1 files changed, 67 insertions, 35 deletions

diff --git a/init/calibrate.c b/init/calibrate.c
index 24fe022c55f9..76ac9194cbc4 100644
--- a/init/calibrate.c
+++ b/init/calibrate.c
@@ -110,8 +110,8 @@ static unsigned long __cpuinit calibrate_delay_direct(void) {return 0;}
 
 /*
  * This is the number of bits of precision for the loops_per_jiffy.  Each
- * bit takes on average 1.5/HZ seconds.  This (like the original) is a little
- * better than 1%
+ * time we refine our estimate after the first takes 1.5/HZ seconds, so try
+ * to start with a good estimate.
  * For the boot cpu we can skip the delay calibration and assign it a value
  * calculated based on the timer frequency.
  * For the rest of the CPUs we cannot assume that the timer frequency is same as
@@ -119,10 +119,72 @@ static unsigned long __cpuinit calibrate_delay_direct(void) {return 0;}
  */
 #define LPS_PREC 8
 
+static unsigned long __cpuinit calibrate_delay_converge(void)
+{
+	/* First stage - slowly accelerate to find initial bounds */
+	unsigned long lpj, lpj_base, ticks, loopadd, loopadd_base, chop_limit;
+	int trials = 0, band = 0, trial_in_band = 0;
+
+	lpj = (1<<12);
+
+	/* wait for "start of" clock tick */
+	ticks = jiffies;
+	while (ticks == jiffies)
+		; /* nothing */
+	/* Go .. */
+	ticks = jiffies;
+	do {
+		if (++trial_in_band == (1<<band)) {
+			++band;
+			trial_in_band = 0;
+		}
+		__delay(lpj * band);
+		trials += band;
+	} while (ticks == jiffies);
+	/*
+	 * We overshot, so retreat to a clear underestimate. Then estimate
+	 * the largest likely undershoot. This defines our chop bounds.
+	 */
+	trials -= band;
+	loopadd_base = lpj * band;
+	lpj_base = lpj * trials;
+
+recalibrate:
+	lpj = lpj_base;
+	loopadd = loopadd_base;
+
+	/*
+	 * Do a binary approximation to get lpj set to
+	 * equal one clock (up to LPS_PREC bits)
+	 */
+	chop_limit = lpj >> LPS_PREC;
+	while (loopadd > chop_limit) {
+		lpj += loopadd;
+		ticks = jiffies;
+		while (ticks == jiffies)
+			; /* nothing */
+		ticks = jiffies;
+		__delay(lpj);
+		if (jiffies != ticks)	/* longer than 1 tick */
+			lpj -= loopadd;
+		loopadd >>= 1;
+	}
+	/*
+	 * If we incremented every single time possible, presume we've
+	 * massively underestimated initially, and retry with a higher
+	 * start, and larger range. (Only seen on x86_64, due to SMIs)
+	 */
+	if (lpj + loopadd * 2 == lpj_base + loopadd_base * 2) {
+		lpj_base = lpj;
+		loopadd_base <<= 2;
+		goto recalibrate;
+	}
+
+	return lpj;
+}
+
 void __cpuinit calibrate_delay(void)
 {
-	unsigned long ticks, loopbit;
-	int lps_precision = LPS_PREC;
 	static bool printed;
 
 	if (preset_lpj) {
@@ -139,39 +201,9 @@ void __cpuinit calibrate_delay(void)
 			pr_info("Calibrating delay using timer "
 				"specific routine.. ");
 	} else {
-		loops_per_jiffy = (1<<12);
-
 		if (!printed)
 			pr_info("Calibrating delay loop... ");
-		while ((loops_per_jiffy <<= 1) != 0) {
-			/* wait for "start of" clock tick */
-			ticks = jiffies;
-			while (ticks == jiffies)
-				/* nothing */;
-			/* Go .. */
-			ticks = jiffies;
-			__delay(loops_per_jiffy);
-			ticks = jiffies - ticks;
-			if (ticks)
-				break;
-		}
-
-		/*
-		 * Do a binary approximation to get loops_per_jiffy set to
-		 * equal one clock (up to lps_precision bits)
-		 */
-		loops_per_jiffy >>= 1;
-		loopbit = loops_per_jiffy;
-		while (lps_precision-- && (loopbit >>= 1)) {
-			loops_per_jiffy |= loopbit;
-			ticks = jiffies;
-			while (ticks == jiffies)
-				/* nothing */;
-			ticks = jiffies;
-			__delay(loops_per_jiffy);
-			if (jiffies != ticks)	/* longer than 1 tick */
-				loops_per_jiffy &= ~loopbit;
-		}
+		loops_per_jiffy = calibrate_delay_converge();
 	}
 	if (!printed)
 		pr_cont("%lu.%02lu BogoMIPS (lpj=%lu)\n",