diff mbox

[v2,2/5] direct-io: don't dirty ITER_BVEC pages on read

Message ID f9b69250ba0598807d96857e9b736d57e6841ba3.1419044605.git.osandov@osandov.com (mailing list archive)
State New, archived
Headers show

Commit Message

Omar Sandoval Dec. 20, 2014, 3:18 a.m. UTC 
Reads through the iov_iter infrastructure for kernel pages shouldn't be
dirtied by the direct I/O code.

This is based on Dave Kleikamp's and Ming Lei's previously posted
patches.

Cc: Ming Lei <ming.lei@canonical.com>
Acked-by: Dave Kleikamp <dave.kleikamp@oracle.com>
Signed-off-by: Omar Sandoval <osandov@osandov.com>
---
 fs/direct-io.c | 8 +++++---
 1 file changed, 5 insertions(+), 3 deletions(-)

Comments

Al Viro Dec. 20, 2014, 6:01 a.m. UTC | #1 
On Fri, Dec 19, 2014 at 07:18:26PM -0800, Omar Sandoval wrote:
> Reads through the iov_iter infrastructure for kernel pages shouldn't be
> dirtied by the direct I/O code.
> 
> This is based on Dave Kleikamp's and Ming Lei's previously posted
> patches.

Umm...  

> +	dio->should_dirty = !iov_iter_is_bvec(iter);

	dio->should_dirty = iter_is_iovec(iter);

perhaps?
--
To unsubscribe from this list: send the line "unsubscribe linux-nfs" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Omar Sandoval Dec. 22, 2014, 7:12 a.m. UTC | #2 
On Sat, Dec 20, 2014 at 06:01:30AM +0000, Al Viro wrote:
> On Fri, Dec 19, 2014 at 07:18:26PM -0800, Omar Sandoval wrote:
> > Reads through the iov_iter infrastructure for kernel pages shouldn't be
> > dirtied by the direct I/O code.
> > 
> > This is based on Dave Kleikamp's and Ming Lei's previously posted
> > patches.
> 
> Umm...  
> 
> > +	dio->should_dirty = !iov_iter_is_bvec(iter);
> 
> 	dio->should_dirty = iter_is_iovec(iter);
> 
> perhaps?

Mm, yeah, I'll do that. That helper snuck in without me noticing it... I
see that we can't do iov_iter_get_pages on an ITER_KVEC, so a kvec
doesn't work for blockdev_direct_IO anyways, right?
diff mbox

Patch

diff --git a/fs/direct-io.c b/fs/direct-io.c
index e181b6b..c71387b 100644
--- a/fs/direct-io.c
+++ b/fs/direct-io.c
@@ -120,6 +120,7 @@  struct dio {
 	spinlock_t bio_lock;		/* protects BIO fields below */
 	int page_errors;		/* errno from get_user_pages() */
 	int is_async;			/* is IO async ? */
+	int should_dirty;		/* should we mark read pages dirty? */
 	bool defer_completion;		/* defer AIO completion to workqueue? */
 	int io_error;			/* IO error in completion path */
 	unsigned long refcount;		/* direct_io_worker() and bios */
@@ -392,7 +393,7 @@  static inline void dio_bio_submit(struct dio *dio, struct dio_submit *sdio)
 	dio->refcount++;
 	spin_unlock_irqrestore(&dio->bio_lock, flags);
 
-	if (dio->is_async && dio->rw == READ)
+	if (dio->is_async && dio->rw == READ && dio->should_dirty)
 		bio_set_pages_dirty(bio);
 
 	if (sdio->submit_io)
@@ -463,13 +464,13 @@  static int dio_bio_complete(struct dio *dio, struct bio *bio)
 	if (!uptodate)
 		dio->io_error = -EIO;
 
-	if (dio->is_async && dio->rw == READ) {
+	if (dio->is_async && dio->rw == READ && dio->should_dirty) {
 		bio_check_pages_dirty(bio);	/* transfers ownership */
 	} else {
 		bio_for_each_segment_all(bvec, bio, i) {
 			struct page *page = bvec->bv_page;
 
-			if (dio->rw == READ && !PageCompound(page))
+			if (dio->rw == READ && !PageCompound(page) && dio->should_dirty)
 				set_page_dirty_lock(page);
 			page_cache_release(page);
 		}
@@ -1177,6 +1178,7 @@  do_blockdev_direct_IO(int rw, struct kiocb *iocb, struct inode *inode,
 
 	dio->inode = inode;
 	dio->rw = rw;
+	dio->should_dirty = !iov_iter_is_bvec(iter);
 
 	/*
 	 * For AIO O_(D)SYNC writes we need to defer completions to a workqueue