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]
Date:   Fri, 8 Jul 2022 04:25:09 +0000
From:   Joel Fernandes <joel@...lfernandes.org>
To:     "Paul E. McKenney" <paulmck@...nel.org>
Cc:     rcu@...r.kernel.org, linux-kernel@...r.kernel.org,
        rushikesh.s.kadam@...el.com, urezki@...il.com,
        neeraj.iitr10@...il.com, frederic@...nel.org, rostedt@...dmis.org,
        vineeth@...byteword.org
Subject: Re: [PATCH v2 6/8] rcuscale: Add test for using call_rcu_lazy() to
 emulate kfree_rcu()

On Sat, Jun 25, 2022 at 09:13:27PM -0700, Paul E. McKenney wrote:
> On Wed, Jun 22, 2022 at 10:51:00PM +0000, Joel Fernandes (Google) wrote:
> > Reuse the kfree_rcu() test in order to be able to compare the memory reclaiming
> > properties of call_rcu_lazy() with kfree_rcu().
> > 
> > With this test, we find similar memory footprint and time call_rcu_lazy()
> > free'ing takes compared to kfree_rcu(). Also we confirm that call_rcu_lazy()
> > can survive OOM during extremely frequent calls.
> > 
> > If we really push it, i.e. boot system with low memory and compare
> > kfree_rcu() with call_rcu_lazy(), I find that call_rcu_lazy() is more
> > resilient and is much harder to produce OOM as compared to kfree_rcu().
> 
> Another approach would be to make rcutorture's forward-progress testing
> able to use call_rcu_lazy().  This would test lazy callback flooding.
> 
> Yet another approach would be to keep one CPU idle other than a
> kthread doing call_rcu_lazy().  Of course "idle" includes redirecting
> those pesky interrupts.
> 
> It is almost certainly necessary for rcutorture to exercise the
> call_rcu_lazy() path regularly.

Currently I added a test like the following which adds a new torture type, my
thought was to stress the new code to make sure nothing crashed or hung the
kernel. That is working well except I don't exactly understand the total-gps
print showing 0, which the other print shows 1188 GPs. I'll go dig into that
tomorrow.. thanks!

The print shows
TREE11 ------- 1474 GPs (12.2833/s) [rcu_lazy: g0 f0x0 total-gps=0]
TREE11 no success message, 7 successful version messages

diff --git a/kernel/rcu/rcutorture.c b/kernel/rcu/rcutorture.c
index 7120165a9342..cc6b7392d801 100644
--- a/kernel/rcu/rcutorture.c
+++ b/kernel/rcu/rcutorture.c
@@ -872,6 +872,64 @@ static struct rcu_torture_ops tasks_rude_ops = {
 
