Commit bc32a633 authored by Linus Torvalds's avatar Linus Torvalds
Browse files

Merge tag 'ext4_for_linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tytso/ext4 

Pull ext4 updates from Ted Ts'o:
 "The first two changes involve files outside of fs/ext4:

   - submit_bh() can never return an error, so change it to return void,
     and remove the unused checks from its callers

   - fix I_DIRTY_TIME handling so it will be set even if the inode
     already has I_DIRTY_INODE

  Performance:

   - Always enable i_version counter (as btrfs and xfs already do).
     Remove some uneeded i_version bumps to avoid unnecessary nfs cache
     invalidations

   - Wake up journal waiters in FIFO order, to avoid some journal users
     from not getting a journal handle for an unfairly long time

   - In ext4_write_begin() allocate any necessary buffer heads before
     starting the journal handle

   - Don't try to prefetch the block allocation bitmaps for a read-only
     file system

  Bug Fixes:

   - Fix a number of fast commit bugs, including resources leaks and out
     of bound references in various error handling paths and/or if the
     fast commit log is corrupted

   - Avoid stopping the online resize early when expanding a file system
     which is less than 16TiB to a size greater than 16TiB

   - Fix apparent metadata corruption caused by a race with a metadata
     buffer head getting migrated while it was trying to be read

   - Mark the lazy initialization thread freezable to prevent suspend
     failures

   - Other miscellaneous bug fixes

  Cleanups:

   - Break up the incredibly long ext4_full_super() function by
     refactoring to move code into more understandable, smaller
     functions

   - Remove the deprecated (and ignored) noacl and nouser_attr mount
     option

   - Factor out some common code in fast commit handling

   - Other miscellaneous cleanups"

* tag 'ext4_for_linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tytso/ext4: (53 commits)
  ext4: fix potential out of bound read in ext4_fc_replay_scan()
  ext4: factor out ext4_fc_get_tl()
  ext4: introduce EXT4_FC_TAG_BASE_LEN helper
  ext4: factor out ext4_free_ext_path()
  ext4: remove unnecessary drop path references in mext_check_coverage()
  ext4: update 'state->fc_regions_size' after successful memory allocation
  ext4: fix potential memory leak in ext4_fc_record_regions()
  ext4: fix potential memory leak in ext4_fc_record_modified_inode()
  ext4: remove redundant checking in ext4_ioctl_checkpoint
  jbd2: add miss release buffer head in fc_do_one_pass()
  ext4: move DIOREAD_NOLOCK setting to ext4_set_def_opts()
  ext4: remove useless local variable 'blocksize'
  ext4: unify the ext4 super block loading operation
  ext4: factor out ext4_journal_data_mode_check()
  ext4: factor out ext4_load_and_init_journal()
  ext4: factor out ext4_group_desc_init() and ext4_group_desc_free()
  ext4: factor out ext4_geometry_check()
  ext4: factor out ext4_check_feature_compatibility()
  ext4: factor out ext4_init_metadata_csum()
  ext4: factor out ext4_encoding_init()
  ...
parents 7f198ba7 1b45cc5c

Documentation/filesystems/vfs.rst

+3 −0
Original line number Diff line number Diff line
@@ -274,6 +274,9 @@ or bottom half). 
	This is specifically for the inode itself being marked dirty,

	not its data.  If the update needs to be persisted by fdatasync(),

	then I_DIRTY_DATASYNC will be set in the flags argument.

	I_DIRTY_TIME will be set in the flags in case lazytime is enabled

	and struct inode has times updated since the last ->dirty_inode

	call.



``write_inode``

	this method is called when the VFS needs to write an inode to

fs/buffer.c

+10 −13
Original line number Diff line number Diff line
@@ -52,7 +52,7 @@ 
#include "internal.h"



static int fsync_buffers_list(spinlock_t *lock, struct list_head *list);

static int submit_bh_wbc(blk_opf_t opf, struct buffer_head *bh,

static void submit_bh_wbc(blk_opf_t opf, struct buffer_head *bh,

			  struct writeback_control *wbc);



#define BH_ENTRY(list) list_entry((list), struct buffer_head, b_assoc_buffers)
@@ -2673,7 +2673,7 @@ static void end_bio_bh_io_sync(struct bio *bio) 
	bio_put(bio);

