mirror of https://lore.kernel.org/lkml/
 help / color / mirror / Atom feed
From: Tal Zussman <tz2294@columbia.edu>
To: "Matthew Wilcox (Oracle)" <willy@infradead.org>,
	Jan Kara <jack@suse.cz>,
	Andrew Morton <akpm@linux-foundation.org>,
	David Hildenbrand <david@kernel.org>,
	Lorenzo Stoakes <ljs@kernel.org>,
	"Liam R. Howlett" <liam@infradead.org>,
	Vlastimil Babka <vbabka@kernel.org>,
	Mike Rapoport <rppt@kernel.org>,
	Suren Baghdasaryan <surenb@google.com>,
	Michal Hocko <mhocko@suse.com>,
	Alexander Viro <viro@zeniv.linux.org.uk>,
	Christian Brauner <brauner@kernel.org>,
	Jens Axboe <axboe@kernel.dk>
Cc: linux-fsdevel@vger.kernel.org, linux-mm@kvack.org,
	linux-kernel@vger.kernel.org, io-uring@vger.kernel.org,
	Tal Zussman <tz2294@columbia.edu>
Subject: [PATCH RFC 10/11] fs: move generic_file_read_iter() to fs/read_write.c
Date: Wed, 20 May 2026 16:49:01 -0400	[thread overview]
Message-ID: <20260520-filemap-split-v1-10-c36ddc2b6cf2@columbia.edu> (raw)
In-Reply-To: <20260520-filemap-split-v1-0-c36ddc2b6cf2@columbia.edu>

generic_file_read_iter() and its kiocb_write_and_wait() helper are
VFS-level read functions: Their callers are filesystems, and their job
is to glue direct I/O or the page cache (filemap_read) to a struct kiocb
and iov_iter caller.

Move both to fs/read_write.c, alongside vfs_iter_read. Drop the extern
from generic_file_read_iter()'s declaration and reflow the
generic_file_read_iter() definition to fit on one line too.

Signed-off-by: Tal Zussman <tz2294@columbia.edu>
---
 fs/read_write.c         | 82 +++++++++++++++++++++++++++++++++++++++++++++++++
 include/linux/fs.h      |  3 +-
 include/linux/pagemap.h |  1 -
 mm/filemap.c            | 82 -------------------------------------------------
 4 files changed, 84 insertions(+), 84 deletions(-)

diff --git a/fs/read_write.c b/fs/read_write.c
index 50bff7edc91f..59ceea85c163 100644
--- a/fs/read_write.c
+++ b/fs/read_write.c
@@ -989,6 +989,88 @@ ssize_t vfs_iter_write(struct file *file, struct iov_iter *iter, loff_t *ppos,
 }
 EXPORT_SYMBOL(vfs_iter_write);
 
