1 files changed, 170 insertions, 289 deletions

diff --git a/block/blk-integrity.c b/block/blk-integrity.c
index 410da060d1f5..9b27963680dc 100644
--- a/block/blk-integrity.c
+++ b/block/blk-integrity.c
@@ -6,13 +6,14 @@
  * Written by: Martin K. Petersen <martin.petersen@oracle.com>
  */
 
-#include <linux/blkdev.h>
+#include <linux/blk-integrity.h>
 #include <linux/backing-dev.h>
 #include <linux/mempool.h>
 #include <linux/bio.h>
 #include <linux/scatterlist.h>
 #include <linux/export.h>
 #include <linux/slab.h>
+#include <linux/t10-pi.h>
 
 #include "blk.h"
 
@@ -53,113 +54,88 @@ new_segment:
 
 	return segments;
 }
-EXPORT_SYMBOL(blk_rq_count_integrity_sg);
 
-/**
- * blk_rq_map_integrity_sg - Map integrity metadata into a scatterlist
- * @q:		request queue
- * @bio:	bio with integrity metadata attached
- * @sglist:	target scatterlist
- *
- * Description: Map the integrity vectors in request into a
- * scatterlist.  The scatterlist must be big enough to hold all
- * elements.  I.e. sized using blk_rq_count_integrity_sg().
- */
-int blk_rq_map_integrity_sg(struct request_queue *q, struct bio *bio,
-			    struct scatterlist *sglist)
+int blk_get_meta_cap(struct block_device *bdev, unsigned int cmd,
+		     struct logical_block_metadata_cap __user *argp)
 {
-	struct bio_vec iv, ivprv = { NULL };
-	struct scatterlist *sg = NULL;
-	unsigned int segments = 0;
-	struct bvec_iter iter;
-	int prev = 0;
-
-	bio_for_each_integrity_vec(iv, bio, iter) {
-
-		if (prev) {
-			if (!biovec_phys_mergeable(q, &ivprv, &iv))
-				goto new_segment;
-			if (sg->length + iv.bv_len > queue_max_segment_size(q))
-				goto new_segment;
+	struct blk_integrity *bi;
+	struct logical_block_metadata_cap meta_cap = {};
+	size_t usize = _IOC_SIZE(cmd);
+
+	if (!extensible_ioctl_valid(cmd, FS_IOC_GETLBMD_CAP, LBMD_SIZE_VER0))
+		return -ENOIOCTLCMD;
+
+	bi = blk_get_integrity(bdev->bd_disk);
+	if (!bi)
+		goto out;
+
+	if (bi->flags & BLK_INTEGRITY_DEVICE_CAPABLE)
+		meta_cap.lbmd_flags |= LBMD_PI_CAP_INTEGRITY;
+	if (bi->flags & BLK_INTEGRITY_REF_TAG)
+		meta_cap.lbmd_flags |= LBMD_PI_CAP_REFTAG;
+	meta_cap.lbmd_interval = 1 << bi->interval_exp;
+	meta_cap.lbmd_size = bi->metadata_size;
+	meta_cap.lbmd_pi_size = bi->pi_tuple_size;
+	meta_cap.lbmd_pi_offset = bi->pi_offset;
+	meta_cap.lbmd_opaque_size = bi->metadata_size - bi->pi_tuple_size;
+	if (meta_cap.lbmd_opaque_size && !bi->pi_offset)
+		meta_cap.lbmd_opaque_offset = bi->pi_tuple_size;
+
+	switch (bi->csum_type) {
+	case BLK_INTEGRITY_CSUM_NONE:
+		meta_cap.lbmd_guard_tag_type = LBMD_PI_CSUM_NONE;
+		break;
+	case BLK_INTEGRITY_CSUM_IP:
+		meta_cap.lbmd_guard_tag_type = LBMD_PI_CSUM_IP;
+		break;
+	case BLK_INTEGRITY_CSUM_CRC:
+		meta_cap.lbmd_guard_tag_type = LBMD_PI_CSUM_CRC16_T10DIF;
+		break;
+	case BLK_INTEGRITY_CSUM_CRC64:
+		meta_cap.lbmd_guard_tag_type = LBMD_PI_CSUM_CRC64_NVME;
+		break;
+	}
 
-			sg->length += iv.bv_len;
-		} else {
-new_segment:
-			if (!sg)
-				sg = sglist;
-			else {
-				sg_unmark_end(sg);
-				sg = sg_next(sg);
-			}
-
-			sg_set_page(sg, iv.bv_page, iv.bv_len, iv.bv_offset);
-			segments++;
+	if (bi->csum_type != BLK_INTEGRITY_CSUM_NONE)
+		meta_cap.lbmd_app_tag_size = 2;
+
+	if (bi->flags & BLK_INTEGRITY_REF_TAG) {
+		switch (bi->csum_type) {
+		case BLK_INTEGRITY_CSUM_CRC64:
+			meta_cap.lbmd_ref_tag_size =
+				sizeof_field(struct crc64_pi_tuple, ref_tag);
+			break;
+		case BLK_INTEGRITY_CSUM_CRC:
+		case BLK_INTEGRITY_CSUM_IP:
+			meta_cap.lbmd_ref_tag_size =
+				sizeof_field(struct t10_pi_tuple, ref_tag);
+			break;
+		default:
+			break;
 		}
-
-		prev = 1;
-		ivprv = iv;
 	}
 
-	if (sg)
-		sg_mark_end(sg);
-
-	return segments;
+out:
+	return copy_struct_to_user(argp, usize, &meta_cap, sizeof(meta_cap),
+				   NULL);
 }
-EXPORT_SYMBOL(blk_rq_map_integrity_sg);
 
-/**
- * blk_integrity_compare - Compare integrity profile of two disks
- * @gd1:	Disk to compare
- * @gd2:	Disk to compare
- *
- * Description: Meta-devices like DM and MD need to verify that all
- * sub-devices use the same integrity format before advertising to
- * upper layers that they can send/receive integrity metadata.  This
- * function can be used to check whether two gendisk devices have
- * compatible integrity formats.
- */
-int blk_integrity_compare(struct gendisk *gd1, struct gendisk *gd2)
+int blk_rq_integrity_map_user(struct request *rq, void __user *ubuf,
+			      ssize_t bytes)
 {
-	struct blk_integrity *b1 = &gd1->queue->integrity;
-	struct blk_integrity *b2 = &gd2->queue->integrity;
-
-	if (!b1->profile && !b2->profile)
-		return 0;
-
-	if (!b1->profile || !b2->profile)
-		return -1;
-
-	if (b1->interval_exp != b2->interval_exp) {
-		pr_err("%s: %s/%s protection interval %u != %u\n",
-		       __func__, gd1->disk_name, gd2->disk_name,
-		       1 << b1->interval_exp, 1 << b2->interval_exp);
-		return -1;
-	}
-
-	if (b1->tuple_size != b2->tuple_size) {
-		pr_err("%s: %s/%s tuple sz %u != %u\n", __func__,
-		       gd1->disk_name, gd2->disk_name,
-		       b1->tuple_size, b2->tuple_size);
-		return -1;
-	}
-
-	if (b1->tag_size && b2->tag_size && (b1->tag_size != b2->tag_size)) {
-		pr_err("%s: %s/%s tag sz %u != %u\n", __func__,
-		       gd1->disk_name, gd2->disk_name,
-		       b1->tag_size, b2->tag_size);
-		return -1;
-	}
+	int ret;
+	struct iov_iter iter;
 
-	if (b1->profile != b2->profile) {
-		pr_err("%s: %s/%s type %s != %s\n", __func__,
-		       gd1->disk_name, gd2->disk_name,
-		       b1->profile->name, b2->profile->name);
-		return -1;
-	}
+	iov_iter_ubuf(&iter, rq_data_dir(rq), ubuf, bytes);
+	ret = bio_integrity_map_user(rq->bio, &iter);
+	if (ret)
+		return ret;
 
+	rq->nr_integrity_segments = blk_rq_count_integrity_sg(rq->q, rq->bio);
+	rq->cmd_flags |= REQ_INTEGRITY;
 	return 0;
 }
-EXPORT_SYMBOL(blk_integrity_compare);
+EXPORT_SYMBOL_GPL(blk_rq_integrity_map_user);
 
 bool blk_integrity_merge_rq(struct request_queue *q, struct request *req,
 			    struct request *next)
@@ -188,7 +164,6 @@ bool blk_integrity_merge_bio(struct request_queue *q, struct request *req,
 			     struct bio *bio)
 {
 	int nr_integrity_segs;
-	struct bio *next = bio->bi_next;
 
 	if (blk_integrity_rq(req) == 0 && bio_integrity(bio) == NULL)
 		return true;
@@ -199,250 +174,156 @@ bool blk_integrity_merge_bio(struct request_queue *q, struct request *req,
 	if (bio_integrity(req->bio)->bip_flags != bio_integrity(bio)->bip_flags)
 		return false;
 
-	bio->bi_next = NULL;
 	nr_integrity_segs = blk_rq_count_integrity_sg(q, bio);
-	bio->bi_next = next;
-
 	if (req->nr_integrity_segments + nr_integrity_segs >
 	    q->limits.max_integrity_segments)
 		return false;
 
