From 05eb6e7263185a6bb0de9501ccf2addc52429414 Mon Sep 17 00:00:00 2001 From: Vladimir Davydov Date: Tue, 2 Aug 2016 14:03:01 -0700 Subject: radix-tree: account nodes to memcg only if explicitly requested Radix trees may be used not only for storing page cache pages, so unconditionally accounting radix tree nodes to the current memory cgroup is bad: if a radix tree node is used for storing data shared among different cgroups we risk pinning dead memory cgroups forever. So let's only account radix tree nodes if it was explicitly requested by passing __GFP_ACCOUNT to INIT_RADIX_TREE. Currently, we only want to account page cache entries, so mark mapping->page_tree so. Fixes: 58e698af4c63 ("radix-tree: account radix_tree_node to memory cgroup") Link: http://lkml.kernel.org/r/1470057188-7864-1-git-send-email-vdavydov@virtuozzo.com Signed-off-by: Vladimir Davydov Acked-by: Johannes Weiner Acked-by: Michal Hocko Cc: [4.6+] Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- lib/radix-tree.c | 14 ++++++++++---- 1 file changed, 10 insertions(+), 4 deletions(-) (limited to 'lib') diff --git a/lib/radix-tree.c b/lib/radix-tree.c index 61b8fb529cef..1b7bf7314141 100644 --- a/lib/radix-tree.c +++ b/lib/radix-tree.c @@ -277,10 +277,11 @@ radix_tree_node_alloc(struct radix_tree_root *root) /* * Even if the caller has preloaded, try to allocate from the - * cache first for the new node to get accounted. + * cache first for the new node to get accounted to the memory + * cgroup. */ ret = kmem_cache_alloc(radix_tree_node_cachep, - gfp_mask | __GFP_ACCOUNT | __GFP_NOWARN); + gfp_mask | __GFP_NOWARN); if (ret) goto out; @@ -303,8 +304,7 @@ radix_tree_node_alloc(struct radix_tree_root *root) kmemleak_update_trace(ret); goto out; } - ret = kmem_cache_alloc(radix_tree_node_cachep, - gfp_mask | __GFP_ACCOUNT); + ret = kmem_cache_alloc(radix_tree_node_cachep, gfp_mask); out: BUG_ON(radix_tree_is_internal_node(ret)); return ret; @@ -351,6 +351,12 @@ static int __radix_tree_preload(gfp_t gfp_mask, int nr) struct radix_tree_node *node; int ret = -ENOMEM; + /* + * Nodes preloaded by one cgroup can be be used by another cgroup, so + * they should never be accounted to any particular memory cgroup. + */ + gfp_mask &= ~__GFP_ACCOUNT; + preempt_disable(); rtp = this_cpu_ptr(&radix_tree_preloads); while (rtp->nr < nr) { -- cgit v1.2.3-70-g09d2