summaryrefslogtreecommitdiffstats
path: root/arch/s390/numa
diff options
context:
space:
mode:
authorHeiko Carstens <heiko.carstens@de.ibm.com>2016-05-25 10:25:50 +0200
committerMartin Schwidefsky <schwidefsky@de.ibm.com>2016-06-13 15:58:27 +0200
commitadac0f1e8c08548d82a48c9913ebc9787f946440 (patch)
tree290e69f3e727a33b0e3a8ed8f012141f4a469b88 /arch/s390/numa
parenttopology/sysfs: provide drawer id and siblings attributes (diff)
downloadlinux-adac0f1e8c08548d82a48c9913ebc9787f946440.tar.xz
linux-adac0f1e8c08548d82a48c9913ebc9787f946440.zip
s390/topology: add drawer scheduling domain level
The z13 machine added a fourth level to the cpu topology information. The new top level is called drawer. A drawer contains two books, which used to be the top level. Adding this additional scheduling domain did show performance improvements for some workloads of up to 8%, while there don't seem to be any workloads impacted in a negative way. Signed-off-by: Heiko Carstens <heiko.carstens@de.ibm.com> Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org> Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
Diffstat (limited to 'arch/s390/numa')
-rw-r--r--arch/s390/numa/mode_emu.c25
1 files changed, 20 insertions, 5 deletions
diff --git a/arch/s390/numa/mode_emu.c b/arch/s390/numa/mode_emu.c
index 828d0695d0d4..fbc394e16b2c 100644
--- a/arch/s390/numa/mode_emu.c
+++ b/arch/s390/numa/mode_emu.c
@@ -34,7 +34,8 @@
#define DIST_CORE 1
#define DIST_MC 2
#define DIST_BOOK 3
-#define DIST_MAX 4
+#define DIST_DRAWER 4
+#define DIST_MAX 5
/* Node distance reported to common code */
#define EMU_NODE_DIST 10
@@ -43,7 +44,7 @@
#define NODE_ID_FREE -1
/* Different levels of toptree */
-enum toptree_level {CORE, MC, BOOK, NODE, TOPOLOGY};
+enum toptree_level {CORE, MC, BOOK, DRAWER, NODE, TOPOLOGY};
/* The two toptree IDs */
enum {TOPTREE_ID_PHYS, TOPTREE_ID_NUMA};
@@ -114,6 +115,14 @@ static int cores_free(struct toptree *tree)
*/
static struct toptree *core_node(struct toptree *core)
{
+ return core->parent->parent->parent->parent;
+}
+
+/*
+ * Return drawer of core
+ */
+static struct toptree *core_drawer(struct toptree *core)
+{
return core->parent->parent->parent;
}
@@ -138,6 +147,8 @@ static struct toptree *core_mc(struct toptree *core)
*/
static int dist_core_to_core(struct toptree *core1, struct toptree *core2)
{
+ if (core_drawer(core1)->id != core_drawer(core2)->id)
+ return DIST_DRAWER;
if (core_book(core1)->id != core_book(core2)->id)
return DIST_BOOK;
if (core_mc(core1)->id != core_mc(core2)->id)
@@ -262,6 +273,8 @@ static void toptree_to_numa_first(struct toptree *numa, struct toptree *phys)
struct toptree *core;
/* Always try to move perfectly fitting structures first */
+ move_level_to_numa(numa, phys, DRAWER, true);
+ move_level_to_numa(numa, phys, DRAWER, false);
move_level_to_numa(numa, phys, BOOK, true);
move_level_to_numa(numa, phys, BOOK, false);
move_level_to_numa(numa, phys, MC, true);
@@ -335,7 +348,7 @@ static struct toptree *toptree_to_numa(struct toptree *phys)
*/
static struct toptree *toptree_from_topology(void)
{
- struct toptree *phys, *node, *book, *mc, *core;
+ struct toptree *phys, *node, *drawer, *book, *mc, *core;
struct cpu_topology_s390 *top;
int cpu;
@@ -344,10 +357,11 @@ static struct toptree *toptree_from_topology(void)
for_each_online_cpu(cpu) {
top = &per_cpu(cpu_topology, cpu);
node = toptree_get_child(phys, 0);
- book = toptree_get_child(node, top->book_id);
+ drawer = toptree_get_child(node, top->drawer_id);
+ book = toptree_get_child(drawer, top->book_id);
mc = toptree_get_child(book, top->socket_id);
core = toptree_get_child(mc, top->core_id);
- if (!book || !mc || !core)
+ if (!drawer || !book || !mc || !core)
panic("NUMA emulation could not allocate memory");
cpumask_set_cpu(cpu, &core->mask);
toptree_update_mask(mc);
@@ -368,6 +382,7 @@ static void topology_add_core(struct toptree *core)
cpumask_copy(&top->thread_mask, &core->mask);
cpumask_copy(&top->core_mask, &core_mc(core)->mask);
cpumask_copy(&top->book_mask, &core_book(core)->mask);
+ cpumask_copy(&top->drawer_mask, &core_drawer(core)->mask);
cpumask_set_cpu(cpu, &node_to_cpumask_map[core_node(core)->id]);
top->node_id = core_node(core)->id;
}