From 685659ee70db0bac47ffd619c726cf600e504fd7 Mon Sep 17 00:00:00 2001
From: yu liu <yu.liu@freescale.com>
Date: Tue, 14 Jun 2011 18:34:25 -0500
Subject: powerpc/e500: Save SPEFCSR in flush_spe_to_thread()

giveup_spe() saves the SPE state which is protected by MSR[SPE].
However, modifying SPEFSCR does not trap when MSR[SPE]=0.
And since SPEFSCR is already saved/restored in _switch(),
not all the callers want to save SPEFSCR again.
Thus, saving SPEFSCR should not belong to giveup_spe().

This patch moves SPEFSCR saving to flush_spe_to_thread(),
and cleans up the caller that needs to save SPEFSCR accordingly.

Signed-off-by: Liu Yu <yu.liu@freescale.com>
Acked-by: Kumar Gala <galak@kernel.crashing.org>
Signed-off-by: Scott Wood <scottwood@freescale.com>
Signed-off-by: Alexander Graf <agraf@suse.de>
---
 arch/powerpc/kernel/head_fsl_booke.S | 2 --
 arch/powerpc/kernel/process.c        | 1 +
 arch/powerpc/kernel/traps.c          | 5 +----
 3 files changed, 2 insertions(+), 6 deletions(-)

(limited to 'arch/powerpc/kernel')

diff --git a/arch/powerpc/kernel/head_fsl_booke.S b/arch/powerpc/kernel/head_fsl_booke.S
index 5ecf54cfa7d4..aede4f87b682 100644
--- a/arch/powerpc/kernel/head_fsl_booke.S
+++ b/arch/powerpc/kernel/head_fsl_booke.S
@@ -792,8 +792,6 @@ _GLOBAL(giveup_spe)
 	evmwumiaa evr6, evr6, evr6	/* evr6 <- ACC = 0 * 0 + ACC */
 	li	r4,THREAD_ACC
 	evstddx	evr6, r4, r3		/* save off accumulator */
-	mfspr	r6,SPRN_SPEFSCR
-	stw	r6,THREAD_SPEFSCR(r3)	/* save spefscr register value */
 	beq	1f
 	lwz	r4,_MSR-STACK_FRAME_OVERHEAD(r5)
 	lis	r3,MSR_SPE@h
diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c
index 91e52df3d81d..60ac2a9251db 100644
--- a/arch/powerpc/kernel/process.c
+++ b/arch/powerpc/kernel/process.c
@@ -213,6 +213,7 @@ void flush_spe_to_thread(struct task_struct *tsk)
 #ifdef CONFIG_SMP
 			BUG_ON(tsk != current);
 #endif
+			tsk->thread.spefscr = mfspr(SPRN_SPEFSCR);
 			giveup_spe(tsk);
 		}
 		preempt_enable();
diff --git a/arch/powerpc/kernel/traps.c b/arch/powerpc/kernel/traps.c
index 1a0141426cda..f19d9777d3c1 100644
--- a/arch/powerpc/kernel/traps.c
+++ b/arch/powerpc/kernel/traps.c
@@ -1387,10 +1387,7 @@ void SPEFloatingPointException(struct pt_regs *regs)
 	int code = 0;
 	int err;
 
-	preempt_disable();
-	if (regs->msr & MSR_SPE)
-		giveup_spe(current);
-	preempt_enable();
+	flush_spe_to_thread(current);
 
 	spefscr = current->thread.spefscr;
 	fpexc_mode = current->thread.fpexc_mode;
-- 
cgit v1.2.3


From c51584d52e3878aa9b2bb98cdfb87173e7acf560 Mon Sep 17 00:00:00 2001
From: Scott Wood <scottwood@freescale.com>
Date: Tue, 14 Jun 2011 18:34:27 -0500
Subject: powerpc/e500: SPE register saving: take arbitrary struct offset

Previously, these macros hardcoded THREAD_EVR0 as the base of the save
area, relative to the base register passed.  This base offset is now
passed as a separate macro parameter, allowing reuse with other SPE
save areas, such as used by KVM.

Acked-by: Kumar Gala <galak@kernel.crashing.org>
Signed-off-by: Scott Wood <scottwood@freescale.com>
Signed-off-by: Alexander Graf <agraf@suse.de>
---
 arch/powerpc/kernel/head_fsl_booke.S | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

(limited to 'arch/powerpc/kernel')

diff --git a/arch/powerpc/kernel/head_fsl_booke.S b/arch/powerpc/kernel/head_fsl_booke.S
index aede4f87b682..fe37dd0dfd17 100644
--- a/arch/powerpc/kernel/head_fsl_booke.S
+++ b/arch/powerpc/kernel/head_fsl_booke.S
@@ -656,7 +656,7 @@ load_up_spe:
 	cmpi	0,r4,0
 	beq	1f
 	addi	r4,r4,THREAD	/* want THREAD of last_task_used_spe */
-	SAVE_32EVRS(0,r10,r4)
+	SAVE_32EVRS(0,r10,r4,THREAD_EVR0)
 	evxor	evr10, evr10, evr10	/* clear out evr10 */
 	evmwumiaa evr10, evr10, evr10	/* evr10 <- ACC = 0 * 0 + ACC */
 	li	r5,THREAD_ACC
@@ -676,7 +676,7 @@ load_up_spe:
 	stw	r4,THREAD_USED_SPE(r5)
 	evlddx	evr4,r10,r5
 	evmra	evr4,evr4
-	REST_32EVRS(0,r10,r5)
+	REST_32EVRS(0,r10,r5,THREAD_EVR0)
 #ifndef CONFIG_SMP
 	subi	r4,r5,THREAD
 	stw	r4,last_task_used_spe@l(r3)
@@ -787,7 +787,7 @@ _GLOBAL(giveup_spe)
 	addi	r3,r3,THREAD		/* want THREAD of task */
 	lwz	r5,PT_REGS(r3)
 	cmpi	0,r5,0
-	SAVE_32EVRS(0, r4, r3)
+	SAVE_32EVRS(0, r4, r3, THREAD_EVR0)
 	evxor	evr6, evr6, evr6	/* clear out evr6 */
 	evmwumiaa evr6, evr6, evr6	/* evr6 <- ACC = 0 * 0 + ACC */
 	li	r4,THREAD_ACC
-- 
cgit v1.2.3


From ecee273fc48f7f48f0c2f074335c43aaa790c308 Mon Sep 17 00:00:00 2001
From: Scott Wood <scottwood@freescale.com>
Date: Tue, 14 Jun 2011 18:34:29 -0500
Subject: KVM: PPC: booke: use shadow_msr

Keep the guest MSR and the guest-mode true MSR separate, rather than
modifying the guest MSR on each guest entry to produce a true MSR.

Any bits which should be modified based on guest MSR must be explicitly
propagated from vcpu->arch.shared->msr to vcpu->arch.shadow_msr in
kvmppc_set_msr().

While we're modifying the guest entry code, reorder a few instructions
to bury some load latencies.

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

(limited to 'arch/powerpc/kernel')

diff --git a/arch/powerpc/kernel/asm-offsets.c b/arch/powerpc/kernel/asm-offsets.c
index 36e1c8a29be8..25de8e4808a4 100644
--- a/arch/powerpc/kernel/asm-offsets.c
+++ b/arch/powerpc/kernel/asm-offsets.c
@@ -404,12 +404,12 @@ int main(void)
 	DEFINE(VCPU_SHADOW_PID, offsetof(struct kvm_vcpu, arch.shadow_pid));
 	DEFINE(VCPU_SHARED, offsetof(struct kvm_vcpu, arch.shared));
 	DEFINE(VCPU_SHARED_MSR, offsetof(struct kvm_vcpu_arch_shared, msr));
+	DEFINE(VCPU_SHADOW_MSR, offsetof(struct kvm_vcpu, arch.shadow_msr));
 
 	/* book3s */
 #ifdef CONFIG_PPC_BOOK3S
 	DEFINE(VCPU_HOST_RETIP, offsetof(struct kvm_vcpu, arch.host_retip));
 	DEFINE(VCPU_HOST_MSR, offsetof(struct kvm_vcpu, arch.host_msr));
-	DEFINE(VCPU_SHADOW_MSR, offsetof(struct kvm_vcpu, arch.shadow_msr));
 	DEFINE(VCPU_TRAMPOLINE_LOWMEM, offsetof(struct kvm_vcpu, arch.trampoline_lowmem));
 	DEFINE(VCPU_TRAMPOLINE_ENTER, offsetof(struct kvm_vcpu, arch.trampoline_enter));
 	DEFINE(VCPU_HIGHMEM_HANDLER, offsetof(struct kvm_vcpu, arch.highmem_handler));
-- 
cgit v1.2.3


From 4cd35f675ba41a99a477e28a6add4a66833325f2 Mon Sep 17 00:00:00 2001
From: Scott Wood <scottwood@freescale.com>
Date: Tue, 14 Jun 2011 18:34:31 -0500
Subject: KVM: PPC: e500: Save/restore SPE state

This is done lazily.  The SPE save will be done only if the guest has
used SPE since the last preemption or heavyweight exit.  Restore will be
done only on demand, when enabling MSR_SPE in the shadow MSR, in response
to an SPE fault or mtmsr emulation.

For SPEFSCR, Linux already switches it on context switch (non-lazily), so
the only remaining bit is to save it between qemu and the guest.

Signed-off-by: Liu Yu <yu.liu@freescale.com>
Signed-off-by: Scott Wood <scottwood@freescale.com>
Signed-off-by: Alexander Graf <agraf@suse.de>
---
 arch/powerpc/kernel/asm-offsets.c | 7 +++++++
 1 file changed, 7 insertions(+)

(limited to 'arch/powerpc/kernel')

diff --git a/arch/powerpc/kernel/asm-offsets.c b/arch/powerpc/kernel/asm-offsets.c
index 25de8e4808a4..ecd2b3ad7ff6 100644
--- a/arch/powerpc/kernel/asm-offsets.c
+++ b/arch/powerpc/kernel/asm-offsets.c
@@ -497,6 +497,13 @@ int main(void)
 	DEFINE(TLBCAM_MAS7, offsetof(struct tlbcam, MAS7));
 #endif
 
+#if defined(CONFIG_KVM) && defined(CONFIG_SPE)
+	DEFINE(VCPU_EVR, offsetof(struct kvm_vcpu, arch.evr[0]));
+	DEFINE(VCPU_ACC, offsetof(struct kvm_vcpu, arch.acc));
+	DEFINE(VCPU_SPEFSCR, offsetof(struct kvm_vcpu, arch.spefscr));
+	DEFINE(VCPU_HOST_SPEFSCR, offsetof(struct kvm_vcpu, arch.host_spefscr));
+#endif
+
 #ifdef CONFIG_KVM_EXIT_TIMING
 	DEFINE(VCPU_TIMING_EXIT_TBU, offsetof(struct kvm_vcpu,
 						arch.timing_exit.tv32.tbu));
-- 
cgit v1.2.3


From dd9ebf1f94354b010f2ac7a98bf69168636cb08e Mon Sep 17 00:00:00 2001
From: Liu Yu <yu.liu@freescale.com>
Date: Tue, 14 Jun 2011 18:35:14 -0500
Subject: KVM: PPC: e500: Add shadow PID support

Dynamically assign host PIDs to guest PIDs, splitting each guest PID into
multiple host (shadow) PIDs based on kernel/user and MSR[IS/DS].  Use
both PID0 and PID1 so that the shadow PIDs for the right mode can be
selected, that correspond both to guest TID = zero and guest TID = guest
PID.

This allows us to significantly reduce the frequency of needing to
invalidate the entire TLB.  When the guest mode or PID changes, we just
update the host PID0/PID1.  And since the allocation of shadow PIDs is
global, multiple guests can share the TLB without conflict.

Note that KVM does not yet support the guest setting PID1 or PID2 to
a value other than zero.  This will need to be fixed for nested KVM
to work.  Until then, we enforce the requirement for guest PID1/PID2
to stay zero by failing the emulation if the guest tries to set them
to something else.

Signed-off-by: Liu Yu <yu.liu@freescale.com>
Signed-off-by: Scott Wood <scottwood@freescale.com>
Signed-off-by: Alexander Graf <agraf@suse.de>
---
 arch/powerpc/kernel/asm-offsets.c | 1 +
 1 file changed, 1 insertion(+)

(limited to 'arch/powerpc/kernel')

diff --git a/arch/powerpc/kernel/asm-offsets.c b/arch/powerpc/kernel/asm-offsets.c
index ecd2b3ad7ff6..faf846131f45 100644
--- a/arch/powerpc/kernel/asm-offsets.c
+++ b/arch/powerpc/kernel/asm-offsets.c
@@ -402,6 +402,7 @@ int main(void)
 	DEFINE(VCPU_SPRG6, offsetof(struct kvm_vcpu, arch.sprg6));
 	DEFINE(VCPU_SPRG7, offsetof(struct kvm_vcpu, arch.sprg7));
 	DEFINE(VCPU_SHADOW_PID, offsetof(struct kvm_vcpu, arch.shadow_pid));
+	DEFINE(VCPU_SHADOW_PID1, offsetof(struct kvm_vcpu, arch.shadow_pid1));
 	DEFINE(VCPU_SHARED, offsetof(struct kvm_vcpu, arch.shared));
 	DEFINE(VCPU_SHARED_MSR, offsetof(struct kvm_vcpu_arch_shared, msr));
 	DEFINE(VCPU_SHADOW_MSR, offsetof(struct kvm_vcpu, arch.shadow_msr));
-- 
cgit v1.2.3


From b01c8b54a1a271c0fc4243845927fe1d250767a3 Mon Sep 17 00:00:00 2001
From: Paul Mackerras <paulus@samba.org>
Date: Wed, 29 Jun 2011 00:18:26 +0000
Subject: powerpc, KVM: Rework KVM checks in first-level interrupt handlers

Instead of branching out-of-line with the DO_KVM macro to check if we
are in a KVM guest at the time of an interrupt, this moves the KVM
check inline in the first-level interrupt handlers.  This speeds up
the non-KVM case and makes sure that none of the interrupt handlers
are missing the check.

Because the first-level interrupt handlers are now larger, some things
had to be move out of line in exceptions-64s.S.

This all necessitated some minor changes to the interrupt entry code
in KVM.  This also streamlines the book3s_32 KVM test.

Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Alexander Graf <agraf@suse.de>
---
 arch/powerpc/kernel/exceptions-64s.S | 189 +++++++++++++++++++++--------------
 1 file changed, 115 insertions(+), 74 deletions(-)

(limited to 'arch/powerpc/kernel')

diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S
index a85f4874cba7..e76472cbf3b5 100644
--- a/arch/powerpc/kernel/exceptions-64s.S
+++ b/arch/powerpc/kernel/exceptions-64s.S
@@ -40,7 +40,6 @@ __start_interrupts:
 	.globl system_reset_pSeries;
 system_reset_pSeries:
 	HMT_MEDIUM;
-	DO_KVM	0x100;
 	SET_SCRATCH0(r13)
 #ifdef CONFIG_PPC_P7_NAP
 BEGIN_FTR_SECTION
@@ -65,67 +64,45 @@ BEGIN_FTR_SECTION
 	beq	.
 END_FTR_SECTION_IFSET(CPU_FTR_HVMODE_206)
 #endif /* CONFIG_PPC_P7_NAP */
-	EXCEPTION_PROLOG_PSERIES(PACA_EXGEN, system_reset_common, EXC_STD)
+	EXCEPTION_PROLOG_PSERIES(PACA_EXGEN, system_reset_common, EXC_STD,
+				 NOTEST, 0x100)
 
 	. = 0x200
-_machine_check_pSeries:
-	HMT_MEDIUM
-	DO_KVM	0x200
-	SET_SCRATCH0(r13)
-	EXCEPTION_PROLOG_PSERIES(PACA_EXMC, machine_check_common, EXC_STD)
+machine_check_pSeries_1:
+	/* This is moved out of line as it can be patched by FW, but
+	 * some code path might still want to branch into the original
+	 * vector
+	 */
+	b	machine_check_pSeries
 
 	. = 0x300
 	.globl data_access_pSeries
 data_access_pSeries:
 	HMT_MEDIUM
-	DO_KVM	0x300
 	SET_SCRATCH0(r13)
+#ifndef CONFIG_POWER4_ONLY
 BEGIN_FTR_SECTION
-	GET_PACA(r13)
-	std	r9,PACA_EXSLB+EX_R9(r13)
-	std	r10,PACA_EXSLB+EX_R10(r13)
-	mfspr	r10,SPRN_DAR
-	mfspr	r9,SPRN_DSISR
-	srdi	r10,r10,60
-	rlwimi	r10,r9,16,0x20
-	mfcr	r9
-	cmpwi	r10,0x2c
-	beq	do_stab_bolted_pSeries
-	ld	r10,PACA_EXSLB+EX_R10(r13)
-	std	r11,PACA_EXGEN+EX_R11(r13)
-	ld	r11,PACA_EXSLB+EX_R9(r13)
-	std	r12,PACA_EXGEN+EX_R12(r13)
-	GET_SCRATCH0(r12)
-	std	r10,PACA_EXGEN+EX_R10(r13)
-	std	r11,PACA_EXGEN+EX_R9(r13)
-	std	r12,PACA_EXGEN+EX_R13(r13)
-	EXCEPTION_PROLOG_PSERIES_1(data_access_common, EXC_STD)
-FTR_SECTION_ELSE
-	EXCEPTION_PROLOG_PSERIES(PACA_EXGEN, data_access_common, EXC_STD)
-ALT_MMU_FTR_SECTION_END_IFCLR(MMU_FTR_SLB)
+	b	data_access_check_stab
+data_access_not_stab:
+END_MMU_FTR_SECTION_IFCLR(MMU_FTR_SLB)
+#endif
+	EXCEPTION_PROLOG_PSERIES(PACA_EXGEN, data_access_common, EXC_STD,
+				 KVMTEST, 0x300)
 
 	. = 0x380
 	.globl data_access_slb_pSeries
 data_access_slb_pSeries:
 	HMT_MEDIUM
-	DO_KVM	0x380
 	SET_SCRATCH0(r13)
-	GET_PACA(r13)
+	EXCEPTION_PROLOG_1(PACA_EXSLB, KVMTEST, 0x380)
 	std	r3,PACA_EXSLB+EX_R3(r13)
 	mfspr	r3,SPRN_DAR
-	std	r9,PACA_EXSLB+EX_R9(r13)	/* save r9 - r12 */
-	mfcr	r9
 #ifdef __DISABLED__
 	/* Keep that around for when we re-implement dynamic VSIDs */
 	cmpdi	r3,0
 	bge	slb_miss_user_pseries
 #endif /* __DISABLED__ */
-	std	r10,PACA_EXSLB+EX_R10(r13)
-	std	r11,PACA_EXSLB+EX_R11(r13)
-	std	r12,PACA_EXSLB+EX_R12(r13)
-	GET_SCRATCH0(r10)
-	std	r10,PACA_EXSLB+EX_R13(r13)
-	mfspr	r12,SPRN_SRR1		/* and SRR1 */
+	mfspr	r12,SPRN_SRR1
 #ifndef CONFIG_RELOCATABLE
 	b	.slb_miss_realmode
 #else
@@ -147,24 +124,16 @@ data_access_slb_pSeries:
 	.globl instruction_access_slb_pSeries
 instruction_access_slb_pSeries:
 	HMT_MEDIUM
-	DO_KVM	0x480
 	SET_SCRATCH0(r13)
-	GET_PACA(r13)
+	EXCEPTION_PROLOG_1(PACA_EXSLB, KVMTEST, 0x480)
 	std	r3,PACA_EXSLB+EX_R3(r13)
 	mfspr	r3,SPRN_SRR0		/* SRR0 is faulting address */
-	std	r9,PACA_EXSLB+EX_R9(r13)	/* save r9 - r12 */
-	mfcr	r9
 #ifdef __DISABLED__
 	/* Keep that around for when we re-implement dynamic VSIDs */
 	cmpdi	r3,0
 	bge	slb_miss_user_pseries
 #endif /* __DISABLED__ */
-	std	r10,PACA_EXSLB+EX_R10(r13)
-	std	r11,PACA_EXSLB+EX_R11(r13)
-	std	r12,PACA_EXSLB+EX_R12(r13)
-	GET_SCRATCH0(r10)
-	std	r10,PACA_EXSLB+EX_R13(r13)
-	mfspr	r12,SPRN_SRR1		/* and SRR1 */
+	mfspr	r12,SPRN_SRR1
 #ifndef CONFIG_RELOCATABLE
 	b	.slb_miss_realmode
 #else
@@ -184,26 +153,46 @@ instruction_access_slb_pSeries:
 hardware_interrupt_pSeries:
 hardware_interrupt_hv:
 	BEGIN_FTR_SECTION
-		_MASKABLE_EXCEPTION_PSERIES(0x500, hardware_interrupt, EXC_STD)
+		_MASKABLE_EXCEPTION_PSERIES(0x500, hardware_interrupt,
+					    EXC_STD, SOFTEN_TEST)
+		KVM_HANDLER(PACA_EXGEN, EXC_STD, 0x500)
 	FTR_SECTION_ELSE
-		_MASKABLE_EXCEPTION_PSERIES(0x502, hardware_interrupt, EXC_HV)
+		_MASKABLE_EXCEPTION_PSERIES(0x502, hardware_interrupt,
+					    EXC_HV, SOFTEN_TEST_HV)
+		KVM_HANDLER(PACA_EXGEN, EXC_HV, 0x502)
 	ALT_FTR_SECTION_END_IFCLR(CPU_FTR_HVMODE_206)
 
 	STD_EXCEPTION_PSERIES(0x600, 0x600, alignment)
+	KVM_HANDLER(PACA_EXGEN, EXC_STD, 0x600)
+
 	STD_EXCEPTION_PSERIES(0x700, 0x700, program_check)
+	KVM_HANDLER(PACA_EXGEN, EXC_STD, 0x700)
+
 	STD_EXCEPTION_PSERIES(0x800, 0x800, fp_unavailable)
+	KVM_HANDLER(PACA_EXGEN, EXC_STD, 0x800)
 
 	MASKABLE_EXCEPTION_PSERIES(0x900, 0x900, decrementer)
-	MASKABLE_EXCEPTION_HV(0x980, 0x980, decrementer)
+	MASKABLE_EXCEPTION_HV(0x980, 0x982, decrementer)
 
 	STD_EXCEPTION_PSERIES(0xa00, 0xa00, trap_0a)
+	KVM_HANDLER(PACA_EXGEN, EXC_STD, 0xa00)
+
 	STD_EXCEPTION_PSERIES(0xb00, 0xb00, trap_0b)
+	KVM_HANDLER(PACA_EXGEN, EXC_STD, 0xb00)
 
 	. = 0xc00
 	.globl	system_call_pSeries
 system_call_pSeries:
 	HMT_MEDIUM
-	DO_KVM	0xc00
+#ifdef CONFIG_KVM_BOOK3S_64_HANDLER
+	SET_SCRATCH0(r13)
+	GET_PACA(r13)
+	std	r9,PACA_EXGEN+EX_R9(r13)
+	std	r10,PACA_EXGEN+EX_R10(r13)
+	mfcr	r9
+	KVMTEST(0xc00)
+	GET_SCRATCH0(r13)
+#endif
 BEGIN_FTR_SECTION
 	cmpdi	r0,0x1ebe
 	beq-	1f
@@ -220,6 +209,8 @@ END_FTR_SECTION_IFSET(CPU_FTR_REAL_LE)
 	rfid
 	b	.	/* prevent speculative execution */
 
+	KVM_HANDLER(PACA_EXGEN, EXC_STD, 0xc00)
+
 /* Fast LE/BE switch system call */
 1:	mfspr	r12,SPRN_SRR1
 	xori	r12,r12,MSR_LE
@@ -228,6 +219,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_REAL_LE)
 	b	.
 
