diff options
| author | Gleb Natapov <gleb@redhat.com> | 2013-11-04 10:20:57 +0200 |
|---|---|---|
| committer | Gleb Natapov <gleb@redhat.com> | 2013-11-04 10:20:57 +0200 |
| commit | 95f328d3ad1a8e4e3175a18546fb35c495e31130 (patch) | |
| tree | 2f6496ef8354e9a0a315f23faef744f93fee8265 | |
| parent | daf727225b8abfdfe424716abac3d15a3ac5626a (diff) | |
| parent | a78b55d1c0218b6d91d504941d20e36435c276f5 (diff) | |
Merge branch 'kvm-ppc-queue' of git://github.com/agraf/linux-2.6 into queue
Conflicts:
arch/powerpc/include/asm/processor.h
73 files changed, 3408 insertions, 1737 deletions
diff --git a/Documentation/virtual/kvm/api.txt b/Documentation/virtual/kvm/api.txt index 488964414f0..a30035dd4c2 100644 --- a/Documentation/virtual/kvm/api.txt +++ b/Documentation/virtual/kvm/api.txt @@ -1810,6 +1810,50 @@ 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 + PPC | KVM_REG_PPC_TFHAR | 64 + PPC | KVM_REG_PPC_TFIAR | 64 + PPC | KVM_REG_PPC_TEXASR | 64 + PPC | KVM_REG_PPC_FSCR | 64 + PPC | KVM_REG_PPC_PSPB | 32 + PPC | KVM_REG_PPC_EBBHR | 64 + PPC | KVM_REG_PPC_EBBRR | 64 + PPC | KVM_REG_PPC_BESCR | 64 + PPC | KVM_REG_PPC_TAR | 64 + PPC | KVM_REG_PPC_DPDES | 64 + PPC | KVM_REG_PPC_DAWR | 64 + PPC | KVM_REG_PPC_DAWRX | 64 + PPC | KVM_REG_PPC_CIABR | 64 + PPC | KVM_REG_PPC_IC | 64 + PPC | KVM_REG_PPC_VTB | 64 + PPC | KVM_REG_PPC_CSIGR | 64 + PPC | KVM_REG_PPC_TACR | 64 + 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_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 + PPC | KVM_REG_PPC_TM_VSR0 | 128 + ... + PPC | KVM_REG_PPC_TM_VSR63 | 128 + PPC | KVM_REG_PPC_TM_CR | 64 + PPC | KVM_REG_PPC_TM_LR | 64 + PPC | KVM_REG_PPC_TM_CTR | 64 + PPC | KVM_REG_PPC_TM_FPSCR | 64 + PPC | KVM_REG_PPC_TM_AMR | 64 + PPC | KVM_REG_PPC_TM_PPR | 64 + PPC | KVM_REG_PPC_TM_VRSAVE | 64 + PPC | KVM_REG_PPC_TM_VSCR | 32 + PPC | KVM_REG_PPC_TM_DSCR | 64 + PPC | KVM_REG_PPC_TM_TAR | 64 ARM registers are mapped using the lower 32 bits. The upper 16 of that is the register group type, or coprocessor number: 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/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/exception-64s.h b/arch/powerpc/include/asm/exception-64s.h index cca12f08484..894662a5d4d 100644 --- a/arch/powerpc/include/asm/exception-64s.h +++ b/arch/powerpc/include/asm/exception-64s.h @@ -198,12 +198,27 @@ 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) \ 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 +232,10 @@ 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; \ @@ -236,7 +255,7 @@ 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_asm.h b/arch/powerpc/include/asm/kvm_asm.h index 851bac7afa4..1bd92fd43cf 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? */ @@ -136,6 +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/include/asm/kvm_book3s.h b/arch/powerpc/include/asm/kvm_book3s.h index fa19e2f1a87..4a594b76674 100644 --- a/arch/powerpc/include/asm/kvm_book3s.h +++ b/arch/powerpc/include/asm/kvm_book3s.h @@ -58,16 +58,18 @@ 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; ulong slot; struct kvmppc_pte pte; + int pagesize; }; 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; @@ -99,6 +101,9 @@ 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; }; @@ -107,8 +112,9 @@ 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 @@ -118,11 +124,12 @@ 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); -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); @@ -134,6 +141,7 @@ 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); @@ -151,7 +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, @@ -172,6 +181,8 @@ 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); @@ -184,11 +195,9 @@ 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); - /* Also add subarch specific defines */ #ifdef CONFIG_KVM_BOOK3S_32_HANDLER @@ -198,203 +207,6 @@ 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; -} - -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]; -} - -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; -} - -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; -} - -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); -} - -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; -} - -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); -} - -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; -} - -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); -} - -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; -} - -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); -} - -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; -} - -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); - - r = svcpu->last_inst; - svcpu_put(svcpu); - return r; -} - -/* - * 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; - 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); - - r = svcpu->last_inst; - svcpu_put(svcpu); - return r; -} - -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; -} - -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 */ - -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 void kvmppc_set_gpr(struct kvm_vcpu *vcpu, int num, ulong val) { vcpu->arch.gpr[num] = val; @@ -489,12 +301,6 @@ 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; -} -#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_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_book3s_64.h b/arch/powerpc/include/asm/kvm_book3s_64.h index 86d638a3b35..bf0fa8b0a88 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(); @@ -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 9039d3c97ee..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; @@ -101,6 +101,7 @@ struct kvmppc_host_state { #endif #ifdef CONFIG_PPC_BOOK3S_64 u64 cfar; + u64 ppr; #endif }; @@ -108,14 +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_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/asm/kvm_host.h b/arch/powerpc/include/asm/kvm_host.h index 0866230b7c2..237d1d25b44 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 @@ -84,6 +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; }; @@ -219,15 +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; @@ -251,7 +256,10 @@ 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 #ifdef CONFIG_PPC_BOOK3S_64 struct list_head spapr_tce_tables; struct list_head rtas_tokens; @@ -262,6 +270,7 @@ struct kvm_arch { #ifdef CONFIG_KVM_XICS struct kvmppc_xics *xics; #endif + struct kvmppc_ops *kvm_ops; }; /* @@ -289,6 +298,10 @@ struct kvmppc_vcore { u64 stolen_tb; u64 preempt_tb; 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) @@ -323,6 +336,7 @@ struct kvmppc_pte { bool may_read : 1; bool may_write : 1; bool may_execute : 1; + u8 page_size; /* MMU_PAGE_xxx */ }; struct kvmppc_mmu { @@ -335,7 +349,8 @@ 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); @@ -355,6 +370,7 @@ 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 @@ -372,17 +388,6 @@ 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 @@ -397,6 +402,10 @@ 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]; @@ -458,6 +467,8 @@ struct kvm_vcpu_arch { u32 ctrl; ulong dabr; ulong cfar; + ulong ppr; + ulong shadow_srr1; #endif u32 vrsave; /* also USPRG0 */ u32 mmucr; @@ -493,6 +504,8 @@ struct kvm_vcpu_arch { u64 mmcr[3]; u32 pmc[8]; + u64 siar; + u64 sdar; #ifdef CONFIG_KVM_EXIT_TIMING struct mutex exit_timing_lock; @@ -526,7 +539,10 @@ struct kvm_vcpu_arch { u32 eptcfg; u32 epr; u32 crit_save; - struct kvmppc_booke_debug_reg dbg_reg; + /* 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; @@ -577,7 +593,7 @@ 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..c8317fbf92c 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); @@ -135,17 +128,17 @@ 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); 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, @@ -177,6 +170,72 @@ 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 { + struct module *owner; + 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 (*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_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. @@ -210,17 +269,6 @@ 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 +293,10 @@ 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); @@ -260,7 +308,7 @@ 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) { @@ -269,10 +317,10 @@ 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; } @@ -281,7 +329,10 @@ 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) +{ + vcpu->kvm->arch.kvm_ops->fast_vcpu_kick(vcpu); +} #else static inline void __init kvm_cma_reserve(void) 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/include/asm/processor.h b/arch/powerpc/include/asm/processor.h index ce4de5aed7b..75a9e5a34ef 100644 --- a/arch/powerpc/include/asm/processor.h +++ b/arch/powerpc/include/asm/processor.h @@ -147,21 +147,7 @@ typedef struct { #define TS_FPR(i) fpr[i][TS_FPROFFSET] #define TS_TRANS_FPR(i) transact_fpr[i][TS_FPROFFSET] -struct thread_struct { - unsigned long ksp; /* Kernel stack pointer */ -#ifdef CONFIG_PPC64 - unsigned long ksp_vsid; -#endif - struct pt_regs *regs; /* Pointer to saved register state */ - mm_segment_t fs; /* for get_fs() validation */ -#ifdef CONFIG_BOOKE - /* BookE base exception scratch space; align on cacheline */ - unsigned long normsave[8] ____cacheline_aligned; -#endif -#ifdef CONFIG_PPC32 - void *pgdir; /* root of page-table tree */ - unsigned long ksp_limit; /* if ksp <= ksp_limit stack overflow */ -#endif +struct debug_reg { #ifdef CONFIG_PPC_ADV_DEBUG_REGS /* * The following help to manage the use of Debug Control Registers @@ -198,6 +184,27 @@ struct thread_struct { unsigned long dvc2; #endif #endif +}; + +struct thread_struct { + unsigned long ksp; /* Kernel stack pointer */ + +#ifdef CONFIG_PPC64 + unsigned long ksp_vsid; +#endif + struct pt_regs *regs; /* Pointer to saved register state */ + mm_segment_t fs; /* for get_fs() validation */ +#ifdef CONFIG_BOOKE + /* BookE base exception scratch space; align on cacheline */ + unsigned long normsave[8] ____cacheline_aligned; +#endif +#ifdef CONFIG_PPC32 + void *pgdir; /* root of page-table tree */ + unsigned long ksp_limit; /* if ksp <= ksp_limit stack overflow */ +#endif + /* Debug Registers */ + struct debug_reg debug; + /* FP and VSX 0-31 register set */ double fpr[32][TS_FPRWIDTH] __attribute__((aligned(16))); struct { diff --git a/arch/powerpc/include/asm/pte-book3e.h b/arch/powerpc/include/asm/pte-book3e.h index 0156702ba24..576ad88104c 100644 --- a/arch/powerpc/include/asm/pte-book3e.h +++ b/arch/powerpc/include/asm/pte-book3e.h @@ -40,7 +40,7 @@ #define _PAGE_U1 0x010000 #define _PAGE_U0 0x020000 #define _PAGE_ACCESSED 0x040000 -#define _PAGE_LENDIAN 0x080000 +#define _PAGE_ENDIAN 0x080000 #define _PAGE_GUARDED 0x100000 #define _PAGE_COHERENT 0x200000 /* M: enforce memory coherence */ #define _PAGE_NO_CACHE 0x400000 /* I: cache inhibit */ diff --git a/arch/powerpc/include/asm/reg.h b/arch/powerpc/include/asm/reg.h index 10d1ef016bf..e294673e9d4 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 */ @@ -283,6 +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)) @@ -299,6 +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 */ @@ -311,6 +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 */ @@ -420,6 +427,7 @@ #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 */ @@ -1102,6 +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/asm/reg_booke.h b/arch/powerpc/include/asm/reg_booke.h index ed8f836da09..2e31aacd8ac 100644 --- a/arch/powerpc/include/asm/reg_booke.h +++ b/arch/powerpc/include/asm/reg_booke.h @@ -381,7 +381,7 @@ #define DBCR0_IA34T 0x00004000 /* Instr Addr 3-4 range Toggle */ #define DBCR0_FT 0x00000001 /* Freeze Timers on debug event */ -#define dbcr_iac_range(task) ((task)->thread.dbcr0) +#define dbcr_iac_range(task) ((task)->thread.debug.dbcr0) #define DBCR_IAC12I DBCR0_IA12 /* Range Inclusive */ #define DBCR_IAC12X (DBCR0_IA12 | DBCR0_IA12X) /* Range Exclusive */ #define DBCR_IAC12MODE (DBCR0_IA12 | DBCR0_IA12X) /* IAC 1-2 Mode Bits */ @@ -395,7 +395,7 @@ #define DBCR1_DAC1W 0x20000000 /* DAC1 Write Debug Event */ #define DBCR1_DAC2W 0x10000000 /* DAC2 Write Debug Event */ -#define dbcr_dac(task) ((task)->thread.dbcr1) +#define dbcr_dac(task) ((task)->thread.debug.dbcr1) #define DBCR_DAC1R DBCR1_DAC1R #define DBCR_DAC1W DBCR1_DAC1W #define DBCR_DAC2R DBCR1_DAC2R @@ -441,7 +441,7 @@ #define DBCR0_CRET 0x00000020 /* Critical Return Debug Event */ #define DBCR0_FT 0x00000001 /* Freeze Timers on debug event */ -#define dbcr_dac(task) ((task)->thread.dbcr0) +#define dbcr_dac(task) ((task)->thread.debug.dbcr0) #define DBCR_DAC1R DBCR0_DAC1R #define DBCR_DAC1W DBCR0_DAC1W #define DBCR_DAC2R DBCR0_DAC2R @@ -475,7 +475,7 @@ #define DBCR1_IAC34MX 0x000000C0 /* Instr Addr 3-4 range eXclusive */ #define DBCR1_IAC34AT 0x00000001 /* Instr Addr 3-4 range Toggle */ -#define dbcr_iac_range(task) ((task)->thread.dbcr1) +#define dbcr_iac_range(task) ((task)->thread.debug.dbcr1) #define DBCR_IAC12I DBCR1_IAC12M /* Range Inclusive */ #define DBCR_IAC12X DBCR1_IAC12MX /* Range Exclusive */ #define DBCR_IAC12MODE DBCR1_IAC12MX /* IAC 1-2 Mode Bits */ diff --git a/arch/powerpc/include/asm/switch_to.h b/arch/powerpc/include/asm/switch_to.h index 2be5618cdec..9ee12610af0 100644 --- a/arch/powerpc/include/asm/switch_to.h +++ b/arch/powerpc/include/asm/switch_to.h @@ -35,6 +35,7 @@ extern void giveup_vsx(struct task_struct *); extern void enable_kernel_spe(void); extern void giveup_spe(struct task_struct *); extern void load_up_spe(struct task_struct *); +extern void switch_booke_debug_regs(struct thread_struct *new_thread); #ifndef CONFIG_SMP extern void discard_lazy_cpu_state(void); diff --git a/arch/powerpc/include/uapi/asm/kvm.h b/arch/powerpc/include/uapi/asm/kvm.h index 0fb1a6e9ff9..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; @@ -269,7 +270,24 @@ 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 +299,6 @@ 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]; @@ -429,6 +443,11 @@ struct kvm_get_htab_header { #define KVM_REG_PPC_MMCR0 (KVM_REG_PPC | KVM_REG_SIZE_U64 | 0x10) #define KVM_REG_PPC_MMCR1 (KVM_REG_PPC | KVM_REG_SIZE_U64 | 0x11) #define KVM_REG_PPC_MMCRA (KVM_REG_PPC | KVM_REG_SIZE_U64 | 0x12) +#define KVM_REG_PPC_MMCR2 (KVM_REG_PPC | KVM_REG_SIZE_U64 | 0x13) +#define KVM_REG_PPC_MMCRS (KVM_REG_PPC | KVM_REG_SIZE_U64 | 0x14) +#define KVM_REG_PPC_SIAR (KVM_REG_PPC | KVM_REG_SIZE_U64 | 0x15) +#define KVM_REG_PPC_SDAR (KVM_REG_PPC | KVM_REG_SIZE_U64 | 0x16) +#define KVM_REG_PPC_SIER (KVM_REG_PPC | KVM_REG_SIZE_U64 | 0x17) #define KVM_REG_PPC_PMC1 (KVM_REG_PPC | KVM_REG_SIZE_U32 | 0x18) #define KVM_REG_PPC_PMC2 (KVM_REG_PPC | KVM_REG_SIZE_U32 | 0x19) @@ -499,6 +518,65 @@ 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) +#define KVM_REG_PPC_IAMR (KVM_REG_PPC | KVM_REG_SIZE_U64 | 0x9f) +#define KVM_REG_PPC_TFHAR (KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xa0) +#define KVM_REG_PPC_TFIAR (KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xa1) +#define KVM_REG_PPC_TEXASR (KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xa2) +#define KVM_REG_PPC_FSCR (KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xa3) +#define KVM_REG_PPC_PSPB (KVM_REG_PPC | KVM_REG_SIZE_U32 | 0xa4) +#define KVM_REG_PPC_EBBHR (KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xa5) +#define KVM_REG_PPC_EBBRR (KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xa6) +#define KVM_REG_PPC_BESCR (KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xa7) +#define KVM_REG_PPC_TAR (KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xa8) +#define KVM_REG_PPC_DPDES (KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xa9) +#define KVM_REG_PPC_DAWR (KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xaa) +#define KVM_REG_PPC_DAWRX (KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xab) +#define KVM_REG_PPC_CIABR (KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xac) +#define KVM_REG_PPC_IC (KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xad) +#define KVM_REG_PPC_VTB (KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xae) +#define KVM_REG_PPC_CSIGR (KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xaf) +#define KVM_REG_PPC_TACR (KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xb0) +#define KVM_REG_PPC_TCSCR (KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xb1) +#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) +#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 + */ +#define KVM_REG_PPC_TM (KVM_REG_PPC | 0x80000000) +/* TM GPRs */ +#define KVM_REG_PPC_TM_GPR0 (KVM_REG_PPC_TM | KVM_REG_SIZE_U64 | 0) +#define KVM_REG_PPC_TM_GPR(n) (KVM_REG_PPC_TM_GPR0 + (n)) +#define KVM_REG_PPC_TM_GPR31 (KVM_REG_PPC_TM | KVM_REG_SIZE_U64 | 0x1f) +/* TM VSX */ +#define KVM_REG_PPC_TM_VSR0 (KVM_REG_PPC_TM | KVM_REG_SIZE_U128 | 0x20) +#define KVM_REG_PPC_TM_VSR(n) (KVM_REG_PPC_TM_VSR0 + (n)) +#define KVM_REG_PPC_TM_VSR63 (KVM_REG_PPC_TM | KVM_REG_SIZE_U128 | 0x5f) +/* TM SPRS */ +#define KVM_REG_PPC_TM_CR (KVM_REG_PPC_TM | KVM_REG_SIZE_U64 | 0x60) +#define KVM_REG_PPC_TM_LR (KVM_REG_PPC_TM | KVM_REG_SIZE_U64 | 0x61) +#define KVM_REG_PPC_TM_CTR (KVM_REG_PPC_TM | KVM_REG_SIZE_U64 | 0x62) +#define KVM_REG_PPC_TM_FPSCR (KVM_REG_PPC_TM | KVM_REG_SIZE_U64 | 0x63) +#define KVM_REG_PPC_TM_AMR (KVM_REG_PPC_TM | KVM_REG_SIZE_U64 | 0x64) +#define KVM_REG_PPC_TM_PPR (KVM_REG_PPC_TM | KVM_REG_SIZE_U64 | 0x65) +#define KVM_REG_PPC_TM_VRSAVE (KVM_REG_PPC_TM | KVM_REG_SIZE_U64 | 0x66) +#define KVM_REG_PPC_TM_VSCR (KVM_REG_PPC_TM | KVM_REG_SIZE_U32 | 0x67) +#define KVM_REG_PPC_TM_DSCR (KVM_REG_PPC_TM | KVM_REG_SIZE_U64 | 0x68) +#define KVM_REG_PPC_TM_TAR (KVM_REG_PPC_TM | KVM_REG_SIZE_U64 | 0x69) + /* PPC64 eXternal Interrupt Controller Specification */ #define KVM_DEV_XICS_GRP_SOURCES 1 /* 64-bit source attributes */ diff --git a/arch/powerpc/kernel/asm-offsets.c b/arch/powerpc/kernel/asm-offsets.c index 502c7a4e73f..479b036d36d 100644 --- a/arch/powerpc/kernel/asm-offsets.c +++ b/arch/powerpc/kernel/asm-offsets.c @@ -114,7 +114,7 @@ int main(void) #endif /* CONFIG_SPE */ #endif /* CONFIG_PPC64 */ #if defined(CONFIG_4xx) || defined(CONFIG_BOOKE) - DEFINE(THREAD_DBCR0, offsetof(struct thread_struct, dbcr0)); + DEFINE(THREAD_DBCR0, offsetof(struct thread_struct, debug.dbcr0)); #endif #ifdef CONFIG_KVM_BOOK3S_32_HANDLER DEFINE(THREAD_KVM_SVCPU, offsetof(struct thread_struct, kvm_shadow_vcpu)); @@ -446,7 +446,7 @@ 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)); @@ -477,7 +477,7 @@ 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)); @@ -509,6 +509,8 @@ int main(void) DEFINE(VCPU_PRODDED, offsetof(struct kvm_vcpu, arch.prodded)); DEFINE(VCPU_MMCR, offsetof(struct kvm_vcpu, arch.mmcr)); DEFINE(VCPU_PMC, offsetof(struct kvm_vcpu, arch.pmc)); + DEFINE(VCPU_SIAR, offsetof(struct kvm_vcpu, arch.siar)); + DEFINE(VCPU_SDAR, offsetof(struct kvm_vcpu, arch.sdar)); 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)); @@ -518,18 +520,22 @@ 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(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)); DEFINE(VCORE_NAPPING_THREADS, offsetof(struct kvmppc_vcore, napping_threads)); - DEFINE(VCPU_SVCPU, offsetof(struct kvmppc_vcpu_book3s, shadow_vcpu) - - offsetof(struct kvmppc_vcpu_book3s, vcpu)); + 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_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 +#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 # define SVCPU_FIELD(x, f) @@ -581,7 +587,7 @@ 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); @@ -597,10 +603,11 @@ 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); + HSTATE_FIELD(HSTATE_PPR, ppr); #endif /* CONFIG_PPC_BOOK3S_64 */ #else /* CONFIG_PPC_BOOK3S */ diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S index 3a9ed6ac224..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 */ @@ -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 @@ -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/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/kernel/process.c b/arch/powerpc/kernel/process.c index 96d2fdf3aa9..ec5ae55ba36 100644 --- a/arch/powerpc/kernel/process.c +++ b/arch/powerpc/kernel/process.c @@ -314,28 +314,28 @@ static DEFINE_PER_CPU(struct arch_hw_breakpoint, current_brk); */ static void set_debug_reg_defaults(struct thread_struct *thread) { - thread->iac1 = thread->iac2 = 0; + thread->debug.iac1 = thread->debug.iac2 = 0; #if CONFIG_PPC_ADV_DEBUG_IACS > 2 - thread->iac3 = thread->iac4 = 0; + thread->debug.iac3 = thread->debug.iac4 = 0; #endif - thread->dac1 = thread->dac2 = 0; + thread->debug.dac1 = thread->debug.dac2 = 0; #if CONFIG_PPC_ADV_DEBUG_DVCS > 0 - thread->dvc1 = thread->dvc2 = 0; + thread->debug.dvc1 = thread->debug.dvc2 = 0; #endif - thread->dbcr0 = 0; + thread->debug.dbcr0 = 0; #ifdef CONFIG_BOOKE /* * Force User/Supervisor bits to b11 (user-only MSR[PR]=1) */ - thread->dbcr1 = DBCR1_IAC1US | DBCR1_IAC2US | \ + thread->debug.dbcr1 = DBCR1_IAC1US | DBCR1_IAC2US | DBCR1_IAC3US | DBCR1_IAC4US; /* * Force Data Address Compare User/Supervisor bits to be User-only * (0b11 MSR[PR]=1) and set all other bits in DBCR2 register to be 0. */ - thread->dbcr2 = DBCR2_DAC1US | DBCR2_DAC2US; + thread->debug.dbcr2 = DBCR2_DAC1US | DBCR2_DAC2US; #else - thread->dbcr1 = 0; + thread->debug.dbcr1 = 0; #endif } @@ -348,22 +348,22 @@ static void prime_debug_regs(struct thread_struct *thread) */ mtmsr(mfmsr() & ~MSR_DE); - mtspr(SPRN_IAC1, thread->iac1); - mtspr(SPRN_IAC2, thread->iac2); + mtspr(SPRN_IAC1, thread->debug.iac1); + mtspr(SPRN_IAC2, thread->debug.iac2); #if CONFIG_PPC_ADV_DEBUG_IACS > 2 - mtspr(SPRN_IAC3, thread->iac3); - mtspr(SPRN_IAC4, thread->iac4); + mtspr(SPRN_IAC3, thread->debug.iac3); + mtspr(SPRN_IAC4, thread->debug.iac4); #endif - mtspr(SPRN_DAC1, thread->dac1); - mtspr(SPRN_DAC2, thread->dac2); + mtspr(SPRN_DAC1, thread->debug.dac1); + mtspr(SPRN_DAC2, thread->debug.dac2); #if CONFIG_PPC_ADV_DEBUG_DVCS > 0 - mtspr(SPRN_DVC1, thread->dvc1); - mtspr(SPRN_DVC2, thread->dvc2); + mtspr(SPRN_DVC1, thread->debug.dvc1); + mtspr(SPRN_DVC2, thread->debug.dvc2); #endif - mtspr(SPRN_DBCR0, thread->dbcr0); - mtspr(SPRN_DBCR1, thread->dbcr1); + mtspr(SPRN_DBCR0, thread->debug.dbcr0); + mtspr(SPRN_DBCR1, thread->debug.dbcr1); #ifdef CONFIG_BOOKE - mtspr(SPRN_DBCR2, thread->dbcr2); + mtspr(SPRN_DBCR2, thread->debug.dbcr2); #endif } /* @@ -371,12 +371,13 @@ static void prime_debug_regs(struct thread_struct *thread) * debug registers, set the debug registers from the values * stored in the new thread. */ -static void switch_booke_debug_regs(struct thread_struct *new_thread) +void switch_booke_debug_regs(struct thread_struct *new_thread) { - if ((current->thread.dbcr0 & DBCR0_IDM) - || (new_thread->dbcr0 & DBCR0_IDM)) + if ((current->thread.debug.dbcr0 & DBCR0_IDM) + || (new_thread->debug.dbcr0 & DBCR0_IDM)) prime_debug_regs(new_thread); } +EXPORT_SYMBOL_GPL(switch_booke_debug_regs); #else /* !CONFIG_PPC_ADV_DEBUG_REGS */ #ifndef CONFIG_HAVE_HW_BREAKPOINT static void set_debug_reg_defaults(struct thread_struct *thread) diff --git a/arch/powerpc/kernel/ptrace.c b/arch/powerpc/kernel/ptrace.c index 9a0d24c390a..ddaf1780879 100644 --- a/arch/powerpc/kernel/ptrace.c +++ b/arch/powerpc/kernel/ptrace.c @@ -854,8 +854,8 @@ void user_enable_single_step(struct task_struct *task) if (regs != NULL) { #ifdef CONFIG_PPC_ADV_DEBUG_REGS - task->thread.dbcr0 &= ~DBCR0_BT; - task->thread.dbcr0 |= DBCR0_IDM | DBCR0_IC; + task->thread.debug.dbcr0 &= ~DBCR0_BT; + task->thread.debug.dbcr0 |= DBCR0_IDM | DBCR0_IC; regs->msr |= MSR_DE; #else regs->msr &= ~MSR_BE; @@ -871,8 +871,8 @@ void user_enable_block_step(struct task_struct *task) if (regs != NULL) { #ifdef CONFIG_PPC_ADV_DEBUG_REGS - task->thread.dbcr0 &= ~DBCR0_IC; - task->thread.dbcr0 = DBCR0_IDM | DBCR0_BT; + task->thread.debug.dbcr0 &= ~DBCR0_IC; + task->thread.debug.dbcr0 = DBCR0_IDM | DBCR0_BT; regs->msr |= MSR_DE; #else regs->msr &= ~MSR_SE; @@ -894,16 +894,16 @@ void user_disable_single_step(struct task_struct *task) * And, after doing so, if all debug flags are off, turn * off DBCR0(IDM) and MSR(DE) .... Torez */ - task->thread.dbcr0 &= ~DBCR0_IC; + task->thread.debug.dbcr0 &= ~DBCR0_IC; /* * Test to see if any of the DBCR_ACTIVE_EVENTS bits are set. */ - if (!DBCR_ACTIVE_EVENTS(task->thread.dbcr0, - task->thread.dbcr1)) { + if (!DBCR_ACTIVE_EVENTS(task->thread.debug.dbcr0, + task->thread.debug.dbcr1)) { /* * All debug events were off..... */ - task->thread.dbcr0 &= ~DBCR0_IDM; + task->thread.debug.dbcr0 &= ~DBCR0_IDM; regs->msr &= ~MSR_DE; } #else @@ -1022,14 +1022,14 @@ int ptrace_set_debugreg(struct task_struct *task, unsigned long addr, */ /* DAC's hold the whole address without any mode flags */ - task->thread.dac1 = data & ~0x3UL; + task->thread.debug.dac1 = data & ~0x3UL; - if (task->thread.dac1 == 0) { + if (task->thread.debug.dac1 == 0) { dbcr_dac(task) &= ~(DBCR_DAC1R | DBCR_DAC1W); - if (!DBCR_ACTIVE_EVENTS(task->thread.dbcr0, - task->thread.dbcr1)) { + if (!DBCR_ACTIVE_EVENTS(task->thread.debug.dbcr0, + task->thread.debug.dbcr1)) { task->thread.regs->msr &= ~MSR_DE; - task->thread.dbcr0 &= ~DBCR0_IDM; + task->thread.debug.dbcr0 &= ~DBCR0_IDM; } return 0; } @@ -1041,7 +1041,7 @@ int ptrace_set_debugreg(struct task_struct *task, unsigned long addr, /* Set the Internal Debugging flag (IDM bit 1) for the DBCR0 register */ - task->thread.dbcr0 |= DBCR0_IDM; + task->thread.debug.dbcr0 |= DBCR0_IDM; /* Check for write and read flags and set DBCR0 accordingly */ @@ -1071,10 +1071,10 @@ static long set_instruction_bp(struct task_struct *child, struct ppc_hw_breakpoint *bp_info) { int slot; - int slot1_in_use = ((child->thread.dbcr0 & DBCR0_IAC1) != 0); - int slot2_in_use = ((child->thread.dbcr0 & DBCR0_IAC2) != 0); - int slot3_in_use = ((child->thread.dbcr0 & DBCR0_IAC3) != 0); - int slot4_in_use = ((child->thread.dbcr0 & DBCR0_IAC4) != 0); + int slot1_in_use = ((child->thread.debug.dbcr0 & DBCR0_IAC1) != 0); + int slot2_in_use = ((child->thread.debug.dbcr0 & DBCR0_IAC2) != 0); + int slot3_in_use = ((child->thread.debug.dbcr0 & DBCR0_IAC3) != 0); + int slot4_in_use = ((child->thread.debug.dbcr0 & DBCR0_IAC4) != 0); if (dbcr_iac_range(child) & DBCR_IAC12MODE) slot2_in_use = 1; @@ -1093,9 +1093,9 @@ static long set_instruction_bp(struct task_struct *child, /* We need a pair of IAC regsisters */ if ((!slot1_in_use) && (!slot2_in_use)) { slot = 1; - child->thread.iac1 = bp_info->addr; - child->thread.iac2 = bp_info->addr2; - child->thread.dbcr0 |= DBCR0_IAC1; + child->thread.debug.iac1 = bp_info->addr; + child->thread.debug.iac2 = bp_info->addr2; + child->thread.debug.dbcr0 |= DBCR0_IAC1; if (bp_info->addr_mode == PPC_BREAKPOINT_MODE_RANGE_EXCLUSIVE) dbcr_iac_range(child) |= DBCR_IAC12X; @@ -1104,9 +1104,9 @@ static long set_instruction_bp(struct task_struct *child, #if CONFIG_PPC_ADV_DEBUG_IACS > 2 } else if ((!slot3_in_use) && (!slot4_in_use)) { slot = 3; - child->thread.iac3 = bp_info->addr; - child->thread.iac4 = bp_info->addr2; - child->thread.dbcr0 |= DBCR0_IAC3; + child->thread.debug.iac3 = bp_info->addr; + child->thread.debug.iac4 = bp_info->addr2; + child->thread.debug.dbcr0 |= DBCR0_IAC3; if (bp_info->addr_mode == PPC_BREAKPOINT_MODE_RANGE_EXCLUSIVE) dbcr_iac_range(child) |= DBCR_IAC34X; @@ -1126,30 +1126,30 @@ static long set_instruction_bp(struct task_struct *child, */ if (slot2_in_use || (slot3_in_use == slot4_in_use)) { slot = 1; - child->thread.iac1 = bp_info->addr; - child->thread.dbcr0 |= DBCR0_IAC1; + child->thread.debug.iac1 = bp_info->addr; + child->thread.debug.dbcr0 |= DBCR0_IAC1; goto out; } } if (!slot2_in_use) { slot = 2; - child->thread.iac2 = bp_info->addr; - child->thread.dbcr0 |= DBCR0_IAC2; + child->thread.debug.iac2 = bp_info->addr; + child->thread.debug.dbcr0 |= DBCR0_IAC2; #if CONFIG_PPC_ADV_DEBUG_IACS > 2 } else if (!slot3_in_use) { slot = 3; - child->thread.iac3 = bp_info->addr; - child->thread.dbcr0 |= DBCR0_IAC3; + child->thread.debug.iac3 = bp_info->addr; + child->thread.debug.dbcr0 |= DBCR0_IAC3; } else if (!slot4_in_use) { slot = 4; - child->thread.iac4 = bp_info->addr; - child->thread.dbcr0 |= DBCR0_IAC4; + child->thread.debug.iac4 = bp_info->addr; + child->thread.debug.dbcr0 |= DBCR0_IAC4; #endif } else return -ENOSPC; } out: - child->thread.dbcr0 |= DBCR0_IDM; + child->thread.debug.dbcr0 |= DBCR0_IDM; child->thread.regs->msr |= MSR_DE; return slot; @@ -1159,49 +1159,49 @@ static int del_instruction_bp(struct task_struct *child, int slot) { switch (slot) { case 1: - if ((child->thread.dbcr0 & DBCR0_IAC1) == 0) + if ((child->thread.debug.dbcr0 & DBCR0_IAC1) == 0) return -ENOENT; if (dbcr_iac_range(child) & DBCR_IAC12MODE) { /* address range - clear slots 1 & 2 */ - child->thread.iac2 = 0; + child->thread.debug.iac2 = 0; dbcr_iac_range(child) &= ~DBCR_IAC12MODE; } - child->thread.iac1 = 0; - child->thread.dbcr0 &= ~DBCR0_IAC1; + child->thread.debug.iac1 = 0; + child->thread.debug.dbcr0 &= ~DBCR0_IAC1; break; case 2: - if ((child->thread.dbcr0 & DBCR0_IAC2) == 0) + if ((child->thread.debug.dbcr0 & DBCR0_IAC2) == 0) return -ENOENT; if (dbcr_iac_range(child) & DBCR_IAC12MODE) /* used in a range */ return -EINVAL; - child->thread.iac2 = 0; - child->thread.dbcr0 &= ~DBCR0_IAC2; + child->thread.debug.iac2 = 0; + child->thread.debug.dbcr0 &= ~DBCR0_IAC2; break; #if CONFIG_PPC_ADV_DEBUG_IACS > 2 case 3: - if ((child->thread.dbcr0 & DBCR0_IAC3) == 0) + if ((child->thread.debug.dbcr0 & DBCR0_IAC3) == 0) return -ENOENT; if (dbcr_iac_range(child) & DBCR_IAC34MODE) { /* address range - clear slots 3 & 4 */ - child->thread.iac4 = 0; + child->thread.debug.iac4 = 0; dbcr_iac_range(child) &= ~DBCR_IAC34MODE; } - child->thread.iac3 = 0; - child->thread.dbcr0 &= ~DBCR0_IAC3; + child->thread.debug.iac3 = 0; + child->thread.debug.dbcr0 &= ~DBCR0_IAC3; break; case 4: - if ((child->thread.dbcr0 & DBCR0_IAC4) == 0) + if ((child->thread.debug.dbcr0 & DBCR0_IAC4) == 0) return -ENOENT; if (dbcr_iac_range(child) & DBCR_IAC34MODE) /* Used in a range */ return -EINVAL; - child->thread.iac4 = 0; - child->thread.dbcr0 &= ~DBCR0_IAC4; + child->thread.debug.iac4 = 0; + child->thread.debug.dbcr0 &= ~DBCR0_IAC4; break; #endif default: @@ -1231,18 +1231,18 @@ static int set_dac(struct task_struct *child, struct ppc_hw_breakpoint *bp_info) dbcr_dac(child) |= DBCR_DAC1R; if (bp_info->trigger_type & PPC_BREAKPOINT_TRIGGER_WRITE) dbcr_dac(child) |= DBCR_DAC1W; - child->thread.dac1 = (unsigned long)bp_info->addr; + child->thread.debug.dac1 = (unsigned long)bp_info->addr; #if CONFIG_PPC_ADV_DEBUG_DVCS > 0 if (byte_enable) { - child->thread.dvc1 = + child->thread.debug.dvc1 = (unsigned long)bp_info->condition_value; - child->thread.dbcr2 |= + child->thread.debug.dbcr2 |= ((byte_enable << DBCR2_DVC1BE_SHIFT) | (condition_mode << DBCR2_DVC1M_SHIFT)); } #endif #ifdef CONFIG_PPC_ADV_DEBUG_DAC_RANGE - } else if (child->thread.dbcr2 & DBCR2_DAC12MODE) { + } else if (child->thread.debug.dbcr2 & DBCR2_DAC12MODE) { /* Both dac1 and dac2 are part of a range */ return -ENOSPC; #endif @@ -1252,19 +1252,19 @@ static int set_dac(struct task_struct *child, struct ppc_hw_breakpoint *bp_info) dbcr_dac(child) |= DBCR_DAC2R; if (bp_info->trigger_type & PPC_BREAKPOINT_TRIGGER_WRITE) dbcr_dac(child) |= DBCR_DAC2W; - child->thread.dac2 = (unsigned long)bp_info->addr; + child->thread.debug.dac2 = (unsigned long)bp_info->addr; #if CONFIG_PPC_ADV_DEBUG_DVCS > 0 if (byte_enable) { - child->thread.dvc2 = + child->thread.debug.dvc2 = (unsigned long)bp_info->condition_value; - child->thread.dbcr2 |= + child->thread.debug.dbcr2 |= ((byte_enable << DBCR2_DVC2BE_SHIFT) | (condition_mode << DBCR2_DVC2M_SHIFT)); } #endif } else return -ENOSPC; - child->thread.dbcr0 |= DBCR0_IDM; + child->thread.debug.dbcr0 |= DBCR0_IDM; child->thread.regs->msr |= MSR_DE; return slot + 4; @@ -1276,32 +1276,32 @@ static int del_dac(struct task_struct *child, int slot) if ((dbcr_dac(child) & (DBCR_DAC1R | DBCR_DAC1W)) == 0) return -ENOENT; - child->thread.dac1 = 0; + child->thread.debug.dac1 = 0; dbcr_dac(child) &= ~(DBCR_DAC1R | DBCR_DAC1W); #ifdef CONFIG_PPC_ADV_DEBUG_DAC_RANGE - if (child->thread.dbcr2 & DBCR2_DAC12MODE) { - child->thread.dac2 = 0; - child->thread.dbcr2 &= ~DBCR2_DAC12MODE; + if (child->thread.debug.dbcr2 & DBCR2_DAC12MODE) { + child->thread.debug.dac2 = 0; + child->thread.debug.dbcr2 &= ~DBCR2_DAC12MODE; } - child->thread.dbcr2 &= ~(DBCR2_DVC1M | DBCR2_DVC1BE); + child->thread.debug.dbcr2 &= ~(DBCR2_DVC1M | DBCR2_DVC1BE); #endif #if CONFIG_PPC_ADV_DEBUG_DVCS > 0 - child->thread.dvc1 = 0; + child->thread.debug.dvc1 = 0; #endif } else if (slot == 2) { if ((dbcr_dac(child) & (DBCR_DAC2R | DBCR_DAC2W)) == 0) return -ENOENT; #ifdef CONFIG_PPC_ADV_DEBUG_DAC_RANGE - if (child->thread.dbcr2 & DBCR2_DAC12MODE) + if (child->thread.debug.dbcr2 & DBCR2_DAC12MODE) /* Part of a range */ return -EINVAL; - child->thread.dbcr2 &= ~(DBCR2_DVC2M | DBCR2_DVC2BE); + child->thread.debug.dbcr2 &= ~(DBCR2_DVC2M | DBCR2_DVC2BE); #endif #if CONFIG_PPC_ADV_DEBUG_DVCS > 0 - child->thread.dvc2 = 0; + child->thread.debug.dvc2 = 0; #endif - child->thread.dac2 = 0; + child->thread.debug.dac2 = 0; dbcr_dac(child) &= ~(DBCR_DAC2R | DBCR_DAC2W); } else return -EINVAL; @@ -1343,22 +1343,22 @@ static int set_dac_range(struct task_struct *child, return -EIO; } - if (child->thread.dbcr0 & + if (child->thread.debug.dbcr0 & (DBCR0_DAC1R | DBCR0_DAC1W | DBCR0_DAC2R | DBCR0_DAC2W)) return -ENOSPC; if (bp_info->trigger_type & PPC_BREAKPOINT_TRIGGER_READ) - child->thread.dbcr0 |= (DBCR0_DAC1R | DBCR0_IDM); + child->thread.debug.dbcr0 |= (DBCR0_DAC1R | DBCR0_IDM); if (bp_info->trigger_type & PPC_BREAKPOINT_TRIGGER_WRITE) - child->thread.dbcr0 |= (DBCR0_DAC1W | DBCR0_IDM); - child->thread.dac1 = bp_info->addr; - child->thread.dac2 = bp_info->addr2; + child->thread.debug.dbcr0 |= (DBCR0_DAC1W | DBCR0_IDM); + child->thread.debug.dac1 = bp_info->addr; + child->thread.debug.dac2 = bp_info->addr2; if (mode == PPC_BREAKPOINT_MODE_RANGE_INCLUSIVE) - child->thread.dbcr2 |= DBCR2_DAC12M; + child->thread.debug.dbcr2 |= DBCR2_DAC12M; else if (mode == PPC_BREAKPOINT_MODE_RANGE_EXCLUSIVE) - child->thread.dbcr2 |= DBCR2_DAC12MX; + child->thread.debug.dbcr2 |= DBCR2_DAC12MX; else /* PPC_BREAKPOINT_MODE_MASK */ - child->thread.dbcr2 |= DBCR2_DAC12MM; + child->thread.debug.dbcr2 |= DBCR2_DAC12MM; child->thread.regs->msr |= MSR_DE; return 5; @@ -1489,9 +1489,9 @@ static long ppc_del_hwdebug(struct task_struct *child, long data) rc = del_dac(child, (int)data - 4); if (!rc) { - if (!DBCR_ACTIVE_EVENTS(child->thread.dbcr0, - child->thread.dbcr1)) { - child->thread.dbcr0 &= ~DBCR0_IDM; + if (!DBCR_ACTIVE_EVENTS(child->thread.debug.dbcr0, + child->thread.debug.dbcr1)) { + child->thread.debug.dbcr0 &= ~DBCR0_IDM; child->thread.regs->msr &= ~MSR_DE; } } @@ -1669,7 +1669,7 @@ long arch_ptrace(struct task_struct *child, long request, if (addr > 0) break; #ifdef CONFIG_PPC_ADV_DEBUG_REGS - ret = put_user(child->thread.dac1, datalp); + ret = put_user(child->thread.debug.dac1, datalp); #else dabr_fake = ((child->thread.hw_brk.address & (~HW_BRK_TYPE_DABR)) | (child->thread.hw_brk.type & HW_BRK_TYPE_DABR)); diff --git a/arch/powerpc/kernel/ptrace32.c b/arch/powerpc/kernel/ptrace32.c index f51599e941c..18c7c65ea46 100644 --- a/arch/powerpc/kernel/ptrace32.c +++ b/arch/powerpc/kernel/ptrace32.c @@ -269,7 +269,7 @@ long compat_arch_ptrace(struct task_struct *child, compat_long_t request, if (addr > 0) break; #ifdef CONFIG_PPC_ADV_DEBUG_REGS - ret = put_user(child->thread.dac1, (u32 __user *)data); + ret = put_user(child->thread.debug.dac1, (u32 __user *)data); #else dabr_fake = ( (child->thread.hw_brk.address & (~HW_BRK_TYPE_DABR)) | diff --git a/arch/powerpc/kernel/signal_32.c b/arch/powerpc/kernel/signal_32.c index bebdf1a1a54..3f220d93c72 100644 --- a/arch/powerpc/kernel/signal_32.c +++ b/arch/powerpc/kernel/signal_32.c @@ -1309,7 +1309,7 @@ int sys_debug_setcontext(struct ucontext __user *ctx, unsigned char tmp; unsigned long new_msr = regs->msr; #ifdef CONFIG_PPC_ADV_DEBUG_REGS - unsigned long new_dbcr0 = current->thread.dbcr0; + unsigned long new_dbcr0 = current->thread.debug.dbcr0; #endif for (i=0; i<ndbg; i++) { @@ -1324,7 +1324,7 @@ int sys_debug_setcontext(struct ucontext __user *ctx, } else { new_dbcr0 &= ~DBCR0_IC; if (!DBCR_ACTIVE_EVENTS(new_dbcr0, - current->thread.dbcr1)) { + current->thread.debug.dbcr1)) { new_msr &= ~MSR_DE; new_dbcr0 &= ~DBCR0_IDM; } @@ -1359,7 +1359,7 @@ int sys_debug_setcontext(struct ucontext __user *ctx, the user is really doing something wrong. */ regs->msr = new_msr; #ifdef CONFIG_PPC_ADV_DEBUG_REGS - current->thread.dbcr0 = new_dbcr0; + current->thread.debug.dbcr0 = new_dbcr0; #endif if (!access_ok(VERIFY_READ, ctx, sizeof(*ctx)) diff --git a/arch/powerpc/kernel/traps.c b/arch/powerpc/kernel/traps.c index f783c932fae..4f5df4e7df1 100644 --- a/arch/powerpc/kernel/traps.c +++ b/arch/powerpc/kernel/traps.c @@ -351,8 +351,8 @@ static inline int check_io_access(struct pt_regs *regs) #define REASON_TRAP ESR_PTR /* single-step stuff */ -#define single_stepping(regs) (current->thread.dbcr0 & DBCR0_IC) -#define clear_single_step(regs) (current->thread.dbcr0 &= ~DBCR0_IC) +#define single_stepping(regs) (current->thread.debug.dbcr0 & DBCR0_IC) +#define clear_single_step(regs) (current->thread.debug.dbcr0 &= ~DBCR0_IC) #else /* On non-4xx, the reason for the machine check or program @@ -1486,7 +1486,7 @@ static void handle_debug(struct pt_regs *regs, unsigned long debug_status) if (debug_status & (DBSR_DAC1R | DBSR_DAC1W)) { dbcr_dac(current) &= ~(DBCR_DAC1R | DBCR_DAC1W); #ifdef CONFIG_PPC_ADV_DEBUG_DAC_RANGE - current->thread.dbcr2 &= ~DBCR2_DAC12MODE; + current->thread.debug.dbcr2 &= ~DBCR2_DAC12MODE; #endif do_send_trap(regs, mfspr(SPRN_DAC1), debug_status, TRAP_HWBKPT, 5); @@ -1497,24 +1497,24 @@ static void handle_debug(struct pt_regs *regs, unsigned long debug_status) 6); changed |= 0x01; } else if (debug_status & DBSR_IAC1) { - current->thread.dbcr0 &= ~DBCR0_IAC1; + current->thread.debug.dbcr0 &= ~DBCR0_IAC1; dbcr_iac_range(current) &= ~DBCR_IAC12MODE; do_send_trap(regs, mfspr(SPRN_IAC1), debug_status, TRAP_HWBKPT, 1); changed |= 0x01; } else if (debug_status & DBSR_IAC2) { - current->thread.dbcr0 &= ~DBCR0_IAC2; + current->thread.debug.dbcr0 &= ~DBCR0_IAC2; do_send_trap(regs, mfspr(SPRN_IAC2), debug_status, TRAP_HWBKPT, 2); changed |= 0x01; } else if (debug_status & DBSR_IAC3) { - current->thread.dbcr0 &= ~DBCR0_IAC3; + current->thread.debug.dbcr0 &= ~DBCR0_IAC3; dbcr_iac_range(current) &= ~DBCR_IAC34MODE; do_send_trap(regs, mfspr(SPRN_IAC3), debug_status, TRAP_HWBKPT, 3); changed |= 0x01; } else if (debug_status & DBSR_IAC4) { - current->thread.dbcr0 &= ~DBCR0_IAC4; + current->thread.debug.dbcr0 &= ~DBCR0_IAC4; do_send_trap(regs, mfspr(SPRN_IAC4), debug_status, TRAP_HWBKPT, 4); changed |= 0x01; @@ -1524,19 +1524,20 @@ static void handle_debug(struct pt_regs *regs, unsigned long debug_status) * Check all other debug flags and see if that bit needs to be turned * back on or not. */ - if (DBCR_ACTIVE_EVENTS(current->thread.dbcr0, current->thread.dbcr1)) + if (DBCR_ACTIVE_EVENTS(current->thread.debug.dbcr0, + current->thread.debug.dbcr1)) regs->msr |= MSR_DE; else /* Make sure the IDM flag is off */ - current->thread.dbcr0 &= ~DBCR0_IDM; + current->thread.debug.dbcr0 &= ~DBCR0_IDM; if (changed & 0x01) - mtspr(SPRN_DBCR0, current->thread.dbcr0); + mtspr(SPRN_DBCR0, current->thread.debug.dbcr0); } void __kprobes DebugException(struct pt_regs *regs, unsigned long debug_status) { - current->thread.dbsr = debug_status; + current->thread.debug.dbsr = debug_status; /* Hack alert: On BookE, Branch Taken stops on the branch itself, while * on server, it stops on the target of the branch. In order to simulate @@ -1553,8 +1554,8 @@ void __kprobes DebugException(struct pt_regs *regs, unsigned long debug_status) /* Do the single step trick only when coming from userspace */ if (user_mode(regs)) { - current->thread.dbcr0 &= ~DBCR0_BT; - current->thread.dbcr0 |= DBCR0_IDM | DBCR0_IC; + current->thread.debug.dbcr0 &= ~DBCR0_BT; + current->thread.debug.dbcr0 |= DBCR0_IDM | DBCR0_IC; regs->msr |= MSR_DE; return; } @@ -1582,13 +1583,13 @@ void __kprobes DebugException(struct pt_regs *regs, unsigned long debug_status) return; if (user_mode(regs)) { - current->thread.dbcr0 &= ~DBCR0_IC; - if (DBCR_ACTIVE_EVENTS(current->thread.dbcr0, - current->thread.dbcr1)) + current->thread.debug.dbcr0 &= ~DBCR0_IC; + if (DBCR_ACTIVE_EVENTS(current->thread.debug.dbcr0, + current->thread.debug.dbcr1)) regs->msr |= MSR_DE; else /* Make sure the IDM bit is off */ - current->thread.dbcr0 &= ~DBCR0_IDM; + current->thread.debug.dbcr0 &= ~DBCR0_IDM; } _exception(SIGTRAP, regs, TRAP_TRACE, regs->nip); diff --git a/arch/powerpc/kvm/44x.c b/arch/powerpc/kvm/44x.c index 2f5c6b6d687..93221e87b91 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); @@ -176,28 +179,53 @@ 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; + + 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; - return kvm_init(NULL, sizeof(struct kvmppc_vcpu_44x), 0, THIS_MODULE); +err_out: + return r; } static void __exit kvmppc_44x_exit(void) { + kvmppc_pr_ops = NULL; kvmppc_booke_exit(); } 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/Kconfig b/arch/powerpc/kvm/Kconfig index ffaef2cb101..8aeeda1ff42 100644 --- a/arch/powerpc/kvm/Kconfig +++ b/arch/powerpc/kvm/Kconfig @@ -34,17 +34,20 @@ 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 +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 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. @@ -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. @@ -69,8 +73,9 @@ 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 select CMA ---help--- @@ -89,9 +94,20 @@ config KVM_BOOK3S_64_HV If unsure, say N. config KVM_BOOK3S_64_PR - def_bool y - depends on KVM_BOOK3S_64 && !KVM_BOOK3S_64_HV - select KVM_BOOK3S_PR + 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 + 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 6646c952c5e..ce569b6bf4d 100644 --- a/arch/powerpc/kvm/Makefile +++ b/arch/powerpc/kvm/Makefile @@ -53,41 +53,51 @@ kvm-e500mc-objs := \ e500_emulate.o kvm-objs-$(CONFIG_KVM_E500MC) := $(kvm-e500mc-objs) -kvm-book3s_64-objs-$(CONFIG_KVM_BOOK3S_64_PR) := \ - $(KVM)/coalesced_mmio.o \ +kvm-book3s_64-builtin-objs-$(CONFIG_KVM_BOOK3S_64_HANDLER) := \ + book3s_64_vio_hv.o + +kvm-pr-y := \ 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) := \ + +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-$(CONFIG_KVM_BOOK3S_64_HV) := \ +kvm-hv-y += \ book3s_hv.o \ book3s_hv_interrupts.o \ book3s_64_mmu_hv.o + kvm-book3s_64-builtin-xics-objs-$(CONFIG_KVM_XICS) := \ book3s_hv_rm_xics.o -kvm-book3s_64-builtin-objs-$(CONFIG_KVM_BOOK3S_64_HV) := \ + +ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE +kvm-book3s_64-builtin-objs-$(CONFIG_KVM_BOOK3S_64_HANDLER) += \ book3s_hv_rmhandlers.o \ book3s_hv_rm_mmu.o \ - book3s_64_vio_hv.