diff options
29 files changed, 685 insertions, 219 deletions
diff --git a/Documentation/virtual/kvm/api.txt b/Documentation/virtual/kvm/api.txt index 0fe36497642c..69553183ef0f 100644 --- a/Documentation/virtual/kvm/api.txt +++ b/Documentation/virtual/kvm/api.txt @@ -2863,8 +2863,8 @@ The fields in each entry are defined as follows: this function/index combination -6. Capabilities that can be enabled ------------------------------------ +6. Capabilities that can be enabled on vCPUs +-------------------------------------------- There are certain capabilities that change the behavior of the virtual CPU when enabled. To enable them, please see section 4.37. Below you can find a list of @@ -3002,3 +3002,44 @@ Parameters: args[0] is the XICS device fd args[1] is the XICS CPU number (server ID) for this vcpu This capability connects the vcpu to an in-kernel XICS device. + + +7. Capabilities that can be enabled on VMs +------------------------------------------ + +There are certain capabilities that change the behavior of the virtual +machine when enabled. To enable them, please see section 4.37. Below +you can find a list of capabilities and what their effect on the VM +is when enabling them. + +The following information is provided along with the description: + + Architectures: which instruction set architectures provide this ioctl. + x86 includes both i386 and x86_64. + + Parameters: what parameters are accepted by the capability. + + Returns: the return value. General error numbers (EBADF, ENOMEM, EINVAL) + are not detailed, but errors with specific meanings are. + + +7.1 KVM_CAP_PPC_ENABLE_HCALL + +Architectures: ppc +Parameters: args[0] is the sPAPR hcall number + args[1] is 0 to disable, 1 to enable in-kernel handling + +This capability controls whether individual sPAPR hypercalls (hcalls) +get handled by the kernel or not. Enabling or disabling in-kernel +handling of an hcall is effective across the VM. On creation, an +initial set of hcalls are enabled for in-kernel handling, which +consists of those hcalls for which in-kernel handlers were implemented +before this capability was implemented. If disabled, the kernel will +not to attempt to handle the hcall, but will always exit to userspace +to handle it. Note that it may not make sense to enable some and +disable others of a group of related hcalls, but KVM does not prevent +userspace from doing that. + +If the hcall number specified is not one that has an in-kernel +implementation, the KVM_ENABLE_CAP ioctl will fail with an EINVAL +error. diff --git a/arch/powerpc/include/asm/asm-compat.h b/arch/powerpc/include/asm/asm-compat.h index 4b237aa35660..21be8ae8f809 100644 --- a/arch/powerpc/include/asm/asm-compat.h +++ b/arch/powerpc/include/asm/asm-compat.h @@ -34,10 +34,14 @@ #define PPC_MIN_STKFRM 112 #ifdef __BIG_ENDIAN__ +#define LWZX_BE stringify_in_c(lwzx) #define LDX_BE stringify_in_c(ldx) +#define STWX_BE stringify_in_c(stwx) #define STDX_BE stringify_in_c(stdx) #else +#define LWZX_BE stringify_in_c(lwbrx) #define LDX_BE stringify_in_c(ldbrx) +#define STWX_BE stringify_in_c(stwbrx) #define STDX_BE stringify_in_c(stdbrx) #endif diff --git a/arch/powerpc/include/asm/hvcall.h b/arch/powerpc/include/asm/hvcall.h index 5dbbb29f5c3e..85bc8c0d257b 100644 --- a/arch/powerpc/include/asm/hvcall.h +++ b/arch/powerpc/include/asm/hvcall.h @@ -279,6 +279,12 @@ #define H_GET_24X7_DATA 0xF07C #define H_GET_PERF_COUNTER_INFO 0xF080 +/* Values for 2nd argument to H_SET_MODE */ +#define H_SET_MODE_RESOURCE_SET_CIABR 1 +#define H_SET_MODE_RESOURCE_SET_DAWR 2 +#define H_SET_MODE_RESOURCE_ADDR_TRANS_MODE 3 +#define H_SET_MODE_RESOURCE_LE 4 + #ifndef __ASSEMBLY__ /** diff --git a/arch/powerpc/include/asm/kvm_book3s.h b/arch/powerpc/include/asm/kvm_book3s.h index f52f65694527..8ac5392dc477 100644 --- a/arch/powerpc/include/asm/kvm_book3s.h +++ b/arch/powerpc/include/asm/kvm_book3s.h @@ -83,8 +83,6 @@ struct kvmppc_vcpu_book3s { u64 sdr1; u64 hior; u64 msr_mask; - u64 purr_offset; - u64 spurr_offset; #ifdef CONFIG_PPC_BOOK3S_32 u32 vsid_pool[VSID_POOL_SIZE]; u32 vsid_next; @@ -148,6 +146,7 @@ extern void kvmppc_mmu_invalidate_pte(struct kvm_vcpu *vcpu, struct hpte_cache * extern int kvmppc_mmu_hpte_sysinit(void); extern void kvmppc_mmu_hpte_sysexit(void); extern int kvmppc_mmu_hv_init(void); +extern int kvmppc_book3s_hcall_implemented(struct kvm *kvm, unsigned long hc); extern int kvmppc_ld(struct kvm_vcpu *vcpu, ulong *eaddr, int size, void *ptr, bool data); extern int kvmppc_st(struct kvm_vcpu *vcpu, ulong *eaddr, int size, void *ptr, bool data); @@ -163,9 +162,9 @@ 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, +extern void kvmppc_invalidate_hpte(struct kvm *kvm, __be64 *hptep, unsigned long pte_index); -void kvmppc_clear_ref_hpte(struct kvm *kvm, unsigned long *hptep, +void kvmppc_clear_ref_hpte(struct kvm *kvm, __be64 *hptep, unsigned long pte_index); extern void *kvmppc_pin_guest_page(struct kvm *kvm, unsigned long addr, unsigned long *nb_ret); @@ -189,6 +188,9 @@ extern void kvmppc_hv_entry_trampoline(void); extern u32 kvmppc_alignment_dsisr(struct kvm_vcpu *vcpu, unsigned int inst); extern ulong kvmppc_alignment_dar(struct kvm_vcpu *vcpu, unsigned int inst); extern int kvmppc_h_pr(struct kvm_vcpu *vcpu, unsigned long cmd); +extern void kvmppc_pr_init_default_hcalls(struct kvm *kvm); +extern int kvmppc_hcall_impl_pr(unsigned long cmd); +extern int kvmppc_hcall_impl_hv_realmode(unsigned long cmd); extern void kvmppc_copy_to_svcpu(struct kvmppc_book3s_shadow_vcpu *svcpu, struct kvm_vcpu *vcpu); extern void kvmppc_copy_from_svcpu(struct kvm_vcpu *vcpu, diff --git a/arch/powerpc/include/asm/kvm_book3s_64.h b/arch/powerpc/include/asm/kvm_book3s_64.h index fddb72b48ce9..e504f8845c42 100644 --- a/arch/powerpc/include/asm/kvm_book3s_64.h +++ b/arch/powerpc/include/asm/kvm_book3s_64.h @@ -59,20 +59,29 @@ extern unsigned long kvm_rma_pages; /* These bits are reserved in the guest view of the HPTE */ #define HPTE_GR_RESERVED HPTE_GR_MODIFIED -static inline long try_lock_hpte(unsigned long *hpte, unsigned long bits) +static inline long try_lock_hpte(__be64 *hpte, unsigned long bits) { unsigned long tmp, old; + __be64 be_lockbit, be_bits; + + /* + * We load/store in native endian, but the HTAB is in big endian. If + * we byte swap all data we apply on the PTE we're implicitly correct + * again. + */ + be_lockbit = cpu_to_be64(HPTE_V_HVLOCK); + be_bits = cpu_to_be64(bits); asm volatile(" ldarx %0,0,%2\n" " and. %1,%0,%3\n" " bne 2f\n" - " ori %0,%0,%4\n" + " or %0,%0,%4\n" " stdcx. %0,0,%2\n" " beq+ 2f\n" " mr %1,%3\n" "2: isync" : "=&r" (tmp), "=&r" (old) - : "r" (hpte), "r" (bits), "i" (HPTE_V_HVLOCK) + : "r" (hpte), "r" (be_bits), "r" (be_lockbit) : "cc", "memory"); return old == 0; } @@ -110,16 +119,12 @@ static inline int __hpte_actual_psize(unsigned int lp, int psize) static inline unsigned long compute_tlbie_rb(unsigned long v, unsigned long r, unsigned long pte_index) { - int b_psize, a_psize; + int b_psize = MMU_PAGE_4K, a_psize = MMU_PAGE_4K; unsigned int penc; unsigned long rb = 0, va_low, sllp; unsigned int lp = (r >> LP_SHIFT) & ((1 << LP_BITS) - 1); - if (!(v & HPTE_V_LARGE)) { - /* both base and actual psize is 4k */ - b_psize = MMU_PAGE_4K; - a_psize = MMU_PAGE_4K; - } else { + if (v & HPTE_V_LARGE) { for (b_psize = 0; b_psize < MMU_PAGE_COUNT; b_psize++) { /* valid entries have a shift value */ diff --git a/arch/powerpc/include/asm/kvm_host.h b/arch/powerpc/include/asm/kvm_host.h index bb66d8b8efdf..855ba4d9539d 100644 --- a/arch/powerpc/include/asm/kvm_host.h +++ b/arch/powerpc/include/asm/kvm_host.h @@ -34,6 +34,7 @@ #include <asm/processor.h> #include <asm/page.h> #include <asm/cacheflush.h> +#include <asm/hvcall.h> #define KVM_MAX_VCPUS NR_CPUS #define KVM_MAX_VCORES NR_CPUS @@ -254,7 +255,6 @@ struct kvm_arch { atomic_t hpte_mod_interest; spinlock_t slot_phys_lock; cpumask_t need_tlb_flush; - struct kvmppc_vcore *vcores[KVM_MAX_VCORES]; int hpt_cma_alloc; #endif /* CONFIG_KVM_BOOK3S_HV_POSSIBLE */ #ifdef CONFIG_KVM_BOOK3S_PR_POSSIBLE @@ -263,6 +263,7 @@ struct kvm_arch { #ifdef CONFIG_PPC_BOOK3S_64 struct list_head spapr_tce_tables; struct list_head rtas_tokens; + DECLARE_BITMAP(enabled_hcalls, MAX_HCALL_OPCODE/4 + 1); #endif #ifdef CONFIG_KVM_MPIC struct openpic *mpic; @@ -271,6 +272,10 @@ struct kvm_arch { struct kvmppc_xics *xics; #endif struct kvmppc_ops *kvm_ops; +#ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE + /* This array can grow quite large, keep it at the end */ + struct kvmppc_vcore *vcores[KVM_MAX_VCORES]; +#endif }; /* @@ -503,8 +508,10 @@ struct kvm_vcpu_arch { #ifdef CONFIG_BOOKE u32 decar; #endif - u32 tbl; - u32 tbu; + /* Time base value when we entered the guest */ + u64 entry_tb; + u64 entry_vtb; + u64 entry_ic; u32 tcr; ulong tsr; /* we need to perform set/clr_bits() which requires ulong */ u32 ivor[64]; @@ -580,6 +587,7 @@ struct kvm_vcpu_arch { u32 mmucfg; u32 eptcfg; u32 epr; + u32 pwrmgtcr0; u32 crit_save; /* guest debug registers*/ struct debug_reg dbg_reg; diff --git a/arch/powerpc/include/asm/kvm_ppc.h b/arch/powerpc/include/asm/kvm_ppc.h index 9c89cdd067a6..e2fd5a133b9c 100644 --- a/arch/powerpc/include/asm/kvm_ppc.h +++ b/arch/powerpc/include/asm/kvm_ppc.h @@ -228,7 +228,7 @@ struct kvmppc_ops { void (*fast_vcpu_kick)(struct kvm_vcpu *vcpu); long (*arch_vm_ioctl)(struct file *filp, unsigned int ioctl, unsigned long arg); - + int (*hcall_implemented)(unsigned long hcall); }; extern struct kvmppc_ops *kvmppc_hv_ops; diff --git a/arch/powerpc/include/asm/mmu-book3e.h b/arch/powerpc/include/asm/mmu-book3e.h index d0918e09557f..8d24f788fd09 100644 --- a/arch/powerpc/include/asm/mmu-book3e.h +++ b/arch/powerpc/include/asm/mmu-book3e.h @@ -40,7 +40,9 @@ /* MAS registers bit definitions */ -#define MAS0_TLBSEL(x) (((x) << 28) & 0x30000000) +#define MAS0_TLBSEL_MASK 0x30000000 +#define MAS0_TLBSEL_SHIFT 28 +#define MAS0_TLBSEL(x) (((x) << MAS0_TLBSEL_SHIFT) & MAS0_TLBSEL_MASK) #define MAS0_ESEL_MASK 0x0FFF0000 #define MAS0_ESEL_SHIFT 16 #define MAS0_ESEL(x) (((x) << MAS0_ESEL_SHIFT) & MAS0_ESEL_MASK) @@ -86,6 +88,7 @@ #define MAS3_SPSIZE 0x0000003e #define MAS3_SPSIZE_SHIFT 1 +#define MAS4_TLBSEL_MASK MAS0_TLBSEL_MASK #define MAS4_TLBSELD(x) MAS0_TLBSEL(x) #define MAS4_INDD 0x00008000 /* Default IND */ #define MAS4_TSIZED(x) MAS1_TSIZE(x) diff --git a/arch/powerpc/include/asm/reg.h b/arch/powerpc/include/asm/reg.h index bffd89d27301..1f34ef7ec4a8 100644 --- a/arch/powerpc/include/asm/reg.h +++ b/arch/powerpc/include/asm/reg.h @@ -25,6 +25,7 @@ #ifdef CONFIG_8xx #include <asm/reg_8xx.h> #endif /* CONFIG_8xx */ +#include <asm/bug.h> #define MSR_SF_LG 63 /* Enable 64 bit mode */ #define MSR_ISF_LG 61 /* Interrupt 64b mode valid on 630 */ @@ -1203,6 +1204,21 @@ : "r" ((unsigned long)(v)) \ : "memory") +static inline unsigned long mfvtb (void) +{ +#ifdef CONFIG_PPC_BOOK3S_64 + if (cpu_has_feature(CPU_FTR_ARCH_207S)) + return mfspr(SPRN_VTB); +#endif + /* + * The above mfspr will be a no-op on anything before Power8 + * That can result in random values returned. We need to + * capture that. + */ + BUG(); + return 0; +} + #ifdef __powerpc64__ #if defined(CONFIG_PPC_CELL) || defined(CONFIG_PPC_FSL_BOOK3E) #define mftb() ({unsigned long rval; \ diff --git a/arch/powerpc/include/asm/time.h b/arch/powerpc/include/asm/time.h index 1d428e6007ca..03cbada59d3a 100644 --- a/arch/powerpc/include/asm/time.h +++ b/arch/powerpc/include/asm/time.h @@ -102,6 +102,15 @@ static inline u64 get_rtc(void) return (u64)hi * 1000000000 + lo; } +static inline u64 get_vtb(void) +{ +#ifdef CONFIG_PPC_BOOK3S_64 + if (cpu_has_feature(CPU_FTR_ARCH_207S)) + return mfvtb(); +#endif + return 0; +} + #ifdef CONFIG_PPC64 static inline u64 get_tb(void) { diff --git a/arch/powerpc/kernel/asm-offsets.c b/arch/powerpc/kernel/asm-offsets.c index f5995a912213..17ffcb4f27f9 100644 --- a/arch/powerpc/kernel/asm-offsets.c +++ b/arch/powerpc/kernel/asm-offsets.c @@ -493,6 +493,7 @@ int main(void) DEFINE(KVM_HOST_SDR1, offsetof(struct kvm, arch.host_sdr1)); DEFINE(KVM_TLBIE_LOCK, offsetof(struct kvm, arch.tlbie_lock)); DEFINE(KVM_NEED_FLUSH, offsetof(struct kvm, arch.need_tlb_flush.bits)); + DEFINE(KVM_ENABLED_HCALLS, offsetof(struct kvm, arch.enabled_hcalls)); DEFINE(KVM_LPCR, offsetof(struct kvm, arch.lpcr)); DEFINE(KVM_RMOR, offsetof(struct kvm, arch.rmor)); DEFINE(KVM_VRMA_SLB_V, offsetof(struct kvm, arch.vrma_slb_v)); diff --git a/arch/powerpc/kvm/Kconfig b/arch/powerpc/kvm/Kconfig index d6a53b95de94..8aeeda1ff42a 100644 --- a/arch/powerpc/kvm/Kconfig +++ b/arch/powerpc/kvm/Kconfig @@ -75,7 +75,6 @@ config KVM_BOOK3S_64 config KVM_BOOK3S_64_HV tristate "KVM support for POWER7 and PPC970 using hypervisor mode in host" depends on KVM_BOOK3S_64 - depends on !CPU_LITTLE_ENDIAN select KVM_BOOK3S_HV_POSSIBLE select MMU_NOTIFIER select CMA diff --git a/arch/powerpc/kvm/book3s.c b/arch/powerpc/kvm/book3s.c index c254c27f240e..bd75902b38ba 100644 --- a/arch/powerpc/kvm/book3s.c +++ b/arch/powerpc/kvm/book3s.c @@ -646,6 +646,12 @@ int kvm_vcpu_ioctl_get_one_reg(struct kvm_vcpu *vcpu, struct kvm_one_reg *reg) case KVM_REG_PPC_BESCR: val = get_reg_val(reg->id, vcpu->arch.bescr); break; + case KVM_REG_PPC_VTB: + val = get_reg_val(reg->id, vcpu->arch.vtb); + break; + case KVM_REG_PPC_IC: + val = get_reg_val(reg->id, vcpu->arch.ic); + break; default: r = -EINVAL; break; @@ -750,6 +756,12 @@ int kvm_vcpu_ioctl_set_one_reg(struct kvm_vcpu *vcpu, struct kvm_one_reg *reg) case KVM_REG_PPC_BESCR: vcpu->arch.bescr = set_reg_val(reg->id, val); break; + case KVM_REG_PPC_VTB: + vcpu->arch.vtb = set_reg_val(reg->id, val); + break; + case KVM_REG_PPC_IC: + vcpu->arch.ic = set_reg_val(reg->id, val); + break; default: r = -EINVAL; break; @@ -913,6 +925,11 @@ int kvmppc_core_check_processor_compat(void) return 0; } +int kvmppc_book3s_hcall_implemented(struct kvm *kvm, unsigned long hcall) +{ + return kvm->arch.kvm_ops->hcall_implemented(hcall); +} + static int kvmppc_book3s_init(void) { int r; diff --git a/arch/powerpc/kvm/book3s_64_mmu_hv.c b/arch/powerpc/kvm/book3s_64_mmu_hv.c index 80561074078d..2d154d9319b3 100644 --- a/arch/powerpc/kvm/book3s_64_mmu_hv.c +++ b/arch/powerpc/kvm/book3s_64_mmu_hv.c @@ -450,7 +450,7 @@ static int kvmppc_mmu_book3s_64_hv_xlate(struct kvm_vcpu *vcpu, gva_t eaddr, unsigned long slb_v; unsigned long pp, key; unsigned long v, gr; - unsigned long *hptep; + __be64 *hptep; int index; int virtmode = vcpu->arch.shregs.msr & (data ? MSR_DR : MSR_IR); @@ -473,13 +473,13 @@ static int kvmppc_mmu_book3s_64_hv_xlate(struct kvm_vcpu *vcpu, gva_t eaddr, preempt_enable(); return -ENOENT; } - hptep = (unsigned long *)(kvm->arch.hpt_virt + (index << 4)); - v = hptep[0] & ~HPTE_V_HVLOCK; + hptep = (__be64 *)(kvm->arch.hpt_virt + (index << 4)); + v = be64_to_cpu(hptep[0]) & ~HPTE_V_HVLOCK; gr = kvm->arch.revmap[index].guest_rpte; /* Unlock the HPTE */ asm volatile("lwsync" : : : "memory"); - hptep[0] = v; + hptep[0] = cpu_to_be64(v); preempt_enable(); gpte->eaddr = eaddr; @@ -583,7 +583,8 @@ int kvmppc_book3s_hv_page_fault(struct kvm_run *run, struct kvm_vcpu *vcpu, unsigned long ea, unsigned long dsisr) { struct kvm *kvm = vcpu->kvm; - unsigned long *hptep, hpte[3], r; + unsigned long hpte[3], r; + __be64 *hptep; unsigned long mmu_seq, psize, pte_size; unsigned long gpa_base, gfn_base; unsigned long gpa, gfn, hva, pfn; @@ -606,16 +607,16 @@ int kvmppc_book3s_hv_page_fault(struct kvm_run *run, struct kvm_vcpu *vcpu, if (ea != vcpu->arch.pgfault_addr) return RESUME_GUEST; index = vcpu->arch.pgfault_index; - hptep = (unsigned long *)(kvm->arch.hpt_virt + (index << 4)); + hptep = (__be64 *)(kvm->arch.hpt_virt + (index << 4)); rev = &kvm->arch.revmap[index]; preempt_disable(); while (!try_lock_hpte(hptep, HPTE_V_HVLOCK)) cpu_relax(); - hpte[0] = hptep[0] & ~HPTE_V_HVLOCK; - hpte[1] = hptep[1]; + hpte[0] = be64_to_cpu(hptep[0]) & ~HPTE_V_HVLOCK; + hpte[1] = be64_to_cpu(hptep[1]); hpte[2] = r = rev->guest_rpte; asm volatile("lwsync" : : : "memory"); - hptep[0] = hpte[0]; + hptep[0] = cpu_to_be64(hpte[0]); preempt_enable(); if (hpte[0] != vcpu->arch.pgfault_hpte[0] || @@ -731,8 +732,9 @@ int kvmppc_book3s_hv_page_fault(struct kvm_run *run, struct kvm_vcpu *vcpu, preempt_disable(); while (!try_lock_hpte(hptep, HPTE_V_HVLOCK)) cpu_relax(); - if ((hptep[0] & ~HPTE_V_HVLOCK) != hpte[0] || hptep[1] != hpte[1] || - rev->guest_rpte != hpte[2]) + if ((be64_to_cpu(hptep[0]) & ~HPTE_V_HVLOCK) != hpte[0] || + be64_to_cpu(hptep[1]) != hpte[1] || + rev->guest_rpte != hpte[2]) /* HPTE has been changed under us; let the guest retry */ goto out_unlock; hpte[0] = (hpte[0] & ~HPTE_V_ABSENT) | HPTE_V_VALID; @@ -752,20 +754,20 @@ int kvmppc_book3s_hv_page_fault(struct kvm_run *run, struct kvm_vcpu *vcpu, rcbits = *rmap >> KVMPPC_RMAP_RC_SHIFT; r &= rcbits | ~(HPTE_R_R | HPTE_R_C); - if (hptep[0] & HPTE_V_VALID) { + if (be64_to_cpu(hptep[0]) & HPTE_V_VALID) { /* HPTE was previously valid, so we need to invalidate it */ unlock_rmap(rmap); - hptep[0] |= HPTE_V_ABSENT; + hptep[0] |= cpu_to_be64(HPTE_V_ABSENT); kvmppc_invalidate_hpte(kvm, hptep, index); /* don't lose previous R and C bits */ - r |= hptep[1] & (HPTE_R_R | HPTE_R_C); + r |= be64_to_cpu(hptep[1]) & (HPTE_R_R | HPTE_R_C); } else { kvmppc_add_revmap_chain(kvm, rev, rmap, index, 0); } - hptep[1] = r; + hptep[1] = cpu_to_be64(r); eieio(); - hptep[0] = hpte[0]; + hptep[0] = cpu_to_be64(hpte[0]); asm volatile("ptesync" : : : "memory"); preempt_enable(); if (page && hpte_is_writable(r)) @@ -784,7 +786,7 @@ int kvmppc_book3s_hv_page_fault(struct kvm_run *run, struct kvm_vcpu *vcpu, return ret; out_unlock: - hptep[0] &= ~HPTE_V_HVLOCK; + hptep[0] &= ~cpu_to_be64(HPTE_V_HVLOCK); preempt_enable(); goto out_put; } @@ -860,7 +862,7 @@ static int kvm_unmap_rmapp(struct kvm *kvm, unsigned long *rmapp, { struct revmap_entry *rev = kvm->arch.revmap; unsigned long h, i, j; - unsigned long *hptep; + __be64 *hptep; unsigned long ptel, psize, rcbits; for (;;) { @@ -876,11 +878,11 @@ static int kvm_unmap_rmapp(struct kvm *kvm, unsigned long *rmapp, * rmap chain lock. */ i = *rmapp & KVMPPC_RMAP_INDEX; - hptep = (unsigned long *) (kvm->arch.hpt_virt + (i << 4)); + hptep = (__be64 *) (kvm->arch.hpt_virt + (i << 4)); if (!try_lock_hpte(hptep, HPTE_V_HVLOCK)) { /* unlock rmap before spinning on the HPTE lock */ unlock_rmap(rmapp); - while (hptep[0] & HPTE_V_HVLOCK) + while (be64_to_cpu(hptep[0]) & HPTE_V_HVLOCK) cpu_relax(); continue; } @@ -899,14 +901,14 @@ static int kvm_unmap_rmapp(struct kvm *kvm, unsigned long *rmapp, /* Now check and modify the HPTE */ ptel = rev[i].guest_rpte; - psize = hpte_page_size(hptep[0], ptel); - if ((hptep[0] & HPTE_V_VALID) && + psize = hpte_page_size(be64_to_cpu(hptep[0]), ptel); + if ((be64_to_cpu(hptep[0]) & HPTE_V_VALID) && hpte_rpn(ptel, psize) == gfn) { if (kvm->arch.using_mmu_notifiers) - hptep[0] |= HPTE_V_ABSENT; + hptep[0] |= cpu_to_be64(HPTE_V_ABSENT); kvmppc_invalidate_hpte(kvm, hptep, i); /* Harvest R and C */ - rcbits = hptep[1] & (HPTE_R_R | HPTE_R_C); + rcbits = be64_to_cpu(hptep[1]) & (HPTE_R_R | HPTE_R_C); *rmapp |= rcbits << KVMPPC_RMAP_RC_SHIFT; if (rcbits & ~rev[i].guest_rpte) { rev[i].guest_rpte = ptel | rcbits; @@ -914,7 +916,7 @@ static int kvm_unmap_rmapp(struct kvm *kvm, unsigned long *rmapp, } } unlock_rmap(rmapp); - hptep[0] &= ~HPTE_V_HVLOCK; + hptep[0] &= ~cpu_to_be64(HPTE_V_HVLOCK); } return 0; } @@ -961,7 +963,7 @@ static int kvm_age_rmapp(struct kvm *kvm, unsigned long *rmapp, { struct revmap_entry *rev = kvm->arch.revmap; unsigned long head, i, j; - unsigned long *hptep; + __be64 *hptep; int ret = 0; retry: @@ -977,23 +979,24 @@ static int kvm_age_rmapp(struct kvm *kvm, unsigned long *rmapp, i = head = *rmapp & KVMPPC_RMAP_INDEX; do { - hptep = (unsigned long *) (kvm->arch.hpt_virt + (i << 4)); + hptep = (__be64 *) (kvm->arch.hpt_virt + (i << 4)); j = rev[i].forw; /* If this HPTE isn't referenced, ignore it */ - if (!(hptep[1] & HPTE_R_R)) + if (!(be64_to_cpu(hptep[1]) & HPTE_R_R)) continue; if (!try_lock_hpte(hptep, HPTE_V_HVLOCK)) { /* unlock rmap before spinning on the HPTE lock */ unlock_rmap(rmapp); - while (hptep[0] & HPTE_V_HVLOCK) + while (be64_to_cpu(hptep[0]) & HPTE_V_HVLOCK) cpu_relax(); goto retry; } /* Now check and modify the HPTE */ - if ((hptep[0] & HPTE_V_VALID) && (hptep[1] & HPTE_R_R)) { + if ((be64_to_cpu(hptep[0]) & HPTE_V_VALID) && + (be64_to_cpu(hptep[1]) & HPTE_R_R)) { kvmppc_clear_ref_hpte(kvm, hptep, i); if (!(rev[i].guest_rpte & HPTE_R_R)) { rev[i].guest_rpte |= HPTE_R_R; @@ -1001,7 +1004,7 @@ static int kvm_age_rmapp(struct kvm *kvm, unsigned long *rmapp, } ret = 1; } - hptep[0] &= ~HPTE_V_HVLOCK; + hptep[0] &= ~cpu_to_be64(HPTE_V_HVLOCK); } while ((i = j) != head); unlock_rmap(rmapp); @@ -1035,7 +1038,7 @@ static int kvm_test_age_rmapp(struct kvm *kvm, unsigned long *rmapp, do { hp = (unsigned long *)(kvm->arch.hpt_virt + (i << 4)); j = rev[i].forw; - if (hp[1] & HPTE_R_R) + if (be64_to_cpu(hp[1]) & HPTE_R_R) goto out; } while ((i = j) != head); } @@ -1075,7 +1078,7 @@ static int kvm_test_clear_dirty_npages(struct kvm *kvm, unsigned long *rmapp) unsigned long head, i, j; unsigned long n; unsigned long v, r; - unsigned long *hptep; + __be64 *hptep; int npages_dirty = 0; retry: @@ -1091,7 +1094,8 @@ static int kvm_test_clear_dirty_npages(struct kvm *kvm, unsigned long *rmapp) i = head = *rmapp & KVMPPC_RMAP_INDEX; do { - hptep = (unsigned long *) (kvm->arch.hpt_virt + (i << 4)); + unsigned long hptep1; + hptep = (__be64 *) (kvm->arch.hpt_virt + (i << 4)); j = rev[i].forw; /* @@ -1108,29 +1112,30 @@ static int kvm_test_clear_dirty_npages(struct kvm *kvm, unsigned long *rmapp) * Otherwise we need to do the tlbie even if C==0 in * order to pick up any delayed writeback of C. */ - if (!(hptep[1] & HPTE_R_C) && - (!hpte_is_writable(hptep[1]) || vcpus_running(kvm))) + hptep1 = be64_to_cpu(hptep[1]); + if (!(hptep1 & HPTE_R_C) && + (!hpte_is_writable(hptep1) || vcpus_running(kvm))) continue; if (!try_lock_hpte(hptep, HPTE_V_HVLOCK)) { /* unlock rmap before spinning on the HPTE lock */ unlock_rmap(rmapp); - while (hptep[0] & HPTE_V_HVLOCK) + while (hptep[0] & cpu_to_be64(HPTE_V_HVLOCK)) cpu_relax(); goto retry; } /* Now check and modify the HPTE */ - if (!(hptep[0] & HPTE_V_VALID)) + if (!(hptep[0] & cpu_to_be64(HPTE_V_VALID))) continue; /* need to make it temporarily absent so C is stable */ - hptep[0] |= HPTE_V_ABSENT; + hptep[0] |= cpu_to_be64(HPTE_V_ABSENT); kvmppc_invalidate_hpte(kvm, hptep, i); - v = hptep[0]; - r = hptep[1]; + v = be64_to_cpu(hptep[0]); + r = be64_to_cpu(hptep[1]); if (r & HPTE_R_C) { - hptep[1] = r & ~HPTE_R_C; + hptep[1] = cpu_to_be64(r & ~HPTE_R_C); if (!(rev[i].guest_rpte & HPTE_R_C)) { rev[i].guest_rpte |= HPTE_R_C; note_hpte_modification(kvm, &rev[i]); @@ -1143,7 +1148,7 @@ static int kvm_test_clear_dirty_npages(struct kvm *kvm, unsigned long *rmapp) } v &= ~(HPTE_V_ABSENT | HPTE_V_HVLOCK); v |= HPTE_V_VALID; - hptep[0] = v; + hptep[0] = cpu_to_be64(v); } while ((i = j) != head); unlock_rmap(rmapp); @@ -1307,7 +1312,7 @@ struct kvm_htab_ctx { * Returns 1 if this HPT entry has been modified or has pending * R/C bit changes. */ -static int hpte_dirty(struct revmap_entry *revp, unsigned long *hptp) +static int hpte_dirty(struct revmap_entry *revp, __be64 *hptp) { unsigned long rcbits_unset; @@ -1316,13 +1321,14 @@ static int hpte_dirty(struct revmap_entry *revp, unsigned long *hptp) /* Also need to consider changes in reference and changed bits */ rcbits_unset = ~revp->guest_rpte & (HPTE_R_R | HPTE_R_C); - if ((hptp[0] & HPTE_V_VALID) && (hptp[1] & rcbits_unset)) + if ((be64_to_cpu(hptp[0]) & HPTE_V_VALID) && + (be64_to_cpu(hptp[1]) & rcbits_unset)) return 1; return 0; } -static long record_hpte(unsigned long flags, unsigned long *hptp, +static long record_hpte(unsigned long flags, __be64 *hptp, unsigned long *hpte, struct revmap_entry *revp, int want_valid, int first_pass) { @@ -1337,10 +1343,10 @@ static long record_hpte(unsigned long flags, unsigned long *hptp, return 0; valid = 0; - if (hptp[0] & (HPTE_V_VALID | HPTE_V_ABSENT)) { + if (be64_to_cpu(hptp[0]) & (HPTE_V_VALID | HPTE_V_ABSENT)) { valid = 1; if ((flags & KVM_GET_HTAB_BOLTED_ONLY) && - !(hptp[0] & HPTE_V_BOLTED)) + !(be64_to_cpu(hptp[0]) & HPTE_V_BOLTED)) valid = 0; } if (valid != want_valid) @@ -1352,7 +1358,7 @@ static long record_hpte(unsigned long flags, unsigned long *hptp, preempt_disable(); while (!try_lock_hpte(hptp, HPTE_V_HVLOCK)) cpu_relax(); - v = hptp[0]; + v = be64_to_cpu(hptp[0]); /* re-evaluate valid and dirty from synchronized HPTE value */ valid = !!