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

Pull KVM fixes from Paolo Bonzini:
"Many patches, pretty much all of them small, that accumulated while I
was on vacation.

ARM:

- Remove the last leftovers of the ill-fated FPSIMD host state
mapping at EL2 stage-1

- Fix unexpected advertisement to the guest of unimplemented S2 base
granule sizes

- Gracefully fail initialising pKVM if the interrupt controller isn't
GICv3

- Also gracefully fail initialising pKVM if the carveout allocation
fails

- Fix the computing of the minimum MMIO range required for the host
on stage-2 fault

- Fix the generation of the GICv3 Maintenance Interrupt in nested
mode

x86:

- Reject SEV{-ES} intra-host migration if one or more vCPUs are
actively being created, so as not to create a non-SEV{-ES} vCPU in
an SEV{-ES} VM

- Use a pre-allocated, per-vCPU buffer for handling de-sparsification
of vCPU masks in Hyper-V hypercalls; fixes a "stack frame too
large" issue

- Allow out-of-range/invalid Xen event channel ports when configuring
IRQ routing, to avoid dictating a specific ioctl() ordering to
userspace

- Conditionally reschedule when setting memory attributes to avoid
soft lockups when userspace converts huge swaths of memory to/from
private

- Add back MWAIT as a required feature for the MONITOR/MWAIT selftest

- Add a missing field in struct sev_data_snp_launch_start that
resulted in the guest-visible workarounds field being filled at the
wrong offset

- Skip non-canonical address when processing Hyper-V PV TLB flushes
to avoid VM-Fail on INVVPID

- Advertise supported TDX TDVMCALLs to userspace

- Pass SetupEventNotifyInterrupt arguments to userspace

- Fix TSC frequency underflow"

* tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm:
KVM: x86: avoid underflow when scaling TSC frequency
KVM: arm64: Remove kvm_arch_vcpu_run_map_fp()
KVM: arm64: Fix handling of FEAT_GTG for unimplemented granule sizes
KVM: arm64: Don't free hyp pages with pKVM on GICv2
KVM: arm64: Fix error path in init_hyp_mode()
KVM: arm64: Adjust range correctly during host stage-2 faults
KVM: arm64: nv: Fix MI line level calculation in vgic_v3_nested_update_mi()
KVM: x86/hyper-v: Skip non-canonical addresses during PV TLB flush
KVM: SVM: Add missing member in SNP_LAUNCH_START command structure
Documentation: KVM: Fix unexpected unindent warnings
KVM: selftests: Add back the missing check of MONITOR/MWAIT availability
KVM: Allow CPU to reschedule while setting per-page memory attributes
KVM: x86/xen: Allow 'out of range' event channel ports in IRQ routing table.
KVM: x86/hyper-v: Use preallocated per-vCPU buffer for de-sparsified vCPU masks
KVM: SVM: Initialize vmsa_pa in VMCB to INVALID_PAGE if VMSA page is NULL
KVM: SVM: Reject SEV{-ES} intra host migration if vCPU creation is in-flight
KVM: TDX: Report supported optional TDVMCALLs in TDX capabilities
KVM: TDX: Exit to userspace for SetupEventNotifyInterrupt

Documentation/virt/kvm/api.rst

···
 					u64 leaf;
 					u64 r11, r12, r13, r14;
 				} get_tdvmcall_info;
+				struct {
+					u64 ret;
+					u64 vector;
+				} setup_event_notify;
 			};
 		} tdx;
 
···
 inputs and outputs of the TDVMCALL.  Currently the following values of
 ``nr`` are defined:
 
-* ``TDVMCALL_GET_QUOTE``: the guest has requested to generate a TD-Quote
-signed by a service hosting TD-Quoting Enclave operating on the host.
-Parameters and return value are in the ``get_quote`` field of the union.
-The ``gpa`` field and ``size`` specify the guest physical address
-(without the shared bit set) and the size of a shared-memory buffer, in
-which the TDX guest passes a TD Report.  The ``ret`` field represents
-the return value of the GetQuote request.  When the request has been
-queued successfully, the TDX guest can poll the status field in the
-shared-memory area to check whether the Quote generation is completed or
-not. When completed, the generated Quote is returned via the same buffer.
+ * ``TDVMCALL_GET_QUOTE``: the guest has requested to generate a TD-Quote
+   signed by a service hosting TD-Quoting Enclave operating on the host.
+   Parameters and return value are in the ``get_quote`` field of the union.
+   The ``gpa`` field and ``size`` specify the guest physical address
+   (without the shared bit set) and the size of a shared-memory buffer, in
+   which the TDX guest passes a TD Report.  The ``ret`` field represents
+   the return value of the GetQuote request.  When the request has been
+   queued successfully, the TDX guest can poll the status field in the
+   shared-memory area to check whether the Quote generation is completed or
+   not. When completed, the generated Quote is returned via the same buffer.
 
-* ``TDVMCALL_GET_TD_VM_CALL_INFO``: the guest has requested the support
-status of TDVMCALLs.  The output values for the given leaf should be
-placed in fields from ``r11`` to ``r14`` of the ``get_tdvmcall_info``
-field of the union.
+ * ``TDVMCALL_GET_TD_VM_CALL_INFO``: the guest has requested the support
+   status of TDVMCALLs.  The output values for the given leaf should be
+   placed in fields from ``r11`` to ``r14`` of the ``get_tdvmcall_info``
+   field of the union.
+
+* ``TDVMCALL_SETUP_EVENT_NOTIFY_INTERRUPT``: the guest has requested to
+set up a notification interrupt for vector ``vector``.
 
 KVM may add support for more values in the future that may cause a userspace
 exit, even without calls to ``KVM_ENABLE_CAP`` or similar.  In this case,

Documentation/virt/kvm/x86/intel-tdx.rst

···
   struct kvm_tdx_capabilities {
         __u64 supported_attrs;
         __u64 supported_xfam;
-        __u64 reserved[254];
+
+        /* TDG.VP.VMCALL hypercalls executed in kernel and forwarded to
+         * userspace, respectively
+         */
+        __u64 kernel_tdvmcallinfo_1_r11;
+        __u64 user_tdvmcallinfo_1_r11;
+
+        /* TDG.VP.VMCALL instruction executions subfunctions executed in kernel
+         * and forwarded to userspace, respectively
+         */
+        __u64 kernel_tdvmcallinfo_1_r12;
+        __u64 user_tdvmcallinfo_1_r12;
+
+        __u64 reserved[250];
 
         /* Configurable CPUID bits for userspace */
         struct kvm_cpuid2 cpuid;

arch/arm64/include/asm/kvm_host.h

···
 					struct reg_mask_range *range);
 
 /* Guest/host FPSIMD coordination helpers */
-int kvm_arch_vcpu_run_map_fp(struct kvm_vcpu *vcpu);
 void kvm_arch_vcpu_load_fp(struct kvm_vcpu *vcpu);
 void kvm_arch_vcpu_ctxflush_fp(struct kvm_vcpu *vcpu);
 void kvm_arch_vcpu_ctxsync_fp(struct kvm_vcpu *vcpu);

arch/arm64/kvm/arm.c

···
 	if (!kvm_arm_vcpu_is_finalized(vcpu))
 		return -EPERM;
 
-	ret = kvm_arch_vcpu_run_map_fp(vcpu);
-	if (ret)
-		return ret;
-
 	if (likely(vcpu_has_run_once(vcpu)))
 		return 0;
 
···
 
 static void cpu_hyp_uninit(void *discard)
 {
-	if (__this_cpu_read(kvm_hyp_initialized)) {
+	if (!is_protected_kvm_enabled() && __this_cpu_read(kvm_hyp_initialized)) {
 		cpu_hyp_reset();
 		__this_cpu_write(kvm_hyp_initialized, 0);
 	}
···
 
 	free_hyp_pgds();
 	for_each_possible_cpu(cpu) {
+		if (per_cpu(kvm_hyp_initialized, cpu))
+			continue;
+
 		free_pages(per_cpu(kvm_arm_hyp_stack_base, cpu), NVHE_STACK_SHIFT - PAGE_SHIFT);
-		free_pages(kvm_nvhe_sym(kvm_arm_hyp_percpu_base)[cpu], nvhe_percpu_order());
+
+		if (!kvm_nvhe_sym(kvm_arm_hyp_percpu_base)[cpu])
+			continue;
 
 		if (free_sve) {
 			struct cpu_sve_state *sve_state;
···
 			sve_state = per_cpu_ptr_nvhe_sym(kvm_host_data, cpu)->sve_state;
 			free_pages((unsigned long) sve_state, pkvm_host_sve_state_order());
 		}
+
+		free_pages(kvm_nvhe_sym(kvm_arm_hyp_percpu_base)[cpu], nvhe_percpu_order());
+
 	}
 }
 

arch/arm64/kvm/fpsimd.c

···
 #include <asm/sysreg.h>
 
 /*
- * Called on entry to KVM_RUN unless this vcpu previously ran at least
- * once and the most recent prior KVM_RUN for this vcpu was called from
- * the same task as current (highly likely).
- *
- * This is guaranteed to execute before kvm_arch_vcpu_load_fp(vcpu),
- * such that on entering hyp the relevant parts of current are already
- * mapped.
- */
-int kvm_arch_vcpu_run_map_fp(struct kvm_vcpu *vcpu)
-{
-	struct user_fpsimd_state *fpsimd = &current->thread.uw.fpsimd_state;
-	int ret;
-
-	/* pKVM has its own tracking of the host fpsimd state. */
-	if (is_protected_kvm_enabled())
-		return 0;
-
-	/* Make sure the host task fpsimd state is visible to hyp: */
-	ret = kvm_share_hyp(fpsimd, fpsimd + 1);
-	if (ret)
-		return ret;
-
-	return 0;
-}
-
-/*
  * Prepare vcpu for saving the host's FPSIMD state and loading the guest's.
  * The actual loading is done by the FPSIMD access trap taken to hyp.
  *

arch/arm64/kvm/hyp/nvhe/mem_protect.c

···
 {
 	struct kvm_mem_range cur;
 	kvm_pte_t pte;
+	u64 granule;
 	s8 level;
 	int ret;
 
···
 		return -EPERM;
 	}
 
-	do {
-		u64 granule = kvm_granule_size(level);
+	for (; level <= KVM_PGTABLE_LAST_LEVEL; level++) {
+		if (!kvm_level_supports_block_mapping(level))
+			continue;
+		granule = kvm_granule_size(level);
 		cur.start = ALIGN_DOWN(addr, granule);
 		cur.end = cur.start + granule;
-		level++;
-	} while ((level <= KVM_PGTABLE_LAST_LEVEL) &&
-			!(kvm_level_supports_block_mapping(level) &&
-			  range_included(&cur, range)));
+		if (!range_included(&cur, range))
+			continue;
+		*range = cur;
+		return 0;
+	}
 
-	*range = cur;
+	WARN_ON(1);
 
-	return 0;
+	return -EINVAL;
 }
 
 int host_stage2_idmap_locked(phys_addr_t addr, u64 size,

arch/arm64/kvm/nested.c

···
 	}
 }
 
+#define has_tgran_2(__r, __sz)						\
+	({								\
+		u64 _s1, _s2, _mmfr0 = __r;				\
+									\
+		_s2 = SYS_FIELD_GET(ID_AA64MMFR0_EL1,			\
+				    TGRAN##__sz##_2, _mmfr0);		\
+									\
+		_s1 = SYS_FIELD_GET(ID_AA64MMFR0_EL1,			\
+				    TGRAN##__sz, _mmfr0);		\
+									\
+		((_s2 != ID_AA64MMFR0_EL1_TGRAN##__sz##_2_NI &&		\
+		  _s2 != ID_AA64MMFR0_EL1_TGRAN##__sz##_2_TGRAN##__sz) || \
+		 (_s2 == ID_AA64MMFR0_EL1_TGRAN##__sz##_2_TGRAN##__sz && \
+		  _s1 != ID_AA64MMFR0_EL1_TGRAN##__sz##_NI));		\
+	})
 /*
  * Our emulated CPU doesn't support all the possible features. For the
  * sake of simplicity (and probably mental sanity), wipe out a number
···
  */
 u64 limit_nv_id_reg(struct kvm *kvm, u32 reg, u64 val)
 {
+	u64 orig_val = val;
+
 	switch (reg) {
 	case SYS_ID_AA64ISAR0_EL1:
 		/* Support everything but TME */
···
 		 */
 		switch (PAGE_SIZE) {
 		case SZ_4K:
-			val |= SYS_FIELD_PREP_ENUM(ID_AA64MMFR0_EL1, TGRAN4_2, IMP);
+			if (has_tgran_2(orig_val, 4))
+				val |= SYS_FIELD_PREP_ENUM(ID_AA64MMFR0_EL1, TGRAN4_2, IMP);
 			fallthrough;
 		case SZ_16K:
-			val |= SYS_FIELD_PREP_ENUM(ID_AA64MMFR0_EL1, TGRAN16_2, IMP);
+			if (has_tgran_2(orig_val, 16))
+				val |= SYS_FIELD_PREP_ENUM(ID_AA64MMFR0_EL1, TGRAN16_2, IMP);
 			fallthrough;
 		case SZ_64K:
-			val |= SYS_FIELD_PREP_ENUM(ID_AA64MMFR0_EL1, TGRAN64_2, IMP);
+			if (has_tgran_2(orig_val, 64))
+				val |= SYS_FIELD_PREP_ENUM(ID_AA64MMFR0_EL1, TGRAN64_2, IMP);
 			break;
 		}
 

arch/arm64/kvm/vgic/vgic-v3-nested.c

···
 {
 	bool level;
 
-	level  = __vcpu_sys_reg(vcpu, ICH_HCR_EL2) & ICH_HCR_EL2_En;
-	if (level)
-		level &= vgic_v3_get_misr(vcpu);
+	level = (__vcpu_sys_reg(vcpu, ICH_HCR_EL2) & ICH_HCR_EL2_En) && vgic_v3_get_misr(vcpu);
 	kvm_vgic_inject_irq(vcpu->kvm, vcpu,
 			    vcpu->kvm->arch.vgic.mi_intid, level, vcpu);
 }

arch/x86/include/asm/kvm_host.h

···
 
 	struct kvm_vcpu_hv_tlb_flush_fifo tlb_flush_fifo[HV_NR_TLB_FLUSH_FIFOS];
 
-	/* Preallocated buffer for handling hypercalls passing sparse vCPU set */
+	/*
+	 * Preallocated buffers for handling hypercalls that pass sparse vCPU
+	 * sets (for high vCPU counts, they're too large to comfortably fit on
+	 * the stack).
+	 */
 	u64 sparse_banks[HV_MAX_SPARSE_VCPU_BANKS];
+	DECLARE_BITMAP(vcpu_mask, KVM_MAX_VCPUS);
 
 	struct hv_vp_assist_page vp_assist_page;
 

arch/x86/include/asm/shared/tdx.h

···
 #define TDVMCALL_MAP_GPA		0x10001
 #define TDVMCALL_GET_QUOTE		0x10002
 #define TDVMCALL_REPORT_FATAL_ERROR	0x10003
+#define TDVMCALL_SETUP_EVENT_NOTIFY_INTERRUPT 0x10004ULL
 
 /*
  * TDG.VP.VMCALL Status Codes (returned in R10)

arch/x86/include/uapi/asm/kvm.h

···
 struct kvm_tdx_capabilities {
 	__u64 supported_attrs;
 	__u64 supported_xfam;
-	__u64 reserved[254];
+
+	__u64 kernel_tdvmcallinfo_1_r11;
+	__u64 user_tdvmcallinfo_1_r11;
+	__u64 kernel_tdvmcallinfo_1_r12;
+	__u64 user_tdvmcallinfo_1_r12;
+
+	__u64 reserved[250];
 
 	/* Configurable CPUID bits for userspace */
 	struct kvm_cpuid2 cpuid;

arch/x86/kvm/hyperv.c

···
 		if (entries[i] == KVM_HV_TLB_FLUSHALL_ENTRY)
 			goto out_flush_all;
 
