diff --git a/kernel/printk/internal.h b/kernel/printk/internal.h
index 1db044f808b7..2a7d04049af4 100644
--- a/kernel/printk/internal.h
+++ b/kernel/printk/internal.h
@@ -18,12 +18,14 @@
 
 #ifdef CONFIG_PRINTK
 
-#define PRINTK_SAFE_CONTEXT_MASK	0x7fffffff
-#define PRINTK_NMI_CONTEXT_MASK	0x80000000
+#define PRINTK_SAFE_CONTEXT_MASK	 0x3fffffff
+#define PRINTK_NMI_DEFERRED_CONTEXT_MASK 0x40000000
+#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);
diff --git a/kernel/printk/printk.c b/kernel/printk/printk.c
index a1db38abac5b..8603a48fcdea 100644
--- a/kernel/printk/printk.c
+++ b/kernel/printk/printk.c
@@ -2720,20 +2720,29 @@ void wake_up_klogd(void)
 	preempt_enable();
 }
 
+int vprintk_deferred(const char *fmt, va_list args)
+{
+	int r;
+
+	r = vprintk_emit(0, LOGLEVEL_SCHED, NULL, 0, fmt, args);
+
+	preempt_disable();
+	__this_cpu_or(printk_pending, PRINTK_PENDING_OUTPUT);
+	irq_work_queue(this_cpu_ptr(&wake_up_klogd_work));
+	preempt_enable();
+
+	return r;
+}
+
 int printk_deferred(const char *fmt, ...)
 {
 	va_list args;
 	int r;
 
-	preempt_disable();
 	va_start(args, fmt);
-	r = vprintk_emit(0, LOGLEVEL_SCHED, NULL, 0, fmt, args);
+	r = vprintk_deferred(fmt, args);
 	va_end(args);
 
-	__this_cpu_or(printk_pending, PRINTK_PENDING_OUTPUT);
-	irq_work_queue(this_cpu_ptr(&wake_up_klogd_work));
-	preempt_enable();
-
 	return r;
 }
 
diff --git a/kernel/printk/printk_safe.c b/kernel/printk/printk_safe.c
index 033e50a7d706..3cdaeaef9ce1 100644
--- a/kernel/printk/printk_safe.c
+++ b/kernel/printk/printk_safe.c
@@ -80,8 +80,8 @@ static void queue_flush_work(struct printk_safe_seq_buf *s)
  * happen, printk_safe_log_store() will notice the buffer->len mismatch
  * and repeat the write.
  */
-static int printk_safe_log_store(struct printk_safe_seq_buf *s,
-				 const char *fmt, va_list args)
+static __printf(2, 0) int printk_safe_log_store(struct printk_safe_seq_buf *s,
+						const char *fmt, va_list args)
 {
 	int add;
 	size_t len;
@@ -299,7 +299,7 @@ void printk_safe_flush_on_panic(void)
  * one writer running. But the buffer might get flushed from another
  * CPU, so we need to be careful.
  */
-static int vprintk_nmi(const char *fmt, va_list args)
+static __printf(1, 0) int vprintk_nmi(const char *fmt, va_list args)
 {
 	struct printk_safe_seq_buf *s = this_cpu_ptr(&nmi_print_seq);
 
@@ -308,17 +308,29 @@ 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);
+	this_cpu_and(printk_context,
+		     ~(PRINTK_NMI_CONTEXT_MASK |
+		       PRINTK_NMI_DEFERRED_CONTEXT_MASK));
 }
 
 #else
 
-static int vprintk_nmi(const char *fmt, va_list args)
+static __printf(1, 0) int vprintk_nmi(const char *fmt, va_list args)
 {
 	return 0;
 }
@@ -330,7 +342,7 @@ static int vprintk_nmi(const char *fmt, va_list args)
  * into itself. It uses a per-CPU buffer to store the message, just like
  * NMI.
  */
-static int vprintk_safe(const char *fmt, va_list args)
+static __printf(1, 0) int vprintk_safe(const char *fmt, va_list args)
 {
 	struct printk_safe_seq_buf *s = this_cpu_ptr(&safe_print_seq);
 
@@ -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);
 }
 
diff --git a/lib/nmi_backtrace.c b/lib/nmi_backtrace.c
index 4e8a30d1c22f..0bc0a3535a8a 100644
--- a/lib/nmi_backtrace.c
+++ b/lib/nmi_backtrace.c
@@ -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))) {
+		arch_spin_lock(&lock);
 		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)
 			else
 				dump_stack();
 		}
+		arch_spin_unlock(&lock);
 		cpumask_clear_cpu(cpu, to_cpumask(backtrace_mask));
 		return true;
 	}