dbb1ed6d87
reproducer: https://www.spinics.net/lists/linux-block/msg28507.html ubuntu bugreport: https://bugs.launchpad.net/ubuntu/+source/linux/+bug/1796542 Signed-off-by: Thomas Lamprecht <t.lamprecht@proxmox.com>
99 lines
3.9 KiB
Diff
99 lines
3.9 KiB
Diff
From 0000000000000000000000000000000000000000 Mon Sep 17 00:00:00 2001
|
|
From: Martin Wilck <mwilck@suse.com>
|
|
Date: Tue, 9 Oct 2018 17:04:42 +0100
|
|
Subject: [PATCH] block: bio_iov_iter_get_pages: pin more pages for
|
|
multi-segment IOs
|
|
|
|
Buglink: https://bugs.launchpad.net/bugs/1796542
|
|
|
|
bio_iov_iter_get_pages() currently only adds pages for the next non-zero
|
|
segment from the iov_iter to the bio. That's suboptimal for callers,
|
|
which typically try to pin as many pages as fit into the bio. This patch
|
|
converts the current bio_iov_iter_get_pages() into a static helper, and
|
|
introduces a new helper that allocates as many pages as
|
|
|
|
1) fit into the bio,
|
|
2) are present in the iov_iter,
|
|
3) and can be pinned by MM.
|
|
|
|
Error is returned only if zero pages could be pinned. Because of 3), a
|
|
zero return value doesn't necessarily mean all pages have been pinned.
|
|
Callers that have to pin every page in the iov_iter must still call this
|
|
function in a loop (this is currently the case).
|
|
|
|
This change matters most for __blkdev_direct_IO_simple(), which calls
|
|
bio_iov_iter_get_pages() only once. If it obtains less pages than
|
|
requested, it returns a "short write" or "short read", and
|
|
__generic_file_write_iter() falls back to buffered writes, which may
|
|
lead to data corruption.
|
|
|
|
Fixes: 72ecad22d9f1 ("block: support a full bio worth of IO for simplified bdev direct-io")
|
|
Reviewed-by: Christoph Hellwig <hch@lst.de>
|
|
Signed-off-by: Martin Wilck <mwilck@suse.com>
|
|
Signed-off-by: Jens Axboe <axboe@kernel.dk>
|
|
(cherry picked from commit 17d51b10d7773e4618bcac64648f30f12d4078fb)
|
|
Signed-off-by: Colin Ian King <colin.king@canonical.com>
|
|
Signed-off-by: Thomas Lamprecht <t.lamprecht@proxmox.com>
|
|
---
|
|
block/bio.c | 35 ++++++++++++++++++++++++++++++++---
|
|
1 file changed, 32 insertions(+), 3 deletions(-)
|
|
|
|
diff --git a/block/bio.c b/block/bio.c
|
|
index d76372a6a5fe..415c65b9c590 100644
|
|
--- a/block/bio.c
|
|
+++ b/block/bio.c
|
|
@@ -902,14 +902,16 @@ int bio_add_page(struct bio *bio, struct page *page,
|
|
EXPORT_SYMBOL(bio_add_page);
|
|
|
|
/**
|
|
- * bio_iov_iter_get_pages - pin user or kernel pages and add them to a bio
|
|
+ * __bio_iov_iter_get_pages - pin user or kernel pages and add them to a bio
|
|
* @bio: bio to add pages to
|
|
* @iter: iov iterator describing the region to be mapped
|
|
*
|
|
- * Pins as many pages from *iter and appends them to @bio's bvec array. The
|
|
+ * Pins pages from *iter and appends them to @bio's bvec array. The
|
|
* pages will have to be released using put_page() when done.
|
|
+ * For multi-segment *iter, this function only adds pages from the
|
|
+ * the next non-empty segment of the iov iterator.
|
|
*/
|
|
-int bio_iov_iter_get_pages(struct bio *bio, struct iov_iter *iter)
|
|
+static int __bio_iov_iter_get_pages(struct bio *bio, struct iov_iter *iter)
|
|
{
|
|
unsigned short nr_pages = bio->bi_max_vecs - bio->bi_vcnt, idx;
|
|
struct bio_vec *bv = bio->bi_io_vec + bio->bi_vcnt;
|
|
@@ -946,6 +948,33 @@ int bio_iov_iter_get_pages(struct bio *bio, struct iov_iter *iter)
|
|
iov_iter_advance(iter, size);
|
|
return 0;
|
|
}
|
|
+
|
|
+/**
|
|
+ * bio_iov_iter_get_pages - pin user or kernel pages and add them to a bio
|
|
+ * @bio: bio to add pages to
|
|
+ * @iter: iov iterator describing the region to be mapped
|
|
+ *
|
|
+ * Pins pages from *iter and appends them to @bio's bvec array. The
|
|
+ * pages will have to be released using put_page() when done.
|
|
+ * 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 MM encounters an error pinning the requested pages, it stops.
|
|
+ * Error is returned only if 0 pages could be pinned.
|
|
+ */
|
|
+int bio_iov_iter_get_pages(struct bio *bio, struct iov_iter *iter)
|
|
+{
|
|
+ unsigned short orig_vcnt = bio->bi_vcnt;
|
|
+
|
|
+ do {
|
|
+ int ret = __bio_iov_iter_get_pages(bio, iter);
|
|
+
|
|
+ if (unlikely(ret))
|
|
+ return bio->bi_vcnt > orig_vcnt ? 0 : ret;
|
|
+
|
|
+ } while (iov_iter_count(iter) && !bio_full(bio));
|
|
+
|
|
+ return 0;
|
|
+}
|
|
EXPORT_SYMBOL_GPL(bio_iov_iter_get_pages);
|
|
|
|
static void submit_bio_wait_endio(struct bio *bio)
|