Merge tag 'v2.6.38' of git://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux-2.6 into for-linus

1 files changed, 10 insertions, 0 deletions

diff --git a/arch/sh/lib/delay.c b/arch/sh/lib/delay.c
index faa8f86c0db4..0901b2f14e15 100644
--- a/arch/sh/lib/delay.c
+++ b/arch/sh/lib/delay.c
@@ -10,6 +10,16 @@
 void __delay(unsigned long loops)
 {
         __asm__ __volatile__(
+                /*
+                 * ST40-300 appears to have an issue with this code,
+                 * normally taking two cycles each loop, as with all
+                 * other SH variants. If however the branch and the
+                 * delay slot straddle an 8 byte boundary, this increases
+                 * to 3 cycles.
+                 * This align directive ensures this doesn't occur.
+                 */
+                ".balign 8\n\t"
+
                 "tst    %0, %0\n\t"
                 "1:\t"
                 "bf/s   1b\n\t"