Merge tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm

Pull KVM updates from Paolo Bonzini:
 "ARM:

   - More progress on the protected VM front, now with the full fixed
     feature set as well as the limitation of some hypercalls after
     initialisation.

   - Cleanup of the RAZ/WI sysreg handling, which was pointlessly
     complicated

   - Fixes for the vgic placement in the IPA space, together with a
     bunch of selftests

   - More memcg accounting of the memory allocated on behalf of a guest

   - Timer and vgic selftests

   - Workarounds for the Apple M1 broken vgic implementation

   - KConfig cleanups

   - New kvmarm.mode=none option, for those who really dislike us

  RISC-V:

   - New KVM port.

  x86:

   - New API to control TSC offset from userspace

   - TSC scaling for nested hypervisors on SVM

   - Switch masterclock protection from raw_spin_lock to seqcount

   - Clean up function prototypes in the page fault code and avoid
     repeated memslot lookups

   - Convey the exit reason to userspace on emulation failure

   - Configure time between NX page recovery iterations

   - Expose Predictive Store Forwarding Disable CPUID leaf

   - Allocate page tracking data structures lazily (if the i915 KVM-GT
     functionality is not compiled in)

   - Cleanups, fixes and optimizations for the shadow MMU code

  s390:

   - SIGP Fixes

   - initial preparations for lazy destroy of secure VMs

   - storage key improvements/fixes

   - Log the guest CPNC

  Starting from this release, KVM-PPC patches will come from Michael
  Ellerman's PPC tree"

* tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm: (227 commits)
  RISC-V: KVM: fix boolreturn.cocci warnings
  RISC-V: KVM: remove unneeded semicolon
  RISC-V: KVM: Fix GPA passed to __kvm_riscv_hfence_gvma_xyz() functions
  RISC-V: KVM: Factor-out FP virtualization into separate sources
  KVM: s390: add debug statement for diag 318 CPNC data
  KVM: s390: pv: properly handle page flags for protected guests
  KVM: s390: Fix handle_sske page fault handling
  KVM: x86: SGX must obey the KVM_INTERNAL_ERROR_EMULATION protocol
  KVM: x86: On emulation failure, convey the exit reason, etc. to userspace
  KVM: x86: Get exit_reason as part of kvm_x86_ops.get_exit_info
  KVM: x86: Clarify the kvm_run.emulation_failure structure layout
  KVM: s390: Add a routine for setting userspace CPU state
  KVM: s390: Simplify SIGP Set Arch handling
  KVM: s390: pv: avoid stalls when making pages secure
  KVM: s390: pv: avoid stalls for kvm_s390_pv_init_vm
  KVM: s390: pv: avoid double free of sida page
  KVM: s390: pv: add macros for UVC CC values
  s390/mm: optimize reset_guest_reference_bit()
  s390/mm: optimize set_guest_storage_key()
  s390/mm: no need for pte_alloc_map_lock() if we know the pmd is present
  ...

1 files changed, 132 insertions, 0 deletions

diff --git a/tools/testing/selftests/kvm/system_counter_offset_test.c b/tools/testing/selftests/kvm/system_counter_offset_test.c
new file mode 100644
index 000000000000..b337bbbfa41f
--- /dev/null
+++ b/tools/testing/selftests/kvm/system_counter_offset_test.c
@@ -0,0 +1,132 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2021, Google LLC.
+ *
+ * Tests for adjusting the system counter from userspace
+ */
+#include <asm/kvm_para.h>
+#include <stdint.h>
+#include <string.h>
+#include <sys/stat.h>
+#include <time.h>
+
+#include "test_util.h"
+#include "kvm_util.h"
+#include "processor.h"
+
+#define VCPU_ID 0
+
+#ifdef __x86_64__
+
+struct test_case {
+	uint64_t tsc_offset;
+};
+
+static struct test_case test_cases[] = {
+	{ 0 },
+	{ 180 * NSEC_PER_SEC },
+	{ -180 * NSEC_PER_SEC },
+};
+
+static void check_preconditions(struct kvm_vm *vm)
+{
+	if (!_vcpu_has_device_attr(vm, VCPU_ID, KVM_VCPU_TSC_CTRL, KVM_VCPU_TSC_OFFSET))
+		return;
+
+	print_skip("KVM_VCPU_TSC_OFFSET not supported; skipping test");
+	exit(KSFT_SKIP);
+}
+
+static void setup_system_counter(struct kvm_vm *vm, struct test_case *test)
+{
+	vcpu_access_device_attr(vm, VCPU_ID, KVM_VCPU_TSC_CTRL,
+				KVM_VCPU_TSC_OFFSET, &test->tsc_offset, true);
+}
+
+static uint64_t guest_read_system_counter(struct test_case *test)
+{
+	return rdtsc();
+}
+
+static uint64_t host_read_guest_system_counter(struct test_case *test)
+{
+	return rdtsc() + test->tsc_offset;
+}
+
+#else /* __x86_64__ */
+
+#error test not implemented for this architecture!
+
+#endif
+
+#define GUEST_SYNC_CLOCK(__stage, __val)			\
+		GUEST_SYNC_ARGS(__stage, __val, 0, 0, 0)
+
+static void guest_main(void)
+{
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(test_cases); i++) {
+		struct test_case *test = &test_cases[i];
+
+		GUEST_SYNC_CLOCK(i, guest_read_system_counter(test));
+	}
+}
+
+static void handle_sync(struct ucall *uc, uint64_t start, uint64_t end)
+{
+	uint64_t obs = uc->args[2];
+
+	TEST_ASSERT(start <= obs && obs <= end,
+		    "unexpected system counter value: %"PRIu64" expected range: [%"PRIu64", %"PRIu64"]",
+		    obs, start, end);
+
+	pr_info("system counter value: %"PRIu64" expected range [%"PRIu64", %"PRIu64"]\n",
+		obs, start, end);
+}
+
+static void handle_abort(struct ucall *uc)
+{
+	TEST_FAIL("%s at %s:%ld", (const char *)uc->args[0],
+		  __FILE__, uc->args[1]);
+}
+
+static void enter_guest(struct kvm_vm *vm)
+{
+	uint64_t start, end;
+	struct ucall uc;
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(test_cases); i++) {
+		struct test_case *test = &test_cases[i];
+
+		setup_system_counter(vm, test);
+		start = host_read_guest_system_counter(test);
+		vcpu_run(vm, VCPU_ID);
+		end = host_read_guest_system_counter(test);
+
+		switch (get_ucall(vm, VCPU_ID, &uc)) {
+		case UCALL_SYNC:
+			handle_sync(&uc, start, end);
+			break;
+		case UCALL_ABORT:
+			handle_abort(&uc);
+			return;
+		default:
+			TEST_ASSERT(0, "unhandled ucall %ld\n",
+				    get_ucall(vm, VCPU_ID, &uc));
+		}
+	}
+}
+
+int main(void)
+{
+	struct kvm_vm *vm;
+
+	vm = vm_create_default(VCPU_ID, 0, guest_main);
+	check_preconditions(vm);
+	ucall_init(vm, NULL);
+
+	enter_guest(vm);
+	kvm_vm_free(vm);
+}