Merge tag 'for-5.15/drivers-2021-08-30' of git://git.kernel.dk/linux-block

Pull block driver updates from Jens Axboe:
 "Sitting on top of the core block changes, here are the driver changes
  for the 5.15 merge window:

   - NVMe updates via Christoph:
       - suspend improvements for devices with an HMB (Keith Busch)
       - handle double completions more gacefull (Sagi Grimberg)
       - cleanup the selects for the nvme core code a bit (Sagi Grimberg)
       - don't update queue count when failing to set io queues (Ruozhu Li)
       - various nvmet connect fixes (Amit Engel)
       - cleanup lightnvm leftovers (Keith Busch, me)
       - small cleanups (Colin Ian King, Hou Pu)
       - add tracing for the Set Features command (Hou Pu)
       - CMB sysfs cleanups (Keith Busch)
       - add a mutex_destroy call (Keith Busch)

   - remove lightnvm subsystem. It's served its purpose and ultimately
     led to zoned nvme support, we no longer need it (Christoph)

   - revert floppy O_NDELAY fix (Denis)

   - nbd fixes (Hou, Pavel, Baokun)

   - nbd locking fixes (Tetsuo)

   - nbd device removal fixes (Christoph)

   - raid10 rcu warning fix (Xiao)

   - raid1 write behind fix (Guoqing)

   - rnbd fixes (Gioh, Md Haris)

   - misc fixes (Colin)"

* tag 'for-5.15/drivers-2021-08-30' of git://git.kernel.dk/linux-block: (42 commits)
  Revert "floppy: reintroduce O_NDELAY fix"
  raid1: ensure write behind bio has less than BIO_MAX_VECS sectors
  md/raid10: Remove unnecessary rcu_dereference in raid10_handle_discard
  nbd: remove nbd->destroy_complete
  nbd: only return usable devices from nbd_find_unused
  nbd: set nbd->index before releasing nbd_index_mutex
  nbd: prevent IDR lookups from finding partially initialized devices
  nbd: reset NBD to NULL when restarting in nbd_genl_connect
  nbd: add missing locking to the nbd_dev_add error path
  nvme: remove the unused NVME_NS_* enum
  nvme: remove nvm_ndev from ns
  nvme: Have NVME_FABRICS select NVME_CORE instead of transport drivers
  block: nbd: add sanity check for first_minor
  nvmet: check that host sqsize does not exceed ctrl MQES
  nvmet: avoid duplicate qid in connect cmd
  nvmet: pass back cntlid on successful completion
  nvme-rdma: don't update queue count when failing to set io queues
  nvme-tcp: don't update queue count when failing to set io queues
  nvme-tcp: pair send_mutex init with destroy
  nvme: allow user toggling hmb usage
  ...

17 files changed, 276 insertions, 1428 deletions

diff --git a/drivers/nvme/host/Kconfig b/drivers/nvme/host/Kconfig
index c3f3d77f1aac..dc0450ca23a3 100644
--- a/drivers/nvme/host/Kconfig
+++ b/drivers/nvme/host/Kconfig
@@ -33,12 +33,12 @@ config NVME_HWMON
 	  in the system.
 
 config NVME_FABRICS
+	select NVME_CORE
 	tristate
 
 config NVME_RDMA
 	tristate "NVM Express over Fabrics RDMA host driver"
 	depends on INFINIBAND && INFINIBAND_ADDR_TRANS && BLOCK
-	select NVME_CORE
 	select NVME_FABRICS
 	select SG_POOL
 	help
@@ -55,7 +55,6 @@ config NVME_FC
 	tristate "NVM Express over Fabrics FC host driver"
 	depends on BLOCK
 	depends on HAS_DMA
-	select NVME_CORE
 	select NVME_FABRICS
 	select SG_POOL
 	help
@@ -72,7 +71,6 @@ config NVME_TCP
 	tristate "NVM Express over Fabrics TCP host driver"
 	depends on INET
 	depends on BLOCK
-	select NVME_CORE
 	select NVME_FABRICS
 	select CRYPTO
 	select CRYPTO_CRC32C
diff --git a/drivers/nvme/host/Makefile b/drivers/nvme/host/Makefile
index cbc509784b2e..dfaacd472e5d 100644
--- a/drivers/nvme/host/Makefile
+++ b/drivers/nvme/host/Makefile
@@ -12,7 +12,6 @@ obj-$(CONFIG_NVME_TCP)			+= nvme-tcp.o
 nvme-core-y				:= core.o ioctl.o
 nvme-core-$(CONFIG_TRACING)		+= trace.o
 nvme-core-$(CONFIG_NVME_MULTIPATH)	+= multipath.o
-nvme-core-$(CONFIG_NVM)			+= lightnvm.o
 nvme-core-$(CONFIG_BLK_DEV_ZONED)	+= zns.o
 nvme-core-$(CONFIG_FAULT_INJECTION_DEBUG_FS)	+= fault_inject.o
 nvme-core-$(CONFIG_NVME_HWMON)		+= hwmon.o
diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c
index 68acd33c3856..8679a108f571 100644
--- a/drivers/nvme/host/core.c
+++ b/drivers/nvme/host/core.c
@@ -587,9 +587,6 @@ static void nvme_free_ns(struct kref *kref)
 {
 	struct nvme_ns *ns = container_of(kref, struct nvme_ns, kref);
 
-	if (ns->ndev)
-		nvme_nvm_unregister(ns);
-
 	put_disk(ns->disk);
 	nvme_put_ns_head(ns->head);
 	nvme_put_ctrl(ns->ctrl);
@@ -1028,7 +1025,8 @@ blk_status_t nvme_setup_cmd(struct nvme_ns *ns, struct request *req)
 		return BLK_STS_IOERR;
 	}
 
-	cmd->common.command_id = req->tag;
+	nvme_req(req)->genctr++;
+	cmd->common.command_id = nvme_cid(req);
 	trace_nvme_setup_cmd(req, cmd);
 	return ret;
 }
@@ -3217,9 +3215,6 @@ static const struct attribute_group nvme_ns_id_attr_group = {
 
 const struct attribute_group *nvme_ns_id_attr_groups[] = {
 	&nvme_ns_id_attr_group,
-#ifdef CONFIG_NVM
-	&nvme_nvm_attr_group,
-#endif
 	NULL,
 };
 
@@ -3762,13 +3757,6 @@ static void nvme_alloc_ns(struct nvme_ctrl *ctrl, unsigned nsid,
 	if (nvme_update_ns_info(ns, id))
 		goto out_unlink_ns;
 
-	if ((ctrl->quirks & NVME_QUIRK_LIGHTNVM) && id->vs[0] == 0x1) {
-		if (nvme_nvm_register(ns, disk->disk_name, node)) {
-			dev_warn(ctrl->device, "LightNVM init failure\n");
-			goto out_unlink_ns;
-		}
-	}
-
 	down_write(&ctrl->namespaces_rwsem);
 	list_add_tail(&ns->list, &ctrl->namespaces);
 	up_write(&ctrl->namespaces_rwsem);
diff --git a/drivers/nvme/host/fabrics.c b/drivers/nvme/host/fabrics.c
index a5469fd9d4c3..668c6bb7a567 100644
--- a/drivers/nvme/host/fabrics.c
+++ b/drivers/nvme/host/fabrics.c
@@ -719,7 +719,6 @@ static int nvmf_parse_options(struct nvmf_ctrl_options *opts,
 				ret = -EINVAL;
 				goto out;
 			}
-			nvmf_host_put(opts->host);
 			opts->host = nvmf_host_add(p);
 			kfree(p);
 			if (!opts->host) {
diff --git a/drivers/nvme/host/ioctl.c b/drivers/nvme/host/ioctl.c
index 305ddd415e45..22314962842d 100644
--- a/drivers/nvme/host/ioctl.c
+++ b/drivers/nvme/host/ioctl.c
@@ -342,9 +342,7 @@ static int nvme_ns_ioctl(struct nvme_ns *ns, unsigned int cmd,
 	case NVME_IOCTL_IO64_CMD:
 		return nvme_user_cmd64(ns->ctrl, ns, argp);
 	default:
-		if (!ns->ndev)
-			return -ENOTTY;
-		return nvme_nvm_ioctl(ns, cmd, argp);
+		return -ENOTTY;
 	}
 }
 
