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: (43 commits)
  ext4: fix a BUG in mb_mark_used during trim.
  ext4: unused variables cleanup in fs/ext4/extents.c
  ext4: remove redundant set_buffer_mapped() in ext4_da_get_block_prep()
  ext4: add more tracepoints and use dev_t in the trace buffer
  ext4: don't kfree uninitialized s_group_info members
  ext4: add missing space in printk's in __ext4_grp_locked_error()
  ext4: add FITRIM to compat_ioctl.
  ext4: handle errors in ext4_clear_blocks()
  ext4: unify the ext4_handle_release_buffer() api
  ext4: handle errors in ext4_rename
  jbd2: add COW fields to struct jbd2_journal_handle
  jbd2: add the b_cow_tid field to journal_head struct
  ext4: Initialize fsync transaction ids in ext4_new_inode()
  ext4: Use single thread to perform DIO unwritten convertion
  ext4: optimize ext4_bio_write_page() when no extent conversion is needed
  ext4: skip orphan cleanup if fs has unknown ROCOMPAT features
  ext4: use the nblocks arg to ext4_truncate_restart_trans()
  ext4: fix missing iput of root inode for some mount error paths
  ext4: make FIEMAP and delayed allocation play well together
  ext4: suppress verbose debugging information if malloc-debug is off
  ...

Fi up conflicts in fs/ext4/super.c due to workqueue changes

Documentation/ABI/testing/sysfs-fs-ext4

@@ -48,7 +48,7 @@ Description:
 		 will have its blocks allocated out of its own unique
 		 preallocation pool.
 
-What:		/sys/fs/ext4/<disk>/inode_readahead
+What:		/sys/fs/ext4/<disk>/inode_readahead_blks
 Date:		March 2008
 Contact:	"Theodore Ts'o" <tytso@mit.edu>
 Description:
@@ -85,7 +85,14 @@ Date:		June 2008
 Contact:	"Theodore Ts'o" <tytso@mit.edu>
 Description:
 		Tuning parameter which (if non-zero) controls the goal
-		inode used by the inode allocator in p0reference to
-		all other allocation hueristics.  This is intended for
+		inode used by the inode allocator in preference to
+		all other allocation heuristics.  This is intended for
 		debugging use only, and should be 0 on production
 		systems.
+
+What:		/sys/fs/ext4/<disk>/max_writeback_mb_bump
+Date:		September 2009
+Contact:	"Theodore Ts'o" <tytso@mit.edu>
+Description:
+		The maximum number of megabytes the writeback code will
+		try to write out before move on to another inode.

fs/ext4/balloc.c

@@ -21,6 +21,8 @@
 #include "ext4_jbd2.h"
 #include "mballoc.h"
 
+#include <trace/events/ext4.h>
+
 /*
  * balloc.c contains the blocks allocation and deallocation routines
  */
@@ -342,6 +344,7 @@ ext4_read_block_bitmap(struct super_block *sb, ext4_group_t block_group)
 	 * We do it here so the bitmap uptodate bit
 	 * get set with buffer lock held.
 	 */
+	trace_ext4_read_block_bitmap_load(sb, block_group);
 	set_bitmap_uptodate(bh);
 	if (bh_submit_read(bh) < 0) {
 		put_bh(bh);

fs/ext4/ext4_jbd2.h

@@ -202,13 +202,6 @@ static inline int ext4_handle_has_enough_credits(handle_t *handle, int needed)
 	return 1;
 }
 
-static inline void ext4_journal_release_buffer(handle_t *handle,
-						struct buffer_head *bh)
-{
-	if (ext4_handle_valid(handle))
-		jbd2_journal_release_buffer(handle, bh);
-}
-
 static inline handle_t *ext4_journal_start(struct inode *inode, int nblocks)
 {
 	return ext4_journal_start_sb(inode->i_sb, nblocks);

fs/ext4/fsync.c

@@ -164,20 +164,20 @@ int ext4_sync_file(struct file *file, int datasync)
 
 	J_ASSERT(ext4_journal_current_handle() == NULL);
 
-	trace_ext4_sync_file(file, datasync);
+	trace_ext4_sync_file_enter(file, datasync);
 
 	if (inode->i_sb->s_flags & MS_RDONLY)
 		return 0;
 
 	ret = ext4_flush_completed_IO(inode);
 	if (ret < 0)
-		return ret;
+		goto out;
 
 	if (!journal) {
 		ret = generic_file_fsync(file, datasync);
 		if (!ret && !list_empty(&inode->i_dentry))
 			ext4_sync_parent(inode);
-		return ret;
+		goto out;
 	}
 
 	/*
@@ -194,8 +194,10 @@ int ext4_sync_file(struct file *file, int datasync)
 	 *  (they were dirtied by commit).  But that's OK - the blocks are
 	 *  safe in-journal, which is all fsync() needs to ensure.
 	 */
-	if (ext4_should_journal_data(inode))
-		return ext4_force_commit(inode->i_sb);
+	if (ext4_should_journal_data(inode)) {
+		ret = ext4_force_commit(inode->i_sb);
+		goto out;
+	}
 
 	commit_tid = datasync ? ei->i_datasync_tid : ei->i_sync_tid;
 	if (jbd2_log_start_commit(journal, commit_tid)) {
@@ -215,5 +217,7 @@ int ext4_sync_file(struct file *file, int datasync)
 		ret = jbd2_log_wait_commit(journal, commit_tid);
 	} else if (journal->j_flags & JBD2_BARRIER)
 		blkdev_issue_flush(inode->i_sb->s_bdev, GFP_KERNEL, NULL);
+ out:
+	trace_ext4_sync_file_exit(inode, ret);
 	return ret;
 }

