From cc902ad4f2b7cd3dd2cc268c63f6fb99fb1abf0f Mon Sep 17 00:00:00 2001
From: Bharat Bhushan <r65777@freescale.com>
Date: Thu, 22 Mar 2012 18:39:11 +0000
Subject: [PATCH 01/16] KVM: Use minimum and maximum address mapped by TLB1

Keep track of minimum and maximum address mapped by tlb1.
This helps in TLBMISS handling in KVM to quick check whether the address lies in mapped range.
If address does not lies in this range then no need to look in each tlb1 entry of tlb1 array.

Signed-off-by: Bharat Bhushan <bharat.bhushan@freescale.com>
Signed-off-by: Alexander Graf <agraf@suse.de>
---
 arch/powerpc/kvm/e500.h     |  4 ++
 arch/powerpc/kvm/e500_tlb.c | 88 ++++++++++++++++++++++++++++++++++++-
 2 files changed, 90 insertions(+), 2 deletions(-)

diff --git a/arch/powerpc/kvm/e500.h b/arch/powerpc/kvm/e500.h
index 7967f3f10a16..aa8b81428bf4 100644
--- a/arch/powerpc/kvm/e500.h
+++ b/arch/powerpc/kvm/e500.h
@@ -89,6 +89,10 @@ struct kvmppc_vcpu_e500 {
 	u64 *g2h_tlb1_map;
 	unsigned int *h2g_tlb1_rmap;
 
+	/* Minimum and maximum address mapped my TLB1 */
+	unsigned long tlb1_min_eaddr;
+	unsigned long tlb1_max_eaddr;
+
 #ifdef CONFIG_KVM_E500V2
 	u32 pid[E500_PID_NUM];
 
diff --git a/arch/powerpc/kvm/e500_tlb.c b/arch/powerpc/kvm/e500_tlb.c
index e05232b746ff..c510fc961302 100644
--- a/arch/powerpc/kvm/e500_tlb.c
+++ b/arch/powerpc/kvm/e500_tlb.c
@@ -261,6 +261,9 @@ static int kvmppc_e500_tlb_index(struct kvmppc_vcpu_e500 *vcpu_e500,
 		set_base = gtlb0_set_base(vcpu_e500, eaddr);
 		size = vcpu_e500->gtlb_params[0].ways;
 	} else {
+		if (eaddr < vcpu_e500->tlb1_min_eaddr ||
+				eaddr > vcpu_e500->tlb1_max_eaddr)
+			return -1;
 		set_base = 0;
 	}
 
@@ -583,6 +586,65 @@ static int kvmppc_e500_tlb1_map(struct kvmppc_vcpu_e500 *vcpu_e500,
 	return victim;
 }
 
+static void kvmppc_recalc_tlb1map_range(struct kvmppc_vcpu_e500 *vcpu_e500)
+{
+	int size = vcpu_e500->gtlb_params[1].entries;
+	unsigned int offset;
+	gva_t eaddr;
+	int i;
+
+	vcpu_e500->tlb1_min_eaddr = ~0UL;
+	vcpu_e500->tlb1_max_eaddr = 0;
+	offset = vcpu_e500->gtlb_offset[1];
+
+	for (i = 0; i < size; i++) {
+		struct kvm_book3e_206_tlb_entry *tlbe =
+			&vcpu_e500->gtlb_arch[offset + i];
+
+		if (!get_tlb_v(tlbe))
+			continue;
+
+		eaddr = get_tlb_eaddr(tlbe);
+		vcpu_e500->tlb1_min_eaddr =
+				min(vcpu_e500->tlb1_min_eaddr, eaddr);
+
+		eaddr = get_tlb_end(tlbe);
+		vcpu_e500->tlb1_max_eaddr =
+				max(vcpu_e500->tlb1_max_eaddr, eaddr);
+	}
+}
+
+static int kvmppc_need_recalc_tlb1map_range(struct kvmppc_vcpu_e500 *vcpu_e500,
+				struct kvm_book3e_206_tlb_entry *gtlbe)
+{
+	unsigned long start, end, size;
+
+	size = get_tlb_bytes(gtlbe);
+	start = get_tlb_eaddr(gtlbe) & ~(size - 1);
+	end = start + size - 1;
+
+	return vcpu_e500->tlb1_min_eaddr == start ||
+			vcpu_e500->tlb1_max_eaddr == end;
+}
+
+/* This function is supposed to be called for a adding a new valid tlb entry */
+static void kvmppc_set_tlb1map_range(struct kvm_vcpu *vcpu,
+				struct kvm_book3e_206_tlb_entry *gtlbe)
+{
+	unsigned long start, end, size;
+	struct kvmppc_vcpu_e500 *vcpu_e500 = to_e500(vcpu);
+
+	if (!get_tlb_v(gtlbe))
+		return;
+
+	size = get_tlb_bytes(gtlbe);
+	start = get_tlb_eaddr(gtlbe) & ~(size - 1);
+	end = start + size - 1;
+
+	vcpu_e500->tlb1_min_eaddr = min(vcpu_e500->tlb1_min_eaddr, start);
+	vcpu_e500->tlb1_max_eaddr = max(vcpu_e500->tlb1_max_eaddr, end);
+}
+
 static inline int kvmppc_e500_gtlbe_invalidate(
 				struct kvmppc_vcpu_e500 *vcpu_e500,
 				int tlbsel, int esel)
@@ -593,6 +655,9 @@ static inline int kvmppc_e500_gtlbe_invalidate(
 	if (unlikely(get_tlb_iprot(gtlbe)))
 		return -1;
 
+	if (tlbsel == 1 && kvmppc_need_recalc_tlb1map_range(vcpu_e500, gtlbe))
+		kvmppc_recalc_tlb1map_range(vcpu_e500);
+
 	gtlbe->mas1 = 0;
 
 	return 0;
@@ -792,14 +857,19 @@ int kvmppc_e500_emul_tlbwe(struct kvm_vcpu *vcpu)
 	struct kvmppc_vcpu_e500 *vcpu_e500 = to_e500(vcpu);
 	struct kvm_book3e_206_tlb_entry *gtlbe, stlbe;
 	int tlbsel, esel, stlbsel, sesel;
+	int recal = 0;
 
 	tlbsel = get_tlb_tlbsel(vcpu);
 	esel = get_tlb_esel(vcpu, tlbsel);
 
 	gtlbe = get_entry(vcpu_e500, tlbsel, esel);
 
-	if (get_tlb_v(gtlbe))
+	if (get_tlb_v(gtlbe)) {
 		inval_gtlbe_on_host(vcpu_e500, tlbsel, esel);
+		if ((tlbsel == 1) &&
+			kvmppc_need_recalc_tlb1map_range(vcpu_e500, gtlbe))
+			recal = 1;
+	}
 
 	gtlbe->mas1 = vcpu->arch.shared->mas1;
 	gtlbe->mas2 = vcpu->arch.shared->mas2;
@@ -808,6 +878,18 @@ int kvmppc_e500_emul_tlbwe(struct kvm_vcpu *vcpu)
 	trace_kvm_booke206_gtlb_write(vcpu->arch.shared->mas0, gtlbe->mas1,
 	                              gtlbe->mas2, gtlbe->mas7_3);
 
+	if (tlbsel == 1) {
+		/*
+		 * If a valid tlb1 entry is overwritten then recalculate the
+		 * min/max TLB1 map address range otherwise no need to look
+		 * in tlb1 array.
+		 */
+		if (recal)
+			kvmppc_recalc_tlb1map_range(vcpu_e500);
+		else
+			kvmppc_set_tlb1map_range(vcpu, gtlbe);
+	}
+
 	/* Invalidate shadow mappings for the about-to-be-clobbered TLBE. */
 	if (tlbe_is_host_safe(vcpu, gtlbe)) {
 		u64 eaddr;
@@ -1145,6 +1227,7 @@ int kvm_vcpu_ioctl_config_tlb(struct kvm_vcpu *vcpu,
 	vcpu_e500->gtlb_params[1].ways = params.tlb_sizes[1];
 	vcpu_e500->gtlb_params[1].sets = 1;
 
+	kvmppc_recalc_tlb1map_range(vcpu_e500);
 	return 0;
 
 err_put_page:
@@ -1163,7 +1246,7 @@ int kvm_vcpu_ioctl_dirty_tlb(struct kvm_vcpu *vcpu,
 			     struct kvm_dirty_tlb *dirty)
 {
 	struct kvmppc_vcpu_e500 *vcpu_e500 = to_e500(vcpu);
-
+	kvmppc_recalc_tlb1map_range(vcpu_e500);
 	clear_tlb_refs(vcpu_e500);
 	return 0;
 }
@@ -1272,6 +1355,7 @@ int kvmppc_e500_tlb_init(struct kvmppc_vcpu_e500 *vcpu_e500)
 	vcpu->arch.tlbcfg[1] |=
 		vcpu_e500->gtlb_params[1].ways << TLBnCFG_ASSOC_SHIFT;
 
+	kvmppc_recalc_tlb1map_range(vcpu_e500);
 	return 0;
 
 err:

From 6e35994d1f6831af1e5577e28c363c9137d7d597 Mon Sep 17 00:00:00 2001
From: Bharat Bhushan <r65777@freescale.com>
Date: Wed, 18 Apr 2012 06:01:19 +0000
Subject: [PATCH 02/16] KVM: PPC: Use clockevent multiplier and shifter for
 decrementer

Time for which the hrtimer is started for decrementer emulation is calculated
using tb_ticks_per_usec. While hrtimer uses the clockevent for DEC
reprogramming (if needed) and which calculate timebase ticks using the
multiplier and shifter mechanism implemented within clockevent layer.

It was observed that this conversion (timebase->time->timebase) are not
correct because the mechanism are not consistent.
In our setup it adds 2% jitter.

With this patch clockevent multiplier and shifter mechanism are used when
starting hrtimer for decrementer emulation. Now the jitter is < 0.5%.

Signed-off-by: Bharat Bhushan <bharat.bhushan@freescale.com>
Signed-off-by: Alexander Graf <agraf@suse.de>
---
 arch/powerpc/include/asm/time.h | 1 +
 arch/powerpc/kernel/time.c      | 3 ++-
 arch/powerpc/kvm/emulate.c      | 9 +++++++--
 3 files changed, 10 insertions(+), 3 deletions(-)

diff --git a/arch/powerpc/include/asm/time.h b/arch/powerpc/include/asm/time.h
index 2136f58a54e8..3b4b4a8da922 100644
--- a/arch/powerpc/include/asm/time.h
+++ b/arch/powerpc/include/asm/time.h
@@ -23,6 +23,7 @@
 extern unsigned long tb_ticks_per_jiffy;
 extern unsigned long tb_ticks_per_usec;
 extern unsigned long tb_ticks_per_sec;
+extern struct clock_event_device decrementer_clockevent;
 
 struct rtc_time;
 extern void to_tm(int tim, struct rtc_time * tm);
diff --git a/arch/powerpc/kernel/time.c b/arch/powerpc/kernel/time.c
index 2c42cd72d0f5..99a995c2a3f2 100644
--- a/arch/powerpc/kernel/time.c
+++ b/arch/powerpc/kernel/time.c
@@ -100,7 +100,7 @@ static int decrementer_set_next_event(unsigned long evt,
 static void decrementer_set_mode(enum clock_event_mode mode,
 				 struct clock_event_device *dev);
 
-static struct clock_event_device decrementer_clockevent = {
+struct clock_event_device decrementer_clockevent = {
 	.name           = "decrementer",
 	.rating         = 200,
 	.irq            = 0,
@@ -108,6 +108,7 @@ static struct clock_event_device decrementer_clockevent = {
 	.set_mode       = decrementer_set_mode,
 	.features       = CLOCK_EVT_FEAT_ONESHOT,
 };
+EXPORT_SYMBOL(decrementer_clockevent);
 
 DEFINE_PER_CPU(u64, decrementers_next_tb);
 static DEFINE_PER_CPU(struct clock_event_device, decrementers);
diff --git a/arch/powerpc/kvm/emulate.c b/arch/powerpc/kvm/emulate.c
index afc9154f1aef..b5872f61a213 100644
--- a/arch/powerpc/kvm/emulate.c
+++ b/arch/powerpc/kvm/emulate.c
@@ -23,6 +23,7 @@
 #include <linux/types.h>
 #include <linux/string.h>
 #include <linux/kvm_host.h>
+#include <linux/clockchips.h>
 
 #include <asm/reg.h>
 #include <asm/time.h>
@@ -104,8 +105,12 @@ void kvmppc_emulate_dec(struct kvm_vcpu *vcpu)
 	 */
 
 	dec_time = vcpu->arch.dec;
-	dec_time *= 1000;
-	do_div(dec_time, tb_ticks_per_usec);
+	/*
+	 * Guest timebase ticks at the same frequency as host decrementer.
+	 * So use the host decrementer calculations for decrementer emulation.
+	 */
+	dec_time = dec_time << decrementer_clockevent.shift;
+	do_div(dec_time, decrementer_clockevent.mult);
 	dec_nsec = do_div(dec_time, NSEC_PER_SEC);
 	hrtimer_start(&vcpu->arch.dec_timer,
 		ktime_set(dec_time, dec_nsec), HRTIMER_MODE_REL);

From 185e4188dab6456409cad66c579501dd89487188 Mon Sep 17 00:00:00 2001
From: Varun Sethi <Varun.Sethi@freescale.com>
Date: Wed, 25 Apr 2012 01:26:43 +0000
Subject: [PATCH 03/16] KVM: PPC: bookehv: Use a Macro for saving/restoring
 guest registers to/from their 64 bit copies.

Introduced PPC_STD/PPC_LD macros for saving/restoring guest registers to/from their 64 bit copies.

Signed-off-by: Varun Sethi <Varun.Sethi@freescale.com>
Signed-off-by: Alexander Graf <agraf@suse.de>
---
 arch/powerpc/include/asm/kvm_asm.h    |  8 ++++++++
 arch/powerpc/kvm/bookehv_interrupts.S | 24 ++++--------------------
 2 files changed, 12 insertions(+), 20 deletions(-)

diff --git a/arch/powerpc/include/asm/kvm_asm.h b/arch/powerpc/include/asm/kvm_asm.h
index 097815233284..7d4018dd0e11 100644
--- a/arch/powerpc/include/asm/kvm_asm.h
+++ b/arch/powerpc/include/asm/kvm_asm.h
@@ -20,6 +20,14 @@
 #ifndef __POWERPC_KVM_ASM_H__
 #define __POWERPC_KVM_ASM_H__
 
+#ifdef CONFIG_64BIT
+#define PPC_STD(sreg, offset, areg)  std sreg, (offset)(areg)
+#define PPC_LD(treg, offset, areg)   ld treg, (offset)(areg)
+#else
+#define PPC_STD(sreg, offset, areg)  stw sreg, (offset+4)(areg)
+#define PPC_LD(treg, offset, areg)   lwz treg, (offset+4)(areg)
+#endif
+
 /* IVPR must be 64KiB-aligned. */
 #define VCPU_SIZE_ORDER 4
 #define VCPU_SIZE_LOG   (VCPU_SIZE_ORDER + 12)
diff --git a/arch/powerpc/kvm/bookehv_interrupts.S b/arch/powerpc/kvm/bookehv_interrupts.S
index 909e96e0650c..41d34850f826 100644
--- a/arch/powerpc/kvm/bookehv_interrupts.S
+++ b/arch/powerpc/kvm/bookehv_interrupts.S
@@ -93,11 +93,7 @@
 #endif
 
 	oris	r8, r6, MSR_CE@h
-#ifdef CONFIG_64BIT
-	std	r6, (VCPU_SHARED_MSR)(r11)
-#else
-	stw	r6, (VCPU_SHARED_MSR + 4)(r11)
-#endif
+	PPC_STD(r6, VCPU_SHARED_MSR, r11)
 	ori	r8, r8, MSR_ME | MSR_RI
 	PPC_STL	r5, VCPU_PC(r4)
 
@@ -335,11 +331,7 @@ _GLOBAL(kvmppc_resume_host)
 	stw	r5, VCPU_SHARED_MAS0(r11)
 	mfspr	r7, SPRN_MAS2
 	stw	r6, VCPU_SHARED_MAS1(r11)
-#ifdef CONFIG_64BIT
-	std	r7, (VCPU_SHARED_MAS2)(r11)
-#else
-	stw	r7, (VCPU_SHARED_MAS2 + 4)(r11)
-#endif
+	PPC_STD(r7, VCPU_SHARED_MAS2, r11)
 	mfspr	r5, SPRN_MAS3
 	mfspr	r6, SPRN_MAS4
 	stw	r5, VCPU_SHARED_MAS7_3+4(r11)
@@ -527,11 +519,7 @@ lightweight_exit:
 	stw	r3, VCPU_HOST_MAS6(r4)
 	lwz	r3, VCPU_SHARED_MAS0(r11)
 	lwz	r5, VCPU_SHARED_MAS1(r11)
-#ifdef CONFIG_64BIT
-	ld	r6, (VCPU_SHARED_MAS2)(r11)
-#else
-	lwz	r6, (VCPU_SHARED_MAS2 + 4)(r11)
-#endif
+	PPC_LD(r6, VCPU_SHARED_MAS2, r11)
 	lwz	r7, VCPU_SHARED_MAS7_3+4(r11)
 	lwz	r8, VCPU_SHARED_MAS4(r11)
 	mtspr	SPRN_MAS0, r3
@@ -565,11 +553,7 @@ lightweight_exit:
 	PPC_LL	r6, VCPU_CTR(r4)
 	PPC_LL	r7, VCPU_CR(r4)
 	PPC_LL	r8, VCPU_PC(r4)
-#ifdef CONFIG_64BIT
-	ld	r9, (VCPU_SHARED_MSR)(r11)
-#else
-	lwz	r9, (VCPU_SHARED_MSR + 4)(r11)
-#endif
+	PPC_LD(r9, VCPU_SHARED_MSR, r11)
 	PPC_LL	r0, VCPU_GPR(r0)(r4)
 	PPC_LL	r1, VCPU_GPR(r1)(r4)
 	PPC_LL	r2, VCPU_GPR(r2)(r4)

From 3d4c6826ed2a28e69e8ee14f1d58c4c8622f04b3 Mon Sep 17 00:00:00 2001
From: Alexander Graf <agraf@suse.de>
Date: Wed, 25 Apr 2012 13:48:54 +0200
Subject: [PATCH 04/16] KVM: PPC: Restrict PPC_[L|ST]D macro to asm code

We only want asm code macros to be accessible from asm code, so #ifdef it
depending on it.

