linux-kernel - [PATCH v3 03/11] block: allow __blk_queue_bounce() to handle bios larger than BIO_MAX

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Message-Id: <1430980461-5235-4-git-send-email-mlin@kernel.org>
Date:	Wed,  6 May 2015 23:34:13 -0700
From:	Ming Lin <mlin@...nel.org>
To:	linux-kernel@...r.kernel.org
Cc:	Christoph Hellwig <hch@....de>, Jens Axboe <axboe@...nel.dk>,
	Kent Overstreet <kent.overstreet@...il.com>,
	Dongsu Park <dpark@...teo.net>, Ming Lin <mlin@...nel.org>,
	Christoph Hellwig <hch@...radead.org>
Subject: [PATCH v3 03/11] block: allow __blk_queue_bounce() to handle bios larger than BIO_MAX_PAGES

From: Kent Overstreet <kent.overstreet@...il.com>

Allow __blk_queue_bounce() to handle bios with more than BIO_MAX_PAGES
segments. Doing that, it becomes possible to simplify the block layer
in the kernel.

The issue is that any code that clones the bio and must clone the biovec
(i.e. it can't use bio_clone_fast()) won't be able to allocate a bio with
more than BIO_MAX_PAGES - bio_alloc_bioset() always fails in that case.

Fortunately, it's easy to make __blk_queue_bounce() just process part of
the bio if necessary, using bi_remaining to count the splits and punting
the rest back to generic_make_request().

Cc: Christoph Hellwig <hch@...radead.org>
Cc: Jens Axboe <axboe@...nel.dk>
Signed-off-by: Kent Overstreet <kent.overstreet@...il.com>
[dpark: add more description in commit message]
Signed-off-by: Dongsu Park <dpark@...teo.net>
Signed-off-by: Ming Lin <mlin@...nel.org>
---
 block/bounce.c | 60 ++++++++++++++++++++++++++++++++++++++++++++++++++--------
 1 file changed, 52 insertions(+), 8 deletions(-)

diff --git a/block/bounce.c b/block/bounce.c
index ab21ba2..689ea89 100644
--- a/block/bounce.c
+++ b/block/bounce.c
@@ -196,6 +196,43 @@ static int must_snapshot_stable_pages(struct request_queue *q, struct bio *bio)
 }
 #endif /* CONFIG_NEED_BOUNCE_POOL */
 
+static struct bio *bio_clone_segments(struct bio *bio_src, gfp_t gfp_mask,
+				      struct bio_set *bs, unsigned nsegs)
+{
+	struct bvec_iter iter;
+	struct bio_vec bv;
+	struct bio *bio;
+
+	bio = bio_alloc_bioset(gfp_mask, nsegs, bs);
+	if (!bio)
+		return NULL;
+
+	bio->bi_bdev		= bio_src->bi_bdev;
+	bio->bi_rw		= bio_src->bi_rw;
+	bio->bi_iter.bi_sector	= bio_src->bi_iter.bi_sector;
+
+	bio_for_each_segment(bv, bio_src, iter) {
+		bio->bi_io_vec[bio->bi_vcnt++] = bv;
+		bio->bi_iter.bi_size += bv.bv_len;
+		if (!--nsegs)
+			break;
+	}
+
+	if (bio_integrity(bio_src)) {
+		int ret;
+
+		ret = bio_integrity_clone(bio, bio_src, gfp_mask);
+		if (ret < 0) {
+			bio_put(bio);
+			return NULL;
+		}
+	}
+
+	bio_src->bi_iter = iter;
+
+	return bio;
+}
+
 static void __blk_queue_bounce(struct request_queue *q, struct bio **bio_orig,
 			       mempool_t *pool, int force)
 {
@@ -203,17 +240,24 @@ static void __blk_queue_bounce(struct request_queue *q, struct bio **bio_orig,
 	int rw = bio_data_dir(*bio_orig);
 	struct bio_vec *to, from;
 	struct bvec_iter iter;
-	unsigned i;
+	int i, nsegs = 0, bounce = force;
 
-	if (force)
-		goto bounce;
-	bio_for_each_segment(from, *bio_orig, iter)
+	bio_for_each_segment(from, *bio_orig, iter) {
+		nsegs++;
 		if (page_to_pfn(from.bv_page) > queue_bounce_pfn(q))
-			goto bounce;
+			bounce = 1;
+	}
+
+	if (!bounce)
+		return;
 
-	return;
-bounce:
-	bio = bio_clone_bioset(*bio_orig, GFP_NOIO, fs_bio_set);
+	bio = bio_clone_segments(*bio_orig, GFP_NOIO, fs_bio_set,
+				 min(nsegs, BIO_MAX_PAGES));
+
+	if ((*bio_orig)->bi_iter.bi_size) {
+		atomic_inc(&(*bio_orig)->bi_remaining);
+		generic_make_request(*bio_orig);
+	}
 
 	bio_for_each_segment_all(to, bio, i) {
 		struct page *page = to->bv_page;
-- 
1.9.1

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