Merge branch 'for-3.19/drivers' of git://git.kernel.dk/linux-block

Pull block layer driver updates from Jens Axboe:

 - NVMe updates:
        - The blk-mq conversion from Matias (and others)

        - A stack of NVMe bug fixes from the nvme tree, mostly from Keith.

        - Various bug fixes from me, fixing issues in both the blk-mq
          conversion and generic bugs.

        - Abort and CPU online fix from Sam.

        - Hot add/remove fix from Indraneel.

 - A couple of drbd fixes from the drbd team (Andreas, Lars, Philipp)

 - With the generic IO stat accounting from 3.19/core, converting md,
   bcache, and rsxx to use those.  From Gu Zheng.

 - Boundary check for queue/irq mode for null_blk from Matias.  Fixes
   cases where invalid values could be given, causing the device to hang.

 - The xen blkfront pull request, with two bug fixes from Vitaly.

* 'for-3.19/drivers' of git://git.kernel.dk/linux-block: (56 commits)
  NVMe: fix race condition in nvme_submit_sync_cmd()
  NVMe: fix retry/error logic in nvme_queue_rq()
  NVMe: Fix FS mount issue (hot-remove followed by hot-add)
  NVMe: fix error return checking from blk_mq_alloc_request()
  NVMe: fix freeing of wrong request in abort path
  xen/blkfront: remove redundant flush_op
  xen/blkfront: improve protection against issuing unsupported REQ_FUA
  NVMe: Fix command setup on IO retry
  null_blk: boundary check queue_mode and irqmode
  block/rsxx: use generic io stats accounting functions to simplify io stat accounting
  md: use generic io stats accounting functions to simplify io stat accounting
  drbd: use generic io stats accounting functions to simplify io stat accounting
  md/bcache: use generic io stats accounting functions to simplify io stat accounting
  NVMe: Update module version major number
  NVMe: fail pci initialization if the device doesn't have any BARs
  NVMe: add ->exit_hctx() hook
  NVMe: make setup work for devices that don't do INTx
  NVMe: enable IO stats by default
  NVMe: nvme_submit_async_admin_req() must use atomic rq allocation
  NVMe: replace blk_put_request() with blk_mq_free_request()
  ...

drivers/block/drbd/drbd_actlog.c

@@ -827,8 +827,7 @@ static int update_sync_bits(struct drbd_device *device,
  *
  */
 int __drbd_change_sync(struct drbd_device *device, sector_t sector, int size,
-		enum update_sync_bits_mode mode,
-		const char *file, const unsigned int line)
+		enum update_sync_bits_mode mode)
 {
 	/* Is called from worker and receiver context _only_ */
 	unsigned long sbnr, ebnr, lbnr;

drivers/block/drbd/drbd_int.h

@@ -1454,7 +1454,6 @@ extern int is_valid_ar_handle(struct drbd_request *, sector_t);
 
 
 /* drbd_nl.c */
-extern int drbd_msg_put_info(struct sk_buff *skb, const char *info);
 extern void drbd_suspend_io(struct drbd_device *device);
 extern void drbd_resume_io(struct drbd_device *device);
 extern char *ppsize(char *buf, unsigned long long size);
@@ -1558,52 +1557,31 @@ extern void drbd_set_recv_tcq(struct drbd_device *device, int tcq_enabled);
 extern void _drbd_clear_done_ee(struct drbd_device *device, struct list_head *to_be_freed);
 extern int drbd_connected(struct drbd_peer_device *);
 
-/* Yes, there is kernel_setsockopt, but only since 2.6.18.
- * So we have our own copy of it here. */
-static inline int drbd_setsockopt(struct socket *sock, int level, int optname,
-				  char *optval, int optlen)
-{
-	mm_segment_t oldfs = get_fs();
-	char __user *uoptval;
-	int err;
-
-	uoptval = (char __user __force *)optval;
-
-	set_fs(KERNEL_DS);
-	if (level == SOL_SOCKET)
-		err = sock_setsockopt(sock, level, optname, uoptval, optlen);
-	else
-		err = sock->ops->setsockopt(sock, level, optname, uoptval,
-					    optlen);
-	set_fs(oldfs);
-	return err;
-}
-
 static inline void drbd_tcp_cork(struct socket *sock)
 {
 	int val = 1;
-	(void) drbd_setsockopt(sock, SOL_TCP, TCP_CORK,
+	(void) kernel_setsockopt(sock, SOL_TCP, TCP_CORK,
 			(char*)&val, sizeof(val));
 }
 
