From 14941789f2a13cd89e2dd567c4f708e571ab714e Mon Sep 17 00:00:00 2001
From: Paul Mackerras <paulus@samba.org>
Date: Fri, 6 Sep 2013 13:11:18 +1000
Subject: KVM: PPC: Book3S HV: Save/restore SIAR and SDAR along with other PMU
 registers

Currently we are not saving and restoring the SIAR and SDAR registers in
the PMU (performance monitor unit) on guest entry and exit.  The result
is that performance monitoring tools in the guest could get false
information about where a program was executing and what data it was
accessing at the time of a performance monitor interrupt.  This fixes
it by saving and restoring these registers along with the other PMU
registers on guest entry/exit.

This also provides a way for userspace to access these values for a
vcpu via the one_reg interface.

Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Alexander Graf <agraf@suse.de>
---
 arch/powerpc/kvm/book3s_hv.c            | 12 ++++++++++++
 arch/powerpc/kvm/book3s_hv_rmhandlers.S |  8 ++++++++
 2 files changed, 20 insertions(+)

(limited to 'arch/powerpc/kvm')

diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c
index 62a2b5ab08e..45a9b876b0a 100644
--- a/arch/powerpc/kvm/book3s_hv.c
+++ b/arch/powerpc/kvm/book3s_hv.c
@@ -749,6 +749,12 @@ int kvmppc_get_one_reg(struct kvm_vcpu *vcpu, u64 id, union kvmppc_one_reg *val)
 		i = id - KVM_REG_PPC_PMC1;
 		*val = get_reg_val(id, vcpu->arch.pmc[i]);
 		break;
+	case KVM_REG_PPC_SIAR:
+		*val = get_reg_val(id, vcpu->arch.siar);
+		break;
+	case KVM_REG_PPC_SDAR:
+		*val = get_reg_val(id, vcpu->arch.sdar);
+		break;
 #ifdef CONFIG_VSX
 	case KVM_REG_PPC_FPR0 ... KVM_REG_PPC_FPR31:
 		if (cpu_has_feature(CPU_FTR_VSX)) {
@@ -833,6 +839,12 @@ int kvmppc_set_one_reg(struct kvm_vcpu *vcpu, u64 id, union kvmppc_one_reg *val)
 		i = id - KVM_REG_PPC_PMC1;
 		vcpu->arch.pmc[i] = set_reg_val(id, *val);
 		break;
+	case KVM_REG_PPC_SIAR:
+		vcpu->arch.siar = set_reg_val(id, *val);
+		break;
+	case KVM_REG_PPC_SDAR:
+		vcpu->arch.sdar = set_reg_val(id, *val);
+		break;
 #ifdef CONFIG_VSX
 	case KVM_REG_PPC_FPR0 ... KVM_REG_PPC_FPR31:
 		if (cpu_has_feature(CPU_FTR_VSX)) {
diff --git a/arch/powerpc/kvm/book3s_hv_rmhandlers.S b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
index 294b7af28cd..541aea0ce91 100644
--- a/arch/powerpc/kvm/book3s_hv_rmhandlers.S
+++ b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
@@ -200,8 +200,12 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_201)
 	ld	r3, VCPU_MMCR(r4)
 	ld	r5, VCPU_MMCR + 8(r4)
 	ld	r6, VCPU_MMCR + 16(r4)
+	ld	r7, VCPU_SIAR(r4)
+	ld	r8, VCPU_SDAR(r4)
 	mtspr	SPRN_MMCR1, r5
 	mtspr	SPRN_MMCRA, r6
+	mtspr	SPRN_SIAR, r7
+	mtspr	SPRN_SDAR, r8
 	mtspr	SPRN_MMCR0, r3
 	isync
 
@@ -1134,9 +1138,13 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_206)
 	std	r3, VCPU_MMCR(r9)	/* if not, set saved MMCR0 to FC */
 	b	22f
 21:	mfspr	r5, SPRN_MMCR1
+	mfspr	r7, SPRN_SIAR
+	mfspr	r8, SPRN_SDAR
 	std	r4, VCPU_MMCR(r9)
 	std	r5, VCPU_MMCR + 8(r9)
 	std	r6, VCPU_MMCR + 16(r9)
+	std	r7, VCPU_SIAR(r9)
+	std	r8, VCPU_SDAR(r9)
 	mfspr	r3, SPRN_PMC1
 	mfspr	r4, SPRN_PMC2
 	mfspr	r5, SPRN_PMC3
-- 
cgit v1.2.3-70-g09d2


From 93b0f4dc29c5f077a1c97bd1d484147230c3779a Mon Sep 17 00:00:00 2001
From: Paul Mackerras <paulus@samba.org>
Date: Fri, 6 Sep 2013 13:17:46 +1000
Subject: KVM: PPC: Book3S HV: Implement timebase offset for guests

This allows guests to have a different timebase origin from the host.
This is needed for migration, where a guest can migrate from one host
to another and the two hosts might have a different timebase origin.
However, the timebase seen by the guest must not go backwards, and
should go forwards only by a small amount corresponding to the time
taken for the migration.

Therefore this provides a new per-vcpu value accessed via the one_reg
interface using the new KVM_REG_PPC_TB_OFFSET identifier.  This value
defaults to 0 and is not modified by KVM.  On entering the guest, this
value is added onto the timebase, and on exiting the guest, it is
subtracted from the timebase.

This is only supported for recent POWER hardware which has the TBU40
(timebase upper 40 bits) register.  Writing to the TBU40 register only
alters the upper 40 bits of the timebase, leaving the lower 24 bits
unchanged.  This provides a way to modify the timebase for guest
migration without disturbing the synchronization of the timebase
registers across CPU cores.  The kernel rounds up the value given
to a multiple of 2^24.

Timebase values stored in KVM structures (struct kvm_vcpu, struct
kvmppc_vcore, etc.) are stored as host timebase values.  The timebase
values in the dispatch trace log need to be guest timebase values,
however, since that is read directly by the guest.  This moves the
setting of vcpu->arch.dec_expires on guest exit to a point after we
have restored the host timebase so that vcpu->arch.dec_expires is a
host timebase value.

Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Alexander Graf <agraf@suse.de>
---
 Documentation/virtual/kvm/api.txt       |  1 +
 arch/powerpc/include/asm/kvm_host.h     |  1 +
 arch/powerpc/include/asm/reg.h          |  1 +
 arch/powerpc/include/uapi/asm/kvm.h     |  3 ++
 arch/powerpc/kernel/asm-offsets.c       |  1 +
 arch/powerpc/kvm/book3s_hv.c            | 10 ++++++-
 arch/powerpc/kvm/book3s_hv_rmhandlers.S | 50 +++++++++++++++++++++++++++------
 7 files changed, 57 insertions(+), 10 deletions(-)

(limited to 'arch/powerpc/kvm')

diff --git a/Documentation/virtual/kvm/api.txt b/Documentation/virtual/kvm/api.txt
index 354a51ba456..e43c6f14c22 100644
--- a/Documentation/virtual/kvm/api.txt
+++ b/Documentation/virtual/kvm/api.txt
@@ -1810,6 +1810,7 @@ registers, find a list below:
   PPC   | KVM_REG_PPC_TLB3PS	| 32
   PPC   | KVM_REG_PPC_EPTCFG	| 32
   PPC   | KVM_REG_PPC_ICP_STATE | 64
+  PPC   | KVM_REG_PPC_TB_OFFSET	| 64
   PPC   | KVM_REG_PPC_SPMC1	| 32
   PPC   | KVM_REG_PPC_SPMC2	| 32
   PPC   | KVM_REG_PPC_IAMR	| 64
diff --git a/arch/powerpc/include/asm/kvm_host.h b/arch/powerpc/include/asm/kvm_host.h
index d9b21af6261..e4d67a606e4 100644
--- a/arch/powerpc/include/asm/kvm_host.h
+++ b/arch/powerpc/include/asm/kvm_host.h
@@ -289,6 +289,7 @@ struct kvmppc_vcore {
 	u64 stolen_tb;
 	u64 preempt_tb;
 	struct kvm_vcpu *runner;
+	u64 tb_offset;		/* guest timebase - host timebase */
 };
 
 #define VCORE_ENTRY_COUNT(vc)	((vc)->entry_exit_count & 0xff)
diff --git a/arch/powerpc/include/asm/reg.h b/arch/powerpc/include/asm/reg.h
index 10d1ef016bf..fd4db15e6f2 100644
--- a/arch/powerpc/include/asm/reg.h
+++ b/arch/powerpc/include/asm/reg.h
@@ -243,6 +243,7 @@
 #define SPRN_TBRU	0x10D	/* Time Base Read Upper Register (user, R/O) */
 #define SPRN_TBWL	0x11C	/* Time Base Lower Register (super, R/W) */
 #define SPRN_TBWU	0x11D	/* Time Base Upper Register (super, R/W) */
+#define SPRN_TBU40	0x11E	/* Timebase upper 40 bits (hyper, R/W) */
 #define SPRN_SPURR	0x134	/* Scaled PURR */
 #define SPRN_HSPRG0	0x130	/* Hypervisor Scratch 0 */
 #define SPRN_HSPRG1	0x131	/* Hypervisor Scratch 1 */
diff --git a/arch/powerpc/include/uapi/asm/kvm.h b/arch/powerpc/include/uapi/asm/kvm.h
index 7ed41c0b404..a8124fe93fb 100644
--- a/arch/powerpc/include/uapi/asm/kvm.h
+++ b/arch/powerpc/include/uapi/asm/kvm.h
@@ -504,6 +504,9 @@ struct kvm_get_htab_header {
 #define KVM_REG_PPC_TLB3PS	(KVM_REG_PPC | KVM_REG_SIZE_U32 | 0x9a)
 #define KVM_REG_PPC_EPTCFG	(KVM_REG_PPC | KVM_REG_SIZE_U32 | 0x9b)
 
+/* Timebase offset */
+#define KVM_REG_PPC_TB_OFFSET	(KVM_REG_PPC | KVM_REG_SIZE_U64 | 0x9c)
+
 /* POWER8 registers */
 #define KVM_REG_PPC_SPMC1	(KVM_REG_PPC | KVM_REG_SIZE_U32 | 0x9d)
 #define KVM_REG_PPC_SPMC2	(KVM_REG_PPC | KVM_REG_SIZE_U32 | 0x9e)
diff --git a/arch/powerpc/kernel/asm-offsets.c b/arch/powerpc/kernel/asm-offsets.c
index 19e699d747b..34d63d87191 100644
--- a/arch/powerpc/kernel/asm-offsets.c
+++ b/arch/powerpc/kernel/asm-offsets.c
@@ -523,6 +523,7 @@ int main(void)
 	DEFINE(VCORE_NAP_COUNT, offsetof(struct kvmppc_vcore, nap_count));
 	DEFINE(VCORE_IN_GUEST, offsetof(struct kvmppc_vcore, in_guest));
 	DEFINE(VCORE_NAPPING_THREADS, offsetof(struct kvmppc_vcore, napping_threads));
+	DEFINE(VCORE_TB_OFFSET, offsetof(struct kvmppc_vcore, tb_offset));
 	DEFINE(VCPU_SVCPU, offsetof(struct kvmppc_vcpu_book3s, shadow_vcpu) -
 			   offsetof(struct kvmppc_vcpu_book3s, vcpu));
 	DEFINE(VCPU_SLB_E, offsetof(struct kvmppc_slb, orige));
diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c
index 45a9b876b0a..56f57af7e73 100644
--- a/arch/powerpc/kvm/book3s_hv.c
+++ b/arch/powerpc/kvm/book3s_hv.c
@@ -489,7 +489,7 @@ static void kvmppc_create_dtl_entry(struct kvm_vcpu *vcpu,
 	memset(dt, 0, sizeof(struct dtl_entry));
 	dt->dispatch_reason = 7;
 	dt->processor_id = vc->pcpu + vcpu->arch.ptid;
-	dt->timebase = now;
+	dt->timebase = now + vc->tb_offset;
 	dt->enqueue_to_dispatch_time = stolen;
 	dt->srr0 = kvmppc_get_pc(vcpu);
 	dt->srr1 = vcpu->arch.shregs.msr;
@@ -793,6 +793,9 @@ int kvmppc_get_one_reg(struct kvm_vcpu *vcpu, u64 id, union kvmppc_one_reg *val)
 		val->vpaval.length = vcpu->arch.dtl.len;
 		spin_unlock(&vcpu->arch.vpa_update_lock);
 		break;
+	case KVM_REG_PPC_TB_OFFSET:
+		*val = get_reg_val(id, vcpu->arch.vcore->tb_offset);
+		break;
 	default:
 		r = -EINVAL;
 		break;
@@ -892,6 +895,11 @@ int kvmppc_set_one_reg(struct kvm_vcpu *vcpu, u64 id, union kvmppc_one_reg *val)
 		len -= len % sizeof(struct dtl_entry);
 		r = set_vpa(vcpu, &vcpu->arch.dtl, addr, len);
 		break;
+	case KVM_REG_PPC_TB_OFFSET:
+		/* round up to multiple of 2^24 */
+		vcpu->arch.vcore->tb_offset =
+			ALIGN(set_reg_val(id, *val), 1UL << 24);
+		break;
 	default:
 		r = -EINVAL;
 		break;
diff --git a/arch/powerpc/kvm/book3s_hv_rmhandlers.S b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
index 541aea0ce91..82b06dfe2d2 100644
--- a/arch/powerpc/kvm/book3s_hv_rmhandlers.S
+++ b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
@@ -347,7 +347,22 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_201)
 	bdnz	28b
 	ptesync
 
-22:	li	r0,1
+	/* Add timebase offset onto timebase */
+22:	ld	r8,VCORE_TB_OFFSET(r5)
+	cmpdi	r8,0
+	beq	37f
+	mftb	r6		/* current host timebase */
+	add	r8,r8,r6
+	mtspr	SPRN_TBU40,r8	/* update upper 40 bits */
+	mftb	r7		/* check if lower 24 bits overflowed */
+	clrldi	r6,r6,40
+	clrldi	r7,r7,40
+	cmpld	r7,r6
+	bge	37f
+	addis	r8,r8,0x100	/* if so, increment upper 40 bits */
+	mtspr	SPRN_TBU40,r8
+
+37:	li	r0,1
 	stb	r0,VCORE_IN_GUEST(r5)	/* signal secondaries to continue */
 	b	10f
 
@@ -782,13 +797,6 @@ ext_stash_for_host:
 ext_interrupt_to_host:
 
 guest_exit_cont:		/* r9 = vcpu, r12 = trap, r13 = paca */
-	/* Save DEC */
-	mfspr	r5,SPRN_DEC
-	mftb	r6
-	extsw	r5,r5
-	add	r5,r5,r6
-	std	r5,VCPU_DEC_EXPIRES(r9)
-
 	/* Save more register state  */
 	mfdar	r6
 	mfdsisr	r7
@@ -958,7 +966,24 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_201)
 	mtspr	SPRN_SDR1,r6		/* switch to partition page table */
 	mtspr	SPRN_LPID,r7
 	isync
-	li	r0,0
+
+	/* Subtract timebase offset from timebase */
+	ld	r8,VCORE_TB_OFFSET(r5)
+	cmpdi	r8,0
+	beq	17f
+	mftb	r6			/* current host timebase */
+	subf	r8,r8,r6
+	mtspr	SPRN_TBU40,r8		/* update upper 40 bits */
+	mftb	r7			/* check if lower 24 bits overflowed */
+	clrldi	r6,r6,40
+	clrldi	r7,r7,40
+	cmpld	r7,r6
+	bge	17f
+	addis	r8,r8,0x100		/* if so, increment upper 40 bits */
+	mtspr	SPRN_TBU40,r8
+
+	/* Signal secondary CPUs to continue */
+17:	li	r0,0
 	stb	r0,VCORE_IN_GUEST(r5)
 	lis	r8,0x7fff		/* MAX_INT@h */
 	mtspr	SPRN_HDEC,r8
@@ -1056,6 +1081,13 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_201)
 1:	addi	r8,r8,16
 	.endr
 
+	/* Save DEC */
+	mfspr	r5,SPRN_DEC
+	mftb	r6
+	extsw	r5,r5
+	add	r5,r5,r6
+	std	r5,VCPU_DEC_EXPIRES(r9)
+
 	/* Save and reset AMR and UAMOR before turning on the MMU */
 BEGIN_FTR_SECTION
 	mfspr	r5,SPRN_AMR
-- 
cgit v1.2.3-70-g09d2


From c0867fd50943d71d9f0bc5078393ce4ec76b3923 Mon Sep 17 00:00:00 2001
From: Paul Mackerras <paulus@samba.org>
Date: Fri, 6 Sep 2013 13:18:32 +1000
Subject: KVM: PPC: Book3S: Add GET/SET_ONE_REG interface for VRSAVE

The VRSAVE register value for a vcpu is accessible through the
GET/SET_SREGS interface for Book E processors, but not for Book 3S
processors.  In order to make this accessible for Book 3S processors,
this adds a new register identifier for GET/SET_ONE_REG, and adds
the code to implement it.

Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Alexander Graf <agraf@suse.de>
---
 Documentation/virtual/kvm/api.txt   |  1 +
 arch/powerpc/include/uapi/asm/kvm.h |  2 ++
 arch/powerpc/kvm/book3s.c           | 10 ++++++++++
 3 files changed, 13 insertions(+)

(limited to 'arch/powerpc/kvm')

diff --git a/Documentation/virtual/kvm/api.txt b/Documentation/virtual/kvm/api.txt
index e43c6f14c22..26fc37355dc 100644
--- a/Documentation/virtual/kvm/api.txt
+++ b/Documentation/virtual/kvm/api.txt
@@ -1834,6 +1834,7 @@ registers, find a list below:
   PPC   | KVM_REG_PPC_TCSCR	| 64
   PPC   | KVM_REG_PPC_PID	| 64
   PPC   | KVM_REG_PPC_ACOP	| 64
+  PPC   | KVM_REG_PPC_VRSAVE	| 32
   PPC   | KVM_REG_PPC_TM_GPR0	| 64
           ...
   PPC   | KVM_REG_PPC_TM_GPR31	| 64
diff --git a/arch/powerpc/include/uapi/asm/kvm.h b/arch/powerpc/include/uapi/asm/kvm.h
index a8124fe93fb..b98bf3f5052 100644
--- a/arch/powerpc/include/uapi/asm/kvm.h
+++ b/arch/powerpc/include/uapi/asm/kvm.h
@@ -532,6 +532,8 @@ struct kvm_get_htab_header {
 #define KVM_REG_PPC_PID		(KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xb2)
 #define KVM_REG_PPC_ACOP	(KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xb3)
 
+#define KVM_REG_PPC_VRSAVE	(KVM_REG_PPC | KVM_REG_SIZE_U32 | 0xb4)
+
 /* Transactional Memory checkpointed state:
  * This is all GPRs, all VSX regs and a subset of SPRs
  */
diff --git a/arch/powerpc/kvm/book3s.c b/arch/powerpc/kvm/book3s.c
index 700df6f1d32..f97369dc457 100644
--- a/arch/powerpc/kvm/book3s.c
+++ b/arch/powerpc/kvm/book3s.c
@@ -528,6 +528,9 @@ int kvm_vcpu_ioctl_get_one_reg(struct kvm_vcpu *vcpu, struct kvm_one_reg *reg)
 			}
 			val = get_reg_val(reg->id, vcpu->arch.vscr.u[3]);
 			break;
+		case KVM_REG_PPC_VRSAVE:
+			val = get_reg_val(reg->id, vcpu->arch.vrsave);
+			break;
 #endif /* CONFIG_ALTIVEC */
 		case KVM_REG_PPC_DEBUG_INST: {
 			u32 opcode = INS_TW;
@@ -605,6 +608,13 @@ int kvm_vcpu_ioctl_set_one_reg(struct kvm_vcpu *vcpu, struct kvm_one_reg *reg)
 			}
 			vcpu->arch.vscr.u[3] = set_reg_val(reg->id, val);
 			break;
+		case KVM_REG_PPC_VRSAVE:
+			if (!cpu_has_feature(CPU_FTR_ALTIVEC)) {
+				r = -ENXIO;
+				break;
+			}
+			vcpu->arch.vrsave = set_reg_val(reg->id, val);
+			break;
 #endif /* CONFIG_ALTIVEC */
 #ifdef CONFIG_KVM_XICS
 		case KVM_REG_PPC_ICP_STATE:
-- 
cgit v1.2.3-70-g09d2


From 42d7604d0c5a24f448983424eb19e3845cb031ba Mon Sep 17 00:00:00 2001
From: Paul Mackerras <paulus@samba.org>
Date: Fri, 6 Sep 2013 13:23:21 +1000
Subject: KVM: PPC: Book3S HV: Implement H_CONFER

The H_CONFER hypercall is used when a guest vcpu is spinning on a lock
held by another vcpu which has been preempted, and the spinning vcpu
wishes to give its timeslice to the lock holder.  We implement this
in the straightforward way using kvm_vcpu_yield_to().

Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Alexander Graf <agraf@suse.de>
---
 arch/powerpc/kvm/book3s_hv.c | 9 +++++++++
 1 file changed, 9 insertions(+)

(limited to 'arch/powerpc/kvm')

diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c
index 56f57af7e73..a010aa4cd02 100644
--- a/arch/powerpc/kvm/book3s_hv.c
+++ b/arch/powerpc/kvm/book3s_hv.c
@@ -538,6 +538,15 @@ int kvmppc_pseries_do_hcall(struct kvm_vcpu *vcpu)
 		}
 		break;
 	case H_CONFER:
+		target = kvmppc_get_gpr(vcpu, 4);
+		if (target == -1)
+			break;
+		tvcpu = kvmppc_find_vcpu(vcpu->kvm, target);
+		if (!tvcpu) {
+			ret = H_PARAMETER;
+			break;
+		}
+		kvm_vcpu_yield_to(tvcpu);
 		break;
 	case H_REGISTER_VPA:
 		ret = do_h_register_vpa(vcpu, kvmppc_get_gpr(vcpu, 4),
-- 
cgit v1.2.3-70-g09d2


From 218309b75b5e800af952362b5cbb086fa64f59ba Mon Sep 17 00:00:00 2001
From: Paul Mackerras <paulus@samba.org>
Date: Fri, 6 Sep 2013 13:23:44 +1000
Subject: KVM: PPC: Book3S HV: Restructure kvmppc_hv_entry to be a subroutine

We have two paths into and out of the low-level guest entry and exit
code: from a vcpu task via kvmppc_hv_entry_trampoline, and from the
system reset vector for an offline secondary thread on POWER7 via
kvm_start_guest.  Currently both just branch to kvmppc_hv_entry to
enter the guest, and on guest exit, we test the vcpu physical thread
ID to detect which way we came in and thus whether we should return
to the vcpu task or go back to nap mode.

In order to make the code flow clearer, and to keep the code relating
to each flow together, this turns kvmppc_hv_entry into a subroutine
that follows the normal conventions for call and return.  This means
that kvmppc_hv_entry_trampoline() and kvmppc_hv_entry() now establish
normal stack frames, and we use the normal stack slots for saving
return addresses rather than local_paca->kvm_hstate.vmhandler.  Apart
from that this is mostly moving code around unchanged.

Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Alexander Graf <agraf@suse.de>
---
 arch/powerpc/kvm/book3s_hv_rmhandlers.S | 344 +++++++++++++++++---------------
 1 file changed, 178 insertions(+), 166 deletions(-)

(limited to 'arch/powerpc/kvm')

diff --git a/arch/powerpc/kvm/book3s_hv_rmhandlers.S b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
index 82b06dfe2d2..2bf295102f6 100644
--- a/arch/powerpc/kvm/book3s_hv_rmhandlers.S
+++ b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
@@ -66,8 +66,11 @@ kvmppc_skip_Hinterrupt:
  * LR = return address to continue at after eventually re-enabling MMU
  */
 _GLOBAL(kvmppc_hv_entry_trampoline)
+	mflr	r0
+	std	r0, PPC_LR_STKOFF(r1)
+	stdu	r1, -112(r1)
 	mfmsr	r10
-	LOAD_REG_ADDR(r5, kvmppc_hv_entry)
+	LOAD_REG_ADDR(r5, kvmppc_call_hv_entry)
 	li	r0,MSR_RI
 	andc	r0,r10,r0
 	li	r6,MSR_IR | MSR_DR
@@ -77,11 +80,103 @@ _GLOBAL(kvmppc_hv_entry_trampoline)
 	mtsrr1	r6
 	RFI
 
-/******************************************************************************
- *                                                                            *
- *                               Entry code                                   *
- *                                                                            *
- *****************************************************************************/
+kvmppc_call_hv_entry:
+	bl	kvmppc_hv_entry
+
+	/* Back from guest - restore host state and return to caller */
+
+	/* Restore host DABR and DABRX */
+	ld	r5,HSTATE_DABR(r13)
+	li	r6,7
+	mtspr	SPRN_DABR,r5
+	mtspr	SPRN_DABRX,r6
+
+	/* Restore SPRG3 */
+	ld	r3,PACA_SPRG3(r13)
+	mtspr	SPRN_SPRG3,r3
+
+	/*
+	 * Reload DEC.  HDEC interrupts were disabled when
+	 * we reloaded the host's LPCR value.
+	 */
+	ld	r3, HSTATE_DECEXP(r13)
+	mftb	r4
+	subf	r4, r4, r3
+	mtspr	SPRN_DEC, r4
+
+	/* Reload the host's PMU registers */
+	ld	r3, PACALPPACAPTR(r13)	/* is the host using the PMU? */
+	lbz	r4, LPPACA_PMCINUSE(r3)
+	cmpwi	r4, 0
+	beq	23f			/* skip if not */
+	lwz	r3, HSTATE_PMC(r13)
+	lwz	r4, HSTATE_PMC + 4(r13)
+	lwz	r5, HSTATE_PMC + 8(r13)
+	lwz	r6, HSTATE_PMC + 12(r13)
+	lwz	r8, HSTATE_PMC + 16(r13)
+	lwz	r9, HSTATE_PMC + 20(r13)
+BEGIN_FTR_SECTION
+	lwz	r10, HSTATE_PMC + 24(r13)
+	lwz	r11, HSTATE_PMC + 28(r13)
+END_FTR_SECTION_IFSET(CPU_FTR_ARCH_201)
+	mtspr	SPRN_PMC1, r3
+	mtspr	SPRN_PMC2, r4
+	mtspr	SPRN_PMC3, r5
+	mtspr	SPRN_PMC4, r6
+	mtspr	SPRN_PMC5, r8
+	mtspr	SPRN_PMC6, r9
+BEGIN_FTR_SECTION
+	mtspr	SPRN_PMC7, r10
+	mtspr	SPRN_PMC8, r11
+END_FTR_SECTION_IFSET(CPU_FTR_ARCH_201)
+	ld	r3, HSTATE_MMCR(r13)
+	ld	r4, HSTATE_MMCR + 8(r13)
+	ld	r5, HSTATE_MMCR + 16(r13)
+	mtspr	SPRN_MMCR1, r4
+	mtspr	SPRN_MMCRA, r5
+	mtspr	SPRN_MMCR0, r3
+	isync
+23:
+
+	/*
+	 * For external and machine check interrupts, we need
+	 * to call the Linux handler to process the interrupt.
+	 * We do that by jumping to absolute address 0x500 for
+	 * external interrupts, or the machine_check_fwnmi label
+	 * for machine checks (since firmware might have patched
+	 * the vector area at 0x200).  The [h]rfid at the end of the
+	 * handler will return to the book3s_hv_interrupts.S code.
+	 * For other interrupts we do the rfid to get back
+	 * to the book3s_hv_interrupts.S code here.
+	 */
+	ld	r8, 112+PPC_LR_STKOFF(r1)
+	addi	r1, r1, 112
+	ld	r7, HSTATE_HOST_MSR(r13)
+
+	cmpwi	cr1, r12, BOOK3S_INTERRUPT_MACHINE_CHECK
+	cmpwi	r12, BOOK3S_INTERRUPT_EXTERNAL
+BEGIN_FTR_SECTION
+	beq	11f
+END_FTR_SECTION_IFSET(CPU_FTR_ARCH_206)
+
+	/* RFI into the highmem handler, or branch to interrupt handler */
+	mfmsr	r6
+	li	r0, MSR_RI
+	andc	r6, r6, r0
+	mtmsrd	r6, 1			/* Clear RI in MSR */
+	mtsrr0	r8
+	mtsrr1	r7
+	beqa	0x500			/* external interrupt (PPC970) */
+	beq	cr1, 13f		/* machine check */
+	RFI
+
+	/* On POWER7, we have external interrupts set to use HSRR0/1 */
+11:	mtspr	SPRN_HSRR0, r8
+	mtspr	SPRN_HSRR1, r7
+	ba	0x500
+
+13:	b	machine_check_fwnmi
+
 
 /*
  * We come in here when wakened from nap mode on a secondary hw thread.
@@ -137,7 +232,7 @@ kvm_start_guest:
 	cmpdi	r4,0
 	/* if we have no vcpu to run, go back to sleep */
 	beq	kvm_no_guest
-	b	kvmppc_hv_entry
+	b	30f
 
 27:	/* XXX should handle hypervisor maintenance interrupts etc. here */
 	b	kvm_no_guest
@@ -147,6 +242,57 @@ kvm_start_guest:
 	stw	r8,HSTATE_SAVED_XIRR(r13)
 	b	kvm_no_guest
 
+30:	bl	kvmppc_hv_entry
+
+	/* Back from the guest, go back to nap */
+	/* Clear our vcpu pointer so we don't come back in early */
+	li	r0, 0
+	std	r0, HSTATE_KVM_VCPU(r13)
+	lwsync
+	/* Clear any pending IPI - we're an offline thread */
+	ld	r5, HSTATE_XICS_PHYS(r13)
+	li	r7, XICS_XIRR
+	lwzcix	r3, r5, r7		/* ack any pending interrupt */
+	rlwinm.	r0, r3, 0, 0xffffff	/* any pending? */
+	beq	37f
+	sync
+	li	r0, 0xff
+	li	r6, XICS_MFRR
+	stbcix	r0, r5, r6		/* clear the IPI */
+	stwcix	r3, r5, r7		/* EOI it */
+37:	sync
+
+	/* increment the nap count and then go to nap mode */
+	ld	r4, HSTATE_KVM_VCORE(r13)
+	addi	r4, r4, VCORE_NAP_COUNT
+	lwsync				/* make previous updates visible */
+51:	lwarx	r3, 0, r4
+	addi	r3, r3, 1
+	stwcx.	r3, 0, r4
+	bne	51b
+
+kvm_no_guest:
+	li	r0, KVM_HWTHREAD_IN_NAP
+	stb	r0, HSTATE_HWTHREAD_STATE(r13)
+	li	r3, LPCR_PECE0
+	mfspr	r4, SPRN_LPCR
+	rlwimi	r4, r3, 0, LPCR_PECE0 | LPCR_PECE1
+	mtspr	SPRN_LPCR, r4
+	isync
+	std	r0, HSTATE_SCRATCH0(r13)
+	ptesync
+	ld	r0, HSTATE_SCRATCH0(r13)
+1:	cmpd	r0, r0
+	bne	1b
+	nap
+	b	.
+
+/******************************************************************************
+ *                                                                            *
+ *                               Entry code                                   *
+ *                                                                            *
+ *****************************************************************************/
+
 .global kvmppc_hv_entry
 kvmppc_hv_entry:
 
@@ -159,7 +305,8 @@ kvmppc_hv_entry:
 	 * all other volatile GPRS = free
 	 */
 	mflr	r0
-	std	r0, HSTATE_VMHANDLER(r13)
+	std	r0, PPC_LR_STKOFF(r1)
+	stdu	r1, -112(r1)
 
 	/* Set partition DABR */
 	/* Do this before re-enabling PMU to avoid P7 DABR corruption bug */
@@ -1198,103 +1345,30 @@ BEGIN_FTR_SECTION
 	stw	r11, VCPU_PMC + 28(r9)
 END_FTR_SECTION_IFSET(CPU_FTR_ARCH_201)
 22:
+	ld	r0, 112+PPC_LR_STKOFF(r1)
+	addi	r1, r1, 112
+	mtlr	r0
+	blr
+secondary_too_late:
+	ld	r5,HSTATE_KVM_VCORE(r13)
+	HMT_LOW
+13:	lbz	r3,VCORE_IN_GUEST(r5)
+	cmpwi	r3,0
+	bne	13b
+	HMT_MEDIUM
+	li	r0, KVM_GUEST_MODE_NONE
+	stb	r0, HSTATE_IN_GUEST(r13)
+	ld	r11,PACA_SLBSHADOWPTR(r13)
 
-	/* Secondary threads go off to take a nap on POWER7 */
-BEGIN_FTR_SECTION
-	lwz	r0,VCPU_PTID(r9)
-	cmpwi	r0,0
-	bne	secondary_nap
-END_FTR_SECTION_IFSET(CPU_FTR_ARCH_206)
-
-	/* Restore host DABR and DABRX */
-	ld	r5,HSTATE_DABR(r13)
-	li	r6,7
-	mtspr	SPRN_DABR,r5
-	mtspr	SPRN_DABRX,r6
-
-	/* Restore SPRG3 */
-	ld	r3,PACA_SPRG3(r13)
-	mtspr	SPRN_SPRG3,r3
-
-	/*
-	 * Reload DEC.  HDEC interrupts were disabled when
-	 * we reloaded the host's LPCR value.
-	 */
-	ld	r3, HSTATE_DECEXP(r13)
-	mftb	r4
-	subf	r4, r4, r3
-	mtspr	SPRN_DEC, r4
-
-	/* Reload the host's PMU registers */
-	ld	r3, PACALPPACAPTR(r13)	/* is the host using the PMU? */
-	lbz	r4, LPPACA_PMCINUSE(r3)
-	cmpwi	r4, 0
-	beq	23f			/* skip if not */
-	lwz	r3, HSTATE_PMC(r13)
-	lwz	r4, HSTATE_PMC + 4(r13)
-	lwz	r5, HSTATE_PMC + 8(r13)
-	lwz	r6, HSTATE_PMC + 12(r13)
-	lwz	r8, HSTATE_PMC + 16(r13)
-	lwz	r9, HSTATE_PMC + 20(r13)
-BEGIN_FTR_SECTION
-	lwz	r10, HSTATE_PMC + 24(r13)
-	lwz	r11, HSTATE_PMC + 28(r13)
-END_FTR_SECTION_IFSET(CPU_FTR_ARCH_201)
-	mtspr	SPRN_PMC1, r3
-	mtspr	SPRN_PMC2, r4
-	mtspr	SPRN_PMC3, r5
-	mtspr	SPRN_PMC4, r6
-	mtspr	SPRN_PMC5, r8
-	mtspr	SPRN_PMC6, r9
-BEGIN_FTR_SECTION
-	mtspr	SPRN_PMC7, r10
-	mtspr	SPRN_PMC8, r11
-END_FTR_SECTION_IFSET(CPU_FTR_ARCH_201)
-	ld	r3, HSTATE_MMCR(r13)
-	ld	r4, HSTATE_MMCR + 8(r13)
-	ld	r5, HSTATE_MMCR + 16(r13)
-	mtspr	SPRN_MMCR1, r4
-	mtspr	SPRN_MMCRA, r5
-	mtspr	SPRN_MMCR0, r3
-	isync
-23:
-	/*
-	 * For external and machine check interrupts, we need
-	 * to call the Linux handler to process the interrupt.
-	 * We do that by jumping to absolute address 0x500 for
-	 * external interrupts, or the machine_check_fwnmi label
-	 * for machine checks (since firmware might have patched
-	 * the vector area at 0x200).  The [h]rfid at the end of the
-	 * handler will return to the book3s_hv_interrupts.S code.
-	 * For other interrupts we do the rfid to get back
-	 * to the book3s_hv_interrupts.S code here.
-	 */
-	ld	r8, HSTATE_VMHANDLER(r13)
-	ld	r7, HSTATE_HOST_MSR(r13)
-
-	cmpwi	cr1, r12, BOOK3S_INTERRUPT_MACHINE_CHECK
-	cmpwi	r12, BOOK3S_INTERRUPT_EXTERNAL
-BEGIN_FTR_SECTION
-	beq	11f
-END_FTR_SECTION_IFSET(CPU_FTR_ARCH_206)
-
-	/* RFI into the highmem handler, or branch to interrupt handler */
-	mfmsr	r6
-	li	r0, MSR_RI
-	andc	r6, r6, r0
-	mtmsrd	r6, 1			/* Clear RI in MSR */
-	mtsrr0	r8
-	mtsrr1	r7
-	beqa	0x500			/* external interrupt (PPC970) */
-	beq	cr1, 13f		/* machine check */
-	RFI
-
-	/* On POWER7, we have external interrupts set to use HSRR0/1 */
-11:	mtspr	SPRN_HSRR0, r8
-	mtspr	SPRN_HSRR1, r7
-	ba	0x500
-
-13:	b	machine_check_fwnmi
+	.rept	SLB_NUM_BOLTED
+	ld	r5,SLBSHADOW_SAVEAREA(r11)
+	ld	r6,SLBSHADOW_SAVEAREA+8(r11)
+	andis.	r7,r5,SLB_ESID_V@h
+	beq	1f
+	slbmte	r6,r5
+1:	addi	r11,r11,16
+	.endr
+	b	22b
 
 /*
  * Check whether an HDSI is an HPTE not found fault or something else.
@@ -1741,68 +1815,6 @@ machine_check_realmode:
 	rotldi	r11, r11, 63
 	b	fast_interrupt_c_return
 
-secondary_too_late:
-	ld	r5,HSTATE_KVM_VCORE(r13)
-	HMT_LOW
-13:	lbz	r3,VCORE_IN_GUEST(r5)
-	cmpwi	r3,0
-	bne	13b
-	HMT_MEDIUM
-	ld	r11,PACA_SLBSHADOWPTR(r13)
-
-	.rept	SLB_NUM_BOLTED
-	ld	r5,SLBSHADOW_SAVEAREA(r11)
-	ld	r6,SLBSHADOW_SAVEAREA+8(r11)
-	andis.	r7,r5,SLB_ESID_V@h
-	beq	1f
-	slbmte	r6,r5
-1:	addi	r11,r11,16
-	.endr
-
-secondary_nap:
-	/* Clear our vcpu pointer so we don't come back in early */
-	li	r0, 0
-	std	r0, HSTATE_KVM_VCPU(r13)
-	lwsync
-	/* Clear any pending IPI - assume we're a secondary thread */
-	ld	r5, HSTATE_XICS_PHYS(r13)
-	li	r7, XICS_XIRR
-	lwzcix	r3, r5, r7		/* ack any pending interrupt */
-	rlwinm.	r0, r3, 0, 0xffffff	/* any pending? */
-	beq	37f
-	sync
-	li	r0, 0xff
-	li	r6, XICS_MFRR
-	stbcix	r0, r5, r6		/* clear the IPI */
-	stwcix	r3, r5, r7		/* EOI it */
-37:	sync
-
-	/* increment the nap count and then go to nap mode */
-	ld	r4, HSTATE_KVM_VCORE(r13)
-	addi	r4, r4, VCORE_NAP_COUNT
-	lwsync				/* make previous updates visible */
-51:	lwarx	r3, 0, r4
-	addi	r3, r3, 1
-	stwcx.	r3, 0, r4
-	bne	51b
-
-kvm_no_guest:
-	li	r0, KVM_HWTHREAD_IN_NAP
-	stb	r0, HSTATE_HWTHREAD_STATE(r13)
-
-	li	r3, LPCR_PECE0
-	mfspr	r4, SPRN_LPCR
-	rlwimi	r4, r3, 0, LPCR_PECE0 | LPCR_PECE1
-	mtspr	SPRN_LPCR, r4
-	isync
-	std	r0, HSTATE_SCRATCH0(r13)
-	ptesync
-	ld	r0, HSTATE_SCRATCH0(r13)
-1:	cmpd	r0, r0
-	bne	1b
-	nap
-	b	.
-
 /*
  * Save away FP, VMX and VSX registers.
  * r3 = vcpu pointer
-- 
cgit v1.2.3-70-g09d2


From c934243ca0aa464610a8b8ff85c7a777bf066ce4 Mon Sep 17 00:00:00 2001
From: Paul Mackerras <paulus@samba.org>
Date: Fri, 6 Sep 2013 13:24:13 +1000
Subject: KVM: PPC: Book3S HV: Pull out interrupt-reading code into a
 subroutine

This moves the code in book3s_hv_rmhandlers.S that reads any pending
interrupt from the XICS interrupt controller, and works out whether
it is an IPI for the guest, an IPI for the host, or a device interrupt,
into a new function called kvmppc_read_intr.  Later patches will
need this.

Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Alexander Graf <agraf@suse.de>
---
 arch/powerpc/kvm/book3s_hv_rmhandlers.S | 117 +++++++++++++++++++-------------
 1 file changed, 68 insertions(+), 49 deletions(-)

(limited to 'arch/powerpc/kvm')

diff --git a/arch/powerpc/kvm/book3s_hv_rmhandlers.S b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
index 2bf295102f6..c91ae2b6784 100644
--- a/arch/powerpc/kvm/book3s_hv_rmhandlers.S
+++ b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
@@ -862,46 +862,11 @@ END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_206)
 	 * set, we know the host wants us out so let's do it now
 	 */
 do_ext_interrupt:
-	lbz	r0, HSTATE_HOST_IPI(r13)
-	cmpwi	r0, 0
-	bne	ext_interrupt_to_host
-
-	/* Now read the interrupt from the ICP */
-	ld	r5, HSTATE_XICS_PHYS(r13)
-	li	r7, XICS_XIRR
-	cmpdi	r5, 0
-	beq-	ext_interrupt_to_host
-	lwzcix	r3, r5, r7
-	rlwinm.	r0, r3, 0, 0xffffff
-	sync
-	beq	3f		/* if nothing pending in the ICP */
-
-	/* We found something in the ICP...
-	 *
-	 * If it's not an IPI, stash it in the PACA and return to
-	 * the host, we don't (yet) handle directing real external
-	 * interrupts directly to the guest
-	 */
-	cmpwi	r0, XICS_IPI
-	bne	ext_stash_for_host
-
-	/* It's an IPI, clear the MFRR and EOI it */
-	li	r0, 0xff
-	li	r6, XICS_MFRR
-	stbcix	r0, r5, r6		/* clear the IPI */
-	stwcix	r3, r5, r7		/* EOI it */
-	sync
-
-	/* We need to re-check host IPI now in case it got set in the
-	 * meantime. If it's clear, we bounce the interrupt to the
-	 * guest
-	 */
-	lbz	r0, HSTATE_HOST_IPI(r13)
-	cmpwi	r0, 0
-	bne-	1f
+	bl	kvmppc_read_intr
+	cmpdi	r3, 0
+	bgt	ext_interrupt_to_host
 
 	/* Allright, looks like an IPI for the guest, we need to set MER */
-3:
 	/* Check if any CPU is heading out to the host, if so head out too */
 	ld	r5, HSTATE_KVM_VCORE(r13)
 	lwz	r0, VCORE_ENTRY_EXIT(r5)
@@ -930,17 +895,6 @@ do_ext_interrupt:
 	mtspr	SPRN_LPCR, r8
 	b	fast_guest_return
 
-	/* We raced with the host, we need to resend that IPI, bummer */
-1:	li	r0, IPI_PRIORITY
-	stbcix	r0, r5, r6		/* set the IPI */
-	sync
-	b	ext_interrupt_to_host
-
-ext_stash_for_host:
-	/* It's not an IPI and it's for the host, stash it in the PACA
-	 * before exit, it will be picked up by the host ICP driver
-	 */
-	stw	r3, HSTATE_SAVED_XIRR(r13)
 ext_interrupt_to_host:
 
 guest_exit_cont:		/* r9 = vcpu, r12 = trap, r13 = paca */
@@ -1815,6 +1769,71 @@ machine_check_realmode:
 	rotldi	r11, r11, 63
 	b	fast_interrupt_c_return
 
+/*
+ * Determine what sort of external interrupt is pending (if any).
+ * Returns:
+ *	0 if no interrupt is pending
+ *	1 if an interrupt is pending that needs to be handled by the host
+ *	-1 if there was a guest wakeup IPI (which has now been cleared)
+ */
+kvmppc_read_intr:
+	/* see if a host IPI is pending */
+	li	r3, 1
+	lbz	r0, HSTATE_HOST_IPI(r13)
+	cmpwi	r0, 0
+	bne	1f
+
+	/* Now read the interrupt from the ICP */
+	ld	r6, HSTATE_XICS_PHYS(r13)
+	li	r7, XICS_XIRR
+	cmpdi	r6, 0
+	beq-	1f
+	lwzcix	r0, r6, r7
+	rlwinm.	r3, r0, 0, 0xffffff
+	sync
+	beq	1f			/* if nothing pending in the ICP */
+
+	/* We found something in the ICP...
+	 *
+	 * If it's not an IPI, stash it in the PACA and return to
+	 * the host, we don't (yet) handle directing real external
+	 * interrupts directly to the guest
+	 */
+	cmpwi	r3, XICS_IPI		/* if there is, is it an IPI? */
+	li	r3, 1
+	bne	42f
+
+	/* It's an IPI, clear the MFRR and EOI it */
+	li	r3, 0xff
+	li	r8, XICS_MFRR
+	stbcix	r3, r6, r8		/* clear the IPI */
+	stwcix	r0, r6, r7		/* EOI it */
+	sync
+
+	/* We need to re-check host IPI now in case it got set in the
+	 * meantime. If it's clear, we bounce the interrupt to the
+	 * guest
+	 */
+	lbz	r0, HSTATE_HOST_IPI(r13)
+	cmpwi	r0, 0
+	bne-	43f
+
+	/* OK, it's an IPI for us */
+	li	r3, -1
+1:	blr
+
+42:	/* It's not an IPI and it's for the host, stash it in the PACA
+	 * before exit, it will be picked up by the host ICP driver
+	 */
+	stw	r0, HSTATE_SAVED_XIRR(r13)
+	b	1b
+
+43:	/* We raced with the host, we need to resend that IPI, bummer */
+	li	r0, IPI_PRIORITY
+	stbcix	r0, r6, r8		/* set the IPI */
+	sync
+	b	1b
+
 /*
  * Save away FP, VMX and VSX registers.
  * r3 = vcpu pointer
-- 
cgit v1.2.3-70-g09d2


From 8c2dbb79c62e9da4857b873435925d3654d9fccd Mon Sep 17 00:00:00 2001
From: Paul Mackerras <paulus@samba.org>
Date: Fri, 6 Sep 2013 13:24:35 +1000
Subject: KVM: PPC: Book3S HV: Avoid unbalanced increments of VPA yield count

The yield count in the VPA is supposed to be incremented every time
we enter the guest, and every time we exit the guest, so that its
value is even when the vcpu is running in the guest and odd when it
isn't.  However, it's currently possible that we increment the yield
count on the way into the guest but then find that other CPU threads
are already exiting the guest, so we go back to nap mode via the
secondary_too_late label.  In this situation we don't increment the
yield count again, breaking the relationship between the LSB of the
count and whether the vcpu is in the guest.

To fix this, we move the increment of the yield count to a point
after we have checked whether other CPU threads are exiting.

Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Alexander Graf <agraf@suse.de>
---
 arch/powerpc/kvm/book3s_hv_rmhandlers.S | 20 ++++++++++----------
 1 file changed, 10 insertions(+), 10 deletions(-)

(limited to 'arch/powerpc/kvm')

diff --git a/arch/powerpc/kvm/book3s_hv_rmhandlers.S b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
index c91ae2b6784..0effcd14424 100644
--- a/arch/powerpc/kvm/book3s_hv_rmhandlers.S
+++ b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
@@ -405,16 +405,6 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_206)
 	/* Save R1 in the PACA */
 	std	r1, HSTATE_HOST_R1(r13)
 
-	/* Increment yield count if they have a VPA */
-	ld	r3, VCPU_VPA(r4)
-	cmpdi	r3, 0
-	beq	25f
-	lwz	r5, LPPACA_YIELDCOUNT(r3)
-	addi	r5, r5, 1
-	stw	r5, LPPACA_YIELDCOUNT(r3)
-	li	r6, 1
-	stb	r6, VCPU_VPA_DIRTY(r4)
-25:
 	/* Load up DAR and DSISR */
 	ld	r5, VCPU_DAR(r4)
 	lwz	r6, VCPU_DSISR(r4)
@@ -525,6 +515,16 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_201)
 	mtspr	SPRN_RMOR,r8
 	isync
 
+	/* Increment yield count if they have a VPA */
+	ld	r3, VCPU_VPA(r4)
+	cmpdi	r3, 0
+	beq	25f
+	lwz	r5, LPPACA_YIELDCOUNT(r3)
+	addi	r5, r5, 1
+	stw	r5, LPPACA_YIELDCOUNT(r3)
+	li	r6, 1
+	stb	r6, VCPU_VPA_DIRTY(r4)
+25:
 	/* Check if HDEC expires soon */
 	mfspr	r3,SPRN_HDEC
 	cmpwi	r3,10
-- 
cgit v1.2.3-70-g09d2


From 8b75cbbe647603f2b3c17ead35ee3cefa88397e7 Mon Sep 17 00:00:00 2001
From: Paul Mackerras <paulus@samba.org>
Date: Fri, 20 Sep 2013 14:52:37 +1000
Subject: KVM: PPC: BookE: Add GET/SET_ONE_REG interface for VRSAVE

This makes the VRSAVE register value for a vcpu accessible through
the GET/SET_ONE_REG interface on Book E systems (in addition to the
existing GET/SET_SREGS interface), for consistency with Book 3S.

Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Alexander Graf <agraf@suse.de>
---
 arch/powerpc/kvm/booke.c | 6 ++++++
 1 file changed, 6 insertions(+)

(limited to 'arch/powerpc/kvm')

diff --git a/arch/powerpc/kvm/booke.c b/arch/powerpc/kvm/booke.c
index 17722d82f1d..65fa7754b19 100644
--- a/arch/powerpc/kvm/booke.c
+++ b/arch/powerpc/kvm/booke.c
@@ -1479,6 +1479,9 @@ int kvm_vcpu_ioctl_get_one_reg(struct kvm_vcpu *vcpu, struct kvm_one_reg *reg)
 	case KVM_REG_PPC_DEBUG_INST:
 		val = get_reg_val(reg->id, KVMPPC_INST_EHPRIV);
 		break;
+	case KVM_REG_PPC_VRSAVE:
+		val = get_reg_val(reg->id, vcpu->arch.vrsave);
+		break;
 	default:
 		r = kvmppc_get_one_reg(vcpu, reg->id, &val);
 		break;
@@ -1552,6 +1555,9 @@ int kvm_vcpu_ioctl_set_one_reg(struct kvm_vcpu *vcpu, struct kvm_one_reg *reg)
 		kvmppc_set_tcr(vcpu, tcr);
 		break;
 	}
+	case KVM_REG_PPC_VRSAVE:
+		vcpu->arch.vrsave = set_reg_val(reg->id, val);
+		break;
 	default:
 		r = kvmppc_set_one_reg(vcpu, reg->id, &val);
 		break;
-- 
cgit v1.2.3-70-g09d2


From a0144e2a6b0b4a137a32f0102354782547bf0935 Mon Sep 17 00:00:00 2001
From: Paul Mackerras <paulus@samba.org>
Date: Fri, 20 Sep 2013 14:52:38 +1000
Subject: KVM: PPC: Book3S HV: Store LPCR value for each virtual core

This adds the ability to have a separate LPCR (Logical Partitioning
Control Register) value relating to a guest for each virtual core,
rather than only having a single value for the whole VM.  This
corresponds to what real POWER hardware does, where there is a LPCR
per CPU thread but most of the fields are required to have the same
value on all active threads in a core.

The per-virtual-core LPCR can be read and written using the
GET/SET_ONE_REG interface.  Userspace can can only modify the
following fields of the LPCR value:

DPFD	Default prefetch depth
ILE	Interrupt little-endian
TC	Translation control (secondary HPT hash group search disable)

We still maintain a per-VM default LPCR value in kvm->arch.lpcr, which
contains bits relating to memory management, i.e. the Virtualized
Partition Memory (VPM) bits and the bits relating to guest real mode.
When this default value is updated, the update needs to be propagated
to the per-vcore values, so we add a kvmppc_update_lpcr() helper to do
that.

Signed-off-by: Paul Mackerras <paulus@samba.org>
[agraf: fix whitespace]
Signed-off-by: Alexander Graf <agraf@suse.de>
---
 Documentation/virtual/kvm/api.txt       |  1 +
 arch/powerpc/include/asm/kvm_book3s.h   |  2 +
 arch/powerpc/include/asm/kvm_host.h     |  1 +
 arch/powerpc/include/asm/reg.h          |  3 ++
 arch/powerpc/include/uapi/asm/kvm.h     |  1 +
 arch/powerpc/kernel/asm-offsets.c       |  1 +
 arch/powerpc/kvm/book3s_64_mmu_hv.c     |  5 +--
 arch/powerpc/kvm/book3s_hv.c            | 73 +++++++++++++++++++++++++++------
 arch/powerpc/kvm/book3s_hv_rmhandlers.S |  5 ++-
 9 files changed, 75 insertions(+), 17 deletions(-)

(limited to 'arch/powerpc/kvm')

diff --git a/Documentation/virtual/kvm/api.txt b/Documentation/virtual/kvm/api.txt
index 26fc37355dc..387f4c7dad9 100644
--- a/Documentation/virtual/kvm/api.txt
+++ b/Documentation/virtual/kvm/api.txt
@@ -1835,6 +1835,7 @@ registers, find a list below:
   PPC   | KVM_REG_PPC_PID	| 64
   PPC   | KVM_REG_PPC_ACOP	| 64
   PPC   | KVM_REG_PPC_VRSAVE	| 32
+  PPC   | KVM_REG_PPC_LPCR	| 64
   PPC   | KVM_REG_PPC_TM_GPR0	| 64
           ...
   PPC   | KVM_REG_PPC_TM_GPR31	| 64
diff --git a/arch/powerpc/include/asm/kvm_book3s.h b/arch/powerpc/include/asm/kvm_book3s.h
index fa19e2f1a87..14a47416bdd 100644
--- a/arch/powerpc/include/asm/kvm_book3s.h
+++ b/arch/powerpc/include/asm/kvm_book3s.h
@@ -172,6 +172,8 @@ extern long kvmppc_do_h_remove(struct kvm *kvm, unsigned long flags,
 			unsigned long *hpret);
 extern long kvmppc_hv_get_dirty_log(struct kvm *kvm,
 			struct kvm_memory_slot *memslot, unsigned long *map);
+extern void kvmppc_update_lpcr(struct kvm *kvm, unsigned long lpcr,
+			unsigned long mask);
 
 extern void kvmppc_entry_trampoline(void);
 extern void kvmppc_hv_entry_trampoline(void);
diff --git a/arch/powerpc/include/asm/kvm_host.h b/arch/powerpc/include/asm/kvm_host.h
index e4d67a606e4..6eabffcb1c3 100644
--- a/arch/powerpc/include/asm/kvm_host.h
+++ b/arch/powerpc/include/asm/kvm_host.h
@@ -290,6 +290,7 @@ struct kvmppc_vcore {
 	u64 preempt_tb;
 	struct kvm_vcpu *runner;
 	u64 tb_offset;		/* guest timebase - host timebase */
+	ulong lpcr;
 };
 
 #define VCORE_ENTRY_COUNT(vc)	((vc)->entry_exit_count & 0xff)
diff --git a/arch/powerpc/include/asm/reg.h b/arch/powerpc/include/asm/reg.h
index fd4db15e6f2..4bec4df3fb9 100644
--- a/arch/powerpc/include/asm/reg.h
+++ b/arch/powerpc/include/asm/reg.h
@@ -284,6 +284,7 @@
 #define   LPCR_ISL	(1ul << (63-2))
 #define   LPCR_VC_SH	(63-2)
 #define   LPCR_DPFD_SH	(63-11)
+#define   LPCR_DPFD	(7ul << LPCR_DPFD_SH)
 #define   LPCR_VRMASD	(0x1ful << (63-16))
 #define   LPCR_VRMA_L	(1ul << (63-12))
 #define   LPCR_VRMA_LP0	(1ul << (63-15))
@@ -300,6 +301,7 @@
 #define     LPCR_PECE2	0x00001000	/* machine check etc can cause exit */
 #define   LPCR_MER	0x00000800	/* Mediated External Exception */
 #define   LPCR_MER_SH	11
+#define   LPCR_TC      0x00000200	/* Translation control */
 #define   LPCR_LPES    0x0000000c
 #define   LPCR_LPES0   0x00000008      /* LPAR Env selector 0 */
 #define   LPCR_LPES1   0x00000004      /* LPAR Env selector 1 */
@@ -421,6 +423,7 @@
 #define	 HID4_RMLS2_SH	 (63 - 2)	/* Real mode limit bottom 2 bits */
 #define	 HID4_LPID5_SH	 (63 - 6)	/* partition ID bottom 4 bits */
 #define	 HID4_RMOR_SH	 (63 - 22)	/* real mode offset (16 bits) */
+#define  HID4_RMOR	 (0xFFFFul << HID4_RMOR_SH)
 #define  HID4_LPES1	 (1 << (63-57))	/* LPAR env. sel. bit 1 */
 #define  HID4_RMLS0_SH	 (63 - 58)	/* Real mode limit top bit */
 #define	 HID4_LPID1_SH	 0		/* partition ID top 2 bits */
diff --git a/arch/powerpc/include/uapi/asm/kvm.h b/arch/powerpc/include/uapi/asm/kvm.h
index b98bf3f5052..e42127d1ae8 100644
--- a/arch/powerpc/include/uapi/asm/kvm.h
+++ b/arch/powerpc/include/uapi/asm/kvm.h
@@ -533,6 +533,7 @@ struct kvm_get_htab_header {
 #define KVM_REG_PPC_ACOP	(KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xb3)
 
 #define KVM_REG_PPC_VRSAVE	(KVM_REG_PPC | KVM_REG_SIZE_U32 | 0xb4)
+#define KVM_REG_PPC_LPCR	(KVM_REG_PPC | KVM_REG_SIZE_U32 | 0xb5)
 
 /* Transactional Memory checkpointed state:
  * This is all GPRs, all VSX regs and a subset of SPRs
diff --git a/arch/powerpc/kernel/asm-offsets.c b/arch/powerpc/kernel/asm-offsets.c
index 34d63d87191..fd7513f8014 100644
--- a/arch/powerpc/kernel/asm-offsets.c
+++ b/arch/powerpc/kernel/asm-offsets.c
@@ -524,6 +524,7 @@ int main(void)
 	DEFINE(VCORE_IN_GUEST, offsetof(struct kvmppc_vcore, in_guest));
 	DEFINE(VCORE_NAPPING_THREADS, offsetof(struct kvmppc_vcore, napping_threads));
 	DEFINE(VCORE_TB_OFFSET, offsetof(struct kvmppc_vcore, tb_offset));
+	DEFINE(VCORE_LPCR, offsetof(struct kvmppc_vcore, lpcr));
 	DEFINE(VCPU_SVCPU, offsetof(struct kvmppc_vcpu_book3s, shadow_vcpu) -
 			   offsetof(struct kvmppc_vcpu_book3s, vcpu));
 	DEFINE(VCPU_SLB_E, offsetof(struct kvmppc_slb, orige));
diff --git a/arch/powerpc/kvm/book3s_64_mmu_hv.c b/arch/powerpc/kvm/book3s_64_mmu_hv.c
index 043eec8461e..ccb89a048bf 100644
--- a/arch/powerpc/kvm/book3s_64_mmu_hv.c
+++ b/arch/powerpc/kvm/book3s_64_mmu_hv.c
@@ -1512,9 +1512,8 @@ static ssize_t kvm_htab_write(struct file *file, const char __user *buf,
 
 				kvm->arch.vrma_slb_v = senc | SLB_VSID_B_1T |
 					(VRMA_VSID << SLB_VSID_SHIFT_1T);
-				lpcr = kvm->arch.lpcr & ~LPCR_VRMASD;
-				lpcr |= senc << (LPCR_VRMASD_SH - 4);
-				kvm->arch.lpcr = lpcr;
+				lpcr = senc << (LPCR_VRMASD_SH - 4);
+				kvmppc_update_lpcr(kvm, lpcr, LPCR_VRMASD);
 				rma_setup = 1;
 			}
 			++i;
diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c
index a010aa4cd02..36eb95cc48a 100644
--- a/arch/powerpc/kvm/book3s_hv.c
+++ b/arch/powerpc/kvm/book3s_hv.c
@@ -195,7 +195,7 @@ void kvmppc_dump_regs(struct kvm_vcpu *vcpu)
 		pr_err("  ESID = %.16llx VSID = %.16llx\n",
 		       vcpu->arch.slb[r].orige, vcpu->arch.slb[r].origv);
 	pr_err("lpcr = %.16lx sdr1 = %.16lx last_inst = %.8x\n",
-	       vcpu->kvm->arch.lpcr, vcpu->kvm->arch.sdr1,
+	       vcpu->arch.vcore->lpcr, vcpu->kvm->arch.sdr1,
 	       vcpu->arch.last_inst);
 }
 
@@ -723,6 +723,21 @@ int kvm_arch_vcpu_ioctl_set_sregs(struct kvm_vcpu *vcpu,
 	return 0;
 }
 
+static void kvmppc_set_lpcr(struct kvm_vcpu *vcpu, u64 new_lpcr)
+{
+	struct kvmppc_vcore *vc = vcpu->arch.vcore;
+	u64 mask;
+
+	spin_lock(&vc->lock);
+	/*
+	 * Userspace can only modify DPFD (default prefetch depth),
+	 * ILE (interrupt little-endian) and TC (translation control).
+	 */
+	mask = LPCR_DPFD | LPCR_ILE | LPCR_TC;
+	vc->lpcr = (vc->lpcr & ~mask) | (new_lpcr & mask);
+	spin_unlock(&vc->lock);
+}
+
 int kvmppc_get_one_reg(struct kvm_vcpu *vcpu, u64 id, union kvmppc_one_reg *val)
 {
 	int r = 0;
@@ -805,6 +820,9 @@ int kvmppc_get_one_reg(struct kvm_vcpu *vcpu, u64 id, union kvmppc_one_reg *val)
 	case KVM_REG_PPC_TB_OFFSET:
 		*val = get_reg_val(id, vcpu->arch.vcore->tb_offset);
 		break;
+	case KVM_REG_PPC_LPCR:
+		*val = get_reg_val(id, vcpu->arch.vcore->lpcr);
+		break;
 	default:
 		r = -EINVAL;
 		break;
@@ -909,6 +927,9 @@ int kvmppc_set_one_reg(struct kvm_vcpu *vcpu, u64 id, union kvmppc_one_reg *val)
 		vcpu->arch.vcore->tb_offset =
 			ALIGN(set_reg_val(id, *val), 1UL << 24);
 		break;
+	case KVM_REG_PPC_LPCR:
+		kvmppc_set_lpcr(vcpu, set_reg_val(id, *val));
+		break;
 	default:
 		r = -EINVAL;
 		break;
@@ -969,6 +990,7 @@ struct kvm_vcpu *kvmppc_core_vcpu_create(struct kvm *kvm, unsigned int id)
 			spin_lock_init(&vcore->lock);
 			init_waitqueue_head(&vcore->wq);
 			vcore->preempt_tb = TB_NIL;
+			vcore->lpcr = kvm->arch.lpcr;
 		}
 		kvm->arch.vcores[core] = vcore;
 		kvm->arch.online_vcores++;
@@ -1758,6 +1780,32 @@ void kvmppc_core_commit_memory_region(struct kvm *kvm,
 	}
 }
 
+/*
+ * Update LPCR values in kvm->arch and in vcores.
+ * Caller must hold kvm->lock.
+ */
+void kvmppc_update_lpcr(struct kvm *kvm, unsigned long lpcr, unsigned long mask)
+{
+	long int i;
+	u32 cores_done = 0;
+
+	if ((kvm->arch.lpcr & mask) == lpcr)
+		return;
+
+	kvm->arch.lpcr = (kvm->arch.lpcr & ~mask) | lpcr;
+
+	for (i = 0; i < KVM_MAX_VCORES; ++i) {
+		struct kvmppc_vcore *vc = kvm->arch.vcores[i];
+		if (!vc)
+			continue;
+		spin_lock(&vc->lock);
+		vc->lpcr = (vc->lpcr & ~mask) | lpcr;
+		spin_unlock(&vc->lock);
+		if (++cores_done >= kvm->arch.online_vcores)
+			break;
+	}
+}
+
 static int kvmppc_hv_setup_htab_rma(struct kvm_vcpu *vcpu)
 {
 	int err = 0;
@@ -1766,7 +1814,8 @@ static int kvmppc_hv_setup_htab_rma(struct kvm_vcpu *vcpu)
 	unsigned long hva;
 	struct kvm_memory_slot *memslot;
 	struct vm_area_struct *vma;
-	unsigned long lpcr, senc;
+	unsigned long lpcr = 0, senc;
+	unsigned long lpcr_mask = 0;
 	unsigned long psize, porder;
 	unsigned long rma_size;
 	unsigned long rmls;
@@ -1831,9 +1880,9 @@ static int kvmppc_hv_setup_htab_rma(struct kvm_vcpu *vcpu)
 		senc = slb_pgsize_encoding(psize);
 		kvm->arch.vrma_slb_v = senc | SLB_VSID_B_1T |
 			(VRMA_VSID << SLB_VSID_SHIFT_1T);
-		lpcr = kvm->arch.lpcr & ~LPCR_VRMASD;
-		lpcr |= senc << (LPCR_VRMASD_SH - 4);
-		kvm->arch.lpcr = lpcr;
+		lpcr_mask = LPCR_VRMASD;
+		/* the -4 is to account for senc values starting at 0x10 */
+		lpcr = senc << (LPCR_VRMASD_SH - 4);
 
 		/* Create HPTEs in the hash page table for the VRMA */
 		kvmppc_map_vrma(vcpu, memslot, porder);
@@ -1854,23 +1903,21 @@ static int kvmppc_hv_setup_htab_rma(struct kvm_vcpu *vcpu)
 		kvm->arch.rma = ri;
 
 		/* Update LPCR and RMOR */
-		lpcr = kvm->arch.lpcr;
 		if (cpu_has_feature(CPU_FTR_ARCH_201)) {
 			/* PPC970; insert RMLS value (split field) in HID4 */
-			lpcr &= ~((1ul << HID4_RMLS0_SH) |
-				  (3ul << HID4_RMLS2_SH));
-			lpcr |= ((rmls >> 2) << HID4_RMLS0_SH) |
+			lpcr_mask = (1ul << HID4_RMLS0_SH) |
+				(3ul << HID4_RMLS2_SH) | HID4_RMOR;
+			lpcr = ((rmls >> 2) << HID4_RMLS0_SH) |
 				((rmls & 3) << HID4_RMLS2_SH);
 			/* RMOR is also in HID4 */
 			lpcr |= ((ri->base_pfn >> (26 - PAGE_SHIFT)) & 0xffff)
 				<< HID4_RMOR_SH;
 		} else {
 			/* POWER7 */
-			lpcr &= ~(LPCR_VPM0 | LPCR_VRMA_L);
-			lpcr |= rmls << LPCR_RMLS_SH;
+			lpcr_mask = LPCR_VPM0 | LPCR_VRMA_L | LPCR_RMLS;
+			lpcr = rmls << LPCR_RMLS_SH;
 			kvm->arch.rmor = ri->base_pfn << PAGE_SHIFT;
 		}
-		kvm->arch.lpcr = lpcr;
 		pr_info("KVM: Using RMO at %lx size %lx (LPCR = %lx)\n",
 			ri->base_pfn << PAGE_SHIFT, rma_size, lpcr);
 
@@ -1889,6 +1936,8 @@ static int kvmppc_hv_setup_htab_rma(struct kvm_vcpu *vcpu)
 		}
 	}
 
+	kvmppc_update_lpcr(kvm, lpcr, lpcr_mask);
+
 	/* Order updates to kvm->arch.lpcr etc. vs. rma_setup_done */
 	smp_wmb();
 	kvm->arch.rma_setup_done = 1;
diff --git a/arch/powerpc/kvm/book3s_hv_rmhandlers.S b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
index 0effcd14424..295fd58af39 100644
--- a/arch/powerpc/kvm/book3s_hv_rmhandlers.S
+++ b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
@@ -509,7 +509,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_201)
 	beq	20b
 
 	/* Set LPCR and RMOR. */
-10:	ld	r8,KVM_LPCR(r9)
+10:	ld	r8,VCORE_LPCR(r5)
 	mtspr	SPRN_LPCR,r8
 	ld	r8,KVM_RMOR(r9)
 	mtspr	SPRN_RMOR,r8
@@ -571,7 +571,8 @@ toc_tlbie_lock:
 	bne	24b
 	isync
 
-	ld	r7,KVM_LPCR(r9)		/* use kvm->arch.lpcr to store HID4 */
+	ld	r5,HSTATE_KVM_VCORE(r13)
+	ld	r7,VCORE_LPCR(r5)	/* use vcore->lpcr to store HID4 */
 	li	r0,0x18f
 	rotldi	r0,r0,HID4_LPID5_SH	/* all lpid bits in HID4 = 1 */
 	or	r0,r7,r0
-- 
cgit v1.2.3-70-g09d2


From 4b8473c9c19dff1b0c672f182cc50b9952cf42e7 Mon Sep 17 00:00:00 2001
From: Paul Mackerras <paulus@samba.org>
Date: Fri, 20 Sep 2013 14:52:39 +1000
Subject: KVM: PPC: Book3S HV: Add support for guest Program Priority Register

POWER7 and later IBM server processors have a register called the
Program Priority Register (PPR), which controls the priority of
each hardware CPU SMT thread, and affects how fast it runs compared
to other SMT threads.  This priority can be controlled by writing to
the PPR or by use of a set of instructions of the form or rN,rN,rN
which are otherwise no-ops but have been defined to set the priority
to particular levels.

This adds code to context switch the PPR when entering and exiting
guests and to make the PPR value accessible through the SET/GET_ONE_REG
interface.  When entering the guest, we set the PPR as late as
possible, because if we are setting a low thread priority it will
make the code run slowly from that point on.  Similarly, the
first-level interrupt handlers save the PPR value in the PACA very
early on, and set the thread priority to the medium level, so that
the interrupt handling code runs at a reasonable speed.

