[PATCH v3 4/4] KVM: guest_memfd: Stop returning struct page from PFN lookup

From: Sean Christopherson <[email protected]>

KVM currently expects guest_memfd PFN lookups to return a refcounted struct
page, which callers hold across fault handling.

Drop the page's refcount before returning from kvm_gmem_get_pfn() to
prepare for the in-place conversions series.

CoCo shared-to-private conversion handling must inspect folio refcounts to
ensure exclusive ownership by guest_memfd. A concurrent guest page fault
taking a temporary reference on the folio causes conversions to fail due to
an elevated refcount.

While this refcount is also taken on host userspace page faults, that
refcount is taken on behalf of the host userspace page tables. This
refcount will be dropped when conversions unmaps the page. Either way, once
there's an mmap() or userspace mapping, the pages are open to way more
refcounts, transient or not. This patch focuses on just dropping refcounts
before handing KVM a page.

guest_memfd already notifies KVM of page invalidations, so callers within
KVM only need to respect the MMU invalidation protocol to safely rely on
guest_memfd for page presence.

Since the page refcounts are dropped, don't return the struct page pointer.

Not returning the struct page from the guest_memfd PFN lookup moves KVM
closer toward supporting memory backends that are not backed by struct
page.

Here are some notes on the cleanup in the callers of kvm_gmem_get_pfn():

kvm_release_faultin_page() in ARM's gmem_abort() originally also serves to
set the page dirty and accessed under some conditions. The dirty and
accessed flags don't matter for guest_memfd anyway, so it is safe to just
drop the call to kvm_release_faultin_page().

For ARM's kvm_translate_vncr(), the local page pointer must be initialized
to NULL so that the shared cleanup path that releases faulted-in pages
safely no-ops for guest_memfd.

For x86, no additional changes are required in the MMU fault path because
the page fault tracking structure is zero-initialized at the start of page
fault handling, ensuring the refcounted page pointer is already NULL.

Reported-by: Yan Zhao <[email protected]>
Closes: https://lore.kernel.org/all/[email protected]/
Signed-off-by: Sean Christopherson <[email protected]>
Co-developed-by: Yan Zhao <[email protected]>
Signed-off-by: Yan Zhao <[email protected]>
Reviewed-by: Suzuki K Poulose <[email protected]>
Reviewed-by: Michael Roth <[email protected]>
Tested-by: Michael Roth <[email protected]>
Tested-by: Yan Zhao <[email protected]>
Co-developed-by: Ackerley Tng <[email protected]>
Signed-off-by: Ackerley Tng <[email protected]>
---
 arch/arm64/kvm/mmu.c     | 4 +---
 arch/arm64/kvm/nested.c  | 4 ++--
 arch/x86/kvm/mmu/mmu.c   | 2 +-
 arch/x86/kvm/svm/sev.c   | 8 ++------
 include/linux/kvm_host.h | 6 ++----
 virt/kvm/guest_memfd.c   | 9 ++-------
 6 files changed, 10 insertions(+), 23 deletions(-)

diff --git a/arch/arm64/kvm/mmu.c b/arch/arm64/kvm/mmu.c
index 6c941aaa10c63..d5aa197d2cbfd 100644
--- a/arch/arm64/kvm/mmu.c
+++ b/arch/arm64/kvm/mmu.c
@@ -1613,7 +1613,6 @@ static int gmem_abort(const struct kvm_s2_fault_desc *s2fd)
 	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 *kvm = s2fd->vcpu->kvm;
 	void *memcache = NULL;
 	kvm_pfn_t pfn;
@@ -1641,7 +1640,7 @@ static int gmem_abort(const struct kvm_s2_fault_desc *s2fd)
 	/* 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, gfn, &pfn, NULL);
 	if (ret) {
 		kvm_prepare_memory_fault_exit(s2fd->vcpu, s2fd->fault_ipa, PAGE_SIZE,
 					      write_fault, exec_fault, false);
@@ -1681,7 +1680,6 @@ static int gmem_abort(const struct kvm_s2_fault_desc *s2fd)
 	}
 
 out_unlock:
-	kvm_release_faultin_page(kvm, page, !!ret, prot & KVM_PGTABLE_PROT_W);
 	kvm_fault_unlock(kvm);
 
 	if ((prot & KVM_PGTABLE_PROT_W) && !ret)
diff --git a/arch/arm64/kvm/nested.c b/arch/arm64/kvm/nested.c
index fb54f6dad995c..43523bb17621a 100644
--- a/arch/arm64/kvm/nested.c
+++ b/arch/arm64/kvm/nested.c
@@ -1360,7 +1360,7 @@ static int kvm_translate_vncr(struct kvm_vcpu *vcpu, bool *is_gmem)
 	bool write_fault, writable;
 	unsigned long mmu_seq;
 	struct vncr_tlb *vt;
-	struct page *page;
+	struct page *page = NULL;
 	u64 va, pfn, gfn;
 	int ret;
 