 	STD_EXCEPTION_PSERIES(0xd00, 0xd00, single_step)
+	KVM_HANDLER(PACA_EXGEN, EXC_STD, 0xd00)
 
 	/* At 0xe??? we have a bunch of hypervisor exceptions, we branch
 	 * out of line to handle them
@@ -262,30 +254,93 @@ vsx_unavailable_pSeries_1:
 
 #ifdef CONFIG_CBE_RAS
 	STD_EXCEPTION_HV(0x1200, 0x1202, cbe_system_error)
+	KVM_HANDLER_SKIP(PACA_EXGEN, EXC_HV, 0x1202)
 #endif /* CONFIG_CBE_RAS */
+
 	STD_EXCEPTION_PSERIES(0x1300, 0x1300, instruction_breakpoint)
+	KVM_HANDLER_SKIP(PACA_EXGEN, EXC_STD, 0x1300)
+
 #ifdef CONFIG_CBE_RAS
 	STD_EXCEPTION_HV(0x1600, 0x1602, cbe_maintenance)
+	KVM_HANDLER_SKIP(PACA_EXGEN, EXC_HV, 0x1602)
 #endif /* CONFIG_CBE_RAS */
+
 	STD_EXCEPTION_PSERIES(0x1700, 0x1700, altivec_assist)
+	KVM_HANDLER(PACA_EXGEN, EXC_STD, 0x1700)
+
 #ifdef CONFIG_CBE_RAS
 	STD_EXCEPTION_HV(0x1800, 0x1802, cbe_thermal)
+	KVM_HANDLER_SKIP(PACA_EXGEN, EXC_HV, 0x1802)
 #endif /* CONFIG_CBE_RAS */
 
 	. = 0x3000
 
 /*** Out of line interrupts support ***/
 
+	/* moved from 0x200 */
+machine_check_pSeries:
+	.globl machine_check_fwnmi
+machine_check_fwnmi:
+	HMT_MEDIUM
+	SET_SCRATCH0(r13)		/* save r13 */
+	EXCEPTION_PROLOG_PSERIES(PACA_EXMC, machine_check_common,
+				 EXC_STD, KVMTEST, 0x200)
+	KVM_HANDLER_SKIP(PACA_EXMC, EXC_STD, 0x200)
+
+#ifndef CONFIG_POWER4_ONLY
+	/* moved from 0x300 */
+data_access_check_stab:
+	GET_PACA(r13)
+	std	r9,PACA_EXSLB+EX_R9(r13)
+	std	r10,PACA_EXSLB+EX_R10(r13)
+	mfspr	r10,SPRN_DAR
+	mfspr	r9,SPRN_DSISR
+	srdi	r10,r10,60
+	rlwimi	r10,r9,16,0x20
+#ifdef CONFIG_KVM_BOOK3S_64_HANDLER
+	lbz	r9,PACA_KVM_SVCPU+SVCPU_IN_GUEST(r13)
+	rlwimi	r10,r9,8,0x300
+#endif
+	mfcr	r9
+	cmpwi	r10,0x2c
+	beq	do_stab_bolted_pSeries
+	mtcrf	0x80,r9
+	ld	r9,PACA_EXSLB+EX_R9(r13)
+	ld	r10,PACA_EXSLB+EX_R10(r13)
+	b	data_access_not_stab
+do_stab_bolted_pSeries:
+	std	r11,PACA_EXSLB+EX_R11(r13)
+	std	r12,PACA_EXSLB+EX_R12(r13)
+	GET_SCRATCH0(r10)
+	std	r10,PACA_EXSLB+EX_R13(r13)
+	EXCEPTION_PROLOG_PSERIES_1(.do_stab_bolted, EXC_STD)
+#endif /* CONFIG_POWER4_ONLY */
+
+	KVM_HANDLER_SKIP(PACA_EXGEN, EXC_STD, 0x300)
+	KVM_HANDLER_SKIP(PACA_EXSLB, EXC_STD, 0x380)
+	KVM_HANDLER(PACA_EXGEN, EXC_STD, 0x400)
+	KVM_HANDLER(PACA_EXSLB, EXC_STD, 0x480)
+	KVM_HANDLER(PACA_EXGEN, EXC_STD, 0x900)
+	KVM_HANDLER(PACA_EXGEN, EXC_HV, 0x982)
+
+	.align	7
 	/* moved from 0xe00 */
-	STD_EXCEPTION_HV(., 0xe00, h_data_storage)
-	STD_EXCEPTION_HV(., 0xe20, h_instr_storage)
-	STD_EXCEPTION_HV(., 0xe40, emulation_assist)
-	STD_EXCEPTION_HV(., 0xe60, hmi_exception) /* need to flush cache ? */
+	STD_EXCEPTION_HV(., 0xe02, h_data_storage)
+	KVM_HANDLER_SKIP(PACA_EXGEN, EXC_HV, 0xe02)
+	STD_EXCEPTION_HV(., 0xe22, h_instr_storage)
+	KVM_HANDLER(PACA_EXGEN, EXC_HV, 0xe22)
+	STD_EXCEPTION_HV(., 0xe42, emulation_assist)
+	KVM_HANDLER(PACA_EXGEN, EXC_HV, 0xe42)
+	STD_EXCEPTION_HV(., 0xe62, hmi_exception) /* need to flush cache ? */
+	KVM_HANDLER(PACA_EXGEN, EXC_HV, 0xe62)
 
 	/* moved from 0xf00 */
 	STD_EXCEPTION_PSERIES(., 0xf00, performance_monitor)
+	KVM_HANDLER(PACA_EXGEN, EXC_STD, 0xf00)
 	STD_EXCEPTION_PSERIES(., 0xf20, altivec_unavailable)
+	KVM_HANDLER(PACA_EXGEN, EXC_STD, 0xf20)
 	STD_EXCEPTION_PSERIES(., 0xf40, vsx_unavailable)
+	KVM_HANDLER(PACA_EXGEN, EXC_STD, 0xf40)
 
 /*
  * An interrupt came in while soft-disabled; clear EE in SRR1,
@@ -317,14 +372,6 @@ masked_Hinterrupt:
 	hrfid
 	b	.
 
-	.align	7
-do_stab_bolted_pSeries:
-	std	r11,PACA_EXSLB+EX_R11(r13)
-	std	r12,PACA_EXSLB+EX_R12(r13)
-	GET_SCRATCH0(r10)
-	std	r10,PACA_EXSLB+EX_R13(r13)
-	EXCEPTION_PROLOG_PSERIES_1(.do_stab_bolted, EXC_STD)
-
 #ifdef CONFIG_PPC_PSERIES
 /*
  * Vectors for the FWNMI option.  Share common code.
@@ -334,14 +381,8 @@ do_stab_bolted_pSeries:
 system_reset_fwnmi:
 	HMT_MEDIUM
 	SET_SCRATCH0(r13)		/* save r13 */
-	EXCEPTION_PROLOG_PSERIES(PACA_EXGEN, system_reset_common, EXC_STD)
-
-	.globl machine_check_fwnmi
-      .align 7
-machine_check_fwnmi:
-	HMT_MEDIUM
-	SET_SCRATCH0(r13)		/* save r13 */
-	EXCEPTION_PROLOG_PSERIES(PACA_EXMC, machine_check_common, EXC_STD)
+	EXCEPTION_PROLOG_PSERIES(PACA_EXGEN, system_reset_common, EXC_STD,
+				 NOTEST, 0x100)
 
 #endif /* CONFIG_PPC_PSERIES */
 
-- 
cgit v1.2.3


From 923c53caea446d246949c94703be83e68f251af7 Mon Sep 17 00:00:00 2001
From: Paul Mackerras <paulus@samba.org>
Date: Wed, 29 Jun 2011 00:20:24 +0000
Subject: powerpc: Set up LPCR for running guest partitions

In hypervisor mode, the LPCR controls several aspects of guest
partitions, including virtual partition memory mode, and also controls
whether the hypervisor decrementer interrupts are enabled.  This sets
up LPCR at boot time so that guest partitions will use a virtual real
memory area (VRMA) composed of 16MB large pages, and hypervisor
decrementer interrupts are disabled.

Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Alexander Graf <agraf@suse.de>
---
 arch/powerpc/kernel/cpu_setup_power7.S | 18 +++++++++++-------
 1 file changed, 11 insertions(+), 7 deletions(-)

(limited to 'arch/powerpc/kernel')

diff --git a/arch/powerpc/kernel/cpu_setup_power7.S b/arch/powerpc/kernel/cpu_setup_power7.S
index 4f9a93fcfe07..2ef6749688e9 100644
--- a/arch/powerpc/kernel/cpu_setup_power7.S
+++ b/arch/powerpc/kernel/cpu_setup_power7.S
@@ -61,19 +61,23 @@ __init_LPCR:
 	 *   LPES = 0b01 (HSRR0/1 used for 0x500)
 	 *   PECE = 0b111
 	 *   DPFD = 4
+	 *   HDICE = 0
+	 *   VC = 0b100 (VPM0=1, VPM1=0, ISL=0)
+	 *   VRMASD = 0b10000 (L=1, LP=00)
 	 *
 	 * Other bits untouched for now
 	 */
 	mfspr	r3,SPRN_LPCR
-	ori	r3,r3,(LPCR_LPES0|LPCR_LPES1)
-	xori	r3,r3, LPCR_LPES0
+	li	r5,1
+	rldimi	r3,r5, LPCR_LPES_SH, 64-LPCR_LPES_SH-2
 	ori	r3,r3,(LPCR_PECE0|LPCR_PECE1|LPCR_PECE2)
-	li	r5,7
-	sldi	r5,r5,LPCR_DPFD_SH
-	andc	r3,r3,r5
 	li	r5,4
-	sldi	r5,r5,LPCR_DPFD_SH
-	or	r3,r3,r5
+	rldimi	r3,r5, LPCR_DPFD_SH, 64-LPCR_DPFD_SH-3
+	clrrdi	r3,r3,1		/* clear HDICE */
+	li	r5,4
+	rldimi	r3,r5, LPCR_VC_SH, 0
+	li	r5,0x10
+	rldimi	r3,r5, LPCR_VRMASD_SH, 64-LPCR_VRMASD_SH-5
 	mtspr	SPRN_LPCR,r3
 	isync
 	blr
-- 
cgit v1.2.3


From 3c42bf8a717cb636e0ed2ed77194669e2ac3ed56 Mon Sep 17 00:00:00 2001
From: Paul Mackerras <paulus@samba.org>
Date: Wed, 29 Jun 2011 00:20:58 +0000
Subject: KVM: PPC: Split host-state fields out of kvmppc_book3s_shadow_vcpu

There are several fields in struct kvmppc_book3s_shadow_vcpu that
temporarily store bits of host state while a guest is running,
rather than anything relating to the particular guest or vcpu.
This splits them out into a new kvmppc_host_state structure and
modifies the definitions in asm-offsets.c to suit.

On 32-bit, we have a kvmppc_host_state structure inside the
kvmppc_book3s_shadow_vcpu since the assembly code needs to be able
to get to them both with one pointer.  On 64-bit they are separate
fields in the PACA.  This means that on 64-bit we don't need to
copy the kvmppc_host_state in and out on vcpu load/unload, and
in future will mean that the book3s_hv code doesn't need a
shadow_vcpu struct in the PACA at all.  That does mean that we
have to be careful not to rely on any values persisting in the
hstate field of the paca across any point where we could block
or get preempted.

Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Alexander Graf <agraf@suse.de>
---
 arch/powerpc/kernel/asm-offsets.c    | 94 ++++++++++++++++++------------------
 arch/powerpc/kernel/exceptions-64s.S |  2 +-
 2 files changed, 48 insertions(+), 48 deletions(-)

(limited to 'arch/powerpc/kernel')

diff --git a/arch/powerpc/kernel/asm-offsets.c b/arch/powerpc/kernel/asm-offsets.c
index faf846131f45..dabfb7346f36 100644
--- a/arch/powerpc/kernel/asm-offsets.c
+++ b/arch/powerpc/kernel/asm-offsets.c
@@ -198,11 +198,6 @@ int main(void)
 	DEFINE(PACA_USER_TIME, offsetof(struct paca_struct, user_time));
 	DEFINE(PACA_SYSTEM_TIME, offsetof(struct paca_struct, system_time));
 	DEFINE(PACA_TRAP_SAVE, offsetof(struct paca_struct, trap_save));
-#ifdef CONFIG_KVM_BOOK3S_64_HANDLER
-	DEFINE(PACA_KVM_SVCPU, offsetof(struct paca_struct, shadow_vcpu));
-	DEFINE(SVCPU_SLB, offsetof(struct kvmppc_book3s_shadow_vcpu, slb));
-	DEFINE(SVCPU_SLB_MAX, offsetof(struct kvmppc_book3s_shadow_vcpu, slb_max));
-#endif
 #endif /* CONFIG_PPC64 */
 
