Merge branch 'guest-memfd-mmap' into HEAD

Add support for host userspace mapping of guest_memfd-backed memory for VM
types that do NOT use support KVM_MEMORY_ATTRIBUTE_PRIVATE (which isn't
precisely the same thing as CoCo VMs, since x86's SEV-MEM and SEV-ES have
no way to detect private vs. shared).

mmap() support paves the way for several evolving KVM use cases:

* Allows VMMs like Firecracker to run guests entirely backed by
  guest_memfd [1]. This provides a unified memory management model for
  both confidential and non-confidential guests, simplifying VMM design.

* Enhanced Security via direct map removal: When combined with Patrick's
  series for direct map removal [2], this provides additional hardening
  against Spectre-like transient execution attacks by eliminating the
  need for host kernel direct maps of guest memory.

* Lays the groundwork for *restricted* mmap() support for guest_memfd-backed
  memory on CoCo platforms [3] that permit in-place sharing of guest memory
   with the host.

Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>

Documentation/virt/kvm/api.rst

@@ -6414,6 +6414,15 @@ most one mapping per page, i.e. binding multiple memory regions to a single
 guest_memfd range is not allowed (any number of memory regions can be bound to
 a single guest_memfd file, but the bound ranges must not overlap).
 
+When the capability KVM_CAP_GUEST_MEMFD_MMAP is supported, the 'flags' field
+supports GUEST_MEMFD_FLAG_MMAP.  Setting this flag on guest_memfd creation
+enables mmap() and faulting of guest_memfd memory to host userspace.
+
+When the KVM MMU performs a PFN lookup to service a guest fault and the backing
+guest_memfd has the GUEST_MEMFD_FLAG_MMAP set, then the fault will always be
+consumed from guest_memfd, regardless of whether it is a shared or a private
+fault.
+
 See KVM_SET_USER_MEMORY_REGION2 for additional details.
 
 4.143 KVM_PRE_FAULT_MEMORY

arch/arm64/kvm/Kconfig

@@ -37,6 +37,7 @@ menuconfig KVM
 	select HAVE_KVM_VCPU_RUN_PID_CHANGE
 	select SCHED_INFO
 	select GUEST_PERF_EVENTS if PERF_EVENTS
+	select KVM_GUEST_MEMFD
 	help
 	  Support hosting virtualized guest machines.
 

arch/arm64/kvm/mmu.c

@@ -1477,13 +1477,132 @@ static bool kvm_vma_is_cacheable(struct vm_area_struct *vma)
 	}
 }
 
+static int prepare_mmu_memcache(struct kvm_vcpu *vcpu, bool topup_memcache,
+				void **memcache)
+{
+	int min_pages;
+
+	if (!is_protected_kvm_enabled())
+		*memcache = &vcpu->arch.mmu_page_cache;
+	else
+		*memcache = &vcpu->arch.pkvm_memcache;
+
+	if (!topup_memcache)
+		return 0;
+
+	min_pages = kvm_mmu_cache_min_pages(vcpu->arch.hw_mmu);
+
+	if (!is_protected_kvm_enabled())
+		return kvm_mmu_topup_memory_cache(*memcache, min_pages);
+
+	return topup_hyp_memcache(*memcache, min_pages);
+}
+
+/*
+ * Potentially reduce shadow S2 permissions to match the guest's own S2. For
+ * exec faults, we'd only reach this point if the guest actually allowed it (see
+ * kvm_s2_handle_perm_fault).
+ *
+ * Also encode the level of the original translation in the SW bits of the leaf
+ * entry as a proxy for the span of that translation. This will be retrieved on
+ * TLB invalidation from the guest and used to limit the invalidation scope if a
+ * TTL hint or a range isn't provided.
+ */
+static void adjust_nested_fault_perms(struct kvm_s2_trans *nested,
+				      enum kvm_pgtable_prot *prot,
+				      bool *writable)
+{
+	*writable &= kvm_s2_trans_writable(nested);
+	if (!kvm_s2_trans_readable(nested))
+		*prot &= ~KVM_PGTABLE_PROT_R;
+
+	*prot |= kvm_encode_nested_level(nested);
+}
+
+#define KVM_PGTABLE_WALK_MEMABORT_FLAGS (KVM_PGTABLE_WALK_HANDLE_FAULT | KVM_PGTABLE_WALK_SHARED)
+
+static int gmem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
+		      struct kvm_s2_trans *nested,
+		      struct kvm_memory_slot *memslot, bool is_perm)
+{
+	bool write_fault, exec_fault, writable;
+	enum kvm_pgtable_walk_flags flags = KVM_PGTABLE_WALK_MEMABORT_FLAGS;
+	enum kvm_pgtable_prot prot = KVM_PGTABLE_PROT_R;
+	struct kvm_pgtable *pgt = vcpu->arch.hw_mmu->pgt;
+	unsigned long mmu_seq;
+	struct page *page;
+	struct kvm *kvm = vcpu->kvm;
+	void *memcache;
+	kvm_pfn_t pfn;
+	gfn_t gfn;
+	int ret;
+
+	ret = prepare_mmu_memcache(vcpu, true, &memcache);
+	if (ret)
+		return ret;
+
+	if (nested)
+		gfn = kvm_s2_trans_output(nested) >> PAGE_SHIFT;
+	else
+		gfn = fault_ipa >> PAGE_SHIFT;
+
+	write_fault = kvm_is_write_fault(vcpu);
+	exec_fault = kvm_vcpu_trap_is_exec_fault(vcpu);
+
+	VM_WARN_ON_ONCE(write_fault && exec_fault);
+
+	mmu_seq = kvm->mmu_invalidate_seq;
+	/* Pairs with the smp_wmb() in kvm_mmu_invalidate_end(). */
+	smp_rmb();
+
+	ret = kvm_gmem_get_pfn(kvm, memslot, gfn, &pfn, &page, NULL);
+	if (ret) {
+		kvm_prepare_memory_fault_exit(vcpu, fault_ipa, PAGE_SIZE,
+					      write_fault, exec_fault, false);
+		return ret;
+	}
+
+	writable = !(memslot->flags & KVM_MEM_READONLY);
+
+	if (nested)
+		adjust_nested_fault_perms(nested, &prot, &writable);
+
+	if (writable)
+		prot |= KVM_PGTABLE_PROT_W;
+
+	if (exec_fault ||
+	    (cpus_have_final_cap(ARM64_HAS_CACHE_DIC) &&
+	     (!nested || kvm_s2_trans_executable(nested))))
+		prot |= KVM_PGTABLE_PROT_X;
+
+	kvm_fault_lock(kvm);
+	if (mmu_invalidate_retry(kvm, mmu_seq)) {
+		ret = -EAGAIN;
+		goto out_unlock;
+	}
+
+	ret = KVM_PGT_FN(kvm_pgtable_stage2_map)(pgt, fault_ipa, PAGE_SIZE,
+						 __pfn_to_phys(pfn), prot,
+						 memcache, flags);
+
+out_unlock:
+	kvm_release_faultin_page(kvm, page, !!ret, writable);
+	kvm_fault_unlock(kvm);
+
+	if (writable && !ret)
+		mark_page_dirty_in_slot(kvm, memslot, gfn);
+
+	return ret != -EAGAIN ? ret : 0;
+}
+
 static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
 			  struct kvm_s2_trans *nested,
 			  struct kvm_memory_slot *memslot, unsigned long hva,
 			  bool fault_is_perm)
 {
 	int ret = 0;
-	bool write_fault, writable, force_pte = false;
+	bool topup_memcache;
+	bool write_fault, writable;
 	bool exec_fault, mte_allowed, is_vma_cacheable;
 	bool s2_force_noncacheable = false, vfio_allow_any_uc = false;
 	unsigned long mmu_seq;
@@ -1495,28 +1614,19 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
 	gfn_t gfn;
 	kvm_pfn_t pfn;
 	bool logging_active = memslot_is_logging(memslot);
+	bool force_pte = logging_active;
 	long vma_pagesize, fault_granule;
 	enum kvm_pgtable_prot prot = KVM_PGTABLE_PROT_R;
 	struct kvm_pgtable *pgt;
 	struct page *page;
 	vm_flags_t vm_flags;
-	enum kvm_pgtable_walk_flags flags = KVM_PGTABLE_WALK_HANDLE_FAULT | KVM_PGTABLE_WALK_SHARED;
+	enum kvm_pgtable_walk_flags flags = KVM_PGTABLE_WALK_MEMABORT_FLAGS;
 
 	if (fault_is_perm)
 		fault_granule = kvm_vcpu_trap_get_perm_fault_granule(vcpu);
 	write_fault = kvm_is_write_fault(vcpu);
 	exec_fault = kvm_vcpu_trap_is_exec_fault(vcpu);
-	VM_BUG_ON(write_fault && exec_fault);
+	VM_WARN_ON_ONCE(write_fault && exec_fault);
-
-	if (fault_is_perm && !write_fault && !exec_fault) {
-		kvm_err("Unexpected L2 read permission error\n");
-		return -EFAULT;
-	}
-
-	if (!is_protected_kvm_enabled())
-		memcache = &vcpu->arch.mmu_page_cache;
-	else
-		memcache = &vcpu->arch.pkvm_memcache;
 
 	/*
 	 * Permission faults just need to update the existing leaf entry,
@@ -1524,17 +1634,10 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
 	 * 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)) {
+	topup_memcache = !fault_is_perm || (logging_active && write_fault);
-		int min_pages = kvm_mmu_cache_min_pages(vcpu->arch.hw_mmu);
+	ret = prepare_mmu_memcache(vcpu, topup_memcache, &memcache);
-
+	if (ret)
-		if (!is_protected_kvm_enabled())
+		return ret;
-			ret = kvm_mmu_topup_memory_cache(memcache, min_pages);
-		else
-			ret = topup_hyp_memcache(memcache, min_pages);
-
-		if (ret)
-			return ret;
-	}
 
 	/*
 	 * Let's check if we will get back a huge page backed by hugetlbfs, or
@@ -1548,16 +1651,10 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
 		return -EFAULT;
 	}
 
-	/*
+	if (force_pte)
-	 * logging_active is guaranteed to never be true for VM_PFNMAP
-	 * memslots.
-	 */
-	if (logging_active) {
-		force_pte = true;
 		vma_shift = PAGE_SHIFT;
-	} else {
+	else
 		vma_shift = get_vma_page_shift(vma, hva);
-	}
 
 	switch (vma_shift) {
 #ifndef __PAGETABLE_PMD_FOLDED
@@ -1609,7 +1706,7 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
 			max_map_size = PAGE_SIZE;
 
 		force_pte = (max_map_size == PAGE_SIZE);
-		vma_pagesize = min(vma_pagesize, (long)max_map_size);
+		vma_pagesize = min_t(long, vma_pagesize, max_map_size);
 	}
 
 	/*
@@ -1642,7 +1739,7 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
 	 * Rely on mmap_read_unlock() for an implicit smp_rmb(), which pairs
 	 * with the smp_wmb() in kvm_mmu_invalidate_end().
 	 */
-	mmu_seq = vcpu->kvm->mmu_invalidate_seq;
+	mmu_seq = kvm->mmu_invalidate_seq;
 	mmap_read_unlock(current->mm);
 
 	pfn = __kvm_faultin_pfn(memslot, gfn, write_fault ? FOLL_WRITE : 0,
@@ -1698,24 +1795,8 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
 	if (exec_fault && s2_force_noncacheable)
 		return -ENOEXEC;
 
-	/*
+	if (nested)
-	 * Potentially reduce shadow S2 permissions to match the guest's own
+		adjust_nested_fault_perms(nested, &prot, &writable);
-	 * S2. For exec faults, we'd only reach this point if the guest
-	 * actually allowed it (see kvm_s2_handle_perm_fault).
-	 *
-	 * Also encode the level of the original translation in the SW bits
-	 * of the leaf entry as a proxy for the span of that translation.
-	 * This will be retrieved on TLB invalidation from the guest and
-	 * used to limit the invalidation scope if a TTL hint or a range
-	 * isn't provided.
-	 */
-	if (nested) {
-		writable &= kvm_s2_trans_writable(nested);
-		if (!kvm_s2_trans_readable(nested))
-			prot &= ~KVM_PGTABLE_PROT_R;
-
-		prot |= kvm_encode_nested_level(nested);
-	}
 
 	kvm_fault_lock(kvm);
 	pgt = vcpu->arch.hw_mmu->pgt;
@@ -1981,8 +2062,15 @@ int kvm_handle_guest_abort(struct kvm_vcpu *vcpu)
 		goto out_unlock;
 	}
 
-	ret = user_mem_abort(vcpu, fault_ipa, nested, memslot, hva,
+	VM_WARN_ON_ONCE(kvm_vcpu_trap_is_permission_fault(vcpu) &&
-			     esr_fsc_is_permission_fault(esr));
+			!write_fault && !kvm_vcpu_trap_is_exec_fault(vcpu));
+
+	if (kvm_slot_has_gmem(memslot))
+		ret = gmem_abort(vcpu, fault_ipa, nested, memslot,
+				 esr_fsc_is_permission_fault(esr));
+	else
+		ret = user_mem_abort(vcpu, fault_ipa, nested, memslot, hva,
+				     esr_fsc_is_permission_fault(esr));
 	if (ret == 0)
 		ret = 1;
 out:
@@ -2214,6 +2302,13 @@ int kvm_arch_prepare_memory_region(struct kvm *kvm,
 	if ((new->base_gfn + new->npages) > (kvm_phys_size(&kvm->arch.mmu) >> PAGE_SHIFT))
 		return -EFAULT;
 
+	/*
+	 * Only support guest_memfd backed memslots with mappable memory, since
+	 * there aren't any CoCo VMs that support only private memory on arm64.
+	 */
+	if (kvm_slot_has_gmem(new) && !kvm_memslot_is_gmem_only(new))
+		return -EINVAL;
+
 	hva = new->userspace_addr;
 	reg_end = hva + (new->npages << PAGE_SHIFT);
 

arch/arm64/kvm/nested.c

@@ -1172,8 +1172,9 @@ static u64 read_vncr_el2(struct kvm_vcpu *vcpu)
 	return (u64)sign_extend64(__vcpu_sys_reg(vcpu, VNCR_EL2), 48);
 }
 
-static int kvm_translate_vncr(struct kvm_vcpu *vcpu)
+static int kvm_translate_vncr(struct kvm_vcpu *vcpu, bool *is_gmem)
 {
+	struct kvm_memory_slot *memslot;
 	bool write_fault, writable;
 	unsigned long mmu_seq;
 	struct vncr_tlb *vt;
@@ -1216,10 +1217,25 @@ static int kvm_translate_vncr(struct kvm_vcpu *vcpu)
 	smp_rmb();
 
 	gfn = vt->wr.pa >> PAGE_SHIFT;
-	pfn = kvm_faultin_pfn(vcpu, gfn, write_fault, &writable, &page);
+	memslot = gfn_to_memslot(vcpu->kvm, gfn);
-	if (is_error_noslot_pfn(pfn) || (write_fault && !writable))
+	if (!memslot)
 		return -EFAULT;
 
+	*is_gmem = kvm_slot_has_gmem(memslot);
+	if (!*is_gmem) {
+		pfn = __kvm_faultin_pfn(memslot, gfn, write_fault ? FOLL_WRITE : 0,
+					&writable, &page);
+		if (is_error_noslot_pfn(pfn) || (write_fault && !writable))
+			return -EFAULT;
+	} else {
+		ret = kvm_gmem_get_pfn(vcpu->kvm, memslot, gfn, &pfn, &page, NULL);
+		if (ret) {
+			kvm_prepare_memory_fault_exit(vcpu, vt->wr.pa, PAGE_SIZE,
+					      write_fault, false, false);
+			return ret;
+		}
+	}
+
 	scoped_guard(write_lock, &vcpu->kvm->mmu_lock) {
 		if (mmu_invalidate_retry(vcpu->kvm, mmu_seq))
 			return -EAGAIN;
@@ -1292,23 +1308,36 @@ int kvm_handle_vncr_abort(struct kvm_vcpu *vcpu)
 	if (esr_fsc_is_permission_fault(esr)) {
 		inject_vncr_perm(vcpu);
 	} else if (esr_fsc_is_translation_fault(esr)) {
-		bool valid;
+		bool valid, is_gmem = false;
 		int ret;
 
 		scoped_guard(read_lock, &vcpu->kvm->mmu_lock)
 			valid = kvm_vncr_tlb_lookup(vcpu);
 
 		if (!valid)
-			ret = kvm_translate_vncr(vcpu);
+			ret = kvm_translate_vncr(vcpu, &is_gmem);
 		else
 			ret = -EPERM;
 
 		switch (ret) {
 		case -EAGAIN:
-		case -ENOMEM:
 			/* Let's try again... */
 			break;
+		case -ENOMEM:
+			/*
+			 * For guest_memfd, this indicates that it failed to
+			 * create a folio to back the memory. Inform userspace.
+			 */
+			if (is_gmem)
+				return 0;
+			/* Otherwise, let's try again... */
+			break;
 		case -EFAULT:
+		case -EIO:
+		case -EHWPOISON:
+			if (is_gmem)
+				return 0;
+			fallthrough;
 		case -EINVAL:
 		case -ENOENT:
 		case -EACCES:

arch/x86/include/asm/kvm-x86-ops.h

@@ -145,7 +145,7 @@ KVM_X86_OP_OPTIONAL_RET0(vcpu_get_apicv_inhibit_reasons);
 KVM_X86_OP_OPTIONAL(get_untagged_addr)
 KVM_X86_OP_OPTIONAL(alloc_apic_backing_page)
 KVM_X86_OP_OPTIONAL_RET0(gmem_prepare)
-KVM_X86_OP_OPTIONAL_RET0(private_max_mapping_level)
+KVM_X86_OP_OPTIONAL_RET0(gmem_max_mapping_level)
 KVM_X86_OP_OPTIONAL(gmem_invalidate)
 
