From 50a212ec906f7524620675f0c57357691c26c81f Mon Sep 17 00:00:00 2001
From: hc <hc@nodka.com>
Date: Wed, 16 Oct 2024 01:20:19 +0000
Subject: [PATCH] 修改GPIO导出默认初始值

---
 kernel/drivers/nvme/host/core.c | 2552 +++++++++++++++++++++++++++++++++++++++++------------------
 1 files changed, 1,777 insertions(+), 775 deletions(-)

diff --git a/kernel/drivers/nvme/host/core.c b/kernel/drivers/nvme/host/core.c
index d3c901c..07c41a1 100644
--- a/kernel/drivers/nvme/host/core.c
+++ b/kernel/drivers/nvme/host/core.c
@@ -1,39 +1,31 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * NVM Express device driver
  * Copyright (c) 2011-2014, Intel Corporation.
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms and conditions of the GNU General Public License,
- * version 2, as published by the Free Software Foundation.
- *
- * This program is distributed in the hope it will be useful, but WITHOUT
- * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
- * more details.
  */
 
 #include <linux/blkdev.h>
 #include <linux/blk-mq.h>
+#include <linux/compat.h>
 #include <linux/delay.h>
 #include <linux/errno.h>
 #include <linux/hdreg.h>
 #include <linux/kernel.h>
 #include <linux/module.h>
-#include <linux/list_sort.h>
+#include <linux/backing-dev.h>
 #include <linux/slab.h>
 #include <linux/types.h>
 #include <linux/pr.h>
 #include <linux/ptrace.h>
 #include <linux/nvme_ioctl.h>
-#include <linux/t10-pi.h>
 #include <linux/pm_qos.h>
 #include <asm/unaligned.h>
 
-#define CREATE_TRACE_POINTS
-#include "trace.h"
-
 #include "nvme.h"
 #include "fabrics.h"
+
+#define CREATE_TRACE_POINTS
+#include "trace.h"
 
 #define NVME_MINORS		(1U << MINORBITS)
 
@@ -73,8 +65,8 @@
  * nvme_reset_wq - hosts nvme reset works
  * nvme_delete_wq - hosts nvme delete works
  *
- * nvme_wq will host works such are scan, aen handling, fw activation,
- * keep-alive error recovery, periodic reconnects etc. nvme_reset_wq
+ * nvme_wq will host works such as scan, aen handling, fw activation,
+ * keep-alive, periodic reconnects etc. nvme_reset_wq
  * runs reset works which also flush works hosted on nvme_wq for
  * serialization purposes. nvme_delete_wq host controller deletion
  * works which flush reset works for serialization.
@@ -88,7 +80,6 @@
 struct workqueue_struct *nvme_delete_wq;
 EXPORT_SYMBOL_GPL(nvme_delete_wq);
 
-static DEFINE_IDA(nvme_subsystems_ida);
 static LIST_HEAD(nvme_subsystems);
 static DEFINE_MUTEX(nvme_subsystems_lock);
 
@@ -97,27 +88,38 @@
 static struct class *nvme_class;
 static struct class *nvme_subsys_class;
 
-static void nvme_ns_remove(struct nvme_ns *ns);
-static int nvme_revalidate_disk(struct gendisk *disk);
 static void nvme_put_subsystem(struct nvme_subsystem *subsys);
 static void nvme_remove_invalid_namespaces(struct nvme_ctrl *ctrl,
 					   unsigned nsid);
 
+static void nvme_update_bdev_size(struct gendisk *disk)
+{
+	struct block_device *bdev = bdget_disk(disk, 0);
+
+	if (bdev) {
+		bd_set_nr_sectors(bdev, get_capacity(disk));
+		bdput(bdev);
+	}
+}
+
+/*
+ * Prepare a queue for teardown.
+ *
+ * This must forcibly unquiesce queues to avoid blocking dispatch, and only set
+ * the capacity to 0 after that to avoid blocking dispatchers that may be
+ * holding bd_butex.  This will end buffered writers dirtying pages that can't
+ * be synced.
+ */
 static void nvme_set_queue_dying(struct nvme_ns *ns)
 {
-	/*
-	 * Revalidating a dead namespace sets capacity to 0. This will end
-	 * buffered writers dirtying pages that can't be synced.
-	 */
-	if (!ns->disk || test_and_set_bit(NVME_NS_DEAD, &ns->flags))
+	if (test_and_set_bit(NVME_NS_DEAD, &ns->flags))
 		return;
+
 	blk_set_queue_dying(ns->queue);
-	/* Forcibly unquiesce queues to avoid blocking dispatch */
 	blk_mq_unquiesce_queue(ns->queue);
-	/*
-	 * Revalidate after unblocking dispatchers that may be holding bd_butex
-	 */
-	revalidate_disk(ns->disk);
+
+	set_capacity(ns->disk, 0);
+	nvme_update_bdev_size(ns->disk);
 }
 
 static void nvme_queue_scan(struct nvme_ctrl *ctrl)
@@ -125,9 +127,25 @@
 	/*
 	 * Only new queue scan work when admin and IO queues are both alive
 	 */
-	if (ctrl->state == NVME_CTRL_LIVE)
+	if (ctrl->state == NVME_CTRL_LIVE && ctrl->tagset)
 		queue_work(nvme_wq, &ctrl->scan_work);
 }
+
+/*
+ * Use this function to proceed with scheduling reset_work for a controller
+ * that had previously been set to the resetting state. This is intended for
+ * code paths that can't be interrupted by other reset attempts. A hot removal
+ * may prevent this from succeeding.
+ */
+int nvme_try_sched_reset(struct nvme_ctrl *ctrl)
+{
+	if (ctrl->state != NVME_CTRL_RESETTING)
+		return -EBUSY;
+	if (!queue_work(nvme_reset_wq, &ctrl->reset_work))
+		return -EBUSY;
+	return 0;
+}
+EXPORT_SYMBOL_GPL(nvme_try_sched_reset);
 
 int nvme_reset_ctrl(struct nvme_ctrl *ctrl)
 {
@@ -146,8 +164,7 @@
 	ret = nvme_reset_ctrl(ctrl);
 	if (!ret) {
 		flush_work(&ctrl->reset_work);
-		if (ctrl->state != NVME_CTRL_LIVE &&
-		    ctrl->state != NVME_CTRL_ADMIN_ONLY)
+		if (ctrl->state != NVME_CTRL_LIVE)
 			ret = -ENETRESET;
 	}
 
@@ -155,11 +172,8 @@
 }
 EXPORT_SYMBOL_GPL(nvme_reset_ctrl_sync);
 
-static void nvme_delete_ctrl_work(struct work_struct *work)
+static void nvme_do_delete_ctrl(struct nvme_ctrl *ctrl)
 {
-	struct nvme_ctrl *ctrl =
-		container_of(work, struct nvme_ctrl, delete_work);
-
 	dev_info(ctrl->device,
 		 "Removing ctrl: NQN \"%s\"\n", ctrl->opts->subsysnqn);
 
@@ -168,7 +182,14 @@
 	nvme_remove_namespaces(ctrl);
 	ctrl->ops->delete_ctrl(ctrl);
 	nvme_uninit_ctrl(ctrl);
-	nvme_put_ctrl(ctrl);
+}
+
+static void nvme_delete_ctrl_work(struct work_struct *work)
+{
+	struct nvme_ctrl *ctrl =
+		container_of(work, struct nvme_ctrl, delete_work);
+
+	nvme_do_delete_ctrl(ctrl);
 }
 
 int nvme_delete_ctrl(struct nvme_ctrl *ctrl)
@@ -181,36 +202,28 @@
 }
 EXPORT_SYMBOL_GPL(nvme_delete_ctrl);
 
-int nvme_delete_ctrl_sync(struct nvme_ctrl *ctrl)
+static void nvme_delete_ctrl_sync(struct nvme_ctrl *ctrl)
 {
-	int ret = 0;
-
 	/*
-	 * Keep a reference until the work is flushed since ->delete_ctrl
-	 * can free the controller.
+	 * Keep a reference until nvme_do_delete_ctrl() complete,
+	 * since ->delete_ctrl can free the controller.
 	 */
 	nvme_get_ctrl(ctrl);
-	ret = nvme_delete_ctrl(ctrl);
-	if (!ret)
-		flush_work(&ctrl->delete_work);
+	if (nvme_change_ctrl_state(ctrl, NVME_CTRL_DELETING))
+		nvme_do_delete_ctrl(ctrl);
 	nvme_put_ctrl(ctrl);
-	return ret;
-}
-EXPORT_SYMBOL_GPL(nvme_delete_ctrl_sync);
-
-static inline bool nvme_ns_has_pi(struct nvme_ns *ns)
-{
-	return ns->pi_type && ns->ms == sizeof(struct t10_pi_tuple);
 }
 
-static blk_status_t nvme_error_status(struct request *req)
+static blk_status_t nvme_error_status(u16 status)
 {
-	switch (nvme_req(req)->status & 0x7ff) {
+	switch (status & 0x7ff) {
 	case NVME_SC_SUCCESS:
 		return BLK_STS_OK;
 	case NVME_SC_CAP_EXCEEDED:
 		return BLK_STS_NOSPC;
 	case NVME_SC_LBA_RANGE:
+	case NVME_SC_CMD_INTERRUPTED:
+	case NVME_SC_NS_NOT_READY:
 		return BLK_STS_TARGET;
 	case NVME_SC_BAD_ATTRIBUTES:
 	case NVME_SC_ONCS_NOT_SUPPORTED:
@@ -232,52 +245,131 @@
 		return BLK_STS_PROTECTION;
 	case NVME_SC_RESERVATION_CONFLICT:
 		return BLK_STS_NEXUS;
+	case NVME_SC_HOST_PATH_ERROR:
+		return BLK_STS_TRANSPORT;
+	case NVME_SC_ZONE_TOO_MANY_ACTIVE:
+		return BLK_STS_ZONE_ACTIVE_RESOURCE;
+	case NVME_SC_ZONE_TOO_MANY_OPEN:
+		return BLK_STS_ZONE_OPEN_RESOURCE;
 	default:
 		return BLK_STS_IOERR;
 	}
 }
 
-static inline bool nvme_req_needs_retry(struct request *req)
+static void nvme_retry_req(struct request *req)
 {
-	if (blk_noretry_request(req))
-		return false;
-	if (nvme_req(req)->status & NVME_SC_DNR)
-		return false;
-	if (nvme_req(req)->retries >= nvme_max_retries)
-		return false;
-	return true;
+	struct nvme_ns *ns = req->q->queuedata;
+	unsigned long delay = 0;
+	u16 crd;
+
+	/* The mask and shift result must be <= 3 */
+	crd = (nvme_req(req)->status & NVME_SC_CRD) >> 11;
+	if (ns && crd)
+		delay = ns->ctrl->crdt[crd - 1] * 100;
+
+	nvme_req(req)->retries++;
+	blk_mq_requeue_request(req, false);
+	blk_mq_delay_kick_requeue_list(req->q, delay);
+}
+
+enum nvme_disposition {
+	COMPLETE,
+	RETRY,
+	FAILOVER,
+};
+
+static inline enum nvme_disposition nvme_decide_disposition(struct request *req)
+{
+	if (likely(nvme_req(req)->status == 0))
+		return COMPLETE;
+
+	if (blk_noretry_request(req) ||
+	    (nvme_req(req)->status & NVME_SC_DNR) ||
+	    nvme_req(req)->retries >= nvme_max_retries)
+		return COMPLETE;
+
+	if (req->cmd_flags & REQ_NVME_MPATH) {
+		if (nvme_is_path_error(nvme_req(req)->status) ||
+		    blk_queue_dying(req->q))
+			return FAILOVER;
+	} else {
+		if (blk_queue_dying(req->q))
+			return COMPLETE;
+	}
+
+	return RETRY;
+}
+
+static inline void nvme_end_req(struct request *req)
+{
+	blk_status_t status = nvme_error_status(nvme_req(req)->status);
+
+	if (IS_ENABLED(CONFIG_BLK_DEV_ZONED) &&
+	    req_op(req) == REQ_OP_ZONE_APPEND)
+		req->__sector = nvme_lba_to_sect(req->q->queuedata,
+			le64_to_cpu(nvme_req(req)->result.u64));
+
+	nvme_trace_bio_complete(req, status);
+	blk_mq_end_request(req, status);
 }
 
 void nvme_complete_rq(struct request *req)
 {
-	blk_status_t status = nvme_error_status(req);
-
 	trace_nvme_complete_rq(req);
+	nvme_cleanup_cmd(req);
 
-	if (unlikely(status != BLK_STS_OK && nvme_req_needs_retry(req))) {
-		if ((req->cmd_flags & REQ_NVME_MPATH) && nvme_failover_req(req))
-			return;
+	if (nvme_req(req)->ctrl->kas)
+		nvme_req(req)->ctrl->comp_seen = true;
 
-		if (!blk_queue_dying(req->q)) {
-			nvme_req(req)->retries++;
-			blk_mq_requeue_request(req, true);
-			return;
-		}
+	switch (nvme_decide_disposition(req)) {
+	case COMPLETE:
+		nvme_end_req(req);
+		return;
+	case RETRY:
+		nvme_retry_req(req);
+		return;
+	case FAILOVER:
+		nvme_failover_req(req);
+		return;
 	}
-	blk_mq_end_request(req, status);
 }
 EXPORT_SYMBOL_GPL(nvme_complete_rq);
 
-void nvme_cancel_request(struct request *req, void *data, bool reserved)
+bool nvme_cancel_request(struct request *req, void *data, bool reserved)
 {
 	dev_dbg_ratelimited(((struct nvme_ctrl *) data)->device,
 				"Cancelling I/O %d", req->tag);
 
-	nvme_req(req)->status = NVME_SC_ABORT_REQ;
-	blk_mq_complete_request(req);
+	/* don't abort one completed request */
+	if (blk_mq_request_completed(req))
+		return true;
 
+	nvme_req(req)->status = NVME_SC_HOST_ABORTED_CMD;
+	nvme_req(req)->flags |= NVME_REQ_CANCELLED;
+	blk_mq_complete_request(req);
+	return true;
 }
 EXPORT_SYMBOL_GPL(nvme_cancel_request);
+
+void nvme_cancel_tagset(struct nvme_ctrl *ctrl)
+{
+	if (ctrl->tagset) {
+		blk_mq_tagset_busy_iter(ctrl->tagset,
+				nvme_cancel_request, ctrl);
+		blk_mq_tagset_wait_completed_request(ctrl->tagset);
+	}
+}
+EXPORT_SYMBOL_GPL(nvme_cancel_tagset);
+
+void nvme_cancel_admin_tagset(struct nvme_ctrl *ctrl)
+{
+	if (ctrl->admin_tagset) {
+		blk_mq_tagset_busy_iter(ctrl->admin_tagset,
+				nvme_cancel_request, ctrl);
+		blk_mq_tagset_wait_completed_request(ctrl->admin_tagset);
+	}
+}
+EXPORT_SYMBOL_GPL(nvme_cancel_admin_tagset);
 
 bool nvme_change_ctrl_state(struct nvme_ctrl *ctrl,
 		enum nvme_ctrl_state new_state)
@@ -290,22 +382,13 @@
 
 	old_state = ctrl->state;
 	switch (new_state) {
-	case NVME_CTRL_ADMIN_ONLY:
-		switch (old_state) {
-		case NVME_CTRL_CONNECTING:
-			changed = true;
-			/* FALLTHRU */
-		default:
-			break;
-		}
-		break;
 	case NVME_CTRL_LIVE:
 		switch (old_state) {
 		case NVME_CTRL_NEW:
 		case NVME_CTRL_RESETTING:
 		case NVME_CTRL_CONNECTING:
 			changed = true;
-			/* FALLTHRU */
+			fallthrough;
 		default:
 			break;
 		}
@@ -314,9 +397,8 @@
 		switch (old_state) {
 		case NVME_CTRL_NEW:
 		case NVME_CTRL_LIVE:
-		case NVME_CTRL_ADMIN_ONLY:
 			changed = true;
-			/* FALLTHRU */
+			fallthrough;
 		default:
 			break;
 		}
@@ -326,7 +408,7 @@
 		case NVME_CTRL_NEW:
 		case NVME_CTRL_RESETTING:
 			changed = true;
-			/* FALLTHRU */
+			fallthrough;
 		default:
 			break;
 		}
@@ -334,11 +416,20 @@
 	case NVME_CTRL_DELETING:
 		switch (old_state) {
 		case NVME_CTRL_LIVE:
-		case NVME_CTRL_ADMIN_ONLY:
 		case NVME_CTRL_RESETTING:
 		case NVME_CTRL_CONNECTING:
 			changed = true;
-			/* FALLTHRU */
+			fallthrough;
+		default:
+			break;
+		}
+		break;
+	case NVME_CTRL_DELETING_NOIO:
+		switch (old_state) {
+		case NVME_CTRL_DELETING:
+		case NVME_CTRL_DEAD:
+			changed = true;
+			fallthrough;
 		default:
 			break;
 		}
@@ -347,7 +438,7 @@
 		switch (old_state) {
 		case NVME_CTRL_DELETING:
 			changed = true;
-			/* FALLTHRU */
+			fallthrough;
 		default:
 			break;
 		}
@@ -356,8 +447,10 @@
 		break;
 	}
 
-	if (changed)
+	if (changed) {
 		ctrl->state = new_state;
+		wake_up_all(&ctrl->state_wq);
+	}
 
 	spin_unlock_irqrestore(&ctrl->lock, flags);
 	if (changed && ctrl->state == NVME_CTRL_LIVE)
@@ -366,6 +459,40 @@
 }
 EXPORT_SYMBOL_GPL(nvme_change_ctrl_state);
 
+/*
+ * Returns true for sink states that can't ever transition back to live.
+ */
+static bool nvme_state_terminal(struct nvme_ctrl *ctrl)
+{
+	switch (ctrl->state) {
+	case NVME_CTRL_NEW:
+	case NVME_CTRL_LIVE:
+	case NVME_CTRL_RESETTING:
+	case NVME_CTRL_CONNECTING:
+		return false;
+	case NVME_CTRL_DELETING:
+	case NVME_CTRL_DELETING_NOIO:
+	case NVME_CTRL_DEAD:
+		return true;
+	default:
+		WARN_ONCE(1, "Unhandled ctrl state:%d", ctrl->state);
+		return true;
+	}
+}
+
+/*
+ * Waits for the controller state to be resetting, or returns false if it is
+ * not possible to ever transition to that state.
+ */
+bool nvme_wait_reset(struct nvme_ctrl *ctrl)
+{
+	wait_event(ctrl->state_wq,
+		   nvme_change_ctrl_state(ctrl, NVME_CTRL_RESETTING) ||
+		   nvme_state_terminal(ctrl));
+	return ctrl->state == NVME_CTRL_RESETTING;
+}
+EXPORT_SYMBOL_GPL(nvme_wait_reset);
+
 static void nvme_free_ns_head(struct kref *ref)
 {
 	struct nvme_ns_head *head =
@@ -373,8 +500,7 @@
 
 	nvme_mpath_remove_disk(head);
 	ida_simple_remove(&head->subsys->ns_ida, head->instance);
-	list_del_init(&head->entry);
-	cleanup_srcu_struct_quiesced(&head->srcu);
+	cleanup_srcu_struct(&head->srcu);
 	nvme_put_subsystem(head->subsys);
 	kfree(head);
 }
@@ -397,42 +523,61 @@
 	kfree(ns);
 }
 
-static void nvme_put_ns(struct nvme_ns *ns)
+void nvme_put_ns(struct nvme_ns *ns)
 {
 	kref_put(&ns->kref, nvme_free_ns);
 }
+EXPORT_SYMBOL_NS_GPL(nvme_put_ns, NVME_TARGET_PASSTHRU);
 
 static inline void nvme_clear_nvme_request(struct request *req)
 {
-	if (!(req->rq_flags & RQF_DONTPREP)) {
-		nvme_req(req)->retries = 0;
-		nvme_req(req)->flags = 0;
-		req->rq_flags |= RQF_DONTPREP;
-	}
+	nvme_req(req)->retries = 0;
+	nvme_req(req)->flags = 0;
+	req->rq_flags |= RQF_DONTPREP;
 }
 
-struct request *nvme_alloc_request(struct request_queue *q,
-		struct nvme_command *cmd, blk_mq_req_flags_t flags, int qid)
+static inline unsigned int nvme_req_op(struct nvme_command *cmd)
 {
-	unsigned op = nvme_is_write(cmd) ? REQ_OP_DRV_OUT : REQ_OP_DRV_IN;
-	struct request *req;
+	return nvme_is_write(cmd) ? REQ_OP_DRV_OUT : REQ_OP_DRV_IN;
+}
 
-	if (qid == NVME_QID_ANY) {
-		req = blk_mq_alloc_request(q, op, flags);
-	} else {
-		req = blk_mq_alloc_request_hctx(q, op, flags,
-				qid ? qid - 1 : 0);
-	}
-	if (IS_ERR(req))
-		return req;
+static inline void nvme_init_request(struct request *req,
+		struct nvme_command *cmd)
+{
+	if (req->q->queuedata)
+		req->timeout = NVME_IO_TIMEOUT;
+	else /* no queuedata implies admin queue */
+		req->timeout = ADMIN_TIMEOUT;
 
 	req->cmd_flags |= REQ_FAILFAST_DRIVER;
 	nvme_clear_nvme_request(req);
 	nvme_req(req)->cmd = cmd;
+}
 
+struct request *nvme_alloc_request(struct request_queue *q,
+		struct nvme_command *cmd, blk_mq_req_flags_t flags)
+{
+	struct request *req;
+
+	req = blk_mq_alloc_request(q, nvme_req_op(cmd), flags);
+	if (!IS_ERR(req))
+		nvme_init_request(req, cmd);
 	return req;
 }
 EXPORT_SYMBOL_GPL(nvme_alloc_request);
+
+struct request *nvme_alloc_request_qid(struct request_queue *q,
+		struct nvme_command *cmd, blk_mq_req_flags_t flags, int qid)
+{
+	struct request *req;
+
+	req = blk_mq_alloc_request_hctx(q, nvme_req_op(cmd), flags,
+			qid ? qid - 1 : 0);
+	if (!IS_ERR(req))
+		nvme_init_request(req, cmd);
+	return req;
+}
+EXPORT_SYMBOL_GPL(nvme_alloc_request_qid);
 
 static int nvme_toggle_streams(struct nvme_ctrl *ctrl, bool enable)
 {
@@ -470,7 +615,7 @@
 
 	c.directive.opcode = nvme_admin_directive_recv;
 	c.directive.nsid = cpu_to_le32(nsid);
-	c.directive.numd = cpu_to_le32((sizeof(*s) >> 2) - 1);
+	c.directive.numd = cpu_to_le32(nvme_bytes_to_numd(sizeof(*s)));
 	c.directive.doper = NVME_DIR_RCV_ST_OP_PARAM;
 	c.directive.dtype = NVME_DIR_STREAMS;
 
@@ -493,19 +638,22 @@
 
 	ret = nvme_get_stream_params(ctrl, &s, NVME_NSID_ALL);
 	if (ret)
-		return ret;
+		goto out_disable_stream;
 
 	ctrl->nssa = le16_to_cpu(s.nssa);
 	if (ctrl->nssa < BLK_MAX_WRITE_HINTS - 1) {
 		dev_info(ctrl->device, "too few streams (%u) available\n",
 					ctrl->nssa);
-		nvme_disable_streams(ctrl);
-		return 0;
+		goto out_disable_stream;
 	}
 
-	ctrl->nr_streams = min_t(unsigned, ctrl->nssa, BLK_MAX_WRITE_HINTS - 1);
+	ctrl->nr_streams = min_t(u16, ctrl->nssa, BLK_MAX_WRITE_HINTS - 1);
 	dev_info(ctrl->device, "Using %u streams\n", ctrl->nr_streams);
 	return 0;
+
+out_disable_stream:
+	nvme_disable_streams(ctrl);
+	return ret;
 }
 
 /*
@@ -533,10 +681,17 @@
 		req->q->write_hints[streamid] += blk_rq_bytes(req) >> 9;
 }
 
+static inline void nvme_setup_passthrough(struct request *req,
+		struct nvme_command *cmd)
+{
+	memcpy(cmd, nvme_req(req)->cmd, sizeof(*cmd));
+	/* passthru commands should let the driver set the SGL flags */
+	cmd->common.flags &= ~NVME_CMD_SGL_ALL;
+}
+
 static inline void nvme_setup_flush(struct nvme_ns *ns,
 		struct nvme_command *cmnd)
 {
-	memset(cmnd, 0, sizeof(*cmnd));
 	cmnd->common.opcode = nvme_cmd_flush;
 	cmnd->common.nsid = cpu_to_le32(ns->head->ns_id);
 }
@@ -568,16 +723,26 @@
 		range = page_address(ns->ctrl->discard_page);
 	}
 
-	__rq_for_each_bio(bio, req) {
-		u64 slba = nvme_block_nr(ns, bio->bi_iter.bi_sector);
-		u32 nlb = bio->bi_iter.bi_size >> ns->lba_shift;
+	if (queue_max_discard_segments(req->q) == 1) {
+		u64 slba = nvme_sect_to_lba(ns, blk_rq_pos(req));
+		u32 nlb = blk_rq_sectors(req) >> (ns->lba_shift - 9);
 
-		if (n < segments) {
-			range[n].cattr = cpu_to_le32(0);
-			range[n].nlb = cpu_to_le32(nlb);
-			range[n].slba = cpu_to_le64(slba);
+		range[0].cattr = cpu_to_le32(0);
+		range[0].nlb = cpu_to_le32(nlb);
+		range[0].slba = cpu_to_le64(slba);
+		n = 1;
+	} else {
+		__rq_for_each_bio(bio, req) {
+			u64 slba = nvme_sect_to_lba(ns, bio->bi_iter.bi_sector);
+			u32 nlb = bio->bi_iter.bi_size >> ns->lba_shift;
+
+			if (n < segments) {
+				range[n].cattr = cpu_to_le32(0);
+				range[n].nlb = cpu_to_le32(nlb);
+				range[n].slba = cpu_to_le64(slba);
+			}
+			n++;
 		}
-		n++;
 	}
 
 	if (WARN_ON_ONCE(n != segments)) {
@@ -588,7 +753,6 @@
 		return BLK_STS_IOERR;
 	}
 
-	memset(cmnd, 0, sizeof(*cmnd));
 	cmnd->dsm.opcode = nvme_cmd_dsm;
 	cmnd->dsm.nsid = cpu_to_le32(ns->head->ns_id);
 	cmnd->dsm.nr = cpu_to_le32(segments - 1);
@@ -602,8 +766,28 @@
 	return BLK_STS_OK;
 }
 
-static inline blk_status_t nvme_setup_rw(struct nvme_ns *ns,
+static inline blk_status_t nvme_setup_write_zeroes(struct nvme_ns *ns,
 		struct request *req, struct nvme_command *cmnd)
+{
+	if (ns->ctrl->quirks & NVME_QUIRK_DEALLOCATE_ZEROES)
+		return nvme_setup_discard(ns, req, cmnd);
+
+	cmnd->write_zeroes.opcode = nvme_cmd_write_zeroes;
+	cmnd->write_zeroes.nsid = cpu_to_le32(ns->head->ns_id);
+	cmnd->write_zeroes.slba =
+		cpu_to_le64(nvme_sect_to_lba(ns, blk_rq_pos(req)));
+	cmnd->write_zeroes.length =
+		cpu_to_le16((blk_rq_bytes(req) >> ns->lba_shift) - 1);
+	if (nvme_ns_has_pi(ns))
+		cmnd->write_zeroes.control = cpu_to_le16(NVME_RW_PRINFO_PRACT);
+	else
+		cmnd->write_zeroes.control = 0;
+	return BLK_STS_OK;
+}
+
+static inline blk_status_t nvme_setup_rw(struct nvme_ns *ns,
+		struct request *req, struct nvme_command *cmnd,
+		enum nvme_opcode op)
 {
 	struct nvme_ctrl *ctrl = ns->ctrl;
 	u16 control = 0;
@@ -617,10 +801,9 @@
 	if (req->cmd_flags & REQ_RAHEAD)
 		dsmgmt |= NVME_RW_DSM_FREQ_PREFETCH;
 
-	memset(cmnd, 0, sizeof(*cmnd));
-	cmnd->rw.opcode = (rq_data_dir(req) ? nvme_cmd_write : nvme_cmd_read);
+	cmnd->rw.opcode = op;
 	cmnd->rw.nsid = cpu_to_le32(ns->head->ns_id);
-	cmnd->rw.slba = cpu_to_le64(nvme_block_nr(ns, blk_rq_pos(req)));
+	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);
 
 	if (req_op(req) == REQ_OP_WRITE && ctrl->nr_streams)
@@ -637,8 +820,6 @@
 			if (WARN_ON_ONCE(!nvme_ns_has_pi(ns)))
 				return BLK_STS_NOTSUPP;
 			control |= NVME_RW_PRINFO_PRACT;
-		} else if (req_op(req) == REQ_OP_WRITE) {
-			t10_pi_prepare(req, ns->pi_type);
 		}
 
 		switch (ns->pi_type) {
@@ -649,6 +830,8 @@
 		case NVME_NS_DPS_PI_TYPE2:
 			control |= NVME_RW_PRINFO_PRCHK_GUARD |
 					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));
 			break;
 		}
@@ -661,13 +844,6 @@
 
 void nvme_cleanup_cmd(struct request *req)
 {
-	if (blk_integrity_rq(req) && req_op(req) == REQ_OP_READ &&
-	    nvme_req(req)->status == 0) {
-		struct nvme_ns *ns = req->rq_disk->private_data;
-
-		t10_pi_complete(req, ns->pi_type,
-				blk_rq_bytes(req) >> ns->lba_shift);
-	}
 	if (req->rq_flags & RQF_SPECIAL_PAYLOAD) {
 		struct nvme_ns *ns = req->rq_disk->private_data;
 		struct page *page = req->special_vec.bv_page;
@@ -683,37 +859,86 @@
 blk_status_t nvme_setup_cmd(struct nvme_ns *ns, struct request *req,
 		struct nvme_command *cmd)
 {
+	struct nvme_ctrl *ctrl = nvme_req(req)->ctrl;
 	blk_status_t ret = BLK_STS_OK;
 
-	nvme_clear_nvme_request(req);
+	if (!(req->rq_flags & RQF_DONTPREP))
+		nvme_clear_nvme_request(req);
 
+	memset(cmd, 0, sizeof(*cmd));
 	switch (req_op(req)) {
 	case REQ_OP_DRV_IN:
 	case REQ_OP_DRV_OUT:
-		memcpy(cmd, nvme_req(req)->cmd, sizeof(*cmd));
+		nvme_setup_passthrough(req, cmd);
 		break;
 	case REQ_OP_FLUSH:
 		nvme_setup_flush(ns, cmd);
 		break;
+	case REQ_OP_ZONE_RESET_ALL:
+	case REQ_OP_ZONE_RESET:
+		ret = nvme_setup_zone_mgmt_send(ns, req, cmd, NVME_ZONE_RESET);
+		break;
+	case REQ_OP_ZONE_OPEN:
+		ret = nvme_setup_zone_mgmt_send(ns, req, cmd, NVME_ZONE_OPEN);
+		break;
+	case REQ_OP_ZONE_CLOSE:
+		ret = nvme_setup_zone_mgmt_send(ns, req, cmd, NVME_ZONE_CLOSE);
+		break;
+	case REQ_OP_ZONE_FINISH:
+		ret = nvme_setup_zone_mgmt_send(ns, req, cmd, NVME_ZONE_FINISH);
+		break;
 	case REQ_OP_WRITE_ZEROES:
-		/* currently only aliased to deallocate for a few ctrls: */
+		ret = nvme_setup_write_zeroes(ns, req, cmd);
+		break;
 	case REQ_OP_DISCARD:
 		ret = nvme_setup_discard(ns, req, cmd);
 		break;
 	case REQ_OP_READ:
+		ret = nvme_setup_rw(ns, req, cmd, nvme_cmd_read);
+		break;
 	case REQ_OP_WRITE:
-		ret = nvme_setup_rw(ns, req, cmd);
+		ret = nvme_setup_rw(ns, req, cmd, nvme_cmd_write);
+		break;
+	case REQ_OP_ZONE_APPEND:
+		ret = nvme_setup_rw(ns, req, cmd, nvme_cmd_zone_append);
 		break;
 	default:
 		WARN_ON_ONCE(1);
 		return BLK_STS_IOERR;
 	}
 
-	cmd->common.command_id = req->tag;
+	if (!(ctrl->quirks & NVME_QUIRK_SKIP_CID_GEN))
+		nvme_req(req)->genctr++;
+	cmd->common.command_id = nvme_cid(req);
 	trace_nvme_setup_cmd(req, cmd);
 	return ret;
 }
 EXPORT_SYMBOL_GPL(nvme_setup_cmd);
+
+static void nvme_end_sync_rq(struct request *rq, blk_status_t error)
+{
+	struct completion *waiting = rq->end_io_data;
+
+	rq->end_io_data = NULL;
+	complete(waiting);
+}
+
+static void nvme_execute_rq_polled(struct request_queue *q,
+		struct gendisk *bd_disk, struct request *rq, int at_head)
+{
+	DECLARE_COMPLETION_ONSTACK(wait);
+
+	WARN_ON_ONCE(!test_bit(QUEUE_FLAG_POLL, &q->queue_flags));
+
+	rq->cmd_flags |= REQ_HIPRI;
+	rq->end_io_data = &wait;
+	blk_execute_rq_nowait(q, bd_disk, rq, at_head, nvme_end_sync_rq);
+
+	while (!completion_done(&wait)) {
+		blk_poll(q, request_to_qc_t(rq->mq_hctx, rq), true);
+		cond_resched();
+	}
+}
 
 /*
  * Returns 0 on success.  If the result is negative, it's a Linux error code;
@@ -722,16 +947,20 @@
 int __nvme_submit_sync_cmd(struct request_queue *q, struct nvme_command *cmd,
 		union nvme_result *result, void *buffer, unsigned bufflen,
 		unsigned timeout, int qid, int at_head,
-		blk_mq_req_flags_t flags)
+		blk_mq_req_flags_t flags, bool poll)
 {
 	struct request *req;
 	int ret;
 
-	req = nvme_alloc_request(q, cmd, flags, qid);
+	if (qid == NVME_QID_ANY)
+		req = nvme_alloc_request(q, cmd, flags);
+	else
+		req = nvme_alloc_request_qid(q, cmd, flags, qid);
 	if (IS_ERR(req))
 		return PTR_ERR(req);
 
-	req->timeout = timeout ? timeout : ADMIN_TIMEOUT;
+	if (timeout)
+		req->timeout = timeout;
 
 	if (buffer && bufflen) {
 		ret = blk_rq_map_kern(q, req, buffer, bufflen, GFP_KERNEL);
@@ -739,7 +968,10 @@
 			goto out;
 	}
 
-	blk_execute_rq(req->q, NULL, req, at_head);
+	if (poll)
+		nvme_execute_rq_polled(req->q, NULL, req, at_head);
+	else
+		blk_execute_rq(req->q, NULL, req, at_head);
 	if (result)
 		*result = nvme_req(req)->result;
 	if (nvme_req(req)->flags & NVME_REQ_CANCELLED)
@@ -756,7 +988,7 @@
 		void *buffer, unsigned bufflen)
 {
 	return __nvme_submit_sync_cmd(q, cmd, NULL, buffer, bufflen, 0,
-			NVME_QID_ANY, 0, 0);
+			NVME_QID_ANY, 0, 0, false);
 }
 EXPORT_SYMBOL_GPL(nvme_submit_sync_cmd);
 
@@ -794,10 +1026,97 @@
 	return ERR_PTR(ret);
 }
 
+static u32 nvme_known_admin_effects(u8 opcode)
+{
+	switch (opcode) {
+	case nvme_admin_format_nvm:
+		return NVME_CMD_EFFECTS_LBCC | NVME_CMD_EFFECTS_NCC |
+			NVME_CMD_EFFECTS_CSE_MASK;
+	case nvme_admin_sanitize_nvm:
+		return NVME_CMD_EFFECTS_LBCC | NVME_CMD_EFFECTS_CSE_MASK;
+	default:
+		break;
+	}
+	return 0;
+}
+
+u32 nvme_command_effects(struct nvme_ctrl *ctrl, struct nvme_ns *ns, u8 opcode)
+{
+	u32 effects = 0;
+
+	if (ns) {
+		if (ns->head->effects)
+			effects = le32_to_cpu(ns->head->effects->iocs[opcode]);
+		if (effects & ~(NVME_CMD_EFFECTS_CSUPP | NVME_CMD_EFFECTS_LBCC))
+			dev_warn(ctrl->device,
+				 "IO command:%02x has unhandled effects:%08x\n",
+				 opcode, effects);
+		return 0;
+	}
+
+	if (ctrl->effects)
+		effects = le32_to_cpu(ctrl->effects->acs[opcode]);
+	effects |= nvme_known_admin_effects(opcode);
+
+	return effects;
+}
+EXPORT_SYMBOL_NS_GPL(nvme_command_effects, NVME_TARGET_PASSTHRU);
+
+static u32 nvme_passthru_start(struct nvme_ctrl *ctrl, struct nvme_ns *ns,
+			       u8 opcode)
+{
+	u32 effects = nvme_command_effects(ctrl, ns, opcode);
+
+	/*
+	 * For simplicity, IO to all namespaces is quiesced even if the command
+	 * effects say only one namespace is affected.
+	 */
+	if (effects & NVME_CMD_EFFECTS_CSE_MASK) {
+		mutex_lock(&ctrl->scan_lock);
+		mutex_lock(&ctrl->subsys->lock);
+		nvme_mpath_start_freeze(ctrl->subsys);
+		nvme_mpath_wait_freeze(ctrl->subsys);
+		nvme_start_freeze(ctrl);
+		nvme_wait_freeze(ctrl);
+	}
+	return effects;
+}
+
+static void nvme_passthru_end(struct nvme_ctrl *ctrl, u32 effects)
+{
+	if (effects & NVME_CMD_EFFECTS_CSE_MASK) {
+		nvme_unfreeze(ctrl);
+		nvme_mpath_unfreeze(ctrl->subsys);
+		mutex_unlock(&ctrl->subsys->lock);
+		nvme_remove_invalid_namespaces(ctrl, NVME_NSID_ALL);
+		mutex_unlock(&ctrl->scan_lock);
+	}
+	if (effects & NVME_CMD_EFFECTS_CCC)
+		nvme_init_identify(ctrl);
+	if (effects & (NVME_CMD_EFFECTS_NIC | NVME_CMD_EFFECTS_NCC)) {
+		nvme_queue_scan(ctrl);
+		flush_work(&ctrl->scan_work);
+	}
+}
+
+void nvme_execute_passthru_rq(struct request *rq)
+{
+	struct nvme_command *cmd = nvme_req(rq)->cmd;
+	struct nvme_ctrl *ctrl = nvme_req(rq)->ctrl;
+	struct nvme_ns *ns = rq->q->queuedata;
+	struct gendisk *disk = ns ? ns->disk : NULL;
+	u32 effects;
+
+	effects = nvme_passthru_start(ctrl, ns, cmd->common.opcode);
+	blk_execute_rq(rq->q, disk, rq, 0);
+	nvme_passthru_end(ctrl, effects);
+}
+EXPORT_SYMBOL_NS_GPL(nvme_execute_passthru_rq, NVME_TARGET_PASSTHRU);
+
 static int nvme_submit_user_cmd(struct request_queue *q,
 		struct nvme_command *cmd, void __user *ubuffer,
 		unsigned bufflen, void __user *meta_buffer, unsigned meta_len,
-		u32 meta_seed, u32 *result, unsigned timeout)
+		u32 meta_seed, u64 *result, unsigned timeout)
 {
 	bool write = nvme_is_write(cmd);
 	struct nvme_ns *ns = q->queuedata;
@@ -807,11 +1126,12 @@
 	void *meta = NULL;
 	int ret;
 
-	req = nvme_alloc_request(q, cmd, 0, NVME_QID_ANY);
+	req = nvme_alloc_request(q, cmd, 0);
 	if (IS_ERR(req))
 		return PTR_ERR(req);
 
-	req->timeout = timeout ? timeout : ADMIN_TIMEOUT;
+	if (timeout)
+		req->timeout = timeout;
 	nvme_req(req)->flags |= NVME_REQ_USERCMD;
 
 	if (ubuffer && bufflen) {
@@ -832,13 +1152,13 @@
 		}
 	}
 
-	blk_execute_rq(req->q, disk, req, 0);
+	nvme_execute_passthru_rq(req);
 	if (nvme_req(req)->flags & NVME_REQ_CANCELLED)
 		ret = -EINTR;
 	else
 		ret = nvme_req(req)->status;
 	if (result)
-		*result = le32_to_cpu(nvme_req(req)->result.u32);
+		*result = le64_to_cpu(nvme_req(req)->result.u64);
 	if (meta && !ret && !write) {
 		if (copy_to_user(meta_buffer, meta, meta_len))
 			ret = -EFAULT;
@@ -867,21 +1187,22 @@
 		return;
 	}
 