fs/ext4/ialloc.c

@@ -152,6 +152,7 @@ ext4_read_inode_bitmap(struct super_block *sb, ext4_group_t block_group)
 	 * We do it here so the bitmap uptodate bit
 	 * get set with buffer lock held.
 	 */
+	trace_ext4_load_inode_bitmap(sb, block_group);
 	set_bitmap_uptodate(bh);
 	if (bh_submit_read(bh) < 0) {
 		put_bh(bh);
@@ -649,7 +650,7 @@ static int find_group_other(struct super_block *sb, struct inode *parent,
 		*group = parent_group + flex_size;
 		if (*group > ngroups)
 			*group = 0;
-		return find_group_orlov(sb, parent, group, mode, 0);
+		return find_group_orlov(sb, parent, group, mode, NULL);
 	}
 
 	/*
@@ -1054,6 +1055,11 @@ struct inode *ext4_new_inode(handle_t *handle, struct inode *dir, int mode,
 		}
 	}
 
+	if (ext4_handle_valid(handle)) {
+		ei->i_sync_tid = handle->h_transaction->t_tid;
+		ei->i_datasync_tid = handle->h_transaction->t_tid;
+	}
+
 	err = ext4_mark_inode_dirty(handle, inode);
 	if (err) {
 		ext4_std_error(sb, err);

fs/ext4/ioctl.c

@@ -334,16 +334,22 @@ long ext4_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
 	case FITRIM:
 	{
 		struct super_block *sb = inode->i_sb;
+		struct request_queue *q = bdev_get_queue(sb->s_bdev);
 		struct fstrim_range range;
 		int ret = 0;
 
 		if (!capable(CAP_SYS_ADMIN))
 			return -EPERM;
 
+		if (!blk_queue_discard(q))
+			return -EOPNOTSUPP;
+
 		if (copy_from_user(&range, (struct fstrim_range *)arg,
 		    sizeof(range)))
 			return -EFAULT;
 
+		range.minlen = max((unsigned int)range.minlen,
+				   q->limits.discard_granularity);
 		ret = ext4_trim_fs(sb, &range);
 		if (ret < 0)
 			return ret;
@@ -421,6 +427,7 @@ long ext4_compat_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
 		return err;
 	}
 	case EXT4_IOC_MOVE_EXT:
+	case FITRIM:
 		break;
 	default:
 		return -ENOIOCTLCMD;

fs/ext4/mballoc.c

@@ -432,9 +432,10 @@ static void *mb_find_buddy(struct ext4_buddy *e4b, int order, int *max)
 	}
 
 	/* at order 0 we see each particular block */
-	*max = 1 << (e4b->bd_blkbits + 3);
-	if (order == 0)
+	if (order == 0) {
+		*max = 1 << (e4b->bd_blkbits + 3);
 		return EXT4_MB_BITMAP(e4b);
+	}
 
 	bb = EXT4_MB_BUDDY(e4b) + EXT4_SB(e4b->bd_sb)->s_mb_offsets[order];
 	*max = EXT4_SB(e4b->bd_sb)->s_mb_maxs[order];
@@ -616,7 +617,6 @@ static int __mb_check_buddy(struct ext4_buddy *e4b, char *file,
 	MB_CHECK_ASSERT(e4b->bd_info->bb_fragments == fragments);
 
 	grp = ext4_get_group_info(sb, e4b->bd_group);
-	buddy = mb_find_buddy(e4b, 0, &max);
 	list_for_each(cur, &grp->bb_prealloc_list) {
 		ext4_group_t groupnr;
 		struct ext4_prealloc_space *pa;
@@ -635,7 +635,12 @@ static int __mb_check_buddy(struct ext4_buddy *e4b, char *file,
 #define mb_check_buddy(e4b)
 #endif
 
-/* FIXME!! need more doc */
+/*
+ * Divide blocks started from @first with length @len into
+ * smaller chunks with power of 2 blocks.
+ * Clear the bits in bitmap which the blocks of the chunk(s) covered,
+ * then increase bb_counters[] for corresponded chunk size.
+ */
 static void ext4_mb_mark_free_simple(struct super_block *sb,
 				void *buddy, ext4_grpblk_t first, ext4_grpblk_t len,
 					struct ext4_group_info *grp)
@@ -2381,7 +2386,7 @@ static int ext4_mb_init_backend(struct super_block *sb)
 	/* An 8TB filesystem with 64-bit pointers requires a 4096 byte
 	 * kmalloc. A 128kb malloc should suffice for a 256TB filesystem.
 	 * So a two level scheme suffices for now. */
-	sbi->s_group_info = kmalloc(array_size, GFP_KERNEL);
+	sbi->s_group_info = kzalloc(array_size, GFP_KERNEL);
 	if (sbi->s_group_info == NULL) {
 		printk(KERN_ERR "EXT4-fs: can't allocate buddy meta group\n");
 		return -ENOMEM;
@@ -3208,7 +3213,7 @@ ext4_mb_check_group_pa(ext4_fsblk_t goal_block,
 	cur_distance = abs(goal_block - cpa->pa_pstart);
 	new_distance = abs(goal_block - pa->pa_pstart);
 
