swap: fix do_swap_page() race with swapoff

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: 0bcac06f27d7 ("mm,swap: skip swapcache for swapin of synchronous device")
Signed-off-by: Miaohe Lin <linmiaohe@huawei.com>
Reviewed-by: "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: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

diff --git a/include/linux/swap.h b/include/linux/swap.h
index c9e7fea..46d51d0 100644 (file)
--- a/include/linux/swap.h
+++ b/include/linux/swap.h
@@ -527,6 +527,15 @@ 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

diff --git a/mm/memory.c b/mm/memory.c
index 486f4a2..b15367c 100644 (file)
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -3353,6 +3353,7 @@ 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;
@@ -3380,14 +3381,16 @@ 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(current, 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 */
@@ -3556,6 +3559,8 @@ 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);
@@ -3567,6 +3572,8 @@ out_release:
                unlock_page(swapcache);
                put_page(swapcache);
        }
+       if (si)
+               put_swap_device(si);
        return ret;
 }