From: Sagi Grimberg <sagi@grimberg.me>
To: Jens Axboe <axboe@kernel.dk>, linux-block@vger.kernel.org
Cc: Christoph Hellwig <hch@lst.de>
Subject: [PATCH 3/3] irq-poll: Reduce local_irq_save/restore operations in irq_poll_softirq
Date: Sun, 13 Nov 2016 01:02:35 +0200 [thread overview]
Message-ID: <1478991755-28153-4-git-send-email-sagi@grimberg.me> (raw)
In-Reply-To: <1478991755-28153-1-git-send-email-sagi@grimberg.me>
splice to a local list (and splice back when done) so we won't
need to enable/disable local_irq in each iteration.
Signed-off-by: Sagi Grimberg <sagi@grimberg.me>
---
lib/irq_poll.c | 31 ++++++++++++++++---------------
1 file changed, 16 insertions(+), 15 deletions(-)
diff --git a/lib/irq_poll.c b/lib/irq_poll.c
index 44a5d1da4260..dc4c7ace9b41 100644
--- a/lib/irq_poll.c
+++ b/lib/irq_poll.c
@@ -75,13 +75,16 @@ EXPORT_SYMBOL(irq_poll_complete);
static void __latent_entropy irq_poll_softirq(struct softirq_action *h)
{
- struct list_head *list = this_cpu_ptr(&blk_cpu_iopoll);
+ struct list_head *iop_list = this_cpu_ptr(&blk_cpu_iopoll);
int rearm = 0, budget = irq_poll_budget;
unsigned long start_time = jiffies;
+ LIST_HEAD(list);
local_irq_disable();
+ list_splice_init(iop_list, &list);
+ local_irq_enable();
- while (!list_empty(list)) {
+ while (!list_empty(&list)) {
struct irq_poll *iop;
int work, weight;
@@ -93,14 +96,7 @@ static void __latent_entropy irq_poll_softirq(struct softirq_action *h)
break;
}
- local_irq_enable();
-
- /* Even though interrupts have been re-enabled, this
- * access is safe because interrupts can only add new
- * entries to the tail of this list, and only ->poll()
- * calls can remove this head entry from the list.
- */
- iop = list_entry(list->next, struct irq_poll, list);
+ iop = list_first_entry(&list, struct irq_poll, list);
weight = iop->weight;
work = 0;
@@ -109,8 +105,6 @@ static void __latent_entropy irq_poll_softirq(struct softirq_action *h)
budget -= work;
- local_irq_disable();
-
/*
* Drivers must not modify the iopoll state, if they
* consume their assigned weight (or more, some drivers can't
@@ -120,13 +114,20 @@ static void __latent_entropy irq_poll_softirq(struct softirq_action *h)
* move the instance around on the list at-will.
*/
if (work >= weight) {
- if (unlikely(test_bit(IRQ_POLL_F_DISABLE, &iop->state)))
+ if (unlikely(test_bit(IRQ_POLL_F_DISABLE, &iop->state))) {
+ local_irq_disable();
__irq_poll_complete(iop);
- else
- list_move_tail(&iop->list, list);
+ local_irq_enable();
+ } else {
+ list_move_tail(&iop->list, &list);
+ }
}
}
+ local_irq_disable();
+ list_splice_tail_init(iop_list, &list);
+ list_splice(&list, iop_list);
+
if (rearm)
__raise_softirq_irqoff(IRQ_POLL_SOFTIRQ);
--
2.7.4
next prev parent reply other threads:[~2016-11-12 23:02 UTC|newest]
Thread overview: 9+ messages / expand[flat|nested] mbox.gz Atom feed top
2016-11-12 23:02 [PATCH 0/3] micro-optimize irq-poll Sagi Grimberg
2016-11-12 23:02 ` [PATCH 1/3] irq-poll: Remove redundant include Sagi Grimberg
2016-11-13 15:12 ` Christoph Hellwig
2016-11-12 23:02 ` [PATCH 2/3] irq-poll: micro optimize some branch predictions Sagi Grimberg
2016-11-13 15:13 ` Christoph Hellwig
2016-11-14 0:49 ` Sagi Grimberg
2016-11-12 23:02 ` Sagi Grimberg [this message]
2016-11-13 15:18 ` [PATCH 3/3] irq-poll: Reduce local_irq_save/restore operations in irq_poll_softirq Christoph Hellwig
2016-11-14 1:02 ` Sagi Grimberg
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=1478991755-28153-4-git-send-email-sagi@grimberg.me \
--to=sagi@grimberg.me \
--cc=axboe@kernel.dk \
--cc=hch@lst.de \
--cc=linux-block@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;
as well as URLs for NNTP newsgroup(s).