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 -kvm-book3s_64-module-objs := \ +kvm-book3s_64-module-objs += \ $(KVM)/kvm_main.o \ $(KVM)/eventfd.o \ powerpc.o \ @@ -123,4 +133,7 @@ obj-$(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 700df6f1d32..8912608b7e1 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 @@ -69,6 +70,50 @@ void kvmppc_core_load_guest_debugstate(struct kvm_vcpu *vcpu) { } +static inline unsigned long kvmppc_interrupt_offset(struct kvm_vcpu *vcpu) +{ + if (!is_kvmppc_hv_enabled(vcpu->kvm)) + 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 (is_kvmppc_hv_enabled(vcpu->kvm)) + 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 (is_kvmppc_hv_enabled(vcpu->kvm)) + 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); @@ -126,28 +171,32 @@ 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) @@ -285,8 +334,10 @@ 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) +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 +353,23 @@ 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); } +EXPORT_SYMBOL_GPL(kvmppc_gfn_to_pfn); 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 +415,7 @@ 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; @@ -374,6 +428,7 @@ 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) @@ -383,7 +438,7 @@ 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; @@ -404,6 +459,7 @@ nopte: mmio: return EMULATE_DO_MMIO; } +EXPORT_SYMBOL_GPL(kvmppc_ld); int kvm_arch_vcpu_setup(struct kvm_vcpu *vcpu) { @@ -419,6 +475,18 @@ 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 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 vcpu->kvm->arch.kvm_ops->set_sregs(vcpu, sregs); +} + int kvm_arch_vcpu_ioctl_get_regs(struct kvm_vcpu *vcpu, struct kvm_regs *regs) { int i; @@ -495,8 +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_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) { @@ -528,6 +595,9 @@ 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; @@ -572,8 +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_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) { @@ -605,6 +674,13 @@ 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: @@ -625,6 +701,27 @@ 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) +{ + vcpu->kvm->arch.kvm_ops->vcpu_load(vcpu, cpu); +} + +void kvmppc_core_vcpu_put(struct kvm_vcpu *vcpu) +{ + vcpu->kvm->arch.kvm_ops->vcpu_put(vcpu); +} + +void kvmppc_set_msr(struct kvm_vcpu *vcpu, u64 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 vcpu->kvm->arch.kvm_ops->vcpu_run(kvm_run, vcpu); +} + int kvm_arch_vcpu_ioctl_translate(struct kvm_vcpu *vcpu, struct kvm_translation *tr) { @@ -644,3 +741,141 @@ 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 kvm->arch.kvm_ops->vcpu_create(kvm, id); +} + +void kvmppc_core_vcpu_free(struct kvm_vcpu *vcpu) +{ + vcpu->kvm->arch.kvm_ops->vcpu_free(vcpu); +} + +int kvmppc_core_check_requests(struct kvm_vcpu *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 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) +{ + 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 kvm->arch.kvm_ops->create_memslot(slot, npages); +} + +void kvmppc_core_flush_memslot(struct kvm *kvm, struct kvm_memory_slot *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 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) +{ + kvm->arch.kvm_ops->commit_memory_region(kvm, mem, old); +} + +int kvm_unmap_hva(struct kvm *kvm, unsigned long 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 kvm->arch.kvm_ops->unmap_hva_range(kvm, start, end); +} + +int kvm_age_hva(struct kvm *kvm, unsigned long hva) +{ + return kvm->arch.kvm_ops->age_hva(kvm, hva); +} + +int kvm_test_age_hva(struct kvm *kvm, unsigned long 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) +{ + kvm->arch.kvm_ops->set_spte_hva(kvm, hva, pte); +} + +void kvmppc_mmu_destroy(struct kvm_vcpu *vcpu) +{ + vcpu->kvm->arch.kvm_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 kvm->arch.kvm_ops->init_vm(kvm); +} + +void kvmppc_core_destroy_vm(struct kvm *kvm) +{ + kvm->arch.kvm_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) +{ + /* + * 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 new file mode 100644 index 00000000000..4bf956cf94d --- /dev/null +++ b/arch/powerpc/kvm/book3s.h @@ -0,0 +1,34 @@ +/* + * 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); +extern int kvmppc_book3s_init_pr(void); +extern void kvmppc_book3s_exit_pr(void); + +#endif diff --git a/arch/powerpc/kvm/book3s_32_mmu.c b/arch/powerpc/kvm/book3s_32_mmu.c index c8cefdd15fd..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); @@ -111,10 +112,11 @@ 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 +134,7 @@ 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); @@ -145,7 +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; @@ -186,8 +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; } @@ -201,9 +203,8 @@ 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) { - struct kvmppc_vcpu_book3s *vcpu_book3s = to_book3s(vcpu); u32 sre; hva_t ptegp; u32 pteg[16]; @@ -218,7 +219,7 @@ 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; @@ -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; @@ -271,19 +269,23 @@ 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 (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; } @@ -302,12 +304,14 @@ 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; pte->eaddr = eaddr; + pte->page_size = MMU_PAGE_4K; /* Magic page override */ if (unlikely(mp_ea) && @@ -323,11 +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; } @@ -347,7 +353,12 @@ 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_32_mmu_host.c b/arch/powerpc/kvm/book3s_32_mmu_host.c index 00e619bf608..3a0abd2e5a1 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; @@ -341,7 +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.c b/arch/powerpc/kvm/book3s_64_mmu.c index 7e345e00661..83da1f868fd 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) @@ -119,11 +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; @@ -148,10 +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; @@ -166,18 +177,38 @@ 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) + struct kvmppc_pte *gpte, bool data, + bool iswrite) { - struct kvmppc_vcpu_book3s *vcpu_book3s = to_book3s(vcpu); struct kvmppc_slb *slbe; hva_t ptegp; u64 pteg[16]; @@ -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; } @@ -222,8 +255,12 @@ 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; + + 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; @@ -240,6 +277,13 @@ 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 +300,15 @@ do_second: v = pteg[i]; r = pteg[i+1]; pp = (r & HPTE_R_PP) | key; - eaddr_mask = 0xFFF; + if (r & HPTE_R_PP0) + pp |= 8; 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; @@ -277,6 +323,7 @@ do_second: case 3: case 5: case 7: + case 10: gpte->may_read = true; break; } @@ -287,30 +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) { - /* 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; + 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) + if (!gpte->may_read || (iswrite && !gpte->may_write)) 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; } @@ -345,6 +399,21 @@ 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; @@ -460,14 +529,45 @@ 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); - if (large) - mask = 0xFFFFFF000ULL; - kvmppc_mmu_pte_vflush(vcpu, va >> 12, mask); + /* + * 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; + } + /* 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 +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) { @@ -475,11 +575,13 @@ 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); @@ -490,28 +592,41 @@ 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..0d513af62bb 100644 --- a/arch/powerpc/kvm/book3s_64_mmu_host.c +++ b/arch/powerpc/kvm/book3s_64_mmu_host.c @@ -27,14 +27,14 @@ #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 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); } @@ -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; @@ -90,16 +91,26 @@ 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; + bool writable; + 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); - 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 |= orig_pte->raddr & (~0xfffULL & ~PAGE_MASK); + 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); @@ -117,20 +128,39 @@ 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; - else - mark_page_dirty(vcpu->kvm, orig_pte->raddr >> PAGE_SHIFT); + kvm_set_pfn_accessed(pfn); + if (!orig_pte->may_write || !writable) + 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, + * 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); - hash = hpt_hash(vpn, PTE_SIZE, 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); @@ -139,11 +169,11 @@ 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, - 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 */ @@ -152,8 +182,6 @@ 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); @@ -164,19 +192,37 @@ 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; + cpte->slot = hpteg + (ret & 7); + cpte->host_vpn = vpn; + cpte->pte = *orig_pte; + cpte->pfn = pfn; + cpte->pagesize = hpsize; - kvmppc_mmu_hpte_cache_map(vcpu, pte); + kvmppc_mmu_hpte_cache_map(vcpu, cpte); + cpte = NULL; } - kvm_release_pfn_clean(hpaddr >> PAGE_SHIFT); + +out_unlock: + spin_unlock(&kvm->mmu_lock); + kvm_release_pfn_clean(pfn); + if (cpte) + kvmppc_mmu_hpte_cache_free(cpte); 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; @@ -291,6 +337,12 @@ 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; @@ -326,7 +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 043eec8461e..