[PATCH] x86_64: On Intel CPUs don't do an additional CPU sync before RDTSC

RDTSC serialization using cpuid is not needed for Intel platforms.
This increases gettimeofday performance.

Cc: vojtech@suse.cz
Cc: rohit.seth@intel.com

Signed-off-by: Andi Kleen <ak@suse.de>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>

5 files changed, 26 insertions, 21 deletions

diff --git a/arch/x86_64/kernel/setup.c b/arch/x86_64/kernel/setup.c
index 8090a0a4688271..46bf556efc301c 100644
--- a/arch/x86_64/kernel/setup.c
+++ b/arch/x86_64/kernel/setup.c
@@ -1042,6 +1042,7 @@ static void __cpuinit init_intel(struct cpuinfo_x86 *c)
 	if ((c->x86 == 0xf && c->x86_model >= 0x03) ||
 	    (c->x86 == 0x6 && c->x86_model >= 0x0e))
 		set_bit(X86_FEATURE_CONSTANT_TSC, &c->x86_capability);
+	set_bit(X86_FEATURE_SYNC_RDTSC, &c->x86_capability);
  	c->x86_max_cores = intel_num_cpu_cores(c);
 
 	srat_detect_node();
diff --git a/arch/x86_64/kernel/time.c b/arch/x86_64/kernel/time.c
index f8d4b69388d2c3..25bc58aac2a52c 100644
--- a/arch/x86_64/kernel/time.c
+++ b/arch/x86_64/kernel/time.c
@@ -71,14 +71,6 @@ unsigned long __wall_jiffies __section_wall_jiffies = INITIAL_JIFFIES;
 struct timespec __xtime __section_xtime;
 struct timezone __sys_tz __section_sys_tz;
 
-static inline void rdtscll_sync(unsigned long *tsc)
-{
-#ifdef CONFIG_SMP
-	sync_core();
-#endif
-	rdtscll(*tsc);
-}
-
 /*
  * do_gettimeoffset() returns microseconds since last timer interrupt was
  * triggered by hardware. A memory read of HPET is slower than a register read
@@ -93,7 +85,7 @@ static inline unsigned int do_gettimeoffset_tsc(void)
 {
 	unsigned long t;
 	unsigned long x;
-	rdtscll_sync(&t);
+	t = get_cycles_sync();
 	if (t < vxtime.last_tsc) t = vxtime.last_tsc; /* hack */
 	x = ((t - vxtime.last_tsc) * vxtime.tsc_quot) >> 32;
 	return x;
@@ -309,8 +301,7 @@ unsigned long long monotonic_clock(void)
 			last_offset = vxtime.last_tsc;
 			base = monotonic_base;
 		} while (read_seqretry(&xtime_lock, seq));
-		sync_core();
-		rdtscll(this_offset);
+		this_offset = get_cycles_sync();
 		offset = (this_offset - last_offset)*1000/cpu_khz; 
 		return base + offset;
 	}
@@ -391,7 +382,7 @@ static irqreturn_t timer_interrupt(int irq, void *dev_id, struct pt_regs *regs)
 		delay = LATCH - 1 - delay;
 	}
 
-	rdtscll_sync(&tsc);
+	tsc = get_cycles_sync();
 
 	if (vxtime.mode == VXTIME_HPET) {
 		if (offset - vxtime.last > hpet_tick) {
@@ -700,8 +691,7 @@ static unsigned int __init hpet_calibrate_tsc(void)
 	do {
 		local_irq_disable();
 		hpet_now = hpet_readl(HPET_COUNTER);
-		sync_core();
-		rdtscl(tsc_now);
+		tsc_now = get_cycles_sync();
 		local_irq_restore(flags);
 	} while ((tsc_now - tsc_start) < TICK_COUNT &&
 		 (hpet_now - hpet_start) < TICK_COUNT);
@@ -731,11 +721,9 @@ static unsigned int __init pit_calibrate_tsc(void)
 	outb(0xb0, 0x43);
 	outb((PIT_TICK_RATE / (1000 / 50)) & 0xff, 0x42);
 	outb((PIT_TICK_RATE / (1000 / 50)) >> 8, 0x42);
-	rdtscll(start);
-	sync_core();
+	start = get_cycles_sync();
 	while ((inb(0x61) & 0x20) == 0);
-	sync_core();
-	rdtscll(end);
+	end = get_cycles_sync();
 
 	spin_unlock_irqrestore(&i8253_lock, flags);
 	
