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

Pull kvm fixes from Paolo Bonzini:

 - Lots of bug fixes.

 - Fix virtualization of RDPID

 - Virtualization of DR6_BUS_LOCK, which on bare metal is new to this
   release

 - More nested virtualization migration fixes (nSVM and eVMCS)

 - Fix for KVM guest hibernation

 - Fix for warning in SEV-ES SRCU usage

 - Block KVM from loading on AMD machines with 5-level page tables, due
   to the APM not mentioning how host CR4.LA57 exactly impacts the
   guest.

* tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm: (48 commits)
  KVM: SVM: Move GHCB unmapping to fix RCU warning
  KVM: SVM: Invert user pointer casting in SEV {en,de}crypt helpers
  kvm: Cap halt polling at kvm->max_halt_poll_ns
  tools/kvm_stat: Fix documentation typo
  KVM: x86: Prevent deadlock against tk_core.seq
  KVM: x86: Cancel pvclock_gtod_work on module removal
  KVM: x86: Prevent KVM SVM from loading on kernels with 5-level paging
  KVM: X86: Expose bus lock debug exception to guest
  KVM: X86: Add support for the emulation of DR6_BUS_LOCK bit
  KVM: PPC: Book3S HV: Fix conversion to gfn-based MMU notifier callbacks
  KVM: x86: Hide RDTSCP and RDPID if MSR_TSC_AUX probing failed
  KVM: x86: Tie Intel and AMD behavior for MSR_TSC_AUX to guest CPU model
  KVM: x86: Move uret MSR slot management to common x86
  KVM: x86: Export the number of uret MSRs to vendor modules
  KVM: VMX: Disable loading of TSX_CTRL MSR the more conventional way
  KVM: VMX: Use common x86's uret MSR list as the one true list
  KVM: VMX: Use flag to indicate "active" uret MSRs instead of sorting list
  KVM: VMX: Configure list of user return MSRs at module init
  KVM: x86: Add support for RDPID without RDTSCP
  KVM: SVM: Probe and load MSR_TSC_AUX regardless of RDTSCP support in host
  ...

2 files changed, 72 insertions, 20 deletions

diff --git a/tools/testing/selftests/kvm/lib/x86_64/handlers.S b/tools/testing/selftests/kvm/lib/x86_64/handlers.S
index aaf7bc7d2ce1..7629819734af 100644
--- a/tools/testing/selftests/kvm/lib/x86_64/handlers.S
+++ b/tools/testing/selftests/kvm/lib/x86_64/handlers.S
@@ -54,9 +54,9 @@ idt_handlers:
 	.align 8
 
 	/* Fetch current address and append it to idt_handlers. */
-	current_handler = .
+666 :
 .pushsection .rodata
-.quad current_handler
+	.quad 666b
 .popsection
 
 	.if ! \has_error
diff --git a/tools/testing/selftests/kvm/x86_64/evmcs_test.c b/tools/testing/selftests/kvm/x86_64/evmcs_test.c
index ca22ee6d19cb..63096cea26c6 100644
--- a/tools/testing/selftests/kvm/x86_64/evmcs_test.c
+++ b/tools/testing/selftests/kvm/x86_64/evmcs_test.c
@@ -18,6 +18,28 @@
 #include "vmx.h"
 
 #define VCPU_ID		5
+#define NMI_VECTOR	2
+
+static int ud_count;
+
+void enable_x2apic(void)
+{
+	uint32_t spiv_reg = APIC_BASE_MSR + (APIC_SPIV >> 4);
+
+	wrmsr(MSR_IA32_APICBASE, rdmsr(MSR_IA32_APICBASE) |
+	      MSR_IA32_APICBASE_ENABLE | MSR_IA32_APICBASE_EXTD);
+	wrmsr(spiv_reg, rdmsr(spiv_reg) | APIC_SPIV_APIC_ENABLED);
+}
+
+static void guest_ud_handler(struct ex_regs *regs)
+{
+	ud_count++;
+	regs->rip += 3; /* VMLAUNCH */
+}
+
+static void guest_nmi_handler(struct ex_regs *regs)
+{
+}
 
 void l2_guest_code(void)
 {
@@ -25,15 +47,23 @@ void l2_guest_code(void)
 
 	GUEST_SYNC(8);
 
+	/* Forced exit to L1 upon restore */
+	GUEST_SYNC(9);
+
 	/* Done, exit to L1 and never come back.  */
 	vmcall();
 }
 
-void l1_guest_code(struct vmx_pages *vmx_pages)
+void guest_code(struct vmx_pages *vmx_pages)
 {
 #define L2_GUEST_STACK_SIZE 64
 	unsigned long l2_guest_stack[L2_GUEST_STACK_SIZE];
 
