public inbox for linux-ia64@vger.kernel.org
 help / color / mirror / Atom feed
* [patch] Update nofault code
@ 2008-01-03 16:23 Russ Anderson
  0 siblings, 0 replies; only message in thread
From: Russ Anderson @ 2008-01-03 16:23 UTC (permalink / raw)
  To: linux-ia64

[patch] Update nofault code

Montecito and Montvale behaves slightly differently than previous 
Itanium processors, resulting in the MCA due to a failed PIO read
to sometimes surfacing outside the nofault code.  This code is
based on discussions with Intel CPU architects and verified at
customer sites.

Signed-off-by: Russ Anderson <rja@sgi.com>

---
 arch/ia64/sn/kernel/xp_nofault.S |   10 +++++++---
 1 file changed, 7 insertions(+), 3 deletions(-)

Index: test/arch/ia64/sn/kernel/xp_nofault.S
=================================--- test.orig/arch/ia64/sn/kernel/xp_nofault.S	2008-01-03 10:00:46.106785444 -0600
+++ test/arch/ia64/sn/kernel/xp_nofault.S	2008-01-03 10:03:28.602998658 -0600
@@ -3,7 +3,7 @@
  * License.  See the file "COPYING" in the main directory of this archive
  * for more details.
  *
- * Copyright (c) 2004-2005 Silicon Graphics, Inc.  All Rights Reserved.
+ * Copyright (c) 2004-2007 Silicon Graphics, Inc.  All Rights Reserved.
  */
 
 
@@ -14,6 +14,11 @@
  * PIO read fails, the MCA handler will force the error to look
  * corrected and vector to the xp_error_PIOR which will return an error.
  *
+ * The definition of "consumption" and the time it takes for an MCA
+ * to surface is processor implementation specific.  This code
+ * is sufficient on Itanium through the Montvale processor family.
+ * It may need to be adjusted for future processor implementations.
+ *
  *	extern int xp_nofault_PIOR(void *remote_register);
  */
 
@@ -22,11 +27,10 @@ xp_nofault_PIOR:
 	mov	r8=r0			// Stage a success return value
 	ld8.acq	r9=[r32];;		// PIO Read the specified register
 	adds	r9=1,r9;;		// Add to force consumption
-	or	r9=r9,r9;;		// Or to force consumption
+	srlz.i;;			// Allow time for MCA to surface
 	br.ret.sptk.many b0;;		// Return success
 
 	.global xp_error_PIOR
 xp_error_PIOR:
 	mov	r8=1			// Return value of 1
 	br.ret.sptk.many b0;;		// Return failure
-
-- 
Russ Anderson, OS RAS/Partitioning Project Lead  
SGI - Silicon Graphics Inc          rja@sgi.com

^ permalink raw reply	[flat|nested] only message in thread

only message in thread, other threads:[~2008-01-03 16:23 UTC | newest]

Thread overview: (only message) (download: mbox.gz follow: Atom feed
-- links below jump to the message on this page --
2008-01-03 16:23 [patch] Update nofault code Russ Anderson

This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox