[RFC PATCH v2 08/10] KVM: arm64: Handle guest_memfd()-backed guest page faults

[Fuad Tabba <tabba@google.com>]

Add arm64 support for resolving guest page faults on
guest_memfd() backed memslots. This support is not contingent on
pKVM, or other confidential computing support, and works in both
VHE and nVHE modes.

Without confidential computing, this support is useful for
testing and debugging. In the future, it might also be useful
should a user want to use guest_memfd() for all code, whether
it's for a protected guest or not.

For now, the fault granule is restricted to PAGE_SIZE.

Signed-off-by: Fuad Tabba <tabba@google.com>
---
 arch/arm64/kvm/mmu.c | 127 ++++++++++++++++++++++++++++++++++++++++++-
 1 file changed, 125 insertions(+), 2 deletions(-)

diff --git a/arch/arm64/kvm/mmu.c b/arch/arm64/kvm/mmu.c
index b1fc636fb670..e15167865cab 100644
--- a/arch/arm64/kvm/mmu.c
+++ b/arch/arm64/kvm/mmu.c
@@ -1378,6 +1378,123 @@ static bool kvm_vma_mte_allowed(struct vm_area_struct *vma)
 	return vma->vm_flags & VM_MTE_ALLOWED;
 }
 
+static int guest_memfd_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
+			     struct kvm_memory_slot *memslot, bool fault_is_perm)
+{
+	struct kvm_mmu_memory_cache *memcache = &vcpu->arch.mmu_page_cache;
+	bool exec_fault = kvm_vcpu_trap_is_exec_fault(vcpu);
+	bool logging_active = memslot_is_logging(memslot);
+	struct kvm_pgtable *pgt = vcpu->arch.hw_mmu->pgt;
+	enum kvm_pgtable_prot prot = KVM_PGTABLE_PROT_R;
+	bool write_fault = kvm_is_write_fault(vcpu);
+	struct mm_struct *mm = current->mm;
+	gfn_t gfn = gpa_to_gfn(fault_ipa);
+	struct kvm *kvm = vcpu->kvm;
+	unsigned long mmu_seq;
+	struct page *page;
+	kvm_pfn_t pfn;
+	int ret;
+
+	/* For now, guest_memfd() only supports PAGE_SIZE granules. */
+	if (WARN_ON_ONCE(fault_is_perm &&
+			 kvm_vcpu_trap_get_perm_fault_granule(vcpu) != PAGE_SIZE)) {
+		return -EFAULT;
+	}
+
+	VM_BUG_ON(write_fault && exec_fault);
+
+	if (fault_is_perm && !write_fault && !exec_fault) {
+		kvm_err("Unexpected L2 read permission error\n");
+		return -EFAULT;
+	}
+
+	/*
+	 * Permission faults just need to update the existing leaf entry,
+	 * and so normally don't require allocations from the memcache. The
+	 * only exception to this is when dirty logging is enabled at runtime
+	 * and a write fault needs to collapse a block entry into a table.
+	 */
+	if (!fault_is_perm || (logging_active && write_fault)) {
+		ret = kvm_mmu_topup_memory_cache(memcache,
+						 kvm_mmu_cache_min_pages(vcpu->arch.hw_mmu));
+		if (ret)
+			return ret;
+	}
+
+	/*
+	 * Read mmu_invalidate_seq so that KVM can detect if the results of
+	 * kvm_gmem_get_pfn_locked() become stale prior to acquiring
+	 * kvm->mmu_lock.
+	 */
+	mmu_seq = vcpu->kvm->mmu_invalidate_seq;
+
+	/* To pair with the smp_wmb() in kvm_mmu_invalidate_end(). */
+	smp_rmb();
+
+	ret = kvm_gmem_get_pfn_locked(kvm, memslot, gfn, &pfn, NULL);
+	if (ret)
+		return ret;
+
+	page = pfn_to_page(pfn);
+
+	if (!kvm_gmem_is_mappable(kvm, gfn, gfn + 1) &&
+	    (page_mapped(page) || page_maybe_dma_pinned(page))) {
+		return -EPERM;
+	}
+
+	/*
+	 * Once it's faulted in, a guest_memfd() page will stay in memory.
+	 * Therefore, count it as locked.
+	 */
+	if (!fault_is_perm) {
+		ret = account_locked_vm(mm, 1, true);
+		if (ret)
+			goto unlock_page;
+	}
+
+	read_lock(&kvm->mmu_lock);
+	if (mmu_invalidate_retry(kvm, mmu_seq))
+		goto unlock_mmu;
+
+	if (write_fault)
+		prot |= KVM_PGTABLE_PROT_W;
+
+	if (exec_fault)
+		prot |= KVM_PGTABLE_PROT_X;
+
+	if (cpus_have_final_cap(ARM64_HAS_CACHE_DIC))
+		prot |= KVM_PGTABLE_PROT_X;
+
+	/*
+	 * Under the premise of getting a FSC_PERM fault, we just need to relax
+	 * permissions.
+	 */
+	if (fault_is_perm)
+		ret = kvm_pgtable_stage2_relax_perms(pgt, fault_ipa, prot);
+	else
+		ret = kvm_pgtable_stage2_map(pgt, fault_ipa, PAGE_SIZE,
+					__pfn_to_phys(pfn), prot,
+					memcache,
+					KVM_PGTABLE_WALK_HANDLE_FAULT |
+					KVM_PGTABLE_WALK_SHARED);
+
+	/* Mark the page dirty only if the fault is handled successfully */
+	if (write_fault && !ret) {
+		kvm_set_pfn_dirty(pfn);
+		mark_page_dirty_in_slot(kvm, memslot, gfn);
+	}
+
+unlock_mmu:
+	read_unlock(&kvm->mmu_lock);
+
+	if (ret && !fault_is_perm)
+		account_locked_vm(mm, 1, false);
+unlock_page:
+	unlock_page(page);
+	put_page(page);
+	return ret != -EAGAIN ? ret : 0;
+}
+
 static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
 			  struct kvm_memory_slot *memslot, unsigned long hva,
 			  bool fault_is_perm)
@@ -1748,8 +1865,14 @@ int kvm_handle_guest_abort(struct kvm_vcpu *vcpu)
 		goto out_unlock;
 	}
 
-	ret = user_mem_abort(vcpu, fault_ipa, memslot, hva,
-			     esr_fsc_is_permission_fault(esr));
+	if (kvm_slot_can_be_private(memslot)) {
+		ret = guest_memfd_abort(vcpu, fault_ipa, memslot,
+					esr_fsc_is_permission_fault(esr));
+	} else {
+		ret = user_mem_abort(vcpu, fault_ipa, memslot, hva,
+				     esr_fsc_is_permission_fault(esr));
+	}
+
 	if (ret == 0)
 		ret = 1;
 out:
-- 
2.46.0.rc1.232.g9752f9e123-goog