1 files changed, 668 insertions, 314 deletions

diff --git a/block/ioctl.c b/block/ioctl.c
index 4825c78a6baa..61feed686418 100644
--- a/block/ioctl.c
+++ b/block/ioctl.c
@@ -1,4 +1,6 @@
+// SPDX-License-Identifier: GPL-2.0
 #include <linux/capability.h>
+#include <linux/compat.h>
 #include <linux/blkdev.h>
 #include <linux/export.h>
 #include <linux/gfp.h>
@@ -9,235 +11,217 @@
 #include <linux/blktrace_api.h>
 #include <linux/pr.h>
 #include <linux/uaccess.h>
-
-static int blkpg_ioctl(struct block_device *bdev, struct blkpg_ioctl_arg __user *arg)
+#include <linux/pagemap.h>
+#include <linux/io_uring/cmd.h>
+#include <linux/blk-integrity.h>
+#include <uapi/linux/blkdev.h>
+#include "blk.h"
+#include "blk-crypto-internal.h"
+
+static int blkpg_do_ioctl(struct block_device *bdev,
+			  struct blkpg_partition __user *upart, int op)
 {
-	struct block_device *bdevp;
-	struct gendisk *disk;
-	struct hd_struct *part, *lpart;
-	struct blkpg_ioctl_arg a;
+	struct gendisk *disk = bdev->bd_disk;
 	struct blkpg_partition p;
-	struct disk_part_iter piter;
-	long long start, length;
-	int partno;
+	sector_t start, length, capacity, end;
 
 	if (!capable(CAP_SYS_ADMIN))
 		return -EACCES;
-	if (copy_from_user(&a, arg, sizeof(struct blkpg_ioctl_arg)))
+	if (copy_from_user(&p, upart, sizeof(struct blkpg_partition)))
 		return -EFAULT;
-	if (copy_from_user(&p, a.data, sizeof(struct blkpg_partition)))
-		return -EFAULT;
-	disk = bdev->bd_disk;
-	if (bdev != bdev->bd_contains)
+	if (bdev_is_partition(bdev))
 		return -EINVAL;
-	partno = p.pno;
-	if (partno <= 0)
+
+	if (p.pno <= 0)
+		return -EINVAL;
+
+	if (op == BLKPG_DEL_PARTITION)
+		return bdev_del_partition(disk, p.pno);
+
+	if (p.start < 0 || p.length <= 0 || LLONG_MAX - p.length < p.start)
+		return -EINVAL;
+	/* Check that the partition is aligned to the block size */
+	if (!IS_ALIGNED(p.start | p.length, bdev_logical_block_size(bdev)))
+		return -EINVAL;
+
+	start = p.start >> SECTOR_SHIFT;
+	length = p.length >> SECTOR_SHIFT;
+	capacity = get_capacity(disk);
+
+	if (check_add_overflow(start, length, &end))
+		return -EINVAL;
+
+	if (start >= capacity || end > capacity)
+		return -EINVAL;
+
+	switch (op) {
+	case BLKPG_ADD_PARTITION:
+		return bdev_add_partition(disk, p.pno, start, length);
+	case BLKPG_RESIZE_PARTITION:
+		return bdev_resize_partition(disk, p.pno, start, length);
+	default:
 		return -EINVAL;
-	switch (a.op) {
-		case BLKPG_ADD_PARTITION:
-			start = p.start >> 9;
-			length = p.length >> 9;
-			/* check for fit in a hd_struct */
-			if (sizeof(sector_t) == sizeof(long) &&
-			    sizeof(long long) > sizeof(long)) {
-				long pstart = start, plength = length;
-				if (pstart != start || plength != length
-				    || pstart < 0 || plength < 0 || partno > 65535)
-					return -EINVAL;
-			}
-			/* check if partition is aligned to blocksize */
-			if (p.start & (bdev_logical_block_size(bdev) - 1))
-				return -EINVAL;
-
-			mutex_lock(&bdev->bd_mutex);
-
-			/* overlap? */
-			disk_part_iter_init(&piter, disk,
-					    DISK_PITER_INCL_EMPTY);
-			while ((part = disk_part_iter_next(&piter))) {
-				if (!(start + length <= part->start_sect ||
-				      start >= part->start_sect + part->nr_sects)) {
-					disk_part_iter_exit(&piter);
-					mutex_unlock(&bdev->bd_mutex);
-					return -EBUSY;
-				}
-			}
-			disk_part_iter_exit(&piter);
-
-			/* all seems OK */
-			part = add_partition(disk, partno, start, length,
-					     ADDPART_FLAG_NONE, NULL);
-			mutex_unlock(&bdev->bd_mutex);
-			return PTR_ERR_OR_ZERO(part);
-		case BLKPG_DEL_PARTITION:
-			part = disk_get_part(disk, partno);
-			if (!part)
-				return -ENXIO;
-
-			bdevp = bdget(part_devt(part));
-			disk_put_part(part);
-			if (!bdevp)
-				return -ENOMEM;
-
-			mutex_lock(&bdevp->bd_mutex);
-			if (bdevp->bd_openers) {
-				mutex_unlock(&bdevp->bd_mutex);
-				bdput(bdevp);
-				return -EBUSY;
-			}
-			/* all seems OK */
-			fsync_bdev(bdevp);
-			invalidate_bdev(bdevp);
-
-			mutex_lock_nested(&bdev->bd_mutex, 1);
-			delete_partition(disk, partno);
-			mutex_unlock(&bdev->bd_mutex);
-			mutex_unlock(&bdevp->bd_mutex);
-			bdput(bdevp);
-
-			return 0;
-		case BLKPG_RESIZE_PARTITION:
-			start = p.start >> 9;
-			/* new length of partition in bytes */
-			length = p.length >> 9;
-			/* check for fit in a hd_struct */
-			if (sizeof(sector_t) == sizeof(long) &&
-			    sizeof(long long) > sizeof(long)) {
-				long pstart = start, plength = length;
-				if (pstart != start || plength != length
-				    || pstart < 0 || plength < 0)
-					return -EINVAL;
-			}
-			part = disk_get_part(disk, partno);
-			if (!part)
-				return -ENXIO;
-			bdevp = bdget(part_devt(part));
-			if (!bdevp) {
-				disk_put_part(part);
-				return -ENOMEM;
-			}
-			mutex_lock(&bdevp->bd_mutex);
-			mutex_lock_nested(&bdev->bd_mutex, 1);
-			if (start != part->start_sect) {
-				mutex_unlock(&bdevp->bd_mutex);
-				mutex_unlock(&bdev->bd_mutex);
-				bdput(bdevp);
-				disk_put_part(part);
-				return -EINVAL;
-			}
-			/* overlap? */
-			disk_part_iter_init(&piter, disk,
-					    DISK_PITER_INCL_EMPTY);
-			while ((lpart = disk_part_iter_next(&piter))) {
-				if (lpart->partno != partno &&
-				   !(start + length <= lpart->start_sect ||
-				   start >= lpart->start_sect + lpart->nr_sects)
-				   ) {
-					disk_part_iter_exit(&piter);
-					mutex_unlock(&bdevp->bd_mutex);
-					mutex_unlock(&bdev->bd_mutex);
-					bdput(bdevp);
-					disk_put_part(part);
-					return -EBUSY;
-				}
-			}
-			disk_part_iter_exit(&piter);
-			part_nr_sects_write(part, (sector_t)length);
-			i_size_write(bdevp->bd_inode, p.length);
-			mutex_unlock(&bdevp->bd_mutex);
-			mutex_unlock(&bdev->bd_mutex);
-			bdput(bdevp);
-			disk_put_part(part);
-			return 0;
-		default:
-			return -EINVAL;
 	}
 }
 
