x86, UV: Fix RTC latency bug by reading replicated cachelines

For SGI UV node controllers (HUB) rev 2.0 or greater, use
replicated cachelines to read the RTC timer.  This optimization
allows faster simulataneous reads from a given socket.

Signed-off-by: Dimitri Sivanich <sivanich@sgi.com>
Cc: Jack Steiner <steiner@sgi.com>
LKML-Reference: <20100122154140.GB4975@sgi.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>

1 files changed, 12 insertions, 1 deletions

diff --git a/arch/x86/kernel/uv_time.c b/arch/x86/kernel/uv_time.c
index 3c84aa001c11..2b75ef638dbc 100644
--- a/arch/x86/kernel/uv_time.c
+++ b/arch/x86/kernel/uv_time.c
@@ -282,10 +282,21 @@ static int uv_rtc_unset_timer(int cpu, int force)
 
 /*
  * Read the RTC.
+ *
+ * Starting with HUB rev 2.0, the UV RTC register is replicated across all
+ * cachelines of it's own page.  This allows faster simultaneous reads
+ * from a given socket.
  */
 static cycle_t uv_read_rtc(struct clocksource *cs)
 {
-        return (cycle_t)uv_read_local_mmr(UVH_RTC);
+        unsigned long offset;
+
+        if (uv_get_min_hub_revision_id() == 1)
+                offset = 0;
+        else
+                offset = (uv_blade_processor_id() * L1_CACHE_BYTES) % PAGE_SIZE;
+
+        return (cycle_t)uv_read_local_mmr(UVH_RTC | offset);
 }
 
 /*