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'
  ...

7 files changed, 15 insertions, 67 deletions

diff --git a/drivers/cpufreq/intel_pstate.c b/drivers/cpufreq/intel_pstate.c
index fcb929ec5304..7898de054f4e 100644
--- a/drivers/cpufreq/intel_pstate.c
+++ b/drivers/cpufreq/intel_pstate.c
@@ -766,7 +766,7 @@ static inline void intel_pstate_sample(struct cpudata *cpu)
 	local_irq_save(flags);
 	rdmsrl(MSR_IA32_APERF, aperf);
 	rdmsrl(MSR_IA32_MPERF, mperf);
-	tsc = native_read_tsc();
+	tsc = rdtsc();
 	local_irq_restore(flags);
 
 	cpu->last_sample_time = cpu->sample.time;
diff --git a/drivers/input/gameport/gameport.c b/drivers/input/gameport/gameport.c
index e853a2134680..4a2a9e370be7 100644
--- a/drivers/input/gameport/gameport.c
+++ b/drivers/input/gameport/gameport.c
@@ -149,9 +149,9 @@ static int old_gameport_measure_speed(struct gameport *gameport)
 
 	for(i = 0; i < 50; i++) {
 		local_irq_save(flags);
-		rdtscl(t1);
+		t1 = rdtsc();
 		for (t = 0; t < 50; t++) gameport_read(gameport);
-		rdtscl(t2);
+		t2 = rdtsc();
 		local_irq_restore(flags);
 		udelay(i * 10);
 		if (t2 - t1 < tx) tx = t2 - t1;
diff --git a/drivers/input/joystick/analog.c b/drivers/input/joystick/analog.c
index 4284080e481d..6f8b084e13d0 100644
--- a/drivers/input/joystick/analog.c
+++ b/drivers/input/joystick/analog.c
@@ -143,7 +143,7 @@ struct analog_port {
 
 #include <linux/i8253.h>
 
-#define GET_TIME(x)	do { if (cpu_has_tsc) rdtscl(x); else x = get_time_pit(); } while (0)
+#define GET_TIME(x)	do { if (cpu_has_tsc) x = (unsigned int)rdtsc(); else x = get_time_pit(); } while (0)
 #define DELTA(x,y)	(cpu_has_tsc ? ((y) - (x)) : ((x) - (y) + ((x) < (y) ? PIT_TICK_RATE / HZ : 0)))
 #define TIME_NAME	(cpu_has_tsc?"TSC":"PIT")
 static unsigned int get_time_pit(void)
@@ -160,7 +160,7 @@ static unsigned int get_time_pit(void)
         return count;
 }
 #elif defined(__x86_64__)
-#define GET_TIME(x)	rdtscl(x)
+#define GET_TIME(x)	do { x = (unsigned int)rdtsc(); } while (0)
 #define DELTA(x,y)	((y)-(x))
 #define TIME_NAME	"TSC"
 #elif defined(__alpha__) || defined(CONFIG_MN10300) || defined(CONFIG_ARM) || defined(CONFIG_ARM64) || defined(CONFIG_TILE)
diff --git a/drivers/net/hamradio/baycom_epp.c b/drivers/net/hamradio/baycom_epp.c
index 83c7cce0d172..72c9f1f352b4 100644
--- a/drivers/net/hamradio/baycom_epp.c
+++ b/drivers/net/hamradio/baycom_epp.c
@@ -638,7 +638,7 @@ static int receive(struct net_device *dev, int cnt)
 #define GETTICK(x)                                                \
 ({                                                                \
 	if (cpu_has_tsc)                                          \
-		rdtscl(x);                                        \
+		x = (unsigned int)rdtsc();		  \
 })
 #else /* __i386__ */
 #define GETTICK(x)
diff --git a/drivers/scsi/dpt_i2o.c b/drivers/scsi/dpt_i2o.c
index f35ed53adaac..d4cda5e9600e 100644
--- a/drivers/scsi/dpt_i2o.c
+++ b/drivers/scsi/dpt_i2o.c
@@ -1924,6 +1924,9 @@ static void adpt_alpha_info(sysInfo_S* si)
 #endif
 
 #if defined __i386__
+
+#include <uapi/asm/vm86.h>
+
 static void adpt_i386_info(sysInfo_S* si)
 {
 	// This is all the info we need for now
diff --git a/drivers/staging/media/lirc/lirc_serial.c b/drivers/staging/media/lirc/lirc_serial.c
index dc7984455c3a..465796a686c4 100644
--- a/drivers/staging/media/lirc/lirc_serial.c
+++ b/drivers/staging/media/lirc/lirc_serial.c
@@ -327,9 +327,6 @@ static void safe_udelay(unsigned long usecs)
  * time
  */
 
