We walk the userspace PTs to discover what mapping size was used there. However, this can race against the userspace tables being freed, and we end-up in the weeds.

Thankfully, the mm code is being generous and will IPI us when doing so. So let's implement our part of the bargain and disable interrupts around the walk. This ensures that nothing terrible happens during that time.

We still need to handle the removal of the page tables before the walk. For that, allow get_user_mapping_size() to return an error, and make sure this error can be propagated all the way to the the exit handler.

Signed-off-by: Marc Zyngier maz@kernel.org Cc: stable@vger.kernel.org --- arch/arm64/kvm/mmu.c | 45 +++++++++++++++++++++++++++++++++++++------- 1 file changed, 38 insertions(+), 7 deletions(-)

diff --git a/arch/arm64/kvm/mmu.c b/arch/arm64/kvm/mmu.c index f54408355d1d..d3d4cdc0f617 100644 --- a/arch/arm64/kvm/mmu.c +++ b/arch/arm64/kvm/mmu.c @@ -666,14 +666,33 @@ static int get_user_mapping_size(struct kvm *kvm, u64 addr) CONFIG_PGTABLE_LEVELS), .mm_ops = &kvm_user_mm_ops, }; + unsigned long flags; kvm_pte_t pte = 0; /* Keep GCC quiet... */ u32 level = ~0; int ret;

+ /* + * Disable IRQs so that we hazard against a concurrent + * teardown of the userspace page tables (which relies on + * IPI-ing threads). + */ + local_irq_save(flags); ret = kvm_pgtable_get_leaf(&pgt, addr, &pte, &level); - VM_BUG_ON(ret); - VM_BUG_ON(level >= KVM_PGTABLE_MAX_LEVELS); - VM_BUG_ON(!(pte & PTE_VALID)); + local_irq_restore(flags); + + if (ret) + return ret; + + /* + * Not seeing an error, but not updating level? Something went + * deeply wrong... + */ + if (WARN_ON(level >= KVM_PGTABLE_MAX_LEVELS)) + return -EFAULT; + + /* Oops, the userspace PTs are gone... Replay the fault */ + if (!(pte & PTE_VALID)) + return -EAGAIN;

return BIT(ARM64_HW_PGTABLE_LEVEL_SHIFT(level)); } @@ -1079,7 +1098,7 @@ static bool fault_supports_stage2_huge_mapping(struct kvm_memory_slot *memslot, * * Returns the size of the mapping. */ -static unsigned long +static long transparent_hugepage_adjust(struct kvm *kvm, struct kvm_memory_slot *memslot, unsigned long hva, kvm_pfn_t *pfnp, phys_addr_t *ipap) @@ -1091,8 +1110,15 @@ transparent_hugepage_adjust(struct kvm *kvm, struct kvm_memory_slot *memslot, * sure that the HVA and IPA are sufficiently aligned and that the * block map is contained within the memslot. */ - if (fault_supports_stage2_huge_mapping(memslot, hva, PMD_SIZE) && - get_user_mapping_size(kvm, hva) >= PMD_SIZE) { + if (fault_supports_stage2_huge_mapping(memslot, hva, PMD_SIZE)) { + int sz = get_user_mapping_size(kvm, hva); + + if (sz < 0) + return sz; + + if (sz < PMD_SIZE) + return PAGE_SIZE; + /* * The address we faulted on is backed by a transparent huge * page. However, because we map the compound huge page and @@ -1203,7 +1229,7 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa, kvm_pfn_t pfn; bool logging_active = memslot_is_logging(memslot); unsigned long fault_level = kvm_vcpu_trap_get_fault_level(vcpu); - unsigned long vma_pagesize, fault_granule; + long vma_pagesize, fault_granule; enum kvm_pgtable_prot prot = KVM_PGTABLE_PROT_R; struct kvm_pgtable *pgt;

@@ -1344,6 +1370,11 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa, vma_pagesize = transparent_hugepage_adjust(kvm, memslot, hva, &pfn, &fault_ipa); + + if (vma_pagesize < 0) { + ret = vma_pagesize; + goto out_unlock; + } }

if (fault_status != ESR_ELx_FSC_PERM && !device && kvm_has_mte(kvm)) {