1 files changed, 202 insertions, 41 deletions

diff --git a/block/ioctl.c b/block/ioctl.c
index a9028a2c2db5..6554b728bae6 100644
--- a/block/ioctl.c
+++ b/block/ioctl.c
@@ -11,6 +11,9 @@
 #include <linux/blktrace_api.h>
 #include <linux/pr.h>
 #include <linux/uaccess.h>
+#include <linux/pagemap.h>
+#include <linux/io_uring/cmd.h>
+#include <uapi/linux/blkdev.h>
 #include "blk.h"
 
 static int blkpg_do_ioctl(struct block_device *bdev,
@@ -33,7 +36,7 @@ static int blkpg_do_ioctl(struct block_device *bdev,
 	if (op == BLKPG_DEL_PARTITION)
 		return bdev_del_partition(disk, p.pno);
 
-	if (p.start < 0 || p.length <= 0 || p.start + p.length < 0)
+	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)))
@@ -92,49 +95,91 @@ static int compat_blkpg_ioctl(struct block_device *bdev,
 }
 #endif
 
+/*
+ * 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.
+ */
+static int blk_validate_byte_range(struct block_device *bdev,
+				   uint64_t start, uint64_t len)
+{
+	unsigned int bs_mask = bdev_logical_block_size(bdev) - 1;
+	uint64_t end;
+
+	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 0;
+}
+
 static int blk_ioctl_discard(struct block_device *bdev, blk_mode_t mode,
 		unsigned long arg)
 {
-	uint64_t range[2];
-	uint64_t start, len, end;
-	struct inode *inode = bdev->bd_inode;
+	uint64_t range[2], start, len;
+	struct bio *prev = NULL, *bio;
+	sector_t sector, nr_sects;
+	struct blk_plug plug;
 	int err;
 
-	if (!(mode & BLK_OPEN_WRITE))
-		return -EBADF;
-
-	if (!bdev_max_discard_sectors(bdev))
-		return -EOPNOTSUPP;
-
 	if (copy_from_user(range, (void __user *)arg, sizeof(range)))
 		return -EFAULT;
-
 	start = range[0];
 	len = range[1];
 
-	if (start & 511)
-		return -EINVAL;
-	if (len & 511)
-		return -EINVAL;
+	if (!bdev_max_discard_sectors(bdev))
+		return -EOPNOTSUPP;
 
-	if (check_add_overflow(start, len, &end) ||
-	    end > bdev_nr_bytes(bdev))
-		return -EINVAL;
+	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;
 
-	filemap_invalidate_lock(inode->i_mapping);
+	filemap_invalidate_lock(bdev->bd_mapping);
 	err = truncate_bdev_range(bdev, mode, start, start + len - 1);
 	if (err)
 		goto fail;
-	err = blkdev_issue_discard(bdev, start >> 9, len >> 9, GFP_KERNEL);
+
+	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(inode->i_mapping);
+	filemap_invalidate_unlock(bdev->bd_mapping);
 	return err;
 }
 
 static int blk_ioctl_secure_erase(struct block_device *bdev, blk_mode_t mode,
 		void __user *argp)
 {
-	uint64_t start, len;
+	uint64_t start, len, end;
 	uint64_t range[2];
 	int err;
 
@@ -149,15 +194,16 @@ static int blk_ioctl_secure_erase(struct block_device *bdev, blk_mode_t mode,
 	len = range[1];
 	if ((start & 511) || (len & 511))
 		return -EINVAL;
-	if (start + len > bdev_nr_bytes(bdev))
+	if (check_add_overflow(start, len, &end) ||
+	    end > bdev_nr_bytes(bdev))
 		return -EINVAL;
 
-	filemap_invalidate_lock(bdev->bd_inode->i_mapping);
-	err = truncate_bdev_range(bdev, mode, start, start + len - 1);
+	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_inode->i_mapping);
+	filemap_invalidate_unlock(bdev->bd_mapping);
 	return err;
 }
 
