block: enable dax for raw block devices

If an application wants exclusive access to all of the persistent memory
provided by an NVDIMM namespace it can use this raw-block-dax facility
to forgo establishing a filesystem.  This capability is targeted
primarily to hypervisors wanting to provision persistent memory for
guests.  It can be disabled / enabled dynamically via the new BLKDAXSET
ioctl.

Cc: Jeff Moyer <jmoyer@redhat.com>
Cc: Christoph Hellwig <hch@lst.de>
Cc: Dave Chinner <david@fromorbit.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Ross Zwisler <ross.zwisler@linux.intel.com>
Reported-by: kbuild test robot <fengguang.wu@intel.com>
Reviewed-by: Jan Kara <jack@suse.com>
Signed-off-by: Dan Williams <dan.j.williams@intel.com>

1 files changed, 61 insertions, 0 deletions

diff --git a/block/ioctl.c b/block/ioctl.c
index 0918aed2d847..7a964d842913 100644
--- a/block/ioctl.c
+++ b/block/ioctl.c
@@ -406,6 +406,62 @@ static inline int is_unrecognized_ioctl(int ret)
                 ret == -ENOIOCTLCMD;
 }
 
+#ifdef CONFIG_FS_DAX
+bool blkdev_dax_capable(struct block_device *bdev)
+{
+        struct gendisk *disk = bdev->bd_disk;
+
+        if (!disk->fops->direct_access)
+                return false;
+
+        /*
+         * If the partition is not aligned on a page boundary, we can't
+         * do dax I/O to it.
+         */
+        if ((bdev->bd_part->start_sect % (PAGE_SIZE / 512))
+                        || (bdev->bd_part->nr_sects % (PAGE_SIZE / 512)))
+                return false;
+
+        return true;
+}
+
+static int blkdev_daxset(struct block_device *bdev, unsigned long argp)
+{
+        unsigned long arg;
+        int rc = 0;
+
+        if (!capable(CAP_SYS_ADMIN))
+                return -EACCES;
+
+        if (get_user(arg, (int __user *)(argp)))
+                return -EFAULT;
+        arg = !!arg;
+        if (arg == !!(bdev->bd_inode->i_flags & S_DAX))
+                return 0;
+
+        if (arg)
+                arg = S_DAX;
+
+        if (arg && !blkdev_dax_capable(bdev))
+                return -ENOTTY;
+
+        mutex_lock(&bdev->bd_inode->i_mutex);
+        if (bdev->bd_map_count == 0)
+                inode_set_flags(bdev->bd_inode, arg, S_DAX);
+        else
+                rc = -EBUSY;
+        mutex_unlock(&bdev->bd_inode->i_mutex);
+        return rc;
+}
+#else
+static int blkdev_daxset(struct block_device *bdev, int arg)
+{
+        if (arg)
+                return -ENOTTY;
+        return 0;
+}
+#endif
+
 static int blkdev_flushbuf(struct block_device *bdev, fmode_t mode,
                 unsigned cmd, unsigned long arg)
 {
@@ -568,6 +624,11 @@ int blkdev_ioctl(struct block_device *bdev, fmode_t mode, unsigned cmd,
         case BLKTRACESETUP:
         case BLKTRACETEARDOWN:
                 return blk_trace_ioctl(bdev, cmd, argp);
+        case BLKDAXSET:
+                return blkdev_daxset(bdev, arg);
+        case BLKDAXGET:
+                return put_int(arg, !!(bdev->bd_inode->i_flags & S_DAX));
+                break;
         case IOC_PR_REGISTER:
                 return blkdev_pr_register(bdev, argp);
         case IOC_PR_RESERVE: