struct root_domain *old_rd = NULL;
unsigned long flags;
- raw_spin_lock_irqsave(&rq->lock, flags);
+ raw_spin_rq_lock_irqsave(rq, flags);
if (rq->rd) {
old_rd = rq->rd;
if (cpumask_test_cpu(rq->cpu, cpu_active_mask))
set_rq_online(rq);
- raw_spin_unlock_irqrestore(&rq->lock, flags);
+ raw_spin_rq_unlock_irqrestore(rq, flags);
if (old_rd)
call_rcu(&old_rd->rcu, free_rootdomain);
#ifdef HAVE_RT_PUSH_IPI
rd->rto_cpu = -1;
raw_spin_lock_init(&rd->rto_lock);
- init_irq_work(&rd->rto_push_work, rto_push_irq_work_func);
+ rd->rto_push_work = IRQ_WORK_INIT_HARD(rto_push_irq_work_func);
#endif
rd->visit_gen = 0;
sd = highest_flag_domain(cpu, SD_ASYM_PACKING);
rcu_assign_pointer(per_cpu(sd_asym_packing, cpu), sd);
- sd = lowest_flag_domain(cpu, SD_ASYM_CPUCAPACITY);
+ sd = lowest_flag_domain(cpu, SD_ASYM_CPUCAPACITY_FULL);
rcu_assign_pointer(per_cpu(sd_asym_cpucapacity, cpu), sd);
}
}
/*
+ * Asymmetric CPU capacity bits
+ */
+struct asym_cap_data {
+ struct list_head link;
+ unsigned long capacity;
+ unsigned long cpus[];
+};
+
+/*
+ * Set of available CPUs grouped by their corresponding capacities
+ * Each list entry contains a CPU mask reflecting CPUs that share the same
+ * capacity.
+ * The lifespan of data is unlimited.
+ */
+static LIST_HEAD(asym_cap_list);
+
+#define cpu_capacity_span(asym_data) to_cpumask((asym_data)->cpus)
+
+/*
+ * Verify whether there is any CPU capacity asymmetry in a given sched domain.
+ * Provides sd_flags reflecting the asymmetry scope.
+ */
+static inline int
+asym_cpu_capacity_classify(const struct cpumask *sd_span,
+ const struct cpumask *cpu_map)
+{
+ struct asym_cap_data *entry;
+ int count = 0, miss = 0;
+
+ /*
+ * Count how many unique CPU capacities this domain spans across
+ * (compare sched_domain CPUs mask with ones representing available
+ * CPUs capacities). Take into account CPUs that might be offline:
+ * skip those.
+ */
+ list_for_each_entry(entry, &asym_cap_list, link) {
+ if (cpumask_intersects(sd_span, cpu_capacity_span(entry)))
+ ++count;
+ else if (cpumask_intersects(cpu_map, cpu_capacity_span(entry)))
+ ++miss;
+ }
+
+ WARN_ON_ONCE(!count && !list_empty(&asym_cap_list));
+
+ /* No asymmetry detected */
+ if (count < 2)
+ return 0;
+ /* Some of the available CPU capacity values have not been detected */
+ if (miss)
+ return SD_ASYM_CPUCAPACITY;
+
+ /* Full asymmetry */
+ return SD_ASYM_CPUCAPACITY | SD_ASYM_CPUCAPACITY_FULL;
+
+}
+
+static inline void asym_cpu_capacity_update_data(int cpu)
+{
+ unsigned long capacity = arch_scale_cpu_capacity(cpu);
+ struct asym_cap_data *entry = NULL;
+
+ list_for_each_entry(entry, &asym_cap_list, link) {
+ if (capacity == entry->capacity)
+ goto done;
+ }
+
+ entry = kzalloc(sizeof(*entry) + cpumask_size(), GFP_KERNEL);
+ if (WARN_ONCE(!entry, "Failed to allocate memory for asymmetry data\n"))
+ return;
+ entry->capacity = capacity;
+ list_add(&entry->link, &asym_cap_list);
+done:
+ __cpumask_set_cpu(cpu, cpu_capacity_span(entry));
+}
+
+/*
+ * Build-up/update list of CPUs grouped by their capacities
+ * An update requires explicit request to rebuild sched domains
+ * with state indicating CPU topology changes.
+ */
+static void asym_cpu_capacity_scan(void)
+{
+ struct asym_cap_data *entry, *next;
+ int cpu;
+
+ list_for_each_entry(entry, &asym_cap_list, link)
+ cpumask_clear(cpu_capacity_span(entry));
+
+ for_each_cpu_and(cpu, cpu_possible_mask, housekeeping_cpumask(HK_FLAG_DOMAIN))
+ asym_cpu_capacity_update_data(cpu);
+
+ list_for_each_entry_safe(entry, next, &asym_cap_list, link) {
+ if (cpumask_empty(cpu_capacity_span(entry))) {
+ list_del(&entry->link);
+ kfree(entry);
+ }
+ }
+
+ /*
+ * Only one capacity value has been detected i.e. this system is symmetric.
