KVM: PPC: e500mc support

Add processor support for e500mc, using hardware virtualization support
(GS-mode).

Current issues include:
 - No support for external proxy (coreint) interrupt mode in the guest.

Includes work by Ashish Kalra <Ashish.Kalra@freescale.com>,
Varun Sethi <Varun.Sethi@freescale.com>, and
Liu Yu <yu.liu@freescale.com>.

Signed-off-by: Scott Wood <scottwood@freescale.com>
Signed-off-by: Alexander Graf <agraf@suse.de>
Signed-off-by: Avi Kivity <avi@redhat.com>

arch/powerpc/include/asm/cputable.h

@@ -168,6 +168,7 @@ extern const char *powerpc_base_platform;
 #define CPU_FTR_LWSYNC			ASM_CONST(0x0000000008000000)
 #define CPU_FTR_NOEXECUTE		ASM_CONST(0x0000000010000000)
 #define CPU_FTR_INDEXED_DCR		ASM_CONST(0x0000000020000000)
+#define CPU_FTR_EMB_HV			ASM_CONST(0x0000000040000000)
 
 /*
  * Add the 64-bit processor unique features in the top half of the word;
@@ -386,11 +387,11 @@ extern const char *powerpc_base_platform;
 	    CPU_FTR_NODSISRALIGN | CPU_FTR_NOEXECUTE)
 #define CPU_FTRS_E500MC	(CPU_FTR_USE_TB | CPU_FTR_NODSISRALIGN | \
 	    CPU_FTR_L2CSR | CPU_FTR_LWSYNC | CPU_FTR_NOEXECUTE | \
-	    CPU_FTR_DBELL | CPU_FTR_DEBUG_LVL_EXC)
+	    CPU_FTR_DBELL | CPU_FTR_DEBUG_LVL_EXC | CPU_FTR_EMB_HV)
 #define CPU_FTRS_E5500	(CPU_FTR_USE_TB | CPU_FTR_NODSISRALIGN | \
 	    CPU_FTR_L2CSR | CPU_FTR_LWSYNC | CPU_FTR_NOEXECUTE | \
 	    CPU_FTR_DBELL | CPU_FTR_POPCNTB | CPU_FTR_POPCNTD | \
-	    CPU_FTR_DEBUG_LVL_EXC)
+	    CPU_FTR_DEBUG_LVL_EXC | CPU_FTR_EMB_HV)
 #define CPU_FTRS_E6500	(CPU_FTR_USE_TB | CPU_FTR_NODSISRALIGN | \
 	    CPU_FTR_L2CSR | CPU_FTR_LWSYNC | CPU_FTR_NOEXECUTE | \
 	    CPU_FTR_DBELL | CPU_FTR_POPCNTB | CPU_FTR_POPCNTD | \
@@ -539,6 +540,7 @@ enum {
 #ifdef CONFIG_PPC_E500MC
 	    CPU_FTRS_E500MC & CPU_FTRS_E5500 & CPU_FTRS_E6500 &
 #endif
+	    ~CPU_FTR_EMB_HV &	/* can be removed at runtime */
 	    CPU_FTRS_POSSIBLE,
 };
 #endif /* __powerpc64__ */

arch/powerpc/include/asm/kvm.h

@@ -277,6 +277,7 @@ struct kvm_sync_regs {
 #define KVM_CPU_E500V2		2
 #define KVM_CPU_3S_32		3
 #define KVM_CPU_3S_64		4
+#define KVM_CPU_E500MC		5
 
 /* for KVM_CAP_SPAPR_TCE */
 struct kvm_create_spapr_tce {

arch/powerpc/kernel/cpu_setup_fsl_booke.S

@@ -73,6 +73,7 @@ _GLOBAL(__setup_cpu_e500v2)
 	mtlr	r4
 	blr
 _GLOBAL(__setup_cpu_e500mc)
+	mr	r5, r4
 	mflr	r4
 	bl	__e500_icache_setup
 	bl	__e500_dcache_setup

arch/powerpc/kernel/head_fsl_booke.S

@@ -380,10 +380,16 @@ interrupt_base:
 	mtspr	SPRN_SPRG_WSCRATCH0, r10 /* Save some working registers */
 	mfspr	r10, SPRN_SPRG_THREAD
 	stw	r11, THREAD_NORMSAVE(0)(r10)
+#ifdef CONFIG_KVM_BOOKE_HV
+BEGIN_FTR_SECTION
+	mfspr	r11, SPRN_SRR1
+END_FTR_SECTION_IFSET(CPU_FTR_EMB_HV)
+#endif
 	stw	r12, THREAD_NORMSAVE(1)(r10)
 	stw	r13, THREAD_NORMSAVE(2)(r10)
 	mfcr	r13
 	stw	r13, THREAD_NORMSAVE(3)(r10)
+	DO_KVM	BOOKE_INTERRUPT_DTLB_MISS SPRN_SRR1
 	mfspr	r10, SPRN_DEAR		/* Get faulting address */
 
 	/* If we are faulting a kernel address, we have to use the
@@ -468,10 +474,16 @@ interrupt_base:
 	mtspr	SPRN_SPRG_WSCRATCH0, r10 /* Save some working registers */
 	mfspr	r10, SPRN_SPRG_THREAD
 	stw	r11, THREAD_NORMSAVE(0)(r10)
+#ifdef CONFIG_KVM_BOOKE_HV
+BEGIN_FTR_SECTION
+	mfspr	r11, SPRN_SRR1
+END_FTR_SECTION_IFSET(CPU_FTR_EMB_HV)
+#endif
 	stw	r12, THREAD_NORMSAVE(1)(r10)
 	stw	r13, THREAD_NORMSAVE(2)(r10)
 	mfcr	r13
 	stw	r13, THREAD_NORMSAVE(3)(r10)
+	DO_KVM	BOOKE_INTERRUPT_ITLB_MISS SPRN_SRR1
 	mfspr	r10, SPRN_SRR0		/* Get faulting address */
 
 	/* If we are faulting a kernel address, we have to use the
@@ -580,6 +592,17 @@ interrupt_base:
 	DEBUG_DEBUG_EXCEPTION
 	DEBUG_CRIT_EXCEPTION
 
+	GUEST_DOORBELL_EXCEPTION
+
+	CRITICAL_EXCEPTION(0, GUEST_DBELL_CRIT, CriticalGuestDoorbell, \
+			   unknown_exception)
+
+	/* Hypercall */
+	EXCEPTION(0, HV_SYSCALL, Hypercall, unknown_exception, EXC_XFER_EE)
+
+	/* Embedded Hypervisor Privilege */
+	EXCEPTION(0, HV_PRIV, Ehvpriv, unknown_exception, EXC_XFER_EE)
+
 /*
  * Local functions
  */
@@ -883,8 +906,31 @@ _GLOBAL(__setup_e500mc_ivors)
 	mtspr	SPRN_IVOR36,r3
 	li	r3,CriticalDoorbell@l
 	mtspr	SPRN_IVOR37,r3
+
+	/*
+	 * We only want to touch IVOR38-41 if we're running on hardware
+	 * that supports category E.HV.  The architectural way to determine
+	 * this is MMUCFG[LPIDSIZE].
+	 */
+	mfspr	r3, SPRN_MMUCFG
+	andis.	r3, r3, MMUCFG_LPIDSIZE@h
+	beq	no_hv
+	li	r3,GuestDoorbell@l
+	mtspr	SPRN_IVOR38,r3
+	li	r3,CriticalGuestDoorbell@l
+	mtspr	SPRN_IVOR39,r3
+	li	r3,Hypercall@l
+	mtspr	SPRN_IVOR40,r3
+	li	r3,Ehvpriv@l
+	mtspr	SPRN_IVOR41,r3
+skip_hv_ivors:
 	sync
 	blr
+no_hv:
+	lwz	r3, CPU_SPEC_FEATURES(r5)
+	rlwinm	r3, r3, 0, ~CPU_FTR_EMB_HV
+	stw	r3, CPU_SPEC_FEATURES(r5)
+	b	skip_hv_ivors
 
 /*
  * extern void giveup_altivec(struct task_struct *prev)

arch/powerpc/kvm/Kconfig

@@ -109,7 +109,7 @@ config KVM_440
 
 config KVM_EXIT_TIMING
 	bool "Detailed exit timing"
-	depends on KVM_440 || KVM_E500
+	depends on KVM_440 || KVM_E500 || KVM_E500MC
 	---help---
 	  Calculate elapsed time for every exit/enter cycle. A per-vcpu
 	  report is available in debugfs kvm/vm#_vcpu#_timing.
@@ -132,6 +132,21 @@ config KVM_E500
 
 	  If unsure, say N.
 
