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>
diff --git a/mm/Kconfig b/mm/Kconfig
index 0d9fdcd..97a4e06 100644
--- a/mm/Kconfig
+++ b/mm/Kconfig
@@ -200,18 +200,6 @@
depends on MEMORY_HOTPLUG && ARCH_ENABLE_MEMORY_HOTREMOVE
depends on MIGRATION
-#
-# If we have space for more page flags then we can enable additional
-# optimizations and functionality.
-#
-# Regular Sparsemem takes page flag bits for the sectionid if it does not
-# use a virtual memmap. Disable extended page flags for 32 bit platforms
-# that require the use of a sectionid in the page flags.
-#
-config PAGEFLAGS_EXTENDED
- def_bool y
- depends on 64BIT || SPARSEMEM_VMEMMAP || !SPARSEMEM
-
# Heavily threaded applications may benefit from splitting the mm-wide
# page_table_lock, so that faults on different parts of the user address
# space can be handled with less contention: split it at this NR_CPUS.
diff --git a/mm/debug.c b/mm/debug.c
index e784110..668aa35 100644
--- a/mm/debug.c
+++ b/mm/debug.c
@@ -25,12 +25,7 @@
{1UL << PG_private, "private" },
{1UL << PG_private_2, "private_2" },
{1UL << PG_writeback, "writeback" },
-#ifdef CONFIG_PAGEFLAGS_EXTENDED
{1UL << PG_head, "head" },
- {1UL << PG_tail, "tail" },
-#else
- {1UL << PG_compound, "compound" },
-#endif
{1UL << PG_swapcache, "swapcache" },
{1UL << PG_mappedtodisk, "mappedtodisk" },
{1UL << PG_reclaim, "reclaim" },
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index 73266ee..e1ccc83f 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -1755,8 +1755,7 @@
(1L << PG_unevictable)));
page_tail->flags |= (1L << PG_dirty);
- /* clear PageTail before overwriting first_page */
- smp_wmb();
+ clear_compound_head(page_tail);
if (page_is_young(page))
set_page_young(page_tail);
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index e90a290..4eb0f09 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -1001,9 +1001,8 @@
struct page *p = page + 1;
for (i = 1; i < nr_pages; i++, p = mem_map_next(p, page, i)) {
- __ClearPageTail(p);
+ clear_compound_head(p);
set_page_refcounted(p);
- p->first_page = NULL;
}
set_compound_order(page, 0);
@@ -1276,10 +1275,7 @@
*/
__ClearPageReserved(p);
set_page_count(p, 0);
- p->first_page = page;
- /* Make sure p->first_page is always valid for PageTail() */
- smp_wmb();
- __SetPageTail(p);
+ set_compound_head(p, page);
}
}
diff --git a/mm/hugetlb_cgroup.c b/mm/hugetlb_cgroup.c
index 33d59ab..d8fb10d 100644
--- a/mm/hugetlb_cgroup.c
+++ b/mm/hugetlb_cgroup.c
@@ -385,7 +385,7 @@
/*
* Add cgroup control files only if the huge page consists
* of more than two normal pages. This is because we use
- * page[2].lru.next for storing cgroup details.
+ * page[2].private for storing cgroup details.
*/
if (huge_page_order(h) >= HUGETLB_CGROUP_MIN_ORDER)
__hugetlb_cgroup_file_init(hstate_index(h));
diff --git a/mm/internal.h b/mm/internal.h
index 5b7841f6..a7f5670 100644
--- a/mm/internal.h
+++ b/mm/internal.h
@@ -80,9 +80,9 @@
* speculative page access (like in
* page_cache_get_speculative()) on tail pages.
