From 07a9748c78cfc39b54f06125a216b67b9c8f09ed Mon Sep 17 00:00:00 2001 From: Ard Biesheuvel Date: Mon, 10 Nov 2014 08:33:55 +0000 Subject: arm/arm64: kvm: drop inappropriate use of kvm_is_mmio_pfn() Instead of using kvm_is_mmio_pfn() to decide whether a host region should be stage 2 mapped with device attributes, add a new static function kvm_is_device_pfn() that disregards RAM pages with the reserved bit set, as those should usually not be mapped as device memory. Signed-off-by: Ard Biesheuvel Signed-off-by: Marc Zyngier --- arch/arm/kvm/mmu.c | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) (limited to 'arch/arm/kvm/mmu.c') diff --git a/arch/arm/kvm/mmu.c b/arch/arm/kvm/mmu.c index 57a403a5c22b..b007438242e2 100644 --- a/arch/arm/kvm/mmu.c +++ b/arch/arm/kvm/mmu.c @@ -834,6 +834,11 @@ 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) @@ -904,7 +909,7 @@ 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); -- cgit From 840f4bfbe03f1ce94ade8fdf84e8cd925ef15a48 Mon Sep 17 00:00:00 2001 From: Laszlo Ersek Date: Mon, 17 Nov 2014 14:58:52 +0000 Subject: arm, arm64: KVM: allow forced dcache flush on page faults To allow handling of incoherent memslots in a subsequent patch, this patch adds a paramater 'ipa_uncached' to cache_coherent_guest_page() so that we can instruct it to flush the page's contents to DRAM even if the guest has caching globally enabled. Signed-off-by: Laszlo Ersek Signed-off-by: Ard Biesheuvel Signed-off-by: Marc Zyngier --- arch/arm/kvm/mmu.c | 9 +++++++-- 1 file changed, 7 insertions(+), 2 deletions(-) (limited to 'arch/arm/kvm/mmu.c') diff --git a/arch/arm/kvm/mmu.c b/arch/arm/kvm/mmu.c index b007438242e2..cb924c6d56a6 100644 --- a/arch/arm/kvm/mmu.c +++ b/arch/arm/kvm/mmu.c @@ -852,6 +852,7 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa, struct vm_area_struct *vma; pfn_t pfn; pgprot_t mem_type = PAGE_S2; + bool fault_ipa_uncached; write_fault = kvm_is_write_fault(vcpu); if (fault_status == FSC_PERM && !write_fault) { @@ -918,6 +919,8 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa, if (!hugetlb && !force_pte) hugetlb = transparent_hugepage_adjust(&pfn, &fault_ipa); + fault_ipa_uncached = false; + if (hugetlb) { pmd_t new_pmd = pfn_pmd(pfn, mem_type); new_pmd = pmd_mkhuge(new_pmd); @@ -925,7 +928,8 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa, kvm_set_s2pmd_writable(&new_pmd); kvm_set_pfn_dirty(pfn); } - coherent_cache_guest_page(vcpu, hva & PMD_MASK, PMD_SIZE); + coherent_cache_guest_page(vcpu, hva & PMD_MASK, PMD_SIZE, + fault_ipa_uncached); ret = stage2_set_pmd_huge(kvm, memcache, fault_ipa, &new_pmd); } else { pte_t new_pte = pfn_pte(pfn, mem_type); @@ -933,7 +937,8 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa, kvm_set_s2pte_writable(&new_pte); kvm_set_pfn_dirty(pfn); } - coherent_cache_guest_page(vcpu, hva, PAGE_SIZE); + coherent_cache_guest_page(vcpu, hva, PAGE_SIZE, + fault_ipa_uncached); ret = stage2_set_pte(kvm, memcache, fault_ipa, &new_pte, pgprot_val(mem_type) == pgprot_val(PAGE_S2_DEVICE)); } -- cgit From 849260c72c6b8bd53850cb00b80027db3a273c2c Mon Sep 17 00:00:00 2001 From: Ard Biesheuvel Date: Mon, 17 Nov 2014 14:58:53 +0000 Subject: arm, arm64: KVM: handle potential incoherency of readonly memslots Readonly memslots are often used to implement emulation of ROMs and NOR flashes, in which case the guest may legally map these regions as uncached. To deal with the incoherency associated with uncached guest mappings, treat all readonly memslots as incoherent, and ensure that pages that belong to regions tagged as such are flushed to DRAM before being passed to the guest. Signed-off-by: Ard Biesheuvel Signed-off-by: Marc Zyngier --- arch/arm/kvm/mmu.c | 20 +++++++++++++++----- 1 file changed, 15 insertions(+), 5 deletions(-) (limited to 'arch/arm/kvm/mmu.c') diff --git a/arch/arm/kvm/mmu.c b/arch/arm/kvm/mmu.c index cb924c6d56a6..f2a9874ff5cb 100644 --- a/arch/arm/kvm/mmu.c +++ b/arch/arm/kvm/mmu.c @@ -919,7 +919,7 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa, if (!hugetlb && !force_pte) hugetlb = transparent_hugepage_adjust(&pfn, &fault_ipa); - fault_ipa_uncached = false; + fault_ipa_uncached = memslot->flags & KVM_MEMSLOT_INCOHERENT; if (hugetlb) { pmd_t new_pmd = pfn_pmd(pfn, mem_type); @@ -1298,11 +1298,12 @@ int kvm_arch_prepare_memory_region(struct kvm *kvm, hva = vm_end; } while (hva < reg_end); - if (ret) { - spin_lock(&kvm->mmu_lock); + spin_lock(&kvm->mmu_lock); + if (ret) unmap_stage2_range(kvm, mem->guest_phys_addr, mem->memory_size); - spin_unlock(&kvm->mmu_lock); - } + else + stage2_flush_memslot(kvm, memslot); + spin_unlock(&kvm->mmu_lock); return ret; } @@ -1314,6 +1315,15 @@ void kvm_arch_free_memslot(struct kvm *kvm, struct kvm_memory_slot *free, int kvm_arch_create_memslot(struct kvm *kvm, struct kvm_memory_slot *slot, unsigned long npages) { + /* + * Readonly memslots are not incoherent with the caches by definition, + * but in practice, they are used mostly to emulate ROMs or NOR flashes + * that the guest may consider devices and hence map as uncached. + * To prevent incoherency issues in these cases, tag all readonly + * regions as incoherent. + */ + if (slot->flags & KVM_MEM_READONLY) + slot->flags |= KVM_MEMSLOT_INCOHERENT; return 0; } -- cgit From 957db105c99792ae8ef61ffc9ae77d910f6471da Mon Sep 17 00:00:00 2001 From: Christoffer Dall Date: Thu, 27 Nov 2014 10:35:03 +0100 Subject: arm/arm64: KVM: Introduce stage2_unmap_vm 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. Acked-by: Marc Zyngier Signed-off-by: Christoffer Dall --- arch/arm/kvm/mmu.c | 65 ++++++++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 65 insertions(+) (limited to 'arch/arm/kvm/mmu.c') diff --git a/arch/arm/kvm/mmu.c b/arch/arm/kvm/mmu.c index f2a9874ff5cb..3756dd3e85c2 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. -- cgit