[PATCH v3] KVM: arm64: Fix protected VM fault on system with pages larger than 4K

[Vincent Donnefort]

Just like commit 08f97454b7fa ("KVM: arm64: Fix protected mode handling
of pages larger than 4kB") fixed the boot of non-protected VMs on system
larger than 4K pages, align the fault IPA down to the page-size for
protected VMs.

To paraphrase Marc, pkvm_pgtable_stage2_map() assumes the address passed
as a parameter is aligned to the size of the intended mapping, while
HPFAR_EL2 gives the IPA minus the bottom 12 bits, regardless of the
system page size configuration.

Add a check at the start of pkvm_pgtable_stage2_map() as we do not
support !PAGE_ALIGNED arguments and ensure callers pass a page-aligned
IPA.

Fixes: ea03466e806f ("KVM: arm64: Handle aborts from protected VMs")
Signed-off-by: Vincent Donnefort <vdonnefort at google.com>
---
 arch/arm64/kvm/mmu.c  | 12 +++++++-----
 arch/arm64/kvm/pkvm.c |  3 +++
 2 files changed, 10 insertions(+), 5 deletions(-)

Changelog:

v3: 
  - Fix nested case in gmem_abort() (Sashiko)

v2: https://lore.kernel.org/all/20260914075839.4019904-1-vdonnefort@google.com/

  - Use gfn_to_gpa(gfn)
  - Drop "phys" from the PAGE_ALIGNED check, it isn't a requirement.
  - Fix gmem_abort() as well (Sashiko)

v1: https://lore.kernel.org/all/20260913173516.3122436-1-vdonnefort@google.com/

diff --git a/arch/arm64/kvm/mmu.c b/arch/arm64/kvm/mmu.c
index 9ba86450fe4a..e199dd339583 100644
--- a/arch/arm64/kvm/mmu.c
+++ b/arch/arm64/kvm/mmu.c
@@ -1610,6 +1610,7 @@ static int gmem_abort(const struct kvm_s2_fault_desc *s2fd)
 	bool write_fault, exec_fault;
 	bool perm_fault = kvm_vcpu_trap_is_permission_fault(s2fd->vcpu);
 	enum kvm_pgtable_walk_flags flags = KVM_PGTABLE_WALK_SHARED;
+	phys_addr_t ipa = ALIGN_DOWN(s2fd->fault_ipa, PAGE_SIZE);
 	enum kvm_pgtable_prot prot = KVM_PGTABLE_PROT_R;
 	struct kvm_pgtable *pgt = s2fd->vcpu->arch.hw_mmu->pgt;
 	unsigned long mmu_seq;
@@ -1672,12 +1673,12 @@ 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, ipa,
 								 prot, flags);
 	} else {
-		ret = KVM_PGT_FN(kvm_pgtable_stage2_map)(pgt, s2fd->fault_ipa, PAGE_SIZE,
-							 __pfn_to_phys(pfn), prot,
-							 memcache, flags);
+		ret = KVM_PGT_FN(kvm_pgtable_stage2_map)(pgt, ipa, PAGE_SIZE,
+							 __pfn_to_phys(pfn),
+							 prot, memcache, flags);
 	}
 
 out_unlock:
@@ -1710,6 +1711,7 @@ static int pkvm_mem_abort(const struct kvm_s2_fault_desc *s2fd)
 	unsigned int flags = FOLL_HWPOISON | FOLL_LONGTERM | FOLL_WRITE;
 	struct kvm_vcpu *vcpu = s2fd->vcpu;
 	struct kvm_pgtable *pgt = vcpu->arch.hw_mmu->pgt;
+	gfn_t gfn = gpa_to_gfn(s2fd->fault_ipa);
 	struct mm_struct *mm = current->mm;
 	struct kvm *kvm = vcpu->kvm;
 	void *hyp_memcache;
@@ -1756,7 +1758,7 @@ static int pkvm_mem_abort(const struct kvm_s2_fault_desc *s2fd)
 	}
 
 	write_lock(&kvm->mmu_lock);
-	ret = pkvm_pgtable_stage2_map(pgt, s2fd->fault_ipa, PAGE_SIZE,
+	ret = pkvm_pgtable_stage2_map(pgt, gfn_to_gpa(gfn), PAGE_SIZE,
 				      page_to_phys(page), KVM_PGTABLE_PROT_RWX,
 				      hyp_memcache, 0);
 	write_unlock(&kvm->mmu_lock);
diff --git a/arch/arm64/kvm/pkvm.c b/arch/arm64/kvm/pkvm.c
index 8e4c6e4bec12..b7340c430ed6 100644
--- a/arch/arm64/kvm/pkvm.c
+++ b/arch/arm64/kvm/pkvm.c
@@ -414,6 +414,9 @@ int pkvm_pgtable_stage2_map(struct kvm_pgtable *pgt, u64 addr, u64 size,
 	u64 end = addr + size;
 	int ret;
 
+	if (!PAGE_ALIGNED(addr | size))
+		return -EINVAL;
+
 	lockdep_assert_held_write(&kvm->mmu_lock);
 	mapping = pkvm_mapping_iter_first(&pgt->pkvm_mappings, addr, end - 1);
 

base-commit: df2908090cda368b01ff43709f51890076c56157
-- 
2.55.0.1032.g73a4cd73de-goog