diff options
Diffstat (limited to 'arch/arm/kvm')
-rw-r--r-- | arch/arm/kvm/arm.c | 31 | ||||
-rw-r--r-- | arch/arm/kvm/guest.c | 1 | ||||
-rw-r--r-- | arch/arm/kvm/interrupts.S | 10 | ||||
-rw-r--r-- | arch/arm/kvm/interrupts_head.S | 20 | ||||
-rw-r--r-- | arch/arm/kvm/mmu.c | 100 |
5 files changed, 144 insertions, 18 deletions
diff --git a/arch/arm/kvm/arm.c b/arch/arm/kvm/arm.c index 7f35063c8882..23eda4c12251 100644 --- a/arch/arm/kvm/arm.c +++ b/arch/arm/kvm/arm.c @@ -213,6 +213,11 @@ struct kvm_vcpu *kvm_arch_vcpu_create(struct kvm *kvm, unsigned int id) int err; struct kvm_vcpu *vcpu; + if (irqchip_in_kernel(kvm) && vgic_initialized(kvm)) { + err = -EBUSY; + goto out; + } + vcpu = kmem_cache_zalloc(kvm_vcpu_cache, GFP_KERNEL); if (!vcpu) { err = -ENOMEM; @@ -419,6 +424,7 @@ static void update_vttbr(struct kvm *kvm) static int kvm_vcpu_first_run_init(struct kvm_vcpu *vcpu) { + struct kvm *kvm = vcpu->kvm; int ret; if (likely(vcpu->arch.has_run_once)) @@ -430,12 +436,20 @@ static int kvm_vcpu_first_run_init(struct kvm_vcpu *vcpu) * Initialize the VGIC before running a vcpu the first time on * this VM. */ - if (unlikely(!vgic_initialized(vcpu->kvm))) { - ret = kvm_vgic_init(vcpu->kvm); + if (unlikely(!vgic_initialized(kvm))) { + ret = kvm_vgic_init(kvm); if (ret) return ret; } + /* + * Enable the arch timers only if we have an in-kernel VGIC + * and it has been properly initialized, since we cannot handle + * interrupts from the virtual timer with a userspace gic. + */ + if (irqchip_in_kernel(kvm) && vgic_initialized(kvm)) + kvm_timer_enable(kvm); + return 0; } @@ -659,10 +673,21 @@ static int kvm_arch_vcpu_ioctl_vcpu_init(struct kvm_vcpu *vcpu, return ret; /* + * Ensure a rebooted VM will fault in RAM pages and detect if the + * guest MMU is turned off and flush the caches as needed. + */ + if (vcpu->arch.has_run_once) + stage2_unmap_vm(vcpu->kvm); + + vcpu_reset_hcr(vcpu); + + /* * Handle the "start in power-off" case by marking the VCPU as paused. */ - if (__test_and_clear_bit(KVM_ARM_VCPU_POWER_OFF, vcpu->arch.features)) + if (test_bit(KVM_ARM_VCPU_POWER_OFF, vcpu->arch.features)) vcpu->arch.pause = true; + else + vcpu->arch.pause = false; return 0; } diff --git a/arch/arm/kvm/guest.c b/arch/arm/kvm/guest.c index cc0b78769bd8..8c97208b9b97 100644 --- a/arch/arm/kvm/guest.c +++ b/arch/arm/kvm/guest.c @@ -38,7 +38,6 @@ struct kvm_stats_debugfs_item debugfs_entries[] = { int kvm_arch_vcpu_setup(struct kvm_vcpu *vcpu) { - vcpu->arch.hcr = HCR_GUEST_MASK; return 0; } diff --git a/arch/arm/kvm/interrupts.S b/arch/arm/kvm/interrupts.S index 01dcb0e752d9..d66d608f7ce7 100644 --- a/arch/arm/kvm/interrupts.S +++ b/arch/arm/kvm/interrupts.S @@ -159,13 +159,9 @@ __kvm_vcpu_return: @ Don't trap coprocessor accesses for host kernel set_hstr vmexit set_hdcr vmexit - set_hcptr vmexit, (HCPTR_TTA | HCPTR_TCP(10) | HCPTR_TCP(11)) + set_hcptr vmexit, (HCPTR_TTA | HCPTR_TCP(10) | HCPTR_TCP(11)), after_vfp_restore #ifdef CONFIG_VFPv3 - @ Save floating point registers we if let guest use them. - tst r2, #(HCPTR_TCP(10) | HCPTR_TCP(11)) - bne after_vfp_restore - @ Switch VFP/NEON hardware state to the host's add r7, vcpu, #VCPU_VFP_GUEST store_vfp_state r7 @@ -177,6 +173,8 @@ after_vfp_restore: @ Restore FPEXC_EN which we clobbered on entry pop {r2} VFPFMXR