Commit 504f60d0 authored by Miaohe Lin's avatar Miaohe Lin Committed by Zheng Zengkai
Browse files

swap: fix do_swap_page() race with swapoff 

mainline inclusion
from mainline-v5.14-rc1
commit 2799e775
category: bugfix
bugzilla: https://gitee.com/openeuler/kernel/issues/I645JI
CVE: NA

Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?id=2799e77529c2a25492a4395db93996e3dacd762d

--------------------------------

When I was investigating the swap code, I found the below possible race
window:

CPU 1                                   	CPU 2
-----                                   	-----
do_swap_page
  if (data_race(si->flags & SWP_SYNCHRONOUS_IO)
  swap_readpage
    if (data_race(sis->flags & SWP_FS_OPS)) {
                                        	swapoff
					  	  ..
					  	  p->swap_file = NULL;
					  	  ..
    struct file *swap_file = sis->swap_file;
    struct address_space *mapping = swap_file->f_mapping;[oops!]

Note that for the pages that are swapped in through swap cache, this isn't
an issue. Because the page is locked, and the swap entry will be marked
with SWAP_HAS_CACHE, so swapoff() can not proceed until the page has been
unlocked.

Fix this race by using get/put_swap_device() to guard against concurrent
swapoff.

Link: https://lkml.kernel.org/r/20210426123316.806267-3-linmiaohe@huawei.com


Fixes: 0bcac06f ("mm,swap: skip swapcache for swapin of synchronous device")
Signed-off-by: default avatarMiaohe Lin <linmiaohe@huawei.com>
Reviewed-by: default avatar"Huang, Ying" <ying.huang@intel.com>
Cc: Alex Shi <alexs@kernel.org>
Cc: David Hildenbrand <david@redhat.com>
Cc: Dennis Zhou <dennis@kernel.org>
Cc: Hugh Dickins <hughd@google.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Cc: Matthew Wilcox <willy@infradead.org>
Cc: Michal Hocko <mhocko@suse.com>
Cc: Minchan Kim <minchan@kernel.org>
Cc: Tim Chen <tim.c.chen@linux.intel.com>
Cc: Wei Yang <richard.weiyang@gmail.com>
Cc: Yang Shi <shy828301@gmail.com>
Cc: Yu Zhao <yuzhao@google.com>
Signed-off-by: default avatarAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: default avatarLinus Torvalds <torvalds@linux-foundation.org>
Conflicts:
	mm/memory.c
Signed-off-by: default avatarChen Wandun <chenwandun@huawei.com>
Reviewed-by: default avatarKefeng <Wang&lt;wangkefeng.wang@huawei.com>
Signed-off-by: default avatarZheng Zengkai <zhengzengkai@huawei.com>
parent 46d673d7

include/linux/swap.h

+9 −0
Original line number Diff line number Diff line
@@ -552,6 +552,15 @@ static inline struct swap_info_struct *swp_swap_info(swp_entry_t entry) 
	return NULL;

}



static inline struct swap_info_struct *get_swap_device(swp_entry_t entry)

{

	return NULL;

}



static inline void put_swap_device(struct swap_info_struct *si)

{

}



#define swap_address_space(entry)		(NULL)

#define get_nr_swap_pages()			0L

#define total_swap_pages			0L

mm/memory.c

+9 −2
Original line number Diff line number Diff line
@@ -3366,6 +3366,7 @@ vm_fault_t do_swap_page(struct vm_fault *vmf) 
{

	struct vm_area_struct *vma = vmf->vma;

	struct page *page = NULL, *swapcache;

	struct swap_info_struct *si = NULL;

	swp_entry_t entry;

	pte_t pte;

	int locked;
@@ -3425,14 +3426,16 @@ vm_fault_t do_swap_page(struct vm_fault *vmf) 
		goto out;

	}



	/* Prevent swapoff from happening to us. */

	si = get_swap_device(entry);

	if (unlikely(!si))

		goto out;



	delayacct_set_flag(DELAYACCT_PF_SWAPIN);

	page = lookup_swap_cache(entry, vma, vmf->address);

	swapcache = page;



	if (!page) {

		struct swap_info_struct *si = swp_swap_info(entry);



		if (data_race(si->flags & SWP_SYNCHRONOUS_IO) &&

		    __swap_count(entry) == 1) {

			/* skip swapcache */
@@ -3604,6 +3607,8 @@ vm_fault_t do_swap_page(struct vm_fault *vmf) 
unlock:

	pte_unmap_unlock(vmf->pte, vmf->ptl);

out:

	if (si)

		put_swap_device(si);

	return ret;

out_nomap:

	pte_unmap_unlock(vmf->pte, vmf->ptl);
@@ -3615,6 +3620,8 @@ vm_fault_t do_swap_page(struct vm_fault *vmf) 
		unlock_page(swapcache);

		put_page(swapcache);

	}

	if (si)

		put_swap_device(si);

	return ret;

}