Merge tag 'kvm-ppc-next-4.16-1' of git://git.kernel.org/pub/scm/linux/kernel/git/paulus/powerpc

PPC KVM update for 4.16

- Allow HPT guests to run on a radix host on POWER9 v2.2 CPUs
  without requiring the complex thread synchronization that earlier
  CPU versions required.

- A series from Ben Herrenschmidt to improve the handling of
  escalation interrupts with the XIVE interrupt controller.

- Provide for the decrementer register to be copied across on
  migration.

- Various minor cleanups and bugfixes.

8 files changed, 298 insertions, 144 deletions

diff --git a/arch/powerpc/kvm/book3s_64_mmu_radix.c b/arch/powerpc/kvm/book3s_64_mmu_radix.c
index 58618f644c56..0c854816e653 100644
--- a/arch/powerpc/kvm/book3s_64_mmu_radix.c
+++ b/arch/powerpc/kvm/book3s_64_mmu_radix.c
@@ -573,7 +573,7 @@ long kvmppc_hv_get_dirty_log_radix(struct kvm *kvm,
 		j = i + 1;
 		if (npages) {
 			set_dirty_bits(map, i, npages);
-			i = j + npages;
+			j = i + npages;
 		}
 	}
 	return 0;
diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c
index 2d46037ce936..e5f81fc108e0 100644
--- a/arch/powerpc/kvm/book3s_hv.c
+++ b/arch/powerpc/kvm/book3s_hv.c
@@ -118,6 +118,9 @@ module_param_cb(h_ipi_redirect, &module_param_ops, &h_ipi_redirect,
 MODULE_PARM_DESC(h_ipi_redirect, "Redirect H_IPI wakeup to a free host core");
 #endif
 
+/* If set, the threads on each CPU core have to be in the same MMU mode */
+static bool no_mixing_hpt_and_radix;
+
 static void kvmppc_end_cede(struct kvm_vcpu *vcpu);
 static int kvmppc_hv_setup_htab_rma(struct kvm_vcpu *vcpu);
 
@@ -1497,6 +1500,10 @@ static int kvmppc_get_one_reg_hv(struct kvm_vcpu *vcpu, u64 id,
 	case KVM_REG_PPC_ARCH_COMPAT:
 		*val = get_reg_val(id, vcpu->arch.vcore->arch_compat);
 		break;
+	case KVM_REG_PPC_DEC_EXPIRY:
+		*val = get_reg_val(id, vcpu->arch.dec_expires +
+				   vcpu->arch.vcore->tb_offset);
+		break;
 	default:
 		r = -EINVAL;
 		break;
@@ -1724,6 +1731,10 @@ static int kvmppc_set_one_reg_hv(struct kvm_vcpu *vcpu, u64 id,
 	case KVM_REG_PPC_ARCH_COMPAT:
 		r = kvmppc_set_arch_compat(vcpu, set_reg_val(id, *val));
 		break;
+	case KVM_REG_PPC_DEC_EXPIRY:
+		vcpu->arch.dec_expires = set_reg_val(id, *val) -
+			vcpu->arch.vcore->tb_offset;
+		break;
 	default:
 		r = -EINVAL;
 		break;
@@ -2378,8 +2389,8 @@ static void init_core_info(struct core_info *cip, struct kvmppc_vcore *vc)
 static bool subcore_config_ok(int n_subcores, int n_threads)
 {
 	/*
-	 * POWER9 "SMT4" cores are permanently in what is effectively a 4-way split-core
-	 * mode, with one thread per subcore.
+	 * POWER9 "SMT4" cores are permanently in what is effectively a 4-way
+	 * split-core mode, with one thread per subcore.
 	 */
 	if (cpu_has_feature(CPU_FTR_ARCH_300))
 		return n_subcores <= 4 && n_threads == 1;
@@ -2415,8 +2426,8 @@ static bool can_dynamic_split(struct kvmppc_vcore *vc, struct core_info *cip)
 	if (!cpu_has_feature(CPU_FTR_ARCH_207S))
 		return false;
 
-	/* POWER9 currently requires all threads to be in the same MMU mode */
-	if (cpu_has_feature(CPU_FTR_ARCH_300) &&
+	/* Some POWER9 chips require all threads to be in the same MMU mode */
+	if (no_mixing_hpt_and_radix &&
 	    kvm_is_radix(vc->kvm) != kvm_is_radix(cip->vc[0]->kvm))
 		return false;
 
@@ -2679,9 +2690,11 @@ static noinline void kvmppc_run_core(struct kvmppc_vcore *vc)
 	 * threads are offline.  Also check if the number of threads in this
 	 * guest are greater than the current system threads per guest.
 	 * On POWER9, we need to be not in independent-threads mode if
-	 * this is a HPT guest on a radix host.
+	 * this is a HPT guest on a radix host machine where the
+	 * CPU threads may not be in different MMU modes.
 	 */
-	hpt_on_radix = radix_enabled() && !kvm_is_radix(vc->kvm);
+	hpt_on_radix = no_mixing_hpt_and_radix && radix_enabled() &&
+		!kvm_is_radix(vc->kvm);
 	if (((controlled_threads > 1) &&
 	     ((vc->num_threads > threads_per_subcore) || !on_primary_thread())) ||
 	    (hpt_on_radix && vc->kvm->arch.threads_indep)) {
@@ -2831,7 +2844,6 @@ static noinline void kvmppc_run_core(struct kvmppc_vcore *vc)
 		 */
 		if (!thr0_done)
 			kvmppc_start_thread(NULL, pvc);
-		thr += pvc->num_threads;
 	}
 
 	/*
@@ -2987,7 +2999,7 @@ static inline bool xive_interrupt_pending(struct kvm_vcpu *vcpu)
 {
 	if (!xive_enabled())
 		return false;
-	return vcpu->arch.xive_saved_state.pipr <
+	return vcpu->arch.irq_pending || vcpu->arch.xive_saved_state.pipr <
 		vcpu->arch.xive_saved_state.cppr;
 }
 #else
@@ -3176,17 +3188,8 @@ static int kvmppc_run_vcpu(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu)
 	 * this thread straight away and have it join in.
 	 */
 	if (!signal_pending(current)) {
-		if (vc->vcore_state == VCORE_PIGGYBACK) {
-			if (spin_trylock(&vc->lock)) {
-				if (vc->vcore_state == VCORE_RUNNING &&
-				    !VCORE_IS_EXITING(vc)) {
-					kvmppc_create_dtl_entry(vcpu, vc);
-					kvmppc_start_thread(vcpu, vc);
-					trace_kvm_guest_enter(vcpu);
-				}
-				spin_unlock(&vc->lock);
-			}
-		} else if (vc->vcore_state == VCORE_RUNNING &&
+		if ((vc->vcore_state == VCORE_PIGGYBACK ||
+		     vc->vcore_state == VCORE_RUNNING) &&
 			   !VCORE_IS_EXITING(vc)) {
 			kvmppc_create_dtl_entry(vcpu, vc);
 			kvmppc_start_thread(vcpu, vc);
@@ -4448,6 +4451,19 @@ static int kvmppc_book3s_init_hv(void)
 
 	if (kvmppc_radix_possible())
 		r = kvmppc_radix_init();
+
+	/*
+	 * POWER9 chips before version 2.02 can't have some threads in
+	 * HPT mode and some in radix mode on the same core.
+	 */
+	if (cpu_has_feature(CPU_FTR_ARCH_300)) {
+		unsigned int pvr = mfspr(SPRN_PVR);
+		if ((pvr >> 16) == PVR_POWER9 &&
+		    (((pvr & 0xe000) == 0 && (pvr & 0xfff) < 0x202) ||
+		     ((pvr & 0xe000) == 0x2000 && (pvr & 0xfff) < 0x101)))
+			no_mixing_hpt_and_radix = true;
+	}
+
 	return r;
 }
 
diff --git a/arch/powerpc/kvm/book3s_hv_ras.c b/arch/powerpc/kvm/book3s_hv_ras.c
index c356f9a40b24..c296343d0dcc 100644
--- a/arch/powerpc/kvm/book3s_hv_ras.c
+++ b/arch/powerpc/kvm/book3s_hv_ras.c
@@ -268,17 +268,19 @@ static void kvmppc_tb_resync_done(void)
  *   secondary threads to proceed.
  * - All secondary threads will eventually call opal hmi handler on
  *   their exit path.
+ *
+ * Returns 1 if the timebase offset should be applied, 0 if not.
  */
 
 long kvmppc_realmode_hmi_handler(void)
 {
-	int ptid = local_paca->kvm_hstate.ptid;
 	bool resync_req;
 
-	/* This is only called on primary thread. */
-	BUG_ON(ptid != 0);
 	__this_cpu_inc(irq_stat.hmi_exceptions);
 
+	if (hmi_handle_debugtrig(NULL) >= 0)
+		return 1;
+
 	/*
 	 * By now primary thread has already completed guest->host
 	 * partition switch but haven't signaled secondaries yet.
diff --git a/arch/powerpc/kvm/book3s_hv_rmhandlers.S b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
index 9c61f736c75b..b64f10a5f5e7 100644
--- a/arch/powerpc/kvm/book3s_hv_rmhandlers.S
+++ b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
@@ -617,13 +617,6 @@ kvmppc_hv_entry:
 	lbz	r0, KVM_RADIX(r9)
 	cmpwi	cr7, r0, 0
 