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); @@ -451,7 +447,7 @@ 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; @@ -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; @@ -1512,9 +1509,8 @@ 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_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); diff --git a/arch/powerpc/kvm/book3s_emulate.c b/arch/powerpc/kvm/book3s_emulate.c index 360ce68c980..99d40f8977e 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); @@ -172,7 +172,7 @@ int kvmppc_core_emulate_op(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 */ @@ -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); @@ -349,7 +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; @@ -472,7 +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_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 diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c index 62a2b5ab08e..072287f1c3b 100644 --- a/arch/powerpc/kvm/book3s_hv.c +++ b/arch/powerpc/kvm/book3s_hv.c @@ -52,6 +52,9 @@ #include <linux/vmalloc.h> #include <linux/highmem.h> #include <linux/hugetlb.h> +#include <linux/module.h> + +#include "book3s.h" /* #define EXIT_DEBUG */ /* #define EXIT_DEBUG_SIMPLE */ @@ -66,7 +69,7 @@ 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 +128,7 @@ 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 +146,7 @@ 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; @@ -155,17 +158,46 @@ 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; } +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; @@ -195,7 +227,7 @@ 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); } @@ -489,7 +521,7 @@ 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; @@ -538,6 +570,15 @@ 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), @@ -576,8 +617,8 @@ 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; @@ -671,16 +712,16 @@ 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; } 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; @@ -694,12 +735,12 @@ 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++) { @@ -714,7 +755,23 @@ 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 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); +} + +static int kvmppc_get_one_reg_hv(struct kvm_vcpu *vcpu, u64 id, + union kvmppc_one_reg *val) { int r = 0; long int i; @@ -749,6 +806,12 @@ 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)) { @@ -787,6 +850,18 @@ 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; + 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; + case KVM_REG_PPC_ARCH_COMPAT: + *val = get_reg_val(id, vcpu->arch.vcore->arch_compat); + break; default: r = -EINVAL; break; @@ -795,7 +870,8 @@ 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; @@ -833,6 +909,12 @@ 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)) { @@ -880,6 +962,20 @@ 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; + 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; + case KVM_REG_PPC_ARCH_COMPAT: + r = kvmppc_set_arch_compat(vcpu, set_reg_val(id, *val)); + break; default: r = -EINVAL; break; @@ -888,14 +984,8 @@ 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; @@ -919,8 +1009,7 @@ 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; @@ -940,6 +1029,7 @@ 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++; @@ -972,7 +1062,7 @@ 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); @@ -983,6 +1073,12 @@ 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; @@ -1264,8 +1360,8 @@ 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; @@ -1424,7 +1520,7 @@ 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; @@ -1546,7 +1642,8 @@ 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; @@ -1592,7 +1689,8 @@ 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; @@ -1613,7 +1711,8 @@ 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; @@ -1667,8 +1766,8 @@ 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); @@ -1681,8 +1780,8 @@ 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) @@ -1692,9 +1791,9 @@ 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; @@ -1710,9 +1809,9 @@ 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; @@ -1729,6 +1828,37 @@ 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 void kvmppc_mmu_destroy_hv(struct kvm_vcpu *vcpu) +{ + return; +} + static int kvmppc_hv_setup_htab_rma(struct kvm_vcpu *vcpu) { int err = 0; @@ -1737,7 +1867,8 @@ 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; @@ -1802,9 +1933,9 @@ 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); @@ -1825,23 +1956,21 @@ 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); @@ -1860,6 +1989,8 @@ 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; @@ -1875,7 +2006,7 @@ 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; @@ -1893,9 +2024,6 @@ 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); @@ -1931,61 +2059,162 @@ int kvmppc_core_init_vm(struct kvm *kvm) return 0; } -void kvmppc_core_destroy_vm(struct kvm *kvm) +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; +} + +static void kvmppc_core_destroy_vm_hv(struct kvm *kvm) { uninhibit_secondary_onlining(); + kvmppc_free_vcores(kvm); if (kvm->arch.rma) { kvm_release_rma(kvm->arch.rma); 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) { - int r; + struct kvm *kvm __maybe_unused = filp->private_data; + void __user *argp = (void __user *)arg; + long r; - r = kvm_init(NULL, sizeof(struct kvm_vcpu), 0, THIS_MODULE); + switch (ioctl) { - if (r) + 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 kvm_ops_hv = { + .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, + .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; + /* + * 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_hv_exit(void) +static void kvmppc_book3s_exit_hv(void) { - kvm_exit(); + kvmppc_hv_ops = NULL; } -module_init(kvmppc_book3s_hv_init); -module_exit(kvmppc_book3s_hv_exit); +module_init(kvmppc_book3s_init_hv); +module_exit(kvmppc_book3s_exit_hv); +MODULE_LICENSE("GPL"); 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_hv_rmhandlers.S b/arch/powerpc/kvm/book3s_hv_rmhandlers.S index c71103b8a74..bc8de75b192 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. @@ -66,8 +42,11 @@ 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 +56,103 @@ _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 +208,7 @@ 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 +218,57 @@ 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 +281,8 @@ 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 */ @@ -200,8 +323,12 @@ 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 @@ -254,22 +381,15 @@ 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) 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) @@ -343,7 +463,28 @@ 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 + + /* 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 @@ -353,12 +494,22 @@ 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 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 @@ -405,7 +556,8 @@ 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 @@ -541,7 +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 */ @@ -550,13 +702,15 @@ 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) @@ -570,6 +724,10 @@ 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 @@ -584,8 +742,8 @@ END_FTR_SECTION_IFSET(CPU_FTR_CFAR) /* * 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 @@ -595,6 +753,19 @@ 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 +#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) + ld r9, HSTATE_KVM_VCPU(r13) /* Save registers */ @@ -620,6 +791,10 @@ 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) @@ -642,10 +817,6 @@ END_FTR_SECTION_IFSET(CPU_FTR_CFAR) 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 @@ -696,46 +867,11 @@ 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) @@ -764,27 +900,9 @@ 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 */ - /* 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 @@ -954,7 +1072,30 @@ 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 + + /* 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 */ stb r0,VCORE_IN_GUEST(r5) lis r8,0x7fff /* MAX_INT@h */ mtspr SPRN_HDEC,r8 @@ -1052,6 +1193,13 @@ 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 @@ -1062,6 +1210,10 @@ 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 @@ -1134,9 +1286,13 @@ 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 @@ -1158,103 +1314,30 @@ 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. @@ -1333,7 +1416,7 @@ 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 @@ -1701,67 +1784,70 @@ 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 +/* + * 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 -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) + /* Now read the interrupt from the ICP */ + ld r6, 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 + cmpdi r6, 0 + beq- 1f + lwzcix r0, r6, r7 + rlwinm. r3, r0, 0, 0xffffff sync - li r0, 0xff - li r6, XICS_MFRR - stbcix r0, r5, r6 /* clear the IPI */ - stwcix r3, r5, r7 /* EOI it */ -37: sync + beq 1f /* if nothing pending in the ICP */ - /* 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 + /* 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 -kvm_no_guest: - li r0, KVM_HWTHREAD_IN_NAP - stb r0, HSTATE_HWTHREAD_STATE(r13) + /* 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 - 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 . + /* 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. @@ -1879,3 +1965,11 @@ 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 . diff --git a/arch/powerpc/kvm/book3s_interrupts.S b/arch/powerpc/kvm/book3s_interrupts.S index 17cfae5497a..f4dd041c14e 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) @@ -111,9 +121,6 @@ kvm_start_lightweight: * */ -.global kvmppc_handler_highmem -kvmppc_handler_highmem: - /* * Register usage at this point: * @@ -125,18 +132,31 @@ 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) @@ -161,7 +181,7 @@ kvmppc_handler_highmem: /* 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_mmu_hpte.c b/arch/powerpc/kvm/book3s_mmu_hpte.c index da8b13c4b77..