[PATCH 0/8 v4] btrfs direct-io using iomap

[PATCH 0/8 v4] btrfs direct-io using iomap

[Goldwyn Rodrigues]

This is an effort to use iomap for direct I/O in btrfs. This would
change the call from __blockdev_direct_io() to iomap_dio_rw().

The main objective is to lose the buffer head and use bio defined by
iomap code, and hopefully to use more of generic-FS codebase.

These patches are based and tested on v5.5-rc1. I have tested it against
xfstests/btrfs.

The tree is available at
https://github.com/goldwynr/linux/tree/btrfs-iomap-dio


Changes since v1
- Incorporated back the efficiency change for inode locking
- Review comments about coding style and git comments
- Merge related patches into one
- Direct read to go through btrfs_direct_IO()
- Removal of no longer used function dio_end_io()

Changes since v2
- aligning iomap offset/length to the position/length of I/O
- Removed btrfs_dio_data
- Removed BTRFS_INODE_READDIO_NEED_LOCK
- Re-incorporating write efficiency changes caused lockdep_assert() in
  iomap to be triggered, remove that code.

Changes since v3
- Fixed freeze on generic/095. Use iomap_end() to account for
  failed/incomplete dio instead of btrfs_dio_data

--
Goldwyn

 fs/btrfs/btrfs_inode.h |   18 ---
 fs/btrfs/ctree.h       |    1
 fs/btrfs/extent_io.c   |   37 ++----
 fs/btrfs/extent_io.h   |    2
 fs/btrfs/file.c        |   21 +++
 fs/btrfs/inode.c       |  282 ++++++++++++++++++-------------------------------
 fs/direct-io.c         |   19 ---
 fs/iomap/direct-io.c   |   16 +-
 include/linux/fs.h     |    4
 include/linux/iomap.h  |    2
 mm/filemap.c           |   13 +-
 11 files changed, 162 insertions(+), 253 deletions(-)

[PATCH 1/8] fs: Export generic_file_buffered_read()

[Goldwyn Rodrigues]

From: Goldwyn Rodrigues <rgoldwyn@suse.com>

Export generic_file_buffered_read() to be used to
supplement incomplete direct reads.

While we are at it, correct the comments and variable names.

Reviewed-by: Johannes Thumshirn <jthumshirn@suse.de>
Signed-off-by: Goldwyn Rodrigues <rgoldwyn@suse.com>
---
 include/linux/fs.h |  2 ++
 mm/filemap.c       | 13 +++++++------
 2 files changed, 9 insertions(+), 6 deletions(-)

diff --git a/include/linux/fs.h b/include/linux/fs.h
index 98e0349adb52..3883adaa0e01 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -3098,6 +3098,8 @@ extern int generic_file_rw_checks(struct file *file_in, struct file *file_out);
 extern int generic_copy_file_checks(struct file *file_in, loff_t pos_in,
 				    struct file *file_out, loff_t pos_out,
 				    size_t *count, unsigned int flags);
+extern ssize_t generic_file_buffered_read(struct kiocb *iocb,
+		struct iov_iter *to, ssize_t already_read);
 extern ssize_t generic_file_read_iter(struct kiocb *, struct iov_iter *);
 extern ssize_t __generic_file_write_iter(struct kiocb *, struct iov_iter *);
 extern ssize_t generic_file_write_iter(struct kiocb *, struct iov_iter *);
diff --git a/mm/filemap.c b/mm/filemap.c
index bf6aa30be58d..dc2c7e3472a0 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -1994,7 +1994,7 @@ static void shrink_readahead_size_eio(struct file *filp,
  * generic_file_buffered_read - generic file read routine
  * @iocb:	the iocb to read
  * @iter:	data destination
- * @written:	already copied
+ * @copied:	already copied
  *
  * This is a generic file read routine, and uses the
  * mapping->a_ops->readpage() function for the actual low-level stuff.
@@ -2003,11 +2003,11 @@ static void shrink_readahead_size_eio(struct file *filp,
  * of the logic when it comes to error handling etc.
  *
  * Return:
- * * total number of bytes copied, including those the were already @written
+ * * total number of bytes copied, including those that were @copied
  * * negative error code if nothing was copied
  */
-static ssize_t generic_file_buffered_read(struct kiocb *iocb,
-		struct iov_iter *iter, ssize_t written)
+ssize_t generic_file_buffered_read(struct kiocb *iocb,
+		struct iov_iter *iter, ssize_t copied)
 {
 	struct file *filp = iocb->ki_filp;
 	struct address_space *mapping = filp->f_mapping;
@@ -2148,7 +2148,7 @@ static ssize_t generic_file_buffered_read(struct kiocb *iocb,
 		prev_offset = offset;
 
 		put_page(page);
-		written += ret;
+		copied += ret;
 		if (!iov_iter_count(iter))
 			goto out;
 		if (ret < nr) {
@@ -2256,8 +2256,9 @@ static ssize_t generic_file_buffered_read(struct kiocb *iocb,
 
 	*ppos = ((loff_t)index << PAGE_SHIFT) + offset;
 	file_accessed(filp);
-	return written ? written : error;
+	return copied ? copied : error;
 }
+EXPORT_SYMBOL_GPL(generic_file_buffered_read);
 
 /**
  * generic_file_read_iter - generic filesystem read routine
-- 
2.16.4

[PATCH 2/8] iomap: add a filesystem hook for direct I/O bio submission

[Goldwyn Rodrigues]

From: Goldwyn Rodrigues <rgoldwyn@suse.com>

This helps filesystems to perform tasks on the bio while submitting for
I/O. This could be post-write operations such as data CRC or data
replication for fs-handled RAID.

Reviewed-by: Johannes Thumshirn <jthumshirn@suse.de>
Reviewed-by: Nikolay Borisov <nborisov@suse.com>
Signed-off-by: Goldwyn Rodrigues <rgoldwyn@suse.com>
---
 fs/iomap/direct-io.c  | 14 +++++++++-----
 include/linux/iomap.h |  2 ++
 2 files changed, 11 insertions(+), 5 deletions(-)

diff --git a/fs/iomap/direct-io.c b/fs/iomap/direct-io.c
index 23837926c0c5..1a3bf3bd86fb 100644
--- a/fs/iomap/direct-io.c
+++ b/fs/iomap/direct-io.c
@@ -59,7 +59,7 @@ int iomap_dio_iopoll(struct kiocb *kiocb, bool spin)
 EXPORT_SYMBOL_GPL(iomap_dio_iopoll);
 
 static void iomap_dio_submit_bio(struct iomap_dio *dio, struct iomap *iomap,
-		struct bio *bio)
+		struct bio *bio, loff_t pos)
 {
 	atomic_inc(&dio->ref);
 
