From 2938396771c8fd0870b5284319f9e78b4b552a79 Mon Sep 17 00:00:00 2001 From: Mike Kravetz Date: Tue, 4 May 2021 18:34:52 -0700 Subject: hugetlb: add per-hstate mutex to synchronize user adjustments The helper routine hstate_next_node_to_alloc accesses and modifies the hstate variable next_nid_to_alloc. The helper is used by the routines alloc_pool_huge_page and adjust_pool_surplus. adjust_pool_surplus is called with hugetlb_lock held. However, alloc_pool_huge_page can not be called with the hugetlb lock held as it will call the page allocator. Two instances of alloc_pool_huge_page could be run in parallel or alloc_pool_huge_page could run in parallel with adjust_pool_surplus which may result in the variable next_nid_to_alloc becoming invalid for the caller and pages being allocated on the wrong node. Both alloc_pool_huge_page and adjust_pool_surplus are only called from the routine set_max_huge_pages after boot. set_max_huge_pages is only called as the reusult of a user writing to the proc/sysfs nr_hugepages, or nr_hugepages_mempolicy file to adjust the number of hugetlb pages. It makes little sense to allow multiple adjustment to the number of hugetlb pages in parallel. Add a mutex to the hstate and use it to only allow one hugetlb page adjustment at a time. This will synchronize modifications to the next_nid_to_alloc variable. Link: https://lkml.kernel.org/r/20210409205254.242291-4-mike.kravetz@oracle.com Signed-off-by: Mike Kravetz Acked-by: Michal Hocko Reviewed-by: Oscar Salvador Reviewed-by: Miaohe Lin Reviewed-by: Muchun Song Reviewed-by: David Hildenbrand Cc: "Aneesh Kumar K . V" Cc: Barry Song Cc: David Rientjes Cc: Hillf Danton Cc: HORIGUCHI NAOYA Cc: Joonsoo Kim Cc: Matthew Wilcox Cc: Mina Almasry Cc: Peter Xu Cc: Peter Zijlstra Cc: Roman Gushchin Cc: Shakeel Butt Cc: Waiman Long Cc: Will Deacon Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/hugetlb.c | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'mm/hugetlb.c') diff --git a/mm/hugetlb.c b/mm/hugetlb.c index a5636e1593c5..067fd29a9d51 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -2621,6 +2621,11 @@ static int set_max_huge_pages(struct hstate *h, unsigned long count, int nid, else return -ENOMEM; + /* + * resize_lock mutex prevents concurrent adjustments to number of + * pages in hstate via the proc/sysfs interfaces. + */ + mutex_lock(&h->resize_lock); spin_lock(&hugetlb_lock); /* @@ -2653,6 +2658,7 @@ static int set_max_huge_pages(struct hstate *h, unsigned long count, int nid, if (hstate_is_gigantic(h) && !IS_ENABLED(CONFIG_CONTIG_ALLOC)) { if (count > persistent_huge_pages(h)) { spin_unlock(&hugetlb_lock); + mutex_unlock(&h->resize_lock); NODEMASK_FREE(node_alloc_noretry); return -EINVAL; } @@ -2727,6 +2733,7 @@ static int set_max_huge_pages(struct hstate *h, unsigned long count, int nid, out: h->max_huge_pages = persistent_huge_pages(h); spin_unlock(&hugetlb_lock); + mutex_unlock(&h->resize_lock); NODEMASK_FREE(node_alloc_noretry); @@ -3214,6 +3221,7 @@ void __init hugetlb_add_hstate(unsigned int order) BUG_ON(hugetlb_max_hstate >= HUGE_MAX_HSTATE); BUG_ON(order == 0); h = &hstates[hugetlb_max_hstate++]; + mutex_init(&h->resize_lock); h->order = order; h->mask = ~(huge_page_size(h) - 1); for (i = 0; i < MAX_NUMNODES; ++i) -- cgit