-	req->nr_integrity_segments += nr_integrity_segs;
-
 	return true;
 }
 
-struct integrity_sysfs_entry {
-	struct attribute attr;
-	ssize_t (*show)(struct blk_integrity *, char *);
-	ssize_t (*store)(struct blk_integrity *, const char *, size_t);
-};
-
-static ssize_t integrity_attr_show(struct kobject *kobj, struct attribute *attr,
-				   char *page)
-{
-	struct gendisk *disk = container_of(kobj, struct gendisk, integrity_kobj);
-	struct blk_integrity *bi = &disk->queue->integrity;
-	struct integrity_sysfs_entry *entry =
-		container_of(attr, struct integrity_sysfs_entry, attr);
-
-	return entry->show(bi, page);
-}
-
-static ssize_t integrity_attr_store(struct kobject *kobj,
-				    struct attribute *attr, const char *page,
-				    size_t count)
+static inline struct blk_integrity *dev_to_bi(struct device *dev)
 {
-	struct gendisk *disk = container_of(kobj, struct gendisk, integrity_kobj);
-	struct blk_integrity *bi = &disk->queue->integrity;
-	struct integrity_sysfs_entry *entry =
-		container_of(attr, struct integrity_sysfs_entry, attr);
-	ssize_t ret = 0;
-
-	if (entry->store)
-		ret = entry->store(bi, page, count);
-
-	return ret;
+	return &dev_to_disk(dev)->queue->limits.integrity;
 }
 
-static ssize_t integrity_format_show(struct blk_integrity *bi, char *page)
+const char *blk_integrity_profile_name(struct blk_integrity *bi)
 {
-	if (bi->profile && bi->profile->name)
-		return sprintf(page, "%s\n", bi->profile->name);
-	else
-		return sprintf(page, "none\n");
-}
+	switch (bi->csum_type) {
+	case BLK_INTEGRITY_CSUM_IP:
+		if (bi->flags & BLK_INTEGRITY_REF_TAG)
+			return "T10-DIF-TYPE1-IP";
+		return "T10-DIF-TYPE3-IP";
+	case BLK_INTEGRITY_CSUM_CRC:
+		if (bi->flags & BLK_INTEGRITY_REF_TAG)
+			return "T10-DIF-TYPE1-CRC";
+		return "T10-DIF-TYPE3-CRC";
+	case BLK_INTEGRITY_CSUM_CRC64:
+		if (bi->flags & BLK_INTEGRITY_REF_TAG)
+			return "EXT-DIF-TYPE1-CRC64";
+		return "EXT-DIF-TYPE3-CRC64";
+	case BLK_INTEGRITY_CSUM_NONE:
+		break;
+	}
 
-static ssize_t integrity_tag_size_show(struct blk_integrity *bi, char *page)
-{
-	return sprintf(page, "%u\n", bi->tag_size);
+	return "nop";
 }
+EXPORT_SYMBOL_GPL(blk_integrity_profile_name);
 
-static ssize_t integrity_interval_show(struct blk_integrity *bi, char *page)
+static ssize_t flag_store(struct device *dev, const char *page, size_t count,
+		unsigned char flag)
 {
-	return sprintf(page, "%u\n",
-		       bi->interval_exp ? 1 << bi->interval_exp : 0);
-}
+	struct request_queue *q = dev_to_disk(dev)->queue;
+	struct queue_limits lim;
+	unsigned long val;
+	int err;
 
-static ssize_t integrity_verify_store(struct blk_integrity *bi,
-				      const char *page, size_t count)
-{
-	char *p = (char *) page;
-	unsigned long val = simple_strtoul(p, &p, 10);
+	err = kstrtoul(page, 10, &val);
+	if (err)
+		return err;
 
+	/* note that the flags are inverted vs the values in the sysfs files */
+	lim = queue_limits_start_update(q);
 	if (val)
-		bi->flags |= BLK_INTEGRITY_VERIFY;
+		lim.integrity.flags &= ~flag;
 	else
-		bi->flags &= ~BLK_INTEGRITY_VERIFY;
+		lim.integrity.flags |= flag;
 
+	err = queue_limits_commit_update_frozen(q, &lim);
+	if (err)
+		return err;
 	return count;
 }
 
-static ssize_t integrity_verify_show(struct blk_integrity *bi, char *page)
+static ssize_t flag_show(struct device *dev, char *page, unsigned char flag)
 {
-	return sprintf(page, "%d\n", (bi->flags & BLK_INTEGRITY_VERIFY) != 0);
+	struct blk_integrity *bi = dev_to_bi(dev);
+
+	return sysfs_emit(page, "%d\n", !(bi->flags & flag));
 }
 
-static ssize_t integrity_generate_store(struct blk_integrity *bi,
-					const char *page, size_t count)
+static ssize_t format_show(struct device *dev, struct device_attribute *attr,
+			   char *page)
 {
-	char *p = (char *) page;
-	unsigned long val = simple_strtoul(p, &p, 10);
+	struct blk_integrity *bi = dev_to_bi(dev);
 
-	if (val)
-		bi->flags |= BLK_INTEGRITY_GENERATE;
-	else
-		bi->flags &= ~BLK_INTEGRITY_GENERATE;
-
-	return count;
+	if (!bi->metadata_size)
+		return sysfs_emit(page, "none\n");
+	return sysfs_emit(page, "%s\n", blk_integrity_profile_name(bi));
 }
 
-static ssize_t integrity_generate_show(struct blk_integrity *bi, char *page)
+static ssize_t tag_size_show(struct device *dev, struct device_attribute *attr,
+			     char *page)
 {
-	return sprintf(page, "%d\n", (bi->flags & BLK_INTEGRITY_GENERATE) != 0);
-}
+	struct blk_integrity *bi = dev_to_bi(dev);
 
-static ssize_t integrity_device_show(struct blk_integrity *bi, char *page)
-{
-	return sprintf(page, "%u\n",
-		       (bi->flags & BLK_INTEGRITY_DEVICE_CAPABLE) != 0);
+	return sysfs_emit(page, "%u\n", bi->tag_size);
 }
 
-static struct integrity_sysfs_entry integrity_format_entry = {
-	.attr = { .name = "format", .mode = 0444 },
-	.show = integrity_format_show,
-};
-
-static struct integrity_sysfs_entry integrity_tag_size_entry = {
-	.attr = { .name = "tag_size", .mode = 0444 },
-	.show = integrity_tag_size_show,
-};
-
-static struct integrity_sysfs_entry integrity_interval_entry = {
-	.attr = { .name = "protection_interval_bytes", .mode = 0444 },
-	.show = integrity_interval_show,
-};
-
-static struct integrity_sysfs_entry integrity_verify_entry = {
-	.attr = { .name = "read_verify", .mode = 0644 },
-	.show = integrity_verify_show,
-	.store = integrity_verify_store,
-};
-
-static struct integrity_sysfs_entry integrity_generate_entry = {
-	.attr = { .name = "write_generate", .mode = 0644 },
-	.show = integrity_generate_show,
-	.store = integrity_generate_store,
-};
-
-static struct integrity_sysfs_entry integrity_device_entry = {
-	.attr = { .name = "device_is_integrity_capable", .mode = 0444 },
-	.show = integrity_device_show,
-};
-
-static struct attribute *integrity_attrs[] = {
-	&integrity_format_entry.attr,
-	&integrity_tag_size_entry.attr,
-	&integrity_interval_entry.attr,
-	&integrity_verify_entry.attr,
-	&integrity_generate_entry.attr,
-	&integrity_device_entry.attr,
-	NULL,
-};
-ATTRIBUTE_GROUPS(integrity);
-
-static const struct sysfs_ops integrity_ops = {
-	.show	= &integrity_attr_show,
-	.store	= &integrity_attr_store,
-};
-
-static struct kobj_type integrity_ktype = {
-	.default_groups = integrity_groups,
-	.sysfs_ops	= &integrity_ops,
-};
-
-static blk_status_t blk_integrity_nop_fn(struct blk_integrity_iter *iter)
+static ssize_t protection_interval_bytes_show(struct device *dev,
+					      struct device_attribute *attr,
+					      char *page)
 {
-	return BLK_STS_OK;
+	struct blk_integrity *bi = dev_to_bi(dev);
+
+	return sysfs_emit(page, "%u\n",
+			  bi->interval_exp ? 1 << bi->interval_exp : 0);
 }
 
-static void blk_integrity_nop_prepare(struct request *rq)
+static ssize_t read_verify_store(struct device *dev,
+				 struct device_attribute *attr,
+				 const char *page, size_t count)
 {
+	return flag_store(dev, page, count, BLK_INTEGRITY_NOVERIFY);
 }
 
-static void blk_integrity_nop_complete(struct request *rq,
-		unsigned int nr_bytes)
+static ssize_t read_verify_show(struct device *dev,
+				struct device_attribute *attr, char *page)
 {
+	return flag_show(dev, page, BLK_INTEGRITY_NOVERIFY);
 }
 
-static const struct blk_integrity_profile nop_profile = {
-	.name = "nop",
-	.generate_fn = blk_integrity_nop_fn,
-	.verify_fn = blk_integrity_nop_fn,
-	.prepare_fn = blk_integrity_nop_prepare,
-	.complete_fn = blk_integrity_nop_complete,
-};
-
-/**
- * blk_integrity_register - Register a gendisk as being integrity-capable
- * @disk:	struct gendisk pointer to make integrity-aware
- * @template:	block integrity profile to register
- *
- * Description: When a device needs to advertise itself as being able to
- * send/receive integrity metadata it must use this function to register
- * the capability with the block layer. The template is a blk_integrity
- * struct with values appropriate for the underlying hardware. See
- * Documentation/block/data-integrity.rst.
- */
-void blk_integrity_register(struct gendisk *disk, struct blk_integrity *template)
+static ssize_t write_generate_store(struct device *dev,
+				    struct device_attribute *attr,
+				    const char *page, size_t count)
 {
-	struct blk_integrity *bi = &disk->queue->integrity;
-
-	bi->flags = BLK_INTEGRITY_VERIFY | BLK_INTEGRITY_GENERATE |
-		template->flags;
-	bi->interval_exp = template->interval_exp ? :
-		ilog2(queue_logical_block_size(disk->queue));
-	bi->profile = template->profile ? template->profile : &nop_profile;
-	bi->tuple_size = template->tuple_size;
-	bi->tag_size = template->tag_size;
-
-	blk_queue_flag_set(QUEUE_FLAG_STABLE_WRITES, disk->queue);
-
-#ifdef CONFIG_BLK_INLINE_ENCRYPTION
-	if (disk->queue->ksm) {
-		pr_warn("blk-integrity: Integrity and hardware inline encryption are not supported together. Disabling hardware inline encryption.\n");
-		blk_ksm_unregister(disk->queue);
-	}
-#endif
+	return flag_store(dev, page, count, BLK_INTEGRITY_NOGENERATE);
 }
-EXPORT_SYMBOL(blk_integrity_register);
 
-/**
- * blk_integrity_unregister - Unregister block integrity profile
- * @disk:	disk whose integrity profile to unregister
- *
- * Description: This function unregisters the integrity capability from
- * a block device.
- */
-void blk_integrity_unregister(struct gendisk *disk)
+static ssize_t write_generate_show(struct device *dev,
+				   struct device_attribute *attr, char *page)
 {
-	blk_queue_flag_clear(QUEUE_FLAG_STABLE_WRITES, disk->queue);
-	memset(&disk->queue->integrity, 0, sizeof(struct blk_integrity));
+	return flag_show(dev, page, BLK_INTEGRITY_NOGENERATE);
 }
-EXPORT_SYMBOL(blk_integrity_unregister);
 
-void blk_integrity_add(struct gendisk *disk)
+static ssize_t device_is_integrity_capable_show(struct device *dev,
+						struct device_attribute *attr,
+						char *page)
 {
-	if (kobject_init_and_add(&disk->integrity_kobj, &integrity_ktype,
-				 &disk_to_dev(disk)->kobj, "%s", "integrity"))
-		return;
+	struct blk_integrity *bi = dev_to_bi(dev);
 
-	kobject_uevent(&disk->integrity_kobj, KOBJ_ADD);
+	return sysfs_emit(page, "%u\n",
+			  !!(bi->flags & BLK_INTEGRITY_DEVICE_CAPABLE));
 }
 
-void blk_integrity_del(struct gendisk *disk)
-{
-	kobject_uevent(&disk->integrity_kobj, KOBJ_REMOVE);
-	kobject_del(&disk->integrity_kobj);
-	kobject_put(&disk->integrity_kobj);
-}
+static DEVICE_ATTR_RO(format);
+static DEVICE_ATTR_RO(tag_size);
+static DEVICE_ATTR_RO(protection_interval_bytes);
+static DEVICE_ATTR_RW(read_verify);
+static DEVICE_ATTR_RW(write_generate);
+static DEVICE_ATTR_RO(device_is_integrity_capable);
+
+static struct attribute *integrity_attrs[] = {
+	&dev_attr_format.attr,
+	&dev_attr_tag_size.attr,
+	&dev_attr_protection_interval_bytes.attr,
+	&dev_attr_read_verify.attr,
+	&dev_attr_write_generate.attr,
+	&dev_attr_device_is_integrity_capable.attr,
+	NULL
+};
+
+const struct attribute_group blk_integrity_attr_group = {
+	.name = "integrity",
+	.attrs = integrity_attrs,
+};