Merge tag 'for-5.20/io_uring-buffered-writes-2022-07-29' of git://git.kernel.dk/linux-block

Pull io_uring buffered writes support from Jens Axboe:
 "This contains support for buffered writes, specifically for XFS. btrfs
  is in progress, will be coming in the next release.

  io_uring does support buffered writes on any file type, but since the
  buffered write path just always -EAGAIN (or -EOPNOTSUPP) any attempt
  to do so if IOCB_NOWAIT is set, any buffered write will effectively be
  handled by io-wq offload. This isn't very efficient, and we even have
  specific code in io-wq to serialize buffered writes to the same inode
  to avoid further inefficiencies with thread offload.

  This is particularly sad since most buffered writes don't block, they
  simply copy data to a page and dirty it. With this pull request, we
  can handle buffered writes a lot more effiently.

  If balance_dirty_pages() needs to block, we back off on writes as
  indicated.

  This improves buffered write support by 2-3x.

  Jan Kara helped with the mm bits for this, and Stefan handled the
  fs/iomap/xfs/io_uring parts of it"

* tag 'for-5.20/io_uring-buffered-writes-2022-07-29' of git://git.kernel.dk/linux-block:
  mm: honor FGP_NOWAIT for page cache page allocation
  xfs: Add async buffered write support
  xfs: Specify lockmode when calling xfs_ilock_for_iomap()
  io_uring: Add tracepoint for short writes
  io_uring: fix issue with io_write() not always undoing sb_start_write()
  io_uring: Add support for async buffered writes
  fs: Add async write file modification handling.
  fs: Split off inode_needs_update_time and __file_update_time
  fs: add __remove_file_privs() with flags parameter
  fs: add a FMODE_BUF_WASYNC flags for f_mode
  iomap: Return -EAGAIN from iomap_write_iter()
  iomap: Add async buffered write support
  iomap: Add flags parameter to iomap_page_create()
  mm: Add balance_dirty_pages_ratelimited_flags() function
  mm: Move updates of dirty_exceeded into one place
  mm: Move starting of background writeback into the main balancing loop

1 files changed, 35 insertions, 6 deletions

diff --git a/io_uring/rw.c b/io_uring/rw.c
index c50a0d66d67a..2b784795103c 100644
--- a/io_uring/rw.c
+++ b/io_uring/rw.c
@@ -641,7 +641,7 @@ static inline int io_iter_do_read(struct io_rw *rw, struct iov_iter *iter)
 		return -EINVAL;
 }
 
-static bool need_read_all(struct io_kiocb *req)
+static bool need_complete_io(struct io_kiocb *req)
 {
 	return req->flags & REQ_F_ISREG ||
 		S_ISBLK(file_inode(req->file)->i_mode);
@@ -775,7 +775,7 @@ int io_read(struct io_kiocb *req, unsigned int issue_flags)
 			kfree(iovec);
 		return IOU_ISSUE_SKIP_COMPLETE;
 	} else if (ret == req->cqe.res || ret <= 0 || !force_nonblock ||
-		   (req->flags & REQ_F_NOWAIT) || !need_read_all(req)) {
+		   (req->flags & REQ_F_NOWAIT) || !need_complete_io(req)) {
 		/* read all, failed, already did sync or don't want to retry */
 		goto done;
 	}
@@ -870,9 +870,10 @@ int io_write(struct io_kiocb *req, unsigned int issue_flags)
 		if (unlikely(!io_file_supports_nowait(req)))
 			goto copy_iov;
 
-		/* file path doesn't support NOWAIT for non-direct_IO */
-		if (force_nonblock && !(kiocb->ki_flags & IOCB_DIRECT) &&
-		    (req->flags & REQ_F_ISREG))
+		/* File path supports NOWAIT for non-direct_IO only for block devices. */
+		if (!(kiocb->ki_flags & IOCB_DIRECT) &&
+			!(kiocb->ki_filp->f_mode & FMODE_BUF_WASYNC) &&
+			(req->flags & REQ_F_ISREG))
 			goto copy_iov;
 
 		kiocb->ki_flags |= IOCB_NOWAIT;
@@ -928,13 +929,41 @@ int io_write(struct io_kiocb *req, unsigned int issue_flags)
 		/* IOPOLL retry should happen for io-wq threads */
 		if (ret2 == -EAGAIN && (req->ctx->flags & IORING_SETUP_IOPOLL))
 			goto copy_iov;
+
+		if (ret2 != req->cqe.res && ret2 >= 0 && need_complete_io(req)) {
+			struct io_async_rw *rw;
+
+			trace_io_uring_short_write(req->ctx, kiocb->ki_pos - ret2,
+						req->cqe.res, ret2);
+
+			/* This is a partial write. The file pos has already been
+			 * updated, setup the async struct to complete the request
+			 * in the worker. Also update bytes_done to account for
+			 * the bytes already written.
+			 */
+			iov_iter_save_state(&s->iter, &s->iter_state);
+			ret = io_setup_async_rw(req, iovec, s, true);
+
+			rw = req->async_data;
+			if (rw)
+				rw->bytes_done += ret2;
+
+			if (kiocb->ki_flags & IOCB_WRITE)
+				kiocb_end_write(req);
+			return ret ? ret : -EAGAIN;
+		}
 done:
 		ret = kiocb_done(req, ret2, issue_flags);
 	} else {
 copy_iov:
 		iov_iter_restore(&s->iter, &s->iter_state);
 		ret = io_setup_async_rw(req, iovec, s, false);
-		return ret ?: -EAGAIN;
+		if (!ret) {
+			if (kiocb->ki_flags & IOCB_WRITE)
+				kiocb_end_write(req);
+			return -EAGAIN;
+		}
+		return ret;
 	}
 	/* it's reportedly faster than delegating the null check to kfree() */
 	if (iovec)