+int kiocb_write_and_wait(struct kiocb *iocb, size_t count)
+{
+	struct address_space *mapping = iocb->ki_filp->f_mapping;
+	loff_t pos = iocb->ki_pos;
+	loff_t end = pos + count - 1;
+
+	if (iocb->ki_flags & IOCB_NOWAIT) {
+		if (filemap_range_needs_writeback(mapping, pos, end))
+			return -EAGAIN;
+		return 0;
+	}
+
+	return filemap_write_and_wait_range(mapping, pos, end);
+}
+EXPORT_SYMBOL_GPL(kiocb_write_and_wait);
+
+/**
+ * generic_file_read_iter - generic filesystem read routine
+ * @iocb:	kernel I/O control block
+ * @iter:	destination for the data read
+ *
+ * This is the "read_iter()" routine for all filesystems
+ * that can use the page cache directly.
+ *
+ * The IOCB_NOWAIT flag in iocb->ki_flags indicates that -EAGAIN shall
+ * be returned when no data can be read without waiting for I/O requests
+ * to complete; it doesn't prevent readahead.
+ *
+ * The IOCB_NOIO flag in iocb->ki_flags indicates that no new I/O
+ * requests shall be made for the read or for readahead.  When no data
+ * can be read, -EAGAIN shall be returned.  When readahead would be
+ * triggered, a partial, possibly empty read shall be returned.
+ *
+ * Return:
+ * * number of bytes copied, even for partial reads
+ * * negative error code (or 0 if IOCB_NOIO) if nothing was read
+ */
+ssize_t generic_file_read_iter(struct kiocb *iocb, struct iov_iter *iter)
+{
+	size_t count = iov_iter_count(iter);
+	ssize_t retval = 0;
+
+	if (!count)
+		return 0; /* skip atime */
+
+	if (iocb->ki_flags & IOCB_DIRECT) {
+		struct file *file = iocb->ki_filp;
+		struct address_space *mapping = file->f_mapping;
+		struct inode *inode = mapping->host;
+
+		retval = kiocb_write_and_wait(iocb, count);
+		if (retval < 0)
+			return retval;
+		file_accessed(file);
+
+		retval = mapping->a_ops->direct_IO(iocb, iter);
+		if (retval >= 0) {
+			iocb->ki_pos += retval;
+			count -= retval;
+		}
+		if (retval != -EIOCBQUEUED)
+			iov_iter_revert(iter, count - iov_iter_count(iter));
+
+		/*
+		 * Btrfs can have a short DIO read if we encounter
+		 * compressed extents, so if there was an error, or if
+		 * we've already read everything we wanted to, or if
+		 * there was a short read because we hit EOF, go ahead
+		 * and return.  Otherwise fallthrough to buffered io for
+		 * the rest of the read.  Buffered reads will not work for
+		 * DAX files, so don't bother trying.
+		 */
+		if (retval < 0 || !count || IS_DAX(inode))
+			return retval;
+		if (iocb->ki_pos >= i_size_read(inode))
+			return retval;
+	}
+
+	return filemap_read(iocb, iter, retval);
+}
+EXPORT_SYMBOL(generic_file_read_iter);
+
 static ssize_t vfs_readv(struct file *file, const struct iovec __user *vec,
 			 unsigned long vlen, loff_t *pos, rwf_t flags)
 {
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 776cc82932a7..c0151ced8e7a 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -3055,7 +3055,8 @@ extern int generic_write_check_limits(struct file *file, loff_t pos,
 extern int generic_file_rw_checks(struct file *file_in, struct file *file_out);
 ssize_t filemap_read(struct kiocb *iocb, struct iov_iter *to,
 		ssize_t already_read);
-extern ssize_t generic_file_read_iter(struct kiocb *, struct iov_iter *);
+ssize_t generic_file_read_iter(struct kiocb *, struct iov_iter *);
+int kiocb_write_and_wait(struct kiocb *iocb, size_t count);
 extern ssize_t __generic_file_write_iter(struct kiocb *, struct iov_iter *);
 extern ssize_t generic_file_write_iter(struct kiocb *, struct iov_iter *);
 extern ssize_t generic_file_direct_write(struct kiocb *, struct iov_iter *);
diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h
index f86a550ad516..46cefd552a51 100644
--- a/include/linux/pagemap.h
+++ b/include/linux/pagemap.h
@@ -59,7 +59,6 @@ int filemap_fdatawrite_range(struct address_space *mapping,
 		loff_t start, loff_t end);
 int filemap_check_errors(struct address_space *mapping);
 void __filemap_set_wb_err(struct address_space *mapping, int err);
-int kiocb_write_and_wait(struct kiocb *iocb, size_t count);
 
 static inline int filemap_write_and_wait(struct address_space *mapping)
 {
diff --git a/mm/filemap.c b/mm/filemap.c
index 079f9c3ac8a2..db7c53cd681b 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -2251,22 +2251,6 @@ ssize_t filemap_read(struct kiocb *iocb, struct iov_iter *iter,
 }
 EXPORT_SYMBOL_GPL(filemap_read);
 
-int kiocb_write_and_wait(struct kiocb *iocb, size_t count)
-{
-	struct address_space *mapping = iocb->ki_filp->f_mapping;
-	loff_t pos = iocb->ki_pos;
-	loff_t end = pos + count - 1;
-
-	if (iocb->ki_flags & IOCB_NOWAIT) {
-		if (filemap_range_needs_writeback(mapping, pos, end))
-			return -EAGAIN;
-		return 0;
-	}
-
-	return filemap_write_and_wait_range(mapping, pos, end);
-}
-EXPORT_SYMBOL_GPL(kiocb_write_and_wait);
-
 int filemap_invalidate_pages(struct address_space *mapping,
 			     loff_t pos, loff_t end, bool nowait)
 {
@@ -2302,72 +2286,6 @@ int kiocb_invalidate_pages(struct kiocb *iocb, size_t count)
 }
 EXPORT_SYMBOL_GPL(kiocb_invalidate_pages);
 
-/**
- * generic_file_read_iter - generic filesystem read routine
- * @iocb:	kernel I/O control block
- * @iter:	destination for the data read
- *
- * This is the "read_iter()" routine for all filesystems
- * that can use the page cache directly.
- *
- * The IOCB_NOWAIT flag in iocb->ki_flags indicates that -EAGAIN shall
- * be returned when no data can be read without waiting for I/O requests
- * to complete; it doesn't prevent readahead.
- *
- * The IOCB_NOIO flag in iocb->ki_flags indicates that no new I/O
- * requests shall be made for the read or for readahead.  When no data
- * can be read, -EAGAIN shall be returned.  When readahead would be
- * triggered, a partial, possibly empty read shall be returned.
- *
- * Return:
- * * number of bytes copied, even for partial reads
- * * negative error code (or 0 if IOCB_NOIO) if nothing was read
- */
-ssize_t
-generic_file_read_iter(struct kiocb *iocb, struct iov_iter *iter)
-{
-	size_t count = iov_iter_count(iter);
-	ssize_t retval = 0;
-
-	if (!count)
-		return 0; /* skip atime */
-
-	if (iocb->ki_flags & IOCB_DIRECT) {
-		struct file *file = iocb->ki_filp;
-		struct address_space *mapping = file->f_mapping;
-		struct inode *inode = mapping->host;
-
-		retval = kiocb_write_and_wait(iocb, count);
-		if (retval < 0)
-			return retval;
-		file_accessed(file);
-
-		retval = mapping->a_ops->direct_IO(iocb, iter);
-		if (retval >= 0) {
-			iocb->ki_pos += retval;
-			count -= retval;
-		}
-		if (retval != -EIOCBQUEUED)
-			iov_iter_revert(iter, count - iov_iter_count(iter));
-
-		/*
-		 * Btrfs can have a short DIO read if we encounter
-		 * compressed extents, so if there was an error, or if
-		 * we've already read everything we wanted to, or if
-		 * there was a short read because we hit EOF, go ahead
-		 * and return.  Otherwise fallthrough to buffered io for
-		 * the rest of the read.  Buffered reads will not work for
-		 * DAX files, so don't bother trying.
-		 */
-		if (retval < 0 || !count || IS_DAX(inode))
-			return retval;
-		if (iocb->ki_pos >= i_size_read(inode))
-			return retval;
-	}
-
-	return filemap_read(iocb, iter, retval);
-}
-EXPORT_SYMBOL(generic_file_read_iter);
 
 /*
  * Splice subpages from a folio into a pipe.

-- 
2.39.5


  parent reply	other threads:[~2026-05-20 20:50 UTC|newest]

Thread overview: 18+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2026-05-20 20:48 [PATCH RFC 00/11] mm/filemap: split out folio wait and VFS code Tal Zussman
2026-05-20 20:48 ` [PATCH RFC 01/11] mm: add folio_wake_writeback() helper Tal Zussman
2026-05-20 20:48 ` [PATCH RFC 02/11] folio_wait: move folio bit-lock and wait implementation to mm/folio_wait.c Tal Zussman
2026-05-20 20:48 ` [PATCH RFC 03/11] folio_wait: move folio bit-lock and wait declarations to include/linux/folio_wait.h Tal Zussman
2026-05-20 20:48 ` [PATCH RFC 04/11] folio_wait: move folio_wait_writeback() family to mm/folio_wait.c Tal Zussman
2026-05-20 20:48 ` [PATCH RFC 05/11] folio_wait: reformat comments and fix alignment Tal Zussman
2026-05-20 20:48 ` [PATCH RFC 06/11] folio_wait: rename wait_page_* infrastructure to wait_folio_* Tal Zussman
2026-05-20 20:48 ` [PATCH RFC 07/11] folio_wait: convert VM_BUG_ON_FOLIO() to VM_WARN_ON_ONCE_FOLIO() Tal Zussman
2026-05-20 20:48 ` [PATCH RFC 08/11] MAINTAINERS: add folio_wait files to MEMORY MANAGEMENT - CORE Tal Zussman
2026-05-20 20:49 ` [PATCH RFC 09/11] fs: move dir_pages() from <linux/pagemap.h> to <linux/fs.h> Tal Zussman
2026-05-20 20:49 ` Tal Zussman [this message]
2026-05-20 20:49 ` [PATCH RFC 11/11] fs: move generic_file_write_iter() family to fs/read_write.c Tal Zussman
2026-05-28  9:22 ` [PATCH RFC 00/11] mm/filemap: split out folio wait and VFS code Jan Kara
2026-05-28 11:04   ` Christian Brauner
2026-05-28 12:49   ` Christoph Hellwig
2026-05-29 22:54     ` Tal Zussman
2026-06-01  8:37       ` Christoph Hellwig
2026-05-29 22:26   ` Tal Zussman

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20260520-filemap-split-v1-10-c36ddc2b6cf2@columbia.edu \
    --to=tz2294@columbia.edu \
    --cc=akpm@linux-foundation.org \
    --cc=axboe@kernel.dk \
    --cc=brauner@kernel.org \
    --cc=david@kernel.org \
    --cc=io-uring@vger.kernel.org \
    --cc=jack@suse.cz \
    --cc=liam@infradead.org \
    --cc=linux-fsdevel@vger.kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-mm@kvack.org \
    --cc=ljs@kernel.org \
    --cc=mhocko@suse.com \
    --cc=rppt@kernel.org \
    --cc=surenb@google.com \
    --cc=vbabka@kernel.org \
    --cc=viro@zeniv.linux.org.uk \
    --cc=willy@infradead.org \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox

all inboxes | Powered by JetHome®