summaryrefslogtreecommitdiff
path: root/include/linux/page-flags.h
diff options
context:
space:
mode:
authorKirill A. Shutemov <kirill.shutemov@linux.intel.com>2015-11-06 16:29:54 -0800
committerLinus Torvalds <torvalds@linux-foundation.org>2015-11-06 17:50:42 -0800
commit1d798ca3f16437c71ff63e36597ff07f9c12e4d6 (patch)
tree4b70d32439fb18ef699175413e4b82c4af206f81 /include/linux/page-flags.h
parentf1e61557f0230d51a3df8d825f2c156e75563bff (diff)
mm: make compound_head() robust
Hugh has pointed that compound_head() call can be unsafe in some context. There's one example: CPU0 CPU1 isolate_migratepages_block() page_count() compound_head() !!PageTail() == true put_page() tail->first_page = NULL head = tail->first_page alloc_pages(__GFP_COMP) prep_compound_page() tail->first_page = head __SetPageTail(p); !!PageTail() == true <head == NULL dereferencing> The race is pure theoretical. I don't it's possible to trigger it in practice. But who knows. We can fix the race by changing how encode PageTail() and compound_head() within struct page to be able to update them in one shot. The patch introduces page->compound_head into third double word block in front of compound_dtor and compound_order. Bit 0 encodes PageTail() and the rest bits are pointer to head page if bit zero is set. The patch moves page->pmd_huge_pte out of word, just in case if an architecture defines pgtable_t into something what can have the bit 0 set. hugetlb_cgroup uses page->lru.next in the second tail page to store pointer struct hugetlb_cgroup. The patch switch it to use page->private in the second tail page instead. The space is free since ->first_page is removed from the union. The patch also opens possibility to remove HUGETLB_CGROUP_MIN_ORDER limitation, since there's now space in first tail page to store struct hugetlb_cgroup pointer. But that's out of scope of the patch. That means page->compound_head shares storage space with: - page->lru.next; - page->next; - page->rcu_head.next; That's too long list to be absolutely sure, but looks like nobody uses bit 0 of the word. page->rcu_head.next guaranteed[1] to have bit 0 clean as long as we use call_rcu(), call_rcu_bh(), call_rcu_sched(), or call_srcu(). But future call_rcu_lazy() is not allowed as it makes use of the bit and we can get false positive PageTail(). [1] http://lkml.kernel.org/g/20150827163634.GD4029@linux.vnet.ibm.com Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Acked-by: Michal Hocko <mhocko@suse.com> Reviewed-by: Andrea Arcangeli <aarcange@redhat.com> Cc: Hugh Dickins <hughd@google.com> Cc: David Rientjes <rientjes@google.com> Cc: Vlastimil Babka <vbabka@suse.cz> Acked-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Cc: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com> Cc: Andi Kleen <ak@linux.intel.com> Cc: Christoph Lameter <cl@linux.com> Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com> Cc: Sergey Senozhatsky <sergey.senozhatsky@gmail.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Diffstat (limited to 'include/linux/page-flags.h')
-rw-r--r--include/linux/page-flags.h80
1 files changed, 18 insertions, 62 deletions
diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h
index a525e5067484..bb53c7b86315 100644
--- a/include/linux/page-flags.h
+++ b/include/linux/page-flags.h
@@ -86,12 +86,7 @@ enum pageflags {
PG_private, /* If pagecache, has fs-private data */
PG_private_2, /* If pagecache, has fs aux data */
PG_writeback, /* Page is under writeback */
-#ifdef CONFIG_PAGEFLAGS_EXTENDED
PG_head, /* A head page */
- PG_tail, /* A tail page */
-#else
- PG_compound, /* A compound page */
-#endif
PG_swapcache, /* Swap page: swp_entry_t in private */
PG_mappedtodisk, /* Has blocks allocated on-disk */
PG_reclaim, /* To be reclaimed asap */
@@ -398,85 +393,46 @@ static inline void set_page_writeback_keepwrite(struct page *page)
test_set_page_writeback_keepwrite(page);
}
-#ifdef CONFIG_PAGEFLAGS_EXTENDED
-/*
- * System with lots of page flags available. This allows separate
- * flags for PageHead() and PageTail() checks of compound pages so that bit
- * tests can be used in performance sensitive paths. PageCompound is
- * generally not used in hot code paths except arch/powerpc/mm/init_64.c
- * and arch/powerpc/kvm/book3s_64_vio_hv.c which use it to detect huge pages
- * and avoid handling those in real mode.
