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, 211 insertions, 0 deletions

diff --git a/tools/testing/selftests/kvm/x86_64/svm_nested_soft_inject_test.c b/tools/testing/selftests/kvm/x86_64/svm_nested_soft_inject_test.c
new file mode 100644
index 000000000000..e637d7736012
--- /dev/null
+++ b/tools/testing/selftests/kvm/x86_64/svm_nested_soft_inject_test.c
@@ -0,0 +1,211 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2022 Oracle and/or its affiliates.
+ *
+ * Based on:
+ *   svm_int_ctl_test
+ *
+ *   Copyright (C) 2021, Red Hat, Inc.
+ *
+ */
+
+#include <stdatomic.h>
+#include <stdio.h>
+#include <unistd.h>
+#include "apic.h"
+#include "kvm_util.h"
+#include "processor.h"
+#include "svm_util.h"
+#include "test_util.h"
+
+#define INT_NR			0x20
+
+static_assert(ATOMIC_INT_LOCK_FREE == 2, "atomic int is not lockless");
+
+static unsigned int bp_fired;
+static void guest_bp_handler(struct ex_regs *regs)
+{
+	bp_fired++;
+}
+
+static unsigned int int_fired;
+static void l2_guest_code_int(void);
+
+static void guest_int_handler(struct ex_regs *regs)
+{
+	int_fired++;
+	GUEST_ASSERT_2(regs->rip == (unsigned long)l2_guest_code_int,
+		       regs->rip, (unsigned long)l2_guest_code_int);
+}
+
+static void l2_guest_code_int(void)
+{
+	GUEST_ASSERT_1(int_fired == 1, int_fired);
+	vmmcall();
+	ud2();
+
+	GUEST_ASSERT_1(bp_fired == 1, bp_fired);
+	hlt();
+}
+
+static atomic_int nmi_stage;
+#define nmi_stage_get() atomic_load_explicit(&nmi_stage, memory_order_acquire)
+#define nmi_stage_inc() atomic_fetch_add_explicit(&nmi_stage, 1, memory_order_acq_rel)
+static void guest_nmi_handler(struct ex_regs *regs)
+{
+	nmi_stage_inc();
+
+	if (nmi_stage_get() == 1) {
+		vmmcall();
+		GUEST_ASSERT(false);
+	} else {
+		GUEST_ASSERT_1(nmi_stage_get() == 3, nmi_stage_get());
+		GUEST_DONE();
+	}
+}
+
+static void l2_guest_code_nmi(void)
+{
+	ud2();
+}
+
+static void l1_guest_code(struct svm_test_data *svm, uint64_t is_nmi, uint64_t idt_alt)
+{
+	#define L2_GUEST_STACK_SIZE 64
+	unsigned long l2_guest_stack[L2_GUEST_STACK_SIZE];
+	struct vmcb *vmcb = svm->vmcb;
+
+	if (is_nmi)
+		x2apic_enable();
+
+	/* Prepare for L2 execution. */
+	generic_svm_setup(svm,
+			  is_nmi ? l2_guest_code_nmi : l2_guest_code_int,
+			  &l2_guest_stack[L2_GUEST_STACK_SIZE]);
+
+	vmcb->control.intercept_exceptions |= BIT(PF_VECTOR) | BIT(UD_VECTOR);
+	vmcb->control.intercept |= BIT(INTERCEPT_NMI) | BIT(INTERCEPT_HLT);
+
+	if (is_nmi) {
+		vmcb->control.event_inj = SVM_EVTINJ_VALID | SVM_EVTINJ_TYPE_NMI;
+	} else {
+		vmcb->control.event_inj = INT_NR | SVM_EVTINJ_VALID | SVM_EVTINJ_TYPE_SOFT;
+		/* The return address pushed on stack */
+		vmcb->control.next_rip = vmcb->save.rip;
+	}
+
+	run_guest(vmcb, svm->vmcb_gpa);
+	GUEST_ASSERT_3(vmcb->control.exit_code == SVM_EXIT_VMMCALL,