}



static int submit_bh_wbc(blk_opf_t opf, struct buffer_head *bh,

static void submit_bh_wbc(blk_opf_t opf, struct buffer_head *bh,

			  struct writeback_control *wbc)

{

	const enum req_op op = opf & REQ_OP_MASK;
@@ -2717,12 +2717,11 @@ static int submit_bh_wbc(blk_opf_t opf, struct buffer_head *bh, 
	}



	submit_bio(bio);

	return 0;

}



int submit_bh(blk_opf_t opf, struct buffer_head *bh)

void submit_bh(blk_opf_t opf, struct buffer_head *bh)

{

	return submit_bh_wbc(opf, bh, NULL);

	submit_bh_wbc(opf, bh, NULL);

}

EXPORT_SYMBOL(submit_bh);
@@ -2801,8 +2800,6 @@ EXPORT_SYMBOL(write_dirty_buffer); 
 */

int __sync_dirty_buffer(struct buffer_head *bh, blk_opf_t op_flags)

{

	int ret = 0;



	WARN_ON(atomic_read(&bh->b_count) < 1);

	lock_buffer(bh);

	if (test_clear_buffer_dirty(bh)) {
@@ -2817,14 +2814,14 @@ int __sync_dirty_buffer(struct buffer_head *bh, blk_opf_t op_flags) 


		get_bh(bh);

		bh->b_end_io = end_buffer_write_sync;

		ret = submit_bh(REQ_OP_WRITE | op_flags, bh);

		submit_bh(REQ_OP_WRITE | op_flags, bh);

		wait_on_buffer(bh);

		if (!ret && !buffer_uptodate(bh))

			ret = -EIO;

		if (!buffer_uptodate(bh))

			return -EIO;

	} else {

		unlock_buffer(bh);

	}

	return ret;

	return 0;

}

EXPORT_SYMBOL(__sync_dirty_buffer);

fs/ext4/ext4.h

+1 −4
Original line number Diff line number Diff line
@@ -3592,9 +3592,6 @@ extern bool empty_inline_dir(struct inode *dir, int *has_inline_data); 
extern struct buffer_head *ext4_get_first_inline_block(struct inode *inode,

					struct ext4_dir_entry_2 **parent_de,

					int *retval);

extern int ext4_inline_data_fiemap(struct inode *inode,

				   struct fiemap_extent_info *fieinfo,

				   int *has_inline, __u64 start, __u64 len);

extern void *ext4_read_inline_link(struct inode *inode);



struct iomap;
@@ -3713,7 +3710,7 @@ extern int ext4_ext_insert_extent(handle_t *, struct inode *, 
extern struct ext4_ext_path *ext4_find_extent(struct inode *, ext4_lblk_t,

					      struct ext4_ext_path **,

					      int flags);

extern void ext4_ext_drop_refs(struct ext4_ext_path *);

extern void ext4_free_ext_path(struct ext4_ext_path *);

extern int ext4_ext_check_inode(struct inode *inode);

extern ext4_lblk_t ext4_ext_next_allocated_block(struct ext4_ext_path *path);

extern int ext4_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,

fs/ext4/extents.c

+44 −63
Original line number Diff line number Diff line
@@ -106,6 +106,25 @@ static int ext4_ext_trunc_restart_fn(struct inode *inode, int *dropped) 
	return 0;

}



static void ext4_ext_drop_refs(struct ext4_ext_path *path)

{

	int depth, i;



	if (!path)

		return;

	depth = path->p_depth;

	for (i = 0; i <= depth; i++, path++) {

		brelse(path->p_bh);

		path->p_bh = NULL;

	}

}



void ext4_free_ext_path(struct ext4_ext_path *path)

{

	ext4_ext_drop_refs(path);

	kfree(path);

}



/*

 * Make sure 'handle' has at least 'check_cred' credits. If not, restart

 * transaction with 'restart_cred' credits. The function drops i_data_sem
@@ -636,8 +655,7 @@ int ext4_ext_precache(struct inode *inode) 
	ext4_set_inode_state(inode, EXT4_STATE_EXT_PRECACHED);

out:

	up_read(&ei->i_data_sem);

	ext4_ext_drop_refs(path);

	kfree(path);

	ext4_free_ext_path(path);

	return ret;

