Merge tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm

Pull kvm updates from Paolo Bonzini:
 "The bulk of the changes here is a largish change to guest_memfd,
  delaying the clearing and encryption of guest-private pages until they
  are actually added to guest page tables. This started as "let's make
  it impossible to misuse the API" for SEV-SNP; but then it ballooned a
  bit.

  The new logic is generally simpler and more ready for hugepage support
  in guest_memfd.

  Summary:

   - fix latent bug in how usage of large pages is determined for
     confidential VMs

   - fix "underline too short" in docs

   - eliminate log spam from limited APIC timer periods

   - disallow pre-faulting of memory before SEV-SNP VMs are initialized

   - delay clearing and encrypting private memory until it is added to
     guest page tables

   - this change also enables another small cleanup: the checks in
     SNP_LAUNCH_UPDATE that limit it to non-populated, private pages can
     now be moved in the common kvm_gmem_populate() function

   - fix compilation error that the RISC-V merge introduced in selftests"

* tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm:
  KVM: x86/mmu: fix determination of max NPT mapping level for private pages
  KVM: riscv: selftests: Fix compile error
  KVM: guest_memfd: abstract how prepared folios are recorded
  KVM: guest_memfd: let kvm_gmem_populate() operate only on private gfns
  KVM: extend kvm_range_has_memory_attributes() to check subset of attributes
  KVM: cleanup and add shortcuts to kvm_range_has_memory_attributes()
  KVM: guest_memfd: move check for already-populated page to common code
  KVM: remove kvm_arch_gmem_prepare_needed()
  KVM: guest_memfd: make kvm_gmem_prepare_folio() operate on a single struct kvm
  KVM: guest_memfd: delay kvm_gmem_prepare_folio() until the memory is passed to the guest
  KVM: guest_memfd: return locked folio from __kvm_gmem_get_pfn
  KVM: rename CONFIG_HAVE_KVM_GMEM_* to CONFIG_HAVE_KVM_ARCH_GMEM_*
  KVM: guest_memfd: do not go through struct page
  KVM: guest_memfd: delay folio_mark_uptodate() until after successful preparation
  KVM: guest_memfd: return folio from __kvm_gmem_get_pfn()
  KVM: x86: disallow pre-fault for SNP VMs before initialization
  KVM: Documentation: Fix title underline too short warning
  KVM: x86: Eliminate log spam from limited APIC timer periods

Author: torvalds

Documentation/virt/kvm/api.rst

@@ -6368,7 +6368,7 @@ a single guest_memfd file, but the bound ranges must not overlap).
 See KVM_SET_USER_MEMORY_REGION2 for additional details.
 
 4.143 KVM_PRE_FAULT_MEMORY
-------------------------
+---------------------------
 
 :Capability: KVM_CAP_PRE_FAULT_MEMORY
 :Architectures: none
@@ -6405,6 +6405,12 @@ for the current vCPU state.  KVM maps memory as if the vCPU generated a
 stage-2 read page fault, e.g. faults in memory as needed, but doesn't break
 CoW.  However, KVM does not mark any newly created stage-2 PTE as Accessed.
 
+In the case of confidential VM types where there is an initial set up of
+private guest memory before the guest is 'finalized'/measured, this ioctl
+should only be issued after completing all the necessary setup to put the
+guest into a 'finalized' state so that the above semantics can be reliably
+ensured.
+
 In some cases, multiple vCPUs might share the page tables.  In this
 case, the ioctl can be called in parallel.
 

arch/x86/include/asm/kvm_host.h

@@ -1305,6 +1305,7 @@ struct kvm_arch {
 	u8 vm_type;
 	bool has_private_mem;
 	bool has_protected_state;
+	bool pre_fault_allowed;
 	struct hlist_head mmu_page_hash[KVM_NUM_MMU_PAGES];
 	struct list_head active_mmu_pages;
 	struct list_head zapped_obsolete_pages;

arch/x86/kvm/Kconfig

@@ -141,8 +141,8 @@ config KVM_AMD_SEV
 	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 HAVE_KVM_GMEM_PREPARE
-	select HAVE_KVM_GMEM_INVALIDATE
+	select HAVE_KVM_ARCH_GMEM_PREPARE
+	select HAVE_KVM_ARCH_GMEM_INVALIDATE
 	help
 	  Provides support for launching Encrypted VMs (SEV) and Encrypted VMs
 	  with Encrypted State (SEV-ES) on AMD processors.

