8 files changed, 98 insertions, 52 deletions

diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h
index b577e45425b0..0ab26fbf3380 100644
--- a/fs/ext4/ext4.h
+++ b/fs/ext4/ext4.h
@@ -2086,6 +2086,7 @@ extern int  ext4_sync_inode(handle_t *, struct inode *);
 extern void ext4_dirty_inode(struct inode *, int);
 extern int ext4_change_inode_journal_flag(struct inode *, int);
 extern int ext4_get_inode_loc(struct inode *, struct ext4_iloc *);
+extern int ext4_inode_attach_jinode(struct inode *inode);
 extern int ext4_can_truncate(struct inode *inode);
 extern void ext4_truncate(struct inode *);
 extern int ext4_punch_hole(struct inode *inode, loff_t offset, loff_t length);
diff --git a/fs/ext4/ext4_jbd2.c b/fs/ext4/ext4_jbd2.c
index 72a3600aedbd..17ac112ab101 100644
--- a/fs/ext4/ext4_jbd2.c
+++ b/fs/ext4/ext4_jbd2.c
@@ -255,10 +255,10 @@ int __ext4_handle_dirty_metadata(const char *where, unsigned int line,
         set_buffer_prio(bh);
         if (ext4_handle_valid(handle)) {
                 err = jbd2_journal_dirty_metadata(handle, bh);
-                if (err) {
-                        /* Errors can only happen if there is a bug */
-                        handle->h_err = err;
-                        __ext4_journal_stop(where, line, handle);
+                /* Errors can only happen if there is a bug */
+                if (WARN_ON_ONCE(err)) {
+                        ext4_journal_abort_handle(where, line, __func__, bh,
+                                                  handle, err);
                 }
         } else {
                 if (inode)
diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c
index a61873808f76..72ba4705d4fa 100644
--- a/fs/ext4/extents.c
+++ b/fs/ext4/extents.c
@@ -4412,7 +4412,7 @@ void ext4_ext_truncate(handle_t *handle, struct inode *inode)
 retry:
         err = ext4_es_remove_extent(inode, last_block,
                                     EXT_MAX_BLOCKS - last_block);
-        if (err == ENOMEM) {
+        if (err == -ENOMEM) {
                 cond_resched();
                 congestion_wait(BLK_RW_ASYNC, HZ/50);
                 goto retry;
diff --git a/fs/ext4/file.c b/fs/ext4/file.c
index 6f4cc567c382..319c9d26279a 100644
--- a/fs/ext4/file.c
+++ b/fs/ext4/file.c
@@ -219,7 +219,6 @@ static int ext4_file_open(struct inode * inode, struct file * filp)
 {
         struct super_block *sb = inode->i_sb;
         struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
-        struct ext4_inode_info *ei = EXT4_I(inode);
         struct vfsmount *mnt = filp->f_path.mnt;
         struct path path;
         char buf[64], *cp;
@@ -259,22 +258,10 @@ static int ext4_file_open(struct inode * inode, struct file * filp)
          * Set up the jbd2_inode if we are opening the inode for
          * writing and the journal is present
          */
-        if (sbi->s_journal && !ei->jinode && (filp->f_mode & FMODE_WRITE)) {
-                struct jbd2_inode *jinode = jbd2_alloc_inode(GFP_KERNEL);
-
-                spin_lock(&inode->i_lock);
-                if (!ei->jinode) {
-                        if (!jinode) {
-                                spin_unlock(&inode->i_lock);
-                                return -ENOMEM;
-                        }
-                        ei->jinode = jinode;
-                        jbd2_journal_init_jbd_inode(ei->jinode, inode);
-                        jinode = NULL;
-                }
-                spin_unlock(&inode->i_lock);
-                if (unlikely(jinode != NULL))
-                        jbd2_free_inode(jinode);
+        if (filp->f_mode & FMODE_WRITE) {
+                int ret = ext4_inode_attach_jinode(inode);
+                if (ret < 0)
+                        return ret;
         }
         return dquot_file_open(inode, filp);
 }
diff --git a/fs/ext4/ialloc.c b/fs/ext4/ialloc.c
index f03598c6ffd3..8bf5999875ee 100644
--- a/fs/ext4/ialloc.c
+++ b/fs/ext4/ialloc.c
@@ -734,11 +734,8 @@ repeat_in_this_group:
                 ino = ext4_find_next_zero_bit((unsigned long *)
                                               inode_bitmap_bh->b_data,
                                               EXT4_INODES_PER_GROUP(sb), ino);
-                if (ino >= EXT4_INODES_PER_GROUP(sb)) {
-                        if (++group == ngroups)
-                                group = 0;
-                        continue;
-                }
+                if (ino >= EXT4_INODES_PER_GROUP(sb))
+                        goto next_group;
                 if (group == 0 && (ino+1) < EXT4_FIRST_INO(sb)) {
                         ext4_error(sb, "reserved inode found cleared - "
                                    "inode=%lu", ino + 1);
@@ -769,6 +766,9 @@ repeat_in_this_group:
                         goto got; /* we grabbed the inode! */
                 if (ino < EXT4_INODES_PER_GROUP(sb))
                         goto repeat_in_this_group;
+next_group:
+                if (++group == ngroups)
+                        group = 0;
         }
         err = -ENOSPC;
         goto out;
diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index ba33c67d6e48..c2ca04e67a4f 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -555,14 +555,13 @@ int ext4_map_blocks(handle_t *handle, struct inode *inode,
                 int ret;
                 unsigned long long status;
 
-#ifdef ES_AGGRESSIVE_TEST
-                if (retval != map->m_len) {
-                        printk("ES len assertion failed for inode: %lu "
-                               "retval %d != map->m_len %d "
-                               "in %s (lookup)\n", inode->i_ino, retval,
-                               map->m_len, __func__);
+                if (unlikely(retval != map->m_len)) {
+                        ext4_warning(inode->i_sb,
+                                     "ES len assertion failed for inode "
+                                     "%lu: retval %d != map->m_len %d",
+                                     inode->i_ino, retval, map->m_len);
+                        WARN_ON(1);
                 }
-#endif
 
                 status = map->m_flags & EXT4_MAP_UNWRITTEN ?
                                 EXTENT_STATUS_UNWRITTEN : EXTENT_STATUS_WRITTEN;
@@ -656,14 +655,13 @@ found:
                 int ret;
                 unsigned long long status;
 
-#ifdef ES_AGGRESSIVE_TEST
-                if (retval != map->m_len) {
-                        printk("ES len assertion failed for inode: %lu "
-                               "retval %d != map->m_len %d "
-                               "in %s (allocation)\n", inode->i_ino, retval,
-                               map->m_len, __func__);
+                if (unlikely(retval != map->m_len)) {
+                        ext4_warning(inode->i_sb,
+                                     "ES len assertion failed for inode "
+                                     "%lu: retval %d != map->m_len %d",
+                                     inode->i_ino, retval, map->m_len);
+                        WARN_ON(1);
                 }
-#endif
 
                 /*
                  * If the extent has been zeroed out, we don't need to update
@@ -1637,14 +1635,13 @@ add_delayed:
                 int ret;
                 unsigned long long status;
 
-#ifdef ES_AGGRESSIVE_TEST
-                if (retval != map->m_len) {
-                        printk("ES len assertion failed for inode: %lu "
-                               "retval %d != map->m_len %d "
-                               "in %s (lookup)\n", inode->i_ino, retval,
-                               map->m_len, __func__);
+                if (unlikely(retval != map->m_len)) {
+                        ext4_warning(inode->i_sb,
+                                     "ES len assertion failed for inode "
+                                     "%lu: retval %d != map->m_len %d",
+                                     inode->i_ino, retval, map->m_len);
+                        WARN_ON(1);
                 }
-#endif
 
                 status = map->m_flags & EXT4_MAP_UNWRITTEN ?
                                 EXTENT_STATUS_UNWRITTEN : EXTENT_STATUS_WRITTEN;
@@ -3536,6 +3533,18 @@ int ext4_punch_hole(struct inode *inode, loff_t offset, loff_t length)
                    offset;
         }
 
+        if (offset & (sb->s_blocksize - 1) ||
+            (offset + length) & (sb->s_blocksize - 1)) {
+                /*
+                 * Attach jinode to inode for jbd2 if we do any zeroing of
+                 * partial block
+                 */
+                ret = ext4_inode_attach_jinode(inode);
+                if (ret < 0)
+                        goto out_mutex;
+
+        }
+
         first_block_offset = round_up(offset, sb->s_blocksize);
         last_block_offset = round_down((offset + length), sb->s_blocksize) - 1;
 
@@ -3604,6 +3613,31 @@ out_mutex:
         return ret;
 }
 
+int ext4_inode_attach_jinode(struct inode *inode)
+{
+        struct ext4_inode_info *ei = EXT4_I(inode);
+        struct jbd2_inode *jinode;
+
+        if (ei->jinode || !EXT4_SB(inode->i_sb)->s_journal)
+                return 0;
+
+        jinode = jbd2_alloc_inode(GFP_KERNEL);
+        spin_lock(&inode->i_lock);
+        if (!ei->jinode) {
+                if (!jinode) {
+                        spin_unlock(&inode->i_lock);
+                        return -ENOMEM;
+                }
+                ei->jinode = jinode;
+                jbd2_journal_init_jbd_inode(ei->jinode, inode);
+                jinode = NULL;
+        }
+        spin_unlock(&inode->i_lock);
+        if (unlikely(jinode != NULL))
+                jbd2_free_inode(jinode);
+        return 0;
+}
+
 /*
  * ext4_truncate()
  *
@@ -3664,6 +3698,12 @@ void ext4_truncate(struct inode *inode)
                         return;
         }
 
