Merge branch 'x86-asm-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull x86 asm changes from Ingo Molnar:
 "The biggest changes in this cycle were:

   - Revamp, simplify (and in some cases fix) Time Stamp Counter (TSC)
     primitives.  (Andy Lutomirski)

   - Add new, comprehensible entry and exit handlers written in C.
     (Andy Lutomirski)

   - vm86 mode cleanups and fixes.  (Brian Gerst)

   - 32-bit compat code cleanups.  (Brian Gerst)

  The amount of simplification in low level assembly code is already
  palpable:

     arch/x86/entry/entry_32.S                          | 130 +----
     arch/x86/entry/entry_64.S                          | 197 ++-----

  but more simplifications are planned.

  There's also the usual laudry mix of low level changes - see the
  changelog for details"

* 'x86-asm-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (83 commits)
  x86/asm: Drop repeated macro of X86_EFLAGS_AC definition
  x86/asm/msr: Make wrmsrl() a function
  x86/asm/delay: Introduce an MWAITX-based delay with a configurable timer
  x86/asm: Add MONITORX/MWAITX instruction support
  x86/traps: Weaken context tracking entry assertions
  x86/asm/tsc: Add rdtscll() merge helper
  selftests/x86: Add syscall_nt selftest
  selftests/x86: Disable sigreturn_64
  x86/vdso: Emit a GNU hash
  x86/entry: Remove do_notify_resume(), syscall_trace_leave(), and their TIF masks
  x86/entry/32: Migrate to C exit path
  x86/entry/32: Remove 32-bit syscall audit optimizations
  x86/vm86: Rename vm86->v86flags and v86mask
  x86/vm86: Rename vm86->vm86_info to user_vm86
  x86/vm86: Clean up vm86.h includes
  x86/vm86: Move the vm86 IRQ definitions to vm86.h
  x86/vm86: Use the normal pt_regs area for vm86
  x86/vm86: Eliminate 'struct kernel_vm86_struct'
  x86/vm86: Move fields from 'struct kernel_vm86_struct' to 'struct vm86'
  x86/vm86: Move vm86 fields out of 'thread_struct'
  ...

4 files changed, 13 insertions, 25 deletions

diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c
index 9a3e342..8d9013c 100644
--- a/arch/x86/kvm/lapic.c
+++ b/arch/x86/kvm/lapic.c
@@ -1172,7 +1172,7 @@ void wait_lapic_expire(struct kvm_vcpu *vcpu)
 
 	tsc_deadline = apic->lapic_timer.expired_tscdeadline;
 	apic->lapic_timer.expired_tscdeadline = 0;
-	guest_tsc = kvm_x86_ops->read_l1_tsc(vcpu, native_read_tsc());
+	guest_tsc = kvm_x86_ops->read_l1_tsc(vcpu, rdtsc());
 	trace_kvm_wait_lapic_expire(vcpu->vcpu_id, guest_tsc - tsc_deadline);
 
 	/* __delay is delay_tsc whenever the hardware has TSC, thus always.  */
@@ -1240,7 +1240,7 @@ static void start_apic_timer(struct kvm_lapic *apic)
 		local_irq_save(flags);
 
 		now = apic->lapic_timer.timer.base->get_time();
-		guest_tsc = kvm_x86_ops->read_l1_tsc(vcpu, native_read_tsc());
+		guest_tsc = kvm_x86_ops->read_l1_tsc(vcpu, rdtsc());
 		if (likely(tscdeadline > guest_tsc)) {
 			ns = (tscdeadline - guest_tsc) * 1000000ULL;
 			do_div(ns, this_tsc_khz);
diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c
index 74d8257..fdb8cb6 100644
--- a/arch/x86/kvm/svm.c
+++ b/arch/x86/kvm/svm.c
@@ -1139,7 +1139,7 @@ static u64 svm_compute_tsc_offset(struct kvm_vcpu *vcpu, u64 target_tsc)
 {
 	u64 tsc;
 
