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

Pull kvm updates from Paolo Bonzini:
 "Quite a large pull request due to a selftest API overhaul and some
  patches that had come in too late for 5.19.

  ARM:

   - Unwinder implementations for both nVHE modes (classic and
     protected), complete with an overflow stack

   - Rework of the sysreg access from userspace, with a complete rewrite
     of the vgic-v3 view to allign with the rest of the infrastructure

   - Disagregation of the vcpu flags in separate sets to better track
     their use model.

   - A fix for the GICv2-on-v3 selftest

   - A small set of cosmetic fixes

  RISC-V:

   - Track ISA extensions used by Guest using bitmap

   - Added system instruction emulation framework

   - Added CSR emulation framework

   - Added gfp_custom flag in struct kvm_mmu_memory_cache

   - Added G-stage ioremap() and iounmap() functions

   - Added support for Svpbmt inside Guest

  s390:

   - add an interface to provide a hypervisor dump for secure guests

   - improve selftests to use TAP interface

   - enable interpretive execution of zPCI instructions (for PCI
     passthrough)

   - First part of deferred teardown

   - CPU Topology

   - PV attestation

   - Minor fixes

  x86:

   - Permit guests to ignore single-bit ECC errors

   - Intel IPI virtualization

   - Allow getting/setting pending triple fault with
     KVM_GET/SET_VCPU_EVENTS

   - PEBS virtualization

   - Simplify PMU emulation by just using PERF_TYPE_RAW events

   - More accurate event reinjection on SVM (avoid retrying
     instructions)

   - Allow getting/setting the state of the speaker port data bit

   - Refuse starting the kvm-intel module if VM-Entry/VM-Exit controls
     are inconsistent

   - "Notify" VM exit (detect microarchitectural hangs) for Intel

   - Use try_cmpxchg64 instead of cmpxchg64

   - Ignore benign host accesses to PMU MSRs when PMU is disabled

   - Allow disabling KVM's "MONITOR/MWAIT are NOPs!" behavior

   - Allow NX huge page mitigation to be disabled on a per-vm basis

   - Port eager page splitting to shadow MMU as well

   - Enable CMCI capability by default and handle injected UCNA errors

   - Expose pid of vcpu threads in debugfs

   - x2AVIC support for AMD

   - cleanup PIO emulation

   - Fixes for LLDT/LTR emulation

   - Don't require refcounted "struct page" to create huge SPTEs

   - Miscellaneous cleanups:
      - MCE MSR emulation
      - Use separate namespaces for guest PTEs and shadow PTEs bitmasks
      - PIO emulation
      - Reorganize rmap API, mostly around rmap destruction
      - Do not workaround very old KVM bugs for L0 that runs with nesting enabled
      - new selftests API for CPUID

  Generic:

   - Fix races in gfn->pfn cache refresh; do not pin pages tracked by
     the cache

   - new selftests API using struct kvm_vcpu instead of a (vm, id)
     tuple"

* tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm: (606 commits)
  selftests: kvm: set rax before vmcall
  selftests: KVM: Add exponent check for boolean stats
  selftests: KVM: Provide descriptive assertions in kvm_binary_stats_test
  selftests: KVM: Check stat name before other fields
  KVM: x86/mmu: remove unused variable
  RISC-V: KVM: Add support for Svpbmt inside Guest/VM
  RISC-V: KVM: Use PAGE_KERNEL_IO in kvm_riscv_gstage_ioremap()
  RISC-V: KVM: Add G-stage ioremap() and iounmap() functions
  KVM: Add gfp_custom flag in struct kvm_mmu_memory_cache
  RISC-V: KVM: Add extensible CSR emulation framework
  RISC-V: KVM: Add extensible system instruction emulation framework
  RISC-V: KVM: Factor-out instruction emulation into separate sources
  RISC-V: KVM: move preempt_disable() call in kvm_arch_vcpu_ioctl_run
  RISC-V: KVM: Make kvm_riscv_guest_timer_init a void function
  RISC-V: KVM: Fix variable spelling mistake
  RISC-V: KVM: Improve ISA extension by using a bitmap
  KVM, x86/mmu: Fix the comment around kvm_tdp_mmu_zap_leafs()
  KVM: SVM: Dump Virtual Machine Save Area (VMSA) to klog
  KVM: x86/mmu: Treat NX as a valid SPTE bit for NPT
  KVM: x86: Do not block APIC write for non ICR registers
  ...

