[PATCH v6 10/15] f2fs: support partial uptodate large folio read

[Nanzhe Zhao <nzzhao.sigma@gmail.com>]

From: Nanzhe Zhao <zhaonanzhe@xiaomi.com>

Buffered write can have write bytes smaller than folio
size for cases when folio minimum order is not zero.
This can left partially uptodate folio in page cache.
So we skip uptodate subpage read in read_data_large_folio.
Also mark hole subpage uptodate in uptodate bitmap.

Signed-off-by: Nanzhe Zhao <zhaonanzhe@xiaomi.com>
---
 fs/f2fs/data.c | 102 +++++++++++++++++++++++++++++++++++++++++++++----
 1 file changed, 95 insertions(+), 7 deletions(-)

diff --git a/fs/f2fs/data.c b/fs/f2fs/data.c
index bc1bffbb15ca..e718ed01fe7c 100644
--- a/fs/f2fs/data.c
+++ b/fs/f2fs/data.c
@@ -148,6 +148,7 @@ static void f2fs_finish_read_bio(struct bio *bio, bool in_task)
 		struct folio *folio = fi.folio;
 		unsigned nr_pages = fi.length >> PAGE_SHIFT;
 		bool finished = true;
+		bool uptodate = bio->bi_status == BLK_STS_OK;
 
 		if (!folio_test_large(folio) &&
 		    f2fs_is_compressed_page(folio)) {
@@ -163,6 +164,9 @@ static void f2fs_finish_read_bio(struct bio *bio, bool in_task)
 				(struct f2fs_folio_state *)folio->private;
 
 			spin_lock_irqsave(&ffs->state_lock, flags);
+			if (uptodate)
+				uptodate = __ffs_mark_subrange_uptodate(folio, ffs,
+						fi.offset, fi.length);
 			ffs->read_pages_pending -= nr_pages;
 			finished = !ffs->read_pages_pending;
 			spin_unlock_irqrestore(&ffs->state_lock, flags);
@@ -172,7 +176,7 @@ static void f2fs_finish_read_bio(struct bio *bio, bool in_task)
 			dec_cache_count(F2FS_F_SB(folio), F2FS_RD_DATA);
 
 		if (finished)
-			folio_end_read(folio, bio->bi_status == BLK_STS_OK);
+			folio_end_read(folio, uptodate);
 	}
 
 	if (ctx)
@@ -3141,6 +3145,70 @@ static bool find_next_valid_block(const struct folio *folio,
 	return false;
 }
 
+static unsigned int ffs_next_uptodate_subpage(struct f2fs_folio_state *ffs,
+			unsigned int start, unsigned int end)
+{
+	return find_next_bit(ffs->state, end + 1, start);
+}
+
+static unsigned int ffs_next_nonuptodate_subpage(struct f2fs_folio_state *ffs,
+			unsigned int start, unsigned int end)
+{
+	return find_next_zero_bit(ffs->state, end + 1, start);
+}
+
+static void f2fs_skip_fully_uptodate_front(struct folio *folio,
+			pgoff_t *index, pgoff_t *offset, unsigned int *nrpages,
+			unsigned int *max_nr_pages)
+{
+	struct f2fs_folio_state *ffs;
+	unsigned int next, skipped;
+
+	if (!f2fs_folio_has_ffs(folio) || !*nrpages)
+		return;
+
+	ffs = (struct f2fs_folio_state *)folio->private;
+	next = ffs_next_nonuptodate_subpage(ffs, *offset,
+					    *offset + *nrpages - 1);
+	skipped = next - *offset;
+	if (!skipped)
+		return;
+
+	*index += skipped;
+	*offset += skipped;
+	*nrpages -= skipped;
+	*max_nr_pages -= skipped;
+}
+
+static void f2fs_truncate_read_extent(struct inode *inode, struct folio *folio,
+				      pgoff_t offset, block_t block_nr,
+				      unsigned int *len_blks)
+{
+	struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
+	struct f2fs_folio_state *ffs;
+	unsigned int next, end;
+
+	if (!f2fs_folio_has_ffs(folio) || *len_blks <= 1)
+		return;
+
+	if (f2fs_is_multi_device(sbi)) {
+		int bidx = f2fs_target_device_index(sbi, block_nr);
+
+		*len_blks = min_t(unsigned int, *len_blks,
+				  FDEV(bidx).end_blk + 1 - block_nr);
+	}
+	*len_blks = min_t(unsigned int, *len_blks,
+			  (unsigned int)fscrypt_limit_io_blocks(inode,
+							folio->index + offset,
+							*len_blks));
+
+	ffs = (struct f2fs_folio_state *)folio->private;
+	end = offset + *len_blks - 1;
+	next = ffs_next_uptodate_subpage(ffs, offset + 1, end);
+	if (next <= end)
+		*len_blks = next - offset;
+}
+
 static int f2fs_read_data_large_folio(struct inode *inode,
 		struct fsverity_info *vi,
 		struct readahead_control *rac, struct folio *folio)
@@ -3173,6 +3241,19 @@ static int f2fs_read_data_large_folio(struct inode *inode,
 	f2fs_update_read_folio_count(F2FS_I_SB(inode), folio);
 
 	folio_in_bio = false;
+	ffs = NULL;
+	if (folio_test_large(folio)) {
+		/*
+		 * Allocate the folio state before doing anything with the
+		 * folio, so that the block mapping helpers below can rely on
+		 * it, and fail early if memory is not available.
+		 */
+		ffs = f2fs_ffs_find_or_alloc(folio);
+		if (!ffs) {
+			ret = -ENOMEM;
+			goto err_out;
+		}
+	}
 	index = folio->index;
 	offset = 0;
 	nrpages = folio_nr_pages(folio);
@@ -3185,6 +3266,11 @@ static int f2fs_read_data_large_folio(struct inode *inode,
 
 		len_blks = 1;
 
+		f2fs_skip_fully_uptodate_front(folio, &index, &offset,
+					       &nrpages, &max_nr_pages);
+		if (!nrpages)
+			break;
+
 		/*
 		 * Map blocks using the previous result first.
 		 */
@@ -3217,6 +3303,8 @@ static int f2fs_read_data_large_folio(struct inode *inode,
 			len_blks = min_t(unsigned int, nrpages, max_nr_pages);
 			len_blks = min_t(unsigned int, len_blks,
 					(unsigned int)(map.m_lblk + map.m_len - index));
+			f2fs_truncate_read_extent(inode, folio, offset,
+						  block_nr, &len_blks);
 
 			for (i = 0; i < len_blks; i++) {
 				if (!f2fs_is_valid_blkaddr(F2FS_I_SB(inode),
@@ -3235,6 +3323,12 @@ static int f2fs_read_data_large_folio(struct inode *inode,
 				ret = -EIO;
 				goto err_out;
 			}
+			if (folio_test_large(folio)) {
+				spin_lock_irq(&ffs->state_lock);
+				__ffs_mark_subrange_uptodate(folio, ffs,
+						page_offset, PAGE_SIZE);
+				spin_unlock_irq(&ffs->state_lock);
+			}
 			continue;
 		}
 
@@ -3242,12 +3336,6 @@ static int f2fs_read_data_large_folio(struct inode *inode,
 		 * to prevent from premature folio_end_read() call on folio
 		 */
 		if (folio_test_large(folio)) {
-			ffs = f2fs_ffs_find_or_alloc(folio);
-			if (!ffs) {
-				ret = -ENOMEM;
-				goto err_out;
-			}
-
 			/* set the bitmap to wait */
 			f2fs_update_read_folio_pending(folio, len_blks);
 		}
-- 
2.43.0