summaryrefslogtreecommitdiff
path: root/mm/hugetlb.c
diff options
context:
space:
mode:
authorMike Kravetz <mike.kravetz@oracle.com>2021-06-30 18:48:34 -0700
committerLinus Torvalds <torvalds@linux-foundation.org>2021-06-30 20:47:27 -0700
commit7118fc2906e2925d7edb5ed9c8a57f2a5f23b849 (patch)
tree0c8e10ad4b90c59e5660f7a51ae43899e71958d1 /mm/hugetlb.c
parent48b8d744ea841b8adf8d07bfe7a2d55f22e4d179 (diff)
hugetlb: address ref count racing in prep_compound_gigantic_page
In [1], Jann Horn points out a possible race between prep_compound_gigantic_page and __page_cache_add_speculative. The root cause of the possible race is prep_compound_gigantic_page uncondittionally setting the ref count of pages to zero. It does this because prep_compound_gigantic_page is handed a 'group' of pages from an allocator and needs to convert that group of pages to a compound page. The ref count of each page in this 'group' is one as set by the allocator. However, the ref count of compound page tail pages must be zero. The potential race comes about when ref counted pages are returned from the allocator. When this happens, other mm code could also take a reference on the page. __page_cache_add_speculative is one such example. Therefore, prep_compound_gigantic_page can not just set the ref count of pages to zero as it does today. Doing so would lose the reference taken by any other code. This would lead to BUGs in code checking ref counts and could possibly even lead to memory corruption. There are two possible ways to address this issue. 1) Make all allocators of gigantic groups of pages be able to return a properly constructed compound page. 2) Make prep_compound_gigantic_page be more careful when constructing a compound page. This patch takes approach 2. In prep_compound_gigantic_page, use cmpxchg to only set ref count to zero if it is one. If the cmpxchg fails, call synchronize_rcu() in the hope that the extra ref count will be driopped during a rcu grace period. This is not a performance critical code path and the wait should be accceptable. If the ref count is still inflated after the grace period, then undo any modifications made and return an error. Currently prep_compound_gigantic_page is type void and does not return errors. Modify the two callers to check for and handle error returns. On error, the caller must free the 'group' of pages as they can not be used to form a gigantic page. After freeing pages, the runtime caller (alloc_fresh_huge_page) will retry the allocation once. Boot time allocations can not be retried. The routine prep_compound_page also unconditionally sets the ref count of compound page tail pages to zero. However, in this case the buddy allocator is constructing a compound page from freshly allocated pages. The ref count on those freshly allocated pages is already zero, so the set_page_count(p, 0) is unnecessary and could lead to confusion. Just remove it. [1] https://lore.kernel.org/linux-mm/CAG48ez23q0Jy9cuVnwAe7t_fdhMk2S7N5Hdi-GLcCeq5bsfLxw@mail.gmail.com/ Link: https://lkml.kernel.org/r/20210622021423.154662-3-mike.kravetz@oracle.com Fixes: 58a84aa92723 ("thp: set compound tail page _count to zero") Signed-off-by: Mike Kravetz <mike.kravetz@oracle.com> Reported-by: Jann Horn <jannh@google.com> Cc: Youquan Song <youquan.song@intel.com> Cc: Andrea Arcangeli <aarcange@redhat.com> Cc: Jan Kara <jack@suse.cz> Cc: John Hubbard <jhubbard@nvidia.com> Cc: "Kirill A . Shutemov" <kirill@shutemov.name> Cc: Matthew Wilcox <willy@infradead.org> Cc: Michal Hocko <mhocko@kernel.org> Cc: Muchun Song <songmuchun@bytedance.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Diffstat (limited to 'mm/hugetlb.c')
-rw-r--r--mm/hugetlb.c72
1 files changed, 64 insertions, 8 deletions
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index 8048763e98a7..89ba5147206e 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -1623,9 +1623,9 @@ static void prep_new_huge_page(struct hstate *h, struct page *page, int nid)
spin_unlock_irq(&hugetlb_lock);
}
-static void prep_compound_gigantic_page(struct page *page, unsigned int order)
+static bool prep_compound_gigantic_page(struct page *page, unsigned int order)
{
- int i;
+ int i, j;
int nr_pages = 1 << order;
struct page *p = page + 1;
@@ -1647,11 +1647,48 @@ static void prep_compound_gigantic_page(struct page *page, unsigned int order)
* after get_user_pages().
*/
__ClearPageReserved(p);
+ /*
+ * Subtle and very unlikely
+ *
+ * Gigantic 'page allocators' such as memblock or cma will
+ * return a set of pages with each page ref counted. We need
+ * to turn this set of pages into a compound page with tail
+ * page ref counts set to zero. Code such as speculative page
+ * cache adding could take a ref on a 'to be' tail page.
+ * We need to respect any increased ref count, and only set
+ * the ref count to zero if count is currently 1. If count
+ * is not 1, we call synchronize_rcu in the hope that a rcu
+ * grace period will cause ref count to drop and then retry.
+ * If count is still inflated on retry we return an error and
+ * must discard the pages.
+ */
+ if (!page_ref_freeze(p, 1)) {
+ pr_info("HugeTLB unexpected inflated ref count on freshly allocated page\n");
+ synchronize_rcu();
+ if (!page_ref_freeze(p, 1))
+ goto out_error;
+ }
set_page_count(p, 0);
set_compound_head(p, page);
}
atomic_set(compound_mapcount_ptr(page), -1);
atomic_set(compound_pincount_ptr(page), 0);
+ return true;
+
+out_error:
+ /* undo tail page modifications made above */
+ p = page + 1;
+ for (j = 1; j < i; j++, p = mem_map_next(p, page, j)) {
+ clear_compound_head(p);
+ set_page_refcounted(p);
+ }
+ /* need to clear PG_reserved on remaining tail pages */
+ for (; j < nr_pages; j++, p = mem_map_next(p, page, j))
+ __ClearPageReserved(p);
+ set_compound_order(page, 0);
+ page[1].compound_nr = 0;
+ __ClearPageHead(page);
+ return false;
}
/*
@@ -1771,7 +1808,9 @@ static struct page *alloc_fresh_huge_page(struct hstate *h,
nodemask_t *node_alloc_noretry)
{
struct page *page;
+ bool retry = false;
+retry:
if (hstate_is_gigantic(h))
page = alloc_gigantic_page(h, gfp_mask, nid, nmask);
else
@@ -1780,8 +1819,21 @@ static struct page *alloc_fresh_huge_page(struct hstate *h,
if (!page)
return NULL;
- if (hstate_is_gigantic(h))
- prep_compound_gigantic_page(page, huge_page_order(h));
+ if (hstate_is_gigantic(h)) {
+ if (!prep_compound_gigantic_page(page, huge_page_order(h))) {
+ /*
+ * Rare failure to convert pages to compound page.
+ * Free pages and try again - ONCE!
+ */
+ free_gigantic_page(page, huge_page_order(h));
+ if (!retry) {
+ retry = true;
+ goto retry;
+ }
+ pr_warn("HugeTLB page can not be used due to unexpected inflated ref count\n");
+ return NULL;
+ }
+ }
prep_new_huge_page(h, page, page_to_nid(page));
return page;
@@ -2771,10 +2823,14 @@ static void __init gather_bootmem_prealloc(void)
VM_BUG_ON(!hstate_is_gigantic(h));
WARN_ON(page_count(page) != 1);
- prep_compound_gigantic_page(page, huge_page_order(h));
- WARN_ON(PageReserved(page));
- prep_new_huge_page(h, page, page_to_nid(page));
- put_page(page); /* free it into the hugepage allocator */
+ if (prep_compound_gigantic_page(page, huge_page_order(h))) {
+ WARN_ON(PageReserved(page));
+ prep_new_huge_page(h, page, page_to_nid(page));
+ put_page(page); /* add to the hugepage allocator */
+ } else {
+ free_gigantic_page(page, huge_page_order(h));
+ pr_warn("HugeTLB page can not be used due to unexpected inflated ref count\n");
+ }
/*
* We need to restore the 'stolen' pages to totalram_pages