@@ -591,4 +591,10 @@ static __always_inline void kvm_incr_pc(struct kvm_vcpu *vcpu)
vcpu->arch.flags |= KVM_ARM64_INCREMENT_PC;
}
+static inline bool kvm_is_shadow_s2_fault(struct kvm_vcpu *vcpu)
+{
+ return (vcpu->arch.hw_mmu != &vcpu->kvm->arch.mmu &&
+ vcpu->arch.hw_mmu->nested_stage2_enabled);
+}
+
#endif /* __ARM64_KVM_EMULATE_H__ */
@@ -78,9 +78,27 @@ struct kvm_s2_trans {
u64 upper_attr;
};
+static inline phys_addr_t kvm_s2_trans_output(struct kvm_s2_trans *trans)
+{
+ return trans->output;
+}
+
+static inline unsigned long kvm_s2_trans_size(struct kvm_s2_trans *trans)
+{
+ return trans->block_size;
+}
+
+static inline u32 kvm_s2_trans_esr(struct kvm_s2_trans *trans)
+{
+ return trans->esr;
+}
+
extern int kvm_walk_nested_s2(struct kvm_vcpu *vcpu, phys_addr_t gipa,
struct kvm_s2_trans *result);
+extern int kvm_s2_handle_perm_fault(struct kvm_vcpu *vcpu,
+ struct kvm_s2_trans *trans);
+extern int kvm_inject_s2_fault(struct kvm_vcpu *vcpu, u64 esr_el2);
int handle_wfx_nested(struct kvm_vcpu *vcpu, bool is_wfe);
extern bool __forward_traps(struct kvm_vcpu *vcpu, unsigned int reg,
u64 control_bit);
@@ -796,7 +796,7 @@ static bool fault_supports_stage2_huge_mapping(struct kvm_memory_slot *memslot,
static unsigned long
transparent_hugepage_adjust(struct kvm_memory_slot *memslot,
unsigned long hva, kvm_pfn_t *pfnp,
- phys_addr_t *ipap)
+ phys_addr_t *ipap, phys_addr_t *fault_ipap)
{
kvm_pfn_t pfn = *pfnp;
@@ -825,6 +825,7 @@ transparent_hugepage_adjust(struct kvm_memory_slot *memslot,
* to PG_head and switch the pfn from a tail page to the head
* page accordingly.
*/
+ *fault_ipap &= PMD_MASK;
*ipap &= PMD_MASK;
kvm_release_pfn_clean(pfn);
pfn &= ~(PTRS_PER_PMD - 1);
@@ -839,14 +840,16 @@ transparent_hugepage_adjust(struct kvm_memory_slot *memslot,
}
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)
+ struct kvm_s2_trans *nested,
+ struct kvm_memory_slot *memslot,
+ unsigned long hva, unsigned long fault_status)
{
int ret = 0;
- bool write_fault, writable, force_pte = false;
+ bool write_fault, writable;
bool exec_fault;
bool device = false;
unsigned long mmu_seq;
+ phys_addr_t ipa = fault_ipa;
struct kvm *kvm = vcpu->kvm;
struct kvm_mmu_memory_cache *memcache = &vcpu->arch.mmu_page_cache;
struct vm_area_struct *vma;
@@ -858,6 +861,7 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
unsigned long vma_pagesize, fault_granule;
enum kvm_pgtable_prot prot = KVM_PGTABLE_PROT_R;
struct kvm_pgtable *pgt;
+ unsigned long max_map_size = PUD_SIZE;
fault_granule = 1UL << ARM64_HW_PGTABLE_LEVEL_SHIFT(fault_level);
write_fault = kvm_is_write_fault(vcpu);
@@ -885,7 +889,7 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
if (logging_active ||
(vma->vm_flags & VM_PFNMAP)) {
- force_pte = true;
+ max_map_size = vma_pagesize = PAGE_SIZE;
vma_shift = PAGE_SHIFT;
}
@@ -905,7 +909,7 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
fallthrough;
case CONT_PTE_SHIFT:
vma_shift = PAGE_SHIFT;
- force_pte = true;
+ max_map_size = PAGE_SIZE;
fallthrough;
case PAGE_SHIFT:
break;
@@ -914,10 +918,25 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
}
vma_pagesize = 1UL << vma_shift;
+
+ if (kvm_is_shadow_s2_fault(vcpu)) {
+ ipa = kvm_s2_trans_output(nested);
+
+ /*
+ * If we're about to create a shadow stage 2 entry, then we
+ * can only create a block mapping if the guest stage 2 page
+ * table uses at least as big a mapping.