-	if (cur_distance < new_distance)
+	if (cur_distance <= new_distance)
 		return cpa;
 
 	/* drop the previous reference */
@@ -3907,7 +3912,8 @@ static void ext4_mb_show_ac(struct ext4_allocation_context *ac)
 	struct super_block *sb = ac->ac_sb;
 	ext4_group_t ngroups, i;
 
-	if (EXT4_SB(sb)->s_mount_flags & EXT4_MF_FS_ABORTED)
+	if (!mb_enable_debug ||
+	    (EXT4_SB(sb)->s_mount_flags & EXT4_MF_FS_ABORTED))
 		return;
 
 	printk(KERN_ERR "EXT4-fs: Can't allocate:"
@@ -4753,7 +4759,8 @@ static int ext4_trim_extent(struct super_block *sb, int start, int count,
  * bitmap. Then issue a TRIM command on this extent and free the extent in
  * the group buddy bitmap. This is done until whole group is scanned.
  */
-ext4_grpblk_t ext4_trim_all_free(struct super_block *sb, struct ext4_buddy *e4b,
+static ext4_grpblk_t
+ext4_trim_all_free(struct super_block *sb, struct ext4_buddy *e4b,
 		ext4_grpblk_t start, ext4_grpblk_t max, ext4_grpblk_t minblocks)
 {
 	void *bitmap;
@@ -4863,10 +4870,15 @@ int ext4_trim_fs(struct super_block *sb, struct fstrim_range *range)
 			break;
 		}
 
-		if (len >= EXT4_BLOCKS_PER_GROUP(sb))
-			len -= (EXT4_BLOCKS_PER_GROUP(sb) - first_block);
-		else
+		/*
+		 * For all the groups except the last one, last block will
+		 * always be EXT4_BLOCKS_PER_GROUP(sb), so we only need to
+		 * change it for the last group in which case start +
+		 * len < EXT4_BLOCKS_PER_GROUP(sb).
+		 */
+		if (first_block + len < EXT4_BLOCKS_PER_GROUP(sb))
 			last_block = first_block + len;
+		len -= last_block - first_block;
 
 		if (e4b.bd_info->bb_free >= minlen) {
 			cnt = ext4_trim_all_free(sb, &e4b, first_block,

fs/ext4/mballoc.h

@@ -169,7 +169,7 @@ struct ext4_allocation_context {
 	/* original request */
 	struct ext4_free_extent ac_o_ex;
 
-	/* goal request (after normalization) */
+	/* goal request (normalized ac_o_ex) */
 	struct ext4_free_extent ac_g_ex;
 
 	/* the best found extent */

fs/ext4/migrate.c

@@ -263,7 +263,7 @@ static int free_dind_blocks(handle_t *handle,
 	for (i = 0; i < max_entries; i++) {
 		if (tmp_idata[i]) {
 			extend_credit_for_blkdel(handle, inode);
-			ext4_free_blocks(handle, inode, 0,
+			ext4_free_blocks(handle, inode, NULL,
 					 le32_to_cpu(tmp_idata[i]), 1,
 					 EXT4_FREE_BLOCKS_METADATA |
 					 EXT4_FREE_BLOCKS_FORGET);
@@ -271,7 +271,7 @@ static int free_dind_blocks(handle_t *handle,
 	}
 	put_bh(bh);
 	extend_credit_for_blkdel(handle, inode);
-	ext4_free_blocks(handle, inode, 0, le32_to_cpu(i_data), 1,
+	ext4_free_blocks(handle, inode, NULL, le32_to_cpu(i_data), 1,
 			 EXT4_FREE_BLOCKS_METADATA |
 			 EXT4_FREE_BLOCKS_FORGET);
 	return 0;
@@ -302,7 +302,7 @@ static int free_tind_blocks(handle_t *handle,
 	}
 	put_bh(bh);
 	extend_credit_for_blkdel(handle, inode);
-	ext4_free_blocks(handle, inode, 0, le32_to_cpu(i_data), 1,
+	ext4_free_blocks(handle, inode, NULL, le32_to_cpu(i_data), 1,
 			 EXT4_FREE_BLOCKS_METADATA |
 			 EXT4_FREE_BLOCKS_FORGET);
 	return 0;
@@ -315,7 +315,7 @@ static int free_ind_block(handle_t *handle, struct inode *inode, __le32 *i_data)
 	/* ei->i_data[EXT4_IND_BLOCK] */
 	if (i_data[0]) {
 		extend_credit_for_blkdel(handle, inode);
-		ext4_free_blocks(handle, inode, 0,
+		ext4_free_blocks(handle, inode, NULL,
 				le32_to_cpu(i_data[0]), 1,
 				 EXT4_FREE_BLOCKS_METADATA |
 				 EXT4_FREE_BLOCKS_FORGET);
@@ -428,7 +428,7 @@ static int free_ext_idx(handle_t *handle, struct inode *inode,
 	}
 	put_bh(bh);
 	extend_credit_for_blkdel(handle, inode);
-	ext4_free_blocks(handle, inode, 0, block, 1,
+	ext4_free_blocks(handle, inode, NULL, block, 1,
 			 EXT4_FREE_BLOCKS_METADATA | EXT4_FREE_BLOCKS_FORGET);
 	return retval;
 }

fs/ext4/namei.c

@@ -40,6 +40,7 @@
 #include "xattr.h"
 #include "acl.h"
 
