aboutsummaryrefslogtreecommitdiffstats
path: root/init/calibrate.c
diff options
context:
space:
mode:
authorPhil Carmody <ext-phil.2.carmody@nokia.com>2011-03-22 16:34:13 -0700
committerLinus Torvalds <torvalds@linux-foundation.org>2011-03-22 17:44:11 -0700
commit191e56880a6a638ce931859317f37deb084b6433 (patch)
tree26853fa62983f12b85badda6b9ee2197c2f10697 /init/calibrate.c
parent71c696b1d0310da3ab8033d743282959bd49d28b (diff)
downloadkernel_goldelico_gta04-191e56880a6a638ce931859317f37deb084b6433.zip
kernel_goldelico_gta04-191e56880a6a638ce931859317f37deb084b6433.tar.gz
kernel_goldelico_gta04-191e56880a6a638ce931859317f37deb084b6433.tar.bz2
calibrate: home in on correct lpj value more quickly
Binary chop with a jiffy-resync on each step to find an upper bound is slow, so just race in a tight-ish loop to find an underestimate. If done with lots of individual steps, sometimes several hundreds of iterations would be required, which would impose a significant overhead, and make the initial estimate very low. By taking slowly increasing steps there will be less overhead. E.g. an x86_64 2.67GHz could have fitted in 613 individual small delays, but in reality should have been able to fit in a single delay 644 times longer, so underestimated by 31 steps. To reach the equivalent of 644 small delays with the accelerating scheme now requires about 130 iterations, so has <1/4th of the overhead, and can therefore be expected to underestimate by only 7 steps. As now we have a better initial estimate we can binary chop over a smaller range. With the loop overhead in the initial estimate kept low, and the step sizes moderate, we won't have under-estimated by much, so chose as tight a range as we can. Signed-off-by: Phil Carmody <ext-phil.2.carmody@nokia.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: "H. Peter Anvin" <hpa@zytor.com> Tested-by: Stephen Boyd <sboyd@codeaurora.org> Cc: Greg KH <greg@kroah.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Diffstat (limited to 'init/calibrate.c')
-rw-r--r--init/calibrate.c57
1 files changed, 34 insertions, 23 deletions
diff --git a/init/calibrate.c b/init/calibrate.c
index b71643a..f9000df 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
@@ -121,38 +121,49 @@ static unsigned long __cpuinit calibrate_delay_direct(void) {return 0;}
static unsigned long __cpuinit calibrate_delay_converge(void)
{
- unsigned long lpj, ticks, loopbit;
- int lps_precision = LPS_PREC;
+ /* First stage - slowly accelerate to find initial bounds */
+ unsigned long lpj, ticks, loopadd, chop_limit;
+ int trials = 0, band = 0, trial_in_band = 0;
lpj = (1<<12);
- while ((lpj <<= 1) != 0) {
- /* wait for "start of" clock tick */
- ticks = jiffies;
- while (ticks == jiffies)
- /* nothing */;
- /* Go .. */
- ticks = jiffies;
- __delay(lpj);
- ticks = jiffies - ticks;
- if (ticks)
- break;
- }
+
+ /* 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 = lpj * band;
+ lpj *= trials;
+ chop_limit = lpj >> (LPS_PREC + 1);
/*
* Do a binary approximation to get lpj set to
- * equal one clock (up to lps_precision bits)
+ * equal one clock (up to LPS_PREC bits)
*/
- lpj >>= 1;
- loopbit = lpj;
- while (lps_precision-- && (loopbit >>= 1)) {
- lpj |= loopbit;
+ while (loopadd > chop_limit) {
+ lpj += loopadd;
ticks = jiffies;
while (ticks == jiffies)
- /* nothing */;
+ ; /* nothing */
ticks = jiffies;
__delay(lpj);
if (jiffies != ticks) /* longer than 1 tick */
- lpj &= ~loopbit;
+ lpj -= loopadd;
+ loopadd >>= 1;
}
return lpj;