1 files changed, 35 insertions, 40 deletions

diff --git a/tools/testing/selftests/kvm/x86_64/xen_shinfo_test.c b/tools/testing/selftests/kvm/x86_64/xen_shinfo_test.c
index 7a51bb648fbb..8a5cb800f50e 100644
--- a/tools/testing/selftests/kvm/x86_64/xen_shinfo_test.c
+++ b/tools/testing/selftests/kvm/x86_64/xen_shinfo_test.c
@@ -18,8 +18,6 @@
 
 #include <sys/eventfd.h>
 
-#define VCPU_ID		5
-
 #define SHINFO_REGION_GVA	0xc0000000ULL
 #define SHINFO_REGION_GPA	0xc0000000ULL
 #define SHINFO_REGION_SLOT	10
@@ -42,8 +40,6 @@
 #define EVTCHN_TEST2 66
 #define EVTCHN_TIMER 13
 
-static struct kvm_vm *vm;
-
 #define XEN_HYPERCALL_MSR	0x40000000
 
 #define MIN_STEAL_TIME		50000
@@ -344,29 +340,29 @@ static int cmp_timespec(struct timespec *a, struct timespec *b)
 	else
 		return 0;
 }
-struct vcpu_info *vinfo;
+
+static struct vcpu_info *vinfo;
+static struct kvm_vcpu *vcpu;
 
 static void handle_alrm(int sig)
 {
 	if (vinfo)
 		printf("evtchn_upcall_pending 0x%x\n", vinfo->evtchn_upcall_pending);
-	vcpu_dump(stdout, vm, VCPU_ID, 0);
+	vcpu_dump(stdout, vcpu, 0);
 	TEST_FAIL("IRQ delivery timed out");
 }
 
 int main(int argc, char *argv[])
 {
 	struct timespec min_ts, max_ts, vm_ts;
+	struct kvm_vm *vm;
 	bool verbose;
 
 	verbose = argc > 1 && (!strncmp(argv[1], "-v", 3) ||
 			       !strncmp(argv[1], "--verbose", 10));
 
 	int xen_caps = kvm_check_cap(KVM_CAP_XEN_HVM);
-	if (!(xen_caps & KVM_XEN_HVM_CONFIG_SHARED_INFO) ) {
-		print_skip("KVM_XEN_HVM_CONFIG_SHARED_INFO not available");
-		exit(KSFT_SKIP);
-	}
+	TEST_REQUIRE(xen_caps & KVM_XEN_HVM_CONFIG_SHARED_INFO);
 
 	bool do_runstate_tests = !!(xen_caps & KVM_XEN_HVM_CONFIG_RUNSTATE);
 	bool do_eventfd_tests = !!(xen_caps & KVM_XEN_HVM_CONFIG_EVTCHN_2LEVEL);
@@ -374,8 +370,7 @@ int main(int argc, char *argv[])
 
 	clock_gettime(CLOCK_REALTIME, &min_ts);
 
-	vm = vm_create_default(VCPU_ID, 0, (void *) guest_code);
-	vcpu_set_cpuid(vm, VCPU_ID, kvm_get_supported_cpuid());
+	vm = vm_create_with_one_vcpu(&vcpu, guest_code);
 
 	/* Map a region for the shared_info page */
 	vm_userspace_mem_region_add(vm, VM_MEM_SRC_ANONYMOUS,
@@ -425,13 +420,13 @@ int main(int argc, char *argv[])
 		.type = KVM_XEN_VCPU_ATTR_TYPE_VCPU_INFO,
 		.u.gpa = VCPU_INFO_ADDR,
 	};
-	vcpu_ioctl(vm, VCPU_ID, KVM_XEN_VCPU_SET_ATTR, &vi);
+	vcpu_ioctl(vcpu, KVM_XEN_VCPU_SET_ATTR, &vi);
 