arch/x86/kvm/lapic.c

@@ -1743,7 +1743,7 @@ static void limit_periodic_timer_frequency(struct kvm_lapic *apic)
 		s64 min_period = min_timer_period_us * 1000LL;
 
 		if (apic->lapic_timer.period < min_period) {
-			pr_info_ratelimited(
+			pr_info_once(
 			    "vcpu %i: requested %lld ns "
 			    "lapic timer period limited to %lld ns\n",
 			    apic->vcpu->vcpu_id,

arch/x86/kvm/mmu/mmu.c

@@ -4335,7 +4335,7 @@ static u8 kvm_max_private_mapping_level(struct kvm *kvm, kvm_pfn_t pfn,
 	if (req_max_level)
 		max_level = min(max_level, req_max_level);
 
-	return req_max_level;
+	return max_level;
 }
 
 static int kvm_faultin_pfn_private(struct kvm_vcpu *vcpu,
@@ -4743,6 +4743,9 @@ long kvm_arch_vcpu_pre_fault_memory(struct kvm_vcpu *vcpu,
 	u64 end;
 	int r;
 
+	if (!vcpu->kvm->arch.pre_fault_allowed)
+		return -EOPNOTSUPP;
+
 	/*
 	 * reload is efficient when called repeatedly, so we can do it on
 	 * every iteration.
@@ -7510,7 +7513,7 @@ static bool hugepage_has_attrs(struct kvm *kvm, struct kvm_memory_slot *slot,
 	const unsigned long end = start + KVM_PAGES_PER_HPAGE(level);
 
 	if (level == PG_LEVEL_2M)
-		return kvm_range_has_memory_attributes(kvm, start, end, attrs);
+		return kvm_range_has_memory_attributes(kvm, start, end, ~0, attrs);
 
 	for (gfn = start; gfn < end; gfn += KVM_PAGES_PER_HPAGE(level - 1)) {
 		if (hugepage_test_mixed(slot, gfn, level - 1) ||

arch/x86/kvm/svm/sev.c

@@ -2279,18 +2279,11 @@ static int sev_gmem_post_populate(struct kvm *kvm, gfn_t gfn_start, kvm_pfn_t pf
 		bool assigned;
 		int level;
 
-		if (!kvm_mem_is_private(kvm, gfn)) {
-			pr_debug("%s: Failed to ensure GFN 0x%llx has private memory attribute set\n",
-				 __func__, gfn);
-			ret = -EINVAL;
-			goto err;
-		}
-
 		ret = snp_lookup_rmpentry((u64)pfn + i, &assigned, &level);
 		if (ret || assigned) {
 			pr_debug("%s: Failed to ensure GFN 0x%llx RMP entry is initial shared state, ret: %d assigned: %d\n",
 				 __func__, gfn, ret, assigned);
-			ret = -EINVAL;
+			ret = ret ? -EINVAL : -EEXIST;
 			goto err;
 		}
 
@@ -2549,6 +2542,14 @@ static int snp_launch_finish(struct kvm *kvm, struct kvm_sev_cmd *argp)
 	data->gctx_paddr = __psp_pa(sev->snp_context);
 	ret = sev_issue_cmd(kvm, SEV_CMD_SNP_LAUNCH_FINISH, data, &argp->error);
 
+	/*
+	 * Now that there will be no more SNP_LAUNCH_UPDATE ioctls, private pages
+	 * can be given to the guest simply by marking the RMP entry as private.
+	 * This can happen on first access and also with KVM_PRE_FAULT_MEMORY.
+	 */
+	if (!ret)
+		kvm->arch.pre_fault_allowed = true;
+
 	kfree(id_auth);
 
 e_free_id_block:

arch/x86/kvm/svm/svm.c

@@ -4949,6 +4949,7 @@ static int svm_vm_init(struct kvm *kvm)
 		to_kvm_sev_info(kvm)->need_init = true;
 
 		kvm->arch.has_private_mem = (type == KVM_X86_SNP_VM);
+		kvm->arch.pre_fault_allowed = !kvm->arch.has_private_mem;
 	}
 
 	if (!pause_filter_count || !pause_filter_thresh)

arch/x86/kvm/x86.c

@@ -12646,6 +12646,9 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type)
 	kvm->arch.vm_type = type;
 	kvm->arch.has_private_mem =
 		(type == KVM_X86_SW_PROTECTED_VM);
+	/* Decided by the vendor code for other VM types.  */
+	kvm->arch.pre_fault_allowed =
+		type == KVM_X86_DEFAULT_VM || type == KVM_X86_SW_PROTECTED_VM;
 
 	ret = kvm_page_track_init(kvm);
 	if (ret)
@@ -13641,19 +13644,14 @@ bool kvm_arch_no_poll(struct kvm_vcpu *vcpu)
 }
 EXPORT_SYMBOL_GPL(kvm_arch_no_poll);
 
