Revert "btrfs: switch to iomap_dio_rw() for dio"

This reverts commit a43a67a2.

This patch reverts the main part of switching direct io implementation
to iomap infrastructure. There's a problem in invalidate page that
couldn't be solved as regression in this development cycle.

The problem occurs when buffered and direct io are mixed, and the ranges
overlap. Although this is not recommended, filesystems implement
measures or fallbacks to make it somehow work. In this case, fallback to
buffered IO would be an option for btrfs (this already happens when
direct io is done on compressed data), but the change would be needed in
the iomap code, bringing new semantics to other filesystems.

Another problem arises when again the buffered and direct ios are mixed,
invalidation fails, then -EIO is set on the mapping and fsync will fail,
though there's no real error.

There have been discussions how to fix that, but revert seems to be the
least intrusive option.

Link: https://lore.kernel.org/linux-btrfs/20200528192103.xm45qoxqmkw7i5yl@fiona/Signed-off-by: David Sterba <dsterba@suse.com>

fs/btrfs/Kconfig

@@ -14,7 +14,6 @@ config BTRFS_FS
 	select LZO_DECOMPRESS
 	select ZSTD_COMPRESS
 	select ZSTD_DECOMPRESS
-	select FS_IOMAP
 	select RAID6_PQ
 	select XOR_BLOCKS
 	select SRCU

fs/btrfs/ctree.h

@@ -2933,7 +2933,6 @@ int btrfs_writepage_cow_fixup(struct page *page, u64 start, u64 end);
 void btrfs_writepage_endio_finish_ordered(struct page *page, u64 start,
 					  u64 end, int uptodate);
 extern const struct dentry_operations btrfs_dentry_operations;
-ssize_t btrfs_direct_IO(struct kiocb *iocb, struct iov_iter *iter);
 
 /* ioctl.c */
 long btrfs_ioctl(struct file *file, unsigned int cmd, unsigned long arg);

fs/btrfs/file.c

@@ -1819,7 +1819,7 @@ static ssize_t __btrfs_direct_write(struct kiocb *iocb, struct iov_iter *from)
 	loff_t endbyte;
 	int err;
 
-	written = btrfs_direct_IO(iocb, from);
+	written = generic_file_direct_write(iocb, from);
 
 	if (written < 0 || !iov_iter_count(from))
 		return written;
@@ -3476,26 +3476,9 @@ static int btrfs_file_open(struct inode *inode, struct file *filp)
 	return generic_file_open(inode, filp);
 }
 
-static ssize_t btrfs_file_read_iter(struct kiocb *iocb, struct iov_iter *to)
-{
-	ssize_t ret = 0;
-
-	if (iocb->ki_flags & IOCB_DIRECT) {
-		struct inode *inode = file_inode(iocb->ki_filp);
-
-		inode_lock_shared(inode);
-		ret = btrfs_direct_IO(iocb, to);
-		inode_unlock_shared(inode);
-		if (ret < 0)
-			return ret;
-	}
-
-	return generic_file_buffered_read(iocb, to, ret);
-}
-
 const struct file_operations btrfs_file_operations = {
 	.llseek		= btrfs_file_llseek,
-	.read_iter      = btrfs_file_read_iter,
+	.read_iter      = generic_file_read_iter,
 	.splice_read	= generic_file_splice_read,
 	.write_iter	= btrfs_file_write_iter,
 	.mmap		= btrfs_file_mmap,

fs/btrfs/inode.c

@@ -5,6 +5,7 @@
 
 #include <linux/kernel.h>
 #include <linux/bio.h>
+#include <linux/buffer_head.h>
 #include <linux/file.h>
 #include <linux/fs.h>
 #include <linux/pagemap.h>
@@ -29,7 +30,6 @@
 #include <linux/swap.h>
 #include <linux/migrate.h>
 #include <linux/sched/mm.h>
-#include <linux/iomap.h>
 #include <asm/unaligned.h>
 #include "misc.h"
 #include "ctree.h"
@@ -58,9 +58,9 @@ struct btrfs_iget_args {
 
 struct btrfs_dio_data {
 	u64 reserve;
-	loff_t length;
-	ssize_t submitted;
-	struct extent_changeset *data_reserved;
+	u64 unsubmitted_oe_range_start;
+	u64 unsubmitted_oe_range_end;
+	int overwrite;
 };
 
 static const struct inode_operations btrfs_dir_inode_operations;
@@ -7045,7 +7045,7 @@ noinline int can_nocow_extent(struct inode *inode, u64 offset, u64 *len,
 }
 
 static int lock_extent_direct(struct inode *inode, u64 lockstart, u64 lockend,
-			      struct extent_state **cached_state, bool writing)
+			      struct extent_state **cached_state, int writing)
 {
 	struct btrfs_ordered_extent *ordered;
 	int ret = 0;
@@ -7183,7 +7183,30 @@ static struct extent_map *create_io_em(struct inode *inode, u64 start, u64 len,
 }
 
 
+static int btrfs_get_blocks_direct_read(struct extent_map *em,
+					struct buffer_head *bh_result,
+					struct inode *inode,
+					u64 start, u64 len)
+{
+	struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
+
+	if (em->block_start == EXTENT_MAP_HOLE ||
+			test_bit(EXTENT_FLAG_PREALLOC, &em->flags))
+		return -ENOENT;
+
+	len = min(len, em->len - (start - em->start));
+
+	bh_result->b_blocknr = (em->block_start + (start - em->start)) >>
+		inode->i_blkbits;
+	bh_result->b_size = len;
+	bh_result->b_bdev = fs_info->fs_devices->latest_bdev;
+	set_buffer_mapped(bh_result);
+
+	return 0;
+}
+
 static int btrfs_get_blocks_direct_write(struct extent_map **map,
+					 struct buffer_head *bh_result,
 					 struct inode *inode,
 					 struct btrfs_dio_data *dio_data,
 					 u64 start, u64 len)
@@ -7245,6 +7268,7 @@ static int btrfs_get_blocks_direct_write(struct extent_map **map,
 	}
 
 	/* this will cow the extent */
+	len = bh_result->b_size;
 	free_extent_map(em);
 	*map = em = btrfs_new_extent_direct(inode, start, len);
 	if (IS_ERR(em)) {
@@ -7255,73 +7279,64 @@ static int btrfs_get_blocks_direct_write(struct extent_map **map,
 	len = min(len, em->len - (start - em->start));
 
 skip_cow:
+	bh_result->b_blocknr = (em->block_start + (start - em->start)) >>
+		inode->i_blkbits;
+	bh_result->b_size = len;
+	bh_result->b_bdev = fs_info->fs_devices->latest_bdev;
+	set_buffer_mapped(bh_result);
+
+	if (!test_bit(EXTENT_FLAG_PREALLOC, &em->flags))
+		set_buffer_new(bh_result);
+
 	/*
 	 * Need to update the i_size under the extent lock so buffered
 	 * readers will get the updated i_size when we unlock.
 	 */
-	if (start + len > i_size_read(inode))
+	if (!dio_data->overwrite && start + len > i_size_read(inode))
 		i_size_write(inode, start + len);
 
+	WARN_ON(dio_data->reserve < len);
 	dio_data->reserve -= len;
+	dio_data->unsubmitted_oe_range_end = start + len;
+	current->journal_info = dio_data;
 out:
 	return ret;
 }
 
-static int btrfs_dio_iomap_begin(struct inode *inode, loff_t start,
-		loff_t length, unsigned flags, struct iomap *iomap,
-		struct iomap *srcmap)
+static int btrfs_get_blocks_direct(struct inode *inode, sector_t iblock,
+				   struct buffer_head *bh_result, int create)
 {
 	struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
 	struct extent_map *em;
 	struct extent_state *cached_state = NULL;
 	struct btrfs_dio_data *dio_data = NULL;
+	u64 start = iblock << inode->i_blkbits;
 	u64 lockstart, lockend;
-	const bool write = !!(flags & IOMAP_WRITE);
+	u64 len = bh_result->b_size;
 	int ret = 0;
-	u64 len = length;
-	bool unlock_extents = false;
 
