Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 23.128.96.18 as permitted sender) client-ip=23.128.96.18;
From:   Gao Xiang <hsiangkao@aol.com>
To:     linux-erofs@lists.ozlabs.org, Chao Yu <yuchao0@huawei.com>,
        Chao Yu <chao@kernel.org>
Cc:     linux-kernel@vger.kernel.org, Gao Xiang <hsiangkao@redhat.com>,
        Martin DEVERA <devik@eaxlabs.cz>
Subject: [PATCH v2] erofs: fix bio->bi_max_vecs behavior change
Date:   Sat,  6 Mar 2021 12:04:38 +0800
Message-Id: <20210306040438.8084-1-hsiangkao@aol.com>
In-Reply-To: <20210306033109.28466-1-hsiangkao@aol.com>
References: <20210306033109.28466-1-hsiangkao@aol.com>
MIME-Version: 1.0
Content-Transfer-Encoding: 8bit
Content-Length: 3892
Precedence: bulk

From: Gao Xiang <hsiangkao@redhat.com>

Martin reported an issue that directory read could be hung on the
latest -rc kernel with some certain image. The root cause is that
commit baa2c7c97153 ("block: set .bi_max_vecs as actual allocated
vector number") changes .bi_max_vecs behavior. bio->bi_max_vecs
is set as actual allocated vector number rather than the requested
number now.

Let's avoid using .bi_max_vecs completely instead.

Reported-by: Martin DEVERA <devik@eaxlabs.cz>
Signed-off-by: Gao Xiang <hsiangkao@redhat.com>
---
change since v1:
 - since bio->bi_max_vecs doesn't record extent blocks anymore,
   introduce a remaining extent block to avoid extent excess.

 fs/erofs/data.c | 28 +++++++++++-----------------
 1 file changed, 11 insertions(+), 17 deletions(-)

diff --git a/fs/erofs/data.c b/fs/erofs/data.c
index f88851c5c250..1249e74b3bf0 100644
--- a/fs/erofs/data.c
+++ b/fs/erofs/data.c
@@ -129,6 +129,7 @@ static inline struct bio *erofs_read_raw_page(struct bio *bio,
 					      struct page *page,
 					      erofs_off_t *last_block,
 					      unsigned int nblocks,
+					      unsigned int *eblks,
 					      bool ra)
 {
 	struct inode *const inode = mapping->host;
@@ -145,8 +146,7 @@ static inline struct bio *erofs_read_raw_page(struct bio *bio,
 
 	/* note that for readpage case, bio also equals to NULL */
 	if (bio &&
-	    /* not continuous */
-	    *last_block + 1 != current_block) {
+	    (*last_block + 1 != current_block || !*eblks)) {
 submit_bio_retry:
 		submit_bio(bio);
 		bio = NULL;
@@ -216,7 +216,8 @@ static inline struct bio *erofs_read_raw_page(struct bio *bio,
 		if (nblocks > DIV_ROUND_UP(map.m_plen, PAGE_SIZE))
 			nblocks = DIV_ROUND_UP(map.m_plen, PAGE_SIZE);
 
-		bio = bio_alloc(GFP_NOIO, bio_max_segs(nblocks));
+		*eblks = bio_max_segs(nblocks);
+		bio = bio_alloc(GFP_NOIO, *eblks);
 
 		bio->bi_end_io = erofs_readendio;
 		bio_set_dev(bio, sb->s_bdev);
@@ -229,16 +230,8 @@ static inline struct bio *erofs_read_raw_page(struct bio *bio,
 	/* out of the extent or bio is full */
 	if (err < PAGE_SIZE)
 		goto submit_bio_retry;
-
+	--*eblks;
 	*last_block = current_block;
-
-	/* shift in advance in case of it followed by too many gaps */
-	if (bio->bi_iter.bi_size >= bio->bi_max_vecs * PAGE_SIZE) {
-		/* err should reassign to 0 after submitting */
-		err = 0;
-		goto submit_bio_out;
-	}
-
 	return bio;
 
 err_out:
@@ -252,7 +245,6 @@ static inline struct bio *erofs_read_raw_page(struct bio *bio,
 
 	/* if updated manually, continuous pages has a gap */
 	if (bio)
-submit_bio_out:
 		submit_bio(bio);
 	return err ? ERR_PTR(err) : NULL;
 }
@@ -264,23 +256,26 @@ static inline struct bio *erofs_read_raw_page(struct bio *bio,
 static int erofs_raw_access_readpage(struct file *file, struct page *page)
 {
 	erofs_off_t last_block;
+	unsigned int eblks;
 	struct bio *bio;
 
 	trace_erofs_readpage(page, true);
 
 	bio = erofs_read_raw_page(NULL, page->mapping,
-				  page, &last_block, 1, false);
+				  page, &last_block, 1, &eblks, false);
 
 	if (IS_ERR(bio))
 		return PTR_ERR(bio);
 
-	DBG_BUGON(bio);	/* since we have only one bio -- must be NULL */
+	if (bio)
+		submit_bio(bio);
 	return 0;
 }
 
 static void erofs_raw_access_readahead(struct readahead_control *rac)
 {
 	erofs_off_t last_block;
+	unsigned int eblks;
 	struct bio *bio = NULL;
 	struct page *page;
 
@@ -291,7 +286,7 @@ static void erofs_raw_access_readahead(struct readahead_control *rac)
 		prefetchw(&page->flags);
 
 		bio = erofs_read_raw_page(bio, rac->mapping, page, &last_block,
-				readahead_count(rac), true);
+				readahead_count(rac), &eblks, true);
 
 		/* all the page errors are ignored when readahead */
 		if (IS_ERR(bio)) {
@@ -305,7 +300,6 @@ static void erofs_raw_access_readahead(struct readahead_control *rac)
 		put_page(page);
 	}
 
-	/* the rare case (end in gaps) */
 	if (bio)
 		submit_bio(bio);
 }
-- 
2.20.1