- */
__PAGEFLAG(Head, head) CLEARPAGEFLAG(Head, head)
-__PAGEFLAG(Tail, tail)
-static inline int PageCompound(struct page *page)
-{
- return page->flags & ((1L << PG_head) | (1L << PG_tail));
-
-}
-#ifdef CONFIG_TRANSPARENT_HUGEPAGE
-static inline void ClearPageCompound(struct page *page)
+static inline int PageTail(struct page *page)
{
- BUG_ON(!PageHead(page));
- ClearPageHead(page);
+ return READ_ONCE(page->compound_head) & 1;
}
-#endif
-
-#define PG_head_mask ((1L << PG_head))
-#else
-/*
- * Reduce page flag use as much as possible by overlapping
- * compound page flags with the flags used for page cache pages. Possible
- * because PageCompound is always set for compound pages and not for
- * pages on the LRU and/or pagecache.
- */
-TESTPAGEFLAG(Compound, compound)
-__SETPAGEFLAG(Head, compound) __CLEARPAGEFLAG(Head, compound)
-
-/*
- * PG_reclaim is used in combination with PG_compound to mark the
- * head and tail of a compound page. This saves one page flag
- * but makes it impossible to use compound pages for the page cache.
- * The PG_reclaim bit would have to be used for reclaim or readahead
- * if compound pages enter the page cache.
- *
- * PG_compound & PG_reclaim => Tail page
- * PG_compound & ~PG_reclaim => Head page
- */
-#define PG_head_mask ((1L << PG_compound))
-#define PG_head_tail_mask ((1L << PG_compound) | (1L << PG_reclaim))
-
-static inline int PageHead(struct page *page)
+static inline void set_compound_head(struct page *page, struct page *head)
{
- return ((page->flags & PG_head_tail_mask) == PG_head_mask);
+ WRITE_ONCE(page->compound_head, (unsigned long)head + 1);
}
-static inline int PageTail(struct page *page)
+static inline void clear_compound_head(struct page *page)
{
- return ((page->flags & PG_head_tail_mask) == PG_head_tail_mask);
+ WRITE_ONCE(page->compound_head, 0);
}
-static inline void __SetPageTail(struct page *page)
+static inline struct page *compound_head(struct page *page)
{
- page->flags |= PG_head_tail_mask;
+ unsigned long head = READ_ONCE(page->compound_head);
+
+ if (unlikely(head & 1))
+ return (struct page *) (head - 1);
+ return page;
}
-static inline void __ClearPageTail(struct page *page)
+static inline int PageCompound(struct page *page)
{
- page->flags &= ~PG_head_tail_mask;
-}
+ return PageHead(page) || PageTail(page);
+}
#ifdef CONFIG_TRANSPARENT_HUGEPAGE
static inline void ClearPageCompound(struct page *page)
{
- BUG_ON((page->flags & PG_head_tail_mask) != (1 << PG_compound));
- clear_bit(PG_compound, &page->flags);
+ BUG_ON(!PageHead(page));
+ ClearPageHead(page);
}
#endif
-#endif /* !PAGEFLAGS_EXTENDED */
+#define PG_head_mask ((1L << PG_head))
#ifdef CONFIG_HUGETLB_PAGE
int PageHuge(struct page *page);