mirror of https://lore.kernel.org/lkml/
 help / color / mirror / Atom feed
From: Dmitry Monakhov <dmonakhov@openvz.org>
To: linux-kernel@vger.kernel.org
Cc: jens.axboe@oracle.com, hch@infradead.org, mkp@mkp.net,
	Dmitry Monakhov <dmonakhov@openvz.org>
Subject: [PATCH 4/5] blkdev: add discard payload flag
Date: Wed, 24 Mar 2010 20:21:20 +0300	[thread overview]
Message-ID: <1269451281-4944-5-git-send-email-dmonakhov@openvz.org> (raw)
In-Reply-To: <1269451281-4944-4-git-send-email-dmonakhov@openvz.org>

Not all implementations require discard bio to be filled with one-sector
sized payload. Let's allocate payload only when necessary.

Signed-off-by: Dmitry Monakhov <dmonakhov@openvz.org>
---
 block/blk-lib.c        |   24 +++++++++++++-----------
 drivers/scsi/sd.c      |    1 +
 include/linux/blkdev.h |    5 ++++-
 3 files changed, 18 insertions(+), 12 deletions(-)

diff --git a/block/blk-lib.c b/block/blk-lib.c
index 67b641e..321d150 100644
--- a/block/blk-lib.c
+++ b/block/blk-lib.c
@@ -184,17 +184,19 @@ int blkdev_issue_discard(struct block_device *bdev, sector_t sector,
 		if (flags & BLKDEV_IFL_BARRIER)
 			bio->bi_private = &wait;
 
-		/*
-		 * Add a zeroed one-sector payload as that's what
-		 * our current implementations need.  If we'll ever need
-		 * more the interface will need revisiting.
-		 */
-		page = alloc_page(gfp_mask | __GFP_ZERO);
-		if (!page)
-			goto out_free_bio;
-		if (bio_add_pc_page(q, bio, page, sector_size, 0) < sector_size)
-			goto out_free_page;
-
+		if (blk_queue_discard_mem(q)) {
+			/*
+			 * Add a zeroed one-sector payload as that's what
+			 * our current implementations need.  If we'll ever
+			 * need more the interface will need revisiting.
+			 */
+			page = alloc_page(gfp_mask | __GFP_ZERO);
+			if (!page)
+				goto out_free_bio;
+			if (bio_add_pc_page(q, bio, page, sector_size, 0) <
+				sector_size)
+				goto out_free_page;
+		}
 		/*
 		 * And override the bio size - the way discard works we
 		 * touch many more blocks on disk than the actual payload
diff --git a/drivers/scsi/sd.c b/drivers/scsi/sd.c
index 1dd4d84..9994977 100644
--- a/drivers/scsi/sd.c
+++ b/drivers/scsi/sd.c
@@ -1513,6 +1513,7 @@ static int read_capacity_16(struct scsi_disk *sdkp, struct scsi_device *sdp,
 			q->limits.discard_zeroes_data = 1;
 
 		queue_flag_set_unlocked(QUEUE_FLAG_DISCARD, q);
+		queue_flag_set_unlocked(QUEUE_FLAG_DISCARD_MEM, q);
 	}
 
 	sdkp->capacity = lba + 1;
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 78180b7..e232a0d 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -461,7 +461,8 @@ struct request_queue
 #define QUEUE_FLAG_VIRT        QUEUE_FLAG_NONROT /* paravirt device */
 #define QUEUE_FLAG_IO_STAT     15	/* do IO stats */
 #define QUEUE_FLAG_DISCARD     16	/* supports DISCARD */
-#define QUEUE_FLAG_NOXMERGES   17	/* No extended merges */
+#define QUEUE_FLAG_DISCARD_MEM 17	/* require memory in DISCARD request*/
+#define QUEUE_FLAG_NOXMERGES   18	/* No extended merges */
 
 #define QUEUE_FLAG_DEFAULT	((1 << QUEUE_FLAG_IO_STAT) |		\
 				 (1 << QUEUE_FLAG_CLUSTER) |		\
@@ -595,6 +596,8 @@ enum {
 #define blk_queue_stackable(q)	\
 	test_bit(QUEUE_FLAG_STACKABLE, &(q)->queue_flags)
 #define blk_queue_discard(q)	test_bit(QUEUE_FLAG_DISCARD, &(q)->queue_flags)
+#define blk_queue_discard_mem(q) \
+	test_bit(QUEUE_FLAG_DISCARD_MEM, &(q)->queue_flags)
 
 #define blk_fs_request(rq)	((rq)->cmd_type == REQ_TYPE_FS)
 #define blk_pc_request(rq)	((rq)->cmd_type == REQ_TYPE_BLOCK_PC)
-- 
1.6.6.1


  parent reply	other threads:[~2010-03-24 17:21 UTC|newest]

Thread overview: 8+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2010-03-24 17:21 [PATCH 0/5] blkdev: discard optimizations v2 Dmitry Monakhov
2010-03-24 17:21 ` [PATCH 1/5] blkdev: pass gfp_mask and flags to blkdev_issue_flush Dmitry Monakhov
     [not found]   ` <1269451281-4944-3-git-send-email-dmonakhov@openvz.org>
     [not found]     ` <1269451281-4944-4-git-send-email-dmonakhov@openvz.org>
2010-03-24 17:21       ` Dmitry Monakhov [this message]
2010-03-24 17:21         ` [PATCH 5/5] blkdev: optimize discard request logic Dmitry Monakhov
2010-03-24 17:29 [PATCH 0/5] blkdev: discard optimizations v2 RESEND Dmitry Monakhov
2010-03-24 17:29 ` [PATCH 1/5] blkdev: pass gfp_mask and flags to blkdev_issue_flush Dmitry Monakhov
     [not found]   ` <1269451792-5205-3-git-send-email-dmonakhov@openvz.org>
     [not found]     ` <1269451792-5205-4-git-send-email-dmonakhov@openvz.org>
2010-03-24 17:29       ` [PATCH 4/5] blkdev: add discard payload flag Dmitry Monakhov
2010-03-24 17:33 [PATCH 0/5] blkdev: discard optimizations v2 RESEND2 Dmitry Monakhov
2010-03-24 17:33 ` [PATCH 1/5] blkdev: pass gfp_mask and flags to blkdev_issue_flush Dmitry Monakhov
2010-03-24 17:33   ` [PATCH 2/5] blkdev: generalize flags for blkdev_issue functions Dmitry Monakhov
2010-03-24 17:33     ` [PATCH 3/5] blkdev: add blkdev_issue helper functions Dmitry Monakhov
2010-03-24 17:33       ` [PATCH 4/5] blkdev: add discard payload flag Dmitry Monakhov
2010-04-05 20:00         ` Christoph Hellwig
2010-04-06  8:29           ` Dmitry Monakhov

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=1269451281-4944-5-git-send-email-dmonakhov@openvz.org \
    --to=dmonakhov@openvz.org \
    --cc=hch@infradead.org \
    --cc=jens.axboe@oracle.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=mkp@mkp.net \
    /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

all inboxes | Powered by JetHome®