From: Ming Lei <ming.lei@canonical.com>
To: Jens Axboe <axboe@kernel.dk>, linux-kernel@vger.kernel.org
Cc: linux-scsi@vger.kernel.org, Christoph Hellwig <hch@lst.de>,
Ming Lei <ming.lei@canonical.com>
Subject: [PATCH 5/6] scsi-lib: implement init_flush_rq and its pair
Date: Sun, 7 Sep 2014 16:39:21 +0800 [thread overview]
Message-ID: <1410079162-9872-6-git-send-email-ming.lei@canonical.com> (raw)
In-Reply-To: <1410079162-9872-1-git-send-email-ming.lei@canonical.com>
Now implement init_flush_rq callback to avoid the unnecessary
pdu copying done in blk_mq_clone_flush_request().
The sense buffer is introduced to flush req, but it won't be
a deal since there is only one flush request per queue. It still
may be borrowed from the sence buffer of the request cloned from,
but looks a bit ugly.
Signed-off-by: Ming Lei <ming.lei@canonical.com>
---
drivers/scsi/scsi_lib.c | 32 +++++++++++++++++++++++++++-----
1 file changed, 27 insertions(+), 5 deletions(-)
diff --git a/drivers/scsi/scsi_lib.c b/drivers/scsi/scsi_lib.c
index b9a8ddd..9090418 100644
--- a/drivers/scsi/scsi_lib.c
+++ b/drivers/scsi/scsi_lib.c
@@ -1930,9 +1930,7 @@ out:
return ret;
}
-static int scsi_init_request(void *data, struct request *rq,
- unsigned int hctx_idx, unsigned int request_idx,
- unsigned int numa_node)
+static int __scsi_init_request(struct request *rq, int numa_node)
{
struct scsi_cmnd *cmd = blk_mq_rq_to_pdu(rq);
@@ -1943,14 +1941,36 @@ static int scsi_init_request(void *data, struct request *rq,
return 0;
}
-static void scsi_exit_request(void *data, struct request *rq,
- unsigned int hctx_idx, unsigned int request_idx)
+static void __scsi_exit_request(struct request *rq)
{
struct scsi_cmnd *cmd = blk_mq_rq_to_pdu(rq);
kfree(cmd->sense_buffer);
}
+static int scsi_init_request(void *data, struct request *rq,
+ unsigned int hctx_idx, unsigned int request_idx,
+ unsigned int numa_node)
+{
+ return __scsi_init_request(rq, numa_node);
+}
+
+static void scsi_exit_request(void *data, struct request *rq,
+ unsigned int hctx_idx, unsigned int request_idx)
+{
+ __scsi_exit_request(rq);
+}
+
+static int scsi_init_flush_rq(struct request_queue *q, struct request *rq)
+{
+ return __scsi_init_request(rq, NUMA_NO_NODE);
+}
+
+static void scsi_exit_flush_rq(struct request_queue *q, struct request *rq)
+{
+ __scsi_exit_request(rq);
+}
+
static u64 scsi_calculate_bounce_limit(struct Scsi_Host *shost)
{
struct device *host_dev;
@@ -2044,6 +2064,8 @@ static struct blk_mq_ops scsi_mq_ops = {
.timeout = scsi_times_out,
.init_request = scsi_init_request,
.exit_request = scsi_exit_request,
+ .init_flush_rq = scsi_init_flush_rq,
+ .exit_flush_rq = scsi_exit_flush_rq,
};
struct request_queue *scsi_mq_alloc_queue(struct scsi_device *sdev)
--
1.7.9.5
next prev parent reply other threads:[~2014-09-07 8:40 UTC|newest]
Thread overview: 13+ messages / expand[flat|nested] mbox.gz Atom feed top
2014-09-07 8:39 [PATCH 0/6] blk-mq: initialize pdu of flush req explicitly Ming Lei
2014-09-07 8:39 ` [PATCH 1/6] blk-mq: allocate flush_rq in blk_mq_init_flush() Ming Lei
2014-09-07 8:39 ` [PATCH 2/6] blk-mq: introduce init_flush_rq callback and its pair Ming Lei
2014-09-07 8:39 ` [PATCH 3/6] blk-mq: don't copy pdu if init_flush_rq is implemented Ming Lei
2014-09-07 8:39 ` [PATCH 4/6] virtio-blk: implement init_flush_rq Ming Lei
2014-09-07 18:52 ` Christoph Hellwig
2014-09-07 8:39 ` Ming Lei [this message]
2014-09-07 18:53 ` [PATCH 5/6] scsi-lib: implement init_flush_rq and its pair Christoph Hellwig
2014-09-07 8:39 ` [PATCH 6/6] blk-mq: don't copy pdu any more for flush req Ming Lei
2014-09-07 18:49 ` [PATCH 0/6] blk-mq: initialize pdu of flush req explicitly Christoph Hellwig
2014-09-08 16:55 ` Ming Lei
2014-09-08 19:03 ` Jens Axboe
2014-09-08 22:53 ` Elliott, Robert (Server Storage)
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=1410079162-9872-6-git-send-email-ming.lei@canonical.com \
--to=ming.lei@canonical.com \
--cc=axboe@kernel.dk \
--cc=hch@lst.de \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-scsi@vger.kernel.org \
/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®