diff options
Diffstat (limited to 'arch/powerpc/kvm/book3s.c')
| -rw-r--r-- | arch/powerpc/kvm/book3s.c | 1121 |
1 files changed, 546 insertions, 575 deletions
diff --git a/arch/powerpc/kvm/book3s.c b/arch/powerpc/kvm/book3s.c index 3e294bd9b8c..c254c27f240 100644 --- a/arch/powerpc/kvm/book3s.c +++ b/arch/powerpc/kvm/book3s.c @@ -16,6 +16,10 @@ #include <linux/kvm_host.h> #include <linux/err.h> +#include <linux/export.h> +#include <linux/slab.h> +#include <linux/module.h> +#include <linux/miscdevice.h> #include <asm/reg.h> #include <asm/cputable.h> @@ -26,19 +30,18 @@ #include <asm/kvm_ppc.h> #include <asm/kvm_book3s.h> #include <asm/mmu_context.h> +#include <asm/page.h> +#include <linux/gfp.h> #include <linux/sched.h> #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 /* #define EXIT_DEBUG */ -/* #define EXIT_DEBUG_SIMPLE */ - -/* Without AGGRESSIVE_DEC we only fire off a DEC interrupt when DEC turns 0. - * When set, we retrigger a DEC interrupt after that if DEC <= 0. - * PPC32 Linux runs faster without AGGRESSIVE_DEC, PPC64 Linux requires it. */ - -/* #define AGGRESSIVE_DEC */ struct kvm_stats_debugfs_item debugfs_entries[] = { { "exits", VCPU_STAT(sum_exits) }, @@ -69,67 +72,62 @@ void kvmppc_core_load_guest_debugstate(struct kvm_vcpu *vcpu) { } -void kvmppc_core_vcpu_load(struct kvm_vcpu *vcpu, int cpu) +static inline unsigned long kvmppc_interrupt_offset(struct kvm_vcpu *vcpu) { - memcpy(get_paca()->kvm_slb, to_book3s(vcpu)->slb_shadow, sizeof(get_paca()->kvm_slb)); - get_paca()->kvm_slb_max = to_book3s(vcpu)->slb_shadow_max; + if (!is_kvmppc_hv_enabled(vcpu->kvm)) + return to_book3s(vcpu)->hior; + return 0; } -void kvmppc_core_vcpu_put(struct kvm_vcpu *vcpu) +static inline void kvmppc_update_int_pending(struct kvm_vcpu *vcpu, + unsigned long pending_now, unsigned long old_pending) { - memcpy(to_book3s(vcpu)->slb_shadow, get_paca()->kvm_slb, sizeof(get_paca()->kvm_slb)); - to_book3s(vcpu)->slb_shadow_max = get_paca()->kvm_slb_max; + if (is_kvmppc_hv_enabled(vcpu->kvm)) + return; + if (pending_now) + kvmppc_set_int_pending(vcpu, 1); + else if (old_pending) + kvmppc_set_int_pending(vcpu, 0); } -#if defined(AGGRESSIVE_DEC) || defined(EXIT_DEBUG) -static u32 kvmppc_get_dec(struct kvm_vcpu *vcpu) +static inline bool kvmppc_critical_section(struct kvm_vcpu *vcpu) { - u64 jd = mftb() - vcpu->arch.dec_jiffies; - return vcpu->arch.dec - jd; -} -#endif + ulong crit_raw; + ulong crit_r1; + bool crit; -void kvmppc_set_msr(struct kvm_vcpu *vcpu, u64 msr) -{ - ulong old_msr = vcpu->arch.msr; + if (is_kvmppc_hv_enabled(vcpu->kvm)) + return false; -#ifdef EXIT_DEBUG - printk(KERN_INFO "KVM: Set MSR to 0x%llx\n", msr); -#endif - msr &= to_book3s(vcpu)->msr_mask; - vcpu->arch.msr = msr; - vcpu->arch.shadow_msr = msr | MSR_USER32; - vcpu->arch.shadow_msr &= ( MSR_VEC | MSR_VSX | MSR_FP | MSR_FE0 | - MSR_USER64 | MSR_SE | MSR_BE | MSR_DE | - MSR_FE1); - - if (msr & (MSR_WE|MSR_POW)) { - if (!vcpu->arch.pending_exceptions) { - kvm_vcpu_block(vcpu); - vcpu->stat.halt_wakeup++; - } - } + crit_raw = kvmppc_get_critical(vcpu); + crit_r1 = kvmppc_get_gpr(vcpu, 1); - if (((vcpu->arch.msr & (MSR_IR|MSR_DR)) != (old_msr & (MSR_IR|MSR_DR))) || - (vcpu->arch.msr & MSR_PR) != (old_msr & MSR_PR)) { - kvmppc_mmu_flush_segments(vcpu); - kvmppc_mmu_map_segment(vcpu, vcpu->arch.pc); + /* Truncate crit indicators in 32 bit mode */ + if (!(kvmppc_get_msr(vcpu) & 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 && !(kvmppc_get_msr(vcpu) & MSR_PR); + + return crit; } void kvmppc_inject_interrupt(struct kvm_vcpu *vcpu, int vec, u64 flags) { - vcpu->arch.srr0 = vcpu->arch.pc; - vcpu->arch.srr1 = vcpu->arch.msr | flags; - vcpu->arch.pc = to_book3s(vcpu)->hior + vec; + kvmppc_set_srr0(vcpu, kvmppc_get_pc(vcpu)); + kvmppc_set_srr1(vcpu, kvmppc_get_msr(vcpu) | flags); + kvmppc_set_pc(vcpu, kvmppc_interrupt_offset(vcpu) + vec); vcpu->arch.mmu.reset_msr(vcpu); } -void kvmppc_book3s_queue_irqprio(struct kvm_vcpu *vcpu, unsigned int vec) +static int kvmppc_book3s_vec2irqprio(unsigned int vec) { unsigned int prio; - vcpu->stat.queue_intr++; switch (vec) { case 0x100: prio = BOOK3S_IRQPRIO_SYSTEM_RESET; break; case 0x200: prio = BOOK3S_IRQPRIO_MACHINE_CHECK; break; @@ -138,6 +136,7 @@ void kvmppc_book3s_queue_irqprio(struct kvm_vcpu *vcpu, unsigned int vec) case 0x400: prio = BOOK3S_IRQPRIO_INST_STORAGE; break; case 0x480: prio = BOOK3S_IRQPRIO_INST_SEGMENT; break; case 0x500: prio = BOOK3S_IRQPRIO_EXTERNAL; break; + case 0x501: prio = BOOK3S_IRQPRIO_EXTERNAL_LEVEL; break; case 0x600: prio = BOOK3S_IRQPRIO_ALIGNMENT; break; case 0x700: prio = BOOK3S_IRQPRIO_PROGRAM; break; case 