+ */
+ max_map_size = min(kvm_s2_trans_size(nested), max_map_size);
+ }
+
+ vma_pagesize = min(vma_pagesize, max_map_size);
+
if (vma_pagesize == PMD_SIZE || vma_pagesize == PUD_SIZE)
fault_ipa &= ~(vma_pagesize - 1);
- gfn = fault_ipa >> PAGE_SHIFT;
+ gfn = ipa >> PAGE_SHIFT;
+
mmap_read_unlock(current->mm);
/*
@@ -960,7 +979,7 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
if (kvm_is_device_pfn(pfn)) {
device = true;
- force_pte = true;
+ max_map_size = PAGE_SIZE;
} else if (logging_active && !write_fault) {
/*
* Only actually map the page as writable if this was a write
@@ -981,9 +1000,9 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
* If we are not forced to use page mapping, check if we are
* backed by a THP and thus use block mapping if possible.
*/
- if (vma_pagesize == PAGE_SIZE && !force_pte)
- vma_pagesize = transparent_hugepage_adjust(memslot, hva,
- &pfn, &fault_ipa);
+ if (vma_pagesize == PAGE_SIZE && max_map_size >= PMD_SIZE)
+ vma_pagesize = transparent_hugepage_adjust(memslot, hva, &pfn,
+ &ipa, &fault_ipa);
if (writable)
prot |= KVM_PGTABLE_PROT_W;
@@ -1059,8 +1078,10 @@ static void handle_access_fault(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa)
int kvm_handle_guest_abort(struct kvm_vcpu *vcpu)
{
unsigned long fault_status;
- phys_addr_t fault_ipa;
+ phys_addr_t fault_ipa; /* The address we faulted on */
+ phys_addr_t ipa; /* Always the IPA in the L1 guest phys space */
struct kvm_memory_slot *memslot;
+ struct kvm_s2_trans nested_trans;
unsigned long hva;
bool is_iabt, write_fault, writable;
gfn_t gfn;
@@ -1068,7 +1089,7 @@ int kvm_handle_guest_abort(struct kvm_vcpu *vcpu)
fault_status = kvm_vcpu_trap_get_fault_type(vcpu);
- fault_ipa = kvm_vcpu_get_fault_ipa(vcpu);
+ ipa = fault_ipa = kvm_vcpu_get_fault_ipa(vcpu);
is_iabt = kvm_vcpu_trap_is_iabt(vcpu);
/* Synchronous External Abort? */
@@ -1089,6 +1110,12 @@ int kvm_handle_guest_abort(struct kvm_vcpu *vcpu)
/* Check the stage-2 fault is trans. fault or write fault */
if (fault_status != FSC_FAULT && fault_status != FSC_PERM &&
fault_status != FSC_ACCESS) {
+ /*
+ * We must never see an address size fault on shadow stage 2
+ * page table walk, because we would have injected an addr
+ * size fault when we walked the nested s2 page and not
+ * create the shadow entry.
+ */
kvm_err("Unsupported FSC: EC=%#x xFSC=%#lx ESR_EL2=%#lx\n",
kvm_vcpu_trap_get_class(vcpu),
(unsigned long)kvm_vcpu_trap_get_fault(vcpu),
@@ -1098,7 +1125,36 @@ int kvm_handle_guest_abort(struct kvm_vcpu *vcpu)
idx = srcu_read_lock(&vcpu->kvm->srcu);
- gfn = fault_ipa >> PAGE_SHIFT;
+ /*
+ * We may have faulted on a shadow stage 2 page table if we are
+ * running a nested guest. In this case, we have to resolve the L2
+ * IPA to the L1 IPA first, before knowing what kind of memory should
+ * back the L1 IPA.
+ *
+ * If the shadow stage 2 page table walk faults, then we simply inject
+ * this to the guest and carry on.
