A coworker was seeing the same symptoms on a system from the
same-era & loaned me the system to debug. The issue ended up being
due to a change in the SRAT table, and a backport of the following
fixed it for me.
I've committed it to the lenny branch - would you be able to test it?
commit 4c31e92b97b6d7e7b19ee5e54a22571ffdebb305
Author: Yinghai Lu <ying...@...>
Date: Wed Apr 22 14:19:27 2009 -0700
x86: check boundary in setup_node_bootmem()
Commit dc09855 ("x86/uv: fix init of memory-less nodes") causes a
two sockets system (where node-1 doesn't have RAM installed) to crash.
That commit makes node_possible include cpu nodes that do not have memory.
So check boundary in setup_node_bootmem().
[ Impact: fix boot crash on RAM-less NUMA node system ]
Signed-off-by: Yinghai Lu <ying...@...>
Cc: Jack Steiner <stei...@...>
LKML-Reference: <49ef89df.9090...@...>
Signed-off-by: Ingo Molnar <mi...@...>
diff --git a/arch/x86/mm/numa_64.c b/arch/x86/mm/numa_64.c
index d73aaa8..2d05a12 100644
--- a/arch/x86/mm/numa_64.c
+++ b/arch/x86/mm/numa_64.c
@@ -188,6 +188,9 @@ void __init setup_node_bootmem(int nodeid, unsigned long
start,
const int pgdat_size = roundup(sizeof(pg_data_t), PAGE_SIZE);
int nid;
+ if (!end)
+ return;
+
start = roundup(start, ZONE_ALIGN);
printk(KERN_INFO "Bootmem setup node %d %016lx-%016lx\n", nodeid,
--
To UNSUBSCRIBE, email to debian-kernel-requ...@lists.debian.org
with a subject of "unsubscribe". Trouble? Contact listmas...@lists.debian.org
Archive: http://lists.debian.org/20100311070642.gc13...@ldl.fc.hp.com
