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

From: Omar Sandoval
Date: Fri Dec 19 2014 - 22:18:56 EST


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@xxxxxxxxxxxxx>
Acked-by: Dave Kleikamp <dave.kleikamp@xxxxxxxxxx>
Signed-off-by: Omar Sandoval <osandov@xxxxxxxxxxx>
---
fs/direct-io.c | 8 +++++---
1 file changed, 5 insertions(+), 3 deletions(-)

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
--
2.2.1

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/