-	if (!write)
+	if (!create)
 		len = min_t(u64, len, fs_info->sectorsize);
 
 	lockstart = start;
 	lockend = start + len - 1;
 
+	if (current->journal_info) {
 		/*
-	 * The generic stuff only does filemap_write_and_wait_range, which
-	 * isn't enough if we've written compressed pages to this area, so we
-	 * need to flush the dirty pages again to make absolutely sure that any
-	 * outstanding dirty pages are on disk.
+		 * Need to pull our outstanding extents and set journal_info to NULL so
+		 * that anything that needs to check if there's a transaction doesn't get
+		 * confused.
 		 */
-	if (test_bit(BTRFS_INODE_HAS_ASYNC_EXTENT,
-		     &BTRFS_I(inode)->runtime_flags))
-		ret = filemap_fdatawrite_range(inode->i_mapping, start,
-					       start + length - 1);
-
-	dio_data = kzalloc(sizeof(*dio_data), GFP_NOFS);
-	if (!dio_data)
-		return -ENOMEM;
-
-	dio_data->length = length;
-	if (write) {
-		dio_data->reserve = round_up(length, fs_info->sectorsize);
-		ret = btrfs_delalloc_reserve_space(inode,
-				&dio_data->data_reserved,
-				start, dio_data->reserve);
-		if (ret) {
-			extent_changeset_free(dio_data->data_reserved);
-			kfree(dio_data);
-			return ret;
-		}
+		dio_data = current->journal_info;
+		current->journal_info = NULL;
 	}
-	iomap->private = dio_data;
-
 
 	/*
 	 * If this errors out it's because we couldn't invalidate pagecache for
 	 * this range and we need to fallback to buffered.
 	 */
-	if (lock_extent_direct(inode, lockstart, lockend, &cached_state, write)) {
+	if (lock_extent_direct(inode, lockstart, lockend, &cached_state,
+			       create)) {
 		ret = -ENOTBLK;
 		goto err;
 	}
@@ -7353,47 +7368,35 @@ static int btrfs_dio_iomap_begin(struct inode *inode, loff_t start,
 		goto unlock_err;
 	}
 
-	len = min(len, em->len - (start - em->start));
-	if (write) {
-		ret = btrfs_get_blocks_direct_write(&em, inode, dio_data,
-						    start, len);
+	if (create) {
+		ret = btrfs_get_blocks_direct_write(&em, bh_result, inode,
+						    dio_data, start, len);
 		if (ret < 0)
 			goto unlock_err;
-		unlock_extents = true;
-		/* Recalc len in case the new em is smaller than requested */
-		len = min(len, em->len - (start - em->start));
+
+		unlock_extent_cached(&BTRFS_I(inode)->io_tree, lockstart,
+				     lockend, &cached_state);
 	} else {
+		ret = btrfs_get_blocks_direct_read(em, bh_result, inode,
+						   start, len);
+		/* Can be negative only if we read from a hole */
+		if (ret < 0) {
+			ret = 0;
+			free_extent_map(em);
+			goto unlock_err;
+		}
 		/*
 		 * We need to unlock only the end area that we aren't using.
 		 * The rest is going to be unlocked by the endio routine.
 		 */
-		lockstart = start + len;
-		if (lockstart < lockend)
-			unlock_extents = true;
-	}
-
-	if (unlock_extents)
+		lockstart = start + bh_result->b_size;
+		if (lockstart < lockend) {
 			unlock_extent_cached(&BTRFS_I(inode)->io_tree,
 					     lockstart, lockend, &cached_state);
-	else
-		free_extent_state(cached_state);
-
-	/*
-	 * Translate extent map information to iomap.
-	 * We trim the extents (and move the addr) even though iomap code does
-	 * that, since we have locked only the parts we are performing I/O in.
-	 */
-	if ((em->block_start == EXTENT_MAP_HOLE) ||
-	    (test_bit(EXTENT_FLAG_PREALLOC, &em->flags) && !write)) {
-		iomap->addr = IOMAP_NULL_ADDR;
-		iomap->type = IOMAP_HOLE;
 		} else {
-		iomap->addr = em->block_start + (start - em->start);
-		iomap->type = IOMAP_MAPPED;
+			free_extent_state(cached_state);
+		}
 	}
-	iomap->offset = start;
-	iomap->bdev = fs_info->fs_devices->latest_bdev;
-	iomap->length = len;
 
