In btrfs data page read path, the page status update are handled in two
different locations:
btrfs_do_read_page()
{
while (cur <= end) {
/* No need to read from disk */
if (HOLE/PREALLOC/INLINE){
memset();
set_extent_uptodate();
continue;
}
/* Read from disk */
ret = submit_extent_page(end_bio_extent_readpage);
}
end_bio_extent_readpage()
{
endio_readpage_uptodate_page_status();
}
This is fine for sectorsize == PAGE_SIZE case, as for above loop we
should only hit one branch and then exit.
But for subpage, there are more works to be done in page status update:
- Page Unlock condition
Unlike regular page size == sectorsize case, we can no longer just
unlock a page without a brain.
Only the last reader of the page can unlock the page.
This means, we can unlock the page either in the while() loop, or in
the endio function.
- Page uptodate condition
Since we have multiple sectors to read for a page, we can only mark
the full page uptodate if all sectors are uptodate.
To handle both subpage and regular cases, introduce a pair of functions
to help handling page status update:
- being_page_read()
For regular case, it does nothing.
For subpage case, it update the reader counters so that later
end_page_read() can know who is the last one to unlock the page.
- end_page_read()
This is just endio_readpage_uptodate_page_status() renamed.
The original name is a little too long and too specific for endio.
The only new trick added is the condition for page unlock.
Now for subage data, we unlock the page if we're the last reader.
This does not only provide the basis for subpage data read, but also
hide the special handling of page read from the main read loop.
Signed-off-by: Qu Wenruo <w...@suse.com>
---
fs/btrfs/extent_io.c | 38 +++++++++++++++++++----------
fs/btrfs/subpage.h | 57 +++++++++++++++++++++++++++++++++++---------
2 files changed, 72 insertions(+), 23 deletions(-)
diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c
index 4bce03fed205..6ae820144ec7 100644
--- a/fs/btrfs/extent_io.c
+++ b/fs/btrfs/extent_io.c
@@ -2839,8 +2839,17 @@ static void endio_readpage_release_extent(struct
processed_extent *processed,
processed->uptodate = uptodate;
}
-static void endio_readpage_update_page_status(struct page *page, bool uptodate,
- u64 start, u32 len)
+static void begin_data_page_read(struct btrfs_fs_info *fs_info, struct page
*page)
+{
+ ASSERT(PageLocked(page));
+ if (fs_info->sectorsize == PAGE_SIZE)
+ return;
+
+ ASSERT(PagePrivate(page));
+ btrfs_subpage_start_reader(fs_info, page, page_offset(page), PAGE_SIZE);
+}
+
+static void end_page_read(struct page *page, bool uptodate, u64 start, u32 len)
{
struct btrfs_fs_info *fs_info = btrfs_sb(page->mapping->host->i_sb);
@@ -2856,7 +2865,12 @@ static void endio_readpage_update_page_status(struct page *page, bool uptodate,
if (fs_info->sectorsize == PAGE_SIZE)
unlock_page(page);
- /* Subpage locking will be handled in later patches */
+ else if (is_data_inode(page->mapping->host))
+ /*
+ * For subpage data, unlock the page if we're the last reader.
+ * For subpage metadata, page lock is not utilized for read.
+ */
+ btrfs_subpage_end_reader(fs_info, page, start, len);
}
/*
@@ -2993,7 +3007,7 @@ static void end_bio_extent_readpage(struct bio *bio)
bio_offset += len;
/* Update page status and unlock */
- endio_readpage_update_page_status(page, uptodate, start, len);
+ end_page_read(page, uptodate, start, len);
endio_readpage_release_extent(&processed, BTRFS_I(inode),
start, end, uptodate);
}
@@ -3267,6 +3281,7 @@ int btrfs_do_readpage(struct page *page, struct
extent_map **em_cached,
unsigned int read_flags, u64 *prev_em_start)
{
struct inode *inode = page->mapping->host;
+ struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
u64 start = page_offset(page);
const u64 end = start + PAGE_SIZE - 1;
u64 cur = start;
@@ -3310,6 +3325,7 @@ int btrfs_do_readpage(struct page *page, struct
extent_map **em_cached,
kunmap_atomic(userpage);
}
}
+ begin_data_page_read(fs_info, page);
while (cur <= end) {
bool force_bio_submit = false;
u64 disk_bytenr;
@@ -3327,13 +3343,14 @@ int btrfs_do_readpage(struct page *page, struct
extent_map **em_cached,
&cached, GFP_NOFS);
unlock_extent_cached(tree, cur,
cur + iosize - 1, &cached);
+ end_page_read(page, true, cur, iosize);
break;
}
em = __get_extent_map(inode, page, pg_offset, cur,
end - cur + 1, em_cached);
if (IS_ERR_OR_NULL(em)) {
- SetPageError(page);
unlock_extent(tree, cur, end);
+ end_page_read(page, false, cur, end + 1 - cur);
break;
}
extent_offset = cur - em->start;
@@ -3416,6 +3433,7 @@ int btrfs_do_readpage(struct page *page, struct
extent_map **em_cached,
&cached, GFP_NOFS);
unlock_extent_cached(tree, cur,
cur + iosize - 1, &cached);
+ end_page_read(page, true, cur, iosize);
cur = cur + iosize;
pg_offset += iosize;
continue;
@@ -3425,6 +3443,7 @@ int btrfs_do_readpage(struct page *page, struct
extent_map **em_cached,
EXTENT_UPTODATE, 1, NULL)) {
check_page_uptodate(tree, page);
unlock_extent(tree, cur, cur + iosize - 1);
+ end_page_read(page, true, cur, iosize);
cur = cur + iosize;
pg_offset += iosize;
continue;
@@ -3433,8 +3452,8 @@ int btrfs_do_readpage(struct page *page, struct
extent_map **em_cached,
* to date. Error out
*/
if (block_start == EXTENT_MAP_INLINE) {
- SetPageError(page);
unlock_extent(tree, cur, cur + iosize - 1);
+ end_page_read(page, false, cur, iosize);
cur = cur + iosize;
pg_offset += iosize;
continue;
@@ -3451,19 +3470,14 @@ int btrfs_do_readpage(struct page *page, struct
extent_map **em_cached,
nr++;
*bio_flags = this_bio_flag;
} else {
- SetPageError(page);
unlock_extent(tree, cur, cur + iosize - 1);
+ end_page_read(page, false, cur, iosize);
goto out;
}
cur = cur + iosize;
pg_offset += iosize;
}
out:
- if (!nr) {
- if (!PageError(page))
- SetPageUptodate(page);
- unlock_page(page);
- }