linux-kernel - [PATCH V13 15/19] block: enable multipage bvecs

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: <20190111110127.21664-16-ming.lei@redhat.com>
Date:   Fri, 11 Jan 2019 19:01:23 +0800
From:   Ming Lei <ming.lei@...hat.com>
To:     Jens Axboe <axboe@...nel.dk>
Cc:     linux-block@...r.kernel.org, linux-kernel@...r.kernel.org,
        linux-mm@...ck.org, Theodore Ts'o <tytso@....edu>,
        Omar Sandoval <osandov@...com>,
        Sagi Grimberg <sagi@...mberg.me>,
        Dave Chinner <dchinner@...hat.com>,
        Kent Overstreet <kent.overstreet@...il.com>,
        Mike Snitzer <snitzer@...hat.com>, dm-devel@...hat.com,
        Alexander Viro <viro@...iv.linux.org.uk>,
        linux-fsdevel@...r.kernel.org, linux-raid@...r.kernel.org,
        David Sterba <dsterba@...e.com>, linux-btrfs@...r.kernel.org,
        "Darrick J . Wong" <darrick.wong@...cle.com>,
        linux-xfs@...r.kernel.org, Gao Xiang <gaoxiang25@...wei.com>,
        Christoph Hellwig <hch@....de>, linux-ext4@...r.kernel.org,
        Coly Li <colyli@...e.de>, linux-bcache@...r.kernel.org,
        Boaz Harrosh <ooo@...ctrozaur.com>,
        Bob Peterson <rpeterso@...hat.com>, cluster-devel@...hat.com,
        Ming Lei <ming.lei@...hat.com>
Subject: [PATCH V13 15/19] block: enable multipage bvecs

This patch pulls the trigger for multi-page bvecs.

Reviewed-by: Omar Sandoval <osandov@...com>
Signed-off-by: Ming Lei <ming.lei@...hat.com>
---
 block/bio.c         | 22 +++++++++++++++-------
 fs/iomap.c          |  4 ++--
 fs/xfs/xfs_aops.c   |  4 ++--
 include/linux/bio.h |  2 +-
 4 files changed, 20 insertions(+), 12 deletions(-)

diff --git a/block/bio.c b/block/bio.c
index 968b12fea564..83a2dfa417ca 100644
--- a/block/bio.c
+++ b/block/bio.c
@@ -753,6 +753,8 @@ EXPORT_SYMBOL(bio_add_pc_page);
  * @page: page to add
  * @len: length of the data to add
  * @off: offset of the data in @page
+ * @same_page: if %true only merge if the new data is in the same physical
+ *		page as the last segment of the bio.
  *
  * Try to add the data at @page + @off to the last bvec of @bio.  This is a
  * a useful optimisation for file systems with a block size smaller than the
@@ -761,19 +763,25 @@ EXPORT_SYMBOL(bio_add_pc_page);
  * Return %true on success or %false on failure.
  */
 bool __bio_try_merge_page(struct bio *bio, struct page *page,
-		unsigned int len, unsigned int off)
+		unsigned int len, unsigned int off, bool same_page)
 {
 	if (WARN_ON_ONCE(bio_flagged(bio, BIO_CLONED)))
 		return false;
 
 	if (bio->bi_vcnt > 0) {
 		struct bio_vec *bv = &bio->bi_io_vec[bio->bi_vcnt - 1];
+		phys_addr_t vec_end_addr = page_to_phys(bv->bv_page) +
+			bv->bv_offset + bv->bv_len - 1;
+		phys_addr_t page_addr = page_to_phys(page);
 
-		if (page == bv->bv_page && off == bv->bv_offset + bv->bv_len) {
-			bv->bv_len += len;
-			bio->bi_iter.bi_size += len;
-			return true;
-		}
+		if (vec_end_addr + 1 != page_addr + off)
+			return false;
+		if (same_page && (vec_end_addr & PAGE_MASK) != page_addr)
+			return false;
+
+		bv->bv_len += len;
+		bio->bi_iter.bi_size += len;
+		return true;
 	}
 	return false;
 }
@@ -819,7 +827,7 @@ EXPORT_SYMBOL_GPL(__bio_add_page);
 int bio_add_page(struct bio *bio, struct page *page,
 		 unsigned int len, unsigned int offset)
 {
-	if (!__bio_try_merge_page(bio, page, len, offset)) {
+	if (!__bio_try_merge_page(bio, page, len, offset, false)) {
 		if (bio_full(bio))
 			return 0;
 		__bio_add_page(bio, page, len, offset);
diff --git a/fs/iomap.c b/fs/iomap.c
index af736acd9006..0c350e658b7f 100644
--- a/fs/iomap.c
+++ b/fs/iomap.c
@@ -318,7 +318,7 @@ iomap_readpage_actor(struct inode *inode, loff_t pos, loff_t length, void *data,
 	 */
 	sector = iomap_sector(iomap, pos);
 	if (ctx->bio && bio_end_sector(ctx->bio) == sector) {
-		if (__bio_try_merge_page(ctx->bio, page, plen, poff))
+		if (__bio_try_merge_page(ctx->bio, page, plen, poff, true))
 			goto done;
 		is_contig = true;
 	}
@@ -349,7 +349,7 @@ iomap_readpage_actor(struct inode *inode, loff_t pos, loff_t length, void *data,
 		ctx->bio->bi_end_io = iomap_read_end_io;
 	}
 
-	__bio_add_page(ctx->bio, page, plen, poff);
+	bio_add_page(ctx->bio, page, plen, poff);
 done:
 	/*
 	 * Move the caller beyond our range so that it keeps making progress.
diff --git a/fs/xfs/xfs_aops.c b/fs/xfs/xfs_aops.c
index 1f1829e506e8..b9fd44168f61 100644
--- a/fs/xfs/xfs_aops.c
+++ b/fs/xfs/xfs_aops.c
@@ -616,12 +616,12 @@ xfs_add_to_ioend(
 				bdev, sector);
 	}
 
-	if (!__bio_try_merge_page(wpc->ioend->io_bio, page, len, poff)) {
+	if (!__bio_try_merge_page(wpc->ioend->io_bio, page, len, poff, true)) {
 		if (iop)
 			atomic_inc(&iop->write_count);
 		if (bio_full(wpc->ioend->io_bio))
 			xfs_chain_bio(wpc->ioend, wbc, bdev, sector);
-		__bio_add_page(wpc->ioend->io_bio, page, len, poff);
+		bio_add_page(wpc->ioend->io_bio, page, len, poff);
 	}
 
 	wpc->ioend->io_size += len;
diff --git a/include/linux/bio.h b/include/linux/bio.h
index c5231e5c7e85..1ece9f30294b 100644
--- a/include/linux/bio.h
+++ b/include/linux/bio.h
@@ -441,7 +441,7 @@ extern int bio_add_page(struct bio *, struct page *, unsigned int,unsigned int);
 extern int bio_add_pc_page(struct request_queue *, struct bio *, struct page *,
 			   unsigned int, unsigned int);
 bool __bio_try_merge_page(struct bio *bio, struct page *page,
-		unsigned int len, unsigned int off);
+		unsigned int len, unsigned int off, bool same_page);
 void __bio_add_page(struct bio *bio, struct page *page,
 		unsigned int len, unsigned int off);
 int bio_iov_iter_get_pages(struct bio *bio, struct iov_iter *iter);
-- 
2.9.5