Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 2620:137:e000::1:20 as permitted sender) client-ip=2620:137:e000::1:20;
From:   "Paul E. McKenney" <paulmck@kernel.org>
To:     rcu@vger.kernel.org
Cc:     linux-kernel@vger.kernel.org, kernel-team@meta.com,
        rostedt@goodmis.org, "Paul E. McKenney" <paulmck@kernel.org>
Subject: [PATCH rcu 01/13] rcuscale: Permit blocking delays between writers
Date:   Mon, 17 Jul 2023 11:11:26 -0700
Message-Id: <20230717181138.1098063-1-paulmck@kernel.org>
In-Reply-To: <c5a593d3-abe0-40fd-92bd-28d269042aa1@paulmck-laptop>
References: <c5a593d3-abe0-40fd-92bd-28d269042aa1@paulmck-laptop>
MIME-Version: 1.0
Content-Transfer-Encoding: 8bit
Precedence: bulk

Some workloads do isolated RCU work, and this can affect operation
latencies.  This commit therefore adds a writer_holdoff_jiffies module
parameter that causes writers to block for the specified number of
jiffies between each pair of consecutive write-side operations.

Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
---
 Documentation/admin-guide/kernel-parameters.txt | 5 +++++
 kernel/rcu/rcuscale.c                           | 4 ++++
 2 files changed, 9 insertions(+)

diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt
index a1457995fd41..5ba231b786f8 100644
--- a/Documentation/admin-guide/kernel-parameters.txt
+++ b/Documentation/admin-guide/kernel-parameters.txt
@@ -4983,6 +4983,11 @@
 			in microseconds.  The default of zero says
 			no holdoff.
 
+	rcuscale.writer_holdoff_jiffies= [KNL]
+			Additional write-side holdoff between grace
+			periods, but in jiffies.  The default of zero
+			says no holdoff.
+
 	rcutorture.fqs_duration= [KNL]
 			Set duration of force_quiescent_state bursts
 			in microseconds.
diff --git a/kernel/rcu/rcuscale.c b/kernel/rcu/rcuscale.c
index d1221731c7cf..4277037e0996 100644
--- a/kernel/rcu/rcuscale.c
+++ b/kernel/rcu/rcuscale.c
@@ -93,6 +93,7 @@ torture_param(bool, shutdown, RCUSCALE_SHUTDOWN,
 	      "Shutdown at end of scalability tests.");
 torture_param(int, verbose, 1, "Enable verbose debugging printk()s");
 torture_param(int, writer_holdoff, 0, "Holdoff (us) between GPs, zero to disable");
+torture_param(int, writer_holdoff_jiffies, 0, "Holdoff (jiffies) between GPs, zero to disable");
 torture_param(int, kfree_rcu_test, 0, "Do we run a kfree_rcu() scale test?");
 torture_param(int, kfree_mult, 1, "Multiple of kfree_obj size to allocate.");
 torture_param(int, kfree_by_call_rcu, 0, "Use call_rcu() to emulate kfree_rcu()?");
@@ -414,6 +415,7 @@ rcu_scale_writer(void *arg)
 	struct rcu_head *rhp = NULL;
 	bool started = false, done = false, alldone = false;
 	u64 t;
+	DEFINE_TORTURE_RANDOM(tr);
 	u64 *wdp;
 	u64 *wdpp = writer_durations[me];
 
@@ -448,6 +450,8 @@ rcu_scale_writer(void *arg)
 	do {
 		if (writer_holdoff)
 			udelay(writer_holdoff);
+		if (writer_holdoff_jiffies)
+			schedule_timeout_idle(torture_random(&tr) % writer_holdoff_jiffies + 1);
 		wdp = &wdpp[i];
 		*wdp = ktime_get_mono_fast_ns();
 		if (gp_async) {
-- 
2.40.1