+config KVM_E500MC
+	bool "KVM support for PowerPC E500MC/E5500 processors"
+	depends on EXPERIMENTAL && PPC_E500MC
+	select KVM
+	select KVM_MMIO
+	select KVM_BOOKE_HV
+	---help---
+	  Support running unmodified E500MC/E5500 (32-bit) guest kernels in
+	  virtual machines on E500MC/E5500 host processors.
+
+	  This module provides access to the hardware capabilities through
+	  a character device node named /dev/kvm.
+
+	  If unsure, say N.
+
 source drivers/vhost/Kconfig
 
 endif # VIRTUALIZATION

arch/powerpc/kvm/Makefile

@@ -38,6 +38,16 @@ kvm-e500-objs := \
 	e500_emulate.o
 kvm-objs-$(CONFIG_KVM_E500) := $(kvm-e500-objs)
 
+kvm-e500mc-objs := \
+	$(common-objs-y) \
+	booke.o \
+	booke_emulate.o \
+	bookehv_interrupts.o \
+	e500mc.o \
+	e500_tlb.o \
+	e500_emulate.o
+kvm-objs-$(CONFIG_KVM_E500MC) := $(kvm-e500mc-objs)
+
 kvm-book3s_64-objs-$(CONFIG_KVM_BOOK3S_64_PR) := \
 	../../../virt/kvm/coalesced_mmio.o \
 	fpu.o \
@@ -89,6 +99,7 @@ kvm-objs := $(kvm-objs-m) $(kvm-objs-y)
 
 obj-$(CONFIG_KVM_440) += kvm.o
 obj-$(CONFIG_KVM_E500) += kvm.o
+obj-$(CONFIG_KVM_E500MC) += kvm.o
 obj-$(CONFIG_KVM_BOOK3S_64) += kvm.o
 obj-$(CONFIG_KVM_BOOK3S_32) += kvm.o
 

arch/powerpc/kvm/e500.h

@@ -2,7 +2,9 @@
  * Copyright (C) 2008-2011 Freescale Semiconductor, Inc. All rights reserved.
  *
  * Author: Yu Liu <yu.liu@freescale.com>
+ *         Scott Wood <scottwood@freescale.com>
  *         Ashish Kalra <ashish.kalra@freescale.com>
+ *         Varun Sethi <varun.sethi@freescale.com>
  *
  * Description:
  * This file is based on arch/powerpc/kvm/44x_tlb.h and
@@ -100,6 +102,7 @@ static inline struct kvmppc_vcpu_e500 *to_e500(struct kvm_vcpu *vcpu)
 	return container_of(vcpu, struct kvmppc_vcpu_e500, vcpu);
 }
 
+
 /* This geometry is the legacy default -- can be overridden by userspace */
 #define KVM_E500_TLB0_WAY_SIZE		128
 #define KVM_E500_TLB0_WAY_NUM		2
@@ -250,10 +253,12 @@ static inline int tlbe_is_host_safe(const struct kvm_vcpu *vcpu,
 	if (!get_tlb_v(tlbe))
 		return 0;
 
+#ifndef CONFIG_KVM_BOOKE_HV
 	/* Does it match current guest AS? */
 	/* XXX what about IS != DS? */
 	if (get_tlb_ts(tlbe) != !!(vcpu->arch.shared->msr & MSR_IS))
 		return 0;
+#endif
 
 	gpa = get_tlb_raddr(tlbe);
 	if (!gfn_to_memslot(vcpu->kvm, gpa >> PAGE_SHIFT))
@@ -274,7 +279,11 @@ void kvmppc_e500_tlbil_one(struct kvmppc_vcpu_e500 *vcpu_e500,
 			   struct kvm_book3e_206_tlb_entry *gtlbe);
 void kvmppc_e500_tlbil_all(struct kvmppc_vcpu_e500 *vcpu_e500);
 
