From: "Gautham R. Shenoy" <e...@linux.vnet.ibm.com>

On POWER platforms where only some groups of threads within a core
share the L2-cache (indicated by the ibm,thread-groups device-tree
property), we currently print the incorrect shared_cpu_map/list for
L2-cache in the sysfs.

This patch reports the correct shared_cpu_map/list on such platforms.

Example:
On a platform with "ibm,thread-groups" set to
                 00000001 00000002 00000004 00000000
                 00000002 00000004 00000006 00000001
                 00000003 00000005 00000007 00000002
                 00000002 00000004 00000000 00000002
                 00000004 00000006 00000001 00000003
                 00000005 00000007

This indicates that threads {0,2,4,6} in the core share the L2-cache
and threads {1,3,5,7} in the core share the L2 cache.

However, without the patch, the shared_cpu_map/list for L2 for CPUs 0,
1 is reported in the sysfs as follows:

/sys/devices/system/cpu/cpu0/cache/index2/shared_cpu_list:0-7
/sys/devices/system/cpu/cpu0/cache/index2/shared_cpu_map:000000,000000ff

/sys/devices/system/cpu/cpu1/cache/index2/shared_cpu_list:0-7
/sys/devices/system/cpu/cpu1/cache/index2/shared_cpu_map:000000,000000ff

With the patch, the shared_cpu_map/list for L2 cache for CPUs 0, 1 is
correctly reported as follows:

/sys/devices/system/cpu/cpu0/cache/index2/shared_cpu_list:0,2,4,6
/sys/devices/system/cpu/cpu0/cache/index2/shared_cpu_map:000000,00000055

/sys/devices/system/cpu/cpu1/cache/index2/shared_cpu_list:1,3,5,7
/sys/devices/system/cpu/cpu1/cache/index2/shared_cpu_map:000000,000000aa

This patch adds #CONFIG_PPC64 checks for these cases to ensure that
32-bit configs build correctly.
Signed-off-by: Gautham R. Shenoy <e...@linux.vnet.ibm.com>
---
 arch/powerpc/kernel/cacheinfo.c | 34 ++++++++++++++++++++++++----------
 1 file changed, 24 insertions(+), 10 deletions(-)

diff --git a/arch/powerpc/kernel/cacheinfo.c b/arch/powerpc/kernel/cacheinfo.c
index 65ab9fc..cb87b68 100644
--- a/arch/powerpc/kernel/cacheinfo.c
+++ b/arch/powerpc/kernel/cacheinfo.c
@@ -641,6 +641,7 @@ static ssize_t level_show(struct kobject *k, struct 
kobj_attribute *attr, char *
 static struct kobj_attribute cache_level_attr =
        __ATTR(level, 0444, level_show, NULL);
 
+#ifdef CONFIG_PPC64
 static unsigned int index_dir_to_cpu(struct cache_index_dir *index)
 {
        struct kobject *index_dir_kobj = &index->kobj;
@@ -650,16 +651,35 @@ static unsigned int index_dir_to_cpu(struct 
cache_index_dir *index)
 
        return dev->id;
 }
+#endif
 
 /*
  * On big-core systems, each core has two groups of CPUs each of which
  * has its own L1-cache. The thread-siblings which share l1-cache with
  * @cpu can be obtained via cpu_smallcore_mask().
+ *
+ * On some big-core systems, the L2 cache is shared only between some
+ * groups of siblings. This is already parsed and encoded in
+ * cpu_l2_cache_mask().
+ *
+ * TODO: cache_lookup_or_instantiate() needs to be made aware of the
+ *       "ibm,thread-groups" property so that cache->shared_cpu_map
+ *       reflects the correct siblings on platforms that have this
+ *       device-tree property. This helper function is only a stop-gap
+ *       solution so that we report the correct siblings to the
+ *       userspace via sysfs.
  */
-static const struct cpumask *get_big_core_shared_cpu_map(int cpu, struct cache 
*cache)
+static const struct cpumask *get_shared_cpu_map(struct cache_index_dir *index, 
struct cache *cache)
 {
-       if (cache->level == 1)
-               return cpu_smallcore_mask(cpu);
+#ifdef CONFIG_PPC64
+       if (has_big_cores) {
+               int cpu = index_dir_to_cpu(index);
+               if (cache->level == 1)
+                       return cpu_smallcore_mask(cpu);
+               if (cache->level == 2 && thread_group_shares_l2)
+                       return cpu_l2_cache_mask(cpu);
+       }
+#endif
 
        return &cache->shared_cpu_map;
 }
@@ -670,17 +690,11 @@ static const struct cpumask 
*get_big_core_shared_cpu_map(int cpu, struct cache *
        struct cache_index_dir *index;
        struct cache *cache;
        const struct cpumask *mask;
-       int cpu;
 
        index = kobj_to_cache_index_dir(k);
        cache = index->cache;
 
-       if (has_big_cores) {
-               cpu = index_dir_to_cpu(index);
-               mask = get_big_core_shared_cpu_map(cpu, cache);
-       } else {
-               mask  = &cache->shared_cpu_map;
-       }
+       mask = get_shared_cpu_map(index, cache);
 
        return cpumap_print_to_pagebuf(list, buf, mask);
 }
-- 
1.9.4

Reply via email to