iomap: move all ioend handling to ioend.c

Now that the writeback code has the proper abstractions, all the ioend
code can be self-contained in ioend.c.

Signed-off-by: Christoph Hellwig <[email protected]>
Reviewed-by: Brian Foster <[email protected]>
Reviewed-by: Joanne Koong <[email protected]>
Reviewed-by: "Darrick J. Wong" <[email protected]>

Author: Christoph Hellwig

fs/iomap/buffered-io.c

@@ -8,7 +8,6 @@
 #include <linux/writeback.h>
 #include <linux/swap.h>
 #include <linux/migrate.h>
-#include "internal.h"
 #include "trace.h"
 
 #include "../internal.h"
@@ -1551,221 +1550,6 @@ void iomap_finish_folio_write(struct inode *inode, struct folio *folio,
 }
 EXPORT_SYMBOL_GPL(iomap_finish_folio_write);
 
-/*
- * We're now finished for good with this ioend structure.  Update the page
- * state, release holds on bios, and finally free up memory.  Do not use the
- * ioend after this.
- */
-u32 iomap_finish_ioend_buffered(struct iomap_ioend *ioend)
-{
-	struct inode *inode = ioend->io_inode;
-	struct bio *bio = &ioend->io_bio;
-	struct folio_iter fi;
-	u32 folio_count = 0;
-
-	if (ioend->io_error) {
-		mapping_set_error(inode->i_mapping, ioend->io_error);
-		if (!bio_flagged(bio, BIO_QUIET)) {
-			pr_err_ratelimited(
-"%s: writeback error on inode %lu, offset %lld, sector %llu",
-				inode->i_sb->s_id, inode->i_ino,
-				ioend->io_offset, ioend->io_sector);
-		}
-	}
-
-	/* walk all folios in bio, ending page IO on them */
-	bio_for_each_folio_all(fi, bio) {
-		iomap_finish_folio_write(inode, fi.folio, fi.length);
-		folio_count++;
-	}
-
-	bio_put(bio);	/* frees the ioend */
-	return folio_count;
-}
-
-static void ioend_writeback_end_bio(struct bio *bio)
-{
-	struct iomap_ioend *ioend = iomap_ioend_from_bio(bio);
-
-	ioend->io_error = blk_status_to_errno(bio->bi_status);
-	iomap_finish_ioend_buffered(ioend);
-}
-
-/*
- * We cannot cancel the ioend directly in case of an error, so call the bio end
- * I/O handler with the error status here to run the normal I/O completion
- * handler.
- */
-int iomap_ioend_writeback_submit(struct iomap_writepage_ctx *wpc, int error)
-{
-	struct iomap_ioend *ioend = wpc->wb_ctx;
-
-	if (!ioend->io_bio.bi_end_io)
-		ioend->io_bio.bi_end_io = ioend_writeback_end_bio;
-
-	if (WARN_ON_ONCE(wpc->iomap.flags & IOMAP_F_ANON_WRITE))
-		error = -EIO;
-
-	if (error) {
-		ioend->io_bio.bi_status = errno_to_blk_status(error);
-		bio_endio(&ioend->io_bio);
-		return error;
-	}
-
-	submit_bio(&ioend->io_bio);
-	return 0;
-}
-EXPORT_SYMBOL_GPL(iomap_ioend_writeback_submit);
-
-static struct iomap_ioend *iomap_alloc_ioend(struct iomap_writepage_ctx *wpc,
-		loff_t pos, u16 ioend_flags)
-{
-	struct bio *bio;
-
-	bio = bio_alloc_bioset(wpc->iomap.bdev, BIO_MAX_VECS,
-			       REQ_OP_WRITE | wbc_to_write_flags(wpc->wbc),
-			       GFP_NOFS, &iomap_ioend_bioset);
-	bio->bi_iter.bi_sector = iomap_sector(&wpc->iomap, pos);
-	bio->bi_write_hint = wpc->inode->i_write_hint;
-	wbc_init_bio(wpc->wbc, bio);
-	wpc->nr_folios = 0;
-	return iomap_init_ioend(wpc->inode, bio, pos, ioend_flags);
-}
-
-static bool iomap_can_add_to_ioend(struct iomap_writepage_ctx *wpc, loff_t pos,
-		u16 ioend_flags)
-{
-	struct iomap_ioend *ioend = wpc->wb_ctx;
-
-	if (ioend_flags & IOMAP_IOEND_BOUNDARY)
-		return false;
-	if ((ioend_flags & IOMAP_IOEND_NOMERGE_FLAGS) !=
-	    (ioend->io_flags & IOMAP_IOEND_NOMERGE_FLAGS))
-		return false;
-	if (pos != ioend->io_offset + ioend->io_size)
-		return false;
-	if (!(wpc->iomap.flags & IOMAP_F_ANON_WRITE) &&
-	    iomap_sector(&wpc->iomap, pos) != bio_end_sector(&ioend->io_bio))
-		return false;
-	/*
-	 * Limit ioend bio chain lengths to minimise IO completion latency. This
-	 * also prevents long tight loops ending page writeback on all the
-	 * folios in the ioend.
-	 */
-	if (wpc->nr_folios >= IOEND_BATCH_SIZE)
-		return false;
-	return true;
-}
-
-/*
- * Test to see if we have an existing ioend structure that we could append to
- * first; otherwise finish off the current ioend and start another.
- *
- * If a new ioend is created and cached, the old ioend is submitted to the block
- * layer instantly.  Batching optimisations are provided by higher level block
- * plugging.
- *
- * At the end of a writeback pass, there will be a cached ioend remaining on the
- * writepage context that the caller will need to submit.
- */
-ssize_t iomap_add_to_ioend(struct iomap_writepage_ctx *wpc, struct folio *folio,
-		loff_t pos, loff_t end_pos, unsigned int dirty_len)
-{
-	struct iomap_ioend *ioend = wpc->wb_ctx;
-	size_t poff = offset_in_folio(folio, pos);
-	unsigned int ioend_flags = 0;
-	unsigned int map_len = min_t(u64, dirty_len,
-		wpc->iomap.offset + wpc->iomap.length - pos);
-	int error;
-
-	trace_iomap_add_to_ioend(wpc->inode, pos, dirty_len, &wpc->iomap);
-
-	WARN_ON_ONCE(!folio->private && map_len < dirty_len);
-
-	switch (wpc->iomap.type) {
-	case IOMAP_INLINE:
-		WARN_ON_ONCE(1);
-		return -EIO;
-	case IOMAP_HOLE:
-		return map_len;
-	default:
-		break;
-	}
-
-	if (wpc->iomap.type == IOMAP_UNWRITTEN)
-		ioend_flags |= IOMAP_IOEND_UNWRITTEN;
-	if (wpc->iomap.flags & IOMAP_F_SHARED)
-		ioend_flags |= IOMAP_IOEND_SHARED;
-	if (folio_test_dropbehind(folio))
-		ioend_flags |= IOMAP_IOEND_DONTCACHE;
-	if (pos == wpc->iomap.offset && (wpc->iomap.flags & IOMAP_F_BOUNDARY))
-		ioend_flags |= IOMAP_IOEND_BOUNDARY;
-
-	if (!ioend || !iomap_can_add_to_ioend(wpc, pos, ioend_flags)) {
-new_ioend:
-		if (ioend) {
-			error = wpc->ops->writeback_submit(wpc, 0);
-			if (error)
-				return error;
-		}
-		wpc->wb_ctx = ioend = iomap_alloc_ioend(wpc, pos, ioend_flags);
-	}
-
-	if (!bio_add_folio(&ioend->io_bio, folio, map_len, poff))
-		goto new_ioend;
-
-	iomap_start_folio_write(wpc->inode, folio, map_len);
-
-	/*
-	 * Clamp io_offset and io_size to the incore EOF so that ondisk
-	 * file size updates in the ioend completion are byte-accurate.
-	 * This avoids recovering files with zeroed tail regions when
-	 * writeback races with appending writes:
-	 *
-	 *    Thread 1:                  Thread 2:
-	 *    ------------               -----------
-	 *    write [A, A+B]
-	 *    update inode size to A+B
-	 *    submit I/O [A, A+BS]
-	 *                               write [A+B, A+B+C]
-	 *                               update inode size to A+B+C
-	 *    <I/O completes, updates disk size to min(A+B+C, A+BS)>
-	 *    <power failure>
-	 *
-	 *  After reboot:
-	 *    1) with A+B+C < A+BS, the file has zero padding in range
-	 *       [A+B, A+B+C]
-	 *
-	 *    |<     Block Size (BS)   >|
-	 *    |DDDDDDDDDDDD0000000000000|
-	 *    ^           ^        ^
-	 *    A          A+B     A+B+C
-	 *                       (EOF)
-	 *
-	 *    2) with A+B+C > A+BS, the file has zero padding in range
-	 *       [A+B, A+BS]
-	 *
-	 *    |<     Block Size (BS)   >|<     Block Size (BS)    >|
-	 *    |DDDDDDDDDDDD0000000000000|00000000000000000000000000|
-	 *    ^           ^             ^           ^
-	 *    A          A+B           A+BS       A+B+C
-	 *                             (EOF)
-	 *
-	 *    D = Valid Data
-	 *    0 = Zero Padding
-	 *
-	 * Note that this defeats the ability to chain the ioends of
-	 * appending writes.
-	 */
-	ioend->io_size += map_len;
-	if (ioend->io_offset + ioend->io_size > end_pos)
-		ioend->io_size = end_pos - ioend->io_offset;
-
-	wbc_account_cgroup_owner(wpc->wbc, folio, map_len);
-	return map_len;
-}
-EXPORT_SYMBOL_GPL(iomap_add_to_ioend);
-
 static int iomap_writeback_range(struct iomap_writepage_ctx *wpc,
 		struct folio *folio, u64 pos, u32 rlen, u64 end_pos,
 		bool *wb_pending)

fs/iomap/internal.h

@@ -4,7 +4,6 @@
 
 #define IOEND_BATCH_SIZE	4096
 
-u32 iomap_finish_ioend_buffered(struct iomap_ioend *ioend);
 u32 iomap_finish_ioend_direct(struct iomap_ioend *ioend);
 
 #endif /* _IOMAP_INTERNAL_H */