Signed-off-by: Alexander Graf <agraf@suse.de>
---
 arch/powerpc/include/asm/kvm_asm.h | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/arch/powerpc/include/asm/kvm_asm.h b/arch/powerpc/include/asm/kvm_asm.h
index 7d4018dd0e11..76fdcfef0889 100644
--- a/arch/powerpc/include/asm/kvm_asm.h
+++ b/arch/powerpc/include/asm/kvm_asm.h
@@ -20,6 +20,7 @@
 #ifndef __POWERPC_KVM_ASM_H__
 #define __POWERPC_KVM_ASM_H__
 
+#ifdef __ASSEMBLY__
 #ifdef CONFIG_64BIT
 #define PPC_STD(sreg, offset, areg)  std sreg, (offset)(areg)
 #define PPC_LD(treg, offset, areg)   ld treg, (offset)(areg)
@@ -27,6 +28,7 @@
 #define PPC_STD(sreg, offset, areg)  stw sreg, (offset+4)(areg)
 #define PPC_LD(treg, offset, areg)   lwz treg, (offset+4)(areg)
 #endif
+#endif
 
 /* IVPR must be 64KiB-aligned. */
 #define VCPU_SIZE_ORDER 4

From 30124906db8598255fba32c8bf0adb7e8f1503ab Mon Sep 17 00:00:00 2001
From: Varun Sethi <Varun.Sethi@freescale.com>
Date: Wed, 25 Apr 2012 01:27:34 +0000
Subject: [PATCH 05/16] KVM: PPC: booke(hv): Fix save/restore of guest
 accessible SPRGs.

For Guest accessible SPRGs 4-7, save/restore must be handled differently for 64bit and
non-64 bit case. Use the PPC_STD/PPC_LD macros for saving/restoring to/from these registers.

Signed-off-by: Varun Sethi <Varun.Sethi@freescale.com>
Signed-off-by: Alexander Graf <agraf@suse.de>
---
 arch/powerpc/kvm/booke_interrupts.S   |  8 ++++----
 arch/powerpc/kvm/bookehv_interrupts.S | 16 ++++++++--------
 2 files changed, 12 insertions(+), 12 deletions(-)

diff --git a/arch/powerpc/kvm/booke_interrupts.S b/arch/powerpc/kvm/booke_interrupts.S
index c8c4b878795a..8feec2ff3928 100644
--- a/arch/powerpc/kvm/booke_interrupts.S
+++ b/arch/powerpc/kvm/booke_interrupts.S
@@ -419,13 +419,13 @@ lightweight_exit:
 	 * written directly to the shared area, so we
 	 * need to reload them here with the guest's values.
 	 */
-	lwz	r3, VCPU_SHARED_SPRG4(r5)
+	PPC_LD(r3, VCPU_SHARED_SPRG4, r5)
 	mtspr	SPRN_SPRG4W, r3
-	lwz	r3, VCPU_SHARED_SPRG5(r5)
+	PPC_LD(r3, VCPU_SHARED_SPRG5, r5)
 	mtspr	SPRN_SPRG5W, r3
-	lwz	r3, VCPU_SHARED_SPRG6(r5)
+	PPC_LD(r3, VCPU_SHARED_SPRG6, r5)
 	mtspr	SPRN_SPRG6W, r3
-	lwz	r3, VCPU_SHARED_SPRG7(r5)
+	PPC_LD(r3, VCPU_SHARED_SPRG7, r5)
 	mtspr	SPRN_SPRG7W, r3
 
 #ifdef CONFIG_KVM_EXIT_TIMING
diff --git a/arch/powerpc/kvm/bookehv_interrupts.S b/arch/powerpc/kvm/bookehv_interrupts.S
index 41d34850f826..b7608ac52b66 100644
--- a/arch/powerpc/kvm/bookehv_interrupts.S
+++ b/arch/powerpc/kvm/bookehv_interrupts.S
@@ -316,13 +316,13 @@ _GLOBAL(kvmppc_resume_host)
 	PPC_STL	r5, VCPU_LR(r4)
 	mfspr	r7, SPRN_SPRG5
 	PPC_STL	r3, VCPU_VRSAVE(r4)
-	PPC_STL	r6, VCPU_SHARED_SPRG4(r11)
+	PPC_STD(r6, VCPU_SHARED_SPRG4, r11)
 	mfspr	r8, SPRN_SPRG6
-	PPC_STL	r7, VCPU_SHARED_SPRG5(r11)
+	PPC_STD(r7, VCPU_SHARED_SPRG5, r11)
 	mfspr	r9, SPRN_SPRG7
-	PPC_STL	r8, VCPU_SHARED_SPRG6(r11)
+	PPC_STD(r8, VCPU_SHARED_SPRG6, r11)
 	mfxer	r3
-	PPC_STL	r9, VCPU_SHARED_SPRG7(r11)
+	PPC_STD(r9, VCPU_SHARED_SPRG7, r11)
 
 	/* save guest MAS registers and restore host mas4 & mas6 */
 	mfspr	r5, SPRN_MAS0
@@ -537,13 +537,13 @@ lightweight_exit:
 	 * SPRGs, so we need to reload them here with the guest's values.
 	 */
 	lwz	r3, VCPU_VRSAVE(r4)
-	lwz	r5, VCPU_SHARED_SPRG4(r11)
+	PPC_LD(r5, VCPU_SHARED_SPRG4, r11)
 	mtspr	SPRN_VRSAVE, r3
-	lwz	r6, VCPU_SHARED_SPRG5(r11)
+	PPC_LD(r6, VCPU_SHARED_SPRG5, r11)
 	mtspr	SPRN_SPRG4W, r5
-	lwz	r7, VCPU_SHARED_SPRG6(r11)
+	PPC_LD(r7, VCPU_SHARED_SPRG6, r11)
 	mtspr	SPRN_SPRG5W, r6
-	lwz	r8, VCPU_SHARED_SPRG7(r11)
+	PPC_LD(r8, VCPU_SHARED_SPRG7, r11)
 	mtspr	SPRN_SPRG6W, r7
 	mtspr	SPRN_SPRG7W, r8
 

From 8c2d0be7efb0b92b5e4f89ea4363f3cdc11e2459 Mon Sep 17 00:00:00 2001
From: Alexander Graf <agraf@suse.de>
Date: Wed, 25 Apr 2012 14:28:23 +0200
Subject: [PATCH 06/16] KVM: PPC: Book3S: PR: Optimize entry path

By shuffling a few instructions around we can execute more memory
loads in parallel, giving us a small performance boost.

With this patch and a simple priviledged SPR access loop guest, I get
a speed bump from 2013052 to 2035607 exits per second.

Signed-off-by: Alexander Graf <agraf@suse.de>
---
 arch/powerpc/kvm/book3s_segment.S | 13 +++++++------
 1 file changed, 7 insertions(+), 6 deletions(-)

diff --git a/arch/powerpc/kvm/book3s_segment.S b/arch/powerpc/kvm/book3s_segment.S
index 0676ae249b9f..6bae0a9414ba 100644
--- a/arch/powerpc/kvm/book3s_segment.S
+++ b/arch/powerpc/kvm/book3s_segment.S
@@ -128,24 +128,25 @@ no_dcbz32_on:
 	/* First clear RI in our current MSR value */
 	li	r0, MSR_RI
 	andc	r6, r6, r0
-	MTMSR_EERI(r6)
-	mtsrr0	r9
-	mtsrr1	r4
 
 	PPC_LL	r0, SVCPU_R0(r3)
 	PPC_LL	r1, SVCPU_R1(r3)
 	PPC_LL	r2, SVCPU_R2(r3)
-	PPC_LL	r4, SVCPU_R4(r3)
 	PPC_LL	r5, SVCPU_R5(r3)
-	PPC_LL	r6, SVCPU_R6(r3)
 	PPC_LL	r7, SVCPU_R7(r3)
 	PPC_LL	r8, SVCPU_R8(r3)
-	PPC_LL	r9, SVCPU_R9(r3)
 	PPC_LL	r10, SVCPU_R10(r3)
 	PPC_LL	r11, SVCPU_R11(r3)
 	PPC_LL	r12, SVCPU_R12(r3)
 	PPC_LL	r13, SVCPU_R13(r3)
 
+	MTMSR_EERI(r6)
+	mtsrr0	r9
+	mtsrr1	r4
+
+	PPC_LL	r4, SVCPU_R4(r3)
+	PPC_LL	r6, SVCPU_R6(r3)
+	PPC_LL	r9, SVCPU_R9(r3)
 	PPC_LL	r3, (SVCPU_R3)(r3)
 
 	RFI

From af415087d2bbbef3cc25cdf371bfb0460cf66b3b Mon Sep 17 00:00:00 2001
From: Alexander Graf <agraf@suse.de>
Date: Wed, 25 Apr 2012 14:29:57 +0200
Subject: [PATCH 07/16] KVM: PPC: Book3S: PR: No isync in slbie path

While messing around with the SLBs we're running in real mode. The
entry to guest space goes through rfid, which is context synchronizing,
so there's no need to manually synchronize anything through isync.

With this patch and a simple priviledged SPR access loop guest, I get
a speed bump from 2035607 to 2181301 exits per second.

Signed-off-by: Alexander Graf <agraf@suse.de>
---
 arch/powerpc/kvm/book3s_64_slb.S | 2 --
 1 file changed, 2 deletions(-)

diff --git a/arch/powerpc/kvm/book3s_64_slb.S b/arch/powerpc/kvm/book3s_64_slb.S
index f2e6e48ea463..56b983e7b738 100644
--- a/arch/powerpc/kvm/book3s_64_slb.S
+++ b/arch/powerpc/kvm/book3s_64_slb.S
@@ -90,8 +90,6 @@ slb_exit_skip_ ## num:
 	or      r10, r10, r12
 	slbie	r10
 
-	isync
-
 	/* Fill SLB with our shadow */
 
 	lbz	r12, SVCPU_SLB_MAX(r3)

From 518f040c826d569daf260153d4f75c21b6d9979b Mon Sep 17 00:00:00 2001
From: Mihai Caraman <mihai.caraman@freescale.com>
Date: Mon, 16 Apr 2012 04:08:54 +0000
Subject: [PATCH 08/16] KVM: PPC: bookehv: Use lwz/stw instead of
 PPC_LL/PPC_STL for 32-bit fields

Interrupt code used PPC_LL/PPC_STL macros to load/store some of u32 fields
which led to memory overflow on 64-bit. Use lwz/stw instead.

Signed-off-by: Mihai Caraman <mihai.caraman@freescale.com>
Signed-off-by: Alexander Graf <agraf@suse.de>
---
 arch/powerpc/kvm/bookehv_interrupts.S | 16 ++++++++--------
 1 file changed, 8 insertions(+), 8 deletions(-)

diff --git a/arch/powerpc/kvm/bookehv_interrupts.S b/arch/powerpc/kvm/bookehv_interrupts.S
index b7608ac52b66..06750cc1050b 100644
--- a/arch/powerpc/kvm/bookehv_interrupts.S
+++ b/arch/powerpc/kvm/bookehv_interrupts.S
@@ -87,9 +87,9 @@
 	mfspr	r8, SPRN_TBRL
 	mfspr	r9, SPRN_TBRU
 	cmpw	r9, r7
-	PPC_STL	r8, VCPU_TIMING_EXIT_TBL(r4)
+	stw	r8, VCPU_TIMING_EXIT_TBL(r4)
 	bne-	1b
-	PPC_STL	r9, VCPU_TIMING_EXIT_TBU(r4)
+	stw	r9, VCPU_TIMING_EXIT_TBU(r4)
 #endif
 
 	oris	r8, r6, MSR_CE@h
@@ -216,7 +216,7 @@ _GLOBAL(kvmppc_handler_\intno\()_\srr1)
 	PPC_STL	r4, VCPU_GPR(r4)(r11)
 	PPC_LL	r4, THREAD_NORMSAVE(0)(r10)
 	PPC_STL	r5, VCPU_GPR(r5)(r11)
-	PPC_STL	r13, VCPU_CR(r11)
+	stw	r13, VCPU_CR(r11)
 	mfspr	r5, \srr0
 	PPC_STL	r3, VCPU_GPR(r10)(r11)
 	PPC_LL	r3, THREAD_NORMSAVE(2)(r10)
@@ -243,7 +243,7 @@ _GLOBAL(kvmppc_handler_\intno\()_\srr1)
 	PPC_STL	r4, VCPU_GPR(r4)(r11)
 	PPC_LL	r4, GPR9(r8)
 	PPC_STL	r5, VCPU_GPR(r5)(r11)
-	PPC_STL	r9, VCPU_CR(r11)
+	stw	r9, VCPU_CR(r11)
 	mfspr	r5, \srr0
 	PPC_STL	r3, VCPU_GPR(r8)(r11)
 	PPC_LL	r3, GPR10(r8)
@@ -315,7 +315,7 @@ _GLOBAL(kvmppc_resume_host)
 	mfspr	r6, SPRN_SPRG4
 	PPC_STL	r5, VCPU_LR(r4)
 	mfspr	r7, SPRN_SPRG5
-	PPC_STL	r3, VCPU_VRSAVE(r4)
+	stw	r3, VCPU_VRSAVE(r4)
 	PPC_STD(r6, VCPU_SHARED_SPRG4, r11)
 	mfspr	r8, SPRN_SPRG6
 	PPC_STD(r7, VCPU_SHARED_SPRG5, r11)
@@ -551,7 +551,7 @@ lightweight_exit:
 	PPC_LL	r3, VCPU_LR(r4)
 	PPC_LL	r5, VCPU_XER(r4)
 	PPC_LL	r6, VCPU_CTR(r4)
-	PPC_LL	r7, VCPU_CR(r4)
+	lwz	r7, VCPU_CR(r4)
 	PPC_LL	r8, VCPU_PC(r4)
 	PPC_LD(r9, VCPU_SHARED_MSR, r11)
 	PPC_LL	r0, VCPU_GPR(r0)(r4)
@@ -574,9 +574,9 @@ lightweight_exit:
 	mfspr	r9, SPRN_TBRL
 	mfspr	r8, SPRN_TBRU
 	cmpw	r8, r6
-	PPC_STL	r9, VCPU_TIMING_LAST_ENTER_TBL(r4)
+	stw	r9, VCPU_TIMING_LAST_ENTER_TBL(r4)
 	bne	1b
-	PPC_STL	r8, VCPU_TIMING_LAST_ENTER_TBU(r4)
+	stw	r8, VCPU_TIMING_LAST_ENTER_TBU(r4)
 #endif
 
 	/*

From 978b4fae45b3fae803a9f56e2262f01f71b7dbc9 Mon Sep 17 00:00:00 2001
From: Alexander Graf <agraf@suse.de>
Date: Fri, 27 Apr 2012 01:00:17 +0200
Subject: [PATCH 09/16] KVM: PPC: Fix stbux emulation

Stbux writes the address it's operating on to the register specified in ra,
not into the data source register.

Signed-off-by: Alexander Graf <agraf@suse.de>
---
 arch/powerpc/kvm/emulate.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/powerpc/kvm/emulate.c b/arch/powerpc/kvm/emulate.c
index b5872f61a213..a27d4dc3b4a3 100644
--- a/arch/powerpc/kvm/emulate.c
+++ b/arch/powerpc/kvm/emulate.c
@@ -229,7 +229,7 @@ int kvmppc_emulate_instruction(struct kvm_run *run, struct kvm_vcpu *vcpu)
 			emulated = kvmppc_handle_store(run, vcpu,
 						       kvmppc_get_gpr(vcpu, rs),
 			                               1, 1);
-			kvmppc_set_gpr(vcpu, rs, vcpu->arch.vaddr_accessed);
+			kvmppc_set_gpr(vcpu, ra, vcpu->arch.vaddr_accessed);
 			break;
 
 		case OP_31_XOP_LHAX:

From 11f7d6c2d1b17abf7b91e0f2d43bfe9de0b9e5cf Mon Sep 17 00:00:00 2001
From: Alexander Graf <agraf@suse.de>
Date: Fri, 27 Apr 2012 16:33:35 +0200
Subject: [PATCH 10/16] KVM: PPC: Fix PR KVM on POWER7 bare metal

When running on a system that is HV capable, some interrupts use HSRR
SPRs instead of the normal SRR SPRs. These are also used in the Linux
handlers to jump back to code after an interrupt got processed.

Unfortunately, in our "jump back to the real host handler after we've
done the context switch" code, we were only setting the SRR SPRs,
rendering Linux to jump back to some invalid IP after it's processed
the interrupt.

This fixes random crashes on p7 opal mode with PR KVM for me.