*/
- VM_BUG_ON_PAGE(atomic_read(&page->first_page->_count) <= 0, page);
+ VM_BUG_ON_PAGE(atomic_read(&compound_head(page)->_count) <= 0, page);
if (get_page_head)
- atomic_inc(&page->first_page->_count);
+ atomic_inc(&compound_head(page)->_count);
get_huge_page_tail(page);
}
diff --git a/mm/memory-failure.c b/mm/memory-failure.c
index 16a0ec3..8424b64 100644
--- a/mm/memory-failure.c
+++ b/mm/memory-failure.c
@@ -776,8 +776,6 @@
#define lru (1UL << PG_lru)
#define swapbacked (1UL << PG_swapbacked)
#define head (1UL << PG_head)
-#define tail (1UL << PG_tail)
-#define compound (1UL << PG_compound)
#define slab (1UL << PG_slab)
#define reserved (1UL << PG_reserved)
@@ -800,12 +798,7 @@
*/
{ slab, slab, MF_MSG_SLAB, me_kernel },
-#ifdef CONFIG_PAGEFLAGS_EXTENDED
{ head, head, MF_MSG_HUGE, me_huge_page },
- { tail, tail, MF_MSG_HUGE, me_huge_page },
-#else
- { compound, compound, MF_MSG_HUGE, me_huge_page },
-#endif
{ sc|dirty, sc|dirty, MF_MSG_DIRTY_SWAPCACHE, me_swapcache_dirty },
{ sc|dirty, sc, MF_MSG_CLEAN_SWAPCACHE, me_swapcache_clean },
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index fae1bd6..e361001 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -445,15 +445,15 @@
/*
* Higher-order pages are called "compound pages". They are structured thusly:
*
- * The first PAGE_SIZE page is called the "head page".
+ * The first PAGE_SIZE page is called the "head page" and have PG_head set.
*
- * The remaining PAGE_SIZE pages are called "tail pages".
+ * The remaining PAGE_SIZE pages are called "tail pages". PageTail() is encoded
+ * in bit 0 of page->compound_head. The rest of bits is pointer to head page.
*
- * All pages have PG_compound set. All tail pages have their ->first_page
- * pointing at the head page.
+ * The first tail page's ->compound_dtor holds the offset in array of compound
+ * page destructors. See compound_page_dtors.
*
- * The first tail page's ->lru.next holds the address of the compound page's
- * put_page() function. Its ->lru.prev holds the order of allocation.
+ * The first tail page's ->compound_order holds the order of allocation.
* This usage means that zero-order pages may not be compound.
*/
@@ -473,10 +473,7 @@
for (i = 1; i < nr_pages; i++) {
struct page *p = page + i;
set_page_count(p, 0);
- p->first_page = page;
- /* Make sure p->first_page is always valid for PageTail() */
- smp_wmb();
- __SetPageTail(p);
+ set_compound_head(p, page);
}
}
@@ -854,17 +851,30 @@
static int free_tail_pages_check(struct page *head_page, struct page *page)
{
- if (!IS_ENABLED(CONFIG_DEBUG_VM))
- return 0;
+ int ret = 1;
+
+ /*
+ * We rely page->lru.next never has bit 0 set, unless the page
+ * is PageTail(). Let's make sure that's true even for poisoned ->lru.
+ */
+ BUILD_BUG_ON((unsigned long)LIST_POISON1 & 1);
+
+ if (!IS_ENABLED(CONFIG_DEBUG_VM)) {
+ ret = 0;
+ goto out;
+ }
if (unlikely(!PageTail(page))) {
bad_page(page, "PageTail not set", 0);
- return 1;
+ goto out;
}
- if (unlikely(page->first_page != head_page)) {
- bad_page(page, "first_page not consistent", 0);
- return 1;
+ if (unlikely(compound_head(page) != head_page)) {
+ bad_page(page, "compound_head not consistent", 0);
+ goto out;
}
- return 0;
+ ret = 0;
+out:
+ clear_compound_head(page);
+ return ret;
}
static void __meminit __init_single_page(struct page *page, unsigned long pfn,
@@ -931,6 +941,10 @@
struct page *page = pfn_to_page(start_pfn);
init_reserved_page(start_pfn);
+
+ /* Avoid false-positive PageTail() */
+ INIT_LIST_HEAD(&page->lru);
+
SetPageReserved(page);
}
}
diff --git a/mm/swap.c b/mm/swap.c
index 983f692..39395fb 100644
--- a/mm/swap.c
+++ b/mm/swap.c
@@ -201,7 +201,7 @@
__put_single_page(page);
return;
}
- VM_BUG_ON_PAGE(page_head != page->first_page, page);
+ VM_BUG_ON_PAGE(page_head != compound_head(page), page);
/*
* We can release the refcount taken by
* get_page_unless_zero() now that
@@ -262,7 +262,7 @@
* Case 3 is possible, as we may race with
* __split_huge_page_refcount tearing down a THP page.
*/
- page_head = compound_head_by_tail(page);
+ page_head = compound_head(page);
if (!__compound_tail_refcounted(page_head))
put_unrefcounted_compound_page(page_head, page);
else