+ * No need to keep this data around.
+ */
+ if (list_is_singular(&asym_cap_list)) {
+ entry = list_first_entry(&asym_cap_list, typeof(*entry), link);
+ list_del(&entry->link);
+ kfree(entry);
+ }
+}
+
+/*
* Initializers for schedule domains
* Non-inlined to reduce accumulated stack pressure in build_sched_domains()
*/
static int *sched_domains_numa_distance;
static struct cpumask ***sched_domains_numa_masks;
int __read_mostly node_reclaim_distance = RECLAIM_DISTANCE;
+
+static unsigned long __read_mostly *sched_numa_onlined_nodes;
#endif
/*
static struct sched_domain *
sd_init(struct sched_domain_topology_level *tl,
const struct cpumask *cpu_map,
- struct sched_domain *child, int dflags, int cpu)
+ struct sched_domain *child, int cpu)
{
struct sd_data *sdd = &tl->data;
struct sched_domain *sd = *per_cpu_ptr(sdd->sd, cpu);
int sd_id, sd_weight, sd_flags = 0;
+ struct cpumask *sd_span;
#ifdef CONFIG_NUMA
/*
"wrong sd_flags in topology description\n"))
sd_flags &= TOPOLOGY_SD_FLAGS;
- /* Apply detected topology flags */
- sd_flags |= dflags;
-
*sd = (struct sched_domain){
.min_interval = sd_weight,
.max_interval = 2*sd_weight,
#endif
};
- cpumask_and(sched_domain_span(sd), cpu_map, tl->mask(cpu));
- sd_id = cpumask_first(sched_domain_span(sd));
+ sd_span = sched_domain_span(sd);
+ cpumask_and(sd_span, cpu_map, tl->mask(cpu));
+ sd_id = cpumask_first(sd_span);
+
+ sd->flags |= asym_cpu_capacity_classify(sd_span, cpu_map);
+
+ WARN_ONCE((sd->flags & (SD_SHARE_CPUCAPACITY | SD_ASYM_CPUCAPACITY)) ==
+ (SD_SHARE_CPUCAPACITY | SD_ASYM_CPUCAPACITY),
+ "CPU capacity asymmetry not supported on SMT\n");
/*
* Convert topological properties into behaviour.
*/
-
/* Don't attempt to spread across CPUs of different capacities. */
if ((sd->flags & SD_ASYM_CPUCAPACITY) && sd->child)
sd->child->flags &= ~SD_PREFER_SIBLING;
sched_domains_numa_masks[i][j] = mask;
for_each_node(k) {
+ /*
+ * Distance information can be unreliable for
+ * offline nodes, defer building the node
+ * masks to its bringup.
+ * This relies on all unique distance values
+ * still being visible at init time.
+ */
+ if (!node_online(j))
+ continue;
+
if (sched_debug() && (node_distance(j, k) != node_distance(k, j)))
sched_numa_warn("Node-distance not symmetric");
sched_max_numa_distance = sched_domains_numa_distance[nr_levels - 1];
init_numa_topology_type();
+
+ sched_numa_onlined_nodes = bitmap_alloc(nr_node_ids, GFP_KERNEL);
+ if (!sched_numa_onlined_nodes)
+ return;
+
+ bitmap_zero(sched_numa_onlined_nodes, nr_node_ids);
+ for_each_online_node(i)
+ bitmap_set(sched_numa_onlined_nodes, i, 1);
+}
+
+static void __sched_domains_numa_masks_set(unsigned int node)
+{
+ int i, j;
+
+ /*
+ * NUMA masks are not built for offline nodes in sched_init_numa().
+ * Thus, when a CPU of a never-onlined-before node gets plugged in,
+ * adding that new CPU to the right NUMA masks is not sufficient: the
+ * masks of that CPU's node must also be updated.
+ */
+ if (test_bit(node, sched_numa_onlined_nodes))
+ return;
+
+ bitmap_set(sched_numa_onlined_nodes, node, 1);
+
+ for (i = 0; i < sched_domains_numa_levels; i++) {
+ for (j = 0; j < nr_node_ids; j++) {
+ if (!node_online(j) || node == j)
+ continue;
+
+ if (node_distance(j, node) > sched_domains_numa_distance[i])
+ continue;
+
+ /* Add remote nodes in our masks */
+ cpumask_or(sched_domains_numa_masks[i][node],
+ sched_domains_numa_masks[i][node],
+ sched_domains_numa_masks[0][j]);
+ }
+ }
+
+ /*
+ * A new node has been brought up, potentially changing the topology
+ * classification.