-#ifdef CONFIG_KVM_E500
+#ifdef CONFIG_KVM_BOOKE_HV
+#define kvmppc_e500_get_tlb_stid(vcpu, gtlbe)       get_tlb_tid(gtlbe)
+#define get_tlbmiss_tid(vcpu)           get_cur_pid(vcpu)
+#define get_tlb_sts(gtlbe)              (gtlbe->mas1 & MAS1_TS)
+#else
 unsigned int kvmppc_e500_get_tlb_stid(struct kvm_vcpu *vcpu,
 				      struct kvm_book3e_206_tlb_entry *gtlbe);
 
@@ -288,6 +297,6 @@ static inline unsigned int get_tlbmiss_tid(struct kvm_vcpu *vcpu)
 
 /* Force TS=1 for all guest mappings. */
 #define get_tlb_sts(gtlbe)              (MAS1_TS)
-#endif /* CONFIG_KVM_E500 */
+#endif /* !BOOKE_HV */
 
 #endif /* KVM_E500_H */

arch/powerpc/kvm/e500_emulate.c

@@ -85,6 +85,7 @@ int kvmppc_core_emulate_mtspr(struct kvm_vcpu *vcpu, int sprn, int rs)
 	ulong spr_val = kvmppc_get_gpr(vcpu, rs);
 
 	switch (sprn) {
+#ifndef CONFIG_KVM_BOOKE_HV
 	case SPRN_PID:
 		kvmppc_set_pid(vcpu, spr_val);
 		break;
@@ -114,6 +115,7 @@ int kvmppc_core_emulate_mtspr(struct kvm_vcpu *vcpu, int sprn, int rs)
 		vcpu->arch.shared->mas7_3 &= (u64)0xffffffff;
 		vcpu->arch.shared->mas7_3 |= (u64)spr_val << 32;
 		break;
+#endif
 	case SPRN_L1CSR0:
 		vcpu_e500->l1csr0 = spr_val;
 		vcpu_e500->l1csr0 &= ~(L1CSR0_DCFI | L1CSR0_CLFC);
@@ -143,7 +145,14 @@ int kvmppc_core_emulate_mtspr(struct kvm_vcpu *vcpu, int sprn, int rs)
 	case SPRN_IVOR35:
 		vcpu->arch.ivor[BOOKE_IRQPRIO_PERFORMANCE_MONITOR] = spr_val;
 		break;
-
+#ifdef CONFIG_KVM_BOOKE_HV
+	case SPRN_IVOR36:
+		vcpu->arch.ivor[BOOKE_IRQPRIO_DBELL] = spr_val;
+		break;
+	case SPRN_IVOR37:
+		vcpu->arch.ivor[BOOKE_IRQPRIO_DBELL_CRIT] = spr_val;
+		break;
+#endif
 	default:
 		emulated = kvmppc_booke_emulate_mtspr(vcpu, sprn, rs);
 	}
@@ -155,9 +164,11 @@ int kvmppc_core_emulate_mfspr(struct kvm_vcpu *vcpu, int sprn, int rt)
 {
 	struct kvmppc_vcpu_e500 *vcpu_e500 = to_e500(vcpu);
 	int emulated = EMULATE_DONE;
-	unsigned long val;
 