Signed-off-by: Alexander Graf <agraf@suse.de>
---
 arch/powerpc/kvm/book3s_segment.S | 35 +++++++++++++++++++------------
 1 file changed, 22 insertions(+), 13 deletions(-)

diff --git a/arch/powerpc/kvm/book3s_segment.S b/arch/powerpc/kvm/book3s_segment.S
index 6bae0a9414ba..8b2fc66a3066 100644
--- a/arch/powerpc/kvm/book3s_segment.S
+++ b/arch/powerpc/kvm/book3s_segment.S
@@ -198,6 +198,7 @@ kvmppc_interrupt:
 	/* Save guest PC and MSR */
 #ifdef CONFIG_PPC64
 BEGIN_FTR_SECTION
+	mr	r10, r12
 	andi.	r0,r12,0x2
 	beq	1f
 	mfspr	r3,SPRN_HSRR0
@@ -317,23 +318,17 @@ no_dcbz32_off:
 	 * Having set up SRR0/1 with the address where we want
 	 * to continue with relocation on (potentially in module
 	 * space), we either just go straight there with rfi[d],
-	 * or we jump to an interrupt handler with bctr if there
-	 * is an interrupt to be handled first.  In the latter
-	 * case, the rfi[d] at the end of the interrupt handler
-	 * will get us back to where we want to continue.
+	 * or we jump to an interrupt handler if there is an
+	 * interrupt to be handled first.  In the latter case,
+	 * the rfi[d] at the end of the interrupt handler will
+	 * get us back to where we want to continue.
 	 */
 
-	cmpwi	r12, BOOK3S_INTERRUPT_EXTERNAL
-	beq	1f
-	cmpwi	r12, BOOK3S_INTERRUPT_DECREMENTER
-	beq	1f
-	cmpwi	r12, BOOK3S_INTERRUPT_PERFMON
-1:	mtctr	r12
-
 	/* Register usage at this point:
 	 *
 	 * R1       = host R1
 	 * R2       = host R2
+	 * R10      = raw exit handler id
 	 * R12      = exit handler id
 	 * R13      = shadow vcpu (32-bit) or PACA (64-bit)
 	 * SVCPU.*  = guest *
@@ -343,12 +338,26 @@ no_dcbz32_off:
 	PPC_LL	r6, HSTATE_HOST_MSR(r13)
 	PPC_LL	r8, HSTATE_VMHANDLER(r13)
 
-	/* Restore host msr -> SRR1 */
+#ifdef CONFIG_PPC64
+BEGIN_FTR_SECTION
+	andi.	r0,r10,0x2
+	beq	1f
+	mtspr	SPRN_HSRR1, r6
+	mtspr	SPRN_HSRR0, r8
+END_FTR_SECTION_IFSET(CPU_FTR_HVMODE)
+#endif
+1:	/* Restore host msr -> SRR1 */
 	mtsrr1	r6
 	/* Load highmem handler address */
 	mtsrr0	r8
 
 	/* RFI into the highmem handler, or jump to interrupt handler */
-	beqctr
+	cmpwi	r12, BOOK3S_INTERRUPT_EXTERNAL
+	beqa	BOOK3S_INTERRUPT_EXTERNAL
+	cmpwi	r12, BOOK3S_INTERRUPT_DECREMENTER
+	beqa	BOOK3S_INTERRUPT_DECREMENTER
+	cmpwi	r12, BOOK3S_INTERRUPT_PERFMON
+	beqa	BOOK3S_INTERRUPT_PERFMON
+
 	RFI
 kvmppc_handler_trampoline_exit_end:

From 3b1d9d7d95e7c62518160edebd92450b58c6d55f Mon Sep 17 00:00:00 2001
From: Alexander Graf <agraf@suse.de>
Date: Mon, 30 Apr 2012 10:56:12 +0200
Subject: [PATCH 11/16] KVM: PPC: Book3S: Enable IRQs during exit handling

While handling an exit, we should listen for interrupts and make sure to
receive them when they arrive, to keep our latencies low.

Signed-off-by: Alexander Graf <agraf@suse.de>
---
 arch/powerpc/kvm/book3s_pr.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/arch/powerpc/kvm/book3s_pr.c b/arch/powerpc/kvm/book3s_pr.c
index dba282e5093f..d169a0aa4887 100644
--- a/arch/powerpc/kvm/book3s_pr.c
+++ b/arch/powerpc/kvm/book3s_pr.c
@@ -548,6 +548,9 @@ int kvmppc_handle_exit(struct kvm_run *run, struct kvm_vcpu *vcpu,
 	run->exit_reason = KVM_EXIT_UNKNOWN;
 	run->ready_for_interrupt_injection = 1;
 
+	/* We get here with MSR.EE=0, so enable it to be a nice citizen */
+	__hard_irq_enable();
+
 	trace_kvm_book3s_exit(exit_nr, vcpu);
 	preempt_enable();
 	kvm_resched(vcpu);

From 4444aa5f78eff73a353c8c4784cda2de74dea54b Mon Sep 17 00:00:00 2001
From: Mihai Caraman <mihai.caraman@freescale.com>
Date: Mon, 16 Apr 2012 04:08:53 +0000
Subject: [PATCH 12/16] KVM: PPC: bookehv: Fix r8/r13 storing in level
 exception handler

Guest r8 register is held in the scratch register and stored correctly,
so remove the instruction that clobbers it. Guest r13 was missing from vcpu,
store it there.

Signed-off-by: Mihai Caraman <mihai.caraman@freescale.com>
Signed-off-by: Alexander Graf <agraf@suse.de>
---
 arch/powerpc/kvm/bookehv_interrupts.S | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/powerpc/kvm/bookehv_interrupts.S b/arch/powerpc/kvm/bookehv_interrupts.S
index 06750cc1050b..6048a00515d7 100644
--- a/arch/powerpc/kvm/bookehv_interrupts.S
+++ b/arch/powerpc/kvm/bookehv_interrupts.S
@@ -252,10 +252,10 @@ _GLOBAL(kvmppc_handler_\intno\()_\srr1)
 	mfspr	r6, \srr1
 	PPC_LL	r4, GPR11(r8)
 	PPC_STL	r7, VCPU_GPR(r7)(r11)
-	PPC_STL	r8, VCPU_GPR(r8)(r11)
 	PPC_STL r3, VCPU_GPR(r10)(r11)
 	mfctr	r7
 	PPC_STL	r12, VCPU_GPR(r12)(r11)
+	PPC_STL r13, VCPU_GPR(r13)(r11)
 	PPC_STL	r4, VCPU_GPR(r11)(r11)
 	PPC_STL	r7, VCPU_CTR(r11)
 	mr	r4, r11

From f31e65e1170edba4a86bd8cba0318e251d3746d0 Mon Sep 17 00:00:00 2001
From: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Date: Thu, 15 Mar 2012 21:58:34 +0000
Subject: [PATCH 13/16] kvm/book3s: Make kernel emulated H_PUT_TCE available
 for "PR" KVM

There is nothing in the code for emulating TCE tables in the kernel
that prevents it from working on "PR" KVM... other than ifdef's and
location of the code.

This and moves the bulk of the code there to a new file called
book3s_64_vio.c.

This speeds things up a bit on my G5.

Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
[agraf: fix for hv kvm, 32bit, whitespace]
Signed-off-by: Alexander Graf <agraf@suse.de>
---
 arch/powerpc/include/asm/kvm_host.h |   4 +-
 arch/powerpc/include/asm/kvm_ppc.h  |   2 +
 arch/powerpc/kvm/Makefile           |   2 +
 arch/powerpc/kvm/book3s_64_vio.c    | 150 ++++++++++++++++++++++++++++
 arch/powerpc/kvm/book3s_64_vio_hv.c |   3 +
 arch/powerpc/kvm/book3s_hv.c        | 109 --------------------
 arch/powerpc/kvm/book3s_pr.c        |   7 ++
 arch/powerpc/kvm/book3s_pr_papr.c   |  18 ++++
 arch/powerpc/kvm/powerpc.c          |   8 +-
 9 files changed, 191 insertions(+), 112 deletions(-)
 create mode 100644 arch/powerpc/kvm/book3s_64_vio.c

diff --git a/arch/powerpc/include/asm/kvm_host.h b/arch/powerpc/include/asm/kvm_host.h
index 42a527e70490..d848cdc49715 100644
--- a/arch/powerpc/include/asm/kvm_host.h
+++ b/arch/powerpc/include/asm/kvm_host.h
@@ -237,7 +237,6 @@ struct kvm_arch {
 	unsigned long vrma_slb_v;
 	int rma_setup_done;
 	int using_mmu_notifiers;
-	struct list_head spapr_tce_tables;
 	spinlock_t slot_phys_lock;
 	unsigned long *slot_phys[KVM_MEM_SLOTS_NUM];
 	int slot_npages[KVM_MEM_SLOTS_NUM];
@@ -245,6 +244,9 @@ struct kvm_arch {
 	struct kvmppc_vcore *vcores[KVM_MAX_VCORES];
 	struct kvmppc_linear_info *hpt_li;
 #endif /* CONFIG_KVM_BOOK3S_64_HV */
+#ifdef CONFIG_PPC_BOOK3S_64
+	struct list_head spapr_tce_tables;
+#endif
 };
 
 /*
diff --git a/arch/powerpc/include/asm/kvm_ppc.h b/arch/powerpc/include/asm/kvm_ppc.h
index 7f0a3dae7cde..c1069f63dcaf 100644
--- a/arch/powerpc/include/asm/kvm_ppc.h
+++ b/arch/powerpc/include/asm/kvm_ppc.h
@@ -126,6 +126,8 @@ extern void kvmppc_map_vrma(struct kvm_vcpu *vcpu,
 extern int kvmppc_pseries_do_hcall(struct kvm_vcpu *vcpu);
 extern long kvm_vm_ioctl_create_spapr_tce(struct kvm *kvm,
 				struct kvm_create_spapr_tce *args);
+extern long kvmppc_h_put_tce(struct kvm_vcpu *vcpu, unsigned long liobn,
+			     unsigned long ioba, unsigned long tce);
 extern long kvm_vm_ioctl_allocate_rma(struct kvm *kvm,
 				struct kvm_allocate_rma *rma);
 extern struct kvmppc_linear_info *kvm_alloc_rma(void);
diff --git a/arch/powerpc/kvm/Makefile b/arch/powerpc/kvm/Makefile
index 25225aea4c39..c2a08636e6d4 100644
--- a/arch/powerpc/kvm/Makefile
+++ b/arch/powerpc/kvm/Makefile
@@ -54,6 +54,7 @@ kvm-book3s_64-objs-$(CONFIG_KVM_BOOK3S_64_PR) := \
 	book3s_paired_singles.o \
 	book3s_pr.o \
 	book3s_pr_papr.o \
+	book3s_64_vio_hv.o \
 	book3s_emulate.o \
 	book3s_interrupts.o \
 	book3s_mmu_hpte.o \
@@ -78,6 +79,7 @@ kvm-book3s_64-module-objs := \
 	powerpc.o \
 	emulate.o \
 	book3s.o \
+	book3s_64_vio.o \
 	$(kvm-book3s_64-objs-y)
 
 kvm-objs-$(CONFIG_KVM_BOOK3S_64) := $(kvm-book3s_64-module-objs)
diff --git a/arch/powerpc/kvm/book3s_64_vio.c b/arch/powerpc/kvm/book3s_64_vio.c
new file mode 100644
index 000000000000..72ffc899c082
--- /dev/null
+++ b/arch/powerpc/kvm/book3s_64_vio.c
@@ -0,0 +1,150 @@
+/*
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License, version 2, as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, 51 Franklin Street, Fifth Floor, Boston, MA  02110-1301, USA.
+ *
+ * Copyright 2010 Paul Mackerras, IBM Corp. <paulus@au1.ibm.com>
+ * Copyright 2011 David Gibson, IBM Corporation <dwg@au1.ibm.com>
+ */
+
+#include <linux/types.h>
+#include <linux/string.h>
+#include <linux/kvm.h>
+#include <linux/kvm_host.h>
+#include <linux/highmem.h>
+#include <linux/gfp.h>
+#include <linux/slab.h>
+#include <linux/hugetlb.h>
+#include <linux/list.h>
+#include <linux/anon_inodes.h>
+
+#include <asm/tlbflush.h>
+#include <asm/kvm_ppc.h>
+#include <asm/kvm_book3s.h>
+#include <asm/mmu-hash64.h>
+#include <asm/hvcall.h>
+#include <asm/synch.h>
+#include <asm/ppc-opcode.h>
+#include <asm/kvm_host.h>
+#include <asm/udbg.h>
+
+#define TCES_PER_PAGE	(PAGE_SIZE / sizeof(u64))
+
+static long kvmppc_stt_npages(unsigned long window_size)
+{
+	return ALIGN((window_size >> SPAPR_TCE_SHIFT)
+		     * sizeof(u64), PAGE_SIZE) / PAGE_SIZE;
+}
+
+static void release_spapr_tce_table(struct kvmppc_spapr_tce_table *stt)
+{
+	struct kvm *kvm = stt->kvm;
+	int i;
+
+	mutex_lock(&kvm->lock);
+	list_del(&stt->list);
+	for (i = 0; i < kvmppc_stt_npages(stt->window_size); i++)
+		__free_page(stt->pages[i]);
+	kfree(stt);
+	mutex_unlock(&kvm->lock);
+
+	kvm_put_kvm(kvm);
+}
+
+static int kvm_spapr_tce_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
+{
+	struct kvmppc_spapr_tce_table *stt = vma->vm_file->private_data;
+	struct page *page;
+
+	if (vmf->pgoff >= kvmppc_stt_npages(stt->window_size))
+		return VM_FAULT_SIGBUS;
+
+	page = stt->pages[vmf->pgoff];
+	get_page(page);
+	vmf->page = page;
+	return 0;
+}
+
+static const struct vm_operations_struct kvm_spapr_tce_vm_ops = {
+	.fault = kvm_spapr_tce_fault,
+};
+
+static int kvm_spapr_tce_mmap(struct file *file, struct vm_area_struct *vma)
+{
+	vma->vm_ops = &kvm_spapr_tce_vm_ops;
+	return 0;
+}
+
+static int kvm_spapr_tce_release(struct inode *inode, struct file *filp)
+{
+	struct kvmppc_spapr_tce_table *stt = filp->private_data;
+
+	release_spapr_tce_table(stt);
+	return 0;
+}
+
+static struct file_operations kvm_spapr_tce_fops = {
+	.mmap           = kvm_spapr_tce_mmap,
+	.release	= kvm_spapr_tce_release,
+};
+
+long kvm_vm_ioctl_create_spapr_tce(struct kvm *kvm,
+				   struct kvm_create_spapr_tce *args)
+{
+	struct kvmppc_spapr_tce_table *stt = NULL;
+	long npages;
+	int ret = -ENOMEM;
+	int i;
+
+	/* Check this LIOBN hasn't been previously allocated */
+	list_for_each_entry(stt, &kvm->arch.spapr_tce_tables, list) {
+		if (stt->liobn == args->liobn)
+			return -EBUSY;
+	}
+
+	npages = kvmppc_stt_npages(args->window_size);
+
+	stt = kzalloc(sizeof(*stt) + npages * sizeof(struct page *),
+		      GFP_KERNEL);
+	if (!stt)
+		goto fail;
+
+	stt->liobn = args->liobn;
+	stt->window_size = args->window_size;
+	stt->kvm = kvm;
+
+	for (i = 0; i < npages; i++) {
+		stt->pages[i] = alloc_page(GFP_KERNEL | __GFP_ZERO);
+		if (!stt->pages[i])
+			goto fail;
+	}
+
+	kvm_get_kvm(kvm);
+
+	mutex_lock(&kvm->lock);
+	list_add(&stt->list, &kvm->arch.spapr_tce_tables);
+
+	mutex_unlock(&kvm->lock);
+
+	return anon_inode_getfd("kvm-spapr-tce", &kvm_spapr_tce_fops,
+				stt, O_RDWR);
+
+fail:
+	if (stt) {
+		for (i = 0; i < npages; i++)
+			if (stt->pages[i])
+				__free_page(stt->pages[i]);
+
+		kfree(stt);
+	}
+	return ret;
+}
diff --git a/arch/powerpc/kvm/book3s_64_vio_hv.c b/arch/powerpc/kvm/book3s_64_vio_hv.c
index ea0f8c537c28..30c2f3b134c6 100644
--- a/arch/powerpc/kvm/book3s_64_vio_hv.c
+++ b/arch/powerpc/kvm/book3s_64_vio_hv.c
@@ -38,6 +38,9 @@
 
 #define TCES_PER_PAGE	(PAGE_SIZE / sizeof(u64))
 
+/* WARNING: This will be called in real-mode on HV KVM and virtual
+ *          mode on PR KVM
+ */
 long kvmppc_h_put_tce(struct kvm_vcpu *vcpu, unsigned long liobn,
 		      unsigned long ioba, unsigned long tce)
 {
diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c
index 907935764de0..59c296743595 100644
--- a/arch/powerpc/kvm/book3s_hv.c
+++ b/arch/powerpc/kvm/book3s_hv.c
@@ -1093,115 +1093,6 @@ int kvmppc_vcpu_run(struct kvm_run *run, struct kvm_vcpu *vcpu)
 	return r;
 }
 