 	free_extent_map(em);
 
@@ -7403,53 +7406,8 @@ static int btrfs_dio_iomap_begin(struct inode *inode, loff_t start,
 	unlock_extent_cached(&BTRFS_I(inode)->io_tree, lockstart, lockend,
 			     &cached_state);
 err:
-	if (dio_data) {
-		btrfs_delalloc_release_space(inode, dio_data->data_reserved,
-				start, dio_data->reserve, true);
-		btrfs_delalloc_release_extents(BTRFS_I(inode), dio_data->reserve);
-		extent_changeset_free(dio_data->data_reserved);
-		kfree(dio_data);
-	}
-	return ret;
-}
-
-static int btrfs_dio_iomap_end(struct inode *inode, loff_t pos, loff_t length,
-		ssize_t written, unsigned flags, struct iomap *iomap)
-{
-	int ret = 0;
-	struct btrfs_dio_data *dio_data = iomap->private;
-	size_t submitted = dio_data->submitted;
-	const bool write = !!(flags & IOMAP_WRITE);
-
-	if (!write && (iomap->type == IOMAP_HOLE)) {
-		/* If reading from a hole, unlock and return */
-		unlock_extent(&BTRFS_I(inode)->io_tree, pos, pos + length - 1);
-		goto out;
-	}
-
-	if (submitted < length) {
-		pos += submitted;
-		length -= submitted;
-		if (write)
-			__endio_write_update_ordered(inode, pos, length, false);
-		else
-			unlock_extent(&BTRFS_I(inode)->io_tree, pos,
-				      pos + length - 1);
-		ret = -ENOTBLK;
-	}
-
-	if (write) {
-		if (dio_data->reserve)
-			btrfs_delalloc_release_space(inode,
-					dio_data->data_reserved, pos,
-					dio_data->reserve, true);
-		btrfs_delalloc_release_extents(BTRFS_I(inode), dio_data->length);
-		extent_changeset_free(dio_data->data_reserved);
-	}
-out:
-	kfree(dio_data);
-	iomap->private = NULL;
-
+	if (dio_data)
+		current->journal_info = dio_data;
 	return ret;
 }
 
@@ -7472,7 +7430,7 @@ static void btrfs_dio_private_put(struct btrfs_dio_private *dip)
 			      dip->logical_offset + dip->bytes - 1);
 	}
 
-	bio_endio(dip->dio_bio);
+	dio_end_io(dip->dio_bio);
 	kfree(dip);
 }
 
@@ -7708,11 +7666,24 @@ static struct btrfs_dio_private *btrfs_create_dio_private(struct bio *dio_bio,
 	dip->disk_bytenr = (u64)dio_bio->bi_iter.bi_sector << 9;
 	dip->dio_bio = dio_bio;
 	refcount_set(&dip->refs, 1);
+
+	if (write) {
+		struct btrfs_dio_data *dio_data = current->journal_info;
+
+		/*
+		 * Setting range start and end to the same value means that
+		 * no cleanup will happen in btrfs_direct_IO
+		 */
+		dio_data->unsubmitted_oe_range_end = dip->logical_offset +
+			dip->bytes;
+		dio_data->unsubmitted_oe_range_start =
+			dio_data->unsubmitted_oe_range_end;
+	}
 	return dip;
 }
 
