mm, swap: bounds check swap_info array accesses to avoid NULL derefs

Dan Carpenter reports a potential NULL dereference in
get_swap_page_of_type:

  Smatch complains that the NULL checks on "si" aren't consistent.  This
  seems like a real bug because we have not ensured that the type is
  valid and so "si" can be NULL.

Add the missing check for NULL, taking care to use a read barrier to
ensure CPU1 observes CPU0's updates in the correct order:

     CPU0                           CPU1
     alloc_swap_info()              if (type >= nr_swapfiles)
       swap_info[type] = p              /* handle invalid entry */
       smp_wmb()                    smp_rmb()
       ++nr_swapfiles               p = swap_info[type]

Without smp_rmb, CPU1 might observe CPU0's write to nr_swapfiles before
CPU0's write to swap_info[type] and read NULL from swap_info[type].

Ying Huang noticed other places in swapfile.c don't order these reads
properly.  Introduce swap_type_to_swap_info to encourage correct usage.

Use READ_ONCE and WRITE_ONCE to follow the Linux Kernel Memory Model
(see tools/memory-model/Documentation/explanation.txt).

This ordering need not be enforced in places where swap_lock is held
(e.g.  si_swapinfo) because swap_lock serializes updates to nr_swapfiles
and the swap_info array.

Link: http://lkml.kernel.org/r/20190131024410.29859-1-daniel.m.jordan@oracle.com
Fixes: ec8acf20afb8 ("swap: add per-partition lock for swapfile")
Signed-off-by: Daniel Jordan <daniel.m.jordan@oracle.com>
Reported-by: Dan Carpenter <dan.carpenter@oracle.com>
Suggested-by: "Huang, Ying" <ying.huang@intel.com>
Reviewed-by: Andrea Parri <andrea.parri@amarulasolutions.com>
Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Alan Stern <stern@rowland.harvard.edu>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Dave Hansen <dave.hansen@linux.intel.com>
Cc: Omar Sandoval <osandov@fb.com>
Cc: Paul McKenney <paulmck@linux.vnet.ibm.com>
Cc: Shaohua Li <shli@kernel.org>
Cc: Stephen Rothwell <sfr@canb.auug.org.au>
Cc: Tejun Heo <tj@kernel.org>
Cc: Will Deacon <will.deacon@arm.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

diff --git a/mm/swapfile.c b/mm/swapfile.c
index 6de4698..57e9b1b 100644 (file)
--- a/mm/swapfile.c
+++ b/mm/swapfile.c
@@ -98,6 +98,15 @@ static atomic_t proc_poll_event = ATOMIC_INIT(0);
 
 atomic_t nr_rotate_swap = ATOMIC_INIT(0);
 
+static struct swap_info_struct *swap_type_to_swap_info(int type)
+{
+       if (type >= READ_ONCE(nr_swapfiles))
+               return NULL;
+
+       smp_rmb();      /* Pairs with smp_wmb in alloc_swap_info. */
+       return READ_ONCE(swap_info[type]);
+}
+
 static inline unsigned char swap_count(unsigned char ent)
 {
        return ent & ~SWAP_HAS_CACHE;   /* may include COUNT_CONTINUED flag */
@@ -1044,12 +1053,14 @@ noswap:
 /* The only caller of this function is now suspend routine */
 swp_entry_t get_swap_page_of_type(int type)
 {
-       struct swap_info_struct *si;
+       struct swap_info_struct *si = swap_type_to_swap_info(type);
        pgoff_t offset;
 
-       si = swap_info[type];
+       if (!si)
+               goto fail;
+
        spin_lock(&si->lock);
-       if (si && (si->flags & SWP_WRITEOK)) {
+       if (si->flags & SWP_WRITEOK) {
                atomic_long_dec(&nr_swap_pages);
                /* This is called for allocating swap entry, not cache */
                offset = scan_swap_map(si, 1);
@@ -1060,6 +1071,7 @@ swp_entry_t get_swap_page_of_type(int type)
                atomic_long_inc(&nr_swap_pages);
        }
        spin_unlock(&si->lock);
+fail:
        return (swp_entry_t) {0};
 }
 
