Add BLKDISCARD ioctl to allow userspace to discard sectors

We may well want mkfs tools to use this to mark the whole device as
unwanted before they format it, for example.

The ioctl takes a pair of uint64_ts, which are start offset and length
in _bytes_. Although at the moment it might make sense for them both to
be in 512-byte sectors, I don't want to limit the ABI to that.

Signed-off-by: David Woodhouse <David.Woodhouse@intel.com>
Signed-off-by: Jens Axboe <jens.axboe@oracle.com>

3 files changed, 78 insertions, 0 deletions

diff --git a/block/compat_ioctl.c b/block/compat_ioctl.c
index c23177e4623..1e559fba7bd 100644
--- a/block/compat_ioctl.c
+++ b/block/compat_ioctl.c
@@ -788,6 +788,7 @@ long compat_blkdev_ioctl(struct file *file, unsigned cmd, unsigned long arg)
 		return compat_hdio_getgeo(disk, bdev, compat_ptr(arg));
 	case BLKFLSBUF:
 	case BLKROSET:
+	case BLKDISCARD:
 	/*
 	 * the ones below are implemented in blkdev_locked_ioctl,
 	 * but we call blkdev_ioctl, which gets the lock for us
diff --git a/block/ioctl.c b/block/ioctl.c
index 77185e5c026..342298bb608 100644
--- a/block/ioctl.c
+++ b/block/ioctl.c
@@ -111,6 +111,69 @@ static int blkdev_reread_part(struct block_device *bdev)
 	return res;
 }
 
+static void blk_ioc_discard_endio(struct bio *bio, int err)
+{
+	if (err) {
+		if (err == -EOPNOTSUPP)
+			set_bit(BIO_EOPNOTSUPP, &bio->bi_flags);
+		clear_bit(BIO_UPTODATE, &bio->bi_flags);
+	}
+	complete(bio->bi_private);
+}
+
+static int blk_ioctl_discard(struct block_device *bdev, uint64_t start,
+			     uint64_t len)
+{
+	struct request_queue *q = bdev_get_queue(bdev);
+	int ret = 0;
+
+	if (start & 511)
+		return -EINVAL;
+	if (len & 511)
+		return -EINVAL;
+	start >>= 9;
+	len >>= 9;
+
+	if (start + len > (bdev->bd_inode->i_size >> 9))
+		return -EINVAL;
+
+	if (!q->prepare_discard_fn)
+		return -EOPNOTSUPP;
+
+	while (len && !ret) {
+		DECLARE_COMPLETION_ONSTACK(wait);
+		struct bio *bio;
+
+		bio = bio_alloc(GFP_KERNEL, 0);
+		if (!bio)
+			return -ENOMEM;
+
+		bio->bi_end_io = blk_ioc_discard_endio;
+		bio->bi_bdev = bdev;
+		bio->bi_private = &wait;
+		bio->bi_sector = start;
+
+		if (len > q->max_hw_sectors) {
+			bio->bi_size = q->max_hw_sectors << 9;
+			len -= q->max_hw_sectors;
+			start += q->max_hw_sectors;
+		} else {
+			bio->bi_size = len << 9;
+			len = 0;
+		}
+		submit_bio(WRITE_DISCARD, bio);
+
+		wait_for_completion(&wait);
+
+		if (bio_flagged(bio, BIO_EOPNOTSUPP))
+			ret = -EOPNOTSUPP;
+		else if (!bio_flagged(bio, BIO_UPTODATE))
+			ret = -EIO;
+		bio_put(bio);
+	}
+	return ret;
+}
+
 static int put_ushort(unsigned long arg, unsigned short val)
 {
 	return put_user(val, (unsigned short __user *)arg);
@@ -258,6 +321,19 @@ int blkdev_ioctl(struct inode *inode, struct file *file, unsigned cmd,
 		set_device_ro(bdev, n);
 		unlock_kernel();
 		return 0;
+
+	case BLKDISCARD: {
+		uint64_t range[2];
+
+		if (!(file->f_mode & FMODE_WRITE))
+			return -EBADF;
+
+		if (copy_from_user(range, (void __user *)arg, sizeof(range)))
+			return -EFAULT;
+
+		return blk_ioctl_discard(bdev, range[0], range[1]);
+	}
+
 	case HDIO_GETGEO: {
 		struct hd_geometry geo;
 
diff --git a/include/linux/fs.h b/include/linux/fs.h
index eb013131913..88358ca6af2 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -223,6 +223,7 @@ extern int dir_notify_enable;
 #define BLKTRACESTART _IO(0x12,116)
 #define BLKTRACESTOP _IO(0x12,117)
 #define BLKTRACETEARDOWN _IO(0x12,118)
+#define BLKDISCARD _IO(0x12,119)
 
 #define BMAP_IOCTL 1		/* obsolete - kept for compatibility */
 #define FIBMAP	   _IO(0x00,1)	/* bmap access */