1d798ca3f1
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>
124 lines
3.0 KiB
C
124 lines
3.0 KiB
C
/*
|
|
* Copyright IBM Corporation, 2012
|
|
* Author Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
|
|
*
|
|
* This program is free software; you can redistribute it and/or modify it
|
|
* under the terms of version 2.1 of the GNU Lesser General Public License
|
|
* as published by the Free Software Foundation.
|
|
*
|
|
* This program is distributed in the hope that it would be useful, but
|
|
* WITHOUT ANY WARRANTY; without even the implied warranty of
|
|
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.
|
|
*
|
|
*/
|
|
|
|
#ifndef _LINUX_HUGETLB_CGROUP_H
|
|
#define _LINUX_HUGETLB_CGROUP_H
|
|
|
|
#include <linux/mmdebug.h>
|
|
|
|
struct hugetlb_cgroup;
|
|
/*
|
|
* Minimum page order trackable by hugetlb cgroup.
|
|
* At least 3 pages are necessary for all the tracking information.
|
|
*/
|
|
#define HUGETLB_CGROUP_MIN_ORDER 2
|
|
|
|
#ifdef CONFIG_CGROUP_HUGETLB
|
|
|
|
static inline struct hugetlb_cgroup *hugetlb_cgroup_from_page(struct page *page)
|
|
{
|
|
VM_BUG_ON_PAGE(!PageHuge(page), page);
|
|
|
|
if (compound_order(page) < HUGETLB_CGROUP_MIN_ORDER)
|
|
return NULL;
|
|
return (struct hugetlb_cgroup *)page[2].private;
|
|
}
|
|
|
|
static inline
|
|
int set_hugetlb_cgroup(struct page *page, struct hugetlb_cgroup *h_cg)
|
|
{
|
|
VM_BUG_ON_PAGE(!PageHuge(page), page);
|
|
|
|
if (compound_order(page) < HUGETLB_CGROUP_MIN_ORDER)
|
|
return -1;
|
|
page[2].private = (unsigned long)h_cg;
|
|
return 0;
|
|
}
|
|
|
|
static inline bool hugetlb_cgroup_disabled(void)
|
|
{
|
|
return !cgroup_subsys_enabled(hugetlb_cgrp_subsys);
|
|
}
|
|
|
|
extern int hugetlb_cgroup_charge_cgroup(int idx, unsigned long nr_pages,
|
|
struct hugetlb_cgroup **ptr);
|
|
extern void hugetlb_cgroup_commit_charge(int idx, unsigned long nr_pages,
|
|
struct hugetlb_cgroup *h_cg,
|
|
struct page *page);
|
|
extern void hugetlb_cgroup_uncharge_page(int idx, unsigned long nr_pages,
|
|
struct page *page);
|
|
extern void hugetlb_cgroup_uncharge_cgroup(int idx, unsigned long nr_pages,
|
|
struct hugetlb_cgroup *h_cg);
|
|
extern void hugetlb_cgroup_file_init(void) __init;
|
|
extern void hugetlb_cgroup_migrate(struct page *oldhpage,
|
|
struct page *newhpage);
|
|
|
|
#else
|
|
static inline struct hugetlb_cgroup *hugetlb_cgroup_from_page(struct page *page)
|
|
{
|
|
return NULL;
|
|
}
|
|
|
|
static inline
|
|
int set_hugetlb_cgroup(struct page *page, struct hugetlb_cgroup *h_cg)
|
|
{
|
|
return 0;
|
|
}
|
|
|
|
static inline bool hugetlb_cgroup_disabled(void)
|
|
{
|
|
return true;
|
|
}
|
|
|
|
static inline int
|
|
hugetlb_cgroup_charge_cgroup(int idx, unsigned long nr_pages,
|
|
struct hugetlb_cgroup **ptr)
|
|
{
|
|
return 0;
|
|
}
|
|
|
|
static inline void
|
|
hugetlb_cgroup_commit_charge(int idx, unsigned long nr_pages,
|
|
struct hugetlb_cgroup *h_cg,
|
|
struct page *page)
|
|
{
|
|
return;
|
|
}
|
|
|
|
static inline void
|
|
hugetlb_cgroup_uncharge_page(int idx, unsigned long nr_pages, struct page *page)
|
|
{
|
|
return;
|
|
}
|
|
|
|
static inline void
|
|
hugetlb_cgroup_uncharge_cgroup(int idx, unsigned long nr_pages,
|
|
struct hugetlb_cgroup *h_cg)
|
|
{
|
|
return;
|
|
}
|
|
|
|
static inline void hugetlb_cgroup_file_init(void)
|
|
{
|
|
}
|
|
|
|
static inline void hugetlb_cgroup_migrate(struct page *oldhpage,
|
|
struct page *newhpage)
|
|
{
|
|
return;
|
|
}
|
|
|
|
#endif /* CONFIG_MEM_RES_CTLR_HUGETLB */
|
|
#endif
|