+ *
+ * Note that this is racy vs any use of sched_numa_topology_type :/
+ */
+ init_numa_topology_type();
}
void sched_domains_numa_masks_set(unsigned int cpu)
int node = cpu_to_node(cpu);
int i, j;
+ __sched_domains_numa_masks_set(node);
+
for (i = 0; i < sched_domains_numa_levels; i++) {
for (j = 0; j < nr_node_ids; j++) {
+ if (!node_online(j))
+ continue;
+
+ /* Set ourselves in the remote node's masks */
if (node_distance(j, node) <= sched_domains_numa_distance[i])
cpumask_set_cpu(cpu, sched_domains_numa_masks[i][j]);
}
static struct sched_domain *build_sched_domain(struct sched_domain_topology_level *tl,
const struct cpumask *cpu_map, struct sched_domain_attr *attr,
- struct sched_domain *child, int dflags, int cpu)
+ struct sched_domain *child, int cpu)
{
- struct sched_domain *sd = sd_init(tl, cpu_map, child, dflags, cpu);
+ struct sched_domain *sd = sd_init(tl, cpu_map, child, cpu);
if (child) {
sd->level = child->level + 1;
}
/*
- * Find the sched_domain_topology_level where all CPU capacities are visible
- * for all CPUs.
- */
-static struct sched_domain_topology_level
-*asym_cpu_capacity_level(const struct cpumask *cpu_map)
-{
- int i, j, asym_level = 0;
- bool asym = false;
- struct sched_domain_topology_level *tl, *asym_tl = NULL;
- unsigned long cap;
-
- /* Is there any asymmetry? */
- cap = arch_scale_cpu_capacity(cpumask_first(cpu_map));
-
- for_each_cpu(i, cpu_map) {
- if (arch_scale_cpu_capacity(i) != cap) {
- asym = true;
- break;
- }
- }
-
- if (!asym)
- return NULL;
-
- /*
- * Examine topology from all CPU's point of views to detect the lowest
- * sched_domain_topology_level where a highest capacity CPU is visible
- * to everyone.
- */
- for_each_cpu(i, cpu_map) {
- unsigned long max_capacity = arch_scale_cpu_capacity(i);
- int tl_id = 0;
-
- for_each_sd_topology(tl) {
- if (tl_id < asym_level)
- goto next_level;
-
- for_each_cpu_and(j, tl->mask(i), cpu_map) {
- unsigned long capacity;
-
- capacity = arch_scale_cpu_capacity(j);
-
- if (capacity <= max_capacity)
- continue;
-
- max_capacity = capacity;
- asym_level = tl_id;
- asym_tl = tl;
- }
-next_level:
- tl_id++;
- }
- }
-
- return asym_tl;
-}
-
-
-/*
* Build sched domains for a given set of CPUs and attach the sched domains
* to the individual CPUs
*/
struct s_data d;
struct rq *rq = NULL;
int i, ret = -ENOMEM;
- struct sched_domain_topology_level *tl_asym;
bool has_asym = false;
if (WARN_ON(cpumask_empty(cpu_map)))
if (alloc_state != sa_rootdomain)
goto error;
- tl_asym = asym_cpu_capacity_level(cpu_map);
-
/* Set up domains for CPUs specified by the cpu_map: */
for_each_cpu(i, cpu_map) {
struct sched_domain_topology_level *tl;
- int dflags = 0;
sd = NULL;
for_each_sd_topology(tl) {
- if (tl == tl_asym) {
- dflags |= SD_ASYM_CPUCAPACITY;
- has_asym = true;
- }
if (WARN_ON(!topology_span_sane(tl, cpu_map, i)))
goto error;
- sd = build_sched_domain(tl, cpu_map, attr, sd, dflags, i);
+ sd = build_sched_domain(tl, cpu_map, attr, sd, i);
+
+ has_asym |= sd->flags & SD_ASYM_CPUCAPACITY;
if (tl == sched_domain_topology)
*per_cpu_ptr(d.sd, i) = sd;
zalloc_cpumask_var(&fallback_doms, GFP_KERNEL);
arch_update_cpu_topology();
+ asym_cpu_capacity_scan();
ndoms_cur = 1;
doms_cur = alloc_sched_domains(ndoms_cur);
if (!doms_cur)
/* Let the architecture update CPU core mappings: */
new_topology = arch_update_cpu_topology();
+ /* Trigger rebuilding CPU capacity asymmetry data */
+ if (new_topology)
+ asym_cpu_capacity_scan();
if (!doms_new) {
WARN_ON_ONCE(dattr_new);