+#include <trace/events/ext4.h>
 /*
  * define how far ahead to read directories while searching them.
  */
@@ -2183,6 +2184,7 @@ static int ext4_unlink(struct inode *dir, struct dentry *dentry)
 	struct ext4_dir_entry_2 *de;
 	handle_t *handle;
 
+	trace_ext4_unlink_enter(dir, dentry);
 	/* Initialize quotas before so that eventual writes go
 	 * in separate transaction */
 	dquot_initialize(dir);
@@ -2228,6 +2230,7 @@ static int ext4_unlink(struct inode *dir, struct dentry *dentry)
 end_unlink:
 	ext4_journal_stop(handle);
 	brelse(bh);
+	trace_ext4_unlink_exit(dentry, retval);
 	return retval;
 }
 
@@ -2402,6 +2405,10 @@ static int ext4_rename(struct inode *old_dir, struct dentry *old_dentry,
 		if (!new_inode && new_dir != old_dir &&
 		    EXT4_DIR_LINK_MAX(new_dir))
 			goto end_rename;
+		BUFFER_TRACE(dir_bh, "get_write_access");
+		retval = ext4_journal_get_write_access(handle, dir_bh);
+		if (retval)
+			goto end_rename;
 	}
 	if (!new_bh) {
 		retval = ext4_add_entry(handle, new_dentry, old_inode);
@@ -2409,7 +2416,9 @@ static int ext4_rename(struct inode *old_dir, struct dentry *old_dentry,
 			goto end_rename;
 	} else {
 		BUFFER_TRACE(new_bh, "get write access");
-		ext4_journal_get_write_access(handle, new_bh);
+		retval = ext4_journal_get_write_access(handle, new_bh);
+		if (retval)
+			goto end_rename;
 		new_de->inode = cpu_to_le32(old_inode->i_ino);
 		if (EXT4_HAS_INCOMPAT_FEATURE(new_dir->i_sb,
 					      EXT4_FEATURE_INCOMPAT_FILETYPE))
@@ -2470,8 +2479,6 @@ static int ext4_rename(struct inode *old_dir, struct dentry *old_dentry,
 	old_dir->i_ctime = old_dir->i_mtime = ext4_current_time(old_dir);
 	ext4_update_dx_flag(old_dir);
 	if (dir_bh) {
-		BUFFER_TRACE(dir_bh, "get_write_access");
-		ext4_journal_get_write_access(handle, dir_bh);
 		PARENT_INO(dir_bh->b_data, new_dir->i_sb->s_blocksize) =
 						cpu_to_le32(new_dir->i_ino);
 		BUFFER_TRACE(dir_bh, "call ext4_handle_dirty_metadata");

fs/ext4/page-io.c

@@ -259,6 +259,11 @@ static void ext4_end_bio(struct bio *bio, int error)
 			     bi_sector >> (inode->i_blkbits - 9));
 	}
 
+	if (!(io_end->flag & EXT4_IO_END_UNWRITTEN)) {
+		ext4_free_io_end(io_end);
+		return;
+	}
+
 	/* Add the io_end to per-inode completed io list*/
 	spin_lock_irqsave(&EXT4_I(inode)->i_completed_io_lock, flags);
 	list_add_tail(&io_end->list, &EXT4_I(inode)->i_completed_io_list);
@@ -279,9 +284,9 @@ void ext4_io_submit(struct ext4_io_submit *io)
 		BUG_ON(bio_flagged(io->io_bio, BIO_EOPNOTSUPP));
 		bio_put(io->io_bio);
 	}
-	io->io_bio = 0;
+	io->io_bio = NULL;
 	io->io_op = 0;
-	io->io_end = 0;
+	io->io_end = NULL;
 }
 
 static int io_submit_init(struct ext4_io_submit *io,
@@ -380,8 +385,6 @@ int ext4_bio_write_page(struct ext4_io_submit *io,
 
 	BUG_ON(!PageLocked(page));
 	BUG_ON(PageWriteback(page));
-	set_page_writeback(page);
-	ClearPageError(page);
 
 	io_page = kmem_cache_alloc(io_page_cachep, GFP_NOFS);
 	if (!io_page) {
@@ -392,6 +395,8 @@ int ext4_bio_write_page(struct ext4_io_submit *io,
 	io_page->p_page = page;
 	atomic_set(&io_page->p_count, 1);
 	get_page(page);
+	set_page_writeback(page);
+	ClearPageError(page);
 
 	for (bh = head = page_buffers(page), block_start = 0;
 	     bh != head || !block_start;

fs/ext4/resize.c

@@ -230,7 +230,7 @@ static int setup_new_group_blocks(struct super_block *sb,
 	}
 
 	/* Zero out all of the reserved backup group descriptor table blocks */
-	ext4_debug("clear inode table blocks %#04llx -> %#04llx\n",
+	ext4_debug("clear inode table blocks %#04llx -> %#04lx\n",
 			block, sbi->s_itb_per_group);
 	err = sb_issue_zeroout(sb, gdblocks + start + 1, reserved_gdb,
 			       GFP_NOFS);
@@ -248,7 +248,7 @@ static int setup_new_group_blocks(struct super_block *sb,
 