@@ -167,7 +213,6 @@ static int blk_ioctl_zeroout(struct block_device *bdev, blk_mode_t mode,
 {
 	uint64_t range[2];
 	uint64_t start, end, len;
-	struct inode *inode = bdev->bd_inode;
 	int err;
 
 	if (!(mode & BLK_OPEN_WRITE))
@@ -190,16 +235,16 @@ static int blk_ioctl_zeroout(struct block_device *bdev, blk_mode_t mode,
 		return -EINVAL;
 
 	/* Invalidate the page cache, including dirty pages */
-	filemap_invalidate_lock(inode->i_mapping);
+	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_NOUNMAP | BLKDEV_ZERO_KILLABLE);
 
 fail:
-	filemap_invalidate_unlock(inode->i_mapping);
+	filemap_invalidate_unlock(bdev->bd_mapping);
 	return err;
 }
 
@@ -403,7 +448,10 @@ static int blkdev_roset(struct block_device *bdev, unsigned cmd,
 		if (ret)
 			return ret;
 	}
-	bdev->bd_read_only = n;
+	if (n)
+		bdev_set_flag(bdev, BD_READ_ONLY);
+	else
+		bdev_clear_flag(bdev, BD_READ_ONLY);
 	return 0;
 }
 
@@ -473,11 +521,14 @@ static int compat_hdio_getgeo(struct block_device *bdev,
 #endif
 
 /* set the logical block size */
-static int blkdev_bszset(struct block_device *bdev, blk_mode_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;
-	struct file *file;
 
 	if (!capable(CAP_SYS_ADMIN))
 		return -EACCES;
@@ -487,13 +538,13 @@ static int blkdev_bszset(struct block_device *bdev, blk_mode_t mode,
 		return -EFAULT;
 
 	if (mode & BLK_OPEN_EXCL)
-		return set_blocksize(bdev, n);
+		return set_blocksize(file, n);
 
-	file = bdev_file_open_by_dev(bdev->bd_dev, mode, &bdev, NULL);
-	if (IS_ERR(file))
+	excl_file = bdev_file_open_by_dev(dev, mode, &dev, NULL);
+	if (IS_ERR(excl_file))
 		return -EBUSY;
-	ret = set_blocksize(bdev, n);
-	fput(file);
+	ret = set_blocksize(excl_file, n);
+	fput(excl_file);
 	return ret;
 }
 
@@ -563,7 +614,8 @@ static int blkdev_common_ioctl(struct block_device *bdev, blk_mode_t mode,
 			return -EACCES;
 		if (bdev_is_partition(bdev))
 			return -EINVAL;
-		return disk_scan_partitions(bdev->bd_disk, mode);
+		return disk_scan_partitions(bdev->bd_disk,
+				mode | BLK_OPEN_STRICT_SCAN);
 	case BLKTRACESTART:
 	case BLKTRACESTOP:
 	case BLKTRACETEARDOWN:
@@ -621,7 +673,7 @@ long blkdev_ioctl(struct file *file, unsigned cmd, unsigned long arg)
 	case BLKBSZGET: /* get block device soft block size (cf. BLKSSZGET) */
 		return put_int(argp, block_size(bdev));
 	case BLKBSZSET:
-		return blkdev_bszset(bdev, mode, argp);
+		return blkdev_bszset(file, mode, argp);
 	case BLKGETSIZE64:
 		return put_u64(argp, bdev_nr_bytes(bdev));
 
@@ -681,7 +733,7 @@ long compat_blkdev_ioctl(struct file *file, unsigned cmd, unsigned long arg)
 	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(bdev, mode, argp);
+		return blkdev_bszset(file, mode, argp);
 	case BLKGETSIZE64_32:
 		return put_u64(argp, bdev_nr_bytes(bdev));
 
@@ -699,3 +751,112 @@ long compat_blkdev_ioctl(struct file *file, unsigned cmd, unsigned long arg)
 	return ret;
 }
 #endif
+
+struct blk_iou_cmd {
+	int res;
+	bool nowait;
+};
+
+static void blk_cmd_complete(struct io_uring_cmd *cmd, unsigned int issue_flags)
+{
+	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, 0, 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;
+}