hangcheck-timer: fix x86_32 bugs

drivers/char/hangcheck-timer.c is doubly broken.  When the overflown value
of TIMER_FREQ is abnormally low, it spams the syslog with KERN_CRIT
messages "Hangcheck: hangcheck value past margin!" But whether it happens
or not depends on HZ and lpj in a complex way.  People have hit it
occasionally as far as google search can tell.

First, the following line overflows unsigned long:

# define TIMER_FREQ (HZ*loops_per_jiffy)

Second, and more importantly, loops_per_jiffy has little to do with the
con= version from the the time scale of get_cycles() (aka rdtsc) to the
time scale of jiffies.

The attached patch resolves both of the problems.

Acked-by: Joel Becker <joel.becker@oracle.com>
Cc: john stultz <johnstul@us.ibm.com>
Cc: Jan Glauber <jan.glauber@de.ibm.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

diff --git a/drivers/char/hangcheck-timer.c b/drivers/char/hangcheck-timer.c
index 712d9f271aa6b8ed7026bca1594cc3b38052287f..e0249722d25f1c8b9dd05fa6705187afc8e23256 100644 (file)
--- a/drivers/char/hangcheck-timer.c
+++ b/drivers/char/hangcheck-timer.c
@@ -49,8 +49,9 @@
 #include <asm/uaccess.h>
 #include <linux/sysrq.h>
 #include <linux/timer.h>
+#include <linux/time.h>
 
-#define VERSION_STR "0.9.0"
+#define VERSION_STR "0.9.1"
 
 #define DEFAULT_IOFENCE_MARGIN 60      /* Default fudge factor, in seconds */
 #define DEFAULT_IOFENCE_TICK 180       /* Default timer timeout, in seconds */
@@ -119,10 +120,8 @@ __setup("hcheck_dump_tasks", hangcheck_parse_dump_tasks);
 #if defined(CONFIG_S390)
 # define HAVE_MONOTONIC
 # define TIMER_FREQ 1000000000ULL
-#elif defined(CONFIG_IA64)
-# define TIMER_FREQ ((unsigned long long)local_cpu_data->itc_freq)
 #else
-# define TIMER_FREQ (HZ*loops_per_jiffy)
+# define TIMER_FREQ 1000000000ULL
 #endif
 
 #ifdef HAVE_MONOTONIC
@@ -130,7 +129,9 @@ extern unsigned long long monotonic_clock(void);
 #else
 static inline unsigned long long monotonic_clock(void)
 {
-       return get_cycles();
+       struct timespec ts;
+       getrawmonotonic(&ts);
+       return timespec_to_ns(&ts);
 }
 #endif  /* HAVE_MONOTONIC */
 
@@ -168,6 +169,13 @@ static void hangcheck_fire(unsigned long data)
                        printk(KERN_CRIT "Hangcheck: hangcheck value past margin!\n");
                }
        }
+#if 0
+       /*
+        * Enable to investigate delays in detail
+        */
+       printk("Hangcheck: called %Ld ns since last time (%Ld ns overshoot)\n",
+                       tsc_diff, tsc_diff - hangcheck_tick*TIMER_FREQ);
+#endif
        mod_timer(&hangcheck_ticktock, jiffies + (hangcheck_tick*HZ));
        hangcheck_tsc = monotonic_clock();
 }
@@ -180,7 +188,7 @@ static int __init hangcheck_init(void)
 #if defined (HAVE_MONOTONIC)
        printk("Hangcheck: Using monotonic_clock().\n");
 #else
-       printk("Hangcheck: Using get_cycles().\n");
+       printk("Hangcheck: Using getrawmonotonic().\n");
 #endif  /* HAVE_MONOTONIC */
        hangcheck_tsc_margin =
                (unsigned long long)(hangcheck_margin + hangcheck_tick);