FPEXC, r2 +#else +after_vfp_restore: #endif @ Reset Hyp-role @@ -472,7 +470,7 @@ switch_to_guest_vfp: push {r3-r7} @ NEON/VFP used. Turn on VFP access. - set_hcptr vmexit, (HCPTR_TCP(10) | HCPTR_TCP(11)) + set_hcptr vmtrap, (HCPTR_TCP(10) | HCPTR_TCP(11)) @ Switch VFP/NEON hardware state to the guest's add r7, r0, #VCPU_VFP_HOST diff --git a/arch/arm/kvm/interrupts_head.S b/arch/arm/kvm/interrupts_head.S index 98c8c5b9a87f..f8f322102989 100644 --- a/arch/arm/kvm/interrupts_head.S +++ b/arch/arm/kvm/interrupts_head.S @@ -592,8 +592,13 @@ ARM_BE8(rev r6, r6 ) .endm /* Configures the HCPTR (Hyp Coprocessor Trap Register) on entry/return - * (hardware reset value is 0). Keep previous value in r2. */ -.macro set_hcptr operation, mask + * (hardware reset value is 0). Keep previous value in r2. + * An ISB is emited on vmexit/vmtrap, but executed on vmexit only if + * VFP wasn't already enabled (always executed on vmtrap). + * If a label is specified with vmexit, it is branched to if VFP wasn't + * enabled. + */ +.macro set_hcptr operation, mask, label = none mrc p15, 4, r2, c1, c1, 2 ldr r3, =\mask .if \operation == vmentry @@ -602,6 +607,17 @@ ARM_BE8(rev r6, r6 ) bic r3, r2, r3 @ Don't trap defined coproc-accesses .endif mcr p15, 4, r3, c1, c1, 2 + .if \operation != vmentry + .if \operation == vmexit + tst r2, #(HCPTR_TCP(10) | HCPTR_TCP(11)) + beq 1f + .endif + isb + .if \label != none + b \label + .endif +1: + .endif .endm /* Configures the HDCR (Hyp Debug Configuration Register) on entry/return diff --git a/arch/arm/kvm/mmu.c b/arch/arm/kvm/mmu.c index eea03069161b..9bd826ce3897 100644 --- a/arch/arm/kvm/mmu.c +++ b/arch/arm/kvm/mmu.c @@ -194,10 +194,11 @@ static void unmap_range(struct kvm *kvm, pgd_t *pgdp, phys_addr_t addr = start, end = start + size; phys_addr_t next; - pgd = pgdp + pgd_index(addr); + pgd = pgdp + kvm_pgd_index(addr); do { next = kvm_pgd_addr_end(addr, end); - unmap_puds(kvm, pgd, addr, next); + if (!pgd_none(*pgd)) + unmap_puds(kvm, pgd, addr, next); } while (pgd++, addr = next, addr != end); } @@ -263,7 +264,7 @@ static void stage2_flush_memslot(struct kvm *kvm, phys_addr_t next; pgd_t *pgd; - pgd = kvm->arch.pgd + pgd_index(addr); + pgd = kvm->arch.pgd + kvm_pgd_index(addr); do { next = kvm_pgd_addr_end(addr, end); stage2_flush_puds(kvm, pgd, addr, next); @@ -555,6 +556,71 @@ static void unmap_stage2_range(struct kvm *kvm, phys_addr_t start, u64 size) unmap_range(kvm, kvm->arch.pgd, start, size); } +static void stage2_unmap_memslot(struct kvm *kvm, + struct kvm_memory_slot *memslot) +{ + hva_t hva = memslot->userspace_addr; + phys_addr_t addr = memslot->base_gfn << PAGE_SHIFT; + phys_addr_t size = PAGE_SIZE * memslot->npages; + hva_t reg_end = hva + size; + + /* + * A memory region could potentially cover multiple VMAs, and any holes + * between them, so iterate over all of them to find out if we should + * unmap any of them. + * + * +--------------------------------------------+ + * +---------------+----------------+ +----------------+ + * | : VMA 1 | VMA 2 | | VMA 3 : | + * +---------------+----------------+ +----------------+ + * | memory region | + * +--------------------------------------------+ + */ + do { + struct vm_area_struct *vma = find_vma(current->mm, hva); + hva_t vm_start, vm_end; + + if (!vma || vma->vm_start >= reg_end) + break; + + /* + * Take the intersection of this VMA with the memory region + */ + vm_start = max(hva, vma->vm_start); + vm_end = min(reg_end, vma->vm_end); + + if (!