+	ctrl->comp_seen = false;
 	spin_lock_irqsave(&ctrl->lock, flags);
 	if (ctrl->state == NVME_CTRL_LIVE ||
 	    ctrl->state == NVME_CTRL_CONNECTING)
 		startka = true;
 	spin_unlock_irqrestore(&ctrl->lock, flags);
 	if (startka)
-		schedule_delayed_work(&ctrl->ka_work, ctrl->kato * HZ);
+		queue_delayed_work(nvme_wq, &ctrl->ka_work, ctrl->kato * HZ);
 }
 
 static int nvme_keep_alive(struct nvme_ctrl *ctrl)
 {
 	struct request *rq;
 
-	rq = nvme_alloc_request(ctrl->admin_q, &ctrl->ka_cmd, BLK_MQ_REQ_RESERVED,
-			NVME_QID_ANY);
+	rq = nvme_alloc_request(ctrl->admin_q, &ctrl->ka_cmd,
+			BLK_MQ_REQ_RESERVED);
 	if (IS_ERR(rq))
 		return PTR_ERR(rq);
 
@@ -897,6 +1218,15 @@
 {
 	struct nvme_ctrl *ctrl = container_of(to_delayed_work(work),
 			struct nvme_ctrl, ka_work);
+	bool comp_seen = ctrl->comp_seen;
+
+	if ((ctrl->ctratt & NVME_CTRL_ATTR_TBKAS) && comp_seen) {
+		dev_dbg(ctrl->device,
+			"reschedule traffic based keep-alive timer\n");
+		ctrl->comp_seen = false;
+		queue_delayed_work(nvme_wq, &ctrl->ka_work, ctrl->kato * HZ);
+		return;
+	}
 
 	if (nvme_keep_alive(ctrl)) {
 		/* allocation failure, reset the controller */
@@ -911,7 +1241,7 @@
 	if (unlikely(ctrl->kato == 0))
 		return;
 
-	schedule_delayed_work(&ctrl->ka_work, ctrl->kato * HZ);
+	queue_delayed_work(nvme_wq, &ctrl->ka_work, ctrl->kato * HZ);
 }
 
 void nvme_stop_keep_alive(struct nvme_ctrl *ctrl)
@@ -956,14 +1286,75 @@
 	return error;
 }
 
+static bool nvme_multi_css(struct nvme_ctrl *ctrl)
+{
+	return (ctrl->ctrl_config & NVME_CC_CSS_MASK) == NVME_CC_CSS_CSI;
+}
+
+static int nvme_process_ns_desc(struct nvme_ctrl *ctrl, struct nvme_ns_ids *ids,
+		struct nvme_ns_id_desc *cur, bool *csi_seen)
+{
+	const char *warn_str = "ctrl returned bogus length:";
+	void *data = cur;
+
+	switch (cur->nidt) {
+	case NVME_NIDT_EUI64:
+		if (cur->nidl != NVME_NIDT_EUI64_LEN) {
+			dev_warn(ctrl->device, "%s %d for NVME_NIDT_EUI64\n",
+				 warn_str, cur->nidl);
+			return -1;
+		}
+		if (ctrl->quirks & NVME_QUIRK_BOGUS_NID)
+			return NVME_NIDT_EUI64_LEN;
+		memcpy(ids->eui64, data + sizeof(*cur), NVME_NIDT_EUI64_LEN);
+		return NVME_NIDT_EUI64_LEN;
+	case NVME_NIDT_NGUID:
+		if (cur->nidl != NVME_NIDT_NGUID_LEN) {
+			dev_warn(ctrl->device, "%s %d for NVME_NIDT_NGUID\n",
+				 warn_str, cur->nidl);
+			return -1;
+		}
+		if (ctrl->quirks & NVME_QUIRK_BOGUS_NID)
+			return NVME_NIDT_NGUID_LEN;
+		memcpy(ids->nguid, data + sizeof(*cur), NVME_NIDT_NGUID_LEN);
+		return NVME_NIDT_NGUID_LEN;
+	case NVME_NIDT_UUID:
+		if (cur->nidl != NVME_NIDT_UUID_LEN) {
+			dev_warn(ctrl->device, "%s %d for NVME_NIDT_UUID\n",
+				 warn_str, cur->nidl);
+			return -1;
+		}
+		if (ctrl->quirks & NVME_QUIRK_BOGUS_NID)
+			return NVME_NIDT_UUID_LEN;
+		uuid_copy(&ids->uuid, data + sizeof(*cur));
+		return NVME_NIDT_UUID_LEN;
+	case NVME_NIDT_CSI:
+		if (cur->nidl != NVME_NIDT_CSI_LEN) {
+			dev_warn(ctrl->device, "%s %d for NVME_NIDT_CSI\n",
+				 warn_str, cur->nidl);
+			return -1;
+		}
+		memcpy(&ids->csi, data + sizeof(*cur), NVME_NIDT_CSI_LEN);
+		*csi_seen = true;
+		return NVME_NIDT_CSI_LEN;
+	default:
+		/* Skip unknown types */
+		return cur->nidl;
+	}
+}
+
 static int nvme_identify_ns_descs(struct nvme_ctrl *ctrl, unsigned nsid,
 		struct nvme_ns_ids *ids)
 {
 	struct nvme_command c = { };
-	int status;
+	bool csi_seen = false;
+	int status, pos, len;
 	void *data;
-	int pos;
-	int len;
+
+	if (ctrl->vs < NVME_VS(1, 3, 0) && !nvme_multi_css(ctrl))
+		return 0;
+	if (ctrl->quirks & NVME_QUIRK_NO_NS_DESC_LIST)
+		return 0;
 
 	c.identify.opcode = nvme_admin_identify;
 	c.identify.nsid = cpu_to_le32(nsid);
@@ -975,8 +1366,11 @@
 
 	status = nvme_submit_sync_cmd(ctrl->admin_q, &c, data,
 				      NVME_IDENTIFY_DATA_SIZE);
-	if (status)
+	if (status) {
+		dev_warn(ctrl->device,
+			"Identify Descriptors failed (%d)\n", status);
 		goto free_data;
+	}
 
 	for (pos = 0; pos < NVME_IDENTIFY_DATA_SIZE; pos += len) {
 		struct nvme_ns_id_desc *cur = data + pos;
@@ -984,65 +1378,27 @@
 		if (cur->nidl == 0)
 			break;
 
-		switch (cur->nidt) {
-		case NVME_NIDT_EUI64:
-			if (cur->nidl != NVME_NIDT_EUI64_LEN) {
-				dev_warn(ctrl->device,
-					 "ctrl returned bogus length: %d for NVME_NIDT_EUI64\n",
-					 cur->nidl);
-				goto free_data;
-			}
-			len = NVME_NIDT_EUI64_LEN;
-			memcpy(ids->eui64, data + pos + sizeof(*cur), len);
+		len = nvme_process_ns_desc(ctrl, ids, cur, &csi_seen);
+		if (len < 0)
 			break;
-		case NVME_NIDT_NGUID:
-			if (cur->nidl != NVME_NIDT_NGUID_LEN) {
-				dev_warn(ctrl->device,
-					 "ctrl returned bogus length: %d for NVME_NIDT_NGUID\n",
-					 cur->nidl);
-				goto free_data;
-			}
-			len = NVME_NIDT_NGUID_LEN;
-			memcpy(ids->nguid, data + pos + sizeof(*cur), len);
-			break;
-		case NVME_NIDT_UUID:
-			if (cur->nidl != NVME_NIDT_UUID_LEN) {
-				dev_warn(ctrl->device,
-					 "ctrl returned bogus length: %d for NVME_NIDT_UUID\n",
-					 cur->nidl);
-				goto free_data;
-			}
-			len = NVME_NIDT_UUID_LEN;
-			uuid_copy(&ids->uuid, data + pos + sizeof(*cur));
-			break;
-		default:
-			/* Skip unnkown types */
-			len = cur->nidl;
-			break;
-		}
 
 		len += sizeof(*cur);
 	}
+
+	if (nvme_multi_css(ctrl) && !csi_seen) {
+		dev_warn(ctrl->device, "Command set not reported for nsid:%d\n",
+			 nsid);
+		status = -EINVAL;
+	}
+
 free_data:
 	kfree(data);
 	return status;
 }
 
-static int nvme_identify_ns_list(struct nvme_ctrl *dev, unsigned nsid, __le32 *ns_list)
+static int nvme_identify_ns(struct nvme_ctrl *ctrl, unsigned nsid,
+			struct nvme_ns_ids *ids, struct nvme_id_ns **id)
 {
-	struct nvme_command c = { };
-
-	c.identify.opcode = nvme_admin_identify;
-	c.identify.cns = NVME_ID_CNS_NS_ACTIVE_LIST;
-	c.identify.nsid = cpu_to_le32(nsid);
-	return nvme_submit_sync_cmd(dev->admin_q, &c, ns_list,
-				    NVME_IDENTIFY_DATA_SIZE);
-}
-
-static struct nvme_id_ns *nvme_identify_ns(struct nvme_ctrl *ctrl,
-		unsigned nsid)
-{
-	struct nvme_id_ns *id;
 	struct nvme_command c = { };
 	int error;
 
@@ -1051,38 +1407,76 @@
 	c.identify.nsid = cpu_to_le32(nsid);
 	c.identify.cns = NVME_ID_CNS_NS;
 
-	id = kmalloc(sizeof(*id), GFP_KERNEL);
-	if (!id)
-		return NULL;
+	*id = kmalloc(sizeof(**id), GFP_KERNEL);
+	if (!*id)
+		return -ENOMEM;
 
-	error = nvme_submit_sync_cmd(ctrl->admin_q, &c, id, sizeof(*id));
+	error = nvme_submit_sync_cmd(ctrl->admin_q, &c, *id, sizeof(**id));
 	if (error) {
-		dev_warn(ctrl->device, "Identify namespace failed\n");
-		kfree(id);
-		return NULL;
+		dev_warn(ctrl->device, "Identify namespace failed (%d)\n", error);
+		goto out_free_id;
 	}
 
-	return id;
+	error = NVME_SC_INVALID_NS | NVME_SC_DNR;
+	if ((*id)->ncap == 0) /* namespace not allocated or attached */
+		goto out_free_id;
+
+
+	if (ctrl->quirks & NVME_QUIRK_BOGUS_NID) {
+		dev_info(ctrl->device,
+			 "Ignoring bogus Namespace Identifiers\n");
+	} else {
+		if (ctrl->vs >= NVME_VS(1, 1, 0) &&
+		    !memchr_inv(ids->eui64, 0, sizeof(ids->eui64)))
+			memcpy(ids->eui64, (*id)->eui64, sizeof(ids->eui64));
+		if (ctrl->vs >= NVME_VS(1, 2, 0) &&
+		    !memchr_inv(ids->nguid, 0, sizeof(ids->nguid)))
+			memcpy(ids->nguid, (*id)->nguid, sizeof(ids->nguid));
+	}
+
+	return 0;
+
+out_free_id:
+	kfree(*id);
+	return error;
 }
 
-static int nvme_set_features(struct nvme_ctrl *dev, unsigned fid, unsigned dword11,
-		      void *buffer, size_t buflen, u32 *result)
+static int nvme_features(struct nvme_ctrl *dev, u8 op, unsigned int fid,
+		unsigned int dword11, void *buffer, size_t buflen, u32 *result)
 {
 	union nvme_result res = { 0 };
 	struct nvme_command c;
 	int ret;
 
 	memset(&c, 0, sizeof(c));
-	c.features.opcode = nvme_admin_set_features;
+	c.features.opcode = op;
 	c.features.fid = cpu_to_le32(fid);
 	c.features.dword11 = cpu_to_le32(dword11);
 
 	ret = __nvme_submit_sync_cmd(dev->admin_q, &c, &res,
-			buffer, buflen, 0, NVME_QID_ANY, 0, 0);
+			buffer, buflen, 0, NVME_QID_ANY, 0, 0, false);
 	if (ret >= 0 && result)
 		*result = le32_to_cpu(res.u32);
 	return ret;
 }
+
+int nvme_set_features(struct nvme_ctrl *dev, unsigned int fid,
+		      unsigned int dword11, void *buffer, size_t buflen,
+		      u32 *result)
+{
+	return nvme_features(dev, nvme_admin_set_features, fid, dword11, buffer,
+			     buflen, result);
+}
+EXPORT_SYMBOL_GPL(nvme_set_features);
+
+int nvme_get_features(struct nvme_ctrl *dev, unsigned int fid,
+		      unsigned int dword11, void *buffer, size_t buflen,
+		      u32 *result)
+{
+	return nvme_features(dev, nvme_admin_get_features, fid, dword11, buffer,
+			     buflen, result);
+}
+EXPORT_SYMBOL_GPL(nvme_get_features);
 
 int nvme_set_queue_count(struct nvme_ctrl *ctrl, int *count)
 {
@@ -1113,7 +1507,8 @@
 EXPORT_SYMBOL_GPL(nvme_set_queue_count);
 
 #define NVME_AEN_SUPPORTED \
-	(NVME_AEN_CFG_NS_ATTR | NVME_AEN_CFG_FW_ACT | NVME_AEN_CFG_ANA_CHANGE)
+	(NVME_AEN_CFG_NS_ATTR | NVME_AEN_CFG_FW_ACT | \
+	 NVME_AEN_CFG_ANA_CHANGE | NVME_AEN_CFG_DISC_CHANGE)
 
 static void nvme_enable_aen(struct nvme_ctrl *ctrl)
 {
@@ -1128,6 +1523,20 @@
 	if (status)
 		dev_warn(ctrl->device, "Failed to configure AEN (cfg %x)\n",
 			 supported_aens);
+
+	queue_work(nvme_wq, &ctrl->async_event_work);
+}
+
+/*
+ * Convert integer values from ioctl structures to user pointers, silently
+ * ignoring the upper bits in the compat case to match behaviour of 32-bit
+ * kernels.
+ */
+static void __user *nvme_to_user_ptr(uintptr_t ptrval)
+{
+	if (in_compat_syscall())
+		ptrval = (compat_uptr_t)ptrval;
+	return (void __user *)ptrval;
 }
 
 static int nvme_submit_io(struct nvme_ns *ns, struct nvme_user_io __user *uio)
@@ -1152,10 +1561,23 @@
 	}
 
 	length = (io.nblocks + 1) << ns->lba_shift;
-	meta_len = (io.nblocks + 1) * ns->ms;
-	metadata = (void __user *)(uintptr_t)io.metadata;
 
-	if (ns->ext) {
+	if ((io.control & NVME_RW_PRINFO_PRACT) &&
+	    ns->ms == sizeof(struct t10_pi_tuple)) {
+		/*
+		 * Protection information is stripped/inserted by the
+		 * controller.
+		 */
+		if (nvme_to_user_ptr(io.metadata))
+			return -EINVAL;
+		meta_len = 0;
+		metadata = NULL;
+	} else {
+		meta_len = (io.nblocks + 1) * ns->ms;
+		metadata = nvme_to_user_ptr(io.metadata);
+	}
+
+	if (ns->features & NVME_NS_EXT_LBAS) {
 		length += meta_len;
 		meta_len = 0;
 	} else if (meta_len) {
@@ -1176,91 +1598,8 @@
 	c.rw.appmask = cpu_to_le16(io.appmask);
 
 	return nvme_submit_user_cmd(ns->queue, &c,
-			(void __user *)(uintptr_t)io.addr, length,
-			metadata, meta_len, io.slba, NULL, 0);
-}
-
-static u32 nvme_known_admin_effects(u8 opcode)
-{
-	switch (opcode) {
-	case nvme_admin_format_nvm:
-		return NVME_CMD_EFFECTS_CSUPP | NVME_CMD_EFFECTS_LBCC |
-					NVME_CMD_EFFECTS_CSE_MASK;
-	case nvme_admin_sanitize_nvm:
-		return NVME_CMD_EFFECTS_CSE_MASK;
-	default:
-		break;
-	}
-	return 0;
-}
-
-static u32 nvme_passthru_start(struct nvme_ctrl *ctrl, struct nvme_ns *ns,
-								u8 opcode)
-{
-	u32 effects = 0;
-
-	if (ns) {
-		if (ctrl->effects)
-			effects = le32_to_cpu(ctrl->effects->iocs[opcode]);
-		if (effects & ~NVME_CMD_EFFECTS_CSUPP)
-			dev_warn(ctrl->device,
-				 "IO command:%02x has unhandled effects:%08x\n",
-				 opcode, effects);
-		return 0;
-	}
-
-	if (ctrl->effects)
-		effects = le32_to_cpu(ctrl->effects->acs[opcode]);
-	else
-		effects = nvme_known_admin_effects(opcode);
-
-	/*
-	 * For simplicity, IO to all namespaces is quiesced even if the command
-	 * effects say only one namespace is affected.
-	 */
-	if (effects & (NVME_CMD_EFFECTS_LBCC | NVME_CMD_EFFECTS_CSE_MASK)) {
-		mutex_lock(&ctrl->scan_lock);
-		mutex_lock(&ctrl->subsys->lock);
-		nvme_mpath_start_freeze(ctrl->subsys);
-		nvme_mpath_wait_freeze(ctrl->subsys);
-		nvme_start_freeze(ctrl);
-		nvme_wait_freeze(ctrl);
-	}
-	return effects;
-}
-
-static void nvme_update_formats(struct nvme_ctrl *ctrl)
-{
-	struct nvme_ns *ns;
-
-	down_read(&ctrl->namespaces_rwsem);
-	list_for_each_entry(ns, &ctrl->namespaces, list)
-		if (ns->disk && nvme_revalidate_disk(ns->disk))
-			nvme_set_queue_dying(ns);
-	up_read(&ctrl->namespaces_rwsem);
-
-	nvme_remove_invalid_namespaces(ctrl, NVME_NSID_ALL);
-}
-
-static void nvme_passthru_end(struct nvme_ctrl *ctrl, u32 effects)
-{
-	/*
-	 * Revalidate LBA changes prior to unfreezing. This is necessary to
-	 * prevent memory corruption if a logical block size was changed by
-	 * this command.
-	 */
-	if (effects & NVME_CMD_EFFECTS_LBCC)
-		nvme_update_formats(ctrl);
-	if (effects & (NVME_CMD_EFFECTS_LBCC | NVME_CMD_EFFECTS_CSE_MASK)) {
-		nvme_unfreeze(ctrl);
-		nvme_mpath_unfreeze(ctrl->subsys);
-		mutex_unlock(&ctrl->subsys->lock);
-		mutex_unlock(&ctrl->scan_lock);
-	}
-	if (effects & NVME_CMD_EFFECTS_CCC)
-		nvme_init_identify(ctrl);
-	if (effects & (NVME_CMD_EFFECTS_NIC | NVME_CMD_EFFECTS_NCC))
-		nvme_queue_scan(ctrl);
+			nvme_to_user_ptr(io.addr), length,
+			metadata, meta_len, lower_32_bits(io.slba), NULL, 0);
 }
 
 static int nvme_user_cmd(struct nvme_ctrl *ctrl, struct nvme_ns *ns,
@@ -1269,7 +1608,7 @@
 	struct nvme_passthru_cmd cmd;
 	struct nvme_command c;
 	unsigned timeout = 0;
-	u32 effects;
+	u64 result;
 	int status;
 
 	if (!capable(CAP_SYS_ADMIN))
@@ -1285,22 +1624,64 @@
 	c.common.nsid = cpu_to_le32(cmd.nsid);
 	c.common.cdw2[0] = cpu_to_le32(cmd.cdw2);
 	c.common.cdw2[1] = cpu_to_le32(cmd.cdw3);
-	c.common.cdw10[0] = cpu_to_le32(cmd.cdw10);
-	c.common.cdw10[1] = cpu_to_le32(cmd.cdw11);
-	c.common.cdw10[2] = cpu_to_le32(cmd.cdw12);
-	c.common.cdw10[3] = cpu_to_le32(cmd.cdw13);
-	c.common.cdw10[4] = cpu_to_le32(cmd.cdw14);
-	c.common.cdw10[5] = cpu_to_le32(cmd.cdw15);
+	c.common.cdw10 = cpu_to_le32(cmd.cdw10);
+	c.common.cdw11 = cpu_to_le32(cmd.cdw11);
+	c.common.cdw12 = cpu_to_le32(cmd.cdw12);
+	c.common.cdw13 = cpu_to_le32(cmd.cdw13);
+	c.common.cdw14 = cpu_to_le32(cmd.cdw14);
+	c.common.cdw15 = cpu_to_le32(cmd.cdw15);
 
 	if (cmd.timeout_ms)
 		timeout = msecs_to_jiffies(cmd.timeout_ms);
 