 static inline void drbd_tcp_uncork(struct socket *sock)
 {
 	int val = 0;
-	(void) drbd_setsockopt(sock, SOL_TCP, TCP_CORK,
+	(void) kernel_setsockopt(sock, SOL_TCP, TCP_CORK,
 			(char*)&val, sizeof(val));
 }
 
 static inline void drbd_tcp_nodelay(struct socket *sock)
 {
 	int val = 1;
-	(void) drbd_setsockopt(sock, SOL_TCP, TCP_NODELAY,
+	(void) kernel_setsockopt(sock, SOL_TCP, TCP_NODELAY,
 			(char*)&val, sizeof(val));
 }
 
 static inline void drbd_tcp_quickack(struct socket *sock)
 {
 	int val = 2;
-	(void) drbd_setsockopt(sock, SOL_TCP, TCP_QUICKACK,
+	(void) kernel_setsockopt(sock, SOL_TCP, TCP_QUICKACK,
 			(char*)&val, sizeof(val));
 }
 
@@ -1662,14 +1640,13 @@ extern void drbd_advance_rs_marks(struct drbd_device *device, unsigned long stil
 
 enum update_sync_bits_mode { RECORD_RS_FAILED, SET_OUT_OF_SYNC, SET_IN_SYNC };
 extern int __drbd_change_sync(struct drbd_device *device, sector_t sector, int size,
-		enum update_sync_bits_mode mode,
-		const char *file, const unsigned int line);
+		enum update_sync_bits_mode mode);
 #define drbd_set_in_sync(device, sector, size) \
-	__drbd_change_sync(device, sector, size, SET_IN_SYNC, __FILE__, __LINE__)
+	__drbd_change_sync(device, sector, size, SET_IN_SYNC)
 #define drbd_set_out_of_sync(device, sector, size) \
-	__drbd_change_sync(device, sector, size, SET_OUT_OF_SYNC, __FILE__, __LINE__)
+	__drbd_change_sync(device, sector, size, SET_OUT_OF_SYNC)
 #define drbd_rs_failed_io(device, sector, size) \
-	__drbd_change_sync(device, sector, size, RECORD_RS_FAILED, __FILE__, __LINE__)
+	__drbd_change_sync(device, sector, size, RECORD_RS_FAILED)
 extern void drbd_al_shrink(struct drbd_device *device);
 extern int drbd_initialize_al(struct drbd_device *, void *);
 

drivers/block/drbd/drbd_main.c

@@ -2532,10 +2532,6 @@ int set_resource_options(struct drbd_resource *resource, struct res_opts *res_op
 
 	if (!zalloc_cpumask_var(&new_cpu_mask, GFP_KERNEL))
 		return -ENOMEM;
-		/*
-		retcode = ERR_NOMEM;
-		drbd_msg_put_info("unable to allocate cpumask");
-		*/
 
 	/* silently ignore cpu mask on UP kernel */
 	if (nr_cpu_ids > 1 && res_opts->cpu_mask[0] != 0) {
@@ -2731,7 +2727,7 @@ enum drbd_ret_code drbd_create_device(struct drbd_config_context *adm_ctx, unsig
 
 	device = minor_to_device(minor);
 	if (device)
-		return ERR_MINOR_EXISTS;
+		return ERR_MINOR_OR_VOLUME_EXISTS;
 
 	/* GFP_KERNEL, we are outside of all write-out paths */
 	device = kzalloc(sizeof(struct drbd_device), GFP_KERNEL);
@@ -2793,20 +2789,16 @@ enum drbd_ret_code drbd_create_device(struct drbd_config_context *adm_ctx, unsig
 
 	id = idr_alloc(&drbd_devices, device, minor, minor + 1, GFP_KERNEL);
 	if (id < 0) {
-		if (id == -ENOSPC) {
-			err = ERR_MINOR_EXISTS;
-			drbd_msg_put_info(adm_ctx->reply_skb, "requested minor exists already");
-		}
+		if (id == -ENOSPC)
+			err = ERR_MINOR_OR_VOLUME_EXISTS;
 		goto out_no_minor_idr;
 	}
 	kref_get(&device->kref);
 
 	id = idr_alloc(&resource->devices, device, vnr, vnr + 1, GFP_KERNEL);
 	if (id < 0) {
-		if (id == -ENOSPC) {
-			err = ERR_MINOR_EXISTS;
-			drbd_msg_put_info(adm_ctx->reply_skb, "requested minor exists already");
-		}
+		if (id == -ENOSPC)
+			err = ERR_MINOR_OR_VOLUME_EXISTS;
 		goto out_idr_remove_minor;
 	}
 	kref_get(&device->kref);
@@ -2825,10 +2817,8 @@ enum drbd_ret_code drbd_create_device(struct drbd_config_context *adm_ctx, unsig
 
 		id = idr_alloc(&connection->peer_devices, peer_device, vnr, vnr + 1, GFP_KERNEL);
 		if (id < 0) {
-			if (id == -ENOSPC) {
+			if (id == -ENOSPC)
 				err = ERR_INVALID_REQUEST;
-				drbd_msg_put_info(adm_ctx->reply_skb, "requested volume exists already");
-			}
 			goto out_idr_remove_from_resource;
 		}
 		kref_get(&connection->kref);
@@ -2836,7 +2826,6 @@ enum drbd_ret_code drbd_create_device(struct drbd_config_context *adm_ctx, unsig
 
 	if (init_submitter(device)) {
 		err = ERR_NOMEM;
-		drbd_msg_put_info(adm_ctx->reply_skb, "unable to create submit workqueue");
 		goto out_idr_remove_vol;
 	}
 

drivers/block/drbd/drbd_nl.c

@@ -92,7 +92,7 @@ static void drbd_adm_send_reply(struct sk_buff *skb, struct genl_info *info)
 
 /* Used on a fresh "drbd_adm_prepare"d reply_skb, this cannot fail: The only
  * reason it could fail was no space in skb, and there are 4k available. */
-int drbd_msg_put_info(struct sk_buff *skb, const char *info)
+static int drbd_msg_put_info(struct sk_buff *skb, const char *info)
 {
 	struct nlattr *nla;
 	int err = -EMSGSIZE;
@@ -588,7 +588,7 @@ drbd_set_role(struct drbd_device *const device, enum drbd_role new_role, int for
 	val.i  = 0; val.role  = new_role;
 
 	while (try++ < max_tries) {
-		rv = _drbd_request_state(device, mask, val, CS_WAIT_COMPLETE);
+		rv = _drbd_request_state_holding_state_mutex(device, mask, val, CS_WAIT_COMPLETE);
 
 		/* in case we first succeeded to outdate,
 		 * but now suddenly could establish a connection */
@@ -2052,7 +2052,7 @@ check_net_options(struct drbd_connection *connection, struct net_conf *new_net_c
 	rv = _check_net_options(connection, rcu_dereference(connection->net_conf), new_net_conf);
 	rcu_read_unlock();
 
-	/* connection->volumes protected by genl_lock() here */
+	/* connection->peer_devices protected by genl_lock() here */
 	idr_for_each_entry(&connection->peer_devices, peer_device, i) {
 		struct drbd_device *device = peer_device->device;
 		if (!device->bitmap) {
@@ -3483,7 +3483,7 @@ int drbd_adm_new_minor(struct sk_buff *skb, struct genl_info *info)
 	 * that first_peer_device(device)->connection and device->vnr match the request. */
 	if (adm_ctx.device) {
 		if (info->nlhdr->nlmsg_flags & NLM_F_EXCL)
-			retcode = ERR_MINOR_EXISTS;
+			retcode = ERR_MINOR_OR_VOLUME_EXISTS;
 		/* else: still NO_ERROR */
 		goto out;
 	}
@@ -3530,6 +3530,27 @@ out:
 	return 0;
 }
 
