block: fine-granular CAP_SYS_ADMIN for Persistent Reservation

Allow of unprivileged Persistent Reservation operations on devices
if the write permission check on the device node has passed.

brw-rw---- 1 root disk 259, 0 Jun 13 07:09 /dev/nvme0n1

In the example above, the "disk" group of nvme0n1 is also allowed to
make reservations on the device even without CAP_SYS_ADMIN.

Signed-off-by: Jingbo Xu <jefflexu@linux.alibaba.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Link: https://lore.kernel.org/r/20230613084008.93795-3-jefflexu@linux.alibaba.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>

Author: lostjeffle

block/ioctl.c

@@ -254,25 +254,28 @@ int blkdev_compat_ptr_ioctl(struct block_device *bdev, blk_mode_t mode,
 EXPORT_SYMBOL(blkdev_compat_ptr_ioctl);
 #endif
 
-static bool blkdev_pr_allowed(struct block_device *bdev)
+static bool blkdev_pr_allowed(struct block_device *bdev, blk_mode_t mode)
 {
 	/* no sense to make reservations for partitions */
 	if (bdev_is_partition(bdev))
 		return false;
 
 	if (capable(CAP_SYS_ADMIN))
 		return true;
-
-	return false;
+	/*
+	 * Only allow unprivileged reservations if the file descriptor is open
+	 * for writing.
+	 */
+	return mode & BLK_OPEN_WRITE;
 }
 
-static int blkdev_pr_register(struct block_device *bdev,
+static int blkdev_pr_register(struct block_device *bdev, blk_mode_t mode,
 		struct pr_registration __user *arg)
 {
 	const struct pr_ops *ops = bdev->bd_disk->fops->pr_ops;
 	struct pr_registration reg;
 
-	if (!blkdev_pr_allowed(bdev))
+	if (!blkdev_pr_allowed(bdev, mode))
 		return -EPERM;
 	if (!ops || !ops->pr_register)
 		return -EOPNOTSUPP;
@@ -284,13 +287,13 @@ static int blkdev_pr_register(struct block_device *bdev,
 	return ops->pr_register(bdev, reg.old_key, reg.new_key, reg.flags);
 }
 
-static int blkdev_pr_reserve(struct block_device *bdev,
+static int blkdev_pr_reserve(struct block_device *bdev, blk_mode_t mode,
 		struct pr_reservation __user *arg)
 {
 	const struct pr_ops *ops = bdev->bd_disk->fops->pr_ops;
 	struct pr_reservation rsv;
 
-	if (!blkdev_pr_allowed(bdev))
+	if (!blkdev_pr_allowed(bdev, mode))
 		return -EPERM;
 	if (!ops || !ops->pr_reserve)
 		return -EOPNOTSUPP;
@@ -302,13 +305,13 @@ static int blkdev_pr_reserve(struct block_device *bdev,
 	return ops->pr_reserve(bdev, rsv.key, rsv.type, rsv.flags);
 }
 
-static int blkdev_pr_release(struct block_device *bdev,
+static int blkdev_pr_release(struct block_device *bdev, blk_mode_t mode,
 		struct pr_reservation __user *arg)
 {
 	const struct pr_ops *ops = bdev->bd_disk->fops->pr_ops;
 	struct pr_reservation rsv;
 
-	if (!blkdev_pr_allowed(bdev))
+	if (!blkdev_pr_allowed(bdev, mode))
 		return -EPERM;
 	if (!ops || !ops->pr_release)
 		return -EOPNOTSUPP;
@@ -320,13 +323,13 @@ static int blkdev_pr_release(struct block_device *bdev,
 	return ops->pr_release(bdev, rsv.key, rsv.type);
 }
 
-static int blkdev_pr_preempt(struct block_device *bdev,
+static int blkdev_pr_preempt(struct block_device *bdev, blk_mode_t mode,
 		struct pr_preempt __user *arg, bool abort)
 {
 	const struct pr_ops *ops = bdev->bd_disk->fops->pr_ops;
 	struct pr_preempt p;
 
-	if (!blkdev_pr_allowed(bdev))
+	if (!blkdev_pr_allowed(bdev, mode))
 		return -EPERM;
 	if (!ops || !ops->pr_preempt)
 		return -EOPNOTSUPP;
@@ -338,13 +341,13 @@ static int blkdev_pr_preempt(struct block_device *bdev,
 	return ops->pr_preempt(bdev, p.old_key, p.new_key, p.type, abort);
 }
 
-static int blkdev_pr_clear(struct block_device *bdev,
+static int blkdev_pr_clear(struct block_device *bdev, blk_mode_t mode,
 		struct pr_clear __user *arg)
 {
 	const struct pr_ops *ops = bdev->bd_disk->fops->pr_ops;
 	struct pr_clear c;
 
-	if (!blkdev_pr_allowed(bdev))
+	if (!blkdev_pr_allowed(bdev, mode))
 		return -EPERM;
 	if (!ops || !ops->pr_clear)
 		return -EOPNOTSUPP;
@@ -546,17 +549,17 @@ static int blkdev_common_ioctl(struct block_device *bdev, blk_mode_t mode,
 	case BLKTRACETEARDOWN:
 		return blk_trace_ioctl(bdev, cmd, argp);
 	case IOC_PR_REGISTER:
-		return blkdev_pr_register(bdev, argp);
+		return blkdev_pr_register(bdev, mode, argp);
 	case IOC_PR_RESERVE:
-		return blkdev_pr_reserve(bdev, argp);
+		return blkdev_pr_reserve(bdev, mode, argp);
 	case IOC_PR_RELEASE:
-		return blkdev_pr_release(bdev, argp);
+		return blkdev_pr_release(bdev, mode, argp);
 	case IOC_PR_PREEMPT:
-		return blkdev_pr_preempt(bdev, argp, false);
+		return blkdev_pr_preempt(bdev, mode, argp, false);
 	case IOC_PR_PREEMPT_ABORT:
-		return blkdev_pr_preempt(bdev, argp, true);
+		return blkdev_pr_preempt(bdev, mode, argp, true);
 	case IOC_PR_CLEAR:
-		return blkdev_pr_clear(bdev, argp);
+		return blkdev_pr_clear(bdev, mode, argp);
 	default:
 		return -ENOIOCTLCMD;
 	}