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>

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:

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);

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),

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;
@@ -176,6 +177,18 @@ 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
@@ -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);

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;

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:

drivers/block/drbd/drbd_receiver.c

@@ -1547,7 +1547,8 @@ int drbd_issue_discard_or_zero_out(struct drbd_device *device, sector_t start, u
 		start = tmp;
 	}
 	while (nr_sectors >= max_discard_sectors) {
-		err |= blkdev_issue_discard(bdev, start, max_discard_sectors, GFP_NOIO, 0);
+		err |= blkdev_issue_discard(bdev, start, max_discard_sectors,
+					    GFP_NOIO);
 		nr_sectors -= max_discard_sectors;
 		start += max_discard_sectors;
 	}
@@ -1559,7 +1560,7 @@ int drbd_issue_discard_or_zero_out(struct drbd_device *device, sector_t start, u
 		nr = nr_sectors;
 		nr -= (unsigned int)nr % granularity;
 		if (nr) {
-			err |= blkdev_issue_discard(bdev, start, nr, GFP_NOIO, 0);
+			err |= blkdev_issue_discard(bdev, start, nr, GFP_NOIO);
 			nr_sectors -= nr;
 			start += nr;
 		}

drivers/block/rnbd/rnbd-clt.c

@@ -1365,8 +1365,8 @@ static void setup_request_queue(struct rnbd_clt_dev *dev)
 	dev->queue->limits.discard_granularity	= dev->discard_granularity;
 	dev->queue->limits.discard_alignment	= dev->discard_alignment;
 	if (dev->secure_discard)
-		blk_queue_flag_set(QUEUE_FLAG_SECERASE, dev->queue);
-
+		blk_queue_max_secure_erase_sectors(dev->queue,
+				dev->max_discard_sectors);
 	blk_queue_flag_set(QUEUE_FLAG_SAME_COMP, dev->queue);
 	blk_queue_flag_set(QUEUE_FLAG_SAME_FORCE, dev->queue);
 	blk_queue_max_segments(dev->queue, dev->max_segments);

drivers/block/rnbd/rnbd-srv-dev.h

@@ -44,7 +44,7 @@ static inline int rnbd_dev_get_max_hw_sects(const struct rnbd_dev *dev)
 
 static inline int rnbd_dev_get_secure_discard(const struct rnbd_dev *dev)
 {
-	return blk_queue_secure_erase(bdev_get_queue(dev->bdev));
+	return bdev_max_secure_erase_sectors(dev->bdev);
 }
 
 static inline int rnbd_dev_get_max_discard_sects(const struct rnbd_dev *dev)

drivers/block/xen-blkback/blkback.c

@@ -970,7 +970,6 @@ static int dispatch_discard_io(struct xen_blkif_ring *ring,
 	int status = BLKIF_RSP_OKAY;
 	struct xen_blkif *blkif = ring->blkif;
 	struct block_device *bdev = blkif->vbd.bdev;
-	unsigned long secure;
 	struct phys_req preq;
 
 	xen_blkif_get(blkif);
@@ -987,13 +986,15 @@ static int dispatch_discard_io(struct xen_blkif_ring *ring,
 	}
 	ring->st_ds_req++;
 
-	secure = (blkif->vbd.discard_secure &&
-		 (req->u.discard.flag & BLKIF_DISCARD_SECURE)) ?
-		 BLKDEV_DISCARD_SECURE : 0;
+	if (blkif->vbd.discard_secure &&
+	    (req->u.discard.flag & BLKIF_DISCARD_SECURE))
+		err = blkdev_issue_secure_erase(bdev,
+				req->u.discard.sector_number,
+				req->u.discard.nr_sectors, GFP_KERNEL);
+	else
+		err = blkdev_issue_discard(bdev, req->u.discard.sector_number,
+				req->u.discard.nr_sectors, GFP_KERNEL);
 
-	err = blkdev_issue_discard(bdev, req->u.discard.sector_number,
-				   req->u.discard.nr_sectors,
-				   GFP_KERNEL, secure);
 fail_response:
 	if (err == -EOPNOTSUPP) {
 		pr_debug("discard op failed, not supported\n");

drivers/block/xen-blkback/xenbus.c

@@ -484,7 +484,6 @@ static int xen_vbd_create(struct xen_blkif *blkif, blkif_vdev_t handle,
 {
 	struct xen_vbd *vbd;
 	struct block_device *bdev;
-	struct request_queue *q;
 
 	vbd = &blkif->vbd;
 	vbd->handle   = handle;
@@ -516,11 +515,9 @@ static int xen_vbd_create(struct xen_blkif *blkif, blkif_vdev_t handle,
 	if (vbd->bdev->bd_disk->flags & GENHD_FL_REMOVABLE)
 		vbd->type |= VDISK_REMOVABLE;
 
-	q = bdev_get_queue(bdev);
 	if (bdev_write_cache(bdev))
 		vbd->flush_support = true;
-
-	if (q && blk_queue_secure_erase(q))
+	if (bdev_max_secure_erase_sectors(bdev))
 		vbd->discard_secure = true;
 
 	vbd->feature_gnt_persistent = feature_persistent;

drivers/block/xen-blkfront.c

@@ -949,7 +949,8 @@ static void blkif_set_queue_limits(struct blkfront_info *info)
 						 info->physical_sector_size;
 		rq->limits.discard_alignment = info->discard_alignment;
 		if (info->feature_secdiscard)
-			blk_queue_flag_set(QUEUE_FLAG_SECERASE, rq);
+			blk_queue_max_secure_erase_sectors(rq,
+							   get_capacity(gd));
 	}
 
