Re: Commit 34d76c41 causes linker errors on ia64 with NR_CPUS=4096

[Jeff Mahoney <jeffm@suse.com>]

On 10/20/2009 10:18 AM, Jeff Mahoney wrote:
> On 10/20/2009 02:27 AM, Jiri Kosina wrote:
>> @@ -1627,11 +1623,10 @@ static int tg_shares_up(struct task_group *tg, void *data)
>>  		return 0;
>>  
>>  	local_irq_save(flags);
>> -	usd = &__get_cpu_var(update_shares_data);
>>  
>>  	for_each_cpu(i, sched_domain_span(sd)) {
>>  		weight = tg->cfs_rq[i]->load.weight;
>> -		usd->rq_weight[i] = weight;
>> +		usd = *per_cpu_ptr(update_shares_data, i) = weight;
>>  
>>  		/*
>>  		 * If there are currently no tasks on the cpu pretend there
> 
> I don't think this is what you want here.
> 
> In the original version, usd is the percpu var using the current cpu. In
> your version, usd is the percpu var using i instead of the current cpu.
> 
> I'll post my version of the patch shortly. I don't think keeping most of
> the original version is a bad thing. We can just allocate it dynamically
> instead.

This version fixes a build issue (__alignof__(unsigned long)) and fixes the
percpu lookup to be usd = percpu array pointer, usd[i] = actual variable.

-Jeff

From: Jiri Kosina <jkosina@suse.cz>
Subject: 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.

Signed-off-by: Jiri Kosina <jkosina@suse.cz>
--- 
 kernel/sched.c |   20 ++++++++++----------
 1 file changed, 10 insertions(+), 10 deletions(-)

--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -1564,11 +1564,7 @@ static unsigned long cpu_avg_load_per_ta
 
 #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);
+unsigned long *update_shares_data;
 
 static void __set_se_shares(struct sched_entity *se, unsigned long shares);
 
@@ -1578,12 +1574,12 @@ static void __set_se_shares(struct sched
 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)
 {
 	unsigned long shares, rq_weight;
 	int boost = 0;
 
-	rq_weight = usd->rq_weight[cpu];
+	rq_weight = usd[cpu];
 	if (!rq_weight) {
 		boost = 1;
 		rq_weight = NICE_0_LOAD;
@@ -1618,7 +1614,7 @@ static void update_group_shares_cpu(stru
 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;
 	struct sched_domain *sd = data;
 	unsigned long flags;
 	int i;
@@ -1627,11 +1623,11 @@ static int tg_shares_up(struct task_grou
 		return 0;
 
 	local_irq_save(flags);
-	usd = &__get_cpu_var(update_shares_data);
+	usd = 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[i] = weight;
 
 		/*
 		 * If there are currently no tasks on the cpu pretend there
@@ -9407,6 +9403,10 @@ void __init sched_init(void)
 #endif /* CONFIG_USER_SCHED */
 #endif /* CONFIG_GROUP_SCHED */
 
+#ifdef CONFIG_FAIR_GROUP_SCHED
+	update_shares_data = __alloc_percpu(nr_cpu_ids * sizeof(unsigned long),
+					    __alignof__(unsigned long));
+#endif
 	for_each_possible_cpu(i) {
 		struct rq *rq;
 
 

-- 
Jeff Mahoney
SUSE Labs