(v & HPTE_V_VALID); @@ -1360,9 +1366,9 @@ static long record_hpte(unsigned long flags, unsigned long *hptp, /* Harvest R and C into guest view if necessary */ rcbits_unset = ~revp->guest_rpte & (HPTE_R_R | HPTE_R_C); - if (valid && (rcbits_unset & hptp[1])) { - revp->guest_rpte |= (hptp[1] & (HPTE_R_R | HPTE_R_C)) | - HPTE_GR_MODIFIED; + if (valid && (rcbits_unset & be64_to_cpu(hptp[1]))) { + revp->guest_rpte |= (be64_to_cpu(hptp[1]) & + (HPTE_R_R | HPTE_R_C)) | HPTE_GR_MODIFIED; dirty = 1; } @@ -1381,13 +1387,13 @@ static long record_hpte(unsigned long flags, unsigned long *hptp, revp->guest_rpte = r; } asm volatile(PPC_RELEASE_BARRIER "" : : : "memory"); - hptp[0] &= ~HPTE_V_HVLOCK; + hptp[0] &= ~cpu_to_be64(HPTE_V_HVLOCK); preempt_enable(); if (!(valid == want_valid && (first_pass || dirty))) ok = 0; } - hpte[0] = v; - hpte[1] = r; + hpte[0] = cpu_to_be64(v); + hpte[1] = cpu_to_be64(r); return ok; } @@ -1397,7 +1403,7 @@ static ssize_t kvm_htab_read(struct file *file, char __user *buf, struct kvm_htab_ctx *ctx = file->private_data; struct kvm *kvm = ctx->kvm; struct kvm_get_htab_header hdr; - unsigned long *hptp; + __be64 *hptp; struct revmap_entry *revp; unsigned long i, nb, nw; unsigned long __user *lbuf; @@ -1413,7 +1419,7 @@ static ssize_t kvm_htab_read(struct file *file, char __user *buf, flags = ctx->flags; i = ctx->index; - hptp = (unsigned long *)(kvm->arch.hpt_virt + (i * HPTE_SIZE)); + hptp = (__be64 *)(kvm->arch.hpt_virt + (i * HPTE_SIZE)); revp = kvm->arch.revmap + i; lbuf = (unsigned long __user *)buf; @@ -1497,7 +1503,7 @@ static ssize_t kvm_htab_write(struct file *file, const char __user *buf, unsigned long i, j; unsigned long v, r; unsigned long __user *lbuf; - unsigned long *hptp; + __be64 *hptp; unsigned long tmp[2]; ssize_t nb; long int err, ret; @@ -1539,7 +1545,7 @@ static ssize_t kvm_htab_write(struct file *file, const char __user *buf, i + hdr.n_valid + hdr.n_invalid > kvm->arch.hpt_npte) break; - hptp = (unsigned long *)(kvm->arch.hpt_virt + (i * HPTE_SIZE)); + hptp = (__be64 *)(kvm->arch.hpt_virt + (i * HPTE_SIZE)); lbuf = (unsigned long __user *)buf; for (j = 0; j < hdr.n_valid; ++j) { err = -EFAULT; @@ -1551,7 +1557,7 @@ static ssize_t kvm_htab_write(struct file *file, const char __user *buf, lbuf += 2; nb += HPTE_SIZE; - if (hptp[0] & (HPTE_V_VALID | HPTE_V_ABSENT)) + if (be64_to_cpu(hptp[0]) & (HPTE_V_VALID | HPTE_V_ABSENT)) kvmppc_do_h_remove(kvm, 0, i, 0, tmp); err = -EIO; ret = kvmppc_virtmode_do_h_enter(kvm, H_EXACT, i, v, r, @@ -1577,7 +1583,7 @@ static ssize_t kvm_htab_write(struct file *file, const char __user *buf, } for (j = 0; j < hdr.n_invalid; ++j) { - if (hptp[0] & (HPTE_V_VALID | HPTE_V_ABSENT)) + if (be64_to_cpu(hptp[0]) & (HPTE_V_VALID | HPTE_V_ABSENT)) kvmppc_do_h_remove(kvm, 0, i, 0, tmp); ++i; hptp += 2; diff --git a/arch/powerpc/kvm/book3s_emulate.c b/arch/powerpc/kvm/book3s_emulate.c index 3f295269af37..84fddcd6c1f8 100644 --- a/arch/powerpc/kvm/book3s_emulate.c +++ b/arch/powerpc/kvm/book3s_emulate.c @@ -439,12 +439,6 @@ int kvmppc_core_emulate_mtspr_pr(struct kvm_vcpu *vcpu, int sprn, ulong spr_val) (mfmsr() & MSR_HV)) vcpu->arch.hflags |= BOOK3S_HFLAG_DCBZ32; break; - case SPRN_PURR: - to_book3s(vcpu)->purr_offset = spr_val - get_tb(); - break; - case SPRN_SPURR: - to_book3s(vcpu)->spurr_offset = spr_val - get_tb(); - break; case SPRN_GQR0: case SPRN_GQR1: case SPRN_GQR2: @@ -572,10 +566,22 @@ int kvmppc_core_emulate_mfspr_pr(struct kvm_vcpu *vcpu, int sprn, ulong *spr_val *spr_val = 0; break; case SPRN_PURR: - *spr_val = get_tb() + to_book3s(vcpu)->purr_offset; + /* + * On exit we would have updated purr + */ + *spr_val = vcpu->arch.purr; break; case SPRN_SPURR: - *spr_val = get_tb() + to_book3s(vcpu)->purr_offset; + /* + * On exit we would have updated spurr + */ + *spr_val = vcpu->arch.spurr; + break; + case SPRN_VTB: + *spr_val = vcpu->arch.vtb; + break; + case SPRN_IC: + *spr_val = vcpu->arch.ic; break; case SPRN_GQR0: case SPRN_GQR1: diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c index 7a12edbb61e7..f1281c4c381c 100644 --- a/arch/powerpc/kvm/book3s_hv.c +++ b/arch/powerpc/kvm/book3s_hv.c @@ -67,6 +67,8 @@ /* Used as a "null" value for timebase values */ #define TB_NIL (~(u64)0) +static DECLARE_BITMAP(default_enabled_hcalls, MAX_HCALL_OPCODE/4 + 1); + static void kvmppc_end_cede(struct kvm_vcpu *vcpu); static int kvmppc_hv_setup_htab_rma(struct kvm_vcpu *vcpu); @@ -270,7 +272,7 @@ struct kvm_vcpu *kvmppc_find_vcpu(struct kvm *kvm, int id) static void init_vpa(struct kvm_vcpu *vcpu, struct lppaca *vpa) { vpa->__old_status |= LPPACA_OLD_SHARED_PROC; - vpa->yield_count = 1; + vpa->yield_count = cpu_to_be32(1); } static int set_vpa(struct kvm_vcpu *vcpu, struct kvmppc_vpa *v, @@ -293,8 +295,8 @@ static int set_vpa(struct kvm_vcpu *vcpu, struct kvmppc_vpa *v, struct reg_vpa { u32 dummy; union { - u16 hword; - u32 word; + __be16 hword; + __be32 word; } length; }; @@ -333,9 +335,9 @@ static unsigned long do_h_register_vpa(struct kvm_vcpu *vcpu, if (va == NULL) return H_PARAMETER; if (subfunc == H_VPA_REG_VPA) - len = ((struct reg_vpa *)va)->length.hword; + len = be16_to_cpu(((struct reg_vpa *)va)->length.hword); else - len = ((struct reg_vpa *)va)->length.word; + len = be32_to_cpu(((struct reg_vpa *)va)->length.word); kvmppc_unpin_guest_page(kvm, va, vpa, false); /* Check length */ @@ -540,21 +542,63 @@ static void kvmppc_create_dtl_entry(struct kvm_vcpu *vcpu, return; memset(dt, 0, sizeof(struct dtl_entry)); dt->dispatch_reason = 7; - dt->processor_id = vc->pcpu + vcpu->arch.ptid; - dt->timebase = now + vc->tb_offset; - dt->enqueue_to_dispatch_time = stolen; - dt->srr0 = kvmppc_get_pc(vcpu); - dt->srr1 = vcpu->arch.shregs.msr; + dt->processor_id = cpu_to_be16(vc->pcpu + vcpu->arch.ptid); + dt->timebase = cpu_to_be64(now + vc->tb_offset); + dt->enqueue_to_dispatch_time = cpu_to_be32(stolen); + dt->srr0 = cpu_to_be64(kvmppc_get_pc(vcpu)); + dt->srr1 = cpu_to_be64(vcpu->arch.shregs.msr); ++dt; if (dt == vcpu->arch.dtl.pinned_end) dt = vcpu->arch.dtl.pinned_addr; vcpu->arch.dtl_ptr = dt; /* order writing *dt vs. writing vpa->dtl_idx */ smp_wmb(); - vpa->dtl_idx = ++vcpu->arch.dtl_index; + vpa->dtl_idx = cpu_to_be64(++vcpu->arch.dtl_index); vcpu->arch.dtl.dirty = true; } +static bool kvmppc_power8_compatible(struct kvm_vcpu *vcpu) +{ + if (vcpu->arch.vcore->arch_compat >= PVR_ARCH_207) + return true; + if ((!vcpu->arch.vcore->arch_compat) && + cpu_has_feature(CPU_FTR_ARCH_207S)) + return true; + return false; +} + +static int kvmppc_h_set_mode(struct kvm_vcpu *vcpu, unsigned long mflags, + unsigned long resource, unsigned long value1, + unsigned long value2) +{ + switch (resource) { + case H_SET_MODE_RESOURCE_SET_CIABR: + if (!kvmppc_power8_compatible(vcpu)) + return H_P2; + if (value2) + return H_P4; + if (mflags) + return H_UNSUPPORTED_FLAG_START; + /* Guests can't breakpoint the hypervisor */ + if ((value1 & CIABR_PRIV) == CIABR_PRIV_HYPER) + return H_P3; + vcpu->arch.ciabr = value1; + return H_SUCCESS; + case H_SET_MODE_RESOURCE_SET_DAWR: + if (!kvmppc_power8_compatible(vcpu)) + return H_P2; + if (mflags) + return H_UNSUPPORTED_FLAG_START; + if (value2 & DABRX_HYP) + return H_P4; + vcpu->arch.dawr = value1; + vcpu->arch.dawrx = value2; + return H_SUCCESS; + default: + return H_TOO_HARD; + } +} + int kvmppc_pseries_do_hcall(struct kvm_vcpu *vcpu) { unsigned long req = kvmppc_get_gpr(vcpu, 3); @@ -562,6 +606,10 @@ int kvmppc_pseries_do_hcall(struct kvm_vcpu *vcpu) struct kvm_vcpu *tvcpu; int idx, rc; + if (req <= MAX_HCALL_OPCODE && + !test_bit(req/4, vcpu->kvm->arch.enabled_hcalls)) + return RESUME_HOST; + switch (req) { case H_ENTER: idx = srcu_read_lock(&vcpu->kvm->srcu); @@ -620,7 +668,14 @@ int kvmppc_pseries_do_hcall(struct kvm_vcpu *vcpu) /* Send the error out to userspace via KVM_RUN */ return rc; - + case H_SET_MODE: + ret = kvmppc_h_set_mode(vcpu, kvmppc_get_gpr(vcpu, 4), + kvmppc_get_gpr(vcpu, 5), + kvmppc_get_gpr(vcpu, 6), + kvmppc_get_gpr(vcpu, 7)); + if (ret == H_TOO_HARD) + return RESUME_HOST; + break; case H_XIRR: case H_CPPR: case H_EOI: @@ -639,6 +694,29 @@ int kvmppc_pseries_do_hcall(struct kvm_vcpu *vcpu) return RESUME_GUEST; } +static int kvmppc_hcall_impl_hv(unsigned long cmd) +{ + switch (cmd) { + case H_CEDE: + case H_PROD: + case H_CONFER: + case H_REGISTER_VPA: + case H_SET_MODE: +#ifdef CONFIG_KVM_XICS + case H_XIRR: + case H_CPPR: + case H_EOI: + case H_IPI: + case H_IPOLL: + case H_XIRR_X: +#endif + return 1; + } + + /* See if it's in the real-mode table */ + return kvmppc_hcall_impl_hv_realmode(cmd); +} + static int kvmppc_handle_exit_hv(struct kvm_run *run, struct kvm_vcpu *vcpu, struct task_struct *tsk) { @@ -894,12 +972,6 @@ static int kvmppc_get_one_reg_hv(struct kvm_vcpu *vcpu, u64 id, case KVM_REG_PPC_CIABR: *val = get_reg_val(id, vcpu->arch.ciabr); break; - case KVM_REG_PPC_IC: - *val = get_reg_val(id, vcpu->arch.ic); - break; - case KVM_REG_PPC_VTB: - *val = get_reg_val(id, vcpu->arch.vtb); - break; case KVM_REG_PPC_CSIGR: *val = get_reg_val(id, vcpu->arch.csigr); break; @@ -1094,12 +1166,6 @@ static int kvmppc_set_one_reg_hv(struct kvm_vcpu *vcpu, u64 id, if ((vcpu->arch.ciabr & CIABR_PRIV) == CIABR_PRIV_HYPER) vcpu->arch.ciabr &= ~CIABR_PRIV; /* disable */ break; - case KVM_REG_PPC_IC: - vcpu->arch.ic = set_reg_val(id, *val); - break; - case KVM_REG_PPC_VTB: - vcpu->arch.vtb = set_reg_val(id, *val); - break; case KVM_REG_PPC_CSIGR: vcpu->arch.csigr = set_reg_val(id, *val); break; @@ -2281,6 +2347,10 @@ static int kvmppc_core_init_vm_hv(struct kvm *kvm) */ cpumask_setall(&kvm->arch.need_tlb_flush); + /* Start out with the default set of hcalls enabled */ + memcpy(kvm->arch.enabled_hcalls, default_enabled_hcalls, + sizeof(kvm->arch.enabled_hcalls)); + kvm->arch.rma = NULL; kvm->arch.host_sdr1 = mfspr(SPRN_SDR1); @@ -2419,6 +2489,49 @@ static long kvm_arch_vm_ioctl_hv(struct file *filp, return r; } +/* + * List of hcall numbers to enable by default. + * For compatibility with old userspace, we enable by default + * all hcalls that were implemented before the hcall-enabling + * facility was added. Note this list should not include H_RTAS. + */ +static unsigned int default_hcall_list[] = { + H_REMOVE, + H_ENTER, + H_READ, + H_PROTECT, + H_BULK_REMOVE, + H_GET_TCE, + H_PUT_TCE, + H_SET_DABR, + H_SET_XDABR, + H_CEDE, + H_PROD, + H_CONFER, + H_REGISTER_VPA, +#ifdef CONFIG_KVM_XICS + H_EOI, + H_CPPR, + H_IPI, + H_IPOLL, + H_XIRR, + H_XIRR_X, +#endif + 0 +}; + +static void init_default_hcalls(void) +{ + int i; + unsigned int hcall; + + for (i = 0; default_hcall_list[i]; ++i) { + hcall = default_hcall_list[i]; + WARN_ON(!kvmppc_hcall_impl_hv(hcall)); + __set_bit(hcall / 4, default_enabled_hcalls); + } +} + 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, @@ -2451,6 +2564,7 @@ static struct kvmppc_ops kvm_ops_hv = { .emulate_mfspr = kvmppc_core_emulate_mfspr_hv, .fast_vcpu_kick = kvmppc_fast_vcpu_kick_hv, .arch_vm_ioctl = kvm_arch_vm_ioctl_hv, + .hcall_implemented = kvmppc_hcall_impl_hv, }; static int kvmppc_book3s_init_hv(void) @@ -2466,6 +2580,8 @@ static int kvmppc_book3s_init_hv(void) kvm_ops_hv.owner = THIS_MODULE; kvmppc_hv_ops = &kvm_ops_hv; + init_default_hcalls(); + r = kvmppc_mmu_hv_init(); return r; } diff --git a/arch/powerpc/kvm/book3s_hv_builtin.c b/arch/powerpc/kvm/book3s_hv_builtin.c index 7cde8a665205..3b41447482e5 100644 --- a/arch/powerpc/kvm/book3s_hv_builtin.c +++ b/arch/powerpc/kvm/book3s_hv_builtin.c @@ -212,3 +212,16 @@ bool kvm_hv_mode_active(void) { return atomic_read(&hv_vm_count) != 0; } + +extern int hcall_real_table[], hcall_real_table_end[]; + +int kvmppc_hcall_impl_hv_realmode(unsigned long cmd) +{ + cmd /= 4; + if (cmd < hcall_real_table_end - hcall_real_table && + hcall_real_table[cmd]) + return 1; + + return 0; +} +EXPORT_SYMBOL_GPL(kvmppc_hcall_impl_hv_realmode); diff --git a/arch/powerpc/kvm/book3s_hv_ras.c b/arch/powerpc/kvm/book3s_hv_ras.c index 3a5c568b1e89..d562c8e2bc30 100644 --- a/arch/powerpc/kvm/book3s_hv_ras.c +++ b/arch/powerpc/kvm/book3s_hv_ras.c @@ -45,14 +45,14 @@ static void reload_slb(struct kvm_vcpu *vcpu) return; /* Sanity check */ - n = min_t(u32, slb->persistent, SLB_MIN_SIZE); + n = min_t(u32, be32_to_cpu(slb->persistent), SLB_MIN_SIZE); if ((void *) &slb->save_area[n] > vcpu->arch.slb_shadow.pinned_end) return; /* Load up the SLB from that */ for (i = 0; i < n; ++i) { - unsigned long rb = slb->save_area[i].esid; - unsigned long rs = slb->save_area[i].vsid; + unsigned long rb = be64_to_cpu(slb->save_area[i].esid); + unsigned long rs = be64_to_cpu(slb->save_area[i].vsid); rb = (rb & ~0xFFFul) | i; /* insert entry number */ asm volatile("slbmte %0,%1" : : "r" (rs), "r" (rb)); diff --git a/arch/powerpc/kvm/book3s_hv_rm_mmu.c b/arch/powerpc/kvm/book3s_hv_rm_mmu.c index 6e6224318c36..e5c6063c83f2 100644 --- a/arch/powerpc/kvm/book3s_hv_rm_mmu.c +++ b/arch/powerpc/kvm/book3s_hv_rm_mmu.c @@ -154,10 +154,10 @@ static pte_t lookup_linux_pte_and_update(pgd_t *pgdir, unsigned long hva, return kvmppc_read_update_linux_pte(ptep, writing, hugepage_shift); } -static inline void unlock_hpte(unsigned long *hpte, unsigned long hpte_v) +static inline void unlock_hpte(__be64 *hpte, unsigned long hpte_v) { asm volatile(PPC_RELEASE_BARRIER "" : : : "memory"); - hpte[0] = hpte_v; + hpte[0] = cpu_to_be64(hpte_v); } long kvmppc_do_h_enter(struct kvm *kvm, unsigned long flags, @@ -166,7 +166,7 @@ long kvmppc_do_h_enter(struct kvm *kvm, unsigned long flags, { unsigned long i, pa, gpa, gfn, psize; unsigned long slot_fn, hva; - unsigned long *hpte; + __be64 *hpte; struct revmap_entry *rev; unsigned long g_ptel; struct kvm_memory_slot *memslot; @@ -275,9 +275,9 @@ long kvmppc_do_h_enter(struct kvm *kvm, unsigned long flags, return H_PARAMETER; if (likely((flags & H_EXACT) == 0)) { pte_index &= ~7UL; - hpte = (unsigned long *)(kvm->arch.hpt_virt + (pte_index << 4)); + hpte = (__be64 *)(kvm->arch.hpt_virt + (pte_index << 4)); for (i = 0; i < 8; ++i) { - if ((*hpte & HPTE_V_VALID) == 0 && + if ((be64_to_cpu(*hpte) & HPTE_V_VALID) == 0 && try_lock_hpte(hpte, HPTE_V_HVLOCK | HPTE_V_VALID | HPTE_V_ABSENT)) break; @@ -292,11 +292,13 @@ long kvmppc_do_h_enter(struct kvm *kvm, unsigned long flags, */ hpte -= 16; for (i = 0; i < 8; ++i) { + u64 pte; while (!try_lock_hpte(hpte, HPTE_V_HVLOCK)) cpu_relax(); - if (!(*hpte & (HPTE_V_VALID | HPTE_V_ABSENT))) + pte = be64_to_cpu(*hpte); + if (!(pte & (HPTE_V_VALID | HPTE_V_ABSENT))) break; - *hpte &= ~HPTE_V_HVLOCK; + *hpte &= ~cpu_to_be64(HPTE_V_HVLOCK); hpte += 2; } if (i == 8) @@ -304,14 +306,17 @@ long kvmppc_do_h_enter(struct kvm *kvm, unsigned long flags, } pte_index += i; } else { - hpte = (unsigned long *)(kvm->arch.hpt_virt + (pte_index << 4)); + hpte = (__be64 *)(kvm->arch.hpt_virt + (pte_index << 4)); if (!try_lock_hpte(hpte, HPTE_V_HVLOCK | HPTE_V_VALID | HPTE_V_ABSENT)) { /* Lock the slot and check again */ + u64 pte; + while (!try_lock_hpte(hpte, HPTE_V_HVLOCK)) cpu_relax(); - if (*hpte & (HPTE_V_VALID | HPTE_V_ABSENT)) { - *hpte &= ~HPTE_V_HVLOCK; + pte = be64_to_cpu(*hpte); + if (pte & (HPTE_V_VALID | HPTE_V_ABSENT)) { + *hpte &= ~cpu_to_be64(HPTE_V_HVLOCK); return H_PTEG_FULL; } } @@ -347,11 +352,11 @@ long kvmppc_do_h_enter(struct kvm *kvm, unsigned long flags, } } - hpte[1] = ptel; + hpte[1] = cpu_to_be64(ptel); /* Write the first HPTE dword, unlocking the HPTE and making it valid */ eieio(); - hpte[0] = pteh; + hpte[0] = cpu_to_be64(pteh); asm volatile("ptesync" : : : "memory"); *pte_idx_ret = pte_index; @@ -468,30 +473,35 @@ long kvmppc_do_h_remove(struct kvm *kvm, unsigned long flags, unsigned long pte_index, unsigned long avpn, unsigned long *hpret) { - unsigned long *hpte; + __be64 *hpte; unsigned long v, r, rb; struct revmap_entry *rev; + u64 pte; if (pte_index >= kvm->arch.hpt_npte) return H_PARAMETER; - hpte = (unsigned long *)(kvm->arch.hpt_virt + (pte_index << 4)); + hpte = (__be64 *)(kvm->arch.hpt_virt + (pte_index << 4)); while (!try_lock_hpte(hpte, HPTE_V_HVLOCK)) cpu_relax(); - if ((hpte[0] & (HPTE_V_ABSENT | HPTE_V_VALID)) == 0 || - ((flags & H_AVPN) && (hpte[0] & ~0x7fUL) != avpn) || - ((flags & H_ANDCOND) && (hpte[0] & avpn) != 0)) { - hpte[0] &= ~HPTE_V_HVLOCK; + pte = be64_to_cpu(hpte[0]); + if ((pte & (HPTE_V_ABSENT | HPTE_V_VALID)) == 0 || + ((flags & H_AVPN) && (pte & ~0x7fUL) != avpn) || + ((flags & H_ANDCOND) && (pte & avpn) != 0)) { + hpte[0] &= ~cpu_to_be64(HPTE_V_HVLOCK); return H_NOT_FOUND; } rev = real_vmalloc_addr(&kvm->arch.revmap[pte_index]); - v = hpte[0] & ~HPTE_V_HVLOCK; + v = pte & ~HPTE_V_HVLOCK; if (v & HPTE_V_VALID) { - hpte[0] &= ~HPTE_V_VALID; - rb = compute_tlbie_rb(v, hpte[1], pte_index); + u64 pte1; + + pte1 = be64_to_cpu(hpte[1]); + hpte[0] &= ~cpu_to_be64(HPTE_V_VALID); + rb = compute_tlbie_rb(v, pte1, pte_index); do_tlbies(kvm, &rb, 1, global_invalidates(kvm, flags), true); /* Read PTE low word after tlbie to get final R/C values */ - remove_revmap_chain(kvm, pte_index, rev, v, hpte[1]); + remove_revmap_chain(kvm, pte_index, rev, v, pte1); } r = rev->guest_rpte & ~HPTE_GR_RESERVED; note_hpte_modification(kvm, rev); @@ -514,12 +524,14 @@ long kvmppc_h_bulk_remove(struct kvm_vcpu *vcpu) { struct kvm *kvm = vcpu->kvm; unsigned long *args = &vcpu->arch.gpr[4]; - unsigned long *hp, *hptes[4], tlbrb[4]; + __be64 *hp, *hptes[4]; + unsigned long tlbrb[4]; long int i, j, k, n, found, indexes[4]; unsigned long flags, req, pte_index, rcbits; int global; long int ret = H_SUCCESS; struct revmap_entry *rev, *revs[4]; + u64 hp0; global = global_invalidates(kvm, 0); for (i = 0; i < 4 && ret == H_SUCCESS; ) { @@ -542,8 +554,7 @@ long kvmppc_h_bulk_remove(struct kvm_vcpu *vcpu) ret = H_PARAMETER; break; } - hp = (unsigned long *) - (kvm->arch.hpt_virt + (pte_index << 4)); + hp = (__be64 *) (kvm->arch.hpt_virt + (pte_index << 4)); /* to avoid deadlock, don't spin except for first */ if (!try_lock_hpte(hp, HPTE_V_HVLOCK)) { if (n) @@ -552,23 +563,24 @@ long kvmppc_h_bulk_remove(struct kvm_vcpu *vcpu) cpu_relax(); } found = 0; - if (hp[0] & (HPTE_V_ABSENT | HPTE_V_VALID)) { + hp0 = be64_to_cpu(hp[0]); + if (hp0 & (HPTE_V_ABSENT | HPTE_V_VALID)) { switch (flags & 3) { case 0: /* absolute */ found = 1; break; case 1: /* andcond */ - if (!(hp[0] & args[j + 1])) + if (!(hp0 & args[j + 1])) found = 1; break; case 2: /* AVPN */ - if ((hp[0] & ~0x7fUL) == args[j + 1]) + if ((hp0 & ~0x7fUL) == args[j + 1]) found = 1; break; } } if (!found) { - hp[0] &= ~HPTE_V_HVLOCK; + hp[0] &= ~cpu_to_be64(HPTE_V_HVLOCK); args[j] = ((0x90 | flags) << 56) + pte_index; continue; } @@ -577,7 +589,7 @@ long kvmppc_h_bulk_remove(struct kvm_vcpu *vcpu) rev = real_vmalloc_addr(&kvm->arch.revmap[pte_index]); note_hpte_modification(kvm, rev); - if (!(hp[0] & HPTE_V_VALID)) { + if (!(hp0 & HPTE_V_VALID)) { /* insert R and C bits from PTE */ rcbits = rev->guest_rpte & (HPTE_R_R|HPTE_R_C); args[j] |= rcbits << (56 - 5); @@ -585,8 +597,10 @@ long kvmppc_h_bulk_remove(struct kvm_vcpu *vcpu) continue; } - hp[0] &= ~HPTE_V_VALID; /* leave it locked */ - tlbrb[n] = compute_tlbie_rb(hp[0], hp[1], pte_index); + /* leave it locked */ + hp[0] &= ~cpu_to_be64(HPTE_V_VALID); + tlbrb[n] = compute_tlbie_rb(be64_to_cpu(hp[0]), + be64_to_cpu(hp[1]), pte_index); indexes[n] = j; hptes[n] = hp; revs[n] = rev; @@ -605,7 +619,8 @@ long kvmppc_h_bulk_remove(struct kvm_vcpu *vcpu) pte_index = args[j] & ((1ul << 56) - 1); hp = hptes[k]; rev = revs[k]; - remove_revmap_chain(kvm, pte_index, rev, hp[0], hp[1]); + remove_revmap_chain(kvm, pte_index, rev, + be64_to_cpu(hp[0]), be64_to_cpu(hp[1])); rcbits = rev->guest_rpte & (HPTE_R_R|HPTE_R_C); args[j] |= rcbits << (56 - 5); hp[0] = 0; @@ -620,23 +635,25 @@ long kvmppc_h_protect(struct kvm_vcpu *vcpu, unsigned long flags, unsigned long va) { struct kvm *kvm = vcpu->kvm; - unsigned long *hpte; + __be64 *hpte; struct revmap_entry *rev; unsigned long v, r, rb, mask, bits; + u64 pte; if (pte_index >= kvm->arch.hpt_npte) return H_PARAMETER; - hpte = (unsigned long *)(kvm->arch.hpt_virt + (pte_index << 4)); + hpte = (__be64 *)(kvm->arch.hpt_virt + (pte_index << 4)); while (!try_lock_hpte(hpte, HPTE_V_HVLOCK)) cpu_relax(); - if ((hpte[0] & (HPTE_V_ABSENT | HPTE_V_VALID)) == 0 || - ((flags & H_AVPN) && (hpte[0] & ~0x7fUL) != avpn)) { - hpte[0] &= ~HPTE_V_HVLOCK; + pte = be64_to_cpu(hpte[0]); + if ((pte & (HPTE_V_ABSENT | HPTE_V_VALID)) == 0 || + ((flags & H_AVPN) && (pte & ~0x7fUL) != avpn)) { + hpte[0] &= ~cpu_to_be64(HPTE_V_HVLOCK); return H_NOT_FOUND; } - v = hpte[0]; + v = pte; bits = (flags << 55) & HPTE_R_PP0; bits |= (flags << 48) & HPTE_R_KEY_HI; bits |= flags & (HPTE_R_PP | HPTE_R_N | HPTE_R_KEY_LO); @@ -650,12 +667,12 @@ long kvmppc_h_protect(struct kvm_vcpu *vcpu, unsigned long flags, rev->guest_rpte = r; note_hpte_modification(kvm, rev); } - r = (hpte[1] & ~mask) | bits; + r = (be64_to_cpu(hpte[1]) & ~mask) | bits; /* Update HPTE */ if (v & HPTE_V_VALID) { rb = compute_tlbie_rb(v, r, pte_index); - hpte[0] = v & ~HPTE_V_VALID; + hpte[0] = cpu_to_be64(v & ~HPTE_V_VALID); do_tlbies(kvm, &rb, 1, global_invalidates(kvm, flags), true); /* * If the host has this page as readonly but the guest @@ -681,9 +698,9 @@ long kvmppc_h_protect(struct kvm_vcpu *vcpu, unsigned long flags, } } } - hpte[1] = r; + hpte[1] = cpu_to_be64(r); eieio(); - hpte[0] = v & ~HPTE_V_HVLOCK; + hpte[0] = cpu_to_be64(v & ~HPTE_V_HVLOCK); asm volatile("ptesync" : : : "memory"); return H_SUCCESS; } @@ -692,7 +709,8 @@ long kvmppc_h_read(struct kvm_vcpu *vcpu, unsigned long flags, unsigned long pte_index) { struct kvm *kvm = vcpu->kvm; - unsigned long *hpte, v, r; + __be64 *hpte; + unsigned long v, r; int i, n = 1; struct revmap_entry *rev = NULL; @@ -704,9 +722,9 @@ long kvmppc_h_read(struct kvm_vcpu *vcpu, unsigned long flags, } rev = real_vmalloc_addr(&kvm->arch.revmap[pte_index]); for (i = 0; i < n; ++i, ++pte_index) { - hpte = (unsigned long *)(kvm->arch.hpt_virt + (pte_index << 4)); - v = hpte[0] & ~HPTE_V_HVLOCK; - r = hpte[1]; + hpte = (__be64 *)(kvm->arch.hpt_virt + (pte_index << 4)); + v = be64_to_cpu(hpte[0]) & ~HPTE_V_HVLOCK; + r = be64_to_cpu(hpte[1]); if (v & HPTE_V_ABSENT) { v &= ~HPTE_V_ABSENT; v |= HPTE_V_VALID; @@ -721,25 +739,27 @@ long kvmppc_h_read(struct kvm_vcpu *vcpu, unsigned long flags, return H_SUCCESS; } -void kvmppc_invalidate_hpte(struct kvm *kvm, unsigned long *hptep, +void kvmppc_invalidate_hpte(struct kvm *kvm, __be64 *hptep, unsigned long pte_index) { unsigned long rb; - hptep[0] &= ~HPTE_V_VALID; - rb = compute_tlbie_rb(hptep[0], hptep[1], pte_index); + hptep[0] &= ~cpu_to_be64(HPTE_V_VALID); + rb = compute_tlbie_rb(be64_to_cpu(hptep[0]), be64_to_cpu(hptep[1]), + pte_index); do_tlbies(kvm, &rb, 1, 1, true); } EXPORT_SYMBOL_GPL(kvmppc_invalidate_hpte); -void kvmppc_clear_ref_hpte(struct kvm *kvm, unsigned long *hptep, +void kvmppc_clear_ref_hpte(struct kvm *kvm, __be64 *hptep, unsigned long pte_index) { unsigned long rb; unsigned char rbyte; - rb = compute_tlbie_rb(hptep[0], hptep[1], pte_index); - rbyte = (hptep[1] & ~HPTE_R_R) >> 8; + rb = compute_tlbie_rb(be64_to_cpu(hptep[0]), be64_to_cpu(hptep[1]), + pte_index); + rbyte = (be64_to_cpu(hptep[1]) & ~HPTE_R_R) >> 8; /* modify only the second-last byte, which contains the ref bit */ *((char *)hptep + 14) = rbyte; do_tlbies(kvm, &rb, 1, 1, false); @@ -765,7 +785,7 @@ long kvmppc_hv_find_lock_hpte(struct kvm *kvm, gva_t eaddr, unsigned long slb_v, unsigned long somask; unsigned long vsid, hash; unsigned long avpn; - unsigned long *hpte; + __be64 *hpte; unsigned long mask, val; unsigned long v, r; @@ -797,11 +817,11 @@ long kvmppc_hv_find_lock_hpte(struct kvm *kvm, gva_t eaddr, unsigned long slb_v, val |= avpn; for (;;) { - hpte = (unsigned long *)(kvm->arch.hpt_virt + (hash << 7)); + hpte = (__be64 *)(kvm->arch.hpt_virt + (hash << 7)); for (i = 0; i < 16; i += 2) { /* Read the PTE racily */ - v = hpte[i] & ~HPTE_V_HVLOCK; + v = be64_to_cpu(hpte[i]) & ~HPTE_V_HVLOCK; /* Check valid/absent, hash, segment size and AVPN */ if (!(v & valid) || (v & mask) != val) @@ -810,8 +830,8 @@ long kvmppc_hv_find_lock_hpte(struct kvm *kvm, gva_t eaddr, unsigned long slb_v, /* Lock the PTE and read it under the lock */ while (!try_lock_hpte(&hpte[i], HPTE_V_HVLOCK)) cpu_relax(); - v = hpte[i] & ~HPTE_V_HVLOCK; - r = hpte[i+1]; + v = be64_to_cpu(hpte[i]) & ~HPTE_V_HVLOCK; + r = be64_to_cpu(hpte[i+1]); /* * Check the HPTE again, including large page size @@ -825,7 +845,7 @@ long kvmppc_hv_find_lock_hpte(struct kvm *kvm, gva_t eaddr, unsigned long slb_v, return (hash << 3) + (i >> 1); /* Unlock and move on */ - hpte[i] = v; + hpte[i] = cpu_to_be64(v); } if (val & HPTE_V_SECONDARY) @@ -854,7 +874,7 @@ long kvmppc_hpte_hv_fault(struct kvm_vcpu *vcpu, unsigned long addr, struct kvm *kvm = vcpu->kvm; long int index; unsigned long v, r, gr; - unsigned long *hpte; + __be64 *hpte; unsigned long valid; struct revmap_entry *rev; unsigned long pp, key; @@ -870,9 +890,9 @@ long kvmppc_hpte_hv_fault(struct kvm_vcpu *vcpu, unsigned long addr, return status; /* there really was no HPTE */ return 0; /* for prot fault, HPTE disappeared */ } - hpte = (unsigned long *)(kvm->arch.hpt_virt + (index << 4)); - v = hpte[0] & ~HPTE_V_HVLOCK; - r = hpte[1]; + hpte = (__be64 *)(kvm->arch.hpt_virt + (index << 4)); + v = be64_to_cpu(hpte[0]) & ~HPTE_V_HVLOCK; + r = be64_to_cpu(hpte[1]); rev = real_vmalloc_addr(&kvm->arch.revmap[index]); gr = rev->guest_rpte; diff --git a/arch/powerpc/kvm/book3s_hv_rmhandlers.S b/arch/powerpc/kvm/book3s_hv_rmhandlers.S index 868347ef09fd..855521ef04e8 100644 --- a/arch/powerpc/kvm/book3s_hv_rmhandlers.S +++ b/arch/powerpc/kvm/book3s_hv_rmhandlers.S @@ -32,10 +32,6 @@ #define VCPU_GPRS_TM(reg) (((reg) * ULONG_SIZE) + VCPU_GPR_TM) -#ifdef __LITTLE_ENDIAN__ -#error Need to fix lppaca and SLB shadow accesses in little endian mode -#endif - /* Values in HSTATE_NAPPING(r13) */ #define NAPPING_CEDE 1 #define NAPPING_NOVCPU 2 @@ -48,7 +44,7 @@ * * LR = return address to continue at after eventually re-enabling MMU */ -_GLOBAL(kvmppc_hv_entry_trampoline) +_GLOBAL_TOC(kvmppc_hv_entry_trampoline) mflr r0 std r0, PPC_LR_STKOFF(r1) stdu r1, -112(r1) @@ -595,9 +591,10 @@ kvmppc_got_guest: ld r3, VCPU_VPA(r4) cmpdi r3, 0 beq 25f - lwz r5, LPPACA_YIELDCOUNT(r3) + li r6, LPPACA_YIELDCOUNT + LWZX_BE r5, r3, r6 addi r5, r5, 1 - stw r5, LPPACA_YIELDCOUNT(r3) + STWX_BE r5, r3, r6 li r6, 1 stb r6, VCPU_VPA_DIRTY(r4) 25: @@ -671,9 +668,9 @@ END_FTR_SECTION_IFCLR(CPU_FTR_TM) mr r31, r4 addi r3, r31, VCPU_FPRS_TM - bl .load_fp_state + bl load_fp_state addi r3, r31, VCPU_VRS_TM - bl .load_vr_state + bl load_vr_state mr r4, r31 lwz r7, VCPU_VRSAVE_TM(r4) mtspr SPRN_VRSAVE, r7 @@ -1417,9 +1414,9 @@ END_FTR_SECTION_IFCLR(CPU_FTR_TM) /* Save FP/VSX. */ addi r3, r9, VCPU_FPRS_TM - bl .store_fp_state + bl store_fp_state addi r3, r9, VCPU_VRS_TM - bl .store_vr_state + bl store_vr_state mfspr r6, SPRN_VRSAVE stw r6, VCPU_VRSAVE_TM(r9) 1: @@ -1442,9 +1439,10 @@ END_FTR_SECTION_IFCLR(CPU_FTR_TM) ld r8, VCPU_VPA(r9) /* do they have a VPA? */ cmpdi r8, 0 beq 25f - lwz r3, LPPACA_YIELDCOUNT(r8) + li r4, LPPACA_YIELDCOUNT + LWZX_BE r3, r8, r4 addi r3, r3, 1 - stw r3, LPPACA_YIELDCOUNT(r8) + STWX_BE r3, r8, r4 li r3, 1 stb r3, VCPU_VPA_DIRTY(r9) 25: @@ -1757,8 +1755,10 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S) 33: ld r8,PACA_SLBSHADOWPTR(r13) .rept SLB_NUM_BOLTED - ld r5,SLBSHADOW_SAVEAREA(r8) - ld r6,SLBSHADOW_SAVEAREA+8(r8) + li r3, SLBSHADOW_SAVEAREA + LDX_BE r5, r8, r3 + addi r3, r3, 8 + LDX_BE r6, r8, r3 andis. r7,r5,SLB_ESID_V@h beq 1f slbmte r6,r5 @@ -1909,12 +1909,23 @@ hcall_try_real_mode: clrrdi r3,r3,2 cmpldi r3,hcall_real_table_end - hcall_real_table bge guest_exit_cont + /* See if this hcall is enabled for in-kernel handling */ + ld r4, VCPU_KVM(r9) + srdi r0, r3, 8 /* r0 = (r3 / 4) >> 6 */ + sldi r0, r0, 3 /* index into kvm->arch.enabled_hcalls[] */ + add r4, r4, r0 + ld r0, KVM_ENABLED_HCALLS(r4) + rlwinm r4, r3, 32-2, 0x3f /* r4 = (r3 / 4) & 0x3f */ + srd r0, r0, r4 + andi. r0, r0, 1 + beq guest_exit_cont + /* Get pointer to handler, if any, and call it */ LOAD_REG_ADDR(r4, hcall_real_table) lwax r3,r3,r4 cmpwi r3,0 beq guest_exit_cont - add r3,r3,r4 - mtctr r3 + add r12,r3,r4 + mtctr r12 mr r3,r9 /* get vcpu pointer */ ld r4,VCPU_GPR(R4)(r9) bctrl @@ -2031,6 +2042,7 @@ hcall_real_table: .long 0 /* 0x12c */ .long 0 /* 0x130 */ .long DOTSYM(kvmppc_h_set_xdabr) - hcall_real_table + .globl hcall_real_table_end hcall_real_table_end: ignore_hdec: @@ -2338,7 +2350,18 @@ kvmppc_read_intr: cmpdi r6, 0 beq- 1f lwzcix r0, r6, r7 - rlwinm. r3, r0, 0, 0xffffff + /* + * Save XIRR for later. Since we get in in reverse endian on LE + * systems, save it byte reversed and fetch it back in host endian. + */ + li r3, HSTATE_SAVED_XIRR + STWX_BE r0, r3, r13 +#ifdef __LITTLE_ENDIAN__ + lwz r3, HSTATE_SAVED_XIRR(r13) +#else + mr r3, r0 +#endif + rlwinm. r3, r3, 0, 0xffffff sync beq 1f /* if nothing pending in the ICP */ @@ -2370,10 +2393,9 @@ kvmppc_read_intr: 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 +42: /* It's not an IPI and it's for the host. We saved a copy of XIRR in + * the PACA earlier, it will be picked up by the host ICP driver */ - stw r0, HSTATE_SAVED_XIRR(r13) li r3, 1 b 1b @@ -2408,11 +2430,11 @@ END_FTR_SECTION_IFSET(CPU_FTR_VSX) mtmsrd r8 isync addi r3,r3,VCPU_FPRS - bl .store_fp_state + bl store_fp_state #ifdef CONFIG_ALTIVEC BEGIN_FTR_SECTION addi r3,r31,VCPU_VRS - bl .store_vr_state + bl store_vr_state END_FTR_SECTION_IFSET(CPU_FTR_ALTIVEC) #endif mfspr r6,SPRN_VRSAVE @@ -2444,11 +2466,11 @@ END_FTR_SECTION_IFSET(CPU_FTR_VSX) mtmsrd r8 isync addi r3,r4,VCPU_FPRS - bl .load_fp_state + bl load_fp_state #ifdef CONFIG_ALTIVEC BEGIN_FTR_SECTION addi r3,r31,VCPU_VRS - bl .load_vr_state + bl load_vr_state END_FTR_SECTION_IFSET(CPU_FTR_ALTIVEC) #endif lwz r7,VCPU_VRSAVE(r31) diff --git a/arch/powerpc/kvm/book3s_interrupts.S b/arch/powerpc/kvm/book3s_interrupts.S index e2c29e381dc7..d044b8b7c69d 100644 --- a/arch/powerpc/kvm/book3s_interrupts.S +++ b/arch/powerpc/kvm/book3s_interrupts.S @@ -25,7 +25,11 @@ #include <asm/exception-64s.h> #if defined(CONFIG_PPC_BOOK3S_64) +#if defined(_CALL_ELF) && _CALL_ELF == 2 +#define FUNC(name) name +#else #define FUNC(name) GLUE(.,name) +#endif #define GET_SHADOW_VCPU(reg) addi reg, r13, PACA_SVCPU #elif defined(CONFIG_PPC_BOOK3S_32) diff --git a/arch/powerpc/kvm/book3s_pr.c b/arch/powerpc/kvm/book3s_pr.c index 8eef1e519077..15fd6c25179c 100644 --- a/arch/powerpc/kvm/book3s_pr.c +++ b/arch/powerpc/kvm/book3s_pr.c @@ -71,6 +71,12 @@ static void kvmppc_core_vcpu_load_pr(struct kvm_vcpu *vcpu, int cpu) svcpu->in_use = 0; svcpu_put(svcpu); #endif + + /* Disable AIL if supported */ + if (cpu_has_feature(CPU_FTR_HVMODE) && + cpu_has_feature(CPU_FTR_ARCH_207S)) + mtspr(SPRN_LPCR, mfspr(SPRN_LPCR) & ~LPCR_AIL); + vcpu->cpu = smp_processor_id(); #ifdef CONFIG_PPC_BOOK3S_32 current->thread.kvm_shadow_vcpu = vcpu->arch.shadow_vcpu; @@ -91,6 +97,12 @@ static void kvmppc_core_vcpu_put_pr(struct kvm_vcpu *vcpu) kvmppc_giveup_ext(vcpu, MSR_FP | MSR_VEC | MSR_VSX); kvmppc_giveup_fac(vcpu, FSCR_TAR_LG); + + /* Enable AIL if supported */ + if (cpu_has_feature(CPU_FTR_HVMODE) && + cpu_has_feature(CPU_FTR_ARCH_207S)) + mtspr(SPRN_LPCR, mfspr(SPRN_LPCR) | LPCR_AIL_3); + vcpu->cpu = -1; } @@ -120,6 +132,14 @@ void kvmppc_copy_to_svcpu(struct kvmppc_book3s_shadow_vcpu *svcpu, #ifdef CONFIG_PPC_BOOK3S_64 svcpu->shadow_fscr = vcpu->arch.shadow_fscr; #endif + /* + * Now also save the current time base value. We use this + * to find the guest purr and spurr value. + */ + vcpu->arch.entry_tb = get_tb(); + vcpu->arch.entry_vtb = get_vtb(); + if (cpu_has_feature(CPU_FTR_ARCH_207S)) + vcpu->arch.entry_ic = mfspr(SPRN_IC); svcpu->in_use = true; } @@ -166,6 +186,14 @@ void kvmppc_copy_from_svcpu(struct kvm_vcpu *vcpu, #ifdef CONFIG_PPC_BOOK3S_64 vcpu->arch.shadow_fscr = svcpu->shadow_fscr; #endif + /* + * Update purr and spurr using time base on exit. + */ + vcpu->arch.purr += get_tb() - vcpu->arch.entry_tb; + vcpu->arch.spurr += get_tb() - vcpu->arch.entry_tb; + vcpu->arch.vtb += get_vtb() - vcpu->arch.entry_vtb; + if (cpu_has_feature(CPU_FTR_ARCH_207S)) + vcpu->arch.ic += mfspr(SPRN_IC) - vcpu->arch.entry_ic; svcpu->in_use = false; out: @@ -960,6 +988,7 @@ int kvmppc_handle_exit_pr(struct kvm_run *run, struct kvm_vcpu *vcpu, case BOOK3S_INTERRUPT_DECREMENTER: case BOOK3S_INTERRUPT_HV_DECREMENTER: case BOOK3S_INTERRUPT_DOORBELL: + case BOOK3S_INTERRUPT_H_DOORBELL: vcpu->stat.dec_exits++; r = RESUME_GUEST; break; @@ -1568,6 +1597,11 @@ static int kvmppc_core_init_vm_pr(struct kvm *kvm) { mutex_init(&kvm->arch.hpt_mutex); +#ifdef CONFIG_PPC_BOOK3S_64 + /* Start out with the default set of hcalls enabled */ + kvmppc_pr_init_default_hcalls(kvm); +#endif + if (firmware_has_feature(FW_FEATURE_SET_MODE)) { spin_lock(&kvm_global_user_count_lock); if (++kvm_global_user_count == 1) @@ -1636,6 +1670,9 @@ static struct kvmppc_ops kvm_ops_pr = { .emulate_mfspr = kvmppc_core_emulate_mfspr_pr, .fast_vcpu_kick = kvm_vcpu_kick, .arch_vm_ioctl = kvm_arch_vm_ioctl_pr, +#ifdef CONFIG_PPC_BOOK3S_64 + .hcall_implemented = kvmppc_hcall_impl_pr, +#endif }; diff --git a/arch/powerpc/kvm/book3s_pr_papr.c b/arch/powerpc/kvm/book3s_pr_papr.c index 52a63bfe3f07..6d0143fbeb63 100644 --- a/arch/powerpc/kvm/book3s_pr_papr.c +++ b/arch/powerpc/kvm/book3s_pr_papr.c @@ -40,8 +40,9 @@ static int kvmppc_h_pr_enter(struct kvm_vcpu *vcpu) { long flags = kvmppc_get_gpr(vcpu, 4); long pte_index = kvmppc_get_gpr(vcpu, 5); - unsigned long pteg[2 * 8]; - unsigned long pteg_addr, i, *hpte; + __be64 