-	/* Clear out SLB if hash */
-	bne	cr7, 2f
-	li	r6,0
-	slbmte	r6,r6
-	slbia
-	ptesync
-2:
 	/*
 	 * POWER7/POWER8 host -> guest partition switch code.
 	 * We don't have to lock against concurrent tlbies,
@@ -738,19 +731,6 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S)
 10:	cmpdi	r4, 0
 	beq	kvmppc_primary_no_guest
 kvmppc_got_guest:
-
-	/* Load up guest SLB entries (N.B. slb_max will be 0 for radix) */
-	lwz	r5,VCPU_SLB_MAX(r4)
-	cmpwi	r5,0
-	beq	9f
-	mtctr	r5
-	addi	r6,r4,VCPU_SLB
-1:	ld	r8,VCPU_SLB_E(r6)
-	ld	r9,VCPU_SLB_V(r6)
-	slbmte	r9,r8
-	addi	r6,r6,VCPU_SLB_SIZE
-	bdnz	1b
-9:
 	/* Increment yield count if they have a VPA */
 	ld	r3, VCPU_VPA(r4)
 	cmpdi	r3, 0
@@ -957,7 +937,6 @@ ALT_FTR_SECTION_END_IFCLR(CPU_FTR_ARCH_300)
 	mftb	r7
 	subf	r3,r7,r8
 	mtspr	SPRN_DEC,r3
-	std	r3,VCPU_DEC(r4)
 
 	ld	r5, VCPU_SPRG0(r4)
 	ld	r6, VCPU_SPRG1(r4)
@@ -1018,6 +997,29 @@ ALT_FTR_SECTION_END_IFCLR(CPU_FTR_ARCH_300)
 	cmpdi	r3, 512		/* 1 microsecond */
 	blt	hdec_soon
 
+	/* For hash guest, clear out and reload the SLB */
+	ld	r6, VCPU_KVM(r4)
+	lbz	r0, KVM_RADIX(r6)
+	cmpwi	r0, 0
+	bne	9f
+	li	r6, 0
+	slbmte	r6, r6
+	slbia
+	ptesync
+
+	/* Load up guest SLB entries (N.B. slb_max will be 0 for radix) */
+	lwz	r5,VCPU_SLB_MAX(r4)
+	cmpwi	r5,0
+	beq	9f
+	mtctr	r5
+	addi	r6,r4,VCPU_SLB
+1:	ld	r8,VCPU_SLB_E(r6)
+	ld	r9,VCPU_SLB_V(r6)
+	slbmte	r9,r8
+	addi	r6,r6,VCPU_SLB_SIZE
+	bdnz	1b
+9:
+
 #ifdef CONFIG_KVM_XICS
 	/* We are entering the guest on that thread, push VCPU to XIVE */
 	ld	r10, HSTATE_XIVE_TIMA_PHYS(r13)
@@ -1031,8 +1033,53 @@ ALT_FTR_SECTION_END_IFCLR(CPU_FTR_ARCH_300)
 	li	r9, TM_QW1_OS + TM_WORD2
 	stwcix	r11,r9,r10
 	li	r9, 1
-	stw	r9, VCPU_XIVE_PUSHED(r4)
+	stb	r9, VCPU_XIVE_PUSHED(r4)
 	eieio
+
+	/*
+	 * We clear the irq_pending flag. There is a small chance of a
+	 * race vs. the escalation interrupt happening on another
+	 * processor setting it again, but the only consequence is to
+	 * cause a spurrious wakeup on the next H_CEDE which is not an
+	 * issue.
+	 */
+	li	r0,0
+	stb	r0, VCPU_IRQ_PENDING(r4)
+
+	/*
+	 * In single escalation mode, if the escalation interrupt is
+	 * on, we mask it.
+	 */
+	lbz	r0, VCPU_XIVE_ESC_ON(r4)
+	cmpwi	r0,0
+	beq	1f
+	ld	r10, VCPU_XIVE_ESC_RADDR(r4)
+	li	r9, XIVE_ESB_SET_PQ_01
+	ldcix	r0, r10, r9
+	sync
+
+	/* We have a possible subtle race here: The escalation interrupt might
+	 * have fired and be on its way to the host queue while we mask it,
+	 * and if we unmask it early enough (re-cede right away), there is
+	 * a theorical possibility that it fires again, thus landing in the
+	 * target queue more than once which is a big no-no.
+	 *
+	 * Fortunately, solving this is rather easy. If the above load setting
+	 * PQ to 01 returns a previous value where P is set, then we know the
+	 * escalation interrupt is somewhere on its way to the host. In that
+	 * case we simply don't clear the xive_esc_on flag below. It will be
+	 * eventually cleared by the handler for the escalation interrupt.
+	 *
+	 * Then, when doing a cede, we check that flag again before re-enabling
+	 * the escalation interrupt, and if set, we abort the cede.
+	 */
+	andi.	r0, r0, XIVE_ESB_VAL_P
+	bne-	1f
+
+	/* Now P is 0, we can clear the flag */
+	li	r0, 0
+	stb	r0, VCPU_XIVE_ESC_ON(r4)
+1:
 no_xive:
 #endif /* CONFIG_KVM_XICS */
 