-static long kvmppc_stt_npages(unsigned long window_size)
-{
-	return ALIGN((window_size >> SPAPR_TCE_SHIFT)
-		     * sizeof(u64), PAGE_SIZE) / PAGE_SIZE;
-}
-
-static void release_spapr_tce_table(struct kvmppc_spapr_tce_table *stt)
-{
-	struct kvm *kvm = stt->kvm;
-	int i;
-
-	mutex_lock(&kvm->lock);
-	list_del(&stt->list);
-	for (i = 0; i < kvmppc_stt_npages(stt->window_size); i++)
-		__free_page(stt->pages[i]);
-	kfree(stt);
-	mutex_unlock(&kvm->lock);
-
-	kvm_put_kvm(kvm);
-}
-
-static int kvm_spapr_tce_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
-{
-	struct kvmppc_spapr_tce_table *stt = vma->vm_file->private_data;
-	struct page *page;
-
-	if (vmf->pgoff >= kvmppc_stt_npages(stt->window_size))
-		return VM_FAULT_SIGBUS;
-
-	page = stt->pages[vmf->pgoff];
-	get_page(page);
-	vmf->page = page;
-	return 0;
-}
-
-static const struct vm_operations_struct kvm_spapr_tce_vm_ops = {
-	.fault = kvm_spapr_tce_fault,
-};
-
-static int kvm_spapr_tce_mmap(struct file *file, struct vm_area_struct *vma)
-{
-	vma->vm_ops = &kvm_spapr_tce_vm_ops;
-	return 0;
-}
-
-static int kvm_spapr_tce_release(struct inode *inode, struct file *filp)
-{
-	struct kvmppc_spapr_tce_table *stt = filp->private_data;
-
-	release_spapr_tce_table(stt);
-	return 0;
-}
-
-static struct file_operations kvm_spapr_tce_fops = {
-	.mmap           = kvm_spapr_tce_mmap,
-	.release	= kvm_spapr_tce_release,
-};
-
-long kvm_vm_ioctl_create_spapr_tce(struct kvm *kvm,
-				   struct kvm_create_spapr_tce *args)
-{
-	struct kvmppc_spapr_tce_table *stt = NULL;
-	long npages;
-	int ret = -ENOMEM;
-	int i;
-
-	/* Check this LIOBN hasn't been previously allocated */
-	list_for_each_entry(stt, &kvm->arch.spapr_tce_tables, list) {
-		if (stt->liobn == args->liobn)
-			return -EBUSY;
-	}
-
-	npages = kvmppc_stt_npages(args->window_size);
-
-	stt = kzalloc(sizeof(*stt) + npages* sizeof(struct page *),
-		      GFP_KERNEL);
-	if (!stt)
-		goto fail;
-
-	stt->liobn = args->liobn;
-	stt->window_size = args->window_size;
-	stt->kvm = kvm;
-
-	for (i = 0; i < npages; i++) {
-		stt->pages[i] = alloc_page(GFP_KERNEL | __GFP_ZERO);
-		if (!stt->pages[i])
-			goto fail;
-	}
-
-	kvm_get_kvm(kvm);
-
-	mutex_lock(&kvm->lock);
-	list_add(&stt->list, &kvm->arch.spapr_tce_tables);
-
-	mutex_unlock(&kvm->lock);
-
-	return anon_inode_getfd("kvm-spapr-tce", &kvm_spapr_tce_fops,
-				stt, O_RDWR);
-
-fail:
-	if (stt) {
-		for (i = 0; i < npages; i++)
-			if (stt->pages[i])
-				__free_page(stt->pages[i]);
-
-		kfree(stt);
-	}
-	return ret;
-}
 
 /* Work out RMLS (real mode limit selector) field value for a given RMA size.
    Assumes POWER7 or PPC970. */
diff --git a/arch/powerpc/kvm/book3s_pr.c b/arch/powerpc/kvm/book3s_pr.c
index d169a0aa4887..815ac5938a9e 100644
--- a/arch/powerpc/kvm/book3s_pr.c
+++ b/arch/powerpc/kvm/book3s_pr.c
@@ -1171,11 +1171,18 @@ void kvmppc_core_commit_memory_region(struct kvm *kvm,
 
 int kvmppc_core_init_vm(struct kvm *kvm)
 {
+#ifdef CONFIG_PPC64
+	INIT_LIST_HEAD(&kvm->arch.spapr_tce_tables);
+#endif
+
 	return 0;
 }
 
 void kvmppc_core_destroy_vm(struct kvm *kvm)
 {
+#ifdef CONFIG_PPC64
+	WARN_ON(!list_empty(&kvm->arch.spapr_tce_tables));
+#endif
 }
 
 static int kvmppc_book3s_init(void)
diff --git a/arch/powerpc/kvm/book3s_pr_papr.c b/arch/powerpc/kvm/book3s_pr_papr.c
index 60ac0e793476..3ff9013d6e79 100644
--- a/arch/powerpc/kvm/book3s_pr_papr.c
+++ b/arch/powerpc/kvm/book3s_pr_papr.c
@@ -15,6 +15,8 @@
  * published by the Free Software Foundation.
  */
 
+#include <linux/anon_inodes.h>
+
 #include <asm/uaccess.h>
 #include <asm/kvm_ppc.h>
 #include <asm/kvm_book3s.h>
@@ -211,6 +213,20 @@ static int kvmppc_h_pr_protect(struct kvm_vcpu *vcpu)
 	return EMULATE_DONE;
 }
 
+static int kvmppc_h_pr_put_tce(struct kvm_vcpu *vcpu)
+{
+	unsigned long liobn = kvmppc_get_gpr(vcpu, 4);
+	unsigned long ioba = kvmppc_get_gpr(vcpu, 5);
+	unsigned long tce = kvmppc_get_gpr(vcpu, 6);
+	long rc;
+
+	rc = kvmppc_h_put_tce(vcpu, liobn, ioba, tce);
+	if (rc == H_TOO_HARD)
+		return EMULATE_FAIL;
+	kvmppc_set_gpr(vcpu, 3, rc);
+	return EMULATE_DONE;
+}
+
 int kvmppc_h_pr(struct kvm_vcpu *vcpu, unsigned long cmd)
 {
 	switch (cmd) {
@@ -222,6 +238,8 @@ int kvmppc_h_pr(struct kvm_vcpu *vcpu, unsigned long cmd)
 		return kvmppc_h_pr_protect(vcpu);
 	case H_BULK_REMOVE:
 		return kvmppc_h_pr_bulk_remove(vcpu);
+	case H_PUT_TCE:
+		return kvmppc_h_pr_put_tce(vcpu);
 	case H_CEDE:
 		kvm_vcpu_block(vcpu);
 		clear_bit(KVM_REQ_UNHALT, &vcpu->requests);
diff --git a/arch/powerpc/kvm/powerpc.c b/arch/powerpc/kvm/powerpc.c
index 58ad8609bb43..6ac31154d170 100644
--- a/arch/powerpc/kvm/powerpc.c
+++ b/arch/powerpc/kvm/powerpc.c
@@ -244,10 +244,12 @@ int kvm_dev_ioctl_check_extension(long ext)
 		r = KVM_COALESCED_MMIO_PAGE_OFFSET;
 		break;
 #endif
-#ifdef CONFIG_KVM_BOOK3S_64_HV
+#ifdef CONFIG_PPC_BOOK3S_64
 	case KVM_CAP_SPAPR_TCE:
 		r = 1;
 		break;
+#endif /* CONFIG_PPC_BOOK3S_64 */
+#ifdef CONFIG_KVM_BOOK3S_64_HV
 	case KVM_CAP_PPC_SMT:
 		r = threads_per_core;
 		break;
@@ -773,7 +775,7 @@ long kvm_arch_vm_ioctl(struct file *filp,
 
 		break;
 	}
-#ifdef CONFIG_KVM_BOOK3S_64_HV
+#ifdef CONFIG_PPC_BOOK3S_64
 	case KVM_CREATE_SPAPR_TCE: {
 		struct kvm_create_spapr_tce create_tce;
 		struct kvm *kvm = filp->private_data;
@@ -784,7 +786,9 @@ long kvm_arch_vm_ioctl(struct file *filp,
 		r = kvm_vm_ioctl_create_spapr_tce(kvm, &create_tce);
 		goto out;
 	}
+#endif /* CONFIG_PPC_BOOK3S_64 */
 
+#ifdef CONFIG_KVM_BOOK3S_64_HV
 	case KVM_ALLOCATE_RMA: {
 		struct kvm *kvm = filp->private_data;
 		struct kvm_allocate_rma rma;

From 5b74716ebab10e7bce960d148fe6d8f6920451e5 Mon Sep 17 00:00:00 2001
From: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Date: Thu, 26 Apr 2012 19:43:42 +0000
Subject: [PATCH 14/16] kvm/powerpc: Add new ioctl to retreive server MMU infos

This is necessary for qemu to be able to pass the right information
to the guest, such as the supported page sizes and corresponding
encodings in the SLB and hash table, which can vary depending
on the processor type, the type of KVM used (PR vs HV) and the
version of KVM

Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
[agraf: fix compilation on hv, adjust for newer ioctl numbers]
Signed-off-by: Alexander Graf <agraf@suse.de>
---
 Documentation/virtual/kvm/api.txt  | 70 ++++++++++++++++++++++++++++++
 arch/powerpc/include/asm/kvm_ppc.h |  2 +
 arch/powerpc/kernel/ppc_ksyms.c    |  4 ++
 arch/powerpc/kvm/book3s_hv.c       | 32 ++++++++++++++
 arch/powerpc/kvm/book3s_pr.c       | 25 +++++++++++
 arch/powerpc/kvm/powerpc.c         | 18 +++++++-
 include/linux/kvm.h                | 27 ++++++++++++
 7 files changed, 177 insertions(+), 1 deletion(-)

diff --git a/Documentation/virtual/kvm/api.txt b/Documentation/virtual/kvm/api.txt
index eb62761b7683..930126698a0f 100644
--- a/Documentation/virtual/kvm/api.txt
+++ b/Documentation/virtual/kvm/api.txt
@@ -1860,6 +1860,76 @@ See KVM_GET_PIT2 for details on struct kvm_pit_state2.
 This IOCTL replaces the obsolete KVM_SET_PIT.
 
 
+4.74 KVM_PPC_GET_SMMU_INFO
+
+Capability: KVM_CAP_PPC_GET_SMMU_INFO
+Architectures: powerpc
+Type: vm ioctl
+Parameters: None
+Returns: 0 on success, -1 on error
+
+This populates and returns a structure describing the features of
+the "Server" class MMU emulation supported by KVM.
+This can in turn be used by userspace to generate the appropariate
+device-tree properties for the guest operating system.
+
+The structure contains some global informations, followed by an
+array of supported segment page sizes:
+
+      struct kvm_ppc_smmu_info {
+	     __u64 flags;
+	     __u32 slb_size;
+	     __u32 pad;
+	     struct kvm_ppc_one_seg_page_size sps[KVM_PPC_PAGE_SIZES_MAX_SZ];
+      };
+
+The supported flags are:
+
+    - KVM_PPC_PAGE_SIZES_REAL:
+        When that flag is set, guest page sizes must "fit" the backing
+        store page sizes. When not set, any page size in the list can
+        be used regardless of how they are backed by userspace.
+
+    - KVM_PPC_1T_SEGMENTS
+        The emulated MMU supports 1T segments in addition to the
+        standard 256M ones.
+
+The "slb_size" field indicates how many SLB entries are supported
+
+The "sps" array contains 8 entries indicating the supported base
+page sizes for a segment in increasing order. Each entry is defined
+as follow:
+
+   struct kvm_ppc_one_seg_page_size {
+	__u32 page_shift;	/* Base page shift of segment (or 0) */
+	__u32 slb_enc;		/* SLB encoding for BookS */
+	struct kvm_ppc_one_page_size enc[KVM_PPC_PAGE_SIZES_MAX_SZ];
+   };
+
+An entry with a "page_shift" of 0 is unused. Because the array is
+organized in increasing order, a lookup can stop when encoutering
+such an entry.
+
+The "slb_enc" field provides the encoding to use in the SLB for the
+page size. The bits are in positions such as the value can directly
+be OR'ed into the "vsid" argument of the slbmte instruction.
+
+The "enc" array is a list which for each of those segment base page
+size provides the list of supported actual page sizes (which can be
+only larger or equal to the base page size), along with the
+corresponding encoding in the hash PTE. Similarily, the array is
+8 entries sorted by increasing sizes and an entry with a "0" shift
+is an empty entry and a terminator:
+
+   struct kvm_ppc_one_page_size {
+	__u32 page_shift;	/* Page shift (or 0) */
+	__u32 pte_enc;		/* Encoding in the HPTE (>>12) */
+   };
+
+The "pte_enc" field provides a value that can OR'ed into the hash
+PTE's RPN field (ie, it needs to be shifted left by 12 to OR it
+into the hash PTE second double word).
+
 5. The kvm_run structure
 ------------------------
 
diff --git a/arch/powerpc/include/asm/kvm_ppc.h b/arch/powerpc/include/asm/kvm_ppc.h
index c1069f63dcaf..c87e3b503fdc 100644
--- a/arch/powerpc/include/asm/kvm_ppc.h
+++ b/arch/powerpc/include/asm/kvm_ppc.h
@@ -140,6 +140,8 @@ extern int kvmppc_core_prepare_memory_region(struct kvm *kvm,
 				struct kvm_userspace_memory_region *mem);
 extern void kvmppc_core_commit_memory_region(struct kvm *kvm,
 				struct kvm_userspace_memory_region *mem);
+extern int kvm_vm_ioctl_get_smmu_info(struct kvm *kvm,
+				      struct kvm_ppc_smmu_info *info);
 
 extern int kvmppc_bookehv_init(void);
 extern void kvmppc_bookehv_exit(void);
diff --git a/arch/powerpc/kernel/ppc_ksyms.c b/arch/powerpc/kernel/ppc_ksyms.c
index 786a2700ec2d..d1f2aafcbe8c 100644
--- a/arch/powerpc/kernel/ppc_ksyms.c
+++ b/arch/powerpc/kernel/ppc_ksyms.c
@@ -190,3 +190,7 @@ EXPORT_SYMBOL(__arch_hweight16);
 EXPORT_SYMBOL(__arch_hweight32);
 EXPORT_SYMBOL(__arch_hweight64);
 #endif
+
+#ifdef CONFIG_PPC_BOOK3S_64
+EXPORT_SYMBOL_GPL(mmu_psize_defs);
+#endif
diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c
index 59c296743595..bb5a0f4b4bbb 100644
--- a/arch/powerpc/kvm/book3s_hv.c
+++ b/arch/powerpc/kvm/book3s_hv.c
@@ -1175,6 +1175,38 @@ long kvm_vm_ioctl_allocate_rma(struct kvm *kvm, struct kvm_allocate_rma *ret)
 	return fd;
 }
 
+static void kvmppc_add_seg_page_size(struct kvm_ppc_one_seg_page_size **sps,
+				     int linux_psize)
+{
+	struct mmu_psize_def *def = &mmu_psize_defs[linux_psize];
+
+	if (!def->shift)
+		return;
+	(*sps)->page_shift = def->shift;
+	(*sps)->slb_enc = def->sllp;
+	(*sps)->enc[0].page_shift = def->shift;
+	(*sps)->enc[0].pte_enc = def->penc;
+	(*sps)++;
+}
+
+int kvm_vm_ioctl_get_smmu_info(struct kvm *kvm, struct kvm_ppc_smmu_info *info)
+{
+	struct kvm_ppc_one_seg_page_size *sps;
+
+	info->flags = KVM_PPC_PAGE_SIZES_REAL;
+	if (mmu_has_feature(MMU_FTR_1T_SEGMENT))
+		info->flags |= KVM_PPC_1T_SEGMENTS;
+	info->slb_size = mmu_slb_size;
+
+	/* We only support these sizes for now, and no muti-size segments */
+	sps = &info->sps[0];
+	kvmppc_add_seg_page_size(&sps, MMU_PAGE_4K);
+	kvmppc_add_seg_page_size(&sps, MMU_PAGE_64K);
+	kvmppc_add_seg_page_size(&sps, MMU_PAGE_16M);
+
+	return 0;
+}
+
 /*
  * Get (and clear) the dirty memory log for a memory slot.
  */
diff --git a/arch/powerpc/kvm/book3s_pr.c b/arch/powerpc/kvm/book3s_pr.c
index 815ac5938a9e..a1baec340f7e 100644
--- a/arch/powerpc/kvm/book3s_pr.c
+++ b/arch/powerpc/kvm/book3s_pr.c
@@ -1158,6 +1158,31 @@ out:
 	return r;
 }
 
+#ifdef CONFIG_PPC64
+int kvm_vm_ioctl_get_smmu_info(struct kvm *kvm, struct kvm_ppc_smmu_info *info)
+{
+	/* No flags */
+	info->flags = 0;
+
+	/* SLB is always 64 entries */
+	info->slb_size = 64;
+
+	/* Standard 4k base page size segment */
+	info->sps[0].page_shift = 12;
+	info->sps[0].slb_enc = 0;
+	info->sps[0].enc[0].page_shift = 12;
+	info->sps[0].enc[0].pte_enc = 0;
+
+	/* Standard 16M large page size segment */
+	info->sps[1].page_shift = 24;
+	info->sps[1].slb_enc = SLB_VSID_L;
+	info->sps[1].enc[0].page_shift = 24;
+	info->sps[1].enc[0].pte_enc = 0;
+
+	return 0;
+}
+#endif /* CONFIG_PPC64 */
+
 int kvmppc_core_prepare_memory_region(struct kvm *kvm,
 				      struct kvm_userspace_memory_region *mem)
 {
diff --git a/arch/powerpc/kvm/powerpc.c b/arch/powerpc/kvm/powerpc.c
index 6ac31154d170..1493c8de947b 100644
--- a/arch/powerpc/kvm/powerpc.c
+++ b/arch/powerpc/kvm/powerpc.c
@@ -279,6 +279,11 @@ int kvm_dev_ioctl_check_extension(long ext)
 	case KVM_CAP_MAX_VCPUS:
 		r = KVM_MAX_VCPUS;
 		break;
+#ifdef CONFIG_PPC_BOOK3S_64
+	case KVM_CAP_PPC_GET_SMMU_INFO:
+		r = 1;
+		break;
+#endif
 	default:
 		r = 0;
 		break;
@@ -718,7 +723,6 @@ long kvm_arch_vcpu_ioctl(struct file *filp,
 		break;
 	}
 #endif
-
 	default:
 		r = -EINVAL;
 	}
@@ -800,6 +804,18 @@ long kvm_arch_vm_ioctl(struct file *filp,
 	}
 #endif /* CONFIG_KVM_BOOK3S_64_HV */
 