+	enable_x2apic();
+
+	GUEST_SYNC(1);
+	GUEST_SYNC(2);
+
 	enable_vp_assist(vmx_pages->vp_assist_gpa, vmx_pages->vp_assist);
 
 	GUEST_ASSERT(vmx_pages->vmcs_gpa);
@@ -55,27 +85,40 @@ void l1_guest_code(struct vmx_pages *vmx_pages)
 	current_evmcs->revision_id = EVMCS_VERSION;
 	GUEST_SYNC(6);
 
+	current_evmcs->pin_based_vm_exec_control |=
+		PIN_BASED_NMI_EXITING;
 	GUEST_ASSERT(!vmlaunch());
 	GUEST_ASSERT(vmptrstz() == vmx_pages->enlightened_vmcs_gpa);
-	GUEST_SYNC(9);
+
+	/*
+	 * NMI forces L2->L1 exit, resuming L2 and hope that EVMCS is
+	 * up-to-date (RIP points where it should and not at the beginning
+	 * of l2_guest_code(). GUEST_SYNC(9) checkes that.
+	 */
 	GUEST_ASSERT(!vmresume());
-	GUEST_ASSERT(vmreadz(VM_EXIT_REASON) == EXIT_REASON_VMCALL);
+
 	GUEST_SYNC(10);
+
+	GUEST_ASSERT(vmreadz(VM_EXIT_REASON) == EXIT_REASON_VMCALL);
+	GUEST_SYNC(11);
+
+	/* Try enlightened vmptrld with an incorrect GPA */
+	evmcs_vmptrld(0xdeadbeef, vmx_pages->enlightened_vmcs);
+	GUEST_ASSERT(vmlaunch());
+	GUEST_ASSERT(ud_count == 1);
+	GUEST_DONE();
 }
 
-void guest_code(struct vmx_pages *vmx_pages)
+void inject_nmi(struct kvm_vm *vm)
 {
-	GUEST_SYNC(1);
-	GUEST_SYNC(2);
+	struct kvm_vcpu_events events;
 
-	if (vmx_pages)
-		l1_guest_code(vmx_pages);
+	vcpu_events_get(vm, VCPU_ID, &events);
 
-	GUEST_DONE();
+	events.nmi.pending = 1;
+	events.flags |= KVM_VCPUEVENT_VALID_NMI_PENDING;
 
-	/* Try enlightened vmptrld with an incorrect GPA */
-	evmcs_vmptrld(0xdeadbeef, vmx_pages->enlightened_vmcs);
-	GUEST_ASSERT(vmlaunch());
+	vcpu_events_set(vm, VCPU_ID, &events);
 }
 
 int main(int argc, char *argv[])
@@ -109,6 +152,13 @@ int main(int argc, char *argv[])
 	vcpu_alloc_vmx(vm, &vmx_pages_gva);
 	vcpu_args_set(vm, VCPU_ID, 1, vmx_pages_gva);
 
+	vm_init_descriptor_tables(vm);
+	vcpu_init_descriptor_tables(vm, VCPU_ID);
+	vm_handle_exception(vm, UD_VECTOR, guest_ud_handler);
+	vm_handle_exception(vm, NMI_VECTOR, guest_nmi_handler);
+
+	pr_info("Running L1 which uses EVMCS to run L2\n");
+
 	for (stage = 1;; stage++) {
 		_vcpu_run(vm, VCPU_ID);
 		TEST_ASSERT(run->exit_reason == KVM_EXIT_IO,
@@ -124,7 +174,7 @@ int main(int argc, char *argv[])
 		case UCALL_SYNC:
 			break;
 		case UCALL_DONE:
-			goto part1_done;
+			goto done;
 		default:
 			TEST_FAIL("Unknown ucall %lu", uc.cmd);
 		}
@@ -154,12 +204,14 @@ int main(int argc, char *argv[])
 		TEST_ASSERT(!memcmp(&regs1, &regs2, sizeof(regs2)),
 			    "Unexpected register values after vcpu_load_state; rdi: %lx rsi: %lx",
 			    (ulong) regs2.rdi, (ulong) regs2.rsi);
-	}
 
-part1_done:
-	_vcpu_run(vm, VCPU_ID);
-	TEST_ASSERT(run->exit_reason == KVM_EXIT_SHUTDOWN,
-		    "Unexpected successful VMEnter with invalid eVMCS pointer!");
+		/* Force immediate L2->L1 exit before resuming */
+		if (stage == 8) {
+			pr_info("Injecting NMI into L1 before L2 had a chance to run after restore\n");
+			inject_nmi(vm);
+		}
+	}
 
+done:
 	kvm_vm_free(vm);
 }