From: Prarit Bhargava <prarit@redhat.com>
Date: Wed, 7 Nov 2007 11:50:17 -0500
Subject: [misc] fix bogus softlockup warnings
Message-id: 20071107165017.18571.94215.sendpatchset@prarit.boston.redhat.com
O-Subject: [RHEL 5 PATCH 1/4]: Fix bogus softlockup warnings
Bugzilla: 252360

- specific backport of Backport commit 99a19cf1c0eb22bad83fff060f08330ee9e029e2

(When dumping memory via sysrq-m it is possible to take a bogus NMI watchdog
or softlockup watchdog because the dump can take a long time on big memory
systems.

Occasionally tickle the watchdog when doing the dump. )

- the lockdep change was sent upstream several times but died on the vine.
It is not upstream, but AFAICT, is correct.

Acked-by: Alan Cox <alan@redhat.com>
Acked-by: Jarod Wilson <jwilson@redhat.com>

diff --git a/arch/ia64/mm/discontig.c b/arch/ia64/mm/discontig.c
index 2e958e6..97641ee 100644
--- a/arch/ia64/mm/discontig.c
+++ b/arch/ia64/mm/discontig.c
@@ -561,6 +561,8 @@ void show_mem(void)
 		present = pgdat->node_present_pages;
 		for(i = 0; i < pgdat->node_spanned_pages; i++) {
 			struct page *page;
+			if (unlikely(i % MAX_ORDER_NR_PAGES == 0))
+				touch_softlockup_watchdog();
 			if (pfn_valid(pgdat->node_start_pfn + i))
 				page = pfn_to_page(pgdat->node_start_pfn + i);
 			else {
diff --git a/kernel/lockdep.c b/kernel/lockdep.c
index 7644fa2..003dab5 100644
--- a/kernel/lockdep.c
+++ b/kernel/lockdep.c
@@ -2714,8 +2714,10 @@ retry:
 	printk("\n");
 	printk("=============================================\n\n");
 
-	if (unlock)
+	if (unlock) {
+		touch_all_softlockup_watchdogs();
 		read_unlock(&tasklist_lock);
+	}
 }
 
 EXPORT_SYMBOL_GPL(debug_show_all_locks);