From: "tip-bot2 for Frederic Weisbecker" <tip-bot2@linutronix.de>
To: linux-tip-commits@vger.kernel.org
Cc: "Paul E. McKenney" <paulmck@kernel.org>,
Frederic Weisbecker <frederic@kernel.org>,
"Peter Zijlstra (Intel)" <peterz@infradead.org>,
Ingo Molnar <mingo@kernel.org>,
stable@vger.kernel.org, x86@kernel.org,
linux-kernel@vger.kernel.org
Subject: [tip: sched/core] rcu/nocb: Trigger self-IPI on late deferred wake up before user resume
Date: Wed, 17 Feb 2021 13:17:31 -0000 [thread overview]
Message-ID: <161356785132.20312.8894338816991730514.tip-bot2@tip-bot2> (raw)
In-Reply-To: <20210131230548.32970-4-frederic@kernel.org>
The following commit has been merged into the sched/core branch of tip:
Commit-ID: f8bb5cae9616224a39cbb399de382d36ac41df10
Gitweb: https://git.kernel.org/tip/f8bb5cae9616224a39cbb399de382d36ac41df10
Author: Frederic Weisbecker <frederic@kernel.org>
AuthorDate: Mon, 01 Feb 2021 00:05:46 +01:00
Committer: Ingo Molnar <mingo@kernel.org>
CommitterDate: Wed, 17 Feb 2021 14:12:43 +01:00
rcu/nocb: Trigger self-IPI on late deferred wake up before user resume
Entering RCU idle mode may cause a deferred wake up of an RCU NOCB_GP
kthread (rcuog) to be serviced.
Unfortunately the call to rcu_user_enter() is already past the last
rescheduling opportunity before we resume to userspace or to guest mode.
We may escape there with the woken task ignored.
The ultimate resort to fix every callsites is to trigger a self-IPI
(nohz_full depends on arch to implement arch_irq_work_raise()) that will
trigger a reschedule on IRQ tail or guest exit.
Eventually every site that want a saner treatment will need to carefully
place a call to rcu_nocb_flush_deferred_wakeup() before the last explicit
need_resched() check upon resume.
Fixes: 96d3fd0d315a (rcu: Break call_rcu() deadlock involving scheduler and perf)
Reported-by: Paul E. McKenney <paulmck@kernel.org>
Signed-off-by: Frederic Weisbecker <frederic@kernel.org>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Cc: stable@vger.kernel.org
Link: https://lkml.kernel.org/r/20210131230548.32970-4-frederic@kernel.org
---
kernel/rcu/tree.c | 21 ++++++++++++++++++++-
kernel/rcu/tree.h | 2 +-
kernel/rcu/tree_plugin.h | 25 ++++++++++++++++---------
3 files changed, 37 insertions(+), 11 deletions(-)
diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
index 82838e9..4b1e5bd 100644
--- a/kernel/rcu/tree.c
+++ b/kernel/rcu/tree.c
@@ -677,6 +677,18 @@ void rcu_idle_enter(void)
EXPORT_SYMBOL_GPL(rcu_idle_enter);
#ifdef CONFIG_NO_HZ_FULL
+
+/*
+ * An empty function that will trigger a reschedule on
+ * IRQ tail once IRQs get re-enabled on userspace resume.
+ */
+static void late_wakeup_func(struct irq_work *work)
+{
+}
+
+static DEFINE_PER_CPU(struct irq_work, late_wakeup_work) =
+ IRQ_WORK_INIT(late_wakeup_func);
+
/**
* rcu_user_enter - inform RCU that we are resuming userspace.
*
@@ -694,12 +706,19 @@ noinstr void rcu_user_enter(void)
lockdep_assert_irqs_disabled();
+ /*
+ * We may be past the last rescheduling opportunity in the entry code.
+ * Trigger a self IPI that will fire and reschedule once we resume to
+ * user/guest mode.