 	/* RTAS */
@@ -416,49 +411,54 @@ int main(void)
 	DEFINE(VCPU_HIGHMEM_HANDLER, offsetof(struct kvm_vcpu, arch.highmem_handler));
 	DEFINE(VCPU_RMCALL, offsetof(struct kvm_vcpu, arch.rmcall));
 	DEFINE(VCPU_HFLAGS, offsetof(struct kvm_vcpu, arch.hflags));
-	DEFINE(VCPU_SVCPU, offsetof(struct kvmppc_vcpu_book3s, shadow_vcpu) -
-			   offsetof(struct kvmppc_vcpu_book3s, vcpu));
-	DEFINE(SVCPU_CR, offsetof(struct kvmppc_book3s_shadow_vcpu, cr));
-	DEFINE(SVCPU_XER, offsetof(struct kvmppc_book3s_shadow_vcpu, xer));
-	DEFINE(SVCPU_CTR, offsetof(struct kvmppc_book3s_shadow_vcpu, ctr));
-	DEFINE(SVCPU_LR, offsetof(struct kvmppc_book3s_shadow_vcpu, lr));
-	DEFINE(SVCPU_PC, offsetof(struct kvmppc_book3s_shadow_vcpu, pc));
-	DEFINE(SVCPU_R0, offsetof(struct kvmppc_book3s_shadow_vcpu, gpr[0]));
-	DEFINE(SVCPU_R1, offsetof(struct kvmppc_book3s_shadow_vcpu, gpr[1]));
-	DEFINE(SVCPU_R2, offsetof(struct kvmppc_book3s_shadow_vcpu, gpr[2]));
-	DEFINE(SVCPU_R3, offsetof(struct kvmppc_book3s_shadow_vcpu, gpr[3]));
-	DEFINE(SVCPU_R4, offsetof(struct kvmppc_book3s_shadow_vcpu, gpr[4]));
-	DEFINE(SVCPU_R5, offsetof(struct kvmppc_book3s_shadow_vcpu, gpr[5]));
-	DEFINE(SVCPU_R6, offsetof(struct kvmppc_book3s_shadow_vcpu, gpr[6]));
-	DEFINE(SVCPU_R7, offsetof(struct kvmppc_book3s_shadow_vcpu, gpr[7]));
-	DEFINE(SVCPU_R8, offsetof(struct kvmppc_book3s_shadow_vcpu, gpr[8]));
-	DEFINE(SVCPU_R9, offsetof(struct kvmppc_book3s_shadow_vcpu, gpr[9]));
-	DEFINE(SVCPU_R10, offsetof(struct kvmppc_book3s_shadow_vcpu, gpr[10]));
-	DEFINE(SVCPU_R11, offsetof(struct kvmppc_book3s_shadow_vcpu, gpr[11]));
-	DEFINE(SVCPU_R12, offsetof(struct kvmppc_book3s_shadow_vcpu, gpr[12]));
-	DEFINE(SVCPU_R13, offsetof(struct kvmppc_book3s_shadow_vcpu, gpr[13]));
-	DEFINE(SVCPU_HOST_R1, offsetof(struct kvmppc_book3s_shadow_vcpu, host_r1));
-	DEFINE(SVCPU_HOST_R2, offsetof(struct kvmppc_book3s_shadow_vcpu, host_r2));
-	DEFINE(SVCPU_VMHANDLER, offsetof(struct kvmppc_book3s_shadow_vcpu,
-					 vmhandler));
-	DEFINE(SVCPU_SCRATCH0, offsetof(struct kvmppc_book3s_shadow_vcpu,
-					scratch0));
-	DEFINE(SVCPU_SCRATCH1, offsetof(struct kvmppc_book3s_shadow_vcpu,
-					scratch1));
-	DEFINE(SVCPU_IN_GUEST, offsetof(struct kvmppc_book3s_shadow_vcpu,
-					in_guest));
-	DEFINE(SVCPU_FAULT_DSISR, offsetof(struct kvmppc_book3s_shadow_vcpu,
-					   fault_dsisr));
-	DEFINE(SVCPU_FAULT_DAR, offsetof(struct kvmppc_book3s_shadow_vcpu,
-					 fault_dar));
-	DEFINE(SVCPU_LAST_INST, offsetof(struct kvmppc_book3s_shadow_vcpu,
-					 last_inst));
-	DEFINE(SVCPU_SHADOW_SRR1, offsetof(struct kvmppc_book3s_shadow_vcpu,
-					   shadow_srr1));
+
+#ifdef CONFIG_PPC_BOOK3S_64
+# define SVCPU_FIELD(x, f)	DEFINE(x, offsetof(struct paca_struct, shadow_vcpu.f))
+# define HSTATE_FIELD(x, f)	DEFINE(x, offsetof(struct paca_struct, kvm_hstate.f))
+#else	/* 32-bit */
+# define SVCPU_FIELD(x, f)	DEFINE(x, offsetof(struct kvmppc_book3s_shadow_vcpu, f))
+# define HSTATE_FIELD(x, f)	DEFINE(x, offsetof(struct kvmppc_book3s_shadow_vcpu, hstate.f))
+#endif
+
+	SVCPU_FIELD(SVCPU_CR, cr);
+	SVCPU_FIELD(SVCPU_XER, xer);
+	SVCPU_FIELD(SVCPU_CTR, ctr);
+	SVCPU_FIELD(SVCPU_LR, lr);
+	SVCPU_FIELD(SVCPU_PC, pc);
+	SVCPU_FIELD(SVCPU_R0, gpr[0]);
+	SVCPU_FIELD(SVCPU_R1, gpr[1]);
+	SVCPU_FIELD(SVCPU_R2, gpr[2]);
+	SVCPU_FIELD(SVCPU_R3, gpr[3]);
+	SVCPU_FIELD(SVCPU_R4, gpr[4]);
+	SVCPU_FIELD(SVCPU_R5, gpr[5]);
+	SVCPU_FIELD(SVCPU_R6, gpr[6]);
+	SVCPU_FIELD(SVCPU_R7, gpr[7]);
+	SVCPU_FIELD(SVCPU_R8, gpr[8]);
+	SVCPU_FIELD(SVCPU_R9, gpr[9]);
+	SVCPU_FIELD(SVCPU_R10, gpr[10]);
+	SVCPU_FIELD(SVCPU_R11, gpr[11]);
+	SVCPU_FIELD(SVCPU_R12, gpr[12]);
+	SVCPU_FIELD(SVCPU_R13, gpr[13]);
+	SVCPU_FIELD(SVCPU_FAULT_DSISR, fault_dsisr);
+	SVCPU_FIELD(SVCPU_FAULT_DAR, fault_dar);
+	SVCPU_FIELD(SVCPU_LAST_INST, last_inst);
+	SVCPU_FIELD(SVCPU_SHADOW_SRR1, shadow_srr1);
 #ifdef CONFIG_PPC_BOOK3S_32
-	DEFINE(SVCPU_SR, offsetof(struct kvmppc_book3s_shadow_vcpu, sr));
+	SVCPU_FIELD(SVCPU_SR, sr);
 #endif
-#else
+#ifdef CONFIG_PPC64
+	SVCPU_FIELD(SVCPU_SLB, slb);
+	SVCPU_FIELD(SVCPU_SLB_MAX, slb_max);
+#endif
+
+	HSTATE_FIELD(HSTATE_HOST_R1, host_r1);
+	HSTATE_FIELD(HSTATE_HOST_R2, host_r2);
+	HSTATE_FIELD(HSTATE_VMHANDLER, vmhandler);
+	HSTATE_FIELD(HSTATE_SCRATCH0, scratch0);
+	HSTATE_FIELD(HSTATE_SCRATCH1, scratch1);
+	HSTATE_FIELD(HSTATE_IN_GUEST, in_guest);
+
+#else /* CONFIG_PPC_BOOK3S */
 	DEFINE(VCPU_CR, offsetof(struct kvm_vcpu, arch.cr));
 	DEFINE(VCPU_XER, offsetof(struct kvm_vcpu, arch.xer));
 	DEFINE(VCPU_LR, offsetof(struct kvm_vcpu, arch.lr));
@@ -468,7 +468,7 @@ int main(void)
 	DEFINE(VCPU_FAULT_DEAR, offsetof(struct kvm_vcpu, arch.fault_dear));
 	DEFINE(VCPU_FAULT_ESR, offsetof(struct kvm_vcpu, arch.fault_esr));
 #endif /* CONFIG_PPC_BOOK3S */
-#endif
+#endif /* CONFIG_KVM */
 
 #ifdef CONFIG_KVM_GUEST
 	DEFINE(KVM_MAGIC_SCRATCH1, offsetof(struct kvm_vcpu_arch_shared,
diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S
index e76472cbf3b5..6da00550afea 100644
--- a/arch/powerpc/kernel/exceptions-64s.S
+++ b/arch/powerpc/kernel/exceptions-64s.S
@@ -298,7 +298,7 @@ data_access_check_stab:
 	srdi	r10,r10,60
 	rlwimi	r10,r9,16,0x20
 #ifdef CONFIG_KVM_BOOK3S_64_HANDLER
-	lbz	r9,PACA_KVM_SVCPU+SVCPU_IN_GUEST(r13)
+	lbz	r9,HSTATE_IN_GUEST(r13)
 	rlwimi	r10,r9,8,0x300
 #endif
 	mfcr	r9
-- 
cgit v1.2.3


From de56a948b9182fbcf92cb8212f114de096c2d574 Mon Sep 17 00:00:00 2001
From: Paul Mackerras <paulus@samba.org>
Date: Wed, 29 Jun 2011 00:21:34 +0000
Subject: KVM: PPC: Add support for Book3S processors in hypervisor mode

This adds support for KVM running on 64-bit Book 3S processors,
specifically POWER7, in hypervisor mode.  Using hypervisor mode means
that the guest can use the processor's supervisor mode.  That means
that the guest can execute privileged instructions and access privileged
registers itself without trapping to the host.  This gives excellent
performance, but does mean that KVM cannot emulate a processor
architecture other than the one that the hardware implements.

This code assumes that the guest is running paravirtualized using the
PAPR (Power Architecture Platform Requirements) interface, which is the
interface that IBM's PowerVM hypervisor uses.  That means that existing
Linux distributions that run on IBM pSeries machines will also run
under KVM without modification.  In order to communicate the PAPR
hypercalls to qemu, this adds a new KVM_EXIT_PAPR_HCALL exit code
to include/linux/kvm.h.

Currently the choice between book3s_hv support and book3s_pr support
(i.e. the existing code, which runs the guest in user mode) has to be
made at kernel configuration time, so a given kernel binary can only
do one or the other.

This new book3s_hv code doesn't support MMIO emulation at present.
Since we are running paravirtualized guests, this isn't a serious
restriction.

With the guest running in supervisor mode, most exceptions go straight
to the guest.  We will never get data or instruction storage or segment
interrupts, alignment interrupts, decrementer interrupts, program
interrupts, single-step interrupts, etc., coming to the hypervisor from
the guest.  Therefore this introduces a new KVMTEST_NONHV macro for the
exception entry path so that we don't have to do the KVM test on entry
to those exception handlers.

We do however get hypervisor decrementer, hypervisor data storage,
hypervisor instruction storage, and hypervisor emulation assist
interrupts, so we have to handle those.

In hypervisor mode, real-mode accesses can access all of RAM, not just
a limited amount.  Therefore we put all the guest state in the vcpu.arch
and use the shadow_vcpu in the PACA only for temporary scratch space.
We allocate the vcpu with kzalloc rather than vzalloc, and we don't use
anything in the kvmppc_vcpu_book3s struct, so we don't allocate it.
We don't have a shared page with the guest, but we still need a
kvm_vcpu_arch_shared struct to store the values of various registers,
so we include one in the vcpu_arch struct.

The POWER7 processor has a restriction that all threads in a core have
to be in the same partition.  MMU-on kernel code counts as a partition
(partition 0), so we have to do a partition switch on every entry to and
exit from the guest.  At present we require the host and guest to run
in single-thread mode because of this hardware restriction.

This code allocates a hashed page table for the guest and initializes
it with HPTEs for the guest's Virtual Real Memory Area (VRMA).  We
require that the guest memory is allocated using 16MB huge pages, in
order to simplify the low-level memory management.  This also means that
we can get away without tracking paging activity in the host for now,
since huge pages can't be paged or swapped.

This also adds a few new exports needed by the book3s_hv code.

Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Alexander Graf <agraf@suse.de>
---
 arch/powerpc/kernel/asm-offsets.c    | 79 ++++++++++++++++++++++++++++++++++++
 arch/powerpc/kernel/exceptions-64s.S | 60 ++++++++++++++-------------
 arch/powerpc/kernel/process.c        |  3 ++
 arch/powerpc/kernel/setup-common.c   |  3 ++
 arch/powerpc/kernel/smp.c            |  1 +
 5 files changed, 118 insertions(+), 28 deletions(-)

(limited to 'arch/powerpc/kernel')

diff --git a/arch/powerpc/kernel/asm-offsets.c b/arch/powerpc/kernel/asm-offsets.c
index dabfb7346f36..936267462cae 100644
--- a/arch/powerpc/kernel/asm-offsets.c
+++ b/arch/powerpc/kernel/asm-offsets.c
@@ -187,6 +187,7 @@ int main(void)
 	DEFINE(LPPACASRR1, offsetof(struct lppaca, saved_srr1));
 	DEFINE(LPPACAANYINT, offsetof(struct lppaca, int_dword.any_int));
 	DEFINE(LPPACADECRINT, offsetof(struct lppaca, int_dword.fields.decr_int));
+	DEFINE(LPPACA_PMCINUSE, offsetof(struct lppaca, pmcregs_in_use));
 	DEFINE(LPPACA_DTLIDX, offsetof(struct lppaca, dtl_idx));
 	DEFINE(PACA_DTL_RIDX, offsetof(struct paca_struct, dtl_ridx));
 #endif /* CONFIG_PPC_STD_MMU_64 */
@@ -392,6 +393,29 @@ int main(void)
 	DEFINE(VCPU_HOST_PID, offsetof(struct kvm_vcpu, arch.host_pid));
 	DEFINE(VCPU_GPRS, offsetof(struct kvm_vcpu, arch.gpr));
 	DEFINE(VCPU_VRSAVE, offsetof(struct kvm_vcpu, arch.vrsave));
+	DEFINE(VCPU_FPRS, offsetof(struct kvm_vcpu, arch.fpr));
+	DEFINE(VCPU_FPSCR, offsetof(struct kvm_vcpu, arch.fpscr));
+#ifdef CONFIG_ALTIVEC
+	DEFINE(VCPU_VRS, offsetof(struct kvm_vcpu, arch.vr));
+	DEFINE(VCPU_VSCR, offsetof(struct kvm_vcpu, arch.vscr));
+#endif
+#ifdef CONFIG_VSX
+	DEFINE(VCPU_VSRS, offsetof(struct kvm_vcpu, arch.vsr));
+#endif
+	DEFINE(VCPU_XER, offsetof(struct kvm_vcpu, arch.xer));
+	DEFINE(VCPU_CTR, offsetof(struct kvm_vcpu, arch.ctr));
+	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
+	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));
+	DEFINE(VCPU_SPRG0, offsetof(struct kvm_vcpu, arch.shregs.sprg0));
+	DEFINE(VCPU_SPRG1, offsetof(struct kvm_vcpu, arch.shregs.sprg1));
+	DEFINE(VCPU_SPRG2, offsetof(struct kvm_vcpu, arch.shregs.sprg2));
+	DEFINE(VCPU_SPRG3, offsetof(struct kvm_vcpu, arch.shregs.sprg3));
+#endif
 	DEFINE(VCPU_SPRG4, offsetof(struct kvm_vcpu, arch.sprg4));
 	DEFINE(VCPU_SPRG5, offsetof(struct kvm_vcpu, arch.sprg5));
 	DEFINE(VCPU_SPRG6, offsetof(struct kvm_vcpu, arch.sprg6));
@@ -403,17 +427,60 @@ int main(void)
 	DEFINE(VCPU_SHADOW_MSR, offsetof(struct kvm_vcpu, arch.shadow_msr));
 
 	/* book3s */
+#ifdef CONFIG_KVM_BOOK3S_64_HV
+	DEFINE(KVM_LPID, offsetof(struct kvm, arch.lpid));
+	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));
+	DEFINE(KVM_HOST_SDR1, offsetof(struct kvm, arch.host_sdr1));
+	DEFINE(KVM_TLBIE_LOCK, offsetof(struct kvm, arch.tlbie_lock));
+	DEFINE(KVM_ONLINE_CPUS, offsetof(struct kvm, online_vcpus.counter));
+	DEFINE(KVM_LAST_VCPU, offsetof(struct kvm, arch.last_vcpu));
+	DEFINE(VCPU_DSISR, offsetof(struct kvm_vcpu, arch.shregs.dsisr));
+	DEFINE(VCPU_DAR, offsetof(struct kvm_vcpu, arch.shregs.dar));
+#endif
 #ifdef CONFIG_PPC_BOOK3S
+	DEFINE(VCPU_KVM, offsetof(struct kvm_vcpu, kvm));
+	DEFINE(VCPU_VCPUID, offsetof(struct kvm_vcpu, vcpu_id));
 	DEFINE(VCPU_HOST_RETIP, offsetof(struct kvm_vcpu, arch.host_retip));
 	DEFINE(VCPU_HOST_MSR, offsetof(struct kvm_vcpu, arch.host_msr));
+	DEFINE(VCPU_PURR, offsetof(struct kvm_vcpu, arch.purr));
+	DEFINE(VCPU_SPURR, offsetof(struct kvm_vcpu, arch.spurr));
+	DEFINE(VCPU_DSCR, offsetof(struct kvm_vcpu, arch.dscr));
+	DEFINE(VCPU_AMR, offsetof(struct kvm_vcpu, arch.amr));
+	DEFINE(VCPU_UAMOR, offsetof(struct kvm_vcpu, arch.uamor));
+	DEFINE(VCPU_CTRL, offsetof(struct kvm_vcpu, arch.ctrl));
+	DEFINE(VCPU_DABR, offsetof(struct kvm_vcpu, arch.dabr));
 	DEFINE(VCPU_TRAMPOLINE_LOWMEM, offsetof(struct kvm_vcpu, arch.trampoline_lowmem));
 	DEFINE(VCPU_TRAMPOLINE_ENTER, offsetof(struct kvm_vcpu, arch.trampoline_enter));
 	DEFINE(VCPU_HIGHMEM_HANDLER, offsetof(struct kvm_vcpu, arch.highmem_handler));
 	DEFINE(VCPU_RMCALL, offsetof(struct kvm_vcpu, arch.rmcall));
 	DEFINE(VCPU_HFLAGS, offsetof(struct kvm_vcpu, arch.hflags));
+	DEFINE(VCPU_DEC, offsetof(struct kvm_vcpu, arch.dec));
+	DEFINE(VCPU_DEC_EXPIRES, offsetof(struct kvm_vcpu, arch.dec_expires));
+	DEFINE(VCPU_LPCR, offsetof(struct kvm_vcpu, arch.lpcr));
+	DEFINE(VCPU_MMCR, offsetof(struct kvm_vcpu, arch.mmcr));
+	DEFINE(VCPU_PMC, offsetof(struct kvm_vcpu, arch.pmc));
+	DEFINE(VCPU_SLB, offsetof(struct kvm_vcpu, arch.slb));
+	DEFINE(VCPU_SLB_MAX, offsetof(struct kvm_vcpu, arch.slb_max));
+	DEFINE(VCPU_SLB_NR, offsetof(struct kvm_vcpu, arch.slb_nr));
+	DEFINE(VCPU_LAST_CPU, offsetof(struct kvm_vcpu, arch.last_cpu));
+	DEFINE(VCPU_FAULT_DSISR, offsetof(struct kvm_vcpu, arch.fault_dsisr));
+	DEFINE(VCPU_FAULT_DAR, offsetof(struct kvm_vcpu, arch.fault_dar));
+	DEFINE(VCPU_LAST_INST, offsetof(struct kvm_vcpu, arch.last_inst));
+	DEFINE(VCPU_TRAP, offsetof(struct kvm_vcpu, arch.trap));
+	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 SVCPU_FIELD(x, f)	DEFINE(x, offsetof(struct paca_struct, shadow_vcpu.f))
+#else
+# define SVCPU_FIELD(x, f)
+#endif
 # define HSTATE_FIELD(x, f)	DEFINE(x, offsetof(struct paca_struct, kvm_hstate.f))
 #else	/* 32-bit */
 # define SVCPU_FIELD(x, f)	DEFINE(x, offsetof(struct kvmppc_book3s_shadow_vcpu, f))
@@ -453,11 +520,23 @@ int main(void)
 
 	HSTATE_FIELD(HSTATE_HOST_R1, host_r1);
 	HSTATE_FIELD(HSTATE_HOST_R2, host_r2);
+	HSTATE_FIELD(HSTATE_HOST_MSR, host_msr);
 	HSTATE_FIELD(HSTATE_VMHANDLER, vmhandler);
 	HSTATE_FIELD(HSTATE_SCRATCH0, scratch0);
 	HSTATE_FIELD(HSTATE_SCRATCH1, scratch1);
 	HSTATE_FIELD(HSTATE_IN_GUEST, in_guest);
 
+#ifdef CONFIG_KVM_BOOK3S_64_HV
+	HSTATE_FIELD(HSTATE_KVM_VCPU, kvm_vcpu);
+	HSTATE_FIELD(HSTATE_MMCR, host_mmcr);
+	HSTATE_FIELD(HSTATE_PMC, host_pmc);
+	HSTATE_FIELD(HSTATE_PURR, host_purr);
+	HSTATE_FIELD(HSTATE_SPURR, host_spurr);
+	HSTATE_FIELD(HSTATE_DSCR, host_dscr);
+	HSTATE_FIELD(HSTATE_DABR, dabr);
+	HSTATE_FIELD(HSTATE_DECEXP, dec_expires);
+#endif /* CONFIG_KVM_BOOK3S_64_HV */
+
 #else /* CONFIG_PPC_BOOK3S */
 	DEFINE(VCPU_CR, offsetof(struct kvm_vcpu, arch.cr));
 	DEFINE(VCPU_XER, offsetof(struct kvm_vcpu, arch.xer));
diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S
index 6da00550afea..163c041cec24 100644
--- a/arch/powerpc/kernel/exceptions-64s.S
+++ b/arch/powerpc/kernel/exceptions-64s.S
@@ -87,14 +87,14 @@ data_access_not_stab:
 END_MMU_FTR_SECTION_IFCLR(MMU_FTR_SLB)
 #endif
 	EXCEPTION_PROLOG_PSERIES(PACA_EXGEN, data_access_common, EXC_STD,
-				 KVMTEST, 0x300)
+				 KVMTEST_PR, 0x300)
 
 	. = 0x380
 	.globl data_access_slb_pSeries
 data_access_slb_pSeries:
 	HMT_MEDIUM
 	SET_SCRATCH0(r13)
-	EXCEPTION_PROLOG_1(PACA_EXSLB, KVMTEST, 0x380)
+	EXCEPTION_PROLOG_1(PACA_EXSLB, KVMTEST_PR, 0x380)
 	std	r3,PACA_EXSLB+EX_R3(r13)
 	mfspr	r3,SPRN_DAR
 #ifdef __DISABLED__
@@ -125,7 +125,7 @@ data_access_slb_pSeries:
 instruction_access_slb_pSeries:
 	HMT_MEDIUM
 	SET_SCRATCH0(r13)
-	EXCEPTION_PROLOG_1(PACA_EXSLB, KVMTEST, 0x480)
+	EXCEPTION_PROLOG_1(PACA_EXSLB, KVMTEST_PR, 0x480)
 	std	r3,PACA_EXSLB+EX_R3(r13)
 	mfspr	r3,SPRN_SRR0		/* SRR0 is faulting address */
 #ifdef __DISABLED__
@@ -153,32 +153,32 @@ instruction_access_slb_pSeries:
 hardware_interrupt_pSeries:
 hardware_interrupt_hv:
 	BEGIN_FTR_SECTION
-		_MASKABLE_EXCEPTION_PSERIES(0x500, hardware_interrupt,
-					    EXC_STD, SOFTEN_TEST)
-		KVM_HANDLER(PACA_EXGEN, EXC_STD, 0x500)
-	FTR_SECTION_ELSE
 		_MASKABLE_EXCEPTION_PSERIES(0x502, hardware_interrupt,
 					    EXC_HV, SOFTEN_TEST_HV)
 		KVM_HANDLER(PACA_EXGEN, EXC_HV, 0x502)
-	ALT_FTR_SECTION_END_IFCLR(CPU_FTR_HVMODE_206)
+	FTR_SECTION_ELSE
+		_MASKABLE_EXCEPTION_PSERIES(0x500, hardware_interrupt,
+					    EXC_STD, SOFTEN_TEST_PR)
+		KVM_HANDLER(PACA_EXGEN, EXC_STD, 0x500)
+	ALT_FTR_SECTION_END_IFSET(CPU_FTR_HVMODE_206)
 
 	STD_EXCEPTION_PSERIES(0x600, 0x600, alignment)
-	KVM_HANDLER(PACA_EXGEN, EXC_STD, 0x600)
+	KVM_HANDLER_PR(PACA_EXGEN, EXC_STD, 0x600)
 
 	STD_EXCEPTION_PSERIES(0x700, 0x700, program_check)
-	KVM_HANDLER(PACA_EXGEN, EXC_STD, 0x700)
+	KVM_HANDLER_PR(PACA_EXGEN, EXC_STD, 0x700)
 
 	STD_EXCEPTION_PSERIES(0x800, 0x800, fp_unavailable)
-	KVM_HANDLER(PACA_EXGEN, EXC_STD, 0x800)
+	KVM_HANDLER_PR(PACA_EXGEN, EXC_STD, 0x800)
 
 	MASKABLE_EXCEPTION_PSERIES(0x900, 0x900, decrementer)
 	MASKABLE_EXCEPTION_HV(0x980, 0x982, decrementer)
 
 	STD_EXCEPTION_PSERIES(0xa00, 0xa00, trap_0a)
-	KVM_HANDLER(PACA_EXGEN, EXC_STD, 0xa00)
+	KVM_HANDLER_PR(PACA_EXGEN, EXC_STD, 0xa00)
 
 	STD_EXCEPTION_PSERIES(0xb00, 0xb00, trap_0b)
-	KVM_HANDLER(PACA_EXGEN, EXC_STD, 0xb00)
+	KVM_HANDLER_PR(PACA_EXGEN, EXC_STD, 0xb00)
 
 	. = 0xc00
 	.globl	system_call_pSeries
@@ -219,7 +219,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_REAL_LE)
 	b	.
 
