[PATCH v2 6/6] arm/arm64: KVM: Introduce stage2_unmap_vm

[marc.zyngier@arm.com (Marc Zyngier)]

On 03/12/14 21:18, Christoffer Dall wrote:
> 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(+)
> 
> diff --git a/arch/arm/include/asm/kvm_mmu.h b/arch/arm/include/asm/kvm_mmu.h
> index acb0d57..4654c42 100644
> --- a/arch/arm/include/asm/kvm_mmu.h
> +++ b/arch/arm/include/asm/kvm_mmu.h
> @@ -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,
> diff --git a/arch/arm/kvm/arm.c b/arch/arm/kvm/arm.c
> index 4043769..da87c07 100644
> --- a/arch/arm/kvm/arm.c
> +++ b/arch/arm/kvm/arm.c
> @@ -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);
>  
>  	/*
> diff --git a/arch/arm/kvm/mmu.c b/arch/arm/kvm/mmu.c
> index 57a403a..b1f3c9a 100644
> --- a/arch/arm/kvm/mmu.c
> +++ b/arch/arm/kvm/mmu.c
> @@ -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.
> diff --git a/arch/arm64/include/asm/kvm_mmu.h b/arch/arm64/include/asm/kvm_mmu.h
> index 0caf7a5..061fed7 100644
> --- a/arch/arm64/include/asm/kvm_mmu.h
> +++ b/arch/arm64/include/asm/kvm_mmu.h
> @@ -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,
> 

Acked-by: Marc Zyngier <marc.zyngier@arm.com>

	M.
-- 
Jazz is not dead. It just smells funny...