hollalinux
/
linux-sg2042
mirror of https://github.com/sophgo/linux-riscv.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

Merge branch 'for-4.10/fs-unmap' of git://git.kernel.dk/linux-block 

Pull fs meta data unmap optimization from Jens Axboe:
 "A series from Jan Kara, providing a more efficient way for unmapping
  meta data from in the buffer cache than doing it block-by-block.

  Provide a general helper that existing callers can use"

* 'for-4.10/fs-unmap' of git://git.kernel.dk/linux-block:
  fs: Remove unmap_underlying_metadata
  fs: Add helper to clean bdev aliases under a bh and use it
  ext2: Use clean_bdev_aliases() instead of iteration
  ext4: Use clean_bdev_aliases() instead of iteration
  direct-io: Use clean_bdev_aliases() instead of handmade iteration
  fs: Provide function to unmap metadata for a range of blocks
This commit is contained in:
Linus Torvalds 2016-12-14 17:09:00 -08:00
parent 852d21ae1f ce98321bf7
commit 80eabba702
13 changed files with 102 additions and 93 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

100
fs/buffer.c
View File

@ -43,6 +43,7 @@
#include <linux/bitops.h>
#include <linux/mpage.h>
#include <linux/bit_spinlock.h>
#include <linux/pagevec.h>
#include <trace/events/block.h>
static int fsync_buffers_list(spinlock_t *lock, struct list_head *list);
@ -1604,37 +1605,80 @@ void create_empty_buffers(struct page *page,
}
EXPORT_SYMBOL(create_empty_buffers);
/*
* We are taking a block for data and we don't want any output from any
* buffer-cache aliases starting from return from that function and
* until the moment when something will explicitly mark the buffer
* dirty (hopefully that will not happen until we will free that block ;-)
* We don't even need to mark it not-uptodate - nobody can expect
* anything from a newly allocated buffer anyway. We used to used
* unmap_buffer() for such invalidation, but that was wrong. We definitely
* don't want to mark the alias unmapped, for example - it would confuse
* anyone who might pick it with bread() afterwards...
/**
* clean_bdev_aliases: clean a range of buffers in block device
* @bdev: Block device to clean buffers in
* @block: Start of a range of blocks to clean
* @len: Number of blocks to clean
*
* Also.. Note that bforget() doesn't lock the buffer. So there can
* be writeout I/O going on against recently-freed buffers. We don't
* wait on that I/O in bforget() - it's more efficient to wait on the I/O
* only if we really need to. That happens here.
* We are taking a range of blocks for data and we don't want writeback of any
* buffer-cache aliases starting from return from this function and until the
* moment when something will explicitly mark the buffer dirty (hopefully that
* will not happen until we will free that block ;-) We don't even need to mark
* it not-uptodate - nobody can expect anything from a newly allocated buffer
* anyway. We used to use unmap_buffer() for such invalidation, but that was
* wrong. We definitely don't want to mark the alias unmapped, for example - it
* would confuse anyone who might pick it with bread() afterwards...
*
* Also.. Note that bforget() doesn't lock the buffer. So there can be
* writeout I/O going on against recently-freed buffers. We don't wait on that
* I/O in bforget() - it's more efficient to wait on the I/O only if we really
* need to. That happens here.
*/
void unmap_underlying_metadata(struct block_device *bdev, sector_t block)
void clean_bdev_aliases(struct block_device *bdev, sector_t block, sector_t len)
{
struct buffer_head *old_bh;
struct inode *bd_inode = bdev->bd_inode;
struct address_space *bd_mapping = bd_inode->i_mapping;
struct pagevec pvec;
pgoff_t index = block >> (PAGE_SHIFT - bd_inode->i_blkbits);
pgoff_t end;
int i;
struct buffer_head *bh;
struct buffer_head *head;
might_sleep();
end = (block + len - 1) >> (PAGE_SHIFT - bd_inode->i_blkbits);
pagevec_init(&pvec, 0);
while (index <= end && pagevec_lookup(&pvec, bd_mapping, index,
min(end - index, (pgoff_t)PAGEVEC_SIZE - 1) + 1)) {
for (i = 0; i < pagevec_count(&pvec); i++) {
struct page *page = pvec.pages[i];
old_bh = __find_get_block_slow(bdev, block);
if (old_bh) {
clear_buffer_dirty(old_bh);
wait_on_buffer(old_bh);
clear_buffer_req(old_bh);
__brelse(old_bh);
index = page->index;
if (index > end)
break;
if (!page_has_buffers(page))
continue;
/*
* We use page lock instead of bd_mapping->private_lock
* to pin buffers here since we can afford to sleep and
* it scales better than a global spinlock lock.
*/
lock_page(page);
/* Recheck when the page is locked which pins bhs */
if (!page_has_buffers(page))
goto unlock_page;
head = page_buffers(page);
bh = head;
do {
if (!buffer_mapped(bh))
goto next;
if (bh->b_blocknr >= block + len)
break;
clear_buffer_dirty(bh);
wait_on_buffer(bh);
clear_buffer_req(bh);
next:
bh = bh->b_this_page;
} while (bh != head);
unlock_page:
unlock_page(page);
}
pagevec_release(&pvec);
cond_resched();
index++;
}
}
EXPORT_SYMBOL(unmap_underlying_metadata);
EXPORT_SYMBOL(clean_bdev_aliases);
/*
* Size is a power-of-two in the range 512..PAGE_SIZE,
@ -1745,8 +1789,7 @@ int __block_write_full_page(struct inode *inode, struct page *page,
if (buffer_new(bh)) {
/* blockdev mappings never come here */
clear_buffer_new(bh);
unmap_underlying_metadata(bh->b_bdev,
bh->b_blocknr);
clean_bdev_bh_alias(bh);
}
}
bh = bh->b_this_page;
@ -1992,8 +2035,7 @@ int __block_write_begin_int(struct page *page, loff_t pos, unsigned len,
}
if (buffer_new(bh)) {
unmap_underlying_metadata(bh->b_bdev,
bh->b_blocknr);
clean_bdev_bh_alias(bh);
if (PageUptodate(page)) {
clear_buffer_new(bh);
set_buffer_uptodate(bh);
@ -2633,7 +2675,7 @@ int nobh_write_begin(struct address_space *mapping,
if (!buffer_mapped(bh))
is_mapped_to_disk = 0;
if (buffer_new(bh))
unmap_underlying_metadata(bh->b_bdev, bh->b_blocknr);
clean_bdev_bh_alias(bh);
if (PageUptodate(page)) {
set_buffer_uptodate(bh);
continue;

28
fs/direct-io.c
View File

@ -842,24 +842,6 @@ out:
return ret;
}
/*
* Clean any dirty buffers in the blockdev mapping which alias newly-created
* file blocks. Only called for S_ISREG files - blockdevs do not set
* buffer_new
*/
static void clean_blockdev_aliases(struct dio *dio, struct buffer_head *map_bh)
{
unsigned i;
unsigned nblocks;
nblocks = map_bh->b_size >> dio->inode->i_blkbits;
for (i = 0; i < nblocks; i++) {
unmap_underlying_metadata(map_bh->b_bdev,
map_bh->b_blocknr + i);
}
}
/*
* If we are not writing the entire block and get_block() allocated
* the block for us, we need to fill-in the unused portion of the
@ -960,11 +942,15 @@ static int do_direct_IO(struct dio *dio, struct dio_submit *sdio,
goto do_holes;
sdio->blocks_available =
map_bh->b_size >> sdio->blkbits;
map_bh->b_size >> blkbits;
sdio->next_block_for_io =
map_bh->b_blocknr << sdio->blkfactor;
if (buffer_new(map_bh))
clean_blockdev_aliases(dio, map_bh);
if (buffer_new(map_bh)) {
clean_bdev_aliases(
map_bh->b_bdev,
map_bh->b_blocknr,
map_bh->b_size >> blkbits);
}
if (!sdio->blkfactor)
goto do_holes;

9
fs/ext2/inode.c
View File

@ -732,16 +732,13 @@ static int ext2_get_blocks(struct inode *inode,
}
if (IS_DAX(inode)) {
int i;
/*
* We must unmap blocks before zeroing so that writeback cannot
* overwrite zeros with stale data from block device page cache.
*/
for (i = 0; i < count; i++) {
unmap_underlying_metadata(inode->i_sb->s_bdev,
le32_to_cpu(chain[depth-1].key) + i);
}
clean_bdev_aliases(inode->i_sb->s_bdev,
le32_to_cpu(chain[depth-1].key),
count);
/*
* block must be initialised before we put it in the tree
* so that it's not found by another thread before it's

13
fs/ext4/extents.c
View File

@ -3777,14 +3777,6 @@ out:
return err;
}
static void unmap_underlying_metadata_blocks(struct block_device *bdev,
sector_t block, int count)
{
int i;
for (i = 0; i < count; i++)
unmap_underlying_metadata(bdev, block + i);
}
/*
* Handle EOFBLOCKS_FL flag, clearing it if necessary
*/
@ -4121,9 +4113,8 @@ out:
* new.
*/
if (allocated > map->m_len) {
unmap_underlying_metadata_blocks(inode->i_sb->s_bdev,
newblock + map->m_len,
allocated - map->m_len);
clean_bdev_aliases(inode->i_sb->s_bdev, newblock + map->m_len,
allocated - map->m_len);
allocated = map->m_len;
}
map->m_len = allocated;

