[34-longterm 155/209] x86, hotplug: In the MWAIT case of play_dead, CLFLUSH the cache line

From: Paul Gortmaker
Date: Thu Apr 14 2011 - 14:13:27 EST


From: H. Peter Anvin <hpa@xxxxxxxxxxxxxxx>

=====================================================================
| This is a commit scheduled for the next v2.6.34 longterm release. |
| If you see a problem with using this for longterm, please comment.|
=====================================================================

commit ce5f68246bf2385d6174856708d0b746dc378f20 upstream.

When we're using MWAIT for play_dead, explicitly CLFLUSH the cache
line before executing MONITOR. This is a potential workaround for the
Xeon 7400 erratum AAI65 after having a spurious wakeup and returning
around the loop. "Potential" here because it is not certain that that
erratum could actually trigger; however, the CLFLUSH should be
harmless.

Signed-off-by: H. Peter Anvin <hpa@xxxxxxxxxxxxxxx>
Acked-by: Venkatesh Pallipadi <venki@xxxxxxxxxx>
Cc: Asit Mallick <asit.k.mallick@xxxxxxxxx>
Cc: Arjan van de Ven <arjan@xxxxxxxxxxxxxxxx>
Cc: Len Brown <lenb@xxxxxxxxxx>
Signed-off-by: Paul Gortmaker <paul.gortmaker@xxxxxxxxxxxxx>
---
arch/x86/kernel/smpboot.c | 20 +++++++++++++++++++-
1 files changed, 19 insertions(+), 1 deletions(-)

diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
index b283dbf..9a4fdc5 100644
--- a/arch/x86/kernel/smpboot.c
+++ b/arch/x86/kernel/smpboot.c
@@ -1371,9 +1371,12 @@ static inline void mwait_play_dead(void)
unsigned int highest_cstate = 0;
unsigned int highest_subcstate = 0;
int i;
+ void *mwait_ptr;

if (!cpu_has(&current_cpu_data, X86_FEATURE_MWAIT))
return;
+ if (!cpu_has(&current_cpu_data, X86_FEATURE_CLFLSH))
+ return;
if (current_cpu_data.cpuid_level < CPUID_MWAIT_LEAF)
return;

@@ -1399,10 +1402,25 @@ static inline void mwait_play_dead(void)
(highest_subcstate - 1);
}

+ /*
+ * This should be a memory location in a cache line which is
+ * unlikely to be touched by other processors. The actual
+ * content is immaterial as it is not actually modified in any way.
+ */
+ mwait_ptr = &current_thread_info()->flags;
+
wbinvd();

while (1) {
- __monitor(&current_thread_info()->flags, 0, 0);
+ /*
+ * The CLFLUSH is a workaround for erratum AAI65 for
+ * the Xeon 7400 series. It's not clear it is actually
+ * needed, but it should be harmless in either case.
+ * The WBINVD is insufficient due to the spurious-wakeup
+ * case where we return around the loop.
+ */
+ clflush(mwait_ptr);
+ __monitor(mwait_ptr, 0, 0);
mb();
__mwait(eax, 0);
}
--
1.7.4.4

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/