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

Pull kvm updates from Paolo Bonzini:
 "This covers all architectures (except MIPS) so I don't expect any
  other feature pull requests this merge window.

  ARM:

   - Add MTE support in guests, complete with tag save/restore interface

   - Reduce the impact of CMOs by moving them in the page-table code

   - Allow device block mappings at stage-2

   - Reduce the footprint of the vmemmap in protected mode

   - Support the vGIC on dumb systems such as the Apple M1

   - Add selftest infrastructure to support multiple configuration and
     apply that to PMU/non-PMU setups

   - Add selftests for the debug architecture

   - The usual crop of PMU fixes

  PPC:

   - Support for the H_RPT_INVALIDATE hypercall

   - Conversion of Book3S entry/exit to C

   - Bug fixes

  S390:

   - new HW facilities for guests

   - make inline assembly more robust with KASAN and co

  x86:

   - Allow userspace to handle emulation errors (unknown instructions)

   - Lazy allocation of the rmap (host physical -> guest physical
     address)

   - Support for virtualizing TSC scaling on VMX machines

   - Optimizations to avoid shattering huge pages at the beginning of
     live migration

   - Support for initializing the PDPTRs without loading them from
     memory

   - Many TLB flushing cleanups

   - Refuse to load if two-stage paging is available but NX is not (this
     has been a requirement in practice for over a year)

   - A large series that separates the MMU mode (WP/SMAP/SMEP etc.) from
     CR0/CR4/EFER, using the MMU mode everywhere once it is computed
     from the CPU registers

   - Use PM notifier to notify the guest about host suspend or hibernate

   - Support for passing arguments to Hyper-V hypercalls using XMM
     registers

   - Support for Hyper-V TLB flush hypercalls and enlightened MSR bitmap
     on AMD processors

   - Hide Hyper-V hypercalls that are not included in the guest CPUID

   - Fixes for live migration of virtual machines that use the Hyper-V
     "enlightened VMCS" optimization of nested virtualization

   - Bugfixes (not many)

  Generic:

   - Support for retrieving statistics without debugfs

   - Cleanups for the KVM selftests API"

* tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm: (314 commits)
  KVM: x86: rename apic_access_page_done to apic_access_memslot_enabled
  kvm: x86: disable the narrow guest module parameter on unload
  selftests: kvm: Allows userspace to handle emulation errors.
  kvm: x86: Allow userspace to handle emulation errors
  KVM: x86/mmu: Let guest use GBPAGES if supported in hardware and TDP is on
  KVM: x86/mmu: Get CR4.SMEP from MMU, not vCPU, in shadow page fault
  KVM: x86/mmu: Get CR0.WP from MMU, not vCPU, in shadow page fault
  KVM: x86/mmu: Drop redundant rsvd bits reset for nested NPT
  KVM: x86/mmu: Optimize and clean up so called "last nonleaf level" logic
  KVM: x86: Enhance comments for MMU roles and nested transition trickiness
  KVM: x86/mmu: WARN on any reserved SPTE value when making a valid SPTE
  KVM: x86/mmu: Add helpers to do full reserved SPTE checks w/ generic MMU
  KVM: x86/mmu: Use MMU's role to determine PTTYPE
  KVM: x86/mmu: Collapse 32-bit PAE and 64-bit statements for helpers
  KVM: x86/mmu: Add a helper to calculate root from role_regs
  KVM: x86/mmu: Add helper to update paging metadata
  KVM: x86/mmu: Don't update nested guest's paging bitmasks if CR0.PG=0
  KVM: x86/mmu: Consolidate reset_rsvds_bits_mask() calls
  KVM: x86/mmu: Use MMU role_regs to get LA57, and drop vCPU LA57 helper
  KVM: x86/mmu: Get nested MMU's root level from the MMU's role
  ...

2 files changed, 141 insertions, 116 deletions

diff --git a/arch/s390/kvm/Makefile b/arch/s390/kvm/Makefile
index 12decca22e7c..b3aaadc60ead 100644
--- a/arch/s390/kvm/Makefile
+++ b/arch/s390/kvm/Makefile
@@ -4,7 +4,8 @@
 # Copyright IBM Corp. 2008
 
 KVM := ../../../virt/kvm
-common-objs = $(KVM)/kvm_main.o $(KVM)/eventfd.o  $(KVM)/async_pf.o $(KVM)/irqchip.o $(KVM)/vfio.o
+common-objs = $(KVM)/kvm_main.o $(KVM)/eventfd.o  $(KVM)/async_pf.o \
+	      $(KVM)/irqchip.o $(KVM)/vfio.o $(KVM)/binary_stats.o
 
 ccflags-y := -Ivirt/kvm -Iarch/s390/kvm
 
diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c
index 1296fc10f80c..f9fb1e1d960d 100644
--- a/arch/s390/kvm/kvm-s390.c
+++ b/arch/s390/kvm/kvm-s390.c
@@ -58,112 +58,132 @@
 #define VCPU_IRQS_MAX_BUF (sizeof(struct kvm_s390_irq) * \
 			   (KVM_MAX_VCPUS + LOCAL_IRQS))
 
-struct kvm_stats_debugfs_item debugfs_entries[] = {
-	VCPU_STAT("userspace_handled", exit_userspace),
-	VCPU_STAT("exit_null", exit_null),
-	VCPU_STAT("pfault_sync", pfault_sync),
-	VCPU_STAT("exit_validity", exit_validity),
-	VCPU_STAT("exit_stop_request", exit_stop_request),
-	VCPU_STAT("exit_external_request", exit_external_request),
-	VCPU_STAT("exit_io_request", exit_io_request),
-	VCPU_STAT("exit_external_interrupt", exit_external_interrupt),
-	VCPU_STAT("exit_instruction", exit_instruction),
-	VCPU_STAT("exit_pei", exit_pei),
-	VCPU_STAT("exit_program_interruption", exit_program_interruption),
-	VCPU_STAT("exit_instr_and_program_int", exit_instr_and_program),
-	VCPU_STAT("exit_operation_exception", exit_operation_exception),
-	VCPU_STAT("halt_successful_poll", halt_successful_poll),
-	VCPU_STAT("halt_attempted_poll", halt_attempted_poll),
-	VCPU_STAT("halt_poll_invalid", halt_poll_invalid),
-	VCPU_STAT("halt_no_poll_steal", halt_no_poll_steal),
-	VCPU_STAT("halt_wakeup", halt_wakeup),
-	VCPU_STAT("halt_poll_success_ns", halt_poll_success_ns),
-	VCPU_STAT("halt_poll_fail_ns", halt_poll_fail_ns),
-	VCPU_STAT("instruction_lctlg", instruction_lctlg),
-	VCPU_STAT("instruction_lctl", instruction_lctl),
-	VCPU_STAT("instruction_stctl", instruction_stctl),
-	VCPU_STAT("instruction_stctg", instruction_stctg),
-	VCPU_STAT("deliver_ckc", deliver_ckc),
-	VCPU_STAT("deliver_cputm", deliver_cputm),
-	VCPU_STAT("deliver_emergency_signal", deliver_emergency_signal),
-	VCPU_STAT("deliver_external_call", deliver_external_call),
-	VCPU_STAT("deliver_service_signal", deliver_service_signal),
-	VCPU_STAT("deliver_virtio", deliver_virtio),
-	VCPU_STAT("deliver_stop_signal", deliver_stop_signal),
-	VCPU_STAT("deliver_prefix_signal", deliver_prefix_signal),
-	VCPU_STAT("deliver_restart_signal", deliver_restart_signal),
-	VCPU_STAT("deliver_program", deliver_program),
-	VCPU_STAT("deliver_io", deliver_io),
-	VCPU_STAT("deliver_machine_check", deliver_machine_check),
-	VCPU_STAT("exit_wait_state", exit_wait_state),
-	VCPU_STAT("inject_ckc", inject_ckc),
-	VCPU_STAT("inject_cputm", inject_cputm),
-	VCPU_STAT("inject_external_call", inject_external_call),
-	VM_STAT("inject_float_mchk", inject_float_mchk),
-	VCPU_STAT("inject_emergency_signal", inject_emergency_signal),
-	VM_STAT("inject_io", inject_io),
-	VCPU_STAT("inject_mchk", inject_mchk),
-	VM_STAT("inject_pfault_done", inject_pfault_done),
-	VCPU_STAT("inject_program", inject_program),
-	VCPU_STAT("inject_restart", inject_restart),
-	VM_STAT("inject_service_signal", inject_service_signal),
-	VCPU_STAT("inject_set_prefix", inject_set_prefix),
-	VCPU_STAT("inject_stop_signal", inject_stop_signal),
-	VCPU_STAT("inject_pfault_init", inject_pfault_init),
-	VM_STAT("inject_virtio", inject_virtio),
-	VCPU_STAT("instruction_epsw", instruction_epsw),
-	VCPU_STAT("instruction_gs", instruction_gs),
-	VCPU_STAT("instruction_io_other", instruction_io_other),
-	VCPU_STAT("instruction_lpsw", instruction_lpsw),
-	VCPU_STAT("instruction_lpswe", instruction_lpswe),
-	VCPU_STAT("instruction_pfmf", instruction_pfmf),
-	VCPU_STAT("instruction_ptff", instruction_ptff),
-	VCPU_STAT("instruction_stidp", instruction_stidp),
-	VCPU_STAT("instruction_sck", instruction_sck),
-	VCPU_STAT("instruction_sckpf", instruction_sckpf),
-	VCPU_STAT("instruction_spx", instruction_spx),
-	VCPU_STAT("instruction_stpx", instruction_stpx),
-	VCPU_STAT("instruction_stap", instruction_stap),
-	VCPU_STAT("instruction_iske", instruction_iske),
-	VCPU_STAT("instruction_ri", instruction_ri),
-	VCPU_STAT("instruction_rrbe", instruction_rrbe),
-	VCPU_STAT("instruction_sske", instruction_sske),
-	VCPU_STAT("instruction_ipte_interlock", instruction_ipte_interlock),
-	VCPU_STAT("instruction_essa", instruction_essa),
-	VCPU_STAT("instruction_stsi", instruction_stsi),
-	VCPU_STAT("instruction_stfl", instruction_stfl),
-	VCPU_STAT("instruction_tb", instruction_tb),
-	VCPU_STAT("instruction_tpi", instruction_tpi),
-	VCPU_STAT("instruction_tprot", instruction_tprot),
-	VCPU_STAT("instruction_tsch", instruction_tsch),
-	VCPU_STAT("instruction_sthyi", instruction_sthyi),
-	VCPU_STAT("instruction_sie", instruction_sie),
-	VCPU_STAT("instruction_sigp_sense", instruction_sigp_sense),
-	VCPU_STAT("instruction_sigp_sense_running", instruction_sigp_sense_running),
-	VCPU_STAT("instruction_sigp_external_call", instruction_sigp_external_call),
-	VCPU_STAT("instruction_sigp_emergency", instruction_sigp_emergency),
-	VCPU_STAT("instruction_sigp_cond_emergency", instruction_sigp_cond_emergency),
-	VCPU_STAT("instruction_sigp_start", instruction_sigp_start),
-	VCPU_STAT("instruction_sigp_stop", instruction_sigp_stop),
-	VCPU_STAT("instruction_sigp_stop_store_status", instruction_sigp_stop_store_status),
-	VCPU_STAT("instruction_sigp_store_status", instruction_sigp_store_status),
-	VCPU_STAT("instruction_sigp_store_adtl_status", instruction_sigp_store_adtl_status),
-	VCPU_STAT("instruction_sigp_set_arch", instruction_sigp_arch),
-	VCPU_STAT("instruction_sigp_set_prefix", instruction_sigp_prefix),
-	VCPU_STAT("instruction_sigp_restart", instruction_sigp_restart),
-	VCPU_STAT("instruction_sigp_cpu_reset", instruction_sigp_cpu_reset),
-	VCPU_STAT("instruction_sigp_init_cpu_reset", instruction_sigp_init_cpu_reset),
-	VCPU_STAT("instruction_sigp_unknown", instruction_sigp_unknown),
-	VCPU_STAT("instruction_diag_10", diagnose_10),
-	VCPU_STAT("instruction_diag_44", diagnose_44),
-	VCPU_STAT("instruction_diag_9c", diagnose_9c),
-	VCPU_STAT("diag_9c_ignored", diagnose_9c_ignored),
-	VCPU_STAT("diag_9c_forward", diagnose_9c_forward),
-	VCPU_STAT("instruction_diag_258", diagnose_258),
-	VCPU_STAT("instruction_diag_308", diagnose_308),
-	VCPU_STAT("instruction_diag_500", diagnose_500),
-	VCPU_STAT("instruction_diag_other", diagnose_other),
-	{ NULL }
+const struct _kvm_stats_desc kvm_vm_stats_desc[] = {
+	KVM_GENERIC_VM_STATS(),
+	STATS_DESC_COUNTER(VM, inject_io),
+	STATS_DESC_COUNTER(VM, inject_float_mchk),
+	STATS_DESC_COUNTER(VM, inject_pfault_done),
+	STATS_DESC_COUNTER(VM, inject_service_signal),
+	STATS_DESC_COUNTER(VM, inject_virtio)
+};
+static_assert(ARRAY_SIZE(kvm_vm_stats_desc) ==
+		sizeof(struct kvm_vm_stat) / sizeof(u64));
+
+const struct kvm_stats_header kvm_vm_stats_header = {
+	.name_size = KVM_STATS_NAME_SIZE,
+	.num_desc = ARRAY_SIZE(kvm_vm_stats_desc),
+	.id_offset = sizeof(struct kvm_stats_header),
+	.desc_offset = sizeof(struct kvm_stats_header) + KVM_STATS_NAME_SIZE,
+	.data_offset = sizeof(struct kvm_stats_header) + KVM_STATS_NAME_SIZE +
+		       sizeof(kvm_vm_stats_desc),
+};
+
+const struct _kvm_stats_desc kvm_vcpu_stats_desc[] = {
+	KVM_GENERIC_VCPU_STATS(),
+	STATS_DESC_COUNTER(VCPU, exit_userspace),
+	STATS_DESC_COUNTER(VCPU, exit_null),
+	STATS_DESC_COUNTER(VCPU, exit_external_request),
+	STATS_DESC_COUNTER(VCPU, exit_io_request),
+	STATS_DESC_COUNTER(VCPU, exit_external_interrupt),
+	STATS_DESC_COUNTER(VCPU, exit_stop_request),
+	STATS_DESC_COUNTER(VCPU, exit_validity),
+	STATS_DESC_COUNTER(VCPU, exit_instruction),
+	STATS_DESC_COUNTER(VCPU, exit_pei),
+	STATS_DESC_COUNTER(VCPU, halt_no_poll_steal),
+	STATS_DESC_COUNTER(VCPU, instruction_lctl),
+	STATS_DESC_COUNTER(VCPU, instruction_lctlg),
+	STATS_DESC_COUNTER(VCPU, instruction_stctl),
+	STATS_DESC_COUNTER(VCPU, instruction_stctg),
+	STATS_DESC_COUNTER(VCPU, exit_program_interruption),
+	STATS_DESC_COUNTER(VCPU, exit_instr_and_program),
+	STATS_DESC_COUNTER(VCPU, exit_operation_exception),
+	STATS_DESC_COUNTER(VCPU, deliver_ckc),
+	STATS_DESC_COUNTER(VCPU, deliver_cputm),
+	STATS_DESC_COUNTER(VCPU, deliver_external_call),
+	STATS_DESC_COUNTER(VCPU, deliver_emergency_signal),
+	STATS_DESC_COUNTER(VCPU, deliver_service_signal),
+	STATS_DESC_COUNTER(VCPU, deliver_virtio),
+	STATS_DESC_COUNTER(VCPU, deliver_stop_signal),
+	STATS_DESC_COUNTER(VCPU, deliver_prefix_signal),
+	STATS_DESC_COUNTER(VCPU, deliver_restart_signal),
+	STATS_DESC_COUNTER(VCPU, deliver_program),
+	STATS_DESC_COUNTER(VCPU, deliver_io),
+	STATS_DESC_COUNTER(VCPU, deliver_machine_check),
+	STATS_DESC_COUNTER(VCPU, exit_wait_state),
+	STATS_DESC_COUNTER(VCPU, inject_ckc),
+	STATS_DESC_COUNTER(VCPU, inject_cputm),
+	STATS_DESC_COUNTER(VCPU, inject_external_call),
+	STATS_DESC_COUNTER(VCPU, inject_emergency_signal),
+	STATS_DESC_COUNTER(VCPU, inject_mchk),
+	STATS_DESC_COUNTER(VCPU, inject_pfault_init),
+	STATS_DESC_COUNTER(VCPU, inject_program),
+	STATS_DESC_COUNTER(VCPU, inject_restart),
+	STATS_DESC_COUNTER(VCPU, inject_set_prefix),
+	STATS_DESC_COUNTER(VCPU, inject_stop_signal),
+	STATS_DESC_COUNTER(VCPU, instruction_epsw),
+	STATS_DESC_COUNTER(VCPU, instruction_gs),
+	STATS_DESC_COUNTER(VCPU, instruction_io_other),
+	STATS_DESC_COUNTER(VCPU, instruction_lpsw),
+	STATS_DESC_COUNTER(VCPU, instruction_lpswe),
+	STATS_DESC_COUNTER(VCPU, instruction_pfmf),
+	STATS_DESC_COUNTER(VCPU, instruction_ptff),
+	STATS_DESC_COUNTER(VCPU, instruction_sck),
+	STATS_DESC_COUNTER(VCPU, instruction_sckpf),
+	STATS_DESC_COUNTER(VCPU, instruction_stidp),
+	STATS_DESC_COUNTER(VCPU, instruction_spx),
+	STATS_DESC_COUNTER(VCPU, instruction_stpx),
+	STATS_DESC_COUNTER(VCPU, instruction_stap),
+	STATS_DESC_COUNTER(VCPU, instruction_iske),
+	STATS_DESC_COUNTER(VCPU, instruction_ri),
+	STATS_DESC_COUNTER(VCPU, instruction_rrbe),
+	STATS_DESC_COUNTER(VCPU, instruction_sske),
+	STATS_DESC_COUNTER(VCPU, instruction_ipte_interlock),
+	STATS_DESC_COUNTER(VCPU, instruction_stsi),
+	STATS_DESC_COUNTER(VCPU, instruction_stfl),
+	STATS_DESC_COUNTER(VCPU, instruction_tb),
+	STATS_DESC_COUNTER(VCPU, instruction_tpi),
+	STATS_DESC_COUNTER(VCPU, instruction_tprot),
+	STATS_DESC_COUNTER(VCPU, instruction_tsch),
+	STATS_DESC_COUNTER(VCPU, instruction_sie),
+	STATS_DESC_COUNTER(VCPU, instruction_essa),
+	STATS_DESC_COUNTER(VCPU, instruction_sthyi),
+	STATS_DESC_COUNTER(VCPU, instruction_sigp_sense),
+	STATS_DESC_COUNTER(VCPU, instruction_sigp_sense_running),
+	STATS_DESC_COUNTER(VCPU, instruction_sigp_external_call),
+	STATS_DESC_COUNTER(VCPU, instruction_sigp_emergency),
+	STATS_DESC_COUNTER(VCPU, instruction_sigp_cond_emergency),
+	STATS_DESC_COUNTER(VCPU, instruction_sigp_start),
+	STATS_DESC_COUNTER(VCPU, instruction_sigp_stop),
+	STATS_DESC_COUNTER(VCPU, instruction_sigp_stop_store_status),
+	STATS_DESC_COUNTER(VCPU, instruction_sigp_store_status),
+	STATS_DESC_COUNTER(VCPU, instruction_sigp_store_adtl_status),
+	STATS_DESC_COUNTER(VCPU, instruction_sigp_arch),
+	STATS_DESC_COUNTER(VCPU, instruction_sigp_prefix),
+	STATS_DESC_COUNTER(VCPU, instruction_sigp_restart),
+	STATS_DESC_COUNTER(VCPU, instruction_sigp_init_cpu_reset),
+	STATS_DESC_COUNTER(VCPU, instruction_sigp_cpu_reset),
+	STATS_DESC_COUNTER(VCPU, instruction_sigp_unknown),
+	STATS_DESC_COUNTER(VCPU, diagnose_10),
+	STATS_DESC_COUNTER(VCPU, diagnose_44),
+	STATS_DESC_COUNTER(VCPU, diagnose_9c),
+	STATS_DESC_COUNTER(VCPU, diagnose_9c_ignored),
+	STATS_DESC_COUNTER(VCPU, diagnose_9c_forward),
+	STATS_DESC_COUNTER(VCPU, diagnose_258),
+	STATS_DESC_COUNTER(VCPU, diagnose_308),
+	STATS_DESC_COUNTER(VCPU, diagnose_500),
+	STATS_DESC_COUNTER(VCPU, diagnose_other),
+	STATS_DESC_COUNTER(VCPU, pfault_sync)
+};
+static_assert(ARRAY_SIZE(kvm_vcpu_stats_desc) ==
+		sizeof(struct kvm_vcpu_stat) / sizeof(u64));
+
+const struct kvm_stats_header kvm_vcpu_stats_header = {
+	.name_size = KVM_STATS_NAME_SIZE,
+	.num_desc = ARRAY_SIZE(kvm_vcpu_stats_desc),
+	.id_offset = sizeof(struct kvm_stats_header),
+	.desc_offset = sizeof(struct kvm_stats_header) + KVM_STATS_NAME_SIZE,
+	.data_offset = sizeof(struct kvm_stats_header) + KVM_STATS_NAME_SIZE +
+		       sizeof(kvm_vcpu_stats_desc),
 };
 
