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, 23 insertions, 26 deletions

diff --git a/tools/testing/selftests/kvm/demand_paging_test.c b/tools/testing/selftests/kvm/demand_paging_test.c
index 6a719d065599..779ae54f89c4 100644
--- a/tools/testing/selftests/kvm/demand_paging_test.c
+++ b/tools/testing/selftests/kvm/demand_paging_test.c
@@ -44,28 +44,26 @@ static char *guest_data_prototype;
 
 static void vcpu_worker(struct perf_test_vcpu_args *vcpu_args)
 {
-	int ret;
-	int vcpu_id = vcpu_args->vcpu_id;
-	struct kvm_vm *vm = perf_test_args.vm;
-	struct kvm_run *run;
+	struct kvm_vcpu *vcpu = vcpu_args->vcpu;
+	int vcpu_idx = vcpu_args->vcpu_idx;
+	struct kvm_run *run = vcpu->run;
 	struct timespec start;
 	struct timespec ts_diff;
-
-	run = vcpu_state(vm, vcpu_id);
+	int ret;
 
 	clock_gettime(CLOCK_MONOTONIC, &start);
 
 	/* Let the guest access its memory */
-	ret = _vcpu_run(vm, vcpu_id);
+	ret = _vcpu_run(vcpu);
 	TEST_ASSERT(ret == 0, "vcpu_run failed: %d\n", ret);
-	if (get_ucall(vm, vcpu_id, NULL) != UCALL_SYNC) {
+	if (get_ucall(vcpu, NULL) != UCALL_SYNC) {
 		TEST_ASSERT(false,
 			    "Invalid guest sync status: exit_reason=%s\n",
 			    exit_reason_str(run->exit_reason));
 	}
 
 	ts_diff = timespec_elapsed(start);
-	PER_VCPU_DEBUG("vCPU %d execution time: %ld.%.9lds\n", vcpu_id,
+	PER_VCPU_DEBUG("vCPU %d execution time: %ld.%.9lds\n", vcpu_idx,
 		       ts_diff.tv_sec, ts_diff.tv_nsec);
 }
 
@@ -223,6 +221,7 @@ static void setup_demand_paging(struct kvm_vm *vm,
 	struct uffdio_api uffdio_api;
 	struct uffdio_register uffdio_register;
 	uint64_t expected_ioctls = ((uint64_t) 1) << _UFFDIO_COPY;
+	int ret;
 
 	PER_PAGE_DEBUG("Userfaultfd %s mode, faults resolved with %s\n",
 		       is_minor ? "MINOR" : "MISSING",
@@ -242,19 +241,18 @@ static void setup_demand_paging(struct kvm_vm *vm,
 	}
 
 	uffd = syscall(__NR_userfaultfd, O_CLOEXEC | O_NONBLOCK);
-	TEST_ASSERT(uffd >= 0, "uffd creation failed, errno: %d", errno);
+	TEST_ASSERT(uffd >= 0, __KVM_SYSCALL_ERROR("userfaultfd()", uffd));
 
 	uffdio_api.api = UFFD_API;
 	uffdio_api.features = 0;
-	TEST_ASSERT(ioctl(uffd, UFFDIO_API, &uffdio_api) != -1,
-		    "ioctl UFFDIO_API failed: %" PRIu64,
-		    (uint64_t)uffdio_api.api);
+	ret = ioctl(uffd, UFFDIO_API, &uffdio_api);
+	TEST_ASSERT(ret != -1, __KVM_SYSCALL_ERROR("UFFDIO_API", ret));
 
 	uffdio_register.range.start = (uint64_t)hva;
 	uffdio_register.range.len = len;
 	uffdio_register.mode = uffd_mode;
-	TEST_ASSERT(ioctl(uffd, UFFDIO_REGISTER, &uffdio_register) != -1,
-		    "ioctl UFFDIO_REGISTER failed");
+	ret = ioctl(uffd, UFFDIO_REGISTER, &uffdio_register);
+	TEST_ASSERT(ret != -1, __KVM_SYSCALL_ERROR("UFFDIO_REGISTER", ret));
 	TEST_ASSERT((uffdio_register.ioctls & expected_ioctls) ==
 		    expected_ioctls, "missing userfaultfd ioctls");
 
@@ -285,8 +283,7 @@ static void run_test(enum vm_guest_mode mode, void *arg)
 	struct timespec ts_diff;
 	int *pipefds = NULL;
 	struct kvm_vm *vm;
-	int vcpu_id;
-	int r;
+	int r, i;
 
 	vm = perf_test_create_vm(mode, nr_vcpus, guest_percpu_mem_size, 1,
 				 p->src_type, p->partition_vcpu_memory_access);
@@ -309,12 +306,12 @@ static void run_test(enum vm_guest_mode mode, void *arg)
 		pipefds = malloc(sizeof(int) * nr_vcpus * 2);
 		TEST_ASSERT(pipefds, "Unable to allocate memory for pipefd");
 
-		for (vcpu_id = 0; vcpu_id < nr_vcpus; vcpu_id++) {
+		for (i = 0; i < nr_vcpus; i++) {
 			struct perf_test_vcpu_args *vcpu_args;
 			void *vcpu_hva;
 			void *vcpu_alias;
 
-			vcpu_args = &perf_test_args.vcpu_args[vcpu_id];
+			vcpu_args = &perf_test_args.vcpu_args[i];
 
 			/* Cache the host addresses of the region */
 			vcpu_hva = addr_gpa2hva(vm, vcpu_args->gpa);
@@ -324,13 +321,13 @@ static void run_test(enum vm_guest_mode mode, void *arg)
 			 * Set up user fault fd to handle demand paging
 			 * requests.
 			 */
-			r = pipe2(&pipefds[vcpu_id * 2],
+			r = pipe2(&pipefds[i * 2],
 				  O_CLOEXEC | O_NONBLOCK);
 			TEST_ASSERT(!r, "Failed to set up pipefd");
 
-			setup_demand_paging(vm, &uffd_handler_threads[vcpu_id],
-					    pipefds[vcpu_id * 2], p->uffd_mode,
-					    p->uffd_delay, &uffd_args[vcpu_id],
+			setup_demand_paging(vm, &uffd_handler_threads[i],
+					    pipefds[i * 2], p->uffd_mode,
+					    p->uffd_delay, &uffd_args[i],
 					    vcpu_hva, vcpu_alias,
 					    vcpu_args->pages * perf_test_args.guest_page_size);
 		}
@@ -350,11 +347,11 @@ static void run_test(enum vm_guest_mode mode, void *arg)
 		char c;
 
 		/* Tell the user fault fd handler threads to quit */
-		for (vcpu_id = 0; vcpu_id < nr_vcpus; vcpu_id++) {
-			r = write(pipefds[vcpu_id * 2 + 1], &c, 1);
+		for (i = 0; i < nr_vcpus; i++) {
+			r = write(pipefds[i * 2 + 1], &c, 1);
 			TEST_ASSERT(r == 1, "Unable to write to pipefd");
 
-			pthread_join(uffd_handler_threads[vcpu_id], NULL);
+			pthread_join(uffd_handler_threads[i], NULL);
 		}
 	}