From 85cc5135ace4c8b75d7b4e1ea9fe15a7fcbd1516 Mon Sep 17 00:00:00 2001 From: Ravikiran G Thirumalai Date: Fri, 30 Sep 2005 11:59:22 -0700 Subject: [PATCH] x86_64 early numa init fix The tests Alok carried out on Petr's box confirmed that cpu_to_node[BP] is not setup early enough by numa_init_array due to the x86_64 changes in 2.6.14-rc*, and unfortunately set wrongly by the work around code in numa_init_array(). cpu_to_node[0] gets set with 1 early and later gets set properly to 0 during identify_cpu() when all cpus are brought up, but confusing the numa slab in the process. Here is a quick fix for this. The right fix obviously is to have cpu_to_node[bsp] setup early for numa_init_array(). The following patch will fix the problem now, and the code can stay on even when cpu_to_node{BP] gets fixed early correctly. Thanks to Petr for access to his box. Signed off by: Ravikiran Thirumalai Signed-off-by: Alok N Kataria Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/x86_64/mm/numa.c | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) (limited to 'arch/x86_64') diff --git a/arch/x86_64/mm/numa.c b/arch/x86_64/mm/numa.c index 68ad75853510..214803821001 100644 --- a/arch/x86_64/mm/numa.c +++ b/arch/x86_64/mm/numa.c @@ -167,15 +167,14 @@ void __init numa_init_array(void) mapping. To avoid this fill in the mapping for all possible CPUs, as the number of CPUs is not known yet. We round robin the existing nodes. */ - rr = 0; + rr = first_node(node_online_map); for (i = 0; i < NR_CPUS; i++) { if (cpu_to_node[i] != NUMA_NO_NODE) continue; + cpu_to_node[i] = rr; rr = next_node(rr, node_online_map); if (rr == MAX_NUMNODES) rr = first_node(node_online_map); - cpu_to_node[i] = rr; - rr++; } } -- cgit v1.2.1