+#ifdef CONFIG_PPC_BOOK3S_64
+	case KVM_PPC_GET_SMMU_INFO: {
+		struct kvm *kvm = filp->private_data;
+		struct kvm_ppc_smmu_info info;
+
+		memset(&info, 0, sizeof(info));
+		r = kvm_vm_ioctl_get_smmu_info(kvm, &info);
+		if (r >= 0 && copy_to_user(argp, &info, sizeof(info)))
+			r = -EFAULT;
+		break;
+	}
+#endif /* CONFIG_PPC_BOOK3S_64 */
 	default:
 		r = -ENOTTY;
 	}
diff --git a/include/linux/kvm.h b/include/linux/kvm.h
index 225b452e1d1d..8d696cf6edcc 100644
--- a/include/linux/kvm.h
+++ b/include/linux/kvm.h
@@ -449,6 +449,30 @@ struct kvm_ppc_pvinfo {
 	__u8  pad[108];
 };
 
+/* for KVM_PPC_GET_SMMU_INFO */
+#define KVM_PPC_PAGE_SIZES_MAX_SZ	8
+
+struct kvm_ppc_one_page_size {
+	__u32 page_shift;	/* Page shift (or 0) */
+	__u32 pte_enc;		/* Encoding in the HPTE (>>12) */
+};
+
+struct kvm_ppc_one_seg_page_size {
+	__u32 page_shift;	/* Base page shift of segment (or 0) */
+	__u32 slb_enc;		/* SLB encoding for BookS */
+	struct kvm_ppc_one_page_size enc[KVM_PPC_PAGE_SIZES_MAX_SZ];
+};
+
+#define KVM_PPC_PAGE_SIZES_REAL		0x00000001
+#define KVM_PPC_1T_SEGMENTS		0x00000002
+
+struct kvm_ppc_smmu_info {
+	__u64 flags;
+	__u32 slb_size;
+	__u32 pad;
+	struct kvm_ppc_one_seg_page_size sps[KVM_PPC_PAGE_SIZES_MAX_SZ];
+};
+
 #define KVMIO 0xAE
 
 /* machine type bits, to be used as argument to KVM_CREATE_VM */
@@ -591,6 +615,7 @@ struct kvm_ppc_pvinfo {
 #define KVM_CAP_PCI_2_3 75
 #define KVM_CAP_KVMCLOCK_CTRL 76
 #define KVM_CAP_SIGNAL_MSI 77
+#define KVM_CAP_PPC_GET_SMMU_INFO 78
 
 #ifdef KVM_CAP_IRQ_ROUTING
 
@@ -800,6 +825,8 @@ struct kvm_s390_ucas_mapping {
 				       struct kvm_assigned_pci_dev)
 /* Available with KVM_CAP_SIGNAL_MSI */
 #define KVM_SIGNAL_MSI            _IOW(KVMIO,  0xa5, struct kvm_msi)
+/* Available with KVM_CAP_PPC_GET_SMMU_INFO */
+#define KVM_PPC_GET_SMMU_INFO	  _IOR(KVMIO,  0xa6, struct kvm_ppc_smmu_info)
 
 /*
  * ioctls for vcpu fds

From c46dc9a86148bc37c31d67a22a3887144ba7aa81 Mon Sep 17 00:00:00 2001
From: Alexander Graf <agraf@suse.de>
Date: Fri, 4 May 2012 14:01:33 +0200
Subject: [PATCH 15/16] KVM: PPC: Emulator: clean up instruction parsing

Instructions on PPC are pretty similarly encoded. So instead of
every instruction emulation code decoding the instruction fields
itself, we can move that code to more generic places and rely on
the compiler to optimize the unused bits away.

This has 2 advantages. It makes the code smaller and it makes the
code less error prone, as the instruction fields are always
available, so accidental misusage is reduced.

Functionally, this patch doesn't change anything.

Signed-off-by: Alexander Graf <agraf@suse.de>
---
 arch/powerpc/kvm/44x_emulate.c    | 27 +++---------
 arch/powerpc/kvm/book3s_emulate.c | 72 ++++++++++++++++---------------
 arch/powerpc/kvm/booke_emulate.c  |  7 +--
 arch/powerpc/kvm/e500_emulate.c   | 16 +++----
 arch/powerpc/kvm/emulate.c        | 71 ++----------------------------
 5 files changed, 56 insertions(+), 137 deletions(-)

diff --git a/arch/powerpc/kvm/44x_emulate.c b/arch/powerpc/kvm/44x_emulate.c
index 549bb2c9a47a..da81a2d92380 100644
--- a/arch/powerpc/kvm/44x_emulate.c
+++ b/arch/powerpc/kvm/44x_emulate.c
@@ -37,22 +37,19 @@ int kvmppc_core_emulate_op(struct kvm_run *run, struct kvm_vcpu *vcpu,
                            unsigned int inst, int *advance)
 {
 	int emulated = EMULATE_DONE;
-	int dcrn;
-	int ra;
-	int rb;
-	int rc;
-	int rs;
-	int rt;
-	int ws;
+	int dcrn = get_dcrn(inst);
+	int ra = get_ra(inst);
+	int rb = get_rb(inst);
+	int rc = get_rc(inst);
+	int rs = get_rs(inst);
+	int rt = get_rt(inst);
+	int ws = get_ws(inst);
 
 	switch (get_op(inst)) {
 	case 31:
 		switch (get_xop(inst)) {
 
 		case XOP_MFDCR:
-			dcrn = get_dcrn(inst);
-			rt = get_rt(inst);
-
 			/* The guest may access CPR0 registers to determine the timebase
 			 * frequency, and it must know the real host frequency because it
 			 * can directly access the timebase registers.
@@ -88,9 +85,6 @@ int kvmppc_core_emulate_op(struct kvm_run *run, struct kvm_vcpu *vcpu,
 			break;
 
 		case XOP_MTDCR:
-			dcrn = get_dcrn(inst);
-			rs = get_rs(inst);
-
 			/* emulate some access in kernel */
 			switch (dcrn) {
 			case DCRN_CPR0_CONFIG_ADDR:
@@ -108,17 +102,10 @@ int kvmppc_core_emulate_op(struct kvm_run *run, struct kvm_vcpu *vcpu,
 			break;
 
 		case XOP_TLBWE:
-			ra = get_ra(inst);
-			rs = get_rs(inst);
-			ws = get_ws(inst);
 			emulated = kvmppc_44x_emul_tlbwe(vcpu, ra, rs, ws);
 			break;
 
 		case XOP_TLBSX:
-			rt = get_rt(inst);
-			ra = get_ra(inst);
-			rb = get_rb(inst);
-			rc = get_rc(inst);
 			emulated = kvmppc_44x_emul_tlbsx(vcpu, rt, ra, rb, rc);
 			break;
 
diff --git a/arch/powerpc/kvm/book3s_emulate.c b/arch/powerpc/kvm/book3s_emulate.c
index 135663a3e4fc..c023bcd253ff 100644
--- a/arch/powerpc/kvm/book3s_emulate.c
+++ b/arch/powerpc/kvm/book3s_emulate.c
@@ -87,6 +87,10 @@ int kvmppc_core_emulate_op(struct kvm_run *run, struct kvm_vcpu *vcpu,
                            unsigned int inst, int *advance)
 {
 	int emulated = EMULATE_DONE;
+	int rt = get_rt(inst);
+	int rs = get_rs(inst);
+	int ra = get_ra(inst);
+	int rb = get_rb(inst);
 
 	switch (get_op(inst)) {
 	case 19:
@@ -106,21 +110,22 @@ int kvmppc_core_emulate_op(struct kvm_run *run, struct kvm_vcpu *vcpu,
 	case 31:
 		switch (get_xop(inst)) {
 		case OP_31_XOP_MFMSR:
-			kvmppc_set_gpr(vcpu, get_rt(inst),
-				       vcpu->arch.shared->msr);
+			kvmppc_set_gpr(vcpu, rt, vcpu->arch.shared->msr);
 			break;
 		case OP_31_XOP_MTMSRD:
 		{
-			ulong rs = kvmppc_get_gpr(vcpu, get_rs(inst));
+			ulong rs_val = kvmppc_get_gpr(vcpu, rs);
 			if (inst & 0x10000) {
-				vcpu->arch.shared->msr &= ~(MSR_RI | MSR_EE);
-				vcpu->arch.shared->msr |= rs & (MSR_RI | MSR_EE);
+				ulong new_msr = vcpu->arch.shared->msr;
+				new_msr &= ~(MSR_RI | MSR_EE);
+				new_msr |= rs_val & (MSR_RI | MSR_EE);
+				vcpu->arch.shared->msr = new_msr;
 			} else
-				kvmppc_set_msr(vcpu, rs);
+				kvmppc_set_msr(vcpu, rs_val);
 			break;
 		}
 		case OP_31_XOP_MTMSR:
-			kvmppc_set_msr(vcpu, kvmppc_get_gpr(vcpu, get_rs(inst)));
+			kvmppc_set_msr(vcpu, kvmppc_get_gpr(vcpu, rs));
 			break;
 		case OP_31_XOP_MFSR:
 		{
@@ -130,7 +135,7 @@ int kvmppc_core_emulate_op(struct kvm_run *run, struct kvm_vcpu *vcpu,
 			if (vcpu->arch.mmu.mfsrin) {
 				u32 sr;
 				sr = vcpu->arch.mmu.mfsrin(vcpu, srnum);
-				kvmppc_set_gpr(vcpu, get_rt(inst), sr);
+				kvmppc_set_gpr(vcpu, rt, sr);
 			}
 			break;
 		}
@@ -138,29 +143,29 @@ int kvmppc_core_emulate_op(struct kvm_run *run, struct kvm_vcpu *vcpu,
 		{
 			int srnum;
 
-			srnum = (kvmppc_get_gpr(vcpu, get_rb(inst)) >> 28) & 0xf;
+			srnum = (kvmppc_get_gpr(vcpu, rb) >> 28) & 0xf;
 			if (vcpu->arch.mmu.mfsrin) {
 				u32 sr;
 				sr = vcpu->arch.mmu.mfsrin(vcpu, srnum);
-				kvmppc_set_gpr(vcpu, get_rt(inst), sr);
+				kvmppc_set_gpr(vcpu, rt, sr);
 			}
 			break;
 		}
 		case OP_31_XOP_MTSR:
 			vcpu->arch.mmu.mtsrin(vcpu,
 				(inst >> 16) & 0xf,
-				kvmppc_get_gpr(vcpu, get_rs(inst)));
+				kvmppc_get_gpr(vcpu, rs));
 			break;
 		case OP_31_XOP_MTSRIN:
 			vcpu->arch.mmu.mtsrin(vcpu,
-				(kvmppc_get_gpr(vcpu, get_rb(inst)) >> 28) & 0xf,
-				kvmppc_get_gpr(vcpu, get_rs(inst)));
+				(kvmppc_get_gpr(vcpu, rb) >> 28) & 0xf,
+				kvmppc_get_gpr(vcpu, rs));
 			break;
 		case OP_31_XOP_TLBIE:
 		case OP_31_XOP_TLBIEL:
 		{
 			bool large = (inst & 0x00200000) ? true : false;
-			ulong addr = kvmppc_get_gpr(vcpu, get_rb(inst));
+			ulong addr = kvmppc_get_gpr(vcpu, rb);
 			vcpu->arch.mmu.tlbie(vcpu, addr, large);
 			break;
 		}
@@ -171,15 +176,15 @@ int kvmppc_core_emulate_op(struct kvm_run *run, struct kvm_vcpu *vcpu,
 				return EMULATE_FAIL;
 
 			vcpu->arch.mmu.slbmte(vcpu,
-					kvmppc_get_gpr(vcpu, get_rs(inst)),
-					kvmppc_get_gpr(vcpu, get_rb(inst)));
+					kvmppc_get_gpr(vcpu, rs),
+					kvmppc_get_gpr(vcpu, rb));
 			break;
 		case OP_31_XOP_SLBIE:
 			if (!vcpu->arch.mmu.slbie)
 				return EMULATE_FAIL;
 
 			vcpu->arch.mmu.slbie(vcpu,
-					kvmppc_get_gpr(vcpu, get_rb(inst)));
+					kvmppc_get_gpr(vcpu, rb));
 			break;
 		case OP_31_XOP_SLBIA:
 			if (!vcpu->arch.mmu.slbia)
@@ -191,22 +196,22 @@ int kvmppc_core_emulate_op(struct kvm_run *run, struct kvm_vcpu *vcpu,
 			if (!vcpu->arch.mmu.slbmfee) {
 				emulated = EMULATE_FAIL;
 			} else {
-				ulong t, rb;
+				ulong t, rb_val;
 
-				rb = kvmppc_get_gpr(vcpu, get_rb(inst));
-				t = vcpu->arch.mmu.slbmfee(vcpu, rb);
-				kvmppc_set_gpr(vcpu, get_rt(inst), t);
+				rb_val = kvmppc_get_gpr(vcpu, rb);
+				t = vcpu->arch.mmu.slbmfee(vcpu, rb_val);
+				kvmppc_set_gpr(vcpu, rt, t);
 			}
 			break;
 		case OP_31_XOP_SLBMFEV:
 			if (!vcpu->arch.mmu.slbmfev) {
 				emulated = EMULATE_FAIL;
 			} else {
-				ulong t, rb;
+				ulong t, rb_val;
 
-				rb = kvmppc_get_gpr(vcpu, get_rb(inst));
-				t = vcpu->arch.mmu.slbmfev(vcpu, rb);
-				kvmppc_set_gpr(vcpu, get_rt(inst), t);
+				rb_val = kvmppc_get_gpr(vcpu, rb);
+				t = vcpu->arch.mmu.slbmfev(vcpu, rb_val);
+				kvmppc_set_gpr(vcpu, rt, t);
 			}
 			break;
 		case OP_31_XOP_DCBA:
@@ -214,17 +219,17 @@ int kvmppc_core_emulate_op(struct kvm_run *run, struct kvm_vcpu *vcpu,
 			break;
 		case OP_31_XOP_DCBZ:
 		{
-			ulong rb = kvmppc_get_gpr(vcpu, get_rb(inst));
-			ulong ra = 0;
+			ulong rb_val = kvmppc_get_gpr(vcpu, rb);
+			ulong ra_val = 0;
 			ulong addr, vaddr;
 			u32 zeros[8] = { 0, 0, 0, 0, 0, 0, 0, 0 };
 			u32 dsisr;
 			int r;
 
-			if (get_ra(inst))
-				ra = kvmppc_get_gpr(vcpu, get_ra(inst));
+			if (ra)
+				ra_val = kvmppc_get_gpr(vcpu, ra);
 
-			addr = (ra + rb) & ~31ULL;
+			addr = (ra_val + rb_val) & ~31ULL;
 			if (!(vcpu->arch.shared->msr & MSR_SF))
 				addr &= 0xffffffff;
 			vaddr = addr;
@@ -565,23 +570,22 @@ u32 kvmppc_alignment_dsisr(struct kvm_vcpu *vcpu, unsigned int inst)
 ulong kvmppc_alignment_dar(struct kvm_vcpu *vcpu, unsigned int inst)
 {
 	ulong dar = 0;
-	ulong ra;
+	ulong ra = get_ra(inst);
+	ulong rb = get_rb(inst);
 
 	switch (get_op(inst)) {
 	case OP_LFS:
 	case OP_LFD:
 	case OP_STFD:
 	case OP_STFS:
-		ra = get_ra(inst);
 		if (ra)
 			dar = kvmppc_get_gpr(vcpu, ra);
 		dar += (s32)((s16)inst);
 		break;
 	case 31:
-		ra = get_ra(inst);
 		if (ra)
 			dar = kvmppc_get_gpr(vcpu, ra);
-		dar += kvmppc_get_gpr(vcpu, get_rb(inst));
+		dar += kvmppc_get_gpr(vcpu, rb);
 		break;
 	default:
 		printk(KERN_INFO "KVM: Unaligned instruction 0x%x\n", inst);
diff --git a/arch/powerpc/kvm/booke_emulate.c b/arch/powerpc/kvm/booke_emulate.c
index 904412bbea40..e14f7b23fd3a 100644
--- a/arch/powerpc/kvm/booke_emulate.c
+++ b/arch/powerpc/kvm/booke_emulate.c
@@ -40,8 +40,8 @@ int kvmppc_booke_emulate_op(struct kvm_run *run, struct kvm_vcpu *vcpu,
                             unsigned int inst, int *advance)
 {
 	int emulated = EMULATE_DONE;
-	int rs;
-	int rt;
+	int rs = get_rs(inst);
+	int rt = get_rt(inst);
 
 	switch (get_op(inst)) {
 	case 19:
@@ -62,19 +62,16 @@ int kvmppc_booke_emulate_op(struct kvm_run *run, struct kvm_vcpu *vcpu,
 		switch (get_xop(inst)) {
 
 		case OP_31_XOP_MFMSR:
-			rt = get_rt(inst);
 			kvmppc_set_gpr(vcpu, rt, vcpu->arch.shared->msr);
 			kvmppc_set_exit_type(vcpu, EMULATED_MFMSR_EXITS);
 			break;
 
 		case OP_31_XOP_MTMSR:
-			rs = get_rs(inst);
 			kvmppc_set_exit_type(vcpu, EMULATED_MTMSR_EXITS);
 			kvmppc_set_msr(vcpu, kvmppc_get_gpr(vcpu, rs));
 			break;
 
 		case OP_31_XOP_WRTEE:
-			rs = get_rs(inst);
 			vcpu->arch.shared->msr = (vcpu->arch.shared->msr & ~MSR_EE)
 					| (kvmppc_get_gpr(vcpu, rs) & MSR_EE);
 			kvmppc_set_exit_type(vcpu, EMULATED_WRTEE_EXITS);
diff --git a/arch/powerpc/kvm/e500_emulate.c b/arch/powerpc/kvm/e500_emulate.c
index 99155f847a6a..9b2dcda71950 100644
--- a/arch/powerpc/kvm/e500_emulate.c
+++ b/arch/powerpc/kvm/e500_emulate.c
@@ -86,9 +86,9 @@ int kvmppc_core_emulate_op(struct kvm_run *run, struct kvm_vcpu *vcpu,
                            unsigned int inst, int *advance)
 {
 	int emulated = EMULATE_DONE;
-	int ra;
-	int rb;
-	int rt;
+	int ra = get_ra(inst);
+	int rb = get_rb(inst);
+	int rt = get_rt(inst);
 
 	switch (get_op(inst)) {
 	case 31:
@@ -96,11 +96,11 @@ int kvmppc_core_emulate_op(struct kvm_run *run, struct kvm_vcpu *vcpu,
 
