From: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
To: Steven Rostedt <rostedt@goodmis.org>
Cc: linux-kernel@vger.kernel.org, linux-rt-users@vger.kernel.org,
Carsten Emde <C.Emde@osadl.org>,
Thomas Gleixner <tglx@linutronix.de>,
Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Subject: [PATCH 05/16] softirq: Adapt NOHZ softirq pending check to new RT scheme
Date: Wed, 13 Feb 2013 17:12:00 +0100 [thread overview]
Message-ID: <1360771932-27150-6-git-send-email-bigeasy@linutronix.de> (raw)
In-Reply-To: <1360771932-27150-1-git-send-email-bigeasy@linutronix.de>
From: Thomas Gleixner <tglx@linutronix.de>
We can't rely on ksoftirqd anymore and we need to check the tasks
which run a particular softirq and if such a task is pi blocked ignore
the other pending bits of that task as well.
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
---
kernel/softirq.c | 68 +++++++++++++++++++++++++++++++++++++++++-------------
1 file changed, 52 insertions(+), 16 deletions(-)
diff --git a/kernel/softirq.c b/kernel/softirq.c
index 3f7b3fb..66999ad 100644
--- a/kernel/softirq.c
+++ b/kernel/softirq.c
@@ -65,45 +65,75 @@ char *softirq_to_name[NR_SOFTIRQS] = {
#ifdef CONFIG_NO_HZ
# ifdef CONFIG_PREEMPT_RT_FULL
+
+struct softirq_runner {
+ struct task_struct *runner[NR_SOFTIRQS];
+};
+
+static DEFINE_PER_CPU(struct softirq_runner, softirq_runners);
+
+static inline void softirq_set_runner(unsigned int sirq)
+{
+ struct softirq_runner *sr = &__get_cpu_var(softirq_runners);
+
+ sr->runner[sirq] = current;
+}
+
+static inline void softirq_clr_runner(unsigned int sirq)
+{
+ struct softirq_runner *sr = &__get_cpu_var(softirq_runners);
+
+ sr->runner[sirq] = NULL;
+}
+
/*
- * On preempt-rt a softirq might be blocked on a lock. There might be
- * no other runnable task on this CPU because the lock owner runs on
- * some other CPU. So we have to go into idle with the pending bit
- * set. Therefor we need to check this otherwise we warn about false
- * positives which confuses users and defeats the whole purpose of
- * this test.
+ * On preempt-rt a softirq running context might be blocked on a
+ * lock. There might be no other runnable task on this CPU because the
+ * lock owner runs on some other CPU. So we have to go into idle with
+ * the pending bit set. Therefor we need to check this otherwise we
+ * warn about false positives which confuses users and defeats the
+ * whole purpose of this test.
*
* This code is called with interrupts disabled.
*/
void softirq_check_pending_idle(void)
{
static int rate_limit;
- u32 warnpending = 0, pending = local_softirq_pending();
+ struct softirq_runner *sr = &__get_cpu_var(softirq_runners);
+ u32 warnpending, pending = local_softirq_pending();
if (rate_limit >= 10)
return;
- if (pending) {
+ warnpending = pending;
+
+ while (pending) {
struct task_struct *tsk;
+ int i = __ffs(pending);
- tsk = __get_cpu_var(ksoftirqd);
+ pending &= ~(1 << i);
+
+ tsk = sr->runner[i];
/*
* The wakeup code in rtmutex.c wakes up the task
* _before_ it sets pi_blocked_on to NULL under
* tsk->pi_lock. So we need to check for both: state
* and pi_blocked_on.
