x86: use cpu_khz for loops_per_jiffy calculation

On the x86 platform we can use the value of tsc_khz computed during tsc
calibration to calculate the loops_per_jiffy value. Its very important
to keep the error in lpj values to minimum as any error in that may
result in kernel panic in check_timer. In virtualization environment, On
a highly overloaded host the guest delay calibration may sometimes
result in errors beyond the ~50% that timer_irq_works can handle,
resulting in the guest panicking.

Does some formating changes to lpj_setup code to now have a single
printk to print the bogomips value.

We do this only for the boot processor because the AP's can have
different base frequencies or the BIOS might boot a AP at a different
frequency.

Signed-off-by: Alok N Kataria <akataria@vmware.com>
Cc: Arjan van de Ven <arjan@infradead.org>
Cc: Daniel Hecht <dhecht@vmware.com>
Cc: Tim Mann <mann@vmware.com>
Cc: Zach Amsden <zach@vmware.com>
Cc: Sahil Rihan <srihan@vmware.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>

4 files changed, 27 insertions, 17 deletions

diff --git a/arch/x86/kernel/time_64.c b/arch/x86/kernel/time_64.c
index c737849e2ef7..12b4a71bd074 100644
--- a/arch/x86/kernel/time_64.c
+++ b/arch/x86/kernel/time_64.c
@@ -123,6 +123,8 @@ void __init time_init(void)
                 (boot_cpu_data.x86_vendor == X86_VENDOR_AMD))
                 cpu_khz = calculate_cpu_khz();
 
+        lpj_tsc = ((unsigned long)tsc_khz * 1000)/HZ;
+
         if (unsynchronized_tsc())
                 mark_tsc_unstable("TSCs unsynchronized");
 
diff --git a/arch/x86/kernel/tsc_32.c b/arch/x86/kernel/tsc_32.c
index 068759db63dd..be729035b30b 100644
--- a/arch/x86/kernel/tsc_32.c
+++ b/arch/x86/kernel/tsc_32.c
@@ -401,6 +401,7 @@ static inline void check_geode_tsc_reliable(void) { }
 void __init tsc_init(void)
 {
         int cpu;
+        u64 lpj;
 
         if (!cpu_has_tsc || tsc_disabled) {
                 /* Disable the TSC in case of !cpu_has_tsc */
@@ -421,6 +422,10 @@ void __init tsc_init(void)
                 return;
         }
 
+        lpj = ((u64)tsc_khz * 1000);
+        do_div(lpj, HZ);
+        lpj_tsc = lpj;
+
         printk("Detected %lu.%03lu MHz processor.\n",
                                 (unsigned long)cpu_khz / 1000,
                                 (unsigned long)cpu_khz % 1000);
diff --git a/include/linux/delay.h b/include/linux/delay.h
index 54552d21296e..01aec60590ab 100644
--- a/include/linux/delay.h
+++ b/include/linux/delay.h
@@ -41,6 +41,7 @@ static inline void ndelay(unsigned long x)
 #define ndelay(x) ndelay(x)
 #endif
 
+extern unsigned long lpj_tsc;
 void calibrate_delay(void);
 void msleep(unsigned int msecs);
 unsigned long msleep_interruptible(unsigned int msecs);
diff --git a/init/calibrate.c b/init/calibrate.c
index ecb3822d4f70..86286974dada 100644
--- a/init/calibrate.c
+++ b/init/calibrate.c
@@ -8,7 +8,9 @@
 #include <linux/delay.h>
 #include <linux/init.h>
 #include <linux/timex.h>
+#include <linux/smp.h>
 
+unsigned long lpj_tsc;
 unsigned long preset_lpj;
 static int __init lpj_setup(char *str)
 {
@@ -108,6 +110,10 @@ 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%
+ * For the boot cpu we can skip the delay calibration and assign it a value
+ * calculated based on the tsc frequency.
+ * For the rest of the CPUs we cannot assume that the tsc frequency is same as
+ * the cpu frequency, hence do the calibration for those.
  */
 #define LPS_PREC 8
 
@@ -118,20 +124,20 @@ void __cpuinit calibrate_delay(void)
 
         if (preset_lpj) {
                 loops_per_jiffy = preset_lpj;
-                printk("Calibrating delay loop (skipped)... "
-                        "%lu.%02lu BogoMIPS preset\n",
-                        loops_per_jiffy/(500000/HZ),
-                        (loops_per_jiffy/(5000/HZ)) % 100);
+                printk(KERN_INFO
+                        "Calibrating delay loop (skipped) preset value.. ");
+        } else if ((smp_processor_id() == 0) && lpj_tsc) {
+                loops_per_jiffy = lpj_tsc;
+                printk(KERN_INFO
+                        "Calibrating delay loop (skipped), "
+                        "using tsc calculated value.. ");
         } else if ((loops_per_jiffy = calibrate_delay_direct()) != 0) {
-                printk("Calibrating delay using timer specific routine.. ");
-                printk("%lu.%02lu BogoMIPS (lpj=%lu)\n",
-                        loops_per_jiffy/(500000/HZ),
-                        (loops_per_jiffy/(5000/HZ)) % 100,
-                        loops_per_jiffy);
+                printk(KERN_INFO
+                        "Calibrating delay using timer specific routine.. ");
         } else {
                 loops_per_jiffy = (1<<12);
 
-                printk(KERN_DEBUG "Calibrating delay loop... ");
+                printk(KERN_INFO "Calibrating delay loop... ");
                 while ((loops_per_jiffy <<= 1) != 0) {
                         /* wait for "start of" clock tick */
                         ticks = jiffies;
@@ -161,12 +167,8 @@ void __cpuinit calibrate_delay(void)
                         if (jiffies != ticks)   /* longer than 1 tick */
                                 loops_per_jiffy &= ~loopbit;
                 }
-
-                /* Round the value and print it */
-                printk("%lu.%02lu BogoMIPS (lpj=%lu)\n",
-                        loops_per_jiffy/(500000/HZ),
-                        (loops_per_jiffy/(5000/HZ)) % 100,
-                        loops_per_jiffy);
         }
-
+        printk(KERN_INFO "%lu.%02lu BogoMIPS (lpj=%lu)\n",
+                        loops_per_jiffy/(500000/HZ),
+                        (loops_per_jiffy/(5000/HZ)) % 100, loops_per_jiffy);
 }