diff --git a/drivers/nvme/host/lightnvm.c b/drivers/nvme/host/lightnvm.c
deleted file mode 100644
index e9d9ad47f70f..000000000000
--- a/drivers/nvme/host/lightnvm.c
+++ /dev/null
@@ -1,1274 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-/*
- * nvme-lightnvm.c - LightNVM NVMe device
- *
- * Copyright (C) 2014-2015 IT University of Copenhagen
- * Initial release: Matias Bjorling <mb@lightnvm.io>
- */
-
-#include "nvme.h"
-
-#include <linux/nvme.h>
-#include <linux/bitops.h>
-#include <linux/lightnvm.h>
-#include <linux/vmalloc.h>
-#include <linux/sched/sysctl.h>
-#include <uapi/linux/lightnvm.h>
-
-enum nvme_nvm_admin_opcode {
-	nvme_nvm_admin_identity		= 0xe2,
-	nvme_nvm_admin_get_bb_tbl	= 0xf2,
-	nvme_nvm_admin_set_bb_tbl	= 0xf1,
-};
-
-enum nvme_nvm_log_page {
-	NVME_NVM_LOG_REPORT_CHUNK	= 0xca,
-};
-
-struct nvme_nvm_ph_rw {
-	__u8			opcode;
-	__u8			flags;
-	__u16			command_id;
-	__le32			nsid;
-	__u64			rsvd2;
-	__le64			metadata;
-	__le64			prp1;
-	__le64			prp2;
-	__le64			spba;
-	__le16			length;
-	__le16			control;
-	__le32			dsmgmt;
-	__le64			resv;
-};
-
-struct nvme_nvm_erase_blk {
-	__u8			opcode;
-	__u8			flags;
-	__u16			command_id;
-	__le32			nsid;
-	__u64			rsvd[2];
-	__le64			prp1;
-	__le64			prp2;
-	__le64			spba;
-	__le16			length;
-	__le16			control;
-	__le32			dsmgmt;
-	__le64			resv;
-};
-
-struct nvme_nvm_identity {
-	__u8			opcode;
-	__u8			flags;
-	__u16			command_id;
-	__le32			nsid;
-	__u64			rsvd[2];
-	__le64			prp1;
-	__le64			prp2;
-	__u32			rsvd11[6];
-};
-
-struct nvme_nvm_getbbtbl {
-	__u8			opcode;
-	__u8			flags;
-	__u16			command_id;
-	__le32			nsid;
-	__u64			rsvd[2];
-	__le64			prp1;
-	__le64			prp2;
-	__le64			spba;
-	__u32			rsvd4[4];
-};
-
-struct nvme_nvm_setbbtbl {
-	__u8			opcode;
-	__u8			flags;
-	__u16			command_id;
-	__le32			nsid;
-	__le64			rsvd[2];
-	__le64			prp1;
-	__le64			prp2;
-	__le64			spba;
-	__le16			nlb;
-	__u8			value;
-	__u8			rsvd3;
-	__u32			rsvd4[3];
-};
-
-struct nvme_nvm_command {
-	union {
-		struct nvme_common_command common;
-		struct nvme_nvm_ph_rw ph_rw;
-		struct nvme_nvm_erase_blk erase;
-		struct nvme_nvm_identity identity;
-		struct nvme_nvm_getbbtbl get_bb;
-		struct nvme_nvm_setbbtbl set_bb;
-	};
-};
-
-struct nvme_nvm_id12_grp {
-	__u8			mtype;
-	__u8			fmtype;
-	__le16			res16;
-	__u8			num_ch;
-	__u8			num_lun;
-	__u8			num_pln;
-	__u8			rsvd1;
-	__le16			num_chk;
-	__le16			num_pg;
-	__le16			fpg_sz;
-	__le16			csecs;
-	__le16			sos;
-	__le16			rsvd2;
-	__le32			trdt;
-	__le32			trdm;
-	__le32			tprt;
-	__le32			tprm;
-	__le32			tbet;
-	__le32			tbem;
-	__le32			mpos;
-	__le32			mccap;
-	__le16			cpar;
-	__u8			reserved[906];
-} __packed;
-
-struct nvme_nvm_id12_addrf {
-	__u8			ch_offset;
-	__u8			ch_len;
-	__u8			lun_offset;
-	__u8			lun_len;
-	__u8			pln_offset;
-	__u8			pln_len;
-	__u8			blk_offset;
-	__u8			blk_len;
-	__u8			pg_offset;
-	__u8			pg_len;
-	__u8			sec_offset;
-	__u8			sec_len;
-	__u8			res[4];
-} __packed;
-
-struct nvme_nvm_id12 {
-	__u8			ver_id;
-	__u8			vmnt;
-	__u8			cgrps;
-	__u8			res;
-	__le32			cap;
-	__le32			dom;
-	struct nvme_nvm_id12_addrf ppaf;
-	__u8			resv[228];
-	struct nvme_nvm_id12_grp grp;
-	__u8			resv2[2880];
-} __packed;
-
-struct nvme_nvm_bb_tbl {
-	__u8	tblid[4];
-	__le16	verid;
-	__le16	revid;
-	__le32	rvsd1;
-	__le32	tblks;
-	__le32	tfact;
-	__le32	tgrown;
-	__le32	tdresv;
-	__le32	thresv;
-	__le32	rsvd2[8];
-	__u8	blk[];
-};
-
-struct nvme_nvm_id20_addrf {
-	__u8			grp_len;
-	__u8			pu_len;
-	__u8			chk_len;
-	__u8			lba_len;
-	__u8			resv[4];
-};
-
-struct nvme_nvm_id20 {
-	__u8			mjr;
-	__u8			mnr;
-	__u8			resv[6];
-
-	struct nvme_nvm_id20_addrf lbaf;
-
-	__le32			mccap;
-	__u8			resv2[12];
-
-	__u8			wit;
-	__u8			resv3[31];
-
-	/* Geometry */
-	__le16			num_grp;
-	__le16			num_pu;
-	__le32			num_chk;
-	__le32			clba;
-	__u8			resv4[52];
-
-	/* Write data requirements */
-	__le32			ws_min;
-	__le32			ws_opt;
-	__le32			mw_cunits;
-	__le32			maxoc;
-	__le32			maxocpu;
-	__u8			resv5[44];
-
-	/* Performance related metrics */
-	__le32			trdt;
-	__le32			trdm;
-	__le32			twrt;
-	__le32			twrm;
-	__le32			tcrst;
-	__le32			tcrsm;
-	__u8			resv6[40];
-
-	/* Reserved area */
-	__u8			resv7[2816];
-
-	/* Vendor specific */
-	__u8			vs[1024];
-};
-
-struct nvme_nvm_chk_meta {
-	__u8	state;
-	__u8	type;
-	__u8	wi;
-	__u8	rsvd[5];
-	__le64	slba;
-	__le64	cnlb;
-	__le64	wp;
-};
-
-/*
- * Check we didn't inadvertently grow the command struct
- */
-static inline void _nvme_nvm_check_size(void)
-{
-	BUILD_BUG_ON(sizeof(struct nvme_nvm_identity) != 64);
-	BUILD_BUG_ON(sizeof(struct nvme_nvm_ph_rw) != 64);
-	BUILD_BUG_ON(sizeof(struct nvme_nvm_erase_blk) != 64);
-	BUILD_BUG_ON(sizeof(struct nvme_nvm_getbbtbl) != 64);
-	BUILD_BUG_ON(sizeof(struct nvme_nvm_setbbtbl) != 64);
-	BUILD_BUG_ON(sizeof(struct nvme_nvm_id12_grp) != 960);
-	BUILD_BUG_ON(sizeof(struct nvme_nvm_id12_addrf) != 16);
-	BUILD_BUG_ON(sizeof(struct nvme_nvm_id12) != NVME_IDENTIFY_DATA_SIZE);
-	BUILD_BUG_ON(sizeof(struct nvme_nvm_bb_tbl) != 64);
-	BUILD_BUG_ON(sizeof(struct nvme_nvm_id20_addrf) != 8);
-	BUILD_BUG_ON(sizeof(struct nvme_nvm_id20) != NVME_IDENTIFY_DATA_SIZE);
-	BUILD_BUG_ON(sizeof(struct nvme_nvm_chk_meta) != 32);
-	BUILD_BUG_ON(sizeof(struct nvme_nvm_chk_meta) !=
-						sizeof(struct nvm_chk_meta));
-}
-
-static void nvme_nvm_set_addr_12(struct nvm_addrf_12 *dst,
-				 struct nvme_nvm_id12_addrf *src)
-{
-	dst->ch_len = src->ch_len;
-	dst->lun_len = src->lun_len;
-	dst->blk_len = src->blk_len;
-	dst->pg_len = src->pg_len;
-	dst->pln_len = src->pln_len;
-	dst->sec_len = src->sec_len;
-
-	dst->ch_offset = src->ch_offset;
-	dst->lun_offset = src->lun_offset;
-	dst->blk_offset = src->blk_offset;
-	dst->pg_offset = src->pg_offset;
-	dst->pln_offset = src->pln_offset;
-	dst->sec_offset = src->sec_offset;
-
-	dst->ch_mask = ((1ULL << dst->ch_len) - 1) << dst->ch_offset;
-	dst->lun_mask = ((1ULL << dst->lun_len) - 1) << dst->lun_offset;
-	dst->blk_mask = ((1ULL << dst->blk_len) - 1) << dst->blk_offset;
-	dst->pg_mask = ((1ULL << dst->pg_len) - 1) << dst->pg_offset;
-	dst->pln_mask = ((1ULL << dst->pln_len) - 1) << dst->pln_offset;
-	dst->sec_mask = ((1ULL << dst->sec_len) - 1) << dst->sec_offset;
-}
-
-static int nvme_nvm_setup_12(struct nvme_nvm_id12 *id,
-			     struct nvm_geo *geo)
-{
-	struct nvme_nvm_id12_grp *src;
-	int sec_per_pg, sec_per_pl, pg_per_blk;
-
-	if (id->cgrps != 1)
-		return -EINVAL;
-
-	src = &id->grp;
-
-	if (src->mtype != 0) {
-		pr_err("nvm: memory type not supported\n");
-		return -EINVAL;
-	}
-
-	/* 1.2 spec. only reports a single version id - unfold */
-	geo->major_ver_id = id->ver_id;
-	geo->minor_ver_id = 2;
-
-	/* Set compacted version for upper layers */
-	geo->version = NVM_OCSSD_SPEC_12;
-
-	geo->num_ch = src->num_ch;
-	geo->num_lun = src->num_lun;
-	geo->all_luns = geo->num_ch * geo->num_lun;
-
-	geo->num_chk = le16_to_cpu(src->num_chk);
-
-	geo->csecs = le16_to_cpu(src->csecs);
-	geo->sos = le16_to_cpu(src->sos);
-
-	pg_per_blk = le16_to_cpu(src->num_pg);
-	sec_per_pg = le16_to_cpu(src->fpg_sz) / geo->csecs;
-	sec_per_pl = sec_per_pg * src->num_pln;
-	geo->clba = sec_per_pl * pg_per_blk;
-
-	geo->all_chunks = geo->all_luns * geo->num_chk;
-	geo->total_secs = geo->clba * geo->all_chunks;
-
-	geo->ws_min = sec_per_pg;
-	geo->ws_opt = sec_per_pg;
-	geo->mw_cunits = geo->ws_opt << 3;	/* default to MLC safe values */
-
-	/* Do not impose values for maximum number of open blocks as it is
-	 * unspecified in 1.2. Users of 1.2 must be aware of this and eventually
-	 * specify these values through a quirk if restrictions apply.
-	 */
-	geo->maxoc = geo->all_luns * geo->num_chk;
-	geo->maxocpu = geo->num_chk;
-
-	geo->mccap = le32_to_cpu(src->mccap);
-
-	geo->trdt = le32_to_cpu(src->trdt);
-	geo->trdm = le32_to_cpu(src->trdm);
-	geo->tprt = le32_to_cpu(src->tprt);
-	geo->tprm = le32_to_cpu(src->tprm);
-	geo->tbet = le32_to_cpu(src->tbet);
-	geo->tbem = le32_to_cpu(src->tbem);
-
-	/* 1.2 compatibility */
-	geo->vmnt = id->vmnt;
-	geo->cap = le32_to_cpu(id->cap);
-	geo->dom = le32_to_cpu(id->dom);
-
-	geo->mtype = src->mtype;
-	geo->fmtype = src->fmtype;
-
-	geo->cpar = le16_to_cpu(src->cpar);
-	geo->mpos = le32_to_cpu(src->mpos);
-
-	geo->pln_mode = NVM_PLANE_SINGLE;
-
-	if (geo->mpos & 0x020202) {
-		geo->pln_mode = NVM_PLANE_DOUBLE;
-		geo->ws_opt <<= 1;
-	} else if (geo->mpos & 0x040404) {
-		geo->pln_mode = NVM_PLANE_QUAD;
-		geo->ws_opt <<= 2;
-	}
-
-	geo->num_pln = src->num_pln;
-	geo->num_pg = le16_to_cpu(src->num_pg);
-	geo->fpg_sz = le16_to_cpu(src->fpg_sz);
-
-	nvme_nvm_set_addr_12((struct nvm_addrf_12 *)&geo->addrf, &id->ppaf);
-
-	return 0;
-}
-
-static void nvme_nvm_set_addr_20(struct nvm_addrf *dst,
-				 struct nvme_nvm_id20_addrf *src)
-{
-	dst->ch_len = src->grp_len;
-	dst->lun_len = src->pu_len;
-	dst->chk_len = src->chk_len;
-	dst->sec_len = src->lba_len;
-
-	dst->sec_offset = 0;
-	dst->chk_offset = dst->sec_len;
-	dst->lun_offset = dst->chk_offset + dst->chk_len;
-	dst->ch_offset = dst->lun_offset + dst->lun_len;
-
-	dst->ch_mask = ((1ULL << dst->ch_len) - 1) << dst->ch_offset;
-	dst->lun_mask = ((1ULL << dst->lun_len) - 1) << dst->lun_offset;
-	dst->chk_mask = ((1ULL << dst->chk_len) - 1) << dst->chk_offset;
-	dst->sec_mask = ((1ULL << dst->sec_len) - 1) << dst->sec_offset;
-}
-
-static int nvme_nvm_setup_20(struct nvme_nvm_id20 *id,
-			     struct nvm_geo *geo)
-{
-	geo->major_ver_id = id->mjr;
-	geo->minor_ver_id = id->mnr;
-
-	/* Set compacted version for upper layers */
-	geo->version = NVM_OCSSD_SPEC_20;
-
-	geo->num_ch = le16_to_cpu(id->num_grp);
-	geo->num_lun = le16_to_cpu(id->num_pu);
-	geo->all_luns = geo->num_ch * geo->num_lun;
-
-	geo->num_chk = le32_to_cpu(id->num_chk);
-	geo->clba = le32_to_cpu(id->clba);
-
-	geo->all_chunks = geo->all_luns * geo->num_chk;
-	geo->total_secs = geo->clba * geo->all_chunks;
-
-	geo->ws_min = le32_to_cpu(id->ws_min);
-	geo->ws_opt = le32_to_cpu(id->ws_opt);
-	geo->mw_cunits = le32_to_cpu(id->mw_cunits);
-	geo->maxoc = le32_to_cpu(id->maxoc);
-	geo->maxocpu = le32_to_cpu(id->maxocpu);
-
-	geo->trdt = le32_to_cpu(id->trdt);
-	geo->trdm = le32_to_cpu(id->trdm);
-	geo->tprt = le32_to_cpu(id->twrt);
-	geo->tprm = le32_to_cpu(id->twrm);
-	geo->tbet = le32_to_cpu(id->tcrst);
-	geo->tbem = le32_to_cpu(id->tcrsm);
-
-	nvme_nvm_set_addr_20(&geo->addrf, &id->lbaf);
-
-	return 0;
-}
-
-static int nvme_nvm_identity(struct nvm_dev *nvmdev)
-{
-	struct nvme_ns *ns = nvmdev->q->queuedata;
-	struct nvme_nvm_id12 *id;
-	struct nvme_nvm_command c = {};
-	int ret;
-
-	c.identity.opcode = nvme_nvm_admin_identity;
-	c.identity.nsid = cpu_to_le32(ns->head->ns_id);
-
-	id = kmalloc(sizeof(struct nvme_nvm_id12), GFP_KERNEL);
-	if (!id)
-		return -ENOMEM;
-
-	ret = nvme_submit_sync_cmd(ns->ctrl->admin_q, (struct nvme_command *)&c,
-				id, sizeof(struct nvme_nvm_id12));
-	if (ret) {
-		ret = -EIO;
-		goto out;
-	}
-
-	/*
-	 * The 1.2 and 2.0 specifications share the first byte in their geometry
-	 * command to make it possible to know what version a device implements.
-	 */
-	switch (id->ver_id) {
-	case 1:
-		ret = nvme_nvm_setup_12(id, &nvmdev->geo);
-		break;
-	case 2:
-		ret = nvme_nvm_setup_20((struct nvme_nvm_id20 *)id,
-							&nvmdev->geo);
-		break;
-	default:
-		dev_err(ns->ctrl->device, "OCSSD revision not supported (%d)\n",
-							id->ver_id);
-		ret = -EINVAL;
-	}
-
-out:
-	kfree(id);
-	return ret;
-}
-
-static int nvme_nvm_get_bb_tbl(struct nvm_dev *nvmdev, struct ppa_addr ppa,
-								u8 *blks)
-{
-	struct request_queue *q = nvmdev->q;
-	struct nvm_geo *geo = &nvmdev->geo;
-	struct nvme_ns *ns = q->queuedata;
-	struct nvme_ctrl *ctrl = ns->ctrl;
