linux-kernel.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Tejun Heo <tj@kernel.org>
To: axboe@kernel.dk, vgoyal@redhat.com
Cc: ctalbott@google.com, rni@google.com,
	linux-kernel@vger.kernel.org, Tejun Heo <tj@kernel.org>
Subject: [PATCH 30/36] block: restructure get_request()
Date: Tue, 21 Feb 2012 17:46:57 -0800	[thread overview]
Message-ID: <1329875223-5102-31-git-send-email-tj@kernel.org> (raw)
In-Reply-To: <1329875223-5102-1-git-send-email-tj@kernel.org>

get_request() is structured a bit unusually in that failure path is
inlined in the usual flow with goto labels atop and inside it.
Relocate the error path to the end of the function.

This is to prepare for icq handling changes in get_request() and
doesn't introduce any behavior change.

Signed-off-by: Tejun Heo <tj@kernel.org>
Cc: Vivek Goyal <vgoyal@redhat.com>
---
 block/blk-core.c |   60 ++++++++++++++++++++++++++---------------------------
 1 files changed, 29 insertions(+), 31 deletions(-)

diff --git a/block/blk-core.c b/block/blk-core.c
index bf06d1d..69fa8c4 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -825,7 +825,7 @@ static bool blk_rq_should_init_elevator(struct bio *bio)
 static struct request *get_request(struct request_queue *q, int rw_flags,
 				   struct bio *bio, gfp_t gfp_mask)
 {
-	struct request *rq = NULL;
+	struct request *rq;
 	struct request_list *rl = &q->rq;
 	struct elevator_type *et;
 	struct io_context *ioc;
@@ -877,7 +877,7 @@ retry:
 					 * process is not a "batcher", and not
 					 * exempted by the IO scheduler
 					 */
-					goto out;
+					return NULL;
 				}
 			}
 		}
@@ -890,7 +890,7 @@ retry:
 	 * allocated with any setting of ->nr_requests
 	 */
 	if (rl->count[is_sync] >= (3 * q->nr_requests / 2))
-		goto out;
+		return NULL;
 
 	rl->count[is_sync]++;
 	rl->starved[is_sync] = 0;
@@ -920,36 +920,12 @@ retry:
 	if ((rw_flags & REQ_ELVPRIV) && unlikely(et->icq_cache && !icq)) {
 		icq = ioc_create_icq(q, gfp_mask);
 		if (!icq)
-			goto fail_icq;
+			goto fail_alloc;
 	}
 
 	rq = blk_alloc_request(q, icq, rw_flags, gfp_mask);
-
-fail_icq:
-	if (unlikely(!rq)) {
-		/*
-		 * Allocation failed presumably due to memory. Undo anything
-		 * we might have messed up.
-		 *
-		 * Allocating task should really be put onto the front of the
-		 * wait queue, but this is pretty rare.
-		 */
-		spin_lock_irq(q->queue_lock);
-		freed_request(q, rw_flags);
-
-		/*
-		 * in the very unlikely event that allocation failed and no
-		 * requests for this direction was pending, mark us starved
-		 * so that freeing of a request in the other direction will
-		 * notice us. another possible fix would be to split the
-		 * rq mempool into READ and WRITE
-		 */
-rq_starved:
-		if (unlikely(rl->count[is_sync] == 0))
-			rl->starved[is_sync] = 1;
-
-		goto out;
-	}
+	if (unlikely(!rq))
+		goto fail_alloc;
 
 	/*
 	 * ioc may be NULL here, and ioc_batching will be false. That's
@@ -961,8 +937,30 @@ rq_starved:
 		ioc->nr_batch_requests--;
 
 	trace_block_getrq(q, bio, rw_flags & 1);
-out:
 	return rq;
+
+fail_alloc:
+	/*
+	 * Allocation failed presumably due to memory. Undo anything we
+	 * might have messed up.
+	 *
+	 * Allocating task should really be put onto the front of the wait
+	 * queue, but this is pretty rare.
+	 */
+	spin_lock_irq(q->queue_lock);
+	freed_request(q, rw_flags);
+
+	/*
+	 * in the very unlikely event that allocation failed and no
+	 * requests for this direction was pending, mark us starved so that
+	 * freeing of a request in the other direction will notice
+	 * us. another possible fix would be to split the rq mempool into
+	 * READ and WRITE
+	 */
+rq_starved:
+	if (unlikely(rl->count[is_sync] == 0))
+		rl->starved[is_sync] = 1;
+	return NULL;
 }
 
 /**
-- 
1.7.7.3


  parent reply	other threads:[~2012-02-22  1:49 UTC|newest]