+static int adm_del_resource(struct drbd_resource *resource)
+{
+	struct drbd_connection *connection;
+
+	for_each_connection(connection, resource) {
+		if (connection->cstate > C_STANDALONE)
+			return ERR_NET_CONFIGURED;
+	}
+	if (!idr_is_empty(&resource->devices))
+		return ERR_RES_IN_USE;
+
+	list_del_rcu(&resource->resources);
+	/* Make sure all threads have actually stopped: state handling only
+	 * does drbd_thread_stop_nowait(). */
+	list_for_each_entry(connection, &resource->connections, connections)
+		drbd_thread_stop(&connection->worker);
+	synchronize_rcu();
+	drbd_free_resource(resource);
+	return NO_ERROR;
+}
+
 int drbd_adm_down(struct sk_buff *skb, struct genl_info *info)
 {
 	struct drbd_config_context adm_ctx;
@@ -3575,14 +3596,6 @@ int drbd_adm_down(struct sk_buff *skb, struct genl_info *info)
 		}
 	}
 
-	/* If we reach this, all volumes (of this connection) are Secondary,
-	 * Disconnected, Diskless, aka Unconfigured. Make sure all threads have
-	 * actually stopped, state handling only does drbd_thread_stop_nowait(). */
-	for_each_connection(connection, resource)
-		drbd_thread_stop(&connection->worker);
-
-	/* Now, nothing can fail anymore */
-
 	/* delete volumes */
 	idr_for_each_entry(&resource->devices, device, i) {
 		retcode = adm_del_minor(device);
@@ -3593,10 +3606,7 @@ int drbd_adm_down(struct sk_buff *skb, struct genl_info *info)
 		}
 	}
 
-	list_del_rcu(&resource->resources);
-	synchronize_rcu();
-	drbd_free_resource(resource);
-	retcode = NO_ERROR;
+	retcode = adm_del_resource(resource);
 out:
 	mutex_unlock(&resource->adm_mutex);
 finish:
@@ -3608,7 +3618,6 @@ int drbd_adm_del_resource(struct sk_buff *skb, struct genl_info *info)
 {
 	struct drbd_config_context adm_ctx;
 	struct drbd_resource *resource;
-	struct drbd_connection *connection;
 	enum drbd_ret_code retcode;
 
 	retcode = drbd_adm_prepare(&adm_ctx, skb, info, DRBD_ADM_NEED_RESOURCE);
@@ -3616,27 +3625,10 @@ int drbd_adm_del_resource(struct sk_buff *skb, struct genl_info *info)
 		return retcode;
 	if (retcode != NO_ERROR)
 		goto finish;
-
 	resource = adm_ctx.resource;
-	mutex_lock(&resource->adm_mutex);
-	for_each_connection(connection, resource) {
-		if (connection->cstate > C_STANDALONE) {
-			retcode = ERR_NET_CONFIGURED;
-			goto out;
-		}
-	}
-	if (!idr_is_empty(&resource->devices)) {
-		retcode = ERR_RES_IN_USE;
-		goto out;
-	}
 
-	list_del_rcu(&resource->resources);
-	for_each_connection(connection, resource)
-		drbd_thread_stop(&connection->worker);
-	synchronize_rcu();
-	drbd_free_resource(resource);
-	retcode = NO_ERROR;
-out:
+	mutex_lock(&resource->adm_mutex);
+	retcode = adm_del_resource(resource);
 	mutex_unlock(&resource->adm_mutex);
 finish:
 	drbd_adm_finish(&adm_ctx, info, retcode);

drivers/block/drbd/drbd_receiver.c

@@ -2482,7 +2482,7 @@ bool drbd_rs_c_min_rate_throttle(struct drbd_device *device)
 			atomic_read(&device->rs_sect_ev);
 
 	if (atomic_read(&device->ap_actlog_cnt)
-	    || !device->rs_last_events || curr_events - device->rs_last_events > 64) {
+	    || curr_events - device->rs_last_events > 64) {
 		unsigned long rs_left;
 		int i;
 