+		if (is_noncanonical_invlpg_address(entries[i], vcpu))
+			continue;
+
 		/*
 		 * Lower 12 bits of 'address' encode the number of additional
 		 * pages to flush.
···
 static u64 kvm_hv_flush_tlb(struct kvm_vcpu *vcpu, struct kvm_hv_hcall *hc)
 {
 	struct kvm_vcpu_hv *hv_vcpu = to_hv_vcpu(vcpu);
+	unsigned long *vcpu_mask = hv_vcpu->vcpu_mask;
 	u64 *sparse_banks = hv_vcpu->sparse_banks;
 	struct kvm *kvm = vcpu->kvm;
 	struct hv_tlb_flush_ex flush_ex;
 	struct hv_tlb_flush flush;
-	DECLARE_BITMAP(vcpu_mask, KVM_MAX_VCPUS);
 	struct kvm_vcpu_hv_tlb_flush_fifo *tlb_flush_fifo;
 	/*
 	 * Normally, there can be no more than 'KVM_HV_TLB_FLUSH_FIFO_SIZE'

arch/x86/kvm/svm/sev.c

···
 	struct kvm_vcpu *src_vcpu;
 	unsigned long i;
 
+	if (src->created_vcpus != atomic_read(&src->online_vcpus) ||
+	    dst->created_vcpus != atomic_read(&dst->online_vcpus))
+		return -EBUSY;
+
 	if (!sev_es_guest(src))
 		return 0;
 
···
 	 * the VMSA will be NULL if this vCPU is the destination for intrahost
 	 * migration, and will be copied later.
 	 */
-	if (svm->sev_es.vmsa && !svm->sev_es.snp_has_guest_vmsa)
-		svm->vmcb->control.vmsa_pa = __pa(svm->sev_es.vmsa);
+	if (!svm->sev_es.snp_has_guest_vmsa) {
+		if (svm->sev_es.vmsa)
+			svm->vmcb->control.vmsa_pa = __pa(svm->sev_es.vmsa);
+		else
+			svm->vmcb->control.vmsa_pa = INVALID_PAGE;
+	}
 
 	if (cpu_feature_enabled(X86_FEATURE_ALLOWED_SEV_FEATURES))
 		svm->vmcb->control.allowed_sev_features = sev->vmsa_features |

arch/x86/kvm/vmx/tdx.c

···
 	tdx_clear_unsupported_cpuid(entry);
 }
 
+#define TDVMCALLINFO_GET_QUOTE				BIT(0)
+#define TDVMCALLINFO_SETUP_EVENT_NOTIFY_INTERRUPT	BIT(1)
+
 static int init_kvm_tdx_caps(const struct tdx_sys_info_td_conf *td_conf,
 			     struct kvm_tdx_capabilities *caps)
 {
···
 		return -EIO;
 
 	caps->cpuid.nent = td_conf->num_cpuid_config;
+
+	caps->user_tdvmcallinfo_1_r11 =
+		TDVMCALLINFO_GET_QUOTE |
+		TDVMCALLINFO_SETUP_EVENT_NOTIFY_INTERRUPT;
 
 	for (i = 0; i < td_conf->num_cpuid_config; i++)
 		td_init_cpuid_entry2(&caps->cpuid.entries[i], i);
···
 	return 0;
 }
 
+static int tdx_setup_event_notify_interrupt(struct kvm_vcpu *vcpu)
+{
+	struct vcpu_tdx *tdx = to_tdx(vcpu);
+	u64 vector = tdx->vp_enter_args.r12;
+
+	if (vector < 32 || vector > 255) {
+		tdvmcall_set_return_code(vcpu, TDVMCALL_STATUS_INVALID_OPERAND);
+		return 1;
+	}
+
+	vcpu->run->exit_reason = KVM_EXIT_TDX;
+	vcpu->run->tdx.flags = 0;
+	vcpu->run->tdx.nr = TDVMCALL_SETUP_EVENT_NOTIFY_INTERRUPT;
+	vcpu->run->tdx.setup_event_notify.ret = TDVMCALL_STATUS_SUBFUNC_UNSUPPORTED;
+	vcpu->run->tdx.setup_event_notify.vector = vector;
+
+	vcpu->arch.complete_userspace_io = tdx_complete_simple;
+
+	return 0;
+}
+
 static int handle_tdvmcall(struct kvm_vcpu *vcpu)
 {
 	switch (tdvmcall_leaf(vcpu)) {
···
 		return tdx_get_td_vm_call_info(vcpu);
 	case TDVMCALL_GET_QUOTE:
 		return tdx_get_quote(vcpu);
+	case TDVMCALL_SETUP_EVENT_NOTIFY_INTERRUPT:
+		return tdx_setup_event_notify_interrupt(vcpu);
 	default:
 		break;
 	}