18
fs/ext4/inode.c
View File

@ -661,12 +661,8 @@ found:
if (flags & EXT4_GET_BLOCKS_ZERO &&
map->m_flags & EXT4_MAP_MAPPED &&
map->m_flags & EXT4_MAP_NEW) {
ext4_lblk_t i;
for (i = 0; i < map->m_len; i++) {
unmap_underlying_metadata(inode->i_sb->s_bdev,
map->m_pblk + i);
}
clean_bdev_aliases(inode->i_sb->s_bdev, map->m_pblk,
map->m_len);
ret = ext4_issue_zeroout(inode, map->m_lblk,
map->m_pblk, map->m_len);
if (ret) {
@ -1137,8 +1133,7 @@ static int ext4_block_write_begin(struct page *page, loff_t pos, unsigned len,
if (err)
break;
if (buffer_new(bh)) {
unmap_underlying_metadata(bh->b_bdev,
bh->b_blocknr);
clean_bdev_bh_alias(bh);
if (PageUptodate(page)) {
clear_buffer_new(bh);
set_buffer_uptodate(bh);
@ -2371,11 +2366,8 @@ static int mpage_map_one_extent(handle_t *handle, struct mpage_da_data *mpd)
BUG_ON(map->m_len == 0);
if (map->m_flags & EXT4_MAP_NEW) {
struct block_device *bdev = inode->i_sb->s_bdev;
int i;
for (i = 0; i < map->m_len; i++)
unmap_underlying_metadata(bdev, map->m_pblk + i);
clean_bdev_aliases(inode->i_sb->s_bdev, map->m_pblk,
map->m_len);
}
return 0;
}

2
fs/ext4/page-io.c
View File

@ -457,7 +457,7 @@ int ext4_bio_write_page(struct ext4_io_submit *io,
}
if (buffer_new(bh)) {
clear_buffer_new(bh);
unmap_underlying_metadata(bh->b_bdev, bh->b_blocknr);
clean_bdev_bh_alias(bh);
}
set_buffer_async_write(bh);
nr_to_submit++;

3
fs/mpage.c
View File

@ -555,8 +555,7 @@ static int __mpage_writepage(struct page *page, struct writeback_control *wbc,
if (mpd->get_block(inode, block_in_file, &map_bh, 1))
goto confused;
if (buffer_new(&map_bh))
unmap_underlying_metadata(map_bh.b_bdev,
map_bh.b_blocknr);
clean_bdev_bh_alias(&map_bh);
if (buffer_boundary(&map_bh)) {
boundary_block = map_bh.b_blocknr;
boundary_bdev = map_bh.b_bdev;

2
fs/ntfs/aops.c
View File

@ -765,7 +765,7 @@ lock_retry_remap:
}
// TODO: Instantiate the hole.
// clear_buffer_new(bh);
// unmap_underlying_metadata(bh->b_bdev, bh->b_blocknr);
// clean_bdev_bh_alias(bh);
ntfs_error(vol->sb, "Writing into sparse regions is "
"not supported yet. Sorry.");
err = -EOPNOTSUPP;

5
fs/ntfs/file.c
View File

@ -740,8 +740,7 @@ map_buffer_cached:
set_buffer_uptodate(bh);
if (unlikely(was_hole)) {
/* We allocated the buffer. */
unmap_underlying_metadata(bh->b_bdev,
bh->b_blocknr);
clean_bdev_bh_alias(bh);
if (bh_end <= pos || bh_pos >= end)
mark_buffer_dirty(bh);
else
@ -784,7 +783,7 @@ map_buffer_cached:
continue;
}
/* We allocated the buffer. */
unmap_underlying_metadata(bh->b_bdev, bh->b_blocknr);
clean_bdev_bh_alias(bh);
/*
* If the buffer is fully outside the write, zero it,
* set it uptodate, and mark it dirty so it gets

2
fs/ocfs2/aops.c
View File

@ -630,7 +630,7 @@ int ocfs2_map_page_blocks(struct page *page, u64 *p_blkno,
if (!buffer_mapped(bh)) {
map_bh(bh, inode->i_sb, *p_blkno);
unmap_underlying_metadata(bh->b_bdev, bh->b_blocknr);
clean_bdev_bh_alias(bh);
}
if (PageUptodate(page)) {

3
fs/ufs/balloc.c
View File

@ -307,8 +307,7 @@ static void ufs_change_blocknr(struct inode *inode, sector_t beg,
(unsigned long long)(pos + newb), pos);
bh->b_blocknr = newb + pos;
unmap_underlying_metadata(bh->b_bdev,
bh->b_blocknr);
clean_bdev_bh_alias(bh);
mark_buffer_dirty(bh);
++j;
bh = bh->b_this_page;

3
fs/ufs/inode.c
View File

@ -1070,8 +1070,7 @@ static int ufs_alloc_lastblock(struct inode *inode, loff_t size)
if (buffer_new(bh)) {
clear_buffer_new(bh);
unmap_underlying_metadata(bh->b_bdev,
bh->b_blocknr);
clean_bdev_bh_alias(bh);
/*
* we do not zeroize fragment, because of
* if it maped to hole, it already contains zeroes

7
include/linux/buffer_head.h
View File

@ -168,7 +168,12 @@ int inode_has_buffers(struct inode *);
void invalidate_inode_buffers(struct inode *);
int remove_inode_buffers(struct inode *inode);
int sync_mapping_buffers(struct address_space *mapping);
void unmap_underlying_metadata(struct block_device *bdev, sector_t block);
void clean_bdev_aliases(struct block_device *bdev, sector_t block,
sector_t len);
static inline void clean_bdev_bh_alias(struct buffer_head *bh)
{
clean_bdev_aliases(bh->b_bdev, bh->b_blocknr, 1);
}
void mark_buffer_async_write(struct buffer_head *bh);
void __wait_on_buffer(struct buffer_head *);