[PATCH v12 10/18] KVM: x86/mmu: Handle guest page faults for guest_memfd with shared memory

[Fuad Tabba <tabba@google.com>]

From: Ackerley Tng <ackerleytng@google.com>

For memslots backed by guest_memfd with shared mem support, the KVM MMU
must always fault in pages from guest_memfd, and not from the host
userspace_addr. Update the fault handler to do so.

This patch also refactors related function names for accuracy:

kvm_mem_is_private() returns true only when the current private/shared
state (in the CoCo sense) of the memory is private, and returns false if
the current state is shared explicitly or impicitly, e.g., belongs to a
non-CoCo VM.

kvm_mmu_faultin_pfn_gmem() is updated to indicate that it can be used to
fault in not just private memory, but more generally, from guest_memfd.

Co-developed-by: David Hildenbrand <david@redhat.com>
Signed-off-by: David Hildenbrand <david@redhat.com>
Signed-off-by: Ackerley Tng <ackerleytng@google.com>
Co-developed-by: Fuad Tabba <tabba@google.com>
Signed-off-by: Fuad Tabba <tabba@google.com>
---
 arch/x86/kvm/mmu/mmu.c   | 38 +++++++++++++++++++++++---------------
 include/linux/kvm_host.h | 25 +++++++++++++++++++++++--
 2 files changed, 46 insertions(+), 17 deletions(-)

diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c
index 75b7b02cfcb7..2aab5a00caee 100644
--- a/arch/x86/kvm/mmu/mmu.c
+++ b/arch/x86/kvm/mmu/mmu.c
@@ -3291,6 +3291,11 @@ int kvm_mmu_max_mapping_level(struct kvm *kvm,
 	return __kvm_mmu_max_mapping_level(kvm, slot, gfn, PG_LEVEL_NUM, is_private);
 }
 
+static inline bool fault_from_gmem(struct kvm_page_fault *fault)
+{
+	return fault->is_private || kvm_gmem_memslot_supports_shared(fault->slot);
+}
+
 void kvm_mmu_hugepage_adjust(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault)
 {
 	struct kvm_memory_slot *slot = fault->slot;
@@ -4467,21 +4472,25 @@ static inline u8 kvm_max_level_for_order(int order)
 	return PG_LEVEL_4K;
 }
 
-static u8 kvm_max_private_mapping_level(struct kvm *kvm, kvm_pfn_t pfn,
-					u8 max_level, int gmem_order)
+static u8 kvm_max_level_for_fault_and_order(struct kvm *kvm,
+					    struct kvm_page_fault *fault,
+					    int order)
 {
-	u8 req_max_level;
+	u8 max_level = fault->max_level;
 
 	if (max_level == PG_LEVEL_4K)
 		return PG_LEVEL_4K;
 
-	max_level = min(kvm_max_level_for_order(gmem_order), max_level);
+	max_level = min(kvm_max_level_for_order(order), max_level);
 	if (max_level == PG_LEVEL_4K)
 		return PG_LEVEL_4K;
 
-	req_max_level = kvm_x86_call(private_max_mapping_level)(kvm, pfn);
-	if (req_max_level)
-		max_level = min(max_level, req_max_level);
+	if (fault->is_private) {
+		u8 level = kvm_x86_call(private_max_mapping_level)(kvm, fault->pfn);
+
+		if (level)
+			max_level = min(max_level, level);
+	}
 
 	return max_level;
 }
@@ -4493,10 +4502,10 @@ static void kvm_mmu_finish_page_fault(struct kvm_vcpu *vcpu,
 				 r == RET_PF_RETRY, fault->map_writable);
 }
 
-static int kvm_mmu_faultin_pfn_private(struct kvm_vcpu *vcpu,
-				       struct kvm_page_fault *fault)
+static int kvm_mmu_faultin_pfn_gmem(struct kvm_vcpu *vcpu,
+				    struct kvm_page_fault *fault)
 {
-	int max_order, r;
+	int gmem_order, r;
 
 	if (!kvm_slot_has_gmem(fault->slot)) {
 		kvm_mmu_prepare_memory_fault_exit(vcpu, fault);
@@ -4504,15 +4513,14 @@ static int kvm_mmu_faultin_pfn_private(struct kvm_vcpu *vcpu,
 	}
 
 	r = kvm_gmem_get_pfn(vcpu->kvm, fault->slot, fault->gfn, &fault->pfn,
-			     &fault->refcounted_page, &max_order);
+			     &fault->refcounted_page, &gmem_order);
 	if (r) {
 		kvm_mmu_prepare_memory_fault_exit(vcpu, fault);
 		return r;
 	}
 
 	fault->map_writable = !(fault->slot->flags & KVM_MEM_READONLY);
-	fault->max_level = kvm_max_private_mapping_level(vcpu->kvm, fault->pfn,
-							 fault->max_level, max_order);
+	fault->max_level = kvm_max_level_for_fault_and_order(vcpu->kvm, fault, gmem_order);
 
 	return RET_PF_CONTINUE;
 }
@@ -4522,8 +4530,8 @@ static int __kvm_mmu_faultin_pfn(struct kvm_vcpu *vcpu,
 {
 	unsigned int foll = fault->write ? FOLL_WRITE : 0;
 
-	if (fault->is_private)
-		return kvm_mmu_faultin_pfn_private(vcpu, fault);
+	if (fault_from_gmem(fault))
+		return kvm_mmu_faultin_pfn_gmem(vcpu, fault);
 
 	foll |= FOLL_NOWAIT;
 	fault->pfn = __kvm_faultin_pfn(fault->slot, fault->gfn, foll,
diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index bba7d2c14177..8f7069385189 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -2547,10 +2547,31 @@ bool kvm_arch_pre_set_memory_attributes(struct kvm *kvm,
 bool kvm_arch_post_set_memory_attributes(struct kvm *kvm,
 					 struct kvm_gfn_range *range);
 
+/*
+ * Returns true if the given gfn's private/shared status (in the CoCo sense) is
+ * private.
+ *
+ * A return value of false indicates that the gfn is explicitly or implicitly
+ * shared (i.e., non-CoCo VMs).
+ */
 static inline bool kvm_mem_is_private(struct kvm *kvm, gfn_t gfn)
 {
-	return IS_ENABLED(CONFIG_KVM_GMEM) &&
-	       kvm_get_memory_attributes(kvm, gfn) & KVM_MEMORY_ATTRIBUTE_PRIVATE;
+	struct kvm_memory_slot *slot;
+
+	if (!IS_ENABLED(CONFIG_KVM_GMEM))
+		return false;
+
+	slot = gfn_to_memslot(kvm, gfn);
+	if (kvm_slot_has_gmem(slot) && kvm_gmem_memslot_supports_shared(slot)) {
+		/*
+		 * Without in-place conversion support, if a guest_memfd memslot
+		 * supports shared memory, then all the slot's memory is
+		 * considered not private, i.e., implicitly shared.
+		 */
+		return false;
+	}
+
+	return kvm_get_memory_attributes(kvm, gfn) & KVM_MEMORY_ATTRIBUTE_PRIVATE;
 }
 #else
 static inline bool kvm_mem_is_private(struct kvm *kvm, gfn_t gfn)
-- 
2.50.0.rc0.642.g800a2b2222-goog