drivers/block/drbd/drbd_req.c

@@ -36,29 +36,15 @@ static bool drbd_may_do_local_read(struct drbd_device *device, sector_t sector,
 /* Update disk stats at start of I/O request */
 static void _drbd_start_io_acct(struct drbd_device *device, struct drbd_request *req)
 {
-	const int rw = bio_data_dir(req->master_bio);
-	int cpu;
-	cpu = part_stat_lock();
-	part_round_stats(cpu, &device->vdisk->part0);
-	part_stat_inc(cpu, &device->vdisk->part0, ios[rw]);
-	part_stat_add(cpu, &device->vdisk->part0, sectors[rw], req->i.size >> 9);
-	(void) cpu; /* The macro invocations above want the cpu argument, I do not like
-		       the compiler warning about cpu only assigned but never used... */
-	part_inc_in_flight(&device->vdisk->part0, rw);
-	part_stat_unlock();
+	generic_start_io_acct(bio_data_dir(req->master_bio), req->i.size >> 9,
+			      &device->vdisk->part0);
 }
 
 /* Update disk stats when completing request upwards */
 static void _drbd_end_io_acct(struct drbd_device *device, struct drbd_request *req)
 {
-	int rw = bio_data_dir(req->master_bio);
-	unsigned long duration = jiffies - req->start_jif;
-	int cpu;
-	cpu = part_stat_lock();
-	part_stat_add(cpu, &device->vdisk->part0, ticks[rw], duration);
-	part_round_stats(cpu, &device->vdisk->part0);
-	part_dec_in_flight(&device->vdisk->part0, rw);
-	part_stat_unlock();
+	generic_end_io_acct(bio_data_dir(req->master_bio),
+			    &device->vdisk->part0, req->start_jif);
 }
 
 static struct drbd_request *drbd_req_new(struct drbd_device *device,
@@ -1545,6 +1531,7 @@ int drbd_merge_bvec(struct request_queue *q, struct bvec_merge_data *bvm, struct
 		struct request_queue * const b =
 			device->ldev->backing_bdev->bd_disk->queue;
 		if (b->merge_bvec_fn) {
+			bvm->bi_bdev = device->ldev->backing_bdev;
 			backing_limit = b->merge_bvec_fn(b, bvm, bvec);
 			limit = min(limit, backing_limit);
 		}
@@ -1628,7 +1615,7 @@ void request_timer_fn(unsigned long data)
 		 time_after(now, req_peer->pre_send_jif + ent) &&
 		!time_in_range(now, connection->last_reconnect_jif, connection->last_reconnect_jif + ent)) {
 		drbd_warn(device, "Remote failed to finish a request within ko-count * timeout\n");
-		_drbd_set_state(_NS(device, conn, C_TIMEOUT), CS_VERBOSE | CS_HARD, NULL);
+		_conn_request_state(connection, NS(conn, C_TIMEOUT), CS_VERBOSE | CS_HARD);
 	}
 	if (dt && oldest_submit_jif != now &&
 		 time_after(now, oldest_submit_jif + dt) &&

drivers/block/drbd/drbd_state.c

@@ -215,6 +215,18 @@ static bool no_peer_wf_report_params(struct drbd_connection *connection)
 	return rv;
 }
 
+static void wake_up_all_devices(struct drbd_connection *connection)
+{
+	struct drbd_peer_device *peer_device;
+	int vnr;
+
+	rcu_read_lock();
+	idr_for_each_entry(&connection->peer_devices, peer_device, vnr)
+		wake_up(&peer_device->device->state_wait);
+	rcu_read_unlock();
+
+}
+
 
 /**
  * cl_wide_st_chg() - true if the state change is a cluster wide one
@@ -410,6 +422,22 @@ _drbd_request_state(struct drbd_device *device, union drbd_state mask,
 	return rv;
 }
 
+enum drbd_state_rv
+_drbd_request_state_holding_state_mutex(struct drbd_device *device, union drbd_state mask,
+		    union drbd_state val, enum chg_state_flags f)
+{
+	enum drbd_state_rv rv;
+
+	BUG_ON(f & CS_SERIALIZE);
+
+	wait_event_cmd(device->state_wait,
+		       (rv = drbd_req_state(device, mask, val, f)) != SS_IN_TRANSIENT_STATE,
+		       mutex_unlock(device->state_mutex),
+		       mutex_lock(device->state_mutex));
+
+	return rv;
+}
+
 static void print_st(struct drbd_device *device, const char *name, union drbd_state ns)
 {
 	drbd_err(device, " %s = { cs:%s ro:%s/%s ds:%s/%s %c%c%c%c%c%c }\n",
@@ -629,14 +657,11 @@ is_valid_soft_transition(union drbd_state os, union drbd_state ns, struct drbd_c
 	if (ns.conn == C_DISCONNECTING && os.conn == C_UNCONNECTED)
 		rv = SS_IN_TRANSIENT_STATE;
 
