mm, page_alloc: enable pcpu_drain with zone capability

drain_all_pages is documented to drain per-cpu pages for a given zone (if
non-NULL).  The current implementation doesn't match the description
though.  It will drain all pcp pages for all zones that happen to have
cached pages on the same cpu as the given zone.  This will lead to
premature pcp cache draining for zones that are not of any interest to the
caller - e.g.  compaction, hwpoison or memory offline.

This forces the page allocator to take locks and potential lock contention
as a result.

There is no real reason for this sub-optimal implementation.  Replace
per-cpu work item with a dedicated structure which contains a pointer to
the zone and pass it over to the worker.  This will get the zone
information all the way down to the worker function and do the right job.

[akpm@linux-foundation.org: avoid 80-col tricks]
[mhocko@suse.com: refactor the whole changelog]
Link: http://lkml.kernel.org/r/20181212142550.61686-1-richard.weiyang@gmail.com
Signed-off-by: Wei Yang <richard.weiyang@gmail.com>
Acked-by: Michal Hocko <mhocko@suse.com>
Reviewed-by: Oscar Salvador <osalvador@suse.de>
Reviewed-by: David Hildenbrand <david@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 2cd1f9bb1b52ec9e9870dd9980eb1290e6637ccd..75865e1325b5d590c09cbfd6a186fc6ace325e95 100644 (file)
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -97,8 +97,12 @@ int _node_numa_mem_[MAX_NUMNODES];
 #endif
 
 /* work_structs for global per-cpu drains */
+struct pcpu_drain {
+       struct zone *zone;
+       struct work_struct work;
+};
 DEFINE_MUTEX(pcpu_drain_mutex);
-DEFINE_PER_CPU(struct work_struct, pcpu_drain);
+DEFINE_PER_CPU(struct pcpu_drain, pcpu_drain);
 
 #ifdef CONFIG_GCC_PLUGIN_LATENT_ENTROPY
 volatile unsigned long latent_entropy __latent_entropy;
@@ -2658,6 +2662,10 @@ void drain_local_pages(struct zone *zone)
 
 static void drain_local_pages_wq(struct work_struct *work)
 {
+       struct pcpu_drain *drain;
+
+       drain = container_of(work, struct pcpu_drain, work);
+
        /*
         * drain_all_pages doesn't use proper cpu hotplug protection so
         * we can race with cpu offline when the WQ can move this from
@@ -2666,7 +2674,7 @@ static void drain_local_pages_wq(struct work_struct *work)
         * a different one.
         */
        preempt_disable();
-       drain_local_pages(NULL);
+       drain_local_pages(drain->zone);
        preempt_enable();
 }
 
@@ -2737,12 +2745,14 @@ void drain_all_pages(struct zone *zone)
        }
 
        for_each_cpu(cpu, &cpus_with_pcps) {
-               struct work_struct *work = per_cpu_ptr(&pcpu_drain, cpu);
-               INIT_WORK(work, drain_local_pages_wq);
-               queue_work_on(cpu, mm_percpu_wq, work);
+               struct pcpu_drain *drain = per_cpu_ptr(&pcpu_drain, cpu);
+
+               drain->zone = zone;
+               INIT_WORK(&drain->work, drain_local_pages_wq);
+               queue_work_on(cpu, mm_percpu_wq, &drain->work);
        }
        for_each_cpu(cpu, &cpus_with_pcps)
-               flush_work(per_cpu_ptr(&pcpu_drain, cpu));
+               flush_work(&per_cpu_ptr(&pcpu_drain, cpu)->work);
 
        mutex_unlock(&pcpu_drain_mutex);
 }