[PATCH v4 Repost 1/2] block: factor out vector mergeable decision to a, helper function

[PATCH v4 Repost 1/2] block: factor out vector mergeable decision to a, helper function

[Tomas Henzl]

From: Jan Vesely <jvesely@redhat.com>

Export the function so it can be used to predict segment counts
without calling the recalc function. This will be used in the next
patch.

Signed-off-by: Jan Vesely <jvesely@redhat.com>
Signed-off-by: Tomas Henzl <thenzl@redhat.com>
---
 block/blk-merge.c   | 52 +++++++++++++++++++++++++++++++---------------------
 include/linux/bio.h |  3 +++
 2 files changed, 34 insertions(+), 21 deletions(-)

diff --git a/block/blk-merge.c b/block/blk-merge.c
index 5f24482..f1ef657 100644
--- a/block/blk-merge.c
+++ b/block/blk-merge.c
@@ -9,11 +9,39 @@
 
 #include "blk.h"
 
+bool bvec_mergeable(struct request_queue *q, struct bio_vec *lastbv,
+		    struct bio_vec *newbv, unsigned int seg_size)
+{
+	unsigned long limit = queue_bounce_pfn(q);
+
+	if (!blk_queue_cluster(q))
+		return false;
+
+	/*
+	 * the trick here is to make sure that a high page is
+	 * never considered part of another segment, since that
+	 * might change with the bounce page.
+	 */
+	if ((page_to_pfn(lastbv->bv_page) > limit)
+	    || (page_to_pfn(newbv->bv_page) > limit))
+		return false;
+
+	if (seg_size + newbv->bv_len > queue_max_segment_size(q))
+		return false;
+
+	if (!BIOVEC_PHYS_MERGEABLE(lastbv, newbv))
+		return false;
+	if (!BIOVEC_SEG_BOUNDARY(q, lastbv, newbv))
+		return false;
+	return true;
+}
+
+
 static unsigned int __blk_recalc_rq_segments(struct request_queue *q,
 					     struct bio *bio)
 {
 	struct bio_vec *bv, *bvprv = NULL;
-	int cluster, i, high, highprv = 1;
+	int i;
 	unsigned int seg_size, nr_phys_segs;
 	struct bio *fbio, *bbio;
 
@@ -21,33 +49,16 @@ static unsigned int __blk_recalc_rq_segments(struct request_queue *q,
 		return 0;
 
 	fbio = bio;
-	cluster = blk_queue_cluster(q);
 	seg_size = 0;
 	nr_phys_segs = 0;
 	for_each_bio(bio) {
 		bio_for_each_segment(bv, bio, i) {
-			/*
-			 * the trick here is making sure that a high page is
-			 * never considered part of another segment, since that
-			 * might change with the bounce page.
-			 */
-			high = page_to_pfn(bv->bv_page) > queue_bounce_pfn(q);
-			if (high || highprv)
-				goto new_segment;
-			if (cluster) {
-				if (seg_size + bv->bv_len
-				    > queue_max_segment_size(q))
-					goto new_segment;
-				if (!BIOVEC_PHYS_MERGEABLE(bvprv, bv))
-					goto new_segment;
-				if (!BIOVEC_SEG_BOUNDARY(q, bvprv, bv))
-					goto new_segment;
-
+			if (bvprv && bvec_mergeable(q, bvprv, bv, seg_size)) {
 				seg_size += bv->bv_len;
 				bvprv = bv;
 				continue;
 			}
-new_segment:
+			/* new segment */
 			if (nr_phys_segs == 1 && seg_size >
 			    fbio->bi_seg_front_size)
 				fbio->bi_seg_front_size = seg_size;
@@ -55,7 +66,6 @@ new_segment:
 			nr_phys_segs++;
 			bvprv = bv;
 			seg_size = bv->bv_len;
-			highprv = high;
 		}
 		bbio = bio;
 	}
diff --git a/include/linux/bio.h b/include/linux/bio.h
index ec48bac..929ac53 100644
--- a/include/linux/bio.h
+++ b/include/linux/bio.h
@@ -307,6 +307,9 @@ extern struct bio_vec *bvec_alloc(gfp_t, int, unsigned long *, mempool_t *);
 extern void bvec_free(mempool_t *, struct bio_vec *, unsigned int);
 extern unsigned int bvec_nr_vecs(unsigned short idx);
 
+extern bool bvec_mergeable(struct request_queue *q, struct bio_vec *lastbv,
+			   struct bio_vec *newbv, unsigned int seg_size);
+
 #ifdef CONFIG_BLK_CGROUP
 int bio_associate_current(struct bio *bio);
 void bio_disassociate_task(struct bio *bio);
-- 
1.8.3.1

[PATCH v4 Repost 2/2] block: modify __bio_add_page check to accept pages, that don't start a new segment

[Tomas Henzl]

From: Jan Vesely <jvesely@redhat.com>

The original behavior was to refuse all pages after the maximum number of
segments has been reached. However, some drivers (like st) craft their buffers
to potentially require exactly max segments and multiple pages in the last
segment. This patch modifies the check to allow pages that can be merged into
the last segment.

Fixes EBUSY failures when using large tape block size in high
memory fragmentation condition. This regression was introduced by commit
46081b166415acb66d4b3150ecefcd9460bb48a1
st: Increase success probability in driver buffer allocation

Signed-off-by: Jan Vesely <jvesely@redhat.com>
Signed-off-by: Tomas Henzl <thenzl@redhat.com>
---
 fs/bio.c | 30 +++++++++++++++++++-----------
 1 file changed, 19 insertions(+), 11 deletions(-)

diff --git a/fs/bio.c b/fs/bio.c
index ea5035d..419bdd6 100644
--- a/fs/bio.c
+++ b/fs/bio.c
@@ -603,7 +603,6 @@ static int __bio_add_page(struct request_queue *q, struct bio *bio, struct page
 			  *page, unsigned int len, unsigned int offset,
 			  unsigned short max_sectors)
 {
-	int retried_segments = 0;
 	struct bio_vec *bvec;
 
 	/*
@@ -654,18 +653,12 @@ static int __bio_add_page(struct request_queue *q, struct bio *bio, struct page
 		return 0;
 
 	/*
-	 * we might lose a segment or two here, but rather that than
-	 * make this too complex.
+	 * The first part of the segment count check,
+	 * reduce segment count if possible
 	 */
-
-	while (bio->bi_phys_segments >= queue_max_segments(q)) {
-
-		if (retried_segments)
-			return 0;
-
-		retried_segments = 1;
+	if (bio->bi_phys_segments >= queue_max_segments(q))
 		blk_recount_segments(q, bio);
-	}
+
 
 	/*
 	 * setup the new entry, we might clear it again later if we
@@ -677,6 +670,21 @@ static int __bio_add_page(struct request_queue *q, struct bio *bio, struct page
 	bvec->bv_offset = offset;
 
 	/*
+	 * the other part of the segment count check, allow mergeable pages.
+	 * BIO_SEG_VALID flag is cleared below
+	 */
+	if ((bio->bi_phys_segments > queue_max_segments(q)) ||
+	    ((bio->bi_phys_segments == queue_max_segments(q)) &&
+	     !bvec_mergeable(q, __BVEC_END(bio), bvec,
+			     bio->bi_seg_back_size))) {
+			bvec->bv_page = NULL;
+			bvec->bv_len = 0;
+			bvec->bv_offset = 0;
+			return 0;
+	}
+
+
+	/*
 	 * if queue has other restrictions (eg varying max sector size
 	 * depending on offset), it can specify a merge_bvec_fn in the
 	 * queue to get further control
-- 
1.8.3.1