pteg[2 * 8]; + __be64 *hpte; + unsigned long pteg_addr, i; long int ret; i = pte_index & 7; @@ -93,8 +94,8 @@ static int kvmppc_h_pr_remove(struct kvm_vcpu *vcpu) pteg = get_pteg_addr(vcpu, pte_index); mutex_lock(&vcpu->kvm->arch.hpt_mutex); copy_from_user(pte, (void __user *)pteg, sizeof(pte)); - pte[0] = be64_to_cpu(pte[0]); - pte[1] = be64_to_cpu(pte[1]); + pte[0] = be64_to_cpu((__force __be64)pte[0]); + pte[1] = be64_to_cpu((__force __be64)pte[1]); ret = H_NOT_FOUND; if ((pte[0] & HPTE_V_VALID) == 0 || @@ -171,8 +172,8 @@ static int kvmppc_h_pr_bulk_remove(struct kvm_vcpu *vcpu) pteg = get_pteg_addr(vcpu, tsh & H_BULK_REMOVE_PTEX); copy_from_user(pte, (void __user *)pteg, sizeof(pte)); - pte[0] = be64_to_cpu(pte[0]); - pte[1] = be64_to_cpu(pte[1]); + pte[0] = be64_to_cpu((__force __be64)pte[0]); + pte[1] = be64_to_cpu((__force __be64)pte[1]); /* tsl = AVPN */ flags = (tsh & H_BULK_REMOVE_FLAGS) >> 26; @@ -211,8 +212,8 @@ static int kvmppc_h_pr_protect(struct kvm_vcpu *vcpu) pteg = get_pteg_addr(vcpu, pte_index); mutex_lock(&vcpu->kvm->arch.hpt_mutex); copy_from_user(pte, (void __user *)pteg, sizeof(pte)); - pte[0] = be64_to_cpu(pte[0]); - pte[1] = be64_to_cpu(pte[1]); + pte[0] = be64_to_cpu((__force __be64)pte[0]); + pte[1] = be64_to_cpu((__force __be64)pte[1]); ret = H_NOT_FOUND; if ((pte[0] & HPTE_V_VALID) == 0 || @@ -231,8 +232,8 @@ 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); - pte[0] = cpu_to_be64(pte[0]); - pte[1] = cpu_to_be64(pte[1]); + pte[0] = (__force u64)cpu_to_be64(pte[0]); + pte[1] = (__force u64)cpu_to_be64(pte[1]); copy_to_user((void __user *)pteg, pte, sizeof(pte)); ret = H_SUCCESS; @@ -266,6 +267,10 @@ static int kvmppc_h_pr_xics_hcall(struct kvm_vcpu *vcpu, u32 cmd) int kvmppc_h_pr(struct kvm_vcpu *vcpu, unsigned long cmd) { + if (cmd <= MAX_HCALL_OPCODE && + !test_bit(cmd/4, vcpu->kvm->arch.enabled_hcalls)) + return EMULATE_FAIL; + switch (cmd) { case H_ENTER: return kvmppc_h_pr_enter(vcpu); @@ -303,3 +308,61 @@ int kvmppc_h_pr(struct kvm_vcpu *vcpu, unsigned long cmd) return EMULATE_FAIL; } + +int kvmppc_hcall_impl_pr(unsigned long cmd) +{ + switch (cmd) { + case H_ENTER: + case H_REMOVE: + case H_PROTECT: + case H_BULK_REMOVE: + case H_PUT_TCE: + case H_CEDE: +#ifdef CONFIG_KVM_XICS + case H_XIRR: + case H_CPPR: + case H_EOI: + case H_IPI: + case H_IPOLL: + case H_XIRR_X: +#endif + return 1; + } + return 0; +} + +/* + * List of hcall numbers to enable by default. + * For compatibility with old userspace, we enable by default + * all hcalls that were implemented before the hcall-enabling + * facility was added. Note this list should not include H_RTAS. + */ +static unsigned int default_hcall_list[] = { + H_ENTER, + H_REMOVE, + H_PROTECT, + H_BULK_REMOVE, + H_PUT_TCE, + H_CEDE, +#ifdef CONFIG_KVM_XICS + H_XIRR, + H_CPPR, + H_EOI, + H_IPI, + H_IPOLL, + H_XIRR_X, +#endif + 0 +}; + +void kvmppc_pr_init_default_hcalls(struct kvm *kvm) +{ + int i; + unsigned int hcall; + + for (i = 0; default_hcall_list[i]; ++i) { + hcall = default_hcall_list[i]; + WARN_ON(!kvmppc_hcall_impl_pr(hcall)); + __set_bit(hcall / 4, kvm->arch.enabled_hcalls); + } +} diff --git a/arch/powerpc/kvm/book3s_rmhandlers.S b/arch/powerpc/kvm/book3s_rmhandlers.S index 9eec675220e6..16c4d88ba27d 100644 --- a/arch/powerpc/kvm/book3s_rmhandlers.S +++ b/arch/powerpc/kvm/book3s_rmhandlers.S @@ -36,7 +36,11 @@ #if defined(CONFIG_PPC_BOOK3S_64) +#if defined(_CALL_ELF) && _CALL_ELF == 2 +#define FUNC(name) name +#else #define FUNC(name) GLUE(.,name) +#endif #elif defined(CONFIG_PPC_BOOK3S_32) @@ -146,7 +150,7 @@ kvmppc_handler_skip_ins: * On entry, r4 contains the guest shadow MSR * MSR.EE has to be 0 when calling this function */ -_GLOBAL(kvmppc_entry_trampoline) +_GLOBAL_TOC(kvmppc_entry_trampoline) mfmsr r5 LOAD_REG_ADDR(r7, kvmppc_handler_trampoline_enter) toreal(r7) diff --git a/arch/powerpc/kvm/e500_emulate.c b/arch/powerpc/kvm/e500_emulate.c index 002d51764143..c99c40e9182a 100644 --- a/arch/powerpc/kvm/e500_emulate.c +++ b/arch/powerpc/kvm/e500_emulate.c @@ -250,6 +250,14 @@ int kvmppc_core_emulate_mtspr_e500(struct kvm_vcpu *vcpu, int sprn, ulong spr_va spr_val); break; + case SPRN_PWRMGTCR0: + /* + * Guest relies on host power management configurations + * Treat the request as a general store + */ + vcpu->arch.pwrmgtcr0 = spr_val; + break; + /* extra exceptions */ case SPRN_IVOR32: vcpu->arch.ivor[BOOKE_IRQPRIO_SPE_UNAVAIL] = spr_val; @@ -368,6 +376,10 @@ int kvmppc_core_emulate_mfspr_e500(struct kvm_vcpu *vcpu, int sprn, ulong *spr_v *spr_val = vcpu->arch.eptcfg; break; + case SPRN_PWRMGTCR0: + *spr_val = vcpu->arch.pwrmgtcr0; + break; + /* extra exceptions */ case SPRN_IVOR32: *spr_val = vcpu->arch.ivor[BOOKE_IRQPRIO_SPE_UNAVAIL]; diff --git a/arch/powerpc/kvm/e500_mmu_host.c b/arch/powerpc/kvm/e500_mmu_host.c index dd2cc03f406f..79677d76d1a4 100644 --- a/arch/powerpc/kvm/e500_mmu_host.c +++ b/arch/powerpc/kvm/e500_mmu_host.c @@ -107,11 +107,15 @@ static u32 get_host_mas0(unsigned long eaddr) { unsigned long flags; u32 mas0; + u32 mas4; local_irq_save(flags); mtspr(SPRN_MAS6, 0); + mas4 = mfspr(SPRN_MAS4); + mtspr(SPRN_MAS4, mas4 & ~MAS4_TLBSEL_MASK); asm volatile("tlbsx 0, %0" : : "b" (eaddr & ~CONFIG_PAGE_OFFSET)); mas0 = mfspr(SPRN_MAS0); + mtspr(SPRN_MAS4, mas4); local_irq_restore(flags); return mas0; diff --git a/arch/powerpc/kvm/e500mc.c b/arch/powerpc/kvm/e500mc.c index 17e456279224..690499d7669d 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); +static DEFINE_PER_CPU(struct kvm_vcpu *[KVMPPC_NR_LPIDS], last_vcpu_of_lpid); static void kvmppc_core_vcpu_load_e500mc(struct kvm_vcpu *vcpu, int cpu) { @@ -141,9 +141,9 @@ static void kvmppc_core_vcpu_load_e500mc(struct kvm_vcpu *vcpu, int cpu) mtspr(SPRN_GESR, vcpu->arch.shared->esr); if (vcpu->arch.oldpir != mfspr(SPRN_PIR) || - __get_cpu_var(last_vcpu_on_cpu) != vcpu) { + __get_cpu_var(last_vcpu_of_lpid)[vcpu->kvm->arch.lpid] != vcpu) { kvmppc_e500_tlbil_all(vcpu_e500); - __get_cpu_var(last_vcpu_on_cpu) = vcpu; + __get_cpu_var(last_vcpu_of_lpid)[vcpu->kvm->arch.lpid] = vcpu; } kvmppc_load_guest_fp(vcpu); diff --git a/arch/powerpc/kvm/powerpc.c b/arch/powerpc/kvm/powerpc.c index 61c738ab1283..7efc2b711404 100644 --- a/arch/powerpc/kvm/powerpc.c +++ b/arch/powerpc/kvm/powerpc.c @@ -387,6 +387,7 @@ int kvm_dev_ioctl_check_extension(long ext) case KVM_CAP_PPC_UNSET_IRQ: case KVM_CAP_PPC_IRQ_LEVEL: case KVM_CAP_ENABLE_CAP: + case KVM_CAP_ENABLE_CAP_VM: case KVM_CAP_ONE_REG: case KVM_CAP_IOEVENTFD: case KVM_CAP_DEVICE_CTRL: @@ -417,6 +418,7 @@ int kvm_dev_ioctl_check_extension(long ext) case KVM_CAP_PPC_ALLOC_HTAB: case KVM_CAP_PPC_RTAS: case KVM_CAP_PPC_FIXUP_HCALL: + case KVM_CAP_PPC_ENABLE_HCALL: #ifdef CONFIG_KVM_XICS case KVM_CAP_IRQ_XICS: #endif @@ -1099,6 +1101,42 @@ int kvm_vm_ioctl_irq_line(struct kvm *kvm, struct kvm_irq_level *irq_event, return 0; } + +static int kvm_vm_ioctl_enable_cap(struct kvm *kvm, + struct kvm_enable_cap *cap) +{ + int r; + + if (cap->flags) + return -EINVAL; + + switch (cap->cap) { +#ifdef CONFIG_KVM_BOOK3S_64_HANDLER + case KVM_CAP_PPC_ENABLE_HCALL: { + unsigned long hcall = cap->args[0]; + + r = -EINVAL; + if (hcall > MAX_HCALL_OPCODE || (hcall & 3) || + cap->args[1] > 1) + break; + if (!kvmppc_book3s_hcall_implemented(kvm, hcall)) + break; + if (cap->args[1]) + set_bit(hcall / 4, kvm->arch.enabled_hcalls); + else + clear_bit(hcall / 4, kvm->arch.enabled_hcalls); + r = 0; + break; + } +#endif + default: + r = -EINVAL; + break; + } + + return r; +} + long kvm_arch_vm_ioctl(struct file *filp, unsigned int ioctl, unsigned long arg) { @@ -1118,6 +1156,15 @@ long kvm_arch_vm_ioctl(struct file *filp, break; } + case KVM_ENABLE_CAP: + { + struct kvm_enable_cap cap; + r = -EFAULT; + if (copy_from_user(&cap, argp, sizeof(cap))) + goto out; + r = kvm_vm_ioctl_enable_cap(kvm, &cap); + break; + } #ifdef CONFIG_PPC_BOOK3S_64 case KVM_CREATE_SPAPR_TCE: { struct kvm_create_spapr_tce create_tce; diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h index e11d8f170a62..0418b746cb68 100644 --- a/include/uapi/linux/kvm.h +++ b/include/uapi/linux/kvm.h @@ -758,6 +758,7 @@ struct kvm_ppc_smmu_info { #define KVM_CAP_VM_ATTRIBUTES 101 #define KVM_CAP_ARM_PSCI_0_2 102 #define KVM_CAP_PPC_FIXUP_HCALL 103 +#define KVM_CAP_PPC_ENABLE_HCALL 104 #ifdef KVM_CAP_IRQ_ROUTING |