@@ -939,7 +927,7 @@ void __init time_init(void)
 	vxtime.mode = VXTIME_TSC;
 	vxtime.quot = (1000000L << 32) / vxtime_hz;
 	vxtime.tsc_quot = (1000L << 32) / cpu_khz;
-	rdtscll_sync(&vxtime.last_tsc);
+	vxtime.last_tsc = get_cycles_sync();
 	setup_irq(0, &irq0);
 
 	set_cyc2ns_scale(cpu_khz);
diff --git a/arch/x86_64/kernel/vsyscall.c b/arch/x86_64/kernel/vsyscall.c
index 70a0bd16085fbd..9e51047fc410ac 100644
--- a/arch/x86_64/kernel/vsyscall.c
+++ b/arch/x86_64/kernel/vsyscall.c
@@ -66,8 +66,7 @@ static force_inline void do_vgettimeofday(struct timeval * tv)
 			(__jiffies - __wall_jiffies) * (1000000 / HZ);
 
 		if (__vxtime.mode != VXTIME_HPET) {
-			sync_core();
-			rdtscll(t);
+			t = get_cycles_sync();
 			if (t < __vxtime.last_tsc)
 				t = __vxtime.last_tsc;
 			usec += ((t - __vxtime.last_tsc) *
diff --git a/include/asm-x86_64/cpufeature.h b/include/asm-x86_64/cpufeature.h
index aea308c6570942..72b39f5147985a 100644
--- a/include/asm-x86_64/cpufeature.h
+++ b/include/asm-x86_64/cpufeature.h
@@ -63,6 +63,7 @@
 #define X86_FEATURE_CENTAUR_MCR	(3*32+ 3) /* Centaur MCRs (= MTRRs) */
 #define X86_FEATURE_K8_C	(3*32+ 4) /* C stepping K8 */
 #define X86_FEATURE_CONSTANT_TSC (3*32+5) /* TSC runs at constant rate */
+#define X86_FEATURE_SYNC_RDTSC  (3*32+6)  /* RDTSC syncs CPU core */
 
 /* Intel-defined CPU features, CPUID level 0x00000001 (ecx), word 4 */
 #define X86_FEATURE_XMM3	(4*32+ 0) /* Streaming SIMD Extensions-3 */
diff --git a/include/asm-x86_64/timex.h b/include/asm-x86_64/timex.h
index f971f45d6d78b6..f18443fcdf04c9 100644
--- a/include/asm-x86_64/timex.h
+++ b/include/asm-x86_64/timex.h
@@ -10,6 +10,9 @@
 #include <asm/msr.h>
 #include <asm/vsyscall.h>
 #include <asm/hpet.h>
+#include <asm/system.h>
+#include <asm/processor.h>
+#include <linux/compiler.h>
 
 #define CLOCK_TICK_RATE	PIT_TICK_RATE	/* Underlying HZ */
 
@@ -23,6 +26,19 @@ static inline cycles_t get_cycles (void)
 	return ret;
 }
 
+/* Like get_cycles, but make sure the CPU is synchronized. */
+static __always_inline cycles_t get_cycles_sync(void)
+{
+	unsigned long long ret;
+	unsigned eax;
+	/* Don't do an additional sync on CPUs where we know
+	   RDTSC is already synchronous. */
+	alternative_io(ASM_NOP2, "cpuid", X86_FEATURE_SYNC_RDTSC,
+			  "=a" (eax), "0" (1) : "ebx","ecx","edx","memory");
+	rdtscll(ret);
+	return ret;
+}
+
 extern unsigned int cpu_khz;
 
 extern int read_current_timer(unsigned long *timer_value);