@@ -1411,7 +1411,7 @@ static int kvm_translate_vncr(struct kvm_vcpu *vcpu, bool *is_gmem)
 		if (is_error_noslot_pfn(pfn) || (write_fault && !writable))
 			return -EFAULT;
 	} else {
-		ret = kvm_gmem_get_pfn(vcpu->kvm, memslot, gfn, &pfn, &page, NULL);
+		ret = kvm_gmem_get_pfn(vcpu->kvm, memslot, gfn, &pfn, NULL);
 		if (ret) {
 			kvm_prepare_memory_fault_exit(vcpu, vt->wr.pa, PAGE_SIZE,
 					      write_fault, false, false);
diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c
index c519e8e8d646f..129d403308051 100644
--- a/arch/x86/kvm/mmu/mmu.c
+++ b/arch/x86/kvm/mmu/mmu.c
@@ -4604,7 +4604,7 @@ static int kvm_mmu_faultin_pfn_gmem(struct kvm_vcpu *vcpu,
 	}
 
 	r = kvm_gmem_get_pfn(vcpu->kvm, fault->slot, fault->gfn, &fault->pfn,
-			     &fault->refcounted_page, &max_order);
+			     &max_order);
 	if (r) {
 		kvm_mmu_prepare_memory_fault_exit(vcpu, fault);
 		return r;
diff --git a/arch/x86/kvm/svm/sev.c b/arch/x86/kvm/svm/sev.c
index 0375ef709ee2c..0c91c904573cc 100644
--- a/arch/x86/kvm/svm/sev.c
+++ b/arch/x86/kvm/svm/sev.c
@@ -4016,7 +4016,6 @@ static void __sev_snp_reload_vmsa(struct kvm_vcpu *vcpu, gpa_t gpa)
 	struct kvm *kvm = vcpu->kvm;
 	gfn_t gfn = gpa_to_gfn(gpa);
 	unsigned long mmu_seq;
-	struct page *page;
 	kvm_pfn_t pfn;
 
 	lockdep_assert_held(&svm->sev_es.snp_vmsa_mutex);
@@ -4060,9 +4059,8 @@ static void __sev_snp_reload_vmsa(struct kvm_vcpu *vcpu, gpa_t gpa)
 	 * The new VMSA will be private memory guest memory, so retrieve the
 	 * PFN from the gmem backend.
 	 */
-	if (kvm_gmem_get_pfn(vcpu->kvm, slot, gfn, &pfn, &page, NULL))
+	if (kvm_gmem_get_pfn(vcpu->kvm, slot, gfn, &pfn, NULL))
 		return;
-	kvm_release_page_clean(page);
 
 	read_lock(&kvm->mmu_lock);
 	/*
@@ -5003,7 +5001,6 @@ void sev_handle_rmp_fault(struct kvm_vcpu *vcpu, gpa_t gpa, u64 error_code)
 	struct kvm *kvm = vcpu->kvm;
 	int order, rmp_level, ret;
 	unsigned long mmu_seq;
-	struct page *page;
 	bool assigned;
 	kvm_pfn_t pfn;
 	gfn_t gfn;
@@ -5033,13 +5030,12 @@ void sev_handle_rmp_fault(struct kvm_vcpu *vcpu, gpa_t gpa, u64 error_code)
 	mmu_seq = kvm->mmu_invalidate_seq;
 	smp_rmb();
 
-	ret = kvm_gmem_get_pfn(kvm, slot, gfn, &pfn, &page, &order);
+	ret = kvm_gmem_get_pfn(kvm, slot, gfn, &pfn, &order);
 	if (ret) {
 		pr_warn_ratelimited("SEV: Unexpected RMP fault, no backing page for private GPA 0x%llx\n",
 				    gpa);
 		return;
 	}
-	kvm_release_page_unused(page);
 
 	ret = snp_lookup_rmpentry(pfn, &assigned, &rmp_level);
 	if (ret || !assigned) {
diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index 03bfc92864b6e..502465119ca0c 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -2586,13 +2586,11 @@ static inline bool kvm_mem_is_private(struct kvm *kvm, gfn_t gfn)
 
 #ifdef CONFIG_KVM_GUEST_MEMFD
 int kvm_gmem_get_pfn(struct kvm *kvm, struct kvm_memory_slot *slot,
-		     gfn_t gfn, kvm_pfn_t *pfn, struct page **page,
-		     int *max_order);
+		     gfn_t gfn, kvm_pfn_t *pfn, int *max_order);
 #else
 static inline int kvm_gmem_get_pfn(struct kvm *kvm,
 				   struct kvm_memory_slot *slot, gfn_t gfn,
-				   kvm_pfn_t *pfn, struct page **page,
-				   int *max_order)
+				   kvm_pfn_t *pfn, int *max_order)
 {
 	KVM_BUG_ON(1, kvm);
 	return -EIO;
diff --git a/virt/kvm/guest_memfd.c b/virt/kvm/guest_memfd.c
index b596486d184ca..589762140c3ef 100644
--- a/virt/kvm/guest_memfd.c
+++ b/virt/kvm/guest_memfd.c
@@ -751,8 +751,7 @@ static struct folio *__kvm_gmem_get_pfn(struct file *file,
 }
 
 int kvm_gmem_get_pfn(struct kvm *kvm, struct kvm_memory_slot *slot,
-		     gfn_t gfn, kvm_pfn_t *pfn, struct page **page,
-		     int *max_order)
+		     gfn_t gfn, kvm_pfn_t *pfn, int *max_order)
 {
 	pgoff_t index = kvm_gmem_get_index(slot, gfn);
 	struct folio *folio;
@@ -780,11 +779,7 @@ int kvm_gmem_get_pfn(struct kvm *kvm, struct kvm_memory_slot *slot,
 #endif
 
 	folio_unlock(folio);
-
-	if (!r)
-		*page = folio_file_page(folio, index);
-	else
-		folio_put(folio);
+	folio_put(folio);
 
 	return r;
 }

-- 
2.55.0.766.g2966f0265a-goog