+		       vmcb->control.exit_code,
+		       vmcb->control.exit_info_1, vmcb->control.exit_info_2);
+
+	if (is_nmi) {
+		clgi();
+		x2apic_write_reg(APIC_ICR, APIC_DEST_SELF | APIC_INT_ASSERT | APIC_DM_NMI);
+
+		GUEST_ASSERT_1(nmi_stage_get() == 1, nmi_stage_get());
+		nmi_stage_inc();
+
+		stgi();
+		/* self-NMI happens here */
+		while (true)
+			cpu_relax();
+	}
+
+	/* Skip over VMMCALL */
+	vmcb->save.rip += 3;
+
+	/* Switch to alternate IDT to cause intervening NPF again */
+	vmcb->save.idtr.base = idt_alt;
+	vmcb->control.clean = 0; /* &= ~BIT(VMCB_DT) would be enough */
+
+	vmcb->control.event_inj = BP_VECTOR | SVM_EVTINJ_VALID | SVM_EVTINJ_TYPE_EXEPT;
+	/* The return address pushed on stack, skip over UD2 */
+	vmcb->control.next_rip = vmcb->save.rip + 2;
+
+	run_guest(vmcb, svm->vmcb_gpa);
+	GUEST_ASSERT_3(vmcb->control.exit_code == SVM_EXIT_HLT,
+		       vmcb->control.exit_code,
+		       vmcb->control.exit_info_1, vmcb->control.exit_info_2);
+
+	GUEST_DONE();
+}
+
+static void run_test(bool is_nmi)
+{
+	struct kvm_vcpu *vcpu;
+	struct kvm_vm *vm;
+	vm_vaddr_t svm_gva;
+	vm_vaddr_t idt_alt_vm;
+	struct kvm_guest_debug debug;
+
+	pr_info("Running %s test\n", is_nmi ? "NMI" : "soft int");
+
+	vm = vm_create_with_one_vcpu(&vcpu, l1_guest_code);
+
+	vm_init_descriptor_tables(vm);
+	vcpu_init_descriptor_tables(vcpu);
+
+	vm_install_exception_handler(vm, NMI_VECTOR, guest_nmi_handler);
+	vm_install_exception_handler(vm, BP_VECTOR, guest_bp_handler);
+	vm_install_exception_handler(vm, INT_NR, guest_int_handler);
+
+	vcpu_alloc_svm(vm, &svm_gva);
+
+	if (!is_nmi) {
+		void *idt, *idt_alt;
+
+		idt_alt_vm = vm_vaddr_alloc_page(vm);
+		idt_alt = addr_gva2hva(vm, idt_alt_vm);
+		idt = addr_gva2hva(vm, vm->idt);
+		memcpy(idt_alt, idt, getpagesize());
+	} else {
+		idt_alt_vm = 0;
+	}
+	vcpu_args_set(vcpu, 3, svm_gva, (uint64_t)is_nmi, (uint64_t)idt_alt_vm);
+
+	memset(&debug, 0, sizeof(debug));
+	vcpu_guest_debug_set(vcpu, &debug);
+
+	struct kvm_run *run = vcpu->run;
+	struct ucall uc;
+
+	alarm(2);
+	vcpu_run(vcpu);
+	alarm(0);
+	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(vcpu, &uc)) {
+	case UCALL_ABORT:
+		REPORT_GUEST_ASSERT_3(uc, "vals = 0x%lx 0x%lx 0x%lx");
+		break;
+		/* NOT REACHED */
+	case UCALL_DONE:
+		goto done;
+	default:
+		TEST_FAIL("Unknown ucall 0x%lx.", uc.cmd);
+	}
+done:
+	kvm_vm_free(vm);
+}
+
+int main(int argc, char *argv[])
+{
+	/* Tell stdout not to buffer its content */
+	setbuf(stdout, NULL);
+
+	TEST_REQUIRE(kvm_cpu_has(X86_FEATURE_SVM));
+
+	TEST_ASSERT(kvm_cpu_has(X86_FEATURE_NRIPS),
+		    "KVM with nSVM is supposed to unconditionally advertise nRIP Save");
+
+	atomic_init(&nmi_stage, 0);
+
+	run_test(false);
+	run_test(true);
+
+	return 0;
+}