sched: move rq_weight data array out of .percpu

Commit 34d76c41 introduced percpu array update_shares_data, size of which
being proportional to NR_CPUS. Unfortunately this blows up ia64 for large
NR_CPUS configuration, as ia64 allows only 64k for .percpu section.

Fix this by allocating this array dynamically and keep only pointer to it
percpu.

The per-cpu handling doesn't impose significant performance penalty on
potentially contented path in tg_shares_up().

...
ffffffff8104337c:       65 48 8b 14 25 20 cd    mov    %gs:0xcd20,%rdx
ffffffff81043383:       00 00
ffffffff81043385:       48 c7 c0 00 e1 00 00    mov    $0xe100,%rax
ffffffff8104338c:       48 c7 45 a0 00 00 00    movq   $0x0,-0x60(%rbp)
ffffffff81043393:       00
ffffffff81043394:       48 c7 45 a8 00 00 00    movq   $0x0,-0x58(%rbp)
ffffffff8104339b:       00
ffffffff8104339c:       48 01 d0                add    %rdx,%rax
ffffffff8104339f:       49 8d 94 24 08 01 00    lea    0x108(%r12),%rdx
ffffffff810433a6:       00
ffffffff810433a7:       b9 ff ff ff ff          mov    $0xffffffff,%ecx
ffffffff810433ac:       48 89 45 b0             mov    %rax,-0x50(%rbp)
ffffffff810433b0:       bb 00 04 00 00          mov    $0x400,%ebx
ffffffff810433b5:       48 89 55 c0             mov    %rdx,-0x40(%rbp)
...

After:

...
ffffffff8104337c:       65 8b 04 25 28 cd 00    mov    %gs:0xcd28,%eax
ffffffff81043383:       00
ffffffff81043384:       48 98                   cltq
ffffffff81043386:       49 8d bc 24 08 01 00    lea    0x108(%r12),%rdi
ffffffff8104338d:       00
ffffffff8104338e:       48 8b 15 d3 7f 76 00    mov    0x767fd3(%rip),%rdx        # ffffffff817ab368 <update_shares_data>
ffffffff81043395:       48 8b 34 c5 00 ee 6d    mov    -0x7e921200(,%rax,8),%rsi
ffffffff8104339c:       81
ffffffff8104339d:       48 c7 45 a0 00 00 00    movq   $0x0,-0x60(%rbp)
ffffffff810433a4:       00
ffffffff810433a5:       b9 ff ff ff ff          mov    $0xffffffff,%ecx
ffffffff810433aa:       48 89 7d c0             mov    %rdi,-0x40(%rbp)
ffffffff810433ae:       48 c7 45 a8 00 00 00    movq   $0x0,-0x58(%rbp)
ffffffff810433b5:       00
ffffffff810433b6:       bb 00 04 00 00          mov    $0x400,%ebx
ffffffff810433bb:       48 01 f2                add    %rsi,%rdx
ffffffff810433be:       48 89 55 b0             mov    %rdx,-0x50(%rbp)
...
Signed-off-by: Jiri Kosina <jkosina@suse.cz>
Acked-by: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Tejun Heo <tj@kernel.org>

kernel/sched.c

@@ -1563,11 +1563,7 @@ static unsigned long cpu_avg_load_per_task(int cpu)
 
 #ifdef CONFIG_FAIR_GROUP_SCHED
 
-struct update_shares_data {
-	unsigned long rq_weight[NR_CPUS];
-};
-
-static DEFINE_PER_CPU(struct update_shares_data, update_shares_data);
+static __read_mostly unsigned long *update_shares_data;
 
 static void __set_se_shares(struct sched_entity *se, unsigned long shares);
 
@@ -1577,12 +1573,12 @@ static void __set_se_shares(struct sched_entity *se, unsigned long shares);
 static void update_group_shares_cpu(struct task_group *tg, int cpu,
 				    unsigned long sd_shares,
 				    unsigned long sd_rq_weight,
-				    struct update_shares_data *usd)
+				    unsigned long *usd_rq_weight)
 {
 	unsigned long shares, rq_weight;
 	int boost = 0;
 
-	rq_weight = usd->rq_weight[cpu];
+	rq_weight = usd_rq_weight[cpu];
 	if (!rq_weight) {
 		boost = 1;
 		rq_weight = NICE_0_LOAD;
@@ -1617,7 +1613,7 @@ static void update_group_shares_cpu(struct task_group *tg, int cpu,
 static int tg_shares_up(struct task_group *tg, void *data)
 {
 	unsigned long weight, rq_weight = 0, shares = 0;
-	struct update_shares_data *usd;
+	unsigned long *usd_rq_weight;
 	struct sched_domain *sd = data;
 	unsigned long flags;
 	int i;
@@ -1626,11 +1622,11 @@ static int tg_shares_up(struct task_group *tg, void *data)
 		return 0;
 
 	local_irq_save(flags);
-	usd = &__get_cpu_var(update_shares_data);
+	usd_rq_weight = per_cpu_ptr(update_shares_data, smp_processor_id());
 
 	for_each_cpu(i, sched_domain_span(sd)) {
 		weight = tg->cfs_rq[i]->load.weight;
-		usd->rq_weight[i] = weight;
+		usd_rq_weight[i] = weight;
 
 		/*
 		 * If there are currently no tasks on the cpu pretend there
@@ -1651,7 +1647,7 @@ static int tg_shares_up(struct task_group *tg, void *data)
 		shares = tg->shares;
 
 	for_each_cpu(i, sched_domain_span(sd))
-		update_group_shares_cpu(tg, i, shares, rq_weight, usd);
+		update_group_shares_cpu(tg, i, shares, rq_weight, usd_rq_weight);
 
 	local_irq_restore(flags);
 
@@ -9406,6 +9402,10 @@ void __init sched_init(void)
 #endif /* CONFIG_USER_SCHED */
 #endif /* CONFIG_GROUP_SCHED */
 
+#if defined CONFIG_FAIR_GROUP_SCHED && defined CONFIG_SMP
+	update_shares_data = __alloc_percpu(nr_cpu_ids * sizeof(unsigned long),
+					    __alignof__(unsigned long));
+#endif
 	for_each_possible_cpu(i) {
 		struct rq *rq;