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'
  ...

arch/x86/kernel/cpu/amd.c

@@ -11,6 +11,7 @@
 #include <asm/cpu.h>
 #include <asm/smp.h>
 #include <asm/pci-direct.h>
+#include <asm/delay.h>
 
 #ifdef CONFIG_X86_64
 # include <asm/mmconfig.h>
@@ -114,7 +115,7 @@ static void init_amd_k6(struct cpuinfo_x86 *c)
 		const int K6_BUG_LOOP = 1000000;
 		int n;
 		void (*f_vide)(void);
-		unsigned long d, d2;
+		u64 d, d2;
 
 		printk(KERN_INFO "AMD K6 stepping B detected - ");
 
@@ -125,10 +126,10 @@ static void init_amd_k6(struct cpuinfo_x86 *c)
 
 		n = K6_BUG_LOOP;
 		f_vide = vide;
-		rdtscl(d);
+		d = rdtsc();
 		while (n--)
 			f_vide();
-		rdtscl(d2);
+		d2 = rdtsc();
 		d = d2-d;
 
 		if (d > 20*K6_BUG_LOOP)
@@ -506,6 +507,9 @@ static void bsp_init_amd(struct cpuinfo_x86 *c)
 		/* A random value per boot for bit slice [12:upper_bit) */
 		va_align.bits = get_random_int() & va_align.mask;
 	}
+
+	if (cpu_has(c, X86_FEATURE_MWAITX))
+		use_mwaitx_delay();
 }
 
 static void early_init_amd(struct cpuinfo_x86 *c)

arch/x86/kernel/cpu/common.c

@@ -1185,10 +1185,10 @@ void syscall_init(void)
 	 * set CS/DS but only a 32bit target. LSTAR sets the 64bit rip.
 	 */
 	wrmsrl(MSR_STAR,  ((u64)__USER32_CS)<<48  | ((u64)__KERNEL_CS)<<32);
-	wrmsrl(MSR_LSTAR, entry_SYSCALL_64);
+	wrmsrl(MSR_LSTAR, (unsigned long)entry_SYSCALL_64);
 
 #ifdef CONFIG_IA32_EMULATION
-	wrmsrl(MSR_CSTAR, entry_SYSCALL_compat);
+	wrmsrl(MSR_CSTAR, (unsigned long)entry_SYSCALL_compat);
 	/*
 	 * This only works on Intel CPUs.
 	 * On AMD CPUs these MSRs are 32-bit, CPU truncates MSR_IA32_SYSENTER_EIP.
@@ -1199,7 +1199,7 @@ void syscall_init(void)
 	wrmsrl_safe(MSR_IA32_SYSENTER_ESP, 0ULL);
 	wrmsrl_safe(MSR_IA32_SYSENTER_EIP, (u64)entry_SYSENTER_compat);
 #else
-	wrmsrl(MSR_CSTAR, ignore_sysret);
+	wrmsrl(MSR_CSTAR, (unsigned long)ignore_sysret);
 	wrmsrl_safe(MSR_IA32_SYSENTER_CS, (u64)GDT_ENTRY_INVALID_SEG);
 	wrmsrl_safe(MSR_IA32_SYSENTER_ESP, 0ULL);
 	wrmsrl_safe(MSR_IA32_SYSENTER_EIP, 0ULL);

arch/x86/kernel/cpu/mcheck/mce.c

@@ -127,7 +127,7 @@ void mce_setup(struct mce *m)
 {
 	memset(m, 0, sizeof(struct mce));
 	m->cpu = m->extcpu = smp_processor_id();
-	rdtscll(m->tsc);
+	m->tsc = rdtsc();
 	/* We hope get_seconds stays lockless */
 	m->time = get_seconds();
 	m->cpuvendor = boot_cpu_data.x86_vendor;
@@ -974,7 +974,6 @@ void do_machine_check(struct pt_regs *regs, long error_code)
 {
 	struct mca_config *cfg = &mca_cfg;
 	struct mce m, *final;
-	enum ctx_state prev_state;
 	int i;
 	int worst = 0;
 	int severity;
@@ -1000,7 +999,7 @@ void do_machine_check(struct pt_regs *regs, long error_code)
 	int flags = MF_ACTION_REQUIRED;
 	int lmce = 0;
 
