42a0bb3f71
printk() takes some locks and could not be used a safe way in NMI
context.
The chance of a deadlock is real especially when printing stacks from
all CPUs. This particular problem has been addressed on x86 by the
commit a9edc88093 ("x86/nmi: Perform a safe NMI stack trace on all
CPUs").
The patchset brings two big advantages. First, it makes the NMI
backtraces safe on all architectures for free. Second, it makes all NMI
messages almost safe on all architectures (the temporary buffer is
limited. We still should keep the number of messages in NMI context at
minimum).
Note that there already are several messages printed in NMI context:
WARN_ON(in_nmi()), BUG_ON(in_nmi()), anything being printed out from MCE
handlers. These are not easy to avoid.
This patch reuses most of the code and makes it generic. It is useful
for all messages and architectures that support NMI.
The alternative printk_func is set when entering and is reseted when
leaving NMI context. It queues IRQ work to copy the messages into the
main ring buffer in a safe context.
__printk_nmi_flush() copies all available messages and reset the buffer.
Then we could use a simple cmpxchg operations to get synchronized with
writers. There is also used a spinlock to get synchronized with other
flushers.
We do not longer use seq_buf because it depends on external lock. It
would be hard to make all supported operations safe for a lockless use.
It would be confusing and error prone to make only some operations safe.
The code is put into separate printk/nmi.c as suggested by Steven
Rostedt. It needs a per-CPU buffer and is compiled only on
architectures that call nmi_enter(). This is achieved by the new
HAVE_NMI Kconfig flag.
The are MN10300 and Xtensa architectures. We need to clean up NMI
handling there first. Let's do it separately.
The patch is heavily based on the draft from Peter Zijlstra, see
https://lkml.org/lkml/2015/6/10/327
[arnd@arndb.de: printk-nmi: use %zu format string for size_t]
[akpm@linux-foundation.org: min_t->min - all types are size_t here]
Signed-off-by: Petr Mladek <pmladek@suse.com>
Suggested-by: Peter Zijlstra <peterz@infradead.org>
Suggested-by: Steven Rostedt <rostedt@goodmis.org>
Cc: Jan Kara <jack@suse.cz>
Acked-by: Russell King <rmk+kernel@arm.linux.org.uk> [arm part]
Cc: Daniel Thompson <daniel.thompson@linaro.org>
Cc: Jiri Kosina <jkosina@suse.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Ralf Baechle <ralf@linux-mips.org>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Martin Schwidefsky <schwidefsky@de.ibm.com>
Cc: David Miller <davem@davemloft.net>
Cc: Daniel Thompson <daniel.thompson@linaro.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
85 lines
1.8 KiB
C
85 lines
1.8 KiB
C
#ifndef LINUX_HARDIRQ_H
|
|
#define LINUX_HARDIRQ_H
|
|
|
|
#include <linux/preempt.h>
|
|
#include <linux/lockdep.h>
|
|
#include <linux/ftrace_irq.h>
|
|
#include <linux/vtime.h>
|
|
#include <asm/hardirq.h>
|
|
|
|
|
|
extern void synchronize_irq(unsigned int irq);
|
|
extern bool synchronize_hardirq(unsigned int irq);
|
|
|
|
#if defined(CONFIG_TINY_RCU)
|
|
|
|
static inline void rcu_nmi_enter(void)
|
|
{
|
|
}
|
|
|
|
static inline void rcu_nmi_exit(void)
|
|
{
|
|
}
|
|
|
|
#else
|
|
extern void rcu_nmi_enter(void);
|
|
extern void rcu_nmi_exit(void);
|
|
#endif
|
|
|
|
/*
|
|
* It is safe to do non-atomic ops on ->hardirq_context,
|
|
* because NMI handlers may not preempt and the ops are
|
|
* always balanced, so the interrupted value of ->hardirq_context
|
|
* will always be restored.
|
|
*/
|
|
#define __irq_enter() \
|
|
do { \
|
|
account_irq_enter_time(current); \
|
|
preempt_count_add(HARDIRQ_OFFSET); \
|
|
trace_hardirq_enter(); \
|
|
} while (0)
|
|
|
|
/*
|
|
* Enter irq context (on NO_HZ, update jiffies):
|
|
*/
|
|
extern void irq_enter(void);
|
|
|
|
/*
|
|
* Exit irq context without processing softirqs:
|
|
*/
|
|
#define __irq_exit() \
|
|
do { \
|
|
trace_hardirq_exit(); \
|
|
account_irq_exit_time(current); \
|
|
preempt_count_sub(HARDIRQ_OFFSET); \
|
|
} while (0)
|
|
|
|
/*
|
|
* Exit irq context and process softirqs if needed:
|
|
*/
|
|
extern void irq_exit(void);
|
|
|
|
#define nmi_enter() \
|
|
do { \
|
|
printk_nmi_enter(); \
|
|
lockdep_off(); \
|
|
ftrace_nmi_enter(); \
|
|
BUG_ON(in_nmi()); \
|
|
preempt_count_add(NMI_OFFSET + HARDIRQ_OFFSET); \
|
|
rcu_nmi_enter(); \
|
|
trace_hardirq_enter(); \
|
|
} while (0)
|
|
|
|
#define nmi_exit() \
|
|
do { \
|
|
trace_hardirq_exit(); \
|
|
rcu_nmi_exit(); \
|
|
BUG_ON(!in_nmi()); \
|
|
preempt_count_sub(NMI_OFFSET + HARDIRQ_OFFSET); \
|
|
ftrace_nmi_exit(); \
|
|
lockdep_on(); \
|
|
printk_nmi_exit(); \
|
|
} while (0)
|
|
|
|
#endif /* LINUX_HARDIRQ_H */
|