提交 32443de3 编写于 作者: Q Qu Wenruo 提交者: David Sterba

btrfs: introduce btrfs_subpage for data inodes

To support subpage sector size, data also need extra info to make sure
which sectors in a page are uptodate/dirty/...

This patch will make pages for data inodes get btrfs_subpage structure
attached, and detached when the page is freed.

This patch also slightly changes the timing when
set_page_extent_mapped() is called to make sure:

- We have page->mapping set
  page->mapping->host is used to grab btrfs_fs_info, thus we can only
  call this function after page is mapped to an inode.

  One call site attaches pages to inode manually, thus we have to modify
  the timing of set_page_extent_mapped() a bit.

- As soon as possible, before other operations
  Since memory allocation can fail, we have to do extra error handling.
  Calling set_page_extent_mapped() as soon as possible can simply the
  error handling for several call sites.

The idea is pretty much the same as iomap_page, but with more bitmaps
for btrfs specific cases.

Currently the plan is to switch iomap if iomap can provide sector
aligned write back (only write back dirty sectors, but not the full
page, data balance require this feature).

So we will stick to btrfs specific bitmap for now.
Signed-off-by: NQu Wenruo <wqu@suse.com>
Reviewed-by: NDavid Sterba <dsterba@suse.com>
Signed-off-by: NDavid Sterba <dsterba@suse.com>
上级 371cdc07
......@@ -542,13 +542,19 @@ static noinline int add_ra_bio_pages(struct inode *inode,
goto next;
}
end = last_offset + PAGE_SIZE - 1;
/*
* at this point, we have a locked page in the page cache
* for these bytes in the file. But, we have to make
* sure they map to this compressed extent on disk.
*/
set_page_extent_mapped(page);
ret = set_page_extent_mapped(page);
if (ret < 0) {
unlock_page(page);
put_page(page);
break;
}
end = last_offset + PAGE_SIZE - 1;
lock_extent(tree, last_offset, end);
read_lock(&em_tree->lock);
em = lookup_extent_mapping(em_tree, last_offset,
......
......@@ -3191,10 +3191,38 @@ static int attach_extent_buffer_page(struct extent_buffer *eb,
return ret;
}
void set_page_extent_mapped(struct page *page)
int set_page_extent_mapped(struct page *page)
{
struct btrfs_fs_info *fs_info;
ASSERT(page->mapping);
if (PagePrivate(page))
return 0;
fs_info = btrfs_sb(page->mapping->host->i_sb);
if (fs_info->sectorsize < PAGE_SIZE)
return btrfs_attach_subpage(fs_info, page, BTRFS_SUBPAGE_DATA);
attach_page_private(page, (void *)EXTENT_PAGE_PRIVATE);
return 0;
}
void clear_page_extent_mapped(struct page *page)
{
struct btrfs_fs_info *fs_info;
ASSERT(page->mapping);
if (!PagePrivate(page))
attach_page_private(page, (void *)EXTENT_PAGE_PRIVATE);
return;
fs_info = btrfs_sb(page->mapping->host->i_sb);
if (fs_info->sectorsize < PAGE_SIZE)
return btrfs_detach_subpage(fs_info, page);
detach_page_private(page);
}
static struct extent_map *
......@@ -3251,7 +3279,12 @@ int btrfs_do_readpage(struct page *page, struct extent_map **em_cached,
unsigned long this_bio_flag = 0;
struct extent_io_tree *tree = &BTRFS_I(inode)->io_tree;
set_page_extent_mapped(page);
ret = set_page_extent_mapped(page);
if (ret < 0) {
unlock_extent(tree, start, end);
SetPageError(page);
goto out;
}
if (!PageUptodate(page)) {
if (cleancache_get_page(page) == 0) {
......@@ -3691,7 +3724,11 @@ static int __extent_writepage(struct page *page, struct writeback_control *wbc,
flush_dcache_page(page);
}
set_page_extent_mapped(page);
ret = set_page_extent_mapped(page);
if (ret < 0) {
SetPageError(page);
goto done;
}
if (!epd->extent_locked) {
ret = writepage_delalloc(BTRFS_I(inode), page, wbc, start,
......
......@@ -178,7 +178,8 @@ int btree_write_cache_pages(struct address_space *mapping,
void extent_readahead(struct readahead_control *rac);
int extent_fiemap(struct btrfs_inode *inode, struct fiemap_extent_info *fieinfo,
u64 start, u64 len);
void set_page_extent_mapped(struct page *page);
int set_page_extent_mapped(struct page *page);
void clear_page_extent_mapped(struct page *page);
struct extent_buffer *alloc_extent_buffer(struct btrfs_fs_info *fs_info,
u64 start, u64 owner_root, int level);
......
......@@ -1369,6 +1369,12 @@ static noinline int prepare_pages(struct inode *inode, struct page **pages,
goto fail;
}
err = set_page_extent_mapped(pages[i]);
if (err < 0) {
faili = i;
goto fail;
}
if (i == 0)
err = prepare_uptodate_page(inode, pages[i], pos,
force_uptodate);
......@@ -1453,23 +1459,11 @@ lock_and_cleanup_extent_if_need(struct btrfs_inode *inode, struct page **pages,
}
/*
* It's possible the pages are dirty right now, but we don't want
* to clean them yet because copy_from_user may catch a page fault
