All of lore.kernel.org
 help / color / mirror / Atom feed
From: zanussi@kernel.org
To: LKML <linux-kernel@vger.kernel.org>,
	linux-rt-users <linux-rt-users@vger.kernel.org>,
	Steven Rostedt <rostedt@goodmis.org>,
	Thomas Gleixner <tglx@linutronix.de>,
	Carsten Emde <C.Emde@osadl.org>, John Kacur <jkacur@redhat.com>,
	Sebastian Andrzej Siewior <bigeasy@linutronix.de>,
	Daniel Wagner <wagi@monom.org>, Tom Zanussi <zanussi@kernel.org>
Subject: [PATCH RT 09/23] lib/smp_processor_id: Don't use cpumask_equal()
Date: Thu, 27 Feb 2020 08:33:20 -0600	[thread overview]
Message-ID: <dc9753ab1be6bcd124b6e96dca353571dbdbaac7.1582814004.git.zanussi@kernel.org> (raw)
In-Reply-To: <cover.1582814004.git.zanussi@kernel.org>
In-Reply-To: <cover.1582814004.git.zanussi@kernel.org>

From: Waiman Long <longman@redhat.com>

v4.14.170-rt75-rc2 stable review patch.
If anyone has any objections, please let me know.

-----------


[ Upstream commit 659252061477862f45b79e1de169e6030f5c8918 ]

The check_preemption_disabled() function uses cpumask_equal() to see
if the task is bounded to the current CPU only. cpumask_equal() calls
memcmp() to do the comparison. As x86 doesn't have __HAVE_ARCH_MEMCMP,
the slow memcmp() function in lib/string.c is used.

On a RT kernel that call check_preemption_disabled() very frequently,
below is the perf-record output of a certain microbenchmark:

  42.75%  2.45%  testpmd [kernel.kallsyms] [k] check_preemption_disabled
  40.01% 39.97%  testpmd [kernel.kallsyms] [k] memcmp

We should avoid calling memcmp() in performance critical path. So the
cpumask_equal() call is now replaced with an equivalent simpler check.

Signed-off-by: Waiman Long <longman@redhat.com>
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Signed-off-by: Tom Zanussi <zanussi@kernel.org>
---
 lib/smp_processor_id.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/lib/smp_processor_id.c b/lib/smp_processor_id.c
index 6f4a4ae881c8..9f3c8bb62e57 100644
--- a/lib/smp_processor_id.c
+++ b/lib/smp_processor_id.c
@@ -23,7 +23,7 @@ notrace static unsigned int check_preemption_disabled(const char *what1,
 	 * Kernel threads bound to a single CPU can safely use
 	 * smp_processor_id():
 	 */
-	if (cpumask_equal(current->cpus_ptr, cpumask_of(this_cpu)))
+	if (current->nr_cpus_allowed == 1)
 		goto out;
 
 	/*
-- 
2.14.1


  parent reply	other threads:[~2020-02-27 14:34 UTC|newest]

Thread overview: 30+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2020-02-27 14:33 [PATCH RT 00/23] Linux v4.14.170-rt75-rc2 zanussi
2020-02-27 14:33 ` [PATCH RT 01/23] Fix wrong-variable use in irq_set_affinity_notifier zanussi
2020-02-27 14:33 ` [PATCH RT 02/23] i2c: exynos5: Remove IRQF_ONESHOT zanussi
2020-02-27 14:33 ` [PATCH RT 03/23] i2c: hix5hd2: " zanussi
2020-02-27 14:33 ` [PATCH RT 04/23] x86: preempt: Check preemption level before looking at lazy-preempt zanussi
2020-02-27 14:33 ` [PATCH RT 05/23] sched: migrate_dis/enable: Use sleeping_lock…() to annotate sleeping points zanussi
2020-02-27 14:33 ` [PATCH RT 06/23] sched: __set_cpus_allowed_ptr: Check cpus_mask, not cpus_ptr zanussi
2020-02-27 14:33 ` [PATCH RT 07/23] sched: Remove dead __migrate_disabled() check zanussi
2020-02-27 14:33 ` [PATCH RT 08/23] sched: migrate disable: Protect cpus_ptr with lock zanussi
2020-02-27 14:33 ` zanussi [this message]
2020-02-27 14:33 ` [PATCH RT 10/23] futex: Make the futex_hash_bucket spinlock_t again and bring back its old state zanussi
2020-02-27 14:33 ` [PATCH RT 11/23] locking/rtmutex: Clean ->pi_blocked_on in the error case zanussi
2020-02-27 14:33 ` [PATCH RT 12/23] lib/ubsan: Don't seralize UBSAN report zanussi
2020-02-27 14:33 ` [PATCH RT 13/23] kmemleak: Change the lock of kmemleak_object to raw_spinlock_t zanussi
2020-02-27 14:33 ` [PATCH RT 14/23] Revert "ARM: Initialize split page table locks for vector page" zanussi
2020-02-27 14:33 ` [PATCH RT 15/23] locking: Make spinlock_t and rwlock_t a RCU section on RT zanussi
2020-02-27 14:33 ` [PATCH RT 16/23] sched: migrate_enable: Use select_fallback_rq() zanussi
2020-02-27 14:33 ` [PATCH RT 17/23] sched: Lazy migrate_disable processing zanussi
2020-02-27 14:33 ` [PATCH RT 18/23] sched: migrate_enable: Use stop_one_cpu_nowait() zanussi
2020-02-27 14:33 ` [PATCH RT 19/23] sched/core: migrate_enable() must access takedown_cpu_task on !HOTPLUG_CPU zanussi
2020-02-27 14:33 ` [PATCH RT 20/23] lib/smp_processor_id: Adjust check_preemption_disabled() zanussi
2020-02-27 14:33 ` [PATCH RT 21/23] sched: migrate_enable: Busy loop until the migration request is completed zanussi
2020-03-03 19:56   ` Scott Wood
2020-03-03 20:39     ` Tom Zanussi
2020-03-03 21:19       ` Scott Wood
2020-03-03 21:54         ` Steven Rostedt
2020-03-05 13:38   ` David Laight
2020-03-05 17:58     ` Tom Zanussi
2020-02-27 14:33 ` [PATCH RT 22/23] sched/deadline: Ensure inactive_timer runs in hardirq context zanussi
2020-02-27 14:33 ` [PATCH RT 23/23] Linux 4.14.170-rt75-rc2 zanussi

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=dc9753ab1be6bcd124b6e96dca353571dbdbaac7.1582814004.git.zanussi@kernel.org \
    --to=zanussi@kernel.org \
    --cc=C.Emde@osadl.org \
    --cc=bigeasy@linutronix.de \
    --cc=jkacur@redhat.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-rt-users@vger.kernel.org \
    --cc=rostedt@goodmis.org \
    --cc=tglx@linutronix.de \
    --cc=wagi@monom.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 an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.