-	struct nvme_nvm_command c = {};
-	struct nvme_nvm_bb_tbl *bb_tbl;
-	int nr_blks = geo->num_chk * geo->num_pln;
-	int tblsz = sizeof(struct nvme_nvm_bb_tbl) + nr_blks;
-	int ret = 0;
-
-	c.get_bb.opcode = nvme_nvm_admin_get_bb_tbl;
-	c.get_bb.nsid = cpu_to_le32(ns->head->ns_id);
-	c.get_bb.spba = cpu_to_le64(ppa.ppa);
-
-	bb_tbl = kzalloc(tblsz, GFP_KERNEL);
-	if (!bb_tbl)
-		return -ENOMEM;
-
-	ret = nvme_submit_sync_cmd(ctrl->admin_q, (struct nvme_command *)&c,
-								bb_tbl, tblsz);
-	if (ret) {
-		dev_err(ctrl->device, "get bad block table failed (%d)\n", ret);
-		ret = -EIO;
-		goto out;
-	}
-
-	if (bb_tbl->tblid[0] != 'B' || bb_tbl->tblid[1] != 'B' ||
-		bb_tbl->tblid[2] != 'L' || bb_tbl->tblid[3] != 'T') {
-		dev_err(ctrl->device, "bbt format mismatch\n");
-		ret = -EINVAL;
-		goto out;
-	}
-
-	if (le16_to_cpu(bb_tbl->verid) != 1) {
-		ret = -EINVAL;
-		dev_err(ctrl->device, "bbt version not supported\n");
-		goto out;
-	}
-
-	if (le32_to_cpu(bb_tbl->tblks) != nr_blks) {
-		ret = -EINVAL;
-		dev_err(ctrl->device,
-				"bbt unsuspected blocks returned (%u!=%u)",
-				le32_to_cpu(bb_tbl->tblks), nr_blks);
-		goto out;
-	}
-
-	memcpy(blks, bb_tbl->blk, geo->num_chk * geo->num_pln);
-out:
-	kfree(bb_tbl);
-	return ret;
-}
-
-static int nvme_nvm_set_bb_tbl(struct nvm_dev *nvmdev, struct ppa_addr *ppas,
-							int nr_ppas, int type)
-{
-	struct nvme_ns *ns = nvmdev->q->queuedata;
-	struct nvme_nvm_command c = {};
-	int ret = 0;
-
-	c.set_bb.opcode = nvme_nvm_admin_set_bb_tbl;
-	c.set_bb.nsid = cpu_to_le32(ns->head->ns_id);
-	c.set_bb.spba = cpu_to_le64(ppas->ppa);
-	c.set_bb.nlb = cpu_to_le16(nr_ppas - 1);
-	c.set_bb.value = type;
-
-	ret = nvme_submit_sync_cmd(ns->ctrl->admin_q, (struct nvme_command *)&c,
-								NULL, 0);
-	if (ret)
-		dev_err(ns->ctrl->device, "set bad block table failed (%d)\n",
-									ret);
-	return ret;
-}
-
-/*
- * Expect the lba in device format
- */
-static int nvme_nvm_get_chk_meta(struct nvm_dev *ndev,
-				 sector_t slba, int nchks,
-				 struct nvm_chk_meta *meta)
-{
-	struct nvm_geo *geo = &ndev->geo;
-	struct nvme_ns *ns = ndev->q->queuedata;
-	struct nvme_ctrl *ctrl = ns->ctrl;
-	struct nvme_nvm_chk_meta *dev_meta, *dev_meta_off;
-	struct ppa_addr ppa;
-	size_t left = nchks * sizeof(struct nvme_nvm_chk_meta);
-	size_t log_pos, offset, len;
-	int i, max_len;
-	int ret = 0;
-
-	/*
-	 * limit requests to maximum 256K to avoid issuing arbitrary large
-	 * requests when the device does not specific a maximum transfer size.
-	 */
-	max_len = min_t(unsigned int, ctrl->max_hw_sectors << 9, 256 * 1024);
-
-	dev_meta = kmalloc(max_len, GFP_KERNEL);
-	if (!dev_meta)
-		return -ENOMEM;
-
-	/* Normalize lba address space to obtain log offset */
-	ppa.ppa = slba;
-	ppa = dev_to_generic_addr(ndev, ppa);
-
-	log_pos = ppa.m.chk;
-	log_pos += ppa.m.pu * geo->num_chk;
-	log_pos += ppa.m.grp * geo->num_lun * geo->num_chk;
-
-	offset = log_pos * sizeof(struct nvme_nvm_chk_meta);
-
-	while (left) {
-		len = min_t(unsigned int, left, max_len);
-
-		memset(dev_meta, 0, max_len);
-		dev_meta_off = dev_meta;
-
-		ret = nvme_get_log(ctrl, ns->head->ns_id,
-				NVME_NVM_LOG_REPORT_CHUNK, 0, NVME_CSI_NVM,
-				dev_meta, len, offset);
-		if (ret) {
-			dev_err(ctrl->device, "Get REPORT CHUNK log error\n");
-			break;
-		}
-
-		for (i = 0; i < len; i += sizeof(struct nvme_nvm_chk_meta)) {
-			meta->state = dev_meta_off->state;
-			meta->type = dev_meta_off->type;
-			meta->wi = dev_meta_off->wi;
-			meta->slba = le64_to_cpu(dev_meta_off->slba);
-			meta->cnlb = le64_to_cpu(dev_meta_off->cnlb);
-			meta->wp = le64_to_cpu(dev_meta_off->wp);
-
-			meta++;
-			dev_meta_off++;
-		}
-
-		offset += len;
-		left -= len;
-	}
-
-	kfree(dev_meta);
-
-	return ret;
-}
-
-static inline void nvme_nvm_rqtocmd(struct nvm_rq *rqd, struct nvme_ns *ns,
-				    struct nvme_nvm_command *c)
-{
-	c->ph_rw.opcode = rqd->opcode;
-	c->ph_rw.nsid = cpu_to_le32(ns->head->ns_id);
-	c->ph_rw.spba = cpu_to_le64(rqd->ppa_addr.ppa);
-	c->ph_rw.metadata = cpu_to_le64(rqd->dma_meta_list);
-	c->ph_rw.control = cpu_to_le16(rqd->flags);
-	c->ph_rw.length = cpu_to_le16(rqd->nr_ppas - 1);
-}
-
-static void nvme_nvm_end_io(struct request *rq, blk_status_t status)
-{
-	struct nvm_rq *rqd = rq->end_io_data;
-
-	rqd->ppa_status = le64_to_cpu(nvme_req(rq)->result.u64);
-	rqd->error = nvme_req(rq)->status;
-	nvm_end_io(rqd);
-
-	kfree(nvme_req(rq)->cmd);
-	blk_mq_free_request(rq);
-}
-
-static struct request *nvme_nvm_alloc_request(struct request_queue *q,
-					      struct nvm_rq *rqd,
-					      struct nvme_nvm_command *cmd)
-{
-	struct nvme_ns *ns = q->queuedata;
-	struct request *rq;
-
-	nvme_nvm_rqtocmd(rqd, ns, cmd);
-
-	rq = nvme_alloc_request(q, (struct nvme_command *)cmd, 0);
-	if (IS_ERR(rq))
-		return rq;
-
-	rq->cmd_flags &= ~REQ_FAILFAST_DRIVER;
-
-	if (rqd->bio)
-		blk_rq_append_bio(rq, rqd->bio);
-	else
-		rq->ioprio = IOPRIO_PRIO_VALUE(IOPRIO_CLASS_BE, IOPRIO_NORM);
-
-	return rq;
-}
-
-static int nvme_nvm_submit_io(struct nvm_dev *dev, struct nvm_rq *rqd,
-			      void *buf)
-{
-	struct nvm_geo *geo = &dev->geo;
-	struct request_queue *q = dev->q;
-	struct nvme_nvm_command *cmd;
-	struct request *rq;
-	int ret;
-
-	cmd = kzalloc(sizeof(struct nvme_nvm_command), GFP_KERNEL);
-	if (!cmd)
-		return -ENOMEM;
-
-	rq = nvme_nvm_alloc_request(q, rqd, cmd);
-	if (IS_ERR(rq)) {
-		ret = PTR_ERR(rq);
-		goto err_free_cmd;
-	}
-
-	if (buf) {
-		ret = blk_rq_map_kern(q, rq, buf, geo->csecs * rqd->nr_ppas,
-				GFP_KERNEL);
-		if (ret)
-			goto err_free_cmd;
-	}
-
-	rq->end_io_data = rqd;
-
-	blk_execute_rq_nowait(NULL, rq, 0, nvme_nvm_end_io);
-
-	return 0;
-
-err_free_cmd:
-	kfree(cmd);
-	return ret;
-}
-
-static void *nvme_nvm_create_dma_pool(struct nvm_dev *nvmdev, char *name,
-					int size)
-{
-	struct nvme_ns *ns = nvmdev->q->queuedata;
-
-	return dma_pool_create(name, ns->ctrl->dev, size, PAGE_SIZE, 0);
-}
-
-static void nvme_nvm_destroy_dma_pool(void *pool)
-{
-	struct dma_pool *dma_pool = pool;
-
-	dma_pool_destroy(dma_pool);
-}
-
-static void *nvme_nvm_dev_dma_alloc(struct nvm_dev *dev, void *pool,
-				    gfp_t mem_flags, dma_addr_t *dma_handler)
-{
-	return dma_pool_alloc(pool, mem_flags, dma_handler);
-}
-
-static void nvme_nvm_dev_dma_free(void *pool, void *addr,
-							dma_addr_t dma_handler)
-{
-	dma_pool_free(pool, addr, dma_handler);
-}
-
-static struct nvm_dev_ops nvme_nvm_dev_ops = {
-	.identity		= nvme_nvm_identity,
-
-	.get_bb_tbl		= nvme_nvm_get_bb_tbl,
-	.set_bb_tbl		= nvme_nvm_set_bb_tbl,
-
-	.get_chk_meta		= nvme_nvm_get_chk_meta,
-
-	.submit_io		= nvme_nvm_submit_io,
-
-	.create_dma_pool	= nvme_nvm_create_dma_pool,
-	.destroy_dma_pool	= nvme_nvm_destroy_dma_pool,
-	.dev_dma_alloc		= nvme_nvm_dev_dma_alloc,
-	.dev_dma_free		= nvme_nvm_dev_dma_free,
-};
-
-static int nvme_nvm_submit_user_cmd(struct request_queue *q,
-				struct nvme_ns *ns,
-				struct nvme_nvm_command *vcmd,
-				void __user *ubuf, unsigned int bufflen,
-				void __user *meta_buf, unsigned int meta_len,
-				void __user *ppa_buf, unsigned int ppa_len,
-				u32 *result, u64 *status, unsigned int timeout)
-{
-	bool write = nvme_is_write((struct nvme_command *)vcmd);
-	struct nvm_dev *dev = ns->ndev;
-	struct request *rq;
-	struct bio *bio = NULL;
-	__le64 *ppa_list = NULL;
-	dma_addr_t ppa_dma;
-	__le64 *metadata = NULL;
-	dma_addr_t metadata_dma;
-	DECLARE_COMPLETION_ONSTACK(wait);
-	int ret = 0;
-
-	rq = nvme_alloc_request(q, (struct nvme_command *)vcmd, 0);
-	if (IS_ERR(rq)) {
-		ret = -ENOMEM;
-		goto err_cmd;
-	}
-
-	if (timeout)
-		rq->timeout = timeout;
-
-	if (ppa_buf && ppa_len) {
-		ppa_list = dma_pool_alloc(dev->dma_pool, GFP_KERNEL, &ppa_dma);
-		if (!ppa_list) {
-			ret = -ENOMEM;
-			goto err_rq;
-		}
-		if (copy_from_user(ppa_list, (void __user *)ppa_buf,
-						sizeof(u64) * (ppa_len + 1))) {
-			ret = -EFAULT;
-			goto err_ppa;
-		}
-		vcmd->ph_rw.spba = cpu_to_le64(ppa_dma);
-	} else {
-		vcmd->ph_rw.spba = cpu_to_le64((uintptr_t)ppa_buf);
-	}
-
-	if (ubuf && bufflen) {
-		ret = blk_rq_map_user(q, rq, NULL, ubuf, bufflen, GFP_KERNEL);
-		if (ret)
-			goto err_ppa;
-		bio = rq->bio;
-
-		if (meta_buf && meta_len) {
-			metadata = dma_pool_alloc(dev->dma_pool, GFP_KERNEL,
-								&metadata_dma);
-			if (!metadata) {
-				ret = -ENOMEM;
-				goto err_map;
-			}
-
-			if (write) {
-				if (copy_from_user(metadata,
-						(void __user *)meta_buf,
-						meta_len)) {
-					ret = -EFAULT;
-					goto err_meta;
-				}
-			}
-			vcmd->ph_rw.metadata = cpu_to_le64(metadata_dma);
-		}
-
-		bio_set_dev(bio, ns->disk->part0);
-	}
-
-	blk_execute_rq(NULL, rq, 0);
-
-	if (nvme_req(rq)->flags & NVME_REQ_CANCELLED)
-		ret = -EINTR;
-	else if (nvme_req(rq)->status & 0x7ff)
-		ret = -EIO;
-	if (result)
-		*result = nvme_req(rq)->status & 0x7ff;
-	if (status)
-		*status = le64_to_cpu(nvme_req(rq)->result.u64);
-
-	if (metadata && !ret && !write) {
-		if (copy_to_user(meta_buf, (void *)metadata, meta_len))
-			ret = -EFAULT;
-	}
-err_meta:
-	if (meta_buf && meta_len)
-		dma_pool_free(dev->dma_pool, metadata, metadata_dma);
-err_map:
-	if (bio)
-		blk_rq_unmap_user(bio);
-err_ppa:
-	if (ppa_buf && ppa_len)
-		dma_pool_free(dev->dma_pool, ppa_list, ppa_dma);
-err_rq:
-	blk_mq_free_request(rq);
-err_cmd:
-	return ret;
-}
-
-static int nvme_nvm_submit_vio(struct nvme_ns *ns,
-					struct nvm_user_vio __user *uvio)
-{
-	struct nvm_user_vio vio;
-	struct nvme_nvm_command c;
-	unsigned int length;
-	int ret;
-
-	if (copy_from_user(&vio, uvio, sizeof(vio)))
-		return -EFAULT;
-	if (vio.flags)
-		return -EINVAL;
-
-	memset(&c, 0, sizeof(c));
-	c.ph_rw.opcode = vio.opcode;
-	c.ph_rw.nsid = cpu_to_le32(ns->head->ns_id);
-	c.ph_rw.control = cpu_to_le16(vio.control);
-	c.ph_rw.length = cpu_to_le16(vio.nppas);
-
-	length = (vio.nppas + 1) << ns->lba_shift;
-
-	ret = nvme_nvm_submit_user_cmd(ns->queue, ns, &c,
-			(void __user *)(uintptr_t)vio.addr, length,
-			(void __user *)(uintptr_t)vio.metadata,
-							vio.metadata_len,
-			(void __user *)(uintptr_t)vio.ppa_list, vio.nppas,
-			&vio.result, &vio.status, 0);
-
-	if (ret && copy_to_user(uvio, &vio, sizeof(vio)))
-		return -EFAULT;
-
-	return ret;
-}
-
-static int nvme_nvm_user_vcmd(struct nvme_ns *ns, int admin,
-					struct nvm_passthru_vio __user *uvcmd)
-{
-	struct nvm_passthru_vio vcmd;
-	struct nvme_nvm_command c;
-	struct request_queue *q;
-	unsigned int timeout = 0;
-	int ret;
-
-	if (copy_from_user(&vcmd, uvcmd, sizeof(vcmd)))
-		return -EFAULT;
-	if ((vcmd.opcode != 0xF2) && (!capable(CAP_SYS_ADMIN)))
-		return -EACCES;
-	if (vcmd.flags)
-		return -EINVAL;
-
-	memset(&c, 0, sizeof(c));
-	c.common.opcode = vcmd.opcode;
-	c.common.nsid = cpu_to_le32(ns->head->ns_id);
-	c.common.cdw2[0] = cpu_to_le32(vcmd.cdw2);
-	c.common.cdw2[1] = cpu_to_le32(vcmd.cdw3);
-	/* cdw11-12 */
-	c.ph_rw.length = cpu_to_le16(vcmd.nppas);
-	c.ph_rw.control  = cpu_to_le16(vcmd.control);
-	c.common.cdw13 = cpu_to_le32(vcmd.cdw13);
-	c.common.cdw14 = cpu_to_le32(vcmd.cdw14);
-	c.common.cdw15 = cpu_to_le32(vcmd.cdw15);
-
-	if (vcmd.timeout_ms)
-		timeout = msecs_to_jiffies(vcmd.timeout_ms);
-
-	q = admin ? ns->ctrl->admin_q : ns->queue;
-
-	ret = nvme_nvm_submit_user_cmd(q, ns,
-			(struct nvme_nvm_command *)&c,
-			(void __user *)(uintptr_t)vcmd.addr, vcmd.data_len,
-			(void __user *)(uintptr_t)vcmd.metadata,
-							vcmd.metadata_len,
-			(void __user *)(uintptr_t)vcmd.ppa_list, vcmd.nppas,
-			&vcmd.result, &vcmd.status, timeout);
-
-	if (ret && copy_to_user(uvcmd, &vcmd, sizeof(vcmd)))
-		return -EFAULT;
-
-	return ret;
-}
-
-int nvme_nvm_ioctl(struct nvme_ns *ns, unsigned int cmd, void __user *argp)
-{
-	switch (cmd) {