@@ -67,7 +67,11 @@ static void iomap_dio_submit_bio(struct iomap_dio *dio, struct iomap *iomap,
 		bio_set_polled(bio, dio->iocb);
 
 	dio->submit.last_queue = bdev_get_queue(iomap->bdev);
-	dio->submit.cookie = submit_bio(bio);
+	if (dio->dops && dio->dops->submit_io)
+		dio->submit.cookie = dio->dops->submit_io(bio,
+				dio->iocb->ki_filp, pos);
+	else
+		dio->submit.cookie = submit_bio(bio);
 }
 
 static ssize_t iomap_dio_complete(struct iomap_dio *dio)
@@ -191,7 +195,7 @@ iomap_dio_zero(struct iomap_dio *dio, struct iomap *iomap, loff_t pos,
 	get_page(page);
 	__bio_add_page(bio, page, len, 0);
 	bio_set_op_attrs(bio, REQ_OP_WRITE, flags);
-	iomap_dio_submit_bio(dio, iomap, bio);
+	iomap_dio_submit_bio(dio, iomap, bio, pos);
 }
 
 static loff_t
@@ -299,11 +303,11 @@ iomap_dio_bio_actor(struct inode *inode, loff_t pos, loff_t length,
 		}
 
 		dio->size += n;
-		pos += n;
 		copied += n;
 
 		nr_pages = iov_iter_npages(dio->submit.iter, BIO_MAX_PAGES);
-		iomap_dio_submit_bio(dio, iomap, bio);
+		iomap_dio_submit_bio(dio, iomap, bio, pos);
+		pos += n;
 	} while (nr_pages);
 
 	/*
diff --git a/include/linux/iomap.h b/include/linux/iomap.h
index 8b09463dae0d..2b093a23ef1c 100644
--- a/include/linux/iomap.h
+++ b/include/linux/iomap.h
@@ -252,6 +252,8 @@ int iomap_writepages(struct address_space *mapping,
 struct iomap_dio_ops {
 	int (*end_io)(struct kiocb *iocb, ssize_t size, int error,
 		      unsigned flags);
+	blk_qc_t (*submit_io)(struct bio *bio, struct file *file,
+			  loff_t file_offset);
 };
 
 ssize_t iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter,
-- 
2.16.4

[PATCH 3/8] iomap: Remove lockdep_assert_held()

[Goldwyn Rodrigues]

From: Goldwyn Rodrigues <rgoldwyn@suse.com>

Filesystems such as btrfs can perform direct I/O without holding the
inode->i_rwsem in some of the cases like writing within i_size.
So, remove the check for lockdep_assert_held().

Signed-off-by: Goldwyn Rodrigues <rgoldwyn@suse.com>
---
 fs/iomap/direct-io.c | 2 --
 1 file changed, 2 deletions(-)

diff --git a/fs/iomap/direct-io.c b/fs/iomap/direct-io.c
index 1a3bf3bd86fb..41c1e7c20a1f 100644
--- a/fs/iomap/direct-io.c
+++ b/fs/iomap/direct-io.c
@@ -415,8 +415,6 @@ iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter,
 	struct blk_plug plug;
 	struct iomap_dio *dio;
 
-	lockdep_assert_held(&inode->i_rwsem);
-
 	if (!count)
 		return 0;
 
-- 
2.16.4

Re: [PATCH 3/8] iomap: Remove lockdep_assert_held()

[Dave Chinner]

On Tue, Dec 10, 2019 at 05:01:50PM -0600, Goldwyn Rodrigues wrote:
> From: Goldwyn Rodrigues <rgoldwyn@suse.com>
> 
> Filesystems such as btrfs can perform direct I/O without holding the
> inode->i_rwsem in some of the cases like writing within i_size.
> So, remove the check for lockdep_assert_held().
> 
> Signed-off-by: Goldwyn Rodrigues <rgoldwyn@suse.com>
> ---
>  fs/iomap/direct-io.c | 2 --
>  1 file changed, 2 deletions(-)
> 
> diff --git a/fs/iomap/direct-io.c b/fs/iomap/direct-io.c
> index 1a3bf3bd86fb..41c1e7c20a1f 100644
> --- a/fs/iomap/direct-io.c
> +++ b/fs/iomap/direct-io.c
> @@ -415,8 +415,6 @@ iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter,
>  	struct blk_plug plug;
>  	struct iomap_dio *dio;
>  
> -	lockdep_assert_held(&inode->i_rwsem);
> -
>  	if (!count)
>  		return 0;

Please move this up into the existing callers so that we don't lose
this debug check from those paths.

Cheers,

Dave.
-- 
Dave Chinner
david@fromorbit.com

[PATCH 4/8] btrfs: Switch to iomap_dio_rw() for dio

[Goldwyn Rodrigues]

From: Goldwyn Rodrigues <rgoldwyn@suse.com>

Switch from __blockdev_direct_IO() to iomap_dio_rw().
Rename btrfs_get_blocks_direct() to btrfs_dio_iomap_begin() and use it
as iomap_begin() for iomap direct I/O functions. This function
allocates and locks all the blocks required for the I/O.
btrfs_submit_direct() is used as the submit_io() hook for direct I/O
ops.

Since we need direct I/O reads to go through iomap_dio_rw(), we change
file_operations.read_iter() to a btrfs_file_read_iter() which calls
btrfs_direct_IO() for direct reads and falls back to
generic_file_buffered_read() for incomplete reads and buffered reads.

We don't need address_space.direct_IO() anymore so set it to noop.
Similarly, we don't need flags used in __blockdev_direct_IO(). iomap is
capable of direct I/O reads from a hole, so we don't need to return
-ENOENT.

BTRFS direct I/O is now done under i_rwsem, shared in case of
reads and exclusive in case of writes. This guards against simultaneous
truncates.

Signed-off-by: Goldwyn Rodrigues <rgoldwyn@suse.com>
---
 fs/btrfs/ctree.h |   1 +
 fs/btrfs/file.c  |  21 ++++++-
 fs/btrfs/inode.c | 184 ++++++++++++++++++++++++++-----------------------------
 3 files changed, 107 insertions(+), 99 deletions(-)

diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h
index b2e8fd8a8e59..113dcd1a11cd 100644
--- a/fs/btrfs/ctree.h
+++ b/fs/btrfs/ctree.h
@@ -2904,6 +2904,7 @@ 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);
diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c
index 0cb43b682789..7010dd7beccc 100644
--- a/fs/btrfs/file.c
+++ b/fs/btrfs/file.c
@@ -1832,7 +1832,7 @@ static ssize_t __btrfs_direct_write(struct kiocb *iocb, struct iov_iter *from)
 	loff_t endbyte;
 	int err;
 
-	written = generic_file_direct_write(iocb, from);
+	written = btrfs_direct_IO(iocb, from);
 
 	if (written < 0 || !iov_iter_count(from))
 		return written;
@@ -3444,9 +3444,26 @@ 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      = generic_file_read_iter,
+	.read_iter      = btrfs_file_read_iter,
 	.splice_read	= generic_file_splice_read,
 	.write_iter	= btrfs_file_write_iter,
 	.mmap		= btrfs_file_mmap,
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index 56032c518b26..86730f2f2bf6 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -29,6 +29,7 @@
 #include <linux/iversion.h>
 #include <linux/swap.h>
 #include <linux/sched/mm.h>
+#include <linux/iomap.h>
 #include <asm/unaligned.h>
 #include "misc.h"
 #include "ctree.h"
@@ -7510,7 +7511,7 @@ 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, int writing)
+			      struct extent_state **cached_state, bool writing)
 {
 	struct btrfs_ordered_extent *ordered;
 	int ret = 0;
@@ -7648,30 +7649,7 @@ 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)
@@ -7733,7 +7711,6 @@ 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)) {
@@ -7744,15 +7721,6 @@ 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.
@@ -7768,24 +7736,37 @@ static int btrfs_get_blocks_direct_write(struct extent_map **map,
 	return ret;
 }
 
-static int btrfs_get_blocks_direct(struct inode *inode, sector_t iblock,
-				   struct buffer_head *bh_result, int create)
+static int btrfs_dio_iomap_begin(struct inode *inode, loff_t start,
+		loff_t length, unsigned flags, struct iomap *iomap,
+		struct iomap *srcmap)
 {
 	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;
-	u64 len = bh_result->b_size;
+	bool write = !!(flags & IOMAP_WRITE);
 	int ret = 0;
+	u64 len = length;
+	bool unlock_extents = false;
 
-	if (!create)
+	if (!write)
 		len = min_t(u64, len, fs_info->sectorsize);
 
 	lockstart = start;
 	lockend = start + len - 1;
 
+	/*
+	 * 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.
+	 */
+	if (test_bit(BTRFS_INODE_HAS_ASYNC_EXTENT,
+		     &BTRFS_I(inode)->runtime_flags))
+		ret = filemap_fdatawrite_range(inode->i_mapping, start,
+					 start + length - 1);
+
 	if (current->journal_info) {
 		/*
 		 * Need to pull our outstanding extents and set journal_info to NULL so
@@ -7801,7 +7782,7 @@ static int btrfs_get_blocks_direct(struct inode *inode, sector_t iblock,
 	 * this range and we need to fallback to buffered.
 	 */
 	if (lock_extent_direct(inode, lockstart, lockend, &cached_state,
-			       create)) {
+			       write)) {
 		ret = -ENOTBLK;
 		goto err;
 	}
@@ -7833,36 +7814,53 @@ static int btrfs_get_blocks_direct(struct inode *inode, sector_t iblock,
 		goto unlock_err;
 	}
 
-	if (create) {
-		ret = btrfs_get_blocks_direct_write(&em, bh_result, inode,
+	len = min(len, em->len - (start - em->start));
+	if (write) {
+		ret = btrfs_get_blocks_direct_write(&em, inode,
 						    dio_data, start, len);
 		if (ret < 0)
 			goto unlock_err;
-
-		unlock_extent_cached(&BTRFS_I(inode)->io_tree, lockstart,
-				     lockend, &cached_state);
+		unlock_extents = true;
+		/* Recalc len in case the new em is smaller than requested */
+		len = min(len, em->len - (start - em->start));
+	} else if (em->block_start == EXTENT_MAP_HOLE ||
+			test_bit(EXTENT_FLAG_PREALLOC, &em->flags)) {
+		/* Unlock in case of direct reading from a hole */
+		unlock_extents = true;
 	} 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 + 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);
-		}
+		lockstart = start + len;
+		if (lockstart < lockend)
+			unlock_extents = true;
 	}
 
+	if (unlock_extents)
+		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;
+	}
+	iomap->offset = start;
+	iomap->bdev = fs_info->fs_devices->latest_bdev;
+	iomap->length = len;
+
 	free_extent_map(em);
 
 	return 0;
@@ -8230,9 +8228,8 @@ static void btrfs_endio_direct_read(struct bio *bio)
 	kfree(dip);
 
 	dio_bio->bi_status = err;
-	dio_end_io(dio_bio);
+	bio_endio(dio_bio);
 	btrfs_io_bio_free_csum(io_bio);
-	bio_put(bio);
 }
 
 static void __endio_write_update_ordered(struct inode *inode,
@@ -8289,8 +8286,7 @@ static void btrfs_endio_direct_write(struct bio *bio)
 	kfree(dip);
 
 	dio_bio->bi_status = bio->bi_status;
-	dio_end_io(dio_bio);
-	bio_put(bio);
+	bio_endio(dio_bio);
 }
 
 static blk_status_t btrfs_submit_bio_start_direct_io(void *private_data,
@@ -8522,9 +8518,10 @@ static int btrfs_submit_direct_hook(struct btrfs_dio_private *dip)
 	return 0;
 }
 
-static void btrfs_submit_direct(struct bio *dio_bio, struct inode *inode,
+static blk_qc_t btrfs_submit_direct(struct bio *dio_bio, struct file *file,
 				loff_t file_offset)
 {
+	struct inode *inode = file_inode(file);
 	struct btrfs_dio_private *dip = NULL;
 	struct bio *bio = NULL;
 	struct btrfs_io_bio *io_bio;
@@ -8575,7 +8572,7 @@ static void btrfs_submit_direct(struct bio *dio_bio, struct inode *inode,
 
 	ret = btrfs_submit_direct_hook(dip);
 	if (!ret)
-		return;
+		return BLK_QC_T_NONE;
 
 	btrfs_io_bio_free_csum(io_bio);
 
@@ -8594,7 +8591,7 @@ static void btrfs_submit_direct(struct bio *dio_bio, struct inode *inode,
 		/*
 		 * The end io callbacks free our dip, do the final put on bio
 		 * and all the cleanup and final put for dio_bio (through
-		 * dio_end_io()).
+		 * end_io()).
 		 */
 		dip = NULL;
 		bio = NULL;
@@ -8613,11 +8610,12 @@ static void btrfs_submit_direct(struct bio *dio_bio, struct inode *inode,
 		 * Releases and cleans up our dio_bio, no need to bio_put()
 		 * nor bio_endio()/bio_io_error() against dio_bio.
 		 */
-		dio_end_io(dio_bio);
+		bio_endio(dio_bio);
 	}
 	if (bio)
 		bio_put(bio);
 	kfree(dip);
+	return BLK_QC_T_NONE;
 }
 
 static ssize_t check_direct_IO(struct btrfs_fs_info *fs_info,
@@ -8653,7 +8651,23 @@ static ssize_t check_direct_IO(struct btrfs_fs_info *fs_info,
 	return retval;
 }
 
