summaryrefslogtreecommitdiffstats
diff options
context:
space:
mode:
authorPavel Pisa <pisa@cmp.felk.cvut.cz>2016-10-04 23:30:22 +0200
committerPavel Pisa <pisa@cmp.felk.cvut.cz>2016-10-04 23:30:22 +0200
commit8714684129e69b6bec7ca56b4e4243854208a976 (patch)
treed294584bac689d634dc31ea981754c96515bfb29
parentlibdl/rtl-obj.c: synchronize cache should not depend on CPU_CACHE_LINE_BYTES. (diff)
downloadrtems-8714684129e69b6bec7ca56b4e4243854208a976.tar.bz2
score/arm: Correct logic to select 64 byte cache line maximum size for Cortex-A.
The use of actual cache line max bytes and minimum required alignment in architecture but not-BSP dependent code could be problematic because there exists even ARM instruction set implementations with 128 byte line length and real maximum can be quite problematic to say. But actually supported ARM BSPs should be OK with these values.
-rw-r--r--cpukit/score/cpu/arm/rtems/score/cpu.h4
1 files changed, 2 insertions, 2 deletions
diff --git a/cpukit/score/cpu/arm/rtems/score/cpu.h b/cpukit/score/cpu/arm/rtems/score/cpu.h
index 9fe28c4a3f..4cdca73838 100644
--- a/cpukit/score/cpu/arm/rtems/score/cpu.h
+++ b/cpukit/score/cpu/arm/rtems/score/cpu.h
@@ -146,9 +146,9 @@
#define CPU_STACK_GROWS_UP FALSE
#if defined(ARM_MULTILIB_CACHE_LINE_MAX_64)
- #define CPU_CACHE_LINE_BYTES 32
-#else
#define CPU_CACHE_LINE_BYTES 64
+#else
+ #define CPU_CACHE_LINE_BYTES 32
#endif
#define CPU_STRUCTURE_ALIGNMENT RTEMS_ALIGNED( CPU_CACHE_LINE_BYTES )