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, 29 insertions, 24 deletions

diff --git a/tools/testing/selftests/kvm/max_guest_memory_test.c b/tools/testing/selftests/kvm/max_guest_memory_test.c
index 15f046e19cb2..9a6e4f3ad6b5 100644
--- a/tools/testing/selftests/kvm/max_guest_memory_test.c
+++ b/tools/testing/selftests/kvm/max_guest_memory_test.c
@@ -28,8 +28,7 @@ static void guest_code(uint64_t start_gpa, uint64_t end_gpa, uint64_t stride)
 }
 
 struct vcpu_info {
-	struct kvm_vm *vm;
-	uint32_t id;
+	struct kvm_vcpu *vcpu;
 	uint64_t start_gpa;
 	uint64_t end_gpa;
 };
@@ -52,45 +51,45 @@ static void rendezvous_with_boss(void)
 	}
 }
 
-static void run_vcpu(struct kvm_vm *vm, uint32_t vcpu_id)
+static void run_vcpu(struct kvm_vcpu *vcpu)
 {
-	vcpu_run(vm, vcpu_id);
-	ASSERT_EQ(get_ucall(vm, vcpu_id, NULL), UCALL_DONE);
+	vcpu_run(vcpu);
+	ASSERT_EQ(get_ucall(vcpu, NULL), UCALL_DONE);
 }
 
 static void *vcpu_worker(void *data)
 {
-	struct vcpu_info *vcpu = data;
+	struct vcpu_info *info = data;
+	struct kvm_vcpu *vcpu = info->vcpu;
 	struct kvm_vm *vm = vcpu->vm;
 	struct kvm_sregs sregs;
 	struct kvm_regs regs;
 
-	vcpu_args_set(vm, vcpu->id, 3, vcpu->start_gpa, vcpu->end_gpa,
-		      vm_get_page_size(vm));
+	vcpu_args_set(vcpu, 3, info->start_gpa, info->end_gpa, vm->page_size);
 
 	/* Snapshot regs before the first run. */
-	vcpu_regs_get(vm, vcpu->id, &regs);
+	vcpu_regs_get(vcpu, &regs);
 	rendezvous_with_boss();
 
-	run_vcpu(vm, vcpu->id);
+	run_vcpu(vcpu);
 	rendezvous_with_boss();
-	vcpu_regs_set(vm, vcpu->id, &regs);
-	vcpu_sregs_get(vm, vcpu->id, &sregs);
+	vcpu_regs_set(vcpu, &regs);
+	vcpu_sregs_get(vcpu, &sregs);
 #ifdef __x86_64__
 	/* Toggle CR0.WP to trigger a MMU context reset. */
 	sregs.cr0 ^= X86_CR0_WP;
 #endif
-	vcpu_sregs_set(vm, vcpu->id, &sregs);
+	vcpu_sregs_set(vcpu, &sregs);
 	rendezvous_with_boss();
 
-	run_vcpu(vm, vcpu->id);
+	run_vcpu(vcpu);
 	rendezvous_with_boss();
 
 	return NULL;
 }
 
-static pthread_t *spawn_workers(struct kvm_vm *vm, uint64_t start_gpa,
-				uint64_t end_gpa)
+static pthread_t *spawn_workers(struct kvm_vm *vm, struct kvm_vcpu **vcpus,
+				uint64_t start_gpa, uint64_t end_gpa)
 {
 	struct vcpu_info *info;
 	uint64_t gpa, nr_bytes;
@@ -104,12 +103,11 @@ static pthread_t *spawn_workers(struct kvm_vm *vm, uint64_t start_gpa,
 	TEST_ASSERT(info, "Failed to allocate vCPU gpa ranges");
 
 	nr_bytes = ((end_gpa - start_gpa) / nr_vcpus) &
-			~((uint64_t)vm_get_page_size(vm) - 1);
+			~((uint64_t)vm->page_size - 1);
 	TEST_ASSERT(nr_bytes, "C'mon, no way you have %d CPUs", nr_vcpus);
 
 	for (i = 0, gpa = start_gpa; i < nr_vcpus; i++, gpa += nr_bytes) {
-		info[i].vm = vm;
-		info[i].id = i;
+		info[i].vcpu = vcpus[i];
 		info[i].start_gpa = gpa;
 		info[i].end_gpa = gpa + nr_bytes;
 		pthread_create(&threads[i], NULL, vcpu_worker, &info[i]);
@@ -172,6 +170,7 @@ int main(int argc, char *argv[])
 	uint64_t max_gpa, gpa, slot_size, max_mem, i;
 	int max_slots, slot, opt, fd;
 	bool hugepages = false;
+	struct kvm_vcpu **vcpus;
 	pthread_t *threads;
 	struct kvm_vm *vm;
 	void *mem;
@@ -215,9 +214,12 @@ int main(int argc, char *argv[])
 		}
 	}
 
-	vm = vm_create_default_with_vcpus(nr_vcpus, 0, 0, guest_code, NULL);
+	vcpus = malloc(nr_vcpus * sizeof(*vcpus));
+	TEST_ASSERT(vcpus, "Failed to allocate vCPU array");
+
+	vm = vm_create_with_vcpus(nr_vcpus, guest_code, vcpus);
 
-	max_gpa = vm_get_max_gfn(vm) << vm_get_page_shift(vm);
+	max_gpa = vm->max_gfn << vm->page_shift;
 	TEST_ASSERT(max_gpa > (4 * slot_size), "MAXPHYADDR <4gb ");
 
 	fd = kvm_memfd_alloc(slot_size, hugepages);
@@ -227,7 +229,7 @@ int main(int argc, char *argv[])
 	TEST_ASSERT(!madvise(mem, slot_size, MADV_NOHUGEPAGE), "madvise() failed");
 
 	/* Pre-fault the memory to avoid taking mmap_sem on guest page faults. */
-	for (i = 0; i < slot_size; i += vm_get_page_size(vm))
+	for (i = 0; i < slot_size; i += vm->page_size)
 		((uint8_t *)mem)[i] = 0xaa;
 
 	gpa = 0;
@@ -246,13 +248,16 @@ int main(int argc, char *argv[])
 		for (i = 0; i < slot_size; i += size_1gb)
 			__virt_pg_map(vm, gpa + i, gpa + i, PG_LEVEL_1G);
 #else
-		for (i = 0; i < slot_size; i += vm_get_page_size(vm))
+		for (i = 0; i < slot_size; i += vm->page_size)
 			virt_pg_map(vm, gpa + i, gpa + i);
 #endif
 	}
 
 	atomic_set(&rendezvous, nr_vcpus + 1);
-	threads = spawn_workers(vm, start_gpa, gpa);
+	threads = spawn_workers(vm, vcpus, start_gpa, gpa);
+
+	free(vcpus);
+	vcpus = NULL;
 
 	pr_info("Running with %lugb of guest memory and %u vCPUs\n",
 		(gpa - start_gpa) / size_1gb, nr_vcpus);