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, 22 insertions, 44 deletions

diff --git a/tools/testing/selftests/kvm/kvm_page_table_test.c b/tools/testing/selftests/kvm/kvm_page_table_test.c
index 2c4a7563a4f8..f42c6ac6d71d 100644
--- a/tools/testing/selftests/kvm/kvm_page_table_test.c
+++ b/tools/testing/selftests/kvm/kvm_page_table_test.c
@@ -46,11 +46,6 @@ static const char * const test_stage_string[] = {
 	"KVM_ADJUST_MAPPINGS",
 };
 
-struct vcpu_args {
-	int vcpu_id;
-	bool vcpu_write;
-};
-
 struct test_args {
 	struct kvm_vm *vm;
 	uint64_t guest_test_virt_mem;
@@ -60,7 +55,7 @@ struct test_args {
 	uint64_t large_num_pages;
 	uint64_t host_pages_per_lpage;
 	enum vm_mem_backing_src_type src_type;
-	struct vcpu_args vcpu_args[KVM_MAX_VCPUS];
+	struct kvm_vcpu *vcpus[KVM_MAX_VCPUS];
 };
 
 /*
@@ -92,17 +87,13 @@ static uint64_t guest_test_phys_mem;
  */
 static uint64_t guest_test_virt_mem = DEFAULT_GUEST_TEST_MEM;
 
-static void guest_code(int vcpu_id)
+static void guest_code(bool do_write)
 {
 	struct test_args *p = &test_args;
-	struct vcpu_args *vcpu_args = &p->vcpu_args[vcpu_id];
 	enum test_stage *current_stage = &guest_test_stage;
 	uint64_t addr;
 	int i, j;
 
-	/* Make sure vCPU args data structure is not corrupt */
-	GUEST_ASSERT(vcpu_args->vcpu_id == vcpu_id);
-
 	while (true) {
 		addr = p->guest_test_virt_mem;
 
@@ -123,7 +114,7 @@ static void guest_code(int vcpu_id)
 		 */
 		case KVM_CREATE_MAPPINGS:
 			for (i = 0; i < p->large_num_pages; i++) {
-				if (vcpu_args->vcpu_write)
+				if (do_write)
 					*(uint64_t *)addr = 0x0123456789ABCDEF;
 				else
 					READ_ONCE(*(uint64_t *)addr);
@@ -193,17 +184,14 @@ static void guest_code(int vcpu_id)
 
 static void *vcpu_worker(void *data)
 {
-	int ret;
-	struct vcpu_args *vcpu_args = data;
-	struct kvm_vm *vm = test_args.vm;
-	int vcpu_id = vcpu_args->vcpu_id;
-	struct kvm_run *run;
+	struct kvm_vcpu *vcpu = data;
+	bool do_write = !(vcpu->id % 2);
 	struct timespec start;
 	struct timespec ts_diff;
 	enum test_stage stage;
+	int ret;
 
-	vcpu_args_set(vm, vcpu_id, 1, vcpu_id);
-	run = vcpu_state(vm, vcpu_id);
+	vcpu_args_set(vcpu, 1, do_write);
 
 	while (!READ_ONCE(host_quit)) {
 		ret = sem_wait(&test_stage_updated);
@@ -213,15 +201,15 @@ static void *vcpu_worker(void *data)
 			return NULL;
 
 		clock_gettime(CLOCK_MONOTONIC_RAW, &start);
-		ret = _vcpu_run(vm, vcpu_id);
+		ret = _vcpu_run(vcpu);
 		ts_diff = timespec_elapsed(start);
 
 		TEST_ASSERT(ret == 0, "vcpu_run failed: %d\n", ret);
-		TEST_ASSERT(get_ucall(vm, vcpu_id, NULL) == UCALL_SYNC,
+		TEST_ASSERT(get_ucall(vcpu, NULL) == UCALL_SYNC,
 			    "Invalid guest sync status: exit_reason=%s\n",
-			    exit_reason_str(run->exit_reason));
+			    exit_reason_str(vcpu->run->exit_reason));
 
-		pr_debug("Got sync event from vCPU %d\n", vcpu_id);
+		pr_debug("Got sync event from vCPU %d\n", vcpu->id);
 		stage = READ_ONCE(*current_stage);
 
