From: Per Øyvind Karlsen <pkarlsen@xxxxxxxxxxxx>
Date: Fri, 28 Apr 2006 00:42:07 +0200
> When running 2.6.17-rc1 or rc2 I seem to get a lot of these oops, not certain
> about what exactly causes those, but might seem to happen during a little
> load..
> 2.6.16 runs fine without this ever happening.
>
> Machine is a blade 100..
I did some investigating. Do you have preemption enabled? That's the
only way this bug could possibly trigger.
Jim reported a nearly identical OOPS to your's and his provided config
has preemption enabled.
This patch should fix the problem:
diff --git a/arch/sparc64/mm/tlb.c b/arch/sparc64/mm/tlb.c
index a079cf4..3f10fc9 100644
--- a/arch/sparc64/mm/tlb.c
+++ b/arch/sparc64/mm/tlb.c
@@ -8,6 +8,7 @@ #include <linux/init.h>
#include <linux/percpu.h>
#include <linux/mm.h>
#include <linux/swap.h>
+#include <linux/preempt.h>
#include <asm/pgtable.h>
#include <asm/pgalloc.h>
@@ -24,6 +25,8 @@ void flush_tlb_pending(void)
{
struct mmu_gather *mp = &__get_cpu_var(mmu_gathers);
+ preempt_disable();
+
if (mp->tlb_nr) {
flush_tsb_user(mp);
@@ -38,6 +41,8 @@ #endif
}
mp->tlb_nr = 0;
}
+
+ preempt_enable();
}
void tlb_batch_add(struct mm_struct *mm, unsigned long vaddr, pte_t *ptep, pte_t orig)
-
To unsubscribe from this list: send the line "unsubscribe sparclinux" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