-/*
- * This is an exported API for the block driver, and will not
- * acquire bd_mutex. This API should be used in case that
- * caller has held bd_mutex already.
- */
-int __blkdev_reread_part(struct block_device *bdev)
+static int blkpg_ioctl(struct block_device *bdev,
+		       struct blkpg_ioctl_arg __user *arg)
 {
-	struct gendisk *disk = bdev->bd_disk;
+	struct blkpg_partition __user *udata;
+	int op;
 
-	if (!disk_part_scan_enabled(disk) || bdev != bdev->bd_contains)
-		return -EINVAL;
-	if (!capable(CAP_SYS_ADMIN))
-		return -EACCES;
+	if (get_user(op, &arg->op) || get_user(udata, &arg->data))
+		return -EFAULT;
+
+	return blkpg_do_ioctl(bdev, udata, op);
+}
+
+#ifdef CONFIG_COMPAT
+struct compat_blkpg_ioctl_arg {
+	compat_int_t op;
+	compat_int_t flags;
+	compat_int_t datalen;
+	compat_caddr_t data;
+};
+
+static int compat_blkpg_ioctl(struct block_device *bdev,
+			      struct compat_blkpg_ioctl_arg __user *arg)
+{
+	compat_caddr_t udata;
+	int op;
 
-	lockdep_assert_held(&bdev->bd_mutex);
+	if (get_user(op, &arg->op) || get_user(udata, &arg->data))
+		return -EFAULT;
 
-	return rescan_partitions(disk, bdev);
+	return blkpg_do_ioctl(bdev, compat_ptr(udata), op);
 }
-EXPORT_SYMBOL(__blkdev_reread_part);
+#endif
 
 /*
- * This is an exported API for the block driver, and will
- * try to acquire bd_mutex. If bd_mutex has been held already
- * in current context, please call __blkdev_reread_part().
- *
- * Make sure the held locks in current context aren't required
- * in open()/close() handler and I/O path for avoiding ABBA deadlock:
- * - bd_mutex is held before calling block driver's open/close
- *   handler
- * - reading partition table may submit I/O to the block device
+ * Check that [start, start + len) is a valid range from the block device's
+ * perspective, including verifying that it can be correctly translated into
+ * logical block addresses.
  */
-int blkdev_reread_part(struct block_device *bdev)
+static int blk_validate_byte_range(struct block_device *bdev,
+				   uint64_t start, uint64_t len)
 {
-	int res;
+	unsigned int bs_mask = bdev_logical_block_size(bdev) - 1;
+	uint64_t end;
 
-	mutex_lock(&bdev->bd_mutex);
-	res = __blkdev_reread_part(bdev);
-	mutex_unlock(&bdev->bd_mutex);
+	if ((start | len) & bs_mask)
+		return -EINVAL;
+	if (!len)
+		return -EINVAL;
+	if (check_add_overflow(start, len, &end) || end > bdev_nr_bytes(bdev))
+		return -EINVAL;
 
-	return res;
+	return 0;
 }
-EXPORT_SYMBOL(blkdev_reread_part);
 
-static int blk_ioctl_discard(struct block_device *bdev, fmode_t mode,
-		unsigned long arg, unsigned long flags)
+static int blk_ioctl_discard(struct block_device *bdev, blk_mode_t mode,
+		unsigned long arg)
 {
-	uint64_t range[2];
-	uint64_t start, len;
-	struct request_queue *q = bdev_get_queue(bdev);
-	struct address_space *mapping = bdev->bd_inode->i_mapping;
+	uint64_t range[2], start, len;
+	struct bio *prev = NULL, *bio;
+	sector_t sector, nr_sects;
+	struct blk_plug plug;
+	int err;
+
+	if (copy_from_user(range, (void __user *)arg, sizeof(range)))
+		return -EFAULT;
+	start = range[0];
+	len = range[1];
 
