linux-kernel - Re: Severe performance regression w/ 4.4+ on Android due to cgroup locking changes

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Message-Id: <20160713214238.GA15996@linux.vnet.ibm.com>
Date:	Wed, 13 Jul 2016 14:42:38 -0700
From:	"Paul E. McKenney" <paulmck@...ux.vnet.ibm.com>
To:	Tejun Heo <tj@...nel.org>
Cc:	Peter Zijlstra <peterz@...radead.org>,
	John Stultz <john.stultz@...aro.org>,
	Ingo Molnar <mingo@...hat.com>,
	lkml <linux-kernel@...r.kernel.org>,
	Dmitry Shmidt <dimitrysh@...gle.com>,
	Rom Lemarchand <romlem@...gle.com>,
	Colin Cross <ccross@...gle.com>, Todd Kjos <tkjos@...gle.com>,
	Oleg Nesterov <oleg@...hat.com>
Subject: Re: Severe performance regression w/ 4.4+ on Android due to cgroup
 locking changes

On Wed, Jul 13, 2016 at 02:18:41PM -0700, Paul E. McKenney wrote:
> On Wed, Jul 13, 2016 at 05:05:26PM -0400, Tejun Heo wrote:
> > On Wed, Jul 13, 2016 at 02:03:15PM -0700, Paul E. McKenney wrote:
> > > Take the patch that I just sent out and make the choice of normal
> > > vs. expedited depend on CONFIG_PREEMPT_RT or whatever the -rt guys are
> > > calling it these days.  Is there a low-latency Kconfig option other
> > > than CONFIG_NO_HZ_FULL?
> > 
> > Sounds like a plan to me.
> 
> I like the way we like each other's idea.  Mutually assured laziness?  ;-)

But here is what mine might look like.  Untested, probably does
not even build.  Note that the default is -no- expediting, use the
rcusync.expedited kernel parameter to enable it.

							Thanx, Paul

------------------------------------------------------------------------

diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt
index 82b42c958d1c..b8bc9854e548 100644
--- a/Documentation/kernel-parameters.txt
+++ b/Documentation/kernel-parameters.txt
@@ -3229,6 +3229,11 @@ bytes respectively. Such letter suffixes can also be entirely omitted.
 			energy efficiency by requiring that the kthreads
 			periodically wake up to do the polling.
 
+	rcusync.expedited	[KNL]
+			Specify that the rcusync mechanism use expedited
+			grace periods.  As of mid-2016, this affects
+			per-CPU rwsems.
+
 	rcutree.blimit=	[KNL]
 			Set maximum number of finished RCU callbacks to
 			process in one batch.
diff --git a/kernel/rcu/sync.c b/kernel/rcu/sync.c
index be922c9f3d37..5bc5bef2e00a 100644
--- a/kernel/rcu/sync.c
+++ b/kernel/rcu/sync.c
@@ -22,6 +22,14 @@
 
 #include <linux/rcu_sync.h>
 #include <linux/sched.h>
+#include <linux/moduleparam.h>
+#include <linux/module.h>
+
+MODULE_ALIAS("rcusync");
+#ifdef MODULE_PARAM_PREFIX
+#undef MODULE_PARAM_PREFIX
+#endif
+#define MODULE_PARAM_PREFIX "rcusync."
 
 #ifdef CONFIG_PROVE_RCU
 #define __INIT_HELD(func)	.held = func,
@@ -29,7 +37,7 @@
 #define __INIT_HELD(func)
 #endif
 
-static const struct {
+static struct {
 	void (*sync)(void);
 	void (*call)(struct rcu_head *, void (*)(struct rcu_head *));
 	void (*wait)(void);
@@ -62,6 +70,20 @@ enum { CB_IDLE = 0, CB_PENDING, CB_REPLAY };
 
 #define	rss_lock	gp_wait.lock
 
+static bool expedited;
+module_param(expedited, bool, 0444);
+
+static int __init rcu_sync_early_init(void)
+{
+	if (expedited) {
+		gp_ops[RCU_SYNC].sync = synchronize_rcu_expedited;
+		gp_ops[RCU_SCHED_SYNC].sync = synchronize_sched_expedited;
+		gp_ops[RCU_BH_SYNC].sync = synchronize_rcu_bh_expedited;
+	}
+	return 0;
+}
+early_initcall(rcu_sync_early_init);
+
 #ifdef CONFIG_PROVE_RCU
 void rcu_sync_lockdep_assert(struct rcu_sync *rsp)
 {