 #endif // #else #ifdef CONFIG_TASKS_RUDE_RCU
 
+#ifdef CONFIG_RCU_LAZY
+
+/*
+ * Definitions for lazy RCU torture testing.
+ */
+unsigned long orig_jiffies_till_flush;
+
+static void rcu_sync_torture_init_lazy(void)
+{
+	rcu_sync_torture_init();
+
+	orig_jiffies_till_flush = rcu_lazy_get_jiffies_till_flush();
+	rcu_lazy_set_jiffies_till_flush(50);
+}
+
+static void rcu_lazy_cleanup(void)
+{
+	rcu_lazy_set_jiffies_till_flush(orig_jiffies_till_flush);
+}
+
+static struct rcu_torture_ops rcu_lazy_ops = {
+	.ttype			= RCU_LAZY_FLAVOR,
+	.init			= rcu_sync_torture_init_lazy,
+	.cleanup		= rcu_lazy_cleanup,
+	.readlock		= rcu_torture_read_lock,
+	.read_delay		= rcu_read_delay,
+	.readunlock		= rcu_torture_read_unlock,
+	.readlock_held		= torture_readlock_not_held,
+	.get_gp_seq		= rcu_get_gp_seq,
+	.gp_diff		= rcu_seq_diff,
+	.deferred_free		= rcu_torture_deferred_free,
+	.sync			= synchronize_rcu,
+	.exp_sync		= synchronize_rcu_expedited,
+	.get_gp_state		= get_state_synchronize_rcu,
+	.start_gp_poll		= start_poll_synchronize_rcu,
+	.poll_gp_state		= poll_state_synchronize_rcu,
+	.cond_sync		= cond_synchronize_rcu,
+	.call			= call_rcu_lazy,
+	.cb_barrier		= rcu_barrier,
+	.fqs			= rcu_force_quiescent_state,
+	.stats			= NULL,
+	.gp_kthread_dbg		= show_rcu_gp_kthreads,
+	.check_boost_failed	= rcu_check_boost_fail,
+	.stall_dur		= rcu_jiffies_till_stall_check,
+	.irq_capable		= 1,
+	.can_boost		= IS_ENABLED(CONFIG_RCU_BOOST),
+	.extendables		= RCUTORTURE_MAX_EXTEND,
+	.name			= "rcu_lazy"
+};
+
+#define LAZY_OPS &rcu_lazy_ops,
+
+#else // #ifdef CONFIG_RCU_LAZY
+
+#define LAZY_OPS
+
+#endif // #else #ifdef CONFIG_RCU_LAZY
+
 
 #ifdef CONFIG_TASKS_TRACE_RCU
 
@@ -3145,7 +3203,7 @@ rcu_torture_init(void)
 	unsigned long gp_seq = 0;
 	static struct rcu_torture_ops *torture_ops[] = {
 		&rcu_ops, &rcu_busted_ops, &srcu_ops, &srcud_ops, &busted_srcud_ops,
-		TASKS_OPS TASKS_RUDE_OPS TASKS_TRACING_OPS
+		TASKS_OPS TASKS_RUDE_OPS TASKS_TRACING_OPS LAZY_OPS
 		&trivial_ops,
 	};
 
diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TREE11 b/tools/testing/selftests/rcutorture/configs/rcu/TREE11
new file mode 100644
index 000000000000..436013f3e015
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/configs/rcu/TREE11
@@ -0,0 +1,18 @@
+CONFIG_SMP=y
+CONFIG_PREEMPT_NONE=n
+CONFIG_PREEMPT_VOLUNTARY=n
+CONFIG_PREEMPT=y
+#CHECK#CONFIG_PREEMPT_RCU=y
+CONFIG_HZ_PERIODIC=n
+CONFIG_NO_HZ_IDLE=y
+CONFIG_NO_HZ_FULL=n
+CONFIG_RCU_TRACE=y
+CONFIG_HOTPLUG_CPU=y
+CONFIG_MAXSMP=y
+CONFIG_CPUMASK_OFFSTACK=y
+CONFIG_RCU_NOCB_CPU=y
+CONFIG_DEBUG_LOCK_ALLOC=n
+CONFIG_RCU_BOOST=n
+CONFIG_DEBUG_OBJECTS_RCU_HEAD=n
+CONFIG_RCU_EXPERT=y
+CONFIG_RCU_LAZY=y
diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TREE11.boot b/tools/testing/selftests/rcutorture/configs/rcu/TREE11.boot
new file mode 100644
index 000000000000..9b6f720d4ccd
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/configs/rcu/TREE11.boot
@@ -0,0 +1,8 @@
+maxcpus=8 nr_cpus=43
+rcutree.gp_preinit_delay=3
+rcutree.gp_init_delay=3
+rcutree.gp_cleanup_delay=3
+rcu_nocbs=0-7
+rcutorture.torture_type=rcu_lazy
+rcutorture.nocbs_nthreads=8
+rcutorture.fwd_progress=0
-- 
2.37.0.rc0.161.g10f37bed90-goog

Powered by blists - more mailing lists

Powered by Openwall GNU/*/Linux Powered by OpenVZ