@@ -1193,7 +1240,7 @@ hdec_soon:
 	addi	r3, r4, VCPU_TB_RMEXIT
 	bl	kvmhv_accumulate_time
 #endif
-	b	guest_exit_cont
+	b	guest_bypass
 
 /******************************************************************************
  *                                                                            *
@@ -1423,15 +1470,35 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_300)
 	blt	deliver_guest_interrupt
 
 guest_exit_cont:		/* r9 = vcpu, r12 = trap, r13 = paca */
+	/* Save more register state  */
+	mfdar	r6
+	mfdsisr	r7
+	std	r6, VCPU_DAR(r9)
+	stw	r7, VCPU_DSISR(r9)
+	/* don't overwrite fault_dar/fault_dsisr if HDSI */
+	cmpwi	r12,BOOK3S_INTERRUPT_H_DATA_STORAGE
+	beq	mc_cont
+	std	r6, VCPU_FAULT_DAR(r9)
+	stw	r7, VCPU_FAULT_DSISR(r9)
+
+	/* See if it is a machine check */
+	cmpwi	r12, BOOK3S_INTERRUPT_MACHINE_CHECK
+	beq	machine_check_realmode
+mc_cont:
+#ifdef CONFIG_KVM_BOOK3S_HV_EXIT_TIMING
+	addi	r3, r9, VCPU_TB_RMEXIT
+	mr	r4, r9
+	bl	kvmhv_accumulate_time
+#endif
 #ifdef CONFIG_KVM_XICS
 	/* We are exiting, pull the VP from the XIVE */
-	lwz	r0, VCPU_XIVE_PUSHED(r9)
+	lbz	r0, VCPU_XIVE_PUSHED(r9)
 	cmpwi	cr0, r0, 0
 	beq	1f
 	li	r7, TM_SPC_PULL_OS_CTX
 	li	r6, TM_QW1_OS
 	mfmsr	r0
-	andi.	r0, r0, MSR_IR		/* in real mode? */
+	andi.	r0, r0, MSR_DR		/* in real mode? */
 	beq	2f
 	ld	r10, HSTATE_XIVE_TIMA_VIRT(r13)
 	cmpldi	cr0, r10, 0
@@ -1454,33 +1521,42 @@ guest_exit_cont:		/* r9 = vcpu, r12 = trap, r13 = paca */
 	/* Fixup some of the state for the next load */
 	li	r10, 0
 	li	r0, 0xff
-	stw	r10, VCPU_XIVE_PUSHED(r9)
+	stb	r10, VCPU_XIVE_PUSHED(r9)
 	stb	r10, (VCPU_XIVE_SAVED_STATE+3)(r9)
 	stb	r0, (VCPU_XIVE_SAVED_STATE+4)(r9)
 	eieio
 1:
 #endif /* CONFIG_KVM_XICS */
-	/* Save more register state  */
-	mfdar	r6
-	mfdsisr	r7
-	std	r6, VCPU_DAR(r9)
-	stw	r7, VCPU_DSISR(r9)
-	/* don't overwrite fault_dar/fault_dsisr if HDSI */
-	cmpwi	r12,BOOK3S_INTERRUPT_H_DATA_STORAGE
-	beq	mc_cont
-	std	r6, VCPU_FAULT_DAR(r9)
-	stw	r7, VCPU_FAULT_DSISR(r9)
 
-	/* See if it is a machine check */
-	cmpwi	r12, BOOK3S_INTERRUPT_MACHINE_CHECK
-	beq	machine_check_realmode
-mc_cont:
-#ifdef CONFIG_KVM_BOOK3S_HV_EXIT_TIMING
-	addi	r3, r9, VCPU_TB_RMEXIT
-	mr	r4, r9
-	bl	kvmhv_accumulate_time
-#endif
+	/* For hash guest, read the guest SLB and save it away */
+	ld	r5, VCPU_KVM(r9)
+	lbz	r0, KVM_RADIX(r5)
+	li	r5, 0
+	cmpwi	r0, 0
+	bne	3f			/* for radix, save 0 entries */
+	lwz	r0,VCPU_SLB_NR(r9)	/* number of entries in SLB */
+	mtctr	r0
+	li	r6,0
+	addi	r7,r9,VCPU_SLB
+1:	slbmfee	r8,r6
+	andis.	r0,r8,SLB_ESID_V@h
+	beq	2f
+	add	r8,r8,r6		/* put index in */
+	slbmfev	r3,r6
+	std	r8,VCPU_SLB_E(r7)
+	std	r3,VCPU_SLB_V(r7)
+	addi	r7,r7,VCPU_SLB_SIZE
+	addi	r5,r5,1
+2:	addi	r6,r6,1
+	bdnz	1b
+	/* Finally clear out the SLB */
+	li	r0,0
+	slbmte	r0,r0
+	slbia
+	ptesync
+3:	stw	r5,VCPU_SLB_MAX(r9)
 
