Now block IO stack is basically ready for supporting multi-page bvec,
however it isn't enabled on passthrough IO.
One reason is that passthrough IO is dispatched to LLD directly and bio
split is bypassed, so the bio has to be built correctly for dispatch to
LLD from the beginning.
Implement multi-page support for passthrough IO by limitting each bvec
as block device's segment and applying all kinds of queue limit in
blk_add_pc_page(). Then we don't need to calculate segments any more for
passthrough IO any more, turns out code is simplified much.
Cc: Omar Sandoval <osandov@xxxxxx>
Cc: Christoph Hellwig <hch@xxxxxx>
Signed-off-by: Ming Lei <ming.lei@xxxxxxxxxx>
---
block/bio.c | 64 +++++++++++++++++++++++++++++++++----------------------------
1 file changed, 35 insertions(+), 29 deletions(-)
diff --git a/block/bio.c b/block/bio.c
index 95ec5e893265..ce15246f9a1f 100644
--- a/block/bio.c
+++ b/block/bio.c
@@ -665,6 +665,27 @@ page_is_mergeable(const struct bio_vec *bv, struct page *page,
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,
+ const struct bio_vec *bv, const struct page *page,
+ unsigned len, unsigned offset)
+{
+ 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;
+}
+
/**
* __bio_add_pc_page - attempt to add page to bio
* @q: the target queue
@@ -680,12 +701,13 @@ page_is_mergeable(const struct bio_vec *bv, struct page *page,
* so it is always possible to add a single page to an empty bio.
*
* This should only be used by REQ_PC bios.
+ *
+ * For REQ_PC bios, bvec is exactly same with segment of block device.
*/
int __bio_add_pc_page(struct request_queue *q, struct bio *bio, struct page
*page, unsigned int len, unsigned int offset,
bool put_same_page)
{
- int retried_segments = 0;
struct bio_vec *bvec;
/*
@@ -705,10 +727,12 @@ int __bio_add_pc_page(struct request_queue *q, struct bio *bio, struct page
if (bio->bi_vcnt > 0) {
struct bio_vec *prev = &bio->bi_io_vec[bio->bi_vcnt - 1];
+ /* segment size is always >= PAGE_SIZE */
if (page == prev->bv_page &&
offset == prev->bv_offset + prev->bv_len) {
if (put_same_page)
put_page(page);
+ bvec_merge:
prev->bv_len += len;
bio->bi_iter.bi_size += len;
goto done;
@@ -720,11 +744,18 @@ int __bio_add_pc_page(struct request_queue *q, struct bio *bio, struct page
*/
if (bvec_gap_to_prev(q, prev, offset))
return 0;
+
+ if (page_is_mergeable(prev, page, len, offset, false) &&
+ can_add_page_to_seg(q, prev, page, len, offset))
+ goto bvec_merge;
}
if (bio_full(bio))
return 0;
+ if (bio->bi_phys_segments >= queue_max_segments(q))
+ return 0;
+
/*
* setup the new entry, we might clear it again later if we
* cannot add the page
@@ -734,38 +765,13 @@ int __bio_add_pc_page(struct request_queue *q, struct bio *bio, struct page
bvec->bv_len = len;
bvec->bv_offset = offset;
bio->bi_vcnt++;
- bio->bi_phys_segments++;
bio->bi_iter.bi_size += len;
- /*
- * Perform a recount if the number of segments is greater
- * than queue_max_segments(q).
- */
-
- while (bio->bi_phys_segments > queue_max_segments(q)) {
-
- if (retried_segments)
- goto failed;
-
- retried_segments = 1;
- blk_recount_segments(q, bio);
- }
-
- /* If we may be able to merge these biovecs, force a recount */
- if (bio->bi_vcnt > 1 && biovec_phys_mergeable(q, bvec - 1, bvec))
- bio_clear_flag(bio, BIO_SEG_VALID);
-
done:
+ bio->bi_phys_segments = bio->bi_vcnt;
+ if (!bio_flagged(bio, BIO_SEG_VALID))
+ bio_set_flag(bio, BIO_SEG_VALID);
return len;
-
- failed:
- bvec->bv_page = NULL;
- bvec->bv_len = 0;
- bvec->bv_offset = 0;
- bio->bi_vcnt--;
- bio->bi_iter.bi_size -= len;
- blk_recount_segments(q, bio);
- return 0;
}
EXPORT_SYMBOL(__bio_add_pc_page);
--
2.9.5
