mirror of https://lore.kernel.org/lkml/
 help / color / mirror / Atom feed
From: Lai Jiangshan <laijs@cn.fujitsu.com>
To: <linux-kernel@vger.kernel.org>
Cc: Lai Jiangshan <laijs@cn.fujitsu.com>, Tejun Heo <tj@kernel.org>
Subject: [PATCH 6/7 V2] workqueue: reuse wq_update_unbound_numa_attrs_buf as temporary attrs
Date: Tue, 12 May 2015 20:32:34 +0800	[thread overview]
Message-ID: <1431433955-3173-7-git-send-email-laijs@cn.fujitsu.com> (raw)
In-Reply-To: <1431433955-3173-1-git-send-email-laijs@cn.fujitsu.com>

tmp_attrs is just temporary attrs, we can use wq_update_unbound_numa_attrs_buf
for it like wq_update_unbound_numa();

This change also avoids frequently alloc/free the tmp_attrs when
the low level cpumask is being updated.

Signed-off-by: Lai Jiangshan <laijs@cn.fujitsu.com>
---
 kernel/workqueue.c | 15 +++++++++------
 1 file changed, 9 insertions(+), 6 deletions(-)

diff --git a/kernel/workqueue.c b/kernel/workqueue.c
index 61f8ace..6426d6e 100644
--- a/kernel/workqueue.c
+++ b/kernel/workqueue.c
@@ -295,7 +295,7 @@ module_param_named(power_efficient, wq_power_efficient, bool, 0444);
 
 static bool wq_numa_enabled;		/* unbound NUMA affinity enabled */
 
-/* buf for wq_update_unbound_numa_attrs(), protected by CPU hotplug exclusion */
+/* PL: buf for apply_wqattrs_prepare() and wq_update_unbound_numa() */
 static struct workqueue_attrs *wq_update_unbound_numa_attrs_buf;
 
 static DEFINE_MUTEX(wq_pool_mutex);	/* protects pools and workqueues list */
@@ -3561,11 +3561,16 @@ apply_wqattrs_prepare(struct workqueue_struct *wq,
 		      GFP_KERNEL);
 
 	new_attrs = alloc_workqueue_attrs(GFP_KERNEL);
-	tmp_attrs = alloc_workqueue_attrs(GFP_KERNEL);
-	if (!ctx || !new_attrs || !tmp_attrs)
+	if (!ctx || !new_attrs)
 		goto out_free;
 
 	/*
+	 * We don't need to alloc/free temporary attrs. Let's use a
+	 * preallocated one.  The following buf is protected by wq_pool_mutex.
+	 */
+	tmp_attrs = wq_update_unbound_numa_attrs_buf;
+
+	/*
 	 * Calculate the attrs of the default pwq.
 	 * If the user configured cpumask doesn't overlap with the
 	 * wq_unbound_cpumask, we fallback to the wq_unbound_cpumask.
@@ -3615,11 +3620,9 @@ apply_wqattrs_prepare(struct workqueue_struct *wq,
 	ctx->attrs = new_attrs;
 
 	ctx->wq = wq;
-	free_workqueue_attrs(tmp_attrs);
 	return ctx;
 
 out_free:
-	free_workqueue_attrs(tmp_attrs);
 	free_workqueue_attrs(new_attrs);
 	apply_wqattrs_cleanup(ctx);
 	return NULL;
@@ -3741,7 +3744,7 @@ static void wq_update_unbound_numa(struct workqueue_struct *wq, int cpu,
 	/*
 	 * We don't wanna alloc/free wq_attrs for each wq for each CPU.
 	 * Let's use a preallocated one.  The following buf is protected by
-	 * CPU hotplug exclusion.
+	 * wq_pool_mutex.
 	 */
 	target_attrs = wq_update_unbound_numa_attrs_buf;
 	cpumask = target_attrs->cpumask;
-- 
2.1.0


  parent reply	other threads:[~2015-05-12 12:29 UTC|newest]

Thread overview: 18+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2015-05-12 12:32 [PATCH 0/7 V2] workqueue: cleanup for attr management Lai Jiangshan
2015-05-12 12:32 ` [PATCH 1/7 V2] workqueue: wq_pool_mutex protects the attrs-installation Lai Jiangshan
2015-05-12 12:32 ` [PATCH 2/7 V2] workqueue: simplify wq_update_unbound_numa() Lai Jiangshan
2015-05-18 20:21   ` Tejun Heo
2015-05-12 12:32 ` [PATCH 3/7 V2] workqueue: introduce get_pwq_unlocked() Lai Jiangshan
2015-05-18 20:28   ` Tejun Heo
2015-05-18 20:41   ` Tejun Heo
2015-05-12 12:32 ` [PATCH 4/7 V2] workqueue: reuse the current per-node pwq when its attrs unchanged Lai Jiangshan
2015-05-18 20:34   ` Tejun Heo
2015-05-25  9:47   ` Lai Jiangshan
2015-05-26 18:51     ` Tejun Heo
2015-05-12 12:32 ` [PATCH 5/7 V2] workqueue: reuse the current default " Lai Jiangshan
2015-05-18 20:38   ` Tejun Heo
2015-05-12 12:32 ` Lai Jiangshan [this message]
2015-05-12 12:32 ` [PATCH 7/7 V2] workqueue: add get_node_unbound_pwq() Lai Jiangshan
2015-05-18  0:39 ` [PATCH 0/7 V2] workqueue: cleanup for attr management Lai Jiangshan
2015-05-18  1:26   ` Tejun Heo
2015-05-18  2:06     ` Lai Jiangshan

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=1431433955-3173-7-git-send-email-laijs@cn.fujitsu.com \
    --to=laijs@cn.fujitsu.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=tj@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®