-	effects = nvme_passthru_start(ctrl, ns, cmd.opcode);
 	status = nvme_submit_user_cmd(ns ? ns->queue : ctrl->admin_q, &c,
-			(void __user *)(uintptr_t)cmd.addr, cmd.data_len,
-			(void __user *)(uintptr_t)cmd.metadata, cmd.metadata_len,
+			nvme_to_user_ptr(cmd.addr), cmd.data_len,
+			nvme_to_user_ptr(cmd.metadata), cmd.metadata_len,
+			0, &result, timeout);
+
+	if (status >= 0) {
+		if (put_user(result, &ucmd->result))
+			return -EFAULT;
+	}
+
+	return status;
+}
+
+static int nvme_user_cmd64(struct nvme_ctrl *ctrl, struct nvme_ns *ns,
+			struct nvme_passthru_cmd64 __user *ucmd)
+{
+	struct nvme_passthru_cmd64 cmd;
+	struct nvme_command c;
+	unsigned timeout = 0;
+	int status;
+
+	if (!capable(CAP_SYS_ADMIN))
+		return -EACCES;
+	if (copy_from_user(&cmd, ucmd, sizeof(cmd)))
+		return -EFAULT;
+	if (cmd.flags)
+		return -EINVAL;
+
+	memset(&c, 0, sizeof(c));
+	c.common.opcode = cmd.opcode;
+	c.common.flags = cmd.flags;
+	c.common.nsid = cpu_to_le32(cmd.nsid);
+	c.common.cdw2[0] = cpu_to_le32(cmd.cdw2);
+	c.common.cdw2[1] = cpu_to_le32(cmd.cdw3);
+	c.common.cdw10 = cpu_to_le32(cmd.cdw10);
+	c.common.cdw11 = cpu_to_le32(cmd.cdw11);
+	c.common.cdw12 = cpu_to_le32(cmd.cdw12);
+	c.common.cdw13 = cpu_to_le32(cmd.cdw13);
+	c.common.cdw14 = cpu_to_le32(cmd.cdw14);
+	c.common.cdw15 = cpu_to_le32(cmd.cdw15);
+
+	if (cmd.timeout_ms)
+		timeout = msecs_to_jiffies(cmd.timeout_ms);
+
+	status = nvme_submit_user_cmd(ns ? ns->queue : ctrl->admin_q, &c,
+			nvme_to_user_ptr(cmd.addr), cmd.data_len,
+			nvme_to_user_ptr(cmd.metadata), cmd.metadata_len,
 			0, &cmd.result, timeout);
-	nvme_passthru_end(ctrl, effects);
 
 	if (status >= 0) {
 		if (put_user(cmd.result, &ucmd->result))
@@ -1314,7 +1695,7 @@
  * Issue ioctl requests on the first available path.  Note that unlike normal
  * block layer requests we will not retry failed request on another controller.
  */
-static struct nvme_ns *nvme_get_ns_from_disk(struct gendisk *disk,
+struct nvme_ns *nvme_get_ns_from_disk(struct gendisk *disk,
 		struct nvme_ns_head **head, int *srcu_idx)
 {
 #ifdef CONFIG_NVME_MULTIPATH
@@ -1334,10 +1715,45 @@
 	return disk->private_data;
 }
 
-static void nvme_put_ns_from_disk(struct nvme_ns_head *head, int idx)
+void nvme_put_ns_from_disk(struct nvme_ns_head *head, int idx)
 {
 	if (head)
 		srcu_read_unlock(&head->srcu, idx);
+}
+
+static bool is_ctrl_ioctl(unsigned int cmd)
+{
+	if (cmd == NVME_IOCTL_ADMIN_CMD || cmd == NVME_IOCTL_ADMIN64_CMD)
+		return true;
+	if (is_sed_ioctl(cmd))
+		return true;
+	return false;
+}
+
+static int nvme_handle_ctrl_ioctl(struct nvme_ns *ns, unsigned int cmd,
+				  void __user *argp,
+				  struct nvme_ns_head *head,
+				  int srcu_idx)
+{
+	struct nvme_ctrl *ctrl = ns->ctrl;
+	int ret;
+
+	nvme_get_ctrl(ns->ctrl);
+	nvme_put_ns_from_disk(head, srcu_idx);
+
+	switch (cmd) {
+	case NVME_IOCTL_ADMIN_CMD:
+		ret = nvme_user_cmd(ctrl, NULL, argp);
+		break;
+	case NVME_IOCTL_ADMIN64_CMD:
+		ret = nvme_user_cmd64(ctrl, NULL, argp);
+		break;
+	default:
+		ret = sed_ioctl(ctrl->opal_dev, cmd, argp);
+		break;
+	}
+	nvme_put_ctrl(ctrl);
+	return ret;
 }
 
 static int nvme_ioctl(struct block_device *bdev, fmode_t mode,
@@ -1357,20 +1773,8 @@
 	 * seperately and drop the ns SRCU reference early.  This avoids a
 	 * deadlock when deleting namespaces using the passthrough interface.
 	 */
-	if (cmd == NVME_IOCTL_ADMIN_CMD || is_sed_ioctl(cmd)) {
-		struct nvme_ctrl *ctrl = ns->ctrl;
-
-		nvme_get_ctrl(ns->ctrl);
-		nvme_put_ns_from_disk(head, srcu_idx);
-
-		if (cmd == NVME_IOCTL_ADMIN_CMD)
-			ret = nvme_user_cmd(ctrl, NULL, argp);
-		else
-			ret = sed_ioctl(ctrl->opal_dev, cmd, argp);
-
-		nvme_put_ctrl(ctrl);
-		return ret;
-	}
+	if (is_ctrl_ioctl(cmd))
+		return nvme_handle_ctrl_ioctl(ns, cmd, argp, head, srcu_idx);
 
 	switch (cmd) {
 	case NVME_IOCTL_ID:
@@ -1383,6 +1787,9 @@
 	case NVME_IOCTL_SUBMIT_IO:
 		ret = nvme_submit_io(ns, argp);
 		break;
+	case NVME_IOCTL_IO64_CMD:
+		ret = nvme_user_cmd64(ns->ctrl, ns, argp);
+		break;
 	default:
 		if (ns->ndev)
 			ret = nvme_nvm_ioctl(ns, cmd, arg);
@@ -1393,6 +1800,47 @@
 	nvme_put_ns_from_disk(head, srcu_idx);
 	return ret;
 }
+
+#ifdef CONFIG_COMPAT
+struct nvme_user_io32 {
+	__u8	opcode;
+	__u8	flags;
+	__u16	control;
+	__u16	nblocks;
+	__u16	rsvd;
+	__u64	metadata;
+	__u64	addr;
+	__u64	slba;
+	__u32	dsmgmt;
+	__u32	reftag;
+	__u16	apptag;
+	__u16	appmask;
+} __attribute__((__packed__));
+
+#define NVME_IOCTL_SUBMIT_IO32	_IOW('N', 0x42, struct nvme_user_io32)
+
+static int nvme_compat_ioctl(struct block_device *bdev, fmode_t mode,
+		unsigned int cmd, unsigned long arg)
+{
+	/*
+	 * Corresponds to the difference of NVME_IOCTL_SUBMIT_IO
+	 * between 32 bit programs and 64 bit kernel.
+	 * The cause is that the results of sizeof(struct nvme_user_io),
+	 * which is used to define NVME_IOCTL_SUBMIT_IO,
+	 * are not same between 32 bit compiler and 64 bit compiler.
+	 * NVME_IOCTL_SUBMIT_IO32 is for 64 bit kernel handling
+	 * NVME_IOCTL_SUBMIT_IO issued from 32 bit programs.
+	 * Other IOCTL numbers are same between 32 bit and 64 bit.
+	 * So there is nothing to do regarding to other IOCTL numbers.
+	 */
+	if (cmd == NVME_IOCTL_SUBMIT_IO32)
+		return nvme_ioctl(bdev, mode, NVME_IOCTL_SUBMIT_IO, arg);
+
+	return nvme_ioctl(bdev, mode, cmd, arg);
+}
+#else
+#define nvme_compat_ioctl	NULL
+#endif /* CONFIG_COMPAT */
 
 static int nvme_open(struct block_device *bdev, fmode_t mode)
 {
@@ -1434,7 +1882,8 @@
 }
 
 #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, u16 ms, u8 pi_type,
+				u32 max_integrity_segments)
 {
 	struct blk_integrity integrity;
 
@@ -1457,24 +1906,19 @@
 	}
 	integrity.tuple_size = ms;
 	blk_integrity_register(disk, &integrity);
-	blk_queue_max_integrity_segments(disk->queue, 1);
+	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, u16 ms, u8 pi_type,
+				u32 max_integrity_segments)
 {
 }
 #endif /* CONFIG_BLK_DEV_INTEGRITY */
 
-static void nvme_set_chunk_size(struct nvme_ns *ns)
-{
-	u32 chunk_size = (((u32)ns->noiob) << (ns->lba_shift - 9));
-	blk_queue_chunk_sectors(ns->queue, rounddown_pow_of_two(chunk_size));
-}
-
-static void nvme_config_discard(struct nvme_ns *ns)
+static void nvme_config_discard(struct gendisk *disk, struct nvme_ns *ns)
 {
 	struct nvme_ctrl *ctrl = ns->ctrl;
-	struct request_queue *queue = ns->queue;
+	struct request_queue *queue = disk->queue;
 	u32 size = queue_logical_block_size(queue);
 
 	if (!(ctrl->oncs & NVME_CTRL_ONCS_DSM)) {
@@ -1502,23 +1946,18 @@
 		blk_queue_max_write_zeroes_sectors(queue, UINT_MAX);
 }
 
-static void nvme_report_ns_ids(struct nvme_ctrl *ctrl, unsigned int nsid,
-		struct nvme_id_ns *id, struct nvme_ns_ids *ids)
+/*
+ * Even though NVMe spec explicitly states that MDTS is not applicable to the
+ * write-zeroes, we are cautious and limit the size to the controllers
+ * max_hw_sectors value, which is based on the MDTS field and possibly other
+ * limiting factors.
+ */
+static void nvme_config_write_zeroes(struct request_queue *q,
+		struct nvme_ctrl *ctrl)
 {
-	memset(ids, 0, sizeof(*ids));
-
-	if (ctrl->vs >= NVME_VS(1, 1, 0))
-		memcpy(ids->eui64, id->eui64, sizeof(id->eui64));
-	if (ctrl->vs >= NVME_VS(1, 2, 0))
-		memcpy(ids->nguid, id->nguid, sizeof(id->nguid));
-	if (ctrl->vs >= NVME_VS(1, 3, 0)) {
-		 /* Don't treat error as fatal we potentially
-		  * already have a NGUID or EUI-64
-		  */
-		if (nvme_identify_ns_descs(ctrl, nsid, ids))
-			dev_warn(ctrl->device,
-				 "%s: Identify Descriptors failed\n", __func__);
-	}
+	if ((ctrl->oncs & NVME_CTRL_ONCS_WRITE_ZEROES) &&
+	    !(ctrl->quirks & NVME_QUIRK_DISABLE_WRITE_ZEROES))
+		blk_queue_max_write_zeroes_sectors(q, ctrl->max_hw_sectors);
 }
 
 static bool nvme_ns_ids_valid(struct nvme_ns_ids *ids)
@@ -1532,110 +1971,250 @@
 {
 	return uuid_equal(&a->uuid, &b->uuid) &&
 		memcmp(&a->nguid, &b->nguid, sizeof(a->nguid)) == 0 &&
-		memcmp(&a->eui64, &b->eui64, sizeof(a->eui64)) == 0;
+		memcmp(&a->eui64, &b->eui64, sizeof(a->eui64)) == 0 &&
+		a->csi == b->csi;
 }
 
-static void nvme_update_disk_info(struct gendisk *disk,
-		struct nvme_ns *ns, struct nvme_id_ns *id)
+static int nvme_setup_streams_ns(struct nvme_ctrl *ctrl, struct nvme_ns *ns,
+				 u32 *phys_bs, u32 *io_opt)
 {
-	sector_t capacity = le64_to_cpup(&id->nsze) << (ns->lba_shift - 9);
-	unsigned short bs = 1 << ns->lba_shift;
+	struct streams_directive_params s;
+	int ret;
 
-	if (ns->lba_shift > PAGE_SHIFT) {
-		/* unsupported block size, set capacity to 0 later */
-		bs = (1 << 9);
+	if (!ctrl->nr_streams)
+		return 0;
+
+	ret = nvme_get_stream_params(ctrl, &s, ns->head->ns_id);
+	if (ret)
+		return ret;
+
+	ns->sws = le32_to_cpu(s.sws);
+	ns->sgs = le16_to_cpu(s.sgs);
+
+	if (ns->sws) {
+		*phys_bs = ns->sws * (1 << ns->lba_shift);
+		if (ns->sgs)
+			*io_opt = *phys_bs * ns->sgs;
 	}
-	blk_mq_freeze_queue(disk->queue);
-	blk_integrity_unregister(disk);
 
-	blk_queue_logical_block_size(disk->queue, bs);
-	blk_queue_physical_block_size(disk->queue, bs);
-	blk_queue_io_min(disk->queue, bs);
-
-	if (ns->ms && !ns->ext &&
-	    (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)
-		capacity = 0;
-
-	set_capacity(disk, capacity);
-	nvme_config_discard(ns);
-
-	if (id->nsattr & (1 << 0))
-		set_disk_ro(disk, true);
-	else
-		set_disk_ro(disk, false);
-
-	blk_mq_unfreeze_queue(disk->queue);
+	return 0;
 }
 
-static void __nvme_revalidate_disk(struct gendisk *disk, struct nvme_id_ns *id)
+static int nvme_configure_metadata(struct nvme_ns *ns, struct nvme_id_ns *id)
 {
-	struct nvme_ns *ns = disk->private_data;
+	struct nvme_ctrl *ctrl = ns->ctrl;
 
 	/*
-	 * If identify namespace failed, use default 512 byte block size so
-	 * block layer can use before failing read/write for 0 capacity.
+	 * The PI implementation requires the metadata size to be equal to the
+	 * t10 pi tuple size.
 	 */
-	ns->lba_shift = id->lbaf[id->flbas & NVME_NS_FLBAS_LBA_MASK].ds;
-	if (ns->lba_shift == 0)
-		ns->lba_shift = 9;
-	ns->noiob = le16_to_cpu(id->noiob);
 	ns->ms = le16_to_cpu(id->lbaf[id->flbas & NVME_NS_FLBAS_LBA_MASK].ms);
-	ns->ext = ns->ms && (id->flbas & NVME_NS_FLBAS_META_EXT);
-	/* 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->noiob)
-		nvme_set_chunk_size(ns);
-	nvme_update_disk_info(disk, ns, id);
-	if (ns->ndev)
-		nvme_nvm_update_nvm_info(ns);
-#ifdef CONFIG_NVME_MULTIPATH
-	if (ns->head->disk) {
-		nvme_update_disk_info(ns->head->disk, ns, id);
-		blk_queue_stack_limits(ns->head->disk->queue, ns->queue);
-		nvme_mpath_update_disk_size(ns->head->disk);
+	ns->features &= ~(NVME_NS_METADATA_SUPPORTED | NVME_NS_EXT_LBAS);
+	if (!ns->ms || !(ctrl->ops->flags & NVME_F_METADATA_SUPPORTED))
+		return 0;
+	if (ctrl->ops->flags & NVME_F_FABRICS) {
+		/*
+		 * The NVMe over Fabrics specification only supports metadata as
+		 * part of the extended data LBA.  We rely on HCA/HBA support to
+		 * remap the separate metadata buffer from the block layer.
+		 */
+		if (WARN_ON_ONCE(!(id->flbas & NVME_NS_FLBAS_META_EXT)))
+			return -EINVAL;
+		if (ctrl->max_integrity_segments)
+			ns->features |=
+				(NVME_NS_METADATA_SUPPORTED | NVME_NS_EXT_LBAS);
+	} else {
+		/*
+		 * For PCIe controllers, we can't easily remap the separate
+		 * metadata buffer from the block layer and thus require a
+		 * separate metadata buffer for block layer metadata/PI support.
+		 * We allow extended LBAs for the passthrough interface, though.
+		 */
+		if (id->flbas & NVME_NS_FLBAS_META_EXT)
+			ns->features |= NVME_NS_EXT_LBAS;
+		else
+			ns->features |= NVME_NS_METADATA_SUPPORTED;
 	}
-#endif
+
+	return 0;
 }
 
-static int nvme_revalidate_disk(struct gendisk *disk)
+static void nvme_set_queue_limits(struct nvme_ctrl *ctrl,
+		struct request_queue *q)
 {
-	struct nvme_ns *ns = disk->private_data;
+	bool vwc = ctrl->vwc & NVME_CTRL_VWC_PRESENT;
+
+	if (ctrl->max_hw_sectors) {
+		u32 max_segments =
+			(ctrl->max_hw_sectors / (NVME_CTRL_PAGE_SIZE >> 9)) + 1;
+
+		max_segments = min_not_zero(max_segments, ctrl->max_segments);
+		blk_queue_max_hw_sectors(q, ctrl->max_hw_sectors);
+		blk_queue_max_segments(q, min_t(u32, max_segments, USHRT_MAX));
+	}
+	blk_queue_virt_boundary(q, NVME_CTRL_PAGE_SIZE - 1);
+	blk_queue_dma_alignment(q, 3);
+	blk_queue_write_cache(q, vwc, vwc);
+}
+
+static void nvme_update_disk_info(struct gendisk *disk,
+		struct nvme_ns *ns, struct nvme_id_ns *id)
+{
+	sector_t capacity = nvme_lba_to_sect(ns, le64_to_cpu(id->nsze));
+	unsigned short bs = 1 << ns->lba_shift;
+	u32 atomic_bs, phys_bs, io_opt = 0;
+
+	/*
+	 * 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;
+		bs = (1 << 9);
+	}
+
+	blk_integrity_unregister(disk);
+
+	atomic_bs = phys_bs = bs;
+	nvme_setup_streams_ns(ns->ctrl, ns, &phys_bs, &io_opt);
+	if (id->nabo == 0) {
+		/*
+		 * Bit 1 indicates whether NAWUPF is defined for this namespace
+		 * and whether it should be used instead of AWUPF. If NAWUPF ==
+		 * 0 then AWUPF must be used instead.
+		 */
+		if (id->nsfeat & NVME_NS_FEAT_ATOMICS && id->nawupf)
+			atomic_bs = (1 + le16_to_cpu(id->nawupf)) * bs;
+		else
+			atomic_bs = (1 + ns->ctrl->subsys->awupf) * bs;
+	}
+
+	if (id->nsfeat & NVME_NS_FEAT_IO_OPT) {
+		/* NPWG = Namespace Preferred Write Granularity */
+		phys_bs = bs * (1 + le16_to_cpu(id->npwg));
+		/* NOWS = Namespace Optimal Write Size */
+		io_opt = bs * (1 + le16_to_cpu(id->nows));
+	}
+
+	blk_queue_logical_block_size(disk->queue, bs);
+	/*
+	 * Linux filesystems assume writing a single physical block is
+	 * an atomic operation. Hence limit the physical block size to the
+	 * value of the Atomic Write Unit Power Fail parameter.
+	 */
+	blk_queue_physical_block_size(disk->queue, min(phys_bs, atomic_bs));
+	blk_queue_io_min(disk->queue, phys_bs);
+	blk_queue_io_opt(disk->queue, io_opt);
+
+	/*
+	 * 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,
+					    ns->ctrl->max_integrity_segments);
+		else if (!nvme_ns_has_pi(ns))
+			capacity = 0;
+	}
+
+	set_capacity_revalidate_and_notify(disk, capacity, false);
+
+	nvme_config_discard(disk, ns);
+	nvme_config_write_zeroes(disk->queue, ns->ctrl);
+
+	if (id->nsattr & NVME_NS_ATTR_RO)
+		set_disk_ro(disk, true);
+}
+
+static inline bool nvme_first_scan(struct gendisk *disk)
+{
+	/* nvme_alloc_ns() scans the disk prior to adding it */
+	return !(disk->flags & GENHD_FL_UP);
+}
+
+static void nvme_set_chunk_sectors(struct nvme_ns *ns, struct nvme_id_ns *id)
+{
 	struct nvme_ctrl *ctrl = ns->ctrl;
-	struct nvme_id_ns *id;
-	struct nvme_ns_ids ids;
-	int ret = 0;
+	u32 iob;
 
-	if (test_bit(NVME_NS_DEAD, &ns->flags)) {
-		set_capacity(disk, 0);
-		return -ENODEV;
+	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));
+
+	if (!iob)
+		return;
+
+	if (!is_power_of_2(iob)) {
+		if (nvme_first_scan(ns->disk))
+			pr_warn("%s: ignoring unaligned IO boundary:%u\n",
+				ns->disk->disk_name, iob);
+		return;
 	}
 