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 @@ -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 +91,15 @@ 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 + + vcpu3s->hpte_cache_count++; + spin_unlock(&vcpu3s->mmu_lock); } @@ -113,10 +130,13 @@ 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 + vcpu3s->hpte_cache_count--; spin_unlock(&vcpu3s->mmu_lock); - vcpu3s->hpte_cache_count--; call_rcu(&pte->rcu_head, free_pte_rcu); } @@ -219,6 +239,29 @@ 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 +292,11 @@ 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; @@ -285,15 +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); @@ -320,6 +372,10 @@ 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 27db1e66595..df36cf2ed22 100644 --- a/arch/powerpc/kvm/book3s_pr.c +++ b/arch/powerpc/kvm/book3s_pr.c @@ -40,8 +40,12 @@ #include <linux/sched.h> #include <linux/vmalloc.h> #include <linux/highmem.h> +#include <linux/module.h> -#include "trace.h" +#include "book3s.h" + +#define CREATE_TRACE_POINTS +#include "trace_pr.h" /* #define EXIT_DEBUG */ /* #define DEBUG_EXT */ @@ -56,29 +60,25 @@ 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); 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 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 } -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); 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 @@ -87,7 +87,61 @@ void kvmppc_core_vcpu_put(struct kvm_vcpu *vcpu) vcpu->cpu = -1; } -int kvmppc_core_check_requests(struct kvm_vcpu *vcpu) +/* 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; +} + +static int kvmppc_core_check_requests_pr(struct kvm_vcpu *vcpu) { int r = 1; /* Indicate we want to get back into the guest */ @@ -100,44 +154,69 @@ 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) +static int kvm_unmap_hva_pr(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) +static int kvm_unmap_hva_range_pr(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; } -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 */ - kvm_unmap_hva(kvm, hva); + do_kvm_unmap_hva(kvm, hva, hva + PAGE_SIZE); } /*****************************************/ @@ -159,7 +238,7 @@ 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; @@ -219,7 +298,7 @@ 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; @@ -256,6 +335,23 @@ 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; @@ -334,6 +430,7 @@ 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; @@ -344,10 +441,12 @@ 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; @@ -355,6 +454,7 @@ 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)) { @@ -388,22 +488,18 @@ 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 */ @@ -411,12 +507,20 @@ 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 */ @@ -619,13 +723,15 @@ 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; } -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; @@ -643,25 +749,32 @@ 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) { + 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))) { @@ -682,25 +795,36 @@ 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) { + /* + * 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; @@ -743,13 +867,10 @@ 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 @@ -798,7 +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; @@ -881,9 +1002,7 @@ 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); @@ -920,8 +1039,8 @@ 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; @@ -947,13 +1066,13 @@ 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) { @@ -983,7 +1102,8 @@ 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; @@ -1012,7 +1132,8 @@ 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; @@ -1042,28 +1163,30 @@ 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; int err = -ENOMEM; unsigned long p; - vcpu_book3s = vzalloc(sizeof(struct kvmppc_vcpu_book3s)); - if (!vcpu_book3s) + vcpu = kmem_cache_zalloc(kvm_vcpu_cache, GFP_KERNEL); + if (!vcpu) goto out; - vcpu_book3s->shadow_vcpu = - kzalloc(sizeof(*vcpu_book3s->shadow_vcpu), GFP_KERNEL); - if (!vcpu_book3s->shadow_vcpu) + vcpu_book3s = vzalloc(sizeof(struct kvmppc_vcpu_book3s)); + if (!vcpu_book3s) goto free_vcpu; + vcpu->arch.book3s = vcpu_book3s; + +#ifdef CONFIG_KVM_BOOK3S_32 + 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; @@ -1076,13 +1199,19 @@ 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; #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; @@ -1096,24 +1225,31 @@ struct kvm_vcpu *kvmppc_core_vcpu_create(struct kvm *kvm, unsigned int id) uninit_vcpu: kvm_vcpu_uninit(vcpu); free_shadow_vcpu: - kfree(vcpu_book3s->shadow_vcpu); -free_vcpu: +#ifdef CONFIG_KVM_BOOK3S_32 + 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); } -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); 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) +static int kvmppc_vcpu_run_pr(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu) { int ret; double fpr[32][TS_FPRWIDTH]; @@ -1222,8 +1358,8 @@ 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; @@ -1258,67 +1394,100 @@ out: return r; } -#ifdef CONFIG_PPC64 -int kvm_vm_ioctl_get_smmu_info(struct kvm *kvm, struct kvm_ppc_smmu_info *info) +static void kvmppc_core_flush_memslot_pr(struct kvm *kvm, + struct kvm_memory_slot *memslot) { - info->flags = KVM_PPC_1T_SEGMENTS; - - /* SLB is always 64 entries */ - info->slb_size = 64; - - /* Standard 4k base page size segment */ - info->sps[0].page_shift = 12; - info->sps[0].slb_enc = 0; - info->sps[0].enc[0].page_shift = 12; - info->sps[0].enc[0].pte_enc = 0; - - /* Standard 16M large page size segment */ - info->sps[1].page_shift = 24; - info->sps[1].slb_enc = SLB_VSID_L; - info->sps[1].enc[0].page_shift = 24; - info->sps[1].enc[0].pte_enc = 0; + return; +} +static int kvmppc_core_prepare_memory_region_pr(struct kvm *kvm, + struct kvm_memory_slot *memslot, + struct kvm_userspace_memory_region *mem) +{ return 0; } -#endif /* CONFIG_PPC64 */ -void kvmppc_core_free_memslot(struct kvm_memory_slot *free, - struct kvm_memory_slot *dont) +static void kvmppc_core_commit_memory_region_pr(struct kvm *kvm, + struct kvm_userspace_memory_region *mem, + const struct kvm_memory_slot *old) { + return; } -int kvmppc_core_create_memslot(struct kvm_memory_slot *slot, - unsigned long npages) +static void kvmppc_core_free_memslot_pr(struct kvm_memory_slot *free, + struct kvm_memory_slot *dont) { - return 0; + return; } -int kvmppc_core_prepare_memory_region(struct kvm *kvm, - struct kvm_memory_slot *memslot, - struct kvm_userspace_memory_region *mem) +static int kvmppc_core_create_memslot_pr(struct kvm_memory_slot *slot, + unsigned long npages) { return 0; } -void kvmppc_core_commit_memory_region(struct kvm *kvm, - struct kvm_userspace_memory_region *mem, - const struct kvm_memory_slot *old) + +#ifdef CONFIG_PPC64 +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; + + info->flags = 0; + + /* SLB is always 64 entries */ + info->slb_size = 64; + + /* Standard 4k base page size segment */ + info->sps[0].page_shift = 12; + info->sps[0].slb_enc = 0; + info->sps[0].enc[0].page_shift = 12; + info->sps[0].enc[0].pte_enc = 0; + + /* + * 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[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; -void kvmppc_core_flush_memslot(struct kvm *kvm, struct kvm_memory_slot *memslot) + return 0; +} +#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)) { spin_lock(&kvm_global_user_count_lock); @@ -1329,7 +1498,7 @@ 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)); @@ -1344,26 +1513,81 @@ void kvmppc_core_destroy_vm(struct kvm *kvm) } } -static int kvmppc_book3s_init(void) +static int kvmppc_core_check_processor_compat_pr(void) { - int r; + /* we are always compatible */ + return 0; +} - r = kvm_init(NULL, sizeof(struct kvmppc_vcpu_book3s), 0, - THIS_MODULE); +static long kvm_arch_vm_ioctl_pr(struct file *filp, + unsigned int ioctl, unsigned long arg) +{ + return -ENOTTY; +} - if (r) +static struct kvmppc_ops kvm_ops_pr = { + .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, + .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, +}; + + +int kvmppc_book3s_init_pr(void) +{ + int 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(void) +void kvmppc_book3s_exit_pr(void) { + kvmppc_pr_ops = NULL; kvmppc_mmu_hpte_sysexit(); - kvm_exit(); } -module_init(kvmppc_book3s_init); -module_exit(kvmppc_book3s_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_pr_papr.c b/arch/powerpc/kvm/book3s_pr_papr.c index da0e0bc268b..5efa97b993d 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 +42,41 @@ 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); + mutex_lock(&vcpu->kvm->arch.hpt_mutex); 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: + mutex_unlock(&vcpu->kvm->arch.hpt_mutex); + kvmppc_set_gpr(vcpu, 3, ret); return EMULATE_DONE; } @@ -77,26 +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; } @@ -124,6 +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); @@ -172,6 +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; @@ -184,15 +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]; @@ -207,8 +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; } diff --git a/arch/powerpc/kvm/book3s_rmhandlers.S b/arch/powerpc/kvm/book3s_rmhandlers.S index 8f7633e3afb..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 @@ -179,11 +153,15 @@ _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/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_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: * diff --git a/arch/powerpc/kvm/book3s_xics.c b/arch/powerpc/kvm/book3s_xics.c index a3a5cb8ee7e..