diff --git a/arch/x86/include/asm/smp.h b/arch/x86/include/asm/smp.h
index a73bced40e24..b3b34032ef23 100644
--- a/arch/x86/include/asm/smp.h
+++ b/arch/x86/include/asm/smp.h
@@ -132,6 +132,8 @@ void wbinvd_on_cpu(int cpu);
 int wbinvd_on_all_cpus(void);
 void cond_wakeup_cpu0(void);
 
+void smp_kick_mwait_play_dead(void);
+
 void native_smp_send_reschedule(int cpu);
 void native_send_call_func_ipi(const struct cpumask *mask);
 void native_send_call_func_single_ipi(int cpu);
diff --git a/arch/x86/kernel/smp.c b/arch/x86/kernel/smp.c
index d842875f986f..174d6232b87f 100644
--- a/arch/x86/kernel/smp.c
+++ b/arch/x86/kernel/smp.c
@@ -21,6 +21,7 @@
 #include <linux/interrupt.h>
 #include <linux/cpu.h>
 #include <linux/gfp.h>
+#include <linux/kexec.h>
 
 #include <asm/mtrr.h>
 #include <asm/tlbflush.h>
@@ -157,6 +158,10 @@ static void native_stop_other_cpus(int wait)
 	if (atomic_cmpxchg(&stopping_cpu, -1, cpu) != -1)
 		return;
 
+	/* For kexec, ensure that offline CPUs are out of MWAIT and in HLT */
+	if (kexec_in_progress)
+		smp_kick_mwait_play_dead();
+
 	/*
 	 * 1) Send an IPI on the reboot vector to all other CPUs.
 	 *
diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
index b96f983e64cc..f32ee967414e 100644
--- a/arch/x86/kernel/smpboot.c
+++ b/arch/x86/kernel/smpboot.c
@@ -53,6 +53,7 @@
 #include <linux/tboot.h>
 #include <linux/gfp.h>
 #include <linux/cpuidle.h>
+#include <linux/kexec.h>
 #include <linux/numa.h>
 #include <linux/pgtable.h>
 #include <linux/overflow.h>
@@ -104,6 +105,9 @@ struct mwait_cpu_dead {
 	unsigned int	status;
 };
 
+#define CPUDEAD_MWAIT_WAIT	0xDEADBEEF
+#define CPUDEAD_MWAIT_KEXEC_HLT	0x4A17DEAD
+
 /*
  * Cache line aligned data for mwait_play_dead(). Separate on purpose so
  * that it's unlikely to be touched by other CPUs.
@@ -166,6 +170,10 @@ static void smp_callin(void)
 {
 	int cpuid;
 
+	/* Mop up eventual mwait_play_dead() wreckage */
+	this_cpu_write(mwait_cpu_dead.status, 0);
+	this_cpu_write(mwait_cpu_dead.control, 0);
+
 	/*
 	 * If waken up by an INIT in an 82489DX configuration
 	 * cpu_callout_mask guarantees we don't get here before
@@ -1795,6 +1803,10 @@ static inline void mwait_play_dead(void)
 			(highest_subcstate - 1);
 	}
 
+	/* Set up state for the kexec() hack below */
+	md->status = CPUDEAD_MWAIT_WAIT;
+	md->control = CPUDEAD_MWAIT_WAIT;
+
 	wbinvd();
 
 	while (1) {
@@ -1812,10 +1824,57 @@ static inline void mwait_play_dead(void)
 		mb();
 		__mwait(eax, 0);
 
+		if (READ_ONCE(md->control) == CPUDEAD_MWAIT_KEXEC_HLT) {
+			/*
+			 * Kexec is about to happen. Don't go back into mwait() as
+			 * the kexec kernel might overwrite text and data including
+			 * page tables and stack. So mwait() would resume when the
+			 * monitor cache line is written to and then the CPU goes
+			 * south due to overwritten text, page tables and stack.
+			 *
+			 * Note: This does _NOT_ protect against a stray MCE, NMI,
+			 * SMI. They will resume execution at the instruction
+			 * following the HLT instruction and run into the problem
+			 * which this is trying to prevent.
+			 */
+			WRITE_ONCE(md->status, CPUDEAD_MWAIT_KEXEC_HLT);
+			while(1)
+				native_halt();
+		}
+
 		cond_wakeup_cpu0();
 	}
 }
 
+/*
+ * Kick all "offline" CPUs out of mwait on kexec(). See comment in
+ * mwait_play_dead().
+ */
+void smp_kick_mwait_play_dead(void)
+{
+	u32 newstate = CPUDEAD_MWAIT_KEXEC_HLT;
+	struct mwait_cpu_dead *md;
+	unsigned int cpu, i;
+
+	for_each_cpu_andnot(cpu, cpu_present_mask, cpu_online_mask) {
+		md = per_cpu_ptr(&mwait_cpu_dead, cpu);
+
+		/* Does it sit in mwait_play_dead() ? */
+		if (READ_ONCE(md->status) != CPUDEAD_MWAIT_WAIT)
+			continue;
+
+		/* Wait up to 5ms */
+		for (i = 0; READ_ONCE(md->status) != newstate && i < 1000; i++) {
+			/* Bring it out of mwait */
+			WRITE_ONCE(md->control, newstate);
+			udelay(5);
+		}
+
+		if (READ_ONCE(md->status) != newstate)
+			pr_err_once("CPU%u is stuck in mwait_play_dead()\n", cpu);
+	}
+}
+
 void hlt_play_dead(void)
 {
 	if (__this_cpu_read(cpu_info.x86) >= 4)