-#ifdef CONFIG_HAVE_KVM_GMEM_PREPARE
-bool kvm_arch_gmem_prepare_needed(struct kvm *kvm)
-{
-	return kvm->arch.vm_type == KVM_X86_SNP_VM;
-}
-
+#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)
 {
 	return kvm_x86_call(gmem_prepare)(kvm, pfn, gfn, max_order);
 }
 #endif
 
-#ifdef CONFIG_HAVE_KVM_GMEM_INVALIDATE
+#ifdef CONFIG_HAVE_KVM_ARCH_GMEM_INVALIDATE
 void kvm_arch_gmem_invalidate(kvm_pfn_t start, kvm_pfn_t end)
 {
 	kvm_x86_call(gmem_invalidate)(start, end);

include/linux/kvm_host.h

@@ -2414,7 +2414,7 @@ static inline unsigned long kvm_get_memory_attributes(struct kvm *kvm, gfn_t gfn
 }
 
 bool kvm_range_has_memory_attributes(struct kvm *kvm, gfn_t start, gfn_t end,
-				     unsigned long attrs);
+				     unsigned long mask, unsigned long attrs);
 bool kvm_arch_pre_set_memory_attributes(struct kvm *kvm,
 					struct kvm_gfn_range *range);
 bool kvm_arch_post_set_memory_attributes(struct kvm *kvm,
@@ -2445,11 +2445,11 @@ static inline int kvm_gmem_get_pfn(struct kvm *kvm,
 }
 #endif /* CONFIG_KVM_PRIVATE_MEM */
 
-#ifdef CONFIG_HAVE_KVM_GMEM_PREPARE
+#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);
-bool kvm_arch_gmem_prepare_needed(struct kvm *kvm);
 #endif
 
+#ifdef CONFIG_KVM_GENERIC_PRIVATE_MEM
 /**
  * kvm_gmem_populate() - Populate/prepare a GPA range with guest data
  *
@@ -2476,8 +2476,9 @@ typedef int (*kvm_gmem_populate_cb)(struct kvm *kvm, gfn_t gfn, kvm_pfn_t pfn,
 
 long kvm_gmem_populate(struct kvm *kvm, gfn_t gfn, void __user *src, long npages,
 		       kvm_gmem_populate_cb post_populate, void *opaque);
+#endif
 
-#ifdef CONFIG_HAVE_KVM_GMEM_INVALIDATE
+#ifdef CONFIG_HAVE_KVM_ARCH_GMEM_INVALIDATE
 void kvm_arch_gmem_invalidate(kvm_pfn_t start, kvm_pfn_t end);
 #endif
 

tools/testing/selftests/kvm/riscv/get-reg-list.c

@@ -961,10 +961,10 @@ KVM_ISA_EXT_SIMPLE_CONFIG(zbkb, ZBKB);
 KVM_ISA_EXT_SIMPLE_CONFIG(zbkc, ZBKC);
 KVM_ISA_EXT_SIMPLE_CONFIG(zbkx, ZBKX);
 KVM_ISA_EXT_SIMPLE_CONFIG(zbs, ZBS);
-KVM_ISA_EXT_SIMPLE_CONFIG(zca, ZCA),
-KVM_ISA_EXT_SIMPLE_CONFIG(zcb, ZCB),
-KVM_ISA_EXT_SIMPLE_CONFIG(zcd, ZCD),
-KVM_ISA_EXT_SIMPLE_CONFIG(zcf, ZCF),
+KVM_ISA_EXT_SIMPLE_CONFIG(zca, ZCA);
+KVM_ISA_EXT_SIMPLE_CONFIG(zcb, ZCB);
+KVM_ISA_EXT_SIMPLE_CONFIG(zcd, ZCD);
+KVM_ISA_EXT_SIMPLE_CONFIG(zcf, ZCF);
 KVM_ISA_EXT_SIMPLE_CONFIG(zcmop, ZCMOP);
 KVM_ISA_EXT_SIMPLE_CONFIG(zfa, ZFA);
 KVM_ISA_EXT_SIMPLE_CONFIG(zfh, ZFH);