 #ifdef CONFIG_KVM_E500MC
 		case XOP_MSGSND:
-			emulated = kvmppc_e500_emul_msgsnd(vcpu, get_rb(inst));
+			emulated = kvmppc_e500_emul_msgsnd(vcpu, rb);
 			break;
 
 		case XOP_MSGCLR:
-			emulated = kvmppc_e500_emul_msgclr(vcpu, get_rb(inst));
+			emulated = kvmppc_e500_emul_msgclr(vcpu, rb);
 			break;
 #endif
 
@@ -113,20 +113,14 @@ int kvmppc_core_emulate_op(struct kvm_run *run, struct kvm_vcpu *vcpu,
 			break;
 
 		case XOP_TLBSX:
-			rb = get_rb(inst);
 			emulated = kvmppc_e500_emul_tlbsx(vcpu,rb);
 			break;
 
 		case XOP_TLBILX:
-			ra = get_ra(inst);
-			rb = get_rb(inst);
-			rt = get_rt(inst);
 			emulated = kvmppc_e500_emul_tlbilx(vcpu, rt, ra, rb);
 			break;
 
 		case XOP_TLBIVAX:
-			ra = get_ra(inst);
-			rb = get_rb(inst);
 			emulated = kvmppc_e500_emul_tlbivax(vcpu, ra, rb);
 			break;
 
diff --git a/arch/powerpc/kvm/emulate.c b/arch/powerpc/kvm/emulate.c
index a27d4dc3b4a3..f63b5cbd8221 100644
--- a/arch/powerpc/kvm/emulate.c
+++ b/arch/powerpc/kvm/emulate.c
@@ -148,11 +148,10 @@ u32 kvmppc_get_dec(struct kvm_vcpu *vcpu, u64 tb)
 int kvmppc_emulate_instruction(struct kvm_run *run, struct kvm_vcpu *vcpu)
 {
 	u32 inst = kvmppc_get_last_inst(vcpu);
-	int ra;
-	int rb;
-	int rs;
-	int rt;
-	int sprn;
+	int ra = get_ra(inst);
+	int rs = get_rs(inst);
+	int rt = get_rt(inst);
+	int sprn = get_sprn(inst);
 	enum emulation_result emulated = EMULATE_DONE;
 	int advance = 1;
 
@@ -189,43 +188,31 @@ int kvmppc_emulate_instruction(struct kvm_run *run, struct kvm_vcpu *vcpu)
 			advance = 0;
 			break;
 		case OP_31_XOP_LWZX:
-			rt = get_rt(inst);
 			emulated = kvmppc_handle_load(run, vcpu, rt, 4, 1);
 			break;
 
 		case OP_31_XOP_LBZX:
-			rt = get_rt(inst);
 			emulated = kvmppc_handle_load(run, vcpu, rt, 1, 1);
 			break;
 
 		case OP_31_XOP_LBZUX:
-			rt = get_rt(inst);
-			ra = get_ra(inst);
-			rb = get_rb(inst);
-
 			emulated = kvmppc_handle_load(run, vcpu, rt, 1, 1);
 			kvmppc_set_gpr(vcpu, ra, vcpu->arch.vaddr_accessed);
 			break;
 
 		case OP_31_XOP_STWX:
-			rs = get_rs(inst);
 			emulated = kvmppc_handle_store(run, vcpu,
 						       kvmppc_get_gpr(vcpu, rs),
 			                               4, 1);
 			break;
 
 		case OP_31_XOP_STBX:
-			rs = get_rs(inst);
 			emulated = kvmppc_handle_store(run, vcpu,
 						       kvmppc_get_gpr(vcpu, rs),
 			                               1, 1);
 			break;
 
 		case OP_31_XOP_STBUX:
-			rs = get_rs(inst);
-			ra = get_ra(inst);
-			rb = get_rb(inst);
-
 			emulated = kvmppc_handle_store(run, vcpu,
 						       kvmppc_get_gpr(vcpu, rs),
 			                               1, 1);
@@ -233,28 +220,19 @@ int kvmppc_emulate_instruction(struct kvm_run *run, struct kvm_vcpu *vcpu)
 			break;
 
 		case OP_31_XOP_LHAX:
-			rt = get_rt(inst);
 			emulated = kvmppc_handle_loads(run, vcpu, rt, 2, 1);
 			break;
 
 		case OP_31_XOP_LHZX:
-			rt = get_rt(inst);
 			emulated = kvmppc_handle_load(run, vcpu, rt, 2, 1);
 			break;
 
 		case OP_31_XOP_LHZUX:
-			rt = get_rt(inst);
-			ra = get_ra(inst);
-			rb = get_rb(inst);
-
 			emulated = kvmppc_handle_load(run, vcpu, rt, 2, 1);
 			kvmppc_set_gpr(vcpu, ra, vcpu->arch.vaddr_accessed);
 			break;
 
 		case OP_31_XOP_MFSPR:
-			sprn = get_sprn(inst);
-			rt = get_rt(inst);
-
 			switch (sprn) {
 			case SPRN_SRR0:
 				kvmppc_set_gpr(vcpu, rt, vcpu->arch.shared->srr0);
@@ -310,20 +288,12 @@ int kvmppc_emulate_instruction(struct kvm_run *run, struct kvm_vcpu *vcpu)
 			break;
 
 		case OP_31_XOP_STHX:
-			rs = get_rs(inst);
-			ra = get_ra(inst);
-			rb = get_rb(inst);
-
 			emulated = kvmppc_handle_store(run, vcpu,
 						       kvmppc_get_gpr(vcpu, rs),
 			                               2, 1);
 			break;
 
 		case OP_31_XOP_STHUX:
-			rs = get_rs(inst);
-			ra = get_ra(inst);
-			rb = get_rb(inst);
-
 			emulated = kvmppc_handle_store(run, vcpu,
 						       kvmppc_get_gpr(vcpu, rs),
 			                               2, 1);
@@ -331,8 +301,6 @@ int kvmppc_emulate_instruction(struct kvm_run *run, struct kvm_vcpu *vcpu)
 			break;
 
 		case OP_31_XOP_MTSPR:
-			sprn = get_sprn(inst);
-			rs = get_rs(inst);
 			switch (sprn) {
 			case SPRN_SRR0:
 				vcpu->arch.shared->srr0 = kvmppc_get_gpr(vcpu, rs);
@@ -384,7 +352,6 @@ int kvmppc_emulate_instruction(struct kvm_run *run, struct kvm_vcpu *vcpu)
 			break;
 
 		case OP_31_XOP_LWBRX:
-			rt = get_rt(inst);
 			emulated = kvmppc_handle_load(run, vcpu, rt, 4, 0);
 			break;
 
@@ -392,25 +359,16 @@ int kvmppc_emulate_instruction(struct kvm_run *run, struct kvm_vcpu *vcpu)
 			break;
 
 		case OP_31_XOP_STWBRX:
-			rs = get_rs(inst);
-			ra = get_ra(inst);
-			rb = get_rb(inst);
-
 			emulated = kvmppc_handle_store(run, vcpu,
 						       kvmppc_get_gpr(vcpu, rs),
 			                               4, 0);
 			break;
 
 		case OP_31_XOP_LHBRX:
-			rt = get_rt(inst);
 			emulated = kvmppc_handle_load(run, vcpu, rt, 2, 0);
 			break;
 
 		case OP_31_XOP_STHBRX:
-			rs = get_rs(inst);
-			ra = get_ra(inst);
-			rb = get_rb(inst);
-
 			emulated = kvmppc_handle_store(run, vcpu,
 						       kvmppc_get_gpr(vcpu, rs),
 			                               2, 0);
@@ -423,39 +381,30 @@ int kvmppc_emulate_instruction(struct kvm_run *run, struct kvm_vcpu *vcpu)
 		break;
 
 	case OP_LWZ:
-		rt = get_rt(inst);
 		emulated = kvmppc_handle_load(run, vcpu, rt, 4, 1);
 		break;
 
 	case OP_LWZU:
-		ra = get_ra(inst);
-		rt = get_rt(inst);
 		emulated = kvmppc_handle_load(run, vcpu, rt, 4, 1);
 		kvmppc_set_gpr(vcpu, ra, vcpu->arch.vaddr_accessed);
 		break;
 
 	case OP_LBZ:
-		rt = get_rt(inst);
 		emulated = kvmppc_handle_load(run, vcpu, rt, 1, 1);
 		break;
 
 	case OP_LBZU:
-		ra = get_ra(inst);
-		rt = get_rt(inst);
 		emulated = kvmppc_handle_load(run, vcpu, rt, 1, 1);
 		kvmppc_set_gpr(vcpu, ra, vcpu->arch.vaddr_accessed);
 		break;
 
 	case OP_STW:
-		rs = get_rs(inst);
 		emulated = kvmppc_handle_store(run, vcpu,
 					       kvmppc_get_gpr(vcpu, rs),
 		                               4, 1);
 		break;
 
 	case OP_STWU:
-		ra = get_ra(inst);
-		rs = get_rs(inst);
 		emulated = kvmppc_handle_store(run, vcpu,
 					       kvmppc_get_gpr(vcpu, rs),
 		                               4, 1);
@@ -463,15 +412,12 @@ int kvmppc_emulate_instruction(struct kvm_run *run, struct kvm_vcpu *vcpu)
 		break;
 
 	case OP_STB:
-		rs = get_rs(inst);
 		emulated = kvmppc_handle_store(run, vcpu,
 					       kvmppc_get_gpr(vcpu, rs),
 		                               1, 1);
 		break;
 
 	case OP_STBU:
-		ra = get_ra(inst);
-		rs = get_rs(inst);
 		emulated = kvmppc_handle_store(run, vcpu,
 					       kvmppc_get_gpr(vcpu, rs),
 		                               1, 1);
@@ -479,39 +425,30 @@ int kvmppc_emulate_instruction(struct kvm_run *run, struct kvm_vcpu *vcpu)
 		break;
 
 	case OP_LHZ:
-		rt = get_rt(inst);
 		emulated = kvmppc_handle_load(run, vcpu, rt, 2, 1);
 		break;
 
 	case OP_LHZU:
-		ra = get_ra(inst);
-		rt = get_rt(inst);
 		emulated = kvmppc_handle_load(run, vcpu, rt, 2, 1);
 		kvmppc_set_gpr(vcpu, ra, vcpu->arch.vaddr_accessed);
 		break;
 
 	case OP_LHA:
-		rt = get_rt(inst);
 		emulated = kvmppc_handle_loads(run, vcpu, rt, 2, 1);
 		break;
 
 	case OP_LHAU:
-		ra = get_ra(inst);
-		rt = get_rt(inst);
 		emulated = kvmppc_handle_loads(run, vcpu, rt, 2, 1);
 		kvmppc_set_gpr(vcpu, ra, vcpu->arch.vaddr_accessed);
 		break;
 
 	case OP_STH:
-		rs = get_rs(inst);
 		emulated = kvmppc_handle_store(run, vcpu,
 					       kvmppc_get_gpr(vcpu, rs),
 		                               2, 1);
 		break;
 
 	case OP_STHU:
-		ra = get_ra(inst);
-		rs = get_rs(inst);
 		emulated = kvmppc_handle_store(run, vcpu,
 					       kvmppc_get_gpr(vcpu, rs),
 		                               2, 1);

From 54771e6217ce05a474827d9b23ff03de9d2ef2a0 Mon Sep 17 00:00:00 2001
From: Alexander Graf <agraf@suse.de>
Date: Fri, 4 May 2012 14:55:12 +0200
Subject: [PATCH 16/16] KVM: PPC: Emulator: clean up SPR reads and writes

When reading and writing SPRs, every SPR emulation piece had to read
or write the respective GPR the value was read from or stored in itself.

This approach is pretty prone to failure. What if we accidentally
implement mfspr emulation where we just do "break" and nothing else?
Suddenly we would get a random value in the return register - which is
always a bad idea.

So let's consolidate the generic code paths and only give the core
specific SPR handling code readily made variables to read/write from/to.

Functionally, this patch doesn't change anything, but it increases the
readability of the code and makes is less prone to bugs.

Signed-off-by: Alexander Graf <agraf@suse.de>
---
 arch/powerpc/include/asm/kvm_ppc.h |   6 +-
 arch/powerpc/kvm/44x_emulate.c     |  24 +++----
 arch/powerpc/kvm/book3s_emulate.c  |  34 +++++----
 arch/powerpc/kvm/book3s_hv.c       |   4 +-
 arch/powerpc/kvm/booke.h           |   4 +-
 arch/powerpc/kvm/booke_emulate.c   |  88 +++++++++++++----------
 arch/powerpc/kvm/e500_emulate.c    | 110 +++++++++++++++++------------
 arch/powerpc/kvm/emulate.c         |  64 +++++++++--------
 8 files changed, 190 insertions(+), 144 deletions(-)

diff --git a/arch/powerpc/include/asm/kvm_ppc.h b/arch/powerpc/include/asm/kvm_ppc.h
index c87e3b503fdc..f68c22fa2fce 100644
--- a/arch/powerpc/include/asm/kvm_ppc.h
+++ b/arch/powerpc/include/asm/kvm_ppc.h
@@ -107,8 +107,10 @@ extern void kvmppc_core_dequeue_external(struct kvm_vcpu *vcpu,
 
 extern int kvmppc_core_emulate_op(struct kvm_run *run, struct kvm_vcpu *vcpu,
                                   unsigned int op, int *advance);
-extern int kvmppc_core_emulate_mtspr(struct kvm_vcpu *vcpu, int sprn, int rs);
-extern int kvmppc_core_emulate_mfspr(struct kvm_vcpu *vcpu, int sprn, int rt);
+extern int kvmppc_core_emulate_mtspr(struct kvm_vcpu *vcpu, int sprn,
+				     ulong val);
+extern int kvmppc_core_emulate_mfspr(struct kvm_vcpu *vcpu, int sprn,
+				     ulong *val);
 
 extern int kvmppc_booke_init(void);
 extern void kvmppc_booke_exit(void);
diff --git a/arch/powerpc/kvm/44x_emulate.c b/arch/powerpc/kvm/44x_emulate.c
index da81a2d92380..c8c61578fdfc 100644
--- a/arch/powerpc/kvm/44x_emulate.c
+++ b/arch/powerpc/kvm/44x_emulate.c
@@ -128,41 +128,41 @@ int kvmppc_core_emulate_op(struct kvm_run *run, struct kvm_vcpu *vcpu,
 	return emulated;
 }
 
-int kvmppc_core_emulate_mtspr(struct kvm_vcpu *vcpu, int sprn, int rs)
+int kvmppc_core_emulate_mtspr(struct kvm_vcpu *vcpu, int sprn, ulong spr_val)
 {
 	int emulated = EMULATE_DONE;
 
 	switch (sprn) {
 	case SPRN_PID:
-		kvmppc_set_pid(vcpu, kvmppc_get_gpr(vcpu, rs)); break;
+		kvmppc_set_pid(vcpu, spr_val); break;
 	case SPRN_MMUCR:
-		vcpu->arch.mmucr = kvmppc_get_gpr(vcpu, rs); break;
+		vcpu->arch.mmucr = spr_val; break;
 	case SPRN_CCR0:
-		vcpu->arch.ccr0 = kvmppc_get_gpr(vcpu, rs); break;
+		vcpu->arch.ccr0 = spr_val; break;
 	case SPRN_CCR1:
-		vcpu->arch.ccr1 = kvmppc_get_gpr(vcpu, rs); break;
+		vcpu->arch.ccr1 = spr_val; break;
 	default:
-		emulated = kvmppc_booke_emulate_mtspr(vcpu, sprn, rs);
+		emulated = kvmppc_booke_emulate_mtspr(vcpu, sprn, spr_val);
 	}
 
 	return emulated;
 }
 
-int kvmppc_core_emulate_mfspr(struct kvm_vcpu *vcpu, int sprn, int rt)
+int kvmppc_core_emulate_mfspr(struct kvm_vcpu *vcpu, int sprn, ulong *spr_val)
 {
 	int emulated = EMULATE_DONE;
 
 	switch (sprn) {
 	case SPRN_PID:
-		kvmppc_set_gpr(vcpu, rt, vcpu->arch.pid); break;
+		*spr_val = vcpu->arch.pid; break;
 	case SPRN_MMUCR:
-		kvmppc_set_gpr(vcpu, rt, vcpu->arch.mmucr); break;
+		*spr_val = vcpu->arch.mmucr; break;
 	case SPRN_CCR0:
-		kvmppc_set_gpr(vcpu, rt, vcpu->arch.ccr0); break;
+		*spr_val = vcpu->arch.ccr0; break;
 	case SPRN_CCR1:
-		kvmppc_set_gpr(vcpu, rt, vcpu->arch.ccr1); break;
+		*spr_val = vcpu->arch.ccr1; break;
 	default:
-		emulated = kvmppc_booke_emulate_mfspr(vcpu, sprn, rt);
+		emulated = kvmppc_booke_emulate_mfspr(vcpu, sprn, spr_val);
 	}
 
 	return emulated;
diff --git a/arch/powerpc/kvm/book3s_emulate.c b/arch/powerpc/kvm/book3s_emulate.c
index c023bcd253ff..b9a989dc76cc 100644
--- a/arch/powerpc/kvm/book3s_emulate.c
+++ b/arch/powerpc/kvm/book3s_emulate.c
@@ -318,10 +318,9 @@ static struct kvmppc_bat *kvmppc_find_bat(struct kvm_vcpu *vcpu, int sprn)
 	return bat;
 }
 