0x800: prio = BOOK3S_IRQPRIO_FP_UNAVAIL; break; @@ -146,49 +145,93 @@ void kvmppc_book3s_queue_irqprio(struct kvm_vcpu *vcpu, unsigned int vec) case 0xd00: prio = BOOK3S_IRQPRIO_DEBUG; break; case 0xf20: prio = BOOK3S_IRQPRIO_ALTIVEC; break; case 0xf40: prio = BOOK3S_IRQPRIO_VSX; break; + case 0xf60: prio = BOOK3S_IRQPRIO_FAC_UNAVAIL; break; default: prio = BOOK3S_IRQPRIO_MAX; break; } - set_bit(prio, &vcpu->arch.pending_exceptions); + return prio; +} + +void kvmppc_book3s_dequeue_irqprio(struct kvm_vcpu *vcpu, + unsigned int vec) +{ + unsigned long old_pending = vcpu->arch.pending_exceptions; + + clear_bit(kvmppc_book3s_vec2irqprio(vec), + &vcpu->arch.pending_exceptions); + + kvmppc_update_int_pending(vcpu, vcpu->arch.pending_exceptions, + old_pending); +} + +void kvmppc_book3s_queue_irqprio(struct kvm_vcpu *vcpu, unsigned int vec) +{ + vcpu->stat.queue_intr++; + + set_bit(kvmppc_book3s_vec2irqprio(vec), + &vcpu->arch.pending_exceptions); #ifdef EXIT_DEBUG 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) +void kvmppc_core_queue_program(struct kvm_vcpu *vcpu, ulong flags) { - kvmppc_book3s_queue_irqprio(vcpu, BOOK3S_INTERRUPT_PROGRAM); + /* 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_INTERRUPT_DECREMENTER >> 7, &vcpu->arch.pending_exceptions); + 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) { - kvmppc_book3s_queue_irqprio(vcpu, BOOK3S_INTERRUPT_EXTERNAL); + unsigned int vec = BOOK3S_INTERRUPT_EXTERNAL; + + if (irq->irq == KVM_INTERRUPT_SET_LEVEL) + vec = BOOK3S_INTERRUPT_EXTERNAL_LEVEL; + + kvmppc_book3s_queue_irqprio(vcpu, vec); +} + +void kvmppc_core_dequeue_external(struct kvm_vcpu *vcpu) +{ + kvmppc_book3s_dequeue_irqprio(vcpu, BOOK3S_INTERRUPT_EXTERNAL); + kvmppc_book3s_dequeue_irqprio(vcpu, BOOK3S_INTERRUPT_EXTERNAL_LEVEL); } int kvmppc_book3s_irqprio_deliver(struct kvm_vcpu *vcpu, unsigned int priority) { int deliver = 1; int vec = 0; + bool crit = kvmppc_critical_section(vcpu); switch (priority) { case BOOK3S_IRQPRIO_DECREMENTER: - deliver = vcpu->arch.msr & MSR_EE; + deliver = (kvmppc_get_msr(vcpu) & MSR_EE) && !crit; vec = BOOK3S_INTERRUPT_DECREMENTER; break; case BOOK3S_IRQPRIO_EXTERNAL: - deliver = vcpu->arch.msr & MSR_EE; + case BOOK3S_IRQPRIO_EXTERNAL_LEVEL: + deliver = (kvmppc_get_msr(vcpu) & MSR_EE) && !crit; vec = BOOK3S_INTERRUPT_EXTERNAL; break; case BOOK3S_IRQPRIO_SYSTEM_RESET: @@ -233,6 +276,9 @@ int kvmppc_book3s_irqprio_deliver(struct kvm_vcpu *vcpu, unsigned int priority) case BOOK3S_IRQPRIO_PERFORMANCE_MONITOR: vec = BOOK3S_INTERRUPT_PERFMON; break; + case BOOK3S_IRQPRIO_FAC_UNAVAIL: + vec = BOOK3S_INTERRUPT_FAC_UNAVAIL; + break; default: deliver = 0; printk(KERN_ERR "KVM: Unknown interrupt: 0x%x\n", priority); @@ -244,31 +290,42 @@ int kvmppc_book3s_irqprio_deliver(struct kvm_vcpu *vcpu, unsigned int priority) #endif if (deliver) - kvmppc_inject_interrupt(vcpu, vec, 0ULL); + kvmppc_inject_interrupt(vcpu, vec, 0); return deliver; } -void kvmppc_core_deliver_interrupts(struct kvm_vcpu *vcpu) +/* + * This function determines if an irqprio should be cleared once issued. + */ +static bool clear_irqprio(struct kvm_vcpu *vcpu, unsigned int priority) +{ + switch (priority) { + case BOOK3S_IRQPRIO_DECREMENTER: + /* DEC interrupts get cleared by mtdec */ + return false; + case BOOK3S_IRQPRIO_EXTERNAL_LEVEL: + /* External interrupts get cleared by userspace */ + return false; + } + + return true; +} + +int kvmppc_core_prepare_to_enter(struct kvm_vcpu *vcpu) { unsigned long *pending = &vcpu->arch.pending_exceptions; + unsigned long old_pending = vcpu->arch.pending_exceptions; unsigned int priority; - /* XXX be more clever here - no need to mftb() on every entry */ - /* Issue DEC again if it's still active */ -#ifdef AGGRESSIVE_DEC - if (vcpu->arch.msr & MSR_EE) - if (kvmppc_get_dec(vcpu) & 0x80000000) - kvmppc_core_queue_dec(vcpu); -#endif - #ifdef EXIT_DEBUG if (vcpu->arch.pending_exceptions) printk(KERN_EMERG "KVM: Check pending: %lx\n", vcpu->arch.pending_exceptions); #endif priority = __ffs(*pending); - while (priority <= (sizeof(unsigned int) * 8)) { - if (kvmppc_book3s_irqprio_deliver(vcpu, priority)) { + while (priority < BOOK3S_IRQPRIO_MAX) { + if (kvmppc_book3s_irqprio_deliver(vcpu, priority) && + clear_irqprio(vcpu, priority)) { clear_bit(priority, &vcpu->arch.pending_exceptions); break; } @@ -277,92 +334,52 @@ void kvmppc_core_deliver_interrupts(struct kvm_vcpu *vcpu) BITS_PER_BYTE * sizeof(*pending), priority + 1); } -} -void kvmppc_set_pvr(struct kvm_vcpu *vcpu, u32 pvr) -{ - vcpu->arch.hflags &= ~BOOK3S_HFLAG_SLB; - vcpu->arch.pvr = pvr; - if ((pvr >= 0x330000) && (pvr < 