UBUNTU: Ubuntu-4.13.0-45.50

[mirror_ubuntu-artful-kernel.git] / fs / block_dev.c

diff --git a/fs/block_dev.c b/fs/block_dev.c
index 9941dc8342dfd7671eb96ad27a736d5220d670c8..ca1732b6364b71055758807ad3162dd7865f707c 100644 (file)
--- a/fs/block_dev.c
+++ b/fs/block_dev.c
@@ -716,10 +716,12 @@ int bdev_write_page(struct block_device *bdev, sector_t sector,
 
        set_page_writeback(page);
        result = ops->rw_page(bdev, sector + get_start_sect(bdev), page, true);
-       if (result)
+       if (result) {
                end_page_writeback(page);
-       else
+       } else {
+               clean_page_buffers(page);
                unlock_page(page);
+       }
        blk_queue_exit(bdev->bd_queue);
        return result;
 }
@@ -1669,9 +1671,14 @@ struct block_device *blkdev_get_by_path(const char *path, fmode_t mode,
                                        void *holder)
 {
        struct block_device *bdev;
+       int perm = 0;
        int err;
 
-       bdev = lookup_bdev(path);
+       if (mode & FMODE_READ)
+               perm |= MAY_READ;
+       if (mode & FMODE_WRITE)
+               perm |= MAY_WRITE;
+       bdev = lookup_bdev(path, perm);
        if (IS_ERR(bdev))
                return bdev;
 
@@ -1750,6 +1757,20 @@ static int blkdev_open(struct inode * inode, struct file * filp)
        if (bdev == NULL)
                return -ENOMEM;
 
+       /*
+        * A negative i_writecount for bdev->bd_inode means that the bdev
+        * or one of its paritions is mounted in a user namespace. Deny
+        * writing for non-root in this case, otherwise an unprivileged
+        * user can attack the kernel by modifying the backing store of a
+        * mounted filesystem.
+        */
+       if ((filp->f_mode & FMODE_WRITE) &&
+           !file_ns_capable(filp, &init_user_ns, CAP_SYS_ADMIN) &&
+           !atomic_inc_unless_negative(&bdev->bd_inode->i_writecount)) {
+               bdput(bdev);
+               return -EBUSY;
+       }
+
        filp->f_mapping = bdev->bd_inode->i_mapping;
        filp->f_wb_err = filemap_sample_wb_err(filp->f_mapping);
 
@@ -1846,6 +1867,9 @@ EXPORT_SYMBOL(blkdev_put);
 static int blkdev_close(struct inode * inode, struct file * filp)
 {
        struct block_device *bdev = I_BDEV(bdev_file_inode(filp));
+       if (filp->f_mode & FMODE_WRITE &&
+           !file_ns_capable(filp, &init_user_ns, CAP_SYS_ADMIN))
+               atomic_dec(&bdev->bd_inode->i_writecount);
        blkdev_put(bdev, filp->f_mode);
        return 0;
 }
@@ -2056,12 +2080,14 @@ EXPORT_SYMBOL(ioctl_by_bdev);
 /**
  * lookup_bdev  - lookup a struct block_device by name
  * @pathname:  special file representing the block device
+ * @mask:      rights to check for (%MAY_READ, %MAY_WRITE, %MAY_EXEC)
  *
  * Get a reference to the blockdevice at @pathname in the current
  * namespace if possible and return it.  Return ERR_PTR(error)
- * otherwise.
+ * otherwise.  If @mask is non-zero, check for access rights to the
+ * inode at @pathname.
  */
-struct block_device *lookup_bdev(const char *pathname)
+struct block_device *lookup_bdev(const char *pathname, int mask)
 {
        struct block_device *bdev;
        struct inode *inode;
@@ -2076,6 +2102,11 @@ struct block_device *lookup_bdev(const char *pathname)
                return ERR_PTR(error);
 
        inode = d_backing_inode(path.dentry);
+       if (mask != 0 && !capable(CAP_SYS_ADMIN)) {
+               error = __inode_permission(inode, mask);
+               if (error)
+                       goto fail;
+       }
        error = -ENOTBLK;
        if (!S_ISBLK(inode->i_mode))
                goto fail;