-/* So send_pulse can quickly convert microseconds to clocks */
-static unsigned long conv_us_to_clocks;
-
 static int init_timing_params(unsigned int new_duty_cycle,
 		unsigned int new_freq)
 {
@@ -344,7 +341,6 @@ static int init_timing_params(unsigned int new_duty_cycle,
 	/* How many clocks in a microsecond?, avoiding long long divide */
 	work = loops_per_sec;
 	work *= 4295;  /* 4295 = 2^32 / 1e6 */
-	conv_us_to_clocks = work >> 32;
 
 	/*
 	 * Carrier period in clocks, approach good up to 32GHz clock,
@@ -357,10 +353,9 @@ static int init_timing_params(unsigned int new_duty_cycle,
 	pulse_width = period * duty_cycle / 100;
 	space_width = period - pulse_width;
 	dprintk("in init_timing_params, freq=%d, duty_cycle=%d, "
-		"clk/jiffy=%ld, pulse=%ld, space=%ld, "
-		"conv_us_to_clocks=%ld\n",
+		"clk/jiffy=%ld, pulse=%ld, space=%ld\n",
 		freq, duty_cycle, __this_cpu_read(cpu_info.loops_per_jiffy),
-		pulse_width, space_width, conv_us_to_clocks);
+		pulse_width, space_width);
 	return 0;
 }
 #else /* ! USE_RDTSC */
@@ -431,63 +426,14 @@ static long send_pulse_irdeo(unsigned long length)
 	return ret;
 }
 
-#ifdef USE_RDTSC
-/* Version that uses Pentium rdtsc instruction to measure clocks */
-
-/*
- * This version does sub-microsecond timing using rdtsc instruction,
- * and does away with the fudged LIRC_SERIAL_TRANSMITTER_LATENCY
- * Implicitly i586 architecture...  - Steve
- */
-
-static long send_pulse_homebrew_softcarrier(unsigned long length)
-{
-	int flag;
-	unsigned long target, start, now;
-
-	/* Get going quick as we can */
-	rdtscl(start);
-	on();
-	/* Convert length from microseconds to clocks */
-	length *= conv_us_to_clocks;
-	/* And loop till time is up - flipping at right intervals */
-	now = start;
-	target = pulse_width;
-	flag = 1;
-	/*
-	 * FIXME: This looks like a hard busy wait, without even an occasional,
-	 * polite, cpu_relax() call.  There's got to be a better way?
-	 *
-	 * The i2c code has the result of a lot of bit-banging work, I wonder if
-	 * there's something there which could be helpful here.
-	 */
-	while ((now - start) < length) {
-		/* Delay till flip time */
-		do {
-			rdtscl(now);
-		} while ((now - start) < target);
-
-		/* flip */
-		if (flag) {
-			rdtscl(now);
-			off();
-			target += space_width;
-		} else {
-			rdtscl(now); on();
-			target += pulse_width;
-		}
-		flag = !flag;
-	}
-	rdtscl(now);
-	return ((now - start) - length) / conv_us_to_clocks;
-}
-#else /* ! USE_RDTSC */
 /* Version using udelay() */
 
 /*
  * here we use fixed point arithmetic, with 8
  * fractional bits.  that gets us within 0.1% or so of the right average
  * frequency, albeit with some jitter in pulse length - Steve
+ *
+ * This should use ndelay instead.
  */
 
 /* To match 8 fractional bits used for pulse/space length */
@@ -520,7 +466,6 @@ static long send_pulse_homebrew_softcarrier(unsigned long length)
 	}
 	return (actual-length) >> 8;
 }
-#endif /* USE_RDTSC */
 
 static long send_pulse_homebrew(unsigned long length)
 {
diff --git a/drivers/thermal/intel_powerclamp.c b/drivers/thermal/intel_powerclamp.c
index 5820e8513927..2ac0c704bcb8 100644
--- a/drivers/thermal/intel_powerclamp.c
+++ b/drivers/thermal/intel_powerclamp.c
@@ -340,7 +340,7 @@ static bool powerclamp_adjust_controls(unsigned int target_ratio,
 
 	/* check result for the last window */
 	msr_now = pkg_state_counter();
-	rdtscll(tsc_now);
+	tsc_now = rdtsc();
 
 	/* calculate pkg cstate vs tsc ratio */
 	if (!msr_last || !tsc_last)
@@ -482,7 +482,7 @@ static void poll_pkg_cstate(struct work_struct *dummy)
 	u64 val64;
 
 	msr_now = pkg_state_counter();
-	rdtscll(tsc_now);
+	tsc_now = rdtsc();
 	jiffies_now = jiffies;
 
 	/* calculate pkg cstate vs tsc ratio */