-static blk_qc_t btrfs_submit_direct(struct inode *inode, struct iomap *iomap,
-		struct bio *dio_bio, loff_t file_offset)
+static void btrfs_submit_direct(struct bio *dio_bio, struct inode *inode,
+				loff_t file_offset)
 {
 	const bool write = (bio_op(dio_bio) == REQ_OP_WRITE);
 	const bool csum = !(BTRFS_I(inode)->flags & BTRFS_INODE_NODATASUM);
@@ -7729,7 +7700,6 @@ static blk_qc_t btrfs_submit_direct(struct inode *inode, struct iomap *iomap,
 	int ret;
 	blk_status_t status;
 	struct btrfs_io_geometry geom;
-	struct btrfs_dio_data *dio_data = iomap->private;
 
 	dip = btrfs_create_dio_private(dio_bio, inode, file_offset);
 	if (!dip) {
@@ -7738,8 +7708,8 @@ static blk_qc_t btrfs_submit_direct(struct inode *inode, struct iomap *iomap,
 				file_offset + dio_bio->bi_iter.bi_size - 1);
 		}
 		dio_bio->bi_status = BLK_STS_RESOURCE;
-		bio_endio(dio_bio);
-		return BLK_QC_T_NONE;
+		dio_end_io(dio_bio);
+		return;
 	}
 
 	if (!write && csum) {
@@ -7810,17 +7780,15 @@ static blk_qc_t btrfs_submit_direct(struct inode *inode, struct iomap *iomap,
 			goto out_err;
 		}
 
-		dio_data->submitted += clone_len;
 		clone_offset += clone_len;
 		start_sector += clone_len >> 9;
 		file_offset += clone_len;
 	} while (submit_len > 0);
-	return BLK_QC_T_NONE;
+	return;
 
 out_err:
 	dip->dio_bio->bi_status = status;
 	btrfs_dio_private_put(dip);
-	return BLK_QC_T_NONE;
 }
 
 static ssize_t check_direct_IO(struct btrfs_fs_info *fs_info,
@@ -7856,30 +7824,37 @@ static ssize_t check_direct_IO(struct btrfs_fs_info *fs_info,
 	return retval;
 }
 
-static const struct iomap_ops btrfs_dio_iomap_ops = {
-	.iomap_begin            = btrfs_dio_iomap_begin,
-	.iomap_end              = btrfs_dio_iomap_end,
-};
-
-static const struct iomap_dio_ops btrfs_dops = {
-	.submit_io		= btrfs_submit_direct,
-};
-
-ssize_t btrfs_direct_IO(struct kiocb *iocb, struct iov_iter *iter)
+static ssize_t btrfs_direct_IO(struct kiocb *iocb, struct iov_iter *iter)
 {
 	struct file *file = iocb->ki_filp;
 	struct inode *inode = file->f_mapping->host;
 	struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
+	struct btrfs_dio_data dio_data = { 0 };
 	struct extent_changeset *data_reserved = NULL;
 	loff_t offset = iocb->ki_pos;
 	size_t count = 0;
+	int flags = 0;
+	bool wakeup = true;
 	bool relock = false;
 	ssize_t ret;
 
 	if (check_direct_IO(fs_info, iter, offset))
 		return 0;
 
