summaryrefslogtreecommitdiff
path: root/arch/x86
diff options
context:
space:
mode:
authorYinghai Lu <yinghai@kernel.org>2010-11-13 21:52:09 +0300
committerIngo Molnar <mingo@elte.hu>2010-11-18 12:10:50 +0300
commit9223081f54e3dc5045fe41a475165d9003c9a779 (patch)
tree8990b8655c992ad2fd4819ebbecbe0a949f5488f /arch/x86
parent96e612ffc301372d3a3b94e2cb5d1e0c1c207dd1 (diff)
downloadlinux-9223081f54e3dc5045fe41a475165d9003c9a779.tar.xz
x86: Use online node real index in calulate_tbl_offset()
Found a NUMA system that doesn't have RAM installed at the first socket which hangs while executing init scripts. bisected it to: | commit 932967202182743c01a2eee4bdfa2c42697bc586 | Author: Shaohua Li <shaohua.li@intel.com> | Date: Wed Oct 20 11:07:03 2010 +0800 | | x86: Spread tlb flush vector between nodes It turns out when first socket is not online it could have cpus on node1 tlb_offset set to bigger than NUM_INVALIDATE_TLB_VECTORS. That could affect systems like 4 sockets, but socket 2 doesn't have installed, sockets 3 will get too big tlb_offset. Need to use real online node idx. Signed-off-by: Yinghai Lu <yinghai@kernel.org> Acked-by: Shaohua Li <shaohua.li@intel.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> LKML-Reference: <4CDEDE59.40603@kernel.org> Signed-off-by: Ingo Molnar <mingo@elte.hu>
Diffstat (limited to 'arch/x86')
-rw-r--r--arch/x86/mm/tlb.c5
1 files changed, 3 insertions, 2 deletions
diff --git a/arch/x86/mm/tlb.c b/arch/x86/mm/tlb.c
index 12cdbb17ad18..6acc724d5d8f 100644
--- a/arch/x86/mm/tlb.c
+++ b/arch/x86/mm/tlb.c
@@ -223,7 +223,7 @@ void native_flush_tlb_others(const struct cpumask *cpumask,
static void __cpuinit calculate_tlb_offset(void)
{
- int cpu, node, nr_node_vecs;
+ int cpu, node, nr_node_vecs, idx = 0;
/*
* we are changing tlb_vector_offset for each CPU in runtime, but this
* will not cause inconsistency, as the write is atomic under X86. we
@@ -239,7 +239,7 @@ static void __cpuinit calculate_tlb_offset(void)
nr_node_vecs = NUM_INVALIDATE_TLB_VECTORS/nr_online_nodes;
for_each_online_node(node) {
- int node_offset = (node % NUM_INVALIDATE_TLB_VECTORS) *
+ int node_offset = (idx % NUM_INVALIDATE_TLB_VECTORS) *
nr_node_vecs;
int cpu_offset = 0;
for_each_cpu(cpu, cpumask_of_node(node)) {
@@ -248,6 +248,7 @@ static void __cpuinit calculate_tlb_offset(void)
cpu_offset++;
cpu_offset = cpu_offset % nr_node_vecs;
}
+ idx++;
}
}