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, 30 insertions, 55 deletions

diff --git a/tools/testing/selftests/kvm/x86_64/emulator_error_test.c b/tools/testing/selftests/kvm/x86_64/emulator_error_test.c
index aeb3850f81bd..236e11755ba6 100644
--- a/tools/testing/selftests/kvm/x86_64/emulator_error_test.c
+++ b/tools/testing/selftests/kvm/x86_64/emulator_error_test.c
@@ -11,7 +11,6 @@
 #include "kvm_util.h"
 #include "vmx.h"
 
-#define VCPU_ID	   1
 #define MAXPHYADDR 36
 
 #define MEM_REGION_GVA	0x0000123456789000
@@ -27,14 +26,6 @@ static void guest_code(void)
 	GUEST_DONE();
 }
 
-static void run_guest(struct kvm_vm *vm)
-{
-	int rc;
-
-	rc = _vcpu_run(vm, VCPU_ID);
-	TEST_ASSERT(rc == 0, "vcpu_run failed: %d\n", rc);
-}
-
 /*
  * Accessors to get R/M, REG, and Mod bits described in the SDM vol 2,
  * figure 2-2 "Table Interpretation of ModR/M Byte (C8H)".
@@ -56,9 +47,9 @@ static bool is_flds(uint8_t *insn_bytes, uint8_t insn_size)
 	       GET_RM(insn_bytes[1]) != 0x5;
 }
 
-static void process_exit_on_emulation_error(struct kvm_vm *vm)
+static void process_exit_on_emulation_error(struct kvm_vcpu *vcpu)
 {
-	struct kvm_run *run = vcpu_state(vm, VCPU_ID);
+	struct kvm_run *run = vcpu->run;
 	struct kvm_regs regs;
 	uint8_t *insn_bytes;
 	uint8_t insn_size;
@@ -92,50 +83,48 @@ static void process_exit_on_emulation_error(struct kvm_vm *vm)
 			 * contained an flds instruction that is 2-bytes in
 			 * length (ie: no prefix, no SIB, no displacement).
 			 */
-			vcpu_regs_get(vm, VCPU_ID, &regs);
+			vcpu_regs_get(vcpu, &regs);
 			regs.rip += 2;
-			vcpu_regs_set(vm, VCPU_ID, &regs);
+			vcpu_regs_set(vcpu, &regs);
 		}
 	}
 }
 
-static void do_guest_assert(struct kvm_vm *vm, struct ucall *uc)
+static void do_guest_assert(struct ucall *uc)
 {
-	TEST_FAIL("%s at %s:%ld", (const char *)uc->args[0], __FILE__,
-		  uc->args[1]);
+	REPORT_GUEST_ASSERT(*uc);
 }
 
-static void check_for_guest_assert(struct kvm_vm *vm)
+static void check_for_guest_assert(struct kvm_vcpu *vcpu)
 {
-	struct kvm_run *run = vcpu_state(vm, VCPU_ID);
 	struct ucall uc;
 
-	if (run->exit_reason == KVM_EXIT_IO &&
-	    get_ucall(vm, VCPU_ID, &uc) == UCALL_ABORT) {
-		do_guest_assert(vm, &uc);
+	if (vcpu->run->exit_reason == KVM_EXIT_IO &&
+	    get_ucall(vcpu, &uc) == UCALL_ABORT) {
+		do_guest_assert(&uc);
 	}
 }
 
-static void process_ucall_done(struct kvm_vm *vm)
+static void process_ucall_done(struct kvm_vcpu *vcpu)
 {
-	struct kvm_run *run = vcpu_state(vm, VCPU_ID);
+	struct kvm_run *run = vcpu->run;
 	struct ucall uc;
 
-	check_for_guest_assert(vm);
+	check_for_guest_assert(vcpu);
 
 	TEST_ASSERT(run->exit_reason == KVM_EXIT_IO,
 		    "Unexpected exit reason: %u (%s)",
 		    run->exit_reason,
 		    exit_reason_str(run->exit_reason));
 
-	TEST_ASSERT(get_ucall(vm, VCPU_ID, &uc) == UCALL_DONE,
+	TEST_ASSERT(get_ucall(vcpu, &uc) == UCALL_DONE,
 		    "Unexpected ucall command: %lu, expected UCALL_DONE (%d)",
 		    uc.cmd, UCALL_DONE);
 }
 
-static uint64_t process_ucall(struct kvm_vm *vm)
+static uint64_t process_ucall(struct kvm_vcpu *vcpu)
 {
-	struct kvm_run *run = vcpu_state(vm, VCPU_ID);
+	struct kvm_run *run = vcpu->run;
 	struct ucall uc;
 
 	TEST_ASSERT(run->exit_reason == KVM_EXIT_IO,
@@ -143,14 +132,14 @@ static uint64_t process_ucall(struct kvm_vm *vm)
 		    run->exit_reason,
 		    exit_reason_str(run->exit_reason));
 
-	switch (get_ucall(vm, VCPU_ID, &uc)) {
+	switch (get_ucall(vcpu, &uc)) {
 	case UCALL_SYNC:
 		break;
 	case UCALL_ABORT:
-		do_guest_assert(vm, &uc);
+		do_guest_assert(&uc);
 		break;
 	case UCALL_DONE:
-		process_ucall_done(vm);
+		process_ucall_done(vcpu);
 		break;
 	default:
 		TEST_ASSERT(false, "Unexpected ucall");
@@ -161,12 +150,7 @@ static uint64_t process_ucall(struct kvm_vm *vm)
 
 int main(int argc, char *argv[])
 {
-	struct kvm_enable_cap emul_failure_cap = {
-		.cap = KVM_CAP_EXIT_ON_EMULATION_FAILURE,
-		.args[0] = 1,
-	};
-	struct kvm_cpuid_entry2 *entry;
-	struct kvm_cpuid2 *cpuid;
+	struct kvm_vcpu *vcpu;
 	struct kvm_vm *vm;
 	uint64_t gpa, pte;
 	uint64_t *hva;
@@ -175,24 +159,15 @@ int main(int argc, char *argv[])
 	/* Tell stdout not to buffer its content */
 	setbuf(stdout, NULL);
 
-	vm = vm_create_default(VCPU_ID, 0, guest_code);
-
-	if (!kvm_check_cap(KVM_CAP_SMALLER_MAXPHYADDR)) {
-		printf("module parameter 'allow_smaller_maxphyaddr' is not set.  Skipping test.\n");
-		return 0;
-	}
-
-	cpuid = kvm_get_supported_cpuid();
+	TEST_REQUIRE(kvm_has_cap(KVM_CAP_SMALLER_MAXPHYADDR));
 
-	entry = kvm_get_supported_cpuid_index(0x80000008, 0);
-	entry->eax = (entry->eax & 0xffffff00) | MAXPHYADDR;
-	set_cpuid(cpuid, entry);
+	vm = vm_create_with_one_vcpu(&vcpu, guest_code);
 
-	vcpu_set_cpuid(vm, VCPU_ID, cpuid);
+	vcpu_set_cpuid_maxphyaddr(vcpu, MAXPHYADDR);
 
 	rc = kvm_check_cap(KVM_CAP_EXIT_ON_EMULATION_FAILURE);
 	TEST_ASSERT(rc, "KVM_CAP_EXIT_ON_EMULATION_FAILURE is unavailable");
-	vm_enable_cap(vm, &emul_failure_cap);
+	vm_enable_cap(vm, KVM_CAP_EXIT_ON_EMULATION_FAILURE, 1);
 
 	vm_userspace_mem_region_add(vm, VM_MEM_SRC_ANONYMOUS,
 				    MEM_REGION_GPA, MEM_REGION_SLOT,
@@ -203,14 +178,14 @@ int main(int argc, char *argv[])
 	virt_map(vm, MEM_REGION_GVA, MEM_REGION_GPA, 1);
 	hva = addr_gpa2hva(vm, MEM_REGION_GPA);
 	memset(hva, 0, PAGE_SIZE);
-	pte = vm_get_page_table_entry(vm, VCPU_ID, MEM_REGION_GVA);
-	vm_set_page_table_entry(vm, VCPU_ID, MEM_REGION_GVA, pte | (1ull << 36));
+	pte = vm_get_page_table_entry(vm, vcpu, MEM_REGION_GVA);
+	vm_set_page_table_entry(vm, vcpu, MEM_REGION_GVA, pte | (1ull << 36));
 
-	run_guest(vm);
-	process_exit_on_emulation_error(vm);
-	run_guest(vm);
+	vcpu_run(vcpu);
+	process_exit_on_emulation_error(vcpu);
+	vcpu_run(vcpu);
 
-	TEST_ASSERT(process_ucall(vm) == UCALL_DONE, "Expected UCALL_DONE");
+	TEST_ASSERT(process_ucall(vcpu) == UCALL_DONE, "Expected UCALL_DONE");
 
 	kvm_vm_free(vm);