-	case NVME_NVM_IOCTL_ADMIN_VIO:
-		return nvme_nvm_user_vcmd(ns, 1, argp);
-	case NVME_NVM_IOCTL_IO_VIO:
-		return nvme_nvm_user_vcmd(ns, 0, argp);
-	case NVME_NVM_IOCTL_SUBMIT_VIO:
-		return nvme_nvm_submit_vio(ns, argp);
-	default:
-		return -ENOTTY;
-	}
-}
-
-int nvme_nvm_register(struct nvme_ns *ns, char *disk_name, int node)
-{
-	struct request_queue *q = ns->queue;
-	struct nvm_dev *dev;
-	struct nvm_geo *geo;
-
-	_nvme_nvm_check_size();
-
-	dev = nvm_alloc_dev(node);
-	if (!dev)
-		return -ENOMEM;
-
-	/* Note that csecs and sos will be overridden if it is a 1.2 drive. */
-	geo = &dev->geo;
-	geo->csecs = 1 << ns->lba_shift;
-	geo->sos = ns->ms;
-	if (ns->features & NVME_NS_EXT_LBAS)
-		geo->ext = true;
-	else
-		geo->ext = false;
-	geo->mdts = ns->ctrl->max_hw_sectors;
-
-	dev->q = q;
-	memcpy(dev->name, disk_name, DISK_NAME_LEN);
-	dev->ops = &nvme_nvm_dev_ops;
-	dev->private_data = ns;
-	ns->ndev = dev;
-
-	return nvm_register(dev);
-}
-
-void nvme_nvm_unregister(struct nvme_ns *ns)
-{
-	nvm_unregister(ns->ndev);
-}
-
-static ssize_t nvm_dev_attr_show(struct device *dev,
-		struct device_attribute *dattr, char *page)
-{
-	struct nvme_ns *ns = nvme_get_ns_from_dev(dev);
-	struct nvm_dev *ndev = ns->ndev;
-	struct nvm_geo *geo = &ndev->geo;
-	struct attribute *attr;
-
-	if (!ndev)
-		return 0;
-
-	attr = &dattr->attr;
-
-	if (strcmp(attr->name, "version") == 0) {
-		if (geo->major_ver_id == 1)
-			return scnprintf(page, PAGE_SIZE, "%u\n",
-						geo->major_ver_id);
-		else
-			return scnprintf(page, PAGE_SIZE, "%u.%u\n",
-						geo->major_ver_id,
-						geo->minor_ver_id);
-	} else if (strcmp(attr->name, "capabilities") == 0) {
-		return scnprintf(page, PAGE_SIZE, "%u\n", geo->cap);
-	} else if (strcmp(attr->name, "read_typ") == 0) {
-		return scnprintf(page, PAGE_SIZE, "%u\n", geo->trdt);
-	} else if (strcmp(attr->name, "read_max") == 0) {
-		return scnprintf(page, PAGE_SIZE, "%u\n", geo->trdm);
-	} else {
-		return scnprintf(page,
-				 PAGE_SIZE,
-				 "Unhandled attr(%s) in `%s`\n",
-				 attr->name, __func__);
-	}
-}
-
-static ssize_t nvm_dev_attr_show_ppaf(struct nvm_addrf_12 *ppaf, char *page)
-{
-	return scnprintf(page, PAGE_SIZE,
-		"0x%02x%02x%02x%02x%02x%02x%02x%02x%02x%02x%02x%02x\n",
-				ppaf->ch_offset, ppaf->ch_len,
-				ppaf->lun_offset, ppaf->lun_len,
-				ppaf->pln_offset, ppaf->pln_len,
-				ppaf->blk_offset, ppaf->blk_len,
-				ppaf->pg_offset, ppaf->pg_len,
-				ppaf->sec_offset, ppaf->sec_len);
-}
-
-static ssize_t nvm_dev_attr_show_12(struct device *dev,
-		struct device_attribute *dattr, char *page)
-{
-	struct nvme_ns *ns = nvme_get_ns_from_dev(dev);
-	struct nvm_dev *ndev = ns->ndev;
-	struct nvm_geo *geo = &ndev->geo;
-	struct attribute *attr;
-
-	if (!ndev)
-		return 0;
-
-	attr = &dattr->attr;
-
-	if (strcmp(attr->name, "vendor_opcode") == 0) {
-		return scnprintf(page, PAGE_SIZE, "%u\n", geo->vmnt);
-	} else if (strcmp(attr->name, "device_mode") == 0) {
-		return scnprintf(page, PAGE_SIZE, "%u\n", geo->dom);
-	/* kept for compatibility */
-	} else if (strcmp(attr->name, "media_manager") == 0) {
-		return scnprintf(page, PAGE_SIZE, "%s\n", "gennvm");
-	} else if (strcmp(attr->name, "ppa_format") == 0) {
-		return nvm_dev_attr_show_ppaf((void *)&geo->addrf, page);
-	} else if (strcmp(attr->name, "media_type") == 0) {	/* u8 */
-		return scnprintf(page, PAGE_SIZE, "%u\n", geo->mtype);
-	} else if (strcmp(attr->name, "flash_media_type") == 0) {
-		return scnprintf(page, PAGE_SIZE, "%u\n", geo->fmtype);
-	} else if (strcmp(attr->name, "num_channels") == 0) {
-		return scnprintf(page, PAGE_SIZE, "%u\n", geo->num_ch);
-	} else if (strcmp(attr->name, "num_luns") == 0) {
-		return scnprintf(page, PAGE_SIZE, "%u\n", geo->num_lun);
-	} else if (strcmp(attr->name, "num_planes") == 0) {
-		return scnprintf(page, PAGE_SIZE, "%u\n", geo->num_pln);
-	} else if (strcmp(attr->name, "num_blocks") == 0) {	/* u16 */
-		return scnprintf(page, PAGE_SIZE, "%u\n", geo->num_chk);
-	} else if (strcmp(attr->name, "num_pages") == 0) {
-		return scnprintf(page, PAGE_SIZE, "%u\n", geo->num_pg);
-	} else if (strcmp(attr->name, "page_size") == 0) {
-		return scnprintf(page, PAGE_SIZE, "%u\n", geo->fpg_sz);
-	} else if (strcmp(attr->name, "hw_sector_size") == 0) {
-		return scnprintf(page, PAGE_SIZE, "%u\n", geo->csecs);
-	} else if (strcmp(attr->name, "oob_sector_size") == 0) {/* u32 */
-		return scnprintf(page, PAGE_SIZE, "%u\n", geo->sos);
-	} else if (strcmp(attr->name, "prog_typ") == 0) {
-		return scnprintf(page, PAGE_SIZE, "%u\n", geo->tprt);
-	} else if (strcmp(attr->name, "prog_max") == 0) {
-		return scnprintf(page, PAGE_SIZE, "%u\n", geo->tprm);
-	} else if (strcmp(attr->name, "erase_typ") == 0) {
-		return scnprintf(page, PAGE_SIZE, "%u\n", geo->tbet);
-	} else if (strcmp(attr->name, "erase_max") == 0) {
-		return scnprintf(page, PAGE_SIZE, "%u\n", geo->tbem);
-	} else if (strcmp(attr->name, "multiplane_modes") == 0) {
-		return scnprintf(page, PAGE_SIZE, "0x%08x\n", geo->mpos);
-	} else if (strcmp(attr->name, "media_capabilities") == 0) {
-		return scnprintf(page, PAGE_SIZE, "0x%08x\n", geo->mccap);
-	} else if (strcmp(attr->name, "max_phys_secs") == 0) {
-		return scnprintf(page, PAGE_SIZE, "%u\n", NVM_MAX_VLBA);
-	} else {
-		return scnprintf(page, PAGE_SIZE,
-			"Unhandled attr(%s) in `%s`\n",
-			attr->name, __func__);
-	}
-}
-
-static ssize_t nvm_dev_attr_show_20(struct device *dev,
-		struct device_attribute *dattr, char *page)
-{
-	struct nvme_ns *ns = nvme_get_ns_from_dev(dev);
-	struct nvm_dev *ndev = ns->ndev;
-	struct nvm_geo *geo = &ndev->geo;
-	struct attribute *attr;
-
-	if (!ndev)
-		return 0;
-
-	attr = &dattr->attr;
-
-	if (strcmp(attr->name, "groups") == 0) {
-		return scnprintf(page, PAGE_SIZE, "%u\n", geo->num_ch);
-	} else if (strcmp(attr->name, "punits") == 0) {
-		return scnprintf(page, PAGE_SIZE, "%u\n", geo->num_lun);
-	} else if (strcmp(attr->name, "chunks") == 0) {
-		return scnprintf(page, PAGE_SIZE, "%u\n", geo->num_chk);
-	} else if (strcmp(attr->name, "clba") == 0) {
-		return scnprintf(page, PAGE_SIZE, "%u\n", geo->clba);
-	} else if (strcmp(attr->name, "ws_min") == 0) {
-		return scnprintf(page, PAGE_SIZE, "%u\n", geo->ws_min);
-	} else if (strcmp(attr->name, "ws_opt") == 0) {
-		return scnprintf(page, PAGE_SIZE, "%u\n", geo->ws_opt);
-	} else if (strcmp(attr->name, "maxoc") == 0) {
-		return scnprintf(page, PAGE_SIZE, "%u\n", geo->maxoc);
-	} else if (strcmp(attr->name, "maxocpu") == 0) {
-		return scnprintf(page, PAGE_SIZE, "%u\n", geo->maxocpu);
-	} else if (strcmp(attr->name, "mw_cunits") == 0) {
-		return scnprintf(page, PAGE_SIZE, "%u\n", geo->mw_cunits);
-	} else if (strcmp(attr->name, "write_typ") == 0) {
-		return scnprintf(page, PAGE_SIZE, "%u\n", geo->tprt);
-	} else if (strcmp(attr->name, "write_max") == 0) {
-		return scnprintf(page, PAGE_SIZE, "%u\n", geo->tprm);
-	} else if (strcmp(attr->name, "reset_typ") == 0) {
-		return scnprintf(page, PAGE_SIZE, "%u\n", geo->tbet);
-	} else if (strcmp(attr->name, "reset_max") == 0) {
-		return scnprintf(page, PAGE_SIZE, "%u\n", geo->tbem);
-	} else {
-		return scnprintf(page, PAGE_SIZE,
-			"Unhandled attr(%s) in `%s`\n",
-			attr->name, __func__);
-	}
-}
-
-#define NVM_DEV_ATTR_RO(_name)					\
-	DEVICE_ATTR(_name, S_IRUGO, nvm_dev_attr_show, NULL)
-#define NVM_DEV_ATTR_12_RO(_name)					\
-	DEVICE_ATTR(_name, S_IRUGO, nvm_dev_attr_show_12, NULL)
-#define NVM_DEV_ATTR_20_RO(_name)					\
-	DEVICE_ATTR(_name, S_IRUGO, nvm_dev_attr_show_20, NULL)
-
-/* general attributes */
-static NVM_DEV_ATTR_RO(version);
-static NVM_DEV_ATTR_RO(capabilities);
-
-static NVM_DEV_ATTR_RO(read_typ);
-static NVM_DEV_ATTR_RO(read_max);
-
-/* 1.2 values */
-static NVM_DEV_ATTR_12_RO(vendor_opcode);
-static NVM_DEV_ATTR_12_RO(device_mode);
-static NVM_DEV_ATTR_12_RO(ppa_format);
-static NVM_DEV_ATTR_12_RO(media_manager);
-static NVM_DEV_ATTR_12_RO(media_type);
-static NVM_DEV_ATTR_12_RO(flash_media_type);
-static NVM_DEV_ATTR_12_RO(num_channels);
-static NVM_DEV_ATTR_12_RO(num_luns);
-static NVM_DEV_ATTR_12_RO(num_planes);
-static NVM_DEV_ATTR_12_RO(num_blocks);
-static NVM_DEV_ATTR_12_RO(num_pages);
-static NVM_DEV_ATTR_12_RO(page_size);
-static NVM_DEV_ATTR_12_RO(hw_sector_size);
-static NVM_DEV_ATTR_12_RO(oob_sector_size);
-static NVM_DEV_ATTR_12_RO(prog_typ);
-static NVM_DEV_ATTR_12_RO(prog_max);
-static NVM_DEV_ATTR_12_RO(erase_typ);
-static NVM_DEV_ATTR_12_RO(erase_max);
-static NVM_DEV_ATTR_12_RO(multiplane_modes);
-static NVM_DEV_ATTR_12_RO(media_capabilities);
-static NVM_DEV_ATTR_12_RO(max_phys_secs);
-
-/* 2.0 values */
-static NVM_DEV_ATTR_20_RO(groups);
-static NVM_DEV_ATTR_20_RO(punits);
-static NVM_DEV_ATTR_20_RO(chunks);
-static NVM_DEV_ATTR_20_RO(clba);
-static NVM_DEV_ATTR_20_RO(ws_min);
-static NVM_DEV_ATTR_20_RO(ws_opt);
-static NVM_DEV_ATTR_20_RO(maxoc);
-static NVM_DEV_ATTR_20_RO(maxocpu);
-static NVM_DEV_ATTR_20_RO(mw_cunits);
-static NVM_DEV_ATTR_20_RO(write_typ);
-static NVM_DEV_ATTR_20_RO(write_max);
-static NVM_DEV_ATTR_20_RO(reset_typ);
-static NVM_DEV_ATTR_20_RO(reset_max);
-
-static struct attribute *nvm_dev_attrs[] = {
-	/* version agnostic attrs */
-	&dev_attr_version.attr,
-	&dev_attr_capabilities.attr,
-	&dev_attr_read_typ.attr,
-	&dev_attr_read_max.attr,
-
-	/* 1.2 attrs */
-	&dev_attr_vendor_opcode.attr,
-	&dev_attr_device_mode.attr,
-	&dev_attr_media_manager.attr,
-	&dev_attr_ppa_format.attr,
-	&dev_attr_media_type.attr,
-	&dev_attr_flash_media_type.attr,
-	&dev_attr_num_channels.attr,
-	&dev_attr_num_luns.attr,
-	&dev_attr_num_planes.attr,
-	&dev_attr_num_blocks.attr,
-	&dev_attr_num_pages.attr,
-	&dev_attr_page_size.attr,
-	&dev_attr_hw_sector_size.attr,
-	&dev_attr_oob_sector_size.attr,
-	&dev_attr_prog_typ.attr,
-	&dev_attr_prog_max.attr,
-	&dev_attr_erase_typ.attr,
-	&dev_attr_erase_max.attr,
-	&dev_attr_multiplane_modes.attr,
-	&dev_attr_media_capabilities.attr,
-	&dev_attr_max_phys_secs.attr,
-
-	/* 2.0 attrs */
-	&dev_attr_groups.attr,
-	&dev_attr_punits.attr,
-	&dev_attr_chunks.attr,
-	&dev_attr_clba.attr,
-	&dev_attr_ws_min.attr,
-	&dev_attr_ws_opt.attr,
-	&dev_attr_maxoc.attr,
-	&dev_attr_maxocpu.attr,
-	&dev_attr_mw_cunits.attr,
-
-	&dev_attr_write_typ.attr,
-	&dev_attr_write_max.attr,
-	&dev_attr_reset_typ.attr,
-	&dev_attr_reset_max.attr,
-
-	NULL,
-};
-
-static umode_t nvm_dev_attrs_visible(struct kobject *kobj,
-				     struct attribute *attr, int index)
-{
-	struct device *dev = kobj_to_dev(kobj);
-	struct gendisk *disk = dev_to_disk(dev);
-	struct nvme_ns *ns = disk->private_data;
-	struct nvm_dev *ndev = ns->ndev;
-	struct device_attribute *dev_attr =
-		container_of(attr, typeof(*dev_attr), attr);
-
-	if (!ndev)
-		return 0;
-
-	if (dev_attr->show == nvm_dev_attr_show)
-		return attr->mode;
-
-	switch (ndev->geo.major_ver_id) {
-	case 1:
-		if (dev_attr->show == nvm_dev_attr_show_12)
-			return attr->mode;
-		break;
-	case 2:
-		if (dev_attr->show == nvm_dev_attr_show_20)
-			return attr->mode;
-		break;
-	}
-
-	return 0;
-}
-
-const struct attribute_group nvme_nvm_attr_group = {
-	.name		= "lightnvm",
-	.attrs		= nvm_dev_attrs,
-	.is_visible	= nvm_dev_attrs_visible,
-};
diff --git a/drivers/nvme/host/nvme.h b/drivers/nvme/host/nvme.h
index 5cd1fa3b8464..a2e1f298b217 100644
--- a/drivers/nvme/host/nvme.h
+++ b/drivers/nvme/host/nvme.h
@@ -11,7 +11,6 @@
 #include <linux/pci.h>
 #include <linux/kref.h>
 #include <linux/blk-mq.h>
-#include <linux/lightnvm.h>
 #include <linux/sed-opal.h>
 #include <linux/fault-inject.h>
 #include <linux/rcupdate.h>
@@ -48,11 +47,6 @@ extern struct workqueue_struct *nvme_wq;
 extern struct workqueue_struct *nvme_reset_wq;
 extern struct workqueue_struct *nvme_delete_wq;
 