+guest_bypass:
 	mr 	r3, r12
 	/* Increment exit count, poke other threads to exit */
 	bl	kvmhv_commence_exit
@@ -1501,31 +1577,6 @@ mc_cont:
 	ori	r6,r6,1
 	mtspr	SPRN_CTRLT,r6
 4:
-	/* Check if we are running hash or radix and store it in cr2 */
-	ld	r5, VCPU_KVM(r9)
-	lbz	r0, KVM_RADIX(r5)
-	cmpwi	cr2,r0,0
-
-	/* Read the guest SLB and save it away */
-	li	r5, 0
-	bne	cr2, 3f			/* for radix, save 0 entries */
-	lwz	r0,VCPU_SLB_NR(r9)	/* number of entries in SLB */
-	mtctr	r0
-	li	r6,0
-	addi	r7,r9,VCPU_SLB
-1:	slbmfee	r8,r6
-	andis.	r0,r8,SLB_ESID_V@h
-	beq	2f
-	add	r8,r8,r6		/* put index in */
-	slbmfev	r3,r6
-	std	r8,VCPU_SLB_E(r7)
-	std	r3,VCPU_SLB_V(r7)
-	addi	r7,r7,VCPU_SLB_SIZE
-	addi	r5,r5,1
-2:	addi	r6,r6,1
-	bdnz	1b
-3:	stw	r5,VCPU_SLB_MAX(r9)
-
 	/*
 	 * Save the guest PURR/SPURR
 	 */
@@ -1803,7 +1854,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_300)
 	ld	r5, VCPU_KVM(r9)
 	lbz	r0, KVM_RADIX(r5)
 	cmpwi	cr2, r0, 0
-	beq	cr2, 3f
+	beq	cr2, 4f
 
 	/* Radix: Handle the case where the guest used an illegal PID */
 	LOAD_REG_ADDR(r4, mmu_base_pid)
@@ -1839,15 +1890,9 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_300)
 BEGIN_FTR_SECTION
 	PPC_INVALIDATE_ERAT
 END_FTR_SECTION_IFSET(CPU_FTR_POWER9_DD1)
-	b	4f
+4:
 #endif /* CONFIG_PPC_RADIX_MMU */
 
-	/* Hash: clear out SLB */
-3:	li	r5,0
-	slbmte	r5,r5
-	slbia
-	ptesync
-4:
 	/*
 	 * POWER7/POWER8 guest -> host partition switch code.
 	 * We don't have to lock against tlbies but we do
@@ -1908,16 +1953,17 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S)
 	bne	27f
 	bl	kvmppc_realmode_hmi_handler
 	nop
+	cmpdi	r3, 0
 	li	r12, BOOK3S_INTERRUPT_HMI
 	/*
-	 * At this point kvmppc_realmode_hmi_handler would have resync-ed
-	 * the TB. Hence it is not required to subtract guest timebase
-	 * offset from timebase. So, skip it.
+	 * At this point kvmppc_realmode_hmi_handler may have resync-ed
+	 * the TB, and if it has, we must not subtract the guest timebase
+	 * offset from the timebase. So, skip it.
 	 *
 	 * Also, do not call kvmppc_subcore_exit_guest() because it has
 	 * been invoked as part of kvmppc_realmode_hmi_handler().
 	 */
-	b	30f
+	beq	30f
 
 27:
 	/* Subtract timebase offset from timebase */
@@ -2744,7 +2790,32 @@ kvm_cede_prodded:
 	/* we've ceded but we want to give control to the host */
 kvm_cede_exit:
 	ld	r9, HSTATE_KVM_VCPU(r13)
-	b	guest_exit_cont
+#ifdef CONFIG_KVM_XICS
+	/* Abort if we still have a pending escalation */
+	lbz	r5, VCPU_XIVE_ESC_ON(r9)
+	cmpwi	r5, 0
+	beq	1f
+	li	r0, 0
+	stb	r0, VCPU_CEDED(r9)
+1:	/* Enable XIVE escalation */
+	li	r5, XIVE_ESB_SET_PQ_00
+	mfmsr	r0
+	andi.	r0, r0, MSR_DR		/* in real mode? */
+	beq	1f
+	ld	r10, VCPU_XIVE_ESC_VADDR(r9)
+	cmpdi	r10, 0
+	beq	3f
+	ldx	r0, r10, r5
+	b	2f
+1:	ld	r10, VCPU_XIVE_ESC_RADDR(r9)
+	cmpdi	r10, 0
+	beq	3f
+	ldcix	r0, r10, r5
+2:	sync
+	li	r0, 1
+	stb	r0, VCPU_XIVE_ESC_ON(r9)
+#endif /* CONFIG_KVM_XICS */
+3:	b	guest_exit_cont
 