 	/* Zero out all of the inode table blocks */
 	block = input->inode_table;
-	ext4_debug("clear inode table blocks %#04llx -> %#04llx\n",
+	ext4_debug("clear inode table blocks %#04llx -> %#04lx\n",
 			block, sbi->s_itb_per_group);
 	err = sb_issue_zeroout(sb, block, sbi->s_itb_per_group, GFP_NOFS);
 	if (err)
@@ -499,12 +499,12 @@ static int add_new_gdb(handle_t *handle, struct inode *inode,
 	return err;
 
 exit_inode:
-	/* ext4_journal_release_buffer(handle, iloc.bh); */
+	/* ext4_handle_release_buffer(handle, iloc.bh); */
 	brelse(iloc.bh);
 exit_dindj:
-	/* ext4_journal_release_buffer(handle, dind); */
+	/* ext4_handle_release_buffer(handle, dind); */
 exit_sbh:
-	/* ext4_journal_release_buffer(handle, EXT4_SB(sb)->s_sbh); */
+	/* ext4_handle_release_buffer(handle, EXT4_SB(sb)->s_sbh); */
 exit_dind:
 	brelse(dind);
 exit_bh:
@@ -586,7 +586,7 @@ static int reserve_backup_gdb(handle_t *handle, struct inode *inode,
 			/*
 			int j;
 			for (j = 0; j < i; j++)
-				ext4_journal_release_buffer(handle, primary[j]);
+				ext4_handle_release_buffer(handle, primary[j]);
 			 */
 			goto exit_bh;
 		}

fs/ext4/super.c

@@ -54,9 +54,9 @@
 
 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 struct ext4_lazy_init *ext4_li_info;
+static struct mutex ext4_li_mtx;
+static struct ext4_features *ext4_feat;
 
 static int ext4_load_journal(struct super_block *, struct ext4_super_block *,
 			     unsigned long journal_devnum);
@@ -75,6 +75,7 @@ static void ext4_write_super(struct super_block *sb);
 static int ext4_freeze(struct super_block *sb);
 static struct dentry *ext4_mount(struct file_system_type *fs_type, int flags,
 		       const char *dev_name, void *data);
+static int ext4_feature_set_ok(struct super_block *sb, int readonly);
 static void ext4_destroy_lazyinit_thread(void);
 static void ext4_unregister_li_request(struct super_block *sb);
 static void ext4_clear_request_list(void);
@@ -594,7 +595,7 @@ __acquires(bitlock)
 
 	vaf.fmt = fmt;
 	vaf.va = &args;
-	printk(KERN_CRIT "EXT4-fs error (device %s): %s:%d: group %u",
+	printk(KERN_CRIT "EXT4-fs error (device %s): %s:%d: group %u, ",
 	       sb->s_id, function, line, grp);
 	if (ino)
 		printk(KERN_CONT "inode %lu: ", ino);
@@ -997,13 +998,10 @@ static int ext4_show_options(struct seq_file *seq, struct vfsmount *vfs)
 	if (test_opt(sb, OLDALLOC))
 		seq_puts(seq, ",oldalloc");
 #ifdef CONFIG_EXT4_FS_XATTR
-	if (test_opt(sb, XATTR_USER) &&
-		!(def_mount_opts & EXT4_DEFM_XATTR_USER))
+	if (test_opt(sb, XATTR_USER))
 		seq_puts(seq, ",user_xattr");
-	if (!test_opt(sb, XATTR_USER) &&
-	    (def_mount_opts & EXT4_DEFM_XATTR_USER)) {
+	if (!test_opt(sb, XATTR_USER))
 		seq_puts(seq, ",nouser_xattr");
-	}
 #endif
 #ifdef CONFIG_EXT4_FS_POSIX_ACL
 	if (test_opt(sb, POSIX_ACL) && !(def_mount_opts & EXT4_DEFM_ACL))
@@ -1041,8 +1039,8 @@ static int ext4_show_options(struct seq_file *seq, struct vfsmount *vfs)
 	    !(def_mount_opts & EXT4_DEFM_NODELALLOC))
 		seq_puts(seq, ",nodelalloc");
 
-	if (test_opt(sb, MBLK_IO_SUBMIT))
-		seq_puts(seq, ",mblk_io_submit");
+	if (!test_opt(sb, MBLK_IO_SUBMIT))
+		seq_puts(seq, ",nomblk_io_submit");
 	if (sbi->s_stripe)
 		seq_printf(seq, ",stripe=%lu", sbi->s_stripe);
 	/*
@@ -1451,7 +1449,7 @@ static int parse_options(char *options, struct super_block *sb,
 		 * Initialize args struct so we know whether arg was
 		 * found; some options take optional arguments.
 		 */
-		args[0].to = args[0].from = 0;
+		args[0].to = args[0].from = NULL;
 		token = match_token(p, tokens, args);
 		switch (token) {
 		case Opt_bsd_df:
@@ -1771,7 +1769,7 @@ static int parse_options(char *options, struct super_block *sb,
 				return 0;
 			if (option < 0 || option > (1 << 30))
 				return 0;
-			if (!is_power_of_2(option)) {
+			if (option && !is_power_of_2(option)) {
 				ext4_msg(sb, KERN_ERR,
 					 "EXT4-fs: inode_readahead_blks"
 					 " must be a power of 2");
@@ -2120,6 +2118,13 @@ static void ext4_orphan_cleanup(struct super_block *sb,
 		return;
 	}
 
+	/* Check if feature set would not allow a r/w mount */
+	if (!ext4_feature_set_ok(sb, 0)) {
+		ext4_msg(sb, KERN_INFO, "Skipping orphan cleanup due to "
+			 "unknown ROCOMPAT features");
+		return;
+	}
+
 	if (EXT4_SB(sb)->s_mount_state & EXT4_ERROR_FS) {
 		if (es->s_last_orphan)
 			jbd_debug(1, "Errors on filesystem, "
@@ -2412,7 +2417,7 @@ static ssize_t inode_readahead_blks_store(struct ext4_attr *a,
 	if (parse_strtoul(buf, 0x40000000, &t))
 		return -EINVAL;
 
-	if (!is_power_of_2(t))
+	if (t && !is_power_of_2(t))
 		return -EINVAL;
 
 	sbi->s_inode_readahead_blks = t;
@@ -3095,14 +3100,14 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
 	}
 	if (def_mount_opts & EXT4_DEFM_UID16)
 		set_opt(sb, NO_UID32);
+	/* xattr user namespace & acls are now defaulted on */
 #ifdef CONFIG_EXT4_FS_XATTR
-	if (def_mount_opts & EXT4_DEFM_XATTR_USER)
-		set_opt(sb, XATTR_USER);
+	set_opt(sb, XATTR_USER);
 #endif
 #ifdef CONFIG_EXT4_FS_POSIX_ACL
-	if (def_mount_opts & EXT4_DEFM_ACL)
-		set_opt(sb, POSIX_ACL);
+	set_opt(sb, POSIX_ACL);
 #endif
+	set_opt(sb, MBLK_IO_SUBMIT);
 	if ((def_mount_opts & EXT4_DEFM_JMODE) == EXT4_DEFM_JMODE_DATA)
 		set_opt(sb, JOURNAL_DATA);
 	else if ((def_mount_opts & EXT4_DEFM_JMODE) == EXT4_DEFM_JMODE_ORDERED)
@@ -3516,7 +3521,7 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
 	 * concurrency isn't really necessary.  Limit it to 1.
 	 */
 	EXT4_SB(sb)->dio_unwritten_wq =
-		alloc_workqueue("ext4-dio-unwritten", WQ_MEM_RECLAIM, 1);
+		alloc_workqueue("ext4-dio-unwritten", WQ_MEM_RECLAIM | WQ_UNBOUND, 1);
 	if (!EXT4_SB(sb)->dio_unwritten_wq) {
 		printk(KERN_ERR "EXT4-fs: failed to create DIO workqueue\n");
 		goto failed_mount_wq;
@@ -3531,17 +3536,16 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
 	if (IS_ERR(root)) {
 		ext4_msg(sb, KERN_ERR, "get root inode failed");
 		ret = PTR_ERR(root);
+		root = NULL;
 		goto failed_mount4;
 	}
 	if (!S_ISDIR(root->i_mode) || !root->i_blocks || !root->i_size) {
-		iput(root);
 		ext4_msg(sb, KERN_ERR, "corrupt root inode, run e2fsck");
 		goto failed_mount4;
 	}
 	sb->s_root = d_alloc_root(root);
 	if (!sb->s_root) {
 		ext4_msg(sb, KERN_ERR, "get root dentry failed");
-		iput(root);
 		ret = -ENOMEM;
 		goto failed_mount4;
 	}
@@ -3657,6 +3661,8 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
 	goto failed_mount;
 
 failed_mount4:
+	iput(root);
+	sb->s_root = NULL;
 	ext4_msg(sb, KERN_ERR, "mount failed");
 	destroy_workqueue(EXT4_SB(sb)->dio_unwritten_wq);
 failed_mount_wq:

fs/ext4/xattr.c

@@ -735,7 +735,7 @@ ext4_xattr_block_set(handle_t *handle, struct inode *inode,
 			int offset = (char *)s->here - bs->bh->b_data;
 
 			unlock_buffer(bs->bh);
-			jbd2_journal_release_buffer(handle, bs->bh);
+			ext4_handle_release_buffer(handle, bs->bh);
 			if (ce) {
 				mb_cache_entry_release(ce);
 				ce = NULL;
@@ -833,7 +833,7 @@ ext4_xattr_block_set(handle_t *handle, struct inode *inode,
 			new_bh = sb_getblk(sb, block);
 			if (!new_bh) {
 getblk_failed:
-				ext4_free_blocks(handle, inode, 0, block, 1,
+				ext4_free_blocks(handle, inode, NULL, block, 1,
 						 EXT4_FREE_BLOCKS_METADATA);
 				error = -EIO;
 				goto cleanup;

include/linux/jbd2.h

@@ -432,13 +432,35 @@ struct jbd2_journal_handle
 	int			h_err;
 
 	/* Flags [no locking] */
-	unsigned int	h_sync:		1;	/* sync-on-close */
-	unsigned int	h_jdata:	1;	/* force data journaling */
-	unsigned int	h_aborted:	1;	/* fatal error on handle */
+	unsigned int	h_sync:1;	/* sync-on-close */
+	unsigned int	h_jdata:1;	/* force data journaling */
+	unsigned int	h_aborted:1;	/* fatal error on handle */
+	unsigned int	h_cowing:1;	/* COWing block to snapshot */
+
+	/* Number of buffers requested by user:
+	 * (before adding the COW credits factor) */
+	unsigned int	h_base_credits:14;
+
+	/* Number of buffers the user is allowed to dirty:
+	 * (counts only buffers dirtied when !h_cowing) */
+	unsigned int	h_user_credits:14;
+
 
 #ifdef CONFIG_DEBUG_LOCK_ALLOC
 	struct lockdep_map	h_lockdep_map;
 #endif
+
+#ifdef CONFIG_JBD2_DEBUG
+	/* COW debugging counters: */
+	unsigned int h_cow_moved; /* blocks moved to snapshot */
+	unsigned int h_cow_copied; /* blocks copied to snapshot */
+	unsigned int h_cow_ok_jh; /* blocks already COWed during current
+				     transaction */
+	unsigned int h_cow_ok_bitmap; /* blocks not set in COW bitmap */
+	unsigned int h_cow_ok_mapped;/* blocks already mapped in snapshot */
+	unsigned int h_cow_bitmaps; /* COW bitmaps created */
+	unsigned int h_cow_excluded; /* blocks set in exclude bitmap */
+#endif
 };
 
 

include/linux/journal-head.h

@@ -40,6 +40,13 @@ struct journal_head {
 	 */
 	unsigned b_modified;
 
+	/*
+	 * This feild tracks the last transaction id in which this buffer
+	 * has been cowed
+	 * [jbd_lock_bh_state()]
+	 */
+	unsigned b_cow_tid;
+
 	/*
 	 * Copy of the buffer data frozen for writing to the log.
 	 * [jbd_lock_bh_state()]

include/trace/events/jbd2.h

@@ -17,19 +17,17 @@ TRACE_EVENT(jbd2_checkpoint,
 	TP_ARGS(journal, result),
 
 	TP_STRUCT__entry(
-		__field(	int,	dev_major		)
-		__field(	int,	dev_minor		)
+		__field(	dev_t,	dev			)
 		__field(	int,	result			)
 	),
 
 	TP_fast_assign(
-		__entry->dev_major	= MAJOR(journal->j_fs_dev->bd_dev);
-		__entry->dev_minor	= MINOR(journal->j_fs_dev->bd_dev);
+		__entry->dev		= journal->j_fs_dev->bd_dev;
 		__entry->result		= result;
 	),
 
-	TP_printk("dev %d,%d result %d",
-		  __entry->dev_major, __entry->dev_minor, __entry->result)
+	TP_printk("dev %s result %d",
+		  jbd2_dev_to_name(__entry->dev), __entry->result)
 );
 
 DECLARE_EVENT_CLASS(jbd2_commit,
@@ -39,22 +37,20 @@ DECLARE_EVENT_CLASS(jbd2_commit,
 	TP_ARGS(journal, commit_transaction),
 
 	TP_STRUCT__entry(
-		__field(	int,   dev_major                )
-		__field(	int,   dev_minor                )
+		__field(	dev_t,	dev			)
 		__field(	char,	sync_commit		  )
 		__field(	int,	transaction		  )
 	),
 
 	TP_fast_assign(
-		__entry->dev_major	= MAJOR(journal->j_fs_dev->bd_dev);
-		__entry->dev_minor	= MINOR(journal->j_fs_dev->bd_dev);
+		__entry->dev		= journal->j_fs_dev->bd_dev;
 		__entry->sync_commit = commit_transaction->t_synchronous_commit;
 		__entry->transaction	= commit_transaction->t_tid;
 	),
 
-	TP_printk("dev %d,%d transaction %d sync %d",
-		  __entry->dev_major, __entry->dev_minor,
-		  __entry->transaction, __entry->sync_commit)
+	TP_printk("dev %s transaction %d sync %d",
+		  jbd2_dev_to_name(__entry->dev), __entry->transaction,
+		  __entry->sync_commit)
 );
 
 DEFINE_EVENT(jbd2_commit, jbd2_start_commit,
@@ -91,24 +87,22 @@ TRACE_EVENT(jbd2_end_commit,
 	TP_ARGS(journal, commit_transaction),
 
 	TP_STRUCT__entry(
-		__field(	int,   dev_major                )
-		__field(	int,   dev_minor                )
+		__field(	dev_t,	dev			)
 		__field(	char,	sync_commit		  )
 		__field(	int,	transaction		  )
 		__field(	int,	head		  	  )
 	),
 
 	TP_fast_assign(
-		__entry->dev_major	= MAJOR(journal->j_fs_dev->bd_dev);
-		__entry->dev_minor	= MINOR(journal->j_fs_dev->bd_dev);
+		__entry->dev		= journal->j_fs_dev->bd_dev;
 		__entry->sync_commit = commit_transaction->t_synchronous_commit;
 		__entry->transaction	= commit_transaction->t_tid;
 		__entry->head		= journal->j_tail_sequence;
 	),
 
-	TP_printk("dev %d,%d transaction %d sync %d head %d",
-		  __entry->dev_major, __entry->dev_minor,
-		  __entry->transaction, __entry->sync_commit, __entry->head)
+	TP_printk("dev %s transaction %d sync %d head %d",
+		  jbd2_dev_to_name(__entry->dev), __entry->transaction,
+		  __entry->sync_commit, __entry->head)
 );
 
 TRACE_EVENT(jbd2_submit_inode_data,
@@ -117,20 +111,17 @@ TRACE_EVENT(jbd2_submit_inode_data,
 	TP_ARGS(inode),
 
 	TP_STRUCT__entry(
-		__field(	int,   dev_major                )
-		__field(	int,   dev_minor                )
+		__field(	dev_t,	dev			)
 		__field(	ino_t,	ino			)
 	),
 
 	TP_fast_assign(
-		__entry->dev_major = MAJOR(inode->i_sb->s_dev);
-		__entry->dev_minor = MINOR(inode->i_sb->s_dev);
+		__entry->dev	= inode->i_sb->s_dev;
 		__entry->ino	= inode->i_ino;
 	),
 
-	TP_printk("dev %d,%d ino %lu",
-		  __entry->dev_major, __entry->dev_minor,
-		  (unsigned long) __entry->ino)
+	TP_printk("dev %s ino %lu",
+		  jbd2_dev_to_name(__entry->dev), (unsigned long) __entry->ino)
 );
 
 TRACE_EVENT(jbd2_run_stats,
@@ -140,8 +131,7 @@ TRACE_EVENT(jbd2_run_stats,
 	TP_ARGS(dev, tid, stats),
 
 	TP_STRUCT__entry(
-		__field(		  int,	dev_major	)
-		__field(		  int,	dev_minor	)
+		__field(		dev_t,	dev		)
 		__field(	unsigned long,	tid		)
 		__field(	unsigned long,	wait		)
 		__field(	unsigned long,	running		)
@@ -154,8 +144,7 @@ TRACE_EVENT(jbd2_run_stats,
 	),
 
 	TP_fast_assign(
-		__entry->dev_major	= MAJOR(dev);
-		__entry->dev_minor	= MINOR(dev);
+		__entry->dev		= dev;
 		__entry->tid		= tid;
 		__entry->wait		= stats->rs_wait;
 		__entry->running	= stats->rs_running;
@@ -167,9 +156,9 @@ TRACE_EVENT(jbd2_run_stats,
 		__entry->blocks_logged	= stats->rs_blocks_logged;
 	),
 
-	TP_printk("dev %d,%d tid %lu wait %u running %u locked %u flushing %u "
+	TP_printk("dev %s tid %lu wait %u running %u locked %u flushing %u "
 		  "logging %u handle_count %u blocks %u blocks_logged %u",
-		  __entry->dev_major, __entry->dev_minor, __entry->tid,
+		  jbd2_dev_to_name(__entry->dev), __entry->tid,
 		  jiffies_to_msecs(__entry->wait),
 		  jiffies_to_msecs(__entry->running),
 		  jiffies_to_msecs(__entry->locked),
@@ -186,8 +175,7 @@ TRACE_EVENT(jbd2_checkpoint_stats,
 	TP_ARGS(dev, tid, stats),
 
 	TP_STRUCT__entry(
-		__field(		  int,	dev_major	)
-		__field(		  int,	dev_minor	)
+		__field(		dev_t,	dev		)
 		__field(	unsigned long,	tid		)
 		__field(	unsigned long,	chp_time	)
 		__field(		__u32,	forced_to_close	)
@@ -196,8 +184,7 @@ TRACE_EVENT(jbd2_checkpoint_stats,
 	),
 
 	TP_fast_assign(
-		__entry->dev_major	= MAJOR(dev);
-		__entry->dev_minor	= MINOR(dev);
+		__entry->dev		= dev;
 		__entry->tid		= tid;
 		__entry->chp_time	= stats->cs_chp_time;
 		__entry->forced_to_close= stats->cs_forced_to_close;
@@ -205,9 +192,9 @@ TRACE_EVENT(jbd2_checkpoint_stats,
 		__entry->dropped	= stats->cs_dropped;
 	),
 
-	TP_printk("dev %d,%d tid %lu chp_time %u forced_to_close %u "
+	TP_printk("dev %s tid %lu chp_time %u forced_to_close %u "
 		  "written %u dropped %u",
-		  __entry->dev_major, __entry->dev_minor, __entry->tid,
+		  jbd2_dev_to_name(__entry->dev), __entry->tid,
 		  jiffies_to_msecs(__entry->chp_time),
 		  __entry->forced_to_close, __entry->written, __entry->dropped)
 );
@@ -220,8 +207,7 @@ TRACE_EVENT(jbd2_cleanup_journal_tail,
 	TP_ARGS(journal, first_tid, block_nr, freed),
 
 	TP_STRUCT__entry(
-		__field(	int,   dev_major                )
-		__field(	int,   dev_minor                )
+		__field(	dev_t,	dev			)
 		__field(	tid_t,	tail_sequence		)
 		__field(	tid_t,	first_tid		)
 		__field(unsigned long,	block_nr		)
@@ -229,18 +215,16 @@ TRACE_EVENT(jbd2_cleanup_journal_tail,
 	),
 
 	TP_fast_assign(
-		__entry->dev_major	= MAJOR(journal->j_fs_dev->bd_dev);
-		__entry->dev_minor	= MINOR(journal->j_fs_dev->bd_dev);
+		__entry->dev		= journal->j_fs_dev->bd_dev;
 		__entry->tail_sequence	= journal->j_tail_sequence;
 		__entry->first_tid	= first_tid;
 		__entry->block_nr	= block_nr;
 		__entry->freed		= freed;
 	),
 
-	TP_printk("dev %d,%d from %u to %u offset %lu freed %lu",
-		  __entry->dev_major, __entry->dev_minor,
-		  __entry->tail_sequence, __entry->first_tid,
-		  __entry->block_nr, __entry->freed)
+	TP_printk("dev %s from %u to %u offset %lu freed %lu",
+		  jbd2_dev_to_name(__entry->dev), __entry->tail_sequence,
+		  __entry->first_tid, __entry->block_nr, __entry->freed)
 );
 
 #endif /* _TRACE_JBD2_H */