mm: thp: make deferred split shrinker memcg aware

[linux.git] / mm / swapfile.c

diff --git a/mm/swapfile.c b/mm/swapfile.c
index 0789a762ce2f49add4f8823c38ba366d88bda9e1..dab43523afdd351426ef5c92e5306a04a9820b36 100644 (file)
--- a/mm/swapfile.c
+++ b/mm/swapfile.c
@@ -2368,9 +2368,8 @@ EXPORT_SYMBOL_GPL(add_swap_extent);
  * requirements, they are simply tossed out - we will never use those blocks
  * for swapping.
  *
- * For S_ISREG swapfiles we set S_SWAPFILE across the life of the swapon.  This
- * prevents root from shooting her foot off by ftruncating an in-use swapfile,
- * which will scribble on the fs.
+ * For all swap devices we set S_SWAPFILE across the life of the swapon.  This
+ * prevents users from writing to the swap device, which will corrupt memory.
  *
  * The amount of disk space which a single swap extent represents varies.
  * Typically it is in the 1-4 megabyte range.  So we can have hundreds of
@@ -2661,13 +2660,14 @@ SYSCALL_DEFINE1(swapoff, const char __user *, specialfile)
        inode = mapping->host;
        if (S_ISBLK(inode->i_mode)) {
                struct block_device *bdev = I_BDEV(inode);
+
                set_blocksize(bdev, old_block_size);
                blkdev_put(bdev, FMODE_READ | FMODE_WRITE | FMODE_EXCL);
-       } else {
-               inode_lock(inode);
-               inode->i_flags &= ~S_SWAPFILE;
-               inode_unlock(inode);
        }
+
+       inode_lock(inode);
+       inode->i_flags &= ~S_SWAPFILE;
+       inode_unlock(inode);
        filp_close(swap_file, NULL);
 
        /*
@@ -2890,11 +2890,11 @@ static int claim_swapfile(struct swap_info_struct *p, struct inode *inode)
                p->flags |= SWP_BLKDEV;
        } else if (S_ISREG(inode->i_mode)) {
                p->bdev = inode->i_sb->s_bdev;
-               inode_lock(inode);
-               if (IS_SWAPFILE(inode))
-                       return -EBUSY;
-       } else
-               return -EINVAL;
+       }
+
+       inode_lock(inode);
+       if (IS_SWAPFILE(inode))
+               return -EBUSY;
 
        return 0;
 }
@@ -3275,6 +3275,17 @@ SYSCALL_DEFINE2(swapon, const char __user *, specialfile, int, swap_flags)
        if (error)
                goto bad_swap;
 
+       /*
+        * Flush any pending IO and dirty mappings before we start using this
+        * swap device.
+        */
+       inode->i_flags |= S_SWAPFILE;
+       error = inode_drain_writes(inode);
+       if (error) {
+               inode->i_flags &= ~S_SWAPFILE;
+               goto bad_swap;
+       }
+
        mutex_lock(&swapon_mutex);
        prio = -1;
        if (swap_flags & SWAP_FLAG_PREFER)
@@ -3295,8 +3306,6 @@ SYSCALL_DEFINE2(swapon, const char __user *, specialfile, int, swap_flags)
        atomic_inc(&proc_poll_event);
        wake_up_interruptible(&proc_poll_wait);
 
-       if (S_ISREG(inode->i_mode))
-               inode->i_flags |= S_SWAPFILE;
        error = 0;
        goto out;
 bad_swap:
@@ -3318,7 +3327,7 @@ SYSCALL_DEFINE2(swapon, const char __user *, specialfile, int, swap_flags)
        if (inced_nr_rotate_swap)
                atomic_dec(&nr_rotate_swap);
        if (swap_file) {
-               if (inode && S_ISREG(inode->i_mode)) {
+               if (inode) {
                        inode_unlock(inode);
                        inode = NULL;
                }
@@ -3331,7 +3340,7 @@ SYSCALL_DEFINE2(swapon, const char __user *, specialfile, int, swap_flags)
        }
        if (name)
                putname(name);
-       if (inode && S_ISREG(inode->i_mode))
+       if (inode)
                inode_unlock(inode);
        if (!error)
                enable_swap_slots_cache();