-static ssize_t btrfs_direct_IO(struct kiocb *iocb, struct iov_iter *iter)
+static const struct iomap_ops btrfs_dio_iomap_ops = {
+	.iomap_begin            = btrfs_dio_iomap_begin,
+};
+
+static const struct iomap_dio_ops btrfs_dops = {
+	.submit_io		= btrfs_submit_direct,
+};
+
+
+/*
+ * btrfs_direct_IO - perform direct I/O
+ * inode->i_rwsem must be locked before calling this function, shared or exclusive.
+ * @iocb - kernel iocb
+ * @iter - iter to/from data is copied
+ */
+
+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;
@@ -8662,28 +8676,13 @@ static ssize_t btrfs_direct_IO(struct kiocb *iocb, struct iov_iter *iter)
 	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
@@ -8714,17 +8713,11 @@ static ssize_t btrfs_direct_IO(struct kiocb *iocb, struct iov_iter *iter)
 		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 = __blockdev_direct_IO(iocb, inode,
-				   fs_info->fs_devices->latest_bdev,
-				   iter, btrfs_get_blocks_direct, NULL,
-				   btrfs_submit_direct, flags);
+	ret = iomap_dio_rw(iocb, iter, &btrfs_dio_iomap_ops, &btrfs_dops,
+			is_sync_kiocb(iocb));
+
 	if (iov_iter_rw(iter) == WRITE) {
 		up_read(&BTRFS_I(inode)->dio_sem);
 		current->journal_info = NULL;
@@ -8751,11 +8744,8 @@ static ssize_t btrfs_direct_IO(struct kiocb *iocb, struct iov_iter *iter)
 		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;
 }
@@ -11045,7 +11035,7 @@ static const struct address_space_operations btrfs_aops = {
 	.writepage	= btrfs_writepage,
 	.writepages	= btrfs_writepages,
 	.readpages	= btrfs_readpages,
-	.direct_IO	= btrfs_direct_IO,
+	.direct_IO	= noop_direct_IO,
 	.invalidatepage = btrfs_invalidatepage,
 	.releasepage	= btrfs_releasepage,
 	.set_page_dirty	= btrfs_set_page_dirty,
-- 
2.16.4

Re: [PATCH 4/8] btrfs: Switch to iomap_dio_rw() for dio

[Filipe Manana]

On Tue, Dec 10, 2019 at 11:02 PM Goldwyn Rodrigues <rgoldwyn@suse.de> wrote:
>
> From: Goldwyn Rodrigues <rgoldwyn@suse.com>
>
> Switch from __blockdev_direct_IO() to iomap_dio_rw().
> Rename btrfs_get_blocks_direct() to btrfs_dio_iomap_begin() and use it
> as iomap_begin() for iomap direct I/O functions. This function
> allocates and locks all the blocks required for the I/O.
> btrfs_submit_direct() is used as the submit_io() hook for direct I/O
> ops.
>
> Since we need direct I/O reads to go through iomap_dio_rw(), we change
> file_operations.read_iter() to a btrfs_file_read_iter() which calls
> btrfs_direct_IO() for direct reads and falls back to
> generic_file_buffered_read() for incomplete reads and buffered reads.
>
> We don't need address_space.direct_IO() anymore so set it to noop.
> Similarly, we don't need flags used in __blockdev_direct_IO(). iomap is
> capable of direct I/O reads from a hole, so we don't need to return
> -ENOENT.
>
> BTRFS direct I/O is now done under i_rwsem, shared in case of
> reads and exclusive in case of writes. This guards against simultaneous
> truncates.
>
> Signed-off-by: Goldwyn Rodrigues <rgoldwyn@suse.com>
> ---
>  fs/btrfs/ctree.h |   1 +
>  fs/btrfs/file.c  |  21 ++++++-
>  fs/btrfs/inode.c | 184 ++++++++++++++++++++++++++-----------------------------
>  3 files changed, 107 insertions(+), 99 deletions(-)
>
> diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h
> index b2e8fd8a8e59..113dcd1a11cd 100644
> --- a/fs/btrfs/ctree.h
> +++ b/fs/btrfs/ctree.h
> @@ -2904,6 +2904,7 @@ 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);
> diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c
> index 0cb43b682789..7010dd7beccc 100644
> --- a/fs/btrfs/file.c
> +++ b/fs/btrfs/file.c
> @@ -1832,7 +1832,7 @@ static ssize_t __btrfs_direct_write(struct kiocb *iocb, struct iov_iter *from)
>         loff_t endbyte;
>         int err;
>
> -       written = generic_file_direct_write(iocb, from);
> +       written = btrfs_direct_IO(iocb, from);
>
>         if (written < 0 || !iov_iter_count(from))
>                 return written;
> @@ -3444,9 +3444,26 @@ 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      = generic_file_read_iter,
> +       .read_iter      = btrfs_file_read_iter,
>         .splice_read    = generic_file_splice_read,
>         .write_iter     = btrfs_file_write_iter,
>         .mmap           = btrfs_file_mmap,
> diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
> index 56032c518b26..86730f2f2bf6 100644
> --- a/fs/btrfs/inode.c
> +++ b/fs/btrfs/inode.c
> @@ -29,6 +29,7 @@
>  #include <linux/iversion.h>
>  #include <linux/swap.h>
>  #include <linux/sched/mm.h>
> +#include <linux/iomap.h>
>  #include <asm/unaligned.h>
>  #include "misc.h"
>  #include "ctree.h"
> @@ -7510,7 +7511,7 @@ 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, int writing)
> +                             struct extent_state **cached_state, bool writing)
>  {
>         struct btrfs_ordered_extent *ordered;
>         int ret = 0;
> @@ -7648,30 +7649,7 @@ 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)
> @@ -7733,7 +7711,6 @@ 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)) {
> @@ -7744,15 +7721,6 @@ 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.
> @@ -7768,24 +7736,37 @@ static int btrfs_get_blocks_direct_write(struct extent_map **map,
>         return ret;
>  }
>
> -static int btrfs_get_blocks_direct(struct inode *inode, sector_t iblock,
> -                                  struct buffer_head *bh_result, int create)
> +static int btrfs_dio_iomap_begin(struct inode *inode, loff_t start,
> +               loff_t length, unsigned flags, struct iomap *iomap,
> +               struct iomap *srcmap)
>  {
>         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;
> -       u64 len = bh_result->b_size;
> +       bool write = !!(flags & IOMAP_WRITE);
>         int ret = 0;
> +       u64 len = length;
> +       bool unlock_extents = false;
>
> -       if (!create)
> +       if (!write)
>                 len = min_t(u64, len, fs_info->sectorsize);
>
>         lockstart = start;
>         lockend = start + len - 1;
>
> +       /*
> +        * 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.
> +        */
> +       if (test_bit(BTRFS_INODE_HAS_ASYNC_EXTENT,
> +                    &BTRFS_I(inode)->runtime_flags))
> +               ret = filemap_fdatawrite_range(inode->i_mapping, start,
> +                                        start + length - 1);
> +
>         if (current->journal_info) {
>                 /*
>                  * Need to pull our outstanding extents and set journal_info to NULL so
> @@ -7801,7 +7782,7 @@ static int btrfs_get_blocks_direct(struct inode *inode, sector_t iblock,
>          * this range and we need to fallback to buffered.
>          */
>         if (lock_extent_direct(inode, lockstart, lockend, &cached_state,
> -                              create)) {
> +                              write)) {
>                 ret = -ENOTBLK;
>                 goto err;
>         }
> @@ -7833,36 +7814,53 @@ static int btrfs_get_blocks_direct(struct inode *inode, sector_t iblock,
>                 goto unlock_err;
>         }
>
> -       if (create) {
> -               ret = btrfs_get_blocks_direct_write(&em, bh_result, inode,
> +       len = min(len, em->len - (start - em->start));
> +       if (write) {
> +               ret = btrfs_get_blocks_direct_write(&em, inode,
>                                                     dio_data, start, len);
>                 if (ret < 0)
>                         goto unlock_err;
> -
> -               unlock_extent_cached(&BTRFS_I(inode)->io_tree, lockstart,
> -                                    lockend, &cached_state);
> +               unlock_extents = true;
> +               /* Recalc len in case the new em is smaller than requested */
> +               len = min(len, em->len - (start - em->start));
> +       } else if (em->block_start == EXTENT_MAP_HOLE ||
> +                       test_bit(EXTENT_FLAG_PREALLOC, &em->flags)) {
> +               /* Unlock in case of direct reading from a hole */
> +               unlock_extents = true;
>         } 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 + 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);
> -               }
> +               lockstart = start + len;
> +               if (lockstart < lockend)
> +                       unlock_extents = true;
>         }
>
> +       if (unlock_extents)
> +               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;
> +       }
> +       iomap->offset = start;
> +       iomap->bdev = fs_info->fs_devices->latest_bdev;
> +       iomap->length = len;
> +
>         free_extent_map(em);
>
>         return 0;
> @@ -8230,9 +8228,8 @@ static void btrfs_endio_direct_read(struct bio *bio)
>         kfree(dip);
>
>         dio_bio->bi_status = err;
> -       dio_end_io(dio_bio);
> +       bio_endio(dio_bio);
>         btrfs_io_bio_free_csum(io_bio);
> -       bio_put(bio);
>  }
>
>  static void __endio_write_update_ordered(struct inode *inode,
> @@ -8289,8 +8286,7 @@ static void btrfs_endio_direct_write(struct bio *bio)
>         kfree(dip);
>
>         dio_bio->bi_status = bio->bi_status;
> -       dio_end_io(dio_bio);
> -       bio_put(bio);
> +       bio_endio(dio_bio);
>  }
>
>  static blk_status_t btrfs_submit_bio_start_direct_io(void *private_data,
> @@ -8522,9 +8518,10 @@ static int btrfs_submit_direct_hook(struct btrfs_dio_private *dip)
>         return 0;
>  }
>
> -static void btrfs_submit_direct(struct bio *dio_bio, struct inode *inode,
> +static blk_qc_t btrfs_submit_direct(struct bio *dio_bio, struct file *file,
>                                 loff_t file_offset)
>  {
> +       struct inode *inode = file_inode(file);
>         struct btrfs_dio_private *dip = NULL;
>         struct bio *bio = NULL;
>         struct btrfs_io_bio *io_bio;
> @@ -8575,7 +8572,7 @@ static void btrfs_submit_direct(struct bio *dio_bio, struct inode *inode,
>
>         ret = btrfs_submit_direct_hook(dip);
>         if (!ret)
> -               return;
> +               return BLK_QC_T_NONE;
>
>         btrfs_io_bio_free_csum(io_bio);
>
> @@ -8594,7 +8591,7 @@ static void btrfs_submit_direct(struct bio *dio_bio, struct inode *inode,
>                 /*
>                  * The end io callbacks free our dip, do the final put on bio
>                  * and all the cleanup and final put for dio_bio (through
> -                * dio_end_io()).
> +                * end_io()).
>                  */
>                 dip = NULL;
>                 bio = NULL;
> @@ -8613,11 +8610,12 @@ static void btrfs_submit_direct(struct bio *dio_bio, struct inode *inode,
>                  * Releases and cleans up our dio_bio, no need to bio_put()
>                  * nor bio_endio()/bio_io_error() against dio_bio.
>                  */
> -               dio_end_io(dio_bio);
> +               bio_endio(dio_bio);

Same as before, the comment is now stale. It mentions no need to call
bio_endio(), yet the change makes it call bio_endio().

thanks

>         }
>         if (bio)
>                 bio_put(bio);
>         kfree(dip);
> +       return BLK_QC_T_NONE;
>  }
>
>  static ssize_t check_direct_IO(struct btrfs_fs_info *fs_info,
> @@ -8653,7 +8651,23 @@ static ssize_t check_direct_IO(struct btrfs_fs_info *fs_info,
>         return retval;
>  }
>
> -static ssize_t btrfs_direct_IO(struct kiocb *iocb, struct iov_iter *iter)
> +static const struct iomap_ops btrfs_dio_iomap_ops = {
> +       .iomap_begin            = btrfs_dio_iomap_begin,
> +};
> +
> +static const struct iomap_dio_ops btrfs_dops = {
> +       .submit_io              = btrfs_submit_direct,
> +};
> +
> +
> +/*
> + * btrfs_direct_IO - perform direct I/O
> + * inode->i_rwsem must be locked before calling this function, shared or exclusive.
> + * @iocb - kernel iocb
> + * @iter - iter to/from data is copied
> + */
> +
> +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;
> @@ -8662,28 +8676,13 @@ static ssize_t btrfs_direct_IO(struct kiocb *iocb, struct iov_iter *iter)
>         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
> @@ -8714,17 +8713,11 @@ static ssize_t btrfs_direct_IO(struct kiocb *iocb, struct iov_iter *iter)
>                 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 = __blockdev_direct_IO(iocb, inode,
> -                                  fs_info->fs_devices->latest_bdev,
> -                                  iter, btrfs_get_blocks_direct, NULL,
> -                                  btrfs_submit_direct, flags);
> +       ret = iomap_dio_rw(iocb, iter, &btrfs_dio_iomap_ops, &btrfs_dops,
> +                       is_sync_kiocb(iocb));
> +
>         if (iov_iter_rw(iter) == WRITE) {
>                 up_read(&BTRFS_I(inode)->dio_sem);
>                 current->journal_info = NULL;
> @@ -8751,11 +8744,8 @@ static ssize_t btrfs_direct_IO(struct kiocb *iocb, struct iov_iter *iter)
>                 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;
>  }
> @@ -11045,7 +11035,7 @@ static const struct address_space_operations btrfs_aops = {
>         .writepage      = btrfs_writepage,
>         .writepages     = btrfs_writepages,
>         .readpages      = btrfs_readpages,
> -       .direct_IO      = btrfs_direct_IO,
> +       .direct_IO      = noop_direct_IO,
>         .invalidatepage = btrfs_invalidatepage,
>         .releasepage    = btrfs_releasepage,
>         .set_page_dirty = btrfs_set_page_dirty,
> --
> 2.16.4
>

Re: [PATCH 4/8] btrfs: Switch to iomap_dio_rw() for dio

[Nikolay Borisov]

On 11.12.19 г. 1:01 ч., Goldwyn Rodrigues wrote:
> From: Goldwyn Rodrigues <rgoldwyn@suse.com>
> 
> Switch from __blockdev_direct_IO() to iomap_dio_rw().
> Rename btrfs_get_blocks_direct() to btrfs_dio_iomap_begin() and use it
> as iomap_begin() for iomap direct I/O functions. This function
> allocates and locks all the blocks required for the I/O.
> btrfs_submit_direct() is used as the submit_io() hook for direct I/O
> ops.
> 
> Since we need direct I/O reads to go through iomap_dio_rw(), we change
> file_operations.read_iter() to a btrfs_file_read_iter() which calls
> btrfs_direct_IO() for direct reads and falls back to
> generic_file_buffered_read() for incomplete reads and buffered reads.
> 
> We don't need address_space.direct_IO() anymore so set it to noop.
> Similarly, we don't need flags used in __blockdev_direct_IO(). iomap is
> capable of direct I/O reads from a hole, so we don't need to return
> -ENOENT.
> 
> BTRFS direct I/O is now done under i_rwsem, shared in case of
> reads and exclusive in case of writes. This guards against simultaneous
> truncates.
> 
> Signed-off-by: Goldwyn Rodrigues <rgoldwyn@suse.com>
> ---
>  fs/btrfs/ctree.h |   1 +
>  fs/btrfs/file.c  |  21 ++++++-
>  fs/btrfs/inode.c | 184 ++++++++++++++++++++++++++-----------------------------
>  3 files changed, 107 insertions(+), 99 deletions(-)
> 

<snip>

> +
> +/*
> + * btrfs_direct_IO - perform direct I/O
> + * inode->i_rwsem must be locked before calling this function, shared or exclusive.

