| 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
| ||
|
Date: Fri, 08 Aug 2008 15:46:58 +0200
From: Peter Zijlstra <peterz@...radead.org>
To: Andrew Morton <akpm@...ux-foundation.org>
Cc: torvalds@...ux-foundation.org, mingo@...e.hu, tglx@...utronix.de,
marcin.slusarz@...il.com, linux-kernel@...r.kernel.org,
David Miller <davem@...emloft.net>,
Steven Rostedt <rostedt@...dmis.org>
Subject: Re: [PATCH 0/2] printk vs rq->lock and xtime lock
/me tatoos on forehead: 'quilt refresh' before posting!!
On Fri, 2008-08-08 at 15:30 +0200, Peter Zijlstra wrote:
> On Mon, 2008-03-24 at 11:57 -0700, Andrew Morton wrote:
> > On Mon, 24 Mar 2008 19:15:47 +0100
> > Peter Zijlstra <a.p.zijlstra@...llo.nl> wrote:
> >
> > > How about I use the lockdep infrastructure to check if printk() is
> > > invoked whole holding either xtime or rq lock, and then avoid calling
> > > wake_up_klogd(). That way, we at least get sane debug output when the
> > > lock debugging infrastructure is enabled?
> >
> > The core problem seems to be that printk shouldn't be calling wake_up().
> > Can we fix that?
> >
> > I expect it would be acceptable to do it from the timer interrupt instead.
> > For NOHZ kernels a poll when we enter the idle loop would also be needed.
>
> Something along the lines of the below patch?
>
> > But does that cover everything? Is it possible for a CPU to run 100% busy
> > while not receiving timer interrupts? I guess so. To receive no
> > interrupts at all? Also possible.
>
> local_irq_disable(); while (1);
>
> But I guess you have more pressing issues when that happens..
>
> ---
Subject: printk: robustify printk wakeup behaviour
The klogd wakeup in the printk patch can cause deadlocks when holding the
rq->lock and or xtime_lock for writing.
Avoid doing the wakeup under certain conditions and delay it to the next jiffy
tick.
Signed-off-by: Peter Zijlstra <a.p.zijlstra@...llo.nl>
---
include/linux/kernel.h | 4 +++
include/linux/seqlock.h | 5 ++++
kernel/printk.c | 48 ++++++++++++++++++++++++++++++++++++++++++++++-
kernel/time/tick-sched.c | 2 -
kernel/timer.c | 1
5 files changed, 58 insertions(+), 2 deletions(-)
Index: linux-2.6/include/linux/kernel.h
===================================================================
--- linux-2.6.orig/include/linux/kernel.h
+++ linux-2.6/include/linux/kernel.h
@@ -200,6 +200,8 @@ extern struct ratelimit_state printk_rat
extern int printk_ratelimit(void);
extern bool printk_timed_ratelimit(unsigned long *caller_jiffies,
unsigned int interval_msec);
+extern void printk_tick(void);
+extern int printk_needs_cpu(int);
#else
static inline int vprintk(const char *s, va_list args)
__attribute__ ((format (printf, 1, 0)));
@@ -211,6 +213,8 @@ static inline int printk_ratelimit(void)
static inline bool printk_timed_ratelimit(unsigned long *caller_jiffies, \
unsigned int interval_msec) \
{ return false; }
+static inline void printk_tick(void) { }
+static inline int printk_needs_cpu(int) { return 0; }
#endif
extern void asmlinkage __attribute__((format(printf, 1, 2)))
Index: linux-2.6/include/linux/seqlock.h
===================================================================
--- linux-2.6.orig/include/linux/seqlock.h
+++ linux-2.6/include/linux/seqlock.h
@@ -71,6 +71,11 @@ static inline void write_sequnlock(seqlo
spin_unlock(&sl->lock);
}
+static inline int seq_is_writelocked(seqlock_t *sl)
+{
+ return spin_is_locked(&sl->lock);
+}
+
static inline int write_tryseqlock(seqlock_t *sl)
{
int ret = spin_trylock(&sl->lock);
Index: linux-2.6/kernel/printk.c
===================================================================
--- linux-2.6.orig/kernel/printk.c
+++ linux-2.6/kernel/printk.c
@@ -32,6 +32,8 @@
#include <linux/security.h>
#include <linux/bootmem.h>
#include <linux/syscalls.h>
+#include <linux/cpumask.h>
+#include <linux/sched.h>
#include <asm/uaccess.h>
@@ -982,12 +984,56 @@ int is_console_locked(void)
return console_locked;
}
-void wake_up_klogd(void)
+static int printk_pending;
+
+void __wake_up_klogd(void)
{
+ if (printk_pending)
+ printk_pending = 0;
+
if (!oops_in_progress && waitqueue_active(&log_wait))
wake_up_interruptible(&log_wait);
}
+int printk_needs_cpu(int cpu)
+{
+ if (!printk_pending)
+ return 0;
+
+ /*
+ * Stop the last awake CPU from entering NOHZ state when there still
+ * is a klogd to kick.
+ */
+ return (cpus_weight(cpu_online_map) - cpus_weight(nohz_cpu_mask)) == 1;
+}
+
+void printk_tick(void)
+{
+ if (unlikely(printk_pending))
+ __wake_up_klogd();
+}
+
+static int printk_do_wakeup(void)
+{
+ if (irqs_disabled())
+ return 0;
+
+#ifdef CONFIG_HRTICK
+ if (seq_is_writelocked(&xtime_lock))
+ return 0;
+#endif
+
+ return 1;
+}
+
+void wake_up_klogd(void)
+{
+ if (printk_do_wakeup())
+ __wake_up_klogd();
+ else
+ printk_pending = 1;
+}
+
/**
* release_console_sem - unlock the console system
*
Index: linux-2.6/kernel/time/tick-sched.c
===================================================================
--- linux-2.6.orig/kernel/time/tick-sched.c
+++ linux-2.6/kernel/time/tick-sched.c
@@ -255,7 +255,7 @@ void tick_nohz_stop_sched_tick(int inidl
next_jiffies = get_next_timer_interrupt(last_jiffies);
delta_jiffies = next_jiffies - last_jiffies;
- if (rcu_needs_cpu(cpu))
+ if (rcu_needs_cpu(cpu) || printk_needs_cpu(cpu))
delta_jiffies = 1;
/*
* Do not stop the tick, if we are only one off
Index: linux-2.6/kernel/timer.c
===================================================================
--- linux-2.6.orig/kernel/timer.c
+++ linux-2.6/kernel/timer.c
@@ -978,6 +978,7 @@ void update_process_times(int user_tick)
run_local_timers();
if (rcu_pending(cpu))
rcu_check_callbacks(cpu, user_tick);
+ printk_tick();
scheduler_tick();
run_posix_cpu_timers(p);
}
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/
Powered by blists - more mailing lists