KVM: x86/mmu: Handle page fault for private memory

Add support for resolving page faults on guest private memory for VMs
that differentiate between "shared" and "private" memory.  For such VMs,
KVM_MEM_GUEST_MEMFD memslots can include both fd-based private memory and
hva-based shared memory, and KVM needs to map in the "correct" variant,
i.e. KVM needs to map the gfn shared/private as appropriate based on the
current state of the gfn's KVM_MEMORY_ATTRIBUTE_PRIVATE flag.

For AMD's SEV-SNP and Intel's TDX, the guest effectively gets to request
shared vs. private via a bit in the guest page tables, i.e. what the guest
wants may conflict with the current memory attributes.  To support such
"implicit" conversion requests, exit to user with KVM_EXIT_MEMORY_FAULT
to forward the request to userspace.  Add a new flag for memory faults,
KVM_MEMORY_EXIT_FLAG_PRIVATE, to communicate whether the guest wants to
map memory as shared vs. private.

Like KVM_MEMORY_ATTRIBUTE_PRIVATE, use bit 3 for flagging private memory
so that KVM can use bits 0-2 for capturing RWX behavior if/when userspace
needs such information, e.g. a likely user of KVM_EXIT_MEMORY_FAULT is to
exit on missing mappings when handling guest page fault VM-Exits.  In
that case, userspace will want to know RWX information in order to
correctly/precisely resolve the fault.

Note, private memory *must* be backed by guest_memfd, i.e. shared mappings
always come from the host userspace page tables, and private mappings
always come from a guest_memfd instance.

Co-developed-by: Yu Zhang <yu.c.zhang@linux.intel.com>
Signed-off-by: Yu Zhang <yu.c.zhang@linux.intel.com>
Signed-off-by: Chao Peng <chao.p.peng@linux.intel.com>
Co-developed-by: Sean Christopherson <seanjc@google.com>
Signed-off-by: Sean Christopherson <seanjc@google.com>
Reviewed-by: Fuad Tabba <tabba@google.com>
Tested-by: Fuad Tabba <tabba@google.com>
Message-Id: <20231027182217.3615211-21-seanjc@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>

2 files changed, 97 insertions, 5 deletions

diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c
index f5c6b0643645..754a5aaebee5 100644
--- a/arch/x86/kvm/mmu/mmu.c
+++ b/arch/x86/kvm/mmu/mmu.c
@@ -3147,9 +3147,9 @@ out:
 	return level;
 }
 
-int kvm_mmu_max_mapping_level(struct kvm *kvm,
-			      const struct kvm_memory_slot *slot, gfn_t gfn,
-			      int max_level)
+static int __kvm_mmu_max_mapping_level(struct kvm *kvm,
+				       const struct kvm_memory_slot *slot,
+				       gfn_t gfn, int max_level, bool is_private)
 {
 	struct kvm_lpage_info *linfo;
 	int host_level;
@@ -3161,6 +3161,9 @@ int kvm_mmu_max_mapping_level(struct kvm *kvm,
 			break;
 	}
 
+	if (is_private)
+		return max_level;
+
 	if (max_level == PG_LEVEL_4K)
 		return PG_LEVEL_4K;
 
@@ -3168,6 +3171,16 @@ int kvm_mmu_max_mapping_level(struct kvm *kvm,
 	return min(host_level, max_level);
 }
 
+int kvm_mmu_max_mapping_level(struct kvm *kvm,
+			      const struct kvm_memory_slot *slot, gfn_t gfn,
+			      int max_level)
+{
+	bool is_private = kvm_slot_can_be_private(slot) &&
+			  kvm_mem_is_private(kvm, gfn);
+
+	return __kvm_mmu_max_mapping_level(kvm, slot, gfn, max_level, is_private);
+}
+
 void kvm_mmu_hugepage_adjust(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault)
 {
 	struct kvm_memory_slot *slot = fault->slot;
@@ -3188,8 +3201,9 @@ void kvm_mmu_hugepage_adjust(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault
 	 * Enforce the iTLB multihit workaround after capturing the requested
 	 * level, which will be used to do precise, accurate accounting.
 	 */
-	fault->req_level = kvm_mmu_max_mapping_level(vcpu->kvm, slot,
-						     fault->gfn, fault->max_level);
+	fault->req_level = __kvm_mmu_max_mapping_level(vcpu->kvm, slot,
+						       fault->gfn, fault->max_level,
+						       fault->is_private);
 	if (fault->req_level == PG_LEVEL_4K || fault->huge_page_disallowed)
 		return;
 
@@ -4269,6 +4283,55 @@ void kvm_arch_async_page_ready(struct kvm_vcpu *vcpu, struct kvm_async_pf *work)
 	kvm_mmu_do_page_fault(vcpu, work->cr2_or_gpa, 0, true, NULL);
 }
 
+static inline u8 kvm_max_level_for_order(int order)
+{
+	BUILD_BUG_ON(KVM_MAX_HUGEPAGE_LEVEL > PG_LEVEL_1G);
+
+	KVM_MMU_WARN_ON(order != KVM_HPAGE_GFN_SHIFT(PG_LEVEL_1G) &&
+			order != KVM_HPAGE_GFN_SHIFT(PG_LEVEL_2M) &&
+			order != KVM_HPAGE_GFN_SHIFT(PG_LEVEL_4K));
+
+	if (order >= KVM_HPAGE_GFN_SHIFT(PG_LEVEL_1G))
+		return PG_LEVEL_1G;
+
+	if (order >= KVM_HPAGE_GFN_SHIFT(PG_LEVEL_2M))
+		return PG_LEVEL_2M;
+
+	return PG_LEVEL_4K;
+}
+
+static void kvm_mmu_prepare_memory_fault_exit(struct kvm_vcpu *vcpu,
+					      struct kvm_page_fault *fault)
+{
+	kvm_prepare_memory_fault_exit(vcpu, fault->gfn << PAGE_SHIFT,
+				      PAGE_SIZE, fault->write, fault->exec,
+				      fault->is_private);
+}
+
+static int kvm_faultin_pfn_private(struct kvm_vcpu *vcpu,
+				   struct kvm_page_fault *fault)
+{
+	int max_order, r;
+
+	if (!kvm_slot_can_be_private(fault->slot)) {
+		kvm_mmu_prepare_memory_fault_exit(vcpu, fault);
+		return -EFAULT;
+	}
+
+	r = kvm_gmem_get_pfn(vcpu->kvm, fault->slot, fault->gfn, &fault->pfn,
+			     &max_order);
+	if (r) {
+		kvm_mmu_prepare_memory_fault_exit(vcpu, fault);
+		return r;
+	}
+
+	fault->max_level = min(kvm_max_level_for_order(max_order),
+			       fault->max_level);
+	fault->map_writable = !(fault->slot->flags & KVM_MEM_READONLY);
+
+	return RET_PF_CONTINUE;
+}
+
 static int __kvm_faultin_pfn(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault)
 {
 	struct kvm_memory_slot *slot = fault->slot;
@@ -4301,6 +4364,14 @@ static int __kvm_faultin_pfn(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault
 			return RET_PF_EMULATE;
 	}
 
+	if (fault->is_private != kvm_mem_is_private(vcpu->kvm, fault->gfn)) {
+		kvm_mmu_prepare_memory_fault_exit(vcpu, fault);
+		return -EFAULT;
+	}
+
+	if (fault->is_private)
+		return kvm_faultin_pfn_private(vcpu, fault);
+
 	async = false;
 	fault->pfn = __gfn_to_pfn_memslot(slot, fault->gfn, false, false, &async,
 					  fault->write, &fault->map_writable,
@@ -7188,6 +7259,26 @@ void kvm_mmu_pre_destroy_vm(struct kvm *kvm)
 }
 
 #ifdef CONFIG_KVM_GENERIC_MEMORY_ATTRIBUTES
+bool kvm_arch_pre_set_memory_attributes(struct kvm *kvm,
+					struct kvm_gfn_range *range)
+{
+	/*
+	 * Zap SPTEs even if the slot can't be mapped PRIVATE.  KVM x86 only
+	 * supports KVM_MEMORY_ATTRIBUTE_PRIVATE, and so it *seems* like KVM
+	 * can simply ignore such slots.  But if userspace is making memory
+	 * PRIVATE, then KVM must prevent the guest from accessing the memory
+	 * as shared.  And if userspace is making memory SHARED and this point
+	 * is reached, then at least one page within the range was previously
+	 * PRIVATE, i.e. the slot's possible hugepage ranges are changing.
+	 * Zapping SPTEs in this case ensures KVM will reassess whether or not
+	 * a hugepage can be used for affected ranges.
+	 */
+	if (WARN_ON_ONCE(!kvm_arch_has_private_mem(kvm)))
+		return false;
+
+	return kvm_unmap_gfn_range(kvm, range);
+}
+
 static bool hugepage_test_mixed(struct kvm_memory_slot *slot, gfn_t gfn,
 				int level)
 {
diff --git a/arch/x86/kvm/mmu/mmu_internal.h b/arch/x86/kvm/mmu/mmu_internal.h
index decc1f153669..86c7cb692786 100644
--- a/arch/x86/kvm/mmu/mmu_internal.h
+++ b/arch/x86/kvm/mmu/mmu_internal.h
@@ -201,6 +201,7 @@ struct kvm_page_fault {
 
 	/* Derived from mmu and global state.  */
 	const bool is_tdp;
+	const bool is_private;
 	const bool nx_huge_page_workaround_enabled;
 
 	/*