 	switch (sprn) {
+#ifndef CONFIG_KVM_BOOKE_HV
+		unsigned long val;
+
 	case SPRN_PID:
 		kvmppc_set_gpr(vcpu, rt, vcpu_e500->pid[0]); break;
 	case SPRN_PID1:
@@ -182,6 +193,7 @@ int kvmppc_core_emulate_mfspr(struct kvm_vcpu *vcpu, int sprn, int rt)
 		val = vcpu->arch.shared->mas7_3 >> 32;
 		kvmppc_set_gpr(vcpu, rt, val);
 		break;
+#endif
 	case SPRN_TLB0CFG:
 		kvmppc_set_gpr(vcpu, rt, vcpu->arch.tlbcfg[0]); break;
 	case SPRN_TLB1CFG:
@@ -216,6 +228,14 @@ int kvmppc_core_emulate_mfspr(struct kvm_vcpu *vcpu, int sprn, int rt)
 	case SPRN_IVOR35:
 		kvmppc_set_gpr(vcpu, rt, vcpu->arch.ivor[BOOKE_IRQPRIO_PERFORMANCE_MONITOR]);
 		break;
+#ifdef CONFIG_KVM_BOOKE_HV
+	case SPRN_IVOR36:
+		kvmppc_set_gpr(vcpu, rt, vcpu->arch.ivor[BOOKE_IRQPRIO_DBELL]);
+		break;
+	case SPRN_IVOR37:
+		kvmppc_set_gpr(vcpu, rt, vcpu->arch.ivor[BOOKE_IRQPRIO_DBELL_CRIT]);
+		break;
+#endif
 	default:
 		emulated = kvmppc_booke_emulate_mfspr(vcpu, sprn, rt);
 	}

arch/powerpc/kvm/e500_tlb.c

@@ -2,7 +2,9 @@
  * Copyright (C) 2008-2011 Freescale Semiconductor, Inc. All rights reserved.
  *
  * Author: Yu Liu, yu.liu@freescale.com
+ *         Scott Wood, scottwood@freescale.com
  *         Ashish Kalra, ashish.kalra@freescale.com
+ *         Varun Sethi, varun.sethi@freescale.com
  *
  * Description:
  * This file is based on arch/powerpc/kvm/44x_tlb.c,
@@ -64,15 +66,17 @@ static inline u32 e500_shadow_mas3_attrib(u32 mas3, int usermode)
 	/* Mask off reserved bits. */
 	mas3 &= MAS3_ATTRIB_MASK;
 
+#ifndef CONFIG_KVM_BOOKE_HV
 	if (!usermode) {
 		/* Guest is in supervisor mode,
 		 * so we need to translate guest
 		 * supervisor permissions into user permissions. */
 		mas3 &= ~E500_TLB_USER_PERM_MASK;
 		mas3 |= (mas3 & E500_TLB_SUPER_PERM_MASK) << 1;
 	}
-
-	return mas3 | E500_TLB_SUPER_PERM_MASK;
+	mas3 |= E500_TLB_SUPER_PERM_MASK;
+#endif
+	return mas3;
 }
 
 static inline u32 e500_shadow_mas2_attrib(u32 mas2, int usermode)
@@ -98,7 +102,16 @@ static inline void __write_host_tlbe(struct kvm_book3e_206_tlb_entry *stlbe,
 	mtspr(SPRN_MAS2, (unsigned long)stlbe->mas2);
 	mtspr(SPRN_MAS3, (u32)stlbe->mas7_3);
 	mtspr(SPRN_MAS7, (u32)(stlbe->mas7_3 >> 32));
+#ifdef CONFIG_KVM_BOOKE_HV
+	mtspr(SPRN_MAS8, stlbe->mas8);
+#endif
 	asm volatile("isync; tlbwe" : : : "memory");
+
+#ifdef CONFIG_KVM_BOOKE_HV
+	/* Must clear mas8 for other host tlbwe's */
+	mtspr(SPRN_MAS8, 0);
+	isync();
+#endif
 	local_irq_restore(flags);
 
 	trace_kvm_booke206_stlb_write(mas0, stlbe->mas8, stlbe->mas1,
@@ -384,6 +397,10 @@ static inline void kvmppc_e500_setup_stlbe(
 		      e500_shadow_mas2_attrib(gtlbe->mas2, pr);
 	stlbe->mas7_3 = ((u64)pfn << PAGE_SHIFT) |
 			e500_shadow_mas3_attrib(gtlbe->mas7_3, pr);
+
+#ifdef CONFIG_KVM_BOOKE_HV
+	stlbe->mas8 = MAS8_TGS | vcpu->kvm->arch.lpid;
+#endif
 }
 
 static inline void kvmppc_e500_shadow_map(struct kvmppc_vcpu_e500 *vcpu_e500,