linux.git/fs/f2fs/node.c, branch v4.0

f2fs: fix accessing wrong indexed data blocks

2015-02-12T01:04:51+00:00

This patch fixes the following test.

This causes:
 attempt to access beyond end of device
 sdb2: rw=16384, want=14413962000, limit=16777216

The reason is:
 - f2fs_write_begin
  - f2fs_convert_inline_inode returns -ENOSPC
  - f2fs_write_failed
   - truncate_blocks
    - truncate_partial_data_page
     - find_data_page
      - get_dnode_of_data returns wrong data index retrieved from inline_data
      - f2fs_submit_page_bio(wrong data index)
       - submit_bio(wrong data index)

Signed-off-by: Jaegeuk Kim

f2fs: check node page contents all the time

2015-02-12T01:04:46+00:00

In get_node_page, if the page is up-to-date, we assumed that the page was not
reclaimed at all.
But, sometimes it was reported that its contents was missing.
So, just for sure, let's check its mapping and contents.

Signed-off-by: Jaegeuk Kim

f2fs: merge {invalidate,release}page for meta/node/data pages

2015-02-12T01:04:44+00:00

This patch merges ->{invalidate,release}page function for meta/node/data pages.

After this, duplication of codes could be removed.

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

f2fs: keep PagePrivate during releasepage

2015-02-12T01:04:42+00:00

If PagePrivate is removed by releasepage, f2fs loses counting dirty pages.

e.g., try_to_release_page will not release page when the page is dirty,
but our releasepage removes PagePrivate.

    [] try_to_release_page+0x35/0x50
    [] invalidate_inode_pages2_range+0x2f9/0x3b0
    [] ? truncate_blocks+0x384/0x4d0 [f2fs]
    [] ? f2fs_direct_IO+0x283/0x290 [f2fs]
    [] ? get_data_block_fiemap+0x20/0x20 [f2fs]
    [] generic_file_direct_write+0x163/0x170
    [] __generic_file_write_iter+0x2a6/0x350
    [] generic_file_write_iter+0x3f/0xb0
    [] new_sync_write+0x81/0xb0
    [] vfs_write+0xb7/0x1f0
    [] SyS_write+0x49/0xb0
    [] system_call_fastpath+0x16/0x1b

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

f2fs: merge flags in struct f2fs_sb_info

2015-02-12T01:04:38+00:00

Currently, there are several variables with Boolean type as below:

struct f2fs_sb_info {
...
	int s_dirty;
	bool need_fsck;
	bool s_closing;
...
	bool por_doing;
...
}

For this there are some issues:
1. there are some space of f2fs_sb_info is wasted due to aligning after Boolean
   type variables by compiler.
2. if we continuously add new flag into f2fs_sb_info, structure will be messed
   up.

So in this patch, we try to:
1. switch s_dirty to Boolean type variable since it has two status 0/1.
2. merge s_dirty/need_fsck/s_closing/por_doing variables into s_flag.
3. introduce an enum type which can indicate different states of sbi.
4. use new introduced universal interfaces is_sbi_flag_set/{set,clear}_sbi_flag
   to operate flags for sbi.

After that, above issues will be fixed.

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

f2fs: free radix_tree_nodes used by nat_set entries

2015-01-10T01:02:28+00:00

In the normal case, the radix_tree_nodes are freed successfully.
But, when cp_error was detected, we should destroy them forcefully.

Signed-off-by: Jaegeuk Kim

f2fs: avoid potential unnecessary codes

2015-01-10T01:02:26+00:00

This patch relocates some operations to avoid unnecessary execution.

Signed-off-by: Jaegeuk Kim

f2fs: activate f2fs_trace_pid

2015-01-10T01:02:24+00:00

This patch activates f2fs_trace_pid.

Signed-off-by: Jaegeuk Kim

f2fs: use f2fs_io_info to clean up messy parameters during IO path

2015-01-10T01:02:23+00:00

This patch cleans up parameters on IO paths.
The key idea is to use f2fs_io_info adding a parameter, block address, and then
use this structure as parameters.

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

f2fs: use ra_meta_pages to simplify readahead code in restore_node_summary

2015-01-10T01:02:23+00:00

Use more common function ra_meta_pages() with META_POR to readahead node blocks
in restore_node_summary() instead of ra_sum_pages(), hence we can simplify the
readahead code there, and also we can remove unused function ra_sum_pages().

changes from v2:
 o use invalidate_mapping_pages as before suggested by Changman Lee.
changes from v1:
 o fix one bug when using truncate_inode_pages_range which is pointed out by
   Jaegeuk Kim.

Reviewed-by: Changman Lee 
Signed-off-by: Chao Yu 
Signed-off-by: Jaegeuk Kim