From 2f7dd7a4100ad4affcb141605bef178ab98ccb18 Mon Sep 17 00:00:00 2001 From: Johannes Weiner Date: Thu, 2 Oct 2014 16:16:57 -0700 Subject: mm: memcontrol: do not iterate uninitialized memcgs The cgroup iterators yield css objects that have not yet gone through css_online(), but they are not complete memcgs at this point and so the memcg iterators should not return them. Commit d8ad30559715 ("mm/memcg: iteration skip memcgs not yet fully initialized") set out to implement exactly this, but it uses CSS_ONLINE, a cgroup-internal flag that does not meet the ordering requirements for memcg, and so the iterator may skip over initialized groups, or return partially initialized memcgs. The cgroup core can not reasonably provide a clear answer on whether the object around the css has been fully initialized, as that depends on controller-specific locking and lifetime rules. Thus, introduce a memcg-specific flag that is set after the memcg has been initialized in css_online(), and read before mem_cgroup_iter() callers access the memcg members. Signed-off-by: Johannes Weiner Cc: Tejun Heo Acked-by: Michal Hocko Cc: Hugh Dickins Cc: Peter Zijlstra Cc: [3.12+] Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/memcontrol.c | 36 +++++++++++++++++++++++++++++++----- 1 file changed, 31 insertions(+), 5 deletions(-) (limited to 'mm') diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 085dc6d2f876..28928ce9b07f 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -292,6 +292,9 @@ struct mem_cgroup { /* vmpressure notifications */ struct vmpressure vmpressure; + /* css_online() has been completed */ + int initialized; + /* * the counter to account for mem+swap usage. */ @@ -1099,10 +1102,21 @@ skip_node: * skipping css reference should be safe. */ if (next_css) { - if ((next_css == &root->css) || - ((next_css->flags & CSS_ONLINE) && - css_tryget_online(next_css))) - return mem_cgroup_from_css(next_css); + struct mem_cgroup *memcg = mem_cgroup_from_css(next_css); + + if (next_css == &root->css) + return memcg; + + if (css_tryget_online(next_css)) { + /* + * Make sure the memcg is initialized: + * mem_cgroup_css_online() orders the the + * initialization against setting the flag. + */ + if (smp_load_acquire(&memcg->initialized)) + return memcg; + css_put(next_css); + } prev_css = next_css; goto skip_node; @@ -5549,6 +5563,7 @@ mem_cgroup_css_online(struct cgroup_subsys_state *css) { struct mem_cgroup *memcg = mem_cgroup_from_css(css); struct mem_cgroup *parent = mem_cgroup_from_css(css->parent); + int ret; if (css->id > MEM_CGROUP_ID_MAX) return -ENOSPC; @@ -5585,7 +5600,18 @@ mem_cgroup_css_online(struct cgroup_subsys_state *css) } mutex_unlock(&memcg_create_mutex); - return memcg_init_kmem(memcg, &memory_cgrp_subsys); + ret = memcg_init_kmem(memcg, &memory_cgrp_subsys); + if (ret) + return ret; + + /* + * Make sure the memcg is initialized: mem_cgroup_iter() + * orders reading memcg->initialized against its callers + * reading the memcg members. + */ + smp_store_release(&memcg->initialized, 1); + + return 0; } /* -- cgit v1.2.3 From abe5f972912d086c080be4bde67750630b6fb38b Mon Sep 17 00:00:00 2001 From: Johannes Weiner Date: Thu, 2 Oct 2014 16:21:10 -0700 Subject: mm: page_alloc: fix zone allocation fairness on UP The zone allocation batches can easily underflow due to higher-order allocations or spills to remote nodes. On SMP that's fine, because underflows are expected from concurrency and dealt with by returning 0. But on UP, zone_page_state will just return a wrapped unsigned long, which will get past the <= 0 check and then consider the zone eligible until its watermarks are hit. Commit 3a025760fc15 ("mm: page_alloc: spill to remote nodes before waking kswapd") already made the counter-resetting use atomic_long_read() to accomodate underflows from remote spills, but it didn't go all the way with it. Make it clear that these batches are expected to go negative regardless of concurrency, and use atomic_long_read() everywhere. Fixes: 81c0a2bb515f ("mm: page_alloc: fair zone allocator policy") Reported-by: Vlastimil Babka Reported-by: Leon Romanovsky Signed-off-by: Johannes Weiner Acked-by: Mel Gorman Cc: [3.12+] Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/page_alloc.c | 7 +++---- 1 file changed, 3 insertions(+), 4 deletions(-) (limited to 'mm') diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 18cee0d4c8a2..eee961958021 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -1612,7 +1612,7 @@ again: } __mod_zone_page_state(zone, NR_ALLOC_BATCH, -(1 << order)); - if (zone_page_state(zone, NR_ALLOC_BATCH) == 0 && + if (atomic_long_read(&zone->vm_stat[NR_ALLOC_BATCH]) <= 0 && !zone_is_fair_depleted(zone)) zone_set_flag(zone, ZONE_FAIR_DEPLETED); @@ -5701,9 +5701,8 @@ static void __setup_per_zone_wmarks(void) zone->watermark[WMARK_HIGH] = min_wmark_pages(zone) + (tmp >> 1); __mod_zone_page_state(zone, NR_ALLOC_BATCH, - high_wmark_pages(zone) - - low_wmark_pages(zone) - - zone_page_state(zone, NR_ALLOC_BATCH)); + high_wmark_pages(zone) - low_wmark_pages(zone) - + atomic_long_read(&zone->vm_stat[NR_ALLOC_BATCH])); setup_zone_migrate_reserve(zone); spin_unlock_irqrestore(&zone->lock, flags); -- cgit v1.2.3