+        /* If we zero-out tail of the page, we have to create jinode for jbd2 */
+        if (inode->i_size & (inode->i_sb->s_blocksize - 1)) {
+                if (ext4_inode_attach_jinode(inode) < 0)
+                        return;
+        }
+
         if (ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS))
                 credits = ext4_writepage_trans_blocks(inode);
         else
diff --git a/fs/ext4/ioctl.c b/fs/ext4/ioctl.c
index 9491ac0590f7..c0427e2f6648 100644
--- a/fs/ext4/ioctl.c
+++ b/fs/ext4/ioctl.c
@@ -77,8 +77,10 @@ static void swap_inode_data(struct inode *inode1, struct inode *inode2)
         memswap(ei1->i_data, ei2->i_data, sizeof(ei1->i_data));
         memswap(&ei1->i_flags, &ei2->i_flags, sizeof(ei1->i_flags));
         memswap(&ei1->i_disksize, &ei2->i_disksize, sizeof(ei1->i_disksize));
-        memswap(&ei1->i_es_tree, &ei2->i_es_tree, sizeof(ei1->i_es_tree));
-        memswap(&ei1->i_es_lru_nr, &ei2->i_es_lru_nr, sizeof(ei1->i_es_lru_nr));
+        ext4_es_remove_extent(inode1, 0, EXT_MAX_BLOCKS);
+        ext4_es_remove_extent(inode2, 0, EXT_MAX_BLOCKS);
+        ext4_es_lru_del(inode1);
+        ext4_es_lru_del(inode2);
 
         isize = i_size_read(inode1);
         i_size_write(inode1, i_size_read(inode2));
diff --git a/fs/ext4/super.c b/fs/ext4/super.c
index bca26f34edf4..b59373b625e9 100644
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -1359,7 +1359,7 @@ static const struct mount_opts {
         {Opt_delalloc, EXT4_MOUNT_DELALLOC,
          MOPT_EXT4_ONLY | MOPT_SET | MOPT_EXPLICIT},
         {Opt_nodelalloc, EXT4_MOUNT_DELALLOC,
-         MOPT_EXT4_ONLY | MOPT_CLEAR | MOPT_EXPLICIT},
+         MOPT_EXT4_ONLY | MOPT_CLEAR},
         {Opt_journal_checksum, EXT4_MOUNT_JOURNAL_CHECKSUM,
          MOPT_EXT4_ONLY | MOPT_SET},
         {Opt_journal_async_commit, (EXT4_MOUNT_JOURNAL_ASYNC_COMMIT |
@@ -3483,7 +3483,7 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
                 }
                 if (test_opt(sb, DIOREAD_NOLOCK)) {
                         ext4_msg(sb, KERN_ERR, "can't mount with "
-                                 "both data=journal and delalloc");
+                                 "both data=journal and dioread_nolock");
                         goto failed_mount;
                 }
                 if (test_opt(sb, DELALLOC))
@@ -4727,6 +4727,21 @@ static int ext4_remount(struct super_block *sb, int *flags, char *data)
                 goto restore_opts;
         }
 
+        if (test_opt(sb, DATA_FLAGS) == EXT4_MOUNT_JOURNAL_DATA) {
+                if (test_opt2(sb, EXPLICIT_DELALLOC)) {
+                        ext4_msg(sb, KERN_ERR, "can't mount with "
+                                 "both data=journal and delalloc");
+                        err = -EINVAL;
+                        goto restore_opts;
+                }
+                if (test_opt(sb, DIOREAD_NOLOCK)) {
+                        ext4_msg(sb, KERN_ERR, "can't mount with "
+                                 "both data=journal and dioread_nolock");
+                        err = -EINVAL;
+                        goto restore_opts;
+                }
+        }
+
         if (sbi->s_mount_flags & EXT4_MF_FS_ABORTED)
                 ext4_abort(sb, "Abort forced by user");
 
@@ -5481,6 +5496,7 @@ static void __exit ext4_exit_fs(void)
         kset_unregister(ext4_kset);
         ext4_exit_system_zone();
         ext4_exit_pageio();
+        ext4_exit_es();
 }
 
 MODULE_AUTHOR("Remy Card, Stephen Tweedie, Andrew Morton, Andreas Dilger, Theodore Ts'o and others");