 #undef KVM_X86_OP

arch/x86/include/asm/kvm_host.h

@@ -1922,7 +1922,7 @@ struct kvm_x86_ops {
 	void *(*alloc_apic_backing_page)(struct kvm_vcpu *vcpu);
 	int (*gmem_prepare)(struct kvm *kvm, kvm_pfn_t pfn, gfn_t gfn, int max_order);
 	void (*gmem_invalidate)(kvm_pfn_t start, kvm_pfn_t end);
-	int (*private_max_mapping_level)(struct kvm *kvm, kvm_pfn_t pfn);
+	int (*gmem_max_mapping_level)(struct kvm *kvm, kvm_pfn_t pfn, bool is_private);
 };
 
 struct kvm_x86_nested_ops {
@@ -2276,10 +2276,8 @@ void kvm_configure_mmu(bool enable_tdp, int tdp_forced_root_level,
 		       int tdp_max_root_level, int tdp_huge_page_level);
 
 
-#ifdef CONFIG_KVM_PRIVATE_MEM
+#ifdef CONFIG_KVM_GENERIC_MEMORY_ATTRIBUTES
 #define kvm_arch_has_private_mem(kvm) ((kvm)->arch.has_private_mem)
-#else
-#define kvm_arch_has_private_mem(kvm) false
 #endif
 
 #define kvm_arch_has_readonly_mem(kvm) (!(kvm)->arch.has_protected_state)

arch/x86/kvm/Kconfig

@@ -46,8 +46,8 @@ config KVM_X86
 	select HAVE_KVM_PM_NOTIFIER if PM
 	select KVM_GENERIC_HARDWARE_ENABLING
 	select KVM_GENERIC_PRE_FAULT_MEMORY
-	select KVM_GENERIC_PRIVATE_MEM if KVM_SW_PROTECTED_VM
 	select KVM_WERROR if WERROR
+	select KVM_GUEST_MEMFD if X86_64
 
 config KVM
 	tristate "Kernel-based Virtual Machine (KVM) support"
@@ -74,7 +74,7 @@ config KVM_WERROR
 	# FRAME_WARN, i.e. KVM_WERROR=y with KASAN=y requires special tuning.
 	# Building KVM with -Werror and KASAN is still doable via enabling
 	# the kernel-wide WERROR=y.
-	depends on KVM && ((EXPERT && !KASAN) || WERROR)
+	depends on KVM_X86 && ((EXPERT && !KASAN) || WERROR)
 	help
 	  Add -Werror to the build flags for KVM.
 
@@ -83,7 +83,8 @@ config KVM_WERROR
 config KVM_SW_PROTECTED_VM
 	bool "Enable support for KVM software-protected VMs"
 	depends on EXPERT
-	depends on KVM && X86_64
+	depends on KVM_X86 && X86_64
+	select KVM_GENERIC_MEMORY_ATTRIBUTES
 	help
 	  Enable support for KVM software-protected VMs.  Currently, software-
 	  protected VMs are purely a development and testing vehicle for
@@ -95,8 +96,6 @@ config KVM_SW_PROTECTED_VM
 config KVM_INTEL
 	tristate "KVM for Intel (and compatible) processors support"
 	depends on KVM && IA32_FEAT_CTL
-	select KVM_GENERIC_PRIVATE_MEM if INTEL_TDX_HOST
-	select KVM_GENERIC_MEMORY_ATTRIBUTES if INTEL_TDX_HOST
 	help
 	  Provides support for KVM on processors equipped with Intel's VT
 	  extensions, a.k.a. Virtual Machine Extensions (VMX).
@@ -135,6 +134,8 @@ config KVM_INTEL_TDX
 	bool "Intel Trust Domain Extensions (TDX) support"
 	default y
 	depends on INTEL_TDX_HOST
+	select KVM_GENERIC_MEMORY_ATTRIBUTES
+	select HAVE_KVM_ARCH_GMEM_POPULATE
 	help
 	  Provides support for launching Intel Trust Domain Extensions (TDX)
 	  confidential VMs on Intel processors.
@@ -157,9 +158,10 @@ config KVM_AMD_SEV
 	depends on KVM_AMD && X86_64
 	depends on CRYPTO_DEV_SP_PSP && !(KVM_AMD=y && CRYPTO_DEV_CCP_DD=m)
 	select ARCH_HAS_CC_PLATFORM
-	select KVM_GENERIC_PRIVATE_MEM
+	select KVM_GENERIC_MEMORY_ATTRIBUTES
 	select HAVE_KVM_ARCH_GMEM_PREPARE
 	select HAVE_KVM_ARCH_GMEM_INVALIDATE
+	select HAVE_KVM_ARCH_GMEM_POPULATE
 	help
 	  Provides support for launching encrypted VMs which use Secure
 	  Encrypted Virtualization (SEV), Secure Encrypted Virtualization with
@@ -169,7 +171,7 @@ config KVM_AMD_SEV
 config KVM_IOAPIC
 	bool "I/O APIC, PIC, and PIT emulation"
 	default y
-	depends on KVM
+	depends on KVM_X86
 	help
 	  Provides support for KVM to emulate an I/O APIC, PIC, and PIT, i.e.
 	  for full in-kernel APIC emulation.
@@ -179,7 +181,7 @@ config KVM_IOAPIC
 config KVM_SMM
 	bool "System Management Mode emulation"
 	default y
-	depends on KVM
+	depends on KVM_X86
 	help
 	  Provides support for KVM to emulate System Management Mode (SMM)
 	  in virtual machines.  This can be used by the virtual machine
@@ -189,7 +191,7 @@ config KVM_SMM
 
 config KVM_HYPERV
 	bool "Support for Microsoft Hyper-V emulation"
-	depends on KVM
+	depends on KVM_X86
 	default y
 	help
 	  Provides KVM support for emulating Microsoft Hyper-V.  This allows KVM
@@ -203,7 +205,7 @@ config KVM_HYPERV
 
 config KVM_XEN
 	bool "Support for Xen hypercall interface"
-	depends on KVM
+	depends on KVM_X86
 	help
 	  Provides KVM support for the hosting Xen HVM guests and
 	  passing Xen hypercalls to userspace.
@@ -213,7 +215,7 @@ config KVM_XEN
 config KVM_PROVE_MMU
 	bool "Prove KVM MMU correctness"
 	depends on DEBUG_KERNEL
-	depends on KVM
+	depends on KVM_X86
 	depends on EXPERT
 	help
 	  Enables runtime assertions in KVM's MMU that are too costly to enable
@@ -228,7 +230,7 @@ config KVM_EXTERNAL_WRITE_TRACKING
 
 config KVM_MAX_NR_VCPUS
 	int "Maximum number of vCPUs per KVM guest"
-	depends on KVM
+	depends on KVM_X86
 	range 1024 4096
 	default 4096 if MAXSMP
 	default 1024

arch/x86/kvm/mmu/mmu.c

@@ -3285,12 +3285,72 @@ static int host_pfn_mapping_level(struct kvm *kvm, gfn_t gfn,
 	return level;
 }
 
-static int __kvm_mmu_max_mapping_level(struct kvm *kvm,
+static u8 kvm_max_level_for_order(int order)
-				       const struct kvm_memory_slot *slot,
+{
-				       gfn_t gfn, int max_level, bool is_private)
+	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 u8 kvm_gmem_max_mapping_level(struct kvm *kvm, struct kvm_page_fault *fault,
+				     const struct kvm_memory_slot *slot, gfn_t gfn,
+				     bool is_private)
+{
+	u8 max_level, coco_level;
+	kvm_pfn_t pfn;
+
+	/* For faults, use the gmem information that was resolved earlier. */
+	if (fault) {
+		pfn = fault->pfn;
+		max_level = fault->max_level;
+	} else {
+		/* TODO: Call into guest_memfd once hugepages are supported. */
+		WARN_ONCE(1, "Get pfn+order from guest_memfd");
+		pfn = KVM_PFN_ERR_FAULT;
+		max_level = PG_LEVEL_4K;
+	}
+
+	if (max_level == PG_LEVEL_4K)
+		return max_level;
+
+	/*
+	 * CoCo may influence the max mapping level, e.g. due to RMP or S-EPT
+	 * restrictions.  A return of '0' means "no additional restrictions", to
+	 * allow for using an optional "ret0" static call.
+	 */
+	coco_level = kvm_x86_call(gmem_max_mapping_level)(kvm, pfn, is_private);
+	if (coco_level)
+		max_level = min(max_level, coco_level);
+
+	return max_level;
+}
+
+int kvm_mmu_max_mapping_level(struct kvm *kvm, struct kvm_page_fault *fault,
+			      const struct kvm_memory_slot *slot, gfn_t gfn)
 {
 	struct kvm_lpage_info *linfo;
-	int host_level;
+	int host_level, max_level;
+	bool is_private;
+
+	lockdep_assert_held(&kvm->mmu_lock);
+
+	if (fault) {
+		max_level = fault->max_level;
+		is_private = fault->is_private;
+	} else {
+		max_level = PG_LEVEL_NUM;
+		is_private = kvm_mem_is_private(kvm, gfn);
+	}
 
 	max_level = min(max_level, max_huge_page_level);
 	for ( ; max_level > PG_LEVEL_4K; max_level--) {
@@ -3299,25 +3359,17 @@ static 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;
 