Acked-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Alexander Graf <agraf@suse.de>
---
 Documentation/virtual/kvm/api.txt         |  1 +
 arch/powerpc/include/asm/exception-64s.h  |  8 ++++++++
 arch/powerpc/include/asm/kvm_book3s_asm.h |  1 +
 arch/powerpc/include/asm/kvm_host.h       |  1 +
 arch/powerpc/include/uapi/asm/kvm.h       |  1 +
 arch/powerpc/kernel/asm-offsets.c         |  2 ++
 arch/powerpc/kvm/book3s_hv.c              |  6 ++++++
 arch/powerpc/kvm/book3s_hv_rmhandlers.S   | 12 +++++++++++-
 8 files changed, 31 insertions(+), 1 deletion(-)

(limited to 'arch/powerpc/kvm')

diff --git a/Documentation/virtual/kvm/api.txt b/Documentation/virtual/kvm/api.txt
index 387f4c7dad9..a9d1072dcbe 100644
--- a/Documentation/virtual/kvm/api.txt
+++ b/Documentation/virtual/kvm/api.txt
@@ -1836,6 +1836,7 @@ registers, find a list below:
   PPC   | KVM_REG_PPC_ACOP	| 64
   PPC   | KVM_REG_PPC_VRSAVE	| 32
   PPC   | KVM_REG_PPC_LPCR	| 64
+  PPC   | KVM_REG_PPC_PPR	| 64
   PPC   | KVM_REG_PPC_TM_GPR0	| 64
           ...
   PPC   | KVM_REG_PPC_TM_GPR31	| 64
diff --git a/arch/powerpc/include/asm/exception-64s.h b/arch/powerpc/include/asm/exception-64s.h
index cca12f08484..402c1c46650 100644
--- a/arch/powerpc/include/asm/exception-64s.h
+++ b/arch/powerpc/include/asm/exception-64s.h
@@ -204,6 +204,10 @@ do_kvm_##n:								\
 	ld	r10,area+EX_CFAR(r13);					\
 	std	r10,HSTATE_CFAR(r13);					\
 	END_FTR_SECTION_NESTED(CPU_FTR_CFAR,CPU_FTR_CFAR,947);		\
+	BEGIN_FTR_SECTION_NESTED(948)					\
+	ld	r10,area+EX_PPR(r13);					\
+	std	r10,HSTATE_PPR(r13);					\
+	END_FTR_SECTION_NESTED(CPU_FTR_HAS_PPR,CPU_FTR_HAS_PPR,948);	\
 	ld	r10,area+EX_R10(r13);					\
 	stw	r9,HSTATE_SCRATCH1(r13);				\
 	ld	r9,area+EX_R9(r13);					\
@@ -217,6 +221,10 @@ do_kvm_##n:								\
 	ld	r10,area+EX_R10(r13);					\
 	beq	89f;							\
 	stw	r9,HSTATE_SCRATCH1(r13);			\
+	BEGIN_FTR_SECTION_NESTED(948)					\
+	ld	r9,area+EX_PPR(r13);					\
+	std	r9,HSTATE_PPR(r13);					\
+	END_FTR_SECTION_NESTED(CPU_FTR_HAS_PPR,CPU_FTR_HAS_PPR,948);	\
 	ld	r9,area+EX_R9(r13);					\
 	std	r12,HSTATE_SCRATCH0(r13);			\
 	li	r12,n;							\
diff --git a/arch/powerpc/include/asm/kvm_book3s_asm.h b/arch/powerpc/include/asm/kvm_book3s_asm.h
index 9039d3c97ee..22f46061ae8 100644
--- a/arch/powerpc/include/asm/kvm_book3s_asm.h
+++ b/arch/powerpc/include/asm/kvm_book3s_asm.h
@@ -101,6 +101,7 @@ struct kvmppc_host_state {
 #endif
 #ifdef CONFIG_PPC_BOOK3S_64
 	u64 cfar;
+	u64 ppr;
 #endif
 };
 
diff --git a/arch/powerpc/include/asm/kvm_host.h b/arch/powerpc/include/asm/kvm_host.h
index 6eabffcb1c3..4934e13fb23 100644
--- a/arch/powerpc/include/asm/kvm_host.h
+++ b/arch/powerpc/include/asm/kvm_host.h
@@ -460,6 +460,7 @@ struct kvm_vcpu_arch {
 	u32 ctrl;
 	ulong dabr;
 	ulong cfar;
+	ulong ppr;
 #endif
 	u32 vrsave; /* also USPRG0 */
 	u32 mmucr;
diff --git a/arch/powerpc/include/uapi/asm/kvm.h b/arch/powerpc/include/uapi/asm/kvm.h
index e42127d1ae8..fab6bc1f8e9 100644
--- a/arch/powerpc/include/uapi/asm/kvm.h
+++ b/arch/powerpc/include/uapi/asm/kvm.h
@@ -534,6 +534,7 @@ struct kvm_get_htab_header {
 
 #define KVM_REG_PPC_VRSAVE	(KVM_REG_PPC | KVM_REG_SIZE_U32 | 0xb4)
 #define KVM_REG_PPC_LPCR	(KVM_REG_PPC | KVM_REG_SIZE_U32 | 0xb5)
+#define KVM_REG_PPC_PPR		(KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xb6)
 
 /* Transactional Memory checkpointed state:
  * This is all GPRs, all VSX regs and a subset of SPRs
diff --git a/arch/powerpc/kernel/asm-offsets.c b/arch/powerpc/kernel/asm-offsets.c
index fd7513f8014..5fda4ef489a 100644
--- a/arch/powerpc/kernel/asm-offsets.c
+++ b/arch/powerpc/kernel/asm-offsets.c
@@ -519,6 +519,7 @@ int main(void)
 	DEFINE(VCPU_TRAP, offsetof(struct kvm_vcpu, arch.trap));
 	DEFINE(VCPU_PTID, offsetof(struct kvm_vcpu, arch.ptid));
 	DEFINE(VCPU_CFAR, offsetof(struct kvm_vcpu, arch.cfar));
+	DEFINE(VCPU_PPR, offsetof(struct kvm_vcpu, arch.ppr));
 	DEFINE(VCORE_ENTRY_EXIT, offsetof(struct kvmppc_vcore, entry_exit_count));
 	DEFINE(VCORE_NAP_COUNT, offsetof(struct kvmppc_vcore, nap_count));
 	DEFINE(VCORE_IN_GUEST, offsetof(struct kvmppc_vcore, in_guest));
@@ -604,6 +605,7 @@ int main(void)
 
 #ifdef CONFIG_PPC_BOOK3S_64
 	HSTATE_FIELD(HSTATE_CFAR, cfar);
+	HSTATE_FIELD(HSTATE_PPR, ppr);
 #endif /* CONFIG_PPC_BOOK3S_64 */
 
 #else /* CONFIG_PPC_BOOK3S */
diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c
index 36eb95cc48a..2a0e38feec1 100644
--- a/arch/powerpc/kvm/book3s_hv.c
+++ b/arch/powerpc/kvm/book3s_hv.c
@@ -823,6 +823,9 @@ int kvmppc_get_one_reg(struct kvm_vcpu *vcpu, u64 id, union kvmppc_one_reg *val)
 	case KVM_REG_PPC_LPCR:
 		*val = get_reg_val(id, vcpu->arch.vcore->lpcr);
 		break;
+	case KVM_REG_PPC_PPR:
+		*val = get_reg_val(id, vcpu->arch.ppr);
+		break;
 	default:
 		r = -EINVAL;
 		break;
@@ -930,6 +933,9 @@ int kvmppc_set_one_reg(struct kvm_vcpu *vcpu, u64 id, union kvmppc_one_reg *val)
 	case KVM_REG_PPC_LPCR:
 		kvmppc_set_lpcr(vcpu, set_reg_val(id, *val));
 		break;
+	case KVM_REG_PPC_PPR:
+		vcpu->arch.ppr = set_reg_val(id, *val);
+		break;
 	default:
 		r = -EINVAL;
 		break;
diff --git a/arch/powerpc/kvm/book3s_hv_rmhandlers.S b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
index 295fd58af39..a81979becf4 100644
--- a/arch/powerpc/kvm/book3s_hv_rmhandlers.S
+++ b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
@@ -717,13 +717,15 @@ BEGIN_FTR_SECTION
 	ld	r5, VCPU_CFAR(r4)
 	mtspr	SPRN_CFAR, r5
 END_FTR_SECTION_IFSET(CPU_FTR_CFAR)
+BEGIN_FTR_SECTION
+	ld	r0, VCPU_PPR(r4)
+END_FTR_SECTION_IFSET(CPU_FTR_HAS_PPR)
 
 	ld	r5, VCPU_LR(r4)
 	lwz	r6, VCPU_CR(r4)
 	mtlr	r5
 	mtcr	r6
 
-	ld	r0, VCPU_GPR(R0)(r4)
 	ld	r1, VCPU_GPR(R1)(r4)
 	ld	r2, VCPU_GPR(R2)(r4)
 	ld	r3, VCPU_GPR(R3)(r4)
@@ -737,6 +739,10 @@ END_FTR_SECTION_IFSET(CPU_FTR_CFAR)
 	ld	r12, VCPU_GPR(R12)(r4)
 	ld	r13, VCPU_GPR(R13)(r4)
 
+BEGIN_FTR_SECTION
+	mtspr	SPRN_PPR, r0
+END_FTR_SECTION_IFSET(CPU_FTR_HAS_PPR)
+	ld	r0, VCPU_GPR(R0)(r4)
 	ld	r4, VCPU_GPR(R4)(r4)
 
 	hrfid
@@ -787,6 +793,10 @@ BEGIN_FTR_SECTION
 	ld	r3, HSTATE_CFAR(r13)
 	std	r3, VCPU_CFAR(r9)
 END_FTR_SECTION_IFSET(CPU_FTR_CFAR)
+BEGIN_FTR_SECTION
+	ld	r4, HSTATE_PPR(r13)
+	std	r4, VCPU_PPR(r9)
+END_FTR_SECTION_IFSET(CPU_FTR_HAS_PPR)
 
 	/* Restore R1/R2 so we can handle faults */
 	ld	r1, HSTATE_HOST_R1(r13)
-- 
cgit v1.2.3-70-g09d2


From 388cc6e133132e6c9b64e7d5361114a3a7d57663 Mon Sep 17 00:00:00 2001
From: Paul Mackerras <paulus@samba.org>
Date: Sat, 21 Sep 2013 14:35:02 +1000
Subject: KVM: PPC: Book3S HV: Support POWER6 compatibility mode on POWER7

This enables us to use the Processor Compatibility Register (PCR) on
POWER7 to put the processor into architecture 2.05 compatibility mode
when running a guest.  In this mode the new instructions and registers
that were introduced on POWER7 are disabled in user mode.  This
includes all the VSX facilities plus several other instructions such
as ldbrx, stdbrx, popcntw, popcntd, etc.

To select this mode, we have a new register accessible through the
set/get_one_reg interface, called KVM_REG_PPC_ARCH_COMPAT.  Setting
this to zero gives the full set of capabilities of the processor.
Setting it to one of the "logical" PVR values defined in PAPR puts
the vcpu into the compatibility mode for the corresponding
architecture level.  The supported values are:

0x0f000002	Architecture 2.05 (POWER6)
0x0f000003	Architecture 2.06 (POWER7)
0x0f100003	Architecture 2.06+ (POWER7+)

Since the PCR is per-core, the architecture compatibility level and
the corresponding PCR value are stored in the struct kvmppc_vcore, and
are therefore shared between all vcpus in a virtual core.

Signed-off-by: Paul Mackerras <paulus@samba.org>
[agraf: squash in fix to add missing break statements and documentation]
Signed-off-by: Alexander Graf <agraf@suse.de>
---
 Documentation/virtual/kvm/api.txt       |  1 +
 arch/powerpc/include/asm/kvm_host.h     |  2 ++
 arch/powerpc/include/asm/reg.h          | 11 +++++++++++
 arch/powerpc/include/uapi/asm/kvm.h     |  3 +++
 arch/powerpc/kernel/asm-offsets.c       |  1 +
 arch/powerpc/kvm/book3s_hv.c            | 35 +++++++++++++++++++++++++++++++++
 arch/powerpc/kvm/book3s_hv_rmhandlers.S | 16 +++++++++++++--
 7 files changed, 67 insertions(+), 2 deletions(-)

(limited to 'arch/powerpc/kvm')

diff --git a/Documentation/virtual/kvm/api.txt b/Documentation/virtual/kvm/api.txt
index a9d1072dcbe..25a19576493 100644
--- a/Documentation/virtual/kvm/api.txt
+++ b/Documentation/virtual/kvm/api.txt
@@ -1837,6 +1837,7 @@ registers, find a list below:
   PPC   | KVM_REG_PPC_VRSAVE	| 32
   PPC   | KVM_REG_PPC_LPCR	| 64
   PPC   | KVM_REG_PPC_PPR	| 64
+  PPC   | KVM_REG_PPC_ARCH_COMPAT 32
   PPC   | KVM_REG_PPC_TM_GPR0	| 64
           ...
   PPC   | KVM_REG_PPC_TM_GPR31	| 64
diff --git a/arch/powerpc/include/asm/kvm_host.h b/arch/powerpc/include/asm/kvm_host.h
index 4934e13fb23..b1e8f2ba2a9 100644
--- a/arch/powerpc/include/asm/kvm_host.h
+++ b/arch/powerpc/include/asm/kvm_host.h
@@ -291,6 +291,8 @@ struct kvmppc_vcore {
 	struct kvm_vcpu *runner;
 	u64 tb_offset;		/* guest timebase - host timebase */
 	ulong lpcr;
+	u32 arch_compat;
+	ulong pcr;
 };
 
 #define VCORE_ENTRY_COUNT(vc)	((vc)->entry_exit_count & 0xff)
diff --git a/arch/powerpc/include/asm/reg.h b/arch/powerpc/include/asm/reg.h
index 4bec4df3fb9..e294673e9d4 100644
--- a/arch/powerpc/include/asm/reg.h
+++ b/arch/powerpc/include/asm/reg.h
@@ -314,6 +314,10 @@
 #define   LPID_RSVD	0x3ff		/* Reserved LPID for partn switching */
 #define	SPRN_HMER	0x150	/* Hardware m? error recovery */
 #define	SPRN_HMEER	0x151	/* Hardware m? enable error recovery */
+#define SPRN_PCR	0x152	/* Processor compatibility register */
+#define   PCR_VEC_DIS	(1ul << (63-0))	/* Vec. disable (bit NA since POWER8) */
+#define   PCR_VSX_DIS	(1ul << (63-1))	/* VSX disable (bit NA since POWER8) */
+#define   PCR_ARCH_205	0x2		/* Architecture 2.05 */
 #define	SPRN_HEIR	0x153	/* Hypervisor Emulated Instruction Register */
 #define SPRN_TLBINDEXR	0x154	/* P7 TLB control register */
 #define SPRN_TLBVPNR	0x155	/* P7 TLB control register */
@@ -1106,6 +1110,13 @@
 #define PVR_BE		0x0070
 #define PVR_PA6T	0x0090
 
+/* "Logical" PVR values defined in PAPR, representing architecture levels */
+#define PVR_ARCH_204	0x0f000001
+#define PVR_ARCH_205	0x0f000002
+#define PVR_ARCH_206	0x0f000003
+#define PVR_ARCH_206p	0x0f100003
+#define PVR_ARCH_207	0x0f000004
+
 /* Macros for setting and retrieving special purpose registers */
 #ifndef __ASSEMBLY__
 #define mfmsr()		({unsigned long rval; \
diff --git a/arch/powerpc/include/uapi/asm/kvm.h b/arch/powerpc/include/uapi/asm/kvm.h
index fab6bc1f8e9..e420d46d363 100644
--- a/arch/powerpc/include/uapi/asm/kvm.h
+++ b/arch/powerpc/include/uapi/asm/kvm.h
@@ -536,6 +536,9 @@ struct kvm_get_htab_header {
 #define KVM_REG_PPC_LPCR	(KVM_REG_PPC | KVM_REG_SIZE_U32 | 0xb5)
 #define KVM_REG_PPC_PPR		(KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xb6)
 
+/* Architecture compatibility level */
+#define KVM_REG_PPC_ARCH_COMPAT	(KVM_REG_PPC | KVM_REG_SIZE_U32 | 0xb7)
+
 /* Transactional Memory checkpointed state:
  * This is all GPRs, all VSX regs and a subset of SPRs
  */
diff --git a/arch/powerpc/kernel/asm-offsets.c b/arch/powerpc/kernel/asm-offsets.c
index 5fda4ef489a..5a285efba17 100644
--- a/arch/powerpc/kernel/asm-offsets.c
+++ b/arch/powerpc/kernel/asm-offsets.c
@@ -526,6 +526,7 @@ int main(void)
 	DEFINE(VCORE_NAPPING_THREADS, offsetof(struct kvmppc_vcore, napping_threads));
 	DEFINE(VCORE_TB_OFFSET, offsetof(struct kvmppc_vcore, tb_offset));
 	DEFINE(VCORE_LPCR, offsetof(struct kvmppc_vcore, lpcr));
+	DEFINE(VCORE_PCR, offsetof(struct kvmppc_vcore, pcr));
 	DEFINE(VCPU_SVCPU, offsetof(struct kvmppc_vcpu_book3s, shadow_vcpu) -
 			   offsetof(struct kvmppc_vcpu_book3s, vcpu));
 	DEFINE(VCPU_SLB_E, offsetof(struct kvmppc_slb, orige));
diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c
index 2a0e38feec1..e42fb544860 100644
--- a/arch/powerpc/kvm/book3s_hv.c
+++ b/arch/powerpc/kvm/book3s_hv.c
@@ -166,6 +166,35 @@ void kvmppc_set_pvr(struct kvm_vcpu *vcpu, u32 pvr)
 	vcpu->arch.pvr = pvr;
 }
 
+int kvmppc_set_arch_compat(struct kvm_vcpu *vcpu, u32 arch_compat)
+{
+	unsigned long pcr = 0;
+	struct kvmppc_vcore *vc = vcpu->arch.vcore;
+
+	if (arch_compat) {
+		if (!cpu_has_feature(CPU_FTR_ARCH_206))
+			return -EINVAL;	/* 970 has no compat mode support */
+
+		switch (arch_compat) {
+		case PVR_ARCH_205:
+			pcr = PCR_ARCH_205;
+			break;
+		case PVR_ARCH_206:
+		case PVR_ARCH_206p:
+			break;
+		default:
+			return -EINVAL;
+		}
+	}
+
+	spin_lock(&vc->lock);
+	vc->arch_compat = arch_compat;
+	vc->pcr = pcr;
+	spin_unlock(&vc->lock);
+
+	return 0;
+}
+
 void kvmppc_dump_regs(struct kvm_vcpu *vcpu)
 {
 	int r;
@@ -826,6 +855,9 @@ int kvmppc_get_one_reg(struct kvm_vcpu *vcpu, u64 id, union kvmppc_one_reg *val)
 	case KVM_REG_PPC_PPR:
 		*val = get_reg_val(id, vcpu->arch.ppr);
 		break;
+	case KVM_REG_PPC_ARCH_COMPAT:
+		*val = get_reg_val(id, vcpu->arch.vcore->arch_compat);
+		break;
 	default:
 		r = -EINVAL;
 		break;
@@ -936,6 +968,9 @@ int kvmppc_set_one_reg(struct kvm_vcpu *vcpu, u64 id, union kvmppc_one_reg *val)
 	case KVM_REG_PPC_PPR:
 		vcpu->arch.ppr = set_reg_val(id, *val);
 		break;
+	case KVM_REG_PPC_ARCH_COMPAT:
+		r = kvmppc_set_arch_compat(vcpu, set_reg_val(id, *val));
+		break;
 	default:
 		r = -EINVAL;
 		break;
diff --git a/arch/powerpc/kvm/book3s_hv_rmhandlers.S b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
index a81979becf4..cd39632a646 100644
--- a/arch/powerpc/kvm/book3s_hv_rmhandlers.S
+++ b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
@@ -499,7 +499,13 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_201)
 	addis	r8,r8,0x100	/* if so, increment upper 40 bits */
 	mtspr	SPRN_TBU40,r8
 
-37:	li	r0,1
+	/* Load guest PCR value to select appropriate compat mode */
+37:	ld	r7, VCORE_PCR(r5)
+	cmpdi	r7, 0
+	beq	38f
+	mtspr	SPRN_PCR, r7
+38:
+	li	r0,1
 	stb	r0,VCORE_IN_GUEST(r5)	/* signal secondaries to continue */
 	b	10f
 
@@ -1094,8 +1100,14 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_201)
 	addis	r8,r8,0x100		/* if so, increment upper 40 bits */
 	mtspr	SPRN_TBU40,r8
 
+	/* Reset PCR */
+17:	ld	r0, VCORE_PCR(r5)
+	cmpdi	r0, 0
+	beq	18f
+	li	r0, 0
+	mtspr	SPRN_PCR, r0
+18:
 	/* Signal secondary CPUs to continue */
-17:	li	r0,0
 	stb	r0,VCORE_IN_GUEST(r5)
 	lis	r8,0x7fff		/* MAX_INT@h */
 	mtspr	SPRN_HDEC,r8
-- 
cgit v1.2.3-70-g09d2


From f3271d4c9011bf5f36a65b9b5e7caaef4280686d Mon Sep 17 00:00:00 2001
From: Paul Mackerras <paulus@samba.org>
Date: Fri, 20 Sep 2013 14:52:41 +1000
Subject: KVM: PPC: Book3S HV: Don't crash host on unknown guest interrupt

If we come out of a guest with an interrupt that we don't know about,
instead of crashing the host with a BUG(), we now return to userspace
with the exit reason set to KVM_EXIT_UNKNOWN and the trap vector in
the hw.hardware_exit_reason field of the kvm_run structure, as is done
on x86.  Note that run->exit_reason is already set to KVM_EXIT_UNKNOWN
at the beginning of kvmppc_handle_exit().

Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Alexander Graf <agraf@suse.de>
---
 arch/powerpc/kvm/book3s_hv.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'arch/powerpc/kvm')

diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c
index e42fb544860..de9520f9241 100644
--- a/arch/powerpc/kvm/book3s_hv.c
+++ b/arch/powerpc/kvm/book3s_hv.c
@@ -709,8 +709,8 @@ static int kvmppc_handle_exit(struct kvm_run *run, struct kvm_vcpu *vcpu,
 		printk(KERN_EMERG "trap=0x%x | pc=0x%lx | msr=0x%llx\n",
 			vcpu->arch.trap, kvmppc_get_pc(vcpu),
 			vcpu->arch.shregs.msr);
+		run->hw.hardware_exit_reason = vcpu->arch.trap;
 		r = RESUME_HOST;
-		BUG();
 		break;
 	}
 
-- 
cgit v1.2.3-70-g09d2


From f24817716efe52f3c8fc137c6893963a0416f3cb Mon Sep 17 00:00:00 2001
From: Paul Mackerras <paulus@samba.org>
Date: Fri, 20 Sep 2013 14:52:42 +1000
Subject: KVM: PPC: Book3S PR: Fix compilation without CONFIG_ALTIVEC

Commit 9d1ffdd8f3 ("KVM: PPC: Book3S PR: Don't corrupt guest state
when kernel uses VMX") added a call to kvmppc_load_up_altivec() that
isn't guarded by CONFIG_ALTIVEC, causing a link failure when building
a kernel without CONFIG_ALTIVEC set.  This adds an #ifdef to fix this.

Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Alexander Graf <agraf@suse.de>
---
 arch/powerpc/kvm/book3s_pr.c | 2 ++
 1 file changed, 2 insertions(+)

(limited to 'arch/powerpc/kvm')

diff --git a/arch/powerpc/kvm/book3s_pr.c b/arch/powerpc/kvm/book3s_pr.c
index 27db1e66595..8d45f185241 100644
--- a/arch/powerpc/kvm/book3s_pr.c
+++ b/arch/powerpc/kvm/book3s_pr.c
@@ -619,8 +619,10 @@ static void kvmppc_handle_lost_ext(struct kvm_vcpu *vcpu)
 
 	if (lost_ext & MSR_FP)
 		kvmppc_load_up_fpu();
+#ifdef CONFIG_ALTIVEC
 	if (lost_ext & MSR_VEC)
 		kvmppc_load_up_altivec();
+#endif
 	current->thread.regs->msr |= lost_ext;
 }
 
-- 
cgit v1.2.3-70-g09d2


From a2d56020d1d91934e7bb3e7c8a5a3b5921ce121b Mon Sep 17 00:00:00 2001
From: Paul Mackerras <paulus@samba.org>
Date: Fri, 20 Sep 2013 14:52:43 +1000
Subject: KVM: PPC: Book3S PR: Keep volatile reg values in vcpu rather than
 shadow_vcpu

Currently PR-style KVM keeps the volatile guest register values
(R0 - R13, CR, LR, CTR, XER, PC) in a shadow_vcpu struct rather than
the main kvm_vcpu struct.  For 64-bit, the shadow_vcpu exists in two
places, a kmalloc'd struct and in the PACA, and it gets copied back
and forth in kvmppc_core_vcpu_load/put(), because the real-mode code
can't rely on being able to access the kmalloc'd struct.

This changes the code to copy the volatile values into the shadow_vcpu
as one of the last things done before entering the guest.  Similarly
the values are copied back out of the shadow_vcpu to the kvm_vcpu
immediately after exiting the guest.  We arrange for interrupts to be
still disabled at this point so that we can't get preempted on 64-bit
and end up copying values from the wrong PACA.

This means that the accessor functions in kvm_book3s.h for these
registers are greatly simplified, and are same between PR and HV KVM.
In places where accesses to shadow_vcpu fields are now replaced by
accesses to the kvm_vcpu, we can also remove the svcpu_get/put pairs.
Finally, on 64-bit, we don't need the kmalloc'd struct at all any more.

With this, the time to read the PVR one million times in a loop went
from 567.7ms to 575.5ms (averages of 6 values), an increase of about
1.4% for this worse-case test for guest entries and exits.  The
standard deviation of the measurements is about 11ms, so the
difference is only marginally significant statistically.

Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Alexander Graf <agraf@suse.de>
---
 arch/powerpc/include/asm/kvm_book3s.h     | 220 +++++-------------------------
 arch/powerpc/include/asm/kvm_book3s_asm.h |   6 +-
 arch/powerpc/include/asm/kvm_host.h       |   1 +
 arch/powerpc/kernel/asm-offsets.c         |   4 +-
 arch/powerpc/kvm/book3s_emulate.c         |   8 +-
 arch/powerpc/kvm/book3s_interrupts.S      |  27 +++-
 arch/powerpc/kvm/book3s_pr.c              | 122 ++++++++++++-----
 arch/powerpc/kvm/book3s_rmhandlers.S      |   6 +-
 arch/powerpc/kvm/trace.h                  |   7 +-
 9 files changed, 162 insertions(+), 239 deletions(-)

(limited to 'arch/powerpc/kvm')

diff --git a/arch/powerpc/include/asm/kvm_book3s.h b/arch/powerpc/include/asm/kvm_book3s.h
index 14a47416bdd..40f22d9c704 100644
--- a/arch/powerpc/include/asm/kvm_book3s.h
+++ b/arch/powerpc/include/asm/kvm_book3s.h
@@ -200,140 +200,76 @@ extern void kvm_return_point(void);
 #include <asm/kvm_book3s_64.h>
 #endif
 
-#ifdef CONFIG_KVM_BOOK3S_PR
-
-static inline unsigned long kvmppc_interrupt_offset(struct kvm_vcpu *vcpu)
-{
-	return to_book3s(vcpu)->hior;
-}
-
-static inline void kvmppc_update_int_pending(struct kvm_vcpu *vcpu,
-			unsigned long pending_now, unsigned long old_pending)
-{
-	if (pending_now)
-		vcpu->arch.shared->int_pending = 1;
-	else if (old_pending)
-		vcpu->arch.shared->int_pending = 0;
-}
-
 static inline void kvmppc_set_gpr(struct kvm_vcpu *vcpu, int num, ulong val)
 {
-	if ( num < 14 ) {
-		struct kvmppc_book3s_shadow_vcpu *svcpu = svcpu_get(vcpu);
-		svcpu->gpr[num] = val;
-		svcpu_put(svcpu);
-		to_book3s(vcpu)->shadow_vcpu->gpr[num] = val;
-	} else
-		vcpu->arch.gpr[num] = val;
+	vcpu->arch.gpr[num] = val;
 }
 
 static inline ulong kvmppc_get_gpr(struct kvm_vcpu *vcpu, int num)
 {
-	if ( num < 14 ) {
-		struct kvmppc_book3s_shadow_vcpu *svcpu = svcpu_get(vcpu);
-		ulong r = svcpu->gpr[num];
-		svcpu_put(svcpu);
-		return r;
-	} else
-		return vcpu->arch.gpr[num];
+	return vcpu->arch.gpr[num];
 }
 
 static inline void kvmppc_set_cr(struct kvm_vcpu *vcpu, u32 val)
 {
-	struct kvmppc_book3s_shadow_vcpu *svcpu = svcpu_get(vcpu);
-	svcpu->cr = val;
-	svcpu_put(svcpu);
-	to_book3s(vcpu)->shadow_vcpu->cr = val;
+	vcpu->arch.cr = val;
 }
 
 static inline u32 kvmppc_get_cr(struct kvm_vcpu *vcpu)
 {
-	struct kvmppc_book3s_shadow_vcpu *svcpu = svcpu_get(vcpu);
-	u32 r;
-	r = svcpu->cr;
-	svcpu_put(svcpu);
-	return r;
+	return vcpu->arch.cr;
 }
 
 static inline void kvmppc_set_xer(struct kvm_vcpu *vcpu, u32 val)
 {
-	struct kvmppc_book3s_shadow_vcpu *svcpu = svcpu_get(vcpu);
-	svcpu->xer = val;
-	to_book3s(vcpu)->shadow_vcpu->xer = val;
-	svcpu_put(svcpu);
+	vcpu->arch.xer = val;
 }
 
 static inline u32 kvmppc_get_xer(struct kvm_vcpu *vcpu)
 {
-	struct kvmppc_book3s_shadow_vcpu *svcpu = svcpu_get(vcpu);
-	u32 r;
-	r = svcpu->xer;
-	svcpu_put(svcpu);
-	return r;
+	return vcpu->arch.xer;
 }
 
 static inline void kvmppc_set_ctr(struct kvm_vcpu *vcpu, ulong val)
 {
-	struct kvmppc_book3s_shadow_vcpu *svcpu = svcpu_get(vcpu);
-	svcpu->ctr = val;
-	svcpu_put(svcpu);
+	vcpu->arch.ctr = val;
 }
 
 static inline ulong kvmppc_get_ctr(struct kvm_vcpu *vcpu)
 {
-	struct kvmppc_book3s_shadow_vcpu *svcpu = svcpu_get(vcpu);
-	ulong r;
-	r = svcpu->ctr;
-	svcpu_put(svcpu);
-	return r;
+	return vcpu->arch.ctr;
 }
 
 static inline void kvmppc_set_lr(struct kvm_vcpu *vcpu, ulong val)
 {
-	struct kvmppc_book3s_shadow_vcpu *svcpu = svcpu_get(vcpu);
-	svcpu->lr = val;
-	svcpu_put(svcpu);
+	vcpu->arch.lr = val;
 }
 
 static inline ulong kvmppc_get_lr(struct kvm_vcpu *vcpu)
 {
-	struct kvmppc_book3s_shadow_vcpu *svcpu = svcpu_get(vcpu);
-	ulong r;
-	r = svcpu->lr;
-	svcpu_put(svcpu);
-	return r;
+	return vcpu->arch.lr;
 }
 
 static inline void kvmppc_set_pc(struct kvm_vcpu *vcpu, ulong val)
 {
-	struct kvmppc_book3s_shadow_vcpu *svcpu = svcpu_get(vcpu);
-	svcpu->pc = val;
-	svcpu_put(svcpu);
+	vcpu->arch.pc = val;
 }
 
 static inline ulong kvmppc_get_pc(struct kvm_vcpu *vcpu)
 {
-	struct kvmppc_book3s_shadow_vcpu *svcpu = svcpu_get(vcpu);
-	ulong r;
-	r = svcpu->pc;
-	svcpu_put(svcpu);
-	return r;
+	return vcpu->arch.pc;
 }
 
 static inline u32 kvmppc_get_last_inst(struct kvm_vcpu *vcpu)
 {
 	ulong pc = kvmppc_get_pc(vcpu);
-	struct kvmppc_book3s_shadow_vcpu *svcpu = svcpu_get(vcpu);
-	u32 r;
 
 	/* Load the instruction manually if it failed to do so in the
 	 * exit path */
-	if (svcpu->last_inst == KVM_INST_FETCH_FAILED)
-		kvmppc_ld(vcpu, &pc, sizeof(u32), &svcpu->last_inst, false);
+	if (vcpu->arch.last_inst == KVM_INST_FETCH_FAILED)
+		kvmppc_ld(vcpu, &pc, sizeof(u32), &vcpu->arch.last_inst, false);
 
-	r = svcpu->last_inst;
-	svcpu_put(svcpu);
-	return r;
+	return vcpu->arch.last_inst;
 }
 
 /*
@@ -344,26 +280,34 @@ static inline u32 kvmppc_get_last_inst(struct kvm_vcpu *vcpu)
 static inline u32 kvmppc_get_last_sc(struct kvm_vcpu *vcpu)
 {
 	ulong pc = kvmppc_get_pc(vcpu) - 4;
-	struct kvmppc_book3s_shadow_vcpu *svcpu = svcpu_get(vcpu);
-	u32 r;
 
 	/* Load the instruction manually if it failed to do so in the
 	 * exit path */
-	if (svcpu->last_inst == KVM_INST_FETCH_FAILED)
-		kvmppc_ld(vcpu, &pc, sizeof(u32), &svcpu->last_inst, false);
+	if (vcpu->arch.last_inst == KVM_INST_FETCH_FAILED)
+		kvmppc_ld(vcpu, &pc, sizeof(u32), &vcpu->arch.last_inst, false);
 
-	r = svcpu->last_inst;
-	svcpu_put(svcpu);
-	return r;
+	return vcpu->arch.last_inst;
 }
 
 static inline ulong kvmppc_get_fault_dar(struct kvm_vcpu *vcpu)
 {
-	struct kvmppc_book3s_shadow_vcpu *svcpu = svcpu_get(vcpu);
-	ulong r;
-	r = svcpu->fault_dar;
-	svcpu_put(svcpu);
-	return r;
+	return vcpu->arch.fault_dar;
+}
+
+#ifdef CONFIG_KVM_BOOK3S_PR
+
+static inline unsigned long kvmppc_interrupt_offset(struct kvm_vcpu *vcpu)
+{
+	return to_book3s(vcpu)->hior;
+}
+
+static inline void kvmppc_update_int_pending(struct kvm_vcpu *vcpu,
+			unsigned long pending_now, unsigned long old_pending)
+{
+	if (pending_now)
+		vcpu->arch.shared->int_pending = 1;
+	else if (old_pending)
+		vcpu->arch.shared->int_pending = 0;
 }
 
 static inline bool kvmppc_critical_section(struct kvm_vcpu *vcpu)
@@ -397,100 +341,6 @@ static inline void kvmppc_update_int_pending(struct kvm_vcpu *vcpu,
 {
 }
 
-static inline void kvmppc_set_gpr(struct kvm_vcpu *vcpu, int num, ulong val)
-{
-	vcpu->arch.gpr[num] = val;
-}
-
-static inline ulong kvmppc_get_gpr(struct kvm_vcpu *vcpu, int num)
-{
-	return vcpu->arch.gpr[num];
-}
-
-static inline void kvmppc_set_cr(struct kvm_vcpu *vcpu, u32 val)
-{
-	vcpu->arch.cr = val;
-}
-
-static inline u32 kvmppc_get_cr(struct kvm_vcpu *vcpu)
-{
-	return vcpu->arch.cr;
-}
-
-static inline void kvmppc_set_xer(struct kvm_vcpu *vcpu, u32 val)
-{
-	vcpu->arch.xer = val;
-}
-
-static inline u32 kvmppc_get_xer(struct kvm_vcpu *vcpu)
-{
-	return vcpu->arch.xer;
-}
-
-static inline void kvmppc_set_ctr(struct kvm_vcpu *vcpu, ulong val)
-{
-	vcpu->arch.ctr = val;
-}
-
-static inline ulong kvmppc_get_ctr(struct kvm_vcpu *vcpu)
-{
-	return vcpu->arch.ctr;
-}
-
-static inline void kvmppc_set_lr(struct kvm_vcpu *vcpu, ulong val)
-{
-	vcpu->arch.lr = val;
-}
-
-static inline ulong kvmppc_get_lr(struct kvm_vcpu *vcpu)
-{
-	return vcpu->arch.lr;
-}
-
-static inline void kvmppc_set_pc(struct kvm_vcpu *vcpu, ulong val)
-{
-	vcpu->arch.pc = val;
-}
-
-static inline ulong kvmppc_get_pc(struct kvm_vcpu *vcpu)
-{
-	return vcpu->arch.pc;
-}
-
-static inline u32 kvmppc_get_last_inst(struct kvm_vcpu *vcpu)
-{
-	ulong pc = kvmppc_get_pc(vcpu);
-
-	/* Load the instruction manually if it failed to do so in the
-	 * exit path */
-	if (vcpu->arch.last_inst == KVM_INST_FETCH_FAILED)
-		kvmppc_ld(vcpu, &pc, sizeof(u32), &vcpu->arch.last_inst, false);
-
-	return vcpu->arch.last_inst;
-}
-
-/*
- * Like kvmppc_get_last_inst(), but for fetching a sc instruction.
- * Because the sc instruction sets SRR0 to point to the following
- * instruction, we have to fetch from pc - 4.
- */
-static inline u32 kvmppc_get_last_sc(struct kvm_vcpu *vcpu)
-{
-	ulong pc = kvmppc_get_pc(vcpu) - 4;
-
-	/* Load the instruction manually if it failed to do so in the
-	 * exit path */
-	if (vcpu->arch.last_inst == KVM_INST_FETCH_FAILED)
-		kvmppc_ld(vcpu, &pc, sizeof(u32), &vcpu->arch.last_inst, false);
-
-	return vcpu->arch.last_inst;
-}
-
-static inline ulong kvmppc_get_fault_dar(struct kvm_vcpu *vcpu)
-{
-	return vcpu->arch.fault_dar;
-}
-
 static inline bool kvmppc_critical_section(struct kvm_vcpu *vcpu)
 {
 	return false;
diff --git a/arch/powerpc/include/asm/kvm_book3s_asm.h b/arch/powerpc/include/asm/kvm_book3s_asm.h
index 22f46061ae8..62737113c2b 100644
--- a/arch/powerpc/include/asm/kvm_book3s_asm.h
+++ b/arch/powerpc/include/asm/kvm_book3s_asm.h
@@ -109,14 +109,14 @@ struct kvmppc_book3s_shadow_vcpu {
 	ulong gpr[14];
 	u32 cr;
 	u32 xer;
-
-	u32 fault_dsisr;
-	u32 last_inst;
 	ulong ctr;
 	ulong lr;
 	ulong pc;
+
 	ulong shadow_srr1;
 	ulong fault_dar;
+	u32 fault_dsisr;
+	u32 last_inst;
 
 #ifdef CONFIG_PPC_BOOK3S_32
 	u32     sr[16];			/* Guest SRs */
diff --git a/arch/powerpc/include/asm/kvm_host.h b/arch/powerpc/include/asm/kvm_host.h
index b1e8f2ba2a9..f48f3f09177 100644
--- a/arch/powerpc/include/asm/kvm_host.h
+++ b/arch/powerpc/include/asm/kvm_host.h
@@ -463,6 +463,7 @@ struct kvm_vcpu_arch {
 	ulong dabr;
 	ulong cfar;
 	ulong ppr;
+	ulong shadow_srr1;
 #endif
 	u32 vrsave; /* also USPRG0 */
 	u32 mmucr;
diff --git a/arch/powerpc/kernel/asm-offsets.c b/arch/powerpc/kernel/asm-offsets.c
index 5a285efba17..fda7f4020a3 100644
--- a/arch/powerpc/kernel/asm-offsets.c
+++ b/arch/powerpc/kernel/asm-offsets.c
@@ -520,6 +520,7 @@ int main(void)
 	DEFINE(VCPU_PTID, offsetof(struct kvm_vcpu, arch.ptid));
 	DEFINE(VCPU_CFAR, offsetof(struct kvm_vcpu, arch.cfar));
 	DEFINE(VCPU_PPR, offsetof(struct kvm_vcpu, arch.ppr));
+	DEFINE(VCPU_SHADOW_SRR1, offsetof(struct kvm_vcpu, arch.shadow_srr1));
 	DEFINE(VCORE_ENTRY_EXIT, offsetof(struct kvmppc_vcore, entry_exit_count));
 	DEFINE(VCORE_NAP_COUNT, offsetof(struct kvmppc_vcore, nap_count));
 	DEFINE(VCORE_IN_GUEST, offsetof(struct kvmppc_vcore, in_guest));
@@ -527,14 +528,13 @@ int main(void)
 	DEFINE(VCORE_TB_OFFSET, offsetof(struct kvmppc_vcore, tb_offset));
 	DEFINE(VCORE_LPCR, offsetof(struct kvmppc_vcore, lpcr));
 	DEFINE(VCORE_PCR, offsetof(struct kvmppc_vcore, pcr));
-	DEFINE(VCPU_SVCPU, offsetof(struct kvmppc_vcpu_book3s, shadow_vcpu) -
-			   offsetof(struct kvmppc_vcpu_book3s, vcpu));
 	DEFINE(VCPU_SLB_E, offsetof(struct kvmppc_slb, orige));
 	DEFINE(VCPU_SLB_V, offsetof(struct kvmppc_slb, origv));
 	DEFINE(VCPU_SLB_SIZE, sizeof(struct kvmppc_slb));
 
 #ifdef CONFIG_PPC_BOOK3S_64
 #ifdef CONFIG_KVM_BOOK3S_PR
+	DEFINE(PACA_SVCPU, offsetof(struct paca_struct, shadow_vcpu));
 # define SVCPU_FIELD(x, f)	DEFINE(x, offsetof(struct paca_struct, shadow_vcpu.f))
 #else
 # define SVCPU_FIELD(x, f)
diff --git a/arch/powerpc/kvm/book3s_emulate.c b/arch/powerpc/kvm/book3s_emulate.c
index 360ce68c980..34044b111da 100644
--- a/arch/powerpc/kvm/book3s_emulate.c
+++ b/arch/powerpc/kvm/book3s_emulate.c
@@ -267,12 +267,9 @@ int kvmppc_core_emulate_op(struct kvm_run *run, struct kvm_vcpu *vcpu,
 
 			r = kvmppc_st(vcpu, &addr, 32, zeros, true);
 			if ((r == -ENOENT) || (r == -EPERM)) {
-				struct kvmppc_book3s_shadow_vcpu *svcpu;
-
-				svcpu = svcpu_get(vcpu);
 				*advance = 0;
 				vcpu->arch.shared->dar = vaddr;
-				svcpu->fault_dar = vaddr;
+				vcpu->arch.fault_dar = vaddr;
 
 				dsisr = DSISR_ISSTORE;
 				if (r == -ENOENT)
@@ -281,8 +278,7 @@ int kvmppc_core_emulate_op(struct kvm_run *run, struct kvm_vcpu *vcpu,
 					dsisr |= DSISR_PROTFAULT;
 
 				vcpu->arch.shared->dsisr = dsisr;
-				svcpu->fault_dsisr = dsisr;
-				svcpu_put(svcpu);
+				vcpu->arch.fault_dsisr = dsisr;
 
 				kvmppc_book3s_queue_irqprio(vcpu,
 					BOOK3S_INTERRUPT_DATA_STORAGE);
diff --git a/arch/powerpc/kvm/book3s_interrupts.S b/arch/powerpc/kvm/book3s_interrupts.S
index 17cfae5497a..d4e30d8fa82 100644
--- a/arch/powerpc/kvm/book3s_interrupts.S
+++ b/arch/powerpc/kvm/book3s_interrupts.S
@@ -26,8 +26,12 @@
 
 #if defined(CONFIG_PPC_BOOK3S_64)
 #define FUNC(name) 		GLUE(.,name)
+#define GET_SHADOW_VCPU(reg)    addi	reg, r13, PACA_SVCPU
+
 #elif defined(CONFIG_PPC_BOOK3S_32)
 #define FUNC(name)		name
+#define GET_SHADOW_VCPU(reg)	lwz     reg, (THREAD + THREAD_KVM_SVCPU)(r2)
+
 #endif /* CONFIG_PPC_BOOK3S_XX */
 
 #define VCPU_LOAD_NVGPRS(vcpu) \
@@ -87,8 +91,14 @@ kvm_start_entry:
 	VCPU_LOAD_NVGPRS(r4)
 
 kvm_start_lightweight:
+	/* Copy registers into shadow vcpu so we can access them in real mode */
+	GET_SHADOW_VCPU(r3)
+	bl	FUNC(kvmppc_copy_to_svcpu)
+	nop
+	REST_GPR(4, r1)
 
 #ifdef CONFIG_PPC_BOOK3S_64
+	/* Get the dcbz32 flag */
 	PPC_LL	r3, VCPU_HFLAGS(r4)
 	rldicl	r3, r3, 0, 63		/* r3 &= 1 */
 	stb	r3, HSTATE_RESTORE_HID5(r13)
@@ -125,18 +135,31 @@ kvmppc_handler_highmem:
 	 *
 	 */
 
-	/* R7 = vcpu */
-	PPC_LL	r7, GPR4(r1)
+	/* Transfer reg values from shadow vcpu back to vcpu struct */
+	/* On 64-bit, interrupts are still off at this point */
+	PPC_LL	r3, GPR4(r1)		/* vcpu pointer */
+	GET_SHADOW_VCPU(r4)
+	bl	FUNC(kvmppc_copy_from_svcpu)
+	nop
 
 #ifdef CONFIG_PPC_BOOK3S_64
+	/* Re-enable interrupts */
+	ld	r3, HSTATE_HOST_MSR(r13)
+	ori	r3, r3, MSR_EE
+	MTMSR_EERI(r3)
+
 	/*
 	 * Reload kernel SPRG3 value.
 	 * No need to save guest value as usermode can't modify SPRG3.
 	 */
 	ld	r3, PACA_SPRG3(r13)
 	mtspr	SPRN_SPRG3, r3
+
 #endif /* CONFIG_PPC_BOOK3S_64 */
 
+	/* R7 = vcpu */
+	PPC_LL	r7, GPR4(r1)
+
 	PPC_STL	r14, VCPU_GPR(R14)(r7)
 	PPC_STL	r15, VCPU_GPR(R15)(r7)
 	PPC_STL	r16, VCPU_GPR(R16)(r7)
diff --git a/arch/powerpc/kvm/book3s_pr.c b/arch/powerpc/kvm/book3s_pr.c
index 8d45f185241..228a9baffd9 100644
--- a/arch/powerpc/kvm/book3s_pr.c
+++ b/arch/powerpc/kvm/book3s_pr.c
@@ -61,8 +61,6 @@ void kvmppc_core_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
 #ifdef CONFIG_PPC_BOOK3S_64
 	struct kvmppc_book3s_shadow_vcpu *svcpu = svcpu_get(vcpu);
 	memcpy(svcpu->slb, to_book3s(vcpu)->slb_shadow, sizeof(svcpu->slb));
-	memcpy(&get_paca()->shadow_vcpu, to_book3s(vcpu)->shadow_vcpu,
-	       sizeof(get_paca()->shadow_vcpu));
 	svcpu->slb_max = to_book3s(vcpu)->slb_shadow_max;
 	svcpu_put(svcpu);
 #endif
@@ -77,8 +75,6 @@ void kvmppc_core_vcpu_put(struct kvm_vcpu *vcpu)
 #ifdef CONFIG_PPC_BOOK3S_64
 	struct kvmppc_book3s_shadow_vcpu *svcpu = svcpu_get(vcpu);
 	memcpy(to_book3s(vcpu)->slb_shadow, svcpu->slb, sizeof(svcpu->slb));
-	memcpy(to_book3s(vcpu)->shadow_vcpu, &get_paca()->shadow_vcpu,
-	       sizeof(get_paca()->shadow_vcpu));
 	to_book3s(vcpu)->slb_shadow_max = svcpu->slb_max;
 	svcpu_put(svcpu);
 #endif
@@ -87,6 +83,60 @@ void kvmppc_core_vcpu_put(struct kvm_vcpu *vcpu)
 	vcpu->cpu = -1;
 }
 
+/* Copy data needed by real-mode code from vcpu to shadow vcpu */
+void kvmppc_copy_to_svcpu(struct kvmppc_book3s_shadow_vcpu *svcpu,
+			  struct kvm_vcpu *vcpu)
+{
+	svcpu->gpr[0] = vcpu->arch.gpr[0];
+	svcpu->gpr[1] = vcpu->arch.gpr[1];
+	svcpu->gpr[2] = vcpu->arch.gpr[2];
+	svcpu->gpr[3] = vcpu->arch.gpr[3];
+	svcpu->gpr[4] = vcpu->arch.gpr[4];
+	svcpu->gpr[5] = vcpu->arch.gpr[5];
+	svcpu->gpr[6] = vcpu->arch.gpr[6];
+	svcpu->gpr[7] = vcpu->arch.gpr[7];
+	svcpu->gpr[8] = vcpu->arch.gpr[8];
+	svcpu->gpr[9] = vcpu->arch.gpr[9];
+	svcpu->gpr[10] = vcpu->arch.gpr[10];
+	svcpu->gpr[11] = vcpu->arch.gpr[11];
+	svcpu->gpr[12] = vcpu->arch.gpr[12];
+	svcpu->gpr[13] = vcpu->arch.gpr[13];
+	svcpu->cr  = vcpu->arch.cr;
+	svcpu->xer = vcpu->arch.xer;
+	svcpu->ctr = vcpu->arch.ctr;
+	svcpu->lr  = vcpu->arch.lr;
+	svcpu->pc  = vcpu->arch.pc;
+}
+
+/* Copy data touched by real-mode code from shadow vcpu back to vcpu */
+void kvmppc_copy_from_svcpu(struct kvm_vcpu *vcpu,
+			    struct kvmppc_book3s_shadow_vcpu *svcpu)
+{
+	vcpu->arch.gpr[0] = svcpu->gpr[0];
+	vcpu->arch.gpr[1] = svcpu->gpr[1];
+	vcpu->arch.gpr[2] = svcpu->gpr[2];
+	vcpu->arch.gpr[3] = svcpu->gpr[3];
+	vcpu->arch.gpr[4] = svcpu->gpr[4];
+	vcpu->arch.gpr[5] = svcpu->gpr[5];
+	vcpu->arch.gpr[6] = svcpu->gpr[6];
+	vcpu->arch.gpr[7] = svcpu->gpr[7];
+	vcpu->arch.gpr[8] = svcpu->gpr[8];
+	vcpu->arch.gpr[9] = svcpu->gpr[9];
+	vcpu->arch.gpr[10] = svcpu->gpr[10];
+	vcpu->arch.gpr[11] = svcpu->gpr[11];
+	vcpu->arch.gpr[12] = svcpu->gpr[12];
+	vcpu->arch.gpr[13] = svcpu->gpr[13];
+	vcpu->arch.cr  = svcpu->cr;
+	vcpu->arch.xer = svcpu->xer;
+	vcpu->arch.ctr = svcpu->ctr;
+	vcpu->arch.lr  = svcpu->lr;
+	vcpu->arch.pc  = svcpu->pc;
+	vcpu->arch.shadow_srr1 = svcpu->shadow_srr1;
+	vcpu->arch.fault_dar   = svcpu->fault_dar;
+	vcpu->arch.fault_dsisr = svcpu->fault_dsisr;
+	vcpu->arch.last_inst   = svcpu->last_inst;
+}
+
 int kvmppc_core_check_requests(struct kvm_vcpu *vcpu)
 {
 	int r = 1; /* Indicate we want to get back into the guest */
@@ -388,22 +438,18 @@ int kvmppc_handle_pagefault(struct kvm_run *run, struct kvm_vcpu *vcpu,
 
 	if (page_found == -ENOENT) {
 		/* Page not found in guest PTE entries */
-		struct kvmppc_book3s_shadow_vcpu *svcpu = svcpu_get(vcpu);
 		vcpu->arch.shared->dar = kvmppc_get_fault_dar(vcpu);
-		vcpu->arch.shared->dsisr = svcpu->fault_dsisr;
+		vcpu->arch.shared->dsisr = vcpu->arch.fault_dsisr;
 		vcpu->arch.shared->msr |=
-			(svcpu->shadow_srr1 & 0x00000000f8000000ULL);
-		svcpu_put(svcpu);
+			vcpu->arch.shadow_srr1 & 0x00000000f8000000ULL;
 		kvmppc_book3s_queue_irqprio(vcpu, vec);
 	} else if (page_found == -EPERM) {
 		/* Storage protection */
-		struct kvmppc_book3s_shadow_vcpu *svcpu = svcpu_get(vcpu);
 		vcpu->arch.shared->dar = kvmppc_get_fault_dar(vcpu);
-		vcpu->arch.shared->dsisr = svcpu->fault_dsisr & ~DSISR_NOHPTE;
+		vcpu->arch.shared->dsisr = vcpu->arch.fault_dsisr & ~DSISR_NOHPTE;
 		vcpu->arch.shared->dsisr |= DSISR_PROTFAULT;
 		vcpu->arch.shared->msr |=
-			svcpu->shadow_srr1 & 0x00000000f8000000ULL;
-		svcpu_put(svcpu);
+			vcpu->arch.shadow_srr1 & 0x00000000f8000000ULL;
 		kvmppc_book3s_queue_irqprio(vcpu, vec);
 	} else if (page_found == -EINVAL) {
 		/* Page not found in guest SLB */
@@ -645,21 +691,26 @@ int kvmppc_handle_exit(struct kvm_run *run, struct kvm_vcpu *vcpu,
 	switch (exit_nr) {
 	case BOOK3S_INTERRUPT_INST_STORAGE:
 	{
-		struct kvmppc_book3s_shadow_vcpu *svcpu = svcpu_get(vcpu);
-		ulong shadow_srr1 = svcpu->shadow_srr1;
+		ulong shadow_srr1 = vcpu->arch.shadow_srr1;
 		vcpu->stat.pf_instruc++;
 
 #ifdef CONFIG_PPC_BOOK3S_32
 		/* We set segments as unused segments when invalidating them. So
 		 * treat the respective fault as segment fault. */
-		if (svcpu->sr[kvmppc_get_pc(vcpu) >> SID_SHIFT] == SR_INVALID) {
-			kvmppc_mmu_map_segment(vcpu, kvmppc_get_pc(vcpu));
-			r = RESUME_GUEST;
+		{
+			struct kvmppc_book3s_shadow_vcpu *svcpu;
+			u32 sr;
+
+			svcpu = svcpu_get(vcpu);
+			sr = svcpu->sr[kvmppc_get_pc(vcpu) >> SID_SHIFT];
 			svcpu_put(svcpu);
-			break;
+			if (sr == SR_INVALID) {
+				kvmppc_mmu_map_segment(vcpu, kvmppc_get_pc(vcpu));
+				r = RESUME_GUEST;
+				break;
+			}
 		}
 #endif
-		svcpu_put(svcpu);
 
 		/* only care about PTEG not found errors, but leave NX alone */
 		if (shadow_srr1 & 0x40000000) {
@@ -684,21 +735,26 @@ int kvmppc_handle_exit(struct kvm_run *run, struct kvm_vcpu *vcpu,
 	case BOOK3S_INTERRUPT_DATA_STORAGE:
 	{
 		ulong dar = kvmppc_get_fault_dar(vcpu);
-		struct kvmppc_book3s_shadow_vcpu *svcpu = svcpu_get(vcpu);
-		u32 fault_dsisr = svcpu->fault_dsisr;
+		u32 fault_dsisr = vcpu->arch.fault_dsisr;
 		vcpu->stat.pf_storage++;
 
 #ifdef CONFIG_PPC_BOOK3S_32
 		/* We set segments as unused segments when invalidating them. So
 		 * treat the respective fault as segment fault. */
-		if ((svcpu->sr[dar >> SID_SHIFT]) == SR_INVALID) {
-			kvmppc_mmu_map_segment(vcpu, dar);
-			r = RESUME_GUEST;
+		{
+			struct kvmppc_book3s_shadow_vcpu *svcpu;
+			u32 sr;
+
+			svcpu = svcpu_get(vcpu);
+			sr = svcpu->sr[dar >> SID_SHIFT];
 			svcpu_put(svcpu);
-			break;
+			if (sr == SR_INVALID) {
+				kvmppc_mmu_map_segment(vcpu, dar);
+				r = RESUME_GUEST;
+				break;
+			}
 		}
 #endif
-		svcpu_put(svcpu);
 
 		/* The only case we need to handle is missing shadow PTEs */
 		if (fault_dsisr & DSISR_NOHPTE) {
@@ -745,13 +801,10 @@ int kvmppc_handle_exit(struct kvm_run *run, struct kvm_vcpu *vcpu,
 	case BOOK3S_INTERRUPT_H_EMUL_ASSIST:
 	{
 		enum emulation_result er;
-		struct kvmppc_book3s_shadow_vcpu *svcpu;
 		ulong flags;
 
 program_interrupt:
-		svcpu = svcpu_get(vcpu);
-		flags = svcpu->shadow_srr1 & 0x1f0000ull;
-		svcpu_put(svcpu);
+		flags = vcpu->arch.shadow_srr1 & 0x1f0000ull;
 
 		if (vcpu->arch.shared->msr & MSR_PR) {
 #ifdef EXIT_DEBUG
@@ -883,9 +936,7 @@ program_interrupt:
 		break;
 	default:
 	{
-		struct kvmppc_book3s_shadow_vcpu *svcpu = svcpu_get(vcpu);
-		ulong shadow_srr1 = svcpu->shadow_srr1;
-		svcpu_put(svcpu);
+		ulong shadow_srr1 = vcpu->arch.shadow_srr1;
 		/* Ugh - bork here! What did we get? */
 		printk(KERN_EMERG "exit_nr=0x%x | pc=0x%lx | msr=0x%lx\n",
 			exit_nr, kvmppc_get_pc(vcpu), shadow_srr1);
@@ -1060,11 +1111,12 @@ struct kvm_vcpu *kvmppc_core_vcpu_create(struct kvm *kvm, unsigned int id)
 	if (!vcpu_book3s)
 		goto out;
 
+#ifdef CONFIG_KVM_BOOK3S_32
 	vcpu_book3s->shadow_vcpu =
 		kzalloc(sizeof(*vcpu_book3s->shadow_vcpu), GFP_KERNEL);
 	if (!vcpu_book3s->shadow_vcpu)
 		goto free_vcpu;
-
+#endif
 	vcpu = &vcpu_book3s->vcpu;
 	err = kvm_vcpu_init(vcpu, kvm, id);
 	if (err)
@@ -1098,8 +1150,10 @@ struct kvm_vcpu *kvmppc_core_vcpu_create(struct kvm *kvm, unsigned int id)
 uninit_vcpu:
 	kvm_vcpu_uninit(vcpu);
 free_shadow_vcpu:
+#ifdef CONFIG_KVM_BOOK3S_32
 	kfree(vcpu_book3s->shadow_vcpu);
 free_vcpu:
+#endif
 	vfree(vcpu_book3s);
 out:
 	return ERR_PTR(err);
diff --git a/arch/powerpc/kvm/book3s_rmhandlers.S b/arch/powerpc/kvm/book3s_rmhandlers.S
index 8f7633e3afb..cd59a3a3848 100644
--- a/arch/powerpc/kvm/book3s_rmhandlers.S
+++ b/arch/powerpc/kvm/book3s_rmhandlers.S
@@ -179,11 +179,15 @@ _GLOBAL(kvmppc_entry_trampoline)
 
 	li	r6, MSR_IR | MSR_DR
 	andc	r6, r5, r6	/* Clear DR and IR in MSR value */
+#ifdef CONFIG_PPC_BOOK3S_32
 	/*
 	 * Set EE in HOST_MSR so that it's enabled when we get into our
-	 * C exit handler function
+	 * C exit handler function.  On 64-bit we delay enabling
+	 * interrupts until we have finished transferring stuff
+	 * to or from the PACA.
 	 */
 	ori	r5, r5, MSR_EE
+#endif
 	mtsrr0	r7
 	mtsrr1	r6
 	RFI
diff --git a/arch/powerpc/kvm/trace.h b/arch/powerpc/kvm/trace.h
index e326489a542..a088e9a8c10 100644
--- a/arch/powerpc/kvm/trace.h
+++ b/arch/powerpc/kvm/trace.h
@@ -101,17 +101,12 @@ TRACE_EVENT(kvm_exit,
 	),
 
 	TP_fast_assign(
-#ifdef CONFIG_KVM_BOOK3S_PR
-		struct kvmppc_book3s_shadow_vcpu *svcpu;
-#endif
 		__entry->exit_nr	= exit_nr;
 		__entry->pc		= kvmppc_get_pc(vcpu);
 		__entry->dar		= kvmppc_get_fault_dar(vcpu);
 		__entry->msr		= vcpu->arch.shared->msr;
 #ifdef CONFIG_KVM_BOOK3S_PR
-		svcpu = svcpu_get(vcpu);
-		__entry->srr1		= svcpu->shadow_srr1;
-		svcpu_put(svcpu);
+		__entry->srr1		= vcpu->arch.shadow_srr1;
 #endif
 		__entry->last_inst	= vcpu->arch.last_inst;
 	),
-- 
cgit v1.2.3-70-g09d2


From a4a0f2524acc2c602cadd8e743be19d86f3a746b Mon Sep 17 00:00:00 2001
From: Paul Mackerras <paulus@samba.org>
Date: Fri, 20 Sep 2013 14:52:44 +1000
Subject: KVM: PPC: Book3S PR: Allow guest to use 64k pages

This adds the code to interpret 64k HPTEs in the guest hashed page
table (HPT), 64k SLB entries, and to tell the guest about 64k pages
in kvm_vm_ioctl_get_smmu_info().  Guest 64k pages are still shadowed
by 4k pages.

This also adds another hash table to the four we have already in
book3s_mmu_hpte.c to allow us to find all the PTEs that we have
instantiated that match a given 64k guest page.

The tlbie instruction changed starting with POWER6 to use a bit in
the RB operand to indicate large page invalidations, and to use other
RB bits to indicate the base and actual page sizes and the segment
size.  64k pages came in slightly earlier, with POWER5++.
We use one bit in vcpu->arch.hflags to indicate that the emulated
cpu supports 64k pages, and another to indicate that it has the new
tlbie definition.

The KVM_PPC_GET_SMMU_INFO ioctl presents a bit of a problem, because
the MMU capabilities depend on which CPU model we're emulating, but it
is a VM ioctl not a VCPU ioctl and therefore doesn't get passed a VCPU
fd.  In addition, commonly-used userspace (QEMU) calls it before
setting the PVR for any VCPU.  Therefore, as a best effort we look at
the first vcpu in the VM and return 64k pages or not depending on its
capabilities.  We also make the PVR default to the host PVR on recent
CPUs that support 1TB segments (and therefore multiple page sizes as
well) so that KVM_PPC_GET_SMMU_INFO will include 64k page and 1TB
segment support on those CPUs.

Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Alexander Graf <agraf@suse.de>
---
 arch/powerpc/include/asm/kvm_asm.h    |  2 +
 arch/powerpc/include/asm/kvm_book3s.h |  6 +++
 arch/powerpc/include/asm/kvm_host.h   |  4 ++
 arch/powerpc/kvm/book3s_64_mmu.c      | 92 +++++++++++++++++++++++++++++++----
 arch/powerpc/kvm/book3s_mmu_hpte.c    | 50 +++++++++++++++++++
 arch/powerpc/kvm/book3s_pr.c          | 58 +++++++++++++++++++---
 6 files changed, 197 insertions(+), 15 deletions(-)

(limited to 'arch/powerpc/kvm')

diff --git a/arch/powerpc/include/asm/kvm_asm.h b/arch/powerpc/include/asm/kvm_asm.h
index 851bac7afa4..e2d4d467ee9 100644
--- a/arch/powerpc/include/asm/kvm_asm.h
+++ b/arch/powerpc/include/asm/kvm_asm.h
@@ -123,6 +123,8 @@
 #define BOOK3S_HFLAG_SLB			0x2
 #define BOOK3S_HFLAG_PAIRED_SINGLE		0x4
 #define BOOK3S_HFLAG_NATIVE_PS			0x8
+#define BOOK3S_HFLAG_MULTI_PGSIZE		0x10
+#define BOOK3S_HFLAG_NEW_TLBIE			0x20
 
 #define RESUME_FLAG_NV          (1<<0)  /* Reload guest nonvolatile state? */
 #define RESUME_FLAG_HOST        (1<<1)  /* Resume host? */
diff --git a/arch/powerpc/include/asm/kvm_book3s.h b/arch/powerpc/include/asm/kvm_book3s.h
index 40f22d9c704..1d4a1202e2d 100644
--- a/arch/powerpc/include/asm/kvm_book3s.h
+++ b/arch/powerpc/include/asm/kvm_book3s.h
@@ -58,6 +58,9 @@ struct hpte_cache {
 	struct hlist_node list_pte_long;
 	struct hlist_node list_vpte;
 	struct hlist_node list_vpte_long;
+#ifdef CONFIG_PPC_BOOK3S_64
+	struct hlist_node list_vpte_64k;
+#endif
 	struct rcu_head rcu_head;
 	u64 host_vpn;
 	u64 pfn;
@@ -99,6 +102,9 @@ struct kvmppc_vcpu_book3s {
 	struct hlist_head hpte_hash_pte_long[HPTEG_HASH_NUM_PTE_LONG];
 	struct hlist_head hpte_hash_vpte[HPTEG_HASH_NUM_VPTE];
 	struct hlist_head hpte_hash_vpte_long[HPTEG_HASH_NUM_VPTE_LONG];
+#ifdef CONFIG_PPC_BOOK3S_64
+	struct hlist_head hpte_hash_vpte_64k[HPTEG_HASH_NUM_VPTE_64K];
+#endif
 	int hpte_cache_count;
 	spinlock_t mmu_lock;
 };
diff --git a/arch/powerpc/include/asm/kvm_host.h b/arch/powerpc/include/asm/kvm_host.h
index f48f3f09177..3d8b8a8921f 100644
--- a/arch/powerpc/include/asm/kvm_host.h
+++ b/arch/powerpc/include/asm/kvm_host.h
@@ -68,10 +68,12 @@ extern void kvm_set_spte_hva(struct kvm *kvm, unsigned long hva, pte_t pte);
 #define HPTEG_HASH_BITS_PTE_LONG	12
 #define HPTEG_HASH_BITS_VPTE		13
 #define HPTEG_HASH_BITS_VPTE_LONG	5
+#define HPTEG_HASH_BITS_VPTE_64K	11
 #define HPTEG_HASH_NUM_PTE		(1 << HPTEG_HASH_BITS_PTE)
 #define HPTEG_HASH_NUM_PTE_LONG		(1 << HPTEG_HASH_BITS_PTE_LONG)
 #define HPTEG_HASH_NUM_VPTE		(1 << HPTEG_HASH_BITS_VPTE)
 #define HPTEG_HASH_NUM_VPTE_LONG	(1 << HPTEG_HASH_BITS_VPTE_LONG)
+#define HPTEG_HASH_NUM_VPTE_64K		(1 << HPTEG_HASH_BITS_VPTE_64K)
 
 /* Physical Address Mask - allowed range of real mode RAM access */
 #define KVM_PAM			0x0fffffffffffffffULL
@@ -327,6 +329,7 @@ struct kvmppc_pte {
 	bool may_read		: 1;
 	bool may_write		: 1;
 	bool may_execute	: 1;
+	u8 page_size;		/* MMU_PAGE_xxx */
 };
 
 struct kvmppc_mmu {
@@ -359,6 +362,7 @@ struct kvmppc_slb {
 	bool large	: 1;	/* PTEs are 16MB */
 	bool tb		: 1;	/* 1TB segment */
 	bool class	: 1;
+	u8 base_page_size;	/* MMU_PAGE_xxx */
 };
 
 # ifdef CONFIG_PPC_FSL_BOOK3E
diff --git a/arch/powerpc/kvm/book3s_64_mmu.c b/arch/powerpc/kvm/book3s_64_mmu.c
index 7e345e00661..8277264a0bc 100644
--- a/arch/powerpc/kvm/book3s_64_mmu.c
+++ b/arch/powerpc/kvm/book3s_64_mmu.c
@@ -107,9 +107,20 @@ static u64 kvmppc_mmu_book3s_64_ea_to_vp(struct kvm_vcpu *vcpu, gva_t eaddr,
 	return kvmppc_slb_calc_vpn(slb, eaddr);
 }
 
+static int mmu_pagesize(int mmu_pg)
+{
+	switch (mmu_pg) {
+	case MMU_PAGE_64K:
+		return 16;
+	case MMU_PAGE_16M:
+		return 24;
+	}
+	return 12;
+}
+
 static int kvmppc_mmu_book3s_64_get_pagesize(struct kvmppc_slb *slbe)
 {
-	return slbe->large ? 24 : 12;
+	return mmu_pagesize(slbe->base_page_size);
 }
 
 static u32 kvmppc_mmu_book3s_64_get_page(struct kvmppc_slb *slbe, gva_t eaddr)
@@ -166,14 +177,34 @@ static u64 kvmppc_mmu_book3s_64_get_avpn(struct kvmppc_slb *slbe, gva_t eaddr)
 	avpn = kvmppc_mmu_book3s_64_get_page(slbe, eaddr);
 	avpn |= slbe->vsid << (kvmppc_slb_sid_shift(slbe) - p);
 
-	if (p < 24)
-		avpn >>= ((80 - p) - 56) - 8;
+	if (p < 16)
+		avpn >>= ((80 - p) - 56) - 8;	/* 16 - p */
 	else
-		avpn <<= 8;
+		avpn <<= p - 16;
 
 	return avpn;
 }
 
+/*
+ * Return page size encoded in the second word of a HPTE, or
+ * -1 for an invalid encoding for the base page size indicated by
+ * the SLB entry.  This doesn't handle mixed pagesize segments yet.
+ */
+static int decode_pagesize(struct kvmppc_slb *slbe, u64 r)
+{
+	switch (slbe->base_page_size) {
+	case MMU_PAGE_64K:
+		if ((r & 0xf000) == 0x1000)
+			return MMU_PAGE_64K;
+		break;
+	case MMU_PAGE_16M:
+		if ((r & 0xff000) == 0)
+			return MMU_PAGE_16M;
+		break;
+	}
+	return -1;
+}
+
 static int kvmppc_mmu_book3s_64_xlate(struct kvm_vcpu *vcpu, gva_t eaddr,
 				struct kvmppc_pte *gpte, bool data)
 {
@@ -189,6 +220,7 @@ static int kvmppc_mmu_book3s_64_xlate(struct kvm_vcpu *vcpu, gva_t eaddr,
 	u8 pp, key = 0;
 	bool found = false;
 	bool second = false;
+	int pgsize;
 	ulong mp_ea = vcpu->arch.magic_page_ea;
 
 	/* Magic page override */
@@ -202,6 +234,7 @@ static int kvmppc_mmu_book3s_64_xlate(struct kvm_vcpu *vcpu, gva_t eaddr,
 		gpte->may_execute = true;
 		gpte->may_read = true;
 		gpte->may_write = true;
+		gpte->page_size = MMU_PAGE_4K;
 
 		return 0;
 	}
@@ -222,6 +255,8 @@ static int kvmppc_mmu_book3s_64_xlate(struct kvm_vcpu *vcpu, gva_t eaddr,
 	v_mask = SLB_VSID_B | HPTE_V_AVPN | HPTE_V_LARGE | HPTE_V_VALID |
 		HPTE_V_SECONDARY;
 
+	pgsize = slbe->large ? MMU_PAGE_16M : MMU_PAGE_4K;
+
 do_second:
 	ptegp = kvmppc_mmu_book3s_64_get_pteg(vcpu_book3s, slbe, eaddr, second);
 	if (kvm_is_error_hva(ptegp))
@@ -240,6 +275,13 @@ do_second:
 	for (i=0; i<16; i+=2) {
 		/* Check all relevant fields of 1st dword */
 		if ((pteg[i] & v_mask) == v_val) {
+			/* If large page bit is set, check pgsize encoding */
+			if (slbe->large &&
+			    (vcpu->arch.hflags & BOOK3S_HFLAG_MULTI_PGSIZE)) {
+				pgsize = decode_pagesize(slbe, pteg[i+1]);
+				if (pgsize < 0)
+					continue;
+			}
 			found = true;
 			break;
 		}
@@ -256,13 +298,13 @@ do_second:
 	v = pteg[i];
 	r = pteg[i+1];
 	pp = (r & HPTE_R_PP) | key;
-	eaddr_mask = 0xFFF;
 
 	gpte->eaddr = eaddr;
 	gpte->vpage = kvmppc_mmu_book3s_64_ea_to_vp(vcpu, eaddr, data);
-	if (slbe->large)
-		eaddr_mask = 0xFFFFFF;
+
+	eaddr_mask = (1ull << mmu_pagesize(pgsize)) - 1;
 	gpte->raddr = (r & HPTE_R_RPN & ~eaddr_mask) | (eaddr & eaddr_mask);
+	gpte->page_size = pgsize;
 	gpte->may_execute = ((r & HPTE_R_N) ? false : true);
 	gpte->may_read = false;
 	gpte->may_write = false;
@@ -345,6 +387,21 @@ static void kvmppc_mmu_book3s_64_slbmte(struct kvm_vcpu *vcpu, u64 rs, u64 rb)
 	slbe->nx    = (rs & SLB_VSID_N) ? 1 : 0;
 	slbe->class = (rs & SLB_VSID_C) ? 1 : 0;
 
+	slbe->base_page_size = MMU_PAGE_4K;
+	if (slbe->large) {
+		if (vcpu->arch.hflags & BOOK3S_HFLAG_MULTI_PGSIZE) {
+			switch (rs & SLB_VSID_LP) {
+			case SLB_VSID_LP_00:
+				slbe->base_page_size = MMU_PAGE_16M;
+				break;
+			case SLB_VSID_LP_01:
+				slbe->base_page_size = MMU_PAGE_64K;
+				break;
+			}
+		} else
+			slbe->base_page_size = MMU_PAGE_16M;
+	}
+
 	slbe->orige = rb & (ESID_MASK | SLB_ESID_V);
 	slbe->origv = rs;
 
@@ -463,8 +520,25 @@ static void kvmppc_mmu_book3s_64_tlbie(struct kvm_vcpu *vcpu, ulong va,
 
 	dprintk("KVM MMU: tlbie(0x%lx)\n", va);
 
-	if (large)
-		mask = 0xFFFFFF000ULL;
+	/*
+	 * The tlbie instruction changed behaviour starting with
+	 * POWER6.  POWER6 and later don't have the large page flag
+	 * in the instruction but in the RB value, along with bits
+	 * indicating page and segment sizes.
+	 */
+	if (vcpu->arch.hflags & BOOK3S_HFLAG_NEW_TLBIE) {
+		/* POWER6 or later */
+		if (va & 1) {		/* L bit */
+			if ((va & 0xf000) == 0x1000)
+				mask = 0xFFFFFFFF0ULL;	/* 64k page */
+			else
+				mask = 0xFFFFFF000ULL;	/* 16M page */
+		}
+	} else {
+		/* older processors, e.g. PPC970 */
+		if (large)
+			mask = 0xFFFFFF000ULL;
+	}
 	kvmppc_mmu_pte_vflush(vcpu, va >> 12, mask);
 }
 
diff --git a/arch/powerpc/kvm/book3s_mmu_hpte.c b/arch/powerpc/kvm/book3s_mmu_hpte.c
index da8b13c4b77..d2d280b1677 100644
--- a/arch/powerpc/kvm/book3s_mmu_hpte.c
+++ b/arch/powerpc/kvm/book3s_mmu_hpte.c
@@ -56,6 +56,14 @@ static inline u64 kvmppc_mmu_hash_vpte_long(u64 vpage)
 		       HPTEG_HASH_BITS_VPTE_LONG);
 }
 
+#ifdef CONFIG_PPC_BOOK3S_64
+static inline u64 kvmppc_mmu_hash_vpte_64k(u64 vpage)
+{
+	return hash_64((vpage & 0xffffffff0ULL) >> 4,
+		       HPTEG_HASH_BITS_VPTE_64K);
+}
+#endif
+
 void kvmppc_mmu_hpte_cache_map(struct kvm_vcpu *vcpu, struct hpte_cache *pte)
 {
 	u64 index;
@@ -83,6 +91,13 @@ void kvmppc_mmu_hpte_cache_map(struct kvm_vcpu *vcpu, struct hpte_cache *pte)
 	hlist_add_head_rcu(&pte->list_vpte_long,
 			   &vcpu3s->hpte_hash_vpte_long[index]);
 
+#ifdef CONFIG_PPC_BOOK3S_64
+	/* Add to vPTE_64k list */
+	index = kvmppc_mmu_hash_vpte_64k(pte->pte.vpage);
+	hlist_add_head_rcu(&pte->list_vpte_64k,
+			   &vcpu3s->hpte_hash_vpte_64k[index]);
+#endif
+
 	spin_unlock(&vcpu3s->mmu_lock);
 }
 
@@ -113,6 +128,9 @@ static void invalidate_pte(struct kvm_vcpu *vcpu, struct hpte_cache *pte)
 	hlist_del_init_rcu(&pte->list_pte_long);
 	hlist_del_init_rcu(&pte->list_vpte);
 	hlist_del_init_rcu(&pte->list_vpte_long);
+#ifdef CONFIG_PPC_BOOK3S_64
+	hlist_del_init_rcu(&pte->list_vpte_64k);
+#endif
 
 	spin_unlock(&vcpu3s->mmu_lock);
 
@@ -219,6 +237,29 @@ static void kvmppc_mmu_pte_vflush_short(struct kvm_vcpu *vcpu, u64 guest_vp)
 	rcu_read_unlock();
 }
 
+#ifdef CONFIG_PPC_BOOK3S_64
+/* Flush with mask 0xffffffff0 */
+static void kvmppc_mmu_pte_vflush_64k(struct kvm_vcpu *vcpu, u64 guest_vp)
+{
+	struct kvmppc_vcpu_book3s *vcpu3s = to_book3s(vcpu);
+	struct hlist_head *list;
+	struct hpte_cache *pte;
+	u64 vp_mask = 0xffffffff0ULL;
+
+	list = &vcpu3s->hpte_hash_vpte_64k[
+		kvmppc_mmu_hash_vpte_64k(guest_vp)];
+
+	rcu_read_lock();
+
+	/* Check the list for matching entries and invalidate */
+	hlist_for_each_entry_rcu(pte, list, list_vpte_64k)
+		if ((pte->pte.vpage & vp_mask) == guest_vp)
+			invalidate_pte(vcpu, pte);
+
+	rcu_read_unlock();
+}
+#endif
+
 /* Flush with mask 0xffffff000 */
 static void kvmppc_mmu_pte_vflush_long(struct kvm_vcpu *vcpu, u64 guest_vp)
 {
@@ -249,6 +290,11 @@ void kvmppc_mmu_pte_vflush(struct kvm_vcpu *vcpu, u64 guest_vp, u64 vp_mask)
 	case 0xfffffffffULL:
 		kvmppc_mmu_pte_vflush_short(vcpu, guest_vp);
 		break;
+#ifdef CONFIG_PPC_BOOK3S_64
+	case 0xffffffff0ULL:
+		kvmppc_mmu_pte_vflush_64k(vcpu, guest_vp);
+		break;
+#endif
 	case 0xffffff000ULL:
 		kvmppc_mmu_pte_vflush_long(vcpu, guest_vp);
 		break;
@@ -320,6 +366,10 @@ int kvmppc_mmu_hpte_init(struct kvm_vcpu *vcpu)
 				  ARRAY_SIZE(vcpu3s->hpte_hash_vpte));
 	kvmppc_mmu_hpte_init_hash(vcpu3s->hpte_hash_vpte_long,
 				  ARRAY_SIZE(vcpu3s->hpte_hash_vpte_long));
+#ifdef CONFIG_PPC_BOOK3S_64
+	kvmppc_mmu_hpte_init_hash(vcpu3s->hpte_hash_vpte_64k,
+				  ARRAY_SIZE(vcpu3s->hpte_hash_vpte_64k));
+#endif
 
 	spin_lock_init(&vcpu3s->mmu_lock);
 
diff --git a/arch/powerpc/kvm/book3s_pr.c b/arch/powerpc/kvm/book3s_pr.c
index 228a9baffd9..6cc99583ed3 100644
--- a/arch/powerpc/kvm/book3s_pr.c
+++ b/arch/powerpc/kvm/book3s_pr.c
@@ -306,6 +306,23 @@ void kvmppc_set_pvr(struct kvm_vcpu *vcpu, u32 pvr)
 	if (!strcmp(cur_cpu_spec->platform, "ppc-cell-be"))
 		to_book3s(vcpu)->msr_mask &= ~(MSR_FE0 | MSR_FE1);
 
+	/*
+	 * If they're asking for POWER6 or later, set the flag
+	 * indicating that we can do multiple large page sizes
+	 * and 1TB segments.
+	 * Also set the flag that indicates that tlbie has the large
+	 * page bit in the RB operand instead of the instruction.
+	 */
+	switch (PVR_VER(pvr)) {
+	case PVR_POWER6:
+	case PVR_POWER7:
+	case PVR_POWER7p:
+	case PVR_POWER8:
+		vcpu->arch.hflags |= BOOK3S_HFLAG_MULTI_PGSIZE |
+			BOOK3S_HFLAG_NEW_TLBIE;
+		break;
+	}
+
 #ifdef CONFIG_PPC_BOOK3S_32
 	/* 32 bit Book3S always has 32 byte dcbz */
 	vcpu->arch.hflags |= BOOK3S_HFLAG_DCBZ32;
@@ -1130,8 +1147,14 @@ struct kvm_vcpu *kvmppc_core_vcpu_create(struct kvm *kvm, unsigned int id)
 	vcpu->arch.shared = (void *)(p + PAGE_SIZE - 4096);
 
 #ifdef CONFIG_PPC_BOOK3S_64
-	/* default to book3s_64 (970fx) */
+	/*
+	 * Default to the same as the host if we're on sufficiently
+	 * recent machine that we have 1TB segments;
+	 * otherwise default to PPC970FX.
+	 */
 	vcpu->arch.pvr = 0x3C0301;
+	if (mmu_has_feature(MMU_FTR_1T_SEGMENT))
+		vcpu->arch.pvr = mfspr(SPRN_PVR);
 #else
 	/* default to book3s_32 (750) */
 	vcpu->arch.pvr = 0x84202;
@@ -1317,7 +1340,10 @@ out:
 #ifdef CONFIG_PPC64
 int kvm_vm_ioctl_get_smmu_info(struct kvm *kvm, struct kvm_ppc_smmu_info *info)
 {
-	info->flags = KVM_PPC_1T_SEGMENTS;
+	long int i;
+	struct kvm_vcpu *vcpu;
+
+	info->flags = 0;
 
 	/* SLB is always 64 entries */
 	info->slb_size = 64;
@@ -1328,11 +1354,31 @@ int kvm_vm_ioctl_get_smmu_info(struct kvm *kvm, struct kvm_ppc_smmu_info *info)
 	info->sps[0].enc[0].page_shift = 12;
 	info->sps[0].enc[0].pte_enc = 0;
 
+	/*
+	 * 64k large page size.
+	 * We only want to put this in if the CPUs we're emulating
+	 * support it, but unfortunately we don't have a vcpu easily
+	 * to hand here to test.  Just pick the first vcpu, and if
+	 * that doesn't exist yet, report the minimum capability,
+	 * i.e., no 64k pages.
+	 * 1T segment support goes along with 64k pages.
+	 */
+	i = 1;
+	vcpu = kvm_get_vcpu(kvm, 0);
+	if (vcpu && (vcpu->arch.hflags & BOOK3S_HFLAG_MULTI_PGSIZE)) {
+		info->flags = KVM_PPC_1T_SEGMENTS;
+		info->sps[i].page_shift = 16;
+		info->sps[i].slb_enc = SLB_VSID_L | SLB_VSID_LP_01;
+		info->sps[i].enc[0].page_shift = 16;
+		info->sps[i].enc[0].pte_enc = 1;
+		++i;
+	}
+
 	/* 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;
+	info->sps[i].page_shift = 24;
+	info->sps[i].slb_enc = SLB_VSID_L;
+	info->sps[i].enc[0].page_shift = 24;
+	info->sps[i].enc[0].pte_enc = 0;
 
 	return 0;
 }
-- 
cgit v1.2.3-70-g09d2


From c9029c341da646ab0c9911ea4c118eaa0a2eb0fa Mon Sep 17 00:00:00 2001
From: Paul Mackerras <paulus@samba.org>
Date: Fri, 20 Sep 2013 14:52:45 +1000
Subject: KVM: PPC: Book3S PR: Use 64k host pages where possible

Currently, PR KVM uses 4k pages for the host-side mappings of guest
memory, regardless of the host page size.  When the host page size is
64kB, we might as well use 64k host page mappings for guest mappings
of 64kB and larger pages and for guest real-mode mappings.  However,
the magic page has to remain a 4k page.

To implement this, we first add another flag bit to the guest VSID
values we use, to indicate that this segment is one where host pages
should be mapped using 64k pages.  For segments with this bit set
we set the bits in the shadow SLB entry to indicate a 64k base page
size.  When faulting in host HPTEs for this segment, we make them
64k HPTEs instead of 4k.  We record the pagesize in struct hpte_cache
for use when invalidating the HPTE.

For now we restrict the segment containing the magic page (if any) to
4k pages.  It should be possible to lift this restriction in future
by ensuring that the magic 4k page is appropriately positioned within
a host 64k page.

Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Alexander Graf <agraf@suse.de>
---
 arch/powerpc/include/asm/kvm_book3s.h |  6 ++++--
 arch/powerpc/kvm/book3s_32_mmu.c      |  1 +
 arch/powerpc/kvm/book3s_64_mmu.c      | 35 ++++++++++++++++++++++++++++++-----
 arch/powerpc/kvm/book3s_64_mmu_host.c | 27 +++++++++++++++++++++------
 arch/powerpc/kvm/book3s_pr.c          |  1 +
 5 files changed, 57 insertions(+), 13 deletions(-)

(limited to 'arch/powerpc/kvm')

diff --git a/arch/powerpc/include/asm/kvm_book3s.h b/arch/powerpc/include/asm/kvm_book3s.h
index 1d4a1202e2d..6bf20b4a284 100644
--- a/arch/powerpc/include/asm/kvm_book3s.h
+++ b/arch/powerpc/include/asm/kvm_book3s.h
@@ -66,6 +66,7 @@ struct hpte_cache {
 	u64 pfn;
 	ulong slot;
 	struct kvmppc_pte pte;
+	int pagesize;
 };
 
 struct kvmppc_vcpu_book3s {
@@ -113,8 +114,9 @@ struct kvmppc_vcpu_book3s {
 #define CONTEXT_GUEST		1
 #define CONTEXT_GUEST_END	2
 
-#define VSID_REAL	0x0fffffffffc00000ULL
-#define VSID_BAT	0x0fffffffffb00000ULL
+#define VSID_REAL	0x07ffffffffc00000ULL
+#define VSID_BAT	0x07ffffffffb00000ULL
+#define VSID_64K	0x0800000000000000ULL
 #define VSID_1T		0x1000000000000000ULL
 #define VSID_REAL_DR	0x2000000000000000ULL
 #define VSID_REAL_IR	0x4000000000000000ULL
diff --git a/arch/powerpc/kvm/book3s_32_mmu.c b/arch/powerpc/kvm/book3s_32_mmu.c
index c8cefdd15fd..af045533e68 100644
--- a/arch/powerpc/kvm/book3s_32_mmu.c
+++ b/arch/powerpc/kvm/book3s_32_mmu.c
@@ -308,6 +308,7 @@ static int kvmppc_mmu_book3s_32_xlate(struct kvm_vcpu *vcpu, gva_t eaddr,
 	ulong mp_ea = vcpu->arch.magic_page_ea;
 
 	pte->eaddr = eaddr;
+	pte->page_size = MMU_PAGE_4K;
 
 	/* Magic page override */
 	if (unlikely(mp_ea) &&
diff --git a/arch/powerpc/kvm/book3s_64_mmu.c b/arch/powerpc/kvm/book3s_64_mmu.c
index 8277264a0bc..ffcde01cb99 100644
--- a/arch/powerpc/kvm/book3s_64_mmu.c
+++ b/arch/powerpc/kvm/book3s_64_mmu.c
@@ -542,6 +542,16 @@ static void kvmppc_mmu_book3s_64_tlbie(struct kvm_vcpu *vcpu, ulong va,
 	kvmppc_mmu_pte_vflush(vcpu, va >> 12, mask);
 }
 
+#ifdef CONFIG_PPC_64K_PAGES
+static int segment_contains_magic_page(struct kvm_vcpu *vcpu, ulong esid)
+{
+	ulong mp_ea = vcpu->arch.magic_page_ea;
+
+	return mp_ea && !(vcpu->arch.shared->msr & MSR_PR) &&
+		(mp_ea >> SID_SHIFT) == esid;
+}
+#endif
+
 static int kvmppc_mmu_book3s_64_esid_to_vsid(struct kvm_vcpu *vcpu, ulong esid,
 					     u64 *vsid)
 {
@@ -549,11 +559,13 @@ static int kvmppc_mmu_book3s_64_esid_to_vsid(struct kvm_vcpu *vcpu, ulong esid,
 	struct kvmppc_slb *slb;
 	u64 gvsid = esid;
 	ulong mp_ea = vcpu->arch.magic_page_ea;
+	int pagesize = MMU_PAGE_64K;
 
 	if (vcpu->arch.shared->msr & (MSR_DR|MSR_IR)) {
 		slb = kvmppc_mmu_book3s_64_find_slbe(vcpu, ea);
 		if (slb) {
 			gvsid = slb->vsid;
+			pagesize = slb->base_page_size;
 			if (slb->tb) {
 				gvsid <<= SID_SHIFT_1T - SID_SHIFT;
 				gvsid |= esid & ((1ul << (SID_SHIFT_1T - SID_SHIFT)) - 1);
@@ -564,28 +576,41 @@ static int kvmppc_mmu_book3s_64_esid_to_vsid(struct kvm_vcpu *vcpu, ulong esid,
 
 	switch (vcpu->arch.shared->msr & (MSR_DR|MSR_IR)) {
 	case 0:
-		*vsid = VSID_REAL | esid;
+		gvsid = VSID_REAL | esid;
 		break;
 	case MSR_IR:
-		*vsid = VSID_REAL_IR | gvsid;
+		gvsid |= VSID_REAL_IR;
 		break;
 	case MSR_DR:
-		*vsid = VSID_REAL_DR | gvsid;
+		gvsid |= VSID_REAL_DR;
 		break;
 	case MSR_DR|MSR_IR:
 		if (!slb)
 			goto no_slb;
 
-		*vsid = gvsid;
 		break;
 	default:
 		BUG();
 		break;
 	}
 
+#ifdef CONFIG_PPC_64K_PAGES
+	/*
+	 * Mark this as a 64k segment if the host is using
+	 * 64k pages, the host MMU supports 64k pages and
+	 * the guest segment page size is >= 64k,
+	 * but not if this segment contains the magic page.
+	 */
+	if (pagesize >= MMU_PAGE_64K &&
+	    mmu_psize_defs[MMU_PAGE_64K].shift &&
+	    !segment_contains_magic_page(vcpu, esid))
+		gvsid |= VSID_64K;
+#endif
+
 	if (vcpu->arch.shared->msr & MSR_PR)
-		*vsid |= VSID_PR;
+		gvsid |= VSID_PR;
 
+	*vsid = gvsid;
 	return 0;
 
 no_slb:
diff --git a/arch/powerpc/kvm/book3s_64_mmu_host.c b/arch/powerpc/kvm/book3s_64_mmu_host.c
index e5240524bf6..6bda504ceda 100644
--- a/arch/powerpc/kvm/book3s_64_mmu_host.c
+++ b/arch/powerpc/kvm/book3s_64_mmu_host.c
@@ -34,7 +34,7 @@
 void kvmppc_mmu_invalidate_pte(struct kvm_vcpu *vcpu, struct hpte_cache *pte)
 {
 	ppc_md.hpte_invalidate(pte->slot, pte->host_vpn,
-			       MMU_PAGE_4K, MMU_PAGE_4K, MMU_SEGSIZE_256M,
+			       pte->pagesize, pte->pagesize, MMU_SEGSIZE_256M,
 			       false);
 }
 
@@ -90,6 +90,7 @@ int kvmppc_mmu_map_page(struct kvm_vcpu *vcpu, struct kvmppc_pte *orig_pte)
 	int attempt = 0;
 	struct kvmppc_sid_map *map;
 	int r = 0;
+	int hpsize = MMU_PAGE_4K;
 
 	/* Get host physical address for gpa */
 	hpaddr = kvmppc_gfn_to_pfn(vcpu, orig_pte->raddr >> PAGE_SHIFT);
@@ -99,7 +100,6 @@ int kvmppc_mmu_map_page(struct kvm_vcpu *vcpu, struct kvmppc_pte *orig_pte)
 		goto out;
 	}
 	hpaddr <<= PAGE_SHIFT;
-	hpaddr |= orig_pte->raddr & (~0xfffULL & ~PAGE_MASK);
 
 	/* and write the mapping ea -> hpa into the pt */
 	vcpu->arch.mmu.esid_to_vsid(vcpu, orig_pte->eaddr >> SID_SHIFT, &vsid);
@@ -117,8 +117,7 @@ int kvmppc_mmu_map_page(struct kvm_vcpu *vcpu, struct kvmppc_pte *orig_pte)
 		goto out;
 	}
 
-	vsid = map->host_vsid;
-	vpn = hpt_vpn(orig_pte->eaddr, vsid, MMU_SEGSIZE_256M);
+	vpn = hpt_vpn(orig_pte->eaddr, map->host_vsid, MMU_SEGSIZE_256M);
 
 	if (!orig_pte->may_write)
 		rflags |= HPTE_R_PP;
@@ -130,7 +129,16 @@ int kvmppc_mmu_map_page(struct kvm_vcpu *vcpu, struct kvmppc_pte *orig_pte)
 	else
 		kvmppc_mmu_flush_icache(hpaddr >> PAGE_SHIFT);
 
-	hash = hpt_hash(vpn, PTE_SIZE, MMU_SEGSIZE_256M);
+	/*
+	 * Use 64K pages if possible; otherwise, on 64K page kernels,
+	 * we need to transfer 4 more bits from guest real to host real addr.
+	 */
+	if (vsid & VSID_64K)
+		hpsize = MMU_PAGE_64K;
+	else
+		hpaddr |= orig_pte->raddr & (~0xfffULL & ~PAGE_MASK);
+
+	hash = hpt_hash(vpn, mmu_psize_defs[hpsize].shift, MMU_SEGSIZE_256M);
 
 map_again:
 	hpteg = ((hash & htab_hash_mask) * HPTES_PER_GROUP);
@@ -143,7 +151,7 @@ map_again:
 		}
 
 	ret = ppc_md.hpte_insert(hpteg, vpn, hpaddr, rflags, vflags,
-				 MMU_PAGE_4K, MMU_PAGE_4K, MMU_SEGSIZE_256M);
+				 hpsize, hpsize, MMU_SEGSIZE_256M);
 
 	if (ret < 0) {
 		/* If we couldn't map a primary PTE, try a secondary */
@@ -168,6 +176,7 @@ map_again:
 		pte->host_vpn = vpn;
 		pte->pte = *orig_pte;
 		pte->pfn = hpaddr >> PAGE_SHIFT;
+		pte->pagesize = hpsize;
 
 		kvmppc_mmu_hpte_cache_map(vcpu, pte);
 	}
@@ -291,6 +300,12 @@ int kvmppc_mmu_map_segment(struct kvm_vcpu *vcpu, ulong eaddr)
 	slb_vsid &= ~SLB_VSID_KP;
 	slb_esid |= slb_index;
 
+#ifdef CONFIG_PPC_64K_PAGES
+	/* Set host segment base page size to 64K if possible */
+	if (gvsid & VSID_64K)
+		slb_vsid |= mmu_psize_defs[MMU_PAGE_64K].sllp;
+#endif
+
 	svcpu->slb[slb_index].esid = slb_esid;
 	svcpu->slb[slb_index].vsid = slb_vsid;
 
diff --git a/arch/powerpc/kvm/book3s_pr.c b/arch/powerpc/kvm/book3s_pr.c
index 6cc99583ed3..e9e8c748e67 100644
--- a/arch/powerpc/kvm/book3s_pr.c
+++ b/arch/powerpc/kvm/book3s_pr.c
@@ -422,6 +422,7 @@ int kvmppc_handle_pagefault(struct kvm_run *run, struct kvm_vcpu *vcpu,
 		pte.raddr = eaddr & KVM_PAM;
 		pte.eaddr = eaddr;
 		pte.vpage = eaddr >> 12;
+		pte.page_size = MMU_PAGE_64K;
 	}
 
 	switch (vcpu->arch.shared->msr & (MSR_DR|MSR_IR)) {
-- 
cgit v1.2.3-70-g09d2


From 03a9c90334d611c3006ac9569579f25f64812bc1 Mon Sep 17 00:00:00 2001
From: Paul Mackerras <paulus@samba.org>
Date: Fri, 20 Sep 2013 14:52:46 +1000
Subject: KVM: PPC: Book3S PR: Handle PP0 page-protection bit in guest HPTEs

64-bit POWER processors have a three-bit field for page protection in
the hashed page table entry (HPTE).  Currently we only interpret the two
bits that were present in older versions of the architecture.  The only
defined combination that has the new bit set is 110, meaning read-only
for supervisor and no access for user mode.

This adds code to kvmppc_mmu_book3s_64_xlate() to interpret the extra
bit appropriately.

Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Alexander Graf <agraf@suse.de>
---
 arch/powerpc/kvm/book3s_64_mmu.c | 3 +++
 1 file changed, 3 insertions(+)

(limited to 'arch/powerpc/kvm')

diff --git a/arch/powerpc/kvm/book3s_64_mmu.c b/arch/powerpc/kvm/book3s_64_mmu.c
index ffcde01cb99..9e6e11270b7 100644
--- a/arch/powerpc/kvm/book3s_64_mmu.c
+++ b/arch/powerpc/kvm/book3s_64_mmu.c
@@ -298,6 +298,8 @@ do_second:
 	v = pteg[i];
 	r = pteg[i+1];
 	pp = (r & HPTE_R_PP) | key;
+	if (r & HPTE_R_PP0)
+		pp |= 8;
 
 	gpte->eaddr = eaddr;
 	gpte->vpage = kvmppc_mmu_book3s_64_ea_to_vp(vcpu, eaddr, data);
@@ -319,6 +321,7 @@ do_second:
 	case 3:
 	case 5:
 	case 7:
+	case 10:
 		gpte->may_read = true;
 		break;
 	}
-- 
cgit v1.2.3-70-g09d2


From 5cd92a9521d35013fff904d3c805323027a33d73 Mon Sep 17 00:00:00 2001
From: Paul Mackerras <paulus@samba.org>
Date: Fri, 20 Sep 2013 14:52:47 +1000
Subject: KVM: PPC: Book3S PR: Correct errors in H_ENTER implementation

The implementation of H_ENTER in PR KVM has some errors:

* With H_EXACT not set, if the HPTEG is full, we return H_PTEG_FULL
  as the return value of kvmppc_h_pr_enter, but the caller is expecting
  one of the EMULATE_* values.  The H_PTEG_FULL needs to go in the
  guest's R3 instead.

* With H_EXACT set, if the selected HPTE is already valid, the H_ENTER
  call should return a H_PTEG_FULL error.

This fixes these errors and also makes it write only the selected HPTE,
not the whole group, since only the selected HPTE has been modified.
This also micro-optimizes the calculations involving pte_index and i.

Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Alexander Graf <agraf@suse.de>
---
 arch/powerpc/kvm/book3s_pr_papr.c | 19 ++++++++++++++-----
 1 file changed, 14 insertions(+), 5 deletions(-)

(limited to 'arch/powerpc/kvm')

diff --git a/arch/powerpc/kvm/book3s_pr_papr.c b/arch/powerpc/kvm/book3s_pr_papr.c
index da0e0bc268b..38f189975fe 100644
--- a/arch/powerpc/kvm/book3s_pr_papr.c
+++ b/arch/powerpc/kvm/book3s_pr_papr.c
@@ -21,6 +21,8 @@
 #include <asm/kvm_ppc.h>
 #include <asm/kvm_book3s.h>
 
+#define HPTE_SIZE	16		/* bytes per HPT entry */
+
 static unsigned long get_pteg_addr(struct kvm_vcpu *vcpu, long pte_index)
 {
 	struct kvmppc_vcpu_book3s *vcpu_book3s = to_book3s(vcpu);
@@ -40,32 +42,39 @@ static int kvmppc_h_pr_enter(struct kvm_vcpu *vcpu)
 	long pte_index = kvmppc_get_gpr(vcpu, 5);
 	unsigned long pteg[2 * 8];
 	unsigned long pteg_addr, i, *hpte;
+	long int ret;
 
+	i = pte_index & 7;
 	pte_index &= ~7UL;
 	pteg_addr = get_pteg_addr(vcpu, pte_index);
 
 	copy_from_user(pteg, (void __user *)pteg_addr, sizeof(pteg));
 	hpte = pteg;
 
+	ret = H_PTEG_FULL;
 	if (likely((flags & H_EXACT) == 0)) {
-		pte_index &= ~7UL;
 		for (i = 0; ; ++i) {
 			if (i == 8)
-				return H_PTEG_FULL;
+				goto done;
 			if ((*hpte & HPTE_V_VALID) == 0)
 				break;
 			hpte += 2;
 		}
 	} else {
-		i = kvmppc_get_gpr(vcpu, 5) & 7UL;
 		hpte += i * 2;
+		if (*hpte & HPTE_V_VALID)
+			goto done;
 	}
 
 	hpte[0] = kvmppc_get_gpr(vcpu, 6);
 	hpte[1] = kvmppc_get_gpr(vcpu, 7);
-	copy_to_user((void __user *)pteg_addr, pteg, sizeof(pteg));
-	kvmppc_set_gpr(vcpu, 3, H_SUCCESS);
+	pteg_addr += i * HPTE_SIZE;
+	copy_to_user((void __user *)pteg_addr, hpte, HPTE_SIZE);
 	kvmppc_set_gpr(vcpu, 4, pte_index | i);
+	ret = H_SUCCESS;
+
+ done:
+	kvmppc_set_gpr(vcpu, 3, ret);
 
 	return EMULATE_DONE;
 }
-- 
cgit v1.2.3-70-g09d2


From 9308ab8e2da933d895ebbb903bf459e33ed94dec Mon Sep 17 00:00:00 2001
From: Paul Mackerras <paulus@samba.org>
Date: Fri, 20 Sep 2013 14:52:48 +1000
Subject: KVM: PPC: Book3S PR: Make HPT accesses and updates SMP-safe

This adds a per-VM mutex to provide mutual exclusion between vcpus
for accesses to and updates of the guest hashed page table (HPT).
This also makes the code use single-byte writes to the HPT entry
when updating of the reference (R) and change (C) bits.  The reason
for doing this, rather than writing back the whole HPTE, is that on
non-PAPR virtual machines, the guest OS might be writing to the HPTE
concurrently, and writing back the whole HPTE might conflict with
that.  Also, real hardware does single-byte writes to update R and C.

The new mutex is taken in kvmppc_mmu_book3s_64_xlate() when reading
the HPT and updating R and/or C, and in the PAPR HPT update hcalls
(H_ENTER, H_REMOVE, etc.).  Having the mutex means that we don't need
to use a hypervisor lock bit in the HPT update hcalls, and we don't
need to be careful about the order in which the bytes of the HPTE are
updated by those hcalls.

The other change here is to make emulated TLB invalidations (tlbie)
effective across all vcpus.  To do this we call kvmppc_mmu_pte_vflush
for all vcpus in kvmppc_ppc_book3s_64_tlbie().

For 32-bit, this makes the setting of the accessed and dirty bits use
single-byte writes, and makes tlbie invalidate shadow HPTEs for all
vcpus.

With this, PR KVM can successfully run SMP guests.

Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Alexander Graf <agraf@suse.de>
---
 arch/powerpc/include/asm/kvm_host.h |  3 +++
 arch/powerpc/kvm/book3s_32_mmu.c    | 36 ++++++++++++++++++++++--------------
 arch/powerpc/kvm/book3s_64_mmu.c    | 33 +++++++++++++++++++++++----------
 arch/powerpc/kvm/book3s_pr.c        |  1 +
 arch/powerpc/kvm/book3s_pr_papr.c   | 33 +++++++++++++++++++++++----------
 5 files changed, 72 insertions(+), 34 deletions(-)

(limited to 'arch/powerpc/kvm')

diff --git a/arch/powerpc/include/asm/kvm_host.h b/arch/powerpc/include/asm/kvm_host.h
index 3d8b8a8921f..0fe48729d07 100644
--- a/arch/powerpc/include/asm/kvm_host.h
+++ b/arch/powerpc/include/asm/kvm_host.h
@@ -254,6 +254,9 @@ struct kvm_arch {
 	struct kvmppc_vcore *vcores[KVM_MAX_VCORES];
 	int hpt_cma_alloc;
 #endif /* CONFIG_KVM_BOOK3S_64_HV */
+#ifdef CONFIG_KVM_BOOK3S_PR
+	struct mutex hpt_mutex;
+#endif
 #ifdef CONFIG_PPC_BOOK3S_64
 	struct list_head spapr_tce_tables;
 	struct list_head rtas_tokens;
diff --git a/arch/powerpc/kvm/book3s_32_mmu.c b/arch/powerpc/kvm/book3s_32_mmu.c
index af045533e68..856af988ad5 100644
--- a/arch/powerpc/kvm/book3s_32_mmu.c
+++ b/arch/powerpc/kvm/book3s_32_mmu.c
@@ -271,19 +271,22 @@ static int kvmppc_mmu_book3s_32_xlate_pte(struct kvm_vcpu *vcpu, gva_t eaddr,
 	/* Update PTE C and A bits, so the guest's swapper knows we used the
 	   page */
 	if (found) {
-		u32 oldpte = pteg[i+1];
-
-		if (pte->may_read)
-			pteg[i+1] |= PTEG_FLAG_ACCESSED;
-		if (pte->may_write)
-			pteg[i+1] |= PTEG_FLAG_DIRTY;
-		else
-			dprintk_pte("KVM: Mapping read-only page!\n");
-
-		/* Write back into the PTEG */
-		if (pteg[i+1] != oldpte)
-			copy_to_user((void __user *)ptegp, pteg, sizeof(pteg));
-
+		u32 pte_r = pteg[i+1];
+		char __user *addr = (char __user *) &pteg[i+1];
+
+		/*
+		 * Use single-byte writes to update the HPTE, to
+		 * conform to what real hardware does.
+		 */
+		if (pte->may_read && !(pte_r & PTEG_FLAG_ACCESSED)) {
+			pte_r |= PTEG_FLAG_ACCESSED;
+			put_user(pte_r >> 8, addr + 2);
+		}
+		if (pte->may_write && !(pte_r & PTEG_FLAG_DIRTY)) {
+			/* XXX should only set this for stores */
+			pte_r |= PTEG_FLAG_DIRTY;
+			put_user(pte_r, addr + 3);
+		}
 		return 0;
 	}
 
@@ -348,7 +351,12 @@ static void kvmppc_mmu_book3s_32_mtsrin(struct kvm_vcpu *vcpu, u32 srnum,
 
 static void kvmppc_mmu_book3s_32_tlbie(struct kvm_vcpu *vcpu, ulong ea, bool large)
 {
-	kvmppc_mmu_pte_flush(vcpu, ea, 0x0FFFF000);
+	int i;
+	struct kvm_vcpu *v;
+
+	/* flush this VA on all cpus */
+	kvm_for_each_vcpu(i, v, vcpu->kvm)
+		kvmppc_mmu_pte_flush(v, ea, 0x0FFFF000);
 }
 
 static int kvmppc_mmu_book3s_32_esid_to_vsid(struct kvm_vcpu *vcpu, ulong esid,
diff --git a/arch/powerpc/kvm/book3s_64_mmu.c b/arch/powerpc/kvm/book3s_64_mmu.c
index 9e6e11270b7..ad9ecfd29c4 100644
--- a/arch/powerpc/kvm/book3s_64_mmu.c
+++ b/arch/powerpc/kvm/book3s_64_mmu.c
@@ -257,6 +257,8 @@ static int kvmppc_mmu_book3s_64_xlate(struct kvm_vcpu *vcpu, gva_t eaddr,
 
 	pgsize = slbe->large ? MMU_PAGE_16M : MMU_PAGE_4K;
 
+	mutex_lock(&vcpu->kvm->arch.hpt_mutex);
+
 do_second:
 	ptegp = kvmppc_mmu_book3s_64_get_pteg(vcpu_book3s, slbe, eaddr, second);
 	if (kvm_is_error_hva(ptegp))
@@ -332,30 +334,37 @@ do_second:
 
 	/* Update PTE R and C bits, so the guest's swapper knows we used the
 	 * page */
-	if (gpte->may_read) {
-		/* Set the accessed flag */
+	if (gpte->may_read && !(r & HPTE_R_R)) {
+		/*
+		 * Set the accessed flag.
+		 * We have to write this back with a single byte write
+		 * because another vcpu may be accessing this on
+		 * non-PAPR platforms such as mac99, and this is
+		 * what real hardware does.
+		 */
+		char __user *addr = (char __user *) &pteg[i+1];
 		r |= HPTE_R_R;
+		put_user(r >> 8, addr + 6);
 	}
-	if (data && gpte->may_write) {
+	if (data && gpte->may_write && !(r & HPTE_R_C)) {
 		/* Set the dirty flag -- XXX even if not writing */
+		/* Use a single byte write */
+		char __user *addr = (char __user *) &pteg[i+1];
 		r |= HPTE_R_C;
+		put_user(r, addr + 7);
 	}
 
-	/* Write back into the PTEG */
-	if (pteg[i+1] != r) {
-		pteg[i+1] = r;
-		copy_to_user((void __user *)ptegp, pteg, sizeof(pteg));
-	}
+	mutex_unlock(&vcpu->kvm->arch.hpt_mutex);
 
 	if (!gpte->may_read)
 		return -EPERM;
 	return 0;
 
 no_page_found:
+	mutex_unlock(&vcpu->kvm->arch.hpt_mutex);
 	return -ENOENT;
 
 no_seg_found:
-
 	dprintk("KVM MMU: Trigger segment fault\n");
 	return -EINVAL;
 }
@@ -520,6 +529,8 @@ static void kvmppc_mmu_book3s_64_tlbie(struct kvm_vcpu *vcpu, ulong va,
 				       bool large)
 {
 	u64 mask = 0xFFFFFFFFFULL;
+	long i;
+	struct kvm_vcpu *v;
 
 	dprintk("KVM MMU: tlbie(0x%lx)\n", va);
 
@@ -542,7 +553,9 @@ static void kvmppc_mmu_book3s_64_tlbie(struct kvm_vcpu *vcpu, ulong va,
 		if (large)
 			mask = 0xFFFFFF000ULL;
 	}
-	kvmppc_mmu_pte_vflush(vcpu, va >> 12, mask);
+	/* flush this VA on all vcpus */
+	kvm_for_each_vcpu(i, v, vcpu->kvm)
+		kvmppc_mmu_pte_vflush(v, va >> 12, mask);
 }
 
 #ifdef CONFIG_PPC_64K_PAGES
diff --git a/arch/powerpc/kvm/book3s_pr.c b/arch/powerpc/kvm/book3s_pr.c
index e9e8c748e67..4fa73c3f571 100644
--- a/arch/powerpc/kvm/book3s_pr.c
+++ b/arch/powerpc/kvm/book3s_pr.c
@@ -1422,6 +1422,7 @@ int kvmppc_core_init_vm(struct kvm *kvm)
 	INIT_LIST_HEAD(&kvm->arch.spapr_tce_tables);
 	INIT_LIST_HEAD(&kvm->arch.rtas_tokens);
 #endif
+	mutex_init(&kvm->arch.hpt_mutex);
 
 	if (firmware_has_feature(FW_FEATURE_SET_MODE)) {
 		spin_lock(&kvm_global_user_count_lock);
diff --git a/arch/powerpc/kvm/book3s_pr_papr.c b/arch/powerpc/kvm/book3s_pr_papr.c
index 38f189975fe..5efa97b993d 100644
--- a/arch/powerpc/kvm/book3s_pr_papr.c
+++ b/arch/powerpc/kvm/book3s_pr_papr.c
@@ -48,6 +48,7 @@ static int kvmppc_h_pr_enter(struct kvm_vcpu *vcpu)
 	pte_index &= ~7UL;
 	pteg_addr = get_pteg_addr(vcpu, pte_index);
 
+	mutex_lock(&vcpu->kvm->arch.hpt_mutex);
 	copy_from_user(pteg, (void __user *)pteg_addr, sizeof(pteg));
 	hpte = pteg;
 
@@ -74,6 +75,7 @@ static int kvmppc_h_pr_enter(struct kvm_vcpu *vcpu)
 	ret = H_SUCCESS;
 
  done:
+	mutex_unlock(&vcpu->kvm->arch.hpt_mutex);
 	kvmppc_set_gpr(vcpu, 3, ret);
 
 	return EMULATE_DONE;
@@ -86,26 +88,31 @@ static int kvmppc_h_pr_remove(struct kvm_vcpu *vcpu)
 	unsigned long avpn = kvmppc_get_gpr(vcpu, 6);
 	unsigned long v = 0, pteg, rb;
 	unsigned long pte[2];
+	long int ret;
 
 	pteg = get_pteg_addr(vcpu, pte_index);
+	mutex_lock(&vcpu->kvm->arch.hpt_mutex);
 	copy_from_user(pte, (void __user *)pteg, sizeof(pte));
 
+	ret = H_NOT_FOUND;
 	if ((pte[0] & HPTE_V_VALID) == 0 ||
 	    ((flags & H_AVPN) && (pte[0] & ~0x7fUL) != avpn) ||
-	    ((flags & H_ANDCOND) && (pte[0] & avpn) != 0)) {
-		kvmppc_set_gpr(vcpu, 3, H_NOT_FOUND);
-		return EMULATE_DONE;
-	}
+	    ((flags & H_ANDCOND) && (pte[0] & avpn) != 0))
+		goto done;
 
 	copy_to_user((void __user *)pteg, &v, sizeof(v));
 
 	rb = compute_tlbie_rb(pte[0], pte[1], pte_index);
 	vcpu->arch.mmu.tlbie(vcpu, rb, rb & 1 ? true : false);
 
-	kvmppc_set_gpr(vcpu, 3, H_SUCCESS);
+	ret = H_SUCCESS;
 	kvmppc_set_gpr(vcpu, 4, pte[0]);
 	kvmppc_set_gpr(vcpu, 5, pte[1]);
 
+ done:
+	mutex_unlock(&vcpu->kvm->arch.hpt_mutex);
+	kvmppc_set_gpr(vcpu, 3, ret);
+
 	return EMULATE_DONE;
 }
 
@@ -133,6 +140,7 @@ static int kvmppc_h_pr_bulk_remove(struct kvm_vcpu *vcpu)
 	int paramnr = 4;
 	int ret = H_SUCCESS;
 
+	mutex_lock(&vcpu->kvm->arch.hpt_mutex);
 	for (i = 0; i < H_BULK_REMOVE_MAX_BATCH; i++) {
 		unsigned long tsh = kvmppc_get_gpr(vcpu, paramnr+(2*i));
 		unsigned long tsl = kvmppc_get_gpr(vcpu, paramnr+(2*i)+1);
@@ -181,6 +189,7 @@ static int kvmppc_h_pr_bulk_remove(struct kvm_vcpu *vcpu)
 		}
 		kvmppc_set_gpr(vcpu, paramnr+(2*i), tsh);
 	}
+	mutex_unlock(&vcpu->kvm->arch.hpt_mutex);
 	kvmppc_set_gpr(vcpu, 3, ret);
 
 	return EMULATE_DONE;
@@ -193,15 +202,16 @@ static int kvmppc_h_pr_protect(struct kvm_vcpu *vcpu)
 	unsigned long avpn = kvmppc_get_gpr(vcpu, 6);
 	unsigned long rb, pteg, r, v;
 	unsigned long pte[2];
+	long int ret;
 
 	pteg = get_pteg_addr(vcpu, pte_index);
+	mutex_lock(&vcpu->kvm->arch.hpt_mutex);
 	copy_from_user(pte, (void __user *)pteg, sizeof(pte));
 
+	ret = H_NOT_FOUND;
 	if ((pte[0] & HPTE_V_VALID) == 0 ||
-	    ((flags & H_AVPN) && (pte[0] & ~0x7fUL) != avpn)) {
-		kvmppc_set_gpr(vcpu, 3, H_NOT_FOUND);
-		return EMULATE_DONE;
-	}
+	    ((flags & H_AVPN) && (pte[0] & ~0x7fUL) != avpn))
+		goto done;
 
 	v = pte[0];
 	r = pte[1];
@@ -216,8 +226,11 @@ static int kvmppc_h_pr_protect(struct kvm_vcpu *vcpu)
 	rb = compute_tlbie_rb(v, r, pte_index);
 	vcpu->arch.mmu.tlbie(vcpu, rb, rb & 1 ? true : false);
 	copy_to_user((void __user *)pteg, pte, sizeof(pte));
+	ret = H_SUCCESS;
 
-	kvmppc_set_gpr(vcpu, 3, H_SUCCESS);
+ done:
+	mutex_unlock(&vcpu->kvm->arch.hpt_mutex);
+	kvmppc_set_gpr(vcpu, 3, ret);
 
 	return EMULATE_DONE;
 }
-- 
cgit v1.2.3-70-g09d2


From 3ff955024d186c512ee91263df9c850d6ae34a12 Mon Sep 17 00:00:00 2001
From: Paul Mackerras <paulus@samba.org>
Date: Fri, 20 Sep 2013 14:52:49 +1000
Subject: KVM: PPC: Book3S PR: Allocate kvm_vcpu structs from kvm_vcpu_cache

This makes PR KVM allocate its kvm_vcpu structs from the kvm_vcpu_cache
rather than having them embedded in the kvmppc_vcpu_book3s struct,
which is allocated with vzalloc.  The reason is to reduce the
differences between PR and HV KVM in order to make is easier to have
them coexist in one kernel binary.

With this, the kvm_vcpu struct has a pointer to the kvmppc_vcpu_book3s
struct.  The pointer to the kvmppc_book3s_shadow_vcpu struct has moved
from the kvmppc_vcpu_book3s struct to the kvm_vcpu struct, and is only
present for 32-bit, since it is only used for 32-bit.

Signed-off-by: Paul Mackerras <paulus@samba.org>
[agraf: squash in compile fix from Aneesh]
Signed-off-by: Alexander Graf <agraf@suse.de>
---
 arch/powerpc/include/asm/kvm_book3s.h    |  4 +---
 arch/powerpc/include/asm/kvm_book3s_32.h |  2 +-
 arch/powerpc/include/asm/kvm_host.h      |  7 +++++++
 arch/powerpc/kvm/book3s_32_mmu.c         |  8 ++++----
 arch/powerpc/kvm/book3s_64_mmu.c         | 11 +++++------
 arch/powerpc/kvm/book3s_pr.c             | 33 ++++++++++++++++++++------------
 6 files changed, 39 insertions(+), 26 deletions(-)

(limited to 'arch/powerpc/kvm')

diff --git a/arch/powerpc/include/asm/kvm_book3s.h b/arch/powerpc/include/asm/kvm_book3s.h
index 6bf20b4a284..603fba494a0 100644
--- a/arch/powerpc/include/asm/kvm_book3s.h
+++ b/arch/powerpc/include/asm/kvm_book3s.h
@@ -70,8 +70,6 @@ struct hpte_cache {
 };
 
 struct kvmppc_vcpu_book3s {
-	struct kvm_vcpu vcpu;
-	struct kvmppc_book3s_shadow_vcpu *shadow_vcpu;
 	struct kvmppc_sid_map sid_map[SID_MAP_NUM];
 	struct {
 		u64 esid;
@@ -194,7 +192,7 @@ extern int kvmppc_h_pr(struct kvm_vcpu *vcpu, unsigned long cmd);
 
 static inline struct kvmppc_vcpu_book3s *to_book3s(struct kvm_vcpu *vcpu)
 {
-	return container_of(vcpu, struct kvmppc_vcpu_book3s, vcpu);
+	return vcpu->arch.book3s;
 }
 
 extern void kvm_return_point(void);
diff --git a/arch/powerpc/include/asm/kvm_book3s_32.h b/arch/powerpc/include/asm/kvm_book3s_32.h
index ce0ef6ce8f8..c720e0b3238 100644
--- a/arch/powerpc/include/asm/kvm_book3s_32.h
+++ b/arch/powerpc/include/asm/kvm_book3s_32.h
@@ -22,7 +22,7 @@
 
 static inline struct kvmppc_book3s_shadow_vcpu *svcpu_get(struct kvm_vcpu *vcpu)
 {
-	return to_book3s(vcpu)->shadow_vcpu;
+	return vcpu->arch.shadow_vcpu;
 }
 
 static inline void svcpu_put(struct kvmppc_book3s_shadow_vcpu *svcpu)
diff --git a/arch/powerpc/include/asm/kvm_host.h b/arch/powerpc/include/asm/kvm_host.h
index 0fe48729d07..404dbc81434 100644
--- a/arch/powerpc/include/asm/kvm_host.h
+++ b/arch/powerpc/include/asm/kvm_host.h
@@ -86,6 +86,9 @@ struct lppaca;
 struct slb_shadow;
 struct dtl_entry;
 
+struct kvmppc_vcpu_book3s;
+struct kvmppc_book3s_shadow_vcpu;
+
 struct kvm_vm_stat {
 	u32 remote_tlb_flush;
 };
@@ -408,6 +411,10 @@ struct kvm_vcpu_arch {
 	int slb_max;		/* 1 + index of last valid entry in slb[] */
 	int slb_nr;		/* total number of entries in SLB */
 	struct kvmppc_mmu mmu;
+	struct kvmppc_vcpu_book3s *book3s;
+#endif
+#ifdef CONFIG_PPC_BOOK3S_32
+	struct kvmppc_book3s_shadow_vcpu *shadow_vcpu;
 #endif
 
 	ulong gpr[32];
diff --git a/arch/powerpc/kvm/book3s_32_mmu.c b/arch/powerpc/kvm/book3s_32_mmu.c
index 856af988ad5..b14af6d0934 100644
--- a/arch/powerpc/kvm/book3s_32_mmu.c
+++ b/arch/powerpc/kvm/book3s_32_mmu.c
@@ -111,10 +111,11 @@ static void kvmppc_mmu_book3s_32_reset_msr(struct kvm_vcpu *vcpu)
 	kvmppc_set_msr(vcpu, 0);
 }
 
-static hva_t kvmppc_mmu_book3s_32_get_pteg(struct kvmppc_vcpu_book3s *vcpu_book3s,
+static hva_t kvmppc_mmu_book3s_32_get_pteg(struct kvm_vcpu *vcpu,
 				      u32 sre, gva_t eaddr,
 				      bool primary)
 {
+	struct kvmppc_vcpu_book3s *vcpu_book3s = to_book3s(vcpu);
 	u32 page, hash, pteg, htabmask;
 	hva_t r;
 
@@ -132,7 +133,7 @@ static hva_t kvmppc_mmu_book3s_32_get_pteg(struct kvmppc_vcpu_book3s *vcpu_book3
 		kvmppc_get_pc(&vcpu_book3s->vcpu), eaddr, vcpu_book3s->sdr1, pteg,
 		sr_vsid(sre));
 
-	r = gfn_to_hva(vcpu_book3s->vcpu.kvm, pteg >> PAGE_SHIFT);
+	r = gfn_to_hva(vcpu->kvm, pteg >> PAGE_SHIFT);
 	if (kvm_is_error_hva(r))
 		return r;
 	return r | (pteg & ~PAGE_MASK);
@@ -203,7 +204,6 @@ static int kvmppc_mmu_book3s_32_xlate_pte(struct kvm_vcpu *vcpu, gva_t eaddr,
 				     struct kvmppc_pte *pte, bool data,
 				     bool primary)
 {
-	struct kvmppc_vcpu_book3s *vcpu_book3s = to_book3s(vcpu);
 	u32 sre;
 	hva_t ptegp;
 	u32 pteg[16];
@@ -218,7 +218,7 @@ static int kvmppc_mmu_book3s_32_xlate_pte(struct kvm_vcpu *vcpu, gva_t eaddr,
 
 	pte->vpage = kvmppc_mmu_book3s_32_ea_to_vp(vcpu, eaddr, data);
 
-	ptegp = kvmppc_mmu_book3s_32_get_pteg(vcpu_book3s, sre, eaddr, primary);
+	ptegp = kvmppc_mmu_book3s_32_get_pteg(vcpu, sre, eaddr, primary);
 	if (kvm_is_error_hva(ptegp)) {
 		printk(KERN_INFO "KVM: Invalid PTEG!\n");
 		goto no_page_found;
diff --git a/arch/powerpc/kvm/book3s_64_mmu.c b/arch/powerpc/kvm/book3s_64_mmu.c
index ad9ecfd29c4..c110145522e 100644
--- a/arch/powerpc/kvm/book3s_64_mmu.c
+++ b/arch/powerpc/kvm/book3s_64_mmu.c
@@ -130,11 +130,11 @@ static u32 kvmppc_mmu_book3s_64_get_page(struct kvmppc_slb *slbe, gva_t eaddr)
 	return ((eaddr & kvmppc_slb_offset_mask(slbe)) >> p);
 }
 
-static hva_t kvmppc_mmu_book3s_64_get_pteg(
-				struct kvmppc_vcpu_book3s *vcpu_book3s,
+static hva_t kvmppc_mmu_book3s_64_get_pteg(struct kvm_vcpu *vcpu,
 				struct kvmppc_slb *slbe, gva_t eaddr,
 				bool second)
 {
+	struct kvmppc_vcpu_book3s *vcpu_book3s = to_book3s(vcpu);
 	u64 hash, pteg, htabsize;
 	u32 ssize;
 	hva_t r;
@@ -159,10 +159,10 @@ static hva_t kvmppc_mmu_book3s_64_get_pteg(
 
 	/* When running a PAPR guest, SDR1 contains a HVA address instead
            of a GPA */
-	if (vcpu_book3s->vcpu.arch.papr_enabled)
+	if (vcpu->arch.papr_enabled)
 		r = pteg;
 	else
-		r = gfn_to_hva(vcpu_book3s->vcpu.kvm, pteg >> PAGE_SHIFT);
+		r = gfn_to_hva(vcpu->kvm, pteg >> PAGE_SHIFT);
 
 	if (kvm_is_error_hva(r))
 		return r;
@@ -208,7 +208,6 @@ static int decode_pagesize(struct kvmppc_slb *slbe, u64 r)
 static int kvmppc_mmu_book3s_64_xlate(struct kvm_vcpu *vcpu, gva_t eaddr,
 				struct kvmppc_pte *gpte, bool data)
 {
-	struct kvmppc_vcpu_book3s *vcpu_book3s = to_book3s(vcpu);
 	struct kvmppc_slb *slbe;
 	hva_t ptegp;
 	u64 pteg[16];
@@ -260,7 +259,7 @@ static int kvmppc_mmu_book3s_64_xlate(struct kvm_vcpu *vcpu, gva_t eaddr,
 	mutex_lock(&vcpu->kvm->arch.hpt_mutex);
 
 do_second:
-	ptegp = kvmppc_mmu_book3s_64_get_pteg(vcpu_book3s, slbe, eaddr, second);
+	ptegp = kvmppc_mmu_book3s_64_get_pteg(vcpu, slbe, eaddr, second);
 	if (kvm_is_error_hva(ptegp))
 		goto no_page_found;
 
diff --git a/arch/powerpc/kvm/book3s_pr.c b/arch/powerpc/kvm/book3s_pr.c
index 4fa73c3f571..677d7e33b1f 100644
--- a/arch/powerpc/kvm/book3s_pr.c
+++ b/arch/powerpc/kvm/book3s_pr.c
@@ -66,7 +66,7 @@ void kvmppc_core_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
 #endif
 	vcpu->cpu = smp_processor_id();
 #ifdef CONFIG_PPC_BOOK3S_32
-	current->thread.kvm_shadow_vcpu = to_book3s(vcpu)->shadow_vcpu;
+	current->thread.kvm_shadow_vcpu = vcpu->arch.shadow_vcpu;
 #endif
 }
 
@@ -1125,17 +1125,22 @@ struct kvm_vcpu *kvmppc_core_vcpu_create(struct kvm *kvm, unsigned int id)
 	int err = -ENOMEM;
 	unsigned long p;
 
+	vcpu = kmem_cache_zalloc(kvm_vcpu_cache, GFP_KERNEL);
+	if (!vcpu)
+		goto out;
+
 	vcpu_book3s = vzalloc(sizeof(struct kvmppc_vcpu_book3s));
 	if (!vcpu_book3s)
-		goto out;
+		goto free_vcpu;
+	vcpu->arch.book3s = vcpu_book3s;
 
 #ifdef CONFIG_KVM_BOOK3S_32
-	vcpu_book3s->shadow_vcpu =
-		kzalloc(sizeof(*vcpu_book3s->shadow_vcpu), GFP_KERNEL);
-	if (!vcpu_book3s->shadow_vcpu)
-		goto free_vcpu;
+	vcpu->arch.shadow_vcpu =
+		kzalloc(sizeof(*vcpu->arch.shadow_vcpu), GFP_KERNEL);
+	if (!vcpu->arch.shadow_vcpu)
+		goto free_vcpu3s;
 #endif
-	vcpu = &vcpu_book3s->vcpu;
+
 	err = kvm_vcpu_init(vcpu, kvm, id);
 	if (err)
 		goto free_shadow_vcpu;
@@ -1175,10 +1180,12 @@ uninit_vcpu:
 	kvm_vcpu_uninit(vcpu);
 free_shadow_vcpu:
 #ifdef CONFIG_KVM_BOOK3S_32
-	kfree(vcpu_book3s->shadow_vcpu);
-free_vcpu:
+	kfree(vcpu->arch.shadow_vcpu);
+free_vcpu3s:
 #endif
 	vfree(vcpu_book3s);
+free_vcpu:
+	kmem_cache_free(kvm_vcpu_cache, vcpu);
 out:
 	return ERR_PTR(err);
 }
@@ -1189,8 +1196,11 @@ void kvmppc_core_vcpu_free(struct kvm_vcpu *vcpu)
 
 	free_page((unsigned long)vcpu->arch.shared & PAGE_MASK);
 	kvm_vcpu_uninit(vcpu);
-	kfree(vcpu_book3s->shadow_vcpu);
+#ifdef CONFIG_KVM_BOOK3S_32
+	kfree(vcpu->arch.shadow_vcpu);
+#endif
 	vfree(vcpu_book3s);
+	kmem_cache_free(kvm_vcpu_cache, vcpu);
 }
 
 int kvmppc_vcpu_run(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu)
@@ -1452,8 +1462,7 @@ static int kvmppc_book3s_init(void)
 {
 	int r;
 
-	r = kvm_init(NULL, sizeof(struct kvmppc_vcpu_book3s), 0,
-		     THIS_MODULE);
+	r = kvm_init(NULL, sizeof(struct kvm_vcpu), 0, THIS_MODULE);
 
 	if (r)
 		return r;
-- 
cgit v1.2.3-70-g09d2


From 4f6c11db10159e362b0100d41b35bf6d731eb4e2 Mon Sep 17 00:00:00 2001
From: Paul Mackerras <paulus@samba.org>
Date: Fri, 20 Sep 2013 14:52:50 +1000
Subject: KVM: PPC: Book3S: Move skip-interrupt handlers to common code

Both PR and HV KVM have separate, identical copies of the
kvmppc_skip_interrupt and kvmppc_skip_Hinterrupt handlers that are
used for the situation where an interrupt happens when loading the
instruction that caused an exit from the guest.  To eliminate this
duplication and make it easier to compile in both PR and HV KVM,
this moves this code to arch/powerpc/kernel/exceptions-64s.S along
with other kernel interrupt handler code.

Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Alexander Graf <agraf@suse.de>
---
 arch/powerpc/kernel/exceptions-64s.S    | 26 ++++++++++++++++++++++++++
 arch/powerpc/kvm/book3s_hv_rmhandlers.S | 24 ------------------------
 arch/powerpc/kvm/book3s_rmhandlers.S    | 26 --------------------------
 3 files changed, 26 insertions(+), 50 deletions(-)

(limited to 'arch/powerpc/kvm')

diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S
index 3a9ed6ac224..2a273bed1ec 100644
--- a/arch/powerpc/kernel/exceptions-64s.S
+++ b/arch/powerpc/kernel/exceptions-64s.S
@@ -650,6 +650,32 @@ slb_miss_user_pseries:
 	b	.				/* prevent spec. execution */
 #endif /* __DISABLED__ */
 
+#ifdef CONFIG_KVM_BOOK3S_64_HANDLER
+kvmppc_skip_interrupt:
+	/*
+	 * Here all GPRs are unchanged from when the interrupt happened
+	 * except for r13, which is saved in SPRG_SCRATCH0.
+	 */
+	mfspr	r13, SPRN_SRR0
+	addi	r13, r13, 4
+	mtspr	SPRN_SRR0, r13
+	GET_SCRATCH0(r13)
+	rfid
+	b	.
+
+kvmppc_skip_Hinterrupt:
+	/*
+	 * Here all GPRs are unchanged from when the interrupt happened
+	 * except for r13, which is saved in SPRG_SCRATCH0.
+	 */
+	mfspr	r13, SPRN_HSRR0
+	addi	r13, r13, 4
+	mtspr	SPRN_HSRR0, r13
+	GET_SCRATCH0(r13)
+	hrfid
+	b	.
+#endif
+
 /*
  * Code from here down to __end_handlers is invoked from the
  * exception prologs above.  Because the prologs assemble the
diff --git a/arch/powerpc/kvm/book3s_hv_rmhandlers.S b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
index cd39632a646..6e3370f42a6 100644
--- a/arch/powerpc/kvm/book3s_hv_rmhandlers.S
+++ b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
@@ -33,30 +33,6 @@
 #error Need to fix lppaca and SLB shadow accesses in little endian mode
 #endif
 
-/*****************************************************************************
- *                                                                           *
- *        Real Mode handlers that need to be in the linear mapping           *
- *                                                                           *
- ****************************************************************************/
-
-	.globl	kvmppc_skip_interrupt
-kvmppc_skip_interrupt:
-	mfspr	r13,SPRN_SRR0
-	addi	r13,r13,4
-	mtspr	SPRN_SRR0,r13
-	GET_SCRATCH0(r13)
-	rfid
-	b	.
-
-	.globl	kvmppc_skip_Hinterrupt
-kvmppc_skip_Hinterrupt:
-	mfspr	r13,SPRN_HSRR0
-	addi	r13,r13,4
-	mtspr	SPRN_HSRR0,r13
-	GET_SCRATCH0(r13)
-	hrfid
-	b	.
-
 /*
  * Call kvmppc_hv_entry in real mode.
  * Must be called with interrupts hard-disabled.
diff --git a/arch/powerpc/kvm/book3s_rmhandlers.S b/arch/powerpc/kvm/book3s_rmhandlers.S
index cd59a3a3848..a38c4c9edab 100644
--- a/arch/powerpc/kvm/book3s_rmhandlers.S
+++ b/arch/powerpc/kvm/book3s_rmhandlers.S
@@ -38,32 +38,6 @@
 
 #define FUNC(name) 		GLUE(.,name)
 
-	.globl	kvmppc_skip_interrupt
-kvmppc_skip_interrupt:
-	/*
-	 * Here all GPRs are unchanged from when the interrupt happened
-	 * except for r13, which is saved in SPRG_SCRATCH0.
-	 */
-	mfspr	r13, SPRN_SRR0
-	addi	r13, r13, 4
-	mtspr	SPRN_SRR0, r13
-	GET_SCRATCH0(r13)
-	rfid
-	b	.
-
-	.globl	kvmppc_skip_Hinterrupt
-kvmppc_skip_Hinterrupt:
-	/*
-	 * Here all GPRs are unchanged from when the interrupt happened
-	 * except for r13, which is saved in SPRG_SCRATCH0.
-	 */
-	mfspr	r13, SPRN_HSRR0
-	addi	r13, r13, 4
-	mtspr	SPRN_HSRR0, r13
-	GET_SCRATCH0(r13)
-	hrfid
-	b	.
-
 #elif defined(CONFIG_PPC_BOOK3S_32)
 
 #define FUNC(name)		name
-- 
cgit v1.2.3-70-g09d2


From 93b159b466bdc9753bba5c3c51b40d7ddbbcc07c Mon Sep 17 00:00:00 2001
From: Paul Mackerras <paulus@samba.org>
Date: Fri, 20 Sep 2013 14:52:51 +1000
Subject: KVM: PPC: Book3S PR: Better handling of host-side read-only pages

Currently we request write access to all pages that get mapped into the
guest, even if the guest is only loading from the page.  This reduces
the effectiveness of KSM because it means that we unshare every page we
access.  Also, we always set the changed (C) bit in the guest HPTE if
it allows writing, even for a guest load.

This fixes both these problems.  We pass an 'iswrite' flag to the
mmu.xlate() functions and to kvmppc_mmu_map_page() to indicate whether
the access is a load or a store.  The mmu.xlate() functions now only
set C for stores.  kvmppc_gfn_to_pfn() now calls gfn_to_pfn_prot()
instead of gfn_to_pfn() so that it can indicate whether we need write
access to the page, and get back a 'writable' flag to indicate whether
the page is writable or not.  If that 'writable' flag is clear, we then
make the host HPTE read-only even if the guest HPTE allowed writing.

This means that we can get a protection fault when the guest writes to a
page that it has mapped read-write but which is read-only on the host
side (perhaps due to KSM having merged the page).  Thus we now call
kvmppc_handle_pagefault() for protection faults as well as HPTE not found
faults.  In kvmppc_handle_pagefault(), if the access was allowed by the
guest HPTE and we thus need to install a new host HPTE, we then need to
remove the old host HPTE if there is one.  This is done with a new
function, kvmppc_mmu_unmap_page(), which uses kvmppc_mmu_pte_vflush() to
find and remove the old host HPTE.

Since the memslot-related functions require the KVM SRCU read lock to
be held, this adds srcu_read_lock/unlock pairs around the calls to
kvmppc_handle_pagefault().

Finally, this changes kvmppc_mmu_book3s_32_xlate_pte() to not ignore
guest HPTEs that don't permit access, and to return -EPERM for accesses
that are not permitted by the page protections.

Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Alexander Graf <agraf@suse.de>
---
 arch/powerpc/include/asm/kvm_book3s.h |  7 +++++--
 arch/powerpc/include/asm/kvm_host.h   |  3 ++-
 arch/powerpc/kvm/book3s.c             | 15 +++++++++------
 arch/powerpc/kvm/book3s_32_mmu.c      | 32 +++++++++++++++++---------------
 arch/powerpc/kvm/book3s_32_mmu_host.c | 14 +++++++++++---
 arch/powerpc/kvm/book3s_64_mmu.c      |  9 +++++----
 arch/powerpc/kvm/book3s_64_mmu_host.c | 20 +++++++++++++++++---
 arch/powerpc/kvm/book3s_64_mmu_hv.c   |  2 +-
 arch/powerpc/kvm/book3s_pr.c          | 29 ++++++++++++++++++++++++-----
 9 files changed, 91 insertions(+), 40 deletions(-)

(limited to 'arch/powerpc/kvm')

diff --git a/arch/powerpc/include/asm/kvm_book3s.h b/arch/powerpc/include/asm/kvm_book3s.h
index 603fba494a0..a07bd7e7d4a 100644
--- a/arch/powerpc/include/asm/kvm_book3s.h
+++ b/arch/powerpc/include/asm/kvm_book3s.h
@@ -128,7 +128,9 @@ extern void kvmppc_set_pvr(struct kvm_vcpu *vcpu, u32 pvr);
 extern void kvmppc_mmu_book3s_64_init(struct kvm_vcpu *vcpu);
 extern void kvmppc_mmu_book3s_32_init(struct kvm_vcpu *vcpu);
 extern void kvmppc_mmu_book3s_hv_init(struct kvm_vcpu *vcpu);
-extern int kvmppc_mmu_map_page(struct kvm_vcpu *vcpu, struct kvmppc_pte *pte);
+extern int kvmppc_mmu_map_page(struct kvm_vcpu *vcpu, struct kvmppc_pte *pte,
+			       bool iswrite);
+extern void kvmppc_mmu_unmap_page(struct kvm_vcpu *vcpu, struct kvmppc_pte *pte);
 extern int kvmppc_mmu_map_segment(struct kvm_vcpu *vcpu, ulong eaddr);
 extern void kvmppc_mmu_flush_segment(struct kvm_vcpu *vcpu, ulong eaddr, ulong seg_size);
 extern void kvmppc_mmu_flush_segments(struct kvm_vcpu *vcpu);
@@ -157,7 +159,8 @@ extern void kvmppc_set_bat(struct kvm_vcpu *vcpu, struct kvmppc_bat *bat,
 			   bool upper, u32 val);
 extern void kvmppc_giveup_ext(struct kvm_vcpu *vcpu, ulong msr);
 extern int kvmppc_emulate_paired_single(struct kvm_run *run, struct kvm_vcpu *vcpu);
-extern pfn_t kvmppc_gfn_to_pfn(struct kvm_vcpu *vcpu, gfn_t gfn);
+extern pfn_t kvmppc_gfn_to_pfn(struct kvm_vcpu *vcpu, gfn_t gfn, bool writing,
+			bool *writable);
 extern void kvmppc_add_revmap_chain(struct kvm *kvm, struct revmap_entry *rev,
 			unsigned long *rmap, long pte_index, int realmode);
 extern void kvmppc_invalidate_hpte(struct kvm *kvm, unsigned long *hptep,
diff --git a/arch/powerpc/include/asm/kvm_host.h b/arch/powerpc/include/asm/kvm_host.h
index 404dbc81434..b6881917cd8 100644
--- a/arch/powerpc/include/asm/kvm_host.h
+++ b/arch/powerpc/include/asm/kvm_host.h
@@ -348,7 +348,8 @@ struct kvmppc_mmu {
 	/* book3s */
 	void (*mtsrin)(struct kvm_vcpu *vcpu, u32 srnum, ulong value);
 	u32  (*mfsrin)(struct kvm_vcpu *vcpu, u32 srnum);
-	int  (*xlate)(struct kvm_vcpu *vcpu, gva_t eaddr, struct kvmppc_pte *pte, bool data);
+	int  (*xlate)(struct kvm_vcpu *vcpu, gva_t eaddr,
+		      struct kvmppc_pte *pte, bool data, bool iswrite);
 	void (*reset_msr)(struct kvm_vcpu *vcpu);
 	void (*tlbie)(struct kvm_vcpu *vcpu, ulong addr, bool large);
 	int  (*esid_to_vsid)(struct kvm_vcpu *vcpu, ulong esid, u64 *vsid);
diff --git a/arch/powerpc/kvm/book3s.c b/arch/powerpc/kvm/book3s.c
index f97369dc457..807103ad262 100644
--- a/arch/powerpc/kvm/book3s.c
+++ b/arch/powerpc/kvm/book3s.c
@@ -286,7 +286,8 @@ int kvmppc_core_prepare_to_enter(struct kvm_vcpu *vcpu)
 	return 0;
 }
 
-pfn_t kvmppc_gfn_to_pfn(struct kvm_vcpu *vcpu, gfn_t gfn)
+pfn_t kvmppc_gfn_to_pfn(struct kvm_vcpu *vcpu, gfn_t gfn, bool writing,
+			bool *writable)
 {
 	ulong mp_pa = vcpu->arch.magic_page_pa;
 
@@ -302,20 +303,22 @@ pfn_t kvmppc_gfn_to_pfn(struct kvm_vcpu *vcpu, gfn_t gfn)
 
 		pfn = (pfn_t)virt_to_phys((void*)shared_page) >> PAGE_SHIFT;
 		get_page(pfn_to_page(pfn));
+		if (writable)
+			*writable = true;
 		return pfn;
 	}
 
-	return gfn_to_pfn(vcpu->kvm, gfn);
+	return gfn_to_pfn_prot(vcpu->kvm, gfn, writing, writable);
 }
 
 static int kvmppc_xlate(struct kvm_vcpu *vcpu, ulong eaddr, bool data,
-			 struct kvmppc_pte *pte)
+			bool iswrite, struct kvmppc_pte *pte)
 {
 	int relocated = (vcpu->arch.shared->msr & (data ? MSR_DR : MSR_IR));
 	int r;
 
 	if (relocated) {
-		r = vcpu->arch.mmu.xlate(vcpu, eaddr, pte, data);
+		r = vcpu->arch.mmu.xlate(vcpu, eaddr, pte, data, iswrite);
 	} else {
 		pte->eaddr = eaddr;
 		pte->raddr = eaddr & KVM_PAM;
@@ -361,7 +364,7 @@ int kvmppc_st(struct kvm_vcpu *vcpu, ulong *eaddr, int size, void *ptr,
 
 	vcpu->stat.st++;
 
-	if (kvmppc_xlate(vcpu, *eaddr, data, &pte))
+	if (kvmppc_xlate(vcpu, *eaddr, data, true, &pte))
 		return -ENOENT;
 
 	*eaddr = pte.raddr;
@@ -383,7 +386,7 @@ int kvmppc_ld(struct kvm_vcpu *vcpu, ulong *eaddr, int size, void *ptr,
 
 	vcpu->stat.ld++;
 
-	if (kvmppc_xlate(vcpu, *eaddr, data, &pte))
+	if (kvmppc_xlate(vcpu, *eaddr, data, false, &pte))
 		goto nopte;
 
 	*eaddr = pte.raddr;
diff --git a/arch/powerpc/kvm/book3s_32_mmu.c b/arch/powerpc/kvm/book3s_32_mmu.c
index b14af6d0934..76a64ce6a5b 100644
--- a/arch/powerpc/kvm/book3s_32_mmu.c
+++ b/arch/powerpc/kvm/book3s_32_mmu.c
@@ -84,7 +84,8 @@ static inline bool sr_nx(u32 sr_raw)
 }
 
 static int kvmppc_mmu_book3s_32_xlate_bat(struct kvm_vcpu *vcpu, gva_t eaddr,
-					  struct kvmppc_pte *pte, bool data);
+					  struct kvmppc_pte *pte, bool data,
+					  bool iswrite);
 static int kvmppc_mmu_book3s_32_esid_to_vsid(struct kvm_vcpu *vcpu, ulong esid,
 					     u64 *vsid);
 
@@ -99,7 +100,7 @@ static u64 kvmppc_mmu_book3s_32_ea_to_vp(struct kvm_vcpu *vcpu, gva_t eaddr,
 	u64 vsid;
 	struct kvmppc_pte pte;
 
-	if (!kvmppc_mmu_book3s_32_xlate_bat(vcpu, eaddr, &pte, data))
+	if (!kvmppc_mmu_book3s_32_xlate_bat(vcpu, eaddr, &pte, data, false))
 		return pte.vpage;
 
 	kvmppc_mmu_book3s_32_esid_to_vsid(vcpu, eaddr >> SID_SHIFT, &vsid);
@@ -146,7 +147,8 @@ static u32 kvmppc_mmu_book3s_32_get_ptem(u32 sre, gva_t eaddr, bool primary)
 }
 
 static int kvmppc_mmu_book3s_32_xlate_bat(struct kvm_vcpu *vcpu, gva_t eaddr,
-					  struct kvmppc_pte *pte, bool data)
+					  struct kvmppc_pte *pte, bool data,
+					  bool iswrite)
 {
 	struct kvmppc_vcpu_book3s *vcpu_book3s = to_book3s(vcpu);
 	struct kvmppc_bat *bat;
@@ -187,8 +189,7 @@ static int kvmppc_mmu_book3s_32_xlate_bat(struct kvm_vcpu *vcpu, gva_t eaddr,
 				printk(KERN_INFO "BAT is not readable!\n");
 				continue;
 			}
-			if (!pte->may_write) {
-				/* let's treat r/o BATs as not-readable for now */
+			if (iswrite && !pte->may_write) {
 				dprintk_pte("BAT is read-only!\n");
 				continue;
 			}
@@ -202,7 +203,7 @@ static int kvmppc_mmu_book3s_32_xlate_bat(struct kvm_vcpu *vcpu, gva_t eaddr,
 
 static int kvmppc_mmu_book3s_32_xlate_pte(struct kvm_vcpu *vcpu, gva_t eaddr,
 				     struct kvmppc_pte *pte, bool data,
-				     bool primary)
+				     bool iswrite, bool primary)
 {
 	u32 sre;
 	hva_t ptegp;
@@ -258,9 +259,6 @@ static int kvmppc_mmu_book3s_32_xlate_pte(struct kvm_vcpu *vcpu, gva_t eaddr,
 					break;
 			}
 
-			if ( !pte->may_read )
-				continue;
-
 			dprintk_pte("MMU: Found PTE -> %x %x - %x\n",
 				    pteg[i], pteg[i+1], pp);
 			found = 1;
@@ -282,11 +280,12 @@ static int kvmppc_mmu_book3s_32_xlate_pte(struct kvm_vcpu *vcpu, gva_t eaddr,
 			pte_r |= PTEG_FLAG_ACCESSED;
 			put_user(pte_r >> 8, addr + 2);
 		}
-		if (pte->may_write && !(pte_r & PTEG_FLAG_DIRTY)) {
-			/* XXX should only set this for stores */
+		if (iswrite && pte->may_write && !(pte_r & PTEG_FLAG_DIRTY)) {
 			pte_r |= PTEG_FLAG_DIRTY;
 			put_user(pte_r, addr + 3);
 		}
+		if (!pte->may_read || (iswrite && !pte->may_write))
+			return -EPERM;
 		return 0;
 	}
 
@@ -305,7 +304,8 @@ no_page_found:
 }
 
 static int kvmppc_mmu_book3s_32_xlate(struct kvm_vcpu *vcpu, gva_t eaddr,
-				      struct kvmppc_pte *pte, bool data)
+				      struct kvmppc_pte *pte, bool data,
+				      bool iswrite)
 {
 	int r;
 	ulong mp_ea = vcpu->arch.magic_page_ea;
@@ -327,11 +327,13 @@ static int kvmppc_mmu_book3s_32_xlate(struct kvm_vcpu *vcpu, gva_t eaddr,
 		return 0;
 	}
 
-	r = kvmppc_mmu_book3s_32_xlate_bat(vcpu, eaddr, pte, data);
+	r = kvmppc_mmu_book3s_32_xlate_bat(vcpu, eaddr, pte, data, iswrite);
 	if (r < 0)
-	       r = kvmppc_mmu_book3s_32_xlate_pte(vcpu, eaddr, pte, data, true);
+		r = kvmppc_mmu_book3s_32_xlate_pte(vcpu, eaddr, pte,
+						   data, iswrite, true);
 	if (r < 0)
-	       r = kvmppc_mmu_book3s_32_xlate_pte(vcpu, eaddr, pte, data, false);
+		r = kvmppc_mmu_book3s_32_xlate_pte(vcpu, eaddr, pte,
+						   data, iswrite, false);
 
 	return r;
 }
diff --git a/arch/powerpc/kvm/book3s_32_mmu_host.c b/arch/powerpc/kvm/book3s_32_mmu_host.c
index 00e619bf608..67332232923 100644
--- a/arch/powerpc/kvm/book3s_32_mmu_host.c
+++ b/arch/powerpc/kvm/book3s_32_mmu_host.c
@@ -138,7 +138,8 @@ static u32 *kvmppc_mmu_get_pteg(struct kvm_vcpu *vcpu, u32 vsid, u32 eaddr,
 
 extern char etext[];
 
-int kvmppc_mmu_map_page(struct kvm_vcpu *vcpu, struct kvmppc_pte *orig_pte)
+int kvmppc_mmu_map_page(struct kvm_vcpu *vcpu, struct kvmppc_pte *orig_pte,
+			bool iswrite)
 {
 	pfn_t hpaddr;
 	u64 vpn;
@@ -152,9 +153,11 @@ int kvmppc_mmu_map_page(struct kvm_vcpu *vcpu, struct kvmppc_pte *orig_pte)
 	bool evict = false;
 	struct hpte_cache *pte;
 	int r = 0;
+	bool writable;
 
 	/* Get host physical address for gpa */
-	hpaddr = kvmppc_gfn_to_pfn(vcpu, orig_pte->raddr >> PAGE_SHIFT);
+	hpaddr = kvmppc_gfn_to_pfn(vcpu, orig_pte->raddr >> PAGE_SHIFT,
+				   iswrite, &writable);
 	if (is_error_noslot_pfn(hpaddr)) {
 		printk(KERN_INFO "Couldn't get guest page for gfn %lx!\n",
 				 orig_pte->eaddr);
@@ -204,7 +207,7 @@ next_pteg:
 		(primary ? 0 : PTE_SEC);
 	pteg1 = hpaddr | PTE_M | PTE_R | PTE_C;
 
-	if (orig_pte->may_write) {
+	if (orig_pte->may_write && writable) {
 		pteg1 |= PP_RWRW;
 		mark_page_dirty(vcpu->kvm, orig_pte->raddr >> PAGE_SHIFT);
 	} else {
@@ -259,6 +262,11 @@ out:
 	return r;
 }
 
+void kvmppc_mmu_unmap_page(struct kvm_vcpu *vcpu, struct kvmppc_pte *pte)
+{
+	kvmppc_mmu_pte_vflush(vcpu, pte->vpage, 0xfffffffffULL);
+}
+
 static struct kvmppc_sid_map *create_sid_map(struct kvm_vcpu *vcpu, u64 gvsid)
 {
 	struct kvmppc_sid_map *map;
diff --git a/arch/powerpc/kvm/book3s_64_mmu.c b/arch/powerpc/kvm/book3s_64_mmu.c
index c110145522e..83da1f868fd 100644
--- a/arch/powerpc/kvm/book3s_64_mmu.c
+++ b/arch/powerpc/kvm/book3s_64_mmu.c
@@ -206,7 +206,8 @@ static int decode_pagesize(struct kvmppc_slb *slbe, u64 r)
 }
 
 static int kvmppc_mmu_book3s_64_xlate(struct kvm_vcpu *vcpu, gva_t eaddr,
-				struct kvmppc_pte *gpte, bool data)
+				      struct kvmppc_pte *gpte, bool data,
+				      bool iswrite)
 {
 	struct kvmppc_slb *slbe;
 	hva_t ptegp;
@@ -345,8 +346,8 @@ do_second:
 		r |= HPTE_R_R;
 		put_user(r >> 8, addr + 6);
 	}
-	if (data && gpte->may_write && !(r & HPTE_R_C)) {
-		/* Set the dirty flag -- XXX even if not writing */
+	if (iswrite && gpte->may_write && !(r & HPTE_R_C)) {
+		/* Set the dirty flag */
 		/* Use a single byte write */
 		char __user *addr = (char __user *) &pteg[i+1];
 		r |= HPTE_R_C;
@@ -355,7 +356,7 @@ do_second:
 
 	mutex_unlock(&vcpu->kvm->arch.hpt_mutex);
 
-	if (!gpte->may_read)
+	if (!gpte->may_read || (iswrite && !gpte->may_write))
 		return -EPERM;
 	return 0;
 
diff --git a/arch/powerpc/kvm/book3s_64_mmu_host.c b/arch/powerpc/kvm/book3s_64_mmu_host.c
index 6bda504ceda..cc9fb89b888 100644
--- a/arch/powerpc/kvm/book3s_64_mmu_host.c
+++ b/arch/powerpc/kvm/book3s_64_mmu_host.c
@@ -78,7 +78,8 @@ static struct kvmppc_sid_map *find_sid_vsid(struct kvm_vcpu *vcpu, u64 gvsid)
 	return NULL;
 }
 
-int kvmppc_mmu_map_page(struct kvm_vcpu *vcpu, struct kvmppc_pte *orig_pte)
+int kvmppc_mmu_map_page(struct kvm_vcpu *vcpu, struct kvmppc_pte *orig_pte,
+			bool iswrite)
 {
 	unsigned long vpn;
 	pfn_t hpaddr;
@@ -91,9 +92,11 @@ int kvmppc_mmu_map_page(struct kvm_vcpu *vcpu, struct kvmppc_pte *orig_pte)
 	struct kvmppc_sid_map *map;
 	int r = 0;
 	int hpsize = MMU_PAGE_4K;
+	bool writable;
 
 	/* Get host physical address for gpa */
-	hpaddr = kvmppc_gfn_to_pfn(vcpu, orig_pte->raddr >> PAGE_SHIFT);
+	hpaddr = kvmppc_gfn_to_pfn(vcpu, orig_pte->raddr >> PAGE_SHIFT,
+				   iswrite, &writable);
 	if (is_error_noslot_pfn(hpaddr)) {
 		printk(KERN_INFO "Couldn't get guest page for gfn %lx!\n", orig_pte->eaddr);
 		r = -EINVAL;
@@ -119,7 +122,7 @@ int kvmppc_mmu_map_page(struct kvm_vcpu *vcpu, struct kvmppc_pte *orig_pte)
 
 	vpn = hpt_vpn(orig_pte->eaddr, map->host_vsid, MMU_SEGSIZE_256M);
 
-	if (!orig_pte->may_write)
+	if (!orig_pte->may_write || !writable)
 		rflags |= HPTE_R_PP;
 	else
 		mark_page_dirty(vcpu->kvm, orig_pte->raddr >> PAGE_SHIFT);
@@ -186,6 +189,17 @@ out:
 	return r;
 }
 
+void kvmppc_mmu_unmap_page(struct kvm_vcpu *vcpu, struct kvmppc_pte *pte)
+{
+	u64 mask = 0xfffffffffULL;
+	u64 vsid;
+
+	vcpu->arch.mmu.esid_to_vsid(vcpu, pte->eaddr >> SID_SHIFT, &vsid);
+	if (vsid & VSID_64K)
+		mask = 0xffffffff0ULL;
+	kvmppc_mmu_pte_vflush(vcpu, pte->vpage, mask);
+}
+
 static struct kvmppc_sid_map *create_sid_map(struct kvm_vcpu *vcpu, u64 gvsid)
 {
 	struct kvmppc_sid_map *map;
diff --git a/arch/powerpc/kvm/book3s_64_mmu_hv.c b/arch/powerpc/kvm/book3s_64_mmu_hv.c
index ccb89a048bf..394fef820f0 100644
--- a/arch/powerpc/kvm/book3s_64_mmu_hv.c
+++ b/arch/powerpc/kvm/book3s_64_mmu_hv.c
@@ -451,7 +451,7 @@ static unsigned long kvmppc_mmu_get_real_addr(unsigned long v, unsigned long r,
 }
 
 static int kvmppc_mmu_book3s_64_hv_xlate(struct kvm_vcpu *vcpu, gva_t eaddr,
-			struct kvmppc_pte *gpte, bool data)
+			struct kvmppc_pte *gpte, bool data, bool iswrite)
 {
 	struct kvm *kvm = vcpu->kvm;
 	struct kvmppc_slb *slbe;
diff --git a/arch/powerpc/kvm/book3s_pr.c b/arch/powerpc/kvm/book3s_pr.c
index 677d7e33b1f..2f84ed80718 100644
--- a/arch/powerpc/kvm/book3s_pr.c
+++ b/arch/powerpc/kvm/book3s_pr.c
@@ -401,6 +401,7 @@ int kvmppc_handle_pagefault(struct kvm_run *run, struct kvm_vcpu *vcpu,
 			    ulong eaddr, int vec)
 {
 	bool data = (vec == BOOK3S_INTERRUPT_DATA_STORAGE);
+	bool iswrite = false;
 	int r = RESUME_GUEST;
 	int relocated;
 	int page_found = 0;
@@ -411,10 +412,12 @@ int kvmppc_handle_pagefault(struct kvm_run *run, struct kvm_vcpu *vcpu,
 	u64 vsid;
 
 	relocated = data ? dr : ir;
+	if (data && (vcpu->arch.fault_dsisr & DSISR_ISSTORE))
+		iswrite = true;
 
 	/* Resolve real address if translation turned on */
 	if (relocated) {
-		page_found = vcpu->arch.mmu.xlate(vcpu, eaddr, &pte, data);
+		page_found = vcpu->arch.mmu.xlate(vcpu, eaddr, &pte, data, iswrite);
 	} else {
 		pte.may_execute = true;
 		pte.may_read = true;
@@ -475,12 +478,20 @@ int kvmppc_handle_pagefault(struct kvm_run *run, struct kvm_vcpu *vcpu,
 		kvmppc_book3s_queue_irqprio(vcpu, vec + 0x80);
 	} else if (!is_mmio &&
 		   kvmppc_visible_gfn(vcpu, pte.raddr >> PAGE_SHIFT)) {
+		if (data && !(vcpu->arch.fault_dsisr & DSISR_NOHPTE)) {
+			/*
+			 * There is already a host HPTE there, presumably
+			 * a read-only one for a page the guest thinks
+			 * is writable, so get rid of it first.
+			 */
+			kvmppc_mmu_unmap_page(vcpu, &pte);
+		}
 		/* The guest's PTE is not mapped yet. Map on the host */
-		kvmppc_mmu_map_page(vcpu, &pte);
+		kvmppc_mmu_map_page(vcpu, &pte, iswrite);
 		if (data)
 			vcpu->stat.sp_storage++;
 		else if (vcpu->arch.mmu.is_dcbz32(vcpu) &&
-			(!(vcpu->arch.hflags & BOOK3S_HFLAG_DCBZ32)))
+			 (!(vcpu->arch.hflags & BOOK3S_HFLAG_DCBZ32)))
 			kvmppc_patch_dcbz(vcpu, &pte);
 	} else {
 		/* MMIO */
@@ -732,7 +743,9 @@ int kvmppc_handle_exit(struct kvm_run *run, struct kvm_vcpu *vcpu,
 
 		/* only care about PTEG not found errors, but leave NX alone */
 		if (shadow_srr1 & 0x40000000) {
+			int idx = srcu_read_lock(&vcpu->kvm->srcu);
 			r = kvmppc_handle_pagefault(run, vcpu, kvmppc_get_pc(vcpu), exit_nr);
+			srcu_read_unlock(&vcpu->kvm->srcu, idx);
 			vcpu->stat.sp_instruc++;
 		} else if (vcpu->arch.mmu.is_dcbz32(vcpu) &&
 			  (!(vcpu->arch.hflags & BOOK3S_HFLAG_DCBZ32))) {
@@ -774,9 +787,15 @@ int kvmppc_handle_exit(struct kvm_run *run, struct kvm_vcpu *vcpu,
 		}
 #endif
 
-		/* The only case we need to handle is missing shadow PTEs */
-		if (fault_dsisr & DSISR_NOHPTE) {
+		/*
+		 * We need to handle missing shadow PTEs, and
+		 * protection faults due to us mapping a page read-only
+		 * when the guest thinks it is writable.
+		 */
+		if (fault_dsisr & (DSISR_NOHPTE | DSISR_PROTFAULT)) {
+			int idx = srcu_read_lock(&vcpu->kvm->srcu);
 			r = kvmppc_handle_pagefault(run, vcpu, dar, exit_nr);
+			srcu_read_unlock(&vcpu->kvm->srcu, idx);
 		} else {
 			vcpu->arch.shared->dar = dar;
 			vcpu->arch.shared->dsisr = fault_dsisr;
-- 
cgit v1.2.3-70-g09d2


From d78bca72961ae816181b386ff6b347419dfcd5cf Mon Sep 17 00:00:00 2001
From: Paul Mackerras <paulus@samba.org>
Date: Fri, 20 Sep 2013 14:52:52 +1000
Subject: KVM: PPC: Book3S PR: Use mmu_notifier_retry() in
 kvmppc_mmu_map_page()

When the MM code is invalidating a range of pages, it calls the KVM
kvm_mmu_notifier_invalidate_range_start() notifier function, which calls
kvm_unmap_hva_range(), which arranges to flush all the existing host
HPTEs for guest pages.  However, the Linux PTEs for the range being
flushed are still valid at that point.  We are not supposed to establish
any new references to pages in the range until the ...range_end()
notifier gets called.  The PPC-specific KVM code doesn't get any
explicit notification of that; instead, we are supposed to use
mmu_notifier_retry() to test whether we are or have been inside a
range flush notifier pair while we have been getting a page and
instantiating a host HPTE for the page.

This therefore adds a call to mmu_notifier_retry inside
kvmppc_mmu_map_page().  This call is inside a region locked with
kvm->mmu_lock, which is the same lock that is called by the KVM
MMU notifier functions, thus ensuring that no new notification can
proceed while we are in the locked region.  Inside this region we
also create the host HPTE and link the corresponding hpte_cache
structure into the lists used to find it later.  We cannot allocate
the hpte_cache structure inside this locked region because that can
lead to deadlock, so we allocate it outside the region and free it
if we end up not using it.

This also moves the updates of vcpu3s->hpte_cache_count inside the
regions locked with vcpu3s->mmu_lock, and does the increment in
kvmppc_mmu_hpte_cache_map() when the pte is added to the cache
rather than when it is allocated, in order that the hpte_cache_count
is accurate.

Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Alexander Graf <agraf@suse.de>
---
 arch/powerpc/include/asm/kvm_book3s.h |  1 +
 arch/powerpc/kvm/book3s_64_mmu_host.c | 37 ++++++++++++++++++++++++++---------
 arch/powerpc/kvm/book3s_mmu_hpte.c    | 14 +++++++++----
 3 files changed, 39 insertions(+), 13 deletions(-)

(limited to 'arch/powerpc/kvm')

diff --git a/arch/powerpc/include/asm/kvm_book3s.h b/arch/powerpc/include/asm/kvm_book3s.h
index a07bd7e7d4a..0ec00f4fef9 100644
--- a/arch/powerpc/include/asm/kvm_book3s.h
+++ b/arch/powerpc/include/asm/kvm_book3s.h
@@ -142,6 +142,7 @@ extern long kvmppc_hv_find_lock_hpte(struct kvm *kvm, gva_t eaddr,
 
 extern void kvmppc_mmu_hpte_cache_map(struct kvm_vcpu *vcpu, struct hpte_cache *pte);
 extern struct hpte_cache *kvmppc_mmu_hpte_cache_next(struct kvm_vcpu *vcpu);
+extern void kvmppc_mmu_hpte_cache_free(struct hpte_cache *pte);
 extern void kvmppc_mmu_hpte_destroy(struct kvm_vcpu *vcpu);
 extern int kvmppc_mmu_hpte_init(struct kvm_vcpu *vcpu);
 extern void kvmppc_mmu_invalidate_pte(struct kvm_vcpu *vcpu, struct hpte_cache *pte);
diff --git a/arch/powerpc/kvm/book3s_64_mmu_host.c b/arch/powerpc/kvm/book3s_64_mmu_host.c
index cc9fb89b888..307e6e838e0 100644
--- a/arch/powerpc/kvm/book3s_64_mmu_host.c
+++ b/arch/powerpc/kvm/book3s_64_mmu_host.c
@@ -93,6 +93,13 @@ int kvmppc_mmu_map_page(struct kvm_vcpu *vcpu, struct kvmppc_pte *orig_pte,
 	int r = 0;
 	int hpsize = MMU_PAGE_4K;
 	bool writable;
+	unsigned long mmu_seq;
+	struct kvm *kvm = vcpu->kvm;
+	struct hpte_cache *cpte;
+
+	/* used to check for invalidations in progress */
+	mmu_seq = kvm->mmu_notifier_seq;
+	smp_rmb();
 
 	/* Get host physical address for gpa */
 	hpaddr = kvmppc_gfn_to_pfn(vcpu, orig_pte->raddr >> PAGE_SHIFT,
@@ -143,6 +150,14 @@ int kvmppc_mmu_map_page(struct kvm_vcpu *vcpu, struct kvmppc_pte *orig_pte,
 
 	hash = hpt_hash(vpn, mmu_psize_defs[hpsize].shift, MMU_SEGSIZE_256M);
 
+	cpte = kvmppc_mmu_hpte_cache_next(vcpu);
+
+	spin_lock(&kvm->mmu_lock);
+	if (!cpte || mmu_notifier_retry(kvm, mmu_seq)) {
+		r = -EAGAIN;
+		goto out_unlock;
+	}
+
 map_again:
 	hpteg = ((hash & htab_hash_mask) * HPTES_PER_GROUP);
 
@@ -150,7 +165,7 @@ map_again:
 	if (attempt > 1)
 		if (ppc_md.hpte_remove(hpteg) < 0) {
 			r = -1;
-			goto out;
+			goto out_unlock;
 		}
 
 	ret = ppc_md.hpte_insert(hpteg, vpn, hpaddr, rflags, vflags,
@@ -163,8 +178,6 @@ map_again:
 		attempt++;
 		goto map_again;
 	} else {
-		struct hpte_cache *pte = kvmppc_mmu_hpte_cache_next(vcpu);
-
 		trace_kvm_book3s_64_mmu_map(rflags, hpteg,
 					    vpn, hpaddr, orig_pte);
 
@@ -175,15 +188,21 @@ map_again:
 			hpteg = ((hash & htab_hash_mask) * HPTES_PER_GROUP);
 		}
 
-		pte->slot = hpteg + (ret & 7);
-		pte->host_vpn = vpn;
-		pte->pte = *orig_pte;
-		pte->pfn = hpaddr >> PAGE_SHIFT;
-		pte->pagesize = hpsize;
+		cpte->slot = hpteg + (ret & 7);
+		cpte->host_vpn = vpn;
+		cpte->pte = *orig_pte;
+		cpte->pfn = hpaddr >> PAGE_SHIFT;
+		cpte->pagesize = hpsize;
 
-		kvmppc_mmu_hpte_cache_map(vcpu, pte);
+		kvmppc_mmu_hpte_cache_map(vcpu, cpte);
+		cpte = NULL;
 	}
+
+out_unlock:
+	spin_unlock(&kvm->mmu_lock);
 	kvm_release_pfn_clean(hpaddr >> PAGE_SHIFT);
+	if (cpte)
+		kvmppc_mmu_hpte_cache_free(cpte);
 
 out:
 	return r;
diff --git a/arch/powerpc/kvm/book3s_mmu_hpte.c b/arch/powerpc/kvm/book3s_mmu_hpte.c
index d2d280b1677..6b79bfc44ba 100644
--- a/arch/powerpc/kvm/book3s_mmu_hpte.c
+++ b/arch/powerpc/kvm/book3s_mmu_hpte.c
@@ -98,6 +98,8 @@ void kvmppc_mmu_hpte_cache_map(struct kvm_vcpu *vcpu, struct hpte_cache *pte)
 			   &vcpu3s->hpte_hash_vpte_64k[index]);
 #endif
 
+	vcpu3s->hpte_cache_count++;
+
 	spin_unlock(&vcpu3s->mmu_lock);
 }
 
@@ -131,10 +133,10 @@ static void invalidate_pte(struct kvm_vcpu *vcpu, struct hpte_cache *pte)
 #ifdef CONFIG_PPC_BOOK3S_64
 	hlist_del_init_rcu(&pte->list_vpte_64k);
 #endif
+	vcpu3s->hpte_cache_count--;
 
 	spin_unlock(&vcpu3s->mmu_lock);
 
-	vcpu3s->hpte_cache_count--;
 	call_rcu(&pte->rcu_head, free_pte_rcu);
 }
 
@@ -331,15 +333,19 @@ struct hpte_cache *kvmppc_mmu_hpte_cache_next(struct kvm_vcpu *vcpu)
 	struct kvmppc_vcpu_book3s *vcpu3s = to_book3s(vcpu);
 	struct hpte_cache *pte;
 
-	pte = kmem_cache_zalloc(hpte_cache, GFP_KERNEL);
-	vcpu3s->hpte_cache_count++;
-
 	if (vcpu3s->hpte_cache_count == HPTEG_CACHE_NUM)
 		kvmppc_mmu_pte_flush_all(vcpu);
 
+	pte = kmem_cache_zalloc(hpte_cache, GFP_KERNEL);
+
 	return pte;
 }
 
+void kvmppc_mmu_hpte_cache_free(struct hpte_cache *pte)
+{
+	kmem_cache_free(hpte_cache, pte);
+}
+
 void kvmppc_mmu_hpte_destroy(struct kvm_vcpu *vcpu)
 {
 	kvmppc_mmu_pte_flush(vcpu, 0, 0);
-- 
cgit v1.2.3-70-g09d2


From adc0bafe00f4c7e5f052c9f29e75a072e03a19fc Mon Sep 17 00:00:00 2001
From: Paul Mackerras <paulus@samba.org>
Date: Fri, 20 Sep 2013 14:52:53 +1000
Subject: KVM: PPC: Book3S PR: Mark pages accessed, and dirty if being written

The mark_page_dirty() function, despite what its name might suggest,
doesn't actually mark the page as dirty as far as the MM subsystem is
concerned.  It merely sets a bit in KVM's map of dirty pages, if
userspace has requested dirty tracking for the relevant memslot.
To tell the MM subsystem that the page is dirty, we have to call
kvm_set_pfn_dirty() (or an equivalent such as SetPageDirty()).

This adds a call to kvm_set_pfn_dirty(), and while we are here, also
adds a call to kvm_set_pfn_accessed() to tell the MM subsystem that
the page has been accessed.  Since we are now using the pfn in
several places, this adds a 'pfn' variable to store it and changes
the places that used hpaddr >> PAGE_SHIFT to use pfn instead, which
is the same thing.

This also changes a use of HPTE_R_PP to PP_RXRX.  Both are 3, but
PP_RXRX is more informative as being the read-only page permission
bit setting.

Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Alexander Graf <agraf@suse.de>
---
 arch/powerpc/kvm/book3s_64_mmu_host.c | 26 +++++++++++++++-----------
 1 file changed, 15 insertions(+), 11 deletions(-)

(limited to 'arch/powerpc/kvm')

diff --git a/arch/powerpc/kvm/book3s_64_mmu_host.c b/arch/powerpc/kvm/book3s_64_mmu_host.c
index 307e6e838e0..e2ab8a747fb 100644
--- a/arch/powerpc/kvm/book3s_64_mmu_host.c
+++ b/arch/powerpc/kvm/book3s_64_mmu_host.c
@@ -96,20 +96,21 @@ int kvmppc_mmu_map_page(struct kvm_vcpu *vcpu, struct kvmppc_pte *orig_pte,
 	unsigned long mmu_seq;
 	struct kvm *kvm = vcpu->kvm;
 	struct hpte_cache *cpte;
+	unsigned long gfn = orig_pte->raddr >> PAGE_SHIFT;
+	unsigned long pfn;
 
 	/* used to check for invalidations in progress */
 	mmu_seq = kvm->mmu_notifier_seq;
 	smp_rmb();
 
 	/* Get host physical address for gpa */
-	hpaddr = kvmppc_gfn_to_pfn(vcpu, orig_pte->raddr >> PAGE_SHIFT,
-				   iswrite, &writable);
-	if (is_error_noslot_pfn(hpaddr)) {
-		printk(KERN_INFO "Couldn't get guest page for gfn %lx!\n", orig_pte->eaddr);
+	pfn = kvmppc_gfn_to_pfn(vcpu, gfn, iswrite, &writable);
+	if (is_error_noslot_pfn(pfn)) {
+		printk(KERN_INFO "Couldn't get guest page for gfn %lx!\n", gfn);
 		r = -EINVAL;
 		goto out;
 	}
-	hpaddr <<= PAGE_SHIFT;
+	hpaddr = pfn << PAGE_SHIFT;
 
 	/* and write the mapping ea -> hpa into the pt */
 	vcpu->arch.mmu.esid_to_vsid(vcpu, orig_pte->eaddr >> SID_SHIFT, &vsid);
@@ -129,15 +130,18 @@ int kvmppc_mmu_map_page(struct kvm_vcpu *vcpu, struct kvmppc_pte *orig_pte,
 
 	vpn = hpt_vpn(orig_pte->eaddr, map->host_vsid, MMU_SEGSIZE_256M);
 
+	kvm_set_pfn_accessed(pfn);
 	if (!orig_pte->may_write || !writable)
-		rflags |= HPTE_R_PP;
-	else
-		mark_page_dirty(vcpu->kvm, orig_pte->raddr >> PAGE_SHIFT);
+		rflags |= PP_RXRX;
+	else {
+		mark_page_dirty(vcpu->kvm, gfn);
+		kvm_set_pfn_dirty(pfn);
+	}
 
 	if (!orig_pte->may_execute)
 		rflags |= HPTE_R_N;
 	else
-		kvmppc_mmu_flush_icache(hpaddr >> PAGE_SHIFT);
+		kvmppc_mmu_flush_icache(pfn);
 
 	/*
 	 * Use 64K pages if possible; otherwise, on 64K page kernels,
@@ -191,7 +195,7 @@ map_again:
 		cpte->slot = hpteg + (ret & 7);
 		cpte->host_vpn = vpn;
 		cpte->pte = *orig_pte;
-		cpte->pfn = hpaddr >> PAGE_SHIFT;
+		cpte->pfn = pfn;
 		cpte->pagesize = hpsize;
 
 		kvmppc_mmu_hpte_cache_map(vcpu, cpte);
@@ -200,7 +204,7 @@ map_again:
 
 out_unlock:
 	spin_unlock(&kvm->mmu_lock);
-	kvm_release_pfn_clean(hpaddr >> PAGE_SHIFT);
+	kvm_release_pfn_clean(pfn);
 	if (cpte)
 		kvmppc_mmu_hpte_cache_free(cpte);
 
-- 
cgit v1.2.3-70-g09d2


From 491d6ecc17171518565358c2cfe33b59722d234c Mon Sep 17 00:00:00 2001
From: Paul Mackerras <paulus@samba.org>
Date: Fri, 20 Sep 2013 14:52:54 +1000
Subject: KVM: PPC: Book3S PR: Reduce number of shadow PTEs invalidated by MMU
 notifiers

Currently, whenever any of the MMU notifier callbacks get called, we
invalidate all the shadow PTEs.  This is inefficient because it means
that we typically then get a lot of DSIs and ISIs in the guest to fault
the shadow PTEs back in.  We do this even if the address range being
notified doesn't correspond to guest memory.

This commit adds code to scan the memslot array to find out what range(s)
of guest physical addresses corresponds to the host virtual address range
being affected.  For each such range we flush only the shadow PTEs
for the range, on all cpus.

Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Alexander Graf <agraf@suse.de>
---
 arch/powerpc/kvm/book3s_pr.c | 40 ++++++++++++++++++++++++++++++++--------
 1 file changed, 32 insertions(+), 8 deletions(-)

(limited to 'arch/powerpc/kvm')

diff --git a/arch/powerpc/kvm/book3s_pr.c b/arch/powerpc/kvm/book3s_pr.c
index 2f84ed80718..6075dbd0b36 100644
--- a/arch/powerpc/kvm/book3s_pr.c
+++ b/arch/powerpc/kvm/book3s_pr.c
@@ -150,24 +150,48 @@ int kvmppc_core_check_requests(struct kvm_vcpu *vcpu)
 }
 
 /************* MMU Notifiers *************/
+static void do_kvm_unmap_hva(struct kvm *kvm, unsigned long start,
+			     unsigned long end)
+{
+	long i;
+	struct kvm_vcpu *vcpu;
+	struct kvm_memslots *slots;
+	struct kvm_memory_slot *memslot;
+
+	slots = kvm_memslots(kvm);
+	kvm_for_each_memslot(memslot, slots) {
+		unsigned long hva_start, hva_end;
+		gfn_t gfn, gfn_end;
+
+		hva_start = max(start, memslot->userspace_addr);
+		hva_end = min(end, memslot->userspace_addr +
+					(memslot->npages << PAGE_SHIFT));
+		if (hva_start >= hva_end)
+			continue;
+		/*
+		 * {gfn(page) | page intersects with [hva_start, hva_end)} =
+		 * {gfn, gfn+1, ..., gfn_end-1}.
+		 */
+		gfn = hva_to_gfn_memslot(hva_start, memslot);
+		gfn_end = hva_to_gfn_memslot(hva_end + PAGE_SIZE - 1, memslot);
+		kvm_for_each_vcpu(i, vcpu, kvm)
+			kvmppc_mmu_pte_pflush(vcpu, gfn << PAGE_SHIFT,
+					      gfn_end << PAGE_SHIFT);
+	}
+}
 
 int kvm_unmap_hva(struct kvm *kvm, unsigned long hva)
 {
 	trace_kvm_unmap_hva(hva);
 
-	/*
-	 * Flush all shadow tlb entries everywhere. This is slow, but
-	 * we are 100% sure that we catch the to be unmapped page
-	 */
-	kvm_flush_remote_tlbs(kvm);
+	do_kvm_unmap_hva(kvm, hva, hva + PAGE_SIZE);
 
 	return 0;
 }
 
 int kvm_unmap_hva_range(struct kvm *kvm, unsigned long start, unsigned long end)
 {
-	/* kvm_unmap_hva flushes everything anyways */
-	kvm_unmap_hva(kvm, start);
+	do_kvm_unmap_hva(kvm, start, end);
 
 	return 0;
 }
@@ -187,7 +211,7 @@ int kvm_test_age_hva(struct kvm *kvm, unsigned long hva)
 void kvm_set_spte_hva(struct kvm *kvm, unsigned long hva, pte_t pte)
 {
 	/* The page will get remapped properly on its next fault */
-	kvm_unmap_hva(kvm, hva);
+	do_kvm_unmap_hva(kvm, hva, hva + PAGE_SIZE);
 }
 
 /*****************************************/
-- 
cgit v1.2.3-70-g09d2


From f1378b1c0bdce349e21f271dec0612a6cfac5d14 Mon Sep 17 00:00:00 2001
From: Paul Mackerras <paulus@samba.org>
Date: Fri, 27 Sep 2013 15:33:43 +0530
Subject: kvm: powerpc: book3s hv: Fix vcore leak

add kvmppc_free_vcores() to free the kvmppc_vcore structures
that we allocate for a guest, which are currently being leaked.

Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
Signed-off-by: Alexander Graf <agraf@suse.de>
---
 arch/powerpc/kvm/book3s_hv.c | 10 ++++++++++
 1 file changed, 10 insertions(+)

(limited to 'arch/powerpc/kvm')

diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c
index de9520f9241..b4d5b3b0676 100644
--- a/arch/powerpc/kvm/book3s_hv.c
+++ b/arch/powerpc/kvm/book3s_hv.c
@@ -2050,10 +2050,20 @@ int kvmppc_core_init_vm(struct kvm *kvm)
 	return 0;
 }
 
+static void kvmppc_free_vcores(struct kvm *kvm)
+{
+	long int i;
+
+	for (i = 0; i < KVM_MAX_VCORES; ++i)
+		kfree(kvm->arch.vcores[i]);
+	kvm->arch.online_vcores = 0;
+}
+
 void kvmppc_core_destroy_vm(struct kvm *kvm)
 {
 	uninhibit_secondary_onlining();
 
+	kvmppc_free_vcores(kvm);
 	if (kvm->arch.rma) {
 		kvm_release_rma(kvm->arch.rma);
 		kvm->arch.rma = NULL;
-- 
cgit v1.2.3-70-g09d2


From 44a3add86311bb9d060d795bcdcdc9b8c7a35bd0 Mon Sep 17 00:00:00 2001
From: Paul Mackerras <paulus@samba.org>
Date: Fri, 4 Oct 2013 21:45:04 +1000
Subject: KVM: PPC: Book3S HV: Better handling of exceptions that happen in
 real mode

When an interrupt or exception happens in the guest that comes to the
host, the CPU goes to hypervisor real mode (MMU off) to handle the
exception but doesn't change the MMU context.  After saving a few
registers, we then clear the "in guest" flag.  If, for any reason,
we get an exception in the real-mode code, that then gets handled
by the normal kernel exception handlers, which turn the MMU on.  This
is disastrous if the MMU is still set to the guest context, since we
end up executing instructions from random places in the guest kernel
with hypervisor privilege.

In order to catch this situation, we define a new value for the "in guest"
flag, KVM_GUEST_MODE_HOST_HV, to indicate that we are in hypervisor real
mode with guest MMU context.  If the "in guest" flag is set to this value,
we branch off to an emergency handler.  For the moment, this just does
a branch to self to stop the CPU from doing anything further.

While we're here, we define another new flag value to indicate that we
are in a HV guest, as distinct from a PR guest.  This will be useful
when we have a kernel that can support both PR and HV guests concurrently.

Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Alexander Graf <agraf@suse.de>
---
 arch/powerpc/include/asm/kvm_asm.h      |  2 ++
 arch/powerpc/kvm/book3s_hv_rmhandlers.S | 31 +++++++++++++++++++++++++------
 2 files changed, 27 insertions(+), 6 deletions(-)

(limited to 'arch/powerpc/kvm')

diff --git a/arch/powerpc/include/asm/kvm_asm.h b/arch/powerpc/include/asm/kvm_asm.h
index e2d4d467ee9..1bd92fd43cf 100644
--- a/arch/powerpc/include/asm/kvm_asm.h
+++ b/arch/powerpc/include/asm/kvm_asm.h
@@ -138,6 +138,8 @@
 #define KVM_GUEST_MODE_NONE	0
 #define KVM_GUEST_MODE_GUEST	1
 #define KVM_GUEST_MODE_SKIP	2
+#define KVM_GUEST_MODE_GUEST_HV	3
+#define KVM_GUEST_MODE_HOST_HV	4
 
 #define KVM_INST_FETCH_FAILED	-1
 
diff --git a/arch/powerpc/kvm/book3s_hv_rmhandlers.S b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
index 6e3370f42a6..84105eb18a0 100644
--- a/arch/powerpc/kvm/book3s_hv_rmhandlers.S
+++ b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
@@ -387,6 +387,9 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_206)
 	mtspr	SPRN_DAR, r5
 	mtspr	SPRN_DSISR, r6
 
+	li	r6, KVM_GUEST_MODE_HOST_HV
+	stb	r6, HSTATE_IN_GUEST(r13)
+
 BEGIN_FTR_SECTION
 	/* Restore AMR and UAMOR, set AMOR to all 1s */
 	ld	r5,VCPU_AMR(r4)
@@ -690,7 +693,7 @@ fast_guest_return:
 	mtspr	SPRN_HSRR1,r11
 
 	/* Activate guest mode, so faults get handled by KVM */
-	li	r9, KVM_GUEST_MODE_GUEST
+	li	r9, KVM_GUEST_MODE_GUEST_HV
 	stb	r9, HSTATE_IN_GUEST(r13)
 
 	/* Enter guest */
@@ -750,6 +753,14 @@ kvmppc_interrupt:
 	 */
 	/* abuse host_r2 as third scratch area; we get r2 from PACATOC(r13) */
 	std	r9, HSTATE_HOST_R2(r13)
+
+	lbz	r9, HSTATE_IN_GUEST(r13)
+	cmpwi	r9, KVM_GUEST_MODE_HOST_HV
+	beq	kvmppc_bad_host_intr
+	/* We're now back in the host but in guest MMU context */
+	li	r9, KVM_GUEST_MODE_HOST_HV
+	stb	r9, HSTATE_IN_GUEST(r13)
+
 	ld	r9, HSTATE_KVM_VCPU(r13)
 
 	/* Save registers */
@@ -801,10 +812,6 @@ END_FTR_SECTION_IFSET(CPU_FTR_HAS_PPR)
 	std	r3, VCPU_GPR(R13)(r9)
 	std	r4, VCPU_LR(r9)
 
-	/* Unset guest mode */
-	li	r0, KVM_GUEST_MODE_NONE
-	stb	r0, HSTATE_IN_GUEST(r13)
-
 	stw	r12,VCPU_TRAP(r9)
 
 	/* Save HEIR (HV emulation assist reg) in last_inst
@@ -1198,6 +1205,10 @@ BEGIN_FTR_SECTION
 	mtspr	SPRN_AMR,r6
 END_FTR_SECTION_IFSET(CPU_FTR_ARCH_206)
 
+	/* Unset guest mode */
+	li	r0, KVM_GUEST_MODE_NONE
+	stb	r0, HSTATE_IN_GUEST(r13)
+
 	/* Switch DSCR back to host value */
 BEGIN_FTR_SECTION
 	mfspr	r8, SPRN_DSCR
@@ -1400,7 +1411,7 @@ fast_interrupt_c_return:
 	stw	r8, VCPU_LAST_INST(r9)
 
 	/* Unset guest mode. */
-	li	r0, KVM_GUEST_MODE_NONE
+	li	r0, KVM_GUEST_MODE_HOST_HV
 	stb	r0, HSTATE_IN_GUEST(r13)
 	b	guest_exit_cont
 
@@ -1949,3 +1960,11 @@ END_FTR_SECTION_IFSET(CPU_FTR_ALTIVEC)
 	lwz	r7,VCPU_VRSAVE(r4)
 	mtspr	SPRN_VRSAVE,r7
 	blr
+
+/*
+ * We come here if we get any exception or interrupt while we are
+ * executing host real mode code while in guest MMU context.
+ * For now just spin, but we should do something better.
+ */
+kvmppc_bad_host_intr:
+	b	.
-- 
cgit v1.2.3-70-g09d2


From fd75cb51f261d77eadd83bcb88f2016f53f4af4a Mon Sep 17 00:00:00 2001
From: Bharat Bhushan <r65777@freescale.com>
Date: Thu, 19 Sep 2013 11:32:42 +0530
Subject: kvm: powerpc: allow guest control "E" attribute in mas2

"E" bit in MAS2 bit indicates whether the page is accessed
in Little-Endian or Big-Endian byte order.
There is no reason to stop guest setting  "E", so allow him."

Signed-off-by: Bharat Bhushan <bharat.bhushan@freescale.com>
Signed-off-by: Alexander Graf <agraf@suse.de>
---
 arch/powerpc/kvm/e500.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'arch/powerpc/kvm')

diff --git a/arch/powerpc/kvm/e500.h b/arch/powerpc/kvm/e500.h
index c2e5e98453a..277cb1851af 100644
--- a/arch/powerpc/kvm/e500.h
+++ b/arch/powerpc/kvm/e500.h
@@ -117,7 +117,7 @@ static inline struct kvmppc_vcpu_e500 *to_e500(struct kvm_vcpu *vcpu)
 #define E500_TLB_USER_PERM_MASK (MAS3_UX|MAS3_UR|MAS3_UW)
 #define E500_TLB_SUPER_PERM_MASK (MAS3_SX|MAS3_SR|MAS3_SW)
 #define MAS2_ATTRIB_MASK \
-	  (MAS2_X0 | MAS2_X1)
+	  (MAS2_X0 | MAS2_X1 | MAS2_E)
 #define MAS3_ATTRIB_MASK \
 	  (MAS3_U0 | MAS3_U1 | MAS3_U2 | MAS3_U3 \
 	   | E500_TLB_USER_PERM_MASK | E500_TLB_SUPER_PERM_MASK)
-- 
cgit v1.2.3-70-g09d2


From ca8ccbd41dcca5ef092d0d8bb972ac9307925cfe Mon Sep 17 00:00:00 2001
From: Bharat Bhushan <r65777@freescale.com>
Date: Thu, 19 Sep 2013 11:32:43 +0530
Subject: kvm: powerpc: allow guest control "G" attribute in mas2

"G" bit in MAS2 indicates whether the page is Guarded.
There is no reason to stop guest setting  "G", so allow him.

Signed-off-by: Bharat Bhushan <bharat.bhushan@freescale.com>
Signed-off-by: Alexander Graf <agraf@suse.de>
---
 arch/powerpc/kvm/e500.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'arch/powerpc/kvm')

diff --git a/arch/powerpc/kvm/e500.h b/arch/powerpc/kvm/e500.h
index 277cb1851af..4fd9650eb01 100644
--- a/arch/powerpc/kvm/e500.h
+++ b/arch/powerpc/kvm/e500.h
@@ -117,7 +117,7 @@ static inline struct kvmppc_vcpu_e500 *to_e500(struct kvm_vcpu *vcpu)
 #define E500_TLB_USER_PERM_MASK (MAS3_UX|MAS3_UR|MAS3_UW)
 #define E500_TLB_SUPER_PERM_MASK (MAS3_SX|MAS3_SR|MAS3_SW)
 #define MAS2_ATTRIB_MASK \
-	  (MAS2_X0 | MAS2_X1 | MAS2_E)
+	  (MAS2_X0 | MAS2_X1 | MAS2_E | MAS2_G)
 #define MAS3_ATTRIB_MASK \
 	  (MAS3_U0 | MAS3_U1 | MAS3_U2 | MAS3_U3 \
 	   | E500_TLB_USER_PERM_MASK | E500_TLB_SUPER_PERM_MASK)
-- 
cgit v1.2.3-70-g09d2


From 84e4d632b5455082b458844b8b8cf48406e001ce Mon Sep 17 00:00:00 2001
From: Bharat Bhushan <r65777@freescale.com>
Date: Wed, 7 Aug 2013 15:33:45 +0530
Subject: kvm: powerpc: e500: mark page accessed when mapping a guest page

Mark the guest page as accessed so that there is likely
less chances of this page getting swap-out.

Signed-off-by: Bharat Bhushan <bharat.bhushan@freescale.com>
Acked-by: Scott Wood <scottwood@freescale.com>
Signed-off-by: Alexander Graf <agraf@suse.de>
---
 arch/powerpc/kvm/e500_mmu_host.c | 3 +++
 1 file changed, 3 insertions(+)

(limited to 'arch/powerpc/kvm')

diff --git a/arch/powerpc/kvm/e500_mmu_host.c b/arch/powerpc/kvm/e500_mmu_host.c
index 1c6a9d729df..8f0d532522d 100644
--- a/arch/powerpc/kvm/e500_mmu_host.c
+++ b/arch/powerpc/kvm/e500_mmu_host.c
@@ -253,6 +253,9 @@ static inline void kvmppc_e500_ref_setup(struct tlbe_ref *ref,
 	ref->pfn = pfn;
 	ref->flags |= E500_TLB_VALID;
 
+	/* Mark the page accessed */
+	kvm_set_pfn_accessed(pfn);
+
 	if (tlbe_is_writable(gtlbe))
 		kvm_set_pfn_dirty(pfn);
 }
-- 
cgit v1.2.3-70-g09d2


From b12c784123ff805c066449ca580f15a903c24994 Mon Sep 17 00:00:00 2001
From: Bharat Bhushan <r65777@freescale.com>
Date: Thu, 4 Jul 2013 12:27:45 +0530
Subject: KVM: PPC: E500: exit to user space on "ehpriv 1" instruction

"ehpriv 1" instruction is used for setting software breakpoints
by user space. This patch adds support to exit to user space
with "run->debug" have relevant information.

As this is the first point we are using run->debug, also defined
the run->debug structure.

Signed-off-by: Bharat Bhushan <bharat.bhushan@freescale.com>
Signed-off-by: Alexander Graf <agraf@suse.de>
---
 arch/powerpc/include/asm/disassemble.h |  4 ++++
 arch/powerpc/include/asm/kvm_booke.h   |  7 ++++++-
 arch/powerpc/include/uapi/asm/kvm.h    | 21 +++++++++++++++++----
 arch/powerpc/kvm/booke.c               |  2 +-
 arch/powerpc/kvm/e500_emulate.c        | 26 ++++++++++++++++++++++++++
 5 files changed, 54 insertions(+), 6 deletions(-)

(limited to 'arch/powerpc/kvm')

diff --git a/arch/powerpc/include/asm/disassemble.h b/arch/powerpc/include/asm/disassemble.h
index 9b198d1b3b2..856f8deb557 100644
--- a/arch/powerpc/include/asm/disassemble.h
+++ b/arch/powerpc/include/asm/disassemble.h
@@ -77,4 +77,8 @@ static inline unsigned int get_d(u32 inst)
 	return inst & 0xffff;
 }
 
+static inline unsigned int get_oc(u32 inst)
+{
+	return (inst >> 11) & 0x7fff;
+}
 #endif /* __ASM_PPC_DISASSEMBLE_H__ */
diff --git a/arch/powerpc/include/asm/kvm_booke.h b/arch/powerpc/include/asm/kvm_booke.h
index d3c1eb34c98..dd8f61510df 100644
--- a/arch/powerpc/include/asm/kvm_booke.h
+++ b/arch/powerpc/include/asm/kvm_booke.h
@@ -26,7 +26,12 @@
 /* LPIDs we support with this build -- runtime limit may be lower */
 #define KVMPPC_NR_LPIDS                        64
 
-#define KVMPPC_INST_EHPRIV	0x7c00021c
+#define KVMPPC_INST_EHPRIV		0x7c00021c
+#define EHPRIV_OC_SHIFT			11
+/* "ehpriv 1" : ehpriv with OC = 1 is used for debug emulation */
+#define EHPRIV_OC_DEBUG			1
+#define KVMPPC_INST_EHPRIV_DEBUG	(KVMPPC_INST_EHPRIV | \
+					 (EHPRIV_OC_DEBUG << EHPRIV_OC_SHIFT))
 
 static inline void kvmppc_set_gpr(struct kvm_vcpu *vcpu, int num, ulong val)
 {
diff --git a/arch/powerpc/include/uapi/asm/kvm.h b/arch/powerpc/include/uapi/asm/kvm.h
index e420d46d363..482bba56e49 100644
--- a/arch/powerpc/include/uapi/asm/kvm.h
+++ b/arch/powerpc/include/uapi/asm/kvm.h
@@ -269,7 +269,24 @@ struct kvm_fpu {
 	__u64 fpr[32];
 };
 
+/*
+ * Defines for h/w breakpoint, watchpoint (read, write or both) and
+ * software breakpoint.
+ * These are used as "type" in KVM_SET_GUEST_DEBUG ioctl and "status"
+ * for KVM_DEBUG_EXIT.
+ */
+#define KVMPPC_DEBUG_NONE		0x0
+#define KVMPPC_DEBUG_BREAKPOINT		(1UL << 1)
+#define KVMPPC_DEBUG_WATCH_WRITE	(1UL << 2)
+#define KVMPPC_DEBUG_WATCH_READ		(1UL << 3)
 struct kvm_debug_exit_arch {
+	__u64 address;
+	/*
+	 * exiting to userspace because of h/w breakpoint, watchpoint
+	 * (read, write or both) and software breakpoint.
+	 */
+	__u32 status;
+	__u32 reserved;
 };
 
 /* for KVM_SET_GUEST_DEBUG */
@@ -281,10 +298,6 @@ struct kvm_guest_debug_arch {
 		 * Type denotes h/w breakpoint, read watchpoint, write
 		 * watchpoint or watchpoint (both read and write).
 		 */
-#define KVMPPC_DEBUG_NONE		0x0
-#define KVMPPC_DEBUG_BREAKPOINT		(1UL << 1)
-#define KVMPPC_DEBUG_WATCH_WRITE	(1UL << 2)
-#define KVMPPC_DEBUG_WATCH_READ		(1UL << 3)
 		__u32 type;
 		__u32 reserved;
 	} bp[16];
diff --git a/arch/powerpc/kvm/booke.c b/arch/powerpc/kvm/booke.c
index 65fa7754b19..1d6edf00e0e 100644
--- a/arch/powerpc/kvm/booke.c
+++ b/arch/powerpc/kvm/booke.c
@@ -1477,7 +1477,7 @@ int kvm_vcpu_ioctl_get_one_reg(struct kvm_vcpu *vcpu, struct kvm_one_reg *reg)
 		val = get_reg_val(reg->id, vcpu->arch.tsr);
 		break;
 	case KVM_REG_PPC_DEBUG_INST:
-		val = get_reg_val(reg->id, KVMPPC_INST_EHPRIV);
+		val = get_reg_val(reg->id, KVMPPC_INST_EHPRIV_DEBUG);
 		break;
 	case KVM_REG_PPC_VRSAVE:
 		val = get_reg_val(reg->id, vcpu->arch.vrsave);
diff --git a/arch/powerpc/kvm/e500_emulate.c b/arch/powerpc/kvm/e500_emulate.c
index b10a01243ab..6163a0318d2 100644
--- a/arch/powerpc/kvm/e500_emulate.c
+++ b/arch/powerpc/kvm/e500_emulate.c
@@ -26,6 +26,7 @@
 #define XOP_TLBRE   946
 #define XOP_TLBWE   978
 #define XOP_TLBILX  18
+#define XOP_EHPRIV  270
 
 #ifdef CONFIG_KVM_E500MC
 static int dbell2prio(ulong param)
@@ -82,6 +83,26 @@ static int kvmppc_e500_emul_msgsnd(struct kvm_vcpu *vcpu, int rb)
 }
 #endif
 
+static int kvmppc_e500_emul_ehpriv(struct kvm_run *run, struct kvm_vcpu *vcpu,
+				   unsigned int inst, int *advance)
+{
+	int emulated = EMULATE_DONE;
+
+	switch (get_oc(inst)) {
+	case EHPRIV_OC_DEBUG:
+		run->exit_reason = KVM_EXIT_DEBUG;
+		run->debug.arch.address = vcpu->arch.pc;
+		run->debug.arch.status = 0;
+		kvmppc_account_exit(vcpu, DEBUG_EXITS);
+		emulated = EMULATE_EXIT_USER;
+		*advance = 0;
+		break;
+	default:
+		emulated = EMULATE_FAIL;
+	}
+	return emulated;
+}
+
 int kvmppc_core_emulate_op(struct kvm_run *run, struct kvm_vcpu *vcpu,
                            unsigned int inst, int *advance)
 {
@@ -130,6 +151,11 @@ int kvmppc_core_emulate_op(struct kvm_run *run, struct kvm_vcpu *vcpu,
 			emulated = kvmppc_e500_emul_tlbivax(vcpu, ea);
 			break;
 
+		case XOP_EHPRIV:
+			emulated = kvmppc_e500_emul_ehpriv(run, vcpu, inst,
+							   advance);
+			break;
+
 		default:
 			emulated = EMULATE_FAIL;
 		}
-- 
cgit v1.2.3-70-g09d2


From 547465ef8bcad77a3a73dad5151d9d28a0c1b88d Mon Sep 17 00:00:00 2001
From: Bharat Bhushan <r65777@freescale.com>
Date: Thu, 4 Jul 2013 12:27:46 +0530
Subject: KVM: PPC: E500: Using "struct debug_reg"

For KVM also use the "struct debug_reg" defined in asm/processor.h

Signed-off-by: Bharat Bhushan <bharat.bhushan@freescale.com>
Signed-off-by: Alexander Graf <agraf@suse.de>
---
 arch/powerpc/include/asm/kvm_host.h | 13 +------------
 arch/powerpc/kvm/booke.c            | 34 ++++++++++++++++++++++++----------
 2 files changed, 25 insertions(+), 22 deletions(-)

(limited to 'arch/powerpc/kvm')

diff --git a/arch/powerpc/include/asm/kvm_host.h b/arch/powerpc/include/asm/kvm_host.h
index b6881917cd8..7e83c5ff830 100644
--- a/arch/powerpc/include/asm/kvm_host.h
+++ b/arch/powerpc/include/asm/kvm_host.h
@@ -387,17 +387,6 @@ struct kvmppc_slb {
 #define KVMPPC_EPR_USER		1 /* exit to userspace to fill EPR */
 #define KVMPPC_EPR_KERNEL	2 /* in-kernel irqchip */
 
-struct kvmppc_booke_debug_reg {
-	u32 dbcr0;
-	u32 dbcr1;
-	u32 dbcr2;
-#ifdef CONFIG_KVM_E500MC
-	u32 dbcr4;
-#endif
-	u64 iac[KVMPPC_BOOKE_MAX_IAC];
-	u64 dac[KVMPPC_BOOKE_MAX_DAC];
-};
-
 #define KVMPPC_IRQ_DEFAULT	0
 #define KVMPPC_IRQ_MPIC		1
 #define KVMPPC_IRQ_XICS		2
@@ -549,7 +538,7 @@ struct kvm_vcpu_arch {
 	u32 eptcfg;
 	u32 epr;
 	u32 crit_save;
-	struct kvmppc_booke_debug_reg dbg_reg;
+	struct debug_reg dbg_reg;
 #endif
 	gpa_t paddr_accessed;
 	gva_t vaddr_accessed;
diff --git a/arch/powerpc/kvm/booke.c b/arch/powerpc/kvm/booke.c
index 1d6edf00e0e..a972fb600a9 100644
--- a/arch/powerpc/kvm/booke.c
+++ b/arch/powerpc/kvm/booke.c
@@ -1441,7 +1441,6 @@ int kvm_vcpu_ioctl_get_one_reg(struct kvm_vcpu *vcpu, struct kvm_one_reg *reg)
 	int r = 0;
 	union kvmppc_one_reg val;
 	int size;
-	long int i;
 
 	size = one_reg_size(reg->id);
 	if (size > sizeof(val))
@@ -1449,16 +1448,24 @@ int kvm_vcpu_ioctl_get_one_reg(struct kvm_vcpu *vcpu, struct kvm_one_reg *reg)
 
 	switch (reg->id) {
 	case KVM_REG_PPC_IAC1:
+		val = get_reg_val(reg->id, vcpu->arch.dbg_reg.iac1);
+		break;
 	case KVM_REG_PPC_IAC2:
+		val = get_reg_val(reg->id, vcpu->arch.dbg_reg.iac2);
+		break;
+#if CONFIG_PPC_ADV_DEBUG_IACS > 2
 	case KVM_REG_PPC_IAC3:
+		val = get_reg_val(reg->id, vcpu->arch.dbg_reg.iac3);
+		break;
 	case KVM_REG_PPC_IAC4:
-		i = reg->id - KVM_REG_PPC_IAC1;
-		val = get_reg_val(reg->id, vcpu->arch.dbg_reg.iac[i]);
+		val = get_reg_val(reg->id, vcpu->arch.dbg_reg.iac4);
 		break;
+#endif
 	case KVM_REG_PPC_DAC1:
+		val = get_reg_val(reg->id, vcpu->arch.dbg_reg.dac1);
+		break;
 	case KVM_REG_PPC_DAC2:
-		i = reg->id - KVM_REG_PPC_DAC1;
-		val = get_reg_val(reg->id, vcpu->arch.dbg_reg.dac[i]);
+		val = get_reg_val(reg->id, vcpu->arch.dbg_reg.dac2);
 		break;
 	case KVM_REG_PPC_EPR: {
 		u32 epr = get_guest_epr(vcpu);
@@ -1501,7 +1508,6 @@ int kvm_vcpu_ioctl_set_one_reg(struct kvm_vcpu *vcpu, struct kvm_one_reg *reg)
 	int r = 0;
 	union kvmppc_one_reg val;
 	int size;
-	long int i;
 
 	size = one_reg_size(reg->id);
 	if (size > sizeof(val))
@@ -1512,16 +1518,24 @@ int kvm_vcpu_ioctl_set_one_reg(struct kvm_vcpu *vcpu, struct kvm_one_reg *reg)
 
 	switch (reg->id) {
 	case KVM_REG_PPC_IAC1:
+		vcpu->arch.dbg_reg.iac1 = set_reg_val(reg->id, val);
+		break;
 	case KVM_REG_PPC_IAC2:
+		vcpu->arch.dbg_reg.iac2 = set_reg_val(reg->id, val);
+		break;
+#if CONFIG_PPC_ADV_DEBUG_IACS > 2
 	case KVM_REG_PPC_IAC3:
+		vcpu->arch.dbg_reg.iac3 = set_reg_val(reg->id, val);
+		break;
 	case KVM_REG_PPC_IAC4:
-		i = reg->id - KVM_REG_PPC_IAC1;
-		vcpu->arch.dbg_reg.iac[i] = set_reg_val(reg->id, val);
+		vcpu->arch.dbg_reg.iac4 = set_reg_val(reg->id, val);
 		break;
+#endif
 	case KVM_REG_PPC_DAC1:
+		vcpu->arch.dbg_reg.dac1 = set_reg_val(reg->id, val);
+		break;
 	case KVM_REG_PPC_DAC2:
-		i = reg->id - KVM_REG_PPC_DAC1;
-		vcpu->arch.dbg_reg.dac[i] = set_reg_val(reg->id, val);
+		vcpu->arch.dbg_reg.dac2 = set_reg_val(reg->id, val);
 		break;
 	case KVM_REG_PPC_EPR: {
 		u32 new_epr = set_reg_val(reg->id, val);
-- 
cgit v1.2.3-70-g09d2


From ce11e48b7fdd256ec68b932a89b397a790566031 Mon Sep 17 00:00:00 2001
From: Bharat Bhushan <r65777@freescale.com>
Date: Thu, 4 Jul 2013 12:27:47 +0530
Subject: KVM: PPC: E500: Add userspace debug stub support

This patch adds the debug stub support on booke/bookehv.
Now QEMU debug stub can use hw breakpoint, watchpoint and
software breakpoint to debug guest.

This is how we save/restore debug register context when switching
between guest, userspace and kernel user-process:

When QEMU is running
 -> thread->debug_reg == QEMU debug register context.
 -> Kernel will handle switching the debug register on context switch.
 -> no vcpu_load() called

QEMU makes ioctls (except RUN)
 -> This will call vcpu_load()
 -> should not change context.
 -> Some ioctls can change vcpu debug register, context saved in vcpu->debug_regs

QEMU Makes RUN ioctl
 -> Save thread->debug_reg on STACK
 -> Store thread->debug_reg == vcpu->debug_reg
 -> load thread->debug_reg
 -> RUN VCPU ( So thread points to vcpu context )

Context switch happens When VCPU running
 -> makes vcpu_load() should not load any context
 -> kernel loads the vcpu context as thread->debug_regs points to vcpu context.

On heavyweight_exit
 -> Load the context saved on stack in thread->debug_reg

Currently we do not support debug resource emulation to guest,
On debug exception, always exit to user space irrespective of
user space is expecting the debug exception or not. If this is
unexpected exception (breakpoint/watchpoint event not set by
userspace) then let us leave the action on user space. This
is similar to what it was before, only thing is that now we
have proper exit state available to user space.

Signed-off-by: Bharat Bhushan <bharat.bhushan@freescale.com>
Signed-off-by: Alexander Graf <agraf@suse.de>
---
 arch/powerpc/include/asm/kvm_host.h |   3 +
 arch/powerpc/include/uapi/asm/kvm.h |   1 +
 arch/powerpc/kvm/booke.c            | 240 +++++++++++++++++++++++++++++++++---
 arch/powerpc/kvm/booke.h            |   5 +
 4 files changed, 231 insertions(+), 18 deletions(-)

(limited to 'arch/powerpc/kvm')

diff --git a/arch/powerpc/include/asm/kvm_host.h b/arch/powerpc/include/asm/kvm_host.h
index 7e83c5ff830..4959ff1b537 100644
--- a/arch/powerpc/include/asm/kvm_host.h
+++ b/arch/powerpc/include/asm/kvm_host.h
@@ -538,7 +538,10 @@ struct kvm_vcpu_arch {
 	u32 eptcfg;
 	u32 epr;
 	u32 crit_save;
+	/* guest debug registers*/
 	struct debug_reg dbg_reg;
+	/* hardware visible debug registers when in guest state */
+	struct debug_reg shadow_dbg_reg;
 #endif
 	gpa_t paddr_accessed;
 	gva_t vaddr_accessed;
diff --git a/arch/powerpc/include/uapi/asm/kvm.h b/arch/powerpc/include/uapi/asm/kvm.h
index 482bba56e49..6836ec79a83 100644
--- a/arch/powerpc/include/uapi/asm/kvm.h
+++ b/arch/powerpc/include/uapi/asm/kvm.h
@@ -27,6 +27,7 @@
 #define __KVM_HAVE_PPC_SMT
 #define __KVM_HAVE_IRQCHIP
 #define __KVM_HAVE_IRQ_LINE
+#define __KVM_HAVE_GUEST_DEBUG
 
 struct kvm_regs {
 	__u64 pc;
diff --git a/arch/powerpc/kvm/booke.c b/arch/powerpc/kvm/booke.c
index a972fb600a9..8b6a790c056 100644
--- a/arch/powerpc/kvm/booke.c
+++ b/arch/powerpc/kvm/booke.c
@@ -133,6 +133,29 @@ static void kvmppc_vcpu_sync_fpu(struct kvm_vcpu *vcpu)
 #endif
 }
 
+static void kvmppc_vcpu_sync_debug(struct kvm_vcpu *vcpu)
+{
+	/* Synchronize guest's desire to get debug interrupts into shadow MSR */
+#ifndef CONFIG_KVM_BOOKE_HV
+	vcpu->arch.shadow_msr &= ~MSR_DE;
+	vcpu->arch.shadow_msr |= vcpu->arch.shared->msr & MSR_DE;
+#endif
+
+	/* Force enable debug interrupts when user space wants to debug */
+	if (vcpu->guest_debug) {
+#ifdef CONFIG_KVM_BOOKE_HV
+		/*
+		 * Since there is no shadow MSR, sync MSR_DE into the guest
+		 * visible MSR.
+		 */
+		vcpu->arch.shared->msr |= MSR_DE;
+#else
+		vcpu->arch.shadow_msr |= MSR_DE;
+		vcpu->arch.shared->msr &= ~MSR_DE;
+#endif
+	}
+}
+
 /*
  * Helper function for "full" MSR writes.  No need to call this if only
  * EE/CE/ME/DE/RI are changing.
@@ -150,6 +173,7 @@ void kvmppc_set_msr(struct kvm_vcpu *vcpu, u32 new_msr)
 	kvmppc_mmu_msr_notify(vcpu, old_msr);
 	kvmppc_vcpu_sync_spe(vcpu);
 	kvmppc_vcpu_sync_fpu(vcpu);
+	kvmppc_vcpu_sync_debug(vcpu);
 }
 
 static void kvmppc_booke_queue_irqprio(struct kvm_vcpu *vcpu,
@@ -655,6 +679,7 @@ int kvmppc_core_check_requests(struct kvm_vcpu *vcpu)
 int kvmppc_vcpu_run(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu)
 {
 	int ret, s;
+	struct thread_struct thread;
 #ifdef CONFIG_PPC_FPU
 	unsigned int fpscr;
 	int fpexc_mode;
@@ -696,6 +721,12 @@ int kvmppc_vcpu_run(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu)
 	kvmppc_load_guest_fp(vcpu);
 #endif
 
+	/* Switch to guest debug context */
+	thread.debug = vcpu->arch.shadow_dbg_reg;
+	switch_booke_debug_regs(&thread);
+	thread.debug = current->thread.debug;
+	current->thread.debug = vcpu->arch.shadow_dbg_reg;
+
 	kvmppc_fix_ee_before_entry();
 
 	ret = __kvmppc_vcpu_run(kvm_run, vcpu);
@@ -703,6 +734,10 @@ int kvmppc_vcpu_run(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu)
 	/* No need for kvm_guest_exit. It's done in handle_exit.
 	   We also get here with interrupts enabled. */
 
+	/* Switch back to user space debug context */
+	switch_booke_debug_regs(&thread);
+	current->thread.debug = thread.debug;
+
 #ifdef CONFIG_PPC_FPU
 	kvmppc_save_guest_fp(vcpu);
 
@@ -758,6 +793,30 @@ static int emulation_exit(struct kvm_run *run, struct kvm_vcpu *vcpu)
 	}
 }
 
+static int kvmppc_handle_debug(struct kvm_run *run, struct kvm_vcpu *vcpu)
+{
+	struct debug_reg *dbg_reg = &(vcpu->arch.shadow_dbg_reg);
+	u32 dbsr = vcpu->arch.dbsr;
+
+	run->debug.arch.status = 0;
+	run->debug.arch.address = vcpu->arch.pc;
+
+	if (dbsr & (DBSR_IAC1 | DBSR_IAC2 | DBSR_IAC3 | DBSR_IAC4)) {
+		run->debug.arch.status |= KVMPPC_DEBUG_BREAKPOINT;
+	} else {
+		if (dbsr & (DBSR_DAC1W | DBSR_DAC2W))
+			run->debug.arch.status |= KVMPPC_DEBUG_WATCH_WRITE;
+		else if (dbsr & (DBSR_DAC1R | DBSR_DAC2R))
+			run->debug.arch.status |= KVMPPC_DEBUG_WATCH_READ;
+		if (dbsr & (DBSR_DAC1R | DBSR_DAC1W))
+			run->debug.arch.address = dbg_reg->dac1;
+		else if (dbsr & (DBSR_DAC2R | DBSR_DAC2W))
+			run->debug.arch.address = dbg_reg->dac2;
+	}
+
+	return RESUME_HOST;
+}
+
 static void kvmppc_fill_pt_regs(struct pt_regs *regs)
 {
 	ulong r1, ip, msr, lr;
@@ -818,6 +877,11 @@ static void kvmppc_restart_interrupt(struct kvm_vcpu *vcpu,
 	case BOOKE_INTERRUPT_CRITICAL:
 		unknown_exception(&regs);
 		break;
+	case BOOKE_INTERRUPT_DEBUG:
+		/* Save DBSR before preemption is enabled */
+		vcpu->arch.dbsr = mfspr(SPRN_DBSR);
+		kvmppc_clear_dbsr();
+		break;
 	}
 }
 
@@ -1135,18 +1199,10 @@ int kvmppc_handle_exit(struct kvm_run *run, struct kvm_vcpu *vcpu,
 	}
 
 	case BOOKE_INTERRUPT_DEBUG: {
-		u32 dbsr;
-
-		vcpu->arch.pc = mfspr(SPRN_CSRR0);
-
-		/* clear IAC events in DBSR register */
-		dbsr = mfspr(SPRN_DBSR);
-		dbsr &= DBSR_IAC1 | DBSR_IAC2 | DBSR_IAC3 | DBSR_IAC4;
-		mtspr(SPRN_DBSR, dbsr);
-
-		run->exit_reason = KVM_EXIT_DEBUG;
+		r = kvmppc_handle_debug(run, vcpu);
+		if (r == RESUME_HOST)
+			run->exit_reason = KVM_EXIT_DEBUG;
 		kvmppc_account_exit(vcpu, DEBUG_EXITS);
-		r = RESUME_HOST;
 		break;
 	}
 
@@ -1197,7 +1253,7 @@ int kvm_arch_vcpu_setup(struct kvm_vcpu *vcpu)
 	kvmppc_set_msr(vcpu, 0);
 
 #ifndef CONFIG_KVM_BOOKE_HV
-	vcpu->arch.shadow_msr = MSR_USER | MSR_DE | MSR_IS | MSR_DS;
+	vcpu->arch.shadow_msr = MSR_USER | MSR_IS | MSR_DS;
 	vcpu->arch.shadow_pid = 1;
 	vcpu->arch.shared->msr = 0;
 #endif
@@ -1580,12 +1636,6 @@ int kvm_vcpu_ioctl_set_one_reg(struct kvm_vcpu *vcpu, struct kvm_one_reg *reg)
 	return r;
 }
 
-int kvm_arch_vcpu_ioctl_set_guest_debug(struct kvm_vcpu *vcpu,
-					 struct kvm_guest_debug *dbg)
-{
-	return -EINVAL;
-}
-
 int kvm_arch_vcpu_ioctl_get_fpu(struct kvm_vcpu *vcpu, struct kvm_fpu *fpu)
 {
 	return -ENOTSUPP;
@@ -1691,6 +1741,157 @@ void kvmppc_decrementer_func(unsigned long data)
 	kvmppc_set_tsr_bits(vcpu, TSR_DIS);
 }
 
+static int kvmppc_booke_add_breakpoint(struct debug_reg *dbg_reg,
+				       uint64_t addr, int index)
+{
+	switch (index) {
+	case 0:
+		dbg_reg->dbcr0 |= DBCR0_IAC1;
+		dbg_reg->iac1 = addr;
+		break;
+	case 1:
+		dbg_reg->dbcr0 |= DBCR0_IAC2;
+		dbg_reg->iac2 = addr;
+		break;
+#if CONFIG_PPC_ADV_DEBUG_IACS > 2
+	case 2:
+		dbg_reg->dbcr0 |= DBCR0_IAC3;
+		dbg_reg->iac3 = addr;
+		break;
+	case 3:
+		dbg_reg->dbcr0 |= DBCR0_IAC4;
+		dbg_reg->iac4 = addr;
+		break;
+#endif
+	default:
+		return -EINVAL;
+	}
+
+	dbg_reg->dbcr0 |= DBCR0_IDM;
+	return 0;
+}
+
+static int kvmppc_booke_add_watchpoint(struct debug_reg *dbg_reg, uint64_t addr,
+				       int type, int index)
+{
+	switch (index) {
+	case 0:
+		if (type & KVMPPC_DEBUG_WATCH_READ)
+			dbg_reg->dbcr0 |= DBCR0_DAC1R;
+		if (type & KVMPPC_DEBUG_WATCH_WRITE)
+			dbg_reg->dbcr0 |= DBCR0_DAC1W;
+		dbg_reg->dac1 = addr;
+		break;
+	case 1:
+		if (type & KVMPPC_DEBUG_WATCH_READ)
+			dbg_reg->dbcr0 |= DBCR0_DAC2R;
+		if (type & KVMPPC_DEBUG_WATCH_WRITE)
+			dbg_reg->dbcr0 |= DBCR0_DAC2W;
+		dbg_reg->dac2 = addr;
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	dbg_reg->dbcr0 |= DBCR0_IDM;
+	return 0;
+}
+void kvm_guest_protect_msr(struct kvm_vcpu *vcpu, ulong prot_bitmap, bool set)
+{
+	/* XXX: Add similar MSR protection for BookE-PR */
+#ifdef CONFIG_KVM_BOOKE_HV
+	BUG_ON(prot_bitmap & ~(MSRP_UCLEP | MSRP_DEP | MSRP_PMMP));
+	if (set) {
+		if (prot_bitmap & MSR_UCLE)
+			vcpu->arch.shadow_msrp |= MSRP_UCLEP;
+		if (prot_bitmap & MSR_DE)
+			vcpu->arch.shadow_msrp |= MSRP_DEP;
+		if (prot_bitmap & MSR_PMM)
+			vcpu->arch.shadow_msrp |= MSRP_PMMP;
+	} else {
+		if (prot_bitmap & MSR_UCLE)
+			vcpu->arch.shadow_msrp &= ~MSRP_UCLEP;
+		if (prot_bitmap & MSR_DE)
+			vcpu->arch.shadow_msrp &= ~MSRP_DEP;
+		if (prot_bitmap & MSR_PMM)
+			vcpu->arch.shadow_msrp &= ~MSRP_PMMP;
+	}
+#endif
+}
+
+int kvm_arch_vcpu_ioctl_set_guest_debug(struct kvm_vcpu *vcpu,
+					 struct kvm_guest_debug *dbg)
+{
+	struct debug_reg *dbg_reg;
+	int n, b = 0, w = 0;
+
+	if (!(dbg->control & KVM_GUESTDBG_ENABLE)) {
+		vcpu->arch.shadow_dbg_reg.dbcr0 = 0;
+		vcpu->guest_debug = 0;
+		kvm_guest_protect_msr(vcpu, MSR_DE, false);
+		return 0;
+	}
+
+	kvm_guest_protect_msr(vcpu, MSR_DE, true);
+	vcpu->guest_debug = dbg->control;
+	vcpu->arch.shadow_dbg_reg.dbcr0 = 0;
+	/* Set DBCR0_EDM in guest visible DBCR0 register. */
+	vcpu->arch.dbg_reg.dbcr0 = DBCR0_EDM;
+
+	if (vcpu->guest_debug & KVM_GUESTDBG_SINGLESTEP)
+		vcpu->arch.shadow_dbg_reg.dbcr0 |= DBCR0_IDM | DBCR0_IC;
+
+	/* Code below handles only HW breakpoints */
+	dbg_reg = &(vcpu->arch.shadow_dbg_reg);
+
+#ifdef CONFIG_KVM_BOOKE_HV
+	/*
+	 * On BookE-HV (e500mc) the guest is always executed with MSR.GS=1
+	 * DBCR1 and DBCR2 are set to trigger debug events when MSR.PR is 0
+	 */
+	dbg_reg->dbcr1 = 0;
+	dbg_reg->dbcr2 = 0;
+#else
+	/*
+	 * On BookE-PR (e500v2) the guest is always executed with MSR.PR=1
+	 * We set DBCR1 and DBCR2 to only trigger debug events when MSR.PR
+	 * is set.
+	 */
+	dbg_reg->dbcr1 = DBCR1_IAC1US | DBCR1_IAC2US | DBCR1_IAC3US |
+			  DBCR1_IAC4US;
+	dbg_reg->dbcr2 = DBCR2_DAC1US | DBCR2_DAC2US;
+#endif
+
+	if (!(vcpu->guest_debug & KVM_GUESTDBG_USE_HW_BP))
+		return 0;
+
+	for (n = 0; n < (KVMPPC_BOOKE_IAC_NUM + KVMPPC_BOOKE_DAC_NUM); n++) {
+		uint64_t addr = dbg->arch.bp[n].addr;
+		uint32_t type = dbg->arch.bp[n].type;
+
+		if (type == KVMPPC_DEBUG_NONE)
+			continue;
+
+		if (type & !(KVMPPC_DEBUG_WATCH_READ |
+			     KVMPPC_DEBUG_WATCH_WRITE |
+			     KVMPPC_DEBUG_BREAKPOINT))
+			return -EINVAL;
+
+		if (type & KVMPPC_DEBUG_BREAKPOINT) {
+			/* Setting H/W breakpoint */
+			if (kvmppc_booke_add_breakpoint(dbg_reg, addr, b++))
+				return -EINVAL;
+		} else {
+			/* Setting H/W watchpoint */
+			if (kvmppc_booke_add_watchpoint(dbg_reg, addr,
+							type, w++))
+				return -EINVAL;
+		}
+	}
+
+	return 0;
+}
+
 void kvmppc_booke_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
 {
 	vcpu->cpu = smp_processor_id();
@@ -1701,6 +1902,9 @@ void kvmppc_booke_vcpu_put(struct kvm_vcpu *vcpu)
 {
 	current->thread.kvm_vcpu = NULL;
 	vcpu->cpu = -1;
+
+	/* Clear pending debug event in DBSR */
+	kvmppc_clear_dbsr();
 }
 
 int __init kvmppc_booke_init(void)
diff --git a/arch/powerpc/kvm/booke.h b/arch/powerpc/kvm/booke.h
index 5fd1ba69357..a1ff67d0402 100644
--- a/arch/powerpc/kvm/booke.h
+++ b/arch/powerpc/kvm/booke.h
@@ -129,4 +129,9 @@ static inline void kvmppc_save_guest_fp(struct kvm_vcpu *vcpu)
 		giveup_fpu(current);
 #endif
 }
+
+static inline void kvmppc_clear_dbsr(void)
+{
+	mtspr(SPRN_DBSR, mfspr(SPRN_DBSR));
+}
 #endif /* __KVM_BOOKE_H__ */
-- 
cgit v1.2.3-70-g09d2


From 178db620ee74ffb0ce7f8031ba8569c31b4193cd Mon Sep 17 00:00:00 2001
From: Paul Mackerras <paulus@samba.org>
Date: Mon, 7 Oct 2013 22:17:49 +0530
Subject: kvm: powerpc: book3s: remove kvmppc_handler_highmem label

This label is not used now.

Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
Signed-off-by: Alexander Graf <agraf@suse.de>
---
 arch/powerpc/kvm/book3s_hv_interrupts.S | 3 ---
 arch/powerpc/kvm/book3s_interrupts.S    | 3 ---
 2 files changed, 6 deletions(-)

(limited to 'arch/powerpc/kvm')

diff --git a/arch/powerpc/kvm/book3s_hv_interrupts.S b/arch/powerpc/kvm/book3s_hv_interrupts.S
index 37f1cc417ca..928142c64cb 100644
--- a/arch/powerpc/kvm/book3s_hv_interrupts.S
+++ b/arch/powerpc/kvm/book3s_hv_interrupts.S
@@ -158,9 +158,6 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_201)
  * Interrupts are enabled again at this point.
  */
 
-.global kvmppc_handler_highmem
-kvmppc_handler_highmem:
-
 	/*
 	 * Register usage at this point:
 	 *
diff --git a/arch/powerpc/kvm/book3s_interrupts.S b/arch/powerpc/kvm/book3s_interrupts.S
index d4e30d8fa82..38166ab2f19 100644
--- a/arch/powerpc/kvm/book3s_interrupts.S
+++ b/arch/powerpc/kvm/book3s_interrupts.S
@@ -121,9 +121,6 @@ kvm_start_lightweight:
  *
  */
 
-.global kvmppc_handler_highmem
-kvmppc_handler_highmem:
-
 	/*
 	 * Register usage at this point:
 	 *
-- 
cgit v1.2.3-70-g09d2


From 066212e02a8fb4ae797fae1d7cede5807ba398e1 Mon Sep 17 00:00:00 2001
From: Paul Mackerras <paulus@samba.org>
Date: Mon, 7 Oct 2013 22:17:50 +0530
Subject: kvm: powerpc: book3s: move book3s_64_vio_hv.c into the main kernel
 binary

Since the code in book3s_64_vio_hv.c is called from real mode with HV
KVM, and therefore has to be built into the main kernel binary, this
makes it always built-in rather than part of the KVM module.  It gets
called from the KVM module by PR KVM, so this adds an EXPORT_SYMBOL_GPL().

Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
Signed-off-by: Alexander Graf <agraf@suse.de>
---
 arch/powerpc/kvm/Makefile           | 12 ++++++++----
 arch/powerpc/kvm/book3s_64_vio_hv.c |  1 +
 2 files changed, 9 insertions(+), 4 deletions(-)

(limited to 'arch/powerpc/kvm')

diff --git a/arch/powerpc/kvm/Makefile b/arch/powerpc/kvm/Makefile
index 6646c952c5e..104e8dcf433 100644
--- a/arch/powerpc/kvm/Makefile
+++ b/arch/powerpc/kvm/Makefile
@@ -53,32 +53,36 @@ kvm-e500mc-objs := \
 	e500_emulate.o
 kvm-objs-$(CONFIG_KVM_E500MC) := $(kvm-e500mc-objs)
 
+kvm-book3s_64-builtin-objs-$(CONFIG_KVM_BOOK3S_64_HANDLER) := \
+	book3s_64_vio_hv.o
+
 kvm-book3s_64-objs-$(CONFIG_KVM_BOOK3S_64_PR) := \
 	$(KVM)/coalesced_mmio.o \
 	fpu.o \
 	book3s_paired_singles.o \
 	book3s_pr.o \
 	book3s_pr_papr.o \
-	book3s_64_vio_hv.o \
 	book3s_emulate.o \
 	book3s_interrupts.o \
 	book3s_mmu_hpte.o \
 	book3s_64_mmu_host.o \
 	book3s_64_mmu.o \
 	book3s_32_mmu.o
-kvm-book3s_64-builtin-objs-$(CONFIG_KVM_BOOK3S_64_PR) := \
+
+kvm-book3s_64-builtin-objs-$(CONFIG_KVM_BOOK3S_64_PR) += \
 	book3s_rmhandlers.o
 
 kvm-book3s_64-objs-$(CONFIG_KVM_BOOK3S_64_HV) := \
 	book3s_hv.o \
 	book3s_hv_interrupts.o \
 	book3s_64_mmu_hv.o
+
 kvm-book3s_64-builtin-xics-objs-$(CONFIG_KVM_XICS) := \
 	book3s_hv_rm_xics.o
-kvm-book3s_64-builtin-objs-$(CONFIG_KVM_BOOK3S_64_HV) := \
+
+kvm-book3s_64-builtin-objs-$(CONFIG_KVM_BOOK3S_64_HV) += \
 	book3s_hv_rmhandlers.o \
 	book3s_hv_rm_mmu.o \
-	book3s_64_vio_hv.o \
 	book3s_hv_ras.o \
 	book3s_hv_builtin.o \
 	book3s_hv_cma.o \
diff --git a/arch/powerpc/kvm/book3s_64_vio_hv.c b/arch/powerpc/kvm/book3s_64_vio_hv.c
index 30c2f3b134c..2c25f5412bd 100644
--- a/arch/powerpc/kvm/book3s_64_vio_hv.c
+++ b/arch/powerpc/kvm/book3s_64_vio_hv.c
@@ -74,3 +74,4 @@ long kvmppc_h_put_tce(struct kvm_vcpu *vcpu, unsigned long liobn,
 	/* Didn't find the liobn, punt it to userspace */
 	return H_TOO_HARD;
 }
+EXPORT_SYMBOL_GPL(kvmppc_h_put_tce);
-- 
cgit v1.2.3-70-g09d2


From 7aa79938f7d76f5865d0b2a2d9bbe2337560261f Mon Sep 17 00:00:00 2001
From: "Aneesh Kumar K.V" <aneesh.kumar@linux.vnet.ibm.com>
Date: Mon, 7 Oct 2013 22:17:51 +0530
Subject: kvm: powerpc: book3s: pr: Rename KVM_BOOK3S_PR to
 KVM_BOOK3S_PR_POSSIBLE

With later patches supporting PR kvm as a kernel module, the changes
that has to be built into the main kernel binary to enable PR KVM module
is now selected via KVM_BOOK3S_PR_POSSIBLE

Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
Signed-off-by: Alexander Graf <agraf@suse.de>
---
 arch/powerpc/include/asm/exception-64s.h |  2 +-
 arch/powerpc/include/asm/kvm_book3s.h    |  4 ++--
 arch/powerpc/include/asm/kvm_book3s_64.h |  2 +-
 arch/powerpc/include/asm/kvm_host.h      |  2 +-
 arch/powerpc/include/asm/paca.h          |  2 +-
 arch/powerpc/kernel/asm-offsets.c        |  2 +-
 arch/powerpc/kernel/exceptions-64s.S     |  2 +-
 arch/powerpc/kvm/Kconfig                 |  6 +++---
 arch/powerpc/kvm/trace.h                 | 10 +++++-----
 9 files changed, 16 insertions(+), 16 deletions(-)

(limited to 'arch/powerpc/kvm')

diff --git a/arch/powerpc/include/asm/exception-64s.h b/arch/powerpc/include/asm/exception-64s.h
index 402c1c46650..a22c9854a63 100644
--- a/arch/powerpc/include/asm/exception-64s.h
+++ b/arch/powerpc/include/asm/exception-64s.h
@@ -244,7 +244,7 @@ do_kvm_##n:								\
 #define KVM_HANDLER_SKIP(area, h, n)
 #endif
 
-#ifdef CONFIG_KVM_BOOK3S_PR
+#ifdef CONFIG_KVM_BOOK3S_PR_POSSIBLE
 #define KVMTEST_PR(n)			__KVMTEST(n)
 #define KVM_HANDLER_PR(area, h, n)	__KVM_HANDLER(area, h, n)
 #define KVM_HANDLER_PR_SKIP(area, h, n)	__KVM_HANDLER_SKIP(area, h, n)
diff --git a/arch/powerpc/include/asm/kvm_book3s.h b/arch/powerpc/include/asm/kvm_book3s.h
index 0ec00f4fef9..5c07d10e3c4 100644
--- a/arch/powerpc/include/asm/kvm_book3s.h
+++ b/arch/powerpc/include/asm/kvm_book3s.h
@@ -304,7 +304,7 @@ static inline ulong kvmppc_get_fault_dar(struct kvm_vcpu *vcpu)
 	return vcpu->arch.fault_dar;
 }
 
-#ifdef CONFIG_KVM_BOOK3S_PR
+#ifdef CONFIG_KVM_BOOK3S_PR_POSSIBLE
 
 static inline unsigned long kvmppc_interrupt_offset(struct kvm_vcpu *vcpu)
 {
@@ -339,7 +339,7 @@ static inline bool kvmppc_critical_section(struct kvm_vcpu *vcpu)
 
 	return crit;
 }
-#else /* CONFIG_KVM_BOOK3S_PR */
+#else /* CONFIG_KVM_BOOK3S_PR_POSSIBLE */
 
 static inline unsigned long kvmppc_interrupt_offset(struct kvm_vcpu *vcpu)
 {
diff --git a/arch/powerpc/include/asm/kvm_book3s_64.h b/arch/powerpc/include/asm/kvm_book3s_64.h
index 86d638a3b35..e6ee7fd32d1 100644
--- a/arch/powerpc/include/asm/kvm_book3s_64.h
+++ b/arch/powerpc/include/asm/kvm_book3s_64.h
@@ -20,7 +20,7 @@
 #ifndef __ASM_KVM_BOOK3S_64_H__
 #define __ASM_KVM_BOOK3S_64_H__
 
-#ifdef CONFIG_KVM_BOOK3S_PR
+#ifdef CONFIG_KVM_BOOK3S_PR_POSSIBLE
 static inline struct kvmppc_book3s_shadow_vcpu *svcpu_get(struct kvm_vcpu *vcpu)
 {
 	preempt_disable();
diff --git a/arch/powerpc/include/asm/kvm_host.h b/arch/powerpc/include/asm/kvm_host.h
index 4959ff1b537..9e9f689106e 100644
--- a/arch/powerpc/include/asm/kvm_host.h
+++ b/arch/powerpc/include/asm/kvm_host.h
@@ -257,7 +257,7 @@ struct kvm_arch {
 	struct kvmppc_vcore *vcores[KVM_MAX_VCORES];
 	int hpt_cma_alloc;
 #endif /* CONFIG_KVM_BOOK3S_64_HV */
-#ifdef CONFIG_KVM_BOOK3S_PR
+#ifdef CONFIG_KVM_BOOK3S_PR_POSSIBLE
 	struct mutex hpt_mutex;
 #endif
 #ifdef CONFIG_PPC_BOOK3S_64
diff --git a/arch/powerpc/include/asm/paca.h b/arch/powerpc/include/asm/paca.h
index a5954cebbc5..b6ea9e068c1 100644
--- a/arch/powerpc/include/asm/paca.h
+++ b/arch/powerpc/include/asm/paca.h
@@ -166,7 +166,7 @@ struct paca_struct {
 	struct dtl_entry *dtl_curr;	/* pointer corresponding to dtl_ridx */
 
 #ifdef CONFIG_KVM_BOOK3S_HANDLER
-#ifdef CONFIG_KVM_BOOK3S_PR
+#ifdef CONFIG_KVM_BOOK3S_PR_POSSIBLE
 	/* We use this to store guest state in */
 	struct kvmppc_book3s_shadow_vcpu shadow_vcpu;
 #endif
diff --git a/arch/powerpc/kernel/asm-offsets.c b/arch/powerpc/kernel/asm-offsets.c
index 95ba8095fc4..29796559c2f 100644
--- a/arch/powerpc/kernel/asm-offsets.c
+++ b/arch/powerpc/kernel/asm-offsets.c
@@ -533,7 +533,7 @@ int main(void)
 	DEFINE(VCPU_SLB_SIZE, sizeof(struct kvmppc_slb));
 
 #ifdef CONFIG_PPC_BOOK3S_64
-#ifdef CONFIG_KVM_BOOK3S_PR
+#ifdef CONFIG_KVM_BOOK3S_PR_POSSIBLE
 	DEFINE(PACA_SVCPU, offsetof(struct paca_struct, shadow_vcpu));
 # define SVCPU_FIELD(x, f)	DEFINE(x, offsetof(struct paca_struct, shadow_vcpu.f))
 #else
diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S
index 2a273bed1ec..3d1c42b03c8 100644
--- a/arch/powerpc/kernel/exceptions-64s.S
+++ b/arch/powerpc/kernel/exceptions-64s.S
@@ -425,7 +425,7 @@ data_access_check_stab:
 	mfspr	r9,SPRN_DSISR
 	srdi	r10,r10,60
 	rlwimi	r10,r9,16,0x20
-#ifdef CONFIG_KVM_BOOK3S_PR
+#ifdef CONFIG_KVM_BOOK3S_PR_POSSIBLE
 	lbz	r9,HSTATE_IN_GUEST(r13)
 	rlwimi	r10,r9,8,0x300
 #endif
diff --git a/arch/powerpc/kvm/Kconfig b/arch/powerpc/kvm/Kconfig
index ffaef2cb101..d0665f231e6 100644
--- a/arch/powerpc/kvm/Kconfig
+++ b/arch/powerpc/kvm/Kconfig
@@ -34,7 +34,7 @@ config KVM_BOOK3S_64_HANDLER
 	bool
 	select KVM_BOOK3S_HANDLER
 
-config KVM_BOOK3S_PR
+config KVM_BOOK3S_PR_POSSIBLE
 	bool
 	select KVM_MMIO
 	select MMU_NOTIFIER
@@ -44,7 +44,7 @@ config KVM_BOOK3S_32
 	depends on PPC_BOOK3S_32 && !SMP && !PTE_64BIT
 	select KVM
 	select KVM_BOOK3S_32_HANDLER
-	select KVM_BOOK3S_PR
+	select KVM_BOOK3S_PR_POSSIBLE
 	---help---
 	  Support running unmodified book3s_32 guest kernels
 	  in virtual machines on book3s_32 host processors.
@@ -91,7 +91,7 @@ config KVM_BOOK3S_64_HV
 config KVM_BOOK3S_64_PR
 	def_bool y
 	depends on KVM_BOOK3S_64 && !KVM_BOOK3S_64_HV
-	select KVM_BOOK3S_PR
+	select KVM_BOOK3S_PR_POSSIBLE
 
 config KVM_BOOKE_HV
 	bool
diff --git a/arch/powerpc/kvm/trace.h b/arch/powerpc/kvm/trace.h
index a088e9a8c10..9e8368edf37 100644
--- a/arch/powerpc/kvm/trace.h
+++ b/arch/powerpc/kvm/trace.h
@@ -94,7 +94,7 @@ TRACE_EVENT(kvm_exit,
 		__field(	unsigned long,	pc		)
 		__field(	unsigned long,	msr		)
 		__field(	unsigned long,	dar		)
-#ifdef CONFIG_KVM_BOOK3S_PR
+#ifdef CONFIG_KVM_BOOK3S_PR_POSSIBLE
 		__field(	unsigned long,	srr1		)
 #endif
 		__field(	unsigned long,	last_inst	)
@@ -105,7 +105,7 @@ TRACE_EVENT(kvm_exit,
 		__entry->pc		= kvmppc_get_pc(vcpu);
 		__entry->dar		= kvmppc_get_fault_dar(vcpu);
 		__entry->msr		= vcpu->arch.shared->msr;
-#ifdef CONFIG_KVM_BOOK3S_PR
+#ifdef CONFIG_KVM_BOOK3S_PR_POSSIBLE
 		__entry->srr1		= vcpu->arch.shadow_srr1;
 #endif
 		__entry->last_inst	= vcpu->arch.last_inst;
@@ -115,7 +115,7 @@ TRACE_EVENT(kvm_exit,
 		" | pc=0x%lx"
 		" | msr=0x%lx"
 		" | dar=0x%lx"
-#ifdef CONFIG_KVM_BOOK3S_PR
+#ifdef CONFIG_KVM_BOOK3S_PR_POSSIBLE
 		" | srr1=0x%lx"
 #endif
 		" | last_inst=0x%lx"
@@ -124,7 +124,7 @@ TRACE_EVENT(kvm_exit,
 		__entry->pc,
 		__entry->msr,
 		__entry->dar,
-#ifdef CONFIG_KVM_BOOK3S_PR
+#ifdef CONFIG_KVM_BOOK3S_PR_POSSIBLE
 		__entry->srr1,
 #endif
 		__entry->last_inst
@@ -236,7 +236,7 @@ TRACE_EVENT(kvm_check_requests,
  *                         Book3S trace points                           *
  *************************************************************************/
 
-#ifdef CONFIG_KVM_BOOK3S_PR
+#ifdef CONFIG_KVM_BOOK3S_PR_POSSIBLE
 
 TRACE_EVENT(kvm_book3s_reenter,
 	TP_PROTO(int r, struct kvm_vcpu *vcpu),
-- 
cgit v1.2.3-70-g09d2


From 9975f5e3692d320b4259a4d2edd8a979adb1e535 Mon Sep 17 00:00:00 2001
From: "Aneesh Kumar K.V" <aneesh.kumar@linux.vnet.ibm.com>
Date: Mon, 7 Oct 2013 22:17:52 +0530
Subject: kvm: powerpc: book3s: Add a new config variable
 CONFIG_KVM_BOOK3S_HV_POSSIBLE

This help ups to select the relevant code in the kernel code
when we later move HV and PR bits as seperate modules. The patch
also makes the config options for PR KVM selectable

Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
Signed-off-by: Alexander Graf <agraf@suse.de>
---
 arch/powerpc/include/asm/kvm_book3s.h     |  2 --
 arch/powerpc/include/asm/kvm_book3s_64.h  |  6 +++---
 arch/powerpc/include/asm/kvm_book3s_asm.h |  2 +-
 arch/powerpc/include/asm/kvm_host.h       | 10 +++++-----
 arch/powerpc/include/asm/kvm_ppc.h        |  2 +-
 arch/powerpc/kernel/asm-offsets.c         |  8 ++++----
 arch/powerpc/kernel/idle_power7.S         |  2 +-
 arch/powerpc/kvm/Kconfig                  | 18 +++++++++++++++++-
 arch/powerpc/kvm/Makefile                 | 12 ++++++++----
 arch/powerpc/kvm/book3s_exports.c         |  5 +++--
 10 files changed, 43 insertions(+), 24 deletions(-)

(limited to 'arch/powerpc/kvm')

diff --git a/arch/powerpc/include/asm/kvm_book3s.h b/arch/powerpc/include/asm/kvm_book3s.h
index 5c07d10e3c4..99ef8711e90 100644
--- a/arch/powerpc/include/asm/kvm_book3s.h
+++ b/arch/powerpc/include/asm/kvm_book3s.h
@@ -199,8 +199,6 @@ static inline struct kvmppc_vcpu_book3s *to_book3s(struct kvm_vcpu *vcpu)
 	return vcpu->arch.book3s;
 }
 
-extern void kvm_return_point(void);
-
 /* Also add subarch specific defines */
 
 #ifdef CONFIG_KVM_BOOK3S_32_HANDLER
diff --git a/arch/powerpc/include/asm/kvm_book3s_64.h b/arch/powerpc/include/asm/kvm_book3s_64.h
index e6ee7fd32d1..bf0fa8b0a88 100644
--- a/arch/powerpc/include/asm/kvm_book3s_64.h
+++ b/arch/powerpc/include/asm/kvm_book3s_64.h
@@ -35,7 +35,7 @@ static inline void svcpu_put(struct kvmppc_book3s_shadow_vcpu *svcpu)
 
 #define SPAPR_TCE_SHIFT		12
 
-#ifdef CONFIG_KVM_BOOK3S_64_HV
+#ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE
 #define KVM_DEFAULT_HPT_ORDER	24	/* 16MB HPT by default */
 extern unsigned long kvm_rma_pages;
 #endif
@@ -278,7 +278,7 @@ static inline int is_vrma_hpte(unsigned long hpte_v)
 		(HPTE_V_1TB_SEG | (VRMA_VSID << (40 - 16)));
 }
 
-#ifdef CONFIG_KVM_BOOK3S_64_HV
+#ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE
 /*
  * Note modification of an HPTE; set the HPTE modified bit
  * if anyone is interested.
@@ -289,6 +289,6 @@ static inline void note_hpte_modification(struct kvm *kvm,
 	if (atomic_read(&kvm->arch.hpte_mod_interest))
 		rev->guest_rpte |= HPTE_GR_MODIFIED;
 }
-#endif /* CONFIG_KVM_BOOK3S_64_HV */
+#endif /* CONFIG_KVM_BOOK3S_HV_POSSIBLE */
 
 #endif /* __ASM_KVM_BOOK3S_64_H__ */
diff --git a/arch/powerpc/include/asm/kvm_book3s_asm.h b/arch/powerpc/include/asm/kvm_book3s_asm.h
index 62737113c2b..0bd9348a4db 100644
--- a/arch/powerpc/include/asm/kvm_book3s_asm.h
+++ b/arch/powerpc/include/asm/kvm_book3s_asm.h
@@ -83,7 +83,7 @@ struct kvmppc_host_state {
 	u8 restore_hid5;
 	u8 napping;
 
-#ifdef CONFIG_KVM_BOOK3S_64_HV
+#ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE
 	u8 hwthread_req;
 	u8 hwthread_state;
 	u8 host_ipi;
diff --git a/arch/powerpc/include/asm/kvm_host.h b/arch/powerpc/include/asm/kvm_host.h
index 9e9f689106e..61ce4dca45d 100644
--- a/arch/powerpc/include/asm/kvm_host.h
+++ b/arch/powerpc/include/asm/kvm_host.h
@@ -224,15 +224,15 @@ struct revmap_entry {
 #define KVMPPC_GOT_PAGE		0x80
 
 struct kvm_arch_memory_slot {
-#ifdef CONFIG_KVM_BOOK3S_64_HV
+#ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE
 	unsigned long *rmap;
 	unsigned long *slot_phys;
-#endif /* CONFIG_KVM_BOOK3S_64_HV */
+#endif /* CONFIG_KVM_BOOK3S_HV_POSSIBLE */
 };
 
 struct kvm_arch {
 	unsigned int lpid;
-#ifdef CONFIG_KVM_BOOK3S_64_HV
+#ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE
 	unsigned long hpt_virt;
 	struct revmap_entry *revmap;
 	unsigned int host_lpid;
@@ -256,7 +256,7 @@ struct kvm_arch {
 	cpumask_t need_tlb_flush;
 	struct kvmppc_vcore *vcores[KVM_MAX_VCORES];
 	int hpt_cma_alloc;
-#endif /* CONFIG_KVM_BOOK3S_64_HV */
+#endif /* CONFIG_KVM_BOOK3S_HV_POSSIBLE */
 #ifdef CONFIG_KVM_BOOK3S_PR_POSSIBLE
 	struct mutex hpt_mutex;
 #endif
@@ -592,7 +592,7 @@ struct kvm_vcpu_arch {
 	struct kvmppc_icp *icp; /* XICS presentation controller */
 #endif
 
-#ifdef CONFIG_KVM_BOOK3S_64_HV
+#ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE
 	struct kvm_vcpu_arch_shared shregs;
 
 	unsigned long pgfault_addr;
diff --git a/arch/powerpc/include/asm/kvm_ppc.h b/arch/powerpc/include/asm/kvm_ppc.h
index b15554a26c2..1823f38906c 100644
--- a/arch/powerpc/include/asm/kvm_ppc.h
+++ b/arch/powerpc/include/asm/kvm_ppc.h
@@ -260,7 +260,7 @@ void kvmppc_set_pid(struct kvm_vcpu *vcpu, u32 pid);
 
 struct openpic;
 
-#ifdef CONFIG_KVM_BOOK3S_64_HV
+#ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE
 extern void kvm_cma_reserve(void) __init;
 static inline void kvmppc_set_xics_phys(int cpu, unsigned long addr)
 {
diff --git a/arch/powerpc/kernel/asm-offsets.c b/arch/powerpc/kernel/asm-offsets.c
index 29796559c2f..1fbb2b63195 100644
--- a/arch/powerpc/kernel/asm-offsets.c
+++ b/arch/powerpc/kernel/asm-offsets.c
@@ -445,7 +445,7 @@ int main(void)
 	DEFINE(VCPU_LR, offsetof(struct kvm_vcpu, arch.lr));
 	DEFINE(VCPU_CR, offsetof(struct kvm_vcpu, arch.cr));
 	DEFINE(VCPU_PC, offsetof(struct kvm_vcpu, arch.pc));
-#ifdef CONFIG_KVM_BOOK3S_64_HV
+#ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE
 	DEFINE(VCPU_MSR, offsetof(struct kvm_vcpu, arch.shregs.msr));
 	DEFINE(VCPU_SRR0, offsetof(struct kvm_vcpu, arch.shregs.srr0));
 	DEFINE(VCPU_SRR1, offsetof(struct kvm_vcpu, arch.shregs.srr1));
@@ -476,7 +476,7 @@ int main(void)
 	DEFINE(KVM_LPID, offsetof(struct kvm, arch.lpid));
 
 	/* book3s */
-#ifdef CONFIG_KVM_BOOK3S_64_HV
+#ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE
 	DEFINE(KVM_SDR1, offsetof(struct kvm, arch.sdr1));
 	DEFINE(KVM_HOST_LPID, offsetof(struct kvm, arch.host_lpid));
 	DEFINE(KVM_HOST_LPCR, offsetof(struct kvm, arch.host_lpcr));
@@ -586,7 +586,7 @@ int main(void)
 	HSTATE_FIELD(HSTATE_RESTORE_HID5, restore_hid5);
 	HSTATE_FIELD(HSTATE_NAPPING, napping);
 
-#ifdef CONFIG_KVM_BOOK3S_64_HV
+#ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE
 	HSTATE_FIELD(HSTATE_HWTHREAD_REQ, hwthread_req);
 	HSTATE_FIELD(HSTATE_HWTHREAD_STATE, hwthread_state);
 	HSTATE_FIELD(HSTATE_KVM_VCPU, kvm_vcpu);
@@ -602,7 +602,7 @@ int main(void)
 	HSTATE_FIELD(HSTATE_DABR, dabr);
 	HSTATE_FIELD(HSTATE_DECEXP, dec_expires);
 	DEFINE(IPI_PRIORITY, IPI_PRIORITY);
-#endif /* CONFIG_KVM_BOOK3S_64_HV */
+#endif /* CONFIG_KVM_BOOK3S_HV_POSSIBLE */
 
 #ifdef CONFIG_PPC_BOOK3S_64
 	HSTATE_FIELD(HSTATE_CFAR, cfar);
diff --git a/arch/powerpc/kernel/idle_power7.S b/arch/powerpc/kernel/idle_power7.S
index e11863f4e59..847e40e62fc 100644
--- a/arch/powerpc/kernel/idle_power7.S
+++ b/arch/powerpc/kernel/idle_power7.S
@@ -84,7 +84,7 @@ _GLOBAL(power7_nap)
 	std	r9,_MSR(r1)
 	std	r1,PACAR1(r13)
 
-#ifdef CONFIG_KVM_BOOK3S_64_HV
+#ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE
 	/* Tell KVM we're napping */
 	li	r4,KVM_HWTHREAD_IN_NAP
 	stb	r4,HSTATE_HWTHREAD_STATE(r13)
diff --git a/arch/powerpc/kvm/Kconfig b/arch/powerpc/kvm/Kconfig
index d0665f231e6..a96d7c32f78 100644
--- a/arch/powerpc/kvm/Kconfig
+++ b/arch/powerpc/kvm/Kconfig
@@ -39,6 +39,9 @@ config KVM_BOOK3S_PR_POSSIBLE
 	select KVM_MMIO
 	select MMU_NOTIFIER
 
+config KVM_BOOK3S_HV_POSSIBLE
+	bool
+
 config KVM_BOOK3S_32
 	tristate "KVM support for PowerPC book3s_32 processors"
 	depends on PPC_BOOK3S_32 && !SMP && !PTE_64BIT
@@ -59,6 +62,7 @@ config KVM_BOOK3S_64
 	depends on PPC_BOOK3S_64
 	select KVM_BOOK3S_64_HANDLER
 	select KVM
+	select KVM_BOOK3S_PR_POSSIBLE if !KVM_BOOK3S_HV_POSSIBLE
 	---help---
 	  Support running unmodified book3s_64 and book3s_32 guest kernels
 	  in virtual machines on book3s_64 host processors.
@@ -71,6 +75,7 @@ config KVM_BOOK3S_64
 config KVM_BOOK3S_64_HV
 	bool "KVM support for POWER7 and PPC970 using hypervisor mode in host"
 	depends on KVM_BOOK3S_64
+	select KVM_BOOK3S_HV_POSSIBLE
 	select MMU_NOTIFIER
 	select CMA
 	---help---
@@ -89,9 +94,20 @@ config KVM_BOOK3S_64_HV
 	  If unsure, say N.
 
 config KVM_BOOK3S_64_PR
-	def_bool y
+	bool "KVM support without using hypervisor mode in host"
 	depends on KVM_BOOK3S_64 && !KVM_BOOK3S_64_HV
 	select KVM_BOOK3S_PR_POSSIBLE
+	---help---
+	  Support running guest kernels in virtual machines on processors
+	  without using hypervisor mode in the host, by running the
+	  guest in user mode (problem state) and emulating all
+	  privileged instructions and registers.
+
+	  This is not as fast as using hypervisor mode, but works on
+	  machines where hypervisor mode is not available or not usable,
+	  and can emulate processors that are different from the host
+	  processor, including emulating 32-bit processors on a 64-bit
+	  host.
 
 config KVM_BOOKE_HV
 	bool
diff --git a/arch/powerpc/kvm/Makefile b/arch/powerpc/kvm/Makefile
index 104e8dcf433..fa17b337bb9 100644
--- a/arch/powerpc/kvm/Makefile
+++ b/arch/powerpc/kvm/Makefile
@@ -57,7 +57,6 @@ kvm-book3s_64-builtin-objs-$(CONFIG_KVM_BOOK3S_64_HANDLER) := \
 	book3s_64_vio_hv.o
 
 kvm-book3s_64-objs-$(CONFIG_KVM_BOOK3S_64_PR) := \
-	$(KVM)/coalesced_mmio.o \
 	fpu.o \
 	book3s_paired_singles.o \
 	book3s_pr.o \
@@ -69,10 +68,15 @@ kvm-book3s_64-objs-$(CONFIG_KVM_BOOK3S_64_PR) := \
 	book3s_64_mmu.o \
 	book3s_32_mmu.o
 
-kvm-book3s_64-builtin-objs-$(CONFIG_KVM_BOOK3S_64_PR) += \
+ifdef CONFIG_KVM_BOOK3S_PR_POSSIBLE
+kvm-book3s_64-module-objs := \
+	$(KVM)/coalesced_mmio.o
+
+kvm-book3s_64-builtin-objs-$(CONFIG_KVM_BOOK3S_64_HANDLER) += \
 	book3s_rmhandlers.o
+endif
 
-kvm-book3s_64-objs-$(CONFIG_KVM_BOOK3S_64_HV) := \
+kvm-book3s_64-objs-$(CONFIG_KVM_BOOK3S_64_HV)  += \
 	book3s_hv.o \
 	book3s_hv_interrupts.o \
 	book3s_64_mmu_hv.o
@@ -91,7 +95,7 @@ kvm-book3s_64-builtin-objs-$(CONFIG_KVM_BOOK3S_64_HV) += \
 kvm-book3s_64-objs-$(CONFIG_KVM_XICS) += \
 	book3s_xics.o
 
-kvm-book3s_64-module-objs := \
+kvm-book3s_64-module-objs += \
 	$(KVM)/kvm_main.o \
 	$(KVM)/eventfd.o \
 	powerpc.o \
diff --git a/arch/powerpc/kvm/book3s_exports.c b/arch/powerpc/kvm/book3s_exports.c
index 7057a02f090..852989a9bad 100644
--- a/arch/powerpc/kvm/book3s_exports.c
+++ b/arch/powerpc/kvm/book3s_exports.c
@@ -20,9 +20,10 @@
 #include <linux/export.h>
 #include <asm/kvm_book3s.h>
 
-#ifdef CONFIG_KVM_BOOK3S_64_HV
+#ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE
 EXPORT_SYMBOL_GPL(kvmppc_hv_entry_trampoline);
-#else
+#endif
+#ifdef CONFIG_KVM_BOOK3S_PR_POSSIBLE
 EXPORT_SYMBOL_GPL(kvmppc_entry_trampoline);
 EXPORT_SYMBOL_GPL(kvmppc_load_up_fpu);
 #ifdef CONFIG_ALTIVEC
-- 
cgit v1.2.3-70-g09d2


From 3a167beac07cba597856c12b87638a06b0d53db7 Mon Sep 17 00:00:00 2001
From: "Aneesh Kumar K.V" <aneesh.kumar@linux.vnet.ibm.com>
Date: Mon, 7 Oct 2013 22:17:53 +0530
Subject: kvm: powerpc: Add kvmppc_ops callback

This patch add a new callback kvmppc_ops. This will help us in enabling
both HV and PR KVM together in the same kernel. The actual change to
enable them together is done in the later patch in the series.

Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
[agraf: squash in booke changes]
Signed-off-by: Alexander Graf <agraf@suse.de>
---
 arch/powerpc/include/asm/kvm_book3s.h |   1 -
 arch/powerpc/include/asm/kvm_ppc.h    |  89 ++++++++++----
 arch/powerpc/kernel/exceptions-64s.S  |   2 +-
 arch/powerpc/kvm/44x.c                |  55 ++++++---
 arch/powerpc/kvm/44x_emulate.c        |   8 +-
 arch/powerpc/kvm/44x_tlb.c            |   2 +-
 arch/powerpc/kvm/book3s.c             | 145 +++++++++++++++++++++-
 arch/powerpc/kvm/book3s.h             |  32 +++++
 arch/powerpc/kvm/book3s_32_mmu_host.c |   2 +-
 arch/powerpc/kvm/book3s_64_mmu_host.c |   2 +-
 arch/powerpc/kvm/book3s_64_mmu_hv.c   |  17 ++-
 arch/powerpc/kvm/book3s_emulate.c     |   8 +-
 arch/powerpc/kvm/book3s_hv.c          | 220 ++++++++++++++++++++++++----------
 arch/powerpc/kvm/book3s_interrupts.S  |   2 +-
 arch/powerpc/kvm/book3s_pr.c          | 194 +++++++++++++++++++-----------
 arch/powerpc/kvm/book3s_xics.c        |   4 +-
 arch/powerpc/kvm/booke.c              |  47 +++++++-
 arch/powerpc/kvm/booke.h              |  24 ++++
 arch/powerpc/kvm/e500.c               |  53 +++++---
 arch/powerpc/kvm/e500_emulate.c       |   8 +-
 arch/powerpc/kvm/e500_mmu.c           |   2 +-
 arch/powerpc/kvm/e500mc.c             |  54 ++++++---
 arch/powerpc/kvm/emulate.c            |   6 +-
 arch/powerpc/kvm/powerpc.c            |  58 +++------
 24 files changed, 748 insertions(+), 287 deletions(-)
 create mode 100644 arch/powerpc/kvm/book3s.h

(limited to 'arch/powerpc/kvm')

diff --git a/arch/powerpc/include/asm/kvm_book3s.h b/arch/powerpc/include/asm/kvm_book3s.h
index 99ef8711e90..315a5d69241 100644
--- a/arch/powerpc/include/asm/kvm_book3s.h
+++ b/arch/powerpc/include/asm/kvm_book3s.h
@@ -124,7 +124,6 @@ extern void kvmppc_mmu_pte_flush(struct kvm_vcpu *vcpu, ulong ea, ulong ea_mask)
 extern void kvmppc_mmu_pte_vflush(struct kvm_vcpu *vcpu, u64 vp, u64 vp_mask);
 extern void kvmppc_mmu_pte_pflush(struct kvm_vcpu *vcpu, ulong pa_start, ulong pa_end);
 extern void kvmppc_set_msr(struct kvm_vcpu *vcpu, u64 new_msr);
-extern void kvmppc_set_pvr(struct kvm_vcpu *vcpu, u32 pvr);
 extern void kvmppc_mmu_book3s_64_init(struct kvm_vcpu *vcpu);
 extern void kvmppc_mmu_book3s_32_init(struct kvm_vcpu *vcpu);
 extern void kvmppc_mmu_book3s_hv_init(struct kvm_vcpu *vcpu);
diff --git a/arch/powerpc/include/asm/kvm_ppc.h b/arch/powerpc/include/asm/kvm_ppc.h
index 1823f38906c..326033c9938 100644
--- a/arch/powerpc/include/asm/kvm_ppc.h
+++ b/arch/powerpc/include/asm/kvm_ppc.h
@@ -106,13 +106,6 @@ extern void kvmppc_core_queue_external(struct kvm_vcpu *vcpu,
                                        struct kvm_interrupt *irq);
 extern void kvmppc_core_dequeue_external(struct kvm_vcpu *vcpu);
 extern void kvmppc_core_flush_tlb(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,
-				     ulong val);
-extern int kvmppc_core_emulate_mfspr(struct kvm_vcpu *vcpu, int sprn,
-				     ulong *val);
 extern int kvmppc_core_check_requests(struct kvm_vcpu *vcpu);
 
 extern int kvmppc_booke_init(void);
@@ -135,8 +128,6 @@ 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 kvm_rma_info *kvm_alloc_rma(void);
 extern void kvm_release_rma(struct kvm_rma_info *ri);
 extern struct page *kvm_alloc_hpt(unsigned long nr_pages);
@@ -177,6 +168,66 @@ extern int kvmppc_xics_get_xive(struct kvm *kvm, u32 irq, u32 *server,
 extern int kvmppc_xics_int_on(struct kvm *kvm, u32 irq);
 extern int kvmppc_xics_int_off(struct kvm *kvm, u32 irq);
 
+union kvmppc_one_reg {
+	u32	wval;
+	u64	dval;
+	vector128 vval;
+	u64	vsxval[2];
+	struct {
+		u64	addr;
+		u64	length;
+	}	vpaval;
+};
+
+struct kvmppc_ops {
+	int (*get_sregs)(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs);
+	int (*set_sregs)(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs);
+	int (*get_one_reg)(struct kvm_vcpu *vcpu, u64 id,
+			   union kvmppc_one_reg *val);
+	int (*set_one_reg)(struct kvm_vcpu *vcpu, u64 id,
+			   union kvmppc_one_reg *val);
+	void (*vcpu_load)(struct kvm_vcpu *vcpu, int cpu);
+	void (*vcpu_put)(struct kvm_vcpu *vcpu);
+	void (*set_msr)(struct kvm_vcpu *vcpu, u64 msr);
+	int (*vcpu_run)(struct kvm_run *run, struct kvm_vcpu *vcpu);
+	struct kvm_vcpu *(*vcpu_create)(struct kvm *kvm, unsigned int id);
+	void (*vcpu_free)(struct kvm_vcpu *vcpu);
+	int (*check_requests)(struct kvm_vcpu *vcpu);
+	int (*get_dirty_log)(struct kvm *kvm, struct kvm_dirty_log *log);
+	void (*flush_memslot)(struct kvm *kvm, struct kvm_memory_slot *memslot);
+	int (*prepare_memory_region)(struct kvm *kvm,
+				     struct kvm_memory_slot *memslot,
+				     struct kvm_userspace_memory_region *mem);
+	void (*commit_memory_region)(struct kvm *kvm,
+				     struct kvm_userspace_memory_region *mem,
+				     const struct kvm_memory_slot *old);
+	int (*unmap_hva)(struct kvm *kvm, unsigned long hva);
+	int (*unmap_hva_range)(struct kvm *kvm, unsigned long start,
+			   unsigned long end);
+	int (*age_hva)(struct kvm *kvm, unsigned long hva);
+	int (*test_age_hva)(struct kvm *kvm, unsigned long hva);
+	void (*set_spte_hva)(struct kvm *kvm, unsigned long hva, pte_t pte);
+	void (*mmu_destroy)(struct kvm_vcpu *vcpu);
+	void (*free_memslot)(struct kvm_memory_slot *free,
+			     struct kvm_memory_slot *dont);
+	int (*create_memslot)(struct kvm_memory_slot *slot,
+			      unsigned long npages);
+	int (*init_vm)(struct kvm *kvm);
+	void (*destroy_vm)(struct kvm *kvm);
+	int (*check_processor_compat)(void);
+	int (*get_smmu_info)(struct kvm *kvm, struct kvm_ppc_smmu_info *info);
+	int (*emulate_op)(struct kvm_run *run, struct kvm_vcpu *vcpu,
+			  unsigned int inst, int *advance);
+	int (*emulate_mtspr)(struct kvm_vcpu *vcpu, int sprn, ulong spr_val);
+	int (*emulate_mfspr)(struct kvm_vcpu *vcpu, int sprn, ulong *spr_val);
+	void (*fast_vcpu_kick)(struct kvm_vcpu *vcpu);
+	long (*arch_vm_ioctl)(struct file *filp, unsigned int ioctl,
+			      unsigned long arg);
+
+};
+
+extern struct kvmppc_ops *kvmppc_ops;
+
 /*
  * Cuts out inst bits with ordering according to spec.
  * That means the leftmost bit is zero. All given bits are included.
@@ -210,17 +261,6 @@ static inline u32 kvmppc_set_field(u64 inst, int msb, int lsb, int value)
 	return r;
 }
 
-union kvmppc_one_reg {
-	u32	wval;
-	u64	dval;
-	vector128 vval;
-	u64	vsxval[2];
-	struct {
-		u64	addr;
-		u64	length;
-	}	vpaval;
-};
-
 #define one_reg_size(id)	\
 	(1ul << (((id) & KVM_REG_SIZE_MASK) >> KVM_REG_SIZE_SHIFT))
 
@@ -245,10 +285,10 @@ union kvmppc_one_reg {
 	__v;					\
 })
 
-void kvmppc_core_get_sregs(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs);
+int kvmppc_core_get_sregs(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs);
 int kvmppc_core_set_sregs(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs);
 
-void kvmppc_get_sregs_ivor(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs);
+int kvmppc_get_sregs_ivor(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs);
 int kvmppc_set_sregs_ivor(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs);
 
 int kvm_vcpu_ioctl_get_one_reg(struct kvm_vcpu *vcpu, struct kvm_one_reg *reg);
@@ -281,7 +321,10 @@ static inline void kvmppc_set_host_ipi(int cpu, u8 host_ipi)
 	paca[cpu].kvm_hstate.host_ipi = host_ipi;
 }
 
-extern void kvmppc_fast_vcpu_kick(struct kvm_vcpu *vcpu);
+static inline void kvmppc_fast_vcpu_kick(struct kvm_vcpu *vcpu)
+{
+	kvmppc_ops->fast_vcpu_kick(vcpu);
+}
 
 #else
 static inline void __init kvm_cma_reserve(void)
diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S
index 3d1c42b03c8..9f905e40922 100644
--- a/arch/powerpc/kernel/exceptions-64s.S
+++ b/arch/powerpc/kernel/exceptions-64s.S
@@ -126,7 +126,7 @@ BEGIN_FTR_SECTION
 	bgt	cr1,.
 	GET_PACA(r13)
 
-#ifdef CONFIG_KVM_BOOK3S_64_HV
+#ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE
 	li	r0,KVM_HWTHREAD_IN_KERNEL
 	stb	r0,HSTATE_HWTHREAD_STATE(r13)
 	/* Order setting hwthread_state vs. testing hwthread_req */
diff --git a/arch/powerpc/kvm/44x.c b/arch/powerpc/kvm/44x.c
index 2f5c6b6d687..a765bcd74fb 100644
--- a/arch/powerpc/kvm/44x.c
+++ b/arch/powerpc/kvm/44x.c
@@ -31,13 +31,13 @@
 #include "44x_tlb.h"
 #include "booke.h"
 
-void kvmppc_core_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
+static void kvmppc_core_vcpu_load_44x(struct kvm_vcpu *vcpu, int cpu)
 {
 	kvmppc_booke_vcpu_load(vcpu, cpu);
 	kvmppc_44x_tlb_load(vcpu);
 }
 
-void kvmppc_core_vcpu_put(struct kvm_vcpu *vcpu)
+static void kvmppc_core_vcpu_put_44x(struct kvm_vcpu *vcpu)
 {
 	kvmppc_44x_tlb_put(vcpu);
 	kvmppc_booke_vcpu_put(vcpu);
@@ -114,29 +114,32 @@ int kvmppc_core_vcpu_translate(struct kvm_vcpu *vcpu,
 	return 0;
 }
 
-void kvmppc_core_get_sregs(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs)
+static int kvmppc_core_get_sregs_44x(struct kvm_vcpu *vcpu,
+				      struct kvm_sregs *sregs)
 {
-	kvmppc_get_sregs_ivor(vcpu, sregs);
+	return kvmppc_get_sregs_ivor(vcpu, sregs);
 }
 
-int kvmppc_core_set_sregs(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs)
+static int kvmppc_core_set_sregs_44x(struct kvm_vcpu *vcpu,
+				     struct kvm_sregs *sregs)
 {
 	return kvmppc_set_sregs_ivor(vcpu, sregs);
 }
 
-int kvmppc_get_one_reg(struct kvm_vcpu *vcpu, u64 id,
-			union kvmppc_one_reg *val)
+static int kvmppc_get_one_reg_44x(struct kvm_vcpu *vcpu, u64 id,
+				  union kvmppc_one_reg *val)
 {
 	return -EINVAL;
 }
 
-int kvmppc_set_one_reg(struct kvm_vcpu *vcpu, u64 id,
-		       union kvmppc_one_reg *val)
+static int kvmppc_set_one_reg_44x(struct kvm_vcpu *vcpu, u64 id,
+				  union kvmppc_one_reg *val)
 {
 	return -EINVAL;
 }
 
-struct kvm_vcpu *kvmppc_core_vcpu_create(struct kvm *kvm, unsigned int id)
+static struct kvm_vcpu *kvmppc_core_vcpu_create_44x(struct kvm *kvm,
+						    unsigned int id)
 {
 	struct kvmppc_vcpu_44x *vcpu_44x;
 	struct kvm_vcpu *vcpu;
@@ -167,7 +170,7 @@ out:
 	return ERR_PTR(err);
 }
 
-void kvmppc_core_vcpu_free(struct kvm_vcpu *vcpu)
+static void kvmppc_core_vcpu_free_44x(struct kvm_vcpu *vcpu)
 {
 	struct kvmppc_vcpu_44x *vcpu_44x = to_44x(vcpu);
 
@@ -176,24 +179,46 @@ void kvmppc_core_vcpu_free(struct kvm_vcpu *vcpu)
 	kmem_cache_free(kvm_vcpu_cache, vcpu_44x);
 }
 
-int kvmppc_core_init_vm(struct kvm *kvm)
+static int kvmppc_core_init_vm_44x(struct kvm *kvm)
 {
 	return 0;
 }
 
-void kvmppc_core_destroy_vm(struct kvm *kvm)
+static void kvmppc_core_destroy_vm_44x(struct kvm *kvm)
 {
 }
 
+static struct kvmppc_ops kvm_ops_44x = {
+	.get_sregs = kvmppc_core_get_sregs_44x,
+	.set_sregs = kvmppc_core_set_sregs_44x,
+	.get_one_reg = kvmppc_get_one_reg_44x,
+	.set_one_reg = kvmppc_set_one_reg_44x,
+	.vcpu_load   = kvmppc_core_vcpu_load_44x,
+	.vcpu_put    = kvmppc_core_vcpu_put_44x,
+	.vcpu_create = kvmppc_core_vcpu_create_44x,
+	.vcpu_free   = kvmppc_core_vcpu_free_44x,
+	.mmu_destroy  = kvmppc_mmu_destroy_44x,
+	.init_vm = kvmppc_core_init_vm_44x,
+	.destroy_vm = kvmppc_core_destroy_vm_44x,
+	.emulate_op = kvmppc_core_emulate_op_44x,
+	.emulate_mtspr = kvmppc_core_emulate_mtspr_44x,
+	.emulate_mfspr = kvmppc_core_emulate_mfspr_44x,
+};
+
 static int __init kvmppc_44x_init(void)
 {
 	int r;
 
 	r = kvmppc_booke_init();
 	if (r)
-		return r;
+		goto err_out;
 
-	return kvm_init(NULL, sizeof(struct kvmppc_vcpu_44x), 0, THIS_MODULE);
+	r = kvm_init(&kvm_ops_44x, sizeof(struct kvmppc_vcpu_44x),
+		     0, THIS_MODULE);
+	if (r)
+		goto err_out;
+err_out:
+	return r;
 }
 
 static void __exit kvmppc_44x_exit(void)
diff --git a/arch/powerpc/kvm/44x_emulate.c b/arch/powerpc/kvm/44x_emulate.c
index 35ec0a8547d..92c9ab4bcfe 100644
--- a/arch/powerpc/kvm/44x_emulate.c
+++ b/arch/powerpc/kvm/44x_emulate.c
@@ -91,8 +91,8 @@ static int emulate_mfdcr(struct kvm_vcpu *vcpu, int rt, int dcrn)
 	return EMULATE_DONE;
 }
 
-int kvmppc_core_emulate_op(struct kvm_run *run, struct kvm_vcpu *vcpu,
-                           unsigned int inst, int *advance)
+int kvmppc_core_emulate_op_44x(struct kvm_run *run, struct kvm_vcpu *vcpu,
+			       unsigned int inst, int *advance)
 {
 	int emulated = EMULATE_DONE;
 	int dcrn = get_dcrn(inst);
@@ -152,7 +152,7 @@ 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, ulong spr_val)
+int kvmppc_core_emulate_mtspr_44x(struct kvm_vcpu *vcpu, int sprn, ulong spr_val)
 {
 	int emulated = EMULATE_DONE;
 
@@ -172,7 +172,7 @@ int kvmppc_core_emulate_mtspr(struct kvm_vcpu *vcpu, int sprn, ulong spr_val)
 	return emulated;
 }
 
-int kvmppc_core_emulate_mfspr(struct kvm_vcpu *vcpu, int sprn, ulong *spr_val)
+int kvmppc_core_emulate_mfspr_44x(struct kvm_vcpu *vcpu, int sprn, ulong *spr_val)
 {
 	int emulated = EMULATE_DONE;
 
diff --git a/arch/powerpc/kvm/44x_tlb.c b/arch/powerpc/kvm/44x_tlb.c
index ed038544814..0deef1082e0 100644
--- a/arch/powerpc/kvm/44x_tlb.c
+++ b/arch/powerpc/kvm/44x_tlb.c
@@ -268,7 +268,7 @@ static void kvmppc_44x_shadow_release(struct kvmppc_vcpu_44x *vcpu_44x,
 	trace_kvm_stlb_inval(stlb_index);
 }
 
-void kvmppc_mmu_destroy(struct kvm_vcpu *vcpu)
+void kvmppc_mmu_destroy_44x(struct kvm_vcpu *vcpu)
 {
 	struct kvmppc_vcpu_44x *vcpu_44x = to_44x(vcpu);
 	int i;
diff --git a/arch/powerpc/kvm/book3s.c b/arch/powerpc/kvm/book3s.c
index 807103ad262..784a1d5ccb0 100644
--- a/arch/powerpc/kvm/book3s.c
+++ b/arch/powerpc/kvm/book3s.c
@@ -422,6 +422,18 @@ void kvmppc_subarch_vcpu_uninit(struct kvm_vcpu *vcpu)
 {
 }
 
+int kvm_arch_vcpu_ioctl_get_sregs(struct kvm_vcpu *vcpu,
+				  struct kvm_sregs *sregs)
+{
+	return kvmppc_ops->get_sregs(vcpu, sregs);
+}
+
+int kvm_arch_vcpu_ioctl_set_sregs(struct kvm_vcpu *vcpu,
+				  struct kvm_sregs *sregs)
+{
+	return kvmppc_ops->set_sregs(vcpu, sregs);
+}
+
 int kvm_arch_vcpu_ioctl_get_regs(struct kvm_vcpu *vcpu, struct kvm_regs *regs)
 {
 	int i;
@@ -498,8 +510,7 @@ int kvm_vcpu_ioctl_get_one_reg(struct kvm_vcpu *vcpu, struct kvm_one_reg *reg)
 	if (size > sizeof(val))
 		return -EINVAL;
 
-	r = kvmppc_get_one_reg(vcpu, reg->id, &val);
-
+	r = kvmppc_ops->get_one_reg(vcpu, reg->id, &val);
 	if (r == -EINVAL) {
 		r = 0;
 		switch (reg->id) {
@@ -578,8 +589,7 @@ int kvm_vcpu_ioctl_set_one_reg(struct kvm_vcpu *vcpu, struct kvm_one_reg *reg)
 	if (copy_from_user(&val, (char __user *)(unsigned long)reg->addr, size))
 		return -EFAULT;
 
-	r = kvmppc_set_one_reg(vcpu, reg->id, &val);
-
+	r = kvmppc_ops->set_one_reg(vcpu, reg->id, &val);
 	if (r == -EINVAL) {
 		r = 0;
 		switch (reg->id) {
@@ -638,6 +648,26 @@ int kvm_vcpu_ioctl_set_one_reg(struct kvm_vcpu *vcpu, struct kvm_one_reg *reg)
 	return r;
 }
 
+void kvmppc_core_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
+{
+	kvmppc_ops->vcpu_load(vcpu, cpu);
+}
+
+void kvmppc_core_vcpu_put(struct kvm_vcpu *vcpu)
+{
+	kvmppc_ops->vcpu_put(vcpu);
+}
+
+void kvmppc_set_msr(struct kvm_vcpu *vcpu, u64 msr)
+{
+	kvmppc_ops->set_msr(vcpu, msr);
+}
+
+int kvmppc_vcpu_run(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu)
+{
+	return kvmppc_ops->vcpu_run(kvm_run, vcpu);
+}
+
 int kvm_arch_vcpu_ioctl_translate(struct kvm_vcpu *vcpu,
                                   struct kvm_translation *tr)
 {
@@ -657,3 +687,110 @@ void kvmppc_decrementer_func(unsigned long data)
 	kvmppc_core_queue_dec(vcpu);
 	kvm_vcpu_kick(vcpu);
 }
+
+struct kvm_vcpu *kvmppc_core_vcpu_create(struct kvm *kvm, unsigned int id)
+{
+	return kvmppc_ops->vcpu_create(kvm, id);
+}
+
+void kvmppc_core_vcpu_free(struct kvm_vcpu *vcpu)
+{
+	kvmppc_ops->vcpu_free(vcpu);
+}
+
+int kvmppc_core_check_requests(struct kvm_vcpu *vcpu)
+{
+	return kvmppc_ops->check_requests(vcpu);
+}
+
+int kvm_vm_ioctl_get_dirty_log(struct kvm *kvm, struct kvm_dirty_log *log)
+{
+	return kvmppc_ops->get_dirty_log(kvm, log);
+}
+
+void kvmppc_core_free_memslot(struct kvm_memory_slot *free,
+			      struct kvm_memory_slot *dont)
+{
+	kvmppc_ops->free_memslot(free, dont);
+}
+
+int kvmppc_core_create_memslot(struct kvm_memory_slot *slot,
+			       unsigned long npages)
+{
+	return kvmppc_ops->create_memslot(slot, npages);
+}
+
+void kvmppc_core_flush_memslot(struct kvm *kvm, struct kvm_memory_slot *memslot)
+{
+	kvmppc_ops->flush_memslot(kvm, memslot);
+}
+
+int kvmppc_core_prepare_memory_region(struct kvm *kvm,
+				struct kvm_memory_slot *memslot,
+				struct kvm_userspace_memory_region *mem)
+{
+	return kvmppc_ops->prepare_memory_region(kvm, memslot, mem);
+}
+
+void kvmppc_core_commit_memory_region(struct kvm *kvm,
+				struct kvm_userspace_memory_region *mem,
+				const struct kvm_memory_slot *old)
+{
+	kvmppc_ops->commit_memory_region(kvm, mem, old);
+}
+
+int kvm_unmap_hva(struct kvm *kvm, unsigned long hva)
+{
+	return kvmppc_ops->unmap_hva(kvm, hva);
+}
+
+int kvm_unmap_hva_range(struct kvm *kvm, unsigned long start, unsigned long end)
+{
+	return kvmppc_ops->unmap_hva_range(kvm, start, end);
+}
+
+int kvm_age_hva(struct kvm *kvm, unsigned long hva)
+{
+	return kvmppc_ops->age_hva(kvm, hva);
+}
+
+int kvm_test_age_hva(struct kvm *kvm, unsigned long hva)
+{
+	return kvmppc_ops->test_age_hva(kvm, hva);
+}
+
+void kvm_set_spte_hva(struct kvm *kvm, unsigned long hva, pte_t pte)
+{
+	kvmppc_ops->set_spte_hva(kvm, hva, pte);
+}
+
+void kvmppc_mmu_destroy(struct kvm_vcpu *vcpu)
+{
+	kvmppc_ops->mmu_destroy(vcpu);
+}
+
+int kvmppc_core_init_vm(struct kvm *kvm)
+{
+
+#ifdef CONFIG_PPC64
+	INIT_LIST_HEAD(&kvm->arch.spapr_tce_tables);
+	INIT_LIST_HEAD(&kvm->arch.rtas_tokens);
+#endif
+
+	return kvmppc_ops->init_vm(kvm);
+}
+
+void kvmppc_core_destroy_vm(struct kvm *kvm)
+{
+	kvmppc_ops->destroy_vm(kvm);
+
+#ifdef CONFIG_PPC64
+	kvmppc_rtas_tokens_free(kvm);
+	WARN_ON(!list_empty(&kvm->arch.spapr_tce_tables));
+#endif
+}
+
+int kvmppc_core_check_processor_compat(void)
+{
+	return kvmppc_ops->check_processor_compat();
+}
diff --git a/arch/powerpc/kvm/book3s.h b/arch/powerpc/kvm/book3s.h
new file mode 100644
index 00000000000..9e5b3a34194
--- /dev/null
+++ b/arch/powerpc/kvm/book3s.h
@@ -0,0 +1,32 @@
+/*
+ * Copyright IBM Corporation, 2013
+ * Author Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License as
+ * published by the Free Software Foundation; either version 2 of the
+ * License or (at your optional) any later version of the license.
+ *
+ */
+
+#ifndef __POWERPC_KVM_BOOK3S_H__
+#define __POWERPC_KVM_BOOK3S_H__
+
+extern void kvmppc_core_flush_memslot_hv(struct kvm *kvm,
+					 struct kvm_memory_slot *memslot);
+extern int kvm_unmap_hva_hv(struct kvm *kvm, unsigned long hva);
+extern int kvm_unmap_hva_range_hv(struct kvm *kvm, unsigned long start,
+				  unsigned long end);
+extern int kvm_age_hva_hv(struct kvm *kvm, unsigned long hva);
+extern int kvm_test_age_hva_hv(struct kvm *kvm, unsigned long hva);
+extern void kvm_set_spte_hva_hv(struct kvm *kvm, unsigned long hva, pte_t pte);
+
+extern void kvmppc_mmu_destroy_pr(struct kvm_vcpu *vcpu);
+extern int kvmppc_core_emulate_op_pr(struct kvm_run *run, struct kvm_vcpu *vcpu,
+				     unsigned int inst, int *advance);
+extern int kvmppc_core_emulate_mtspr_pr(struct kvm_vcpu *vcpu,
+					int sprn, ulong spr_val);
+extern int kvmppc_core_emulate_mfspr_pr(struct kvm_vcpu *vcpu,
+					int sprn, ulong *spr_val);
+
+#endif
diff --git a/arch/powerpc/kvm/book3s_32_mmu_host.c b/arch/powerpc/kvm/book3s_32_mmu_host.c
index 67332232923..3a0abd2e5a1 100644
--- a/arch/powerpc/kvm/book3s_32_mmu_host.c
+++ b/arch/powerpc/kvm/book3s_32_mmu_host.c
@@ -349,7 +349,7 @@ void kvmppc_mmu_flush_segments(struct kvm_vcpu *vcpu)
 	svcpu_put(svcpu);
 }
 
-void kvmppc_mmu_destroy(struct kvm_vcpu *vcpu)
+void kvmppc_mmu_destroy_pr(struct kvm_vcpu *vcpu)
 {
 	int i;
 
diff --git a/arch/powerpc/kvm/book3s_64_mmu_host.c b/arch/powerpc/kvm/book3s_64_mmu_host.c
index e2ab8a747fb..819672c9d78 100644
--- a/arch/powerpc/kvm/book3s_64_mmu_host.c
+++ b/arch/powerpc/kvm/book3s_64_mmu_host.c
@@ -378,7 +378,7 @@ void kvmppc_mmu_flush_segments(struct kvm_vcpu *vcpu)
 	svcpu_put(svcpu);
 }
 
-void kvmppc_mmu_destroy(struct kvm_vcpu *vcpu)
+void kvmppc_mmu_destroy_pr(struct kvm_vcpu *vcpu)
 {
 	kvmppc_mmu_hpte_destroy(vcpu);
 	__destroy_context(to_book3s(vcpu)->context_id[0]);
diff --git a/arch/powerpc/kvm/book3s_64_mmu_hv.c b/arch/powerpc/kvm/book3s_64_mmu_hv.c
index 394fef820f0..f3ff587a8b7 100644
--- a/arch/powerpc/kvm/book3s_64_mmu_hv.c
+++ b/arch/powerpc/kvm/book3s_64_mmu_hv.c
@@ -260,10 +260,6 @@ int kvmppc_mmu_hv_init(void)
 	return 0;
 }
 
-void kvmppc_mmu_destroy(struct kvm_vcpu *vcpu)
-{
-}
-
 static void kvmppc_mmu_book3s_64_hv_reset_msr(struct kvm_vcpu *vcpu)
 {
 	kvmppc_set_msr(vcpu, MSR_SF | MSR_ME);
@@ -906,21 +902,22 @@ static int kvm_unmap_rmapp(struct kvm *kvm, unsigned long *rmapp,
 	return 0;
 }
 
-int kvm_unmap_hva(struct kvm *kvm, unsigned long hva)
+int kvm_unmap_hva_hv(struct kvm *kvm, unsigned long hva)
 {
 	if (kvm->arch.using_mmu_notifiers)
 		kvm_handle_hva(kvm, hva, kvm_unmap_rmapp);
 	return 0;
 }
 
-int kvm_unmap_hva_range(struct kvm *kvm, unsigned long start, unsigned long end)
+int kvm_unmap_hva_range_hv(struct kvm *kvm, unsigned long start, unsigned long end)
 {
 	if (kvm->arch.using_mmu_notifiers)
 		kvm_handle_hva_range(kvm, start, end, kvm_unmap_rmapp);
 	return 0;
 }
 
-void kvmppc_core_flush_memslot(struct kvm *kvm, struct kvm_memory_slot *memslot)
+void kvmppc_core_flush_memslot_hv(struct kvm *kvm,
+				  struct kvm_memory_slot *memslot)
 {
 	unsigned long *rmapp;
 	unsigned long gfn;
@@ -994,7 +991,7 @@ static int kvm_age_rmapp(struct kvm *kvm, unsigned long *rmapp,
 	return ret;
 }
 
-int kvm_age_hva(struct kvm *kvm, unsigned long hva)
+int kvm_age_hva_hv(struct kvm *kvm, unsigned long hva)
 {
 	if (!kvm->arch.using_mmu_notifiers)
 		return 0;
@@ -1032,14 +1029,14 @@ static int kvm_test_age_rmapp(struct kvm *kvm, unsigned long *rmapp,
 	return ret;
 }
 
-int kvm_test_age_hva(struct kvm *kvm, unsigned long hva)
+int kvm_test_age_hva_hv(struct kvm *kvm, unsigned long hva)
 {
 	if (!kvm->arch.using_mmu_notifiers)
 		return 0;
 	return kvm_handle_hva(kvm, hva, kvm_test_age_rmapp);
 }
 
-void kvm_set_spte_hva(struct kvm *kvm, unsigned long hva, pte_t pte)
+void kvm_set_spte_hva_hv(struct kvm *kvm, unsigned long hva, pte_t pte)
 {
 	if (!kvm->arch.using_mmu_notifiers)
 		return;
diff --git a/arch/powerpc/kvm/book3s_emulate.c b/arch/powerpc/kvm/book3s_emulate.c
index 34044b111da..b9841ad844f 100644
--- a/arch/powerpc/kvm/book3s_emulate.c
+++ b/arch/powerpc/kvm/book3s_emulate.c
@@ -86,8 +86,8 @@ static bool spr_allowed(struct kvm_vcpu *vcpu, enum priv_level level)
 	return true;
 }
 
-int kvmppc_core_emulate_op(struct kvm_run *run, struct kvm_vcpu *vcpu,
-                           unsigned int inst, int *advance)
+int kvmppc_core_emulate_op_pr(struct kvm_run *run, struct kvm_vcpu *vcpu,
+			      unsigned int inst, int *advance)
 {
 	int emulated = EMULATE_DONE;
 	int rt = get_rt(inst);
@@ -345,7 +345,7 @@ 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, ulong spr_val)
+int kvmppc_core_emulate_mtspr_pr(struct kvm_vcpu *vcpu, int sprn, ulong spr_val)
 {
 	int emulated = EMULATE_DONE;
 
@@ -468,7 +468,7 @@ unprivileged:
 	return emulated;
 }
 
-int kvmppc_core_emulate_mfspr(struct kvm_vcpu *vcpu, int sprn, ulong *spr_val)
+int kvmppc_core_emulate_mfspr_pr(struct kvm_vcpu *vcpu, int sprn, ulong *spr_val)
 {
 	int emulated = EMULATE_DONE;
 
diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c
index b4d5b3b0676..3d7079a08d2 100644
--- a/arch/powerpc/kvm/book3s_hv.c
+++ b/arch/powerpc/kvm/book3s_hv.c
@@ -53,6 +53,8 @@
 #include <linux/highmem.h>
 #include <linux/hugetlb.h>
 
+#include "book3s.h"
+
 /* #define EXIT_DEBUG */
 /* #define EXIT_DEBUG_SIMPLE */
 /* #define EXIT_DEBUG_INT */
@@ -66,7 +68,7 @@
 static void kvmppc_end_cede(struct kvm_vcpu *vcpu);
 static int kvmppc_hv_setup_htab_rma(struct kvm_vcpu *vcpu);
 
-void kvmppc_fast_vcpu_kick(struct kvm_vcpu *vcpu)
+static void kvmppc_fast_vcpu_kick_hv(struct kvm_vcpu *vcpu)
 {
 	int me;
 	int cpu = vcpu->cpu;
@@ -125,7 +127,7 @@ void kvmppc_fast_vcpu_kick(struct kvm_vcpu *vcpu)
  * purely defensive; they should never fail.)
  */
 
-void kvmppc_core_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
+static void kvmppc_core_vcpu_load_hv(struct kvm_vcpu *vcpu, int cpu)
 {
 	struct kvmppc_vcore *vc = vcpu->arch.vcore;
 
@@ -143,7 +145,7 @@ void kvmppc_core_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
 	spin_unlock(&vcpu->arch.tbacct_lock);
 }
 
-void kvmppc_core_vcpu_put(struct kvm_vcpu *vcpu)
+static void kvmppc_core_vcpu_put_hv(struct kvm_vcpu *vcpu)
 {
 	struct kvmppc_vcore *vc = vcpu->arch.vcore;
 
@@ -155,13 +157,13 @@ void kvmppc_core_vcpu_put(struct kvm_vcpu *vcpu)
 	spin_unlock(&vcpu->arch.tbacct_lock);
 }
 
-void kvmppc_set_msr(struct kvm_vcpu *vcpu, u64 msr)
+static void kvmppc_set_msr_hv(struct kvm_vcpu *vcpu, u64 msr)
 {
 	vcpu->arch.shregs.msr = msr;
 	kvmppc_end_cede(vcpu);
 }
 
-void kvmppc_set_pvr(struct kvm_vcpu *vcpu, u32 pvr)
+void kvmppc_set_pvr_hv(struct kvm_vcpu *vcpu, u32 pvr)
 {
 	vcpu->arch.pvr = pvr;
 }
@@ -614,8 +616,8 @@ int kvmppc_pseries_do_hcall(struct kvm_vcpu *vcpu)
 	return RESUME_GUEST;
 }
 
-static int kvmppc_handle_exit(struct kvm_run *run, struct kvm_vcpu *vcpu,
-			      struct task_struct *tsk)
+static int kvmppc_handle_exit_hv(struct kvm_run *run, struct kvm_vcpu *vcpu,
+				 struct task_struct *tsk)
 {
 	int r = RESUME_HOST;
 
@@ -717,8 +719,8 @@ static int kvmppc_handle_exit(struct kvm_run *run, struct kvm_vcpu *vcpu,
 	return r;
 }
 
-int kvm_arch_vcpu_ioctl_get_sregs(struct kvm_vcpu *vcpu,
-				  struct kvm_sregs *sregs)
+static int kvm_arch_vcpu_ioctl_get_sregs_hv(struct kvm_vcpu *vcpu,
+					    struct kvm_sregs *sregs)
 {
 	int i;
 
@@ -732,12 +734,12 @@ int kvm_arch_vcpu_ioctl_get_sregs(struct kvm_vcpu *vcpu,
 	return 0;
 }
 
-int kvm_arch_vcpu_ioctl_set_sregs(struct kvm_vcpu *vcpu,
-				  struct kvm_sregs *sregs)
+static int kvm_arch_vcpu_ioctl_set_sregs_hv(struct kvm_vcpu *vcpu,
+					    struct kvm_sregs *sregs)
 {
 	int i, j;
 
-	kvmppc_set_pvr(vcpu, sregs->pvr);
+	kvmppc_set_pvr_hv(vcpu, sregs->pvr);
 
 	j = 0;
 	for (i = 0; i < vcpu->arch.slb_nr; i++) {
@@ -767,7 +769,8 @@ static void kvmppc_set_lpcr(struct kvm_vcpu *vcpu, u64 new_lpcr)
 	spin_unlock(&vc->lock);
 }
 
-int kvmppc_get_one_reg(struct kvm_vcpu *vcpu, u64 id, union kvmppc_one_reg *val)
+static int kvmppc_get_one_reg_hv(struct kvm_vcpu *vcpu, u64 id,
+				 union kvmppc_one_reg *val)
 {
 	int r = 0;
 	long int i;
@@ -866,7 +869,8 @@ int kvmppc_get_one_reg(struct kvm_vcpu *vcpu, u64 id, union kvmppc_one_reg *val)
 	return r;
 }
 
-int kvmppc_set_one_reg(struct kvm_vcpu *vcpu, u64 id, union kvmppc_one_reg *val)
+static int kvmppc_set_one_reg_hv(struct kvm_vcpu *vcpu, u64 id,
+				 union kvmppc_one_reg *val)
 {
 	int r = 0;
 	long int i;
@@ -979,14 +983,8 @@ int kvmppc_set_one_reg(struct kvm_vcpu *vcpu, u64 id, union kvmppc_one_reg *val)
 	return r;
 }
 
-int kvmppc_core_check_processor_compat(void)
-{
-	if (cpu_has_feature(CPU_FTR_HVMODE))
-		return 0;
-	return -EIO;
-}
-
-struct kvm_vcpu *kvmppc_core_vcpu_create(struct kvm *kvm, unsigned int id)
+static struct kvm_vcpu *kvmppc_core_vcpu_create_hv(struct kvm *kvm,
+						   unsigned int id)
 {
 	struct kvm_vcpu *vcpu;
 	int err = -EINVAL;
@@ -1010,8 +1008,7 @@ struct kvm_vcpu *kvmppc_core_vcpu_create(struct kvm *kvm, unsigned int id)
 	vcpu->arch.mmcr[0] = MMCR0_FC;
 	vcpu->arch.ctrl = CTRL_RUNLATCH;
 	/* default to host PVR, since we can't spoof it */
-	vcpu->arch.pvr = mfspr(SPRN_PVR);
-	kvmppc_set_pvr(vcpu, vcpu->arch.pvr);
+	kvmppc_set_pvr_hv(vcpu, mfspr(SPRN_PVR));
 	spin_lock_init(&vcpu->arch.vpa_update_lock);
 	spin_lock_init(&vcpu->arch.tbacct_lock);
 	vcpu->arch.busy_preempt = TB_NIL;
@@ -1064,7 +1061,7 @@ static void unpin_vpa(struct kvm *kvm, struct kvmppc_vpa *vpa)
 					vpa->dirty);
 }
 
-void kvmppc_core_vcpu_free(struct kvm_vcpu *vcpu)
+static void kvmppc_core_vcpu_free_hv(struct kvm_vcpu *vcpu)
 {
 	spin_lock(&vcpu->arch.vpa_update_lock);
 	unpin_vpa(vcpu->kvm, &vcpu->arch.dtl);
@@ -1075,6 +1072,12 @@ void kvmppc_core_vcpu_free(struct kvm_vcpu *vcpu)
 	kmem_cache_free(kvm_vcpu_cache, vcpu);
 }
 
+static int kvmppc_core_check_requests_hv(struct kvm_vcpu *vcpu)
+{
+	/* Indicate we want to get back into the guest */
+	return 1;
+}
+
 static void kvmppc_set_timer(struct kvm_vcpu *vcpu)
 {
 	unsigned long dec_nsec, now;
@@ -1356,8 +1359,8 @@ static void kvmppc_run_core(struct kvmppc_vcore *vc)
 
 		ret = RESUME_GUEST;
 		if (vcpu->arch.trap)
-			ret = kvmppc_handle_exit(vcpu->arch.kvm_run, vcpu,
-						 vcpu->arch.run_task);
+			ret = kvmppc_handle_exit_hv(vcpu->arch.kvm_run, vcpu,
+						    vcpu->arch.run_task);
 
 		vcpu->arch.ret = ret;
 		vcpu->arch.trap = 0;
@@ -1516,7 +1519,7 @@ static int kvmppc_run_vcpu(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu)
 	return vcpu->arch.ret;
 }
 
-int kvmppc_vcpu_run(struct kvm_run *run, struct kvm_vcpu *vcpu)
+static int kvmppc_vcpu_run_hv(struct kvm_run *run, struct kvm_vcpu *vcpu)
 {
 	int r;
 	int srcu_idx;
@@ -1638,7 +1641,8 @@ static const struct file_operations kvm_rma_fops = {
 	.release	= kvm_rma_release,
 };
 
-long kvm_vm_ioctl_allocate_rma(struct kvm *kvm, struct kvm_allocate_rma *ret)
+static long kvm_vm_ioctl_allocate_rma(struct kvm *kvm,
+				      struct kvm_allocate_rma *ret)
 {
 	long fd;
 	struct kvm_rma_info *ri;
@@ -1684,7 +1688,8 @@ static void kvmppc_add_seg_page_size(struct kvm_ppc_one_seg_page_size **sps,
 	(*sps)++;
 }
 
-int kvm_vm_ioctl_get_smmu_info(struct kvm *kvm, struct kvm_ppc_smmu_info *info)
+static int kvm_vm_ioctl_get_smmu_info_hv(struct kvm *kvm,
+					 struct kvm_ppc_smmu_info *info)
 {
 	struct kvm_ppc_one_seg_page_size *sps;
 
@@ -1705,7 +1710,8 @@ int kvm_vm_ioctl_get_smmu_info(struct kvm *kvm, struct kvm_ppc_smmu_info *info)
 /*
  * Get (and clear) the dirty memory log for a memory slot.
  */
-int kvm_vm_ioctl_get_dirty_log(struct kvm *kvm, struct kvm_dirty_log *log)
+static int kvm_vm_ioctl_get_dirty_log_hv(struct kvm *kvm,
+					 struct kvm_dirty_log *log)
 {
 	struct kvm_memory_slot *memslot;
 	int r;
@@ -1759,8 +1765,8 @@ static void unpin_slot(struct kvm_memory_slot *memslot)
 	}
 }
 
-void kvmppc_core_free_memslot(struct kvm_memory_slot *free,
-			      struct kvm_memory_slot *dont)
+static void kvmppc_core_free_memslot_hv(struct kvm_memory_slot *free,
+					struct kvm_memory_slot *dont)
 {
 	if (!dont || free->arch.rmap != dont->arch.rmap) {
 		vfree(free->arch.rmap);
@@ -1773,8 +1779,8 @@ void kvmppc_core_free_memslot(struct kvm_memory_slot *free,
 	}
 }
 
-int kvmppc_core_create_memslot(struct kvm_memory_slot *slot,
-			       unsigned long npages)
+static int kvmppc_core_create_memslot_hv(struct kvm_memory_slot *slot,
+					 unsigned long npages)
 {
 	slot->arch.rmap = vzalloc(npages * sizeof(*slot->arch.rmap));
 	if (!slot->arch.rmap)
@@ -1784,9 +1790,9 @@ int kvmppc_core_create_memslot(struct kvm_memory_slot *slot,
 	return 0;
 }
 
-int kvmppc_core_prepare_memory_region(struct kvm *kvm,
-				      struct kvm_memory_slot *memslot,
-				      struct kvm_userspace_memory_region *mem)
+static int kvmppc_core_prepare_memory_region_hv(struct kvm *kvm,
+					struct kvm_memory_slot *memslot,
+					struct kvm_userspace_memory_region *mem)
 {
 	unsigned long *phys;
 
@@ -1802,9 +1808,9 @@ int kvmppc_core_prepare_memory_region(struct kvm *kvm,
 	return 0;
 }
 
-void kvmppc_core_commit_memory_region(struct kvm *kvm,
-				      struct kvm_userspace_memory_region *mem,
-				      const struct kvm_memory_slot *old)
+static void kvmppc_core_commit_memory_region_hv(struct kvm *kvm,
+				struct kvm_userspace_memory_region *mem,
+				const struct kvm_memory_slot *old)
 {
 	unsigned long npages = mem->memory_size >> PAGE_SHIFT;
 	struct kvm_memory_slot *memslot;
@@ -1847,6 +1853,11 @@ void kvmppc_update_lpcr(struct kvm *kvm, unsigned long lpcr, unsigned long mask)
 	}
 }
 
+static void kvmppc_mmu_destroy_hv(struct kvm_vcpu *vcpu)
+{
+	return;
+}
+
 static int kvmppc_hv_setup_htab_rma(struct kvm_vcpu *vcpu)
 {
 	int err = 0;
@@ -1994,7 +2005,7 @@ static int kvmppc_hv_setup_htab_rma(struct kvm_vcpu *vcpu)
 	goto out_srcu;
 }
 
-int kvmppc_core_init_vm(struct kvm *kvm)
+static int kvmppc_core_init_vm_hv(struct kvm *kvm)
 {
 	unsigned long lpcr, lpid;
 
@@ -2012,9 +2023,6 @@ int kvmppc_core_init_vm(struct kvm *kvm)
 	 */
 	cpumask_setall(&kvm->arch.need_tlb_flush);
 
-	INIT_LIST_HEAD(&kvm->arch.spapr_tce_tables);
-	INIT_LIST_HEAD(&kvm->arch.rtas_tokens);
-
 	kvm->arch.rma = NULL;
 
 	kvm->arch.host_sdr1 = mfspr(SPRN_SDR1);
@@ -2059,7 +2067,7 @@ static void kvmppc_free_vcores(struct kvm *kvm)
 	kvm->arch.online_vcores = 0;
 }
 
-void kvmppc_core_destroy_vm(struct kvm *kvm)
+static void kvmppc_core_destroy_vm_hv(struct kvm *kvm)
 {
 	uninhibit_secondary_onlining();
 
@@ -2069,39 +2077,127 @@ void kvmppc_core_destroy_vm(struct kvm *kvm)
 		kvm->arch.rma = NULL;
 	}
 
-	kvmppc_rtas_tokens_free(kvm);
-
 	kvmppc_free_hpt(kvm);
-	WARN_ON(!list_empty(&kvm->arch.spapr_tce_tables));
 }
 
-/* These are stubs for now */
-void kvmppc_mmu_pte_pflush(struct kvm_vcpu *vcpu, ulong pa_start, ulong pa_end)
+/* We don't need to emulate any privileged instructions or dcbz */
+static int kvmppc_core_emulate_op_hv(struct kvm_run *run, struct kvm_vcpu *vcpu,
+				     unsigned int inst, int *advance)
 {
+	return EMULATE_FAIL;
 }
 
-/* We don't need to emulate any privileged instructions or dcbz */
-int kvmppc_core_emulate_op(struct kvm_run *run, struct kvm_vcpu *vcpu,
-                           unsigned int inst, int *advance)
+static int kvmppc_core_emulate_mtspr_hv(struct kvm_vcpu *vcpu, int sprn,
+					ulong spr_val)
 {
 	return EMULATE_FAIL;
 }
 
-int kvmppc_core_emulate_mtspr(struct kvm_vcpu *vcpu, int sprn, ulong spr_val)
+static int kvmppc_core_emulate_mfspr_hv(struct kvm_vcpu *vcpu, int sprn,
+					ulong *spr_val)
 {
 	return EMULATE_FAIL;
 }
 
-int kvmppc_core_emulate_mfspr(struct kvm_vcpu *vcpu, int sprn, ulong *spr_val)
+static int kvmppc_core_check_processor_compat_hv(void)
 {
-	return EMULATE_FAIL;
+	if (!cpu_has_feature(CPU_FTR_HVMODE))
+		return -EIO;
+	return 0;
 }
 
-static int kvmppc_book3s_hv_init(void)
+static long kvm_arch_vm_ioctl_hv(struct file *filp,
+				 unsigned int ioctl, unsigned long arg)
+{
+	struct kvm *kvm __maybe_unused = filp->private_data;
+	void __user *argp = (void __user *)arg;
+	long r;
+
+	switch (ioctl) {
+
+	case KVM_ALLOCATE_RMA: {
+		struct kvm_allocate_rma rma;
+		struct kvm *kvm = filp->private_data;
+
+		r = kvm_vm_ioctl_allocate_rma(kvm, &rma);
+		if (r >= 0 && copy_to_user(argp, &rma, sizeof(rma)))
+			r = -EFAULT;
+		break;
+	}
+
+	case KVM_PPC_ALLOCATE_HTAB: {
+		u32 htab_order;
+
+		r = -EFAULT;
+		if (get_user(htab_order, (u32 __user *)argp))
+			break;
+		r = kvmppc_alloc_reset_hpt(kvm, &htab_order);
+		if (r)
+			break;
+		r = -EFAULT;
+		if (put_user(htab_order, (u32 __user *)argp))
+			break;
+		r = 0;
+		break;
+	}
+
+	case KVM_PPC_GET_HTAB_FD: {
+		struct kvm_get_htab_fd ghf;
+
+		r = -EFAULT;
+		if (copy_from_user(&ghf, argp, sizeof(ghf)))
+			break;
+		r = kvm_vm_ioctl_get_htab_fd(kvm, &ghf);
+		break;
+	}
+
+	default:
+		r = -ENOTTY;
+	}
+
+	return r;
+}
+
+static struct kvmppc_ops kvmppc_hv_ops = {
+	.get_sregs = kvm_arch_vcpu_ioctl_get_sregs_hv,
+	.set_sregs = kvm_arch_vcpu_ioctl_set_sregs_hv,
+	.get_one_reg = kvmppc_get_one_reg_hv,
+	.set_one_reg = kvmppc_set_one_reg_hv,
+	.vcpu_load   = kvmppc_core_vcpu_load_hv,
+	.vcpu_put    = kvmppc_core_vcpu_put_hv,
+	.set_msr     = kvmppc_set_msr_hv,
+	.vcpu_run    = kvmppc_vcpu_run_hv,
+	.vcpu_create = kvmppc_core_vcpu_create_hv,
+	.vcpu_free   = kvmppc_core_vcpu_free_hv,
+	.check_requests = kvmppc_core_check_requests_hv,
+	.get_dirty_log  = kvm_vm_ioctl_get_dirty_log_hv,
+	.flush_memslot  = kvmppc_core_flush_memslot_hv,
+	.prepare_memory_region = kvmppc_core_prepare_memory_region_hv,
+	.commit_memory_region  = kvmppc_core_commit_memory_region_hv,
+	.unmap_hva = kvm_unmap_hva_hv,
+	.unmap_hva_range = kvm_unmap_hva_range_hv,
+	.age_hva  = kvm_age_hva_hv,
+	.test_age_hva = kvm_test_age_hva_hv,
+	.set_spte_hva = kvm_set_spte_hva_hv,
+	.mmu_destroy  = kvmppc_mmu_destroy_hv,
+	.free_memslot = kvmppc_core_free_memslot_hv,
+	.create_memslot = kvmppc_core_create_memslot_hv,
+	.init_vm =  kvmppc_core_init_vm_hv,
+	.destroy_vm = kvmppc_core_destroy_vm_hv,
+	.check_processor_compat = kvmppc_core_check_processor_compat_hv,
+	.get_smmu_info = kvm_vm_ioctl_get_smmu_info_hv,
+	.emulate_op = kvmppc_core_emulate_op_hv,
+	.emulate_mtspr = kvmppc_core_emulate_mtspr_hv,
+	.emulate_mfspr = kvmppc_core_emulate_mfspr_hv,
+	.fast_vcpu_kick = kvmppc_fast_vcpu_kick_hv,
+	.arch_vm_ioctl  = kvm_arch_vm_ioctl_hv,
+};
+
+static int kvmppc_book3s_init_hv(void)
 {
 	int r;
 
-	r = kvm_init(NULL, sizeof(struct kvm_vcpu), 0, THIS_MODULE);
+	r = kvm_init(&kvmppc_hv_ops, sizeof(struct kvm_vcpu), 0, THIS_MODULE);
 
 	if (r)
 		return r;
@@ -2111,10 +2207,10 @@ static int kvmppc_book3s_hv_init(void)
 	return r;
 }
 
-static void kvmppc_book3s_hv_exit(void)
+static void kvmppc_book3s_exit_hv(void)
 {
 	kvm_exit();
 }
 
-module_init(kvmppc_book3s_hv_init);
-module_exit(kvmppc_book3s_hv_exit);
+module_init(kvmppc_book3s_init_hv);
+module_exit(kvmppc_book3s_exit_hv);
diff --git a/arch/powerpc/kvm/book3s_interrupts.S b/arch/powerpc/kvm/book3s_interrupts.S
index 38166ab2f19..f4dd041c14e 100644
--- a/arch/powerpc/kvm/book3s_interrupts.S
+++ b/arch/powerpc/kvm/book3s_interrupts.S
@@ -181,7 +181,7 @@ kvm_start_lightweight:
 
 	/* Restore r3 (kvm_run) and r4 (vcpu) */
 	REST_2GPRS(3, r1)
-	bl	FUNC(kvmppc_handle_exit)
+	bl	FUNC(kvmppc_handle_exit_pr)
 
 	/* If RESUME_GUEST, get back in the loop */
 	cmpwi	r3, RESUME_GUEST
diff --git a/arch/powerpc/kvm/book3s_pr.c b/arch/powerpc/kvm/book3s_pr.c
index 6075dbd0b36..05d28cf4a06 100644
--- a/arch/powerpc/kvm/book3s_pr.c
+++ b/arch/powerpc/kvm/book3s_pr.c
@@ -41,6 +41,7 @@
 #include <linux/vmalloc.h>
 #include <linux/highmem.h>
 
+#include "book3s.h"
 #include "trace.h"
 
 /* #define EXIT_DEBUG */
@@ -56,7 +57,7 @@ static int kvmppc_handle_ext(struct kvm_vcpu *vcpu, unsigned int exit_nr,
 #define HW_PAGE_SIZE PAGE_SIZE
 #endif
 
-void kvmppc_core_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
+static void kvmppc_core_vcpu_load_pr(struct kvm_vcpu *vcpu, int cpu)
 {
 #ifdef CONFIG_PPC_BOOK3S_64
 	struct kvmppc_book3s_shadow_vcpu *svcpu = svcpu_get(vcpu);
@@ -70,7 +71,7 @@ void kvmppc_core_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
 #endif
 }
 
-void kvmppc_core_vcpu_put(struct kvm_vcpu *vcpu)
+static void kvmppc_core_vcpu_put_pr(struct kvm_vcpu *vcpu)
 {
 #ifdef CONFIG_PPC_BOOK3S_64
 	struct kvmppc_book3s_shadow_vcpu *svcpu = svcpu_get(vcpu);
@@ -137,7 +138,7 @@ void kvmppc_copy_from_svcpu(struct kvm_vcpu *vcpu,
 	vcpu->arch.last_inst   = svcpu->last_inst;
 }
 
-int kvmppc_core_check_requests(struct kvm_vcpu *vcpu)
+static int kvmppc_core_check_requests_pr(struct kvm_vcpu *vcpu)
 {
 	int r = 1; /* Indicate we want to get back into the guest */
 
@@ -180,7 +181,7 @@ static void do_kvm_unmap_hva(struct kvm *kvm, unsigned long start,
 	}
 }
 
-int kvm_unmap_hva(struct kvm *kvm, unsigned long hva)
+static int kvm_unmap_hva_pr(struct kvm *kvm, unsigned long hva)
 {
 	trace_kvm_unmap_hva(hva);
 
@@ -189,26 +190,27 @@ int kvm_unmap_hva(struct kvm *kvm, unsigned long hva)
 	return 0;
 }
 
-int kvm_unmap_hva_range(struct kvm *kvm, unsigned long start, unsigned long end)
+static int kvm_unmap_hva_range_pr(struct kvm *kvm, unsigned long start,
+				  unsigned long end)
 {
 	do_kvm_unmap_hva(kvm, start, end);
 
 	return 0;
 }
 
-int kvm_age_hva(struct kvm *kvm, unsigned long hva)
+static int kvm_age_hva_pr(struct kvm *kvm, unsigned long hva)
 {
 	/* XXX could be more clever ;) */
 	return 0;
 }
 
-int kvm_test_age_hva(struct kvm *kvm, unsigned long hva)
+static int kvm_test_age_hva_pr(struct kvm *kvm, unsigned long hva)
 {
 	/* XXX could be more clever ;) */
 	return 0;
 }
 
-void kvm_set_spte_hva(struct kvm *kvm, unsigned long hva, pte_t pte)
+static void kvm_set_spte_hva_pr(struct kvm *kvm, unsigned long hva, pte_t pte)
 {
 	/* The page will get remapped properly on its next fault */
 	do_kvm_unmap_hva(kvm, hva, hva + PAGE_SIZE);
@@ -233,7 +235,7 @@ static void kvmppc_recalc_shadow_msr(struct kvm_vcpu *vcpu)
 	vcpu->arch.shadow_msr = smsr;
 }
 
-void kvmppc_set_msr(struct kvm_vcpu *vcpu, u64 msr)
+static void kvmppc_set_msr_pr(struct kvm_vcpu *vcpu, u64 msr)
 {
 	ulong old_msr = vcpu->arch.shared->msr;
 
@@ -293,7 +295,7 @@ void kvmppc_set_msr(struct kvm_vcpu *vcpu, u64 msr)
 		kvmppc_handle_ext(vcpu, BOOK3S_INTERRUPT_FP_UNAVAIL, MSR_FP);
 }
 
-void kvmppc_set_pvr(struct kvm_vcpu *vcpu, u32 pvr)
+void kvmppc_set_pvr_pr(struct kvm_vcpu *vcpu, u32 pvr)
 {
 	u32 host_pvr;
 
@@ -725,8 +727,8 @@ static void kvmppc_handle_lost_ext(struct kvm_vcpu *vcpu)
 	current->thread.regs->msr |= lost_ext;
 }
 
-int kvmppc_handle_exit(struct kvm_run *run, struct kvm_vcpu *vcpu,
-                       unsigned int exit_nr)
+int kvmppc_handle_exit_pr(struct kvm_run *run, struct kvm_vcpu *vcpu,
+			  unsigned int exit_nr)
 {
 	int r = RESUME_HOST;
 	int s;
@@ -1034,8 +1036,8 @@ program_interrupt:
 	return r;
 }
 
-int kvm_arch_vcpu_ioctl_get_sregs(struct kvm_vcpu *vcpu,
-                                  struct kvm_sregs *sregs)
+static int kvm_arch_vcpu_ioctl_get_sregs_pr(struct kvm_vcpu *vcpu,
+					    struct kvm_sregs *sregs)
 {
 	struct kvmppc_vcpu_book3s *vcpu3s = to_book3s(vcpu);
 	int i;
@@ -1061,13 +1063,13 @@ int kvm_arch_vcpu_ioctl_get_sregs(struct kvm_vcpu *vcpu,
 	return 0;
 }
 
-int kvm_arch_vcpu_ioctl_set_sregs(struct kvm_vcpu *vcpu,
-                                  struct kvm_sregs *sregs)
+static int kvm_arch_vcpu_ioctl_set_sregs_pr(struct kvm_vcpu *vcpu,
+					    struct kvm_sregs *sregs)
 {
 	struct kvmppc_vcpu_book3s *vcpu3s = to_book3s(vcpu);
 	int i;
 
-	kvmppc_set_pvr(vcpu, sregs->pvr);
+	kvmppc_set_pvr_pr(vcpu, sregs->pvr);
 
 	vcpu3s->sdr1 = sregs->u.s.sdr1;
 	if (vcpu->arch.hflags & BOOK3S_HFLAG_SLB) {
@@ -1097,7 +1099,8 @@ int kvm_arch_vcpu_ioctl_set_sregs(struct kvm_vcpu *vcpu,
 	return 0;
 }
 
-int kvmppc_get_one_reg(struct kvm_vcpu *vcpu, u64 id, union kvmppc_one_reg *val)
+static int kvmppc_get_one_reg_pr(struct kvm_vcpu *vcpu, u64 id,
+				 union kvmppc_one_reg *val)
 {
 	int r = 0;
 
@@ -1126,7 +1129,8 @@ int kvmppc_get_one_reg(struct kvm_vcpu *vcpu, u64 id, union kvmppc_one_reg *val)
 	return r;
 }
 
-int kvmppc_set_one_reg(struct kvm_vcpu *vcpu, u64 id, union kvmppc_one_reg *val)
+static int kvmppc_set_one_reg_pr(struct kvm_vcpu *vcpu, u64 id,
+				 union kvmppc_one_reg *val)
 {
 	int r = 0;
 
@@ -1156,12 +1160,8 @@ int kvmppc_set_one_reg(struct kvm_vcpu *vcpu, u64 id, union kvmppc_one_reg *val)
 	return r;
 }
 
-int kvmppc_core_check_processor_compat(void)
-{
-	return 0;
-}
-
-struct kvm_vcpu *kvmppc_core_vcpu_create(struct kvm *kvm, unsigned int id)
+static struct kvm_vcpu *kvmppc_core_vcpu_create_pr(struct kvm *kvm,
+						   unsigned int id)
 {
 	struct kvmppc_vcpu_book3s *vcpu_book3s;
 	struct kvm_vcpu *vcpu;
@@ -1208,7 +1208,7 @@ struct kvm_vcpu *kvmppc_core_vcpu_create(struct kvm *kvm, unsigned int id)
 	/* default to book3s_32 (750) */
 	vcpu->arch.pvr = 0x84202;
 #endif
-	kvmppc_set_pvr(vcpu, vcpu->arch.pvr);
+	kvmppc_set_pvr_pr(vcpu, vcpu->arch.pvr);
 	vcpu->arch.slb_nr = 64;
 
 	vcpu->arch.shadow_msr = MSR_USER64;
@@ -1233,7 +1233,7 @@ out:
 	return ERR_PTR(err);
 }
 
-void kvmppc_core_vcpu_free(struct kvm_vcpu *vcpu)
+static void kvmppc_core_vcpu_free_pr(struct kvm_vcpu *vcpu)
 {
 	struct kvmppc_vcpu_book3s *vcpu_book3s = to_book3s(vcpu);
 
@@ -1246,7 +1246,7 @@ void kvmppc_core_vcpu_free(struct kvm_vcpu *vcpu)
 	kmem_cache_free(kvm_vcpu_cache, vcpu);
 }
 
-int kvmppc_vcpu_run(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu)
+static int kvmppc_vcpu_run_pr(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu)
 {
 	int ret;
 	double fpr[32][TS_FPRWIDTH];
@@ -1355,8 +1355,8 @@ out:
 /*
  * Get (and clear) the dirty memory log for a memory slot.
  */
-int kvm_vm_ioctl_get_dirty_log(struct kvm *kvm,
-				      struct kvm_dirty_log *log)
+static int kvm_vm_ioctl_get_dirty_log_pr(struct kvm *kvm,
+					 struct kvm_dirty_log *log)
 {
 	struct kvm_memory_slot *memslot;
 	struct kvm_vcpu *vcpu;
@@ -1391,8 +1391,42 @@ out:
 	return r;
 }
 
+static void kvmppc_core_flush_memslot_pr(struct kvm *kvm,
+					 struct kvm_memory_slot *memslot)
+{
+	return;
+}
+
+static int kvmppc_core_prepare_memory_region_pr(struct kvm *kvm,
+					struct kvm_memory_slot *memslot,
+					struct kvm_userspace_memory_region *mem)
+{
+	return 0;
+}
+
+static void kvmppc_core_commit_memory_region_pr(struct kvm *kvm,
+				struct kvm_userspace_memory_region *mem,
+				const struct kvm_memory_slot *old)
+{
+	return;
+}
+
+static void kvmppc_core_free_memslot_pr(struct kvm_memory_slot *free,
+					struct kvm_memory_slot *dont)
+{
+	return;
+}
+
+static int kvmppc_core_create_memslot_pr(struct kvm_memory_slot *slot,
+					 unsigned long npages)
+{
+	return 0;
+}
+
+
 #ifdef CONFIG_PPC64
-int kvm_vm_ioctl_get_smmu_info(struct kvm *kvm, struct kvm_ppc_smmu_info *info)
+static int kvm_vm_ioctl_get_smmu_info_pr(struct kvm *kvm,
+					 struct kvm_ppc_smmu_info *info)
 {
 	long int i;
 	struct kvm_vcpu *vcpu;
@@ -1436,45 +1470,20 @@ int kvm_vm_ioctl_get_smmu_info(struct kvm *kvm, struct kvm_ppc_smmu_info *info)
 
 	return 0;
 }
-#endif /* CONFIG_PPC64 */
-
-void kvmppc_core_free_memslot(struct kvm_memory_slot *free,
-			      struct kvm_memory_slot *dont)
-{
-}
-
-int kvmppc_core_create_memslot(struct kvm_memory_slot *slot,
-			       unsigned long npages)
-{
-	return 0;
-}
-
-int kvmppc_core_prepare_memory_region(struct kvm *kvm,
-				      struct kvm_memory_slot *memslot,
-				      struct kvm_userspace_memory_region *mem)
-{
-	return 0;
-}
-
-void kvmppc_core_commit_memory_region(struct kvm *kvm,
-				struct kvm_userspace_memory_region *mem,
-				const struct kvm_memory_slot *old)
-{
-}
-
-void kvmppc_core_flush_memslot(struct kvm *kvm, struct kvm_memory_slot *memslot)
+#else
+static int kvm_vm_ioctl_get_smmu_info_pr(struct kvm *kvm,
+					 struct kvm_ppc_smmu_info *info)
 {
+	/* We should not get called */
+	BUG();
 }
+#endif /* CONFIG_PPC64 */
 
 static unsigned int kvm_global_user_count = 0;
 static DEFINE_SPINLOCK(kvm_global_user_count_lock);
 
-int kvmppc_core_init_vm(struct kvm *kvm)
+static int kvmppc_core_init_vm_pr(struct kvm *kvm)
 {
-#ifdef CONFIG_PPC64
-	INIT_LIST_HEAD(&kvm->arch.spapr_tce_tables);
-	INIT_LIST_HEAD(&kvm->arch.rtas_tokens);
-#endif
 	mutex_init(&kvm->arch.hpt_mutex);
 
 	if (firmware_has_feature(FW_FEATURE_SET_MODE)) {
@@ -1486,7 +1495,7 @@ int kvmppc_core_init_vm(struct kvm *kvm)
 	return 0;
 }
 
-void kvmppc_core_destroy_vm(struct kvm *kvm)
+static void kvmppc_core_destroy_vm_pr(struct kvm *kvm)
 {
 #ifdef CONFIG_PPC64
 	WARN_ON(!list_empty(&kvm->arch.spapr_tce_tables));
@@ -1501,11 +1510,58 @@ void kvmppc_core_destroy_vm(struct kvm *kvm)
 	}
 }
 
-static int kvmppc_book3s_init(void)
+static int kvmppc_core_check_processor_compat_pr(void)
+{
+	/* we are always compatible */
+	return 0;
+}
+
+static long kvm_arch_vm_ioctl_pr(struct file *filp,
+				 unsigned int ioctl, unsigned long arg)
+{
+	return -ENOTTY;
+}
+
+static struct kvmppc_ops kvmppc_pr_ops = {
+	.get_sregs = kvm_arch_vcpu_ioctl_get_sregs_pr,
+	.set_sregs = kvm_arch_vcpu_ioctl_set_sregs_pr,
+	.get_one_reg = kvmppc_get_one_reg_pr,
+	.set_one_reg = kvmppc_set_one_reg_pr,
+	.vcpu_load   = kvmppc_core_vcpu_load_pr,
+	.vcpu_put    = kvmppc_core_vcpu_put_pr,
+	.set_msr     = kvmppc_set_msr_pr,
+	.vcpu_run    = kvmppc_vcpu_run_pr,
+	.vcpu_create = kvmppc_core_vcpu_create_pr,
+	.vcpu_free   = kvmppc_core_vcpu_free_pr,
+	.check_requests = kvmppc_core_check_requests_pr,
+	.get_dirty_log = kvm_vm_ioctl_get_dirty_log_pr,
+	.flush_memslot = kvmppc_core_flush_memslot_pr,
+	.prepare_memory_region = kvmppc_core_prepare_memory_region_pr,
+	.commit_memory_region = kvmppc_core_commit_memory_region_pr,
+	.unmap_hva = kvm_unmap_hva_pr,
+	.unmap_hva_range = kvm_unmap_hva_range_pr,
+	.age_hva  = kvm_age_hva_pr,
+	.test_age_hva = kvm_test_age_hva_pr,
+	.set_spte_hva = kvm_set_spte_hva_pr,
+	.mmu_destroy  = kvmppc_mmu_destroy_pr,
+	.free_memslot = kvmppc_core_free_memslot_pr,
+	.create_memslot = kvmppc_core_create_memslot_pr,
+	.init_vm = kvmppc_core_init_vm_pr,
+	.destroy_vm = kvmppc_core_destroy_vm_pr,
+	.check_processor_compat = kvmppc_core_check_processor_compat_pr,
+	.get_smmu_info = kvm_vm_ioctl_get_smmu_info_pr,
+	.emulate_op = kvmppc_core_emulate_op_pr,
+	.emulate_mtspr = kvmppc_core_emulate_mtspr_pr,
+	.emulate_mfspr = kvmppc_core_emulate_mfspr_pr,
+	.fast_vcpu_kick = kvm_vcpu_kick,
+	.arch_vm_ioctl  = kvm_arch_vm_ioctl_pr,
+};
+
+static int kvmppc_book3s_init_pr(void)
 {
 	int r;
 
-	r = kvm_init(NULL, sizeof(struct kvm_vcpu), 0, THIS_MODULE);
+	r = kvm_init(&kvmppc_pr_ops, sizeof(struct kvm_vcpu), 0, THIS_MODULE);
 
 	if (r)
 		return r;
@@ -1515,11 +1571,11 @@ static int kvmppc_book3s_init(void)
 	return r;
 }
 
-static void kvmppc_book3s_exit(void)
+static void kvmppc_book3s_exit_pr(void)
 {
 	kvmppc_mmu_hpte_sysexit();
 	kvm_exit();
 }
 
-module_init(kvmppc_book3s_init);
-module_exit(kvmppc_book3s_exit);
+module_init(kvmppc_book3s_init_pr);
+module_exit(kvmppc_book3s_exit_pr);
diff --git a/arch/powerpc/kvm/book3s_xics.c b/arch/powerpc/kvm/book3s_xics.c
index a3a5cb8ee7e..51ed1ea440e 100644
--- a/arch/powerpc/kvm/book3s_xics.c
+++ b/arch/powerpc/kvm/book3s_xics.c
@@ -1250,13 +1250,13 @@ static int kvmppc_xics_create(struct kvm_device *dev, u32 type)
 
 	xics_debugfs_init(xics);
 
-#ifdef CONFIG_KVM_BOOK3S_64_HV
+#ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE
 	if (cpu_has_feature(CPU_FTR_ARCH_206)) {
 		/* Enable real mode support */
 		xics->real_mode = ENABLE_REALMODE;
 		xics->real_mode_dbg = DEBUG_REALMODE;
 	}
-#endif /* CONFIG_KVM_BOOK3S_64_HV */
+#endif /* CONFIG_KVM_BOOK3S_HV_POSSIBLE */
 
 	return 0;
 }
diff --git a/arch/powerpc/kvm/booke.c b/arch/powerpc/kvm/booke.c
index 8b6a790c056..e5f8ba793c3 100644
--- a/arch/powerpc/kvm/booke.c
+++ b/arch/powerpc/kvm/booke.c
@@ -1415,7 +1415,7 @@ static int set_sregs_arch206(struct kvm_vcpu *vcpu,
 	return 0;
 }
 
-void kvmppc_get_sregs_ivor(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs)
+int kvmppc_get_sregs_ivor(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs)
 {
 	sregs->u.e.features |= KVM_SREGS_E_IVOR;
 
@@ -1435,6 +1435,7 @@ void kvmppc_get_sregs_ivor(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs)
 	sregs->u.e.ivor_low[13] = vcpu->arch.ivor[BOOKE_IRQPRIO_DTLB_MISS];
 	sregs->u.e.ivor_low[14] = vcpu->arch.ivor[BOOKE_IRQPRIO_ITLB_MISS];
 	sregs->u.e.ivor_low[15] = vcpu->arch.ivor[BOOKE_IRQPRIO_DEBUG];
+	return 0;
 }
 
 int kvmppc_set_sregs_ivor(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs)
@@ -1469,8 +1470,7 @@ int kvm_arch_vcpu_ioctl_get_sregs(struct kvm_vcpu *vcpu,
 
 	get_sregs_base(vcpu, sregs);
 	get_sregs_arch206(vcpu, sregs);
-	kvmppc_core_get_sregs(vcpu, sregs);
-	return 0;
+	return kvmppc_ops->get_sregs(vcpu, sregs);
 }
 
 int kvm_arch_vcpu_ioctl_set_sregs(struct kvm_vcpu *vcpu,
@@ -1489,7 +1489,7 @@ int kvm_arch_vcpu_ioctl_set_sregs(struct kvm_vcpu *vcpu,
 	if (ret < 0)
 		return ret;
 
-	return kvmppc_core_set_sregs(vcpu, sregs);
+	return kvmppc_ops->set_sregs(vcpu, sregs);
 }
 
 int kvm_vcpu_ioctl_get_one_reg(struct kvm_vcpu *vcpu, struct kvm_one_reg *reg)
@@ -1546,7 +1546,7 @@ int kvm_vcpu_ioctl_get_one_reg(struct kvm_vcpu *vcpu, struct kvm_one_reg *reg)
 		val = get_reg_val(reg->id, vcpu->arch.vrsave);
 		break;
 	default:
-		r = kvmppc_get_one_reg(vcpu, reg->id, &val);
+		r = kvmppc_ops->get_one_reg(vcpu, reg->id, &val);
 		break;
 	}
 
@@ -1629,7 +1629,7 @@ int kvm_vcpu_ioctl_set_one_reg(struct kvm_vcpu *vcpu, struct kvm_one_reg *reg)
 		vcpu->arch.vrsave = set_reg_val(reg->id, val);
 		break;
 	default:
-		r = kvmppc_set_one_reg(vcpu, reg->id, &val);
+		r = kvmppc_ops->set_one_reg(vcpu, reg->id, &val);
 		break;
 	}
 
@@ -1907,6 +1907,41 @@ void kvmppc_booke_vcpu_put(struct kvm_vcpu *vcpu)
 	kvmppc_clear_dbsr();
 }
 
+void kvmppc_mmu_destroy(struct kvm_vcpu *vcpu)
+{
+	kvmppc_ops->mmu_destroy(vcpu);
+}
+
+int kvmppc_core_init_vm(struct kvm *kvm)
+{
+	return kvmppc_ops->init_vm(kvm);
+}
+
+struct kvm_vcpu *kvmppc_core_vcpu_create(struct kvm *kvm, unsigned int id)
+{
+	return kvmppc_ops->vcpu_create(kvm, id);
+}
+
+void kvmppc_core_vcpu_free(struct kvm_vcpu *vcpu)
+{
+	kvmppc_ops->vcpu_free(vcpu);
+}
+
+void kvmppc_core_destroy_vm(struct kvm *kvm)
+{
+	kvmppc_ops->destroy_vm(kvm);
+}
+
+void kvmppc_core_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
+{
+	kvmppc_ops->vcpu_load(vcpu, cpu);
+}
+
+void kvmppc_core_vcpu_put(struct kvm_vcpu *vcpu)
+{
+	kvmppc_ops->vcpu_put(vcpu);
+}
+
 int __init kvmppc_booke_init(void)
 {
 #ifndef CONFIG_KVM_BOOKE_HV
diff --git a/arch/powerpc/kvm/booke.h b/arch/powerpc/kvm/booke.h
index a1ff67d0402..09bfd9bc7cf 100644
--- a/arch/powerpc/kvm/booke.h
+++ b/arch/powerpc/kvm/booke.h
@@ -99,6 +99,30 @@ enum int_class {
 
 void kvmppc_set_pending_interrupt(struct kvm_vcpu *vcpu, enum int_class type);
 
+extern void kvmppc_mmu_destroy_44x(struct kvm_vcpu *vcpu);
+extern int kvmppc_core_emulate_op_44x(struct kvm_run *run, struct kvm_vcpu *vcpu,
+				      unsigned int inst, int *advance);
+extern int kvmppc_core_emulate_mtspr_44x(struct kvm_vcpu *vcpu, int sprn,
+					 ulong spr_val);
+extern int kvmppc_core_emulate_mfspr_44x(struct kvm_vcpu *vcpu, int sprn,
+					 ulong *spr_val);
+extern void kvmppc_mmu_destroy_e500(struct kvm_vcpu *vcpu);
+extern int kvmppc_core_emulate_op_e500(struct kvm_run *run,
+				       struct kvm_vcpu *vcpu,
+				       unsigned int inst, int *advance);
+extern int kvmppc_core_emulate_mtspr_e500(struct kvm_vcpu *vcpu, int sprn,
+					  ulong spr_val);
+extern int kvmppc_core_emulate_mfspr_e500(struct kvm_vcpu *vcpu, int sprn,
+					  ulong *spr_val);
+extern void kvmppc_mmu_destroy_e500(struct kvm_vcpu *vcpu);
+extern int kvmppc_core_emulate_op_e500(struct kvm_run *run,
+				       struct kvm_vcpu *vcpu,
+				       unsigned int inst, int *advance);
+extern int kvmppc_core_emulate_mtspr_e500(struct kvm_vcpu *vcpu, int sprn,
+					  ulong spr_val);
+extern int kvmppc_core_emulate_mfspr_e500(struct kvm_vcpu *vcpu, int sprn,
+					  ulong *spr_val);
+
 /*
  * Load up guest vcpu FP state if it's needed.
  * It also set the MSR_FP in thread so that host know
diff --git a/arch/powerpc/kvm/e500.c b/arch/powerpc/kvm/e500.c
index ce6b73c2961..d225d5ebddc 100644
--- a/arch/powerpc/kvm/e500.c
+++ b/arch/powerpc/kvm/e500.c
@@ -305,7 +305,7 @@ void kvmppc_core_load_guest_debugstate(struct kvm_vcpu *vcpu)
 {
 }
 
-void kvmppc_core_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
+static void kvmppc_core_vcpu_load_e500(struct kvm_vcpu *vcpu, int cpu)
 {
 	kvmppc_booke_vcpu_load(vcpu, cpu);
 
@@ -313,7 +313,7 @@ void kvmppc_core_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
 	kvmppc_e500_recalc_shadow_pid(to_e500(vcpu));
 }
 
-void kvmppc_core_vcpu_put(struct kvm_vcpu *vcpu)
+static void kvmppc_core_vcpu_put_e500(struct kvm_vcpu *vcpu)
 {
 #ifdef CONFIG_SPE
 	if (vcpu->arch.shadow_msr & MSR_SPE)
@@ -367,7 +367,8 @@ int kvmppc_core_vcpu_setup(struct kvm_vcpu *vcpu)
 	return 0;
 }
 
-void kvmppc_core_get_sregs(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs)
+static int kvmppc_core_get_sregs_e500(struct kvm_vcpu *vcpu,
+				      struct kvm_sregs *sregs)
 {
 	struct kvmppc_vcpu_e500 *vcpu_e500 = to_e500(vcpu);
 
@@ -388,9 +389,11 @@ void kvmppc_core_get_sregs(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs)
 
 	kvmppc_get_sregs_ivor(vcpu, sregs);
 	kvmppc_get_sregs_e500_tlb(vcpu, sregs);
+	return 0;
 }
 
-int kvmppc_core_set_sregs(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs)
+static int kvmppc_core_set_sregs_e500(struct kvm_vcpu *vcpu,
+				      struct kvm_sregs *sregs)
 {
 	struct kvmppc_vcpu_e500 *vcpu_e500 = to_e500(vcpu);
 	int ret;
@@ -425,21 +428,22 @@ int kvmppc_core_set_sregs(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs)
 	return kvmppc_set_sregs_ivor(vcpu, sregs);
 }
 
-int kvmppc_get_one_reg(struct kvm_vcpu *vcpu, u64 id,
-			union kvmppc_one_reg *val)
+static int kvmppc_get_one_reg_e500(struct kvm_vcpu *vcpu, u64 id,
+				   union kvmppc_one_reg *val)
 {
 	int r = kvmppc_get_one_reg_e500_tlb(vcpu, id, val);
 	return r;
 }
 
-int kvmppc_set_one_reg(struct kvm_vcpu *vcpu, u64 id,
-		       union kvmppc_one_reg *val)
+static int kvmppc_set_one_reg_e500(struct kvm_vcpu *vcpu, u64 id,
+				   union kvmppc_one_reg *val)
 {
 	int r = kvmppc_get_one_reg_e500_tlb(vcpu, id, val);
 	return r;
 }
 
-struct kvm_vcpu *kvmppc_core_vcpu_create(struct kvm *kvm, unsigned int id)
+static struct kvm_vcpu *kvmppc_core_vcpu_create_e500(struct kvm *kvm,
+						     unsigned int id)
 {
 	struct kvmppc_vcpu_e500 *vcpu_e500;
 	struct kvm_vcpu *vcpu;
@@ -481,7 +485,7 @@ out:
 	return ERR_PTR(err);
 }
 
-void kvmppc_core_vcpu_free(struct kvm_vcpu *vcpu)
+static void kvmppc_core_vcpu_free_e500(struct kvm_vcpu *vcpu)
 {
 	struct kvmppc_vcpu_e500 *vcpu_e500 = to_e500(vcpu);
 
@@ -492,15 +496,32 @@ void kvmppc_core_vcpu_free(struct kvm_vcpu *vcpu)
 	kmem_cache_free(kvm_vcpu_cache, vcpu_e500);
 }
 
-int kvmppc_core_init_vm(struct kvm *kvm)
+static int kvmppc_core_init_vm_e500(struct kvm *kvm)
 {
 	return 0;
 }
 
-void kvmppc_core_destroy_vm(struct kvm *kvm)
+static void kvmppc_core_destroy_vm_e500(struct kvm *kvm)
 {
 }
 
+static struct kvmppc_ops kvm_ops_e500 = {
+	.get_sregs = kvmppc_core_get_sregs_e500,
+	.set_sregs = kvmppc_core_set_sregs_e500,
+	.get_one_reg = kvmppc_get_one_reg_e500,
+	.set_one_reg = kvmppc_set_one_reg_e500,
+	.vcpu_load   = kvmppc_core_vcpu_load_e500,
+	.vcpu_put    = kvmppc_core_vcpu_put_e500,
+	.vcpu_create = kvmppc_core_vcpu_create_e500,
+	.vcpu_free   = kvmppc_core_vcpu_free_e500,
+	.mmu_destroy  = kvmppc_mmu_destroy_e500,
+	.init_vm = kvmppc_core_init_vm_e500,
+	.destroy_vm = kvmppc_core_destroy_vm_e500,
+	.emulate_op = kvmppc_core_emulate_op_e500,
+	.emulate_mtspr = kvmppc_core_emulate_mtspr_e500,
+	.emulate_mfspr = kvmppc_core_emulate_mfspr_e500,
+};
+
 static int __init kvmppc_e500_init(void)
 {
 	int r, i;
@@ -512,11 +533,11 @@ static int __init kvmppc_e500_init(void)
 
 	r = kvmppc_core_check_processor_compat();
 	if (r)
-		return r;
+		goto err_out;
 
 	r = kvmppc_booke_init();
 	if (r)
-		return r;
+		goto err_out;
 
 	/* copy extra E500 exception handlers */
 	ivor[0] = mfspr(SPRN_IVOR32);
@@ -534,7 +555,9 @@ static int __init kvmppc_e500_init(void)
 	flush_icache_range(kvmppc_booke_handlers, kvmppc_booke_handlers +
 			   ivor[max_ivor] + handler_len);
 
-	return kvm_init(NULL, sizeof(struct kvmppc_vcpu_e500), 0, THIS_MODULE);
+	r = kvm_init(&kvm_ops_e500, sizeof(struct kvmppc_vcpu_e500), 0, THIS_MODULE);
+err_out:
+	return r;
 }
 
 static void __exit kvmppc_e500_exit(void)
diff --git a/arch/powerpc/kvm/e500_emulate.c b/arch/powerpc/kvm/e500_emulate.c
index 6163a0318d2..89b7f821f6c 100644
--- a/arch/powerpc/kvm/e500_emulate.c
+++ b/arch/powerpc/kvm/e500_emulate.c
@@ -103,8 +103,8 @@ static int kvmppc_e500_emul_ehpriv(struct kvm_run *run, struct kvm_vcpu *vcpu,
 	return emulated;
 }
 
-int kvmppc_core_emulate_op(struct kvm_run *run, struct kvm_vcpu *vcpu,
-                           unsigned int inst, int *advance)
+int kvmppc_core_emulate_op_e500(struct kvm_run *run, struct kvm_vcpu *vcpu,
+				unsigned int inst, int *advance)
 {
 	int emulated = EMULATE_DONE;
 	int ra = get_ra(inst);
@@ -172,7 +172,7 @@ 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, ulong spr_val)
+int kvmppc_core_emulate_mtspr_e500(struct kvm_vcpu *vcpu, int sprn, ulong spr_val)
 {
 	struct kvmppc_vcpu_e500 *vcpu_e500 = to_e500(vcpu);
 	int emulated = EMULATE_DONE;
@@ -263,7 +263,7 @@ int kvmppc_core_emulate_mtspr(struct kvm_vcpu *vcpu, int sprn, ulong spr_val)
 	return emulated;
 }
 
-int kvmppc_core_emulate_mfspr(struct kvm_vcpu *vcpu, int sprn, ulong *spr_val)
+int kvmppc_core_emulate_mfspr_e500(struct kvm_vcpu *vcpu, int sprn, ulong *spr_val)
 {
 	struct kvmppc_vcpu_e500 *vcpu_e500 = to_e500(vcpu);
 	int emulated = EMULATE_DONE;
diff --git a/arch/powerpc/kvm/e500_mmu.c b/arch/powerpc/kvm/e500_mmu.c
index 6d6f153b6c1..d25bb75aec9 100644
--- a/arch/powerpc/kvm/e500_mmu.c
+++ b/arch/powerpc/kvm/e500_mmu.c
@@ -536,7 +536,7 @@ gpa_t kvmppc_mmu_xlate(struct kvm_vcpu *vcpu, unsigned int index,
 	return get_tlb_raddr(gtlbe) | (eaddr & pgmask);
 }
 
-void kvmppc_mmu_destroy(struct kvm_vcpu *vcpu)
+void kvmppc_mmu_destroy_e500(struct kvm_vcpu *vcpu)
 {
 }
 
diff --git a/arch/powerpc/kvm/e500mc.c b/arch/powerpc/kvm/e500mc.c
index 19c8379575f..db6a383401c 100644
--- a/arch/powerpc/kvm/e500mc.c
+++ b/arch/powerpc/kvm/e500mc.c
@@ -110,7 +110,7 @@ void kvmppc_mmu_msr_notify(struct kvm_vcpu *vcpu, u32 old_msr)
 
 static DEFINE_PER_CPU(struct kvm_vcpu *, last_vcpu_on_cpu);
 
-void kvmppc_core_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
+static void kvmppc_core_vcpu_load_e500mc(struct kvm_vcpu *vcpu, int cpu)
 {
 	struct kvmppc_vcpu_e500 *vcpu_e500 = to_e500(vcpu);
 
@@ -147,7 +147,7 @@ void kvmppc_core_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
 	kvmppc_load_guest_fp(vcpu);
 }
 
-void kvmppc_core_vcpu_put(struct kvm_vcpu *vcpu)
+static void kvmppc_core_vcpu_put_e500mc(struct kvm_vcpu *vcpu)
 {
 	vcpu->arch.eplc = mfspr(SPRN_EPLC);
 	vcpu->arch.epsc = mfspr(SPRN_EPSC);
@@ -204,7 +204,8 @@ int kvmppc_core_vcpu_setup(struct kvm_vcpu *vcpu)
 	return 0;
 }
 
-void kvmppc_core_get_sregs(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs)
+static int kvmppc_core_get_sregs_e500mc(struct kvm_vcpu *vcpu,
+					struct kvm_sregs *sregs)
 {
 	struct kvmppc_vcpu_e500 *vcpu_e500 = to_e500(vcpu);
 
@@ -224,10 +225,11 @@ void kvmppc_core_get_sregs(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs)
 	sregs->u.e.ivor_high[4] = vcpu->arch.ivor[BOOKE_IRQPRIO_DBELL];
 	sregs->u.e.ivor_high[5] = vcpu->arch.ivor[BOOKE_IRQPRIO_DBELL_CRIT];
 
-	kvmppc_get_sregs_ivor(vcpu, sregs);
+	return kvmppc_get_sregs_ivor(vcpu, sregs);
 }
 
-int kvmppc_core_set_sregs(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs)
+static int kvmppc_core_set_sregs_e500mc(struct kvm_vcpu *vcpu,
+					struct kvm_sregs *sregs)
 {
 	struct kvmppc_vcpu_e500 *vcpu_e500 = to_e500(vcpu);
 	int ret;
@@ -260,21 +262,22 @@ int kvmppc_core_set_sregs(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs)
 	return kvmppc_set_sregs_ivor(vcpu, sregs);
 }
 
-int kvmppc_get_one_reg(struct kvm_vcpu *vcpu, u64 id,
-			union kvmppc_one_reg *val)
+static int kvmppc_get_one_reg_e500mc(struct kvm_vcpu *vcpu, u64 id,
+			      union kvmppc_one_reg *val)
 {
 	int r = kvmppc_get_one_reg_e500_tlb(vcpu, id, val);
 	return r;
 }
 
-int kvmppc_set_one_reg(struct kvm_vcpu *vcpu, u64 id,
-		       union kvmppc_one_reg *val)
+static int kvmppc_set_one_reg_e500mc(struct kvm_vcpu *vcpu, u64 id,
+			      union kvmppc_one_reg *val)
 {
 	int r = kvmppc_set_one_reg_e500_tlb(vcpu, id, val);
 	return r;
 }
 
-struct kvm_vcpu *kvmppc_core_vcpu_create(struct kvm *kvm, unsigned int id)
+static struct kvm_vcpu *kvmppc_core_vcpu_create_e500mc(struct kvm *kvm,
+						       unsigned int id)
 {
 	struct kvmppc_vcpu_e500 *vcpu_e500;
 	struct kvm_vcpu *vcpu;
@@ -315,7 +318,7 @@ out:
 	return ERR_PTR(err);
 }
 
-void kvmppc_core_vcpu_free(struct kvm_vcpu *vcpu)
+static void kvmppc_core_vcpu_free_e500mc(struct kvm_vcpu *vcpu)
 {
 	struct kvmppc_vcpu_e500 *vcpu_e500 = to_e500(vcpu);
 
@@ -325,7 +328,7 @@ void kvmppc_core_vcpu_free(struct kvm_vcpu *vcpu)
 	kmem_cache_free(kvm_vcpu_cache, vcpu_e500);
 }
 
-int kvmppc_core_init_vm(struct kvm *kvm)
+static int kvmppc_core_init_vm_e500mc(struct kvm *kvm)
 {
 	int lpid;
 
@@ -337,23 +340,44 @@ int kvmppc_core_init_vm(struct kvm *kvm)
 	return 0;
 }
 
-void kvmppc_core_destroy_vm(struct kvm *kvm)
+static void kvmppc_core_destroy_vm_e500mc(struct kvm *kvm)
 {
 	kvmppc_free_lpid(kvm->arch.lpid);
 }
 
+static struct kvmppc_ops kvm_ops_e500mc = {
+	.get_sregs = kvmppc_core_get_sregs_e500mc,
+	.set_sregs = kvmppc_core_set_sregs_e500mc,
+	.get_one_reg = kvmppc_get_one_reg_e500mc,
+	.set_one_reg = kvmppc_set_one_reg_e500mc,
+	.vcpu_load   = kvmppc_core_vcpu_load_e500mc,
+	.vcpu_put    = kvmppc_core_vcpu_put_e500mc,
+	.vcpu_create = kvmppc_core_vcpu_create_e500mc,
+	.vcpu_free   = kvmppc_core_vcpu_free_e500mc,
+	.mmu_destroy  = kvmppc_mmu_destroy_e500,
+	.init_vm = kvmppc_core_init_vm_e500mc,
+	.destroy_vm = kvmppc_core_destroy_vm_e500mc,
+	.emulate_op = kvmppc_core_emulate_op_e500,
+	.emulate_mtspr = kvmppc_core_emulate_mtspr_e500,
+	.emulate_mfspr = kvmppc_core_emulate_mfspr_e500,
+};
+
 static int __init kvmppc_e500mc_init(void)
 {
 	int r;
 
 	r = kvmppc_booke_init();
 	if (r)
-		return r;
+		goto err_out;
 
 	kvmppc_init_lpid(64);
 	kvmppc_claim_lpid(0); /* host */
 
-	return kvm_init(NULL, sizeof(struct kvmppc_vcpu_e500), 0, THIS_MODULE);
+	r = kvm_init(&kvm_ops_e500mc, sizeof(struct kvmppc_vcpu_e500), 0, THIS_MODULE);
+	if (r)
+		goto err_out;
+err_out:
+	return r;
 }
 
 static void __exit kvmppc_e500mc_exit(void)
diff --git a/arch/powerpc/kvm/emulate.c b/arch/powerpc/kvm/emulate.c
index 751cd45f65a..81762eb7957 100644
--- a/arch/powerpc/kvm/emulate.c
+++ b/arch/powerpc/kvm/emulate.c
@@ -130,7 +130,7 @@ static int kvmppc_emulate_mtspr(struct kvm_vcpu *vcpu, int sprn, int rs)
 	case SPRN_PIR: break;
 
 	default:
-		emulated = kvmppc_core_emulate_mtspr(vcpu, sprn,
+		emulated = kvmppc_ops->emulate_mtspr(vcpu, sprn,
 						     spr_val);
 		if (emulated == EMULATE_FAIL)
 			printk(KERN_INFO "mtspr: unknown spr "
@@ -191,7 +191,7 @@ static int kvmppc_emulate_mfspr(struct kvm_vcpu *vcpu, int sprn, int rt)
 		spr_val = kvmppc_get_dec(vcpu, get_tb());
 		break;
 	default:
-		emulated = kvmppc_core_emulate_mfspr(vcpu, sprn,
+		emulated = kvmppc_ops->emulate_mfspr(vcpu, sprn,
 						     &spr_val);
 		if (unlikely(emulated == EMULATE_FAIL)) {
 			printk(KERN_INFO "mfspr: unknown spr "
@@ -464,7 +464,7 @@ int kvmppc_emulate_instruction(struct kvm_run *run, struct kvm_vcpu *vcpu)
 	}
 
 	if (emulated == EMULATE_FAIL) {
-		emulated = kvmppc_core_emulate_op(run, vcpu, inst, &advance);
+		emulated = kvmppc_ops->emulate_op(run, vcpu, inst, &advance);
 		if (emulated == EMULATE_AGAIN) {
 			advance = 0;
 		} else if (emulated == EMULATE_FAIL) {
diff --git a/arch/powerpc/kvm/powerpc.c b/arch/powerpc/kvm/powerpc.c
index 07c0106fab7..69b930550d2 100644
--- a/arch/powerpc/kvm/powerpc.c
+++ b/arch/powerpc/kvm/powerpc.c
@@ -39,6 +39,8 @@
 #define CREATE_TRACE_POINTS
 #include "trace.h"
 
+struct kvmppc_ops *kvmppc_ops;
+
 int kvm_arch_vcpu_runnable(struct kvm_vcpu *v)
 {
 	return !!(v->arch.pending_exceptions) ||
@@ -1024,52 +1026,11 @@ 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_allocate_rma rma;
-		struct kvm *kvm = filp->private_data;
-
-		r = kvm_vm_ioctl_allocate_rma(kvm, &rma);
-		if (r >= 0 && copy_to_user(argp, &rma, sizeof(rma)))
-			r = -EFAULT;
-		break;
-	}
-
-	case KVM_PPC_ALLOCATE_HTAB: {
-		u32 htab_order;
-
-		r = -EFAULT;
-		if (get_user(htab_order, (u32 __user *)argp))
-			break;
-		r = kvmppc_alloc_reset_hpt(kvm, &htab_order);
-		if (r)
-			break;
-		r = -EFAULT;
-		if (put_user(htab_order, (u32 __user *)argp))
-			break;
-		r = 0;
-		break;
-	}
-
-	case KVM_PPC_GET_HTAB_FD: {
-		struct kvm_get_htab_fd ghf;
-
-		r = -EFAULT;
-		if (copy_from_user(&ghf, argp, sizeof(ghf)))
-			break;
-		r = kvm_vm_ioctl_get_htab_fd(kvm, &ghf);
-		break;
-	}
-#endif /* CONFIG_KVM_BOOK3S_64_HV */
-
-#ifdef CONFIG_PPC_BOOK3S_64
 	case KVM_PPC_GET_SMMU_INFO: {
 		struct kvm_ppc_smmu_info info;
 
 		memset(&info, 0, sizeof(info));
-		r = kvm_vm_ioctl_get_smmu_info(kvm, &info);
+		r = kvmppc_ops->get_smmu_info(kvm, &info);
 		if (r >= 0 && copy_to_user(argp, &info, sizeof(info)))
 			r = -EFAULT;
 		break;
@@ -1080,11 +1041,14 @@ long kvm_arch_vm_ioctl(struct file *filp,
 		r = kvm_vm_ioctl_rtas_define_token(kvm, argp);
 		break;
 	}
-#endif /* CONFIG_PPC_BOOK3S_64 */
+	default:
+		r = kvmppc_ops->arch_vm_ioctl(filp, ioctl, arg);
+
+#else /* CONFIG_PPC_BOOK3S_64 */
 	default:
 		r = -ENOTTY;
+#endif
 	}
-
 out:
 	return r;
 }
@@ -1125,9 +1089,15 @@ void kvmppc_init_lpid(unsigned long nr_lpids_param)
 
 int kvm_arch_init(void *opaque)
 {
+	if (kvmppc_ops) {
+		printk(KERN_ERR "kvm: already loaded the other module\n");
+		return -EEXIST;
+	}
+	kvmppc_ops = (struct kvmppc_ops *)opaque;
 	return 0;
 }
 
 void kvm_arch_exit(void)
 {
+	kvmppc_ops = NULL;
 }
-- 
cgit v1.2.3-70-g09d2


From dd96b2c2dc408faf2213bc0a05897c1359f7969c Mon Sep 17 00:00:00 2001
From: "Aneesh Kumar K.V" <aneesh.kumar@linux.vnet.ibm.com>
Date: Mon, 7 Oct 2013 22:17:55 +0530
Subject: kvm: powerpc: book3s: Cleanup interrupt handling code

With this patch if HV is included, interrupts come in to the HV version
of the kvmppc_interrupt code, which then jumps to the PR handler,
renamed to kvmppc_interrupt_pr, if the guest is a PR guest. This helps
in enabling both HV and PR, which we do in later patch

Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
Signed-off-by: Alexander Graf <agraf@suse.de>
---
 arch/powerpc/include/asm/exception-64s.h | 11 +++++++++++
 arch/powerpc/kvm/book3s_hv_rmhandlers.S  |  9 +++++++--
 arch/powerpc/kvm/book3s_segment.S        |  4 ++--
 3 files changed, 20 insertions(+), 4 deletions(-)

(limited to 'arch/powerpc/kvm')

diff --git a/arch/powerpc/include/asm/exception-64s.h b/arch/powerpc/include/asm/exception-64s.h
index a22c9854a63..894662a5d4d 100644
--- a/arch/powerpc/include/asm/exception-64s.h
+++ b/arch/powerpc/include/asm/exception-64s.h
@@ -198,6 +198,17 @@ END_FTR_SECTION_NESTED(ftr,ftr,943)
 	cmpwi	r10,0;							\
 	bne	do_kvm_##n
 
+#ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE
+/*
+ * If hv is possible, interrupts come into to the hv version
+ * of the kvmppc_interrupt code, which then jumps to the PR handler,
+ * kvmppc_interrupt_pr, if the guest is a PR guest.
+ */
+#define kvmppc_interrupt kvmppc_interrupt_hv
+#else
+#define kvmppc_interrupt kvmppc_interrupt_pr
+#endif
+
 #define __KVM_HANDLER(area, h, n)					\
 do_kvm_##n:								\
 	BEGIN_FTR_SECTION_NESTED(947)					\
diff --git a/arch/powerpc/kvm/book3s_hv_rmhandlers.S b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
index 84105eb18a0..f7e24c6cb8e 100644
--- a/arch/powerpc/kvm/book3s_hv_rmhandlers.S
+++ b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
@@ -742,8 +742,8 @@ END_FTR_SECTION_IFSET(CPU_FTR_HAS_PPR)
 /*
  * We come here from the first-level interrupt handlers.
  */
-	.globl	kvmppc_interrupt
-kvmppc_interrupt:
+	.globl	kvmppc_interrupt_hv
+kvmppc_interrupt_hv:
 	/*
 	 * Register contents:
 	 * R12		= interrupt vector
@@ -757,6 +757,11 @@ kvmppc_interrupt:
 	lbz	r9, HSTATE_IN_GUEST(r13)
 	cmpwi	r9, KVM_GUEST_MODE_HOST_HV
 	beq	kvmppc_bad_host_intr
+#ifdef CONFIG_KVM_BOOK3S_PR_POSSIBLE
+	cmpwi	r9, KVM_GUEST_MODE_GUEST
+	ld	r9, HSTATE_HOST_R2(r13)
+	beq	kvmppc_interrupt_pr
+#endif
 	/* We're now back in the host but in guest MMU context */
 	li	r9, KVM_GUEST_MODE_HOST_HV
 	stb	r9, HSTATE_IN_GUEST(r13)
diff --git a/arch/powerpc/kvm/book3s_segment.S b/arch/powerpc/kvm/book3s_segment.S
index 1abe4788191..bc50c97751d 100644
--- a/arch/powerpc/kvm/book3s_segment.S
+++ b/arch/powerpc/kvm/book3s_segment.S
@@ -161,8 +161,8 @@ kvmppc_handler_trampoline_enter_end:
 .global kvmppc_handler_trampoline_exit
 kvmppc_handler_trampoline_exit:
 
-.global kvmppc_interrupt
-kvmppc_interrupt:
+.global kvmppc_interrupt_pr
+kvmppc_interrupt_pr:
 
 	/* Register usage at this point:
 	 *
-- 
cgit v1.2.3-70-g09d2


From 699cc87641c123128bf3a4e12c0a8d739b1ac2f3 Mon Sep 17 00:00:00 2001
From: "Aneesh Kumar K.V" <aneesh.kumar@linux.vnet.ibm.com>
Date: Mon, 7 Oct 2013 22:17:56 +0530
Subject: kvm: powerpc: book3s: Add is_hv_enabled to kvmppc_ops

This help us to identify whether we are running with hypervisor mode KVM
enabled. The change is needed so that we can have both HV and PR kvm
enabled in the same kernel.

If both HV and PR KVM are included, interrupts come in to the HV version
of the kvmppc_interrupt code, which then jumps to the PR handler,
renamed to kvmppc_interrupt_pr, if the guest is a PR guest.

Allowing both PR and HV in the same kernel required some changes to
kvm_dev_ioctl_check_extension(), since the values returned now can't
be selected with #ifdefs as much as previously. We look at is_hv_enabled
to return the right value when checking for capabilities.For capabilities that
are only provided by HV KVM, we return the HV value only if
is_hv_enabled is true. For capabilities provided by PR KVM but not HV,
we return the PR value only if is_hv_enabled is false.

NOTE: in later patch we replace is_hv_enabled with a static inline
function comparing kvm_ppc_ops

Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
Signed-off-by: Alexander Graf <agraf@suse.de>
---
 arch/powerpc/include/asm/kvm_book3s.h | 53 ----------------------------------
 arch/powerpc/include/asm/kvm_ppc.h    |  5 ++--
 arch/powerpc/kvm/book3s.c             | 44 ++++++++++++++++++++++++++++
 arch/powerpc/kvm/book3s_hv.c          |  1 +
 arch/powerpc/kvm/book3s_pr.c          |  1 +
 arch/powerpc/kvm/book3s_xics.c        |  2 +-
 arch/powerpc/kvm/powerpc.c            | 54 +++++++++++++++++++----------------
 7 files changed, 79 insertions(+), 81 deletions(-)

(limited to 'arch/powerpc/kvm')

diff --git a/arch/powerpc/include/asm/kvm_book3s.h b/arch/powerpc/include/asm/kvm_book3s.h
index 315a5d69241..4a594b76674 100644
--- a/arch/powerpc/include/asm/kvm_book3s.h
+++ b/arch/powerpc/include/asm/kvm_book3s.h
@@ -301,59 +301,6 @@ static inline ulong kvmppc_get_fault_dar(struct kvm_vcpu *vcpu)
 	return vcpu->arch.fault_dar;
 }
 
-#ifdef CONFIG_KVM_BOOK3S_PR_POSSIBLE
-
-static inline unsigned long kvmppc_interrupt_offset(struct kvm_vcpu *vcpu)
-{
-	return to_book3s(vcpu)->hior;
-}
-
-static inline void kvmppc_update_int_pending(struct kvm_vcpu *vcpu,
-			unsigned long pending_now, unsigned long old_pending)
-{
-	if (pending_now)
-		vcpu->arch.shared->int_pending = 1;
-	else if (old_pending)
-		vcpu->arch.shared->int_pending = 0;
-}
-
-static inline bool kvmppc_critical_section(struct kvm_vcpu *vcpu)
-{
-	ulong crit_raw = vcpu->arch.shared->critical;
-	ulong crit_r1 = kvmppc_get_gpr(vcpu, 1);
-	bool crit;
-
-	/* Truncate crit indicators in 32 bit mode */
-	if (!(vcpu->arch.shared->msr & MSR_SF)) {
-		crit_raw &= 0xffffffff;
-		crit_r1 &= 0xffffffff;
-	}
-
-	/* Critical section when crit == r1 */
-	crit = (crit_raw == crit_r1);
-	/* ... and we're in supervisor mode */
-	crit = crit && !(vcpu->arch.shared->msr & MSR_PR);
-
-	return crit;
-}
-#else /* CONFIG_KVM_BOOK3S_PR_POSSIBLE */
-
-static inline unsigned long kvmppc_interrupt_offset(struct kvm_vcpu *vcpu)
-{
-	return 0;
-}
-
-static inline void kvmppc_update_int_pending(struct kvm_vcpu *vcpu,
-			unsigned long pending_now, unsigned long old_pending)
-{
-}
-
-static inline bool kvmppc_critical_section(struct kvm_vcpu *vcpu)
-{
-	return false;
-}
-#endif
-
 /* Magic register values loaded into r3 and r4 before the 'sc' assembly
  * instruction for the OSI hypercalls */
 #define OSI_SC_MAGIC_R3			0x113724FA
diff --git a/arch/powerpc/include/asm/kvm_ppc.h b/arch/powerpc/include/asm/kvm_ppc.h
index 326033c9938..c13f15db476 100644
--- a/arch/powerpc/include/asm/kvm_ppc.h
+++ b/arch/powerpc/include/asm/kvm_ppc.h
@@ -180,6 +180,7 @@ union kvmppc_one_reg {
 };
 
 struct kvmppc_ops {
+	bool is_hv_enabled;
 	int (*get_sregs)(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs);
 	int (*set_sregs)(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs);
 	int (*get_one_reg)(struct kvm_vcpu *vcpu, u64 id,
@@ -309,10 +310,10 @@ static inline void kvmppc_set_xics_phys(int cpu, unsigned long addr)
 
 static inline u32 kvmppc_get_xics_latch(void)
 {
-	u32 xirr = get_paca()->kvm_hstate.saved_xirr;
+	u32 xirr;
 
+	xirr = get_paca()->kvm_hstate.saved_xirr;
 	get_paca()->kvm_hstate.saved_xirr = 0;
-
 	return xirr;
 }
 
diff --git a/arch/powerpc/kvm/book3s.c b/arch/powerpc/kvm/book3s.c
index 784a1d5ccb0..493aff77f84 100644
--- a/arch/powerpc/kvm/book3s.c
+++ b/arch/powerpc/kvm/book3s.c
@@ -69,6 +69,50 @@ void kvmppc_core_load_guest_debugstate(struct kvm_vcpu *vcpu)
 {
 }
 
+static inline unsigned long kvmppc_interrupt_offset(struct kvm_vcpu *vcpu)
+{
+	if (!kvmppc_ops->is_hv_enabled)
+		return to_book3s(vcpu)->hior;
+	return 0;
+}
+
+static inline void kvmppc_update_int_pending(struct kvm_vcpu *vcpu,
+			unsigned long pending_now, unsigned long old_pending)
+{
+	if (kvmppc_ops->is_hv_enabled)
+		return;
+	if (pending_now)
+		vcpu->arch.shared->int_pending = 1;
+	else if (old_pending)
+		vcpu->arch.shared->int_pending = 0;
+}
+
+static inline bool kvmppc_critical_section(struct kvm_vcpu *vcpu)
+{
+	ulong crit_raw;
+	ulong crit_r1;
+	bool crit;
+
+	if (kvmppc_ops->is_hv_enabled)
+		return false;
+
+	crit_raw = vcpu->arch.shared->critical;
+	crit_r1 = kvmppc_get_gpr(vcpu, 1);
+
+	/* Truncate crit indicators in 32 bit mode */
+	if (!(vcpu->arch.shared->msr & MSR_SF)) {
+		crit_raw &= 0xffffffff;
+		crit_r1 &= 0xffffffff;
+	}
+
+	/* Critical section when crit == r1 */
+	crit = (crit_raw == crit_r1);
+	/* ... and we're in supervisor mode */
+	crit = crit && !(vcpu->arch.shared->msr & MSR_PR);
+
+	return crit;
+}
+
 void kvmppc_inject_interrupt(struct kvm_vcpu *vcpu, int vec, u64 flags)
 {
 	vcpu->arch.shared->srr0 = kvmppc_get_pc(vcpu);
diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c
index 3d7079a08d2..0782c8688c8 100644
--- a/arch/powerpc/kvm/book3s_hv.c
+++ b/arch/powerpc/kvm/book3s_hv.c
@@ -2159,6 +2159,7 @@ static long kvm_arch_vm_ioctl_hv(struct file *filp,
 }
 
 static struct kvmppc_ops kvmppc_hv_ops = {
+	.is_hv_enabled = true,
 	.get_sregs = kvm_arch_vcpu_ioctl_get_sregs_hv,
 	.set_sregs = kvm_arch_vcpu_ioctl_set_sregs_hv,
 	.get_one_reg = kvmppc_get_one_reg_hv,
diff --git a/arch/powerpc/kvm/book3s_pr.c b/arch/powerpc/kvm/book3s_pr.c
index 05d28cf4a06..b6a525d7b5c 100644
--- a/arch/powerpc/kvm/book3s_pr.c
+++ b/arch/powerpc/kvm/book3s_pr.c
@@ -1523,6 +1523,7 @@ static long kvm_arch_vm_ioctl_pr(struct file *filp,
 }
 
 static struct kvmppc_ops kvmppc_pr_ops = {
+	.is_hv_enabled = false,
 	.get_sregs = kvm_arch_vcpu_ioctl_get_sregs_pr,
 	.set_sregs = kvm_arch_vcpu_ioctl_set_sregs_pr,
 	.get_one_reg = kvmppc_get_one_reg_pr,
diff --git a/arch/powerpc/kvm/book3s_xics.c b/arch/powerpc/kvm/book3s_xics.c
index 51ed1ea440e..cef3de96ff6 100644
--- a/arch/powerpc/kvm/book3s_xics.c
+++ b/arch/powerpc/kvm/book3s_xics.c
@@ -818,7 +818,7 @@ int kvmppc_xics_hcall(struct kvm_vcpu *vcpu, u32 req)
 	}
 
 	/* Check for real mode returning too hard */
-	if (xics->real_mode)
+	if (xics->real_mode && kvmppc_ops->is_hv_enabled)
 		return kvmppc_xics_rm_complete(vcpu, req);
 
 	switch (req) {
diff --git a/arch/powerpc/kvm/powerpc.c b/arch/powerpc/kvm/powerpc.c
index 69b930550d2..874a2a5e6ce 100644
--- a/arch/powerpc/kvm/powerpc.c
+++ b/arch/powerpc/kvm/powerpc.c
@@ -52,7 +52,6 @@ int kvm_arch_vcpu_should_kick(struct kvm_vcpu *vcpu)
 	return 1;
 }
 
-#ifndef CONFIG_KVM_BOOK3S_64_HV
 /*
  * Common checks before entering the guest world.  Call with interrupts
  * disabled.
@@ -127,7 +126,6 @@ int kvmppc_prepare_to_enter(struct kvm_vcpu *vcpu)
 
 	return r;
 }
-#endif /* CONFIG_KVM_BOOK3S_64_HV */
 
 int kvmppc_kvm_pv(struct kvm_vcpu *vcpu)
 {
@@ -194,11 +192,9 @@ int kvmppc_sanity_check(struct kvm_vcpu *vcpu)
 	if ((vcpu->arch.cpu_type != KVM_CPU_3S_64) && vcpu->arch.papr_enabled)
 		goto out;
 
-#ifdef CONFIG_KVM_BOOK3S_64_HV
 	/* HV KVM can only do PAPR mode for now */
-	if (!vcpu->arch.papr_enabled)
+	if (!vcpu->arch.papr_enabled && kvmppc_ops->is_hv_enabled)
 		goto out;
-#endif
 
 #ifdef CONFIG_KVM_BOOKE_HV
 	if (!cpu_has_feature(CPU_FTR_EMB_HV))
@@ -322,22 +318,26 @@ int kvm_dev_ioctl_check_extension(long ext)
 	case KVM_CAP_DEVICE_CTRL:
 		r = 1;
 		break;
-#ifndef CONFIG_KVM_BOOK3S_64_HV
 	case KVM_CAP_PPC_PAIRED_SINGLES:
 	case KVM_CAP_PPC_OSI:
 	case KVM_CAP_PPC_GET_PVINFO:
 #if defined(CONFIG_KVM_E500V2) || defined(CONFIG_KVM_E500MC)
 	case KVM_CAP_SW_TLB:
 #endif
-#ifdef CONFIG_KVM_MPIC
-	case KVM_CAP_IRQ_MPIC:
-#endif
-		r = 1;
+		/* We support this only for PR */
+		r = !kvmppc_ops->is_hv_enabled;
 		break;
+#ifdef CONFIG_KVM_MMIO
 	case KVM_CAP_COALESCED_MMIO:
 		r = KVM_COALESCED_MMIO_PAGE_OFFSET;
 		break;
 #endif
+#ifdef CONFIG_KVM_MPIC
+	case KVM_CAP_IRQ_MPIC:
+		r = 1;
+		break;
+#endif
+
 #ifdef CONFIG_PPC_BOOK3S_64
 	case KVM_CAP_SPAPR_TCE:
 	case KVM_CAP_PPC_ALLOC_HTAB:
@@ -348,32 +348,37 @@ int kvm_dev_ioctl_check_extension(long ext)
 		r = 1;
 		break;
 #endif /* CONFIG_PPC_BOOK3S_64 */
-#ifdef CONFIG_KVM_BOOK3S_64_HV
+#ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE
 	case KVM_CAP_PPC_SMT:
-		r = threads_per_core;
+		if (kvmppc_ops->is_hv_enabled)
+			r = threads_per_core;
+		else
+			r = 0;
 		break;
 	case KVM_CAP_PPC_RMA:
-		r = 1;
+		r = kvmppc_ops->is_hv_enabled;
 		/* PPC970 requires an RMA */
-		if (cpu_has_feature(CPU_FTR_ARCH_201))
+		if (r && cpu_has_feature(CPU_FTR_ARCH_201))
 			r = 2;
 		break;
 #endif
 	case KVM_CAP_SYNC_MMU:
-#ifdef CONFIG_KVM_BOOK3S_64_HV
-		r = cpu_has_feature(CPU_FTR_ARCH_206) ? 1 : 0;
+#ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE
+		if (kvmppc_ops->is_hv_enabled)
+			r = cpu_has_feature(CPU_FTR_ARCH_206) ? 1 : 0;
+		else
+			r = 0;
 #elif defined(KVM_ARCH_WANT_MMU_NOTIFIER)
 		r = 1;
 #else
 		r = 0;
-		break;
 #endif
-#ifdef CONFIG_KVM_BOOK3S_64_HV
+		break;
+#ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE
 	case KVM_CAP_PPC_HTAB_FD:
-		r = 1;
+		r = kvmppc_ops->is_hv_enabled;
 		break;
 #endif
-		break;
 	case KVM_CAP_NR_VCPUS:
 		/*
 		 * Recommending a number of CPUs is somewhat arbitrary; we
@@ -381,11 +386,10 @@ int kvm_dev_ioctl_check_extension(long ext)
 		 * will have secondary threads "offline"), and for other KVM
 		 * implementations just count online CPUs.
 		 */
-#ifdef CONFIG_KVM_BOOK3S_64_HV
-		r = num_present_cpus();
-#else
-		r = num_online_cpus();
-#endif
+		if (kvmppc_ops->is_hv_enabled)
+			r = num_present_cpus();
+		else
+			r = num_online_cpus();
 		break;
 	case KVM_CAP_MAX_VCPUS:
 		r = KVM_MAX_VCPUS;
-- 
cgit v1.2.3-70-g09d2


From 72c1253574a1854b0b6f196e24cd0dd08c1ad9b9 Mon Sep 17 00:00:00 2001
From: "Aneesh Kumar K.V" <aneesh.kumar@linux.vnet.ibm.com>
Date: Mon, 7 Oct 2013 22:17:57 +0530
Subject: kvm: powerpc: book3s: pr: move PR related tracepoints to a separate
 header

This patch moves PR related tracepoints to a separate header. This
enables in converting PR to a kernel module which will be done in
later patches

Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
Signed-off-by: Alexander Graf <agraf@suse.de>
---
 arch/powerpc/kvm/book3s_64_mmu_host.c |   2 +-
 arch/powerpc/kvm/book3s_mmu_hpte.c    |   2 +-
 arch/powerpc/kvm/book3s_pr.c          |   4 +-
 arch/powerpc/kvm/trace.h              | 234 +--------------------------
 arch/powerpc/kvm/trace_pr.h           | 297 ++++++++++++++++++++++++++++++++++
 5 files changed, 309 insertions(+), 230 deletions(-)
 create mode 100644 arch/powerpc/kvm/trace_pr.h

(limited to 'arch/powerpc/kvm')

diff --git a/arch/powerpc/kvm/book3s_64_mmu_host.c b/arch/powerpc/kvm/book3s_64_mmu_host.c
index 819672c9d78..0d513af62bb 100644
--- a/arch/powerpc/kvm/book3s_64_mmu_host.c
+++ b/arch/powerpc/kvm/book3s_64_mmu_host.c
@@ -27,7 +27,7 @@
 #include <asm/machdep.h>
 #include <asm/mmu_context.h>
 #include <asm/hw_irq.h>
-#include "trace.h"
+#include "trace_pr.h"
 
 #define PTE_SIZE 12
 
diff --git a/arch/powerpc/kvm/book3s_mmu_hpte.c b/arch/powerpc/kvm/book3s_mmu_hpte.c
index 6b79bfc44ba..5a1ab1250a0 100644
--- a/arch/powerpc/kvm/book3s_mmu_hpte.c
+++ b/arch/powerpc/kvm/book3s_mmu_hpte.c
@@ -28,7 +28,7 @@
 #include <asm/mmu_context.h>
 #include <asm/hw_irq.h>
 
-#include "trace.h"
+#include "trace_pr.h"
 
 #define PTE_SIZE	12
 
diff --git a/arch/powerpc/kvm/book3s_pr.c b/arch/powerpc/kvm/book3s_pr.c
index b6a525d7b5c..ca6c73d2ee7 100644
--- a/arch/powerpc/kvm/book3s_pr.c
+++ b/arch/powerpc/kvm/book3s_pr.c
@@ -42,7 +42,9 @@
 #include <linux/highmem.h>
 
 #include "book3s.h"
-#include "trace.h"
+
+#define CREATE_TRACE_POINTS
+#include "trace_pr.h"
 
 /* #define EXIT_DEBUG */
 /* #define DEBUG_EXT */
diff --git a/arch/powerpc/kvm/trace.h b/arch/powerpc/kvm/trace.h
index 9e8368edf37..80f252af6cb 100644
--- a/arch/powerpc/kvm/trace.h
+++ b/arch/powerpc/kvm/trace.h
@@ -85,6 +85,12 @@ TRACE_EVENT(kvm_ppc_instr,
 	{41, "HV_PRIV"}
 #endif
 
+#ifndef CONFIG_KVM_BOOK3S_PR_POSSIBLE
+/*
+ * For pr we define this in trace_pr.h since it pr can be built as
+ * a module
+ */
+
 TRACE_EVENT(kvm_exit,
 	TP_PROTO(unsigned int exit_nr, struct kvm_vcpu *vcpu),
 	TP_ARGS(exit_nr, vcpu),
@@ -94,9 +100,6 @@ TRACE_EVENT(kvm_exit,
 		__field(	unsigned long,	pc		)
 		__field(	unsigned long,	msr		)
 		__field(	unsigned long,	dar		)
-#ifdef CONFIG_KVM_BOOK3S_PR_POSSIBLE
-		__field(	unsigned long,	srr1		)
-#endif
 		__field(	unsigned long,	last_inst	)
 	),
 
@@ -105,9 +108,6 @@ TRACE_EVENT(kvm_exit,
 		__entry->pc		= kvmppc_get_pc(vcpu);
 		__entry->dar		= kvmppc_get_fault_dar(vcpu);
 		__entry->msr		= vcpu->arch.shared->msr;
-#ifdef CONFIG_KVM_BOOK3S_PR_POSSIBLE
-		__entry->srr1		= vcpu->arch.shadow_srr1;
-#endif
 		__entry->last_inst	= vcpu->arch.last_inst;
 	),
 
@@ -115,18 +115,12 @@ TRACE_EVENT(kvm_exit,
 		" | pc=0x%lx"
 		" | msr=0x%lx"
 		" | dar=0x%lx"
-#ifdef CONFIG_KVM_BOOK3S_PR_POSSIBLE
-		" | srr1=0x%lx"
-#endif
 		" | last_inst=0x%lx"
 		,
 		__print_symbolic(__entry->exit_nr, kvm_trace_symbol_exit),
 		__entry->pc,
 		__entry->msr,
 		__entry->dar,
-#ifdef CONFIG_KVM_BOOK3S_PR_POSSIBLE
-		__entry->srr1,
-#endif
 		__entry->last_inst
 		)
 );
@@ -145,6 +139,7 @@ TRACE_EVENT(kvm_unmap_hva,
 
 	TP_printk("unmap hva 0x%lx\n", __entry->hva)
 );
+#endif
 
 TRACE_EVENT(kvm_stlb_inval,
 	TP_PROTO(unsigned int stlb_index),
@@ -231,221 +226,6 @@ TRACE_EVENT(kvm_check_requests,
 		__entry->cpu_nr, __entry->requests)
 );
 
-
-/*************************************************************************
- *                         Book3S trace points                           *
- *************************************************************************/
-
-#ifdef CONFIG_KVM_BOOK3S_PR_POSSIBLE
-
-TRACE_EVENT(kvm_book3s_reenter,
-	TP_PROTO(int r, struct kvm_vcpu *vcpu),
-	TP_ARGS(r, vcpu),
-
-	TP_STRUCT__entry(
-		__field(	unsigned int,	r		)
-		__field(	unsigned long,	pc		)
-	),
-
-	TP_fast_assign(
-		__entry->r		= r;
-		__entry->pc		= kvmppc_get_pc(vcpu);
-	),
-
-	TP_printk("reentry r=%d | pc=0x%lx", __entry->r, __entry->pc)
-);
-
-#ifdef CONFIG_PPC_BOOK3S_64
-
-TRACE_EVENT(kvm_book3s_64_mmu_map,
-	TP_PROTO(int rflags, ulong hpteg, ulong va, pfn_t hpaddr,
-		 struct kvmppc_pte *orig_pte),
-	TP_ARGS(rflags, hpteg, va, hpaddr, orig_pte),
-
-	TP_STRUCT__entry(
-		__field(	unsigned char,		flag_w		)
-		__field(	unsigned char,		flag_x		)
-		__field(	unsigned long,		eaddr		)
-		__field(	unsigned long,		hpteg		)
-		__field(	unsigned long,		va		)
-		__field(	unsigned long long,	vpage		)
-		__field(	unsigned long,		hpaddr		)
-	),
-
-	TP_fast_assign(
-		__entry->flag_w	= ((rflags & HPTE_R_PP) == 3) ? '-' : 'w';
-		__entry->flag_x	= (rflags & HPTE_R_N) ? '-' : 'x';
-		__entry->eaddr	= orig_pte->eaddr;
-		__entry->hpteg	= hpteg;
-		__entry->va	= va;
-		__entry->vpage	= orig_pte->vpage;
-		__entry->hpaddr	= hpaddr;
-	),
-
-	TP_printk("KVM: %c%c Map 0x%lx: [%lx] 0x%lx (0x%llx) -> %lx",
-		  __entry->flag_w, __entry->flag_x, __entry->eaddr,
-		  __entry->hpteg, __entry->va, __entry->vpage, __entry->hpaddr)
-);
-
-#endif /* CONFIG_PPC_BOOK3S_64 */
-
-TRACE_EVENT(kvm_book3s_mmu_map,
-	TP_PROTO(struct hpte_cache *pte),
-	TP_ARGS(pte),
-
-	TP_STRUCT__entry(
-		__field(	u64,		host_vpn	)
-		__field(	u64,		pfn		)
-		__field(	ulong,		eaddr		)
-		__field(	u64,		vpage		)
-		__field(	ulong,		raddr		)
-		__field(	int,		flags		)
-	),
-
-	TP_fast_assign(
-		__entry->host_vpn	= pte->host_vpn;
-		__entry->pfn		= pte->pfn;
-		__entry->eaddr		= pte->pte.eaddr;
-		__entry->vpage		= pte->pte.vpage;
-		__entry->raddr		= pte->pte.raddr;
-		__entry->flags		= (pte->pte.may_read ? 0x4 : 0) |
-					  (pte->pte.may_write ? 0x2 : 0) |
-					  (pte->pte.may_execute ? 0x1 : 0);
-	),
-
-	TP_printk("Map: hvpn=%llx pfn=%llx ea=%lx vp=%llx ra=%lx [%x]",
-		  __entry->host_vpn, __entry->pfn, __entry->eaddr,
-		  __entry->vpage, __entry->raddr, __entry->flags)
-);
-
-TRACE_EVENT(kvm_book3s_mmu_invalidate,
-	TP_PROTO(struct hpte_cache *pte),
-	TP_ARGS(pte),
-
-	TP_STRUCT__entry(
-		__field(	u64,		host_vpn	)
-		__field(	u64,		pfn		)
-		__field(	ulong,		eaddr		)
-		__field(	u64,		vpage		)
-		__field(	ulong,		raddr		)
-		__field(	int,		flags		)
-	),
-
-	TP_fast_assign(
-		__entry->host_vpn	= pte->host_vpn;
-		__entry->pfn		= pte->pfn;
-		__entry->eaddr		= pte->pte.eaddr;
-		__entry->vpage		= pte->pte.vpage;
-		__entry->raddr		= pte->pte.raddr;
-		__entry->flags		= (pte->pte.may_read ? 0x4 : 0) |
-					  (pte->pte.may_write ? 0x2 : 0) |
-					  (pte->pte.may_execute ? 0x1 : 0);
-	),
-
-	TP_printk("Flush: hva=%llx pfn=%llx ea=%lx vp=%llx ra=%lx [%x]",
-		  __entry->host_vpn, __entry->pfn, __entry->eaddr,
-		  __entry->vpage, __entry->raddr, __entry->flags)
-);
-
-TRACE_EVENT(kvm_book3s_mmu_flush,
-	TP_PROTO(const char *type, struct kvm_vcpu *vcpu, unsigned long long p1,
-		 unsigned long long p2),
-	TP_ARGS(type, vcpu, p1, p2),
-
-	TP_STRUCT__entry(
-		__field(	int,			count		)
-		__field(	unsigned long long,	p1		)
-		__field(	unsigned long long,	p2		)
-		__field(	const char *,		type		)
-	),
-
-	TP_fast_assign(
-		__entry->count		= to_book3s(vcpu)->hpte_cache_count;
-		__entry->p1		= p1;
-		__entry->p2		= p2;
-		__entry->type		= type;
-	),
-
-	TP_printk("Flush %d %sPTEs: %llx - %llx",
-		  __entry->count, __entry->type, __entry->p1, __entry->p2)
-);
-
-TRACE_EVENT(kvm_book3s_slb_found,
-	TP_PROTO(unsigned long long gvsid, unsigned long long hvsid),
-	TP_ARGS(gvsid, hvsid),
-
-	TP_STRUCT__entry(
-		__field(	unsigned long long,	gvsid		)
-		__field(	unsigned long long,	hvsid		)
-	),
-
-	TP_fast_assign(
-		__entry->gvsid		= gvsid;
-		__entry->hvsid		= hvsid;
-	),
-
-	TP_printk("%llx -> %llx", __entry->gvsid, __entry->hvsid)
-);
-
-TRACE_EVENT(kvm_book3s_slb_fail,
-	TP_PROTO(u16 sid_map_mask, unsigned long long gvsid),
-	TP_ARGS(sid_map_mask, gvsid),
-
-	TP_STRUCT__entry(
-		__field(	unsigned short,		sid_map_mask	)
-		__field(	unsigned long long,	gvsid		)
-	),
-
-	TP_fast_assign(
-		__entry->sid_map_mask	= sid_map_mask;
-		__entry->gvsid		= gvsid;
-	),
-
-	TP_printk("%x/%x: %llx", __entry->sid_map_mask,
-		  SID_MAP_MASK - __entry->sid_map_mask, __entry->gvsid)
-);
-
-TRACE_EVENT(kvm_book3s_slb_map,
-	TP_PROTO(u16 sid_map_mask, unsigned long long gvsid,
-		 unsigned long long hvsid),
-	TP_ARGS(sid_map_mask, gvsid, hvsid),
-
-	TP_STRUCT__entry(
-		__field(	unsigned short,		sid_map_mask	)
-		__field(	unsigned long long,	guest_vsid	)
-		__field(	unsigned long long,	host_vsid	)
-	),
-
-	TP_fast_assign(
-		__entry->sid_map_mask	= sid_map_mask;
-		__entry->guest_vsid	= gvsid;
-		__entry->host_vsid	= hvsid;
-	),
-
-	TP_printk("%x: %llx -> %llx", __entry->sid_map_mask,
-		  __entry->guest_vsid, __entry->host_vsid)
-);
-
-TRACE_EVENT(kvm_book3s_slbmte,
-	TP_PROTO(u64 slb_vsid, u64 slb_esid),
-	TP_ARGS(slb_vsid, slb_esid),
-
-	TP_STRUCT__entry(
-		__field(	u64,	slb_vsid	)
-		__field(	u64,	slb_esid	)
-	),
-
-	TP_fast_assign(
-		__entry->slb_vsid	= slb_vsid;
-		__entry->slb_esid	= slb_esid;
-	),
-
-	TP_printk("%llx, %llx", __entry->slb_vsid, __entry->slb_esid)
-);
-
-#endif /* CONFIG_PPC_BOOK3S */
-
-
 /*************************************************************************
  *                         Book3E trace points                           *
  *************************************************************************/
diff --git a/arch/powerpc/kvm/trace_pr.h b/arch/powerpc/kvm/trace_pr.h
new file mode 100644
index 00000000000..8b22e474834
--- /dev/null
+++ b/arch/powerpc/kvm/trace_pr.h
@@ -0,0 +1,297 @@
+
+#if !defined(_TRACE_KVM_PR_H) || defined(TRACE_HEADER_MULTI_READ)
+#define _TRACE_KVM_PR_H
+
+#include <linux/tracepoint.h>
+
+#undef TRACE_SYSTEM
+#define TRACE_SYSTEM kvm_pr
+#define TRACE_INCLUDE_PATH .
+#define TRACE_INCLUDE_FILE trace_pr
+
+#define kvm_trace_symbol_exit \
+	{0x100, "SYSTEM_RESET"}, \
+	{0x200, "MACHINE_CHECK"}, \
+	{0x300, "DATA_STORAGE"}, \
+	{0x380, "DATA_SEGMENT"}, \
+	{0x400, "INST_STORAGE"}, \
+	{0x480, "INST_SEGMENT"}, \
+	{0x500, "EXTERNAL"}, \
+	{0x501, "EXTERNAL_LEVEL"}, \
+	{0x502, "EXTERNAL_HV"}, \
+	{0x600, "ALIGNMENT"}, \
+	{0x700, "PROGRAM"}, \
+	{0x800, "FP_UNAVAIL"}, \
+	{0x900, "DECREMENTER"}, \
+	{0x980, "HV_DECREMENTER"}, \
+	{0xc00, "SYSCALL"}, \
+	{0xd00, "TRACE"}, \
+	{0xe00, "H_DATA_STORAGE"}, \
+	{0xe20, "H_INST_STORAGE"}, \
+	{0xe40, "H_EMUL_ASSIST"}, \
+	{0xf00, "PERFMON"}, \
+	{0xf20, "ALTIVEC"}, \
+	{0xf40, "VSX"}
+
+TRACE_EVENT(kvm_book3s_reenter,
+	TP_PROTO(int r, struct kvm_vcpu *vcpu),
+	TP_ARGS(r, vcpu),
+
+	TP_STRUCT__entry(
+		__field(	unsigned int,	r		)
+		__field(	unsigned long,	pc		)
+	),
+
+	TP_fast_assign(
+		__entry->r		= r;
+		__entry->pc		= kvmppc_get_pc(vcpu);
+	),
+
+	TP_printk("reentry r=%d | pc=0x%lx", __entry->r, __entry->pc)
+);
+
+#ifdef CONFIG_PPC_BOOK3S_64
+
+TRACE_EVENT(kvm_book3s_64_mmu_map,
+	TP_PROTO(int rflags, ulong hpteg, ulong va, pfn_t hpaddr,
+		 struct kvmppc_pte *orig_pte),
+	TP_ARGS(rflags, hpteg, va, hpaddr, orig_pte),
+
+	TP_STRUCT__entry(
+		__field(	unsigned char,		flag_w		)
+		__field(	unsigned char,		flag_x		)
+		__field(	unsigned long,		eaddr		)
+		__field(	unsigned long,		hpteg		)
+		__field(	unsigned long,		va		)
+		__field(	unsigned long long,	vpage		)
+		__field(	unsigned long,		hpaddr		)
+	),
+
+	TP_fast_assign(
+		__entry->flag_w	= ((rflags & HPTE_R_PP) == 3) ? '-' : 'w';
+		__entry->flag_x	= (rflags & HPTE_R_N) ? '-' : 'x';
+		__entry->eaddr	= orig_pte->eaddr;
+		__entry->hpteg	= hpteg;
+		__entry->va	= va;
+		__entry->vpage	= orig_pte->vpage;
+		__entry->hpaddr	= hpaddr;
+	),
+
+	TP_printk("KVM: %c%c Map 0x%lx: [%lx] 0x%lx (0x%llx) -> %lx",
+		  __entry->flag_w, __entry->flag_x, __entry->eaddr,
+		  __entry->hpteg, __entry->va, __entry->vpage, __entry->hpaddr)
+);
+
+#endif /* CONFIG_PPC_BOOK3S_64 */
+
+TRACE_EVENT(kvm_book3s_mmu_map,
+	TP_PROTO(struct hpte_cache *pte),
+	TP_ARGS(pte),
+
+	TP_STRUCT__entry(
+		__field(	u64,		host_vpn	)
+		__field(	u64,		pfn		)
+		__field(	ulong,		eaddr		)
+		__field(	u64,		vpage		)
+		__field(	ulong,		raddr		)
+		__field(	int,		flags		)
+	),
+
+	TP_fast_assign(
+		__entry->host_vpn	= pte->host_vpn;
+		__entry->pfn		= pte->pfn;
+		__entry->eaddr		= pte->pte.eaddr;
+		__entry->vpage		= pte->pte.vpage;
+		__entry->raddr		= pte->pte.raddr;
+		__entry->flags		= (pte->pte.may_read ? 0x4 : 0) |
+					  (pte->pte.may_write ? 0x2 : 0) |
+					  (pte->pte.may_execute ? 0x1 : 0);
+	),
+
+	TP_printk("Map: hvpn=%llx pfn=%llx ea=%lx vp=%llx ra=%lx [%x]",
+		  __entry->host_vpn, __entry->pfn, __entry->eaddr,
+		  __entry->vpage, __entry->raddr, __entry->flags)
+);
+
+TRACE_EVENT(kvm_book3s_mmu_invalidate,
+	TP_PROTO(struct hpte_cache *pte),
+	TP_ARGS(pte),
+
+	TP_STRUCT__entry(
+		__field(	u64,		host_vpn	)
+		__field(	u64,		pfn		)
+		__field(	ulong,		eaddr		)
+		__field(	u64,		vpage		)
+		__field(	ulong,		raddr		)
+		__field(	int,		flags		)
+	),
+
+	TP_fast_assign(
+		__entry->host_vpn	= pte->host_vpn;
+		__entry->pfn		= pte->pfn;
+		__entry->eaddr		= pte->pte.eaddr;
+		__entry->vpage		= pte->pte.vpage;
+		__entry->raddr		= pte->pte.raddr;
+		__entry->flags		= (pte->pte.may_read ? 0x4 : 0) |
+					  (pte->pte.may_write ? 0x2 : 0) |
+					  (pte->pte.may_execute ? 0x1 : 0);
+	),
+
+	TP_printk("Flush: hva=%llx pfn=%llx ea=%lx vp=%llx ra=%lx [%x]",
+		  __entry->host_vpn, __entry->pfn, __entry->eaddr,
+		  __entry->vpage, __entry->raddr, __entry->flags)
+);
+
+TRACE_EVENT(kvm_book3s_mmu_flush,
+	TP_PROTO(const char *type, struct kvm_vcpu *vcpu, unsigned long long p1,
+		 unsigned long long p2),
+	TP_ARGS(type, vcpu, p1, p2),
+
+	TP_STRUCT__entry(
+		__field(	int,			count		)
+		__field(	unsigned long long,	p1		)
+		__field(	unsigned long long,	p2		)
+		__field(	const char *,		type		)
+	),
+
+	TP_fast_assign(
+		__entry->count		= to_book3s(vcpu)->hpte_cache_count;
+		__entry->p1		= p1;
+		__entry->p2		= p2;
+		__entry->type		= type;
+	),
+
+	TP_printk("Flush %d %sPTEs: %llx - %llx",
+		  __entry->count, __entry->type, __entry->p1, __entry->p2)
+);
+
+TRACE_EVENT(kvm_book3s_slb_found,
+	TP_PROTO(unsigned long long gvsid, unsigned long long hvsid),
+	TP_ARGS(gvsid, hvsid),
+
+	TP_STRUCT__entry(
+		__field(	unsigned long long,	gvsid		)
+		__field(	unsigned long long,	hvsid		)
+	),
+
+	TP_fast_assign(
+		__entry->gvsid		= gvsid;
+		__entry->hvsid		= hvsid;
+	),
+
+	TP_printk("%llx -> %llx", __entry->gvsid, __entry->hvsid)
+);
+
+TRACE_EVENT(kvm_book3s_slb_fail,
+	TP_PROTO(u16 sid_map_mask, unsigned long long gvsid),
+	TP_ARGS(sid_map_mask, gvsid),
+
+	TP_STRUCT__entry(
+		__field(	unsigned short,		sid_map_mask	)
+		__field(	unsigned long long,	gvsid		)
+	),
+
+	TP_fast_assign(
+		__entry->sid_map_mask	= sid_map_mask;
+		__entry->gvsid		= gvsid;
+	),
+
+	TP_printk("%x/%x: %llx", __entry->sid_map_mask,
+		  SID_MAP_MASK - __entry->sid_map_mask, __entry->gvsid)
+);
+
+TRACE_EVENT(kvm_book3s_slb_map,
+	TP_PROTO(u16 sid_map_mask, unsigned long long gvsid,
+		 unsigned long long hvsid),
+	TP_ARGS(sid_map_mask, gvsid, hvsid),
+
+	TP_STRUCT__entry(
+		__field(	unsigned short,		sid_map_mask	)
+		__field(	unsigned long long,	guest_vsid	)
+		__field(	unsigned long long,	host_vsid	)
+	),
+
+	TP_fast_assign(
+		__entry->sid_map_mask	= sid_map_mask;
+		__entry->guest_vsid	= gvsid;
+		__entry->host_vsid	= hvsid;
+	),
+
+	TP_printk("%x: %llx -> %llx", __entry->sid_map_mask,
+		  __entry->guest_vsid, __entry->host_vsid)
+);
+
+TRACE_EVENT(kvm_book3s_slbmte,
+	TP_PROTO(u64 slb_vsid, u64 slb_esid),
+	TP_ARGS(slb_vsid, slb_esid),
+
+	TP_STRUCT__entry(
+		__field(	u64,	slb_vsid	)
+		__field(	u64,	slb_esid	)
+	),
+
+	TP_fast_assign(
+		__entry->slb_vsid	= slb_vsid;
+		__entry->slb_esid	= slb_esid;
+	),
+
+	TP_printk("%llx, %llx", __entry->slb_vsid, __entry->slb_esid)
+);
+
+TRACE_EVENT(kvm_exit,
+	TP_PROTO(unsigned int exit_nr, struct kvm_vcpu *vcpu),
+	TP_ARGS(exit_nr, vcpu),
+
+	TP_STRUCT__entry(
+		__field(	unsigned int,	exit_nr		)
+		__field(	unsigned long,	pc		)
+		__field(	unsigned long,	msr		)
+		__field(	unsigned long,	dar		)
+		__field(	unsigned long,	srr1		)
+		__field(	unsigned long,	last_inst	)
+	),
+
+	TP_fast_assign(
+		__entry->exit_nr	= exit_nr;
+		__entry->pc		= kvmppc_get_pc(vcpu);
+		__entry->dar		= kvmppc_get_fault_dar(vcpu);
+		__entry->msr		= vcpu->arch.shared->msr;
+		__entry->srr1		= vcpu->arch.shadow_srr1;
+		__entry->last_inst	= vcpu->arch.last_inst;
+	),
+
+	TP_printk("exit=%s"
+		" | pc=0x%lx"
+		" | msr=0x%lx"
+		" | dar=0x%lx"
+		" | srr1=0x%lx"
+		" | last_inst=0x%lx"
+		,
+		__print_symbolic(__entry->exit_nr, kvm_trace_symbol_exit),
+		__entry->pc,
+		__entry->msr,
+		__entry->dar,
+		__entry->srr1,
+		__entry->last_inst
+		)
+);
+
+TRACE_EVENT(kvm_unmap_hva,
+	TP_PROTO(unsigned long hva),
+	TP_ARGS(hva),
+
+	TP_STRUCT__entry(
+		__field(	unsigned long,	hva		)
+	),
+
+	TP_fast_assign(
+		__entry->hva		= hva;
+	),
+
+	TP_printk("unmap hva 0x%lx\n", __entry->hva)
+);
+
+#endif /* _TRACE_KVM_H */
+
+/* This part must be outside protection */
+#include <trace/define_trace.h>
-- 
cgit v1.2.3-70-g09d2


From dba291f2ceacb833063179530eeb83a317a6cc95 Mon Sep 17 00:00:00 2001
From: "Aneesh Kumar K.V" <aneesh.kumar@linux.vnet.ibm.com>
Date: Mon, 7 Oct 2013 22:17:58 +0530
Subject: kvm: powerpc: booke: Move booke related tracepoints to separate
 header

Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
Signed-off-by: Alexander Graf <agraf@suse.de>
---
 arch/powerpc/kvm/booke.c         |   4 +-
 arch/powerpc/kvm/e500_mmu.c      |   2 +-
 arch/powerpc/kvm/e500_mmu_host.c |   3 +-
 arch/powerpc/kvm/trace.h         | 204 ---------------------------------------
 arch/powerpc/kvm/trace_booke.h   | 177 +++++++++++++++++++++++++++++++++
 5 files changed, 183 insertions(+), 207 deletions(-)
 create mode 100644 arch/powerpc/kvm/trace_booke.h

(limited to 'arch/powerpc/kvm')

diff --git a/arch/powerpc/kvm/booke.c b/arch/powerpc/kvm/booke.c
index e5f8ba793c3..1769354d0bf 100644
--- a/arch/powerpc/kvm/booke.c
+++ b/arch/powerpc/kvm/booke.c
@@ -40,7 +40,9 @@
 
 #include "timing.h"
 #include "booke.h"
-#include "trace.h"
+
+#define CREATE_TRACE_POINTS
+#include "trace_booke.h"
 
 unsigned long kvmppc_booke_handlers;
 
diff --git a/arch/powerpc/kvm/e500_mmu.c b/arch/powerpc/kvm/e500_mmu.c
index d25bb75aec9..ebca6b88ea5 100644
--- a/arch/powerpc/kvm/e500_mmu.c
+++ b/arch/powerpc/kvm/e500_mmu.c
@@ -32,7 +32,7 @@
 #include <asm/kvm_ppc.h>
 
 #include "e500.h"
-#include "trace.h"
+#include "trace_booke.h"
 #include "timing.h"
 #include "e500_mmu_host.h"
 
diff --git a/arch/powerpc/kvm/e500_mmu_host.c b/arch/powerpc/kvm/e500_mmu_host.c
index 8f0d532522d..e7dde4b8878 100644
--- a/arch/powerpc/kvm/e500_mmu_host.c
+++ b/arch/powerpc/kvm/e500_mmu_host.c
@@ -32,10 +32,11 @@
 #include <asm/kvm_ppc.h>
 
 #include "e500.h"
-#include "trace.h"
 #include "timing.h"
 #include "e500_mmu_host.h"
 
+#include "trace_booke.h"
+
 #define to_htlb1_esel(esel) (host_tlb_params[1].entries - (esel) - 1)
 
 static struct kvmppc_e500_tlb_params host_tlb_params[E500_TLB_NUM];
diff --git a/arch/powerpc/kvm/trace.h b/arch/powerpc/kvm/trace.h
index 80f252af6cb..2e0e67ef354 100644
--- a/arch/powerpc/kvm/trace.h
+++ b/arch/powerpc/kvm/trace.h
@@ -31,116 +31,6 @@ TRACE_EVENT(kvm_ppc_instr,
 		  __entry->inst, __entry->pc, __entry->emulate)
 );
 
-#ifdef CONFIG_PPC_BOOK3S
-#define kvm_trace_symbol_exit \
-	{0x100, "SYSTEM_RESET"}, \
-	{0x200, "MACHINE_CHECK"}, \
-	{0x300, "DATA_STORAGE"}, \
-	{0x380, "DATA_SEGMENT"}, \
-	{0x400, "INST_STORAGE"}, \
-	{0x480, "INST_SEGMENT"}, \
-	{0x500, "EXTERNAL"}, \
-	{0x501, "EXTERNAL_LEVEL"}, \
-	{0x502, "EXTERNAL_HV"}, \
-	{0x600, "ALIGNMENT"}, \
-	{0x700, "PROGRAM"}, \
-	{0x800, "FP_UNAVAIL"}, \
-	{0x900, "DECREMENTER"}, \
-	{0x980, "HV_DECREMENTER"}, \
-	{0xc00, "SYSCALL"}, \
-	{0xd00, "TRACE"}, \
-	{0xe00, "H_DATA_STORAGE"}, \
-	{0xe20, "H_INST_STORAGE"}, \
-	{0xe40, "H_EMUL_ASSIST"}, \
-	{0xf00, "PERFMON"}, \
-	{0xf20, "ALTIVEC"}, \
-	{0xf40, "VSX"}
-#else
-#define kvm_trace_symbol_exit \
-	{0, "CRITICAL"}, \
-	{1, "MACHINE_CHECK"}, \
-	{2, "DATA_STORAGE"}, \
-	{3, "INST_STORAGE"}, \
-	{4, "EXTERNAL"}, \
-	{5, "ALIGNMENT"}, \
-	{6, "PROGRAM"}, \
-	{7, "FP_UNAVAIL"}, \
-	{8, "SYSCALL"}, \
-	{9, "AP_UNAVAIL"}, \
-	{10, "DECREMENTER"}, \
-	{11, "FIT"}, \
-	{12, "WATCHDOG"}, \
-	{13, "DTLB_MISS"}, \
-	{14, "ITLB_MISS"}, \
-	{15, "DEBUG"}, \
-	{32, "SPE_UNAVAIL"}, \
-	{33, "SPE_FP_DATA"}, \
-	{34, "SPE_FP_ROUND"}, \
-	{35, "PERFORMANCE_MONITOR"}, \
-	{36, "DOORBELL"}, \
-	{37, "DOORBELL_CRITICAL"}, \
-	{38, "GUEST_DBELL"}, \
-	{39, "GUEST_DBELL_CRIT"}, \
-	{40, "HV_SYSCALL"}, \
-	{41, "HV_PRIV"}
-#endif
-
-#ifndef CONFIG_KVM_BOOK3S_PR_POSSIBLE
-/*
- * For pr we define this in trace_pr.h since it pr can be built as
- * a module
- */
-
-TRACE_EVENT(kvm_exit,
-	TP_PROTO(unsigned int exit_nr, struct kvm_vcpu *vcpu),
-	TP_ARGS(exit_nr, vcpu),
-
-	TP_STRUCT__entry(
-		__field(	unsigned int,	exit_nr		)
-		__field(	unsigned long,	pc		)
-		__field(	unsigned long,	msr		)
-		__field(	unsigned long,	dar		)
-		__field(	unsigned long,	last_inst	)
-	),
-
-	TP_fast_assign(
-		__entry->exit_nr	= exit_nr;
-		__entry->pc		= kvmppc_get_pc(vcpu);
-		__entry->dar		= kvmppc_get_fault_dar(vcpu);
-		__entry->msr		= vcpu->arch.shared->msr;
-		__entry->last_inst	= vcpu->arch.last_inst;
-	),
-
-	TP_printk("exit=%s"
-		" | pc=0x%lx"
-		" | msr=0x%lx"
-		" | dar=0x%lx"
-		" | last_inst=0x%lx"
-		,
-		__print_symbolic(__entry->exit_nr, kvm_trace_symbol_exit),
-		__entry->pc,
-		__entry->msr,
-		__entry->dar,
-		__entry->last_inst
-		)
-);
-
-TRACE_EVENT(kvm_unmap_hva,
-	TP_PROTO(unsigned long hva),
-	TP_ARGS(hva),
-
-	TP_STRUCT__entry(
-		__field(	unsigned long,	hva		)
-	),
-
-	TP_fast_assign(
-		__entry->hva		= hva;
-	),
-
-	TP_printk("unmap hva 0x%lx\n", __entry->hva)
-);
-#endif
-
 TRACE_EVENT(kvm_stlb_inval,
 	TP_PROTO(unsigned int stlb_index),
 	TP_ARGS(stlb_index),
@@ -226,100 +116,6 @@ TRACE_EVENT(kvm_check_requests,
 		__entry->cpu_nr, __entry->requests)
 );
 
-/*************************************************************************
- *                         Book3E trace points                           *
- *************************************************************************/
-
-#ifdef CONFIG_BOOKE
-
-TRACE_EVENT(kvm_booke206_stlb_write,
-	TP_PROTO(__u32 mas0, __u32 mas8, __u32 mas1, __u64 mas2, __u64 mas7_3),
-	TP_ARGS(mas0, mas8, mas1, mas2, mas7_3),
-
-	TP_STRUCT__entry(
-		__field(	__u32,	mas0		)
-		__field(	__u32,	mas8		)
-		__field(	__u32,	mas1		)
-		__field(	__u64,	mas2		)
-		__field(	__u64,	mas7_3		)
-	),
-
-	TP_fast_assign(
-		__entry->mas0		= mas0;
-		__entry->mas8		= mas8;
-		__entry->mas1		= mas1;
-		__entry->mas2		= mas2;
-		__entry->mas7_3		= mas7_3;
-	),
-
-	TP_printk("mas0=%x mas8=%x mas1=%x mas2=%llx mas7_3=%llx",
-		__entry->mas0, __entry->mas8, __entry->mas1,
-		__entry->mas2, __entry->mas7_3)
-);
-
-TRACE_EVENT(kvm_booke206_gtlb_write,
-	TP_PROTO(__u32 mas0, __u32 mas1, __u64 mas2, __u64 mas7_3),
-	TP_ARGS(mas0, mas1, mas2, mas7_3),
-
-	TP_STRUCT__entry(
-		__field(	__u32,	mas0		)
-		__field(	__u32,	mas1		)
-		__field(	__u64,	mas2		)
-		__field(	__u64,	mas7_3		)
-	),
-
-	TP_fast_assign(
-		__entry->mas0		= mas0;
-		__entry->mas1		= mas1;
-		__entry->mas2		= mas2;
-		__entry->mas7_3		= mas7_3;
-	),
-
-	TP_printk("mas0=%x mas1=%x mas2=%llx mas7_3=%llx",
-		__entry->mas0, __entry->mas1,
-		__entry->mas2, __entry->mas7_3)
-);
-
-TRACE_EVENT(kvm_booke206_ref_release,
-	TP_PROTO(__u64 pfn, __u32 flags),
-	TP_ARGS(pfn, flags),
-
-	TP_STRUCT__entry(
-		__field(	__u64,	pfn		)
-		__field(	__u32,	flags		)
-	),
-
-	TP_fast_assign(
-		__entry->pfn		= pfn;
-		__entry->flags		= flags;
-	),
-
-	TP_printk("pfn=%llx flags=%x",
-		__entry->pfn, __entry->flags)
-);
-
-TRACE_EVENT(kvm_booke_queue_irqprio,
-	TP_PROTO(struct kvm_vcpu *vcpu, unsigned int priority),
-	TP_ARGS(vcpu, priority),
-
-	TP_STRUCT__entry(
-		__field(	__u32,	cpu_nr		)
-		__field(	__u32,	priority		)
-		__field(	unsigned long,	pending		)
-	),
-
-	TP_fast_assign(
-		__entry->cpu_nr		= vcpu->vcpu_id;
-		__entry->priority	= priority;
-		__entry->pending	= vcpu->arch.pending_exceptions;
-	),
-
-	TP_printk("vcpu=%x prio=%x pending=%lx",
-		__entry->cpu_nr, __entry->priority, __entry->pending)
-);
-
-#endif
-
 #endif /* _TRACE_KVM_H */
 
 /* This part must be outside protection */
diff --git a/arch/powerpc/kvm/trace_booke.h b/arch/powerpc/kvm/trace_booke.h
new file mode 100644
index 00000000000..f7537cf26ce
--- /dev/null
+++ b/arch/powerpc/kvm/trace_booke.h
@@ -0,0 +1,177 @@
+#if !defined(_TRACE_KVM_BOOKE_H) || defined(TRACE_HEADER_MULTI_READ)
+#define _TRACE_KVM_BOOKE_H
+
+#include <linux/tracepoint.h>
+
+#undef TRACE_SYSTEM
+#define TRACE_SYSTEM kvm_booke
+#define TRACE_INCLUDE_PATH .
+#define TRACE_INCLUDE_FILE trace_booke
+
+#define kvm_trace_symbol_exit \
+	{0, "CRITICAL"}, \
+	{1, "MACHINE_CHECK"}, \
+	{2, "DATA_STORAGE"}, \
+	{3, "INST_STORAGE"}, \
+	{4, "EXTERNAL"}, \
+	{5, "ALIGNMENT"}, \
+	{6, "PROGRAM"}, \
+	{7, "FP_UNAVAIL"}, \
+	{8, "SYSCALL"}, \
+	{9, "AP_UNAVAIL"}, \
+	{10, "DECREMENTER"}, \
+	{11, "FIT"}, \
+	{12, "WATCHDOG"}, \
+	{13, "DTLB_MISS"}, \
+	{14, "ITLB_MISS"}, \
+	{15, "DEBUG"}, \
+	{32, "SPE_UNAVAIL"}, \
+	{33, "SPE_FP_DATA"}, \
+	{34, "SPE_FP_ROUND"}, \
+	{35, "PERFORMANCE_MONITOR"}, \
+	{36, "DOORBELL"}, \
+	{37, "DOORBELL_CRITICAL"}, \
+	{38, "GUEST_DBELL"}, \
+	{39, "GUEST_DBELL_CRIT"}, \
+	{40, "HV_SYSCALL"}, \
+	{41, "HV_PRIV"}
+
+TRACE_EVENT(kvm_exit,
+	TP_PROTO(unsigned int exit_nr, struct kvm_vcpu *vcpu),
+	TP_ARGS(exit_nr, vcpu),
+
+	TP_STRUCT__entry(
+		__field(	unsigned int,	exit_nr		)
+		__field(	unsigned long,	pc		)
+		__field(	unsigned long,	msr		)
+		__field(	unsigned long,	dar		)
+		__field(	unsigned long,	last_inst	)
+	),
+
+	TP_fast_assign(
+		__entry->exit_nr	= exit_nr;
+		__entry->pc		= kvmppc_get_pc(vcpu);
+		__entry->dar		= kvmppc_get_fault_dar(vcpu);
+		__entry->msr		= vcpu->arch.shared->msr;
+		__entry->last_inst	= vcpu->arch.last_inst;
+	),
+
+	TP_printk("exit=%s"
+		" | pc=0x%lx"
+		" | msr=0x%lx"
+		" | dar=0x%lx"
+		" | last_inst=0x%lx"
+		,
+		__print_symbolic(__entry->exit_nr, kvm_trace_symbol_exit),
+		__entry->pc,
+		__entry->msr,
+		__entry->dar,
+		__entry->last_inst
+		)
+);
+
+TRACE_EVENT(kvm_unmap_hva,
+	TP_PROTO(unsigned long hva),
+	TP_ARGS(hva),
+
+	TP_STRUCT__entry(
+		__field(	unsigned long,	hva		)
+	),
+
+	TP_fast_assign(
+		__entry->hva		= hva;
+	),
+
+	TP_printk("unmap hva 0x%lx\n", __entry->hva)
+);
+
+TRACE_EVENT(kvm_booke206_stlb_write,
+	TP_PROTO(__u32 mas0, __u32 mas8, __u32 mas1, __u64 mas2, __u64 mas7_3),
+	TP_ARGS(mas0, mas8, mas1, mas2, mas7_3),
+
+	TP_STRUCT__entry(
+		__field(	__u32,	mas0		)
+		__field(	__u32,	mas8		)
+		__field(	__u32,	mas1		)
+		__field(	__u64,	mas2		)
+		__field(	__u64,	mas7_3		)
+	),
+
+	TP_fast_assign(
+		__entry->mas0		= mas0;
+		__entry->mas8		= mas8;
+		__entry->mas1		= mas1;
+		__entry->mas2		= mas2;
+		__entry->mas7_3		= mas7_3;
+	),
+
+	TP_printk("mas0=%x mas8=%x mas1=%x mas2=%llx mas7_3=%llx",
+		__entry->mas0, __entry->mas8, __entry->mas1,
+		__entry->mas2, __entry->mas7_3)
+);
+
+TRACE_EVENT(kvm_booke206_gtlb_write,
+	TP_PROTO(__u32 mas0, __u32 mas1, __u64 mas2, __u64 mas7_3),
+	TP_ARGS(mas0, mas1, mas2, mas7_3),
+
+	TP_STRUCT__entry(
+		__field(	__u32,	mas0		)
+		__field(	__u32,	mas1		)
+		__field(	__u64,	mas2		)
+		__field(	__u64,	mas7_3		)
+	),
+
+	TP_fast_assign(
+		__entry->mas0		= mas0;
+		__entry->mas1		= mas1;
+		__entry->mas2		= mas2;
+		__entry->mas7_3		= mas7_3;
+	),
+
+	TP_printk("mas0=%x mas1=%x mas2=%llx mas7_3=%llx",
+		__entry->mas0, __entry->mas1,
+		__entry->mas2, __entry->mas7_3)
+);
+
+TRACE_EVENT(kvm_booke206_ref_release,
+	TP_PROTO(__u64 pfn, __u32 flags),
+	TP_ARGS(pfn, flags),
+
+	TP_STRUCT__entry(
+		__field(	__u64,	pfn		)
+		__field(	__u32,	flags		)
+	),
+
+	TP_fast_assign(
+		__entry->pfn		= pfn;
+		__entry->flags		= flags;
+	),
+
+	TP_printk("pfn=%llx flags=%x",
+		__entry->pfn, __entry->flags)
+);
+
+TRACE_EVENT(kvm_booke_queue_irqprio,
+	TP_PROTO(struct kvm_vcpu *vcpu, unsigned int priority),
+	TP_ARGS(vcpu, priority),
+
+	TP_STRUCT__entry(
+		__field(	__u32,	cpu_nr		)
+		__field(	__u32,	priority		)
+		__field(	unsigned long,	pending		)
+	),
+
+	TP_fast_assign(
+		__entry->cpu_nr		= vcpu->vcpu_id;
+		__entry->priority	= priority;
+		__entry->pending	= vcpu->arch.pending_exceptions;
+	),
+
+	TP_printk("vcpu=%x prio=%x pending=%lx",
+		__entry->cpu_nr, __entry->priority, __entry->pending)
+);
+
+#endif
+
+/* This part must be outside protection */
+#include <trace/define_trace.h>
-- 
cgit v1.2.3-70-g09d2


From 2ba9f0d8875073a2ed802fca0c25c9bfc4338439 Mon Sep 17 00:00:00 2001
From: "Aneesh Kumar K.V" <aneesh.kumar@linux.vnet.ibm.com>
Date: Mon, 7 Oct 2013 22:17:59 +0530
Subject: kvm: powerpc: book3s: Support building HV and PR KVM as module

Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
[agraf: squash in compile fix]
Signed-off-by: Alexander Graf <agraf@suse.de>
---
 arch/powerpc/kvm/Kconfig          |  6 +++---
 arch/powerpc/kvm/Makefile         | 11 ++++++++---
 arch/powerpc/kvm/book3s.c         | 12 +++++++++++-
 arch/powerpc/kvm/book3s_emulate.c |  2 +-
 arch/powerpc/kvm/book3s_hv.c      |  2 ++
 arch/powerpc/kvm/book3s_pr.c      |  5 ++++-
 arch/powerpc/kvm/book3s_rtas.c    |  1 +
 arch/powerpc/kvm/book3s_xics.c    |  1 +
 arch/powerpc/kvm/emulate.c        |  1 +
 arch/powerpc/kvm/powerpc.c        | 10 ++++++++++
 virt/kvm/kvm_main.c               |  4 ++++
 11 files changed, 46 insertions(+), 9 deletions(-)

(limited to 'arch/powerpc/kvm')

diff --git a/arch/powerpc/kvm/Kconfig b/arch/powerpc/kvm/Kconfig
index a96d7c32f78..8aeeda1ff42 100644
--- a/arch/powerpc/kvm/Kconfig
+++ b/arch/powerpc/kvm/Kconfig
@@ -73,7 +73,7 @@ config KVM_BOOK3S_64
 	  If unsure, say N.
 
 config KVM_BOOK3S_64_HV
-	bool "KVM support for POWER7 and PPC970 using hypervisor mode in host"
+	tristate "KVM support for POWER7 and PPC970 using hypervisor mode in host"
 	depends on KVM_BOOK3S_64
 	select KVM_BOOK3S_HV_POSSIBLE
 	select MMU_NOTIFIER
@@ -94,8 +94,8 @@ config KVM_BOOK3S_64_HV
 	  If unsure, say N.
 
 config KVM_BOOK3S_64_PR
-	bool "KVM support without using hypervisor mode in host"
-	depends on KVM_BOOK3S_64 && !KVM_BOOK3S_64_HV
+	tristate "KVM support without using hypervisor mode in host"
+	depends on KVM_BOOK3S_64
 	select KVM_BOOK3S_PR_POSSIBLE
 	---help---
 	  Support running guest kernels in virtual machines on processors
diff --git a/arch/powerpc/kvm/Makefile b/arch/powerpc/kvm/Makefile
index fa17b337bb9..ce569b6bf4d 100644
--- a/arch/powerpc/kvm/Makefile
+++ b/arch/powerpc/kvm/Makefile
@@ -56,7 +56,7 @@ kvm-objs-$(CONFIG_KVM_E500MC) := $(kvm-e500mc-objs)
 kvm-book3s_64-builtin-objs-$(CONFIG_KVM_BOOK3S_64_HANDLER) := \
 	book3s_64_vio_hv.o
 
-kvm-book3s_64-objs-$(CONFIG_KVM_BOOK3S_64_PR) := \
+kvm-pr-y := \
 	fpu.o \
 	book3s_paired_singles.o \
 	book3s_pr.o \
@@ -76,7 +76,7 @@ kvm-book3s_64-builtin-objs-$(CONFIG_KVM_BOOK3S_64_HANDLER) += \
 	book3s_rmhandlers.o
 endif
 
-kvm-book3s_64-objs-$(CONFIG_KVM_BOOK3S_64_HV)  += \
+kvm-hv-y += \
 	book3s_hv.o \
 	book3s_hv_interrupts.o \
 	book3s_64_mmu_hv.o
@@ -84,13 +84,15 @@ kvm-book3s_64-objs-$(CONFIG_KVM_BOOK3S_64_HV)  += \
 kvm-book3s_64-builtin-xics-objs-$(CONFIG_KVM_XICS) := \
 	book3s_hv_rm_xics.o
 
-kvm-book3s_64-builtin-objs-$(CONFIG_KVM_BOOK3S_64_HV) += \
+ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE
+kvm-book3s_64-builtin-objs-$(CONFIG_KVM_BOOK3S_64_HANDLER) += \
 	book3s_hv_rmhandlers.o \
 	book3s_hv_rm_mmu.o \
 	book3s_hv_ras.o \
 	book3s_hv_builtin.o \
 	book3s_hv_cma.o \
 	$(kvm-book3s_64-builtin-xics-objs-y)
+endif
 
 kvm-book3s_64-objs-$(CONFIG_KVM_XICS) += \
 	book3s_xics.o
@@ -131,4 +133,7 @@ obj-$(CONFIG_KVM_E500MC) += kvm.o
 obj-$(CONFIG_KVM_BOOK3S_64) += kvm.o
 obj-$(CONFIG_KVM_BOOK3S_32) += kvm.o
 
+obj-$(CONFIG_KVM_BOOK3S_64_PR) += kvm-pr.o
+obj-$(CONFIG_KVM_BOOK3S_64_HV) += kvm-hv.o
+
 obj-y += $(kvm-book3s_64-builtin-objs-y)
diff --git a/arch/powerpc/kvm/book3s.c b/arch/powerpc/kvm/book3s.c
index 493aff77f84..39d2994f9d2 100644
--- a/arch/powerpc/kvm/book3s.c
+++ b/arch/powerpc/kvm/book3s.c
@@ -170,28 +170,32 @@ void kvmppc_book3s_queue_irqprio(struct kvm_vcpu *vcpu, unsigned int vec)
 	printk(KERN_INFO "Queueing interrupt %x\n", vec);
 #endif
 }
-
+EXPORT_SYMBOL_GPL(kvmppc_book3s_queue_irqprio);
 
 void kvmppc_core_queue_program(struct kvm_vcpu *vcpu, ulong flags)
 {
 	/* might as well deliver this straight away */
 	kvmppc_inject_interrupt(vcpu, BOOK3S_INTERRUPT_PROGRAM, flags);
 }
+EXPORT_SYMBOL_GPL(kvmppc_core_queue_program);
 
 void kvmppc_core_queue_dec(struct kvm_vcpu *vcpu)
 {
 	kvmppc_book3s_queue_irqprio(vcpu, BOOK3S_INTERRUPT_DECREMENTER);
 }
+EXPORT_SYMBOL_GPL(kvmppc_core_queue_dec);
 
 int kvmppc_core_pending_dec(struct kvm_vcpu *vcpu)
 {
 	return test_bit(BOOK3S_IRQPRIO_DECREMENTER, &vcpu->arch.pending_exceptions);
 }
+EXPORT_SYMBOL_GPL(kvmppc_core_pending_dec);
 
 void kvmppc_core_dequeue_dec(struct kvm_vcpu *vcpu)
 {
 	kvmppc_book3s_dequeue_irqprio(vcpu, BOOK3S_INTERRUPT_DECREMENTER);
 }
+EXPORT_SYMBOL_GPL(kvmppc_core_dequeue_dec);
 
 void kvmppc_core_queue_external(struct kvm_vcpu *vcpu,
                                 struct kvm_interrupt *irq)
@@ -329,6 +333,7 @@ int kvmppc_core_prepare_to_enter(struct kvm_vcpu *vcpu)
 
 	return 0;
 }
+EXPORT_SYMBOL_GPL(kvmppc_core_prepare_to_enter);
 
 pfn_t kvmppc_gfn_to_pfn(struct kvm_vcpu *vcpu, gfn_t gfn, bool writing,
 			bool *writable)
@@ -354,6 +359,7 @@ pfn_t kvmppc_gfn_to_pfn(struct kvm_vcpu *vcpu, gfn_t gfn, bool writing,
 
 	return gfn_to_pfn_prot(vcpu->kvm, gfn, writing, writable);
 }
+EXPORT_SYMBOL_GPL(kvmppc_gfn_to_pfn);
 
 static int kvmppc_xlate(struct kvm_vcpu *vcpu, ulong eaddr, bool data,
 			bool iswrite, struct kvmppc_pte *pte)
@@ -421,6 +427,7 @@ int kvmppc_st(struct kvm_vcpu *vcpu, ulong *eaddr, int size, void *ptr,
 
 	return EMULATE_DONE;
 }
+EXPORT_SYMBOL_GPL(kvmppc_st);
 
 int kvmppc_ld(struct kvm_vcpu *vcpu, ulong *eaddr, int size, void *ptr,
 		      bool data)
@@ -451,6 +458,7 @@ nopte:
 mmio:
 	return EMULATE_DO_MMIO;
 }
+EXPORT_SYMBOL_GPL(kvmppc_ld);
 
 int kvm_arch_vcpu_setup(struct kvm_vcpu *vcpu)
 {
@@ -706,6 +714,7 @@ void kvmppc_set_msr(struct kvm_vcpu *vcpu, u64 msr)
 {
 	kvmppc_ops->set_msr(vcpu, msr);
 }
+EXPORT_SYMBOL_GPL(kvmppc_set_msr);
 
 int kvmppc_vcpu_run(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu)
 {
@@ -787,6 +796,7 @@ int kvm_unmap_hva(struct kvm *kvm, unsigned long hva)
 {
 	return kvmppc_ops->unmap_hva(kvm, hva);
 }
+EXPORT_SYMBOL_GPL(kvm_unmap_hva);
 
 int kvm_unmap_hva_range(struct kvm *kvm, unsigned long start, unsigned long end)
 {
diff --git a/arch/powerpc/kvm/book3s_emulate.c b/arch/powerpc/kvm/book3s_emulate.c
index b9841ad844f..99d40f8977e 100644
--- a/arch/powerpc/kvm/book3s_emulate.c
+++ b/arch/powerpc/kvm/book3s_emulate.c
@@ -172,7 +172,7 @@ int kvmppc_core_emulate_op_pr(struct kvm_run *run, struct kvm_vcpu *vcpu,
 			vcpu->arch.mmu.tlbie(vcpu, addr, large);
 			break;
 		}
-#ifdef CONFIG_KVM_BOOK3S_64_PR
+#ifdef CONFIG_PPC_BOOK3S_64
 		case OP_31_XOP_FAKE_SC1:
 		{
 			/* SC 1 papr hypercalls */
diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c
index 0782c8688c8..9e954a81c07 100644
--- a/arch/powerpc/kvm/book3s_hv.c
+++ b/arch/powerpc/kvm/book3s_hv.c
@@ -52,6 +52,7 @@
 #include <linux/vmalloc.h>
 #include <linux/highmem.h>
 #include <linux/hugetlb.h>
+#include <linux/module.h>
 
 #include "book3s.h"
 
@@ -2215,3 +2216,4 @@ static void kvmppc_book3s_exit_hv(void)
 
 module_init(kvmppc_book3s_init_hv);
 module_exit(kvmppc_book3s_exit_hv);
+MODULE_LICENSE("GPL");
diff --git a/arch/powerpc/kvm/book3s_pr.c b/arch/powerpc/kvm/book3s_pr.c
index ca6c73d2ee7..7f583a48216 100644
--- a/arch/powerpc/kvm/book3s_pr.c
+++ b/arch/powerpc/kvm/book3s_pr.c
@@ -40,6 +40,7 @@
 #include <linux/sched.h>
 #include <linux/vmalloc.h>
 #include <linux/highmem.h>
+#include <linux/module.h>
 
 #include "book3s.h"
 
@@ -918,7 +919,7 @@ program_interrupt:
 			ulong cmd = kvmppc_get_gpr(vcpu, 3);
 			int i;
 
-#ifdef CONFIG_KVM_BOOK3S_64_PR
+#ifdef CONFIG_PPC_BOOK3S_64
 			if (kvmppc_h_pr(vcpu, cmd) == EMULATE_DONE) {
 				r = RESUME_GUEST;
 				break;
@@ -1582,3 +1583,5 @@ static void kvmppc_book3s_exit_pr(void)
 
 module_init(kvmppc_book3s_init_pr);
 module_exit(kvmppc_book3s_exit_pr);
+
+MODULE_LICENSE("GPL");
diff --git a/arch/powerpc/kvm/book3s_rtas.c b/arch/powerpc/kvm/book3s_rtas.c
index 3219ba89524..cf95cdef73c 100644
--- a/arch/powerpc/kvm/book3s_rtas.c
+++ b/arch/powerpc/kvm/book3s_rtas.c
@@ -260,6 +260,7 @@ fail:
 	 */
 	return rc;
 }
+EXPORT_SYMBOL_GPL(kvmppc_rtas_hcall);
 
 void kvmppc_rtas_tokens_free(struct kvm *kvm)
 {
diff --git a/arch/powerpc/kvm/book3s_xics.c b/arch/powerpc/kvm/book3s_xics.c
index cef3de96ff6..c3c832b27ee 100644
--- a/arch/powerpc/kvm/book3s_xics.c
+++ b/arch/powerpc/kvm/book3s_xics.c
@@ -840,6 +840,7 @@ int kvmppc_xics_hcall(struct kvm_vcpu *vcpu, u32 req)
 
 	return rc;
 }
+EXPORT_SYMBOL_GPL(kvmppc_xics_hcall);
 
 
 /* -- Initialisation code etc. -- */
diff --git a/arch/powerpc/kvm/emulate.c b/arch/powerpc/kvm/emulate.c
index 81762eb7957..de9a340d22e 100644
--- a/arch/powerpc/kvm/emulate.c
+++ b/arch/powerpc/kvm/emulate.c
@@ -483,3 +483,4 @@ int kvmppc_emulate_instruction(struct kvm_run *run, struct kvm_vcpu *vcpu)
 
 	return emulated;
 }
+EXPORT_SYMBOL_GPL(kvmppc_emulate_instruction);
diff --git a/arch/powerpc/kvm/powerpc.c b/arch/powerpc/kvm/powerpc.c
index 874a2a5e6ce..9aaa07efa4b 100644
--- a/arch/powerpc/kvm/powerpc.c
+++ b/arch/powerpc/kvm/powerpc.c
@@ -126,6 +126,7 @@ int kvmppc_prepare_to_enter(struct kvm_vcpu *vcpu)
 
 	return r;
 }
+EXPORT_SYMBOL_GPL(kvmppc_prepare_to_enter);
 
 int kvmppc_kvm_pv(struct kvm_vcpu *vcpu)
 {
@@ -179,6 +180,7 @@ int kvmppc_kvm_pv(struct kvm_vcpu *vcpu)
 
 	return r;
 }
+EXPORT_SYMBOL_GPL(kvmppc_kvm_pv);
 
 int kvmppc_sanity_check(struct kvm_vcpu *vcpu)
 {
@@ -207,6 +209,7 @@ out:
 	vcpu->arch.sane = r;
 	return r ? 0 : -EINVAL;
 }
+EXPORT_SYMBOL_GPL(kvmppc_sanity_check);
 
 int kvmppc_emulate_mmio(struct kvm_run *run, struct kvm_vcpu *vcpu)
 {
@@ -241,6 +244,7 @@ int kvmppc_emulate_mmio(struct kvm_run *run, struct kvm_vcpu *vcpu)
 
 	return r;
 }
+EXPORT_SYMBOL_GPL(kvmppc_emulate_mmio);
 
 int kvm_arch_hardware_enable(void *garbage)
 {
@@ -665,6 +669,7 @@ int kvmppc_handle_load(struct kvm_run *run, struct kvm_vcpu *vcpu,
 
 	return EMULATE_DO_MMIO;
 }
+EXPORT_SYMBOL_GPL(kvmppc_handle_load);
 
 /* Same as above, but sign extends */
 int kvmppc_handle_loads(struct kvm_run *run, struct kvm_vcpu *vcpu,
@@ -726,6 +731,7 @@ int kvmppc_handle_store(struct kvm_run *run, struct kvm_vcpu *vcpu,
 
 	return EMULATE_DO_MMIO;
 }
+EXPORT_SYMBOL_GPL(kvmppc_handle_store);
 
 int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *run)
 {
@@ -1074,22 +1080,26 @@ long kvmppc_alloc_lpid(void)
 
 	return lpid;
 }
+EXPORT_SYMBOL_GPL(kvmppc_alloc_lpid);
 
 void kvmppc_claim_lpid(long lpid)
 {
 	set_bit(lpid, lpid_inuse);
 }
+EXPORT_SYMBOL_GPL(kvmppc_claim_lpid);
 
 void kvmppc_free_lpid(long lpid)
 {
 	clear_bit(lpid, lpid_inuse);
 }
+EXPORT_SYMBOL_GPL(kvmppc_free_lpid);
 
 void kvmppc_init_lpid(unsigned long nr_lpids_param)
 {
 	nr_lpids = min_t(unsigned long, KVMPPC_NR_LPIDS, nr_lpids_param);
 	memset(lpid_inuse, 0, sizeof(lpid_inuse));
 }
+EXPORT_SYMBOL_GPL(kvmppc_init_lpid);
 
 int kvm_arch_init(void *opaque)
 {
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index d469114aff0..94c6e3f6f24 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -187,6 +187,7 @@ void kvm_flush_remote_tlbs(struct kvm *kvm)
 		++kvm->stat.remote_tlb_flush;
 	cmpxchg(&kvm->tlbs_dirty, dirty_count, 0);
 }
+EXPORT_SYMBOL_GPL(kvm_flush_remote_tlbs);
 
 void kvm_reload_remote_mmus(struct kvm *kvm)
 {
@@ -965,6 +966,7 @@ int kvm_get_dirty_log(struct kvm *kvm,
 out:
 	return r;
 }
+EXPORT_SYMBOL_GPL(kvm_get_dirty_log);
 
 bool kvm_largepages_enabled(void)
 {
@@ -1653,6 +1655,7 @@ void mark_page_dirty(struct kvm *kvm, gfn_t gfn)
 	memslot = gfn_to_memslot(kvm, gfn);
 	mark_page_dirty_in_slot(kvm, memslot, gfn);
 }
+EXPORT_SYMBOL_GPL(mark_page_dirty);
 
 /*
  * The vCPU has executed a HLT instruction with in-kernel mode enabled.
@@ -1678,6 +1681,7 @@ void kvm_vcpu_block(struct kvm_vcpu *vcpu)
 
 	finish_wait(&vcpu->wq, &wait);
 }
+EXPORT_SYMBOL_GPL(kvm_vcpu_block);
 
 #ifndef CONFIG_S390
 /*
-- 
cgit v1.2.3-70-g09d2


From 5587027ce9d59a57aecaa190be1c8e560aaff45d Mon Sep 17 00:00:00 2001
From: "Aneesh Kumar K.V" <aneesh.kumar@linux.vnet.ibm.com>
Date: Mon, 7 Oct 2013 22:18:00 +0530
Subject: kvm: Add struct kvm arg to memslot APIs

We will use that in the later patch to find the kvm ops handler

Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
Signed-off-by: Alexander Graf <agraf@suse.de>
---
 arch/arm/kvm/arm.c                 |  5 +++--
 arch/ia64/kvm/kvm-ia64.c           |  5 +++--
 arch/mips/kvm/kvm_mips.c           |  5 +++--
 arch/powerpc/include/asm/kvm_ppc.h |  6 ++++--
 arch/powerpc/kvm/book3s.c          |  4 ++--
 arch/powerpc/kvm/booke.c           |  4 ++--
 arch/powerpc/kvm/powerpc.c         |  9 +++++----
 arch/s390/kvm/kvm-s390.c           |  5 +++--
 arch/x86/kvm/x86.c                 |  5 +++--
 include/linux/kvm_host.h           |  5 +++--
 virt/kvm/kvm_main.c                | 12 ++++++------
 11 files changed, 37 insertions(+), 28 deletions(-)

(limited to 'arch/powerpc/kvm')

diff --git a/arch/arm/kvm/arm.c b/arch/arm/kvm/arm.c
index cc5adb9349e..e312e4a53f8 100644
--- a/arch/arm/kvm/arm.c
+++ b/arch/arm/kvm/arm.c
@@ -152,12 +152,13 @@ int kvm_arch_vcpu_fault(struct kvm_vcpu *vcpu, struct vm_fault *vmf)
 	return VM_FAULT_SIGBUS;
 }
 
-void kvm_arch_free_memslot(struct kvm_memory_slot *free,
+void kvm_arch_free_memslot(struct kvm *kvm, struct kvm_memory_slot *free,
 			   struct kvm_memory_slot *dont)
 {
 }
 
-int kvm_arch_create_memslot(struct kvm_memory_slot *slot, unsigned long npages)
+int kvm_arch_create_memslot(struct kvm *kvm, struct kvm_memory_slot *slot,
+			    unsigned long npages)
 {
 	return 0;
 }
diff --git a/arch/ia64/kvm/kvm-ia64.c b/arch/ia64/kvm/kvm-ia64.c
index bdfd8789b37..985bf80c622 100644
--- a/arch/ia64/kvm/kvm-ia64.c
+++ b/arch/ia64/kvm/kvm-ia64.c
@@ -1550,12 +1550,13 @@ int kvm_arch_vcpu_fault(struct kvm_vcpu *vcpu, struct vm_fault *vmf)
 	return VM_FAULT_SIGBUS;
 }
 
-void kvm_arch_free_memslot(struct kvm_memory_slot *free,
+void kvm_arch_free_memslot(struct kvm *kvm, struct kvm_memory_slot *free,
 			   struct kvm_memory_slot *dont)
 {
 }
 
-int kvm_arch_create_memslot(struct kvm_memory_slot *slot, unsigned long npages)
+int kvm_arch_create_memslot(struct kvm *kvm, struct kvm_memory_slot *slot,
+			    unsigned long npages)
 {
 	return 0;
 }
diff --git a/arch/mips/kvm/kvm_mips.c b/arch/mips/kvm/kvm_mips.c
index a7b044536de..73b34827826 100644
--- a/arch/mips/kvm/kvm_mips.c
+++ b/arch/mips/kvm/kvm_mips.c
@@ -198,12 +198,13 @@ kvm_arch_dev_ioctl(struct file *filp, unsigned int ioctl, unsigned long arg)
 	return -ENOIOCTLCMD;
 }
 
-void kvm_arch_free_memslot(struct kvm_memory_slot *free,
+void kvm_arch_free_memslot(struct kvm *kvm, struct kvm_memory_slot *free,
 			   struct kvm_memory_slot *dont)
 {
 }
 
-int kvm_arch_create_memslot(struct kvm_memory_slot *slot, unsigned long npages)
+int kvm_arch_create_memslot(struct kvm *kvm, struct kvm_memory_slot *slot,
+			    unsigned long npages)
 {
 	return 0;
 }
diff --git a/arch/powerpc/include/asm/kvm_ppc.h b/arch/powerpc/include/asm/kvm_ppc.h
index c13f15db476..20f46163709 100644
--- a/arch/powerpc/include/asm/kvm_ppc.h
+++ b/arch/powerpc/include/asm/kvm_ppc.h
@@ -134,9 +134,11 @@ extern struct page *kvm_alloc_hpt(unsigned long nr_pages);
 extern void kvm_release_hpt(struct page *page, unsigned long nr_pages);
 extern int kvmppc_core_init_vm(struct kvm *kvm);
 extern void kvmppc_core_destroy_vm(struct kvm *kvm);
-extern void kvmppc_core_free_memslot(struct kvm_memory_slot *free,
+extern void kvmppc_core_free_memslot(struct kvm *kvm,
+				     struct kvm_memory_slot *free,
 				     struct kvm_memory_slot *dont);
-extern int kvmppc_core_create_memslot(struct kvm_memory_slot *slot,
+extern int kvmppc_core_create_memslot(struct kvm *kvm,
+				      struct kvm_memory_slot *slot,
 				      unsigned long npages);
 extern int kvmppc_core_prepare_memory_region(struct kvm *kvm,
 				struct kvm_memory_slot *memslot,
diff --git a/arch/powerpc/kvm/book3s.c b/arch/powerpc/kvm/book3s.c
index 39d2994f9d2..130fe1d75ba 100644
--- a/arch/powerpc/kvm/book3s.c
+++ b/arch/powerpc/kvm/book3s.c
@@ -761,13 +761,13 @@ int kvm_vm_ioctl_get_dirty_log(struct kvm *kvm, struct kvm_dirty_log *log)
 	return kvmppc_ops->get_dirty_log(kvm, log);
 }
 
-void kvmppc_core_free_memslot(struct kvm_memory_slot *free,
+void kvmppc_core_free_memslot(struct kvm *kvm, struct kvm_memory_slot *free,
 			      struct kvm_memory_slot *dont)
 {
 	kvmppc_ops->free_memslot(free, dont);
 }
 
-int kvmppc_core_create_memslot(struct kvm_memory_slot *slot,
+int kvmppc_core_create_memslot(struct kvm *kvm, struct kvm_memory_slot *slot,
 			       unsigned long npages)
 {
 	return kvmppc_ops->create_memslot(slot, npages);
diff --git a/arch/powerpc/kvm/booke.c b/arch/powerpc/kvm/booke.c
index 1769354d0bf..cb2d986a338 100644
--- a/arch/powerpc/kvm/booke.c
+++ b/arch/powerpc/kvm/booke.c
@@ -1662,12 +1662,12 @@ int kvm_vm_ioctl_get_dirty_log(struct kvm *kvm, struct kvm_dirty_log *log)
 	return -ENOTSUPP;
 }
 
-void kvmppc_core_free_memslot(struct kvm_memory_slot *free,
+void kvmppc_core_free_memslot(struct kvm *kvm, struct kvm_memory_slot *free,
 			      struct kvm_memory_slot *dont)
 {
 }
 
-int kvmppc_core_create_memslot(struct kvm_memory_slot *slot,
+int kvmppc_core_create_memslot(struct kvm *kvm, struct kvm_memory_slot *slot,
 			       unsigned long npages)
 {
 	return 0;
diff --git a/arch/powerpc/kvm/powerpc.c b/arch/powerpc/kvm/powerpc.c
index 9aaa07efa4b..b103d747934 100644
--- a/arch/powerpc/kvm/powerpc.c
+++ b/arch/powerpc/kvm/powerpc.c
@@ -417,15 +417,16 @@ long kvm_arch_dev_ioctl(struct file *filp,
 	return -EINVAL;
 }
 
-void kvm_arch_free_memslot(struct kvm_memory_slot *free,
+void kvm_arch_free_memslot(struct kvm *kvm, struct kvm_memory_slot *free,
 			   struct kvm_memory_slot *dont)
 {
-	kvmppc_core_free_memslot(free, dont);
+	kvmppc_core_free_memslot(kvm, free, dont);
 }
 
-int kvm_arch_create_memslot(struct kvm_memory_slot *slot, unsigned long npages)
+int kvm_arch_create_memslot(struct kvm *kvm, struct kvm_memory_slot *slot,
+			    unsigned long npages)
 {
-	return kvmppc_core_create_memslot(slot, npages);
+	return kvmppc_core_create_memslot(kvm, slot, npages);
 }
 
 void kvm_arch_memslots_updated(struct kvm *kvm)
diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c
index 1e4e7b97337..bedda67cc22 100644
--- a/arch/s390/kvm/kvm-s390.c
+++ b/arch/s390/kvm/kvm-s390.c
@@ -1089,12 +1089,13 @@ int kvm_arch_vcpu_fault(struct kvm_vcpu *vcpu, struct vm_fault *vmf)
 	return VM_FAULT_SIGBUS;
 }
 
-void kvm_arch_free_memslot(struct kvm_memory_slot *free,
+void kvm_arch_free_memslot(struct kvm *kvm, struct kvm_memory_slot *free,
 			   struct kvm_memory_slot *dont)
 {
 }
 
-int kvm_arch_create_memslot(struct kvm_memory_slot *slot, unsigned long npages)
+int kvm_arch_create_memslot(struct kvm *kvm, struct kvm_memory_slot *slot,
+			    unsigned long npages)
 {
 	return 0;
 }
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index edf2a07df3a..666526a55c4 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -7080,7 +7080,7 @@ void kvm_arch_destroy_vm(struct kvm *kvm)
 	kfree(rcu_dereference_check(kvm->arch.apic_map, 1));
 }
 
-void kvm_arch_free_memslot(struct kvm_memory_slot *free,
+void kvm_arch_free_memslot(struct kvm *kvm, struct kvm_memory_slot *free,
 			   struct kvm_memory_slot *dont)
 {
 	int i;
@@ -7101,7 +7101,8 @@ void kvm_arch_free_memslot(struct kvm_memory_slot *free,
 	}
 }
 
-int kvm_arch_create_memslot(struct kvm_memory_slot *slot, unsigned long npages)
+int kvm_arch_create_memslot(struct kvm *kvm, struct kvm_memory_slot *slot,
+			    unsigned long npages)
 {
 	int i;
 
diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index c9d4236ab44..8b0107dc206 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -507,9 +507,10 @@ int kvm_set_memory_region(struct kvm *kvm,
 			  struct kvm_userspace_memory_region *mem);
 int __kvm_set_memory_region(struct kvm *kvm,
 			    struct kvm_userspace_memory_region *mem);
-void kvm_arch_free_memslot(struct kvm_memory_slot *free,
+void kvm_arch_free_memslot(struct kvm *kvm, struct kvm_memory_slot *free,
 			   struct kvm_memory_slot *dont);
-int kvm_arch_create_memslot(struct kvm_memory_slot *slot, unsigned long npages);
+int kvm_arch_create_memslot(struct kvm *kvm, struct kvm_memory_slot *slot,
+			    unsigned long npages);
 void kvm_arch_memslots_updated(struct kvm *kvm);
 int kvm_arch_prepare_memory_region(struct kvm *kvm,
 				struct kvm_memory_slot *memslot,
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index 94c6e3f6f24..0932c3b6415 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -542,13 +542,13 @@ static void kvm_destroy_dirty_bitmap(struct kvm_memory_slot *memslot)
 /*
  * Free any memory in @free but not in @dont.
  */
-static void kvm_free_physmem_slot(struct kvm_memory_slot *free,
+static void kvm_free_physmem_slot(struct kvm *kvm, struct kvm_memory_slot *free,
 				  struct kvm_memory_slot *dont)
 {
 	if (!dont || free->dirty_bitmap != dont->dirty_bitmap)
 		kvm_destroy_dirty_bitmap(free);
 
-	kvm_arch_free_memslot(free, dont);
+	kvm_arch_free_memslot(kvm, free, dont);
 
 	free->npages = 0;
 }
@@ -559,7 +559,7 @@ void kvm_free_physmem(struct kvm *kvm)
 	struct kvm_memory_slot *memslot;
 
 	kvm_for_each_memslot(memslot, slots)
-		kvm_free_physmem_slot(memslot, NULL);
+		kvm_free_physmem_slot(kvm, memslot, NULL);
 
 	kfree(kvm->memslots);
 }
@@ -823,7 +823,7 @@ int __kvm_set_memory_region(struct kvm *kvm,
 	if (change == KVM_MR_CREATE) {
 		new.userspace_addr = mem->userspace_addr;
 
-		if (kvm_arch_create_memslot(&new, npages))
+		if (kvm_arch_create_memslot(kvm, &new, npages))
 			goto out_free;
 	}
 
@@ -899,7 +899,7 @@ int __kvm_set_memory_region(struct kvm *kvm,
 
 	kvm_arch_commit_memory_region(kvm, mem, &old, change);
 
-	kvm_free_physmem_slot(&old, &new);
+	kvm_free_physmem_slot(kvm, &old, &new);
 	kfree(old_memslots);
 
 	return 0;
@@ -907,7 +907,7 @@ int __kvm_set_memory_region(struct kvm *kvm,
 out_slots:
 	kfree(slots);
 out_free:
-	kvm_free_physmem_slot(&new, &old);
+	kvm_free_physmem_slot(kvm, &new, &old);
 out:
 	return r;
 }
-- 
cgit v1.2.3-70-g09d2


From cbbc58d4fdfab1a39a6ac1b41fcb17885952157a Mon Sep 17 00:00:00 2001
From: "Aneesh Kumar K.V" <aneesh.kumar@linux.vnet.ibm.com>
Date: Mon, 7 Oct 2013 22:18:01 +0530
Subject: kvm: powerpc: book3s: Allow the HV and PR selection per virtual
 machine

This moves the kvmppc_ops callbacks to be a per VM entity. This
enables us to select HV and PR mode when creating a VM. We also
allow both kvm-hv and kvm-pr kernel module to be loaded. To
achieve this we move /dev/kvm ownership to kvm.ko module. Depending on
which KVM mode we select during VM creation we take a reference
count on respective module

Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
[agraf: fix coding style]
Signed-off-by: Alexander Graf <agraf@suse.de>
---
 arch/powerpc/include/asm/kvm_host.h |  1 +
 arch/powerpc/include/asm/kvm_ppc.h  |  7 +--
 arch/powerpc/kvm/44x.c              |  7 ++-
 arch/powerpc/kvm/book3s.c           | 89 +++++++++++++++++++++++++------------
 arch/powerpc/kvm/book3s.h           |  2 +
 arch/powerpc/kvm/book3s_hv.c        | 18 ++++----
 arch/powerpc/kvm/book3s_pr.c        | 25 +++++++----
 arch/powerpc/kvm/book3s_xics.c      |  2 +-
 arch/powerpc/kvm/booke.c            | 22 ++++-----
 arch/powerpc/kvm/e500.c             |  8 +++-
 arch/powerpc/kvm/e500mc.c           |  6 ++-
 arch/powerpc/kvm/emulate.c          | 11 ++---
 arch/powerpc/kvm/powerpc.c          | 76 ++++++++++++++++++++++---------
 include/uapi/linux/kvm.h            |  4 ++
 14 files changed, 187 insertions(+), 91 deletions(-)

(limited to 'arch/powerpc/kvm')

diff --git a/arch/powerpc/include/asm/kvm_host.h b/arch/powerpc/include/asm/kvm_host.h
index 61ce4dca45d..237d1d25b44 100644
--- a/arch/powerpc/include/asm/kvm_host.h
+++ b/arch/powerpc/include/asm/kvm_host.h
@@ -270,6 +270,7 @@ struct kvm_arch {
 #ifdef CONFIG_KVM_XICS
 	struct kvmppc_xics *xics;
 #endif
+	struct kvmppc_ops *kvm_ops;
 };
 
 /*
diff --git a/arch/powerpc/include/asm/kvm_ppc.h b/arch/powerpc/include/asm/kvm_ppc.h
index 20f46163709..3069cf4dcc8 100644
--- a/arch/powerpc/include/asm/kvm_ppc.h
+++ b/arch/powerpc/include/asm/kvm_ppc.h
@@ -182,6 +182,7 @@ union kvmppc_one_reg {
 };
 
 struct kvmppc_ops {
+	struct module *owner;
 	bool is_hv_enabled;
 	int (*get_sregs)(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs);
 	int (*set_sregs)(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs);
@@ -217,7 +218,6 @@ struct kvmppc_ops {
 			      unsigned long npages);
 	int (*init_vm)(struct kvm *kvm);
 	void (*destroy_vm)(struct kvm *kvm);
-	int (*check_processor_compat)(void);
 	int (*get_smmu_info)(struct kvm *kvm, struct kvm_ppc_smmu_info *info);
 	int (*emulate_op)(struct kvm_run *run, struct kvm_vcpu *vcpu,
 			  unsigned int inst, int *advance);
@@ -229,7 +229,8 @@ struct kvmppc_ops {
 
 };
 
-extern struct kvmppc_ops *kvmppc_ops;
+extern struct kvmppc_ops *kvmppc_hv_ops;
+extern struct kvmppc_ops *kvmppc_pr_ops;
 
 /*
  * Cuts out inst bits with ordering according to spec.
@@ -326,7 +327,7 @@ static inline void kvmppc_set_host_ipi(int cpu, u8 host_ipi)
 
 static inline void kvmppc_fast_vcpu_kick(struct kvm_vcpu *vcpu)
 {
-	kvmppc_ops->fast_vcpu_kick(vcpu);
+	vcpu->kvm->arch.kvm_ops->fast_vcpu_kick(vcpu);
 }
 
 #else
diff --git a/arch/powerpc/kvm/44x.c b/arch/powerpc/kvm/44x.c
index a765bcd74fb..93221e87b91 100644
--- a/arch/powerpc/kvm/44x.c
+++ b/arch/powerpc/kvm/44x.c
@@ -213,16 +213,19 @@ static int __init kvmppc_44x_init(void)
 	if (r)
 		goto err_out;
 
-	r = kvm_init(&kvm_ops_44x, sizeof(struct kvmppc_vcpu_44x),
-		     0, THIS_MODULE);
+	r = kvm_init(NULL, sizeof(struct kvmppc_vcpu_44x), 0, THIS_MODULE);
 	if (r)
 		goto err_out;
+	kvm_ops_44x.owner = THIS_MODULE;
+	kvmppc_pr_ops = &kvm_ops_44x;
+
 err_out:
 	return r;
 }
 
 static void __exit kvmppc_44x_exit(void)
 {
+	kvmppc_pr_ops = NULL;
 	kvmppc_booke_exit();
 }
 
diff --git a/arch/powerpc/kvm/book3s.c b/arch/powerpc/kvm/book3s.c
index 130fe1d75ba..ad8f6ed3f13 100644
--- a/arch/powerpc/kvm/book3s.c
+++ b/arch/powerpc/kvm/book3s.c
@@ -34,6 +34,7 @@
 #include <linux/vmalloc.h>
 #include <linux/highmem.h>
 
+#include "book3s.h"
 #include "trace.h"
 
 #define VCPU_STAT(x) offsetof(struct kvm_vcpu, stat.x), KVM_STAT_VCPU
@@ -71,7 +72,7 @@ void kvmppc_core_load_guest_debugstate(struct kvm_vcpu *vcpu)
 
 static inline unsigned long kvmppc_interrupt_offset(struct kvm_vcpu *vcpu)
 {
-	if (!kvmppc_ops->is_hv_enabled)
+	if (!vcpu->kvm->arch.kvm_ops->is_hv_enabled)
 		return to_book3s(vcpu)->hior;
 	return 0;
 }
@@ -79,7 +80,7 @@ static inline unsigned long kvmppc_interrupt_offset(struct kvm_vcpu *vcpu)
 static inline void kvmppc_update_int_pending(struct kvm_vcpu *vcpu,
 			unsigned long pending_now, unsigned long old_pending)
 {
-	if (kvmppc_ops->is_hv_enabled)
+	if (vcpu->kvm->arch.kvm_ops->is_hv_enabled)
 		return;
 	if (pending_now)
 		vcpu->arch.shared->int_pending = 1;
@@ -93,7 +94,7 @@ static inline bool kvmppc_critical_section(struct kvm_vcpu *vcpu)
 	ulong crit_r1;
 	bool crit;
 
-	if (kvmppc_ops->is_hv_enabled)
+	if (vcpu->kvm->arch.kvm_ops->is_hv_enabled)
 		return false;
 
 	crit_raw = vcpu->arch.shared->critical;
@@ -477,13 +478,13 @@ void kvmppc_subarch_vcpu_uninit(struct kvm_vcpu *vcpu)
 int kvm_arch_vcpu_ioctl_get_sregs(struct kvm_vcpu *vcpu,
 				  struct kvm_sregs *sregs)
 {
-	return kvmppc_ops->get_sregs(vcpu, sregs);
+	return vcpu->kvm->arch.kvm_ops->get_sregs(vcpu, sregs);
 }
 
 int kvm_arch_vcpu_ioctl_set_sregs(struct kvm_vcpu *vcpu,
 				  struct kvm_sregs *sregs)
 {
-	return kvmppc_ops->set_sregs(vcpu, sregs);
+	return vcpu->kvm->arch.kvm_ops->set_sregs(vcpu, sregs);
 }
 
 int kvm_arch_vcpu_ioctl_get_regs(struct kvm_vcpu *vcpu, struct kvm_regs *regs)
@@ -562,7 +563,7 @@ int kvm_vcpu_ioctl_get_one_reg(struct kvm_vcpu *vcpu, struct kvm_one_reg *reg)
 	if (size > sizeof(val))
 		return -EINVAL;
 
-	r = kvmppc_ops->get_one_reg(vcpu, reg->id, &val);
+	r = vcpu->kvm->arch.kvm_ops->get_one_reg(vcpu, reg->id, &val);
 	if (r == -EINVAL) {
 		r = 0;
 		switch (reg->id) {
@@ -641,7 +642,7 @@ int kvm_vcpu_ioctl_set_one_reg(struct kvm_vcpu *vcpu, struct kvm_one_reg *reg)
 	if (copy_from_user(&val, (char __user *)(unsigned long)reg->addr, size))
 		return -EFAULT;
 
-	r = kvmppc_ops->set_one_reg(vcpu, reg->id, &val);
+	r = vcpu->kvm->arch.kvm_ops->set_one_reg(vcpu, reg->id, &val);
 	if (r == -EINVAL) {
 		r = 0;
 		switch (reg->id) {
@@ -702,23 +703,23 @@ int kvm_vcpu_ioctl_set_one_reg(struct kvm_vcpu *vcpu, struct kvm_one_reg *reg)
 
 void kvmppc_core_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
 {
-	kvmppc_ops->vcpu_load(vcpu, cpu);
+	vcpu->kvm->arch.kvm_ops->vcpu_load(vcpu, cpu);
 }
 
 void kvmppc_core_vcpu_put(struct kvm_vcpu *vcpu)
 {
-	kvmppc_ops->vcpu_put(vcpu);
+	vcpu->kvm->arch.kvm_ops->vcpu_put(vcpu);
 }
 
 void kvmppc_set_msr(struct kvm_vcpu *vcpu, u64 msr)
 {
-	kvmppc_ops->set_msr(vcpu, msr);
+	vcpu->kvm->arch.kvm_ops->set_msr(vcpu, msr);
 }
 EXPORT_SYMBOL_GPL(kvmppc_set_msr);
 
 int kvmppc_vcpu_run(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu)
 {
-	return kvmppc_ops->vcpu_run(kvm_run, vcpu);
+	return vcpu->kvm->arch.kvm_ops->vcpu_run(kvm_run, vcpu);
 }
 
 int kvm_arch_vcpu_ioctl_translate(struct kvm_vcpu *vcpu,
@@ -743,84 +744,84 @@ void kvmppc_decrementer_func(unsigned long data)
 
 struct kvm_vcpu *kvmppc_core_vcpu_create(struct kvm *kvm, unsigned int id)
 {
-	return kvmppc_ops->vcpu_create(kvm, id);
+	return kvm->arch.kvm_ops->vcpu_create(kvm, id);
 }
 
 void kvmppc_core_vcpu_free(struct kvm_vcpu *vcpu)
 {
-	kvmppc_ops->vcpu_free(vcpu);
+	vcpu->kvm->arch.kvm_ops->vcpu_free(vcpu);
 }
 
 int kvmppc_core_check_requests(struct kvm_vcpu *vcpu)
 {
-	return kvmppc_ops->check_requests(vcpu);
+	return vcpu->kvm->arch.kvm_ops->check_requests(vcpu);
 }
 
 int kvm_vm_ioctl_get_dirty_log(struct kvm *kvm, struct kvm_dirty_log *log)
 {
-	return kvmppc_ops->get_dirty_log(kvm, log);
+	return kvm->arch.kvm_ops->get_dirty_log(kvm, log);
 }
 
 void kvmppc_core_free_memslot(struct kvm *kvm, struct kvm_memory_slot *free,
 			      struct kvm_memory_slot *dont)
 {
-	kvmppc_ops->free_memslot(free, dont);
+	kvm->arch.kvm_ops->free_memslot(free, dont);
 }
 
 int kvmppc_core_create_memslot(struct kvm *kvm, struct kvm_memory_slot *slot,
 			       unsigned long npages)
 {
-	return kvmppc_ops->create_memslot(slot, npages);
+	return kvm->arch.kvm_ops->create_memslot(slot, npages);
 }
 
 void kvmppc_core_flush_memslot(struct kvm *kvm, struct kvm_memory_slot *memslot)
 {
-	kvmppc_ops->flush_memslot(kvm, memslot);
+	kvm->arch.kvm_ops->flush_memslot(kvm, memslot);
 }
 
 int kvmppc_core_prepare_memory_region(struct kvm *kvm,
 				struct kvm_memory_slot *memslot,
 				struct kvm_userspace_memory_region *mem)
 {
-	return kvmppc_ops->prepare_memory_region(kvm, memslot, mem);
+	return kvm->arch.kvm_ops->prepare_memory_region(kvm, memslot, mem);
 }
 
 void kvmppc_core_commit_memory_region(struct kvm *kvm,
 				struct kvm_userspace_memory_region *mem,
 				const struct kvm_memory_slot *old)
 {
-	kvmppc_ops->commit_memory_region(kvm, mem, old);
+	kvm->arch.kvm_ops->commit_memory_region(kvm, mem, old);
 }
 
 int kvm_unmap_hva(struct kvm *kvm, unsigned long hva)
 {
-	return kvmppc_ops->unmap_hva(kvm, hva);
+	return kvm->arch.kvm_ops->unmap_hva(kvm, hva);
 }
 EXPORT_SYMBOL_GPL(kvm_unmap_hva);
 
 int kvm_unmap_hva_range(struct kvm *kvm, unsigned long start, unsigned long end)
 {
-	return kvmppc_ops->unmap_hva_range(kvm, start, end);
+	return kvm->arch.kvm_ops->unmap_hva_range(kvm, start, end);
 }
 
 int kvm_age_hva(struct kvm *kvm, unsigned long hva)
 {
-	return kvmppc_ops->age_hva(kvm, hva);
+	return kvm->arch.kvm_ops->age_hva(kvm, hva);
 }
 
 int kvm_test_age_hva(struct kvm *kvm, unsigned long hva)
 {
-	return kvmppc_ops->test_age_hva(kvm, hva);
+	return kvm->arch.kvm_ops->test_age_hva(kvm, hva);
 }
 
 void kvm_set_spte_hva(struct kvm *kvm, unsigned long hva, pte_t pte)
 {
-	kvmppc_ops->set_spte_hva(kvm, hva, pte);
+	kvm->arch.kvm_ops->set_spte_hva(kvm, hva, pte);
 }
 
 void kvmppc_mmu_destroy(struct kvm_vcpu *vcpu)
 {
-	kvmppc_ops->mmu_destroy(vcpu);
+	vcpu->kvm->arch.kvm_ops->mmu_destroy(vcpu);
 }
 
 int kvmppc_core_init_vm(struct kvm *kvm)
@@ -831,12 +832,12 @@ int kvmppc_core_init_vm(struct kvm *kvm)
 	INIT_LIST_HEAD(&kvm->arch.rtas_tokens);
 #endif
 
-	return kvmppc_ops->init_vm(kvm);
+	return kvm->arch.kvm_ops->init_vm(kvm);
 }
 
 void kvmppc_core_destroy_vm(struct kvm *kvm)
 {
-	kvmppc_ops->destroy_vm(kvm);
+	kvm->arch.kvm_ops->destroy_vm(kvm);
 
 #ifdef CONFIG_PPC64
 	kvmppc_rtas_tokens_free(kvm);
@@ -846,5 +847,35 @@ void kvmppc_core_destroy_vm(struct kvm *kvm)
 
 int kvmppc_core_check_processor_compat(void)
 {
-	return kvmppc_ops->check_processor_compat();
+	/*
+	 * We always return 0 for book3s. We check
+	 * for compatability while loading the HV
+	 * or PR module
+	 */
+	return 0;
+}
+
+static int kvmppc_book3s_init(void)
+{
+	int r;
+
+	r = kvm_init(NULL, sizeof(struct kvm_vcpu), 0, THIS_MODULE);
+	if (r)
+		return r;
+#ifdef CONFIG_KVM_BOOK3S_32
+	r = kvmppc_book3s_init_pr();
+#endif
+	return r;
+
+}
+
+static void kvmppc_book3s_exit(void)
+{
+#ifdef CONFIG_KVM_BOOK3S_32
+	kvmppc_book3s_exit_pr();
+#endif
+	kvm_exit();
 }
+
+module_init(kvmppc_book3s_init);
+module_exit(kvmppc_book3s_exit);
diff --git a/arch/powerpc/kvm/book3s.h b/arch/powerpc/kvm/book3s.h
index 9e5b3a34194..4bf956cf94d 100644
--- a/arch/powerpc/kvm/book3s.h
+++ b/arch/powerpc/kvm/book3s.h
@@ -28,5 +28,7 @@ extern int kvmppc_core_emulate_mtspr_pr(struct kvm_vcpu *vcpu,
 					int sprn, ulong spr_val);
 extern int kvmppc_core_emulate_mfspr_pr(struct kvm_vcpu *vcpu,
 					int sprn, ulong *spr_val);
+extern int kvmppc_book3s_init_pr(void);
+extern void kvmppc_book3s_exit_pr(void);
 
 #endif
diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c
index 9e954a81c07..8743048881b 100644
--- a/arch/powerpc/kvm/book3s_hv.c
+++ b/arch/powerpc/kvm/book3s_hv.c
@@ -2159,7 +2159,7 @@ static long kvm_arch_vm_ioctl_hv(struct file *filp,
 	return r;
 }
 
-static struct kvmppc_ops kvmppc_hv_ops = {
+static struct kvmppc_ops kvm_ops_hv = {
 	.is_hv_enabled = true,
 	.get_sregs = kvm_arch_vcpu_ioctl_get_sregs_hv,
 	.set_sregs = kvm_arch_vcpu_ioctl_set_sregs_hv,
@@ -2186,7 +2186,6 @@ static struct kvmppc_ops kvmppc_hv_ops = {
 	.create_memslot = kvmppc_core_create_memslot_hv,
 	.init_vm =  kvmppc_core_init_vm_hv,
 	.destroy_vm = kvmppc_core_destroy_vm_hv,
-	.check_processor_compat = kvmppc_core_check_processor_compat_hv,
 	.get_smmu_info = kvm_vm_ioctl_get_smmu_info_hv,
 	.emulate_op = kvmppc_core_emulate_op_hv,
 	.emulate_mtspr = kvmppc_core_emulate_mtspr_hv,
@@ -2198,20 +2197,23 @@ static struct kvmppc_ops kvmppc_hv_ops = {
 static int kvmppc_book3s_init_hv(void)
 {
 	int r;
-
-	r = kvm_init(&kvmppc_hv_ops, sizeof(struct kvm_vcpu), 0, THIS_MODULE);
-
-	if (r)
+	/*
+	 * FIXME!! Do we need to check on all cpus ?
+	 */
+	r = kvmppc_core_check_processor_compat_hv();
+	if (r < 0)
 		return r;
 
-	r = kvmppc_mmu_hv_init();
+	kvm_ops_hv.owner = THIS_MODULE;
+	kvmppc_hv_ops = &kvm_ops_hv;
 
+	r = kvmppc_mmu_hv_init();
 	return r;
 }
 
 static void kvmppc_book3s_exit_hv(void)
 {
-	kvm_exit();
+	kvmppc_hv_ops = NULL;
 }
 
 module_init(kvmppc_book3s_init_hv);
diff --git a/arch/powerpc/kvm/book3s_pr.c b/arch/powerpc/kvm/book3s_pr.c
index 7f583a48216..fbd985f0cb0 100644
--- a/arch/powerpc/kvm/book3s_pr.c
+++ b/arch/powerpc/kvm/book3s_pr.c
@@ -1525,7 +1525,7 @@ static long kvm_arch_vm_ioctl_pr(struct file *filp,
 	return -ENOTTY;
 }
 
-static struct kvmppc_ops kvmppc_pr_ops = {
+static struct kvmppc_ops kvm_ops_pr = {
 	.is_hv_enabled = false,
 	.get_sregs = kvm_arch_vcpu_ioctl_get_sregs_pr,
 	.set_sregs = kvm_arch_vcpu_ioctl_set_sregs_pr,
@@ -1552,7 +1552,6 @@ static struct kvmppc_ops kvmppc_pr_ops = {
 	.create_memslot = kvmppc_core_create_memslot_pr,
 	.init_vm = kvmppc_core_init_vm_pr,
 	.destroy_vm = kvmppc_core_destroy_vm_pr,
-	.check_processor_compat = kvmppc_core_check_processor_compat_pr,
 	.get_smmu_info = kvm_vm_ioctl_get_smmu_info_pr,
 	.emulate_op = kvmppc_core_emulate_op_pr,
 	.emulate_mtspr = kvmppc_core_emulate_mtspr_pr,
@@ -1561,27 +1560,35 @@ static struct kvmppc_ops kvmppc_pr_ops = {
 	.arch_vm_ioctl  = kvm_arch_vm_ioctl_pr,
 };
 
-static int kvmppc_book3s_init_pr(void)
+
+int kvmppc_book3s_init_pr(void)
 {
 	int r;
 
-	r = kvm_init(&kvmppc_pr_ops, sizeof(struct kvm_vcpu), 0, THIS_MODULE);
-
-	if (r)
+	r = kvmppc_core_check_processor_compat_pr();
+	if (r < 0)
 		return r;
 
-	r = kvmppc_mmu_hpte_sysinit();
+	kvm_ops_pr.owner = THIS_MODULE;
+	kvmppc_pr_ops = &kvm_ops_pr;
 
+	r = kvmppc_mmu_hpte_sysinit();
 	return r;
 }
 
-static void kvmppc_book3s_exit_pr(void)
+void kvmppc_book3s_exit_pr(void)
 {
+	kvmppc_pr_ops = NULL;
 	kvmppc_mmu_hpte_sysexit();
-	kvm_exit();
 }
 
+/*
+ * We only support separate modules for book3s 64
+ */
+#ifdef CONFIG_PPC_BOOK3S_64
+
 module_init(kvmppc_book3s_init_pr);
 module_exit(kvmppc_book3s_exit_pr);
 
 MODULE_LICENSE("GPL");
+#endif
diff --git a/arch/powerpc/kvm/book3s_xics.c b/arch/powerpc/kvm/book3s_xics.c
index c3c832b27ee..f7a5108a348 100644
--- a/arch/powerpc/kvm/book3s_xics.c
+++ b/arch/powerpc/kvm/book3s_xics.c
@@ -818,7 +818,7 @@ int kvmppc_xics_hcall(struct kvm_vcpu *vcpu, u32 req)
 	}
 
 	/* Check for real mode returning too hard */
-	if (xics->real_mode && kvmppc_ops->is_hv_enabled)
+	if (xics->real_mode && vcpu->kvm->arch.kvm_ops->is_hv_enabled)
 		return kvmppc_xics_rm_complete(vcpu, req);
 
 	switch (req) {
diff --git a/arch/powerpc/kvm/booke.c b/arch/powerpc/kvm/booke.c
index cb2d986a338..15d0149511e 100644
--- a/arch/powerpc/kvm/booke.c
+++ b/arch/powerpc/kvm/booke.c
@@ -1472,7 +1472,7 @@ int kvm_arch_vcpu_ioctl_get_sregs(struct kvm_vcpu *vcpu,
 
 	get_sregs_base(vcpu, sregs);
 	get_sregs_arch206(vcpu, sregs);
-	return kvmppc_ops->get_sregs(vcpu, sregs);
+	return vcpu->kvm->arch.kvm_ops->get_sregs(vcpu, sregs);
 }
 
 int kvm_arch_vcpu_ioctl_set_sregs(struct kvm_vcpu *vcpu,
@@ -1491,7 +1491,7 @@ int kvm_arch_vcpu_ioctl_set_sregs(struct kvm_vcpu *vcpu,
 	if (ret < 0)
 		return ret;
 
-	return kvmppc_ops->set_sregs(vcpu, sregs);
+	return vcpu->kvm->arch.kvm_ops->set_sregs(vcpu, sregs);
 }
 
 int kvm_vcpu_ioctl_get_one_reg(struct kvm_vcpu *vcpu, struct kvm_one_reg *reg)
@@ -1548,7 +1548,7 @@ int kvm_vcpu_ioctl_get_one_reg(struct kvm_vcpu *vcpu, struct kvm_one_reg *reg)
 		val = get_reg_val(reg->id, vcpu->arch.vrsave);
 		break;
 	default:
-		r = kvmppc_ops->get_one_reg(vcpu, reg->id, &val);
+		r = vcpu->kvm->arch.kvm_ops->get_one_reg(vcpu, reg->id, &val);
 		break;
 	}
 
@@ -1631,7 +1631,7 @@ int kvm_vcpu_ioctl_set_one_reg(struct kvm_vcpu *vcpu, struct kvm_one_reg *reg)
 		vcpu->arch.vrsave = set_reg_val(reg->id, val);
 		break;
 	default:
-		r = kvmppc_ops->set_one_reg(vcpu, reg->id, &val);
+		r = vcpu->kvm->arch.kvm_ops->set_one_reg(vcpu, reg->id, &val);
 		break;
 	}
 
@@ -1911,37 +1911,37 @@ void kvmppc_booke_vcpu_put(struct kvm_vcpu *vcpu)
 
 void kvmppc_mmu_destroy(struct kvm_vcpu *vcpu)
 {
-	kvmppc_ops->mmu_destroy(vcpu);
+	vcpu->kvm->arch.kvm_ops->mmu_destroy(vcpu);
 }
 
 int kvmppc_core_init_vm(struct kvm *kvm)
 {
-	return kvmppc_ops->init_vm(kvm);
+	return kvm->arch.kvm_ops->init_vm(kvm);
 }
 
 struct kvm_vcpu *kvmppc_core_vcpu_create(struct kvm *kvm, unsigned int id)
 {
-	return kvmppc_ops->vcpu_create(kvm, id);
+	return kvm->arch.kvm_ops->vcpu_create(kvm, id);
 }
 
 void kvmppc_core_vcpu_free(struct kvm_vcpu *vcpu)
 {
-	kvmppc_ops->vcpu_free(vcpu);
+	vcpu->kvm->arch.kvm_ops->vcpu_free(vcpu);
 }
 
 void kvmppc_core_destroy_vm(struct kvm *kvm)
 {
-	kvmppc_ops->destroy_vm(kvm);
+	kvm->arch.kvm_ops->destroy_vm(kvm);
 }
 
 void kvmppc_core_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
 {
-	kvmppc_ops->vcpu_load(vcpu, cpu);
+	vcpu->kvm->arch.kvm_ops->vcpu_load(vcpu, cpu);
 }
 
 void kvmppc_core_vcpu_put(struct kvm_vcpu *vcpu)
 {
-	kvmppc_ops->vcpu_put(vcpu);
+	vcpu->kvm->arch.kvm_ops->vcpu_put(vcpu);
 }
 
 int __init kvmppc_booke_init(void)
diff --git a/arch/powerpc/kvm/e500.c b/arch/powerpc/kvm/e500.c
index d225d5ebddc..497b142f651 100644
--- a/arch/powerpc/kvm/e500.c
+++ b/arch/powerpc/kvm/e500.c
@@ -555,13 +555,19 @@ static int __init kvmppc_e500_init(void)
 	flush_icache_range(kvmppc_booke_handlers, kvmppc_booke_handlers +
 			   ivor[max_ivor] + handler_len);
 
-	r = kvm_init(&kvm_ops_e500, sizeof(struct kvmppc_vcpu_e500), 0, THIS_MODULE);
+	r = kvm_init(NULL, sizeof(struct kvmppc_vcpu_e500), 0, THIS_MODULE);
+	if (r)
+		goto err_out;
+	kvm_ops_e500.owner = THIS_MODULE;
+	kvmppc_pr_ops = &kvm_ops_e500;
+
 err_out:
 	return r;
 }
 
 static void __exit kvmppc_e500_exit(void)
 {
+	kvmppc_pr_ops = NULL;
 	kvmppc_booke_exit();
 }
 
diff --git a/arch/powerpc/kvm/e500mc.c b/arch/powerpc/kvm/e500mc.c
index db6a383401c..4132cd2fc17 100644
--- a/arch/powerpc/kvm/e500mc.c
+++ b/arch/powerpc/kvm/e500mc.c
@@ -373,15 +373,19 @@ static int __init kvmppc_e500mc_init(void)
 	kvmppc_init_lpid(64);
 	kvmppc_claim_lpid(0); /* host */
 
-	r = kvm_init(&kvm_ops_e500mc, sizeof(struct kvmppc_vcpu_e500), 0, THIS_MODULE);
+	r = kvm_init(NULL, sizeof(struct kvmppc_vcpu_e500), 0, THIS_MODULE);
 	if (r)
 		goto err_out;
+	kvm_ops_e500mc.owner = THIS_MODULE;
+	kvmppc_pr_ops = &kvm_ops_e500mc;
+
 err_out:
 	return r;
 }
 
 static void __exit kvmppc_e500mc_exit(void)
 {
+	kvmppc_pr_ops = NULL;
 	kvmppc_booke_exit();
 }
 
diff --git a/arch/powerpc/kvm/emulate.c b/arch/powerpc/kvm/emulate.c
index de9a340d22e..2f9a0873b44 100644
--- a/arch/powerpc/kvm/emulate.c
+++ b/arch/powerpc/kvm/emulate.c
@@ -130,8 +130,8 @@ static int kvmppc_emulate_mtspr(struct kvm_vcpu *vcpu, int sprn, int rs)
 	case SPRN_PIR: break;
 
 	default:
-		emulated = kvmppc_ops->emulate_mtspr(vcpu, sprn,
-						     spr_val);
+		emulated = vcpu->kvm->arch.kvm_ops->emulate_mtspr(vcpu, sprn,
+								  spr_val);
 		if (emulated == EMULATE_FAIL)
 			printk(KERN_INFO "mtspr: unknown spr "
 				"0x%x\n", sprn);
@@ -191,8 +191,8 @@ static int kvmppc_emulate_mfspr(struct kvm_vcpu *vcpu, int sprn, int rt)
 		spr_val = kvmppc_get_dec(vcpu, get_tb());
 		break;
 	default:
-		emulated = kvmppc_ops->emulate_mfspr(vcpu, sprn,
-						     &spr_val);
+		emulated = vcpu->kvm->arch.kvm_ops->emulate_mfspr(vcpu, sprn,
+								  &spr_val);
 		if (unlikely(emulated == EMULATE_FAIL)) {
 			printk(KERN_INFO "mfspr: unknown spr "
 				"0x%x\n", sprn);
@@ -464,7 +464,8 @@ int kvmppc_emulate_instruction(struct kvm_run *run, struct kvm_vcpu *vcpu)
 	}
 
 	if (emulated == EMULATE_FAIL) {
-		emulated = kvmppc_ops->emulate_op(run, vcpu, inst, &advance);
+		emulated = vcpu->kvm->arch.kvm_ops->emulate_op(run, vcpu, inst,
+							       &advance);
 		if (emulated == EMULATE_AGAIN) {
 			advance = 0;
 		} else if (emulated == EMULATE_FAIL) {
diff --git a/arch/powerpc/kvm/powerpc.c b/arch/powerpc/kvm/powerpc.c
index b103d747934..0320c1721ca 100644
--- a/arch/powerpc/kvm/powerpc.c
+++ b/arch/powerpc/kvm/powerpc.c
@@ -26,6 +26,7 @@
 #include <linux/fs.h>
 #include <linux/slab.h>
 #include <linux/file.h>
+#include <linux/module.h>
 #include <asm/cputable.h>
 #include <asm/uaccess.h>
 #include <asm/kvm_ppc.h>
@@ -39,7 +40,11 @@
 #define CREATE_TRACE_POINTS
 #include "trace.h"
 
-struct kvmppc_ops *kvmppc_ops;
+struct kvmppc_ops *kvmppc_hv_ops;
+EXPORT_SYMBOL_GPL(kvmppc_hv_ops);
+struct kvmppc_ops *kvmppc_pr_ops;
+EXPORT_SYMBOL_GPL(kvmppc_pr_ops);
+
 
 int kvm_arch_vcpu_runnable(struct kvm_vcpu *v)
 {
@@ -195,7 +200,7 @@ int kvmppc_sanity_check(struct kvm_vcpu *vcpu)
 		goto out;
 
 	/* HV KVM can only do PAPR mode for now */
-	if (!vcpu->arch.papr_enabled && kvmppc_ops->is_hv_enabled)
+	if (!vcpu->arch.papr_enabled && vcpu->kvm->arch.kvm_ops->is_hv_enabled)
 		goto out;
 
 #ifdef CONFIG_KVM_BOOKE_HV
@@ -271,10 +276,35 @@ void kvm_arch_check_processor_compat(void *rtn)
 
 int kvm_arch_init_vm(struct kvm *kvm, unsigned long type)
 {
-	if (type)
-		return -EINVAL;
-
+	struct kvmppc_ops *kvm_ops = NULL;
+	/*
+	 * if we have both HV and PR enabled, default is HV
+	 */
+	if (type == 0) {
+		if (kvmppc_hv_ops)
+			kvm_ops = kvmppc_hv_ops;
+		else
+			kvm_ops = kvmppc_pr_ops;
+		if (!kvm_ops)
+			goto err_out;
+	} else	if (type == KVM_VM_PPC_HV) {
+		if (!kvmppc_hv_ops)
+			goto err_out;
+		kvm_ops = kvmppc_hv_ops;
+	} else if (type == KVM_VM_PPC_PR) {
+		if (!kvmppc_pr_ops)
+			goto err_out;
+		kvm_ops = kvmppc_pr_ops;
+	} else
+		goto err_out;
+
+	if (kvm_ops->owner && !try_module_get(kvm_ops->owner))
+		return -ENOENT;
+
+	kvm->arch.kvm_ops = kvm_ops;
 	return kvmppc_core_init_vm(kvm);
+err_out:
+	return -EINVAL;
 }
 
 void kvm_arch_destroy_vm(struct kvm *kvm)
@@ -294,6 +324,9 @@ void kvm_arch_destroy_vm(struct kvm *kvm)
 	kvmppc_core_destroy_vm(kvm);
 
 	mutex_unlock(&kvm->lock);
+
+	/* drop the module reference */
+	module_put(kvm->arch.kvm_ops->owner);
 }
 
 void kvm_arch_sync_events(struct kvm *kvm)
@@ -303,6 +336,10 @@ void kvm_arch_sync_events(struct kvm *kvm)
 int kvm_dev_ioctl_check_extension(long ext)
 {
 	int r;
+	/* FIXME!!
+	 * Should some of this be vm ioctl ? is it possible now ?
+	 */
+	int hv_enabled = kvmppc_hv_ops ? 1 : 0;
 
 	switch (ext) {
 #ifdef CONFIG_BOOKE
@@ -329,7 +366,7 @@ int kvm_dev_ioctl_check_extension(long ext)
 	case KVM_CAP_SW_TLB:
 #endif
 		/* We support this only for PR */
-		r = !kvmppc_ops->is_hv_enabled;
+		r = !hv_enabled;
 		break;
 #ifdef CONFIG_KVM_MMIO
 	case KVM_CAP_COALESCED_MMIO:
@@ -354,13 +391,13 @@ int kvm_dev_ioctl_check_extension(long ext)
 #endif /* CONFIG_PPC_BOOK3S_64 */
 #ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE
 	case KVM_CAP_PPC_SMT:
-		if (kvmppc_ops->is_hv_enabled)
+		if (hv_enabled)
 			r = threads_per_core;
 		else
 			r = 0;
 		break;
 	case KVM_CAP_PPC_RMA:
-		r = kvmppc_ops->is_hv_enabled;
+		r = hv_enabled;
 		/* PPC970 requires an RMA */
 		if (r && cpu_has_feature(CPU_FTR_ARCH_201))
 			r = 2;
@@ -368,7 +405,7 @@ int kvm_dev_ioctl_check_extension(long ext)
 #endif
 	case KVM_CAP_SYNC_MMU:
 #ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE
-		if (kvmppc_ops->is_hv_enabled)
+		if (hv_enabled)
 			r = cpu_has_feature(CPU_FTR_ARCH_206) ? 1 : 0;
 		else
 			r = 0;
@@ -380,7 +417,7 @@ int kvm_dev_ioctl_check_extension(long ext)
 		break;
 #ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE
 	case KVM_CAP_PPC_HTAB_FD:
-		r = kvmppc_ops->is_hv_enabled;
+		r = hv_enabled;
 		break;
 #endif
 	case KVM_CAP_NR_VCPUS:
@@ -390,7 +427,7 @@ int kvm_dev_ioctl_check_extension(long ext)
 		 * will have secondary threads "offline"), and for other KVM
 		 * implementations just count online CPUs.
 		 */
-		if (kvmppc_ops->is_hv_enabled)
+		if (hv_enabled)
 			r = num_present_cpus();
 		else
 			r = num_online_cpus();
@@ -1039,9 +1076,10 @@ long kvm_arch_vm_ioctl(struct file *filp,
 	}
 	case KVM_PPC_GET_SMMU_INFO: {
 		struct kvm_ppc_smmu_info info;
+		struct kvm *kvm = filp->private_data;
 
 		memset(&info, 0, sizeof(info));
-		r = kvmppc_ops->get_smmu_info(kvm, &info);
+		r = kvm->arch.kvm_ops->get_smmu_info(kvm, &info);
 		if (r >= 0 && copy_to_user(argp, &info, sizeof(info)))
 			r = -EFAULT;
 		break;
@@ -1052,9 +1090,10 @@ long kvm_arch_vm_ioctl(struct file *filp,
 		r = kvm_vm_ioctl_rtas_define_token(kvm, argp);
 		break;
 	}
-	default:
-		r = kvmppc_ops->arch_vm_ioctl(filp, ioctl, arg);
-
+	default: {
+		struct kvm *kvm = filp->private_data;
+		r = kvm->arch.kvm_ops->arch_vm_ioctl(filp, ioctl, arg);
+	}
 #else /* CONFIG_PPC_BOOK3S_64 */
 	default:
 		r = -ENOTTY;
@@ -1104,15 +1143,10 @@ EXPORT_SYMBOL_GPL(kvmppc_init_lpid);
 
 int kvm_arch_init(void *opaque)
 {
-	if (kvmppc_ops) {
-		printk(KERN_ERR "kvm: already loaded the other module\n");
-		return -EEXIST;
-	}
-	kvmppc_ops = (struct kvmppc_ops *)opaque;
 	return 0;
 }
 
 void kvm_arch_exit(void)
 {
-	kvmppc_ops = NULL;
+
 }
diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h
index e32e776f20c..5b5341f7836 100644
--- a/include/uapi/linux/kvm.h
+++ b/include/uapi/linux/kvm.h
@@ -518,6 +518,10 @@ struct kvm_ppc_smmu_info {
 /* machine type bits, to be used as argument to KVM_CREATE_VM */
 #define KVM_VM_S390_UCONTROL	1
 
+/* on ppc, 0 indicate default, 1 should force HV and 2 PR */
+#define KVM_VM_PPC_HV 1
+#define KVM_VM_PPC_PR 2
+
 #define KVM_S390_SIE_PAGE_OFFSET 1
 
 /*
-- 
cgit v1.2.3-70-g09d2


From a78b55d1c0218b6d91d504941d20e36435c276f5 Mon Sep 17 00:00:00 2001
From: "Aneesh Kumar K.V" <aneesh.kumar@linux.vnet.ibm.com>
Date: Mon, 7 Oct 2013 22:18:02 +0530
Subject: kvm: powerpc: book3s: drop is_hv_enabled

drop is_hv_enabled, because that should not be a callback property

Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
Signed-off-by: Alexander Graf <agraf@suse.de>
---
 arch/powerpc/include/asm/kvm_ppc.h | 6 +++++-
 arch/powerpc/kvm/book3s.c          | 6 +++---
 arch/powerpc/kvm/book3s_hv.c       | 1 -
 arch/powerpc/kvm/book3s_pr.c       | 1 -
 arch/powerpc/kvm/book3s_xics.c     | 2 +-
 arch/powerpc/kvm/powerpc.c         | 2 +-
 6 files changed, 10 insertions(+), 8 deletions(-)

(limited to 'arch/powerpc/kvm')

diff --git a/arch/powerpc/include/asm/kvm_ppc.h b/arch/powerpc/include/asm/kvm_ppc.h
index 3069cf4dcc8..c8317fbf92c 100644
--- a/arch/powerpc/include/asm/kvm_ppc.h
+++ b/arch/powerpc/include/asm/kvm_ppc.h
@@ -183,7 +183,6 @@ union kvmppc_one_reg {
 
 struct kvmppc_ops {
 	struct module *owner;
-	bool is_hv_enabled;
 	int (*get_sregs)(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs);
 	int (*set_sregs)(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs);
 	int (*get_one_reg)(struct kvm_vcpu *vcpu, u64 id,
@@ -232,6 +231,11 @@ struct kvmppc_ops {
 extern struct kvmppc_ops *kvmppc_hv_ops;
 extern struct kvmppc_ops *kvmppc_pr_ops;
 
+static inline bool is_kvmppc_hv_enabled(struct kvm *kvm)
+{
+	return kvm->arch.kvm_ops == kvmppc_hv_ops;
+}
+
 /*
  * Cuts out inst bits with ordering according to spec.
  * That means the leftmost bit is zero. All given bits are included.
diff --git a/arch/powerpc/kvm/book3s.c b/arch/powerpc/kvm/book3s.c
index ad8f6ed3f13..8912608b7e1 100644
--- a/arch/powerpc/kvm/book3s.c
+++ b/arch/powerpc/kvm/book3s.c
@@ -72,7 +72,7 @@ void kvmppc_core_load_guest_debugstate(struct kvm_vcpu *vcpu)
 
 static inline unsigned long kvmppc_interrupt_offset(struct kvm_vcpu *vcpu)
 {
-	if (!vcpu->kvm->arch.kvm_ops->is_hv_enabled)
+	if (!is_kvmppc_hv_enabled(vcpu->kvm))
 		return to_book3s(vcpu)->hior;
 	return 0;
 }
@@ -80,7 +80,7 @@ static inline unsigned long kvmppc_interrupt_offset(struct kvm_vcpu *vcpu)
 static inline void kvmppc_update_int_pending(struct kvm_vcpu *vcpu,
 			unsigned long pending_now, unsigned long old_pending)
 {
-	if (vcpu->kvm->arch.kvm_ops->is_hv_enabled)
+	if (is_kvmppc_hv_enabled(vcpu->kvm))
 		return;
 	if (pending_now)
 		vcpu->arch.shared->int_pending = 1;
@@ -94,7 +94,7 @@ static inline bool kvmppc_critical_section(struct kvm_vcpu *vcpu)
 	ulong crit_r1;
 	bool crit;
 
-	if (vcpu->kvm->arch.kvm_ops->is_hv_enabled)
+	if (is_kvmppc_hv_enabled(vcpu->kvm))
 		return false;
 
 	crit_raw = vcpu->arch.shared->critical;
diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c
index 8743048881b..072287f1c3b 100644
--- a/arch/powerpc/kvm/book3s_hv.c
+++ b/arch/powerpc/kvm/book3s_hv.c
@@ -2160,7 +2160,6 @@ static long kvm_arch_vm_ioctl_hv(struct file *filp,
 }
 
 static struct kvmppc_ops kvm_ops_hv = {
-	.is_hv_enabled = true,
 	.get_sregs = kvm_arch_vcpu_ioctl_get_sregs_hv,
 	.set_sregs = kvm_arch_vcpu_ioctl_set_sregs_hv,
 	.get_one_reg = kvmppc_get_one_reg_hv,
diff --git a/arch/powerpc/kvm/book3s_pr.c b/arch/powerpc/kvm/book3s_pr.c
index fbd985f0cb0..df36cf2ed22 100644
--- a/arch/powerpc/kvm/book3s_pr.c
+++ b/arch/powerpc/kvm/book3s_pr.c
@@ -1526,7 +1526,6 @@ static long kvm_arch_vm_ioctl_pr(struct file *filp,
 }
 
 static struct kvmppc_ops kvm_ops_pr = {
-	.is_hv_enabled = false,
 	.get_sregs = kvm_arch_vcpu_ioctl_get_sregs_pr,
 	.set_sregs = kvm_arch_vcpu_ioctl_set_sregs_pr,
 	.get_one_reg = kvmppc_get_one_reg_pr,
diff --git a/arch/powerpc/kvm/book3s_xics.c b/arch/powerpc/kvm/book3s_xics.c
index f7a5108a348..02a17dcf161 100644
--- a/arch/powerpc/kvm/book3s_xics.c
+++ b/arch/powerpc/kvm/book3s_xics.c
@@ -818,7 +818,7 @@ int kvmppc_xics_hcall(struct kvm_vcpu *vcpu, u32 req)
 	}
 
 	/* Check for real mode returning too hard */
-	if (xics->real_mode && vcpu->kvm->arch.kvm_ops->is_hv_enabled)
+	if (xics->real_mode && is_kvmppc_hv_enabled(vcpu->kvm))
 		return kvmppc_xics_rm_complete(vcpu, req);
 
 	switch (req) {
diff --git a/arch/powerpc/kvm/powerpc.c b/arch/powerpc/kvm/powerpc.c
index 0320c1721ca..9ae97686e9f 100644
--- a/arch/powerpc/kvm/powerpc.c
+++ b/arch/powerpc/kvm/powerpc.c
@@ -200,7 +200,7 @@ int kvmppc_sanity_check(struct kvm_vcpu *vcpu)
 		goto out;
 
 	/* HV KVM can only do PAPR mode for now */
-	if (!vcpu->arch.papr_enabled && vcpu->kvm->arch.kvm_ops->is_hv_enabled)
+	if (!vcpu->arch.papr_enabled && is_kvmppc_hv_enabled(vcpu->kvm))
 		goto out;
 
 #ifdef CONFIG_KVM_BOOKE_HV
-- 
cgit v1.2.3-70-g09d2