Merge branch 'for_linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tytso/ext4

* 'for_linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tytso/ext4:
  ext4: fix data corruption regression by reverting commit 6de9843dab3f
  ext4: Allow indirect-block file to grow the file size to max file size
  ext4: allow an active handle to be started when freezing
  ext4: sync the directory inode in ext4_sync_parent()
  ext4: init timer earlier to avoid a kernel panic in __save_error_info
  jbd2: fix potential memory leak on transaction commit
  ext4: fix a double free in ext4_register_li_request
  ext4: fix credits computing for indirect mapped files
  ext4: remove unnecessary [cm]time update of quota file
  jbd2: move bdget out of critical section

6 files changed, 102 insertions, 35 deletions

diff --git a/fs/ext4/ext4_jbd2.h b/fs/ext4/ext4_jbd2.h
index e25e99bf7ee1..d0f53538a57f 100644
--- a/fs/ext4/ext4_jbd2.h
+++ b/fs/ext4/ext4_jbd2.h
@@ -86,8 +86,8 @@
 
 #ifdef CONFIG_QUOTA
 /* Amount of blocks needed for quota update - we know that the structure was
- * allocated so we need to update only inode+data */
-#define EXT4_QUOTA_TRANS_BLOCKS(sb) (test_opt(sb, QUOTA) ? 2 : 0)
+ * allocated so we need to update only data block */
+#define EXT4_QUOTA_TRANS_BLOCKS(sb) (test_opt(sb, QUOTA) ? 1 : 0)
 /* Amount of blocks needed for quota insert/delete - we do some block writes
  * but inode, sb and group updates are done only once */
 #define EXT4_QUOTA_INIT_BLOCKS(sb) (test_opt(sb, QUOTA) ? (DQUOT_INIT_ALLOC*\
diff --git a/fs/ext4/fsync.c b/fs/ext4/fsync.c
index 4673bc05274f..e9473cbe80df 100644
--- a/fs/ext4/fsync.c
+++ b/fs/ext4/fsync.c
@@ -125,9 +125,11 @@ extern int ext4_flush_completed_IO(struct inode *inode)
  * the parent directory's parent as well, and so on recursively, if
  * they are also freshly created.
  */
-static void ext4_sync_parent(struct inode *inode)
+static int ext4_sync_parent(struct inode *inode)
 {
+        struct writeback_control wbc;
         struct dentry *dentry = NULL;
+        int ret = 0;
 
         while (inode && ext4_test_inode_state(inode, EXT4_STATE_NEWENTRY)) {
                 ext4_clear_inode_state(inode, EXT4_STATE_NEWENTRY);
@@ -136,8 +138,17 @@ static void ext4_sync_parent(struct inode *inode)
                 if (!dentry || !dentry->d_parent || !dentry->d_parent->d_inode)
                         break;
                 inode = dentry->d_parent->d_inode;
-                sync_mapping_buffers(inode->i_mapping);
+                ret = sync_mapping_buffers(inode->i_mapping);
+                if (ret)
+                        break;
+                memset(&wbc, 0, sizeof(wbc));
+                wbc.sync_mode = WB_SYNC_ALL;
+                wbc.nr_to_write = 0;         /* only write out the inode */
+                ret = sync_inode(inode, &wbc);
+                if (ret)
+                        break;
         }
+        return ret;
 }
 
 /*
@@ -176,7 +187,7 @@ int ext4_sync_file(struct file *file, int datasync)
         if (!journal) {
                 ret = generic_file_fsync(file, datasync);
                 if (!ret && !list_empty(&inode->i_dentry))
-                        ext4_sync_parent(inode);
+                        ret = ext4_sync_parent(inode);
                 goto out;
         }
 
diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index ad8e303c0d29..f2fa5e8a582c 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -2502,6 +2502,7 @@ static int ext4_da_get_block_prep(struct inode *inode, sector_t iblock,
                  * for partial write.
                  */
                 set_buffer_new(bh);
+                set_buffer_mapped(bh);
         }
         return 0;
 }
@@ -4429,8 +4430,8 @@ void ext4_truncate(struct inode *inode)
         Indirect chain[4];
         Indirect *partial;
         __le32 nr = 0;
-        int n;
-        ext4_lblk_t last_block;
+        int n = 0;
+        ext4_lblk_t last_block, max_block;
         unsigned blocksize = inode->i_sb->s_blocksize;
 
         trace_ext4_truncate_enter(inode);
@@ -4455,14 +4456,18 @@ void ext4_truncate(struct inode *inode)
 
         last_block = (inode->i_size + blocksize-1)
                                         >> EXT4_BLOCK_SIZE_BITS(inode->i_sb);
+        max_block = (EXT4_SB(inode->i_sb)->s_bitmap_maxbytes + blocksize-1)
+                                        >> EXT4_BLOCK_SIZE_BITS(inode->i_sb);
 
         if (inode->i_size & (blocksize - 1))
                 if (ext4_block_truncate_page(handle, mapping, inode->i_size))
                         goto out_stop;
 