+ */
instrumentation_begin();
- do_nocb_deferred_wakeup(rdp);
+ if (do_nocb_deferred_wakeup(rdp) && need_resched())
+ irq_work_queue(this_cpu_ptr(&late_wakeup_work));
instrumentation_end();
rcu_eqs_enter(true);
}
+
#endif /* CONFIG_NO_HZ_FULL */
/**
diff --git a/kernel/rcu/tree.h b/kernel/rcu/tree.h
index 7708ed1..9226f40 100644
--- a/kernel/rcu/tree.h
+++ b/kernel/rcu/tree.h
@@ -433,7 +433,7 @@ static bool rcu_nocb_try_bypass(struct rcu_data *rdp, struct rcu_head *rhp,
static void __call_rcu_nocb_wake(struct rcu_data *rdp, bool was_empty,
unsigned long flags);
static int rcu_nocb_need_deferred_wakeup(struct rcu_data *rdp);
-static void do_nocb_deferred_wakeup(struct rcu_data *rdp);
+static bool do_nocb_deferred_wakeup(struct rcu_data *rdp);
static void rcu_boot_init_nocb_percpu_data(struct rcu_data *rdp);
static void rcu_spawn_cpu_nocb_kthread(int cpu);
static void __init rcu_spawn_nocb_kthreads(void);
diff --git a/kernel/rcu/tree_plugin.h b/kernel/rcu/tree_plugin.h
index d5b38c2..384856e 100644
--- a/kernel/rcu/tree_plugin.h
+++ b/kernel/rcu/tree_plugin.h
@@ -1631,8 +1631,8 @@ bool rcu_is_nocb_cpu(int cpu)
* Kick the GP kthread for this NOCB group. Caller holds ->nocb_lock
* and this function releases it.
*/
-static void wake_nocb_gp(struct rcu_data *rdp, bool force,
- unsigned long flags)
+static bool wake_nocb_gp(struct rcu_data *rdp, bool force,
+ unsigned long flags)
__releases(rdp->nocb_lock)
{
bool needwake = false;
@@ -1643,7 +1643,7 @@ static void wake_nocb_gp(struct rcu_data *rdp, bool force,
trace_rcu_nocb_wake(rcu_state.name, rdp->cpu,
TPS("AlreadyAwake"));
rcu_nocb_unlock_irqrestore(rdp, flags);
- return;
+ return false;
}
del_timer(&rdp->nocb_timer);
rcu_nocb_unlock_irqrestore(rdp, flags);
@@ -1656,6 +1656,8 @@ static void wake_nocb_gp(struct rcu_data *rdp, bool force,
raw_spin_unlock_irqrestore(&rdp_gp->nocb_gp_lock, flags);
if (needwake)
wake_up_process(rdp_gp->nocb_gp_kthread);
+
+ return needwake;
}
/*
@@ -2152,20 +2154,23 @@ static int rcu_nocb_need_deferred_wakeup(struct rcu_data *rdp)
}
/* Do a deferred wakeup of rcu_nocb_kthread(). */
-static void do_nocb_deferred_wakeup_common(struct rcu_data *rdp)
+static bool do_nocb_deferred_wakeup_common(struct rcu_data *rdp)
{
unsigned long flags;
int ndw;
+ int ret;
rcu_nocb_lock_irqsave(rdp, flags);
if (!rcu_nocb_need_deferred_wakeup(rdp)) {
rcu_nocb_unlock_irqrestore(rdp, flags);
- return;
+ return false;
}
ndw = READ_ONCE(rdp->nocb_defer_wakeup);
WRITE_ONCE(rdp->nocb_defer_wakeup, RCU_NOCB_WAKE_NOT);
- wake_nocb_gp(rdp, ndw == RCU_NOCB_WAKE_FORCE, flags);
+ ret = wake_nocb_gp(rdp, ndw == RCU_NOCB_WAKE_FORCE, flags);
trace_rcu_nocb_wake(rcu_state.name, rdp->cpu, TPS("DeferredWake"));
+
+ return ret;
}
/* Do a deferred wakeup of rcu_nocb_kthread() from a timer handler. */
@@ -2181,10 +2186,11 @@ static void do_nocb_deferred_wakeup_timer(struct timer_list *t)
* This means we do an inexact common-case check. Note that if
* we miss, ->nocb_timer will eventually clean things up.
*/
-static void do_nocb_deferred_wakeup(struct rcu_data *rdp)
+static bool do_nocb_deferred_wakeup(struct rcu_data *rdp)
{
if (rcu_nocb_need_deferred_wakeup(rdp))
- do_nocb_deferred_wakeup_common(rdp);
+ return do_nocb_deferred_wakeup_common(rdp);
+ return false;
}
void rcu_nocb_flush_deferred_wakeup(void)
@@ -2523,8 +2529,9 @@ static int rcu_nocb_need_deferred_wakeup(struct rcu_data *rdp)
return false;
}
-static void do_nocb_deferred_wakeup(struct rcu_data *rdp)
+static bool do_nocb_deferred_wakeup(struct rcu_data *rdp)
{
+ return false;
}
static void rcu_spawn_cpu_nocb_kthread(int cpu)
next prev parent reply other threads:[~2021-02-17 13:19 UTC|newest]
Thread overview: 18+ messages / expand[flat|nested] mbox.gz Atom feed top
2021-01-31 23:05 [PATCH 0/5] rcu/sched: Fix ignored rescheduling after rcu_eqs_enter() v4 Frederic Weisbecker
2021-01-31 23:05 ` [PATCH 1/5] rcu: Pull deferred rcuog wake up to rcu_eqs_enter() callers Frederic Weisbecker
2021-02-10 13:53 ` [tip: sched/core] " tip-bot2 for Frederic Weisbecker
2021-02-17 13:17 ` tip-bot2 for Frederic Weisbecker
2021-01-31 23:05 ` [PATCH 2/5] rcu/nocb: Perform deferred wake up before last idle's need_resched() check Frederic Weisbecker
2021-02-08 14:45 ` Peter Zijlstra
2021-02-08 14:53 ` Frederic Weisbecker
2021-02-10 13:53 ` [tip: sched/core] " tip-bot2 for Frederic Weisbecker
2021-02-17 13:17 ` tip-bot2 for Frederic Weisbecker
2021-01-31 23:05 ` [PATCH 3/5] rcu/nocb: Trigger self-IPI on late deferred wake up before user resume Frederic Weisbecker
2021-02-10 13:53 ` [tip: sched/core] " tip-bot2 for Frederic Weisbecker
2021-02-17 13:17 ` tip-bot2 for Frederic Weisbecker [this message]
2021-01-31 23:05 ` [PATCH 4/5] entry: Explicitly flush pending rcuog wakeup before last rescheduling point Frederic Weisbecker
2021-02-10 13:53 ` [tip: sched/core] " tip-bot2 for Frederic Weisbecker
2021-02-17 13:17 ` tip-bot2 for Frederic Weisbecker
2021-01-31 23:05 ` [PATCH 5/5] entry/kvm: " Frederic Weisbecker
2021-02-10 13:53 ` [tip: sched/core] " tip-bot2 for Frederic Weisbecker
2021-02-17 13:17 ` tip-bot2 for Frederic Weisbecker
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=161356785132.20312.8894338816991730514.tip-bot2@tip-bot2 \
--to=tip-bot2@linutronix.de \
--cc=frederic@kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-tip-commits@vger.kernel.org \
--cc=mingo@kernel.org \
--cc=paulmck@kernel.org \
--cc=peterz@infradead.org \
--cc=stable@vger.kernel.org \
--cc=x86@kernel.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;
as well as URLs for NNTP newsgroup(s).