 	/* Hard sector size and max sectors impersonate the equiv. hardware. */
@@ -1606,7 +1607,7 @@ static irqreturn_t blkif_interrupt(int irq, void *dev_id)
 				info->feature_discard = 0;
 				info->feature_secdiscard = 0;
 				blk_queue_max_discard_sectors(rq, 0);
-				blk_queue_flag_clear(QUEUE_FLAG_SECERASE, rq);
+				blk_queue_max_secure_erase_sectors(rq, 0);
 			}
 			break;
 		case BLKIF_OP_FLUSH_DISKCACHE:

drivers/md/bcache/alloc.c

@@ -336,7 +336,7 @@ static int bch_allocator_thread(void *arg)
 				mutex_unlock(&ca->set->bucket_lock);
 				blkdev_issue_discard(ca->bdev,
 					bucket_to_sector(ca->set, bucket),
-					ca->sb.bucket_size, GFP_KERNEL, 0);
+					ca->sb.bucket_size, GFP_KERNEL);
 				mutex_lock(&ca->set->bucket_lock);
 			}
 

drivers/md/dm-table.c

@@ -1920,9 +1920,7 @@ static int device_not_secure_erase_capable(struct dm_target *ti,
 					   struct dm_dev *dev, sector_t start,
 					   sector_t len, void *data)
 {
-	struct request_queue *q = bdev_get_queue(dev->bdev);
-
-	return !blk_queue_secure_erase(q);
+	return !bdev_max_secure_erase_sectors(dev->bdev);
 }
 
 static bool dm_table_supports_secure_erase(struct dm_table *t)
@@ -1975,8 +1973,8 @@ int dm_table_set_restrictions(struct dm_table *t, struct request_queue *q,
 		q->limits.discard_misaligned = 0;
 	}
 
-	if (dm_table_supports_secure_erase(t))
-		blk_queue_flag_set(QUEUE_FLAG_SECERASE, q);
+	if (!dm_table_supports_secure_erase(t))
+		q->limits.max_secure_erase_sectors = 0;
 
 	if (dm_table_supports_flush(t, (1UL << QUEUE_FLAG_WC))) {
 		wc = true;

drivers/md/dm-thin.c

@@ -398,8 +398,8 @@ static int issue_discard(struct discard_op *op, dm_block_t data_b, dm_block_t da
 	sector_t s = block_to_sectors(tc->pool, data_b);
 	sector_t len = block_to_sectors(tc->pool, data_e - data_b);
 
-	return __blkdev_issue_discard(tc->pool_dev->bdev, s, len,
-				      GFP_NOWAIT, 0, &op->bio);
+	return __blkdev_issue_discard(tc->pool_dev->bdev, s, len, GFP_NOWAIT,
+				      &op->bio);
 }
 
 static void end_discard(struct discard_op *op, int r)

drivers/md/md.c

@@ -8584,7 +8584,7 @@ void md_submit_discard_bio(struct mddev *mddev, struct md_rdev *rdev,
 {
 	struct bio *discard_bio = NULL;
 
-	if (__blkdev_issue_discard(rdev->bdev, start, size, GFP_NOIO, 0,
+	if (__blkdev_issue_discard(rdev->bdev, start, size, GFP_NOIO,
 			&discard_bio) || !discard_bio)
 		return;
 

drivers/md/raid5-cache.c

@@ -1344,14 +1344,14 @@ static void r5l_write_super_and_discard_space(struct r5l_log *log,
 	if (log->last_checkpoint < end) {
 		blkdev_issue_discard(bdev,
 				log->last_checkpoint + log->rdev->data_offset,
-				end - log->last_checkpoint, GFP_NOIO, 0);
+				end - log->last_checkpoint, GFP_NOIO);
 	} else {
 		blkdev_issue_discard(bdev,
 				log->last_checkpoint + log->rdev->data_offset,
 				log->device_size - log->last_checkpoint,
-				GFP_NOIO, 0);
+				GFP_NOIO);
 		blkdev_issue_discard(bdev, log->rdev->data_offset, end,
-				GFP_NOIO, 0);
+				GFP_NOIO);
 	}
 }
 

drivers/mmc/core/queue.c

@@ -189,7 +189,7 @@ static void mmc_queue_setup_discard(struct request_queue *q,
 	if (card->pref_erase > max_discard)
 		q->limits.discard_granularity = SECTOR_SIZE;
 	if (mmc_can_secure_erase_trim(card))
-		blk_queue_flag_set(QUEUE_FLAG_SECERASE, q);
+		blk_queue_max_secure_erase_sectors(q, max_discard);
 }
 
 static unsigned short mmc_get_max_segments(struct mmc_host *host)

drivers/nvme/target/io-cmd-bdev.c

@@ -360,7 +360,7 @@ static u16 nvmet_bdev_discard_range(struct nvmet_req *req,
 	ret = __blkdev_issue_discard(ns->bdev,
 			nvmet_lba_to_sect(ns, range->slba),
 			le32_to_cpu(range->nlb) << (ns->blksize_shift - 9),
-			GFP_KERNEL, 0, bio);
+			GFP_KERNEL, bio);
 	if (ret && ret != -EOPNOTSUPP) {
 		req->error_slba = le64_to_cpu(range->slba);
 		return errno_to_nvme_status(req, ret);

drivers/target/target_core_file.c

@@ -558,7 +558,7 @@ fd_execute_unmap(struct se_cmd *cmd, sector_t lba, sector_t nolb)
 		ret = blkdev_issue_discard(bdev,
 					   target_to_linux_sector(dev, lba),
 					   target_to_linux_sector(dev,  nolb),
-					   GFP_KERNEL, 0);
+					   GFP_KERNEL);
 		if (ret < 0) {
 			pr_warn("FILEIO: blkdev_issue_discard() failed: %d\n",
 				ret);