+	if (!bdev_max_discard_sectors(bdev))
+		return -EOPNOTSUPP;
 
-	if (!(mode & FMODE_WRITE))
+	if (!(mode & BLK_OPEN_WRITE))
 		return -EBADF;
+	if (bdev_read_only(bdev))
+		return -EPERM;
+	err = blk_validate_byte_range(bdev, start, len);
+	if (err)
+		return err;
+
+	inode_lock(bdev->bd_mapping->host);
+	filemap_invalidate_lock(bdev->bd_mapping);
+	err = truncate_bdev_range(bdev, mode, start, start + len - 1);
+	if (err)
+		goto fail;
+
+	sector = start >> SECTOR_SHIFT;
+	nr_sects = len >> SECTOR_SHIFT;
+
+	blk_start_plug(&plug);
+	while (1) {
+		if (fatal_signal_pending(current)) {
+			if (prev)
+				bio_await_chain(prev);
+			err = -EINTR;
+			goto out_unplug;
+		}
+		bio = blk_alloc_discard_bio(bdev, &sector, &nr_sects,
+				GFP_KERNEL);
+		if (!bio)
+			break;
+		prev = bio_chain_and_submit(prev, bio);
+	}
+	if (prev) {
+		err = submit_bio_wait(prev);
+		if (err == -EOPNOTSUPP)
+			err = 0;
+		bio_put(prev);
+	}
+out_unplug:
+	blk_finish_plug(&plug);
+fail:
+	filemap_invalidate_unlock(bdev->bd_mapping);
+	inode_unlock(bdev->bd_mapping->host);
+	return err;
+}
 
-	if (!blk_queue_discard(q))
-		return -EOPNOTSUPP;
+static int blk_ioctl_secure_erase(struct block_device *bdev, blk_mode_t mode,
+		void __user *argp)
+{
+	uint64_t start, len, end;
+	uint64_t range[2];
+	int err;
 
-	if (copy_from_user(range, (void __user *)arg, sizeof(range)))
+	if (!(mode & BLK_OPEN_WRITE))
+		return -EBADF;
+	if (!bdev_max_secure_erase_sectors(bdev))
+		return -EOPNOTSUPP;
+	if (copy_from_user(range, argp, sizeof(range)))
 		return -EFAULT;
 
 	start = range[0];
 	len = range[1];
-
-	if (start & 511)
+	if ((start & 511) || (len & 511))
 		return -EINVAL;
-	if (len & 511)
+	if (check_add_overflow(start, len, &end) ||
+	    end > bdev_nr_bytes(bdev))
 		return -EINVAL;
 
-	if (start + len > i_size_read(bdev->bd_inode))
-		return -EINVAL;
-	truncate_inode_pages_range(mapping, start, start + len - 1);
-	return blkdev_issue_discard(bdev, start >> 9, len >> 9,
-				    GFP_KERNEL, flags);
+	inode_lock(bdev->bd_mapping->host);
+	filemap_invalidate_lock(bdev->bd_mapping);
+	err = truncate_bdev_range(bdev, mode, start, end - 1);
+	if (!err)
+		err = blkdev_issue_secure_erase(bdev, start >> 9, len >> 9,
+						GFP_KERNEL);
+	filemap_invalidate_unlock(bdev->bd_mapping);
+	inode_unlock(bdev->bd_mapping->host);
+	return err;
 }
 
-static int blk_ioctl_zeroout(struct block_device *bdev, fmode_t mode,
+
+static int blk_ioctl_zeroout(struct block_device *bdev, blk_mode_t mode,
 		unsigned long arg)
 {
 	uint64_t range[2];
-	struct address_space *mapping;
 	uint64_t start, end, len;
+	int err;
 
-	if (!(mode & FMODE_WRITE))
+	if (!(mode & BLK_OPEN_WRITE))
 		return -EBADF;
 
 	if (copy_from_user(range, (void __user *)arg, sizeof(range)))
@@ -251,73 +235,111 @@ static int blk_ioctl_zeroout(struct block_device *bdev, fmode_t mode,
 		return -EINVAL;
 	if (len & 511)
 		return -EINVAL;
-	if (end >= (uint64_t)i_size_read(bdev->bd_inode))
+	if (end >= (uint64_t)bdev_nr_bytes(bdev))
 		return -EINVAL;
 	if (end < start)
 		return -EINVAL;
 
 	/* Invalidate the page cache, including dirty pages */
-	mapping = bdev->bd_inode->i_mapping;
-	truncate_inode_pages_range(mapping, start, end);
+	inode_lock(bdev->bd_mapping->host);
+	filemap_invalidate_lock(bdev->bd_mapping);
+	err = truncate_bdev_range(bdev, mode, start, end);
+	if (err)
+		goto fail;
+
+	err = blkdev_issue_zeroout(bdev, start >> 9, len >> 9, GFP_KERNEL,
+				   BLKDEV_ZERO_NOUNMAP | BLKDEV_ZERO_KILLABLE);
+
+fail:
+	filemap_invalidate_unlock(bdev->bd_mapping);
+	inode_unlock(bdev->bd_mapping->host);
+	return err;
+}
 
-	return blkdev_issue_zeroout(bdev, start >> 9, len >> 9, GFP_KERNEL,
-			BLKDEV_ZERO_NOUNMAP);
+static int put_ushort(unsigned short __user *argp, unsigned short val)
+{
+	return put_user(val, argp);
+}
+
+static int put_int(int __user *argp, int val)
+{
+	return put_user(val, argp);
 }
 
-static int put_ushort(unsigned long arg, unsigned short val)
+static int put_uint(unsigned int __user *argp, unsigned int val)
 {
-	return put_user(val, (unsigned short __user *)arg);
+	return put_user(val, argp);
 }
 
-static int put_int(unsigned long arg, int val)
+static int put_long(long __user *argp, long val)
 {
-	return put_user(val, (int __user *)arg);
+	return put_user(val, argp);
 }
 
-static int put_uint(unsigned long arg, unsigned int val)
+static int put_ulong(unsigned long __user *argp, unsigned long val)
 {
-	return put_user(val, (unsigned int __user *)arg);
+	return put_user(val, argp);
 }
 
-static int put_long(unsigned long arg, long val)
+static int put_u64(u64 __user *argp, u64 val)
 {
-	return put_user(val, (long __user *)arg);
+	return put_user(val, argp);
 }
 
-static int put_ulong(unsigned long arg, unsigned long val)
+#ifdef CONFIG_COMPAT
+static int compat_put_long(compat_long_t __user *argp, long val)
 {
-	return put_user(val, (unsigned long __user *)arg);
+	return put_user(val, argp);
 }
 
-static int put_u64(unsigned long arg, u64 val)
+static int compat_put_ulong(compat_ulong_t __user *argp, compat_ulong_t val)
 {
-	return put_user(val, (u64 __user *)arg);
+	return put_user(val, argp);
 }
+#endif
 
-int __blkdev_driver_ioctl(struct block_device *bdev, fmode_t mode,
+#ifdef CONFIG_COMPAT
+/*
+ * This is the equivalent of compat_ptr_ioctl(), to be used by block
+ * drivers that implement only commands that are completely compatible
+ * between 32-bit and 64-bit user space
+ */
+int blkdev_compat_ptr_ioctl(struct block_device *bdev, blk_mode_t mode,
 			unsigned cmd, unsigned long arg)
 {
 	struct gendisk *disk = bdev->bd_disk;
 
 	if (disk->fops->ioctl)
-		return disk->fops->ioctl(bdev, mode, cmd, arg);
+		return disk->fops->ioctl(bdev, mode, cmd,
+					 (unsigned long)compat_ptr(arg));
 
-	return -ENOTTY;
+	return -ENOIOCTLCMD;
+}
+EXPORT_SYMBOL(blkdev_compat_ptr_ioctl);
+#endif
+
+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;
+	/*
+	 * Only allow unprivileged reservations if the file descriptor is open
+	 * for writing.
+	 */
+	return mode & BLK_OPEN_WRITE;
 }
-/*
- * For the record: _GPL here is only because somebody decided to slap it
- * on the previous export.  Sheer idiocy, since it wasn't copyrightable
- * at all and could be open-coded without any exports by anybody who cares.
- */
-EXPORT_SYMBOL_GPL(__blkdev_driver_ioctl);
 
-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 (!capable(CAP_SYS_ADMIN))
+	if (!blkdev_pr_allowed(bdev, mode))
 		return -EPERM;
 	if (!ops || !ops->pr_register)
 		return -EOPNOTSUPP;
@@ -329,13 +351,13 @@ 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 (!capable(CAP_SYS_ADMIN))
+	if (!blkdev_pr_allowed(bdev, mode))
 		return -EPERM;
 	if (!ops || !ops->pr_reserve)
 		return -EOPNOTSUPP;
@@ -347,13 +369,13 @@ 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 (!capable(CAP_SYS_ADMIN))
+	if (!blkdev_pr_allowed(bdev, mode))
 		return -EPERM;
 	if (!ops || !ops->pr_release)
 		return -EOPNOTSUPP;
@@ -365,13 +387,13 @@ 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 (!capable(CAP_SYS_ADMIN))
+	if (!blkdev_pr_allowed(bdev, mode))
 		return -EPERM;
 	if (!ops || !ops->pr_preempt)
 		return -EOPNOTSUPP;
@@ -383,13 +405,13 @@ 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 (!capable(CAP_SYS_ADMIN))
+	if (!blkdev_pr_allowed(bdev, mode))
 		return -EPERM;
 	if (!ops || !ops->pr_clear)
 		return -EOPNOTSUPP;
@@ -401,57 +423,123 @@ static int blkdev_pr_clear(struct block_device *bdev,
 	return ops->pr_clear(bdev, c.key);
 }
 
-/*
- * Is it an unrecognized ioctl? The correct returns are either
- * ENOTTY (final) or ENOIOCTLCMD ("I don't know this one, try a
- * fallback"). ENOIOCTLCMD gets turned into ENOTTY by the ioctl
- * code before returning.
- *
- * Confused drivers sometimes return EINVAL, which is wrong. It
- * means "I understood the ioctl command, but the parameters to
- * it were wrong".
- *
- * We should aim to just fix the broken drivers, the EINVAL case
- * should go away.
- */
-static inline int is_unrecognized_ioctl(int ret)
+static int blkdev_pr_read_keys(struct block_device *bdev, blk_mode_t mode,
+		struct pr_read_keys __user *arg)
 {
-	return	ret == -EINVAL ||
-		ret == -ENOTTY ||
-		ret == -ENOIOCTLCMD;
+	const struct pr_ops *ops = bdev->bd_disk->fops->pr_ops;
+	struct pr_keys *keys_info;
+	struct pr_read_keys read_keys;
+	u64 __user *keys_ptr;
+	size_t keys_info_len;
+	size_t keys_copy_len;
+	int ret;
+
+	if (!blkdev_pr_allowed(bdev, mode))
+		return -EPERM;
+	if (!ops || !ops->pr_read_keys)
+		return -EOPNOTSUPP;
+
+	if (copy_from_user(&read_keys, arg, sizeof(read_keys)))
+		return -EFAULT;
+
+	keys_info_len = struct_size(keys_info, keys, read_keys.num_keys);
+	if (keys_info_len == SIZE_MAX)
+		return -EINVAL;
+
+	keys_info = kzalloc(keys_info_len, GFP_KERNEL);
+	if (!keys_info)
+		return -ENOMEM;
+
+	keys_info->num_keys = read_keys.num_keys;
+
+	ret = ops->pr_read_keys(bdev, keys_info);
+	if (ret)
+		goto out;
+
+	/* Copy out individual keys */
+	keys_ptr = u64_to_user_ptr(read_keys.keys_ptr);
+	keys_copy_len = min(read_keys.num_keys, keys_info->num_keys) *
+		        sizeof(keys_info->keys[0]);
+
+	if (copy_to_user(keys_ptr, keys_info->keys, keys_copy_len)) {
+		ret = -EFAULT;
+		goto out;
+	}
+
+	/* Copy out the arg struct */
+	read_keys.generation = keys_info->generation;
+	read_keys.num_keys = keys_info->num_keys;
+
+	if (copy_to_user(arg, &read_keys, sizeof(read_keys)))
+		ret = -EFAULT;
+out:
+	kfree(keys_info);
+	return ret;
 }
 
-static int blkdev_flushbuf(struct block_device *bdev, fmode_t mode,
-		unsigned cmd, unsigned long arg)
+static int blkdev_pr_read_reservation(struct block_device *bdev,
+		blk_mode_t mode, struct pr_read_reservation __user *arg)
 {
+	const struct pr_ops *ops = bdev->bd_disk->fops->pr_ops;
+	struct pr_held_reservation rsv = {};
+	struct pr_read_reservation out = {};
 	int ret;
 
+	if (!blkdev_pr_allowed(bdev, mode))
+		return -EPERM;
+	if (!ops || !ops->pr_read_reservation)
+		return -EOPNOTSUPP;
+
+	ret = ops->pr_read_reservation(bdev, &rsv);
+	if (ret)
+		return ret;
+
+	out.key = rsv.key;
+	out.generation = rsv.generation;
+	out.type = rsv.type;
+
+	if (copy_to_user(arg, &out, sizeof(out)))
+		return -EFAULT;
+	return 0;
+}
+
+static int blkdev_flushbuf(struct block_device *bdev, unsigned cmd,
+		unsigned long arg)
+{
 	if (!capable(CAP_SYS_ADMIN))
 		return -EACCES;
 
-	ret = __blkdev_driver_ioctl(bdev, mode, cmd, arg);
-	if (!is_unrecognized_ioctl(ret))
-		return ret;
+	mutex_lock(&bdev->bd_holder_lock);
+	if (bdev->bd_holder_ops && bdev->bd_holder_ops->sync)
+		bdev->bd_holder_ops->sync(bdev);
+	else {
+		mutex_unlock(&bdev->bd_holder_lock);
+		sync_blockdev(bdev);
+	}
 
-	fsync_bdev(bdev);
 	invalidate_bdev(bdev);
 	return 0;
 }
 
-static int blkdev_roset(struct block_device *bdev, fmode_t mode,
-		unsigned cmd, unsigned long arg)
+static int blkdev_roset(struct block_device *bdev, unsigned cmd,
+		unsigned long arg)
 {
 	int ret, n;
 
 	if (!capable(CAP_SYS_ADMIN))
 		return -EACCES;
 
-	ret = __blkdev_driver_ioctl(bdev, mode, cmd, arg);
-	if (!is_unrecognized_ioctl(ret))
-		return ret;
 	if (get_user(n, (int __user *)arg))
 		return -EFAULT;
-	set_device_ro(bdev, n);
+	if (bdev->bd_disk->fops->set_read_only) {
+		ret = bdev->bd_disk->fops->set_read_only(bdev, n);
+		if (ret)
+			return ret;
+	}
+	if (n)
+		bdev_set_flag(bdev, BD_READ_ONLY);
+	else
+		bdev_clear_flag(bdev, BD_READ_ONLY);
 	return 0;
 }
 
@@ -473,7 +561,7 @@ static int blkdev_getgeo(struct block_device *bdev,
 	 */
 	memset(&geo, 0, sizeof(geo));
 	geo.start = get_start_sect(bdev);
-	ret = disk->fops->getgeo(bdev, &geo);
+	ret = disk->fops->getgeo(disk, &geo);
 	if (ret)
 		return ret;
 	if (copy_to_user(argp, &geo, sizeof(geo)))
@@ -481,10 +569,53 @@ static int blkdev_getgeo(struct block_device *bdev,
 	return 0;
 }
 
+#ifdef CONFIG_COMPAT
+struct compat_hd_geometry {
+	unsigned char heads;
+	unsigned char sectors;
+	unsigned short cylinders;
+	u32 start;
+};
+
+static int compat_hdio_getgeo(struct block_device *bdev,
+			      struct compat_hd_geometry __user *ugeo)
+{
+	struct gendisk *disk = bdev->bd_disk;
+	struct hd_geometry geo;
+	int ret;
+
+	if (!ugeo)
+		return -EINVAL;
+	if (!disk->fops->getgeo)
+		return -ENOTTY;
+
+	memset(&geo, 0, sizeof(geo));
+	/*
+	 * We need to set the startsect first, the driver may
+	 * want to override it.
+	 */
+	geo.start = get_start_sect(bdev);
+	ret = disk->fops->getgeo(disk, &geo);
+	if (ret)
+		return ret;
+
+	ret = copy_to_user(ugeo, &geo, 4);
+	ret |= put_user(geo.start, &ugeo->start);
+	if (ret)
+		ret = -EFAULT;
+
+	return ret;
+}
+#endif
+
 /* set the logical block size */
-static int blkdev_bszset(struct block_device *bdev, fmode_t mode,
+static int blkdev_bszset(struct file *file, blk_mode_t mode,
 		int __user *argp)
 {
+	// this one might be file_inode(file)->i_rdev - a rare valid
+	// use of file_inode() for those.
+	dev_t dev = I_BDEV(file->f_mapping->host)->bd_dev;
+	struct file *excl_file;
 	int ret, n;
 
 	if (!capable(CAP_SYS_ADMIN))
@@ -494,115 +625,338 @@ static int blkdev_bszset(struct block_device *bdev, fmode_t mode,
 	if (get_user(n, argp))
 		return -EFAULT;
 
