diff --git a/arch/powerpc/include/asm/percpu.h b/arch/powerpc/include/asm/percpu.h
index 8e5b7d0b851c61246b00d2f3e8d53e322777ffbc..634970ce13c6b9884f7d7058b9022b72bb6ce388 100644
--- a/arch/powerpc/include/asm/percpu.h
+++ b/arch/powerpc/include/asm/percpu.h
@@ -15,6 +15,16 @@
 #endif /* CONFIG_SMP */
 #endif /* __powerpc64__ */
 
+#if defined(CONFIG_NEED_PER_CPU_PAGE_FIRST_CHUNK) && defined(CONFIG_SMP)
+#include <linux/jump_label.h>
+DECLARE_STATIC_KEY_FALSE(__percpu_first_chunk_is_paged);
+
+#define percpu_first_chunk_is_paged	\
+		(static_key_enabled(&__percpu_first_chunk_is_paged.key))
+#else
+#define percpu_first_chunk_is_paged	false
+#endif /* CONFIG_PPC64 && CONFIG_SMP */
+
 #include <asm-generic/percpu.h>
 
 #include <asm/paca.h>
diff --git a/arch/powerpc/kernel/mce.c b/arch/powerpc/kernel/mce.c
index 63702c0badb973651d5629f15a72d8eec10fcc13..b652105fc4c83401fbedde92369ed3afbede6113 100644
--- a/arch/powerpc/kernel/mce.c
+++ b/arch/powerpc/kernel/mce.c
@@ -594,8 +594,15 @@ long notrace machine_check_early(struct pt_regs *regs)
 	u8 ftrace_enabled = this_cpu_get_ftrace_enabled();
 
 	this_cpu_set_ftrace_enabled(0);
-	/* Do not use nmi_enter/exit for pseries hpte guest */
-	if (radix_enabled() || !firmware_has_feature(FW_FEATURE_LPAR))
+	/*
+	 * Do not use nmi_enter/exit for pseries hpte guest.
+	 *
+	 * Likewise, do not use it in real mode if percpu first chunk is not
+	 * embedded. With CONFIG_NEED_PER_CPU_PAGE_FIRST_CHUNK enabled there
+	 * are chances where percpu allocation can come from vmalloc area.
+	 */
+	if ((radix_enabled() || !firmware_has_feature(FW_FEATURE_LPAR)) &&
+	    !percpu_first_chunk_is_paged)
 		nmi_enter();
 
 	hv_nmi_check_nonrecoverable(regs);
@@ -606,7 +613,8 @@ long notrace machine_check_early(struct pt_regs *regs)
 	if (ppc_md.machine_check_early)
 		handled = ppc_md.machine_check_early(regs);
 
-	if (radix_enabled() || !firmware_has_feature(FW_FEATURE_LPAR))
+	if ((radix_enabled() || !firmware_has_feature(FW_FEATURE_LPAR)) &&
+	    !percpu_first_chunk_is_paged)
 		nmi_exit();
 
 	this_cpu_set_ftrace_enabled(ftrace_enabled);
diff --git a/arch/powerpc/kernel/setup_64.c b/arch/powerpc/kernel/setup_64.c
index cc285e0b97223e59051d8c5329c7fddd7cd86eb4..4875e84eb975251b8c57f278a5809afdd7abc26a 100644
--- a/arch/powerpc/kernel/setup_64.c
+++ b/arch/powerpc/kernel/setup_64.c
@@ -827,6 +827,7 @@ static int pcpu_cpu_distance(unsigned int from, unsigned int to)
 
 unsigned long __per_cpu_offset[NR_CPUS] __read_mostly;
 EXPORT_SYMBOL(__per_cpu_offset);
+DEFINE_STATIC_KEY_FALSE(__percpu_first_chunk_is_paged);
 
 static void __init pcpu_populate_pte(unsigned long addr)
 {
@@ -906,6 +907,7 @@ void __init setup_per_cpu_areas(void)
 	if (rc < 0)
 		panic("cannot initialize percpu area (err=%d)", rc);
 
+	static_key_enable(&__percpu_first_chunk_is_paged.key);
 	delta = (unsigned long)pcpu_base_addr - (unsigned long)__per_cpu_start;
 	for_each_possible_cpu(cpu) {
                 __per_cpu_offset[cpu] = delta + pcpu_unit_offsets[cpu];