On Power systems with shared configurations of CPUs and memory, there
are some issues with association of additional CPUs and memory to nodes
when hot-adding resources. These patches address some of those problems.
powerpc/hotplug: On systems like PowerPC which allow 'hot-add' of CPU
or memory resources, it may occur that the new resources are to be
inserted into nodes that were not used for these resources at bootup.
In the kernel, any node that is used must be defined and initialized
at boot. In order to meet both needs, this patch adds a new kernel
command line option (numnodes=<int>) for use by the PowerPC
architecture-specific code that defines the maximum number of nodes
that the kernel will ever need in its current hardware environment.
The boot code that initializes nodes for PowerPC will read this value
and use it to ensure that all of the desired nodes are setup in the
'node_possible_map', and elsewhere.
powerpc/numa: Correct the currently broken capability to set the
topology for shared CPUs in LPARs. At boot time for shared CPU
lpars, the topology for each shared CPU is set to node zero, however,
this is now updated correctly using the Virtual Processor Home Node
(VPHN) capabilities information provided by the pHyp. The VPHN handling
in Linux is disabled, if PRRN handling is present.
Signed-off-by: Michael Bringmann <[email protected]>
Michael Bringmann (2):
powerpc/hotplug: Add option to define max nodes allowing dynamic
growth of resources.
powerpc/numa: Update CPU topology when VPHN enabled
---
Changes in V5:
-- Add 'numnodes' kernel command line option.
powerpc/numa: Correct the currently broken capability to set the
topology for shared CPUs in LPARs. At boot time for shared CPU
lpars, the topology for each shared CPU is set to node zero, however,
this is now updated correctly using the Virtual Processor Home Node
(VPHN) capabilities information provided by the pHyp.
Also, update initialization checks for device-tree attributes to
independently recognize PRRN or VPHN usage.
Signed-off-by: Michael Bringmann <[email protected]>
---
Changes in V5:
-- Independently recognize PRRN or VPHN usage at boot time.
-- Modify interface used to trigger domain updates in shared configs.
---
arch/powerpc/include/asm/topology.h | 11 ++++
arch/powerpc/mm/numa.c | 64 +++++++++++++++++++++++---
arch/powerpc/platforms/pseries/dlpar.c | 2 +
arch/powerpc/platforms/pseries/hotplug-cpu.c | 2 +
4 files changed, 72 insertions(+), 7 deletions(-)
diff --git a/arch/powerpc/include/asm/topology.h b/arch/powerpc/include/asm/topology.h
index 8b3b46b..8b20ac4 100644
--- a/arch/powerpc/include/asm/topology.h
+++ b/arch/powerpc/include/asm/topology.h
@@ -62,6 +62,7 @@ static inline void sysfs_remove_device_from_node(struct device *dev,
#if defined(CONFIG_NUMA) && defined(CONFIG_PPC_SPLPAR)
extern int start_topology_update(void);
extern int stop_topology_update(void);
+extern int timed_topology_update(int nsecs);
extern int prrn_is_enabled(void);
#else
static inline int start_topology_update(void)
@@ -72,12 +73,22 @@ static inline int stop_topology_update(void)
{
return 0;
}
+static int timed_topology_update(int nsecs)
+{
+ return 0;
+}
static inline int prrn_is_enabled(void)
{
return 0;
}
#endif /* CONFIG_NUMA && CONFIG_PPC_SPLPAR */
+#if defined(CONFIG_PPC_SPLPAR)
+extern void shared_topology_update(void);
+#else
+#define shared_topology_update() 0
+#endif /* CONFIG_PPC_SPLPAR */
+
#include <asm-generic/topology.h>
#ifdef CONFIG_SMP
diff --git a/arch/powerpc/mm/numa.c b/arch/powerpc/mm/numa.c
index 11b04a3..6111448 100644
--- a/arch/powerpc/mm/numa.c
+++ b/arch/powerpc/mm/numa.c
@@ -29,6 +29,7 @@
#include <linux/seq_file.h>
#include <linux/uaccess.h>
#include <linux/slab.h>
+#include <linux/sched.h>
#include <asm/cputhreads.h>
#include <asm/sparsemem.h>
#include <asm/prom.h>
@@ -935,7 +936,7 @@ void __init initmem_init(void)
/*
* Reduce the possible NUMA nodes to the online NUMA nodes,
- * since we do not support node hotplug. This ensures that we
+ * since we do not support node hotplug. This ensures that we
* lower the maximum NUMA node ID to what is actually present.
*/
nodes_and(node_possible_map, node_possible_map, node_online_map);
@@ -1179,11 +1180,16 @@ struct topology_update_data {
int new_nid;
};
+#define TOPOLOGY_DEF_TIMER_SECS 60
+
static u8 vphn_cpu_change_counts[NR_CPUS][MAX_DISTANCE_REF_POINTS];
static cpumask_t cpu_associativity_changes_mask;
static int vphn_enabled;
static int prrn_enabled;
static void reset_topology_timer(void);
+static int topology_timer_secs = TOPOLOGY_DEF_TIMER_SECS;
+static int topology_inited;
+static int topology_update_needed;
/*
* Store the current values of the associativity change counters in the
@@ -1277,6 +1283,12 @@ static long vphn_get_associativity(unsigned long cpu,
"hcall_vphn() experienced a hardware fault "
"preventing VPHN. Disabling polling...\n");
stop_topology_update();
+ break;
+ case H_SUCCESS:
+ printk(KERN_INFO
+ "VPHN hcall succeeded. Reset polling...\n");
+ timed_topology_update(0);
+ break;
}
return rc;
@@ -1352,8 +1364,11 @@ int arch_update_cpu_topology(void)
struct device *dev;
int weight, new_nid, i = 0;
- if (!prrn_enabled && !vphn_enabled)
+ if (!prrn_enabled && !vphn_enabled) {
+ if (!topology_inited)
+ topology_update_needed = 1;
return 0;
+ }
weight = cpumask_weight(&cpu_associativity_changes_mask);
if (!weight)
@@ -1392,6 +1407,8 @@ int arch_update_cpu_topology(void)
cpumask_andnot(&cpu_associativity_changes_mask,
&cpu_associativity_changes_mask,
cpu_sibling_mask(cpu));
+ pr_info("Assoc chg gives same node %d for cpu%d\n",
+ new_nid, cpu);
cpu = cpu_last_thread_sibling(cpu);
continue;
}
@@ -1408,6 +1425,9 @@ int arch_update_cpu_topology(void)
cpu = cpu_last_thread_sibling(cpu);
}
+ if (i)
+ updates[i-1].next = NULL;
+
pr_debug("Topology update for the following CPUs:\n");
if (cpumask_weight(&updated_cpus)) {
for (ud = &updates[0]; ud; ud = ud->next) {
@@ -1454,6 +1474,7 @@ int arch_update_cpu_topology(void)
out:
kfree(updates);
+ topology_update_needed = 0;
return changed;
}
@@ -1468,6 +1489,14 @@ static void topology_schedule_update(void)
schedule_work(&topology_work);
}
+void shared_topology_update(void)
+{
+ if (firmware_has_feature(FW_FEATURE_VPHN) &&
+ lppaca_shared_proc(get_lppaca()))
+ topology_schedule_update();
+}
+EXPORT_SYMBOL(shared_topology_update);
+
static void topology_timer_fn(unsigned long ignored)
{
if (prrn_enabled && cpumask_weight(&cpu_associativity_changes_mask))
@@ -1484,7 +1513,7 @@ static void topology_timer_fn(unsigned long ignored)
static void reset_topology_timer(void)
{
topology_timer.data = 0;
- topology_timer.expires = jiffies + 60 * HZ;
+ topology_timer.expires = jiffies + topology_timer_secs * HZ;
mod_timer(&topology_timer, topology_timer.expires);
}
@@ -1534,15 +1563,14 @@ int start_topology_update(void)
if (firmware_has_feature(FW_FEATURE_PRRN)) {
if (!prrn_enabled) {
prrn_enabled = 1;
- vphn_enabled = 0;
#ifdef CONFIG_SMP
rc = of_reconfig_notifier_register(&dt_update_nb);
#endif
}
- } else if (firmware_has_feature(FW_FEATURE_VPHN) &&
+ }
+ if (firmware_has_feature(FW_FEATURE_VPHN) &&
lppaca_shared_proc(get_lppaca())) {
if (!vphn_enabled) {
- prrn_enabled = 0;
vphn_enabled = 1;
setup_cpu_associativity_change_counters();
init_timer_deferrable(&topology_timer);
@@ -1565,7 +1593,8 @@ int stop_topology_update(void)
#ifdef CONFIG_SMP
rc = of_reconfig_notifier_unregister(&dt_update_nb);
#endif
- } else if (vphn_enabled) {
+ }
+ if (vphn_enabled) {
vphn_enabled = 0;
rc = del_timer_sync(&topology_timer);
}
@@ -1573,6 +1602,22 @@ int stop_topology_update(void)
return rc;
}
+/*
+ * Change polling interval for associativity changes.
+ */
+int timed_topology_update(int nsecs)
+{
+ if (nsecs > 0)
+ topology_timer_secs = nsecs;
+ else
+ topology_timer_secs = TOPOLOGY_DEF_TIMER_SECS;
+
+ if (vphn_enabled)
+ reset_topology_timer();
+
+ return 0;
+}
+
int prrn_is_enabled(void)
{
return prrn_enabled;
@@ -1631,6 +1676,11 @@ static int topology_update_init(void)
if (!proc_create("powerpc/topology_updates", 0644, NULL, &topology_ops))
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);
diff --git a/arch/powerpc/platforms/pseries/dlpar.c b/arch/powerpc/platforms/pseries/dlpar.c
index bda18d8..0219cd3 100644
--- a/arch/powerpc/platforms/pseries/dlpar.c
+++ b/arch/powerpc/platforms/pseries/dlpar.c
@@ -592,6 +592,8 @@ static ssize_t dlpar_show(struct class *class, struct class_attribute *attr,
static int __init pseries_dlpar_init(void)
{
+ shared_topology_update();
+
pseries_hp_wq = alloc_workqueue("pseries hotplug workqueue",
WQ_UNBOUND, 1);
return sysfs_create_file(kernel_kobj, &class_attr_dlpar.attr);
diff --git a/arch/powerpc/platforms/pseries/hotplug-cpu.c b/arch/powerpc/platforms/pseries/hotplug-cpu.c
index 7bc0e91..96c02d0 100644
--- a/arch/powerpc/platforms/pseries/hotplug-cpu.c
+++ b/arch/powerpc/platforms/pseries/hotplug-cpu.c
@@ -356,6 +356,7 @@ static int dlpar_online_cpu(struct device_node *dn)
BUG_ON(get_cpu_current_state(cpu)
!= CPU_STATE_OFFLINE);
cpu_maps_update_done();
+ timed_topology_update(1);
rc = device_online(get_cpu_device(cpu));
if (rc)
goto out;
@@ -522,6 +523,7 @@ static int dlpar_offline_cpu(struct device_node *dn)
set_preferred_offline_state(cpu,
CPU_STATE_OFFLINE);
cpu_maps_update_done();
+ timed_topology_update(1);
rc = device_offline(get_cpu_device(cpu));
if (rc)
goto out;
Hi Michael,
[auto build test ERROR on powerpc/next]
[also build test ERROR on v4.12-rc5 next-20170616]
[if your patch is applied to the wrong git tree, please drop us a note to help improve the system]
url: https://github.com/0day-ci/linux/commits/Michael-Bringmann/powerpc-dlpar-Correct-display-of-hot-add-hot-remove-CPUs-and-memory/20170619-081809
base: https://git.kernel.org/pub/scm/linux/kernel/git/powerpc/linux.git next
config: powerpc-ksi8560_defconfig (attached as .config)
compiler: powerpc-linux-gnu-gcc (Debian 6.1.1-9) 6.1.1 20160705
reproduce:
wget https://raw.githubusercontent.com/01org/lkp-tests/master/sbin/make.cross -O ~/bin/make.cross
chmod +x ~/bin/make.cross
# save the attached .config to linux build tree
make.cross ARCH=powerpc
All errors (new ones prefixed by >>):
In file included from include/linux/topology.h:35:0,
from include/linux/gfp.h:8,
from include/linux/idr.h:16,
from include/linux/kernfs.h:14,
from include/linux/sysfs.h:15,
from include/linux/kobject.h:21,
from include/linux/of.h:21,
from include/linux/irqdomain.h:34,
from arch/powerpc/include/asm/irq.h:12,
from arch/powerpc/include/asm/prom.h:19,
from arch/powerpc/kernel/cputable.c:22:
>> arch/powerpc/include/asm/topology.h:76:12: error: 'timed_topology_update' defined but not used [-Werror=unused-function]
static int timed_topology_update(int nsecs)
^~~~~~~~~~~~~~~~~~~~~
cc1: all warnings being treated as errors
vim +/timed_topology_update +76 arch/powerpc/include/asm/topology.h
70 return 0;
71 }
72 static inline int stop_topology_update(void)
73 {
74 return 0;
75 }
> 76 static int timed_topology_update(int nsecs)
77 {
78 return 0;
79 }
---
0-DAY kernel test infrastructure Open Source Technology Center
https://lists.01.org/pipermail/kbuild-all Intel Corporation