sched: convert struct cpupri_vec cpumask_var_t.

Impact: stack usage reduction, (future) size reduction for large NR_CPUS.

Dynamically allocating cpumasks (when CONFIG_CPUMASK_OFFSTACK) saves
space for small nr_cpu_ids but big CONFIG_NR_CPUS.

The fact cpupro_init is called both before and after the slab is
available makes for an ugly parameter unfortunately.

We also use cpumask_any_and to get rid of a temporary in cpupri_find.

Signed-off-by: Rusty Russell <rusty@rustcorp.com.au>
Signed-off-by: Ingo Molnar <mingo@elte.hu>

3 files changed, 38 insertions, 15 deletions

diff --git a/kernel/sched.c b/kernel/sched.c
index 42588ad..94fa333 100644
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -6792,6 +6792,8 @@ sd_parent_degenerate(struct sched_domain *sd, struct sched_domain *parent)
 
 static void free_rootdomain(struct root_domain *rd)
 {
+	cpupri_cleanup(&rd->cpupri);
+
 	free_cpumask_var(rd->rto_mask);
 	free_cpumask_var(rd->online);
 	free_cpumask_var(rd->span);
@@ -6834,7 +6836,7 @@ static int init_rootdomain(struct root_domain *rd, bool bootmem)
 		alloc_bootmem_cpumask_var(&def_root_domain.span);
 		alloc_bootmem_cpumask_var(&def_root_domain.online);
 		alloc_bootmem_cpumask_var(&def_root_domain.rto_mask);
-		cpupri_init(&rd->cpupri);
+		cpupri_init(&rd->cpupri, true);
 		return 0;
 	}
 
@@ -6845,9 +6847,12 @@ static int init_rootdomain(struct root_domain *rd, bool bootmem)
 	if (!alloc_cpumask_var(&rd->rto_mask, GFP_KERNEL))
 		goto free_online;
 
-	cpupri_init(&rd->cpupri);
+	if (cpupri_init(&rd->cpupri, false) != 0)
+		goto free_rto_mask;
 	return 0;
 
+free_rto_mask:
+	free_cpumask_var(rd->rto_mask);
 free_online:
 	free_cpumask_var(rd->online);
 free_span:
diff --git a/kernel/sched_cpupri.c b/kernel/sched_cpupri.c
index 52154fe..018b7be 100644
--- a/kernel/sched_cpupri.c
+++ b/kernel/sched_cpupri.c
@@ -67,24 +67,21 @@ static int convert_prio(int prio)
  * Returns: (int)bool - CPUs were found
  */
 int cpupri_find(struct cpupri *cp, struct task_struct *p,
-		cpumask_t *lowest_mask)
+		struct cpumask *lowest_mask)
 {
 	int                  idx      = 0;
 	int                  task_pri = convert_prio(p->prio);
 
 	for_each_cpupri_active(cp->pri_active, idx) {
 		struct cpupri_vec *vec  = &cp->pri_to_cpu[idx];
-		cpumask_t mask;
 
 		if (idx >= task_pri)
 			break;
 
-		cpus_and(mask, p->cpus_allowed, vec->mask);
-
-		if (cpus_empty(mask))
+		if (cpumask_any_and(&p->cpus_allowed, vec->mask) >= nr_cpu_ids)
 			continue;
 
-		*lowest_mask = mask;
+		cpumask_and(lowest_mask, &p->cpus_allowed, vec->mask);
 		return 1;
 	}
 
@@ -126,7 +123,7 @@ void cpupri_set(struct cpupri *cp, int cpu, int newpri)
 		vec->count--;
 		if (!vec->count)
 			clear_bit(oldpri, cp->pri_active);
-		cpu_clear(cpu, vec->mask);
+		cpumask_clear_cpu(cpu, vec->mask);
 
 		spin_unlock_irqrestore(&vec->lock, flags);
 	}
@@ -136,7 +133,7 @@ void cpupri_set(struct cpupri *cp, int cpu, int newpri)
 
 		spin_lock_irqsave(&vec->lock, flags);
 
-		cpu_set(cpu, vec->mask);
+		cpumask_set_cpu(cpu, vec->mask);
 		vec->count++;
 		if (vec->count == 1)
 			set_bit(newpri, cp->pri_active);
@@ -150,10 +147,11 @@ void cpupri_set(struct cpupri *cp, int cpu, int newpri)
 /**
  * cpupri_init - initialize the cpupri structure
  * @cp: The cpupri context
+ * @bootmem: true if allocations need to use bootmem
  *
- * Returns: (void)
+ * Returns: -ENOMEM if memory fails.
  */
-void cpupri_init(struct cpupri *cp)
+int cpupri_init(struct cpupri *cp, bool bootmem)
 {
 	int i;
 
@@ -164,11 +162,30 @@ void cpupri_init(struct cpupri *cp)
 
 		spin_lock_init(&vec->lock);
 		vec->count = 0;
-		cpus_clear(vec->mask);
+		if (bootmem)
+			alloc_bootmem_cpumask_var(&vec->mask);
+		else if (!alloc_cpumask_var(&vec->mask, GFP_KERNEL))
+			goto cleanup;
 	}
 
 	for_each_possible_cpu(i)
 		cp->cpu_to_pri[i] = CPUPRI_INVALID;
+	return 0;
+
+cleanup:
+	for (i--; i >= 0; i--)
+		free_cpumask_var(cp->pri_to_cpu[i].mask);
+	return -ENOMEM;
 }
 
+/**
+ * cpupri_cleanup - clean up the cpupri structure
+ * @cp: The cpupri context
+ */
+void cpupri_cleanup(struct cpupri *cp)
+{
+	int i;
 
+	for (i = 0; i < CPUPRI_NR_PRIORITIES; i++)
+		free_cpumask_var(cp->pri_to_cpu[i].mask);
+}
diff --git a/kernel/sched_cpupri.h b/kernel/sched_cpupri.h
index f25811b0..642a94e 100644
--- a/kernel/sched_cpupri.h
+++ b/kernel/sched_cpupri.h
@@ -14,7 +14,7 @@
 struct cpupri_vec {
 	spinlock_t lock;
 	int        count;
-	cpumask_t  mask;
+	cpumask_var_t mask;
 };
 
 struct cpupri {
@@ -27,7 +27,8 @@ struct cpupri {
 int  cpupri_find(struct cpupri *cp,
 		 struct task_struct *p, cpumask_t *lowest_mask);
 void cpupri_set(struct cpupri *cp, int cpu, int pri);
-void cpupri_init(struct cpupri *cp);
+int cpupri_init(struct cpupri *cp, bool bootmem);
+void cpupri_cleanup(struct cpupri *cp);
 #else
 #define cpupri_set(cp, cpu, pri) do { } while (0)
 #define cpupri_init() do { } while (0)