@@ -1071,9 +1083,9 @@ static struct swap_info_struct *__swap_info_get(swp_entry_t entry)
        if (!entry.val)
                goto out;
        type = swp_type(entry);
-       if (type >= nr_swapfiles)
+       p = swap_type_to_swap_info(type);
+       if (!p)
                goto bad_nofile;
-       p = swap_info[type];
        if (!(p->flags & SWP_USED))
                goto bad_device;
        offset = swp_offset(entry);
@@ -1697,10 +1709,9 @@ int swap_type_of(dev_t device, sector_t offset, struct block_device **bdev_p)
 sector_t swapdev_block(int type, pgoff_t offset)
 {
        struct block_device *bdev;
+       struct swap_info_struct *si = swap_type_to_swap_info(type);
 
-       if ((unsigned int)type >= nr_swapfiles)
-               return 0;
-       if (!(swap_info[type]->flags & SWP_WRITEOK))
+       if (!si || !(si->flags & SWP_WRITEOK))
                return 0;
        return map_swap_entry(swp_entry(type, offset), &bdev);
 }
@@ -2151,7 +2162,7 @@ static sector_t map_swap_entry(swp_entry_t entry, struct block_device **bdev)
        struct swap_extent *se;
        pgoff_t offset;
 
-       sis = swap_info[swp_type(entry)];
+       sis = swp_swap_info(entry);
        *bdev = sis->bdev;
 
        offset = swp_offset(entry);
@@ -2593,9 +2604,7 @@ static void *swap_start(struct seq_file *swap, loff_t *pos)
        if (!l)
                return SEQ_START_TOKEN;
 
-       for (type = 0; type < nr_swapfiles; type++) {
-               smp_rmb();      /* read nr_swapfiles before swap_info[type] */
-               si = swap_info[type];
+       for (type = 0; (si = swap_type_to_swap_info(type)); type++) {
                if (!(si->flags & SWP_USED) || !si->swap_map)
                        continue;
                if (!--l)
@@ -2615,9 +2624,7 @@ static void *swap_next(struct seq_file *swap, void *v, loff_t *pos)
        else
                type = si->type + 1;
 
-       for (; type < nr_swapfiles; type++) {
-               smp_rmb();      /* read nr_swapfiles before swap_info[type] */
-               si = swap_info[type];
+       for (; (si = swap_type_to_swap_info(type)); type++) {
                if (!(si->flags & SWP_USED) || !si->swap_map)
                        continue;
                ++*pos;
@@ -2724,14 +2731,14 @@ static struct swap_info_struct *alloc_swap_info(void)
        }
        if (type >= nr_swapfiles) {
                p->type = type;
-               swap_info[type] = p;
+               WRITE_ONCE(swap_info[type], p);
                /*
                 * Write swap_info[type] before nr_swapfiles, in case a
                 * racing procfs swap_start() or swap_next() is reading them.
                 * (We never shrink nr_swapfiles, we never free this entry.)
                 */
                smp_wmb();
-               nr_swapfiles++;
+               WRITE_ONCE(nr_swapfiles, nr_swapfiles + 1);
        } else {
                kvfree(p);
                p = swap_info[type];
@@ -3251,7 +3258,7 @@ static int __swap_duplicate(swp_entry_t entry, unsigned char usage)
 {
        struct swap_info_struct *p;
        struct swap_cluster_info *ci;
-       unsigned long offset, type;
+       unsigned long offset;
        unsigned char count;
        unsigned char has_cache;
        int err = -EINVAL;
@@ -3259,10 +3266,10 @@ static int __swap_duplicate(swp_entry_t entry, unsigned char usage)
        if (non_swap_entry(entry))
                goto out;
 
-       type = swp_type(entry);
-       if (type >= nr_swapfiles)
+       p = swp_swap_info(entry);
+       if (!p)
                goto bad_file;
-       p = swap_info[type];
+
        offset = swp_offset(entry);
        if (unlikely(offset >= p->max))
                goto out;
@@ -3359,7 +3366,7 @@ int swapcache_prepare(swp_entry_t entry)
 
 struct swap_info_struct *swp_swap_info(swp_entry_t entry)
 {
-       return swap_info[swp_type(entry)];
+       return swap_type_to_swap_info(swp_type(entry));
 }
 
 struct swap_info_struct *page_swap_info(struct page *page)