From b93e0f329e24f3615aa551fd9b99a75fb7c9195f Mon Sep 17 00:00:00 2001 From: Michal Hocko Date: Wed, 6 Sep 2017 16:20:37 -0700 Subject: mm, memory_hotplug: get rid of zonelists_mutex zonelists_mutex was introduced by commit 4eaf3f64397c ("mem-hotplug: fix potential race while building zonelist for new populated zone") to protect zonelist building from races. This is no longer needed though because both memory online and offline are fully serialized. New users have grown since then. Notably setup_per_zone_wmarks wants to prevent from races between memory hotplug, khugepaged setup and manual min_free_kbytes update via sysctl (see cfd3da1e49bb ("mm: Serialize access to min_free_kbytes"). Let's add a private lock for that purpose. This will not prevent from seeing halfway through memory hotplug operation but that shouldn't be a big deal becuse memory hotplug will update watermarks explicitly so we will eventually get a full picture. The lock just makes sure we won't race when updating watermarks leading to weird results. Also __build_all_zonelists manipulates global data so add a private lock for it as well. This doesn't seem to be necessary today but it is more robust to have a lock there. While we are at it make sure we document that memory online/offline depends on a full serialization either via mem_hotplug_begin() or device_lock. Link: http://lkml.kernel.org/r/20170721143915.14161-9-mhocko@kernel.org Signed-off-by: Michal Hocko Cc: Johannes Weiner Cc: Joonsoo Kim Cc: Mel Gorman Cc: Shaohua Li Cc: Toshi Kani Cc: Vlastimil Babka Cc: Haicheng Li Cc: Wu Fengguang Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/memory_hotplug.c | 12 ++---------- 1 file changed, 2 insertions(+), 10 deletions(-) (limited to 'mm/memory_hotplug.c') diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c index 2f0c7ebc7624..73bf17df6899 100644 --- a/mm/memory_hotplug.c +++ b/mm/memory_hotplug.c @@ -897,7 +897,7 @@ static struct zone * __meminit move_pfn_range(int online_type, int nid, return zone; } -/* Must be protected by mem_hotplug_begin() */ +/* Must be protected by mem_hotplug_begin() or a device_lock */ int __ref online_pages(unsigned long pfn, unsigned long nr_pages, int online_type) { unsigned long flags; @@ -926,7 +926,6 @@ int __ref online_pages(unsigned long pfn, unsigned long nr_pages, int online_typ * This means the page allocator ignores this zone. * So, zonelist must be updated after online. */ - mutex_lock(&zonelists_mutex); if (!populated_zone(zone)) { need_zonelists_rebuild = 1; setup_zone_pageset(zone); @@ -937,7 +936,6 @@ int __ref online_pages(unsigned long pfn, unsigned long nr_pages, int online_typ if (ret) { if (need_zonelists_rebuild) zone_pcp_reset(zone); - mutex_unlock(&zonelists_mutex); goto failed_addition; } @@ -955,8 +953,6 @@ int __ref online_pages(unsigned long pfn, unsigned long nr_pages, int online_typ zone_pcp_update(zone); } - mutex_unlock(&zonelists_mutex); - init_per_zone_wmark_min(); if (onlined_pages) { @@ -1027,9 +1023,7 @@ static pg_data_t __ref *hotadd_new_pgdat(int nid, u64 start) * The node we allocated has no zone fallback lists. For avoiding * to access not-initialized zonelist, build here. */ - mutex_lock(&zonelists_mutex); build_all_zonelists(pgdat); - mutex_unlock(&zonelists_mutex); /* * zone->managed_pages is set to an approximate value in @@ -1696,9 +1690,7 @@ repeat: if (!populated_zone(zone)) { zone_pcp_reset(zone); - mutex_lock(&zonelists_mutex); build_all_zonelists(NULL); - mutex_unlock(&zonelists_mutex); } else zone_pcp_update(zone); @@ -1724,7 +1716,7 @@ failed_removal: return ret; } -/* Must be protected by mem_hotplug_begin() */ +/* Must be protected by mem_hotplug_begin() or a device_lock */ int offline_pages(unsigned long start_pfn, unsigned long nr_pages) { return __offline_pages(start_pfn, start_pfn + nr_pages, 120 * HZ); -- cgit v1.2.3