aboutsummaryrefslogtreecommitdiffstats
path: root/init
diff options
context:
space:
mode:
authorPhil Carmody <ext-phil.2.carmody@nokia.com>2011-03-22 16:34:12 -0700
committerLinus Torvalds <torvalds@linux-foundation.org>2011-03-22 17:44:11 -0700
commit71c696b1d0310da3ab8033d743282959bd49d28b (patch)
treecf501760d1bb1e045c23bf5155742fa8aa221776 /init
parent9bfb23fc4a481650e60d22dbe84c0fd5a9d49bba (diff)
downloadkernel_samsung_smdk4412-71c696b1d0310da3ab8033d743282959bd49d28b.tar.gz
kernel_samsung_smdk4412-71c696b1d0310da3ab8033d743282959bd49d28b.tar.bz2
kernel_samsung_smdk4412-71c696b1d0310da3ab8033d743282959bd49d28b.zip
calibrate: extract fall-back calculation into own helper
The motivation for this patch series is that currently our OMAP calibrates itself using the trial-and-error binary chop fallback that some other architectures no longer need to perform. This is a lengthy process, taking 0.2s in an environment where boot time is of great interest. Patch 2/4 has two optimisations. Firstly, it replaces the initial repeated- doubling to find the relevant power of 2 with a tight loop that just does as much as it can in a jiffy. Secondly, it doesn't binary chop over an entire power of 2 range, it choses a much smaller range based on how much it squeezed in, and failed to squeeze in, during the first stage. Both are significant optimisations, and bring our calibration down from 23 jiffies to 5, and, in the process, often arrive at a more accurate lpj value. The 'bands' and 'sub-logarithmic' growth may look over-engineered, but they only cost a small level of inaccuracy in the initial guess (for all architectures) in order to avoid the very large inaccuracies that appeared during testing (on x86_64 architectures, and presumably others with less metronomic operation). Note that due to the existence of the TSC and other timers, the x86_64 will not typically use this fallback routine, but I wanted to code defensively, able to cope with all kinds of processor behaviours and kernel command line options. Patch 3/4 is an additional trap for the nightmare scenario where the initial estimate is very inaccurate, possibly due to things like SMIs. It simply retries with a larger bound. Stephen said: I tried this patch set out on an MSM7630. : : Before: : : Calibrating delay loop... 681.57 BogoMIPS (lpj=3407872) : : After: : : Calibrating delay loop... 680.75 BogoMIPS (lpj=3403776) : : But the really good news is calibration time dropped from ~247ms to ~56ms. : Sadly we won't be able to benefit from this should my udelay patches make : it into ARM because we would be using calibrate_delay_direct() instead (at : least on machines who choose to). Can we somehow reapply the logic behind : this to calibrate_delay_direct()? That would be even better, but this is : definitely a boot time improvement. : : Or maybe we could just replace calibrate_delay_direct() with this fallback : calculation? If __delay() is a thin wrapper around read_current_timer() : it should work just as well (plus patch 3 makes it handle SMIs). I'll try : that out. This patch: ... so that it can be modified more clinically. This is almost entirely cosmetic. The only change to the operation is that the global variable is only set once after the estimation is completed, rather than taking on all the intermediate values. However, there are no readers of that variable, so this change is unimportant. 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')
-rw-r--r--init/calibrate.c73
1 files changed, 40 insertions, 33 deletions
diff --git a/init/calibrate.c b/init/calibrate.c
index 24fe022c55f..b71643a7aca 100644
--- a/init/calibrate.c
+++ b/init/calibrate.c
@@ -119,10 +119,47 @@ static unsigned long __cpuinit calibrate_delay_direct(void) {return 0;}
*/
#define LPS_PREC 8
-void __cpuinit calibrate_delay(void)
+static unsigned long __cpuinit calibrate_delay_converge(void)
{
- unsigned long ticks, loopbit;
+ unsigned long lpj, ticks, loopbit;
int lps_precision = LPS_PREC;
+
+ 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;
+ }
+
+ /*
+ * Do a binary approximation to get lpj set to
+ * equal one clock (up to lps_precision bits)
+ */
+ lpj >>= 1;
+ loopbit = lpj;
+ while (lps_precision-- && (loopbit >>= 1)) {
+ lpj |= loopbit;
+ ticks = jiffies;
+ while (ticks == jiffies)
+ /* nothing */;
+ ticks = jiffies;
+ __delay(lpj);
+ if (jiffies != ticks) /* longer than 1 tick */
+ lpj &= ~loopbit;
+ }
+
+ return lpj;
+}
+
+void __cpuinit calibrate_delay(void)
+{
static bool printed;
if (preset_lpj) {
@@ -139,39 +176,9 @@ 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",