[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <20100627145515.GE3970@redhat.com>
Date: Sun, 27 Jun 2010 10:55:15 -0400
From: Mike Snitzer <snitzer@...hat.com>
To: Christoph Hellwig <hch@....de>
Cc: axboe@...nel.dk, martin.petersen@...cle.com,
linux-kernel@...r.kernel.org, dm-devel@...hat.com,
James.Bottomley@...e.de, akpm@...ux-foundation.org
Subject: [PATCH 2/2 v2] block: defer the use of inline biovecs for discard
requests
Don't alloc discard bio with a biovec in blkdev_issue_discard. Doing so
means bio_has_data() will not be true until the SCSI layer adds the
payload to the discard request via blk_add_request_payload.
This patch avoids the need for the following VM accounting fix for
discards: http://lkml.org/lkml/2010/6/23/361
NOTE: Jens, you said you applied Tao Ma's fix but I cannot see it in
your linux-2.6-block's for-next or for-2.6.36... as such I didn't revert
it in this patch.
Signed-off-by: Mike Snitzer <snitzer@...hat.com>
---
block/blk-core.c | 2 ++
block/blk-lib.c | 2 +-
fs/bio.c | 25 +++++++++++++++++++++++--
include/linux/bio.h | 3 +++
4 files changed, 29 insertions(+), 3 deletions(-)
Index: linux-2.6-block/block/blk-core.c
===================================================================
--- linux-2.6-block.orig/block/blk-core.c
+++ linux-2.6-block/block/blk-core.c
@@ -1153,6 +1153,7 @@ void blk_add_request_payload(struct requ
{
struct bio *bio = rq->bio;
+ bio_enable_inline_vecs(bio);
bio->bi_io_vec->bv_page = page;
bio->bi_io_vec->bv_offset = 0;
bio->bi_io_vec->bv_len = len;
@@ -1187,6 +1188,7 @@ void blk_clear_request_payload(struct re
bio->bi_io_vec->bv_page = NULL;
bio->bi_io_vec->bv_len = 0;
+ bio_disable_inline_vecs(bio);
}
EXPORT_SYMBOL_GPL(blk_clear_request_payload);
Index: linux-2.6-block/block/blk-lib.c
===================================================================
--- linux-2.6-block.orig/block/blk-lib.c
+++ linux-2.6-block/block/blk-lib.c
@@ -54,7 +54,7 @@ int blkdev_issue_discard(struct block_de
unsigned int max_discard_sectors =
min(q->limits.max_discard_sectors, UINT_MAX >> 9);
- bio = bio_alloc(gfp_mask, 1);
+ bio = bio_alloc(gfp_mask, 0);
if (!bio) {
ret = -ENOMEM;
break;
Index: linux-2.6-block/fs/bio.c
===================================================================
--- linux-2.6-block.orig/fs/bio.c
+++ linux-2.6-block/fs/bio.c
@@ -261,6 +261,27 @@ void bio_init(struct bio *bio)
EXPORT_SYMBOL(bio_init);
/**
+ * bio_enable_inline_vecs - enable use of bio's inline iovecs
+ * @bio: bio that will use its inline iovecs
+ */
+void bio_enable_inline_vecs(struct bio *bio)
+{
+ bio->bi_flags |= BIO_POOL_NONE << BIO_POOL_OFFSET;
+ bio->bi_max_vecs = BIO_INLINE_VECS;
+ bio->bi_io_vec = bio->bi_inline_vecs;;
+}
+
+/**
+ * bio_disable_inline_vecs - disable use of bio's inline iovecs
+ * @bio: bio that will no longer use its inline iovecs
+ */
+void bio_disable_inline_vecs(struct bio *bio)
+{
+ bio->bi_max_vecs = 0;
+ bio->bi_io_vec = NULL;
+}
+
+/**
* bio_alloc_bioset - allocate a bio for I/O
* @gfp_mask: the GFP_ mask given to the slab allocator
* @nr_iovecs: number of iovecs to pre-allocate
@@ -293,8 +314,8 @@ struct bio *bio_alloc_bioset(gfp_t gfp_m
goto out_set;
if (nr_iovecs <= BIO_INLINE_VECS) {
- bvl = bio->bi_inline_vecs;
- nr_iovecs = BIO_INLINE_VECS;
+ bio_enable_inline_vecs(bio);
+ return bio;
} else {
bvl = bvec_alloc_bs(gfp_mask, nr_iovecs, &idx, bs);
if (unlikely(!bvl))
Index: linux-2.6-block/include/linux/bio.h
===================================================================
--- linux-2.6-block.orig/include/linux/bio.h
+++ linux-2.6-block/include/linux/bio.h
@@ -403,6 +403,9 @@ extern struct bio *bio_clone(struct bio
extern void bio_init(struct bio *);
+extern void bio_enable_inline_vecs(struct bio *);
+extern void bio_disable_inline_vecs(struct bio *);
+
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);
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/
Powered by blists - more mailing lists