 	STD_EXCEPTION_PSERIES(0xd00, 0xd00, single_step)
-	KVM_HANDLER(PACA_EXGEN, EXC_STD, 0xd00)
+	KVM_HANDLER_PR(PACA_EXGEN, EXC_STD, 0xd00)
 
 	/* At 0xe??? we have a bunch of hypervisor exceptions, we branch
 	 * out of line to handle them
@@ -254,23 +254,23 @@ vsx_unavailable_pSeries_1:
 
 #ifdef CONFIG_CBE_RAS
 	STD_EXCEPTION_HV(0x1200, 0x1202, cbe_system_error)
-	KVM_HANDLER_SKIP(PACA_EXGEN, EXC_HV, 0x1202)
+	KVM_HANDLER_PR_SKIP(PACA_EXGEN, EXC_HV, 0x1202)
 #endif /* CONFIG_CBE_RAS */
 
 	STD_EXCEPTION_PSERIES(0x1300, 0x1300, instruction_breakpoint)
-	KVM_HANDLER_SKIP(PACA_EXGEN, EXC_STD, 0x1300)
+	KVM_HANDLER_PR_SKIP(PACA_EXGEN, EXC_STD, 0x1300)
 
 #ifdef CONFIG_CBE_RAS
 	STD_EXCEPTION_HV(0x1600, 0x1602, cbe_maintenance)
-	KVM_HANDLER_SKIP(PACA_EXGEN, EXC_HV, 0x1602)
+	KVM_HANDLER_PR_SKIP(PACA_EXGEN, EXC_HV, 0x1602)
 #endif /* CONFIG_CBE_RAS */
 
 	STD_EXCEPTION_PSERIES(0x1700, 0x1700, altivec_assist)
-	KVM_HANDLER(PACA_EXGEN, EXC_STD, 0x1700)
+	KVM_HANDLER_PR(PACA_EXGEN, EXC_STD, 0x1700)
 
 #ifdef CONFIG_CBE_RAS
 	STD_EXCEPTION_HV(0x1800, 0x1802, cbe_thermal)
-	KVM_HANDLER_SKIP(PACA_EXGEN, EXC_HV, 0x1802)
+	KVM_HANDLER_PR_SKIP(PACA_EXGEN, EXC_HV, 0x1802)
 #endif /* CONFIG_CBE_RAS */
 
 	. = 0x3000
@@ -297,7 +297,7 @@ data_access_check_stab:
 	mfspr	r9,SPRN_DSISR
 	srdi	r10,r10,60
 	rlwimi	r10,r9,16,0x20
-#ifdef CONFIG_KVM_BOOK3S_64_HANDLER
+#ifdef CONFIG_KVM_BOOK3S_PR
 	lbz	r9,HSTATE_IN_GUEST(r13)
 	rlwimi	r10,r9,8,0x300
 #endif
@@ -316,11 +316,11 @@ do_stab_bolted_pSeries:
 	EXCEPTION_PROLOG_PSERIES_1(.do_stab_bolted, EXC_STD)
 #endif /* CONFIG_POWER4_ONLY */
 
-	KVM_HANDLER_SKIP(PACA_EXGEN, EXC_STD, 0x300)
-	KVM_HANDLER_SKIP(PACA_EXSLB, EXC_STD, 0x380)
-	KVM_HANDLER(PACA_EXGEN, EXC_STD, 0x400)
-	KVM_HANDLER(PACA_EXSLB, EXC_STD, 0x480)
-	KVM_HANDLER(PACA_EXGEN, EXC_STD, 0x900)
+	KVM_HANDLER_PR_SKIP(PACA_EXGEN, EXC_STD, 0x300)
+	KVM_HANDLER_PR_SKIP(PACA_EXSLB, EXC_STD, 0x380)
+	KVM_HANDLER_PR(PACA_EXGEN, EXC_STD, 0x400)
+	KVM_HANDLER_PR(PACA_EXSLB, EXC_STD, 0x480)
+	KVM_HANDLER_PR(PACA_EXGEN, EXC_STD, 0x900)
 	KVM_HANDLER(PACA_EXGEN, EXC_HV, 0x982)
 
 	.align	7
@@ -336,11 +336,11 @@ do_stab_bolted_pSeries:
 
 	/* moved from 0xf00 */
 	STD_EXCEPTION_PSERIES(., 0xf00, performance_monitor)
-	KVM_HANDLER(PACA_EXGEN, EXC_STD, 0xf00)
+	KVM_HANDLER_PR(PACA_EXGEN, EXC_STD, 0xf00)
 	STD_EXCEPTION_PSERIES(., 0xf20, altivec_unavailable)
-	KVM_HANDLER(PACA_EXGEN, EXC_STD, 0xf20)
+	KVM_HANDLER_PR(PACA_EXGEN, EXC_STD, 0xf20)
 	STD_EXCEPTION_PSERIES(., 0xf40, vsx_unavailable)
-	KVM_HANDLER(PACA_EXGEN, EXC_STD, 0xf40)
+	KVM_HANDLER_PR(PACA_EXGEN, EXC_STD, 0xf40)
 
 /*
  * An interrupt came in while soft-disabled; clear EE in SRR1,
@@ -417,7 +417,11 @@ slb_miss_user_pseries:
 /* KVM's trampoline code needs to be close to the interrupt handlers */
 
 #ifdef CONFIG_KVM_BOOK3S_64_HANDLER
+#ifdef CONFIG_KVM_BOOK3S_PR
 #include "../kvm/book3s_rmhandlers.S"
+#else
+#include "../kvm/book3s_hv_rmhandlers.S"
+#endif
 #endif
 
 	.align	7
diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c
index 60ac2a9251db..ec2d0edeb134 100644
--- a/arch/powerpc/kernel/process.c
+++ b/arch/powerpc/kernel/process.c
@@ -96,6 +96,7 @@ void flush_fp_to_thread(struct task_struct *tsk)
 		preempt_enable();
 	}
 }
+EXPORT_SYMBOL_GPL(flush_fp_to_thread);
 
 void enable_kernel_fp(void)
 {
@@ -145,6 +146,7 @@ void flush_altivec_to_thread(struct task_struct *tsk)
 		preempt_enable();
 	}
 }
+EXPORT_SYMBOL_GPL(flush_altivec_to_thread);
 #endif /* CONFIG_ALTIVEC */
 
 #ifdef CONFIG_VSX
@@ -186,6 +188,7 @@ void flush_vsx_to_thread(struct task_struct *tsk)
 		preempt_enable();
 	}
 }
+EXPORT_SYMBOL_GPL(flush_vsx_to_thread);
 #endif /* CONFIG_VSX */
 
 #ifdef CONFIG_SPE
diff --git a/arch/powerpc/kernel/setup-common.c b/arch/powerpc/kernel/setup-common.c
index 79fca2651b65..22051ef04bd9 100644
--- a/arch/powerpc/kernel/setup-common.c
+++ b/arch/powerpc/kernel/setup-common.c
@@ -375,6 +375,9 @@ void __init check_for_initrd(void)
 
 int threads_per_core, threads_shift;
 cpumask_t threads_core_mask;
+EXPORT_SYMBOL_GPL(threads_per_core);
+EXPORT_SYMBOL_GPL(threads_shift);
+EXPORT_SYMBOL_GPL(threads_core_mask);
 
 static void __init cpu_init_thread_core_maps(int tpc)
 {
diff --git a/arch/powerpc/kernel/smp.c b/arch/powerpc/kernel/smp.c
index 8ebc6700b98d..09a85a9045d6 100644
--- a/arch/powerpc/kernel/smp.c
+++ b/arch/powerpc/kernel/smp.c
@@ -243,6 +243,7 @@ void smp_send_reschedule(int cpu)
 	if (likely(smp_ops))
 		smp_ops->message_pass(cpu, PPC_MSG_RESCHEDULE);
 }
+EXPORT_SYMBOL_GPL(smp_send_reschedule);
 
 void arch_send_call_function_single_ipi(int cpu)
 {
-- 
cgit v1.2.3


From a8606e20e41a8149456bafdf76ad29d47672027c Mon Sep 17 00:00:00 2001
From: Paul Mackerras <paulus@samba.org>
Date: Wed, 29 Jun 2011 00:22:05 +0000
Subject: KVM: PPC: Handle some PAPR hcalls in the kernel

This adds the infrastructure for handling PAPR hcalls in the kernel,
either early in the guest exit path while we are still in real mode,
or later once the MMU has been turned back on and we are in the full
kernel context.  The advantage of handling hcalls in real mode if
possible is that we avoid two partition switches -- and this will
become more important when we support SMT4 guests, since a partition
switch means we have to pull all of the threads in the core out of
the guest.  The disadvantage is that we can only access the kernel
linear mapping, not anything vmalloced or ioremapped, since the MMU
is off.

This also adds code to handle the following hcalls in real mode:

H_ENTER       Add an HPTE to the hashed page table
H_REMOVE      Remove an HPTE from the hashed page table
H_READ        Read HPTEs from the hashed page table
H_PROTECT     Change the protection bits in an HPTE
H_BULK_REMOVE Remove up to 4 HPTEs from the hashed page table
H_SET_DABR    Set the data address breakpoint register

Plus code to handle the following hcalls in the kernel:

H_CEDE        Idle the vcpu until an interrupt or H_PROD hcall arrives
H_PROD        Wake up a ceded vcpu
H_REGISTER_VPA Register a virtual processor area (VPA)

The code that runs in real mode has to be in the base kernel, not in
the module, if KVM is compiled as a module.  The real-mode code can
only access the kernel linear mapping, not vmalloc or ioremap space.

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

(limited to 'arch/powerpc/kernel')

diff --git a/arch/powerpc/kernel/asm-offsets.c b/arch/powerpc/kernel/asm-offsets.c
index 936267462cae..c70d106bf1a4 100644
--- a/arch/powerpc/kernel/asm-offsets.c
+++ b/arch/powerpc/kernel/asm-offsets.c
@@ -189,6 +189,7 @@ int main(void)
 	DEFINE(LPPACADECRINT, offsetof(struct lppaca, int_dword.fields.decr_int));
 	DEFINE(LPPACA_PMCINUSE, offsetof(struct lppaca, pmcregs_in_use));
 	DEFINE(LPPACA_DTLIDX, offsetof(struct lppaca, dtl_idx));
+	DEFINE(LPPACA_YIELDCOUNT, offsetof(struct lppaca, yield_count));
 	DEFINE(PACA_DTL_RIDX, offsetof(struct paca_struct, dtl_ridx));
 #endif /* CONFIG_PPC_STD_MMU_64 */
 	DEFINE(PACAEMERGSP, offsetof(struct paca_struct, emergency_sp));
@@ -459,6 +460,7 @@ int main(void)
 	DEFINE(VCPU_DEC, offsetof(struct kvm_vcpu, arch.dec));
 	DEFINE(VCPU_DEC_EXPIRES, offsetof(struct kvm_vcpu, arch.dec_expires));
 	DEFINE(VCPU_LPCR, offsetof(struct kvm_vcpu, arch.lpcr));
+	DEFINE(VCPU_VPA, offsetof(struct kvm_vcpu, arch.vpa));
 	DEFINE(VCPU_MMCR, offsetof(struct kvm_vcpu, arch.mmcr));
 	DEFINE(VCPU_PMC, offsetof(struct kvm_vcpu, arch.pmc));
 	DEFINE(VCPU_SLB, offsetof(struct kvm_vcpu, arch.slb));
-- 
cgit v1.2.3


From 371fefd6f2dc46668e00871930dde613b88d4bde Mon Sep 17 00:00:00 2001
From: Paul Mackerras <paulus@samba.org>
Date: Wed, 29 Jun 2011 00:23:08 +0000
Subject: KVM: PPC: Allow book3s_hv guests to use SMT processor modes

This lifts the restriction that book3s_hv guests can only run one
hardware thread per core, and allows them to use up to 4 threads
per core on POWER7.  The host still has to run single-threaded.