-enum {
-	NVME_NS_LBA		= 0,
-	NVME_NS_LIGHTNVM	= 1,
-};
-
 /*
  * List of workarounds for devices that required behavior not specified in
  * the standard.
@@ -93,11 +87,6 @@ enum nvme_quirks {
 	NVME_QUIRK_NO_DEEPEST_PS		= (1 << 5),
 
 	/*
-	 * Supports the LighNVM command set if indicated in vs[1].
-	 */
-	NVME_QUIRK_LIGHTNVM			= (1 << 6),
-
-	/*
 	 * Set MEDIUM priority on SQ creation
 	 */
 	NVME_QUIRK_MEDIUM_PRIO_SQ		= (1 << 7),
@@ -158,6 +147,7 @@ enum nvme_quirks {
 struct nvme_request {
 	struct nvme_command	*cmd;
 	union nvme_result	result;
+	u8			genctr;
 	u8			retries;
 	u8			flags;
 	u16			status;
@@ -449,7 +439,6 @@ struct nvme_ns {
 	u32 ana_grpid;
 #endif
 	struct list_head siblings;
-	struct nvm_dev *ndev;
 	struct kref kref;
 	struct nvme_ns_head *head;
 
@@ -497,6 +486,49 @@ struct nvme_ctrl_ops {
 	int (*get_address)(struct nvme_ctrl *ctrl, char *buf, int size);
 };
 