+ */
+ if (kvm_is_shadow_s2_fault(vcpu)) {
+ u32 esr;
+
+ ret = kvm_walk_nested_s2(vcpu, fault_ipa, &nested_trans);
+ esr = kvm_s2_trans_esr(&nested_trans);
+ if (esr)
+ kvm_inject_s2_fault(vcpu, esr);
+ if (ret)
+ goto out_unlock;
+
+ ret = kvm_s2_handle_perm_fault(vcpu, &nested_trans);
+ esr = kvm_s2_trans_esr(&nested_trans);
+ if (esr)
+ kvm_inject_s2_fault(vcpu, esr);
+ if (ret)
+ goto out_unlock;
+
+ ipa = kvm_s2_trans_output(&nested_trans);
+ }
+
+ gfn = ipa >> PAGE_SHIFT;
memslot = gfn_to_memslot(vcpu->kvm, gfn);
hva = gfn_to_hva_memslot_prot(memslot, gfn, &writable);
write_fault = kvm_is_write_fault(vcpu);
@@ -1142,13 +1198,13 @@ int kvm_handle_guest_abort(struct kvm_vcpu *vcpu)
* faulting VA. This is always 12 bits, irrespective
* of the page size.
*/
- fault_ipa |= kvm_vcpu_get_hfar(vcpu) & ((1 << 12) - 1);
- ret = io_mem_abort(vcpu, fault_ipa);
+ ipa |= kvm_vcpu_get_hfar(vcpu) & ((1 << 12) - 1);
+ ret = io_mem_abort(vcpu, ipa);
goto out_unlock;
}
/* Userspace should not be able to register out-of-bounds IPAs */
- VM_BUG_ON(fault_ipa >= kvm_phys_size(vcpu->kvm));
+ VM_BUG_ON(ipa >= kvm_phys_size(vcpu->kvm));
if (fault_status == FSC_ACCESS) {
handle_access_fault(vcpu, fault_ipa);
@@ -1156,7 +1212,8 @@ int kvm_handle_guest_abort(struct kvm_vcpu *vcpu)
goto out_unlock;
}
- ret = user_mem_abort(vcpu, fault_ipa, memslot, hva, fault_status);
+ ret = user_mem_abort(vcpu, fault_ipa, &nested_trans,
+ memslot, hva, fault_status);
if (ret == 0)
ret = 1;
out:
@@ -108,6 +108,15 @@ static u32 compute_fsc(int level, u32 fsc)
return fsc | (level & 0x3);
}
+static int esr_s2_fault(struct kvm_vcpu *vcpu, int level, u32 fsc)
+{
+ u32 esr;
+
+ esr = kvm_vcpu_get_esr(vcpu) & ~ESR_ELx_FSC;
+ esr |= compute_fsc(level, fsc);
+ return esr;
+}
+
static int check_base_s2_limits(struct s2_walk_info *wi,
int level, int input_size, int stride)
{
@@ -457,6 +466,45 @@ void kvm_vcpu_put_hw_mmu(struct kvm_vcpu *vcpu)
}
}
+/*
+ * Returns non-zero if permission fault is handled by injecting it to the next
+ * level hypervisor.
+ */
+int kvm_s2_handle_perm_fault(struct kvm_vcpu *vcpu, struct kvm_s2_trans *trans)
+{
+ unsigned long fault_status = kvm_vcpu_trap_get_fault_type(vcpu);
+ bool forward_fault = false;
+
+ trans->esr = 0;
+
+ if (fault_status != FSC_PERM)
+ return 0;
+
+ if (kvm_vcpu_trap_is_iabt(vcpu)) {
+ forward_fault = (trans->upper_attr & BIT(54));
+ } else {
+ bool write_fault = kvm_is_write_fault(vcpu);
+
+ forward_fault = ((write_fault && !trans->writable) ||
+ (!write_fault && !trans->readable));
+ }
+
+ if (forward_fault) {
+ trans->esr = esr_s2_fault(vcpu, trans->level, ESR_ELx_FSC_PERM);
+ return 1;
+ }
+
+ return 0;
+}
+
+int kvm_inject_s2_fault(struct kvm_vcpu *vcpu, u64 esr_el2)
+{
+ vcpu_write_sys_reg(vcpu, vcpu->arch.fault.far_el2, FAR_EL2);
+ vcpu_write_sys_reg(vcpu, vcpu->arch.fault.hpfar_el2, HPFAR_EL2);
+
+ return kvm_inject_nested_sync(vcpu, esr_el2);
+}
+
/*
* Inject wfx to the virtual EL2 if this is not from the virtual EL2 and
* the virtual HCR_EL2.TWX is set. Otherwise, let the host hypervisor