Optimize timespec_trunc()

The first thing done by timespec_trunc() is :

  if (gran <= jiffies_to_usecs(1) * 1000)

This should really be a test against a constant known at compile time.

Alas, it isnt. jiffies_to_usec() was unilined so C compiler emits a function
call and a multiply to compute : a CONSTANT.

mov    $0x1,%edi
mov    %rbx,0xffffffffffffffe8(%rbp)
mov    %r12,0xfffffffffffffff0(%rbp)
mov    %edx,%ebx
mov    %rsi,0xffffffffffffffc8(%rbp)
mov    %rsi,%r12
callq  ffffffff80232010 <jiffies_to_usecs>
imul   $0x3e8,%eax,%eax
cmp    %ebx,%eax

This patch reorders kernel/time.c a bit so that jiffies_to_usecs() is defined
before timespec_trunc() so that compiler now generates :

cmp    $0x3d0900,%edx  (HZ=250 on my machine)

This gives a better code (timespec_trunc() becoming a leaf function), and
shorter kernel size as well.

Signed-off-by: Eric Dumazet <dada1@cosmosbay.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: john stultz <johnstul@us.ibm.com>
Cc: Roman Zippel <zippel@linux-m68k.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

diff --git a/kernel/time.c b/kernel/time.c
index ba18ec4899bd92fe23a93716daf495bd2876025e..6d98ab72f38b075c707d5a78cc7d231cc919aa02 100644 (file)
--- a/kernel/time.c
+++ b/kernel/time.c
@@ -247,6 +247,36 @@ struct timespec current_fs_time(struct super_block *sb)
 }
 EXPORT_SYMBOL(current_fs_time);
 
+/*
+ * Convert jiffies to milliseconds and back.
+ *
+ * Avoid unnecessary multiplications/divisions in the
+ * two most common HZ cases:
+ */
+unsigned int inline jiffies_to_msecs(const unsigned long j)
+{
+#if HZ <= MSEC_PER_SEC && !(MSEC_PER_SEC % HZ)
+       return (MSEC_PER_SEC / HZ) * j;
+#elif HZ > MSEC_PER_SEC && !(HZ % MSEC_PER_SEC)
+       return (j + (HZ / MSEC_PER_SEC) - 1)/(HZ / MSEC_PER_SEC);
+#else
+       return (j * MSEC_PER_SEC) / HZ;
+#endif
+}
+EXPORT_SYMBOL(jiffies_to_msecs);
+
+unsigned int inline jiffies_to_usecs(const unsigned long j)
+{
+#if HZ <= USEC_PER_SEC && !(USEC_PER_SEC % HZ)
+       return (USEC_PER_SEC / HZ) * j;
+#elif HZ > USEC_PER_SEC && !(HZ % USEC_PER_SEC)
+       return (j + (HZ / USEC_PER_SEC) - 1)/(HZ / USEC_PER_SEC);
+#else
+       return (j * USEC_PER_SEC) / HZ;
+#endif
+}
+EXPORT_SYMBOL(jiffies_to_usecs);
+
 /**
  * timespec_trunc - Truncate timespec to a granularity
  * @t: Timespec
@@ -472,36 +502,6 @@ struct timeval ns_to_timeval(const s64 nsec)
 }
 EXPORT_SYMBOL(ns_to_timeval);
 
-/*
- * Convert jiffies to milliseconds and back.
- *
- * Avoid unnecessary multiplications/divisions in the
- * two most common HZ cases:
- */
-unsigned int jiffies_to_msecs(const unsigned long j)
-{
-#if HZ <= MSEC_PER_SEC && !(MSEC_PER_SEC % HZ)
-       return (MSEC_PER_SEC / HZ) * j;
-#elif HZ > MSEC_PER_SEC && !(HZ % MSEC_PER_SEC)
-       return (j + (HZ / MSEC_PER_SEC) - 1)/(HZ / MSEC_PER_SEC);
-#else
-       return (j * MSEC_PER_SEC) / HZ;
-#endif
-}
-EXPORT_SYMBOL(jiffies_to_msecs);
-
-unsigned int jiffies_to_usecs(const unsigned long j)
-{
-#if HZ <= USEC_PER_SEC && !(USEC_PER_SEC % HZ)
-       return (USEC_PER_SEC / HZ) * j;
-#elif HZ > USEC_PER_SEC && !(HZ % USEC_PER_SEC)
-       return (j + (HZ / USEC_PER_SEC) - 1)/(HZ / USEC_PER_SEC);
-#else
-       return (j * USEC_PER_SEC) / HZ;
-#endif
-}
-EXPORT_SYMBOL(jiffies_to_usecs);
-
 /*
  * When we convert to jiffies then we interpret incoming values
  * the following way: