[2/3] block: create bio_try_merge_pc_page helper __bio_add_pc_page
diff mbox series

Message ID 20190703130036.4105-3-hch@lst.de
State New
Headers show
Series
  • [1/3] block: improve the gap check in __bio_add_pc_page
Related show

Commit Message

Christoph Hellwig July 3, 2019, 1 p.m. UTC
Passsthrough bio handling should be the same as normal bio handling,
except that we need to take hardware limitations into account.  Thus
use the common try_merge implementation after checking the hardware
limits.  This changes behavior in that we now also check segment
and dma boundary settings for same page merges, which is a little
more work but has no effect as those need to be larger than the
page size.

Signed-off-by: Christoph Hellwig <hch@lst.de>
---
 block/bio.c | 34 ++++++++++------------------------
 1 file changed, 10 insertions(+), 24 deletions(-)

Comments

Johannes Thumshirn July 3, 2019, 1:34 p.m. UTC | #1
On Wed, Jul 03, 2019 at 06:00:35AM -0700, Christoph Hellwig wrote:
[snip]
>  	phys_addr_t addr2 = page_to_phys(page) + offset + len - 1;
>  
>  	if ((addr1 | mask) != (addr2 | mask))
>  		return false;
> -
>  	if (bv->bv_len + len > queue_max_segment_size(q))
>  		return false;
> -
> -	return true;
> +	return __bio_try_merge_page(bio, page, len, offset, same_page);
>  }

That's a lot of spurious whitespace changes here.
Christoph Hellwig July 3, 2019, 2:34 p.m. UTC | #2
On Wed, Jul 03, 2019 at 03:34:55PM +0200, Johannes Thumshirn wrote:
> On Wed, Jul 03, 2019 at 06:00:35AM -0700, Christoph Hellwig wrote:
> [snip]
> >  	phys_addr_t addr2 = page_to_phys(page) + offset + len - 1;
> >  
> >  	if ((addr1 | mask) != (addr2 | mask))
> >  		return false;
> > -
> >  	if (bv->bv_len + len > queue_max_segment_size(q))
> >  		return false;
> > -
> > -	return true;
> > +	return __bio_try_merge_page(bio, page, len, offset, same_page);
> >  }
> 
> That's a lot of spurious whitespace changes here.

Really just an empty line going away outside the directly touched code.
I think it is more effective to boundle that here rather than having
an extra patch for that..
Johannes Thumshirn July 3, 2019, 2:40 p.m. UTC | #3
On Wed, Jul 03, 2019 at 04:34:59PM +0200, Christoph Hellwig wrote:
> Really just an empty line going away outside the directly touched code.
> I think it is more effective to boundle that here rather than having
> an extra patch for that..

I'm not a fan of stuff glued together, but admittedly that's pure bikeshedding
here.

Patch
diff mbox series

diff --git a/block/bio.c b/block/bio.c
index 6be22b8477ce..1db626f99bcb 100644
--- a/block/bio.c
+++ b/block/bio.c
@@ -645,25 +645,20 @@  static inline bool page_is_mergeable(const struct bio_vec *bv,
 	return true;
 }
 
-/*
- * Check if the @page can be added to the current segment(@bv), and make
- * sure to call it only if page_is_mergeable(@bv, @page) is true
- */
-static bool can_add_page_to_seg(struct request_queue *q,
-		struct bio_vec *bv, struct page *page, unsigned len,
-		unsigned offset)
+static bool bio_try_merge_pc_page(struct request_queue *q, struct bio *bio,
+		struct page *page, unsigned len, unsigned offset,
+		bool *same_page)
 {
+	struct bio_vec *bv = &bio->bi_io_vec[bio->bi_vcnt - 1];
 	unsigned long mask = queue_segment_boundary(q);
 	phys_addr_t addr1 = page_to_phys(bv->bv_page) + bv->bv_offset;
 	phys_addr_t addr2 = page_to_phys(page) + offset + len - 1;
 
 	if ((addr1 | mask) != (addr2 | mask))
 		return false;
-
 	if (bv->bv_len + len > queue_max_segment_size(q))
 		return false;
-
-	return true;
+	return __bio_try_merge_page(bio, page, len, offset, same_page);
 }
 
 /**
@@ -699,26 +694,18 @@  static int __bio_add_pc_page(struct request_queue *q, struct bio *bio,
 		return 0;
 
 	if (bio->bi_vcnt > 0) {
-		bvec = &bio->bi_io_vec[bio->bi_vcnt - 1];
-
-		if (page == bvec->bv_page &&
-		    offset == bvec->bv_offset + bvec->bv_len) {
-			if (put_same_page)
+		if (bio_try_merge_pc_page(q, bio, page, len, offset,
+				&same_page)) {
+			if (put_same_page && same_page)
 				put_page(page);
-			bvec->bv_len += len;
-			goto done;
-		}
-
-		if (page_is_mergeable(bvec, page, len, offset, &same_page) &&
-		    can_add_page_to_seg(q, bvec, page, len, offset)) {
-			bvec->bv_len += len;
-			goto done;
+			return len;
 		}
 
 		/*
 		 * If the queue doesn't support SG gaps and adding this segment
 		 * would create a gap, disallow it.
 		 */
+		bvec = &bio->bi_io_vec[bio->bi_vcnt - 1];
 		if (bvec_gap_to_prev(q, bvec, offset))
 			return 0;
 	}
@@ -734,7 +721,6 @@  static int __bio_add_pc_page(struct request_queue *q, struct bio *bio,
 	bvec->bv_len = len;
 	bvec->bv_offset = offset;
 	bio->bi_vcnt++;
- done:
 	bio->bi_iter.bi_size += len;
 	return len;
 }