@@ -52,6 +52,7 @@ int create_hyp_io_mappings(void *from, void *to, phys_addr_t);
void free_boot_hyp_pgd(void);
void free_hyp_pgds(void);
+void stage2_unmap_vm(struct kvm *kvm);
int kvm_alloc_stage2_pgd(struct kvm *kvm);
void kvm_free_stage2_pgd(struct kvm *kvm);
int kvm_phys_addr_ioremap(struct kvm *kvm, phys_addr_t guest_ipa,
@@ -701,6 +701,13 @@ static int kvm_arch_vcpu_ioctl_vcpu_init(struct kvm_vcpu *vcpu,
if (ret)
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);
/*
@@ -611,6 +611,71 @@ 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.
@@ -83,6 +83,7 @@ int create_hyp_io_mappings(void *from, void *to, phys_addr_t);
void free_boot_hyp_pgd(void);
void free_hyp_pgds(void);
+void stage2_unmap_vm(struct kvm *kvm);
int kvm_alloc_stage2_pgd(struct kvm *kvm);
void kvm_free_stage2_pgd(struct kvm *kvm);
int kvm_phys_addr_ioremap(struct kvm *kvm, phys_addr_t guest_ipa,
Introduce a new function to unmap user RAM regions in the stage2 page tables. This is needed on reboot (or when the guest turns off the MMU) to ensure we fault in pages again and make the dcache, RAM, and icache coherent. Using unmap_stage2_range for the whole guest physical range does not work, because that unmaps IO regions (such as the GIC) which will not be recreated or in the best case faulted in on a page-by-page basis. Call this function on secondary and subsequent calls to the KVM_ARM_VCPU_INIT ioctl so that a reset VCPU will detect the guest Stage-1 MMU is off when faulting in pages and make the caches coherent. Signed-off-by: Christoffer Dall <christoffer.dall@linaro.org> --- arch/arm/include/asm/kvm_mmu.h | 1 + arch/arm/kvm/arm.c | 7 +++++ arch/arm/kvm/mmu.c | 65 ++++++++++++++++++++++++++++++++++++++++ arch/arm64/include/asm/kvm_mmu.h | 1 + 4 files changed, 74 insertions(+)