This patch pulls the trigger for multi-page bvecs.
Reviewed-by: Omar Sandoval <osan...@fb.com>
Signed-off-by: Ming Lei <ming....@redhat.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 e6a6f3d78afd..af288f6e8ab0 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
