Commit 719f6a70 authored by Petr Mladek's avatar Petr Mladek
Browse files

printk: Use the main logbuf in NMI when logbuf_lock is available

The commit 42a0bb3f ("printk/nmi: generic solution for safe
printk in NMI") caused that printk stores messages into a temporary
buffer in NMI context.

The buffer is per-CPU and therefore the size is rather limited.
It works quite well for NMI backtraces. But there are longer logs
that might get printed in NMI context, for example, lockdep
warnings, ftrace_dump_on_oops.

The temporary buffer is used to avoid deadlocks caused by
logbuf_lock. Also it is needed to avoid races with the other
temporary buffer that is used when PRINTK_SAFE_CONTEXT is entered.
But the main buffer can be used in NMI if the lock is available
and we did not interrupt PRINTK_SAFE_CONTEXT.

The lock is checked using raw_spin_is_locked(). It might cause
false negatives when the lock is taken on another CPU and
this CPU is in the safe context from other reasons. Note that
the safe context is used also to get console semaphore or when
calling console drivers. For this reason, we do the check in
printk_nmi_enter(). It makes the handling consistent for
the entire NMI handler and avoids reshuffling of the messages.

The patch also defines special printk context that allows
to use printk_deferred() in NMI. Note that we could not flush
the messages to the consoles because console drivers might use
many other internal locks.

The newly created vprintk_deferred() disables the preemption
only around the irq work handling. It is needed there to keep
the consistency between the two per-CPU variables. But there
is no reason to disable preemption around vprintk_emit().

Finally, the patch puts back explicit serialization of the NMI
backtraces from different CPUs. It was removed by the
commit a9edc880 ("x86/nmi: Perform a safe
NMI stack trace on all CPUs"). It was not needed because
the flushing of the temporary per-CPU buffers was serialized.


Cc: Steven Rostedt <>
Cc: Andrew Morton <>
Cc: Peter Zijlstra <>
Cc: Russell King <>
Cc: Daniel Thompson <>
Cc: Ingo Molnar <>
Cc: Thomas Gleixner <>
Cc: Chris Metcalf <>
Suggested-by: default avatarSergey Senozhatsky <>
Acked-by: default avatarSergey Senozhatsky <>
Signed-off-by: default avatarPetr Mladek <>
parent 9c35baf6
......@@ -18,12 +18,14 @@
#define PRINTK_SAFE_CONTEXT_MASK 0x7fffffff
#define PRINTK_NMI_CONTEXT_MASK 0x80000000
#define PRINTK_SAFE_CONTEXT_MASK 0x3fffffff
#define PRINTK_NMI_CONTEXT_MASK 0x80000000
extern raw_spinlock_t logbuf_lock;
__printf(1, 0) int vprintk_default(const char *fmt, va_list args);
__printf(1, 0) int vprintk_deferred(const char *fmt, va_list args);
__printf(1, 0) int vprintk_func(const char *fmt, va_list args);
void __printk_safe_enter(void);
void __printk_safe_exit(void);
......@@ -2722,16 +2722,13 @@ void wake_up_klogd(void)
int printk_deferred(const char *fmt, ...)
int vprintk_deferred(const char *fmt, va_list args)
va_list args;
int r;
va_start(args, fmt);
r = vprintk_emit(0, LOGLEVEL_SCHED, NULL, 0, fmt, args);
__this_cpu_or(printk_pending, PRINTK_PENDING_OUTPUT);
......@@ -2739,6 +2736,18 @@ int printk_deferred(const char *fmt, ...)
return r;
int printk_deferred(const char *fmt, ...)
va_list args;
int r;
va_start(args, fmt);
r = vprintk_deferred(fmt, args);
return r;
* printk rate limiting, lifted from the networking subsystem.
......@@ -308,12 +308,24 @@ static int vprintk_nmi(const char *fmt, va_list args)
void printk_nmi_enter(void)
this_cpu_or(printk_context, PRINTK_NMI_CONTEXT_MASK);
* The size of the extra per-CPU buffer is limited. Use it only when
* the main one is locked. If this CPU is not in the safe context,
* the lock must be taken on another CPU and we could wait for it.
if ((this_cpu_read(printk_context) & PRINTK_SAFE_CONTEXT_MASK) &&
raw_spin_is_locked(&logbuf_lock)) {
this_cpu_or(printk_context, PRINTK_NMI_CONTEXT_MASK);
} else {
this_cpu_or(printk_context, PRINTK_NMI_DEFERRED_CONTEXT_MASK);
void printk_nmi_exit(void)
this_cpu_and(printk_context, ~PRINTK_NMI_CONTEXT_MASK);
......@@ -351,12 +363,22 @@ void __printk_safe_exit(void)
__printf(1, 0) int vprintk_func(const char *fmt, va_list args)
/* Use extra buffer in NMI when logbuf_lock is taken or in safe mode. */
if (this_cpu_read(printk_context) & PRINTK_NMI_CONTEXT_MASK)
return vprintk_nmi(fmt, args);
/* Use extra buffer to prevent a recursion deadlock in safe mode. */
if (this_cpu_read(printk_context) & PRINTK_SAFE_CONTEXT_MASK)
return vprintk_safe(fmt, args);
* Use the main logbuf when logbuf_lock is available in NMI.
* But avoid calling console drivers that might have their own locks.
if (this_cpu_read(printk_context) & PRINTK_NMI_DEFERRED_CONTEXT_MASK)
return vprintk_deferred(fmt, args);
/* No obstacles. */
return vprintk_default(fmt, args);
......@@ -86,9 +86,11 @@ void nmi_trigger_cpumask_backtrace(const cpumask_t *mask,
bool nmi_cpu_backtrace(struct pt_regs *regs)
static arch_spinlock_t lock = __ARCH_SPIN_LOCK_UNLOCKED;
int cpu = smp_processor_id();
if (cpumask_test_cpu(cpu, to_cpumask(backtrace_mask))) {
if (regs && cpu_in_idle(instruction_pointer(regs))) {
pr_warn("NMI backtrace for cpu %d skipped: idling at pc %#lx\n",
cpu, instruction_pointer(regs));
......@@ -99,6 +101,7 @@ bool nmi_cpu_backtrace(struct pt_regs *regs)
cpumask_clear_cpu(cpu, to_cpumask(backtrace_mask));
return true;
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment