powerpc/numa: On Power systems with shared configurations of CPUs
and memory, there are some issues with the association of additional
CPUs and memory to nodes when hot-adding resources. This patch
addresses some of those problems.
First, it corrects the currently broken capability to set the
topology for shared CPUs in LPARs. At boot time for shared CPU
lpars, the topology for each CPU was being set to node zero. Now
when numa_update_cpu_topology() is called appropriately, the Virtual
Processor Home Node (VPHN) capabilities information provided by the
pHyp allows the appropriate node in the shared configuration to be
selected for the CPU.
Next, it updates the initialization checks to independently recognize
PRRN or VPHN support.
Next, during hotplug CPU operations, it resets the timer on topology
update work function to a small value to better ensure that the CPU
topology is detected and configured sooner.
Also, fix an end-of-updates processing problem observed occasionally
in numa_update_cpu_topology().
Signed-off-by: Michael Bringmann <[email protected]>
Michael Bringmann (4):
powerpc/vphn: Update CPU topology when VPHN enabled
powerpc/vphn: Improve recognition of PRRN/VPHN
powerpc/hotplug: Improve responsiveness of hotplug change
powerpc/vphn: Fix numa update end-loop bug
---
Changes in V14:
-- Cleanup and compress some code after split.
powerpc/vphn: On Power systems with shared configurations of CPUs
and memory, there are some issues with the association of additional
CPUs and memory to nodes when hot-adding resources. This patch
corrects the currently broken capability to set the topology for
shared CPUs in LPARs. At boot time for shared CPU lpars, the
topology for each CPU was being set to node zero. Now when
numa_update_cpu_topology() is called appropriately, the Virtual
Processor Home Node (VPHN) capabilities information provided by the
pHyp allows the appropriate node in the shared configuration to be
selected for the CPU.
Signed-off-by: Michael Bringmann <[email protected]>
---
Changes in V14:
-- Cleanup some duplicate code. Change a trace stmt to debug.
---
arch/powerpc/mm/numa.c | 22 +++++++++++++++++++++-
1 file changed, 21 insertions(+), 1 deletion(-)
diff --git a/arch/powerpc/mm/numa.c b/arch/powerpc/mm/numa.c
index b95c584..3ae031d 100644
--- a/arch/powerpc/mm/numa.c
+++ b/arch/powerpc/mm/numa.c
@@ -1153,6 +1153,8 @@ struct topology_update_data {
static int vphn_enabled;
static int prrn_enabled;
static void reset_topology_timer(void);
+static int topology_inited;
+static int topology_update_needed;
/*
* Store the current values of the associativity change counters in the
@@ -1246,6 +1248,10 @@ 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:
+ dbg("VPHN hcall succeeded. Reset polling...\n");
+ break;
}
return rc;
@@ -1323,8 +1329,11 @@ int numa_update_cpu_topology(bool cpus_locked)
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)
@@ -1363,6 +1372,8 @@ int numa_update_cpu_topology(bool cpus_locked)
cpumask_andnot(&cpu_associativity_changes_mask,
&cpu_associativity_changes_mask,
cpu_sibling_mask(cpu));
+ dbg("Assoc chg gives same node %d for cpu%d\n",
+ new_nid, cpu);
cpu = cpu_last_thread_sibling(cpu);
continue;
}
@@ -1433,6 +1444,7 @@ int numa_update_cpu_topology(bool cpus_locked)
out:
kfree(updates);
+ topology_update_needed = 0;
return changed;
}
@@ -1613,9 +1625,17 @@ static int topology_update_init(void)
if (topology_updates_enabled)
start_topology_update();
+ if (vphn_enabled)
+ topology_schedule_update();
+
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);
powerpc/vphn: On Power systems with shared configurations of CPUs
and memory, there are some issues with the association of additional
CPUs and memory to nodes when hot-adding resources. This patch
updates the initialization checks to independently recognize PRRN
or VPHN support.
Signed-off-by: Michael Bringmann <[email protected]>
---
Changes in V14:
-- Code cleanup to reduce patch sizes
---
arch/powerpc/mm/numa.c | 8 ++++----
1 file changed, 4 insertions(+), 4 deletions(-)
diff --git a/arch/powerpc/mm/numa.c b/arch/powerpc/mm/numa.c
index 3ae031d..5f5ff46 100644
--- a/arch/powerpc/mm/numa.c
+++ b/arch/powerpc/mm/numa.c
@@ -1531,15 +1531,14 @@ 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);
@@ -1562,7 +1561,8 @@ 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);
}
powerpc/hotplug: On Power systems with shared configurations of CPUs
and memory, there are some issues with the association of additional
CPUs and memory to nodes when hot-adding resources. During hotplug
CPU operations, this patch resets the timer on topology update work
function to a small value to better ensure that the CPU topology is
detected and configured sooner.
Signed-off-by: Michael Bringmann <[email protected]>
---
Changes in V14:
-- Restore accidentally deleted reset of topology timer.
---
arch/powerpc/include/asm/topology.h | 8 ++++++++
arch/powerpc/mm/numa.c | 23 ++++++++++++++++++++++-
arch/powerpc/platforms/pseries/hotplug-cpu.c | 2 ++
3 files changed, 32 insertions(+), 1 deletion(-)
diff --git a/arch/powerpc/include/asm/topology.h b/arch/powerpc/include/asm/topology.h
index dc4e159..beb9bca 100644
--- a/arch/powerpc/include/asm/topology.h
+++ b/arch/powerpc/include/asm/topology.h
@@ -98,6 +98,14 @@ static inline int prrn_is_enabled(void)
}
#endif /* CONFIG_NUMA && CONFIG_PPC_SPLPAR */
+#if defined(CONFIG_HOTPLUG_CPU) || defined(CONFIG_NEED_MULTIPLE_NODES)
+#if defined(CONFIG_PPC_SPLPAR)
+extern int timed_topology_update(int nsecs);
+#else
+#define timed_topology_update(nsecs)
+#endif /* CONFIG_PPC_SPLPAR */
+#endif /* CONFIG_HOTPLUG_CPU || CONFIG_NEED_MULTIPLE_NODES */
+
#include <asm-generic/topology.h>
#ifdef CONFIG_SMP
diff --git a/arch/powerpc/mm/numa.c b/arch/powerpc/mm/numa.c
index 5f5ff46..32f5f8d 100644
--- a/arch/powerpc/mm/numa.c
+++ b/arch/powerpc/mm/numa.c
@@ -1148,15 +1148,35 @@ 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 = 1;
static int topology_inited;
static int topology_update_needed;
/*
+ * Change polling interval for associativity changes.
+ */
+int timed_topology_update(int nsecs)
+{
+ if (vphn_enabled) {
+ if (nsecs > 0)
+ topology_timer_secs = nsecs;
+ else
+ topology_timer_secs = TOPOLOGY_DEF_TIMER_SECS;
+
+ reset_topology_timer();
+ }
+
+ return 0;
+}
+
+/*
* Store the current values of the associativity change counters in the
* hypervisor.
*/
@@ -1251,6 +1271,7 @@ static long vphn_get_associativity(unsigned long cpu,
break;
case H_SUCCESS:
dbg("VPHN hcall succeeded. Reset polling...\n");
+ timed_topology_update(0);
break;
}
@@ -1481,7 +1502,7 @@ 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);
}
diff --git a/arch/powerpc/platforms/pseries/hotplug-cpu.c b/arch/powerpc/platforms/pseries/hotplug-cpu.c
index 6afd1ef..5a7fb1e 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;
powerpc/vphn: On Power systems with shared configurations of CPUs
and memory, there are some issues with the association of additional
CPUs and memory to nodes when hot-adding resources. This patch
fixes an end-of-updates processing problem observed occasionally
in numa_update_cpu_topology().
Signed-off-by: Michael Bringmann <[email protected]>
---
Changes in V14:
-- More code cleanup
---
arch/powerpc/mm/numa.c | 10 ++++++++--
1 file changed, 8 insertions(+), 2 deletions(-)
diff --git a/arch/powerpc/mm/numa.c b/arch/powerpc/mm/numa.c
index 32f5f8d..ec098b3 100644
--- a/arch/powerpc/mm/numa.c
+++ b/arch/powerpc/mm/numa.c
@@ -1401,16 +1401,22 @@ int numa_update_cpu_topology(bool cpus_locked)
for_each_cpu(sibling, cpu_sibling_mask(cpu)) {
ud = &updates[i++];
+ ud->next = &updates[i];
ud->cpu = sibling;
ud->new_nid = new_nid;
ud->old_nid = numa_cpu_lookup_table[sibling];
cpumask_set_cpu(sibling, &updated_cpus);
- if (i < weight)
- ud->next = &updates[i];
}
cpu = cpu_last_thread_sibling(cpu);
}
+ /*
+ * Prevent processing of 'updates' from overflowing array
+ * where last entry filled in a 'next' pointer.
+ */
+ 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) {