Linux-NVME Archive on lore.kernel.org
 help / color / Atom feed
From: Max Gurtovoy <maxg@mellanox.com>
To: maxg@mellanox.com, linux-nvme@lists.infradead.org,
	kbusch@kernel.org, hch@lst.de, sagi@grimberg.me,
	martin.petersen@oracle.com, jsmart2021@gmail.com,
	axboe@kernel.dk
Cc: vladimirk@mellanox.com, shlomin@mellanox.com,
	israelr@mellanox.com, idanb@mellanox.com, oren@mellanox.com,
	nitzanc@mellanox.com
Subject: [PATCH 04/15] nvme: enforce extended LBA format for fabrics metadata
Date: Tue, 28 Apr 2020 16:11:24 +0300
Message-ID: <20200428131135.211521-5-maxg@mellanox.com> (raw)
In-Reply-To: <20200428131135.211521-1-maxg@mellanox.com>

An extended LBA is a larger LBA that is created when metadata associated
with the LBA is transferred contiguously with the LBA data (AKA
interleaved). The metadata may be either transferred as part of the LBA
(creating an extended LBA) or it may be transferred as a separate
contiguous buffer of data. According to the NVMeoF spec, a fabrics ctrl
supports only an Extended LBA format. Fail revalidation in case we have a
spec violation. Also add a flag that will imply on capable transports and
controllers as part of a preparation for allowing end-to-end protection
information for fabric controllers.

Suggested-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Max Gurtovoy <maxg@mellanox.com>
Signed-off-by: Israel Rukshin <israelr@mellanox.com>
---
 drivers/nvme/host/core.c | 41 +++++++++++++++++++++++++++--------------
 drivers/nvme/host/nvme.h |  1 +
 2 files changed, 28 insertions(+), 14 deletions(-)

diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c
index 40aa2be..dd59de0 100644
--- a/drivers/nvme/host/core.c
+++ b/drivers/nvme/host/core.c
@@ -1908,9 +1908,10 @@ static void nvme_update_disk_info(struct gendisk *disk,
 	blk_mq_unfreeze_queue(disk->queue);
 }
 
-static void __nvme_revalidate_disk(struct gendisk *disk, struct nvme_id_ns *id)
+static int __nvme_revalidate_disk(struct gendisk *disk, struct nvme_id_ns *id)
 {
 	struct nvme_ns *ns = disk->private_data;
+	struct nvme_ctrl *ctrl = ns->ctrl;
 	u32 iob;
 
 	/*
@@ -1921,9 +1922,9 @@ static void __nvme_revalidate_disk(struct gendisk *disk, struct nvme_id_ns *id)
 	if (ns->lba_shift == 0)
 		ns->lba_shift = 9;
 
-	if ((ns->ctrl->quirks & NVME_QUIRK_STRIPE_SIZE) &&
-	    is_power_of_2(ns->ctrl->max_hw_sectors))
-		iob = ns->ctrl->max_hw_sectors;
+	if ((ctrl->quirks & NVME_QUIRK_STRIPE_SIZE) &&
+	    is_power_of_2(ctrl->max_hw_sectors))
+		iob = ctrl->max_hw_sectors;
 	else
 		iob = nvme_lba_to_sect(ns, le16_to_cpu(id->noiob));
 
