From: Heiko Carstens <heiko.carstens@de.ibm.com>
Date: Fri, 28 Apr 2006 01:40:23 +0000 (-0700)
Subject: [PATCH] s390: instruction processing damage handling
X-Git-Tag: v2.6.17-rc4~115
X-Git-Url: https://err.no/cgi-bin/gitweb.cgi?a=commitdiff_plain;h=b73d40c6178f2c8b2d574db566b47f36e3d12072;p=linux-2.6

[PATCH] s390: instruction processing damage handling

In case of an instruction processing damage (IPD) machine check in kernel mode
the resulting action is always to stop the kernel.  This is not necessarily
the best solution since a retry of the failing instruction might succeed.  Add
logic to retry the instruction if no more than 30 instruction processing
damage checks occured in the last 5 minutes.

Signed-off-by: Heiko Carstens <heiko.carstens@de.ibm.com>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
---

diff --git a/drivers/s390/s390mach.c b/drivers/s390/s390mach.c
index 3bf4666035..5ae1480309 100644
--- a/drivers/s390/s390mach.c
+++ b/drivers/s390/s390mach.c
@@ -362,12 +362,19 @@ s390_revalidate_registers(struct mci *mci)
 	return kill_task;
 }
 
+#define MAX_IPD_COUNT	29
+#define MAX_IPD_TIME	(5 * 60 * 100 * 1000) /* 5 minutes */
+
 /*
  * machine check handler.
  */
 void
 s390_do_machine_check(struct pt_regs *regs)
 {
+	static DEFINE_SPINLOCK(ipd_lock);
+	static unsigned long long last_ipd;
+	static int ipd_count;
+	unsigned long long tmp;
 	struct mci *mci;
 	struct mcck_struct *mcck;
 	int umode;
@@ -404,11 +411,27 @@ s390_do_machine_check(struct pt_regs *regs)
 				s390_handle_damage("processing backup machine "
 						   "check with damage.");
 			}
-			if (!umode)
-				s390_handle_damage("processing backup machine "
-						   "check in kernel mode.");
-			mcck->kill_task = 1;
-			mcck->mcck_code = *(unsigned long long *) mci;
+
+			/*
+			 * Nullifying exigent condition, therefore we might
+			 * retry this instruction.
+			 */
+
+			spin_lock(&ipd_lock);
+
+			tmp = get_clock();
+
+			if (((tmp - last_ipd) >> 12) < MAX_IPD_TIME)
+				ipd_count++;
+			else
+				ipd_count = 1;
+
+			last_ipd = tmp;
+
+			if (ipd_count == MAX_IPD_COUNT)
+				s390_handle_damage("too many ipd retries.");
+
+			spin_unlock(&ipd_lock);
 		}
 		else {
 			/* Processing damage -> stopping machine */