nvme: add support for enhanced metadata

NVM Express ratified TP 4068 defines new protection information formats.
Implement support for the CRC64 guard tags.

Since the block layer doesn't support variable length reference tags,
driver support for the Storage Tag space is not supported at this time.

Cc: Hannes Reinecke <hare@suse.de>
Cc: "Martin K. Petersen" <martin.petersen@oracle.com>
Cc: Klaus Jensen <its@irrelevant.dk>
Signed-off-by: Keith Busch <kbusch@kernel.org>
Reviewed-by: Martin K. Petersen <martin.petersen@oracle.com>
Link: https://lore.kernel.org/r/20220303201312.3255347-9-kbusch@kernel.org
Signed-off-by: Jens Axboe <axboe@kernel.dk>

Author: keithbusch

drivers/nvme/host/core.c

@@ -813,6 +813,30 @@ static blk_status_t nvme_setup_discard(struct nvme_ns *ns, struct request *req,
 	return BLK_STS_OK;
 }
 
+static void nvme_set_ref_tag(struct nvme_ns *ns, struct nvme_command *cmnd,
+			      struct request *req)
+{
+	u32 upper, lower;
+	u64 ref48;
+
+	/* both rw and write zeroes share the same reftag format */
+	switch (ns->guard_type) {
+	case NVME_NVM_NS_16B_GUARD:
+		cmnd->rw.reftag = cpu_to_le32(t10_pi_ref_tag(req));
+		break;
+	case NVME_NVM_NS_64B_GUARD:
+		ref48 = ext_pi_ref_tag(req);
+		lower = lower_32_bits(ref48);
+		upper = upper_32_bits(ref48);
+
+		cmnd->rw.reftag = cpu_to_le32(lower);
+		cmnd->rw.cdw3 = cpu_to_le32(upper);
+		break;
+	default:
+		break;
+	}
+}
+
 static inline blk_status_t nvme_setup_write_zeroes(struct nvme_ns *ns,
 		struct request *req, struct nvme_command *cmnd)
 {
@@ -834,8 +858,7 @@ static inline blk_status_t nvme_setup_write_zeroes(struct nvme_ns *ns,
 		switch (ns->pi_type) {
 		case NVME_NS_DPS_PI_TYPE1:
 		case NVME_NS_DPS_PI_TYPE2:
-			cmnd->write_zeroes.reftag =
-				cpu_to_le32(t10_pi_ref_tag(req));
+			nvme_set_ref_tag(ns, cmnd, req);
 			break;
 		}
 	}
@@ -861,7 +884,8 @@ static inline blk_status_t nvme_setup_rw(struct nvme_ns *ns,
 	cmnd->rw.opcode = op;
 	cmnd->rw.flags = 0;
 	cmnd->rw.nsid = cpu_to_le32(ns->head->ns_id);
-	cmnd->rw.rsvd2 = 0;
+	cmnd->rw.cdw2 = 0;
+	cmnd->rw.cdw3 = 0;
 	cmnd->rw.metadata = 0;
 	cmnd->rw.slba = cpu_to_le64(nvme_sect_to_lba(ns, blk_rq_pos(req)));
 	cmnd->rw.length = cpu_to_le16((blk_rq_bytes(req) >> ns->lba_shift) - 1);
@@ -892,7 +916,7 @@ static inline blk_status_t nvme_setup_rw(struct nvme_ns *ns,
 					NVME_RW_PRINFO_PRCHK_REF;
 			if (op == nvme_cmd_zone_append)
 				control |= NVME_RW_APPEND_PIREMAP;
-			cmnd->rw.reftag = cpu_to_le32(t10_pi_ref_tag(req));
+			nvme_set_ref_tag(ns, cmnd, req);
 			break;
 		}
 	}
@@ -1544,33 +1568,58 @@ int nvme_getgeo(struct block_device *bdev, struct hd_geometry *geo)
 }
 
 #ifdef CONFIG_BLK_DEV_INTEGRITY
-static void nvme_init_integrity(struct gendisk *disk, u16 ms, u8 pi_type,
+static void nvme_init_integrity(struct gendisk *disk, struct nvme_ns *ns,
 				u32 max_integrity_segments)
 {
 	struct blk_integrity integrity = { };
 