-        n = ext4_block_to_path(inode, last_block, offsets, NULL);
-        if (n == 0)
-                goto out_stop;  /* error */
+        if (last_block != max_block) {
+                n = ext4_block_to_path(inode, last_block, offsets, NULL);
+                if (n == 0)
+                        goto out_stop;  /* error */
+        }
 
         /*
          * OK.  This truncate is going to happen.  We add the inode to the
@@ -4493,7 +4498,13 @@ void ext4_truncate(struct inode *inode)
          */
         ei->i_disksize = inode->i_size;
 
-        if (n == 1) {           /* direct blocks */
+        if (last_block == max_block) {
+                /*
+                 * It is unnecessary to free any data blocks if last_block is
+                 * equal to the indirect block limit.
+                 */
+                goto out_unlock;
+        } else if (n == 1) {            /* direct blocks */
                 ext4_free_data(handle, inode, NULL, i_data+offsets[0],
                                i_data + EXT4_NDIR_BLOCKS);
                 goto do_indirects;
@@ -4553,6 +4564,7 @@ do_indirects:
                 ;
         }
 
+out_unlock:
         up_write(&ei->i_data_sem);
         inode->i_mtime = inode->i_ctime = ext4_current_time(inode);
         ext4_mark_inode_dirty(handle, inode);
@@ -5398,13 +5410,12 @@ static int ext4_indirect_trans_blocks(struct inode *inode, int nrblocks,
         /* if nrblocks are contiguous */
         if (chunk) {
                 /*
-                 * With N contiguous data blocks, it need at most
-                 * N/EXT4_ADDR_PER_BLOCK(inode->i_sb) indirect blocks
-                 * 2 dindirect blocks
-                 * 1 tindirect block
+                 * With N contiguous data blocks, we need at most
+                 * N/EXT4_ADDR_PER_BLOCK(inode->i_sb) + 1 indirect blocks,
+                 * 2 dindirect blocks, and 1 tindirect block
                  */
-                indirects = nrblocks / EXT4_ADDR_PER_BLOCK(inode->i_sb);
-                return indirects + 3;
+                return DIV_ROUND_UP(nrblocks,
+                                    EXT4_ADDR_PER_BLOCK(inode->i_sb)) + 4;
         }
         /*
          * if nrblocks are not contiguous, worse case, each block touch
diff --git a/fs/ext4/super.c b/fs/ext4/super.c
index 056474b7b8e0..8553dfb310af 100644
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -242,27 +242,44 @@ static void ext4_put_nojournal(handle_t *handle)
  * journal_end calls result in the superblock being marked dirty, so
  * that sync() will call the filesystem's write_super callback if
  * appropriate.
+ *
+ * To avoid j_barrier hold in userspace when a user calls freeze(),
+ * ext4 prevents a new handle from being started by s_frozen, which
+ * is in an upper layer.
  */
 handle_t *ext4_journal_start_sb(struct super_block *sb, int nblocks)
 {
         journal_t *journal;
+        handle_t  *handle;
 
         if (sb->s_flags & MS_RDONLY)
                 return ERR_PTR(-EROFS);
 
-        vfs_check_frozen(sb, SB_FREEZE_TRANS);
-        /* Special case here: if the journal has aborted behind our
-         * backs (eg. EIO in the commit thread), then we still need to
-         * take the FS itself readonly cleanly. */
         journal = EXT4_SB(sb)->s_journal;
-        if (journal) {
-                if (is_journal_aborted(journal)) {
-                        ext4_abort(sb, "Detected aborted journal");
-                        return ERR_PTR(-EROFS);
-                }
-                return jbd2_journal_start(journal, nblocks);
+        handle = ext4_journal_current_handle();
+
+        /*
+         * If a handle has been started, it should be allowed to
+         * finish, otherwise deadlock could happen between freeze
+         * and others(e.g. truncate) due to the restart of the
+         * journal handle if the filesystem is forzen and active
+         * handles are not stopped.
+         */
+        if (!handle)
+                vfs_check_frozen(sb, SB_FREEZE_TRANS);
+
+        if (!journal)
+                return ext4_get_nojournal();
+        /*
+         * Special case here: if the journal has aborted behind our
+         * backs (eg. EIO in the commit thread), then we still need to
+         * take the FS itself readonly cleanly.
+         */
+        if (is_journal_aborted(journal)) {
+                ext4_abort(sb, "Detected aborted journal");
+                return ERR_PTR(-EROFS);
         }
-        return ext4_get_nojournal();
+        return jbd2_journal_start(journal, nblocks);
 }
 
 /*
@@ -2975,6 +2992,12 @@ static int ext4_register_li_request(struct super_block *sb,
         mutex_unlock(&ext4_li_info->li_list_mtx);
 
         sbi->s_li_request = elr;
+        /*
+         * set elr to NULL here since it has been inserted to
+         * the request_list and the removal and free of it is
+         * handled by ext4_clear_request_list from now on.
+         */
+        elr = NULL;
 
         if (!(ext4_li_info->li_state & EXT4_LAZYINIT_RUNNING)) {
                 ret = ext4_run_lazyinit_thread();
@@ -3385,6 +3408,10 @@ 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);
 
