[lkml]   [2009]   [Dec]   [9]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
Messages in this thread
Patch in this message
Subject[PATCH]: AMD cache - Fix stale data in shared_cpu_map cpumasks
The per_cpu cpuid4_info shared_map can contain stale data when CPUs are added
and removed.

The stale data can lead to a NULL pointer derefernce panic on a remove of a
CPU that has had siblings previously removed.

This patch resolves the panic by verifying a cpu is actually online before
adding it to the shared_cpu_map, only examining cpus that are part of
the same lower level cache, and by updating other siblings lowest level cache
maps when a cpu is added.

Signed-off-by: Prarit Bhargava <>

diff --git a/arch/x86/kernel/cpu/intel_cacheinfo.c b/arch/x86/kernel/cpu/intel_cacheinfo.c
index 0df4c2b..70df1e4 100644
--- a/arch/x86/kernel/cpu/intel_cacheinfo.c
+++ b/arch/x86/kernel/cpu/intel_cacheinfo.c
@@ -504,18 +504,19 @@ static void __cpuinit cache_shared_cpu_map_setup(unsigned int cpu, int index)
struct _cpuid4_info *this_leaf, *sibling_leaf;
unsigned long num_threads_sharing;
- int index_msb, i;
+ int index_msb, i, sibling;
struct cpuinfo_x86 *c = &cpu_data(cpu);

if ((index == 3) && (c->x86_vendor == X86_VENDOR_AMD)) {
- struct cpuinfo_x86 *d;
- for_each_online_cpu(i) {
+ for_each_cpu(i, c->llc_shared_map) {
if (!per_cpu(cpuid4_info, i))
- d = &cpu_data(i);
this_leaf = CPUID4_INFO_IDX(i, index);
- cpumask_copy(to_cpumask(this_leaf->shared_cpu_map),
- d->llc_shared_map);
+ for_each_cpu(sibling, c->llc_shared_map) {
+ if (!cpu_online(sibling))
+ continue;
+ set_bit(sibling, this_leaf->shared_cpu_map);
+ }

 \ /
  Last update: 2009-12-09 19:39    [W:0.049 / U:12.144 seconds]
©2003-2020 Jasper Spaans|hosted at Digital Ocean and TransIP|Read the blog|Advertise on this site