-	switch (pi_type) {
+	switch (ns->pi_type) {
 	case NVME_NS_DPS_PI_TYPE3:
-		integrity.profile = &t10_pi_type3_crc;
-		integrity.tag_size = sizeof(u16) + sizeof(u32);
-		integrity.flags |= BLK_INTEGRITY_DEVICE_CAPABLE;
+		switch (ns->guard_type) {
+		case NVME_NVM_NS_16B_GUARD:
+			integrity.profile = &t10_pi_type3_crc;
+			integrity.tag_size = sizeof(u16) + sizeof(u32);
+			integrity.flags |= BLK_INTEGRITY_DEVICE_CAPABLE;
+			break;
+		case NVME_NVM_NS_64B_GUARD:
+			integrity.profile = &ext_pi_type3_crc64;
+			integrity.tag_size = sizeof(u16) + 6;
+			integrity.flags |= BLK_INTEGRITY_DEVICE_CAPABLE;
+			break;
+		default:
+			integrity.profile = NULL;
+			break;
+		}
 		break;
 	case NVME_NS_DPS_PI_TYPE1:
 	case NVME_NS_DPS_PI_TYPE2:
-		integrity.profile = &t10_pi_type1_crc;
-		integrity.tag_size = sizeof(u16);
-		integrity.flags |= BLK_INTEGRITY_DEVICE_CAPABLE;
+		switch (ns->guard_type) {
+		case NVME_NVM_NS_16B_GUARD:
+			integrity.profile = &t10_pi_type1_crc;
+			integrity.tag_size = sizeof(u16);
+			integrity.flags |= BLK_INTEGRITY_DEVICE_CAPABLE;
+			break;
+		case NVME_NVM_NS_64B_GUARD:
+			integrity.profile = &ext_pi_type1_crc64;
+			integrity.tag_size = sizeof(u16);
+			integrity.flags |= BLK_INTEGRITY_DEVICE_CAPABLE;
+			break;
+		default:
+			integrity.profile = NULL;
+			break;
+		}
 		break;
 	default:
 		integrity.profile = NULL;
 		break;
 	}
-	integrity.tuple_size = ms;
+
+	integrity.tuple_size = ns->ms;
 	blk_integrity_register(disk, &integrity);
 	blk_queue_max_integrity_segments(disk->queue, max_integrity_segments);
 }
 #else
-static void nvme_init_integrity(struct gendisk *disk, u16 ms, u8 pi_type,
+static void nvme_init_integrity(struct gendisk *disk, struct nvme_ns *ns,
 				u32 max_integrity_segments)
 {
 }
@@ -1612,17 +1661,73 @@ static bool nvme_ns_ids_equal(struct nvme_ns_ids *a, struct nvme_ns_ids *b)
 		a->csi == b->csi;
 }
 
-static void nvme_configure_metadata(struct nvme_ns *ns, struct nvme_id_ns *id)
+static int nvme_init_ms(struct nvme_ns *ns, struct nvme_id_ns *id)
 {
+	bool first = id->dps & NVME_NS_DPS_PI_FIRST;
+	unsigned lbaf = nvme_lbaf_index(id->flbas);
 	struct nvme_ctrl *ctrl = ns->ctrl;
+	struct nvme_command c = { };
+	struct nvme_id_ns_nvm *nvm;
+	int ret = 0;
+	u32 elbaf;
+
+	ns->pi_size = 0;
+	ns->ms = le16_to_cpu(id->lbaf[lbaf].ms);
+	if (!(ctrl->ctratt & NVME_CTRL_ATTR_ELBAS)) {
+		ns->pi_size = sizeof(struct t10_pi_tuple);
+		ns->guard_type = NVME_NVM_NS_16B_GUARD;
+		goto set_pi;
+	}
+
+	nvm = kzalloc(sizeof(*nvm), GFP_KERNEL);
+	if (!nvm)
+		return -ENOMEM;
 
-	ns->ms = le16_to_cpu(id->lbaf[id->flbas & NVME_NS_FLBAS_LBA_MASK].ms);
-	if (id->dps & NVME_NS_DPS_PI_FIRST ||
-	    ns->ms == sizeof(struct t10_pi_tuple))
+	c.identify.opcode = nvme_admin_identify;
+	c.identify.nsid = cpu_to_le32(ns->head->ns_id);
+	c.identify.cns = NVME_ID_CNS_CS_NS;
+	c.identify.csi = NVME_CSI_NVM;
+
+	ret = nvme_submit_sync_cmd(ns->ctrl->admin_q, &c, nvm, sizeof(*nvm));
+	if (ret)
+		goto free_data;
+
+	elbaf = le32_to_cpu(nvm->elbaf[lbaf]);
+
+	/* no support for storage tag formats right now */
+	if (nvme_elbaf_sts(elbaf))
+		goto free_data;
+
+	ns->guard_type = nvme_elbaf_guard_type(elbaf);
+	switch (ns->guard_type) {
+	case NVME_NVM_NS_64B_GUARD:
+		ns->pi_size = sizeof(struct crc64_pi_tuple);
+		break;
+	case NVME_NVM_NS_16B_GUARD:
+		ns->pi_size = sizeof(struct t10_pi_tuple);
+		break;
+	default:
+		break;
+	}
+
+free_data:
+	kfree(nvm);
+set_pi:
+	if (ns->pi_size && (first || ns->ms == ns->pi_size))
 		ns->pi_type = id->dps & NVME_NS_DPS_PI_MASK;
 	else
 		ns->pi_type = 0;
 
+	return ret;
+}
+
+static void nvme_configure_metadata(struct nvme_ns *ns, struct nvme_id_ns *id)
+{
+	struct nvme_ctrl *ctrl = ns->ctrl;
+
+	if (nvme_init_ms(ns, id))
+		return;
+
 	ns->features &= ~(NVME_NS_METADATA_SUPPORTED | NVME_NS_EXT_LBAS);
 	if (!ns->ms || !(ctrl->ops->flags & NVME_F_METADATA_SUPPORTED))
 		return;
@@ -1738,7 +1843,7 @@ static void nvme_update_disk_info(struct gendisk *disk,
 	if (ns->ms) {
 		if (IS_ENABLED(CONFIG_BLK_DEV_INTEGRITY) &&
 		    (ns->features & NVME_NS_METADATA_SUPPORTED))
-			nvme_init_integrity(disk, ns->ms, ns->pi_type,
+			nvme_init_integrity(disk, ns,
 					    ns->ctrl->max_integrity_segments);
 		else if (!nvme_ns_has_pi(ns))
 			capacity = 0;
@@ -1793,7 +1898,7 @@ static void nvme_set_chunk_sectors(struct nvme_ns *ns, struct nvme_id_ns *id)
 
 static int nvme_update_ns_info(struct nvme_ns *ns, struct nvme_id_ns *id)
 {
-	unsigned lbaf = id->flbas & NVME_NS_FLBAS_LBA_MASK;
+	unsigned lbaf = nvme_lbaf_index(id->flbas);
 	int ret;
 
 	blk_mq_freeze_queue(ns->disk->queue);
@@ -2138,20 +2243,27 @@ static int nvme_configure_timestamp(struct nvme_ctrl *ctrl)
 	return ret;
 }
 
-static int nvme_configure_acre(struct nvme_ctrl *ctrl)
+static int nvme_configure_host_options(struct nvme_ctrl *ctrl)
 {
 	struct nvme_feat_host_behavior *host;
+	u8 acre = 0, lbafee = 0;
 	int ret;
 
 	/* Don't bother enabling the feature if retry delay is not reported */
-	if (!ctrl->crdt[0])
+	if (ctrl->crdt[0])
+		acre = NVME_ENABLE_ACRE;
+	if (ctrl->ctratt & NVME_CTRL_ATTR_ELBAS)
+		lbafee = NVME_ENABLE_LBAFEE;
+
+	if (!acre && !lbafee)
 		return 0;
 
 	host = kzalloc(sizeof(*host), GFP_KERNEL);
 	if (!host)
 		return 0;
 
-	host->acre = NVME_ENABLE_ACRE;
+	host->acre = acre;
+	host->lbafee = lbafee;
 	ret = nvme_set_features(ctrl, NVME_FEAT_HOST_BEHAVIOR, 0,
 				host, sizeof(*host), NULL);
 	kfree(host);
@@ -2989,7 +3101,7 @@ int nvme_init_ctrl_finish(struct nvme_ctrl *ctrl)
 	if (ret < 0)
 		return ret;
 
-	ret = nvme_configure_acre(ctrl);
+	ret = nvme_configure_host_options(ctrl);
 	if (ret < 0)
 		return ret;
 
@@ -4703,12 +4815,14 @@ static inline void _nvme_check_size(void)
 	BUILD_BUG_ON(sizeof(struct nvme_id_ctrl) != NVME_IDENTIFY_DATA_SIZE);
 	BUILD_BUG_ON(sizeof(struct nvme_id_ns) != NVME_IDENTIFY_DATA_SIZE);
 	BUILD_BUG_ON(sizeof(struct nvme_id_ns_zns) != NVME_IDENTIFY_DATA_SIZE);
+	BUILD_BUG_ON(sizeof(struct nvme_id_ns_nvm) != NVME_IDENTIFY_DATA_SIZE);
 	BUILD_BUG_ON(sizeof(struct nvme_id_ctrl_zns) != NVME_IDENTIFY_DATA_SIZE);
 	BUILD_BUG_ON(sizeof(struct nvme_id_ctrl_nvm) != NVME_IDENTIFY_DATA_SIZE);
 	BUILD_BUG_ON(sizeof(struct nvme_lba_range_type) != 64);
 	BUILD_BUG_ON(sizeof(struct nvme_smart_log) != 512);
 	BUILD_BUG_ON(sizeof(struct nvme_dbbuf) != 64);
 	BUILD_BUG_ON(sizeof(struct nvme_directive_cmd) != 64);
+	BUILD_BUG_ON(sizeof(struct nvme_feat_host_behavior) != 512);
 }
 
 

drivers/nvme/host/nvme.h

@@ -453,9 +453,11 @@ struct nvme_ns {
 
 	int lba_shift;
 	u16 ms;
+	u16 pi_size;
 	u16 sgs;
 	u32 sws;
 	u8 pi_type;
+	u8 guard_type;
 #ifdef CONFIG_BLK_DEV_ZONED
 	u64 zsze;
 #endif
@@ -478,7 +480,7 @@ struct nvme_ns {
 /* NVMe ns supports metadata actions by the controller (generate/strip) */
 static inline bool nvme_ns_has_pi(struct nvme_ns *ns)
 {
-	return ns->pi_type && ns->ms == sizeof(struct t10_pi_tuple);
+	return ns->pi_type && ns->ms == ns->pi_size;
 }
 
 struct nvme_ctrl_ops {