swap: fix do_swap_page() race with swapoff

jira LE-1907
cve CVE-2024-26759
Rebuild_History Non-Buildable kernel-4.18.0-553.8.1.el8_10
commit-author Miaohe Lin <[email protected]>
commit 2799e77

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/[email protected]
Fixes: 0bcac06 ("mm,swap: skip swapcache for swapin of synchronous device")
	Signed-off-by: Miaohe Lin <[email protected]>
	Reviewed-by: "Huang, Ying" <[email protected]>
	Cc: Alex Shi <[email protected]>
	Cc: David Hildenbrand <[email protected]>
	Cc: Dennis Zhou <[email protected]>
	Cc: Hugh Dickins <[email protected]>
	Cc: Johannes Weiner <[email protected]>
	Cc: Joonsoo Kim <[email protected]>
	Cc: Matthew Wilcox <[email protected]>
	Cc: Michal Hocko <[email protected]>
	Cc: Minchan Kim <[email protected]>
	Cc: Tim Chen <[email protected]>
	Cc: Wei Yang <[email protected]>
	Cc: Yang Shi <[email protected]>
	Cc: Yu Zhao <[email protected]>
	Signed-off-by: Andrew Morton <[email protected]>
	Signed-off-by: Linus Torvalds <[email protected]>
(cherry picked from commit 2799e77)
	Signed-off-by: Jonathan Maple <[email protected]>

Author: PlaidCat

include/linux/swap.h

@@ -496,6 +496,15 @@ 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

@@ -3179,6 +3179,7 @@ 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;
@@ -3206,14 +3207,16 @@ 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 */
@@ -3382,6 +3385,8 @@ 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);
@@ -3393,6 +3398,8 @@ vm_fault_t do_swap_page(struct vm_fault *vmf)
 		unlock_page(swapcache);
 		put_page(swapcache);
 	}
+	if (si)
+		put_swap_device(si);
 	return ret;
 }