 	struct kvm_xen_vcpu_attr pvclock = {
 		.type = KVM_XEN_VCPU_ATTR_TYPE_VCPU_TIME_INFO,
 		.u.gpa = PVTIME_ADDR,
 	};
-	vcpu_ioctl(vm, VCPU_ID, KVM_XEN_VCPU_SET_ATTR, &pvclock);
+	vcpu_ioctl(vcpu, KVM_XEN_VCPU_SET_ATTR, &pvclock);
 
 	struct kvm_xen_hvm_attr vec = {
 		.type = KVM_XEN_ATTR_TYPE_UPCALL_VECTOR,
@@ -440,7 +435,7 @@ int main(int argc, char *argv[])
 	vm_ioctl(vm, KVM_XEN_HVM_SET_ATTR, &vec);
 
 	vm_init_descriptor_tables(vm);
-	vcpu_init_descriptor_tables(vm, VCPU_ID);
+	vcpu_init_descriptor_tables(vcpu);
 	vm_install_exception_handler(vm, EVTCHN_VECTOR, evtchn_handler);
 
 	if (do_runstate_tests) {
@@ -448,7 +443,7 @@ int main(int argc, char *argv[])
 			.type = KVM_XEN_VCPU_ATTR_TYPE_RUNSTATE_ADDR,
 			.u.gpa = RUNSTATE_ADDR,
 		};
-		vcpu_ioctl(vm, VCPU_ID, KVM_XEN_VCPU_SET_ATTR, &st);
+		vcpu_ioctl(vcpu, KVM_XEN_VCPU_SET_ATTR, &st);
 	}
 
 	int irq_fd[2] = { -1, -1 };
@@ -468,16 +463,16 @@ int main(int argc, char *argv[])
 		irq_routes.entries[0].gsi = 32;
 		irq_routes.entries[0].type = KVM_IRQ_ROUTING_XEN_EVTCHN;
 		irq_routes.entries[0].u.xen_evtchn.port = EVTCHN_TEST1;
-		irq_routes.entries[0].u.xen_evtchn.vcpu = VCPU_ID;
+		irq_routes.entries[0].u.xen_evtchn.vcpu = vcpu->id;
 		irq_routes.entries[0].u.xen_evtchn.priority = KVM_IRQ_ROUTING_XEN_EVTCHN_PRIO_2LEVEL;
 
 		irq_routes.entries[1].gsi = 33;
 		irq_routes.entries[1].type = KVM_IRQ_ROUTING_XEN_EVTCHN;
 		irq_routes.entries[1].u.xen_evtchn.port = EVTCHN_TEST2;
-		irq_routes.entries[1].u.xen_evtchn.vcpu = VCPU_ID;
+		irq_routes.entries[1].u.xen_evtchn.vcpu = vcpu->id;
 		irq_routes.entries[1].u.xen_evtchn.priority = KVM_IRQ_ROUTING_XEN_EVTCHN_PRIO_2LEVEL;
 
-		vm_ioctl(vm, KVM_SET_GSI_ROUTING, &irq_routes);
+		vm_ioctl(vm, KVM_SET_GSI_ROUTING, &irq_routes.info);
 
 		struct kvm_irqfd ifd = { };
 
@@ -508,14 +503,14 @@ int main(int argc, char *argv[])
 			.u.evtchn.type = EVTCHNSTAT_interdomain,
 			.u.evtchn.flags = 0,
 			.u.evtchn.deliver.port.port = EVTCHN_TEST1,
-			.u.evtchn.deliver.port.vcpu = VCPU_ID + 1,
+			.u.evtchn.deliver.port.vcpu = vcpu->id + 1,
 			.u.evtchn.deliver.port.priority = KVM_IRQ_ROUTING_XEN_EVTCHN_PRIO_2LEVEL,
 		};
 		vm_ioctl(vm, KVM_XEN_HVM_SET_ATTR, &inj);
 
 		/* Test migration to a different vCPU */
 		inj.u.evtchn.flags = KVM_XEN_EVTCHN_UPDATE;
-		inj.u.evtchn.deliver.port.vcpu = VCPU_ID;
+		inj.u.evtchn.deliver.port.vcpu = vcpu->id;
 		vm_ioctl(vm, KVM_XEN_HVM_SET_ATTR, &inj);
 
 		inj.u.evtchn.send_port = 197;
@@ -524,7 +519,7 @@ int main(int argc, char *argv[])
 		inj.u.evtchn.flags = 0;
 		vm_ioctl(vm, KVM_XEN_HVM_SET_ATTR, &inj);
 
-		vcpu_ioctl(vm, VCPU_ID, KVM_XEN_VCPU_SET_ATTR, &tmr);
+		vcpu_ioctl(vcpu, KVM_XEN_VCPU_SET_ATTR, &tmr);
 	}
 	vinfo = addr_gpa2hva(vm, VCPU_INFO_VADDR);
 	vinfo->evtchn_upcall_pending = 0;
@@ -535,19 +530,19 @@ int main(int argc, char *argv[])
 	bool evtchn_irq_expected = false;
 
 	for (;;) {
-		volatile struct kvm_run *run = vcpu_state(vm, VCPU_ID);
+		volatile struct kvm_run *run = vcpu->run;
 		struct ucall uc;
 
-		vcpu_run(vm, VCPU_ID);
+		vcpu_run(vcpu);
 
 		TEST_ASSERT(run->exit_reason == KVM_EXIT_IO,
 			    "Got exit_reason other than KVM_EXIT_IO: %u (%s)\n",
 			    run->exit_reason,
 			    exit_reason_str(run->exit_reason));
 
-		switch (get_ucall(vm, VCPU_ID, &uc)) {
+		switch (get_ucall(vcpu, &uc)) {
 		case UCALL_ABORT:
-			TEST_FAIL("%s", (const char *)uc.args[0]);
+			REPORT_GUEST_ASSERT(uc);
 			/* NOT REACHED */
 		case UCALL_SYNC: {
 			struct kvm_xen_vcpu_attr rst;
@@ -574,7 +569,7 @@ int main(int argc, char *argv[])
 					printf("Testing runstate %s\n", runstate_names[uc.args[1]]);
 				rst.type = KVM_XEN_VCPU_ATTR_TYPE_RUNSTATE_CURRENT;
 				rst.u.runstate.state = uc.args[1];
-				vcpu_ioctl(vm, VCPU_ID, KVM_XEN_VCPU_SET_ATTR, &rst);
+				vcpu_ioctl(vcpu, KVM_XEN_VCPU_SET_ATTR, &rst);
 				break;
 
 			case 4:
@@ -589,7 +584,7 @@ int main(int argc, char *argv[])
 					0x6b6b - rs->time[RUNSTATE_offline];
 				rst.u.runstate.time_runnable = -rst.u.runstate.time_blocked -
 					rst.u.runstate.time_offline;
-				vcpu_ioctl(vm, VCPU_ID, KVM_XEN_VCPU_SET_ATTR, &rst);
+				vcpu_ioctl(vcpu, KVM_XEN_VCPU_SET_ATTR, &rst);
 				break;
 
 			case 5:
@@ -601,7 +596,7 @@ int main(int argc, char *argv[])
 				rst.u.runstate.state_entry_time = 0x6b6b + 0x5a;
 				rst.u.runstate.time_blocked = 0x6b6b;
 				rst.u.runstate.time_offline = 0x5a;
-				vcpu_ioctl(vm, VCPU_ID, KVM_XEN_VCPU_SET_ATTR, &rst);
+				vcpu_ioctl(vcpu, KVM_XEN_VCPU_SET_ATTR, &rst);
 				break;
 
 			case 6:
@@ -660,7 +655,7 @@ int main(int argc, char *argv[])
 
 				struct kvm_irq_routing_xen_evtchn e;
 				e.port = EVTCHN_TEST2;
-				e.vcpu = VCPU_ID;
+				e.vcpu = vcpu->id;
 				e.priority = KVM_IRQ_ROUTING_XEN_EVTCHN_PRIO_2LEVEL;
 
 				vm_ioctl(vm, KVM_XEN_HVM_EVTCHN_SEND, &e);
@@ -702,7 +697,7 @@ int main(int argc, char *argv[])
 			case 14:
 				memset(&tmr, 0, sizeof(tmr));
 				tmr.type = KVM_XEN_VCPU_ATTR_TYPE_TIMER;
-				vcpu_ioctl(vm, VCPU_ID, KVM_XEN_VCPU_GET_ATTR, &tmr);
+				vcpu_ioctl(vcpu, KVM_XEN_VCPU_GET_ATTR, &tmr);
 				TEST_ASSERT(tmr.u.timer.port == EVTCHN_TIMER,
 					    "Timer port not returned");
 				TEST_ASSERT(tmr.u.timer.priority == KVM_IRQ_ROUTING_XEN_EVTCHN_PRIO_2LEVEL,
@@ -721,8 +716,8 @@ int main(int argc, char *argv[])
 				if (verbose)
 					printf("Testing restored oneshot timer\n");
 