-	id = nvme_identify_ns(ctrl, ns->head->ns_id);
-	if (!id)
-		return -ENODEV;
-
-	if (id->ncap == 0) {
-		ret = -ENODEV;
-		goto out;
+	if (blk_queue_is_zoned(ns->disk->queue)) {
+		if (nvme_first_scan(ns->disk))
+			pr_warn("%s: ignoring zoned namespace IO boundary\n",
+				ns->disk->disk_name);
+		return;
 	}
 
-	__nvme_revalidate_disk(disk, id);
-	nvme_report_ns_ids(ctrl, ns->head->ns_id, id, &ids);
-	if (!nvme_ns_ids_equal(&ns->head->ids, &ids)) {
-		dev_err(ctrl->device,
-			"identifiers changed for nsid %d\n", ns->head->ns_id);
-		ret = -ENODEV;
+	blk_queue_chunk_sectors(ns->queue, iob);
+}
+
+static int nvme_update_ns_info(struct nvme_ns *ns, struct nvme_id_ns *id)
+{
+	unsigned lbaf = id->flbas & NVME_NS_FLBAS_LBA_MASK;
+	int ret;
+
+	blk_mq_freeze_queue(ns->disk->queue);
+	ns->lba_shift = id->lbaf[lbaf].ds;
+	nvme_set_queue_limits(ns->ctrl, ns->queue);
+
+	if (ns->head->ids.csi == NVME_CSI_ZNS) {
+		ret = nvme_update_zone_info(ns, lbaf);
+		if (ret)
+			goto out_unfreeze;
 	}
 
-out:
-	kfree(id);
+	ret = nvme_configure_metadata(ns, id);
+	if (ret)
+		goto out_unfreeze;
+	nvme_set_chunk_sectors(ns, id);
+	nvme_update_disk_info(ns->disk, ns, id);
+	blk_mq_unfreeze_queue(ns->disk->queue);
+
+	if (blk_queue_is_zoned(ns->queue)) {
+		ret = nvme_revalidate_zones(ns);
+		if (ret && !nvme_first_scan(ns->disk))
+			return ret;
+	}
+
+#ifdef CONFIG_NVME_MULTIPATH
+	if (ns->head->disk) {
+		blk_mq_freeze_queue(ns->head->disk->queue);
+		nvme_update_disk_info(ns->head->disk, ns, id);
+		blk_stack_limits(&ns->head->disk->queue->limits,
+				 &ns->queue->limits, 0);
+		blk_queue_update_readahead(ns->head->disk->queue);
+		nvme_update_bdev_size(ns->head->disk);
+		blk_mq_unfreeze_queue(ns->head->disk->queue);
+	}
+#endif
+	return 0;
+
+out_unfreeze:
+	blk_mq_unfreeze_queue(ns->disk->queue);
 	return ret;
 }
 
@@ -1678,7 +2257,7 @@
 	memset(&c, 0, sizeof(c));
 	c.common.opcode = op;
 	c.common.nsid = cpu_to_le32(ns->head->ns_id);
-	c.common.cdw10[0] = cpu_to_le32(cdw10);
+	c.common.cdw10 = cpu_to_le32(cdw10);
 
 	ret = nvme_submit_sync_cmd(ns->queue, &c, data, 16);
 	nvme_put_ns_from_disk(head, srcu_idx);
@@ -1716,18 +2295,21 @@
 		enum pr_type type, bool abort)
 {
 	u32 cdw10 = nvme_pr_type(type) << 8 | (abort ? 2 : 1);
+
 	return nvme_pr_command(bdev, cdw10, old, new, nvme_cmd_resv_acquire);
 }
 
 static int nvme_pr_clear(struct block_device *bdev, u64 key)
 {
-	u32 cdw10 = 1 | (key ? 1 << 3 : 0);
-	return nvme_pr_command(bdev, cdw10, key, 0, nvme_cmd_resv_register);
+	u32 cdw10 = 1 | (key ? 0 : 1 << 3);
+
+	return nvme_pr_command(bdev, cdw10, key, 0, nvme_cmd_resv_release);
 }
 
 static int nvme_pr_release(struct block_device *bdev, u64 key, enum pr_type type)
 {
-	u32 cdw10 = nvme_pr_type(type) << 8 | (key ? 1 << 3 : 0);
+	u32 cdw10 = nvme_pr_type(type) << 8 | (key ? 0 : 1 << 3);
+
 	return nvme_pr_command(bdev, cdw10, key, 0, nvme_cmd_resv_release);
 }
 
@@ -1752,11 +2334,11 @@
 	else
 		cmd.common.opcode = nvme_admin_security_recv;
 	cmd.common.nsid = 0;
-	cmd.common.cdw10[0] = cpu_to_le32(((u32)secp) << 24 | ((u32)spsp) << 8);
-	cmd.common.cdw10[1] = cpu_to_le32(len);
+	cmd.common.cdw10 = cpu_to_le32(((u32)secp) << 24 | ((u32)spsp) << 8);
+	cmd.common.cdw11 = cpu_to_le32(len);
 
 	return __nvme_submit_sync_cmd(ctrl->admin_q, &cmd, NULL, buffer, len,
-				      ADMIN_TIMEOUT, NVME_QID_ANY, 1, 0);
+				      ADMIN_TIMEOUT, NVME_QID_ANY, 1, 0, false);
 }
 EXPORT_SYMBOL_GPL(nvme_sec_submit);
 #endif /* CONFIG_BLK_SED_OPAL */
@@ -1764,11 +2346,11 @@
 static const struct block_device_operations nvme_fops = {
 	.owner		= THIS_MODULE,
 	.ioctl		= nvme_ioctl,
-	.compat_ioctl	= nvme_ioctl,
+	.compat_ioctl	= nvme_compat_ioctl,
 	.open		= nvme_open,
 	.release	= nvme_release,
 	.getgeo		= nvme_getgeo,
-	.revalidate_disk= nvme_revalidate_disk,
+	.report_zones	= nvme_report_zones,
 	.pr_ops		= &nvme_pr_ops,
 };
 
@@ -1789,11 +2371,13 @@
 
 const struct block_device_operations nvme_ns_head_ops = {
 	.owner		= THIS_MODULE,
+	.submit_bio	= nvme_ns_head_submit_bio,
 	.open		= nvme_ns_head_open,
 	.release	= nvme_ns_head_release,
 	.ioctl		= nvme_ioctl,
-	.compat_ioctl	= nvme_ioctl,
+	.compat_ioctl	= nvme_compat_ioctl,
 	.getgeo		= nvme_getgeo,
+	.report_zones	= nvme_report_zones,
 	.pr_ops		= &nvme_pr_ops,
 };
 #endif /* CONFIG_NVME_MULTIPATH */
@@ -1811,13 +2395,13 @@
 		if ((csts & NVME_CSTS_RDY) == bit)
 			break;
 
-		msleep(100);
+		usleep_range(1000, 2000);
 		if (fatal_signal_pending(current))
 			return -EINTR;
 		if (time_after(jiffies, timeout)) {
 			dev_err(ctrl->device,
-				"Device not ready; aborting %s\n", enabled ?
-						"initialisation" : "reset");
+				"Device not ready; aborting %s, CSTS=0x%x\n",
+				enabled ? "initialisation" : "reset", csts);
 			return -ENODEV;
 		}
 	}
@@ -1831,7 +2415,7 @@
  * bits', but doing so may cause the device to complete commands to the
  * admin queue ... and we don't know what memory that might be pointing at!
  */
-int nvme_disable_ctrl(struct nvme_ctrl *ctrl, u64 cap)
+int nvme_disable_ctrl(struct nvme_ctrl *ctrl)
 {
 	int ret;
 
@@ -1845,31 +2429,34 @@
 	if (ctrl->quirks & NVME_QUIRK_DELAY_BEFORE_CHK_RDY)
 		msleep(NVME_QUIRK_DELAY_AMOUNT);
 
-	return nvme_wait_ready(ctrl, cap, false);
+	return nvme_wait_ready(ctrl, ctrl->cap, false);
 }
 EXPORT_SYMBOL_GPL(nvme_disable_ctrl);
 
-int nvme_enable_ctrl(struct nvme_ctrl *ctrl, u64 cap)
+int nvme_enable_ctrl(struct nvme_ctrl *ctrl)
 {
-	/*
-	 * Default to a 4K page size, with the intention to update this
-	 * path in the future to accomodate architectures with differing
-	 * kernel and IO page sizes.
-	 */
-	unsigned dev_page_min = NVME_CAP_MPSMIN(cap) + 12, page_shift = 12;
+	unsigned dev_page_min;
 	int ret;
 
-	if (page_shift < dev_page_min) {
+	ret = ctrl->ops->reg_read64(ctrl, NVME_REG_CAP, &ctrl->cap);
+	if (ret) {
+		dev_err(ctrl->device, "Reading CAP failed (%d)\n", ret);
+		return ret;
+	}
+	dev_page_min = NVME_CAP_MPSMIN(ctrl->cap) + 12;
+
+	if (NVME_CTRL_PAGE_SHIFT < dev_page_min) {
 		dev_err(ctrl->device,
 			"Minimum device page size %u too large for host (%u)\n",
-			1 << dev_page_min, 1 << page_shift);
+			1 << dev_page_min, 1 << NVME_CTRL_PAGE_SHIFT);
 		return -ENODEV;
 	}
 
-	ctrl->page_size = 1 << page_shift;
-
-	ctrl->ctrl_config = NVME_CC_CSS_NVM;
-	ctrl->ctrl_config |= (page_shift - 12) << NVME_CC_MPS_SHIFT;
+	if (NVME_CAP_CSS(ctrl->cap) & NVME_CAP_CSS_CSI)
+		ctrl->ctrl_config = NVME_CC_CSS_CSI;
+	else
+		ctrl->ctrl_config = NVME_CC_CSS_NVM;
+	ctrl->ctrl_config |= (NVME_CTRL_PAGE_SHIFT - 12) << NVME_CC_MPS_SHIFT;
 	ctrl->ctrl_config |= NVME_CC_AMS_RR | NVME_CC_SHN_NONE;
 	ctrl->ctrl_config |= NVME_CC_IOSQES | NVME_CC_IOCQES;
 	ctrl->ctrl_config |= NVME_CC_ENABLE;
@@ -1877,7 +2464,7 @@
 	ret = ctrl->ops->reg_write32(ctrl, NVME_REG_CC, ctrl->ctrl_config);
 	if (ret)
 		return ret;
-	return nvme_wait_ready(ctrl, cap, true);
+	return nvme_wait_ready(ctrl, ctrl->cap, true);
 }
 EXPORT_SYMBOL_GPL(nvme_enable_ctrl);
 
@@ -1912,28 +2499,6 @@
 }
 EXPORT_SYMBOL_GPL(nvme_shutdown_ctrl);
 
-static void nvme_set_queue_limits(struct nvme_ctrl *ctrl,
-		struct request_queue *q)
-{
-	bool vwc = false;
-
-	if (ctrl->max_hw_sectors) {
-		u32 max_segments =
-			(ctrl->max_hw_sectors / (ctrl->page_size >> 9)) + 1;
-
-		max_segments = min_not_zero(max_segments, ctrl->max_segments);
-		blk_queue_max_hw_sectors(q, ctrl->max_hw_sectors);
-		blk_queue_max_segments(q, min_t(u32, max_segments, USHRT_MAX));
-	}
-	if ((ctrl->quirks & NVME_QUIRK_STRIPE_SIZE) &&
-	    is_power_of_2(ctrl->max_hw_sectors))
-		blk_queue_chunk_sectors(q, ctrl->max_hw_sectors);
-	blk_queue_virt_boundary(q, ctrl->page_size - 1);
-	if (ctrl->vwc & NVME_CTRL_VWC_PRESENT)
-		vwc = true;
-	blk_queue_write_cache(q, vwc, vwc);
-}
-
 static int nvme_configure_timestamp(struct nvme_ctrl *ctrl)
 {
 	__le64 ts;
@@ -1948,6 +2513,26 @@
 	if (ret)
 		dev_warn_once(ctrl->device,
 			"could not set timestamp (%d)\n", ret);
+	return ret;
+}
+
+static int nvme_configure_acre(struct nvme_ctrl *ctrl)
+{
+	struct nvme_feat_host_behavior *host;
+	int ret;
+
+	/* Don't bother enabling the feature if retry delay is not reported */
+	if (!ctrl->crdt[0])
+		return 0;
+
+	host = kzalloc(sizeof(*host), GFP_KERNEL);
+	if (!host)
+		return 0;
+
+	host->acre = NVME_ENABLE_ACRE;
+	ret = nvme_set_features(ctrl, NVME_FEAT_HOST_BEHAVIOR, 0,
+				host, sizeof(*host), NULL);
+	kfree(host);
 	return ret;
 }
 
@@ -2117,6 +2702,44 @@
 		.vid = 0x1179,
 		.mn = "THNSF5256GPUK TOSHIBA",
 		.quirks = NVME_QUIRK_NO_APST,
+	},
+	{
+		/*
+		 * This LiteON CL1-3D*-Q11 firmware version has a race
+		 * condition associated with actions related to suspend to idle
+		 * LiteON has resolved the problem in future firmware
+		 */
+		.vid = 0x14a4,
+		.fr = "22301111",
+		.quirks = NVME_QUIRK_SIMPLE_SUSPEND,
+	},
+	{
+		/*
+		 * This Kioxia CD6-V Series / HPE PE8030 device times out and
+		 * aborts I/O during any load, but more easily reproducible
+		 * with discards (fstrim).
+		 *
+		 * The device is left in a state where it is also not possible
+		 * to use "nvme set-feature" to disable APST, but booting with
+		 * nvme_core.default_ps_max_latency=0 works.
+		 */
+		.vid = 0x1e0f,
+		.mn = "KCD6XVUL6T40",
+		.quirks = NVME_QUIRK_NO_APST,
+	},
+	{
+		/*
+		 * The external Samsung X5 SSD fails initialization without a
+		 * delay before checking if it is ready and has a whole set of
+		 * other problems.  To make this even more interesting, it
+		 * shares the PCI ID with internal Samsung 970 Evo Plus that
+		 * does not need or want these quirks.
+		 */
+		.vid = 0x144d,
+		.mn = "Samsung Portable SSD X5",
+		.quirks = NVME_QUIRK_DELAY_BEFORE_CHK_RDY |
+			  NVME_QUIRK_NO_DEEPEST_PS |
+			  NVME_QUIRK_IGNORE_DEV_SUBNQN,
 	}
 };
 
@@ -2155,14 +2778,16 @@
 	size_t nqnlen;
 	int off;
 
-	nqnlen = strnlen(id->subnqn, NVMF_NQN_SIZE);
-	if (nqnlen > 0 && nqnlen < NVMF_NQN_SIZE) {
-		strncpy(subsys->subnqn, id->subnqn, NVMF_NQN_SIZE);
-		return;
-	}
+	if(!(ctrl->quirks & NVME_QUIRK_IGNORE_DEV_SUBNQN)) {
+		nqnlen = strnlen(id->subnqn, NVMF_NQN_SIZE);
+		if (nqnlen > 0 && nqnlen < NVMF_NQN_SIZE) {
+			strlcpy(subsys->subnqn, id->subnqn, NVMF_NQN_SIZE);
+			return;
+		}
 
-	if (ctrl->vs >= NVME_VS(1, 2, 1))
-		dev_warn(ctrl->device, "missing or invalid SUBNQN field.\n");
+		if (ctrl->vs >= NVME_VS(1, 2, 1))
+			dev_warn(ctrl->device, "missing or invalid SUBNQN field.\n");
+	}
 
 	/* Generate a "fake" NQN per Figure 254 in NVMe 1.3 + ECN 001 */
 	off = snprintf(subsys->subnqn, NVMF_NQN_SIZE,
@@ -2175,15 +2800,14 @@
 	memset(subsys->subnqn + off, 0, sizeof(subsys->subnqn) - off);
 }
 
-static void __nvme_release_subsystem(struct nvme_subsystem *subsys)
-{
-	ida_simple_remove(&nvme_subsystems_ida, subsys->instance);
-	kfree(subsys);
-}
-
 static void nvme_release_subsystem(struct device *dev)
 {
-	__nvme_release_subsystem(container_of(dev, struct nvme_subsystem, dev));
+	struct nvme_subsystem *subsys =
+		container_of(dev, struct nvme_subsystem, dev);
+
+	if (subsys->instance >= 0)
+		ida_simple_remove(&nvme_instance_ida, subsys->instance);
+	kfree(subsys);
 }
 
 static void nvme_destroy_subsystem(struct kref *ref)
@@ -2254,8 +2878,8 @@
 {									\
 	struct nvme_subsystem *subsys =					\
 		container_of(dev, struct nvme_subsystem, dev);		\
-	return sprintf(buf, "%.*s\n",					\
-		       (int)sizeof(subsys->field), subsys->field);	\
+	return sysfs_emit(buf, "%.*s\n",				\
+			   (int)sizeof(subsys->field), subsys->field);	\
 }									\
 static SUBSYS_ATTR_RO(field, S_IRUGO, subsys_##field##_show);
 
@@ -2268,6 +2892,9 @@
 	&subsys_attr_serial.attr,
 	&subsys_attr_firmware_rev.attr,
 	&subsys_attr_subsysnqn.attr,
+#ifdef CONFIG_NVME_MULTIPATH
+	&subsys_attr_iopolicy.attr,
+#endif
 	NULL,
 };
 
@@ -2280,20 +2907,39 @@
 	NULL,
 };
 
-static int nvme_active_ctrls(struct nvme_subsystem *subsys)
+static inline bool nvme_discovery_ctrl(struct nvme_ctrl *ctrl)
 {
-	int count = 0;
-	struct nvme_ctrl *ctrl;
+	return ctrl->opts && ctrl->opts->discovery_nqn;
+}
 
-	mutex_lock(&subsys->lock);
-	list_for_each_entry(ctrl, &subsys->ctrls, subsys_entry) {
-		if (ctrl->state != NVME_CTRL_DELETING &&
-		    ctrl->state != NVME_CTRL_DEAD)
-			count++;
+static bool nvme_validate_cntlid(struct nvme_subsystem *subsys,
+		struct nvme_ctrl *ctrl, struct nvme_id_ctrl *id)
+{
+	struct nvme_ctrl *tmp;
+
+	lockdep_assert_held(&nvme_subsystems_lock);
+
+	list_for_each_entry(tmp, &subsys->ctrls, subsys_entry) {
+		if (nvme_state_terminal(tmp))
+			continue;
+
+		if (tmp->cntlid == ctrl->cntlid) {
+			dev_err(ctrl->device,
+				"Duplicate cntlid %u with %s, rejecting\n",
+				ctrl->cntlid, dev_name(tmp->device));
+			return false;
+		}
+
+		if ((id->cmic & NVME_CTRL_CMIC_MULTI_CTRL) ||
+		    nvme_discovery_ctrl(ctrl))
+			continue;
+
+		dev_err(ctrl->device,
+			"Subsystem does not support multiple controllers\n");
+		return false;
 	}
-	mutex_unlock(&subsys->lock);
 
-	return count;
+	return true;
 }
 
 static int nvme_init_subsystem(struct nvme_ctrl *ctrl, struct nvme_id_ctrl *id)
@@ -2304,12 +2950,8 @@
 	subsys = kzalloc(sizeof(*subsys), GFP_KERNEL);
 	if (!subsys)
 		return -ENOMEM;
-	ret = ida_simple_get(&nvme_subsystems_ida, 0, 0, GFP_KERNEL);
-	if (ret < 0) {
-		kfree(subsys);
-		return ret;
-	}
-	subsys->instance = ret;
+
+	subsys->instance = -1;
 	mutex_init(&subsys->lock);
 	kref_init(&subsys->ref);
 	INIT_LIST_HEAD(&subsys->ctrls);
@@ -2317,74 +2959,68 @@
 	nvme_init_subnqn(subsys, ctrl, id);
 	memcpy(subsys->serial, id->sn, sizeof(subsys->serial));
 	memcpy(subsys->model, id->mn, sizeof(subsys->model));
-	memcpy(subsys->firmware_rev, id->fr, sizeof(subsys->firmware_rev));
 	subsys->vendor_id = le16_to_cpu(id->vid);
 	subsys->cmic = id->cmic;
+	subsys->awupf = le16_to_cpu(id->awupf);
+#ifdef CONFIG_NVME_MULTIPATH
+	subsys->iopolicy = NVME_IOPOLICY_NUMA;
+#endif
 
 	subsys->dev.class = nvme_subsys_class;
 	subsys->dev.release = nvme_release_subsystem;
 	subsys->dev.groups = nvme_subsys_attrs_groups;
-	dev_set_name(&subsys->dev, "nvme-subsys%d", subsys->instance);
+	dev_set_name(&subsys->dev, "nvme-subsys%d", ctrl->instance);
 	device_initialize(&subsys->dev);
 
 	mutex_lock(&nvme_subsystems_lock);
 	found = __nvme_find_get_subsystem(subsys->subnqn);
 	if (found) {
-		/*
-		 * Verify that the subsystem actually supports multiple
-		 * controllers, else bail out.
-		 */
-		if (!(ctrl->opts && ctrl->opts->discovery_nqn) &&
-		    nvme_active_ctrls(found) && !(id->cmic & (1 << 1))) {
-			dev_err(ctrl->device,
-				"ignoring ctrl due to duplicate subnqn (%s).\n",
-				found->subnqn);
-			nvme_put_subsystem(found);
-			ret = -EINVAL;
-			goto out_unlock;
-		}
-
-		__nvme_release_subsystem(subsys);
+		put_device(&subsys->dev);
 		subsys = found;
+
+		if (!nvme_validate_cntlid(subsys, ctrl, id)) {
+			ret = -EINVAL;
+			goto out_put_subsystem;
+		}
 	} else {
 		ret = device_add(&subsys->dev);
 		if (ret) {
 			dev_err(ctrl->device,
 				"failed to register subsystem device.\n");
+			put_device(&subsys->dev);
 			goto out_unlock;
 		}
 		ida_init(&subsys->ns_ida);
 		list_add_tail(&subsys->entry, &nvme_subsystems);
 	}
 