-	prev_state = ist_enter(regs);
+	ist_enter(regs);
 
 	this_cpu_inc(mce_exception_count);
 
@@ -1166,7 +1165,7 @@ out:
 	local_irq_disable();
 	ist_end_non_atomic();
 done:
-	ist_exit(regs, prev_state);
+	ist_exit(regs);
 }
 EXPORT_SYMBOL_GPL(do_machine_check);
 
@@ -1754,7 +1753,7 @@ static void collect_tscs(void *data)
 {
 	unsigned long *cpu_tsc = (unsigned long *)data;
 
-	rdtscll(cpu_tsc[smp_processor_id()]);
+	cpu_tsc[smp_processor_id()] = rdtsc();
 }
 
 static int mce_apei_read_done;

arch/x86/kernel/cpu/mcheck/p5.c

@@ -19,10 +19,9 @@ int mce_p5_enabled __read_mostly;
 /* Machine check handler for Pentium class Intel CPUs: */
 static void pentium_machine_check(struct pt_regs *regs, long error_code)
 {
-	enum ctx_state prev_state;
 	u32 loaddr, hi, lotype;
 
-	prev_state = ist_enter(regs);
+	ist_enter(regs);
 
 	rdmsr(MSR_IA32_P5_MC_ADDR, loaddr, hi);
 	rdmsr(MSR_IA32_P5_MC_TYPE, lotype, hi);
@@ -39,7 +38,7 @@ static void pentium_machine_check(struct pt_regs *regs, long error_code)
 
 	add_taint(TAINT_MACHINE_CHECK, LOCKDEP_NOW_UNRELIABLE);
 
-	ist_exit(regs, prev_state);
+	ist_exit(regs);
 }
 
 /* Set up machine check reporting for processors with Intel style MCE: */

arch/x86/kernel/cpu/mcheck/winchip.c

@@ -15,12 +15,12 @@
 /* Machine check handler for WinChip C6: */
 static void winchip_machine_check(struct pt_regs *regs, long error_code)
 {
-	enum ctx_state prev_state = ist_enter(regs);
+	ist_enter(regs);
 
 	printk(KERN_EMERG "CPU0: Machine Check Exception.\n");
 	add_taint(TAINT_MACHINE_CHECK, LOCKDEP_NOW_UNRELIABLE);
 
-	ist_exit(regs, prev_state);
+	ist_exit(regs);
 }
 
 /* Set up machine check reporting on the Winchip C6 series */

arch/x86/kernel/cpu/perf_event.c

@@ -2179,6 +2179,7 @@ static unsigned long get_segment_base(unsigned int segment)
 	int idx = segment >> 3;
 
 	if ((segment & SEGMENT_TI_MASK) == SEGMENT_LDT) {
+#ifdef CONFIG_MODIFY_LDT_SYSCALL
 		struct ldt_struct *ldt;
 
 		if (idx > LDT_ENTRIES)
@@ -2190,6 +2191,9 @@ static unsigned long get_segment_base(unsigned int segment)
 			return 0;
 
 		desc = &ldt->entries[idx];
+#else
+		return 0;
+#endif
 	} else {
 		if (idx > GDT_ENTRIES)
 			return 0;
@@ -2200,7 +2204,7 @@ static unsigned long get_segment_base(unsigned int segment)
 	return get_desc_base(desc);
 }
 
-#ifdef CONFIG_COMPAT
+#ifdef CONFIG_IA32_EMULATION
 
 #include <asm/compat.h>