nvme: introduce NVME_NS_METADATA_SUPPORTED flag

This is a preparation for adding support for metadata in fabric
controllers. New flag will imply that NVMe namespace supports getting
metadata that was originally generated by host's block layer.

Signed-off-by: Max Gurtovoy <maxg@mellanox.com>
Reviewed-by: Israel Rukshin <israelr@mellanox.com>
Reviewed-by: Martin K. Petersen <martin.petersen@oracle.com>
Reviewed-by: James Smart <james.smart@broadcom.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>

2 files changed, 35 insertions, 7 deletions

diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c
index fecf484e7b08..aa168dd58f31 100644
--- a/drivers/nvme/host/core.c
+++ b/drivers/nvme/host/core.c
@@ -1885,13 +1885,27 @@ static void nvme_update_disk_info(struct gendisk *disk,
 	blk_queue_io_min(disk->queue, phys_bs);
 	blk_queue_io_opt(disk->queue, io_opt);
 
-	if (ns->ms && !(ns->features & NVME_NS_EXT_LBAS) &&
-	    (ns->ctrl->ops->flags & NVME_F_METADATA_SUPPORTED))
-		nvme_init_integrity(disk, ns->ms, ns->pi_type);
-	if ((ns->ms && !nvme_ns_has_pi(ns) && !blk_get_integrity(disk)) ||
-	    ns->lba_shift > PAGE_SHIFT)
+	/*
+	 * The block layer can't support LBA sizes larger than the page size
+	 * yet, so catch this early and don't allow block I/O.
+	 */
+	if (ns->lba_shift > PAGE_SHIFT)
 		capacity = 0;
 
+	/*
+	 * Register a metadata profile for PI, or the plain non-integrity NVMe
+	 * metadata masquerading as Type 0 if supported, otherwise reject block
+	 * I/O to namespaces with metadata except when the namespace supports
+	 * PI, as it can strip/insert in that case.
+	 */
+	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);
+		else if (!nvme_ns_has_pi(ns))
+			capacity = 0;
+	}
+
 	set_capacity_revalidate_and_notify(disk, capacity, false);
 
 	nvme_config_discard(disk, ns);
@@ -1926,14 +1940,27 @@ static void __nvme_revalidate_disk(struct gendisk *disk, struct nvme_id_ns *id)
 
 	ns->features = 0;
 	ns->ms = le16_to_cpu(id->lbaf[id->flbas & NVME_NS_FLBAS_LBA_MASK].ms);
-	if (ns->ms && (id->flbas & NVME_NS_FLBAS_META_EXT))
-		ns->features |= NVME_NS_EXT_LBAS;
 	/* the PI implementation requires metadata equal t10 pi tuple size */
 	if (ns->ms == sizeof(struct t10_pi_tuple))
 		ns->pi_type = id->dps & NVME_NS_DPS_PI_MASK;
 	else
 		ns->pi_type = 0;
 
+	if (ns->ms) {
+		if (id->flbas & NVME_NS_FLBAS_META_EXT)
+			ns->features |= NVME_NS_EXT_LBAS;
+
+		/*
+		 * For PCI, Extended logical block will be generated by the
+		 * controller. Non-extended format can be generated by the
+		 * block layer.
+		 */
+		if (ns->ctrl->ops->flags & NVME_F_METADATA_SUPPORTED) {
+			if (!(ns->features & NVME_NS_EXT_LBAS))
+				ns->features |= NVME_NS_METADATA_SUPPORTED;
+		}
+	}
+
 	if (iob)
 		blk_queue_chunk_sectors(ns->queue, rounddown_pow_of_two(iob));
 	nvme_update_disk_info(disk, ns, id);
diff --git a/drivers/nvme/host/nvme.h b/drivers/nvme/host/nvme.h
index 58ae6ebdc63a..9ed6a3dac537 100644
--- a/drivers/nvme/host/nvme.h
+++ b/drivers/nvme/host/nvme.h
@@ -366,6 +366,7 @@ struct nvme_ns_head {
 
 enum nvme_ns_features {
 	NVME_NS_EXT_LBAS = 1 << 0, /* support extended LBA format */
+	NVME_NS_METADATA_SUPPORTED = 1 << 1, /* support getting generated md */
 };
 
 struct nvme_ns {