 /* allow nested virtualization in KVM (if enabled by user space) */
@@ -329,31 +349,31 @@ static void allow_cpu_feat(unsigned long nr)
 
 static inline int plo_test_bit(unsigned char nr)
 {
-	register unsigned long r0 asm("0") = (unsigned long) nr | 0x100;
+	unsigned long function = (unsigned long)nr | 0x100;
 	int cc;
 
 	asm volatile(
+		"	lgr	0,%[function]\n"
 		/* Parameter registers are ignored for "test bit" */
 		"	plo	0,0,0,0(0)\n"
 		"	ipm	%0\n"
 		"	srl	%0,28\n"
 		: "=d" (cc)
-		: "d" (r0)
-		: "cc");
+		: [function] "d" (function)
+		: "cc", "0");
 	return cc == 0;
 }
 
 static __always_inline void __insn32_query(unsigned int opcode, u8 *query)
 {
-	register unsigned long r0 asm("0") = 0;	/* query function */
-	register unsigned long r1 asm("1") = (unsigned long) query;
-
 	asm volatile(
-		/* Parameter regs are ignored */
+		"	lghi	0,0\n"
+		"	lgr	1,%[query]\n"
+		/* Parameter registers are ignored */
 		"	.insn	rrf,%[opc] << 16,2,4,6,0\n"
 		:
-		: "d" (r0), "a" (r1), [opc] "i" (opcode)
-		: "cc", "memory");
+		: [query] "d" ((unsigned long)query), [opc] "i" (opcode)
+		: "cc", "memory", "0", "1");
 }
 
 #define INSN_SORTL 0xb938
@@ -713,6 +733,10 @@ int kvm_vm_ioctl_enable_cap(struct kvm *kvm, struct kvm_enable_cap *cap)
 				set_kvm_facility(kvm->arch.model.fac_mask, 152);
 				set_kvm_facility(kvm->arch.model.fac_list, 152);
 			}
+			if (test_facility(192)) {
+				set_kvm_facility(kvm->arch.model.fac_mask, 192);
+				set_kvm_facility(kvm->arch.model.fac_list, 192);
+			}
 			r = 0;
 		} else
 			r = -EINVAL;