@@ -43,6 +43,7 @@ extern void __init dump_numa_cpu_topology(void);
extern int sysfs_add_device_to_node(struct device *dev, int nid);
extern void sysfs_remove_device_from_node(struct device *dev, int nid);
extern int numa_update_cpu_topology(bool cpus_locked);
+extern void check_topology_updates(void);
static inline void update_numa_cpu_lookup_table(unsigned int cpu, int node)
{
@@ -84,6 +85,9 @@ static inline int numa_update_cpu_topology(bool cpus_locked)
static inline void update_numa_cpu_lookup_table(unsigned int cpu, int node) {}
+static void check_topology_updates(void)
+{
+}
#endif /* CONFIG_NUMA */
#if defined(CONFIG_NUMA) && defined(CONFIG_PPC_SPLPAR)
@@ -1156,6 +1156,12 @@ void __init smp_cpus_done(unsigned int max_cpus)
if (smp_ops && smp_ops->bringup_done)
smp_ops->bringup_done();
+ /*
+ * On a shared LPAR, associativity needs to be requested.
+ * Hence, check for numa topology updates before dumping
+ * cpu topology
+ */
+ check_topology_updates();
dump_numa_cpu_topology();
/*
@@ -1515,6 +1515,7 @@ int start_topology_update(void)
lppaca_shared_proc(get_lppaca())) {
if (!vphn_enabled) {
vphn_enabled = 1;
+ topology_update_needed = 1;
setup_cpu_associativity_change_counters();
timer_setup(&topology_timer, topology_timer_fn,
TIMER_DEFERRABLE);
@@ -1551,6 +1552,19 @@ int prrn_is_enabled(void)
return prrn_enabled;
}
+void check_topology_updates(void)
+{
+ /* Do not poll for changes if disabled at boot */
+ if (topology_updates_enabled)
+ start_topology_update();
+
+ if (topology_update_needed) {
+ bitmap_fill(cpumask_bits(&cpu_associativity_changes_mask),
+ nr_cpumask_bits);
+ numa_update_cpu_topology(false);
+ }
+}
+
static int topology_read(struct seq_file *file, void *v)
{
if (vphn_enabled || prrn_enabled)
@@ -1597,10 +1611,6 @@ static const struct file_operations topology_ops = {
static int topology_update_init(void)
{
- /* Do not poll for changes if disabled at boot */
- if (topology_updates_enabled)
- start_topology_update();
-
if (vphn_enabled)
topology_schedule_update();
@@ -1608,10 +1618,6 @@ static int topology_update_init(void)
return -ENOMEM;
topology_inited = 1;
- if (topology_update_needed)
- bitmap_fill(cpumask_bits(&cpu_associativity_changes_mask),
- nr_cpumask_bits);
-
return 0;
}
device_initcall(topology_update_init);
On a shared lpar, Phyp will not update the cpu associativity at boot time. Just after the boot system does recognize itself as a shared lpar and trigger a request for correct cpu associativity. But by then the scheduler would have already created/destroyed its sched domains. This causes - Broken load balance across Nodes causing islands of cores. - Performance degradation esp if the system is lightly loaded - dmesg to wrongly report all cpus to be in Node 0. - Messages in dmesg saying borken topology. - With commit 051f3ca02e46 ("sched/topology: Introduce NUMA identity node sched domain"), can cause rcu stalls at boot up. From a scheduler maintainer's perspective, moving cpus from one node to another or creating more numa levels after boot is not appropriate without some notification to the user space. https://lore.kernel.org/lkml/20150406214558.GA38501@linux.vnet.ibm.com/T/#u The sched_domains_numa_masks table which is used to generate cpumasks is only created at boot time just before creating sched domains and never updated. Hence, its better to get the topology correct before the sched domains are created. For example on 64 core Power 8 shared lpar, dmesg reports [ 2.088360] Brought up 512 CPUs [ 2.088368] Node 0 CPUs: 0-511 [ 2.088371] Node 1 CPUs: [ 2.088373] Node 2 CPUs: [ 2.088375] Node 3 CPUs: [ 2.088376] Node 4 CPUs: [ 2.088378] Node 5 CPUs: [ 2.088380] Node 6 CPUs: [ 2.088382] Node 7 CPUs: [ 2.088386] Node 8 CPUs: [ 2.088388] Node 9 CPUs: [ 2.088390] Node 10 CPUs: [ 2.088392] Node 11 CPUs: ... [ 3.916091] BUG: arch topology borken [ 3.916103] the DIE domain not a subset of the NUMA domain [ 3.916105] BUG: arch topology borken [ 3.916106] the DIE domain not a subset of the NUMA domain ... numactl/lscpu output will still be correct with cores spreading across all nodes. Socket(s): 64 NUMA node(s): 12 Model: 2.0 (pvr 004d 0200) Model name: POWER8 (architected), altivec supported Hypervisor vendor: pHyp Virtualization type: para L1d cache: 64K L1i cache: 32K NUMA node0 CPU(s): 0-7,32-39,64-71,96-103,176-183,272-279,368-375,464-471 NUMA node1 CPU(s): 8-15,40-47,72-79,104-111,184-191,280-287,376-383,472-479 NUMA node2 CPU(s): 16-23,48-55,80-87,112-119,192-199,288-295,384-391,480-487 NUMA node3 CPU(s): 24-31,56-63,88-95,120-127,200-207,296-303,392-399,488-495 NUMA node4 CPU(s): 208-215,304-311,400-407,496-503 NUMA node5 CPU(s): 168-175,264-271,360-367,456-463 NUMA node6 CPU(s): 128-135,224-231,320-327,416-423 NUMA node7 CPU(s): 136-143,232-239,328-335,424-431 NUMA node8 CPU(s): 216-223,312-319,408-415,504-511 NUMA node9 CPU(s): 144-151,240-247,336-343,432-439 NUMA node10 CPU(s): 152-159,248-255,344-351,440-447 NUMA node11 CPU(s): 160-167,256-263,352-359,448-455 Currently on this lpar, the scheduler detects 2 levels of Numa and created numa sched domains for all cpus, but it finds a single DIE domain consisting of all cpus. Hence it deletes all numa sched domains. To address this, split the topology update init, such that the first part detects vphn/prrn soon after cpus are setup and force updates topology just before scheduler creates sched domain. With the fix, dmesg reports [ 0.491336] numa: Node 0 CPUs: 0-7 32-39 64-71 96-103 176-183 272-279 368-375 464-471 [ 0.491351] numa: Node 1 CPUs: 8-15 40-47 72-79 104-111 184-191 280-287 376-383 472-479 [ 0.491359] numa: Node 2 CPUs: 16-23 48-55 80-87 112-119 192-199 288-295 384-391 480-487 [ 0.491366] numa: Node 3 CPUs: 24-31 56-63 88-95 120-127 200-207 296-303 392-399 488-495 [ 0.491374] numa: Node 4 CPUs: 208-215 304-311 400-407 496-503 [ 0.491379] numa: Node 5 CPUs: 168-175 264-271 360-367 456-463 [ 0.491384] numa: Node 6 CPUs: 128-135 224-231 320-327 416-423 [ 0.491389] numa: Node 7 CPUs: 136-143 232-239 328-335 424-431 [ 0.491394] numa: Node 8 CPUs: 216-223 312-319 408-415 504-511 [ 0.491399] numa: Node 9 CPUs: 144-151 240-247 336-343 432-439 [ 0.491404] numa: Node 10 CPUs: 152-159 248-255 344-351 440-447 [ 0.491409] numa: Node 11 CPUs: 160-167 256-263 352-359 448-455 and lscpu would also report Socket(s): 64 NUMA node(s): 12 Model: 2.0 (pvr 004d 0200) Model name: POWER8 (architected), altivec supported Hypervisor vendor: pHyp Virtualization type: para L1d cache: 64K L1i cache: 32K NUMA node0 CPU(s): 0-7,32-39,64-71,96-103,176-183,272-279,368-375,464-471 NUMA node1 CPU(s): 8-15,40-47,72-79,104-111,184-191,280-287,376-383,472-479 NUMA node2 CPU(s): 16-23,48-55,80-87,112-119,192-199,288-295,384-391,480-487 NUMA node3 CPU(s): 24-31,56-63,88-95,120-127,200-207,296-303,392-399,488-495 NUMA node4 CPU(s): 208-215,304-311,400-407,496-503 NUMA node5 CPU(s): 168-175,264-271,360-367,456-463 NUMA node6 CPU(s): 128-135,224-231,320-327,416-423 NUMA node7 CPU(s): 136-143,232-239,328-335,424-431 NUMA node8 CPU(s): 216-223,312-319,408-415,504-511 NUMA node9 CPU(s): 144-151,240-247,336-343,432-439 NUMA node10 CPU(s): 152-159,248-255,344-351,440-447 NUMA node11 CPU(s): 160-167,256-263,352-359,448-455 Previous attempt to solve this problem https://patchwork.ozlabs.org/patch/530090/ Reported-by: Manjunatha H R <manjuhr1@in.ibm.com> Signed-off-by: Srikar Dronamraju <srikar@linux.vnet.ibm.com> --- Changelog v1->v2: Fix compile warnings and checkpatch issues. arch/powerpc/include/asm/topology.h | 4 ++++ arch/powerpc/kernel/smp.c | 6 ++++++ arch/powerpc/mm/numa.c | 22 ++++++++++++++-------- 3 files changed, 24 insertions(+), 8 deletions(-)