This capability is advertised to qemu through a new KVM_CAP_PPC_SMT
capability.  The return value of the ioctl querying this capability
is the number of vcpus per virtual CPU core (vcore), currently 4.

To use this, the host kernel should be booted with all threads
active, and then all the secondary threads should be offlined.
This will put the secondary threads into nap mode.  KVM will then
wake them from nap mode and use them for running guest code (while
they are still offline).  To wake the secondary threads, we send
them an IPI using a new xics_wake_cpu() function, implemented in
arch/powerpc/sysdev/xics/icp-native.c.  In other words, at this stage
we assume that the platform has a XICS interrupt controller and
we are using icp-native.c to drive it.  Since the woken thread will
need to acknowledge and clear the IPI, we also export the base
physical address of the XICS registers using kvmppc_set_xics_phys()
for use in the low-level KVM book3s code.

When a vcpu is created, it is assigned to a virtual CPU core.
The vcore number is obtained by dividing the vcpu number by the
number of threads per core in the host.  This number is exported
to userspace via the KVM_CAP_PPC_SMT capability.  If qemu wishes
to run the guest in single-threaded mode, it should make all vcpu
numbers be multiples of the number of threads per core.

We distinguish three states of a vcpu: runnable (i.e., ready to execute
the guest), blocked (that is, idle), and busy in host.  We currently
implement a policy that the vcore can run only when all its threads
are runnable or blocked.  This way, if a vcpu needs to execute elsewhere
in the kernel or in qemu, it can do so without being starved of CPU
by the other vcpus.

When a vcore starts to run, it executes in the context of one of the
vcpu threads.  The other vcpu threads all go to sleep and stay asleep
until something happens requiring the vcpu thread to return to qemu,
or to wake up to run the vcore (this can happen when another vcpu
thread goes from busy in host state to blocked).

It can happen that a vcpu goes from blocked to runnable state (e.g.
because of an interrupt), and the vcore it belongs to is already
running.  In that case it can start to run immediately as long as
the none of the vcpus in the vcore have started to exit the guest.
We send the next free thread in the vcore an IPI to get it to start
to execute the guest.  It synchronizes with the other threads via
the vcore->entry_exit_count field to make sure that it doesn't go
into the guest if the other vcpus are exiting by the time that it
is ready to actually enter the guest.

Note that there is no fixed relationship between the hardware thread
number and the vcpu number.  Hardware threads are assigned to vcpus
as they become runnable, so we will always use the lower-numbered
hardware threads in preference to higher-numbered threads if not all
the vcpus in the vcore are runnable, regardless of which vcpus are
runnable.

Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Alexander Graf <agraf@suse.de>
---
 arch/powerpc/kernel/asm-offsets.c    |  6 ++++++
 arch/powerpc/kernel/exceptions-64s.S | 31 ++++++++++++++++++++++---------
 arch/powerpc/kernel/idle_power7.S    |  2 --
 3 files changed, 28 insertions(+), 11 deletions(-)

(limited to 'arch/powerpc/kernel')

diff --git a/arch/powerpc/kernel/asm-offsets.c b/arch/powerpc/kernel/asm-offsets.c
index c70d106bf1a4..d0f2387fd792 100644
--- a/arch/powerpc/kernel/asm-offsets.c
+++ b/arch/powerpc/kernel/asm-offsets.c
@@ -471,6 +471,10 @@ int main(void)
 	DEFINE(VCPU_FAULT_DAR, offsetof(struct kvm_vcpu, arch.fault_dar));
 	DEFINE(VCPU_LAST_INST, offsetof(struct kvm_vcpu, arch.last_inst));
 	DEFINE(VCPU_TRAP, offsetof(struct kvm_vcpu, arch.trap));
+	DEFINE(VCPU_PTID, offsetof(struct kvm_vcpu, arch.ptid));
+	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));
 	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));
@@ -530,6 +534,8 @@ int main(void)
 
 #ifdef CONFIG_KVM_BOOK3S_64_HV
 	HSTATE_FIELD(HSTATE_KVM_VCPU, kvm_vcpu);
+	HSTATE_FIELD(HSTATE_KVM_VCORE, kvm_vcore);
+	HSTATE_FIELD(HSTATE_XICS_PHYS, xics_phys);
 	HSTATE_FIELD(HSTATE_MMCR, host_mmcr);
 	HSTATE_FIELD(HSTATE_PMC, host_pmc);
 	HSTATE_FIELD(HSTATE_PURR, host_purr);
diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S
index 163c041cec24..5bc06fdfa6c0 100644
--- a/arch/powerpc/kernel/exceptions-64s.S
+++ b/arch/powerpc/kernel/exceptions-64s.S
@@ -49,19 +49,32 @@ BEGIN_FTR_SECTION
 	 * state loss at this time.
 	 */
 	mfspr	r13,SPRN_SRR1
-	rlwinm	r13,r13,47-31,30,31
-	cmpwi	cr0,r13,1
-	bne	1f
-	b	.power7_wakeup_noloss
-1:	cmpwi	cr0,r13,2
-	bne	1f
-	b	.power7_wakeup_loss
+	rlwinm.	r13,r13,47-31,30,31
+	beq	9f
+
+	/* waking up from powersave (nap) state */
+	cmpwi	cr1,r13,2
 	/* Total loss of HV state is fatal, we could try to use the
 	 * PIR to locate a PACA, then use an emergency stack etc...
 	 * but for now, let's just stay stuck here
 	 */
-1:	cmpwi	cr0,r13,3
-	beq	.
+	bgt	cr1,.
+	GET_PACA(r13)
+
+#ifdef CONFIG_KVM_BOOK3S_64_HV
+	lbz	r0,PACAPROCSTART(r13)
+	cmpwi	r0,0x80
+	bne	1f
+	li	r0,0
+	stb	r0,PACAPROCSTART(r13)
+	b	kvm_start_guest
+1:
+#endif
+
+	beq	cr1,2f
+	b	.power7_wakeup_noloss
+2:	b	.power7_wakeup_loss
+9:
 END_FTR_SECTION_IFSET(CPU_FTR_HVMODE_206)
 #endif /* CONFIG_PPC_P7_NAP */
 	EXCEPTION_PROLOG_PSERIES(PACA_EXGEN, system_reset_common, EXC_STD,
diff --git a/arch/powerpc/kernel/idle_power7.S b/arch/powerpc/kernel/idle_power7.S
index f8f0bc7f1d4f..3a70845a51c7 100644
--- a/arch/powerpc/kernel/idle_power7.S
+++ b/arch/powerpc/kernel/idle_power7.S
@@ -73,7 +73,6 @@ _GLOBAL(power7_idle)
 	b	.
 
 _GLOBAL(power7_wakeup_loss)
-	GET_PACA(r13)
 	ld	r1,PACAR1(r13)
 	REST_NVGPRS(r1)
 	REST_GPR(2, r1)
@@ -87,7 +86,6 @@ _GLOBAL(power7_wakeup_loss)
 	rfid
 
 _GLOBAL(power7_wakeup_noloss)
-	GET_PACA(r13)
 	ld	r1,PACAR1(r13)
 	ld	r4,_MSR(r1)
 	ld	r5,_NIP(r1)
-- 
cgit v1.2.3


From aa04b4cc5be64b4fb9ef4e0fdf2418e2f4737fb2 Mon Sep 17 00:00:00 2001
From: Paul Mackerras <paulus@samba.org>
Date: Wed, 29 Jun 2011 00:25:44 +0000
Subject: KVM: PPC: Allocate RMAs (Real Mode Areas) at boot for use by guests

This adds infrastructure which will be needed to allow book3s_hv KVM to
run on older POWER processors, including PPC970, which don't support
the Virtual Real Mode Area (VRMA) facility, but only the Real Mode
Offset (RMO) facility.  These processors require a physically
contiguous, aligned area of memory for each guest.  When the guest does
an access in real mode (MMU off), the address is compared against a
limit value, and if it is lower, the address is ORed with an offset
value (from the Real Mode Offset Register (RMOR)) and the result becomes
the real address for the access.  The size of the RMA has to be one of
a set of supported values, which usually includes 64MB, 128MB, 256MB
and some larger powers of 2.

Since we are unlikely to be able to allocate 64MB or more of physically
contiguous memory after the kernel has been running for a while, we
allocate a pool of RMAs at boot time using the bootmem allocator.  The
size and number of the RMAs can be set using the kvm_rma_size=xx and
kvm_rma_count=xx kernel command line options.

KVM exports a new capability, KVM_CAP_PPC_RMA, to signal the availability
of the pool of preallocated RMAs.  The capability value is 1 if the
processor can use an RMA but doesn't require one (because it supports
the VRMA facility), or 2 if the processor requires an RMA for each guest.

This adds a new ioctl, KVM_ALLOCATE_RMA, which allocates an RMA from the
pool and returns a file descriptor which can be used to map the RMA.  It
also returns the size of the RMA in the argument structure.

Having an RMA means we will get multiple KMV_SET_USER_MEMORY_REGION
ioctl calls from userspace.  To cope with this, we now preallocate the
kvm->arch.ram_pginfo array when the VM is created with a size sufficient
for up to 64GB of guest memory.  Subsequently we will get rid of this
array and use memory associated with each memslot instead.

This moves most of the code that translates the user addresses into
host pfns (page frame numbers) out of kvmppc_prepare_vrma up one level
to kvmppc_core_prepare_memory_region.  Also, instead of having to look
up the VMA for each page in order to check the page size, we now check
that the pages we get are compound pages of 16MB.  However, if we are
adding memory that is mapped to an RMA, we don't bother with calling
get_user_pages_fast and instead just offset from the base pfn for the
RMA.

Typically the RMA gets added after vcpus are created, which makes it
inconvenient to have the LPCR (logical partition control register) value
in the vcpu->arch struct, since the LPCR controls whether the processor
uses RMA or VRMA for the guest.  This moves the LPCR value into the
kvm->arch struct and arranges for the MER (mediated external request)
bit, which is the only bit that varies between vcpus, to be set in
assembly code when going into the guest if there is a pending external
interrupt request.

Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Alexander Graf <agraf@suse.de>
---
 arch/powerpc/kernel/asm-offsets.c | 4 +++-
 arch/powerpc/kernel/setup_64.c    | 3 +++
 2 files changed, 6 insertions(+), 1 deletion(-)

(limited to 'arch/powerpc/kernel')

diff --git a/arch/powerpc/kernel/asm-offsets.c b/arch/powerpc/kernel/asm-offsets.c
index d0f2387fd792..f4aba938166b 100644
--- a/arch/powerpc/kernel/asm-offsets.c
+++ b/arch/powerpc/kernel/asm-offsets.c
@@ -437,6 +437,8 @@ int main(void)
 	DEFINE(KVM_TLBIE_LOCK, offsetof(struct kvm, arch.tlbie_lock));
 	DEFINE(KVM_ONLINE_CPUS, offsetof(struct kvm, online_vcpus.counter));
 	DEFINE(KVM_LAST_VCPU, offsetof(struct kvm, arch.last_vcpu));
+	DEFINE(KVM_LPCR, offsetof(struct kvm, arch.lpcr));
+	DEFINE(KVM_RMOR, offsetof(struct kvm, arch.rmor));
 	DEFINE(VCPU_DSISR, offsetof(struct kvm_vcpu, arch.shregs.dsisr));
 	DEFINE(VCPU_DAR, offsetof(struct kvm_vcpu, arch.shregs.dar));
 #endif
@@ -459,7 +461,7 @@ int main(void)
 	DEFINE(VCPU_HFLAGS, offsetof(struct kvm_vcpu, arch.hflags));
 	DEFINE(VCPU_DEC, offsetof(struct kvm_vcpu, arch.dec));
 	DEFINE(VCPU_DEC_EXPIRES, offsetof(struct kvm_vcpu, arch.dec_expires));
-	DEFINE(VCPU_LPCR, offsetof(struct kvm_vcpu, arch.lpcr));
+	DEFINE(VCPU_PENDING_EXC, offsetof(struct kvm_vcpu, arch.pending_exceptions));
 	DEFINE(VCPU_VPA, offsetof(struct kvm_vcpu, arch.vpa));
 	DEFINE(VCPU_MMCR, offsetof(struct kvm_vcpu, arch.mmcr));
 	DEFINE(VCPU_PMC, offsetof(struct kvm_vcpu, arch.pmc));
diff --git a/arch/powerpc/kernel/setup_64.c b/arch/powerpc/kernel/setup_64.c
index a88bf2713d41..532054f24ecb 100644
--- a/arch/powerpc/kernel/setup_64.c
+++ b/arch/powerpc/kernel/setup_64.c
@@ -63,6 +63,7 @@
 #include <asm/kexec.h>
 #include <asm/mmu_context.h>
 #include <asm/code-patching.h>
+#include <asm/kvm_ppc.h>
 
 #include "setup.h"
 
@@ -580,6 +581,8 @@ void __init setup_arch(char **cmdline_p)
 	/* Initialize the MMU context management stuff */
 	mmu_context_init();
 
+	kvm_rma_init();
+
 	ppc64_boot_msg(0x15, "Setup Done");
 }
 
-- 
cgit v1.2.3


From 969391c58a4efb8411d6881179945f425ad9cbb5 Mon Sep 17 00:00:00 2001
From: Paul Mackerras <paulus@samba.org>
Date: Wed, 29 Jun 2011 00:26:11 +0000
Subject: powerpc, KVM: Split HVMODE_206 cpu feature bit into separate HV and
 architecture bits

This replaces the single CPU_FTR_HVMODE_206 bit with two bits, one to
indicate that we have a usable hypervisor mode, and another to indicate
that the processor conforms to PowerISA version 2.06.  We also add
another bit to indicate that the processor conforms to ISA version 2.01
and set that for PPC970 and derivatives.