@@ -1936,16 +1937,24 @@ static void __nvme_revalidate_disk(struct gendisk *disk, struct nvme_id_ns *id)
 		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.
+		 * For PCIe only the separate metadata pointer is supported,
+		 * as the block layer supplies metadata in a separate bio_vec
+		 * chain. For Fabrics, only metadata as part of extended data
+		 * LBA is supported on the wire per the Fabrics specification,
+		 * but the HBA/HCA will do the remapping from the separate
+		 * metadata buffers for us.
 		 */
-		if (ns->ctrl->ops->flags & NVME_F_METADATA_SUPPORTED) {
-			if (!(ns->features & NVME_NS_EXT_LBAS))
+		if (id->flbas & NVME_NS_FLBAS_META_EXT) {
+			ns->features |= NVME_NS_EXT_LBAS;
+			if ((ctrl->ops->flags & NVME_F_FABRICS) &&
+			    (ctrl->ops->flags & NVME_F_METADATA_SUPPORTED) &&
+			    ctrl->pi_capable)
+				ns->features |= NVME_NS_METADATA_SUPPORTED;
+		} else {
+			if (WARN_ON_ONCE(ctrl->ops->flags & NVME_F_FABRICS))
+				return -EINVAL;
+			if (ctrl->ops->flags & NVME_F_METADATA_SUPPORTED)
 				ns->features |= NVME_NS_METADATA_SUPPORTED;
 		}
 	}
@@ -1960,6 +1969,7 @@ static void __nvme_revalidate_disk(struct gendisk *disk, struct nvme_id_ns *id)
 		revalidate_disk(ns->head->disk);
 	}
 #endif
+	return 0;
 }
 
 static int nvme_revalidate_disk(struct gendisk *disk)
@@ -1995,7 +2005,7 @@ static int nvme_revalidate_disk(struct gendisk *disk)
 		goto free_id;
 	}
 
-	__nvme_revalidate_disk(disk, id);
+	ret = __nvme_revalidate_disk(disk, id);
 free_id:
 	kfree(id);
 out:
@@ -3649,7 +3659,8 @@ static void nvme_alloc_ns(struct nvme_ctrl *ctrl, unsigned nsid)
 	memcpy(disk->disk_name, disk_name, DISK_NAME_LEN);
 	ns->disk = disk;
 
-	__nvme_revalidate_disk(disk, id);
+	if (__nvme_revalidate_disk(disk, id))
+		goto out_free_disk;
 
 	if ((ctrl->quirks & NVME_QUIRK_LIGHTNVM) && id->vs[0] == 0x1) {
 		ret = nvme_nvm_register(ns, disk_name, node);
@@ -3674,6 +3685,8 @@ static void nvme_alloc_ns(struct nvme_ctrl *ctrl, unsigned nsid)
 	return;
  out_put_disk:
 	put_disk(ns->disk);
+ out_free_disk:
+	del_gendisk(ns->disk);
  out_unlink_ns:
 	mutex_lock(&ctrl->subsys->lock);
 	list_del_rcu(&ns->siblings);
diff --git a/drivers/nvme/host/nvme.h b/drivers/nvme/host/nvme.h
index 0f5fa85..f60ca01 100644
--- a/drivers/nvme/host/nvme.h
+++ b/drivers/nvme/host/nvme.h
@@ -291,6 +291,7 @@ struct nvme_ctrl {
 	u16 icdoff;
 	u16 maxcmd;
 	int nr_reconnects;
+	bool pi_capable;
 	struct nvmf_ctrl_options *opts;
 
 	struct page *discard_page;
-- 
1.8.3.1


_______________________________________________
linux-nvme mailing list
linux-nvme@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/linux-nvme

  parent reply index

Thread overview: 35+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2020-04-28 13:11 [PATCH 00/15 V6] nvme-rdma/nvmet-rdma: Add metadata/T10-PI support Max Gurtovoy
2020-04-28 13:11 ` [PATCH 01/15] nvme: introduce namespace features flag Max Gurtovoy
2020-05-01 13:20   ` Christoph Hellwig
2020-05-01 14:24   ` Christoph Hellwig
2020-05-01 14:33     ` Max Gurtovoy
2020-04-28 13:11 ` [PATCH 02/15] nvme: introduce NVME_NS_METADATA_SUPPORTED flag Max Gurtovoy
2020-05-01 13:20   ` Christoph Hellwig
2020-04-28 13:11 ` [PATCH 03/15] nvme: make nvme_ns_has_pi accessible to transports Max Gurtovoy
2020-05-01 13:20   ` Christoph Hellwig
2020-04-28 13:11 ` Max Gurtovoy [this message]
2020-05-01 13:21   ` [PATCH 04/15] nvme: enforce extended LBA format for fabrics metadata Christoph Hellwig
2020-05-01 13:41   ` Christoph Hellwig
2020-04-28 13:11 ` [PATCH 05/15] nvme: introduce max_integrity_segments ctrl attribute Max Gurtovoy
2020-04-28 13:11 ` [PATCH 06/15] nvme: introduce NVME_INLINE_MD_SG_CNT Max Gurtovoy
2020-04-28 13:11 ` [PATCH 07/15] nvme-rdma: introduce nvme_rdma_sgl structure Max Gurtovoy
2020-04-28 13:11 ` [PATCH 08/15] nvme-rdma: add metadata/T10-PI support Max Gurtovoy
2020-05-01 14:26   ` Christoph Hellwig
2020-05-01 15:00     ` Max Gurtovoy
2020-04-28 13:11 ` [PATCH 09/15] nvmet: add metadata characteristics for a namespace Max Gurtovoy
2020-05-01 15:50   ` Christoph Hellwig
2020-04-28 13:11 ` [PATCH 10/15] nvmet: rename nvmet_rw_len to nvmet_rw_data_len Max Gurtovoy
2020-04-28 13:11 ` [PATCH 11/15] nvmet: rename nvmet_check_data_len to nvmet_check_transfer_len Max Gurtovoy
2020-04-28 13:11 ` [PATCH 12/15] nvme: add Metadata Capabilities enumerations Max Gurtovoy
2020-05-01 15:53   ` Christoph Hellwig
2020-05-03 12:43     ` Max Gurtovoy
2020-04-28 13:11 ` [PATCH 13/15] nvmet: add metadata/T10-PI support Max Gurtovoy
2020-05-01 15:58   ` Christoph Hellwig
2020-05-01 16:19   ` Christoph Hellwig
2020-04-28 13:11 ` [PATCH 14/15] nvmet: add metadata support for block devices Max Gurtovoy
2020-05-01 16:25   ` Christoph Hellwig
2020-04-28 13:11 ` [PATCH 15/15] nvmet-rdma: add metadata/T10-PI support Max Gurtovoy
2020-05-01 16:48   ` Christoph Hellwig
2020-05-03 16:29     ` Max Gurtovoy
2020-05-04 14:08       ` Christoph Hellwig
2020-05-04 14:19         ` Max Gurtovoy

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20200428131135.211521-5-maxg@mellanox.com \
    --to=maxg@mellanox.com \
    --cc=axboe@kernel.dk \
    --cc=hch@lst.de \
    --cc=idanb@mellanox.com \
    --cc=israelr@mellanox.com \
    --cc=jsmart2021@gmail.com \
    --cc=kbusch@kernel.org \
    --cc=linux-nvme@lists.infradead.org \
    --cc=martin.petersen@oracle.com \
    --cc=nitzanc@mellanox.com \
    --cc=oren@mellanox.com \
    --cc=sagi@grimberg.me \
    --cc=shlomin@mellanox.com \
    --cc=vladimirk@mellanox.com \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link

Linux-NVME Archive on lore.kernel.org

Archives are clonable:
	git clone --mirror https://lore.kernel.org/linux-nvme/0 linux-nvme/git/0.git

	# If you have public-inbox 1.1+ installed, you may
	# initialize and index your mirror using the following commands:
	public-inbox-init -V2 linux-nvme linux-nvme/ https://lore.kernel.org/linux-nvme \
		linux-nvme@lists.infradead.org
	public-inbox-index linux-nvme

Example config snippet for mirrors

Newsgroup available over NNTP:
	nntp://nntp.lore.kernel.org/org.infradead.lists.linux-nvme


AGPL code for this site: git clone https://public-inbox.org/public-inbox.git