-int kvmppc_core_emulate_mtspr(struct kvm_vcpu *vcpu, int sprn, int rs)
+int kvmppc_core_emulate_mtspr(struct kvm_vcpu *vcpu, int sprn, ulong spr_val)
 {
 	int emulated = EMULATE_DONE;
-	ulong spr_val = kvmppc_get_gpr(vcpu, rs);
 
 	switch (sprn) {
 	case SPRN_SDR1:
@@ -433,7 +432,7 @@ unprivileged:
 	return emulated;
 }
 
-int kvmppc_core_emulate_mfspr(struct kvm_vcpu *vcpu, int sprn, int rt)
+int kvmppc_core_emulate_mfspr(struct kvm_vcpu *vcpu, int sprn, ulong *spr_val)
 {
 	int emulated = EMULATE_DONE;
 
@@ -446,46 +445,46 @@ int kvmppc_core_emulate_mfspr(struct kvm_vcpu *vcpu, int sprn, int rt)
 		struct kvmppc_bat *bat = kvmppc_find_bat(vcpu, sprn);
 
 		if (sprn % 2)
-			kvmppc_set_gpr(vcpu, rt, bat->raw >> 32);
+			*spr_val = bat->raw >> 32;
 		else
-			kvmppc_set_gpr(vcpu, rt, bat->raw);
+			*spr_val = bat->raw;
 
 		break;
 	}
 	case SPRN_SDR1:
 		if (!spr_allowed(vcpu, PRIV_HYPER))
 			goto unprivileged;
-		kvmppc_set_gpr(vcpu, rt, to_book3s(vcpu)->sdr1);
+		*spr_val = to_book3s(vcpu)->sdr1;
 		break;
 	case SPRN_DSISR:
-		kvmppc_set_gpr(vcpu, rt, vcpu->arch.shared->dsisr);
+		*spr_val = vcpu->arch.shared->dsisr;
 		break;
 	case SPRN_DAR:
-		kvmppc_set_gpr(vcpu, rt, vcpu->arch.shared->dar);
+		*spr_val = vcpu->arch.shared->dar;
 		break;
 	case SPRN_HIOR:
-		kvmppc_set_gpr(vcpu, rt, to_book3s(vcpu)->hior);
+		*spr_val = to_book3s(vcpu)->hior;
 		break;
 	case SPRN_HID0:
-		kvmppc_set_gpr(vcpu, rt, to_book3s(vcpu)->hid[0]);
+		*spr_val = to_book3s(vcpu)->hid[0];
 		break;
 	case SPRN_HID1:
-		kvmppc_set_gpr(vcpu, rt, to_book3s(vcpu)->hid[1]);
+		*spr_val = to_book3s(vcpu)->hid[1];
 		break;
 	case SPRN_HID2:
 	case SPRN_HID2_GEKKO:
-		kvmppc_set_gpr(vcpu, rt, to_book3s(vcpu)->hid[2]);
+		*spr_val = to_book3s(vcpu)->hid[2];
 		break;
 	case SPRN_HID4:
 	case SPRN_HID4_GEKKO:
-		kvmppc_set_gpr(vcpu, rt, to_book3s(vcpu)->hid[4]);
+		*spr_val = to_book3s(vcpu)->hid[4];
 		break;
 	case SPRN_HID5:
-		kvmppc_set_gpr(vcpu, rt, to_book3s(vcpu)->hid[5]);
+		*spr_val = to_book3s(vcpu)->hid[5];
 		break;
 	case SPRN_CFAR:
 	case SPRN_PURR:
-		kvmppc_set_gpr(vcpu, rt, 0);
+		*spr_val = 0;
 		break;
 	case SPRN_GQR0:
 	case SPRN_GQR1:
@@ -495,8 +494,7 @@ int kvmppc_core_emulate_mfspr(struct kvm_vcpu *vcpu, int sprn, int rt)
 	case SPRN_GQR5:
 	case SPRN_GQR6:
 	case SPRN_GQR7:
-		kvmppc_set_gpr(vcpu, rt,
-			       to_book3s(vcpu)->gqr[sprn - SPRN_GQR0]);
+		*spr_val = to_book3s(vcpu)->gqr[sprn - SPRN_GQR0];
 		break;
 	case SPRN_THRM1:
 	case SPRN_THRM2:
@@ -511,7 +509,7 @@ int kvmppc_core_emulate_mfspr(struct kvm_vcpu *vcpu, int sprn, int rt)
 	case SPRN_PMC3_GEKKO:
 	case SPRN_PMC4_GEKKO:
 	case SPRN_WPAR_GEKKO:
-		kvmppc_set_gpr(vcpu, rt, 0);
+		*spr_val = 0;
 		break;
 	default:
 unprivileged:
diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c
index bb5a0f4b4bbb..db36598a90d7 100644
--- a/arch/powerpc/kvm/book3s_hv.c
+++ b/arch/powerpc/kvm/book3s_hv.c
@@ -1505,12 +1505,12 @@ int kvmppc_core_emulate_op(struct kvm_run *run, struct kvm_vcpu *vcpu,
 	return EMULATE_FAIL;
 }
 
-int kvmppc_core_emulate_mtspr(struct kvm_vcpu *vcpu, int sprn, int rs)
+int kvmppc_core_emulate_mtspr(struct kvm_vcpu *vcpu, int sprn, ulong spr_val)
 {
 	return EMULATE_FAIL;
 }
 
-int kvmppc_core_emulate_mfspr(struct kvm_vcpu *vcpu, int sprn, int rt)
+int kvmppc_core_emulate_mfspr(struct kvm_vcpu *vcpu, int sprn, ulong *spr_val)
 {
 	return EMULATE_FAIL;
 }
diff --git a/arch/powerpc/kvm/booke.h b/arch/powerpc/kvm/booke.h
index 62c4fe55d19b..ba61974c1e20 100644
--- a/arch/powerpc/kvm/booke.h
+++ b/arch/powerpc/kvm/booke.h
@@ -75,8 +75,8 @@ void kvmppc_clr_tsr_bits(struct kvm_vcpu *vcpu, u32 tsr_bits);
 
 int kvmppc_booke_emulate_op(struct kvm_run *run, struct kvm_vcpu *vcpu,
                             unsigned int inst, int *advance);
-int kvmppc_booke_emulate_mfspr(struct kvm_vcpu *vcpu, int sprn, int rt);
-int kvmppc_booke_emulate_mtspr(struct kvm_vcpu *vcpu, int sprn, int rs);
+int kvmppc_booke_emulate_mfspr(struct kvm_vcpu *vcpu, int sprn, ulong *spr_val);
+int kvmppc_booke_emulate_mtspr(struct kvm_vcpu *vcpu, int sprn, ulong spr_val);
 
 /* low-level asm code to transfer guest state */
 void kvmppc_load_guest_spe(struct kvm_vcpu *vcpu);
diff --git a/arch/powerpc/kvm/booke_emulate.c b/arch/powerpc/kvm/booke_emulate.c
index e14f7b23fd3a..6c76397f2af4 100644
--- a/arch/powerpc/kvm/booke_emulate.c
+++ b/arch/powerpc/kvm/booke_emulate.c
@@ -102,22 +102,26 @@ int kvmppc_booke_emulate_op(struct kvm_run *run, struct kvm_vcpu *vcpu,
  * will return the wrong result if called for them in another context
  * (such as debugging).
  */
-int kvmppc_booke_emulate_mtspr(struct kvm_vcpu *vcpu, int sprn, int rs)
+int kvmppc_booke_emulate_mtspr(struct kvm_vcpu *vcpu, int sprn, ulong spr_val)
 {
 	int emulated = EMULATE_DONE;
-	ulong spr_val = kvmppc_get_gpr(vcpu, rs);
 
 	switch (sprn) {
 	case SPRN_DEAR:
-		vcpu->arch.shared->dar = spr_val; break;
+		vcpu->arch.shared->dar = spr_val;
+		break;
 	case SPRN_ESR:
-		vcpu->arch.shared->esr = spr_val; break;
+		vcpu->arch.shared->esr = spr_val;
+		break;
 	case SPRN_DBCR0:
-		vcpu->arch.dbcr0 = spr_val; break;
+		vcpu->arch.dbcr0 = spr_val;
+		break;
 	case SPRN_DBCR1:
-		vcpu->arch.dbcr1 = spr_val; break;
+		vcpu->arch.dbcr1 = spr_val;
+		break;
 	case SPRN_DBSR:
-		vcpu->arch.dbsr &= ~spr_val; break;
+		vcpu->arch.dbsr &= ~spr_val;
+		break;
 	case SPRN_TSR:
 		kvmppc_clr_tsr_bits(vcpu, spr_val);
 		break;
@@ -131,13 +135,17 @@ int kvmppc_booke_emulate_mtspr(struct kvm_vcpu *vcpu, int sprn, int rs)
 	 * guest (PR-mode only).
 	 */
 	case SPRN_SPRG4:
-		vcpu->arch.shared->sprg4 = spr_val; break;
+		vcpu->arch.shared->sprg4 = spr_val;
+		break;
 	case SPRN_SPRG5:
-		vcpu->arch.shared->sprg5 = spr_val; break;
+		vcpu->arch.shared->sprg5 = spr_val;
+		break;
 	case SPRN_SPRG6:
-		vcpu->arch.shared->sprg6 = spr_val; break;
+		vcpu->arch.shared->sprg6 = spr_val;
+		break;
 	case SPRN_SPRG7:
-		vcpu->arch.shared->sprg7 = spr_val; break;
+		vcpu->arch.shared->sprg7 = spr_val;
+		break;
 
 	case SPRN_IVPR:
 		vcpu->arch.ivpr = spr_val;
@@ -207,75 +215,83 @@ int kvmppc_booke_emulate_mtspr(struct kvm_vcpu *vcpu, int sprn, int rs)
 	return emulated;
 }
 
-int kvmppc_booke_emulate_mfspr(struct kvm_vcpu *vcpu, int sprn, int rt)
+int kvmppc_booke_emulate_mfspr(struct kvm_vcpu *vcpu, int sprn, ulong *spr_val)
 {
 	int emulated = EMULATE_DONE;
 
 	switch (sprn) {
 	case SPRN_IVPR:
-		kvmppc_set_gpr(vcpu, rt, vcpu->arch.ivpr); break;
+		*spr_val = vcpu->arch.ivpr;
+		break;
 	case SPRN_DEAR:
-		kvmppc_set_gpr(vcpu, rt, vcpu->arch.shared->dar); break;
+		*spr_val = vcpu->arch.shared->dar;
+		break;
 	case SPRN_ESR:
-		kvmppc_set_gpr(vcpu, rt, vcpu->arch.shared->esr); break;
+		*spr_val = vcpu->arch.shared->esr;
+		break;
 	case SPRN_DBCR0:
-		kvmppc_set_gpr(vcpu, rt, vcpu->arch.dbcr0); break;
+		*spr_val = vcpu->arch.dbcr0;
+		break;
 	case SPRN_DBCR1:
-		kvmppc_set_gpr(vcpu, rt, vcpu->arch.dbcr1); break;
+		*spr_val = vcpu->arch.dbcr1;
+		break;
 	case SPRN_DBSR:
-		kvmppc_set_gpr(vcpu, rt, vcpu->arch.dbsr); break;
+		*spr_val = vcpu->arch.dbsr;
+		break;
 	case SPRN_TSR:
-		kvmppc_set_gpr(vcpu, rt, vcpu->arch.tsr); break;
+		*spr_val = vcpu->arch.tsr;
+		break;
 	case SPRN_TCR:
-		kvmppc_set_gpr(vcpu, rt, vcpu->arch.tcr); break;
+		*spr_val = vcpu->arch.tcr;
+		break;
 
 	case SPRN_IVOR0:
-		kvmppc_set_gpr(vcpu, rt, vcpu->arch.ivor[BOOKE_IRQPRIO_CRITICAL]);
+		*spr_val = vcpu->arch.ivor[BOOKE_IRQPRIO_CRITICAL];
 		break;
 	case SPRN_IVOR1:
-		kvmppc_set_gpr(vcpu, rt, vcpu->arch.ivor[BOOKE_IRQPRIO_MACHINE_CHECK]);
+		*spr_val = vcpu->arch.ivor[BOOKE_IRQPRIO_MACHINE_CHECK];
 		break;
 	case SPRN_IVOR2:
-		kvmppc_set_gpr(vcpu, rt, vcpu->arch.ivor[BOOKE_IRQPRIO_DATA_STORAGE]);
+		*spr_val = vcpu->arch.ivor[BOOKE_IRQPRIO_DATA_STORAGE];
 		break;
 	case SPRN_IVOR3:
-		kvmppc_set_gpr(vcpu, rt, vcpu->arch.ivor[BOOKE_IRQPRIO_INST_STORAGE]);
+		*spr_val = vcpu->arch.ivor[BOOKE_IRQPRIO_INST_STORAGE];
 		break;
 	case SPRN_IVOR4:
-		kvmppc_set_gpr(vcpu, rt, vcpu->arch.ivor[BOOKE_IRQPRIO_EXTERNAL]);
+		*spr_val = vcpu->arch.ivor[BOOKE_IRQPRIO_EXTERNAL];
 		break;
 	case SPRN_IVOR5:
-		kvmppc_set_gpr(vcpu, rt, vcpu->arch.ivor[BOOKE_IRQPRIO_ALIGNMENT]);
+		*spr_val = vcpu->arch.ivor[BOOKE_IRQPRIO_ALIGNMENT];
 		break;
 	case SPRN_IVOR6:
-		kvmppc_set_gpr(vcpu, rt, vcpu->arch.ivor[BOOKE_IRQPRIO_PROGRAM]);
+		*spr_val = vcpu->arch.ivor[BOOKE_IRQPRIO_PROGRAM];
 		break;
 	case SPRN_IVOR7:
-		kvmppc_set_gpr(vcpu, rt, vcpu->arch.ivor[BOOKE_IRQPRIO_FP_UNAVAIL]);
+		*spr_val = vcpu->arch.ivor[BOOKE_IRQPRIO_FP_UNAVAIL];
 		break;
 	case SPRN_IVOR8:
-		kvmppc_set_gpr(vcpu, rt, vcpu->arch.ivor[BOOKE_IRQPRIO_SYSCALL]);
+		*spr_val = vcpu->arch.ivor[BOOKE_IRQPRIO_SYSCALL];
 		break;
 	case SPRN_IVOR9:
-		kvmppc_set_gpr(vcpu, rt, vcpu->arch.ivor[BOOKE_IRQPRIO_AP_UNAVAIL]);
+		*spr_val = vcpu->arch.ivor[BOOKE_IRQPRIO_AP_UNAVAIL];
 		break;
 	case SPRN_IVOR10:
-		kvmppc_set_gpr(vcpu, rt, vcpu->arch.ivor[BOOKE_IRQPRIO_DECREMENTER]);
+		*spr_val = vcpu->arch.ivor[BOOKE_IRQPRIO_DECREMENTER];
 		break;
 	case SPRN_IVOR11:
-		kvmppc_set_gpr(vcpu, rt, vcpu->arch.ivor[BOOKE_IRQPRIO_FIT]);
+		*spr_val = vcpu->arch.ivor[BOOKE_IRQPRIO_FIT];
 		break;
 	case SPRN_IVOR12:
-		kvmppc_set_gpr(vcpu, rt, vcpu->arch.ivor[BOOKE_IRQPRIO_WATCHDOG]);
+		*spr_val = vcpu->arch.ivor[BOOKE_IRQPRIO_WATCHDOG];
 		break;
 	case SPRN_IVOR13:
-		kvmppc_set_gpr(vcpu, rt, vcpu->arch.ivor[BOOKE_IRQPRIO_DTLB_MISS]);
+		*spr_val = vcpu->arch.ivor[BOOKE_IRQPRIO_DTLB_MISS];
 		break;
 	case SPRN_IVOR14:
-		kvmppc_set_gpr(vcpu, rt, vcpu->arch.ivor[BOOKE_IRQPRIO_ITLB_MISS]);
+		*spr_val = vcpu->arch.ivor[BOOKE_IRQPRIO_ITLB_MISS];
 		break;
 	case SPRN_IVOR15:
-		kvmppc_set_gpr(vcpu, rt, vcpu->arch.ivor[BOOKE_IRQPRIO_DEBUG]);
+		*spr_val = vcpu->arch.ivor[BOOKE_IRQPRIO_DEBUG];
 		break;
 
 	default:
diff --git a/arch/powerpc/kvm/e500_emulate.c b/arch/powerpc/kvm/e500_emulate.c
index 9b2dcda71950..8b99e076dc81 100644
--- a/arch/powerpc/kvm/e500_emulate.c
+++ b/arch/powerpc/kvm/e500_emulate.c
@@ -140,11 +140,10 @@ int kvmppc_core_emulate_op(struct kvm_run *run, struct kvm_vcpu *vcpu,
 	return emulated;
 }
 
