+static int __init ext4_init_fs(void)
 {
         int err;
 
         ext4_check_flag_values();
-        err = init_ext4_system_zone();
+        err = ext4_init_pageio();
         if (err)
                 return err;
+        err = ext4_init_system_zone();
+        if (err)
+                goto out5;
         ext4_kset = kset_create_and_add("ext4", NULL, fs_kobj);
         if (!ext4_kset)
                 goto out4;
         ext4_proc_root = proc_mkdir("fs/ext4", NULL);
-        err = init_ext4_mballoc();
+
+        err = ext4_init_feat_adverts();
+
+        err = ext4_init_mballoc();
         if (err)
                 goto out3;
 
-        err = init_ext4_xattr();
+        err = ext4_init_xattr();
         if (err)
                 goto out2;
         err = init_inodecache();
@@ -4314,38 +4806,46 @@ static int __init init_ext4_fs(void)
         err = register_filesystem(&ext4_fs_type);
         if (err)
                 goto out;
+
+        ext4_li_info = NULL;
+        mutex_init(&ext4_li_mtx);
         return 0;
 out:
         unregister_as_ext2();
         unregister_as_ext3();
         destroy_inodecache();
 out1:
-        exit_ext4_xattr();
+        ext4_exit_xattr();
 out2:
-        exit_ext4_mballoc();
+        ext4_exit_mballoc();
 out3:
+        kfree(ext4_feat);
         remove_proc_entry("fs/ext4", NULL);
         kset_unregister(ext4_kset);
 out4:
-        exit_ext4_system_zone();
+        ext4_exit_system_zone();
+out5:
+        ext4_exit_pageio();
         return err;
 }
 
-static void __exit exit_ext4_fs(void)
+static void __exit ext4_exit_fs(void)
 {
+        ext4_destroy_lazyinit_thread();
         unregister_as_ext2();
         unregister_as_ext3();
         unregister_filesystem(&ext4_fs_type);
         destroy_inodecache();
-        exit_ext4_xattr();
-        exit_ext4_mballoc();
+        ext4_exit_xattr();
+        ext4_exit_mballoc();
         remove_proc_entry("fs/ext4", NULL);
         kset_unregister(ext4_kset);
-        exit_ext4_system_zone();
+        ext4_exit_system_zone();
+        ext4_exit_pageio();
 }
 
 MODULE_AUTHOR("Remy Card, Stephen Tweedie, Andrew Morton, Andreas Dilger, Theodore Ts'o and others");
 MODULE_DESCRIPTION("Fourth Extended Filesystem");
 MODULE_LICENSE("GPL");
-module_init(init_ext4_fs)
-module_exit(exit_ext4_fs)
+module_init(ext4_init_fs)
+module_exit(ext4_exit_fs)