}
@@ -724,19 +742,6 @@ static void ext4_ext_show_move(struct inode *inode, struct ext4_ext_path *path, 
#define ext4_ext_show_move(inode, path, newblock, level)

#endif



void ext4_ext_drop_refs(struct ext4_ext_path *path)

{

	int depth, i;



	if (!path)

		return;

	depth = path->p_depth;

	for (i = 0; i <= depth; i++, path++) {

		brelse(path->p_bh);

		path->p_bh = NULL;

	}

}



/*

 * ext4_ext_binsearch_idx:

 * binary search for the closest index of the given block
@@ -955,8 +960,7 @@ ext4_find_extent(struct inode *inode, ext4_lblk_t block, 
	return path;



err:

	ext4_ext_drop_refs(path);

	kfree(path);

	ext4_free_ext_path(path);

	if (orig_path)

		*orig_path = NULL;

	return ERR_PTR(ret);
@@ -2174,8 +2178,7 @@ int ext4_ext_insert_extent(handle_t *handle, struct inode *inode, 
	err = ext4_ext_dirty(handle, inode, path + path->p_depth);



cleanup:

	ext4_ext_drop_refs(npath);

	kfree(npath);

	ext4_free_ext_path(npath);

	return err;

}
@@ -3061,8 +3064,7 @@ int ext4_ext_remove_space(struct inode *inode, ext4_lblk_t start, 
		}

	}

out:

	ext4_ext_drop_refs(path);

	kfree(path);

	ext4_free_ext_path(path);

	path = NULL;

	if (err == -EAGAIN)

		goto again;
@@ -4375,8 +4377,7 @@ int ext4_ext_map_blocks(handle_t *handle, struct inode *inode, 
	allocated = map->m_len;

	ext4_ext_show_leaf(inode, path);

out:

	ext4_ext_drop_refs(path);

	kfree(path);

	ext4_free_ext_path(path);



	trace_ext4_ext_map_blocks_exit(inode, flags, map,

				       err ? err : allocated);
@@ -5245,8 +5246,7 @@ ext4_ext_shift_extents(struct inode *inode, handle_t *handle, 
			break;

	}

out:

	ext4_ext_drop_refs(path);

	kfree(path);

	ext4_free_ext_path(path);

	return ret;

}
@@ -5538,15 +5538,13 @@ static int ext4_insert_range(struct file *file, loff_t offset, loff_t len) 
					EXT4_GET_BLOCKS_METADATA_NOFAIL);

		}



		ext4_ext_drop_refs(path);

		kfree(path);

		ext4_free_ext_path(path);

		if (ret < 0) {

			up_write(&EXT4_I(inode)->i_data_sem);

			goto out_stop;

		}

	} else {

		ext4_ext_drop_refs(path);

		kfree(path);

		ext4_free_ext_path(path);

	}



	ret = ext4_es_remove_extent(inode, offset_lblk,
@@ -5766,10 +5764,8 @@ ext4_swap_extents(handle_t *handle, struct inode *inode1, 
		count -= len;



	repeat:

		ext4_ext_drop_refs(path1);

		kfree(path1);

		ext4_ext_drop_refs(path2);

		kfree(path2);

		ext4_free_ext_path(path1);

		ext4_free_ext_path(path2);

		path1 = path2 = NULL;

	}

	return replaced_count;
@@ -5848,8 +5844,7 @@ int ext4_clu_mapped(struct inode *inode, ext4_lblk_t lclu) 
	}



out:

	ext4_ext_drop_refs(path);

	kfree(path);

	ext4_free_ext_path(path);



	return err ? err : mapped;

}
@@ -5916,8 +5911,7 @@ int ext4_ext_replay_update_ex(struct inode *inode, ext4_lblk_t start, 
	ret = ext4_ext_dirty(NULL, inode, &path[path->p_depth]);

	up_write(&EXT4_I(inode)->i_data_sem);

out:

	ext4_ext_drop_refs(path);

	kfree(path);

	ext4_free_ext_path(path);

	ext4_mark_inode_dirty(NULL, inode);

	return ret;

}
@@ -5935,8 +5929,7 @@ void ext4_ext_replay_shrink_inode(struct inode *inode, ext4_lblk_t end) 
			return;

		ex = path[path->p_depth].p_ext;

		if (!ex) {

			ext4_ext_drop_refs(path);

			kfree(path);

			ext4_free_ext_path(path);

			ext4_mark_inode_dirty(NULL, inode);

			return;