(vma->vm_flags & VM_PFNMAP)) { + gpa_t gpa = addr + (vm_start - memslot->userspace_addr); + unmap_stage2_range(kvm, gpa, vm_end - vm_start); + } + hva = vm_end; + } while (hva < reg_end); +} + +/** + * stage2_unmap_vm - Unmap Stage-2 RAM mappings + * @kvm: The struct kvm pointer + * + * Go through the memregions and unmap any reguler RAM + * backing memory already mapped to the VM. + */ +void stage2_unmap_vm(struct kvm *kvm) +{ + struct kvm_memslots *slots; + struct kvm_memory_slot *memslot; + int idx; + + idx = srcu_read_lock(&kvm->srcu); + spin_lock(&kvm->mmu_lock); + + slots = kvm_memslots(kvm); + kvm_for_each_memslot(memslot, slots) + stage2_unmap_memslot(kvm, memslot); + + spin_unlock(&kvm->mmu_lock); + srcu_read_unlock(&kvm->srcu, idx); +} + /** * kvm_free_stage2_pgd - free all stage-2 tables * @kvm: The KVM struct pointer for the VM. @@ -583,7 +649,7 @@ static pmd_t *stage2_get_pmd(struct kvm *kvm, struct kvm_mmu_memory_cache *cache pud_t *pud; pmd_t *pmd; - pgd = kvm->arch.pgd + pgd_index(addr); + pgd = kvm->arch.pgd + kvm_pgd_index(addr); pud = pud_offset(pgd, addr); if (pud_none(*pud)) { if (!cache) @@ -754,6 +820,11 @@ static bool kvm_is_write_fault(struct kvm_vcpu *vcpu) return kvm_vcpu_dabt_iswrite(vcpu); } +static bool kvm_is_device_pfn(unsigned long pfn) +{ + return !pfn_valid(pfn); +} + static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa, struct kvm_memory_slot *memslot, unsigned long hva, unsigned long fault_status) @@ -777,6 +848,12 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa, /* Let's check if we will get back a huge page backed by hugetlbfs */ down_read(¤t->mm->mmap_sem); vma = find_vma_intersection(current->mm, hva, hva + 1); + if (unlikely(!vma)) { + kvm_err("Failed to find VMA for hva 0x%lx\n", hva); + up_read(¤t->mm->mmap_sem); + return -EFAULT; + } + if (is_vm_hugetlb_page(vma)) { hugetlb = true; gfn = (fault_ipa & PMD_MASK) >> PAGE_SHIFT; @@ -817,7 +894,7 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa, if (is_error_pfn(pfn)) return -EFAULT; - if (kvm_is_mmio_pfn(pfn)) + if (kvm_is_device_pfn(pfn)) mem_type = PAGE_S2_DEVICE; spin_lock(&kvm->mmu_lock); @@ -843,7 +920,7 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa, } coherent_cache_guest_page(vcpu, hva, PAGE_SIZE); ret = stage2_set_pte(kvm, memcache, fault_ipa, &new_pte, - mem_type == PAGE_S2_DEVICE); + pgprot_val(mem_type) == pgprot_val(PAGE_S2_DEVICE)); } @@ -916,6 +993,9 @@ int kvm_handle_guest_abort(struct kvm_vcpu *vcpu, struct kvm_run *run) goto out_unlock; } + /* Userspace should not be able to register out-of-bounds IPAs */ + VM_BUG_ON(fault_ipa >= KVM_PHYS_SIZE); + ret = user_mem_abort(vcpu, fault_ipa, memslot, hva, fault_status); if (ret == 0) ret = 1; @@ -1140,6 +1220,14 @@ int kvm_arch_prepare_memory_region(struct kvm *kvm, struct kvm_userspace_memory_region *mem, enum kvm_mr_change change) { + /* + * Prevent userspace from creating a memory region outside of the IPA + * space addressable by the KVM guest IPA space. + */ + if (memslot->base_gfn + memslot->npages >= + (KVM_PHYS_SIZE >> PAGE_SHIFT)) + return -EFAULT; + return 0; } |