0x70330000)) { - kvmppc_mmu_book3s_64_init(vcpu); - to_book3s(vcpu)->hior = 0xfff00000; - to_book3s(vcpu)->msr_mask = 0xffffffffffffffffULL; - } else { - kvmppc_mmu_book3s_32_init(vcpu); - to_book3s(vcpu)->hior = 0; - to_book3s(vcpu)->msr_mask = 0xffffffffULL; - } - - /* If we are in hypervisor level on 970, we can tell the CPU to - * treat DCBZ as 32 bytes store */ - vcpu->arch.hflags &= ~BOOK3S_HFLAG_DCBZ32; - if (vcpu->arch.mmu.is_dcbz32(vcpu) && (mfmsr() & MSR_HV) && - !strcmp(cur_cpu_spec->platform, "ppc970")) - vcpu->arch.hflags |= BOOK3S_HFLAG_DCBZ32; + /* Tell the guest about our interrupt status */ + kvmppc_update_int_pending(vcpu, *pending, old_pending); + return 0; } +EXPORT_SYMBOL_GPL(kvmppc_core_prepare_to_enter); -/* Book3s_32 CPUs always have 32 bytes cache line size, which Linux assumes. To - * make Book3s_32 Linux work on Book3s_64, we have to make sure we trap dcbz to - * emulate 32 bytes dcbz length. - * - * The Book3s_64 inventors also realized this case and implemented a special bit - * in the HID5 register, which is a hypervisor ressource. Thus we can't use it. - * - * My approach here is to patch the dcbz instruction on executing pages. - */ -static void kvmppc_patch_dcbz(struct kvm_vcpu *vcpu, struct kvmppc_pte *pte) +pfn_t kvmppc_gfn_to_pfn(struct kvm_vcpu *vcpu, gfn_t gfn, bool writing, + bool *writable) { - bool touched = false; - hva_t hpage; - u32 *page; - int i; - - hpage = gfn_to_hva(vcpu->kvm, pte->raddr >> PAGE_SHIFT); - if (kvm_is_error_hva(hpage)) - return; - - hpage |= pte->raddr & ~PAGE_MASK; - hpage &= ~0xFFFULL; + ulong mp_pa = vcpu->arch.magic_page_pa; - page = vmalloc(HW_PAGE_SIZE); + if (!(kvmppc_get_msr(vcpu) & MSR_SF)) + mp_pa = (uint32_t)mp_pa; - if (copy_from_user(page, (void __user *)hpage, HW_PAGE_SIZE)) - goto out; - - for (i=0; i < HW_PAGE_SIZE / 4; i++) - if ((page[i] & 0xff0007ff) == INS_DCBZ) { - page[i] &= 0xfffffff7; // reserved instruction, so we trap - touched = true; - } + /* Magic page override */ + if (unlikely(mp_pa) && + unlikely(((gfn << PAGE_SHIFT) & KVM_PAM) == + ((mp_pa & PAGE_MASK) & KVM_PAM))) { + ulong shared_page = ((ulong)vcpu->arch.shared) & PAGE_MASK; + pfn_t pfn; - if (touched) - copy_to_user((void __user *)hpage, page, HW_PAGE_SIZE); + pfn = (pfn_t)virt_to_phys((void*)shared_page) >> PAGE_SHIFT; + get_page(pfn_to_page(pfn)); + if (writable) + *writable = true; + return pfn; + } -out: - vfree(page); + 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.msr & (data ? MSR_DR : MSR_IR)); + int relocated = (kvmppc_get_msr(vcpu) & (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 & 0xffffffff; - pte->vpage = eaddr >> 12; - switch (vcpu->arch.msr & (MSR_DR|MSR_IR)) { - case 0: - pte->vpage |= VSID_REAL; - case MSR_DR: - pte->vpage |= VSID_REAL_DR; - case MSR_IR: - pte->vpage |= VSID_REAL_IR; - } + pte->raddr = eaddr & KVM_PAM; + pte->vpage = VSID_REAL | eaddr >> 12; pte->may_read = true; pte->may_write = true; pte->may_execute = true; @@ -397,339 +414,109 @@ err: return kvmppc_bad_hva(); } -int kvmppc_st(struct kvm_vcpu *vcpu, ulong eaddr, int size, void *ptr) +int kvmppc_st(struct kvm_vcpu *vcpu, ulong *eaddr, int size, void *ptr, + bool data) { struct kvmppc_pte pte; - hva_t hva = eaddr; vcpu->stat.st++; - if (kvmppc_xlate(vcpu, eaddr, false, &pte)) - goto err; + if (kvmppc_xlate(vcpu, *eaddr, data, true, &pte)) + return -ENOENT; - hva = kvmppc_pte_to_hva(vcpu, &pte, false); - if (kvm_is_error_hva(hva)) - goto err; + *eaddr = pte.raddr; - if (copy_to_user((void __user *)hva, ptr, size)) { - printk(KERN_INFO "kvmppc_st at 0x%lx failed\n", hva); - goto err; - } + if (!pte.may_write) + return -EPERM; - return 0; + if (kvm_write_guest(vcpu->kvm, pte.raddr, ptr, size)) + return EMULATE_DO_MMIO; -err: - return -ENOENT; + return EMULATE_DONE; } +EXPORT_SYMBOL_GPL(kvmppc_st); -int kvmppc_ld(struct kvm_vcpu *vcpu, ulong eaddr, int size, void *ptr, +int kvmppc_ld(struct kvm_vcpu *vcpu, ulong *eaddr, int size, void *ptr, bool data) { struct kvmppc_pte pte; - hva_t hva = eaddr; + hva_t hva = *eaddr; vcpu->stat.ld++; - if (kvmppc_xlate(vcpu, eaddr, data, &pte)) - goto err; + if (kvmppc_xlate(vcpu, *eaddr, data, false, &pte)) + goto nopte; + + *eaddr = pte.raddr; hva = kvmppc_pte_to_hva(vcpu, &pte, true); if (kvm_is_error_hva(hva)) - goto err; + goto mmio; if (copy_from_user(ptr, (void __user *)hva, size)) { printk(KERN_INFO "kvmppc_ld at 0x%lx failed\n", hva); - goto err; + goto mmio; } - return 0; + return EMULATE_DONE; -err: +nopte: return -ENOENT; +mmio: + return EMULATE_DO_MMIO; } +EXPORT_SYMBOL_GPL(kvmppc_ld); -static int kvmppc_visible_gfn(struct kvm_vcpu *vcpu, gfn_t