block: decouple REQ_OP_SECURE_ERASE from REQ_OP_DISCARD

Secure erase is a very different operation from discard in that it is
a data integrity operation vs hint.  Fully split the limits and helper
infrastructure to make the separation more clear.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Martin K. Petersen <martin.petersen@oracle.com>
Acked-by: Christoph Böhmwalder <christoph.boehmwalder@linbit.com> [drbd]
Acked-by: Ryusuke Konishi <konishi.ryusuke@gmail.com> [nifs2]
Acked-by: Jaegeuk Kim <jaegeuk@kernel.org> [f2fs]
Acked-by: Coly Li <colyli@suse.de> [bcache]
Acked-by: David Sterba <dsterba@suse.com> [btrfs]
Acked-by: Chao Yu <chao@kernel.org>
Reviewed-by: Chaitanya Kulkarni <kch@nvidia.com>
Link: https://lore.kernel.org/r/20220415045258.199825-27-hch@lst.de
Signed-off-by: Jens Axboe <axboe@kernel.dk>

6 files changed, 97 insertions, 31 deletions

diff --git a/block/blk-core.c b/block/blk-core.c
index b5c3a8049134..ee18b6a699bd 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -824,7 +824,7 @@ void submit_bio_noacct(struct bio *bio)
 			goto not_supported;
 		break;
 	case REQ_OP_SECURE_ERASE:
-		if (!blk_queue_secure_erase(q))
+		if (!bdev_max_secure_erase_sectors(bdev))
 			goto not_supported;
 		break;
 	case REQ_OP_ZONE_APPEND:
diff --git a/block/blk-lib.c b/block/blk-lib.c
index 43aa4d7fe859..09b7e1200c0f 100644
--- a/block/blk-lib.c
+++ b/block/blk-lib.c
@@ -36,26 +36,15 @@ static sector_t bio_discard_limit(struct block_device *bdev, sector_t sector)
 }
 
 int __blkdev_issue_discard(struct block_device *bdev, sector_t sector,
-		sector_t nr_sects, gfp_t gfp_mask, int flags,
-		struct bio **biop)
+		sector_t nr_sects, gfp_t gfp_mask, struct bio **biop)
 {
-	struct request_queue *q = bdev_get_queue(bdev);
 	struct bio *bio = *biop;
-	unsigned int op;
 	sector_t bs_mask;
 
 	if (bdev_read_only(bdev))
 		return -EPERM;
-
-	if (flags & BLKDEV_DISCARD_SECURE) {
-		if (!blk_queue_secure_erase(q))
-			return -EOPNOTSUPP;
-		op = REQ_OP_SECURE_ERASE;
-	} else {
-		if (!bdev_max_discard_sectors(bdev))
-			return -EOPNOTSUPP;
-		op = REQ_OP_DISCARD;
-	}
+	if (!bdev_max_discard_sectors(bdev))
+		return -EOPNOTSUPP;
 
 	/* In case the discard granularity isn't set by buggy device driver */
 	if (WARN_ON_ONCE(!bdev_discard_granularity(bdev))) {
@@ -77,7 +66,7 @@ int __blkdev_issue_discard(struct block_device *bdev, sector_t sector,
 		sector_t req_sects =
 			min(nr_sects, bio_discard_limit(bdev, sector));
 
-		bio = blk_next_bio(bio, bdev, 0, op, gfp_mask);
+		bio = blk_next_bio(bio, bdev, 0, REQ_OP_DISCARD, gfp_mask);
 		bio->bi_iter.bi_sector = sector;
 		bio->bi_iter.bi_size = req_sects << 9;
 		sector += req_sects;
@@ -103,21 +92,19 @@ EXPORT_SYMBOL(__blkdev_issue_discard);
  * @sector:	start sector
  * @nr_sects:	number of sectors to discard
  * @gfp_mask:	memory allocation flags (for bio_alloc)
- * @flags:	BLKDEV_DISCARD_* flags to control behaviour
  *
  * Description:
  *    Issue a discard request for the sectors in question.
  */
 int blkdev_issue_discard(struct block_device *bdev, sector_t sector,
-		sector_t nr_sects, gfp_t gfp_mask, unsigned long flags)
+		sector_t nr_sects, gfp_t gfp_mask)
 {
 	struct bio *bio = NULL;
 	struct blk_plug plug;
 	int ret;
 
 	blk_start_plug(&plug);
-	ret = __blkdev_issue_discard(bdev, sector, nr_sects, gfp_mask, flags,
-			&bio);
+	ret = __blkdev_issue_discard(bdev, sector, nr_sects, gfp_mask, &bio);
 	if (!ret && bio) {
 		ret = submit_bio_wait(bio);
 		if (ret == -EOPNOTSUPP)
@@ -314,3 +301,42 @@ retry:
 	return ret;
 }
 EXPORT_SYMBOL(blkdev_issue_zeroout);
+
+int blkdev_issue_secure_erase(struct block_device *bdev, sector_t sector,
+		sector_t nr_sects, gfp_t gfp)
+{
+	sector_t bs_mask = (bdev_logical_block_size(bdev) >> 9) - 1;
+	unsigned int max_sectors = bdev_max_secure_erase_sectors(bdev);
+	struct bio *bio = NULL;
+	struct blk_plug plug;
+	int ret = 0;
+
+	if (max_sectors == 0)
+		return -EOPNOTSUPP;
+	if ((sector | nr_sects) & bs_mask)
+		return -EINVAL;
+	if (bdev_read_only(bdev))
+		return -EPERM;
+
+	blk_start_plug(&plug);
+	for (;;) {
+		unsigned int len = min_t(sector_t, nr_sects, max_sectors);
+
+		bio = blk_next_bio(bio, bdev, 0, REQ_OP_SECURE_ERASE, gfp);
+		bio->bi_iter.bi_sector = sector;
+		bio->bi_iter.bi_size = len;
+
+		sector += len << SECTOR_SHIFT;
+		nr_sects -= len << SECTOR_SHIFT;
+		if (!nr_sects) {
+			ret = submit_bio_wait(bio);
+			bio_put(bio);
+			break;
+		}
+		cond_resched();
+	}
+	blk_finish_plug(&plug);
+
+	return ret;
+}
+EXPORT_SYMBOL(blkdev_issue_secure_erase);
diff --git a/block/blk-mq-debugfs.c b/block/blk-mq-debugfs.c
index fd111c500125..7e4136a60e1c 100644
--- a/block/blk-mq-debugfs.c
+++ b/block/blk-mq-debugfs.c
@@ -115,7 +115,6 @@ static const char *const blk_queue_flag_name[] = {
 	QUEUE_FLAG_NAME(IO_STAT),
 	QUEUE_FLAG_NAME(NOXMERGES),
 	QUEUE_FLAG_NAME(ADD_RANDOM),
-	QUEUE_FLAG_NAME(SECERASE),
 	QUEUE_FLAG_NAME(SAME_FORCE),
 	QUEUE_FLAG_NAME(DEAD),
 	QUEUE_FLAG_NAME(INIT_DONE),
diff --git a/block/blk-settings.c b/block/blk-settings.c
index fd83d674afd0..6ccceb421ed2 100644
--- a/block/blk-settings.c
+++ b/block/blk-settings.c
@@ -46,6 +46,7 @@ void blk_set_default_limits(struct queue_limits *lim)
 	lim->max_zone_append_sectors = 0;
 	lim->max_discard_sectors = 0;
 	lim->max_hw_discard_sectors = 0;
+	lim->max_secure_erase_sectors = 0;
 	lim->discard_granularity = 0;
 	lim->discard_alignment = 0;
 	lim->discard_misaligned = 0;
@@ -177,6 +178,18 @@ void blk_queue_max_discard_sectors(struct request_queue *q,
 EXPORT_SYMBOL(blk_queue_max_discard_sectors);
 
 /**
+ * blk_queue_max_secure_erase_sectors - set max sectors for a secure erase
+ * @q:  the request queue for the device
+ * @max_sectors: maximum number of sectors to secure_erase
+ **/
+void blk_queue_max_secure_erase_sectors(struct request_queue *q,
+		unsigned int max_sectors)
+{
+	q->limits.max_secure_erase_sectors = max_sectors;
+}
+EXPORT_SYMBOL(blk_queue_max_secure_erase_sectors);
+
+/**
  * blk_queue_max_write_zeroes_sectors - set max sectors for a single
  *                                      write zeroes
  * @q:  the request queue for the device
@@ -661,7 +674,8 @@ int blk_stack_limits(struct queue_limits *t, struct queue_limits *b,
 		t->discard_alignment = lcm_not_zero(t->discard_alignment, alignment) %
 			t->discard_granularity;
 	}
-
+	t->max_secure_erase_sectors = min_not_zero(t->max_secure_erase_sectors,
+						   b->max_secure_erase_sectors);
 	t->zone_write_granularity = max(t->zone_write_granularity,
 					b->zone_write_granularity);
 	t->zoned = max(t->zoned, b->zoned);
diff --git a/block/fops.c b/block/fops.c
index ba5e7d5ff9a5..e3643362c244 100644
--- a/block/fops.c
+++ b/block/fops.c
@@ -677,7 +677,7 @@ static long blkdev_fallocate(struct file *file, int mode, loff_t start,
 		break;
 	case FALLOC_FL_PUNCH_HOLE | FALLOC_FL_KEEP_SIZE | FALLOC_FL_NO_HIDE_STALE:
 		error = blkdev_issue_discard(bdev, start >> SECTOR_SHIFT,
-					     len >> SECTOR_SHIFT, GFP_KERNEL, 0);
+					     len >> SECTOR_SHIFT, GFP_KERNEL);
 		break;
 	default:
 		error = -EOPNOTSUPP;
diff --git a/block/ioctl.c b/block/ioctl.c
index eaee0efc0bea..46949f1b0dba 100644
--- a/block/ioctl.c
+++ b/block/ioctl.c
@@ -83,7 +83,7 @@ static int compat_blkpg_ioctl(struct block_device *bdev,
 #endif
 
 static int blk_ioctl_discard(struct block_device *bdev, fmode_t mode,
-		unsigned long arg, unsigned long flags)
+		unsigned long arg)
 {
 	uint64_t range[2];
 	uint64_t start, len;
@@ -114,15 +114,43 @@ static int blk_ioctl_discard(struct block_device *bdev, fmode_t mode,
 	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, flags);
-
+	err = blkdev_issue_discard(bdev, start >> 9, len >> 9, GFP_KERNEL);
 fail:
 	filemap_invalidate_unlock(inode->i_mapping);
 	return err;
 }
 
+static int blk_ioctl_secure_erase(struct block_device *bdev, fmode_t mode,
+		void __user *argp)
+{
+	uint64_t start, len;
+	uint64_t range[2];
+	int err;
+
+	if (!(mode & FMODE_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) || (len & 511))
+		return -EINVAL;
+	if (start + len > bdev_nr_bytes(bdev))
+		return -EINVAL;
+
+	filemap_invalidate_lock(bdev->bd_inode->i_mapping);
+	err = truncate_bdev_range(bdev, mode, start, start + len - 1);
+	if (!err)
+		err = blkdev_issue_secure_erase(bdev, start >> 9, len >> 9,
+						GFP_KERNEL);
+	filemap_invalidate_unlock(bdev->bd_inode->i_mapping);
+	return err;
+}
+
+
 static int blk_ioctl_zeroout(struct block_device *bdev, fmode_t mode,
 		unsigned long arg)
 {
@@ -450,10 +478,9 @@ static int blkdev_common_ioctl(struct block_device *bdev, fmode_t mode,
 	case BLKROSET:
 		return blkdev_roset(bdev, mode, 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: