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 <[email protected]>

Author: bonzini

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;
@@ -1495,46 +1614,30 @@ 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);
-
-	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;
+	VM_WARN_ON_ONCE(write_fault && exec_fault);
 
 	/*
 	 * Permission faults just need to update the existing leaf entry,
 	 * and so normally don't require allocations from the memcache. The
 	 * 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)) {
-		int min_pages = kvm_mmu_cache_min_pages(vcpu->arch.hw_mmu);
-
-		if (!is_protected_kvm_enabled())
-			ret = kvm_mmu_topup_memory_cache(memcache, min_pages);
-		else
-			ret = topup_hyp_memcache(memcache, min_pages);
-
-		if (ret)
-			return ret;
-	}
+	topup_memcache = !fault_is_perm || (logging_active && write_fault);
+	ret = prepare_mmu_memcache(vcpu, topup_memcache, &memcache);
+	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;
 	}
 
-	/*
-	 * logging_active is guaranteed to never be true for VM_PFNMAP
-	 * memslots.
-	 */
-	if (logging_active) {
-		force_pte = true;
+	if (force_pte)
 		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;
 
-	/*
-	 * 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.
-	 */
-	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);
-	}
+	if (nested)
+		adjust_nested_fault_perms(nested, &prot, &writable);
 
 	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,
-			     esr_fsc_is_permission_fault(esr));
+	VM_WARN_ON_ONCE(kvm_vcpu_trap_is_permission_fault(vcpu) &&
+			!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);
-	if (is_error_noslot_pfn(pfn) || (write_fault && !writable))
+	memslot = gfn_to_memslot(vcpu->kvm, gfn);
+	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