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>

diff --git a/arch/x86/kernel/uv_time.c b/arch/x86/kernel/uv_time.c
index 3c84aa001c118275829783da04a5cdda9557a47d..2b75ef638dbc6f0716d02c58dd23cc8a97acc45a 100644 (file)
--- 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);
 }
 
 /*

diff --git a/drivers/char/uv_mmtimer.c b/drivers/char/uv_mmtimer.c
index 867b67be9f0ac0db007cb8116d7f7b970ab1ba87..c7072ba14f48130d8f04977232bb38ed8dbe067e 100644 (file)
--- a/drivers/char/uv_mmtimer.c
+++ b/drivers/char/uv_mmtimer.c
@@ -89,13 +89,17 @@ static long uv_mmtimer_ioctl(struct file *file, unsigned int cmd,
        switch (cmd) {
        case MMTIMER_GETOFFSET: /* offset of the counter */
                /*
-                * UV RTC register is on its own page
+                * 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.
+                *
+                * The offset returned is in 64 bit units.
                 */
-               if (PAGE_SIZE <= (1 << 16))
-                       ret = ((UV_LOCAL_MMR_BASE | UVH_RTC) & (PAGE_SIZE-1))
-                               / 8;
+               if (uv_get_min_hub_revision_id() == 1)
+                       ret = 0;
                else
-                       ret = -ENOSYS;
+                       ret = ((uv_blade_processor_id() * L1_CACHE_BYTES) %
+                                       PAGE_SIZE) / 8;
                break;
 
        case MMTIMER_GETRES: /* resolution of the clock in 10^-15 s */
@@ -115,8 +119,8 @@ static long uv_mmtimer_ioctl(struct file *file, unsigned int cmd,
                ret = hweight64(UVH_RTC_REAL_TIME_CLOCK_MASK);
                break;
 
-       case MMTIMER_MMAPAVAIL: /* can we mmap the clock into userspace? */
-               ret = (PAGE_SIZE <= (1 << 16)) ? 1 : 0;
+       case MMTIMER_MMAPAVAIL:
+               ret = 1;
                break;
 
        case MMTIMER_GETCOUNTER: