Merge patch series "add ioctl to query metadata and protection info capabilities"

Anuj Gupta <anuj20.g@samsung.com> says:

This patch series adds a new ioctl to query metadata and integrity
capability.

* patches from https://lore.kernel.org/20250630090548.3317-1-anuj20.g@samsung.com:
  fs: add ioctl to query metadata and protection info capabilities
  nvme: set pi_offset only when checksum type is not BLK_INTEGRITY_CSUM_NONE
  block: introduce pi_tuple_size field in blk_integrity
  block: rename tuple_size field in blk_integrity to metadata_size

Link: https://lore.kernel.org/20250630090548.3317-1-anuj20.g@samsung.com
Signed-off-by: Christian Brauner <brauner@kernel.org>

block/bio-integrity-auto.c

@@ -54,10 +54,10 @@ static bool bi_offload_capable(struct blk_integrity *bi)
 {
 	switch (bi->csum_type) {
 	case BLK_INTEGRITY_CSUM_CRC64:
-		return bi->tuple_size == sizeof(struct crc64_pi_tuple);
+		return bi->metadata_size == sizeof(struct crc64_pi_tuple);
 	case BLK_INTEGRITY_CSUM_CRC:
 	case BLK_INTEGRITY_CSUM_IP:
-		return bi->tuple_size == sizeof(struct t10_pi_tuple);
+		return bi->metadata_size == sizeof(struct t10_pi_tuple);
 	default:
 		pr_warn_once("%s: unknown integrity checksum type:%d\n",
 			__func__, bi->csum_type);

block/blk-integrity.c

@@ -13,6 +13,7 @@
 #include <linux/scatterlist.h>
 #include <linux/export.h>
 #include <linux/slab.h>
+#include <linux/t10-pi.h>
 
 #include "blk.h"
 
@@ -54,6 +55,57 @@ new_segment:
 	return segments;
 }
 
+int blk_get_meta_cap(struct block_device *bdev, unsigned int cmd,
+		     struct logical_block_metadata_cap __user *argp)
+{
+	struct blk_integrity *bi = blk_get_integrity(bdev->bd_disk);
+	struct logical_block_metadata_cap meta_cap = {};
+	size_t usize = _IOC_SIZE(cmd);
+
+	if (!argp)
+		return -EINVAL;
+	if (usize < LBMD_SIZE_VER0)
+		return -EINVAL;
+	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;
+
+	meta_cap.lbmd_guard_tag_type = bi->csum_type;
+	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;
+		}
+	}
+
+out:
+	return copy_struct_to_user(argp, usize, &meta_cap, sizeof(meta_cap),
+				   NULL);
+}
+
 /**
  * blk_rq_map_integrity_sg - Map integrity metadata into a scatterlist
  * @rq:		request to map
@@ -239,7 +291,7 @@ static ssize_t format_show(struct device *dev, struct device_attribute *attr,
 {
 	struct blk_integrity *bi = dev_to_bi(dev);
 
-	if (!bi->tuple_size)
+	if (!bi->metadata_size)
 		return sysfs_emit(page, "none\n");
 	return sysfs_emit(page, "%s\n", blk_integrity_profile_name(bi));
 }

block/blk-settings.c

@@ -14,6 +14,8 @@
 #include <linux/jiffies.h>
 #include <linux/gfp.h>
 #include <linux/dma-mapping.h>
+#include <linux/t10-pi.h>
+#include <linux/crc64.h>
 
 #include "blk.h"
 #include "blk-rq-qos.h"
@@ -114,7 +116,7 @@ static int blk_validate_integrity_limits(struct queue_limits *lim)
 {
 	struct blk_integrity *bi = &lim->integrity;
 
-	if (!bi->tuple_size) {
+	if (!bi->metadata_size) {
 		if (bi->csum_type != BLK_INTEGRITY_CSUM_NONE ||
 		    bi->tag_size || ((bi->flags & BLK_INTEGRITY_REF_TAG))) {
 			pr_warn("invalid PI settings.\n");
@@ -135,6 +137,42 @@ static int blk_validate_integrity_limits(struct queue_limits *lim)
 		return -EINVAL;
 	}
 
+	if (bi->pi_tuple_size > bi->metadata_size) {
+		pr_warn("pi_tuple_size (%u) exceeds metadata_size (%u)\n",
+			 bi->pi_tuple_size,
+			 bi->metadata_size);
+		return -EINVAL;
+	}
+
+	switch (bi->csum_type) {
+	case BLK_INTEGRITY_CSUM_NONE:
+		if (bi->pi_tuple_size) {
+			pr_warn("pi_tuple_size must be 0 when checksum type \
+				 is none\n");
+			return -EINVAL;
+		}
+		break;
+	case BLK_INTEGRITY_CSUM_CRC:
+	case BLK_INTEGRITY_CSUM_IP:
+		if (bi->pi_tuple_size != sizeof(struct t10_pi_tuple)) {
+			pr_warn("pi_tuple_size mismatch for T10 PI: expected \
+				 %zu, got %u\n",
+				 sizeof(struct t10_pi_tuple),
+				 bi->pi_tuple_size);
+			return -EINVAL;
+		}
+		break;
+	case BLK_INTEGRITY_CSUM_CRC64:
+		if (bi->pi_tuple_size != sizeof(struct crc64_pi_tuple)) {
+			pr_warn("pi_tuple_size mismatch for CRC64 PI: \
+				 expected %zu, got %u\n",
+				 sizeof(struct crc64_pi_tuple),
+				 bi->pi_tuple_size);
+			return -EINVAL;
+		}
+		break;
+	}
+
 	if (!bi->interval_exp)
 		bi->interval_exp = ilog2(lim->logical_block_size);
 
@@ -875,7 +913,7 @@ bool queue_limits_stack_integrity(struct queue_limits *t,
 		return true;
 
 	if (ti->flags & BLK_INTEGRITY_STACKED) {
-		if (ti->tuple_size != bi->tuple_size)
+		if (ti->metadata_size != bi->metadata_size)
 			goto incompatible;
 		if (ti->interval_exp != bi->interval_exp)
 			goto incompatible;
@@ -891,7 +929,7 @@ bool queue_limits_stack_integrity(struct queue_limits *t,
 		ti->flags |= (bi->flags & BLK_INTEGRITY_DEVICE_CAPABLE) |
 			     (bi->flags & BLK_INTEGRITY_REF_TAG);
 		ti->csum_type = bi->csum_type;
-		ti->tuple_size = bi->tuple_size;
+		ti->metadata_size = bi->metadata_size;
 		ti->pi_offset = bi->pi_offset;
 		ti->interval_exp = bi->interval_exp;
 		ti->tag_size = bi->tag_size;

block/ioctl.c

@@ -13,6 +13,7 @@
 #include <linux/uaccess.h>
 #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"
@@ -566,6 +567,9 @@ static int blkdev_common_ioctl(struct block_device *bdev, blk_mode_t mode,
 {
 	unsigned int max_sectors;
 
+	if (_IOC_NR(cmd) == _IOC_NR(FS_IOC_GETLBMD_CAP))
+		return blk_get_meta_cap(bdev, cmd, argp);
+
 	switch (cmd) {
 	case BLKFLSBUF:
 		return blkdev_flushbuf(bdev, cmd, arg);

block/t10-pi.c

@@ -56,7 +56,7 @@ static void t10_pi_generate(struct blk_integrity_iter *iter,
 			pi->ref_tag = 0;
 
 		iter->data_buf += iter->interval;
-		iter->prot_buf += bi->tuple_size;
+		iter->prot_buf += bi->metadata_size;
 		iter->seed++;
 	}
 }
@@ -105,7 +105,7 @@ static blk_status_t t10_pi_verify(struct blk_integrity_iter *iter,
 
 next:
 		iter->data_buf += iter->interval;
-		iter->prot_buf += bi->tuple_size;
+		iter->prot_buf += bi->metadata_size;
 		iter->seed++;
 	}
 
@@ -125,7 +125,7 @@ next:
 static void t10_pi_type1_prepare(struct request *rq)
 {
 	struct blk_integrity *bi = &rq->q->limits.integrity;
-	const int tuple_sz = bi->tuple_size;
+	const int tuple_sz = bi->metadata_size;
 	u32 ref_tag = t10_pi_ref_tag(rq);
 	u8 offset = bi->pi_offset;
 	struct bio *bio;
@@ -177,7 +177,7 @@ static void t10_pi_type1_complete(struct request *rq, unsigned int nr_bytes)
 {
 	struct blk_integrity *bi = &rq->q->limits.integrity;
 	unsigned intervals = nr_bytes >> bi->interval_exp;
-	const int tuple_sz = bi->tuple_size;
+	const int tuple_sz = bi->metadata_size;
 	u32 ref_tag = t10_pi_ref_tag(rq);
 	u8 offset = bi->pi_offset;
 	struct bio *bio;
@@ -234,7 +234,7 @@ static void ext_pi_crc64_generate(struct blk_integrity_iter *iter,
 			put_unaligned_be48(0ULL, pi->ref_tag);
 
 		iter->data_buf += iter->interval;
-		iter->prot_buf += bi->tuple_size;
+		iter->prot_buf += bi->metadata_size;
 		iter->seed++;
 	}
 }
@@ -289,7 +289,7 @@ static blk_status_t ext_pi_crc64_verify(struct blk_integrity_iter *iter,
 
 next:
 		iter->data_buf += iter->interval;
-		iter->prot_buf += bi->tuple_size;
+		iter->prot_buf += bi->metadata_size;
 		iter->seed++;
 	}
 
@@ -299,7 +299,7 @@ next:
 static void ext_pi_type1_prepare(struct request *rq)
 {
 	struct blk_integrity *bi = &rq->q->limits.integrity;
-	const int tuple_sz = bi->tuple_size;
+	const int tuple_sz = bi->metadata_size;
 	u64 ref_tag = ext_pi_ref_tag(rq);
 	u8 offset = bi->pi_offset;
 	struct bio *bio;
@@ -340,7 +340,7 @@ static void ext_pi_type1_complete(struct request *rq, unsigned int nr_bytes)
 {
 	struct blk_integrity *bi = &rq->q->limits.integrity;
 	unsigned intervals = nr_bytes >> bi->interval_exp;
-	const int tuple_sz = bi->tuple_size;
+	const int tuple_sz = bi->metadata_size;
 	u64 ref_tag = ext_pi_ref_tag(rq);
 	u8 offset = bi->pi_offset;
 	struct bio *bio;

drivers/md/dm-crypt.c

@@ -1189,11 +1189,11 @@ static int crypt_integrity_ctr(struct crypt_config *cc, struct dm_target *ti)
 		return -EINVAL;
 	}
 
-	if (bi->tuple_size < cc->used_tag_size) {
+	if (bi->metadata_size < cc->used_tag_size) {
 		ti->error = "Integrity profile tag size mismatch.";
 		return -EINVAL;
 	}
-	cc->tuple_size = bi->tuple_size;
+	cc->tuple_size = bi->metadata_size;
 	if (1 << bi->interval_exp != cc->sector_size) {
 		ti->error = "Integrity profile sector size mismatch.";
 		return -EINVAL;

drivers/md/dm-integrity.c

@@ -3906,8 +3906,8 @@ static void dm_integrity_io_hints(struct dm_target *ti, struct queue_limits *lim
 		struct blk_integrity *bi = &limits->integrity;
 
 		memset(bi, 0, sizeof(*bi));
-		bi->tuple_size = ic->tag_size;
-		bi->tag_size = bi->tuple_size;
+		bi->metadata_size = ic->tag_size;
+		bi->tag_size = bi->metadata_size;
 		bi->interval_exp =
 			ic->sb->log2_sectors_per_block + SECTOR_SHIFT;
 	}
@@ -4746,18 +4746,18 @@ static int dm_integrity_ctr(struct dm_target *ti, unsigned int argc, char **argv
 			ti->error = "Integrity profile not supported";
 			goto bad;
 		}
-		/*printk("tag_size: %u, tuple_size: %u\n", bi->tag_size, bi->tuple_size);*/
-		if (bi->tuple_size < ic->tag_size) {
+		/*printk("tag_size: %u, metadata_size: %u\n", bi->tag_size, bi->metadata_size);*/
+		if (bi->metadata_size < ic->tag_size) {
 			r = -EINVAL;
 			ti->error = "The integrity profile is smaller than tag size";
 			goto bad;
 		}
-		if ((unsigned long)bi->tuple_size > PAGE_SIZE / 2) {
+		if ((unsigned long)bi->metadata_size > PAGE_SIZE / 2) {
 			r = -EINVAL;
 			ti->error = "Too big tuple size";
 			goto bad;
 		}
-		ic->tuple_size = bi->tuple_size;
+		ic->tuple_size = bi->metadata_size;
 		if (1 << bi->interval_exp != ic->sectors_per_block << SECTOR_SHIFT) {
 			r = -EINVAL;
 			ti->error = "Integrity profile sector size mismatch";

drivers/nvdimm/btt.c

@@ -1506,7 +1506,7 @@ static int btt_blk_init(struct btt *btt)
 	int rc;
 
 	if (btt_meta_size(btt) && IS_ENABLED(CONFIG_BLK_DEV_INTEGRITY)) {
-		lim.integrity.tuple_size = btt_meta_size(btt);
+		lim.integrity.metadata_size = btt_meta_size(btt);
 		lim.integrity.tag_size = btt_meta_size(btt);
 	}
 

drivers/nvme/host/core.c

@@ -1866,8 +1866,11 @@ static bool nvme_init_integrity(struct nvme_ns_head *head,
 		break;
 	}
 
-	bi->tuple_size = head->ms;
-	bi->pi_offset = info->pi_offset;
+	bi->metadata_size = head->ms;
+	if (bi->csum_type) {
+		bi->pi_tuple_size = head->pi_size;
+		bi->pi_offset = info->pi_offset;
+	}
 	return true;
 }
 

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

@@ -65,7 +65,7 @@ static void nvmet_bdev_ns_enable_integrity(struct nvmet_ns *ns)
 		return;
 
 	if (bi->csum_type == BLK_INTEGRITY_CSUM_CRC) {
-		ns->metadata_size = bi->tuple_size;
+		ns->metadata_size = bi->metadata_size;
 		if (bi->flags & BLK_INTEGRITY_REF_TAG)
 			ns->pi_type = NVME_NS_DPS_PI_TYPE1;
 		else

drivers/scsi/sd_dif.c

@@ -52,7 +52,8 @@ void sd_dif_config_host(struct scsi_disk *sdkp, struct queue_limits *lim)
 	if (type != T10_PI_TYPE3_PROTECTION)
 		bi->flags |= BLK_INTEGRITY_REF_TAG;
 
-	bi->tuple_size = sizeof(struct t10_pi_tuple);
+	bi->metadata_size = sizeof(struct t10_pi_tuple);
+	bi->pi_tuple_size = bi->metadata_size;
 
 	if (dif && type) {
 		bi->flags |= BLK_INTEGRITY_DEVICE_CAPABLE;

include/linux/blk-integrity.h

@@ -29,11 +29,13 @@ int blk_rq_map_integrity_sg(struct request *, struct scatterlist *);
 int blk_rq_count_integrity_sg(struct request_queue *, struct bio *);
 int blk_rq_integrity_map_user(struct request *rq, void __user *ubuf,
 			      ssize_t bytes);
+int blk_get_meta_cap(struct block_device *bdev, unsigned int cmd,
+		     struct logical_block_metadata_cap __user *argp);
 
 static inline bool
 blk_integrity_queue_supports_integrity(struct request_queue *q)
 {
-	return q->limits.integrity.tuple_size;
+	return q->limits.integrity.metadata_size;
 }
 
 static inline struct blk_integrity *blk_get_integrity(struct gendisk *disk)
@@ -74,7 +76,7 @@ static inline unsigned int bio_integrity_intervals(struct blk_integrity *bi,
 static inline unsigned int bio_integrity_bytes(struct blk_integrity *bi,
 					       unsigned int sectors)
 {
-	return bio_integrity_intervals(bi, sectors) * bi->tuple_size;
+	return bio_integrity_intervals(bi, sectors) * bi->metadata_size;
 }
 
 static inline bool blk_integrity_rq(struct request *rq)
@@ -92,6 +94,11 @@ static inline struct bio_vec rq_integrity_vec(struct request *rq)
 				 rq->bio->bi_integrity->bip_iter);
 }
 #else /* CONFIG_BLK_DEV_INTEGRITY */
+static inline int blk_get_meta_cap(struct block_device *bdev, unsigned int cmd,
+				   struct logical_block_metadata_cap __user *argp)
+{
+	return -EOPNOTSUPP;
+}
 static inline int blk_rq_count_integrity_sg(struct request_queue *q,
 					    struct bio *b)
 {

include/linux/blkdev.h

@@ -116,10 +116,11 @@ enum blk_integrity_checksum {
 struct blk_integrity {
 	unsigned char				flags;
 	enum blk_integrity_checksum		csum_type;
-	unsigned char				tuple_size;
+	unsigned char				metadata_size;
 	unsigned char				pi_offset;
 	unsigned char				interval_exp;
 	unsigned char				tag_size;
+	unsigned char				pi_tuple_size;
 };
 
 typedef unsigned int __bitwise blk_mode_t;

include/uapi/linux/fs.h

@@ -91,6 +91,63 @@ struct fs_sysfs_path {
 	__u8			name[128];
 };
 
+/* Protection info capability flags */
+#define	LBMD_PI_CAP_INTEGRITY		(1 << 0)
+#define	LBMD_PI_CAP_REFTAG		(1 << 1)
+
+/* Checksum types for Protection Information */
+#define LBMD_PI_CSUM_NONE		0
+#define LBMD_PI_CSUM_IP			1
+#define LBMD_PI_CSUM_CRC16_T10DIF	2
+#define LBMD_PI_CSUM_CRC64_NVME		4
+
+/* sizeof first published struct */
+#define LBMD_SIZE_VER0			16
+
+/*
+ * Logical block metadata capability descriptor
+ * If the device does not support metadata, all the fields will be zero.
+ * Applications must check lbmd_flags to determine whether metadata is
+ * supported or not.
+ */
+struct logical_block_metadata_cap {
+	/* Bitmask of logical block metadata capability flags */
+	__u32	lbmd_flags;
+	/*
+	 * The amount of data described by each unit of logical block
+	 * metadata
+	 */
+	__u16	lbmd_interval;
+	/*
+	 * Size in bytes of the logical block metadata associated with each
+	 * interval
+	 */
+	__u8	lbmd_size;
+	/*
+	 * Size in bytes of the opaque block tag associated with each
+	 * interval
+	 */
+	__u8	lbmd_opaque_size;
+	/*
+	 * Offset in bytes of the opaque block tag within the logical block
+	 * metadata
+	 */
+	__u8	lbmd_opaque_offset;
+	/* Size in bytes of the T10 PI tuple associated with each interval */
+	__u8	lbmd_pi_size;
+	/* Offset in bytes of T10 PI tuple within the logical block metadata */
+	__u8	lbmd_pi_offset;
+	/* T10 PI guard tag type */
+	__u8	lbmd_guard_tag_type;
+	/* Size in bytes of the T10 PI application tag */
+	__u8	lbmd_app_tag_size;
+	/* Size in bytes of the T10 PI reference tag */
+	__u8	lbmd_ref_tag_size;
+	/* Size in bytes of the T10 PI storage tag */
+	__u8	lbmd_storage_tag_size;
+	__u8	pad;
+};
+
 /* extent-same (dedupe) ioctls; these MUST match the btrfs ioctl definitions */
 #define FILE_DEDUPE_RANGE_SAME		0
 #define FILE_DEDUPE_RANGE_DIFFERS	1
@@ -247,6 +304,8 @@ struct fsxattr {
  * also /sys/kernel/debug/ for filesystems with debugfs exports
  */
 #define FS_IOC_GETFSSYSFSPATH		_IOR(0x15, 1, struct fs_sysfs_path)
+/* Get logical block metadata capability details */
+#define FS_IOC_GETLBMD_CAP		_IOWR(0x15, 2, struct logical_block_metadata_cap)
 
 /*
  * Inode flags (FS_IOC_GETFLAGS / FS_IOC_SETFLAGS)