gfn) +int kvm_arch_vcpu_setup(struct kvm_vcpu *vcpu) { - return kvm_is_visible_gfn(vcpu->kvm, gfn); + return 0; } -int kvmppc_handle_pagefault(struct kvm_run *run, struct kvm_vcpu *vcpu, - ulong eaddr, int vec) +int kvmppc_subarch_vcpu_init(struct kvm_vcpu *vcpu) { - bool data = (vec == BOOK3S_INTERRUPT_DATA_STORAGE); - int r = RESUME_GUEST; - int relocated; - int page_found = 0; - struct kvmppc_pte pte; - bool is_mmio = false; - - if ( vec == BOOK3S_INTERRUPT_DATA_STORAGE ) { - relocated = (vcpu->arch.msr & MSR_DR); - } else { - relocated = (vcpu->arch.msr & MSR_IR); - } - - /* Resolve real address if translation turned on */ - if (relocated) { - page_found = vcpu->arch.mmu.xlate(vcpu, eaddr, &pte, data); - } else { - pte.may_execute = true; - pte.may_read = true; - pte.may_write = true; - pte.raddr = eaddr & 0xffffffff; - pte.eaddr = eaddr; - pte.vpage = eaddr >> 12; - switch (vcpu->arch.msr & (MSR_DR|MSR_IR)) { - case 0: - pte.vpage |= VSID_REAL; - case MSR_DR: - pte.vpage |= VSID_REAL_DR; - case MSR_IR: - pte.vpage |= VSID_REAL_IR; - } - } - - if (vcpu->arch.mmu.is_dcbz32(vcpu) && - (!(vcpu->arch.hflags & BOOK3S_HFLAG_DCBZ32))) { - /* - * If we do the dcbz hack, we have to NX on every execution, - * so we can patch the executing code. This renders our guest - * NX-less. - */ - pte.may_execute = !data; - } - - if (page_found == -ENOENT) { - /* Page not found in guest PTE entries */ - vcpu->arch.dear = vcpu->arch.fault_dear; - to_book3s(vcpu)->dsisr = vcpu->arch.fault_dsisr; - vcpu->arch.msr |= (vcpu->arch.shadow_msr & 0x00000000f8000000ULL); - kvmppc_book3s_queue_irqprio(vcpu, vec); - } else if (page_found == -EPERM) { - /* Storage protection */ - vcpu->arch.dear = vcpu->arch.fault_dear; - to_book3s(vcpu)->dsisr = vcpu->arch.fault_dsisr & ~DSISR_NOHPTE; - to_book3s(vcpu)->dsisr |= DSISR_PROTFAULT; - vcpu->arch.msr |= (vcpu->arch.shadow_msr & 0x00000000f8000000ULL); - kvmppc_book3s_queue_irqprio(vcpu, vec); - } else if (page_found == -EINVAL) { - /* Page not found in guest SLB */ - vcpu->arch.dear = vcpu->arch.fault_dear; - kvmppc_book3s_queue_irqprio(vcpu, vec + 0x80); - } else if (!is_mmio && - kvmppc_visible_gfn(vcpu, pte.raddr >> PAGE_SHIFT)) { - /* The guest's PTE is not mapped yet. Map on the host */ - kvmppc_mmu_map_page(vcpu, &pte); - if (data) - vcpu->stat.sp_storage++; - else if (vcpu->arch.mmu.is_dcbz32(vcpu) && - (!(vcpu->arch.hflags & BOOK3S_HFLAG_DCBZ32))) - kvmppc_patch_dcbz(vcpu, &pte); - } else { - /* MMIO */ - vcpu->stat.mmio_exits++; - vcpu->arch.paddr_accessed = pte.raddr; - r = kvmppc_emulate_mmio(run, vcpu); - if ( r == RESUME_HOST_NV ) - r = RESUME_HOST; - if ( r == RESUME_GUEST_NV ) - r = RESUME_GUEST; - } - - return r; + return 0; } -int kvmppc_handle_exit(struct kvm_run *run, struct kvm_vcpu *vcpu, - unsigned int exit_nr) +void kvmppc_subarch_vcpu_uninit(struct kvm_vcpu *vcpu) { - int r = RESUME_HOST; - - vcpu->stat.sum_exits++; - - run->exit_reason = KVM_EXIT_UNKNOWN; - run->ready_for_interrupt_injection = 1; -#ifdef EXIT_DEBUG - printk(KERN_EMERG "exit_nr=0x%x | pc=0x%lx | dar=0x%lx | dec=0x%x | msr=0x%lx\n", - exit_nr, vcpu->arch.pc, vcpu->arch.fault_dear, - kvmppc_get_dec(vcpu), vcpu->arch.msr); -#elif defined (EXIT_DEBUG_SIMPLE) - if ((exit_nr != 0x900) && (exit_nr != 0x500)) - printk(KERN_EMERG "exit_nr=0x%x | pc=0x%lx | dar=0x%lx | msr=0x%lx\n", - exit_nr, vcpu->arch.pc, vcpu->arch.fault_dear, - vcpu->arch.msr); -#endif - kvm_resched(vcpu); - switch (exit_nr) { - case BOOK3S_INTERRUPT_INST_STORAGE: - vcpu->stat.pf_instruc++; - /* only care about PTEG not found errors, but leave NX alone */ - if (vcpu->arch.shadow_msr & 0x40000000) { - r = kvmppc_handle_pagefault(run, vcpu, vcpu->arch.pc, exit_nr); - vcpu->stat.sp_instruc++; - } else if (vcpu->arch.mmu.is_dcbz32(vcpu) && - (!(vcpu->arch.hflags & BOOK3S_HFLAG_DCBZ32))) { - /* - * XXX If we do the dcbz hack we use the NX bit to flush&patch the page, - * so we can't use the NX bit inside the guest. Let's cross our fingers, - * that no guest that needs the dcbz hack does NX. - */ - kvmppc_mmu_pte_flush(vcpu, vcpu->arch.pc, ~0xFFFULL); - } else { - vcpu->arch.msr |= (vcpu->arch.shadow_msr & 0x58000000); - kvmppc_book3s_queue_irqprio(vcpu, exit_nr); - kvmppc_mmu_pte_flush(vcpu, vcpu->arch.pc, ~0xFFFULL); - r = RESUME_GUEST; - } - break; - case BOOK3S_INTERRUPT_DATA_STORAGE: - vcpu->stat.pf_storage++; - /* The only case we need to handle is missing shadow PTEs */ - if (vcpu->arch.fault_dsisr & DSISR_NOHPTE) { - r = kvmppc_handle_pagefault(run, vcpu, vcpu->arch.fault_dear, exit_nr); - } else { - vcpu->arch.dear = vcpu->arch.fault_dear; - to_book3s(vcpu)->dsisr = vcpu->arch.fault_dsisr; - kvmppc_book3s_queue_irqprio(vcpu, exit_nr); - kvmppc_mmu_pte_flush(vcpu, vcpu->arch.dear, ~0xFFFULL); - r = RESUME_GUEST; - } - break; - case BOOK3S_INTERRUPT_DATA_SEGMENT: - if (kvmppc_mmu_map_segment(vcpu, vcpu->arch.fault_dear) < 0) { - vcpu->arch.dear = vcpu->arch.fault_dear; - kvmppc_book3s_queue_irqprio(vcpu, - BOOK3S_INTERRUPT_DATA_SEGMENT); - } - r = RESUME_GUEST; - break; - case BOOK3S_INTERRUPT_INST_SEGMENT: - if (kvmppc_mmu_map_segment(vcpu, vcpu->arch.pc) < 0) { - kvmppc_book3s_queue_irqprio(vcpu, - BOOK3S_INTERRUPT_INST_SEGMENT); - } - r = RESUME_GUEST; - break; - /* We're good on these - the host merely wanted to get our attention */ - case BOOK3S_INTERRUPT_DECREMENTER: - vcpu->stat.dec_exits++; - r = RESUME_GUEST; - break; - case BOOK3S_INTERRUPT_EXTERNAL: - vcpu->stat.ext_intr_exits++; - r = RESUME_GUEST; - break; - case BOOK3S_INTERRUPT_PROGRAM: - { - enum emulation_result er; - - if (vcpu->arch.msr & MSR_PR) { -#ifdef EXIT_DEBUG - printk(KERN_INFO "Userspace triggered 0x700 exception at 0x%lx (0x%x)\n", vcpu->arch.pc, vcpu->arch.last_inst); -#endif - if ((vcpu->arch.last_inst & 0xff0007ff) != - (INS_DCBZ & 0xfffffff7)) { - kvmppc_book3s_queue_irqprio(vcpu, exit_nr); - r = RESUME_GUEST; - break; - } - } - - vcpu->stat.emulated_inst_exits++; - er = kvmppc_emulate_instruction(run, vcpu); - switch (er) { - case EMULATE_DONE: - r = RESUME_GUEST; - break; - case EMULATE_FAIL: - printk(KERN_CRIT "%s: emulation at %lx failed (%08x)\n", - __func__, vcpu->arch.pc, vcpu->arch.last_inst); - kvmppc_book3s_queue_irqprio(vcpu, exit_nr); - r = RESUME_GUEST; - break; - default: - BUG(); - } - break; - } - case BOOK3S_INTERRUPT_SYSCALL: -#ifdef EXIT_DEBUG - printk(KERN_INFO "Syscall Nr %d\n", (int)vcpu->arch.gpr[0]); -#endif - vcpu->stat.syscall_exits++; - kvmppc_book3s_queue_irqprio(vcpu, exit_nr); - r = RESUME_GUEST; - break; - case BOOK3S_INTERRUPT_MACHINE_CHECK: - case BOOK3S_INTERRUPT_FP_UNAVAIL: - case BOOK3S_INTERRUPT_TRACE: - case BOOK3S_INTERRUPT_ALTIVEC: - case BOOK3S_INTERRUPT_VSX: - kvmppc_book3s_queue_irqprio(vcpu, exit_nr); - r = RESUME_GUEST; - break; - default: - /* Ugh - bork here! What did we get? */ - printk(KERN_EMERG "exit_nr=0x%x | pc=0x%lx | msr=0x%lx\n", exit_nr, vcpu->arch.pc, vcpu->arch.shadow_msr); - r = RESUME_HOST; - BUG(); - break; - } - - - if (!(r & RESUME_HOST)) { - /* To avoid clobbering exit_reason, only check for signals if - * we aren't already exiting to userspace for some other - * reason. */ - if (signal_pending(current)) { -#ifdef EXIT_DEBUG - printk(KERN_EMERG "KVM: Going back to host\n"); -#endif - vcpu->stat.signal_exits++; - run->exit_reason = KVM_EXIT_INTR; - r = -EINTR; - } else { - /* In case an interrupt came in that was triggered - * from userspace (like DEC), we need to check what - * to inject now! */ - kvmppc_core_deliver_interrupts(vcpu); - } - } - -#ifdef EXIT_DEBUG - printk(KERN_EMERG "KVM exit: vcpu=0x%p pc=0x%lx r=0x%x\n", vcpu, vcpu->arch.pc, r); -#endif +} - return r; +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_setup(struct kvm_vcpu *vcpu) +int kvm_arch_vcpu_ioctl_set_sregs(struct kvm_vcpu *vcpu, + struct kvm_sregs *sregs) { - return 0; + 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; - regs->pc = vcpu->arch.pc; - regs->cr = vcpu->arch.cr; - regs->ctr = vcpu->arch.ctr; - regs->lr = vcpu->arch.lr; - regs->xer = vcpu->arch.xer; - regs->msr = vcpu->arch.msr; - regs->srr0 = vcpu->arch.srr0; - regs->srr1 = vcpu->arch.srr1; + regs->pc = kvmppc_get_pc(vcpu); + regs->cr = kvmppc_get_cr(vcpu); + regs->ctr = kvmppc_get_ctr(vcpu); + regs->lr = kvmppc_get_lr(vcpu); + regs->xer = kvmppc_get_xer(vcpu); + regs->msr = kvmppc_get_msr(vcpu); + regs->srr0 = kvmppc_get_srr0(vcpu); + regs->srr1 = kvmppc_get_srr1(vcpu); regs->pid = vcpu->arch.pid; - regs->sprg0 = vcpu->arch.sprg0; - regs->sprg1 = vcpu->arch.sprg1; - regs->sprg2 = vcpu->arch.sprg2; - regs->sprg3 = vcpu->arch.sprg3; - regs->sprg5 = vcpu->arch.sprg4; - regs->sprg6 = vcpu->arch.sprg5; - regs->sprg7 = vcpu->arch.sprg6; + regs->sprg0 = kvmppc_get_sprg0(vcpu); + regs->sprg1 = kvmppc_get_sprg1(vcpu); + regs->sprg2 = kvmppc_get_sprg2(vcpu); + regs->sprg3 = kvmppc_get_sprg3(vcpu); + regs->sprg4 = kvmppc_get_sprg4(vcpu); + regs->sprg5 = kvmppc_get_sprg5(vcpu); + regs->sprg6 = kvmppc_get_sprg6(vcpu); + regs->sprg7 = kvmppc_get_sprg7(vcpu); for (i = 0; i < ARRAY_SIZE(regs->gpr); i++) - regs->gpr[i] = vcpu->arch.gpr[i]; + regs->gpr[i] = kvmppc_get_gpr(vcpu, i); return 0; } @@ -738,98 +525,259 @@ int kvm_arch_vcpu_ioctl_set_regs(struct kvm_vcpu *vcpu, struct kvm_regs *regs) { int i; - vcpu->arch.pc = regs->pc; - vcpu->arch.cr = regs->cr; - vcpu->arch.ctr = regs->ctr; - vcpu->arch.lr = regs->lr; - vcpu->arch.xer = regs->xer; + kvmppc_set_pc(vcpu, regs->pc); + kvmppc_set_cr(vcpu, regs->cr); + kvmppc_set_ctr(vcpu, regs->ctr); + kvmppc_set_lr(vcpu, regs->lr); + kvmppc_set_xer(vcpu, regs->xer); kvmppc_set_msr(vcpu, regs->msr); - vcpu->arch.srr0 = regs->srr0; - vcpu->arch.srr1 = regs->srr1; - vcpu->arch.sprg0 = regs->sprg0; - vcpu->arch.sprg1 = regs->sprg1; - vcpu->arch.sprg2 = regs->sprg2; - vcpu->arch.sprg3 = regs->sprg3; - vcpu->arch.sprg5 = regs->sprg4; - vcpu->arch.sprg6 = regs->sprg5; - vcpu->arch.sprg7 = regs->sprg6; - - for (i = 0; i < ARRAY_SIZE(vcpu->arch.gpr); i++) - vcpu->arch.gpr[i] = regs->gpr[i]; + kvmppc_set_srr0(vcpu, regs->srr0); + kvmppc_set_srr1(vcpu, regs->srr1); + kvmppc_set_sprg0(vcpu, regs->sprg0); + kvmppc_set_sprg1(vcpu, regs->sprg1); + kvmppc_set_sprg2(vcpu, regs->sprg2); + kvmppc_set_sprg3(vcpu, regs->sprg3); + kvmppc_set_sprg4(vcpu, regs->sprg4); + kvmppc_set_sprg5(vcpu, regs->sprg5); + kvmppc_set_sprg6(vcpu, regs->sprg6); + kvmppc_set_sprg7(vcpu, regs->sprg7); + + for (i = 0; i < ARRAY_SIZE(regs->gpr); i++) + kvmppc_set_gpr(vcpu, i, regs->gpr[i]); return 0; } -int kvm_arch_vcpu_ioctl_get_sregs(struct kvm_vcpu *vcpu, - struct kvm_sregs *sregs) +int kvm_arch_vcpu_ioctl_get_fpu(struct kvm_vcpu *vcpu, struct kvm_fpu *fpu) { - struct kvmppc_vcpu_book3s *vcpu3s = to_book3s(vcpu); - int i; + return -ENOTSUPP; +} + +int kvm_arch_vcpu_ioctl_set_fpu(struct kvm_vcpu *vcpu, struct kvm_fpu *fpu) +{ + return -ENOTSUPP; +} - sregs->pvr = vcpu->arch.pvr; +int kvm_vcpu_ioctl_get_one_reg(struct kvm_vcpu *vcpu, struct kvm_one_reg *reg) +{ + int r; + union kvmppc_one_reg val; + int size; + long int i; - sregs->u.s.sdr1 = to_book3s(vcpu)->sdr1; - if (vcpu->arch.hflags & BOOK3S_HFLAG_SLB) { - for (i = 0; i < 64; i++) { - sregs->u.s.ppc64.slb[i].slbe = vcpu3s->slb[i].orige | i; - sregs->u.s.ppc64.slb[i].slbv = vcpu3s->slb[i].origv; - } - } else { - for (i = 0; i < 16; i++) { - sregs->u.s.ppc32.sr[i] = vcpu3s->sr[i].raw; - sregs->u.s.ppc32.sr[i] = vcpu3s->sr[i].raw; + size = one_reg_size(reg->id); + if (size > sizeof(val)) + return -EINVAL; + + r = vcpu->kvm->arch.kvm_ops->get_one_reg(vcpu, reg->id, &val); + if (r == -EINVAL) { + r = 0; + switch (reg->id) { + case KVM_REG_PPC_DAR: + val = get_reg_val(reg->id, kvmppc_get_dar(vcpu)); + break; + case KVM_REG_PPC_DSISR: + val = get_reg_val(reg->id, kvmppc_get_dsisr(vcpu)); + break; + case KVM_REG_PPC_FPR0 ... KVM_REG_PPC_FPR31: + i = reg->id - KVM_REG_PPC_FPR0; + val = get_reg_val(reg->id, VCPU_FPR(vcpu, i)); + break; + case KVM_REG_PPC_FPSCR: + val = get_reg_val(reg->id, vcpu->arch.fp.fpscr); + break; +#ifdef CONFIG_ALTIVEC + case KVM_REG_PPC_VR0 ... KVM_REG_PPC_VR31: + if (!cpu_has_feature(CPU_FTR_ALTIVEC)) { + r = -ENXIO; + break; + } + val.vval = vcpu->arch.vr.vr[reg->id - KVM_REG_PPC_VR0]; + break; + case KVM_REG_PPC_VSCR: + if (!cpu_has_feature(CPU_FTR_ALTIVEC)) { + r = -ENXIO; + break; + } + val = get_reg_val(reg->id, vcpu->arch.vr.vscr.u[3]); + break; + case KVM_REG_PPC_VRSAVE: + val = get_reg_val(reg->id, vcpu->arch.vrsave); + break; +#endif /* CONFIG_ALTIVEC */ +#ifdef CONFIG_VSX + case KVM_REG_PPC_VSR0 ... KVM_REG_PPC_VSR31: + if (cpu_has_feature(CPU_FTR_VSX)) { + long int i = reg->id - KVM_REG_PPC_VSR0; + val.vsxval[0] = vcpu->arch.fp.fpr[i][0]; + val.vsxval[1] = vcpu->arch.fp.fpr[i][1]; + } else { + r = -ENXIO; + } + break; +#endif /* CONFIG_VSX */ + case KVM_REG_PPC_DEBUG_INST: { + u32 opcode = INS_TW; + r = copy_to_user((u32 __user *)(long)reg->addr, + &opcode, sizeof(u32)); + break; } - for (i = 0; i < 8; i++) { - sregs->u.s.ppc32.ibat[i] = vcpu3s->ibat[i].raw; - sregs->u.s.ppc32.dbat[i] = vcpu3s->dbat[i].raw; +#ifdef CONFIG_KVM_XICS + case KVM_REG_PPC_ICP_STATE: + if (!vcpu->arch.icp) { + r = -ENXIO; + break; + } + val = get_reg_val(reg->id, kvmppc_xics_get_icp(vcpu)); + break; +#endif /* CONFIG_KVM_XICS */ + case KVM_REG_PPC_FSCR: + val = get_reg_val(reg->id, vcpu->arch.fscr); + break; + case KVM_REG_PPC_TAR: + val = get_reg_val(reg->id, vcpu->arch.tar); + break; + case KVM_REG_PPC_EBBHR: + val = get_reg_val(reg->id, vcpu->arch.ebbhr); + break; + case KVM_REG_PPC_EBBRR: + val = get_reg_val(reg->id, vcpu->arch.ebbrr); + break; + case KVM_REG_PPC_BESCR: + val = get_reg_val(reg->id, vcpu->arch.bescr); + break; + default: + r = -EINVAL; + break; } } - return 0; + if (r) + return r; + + if (copy_to_user((char __user *)(unsigned long)reg->addr, &val, size)) + r = -EFAULT; + + return r; } -int kvm_arch_vcpu_ioctl_set_sregs(struct kvm_vcpu *vcpu, - struct kvm_sregs *sregs) +int kvm_vcpu_ioctl_set_one_reg(struct kvm_vcpu *vcpu, struct kvm_one_reg *reg) { - struct kvmppc_vcpu_book3s *vcpu3s = to_book3s(vcpu); - int i; + int r; + union kvmppc_one_reg val; + int size; + long int i; - kvmppc_set_pvr(vcpu, sregs->pvr); + size = one_reg_size(reg->id); + if (size > sizeof(val)) + return -EINVAL; - vcpu3s->sdr1 = sregs->u.s.sdr1; - if (vcpu->arch.hflags & BOOK3S_HFLAG_SLB) { - for (i = 0; i < 64; i++) { - vcpu->arch.mmu.slbmte(vcpu, sregs->u.s.ppc64.slb[i].slbv, - sregs->u.s.ppc64.slb[i].slbe); - } - } else { - for (i = 0; i < 16; i++) { - vcpu->arch.mmu.mtsrin(vcpu, i, sregs->u.s.ppc32.sr[i]); - } - for (i = 0; i < 8; i++) { - kvmppc_set_bat(vcpu, &(vcpu3s->ibat[i]), false, - (u32)sregs->u.s.ppc32.ibat[i]); - kvmppc_set_bat(vcpu, &(vcpu3s->ibat[i]), true, - (u32)(sregs->u.s.ppc32.ibat[i] >> 32)); - kvmppc_set_bat(vcpu, &(vcpu3s->dbat[i]), false, - (u32)sregs->u.s.ppc32.dbat[i]); - kvmppc_set_bat(vcpu, &(vcpu3s->dbat[i]), true, - (u32)(sregs->u.s.ppc32.dbat[i] >> 32)); + if (copy_from_user(&val, (char __user *)(unsigned long)reg->addr, size)) + return -EFAULT; + + r = vcpu->kvm->arch.kvm_ops->set_one_reg(vcpu, reg->id, &val); + if (r == -EINVAL) { + r = 0; + switch (reg->id) { + case KVM_REG_PPC_DAR: + kvmppc_set_dar(vcpu, set_reg_val(reg->id, val)); + break; + case KVM_REG_PPC_DSISR: + kvmppc_set_dsisr(vcpu, set_reg_val(reg->id, val)); + break; + case KVM_REG_PPC_FPR0 ... KVM_REG_PPC_FPR31: + i = reg->id - KVM_REG_PPC_FPR0; + VCPU_FPR(vcpu, i) = set_reg_val(reg->id, val); + break; + case KVM_REG_PPC_FPSCR: + vcpu->arch.fp.fpscr = set_reg_val(reg->id, val); + break; +#ifdef CONFIG_ALTIVEC + case KVM_REG_PPC_VR0 ... KVM_REG_PPC_VR31: + if (!cpu_has_feature(CPU_FTR_ALTIVEC)) { + r = -ENXIO; + break; + } + vcpu->arch.vr.vr[reg->id - KVM_REG_PPC_VR0] = val.vval; + break; + case KVM_REG_PPC_VSCR: + if (!cpu_has_feature(CPU_FTR_ALTIVEC)) { + r = -ENXIO; + break; + } + vcpu->arch.vr.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_VSX + case KVM_REG_PPC_VSR0 ... KVM_REG_PPC_VSR31: + if (cpu_has_feature(CPU_FTR_VSX)) { + long int i = reg->id - KVM_REG_PPC_VSR0; + vcpu->arch.fp.fpr[i][0] = val.vsxval[0]; + vcpu->arch.fp.fpr[i][1] = val.vsxval[1]; + } else { + r = -ENXIO; + } + break; +#endif /* CONFIG_VSX */ +#ifdef CONFIG_KVM_XICS + case KVM_REG_PPC_ICP_STATE: + if (!vcpu->arch.icp) { + r = -ENXIO; + break; + } + r = kvmppc_xics_set_icp(vcpu, + set_reg_val(reg->id, val)); + break; +#endif /* CONFIG_KVM_XICS */ + case KVM_REG_PPC_FSCR: + vcpu->arch.fscr = set_reg_val(reg->id, val); + break; + case KVM_REG_PPC_TAR: + vcpu->arch.tar = set_reg_val(reg->id, val); + break; + case KVM_REG_PPC_EBBHR: + vcpu->arch.ebbhr = set_reg_val(reg->id, val); + break; + case KVM_REG_PPC_EBBRR: + vcpu->arch.ebbrr = set_reg_val(reg->id, val); + break; + case KVM_REG_PPC_BESCR: + vcpu->arch.bescr = set_reg_val(reg->id, val); + break; + default: + r = -EINVAL; + break; } } - /* Flush the MMU after messing with the segments */ - kvmppc_mmu_pte_flush(vcpu, 0, 0); - return 0; + return r; } -int kvm_arch_vcpu_ioctl_get_fpu(struct kvm_vcpu *vcpu, struct kvm_fpu *fpu) +void kvmppc_core_vcpu_load(struct kvm_vcpu *vcpu, int cpu) { - return -ENOTSUPP; + vcpu->kvm->arch.kvm_ops->vcpu_load(vcpu, cpu); } -int kvm_arch_vcpu_ioctl_set_fpu(struct kvm_vcpu *vcpu, struct kvm_fpu *fpu) +void kvmppc_core_vcpu_put(struct kvm_vcpu *vcpu) { - return -ENOTSUPP; + 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, @@ -838,137 +786,160 @@ int kvm_arch_vcpu_ioctl_translate(struct kvm_vcpu *vcpu, return 0; } -/* - * 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) +int kvm_arch_vcpu_ioctl_set_guest_debug(struct kvm_vcpu *vcpu, + struct kvm_guest_debug *dbg) { - struct kvm_memory_slot *memslot; - struct kvm_vcpu *vcpu; - ulong ga, ga_end; - int is_dirty = 0; - int r, n; - - down_write(&kvm->slots_lock); - - r = kvm_get_dirty_log(kvm, log, &is_dirty); - if (r) - goto out; - - /* If nothing is dirty, don't bother messing with page tables. */ - if (is_dirty) { - memslot = &kvm->memslots[log->slot]; + return -EINVAL; +} - ga = memslot->base_gfn << PAGE_SHIFT; - ga_end = ga + (memslot->npages << PAGE_SHIFT); +void kvmppc_decrementer_func(unsigned long data) +{ + struct kvm_vcpu *vcpu = (struct kvm_vcpu *)data; - kvm_for_each_vcpu(n, vcpu, kvm) - kvmppc_mmu_pte_pflush(vcpu, ga, ga_end); + kvmppc_core_queue_dec(vcpu); + kvm_vcpu_kick(vcpu); +} - n = ALIGN(memslot->npages, BITS_PER_LONG) / 8; - memset(memslot->dirty_bitmap, 0, n); - } +struct kvm_vcpu *kvmppc_core_vcpu_create(struct kvm *kvm, unsigned int id) +{ + return kvm->arch.kvm_ops->vcpu_create(kvm, id); +} - r = 0; -out: - up_write(&kvm->slots_lock); - return r; +void kvmppc_core_vcpu_free(struct kvm_vcpu *vcpu) +{ + vcpu->kvm->arch.kvm_ops->vcpu_free(vcpu); } -int kvmppc_core_check_processor_compat(void) +int kvmppc_core_check_requests(struct kvm_vcpu *vcpu) { - return 0; + return vcpu->kvm->arch.kvm_ops->check_requests(vcpu); } -struct kvm_vcpu *kvmppc_core_vcpu_create(struct kvm *kvm, unsigned int id) +int kvm_vm_ioctl_get_dirty_log(struct kvm *kvm, struct kvm_dirty_log *log) { - struct kvmppc_vcpu_book3s *vcpu_book3s; - struct kvm_vcpu *vcpu; - int err; + return kvm->arch.kvm_ops->get_dirty_log(kvm, log); +} - vcpu_book3s = (struct kvmppc_vcpu_book3s *)__get_free_pages( GFP_KERNEL | __GFP_ZERO, - get_order(sizeof(struct kvmppc_vcpu_book3s))); - if (!vcpu_book3s) { - err = -ENOMEM; - goto out; - } +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); +} - vcpu = &vcpu_book3s->vcpu; - err = kvm_vcpu_init(vcpu, kvm, id); - if (err) - goto free_vcpu; +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); +} - vcpu->arch.host_retip = kvm_return_point; - vcpu->arch.host_msr = mfmsr(); - /* default to book3s_64 (970fx) */ - vcpu->arch.pvr = 0x3C0301; - kvmppc_set_pvr(vcpu, vcpu->arch.pvr); - vcpu_book3s->slb_nr = 64; +void kvmppc_core_flush_memslot(struct kvm *kvm, struct kvm_memory_slot *memslot) +{ + kvm->arch.kvm_ops->flush_memslot(kvm, memslot); +} - /* remember where some real-mode handlers are */ - vcpu->arch.trampoline_lowmem = kvmppc_trampoline_lowmem; - vcpu->arch.trampoline_enter = kvmppc_trampoline_enter; - vcpu->arch.highmem_handler = (ulong)kvmppc_handler_highmem; +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); +} - vcpu->arch.shadow_msr = MSR_USER64; +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); +} - err = __init_new_context(); - if (err < 0) - goto free_vcpu; - vcpu_book3s->context_id = err; +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); - vcpu_book3s->vsid_max = ((vcpu_book3s->context_id + 1) << USER_ESID_BITS) - 1; - vcpu_book3s->vsid_first = vcpu_book3s->context_id << USER_ESID_BITS; - vcpu_book3s->vsid_next = vcpu_book3s->vsid_first; +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); +} - return vcpu; +int kvm_age_hva(struct kvm *kvm, unsigned long hva) +{ + return kvm->arch.kvm_ops->age_hva(kvm, hva); +} -free_vcpu: - free_pages((long)vcpu_book3s, get_order(sizeof(struct kvmppc_vcpu_book3s))); -out: - return ERR_PTR(err); +int kvm_test_age_hva(struct kvm *kvm, unsigned long hva) +{ + return kvm->arch.kvm_ops->test_age_hva(kvm, hva); } -void kvmppc_core_vcpu_free(struct kvm_vcpu *vcpu) +void kvm_set_spte_hva(struct kvm *kvm, unsigned long hva, pte_t pte) { - struct kvmppc_vcpu_book3s *vcpu_book3s = to_book3s(vcpu); + kvm->arch.kvm_ops->set_spte_hva(kvm, hva, pte); +} - __destroy_context(vcpu_book3s->context_id); - kvm_vcpu_uninit(vcpu); - free_pages((long)vcpu_book3s, get_order(sizeof(struct kvmppc_vcpu_book3s))); +void kvmppc_mmu_destroy(struct kvm_vcpu *vcpu) +{ + vcpu->kvm->arch.kvm_ops->mmu_destroy(vcpu); } -extern int __kvmppc_vcpu_entry(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu); -int __kvmppc_vcpu_run(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu) +int kvmppc_core_init_vm(struct kvm *kvm) { - int ret; - /* No need to go into the guest when all we do is going out */ - if (signal_pending(current)) { - kvm_run->exit_reason = KVM_EXIT_INTR; - return -EINTR; - } +#ifdef CONFIG_PPC64 + INIT_LIST_HEAD(&kvm->arch.spapr_tce_tables); + INIT_LIST_HEAD(&kvm->arch.rtas_tokens); +#endif - /* XXX we get called with irq disabled - change that! */ - local_irq_enable(); + return kvm->arch.kvm_ops->init_vm(kvm); +} - ret = __kvmppc_vcpu_entry(kvm_run, vcpu); +void kvmppc_core_destroy_vm(struct kvm *kvm) +{ + kvm->arch.kvm_ops->destroy_vm(kvm); - local_irq_disable(); +#ifdef CONFIG_PPC64 + kvmppc_rtas_tokens_free(kvm); + WARN_ON(!list_empty(&kvm->arch.spapr_tce_tables)); +#endif +} - return ret; +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) { - return kvm_init(NULL, sizeof(struct kvmppc_vcpu_book3s), THIS_MODULE); + int r; + + r = kvm_init(NULL, sizeof(struct kvm_vcpu), 0, THIS_MODULE); + if (r) + return r; +#ifdef CONFIG_KVM_BOOK3S_32_HANDLER + r = kvmppc_book3s_init_pr(); +#endif + return r; + } static void kvmppc_book3s_exit(void) { +#ifdef CONFIG_KVM_BOOK3S_32_HANDLER + kvmppc_book3s_exit_pr(); +#endif kvm_exit(); } module_init(kvmppc_book3s_init); module_exit(kvmppc_book3s_exit); + +/* On 32bit this is our one and only kernel module */ +#ifdef CONFIG_KVM_BOOK3S_32_HANDLER +MODULE_ALIAS_MISCDEV(KVM_MINOR); +MODULE_ALIAS("devname:kvm"); +#endif |