summaryrefslogtreecommitdiffstats
path: root/arch/ia64/kernel/patch.c
diff options
context:
space:
mode:
authorHidetoshi Seto <seto.hidetoshi@jp.fujitsu.com>2008-01-29 14:39:33 +0900
committerTony Luck <tony.luck@intel.com>2008-03-10 16:35:47 -0700
commit4fe01c68eba53c3f324807faff71535218c41e9c (patch)
tree43e061a07d84b2ec80cd40e91156d008e4d0ef55 /arch/ia64/kernel/patch.c
parentcdeeeae056a429e729ae9e914fa8142ee45bee93 (diff)
downloadlinux-4fe01c68eba53c3f324807faff71535218c41e9c.tar.gz
linux-4fe01c68eba53c3f324807faff71535218c41e9c.tar.bz2
linux-4fe01c68eba53c3f324807faff71535218c41e9c.zip
[IA64] cleanup and improve fsys_gettimeofday
This patch does: - Remove outdated comments (which someday I marked with "?"). - Reassemble instructions to fit them in fewer bundles. - If McKinley Errata 9 workaround is not needed, the workaround bundles will be patched out with NOPs. However it also not needed to have a totally NOP bundle (nop * 3) before branch. As a result, this makes the code path 3 (or 2) bundles shorter (and remove 1 unnecessary stop bit). It seems to be 1% faster. (10sec loop test, with nojitter @ Madison 1.5GHz x 4) Before: CPU 0: 0.14 (usecs) (0 errors / 69598875 iterations) CPU 1: 0.14 (usecs) (0 errors / 69630721 iterations) CPU 2: 0.14 (usecs) (0 errors / 69607850 iterations) CPU 3: 0.14 (usecs) (0 errors / 69619832 iterations) After: CPU 0: 0.14 (usecs) (0 errors / 70257728 iterations) CPU 1: 0.14 (usecs) (0 errors / 70309498 iterations) CPU 2: 0.14 (usecs) (0 errors / 70280639 iterations) CPU 3: 0.14 (usecs) (0 errors / 70260682 iterations) Signed-off-by: Hidetoshi Seto <seto.hidetoshi@jp.fujitsu.com> Signed-off-by: Tony Luck <tony.luck@intel.com>
Diffstat (limited to 'arch/ia64/kernel/patch.c')
-rw-r--r--arch/ia64/kernel/patch.c8
1 files changed, 4 insertions, 4 deletions
diff --git a/arch/ia64/kernel/patch.c b/arch/ia64/kernel/patch.c
index 2cb9425e0421..e0dca8743dbb 100644
--- a/arch/ia64/kernel/patch.c
+++ b/arch/ia64/kernel/patch.c
@@ -135,10 +135,10 @@ ia64_patch_mckinley_e9 (unsigned long start, unsigned long end)
while (offp < (s32 *) end) {
wp = (u64 *) ia64_imva((char *) offp + *offp);
- wp[0] = 0x0000000100000000UL; /* nop.m 0; nop.i 0; nop.i 0 */
- wp[1] = 0x0004000000000200UL;
- wp[2] = 0x0000000100000011UL; /* nop.m 0; nop.i 0; br.ret.sptk.many b6 */
- wp[3] = 0x0084006880000200UL;
+ wp[0] = 0x0000000100000011UL; /* nop.m 0; nop.i 0; br.ret.sptk.many b6 */
+ wp[1] = 0x0084006880000200UL;
+ wp[2] = 0x0000000100000000UL; /* nop.m 0; nop.i 0; nop.i 0 */
+ wp[3] = 0x0004000000000200UL;
ia64_fc(wp); ia64_fc(wp + 2);
++offp;
}