-				tmr.u.timer.expires_ns = rs->state_entry_time + 100000000,
-				vcpu_ioctl(vm, VCPU_ID, KVM_XEN_VCPU_SET_ATTR, &tmr);
+				tmr.u.timer.expires_ns = rs->state_entry_time + 100000000;
+				vcpu_ioctl(vcpu, KVM_XEN_VCPU_SET_ATTR, &tmr);
 				evtchn_irq_expected = true;
 				alarm(1);
 				break;
@@ -748,8 +743,8 @@ int main(int argc, char *argv[])
 				if (verbose)
 					printf("Testing SCHEDOP_poll wake on masked event\n");
 
-				tmr.u.timer.expires_ns = rs->state_entry_time + 100000000,
-				vcpu_ioctl(vm, VCPU_ID, KVM_XEN_VCPU_SET_ATTR, &tmr);
+				tmr.u.timer.expires_ns = rs->state_entry_time + 100000000;
+				vcpu_ioctl(vcpu, KVM_XEN_VCPU_SET_ATTR, &tmr);
 				alarm(1);
 				break;
 
@@ -760,11 +755,11 @@ int main(int argc, char *argv[])
 
 				evtchn_irq_expected = true;
 				tmr.u.timer.expires_ns = rs->state_entry_time + 100000000;
-				vcpu_ioctl(vm, VCPU_ID, KVM_XEN_VCPU_SET_ATTR, &tmr);
+				vcpu_ioctl(vcpu, KVM_XEN_VCPU_SET_ATTR, &tmr);
 
 				/* Read it back and check the pending time is reported correctly */
 				tmr.u.timer.expires_ns = 0;
-				vcpu_ioctl(vm, VCPU_ID, KVM_XEN_VCPU_GET_ATTR, &tmr);
+				vcpu_ioctl(vcpu, KVM_XEN_VCPU_GET_ATTR, &tmr);
 				TEST_ASSERT(tmr.u.timer.expires_ns == rs->state_entry_time + 100000000,
 					    "Timer not reported pending");
 				alarm(1);
@@ -774,7 +769,7 @@ int main(int argc, char *argv[])
 				TEST_ASSERT(!evtchn_irq_expected,
 					    "Expected event channel IRQ but it didn't happen");
 				/* Read timer and check it is no longer pending */
-				vcpu_ioctl(vm, VCPU_ID, KVM_XEN_VCPU_GET_ATTR, &tmr);
+				vcpu_ioctl(vcpu, KVM_XEN_VCPU_GET_ATTR, &tmr);
 				TEST_ASSERT(!tmr.u.timer.expires_ns, "Timer still reported pending");
 
 				shinfo->evtchn_pending[0] = 0;
@@ -783,7 +778,7 @@ int main(int argc, char *argv[])
 
 				evtchn_irq_expected = true;
 				tmr.u.timer.expires_ns = rs->state_entry_time - 100000000ULL;
-				vcpu_ioctl(vm, VCPU_ID, KVM_XEN_VCPU_SET_ATTR, &tmr);
+				vcpu_ioctl(vcpu, KVM_XEN_VCPU_SET_ATTR, &tmr);
 				alarm(1);
 				break;
 
@@ -853,7 +848,7 @@ int main(int argc, char *argv[])
 		struct kvm_xen_vcpu_attr rst = {
 			.type = KVM_XEN_VCPU_ATTR_TYPE_RUNSTATE_DATA,
 		};
-		vcpu_ioctl(vm, VCPU_ID, KVM_XEN_VCPU_GET_ATTR, &rst);
+		vcpu_ioctl(vcpu, KVM_XEN_VCPU_GET_ATTR, &rst);
 
 		if (verbose) {
 			printf("Runstate: %s(%d), entry %" PRIu64 " ns\n",