Thread overview: 57+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2012-02-22  1:46 [PATCHSET] blkcg: accumulated blkcg updates Tejun Heo
2012-02-22  1:46 ` [PATCH 01/36] block: blk-throttle should be drained regardless of q->elevator Tejun Heo
2012-02-22  1:46 ` [PATCH 02/36] blkcg: make CONFIG_BLK_CGROUP bool Tejun Heo
2012-02-22  1:46 ` [PATCH 03/36] cfq: don't register propio policy if !CONFIG_CFQ_GROUP_IOSCHED Tejun Heo
2012-02-22  1:46 ` [PATCH 04/36] elevator: clear auxiliary data earlier during elevator switch Tejun Heo
2012-02-22  1:46 ` [PATCH 05/36] elevator: make elevator_init_fn() return 0/-errno Tejun Heo
2012-02-22  1:46 ` [PATCH 06/36] block: implement blk_queue_bypass_start/end() Tejun Heo
2012-02-22  1:46 ` [PATCH 07/36] block: extend queue bypassing to cover blkcg policies Tejun Heo
2012-02-22  1:46 ` [PATCH 08/36] blkcg: shoot down blkio_groups on elevator switch Tejun Heo
2012-02-22  1:46 ` [PATCH 09/36] blkcg: move rcu_read_lock() outside of blkio_group get functions Tejun Heo
2012-02-22  1:46 ` [PATCH 10/36] blkcg: update blkg get functions take blkio_cgroup as parameter Tejun Heo
2012-02-22  1:46 ` [PATCH 11/36] blkcg: use q and plid instead of opaque void * for blkio_group association Tejun Heo
2012-02-22  1:46 ` [PATCH 12/36] blkcg: add blkio_policy[] array and allow one policy per policy ID Tejun Heo
2012-02-22  1:46 ` [PATCH 13/36] blkcg: use the usual get blkg path for root blkio_group Tejun Heo
2012-02-22  1:46 ` [PATCH 14/36] blkcg: factor out blkio_group creation Tejun Heo
2012-02-22  1:46 ` [PATCH 15/36] blkcg: don't allow or retain configuration of missing devices Tejun Heo
2012-02-22  1:46 ` [PATCH 16/36] blkcg: kill blkio_policy_node Tejun Heo
2012-02-22  1:46 ` [PATCH 17/36] blkcg: kill the mind-bending blkg->dev Tejun Heo
2012-02-22  1:46 ` [PATCH 18/36] blkcg: let blkio_group point to blkio_cgroup directly Tejun Heo
2012-02-22  1:46 ` [PATCH 19/36] blkcg: add blkcg_{init|drain|exit}_queue() Tejun Heo
2012-02-22  1:46 ` [PATCH 20/36] blkcg: clear all request_queues on blkcg policy [un]registrations Tejun Heo
2012-02-22  1:46 ` [PATCH 21/36] blkcg: let blkcg core handle policy private data allocation Tejun Heo
2012-02-22  1:46 ` [PATCH 22/36] blkcg: move refcnt to blkcg core Tejun Heo
2012-02-22  1:46 ` [PATCH 23/36] blkcg: make blkg->pd an array and move configuration and stats into it Tejun Heo
2012-02-22  1:46 ` [PATCH 24/36] blkcg: don't use blkg->plid in stat related functions Tejun Heo
2012-02-22  1:46 ` [PATCH 25/36] blkcg: move per-queue blkg list heads and counters to queue and blkg Tejun Heo
2012-02-22  1:46 ` [PATCH 26/36] blkcg: let blkcg core manage per-queue blkg list and counter Tejun Heo
2012-02-22  1:46 ` [PATCH 27/36] blkcg: unify blkg's for blkcg policies Tejun Heo
2012-03-05 21:01   ` [PATCH UPDATED " Tejun Heo
2012-02-22  1:46 ` [PATCH 28/36] blkcg: use double locking instead of RCU for blkg synchronization Tejun Heo
2012-02-22  1:46 ` [PATCH 29/36] blkcg: drop unnecessary RCU locking Tejun Heo
2012-02-23 18:51   ` [PATCH UPDATED " Tejun Heo
2012-02-22  1:46 ` Tejun Heo [this message]
2012-02-22  1:46 ` [PATCH 31/36] block: interface update for ioc/icq creation functions Tejun Heo
2012-02-22  1:46 ` [PATCH 32/36] block: ioc_task_link() can't fail Tejun Heo
2012-02-22  1:47 ` [PATCH 33/36] block: add io_context->active_ref Tejun Heo
2012-02-22 18:47   ` Vivek Goyal
2012-02-22 19:13     ` Tejun Heo
2012-02-23 18:20       ` Vivek Goyal
2012-02-22  1:47 ` [PATCH 34/36] block: implement bio_associate_current() Tejun Heo
2012-02-22 13:45   ` Jeff Moyer
2012-02-22 19:07     ` Tejun Heo
2012-02-22 19:33       ` Jeff Moyer
2012-02-22 19:37         ` Vivek Goyal
2012-02-22 19:41           ` Jeff Moyer
2012-02-22  1:47 ` [PATCH 35/36] block: make block cgroup policies follow bio task association Tejun Heo
2012-02-22  1:47 ` [PATCH 36/36] block: make blk-throttle preserve the issuing task on delayed bios Tejun Heo
2012-02-22 19:34 ` [PATCHSET] blkcg: accumulated blkcg updates Vivek Goyal
2012-02-22 22:04   ` Tejun Heo
2012-03-05 20:59 ` [PATCH 17.5] blkcg: skip blkg printing if q isn't associated with disk Tejun Heo
2012-03-05 21:07 ` [PATCHSET] blkcg: accumulated blkcg updates Tejun Heo
2012-03-05 21:08   ` Tejun Heo
2012-03-06 15:07     ` Vivek Goyal
2012-03-06 16:24       ` Vivek Goyal
2012-03-06 18:39         ` Vivek Goyal
2012-03-06 19:02           ` Vivek Goyal
2012-03-08  0:06             ` Tejun Heo

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=1329875223-5102-31-git-send-email-tj@kernel.org \
    --to=tj@kernel.org \
    --cc=axboe@kernel.dk \
    --cc=ctalbott@google.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=rni@google.com \
    --cc=vgoyal@redhat.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;
as well as URLs for NNTP newsgroup(s).