From bd225530a4c717714722c3731442b78954c765b3 Mon Sep 17 00:00:00 2001 From: Yu Zhao Date: Thu, 27 Jun 2024 16:27:05 -0600 Subject: mm/hugetlb_vmemmap: fix race with speculative PFN walkers While investigating HVO for THPs [1], it turns out that speculative PFN walkers like compaction can race with vmemmap modifications, e.g., CPU 1 (vmemmap modifier) CPU 2 (speculative PFN walker) ------------------------------- ------------------------------ Allocates an LRU folio page1 Sees page1 Frees page1 Allocates a hugeTLB folio page2 (page1 being a tail of page2) Updates vmemmap mapping page1 get_page_unless_zero(page1) Even though page1->_refcount is zero after HVO, get_page_unless_zero() can still try to modify this read-only field, resulting in a crash. An independent report [2] confirmed this race. There are two discussed approaches to fix this race: 1. Make RO vmemmap RW so that get_page_unless_zero() can fail without triggering a PF. 2. Use RCU to make sure get_page_unless_zero() either sees zero page->_refcount through the old vmemmap or non-zero page->_refcount through the new one. The second approach is preferred here because: 1. It can prevent illegal modifications to struct page[] that has been HVO'ed; 2. It can be generalized, in a way similar to ZERO_PAGE(), to fix similar races in other places, e.g., arch_remove_memory() on x86 [3], which frees vmemmap mapping offlined struct page[]. While adding synchronize_rcu(), the goal is to be surgical, rather than optimized. Specifically, calls to synchronize_rcu() on the error handling paths can be coalesced, but it is not done for the sake of Simplicity: noticeably, this fix removes ~50% more lines than it adds. According to the hugetlb_optimize_vmemmap section in Documentation/admin-guide/sysctl/vm.rst, enabling HVO makes allocating or freeing hugeTLB pages "~2x slower than before". Having synchronize_rcu() on top makes those operations even worse, and this also affects the user interface /proc/sys/vm/nr_overcommit_hugepages. This is *very* hard to trigger: 1. Most hugeTLB use cases I know of are static, i.e., reserved at boot time, because allocating at runtime is not reliable at all. 2. On top of that, someone has to be very unlucky to get tripped over above, because the race window is so small -- I wasn't able to trigger it with a stress testing that does nothing but that (with THPs though). [1] https://lore.kernel.org/20240229183436.4110845-4-yuzhao@google.com/ [2] https://lore.kernel.org/917FFC7F-0615-44DD-90EE-9F85F8EA9974@linux.dev/ [3] https://lore.kernel.org/be130a96-a27e-4240-ad78-776802f57cad@redhat.com/ Link: https://lkml.kernel.org/r/20240627222705.2974207-1-yuzhao@google.com Signed-off-by: Yu Zhao Acked-by: Muchun Song Cc: David Hildenbrand Cc: Frank van der Linden Cc: Matthew Wilcox (Oracle) Cc: Peter Xu Cc: Yang Shi Cc: Yu Zhao Signed-off-by: Andrew Morton --- mm/hugetlb.c | 53 +++++++---------------------------------------------- 1 file changed, 7 insertions(+), 46 deletions(-) (limited to 'mm/hugetlb.c') diff --git a/mm/hugetlb.c b/mm/hugetlb.c index f35abff8be60..2afb70171b76 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -1625,13 +1625,10 @@ static inline void destroy_compound_gigantic_folio(struct folio *folio, * folio appears as just a compound page. Otherwise, wait until after * allocating vmemmap to clear the flag. * - * A reference is held on the folio, except in the case of demote. - * * Must be called with hugetlb lock held. */ -static void __remove_hugetlb_folio(struct hstate *h, struct folio *folio, - bool adjust_surplus, - bool demote) +static void remove_hugetlb_folio(struct hstate *h, struct folio *folio, + bool adjust_surplus) { int nid = folio_nid(folio); @@ -1645,6 +1642,7 @@ static void __remove_hugetlb_folio(struct hstate *h, struct folio *folio, list_del(&folio->lru); if (folio_test_hugetlb_freed(folio)) { + folio_clear_hugetlb_freed(folio); h->free_huge_pages--; h->free_huge_pages_node[nid]--; } @@ -1661,33 +1659,13 @@ static void __remove_hugetlb_folio(struct hstate *h, struct folio *folio, if (!folio_test_hugetlb_vmemmap_optimized(folio)) __folio_clear_hugetlb(folio); - /* - * In the case of demote we do not ref count the page as it will soon - * be turned into a page of smaller size. - */ - if (!demote) - folio_ref_unfreeze(folio, 1); - h->nr_huge_pages--; h->nr_huge_pages_node[nid]--; } -static void remove_hugetlb_folio(struct hstate *h, struct folio *folio, - bool adjust_surplus) -{ - __remove_hugetlb_folio(h, folio, adjust_surplus, false); -} - -static void remove_hugetlb_folio_for_demote(struct hstate *h, struct folio *folio, - bool adjust_surplus) -{ - __remove_hugetlb_folio(h, folio, adjust_surplus, true); -} - static void add_hugetlb_folio(struct hstate *h, struct folio *folio, bool adjust_surplus) { - int zeroed; int nid = folio_nid(folio); VM_BUG_ON_FOLIO(!folio_test_hugetlb_vmemmap_optimized(folio), folio); @@ -1711,21 +1689,6 @@ static void add_hugetlb_folio(struct hstate *h, struct folio *folio, */ folio_set_hugetlb_vmemmap_optimized(folio); - /* - * This folio is about to be managed by the hugetlb allocator and - * should have no users. Drop our reference, and check for others - * just in case. - */ - zeroed = folio_put_testzero(folio); - if (unlikely(!zeroed)) - /* - * It is VERY unlikely soneone else has taken a ref - * on the folio. In this case, we simply return as - * free_huge_folio() will be called when this other ref - * is dropped. - */ - return; - arch_clear_hugetlb_flags(folio); enqueue_hugetlb_folio(h, folio); } @@ -1779,6 +1742,8 @@ static void __update_and_free_hugetlb_folio(struct hstate *h, spin_unlock_irq(&hugetlb_lock); } + folio_ref_unfreeze(folio, 1); + /* * Non-gigantic pages demoted from CMA allocated gigantic pages * need to be given back to CMA in free_gigantic_folio. @@ -3079,11 +3044,8 @@ retry: free_new: spin_unlock_irq(&hugetlb_lock); - if (new_folio) { - /* Folio has a zero ref count, but needs a ref to be freed */ - folio_ref_unfreeze(new_folio, 1); + if (new_folio) update_and_free_hugetlb_folio(h, new_folio, false); - } return ret; } @@ -3938,7 +3900,7 @@ static int demote_free_hugetlb_folio(struct hstate *h, struct folio *folio) target_hstate = size_to_hstate(PAGE_SIZE << h->demote_order); - remove_hugetlb_folio_for_demote(h, folio, false); + remove_hugetlb_folio(h, folio, false); spin_unlock_irq(&hugetlb_lock); /* @@ -3952,7 +3914,6 @@ static int demote_free_hugetlb_folio(struct hstate *h, struct folio *folio) if (rc) { /* Allocation of vmemmmap failed, we can not demote folio */ spin_lock_irq(&hugetlb_lock); - folio_ref_unfreeze(folio, 1); add_hugetlb_folio(h, folio, false); return rc; } -- cgit v1.2.3-58-ga151