powerpc/perf: Avoid spurious PMU interrupts after idle

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

diff --git a/fs/block_dev.c b/fs/block_dev.c
index 5db5d1340d69eccf475f0feac7f85665bd6aceb5..99d4e1af5502e45ca1725d94ae08867f0accf2f6 100644 (file)
--- a/fs/block_dev.c
+++ b/fs/block_dev.c
@@ -103,12 +103,11 @@ void invalidate_bdev(struct block_device *bdev)
 {
        struct address_space *mapping = bdev->bd_inode->i_mapping;
 
-       if (mapping->nrpages == 0)
-               return;
-
-       invalidate_bh_lrus();
-       lru_add_drain_all();    /* make sure all lru add caches are flushed */
-       invalidate_mapping_pages(mapping, 0, -1);
+       if (mapping->nrpages) {
+               invalidate_bh_lrus();
+               lru_add_drain_all();    /* make sure all lru add caches are flushed */
+               invalidate_mapping_pages(mapping, 0, -1);
+       }
        /* 99% of the time, we don't need to flush the cleancache on the bdev.
         * But, for the strange corners, lets be cautious
         */
@@ -331,7 +330,7 @@ __blkdev_direct_IO(struct kiocb *iocb, struct iov_iter *iter, int nr_pages)
        struct blk_plug plug;
        struct blkdev_dio *dio;
        struct bio *bio;
-       bool is_read = (iov_iter_rw(iter) == READ);
+       bool is_read = (iov_iter_rw(iter) == READ), is_sync;
        loff_t pos = iocb->ki_pos;
        blk_qc_t qc = BLK_QC_T_NONE;
        int ret;
@@ -344,7 +343,7 @@ __blkdev_direct_IO(struct kiocb *iocb, struct iov_iter *iter, int nr_pages)
        bio_get(bio); /* extra ref for the completion handler */
 
        dio = container_of(bio, struct blkdev_dio, bio);
-       dio->is_sync = is_sync_kiocb(iocb);
+       dio->is_sync = is_sync = is_sync_kiocb(iocb);
        if (dio->is_sync)
                dio->waiter = current;
        else
@@ -398,7 +397,7 @@ __blkdev_direct_IO(struct kiocb *iocb, struct iov_iter *iter, int nr_pages)
        }
        blk_finish_plug(&plug);
 
-       if (!dio->is_sync)
+       if (!is_sync)
                return -EIOCBQUEUED;
 
        for (;;) {
@@ -1422,7 +1421,6 @@ int revalidate_disk(struct gendisk *disk)
 
        if (disk->fops->revalidate_disk)
                ret = disk->fops->revalidate_disk(disk);
-       blk_integrity_revalidate(disk);
        bdev = bdget_disk(disk, 0);
        if (!bdev)
                return ret;
@@ -1742,9 +1740,14 @@ 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;
 
@@ -1823,6 +1826,20 @@ 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;
 
        return blkdev_get(bdev, filp->f_mode, filp);
@@ -1924,6 +1941,9 @@ 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;
 }
@@ -2140,12 +2160,14 @@ 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;
@@ -2160,6 +2182,11 @@ 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;