Instead of having this as a comment which cannot easily be checked
automatically I'd rather it gets codified via lockdep_assert_held. I
believe this is in line with Dave's comment comment on patch 3.

> + * @iocb - kernel iocb
> + * @iter - iter to/from data is copied
> + */
> +
> +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;
> @@ -8662,28 +8676,13 @@ static ssize_t btrfs_direct_IO(struct kiocb *iocb, struct iov_iter *iter)
>  	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
> @@ -8714,17 +8713,11 @@ static ssize_t btrfs_direct_IO(struct kiocb *iocb, struct iov_iter *iter)
>  		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 = __blockdev_direct_IO(iocb, inode,
> -				   fs_info->fs_devices->latest_bdev,
> -				   iter, btrfs_get_blocks_direct, NULL,
> -				   btrfs_submit_direct, flags);
> +	ret = iomap_dio_rw(iocb, iter, &btrfs_dio_iomap_ops, &btrfs_dops,
> +			is_sync_kiocb(iocb));
> +
>  	if (iov_iter_rw(iter) == WRITE) {
>  		up_read(&BTRFS_I(inode)->dio_sem);
>  		current->journal_info = NULL;
> @@ -8751,11 +8744,8 @@ static ssize_t btrfs_direct_IO(struct kiocb *iocb, struct iov_iter *iter)
>  		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;
>  }
> @@ -11045,7 +11035,7 @@ static const struct address_space_operations btrfs_aops = {
>  	.writepage	= btrfs_writepage,
>  	.writepages	= btrfs_writepages,
>  	.readpages	= btrfs_readpages,
> -	.direct_IO	= btrfs_direct_IO,
> +	.direct_IO	= noop_direct_IO,
>  	.invalidatepage = btrfs_invalidatepage,
>  	.releasepage	= btrfs_releasepage,
>  	.set_page_dirty	= btrfs_set_page_dirty,
> 

[PATCH 5/8] fs: Remove dio_end_io()

[Goldwyn Rodrigues]

From: Goldwyn Rodrigues <rgoldwyn@suse.com>

Since we removed the last user of dio_end_io(), remove the helper
function dio_end_io().

Reviewed-by: Nikolay Borisov <nborisov@suse.com>
Reviewed-by: Johannes Thumshirn <jthumshirn@suse.de>
Signed-off-by: Goldwyn Rodrigues <rgoldwyn@suse.com>
---
 fs/direct-io.c     | 19 -------------------
 include/linux/fs.h |  2 --
 2 files changed, 21 deletions(-)

diff --git a/fs/direct-io.c b/fs/direct-io.c
index 0ec4f270139f..fb19a77bec22 100644
--- a/fs/direct-io.c
+++ b/fs/direct-io.c
@@ -384,25 +384,6 @@ static void dio_bio_end_io(struct bio *bio)
 	spin_unlock_irqrestore(&dio->bio_lock, flags);
 }
 
-/**
- * dio_end_io - handle the end io action for the given bio
- * @bio: The direct io bio thats being completed
- *
- * This is meant to be called by any filesystem that uses their own dio_submit_t
- * so that the DIO specific endio actions are dealt with after the filesystem
- * has done it's completion work.
- */
-void dio_end_io(struct bio *bio)
-{
-	struct dio *dio = bio->bi_private;
-
-	if (dio->is_async)
-		dio_bio_end_aio(bio);
-	else
-		dio_bio_end_io(bio);
-}
-EXPORT_SYMBOL_GPL(dio_end_io);
-
 static inline void
 dio_bio_alloc(struct dio *dio, struct dio_submit *sdio,
 	      struct block_device *bdev,
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 3883adaa0e01..d708422f77e0 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -3157,8 +3157,6 @@ enum {
 	DIO_SKIP_HOLES	= 0x02,
 };
 
-void dio_end_io(struct bio *bio);
-
 ssize_t __blockdev_direct_IO(struct kiocb *iocb, struct inode *inode,
 			     struct block_device *bdev, struct iov_iter *iter,
 			     get_block_t get_block,
-- 
2.16.4

[PATCH 6/8] btrfs: Wait for extent bits to release page

[Goldwyn Rodrigues]

From: Goldwyn Rodrigues <rgoldwyn@suse.com>

While trying to release a page, the extent containing the page may be locked
which would stop the page from being released. Wait for the
extent lock to be cleared, if blocking is allowed and then clear
the bits.

While we are at it, clean the code of try_release_extent_state() to make
it simpler.

Signed-off-by: Goldwyn Rodrigues <rgoldwyn@suse.com>
Reviewed-by: Johannes Thumshirn <jthumshirn@suse.de>
Reviewed-by: Nikolay Borisov <nborisov@suse.com>
---
 fs/btrfs/extent_io.c | 37 ++++++++++++++++---------------------
 fs/btrfs/extent_io.h |  2 +-
 fs/btrfs/inode.c     |  4 ++--
 3 files changed, 19 insertions(+), 24 deletions(-)

diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c
index eb8bd0258360..193785981183 100644
--- a/fs/btrfs/extent_io.c
+++ b/fs/btrfs/extent_io.c
@@ -4360,33 +4360,28 @@ int extent_invalidatepage(struct extent_io_tree *tree,
  * are locked or under IO and drops the related state bits if it is safe
  * to drop the page.
  */
-static int try_release_extent_state(struct extent_io_tree *tree,
+static bool try_release_extent_state(struct extent_io_tree *tree,
 				    struct page *page, gfp_t mask)
 {
 	u64 start = page_offset(page);
 	u64 end = start + PAGE_SIZE - 1;
-	int ret = 1;
 
 	if (test_range_bit(tree, start, end, EXTENT_LOCKED, 0, NULL)) {
-		ret = 0;
-	} else {
-		/*
-		 * at this point we can safely clear everything except the
-		 * locked bit and the nodatasum bit
-		 */
-		ret = __clear_extent_bit(tree, start, end,
-				 ~(EXTENT_LOCKED | EXTENT_NODATASUM),
-				 0, 0, NULL, mask, NULL);
-
-		/* if clear_extent_bit failed for enomem reasons,
-		 * we can't allow the release to continue.
-		 */
-		if (ret < 0)
-			ret = 0;
-		else
-			ret = 1;
+		if (!gfpflags_allow_blocking(mask))
+			return false;
+		wait_extent_bit(tree, start, end, EXTENT_LOCKED);
 	}
-	return ret;
+	/*
+	 * At this point we can safely clear everything except the locked and
+	 * nodatasum bits. If clear_extent_bit failed due to -ENOMEM,
+	 * don't allow release.
+	 */
+	if (__clear_extent_bit(tree, start, end,
+				~(EXTENT_LOCKED | EXTENT_NODATASUM), 0, 0,
+				NULL, mask, NULL) < 0)
+		return false;
+
+	return true;
 }
 
 /*
@@ -4394,7 +4389,7 @@ static int try_release_extent_state(struct extent_io_tree *tree,
  * in the range corresponding to the page, both state records and extent
  * map records are removed
  */
-int try_release_extent_mapping(struct page *page, gfp_t mask)
+bool try_release_extent_mapping(struct page *page, gfp_t mask)
 {
 	struct extent_map *em;
 	u64 start = page_offset(page);
diff --git a/fs/btrfs/extent_io.h b/fs/btrfs/extent_io.h
index a8551a1f56e2..89cc0cf8a7fd 100644
--- a/fs/btrfs/extent_io.h
+++ b/fs/btrfs/extent_io.h
@@ -188,7 +188,7 @@ typedef struct extent_map *(get_extent_t)(struct btrfs_inode *inode,
 					  u64 start, u64 len,
 					  int create);
 
-int try_release_extent_mapping(struct page *page, gfp_t mask);
+bool try_release_extent_mapping(struct page *page, gfp_t mask);
 int try_release_extent_buffer(struct page *page);
 
 int extent_read_full_page(struct extent_io_tree *tree, struct page *page,
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index 86730f2f2bf6..88f2a7229459 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -8811,8 +8811,8 @@ btrfs_readpages(struct file *file, struct address_space *mapping,
 
 static int __btrfs_releasepage(struct page *page, gfp_t gfp_flags)
 {
-	int ret = try_release_extent_mapping(page, gfp_flags);
-	if (ret == 1) {
+	bool ret = try_release_extent_mapping(page, gfp_flags);
+	if (ret) {
 		ClearPagePrivate(page);
 		set_page_private(page, 0);
 		put_page(page);
-- 
2.16.4

[PATCH 7/8] btrfs: Use iomap_end() instead of btrfs_dio_data

[Goldwyn Rodrigues]

From: Goldwyn Rodrigues <rgoldwyn@suse.com>

Use iomap_end() to check for failed or incomplete writes and call
__endio_write_update_ordered(). We don't need btrfs_dio_data
anymore so remove that. The bonus is we don't abuse
current->journal_info anymore.

Signed-off-by: Goldwyn Rodrigues <rgoldwyn@suse.com>
---
 fs/btrfs/inode.c | 89 ++++++++++----------------------------------------------
 1 file changed, 16 insertions(+), 73 deletions(-)

diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index 88f2a7229459..ce53f2889673 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -56,13 +56,6 @@ struct btrfs_iget_args {
 	struct btrfs_root *root;
 };
 
-struct btrfs_dio_data {
-	u64 reserve;
-	u64 unsubmitted_oe_range_start;
-	u64 unsubmitted_oe_range_end;
-	int overwrite;
-};
-
 static const struct inode_operations btrfs_dir_inode_operations;
 static const struct inode_operations btrfs_symlink_inode_operations;
 static const struct inode_operations btrfs_dir_ro_inode_operations;
@@ -7651,7 +7644,6 @@ static struct extent_map *create_io_em(struct inode *inode, u64 start, u64 len,
 
 static int btrfs_get_blocks_direct_write(struct extent_map **map,
 					 struct inode *inode,
-					 struct btrfs_dio_data *dio_data,
 					 u64 start, u64 len)
 {
 	struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
@@ -7725,13 +7717,9 @@ static int btrfs_get_blocks_direct_write(struct extent_map **map,
 	 * Need to update the i_size under the extent lock so buffered
 	 * readers will get the updated i_size when we unlock.
 	 */
-	if (!dio_data->overwrite && start + len > i_size_read(inode))
+	if (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;
 }
@@ -7743,7 +7731,6 @@ static int btrfs_dio_iomap_begin(struct inode *inode, loff_t start,
 	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 lockstart, lockend;
 	bool write = !!(flags & IOMAP_WRITE);
 	int ret = 0;
@@ -7767,16 +7754,6 @@ static int btrfs_dio_iomap_begin(struct inode *inode, loff_t start,
 		ret = filemap_fdatawrite_range(inode->i_mapping, start,
 					 start + length - 1);
 
-	if (current->journal_info) {
-		/*
-		 * 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.
-		 */
-		dio_data = current->journal_info;
-		current->journal_info = NULL;
-	}
-
 	/*
 	 * If this errors out it's because we couldn't invalidate pagecache for
 	 * this range and we need to fallback to buffered.
@@ -7817,7 +7794,7 @@ static int btrfs_dio_iomap_begin(struct inode *inode, loff_t start,
 	len = min(len, em->len - (start - em->start));
 	if (write) {
 		ret = btrfs_get_blocks_direct_write(&em, inode,
-						    dio_data, start, len);
+						    start, len);
 		if (ret < 0)
 			goto unlock_err;
 		unlock_extents = true;
@@ -7869,11 +7846,21 @@ 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)
-		current->journal_info = 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)
+{
+	if (!(flags & IOMAP_WRITE))
+		return 0;
+
+	if (written < length)
+		__endio_write_update_ordered(inode, pos + written,
+				length - written, false);
+	return 0;
+}
+
 static inline blk_status_t submit_dio_repair_bio(struct inode *inode,
 						 struct bio *bio,
 						 int mirror_num)
@@ -8555,21 +8542,6 @@ static blk_qc_t btrfs_submit_direct(struct bio *dio_bio, struct file *file,
 		dip->subio_endio = btrfs_subio_endio_read;
 	}
 
-	/*
-	 * Reset the range for unsubmitted ordered extents (to a 0 length range)
-	 * even if we fail to submit a bio, because in such case we do the
-	 * corresponding error handling below and it must not be done a second
-	 * time by btrfs_direct_IO().
-	 */
-	if (write) {
-		struct btrfs_dio_data *dio_data = current->journal_info;
-
-		dio_data->unsubmitted_oe_range_end = dip->logical_offset +
-			dip->bytes;
-		dio_data->unsubmitted_oe_range_start =
-			dio_data->unsubmitted_oe_range_end;
-	}
-
 	ret = btrfs_submit_direct_hook(dip);
 	if (!ret)
 		return BLK_QC_T_NONE;
@@ -8653,6 +8625,7 @@ static ssize_t check_direct_IO(struct btrfs_fs_info *fs_info,
 
 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 = {
@@ -8672,7 +8645,6 @@ 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;
@@ -8690,7 +8662,6 @@ 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) {
@@ -8702,16 +8673,6 @@ ssize_t btrfs_direct_IO(struct kiocb *iocb, struct iov_iter *iter)
 		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);
 	}
 
@@ -8720,25 +8681,7 @@ ssize_t btrfs_direct_IO(struct kiocb *iocb, struct iov_iter *iter)
 
 	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)
+		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);
-- 
2.16.4

[PATCH 8/8] btrfs: remove BTRFS_INODE_READDIO_NEED_LOCK

[Goldwyn Rodrigues]

From: Goldwyn Rodrigues <rgoldwyn@suse.com>

Since we now perform direct reads using i_rwsem, we can remove this
inode flag used to co-ordinate unlocked reads.