-	host_level = host_pfn_mapping_level(kvm, gfn, slot);
+	if (is_private || kvm_memslot_is_gmem_only(slot))
+		host_level = kvm_gmem_max_mapping_level(kvm, fault, slot, gfn,
+							is_private);
+	else
+		host_level = host_pfn_mapping_level(kvm, gfn, slot);
 	return min(host_level, max_level);
 }
 
-int kvm_mmu_max_mapping_level(struct kvm *kvm,
-			      const struct kvm_memory_slot *slot, gfn_t gfn)
-{
-	bool is_private = kvm_slot_can_be_private(slot) &&
-			  kvm_mem_is_private(kvm, gfn);
-
-	return __kvm_mmu_max_mapping_level(kvm, slot, gfn, PG_LEVEL_NUM, is_private);
-}
-
 void kvm_mmu_hugepage_adjust(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault)
 {
 	struct kvm_memory_slot *slot = fault->slot;
@@ -3338,9 +3390,8 @@ 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->req_level = kvm_mmu_max_mapping_level(vcpu->kvm, fault,
-						       fault->gfn, fault->max_level,
+						     fault->slot, fault->gfn);
-						       fault->is_private);
 	if (fault->req_level == PG_LEVEL_4K || fault->huge_page_disallowed)
 		return;
 
@@ -4503,42 +4554,6 @@ void kvm_arch_async_page_ready(struct kvm_vcpu *vcpu, struct kvm_async_pf *work)
 		vcpu->stat.pf_fixed++;
 }
 
-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 u8 kvm_max_private_mapping_level(struct kvm *kvm, kvm_pfn_t pfn,
-					u8 max_level, int gmem_order)
-{
-	u8 req_max_level;
-
-	if (max_level == PG_LEVEL_4K)
-		return PG_LEVEL_4K;
-
-	max_level = min(kvm_max_level_for_order(gmem_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);
-
-	return max_level;
-}
-
 static void kvm_mmu_finish_page_fault(struct kvm_vcpu *vcpu,
 				      struct kvm_page_fault *fault, int r)
 {
@@ -4546,12 +4561,12 @@ 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,
+static int kvm_mmu_faultin_pfn_gmem(struct kvm_vcpu *vcpu,
-				       struct kvm_page_fault *fault)
+				    struct kvm_page_fault *fault)
 {
 	int max_order, r;
 
-	if (!kvm_slot_can_be_private(fault->slot)) {
+	if (!kvm_slot_has_gmem(fault->slot)) {
 		kvm_mmu_prepare_memory_fault_exit(vcpu, fault);
 		return -EFAULT;
 	}
@@ -4564,8 +4579,7 @@ static int kvm_mmu_faultin_pfn_private(struct kvm_vcpu *vcpu,
 	}
 
 	fault->map_writable = !(fault->slot->flags & KVM_MEM_READONLY);
-	fault->max_level = kvm_max_private_mapping_level(vcpu->kvm, fault->pfn,
+	fault->max_level = kvm_max_level_for_order(max_order);
-							 fault->max_level, max_order);
 
 	return RET_PF_CONTINUE;
 }
@@ -4575,8 +4589,8 @@ static int __kvm_mmu_faultin_pfn(struct kvm_vcpu *vcpu,
 {
 	unsigned int foll = fault->write ? FOLL_WRITE : 0;
 
-	if (fault->is_private)
+	if (fault->is_private || kvm_memslot_is_gmem_only(fault->slot))
-		return kvm_mmu_faultin_pfn_private(vcpu, fault);
+		return kvm_mmu_faultin_pfn_gmem(vcpu, fault);
 
 	foll |= FOLL_NOWAIT;
 	fault->pfn = __kvm_faultin_pfn(fault->slot, fault->gfn, foll,
@@ -7165,7 +7179,7 @@ static bool kvm_mmu_zap_collapsible_spte(struct kvm *kvm,
 		 * mapping if the indirect sp has level = 1.
 		 */
 		if (sp->role.direct &&
-		    sp->role.level < kvm_mmu_max_mapping_level(kvm, slot, sp->gfn)) {
+		    sp->role.level < kvm_mmu_max_mapping_level(kvm, NULL, slot, sp->gfn)) {
 			kvm_zap_one_rmap_spte(kvm, rmap_head, sptep);
 
 			if (kvm_available_flush_remote_tlbs_range())

arch/x86/kvm/mmu/mmu_internal.h

@@ -411,7 +411,7 @@ static inline int kvm_mmu_do_page_fault(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa,
 	return r;
 }
 
-int kvm_mmu_max_mapping_level(struct kvm *kvm,
+int kvm_mmu_max_mapping_level(struct kvm *kvm, struct kvm_page_fault *fault,
 			      const struct kvm_memory_slot *slot, gfn_t gfn);
 void kvm_mmu_hugepage_adjust(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault);
 void disallowed_hugepage_adjust(struct kvm_page_fault *fault, u64 spte, int cur_level);

arch/x86/kvm/mmu/tdp_mmu.c

@@ -1813,7 +1813,7 @@ static void recover_huge_pages_range(struct kvm *kvm,
 		if (iter.gfn < start || iter.gfn >= end)
 			continue;
 
-		max_mapping_level = kvm_mmu_max_mapping_level(kvm, slot, iter.gfn);
+		max_mapping_level = kvm_mmu_max_mapping_level(kvm, NULL, slot, iter.gfn);
 		if (max_mapping_level < iter.level)
 			continue;
 

arch/x86/kvm/svm/sev.c

@@ -2361,7 +2361,7 @@ static int snp_launch_update(struct kvm *kvm, struct kvm_sev_cmd *argp)
 	mutex_lock(&kvm->slots_lock);
 
 	memslot = gfn_to_memslot(kvm, params.gfn_start);
-	if (!kvm_slot_can_be_private(memslot)) {
+	if (!kvm_slot_has_gmem(memslot)) {
 		ret = -EINVAL;
 		goto out;
 	}
@@ -4715,7 +4715,7 @@ void sev_handle_rmp_fault(struct kvm_vcpu *vcpu, gpa_t gpa, u64 error_code)
 	}
 
 	slot = gfn_to_memslot(kvm, gfn);
-	if (!kvm_slot_can_be_private(slot)) {
+	if (!kvm_slot_has_gmem(slot)) {
 		pr_warn_ratelimited("SEV: Unexpected RMP fault, non-private slot for GPA 0x%llx\n",
 				    gpa);
 		return;
@@ -4943,7 +4943,7 @@ void sev_gmem_invalidate(kvm_pfn_t start, kvm_pfn_t end)
 	}
 }
 
-int sev_private_max_mapping_level(struct kvm *kvm, kvm_pfn_t pfn)
+int sev_gmem_max_mapping_level(struct kvm *kvm, kvm_pfn_t pfn, bool is_private)
 {
 	int level, rc;
 	bool assigned;

arch/x86/kvm/svm/svm.c

@@ -5180,7 +5180,7 @@ static struct kvm_x86_ops svm_x86_ops __initdata = {
 
 	.gmem_prepare = sev_gmem_prepare,
 	.gmem_invalidate = sev_gmem_invalidate,
-	.private_max_mapping_level = sev_private_max_mapping_level,
+	.gmem_max_mapping_level = sev_gmem_max_mapping_level,
 };
 
 /*

arch/x86/kvm/svm/svm.h

@@ -866,7 +866,7 @@ void sev_handle_rmp_fault(struct kvm_vcpu *vcpu, gpa_t gpa, u64 error_code);
 void sev_snp_init_protected_guest_state(struct kvm_vcpu *vcpu);
 int sev_gmem_prepare(struct kvm *kvm, kvm_pfn_t pfn, gfn_t gfn, int max_order);
 void sev_gmem_invalidate(kvm_pfn_t start, kvm_pfn_t end);
-int sev_private_max_mapping_level(struct kvm *kvm, kvm_pfn_t pfn);
+int sev_gmem_max_mapping_level(struct kvm *kvm, kvm_pfn_t pfn, bool is_private);
 struct vmcb_save_area *sev_decrypt_vmsa(struct kvm_vcpu *vcpu);
 void sev_free_decrypted_vmsa(struct kvm_vcpu *vcpu, struct vmcb_save_area *vmsa);
 #else
@@ -895,7 +895,7 @@ static inline int sev_gmem_prepare(struct kvm *kvm, kvm_pfn_t pfn, gfn_t gfn, in
 	return 0;
 }
 static inline void sev_gmem_invalidate(kvm_pfn_t start, kvm_pfn_t end) {}
-static inline int sev_private_max_mapping_level(struct kvm *kvm, kvm_pfn_t pfn)
+static inline int sev_gmem_max_mapping_level(struct kvm *kvm, kvm_pfn_t pfn, bool is_private)
 {
 	return 0;
 }

arch/x86/kvm/vmx/main.c

@@ -831,10 +831,11 @@ static int vt_vcpu_mem_enc_ioctl(struct kvm_vcpu *vcpu, void __user *argp)
 	return tdx_vcpu_ioctl(vcpu, argp);
 }
 
-static int vt_gmem_private_max_mapping_level(struct kvm *kvm, kvm_pfn_t pfn)
+static int vt_gmem_max_mapping_level(struct kvm *kvm, kvm_pfn_t pfn,
+				     bool is_private)
 {
 	if (is_td(kvm))
-		return tdx_gmem_private_max_mapping_level(kvm, pfn);
+		return tdx_gmem_max_mapping_level(kvm, pfn, is_private);
 
 	return 0;
 }
@@ -1005,7 +1006,7 @@ struct kvm_x86_ops vt_x86_ops __initdata = {
 	.mem_enc_ioctl = vt_op_tdx_only(mem_enc_ioctl),
 	.vcpu_mem_enc_ioctl = vt_op_tdx_only(vcpu_mem_enc_ioctl),
 
-	.private_max_mapping_level = vt_op_tdx_only(gmem_private_max_mapping_level)
+	.gmem_max_mapping_level = vt_op_tdx_only(gmem_max_mapping_level)
 };
 
 struct kvm_x86_init_ops vt_init_ops __initdata = {

arch/x86/kvm/vmx/tdx.c

@@ -3318,8 +3318,11 @@ int tdx_vcpu_ioctl(struct kvm_vcpu *vcpu, void __user *argp)
 	return ret;
 }
 
-int tdx_gmem_private_max_mapping_level(struct kvm *kvm, kvm_pfn_t pfn)
+int tdx_gmem_max_mapping_level(struct kvm *kvm, kvm_pfn_t pfn, bool is_private)
 {
+	if (!is_private)
+		return 0;
+
 	return PG_LEVEL_4K;
 }
 

arch/x86/kvm/vmx/x86_ops.h

@@ -153,7 +153,7 @@ int tdx_vcpu_ioctl(struct kvm_vcpu *vcpu, void __user *argp);
 void tdx_flush_tlb_current(struct kvm_vcpu *vcpu);
 void tdx_flush_tlb_all(struct kvm_vcpu *vcpu);
 void tdx_load_mmu_pgd(struct kvm_vcpu *vcpu, hpa_t root_hpa, int root_level);
-int tdx_gmem_private_max_mapping_level(struct kvm *kvm, kvm_pfn_t pfn);
+int tdx_gmem_max_mapping_level(struct kvm *kvm, kvm_pfn_t pfn, bool is_private);
 #endif
 
 #endif /* __KVM_X86_VMX_X86_OPS_H */

arch/x86/kvm/x86.c

@@ -13521,6 +13521,16 @@ bool kvm_arch_no_poll(struct kvm_vcpu *vcpu)
 }
 EXPORT_SYMBOL_GPL(kvm_arch_no_poll);
 
+#ifdef CONFIG_KVM_GUEST_MEMFD
+/*
+ * KVM doesn't yet support mmap() on guest_memfd for VMs with private memory
+ * (the private vs. shared tracking needs to be moved into guest_memfd).
+ */
+bool kvm_arch_supports_gmem_mmap(struct kvm *kvm)
+{
+	return !kvm_arch_has_private_mem(kvm);
+}
+
 #ifdef CONFIG_HAVE_KVM_ARCH_GMEM_PREPARE
 int kvm_arch_gmem_prepare(struct kvm *kvm, gfn_t gfn, kvm_pfn_t pfn, int max_order)
 {
@@ -13534,6 +13544,7 @@ void kvm_arch_gmem_invalidate(kvm_pfn_t start, kvm_pfn_t end)
 	kvm_x86_call(gmem_invalidate)(start, end);
 }
 #endif
+#endif
 
 int kvm_spec_ctrl_test_value(u64 value)
 {

include/linux/kvm_host.h

@@ -52,9 +52,10 @@
 /*
  * The bit 16 ~ bit 31 of kvm_userspace_memory_region::flags are internally
  * used in kvm, other bits are visible for userspace which are defined in
- * include/linux/kvm_h.
+ * include/uapi/linux/kvm.h.
  */
-#define KVM_MEMSLOT_INVALID	(1UL << 16)
+#define KVM_MEMSLOT_INVALID			(1UL << 16)
+#define KVM_MEMSLOT_GMEM_ONLY			(1UL << 17)
 
 /*
  * Bit 63 of the memslot generation number is an "update in-progress flag",
@@ -602,7 +603,7 @@ struct kvm_memory_slot {
 	short id;
 	u16 as_id;
 
-#ifdef CONFIG_KVM_PRIVATE_MEM
+#ifdef CONFIG_KVM_GUEST_MEMFD
 	struct {
 		/*
 		 * Writes protected by kvm->slots_lock.  Acquiring a
@@ -615,7 +616,7 @@ struct kvm_memory_slot {
 #endif
 };
 
-static inline bool kvm_slot_can_be_private(const struct kvm_memory_slot *slot)
+static inline bool kvm_slot_has_gmem(const struct kvm_memory_slot *slot)
 {
 	return slot && (slot->flags & KVM_MEM_GUEST_MEMFD);
 }
@@ -719,17 +720,17 @@ static inline int kvm_arch_vcpu_memslots_id(struct kvm_vcpu *vcpu)
 }
 #endif
 
-/*
+#ifndef CONFIG_KVM_GENERIC_MEMORY_ATTRIBUTES
- * Arch code must define kvm_arch_has_private_mem if support for private memory
- * is enabled.
- */
-#if !defined(kvm_arch_has_private_mem) && !IS_ENABLED(CONFIG_KVM_PRIVATE_MEM)
 static inline bool kvm_arch_has_private_mem(struct kvm *kvm)
 {
 	return false;
 }
 #endif
 
+#ifdef CONFIG_KVM_GUEST_MEMFD
+bool kvm_arch_supports_gmem_mmap(struct kvm *kvm);
+#endif
+
 #ifndef kvm_arch_has_readonly_mem
 static inline bool kvm_arch_has_readonly_mem(struct kvm *kvm)
 {
@@ -860,7 +861,7 @@ struct kvm {
 	struct notifier_block pm_notifier;
 #endif
 #ifdef CONFIG_KVM_GENERIC_MEMORY_ATTRIBUTES
-	/* Protected by slots_locks (for writes) and RCU (for reads) */
+	/* Protected by slots_lock (for writes) and RCU (for reads) */
 	struct xarray mem_attr_array;
 #endif
 	char stats_id[KVM_STATS_NAME_SIZE];
@@ -2490,6 +2491,14 @@ static inline void kvm_prepare_memory_fault_exit(struct kvm_vcpu *vcpu,
 		vcpu->run->memory_fault.flags |= KVM_MEMORY_EXIT_FLAG_PRIVATE;
 }
 
+static inline bool kvm_memslot_is_gmem_only(const struct kvm_memory_slot *slot)
+{
+	if (!IS_ENABLED(CONFIG_KVM_GUEST_MEMFD))
+		return false;
+
+	return slot->flags & KVM_MEMSLOT_GMEM_ONLY;
+}
+
 #ifdef CONFIG_KVM_GENERIC_MEMORY_ATTRIBUTES
 static inline unsigned long kvm_get_memory_attributes(struct kvm *kvm, gfn_t gfn)
 {
@@ -2505,8 +2514,7 @@ bool kvm_arch_post_set_memory_attributes(struct kvm *kvm,
 
 static inline bool kvm_mem_is_private(struct kvm *kvm, gfn_t gfn)
 {
-	return IS_ENABLED(CONFIG_KVM_PRIVATE_MEM) &&
+	return kvm_get_memory_attributes(kvm, gfn) & KVM_MEMORY_ATTRIBUTE_PRIVATE;
-	       kvm_get_memory_attributes(kvm, gfn) & KVM_MEMORY_ATTRIBUTE_PRIVATE;
 }
 #else
 static inline bool kvm_mem_is_private(struct kvm *kvm, gfn_t gfn)
@@ -2515,7 +2523,7 @@ static inline bool kvm_mem_is_private(struct kvm *kvm, gfn_t gfn)
 }
 #endif /* CONFIG_KVM_GENERIC_MEMORY_ATTRIBUTES */
 
-#ifdef CONFIG_KVM_PRIVATE_MEM
+#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);
@@ -2528,13 +2536,13 @@ static inline int kvm_gmem_get_pfn(struct kvm *kvm,
 	KVM_BUG_ON(1, kvm);
 	return -EIO;
 }
-#endif /* CONFIG_KVM_PRIVATE_MEM */
+#endif /* CONFIG_KVM_GUEST_MEMFD */
 
 #ifdef CONFIG_HAVE_KVM_ARCH_GMEM_PREPARE
 int kvm_arch_gmem_prepare(struct kvm *kvm, gfn_t gfn, kvm_pfn_t pfn, int max_order);
 #endif
 
-#ifdef CONFIG_KVM_GENERIC_PRIVATE_MEM
+#ifdef CONFIG_HAVE_KVM_ARCH_GMEM_POPULATE
 /**
  * kvm_gmem_populate() - Populate/prepare a GPA range with guest data
  *

include/uapi/linux/kvm.h

@@ -962,6 +962,7 @@ struct kvm_enable_cap {
 #define KVM_CAP_ARM_EL2_E2H0 241
 #define KVM_CAP_RISCV_MP_STATE_RESET 242
 #define KVM_CAP_ARM_CACHEABLE_PFNMAP_SUPPORTED 243
+#define KVM_CAP_GUEST_MEMFD_MMAP 244
 
 struct kvm_irq_routing_irqchip {
 	__u32 irqchip;
@@ -1598,6 +1599,7 @@ struct kvm_memory_attributes {
 #define KVM_MEMORY_ATTRIBUTE_PRIVATE           (1ULL << 3)
 
 #define KVM_CREATE_GUEST_MEMFD	_IOWR(KVMIO,  0xd4, struct kvm_create_guest_memfd)
+#define GUEST_MEMFD_FLAG_MMAP	(1ULL << 0)
 
 struct kvm_create_guest_memfd {
 	__u64 size;

tools/testing/selftests/kvm/Makefile.kvm

@@ -174,6 +174,7 @@ TEST_GEN_PROGS_arm64 += arch_timer
 TEST_GEN_PROGS_arm64 += coalesced_io_test
 TEST_GEN_PROGS_arm64 += dirty_log_perf_test
 TEST_GEN_PROGS_arm64 += get-reg-list
+TEST_GEN_PROGS_arm64 += guest_memfd_test
 TEST_GEN_PROGS_arm64 += memslot_modification_stress_test
 TEST_GEN_PROGS_arm64 += memslot_perf_test
 TEST_GEN_PROGS_arm64 += mmu_stress_test

tools/testing/selftests/kvm/guest_memfd_test.c

@@ -13,12 +13,16 @@
 
 #include <linux/bitmap.h>
 #include <linux/falloc.h>
+#include <linux/sizes.h>
+#include <setjmp.h>
+#include <signal.h>
 #include <sys/mman.h>
 #include <sys/types.h>
 #include <sys/stat.h>
 
 #include "kvm_util.h"
 #include "test_util.h"
+#include "ucall_common.h"
 
 static void test_file_read_write(int fd)
 {
@@ -34,12 +38,83 @@ static void test_file_read_write(int fd)
 		    "pwrite on a guest_mem fd should fail");
 }
 
-static void test_mmap(int fd, size_t page_size)
+static void test_mmap_supported(int fd, size_t page_size, size_t total_size)
+{
+	const char val = 0xaa;
+	char *mem;
+	size_t i;
+	int ret;
+
+	mem = mmap(NULL, total_size, PROT_READ | PROT_WRITE, MAP_PRIVATE, fd, 0);
+	TEST_ASSERT(mem == MAP_FAILED, "Copy-on-write not allowed by guest_memfd.");
+
+	mem = mmap(NULL, total_size, PROT_READ | PROT_WRITE, MAP_SHARED, fd, 0);
+	TEST_ASSERT(mem != MAP_FAILED, "mmap() for guest_memfd should succeed.");
+
+	memset(mem, val, total_size);
+	for (i = 0; i < total_size; i++)
+		TEST_ASSERT_EQ(READ_ONCE(mem[i]), val);
+
+	ret = fallocate(fd, FALLOC_FL_KEEP_SIZE | FALLOC_FL_PUNCH_HOLE, 0,
+			page_size);
+	TEST_ASSERT(!ret, "fallocate the first page should succeed.");
+
+	for (i = 0; i < page_size; i++)
+		TEST_ASSERT_EQ(READ_ONCE(mem[i]), 0x00);
+	for (; i < total_size; i++)
+		TEST_ASSERT_EQ(READ_ONCE(mem[i]), val);
+
+	memset(mem, val, page_size);
+	for (i = 0; i < total_size; i++)
+		TEST_ASSERT_EQ(READ_ONCE(mem[i]), val);
+
+	ret = munmap(mem, total_size);
+	TEST_ASSERT(!ret, "munmap() should succeed.");
+}
+
+static sigjmp_buf jmpbuf;
+void fault_sigbus_handler(int signum)
+{
+	siglongjmp(jmpbuf, 1);
+}
+
+static void test_fault_overflow(int fd, size_t page_size, size_t total_size)
+{
+	struct sigaction sa_old, sa_new = {
+		.sa_handler = fault_sigbus_handler,
+	};
+	size_t map_size = total_size * 4;
+	const char val = 0xaa;
+	char *mem;
+	size_t i;
+	int ret;
+
+	mem = mmap(NULL, map_size, PROT_READ | PROT_WRITE, MAP_SHARED, fd, 0);
+	TEST_ASSERT(mem != MAP_FAILED, "mmap() for guest_memfd should succeed.");
+
+	sigaction(SIGBUS, &sa_new, &sa_old);
+	if (sigsetjmp(jmpbuf, 1) == 0) {
+		memset(mem, 0xaa, map_size);
+		TEST_ASSERT(false, "memset() should have triggered SIGBUS.");
+	}
+	sigaction(SIGBUS, &sa_old, NULL);
+
+	for (i = 0; i < total_size; i++)
+		TEST_ASSERT_EQ(READ_ONCE(mem[i]), val);
+
+	ret = munmap(mem, map_size);
+	TEST_ASSERT(!ret, "munmap() should succeed.");
+}
+
+static void test_mmap_not_supported(int fd, size_t page_size, size_t total_size)
 {
 	char *mem;
 
 	mem = mmap(NULL, page_size, PROT_READ | PROT_WRITE, MAP_SHARED, fd, 0);
 	TEST_ASSERT_EQ(mem, MAP_FAILED);
+
+	mem = mmap(NULL, total_size, PROT_READ | PROT_WRITE, MAP_SHARED, fd, 0);
+	TEST_ASSERT_EQ(mem, MAP_FAILED);
 }
 
 static void test_file_size(int fd, size_t page_size, size_t total_size)
@@ -120,80 +195,187 @@ static void test_invalid_punch_hole(int fd, size_t page_size, size_t total_size)
 	}
 }
 
-static void test_create_guest_memfd_invalid(struct kvm_vm *vm)
+static void test_create_guest_memfd_invalid_sizes(struct kvm_vm *vm,
+						  uint64_t guest_memfd_flags,
+						  size_t page_size)
 {
-	size_t page_size = getpagesize();
-	uint64_t flag;
 	size_t size;
 	int fd;
 
 	for (size = 1; size < page_size; size++) {
-		fd = __vm_create_guest_memfd(vm, size, 0);
+		fd = __vm_create_guest_memfd(vm, size, guest_memfd_flags);
-		TEST_ASSERT(fd == -1 && errno == EINVAL,
+		TEST_ASSERT(fd < 0 && errno == EINVAL,
 			    "guest_memfd() with non-page-aligned page size '0x%lx' should fail with EINVAL",
 			    size);
 	}
-
-	for (flag = BIT(0); flag; flag <<= 1) {
-		fd = __vm_create_guest_memfd(vm, page_size, flag);
-		TEST_ASSERT(fd == -1 && errno == EINVAL,
-			    "guest_memfd() with flag '0x%lx' should fail with EINVAL",
-			    flag);
-	}
 }
 
 static void test_create_guest_memfd_multiple(struct kvm_vm *vm)
 {
 	int fd1, fd2, ret;
 	struct stat st1, st2;
+	size_t page_size = getpagesize();
 
-	fd1 = __vm_create_guest_memfd(vm, 4096, 0);
+	fd1 = __vm_create_guest_memfd(vm, page_size, 0);
 	TEST_ASSERT(fd1 != -1, "memfd creation should succeed");
 
 	ret = fstat(fd1, &st1);
 	TEST_ASSERT(ret != -1, "memfd fstat should succeed");
-	TEST_ASSERT(st1.st_size == 4096, "memfd st_size should match requested size");
+	TEST_ASSERT(st1.st_size == page_size, "memfd st_size should match requested size");
 
-	fd2 = __vm_create_guest_memfd(vm, 8192, 0);
+	fd2 = __vm_create_guest_memfd(vm, page_size * 2, 0);
 	TEST_ASSERT(fd2 != -1, "memfd creation should succeed");
 
 	ret = fstat(fd2, &st2);
 	TEST_ASSERT(ret != -1, "memfd fstat should succeed");
-	TEST_ASSERT(st2.st_size == 8192, "second memfd st_size should match requested size");
+	TEST_ASSERT(st2.st_size == page_size * 2, "second memfd st_size should match requested size");
 
 	ret = fstat(fd1, &st1);
 	TEST_ASSERT(ret != -1, "memfd fstat should succeed");
-	TEST_ASSERT(st1.st_size == 4096, "first memfd st_size should still match requested size");
+	TEST_ASSERT(st1.st_size == page_size, "first memfd st_size should still match requested size");
 	TEST_ASSERT(st1.st_ino != st2.st_ino, "different memfd should have different inode numbers");
 
 	close(fd2);
 	close(fd1);
 }
 
-int main(int argc, char *argv[])
+static void test_guest_memfd_flags(struct kvm_vm *vm, uint64_t valid_flags)
 {
-	size_t page_size;
+	size_t page_size = getpagesize();
-	size_t total_size;
+	uint64_t flag;
 	int fd;
-	struct kvm_vm *vm;
 
-	TEST_REQUIRE(kvm_has_cap(KVM_CAP_GUEST_MEMFD));
+	for (flag = BIT(0); flag; flag <<= 1) {
+		fd = __vm_create_guest_memfd(vm, page_size, flag);
+		if (flag & valid_flags) {
+			TEST_ASSERT(fd >= 0,
+				    "guest_memfd() with flag '0x%lx' should succeed",
+				    flag);
+			close(fd);
+		} else {
+			TEST_ASSERT(fd < 0 && errno == EINVAL,
+				    "guest_memfd() with flag '0x%lx' should fail with EINVAL",
+				    flag);
+		}
+	}
+}
+
+static void test_guest_memfd(unsigned long vm_type)
+{
+	uint64_t flags = 0;
+	struct kvm_vm *vm;
+	size_t total_size;
+	size_t page_size;
+	int fd;
 
 	page_size = getpagesize();
 	total_size = page_size * 4;
 
-	vm = vm_create_barebones();
+	vm = vm_create_barebones_type(vm_type);
+
+	if (vm_check_cap(vm, KVM_CAP_GUEST_MEMFD_MMAP))
+		flags |= GUEST_MEMFD_FLAG_MMAP;
 
-	test_create_guest_memfd_invalid(vm);
 	test_create_guest_memfd_multiple(vm);
+	test_create_guest_memfd_invalid_sizes(vm, flags, page_size);
 
-	fd = vm_create_guest_memfd(vm, total_size, 0);
+	fd = vm_create_guest_memfd(vm, total_size, flags);
 
 	test_file_read_write(fd);
-	test_mmap(fd, page_size);
+
+	if (flags & GUEST_MEMFD_FLAG_MMAP) {
+		test_mmap_supported(fd, page_size, total_size);
+		test_fault_overflow(fd, page_size, total_size);
+	} else {
+		test_mmap_not_supported(fd, page_size, total_size);
+	}
+
 	test_file_size(fd, page_size, total_size);
 	test_fallocate(fd, page_size, total_size);
 	test_invalid_punch_hole(fd, page_size, total_size);
 
+	test_guest_memfd_flags(vm, flags);
+
 	close(fd);
+	kvm_vm_free(vm);
+}
+
+static void guest_code(uint8_t *mem, uint64_t size)
+{
+	size_t i;
+
+	for (i = 0; i < size; i++)
+		__GUEST_ASSERT(mem[i] == 0xaa,
+			       "Guest expected 0xaa at offset %lu, got 0x%x", i, mem[i]);
+
+	memset(mem, 0xff, size);
+	GUEST_DONE();
+}
+
+static void test_guest_memfd_guest(void)
+{
+	/*
+	 * Skip the first 4gb and slot0.  slot0 maps <1gb and is used to back
+	 * the guest's code, stack, and page tables, and low memory contains
+	 * the PCI hole and other MMIO regions that need to be avoided.
+	 */
+	const uint64_t gpa = SZ_4G;
+	const int slot = 1;
+
+	struct kvm_vcpu *vcpu;
+	struct kvm_vm *vm;
+	uint8_t *mem;
+	size_t size;
+	int fd, i;
+
+	if (!kvm_has_cap(KVM_CAP_GUEST_MEMFD_MMAP))
+		return;
+
+	vm = __vm_create_shape_with_one_vcpu(VM_SHAPE_DEFAULT, &vcpu, 1, guest_code);
+
+	TEST_ASSERT(vm_check_cap(vm, KVM_CAP_GUEST_MEMFD_MMAP),
+		    "Default VM type should always support guest_memfd mmap()");
+
+	size = vm->page_size;
+	fd = vm_create_guest_memfd(vm, size, GUEST_MEMFD_FLAG_MMAP);
+	vm_set_user_memory_region2(vm, slot, KVM_MEM_GUEST_MEMFD, gpa, size, NULL, fd, 0);
+
+	mem = mmap(NULL, size, PROT_READ | PROT_WRITE, MAP_SHARED, fd, 0);
+	TEST_ASSERT(mem != MAP_FAILED, "mmap() on guest_memfd failed");
+	memset(mem, 0xaa, size);
+	munmap(mem, size);
+
+	virt_pg_map(vm, gpa, gpa);
+	vcpu_args_set(vcpu, 2, gpa, size);
+	vcpu_run(vcpu);
+
+	TEST_ASSERT_EQ(get_ucall(vcpu, NULL), UCALL_DONE);
+
+	mem = mmap(NULL, size, PROT_READ | PROT_WRITE, MAP_SHARED, fd, 0);
+	TEST_ASSERT(mem != MAP_FAILED, "mmap() on guest_memfd failed");
+	for (i = 0; i < size; i++)
+		TEST_ASSERT_EQ(mem[i], 0xff);
+
+	close(fd);
+	kvm_vm_free(vm);
+}
+
+int main(int argc, char *argv[])
+{
+	unsigned long vm_types, vm_type;
+
+	TEST_REQUIRE(kvm_has_cap(KVM_CAP_GUEST_MEMFD));
+
+	/*
+	 * Not all architectures support KVM_CAP_VM_TYPES. However, those that
+	 * support guest_memfd have that support for the default VM type.
+	 */
+	vm_types = kvm_check_cap(KVM_CAP_VM_TYPES);
+	if (!vm_types)
+		vm_types = BIT(VM_TYPE_DEFAULT);
+
+	for_each_set_bit(vm_type, &vm_types, BITS_PER_TYPE(vm_types))
+		test_guest_memfd(vm_type);
+
+	test_guest_memfd_guest();
 }

virt/kvm/Kconfig

@@ -112,19 +112,18 @@ config KVM_GENERIC_MEMORY_ATTRIBUTES
        depends on KVM_GENERIC_MMU_NOTIFIER
        bool
 
-config KVM_PRIVATE_MEM
+config KVM_GUEST_MEMFD
        select XARRAY_MULTI
        bool
 
-config KVM_GENERIC_PRIVATE_MEM
-       select KVM_GENERIC_MEMORY_ATTRIBUTES
-       select KVM_PRIVATE_MEM
-       bool
-
 config HAVE_KVM_ARCH_GMEM_PREPARE
        bool
-       depends on KVM_PRIVATE_MEM
+       depends on KVM_GUEST_MEMFD
 
 config HAVE_KVM_ARCH_GMEM_INVALIDATE
        bool
-       depends on KVM_PRIVATE_MEM
+       depends on KVM_GUEST_MEMFD
+
+config HAVE_KVM_ARCH_GMEM_POPULATE
+       bool
+       depends on KVM_GUEST_MEMFD

virt/kvm/Makefile.kvm

@@ -12,4 +12,4 @@ kvm-$(CONFIG_KVM_ASYNC_PF) += $(KVM)/async_pf.o
 kvm-$(CONFIG_HAVE_KVM_IRQ_ROUTING) += $(KVM)/irqchip.o
 kvm-$(CONFIG_HAVE_KVM_DIRTY_RING) += $(KVM)/dirty_ring.o
 kvm-$(CONFIG_HAVE_KVM_PFNCACHE) += $(KVM)/pfncache.o
-kvm-$(CONFIG_KVM_PRIVATE_MEM) += $(KVM)/guest_memfd.o
+kvm-$(CONFIG_KVM_GUEST_MEMFD) += $(KVM)/guest_memfd.o

virt/kvm/guest_memfd.c

@@ -312,7 +312,74 @@ static pgoff_t kvm_gmem_get_index(struct kvm_memory_slot *slot, gfn_t gfn)
 	return gfn - slot->base_gfn + slot->gmem.pgoff;
 }
 
+static bool kvm_gmem_supports_mmap(struct inode *inode)
+{
+	const u64 flags = (u64)inode->i_private;
+
+	return flags & GUEST_MEMFD_FLAG_MMAP;
+}
+
+static vm_fault_t kvm_gmem_fault_user_mapping(struct vm_fault *vmf)
+{
+	struct inode *inode = file_inode(vmf->vma->vm_file);
+	struct folio *folio;
+	vm_fault_t ret = VM_FAULT_LOCKED;
+
+	if (((loff_t)vmf->pgoff << PAGE_SHIFT) >= i_size_read(inode))
+		return VM_FAULT_SIGBUS;
+
+	folio = kvm_gmem_get_folio(inode, vmf->pgoff);
+	if (IS_ERR(folio)) {
+		int err = PTR_ERR(folio);
+
+		if (err == -EAGAIN)
+			return VM_FAULT_RETRY;
+
+		return vmf_error(err);
+	}
+
+	if (WARN_ON_ONCE(folio_test_large(folio))) {
+		ret = VM_FAULT_SIGBUS;
+		goto out_folio;
+	}
+
+	if (!folio_test_uptodate(folio)) {
+		clear_highpage(folio_page(folio, 0));
+		kvm_gmem_mark_prepared(folio);
+	}
+
+	vmf->page = folio_file_page(folio, vmf->pgoff);
+
+out_folio:
+	if (ret != VM_FAULT_LOCKED) {
+		folio_unlock(folio);
+		folio_put(folio);
+	}
+
+	return ret;
+}
+
+static const struct vm_operations_struct kvm_gmem_vm_ops = {
+	.fault = kvm_gmem_fault_user_mapping,
+};
+
+static int kvm_gmem_mmap(struct file *file, struct vm_area_struct *vma)
+{
+	if (!kvm_gmem_supports_mmap(file_inode(file)))
+		return -ENODEV;
+
+	if ((vma->vm_flags & (VM_SHARED | VM_MAYSHARE)) !=
+	    (VM_SHARED | VM_MAYSHARE)) {
+		return -EINVAL;
+	}
+
+	vma->vm_ops = &kvm_gmem_vm_ops;
+
+	return 0;
+}
+
 static struct file_operations kvm_gmem_fops = {
+	.mmap		= kvm_gmem_mmap,
 	.open		= generic_file_open,
 	.release	= kvm_gmem_release,
 	.fallocate	= kvm_gmem_fallocate,
@@ -391,6 +458,11 @@ static const struct inode_operations kvm_gmem_iops = {
 	.setattr	= kvm_gmem_setattr,
 };
 
+bool __weak kvm_arch_supports_gmem_mmap(struct kvm *kvm)
+{
+	return true;
+}
+
 static int __kvm_gmem_create(struct kvm *kvm, loff_t size, u64 flags)
 {
 	const char *anon_name = "[kvm-gmem]";
@@ -452,6 +524,9 @@ int kvm_gmem_create(struct kvm *kvm, struct kvm_create_guest_memfd *args)
 	u64 flags = args->flags;
 	u64 valid_flags = 0;
 
+	if (kvm_arch_supports_gmem_mmap(kvm))
+		valid_flags |= GUEST_MEMFD_FLAG_MMAP;
+
 	if (flags & ~valid_flags)
 		return -EINVAL;
 
@@ -508,6 +583,8 @@ int kvm_gmem_bind(struct kvm *kvm, struct kvm_memory_slot *slot,
 	 */
 	WRITE_ONCE(slot->gmem.file, file);
 	slot->gmem.pgoff = start;
+	if (kvm_gmem_supports_mmap(inode))
+		slot->flags |= KVM_MEMSLOT_GMEM_ONLY;
 
 	xa_store_range(&gmem->bindings, start, end - 1, slot, GFP_KERNEL);
 	filemap_invalidate_unlock(inode->i_mapping);
@@ -627,7 +704,7 @@ int kvm_gmem_get_pfn(struct kvm *kvm, struct kvm_memory_slot *slot,
 }
 EXPORT_SYMBOL_GPL(kvm_gmem_get_pfn);
 
-#ifdef CONFIG_KVM_GENERIC_PRIVATE_MEM
+#ifdef CONFIG_HAVE_KVM_ARCH_GMEM_POPULATE
 long kvm_gmem_populate(struct kvm *kvm, gfn_t start_gfn, void __user *src, long npages,
 		       kvm_gmem_populate_cb post_populate, void *opaque)
 {
@@ -643,7 +720,7 @@ long kvm_gmem_populate(struct kvm *kvm, gfn_t start_gfn, void __user *src, long
 		return -EINVAL;
 
 	slot = gfn_to_memslot(kvm, start_gfn);
-	if (!kvm_slot_can_be_private(slot))
+	if (!kvm_slot_has_gmem(slot))
 		return -EINVAL;
 
 	file = kvm_gmem_get_file(slot);

virt/kvm/kvm_main.c

@@ -331,7 +331,7 @@ void kvm_flush_remote_tlbs_memslot(struct kvm *kvm,
 	 * All current use cases for flushing the TLBs for a specific memslot
 	 * are related to dirty logging, and many do the TLB flush out of
 	 * mmu_lock. The interaction between the various operations on memslot
-	 * must be serialized by slots_locks to ensure the TLB flush from one
+	 * must be serialized by slots_lock to ensure the TLB flush from one
 	 * operation is observed by any other operation on the same memslot.
 	 */
 	lockdep_assert_held(&kvm->slots_lock);
@@ -1588,7 +1588,7 @@ static int check_memory_region_flags(struct kvm *kvm,
 {
 	u32 valid_flags = KVM_MEM_LOG_DIRTY_PAGES;
 
-	if (kvm_arch_has_private_mem(kvm))
+	if (IS_ENABLED(CONFIG_KVM_GUEST_MEMFD))
 		valid_flags |= KVM_MEM_GUEST_MEMFD;
 
 	/* Dirty logging private memory is not currently supported. */
@@ -4915,9 +4915,11 @@ static int kvm_vm_ioctl_check_extension_generic(struct kvm *kvm, long arg)
 	case KVM_CAP_MEMORY_ATTRIBUTES:
 		return kvm_supported_mem_attributes(kvm);
 #endif
-#ifdef CONFIG_KVM_PRIVATE_MEM
+#ifdef CONFIG_KVM_GUEST_MEMFD
 	case KVM_CAP_GUEST_MEMFD:
-		return !kvm || kvm_arch_has_private_mem(kvm);
+		return 1;
+	case KVM_CAP_GUEST_MEMFD_MMAP:
+		return !kvm || kvm_arch_supports_gmem_mmap(kvm);
 #endif
 	default:
 		break;
@@ -5352,7 +5354,7 @@ static long kvm_vm_ioctl(struct file *filp,
 	case KVM_GET_STATS_FD:
 		r = kvm_vm_ioctl_get_stats_fd(kvm);
 		break;
-#ifdef CONFIG_KVM_PRIVATE_MEM
+#ifdef CONFIG_KVM_GUEST_MEMFD
 	case KVM_CREATE_GUEST_MEMFD: {
 		struct kvm_create_guest_memfd guest_memfd;
 

virt/kvm/kvm_mm.h

@@ -67,7 +67,7 @@ static inline void gfn_to_pfn_cache_invalidate_start(struct kvm *kvm,
 }
 #endif /* HAVE_KVM_PFNCACHE */
 
-#ifdef CONFIG_KVM_PRIVATE_MEM
+#ifdef CONFIG_KVM_GUEST_MEMFD
 void kvm_gmem_init(struct module *module);
 int kvm_gmem_create(struct kvm *kvm, struct kvm_create_guest_memfd *args);
 int kvm_gmem_bind(struct kvm *kvm, struct kvm_memory_slot *slot,
@@ -91,6 +91,6 @@ static inline void kvm_gmem_unbind(struct kvm_memory_slot *slot)
 {
 	WARN_ON_ONCE(1);
 }
-#endif /* CONFIG_KVM_PRIVATE_MEM */
+#endif /* CONFIG_KVM_GUEST_MEMFD */
 
 #endif /* __KVM_MM_H__ */