[RFC,v1,19/26] KVM: arm64: Handle guest_memfd()-backed guest page faults

Commit Message

Fuad Tabba Feb. 22, 2024, 4:10 p.m. UTC

Introduce a new fault handler which responds to guest faults for
guestmem pages.

Signed-off-by: Fuad Tabba <[e-mail]>
---
 arch/arm64/kvm/mmu.c | 75 ++++++++++++++++++++++++++++++++++++++++++--
 1 file changed, 72 insertions(+), 3 deletions(-)

Patch

diff --git a/arch/arm64/kvm/mmu.c b/arch/arm64/kvm/mmu.c
index 6ad79390b15c..570b14da16b1 100644
--- a/arch/arm64/kvm/mmu.c
+++ b/arch/arm64/kvm/mmu.c
@@ -1438,6 +1438,70 @@  static int insert_ppage(struct kvm *kvm, struct kvm_guest_page *ppage)
 	return 0;
 }
 
+static int guestmem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
+			  struct kvm_memory_slot *memslot)
+{
+	struct kvm_hyp_memcache *hyp_memcache = &vcpu->arch.pkvm_memcache;
+	struct kvm_guest_page *guest_page;
+	struct mm_struct *mm = current->mm;
+	gfn_t gfn = gpa_to_gfn(fault_ipa);
+	struct kvm *kvm = vcpu->kvm;
+	struct kvm_s2_mmu *mmu =  &kvm->arch.mmu;
+	struct page *page = NULL;
+	kvm_pfn_t pfn;
+	int ret;
+
+	ret = topup_hyp_memcache(hyp_memcache, kvm_mmu_cache_min_pages(mmu));
+	if (ret)
+		return ret;
+
+	/*
+	 * Acquire the page lock to avoid racing with kvm_gmem_fault() when
+	 * checking the page_mapcount later on.
+	 */
+	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) && page_mapcount(page)) {
+		ret = -EPERM;
+		goto rel_page;
+	}
+
+	guest_page = kmalloc(sizeof(*guest_page), GFP_KERNEL_ACCOUNT);
+	if (!guest_page) {
+		ret = -ENOMEM;
+		goto rel_page;
+	}
+
+	guest_page->page = page;
+	guest_page->ipa = fault_ipa;
+	guest_page->is_pinned = false;
+
+	ret = account_locked_vm(mm, 1, true);
+	if (ret)
+		goto free_gp;
+
+	write_lock(&kvm->mmu_lock);
+	ret = pkvm_host_map_guest(pfn, gfn);
+	if (!ret)
+		WARN_ON(insert_ppage(kvm, guest_page));
+	write_unlock(&kvm->mmu_lock);
+
+	if (ret)
+		account_locked_vm(mm, 1, false);
+free_gp:
+	if (ret)
+		kfree(guest_page);
+rel_page:
+	unlock_page(page);
+	put_page(page);
+
+	return ret != -EAGAIN ? ret : 0;
+}
+
 static int pkvm_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
 			  struct kvm_memory_slot *memslot)
 {
@@ -1887,11 +1951,16 @@  int kvm_handle_guest_abort(struct kvm_vcpu *vcpu)
 		goto out_unlock;
 	}
 
-	if (is_protected_kvm_enabled())
-		ret = pkvm_mem_abort(vcpu, fault_ipa, memslot);
-	else
+	if (is_protected_kvm_enabled()) {
+		if ((kvm_slot_can_be_private(memslot)))
+			ret = guestmem_abort(vcpu, fault_ipa, memslot);
+		else
+			ret = pkvm_mem_abort(vcpu, fault_ipa, memslot);
+	} else {
 		ret = user_mem_abort(vcpu, fault_ipa, memslot,
 				     esr_fsc_is_permission_fault(esr));
+	}
+
 
 	if (ret == 0)
 		ret = 1;