-	if (!(mode & FMODE_EXCL)) {
-		bdgrab(bdev);
-		if (blkdev_get(bdev, mode | FMODE_EXCL, &bdev) < 0)
-			return -EBUSY;
-	}
+	if (mode & BLK_OPEN_EXCL)
+		return set_blocksize(file, n);
 
-	ret = set_blocksize(bdev, n);
-	if (!(mode & FMODE_EXCL))
-		blkdev_put(bdev, mode | FMODE_EXCL);
+	excl_file = bdev_file_open_by_dev(dev, mode, &dev, NULL);
+	if (IS_ERR(excl_file))
+		return -EBUSY;
+	ret = set_blocksize(excl_file, n);
+	fput(excl_file);
 	return ret;
 }
 
 /*
- * always keep this in sync with compat_blkdev_ioctl()
+ * Common commands that are handled the same way on native and compat
+ * user space. Note the separate arg/argp parameters that are needed
+ * to deal with the compat_ptr() conversion.
  */
-int blkdev_ioctl(struct block_device *bdev, fmode_t mode, unsigned cmd,
-			unsigned long arg)
+static int blkdev_common_ioctl(struct block_device *bdev, blk_mode_t mode,
+			       unsigned int cmd, unsigned long arg,
+			       void __user *argp)
 {
-	void __user *argp = (void __user *)arg;
-	loff_t size;
 	unsigned int max_sectors;
 