arch/x86/kvm/x86.c

···
 
 	/* With all the info we got, fill in the values */
 
-	if (kvm_caps.has_tsc_control)
+	if (kvm_caps.has_tsc_control) {
 		tgt_tsc_khz = kvm_scale_tsc(tgt_tsc_khz,
 					    v->arch.l1_tsc_scaling_ratio);
+		tgt_tsc_khz = tgt_tsc_khz ? : 1;
+	}
 
 	if (unlikely(vcpu->hw_tsc_khz != tgt_tsc_khz)) {
 		kvm_get_time_scale(NSEC_PER_SEC, tgt_tsc_khz * 1000LL,

arch/x86/kvm/xen.c

···
 {
 	struct kvm_vcpu *vcpu;
 
-	if (ue->u.xen_evtchn.port >= max_evtchn_port(kvm))
-		return -EINVAL;
+	/*
+	 * Don't check for the port being within range of max_evtchn_port().
+	 * Userspace can configure what ever targets it likes; events just won't
+	 * be delivered if/while the target is invalid, just like userspace can
+	 * configure MSIs which target non-existent APICs.
+	 *
+	 * This allow on Live Migration and Live Update, the IRQ routing table
+	 * can be restored *independently* of other things like creating vCPUs,
+	 * without imposing an ordering dependency on userspace.  In this
+	 * particular case, the problematic ordering would be with setting the
+	 * Xen 'long mode' flag, which changes max_evtchn_port() to allow 4096
+	 * instead of 1024 event channels.
+	 */
 
 	/* We only support 2 level event channels for now */
 	if (ue->u.xen_evtchn.priority != KVM_IRQ_ROUTING_XEN_EVTCHN_PRIO_2LEVEL)

include/linux/psp-sev.h

···
  * @imi_en: launch flow is launching an IMI (Incoming Migration Image) for the
  *          purpose of guest-assisted migration.
  * @rsvd: reserved
+ * @desired_tsc_khz: hypervisor desired mean TSC freq in kHz of the guest
  * @gosvw: guest OS-visible workarounds, as defined by hypervisor
  */
 struct sev_data_snp_launch_start {
···
 	u32 ma_en:1;				/* In */
 	u32 imi_en:1;				/* In */
 	u32 rsvd:30;
+	u32 desired_tsc_khz;			/* In */
 	u8 gosvw[16];				/* In */
 } __packed;
 

include/uapi/linux/kvm.h

···
 					__u64 leaf;
 					__u64 r11, r12, r13, r14;
 				} get_tdvmcall_info;
+				struct {
+					__u64 ret;
+					__u64 vector;
+				} setup_event_notify;
 			};
 		} tdx;
 		/* Fix the size of the union. */

tools/testing/selftests/kvm/x86/monitor_mwait_test.c

···
 	int testcase;
 	char test[80];
 
+	TEST_REQUIRE(this_cpu_has(X86_FEATURE_MWAIT));
 	TEST_REQUIRE(kvm_has_cap(KVM_CAP_DISABLE_QUIRKS2));
 
 	ksft_print_header();

virt/kvm/kvm_main.c

···
 		r = xa_reserve(&kvm->mem_attr_array, i, GFP_KERNEL_ACCOUNT);
 		if (r)
 			goto out_unlock;
+
+		cond_resched();
 	}
 
 	kvm_handle_gfn_range(kvm, &pre_set_range);
···
 		r = xa_err(xa_store(&kvm->mem_attr_array, i, entry,
 				    GFP_KERNEL_ACCOUNT));
 		KVM_BUG_ON(r, kvm);
+		cond_resched();
 	}
 
 	kvm_handle_gfn_range(kvm, &post_set_range);