mirror of https://lore.kernel.org/lkml/
 help / color / mirror / Atom feed
From: Mike Snitzer <snitzer@redhat.com>
To: Christoph Hellwig <hch@lst.de>
Cc: axboe@kernel.dk, martin.petersen@oracle.com,
	linux-kernel@vger.kernel.org, dm-devel@redhat.com,
	James.Bottomley@suse.de, akpm@linux-foundation.org
Subject: [PATCH 2/2 v2] block: defer the use of inline biovecs for discard requests
Date: Sun, 27 Jun 2010 10:55:15 -0400	[thread overview]
Message-ID: <20100627145515.GE3970@redhat.com> (raw)
In-Reply-To: <1277582211-10725-2-git-send-email-snitzer@redhat.com>

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@redhat.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);

  parent reply	other threads:[~2010-06-27 14:55 UTC|newest]

Thread overview: 57+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2010-06-18 14:59 [PATCH, RFC] block: don't allocate a payload for discard request Christoph Hellwig
2010-06-19  4:25 ` Mike Snitzer
2010-06-22 18:00   ` Mike Snitzer
2010-06-26 19:56     ` [PATCH 1/2] block: fix leaks associated with discard request payload Mike Snitzer
2010-06-27  8:49       ` FUJITA Tomonori
2010-06-27  9:26         ` Christoph Hellwig
2010-06-27 10:01           ` FUJITA Tomonori
2010-06-27 10:35             ` FUJITA Tomonori
2010-06-27 11:07               ` Christoph Hellwig
2010-06-27 12:32                 ` FUJITA Tomonori
2010-06-27 14:16                   ` Mike Snitzer
2010-06-27 15:35                     ` Christoph Hellwig
2010-06-27 16:23                       ` FUJITA Tomonori
2010-06-27 15:33                   ` Christoph Hellwig
2010-06-28  7:57                   ` Christoph Hellwig
2010-06-28  8:14                     ` FUJITA Tomonori
2010-06-28  8:18                       ` Jens Axboe
2010-06-28  8:45                         ` FUJITA Tomonori
2010-06-28 15:25                       ` Christoph Hellwig
2010-06-30 11:55                         ` FUJITA Tomonori
2010-07-01  4:21                           ` FUJITA Tomonori
2010-06-27  9:38       ` Christoph Hellwig
2010-06-27 15:29       ` James Bottomley
2010-06-28 17:16         ` Martin K. Petersen
2010-06-29  8:00           ` Boaz Harrosh
2010-06-29 22:28         ` [dm-devel] " Mikulas Patocka
2010-06-29 23:03           ` James Bottomley
2010-06-29 23:51             ` Mike Snitzer
2010-06-30  0:11             ` [dm-devel] " Mikulas Patocka
2010-06-30 14:22               ` James Bottomley
2010-06-30 15:36                 ` Mike Snitzer
2010-06-30 16:26                   ` James Bottomley
2010-07-01 12:28                 ` [dm-devel] " Mikulas Patocka
2010-07-01 12:46                   ` Mike Snitzer
2010-07-01 14:03                     ` Mikulas Patocka
2010-07-01 12:49                   ` [dm-devel] " Alasdair G Kergon
2010-06-30  8:32         ` Boaz Harrosh
2010-06-30  8:42           ` Christoph Hellwig
2010-06-30 10:25             ` Boaz Harrosh
2010-06-30 10:41               ` Christoph Hellwig
2010-06-30 10:57                 ` Boaz Harrosh
2010-06-30 12:18                   ` Mike Snitzer
2010-06-26 19:56     ` [PATCH 2/2] block: defer the use of inline biovecs for discard requests Mike Snitzer
2010-06-27  9:39       ` Christoph Hellwig
2010-06-27 14:00         ` Mike Snitzer
2010-06-27 14:55       ` Mike Snitzer [this message]
2010-06-27 15:33         ` [PATCH 2/2 v2] " Christoph Hellwig
2010-06-28 10:33       ` [PATCH 2/2] " FUJITA Tomonori
2010-06-28 12:29         ` Mike Snitzer
2010-06-28 15:15           ` FUJITA Tomonori
2010-06-28 15:31             ` Mike Snitzer
2010-06-28 12:34       ` Jens Axboe
2010-06-28 12:37         ` Mike Snitzer
2010-06-28 12:41           ` Jens Axboe
2010-06-28 12:44             ` Christoph Hellwig
2010-06-28 12:49               ` Jens Axboe
2010-06-28 12:45             ` Mike Snitzer

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20100627145515.GE3970@redhat.com \
    --to=snitzer@redhat.com \
    --cc=James.Bottomley@suse.de \
    --cc=akpm@linux-foundation.org \
    --cc=axboe@kernel.dk \
    --cc=dm-devel@redhat.com \
    --cc=hch@lst.de \
    --cc=linux-kernel@vger.kernel.org \
    --cc=martin.petersen@oracle.com \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox

Powered by JetHome