[PATCH] optimize writer path in time_interpolator_get_counter()

      Christoph Lameter <clameter@engr.sgi.com>

When using a time interpolator that is susceptible to jitter there's
potentially contention over a cmpxchg used to prevent time from going
backwards.  This is unnecessary when the caller holds the xtime write
seqlock as all readers will be blocked from returning until the write is
complete.  We can therefore allow writers to insert a new value and exit
rather than fight with CPUs who only hold a reader lock.

Signed-off-by: Alex Williamson <alex.williamson@hp.com>
Signed-off-by: Christoph Lameter <clameter@sgi.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>

1 files changed, 13 insertions, 4 deletions

diff --git a/kernel/timer.c b/kernel/timer.c
index 1433d87f46b3..13e2b513be01 100644
--- a/kernel/timer.c
+++ b/kernel/timer.c
@@ -1429,7 +1429,7 @@ static inline u64 time_interpolator_get_cycles(unsigned int src)
         }
 }
 
-static inline u64 time_interpolator_get_counter(void)
+static inline u64 time_interpolator_get_counter(int writelock)
 {
         unsigned int src = time_interpolator->source;
 
@@ -1443,6 +1443,15 @@ static inline u64 time_interpolator_get_counter(void)
                         now = time_interpolator_get_cycles(src);
                         if (lcycle && time_after(lcycle, now))
                                 return lcycle;
+
+                        /* When holding the xtime write lock, there's no need
+                         * to add the overhead of the cmpxchg.  Readers are
+                         * force to retry until the write lock is released.
+                         */
+                        if (writelock) {
+                                time_interpolator->last_cycle = now;
+                                return now;
+                        }
                         /* Keep track of the last timer value returned. The use of cmpxchg here
                          * will cause contention in an SMP environment.
                          */
@@ -1456,7 +1465,7 @@ static inline u64 time_interpolator_get_counter(void)
 void time_interpolator_reset(void)
 {
         time_interpolator->offset = 0;
-        time_interpolator->last_counter = time_interpolator_get_counter();
+        time_interpolator->last_counter = time_interpolator_get_counter(1);
 }
 
 #define GET_TI_NSECS(count,i) (((((count) - i->last_counter) & (i)->mask) * (i)->nsec_per_cyc) >> (i)->shift)
@@ -1468,7 +1477,7 @@ unsigned long time_interpolator_get_offset(void)
                 return 0;
 
         return time_interpolator->offset +
-                GET_TI_NSECS(time_interpolator_get_counter(), time_interpolator);
+                GET_TI_NSECS(time_interpolator_get_counter(0), time_interpolator);
 }
 
 #define INTERPOLATOR_ADJUST 65536
@@ -1491,7 +1500,7 @@ static void time_interpolator_update(long delta_nsec)
          * and the tuning logic insures that.
          */
 
-        counter = time_interpolator_get_counter();
+        counter = time_interpolator_get_counter(1);
         offset = time_interpolator->offset + GET_TI_NSECS(counter, time_interpolator);
 
         if (delta_nsec < 0 || (unsigned long) delta_nsec < offset)