From 989348b5fc2367d6880d23a1c779a90bbb6f9baf Mon Sep 17 00:00:00 2001 From: Mel Gorman Date: Mon, 7 Oct 2013 11:29:40 +0100 Subject: [PATCH] sched/numa: Use unsigned longs for numa group fault stats As Peter says "If you're going to hold locks you can also do away with all that atomic_long_*() nonsense". Lock aquisition moved slightly to protect the updates. Signed-off-by: Mel Gorman Reviewed-by: Rik van Riel Cc: Andrea Arcangeli Cc: Johannes Weiner Cc: Srikar Dronamraju Signed-off-by: Peter Zijlstra Link: http://lkml.kernel.org/r/1381141781-10992-63-git-send-email-mgorman@suse.de Signed-off-by: Ingo Molnar --- kernel/sched/fair.c | 49 ++++++++++++++++++++----------------------------- 1 file changed, 20 insertions(+), 29 deletions(-) diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index e7884dc..5b2208e 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -916,8 +916,8 @@ struct numa_group { struct list_head task_list; struct rcu_head rcu; - atomic_long_t total_faults; - atomic_long_t faults[0]; + unsigned long total_faults; + unsigned long faults[0]; }; pid_t task_numa_group_id(struct task_struct *p) @@ -944,8 +944,7 @@ static inline unsigned long group_faults(struct task_struct *p, int nid) if (!p->numa_group) return 0; - return atomic_long_read(&p->numa_group->faults[2*nid]) + - atomic_long_read(&p->numa_group->faults[2*nid+1]); + return p->numa_group->faults[2*nid] + p->numa_group->faults[2*nid+1]; } /* @@ -971,17 +970,10 @@ static inline unsigned long task_weight(struct task_struct *p, int nid) static inline unsigned long group_weight(struct task_struct *p, int nid) { - unsigned long total_faults; - - if (!p->numa_group) - return 0; - - total_faults = atomic_long_read(&p->numa_group->total_faults); - - if (!total_faults) + if (!p->numa_group || !p->numa_group->total_faults) return 0; - return 1000 * group_faults(p, nid) / total_faults; + return 1000 * group_faults(p, nid) / p->numa_group->total_faults; } static unsigned long weighted_cpuload(const int cpu); @@ -1397,9 +1389,9 @@ static void task_numa_placement(struct task_struct *p) p->total_numa_faults += diff; if (p->numa_group) { /* safe because we can only change our own group */ - atomic_long_add(diff, &p->numa_group->faults[i]); - atomic_long_add(diff, &p->numa_group->total_faults); - group_faults += atomic_long_read(&p->numa_group->faults[i]); + p->numa_group->faults[i] += diff; + p->numa_group->total_faults += diff; + group_faults += p->numa_group->faults[i]; } } @@ -1475,7 +1467,7 @@ static void task_numa_group(struct task_struct *p, int cpupid, int flags, if (unlikely(!p->numa_group)) { unsigned int size = sizeof(struct numa_group) + - 2*nr_node_ids*sizeof(atomic_long_t); + 2*nr_node_ids*sizeof(unsigned long); grp = kzalloc(size, GFP_KERNEL | __GFP_NOWARN); if (!grp) @@ -1487,9 +1479,9 @@ static void task_numa_group(struct task_struct *p, int cpupid, int flags, grp->gid = p->pid; for (i = 0; i < 2*nr_node_ids; i++) - atomic_long_set(&grp->faults[i], p->numa_faults[i]); + grp->faults[i] = p->numa_faults[i]; - atomic_long_set(&grp->total_faults, p->total_numa_faults); + grp->total_faults = p->total_numa_faults; list_add(&p->numa_entry, &grp->task_list); grp->nr_tasks++; @@ -1543,14 +1535,14 @@ unlock: if (!join) return; + double_lock(&my_grp->lock, &grp->lock); + for (i = 0; i < 2*nr_node_ids; i++) { - atomic_long_sub(p->numa_faults[i], &my_grp->faults[i]); - atomic_long_add(p->numa_faults[i], &grp->faults[i]); + my_grp->faults[i] -= p->numa_faults[i]; + grp->faults[i] += p->numa_faults[i]; } - atomic_long_sub(p->total_numa_faults, &my_grp->total_faults); - atomic_long_add(p->total_numa_faults, &grp->total_faults); - - double_lock(&my_grp->lock, &grp->lock); + my_grp->total_faults -= p->total_numa_faults; + grp->total_faults += p->total_numa_faults; list_move(&p->numa_entry, &grp->task_list); my_grp->nr_tasks--; @@ -1571,12 +1563,11 @@ void task_numa_free(struct task_struct *p) void *numa_faults = p->numa_faults; if (grp) { + spin_lock(&grp->lock); for (i = 0; i < 2*nr_node_ids; i++) - atomic_long_sub(p->numa_faults[i], &grp->faults[i]); - - atomic_long_sub(p->total_numa_faults, &grp->total_faults); + grp->faults[i] -= p->numa_faults[i]; + grp->total_faults -= p->total_numa_faults; - spin_lock(&grp->lock); list_del(&p->numa_entry); grp->nr_tasks--; spin_unlock(&grp->lock); -- 2.7.4