-	tsc = svm_scale_tsc(vcpu, native_read_tsc());
+	tsc = svm_scale_tsc(vcpu, rdtsc());
 
 	return target_tsc - tsc;
 }
@@ -3174,7 +3174,7 @@ static int svm_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 	switch (msr_info->index) {
 	case MSR_IA32_TSC: {
 		msr_info->data = svm->vmcb->control.tsc_offset +
-			svm_scale_tsc(vcpu, native_read_tsc());
+			svm_scale_tsc(vcpu, rdtsc());
 
 		break;
 	}
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index da1590e..4a4eec30 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -2236,7 +2236,7 @@ static u64 guest_read_tsc(void)
 {
 	u64 host_tsc, tsc_offset;
 
-	rdtscll(host_tsc);
+	host_tsc = rdtsc();
 	tsc_offset = vmcs_read64(TSC_OFFSET);
 	return host_tsc + tsc_offset;
 }
@@ -2317,7 +2317,7 @@ static void vmx_adjust_tsc_offset(struct kvm_vcpu *vcpu, s64 adjustment, bool ho
 
 static u64 vmx_compute_tsc_offset(struct kvm_vcpu *vcpu, u64 target_tsc)
 {
-	return target_tsc - native_read_tsc();
+	return target_tsc - rdtsc();
 }
 
 static bool guest_cpuid_has_vmx(struct kvm_vcpu *vcpu)
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 4bbc2a1..1e7e76e 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -1441,20 +1441,8 @@ EXPORT_SYMBOL_GPL(kvm_write_tsc);
 
 static cycle_t read_tsc(void)
 {
-	cycle_t ret;
-	u64 last;
-
-	/*
-	 * Empirically, a fence (of type that depends on the CPU)
-	 * before rdtsc is enough to ensure that rdtsc is ordered
-	 * with respect to loads.  The various CPU manuals are unclear
-	 * as to whether rdtsc can be reordered with later loads,
-	 * but no one has ever seen it happen.
-	 */
-	rdtsc_barrier();
-	ret = (cycle_t)vget_cycles();
-
-	last = pvclock_gtod_data.clock.cycle_last;
+	cycle_t ret = (cycle_t)rdtsc_ordered();
+	u64 last = pvclock_gtod_data.clock.cycle_last;
 
 	if (likely(ret >= last))
 		return ret;
@@ -1643,7 +1631,7 @@ static int kvm_guest_time_update(struct kvm_vcpu *v)
 		return 1;
 	}
 	if (!use_master_clock) {
-		host_tsc = native_read_tsc();
+		host_tsc = rdtsc();
 		kernel_ns = get_kernel_ns();
 	}
 
@@ -2620,7 +2608,7 @@ void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
 
 	if (unlikely(vcpu->cpu != cpu) || check_tsc_unstable()) {
 		s64 tsc_delta = !vcpu->arch.last_host_tsc ? 0 :
-				native_read_tsc() - vcpu->arch.last_host_tsc;
+				rdtsc() - vcpu->arch.last_host_tsc;
 		if (tsc_delta < 0)
 			mark_tsc_unstable("KVM discovered backwards TSC");
 		if (check_tsc_unstable()) {
@@ -2648,7 +2636,7 @@ void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu)
 {
 	kvm_x86_ops->vcpu_put(vcpu);
 	kvm_put_guest_fpu(vcpu);
-	vcpu->arch.last_host_tsc = native_read_tsc();
+	vcpu->arch.last_host_tsc = rdtsc();
 }
 
 static int kvm_vcpu_ioctl_get_lapic(struct kvm_vcpu *vcpu,
@@ -6387,7 +6375,7 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu)
 		hw_breakpoint_restore();
 
 	vcpu->arch.last_guest_tsc = kvm_x86_ops->read_l1_tsc(vcpu,
-							   native_read_tsc());
+							   rdtsc());
 
 	vcpu->mode = OUTSIDE_GUEST_MODE;
 	smp_wmb();
@@ -7196,7 +7184,7 @@ int kvm_arch_hardware_enable(void)
 	if (ret != 0)
 		return ret;
 
-	local_tsc = native_read_tsc();
+	local_tsc = rdtsc();
 	stable = !check_tsc_unstable();
 	list_for_each_entry(kvm, &vm_list, vm_list) {
 		kvm_for_each_vcpu(i, vcpu, kvm) {