The truncate call chain gets the i_rwsem which may conflict with direct
reads:
do_truncate <-- calls inode_lock
  notify_change
   ->setattr/btrfs_setattr
     btrfs_setsize

Signed-off-by: Goldwyn Rodrigues <rgoldwyn@suse.com>
Reviewed-by: Nikolay Borisov <nborisov@suse.com>
---
 fs/btrfs/btrfs_inode.h | 18 ------------------
 fs/btrfs/inode.c       |  5 -----
 2 files changed, 23 deletions(-)

diff --git a/fs/btrfs/btrfs_inode.h b/fs/btrfs/btrfs_inode.h
index 4e12a477d32e..cd8f378ed8e7 100644
--- a/fs/btrfs/btrfs_inode.h
+++ b/fs/btrfs/btrfs_inode.h
@@ -27,7 +27,6 @@ enum {
 	BTRFS_INODE_NEEDS_FULL_SYNC,
 	BTRFS_INODE_COPY_EVERYTHING,
 	BTRFS_INODE_IN_DELALLOC_LIST,
-	BTRFS_INODE_READDIO_NEED_LOCK,
 	BTRFS_INODE_HAS_PROPS,
 	BTRFS_INODE_SNAPSHOT_FLUSH,
 };
@@ -317,23 +316,6 @@ struct btrfs_dio_private {
 			blk_status_t);
 };
 
-/*
- * Disable DIO read nolock optimization, so new dio readers will be forced
- * to grab i_mutex. It is used to avoid the endless truncate due to
- * nonlocked dio read.
- */
-static inline void btrfs_inode_block_unlocked_dio(struct btrfs_inode *inode)
-{
-	set_bit(BTRFS_INODE_READDIO_NEED_LOCK, &inode->runtime_flags);
-	smp_mb();
-}
-
-static inline void btrfs_inode_resume_unlocked_dio(struct btrfs_inode *inode)
-{
-	smp_mb__before_atomic();
-	clear_bit(BTRFS_INODE_READDIO_NEED_LOCK, &inode->runtime_flags);
-}
-
 /* Array of bytes with variable length, hexadecimal format 0x1234 */
 #define CSUM_FMT				"0x%*phN"
 #define CSUM_FMT_VALUE(size, bytes)		size, bytes
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index ce53f2889673..4c76a6d5e6a4 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -5273,11 +5273,6 @@ static int btrfs_setsize(struct inode *inode, struct iattr *attr)
 
 		truncate_setsize(inode, newsize);
 
-		/* Disable nonlocked read DIO to avoid the endless truncate */
-		btrfs_inode_block_unlocked_dio(BTRFS_I(inode));
-		inode_dio_wait(inode);
-		btrfs_inode_resume_unlocked_dio(BTRFS_I(inode));
-
 		ret = btrfs_truncate(inode, newsize == oldsize);
 		if (ret && inode->i_nlink) {
 			int err;
-- 
2.16.4

Re: [PATCH 8/8] btrfs: remove BTRFS_INODE_READDIO_NEED_LOCK

[Nikolay Borisov]

On 11.12.19 г. 1:01 ч., Goldwyn Rodrigues wrote:
> From: Goldwyn Rodrigues <rgoldwyn@suse.com>
> 
> Since we now perform direct reads using i_rwsem, we can remove this
> inode flag used to co-ordinate unlocked reads.
> 
> The truncate call chain gets the i_rwsem which may conflict with direct

nit: Truncating taking i_rwsem means it's correctly synchronized with
concurrent DIO reads. So it's protected, just the wording needs to be
tweaked.

> reads:
> do_truncate <-- calls inode_lock
>   notify_change
>    ->setattr/btrfs_setattr
>      btrfs_setsize
> 
> Signed-off-by: Goldwyn Rodrigues <rgoldwyn@suse.com>
> Reviewed-by: Nikolay Borisov <nborisov@suse.com>
> ---
>  fs/btrfs/btrfs_inode.h | 18 ------------------
>  fs/btrfs/inode.c       |  5 -----
>  2 files changed, 23 deletions(-)
> 
> diff --git a/fs/btrfs/btrfs_inode.h b/fs/btrfs/btrfs_inode.h
> index 4e12a477d32e..cd8f378ed8e7 100644
> --- a/fs/btrfs/btrfs_inode.h
> +++ b/fs/btrfs/btrfs_inode.h
> @@ -27,7 +27,6 @@ enum {
>  	BTRFS_INODE_NEEDS_FULL_SYNC,
>  	BTRFS_INODE_COPY_EVERYTHING,
>  	BTRFS_INODE_IN_DELALLOC_LIST,
> -	BTRFS_INODE_READDIO_NEED_LOCK,
>  	BTRFS_INODE_HAS_PROPS,
>  	BTRFS_INODE_SNAPSHOT_FLUSH,
>  };
> @@ -317,23 +316,6 @@ struct btrfs_dio_private {
>  			blk_status_t);
>  };
>  
> -/*
> - * Disable DIO read nolock optimization, so new dio readers will be forced
> - * to grab i_mutex. It is used to avoid the endless truncate due to
> - * nonlocked dio read.
> - */
> -static inline void btrfs_inode_block_unlocked_dio(struct btrfs_inode *inode)
> -{
> -	set_bit(BTRFS_INODE_READDIO_NEED_LOCK, &inode->runtime_flags);
> -	smp_mb();
> -}
> -
> -static inline void btrfs_inode_resume_unlocked_dio(struct btrfs_inode *inode)
> -{
> -	smp_mb__before_atomic();
> -	clear_bit(BTRFS_INODE_READDIO_NEED_LOCK, &inode->runtime_flags);
> -}
> -
>  /* Array of bytes with variable length, hexadecimal format 0x1234 */
>  #define CSUM_FMT				"0x%*phN"
>  #define CSUM_FMT_VALUE(size, bytes)		size, bytes
> diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
> index ce53f2889673..4c76a6d5e6a4 100644
> --- a/fs/btrfs/inode.c
> +++ b/fs/btrfs/inode.c
> @@ -5273,11 +5273,6 @@ static int btrfs_setsize(struct inode *inode, struct iattr *attr)
>  
>  		truncate_setsize(inode, newsize);
>  
> -		/* Disable nonlocked read DIO to avoid the endless truncate */
> -		btrfs_inode_block_unlocked_dio(BTRFS_I(inode));
> -		inode_dio_wait(inode);
> -		btrfs_inode_resume_unlocked_dio(BTRFS_I(inode));
> -
>  		ret = btrfs_truncate(inode, newsize == oldsize);
>  		if (ret && inode->i_nlink) {
>  			int err;
>