 	switch (cmd) {
 	case BLKFLSBUF:
-		return blkdev_flushbuf(bdev, mode, cmd, arg);
+		return blkdev_flushbuf(bdev, cmd, arg);
 	case BLKROSET:
-		return blkdev_roset(bdev, mode, cmd, arg);
+		return blkdev_roset(bdev, cmd, arg);
 	case BLKDISCARD:
-		return blk_ioctl_discard(bdev, mode, arg, 0);
+		return blk_ioctl_discard(bdev, mode, arg);
 	case BLKSECDISCARD:
-		return blk_ioctl_discard(bdev, mode, arg,
-				BLKDEV_DISCARD_SECURE);
+		return blk_ioctl_secure_erase(bdev, mode, argp);
 	case BLKZEROOUT:
 		return blk_ioctl_zeroout(bdev, mode, arg);
+	case BLKGETDISKSEQ:
+		return put_u64(argp, bdev->bd_disk->diskseq);
 	case BLKREPORTZONE:
-		return blkdev_report_zones_ioctl(bdev, mode, cmd, arg);
+	case BLKREPORTZONEV2:
+		return blkdev_report_zones_ioctl(bdev, cmd, arg);
 	case BLKRESETZONE:
-		return blkdev_reset_zones_ioctl(bdev, mode, cmd, arg);
+	case BLKOPENZONE:
+	case BLKCLOSEZONE:
+	case BLKFINISHZONE:
+		return blkdev_zone_mgmt_ioctl(bdev, mode, cmd, arg);
 	case BLKGETZONESZ:
-		return put_uint(arg, bdev_zone_sectors(bdev));
+		return put_uint(argp, bdev_zone_sectors(bdev));
 	case BLKGETNRZONES:
-		return put_uint(arg, blkdev_nr_zones(bdev));
-	case HDIO_GETGEO:
-		return blkdev_getgeo(bdev, argp);
-	case BLKRAGET:
-	case BLKFRAGET:
-		if (!arg)
-			return -EINVAL;
-		return put_long(arg, (bdev->bd_bdi->ra_pages*PAGE_SIZE) / 512);
+		return put_uint(argp, bdev_nr_zones(bdev));
 	case BLKROGET:
-		return put_int(arg, bdev_read_only(bdev) != 0);
-	case BLKBSZGET: /* get block device soft block size (cf. BLKSSZGET) */
-		return put_int(arg, block_size(bdev));
+		return put_int(argp, bdev_read_only(bdev) != 0);
 	case BLKSSZGET: /* get block device logical block size */
-		return put_int(arg, bdev_logical_block_size(bdev));
+		return put_int(argp, bdev_logical_block_size(bdev));
 	case BLKPBSZGET: /* get block device physical block size */
-		return put_uint(arg, bdev_physical_block_size(bdev));
+		return put_uint(argp, bdev_physical_block_size(bdev));
 	case BLKIOMIN:
-		return put_uint(arg, bdev_io_min(bdev));
+		return put_uint(argp, bdev_io_min(bdev));
 	case BLKIOOPT:
-		return put_uint(arg, bdev_io_opt(bdev));
+		return put_uint(argp, bdev_io_opt(bdev));
 	case BLKALIGNOFF:
-		return put_int(arg, bdev_alignment_offset(bdev));
+		return put_int(argp, bdev_alignment_offset(bdev));
 	case BLKDISCARDZEROES:
-		return put_uint(arg, 0);
+		return put_uint(argp, 0);
 	case BLKSECTGET:
 		max_sectors = min_t(unsigned int, USHRT_MAX,
 				    queue_max_sectors(bdev_get_queue(bdev)));
-		return put_ushort(arg, max_sectors);
+		return put_ushort(argp, max_sectors);
 	case BLKROTATIONAL:
-		return put_ushort(arg, !blk_queue_nonrot(bdev_get_queue(bdev)));
+		return put_ushort(argp, !bdev_nonrot(bdev));
 	case BLKRASET:
 	case BLKFRASET:
 		if(!capable(CAP_SYS_ADMIN))
 			return -EACCES;
-		bdev->bd_bdi->ra_pages = (arg * 512) / PAGE_SIZE;
+		bdev->bd_disk->bdi->ra_pages = (arg * 512) / PAGE_SIZE;
 		return 0;
-	case BLKBSZSET:
-		return blkdev_bszset(bdev, mode, argp);
-	case BLKPG:
-		return blkpg_ioctl(bdev, argp);
 	case BLKRRPART:
-		return blkdev_reread_part(bdev);
-	case BLKGETSIZE:
-		size = i_size_read(bdev->bd_inode);
-		if ((size >> 9) > ~0UL)
-			return -EFBIG;
-		return put_ulong(arg, size >> 9);
-	case BLKGETSIZE64:
-		return put_u64(arg, i_size_read(bdev->bd_inode));
+		if (!capable(CAP_SYS_ADMIN))
+			return -EACCES;
+		if (bdev_is_partition(bdev))
+			return -EINVAL;
+		return disk_scan_partitions(bdev->bd_disk,
+				mode | BLK_OPEN_STRICT_SCAN);
 	case BLKTRACESTART:
 	case BLKTRACESTOP:
-	case BLKTRACESETUP:
 	case BLKTRACETEARDOWN:
 		return blk_trace_ioctl(bdev, cmd, argp);
+	case BLKCRYPTOIMPORTKEY:
+	case BLKCRYPTOGENERATEKEY:
+	case BLKCRYPTOPREPAREKEY:
+		return blk_crypto_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);
+	case IOC_PR_READ_KEYS:
+		return blkdev_pr_read_keys(bdev, mode, argp);
+	case IOC_PR_READ_RESERVATION:
+		return blkdev_pr_read_reservation(bdev, mode, argp);
 	default:
-		return __blkdev_driver_ioctl(bdev, mode, cmd, arg);
+		return blk_get_meta_cap(bdev, cmd, argp);
+	}
+}
+
+/*
+ * Always keep this in sync with compat_blkdev_ioctl()
+ * to handle all incompatible commands in both functions.
+ *
+ * New commands must be compatible and go into blkdev_common_ioctl
+ */
+long blkdev_ioctl(struct file *file, unsigned cmd, unsigned long arg)
+{
+	struct block_device *bdev = I_BDEV(file->f_mapping->host);
+	void __user *argp = (void __user *)arg;
+	blk_mode_t mode = file_to_blk_mode(file);
+	int ret;
+
+	switch (cmd) {
+	/* These need separate implementations for the data structure */
+	case HDIO_GETGEO:
+		return blkdev_getgeo(bdev, argp);
+	case BLKPG:
+		return blkpg_ioctl(bdev, argp);
+
+	/* Compat mode returns 32-bit data instead of 'long' */
+	case BLKRAGET:
+	case BLKFRAGET:
+		if (!argp)
+			return -EINVAL;
+		return put_long(argp,
+			(bdev->bd_disk->bdi->ra_pages * PAGE_SIZE) / 512);
+	case BLKGETSIZE:
+		if (bdev_nr_sectors(bdev) > ~0UL)
+			return -EFBIG;
+		return put_ulong(argp, bdev_nr_sectors(bdev));
+
+	/* The data is compatible, but the command number is different */
+	case BLKBSZGET: /* get block device soft block size (cf. BLKSSZGET) */
+		return put_int(argp, block_size(bdev));
+	case BLKBSZSET:
+		return blkdev_bszset(file, mode, argp);
