mirror of https://lore.kernel.org/lkml/
 help / color / mirror / Atom feed
From: "Joel Fernandes (Google)" <joel@joelfernandes.org>
To: linux-kernel@vger.kernel.org
Cc: "Joel Fernandes (Google)" <joel@joelfernandes.org>,
	paulmck@kernel.org,
	Rushikesh S Kadam <rushikesh.s.kadam@intel.com>,
	"Uladzislau Rezki (Sony)" <urezki@gmail.com>,
	Neeraj upadhyay <neeraj.iitr10@gmail.com>,
	Frederic Weisbecker <frederic@kernel.org>,
	Steven Rostedt <rostedt@goodmis.org>, rcu <rcu@vger.kernel.org>,
	vineeth@bitbyteword.org
Subject: [PATCH v4 06/14] debug: Toggle lazy at runtime and change flush jiffies
Date: Fri, 19 Aug 2022 20:48:49 +0000	[thread overview]
Message-ID: <20220819204857.3066329-7-joel@joelfernandes.org> (raw)
In-Reply-To: <20220819204857.3066329-1-joel@joelfernandes.org>

Enable/Disable this feature by writing 1 or 0 /proc/sys/vm/rcu_lazy.

Change value of /proc/sys/vm/rcu_lazy_jiffies to change max duration before
flush.

Do not merge, only for debug for reviewers.

Signed-off-by: Joel Fernandes (Google) <joel@joelfernandes.org>
---
 include/linux/sched/sysctl.h |  3 +++
 kernel/rcu/tree_nocb.h       |  9 +++++++++
 kernel/sysctl.c              | 17 +++++++++++++++++
 3 files changed, 29 insertions(+)

diff --git a/include/linux/sched/sysctl.h b/include/linux/sched/sysctl.h
index 2cd928f15df6..54610f9cd962 100644
--- a/include/linux/sched/sysctl.h
+++ b/include/linux/sched/sysctl.h
@@ -14,6 +14,9 @@ extern unsigned long sysctl_hung_task_timeout_secs;
 enum { sysctl_hung_task_timeout_secs = 0 };
 #endif
 
+extern unsigned int sysctl_rcu_lazy;
+extern unsigned int sysctl_rcu_lazy_jiffies;
+
 enum sched_tunable_scaling {
 	SCHED_TUNABLESCALING_NONE,
 	SCHED_TUNABLESCALING_LOG,
diff --git a/kernel/rcu/tree_nocb.h b/kernel/rcu/tree_nocb.h
index edb4e59dbf38..16621b32de46 100644
--- a/kernel/rcu/tree_nocb.h
+++ b/kernel/rcu/tree_nocb.h
@@ -266,6 +266,9 @@ static bool wake_nocb_gp(struct rcu_data *rdp, bool force)
 #define LAZY_FLUSH_JIFFIES (10 * HZ)
 unsigned long jiffies_till_flush = LAZY_FLUSH_JIFFIES;
 
+unsigned int sysctl_rcu_lazy_jiffies = LAZY_FLUSH_JIFFIES;
+unsigned int sysctl_rcu_lazy = 1;
+
 #ifdef CONFIG_RCU_LAZY
 // To be called only from test code.
 void rcu_lazy_set_jiffies_till_flush(unsigned long jif)
@@ -292,6 +295,9 @@ static void wake_nocb_gp_defer(struct rcu_data *rdp, int waketype,
 	struct rcu_data *rdp_gp = rdp->nocb_gp_rdp;
 	unsigned long mod_jif = 0;
 
+	/* debug: not for merge */
+	rcu_lazy_set_jiffies_till_flush(sysctl_rcu_lazy_jiffies);
+
 	raw_spin_lock_irqsave(&rdp_gp->nocb_gp_lock, flags);
 
 	/*
@@ -697,6 +703,9 @@ static void nocb_gp_wait(struct rcu_data *my_rdp)
 	unsigned long wait_gp_seq = 0; // Suppress "use uninitialized" warning.
 	bool wasempty = false;
 
+	/* debug: not for merge */
+	rcu_lazy_set_jiffies_till_flush(sysctl_rcu_lazy_jiffies);
+
 	/*
 	 * Each pass through the following loop checks for CBs and for the
 	 * nearest grace period (if any) to wait for next.  The CB kthreads
diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index b00f92df0af5..bbe25d635dc0 100644
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -2450,6 +2450,23 @@ static struct ctl_table vm_table[] = {
 		.extra2		= SYSCTL_ONE,
 	},
 #endif
+#ifdef CONFIG_RCU_LAZY
+	{
+		.procname	= "rcu_lazy",
+		.data		= &sysctl_rcu_lazy,
+		.maxlen		= sizeof(unsigned int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec,
+	},
+	{
+		.procname	= "rcu_lazy_jiffies",
+		.data		= &sysctl_rcu_lazy_jiffies,
+		.maxlen		= sizeof(unsigned int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec,
+	},
+#endif
+
 	{ }
 };
 
