From 80b0b86dc5e4344e62a2fd3ee43d0ef816fe9122 Mon Sep 17 00:00:00 2001 From: Fuad Tabba Date: Mon, 28 Sep 2026 10:54:52 +0100 Subject: [PATCH] KVM: arm64: Use kvm_s2_fault_vma_info in gmem_abort() gmem_abort() maps at s2fd->fault_ipa, which HPFAR_EL2 holds at 4K granularity whatever the page size. The generic page-table code aligns it, but pkvm_pgtable_stage2_map() looks up existing mappings over [addr, addr + size), so on a pKVM host with pages larger than 4K a guest_memfd-backed guest that faults past the first 4K of a page can find its neighbour's mapping, get -EAGAIN and take the same fault forever. The memory fault exit reports s2fd->fault_ipa too, which for a nested guest's fault is the nested IPA rather than the canonical one kvm_gmem_get_pfn() failed on. Take the addresses from kvm_s2_fault_vma_info instead, as user_mem_abort() does, and report the canonical gfn in the memory fault exit. kvm_s2_fault_get_vma_info() itself isn't called: a guest_memfd memslot's userspace_addr doesn't need to be backed by a VMA. Fixes: a7b57e0995927 ("KVM: arm64: Handle guest_memfd-backed guest page faults") Reported-by: Sashiko Closes: https://lore.kernel.org/r/20260913175105.A57AC1F000FF@smtp.kernel.org Cc: stable@vger.kernel.org Signed-off-by: Fuad Tabba Signed-off-by: Vincent Donnefort Link: https://patch.msgid.link/20260928095454.3255918-4-vdonnefort@google.com Signed-off-by: Marc Zyngier --- arch/arm64/kvm/mmu.c | 67 ++++++++++++++++++++++---------------------- 1 file changed, 34 insertions(+), 33 deletions(-) diff --git a/arch/arm64/kvm/mmu.c b/arch/arm64/kvm/mmu.c index 9dfaf4f277b5..658ac6a09e7b 100644 --- a/arch/arm64/kvm/mmu.c +++ b/arch/arm64/kvm/mmu.c @@ -1606,6 +1606,24 @@ static enum kvm_pgtable_prot adjust_nested_exec_perms(struct kvm *kvm, return prot; } +struct kvm_s2_fault_vma_info { + unsigned long mmu_seq; + long vma_pagesize; + vm_flags_t vm_flags; + unsigned long max_map_size; + struct page *page; + kvm_pfn_t pfn; + gfn_t gfn; + bool device; + bool mte_allowed; + bool is_vma_cacheable; + bool map_writable; + bool map_non_cacheable; +}; + +static gfn_t get_canonical_gfn(const struct kvm_s2_fault_desc *s2fd, + const struct kvm_s2_fault_vma_info *s2vi); + static int gmem_abort(const struct kvm_s2_fault_desc *s2fd) { bool write_fault, exec_fault; @@ -1613,12 +1631,10 @@ static int gmem_abort(const struct kvm_s2_fault_desc *s2fd) enum kvm_pgtable_walk_flags flags = KVM_PGTABLE_WALK_SHARED; enum kvm_pgtable_prot prot = KVM_PGTABLE_PROT_R; struct kvm_pgtable *pgt = s2fd->vcpu->arch.hw_mmu->pgt; - unsigned long mmu_seq; - struct page *page; + struct kvm_s2_fault_vma_info s2vi = {}; struct kvm *kvm = s2fd->vcpu->kvm; void *memcache = NULL; - kvm_pfn_t pfn; - gfn_t gfn; + gfn_t canonical_gfn; int ret; if (!perm_fault) { @@ -1628,24 +1644,23 @@ static int gmem_abort(const struct kvm_s2_fault_desc *s2fd) return ret; } - if (s2fd->nested) - gfn = kvm_s2_trans_output(s2fd->nested) >> PAGE_SHIFT; - else - gfn = s2fd->fault_ipa >> PAGE_SHIFT; + s2vi.vma_pagesize = PAGE_SIZE; + s2vi.gfn = ALIGN_DOWN(s2fd->fault_ipa, s2vi.vma_pagesize) >> PAGE_SHIFT; + canonical_gfn = get_canonical_gfn(s2fd, &s2vi); write_fault = kvm_is_write_fault(s2fd->vcpu); exec_fault = kvm_vcpu_trap_is_exec_fault(s2fd->vcpu); VM_WARN_ON_ONCE(write_fault && exec_fault); - mmu_seq = kvm->mmu_invalidate_seq; + s2vi.mmu_seq = kvm->mmu_invalidate_seq; /* Pairs with the smp_wmb() in kvm_mmu_invalidate_end(). */ smp_rmb(); - ret = kvm_gmem_get_pfn(kvm, s2fd->memslot, gfn, &pfn, &page, NULL); + ret = kvm_gmem_get_pfn(kvm, s2fd->memslot, canonical_gfn, &s2vi.pfn, &s2vi.page, NULL); if (ret) { - kvm_prepare_memory_fault_exit(s2fd->vcpu, s2fd->fault_ipa, PAGE_SIZE, - write_fault, exec_fault, false); + kvm_prepare_memory_fault_exit(s2fd->vcpu, gfn_to_gpa(canonical_gfn), + s2vi.vma_pagesize, write_fault, exec_fault, false); return ret; } @@ -1662,7 +1677,7 @@ static int gmem_abort(const struct kvm_s2_fault_desc *s2fd) prot = adjust_nested_exec_perms(kvm, s2fd->nested, prot); kvm_fault_lock(kvm); - if (mmu_invalidate_retry(kvm, mmu_seq)) { + if (mmu_invalidate_retry(kvm, s2vi.mmu_seq)) { ret = -EAGAIN; goto out_unlock; } @@ -1673,39 +1688,25 @@ static int gmem_abort(const struct kvm_s2_fault_desc *s2fd) * PTE, which will be preserved. */ prot &= ~KVM_NV_GUEST_MAP_SZ; - ret = KVM_PGT_FN(kvm_pgtable_stage2_relax_perms)(pgt, s2fd->fault_ipa, + ret = KVM_PGT_FN(kvm_pgtable_stage2_relax_perms)(pgt, gfn_to_gpa(s2vi.gfn), prot, flags); } else { - ret = KVM_PGT_FN(kvm_pgtable_stage2_map)(pgt, s2fd->fault_ipa, PAGE_SIZE, - __pfn_to_phys(pfn), prot, + ret = KVM_PGT_FN(kvm_pgtable_stage2_map)(pgt, gfn_to_gpa(s2vi.gfn), + s2vi.vma_pagesize, + __pfn_to_phys(s2vi.pfn), prot, memcache, flags); } out_unlock: - kvm_release_faultin_page(kvm, page, !!ret, prot & KVM_PGTABLE_PROT_W); + kvm_release_faultin_page(kvm, s2vi.page, !!ret, prot & KVM_PGTABLE_PROT_W); kvm_fault_unlock(kvm); if ((prot & KVM_PGTABLE_PROT_W) && !ret) - mark_page_dirty_in_slot(kvm, s2fd->memslot, gfn); + mark_page_dirty_in_slot(kvm, s2fd->memslot, canonical_gfn); return ret != -EAGAIN ? ret : 0; } -struct kvm_s2_fault_vma_info { - unsigned long mmu_seq; - long vma_pagesize; - vm_flags_t vm_flags; - unsigned long max_map_size; - struct page *page; - kvm_pfn_t pfn; - gfn_t gfn; - bool device; - bool mte_allowed; - bool is_vma_cacheable; - bool map_writable; - bool map_non_cacheable; -}; - static int pkvm_mem_abort(const struct kvm_s2_fault_desc *s2fd) { unsigned int flags = FOLL_HWPOISON | FOLL_LONGTERM | FOLL_WRITE;