path: root/block
diff options
authorLinus Torvalds <torvalds@linux-foundation.org>2019-03-23 10:25:12 -0700
committerLinus Torvalds <torvalds@linux-foundation.org>2019-03-23 10:25:12 -0700
commit1bdd3dbfff7a308643c7f9ef74e4a8ef3923e686 (patch)
treed909952844644eefba33baabb267ad49195973b5 /block
parent2335cbe648e7163e78b3f85cd61816271d1a4313 (diff)
parent399254aaf4892113c806816f7e64cf40c804d46d (diff)
Merge tag 'io_uring-20190323' of git://git.kernel.dk/linux-block
Pull io_uring fixes and improvements from Jens Axboe: "The first five in this series are heavily inspired by the work Al did on the aio side to fix the races there. The last two re-introduce a feature that was in io_uring before it got merged, but which I pulled since we didn't have a good way to have BVEC iters that already have a stable reference. These aren't necessarily related to block, it's just how io_uring pins fixed buffers" * tag 'io_uring-20190323' of git://git.kernel.dk/linux-block: block: add BIO_NO_PAGE_REF flag iov_iter: add ITER_BVEC_FLAG_NO_REF flag io_uring: mark me as the maintainer io_uring: retry bulk slab allocs as single allocs io_uring: fix poll races io_uring: fix fget/fput handling io_uring: add prepped flag io_uring: make io_read/write return an integer io_uring: use regular request ref counts
Diffstat (limited to 'block')
1 files changed, 24 insertions, 19 deletions
diff --git a/block/bio.c b/block/bio.c
index 71a78d9fb8b7..b64cedc7f87c 100644
--- a/block/bio.c
+++ b/block/bio.c
@@ -849,20 +849,14 @@ static int __bio_iov_bvec_add_pages(struct bio *bio, struct iov_iter *iter)
size = bio_add_page(bio, bv->bv_page, len,
bv->bv_offset + iter->iov_offset);
if (size == len) {
- struct page *page;
- int i;
+ if (!bio_flagged(bio, BIO_NO_PAGE_REF)) {
+ struct page *page;
+ int i;
+ mp_bvec_for_each_page(page, bv, i)
+ get_page(page);
+ }
- /*
- * For the normal O_DIRECT case, we could skip grabbing this
- * reference and then not have to put them again when IO
- * completes. But this breaks some in-kernel users, like
- * splicing to/from a loop device, where we release the pipe
- * pages unconditionally. If we can fix that case, we can
- * get rid of the get here and the need to call
- * bio_release_pages() at IO completion time.
- */
- mp_bvec_for_each_page(page, bv, i)
- get_page(page);
iov_iter_advance(iter, size);
return 0;
@@ -925,10 +919,12 @@ static int __bio_iov_iter_get_pages(struct bio *bio, struct iov_iter *iter)
* This takes either an iterator pointing to user memory, or one pointing to
* kernel pages (BVEC iterator). If we're adding user pages, we pin them and
* map them into the kernel. On IO completion, the caller should put those
- * pages. For now, when adding kernel pages, we still grab a reference to the
- * page. This isn't strictly needed for the common case, but some call paths
- * end up releasing pages from eg a pipe and we can't easily control these.
- * See comment in __bio_iov_bvec_add_pages().
+ * pages. If we're adding kernel pages, and the caller told us it's safe to
+ * do so, we just have to add the pages to the bio directly. We don't grab an
+ * extra reference to those pages (the user should already have that), and we
+ * don't put the page on IO completion. The caller needs to check if the bio is
+ * flagged BIO_NO_PAGE_REF on IO completion. If it isn't, then pages should be
+ * released.
* The function tries, but does not guarantee, to pin as many pages as
* fit into the bio, or are requested in *iter, whatever is smaller. If
@@ -940,6 +936,13 @@ int bio_iov_iter_get_pages(struct bio *bio, struct iov_iter *iter)
const bool is_bvec = iov_iter_is_bvec(iter);
unsigned short orig_vcnt = bio->bi_vcnt;
+ /*
+ * If this is a BVEC iter, then the pages are kernel pages. Don't
+ * release them on IO completion, if the caller asked us to.
+ */
+ if (is_bvec && iov_iter_bvec_no_ref(iter))
+ bio_set_flag(bio, BIO_NO_PAGE_REF);
do {
int ret;
@@ -1696,7 +1699,8 @@ static void bio_dirty_fn(struct work_struct *work)
next = bio->bi_private;
- bio_release_pages(bio);
+ if (!bio_flagged(bio, BIO_NO_PAGE_REF))
+ bio_release_pages(bio);
@@ -1713,7 +1717,8 @@ void bio_check_pages_dirty(struct bio *bio)
goto defer;
- bio_release_pages(bio);
+ if (!bio_flagged(bio, BIO_NO_PAGE_REF))
+ bio_release_pages(bio);