 	/* Try to handle a machine check in real mode */
 machine_check_realmode:
diff --git a/arch/powerpc/kvm/book3s_xive.c b/arch/powerpc/kvm/book3s_xive.c
index 0d750d274c4e..badfdbb857a2 100644
--- a/arch/powerpc/kvm/book3s_xive.c
+++ b/arch/powerpc/kvm/book3s_xive.c
@@ -84,12 +84,22 @@ static irqreturn_t xive_esc_irq(int irq, void *data)
 {
 	struct kvm_vcpu *vcpu = data;
 
-	/* We use the existing H_PROD mechanism to wake up the target */
-	vcpu->arch.prodded = 1;
+	vcpu->arch.irq_pending = 1;
 	smp_mb();
 	if (vcpu->arch.ceded)
 		kvmppc_fast_vcpu_kick(vcpu);
 
+	/* Since we have the no-EOI flag, the interrupt is effectively
+	 * disabled now. Clearing xive_esc_on means we won't bother
+	 * doing so on the next entry.
+	 *
+	 * This also allows the entry code to know that if a PQ combination
+	 * of 10 is observed while xive_esc_on is true, it means the queue
+	 * contains an unprocessed escalation interrupt. We don't make use of
+	 * that knowledge today but might (see comment in book3s_hv_rmhandler.S)
+	 */
+	vcpu->arch.xive_esc_on = false;
+
 	return IRQ_HANDLED;
 }
 
@@ -112,19 +122,21 @@ static int xive_attach_escalation(struct kvm_vcpu *vcpu, u8 prio)
 		return -EIO;
 	}
 
-	/*
-	 * Future improvement: start with them disabled
-	 * and handle DD2 and later scheme of merged escalation
-	 * interrupts
-	 */
-	name = kasprintf(GFP_KERNEL, "kvm-%d-%d-%d",
-			 vcpu->kvm->arch.lpid, xc->server_num, prio);
+	if (xc->xive->single_escalation)
+		name = kasprintf(GFP_KERNEL, "kvm-%d-%d",
+				 vcpu->kvm->arch.lpid, xc->server_num);
+	else
+		name = kasprintf(GFP_KERNEL, "kvm-%d-%d-%d",
+				 vcpu->kvm->arch.lpid, xc->server_num, prio);
 	if (!name) {
 		pr_err("Failed to allocate escalation irq name for queue %d of VCPU %d\n",
 		       prio, xc->server_num);
 		rc = -ENOMEM;
 		goto error;
 	}
+
+	pr_devel("Escalation %s irq %d (prio %d)\n", name, xc->esc_virq[prio], prio);
+
 	rc = request_irq(xc->esc_virq[prio], xive_esc_irq,
 			 IRQF_NO_THREAD, name, vcpu);
 	if (rc) {
@@ -133,6 +145,25 @@ static int xive_attach_escalation(struct kvm_vcpu *vcpu, u8 prio)
 		goto error;
 	}
 	xc->esc_virq_names[prio] = name;
+
+	/* In single escalation mode, we grab the ESB MMIO of the
+	 * interrupt and mask it. Also populate the VCPU v/raddr
+	 * of the ESB page for use by asm entry/exit code. Finally
+	 * set the XIVE_IRQ_NO_EOI flag which will prevent the
+	 * core code from performing an EOI on the escalation
+	 * interrupt, thus leaving it effectively masked after
+	 * it fires once.
+	 */
+	if (xc->xive->single_escalation) {
+		struct irq_data *d = irq_get_irq_data(xc->esc_virq[prio]);
+		struct xive_irq_data *xd = irq_data_get_irq_handler_data(d);
+
+		xive_vm_esb_load(xd, XIVE_ESB_SET_PQ_01);
+		vcpu->arch.xive_esc_raddr = xd->eoi_page;
+		vcpu->arch.xive_esc_vaddr = (__force u64)xd->eoi_mmio;
+		xd->flags |= XIVE_IRQ_NO_EOI;
+	}
+
 	return 0;
 error:
 	irq_dispose_mapping(xc->esc_virq[prio]);
@@ -191,12 +222,12 @@ static int xive_check_provisioning(struct kvm *kvm, u8 prio)
 
 	pr_devel("Provisioning prio... %d\n", prio);
 
-	/* Provision each VCPU and enable escalations */
+	/* Provision each VCPU and enable escalations if needed */
 	kvm_for_each_vcpu(i, vcpu, kvm) {
 		if (!vcpu->arch.xive_vcpu)
 			continue;
 		rc = xive_provision_queue(vcpu, prio);
-		if (rc == 0)
+		if (rc == 0 && !xive->single_escalation)
 			xive_attach_escalation(vcpu, prio);
 		if (rc)
 			return rc;
@@ -1082,6 +1113,7 @@ int kvmppc_xive_connect_vcpu(struct kvm_device *dev,
 	/* Allocate IPI */
 	xc->vp_ipi = xive_native_alloc_irq();
 	if (!xc->vp_ipi) {
+		pr_err("Failed to allocate xive irq for VCPU IPI\n");
 		r = -EIO;
 		goto bail;
 	}
@@ -1092,18 +1124,33 @@ int kvmppc_xive_connect_vcpu(struct kvm_device *dev,
 		goto bail;
 
 	/*
+	 * Enable the VP first as the single escalation mode will
+	 * affect escalation interrupts numbering
+	 */
+	r = xive_native_enable_vp(xc->vp_id, xive->single_escalation);
+	if (r) {
+		pr_err("Failed to enable VP in OPAL, err %d\n", r);
+		goto bail;
+	}
+
+	/*
 	 * Initialize queues. Initially we set them all for no queueing
 	 * and we enable escalation for queue 0 only which we'll use for
 	 * our mfrr change notifications. If the VCPU is hot-plugged, we
-	 * do handle provisioning however.
+	 * do handle provisioning however based on the existing "map"
+	 * of enabled queues.
 	 */
 	for (i = 0; i < KVMPPC_XIVE_Q_COUNT; i++) {
 		struct xive_q *q = &xc->queues[i];
 
+		/* Single escalation, no queue 7 */
+		if (i == 7 && xive->single_escalation)
+			break;
+
 		/* Is queue already enabled ? Provision it */
 		if (xive->qmap & (1 << i)) {
 			r = xive_provision_queue(vcpu, i);
-			if (r == 0)
+			if (r == 0 && !xive->single_escalation)
 				xive_attach_escalation(vcpu, i);
 			if (r)
 				goto bail;
@@ -1123,11 +1170,6 @@ int kvmppc_xive_connect_vcpu(struct kvm_device *dev,
 	if (r)
 		goto bail;
 
-	/* Enable the VP */
-	r = xive_native_enable_vp(xc->vp_id);
-	if (r)
-		goto bail;
-
 	/* Route the IPI */
 	r = xive_native_configure_irq(xc->vp_ipi, xc->vp_id, 0, XICS_IPI);
 	if (!r)
@@ -1474,6 +1516,7 @@ static int xive_set_source(struct kvmppc_xive *xive, long irq, u64 addr)
 
 	pr_devel("  val=0x016%llx (server=0x%x, guest_prio=%d)\n",
 		 val, server, guest_prio);
+
 	/*
 	 * If the source doesn't already have an IPI, allocate
 	 * one and get the corresponding data
@@ -1762,6 +1805,8 @@ static int kvmppc_xive_create(struct kvm_device *dev, u32 type)
 	if (xive->vp_base == XIVE_INVALID_VP)
 		ret = -ENOMEM;
 
+	xive->single_escalation = xive_native_has_single_escalation();
+
 	if (ret) {
 		kfree(xive);
 		return ret;
@@ -1795,6 +1840,7 @@ static int xive_debug_show(struct seq_file *m, void *private)
 
 	kvm_for_each_vcpu(i, vcpu, kvm) {
 		struct kvmppc_xive_vcpu *xc = vcpu->arch.xive_vcpu;
+		unsigned int i;
 
 		if (!xc)
 			continue;
@@ -1804,6 +1850,33 @@ static int xive_debug_show(struct seq_file *m, void *private)
 			   xc->server_num, xc->cppr, xc->hw_cppr,
 			   xc->mfrr, xc->pending,
 			   xc->stat_rm_h_xirr, xc->stat_vm_h_xirr);
+		for (i = 0; i < KVMPPC_XIVE_Q_COUNT; i++) {
+			struct xive_q *q = &xc->queues[i];
+			u32 i0, i1, idx;
+
+			if (!q->qpage && !xc->esc_virq[i])
+				continue;
+
+			seq_printf(m, " [q%d]: ", i);
+
+			if (q->qpage) {
+				idx = q->idx;
+				i0 = be32_to_cpup(q->qpage + idx);
+				idx = (idx + 1) & q->msk;
+				i1 = be32_to_cpup(q->qpage + idx);
+				seq_printf(m, "T=%d %08x %08x... \n", q->toggle, i0, i1);
+			}
+			if (xc->esc_virq[i]) {
+				struct irq_data *d = irq_get_irq_data(xc->esc_virq[i]);
+				struct xive_irq_data *xd = irq_data_get_irq_handler_data(d);
+				u64 pq = xive_vm_esb_load(xd, XIVE_ESB_GET);
+				seq_printf(m, "E:%c%c I(%d:%llx:%llx)",
+					   (pq & XIVE_ESB_VAL_P) ? 'P' : 'p',
+					   (pq & XIVE_ESB_VAL_Q) ? 'Q' : 'q',
+					   xc->esc_virq[i], pq, xd->eoi_page);
+				seq_printf(m, "\n");
+			}
+		}
 
 		t_rm_h_xirr += xc->stat_rm_h_xirr;
 		t_rm_h_ipoll += xc->stat_rm_h_ipoll;
diff --git a/arch/powerpc/kvm/book3s_xive.h b/arch/powerpc/kvm/book3s_xive.h
index 6ba63f8e8a61..a08ae6fd4c51 100644
--- a/arch/powerpc/kvm/book3s_xive.h
+++ b/arch/powerpc/kvm/book3s_xive.h
@@ -120,6 +120,8 @@ struct kvmppc_xive {
 	u32	q_order;
 	u32	q_page_order;
 
