From 35d5a9a61490bf39d2e48d7f499c8c801a39ebe9 Mon Sep 17 00:00:00 2001 From: Yinghai Lu Date: Fri, 15 May 2009 13:59:37 -0700 Subject: [PATCH] x86: fix system without memory on node0 Jack found a boot crash on a system which doesn't have memory on node0. It turns out with recent per_cpu changes, node_number for BSP will always be 0, and it is not consistent to cpu_to_node() that might set it to a different (nearer) node already. aka when numa_set_node() for node0 is called early before per_cpu area is setup: two places touched that per_cpu(node_number,): 1. in cpu/common.c::cpu_init() and it is not for BP | #ifdef CONFIG_NUMA | if (cpu != 0 && percpu_read(node_number) == 0 && | cpu_to_node(cpu) != NUMA_NO_NODE) | percpu_write(node_number, cpu_to_node(cpu)); | #endif for BP: traps_init ==> cpu_init for AP: start_secondary ==> cpu_init 2. cpu/intel.c or amd.c::srat_detect_node via numa_set_node() for BP: check_bugs ==> identify_boot_cpu ==> identify_cpu() that is rather later before numa_node_id() is used for BP... for AP: start_secondary => smp_callin => smp_store_cpu_info() => => identify_secondary_cpu => identify_cpu() so try to set that for BP earlier in setup_per_cpu_areas(), and don't bother to set that for APs there (it will be updated later and will be used later) (and don't mess the 0 before the copying BP per_cpu data to APs) [ Impact: fix boot crash on memoryless node-0 ] Reported-and-tested-by: Jack Steiner Cc: Tejun Heo Signed-off-by: Yinghai Lu LKML-Reference: <4A0C4A02.7050401@kernel.org> Signed-off-by: Ingo Molnar --- arch/x86/kernel/setup_percpu.c | 8 ++++++++ 1 file changed, 8 insertions(+) diff --git a/arch/x86/kernel/setup_percpu.c b/arch/x86/kernel/setup_percpu.c index 3a97a4cf1872..3b5f3271e730 100644 --- a/arch/x86/kernel/setup_percpu.c +++ b/arch/x86/kernel/setup_percpu.c @@ -423,6 +423,14 @@ void __init setup_per_cpu_areas(void) early_per_cpu_ptr(x86_cpu_to_node_map) = NULL; #endif +#if defined(CONFIG_X86_64) && defined(CONFIG_NUMA) + /* + * make sure boot cpu node_number is right, when boot cpu is on the + * node that doesn't have mem installed + */ + per_cpu(node_number, boot_cpu_id) = cpu_to_node(boot_cpu_id); +#endif + /* Setup node to cpumask map */ setup_node_to_cpumask_map();