linux-stable.git/fs/f2fs, branch v3.16

f2fs: avoid to access NULL pointer in issue_flush_thread

2014-07-09T12:59:55+00:00

Bugzilla: https://bugzilla.kernel.org/show_bug.cgi?id=75861

Denis 2014-05-10 11:28:59 UTC reported:
"F2FS-fs (mmcblk0p28): mounting..
 Unable to handle kernel NULL pointer dereference at virtual address 00000018
 ...
 [] (_raw_spin_lock+0x3c/0x70) from [] (issue_flush_thread+0x50/0x17c)
 [] (issue_flush_thread+0x50/0x17c) from [] (kthread+0x98/0xa4)
 [] (kthread+0x98/0xa4) from [] (kernel_thread_exit+0x0/0x8)"

This patch assign cmd_control_info in sm_info before issue_flush_thread is being
created, so this make sure that issue flush thread will have no chance to access
invalid info in fcc.

Signed-off-by: Chao Yu 
Reviewed-by: Gu Zheng 
Signed-off-by: Jaegeuk Kim

f2fs: check bdi->dirty_exceeded when trying to skip data writes

2014-07-09T12:59:45+00:00

If we don't check the current backing device status, balance_dirty_pages can
fall into infinite pausing routine.

This can be occurred when a lot of directories make a small number of dirty
dentry pages including files.

Reported-by: Brian Chadwick 
Signed-off-by: Jaegeuk Kim

f2fs: do checkpoint for the renamed inode

2014-07-09T12:59:31+00:00

If an inode is renamed, it should be registered as file_lost_pino to conduct
checkpoint at f2fs_sync_file.
Otherwise, the inode cannot be recovered due to no dent_mark in the following
scenario.

Note that, this scenario is from xfstests/322.

1. create "a"
2. fsync "a"
3. rename "a" to "b"
4. fsync "b"
5. Sudden power-cut

After recovery is done, "b" should be seen.
However, the result shows "a", since the recovery procedure does not enter
recover_dentry due to no dent_mark.

The reason is like below.
- The nid of "a" is checkpointed during #2, f2fs_sync_file.
- The inode page for "b" produced by #3 is written without dent_mark by
sync_node_pages.

So, this patch fixes this bug by assinging file_lost_pino to the "a"'s inode.
If the pino is lost, f2fs_sync_file conducts checkpoint, and then recovers
the latest pino and its dentry information for further recovery.

Signed-off-by: Jaegeuk Kim

f2fs: release new entry page correctly in error path of f2fs_rename

2014-07-09T12:59:11+00:00

This patch correct releasing code of new_page to avoid BUG_ON in error patch of
f2fs_rename.

Signed-off-by: Chao Yu 
Signed-off-by: Jaegeuk Kim

f2fs: fix error path in init_inode_metadata

2014-07-09T12:58:50+00:00

If we fail in this path:
->init_inode_metadata
  ->make_empty_dir
    ->get_new_data_page
      ->grab_cache_page return -ENOMEM

We will bug on in error path of init_inode_metadata when call remove_inode_page
because i_block = 2 (one inode block will be released later & one dentry block).

We should release the dentry block in init_inode_metadata to avoid this BUG_ON,
and avoid leak of dentry block resource, because we never have second chance to
release that block in ->evict_inode as in upper error path we make this inode
'bad'.

Signed-off-by: Chao Yu 
Signed-off-by: Jaegeuk Kim

f2fs: check lower bound nid value in check_nid_range

2014-07-09T12:58:08+00:00

This patch add lower bound verification for nid in check_nid_range, so nids
reserved like 0, node, meta passed by caller could be checked there.

And then check_nid_range could be used in f2fs_nfs_get_inode for simplifying
code.

Signed-off-by: Chao Yu 
Signed-off-by: Jaegeuk Kim

f2fs: remove unused variables in f2fs_sm_info

2014-07-09T12:57:57+00:00

Remove unused variables in struct f2fs_sm_info.

Signed-off-by: Chao Yu 
Signed-off-by: Jaegeuk Kim

f2fs: fix not to allocate unnecessary blocks during fallocate

2014-06-23T01:05:08+00:00

This patch fixes the fallocate bug like below. (See xfstests/255)

In fallocate(fd, 0, 20480),
expand_inode_data processes
	for (index = pg_start; index <= pg_end; index++) {
		f2fs_reserve_block();
		...
	}

So, even though fallocate requests 20480, 5 blocks, f2fs allocates 6 blocks
including pg_end.
So, this patch adds one condition to avoid block allocation.

Signed-off-by: Jaegeuk Kim

f2fs: recover fallocated data and its i_size together

2014-06-23T01:05:08+00:00

This patch arranges the f2fs_locks to cover the fallocated data and its i_size.

Signed-off-by: Jaegeuk Kim

f2fs: fix to report newly allocate region as extent

2014-06-23T01:05:07+00:00

Previous get_block in f2fs didn't report the newly allocated region which has
NEW_ADDR.
For reader, it should not report, but fiemap needs this.
So, this patch introduces two get_block sharing core function.

Signed-off-by: Jaegeuk Kim