+	case BLKGETSIZE64:
+		return put_u64(argp, bdev_nr_bytes(bdev));
+
+	/* Incompatible alignment on i386 */
+	case BLKTRACESETUP:
+	case BLKTRACESETUP2:
+		return blk_trace_ioctl(bdev, cmd, argp);
+	default:
+		break;
+	}
+
+	ret = blkdev_common_ioctl(bdev, mode, cmd, arg, argp);
+	if (ret != -ENOIOCTLCMD)
+		return ret;
+
+	if (!bdev->bd_disk->fops->ioctl)
+		return -ENOTTY;
+	return bdev->bd_disk->fops->ioctl(bdev, mode, cmd, arg);
+}
+
+#ifdef CONFIG_COMPAT
+
+#define BLKBSZGET_32		_IOR(0x12, 112, int)
+#define BLKBSZSET_32		_IOW(0x12, 113, int)
+#define BLKGETSIZE64_32		_IOR(0x12, 114, int)
+
+/* Most of the generic ioctls are handled in the normal fallback path.
+   This assumes the blkdev's low level compat_ioctl always returns
+   ENOIOCTLCMD for unknown ioctls. */
+long compat_blkdev_ioctl(struct file *file, unsigned cmd, unsigned long arg)
+{
+	int ret;
+	void __user *argp = compat_ptr(arg);
+	struct block_device *bdev = I_BDEV(file->f_mapping->host);
+	struct gendisk *disk = bdev->bd_disk;
+	blk_mode_t mode = file_to_blk_mode(file);
+
+	switch (cmd) {
+	/* These need separate implementations for the data structure */
+	case HDIO_GETGEO:
+		return compat_hdio_getgeo(bdev, argp);
+	case BLKPG:
+		return compat_blkpg_ioctl(bdev, argp);
+
+	/* Compat mode returns 32-bit data instead of 'long' */
+	case BLKRAGET:
+	case BLKFRAGET:
+		if (!argp)
+			return -EINVAL;
+		return compat_put_long(argp,
+			(bdev->bd_disk->bdi->ra_pages * PAGE_SIZE) / 512);
+	case BLKGETSIZE:
+		if (bdev_nr_sectors(bdev) > ~(compat_ulong_t)0)
+			return -EFBIG;
+		return compat_put_ulong(argp, bdev_nr_sectors(bdev));
+
+	/* The data is compatible, but the command number is different */
+	case BLKBSZGET_32: /* get the logical block size (cf. BLKSSZGET) */
+		return put_int(argp, bdev_logical_block_size(bdev));
+	case BLKBSZSET_32:
+		return blkdev_bszset(file, mode, argp);
+	case BLKGETSIZE64_32:
+		return put_u64(argp, bdev_nr_bytes(bdev));
+
+	/* Incompatible alignment on i386 */
+	case BLKTRACESETUP32:
+		return blk_trace_ioctl(bdev, cmd, argp);
+	default:
+		break;
+	}
+
+	ret = blkdev_common_ioctl(bdev, mode, cmd, arg, argp);
+	if (ret == -ENOIOCTLCMD && disk->fops->compat_ioctl)
+		ret = disk->fops->compat_ioctl(bdev, mode, cmd, arg);
+
+	return ret;
+}
+#endif
+
+struct blk_iou_cmd {
+	int res;
+	bool nowait;
+};
+
+static void blk_cmd_complete(struct io_tw_req tw_req, io_tw_token_t tw)
+{
+	struct io_uring_cmd *cmd = io_uring_cmd_from_tw(tw_req);
+	struct blk_iou_cmd *bic = io_uring_cmd_to_pdu(cmd, struct blk_iou_cmd);
+
+	if (bic->res == -EAGAIN && bic->nowait)
+		io_uring_cmd_issue_blocking(cmd);
+	else
+		io_uring_cmd_done(cmd, bic->res,
+				  IO_URING_CMD_TASK_WORK_ISSUE_FLAGS);
+}
+
+static void bio_cmd_bio_end_io(struct bio *bio)
+{
+	struct io_uring_cmd *cmd = bio->bi_private;
+	struct blk_iou_cmd *bic = io_uring_cmd_to_pdu(cmd, struct blk_iou_cmd);
+
+	if (unlikely(bio->bi_status) && !bic->res)
+		bic->res = blk_status_to_errno(bio->bi_status);
+
+	io_uring_cmd_do_in_task_lazy(cmd, blk_cmd_complete);
+	bio_put(bio);
+}
+
+static int blkdev_cmd_discard(struct io_uring_cmd *cmd,
+			      struct block_device *bdev,
+			      uint64_t start, uint64_t len, bool nowait)
+{
+	struct blk_iou_cmd *bic = io_uring_cmd_to_pdu(cmd, struct blk_iou_cmd);
+	gfp_t gfp = nowait ? GFP_NOWAIT : GFP_KERNEL;
+	sector_t sector = start >> SECTOR_SHIFT;
+	sector_t nr_sects = len >> SECTOR_SHIFT;
+	struct bio *prev = NULL, *bio;
+	int err;
+
+	if (!bdev_max_discard_sectors(bdev))
+		return -EOPNOTSUPP;
+	if (!(file_to_blk_mode(cmd->file) & BLK_OPEN_WRITE))
+		return -EBADF;
+	if (bdev_read_only(bdev))
+		return -EPERM;
+	err = blk_validate_byte_range(bdev, start, len);
+	if (err)
+		return err;
+
+	err = filemap_invalidate_pages(bdev->bd_mapping, start,
+					start + len - 1, nowait);
+	if (err)
+		return err;
+
+	while (true) {
+		bio = blk_alloc_discard_bio(bdev, &sector, &nr_sects, gfp);
+		if (!bio)
+			break;
+		if (nowait) {
+			/*
+			 * Don't allow multi-bio non-blocking submissions as
+			 * subsequent bios may fail but we won't get a direct
+			 * indication of that. Normally, the caller should
+			 * retry from a blocking context.
+			 */
+			if (unlikely(nr_sects)) {
+				bio_put(bio);
+				return -EAGAIN;
+			}
+			bio->bi_opf |= REQ_NOWAIT;
+		}
+
+		prev = bio_chain_and_submit(prev, bio);
+	}
+	if (unlikely(!prev))
+		return -EAGAIN;
+	if (unlikely(nr_sects))
+		bic->res = -EAGAIN;
+
+	prev->bi_private = cmd;
+	prev->bi_end_io = bio_cmd_bio_end_io;
+	submit_bio(prev);
+	return -EIOCBQUEUED;
+}
+
+int blkdev_uring_cmd(struct io_uring_cmd *cmd, unsigned int issue_flags)
+{
+	struct block_device *bdev = I_BDEV(cmd->file->f_mapping->host);
+	struct blk_iou_cmd *bic = io_uring_cmd_to_pdu(cmd, struct blk_iou_cmd);
+	const struct io_uring_sqe *sqe = cmd->sqe;
+	u32 cmd_op = cmd->cmd_op;
+	uint64_t start, len;
+
+	if (unlikely(sqe->ioprio || sqe->__pad1 || sqe->len ||
+		     sqe->rw_flags || sqe->file_index))
+		return -EINVAL;
+
+	bic->res = 0;
+	bic->nowait = issue_flags & IO_URING_F_NONBLOCK;
+
+	start = READ_ONCE(sqe->addr);
+	len = READ_ONCE(sqe->addr3);
+
+	switch (cmd_op) {
+	case BLOCK_URING_CMD_DISCARD:
+		return blkdev_cmd_discard(cmd, bdev, start, len, bic->nowait);
 	}
+	return -EINVAL;
 }
-EXPORT_SYMBOL_GPL(blkdev_ioctl);