-	ctrl->subsys = subsys;
-	mutex_unlock(&nvme_subsystems_lock);
-
-	if (sysfs_create_link(&subsys->dev.kobj, &ctrl->device->kobj,
-			dev_name(ctrl->device))) {
+	ret = sysfs_create_link(&subsys->dev.kobj, &ctrl->device->kobj,
+				dev_name(ctrl->device));
+	if (ret) {
 		dev_err(ctrl->device,
 			"failed to create sysfs link from subsystem.\n");
-		/* the transport driver will eventually put the subsystem */
-		return -EINVAL;
+		goto out_put_subsystem;
 	}
 
-	mutex_lock(&subsys->lock);
+	if (!found)
+		subsys->instance = ctrl->instance;
+	ctrl->subsys = subsys;
 	list_add_tail(&ctrl->subsys_entry, &subsys->ctrls);
-	mutex_unlock(&subsys->lock);
-
+	mutex_unlock(&nvme_subsystems_lock);
 	return 0;
 
+out_put_subsystem:
+	nvme_put_subsystem(subsys);
 out_unlock:
 	mutex_unlock(&nvme_subsystems_lock);
-	put_device(&subsys->dev);
 	return ret;
 }
 
-int nvme_get_log(struct nvme_ctrl *ctrl, u32 nsid, u8 log_page, u8 lsp,
+int nvme_get_log(struct nvme_ctrl *ctrl, u32 nsid, u8 log_page, u8 lsp, u8 csi,
 		void *log, size_t size, u64 offset)
 {
 	struct nvme_command c = { };
-	unsigned long dwlen = size / 4 - 1;
+	u32 dwlen = nvme_bytes_to_numd(size);
 
 	c.get_log_page.opcode = nvme_admin_get_log_page;
 	c.get_log_page.nsid = cpu_to_le32(nsid);
@@ -2394,27 +3030,35 @@
 	c.get_log_page.numdu = cpu_to_le16(dwlen >> 16);
 	c.get_log_page.lpol = cpu_to_le32(lower_32_bits(offset));
 	c.get_log_page.lpou = cpu_to_le32(upper_32_bits(offset));
+	c.get_log_page.csi = csi;
 
 	return nvme_submit_sync_cmd(ctrl->admin_q, &c, log, size);
 }
 
-static int nvme_get_effects_log(struct nvme_ctrl *ctrl)
+static int nvme_get_effects_log(struct nvme_ctrl *ctrl, u8 csi,
+				struct nvme_effects_log **log)
 {
+	struct nvme_effects_log	*cel = xa_load(&ctrl->cels, csi);
 	int ret;
 
-	if (!ctrl->effects)
-		ctrl->effects = kzalloc(sizeof(*ctrl->effects), GFP_KERNEL);
+	if (cel)
+		goto out;
 
-	if (!ctrl->effects)
-		return 0;
+	cel = kzalloc(sizeof(*cel), GFP_KERNEL);
+	if (!cel)
+		return -ENOMEM;
 
-	ret = nvme_get_log(ctrl, NVME_NSID_ALL, NVME_LOG_CMD_EFFECTS, 0,
-			ctrl->effects, sizeof(*ctrl->effects), 0);
+	ret = nvme_get_log(ctrl, 0x00, NVME_LOG_CMD_EFFECTS, 0, csi,
+			cel, sizeof(*cel), 0);
 	if (ret) {
-		kfree(ctrl->effects);
-		ctrl->effects = NULL;
+		kfree(cel);
+		return ret;
 	}
-	return ret;
+
+	xa_store(&ctrl->cels, csi, cel, GFP_KERNEL);
+out:
+	*log = cel;
+	return 0;
 }
 
 /*
@@ -2425,7 +3069,6 @@
 int nvme_init_identify(struct nvme_ctrl *ctrl)
 {
 	struct nvme_id_ctrl *id;
-	u64 cap;
 	int ret, page_shift;
 	u32 max_hw_sectors;
 	bool prev_apst_enabled;
@@ -2435,16 +3078,11 @@
 		dev_err(ctrl->device, "Reading VS failed (%d)\n", ret);
 		return ret;
 	}
-
-	ret = ctrl->ops->reg_read64(ctrl, NVME_REG_CAP, &cap);
-	if (ret) {
-		dev_err(ctrl->device, "Reading CAP failed (%d)\n", ret);
-		return ret;
-	}
-	page_shift = NVME_CAP_MPSMIN(cap) + 12;
+	page_shift = NVME_CAP_MPSMIN(ctrl->cap) + 12;
+	ctrl->sqsize = min_t(u16, NVME_CAP_MQES(ctrl->cap), ctrl->sqsize);
 
 	if (ctrl->vs >= NVME_VS(1, 1, 0))
-		ctrl->subsystem = NVME_CAP_NSSRC(cap);
+		ctrl->subsystem = NVME_CAP_NSSRC(ctrl->cap);
 
 	ret = nvme_identify_ctrl(ctrl, &id);
 	if (ret) {
@@ -2453,17 +3091,16 @@
 	}
 
 	if (id->lpa & NVME_CTRL_LPA_CMD_EFFECTS_LOG) {
-		ret = nvme_get_effects_log(ctrl);
+		ret = nvme_get_effects_log(ctrl, NVME_CSI_NVM, &ctrl->effects);
 		if (ret < 0)
 			goto out_free;
 	}
 
+	if (!(ctrl->ops->flags & NVME_F_FABRICS))
+		ctrl->cntlid = le16_to_cpu(id->cntlid);
+
 	if (!ctrl->identified) {
 		int i;
-
-		ret = nvme_init_subsystem(ctrl, id);
-		if (ret)
-			goto out_free;
 
 		/*
 		 * Check for quirks.  Quirk can depend on firmware version,
@@ -2477,19 +3114,32 @@
 			if (quirk_matches(id, &core_quirks[i]))
 				ctrl->quirks |= core_quirks[i].quirks;
 		}
+
+		ret = nvme_init_subsystem(ctrl, id);
+		if (ret)
+			goto out_free;
 	}
+	memcpy(ctrl->subsys->firmware_rev, id->fr,
+	       sizeof(ctrl->subsys->firmware_rev));
 
 	if (force_apst && (ctrl->quirks & NVME_QUIRK_NO_DEEPEST_PS)) {
 		dev_warn(ctrl->device, "forcibly allowing all power states due to nvme_core.force_apst -- use at your own risk\n");
 		ctrl->quirks &= ~NVME_QUIRK_NO_DEEPEST_PS;
 	}
 
+	ctrl->crdt[0] = le16_to_cpu(id->crdt1);
+	ctrl->crdt[1] = le16_to_cpu(id->crdt2);
+	ctrl->crdt[2] = le16_to_cpu(id->crdt3);
+
 	ctrl->oacs = le16_to_cpu(id->oacs);
-	ctrl->oncs = le16_to_cpup(&id->oncs);
+	ctrl->oncs = le16_to_cpu(id->oncs);
+	ctrl->mtfa = le16_to_cpu(id->mtfa);
 	ctrl->oaes = le32_to_cpu(id->oaes);
+	ctrl->wctemp = le16_to_cpu(id->wctemp);
+	ctrl->cctemp = le16_to_cpu(id->cctemp);
+
 	atomic_set(&ctrl->abort_limit, id->acl + 1);
 	ctrl->vwc = id->vwc;
-	ctrl->cntlid = le16_to_cpup(&id->cntlid);
 	if (id->mdts)
 		max_hw_sectors = 1 << (id->mdts + page_shift - 9);
 	else
@@ -2501,10 +3151,11 @@
 	ctrl->sgls = le32_to_cpu(id->sgls);
 	ctrl->kas = le16_to_cpu(id->kas);
 	ctrl->max_namespaces = le32_to_cpu(id->mnan);
+	ctrl->ctratt = le32_to_cpu(id->ctratt);
 
 	if (id->rtd3e) {
 		/* us -> s */
-		u32 transition_time = le32_to_cpu(id->rtd3e) / 1000000;
+		u32 transition_time = le32_to_cpu(id->rtd3e) / USEC_PER_SEC;
 
 		ctrl->shutdown_timeout = clamp_t(unsigned int, transition_time,
 						 shutdown_timeout, 60);
@@ -2542,25 +3193,28 @@
 		 * admin connect
 		 */
 		if (ctrl->cntlid != le16_to_cpu(id->cntlid)) {
+			dev_err(ctrl->device,
+				"Mismatching cntlid: Connect %u vs Identify "
+				"%u, rejecting\n",
+				ctrl->cntlid, le16_to_cpu(id->cntlid));
 			ret = -EINVAL;
 			goto out_free;
 		}
 
-		if (!ctrl->opts->discovery_nqn && !ctrl->kas) {
+		if (!nvme_discovery_ctrl(ctrl) && !ctrl->kas) {
 			dev_err(ctrl->device,
 				"keep-alive support is mandatory for fabrics\n");
 			ret = -EINVAL;
 			goto out_free;
 		}
 	} else {
-		ctrl->cntlid = le16_to_cpu(id->cntlid);
 		ctrl->hmpre = le32_to_cpu(id->hmpre);
 		ctrl->hmmin = le32_to_cpu(id->hmmin);
 		ctrl->hmminds = le32_to_cpu(id->hmminds);
 		ctrl->hmmaxd = le16_to_cpu(id->hmmaxd);
 	}
 
-	ret = nvme_mpath_init(ctrl, id);
+	ret = nvme_mpath_init_identify(ctrl, id);
 	kfree(id);
 
 	if (ret < 0)
@@ -2583,6 +3237,20 @@
 	if (ret < 0)
 		return ret;
 
+	ret = nvme_configure_acre(ctrl);
+	if (ret < 0)
+		return ret;
+
+	if (!ctrl->identified && !nvme_discovery_ctrl(ctrl)) {
+		/*
+		 * Do not return errors unless we are in a controller reset,
+		 * the controller works perfectly fine without hwmon.
+		 */
+		ret = nvme_hwmon_init(ctrl);
+		if (ret == -EINTR)
+			return ret;
+	}
+
 	ctrl->identified = true;
 
 	return 0;
@@ -2600,7 +3268,6 @@
 
 	switch (ctrl->state) {
 	case NVME_CTRL_LIVE:
-	case NVME_CTRL_ADMIN_ONLY:
 		break;
 	default:
 		return -EWOULDBLOCK;
@@ -2668,14 +3335,22 @@
 	switch (cmd) {
 	case NVME_IOCTL_ADMIN_CMD:
 		return nvme_user_cmd(ctrl, NULL, argp);
+	case NVME_IOCTL_ADMIN64_CMD:
+		return nvme_user_cmd64(ctrl, NULL, argp);
 	case NVME_IOCTL_IO_CMD:
 		return nvme_dev_user_cmd(ctrl, argp);
 	case NVME_IOCTL_RESET:
+		if (!capable(CAP_SYS_ADMIN))
+			return -EACCES;
 		dev_warn(ctrl->device, "resetting controller\n");
 		return nvme_reset_ctrl_sync(ctrl);
 	case NVME_IOCTL_SUBSYS_RESET:
+		if (!capable(CAP_SYS_ADMIN))
+			return -EACCES;
 		return nvme_reset_subsystem(ctrl);
 	case NVME_IOCTL_RESCAN:
+		if (!capable(CAP_SYS_ADMIN))
+			return -EACCES;
 		nvme_queue_scan(ctrl);
 		return 0;
 	default:
@@ -2688,7 +3363,7 @@
 	.open		= nvme_dev_open,
 	.release	= nvme_dev_release,
 	.unlocked_ioctl	= nvme_dev_ioctl,
-	.compat_ioctl	= nvme_dev_ioctl,
+	.compat_ioctl	= compat_ptr_ioctl,
 };
 
 static ssize_t nvme_sysfs_reset(struct device *dev,
@@ -2736,13 +3411,13 @@
 	int model_len = sizeof(subsys->model);
 
 	if (!uuid_is_null(&ids->uuid))
-		return sprintf(buf, "uuid.%pU\n", &ids->uuid);
+		return sysfs_emit(buf, "uuid.%pU\n", &ids->uuid);
 
 	if (memchr_inv(ids->nguid, 0, sizeof(ids->nguid)))
-		return sprintf(buf, "eui.%16phN\n", ids->nguid);
+		return sysfs_emit(buf, "eui.%16phN\n", ids->nguid);
 
 	if (memchr_inv(ids->eui64, 0, sizeof(ids->eui64)))
-		return sprintf(buf, "eui.%8phN\n", ids->eui64);
+		return sysfs_emit(buf, "eui.%8phN\n", ids->eui64);
 
 	while (serial_len > 0 && (subsys->serial[serial_len - 1] == ' ' ||
 				  subsys->serial[serial_len - 1] == '\0'))
@@ -2751,7 +3426,7 @@
 				 subsys->model[model_len - 1] == '\0'))
 		model_len--;
 
-	return sprintf(buf, "nvme.%04x-%*phN-%*phN-%08x\n", subsys->vendor_id,
+	return sysfs_emit(buf, "nvme.%04x-%*phN-%*phN-%08x\n", subsys->vendor_id,
 		serial_len, subsys->serial, model_len, subsys->model,
 		head->ns_id);
 }
@@ -2760,7 +3435,7 @@
 static ssize_t nguid_show(struct device *dev, struct device_attribute *attr,
 		char *buf)
 {
-	return sprintf(buf, "%pU\n", dev_to_ns_head(dev)->ids.nguid);
+	return sysfs_emit(buf, "%pU\n", dev_to_ns_head(dev)->ids.nguid);
 }
 static DEVICE_ATTR_RO(nguid);
 
@@ -2773,25 +3448,25 @@
 	 * we have no UUID set
 	 */
 	if (uuid_is_null(&ids->uuid)) {
-		printk_ratelimited(KERN_WARNING
-				   "No UUID available providing old NGUID\n");
-		return sprintf(buf, "%pU\n", ids->nguid);
+		dev_warn_ratelimited(dev,
+			"No UUID available providing old NGUID\n");
+		return sysfs_emit(buf, "%pU\n", ids->nguid);
 	}
-	return sprintf(buf, "%pU\n", &ids->uuid);
+	return sysfs_emit(buf, "%pU\n", &ids->uuid);
 }
 static DEVICE_ATTR_RO(uuid);
 
 static ssize_t eui_show(struct device *dev, struct device_attribute *attr,
 		char *buf)
 {
-	return sprintf(buf, "%8ph\n", dev_to_ns_head(dev)->ids.eui64);
+	return sysfs_emit(buf, "%8ph\n", dev_to_ns_head(dev)->ids.eui64);
 }
 static DEVICE_ATTR_RO(eui);
 
 static ssize_t nsid_show(struct device *dev, struct device_attribute *attr,
 		char *buf)
 {
-	return sprintf(buf, "%d\n", dev_to_ns_head(dev)->ns_id);
+	return sysfs_emit(buf, "%d\n", dev_to_ns_head(dev)->ns_id);
 }
 static DEVICE_ATTR_RO(nsid);
 
@@ -2838,9 +3513,17 @@
 	return a->mode;
 }
 
-const struct attribute_group nvme_ns_id_attr_group = {
+static const struct attribute_group nvme_ns_id_attr_group = {
 	.attrs		= nvme_ns_id_attrs,
 	.is_visible	= nvme_ns_id_attrs_are_visible,
+};
+
+const struct attribute_group *nvme_ns_id_attr_groups[] = {
+	&nvme_ns_id_attr_group,
+#ifdef CONFIG_NVM
+	&nvme_nvm_attr_group,
+#endif
+	NULL,
 };
 
 #define nvme_show_str_function(field)						\
@@ -2848,7 +3531,7 @@
 			    struct device_attribute *attr, char *buf)		\
 {										\
         struct nvme_ctrl *ctrl = dev_get_drvdata(dev);				\
-        return sprintf(buf, "%.*s\n",						\
+        return sysfs_emit(buf, "%.*s\n",					\
 		(int)sizeof(ctrl->subsys->field), ctrl->subsys->field);		\
 }										\
 static DEVICE_ATTR(field, S_IRUGO, field##_show, NULL);
@@ -2862,21 +3545,20 @@
 			    struct device_attribute *attr, char *buf)		\
 {										\
         struct nvme_ctrl *ctrl = dev_get_drvdata(dev);				\
-        return sprintf(buf, "%d\n", ctrl->field);	\
+        return sysfs_emit(buf, "%d\n", ctrl->field);				\
 }										\
 static DEVICE_ATTR(field, S_IRUGO, field##_show, NULL);
 
 nvme_show_int_function(cntlid);
+nvme_show_int_function(numa_node);
+nvme_show_int_function(queue_count);
+nvme_show_int_function(sqsize);
 
 static ssize_t nvme_sysfs_delete(struct device *dev,
 				struct device_attribute *attr, const char *buf,
 				size_t count)
 {
 	struct nvme_ctrl *ctrl = dev_get_drvdata(dev);
-
-	/* Can't delete non-created controllers */
-	if (!ctrl->created)
-		return -EBUSY;
 
 	if (device_remove_file_self(dev, attr))
 		nvme_delete_ctrl_sync(ctrl);
@@ -2902,18 +3584,18 @@
 	static const char *const state_name[] = {
 		[NVME_CTRL_NEW]		= "new",
 		[NVME_CTRL_LIVE]	= "live",
-		[NVME_CTRL_ADMIN_ONLY]	= "only-admin",
 		[NVME_CTRL_RESETTING]	= "resetting",
 		[NVME_CTRL_CONNECTING]	= "connecting",
 		[NVME_CTRL_DELETING]	= "deleting",
+		[NVME_CTRL_DELETING_NOIO]= "deleting (no IO)",
 		[NVME_CTRL_DEAD]	= "dead",
 	};
 
 	if ((unsigned)ctrl->state < ARRAY_SIZE(state_name) &&
 	    state_name[ctrl->state])
-		return sprintf(buf, "%s\n", state_name[ctrl->state]);
+		return sysfs_emit(buf, "%s\n", state_name[ctrl->state]);
 
-	return sprintf(buf, "unknown state\n");
+	return sysfs_emit(buf, "unknown state\n");
 }
 
 static DEVICE_ATTR(state, S_IRUGO, nvme_sysfs_show_state, NULL);
@@ -2928,6 +3610,26 @@
 }
 static DEVICE_ATTR(subsysnqn, S_IRUGO, nvme_sysfs_show_subsysnqn, NULL);
 
