Commit-ID: f9c57f07a41a259aa5b6185e962572330cd31fbf Gitweb: http://git.kernel.org/tip/f9c57f07a41a259aa5b6185e962572330cd31fbf Author: Peter Zijlstra <a.p.zijlstra@xxxxxxxxx> AuthorDate: Mon, 5 Mar 2012 13:24:34 +0100 Committer: Ingo Molnar <mingo@xxxxxxxxxx> CommitDate: Fri, 18 May 2012 08:16:24 +0200 sched/numa: Abstract out the struct numa_entity some more In order to prepare the NUMA balancer for non-process entities, add further abstraction to the thing. Signed-off-by: Peter Zijlstra <a.p.zijlstra@xxxxxxxxx> Cc: Suresh Siddha <suresh.b.siddha@xxxxxxxxx> Cc: Paul Turner <pjt@xxxxxxxxxx> Cc: Dan Smith <danms@xxxxxxxxxx> Cc: Bharata B Rao <bharata.rao@xxxxxxxxx> Cc: Lee Schermerhorn <Lee.Schermerhorn@xxxxxx> Cc: Christoph Lameter <cl@xxxxxxxxx> Cc: Rik van Riel <riel@xxxxxxxxxx> Cc: Andrea Arcangeli <aarcange@xxxxxxxxxx> Cc: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx> Cc: Linus Torvalds <torvalds@xxxxxxxxxxxxxxxxxxxx> Link: http://lkml.kernel.org/n/tip-edy9lbaowd8f3sud2xf656wg@xxxxxxxxxxxxxx Signed-off-by: Ingo Molnar <mingo@xxxxxxxxxx> --- include/linux/mm_types.h | 5 ++- kernel/sched/numa.c | 85 +++++++++++++++++++++++++++++----------------- 2 files changed, 57 insertions(+), 33 deletions(-) diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index 6a85ad7..9b98193 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -287,8 +287,9 @@ struct mm_rss_stat { struct numa_entity { #ifdef CONFIG_NUMA - int node; /* home node */ - struct list_head numa_entry; /* balance list */ + int node; /* home node */ + struct list_head numa_entry; /* balance list */ + const struct numa_ops *nops; #endif }; diff --git a/kernel/sched/numa.c b/kernel/sched/numa.c index 99585d5..6088165 100644 --- a/kernel/sched/numa.c +++ b/kernel/sched/numa.c @@ -20,6 +20,17 @@ static const int numa_balance_interval = 2 * HZ; /* 2 seconds */ +struct numa_ops { + unsigned long (*mem_load)(struct numa_entity *ne); + unsigned long (*cpu_load)(struct numa_entity *ne); + + void (*mem_migrate)(struct numa_entity *ne, int node); + void (*cpu_migrate)(struct numa_entity *ne, int node); + + bool (*tryget)(struct numa_entity *ne); + void (*put)(struct numa_entity *ne); +}; + struct numa_cpu_load { unsigned long remote; /* load of tasks running away from their home node */ unsigned long all; /* load of tasks that should be running on this node */ @@ -160,6 +171,26 @@ static inline struct task_struct *ne_owner(struct numa_entity *ne) return rcu_dereference(ne_mm(ne)->owner); } +static unsigned long process_cpu_load(struct numa_entity *ne) +{ + unsigned long load = 0; + struct task_struct *t, *p; + + rcu_read_lock(); + t = p = ne_owner(ne); + if (p) do { + load += t->numa_contrib; + } while ((t = next_thread(t)) != p); + rcu_read_unlock(); + + return load; +} + +static unsigned long process_mem_load(struct numa_entity *ne) +{ + return get_mm_counter(ne_mm(ne), MM_ANONPAGES); +} + static void process_cpu_migrate(struct numa_entity *ne, int node) { struct task_struct *p, *t; @@ -177,7 +208,7 @@ static void process_mem_migrate(struct numa_entity *ne, int node) lazy_migrate_process(ne_mm(ne), node); } -static int process_tryget(struct numa_entity *ne) +static bool process_tryget(struct numa_entity *ne) { /* * This is possible when we hold &nq_of(ne->node)->lock since then @@ -193,6 +224,17 @@ static void process_put(struct numa_entity *ne) mmput(ne_mm(ne)); } +static const struct numa_ops process_numa_ops = { + .mem_load = process_mem_load, + .cpu_load = process_cpu_load, + + .mem_migrate = process_mem_migrate, + .cpu_migrate = process_cpu_migrate, + + .tryget = process_tryget, + .put = process_put, +}; + static struct node_queue *lock_ne_nq(struct numa_entity *ne) { struct node_queue *nq; @@ -252,8 +294,8 @@ static void enqueue_ne(struct numa_entity *ne, int node) BUG_ON(ne->node != -1); - process_cpu_migrate(ne, node); - process_mem_migrate(ne, node); + ne->nops->cpu_migrate(ne, node); + ne->nops->mem_migrate(ne, node); spin_lock(&nq->lock); __enqueue_ne(nq, ne); @@ -273,14 +315,15 @@ static void dequeue_ne(struct numa_entity *ne) spin_unlock(&nq->lock); } -static void init_ne(struct numa_entity *ne) +static void init_ne(struct numa_entity *ne, const struct numa_ops *nops) { ne->node = -1; + ne->nops = nops; } void mm_init_numa(struct mm_struct *mm) { - init_ne(&mm->numa); + init_ne(&mm->numa, &process_numa_ops); } void exit_numa(struct mm_struct *mm) @@ -467,26 +510,6 @@ struct numa_imbalance { enum numa_balance_type type; }; -static unsigned long process_cpu_load(struct numa_entity *ne) -{ - unsigned long load = 0; - struct task_struct *t, *p; - - rcu_read_lock(); - t = p = ne_owner(ne); - if (p) do { - load += t->numa_contrib; - } while ((t = next_thread(t)) != p); - rcu_read_unlock(); - - return load; -} - -static unsigned long process_mem_load(struct numa_entity *ne) -{ - return get_mm_counter(ne_mm(ne), MM_ANONPAGES); -} - static int find_busiest_node(int this_node, struct numa_imbalance *imb) { unsigned long cpu_load, mem_load; @@ -608,8 +631,8 @@ static void move_processes(struct node_queue *busiest_nq, struct numa_entity, numa_entry); - ne_cpu = process_cpu_load(ne); - ne_mem = process_mem_load(ne); + ne_cpu = ne->nops->cpu_load(ne); + ne_mem = ne->nops->mem_load(ne); if (sched_feat(NUMA_BALANCE_FILTER)) { /* @@ -634,13 +657,13 @@ static void move_processes(struct node_queue *busiest_nq, __dequeue_ne(busiest_nq, ne); __enqueue_ne(this_nq, ne); - if (process_tryget(ne)) { + if (ne->nops->tryget(ne)) { double_unlock_nq(this_nq, busiest_nq); - process_cpu_migrate(ne, this_nq->node); - process_mem_migrate(ne, this_nq->node); + ne->nops->cpu_migrate(ne, this_nq->node); + ne->nops->mem_migrate(ne, this_nq->node); + ne->nops->put(ne); - process_put(ne); double_lock_nq(this_nq, busiest_nq); } -- To unsubscribe from this list: send the line "unsubscribe linux-tip-commits" in the body of a message to majordomo@xxxxxxxxxxxxxxx More majordomo info at http://vger.kernel.org/majordomo-info.html