Some PPC970 chips (specifically those in Apple machines) have a
hypervisor mode in that MSR[HV] is always 1, but the hypervisor mode
is not useful in the sense that there is no way to run any code in
supervisor mode (HV=0 PR=0).  On these processors, the LPES0 and LPES1
bits in HID4 are always 0, and we use that as a way of detecting that
hypervisor mode is not useful.

Where we have a feature section in assembly code around code that
only applies on POWER7 in hypervisor mode, we use a construct like

END_FTR_SECTION_IFSET(CPU_FTR_HVMODE | CPU_FTR_ARCH_206)

The definition of END_FTR_SECTION_IFSET is such that the code will
be enabled (not overwritten with nops) only if all bits in the
provided mask are set.

Note that the CPU feature check in __tlbie() only needs to check the
ARCH_206 bit, not the HVMODE bit, because __tlbie() can only get called
if we are running bare-metal, i.e. in hypervisor mode.

Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Alexander Graf <agraf@suse.de>
---
 arch/powerpc/kernel/cpu_setup_power7.S |  4 ++--
 arch/powerpc/kernel/cpu_setup_ppc970.S | 26 ++++++++++++++++++++++----
 arch/powerpc/kernel/exceptions-64s.S   |  4 ++--
 arch/powerpc/kernel/paca.c             |  2 +-
 4 files changed, 27 insertions(+), 9 deletions(-)

(limited to 'arch/powerpc/kernel')

diff --git a/arch/powerpc/kernel/cpu_setup_power7.S b/arch/powerpc/kernel/cpu_setup_power7.S
index 2ef6749688e9..76797c5105d6 100644
--- a/arch/powerpc/kernel/cpu_setup_power7.S
+++ b/arch/powerpc/kernel/cpu_setup_power7.S
@@ -45,12 +45,12 @@ _GLOBAL(__restore_cpu_power7)
 	blr
 
 __init_hvmode_206:
-	/* Disable CPU_FTR_HVMODE_206 and exit if MSR:HV is not set */
+	/* Disable CPU_FTR_HVMODE and exit if MSR:HV is not set */
 	mfmsr	r3
 	rldicl.	r0,r3,4,63
 	bnelr
 	ld	r5,CPU_SPEC_FEATURES(r4)
-	LOAD_REG_IMMEDIATE(r6,CPU_FTR_HVMODE_206)
+	LOAD_REG_IMMEDIATE(r6,CPU_FTR_HVMODE)
 	xor	r5,r5,r6
 	std	r5,CPU_SPEC_FEATURES(r4)
 	blr
diff --git a/arch/powerpc/kernel/cpu_setup_ppc970.S b/arch/powerpc/kernel/cpu_setup_ppc970.S
index 27f2507279d8..12fac8df01c5 100644
--- a/arch/powerpc/kernel/cpu_setup_ppc970.S
+++ b/arch/powerpc/kernel/cpu_setup_ppc970.S
@@ -76,7 +76,7 @@ _GLOBAL(__setup_cpu_ppc970)
 	/* Do nothing if not running in HV mode */
 	mfmsr	r0
 	rldicl.	r0,r0,4,63
-	beqlr
+	beq	no_hv_mode
 
 	mfspr	r0,SPRN_HID0
 	li	r11,5			/* clear DOZE and SLEEP */
@@ -90,7 +90,7 @@ _GLOBAL(__setup_cpu_ppc970MP)
 	/* Do nothing if not running in HV mode */
 	mfmsr	r0
 	rldicl.	r0,r0,4,63
-	beqlr
+	beq	no_hv_mode
 
 	mfspr	r0,SPRN_HID0
 	li	r11,0x15		/* clear DOZE and SLEEP */
@@ -109,6 +109,14 @@ load_hids:
 	sync
 	isync
 
+	/* Try to set LPES = 01 in HID4 */
+	mfspr	r0,SPRN_HID4
+	clrldi	r0,r0,1			/* clear LPES0 */
+	ori	r0,r0,HID4_LPES1	/* set LPES1 */
+	sync
+	mtspr	SPRN_HID4,r0
+	isync
+
 	/* Save away cpu state */
 	LOAD_REG_ADDR(r5,cpu_state_storage)
 
@@ -117,11 +125,21 @@ load_hids:
 	std	r3,CS_HID0(r5)
 	mfspr	r3,SPRN_HID1
 	std	r3,CS_HID1(r5)
-	mfspr	r3,SPRN_HID4
-	std	r3,CS_HID4(r5)
+	mfspr	r4,SPRN_HID4
+	std	r4,CS_HID4(r5)
 	mfspr	r3,SPRN_HID5
 	std	r3,CS_HID5(r5)
 
+	/* See if we successfully set LPES1 to 1; if not we are in Apple mode */
+	andi.	r4,r4,HID4_LPES1
+	bnelr
+
+no_hv_mode:
+	/* Disable CPU_FTR_HVMODE and exit, since we don't have HV mode */
+	ld	r5,CPU_SPEC_FEATURES(r4)
+	LOAD_REG_IMMEDIATE(r6,CPU_FTR_HVMODE)
+	andc	r5,r5,r6
+	std	r5,CPU_SPEC_FEATURES(r4)
 	blr
 
 /* Called with no MMU context (typically MSR:IR/DR off) to
diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S
index 5bc06fdfa6c0..a5345380bef3 100644
--- a/arch/powerpc/kernel/exceptions-64s.S
+++ b/arch/powerpc/kernel/exceptions-64s.S
@@ -75,7 +75,7 @@ BEGIN_FTR_SECTION
 	b	.power7_wakeup_noloss
 2:	b	.power7_wakeup_loss
 9:
-END_FTR_SECTION_IFSET(CPU_FTR_HVMODE_206)
+END_FTR_SECTION_IFSET(CPU_FTR_HVMODE | CPU_FTR_ARCH_206)
 #endif /* CONFIG_PPC_P7_NAP */
 	EXCEPTION_PROLOG_PSERIES(PACA_EXGEN, system_reset_common, EXC_STD,
 				 NOTEST, 0x100)
@@ -173,7 +173,7 @@ hardware_interrupt_hv:
 		_MASKABLE_EXCEPTION_PSERIES(0x500, hardware_interrupt,
 					    EXC_STD, SOFTEN_TEST_PR)
 		KVM_HANDLER(PACA_EXGEN, EXC_STD, 0x500)
-	ALT_FTR_SECTION_END_IFSET(CPU_FTR_HVMODE_206)
+	ALT_FTR_SECTION_END_IFSET(CPU_FTR_HVMODE | CPU_FTR_ARCH_206)
 
 	STD_EXCEPTION_PSERIES(0x600, 0x600, alignment)
 	KVM_HANDLER_PR(PACA_EXGEN, EXC_STD, 0x600)
diff --git a/arch/powerpc/kernel/paca.c b/arch/powerpc/kernel/paca.c
index efeb88184182..0a5a899846bb 100644
--- a/arch/powerpc/kernel/paca.c
+++ b/arch/powerpc/kernel/paca.c
@@ -167,7 +167,7 @@ void setup_paca(struct paca_struct *new_paca)
 	 * if we do a GET_PACA() before the feature fixups have been
 	 * applied
 	 */
-	if (cpu_has_feature(CPU_FTR_HVMODE_206))
+	if (cpu_has_feature(CPU_FTR_HVMODE))
 		mtspr(SPRN_SPRG_HPACA, local_paca);
 #endif
 	mtspr(SPRN_SPRG_PACA, local_paca);
-- 
cgit v1.2.3


From 9e368f2915601cd5bc7f5fd638b58435b018bbd7 Mon Sep 17 00:00:00 2001
From: Paul Mackerras <paulus@samba.org>
Date: Wed, 29 Jun 2011 00:40:08 +0000
Subject: KVM: PPC: book3s_hv: Add support for PPC970-family processors

This adds support for running KVM guests in supervisor mode on those
PPC970 processors that have a usable hypervisor mode.  Unfortunately,
Apple G5 machines have supervisor mode disabled (MSR[HV] is forced to
1), but the YDL PowerStation does have a usable hypervisor mode.

There are several differences between the PPC970 and POWER7 in how
guests are managed.  These differences are accommodated using the
CPU_FTR_ARCH_201 (PPC970) and CPU_FTR_ARCH_206 (POWER7) CPU feature
bits.  Notably, on PPC970:

* The LPCR, LPID or RMOR registers don't exist, and the functions of
  those registers are provided by bits in HID4 and one bit in HID0.

* External interrupts can be directed to the hypervisor, but unlike
  POWER7 they are masked by MSR[EE] in non-hypervisor modes and use
  SRR0/1 not HSRR0/1.

* There is no virtual RMA (VRMA) mode; the guest must use an RMO
  (real mode offset) area.

* The TLB entries are not tagged with the LPID, so it is necessary to
  flush the whole TLB on partition switch.  Furthermore, when switching
  partitions we have to ensure that no other CPU is executing the tlbie
  or tlbsync instructions in either the old or the new partition,
  otherwise undefined behaviour can occur.

* The PMU has 8 counters (PMC registers) rather than 6.

* The DSCR, PURR, SPURR, AMR, AMOR, UAMOR registers don't exist.

* The SLB has 64 entries rather than 32.

* There is no mediated external interrupt facility, so if we switch to
  a guest that has a virtual external interrupt pending but the guest
  has MSR[EE] = 0, we have to arrange to have an interrupt pending for
  it so that we can get control back once it re-enables interrupts.  We
  do that by sending ourselves an IPI with smp_send_reschedule after
  hard-disabling interrupts.

Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Alexander Graf <agraf@suse.de>
---
 arch/powerpc/kernel/asm-offsets.c    | 1 +
 arch/powerpc/kernel/exceptions-64s.S | 2 +-
 2 files changed, 2 insertions(+), 1 deletion(-)

(limited to 'arch/powerpc/kernel')

diff --git a/arch/powerpc/kernel/asm-offsets.c b/arch/powerpc/kernel/asm-offsets.c
index f4aba938166b..54b935f2f5de 100644
--- a/arch/powerpc/kernel/asm-offsets.c
+++ b/arch/powerpc/kernel/asm-offsets.c
@@ -128,6 +128,7 @@ int main(void)
 	DEFINE(ICACHEL1LINESPERPAGE, offsetof(struct ppc64_caches, ilines_per_page));
 	/* paca */
 	DEFINE(PACA_SIZE, sizeof(struct paca_struct));
+	DEFINE(PACA_LOCK_TOKEN, offsetof(struct paca_struct, lock_token));
 	DEFINE(PACAPACAINDEX, offsetof(struct paca_struct, paca_index));
 	DEFINE(PACAPROCSTART, offsetof(struct paca_struct, cpu_start));
 	DEFINE(PACAKSAVE, offsetof(struct paca_struct, kstack));
diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S
index a5345380bef3..41b02c792aa3 100644
--- a/arch/powerpc/kernel/exceptions-64s.S
+++ b/arch/powerpc/kernel/exceptions-64s.S
@@ -171,7 +171,7 @@ hardware_interrupt_hv:
 		KVM_HANDLER(PACA_EXGEN, EXC_HV, 0x502)
 	FTR_SECTION_ELSE
 		_MASKABLE_EXCEPTION_PSERIES(0x500, hardware_interrupt,
-					    EXC_STD, SOFTEN_TEST_PR)
+					    EXC_STD, SOFTEN_TEST_HV_201)
 		KVM_HANDLER(PACA_EXGEN, EXC_STD, 0x500)
 	ALT_FTR_SECTION_END_IFSET(CPU_FTR_HVMODE | CPU_FTR_ARCH_206)
 
-- 
cgit v1.2.3