* and we might have to fall back to one page at a time. If that
* happens, we'll unlock these pages and we'd have a window where
* reclaim could sneak in and drop the once-dirty page on the floor
* without writing it.
*
* We have the pages locked and the extent range locked, so there's
* no way someone can start IO on any dirty pages in this range.
*
* We'll call btrfs_dirty_pages() later on, and that will flip around
* delalloc bits and dirty the pages as required.
* We should be called after prepare_pages() which should have locked
* all pages in the range.
*/
for (i = 0; i < num_pages; i++) {
set_page_extent_mapped(pages[i]);
for (i = 0; i < num_pages; i++)
WARN_ON(!PageLocked(pages[i]));
}
return ret;
}
......
......@@ -431,11 +431,22 @@ static int io_ctl_prepare_pages(struct btrfs_io_ctl *io_ctl, bool uptodate)
int i;
for (i = 0; i < io_ctl->num_pages; i++) {
int ret;
page = find_or_create_page(inode->i_mapping, i, mask);
if (!page) {
io_ctl_drop_pages(io_ctl);
return -ENOMEM;
}
ret = set_page_extent_mapped(page);
if (ret < 0) {
unlock_page(page);
put_page(page);
io_ctl_drop_pages(io_ctl);
return ret;
}
io_ctl->pages[i] = page;
if (uptodate && !PageUptodate(page)) {
btrfs_readpage(NULL, page);
......@@ -455,10 +466,8 @@ static int io_ctl_prepare_pages(struct btrfs_io_ctl *io_ctl, bool uptodate)
}
}
for (i = 0; i < io_ctl->num_pages; i++) {
for (i = 0; i < io_ctl->num_pages; i++)
clear_page_dirty_for_io(io_ctl->pages[i]);
set_page_extent_mapped(io_ctl->pages[i]);
}
return 0;
}
......
......@@ -4720,6 +4720,9 @@ int btrfs_truncate_block(struct btrfs_inode *inode, loff_t from, loff_t len,
ret = -ENOMEM;
goto out;
}
ret = set_page_extent_mapped(page);
if (ret < 0)
goto out_unlock;
if (!PageUptodate(page)) {
ret = btrfs_readpage(NULL, page);
......@@ -4737,7 +4740,6 @@ int btrfs_truncate_block(struct btrfs_inode *inode, loff_t from, loff_t len,
wait_on_page_writeback(page);
lock_extent_bits(io_tree, block_start, block_end, &cached_state);
set_page_extent_mapped(page);
ordered = btrfs_lookup_ordered_extent(inode, block_start);
if (ordered) {
......@@ -8125,7 +8127,7 @@ static int __btrfs_releasepage(struct page *page, gfp_t gfp_flags)
{
int ret = try_release_extent_mapping(page, gfp_flags);
if (ret == 1)
detach_page_private(page);
clear_page_extent_mapped(page);
return ret;
}
......@@ -8285,7 +8287,7 @@ static void btrfs_invalidatepage(struct page *page, unsigned int offset,
}
ClearPageChecked(page);
detach_page_private(page);
clear_page_extent_mapped(page);
}
/*
......@@ -8364,7 +8366,12 @@ vm_fault_t btrfs_page_mkwrite(struct vm_fault *vmf)
wait_on_page_writeback(page);
lock_extent_bits(io_tree, page_start, page_end, &cached_state);
set_page_extent_mapped(page);
ret2 = set_page_extent_mapped(page);
if (ret2 < 0) {
ret = vmf_error(ret2);
unlock_extent_cached(io_tree, page_start, page_end, &cached_state);
goto out_unlock;
}
/*
* we can't set the delalloc bits if there are pending ordered
......
......@@ -1314,6 +1314,13 @@ static int cluster_pages_for_defrag(struct inode *inode,
if (!page)
break;
ret = set_page_extent_mapped(page);
if (ret < 0) {
unlock_page(page);
put_page(page);
break;
}
page_start = page_offset(page);
page_end = page_start + PAGE_SIZE - 1;
while (1) {
......@@ -1435,7 +1442,6 @@ static int cluster_pages_for_defrag(struct inode *inode,
for (i = 0; i < i_done; i++) {
clear_page_dirty_for_io(pages[i]);
ClearPageChecked(pages[i]);
set_page_extent_mapped(pages[i]);
set_page_dirty(pages[i]);
unlock_page(pages[i]);
put_page(pages[i]);
......
......@@ -81,7 +81,10 @@ static int copy_inline_to_page(struct btrfs_inode *inode,
goto out_unlock;
}
set_page_extent_mapped(page);
ret = set_page_extent_mapped(page);
if (ret < 0)
goto out_unlock;
clear_extent_bit(&inode->io_tree, file_offset, range_end,
EXTENT_DELALLOC | EXTENT_DO_ACCOUNTING | EXTENT_DEFRAG,
0, 0, NULL);
......
......@@ -2679,6 +2679,15 @@ static int relocate_file_extent_cluster(struct inode *inode,
goto out;
}
}
ret = set_page_extent_mapped(page);
if (ret < 0) {
btrfs_delalloc_release_metadata(BTRFS_I(inode),
PAGE_SIZE, true);
btrfs_delalloc_release_extents(BTRFS_I(inode), PAGE_SIZE);
unlock_page(page);
put_page(page);
goto out;
}
if (PageReadahead(page)) {
page_cache_async_readahead(inode->i_mapping,
......@@ -2706,8 +2715,6 @@ static int relocate_file_extent_cluster(struct inode *inode,
lock_extent(&BTRFS_I(inode)->io_tree, page_start, page_end);
set_page_extent_mapped(page);
if (nr < cluster->nr &&
page_start + offset == cluster->boundary[nr]) {
set_extent_bits(&BTRFS_I(inode)->io_tree,
......
Markdown is supported
0% .
You are about to add 0 people to the discussion. Proceed with caution.
先完成此消息的编辑!
想要评论请 注册