-int kvmppc_core_emulate_mtspr(struct kvm_vcpu *vcpu, int sprn, int rs)
+int kvmppc_core_emulate_mtspr(struct kvm_vcpu *vcpu, int sprn, ulong spr_val)
 {
 	struct kvmppc_vcpu_e500 *vcpu_e500 = to_e500(vcpu);
 	int emulated = EMULATE_DONE;
-	ulong spr_val = kvmppc_get_gpr(vcpu, rs);
 
 	switch (sprn) {
 #ifndef CONFIG_KVM_BOOKE_HV
@@ -154,25 +153,32 @@ int kvmppc_core_emulate_mtspr(struct kvm_vcpu *vcpu, int sprn, int rs)
 	case SPRN_PID1:
 		if (spr_val != 0)
 			return EMULATE_FAIL;
-		vcpu_e500->pid[1] = spr_val; break;
+		vcpu_e500->pid[1] = spr_val;
+		break;
 	case SPRN_PID2:
 		if (spr_val != 0)
 			return EMULATE_FAIL;
-		vcpu_e500->pid[2] = spr_val; break;
+		vcpu_e500->pid[2] = spr_val;
+		break;
 	case SPRN_MAS0:
-		vcpu->arch.shared->mas0 = spr_val; break;
+		vcpu->arch.shared->mas0 = spr_val;
+		break;
 	case SPRN_MAS1:
-		vcpu->arch.shared->mas1 = spr_val; break;
+		vcpu->arch.shared->mas1 = spr_val;
+		break;
 	case SPRN_MAS2:
-		vcpu->arch.shared->mas2 = spr_val; break;
+		vcpu->arch.shared->mas2 = spr_val;
+		break;
 	case SPRN_MAS3:
 		vcpu->arch.shared->mas7_3 &= ~(u64)0xffffffff;
 		vcpu->arch.shared->mas7_3 |= spr_val;
 		break;
 	case SPRN_MAS4:
-		vcpu->arch.shared->mas4 = spr_val; break;
+		vcpu->arch.shared->mas4 = spr_val;
+		break;
 	case SPRN_MAS6:
-		vcpu->arch.shared->mas6 = spr_val; break;
+		vcpu->arch.shared->mas6 = spr_val;
+		break;
 	case SPRN_MAS7:
 		vcpu->arch.shared->mas7_3 &= (u64)0xffffffff;
 		vcpu->arch.shared->mas7_3 |= (u64)spr_val << 32;
@@ -183,11 +189,14 @@ int kvmppc_core_emulate_mtspr(struct kvm_vcpu *vcpu, int sprn, int rs)
 		vcpu_e500->l1csr0 &= ~(L1CSR0_DCFI | L1CSR0_CLFC);
 		break;
 	case SPRN_L1CSR1:
-		vcpu_e500->l1csr1 = spr_val; break;
+		vcpu_e500->l1csr1 = spr_val;
+		break;
 	case SPRN_HID0:
-		vcpu_e500->hid0 = spr_val; break;
+		vcpu_e500->hid0 = spr_val;
+		break;
 	case SPRN_HID1:
-		vcpu_e500->hid1 = spr_val; break;
+		vcpu_e500->hid1 = spr_val;
+		break;
 
 	case SPRN_MMUCSR0:
 		emulated = kvmppc_e500_emul_mt_mmucsr0(vcpu_e500,
@@ -216,90 +225,103 @@ int kvmppc_core_emulate_mtspr(struct kvm_vcpu *vcpu, int sprn, int rs)
 		break;
 #endif
 	default:
-		emulated = kvmppc_booke_emulate_mtspr(vcpu, sprn, rs);
+		emulated = kvmppc_booke_emulate_mtspr(vcpu, sprn, spr_val);
 	}
 
 	return emulated;
 }
 
-int kvmppc_core_emulate_mfspr(struct kvm_vcpu *vcpu, int sprn, int rt)
+int kvmppc_core_emulate_mfspr(struct kvm_vcpu *vcpu, int sprn, ulong *spr_val)
 {
 	struct kvmppc_vcpu_e500 *vcpu_e500 = to_e500(vcpu);
 	int emulated = EMULATE_DONE;
 
 	switch (sprn) {
 #ifndef CONFIG_KVM_BOOKE_HV
-		unsigned long val;
-
 	case SPRN_PID:
-		kvmppc_set_gpr(vcpu, rt, vcpu_e500->pid[0]); break;
+		*spr_val = vcpu_e500->pid[0];
+		break;
 	case SPRN_PID1:
-		kvmppc_set_gpr(vcpu, rt, vcpu_e500->pid[1]); break;
+		*spr_val = vcpu_e500->pid[1];
+		break;
 	case SPRN_PID2:
-		kvmppc_set_gpr(vcpu, rt, vcpu_e500->pid[2]); break;
+		*spr_val = vcpu_e500->pid[2];
+		break;
 	case SPRN_MAS0:
-		kvmppc_set_gpr(vcpu, rt, vcpu->arch.shared->mas0); break;
+		*spr_val = vcpu->arch.shared->mas0;
+		break;
 	case SPRN_MAS1:
-		kvmppc_set_gpr(vcpu, rt, vcpu->arch.shared->mas1); break;
+		*spr_val = vcpu->arch.shared->mas1;
+		break;
 	case SPRN_MAS2:
-		kvmppc_set_gpr(vcpu, rt, vcpu->arch.shared->mas2); break;
+		*spr_val = vcpu->arch.shared->mas2;
+		break;
 	case SPRN_MAS3:
-		val = (u32)vcpu->arch.shared->mas7_3;
-		kvmppc_set_gpr(vcpu, rt, val);
+		*spr_val = (u32)vcpu->arch.shared->mas7_3;
 		break;
 	case SPRN_MAS4:
-		kvmppc_set_gpr(vcpu, rt, vcpu->arch.shared->mas4); break;
+		*spr_val = vcpu->arch.shared->mas4;
+		break;
 	case SPRN_MAS6:
-		kvmppc_set_gpr(vcpu, rt, vcpu->arch.shared->mas6); break;
+		*spr_val = vcpu->arch.shared->mas6;
+		break;
 	case SPRN_MAS7:
-		val = vcpu->arch.shared->mas7_3 >> 32;
-		kvmppc_set_gpr(vcpu, rt, val);
+		*spr_val = vcpu->arch.shared->mas7_3 >> 32;
 		break;
 #endif
 	case SPRN_TLB0CFG:
-		kvmppc_set_gpr(vcpu, rt, vcpu->arch.tlbcfg[0]); break;
+		*spr_val = vcpu->arch.tlbcfg[0];
+		break;
 	case SPRN_TLB1CFG:
-		kvmppc_set_gpr(vcpu, rt, vcpu->arch.tlbcfg[1]); break;
+		*spr_val = vcpu->arch.tlbcfg[1];
+		break;
 	case SPRN_L1CSR0:
-		kvmppc_set_gpr(vcpu, rt, vcpu_e500->l1csr0); break;
+		*spr_val = vcpu_e500->l1csr0;
+		break;
 	case SPRN_L1CSR1:
-		kvmppc_set_gpr(vcpu, rt, vcpu_e500->l1csr1); break;
+		*spr_val = vcpu_e500->l1csr1;
+		break;
 	case SPRN_HID0:
-		kvmppc_set_gpr(vcpu, rt, vcpu_e500->hid0); break;
+		*spr_val = vcpu_e500->hid0;
+		break;
 	case SPRN_HID1:
-		kvmppc_set_gpr(vcpu, rt, vcpu_e500->hid1); break;
+		*spr_val = vcpu_e500->hid1;
+		break;
 	case SPRN_SVR:
-		kvmppc_set_gpr(vcpu, rt, vcpu_e500->svr); break;
+		*spr_val = vcpu_e500->svr;
+		break;
 
 	case SPRN_MMUCSR0:
-		kvmppc_set_gpr(vcpu, rt, 0); break;
+		*spr_val = 0;
+		break;
 
 	case SPRN_MMUCFG:
-		kvmppc_set_gpr(vcpu, rt, vcpu->arch.mmucfg); break;
+		*spr_val = vcpu->arch.mmucfg;
+		break;
 
 	/* extra exceptions */
 	case SPRN_IVOR32:
-		kvmppc_set_gpr(vcpu, rt, vcpu->arch.ivor[BOOKE_IRQPRIO_SPE_UNAVAIL]);
+		*spr_val = vcpu->arch.ivor[BOOKE_IRQPRIO_SPE_UNAVAIL];
 		break;
 	case SPRN_IVOR33:
-		kvmppc_set_gpr(vcpu, rt, vcpu->arch.ivor[BOOKE_IRQPRIO_SPE_FP_DATA]);
+		*spr_val = vcpu->arch.ivor[BOOKE_IRQPRIO_SPE_FP_DATA];
 		break;
 	case SPRN_IVOR34:
-		kvmppc_set_gpr(vcpu, rt, vcpu->arch.ivor[BOOKE_IRQPRIO_SPE_FP_ROUND]);
+		*spr_val = vcpu->arch.ivor[BOOKE_IRQPRIO_SPE_FP_ROUND];
 		break;
 	case SPRN_IVOR35:
-		kvmppc_set_gpr(vcpu, rt, vcpu->arch.ivor[BOOKE_IRQPRIO_PERFORMANCE_MONITOR]);
+		*spr_val = vcpu->arch.ivor[BOOKE_IRQPRIO_PERFORMANCE_MONITOR];
 		break;
 #ifdef CONFIG_KVM_BOOKE_HV
 	case SPRN_IVOR36:
-		kvmppc_set_gpr(vcpu, rt, vcpu->arch.ivor[BOOKE_IRQPRIO_DBELL]);
+		*spr_val = vcpu->arch.ivor[BOOKE_IRQPRIO_DBELL];
 		break;
 	case SPRN_IVOR37:
-		kvmppc_set_gpr(vcpu, rt, vcpu->arch.ivor[BOOKE_IRQPRIO_DBELL_CRIT]);
+		*spr_val = vcpu->arch.ivor[BOOKE_IRQPRIO_DBELL_CRIT];
 		break;
 #endif
 	default:
-		emulated = kvmppc_booke_emulate_mfspr(vcpu, sprn, rt);
+		emulated = kvmppc_booke_emulate_mfspr(vcpu, sprn, spr_val);
 	}
 
 	return emulated;
diff --git a/arch/powerpc/kvm/emulate.c b/arch/powerpc/kvm/emulate.c
index f63b5cbd8221..f90e86dea7a2 100644
--- a/arch/powerpc/kvm/emulate.c
+++ b/arch/powerpc/kvm/emulate.c
@@ -154,6 +154,7 @@ int kvmppc_emulate_instruction(struct kvm_run *run, struct kvm_vcpu *vcpu)
 	int sprn = get_sprn(inst);
 	enum emulation_result emulated = EMULATE_DONE;
 	int advance = 1;
+	ulong spr_val = 0;
 
 	/* this default type might be overwritten by subcategories */
 	kvmppc_set_exit_type(vcpu, EMULATED_INST_EXITS);
@@ -235,55 +236,59 @@ int kvmppc_emulate_instruction(struct kvm_run *run, struct kvm_vcpu *vcpu)
 		case OP_31_XOP_MFSPR:
 			switch (sprn) {
 			case SPRN_SRR0:
-				kvmppc_set_gpr(vcpu, rt, vcpu->arch.shared->srr0);
+				spr_val = vcpu->arch.shared->srr0;
 				break;
 			case SPRN_SRR1:
-				kvmppc_set_gpr(vcpu, rt, vcpu->arch.shared->srr1);
+				spr_val = vcpu->arch.shared->srr1;
 				break;
 			case SPRN_PVR:
-				kvmppc_set_gpr(vcpu, rt, vcpu->arch.pvr); break;
+				spr_val = vcpu->arch.pvr;
+				break;
 			case SPRN_PIR:
-				kvmppc_set_gpr(vcpu, rt, vcpu->vcpu_id); break;
+				spr_val = vcpu->vcpu_id;
+				break;
 			case SPRN_MSSSR0:
-				kvmppc_set_gpr(vcpu, rt, 0); break;
+				spr_val = 0;
+				break;
 
 			/* Note: mftb and TBRL/TBWL are user-accessible, so
 			 * the guest can always access the real TB anyways.
 			 * In fact, we probably will never see these traps. */
 			case SPRN_TBWL:
-				kvmppc_set_gpr(vcpu, rt, get_tb() >> 32); break;
+				spr_val = get_tb() >> 32;
+				break;
 			case SPRN_TBWU:
-				kvmppc_set_gpr(vcpu, rt, get_tb()); break;
+				spr_val = get_tb();
+				break;
 
 			case SPRN_SPRG0:
-				kvmppc_set_gpr(vcpu, rt, vcpu->arch.shared->sprg0);
+				spr_val = vcpu->arch.shared->sprg0;
 				break;
 			case SPRN_SPRG1:
-				kvmppc_set_gpr(vcpu, rt, vcpu->arch.shared->sprg1);
+				spr_val = vcpu->arch.shared->sprg1;
 				break;
 			case SPRN_SPRG2:
-				kvmppc_set_gpr(vcpu, rt, vcpu->arch.shared->sprg2);
+				spr_val = vcpu->arch.shared->sprg2;
 				break;
 			case SPRN_SPRG3:
-				kvmppc_set_gpr(vcpu, rt, vcpu->arch.shared->sprg3);
+				spr_val = vcpu->arch.shared->sprg3;
 				break;
 			/* Note: SPRG4-7 are user-readable, so we don't get
 			 * a trap. */
 
 			case SPRN_DEC:
-			{
-				kvmppc_set_gpr(vcpu, rt,
-					       kvmppc_get_dec(vcpu, get_tb()));
+				spr_val = kvmppc_get_dec(vcpu, get_tb());
 				break;
-			}
 			default:
-				emulated = kvmppc_core_emulate_mfspr(vcpu, sprn, rt);
-				if (emulated == EMULATE_FAIL) {
-					printk("mfspr: unknown spr %x\n", sprn);
-					kvmppc_set_gpr(vcpu, rt, 0);
+				emulated = kvmppc_core_emulate_mfspr(vcpu, sprn,
+								     &spr_val);
+				if (unlikely(emulated == EMULATE_FAIL)) {
+					printk(KERN_INFO "mfspr: unknown spr "
+						"0x%x\n", sprn);
 				}
 				break;
 			}
+			kvmppc_set_gpr(vcpu, rt, spr_val);
 			kvmppc_set_exit_type(vcpu, EMULATED_MFSPR_EXITS);
 			break;
 
@@ -301,12 +306,13 @@ int kvmppc_emulate_instruction(struct kvm_run *run, struct kvm_vcpu *vcpu)
 			break;
 
 		case OP_31_XOP_MTSPR:
+			spr_val = kvmppc_get_gpr(vcpu, rs);
 			switch (sprn) {
 			case SPRN_SRR0:
-				vcpu->arch.shared->srr0 = kvmppc_get_gpr(vcpu, rs);
+				vcpu->arch.shared->srr0 = spr_val;
 				break;
 			case SPRN_SRR1:
-				vcpu->arch.shared->srr1 = kvmppc_get_gpr(vcpu, rs);
+				vcpu->arch.shared->srr1 = spr_val;
 				break;
 
 			/* XXX We need to context-switch the timebase for
@@ -317,27 +323,29 @@ int kvmppc_emulate_instruction(struct kvm_run *run, struct kvm_vcpu *vcpu)
 			case SPRN_MSSSR0: break;
 
 			case SPRN_DEC:
-				vcpu->arch.dec = kvmppc_get_gpr(vcpu, rs);
+				vcpu->arch.dec = spr_val;
 				kvmppc_emulate_dec(vcpu);
 				break;
 
 			case SPRN_SPRG0:
-				vcpu->arch.shared->sprg0 = kvmppc_get_gpr(vcpu, rs);
+				vcpu->arch.shared->sprg0 = spr_val;
 				break;
 			case SPRN_SPRG1:
-				vcpu->arch.shared->sprg1 = kvmppc_get_gpr(vcpu, rs);
+				vcpu->arch.shared->sprg1 = spr_val;
 				break;
 			case SPRN_SPRG2:
-				vcpu->arch.shared->sprg2 = kvmppc_get_gpr(vcpu, rs);
+				vcpu->arch.shared->sprg2 = spr_val;
 				break;
 			case SPRN_SPRG3:
-				vcpu->arch.shared->sprg3 = kvmppc_get_gpr(vcpu, rs);
+				vcpu->arch.shared->sprg3 = spr_val;
 				break;
 
 			default:
-				emulated = kvmppc_core_emulate_mtspr(vcpu, sprn, rs);
+				emulated = kvmppc_core_emulate_mtspr(vcpu, sprn,
+								     spr_val);
 				if (emulated == EMULATE_FAIL)
-					printk("mtspr: unknown spr %x\n", sprn);
+					printk(KERN_INFO "mtspr: unknown spr "
+						"0x%x\n", sprn);
 				break;
 			}
 			kvmppc_set_exit_type(vcpu, EMULATED_MTSPR_EXITS);