+/*
+ * nvme command_id is constructed as such:
+ * | xxxx | xxxxxxxxxxxx |
+ *   gen    request tag
+ */
+#define nvme_genctr_mask(gen)			(gen & 0xf)
+#define nvme_cid_install_genctr(gen)		(nvme_genctr_mask(gen) << 12)
+#define nvme_genctr_from_cid(cid)		((cid & 0xf000) >> 12)
+#define nvme_tag_from_cid(cid)			(cid & 0xfff)
+
+static inline u16 nvme_cid(struct request *rq)
+{
+	return nvme_cid_install_genctr(nvme_req(rq)->genctr) | rq->tag;
+}
+
+static inline struct request *nvme_find_rq(struct blk_mq_tags *tags,
+		u16 command_id)
+{
+	u8 genctr = nvme_genctr_from_cid(command_id);
+	u16 tag = nvme_tag_from_cid(command_id);
+	struct request *rq;
+
+	rq = blk_mq_tag_to_rq(tags, tag);
+	if (unlikely(!rq)) {
+		pr_err("could not locate request for tag %#x\n",
+			tag);
+		return NULL;
+	}
+	if (unlikely(nvme_genctr_mask(nvme_req(rq)->genctr) != genctr)) {
+		dev_err(nvme_req(rq)->ctrl->device,
+			"request %#x genctr mismatch (got %#x expected %#x)\n",
+			tag, genctr, nvme_genctr_mask(nvme_req(rq)->genctr));
+		return NULL;
+	}
+	return rq;
+}
+
+static inline struct request *nvme_cid_to_rq(struct blk_mq_tags *tags,
+                u16 command_id)
+{
+	return blk_mq_tag_to_rq(tags, nvme_tag_from_cid(command_id));
+}
+
 #ifdef CONFIG_FAULT_INJECTION_DEBUG_FS
 void nvme_fault_inject_init(struct nvme_fault_inject *fault_inj,
 			    const char *dev_name);
@@ -594,7 +626,8 @@ static inline void nvme_put_ctrl(struct nvme_ctrl *ctrl)
 
 static inline bool nvme_is_aen_req(u16 qid, __u16 command_id)
 {
-	return !qid && command_id >= NVME_AQ_BLK_MQ_DEPTH;
+	return !qid &&
+		nvme_tag_from_cid(command_id) >= NVME_AQ_BLK_MQ_DEPTH;
 }
 
 void nvme_complete_rq(struct request *req);
@@ -823,26 +856,6 @@ static inline int nvme_update_zone_info(struct nvme_ns *ns, unsigned lbaf)
 }
 #endif
 
-#ifdef CONFIG_NVM
-int nvme_nvm_register(struct nvme_ns *ns, char *disk_name, int node);
-void nvme_nvm_unregister(struct nvme_ns *ns);
-extern const struct attribute_group nvme_nvm_attr_group;
-int nvme_nvm_ioctl(struct nvme_ns *ns, unsigned int cmd, void __user *argp);
-#else
-static inline int nvme_nvm_register(struct nvme_ns *ns, char *disk_name,
-				    int node)
-{
-	return 0;
-}
-
-static inline void nvme_nvm_unregister(struct nvme_ns *ns) {};
-static inline int nvme_nvm_ioctl(struct nvme_ns *ns, unsigned int cmd,
-		void __user *argp)
-{
-	return -ENOTTY;
-}
-#endif /* CONFIG_NVM */
-
 static inline struct nvme_ns *nvme_get_ns_from_dev(struct device *dev)
 {
 	return dev_to_disk(dev)->private_data;
diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c
index 51852085239e..b82492cd7503 100644
--- a/drivers/nvme/host/pci.c
+++ b/drivers/nvme/host/pci.c
@@ -60,6 +60,8 @@ MODULE_PARM_DESC(sgl_threshold,
 		"Use SGLs when average request segment size is larger or equal to "
 		"this size. Use 0 to disable SGLs.");
 
+#define NVME_PCI_MIN_QUEUE_SIZE 2
+#define NVME_PCI_MAX_QUEUE_SIZE 4095
 static int io_queue_depth_set(const char *val, const struct kernel_param *kp);
 static const struct kernel_param_ops io_queue_depth_ops = {
 	.set = io_queue_depth_set,
@@ -68,7 +70,7 @@ static const struct kernel_param_ops io_queue_depth_ops = {
 
 static unsigned int io_queue_depth = 1024;
 module_param_cb(io_queue_depth, &io_queue_depth_ops, &io_queue_depth, 0644);
-MODULE_PARM_DESC(io_queue_depth, "set io queue depth, should >= 2");
+MODULE_PARM_DESC(io_queue_depth, "set io queue depth, should >= 2 and < 4096");
 
 static int io_queue_count_set(const char *val, const struct kernel_param *kp)
 {
@@ -135,6 +137,7 @@ struct nvme_dev {
 	u32 cmbloc;
 	struct nvme_ctrl ctrl;
 	u32 last_ps;
+	bool hmb;
 
 	mempool_t *iod_mempool;
 
@@ -153,18 +156,14 @@ struct nvme_dev {
 	unsigned int nr_allocated_queues;
 	unsigned int nr_write_queues;
 	unsigned int nr_poll_queues;
+
+	bool attrs_added;
 };
 
 static int io_queue_depth_set(const char *val, const struct kernel_param *kp)
 {
-	int ret;
-	u32 n;
-
-	ret = kstrtou32(val, 10, &n);
-	if (ret != 0 || n < 2)
-		return -EINVAL;
-
-	return param_set_uint(val, kp);
+	return param_set_uint_minmax(val, kp, NVME_PCI_MIN_QUEUE_SIZE,
+			NVME_PCI_MAX_QUEUE_SIZE);
 }
 
 static inline unsigned int sq_idx(unsigned int qid, u32 stride)
@@ -1014,7 +1013,7 @@ static inline void nvme_handle_cqe(struct nvme_queue *nvmeq, u16 idx)
 		return;
 	}
 
-	req = blk_mq_tag_to_rq(nvme_queue_tagset(nvmeq), command_id);
+	req = nvme_find_rq(nvme_queue_tagset(nvmeq), command_id);
 	if (unlikely(!req)) {
 		dev_warn(nvmeq->dev->ctrl.device,
 			"invalid id %d completed on queue %d\n",
@@ -1808,17 +1807,6 @@ static int nvme_create_io_queues(struct nvme_dev *dev)
 	return ret >= 0 ? 0 : ret;
 }
 
-static ssize_t nvme_cmb_show(struct device *dev,
-			     struct device_attribute *attr,
-			     char *buf)
-{
-	struct nvme_dev *ndev = to_nvme_dev(dev_get_drvdata(dev));
-
-	return scnprintf(buf, PAGE_SIZE, "cmbloc : x%08x\ncmbsz  : x%08x\n",
-		       ndev->cmbloc, ndev->cmbsz);
-}
-static DEVICE_ATTR(cmb, S_IRUGO, nvme_cmb_show, NULL);
-
 static u64 nvme_cmb_size_unit(struct nvme_dev *dev)
 {
 	u8 szu = (dev->cmbsz >> NVME_CMBSZ_SZU_SHIFT) & NVME_CMBSZ_SZU_MASK;
@@ -1887,20 +1875,6 @@ static void nvme_map_cmb(struct nvme_dev *dev)
 	if ((dev->cmbsz & (NVME_CMBSZ_WDS | NVME_CMBSZ_RDS)) ==
 			(NVME_CMBSZ_WDS | NVME_CMBSZ_RDS))
 		pci_p2pmem_publish(pdev, true);
-
-	if (sysfs_add_file_to_group(&dev->ctrl.device->kobj,
-				    &dev_attr_cmb.attr, NULL))
-		dev_warn(dev->ctrl.device,
-			 "failed to add sysfs attribute for CMB\n");
-}
-
-static inline void nvme_release_cmb(struct nvme_dev *dev)
-{
-	if (dev->cmb_size) {
-		sysfs_remove_file_from_group(&dev->ctrl.device->kobj,
-					     &dev_attr_cmb.attr, NULL);
-		dev->cmb_size = 0;
-	}
 }
 
 static int nvme_set_host_mem(struct nvme_dev *dev, u32 bits)
@@ -1923,7 +1897,9 @@ static int nvme_set_host_mem(struct nvme_dev *dev, u32 bits)
 		dev_warn(dev->ctrl.device,
 			 "failed to set host mem (err %d, flags %#x).\n",
 			 ret, bits);
-	}
+	} else
+		dev->hmb = bits & NVME_HOST_MEM_ENABLE;
+
 	return ret;
 }
 
@@ -2080,6 +2056,102 @@ static int nvme_setup_host_mem(struct nvme_dev *dev)
 	return ret;
 }
 
+static ssize_t cmb_show(struct device *dev, struct device_attribute *attr,
+		char *buf)
+{
+	struct nvme_dev *ndev = to_nvme_dev(dev_get_drvdata(dev));
+
+	return sysfs_emit(buf, "cmbloc : x%08x\ncmbsz  : x%08x\n",
+		       ndev->cmbloc, ndev->cmbsz);
+}
+static DEVICE_ATTR_RO(cmb);
+
+static ssize_t cmbloc_show(struct device *dev, struct device_attribute *attr,
+		char *buf)
+{
+	struct nvme_dev *ndev = to_nvme_dev(dev_get_drvdata(dev));
+
+	return sysfs_emit(buf, "%u\n", ndev->cmbloc);
+}
+static DEVICE_ATTR_RO(cmbloc);
+
+static ssize_t cmbsz_show(struct device *dev, struct device_attribute *attr,
+		char *buf)
+{
+	struct nvme_dev *ndev = to_nvme_dev(dev_get_drvdata(dev));
+
+	return sysfs_emit(buf, "%u\n", ndev->cmbsz);
+}
+static DEVICE_ATTR_RO(cmbsz);
+
+static ssize_t hmb_show(struct device *dev, struct device_attribute *attr,
+			char *buf)
+{
+	struct nvme_dev *ndev = to_nvme_dev(dev_get_drvdata(dev));
+
+	return sysfs_emit(buf, "%d\n", ndev->hmb);
+}
+
+static ssize_t hmb_store(struct device *dev, struct device_attribute *attr,
+			 const char *buf, size_t count)
+{
+	struct nvme_dev *ndev = to_nvme_dev(dev_get_drvdata(dev));
+	bool new;
+	int ret;
+
+	if (strtobool(buf, &new) < 0)
+		return -EINVAL;
+
+	if (new == ndev->hmb)
+		return count;
+
+	if (new) {
+		ret = nvme_setup_host_mem(ndev);
+	} else {
+		ret = nvme_set_host_mem(ndev, 0);
+		if (!ret)
+			nvme_free_host_mem(ndev);
+	}
+
+	if (ret < 0)
+		return ret;
+
+	return count;
+}
+static DEVICE_ATTR_RW(hmb);
+
+static umode_t nvme_pci_attrs_are_visible(struct kobject *kobj,
+		struct attribute *a, int n)
+{
+	struct nvme_ctrl *ctrl =
+		dev_get_drvdata(container_of(kobj, struct device, kobj));
+	struct nvme_dev *dev = to_nvme_dev(ctrl);
+
+	if (a == &dev_attr_cmb.attr ||
+	    a == &dev_attr_cmbloc.attr ||
+	    a == &dev_attr_cmbsz.attr) {
+	    	if (!dev->cmbsz)
+			return 0;
+	}
+	if (a == &dev_attr_hmb.attr && !ctrl->hmpre)
+		return 0;
+
+	return a->mode;
+}
+
+static struct attribute *nvme_pci_attrs[] = {
+	&dev_attr_cmb.attr,
+	&dev_attr_cmbloc.attr,
+	&dev_attr_cmbsz.attr,
+	&dev_attr_hmb.attr,
+	NULL,
+};
+
+static const struct attribute_group nvme_pci_attr_group = {
+	.attrs		= nvme_pci_attrs,
+	.is_visible	= nvme_pci_attrs_are_visible,
+};
+
 /*
  * nirqs is the number of interrupts available for write and read
  * queues. The core already reserved an interrupt for the admin queue.
@@ -2751,6 +2823,10 @@ static void nvme_reset_work(struct work_struct *work)
 		goto out;
 	}
 
+	if (!dev->attrs_added && !sysfs_create_group(&dev->ctrl.device->kobj,
+			&nvme_pci_attr_group))
+		dev->attrs_added = true;
+
 	nvme_start_ctrl(&dev->ctrl);
 	return;
 
@@ -2999,6 +3075,13 @@ static void nvme_shutdown(struct pci_dev *pdev)
 	nvme_disable_prepare_reset(dev, true);
 }
 
+static void nvme_remove_attrs(struct nvme_dev *dev)
+{
+	if (dev->attrs_added)
+		sysfs_remove_group(&dev->ctrl.device->kobj,
+				   &nvme_pci_attr_group);
+}
+
 /*
  * The driver's remove may be called on a device in a partially initialized
  * state. This function must not have any dependencies on the device state in
@@ -3020,7 +3103,7 @@ static void nvme_remove(struct pci_dev *pdev)
 	nvme_stop_ctrl(&dev->ctrl);
 	nvme_remove_namespaces(&dev->ctrl);
 	nvme_dev_disable(dev, true);
-	nvme_release_cmb(dev);
+	nvme_remove_attrs(dev);
 	nvme_free_host_mem(dev);
 	nvme_dev_remove_admin(dev);
 	nvme_free_queues(dev, 0);
@@ -3047,8 +3130,13 @@ static int nvme_resume(struct device *dev)
 
 	if (ndev->last_ps == U32_MAX ||
 	    nvme_set_power_state(ctrl, ndev->last_ps) != 0)
-		return nvme_try_sched_reset(&ndev->ctrl);
+		goto reset;
+	if (ctrl->hmpre && nvme_setup_host_mem(ndev))
+		goto reset;
+
 	return 0;
+reset:
+	return nvme_try_sched_reset(ctrl);
 }
 
 static int nvme_suspend(struct device *dev)
@@ -3072,15 +3160,9 @@ static int nvme_suspend(struct device *dev)
 	 * the PCI bus layer to put it into D3 in order to take the PCIe link
 	 * down, so as to allow the platform to achieve its minimum low-power
 	 * state (which may not be possible if the link is up).
-	 *
-	 * If a host memory buffer is enabled, shut down the device as the NVMe
-	 * specification allows the device to access the host memory buffer in
-	 * host DRAM from all power states, but hosts will fail access to DRAM
-	 * during S3.
 	 */
 	if (pm_suspend_via_firmware() || !ctrl->npss ||
 	    !pcie_aspm_enabled(pdev) ||
-	    ndev->nr_host_mem_descs ||
 	    (ndev->ctrl.quirks & NVME_QUIRK_SIMPLE_SUSPEND))
 		return nvme_disable_prepare_reset(ndev, true);
 
@@ -3091,6 +3173,17 @@ static int nvme_suspend(struct device *dev)
 	if (ctrl->state != NVME_CTRL_LIVE)
 		goto unfreeze;
 
+	/*
+	 * Host memory access may not be successful in a system suspend state,
+	 * but the specification allows the controller to access memory in a
+	 * non-operational power state.
+	 */
+	if (ndev->hmb) {
+		ret = nvme_set_host_mem(ndev, 0);
+		if (ret < 0)
+			goto unfreeze;
+	}
+
 	ret = nvme_get_power_state(ctrl, &ndev->last_ps);
 	if (ret < 0)
 		goto unfreeze;
@@ -3243,12 +3336,6 @@ static const struct pci_device_id nvme_id_table[] = {
 	{ PCI_DEVICE(0x1b4b, 0x1092),	/* Lexar 256 GB SSD */
 		.driver_data = NVME_QUIRK_NO_NS_DESC_LIST |
 				NVME_QUIRK_IGNORE_DEV_SUBNQN, },
-	{ PCI_DEVICE(0x1d1d, 0x1f1f),	/* LighNVM qemu device */
-		.driver_data = NVME_QUIRK_LIGHTNVM, },
-	{ PCI_DEVICE(0x1d1d, 0x2807),	/* CNEX WL */
-		.driver_data = NVME_QUIRK_LIGHTNVM, },
-	{ PCI_DEVICE(0x1d1d, 0x2601),	/* CNEX Granby */
-		.driver_data = NVME_QUIRK_LIGHTNVM, },
 	{ PCI_DEVICE(0x10ec, 0x5762),   /* ADATA SX6000LNP */
 		.driver_data = NVME_QUIRK_IGNORE_DEV_SUBNQN, },
 	{ PCI_DEVICE(0x1cc1, 0x8201),   /* ADATA SX8200PNP 512GB */
diff --git a/drivers/nvme/host/rdma.c b/drivers/nvme/host/rdma.c
index 7f6b3a991501..a68704e39084 100644
--- a/drivers/nvme/host/rdma.c
+++ b/drivers/nvme/host/rdma.c
@@ -735,13 +735,13 @@ static int nvme_rdma_alloc_io_queues(struct nvme_rdma_ctrl *ctrl)
 	if (ret)
 		return ret;
 
-	ctrl->ctrl.queue_count = nr_io_queues + 1;
-	if (ctrl->ctrl.queue_count < 2) {
+	if (nr_io_queues == 0) {
 		dev_err(ctrl->ctrl.device,
 			"unable to set any I/O queues\n");
 		return -ENOMEM;
 	}
 
+	ctrl->ctrl.queue_count = nr_io_queues + 1;
 	dev_info(ctrl->ctrl.device,
 		"creating %d I/O queues.\n", nr_io_queues);
 
@@ -1730,10 +1730,10 @@ static void nvme_rdma_process_nvme_rsp(struct nvme_rdma_queue *queue,
 	struct request *rq;
 	struct nvme_rdma_request *req;
 
-	rq = blk_mq_tag_to_rq(nvme_rdma_tagset(queue), cqe->command_id);
+	rq = nvme_find_rq(nvme_rdma_tagset(queue), cqe->command_id);
 	if (!rq) {
 		dev_err(queue->ctrl->ctrl.device,
-			"tag 0x%x on QP %#x not found\n",
+			"got bad command_id %#x on QP %#x\n",
 			cqe->command_id, queue->qp->qp_num);
 		nvme_rdma_error_recovery(queue->ctrl);
 		return;
diff --git a/drivers/nvme/host/tcp.c b/drivers/nvme/host/tcp.c
index 8cb15ee5b249..645025620154 100644
--- a/drivers/nvme/host/tcp.c
+++ b/drivers/nvme/host/tcp.c
@@ -487,11 +487,11 @@ static int nvme_tcp_process_nvme_cqe(struct nvme_tcp_queue *queue,
 {
 	struct request *rq;
 
-	rq = blk_mq_tag_to_rq(nvme_tcp_tagset(queue), cqe->command_id);
+	rq = nvme_find_rq(nvme_tcp_tagset(queue), cqe->command_id);
 	if (!rq) {
 		dev_err(queue->ctrl->ctrl.device,
-			"queue %d tag 0x%x not found\n",
-			nvme_tcp_queue_id(queue), cqe->command_id);
+			"got bad cqe.command_id %#x on queue %d\n",
+			cqe->command_id, nvme_tcp_queue_id(queue));
 		nvme_tcp_error_recovery(&queue->ctrl->ctrl);
 		return -EINVAL;
 	}
@@ -508,11 +508,11 @@ static int nvme_tcp_handle_c2h_data(struct nvme_tcp_queue *queue,
 {
 	struct request *rq;
 
-	rq = blk_mq_tag_to_rq(nvme_tcp_tagset(queue), pdu->command_id);
+	rq = nvme_find_rq(nvme_tcp_tagset(queue), pdu->command_id);
 	if (!rq) {
 		dev_err(queue->ctrl->ctrl.device,
-			"queue %d tag %#x not found\n",
-			nvme_tcp_queue_id(queue), pdu->command_id);
+			"got bad c2hdata.command_id %#x on queue %d\n",
+			pdu->command_id, nvme_tcp_queue_id(queue));
 		return -ENOENT;
 	}
 
@@ -606,7 +606,7 @@ static int nvme_tcp_setup_h2c_data_pdu(struct nvme_tcp_request *req,
 	data->hdr.plen =
 		cpu_to_le32(data->hdr.hlen + hdgst + req->pdu_len + ddgst);
 	data->ttag = pdu->ttag;
-	data->command_id = rq->tag;
+	data->command_id = nvme_cid(rq);
 	data->data_offset = cpu_to_le32(req->data_sent);
 	data->data_length = cpu_to_le32(req->pdu_len);
 	return 0;
@@ -619,11 +619,11 @@ static int nvme_tcp_handle_r2t(struct nvme_tcp_queue *queue,
 	struct request *rq;
 	int ret;
 
-	rq = blk_mq_tag_to_rq(nvme_tcp_tagset(queue), pdu->command_id);
+	rq = nvme_find_rq(nvme_tcp_tagset(queue), pdu->command_id);
 	if (!rq) {
 		dev_err(queue->ctrl->ctrl.device,
-			"queue %d tag %#x not found\n",
-			nvme_tcp_queue_id(queue), pdu->command_id);
+			"got bad r2t.command_id %#x on queue %d\n",
+			pdu->command_id, nvme_tcp_queue_id(queue));
 		return -ENOENT;
 	}
 	req = blk_mq_rq_to_pdu(rq);
@@ -702,17 +702,9 @@ static int nvme_tcp_recv_data(struct nvme_tcp_queue *queue, struct sk_buff *skb,
 			      unsigned int *offset, size_t *len)
 {
 	struct nvme_tcp_data_pdu *pdu = (void *)queue->pdu;
-	struct nvme_tcp_request *req;
-	struct request *rq;
-
-	rq = blk_mq_tag_to_rq(nvme_tcp_tagset(queue), pdu->command_id);
-	if (!rq) {
-		dev_err(queue->ctrl->ctrl.device,
-			"queue %d tag %#x not found\n",
-			nvme_tcp_queue_id(queue), pdu->command_id);
-		return -ENOENT;
-	}
-	req = blk_mq_rq_to_pdu(rq);
+	struct request *rq =
+		nvme_cid_to_rq(nvme_tcp_tagset(queue), pdu->command_id);
+	struct nvme_tcp_request *req = blk_mq_rq_to_pdu(rq);
 
 	while (true) {
 		int recv_len, ret;
@@ -804,8 +796,8 @@ static int nvme_tcp_recv_ddgst(struct nvme_tcp_queue *queue,
 	}
 
 	if (pdu->hdr.flags & NVME_TCP_F_DATA_SUCCESS) {
-		struct request *rq = blk_mq_tag_to_rq(nvme_tcp_tagset(queue),
-						pdu->command_id);
+		struct request *rq = nvme_cid_to_rq(nvme_tcp_tagset(queue),
+					pdu->command_id);
 
 		nvme_tcp_end_request(rq, NVME_SC_SUCCESS);
 		queue->nr_cqe++;
@@ -1228,6 +1220,7 @@ static void nvme_tcp_free_queue(struct nvme_ctrl *nctrl, int qid)
 
 	sock_release(queue->sock);
 	kfree(queue->pdu);
+	mutex_destroy(&queue->send_mutex);
 	mutex_destroy(&queue->queue_lock);
 }
 
@@ -1533,6 +1526,7 @@ err_sock:
 	sock_release(queue->sock);
 	queue->sock = NULL;
 err_destroy_mutex:
+	mutex_destroy(&queue->send_mutex);
 	mutex_destroy(&queue->queue_lock);
 	return ret;
 }
@@ -1769,13 +1763,13 @@ static int nvme_tcp_alloc_io_queues(struct nvme_ctrl *ctrl)
 	if (ret)
 		return ret;
 
-	ctrl->queue_count = nr_io_queues + 1;
-	if (ctrl->queue_count < 2) {
+	if (nr_io_queues == 0) {
 		dev_err(ctrl->device,
 			"unable to set any I/O queues\n");
 		return -ENOMEM;
 	}
 
+	ctrl->queue_count = nr_io_queues + 1;
 	dev_info(ctrl->device,
 		"creating %d I/O queues.\n", nr_io_queues);
 
diff --git a/drivers/nvme/host/trace.c b/drivers/nvme/host/trace.c
index 6543015b6121..2a89c5aa0790 100644
--- a/drivers/nvme/host/trace.c
+++ b/drivers/nvme/host/trace.c
@@ -72,6 +72,20 @@ static const char *nvme_trace_admin_identify(struct trace_seq *p, u8 *cdw10)
 	return ret;
 }
 
+static const char *nvme_trace_admin_set_features(struct trace_seq *p,
+						 u8 *cdw10)
+{
+	const char *ret = trace_seq_buffer_ptr(p);
+	u8 fid = cdw10[0];
+	u8 sv = cdw10[3] & 0x8;
+	u32 cdw11 = get_unaligned_le32(cdw10 + 4);
+
+	trace_seq_printf(p, "fid=0x%x, sv=0x%x, cdw11=0x%x", fid, sv, cdw11);
+	trace_seq_putc(p, 0);
+
+	return ret;
+}
+
 static const char *nvme_trace_admin_get_features(struct trace_seq *p,
 						 u8 *cdw10)
 {
@@ -80,7 +94,7 @@ static const char *nvme_trace_admin_get_features(struct trace_seq *p,
 	u8 sel = cdw10[1] & 0x7;
 	u32 cdw11 = get_unaligned_le32(cdw10 + 4);
 
-	trace_seq_printf(p, "fid=0x%x sel=0x%x cdw11=0x%x", fid, sel, cdw11);
+	trace_seq_printf(p, "fid=0x%x, sel=0x%x, cdw11=0x%x", fid, sel, cdw11);
 	trace_seq_putc(p, 0);
 
 	return ret;
@@ -201,6 +215,8 @@ const char *nvme_trace_parse_admin_cmd(struct trace_seq *p,
 		return nvme_trace_create_cq(p, cdw10);
 	case nvme_admin_identify:
 		return nvme_trace_admin_identify(p, cdw10);
+	case nvme_admin_set_features:
+		return nvme_trace_admin_set_features(p, cdw10);
 	case nvme_admin_get_features:
 		return nvme_trace_admin_get_features(p, cdw10);
 	case nvme_admin_get_lba_status:
diff --git a/drivers/nvme/target/Kconfig b/drivers/nvme/target/Kconfig
index 4be2ececbc45..973561c93888 100644
--- a/drivers/nvme/target/Kconfig
+++ b/drivers/nvme/target/Kconfig
@@ -31,7 +31,6 @@ config NVME_TARGET_PASSTHRU
 config NVME_TARGET_LOOP
 	tristate "NVMe loopback device support"
 	depends on NVME_TARGET
-	select NVME_CORE
 	select NVME_FABRICS
 	select SG_POOL
 	help
@@ -65,7 +64,6 @@ config NVME_TARGET_FC
 config NVME_TARGET_FCLOOP
 	tristate "NVMe over Fabrics FC Transport Loopback Test driver"
 	depends on NVME_TARGET
-	select NVME_CORE
 	select NVME_FABRICS
 	select SG_POOL
 	depends on NVME_FC
diff --git a/drivers/nvme/target/core.c b/drivers/nvme/target/core.c
index ac7210a3ea1c..66d05eecc2a9 100644
--- a/drivers/nvme/target/core.c
+++ b/drivers/nvme/target/core.c
@@ -802,6 +802,7 @@ void nvmet_sq_destroy(struct nvmet_sq *sq)
 		 * controller teardown as a result of a keep-alive expiration.
 		 */
 		ctrl->reset_tbkas = true;
+		sq->ctrl->sqs[sq->qid] = NULL;
 		nvmet_ctrl_put(ctrl);
 		sq->ctrl = NULL; /* allows reusing the queue later */
 	}
diff --git a/drivers/nvme/target/fabrics-cmd.c b/drivers/nvme/target/fabrics-cmd.c
index 7d0f3523fdab..7d0454cee920 100644
--- a/drivers/nvme/target/fabrics-cmd.c
+++ b/drivers/nvme/target/fabrics-cmd.c
@@ -109,21 +109,38 @@ static u16 nvmet_install_queue(struct nvmet_ctrl *ctrl, struct nvmet_req *req)
 	u16 qid = le16_to_cpu(c->qid);
 	u16 sqsize = le16_to_cpu(c->sqsize);
 	struct nvmet_ctrl *old;
+	u16 mqes = NVME_CAP_MQES(ctrl->cap);
 	u16 ret;
 
-	old = cmpxchg(&req->sq->ctrl, NULL, ctrl);
-	if (old) {
-		pr_warn("queue already connected!\n");
-		req->error_loc = offsetof(struct nvmf_connect_command, opcode);
-		return NVME_SC_CONNECT_CTRL_BUSY | NVME_SC_DNR;
-	}
 	if (!sqsize) {
 		pr_warn("queue size zero!\n");
 		req->error_loc = offsetof(struct nvmf_connect_command, sqsize);
+		req->cqe->result.u32 = IPO_IATTR_CONNECT_SQE(sqsize);
 		ret = NVME_SC_CONNECT_INVALID_PARAM | NVME_SC_DNR;
 		goto err;
 	}
 
+	if (ctrl->sqs[qid] != NULL) {
+		pr_warn("qid %u has already been created\n", qid);
+		req->error_loc = offsetof(struct nvmf_connect_command, qid);
+		return NVME_SC_CMD_SEQ_ERROR | NVME_SC_DNR;
+	}
+
+	if (sqsize > mqes) {
+		pr_warn("sqsize %u is larger than MQES supported %u cntlid %d\n",
+				sqsize, mqes, ctrl->cntlid);
+		req->error_loc = offsetof(struct nvmf_connect_command, sqsize);
+		req->cqe->result.u32 = IPO_IATTR_CONNECT_SQE(sqsize);
+		return NVME_SC_CONNECT_INVALID_PARAM | NVME_SC_DNR;
+	}
+
+	old = cmpxchg(&req->sq->ctrl, NULL, ctrl);
+	if (old) {
+		pr_warn("queue already connected!\n");
+		req->error_loc = offsetof(struct nvmf_connect_command, opcode);
+		return NVME_SC_CONNECT_CTRL_BUSY | NVME_SC_DNR;
+	}
+
 	/* note: convert queue size from 0's-based value to 1's-based value */
 	nvmet_cq_setup(ctrl, req->cq, qid, sqsize + 1);
 	nvmet_sq_setup(ctrl, req->sq, qid, sqsize + 1);
@@ -138,6 +155,7 @@ static u16 nvmet_install_queue(struct nvmet_ctrl *ctrl, struct nvmet_req *req)
 		if (ret) {
 			pr_err("failed to install queue %d cntlid %d ret %x\n",
 				qid, ctrl->cntlid, ret);
+			ctrl->sqs[qid] = NULL;
 			goto err;
 		}
 	}
@@ -260,11 +278,11 @@ static void nvmet_execute_io_connect(struct nvmet_req *req)
 	}
 
 	status = nvmet_install_queue(ctrl, req);
-	if (status) {
-		/* pass back cntlid that had the issue of installing queue */
-		req->cqe->result.u16 = cpu_to_le16(ctrl->cntlid);
+	if (status)
 		goto out_ctrl_put;
-	}
+
+	/* pass back cntlid for successful completion */
+	req->cqe->result.u16 = cpu_to_le16(ctrl->cntlid);
 
 	pr_debug("adding queue %d to ctrl %d.\n", qid, ctrl->cntlid);
 
diff --git a/drivers/nvme/target/loop.c b/drivers/nvme/target/loop.c
index 3a17a7e26bbf..0285ccc7541f 100644
--- a/drivers/nvme/target/loop.c
+++ b/drivers/nvme/target/loop.c
@@ -107,10 +107,10 @@ static void nvme_loop_queue_response(struct nvmet_req *req)
 	} else {
 		struct request *rq;
 
-		rq = blk_mq_tag_to_rq(nvme_loop_tagset(queue), cqe->command_id);
+		rq = nvme_find_rq(nvme_loop_tagset(queue), cqe->command_id);
 		if (!rq) {
 			dev_err(queue->ctrl->ctrl.device,
-				"tag 0x%x on queue %d not found\n",
+				"got bad command_id %#x on queue %d\n",
 				cqe->command_id, nvme_loop_queue_idx(queue));
 			return;
 		}
diff --git a/drivers/nvme/target/trace.c b/drivers/nvme/target/trace.c
index 1373a3c67962..bff454d46255 100644
--- a/drivers/nvme/target/trace.c
+++ b/drivers/nvme/target/trace.c
@@ -27,7 +27,7 @@ static const char *nvmet_trace_admin_get_features(struct trace_seq *p,
 	u8 sel = cdw10[1] & 0x7;
 	u32 cdw11 = get_unaligned_le32(cdw10 + 4);
 
-	trace_seq_printf(p, "fid=0x%x sel=0x%x cdw11=0x%x", fid, sel, cdw11);
+	trace_seq_printf(p, "fid=0x%x, sel=0x%x, cdw11=0x%x", fid, sel, cdw11);
 	trace_seq_putc(p, 0);
 
 	return ret;
@@ -49,6 +49,20 @@ static const char *nvmet_trace_get_lba_status(struct trace_seq *p,
 	return ret;
 }
 
+static const char *nvmet_trace_admin_set_features(struct trace_seq *p,
+						 u8 *cdw10)
+{
+	const char *ret = trace_seq_buffer_ptr(p);
+	u8 fid = cdw10[0];
+	u8 sv = cdw10[3] & 0x8;
+	u32 cdw11 = get_unaligned_le32(cdw10 + 4);
+
+	trace_seq_printf(p, "fid=0x%x, sv=0x%x, cdw11=0x%x", fid, sv, cdw11);
+	trace_seq_putc(p, 0);
+
+	return ret;
+}
+
 static const char *nvmet_trace_read_write(struct trace_seq *p, u8 *cdw10)
 {
 	const char *ret = trace_seq_buffer_ptr(p);
@@ -94,6 +108,8 @@ const char *nvmet_trace_parse_admin_cmd(struct trace_seq *p,
 	switch (opcode) {
 	case nvme_admin_identify:
 		return nvmet_trace_admin_identify(p, cdw10);
+	case nvme_admin_set_features:
+		return nvmet_trace_admin_set_features(p, cdw10);
 	case nvme_admin_get_features:
 		return nvmet_trace_admin_get_features(p, cdw10);
 	case nvme_admin_get_lba_status:
diff --git a/drivers/nvme/target/zns.c b/drivers/nvme/target/zns.c
index 17f8b7a45f21..46bc30fe85d2 100644
--- a/drivers/nvme/target/zns.c
+++ b/drivers/nvme/target/zns.c
@@ -115,14 +115,11 @@ void nvmet_execute_identify_cns_cs_ns(struct nvmet_req *req)
 	}
 
 	status = nvmet_req_find_ns(req);
-	if (status) {
-		status = NVME_SC_INTERNAL;
+	if (status)
 		goto done;
-	}
 
 	if (!bdev_is_zoned(req->ns->bdev)) {
 		req->error_loc = offsetof(struct nvme_identify, nsid);
-		status = NVME_SC_INVALID_NS | NVME_SC_DNR;
 		goto done;
 	}