*/
- raw_spin_lock(&tsk->pi_lock);
-
- if (!tsk->pi_blocked_on && !(tsk->state == TASK_RUNNING))
- warnpending = 1;
-
- raw_spin_unlock(&tsk->pi_lock);
+ if (tsk) {
+ raw_spin_lock(&tsk->pi_lock);
+ if (tsk->pi_blocked_on || tsk->state == TASK_RUNNING) {
+ /* Clear all bits pending in that task */
+ warnpending &= ~(tsk->softirqs_raised);
+ warnpending &= ~(1 << i);
+ }
+ raw_spin_unlock(&tsk->pi_lock);
+ }
}
if (warnpending) {
printk(KERN_ERR "NOHZ: local_softirq_pending %02x\n",
- pending);
+ warnpending);
rate_limit++;
}
}
@@ -122,6 +152,10 @@ void softirq_check_pending_idle(void)
}
}
# endif
+
+#else /* !NO_HZ */
+static inline void softirq_set_runner(unsigned int sirq) { }
+static inline void softirq_clr_runner(unsigned int sirq) { }
#endif
/*
@@ -469,6 +503,7 @@ static void do_current_softirqs(int need_rcu_bh_qs)
*/
lock_softirq(i);
local_irq_disable();
+ softirq_set_runner(i);
/*
* Check with the local_softirq_pending() bits,
* whether we need to process this still or if someone
@@ -479,6 +514,7 @@ static void do_current_softirqs(int need_rcu_bh_qs)
set_softirq_pending(pending & ~mask);
do_single_softirq(i, need_rcu_bh_qs);
}
+ softirq_clr_runner(i);
unlock_softirq(i);
WARN_ON(current->softirq_nestcnt != 1);
}
--
1.7.10.4
next prev parent reply other threads:[~2013-02-13 16:12 UTC|newest]
Thread overview: 28+ messages / expand[flat|nested] mbox.gz Atom feed top
2013-02-13 16:11 [PREEMPT RT] SLUB and split softirq lock for v3.2-rt Sebastian Andrzej Siewior
2013-02-13 16:11 ` [PATCH 01/16] softirq: Make serving softirqs a task flag Sebastian Andrzej Siewior
2013-02-13 16:11 ` [PATCH 02/16] softirq: Split handling function Sebastian Andrzej Siewior
2013-02-13 16:11 ` [PATCH 03/16] softirq: Split softirq locks Sebastian Andrzej Siewior
2013-02-13 16:11 ` [PATCH 04/16] rcu: rcutiny: Prevent RCU stall Sebastian Andrzej Siewior
2013-02-16 20:59 ` Paul E. McKenney
2013-02-18 15:02 ` Steven Rostedt
2013-02-13 16:12 ` Sebastian Andrzej Siewior [this message]
2013-02-13 16:12 ` [PATCH 06/16] softirq: Add more debugging Sebastian Andrzej Siewior
2013-02-13 16:12 ` [PATCH 07/16] softirq: Fix nohz pending issue for real Sebastian Andrzej Siewior
2013-02-13 16:12 ` [PATCH 08/16] net: Use local_bh_disable in netif_rx_ni() Sebastian Andrzej Siewior
2013-02-13 16:12 ` [PATCH 09/16] FIX [1/2] slub: Do not dereference NULL pointer in node_match Sebastian Andrzej Siewior
2013-02-13 16:12 ` [PATCH 10/16] FIX [2/2] slub: Tid must be retrieved from the percpu area of the current processor Sebastian Andrzej Siewior
2013-02-13 16:12 ` [PATCH 11/16] slub: Use correct cpu_slab on dead cpu Sebastian Andrzej Siewior
2013-02-13 16:12 ` [PATCH 12/16] smp: introduce a generic on_each_cpu_mask() function Sebastian Andrzej Siewior
2013-02-13 16:12 ` [PATCH 13/16] smp: add func to IPI cpus based on parameter func Sebastian Andrzej Siewior
2013-02-13 16:12 ` [PATCH 14/16] slub: only IPI CPUs that have per cpu obj to flush Sebastian Andrzej Siewior
2013-02-13 16:12 ` [PATCH 15/16] mm: Enable SLUB for RT Sebastian Andrzej Siewior
2013-02-13 16:12 ` [PATCH 16/16] slub: Enable irqs for __GFP_WAIT Sebastian Andrzej Siewior
2013-02-13 17:24 ` [PREEMPT RT] SLUB and split softirq lock for v3.2-rt Steven Rostedt
2013-02-13 17:41 ` Thomas Gleixner
2013-02-19 1:54 ` Li Zefan
2013-02-19 1:56 ` Li Zefan
2013-02-19 4:06 ` Steven Rostedt
2013-02-19 6:17 ` Mike Galbraith
2013-04-24 2:36 ` Steven Rostedt
2013-04-24 8:11 ` Sebastian Andrzej Siewior
2013-04-24 15:45 ` Steven Rostedt
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=1360771932-27150-6-git-send-email-bigeasy@linutronix.de \
--to=bigeasy@linutronix.de \
--cc=C.Emde@osadl.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-rt-users@vger.kernel.org \
--cc=rostedt@goodmis.org \
--cc=tglx@linutronix.de \
/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