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) + if (xics->real_mode && is_kvmppc_hv_enabled(vcpu->kvm)) return kvmppc_xics_rm_complete(vcpu, req); switch (req) { @@ -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. -- */ @@ -1250,13 +1251,13 @@ 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 17722d82f1d..15d0149511e 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; @@ -133,6 +135,29 @@ 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 +175,7 @@ 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 +681,7 @@ 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 +723,12 @@ 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 +736,10 @@ 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 +795,30 @@ 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 +879,11 @@ static void kvmppc_restart_interrupt(struct kvm_vcpu *vcpu, case BOOKE_INTERRUPT_CRITICAL: unknown_exception(®s); break; + case BOOKE_INTERRUPT_DEBUG: + /* Save DBSR before preemption is enabled */ + vcpu->arch.dbsr = mfspr(SPRN_DBSR); + kvmppc_clear_dbsr(); + break; } } @@ -1135,18 +1201,10 @@ 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 +1255,7 @@ 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 @@ -1359,7 +1417,7 @@ 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; @@ -1379,6 +1437,7 @@ 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) @@ -1413,8 +1472,7 @@ 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 vcpu->kvm->arch.kvm_ops->get_sregs(vcpu, sregs); } int kvm_arch_vcpu_ioctl_set_sregs(struct kvm_vcpu *vcpu, @@ -1433,7 +1491,7 @@ int kvm_arch_vcpu_ioctl_set_sregs(struct kvm_vcpu *vcpu, if (ret < 0) return ret; - return kvmppc_core_set_sregs(vcpu, sregs); + return 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) @@ -1441,7 +1499,6 @@ 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 +1506,24 @@ 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); @@ -1477,10 +1542,13 @@ 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); break; default: - r = kvmppc_get_one_reg(vcpu, reg->id, &val); + r = vcpu->kvm->arch.kvm_ops->get_one_reg(vcpu, reg->id, &val); break; } @@ -1498,7 +1566,6 @@ 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)) @@ -1509,16 +1576,24 @@ 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); @@ -1552,20 +1627,17 @@ 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); + r = vcpu->kvm->arch.kvm_ops->set_one_reg(vcpu, reg->id, &val); break; } 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; @@ -1590,12 +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; @@ -1671,6 +1743,157 @@ 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(); @@ -1681,6 +1904,44 @@ 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(); +} + +void kvmppc_mmu_destroy(struct kvm_vcpu *vcpu) +{ + vcpu->kvm->arch.kvm_ops->mmu_destroy(vcpu); +} + +int kvmppc_core_init_vm(struct kvm *kvm) +{ + return kvm->arch.kvm_ops->init_vm(kvm); +} + +struct kvm_vcpu *kvmppc_core_vcpu_create(struct kvm *kvm, unsigned int id) +{ + return kvm->arch.kvm_ops->vcpu_create(kvm, id); +} + +void kvmppc_core_vcpu_free(struct kvm_vcpu *vcpu) +{ + vcpu->kvm->arch.kvm_ops->vcpu_free(vcpu); +} + +void kvmppc_core_destroy_vm(struct kvm *kvm) +{ + kvm->arch.kvm_ops->destroy_vm(kvm); +} + +void kvmppc_core_vcpu_load(struct kvm_vcpu *vcpu, int cpu) +{ + vcpu->kvm->arch.kvm_ops->vcpu_load(vcpu, cpu); +} + +void kvmppc_core_vcpu_put(struct kvm_vcpu *vcpu) +{ + vcpu->kvm->arch.kvm_ops->vcpu_put(vcpu); } int __init kvmppc_booke_init(void) diff --git a/arch/powerpc/kvm/booke.h b/arch/powerpc/kvm/booke.h index 5fd1ba69357..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 @@ -129,4 +153,9 @@ 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__ */ diff --git a/arch/powerpc/kvm/e500.c b/arch/powerpc/kvm/e500.c index ce6b73c2961..497b142f651 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); @@ -534,11 +555,19 @@ 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(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/e500.h b/arch/powerpc/kvm/e500.h index c2e5e98453a..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_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) diff --git a/arch/powerpc/kvm/e500_emulate.c b/arch/powerpc/kvm/e500_emulate.c index b10a01243ab..89b7f821f6c 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) @@ -82,8 +83,28 @@ static int kvmppc_e500_emul_msgsnd(struct kvm_vcpu *vcpu, int rb) } #endif -int kvmppc_core_emulate_op(struct kvm_run *run, struct kvm_vcpu *vcpu, - unsigned int inst, int *advance) +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_e500(struct kvm_run *run, struct kvm_vcpu *vcpu, + unsigned int inst, int *advance) { int emulated = EMULATE_DONE; int ra = get_ra(inst); @@ -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; } @@ -146,7 +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; @@ -237,7 +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..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" @@ -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/e500_mmu_host.c b/arch/powerpc/kvm/e500_mmu_host.c index c65593abae8..ecf2247b13b 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]; @@ -253,6 +254,9 @@ 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); } diff --git a/arch/powerpc/kvm/e500mc.c b/arch/powerpc/kvm/e500mc.c index 19c8379575f..4132cd2fc17 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; @@ -337,27 +340,52 @@ 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(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 751cd45f65a..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_core_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_core_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_core_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) { @@ -483,3 +484,4 @@ 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 07c0106fab7..9ae97686e9f 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> @@ -39,6 +40,12 @@ #define CREATE_TRACE_POINTS #include "trace.h" +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) { return !!(v->arch.pending_exceptions) || @@ -50,7 +57,6 @@ 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. @@ -125,7 +131,7 @@ int kvmppc_prepare_to_enter(struct kvm_vcpu *vcpu) return r; } -#endif /* CONFIG_KVM_BOOK3S_64_HV */ +EXPORT_SYMBOL_GPL(kvmppc_prepare_to_enter); int kvmppc_kvm_pv(struct kvm_vcpu *vcpu) { @@ -179,6 +185,7 @@ int kvmppc_kvm_pv(struct kvm_vcpu *vcpu) return r; } +EXPORT_SYMBOL_GPL(kvmppc_kvm_pv); int kvmppc_sanity_check(struct kvm_vcpu *vcpu) { @@ -192,11 +199,9 @@ 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 && is_kvmppc_hv_enabled(vcpu->kvm)) goto out; -#endif #ifdef CONFIG_KVM_BOOKE_HV if (!cpu_has_feature(CPU_FTR_EMB_HV)) @@ -209,6 +214,7 @@ 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) { @@ -243,6 +249,7 @@ 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) { @@ -269,10 +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) @@ -292,6 +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) @@ -301,6 +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 @@ -320,22 +359,26 @@ 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 = !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: @@ -346,32 +389,37 @@ 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 (hv_enabled) + r = threads_per_core; + else + r = 0; break; case KVM_CAP_PPC_RMA: - r = 1; + r = 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 (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 = hv_enabled; break; #endif - break; case KVM_CAP_NR_VCPUS: /* * Recommending a number of CPUs is somewhat arbitrary; we @@ -379,11 +427,10 @@ 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 (hv_enabled) + r = num_present_cpus(); + else + r = num_online_cpus(); break; case KVM_CAP_MAX_VCPUS: r = KVM_MAX_VCPUS; @@ -407,15 +454,16 @@ 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) @@ -659,6 +707,7 @@ 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, @@ -720,6 +769,7 @@ 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) { @@ -1024,52 +1074,12 @@ 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; + struct kvm *kvm = filp->private_data; memset(&info, 0, sizeof(info)); - r = kvm_vm_ioctl_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; @@ -1080,11 +1090,15 @@ long kvm_arch_vm_ioctl(struct file *filp, r = kvm_vm_ioctl_rtas_define_token(kvm, argp); break; } -#endif /* CONFIG_PPC_BOOK3S_64 */ + 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; +#endif } - out: return r; } @@ -1106,22 +1120,26 @@ 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) { @@ -1130,4 +1148,5 @@ int kvm_arch_init(void *opaque) void kvm_arch_exit(void) { + } diff --git a/arch/powerpc/kvm/trace.h b/arch/powerpc/kvm/trace.h index e326489a542..2e0e67ef354 100644 --- a/arch/powerpc/kvm/trace.h +++ b/arch/powerpc/kvm/trace.h @@ -31,126 +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 - -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 ) -#ifdef CONFIG_KVM_BOOK3S_PR - __field( unsigned long, srr1 ) -#endif - __field( unsigned long, last_inst ) - ), - - 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); -#endif - __entry->last_inst = vcpu->arch.last_inst; - ), - - TP_printk("exit=%s" - " | pc=0x%lx" - " | msr=0x%lx" - " | dar=0x%lx" -#ifdef CONFIG_KVM_BOOK3S_PR - " | 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 - __entry->srr1, -#endif - __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_stlb_inval, TP_PROTO(unsigned int stlb_index), TP_ARGS(stlb_index), @@ -236,315 +116,6 @@ TRACE_EVENT(kvm_check_requests, __entry->cpu_nr, __entry->requests) ); - -/************************************************************************* - * Book3S trace points * - *************************************************************************/ - -#ifdef CONFIG_KVM_BOOK3S_PR - -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 * - *************************************************************************/ - -#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> 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> 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 6d16fc53024..07c127fc206 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -7091,7 +7091,7 @@ 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; @@ -7112,7 +7112,8 @@ 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 9bb1048d010..9523d2ad753 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/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h index 509cfbfe965..902f1246187 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 /* diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index 82c4047aa0e..7a317a7f902 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) { @@ -541,13 +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; } @@ -558,7 +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); } @@ -822,7 +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; } @@ -883,7 +884,7 @@ 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); /* @@ -905,7 +906,7 @@ 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; } @@ -964,6 +965,7 @@ int kvm_get_dirty_log(struct kvm *kvm, out: return r; } +EXPORT_SYMBOL_GPL(kvm_get_dirty_log); bool kvm_largepages_enabled(void) { @@ -1654,6 +1656,7 @@ 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. @@ -1679,6 +1682,7 @@ void kvm_vcpu_block(struct kvm_vcpu *vcpu) finish_wait(&vcpu->wq, &wait); } +EXPORT_SYMBOL_GPL(kvm_vcpu_block); #ifndef CONFIG_S390 /* |