		}
@@ -5949,8 +5942,7 @@ void ext4_ext_replay_shrink_inode(struct inode *inode, ext4_lblk_t end) 
		ext4_ext_dirty(NULL, inode, &path[path->p_depth]);

		up_write(&EXT4_I(inode)->i_data_sem);

		ext4_mark_inode_dirty(NULL, inode);

		ext4_ext_drop_refs(path);

		kfree(path);

		ext4_free_ext_path(path);

	}

}
@@ -5989,13 +5981,11 @@ int ext4_ext_replay_set_iblocks(struct inode *inode) 
		return PTR_ERR(path);

	ex = path[path->p_depth].p_ext;

	if (!ex) {

		ext4_ext_drop_refs(path);

		kfree(path);

		ext4_free_ext_path(path);

		goto out;

	}

	end = le32_to_cpu(ex->ee_block) + ext4_ext_get_actual_len(ex);

	ext4_ext_drop_refs(path);

	kfree(path);

	ext4_free_ext_path(path);



	/* Count the number of data blocks */

	cur = 0;
@@ -6025,30 +6015,26 @@ int ext4_ext_replay_set_iblocks(struct inode *inode) 
	if (IS_ERR(path))

		goto out;

	numblks += path->p_depth;

	ext4_ext_drop_refs(path);

	kfree(path);

	ext4_free_ext_path(path);

	while (cur < end) {

		path = ext4_find_extent(inode, cur, NULL, 0);

		if (IS_ERR(path))

			break;

		ex = path[path->p_depth].p_ext;

		if (!ex) {

			ext4_ext_drop_refs(path);

			kfree(path);

			ext4_free_ext_path(path);

			return 0;

		}

		cur = max(cur + 1, le32_to_cpu(ex->ee_block) +

					ext4_ext_get_actual_len(ex));

		ret = skip_hole(inode, &cur);

		if (ret < 0) {

			ext4_ext_drop_refs(path);

			kfree(path);

			ext4_free_ext_path(path);

			break;

		}

		path2 = ext4_find_extent(inode, cur, NULL, 0);

		if (IS_ERR(path2)) {

			ext4_ext_drop_refs(path);

			kfree(path);

			ext4_free_ext_path(path);

			break;

		}

		for (i = 0; i <= max(path->p_depth, path2->p_depth); i++) {
@@ -6062,10 +6048,8 @@ int ext4_ext_replay_set_iblocks(struct inode *inode) 
			if (cmp1 != cmp2 && cmp2 != 0)

				numblks++;

		}

		ext4_ext_drop_refs(path);

		ext4_ext_drop_refs(path2);

		kfree(path);

		kfree(path2);

		ext4_free_ext_path(path);

		ext4_free_ext_path(path2);

	}



out:
@@ -6092,13 +6076,11 @@ int ext4_ext_clear_bb(struct inode *inode) 
		return PTR_ERR(path);

	ex = path[path->p_depth].p_ext;

	if (!ex) {

		ext4_ext_drop_refs(path);

		kfree(path);

		ext4_free_ext_path(path);

		return 0;

	}

	end = le32_to_cpu(ex->ee_block) + ext4_ext_get_actual_len(ex);

	ext4_ext_drop_refs(path);

	kfree(path);

	ext4_free_ext_path(path);



	cur = 0;

	while (cur < end) {
@@ -6117,8 +6099,7 @@ int ext4_ext_clear_bb(struct inode *inode) 
					ext4_fc_record_regions(inode->i_sb, inode->i_ino,

							0, path[j].p_block, 1, 1);

				}

				ext4_ext_drop_refs(path);

				kfree(path);

				ext4_free_ext_path(path);

			}

			ext4_mb_mark_bb(inode->i_sb, map.m_pblk, map.m_len, 0);

			ext4_fc_record_regions(inode->i_sb, inode->i_ino,

fs/ext4/extents_status.c

+1 −2
Original line number Diff line number Diff line
@@ -667,8 +667,7 @@ static void ext4_es_insert_extent_ext_check(struct inode *inode, 
		}

	}

out:

	ext4_ext_drop_refs(path);

	kfree(path);

	ext4_free_ext_path(path);

}



static void ext4_es_insert_extent_ind_check(struct inode *inode,