 		/*
@@ -230,7 +218,7 @@ static void *vcpu_worker(void *data)
 		 */
 		pr_debug("vCPU %d has completed stage %s\n"
 			 "execution time is: %ld.%.9lds\n\n",
-			 vcpu_id, test_stage_string[stage],
+			 vcpu->id, test_stage_string[stage],
 			 ts_diff.tv_sec, ts_diff.tv_nsec);
 
 		ret = sem_post(&test_stage_completed);
@@ -250,7 +238,6 @@ static struct kvm_vm *pre_init_before_test(enum vm_guest_mode mode, void *arg)
 {
 	int ret;
 	struct test_params *p = arg;
-	struct vcpu_args *vcpu_args;
 	enum vm_mem_backing_src_type src_type = p->src_type;
 	uint64_t large_page_size = get_backing_src_pagesz(src_type);
 	uint64_t guest_page_size = vm_guest_mode_params[mode].page_size;
@@ -260,7 +247,6 @@ static struct kvm_vm *pre_init_before_test(enum vm_guest_mode mode, void *arg)
 	uint64_t alignment;
 	void *host_test_mem;
 	struct kvm_vm *vm;
-	int vcpu_id;
 
 	/* Align up the test memory size */
 	alignment = max(large_page_size, guest_page_size);
@@ -268,12 +254,12 @@ static struct kvm_vm *pre_init_before_test(enum vm_guest_mode mode, void *arg)
 
 	/* Create a VM with enough guest pages */
 	guest_num_pages = test_mem_size / guest_page_size;
-	vm = vm_create_with_vcpus(mode, nr_vcpus, DEFAULT_GUEST_PHY_PAGES,
-				  guest_num_pages, 0, guest_code, NULL);
+	vm = __vm_create_with_vcpus(mode, nr_vcpus, guest_num_pages,
+				    guest_code, test_args.vcpus);
 
 	/* Align down GPA of the testing memslot */
 	if (!p->phys_offset)
-		guest_test_phys_mem = (vm_get_max_gfn(vm) - guest_num_pages) *
+		guest_test_phys_mem = (vm->max_gfn - guest_num_pages) *
 				       guest_page_size;
 	else
 		guest_test_phys_mem = p->phys_offset;
@@ -292,12 +278,6 @@ static struct kvm_vm *pre_init_before_test(enum vm_guest_mode mode, void *arg)
 	test_args.host_pages_per_lpage = large_page_size / host_page_size;
 	test_args.src_type = src_type;
 
-	for (vcpu_id = 0; vcpu_id < KVM_MAX_VCPUS; vcpu_id++) {
-		vcpu_args = &test_args.vcpu_args[vcpu_id];
-		vcpu_args->vcpu_id = vcpu_id;
-		vcpu_args->vcpu_write = !(vcpu_id % 2);
-	}
-
 	/* Add an extra memory slot with specified backing src type */
 	vm_userspace_mem_region_add(vm, src_type, guest_test_phys_mem,
 				    TEST_MEM_SLOT_INDEX, guest_num_pages, 0);
@@ -363,12 +343,11 @@ static void vcpus_complete_new_stage(enum test_stage stage)
 
 static void run_test(enum vm_guest_mode mode, void *arg)
 {
-	int ret;
 	pthread_t *vcpu_threads;
 	struct kvm_vm *vm;
-	int vcpu_id;
 	struct timespec start;
 	struct timespec ts_diff;
+	int ret, i;
 
 	/* Create VM with vCPUs and make some pre-initialization */
 	vm = pre_init_before_test(mode, arg);
@@ -379,10 +358,9 @@ static void run_test(enum vm_guest_mode mode, void *arg)
 	host_quit = false;
 	*current_stage = KVM_BEFORE_MAPPINGS;
 
-	for (vcpu_id = 0; vcpu_id < nr_vcpus; vcpu_id++) {
-		pthread_create(&vcpu_threads[vcpu_id], NULL, vcpu_worker,
-			       &test_args.vcpu_args[vcpu_id]);
-	}
+	for (i = 0; i < nr_vcpus; i++)
+		pthread_create(&vcpu_threads[i], NULL, vcpu_worker,
+			       test_args.vcpus[i]);
 
 	vcpus_complete_new_stage(*current_stage);
 	pr_info("Started all vCPUs successfully\n");
@@ -424,13 +402,13 @@ static void run_test(enum vm_guest_mode mode, void *arg)
 
 	/* Tell the vcpu thread to quit */
 	host_quit = true;
-	for (vcpu_id = 0; vcpu_id < nr_vcpus; vcpu_id++) {
+	for (i = 0; i < nr_vcpus; i++) {
 		ret = sem_post(&test_stage_updated);
 		TEST_ASSERT(ret == 0, "Error in sem_post");
 	}
 
-	for (vcpu_id = 0; vcpu_id < nr_vcpus; vcpu_id++)
-		pthread_join(vcpu_threads[vcpu_id], NULL);
+	for (i = 0; i < nr_vcpus; i++)
+		pthread_join(vcpu_threads[i], NULL);
 
 	ret = sem_destroy(&test_stage_updated);
 	TEST_ASSERT(ret == 0, "Error in sem_destroy");