A device mapping is normally always mapped at Stage-2, since there
is very little gain in having it faulted in.
Nonetheless, it is possible to end-up in a situation where the device
mapping has been removed from Stage-2 (userspace munmaped the VFIO
region, and the MMU notifier did its job), but present in a userspace
mapping (userpace has mapped it back at the same address). In such
a situation, the device mapping will be demand-paged as the guest
performs memory accesses.
This requires to be careful when dealing with mapping size, cache
management, and to handle potential execution of a device mapping.
Reported-by: Alexandru Elisei <alexandru.elisei@arm.com>
Signed-off-by: Marc Zyngier <maz@kernel.org>
Tested-by: Alexandru Elisei <alexandru.elisei@arm.com>
Reviewed-by: James Morse <james.morse@arm.com>
Cc: stable@vger.kernel.org
Link: https://lore.kernel.org/r/20191211165651.7889-2-maz@kernel.org
#define KVM_S2PTE_FLAG_IS_IOMAP (1UL << 0)
#define KVM_S2_FLAG_LOGGING_ACTIVE (1UL << 1)
#define KVM_S2PTE_FLAG_IS_IOMAP (1UL << 0)
#define KVM_S2_FLAG_LOGGING_ACTIVE (1UL << 1)
+static bool is_iomap(unsigned long flags)
+{
+ return flags & KVM_S2PTE_FLAG_IS_IOMAP;
+}
+
static bool memslot_is_logging(struct kvm_memory_slot *memslot)
{
return memslot->dirty_bitmap && !(memslot->flags & KVM_MEM_READONLY);
static bool memslot_is_logging(struct kvm_memory_slot *memslot)
{
return memslot->dirty_bitmap && !(memslot->flags & KVM_MEM_READONLY);
vma_pagesize = vma_kernel_pagesize(vma);
if (logging_active ||
vma_pagesize = vma_kernel_pagesize(vma);
if (logging_active ||
+ (vma->vm_flags & VM_PFNMAP) ||
!fault_supports_stage2_huge_mapping(memslot, hva, vma_pagesize)) {
force_pte = true;
vma_pagesize = PAGE_SIZE;
!fault_supports_stage2_huge_mapping(memslot, hva, vma_pagesize)) {
force_pte = true;
vma_pagesize = PAGE_SIZE;
+ if (exec_fault && is_iomap(flags))
+ return -ENOEXEC;
+
spin_lock(&kvm->mmu_lock);
if (mmu_notifier_retry(kvm, mmu_seq))
goto out_unlock;
spin_lock(&kvm->mmu_lock);
if (mmu_notifier_retry(kvm, mmu_seq))
goto out_unlock;
if (writable)
kvm_set_pfn_dirty(pfn);
if (writable)
kvm_set_pfn_dirty(pfn);
- if (fault_status != FSC_PERM)
+ if (fault_status != FSC_PERM && !is_iomap(flags))
clean_dcache_guest_page(pfn, vma_pagesize);
if (exec_fault)
clean_dcache_guest_page(pfn, vma_pagesize);
if (exec_fault)
if (kvm_is_error_hva(hva) || (write_fault && !writable)) {
if (is_iabt) {
/* Prefetch Abort on I/O address */
if (kvm_is_error_hva(hva) || (write_fault && !writable)) {
if (is_iabt) {
/* Prefetch Abort on I/O address */
- kvm_inject_pabt(vcpu, kvm_vcpu_get_hfar(vcpu));
- ret = 1;
- goto out_unlock;
+ ret = -ENOEXEC;
+ goto out;
ret = user_mem_abort(vcpu, fault_ipa, memslot, hva, fault_status);
if (ret == 0)
ret = 1;
ret = user_mem_abort(vcpu, fault_ipa, memslot, hva, fault_status);
if (ret == 0)
ret = 1;
+out:
+ if (ret == -ENOEXEC) {
+ kvm_inject_pabt(vcpu, kvm_vcpu_get_hfar(vcpu));
+ ret = 1;
+ }
out_unlock:
srcu_read_unlock(&vcpu->kvm->srcu, idx);
return ret;
out_unlock:
srcu_read_unlock(&vcpu->kvm->srcu, idx);
return ret;