+static ssize_t nvme_sysfs_show_hostnqn(struct device *dev,
+					struct device_attribute *attr,
+					char *buf)
+{
+	struct nvme_ctrl *ctrl = dev_get_drvdata(dev);
+
+	return snprintf(buf, PAGE_SIZE, "%s\n", ctrl->opts->host->nqn);
+}
+static DEVICE_ATTR(hostnqn, S_IRUGO, nvme_sysfs_show_hostnqn, NULL);
+
+static ssize_t nvme_sysfs_show_hostid(struct device *dev,
+					struct device_attribute *attr,
+					char *buf)
+{
+	struct nvme_ctrl *ctrl = dev_get_drvdata(dev);
+
+	return snprintf(buf, PAGE_SIZE, "%pU\n", &ctrl->opts->host->id);
+}
+static DEVICE_ATTR(hostid, S_IRUGO, nvme_sysfs_show_hostid, NULL);
+
 static ssize_t nvme_sysfs_show_address(struct device *dev,
 					 struct device_attribute *attr,
 					 char *buf)
@@ -2937,6 +3639,66 @@
 	return ctrl->ops->get_address(ctrl, buf, PAGE_SIZE);
 }
 static DEVICE_ATTR(address, S_IRUGO, nvme_sysfs_show_address, NULL);
+
+static ssize_t nvme_ctrl_loss_tmo_show(struct device *dev,
+		struct device_attribute *attr, char *buf)
+{
+	struct nvme_ctrl *ctrl = dev_get_drvdata(dev);
+	struct nvmf_ctrl_options *opts = ctrl->opts;
+
+	if (ctrl->opts->max_reconnects == -1)
+		return sysfs_emit(buf, "off\n");
+	return sysfs_emit(buf, "%d\n",
+			  opts->max_reconnects * opts->reconnect_delay);
+}
+
+static ssize_t nvme_ctrl_loss_tmo_store(struct device *dev,
+		struct device_attribute *attr, const char *buf, size_t count)
+{
+	struct nvme_ctrl *ctrl = dev_get_drvdata(dev);
+	struct nvmf_ctrl_options *opts = ctrl->opts;
+	int ctrl_loss_tmo, err;
+
+	err = kstrtoint(buf, 10, &ctrl_loss_tmo);
+	if (err)
+		return -EINVAL;
+
+	else if (ctrl_loss_tmo < 0)
+		opts->max_reconnects = -1;
+	else
+		opts->max_reconnects = DIV_ROUND_UP(ctrl_loss_tmo,
+						opts->reconnect_delay);
+	return count;
+}
+static DEVICE_ATTR(ctrl_loss_tmo, S_IRUGO | S_IWUSR,
+	nvme_ctrl_loss_tmo_show, nvme_ctrl_loss_tmo_store);
+
+static ssize_t nvme_ctrl_reconnect_delay_show(struct device *dev,
+		struct device_attribute *attr, char *buf)
+{
+	struct nvme_ctrl *ctrl = dev_get_drvdata(dev);
+
+	if (ctrl->opts->reconnect_delay == -1)
+		return sysfs_emit(buf, "off\n");
+	return sysfs_emit(buf, "%d\n", ctrl->opts->reconnect_delay);
+}
+
+static ssize_t nvme_ctrl_reconnect_delay_store(struct device *dev,
+		struct device_attribute *attr, const char *buf, size_t count)
+{
+	struct nvme_ctrl *ctrl = dev_get_drvdata(dev);
+	unsigned int v;
+	int err;
+
+	err = kstrtou32(buf, 10, &v);
+	if (err)
+		return err;
+
+	ctrl->opts->reconnect_delay = v;
+	return count;
+}
+static DEVICE_ATTR(reconnect_delay, S_IRUGO | S_IWUSR,
+	nvme_ctrl_reconnect_delay_show, nvme_ctrl_reconnect_delay_store);
 
 static struct attribute *nvme_dev_attrs[] = {
 	&dev_attr_reset_controller.attr,
@@ -2950,6 +3712,13 @@
 	&dev_attr_subsysnqn.attr,
 	&dev_attr_address.attr,
 	&dev_attr_state.attr,
+	&dev_attr_numa_node.attr,
+	&dev_attr_queue_count.attr,
+	&dev_attr_sqsize.attr,
+	&dev_attr_hostnqn.attr,
+	&dev_attr_hostid.attr,
+	&dev_attr_ctrl_loss_tmo.attr,
+	&dev_attr_reconnect_delay.attr,
 	NULL
 };
 
@@ -2962,6 +3731,14 @@
 	if (a == &dev_attr_delete_controller.attr && !ctrl->ops->delete_ctrl)
 		return 0;
 	if (a == &dev_attr_address.attr && !ctrl->ops->get_address)
+		return 0;
+	if (a == &dev_attr_hostnqn.attr && !ctrl->opts)
+		return 0;
+	if (a == &dev_attr_hostid.attr && !ctrl->opts)
+		return 0;
+	if (a == &dev_attr_ctrl_loss_tmo.attr && !ctrl->opts)
+		return 0;
+	if (a == &dev_attr_reconnect_delay.attr && !ctrl->opts)
 		return 0;
 
 	return a->mode;
@@ -2977,7 +3754,7 @@
 	NULL,
 };
 
-static struct nvme_ns_head *__nvme_find_ns_head(struct nvme_subsystem *subsys,
+static struct nvme_ns_head *nvme_find_ns_head(struct nvme_subsystem *subsys,
 		unsigned nsid)
 {
 	struct nvme_ns_head *h;
@@ -2992,17 +3769,15 @@
 	return NULL;
 }
 
-static int __nvme_check_ids(struct nvme_subsystem *subsys,
-		struct nvme_ns_head *new)
+static int nvme_subsys_check_duplicate_ids(struct nvme_subsystem *subsys,
+		struct nvme_ns_ids *ids)
 {
 	struct nvme_ns_head *h;
 
 	lockdep_assert_held(&subsys->lock);
 
 	list_for_each_entry(h, &subsys->nsheads, entry) {
-		if (nvme_ns_ids_valid(&new->ids) &&
-		    !list_empty(&h->list) &&
-		    nvme_ns_ids_equal(&new->ids, &h->ids))
+		if (nvme_ns_ids_valid(ids) && nvme_ns_ids_equal(ids, &h->ids))
 			return -EINVAL;
 	}
 
@@ -3010,12 +3785,17 @@
 }
 
 static struct nvme_ns_head *nvme_alloc_ns_head(struct nvme_ctrl *ctrl,
-		unsigned nsid, struct nvme_id_ns *id)
+		unsigned nsid, struct nvme_ns_ids *ids)
 {
 	struct nvme_ns_head *head;
+	size_t size = sizeof(*head);
 	int ret = -ENOMEM;
 
-	head = kzalloc(sizeof(*head), GFP_KERNEL);
+#ifdef CONFIG_NVME_MULTIPATH
+	size += num_possible_nodes() * sizeof(struct nvme_ns *);
+#endif
+
+	head = kzalloc(size, GFP_KERNEL);
 	if (!head)
 		goto out;
 	ret = ida_simple_get(&ctrl->subsys->ns_ida, 1, 0, GFP_KERNEL);
@@ -3028,16 +3808,22 @@
 		goto out_ida_remove;
 	head->subsys = ctrl->subsys;
 	head->ns_id = nsid;
+	head->ids = *ids;
 	kref_init(&head->ref);
 
-	nvme_report_ns_ids(ctrl, nsid, id, &head->ids);
-
-	ret = __nvme_check_ids(ctrl->subsys, head);
+	ret = nvme_subsys_check_duplicate_ids(ctrl->subsys, &head->ids);
 	if (ret) {
 		dev_err(ctrl->device,
 			"duplicate IDs for nsid %d\n", nsid);
 		goto out_cleanup_srcu;
 	}
+
+	if (head->ids.csi) {
+		ret = nvme_get_effects_log(ctrl, head->ids.csi, &head->effects);
+		if (ret)
+			goto out_cleanup_srcu;
+	} else
+		head->effects = ctrl->effects;
 
 	ret = nvme_mpath_alloc_disk(ctrl, head);
 	if (ret)
@@ -3055,56 +3841,55 @@
 out_free_head:
 	kfree(head);
 out:
+	if (ret > 0)
+		ret = blk_status_to_errno(nvme_error_status(ret));
 	return ERR_PTR(ret);
 }
 
 static int nvme_init_ns_head(struct nvme_ns *ns, unsigned nsid,
-		struct nvme_id_ns *id)
+		struct nvme_ns_ids *ids, bool is_shared)
 {
 	struct nvme_ctrl *ctrl = ns->ctrl;
-	bool is_shared = id->nmic & (1 << 0);
 	struct nvme_ns_head *head = NULL;
 	int ret = 0;
 
 	mutex_lock(&ctrl->subsys->lock);
-	if (is_shared)
-		head = __nvme_find_ns_head(ctrl->subsys, nsid);
+	head = nvme_find_ns_head(ctrl->subsys, nsid);
 	if (!head) {
-		head = nvme_alloc_ns_head(ctrl, nsid, id);
+		head = nvme_alloc_ns_head(ctrl, nsid, ids);
 		if (IS_ERR(head)) {
 			ret = PTR_ERR(head);
 			goto out_unlock;
 		}
+		head->shared = is_shared;
 	} else {
-		struct nvme_ns_ids ids;
-
-		nvme_report_ns_ids(ctrl, nsid, id, &ids);
-		if (!nvme_ns_ids_equal(&head->ids, &ids)) {
+		ret = -EINVAL;
+		if (!is_shared || !head->shared) {
+			dev_err(ctrl->device,
+				"Duplicate unshared namespace %d\n", nsid);
+			goto out_put_ns_head;
+		}
+		if (!nvme_ns_ids_equal(&head->ids, ids)) {
 			dev_err(ctrl->device,
 				"IDs don't match for shared namespace %d\n",
 					nsid);
-			ret = -EINVAL;
-			goto out_unlock;
+			goto out_put_ns_head;
 		}
 	}
 
 	list_add_tail(&ns->siblings, &head->list);
 	ns->head = head;
+	mutex_unlock(&ctrl->subsys->lock);
+	return 0;
 
+out_put_ns_head:
+	nvme_put_ns_head(head);
 out_unlock:
 	mutex_unlock(&ctrl->subsys->lock);
 	return ret;
 }
 
-static int ns_cmp(void *priv, struct list_head *a, struct list_head *b)
-{
-	struct nvme_ns *nsa = container_of(a, struct nvme_ns, list);
-	struct nvme_ns *nsb = container_of(b, struct nvme_ns, list);
-
-	return nsa->head->ns_id - nsb->head->ns_id;
-}
-
-static struct nvme_ns *nvme_find_get_ns(struct nvme_ctrl *ctrl, unsigned nsid)
+struct nvme_ns *nvme_find_get_ns(struct nvme_ctrl *ctrl, unsigned nsid)
 {
 	struct nvme_ns *ns, *ret = NULL;
 
@@ -3122,76 +3907,59 @@
 	up_read(&ctrl->namespaces_rwsem);
 	return ret;
 }
+EXPORT_SYMBOL_NS_GPL(nvme_find_get_ns, NVME_TARGET_PASSTHRU);
 
-static int nvme_setup_streams_ns(struct nvme_ctrl *ctrl, struct nvme_ns *ns)
+/*
+ * Add the namespace to the controller list while keeping the list ordered.
+ */
+static void nvme_ns_add_to_ctrl_list(struct nvme_ns *ns)
 {
-	struct streams_directive_params s;
-	int ret;
+	struct nvme_ns *tmp;
 
-	if (!ctrl->nr_streams)
-		return 0;
-
-	ret = nvme_get_stream_params(ctrl, &s, ns->head->ns_id);
-	if (ret)
-		return ret;
-
-	ns->sws = le32_to_cpu(s.sws);
-	ns->sgs = le16_to_cpu(s.sgs);
-
-	if (ns->sws) {
-		unsigned int bs = 1 << ns->lba_shift;
-
-		blk_queue_io_min(ns->queue, bs * ns->sws);
-		if (ns->sgs)
-			blk_queue_io_opt(ns->queue, bs * ns->sws * ns->sgs);
+	list_for_each_entry_reverse(tmp, &ns->ctrl->namespaces, list) {
+		if (tmp->head->ns_id < ns->head->ns_id) {
+			list_add(&ns->list, &tmp->list);
+			return;
+		}
 	}
-
-	return 0;
+	list_add(&ns->list, &ns->ctrl->namespaces);
 }
 
-static void nvme_alloc_ns(struct nvme_ctrl *ctrl, unsigned nsid)
+static void nvme_alloc_ns(struct nvme_ctrl *ctrl, unsigned nsid,
+		struct nvme_ns_ids *ids)
 {
 	struct nvme_ns *ns;
 	struct gendisk *disk;
 	struct nvme_id_ns *id;
 	char disk_name[DISK_NAME_LEN];
-	int node = dev_to_node(ctrl->dev), flags = GENHD_FL_EXT_DEVT;
+	int node = ctrl->numa_node, flags = GENHD_FL_EXT_DEVT, ret;
+
+	if (nvme_identify_ns(ctrl, nsid, ids, &id))
+		return;
 
 	ns = kzalloc_node(sizeof(*ns), GFP_KERNEL, node);
 	if (!ns)
-		return;
+		goto out_free_id;
 
 	ns->queue = blk_mq_init_queue(ctrl->tagset);
 	if (IS_ERR(ns->queue))
 		goto out_free_ns;
+
+	if (ctrl->opts && ctrl->opts->data_digest)
+		blk_queue_flag_set(QUEUE_FLAG_STABLE_WRITES, ns->queue);
+
 	blk_queue_flag_set(QUEUE_FLAG_NONROT, ns->queue);
+	if (ctrl->ops->flags & NVME_F_PCI_P2PDMA)
+		blk_queue_flag_set(QUEUE_FLAG_PCI_P2PDMA, ns->queue);
+
 	ns->queue->queuedata = ns;
 	ns->ctrl = ctrl;
-
 	kref_init(&ns->kref);
-	ns->lba_shift = 9; /* set to a default value for 512 until disk is validated */
 
-	blk_queue_logical_block_size(ns->queue, 1 << ns->lba_shift);
-	nvme_set_queue_limits(ctrl, ns->queue);
-
-	id = nvme_identify_ns(ctrl, nsid);
-	if (!id)
+	ret = nvme_init_ns_head(ns, nsid, ids, id->nmic & NVME_NS_NMIC_SHARED);
+	if (ret)
 		goto out_free_queue;
-
-	if (id->ncap == 0)
-		goto out_free_id;
-
-	if (nvme_init_ns_head(ns, nsid, id))
-		goto out_free_id;
-	nvme_setup_streams_ns(ctrl, ns);
 	nvme_set_disk_name(disk_name, ns, ctrl, &flags);
-
-	if ((ctrl->quirks & NVME_QUIRK_LIGHTNVM) && id->vs[0] == 0x1) {
-		if (nvme_nvm_register(ns, disk_name, node)) {
-			dev_warn(ctrl->device, "LightNVM init failure\n");
-			goto out_unlink_ns;
-		}
-	}
 
 	disk = alloc_disk_node(0, node);
 	if (!disk)
@@ -3204,38 +3972,46 @@
 	memcpy(disk->disk_name, disk_name, DISK_NAME_LEN);
 	ns->disk = disk;
 
-	__nvme_revalidate_disk(disk, id);
+	if (nvme_update_ns_info(ns, id))
+		goto out_put_disk;
+
+	if ((ctrl->quirks & NVME_QUIRK_LIGHTNVM) && id->vs[0] == 0x1) {
+		ret = nvme_nvm_register(ns, disk_name, node);
+		if (ret) {
+			dev_warn(ctrl->device, "LightNVM init failure\n");
+			goto out_put_disk;
+		}
+	}
 
 	down_write(&ctrl->namespaces_rwsem);
-	list_add_tail(&ns->list, &ctrl->namespaces);
+	nvme_ns_add_to_ctrl_list(ns);
 	up_write(&ctrl->namespaces_rwsem);
-
 	nvme_get_ctrl(ctrl);
 
-	device_add_disk(ctrl->device, ns->disk);
-	if (sysfs_create_group(&disk_to_dev(ns->disk)->kobj,
-					&nvme_ns_id_attr_group))
-		pr_warn("%s: failed to create sysfs group for identification\n",
-			ns->disk->disk_name);
-	if (ns->ndev && nvme_nvm_register_sysfs(ns))
-		pr_warn("%s: failed to register lightnvm sysfs group for identification\n",
-			ns->disk->disk_name);
+	device_add_disk(ctrl->device, ns->disk, nvme_ns_id_attr_groups);
 
 	nvme_mpath_add_disk(ns, id);
-	nvme_fault_inject_init(ns);
+	nvme_fault_inject_init(&ns->fault_inject, ns->disk->disk_name);
 	kfree(id);
 
 	return;
+ out_put_disk:
+	/* prevent double queue cleanup */
+	ns->disk->queue = NULL;
+	put_disk(ns->disk);
  out_unlink_ns:
 	mutex_lock(&ctrl->subsys->lock);
 	list_del_rcu(&ns->siblings);
+	if (list_empty(&ns->head->list))
+		list_del_init(&ns->head->entry);
 	mutex_unlock(&ctrl->subsys->lock);
- out_free_id:
-	kfree(id);
+	nvme_put_ns_head(ns->head);
  out_free_queue:
 	blk_cleanup_queue(ns->queue);
  out_free_ns:
 	kfree(ns);
+ out_free_id:
+	kfree(id);
 }
 
 static void nvme_ns_remove(struct nvme_ns *ns)
@@ -3243,20 +4019,20 @@
 	if (test_and_set_bit(NVME_NS_REMOVING, &ns->flags))
 		return;
 
-	nvme_fault_inject_fini(ns);
+	set_capacity(ns->disk, 0);
+	nvme_fault_inject_fini(&ns->fault_inject);
 
 	mutex_lock(&ns->ctrl->subsys->lock);
 	list_del_rcu(&ns->siblings);
+	if (list_empty(&ns->head->list))
+		list_del_init(&ns->head->entry);
 	mutex_unlock(&ns->ctrl->subsys->lock);
+
 	synchronize_rcu(); /* guarantee not available in head->list */
 	nvme_mpath_clear_current_path(ns);
 	synchronize_srcu(&ns->head->srcu); /* wait for concurrent submissions */
 
-	if (ns->disk && ns->disk->flags & GENHD_FL_UP) {
-		sysfs_remove_group(&disk_to_dev(ns->disk)->kobj,
-					&nvme_ns_id_attr_group);
-		if (ns->ndev)
-			nvme_nvm_unregister_sysfs(ns);
+	if (ns->disk->flags & GENHD_FL_UP) {
 		del_gendisk(ns->disk);
 		blk_cleanup_queue(ns->queue);
 		if (blk_get_integrity(ns->disk))
@@ -3271,17 +4047,91 @@
 	nvme_put_ns(ns);
 }
 
-static void nvme_validate_ns(struct nvme_ctrl *ctrl, unsigned nsid)
+static void nvme_ns_remove_by_nsid(struct nvme_ctrl *ctrl, u32 nsid)
 {
+	struct nvme_ns *ns = nvme_find_get_ns(ctrl, nsid);
+
+	if (ns) {
+		nvme_ns_remove(ns);
+		nvme_put_ns(ns);
+	}
+}
+
+static void nvme_validate_ns(struct nvme_ns *ns, struct nvme_ns_ids *ids)
+{
+	struct nvme_id_ns *id;
+	int ret = NVME_SC_INVALID_NS | NVME_SC_DNR;
+
+	if (test_bit(NVME_NS_DEAD, &ns->flags))
+		goto out;
+
+	ret = nvme_identify_ns(ns->ctrl, ns->head->ns_id, ids, &id);
+	if (ret)
+		goto out;
+
+	ret = NVME_SC_INVALID_NS | NVME_SC_DNR;
+	if (!nvme_ns_ids_equal(&ns->head->ids, ids)) {
+		dev_err(ns->ctrl->device,
+			"identifiers changed for nsid %d\n", ns->head->ns_id);
+		goto out_free_id;
+	}
+
+	ret = nvme_update_ns_info(ns, id);
+
+out_free_id:
+	kfree(id);
+out:
+	/*
+	 * Only remove the namespace if we got a fatal error back from the
+	 * device, otherwise ignore the error and just move on.
+	 *
+	 * TODO: we should probably schedule a delayed retry here.
+	 */
+	if (ret > 0 && (ret & NVME_SC_DNR))
+		nvme_ns_remove(ns);
+	else
+		revalidate_disk_size(ns->disk, true);
+}
+
+static void nvme_validate_or_alloc_ns(struct nvme_ctrl *ctrl, unsigned nsid)
+{
+	struct nvme_ns_ids ids = { };
 	struct nvme_ns *ns;
+
+	if (nvme_identify_ns_descs(ctrl, nsid, &ids))
+		return;
 
 	ns = nvme_find_get_ns(ctrl, nsid);
 	if (ns) {
-		if (ns->disk && revalidate_disk(ns->disk))
-			nvme_ns_remove(ns);
+		nvme_validate_ns(ns, &ids);
 		nvme_put_ns(ns);
-	} else
-		nvme_alloc_ns(ctrl, nsid);
+		return;
+	}
+
+	switch (ids.csi) {
+	case NVME_CSI_NVM:
+		nvme_alloc_ns(ctrl, nsid, &ids);
+		break;
+	case NVME_CSI_ZNS:
+		if (!IS_ENABLED(CONFIG_BLK_DEV_ZONED)) {
+			dev_warn(ctrl->device,
+				"nsid %u not supported without CONFIG_BLK_DEV_ZONED\n",
+				nsid);
+			break;
+		}
+		if (!nvme_multi_css(ctrl)) {
+			dev_warn(ctrl->device,
+				"command set not reported for nsid: %d\n",
+				nsid);
+			break;
+		}
+		nvme_alloc_ns(ctrl, nsid, &ids);
+		break;
+	default:
+		dev_warn(ctrl->device, "unknown csi %u for nsid %u\n",
+			ids.csi, nsid);
+		break;
+	}
 }
 
 static void nvme_remove_invalid_namespaces(struct nvme_ctrl *ctrl,
@@ -3302,39 +4152,41 @@
 