+	inode_dio_begin(inode);
+
+	/*
+	 * The generic stuff only does filemap_write_and_wait_range, which
+	 * isn't enough if we've written compressed pages to this area, so
+	 * we need to flush the dirty pages again to make absolutely sure
+	 * that any outstanding dirty pages are on disk.
+	 */
 	count = iov_iter_count(iter);
+	if (test_bit(BTRFS_INODE_HAS_ASYNC_EXTENT,
+		     &BTRFS_I(inode)->runtime_flags))
+		filemap_fdatawrite_range(inode->i_mapping, offset,
+					 offset + count - 1);
+
 	if (iov_iter_rw(iter) == WRITE) {
 		/*
 		 * If the write DIO is beyond the EOF, we need update
@@ -7887,24 +7862,71 @@ ssize_t btrfs_direct_IO(struct kiocb *iocb, struct iov_iter *iter)
 		 * not unlock the i_mutex at this case.
 		 */
 		if (offset + count <= inode->i_size) {
+			dio_data.overwrite = 1;
 			inode_unlock(inode);
 			relock = true;
 		} else if (iocb->ki_flags & IOCB_NOWAIT) {
 			ret = -EAGAIN;
 			goto out;
 		}
+		ret = btrfs_delalloc_reserve_space(inode, &data_reserved,
+						   offset, count);
+		if (ret)
+			goto out;
+
+		/*
+		 * We need to know how many extents we reserved so that we can
+		 * do the accounting properly if we go over the number we
+		 * originally calculated.  Abuse current->journal_info for this.
+		 */
+		dio_data.reserve = round_up(count,
+					    fs_info->sectorsize);
+		dio_data.unsubmitted_oe_range_start = (u64)offset;
+		dio_data.unsubmitted_oe_range_end = (u64)offset;
+		current->journal_info = &dio_data;
 		down_read(&BTRFS_I(inode)->dio_sem);
+	} else if (test_bit(BTRFS_INODE_READDIO_NEED_LOCK,
+				     &BTRFS_I(inode)->runtime_flags)) {
+		inode_dio_end(inode);
+		flags = DIO_LOCKING | DIO_SKIP_HOLES;
+		wakeup = false;
 	}
 
-	ret = iomap_dio_rw(iocb, iter, &btrfs_dio_iomap_ops, &btrfs_dops,
-			is_sync_kiocb(iocb));
-
+	ret = __blockdev_direct_IO(iocb, inode,
+				   fs_info->fs_devices->latest_bdev,
+				   iter, btrfs_get_blocks_direct, NULL,
+				   btrfs_submit_direct, flags);
 	if (iov_iter_rw(iter) == WRITE) {
 		up_read(&BTRFS_I(inode)->dio_sem);
+		current->journal_info = NULL;
+		if (ret < 0 && ret != -EIOCBQUEUED) {
+			if (dio_data.reserve)
+				btrfs_delalloc_release_space(inode, data_reserved,
+					offset, dio_data.reserve, true);
+			/*
+			 * On error we might have left some ordered extents
+			 * without submitting corresponding bios for them, so
+			 * cleanup them up to avoid other tasks getting them
+			 * and waiting for them to complete forever.
+			 */
+			if (dio_data.unsubmitted_oe_range_start <
+			    dio_data.unsubmitted_oe_range_end)
+				__endio_write_update_ordered(inode,
+					dio_data.unsubmitted_oe_range_start,
+					dio_data.unsubmitted_oe_range_end -
+					dio_data.unsubmitted_oe_range_start,
+					false);
+		} else if (ret >= 0 && (size_t)ret < count)
+			btrfs_delalloc_release_space(inode, data_reserved,
+					offset, count - (size_t)ret, true);
+		btrfs_delalloc_release_extents(BTRFS_I(inode), count);
 	}
 out:
+	if (wakeup)
+		inode_dio_end(inode);
 	if (relock)
 		inode_lock(inode);
+
 	extent_changeset_free(data_reserved);
 	return ret;
 }
@@ -10220,7 +10242,7 @@ static const struct address_space_operations btrfs_aops = {
 	.writepage	= btrfs_writepage,
 	.writepages	= btrfs_writepages,
 	.readpages	= btrfs_readpages,
-	.direct_IO	= noop_direct_IO,
+	.direct_IO	= btrfs_direct_IO,
 	.invalidatepage = btrfs_invalidatepage,
 	.releasepage	= btrfs_releasepage,
 #ifdef CONFIG_MIGRATION