From 96bc451a153297bf1f99ef2d633d512ea349ae7a Mon Sep 17 00:00:00 2001
From: Alexander Graf <agraf@suse.de>
Date: Thu, 29 Jul 2010 14:47:42 +0200
Subject: KVM: PPC: Introduce shared page

For transparent variable sharing between the hypervisor and guest, I introduce
a shared page. This shared page will contain all the registers the guest can
read and write safely without exiting guest context.

This patch only implements the stubs required for the basic structure of the
shared page. The actual register moving follows.

Signed-off-by: Alexander Graf <agraf@suse.de>
Signed-off-by: Avi Kivity <avi@redhat.com>
---
 arch/powerpc/kernel/asm-offsets.c | 1 +
 1 file changed, 1 insertion(+)

(limited to 'arch/powerpc/kernel')

diff --git a/arch/powerpc/kernel/asm-offsets.c b/arch/powerpc/kernel/asm-offsets.c
index 1c0607ddccc0..60e7db4c13af 100644
--- a/arch/powerpc/kernel/asm-offsets.c
+++ b/arch/powerpc/kernel/asm-offsets.c
@@ -400,6 +400,7 @@ int main(void)
 	DEFINE(VCPU_SPRG6, offsetof(struct kvm_vcpu, arch.sprg6));
 	DEFINE(VCPU_SPRG7, offsetof(struct kvm_vcpu, arch.sprg7));
 	DEFINE(VCPU_SHADOW_PID, offsetof(struct kvm_vcpu, arch.shadow_pid));
+	DEFINE(VCPU_SHARED, offsetof(struct kvm_vcpu, arch.shared));
 
 	/* book3s */
 #ifdef CONFIG_PPC_BOOK3S
-- 
cgit v1.2.1


From 666e7252a15b7fc4a116e65deaf6da5e4ce660e3 Mon Sep 17 00:00:00 2001
From: Alexander Graf <agraf@suse.de>
Date: Thu, 29 Jul 2010 14:47:43 +0200
Subject: KVM: PPC: Convert MSR to shared page

One of the most obvious registers to share with the guest directly is the
MSR. The MSR contains the "interrupts enabled" flag which the guest has to
toggle in critical sections.

So in order to bring the overhead of interrupt en- and disabling down, let's
put msr into the shared page. Keep in mind that even though you can fully read
its contents, writing to it doesn't always update all state. There are a few
safe fields that don't require hypervisor interaction. See the documentation
for a list of MSR bits that are safe to be set from inside the guest.

Signed-off-by: Alexander Graf <agraf@suse.de>
Signed-off-by: Avi Kivity <avi@redhat.com>
---
 arch/powerpc/kernel/asm-offsets.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'arch/powerpc/kernel')

diff --git a/arch/powerpc/kernel/asm-offsets.c b/arch/powerpc/kernel/asm-offsets.c
index 60e7db4c13af..1221bcdff52f 100644
--- a/arch/powerpc/kernel/asm-offsets.c
+++ b/arch/powerpc/kernel/asm-offsets.c
@@ -394,13 +394,13 @@ int main(void)
 	DEFINE(VCPU_HOST_STACK, offsetof(struct kvm_vcpu, arch.host_stack));
 	DEFINE(VCPU_HOST_PID, offsetof(struct kvm_vcpu, arch.host_pid));
 	DEFINE(VCPU_GPRS, offsetof(struct kvm_vcpu, arch.gpr));
-	DEFINE(VCPU_MSR, offsetof(struct kvm_vcpu, arch.msr));
 	DEFINE(VCPU_SPRG4, offsetof(struct kvm_vcpu, arch.sprg4));
 	DEFINE(VCPU_SPRG5, offsetof(struct kvm_vcpu, arch.sprg5));
 	DEFINE(VCPU_SPRG6, offsetof(struct kvm_vcpu, arch.sprg6));
 	DEFINE(VCPU_SPRG7, offsetof(struct kvm_vcpu, arch.sprg7));
 	DEFINE(VCPU_SHADOW_PID, offsetof(struct kvm_vcpu, arch.shadow_pid));
 	DEFINE(VCPU_SHARED, offsetof(struct kvm_vcpu, arch.shared));
+	DEFINE(VCPU_SHARED_MSR, offsetof(struct kvm_vcpu_arch_shared, msr));
 
 	/* book3s */
 #ifdef CONFIG_PPC_BOOK3S
-- 
cgit v1.2.1


From 2a342ed57756ad5d8af5456959433884367e5ab2 Mon Sep 17 00:00:00 2001
From: Alexander Graf <agraf@suse.de>
Date: Thu, 29 Jul 2010 14:47:48 +0200
Subject: KVM: PPC: Implement hypervisor interface

To communicate with KVM directly we need to plumb some sort of interface
between the guest and KVM. Usually those interfaces use hypercalls.

This hypercall implementation is described in the last patch of the series
in a special documentation file. Please read that for further information.

This patch implements stubs to handle KVM PPC hypercalls on the host and
guest side alike.

Signed-off-by: Alexander Graf <agraf@suse.de>
Signed-off-by: Avi Kivity <avi@redhat.com>
---
 arch/powerpc/kernel/Makefile |  2 ++
 arch/powerpc/kernel/kvm.c    | 68 ++++++++++++++++++++++++++++++++++++++++++++
 2 files changed, 70 insertions(+)
 create mode 100644 arch/powerpc/kernel/kvm.c

(limited to 'arch/powerpc/kernel')

diff --git a/arch/powerpc/kernel/Makefile b/arch/powerpc/kernel/Makefile
index 1dda70129141..3a6955dc7191 100644
--- a/arch/powerpc/kernel/Makefile
+++ b/arch/powerpc/kernel/Makefile
@@ -127,6 +127,8 @@ ifneq ($(CONFIG_XMON)$(CONFIG_KEXEC),)
 obj-y				+= ppc_save_regs.o
 endif
 
+obj-$(CONFIG_KVM_GUEST)		+= kvm.o
+
 # Disable GCOV in odd or sensitive code
 GCOV_PROFILE_prom_init.o := n
 GCOV_PROFILE_ftrace.o := n
diff --git a/arch/powerpc/kernel/kvm.c b/arch/powerpc/kernel/kvm.c
new file mode 100644
index 000000000000..4f85505e4653
--- /dev/null
+++ b/arch/powerpc/kernel/kvm.c
@@ -0,0 +1,68 @@
+/*
+ * Copyright (C) 2010 SUSE Linux Products GmbH. All rights reserved.
+ *
+ * Authors:
+ *     Alexander Graf <agraf@suse.de>
+ *
+ * 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.
+ */
+
+#include <linux/kvm_host.h>
+#include <linux/init.h>
+#include <linux/kvm_para.h>
+#include <linux/slab.h>
+#include <linux/of.h>
+
+#include <asm/reg.h>
+#include <asm/kvm_ppc.h>
+#include <asm/sections.h>
+#include <asm/cacheflush.h>
+#include <asm/disassemble.h>
+
+unsigned long kvm_hypercall(unsigned long *in,
+			    unsigned long *out,
+			    unsigned long nr)
+{
+	unsigned long register r0 asm("r0");
+	unsigned long register r3 asm("r3") = in[0];
+	unsigned long register r4 asm("r4") = in[1];
+	unsigned long register r5 asm("r5") = in[2];
+	unsigned long register r6 asm("r6") = in[3];
+	unsigned long register r7 asm("r7") = in[4];
+	unsigned long register r8 asm("r8") = in[5];
+	unsigned long register r9 asm("r9") = in[6];
+	unsigned long register r10 asm("r10") = in[7];
+	unsigned long register r11 asm("r11") = nr;
+	unsigned long register r12 asm("r12");
+
+	asm volatile("bl	kvm_hypercall_start"
+		     : "=r"(r0), "=r"(r3), "=r"(r4), "=r"(r5), "=r"(r6),
+		       "=r"(r7), "=r"(r8), "=r"(r9), "=r"(r10), "=r"(r11),
+		       "=r"(r12)
+		     : "r"(r3), "r"(r4), "r"(r5), "r"(r6), "r"(r7), "r"(r8),
+		       "r"(r9), "r"(r10), "r"(r11)
+		     : "memory", "cc", "xer", "ctr", "lr");
+
+	out[0] = r4;
+	out[1] = r5;
+	out[2] = r6;
+	out[3] = r7;
+	out[4] = r8;
+	out[5] = r9;
+	out[6] = r10;
+	out[7] = r11;
+
+	return r3;
+}
+EXPORT_SYMBOL_GPL(kvm_hypercall);
-- 
cgit v1.2.1


From d17051cb8d223dffd6bb847b0565ef1654f8e0e1 Mon Sep 17 00:00:00 2001
From: Alexander Graf <agraf@suse.de>
Date: Thu, 29 Jul 2010 14:47:57 +0200
Subject: KVM: PPC: Generic KVM PV guest support

We have all the hypervisor pieces in place now, but the guest parts are still
missing.

This patch implements basic awareness of KVM when running Linux as guest. It
doesn't do anything with it yet though.

Signed-off-by: Alexander Graf <agraf@suse.de>
Signed-off-by: Avi Kivity <avi@redhat.com>
---
 arch/powerpc/kernel/Makefile      |  2 +-
 arch/powerpc/kernel/asm-offsets.c | 15 +++++++++++++++
 arch/powerpc/kernel/kvm.c         |  3 +++
 arch/powerpc/kernel/kvm_emul.S    | 36 ++++++++++++++++++++++++++++++++++++
 4 files changed, 55 insertions(+), 1 deletion(-)
 create mode 100644 arch/powerpc/kernel/kvm_emul.S

(limited to 'arch/powerpc/kernel')

diff --git a/arch/powerpc/kernel/Makefile b/arch/powerpc/kernel/Makefile
index 3a6955dc7191..be257b0aae36 100644
--- a/arch/powerpc/kernel/Makefile
+++ b/arch/powerpc/kernel/Makefile
@@ -127,7 +127,7 @@ ifneq ($(CONFIG_XMON)$(CONFIG_KEXEC),)
 obj-y				+= ppc_save_regs.o
 endif
 
-obj-$(CONFIG_KVM_GUEST)		+= kvm.o
+obj-$(CONFIG_KVM_GUEST)		+= kvm.o kvm_emul.o
 
 # Disable GCOV in odd or sensitive code
 GCOV_PROFILE_prom_init.o := n
diff --git a/arch/powerpc/kernel/asm-offsets.c b/arch/powerpc/kernel/asm-offsets.c
index 1221bcdff52f..37486cafb69d 100644
--- a/arch/powerpc/kernel/asm-offsets.c
+++ b/arch/powerpc/kernel/asm-offsets.c
@@ -465,6 +465,21 @@ int main(void)
 	DEFINE(VCPU_FAULT_ESR, offsetof(struct kvm_vcpu, arch.fault_esr));
 #endif /* CONFIG_PPC_BOOK3S */
 #endif
+
+#ifdef CONFIG_KVM_GUEST
+	DEFINE(KVM_MAGIC_SCRATCH1, offsetof(struct kvm_vcpu_arch_shared,
+					    scratch1));
+	DEFINE(KVM_MAGIC_SCRATCH2, offsetof(struct kvm_vcpu_arch_shared,
+					    scratch2));
+	DEFINE(KVM_MAGIC_SCRATCH3, offsetof(struct kvm_vcpu_arch_shared,
+					    scratch3));
+	DEFINE(KVM_MAGIC_INT, offsetof(struct kvm_vcpu_arch_shared,
+				       int_pending));
+	DEFINE(KVM_MAGIC_MSR, offsetof(struct kvm_vcpu_arch_shared, msr));
+	DEFINE(KVM_MAGIC_CRITICAL, offsetof(struct kvm_vcpu_arch_shared,
+					    critical));
+#endif
+
 #ifdef CONFIG_44x
 	DEFINE(PGD_T_LOG2, PGD_T_LOG2);
 	DEFINE(PTE_T_LOG2, PTE_T_LOG2);
diff --git a/arch/powerpc/kernel/kvm.c b/arch/powerpc/kernel/kvm.c
index 4f85505e4653..a5ece71ecdd2 100644
--- a/arch/powerpc/kernel/kvm.c
+++ b/arch/powerpc/kernel/kvm.c
@@ -30,6 +30,9 @@
 #include <asm/cacheflush.h>
 #include <asm/disassemble.h>
 
+#define KVM_MAGIC_PAGE		(-4096L)
+#define magic_var(x) KVM_MAGIC_PAGE + offsetof(struct kvm_vcpu_arch_shared, x)
+
 unsigned long kvm_hypercall(unsigned long *in,
 			    unsigned long *out,
 			    unsigned long nr)
diff --git a/arch/powerpc/kernel/kvm_emul.S b/arch/powerpc/kernel/kvm_emul.S
new file mode 100644
index 000000000000..5cfa2aeeecb0
--- /dev/null
+++ b/arch/powerpc/kernel/kvm_emul.S
@@ -0,0 +1,36 @@
+/*
+ * 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 SUSE Linux Products GmbH 2010
+ *
+ * Authors: Alexander Graf <agraf@suse.de>
+ */
+
+#include <asm/ppc_asm.h>
+#include <asm/kvm_asm.h>
+#include <asm/reg.h>
+#include <asm/page.h>
+#include <asm/asm-offsets.h>
+
+/* Hypercall entry point. Will be patched with device tree instructions. */
+
+.global kvm_hypercall_start
+kvm_hypercall_start:
+	li	r3, -1
+	nop
+	nop
+	nop
+	blr
+
+#define KVM_MAGIC_PAGE		(-4096)
-- 
cgit v1.2.1


From 73a18109829e7696226a9fd4062d339e7c6ee130 Mon Sep 17 00:00:00 2001
From: Alexander Graf <agraf@suse.de>
Date: Thu, 29 Jul 2010 14:47:58 +0200
Subject: KVM: PPC: KVM PV guest stubs

We will soon start and replace instructions from the text section with
other, paravirtualized versions. To ease the readability of those patches
I split out the generic looping and magic page mapping code out.

This patch still only contains stubs. But at least it loops through the
text section :).

Signed-off-by: Alexander Graf <agraf@suse.de>
Signed-off-by: Avi Kivity <avi@redhat.com>
---
 arch/powerpc/kernel/kvm.c | 95 +++++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 95 insertions(+)

(limited to 'arch/powerpc/kernel')

diff --git a/arch/powerpc/kernel/kvm.c b/arch/powerpc/kernel/kvm.c
index a5ece71ecdd2..e93366fbbd21 100644
--- a/arch/powerpc/kernel/kvm.c
+++ b/arch/powerpc/kernel/kvm.c
@@ -33,6 +33,62 @@
 #define KVM_MAGIC_PAGE		(-4096L)
 #define magic_var(x) KVM_MAGIC_PAGE + offsetof(struct kvm_vcpu_arch_shared, x)
 
+#define KVM_MASK_RT		0x03e00000
+
+static bool kvm_patching_worked = true;
+
+static inline void kvm_patch_ins(u32 *inst, u32 new_inst)
+{
+	*inst = new_inst;
+	flush_icache_range((ulong)inst, (ulong)inst + 4);
+}
+
+static void kvm_map_magic_page(void *data)
+{
+	kvm_hypercall2(KVM_HC_PPC_MAP_MAGIC_PAGE,
+		       KVM_MAGIC_PAGE,  /* Physical Address */
+		       KVM_MAGIC_PAGE); /* Effective Address */
+}
+
+static void kvm_check_ins(u32 *inst)
+{
+	u32 _inst = *inst;
+	u32 inst_no_rt = _inst & ~KVM_MASK_RT;
+	u32 inst_rt = _inst & KVM_MASK_RT;
+
+	switch (inst_no_rt) {
+	}
+
+	switch (_inst) {
+	}
+}
+
+static void kvm_use_magic_page(void)
+{
+	u32 *p;
+	u32 *start, *end;
+	u32 tmp;
+
+	/* Tell the host to map the magic page to -4096 on all CPUs */
+	on_each_cpu(kvm_map_magic_page, NULL, 1);
+
+	/* Quick self-test to see if the mapping works */
+	if (__get_user(tmp, (u32*)KVM_MAGIC_PAGE)) {
+		kvm_patching_worked = false;
+		return;
+	}
+
+	/* Now loop through all code and find instructions */
+	start = (void*)_stext;
+	end = (void*)_etext;
+
+	for (p = start; p < end; p++)
+		kvm_check_ins(p);
+
+	printk(KERN_INFO "KVM: Live patching for a fast VM %s\n",
+			 kvm_patching_worked ? "worked" : "failed");
+}
+
 unsigned long kvm_hypercall(unsigned long *in,
 			    unsigned long *out,
 			    unsigned long nr)
@@ -69,3 +125,42 @@ unsigned long kvm_hypercall(unsigned long *in,
 	return r3;
 }
 EXPORT_SYMBOL_GPL(kvm_hypercall);
+
+static int kvm_para_setup(void)
+{
+	extern u32 kvm_hypercall_start;
+	struct device_node *hyper_node;
+	u32 *insts;
+	int len, i;
+
+	hyper_node = of_find_node_by_path("/hypervisor");
+	if (!hyper_node)
+		return -1;
+
+	insts = (u32*)of_get_property(hyper_node, "hcall-instructions", &len);
+	if (len % 4)
+		return -1;
+	if (len > (4 * 4))
+		return -1;
+
+	for (i = 0; i < (len / 4); i++)
+		kvm_patch_ins(&(&kvm_hypercall_start)[i], insts[i]);
+
+	return 0;
+}
+
+static int __init kvm_guest_init(void)
+{
+	if (!kvm_para_available())
+		return 0;
+
+	if (kvm_para_setup())
+		return 0;
+
+	if (kvm_para_has_feature(KVM_FEATURE_MAGIC_PAGE))
+		kvm_use_magic_page();
+
+	return 0;
+}
+
+postcore_initcall(kvm_guest_init);
-- 
cgit v1.2.1


From d1293c927568f5b5b8dd3fa263a98683cf8556dc Mon Sep 17 00:00:00 2001
From: Alexander Graf <agraf@suse.de>
Date: Thu, 29 Jul 2010 14:47:59 +0200
Subject: KVM: PPC: PV instructions to loads and stores

Some instructions can simply be replaced by load and store instructions to
or from the magic page.

This patch replaces often called instructions that fall into the above category.

Signed-off-by: Alexander Graf <agraf@suse.de>
Signed-off-by: Avi Kivity <avi@redhat.com>
---
 arch/powerpc/kernel/kvm.c | 109 ++++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 109 insertions(+)

(limited to 'arch/powerpc/kernel')

diff --git a/arch/powerpc/kernel/kvm.c b/arch/powerpc/kernel/kvm.c
index e93366fbbd21..9ec572c4d2a5 100644
--- a/arch/powerpc/kernel/kvm.c
+++ b/arch/powerpc/kernel/kvm.c
@@ -33,7 +33,34 @@
 #define KVM_MAGIC_PAGE		(-4096L)
 #define magic_var(x) KVM_MAGIC_PAGE + offsetof(struct kvm_vcpu_arch_shared, x)
 
+#define KVM_INST_LWZ		0x80000000
+#define KVM_INST_STW		0x90000000
+#define KVM_INST_LD		0xe8000000
+#define KVM_INST_STD		0xf8000000
+#define KVM_INST_NOP		0x60000000
+#define KVM_INST_B		0x48000000
+#define KVM_INST_B_MASK		0x03ffffff
+#define KVM_INST_B_MAX		0x01ffffff
+
 #define KVM_MASK_RT		0x03e00000
+#define KVM_INST_MFMSR		0x7c0000a6
+#define KVM_INST_MFSPR_SPRG0	0x7c1042a6
+#define KVM_INST_MFSPR_SPRG1	0x7c1142a6
+#define KVM_INST_MFSPR_SPRG2	0x7c1242a6
+#define KVM_INST_MFSPR_SPRG3	0x7c1342a6
+#define KVM_INST_MFSPR_SRR0	0x7c1a02a6
+#define KVM_INST_MFSPR_SRR1	0x7c1b02a6
+#define KVM_INST_MFSPR_DAR	0x7c1302a6
+#define KVM_INST_MFSPR_DSISR	0x7c1202a6
+
+#define KVM_INST_MTSPR_SPRG0	0x7c1043a6
+#define KVM_INST_MTSPR_SPRG1	0x7c1143a6
+#define KVM_INST_MTSPR_SPRG2	0x7c1243a6
+#define KVM_INST_MTSPR_SPRG3	0x7c1343a6
+#define KVM_INST_MTSPR_SRR0	0x7c1a03a6
+#define KVM_INST_MTSPR_SRR1	0x7c1b03a6
+#define KVM_INST_MTSPR_DAR	0x7c1303a6
+#define KVM_INST_MTSPR_DSISR	0x7c1203a6
 
 static bool kvm_patching_worked = true;
 
@@ -43,6 +70,34 @@ static inline void kvm_patch_ins(u32 *inst, u32 new_inst)
 	flush_icache_range((ulong)inst, (ulong)inst + 4);
 }
 
+static void kvm_patch_ins_ld(u32 *inst, long addr, u32 rt)
+{
+#ifdef CONFIG_64BIT
+	kvm_patch_ins(inst, KVM_INST_LD | rt | (addr & 0x0000fffc));
+#else
+	kvm_patch_ins(inst, KVM_INST_LWZ | rt | ((addr + 4) & 0x0000fffc));
+#endif
+}
+
+static void kvm_patch_ins_lwz(u32 *inst, long addr, u32 rt)
+{
+	kvm_patch_ins(inst, KVM_INST_LWZ | rt | (addr & 0x0000ffff));
+}
+
+static void kvm_patch_ins_std(u32 *inst, long addr, u32 rt)
+{
+#ifdef CONFIG_64BIT
+	kvm_patch_ins(inst, KVM_INST_STD | rt | (addr & 0x0000fffc));
+#else
+	kvm_patch_ins(inst, KVM_INST_STW | rt | ((addr + 4) & 0x0000fffc));
+#endif
+}
+
+static void kvm_patch_ins_stw(u32 *inst, long addr, u32 rt)
+{
+	kvm_patch_ins(inst, KVM_INST_STW | rt | (addr & 0x0000fffc));
+}
+
 static void kvm_map_magic_page(void *data)
 {
 	kvm_hypercall2(KVM_HC_PPC_MAP_MAGIC_PAGE,
@@ -57,6 +112,60 @@ static void kvm_check_ins(u32 *inst)
 	u32 inst_rt = _inst & KVM_MASK_RT;
 
 	switch (inst_no_rt) {
+	/* Loads */
+	case KVM_INST_MFMSR:
+		kvm_patch_ins_ld(inst, magic_var(msr), inst_rt);
+		break;
+	case KVM_INST_MFSPR_SPRG0:
+		kvm_patch_ins_ld(inst, magic_var(sprg0), inst_rt);
+		break;
+	case KVM_INST_MFSPR_SPRG1:
+		kvm_patch_ins_ld(inst, magic_var(sprg1), inst_rt);
+		break;
+	case KVM_INST_MFSPR_SPRG2:
+		kvm_patch_ins_ld(inst, magic_var(sprg2), inst_rt);
+		break;
+	case KVM_INST_MFSPR_SPRG3:
+		kvm_patch_ins_ld(inst, magic_var(sprg3), inst_rt);
+		break;
+	case KVM_INST_MFSPR_SRR0:
+		kvm_patch_ins_ld(inst, magic_var(srr0), inst_rt);
+		break;
+	case KVM_INST_MFSPR_SRR1:
+		kvm_patch_ins_ld(inst, magic_var(srr1), inst_rt);
+		break;
+	case KVM_INST_MFSPR_DAR:
+		kvm_patch_ins_ld(inst, magic_var(dar), inst_rt);
+		break;
+	case KVM_INST_MFSPR_DSISR:
+		kvm_patch_ins_lwz(inst, magic_var(dsisr), inst_rt);
+		break;
+
+	/* Stores */
+	case KVM_INST_MTSPR_SPRG0:
+		kvm_patch_ins_std(inst, magic_var(sprg0), inst_rt);
+		break;
+	case KVM_INST_MTSPR_SPRG1:
+		kvm_patch_ins_std(inst, magic_var(sprg1), inst_rt);
+		break;
+	case KVM_INST_MTSPR_SPRG2:
+		kvm_patch_ins_std(inst, magic_var(sprg2), inst_rt);
+		break;
+	case KVM_INST_MTSPR_SPRG3:
+		kvm_patch_ins_std(inst, magic_var(sprg3), inst_rt);
+		break;
+	case KVM_INST_MTSPR_SRR0:
+		kvm_patch_ins_std(inst, magic_var(srr0), inst_rt);
+		break;
+	case KVM_INST_MTSPR_SRR1:
+		kvm_patch_ins_std(inst, magic_var(srr1), inst_rt);
+		break;
+	case KVM_INST_MTSPR_DAR:
+		kvm_patch_ins_std(inst, magic_var(dar), inst_rt);
+		break;
+	case KVM_INST_MTSPR_DSISR:
+		kvm_patch_ins_stw(inst, magic_var(dsisr), inst_rt);
+		break;
 	}
 
 	switch (_inst) {
-- 
cgit v1.2.1


From d1290b15e7f139e24150cc6e6d8e904214359e8a Mon Sep 17 00:00:00 2001
From: Alexander Graf <agraf@suse.de>
Date: Thu, 29 Jul 2010 14:48:00 +0200
Subject: KVM: PPC: PV tlbsync to nop

With our current MMU scheme we don't need to know about the tlbsync instruction.
So we can just nop it out.

Signed-off-by: Alexander Graf <agraf@suse.de>
Signed-off-by: Avi Kivity <avi@redhat.com>
---
 arch/powerpc/kernel/kvm.c | 12 ++++++++++++
 1 file changed, 12 insertions(+)

(limited to 'arch/powerpc/kernel')

diff --git a/arch/powerpc/kernel/kvm.c b/arch/powerpc/kernel/kvm.c
index 9ec572c4d2a5..3258922cc22c 100644
--- a/arch/powerpc/kernel/kvm.c
+++ b/arch/powerpc/kernel/kvm.c
@@ -62,6 +62,8 @@
 #define KVM_INST_MTSPR_DAR	0x7c1303a6
 #define KVM_INST_MTSPR_DSISR	0x7c1203a6
 
+#define KVM_INST_TLBSYNC	0x7c00046c
+
 static bool kvm_patching_worked = true;
 
 static inline void kvm_patch_ins(u32 *inst, u32 new_inst)
@@ -98,6 +100,11 @@ static void kvm_patch_ins_stw(u32 *inst, long addr, u32 rt)
 	kvm_patch_ins(inst, KVM_INST_STW | rt | (addr & 0x0000fffc));
 }
 
+static void kvm_patch_ins_nop(u32 *inst)
+{
+	kvm_patch_ins(inst, KVM_INST_NOP);
+}
+
 static void kvm_map_magic_page(void *data)
 {
 	kvm_hypercall2(KVM_HC_PPC_MAP_MAGIC_PAGE,
@@ -166,6 +173,11 @@ static void kvm_check_ins(u32 *inst)
 	case KVM_INST_MTSPR_DSISR:
 		kvm_patch_ins_stw(inst, magic_var(dsisr), inst_rt);
 		break;
+
+	/* Nops */
+	case KVM_INST_TLBSYNC:
+		kvm_patch_ins_nop(inst);
+		break;
 	}
 
 	switch (_inst) {
-- 
cgit v1.2.1


From 2d4f567103ff5a931e773f2e356b4eb303115deb Mon Sep 17 00:00:00 2001
From: Alexander Graf <agraf@suse.de>
Date: Thu, 29 Jul 2010 14:48:01 +0200
Subject: KVM: PPC: Introduce kvm_tmp framework

We will soon require more sophisticated methods to replace single instructions
with multiple instructions. We do that by branching to a memory region where we
write replacement code for the instruction to.

This region needs to be within 32 MB of the patched instruction though, because
that's the furthest we can jump with immediate branches.

So we keep 1MB of free space around in bss. After we're done initing we can just
tell the mm system that the unused pages are free, but until then we have enough
space to fit all our code in.

Signed-off-by: Alexander Graf <agraf@suse.de>
Signed-off-by: Avi Kivity <avi@redhat.com>
---
 arch/powerpc/kernel/kvm.c | 42 ++++++++++++++++++++++++++++++++++++++++--
 1 file changed, 40 insertions(+), 2 deletions(-)

(limited to 'arch/powerpc/kernel')

diff --git a/arch/powerpc/kernel/kvm.c b/arch/powerpc/kernel/kvm.c
index 3258922cc22c..926f93fd722d 100644
--- a/arch/powerpc/kernel/kvm.c
+++ b/arch/powerpc/kernel/kvm.c
@@ -65,6 +65,8 @@
 #define KVM_INST_TLBSYNC	0x7c00046c
 
 static bool kvm_patching_worked = true;
+static char kvm_tmp[1024 * 1024];
+static int kvm_tmp_index;
 
 static inline void kvm_patch_ins(u32 *inst, u32 new_inst)
 {
@@ -105,6 +107,23 @@ static void kvm_patch_ins_nop(u32 *inst)
 	kvm_patch_ins(inst, KVM_INST_NOP);
 }
 
+static u32 *kvm_alloc(int len)
+{
+	u32 *p;
+
+	if ((kvm_tmp_index + len) > ARRAY_SIZE(kvm_tmp)) {
+		printk(KERN_ERR "KVM: No more space (%d + %d)\n",
+				kvm_tmp_index, len);
+		kvm_patching_worked = false;
+		return NULL;
+	}
+
+	p = (void*)&kvm_tmp[kvm_tmp_index];
+	kvm_tmp_index += len;
+
+	return p;
+}
+
 static void kvm_map_magic_page(void *data)
 {
 	kvm_hypercall2(KVM_HC_PPC_MAP_MAGIC_PAGE,
@@ -270,17 +289,36 @@ static int kvm_para_setup(void)
 	return 0;
 }
 
+static __init void kvm_free_tmp(void)
+{
+	unsigned long start, end;
+
+	start = (ulong)&kvm_tmp[kvm_tmp_index + (PAGE_SIZE - 1)] & PAGE_MASK;
+	end = (ulong)&kvm_tmp[ARRAY_SIZE(kvm_tmp)] & PAGE_MASK;
+
+	/* Free the tmp space we don't need */
+	for (; start < end; start += PAGE_SIZE) {
+		ClearPageReserved(virt_to_page(start));
+		init_page_count(virt_to_page(start));
+		free_page(start);
+		totalram_pages++;
+	}
+}
+
 static int __init kvm_guest_init(void)
 {
 	if (!kvm_para_available())
-		return 0;
+		goto free_tmp;
 
 	if (kvm_para_setup())
-		return 0;
+		goto free_tmp;
 
 	if (kvm_para_has_feature(KVM_FEATURE_MAGIC_PAGE))
 		kvm_use_magic_page();
 
+free_tmp:
+	kvm_free_tmp();
+
 	return 0;
 }
 
-- 
cgit v1.2.1


From 71ee8e34fe26252b11668a95708783ec9c58cbda Mon Sep 17 00:00:00 2001
From: Alexander Graf <agraf@suse.de>
Date: Thu, 29 Jul 2010 14:48:02 +0200
Subject: KVM: PPC: Introduce branch patching helper

We will need to patch several instruction streams over to a different
code path, so we need a way to patch a single instruction with a branch
somewhere else.

This patch adds a helper to facilitate this patching.

Signed-off-by: Alexander Graf <agraf@suse.de>
Signed-off-by: Avi Kivity <avi@redhat.com>
---
 arch/powerpc/kernel/kvm.c | 14 ++++++++++++++
 1 file changed, 14 insertions(+)

(limited to 'arch/powerpc/kernel')

diff --git a/arch/powerpc/kernel/kvm.c b/arch/powerpc/kernel/kvm.c
index 926f93fd722d..239a70d750a2 100644
--- a/arch/powerpc/kernel/kvm.c
+++ b/arch/powerpc/kernel/kvm.c
@@ -107,6 +107,20 @@ static void kvm_patch_ins_nop(u32 *inst)
 	kvm_patch_ins(inst, KVM_INST_NOP);
 }
 
+static void kvm_patch_ins_b(u32 *inst, int addr)
+{
+#ifdef CONFIG_RELOCATABLE
+	/* On relocatable kernels interrupts handlers and our code
+	   can be in different regions, so we don't patch them */
+
+	extern u32 __end_interrupts;
+	if ((ulong)inst < (ulong)&__end_interrupts)
+		return;
+#endif
+
+	kvm_patch_ins(inst, KVM_INST_B | (addr & KVM_INST_B_MASK));
+}
+
 static u32 *kvm_alloc(int len)
 {
 	u32 *p;
-- 
cgit v1.2.1


From 92234722ed631f472f1c4d79d35d8e5cf6910002 Mon Sep 17 00:00:00 2001
From: Alexander Graf <agraf@suse.de>
Date: Thu, 29 Jul 2010 14:48:03 +0200
Subject: KVM: PPC: PV assembler helpers

When we hook an instruction we need to make sure we don't clobber any of
the registers at that point. So we write them out to scratch space in the
magic page. To make sure we don't fall into a race with another piece of
hooked code, we need to disable interrupts.

To make the later patches and code in general easier readable, let's introduce
a set of defines that save and restore r30, r31 and cr. Let's also define some
helpers to read the lower 32 bits of a 64 bit field on 32 bit systems.

Signed-off-by: Alexander Graf <agraf@suse.de>
Signed-off-by: Avi Kivity <avi@redhat.com>
---
 arch/powerpc/kernel/kvm_emul.S | 30 ++++++++++++++++++++++++++++++
 1 file changed, 30 insertions(+)

(limited to 'arch/powerpc/kernel')

diff --git a/arch/powerpc/kernel/kvm_emul.S b/arch/powerpc/kernel/kvm_emul.S
index 5cfa2aeeecb0..1dac72dd6f6e 100644
--- a/arch/powerpc/kernel/kvm_emul.S
+++ b/arch/powerpc/kernel/kvm_emul.S
@@ -34,3 +34,33 @@ kvm_hypercall_start:
 	blr
 
 #define KVM_MAGIC_PAGE		(-4096)
+
+#ifdef CONFIG_64BIT
+#define LL64(reg, offs, reg2)	ld	reg, (offs)(reg2)
+#define STL64(reg, offs, reg2)	std	reg, (offs)(reg2)
+#else
+#define LL64(reg, offs, reg2)	lwz	reg, (offs + 4)(reg2)
+#define STL64(reg, offs, reg2)	stw	reg, (offs + 4)(reg2)
+#endif
+
+#define SCRATCH_SAVE							\
+	/* Enable critical section. We are critical if			\
+	   shared->critical == r1 */					\
+	STL64(r1, KVM_MAGIC_PAGE + KVM_MAGIC_CRITICAL, 0);		\
+									\
+	/* Save state */						\
+	PPC_STL	r31, (KVM_MAGIC_PAGE + KVM_MAGIC_SCRATCH1)(0);		\
+	PPC_STL	r30, (KVM_MAGIC_PAGE + KVM_MAGIC_SCRATCH2)(0);		\
+	mfcr	r31;							\
+	stw	r31, (KVM_MAGIC_PAGE + KVM_MAGIC_SCRATCH3)(0);
+
+#define SCRATCH_RESTORE							\
+	/* Restore state */						\
+	PPC_LL	r31, (KVM_MAGIC_PAGE + KVM_MAGIC_SCRATCH1)(0);		\
+	lwz	r30, (KVM_MAGIC_PAGE + KVM_MAGIC_SCRATCH3)(0);		\
+	mtcr	r30;							\
+	PPC_LL	r30, (KVM_MAGIC_PAGE + KVM_MAGIC_SCRATCH2)(0);		\
+									\
+	/* Disable critical section. We are critical if			\
+	   shared->critical == r1 and r2 is always != r1 */		\
+	STL64(r2, KVM_MAGIC_PAGE + KVM_MAGIC_CRITICAL, 0);
-- 
cgit v1.2.1


From 819a63dc792b0888edd3eda306a9e1e049dcbb1c Mon Sep 17 00:00:00 2001
From: Alexander Graf <agraf@suse.de>
Date: Thu, 29 Jul 2010 14:48:04 +0200
Subject: KVM: PPC: PV mtmsrd L=1

The PowerPC ISA has a special instruction for mtmsr that only changes the EE
and RI bits, namely the L=1 form.

Since that one is reasonably often occuring and simple to implement, let's
go with this first. Writing EE=0 is always just a store. Doing EE=1 also
requires us to check for pending interrupts and if necessary exit back to the
hypervisor.

Signed-off-by: Alexander Graf <agraf@suse.de>
Signed-off-by: Avi Kivity <avi@redhat.com>
---
 arch/powerpc/kernel/kvm.c      | 45 +++++++++++++++++++++++++++++++++
 arch/powerpc/kernel/kvm_emul.S | 56 ++++++++++++++++++++++++++++++++++++++++++
 2 files changed, 101 insertions(+)

(limited to 'arch/powerpc/kernel')

diff --git a/arch/powerpc/kernel/kvm.c b/arch/powerpc/kernel/kvm.c
index 239a70d750a2..717ab0dded25 100644
--- a/arch/powerpc/kernel/kvm.c
+++ b/arch/powerpc/kernel/kvm.c
@@ -63,6 +63,7 @@
 #define KVM_INST_MTSPR_DSISR	0x7c1203a6
 
 #define KVM_INST_TLBSYNC	0x7c00046c
+#define KVM_INST_MTMSRD_L1	0x7c010164
 
 static bool kvm_patching_worked = true;
 static char kvm_tmp[1024 * 1024];
@@ -138,6 +139,43 @@ static u32 *kvm_alloc(int len)
 	return p;
 }
 
+extern u32 kvm_emulate_mtmsrd_branch_offs;
+extern u32 kvm_emulate_mtmsrd_reg_offs;
+extern u32 kvm_emulate_mtmsrd_len;
+extern u32 kvm_emulate_mtmsrd[];
+
+static void kvm_patch_ins_mtmsrd(u32 *inst, u32 rt)
+{
+	u32 *p;
+	int distance_start;
+	int distance_end;
+	ulong next_inst;
+
+	p = kvm_alloc(kvm_emulate_mtmsrd_len * 4);
+	if (!p)
+		return;
+
+	/* Find out where we are and put everything there */
+	distance_start = (ulong)p - (ulong)inst;
+	next_inst = ((ulong)inst + 4);
+	distance_end = next_inst - (ulong)&p[kvm_emulate_mtmsrd_branch_offs];
+
+	/* Make sure we only write valid b instructions */
+	if (distance_start > KVM_INST_B_MAX) {
+		kvm_patching_worked = false;
+		return;
+	}
+
+	/* Modify the chunk to fit the invocation */
+	memcpy(p, kvm_emulate_mtmsrd, kvm_emulate_mtmsrd_len * 4);
+	p[kvm_emulate_mtmsrd_branch_offs] |= distance_end & KVM_INST_B_MASK;
+	p[kvm_emulate_mtmsrd_reg_offs] |= rt;
+	flush_icache_range((ulong)p, (ulong)p + kvm_emulate_mtmsrd_len * 4);
+
+	/* Patch the invocation */
+	kvm_patch_ins_b(inst, distance_start);
+}
+
 static void kvm_map_magic_page(void *data)
 {
 	kvm_hypercall2(KVM_HC_PPC_MAP_MAGIC_PAGE,
@@ -211,6 +249,13 @@ static void kvm_check_ins(u32 *inst)
 	case KVM_INST_TLBSYNC:
 		kvm_patch_ins_nop(inst);
 		break;
+
+	/* Rewrites */
+	case KVM_INST_MTMSRD_L1:
+		/* We use r30 and r31 during the hook */
+		if (get_rt(inst_rt) < 30)
+			kvm_patch_ins_mtmsrd(inst, inst_rt);
+		break;
 	}
 
 	switch (_inst) {
diff --git a/arch/powerpc/kernel/kvm_emul.S b/arch/powerpc/kernel/kvm_emul.S
index 1dac72dd6f6e..10dc4a6632fd 100644
--- a/arch/powerpc/kernel/kvm_emul.S
+++ b/arch/powerpc/kernel/kvm_emul.S
@@ -64,3 +64,59 @@ kvm_hypercall_start:
 	/* Disable critical section. We are critical if			\
 	   shared->critical == r1 and r2 is always != r1 */		\
 	STL64(r2, KVM_MAGIC_PAGE + KVM_MAGIC_CRITICAL, 0);
+
+.global kvm_emulate_mtmsrd
+kvm_emulate_mtmsrd:
+
+	SCRATCH_SAVE
+
+	/* Put MSR & ~(MSR_EE|MSR_RI) in r31 */
+	LL64(r31, KVM_MAGIC_PAGE + KVM_MAGIC_MSR, 0)
+	lis	r30, (~(MSR_EE | MSR_RI))@h
+	ori	r30, r30, (~(MSR_EE | MSR_RI))@l
+	and	r31, r31, r30
+
+	/* OR the register's (MSR_EE|MSR_RI) on MSR */
+kvm_emulate_mtmsrd_reg:
+	andi.	r30, r0, (MSR_EE|MSR_RI)
+	or	r31, r31, r30
+
+	/* Put MSR back into magic page */
+	STL64(r31, KVM_MAGIC_PAGE + KVM_MAGIC_MSR, 0)
+
+	/* Check if we have to fetch an interrupt */
+	lwz	r31, (KVM_MAGIC_PAGE + KVM_MAGIC_INT)(0)
+	cmpwi	r31, 0
+	beq+	no_check
+
+	/* Check if we may trigger an interrupt */
+	andi.	r30, r30, MSR_EE
+	beq	no_check
+
+	SCRATCH_RESTORE
+
+	/* Nag hypervisor */
+	tlbsync
+
+	b	kvm_emulate_mtmsrd_branch
+
+no_check:
+
+	SCRATCH_RESTORE
+
+	/* Go back to caller */
+kvm_emulate_mtmsrd_branch:
+	b	.
+kvm_emulate_mtmsrd_end:
+
+.global kvm_emulate_mtmsrd_branch_offs
+kvm_emulate_mtmsrd_branch_offs:
+	.long (kvm_emulate_mtmsrd_branch - kvm_emulate_mtmsrd) / 4
+
+.global kvm_emulate_mtmsrd_reg_offs
+kvm_emulate_mtmsrd_reg_offs:
+	.long (kvm_emulate_mtmsrd_reg - kvm_emulate_mtmsrd) / 4
+
+.global kvm_emulate_mtmsrd_len
+kvm_emulate_mtmsrd_len:
+	.long (kvm_emulate_mtmsrd_end - kvm_emulate_mtmsrd) / 4
-- 
cgit v1.2.1


From 7810927760a0d16d7a41be4dab895fbbf9445bc0 Mon Sep 17 00:00:00 2001
From: Alexander Graf <agraf@suse.de>
Date: Thu, 29 Jul 2010 14:48:05 +0200
Subject: KVM: PPC: PV mtmsrd L=0 and mtmsr

There is also a form of mtmsr where all bits need to be addressed. While the
PPC64 Linux kernel behaves resonably well here, on PPC32 we do not have an
L=1 form. It does mtmsr even for simple things like only changing EE.

So we need to hook into that one as well and check for a mask of bits that we
deem safe to change from within guest context.

Signed-off-by: Alexander Graf <agraf@suse.de>
Signed-off-by: Avi Kivity <avi@redhat.com>
---
 arch/powerpc/kernel/kvm.c      | 51 +++++++++++++++++++++++++
 arch/powerpc/kernel/kvm_emul.S | 84 ++++++++++++++++++++++++++++++++++++++++++
 2 files changed, 135 insertions(+)

(limited to 'arch/powerpc/kernel')

diff --git a/arch/powerpc/kernel/kvm.c b/arch/powerpc/kernel/kvm.c
index 717ab0dded25..8ac57e2c52fa 100644
--- a/arch/powerpc/kernel/kvm.c
+++ b/arch/powerpc/kernel/kvm.c
@@ -63,7 +63,9 @@
 #define KVM_INST_MTSPR_DSISR	0x7c1203a6
 
 #define KVM_INST_TLBSYNC	0x7c00046c
+#define KVM_INST_MTMSRD_L0	0x7c000164
 #define KVM_INST_MTMSRD_L1	0x7c010164
+#define KVM_INST_MTMSR		0x7c000124
 
 static bool kvm_patching_worked = true;
 static char kvm_tmp[1024 * 1024];
@@ -176,6 +178,49 @@ static void kvm_patch_ins_mtmsrd(u32 *inst, u32 rt)
 	kvm_patch_ins_b(inst, distance_start);
 }
 
+extern u32 kvm_emulate_mtmsr_branch_offs;
+extern u32 kvm_emulate_mtmsr_reg1_offs;
+extern u32 kvm_emulate_mtmsr_reg2_offs;
+extern u32 kvm_emulate_mtmsr_reg3_offs;
+extern u32 kvm_emulate_mtmsr_orig_ins_offs;
+extern u32 kvm_emulate_mtmsr_len;
+extern u32 kvm_emulate_mtmsr[];
+
+static void kvm_patch_ins_mtmsr(u32 *inst, u32 rt)
+{
+	u32 *p;
+	int distance_start;
+	int distance_end;
+	ulong next_inst;
+
+	p = kvm_alloc(kvm_emulate_mtmsr_len * 4);
+	if (!p)
+		return;
+
+	/* Find out where we are and put everything there */
+	distance_start = (ulong)p - (ulong)inst;
+	next_inst = ((ulong)inst + 4);
+	distance_end = next_inst - (ulong)&p[kvm_emulate_mtmsr_branch_offs];
+
+	/* Make sure we only write valid b instructions */
+	if (distance_start > KVM_INST_B_MAX) {
+		kvm_patching_worked = false;
+		return;
+	}
+
+	/* Modify the chunk to fit the invocation */
+	memcpy(p, kvm_emulate_mtmsr, kvm_emulate_mtmsr_len * 4);
+	p[kvm_emulate_mtmsr_branch_offs] |= distance_end & KVM_INST_B_MASK;
+	p[kvm_emulate_mtmsr_reg1_offs] |= rt;
+	p[kvm_emulate_mtmsr_reg2_offs] |= rt;
+	p[kvm_emulate_mtmsr_reg3_offs] |= rt;
+	p[kvm_emulate_mtmsr_orig_ins_offs] = *inst;
+	flush_icache_range((ulong)p, (ulong)p + kvm_emulate_mtmsr_len * 4);
+
+	/* Patch the invocation */
+	kvm_patch_ins_b(inst, distance_start);
+}
+
 static void kvm_map_magic_page(void *data)
 {
 	kvm_hypercall2(KVM_HC_PPC_MAP_MAGIC_PAGE,
@@ -256,6 +301,12 @@ static void kvm_check_ins(u32 *inst)
 		if (get_rt(inst_rt) < 30)
 			kvm_patch_ins_mtmsrd(inst, inst_rt);
 		break;
+	case KVM_INST_MTMSR:
+	case KVM_INST_MTMSRD_L0:
+		/* We use r30 and r31 during the hook */
+		if (get_rt(inst_rt) < 30)
+			kvm_patch_ins_mtmsr(inst, inst_rt);
+		break;
 	}
 
 	switch (_inst) {
diff --git a/arch/powerpc/kernel/kvm_emul.S b/arch/powerpc/kernel/kvm_emul.S
index 10dc4a6632fd..8cd22f47dd01 100644
--- a/arch/powerpc/kernel/kvm_emul.S
+++ b/arch/powerpc/kernel/kvm_emul.S
@@ -120,3 +120,87 @@ kvm_emulate_mtmsrd_reg_offs:
 .global kvm_emulate_mtmsrd_len
 kvm_emulate_mtmsrd_len:
 	.long (kvm_emulate_mtmsrd_end - kvm_emulate_mtmsrd) / 4
+
+
+#define MSR_SAFE_BITS (MSR_EE | MSR_CE | MSR_ME | MSR_RI)
+#define MSR_CRITICAL_BITS ~MSR_SAFE_BITS
+
+.global kvm_emulate_mtmsr
+kvm_emulate_mtmsr:
+
+	SCRATCH_SAVE
+
+	/* Fetch old MSR in r31 */
+	LL64(r31, KVM_MAGIC_PAGE + KVM_MAGIC_MSR, 0)
+
+	/* Find the changed bits between old and new MSR */
+kvm_emulate_mtmsr_reg1:
+	xor	r31, r0, r31
+
+	/* Check if we need to really do mtmsr */
+	LOAD_REG_IMMEDIATE(r30, MSR_CRITICAL_BITS)
+	and.	r31, r31, r30
+
+	/* No critical bits changed? Maybe we can stay in the guest. */
+	beq	maybe_stay_in_guest
+
+do_mtmsr:
+
+	SCRATCH_RESTORE
+
+	/* Just fire off the mtmsr if it's critical */
+kvm_emulate_mtmsr_orig_ins:
+	mtmsr	r0
+
+	b	kvm_emulate_mtmsr_branch
+
+maybe_stay_in_guest:
+
+	/* Check if we have to fetch an interrupt */
+	lwz	r31, (KVM_MAGIC_PAGE + KVM_MAGIC_INT)(0)
+	cmpwi	r31, 0
+	beq+	no_mtmsr
+
+	/* Check if we may trigger an interrupt */
+kvm_emulate_mtmsr_reg2:
+	andi.	r31, r0, MSR_EE
+	beq	no_mtmsr
+
+	b	do_mtmsr
+
+no_mtmsr:
+
+	/* Put MSR into magic page because we don't call mtmsr */
+kvm_emulate_mtmsr_reg3:
+	STL64(r0, KVM_MAGIC_PAGE + KVM_MAGIC_MSR, 0)
+
+	SCRATCH_RESTORE
+
+	/* Go back to caller */
+kvm_emulate_mtmsr_branch:
+	b	.
+kvm_emulate_mtmsr_end:
+
+.global kvm_emulate_mtmsr_branch_offs
+kvm_emulate_mtmsr_branch_offs:
+	.long (kvm_emulate_mtmsr_branch - kvm_emulate_mtmsr) / 4
+
+.global kvm_emulate_mtmsr_reg1_offs
+kvm_emulate_mtmsr_reg1_offs:
+	.long (kvm_emulate_mtmsr_reg1 - kvm_emulate_mtmsr) / 4
+
+.global kvm_emulate_mtmsr_reg2_offs
+kvm_emulate_mtmsr_reg2_offs:
+	.long (kvm_emulate_mtmsr_reg2 - kvm_emulate_mtmsr) / 4
+
+.global kvm_emulate_mtmsr_reg3_offs
+kvm_emulate_mtmsr_reg3_offs:
+	.long (kvm_emulate_mtmsr_reg3 - kvm_emulate_mtmsr) / 4
+
+.global kvm_emulate_mtmsr_orig_ins_offs
+kvm_emulate_mtmsr_orig_ins_offs:
+	.long (kvm_emulate_mtmsr_orig_ins - kvm_emulate_mtmsr) / 4
+
+.global kvm_emulate_mtmsr_len
+kvm_emulate_mtmsr_len:
+	.long (kvm_emulate_mtmsr_end - kvm_emulate_mtmsr) / 4
-- 
cgit v1.2.1


From 644bfa013fd589b0df2470a66bcd104318ef24cd Mon Sep 17 00:00:00 2001
From: Alexander Graf <agraf@suse.de>
Date: Thu, 29 Jul 2010 14:48:06 +0200
Subject: KVM: PPC: PV wrteei

On BookE the preferred way to write the EE bit is the wrteei instruction. It
already encodes the EE bit in the instruction.

So in order to get BookE some speedups as well, let's also PV'nize thati
instruction.

Signed-off-by: Alexander Graf <agraf@suse.de>
Signed-off-by: Avi Kivity <avi@redhat.com>
---
 arch/powerpc/kernel/kvm.c      | 50 ++++++++++++++++++++++++++++++++++++++++++
 arch/powerpc/kernel/kvm_emul.S | 41 ++++++++++++++++++++++++++++++++++
 2 files changed, 91 insertions(+)

(limited to 'arch/powerpc/kernel')

diff --git a/arch/powerpc/kernel/kvm.c b/arch/powerpc/kernel/kvm.c
index 8ac57e2c52fa..e93681753deb 100644
--- a/arch/powerpc/kernel/kvm.c
+++ b/arch/powerpc/kernel/kvm.c
@@ -67,6 +67,9 @@
 #define KVM_INST_MTMSRD_L1	0x7c010164
 #define KVM_INST_MTMSR		0x7c000124
 
+#define KVM_INST_WRTEEI_0	0x7c000146
+#define KVM_INST_WRTEEI_1	0x7c008146
+
 static bool kvm_patching_worked = true;
 static char kvm_tmp[1024 * 1024];
 static int kvm_tmp_index;
@@ -221,6 +224,47 @@ static void kvm_patch_ins_mtmsr(u32 *inst, u32 rt)
 	kvm_patch_ins_b(inst, distance_start);
 }
 
+#ifdef CONFIG_BOOKE
+
+extern u32 kvm_emulate_wrteei_branch_offs;
+extern u32 kvm_emulate_wrteei_ee_offs;
+extern u32 kvm_emulate_wrteei_len;
+extern u32 kvm_emulate_wrteei[];
+
+static void kvm_patch_ins_wrteei(u32 *inst)
+{
+	u32 *p;
+	int distance_start;
+	int distance_end;
+	ulong next_inst;
+
+	p = kvm_alloc(kvm_emulate_wrteei_len * 4);
+	if (!p)
+		return;
+
+	/* Find out where we are and put everything there */
+	distance_start = (ulong)p - (ulong)inst;
+	next_inst = ((ulong)inst + 4);
+	distance_end = next_inst - (ulong)&p[kvm_emulate_wrteei_branch_offs];
+
+	/* Make sure we only write valid b instructions */
+	if (distance_start > KVM_INST_B_MAX) {
+		kvm_patching_worked = false;
+		return;
+	}
+
+	/* Modify the chunk to fit the invocation */
+	memcpy(p, kvm_emulate_wrteei, kvm_emulate_wrteei_len * 4);
+	p[kvm_emulate_wrteei_branch_offs] |= distance_end & KVM_INST_B_MASK;
+	p[kvm_emulate_wrteei_ee_offs] |= (*inst & MSR_EE);
+	flush_icache_range((ulong)p, (ulong)p + kvm_emulate_wrteei_len * 4);
+
+	/* Patch the invocation */
+	kvm_patch_ins_b(inst, distance_start);
+}
+
+#endif
+
 static void kvm_map_magic_page(void *data)
 {
 	kvm_hypercall2(KVM_HC_PPC_MAP_MAGIC_PAGE,
@@ -310,6 +354,12 @@ static void kvm_check_ins(u32 *inst)
 	}
 
 	switch (_inst) {
+#ifdef CONFIG_BOOKE
+	case KVM_INST_WRTEEI_0:
+	case KVM_INST_WRTEEI_1:
+		kvm_patch_ins_wrteei(inst);
+		break;
+#endif
 	}
 }
 
diff --git a/arch/powerpc/kernel/kvm_emul.S b/arch/powerpc/kernel/kvm_emul.S
index 8cd22f47dd01..3199f65ede2c 100644
--- a/arch/powerpc/kernel/kvm_emul.S
+++ b/arch/powerpc/kernel/kvm_emul.S
@@ -204,3 +204,44 @@ kvm_emulate_mtmsr_orig_ins_offs:
 .global kvm_emulate_mtmsr_len
 kvm_emulate_mtmsr_len:
 	.long (kvm_emulate_mtmsr_end - kvm_emulate_mtmsr) / 4
+
+
+
+.global kvm_emulate_wrteei
+kvm_emulate_wrteei:
+
+	SCRATCH_SAVE
+
+	/* Fetch old MSR in r31 */
+	LL64(r31, KVM_MAGIC_PAGE + KVM_MAGIC_MSR, 0)
+
+	/* Remove MSR_EE from old MSR */
+	li	r30, 0
+	ori	r30, r30, MSR_EE
+	andc	r31, r31, r30
+
+	/* OR new MSR_EE onto the old MSR */
+kvm_emulate_wrteei_ee:
+	ori	r31, r31, 0
+
+	/* Write new MSR value back */
+	STL64(r31, KVM_MAGIC_PAGE + KVM_MAGIC_MSR, 0)
+
+	SCRATCH_RESTORE
+
+	/* Go back to caller */
+kvm_emulate_wrteei_branch:
+	b	.
+kvm_emulate_wrteei_end:
+
+.global kvm_emulate_wrteei_branch_offs
+kvm_emulate_wrteei_branch_offs:
+	.long (kvm_emulate_wrteei_branch - kvm_emulate_wrteei) / 4
+
+.global kvm_emulate_wrteei_ee_offs
+kvm_emulate_wrteei_ee_offs:
+	.long (kvm_emulate_wrteei_ee - kvm_emulate_wrteei) / 4
+
+.global kvm_emulate_wrteei_len
+kvm_emulate_wrteei_len:
+	.long (kvm_emulate_wrteei_end - kvm_emulate_wrteei) / 4
-- 
cgit v1.2.1


From a58ddea556f8877ccf7caa046b6d6b32982f5b1d Mon Sep 17 00:00:00 2001
From: Alexander Graf <agraf@suse.de>
Date: Thu, 29 Jul 2010 15:04:22 +0200
Subject: KVM: PPC: Move KVM trampolines before __end_interrupts

When using a relocatable kernel we need to make sure that the trampline code
and the interrupt handlers are both copied to low memory. The only way to do
this reliably is to put them in the copied section.

This patch should make relocated kernels work with KVM.

KVM-Stable-Tag
Signed-off-by: Alexander Graf <agraf@suse.de>
Signed-off-by: Avi Kivity <avi@redhat.com>
---
 arch/powerpc/kernel/exceptions-64s.S | 6 ++++++
 arch/powerpc/kernel/head_64.S        | 6 ------
 2 files changed, 6 insertions(+), 6 deletions(-)

(limited to 'arch/powerpc/kernel')

diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S
index f53029a01554..1667a078b3e6 100644
--- a/arch/powerpc/kernel/exceptions-64s.S
+++ b/arch/powerpc/kernel/exceptions-64s.S
@@ -299,6 +299,12 @@ slb_miss_user_pseries:
 	b	.				/* prevent spec. execution */
 #endif /* __DISABLED__ */
 
+/* KVM's trampoline code needs to be close to the interrupt handlers */
+
+#ifdef CONFIG_KVM_BOOK3S_64_HANDLER
+#include "../kvm/book3s_rmhandlers.S"
+#endif
+
 	.align	7
 	.globl	__end_interrupts
 __end_interrupts:
diff --git a/arch/powerpc/kernel/head_64.S b/arch/powerpc/kernel/head_64.S
index c571cd3c1453..f0dd577e4a5b 100644
--- a/arch/powerpc/kernel/head_64.S
+++ b/arch/powerpc/kernel/head_64.S
@@ -166,12 +166,6 @@ exception_marker:
 #include "exceptions-64s.S"
 #endif
 
-/* KVM trampoline code needs to be close to the interrupt handlers */
-
-#ifdef CONFIG_KVM_BOOK3S_64_HANDLER
-#include "../kvm/book3s_rmhandlers.S"
-#endif
-
 _GLOBAL(generic_secondary_thread_init)
 	mr	r24,r3
 
-- 
cgit v1.2.1


From 989044ee0fdc6c22a11ea1d22e2a3d17463cb564 Mon Sep 17 00:00:00 2001
From: Alexander Graf <agraf@suse.de>
Date: Mon, 30 Aug 2010 12:01:56 +0200
Subject: KVM: PPC: Fix CONFIG_KVM_GUEST && !CONFIG_KVM case

When CONFIG_KVM_GUEST is selected, but CONFIG_KVM is not, we were missing
some defines in asm-offsets.c and included too many headers at other places.

This patch makes above configuration work.

Reported-by: Stephen Rothwell <sfr@canb.auug.org.au>
Signed-off-by: Alexander Graf <agraf@suse.de>
Signed-off-by: Avi Kivity <avi@redhat.com>
---
 arch/powerpc/kernel/asm-offsets.c | 6 +++---
 arch/powerpc/kernel/kvm.c         | 1 -
 2 files changed, 3 insertions(+), 4 deletions(-)

(limited to 'arch/powerpc/kernel')

diff --git a/arch/powerpc/kernel/asm-offsets.c b/arch/powerpc/kernel/asm-offsets.c
index 37486cafb69d..6d92b4e13ebf 100644
--- a/arch/powerpc/kernel/asm-offsets.c
+++ b/arch/powerpc/kernel/asm-offsets.c
@@ -48,11 +48,11 @@
 #ifdef CONFIG_PPC_ISERIES
 #include <asm/iseries/alpaca.h>
 #endif
-#ifdef CONFIG_KVM
+#if defined(CONFIG_KVM) || defined(CONFIG_KVM_GUEST)
 #include <linux/kvm_host.h>
-#ifndef CONFIG_BOOKE
-#include <asm/kvm_book3s.h>
 #endif
+#if defined(CONFIG_KVM) && defined(CONFIG_PPC_BOOK3S)
+#include <asm/kvm_book3s.h>
 #endif
 
 #ifdef CONFIG_PPC32
diff --git a/arch/powerpc/kernel/kvm.c b/arch/powerpc/kernel/kvm.c
index e93681753deb..d3a2cc50d611 100644
--- a/arch/powerpc/kernel/kvm.c
+++ b/arch/powerpc/kernel/kvm.c
@@ -25,7 +25,6 @@
 #include <linux/of.h>
 
 #include <asm/reg.h>
-#include <asm/kvm_ppc.h>
 #include <asm/sections.h>
 #include <asm/cacheflush.h>
 #include <asm/disassemble.h>
-- 
cgit v1.2.1


From 7508e16c9f2a20f7721d7bc47c33a7b34c873a2c Mon Sep 17 00:00:00 2001
From: Alexander Graf <agraf@suse.de>
Date: Tue, 3 Aug 2010 11:32:56 +0200
Subject: KVM: PPC: Add feature bitmap for magic page

We will soon add SR PV support to the shared page, so we need some
infrastructure that allows the guest to query for features KVM exports.

This patch adds a second return value to the magic mapping that
indicated to the guest which features are available.

Signed-off-by: Alexander Graf <agraf@suse.de>
---
 arch/powerpc/kernel/kvm.c | 21 +++++++++++++++------
 1 file changed, 15 insertions(+), 6 deletions(-)

(limited to 'arch/powerpc/kernel')

diff --git a/arch/powerpc/kernel/kvm.c b/arch/powerpc/kernel/kvm.c
index d3a2cc50d611..226882fe85a6 100644
--- a/arch/powerpc/kernel/kvm.c
+++ b/arch/powerpc/kernel/kvm.c
@@ -266,12 +266,20 @@ static void kvm_patch_ins_wrteei(u32 *inst)
 
 static void kvm_map_magic_page(void *data)
 {
-	kvm_hypercall2(KVM_HC_PPC_MAP_MAGIC_PAGE,
-		       KVM_MAGIC_PAGE,  /* Physical Address */
-		       KVM_MAGIC_PAGE); /* Effective Address */
+	u32 *features = data;
+
+	ulong in[8];
+	ulong out[8];
+
+	in[0] = KVM_MAGIC_PAGE;
+	in[1] = KVM_MAGIC_PAGE;
+
+	kvm_hypercall(in, out, HC_VENDOR_KVM | KVM_HC_PPC_MAP_MAGIC_PAGE);
+
+	*features = out[0];
 }
 
-static void kvm_check_ins(u32 *inst)
+static void kvm_check_ins(u32 *inst, u32 features)
 {
 	u32 _inst = *inst;
 	u32 inst_no_rt = _inst & ~KVM_MASK_RT;
@@ -367,9 +375,10 @@ static void kvm_use_magic_page(void)
 	u32 *p;
 	u32 *start, *end;
 	u32 tmp;
+	u32 features;
 
 	/* Tell the host to map the magic page to -4096 on all CPUs */
-	on_each_cpu(kvm_map_magic_page, NULL, 1);
+	on_each_cpu(kvm_map_magic_page, &features, 1);
 
 	/* Quick self-test to see if the mapping works */
 	if (__get_user(tmp, (u32*)KVM_MAGIC_PAGE)) {
@@ -382,7 +391,7 @@ static void kvm_use_magic_page(void)
 	end = (void*)_etext;
 
 	for (p = start; p < end; p++)
-		kvm_check_ins(p);
+		kvm_check_ins(p, features);
 
 	printk(KERN_INFO "KVM: Live patching for a fast VM %s\n",
 			 kvm_patching_worked ? "worked" : "failed");
-- 
cgit v1.2.1


From cbe487fac7fc016dbabbcbe83f11384e1803a56d Mon Sep 17 00:00:00 2001
From: Alexander Graf <agraf@suse.de>
Date: Tue, 3 Aug 2010 10:39:35 +0200
Subject: KVM: PPC: Add mtsrin PV code

This is the guest side of the mtsr acceleration. Using this a guest can now
call mtsrin with almost no overhead as long as it ensures that it only uses
it with (MSR_IR|MSR_DR) == 0. Linux does that, so we're good.

Signed-off-by: Alexander Graf <agraf@suse.de>
---
 arch/powerpc/kernel/asm-offsets.c |  1 +
 arch/powerpc/kernel/kvm.c         | 60 +++++++++++++++++++++++++++++++++++++++
 arch/powerpc/kernel/kvm_emul.S    | 50 ++++++++++++++++++++++++++++++++
 3 files changed, 111 insertions(+)

(limited to 'arch/powerpc/kernel')

diff --git a/arch/powerpc/kernel/asm-offsets.c b/arch/powerpc/kernel/asm-offsets.c
index 6d92b4e13ebf..7f0d6fcc28a3 100644
--- a/arch/powerpc/kernel/asm-offsets.c
+++ b/arch/powerpc/kernel/asm-offsets.c
@@ -478,6 +478,7 @@ int main(void)
 	DEFINE(KVM_MAGIC_MSR, offsetof(struct kvm_vcpu_arch_shared, msr));
 	DEFINE(KVM_MAGIC_CRITICAL, offsetof(struct kvm_vcpu_arch_shared,
 					    critical));
+	DEFINE(KVM_MAGIC_SR, offsetof(struct kvm_vcpu_arch_shared, sr));
 #endif
 
 #ifdef CONFIG_44x
diff --git a/arch/powerpc/kernel/kvm.c b/arch/powerpc/kernel/kvm.c
index 226882fe85a6..c8bab24ff8ac 100644
--- a/arch/powerpc/kernel/kvm.c
+++ b/arch/powerpc/kernel/kvm.c
@@ -42,6 +42,7 @@
 #define KVM_INST_B_MAX		0x01ffffff
 
 #define KVM_MASK_RT		0x03e00000
+#define KVM_MASK_RB		0x0000f800
 #define KVM_INST_MFMSR		0x7c0000a6
 #define KVM_INST_MFSPR_SPRG0	0x7c1042a6
 #define KVM_INST_MFSPR_SPRG1	0x7c1142a6
@@ -69,6 +70,8 @@
 #define KVM_INST_WRTEEI_0	0x7c000146
 #define KVM_INST_WRTEEI_1	0x7c008146
 
+#define KVM_INST_MTSRIN		0x7c0001e4
+
 static bool kvm_patching_worked = true;
 static char kvm_tmp[1024 * 1024];
 static int kvm_tmp_index;
@@ -264,6 +267,51 @@ static void kvm_patch_ins_wrteei(u32 *inst)
 
 #endif
 
+#ifdef CONFIG_PPC_BOOK3S_32
+
+extern u32 kvm_emulate_mtsrin_branch_offs;
+extern u32 kvm_emulate_mtsrin_reg1_offs;
+extern u32 kvm_emulate_mtsrin_reg2_offs;
+extern u32 kvm_emulate_mtsrin_orig_ins_offs;
+extern u32 kvm_emulate_mtsrin_len;
+extern u32 kvm_emulate_mtsrin[];
+
+static void kvm_patch_ins_mtsrin(u32 *inst, u32 rt, u32 rb)
+{
+	u32 *p;
+	int distance_start;
+	int distance_end;
+	ulong next_inst;
+
+	p = kvm_alloc(kvm_emulate_mtsrin_len * 4);
+	if (!p)
+		return;
+
+	/* Find out where we are and put everything there */
+	distance_start = (ulong)p - (ulong)inst;
+	next_inst = ((ulong)inst + 4);
+	distance_end = next_inst - (ulong)&p[kvm_emulate_mtsrin_branch_offs];
+
+	/* Make sure we only write valid b instructions */
+	if (distance_start > KVM_INST_B_MAX) {
+		kvm_patching_worked = false;
+		return;
+	}
+
+	/* Modify the chunk to fit the invocation */
+	memcpy(p, kvm_emulate_mtsrin, kvm_emulate_mtsrin_len * 4);
+	p[kvm_emulate_mtsrin_branch_offs] |= distance_end & KVM_INST_B_MASK;
+	p[kvm_emulate_mtsrin_reg1_offs] |= (rb << 10);
+	p[kvm_emulate_mtsrin_reg2_offs] |= rt;
+	p[kvm_emulate_mtsrin_orig_ins_offs] = *inst;
+	flush_icache_range((ulong)p, (ulong)p + kvm_emulate_mtsrin_len * 4);
+
+	/* Patch the invocation */
+	kvm_patch_ins_b(inst, distance_start);
+}
+
+#endif
+
 static void kvm_map_magic_page(void *data)
 {
 	u32 *features = data;
@@ -360,6 +408,18 @@ static void kvm_check_ins(u32 *inst, u32 features)
 		break;
 	}
 
+	switch (inst_no_rt & ~KVM_MASK_RB) {
+#ifdef CONFIG_PPC_BOOK3S_32
+	case KVM_INST_MTSRIN:
+		if (features & KVM_MAGIC_FEAT_SR) {
+			u32 inst_rb = _inst & KVM_MASK_RB;
+			kvm_patch_ins_mtsrin(inst, inst_rt, inst_rb);
+		}
+		break;
+		break;
+#endif
+	}
+
 	switch (_inst) {
 #ifdef CONFIG_BOOKE
 	case KVM_INST_WRTEEI_0:
diff --git a/arch/powerpc/kernel/kvm_emul.S b/arch/powerpc/kernel/kvm_emul.S
index 3199f65ede2c..a6e97e7a55e0 100644
--- a/arch/powerpc/kernel/kvm_emul.S
+++ b/arch/powerpc/kernel/kvm_emul.S
@@ -245,3 +245,53 @@ kvm_emulate_wrteei_ee_offs:
 .global kvm_emulate_wrteei_len
 kvm_emulate_wrteei_len:
 	.long (kvm_emulate_wrteei_end - kvm_emulate_wrteei) / 4
+
+
+.global kvm_emulate_mtsrin
+kvm_emulate_mtsrin:
+
+	SCRATCH_SAVE
+
+	LL64(r31, KVM_MAGIC_PAGE + KVM_MAGIC_MSR, 0)
+	andi.	r31, r31, MSR_DR | MSR_IR
+	beq	kvm_emulate_mtsrin_reg1
+
+	SCRATCH_RESTORE
+
+kvm_emulate_mtsrin_orig_ins:
+	nop
+	b	kvm_emulate_mtsrin_branch
+
+kvm_emulate_mtsrin_reg1:
+	/* rX >> 26 */
+	rlwinm  r30,r0,6,26,29
+
+kvm_emulate_mtsrin_reg2:
+	stw	r0, (KVM_MAGIC_PAGE + KVM_MAGIC_SR)(r30)
+
+	SCRATCH_RESTORE
+
+	/* Go back to caller */
+kvm_emulate_mtsrin_branch:
+	b	.
+kvm_emulate_mtsrin_end:
+
+.global kvm_emulate_mtsrin_branch_offs
+kvm_emulate_mtsrin_branch_offs:
+	.long (kvm_emulate_mtsrin_branch - kvm_emulate_mtsrin) / 4
+
+.global kvm_emulate_mtsrin_reg1_offs
+kvm_emulate_mtsrin_reg1_offs:
+	.long (kvm_emulate_mtsrin_reg1 - kvm_emulate_mtsrin) / 4
+
+.global kvm_emulate_mtsrin_reg2_offs
+kvm_emulate_mtsrin_reg2_offs:
+	.long (kvm_emulate_mtsrin_reg2 - kvm_emulate_mtsrin) / 4
+
+.global kvm_emulate_mtsrin_orig_ins_offs
+kvm_emulate_mtsrin_orig_ins_offs:
+	.long (kvm_emulate_mtsrin_orig_ins - kvm_emulate_mtsrin) / 4
+
+.global kvm_emulate_mtsrin_len
+kvm_emulate_mtsrin_len:
+	.long (kvm_emulate_mtsrin_end - kvm_emulate_mtsrin) / 4
-- 
cgit v1.2.1


From 512ba59ed9c580b5e5575beda0041bb19a641127 Mon Sep 17 00:00:00 2001
From: Alexander Graf <agraf@suse.de>
Date: Thu, 5 Aug 2010 11:26:04 +0200
Subject: KVM: PPC: Make PV mtmsr work with r30 and r31

So far we've been restricting ourselves to r0-r29 as registers an mtmsr
instruction could use. This was bad, as there are some code paths in
Linux actually using r30.

So let's instead handle all registers gracefully and get rid of that
stupid limitation

Signed-off-by: Alexander Graf <agraf@suse.de>
---
 arch/powerpc/kernel/kvm.c      | 39 ++++++++++++++++++++++++++++++++-------
 arch/powerpc/kernel/kvm_emul.S | 17 ++++++++---------
 2 files changed, 40 insertions(+), 16 deletions(-)

(limited to 'arch/powerpc/kernel')

diff --git a/arch/powerpc/kernel/kvm.c b/arch/powerpc/kernel/kvm.c
index c8bab24ff8ac..10b681c092ed 100644
--- a/arch/powerpc/kernel/kvm.c
+++ b/arch/powerpc/kernel/kvm.c
@@ -42,6 +42,7 @@
 #define KVM_INST_B_MAX		0x01ffffff
 
 #define KVM_MASK_RT		0x03e00000
+#define KVM_RT_30		0x03c00000
 #define KVM_MASK_RB		0x0000f800
 #define KVM_INST_MFMSR		0x7c0000a6
 #define KVM_INST_MFSPR_SPRG0	0x7c1042a6
@@ -82,6 +83,15 @@ static inline void kvm_patch_ins(u32 *inst, u32 new_inst)
 	flush_icache_range((ulong)inst, (ulong)inst + 4);
 }
 
+static void kvm_patch_ins_ll(u32 *inst, long addr, u32 rt)
+{
+#ifdef CONFIG_64BIT
+	kvm_patch_ins(inst, KVM_INST_LD | rt | (addr & 0x0000fffc));
+#else
+	kvm_patch_ins(inst, KVM_INST_LWZ | rt | (addr & 0x0000fffc));
+#endif
+}
+
 static void kvm_patch_ins_ld(u32 *inst, long addr, u32 rt)
 {
 #ifdef CONFIG_64BIT
@@ -186,7 +196,6 @@ static void kvm_patch_ins_mtmsrd(u32 *inst, u32 rt)
 extern u32 kvm_emulate_mtmsr_branch_offs;
 extern u32 kvm_emulate_mtmsr_reg1_offs;
 extern u32 kvm_emulate_mtmsr_reg2_offs;
-extern u32 kvm_emulate_mtmsr_reg3_offs;
 extern u32 kvm_emulate_mtmsr_orig_ins_offs;
 extern u32 kvm_emulate_mtmsr_len;
 extern u32 kvm_emulate_mtmsr[];
@@ -216,9 +225,27 @@ static void kvm_patch_ins_mtmsr(u32 *inst, u32 rt)
 	/* Modify the chunk to fit the invocation */
 	memcpy(p, kvm_emulate_mtmsr, kvm_emulate_mtmsr_len * 4);
 	p[kvm_emulate_mtmsr_branch_offs] |= distance_end & KVM_INST_B_MASK;
-	p[kvm_emulate_mtmsr_reg1_offs] |= rt;
-	p[kvm_emulate_mtmsr_reg2_offs] |= rt;
-	p[kvm_emulate_mtmsr_reg3_offs] |= rt;
+
+	/* Make clobbered registers work too */
+	switch (get_rt(rt)) {
+	case 30:
+		kvm_patch_ins_ll(&p[kvm_emulate_mtmsr_reg1_offs],
+				 magic_var(scratch2), KVM_RT_30);
+		kvm_patch_ins_ll(&p[kvm_emulate_mtmsr_reg2_offs],
+				 magic_var(scratch2), KVM_RT_30);
+		break;
+	case 31:
+		kvm_patch_ins_ll(&p[kvm_emulate_mtmsr_reg1_offs],
+				 magic_var(scratch1), KVM_RT_30);
+		kvm_patch_ins_ll(&p[kvm_emulate_mtmsr_reg2_offs],
+				 magic_var(scratch1), KVM_RT_30);
+		break;
+	default:
+		p[kvm_emulate_mtmsr_reg1_offs] |= rt;
+		p[kvm_emulate_mtmsr_reg2_offs] |= rt;
+		break;
+	}
+
 	p[kvm_emulate_mtmsr_orig_ins_offs] = *inst;
 	flush_icache_range((ulong)p, (ulong)p + kvm_emulate_mtmsr_len * 4);
 
@@ -402,9 +429,7 @@ static void kvm_check_ins(u32 *inst, u32 features)
 		break;
 	case KVM_INST_MTMSR:
 	case KVM_INST_MTMSRD_L0:
-		/* We use r30 and r31 during the hook */
-		if (get_rt(inst_rt) < 30)
-			kvm_patch_ins_mtmsr(inst, inst_rt);
+		kvm_patch_ins_mtmsr(inst, inst_rt);
 		break;
 	}
 
diff --git a/arch/powerpc/kernel/kvm_emul.S b/arch/powerpc/kernel/kvm_emul.S
index a6e97e7a55e0..65305325250b 100644
--- a/arch/powerpc/kernel/kvm_emul.S
+++ b/arch/powerpc/kernel/kvm_emul.S
@@ -135,7 +135,8 @@ kvm_emulate_mtmsr:
 
 	/* Find the changed bits between old and new MSR */
 kvm_emulate_mtmsr_reg1:
-	xor	r31, r0, r31
+	ori	r30, r0, 0
+	xor	r31, r30, r31
 
 	/* Check if we need to really do mtmsr */
 	LOAD_REG_IMMEDIATE(r30, MSR_CRITICAL_BITS)
@@ -156,14 +157,17 @@ kvm_emulate_mtmsr_orig_ins:
 
 maybe_stay_in_guest:
 
+	/* Get the target register in r30 */
+kvm_emulate_mtmsr_reg2:
+	ori	r30, r0, 0
+
 	/* Check if we have to fetch an interrupt */
 	lwz	r31, (KVM_MAGIC_PAGE + KVM_MAGIC_INT)(0)
 	cmpwi	r31, 0
 	beq+	no_mtmsr
 
 	/* Check if we may trigger an interrupt */
-kvm_emulate_mtmsr_reg2:
-	andi.	r31, r0, MSR_EE
+	andi.	r31, r30, MSR_EE
 	beq	no_mtmsr
 
 	b	do_mtmsr
@@ -171,8 +175,7 @@ kvm_emulate_mtmsr_reg2:
 no_mtmsr:
 
 	/* Put MSR into magic page because we don't call mtmsr */
-kvm_emulate_mtmsr_reg3:
-	STL64(r0, KVM_MAGIC_PAGE + KVM_MAGIC_MSR, 0)
+	STL64(r30, KVM_MAGIC_PAGE + KVM_MAGIC_MSR, 0)
 
 	SCRATCH_RESTORE
 
@@ -193,10 +196,6 @@ kvm_emulate_mtmsr_reg1_offs:
 kvm_emulate_mtmsr_reg2_offs:
 	.long (kvm_emulate_mtmsr_reg2 - kvm_emulate_mtmsr) / 4
 
-.global kvm_emulate_mtmsr_reg3_offs
-kvm_emulate_mtmsr_reg3_offs:
-	.long (kvm_emulate_mtmsr_reg3 - kvm_emulate_mtmsr) / 4
-
 .global kvm_emulate_mtmsr_orig_ins_offs
 kvm_emulate_mtmsr_orig_ins_offs:
 	.long (kvm_emulate_mtmsr_orig_ins - kvm_emulate_mtmsr) / 4
-- 
cgit v1.2.1


From df08bd10266ce6132278f6b4ddc4bb0a12330b56 Mon Sep 17 00:00:00 2001
From: Alexander Graf <agraf@suse.de>
Date: Thu, 5 Aug 2010 15:44:41 +0200
Subject: KVM: PPC: Make PV mtmsrd L=1 work with r30 and r31

We had an arbitrary limitation in mtmsrd L=1 that kept us from using r30 and
r31 as input registers. Let's get rid of that and get more potential speedups!

Signed-off-by: Alexander Graf <agraf@suse.de>
---
 arch/powerpc/kernel/kvm.c      | 21 +++++++++++++++++----
 arch/powerpc/kernel/kvm_emul.S |  8 +++++++-
 2 files changed, 24 insertions(+), 5 deletions(-)

(limited to 'arch/powerpc/kernel')

diff --git a/arch/powerpc/kernel/kvm.c b/arch/powerpc/kernel/kvm.c
index 10b681c092ed..48a033865410 100644
--- a/arch/powerpc/kernel/kvm.c
+++ b/arch/powerpc/kernel/kvm.c
@@ -158,6 +158,7 @@ static u32 *kvm_alloc(int len)
 
 extern u32 kvm_emulate_mtmsrd_branch_offs;
 extern u32 kvm_emulate_mtmsrd_reg_offs;
+extern u32 kvm_emulate_mtmsrd_orig_ins_offs;
 extern u32 kvm_emulate_mtmsrd_len;
 extern u32 kvm_emulate_mtmsrd[];
 
@@ -186,7 +187,21 @@ static void kvm_patch_ins_mtmsrd(u32 *inst, u32 rt)
 	/* Modify the chunk to fit the invocation */
 	memcpy(p, kvm_emulate_mtmsrd, kvm_emulate_mtmsrd_len * 4);
 	p[kvm_emulate_mtmsrd_branch_offs] |= distance_end & KVM_INST_B_MASK;
-	p[kvm_emulate_mtmsrd_reg_offs] |= rt;
+	switch (get_rt(rt)) {
+	case 30:
+		kvm_patch_ins_ll(&p[kvm_emulate_mtmsrd_reg_offs],
+				 magic_var(scratch2), KVM_RT_30);
+		break;
+	case 31:
+		kvm_patch_ins_ll(&p[kvm_emulate_mtmsrd_reg_offs],
+				 magic_var(scratch1), KVM_RT_30);
+		break;
+	default:
+		p[kvm_emulate_mtmsrd_reg_offs] |= rt;
+		break;
+	}
+
+	p[kvm_emulate_mtmsrd_orig_ins_offs] = *inst;
 	flush_icache_range((ulong)p, (ulong)p + kvm_emulate_mtmsrd_len * 4);
 
 	/* Patch the invocation */
@@ -423,9 +438,7 @@ static void kvm_check_ins(u32 *inst, u32 features)
 
 	/* Rewrites */
 	case KVM_INST_MTMSRD_L1:
-		/* We use r30 and r31 during the hook */
-		if (get_rt(inst_rt) < 30)
-			kvm_patch_ins_mtmsrd(inst, inst_rt);
+		kvm_patch_ins_mtmsrd(inst, inst_rt);
 		break;
 	case KVM_INST_MTMSR:
 	case KVM_INST_MTMSRD_L0:
diff --git a/arch/powerpc/kernel/kvm_emul.S b/arch/powerpc/kernel/kvm_emul.S
index 65305325250b..f2b1b2523e61 100644
--- a/arch/powerpc/kernel/kvm_emul.S
+++ b/arch/powerpc/kernel/kvm_emul.S
@@ -78,7 +78,8 @@ kvm_emulate_mtmsrd:
 
 	/* OR the register's (MSR_EE|MSR_RI) on MSR */
 kvm_emulate_mtmsrd_reg:
-	andi.	r30, r0, (MSR_EE|MSR_RI)
+	ori	r30, r0, 0
+	andi.	r30, r30, (MSR_EE|MSR_RI)
 	or	r31, r31, r30
 
 	/* Put MSR back into magic page */
@@ -96,6 +97,7 @@ kvm_emulate_mtmsrd_reg:
 	SCRATCH_RESTORE
 
 	/* Nag hypervisor */
+kvm_emulate_mtmsrd_orig_ins:
 	tlbsync
 
 	b	kvm_emulate_mtmsrd_branch
@@ -117,6 +119,10 @@ kvm_emulate_mtmsrd_branch_offs:
 kvm_emulate_mtmsrd_reg_offs:
 	.long (kvm_emulate_mtmsrd_reg - kvm_emulate_mtmsrd) / 4
 
+.global kvm_emulate_mtmsrd_orig_ins_offs
+kvm_emulate_mtmsrd_orig_ins_offs:
+	.long (kvm_emulate_mtmsrd_orig_ins - kvm_emulate_mtmsrd) / 4
+
 .global kvm_emulate_mtmsrd_len
 kvm_emulate_mtmsrd_len:
 	.long (kvm_emulate_mtmsrd_end - kvm_emulate_mtmsrd) / 4
-- 
cgit v1.2.1


From ad0873763a83e7b31ba87a85ec2027dd6a9d7b55 Mon Sep 17 00:00:00 2001
From: Alexander Graf <agraf@suse.de>
Date: Tue, 17 Aug 2010 11:41:44 +0200
Subject: KVM: PPC: Force enable nap on KVM

There are some heuristics in the PPC power management code that try to find
out if the particular hardware we're running on supports proper power management
or just hangs the machine when going into nap mode.

Since we know that KVM is safe with nap, let's force enable it in the PV code
once we're certain that we are on a KVM VM.

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

(limited to 'arch/powerpc/kernel')

diff --git a/arch/powerpc/kernel/kvm.c b/arch/powerpc/kernel/kvm.c
index 48a033865410..669d989be1d6 100644
--- a/arch/powerpc/kernel/kvm.c
+++ b/arch/powerpc/kernel/kvm.c
@@ -582,6 +582,9 @@ static int __init kvm_guest_init(void)
 	if (kvm_para_has_feature(KVM_FEATURE_MAGIC_PAGE))
 		kvm_use_magic_page();
 
+	/* Enable napping */
+	powersave_nap = 1;
+
 free_tmp:
 	kvm_free_tmp();
 
-- 
cgit v1.2.1


From 591bd8e7b4c8b9246d7a1c81ffbd28e35dc5de4e Mon Sep 17 00:00:00 2001
From: Alexander Graf <agraf@suse.de>
Date: Tue, 17 Aug 2010 22:08:39 +0200
Subject: KVM: PPC: Enable napping only for Book3s_64

Before I incorrectly enabled napping also for BookE, which would result in
needless dcache flushes. Since we only need to force enable napping on
Book3s_64 because it doesn't go into MSR_POW otherwise, we can just #ifdef
that code to this particular platform.

Reported-by: Scott Wood <scottwood@freescale.com>
Signed-off-by: Alexander Graf <agraf@suse.de>
---
 arch/powerpc/kernel/kvm.c | 2 ++
 1 file changed, 2 insertions(+)

(limited to 'arch/powerpc/kernel')

diff --git a/arch/powerpc/kernel/kvm.c b/arch/powerpc/kernel/kvm.c
index 669d989be1d6..428d0e538aec 100644
--- a/arch/powerpc/kernel/kvm.c
+++ b/arch/powerpc/kernel/kvm.c
@@ -582,8 +582,10 @@ static int __init kvm_guest_init(void)
 	if (kvm_para_has_feature(KVM_FEATURE_MAGIC_PAGE))
 		kvm_use_magic_page();
 
+#ifdef CONFIG_PPC_BOOK3S_64
 	/* Enable napping */
 	powersave_nap = 1;
+#endif
 
 free_tmp:
 	kvm_free_tmp();
-- 
cgit v1.2.1