+	/* Flags */
+	u8	single_escalation;
 };
 
 #define KVMPPC_XIVE_Q_COUNT	8
@@ -201,25 +203,20 @@ static inline struct kvmppc_xive_src_block *kvmppc_xive_find_source(struct kvmpp
  * is as follow.
  *
  * Guest request for 0...6 are honored. Guest request for anything
- * higher results in a priority of 7 being applied.
- *
- * However, when XIRR is returned via H_XIRR, 7 is translated to 0xb
- * in order to match AIX expectations
+ * higher results in a priority of 6 being applied.
  *
  * Similar mapping is done for CPPR values
  */
 static inline u8 xive_prio_from_guest(u8 prio)
 {
-	if (prio == 0xff || prio < 8)
+	if (prio == 0xff || prio < 6)
 		return prio;
-	return 7;
+	return 6;
 }
 
 static inline u8 xive_prio_to_guest(u8 prio)
 {
-	if (prio == 0xff || prio < 7)
-		return prio;
-	return 0xb;
+	return prio;
 }
 
 static inline u32 __xive_read_eq(__be32 *qpage, u32 msk, u32 *idx, u32 *toggle)
diff --git a/arch/powerpc/kvm/powerpc.c b/arch/powerpc/kvm/powerpc.c
index 545a230f675f..748562ec9a04 100644
--- a/arch/powerpc/kvm/powerpc.c
+++ b/arch/powerpc/kvm/powerpc.c
@@ -763,7 +763,7 @@ int kvm_arch_vcpu_init(struct kvm_vcpu *vcpu)
 
 	hrtimer_init(&vcpu->arch.dec_timer, CLOCK_REALTIME, HRTIMER_MODE_ABS);
 	vcpu->arch.dec_timer.function = kvmppc_decrementer_wakeup;
-	vcpu->arch.dec_expires = ~(u64)0;
+	vcpu->arch.dec_expires = get_tb();
 
 #ifdef CONFIG_KVM_EXIT_TIMING
 	mutex_init(&vcpu->arch.exit_timing_lock);
@@ -1106,11 +1106,9 @@ int kvmppc_handle_vsx_load(struct kvm_run *run, struct kvm_vcpu *vcpu,
 {
 	enum emulation_result emulated = EMULATE_DONE;
 
-	/* Currently, mmio_vsx_copy_nums only allowed to be less than 4 */
-	if ( (vcpu->arch.mmio_vsx_copy_nums > 4) ||
-		(vcpu->arch.mmio_vsx_copy_nums < 0) ) {
+	/* Currently, mmio_vsx_copy_nums only allowed to be 4 or less */
+	if (vcpu->arch.mmio_vsx_copy_nums > 4)
 		return EMULATE_FAIL;
-	}
 
 	while (vcpu->arch.mmio_vsx_copy_nums) {
 		emulated = __kvmppc_handle_load(run, vcpu, rt, bytes,
@@ -1252,11 +1250,9 @@ int kvmppc_handle_vsx_store(struct kvm_run *run, struct kvm_vcpu *vcpu,
 
 	vcpu->arch.io_gpr = rs;
 
-	/* Currently, mmio_vsx_copy_nums only allowed to be less than 4 */
-	if ( (vcpu->arch.mmio_vsx_copy_nums > 4) ||
-		(vcpu->arch.mmio_vsx_copy_nums < 0) ) {
+	/* Currently, mmio_vsx_copy_nums only allowed to be 4 or less */
+	if (vcpu->arch.mmio_vsx_copy_nums > 4)
 		return EMULATE_FAIL;
-	}
 
 	while (vcpu->arch.mmio_vsx_copy_nums) {
 		if (kvmppc_get_vsr_data(vcpu, rs, &val) == -1)
diff --git a/arch/powerpc/kvm/timing.c b/arch/powerpc/kvm/timing.c
index e44d2b2ea97e..1c03c978eb18 100644
--- a/arch/powerpc/kvm/timing.c
+++ b/arch/powerpc/kvm/timing.c
@@ -143,8 +143,7 @@ static int kvmppc_exit_timing_show(struct seq_file *m, void *private)
 	int i;
 	u64 min, max, sum, sum_quad;
 
-	seq_printf(m, "%s", "type	count	min	max	sum	sum_squared\n");
-
+	seq_puts(m, "type	count	min	max	sum	sum_squared\n");
 
 	for (i = 0; i < __NUMBER_OF_KVM_EXIT_TYPES; i++) {