diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h
index c90c6a41c448c0410b1f5e0d4efff32dfdb1e103..cfb675466e86c32664810c9e2fcbe636d58fecb9 100644
--- a/arch/arm64/include/asm/kvm_host.h
+++ b/arch/arm64/include/asm/kvm_host.h
@@ -123,6 +123,17 @@ struct kvm_vcpu_arch {
 	 * here.
 	 */
 
+	/*
+	 * Guest registers we preserve during guest debugging.
+	 *
+	 * These shadow registers are updated by the kvm_handle_sys_reg
+	 * trap handler if the guest accesses or updates them while we
+	 * are using guest debug.
+	 */
+	struct {
+		u32	mdscr_el1;
+	} guest_debug_preserved;
+
 	/* Don't run the guest */
 	bool pause;
 
diff --git a/arch/arm64/kvm/debug.c b/arch/arm64/kvm/debug.c
index 8d1bfa4383109bd8335fb6b81f7da370183ff190..d439eb8f3239ecaab16abc29a30d23f03cc9bc01 100644
--- a/arch/arm64/kvm/debug.c
+++ b/arch/arm64/kvm/debug.c
@@ -19,10 +19,38 @@
 
 #include <linux/kvm_host.h>
 
+#include <asm/debug-monitors.h>
+#include <asm/kvm_asm.h>
 #include <asm/kvm_arm.h>
+#include <asm/kvm_emulate.h>
+
+/* These are the bits of MDSCR_EL1 we may manipulate */
+#define MDSCR_EL1_DEBUG_MASK	(DBG_MDSCR_SS | \
+				DBG_MDSCR_KDE | \
+				DBG_MDSCR_MDE)
 
 static DEFINE_PER_CPU(u32, mdcr_el2);
 
+/**
+ * save/restore_guest_debug_regs
+ *
+ * For some debug operations we need to tweak some guest registers. As
+ * a result we need to save the state of those registers before we
+ * make those modifications.
+ *
+ * Guest access to MDSCR_EL1 is trapped by the hypervisor and handled
+ * after we have restored the preserved value to the main context.
+ */
+static void save_guest_debug_regs(struct kvm_vcpu *vcpu)
+{
+	vcpu->arch.guest_debug_preserved.mdscr_el1 = vcpu_sys_reg(vcpu, MDSCR_EL1);
+}
+
+static void restore_guest_debug_regs(struct kvm_vcpu *vcpu)
+{
+	vcpu_sys_reg(vcpu, MDSCR_EL1) = vcpu->arch.guest_debug_preserved.mdscr_el1;
+}
+
 /**
  * kvm_arm_init_debug - grab what we need for debug
  *
@@ -38,7 +66,6 @@ void kvm_arm_init_debug(void)
 	__this_cpu_write(mdcr_el2, kvm_call_hyp(__kvm_get_mdcr_el2));
 }
 
-
 /**
  * kvm_arm_setup_debug - set up debug related stuff
  *
@@ -73,12 +100,45 @@ void kvm_arm_setup_debug(struct kvm_vcpu *vcpu)
 	if (trap_debug)
 		vcpu->arch.mdcr_el2 |= MDCR_EL2_TDA;
 
-	/* Trap breakpoints? */
-	if (vcpu->guest_debug & KVM_GUESTDBG_USE_SW_BP)
+	/* Is Guest debugging in effect? */
+	if (vcpu->guest_debug) {
+		/* Route all software debug exceptions to EL2 */
 		vcpu->arch.mdcr_el2 |= MDCR_EL2_TDE;
+
+		/* Save guest debug state */
+		save_guest_debug_regs(vcpu);
+
+		/*
+		 * Single Step (ARM ARM D2.12.3 The software step state
+		 * machine)
+		 *
+		 * If we are doing Single Step we need to manipulate
+		 * the guest's MDSCR_EL1.SS and PSTATE.SS. Once the
+		 * step has occurred the hypervisor will trap the
+		 * debug exception and we return to userspace.
+		 *
+		 * If the guest attempts to single step its userspace
+		 * we would have to deal with a trapped exception
+		 * while in the guest kernel. Because this would be
+		 * hard to unwind we suppress the guest's ability to
+		 * do so by masking MDSCR_EL.SS.
+		 *
+		 * This confuses guest debuggers which use
+		 * single-step behind the scenes but everything
+		 * returns to normal once the host is no longer
+		 * debugging the system.
+		 */
+		if (vcpu->guest_debug & KVM_GUESTDBG_SINGLESTEP) {
+			*vcpu_cpsr(vcpu) |=  DBG_SPSR_SS;
+			vcpu_sys_reg(vcpu, MDSCR_EL1) |= DBG_MDSCR_SS;
+		} else {
+			vcpu_sys_reg(vcpu, MDSCR_EL1) &= ~DBG_MDSCR_SS;
+		}
+	}
 }
 
 void kvm_arm_clear_debug(struct kvm_vcpu *vcpu)
 {
-	/* Nothing to do yet */
+	if (vcpu->guest_debug)
+		restore_guest_debug_regs(vcpu);
 }
diff --git a/arch/arm64/kvm/guest.c b/arch/arm64/kvm/guest.c
index 22d22c54fd8d158a352fcae958e013e05e0ef158..48de4f4aaa1a567b530e0d2241dff02909dc4b6f 100644
--- a/arch/arm64/kvm/guest.c
+++ b/arch/arm64/kvm/guest.c
@@ -332,7 +332,9 @@ int kvm_arch_vcpu_ioctl_translate(struct kvm_vcpu *vcpu,
 	return -EINVAL;
 }
 
-#define KVM_GUESTDBG_VALID_MASK (KVM_GUESTDBG_ENABLE | KVM_GUESTDBG_USE_SW_BP)
+#define KVM_GUESTDBG_VALID_MASK (KVM_GUESTDBG_ENABLE |    \
+			    KVM_GUESTDBG_USE_SW_BP | \
+			    KVM_GUESTDBG_SINGLESTEP)
 
 /**
  * kvm_arch_vcpu_ioctl_set_guest_debug - set up guest debugging
diff --git a/arch/arm64/kvm/handle_exit.c b/arch/arm64/kvm/handle_exit.c
index 27f38a9f9ea277daaf48e1e344f4f0f32097ae2a..e9de13ed477e699aa755ee640aacd2219e2392f8 100644
--- a/arch/arm64/kvm/handle_exit.c
+++ b/arch/arm64/kvm/handle_exit.c
@@ -103,6 +103,7 @@ static int kvm_handle_guest_debug(struct kvm_vcpu *vcpu, struct kvm_run *run)
 	run->debug.arch.hsr = hsr;
 
 	switch (hsr >> ESR_ELx_EC_SHIFT) {
+	case ESR_ELx_EC_SOFTSTP_LOW:
 	case ESR_ELx_EC_BKPT32:
 	case ESR_ELx_EC_BRK64:
 		break;
@@ -130,6 +131,7 @@ static exit_handle_fn arm_exit_handlers[] = {
 	[ESR_ELx_EC_SYS64]	= kvm_handle_sys_reg,
 	[ESR_ELx_EC_IABT_LOW]	= kvm_handle_guest_abort,
 	[ESR_ELx_EC_DABT_LOW]	= kvm_handle_guest_abort,
+	[ESR_ELx_EC_SOFTSTP_LOW]= kvm_handle_guest_debug,
 	[ESR_ELx_EC_BKPT32]	= kvm_handle_guest_debug,
 	[ESR_ELx_EC_BRK64]	= kvm_handle_guest_debug,
 };