+        init_timer(&sbi->s_err_report);
+        sbi->s_err_report.function = print_daily_error_info;
+        sbi->s_err_report.data = (unsigned long) sb;
+
         err = percpu_counter_init(&sbi->s_freeblocks_counter,
                         ext4_count_free_blocks(sb));
         if (!err) {
@@ -3646,9 +3673,6 @@ no_journal:
                  "Opts: %s%s%s", descr, sbi->s_es->s_mount_opts,
                  *sbi->s_es->s_mount_opts ? "; " : "", orig_data);
 
-        init_timer(&sbi->s_err_report);
-        sbi->s_err_report.function = print_daily_error_info;
-        sbi->s_err_report.data = (unsigned long) sb;
         if (es->s_error_count)
                 mod_timer(&sbi->s_err_report, jiffies + 300*HZ); /* 5 minutes */
 
@@ -3672,6 +3696,7 @@ failed_mount_wq:
                 sbi->s_journal = NULL;
         }
 failed_mount3:
+        del_timer(&sbi->s_err_report);
         if (sbi->s_flex_groups) {
                 if (is_vmalloc_addr(sbi->s_flex_groups))
                         vfree(sbi->s_flex_groups);
@@ -4138,6 +4163,11 @@ static int ext4_sync_fs(struct super_block *sb, int wait)
 /*
  * LVM calls this function before a (read-only) snapshot is created.  This
  * gives us a chance to flush the journal completely and mark the fs clean.
+ *
+ * Note that only this function cannot bring a filesystem to be in a clean
+ * state independently, because ext4 prevents a new handle from being started
+ * by @sb->s_frozen, which stays in an upper layer.  It thus needs help from
+ * the upper layer.
  */
 static int ext4_freeze(struct super_block *sb)
 {
@@ -4614,11 +4644,24 @@ 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)
 {
+        struct inode *inode = sb_dqopt(sb)->files[type];
+        handle_t *handle;
+
         /* Force all delayed allocation blocks to be allocated.
          * Caller already holds s_umount sem */
         if (test_opt(sb, DELALLOC))
                 sync_filesystem(sb);
 
+        /* Update modification times of quota files when userspace can
+         * start looking at them */
+        handle = ext4_journal_start(inode, 1);
+        if (IS_ERR(handle))
+                goto out;
+        inode->i_mtime = inode->i_ctime = CURRENT_TIME;
+        ext4_mark_inode_dirty(handle, inode);
+        ext4_journal_stop(handle);
+
+out:
         return dquot_quota_off(sb, type);
 }
 
@@ -4714,9 +4757,8 @@ out:
         if (inode->i_size < off + len) {
                 i_size_write(inode, off + len);
                 EXT4_I(inode)->i_disksize = inode->i_size;
+                ext4_mark_inode_dirty(handle, inode);
         }
-        inode->i_mtime = inode->i_ctime = CURRENT_TIME;
-        ext4_mark_inode_dirty(handle, inode);
         mutex_unlock(&inode->i_mutex);
         return len;
 }
diff --git a/fs/jbd2/commit.c b/fs/jbd2/commit.c
index 20af62f4304b..6e28000a4b21 100644
--- a/fs/jbd2/commit.c
+++ b/fs/jbd2/commit.c
@@ -105,6 +105,8 @@ static int journal_submit_commit_record(journal_t *journal,
         int ret;
         struct timespec now = current_kernel_time();
 
+        *cbh = NULL;
+
         if (is_journal_aborted(journal))
                 return 0;
 
@@ -806,7 +808,7 @@ wait_for_iobuf:
                 if (err)
                         __jbd2_journal_abort_hard(journal);
         }
-        if (!err && !is_journal_aborted(journal))
+        if (cbh)
                 err = journal_wait_on_commit_record(journal, cbh);
         if (JBD2_HAS_INCOMPAT_FEATURE(journal,
                                       JBD2_FEATURE_INCOMPAT_ASYNC_COMMIT) &&
diff --git a/fs/jbd2/journal.c b/fs/jbd2/journal.c
index aba8ebaec25c..e0ec3db1c395 100644
--- a/fs/jbd2/journal.c
+++ b/fs/jbd2/journal.c
@@ -2413,10 +2413,12 @@ const char *jbd2_dev_to_name(dev_t device)
         new_dev = kmalloc(sizeof(struct devname_cache), GFP_KERNEL);
         if (!new_dev)
                 return "NODEV-ALLOCFAILURE"; /* Something non-NULL */
+        bd = bdget(device);
         spin_lock(&devname_cache_lock);
         if (devcache[i]) {
                 if (devcache[i]->device == device) {
                         kfree(new_dev);
+                        bdput(bd);
                         ret = devcache[i]->devname;
                         spin_unlock(&devname_cache_lock);
                         return ret;
@@ -2425,7 +2427,6 @@ const char *jbd2_dev_to_name(dev_t device)
         }
         devcache[i] = new_dev;
         devcache[i]->device = device;
-        bd = bdget(device);
         if (bd) {
                 bdevname(bd, devcache[i]->devname);
                 bdput(bd);