This is a note to let you know that I've just added the patch titled
powerpc: VPHN topology change updates all siblings
to the 3.10-stable tree which can be found at:
http://www.kernel.org/git/?p=linux/kernel/git/stable/stable-queue.git;a=summary
The filename of the patch is:
powerpc-vphn-topology-change-updates-all-siblings.patch
and it can be found in the queue-3.10 subdirectory.
If you, or anyone else, feels it should not be added to the stable tree,
please let <stable@xxxxxxxxxxxxxxx> know about it.
>From 3be7db6ab45b21345386d1a466da133b19cde5e4 Mon Sep 17 00:00:00 2001
From: Robert Jennings <rcj@xxxxxxxxxxxxxxxxxx>
Date: Wed, 24 Jul 2013 20:13:21 -0500
Subject: powerpc: VPHN topology change updates all siblings
From: Robert Jennings <rcj@xxxxxxxxxxxxxxxxxx>
commit 3be7db6ab45b21345386d1a466da133b19cde5e4 upstream.
When an associativity level change is found for one thread, the
siblings threads need to be updated as well. This is done today
for PRRN in stage_topology_update() but is missing for VPHN in
update_cpu_associativity_changes_mask(). This patch will correctly
update all thread siblings during a topology change.
Without this patch a topology update can result in a CPU in
init_sched_groups_power() getting stuck indefinitely in a loop.
This loop is built in build_sched_groups(). As a result of the thread
moving to a node separate from its siblings the struct sched_group will
have its next pointer set to point to itself rather than the sched_group
struct of the next thread. This happens because we have a domain without
the SD_OVERLAP flag, which is correct, and a topology that doesn't conform
with reality (threads on the same core assigned to different numa nodes).
When this list is traversed by init_sched_groups_power() it will reach
the thread's sched_group structure and loop indefinitely; the cpu will
be stuck at this point.
The bug was exposed when VPHN was enabled in commit b7abef0 (v3.9).
Reported-by: Jan Stancek <jstancek@xxxxxxxxxx>
Signed-off-by: Robert Jennings <rcj@xxxxxxxxxxxxxxxxxx>
Signed-off-by: Benjamin Herrenschmidt <benh@xxxxxxxxxxxxxxxxxxx>
Signed-off-by: Greg Kroah-Hartman <gregkh@xxxxxxxxxxxxxxxxxxx>
---
arch/powerpc/include/asm/smp.h | 4 ++
arch/powerpc/mm/numa.c | 59 ++++++++++++++++++++++++++++++-----------
2 files changed, 48 insertions(+), 15 deletions(-)
--- a/arch/powerpc/include/asm/smp.h
+++ b/arch/powerpc/include/asm/smp.h
@@ -145,6 +145,10 @@ extern void __cpu_die(unsigned int cpu);
#define smp_setup_cpu_maps()
static inline void inhibit_secondary_onlining(void) {}
static inline void uninhibit_secondary_onlining(void) {}
+static inline const struct cpumask *cpu_sibling_mask(int cpu)
+{
+ return cpumask_of(cpu);
+}
#endif /* CONFIG_SMP */
--- a/arch/powerpc/mm/numa.c
+++ b/arch/powerpc/mm/numa.c
@@ -27,6 +27,7 @@
#include <linux/seq_file.h>
#include <linux/uaccess.h>
#include <linux/slab.h>
+#include <asm/cputhreads.h>
#include <asm/sparsemem.h>
#include <asm/prom.h>
#include <asm/smp.h>
@@ -1319,7 +1320,8 @@ static int update_cpu_associativity_chan
}
}
if (changed) {
- cpumask_set_cpu(cpu, changes);
+ cpumask_or(changes, changes, cpu_sibling_mask(cpu));
+ cpu = cpu_last_thread_sibling(cpu);
}
}
@@ -1427,7 +1429,7 @@ static int update_cpu_topology(void *dat
if (!data)
return -EINVAL;
- cpu = get_cpu();
+ cpu = smp_processor_id();
for (update = data; update; update = update->next) {
if (cpu != update->cpu)
@@ -1447,12 +1449,12 @@ static int update_cpu_topology(void *dat
*/
int arch_update_cpu_topology(void)
{
- unsigned int cpu, changed = 0;
+ unsigned int cpu, sibling, changed = 0;
struct topology_update_data *updates, *ud;
unsigned int associativity[VPHN_ASSOC_BUFSIZE] = {0};
cpumask_t updated_cpus;
struct device *dev;
- int weight, i = 0;
+ int weight, new_nid, i = 0;
weight = cpumask_weight(&cpu_associativity_changes_mask);
if (!weight)
@@ -1465,19 +1467,46 @@ int arch_update_cpu_topology(void)
cpumask_clear(&updated_cpus);
for_each_cpu(cpu, &cpu_associativity_changes_mask) {
- ud = &updates[i++];
- ud->cpu = cpu;
- vphn_get_associativity(cpu, associativity);
- ud->new_nid = associativity_to_nid(associativity);
-
- if (ud->new_nid < 0 || !node_online(ud->new_nid))
- ud->new_nid = first_online_node;
+ /*
+ * If siblings aren't flagged for changes, updates list
+ * will be too short. Skip on this update and set for next
+ * update.
+ */
+ if (!cpumask_subset(cpu_sibling_mask(cpu),
+ &cpu_associativity_changes_mask)) {
+ pr_info("Sibling bits not set for associativity "
+ "change, cpu%d\n", cpu);
+ cpumask_or(&cpu_associativity_changes_mask,
+ &cpu_associativity_changes_mask,
+ cpu_sibling_mask(cpu));
+ cpu = cpu_last_thread_sibling(cpu);
+ continue;
+ }
- ud->old_nid = numa_cpu_lookup_table[cpu];
- cpumask_set_cpu(cpu, &updated_cpus);
+ /* Use associativity from first thread for all siblings */
+ vphn_get_associativity(cpu, associativity);
+ new_nid = associativity_to_nid(associativity);
+ if (new_nid < 0 || !node_online(new_nid))
+ new_nid = first_online_node;
+
+ if (new_nid == numa_cpu_lookup_table[cpu]) {
+ cpumask_andnot(&cpu_associativity_changes_mask,
+ &cpu_associativity_changes_mask,
+ cpu_sibling_mask(cpu));
+ cpu = cpu_last_thread_sibling(cpu);
+ continue;
+ }
- if (i < weight)
- ud->next = &updates[i];
+ for_each_cpu(sibling, cpu_sibling_mask(cpu)) {
+ ud = &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);
}
stop_machine(update_cpu_topology, &updates[0], &updated_cpus);
Patches currently in stable-queue which might be from rcj@xxxxxxxxxxxxxxxxxx are
queue-3.10/powerpc-vphn-topology-change-updates-all-siblings.patch
--
To unsubscribe from this list: send the line "unsubscribe stable" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html