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 to get btrfs_subpage
structure attached, and detached when the page is freed.
This patch also slightly changes the timing when
set_page_extent_mapped() 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 little.
- 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: Qu Wenruo <w...@suse.com>
---
fs/btrfs/compression.c | 10 ++++++--
fs/btrfs/extent_io.c | 46 +++++++++++++++++++++++++++++++++----
fs/btrfs/extent_io.h | 3 ++-
fs/btrfs/file.c | 24 ++++++++-----------
fs/btrfs/free-space-cache.c | 15 +++++++++---
fs/btrfs/inode.c | 12 ++++++----
fs/btrfs/ioctl.c | 5 +++-
fs/btrfs/reflink.c | 5 +++-
fs/btrfs/relocation.c | 12 ++++++++--
9 files changed, 99 insertions(+), 33 deletions(-)
diff --git a/fs/btrfs/compression.c b/fs/btrfs/compression.c
index 5ae3fa0386b7..6d203acfdeb3 100644
--- a/fs/btrfs/compression.c
+++ b/fs/btrfs/compression.c
@@ -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,
diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c
index 35fbef15d84e..4bce03fed205 100644
--- a/fs/btrfs/extent_io.c
+++ b/fs/btrfs/extent_io.c
@@ -3194,10 +3194,39 @@ static int attach_extent_buffer_page(struct
extent_buffer *eb,
return 0;
}
-void set_page_extent_mapped(struct page *page)
+int __must_check 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);
+
+ 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 *
@@ -3254,7 +3283,12 @@ 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) {
@@ -3694,7 +3728,11 @@ 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,
diff --git a/fs/btrfs/extent_io.h b/fs/btrfs/extent_io.h
index bedf761a0300..357a3380cd42 100644
--- a/fs/btrfs/extent_io.h
+++ b/fs/btrfs/extent_io.h
@@ -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 __must_check 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);
diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c
index d81ae1f518f2..63b290210eaa 100644
--- a/fs/btrfs/file.c
+++ b/fs/btrfs/file.c
@@ -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;
}
diff --git a/fs/btrfs/free-space-cache.c b/fs/btrfs/free-space-cache.c
index fd6ddd6b8165..379bef967e1d 100644
--- a/fs/btrfs/free-space-cache.c
+++ b/fs/btrfs/free-space-cache.c
@@ -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 -ENOMEM;
+ }