-- 
2.37.2.609.g9ff673ca1a-goog


  parent reply	other threads:[~2022-08-19 20:49 UTC|newest]

Thread overview: 54+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2022-08-19 20:48 [PATCH v4 00/14] Implement call_rcu_lazy() and miscellaneous fixes Joel Fernandes (Google)
2022-08-19 20:48 ` [PATCH v4 01/14] rcu: Introduce call_rcu_lazy() API implementation Joel Fernandes (Google)
2022-08-19 20:48 ` [PATCH v4 02/14] rcu: shrinker for lazy rcu Joel Fernandes (Google)
2022-08-19 20:48 ` [PATCH v4 03/14] rcuscale: Add laziness and kfree tests Joel Fernandes (Google)
2022-08-19 20:48 ` [PATCH v4 04/14] fs: Move call_rcu() to call_rcu_lazy() in some paths Joel Fernandes (Google)
2022-08-19 20:48 ` [PATCH v4 05/14] rcutorture: Add test code for call_rcu_lazy() Joel Fernandes (Google)
2022-08-19 20:48 ` Joel Fernandes (Google) [this message]
2022-08-19 20:48 ` [PATCH v4 07/14] cred: Move call_rcu() to call_rcu_lazy() Joel Fernandes (Google)
2022-08-19 20:48 ` [PATCH v4 08/14] security: " Joel Fernandes (Google)
2022-08-19 20:48 ` [PATCH v4 09/14] net/core: " Joel Fernandes (Google)
2022-08-19 20:48 ` [PATCH v4 10/14] kernel: Move various core kernel usages " Joel Fernandes (Google)
2022-08-19 20:48 ` [PATCH v4 11/14] lib: Move call_rcu() " Joel Fernandes (Google)
2022-08-19 20:48 ` [PATCH v4 12/14] i915: " Joel Fernandes (Google)
2022-08-19 20:48 ` [PATCH v4 13/14] fork: Move thread_stack_free_rcu to call_rcu_lazy Joel Fernandes (Google)
2022-08-19 20:48 ` [PATCH v4 14/14] rcu/tree: Move trace_rcu_callback() before bypassing Joel Fernandes (Google)
2022-08-29 13:40 ` [PATCH v4 00/14] Implement call_rcu_lazy() and miscellaneous fixes Frederic Weisbecker
2022-08-29 16:45   ` Joel Fernandes
2022-08-29 19:46     ` Frederic Weisbecker
2022-08-29 20:31       ` Paul E. McKenney
2022-08-29 20:54         ` Joel Fernandes
2022-08-30 10:50         ` Frederic Weisbecker
2022-08-30 11:47           ` Paul E. McKenney
2022-08-29 20:36       ` Joel Fernandes
2022-08-29 20:42         ` Paul E. McKenney
2022-08-29 20:48           ` Joel Fernandes
2022-08-30 10:57             ` Frederic Weisbecker
2022-08-30 10:53           ` Frederic Weisbecker
2022-08-30 11:43             ` Paul E. McKenney
2022-08-30 16:03               ` Frederic Weisbecker
2022-08-30 16:22                 ` Frederic Weisbecker
2022-08-30 16:44                   ` Uladzislau Rezki
2022-08-30 18:53                     ` Joel Fernandes
2022-09-01 11:29                     ` Frederic Weisbecker
2022-09-01 11:59                       ` Uladzislau Rezki
2022-09-01 14:41                         ` Paul E. McKenney
2022-09-01 15:30                           ` Frederic Weisbecker
2022-09-01 16:11                             ` Joel Fernandes
2022-09-01 16:52                             ` Paul E. McKenney
2022-09-01 15:13                         ` Frederic Weisbecker
2022-09-01 16:07                           ` Joel Fernandes
2022-08-30 16:46                   ` Paul E. McKenney
2022-08-31 15:26                     ` Frederic Weisbecker
2022-09-01 14:39                       ` Paul E. McKenney
2022-09-01 14:58                         ` Frederic Weisbecker
2022-09-01 16:07                           ` Joel Fernandes
2022-09-01 16:49                             ` Paul E. McKenney
2022-09-01 18:28                               ` Frederic Weisbecker
2022-09-01 20:36                                 ` Paul E. McKenney
2022-08-30 18:46                   ` Joel Fernandes
2022-08-30 10:26         ` Frederic Weisbecker
2022-08-30 18:40           ` Joel Fernandes
2022-08-29 19:57     ` Paul E. McKenney
2022-08-30 10:43       ` Frederic Weisbecker
2022-08-30 12:08         ` Paul E. McKenney

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=20220819204857.3066329-7-joel@joelfernandes.org \
    --to=joel@joelfernandes.org \
    --cc=frederic@kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=neeraj.iitr10@gmail.com \
    --cc=paulmck@kernel.org \
    --cc=rcu@vger.kernel.org \
    --cc=rostedt@goodmis.org \
    --cc=rushikesh.s.kadam@intel.com \
    --cc=urezki@gmail.com \
    --cc=vineeth@bitbyteword.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

all inboxes | Powered by JetHome®