 }
 
-static int nvme_scan_ns_list(struct nvme_ctrl *ctrl, unsigned nn)
+static int nvme_scan_ns_list(struct nvme_ctrl *ctrl)
 {
-	struct nvme_ns *ns;
+	const int nr_entries = NVME_IDENTIFY_DATA_SIZE / sizeof(__le32);
 	__le32 *ns_list;
-	unsigned i, j, nsid, prev = 0;
-	unsigned num_lists = DIV_ROUND_UP_ULL((u64)nn, 1024);
-	int ret = 0;
+	u32 prev = 0;
+	int ret = 0, i;
+
+	if (nvme_ctrl_limited_cns(ctrl))
+		return -EOPNOTSUPP;
 
 	ns_list = kzalloc(NVME_IDENTIFY_DATA_SIZE, GFP_KERNEL);
 	if (!ns_list)
 		return -ENOMEM;
 
-	for (i = 0; i < num_lists; i++) {
-		ret = nvme_identify_ns_list(ctrl, prev, ns_list);
+	for (;;) {
+		struct nvme_command cmd = {
+			.identify.opcode	= nvme_admin_identify,
+			.identify.cns		= NVME_ID_CNS_NS_ACTIVE_LIST,
+			.identify.nsid		= cpu_to_le32(prev),
+		};
+
+		ret = nvme_submit_sync_cmd(ctrl->admin_q, &cmd, ns_list,
+					    NVME_IDENTIFY_DATA_SIZE);
 		if (ret)
 			goto free;
 
-		for (j = 0; j < min(nn, 1024U); j++) {
-			nsid = le32_to_cpu(ns_list[j]);
-			if (!nsid)
+		for (i = 0; i < nr_entries; i++) {
+			u32 nsid = le32_to_cpu(ns_list[i]);
+
+			if (!nsid)	/* end of the list? */
 				goto out;
-
-			nvme_validate_ns(ctrl, nsid);
-
-			while (++prev < nsid) {
-				ns = nvme_find_get_ns(ctrl, prev);
-				if (ns) {
-					nvme_ns_remove(ns);
-					nvme_put_ns(ns);
-				}
-			}
+			nvme_validate_or_alloc_ns(ctrl, nsid);
+			while (++prev < nsid)
+				nvme_ns_remove_by_nsid(ctrl, prev);
 		}
-		nn -= j;
 	}
  out:
 	nvme_remove_invalid_namespaces(ctrl, prev);
@@ -3343,12 +4195,18 @@
 	return ret;
 }
 
-static void nvme_scan_ns_sequential(struct nvme_ctrl *ctrl, unsigned nn)
+static void nvme_scan_ns_sequential(struct nvme_ctrl *ctrl)
 {
-	unsigned i;
+	struct nvme_id_ctrl *id;
+	u32 nn, i;
+
+	if (nvme_identify_ctrl(ctrl, &id))
+		return;
+	nn = le32_to_cpu(id->nn);
+	kfree(id);
 
 	for (i = 1; i <= nn; i++)
-		nvme_validate_ns(ctrl, i);
+		nvme_validate_or_alloc_ns(ctrl, i);
 
 	nvme_remove_invalid_namespaces(ctrl, nn);
 }
@@ -3369,8 +4227,8 @@
 	 * raced with us in reading the log page, which could cause us to miss
 	 * updates.
 	 */
-	error = nvme_get_log(ctrl, NVME_NSID_ALL, NVME_LOG_CHANGED_NS, 0, log,
-			log_size, 0);
+	error = nvme_get_log(ctrl, NVME_NSID_ALL, NVME_LOG_CHANGED_NS, 0,
+			NVME_CSI_NVM, log, log_size, 0);
 	if (error)
 		dev_warn(ctrl->device,
 			"reading changed ns log failed: %d\n", error);
@@ -3382,35 +4240,20 @@
 {
 	struct nvme_ctrl *ctrl =
 		container_of(work, struct nvme_ctrl, scan_work);
-	struct nvme_id_ctrl *id;
-	unsigned nn;
 
-	if (ctrl->state != NVME_CTRL_LIVE)
+	/* No tagset on a live ctrl means IO queues could not created */
+	if (ctrl->state != NVME_CTRL_LIVE || !ctrl->tagset)
 		return;
-
-	WARN_ON_ONCE(!ctrl->tagset);
 
 	if (test_and_clear_bit(NVME_AER_NOTICE_NS_CHANGED, &ctrl->events)) {
 		dev_info(ctrl->device, "rescanning namespaces.\n");
 		nvme_clear_changed_ns_log(ctrl);
 	}
 
-	if (nvme_identify_ctrl(ctrl, &id))
-		return;
-
 	mutex_lock(&ctrl->scan_lock);
-	nn = le32_to_cpu(id->nn);
-	if (!nvme_ctrl_limited_cns(ctrl)) {
-		if (!nvme_scan_ns_list(ctrl, nn))
-			goto out_free_id;
-	}
-	nvme_scan_ns_sequential(ctrl, nn);
-out_free_id:
+	if (nvme_scan_ns_list(ctrl) != 0)
+		nvme_scan_ns_sequential(ctrl);
 	mutex_unlock(&ctrl->scan_lock);
-	kfree(id);
-	down_write(&ctrl->namespaces_rwsem);
-	list_sort(NULL, &ctrl->namespaces, ns_cmp);
-	up_write(&ctrl->namespaces_rwsem);
 }
 
 /*
@@ -3422,6 +4265,13 @@
 {
 	struct nvme_ns *ns, *next;
 	LIST_HEAD(ns_list);
+
+	/*
+	 * make sure to requeue I/O to all namespaces as these
+	 * might result from the scan itself and must complete
+	 * for the scan_work to make progress
+	 */
+	nvme_mpath_clear_ctrl_paths(ctrl);
 
 	/* prevent racing with ns scanning */
 	flush_work(&ctrl->scan_work);
@@ -3435,6 +4285,9 @@
 	if (ctrl->state == NVME_CTRL_DEAD)
 		nvme_kill_queues(ctrl);
 
+	/* this is a no-op when called from the controller reset handler */
+	nvme_change_ctrl_state(ctrl, NVME_CTRL_DELETING_NOIO);
+
 	down_write(&ctrl->namespaces_rwsem);
 	list_splice_init(&ctrl->namespaces, &ns_list);
 	up_write(&ctrl->namespaces_rwsem);
@@ -3443,6 +4296,33 @@
 		nvme_ns_remove(ns);
 }
 EXPORT_SYMBOL_GPL(nvme_remove_namespaces);
+
+static int nvme_class_uevent(struct device *dev, struct kobj_uevent_env *env)
+{
+	struct nvme_ctrl *ctrl =
+		container_of(dev, struct nvme_ctrl, ctrl_device);
+	struct nvmf_ctrl_options *opts = ctrl->opts;
+	int ret;
+
+	ret = add_uevent_var(env, "NVME_TRTYPE=%s", ctrl->ops->name);
+	if (ret)
+		return ret;
+
+	if (opts) {
+		ret = add_uevent_var(env, "NVME_TRADDR=%s", opts->traddr);
+		if (ret)
+			return ret;
+
+		ret = add_uevent_var(env, "NVME_TRSVCID=%s",
+				opts->trsvcid ?: "none");
+		if (ret)
+			return ret;
+
+		ret = add_uevent_var(env, "NVME_HOST_TRADDR=%s",
+				opts->host_traddr ?: "none");
+	}
+	return ret;
+}
 
 static void nvme_aen_uevent(struct nvme_ctrl *ctrl)
 {
@@ -3498,8 +4378,8 @@
 	if (!log)
 		return;
 
-	if (nvme_get_log(ctrl, NVME_NSID_ALL, NVME_LOG_FW_SLOT, 0, log,
-			sizeof(*log), 0))
+	if (nvme_get_log(ctrl, NVME_NSID_ALL, NVME_LOG_FW_SLOT, 0, NVME_CSI_NVM,
+			log, sizeof(*log), 0))
 		dev_warn(ctrl->device, "Get FW SLOT INFO log error\n");
 	kfree(log);
 }
@@ -3522,13 +4402,13 @@
 		if (time_after(jiffies, fw_act_timeout)) {
 			dev_warn(ctrl->device,
 				"Fw activation timeout, reset controller\n");
-			nvme_reset_ctrl(ctrl);
-			break;
+			nvme_try_sched_reset(ctrl);
+			return;
 		}
 		msleep(100);
 	}
 
-	if (ctrl->state != NVME_CTRL_LIVE)
+	if (!nvme_change_ctrl_state(ctrl, NVME_CTRL_LIVE))
 		return;
 
 	nvme_start_queues(ctrl);
@@ -3536,15 +4416,33 @@
 	nvme_get_fw_slot_info(ctrl);
 }
 
+static u32 nvme_aer_type(u32 result)
+{
+	return result & 0x7;
+}
+
+static u32 nvme_aer_subtype(u32 result)
+{
+	return (result & 0xff00) >> 8;
+}
+
 static void nvme_handle_aen_notice(struct nvme_ctrl *ctrl, u32 result)
 {
-	switch ((result & 0xff00) >> 8) {
+	u32 aer_notice_type = nvme_aer_subtype(result);
+
+	switch (aer_notice_type) {
 	case NVME_AER_NOTICE_NS_CHANGED:
 		set_bit(NVME_AER_NOTICE_NS_CHANGED, &ctrl->events);
 		nvme_queue_scan(ctrl);
 		break;
 	case NVME_AER_NOTICE_FW_ACT_STARTING:
-		queue_work(nvme_wq, &ctrl->fw_act_work);
+		/*
+		 * We are (ab)using the RESETTING state to prevent subsequent
+		 * recovery actions from interfering with the controller's
+		 * firmware activation.
+		 */
+		if (nvme_change_ctrl_state(ctrl, NVME_CTRL_RESETTING))
+			queue_work(nvme_wq, &ctrl->fw_act_work);
 		break;
 #ifdef CONFIG_NVME_MULTIPATH
 	case NVME_AER_NOTICE_ANA:
@@ -3553,24 +4451,45 @@
 		queue_work(nvme_wq, &ctrl->ana_work);
 		break;
 #endif
+	case NVME_AER_NOTICE_DISC_CHANGED:
+		ctrl->aen_result = result;
+		break;
 	default:
 		dev_warn(ctrl->device, "async event result %08x\n", result);
 	}
+}
+
+static void nvme_handle_aer_persistent_error(struct nvme_ctrl *ctrl)
+{
+	dev_warn(ctrl->device, "resetting controller due to AER\n");
+	nvme_reset_ctrl(ctrl);
 }
 
 void nvme_complete_async_event(struct nvme_ctrl *ctrl, __le16 status,
 		volatile union nvme_result *res)
 {
 	u32 result = le32_to_cpu(res->u32);
+	u32 aer_type = nvme_aer_type(result);
+	u32 aer_subtype = nvme_aer_subtype(result);
 
 	if (le16_to_cpu(status) >> 1 != NVME_SC_SUCCESS)
 		return;
 
-	switch (result & 0x7) {
+	trace_nvme_async_event(ctrl, result);
+	switch (aer_type) {
 	case NVME_AER_NOTICE:
 		nvme_handle_aen_notice(ctrl, result);
 		break;
 	case NVME_AER_ERROR:
+		/*
+		 * For a persistent internal error, don't run async_event_work
+		 * to submit a new AER. The controller reset will do it.
+		 */
+		if (aer_subtype == NVME_AER_ERROR_PERSIST_INT_ERR) {
+			nvme_handle_aer_persistent_error(ctrl);
+			return;
+		}
+		fallthrough;
 	case NVME_AER_SMART:
 	case NVME_AER_CSS:
 	case NVME_AER_VS:
@@ -3596,25 +4515,40 @@
 
 void nvme_start_ctrl(struct nvme_ctrl *ctrl)
 {
-	if (ctrl->kato)
-		nvme_start_keep_alive(ctrl);
+	nvme_start_keep_alive(ctrl);
+
+	nvme_enable_aen(ctrl);
 
 	if (ctrl->queue_count > 1) {
 		nvme_queue_scan(ctrl);
-		nvme_enable_aen(ctrl);
-		queue_work(nvme_wq, &ctrl->async_event_work);
 		nvme_start_queues(ctrl);
+		nvme_mpath_update(ctrl);
 	}
-	ctrl->created = true;
 }
 EXPORT_SYMBOL_GPL(nvme_start_ctrl);
 
 void nvme_uninit_ctrl(struct nvme_ctrl *ctrl)
 {
+	nvme_hwmon_exit(ctrl);
+	nvme_fault_inject_fini(&ctrl->fault_inject);
 	dev_pm_qos_hide_latency_tolerance(ctrl->device);
 	cdev_device_del(&ctrl->cdev, ctrl->device);
+	nvme_put_ctrl(ctrl);
 }
 EXPORT_SYMBOL_GPL(nvme_uninit_ctrl);
+
+static void nvme_free_cels(struct nvme_ctrl *ctrl)
+{
+	struct nvme_effects_log	*cel;
+	unsigned long i;
+
+	xa_for_each (&ctrl->cels, i, cel) {
+		xa_erase(&ctrl->cels, i);
+		kfree(cel);
+	}
+
+	xa_destroy(&ctrl->cels);
+}
 
 static void nvme_free_ctrl(struct device *dev)
 {
@@ -3622,16 +4556,18 @@
 		container_of(dev, struct nvme_ctrl, ctrl_device);
 	struct nvme_subsystem *subsys = ctrl->subsys;
 
-	ida_simple_remove(&nvme_instance_ida, ctrl->instance);
-	kfree(ctrl->effects);
+	if (!subsys || ctrl->instance != subsys->instance)
+		ida_simple_remove(&nvme_instance_ida, ctrl->instance);
+
+	nvme_free_cels(ctrl);
 	nvme_mpath_uninit(ctrl);
 	__free_page(ctrl->discard_page);
 
 	if (subsys) {
-		mutex_lock(&subsys->lock);
+		mutex_lock(&nvme_subsystems_lock);
 		list_del(&ctrl->subsys_entry);
-		mutex_unlock(&subsys->lock);
 		sysfs_remove_link(&subsys->dev.kobj, dev_name(ctrl->device));
+		mutex_unlock(&nvme_subsystems_lock);
 	}
 
 	ctrl->ops->free_ctrl(ctrl);
@@ -3654,14 +4590,17 @@
 	spin_lock_init(&ctrl->lock);
 	mutex_init(&ctrl->scan_lock);
 	INIT_LIST_HEAD(&ctrl->namespaces);
+	xa_init(&ctrl->cels);
 	init_rwsem(&ctrl->namespaces_rwsem);
 	ctrl->dev = dev;
 	ctrl->ops = ops;
 	ctrl->quirks = quirks;
+	ctrl->numa_node = NUMA_NO_NODE;
 	INIT_WORK(&ctrl->scan_work, nvme_scan_work);
 	INIT_WORK(&ctrl->async_event_work, nvme_async_event_work);
 	INIT_WORK(&ctrl->fw_act_work, nvme_fw_act_work);
 	INIT_WORK(&ctrl->delete_work, nvme_delete_ctrl_work);
+	init_waitqueue_head(&ctrl->state_wq);
 
 	INIT_DELAYED_WORK(&ctrl->ka_work, nvme_keep_alive_work);
 	memset(&ctrl->ka_cmd, 0, sizeof(ctrl->ka_cmd));
@@ -3692,6 +4631,7 @@
 	if (ret)
 		goto out_release_instance;
 
+	nvme_get_ctrl(ctrl);
 	cdev_init(&ctrl->cdev, &nvme_dev_fops);
 	ctrl->cdev.owner = ops->module;
 	ret = cdev_device_add(&ctrl->cdev, ctrl->device);
@@ -3706,8 +4646,12 @@
 	dev_pm_qos_update_user_latency_tolerance(ctrl->device,
 		min(default_ps_max_latency_us, (unsigned long)S32_MAX));
 
+	nvme_fault_inject_init(&ctrl->fault_inject, dev_name(ctrl->device));
+	nvme_mpath_init_ctrl(ctrl);
+
 	return 0;
 out_free_name:
+	nvme_put_ctrl(ctrl);
 	kfree_const(ctrl->device->kobj.name);
 out_release_instance:
 	ida_simple_remove(&nvme_instance_ida, ctrl->instance);
@@ -3753,7 +4697,7 @@
 }
 EXPORT_SYMBOL_GPL(nvme_unfreeze);
 
-void nvme_wait_freeze_timeout(struct nvme_ctrl *ctrl, long timeout)
+int nvme_wait_freeze_timeout(struct nvme_ctrl *ctrl, long timeout)
 {
 	struct nvme_ns *ns;
 
@@ -3764,6 +4708,7 @@
 			break;
 	}
 	up_read(&ctrl->namespaces_rwsem);
+	return timeout;
 }
 EXPORT_SYMBOL_GPL(nvme_wait_freeze_timeout);
 
@@ -3811,9 +4756,65 @@
 }
 EXPORT_SYMBOL_GPL(nvme_start_queues);
 
-int __init nvme_core_init(void)
+void nvme_sync_io_queues(struct nvme_ctrl *ctrl)
+{
+	struct nvme_ns *ns;
+
+	down_read(&ctrl->namespaces_rwsem);
+	list_for_each_entry(ns, &ctrl->namespaces, list)
+		blk_sync_queue(ns->queue);
+	up_read(&ctrl->namespaces_rwsem);
+}
+EXPORT_SYMBOL_GPL(nvme_sync_io_queues);
+
+void nvme_sync_queues(struct nvme_ctrl *ctrl)
+{
+	nvme_sync_io_queues(ctrl);
+	if (ctrl->admin_q)
+		blk_sync_queue(ctrl->admin_q);
+}
+EXPORT_SYMBOL_GPL(nvme_sync_queues);
+
+struct nvme_ctrl *nvme_ctrl_from_file(struct file *file)
+{
+	if (file->f_op != &nvme_dev_fops)
+		return NULL;
+	return file->private_data;
+}
+EXPORT_SYMBOL_NS_GPL(nvme_ctrl_from_file, NVME_TARGET_PASSTHRU);
+
+/*
+ * Check we didn't inadvertently grow the command structure sizes:
+ */
+static inline void _nvme_check_size(void)
+{
+	BUILD_BUG_ON(sizeof(struct nvme_common_command) != 64);
+	BUILD_BUG_ON(sizeof(struct nvme_rw_command) != 64);
+	BUILD_BUG_ON(sizeof(struct nvme_identify) != 64);
+	BUILD_BUG_ON(sizeof(struct nvme_features) != 64);
+	BUILD_BUG_ON(sizeof(struct nvme_download_firmware) != 64);
+	BUILD_BUG_ON(sizeof(struct nvme_format_cmd) != 64);
+	BUILD_BUG_ON(sizeof(struct nvme_dsm_cmd) != 64);
+	BUILD_BUG_ON(sizeof(struct nvme_write_zeroes_cmd) != 64);
+	BUILD_BUG_ON(sizeof(struct nvme_abort_cmd) != 64);
+	BUILD_BUG_ON(sizeof(struct nvme_get_log_page_command) != 64);
+	BUILD_BUG_ON(sizeof(struct nvme_command) != 64);
+	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_ctrl_zns) != 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);
+}
+
+
+static int __init nvme_core_init(void)
 {
 	int result = -ENOMEM;
+
+	_nvme_check_size();
 
 	nvme_wq = alloc_workqueue("nvme-wq",
 			WQ_UNBOUND | WQ_MEM_RECLAIM | WQ_SYSFS, 0);
@@ -3839,6 +4840,7 @@
 		result = PTR_ERR(nvme_class);
 		goto unregister_chrdev;
 	}
+	nvme_class->dev_uevent = nvme_class_uevent;
 
 	nvme_subsys_class = class_create(THIS_MODULE, "nvme-subsystem");
 	if (IS_ERR(nvme_subsys_class)) {
@@ -3861,15 +4863,15 @@
 	return result;
 }
 
-void nvme_core_exit(void)
+static void __exit nvme_core_exit(void)
 {
-	ida_destroy(&nvme_subsystems_ida);
 	class_destroy(nvme_subsys_class);
 	class_destroy(nvme_class);
 	unregister_chrdev_region(nvme_chr_devt, NVME_MINORS);
 	destroy_workqueue(nvme_delete_wq);
 	destroy_workqueue(nvme_reset_wq);
 	destroy_workqueue(nvme_wq);
+	ida_destroy(&nvme_instance_ida);
 }
 
 MODULE_LICENSE("GPL");

--
Gitblit v1.6.2