-	/* if (ns.conn == os.conn && ns.conn == C_WF_REPORT_PARAMS)
-	   rv = SS_IN_TRANSIENT_STATE; */
-
 	/* While establishing a connection only allow cstate to change.
-	   Delay/refuse role changes, detach attach etc... */
+	   Delay/refuse role changes, detach attach etc... (they do not touch cstate) */
 	if (test_bit(STATE_SENT, &connection->flags) &&
-	    !(os.conn == C_WF_REPORT_PARAMS ||
-	      (ns.conn == C_WF_REPORT_PARAMS && os.conn == C_WF_CONNECTION)))
+	    !((ns.conn == C_WF_REPORT_PARAMS && os.conn == C_WF_CONNECTION) ||
+	      (ns.conn >= C_CONNECTED && os.conn == C_WF_REPORT_PARAMS)))
 		rv = SS_IN_TRANSIENT_STATE;
 
 	if ((ns.conn == C_VERIFY_S || ns.conn == C_VERIFY_T) && os.conn < C_CONNECTED)
@@ -1032,8 +1057,10 @@ __drbd_set_state(struct drbd_device *device, union drbd_state ns,
 
 	/* Wake up role changes, that were delayed because of connection establishing */
 	if (os.conn == C_WF_REPORT_PARAMS && ns.conn != C_WF_REPORT_PARAMS &&
-	    no_peer_wf_report_params(connection))
+	    no_peer_wf_report_params(connection)) {
 		clear_bit(STATE_SENT, &connection->flags);
+		wake_up_all_devices(connection);
+	}
 
 	wake_up(&device->misc_wait);
 	wake_up(&device->state_wait);
@@ -1072,7 +1099,6 @@ __drbd_set_state(struct drbd_device *device, union drbd_state ns,
 
 		set_ov_position(device, ns.conn);
 		device->rs_start = now;
-		device->rs_last_events = 0;
 		device->rs_last_sect_ev = 0;
 		device->ov_last_oos_size = 0;
 		device->ov_last_oos_start = 0;

drivers/block/drbd/drbd_state.h

@@ -117,6 +117,11 @@ extern enum drbd_state_rv _drbd_request_state(struct drbd_device *,
 					      union drbd_state,
 					      union drbd_state,
 					      enum chg_state_flags);
+
+extern enum drbd_state_rv
+_drbd_request_state_holding_state_mutex(struct drbd_device *, union drbd_state,
+					union drbd_state, enum chg_state_flags);
+
 extern enum drbd_state_rv __drbd_set_state(struct drbd_device *, union drbd_state,
 					   enum chg_state_flags,
 					   struct completion *done);

drivers/block/drbd/drbd_worker.c

@@ -1592,11 +1592,15 @@ void drbd_resync_after_changed(struct drbd_device *device)
 
 void drbd_rs_controller_reset(struct drbd_device *device)
 {
+	struct gendisk *disk = device->ldev->backing_bdev->bd_contains->bd_disk;
 	struct fifo_buffer *plan;
 
 	atomic_set(&device->rs_sect_in, 0);
 	atomic_set(&device->rs_sect_ev, 0);
 	device->rs_in_flight = 0;
+	device->rs_last_events =
+		(int)part_stat_read(&disk->part0, sectors[0]) +
+		(int)part_stat_read(&disk->part0, sectors[1]);
 
 	/* Updating the RCU protected object in place is necessary since
 	   this function gets called from atomic context.
@@ -1743,7 +1747,6 @@ void drbd_start_resync(struct drbd_device *device, enum drbd_conns side)
 		device->rs_failed    = 0;
 		device->rs_paused    = 0;
 		device->rs_same_csum = 0;
-		device->rs_last_events = 0;
 		device->rs_last_sect_ev = 0;
 		device->rs_total     = tw;
 		device->rs_start     = now;

drivers/block/null_blk.c

@@ -78,7 +78,33 @@ module_param(home_node, int, S_IRUGO);
 MODULE_PARM_DESC(home_node, "Home node for the device");
 
 static int queue_mode = NULL_Q_MQ;
-module_param(queue_mode, int, S_IRUGO);
+
+static int null_param_store_val(const char *str, int *val, int min, int max)
+{
+	int ret, new_val;
+
+	ret = kstrtoint(str, 10, &new_val);
+	if (ret)
+		return -EINVAL;
+
+	if (new_val < min || new_val > max)
+		return -EINVAL;
+
+	*val = new_val;
+	return 0;
+}
+
+static int null_set_queue_mode(const char *str, const struct kernel_param *kp)
+{
+	return null_param_store_val(str, &queue_mode, NULL_Q_BIO, NULL_Q_MQ);
+}
+
+static struct kernel_param_ops null_queue_mode_param_ops = {
+	.set	= null_set_queue_mode,
+	.get	= param_get_int,
+};
+
+device_param_cb(queue_mode, &null_queue_mode_param_ops, &queue_mode, S_IRUGO);
 MODULE_PARM_DESC(queue_mode, "Block interface to use (0=bio,1=rq,2=multiqueue)");
 
 static int gb = 250;
@@ -94,7 +120,19 @@ module_param(nr_devices, int, S_IRUGO);
 MODULE_PARM_DESC(nr_devices, "Number of devices to register");
 
 static int irqmode = NULL_IRQ_SOFTIRQ;
-module_param(irqmode, int, S_IRUGO);
+
+static int null_set_irqmode(const char *str, const struct kernel_param *kp)
+{
+	return null_param_store_val(str, &irqmode, NULL_IRQ_NONE,
+					NULL_IRQ_TIMER);
+}
+
+static struct kernel_param_ops null_irqmode_param_ops = {
+	.set	= null_set_irqmode,
+	.get	= param_get_int,
+};
+
+device_param_cb(irqmode, &null_irqmode_param_ops, &irqmode, S_IRUGO);
 MODULE_PARM_DESC(irqmode, "IRQ completion handler. 0-none, 1-softirq, 2-timer");
 
 static int completion_nsec = 10000;

drivers/block/nvme-core.c

@@ -13,9 +13,9 @@
  */
 
 #include <linux/nvme.h>
-#include <linux/bio.h>
 #include <linux/bitops.h>
 #include <linux/blkdev.h>
+#include <linux/blk-mq.h>
 #include <linux/cpu.h>
 #include <linux/delay.h>
 #include <linux/errno.h>
@@ -33,7 +33,6 @@
 #include <linux/module.h>
 #include <linux/moduleparam.h>
 #include <linux/pci.h>
-#include <linux/percpu.h>
 #include <linux/poison.h>
 #include <linux/ptrace.h>
 #include <linux/sched.h>
@@ -42,12 +41,12 @@
 #include <scsi/sg.h>
 #include <asm-generic/io-64-nonatomic-lo-hi.h>
 
-#include <trace/events/block.h>
-
 #define NVME_Q_DEPTH		1024
+#define NVME_AQ_DEPTH		64
 #define SQ_SIZE(depth)		(depth * sizeof(struct nvme_command))
 #define CQ_SIZE(depth)		(depth * sizeof(struct nvme_completion))
 #define ADMIN_TIMEOUT		(admin_timeout * HZ)
+#define SHUTDOWN_TIMEOUT	(shutdown_timeout * HZ)
 #define IOD_TIMEOUT		(retry_time * HZ)
 
 static unsigned char admin_timeout = 60;
@@ -62,6 +61,10 @@ static unsigned char retry_time = 30;
 module_param(retry_time, byte, 0644);
 MODULE_PARM_DESC(retry_time, "time in seconds to retry failed I/O");
 
+static unsigned char shutdown_timeout = 5;
+module_param(shutdown_timeout, byte, 0644);
+MODULE_PARM_DESC(shutdown_timeout, "timeout in seconds for controller shutdown");
+
 static int nvme_major;
 module_param(nvme_major, int, 0);
 
@@ -76,10 +79,12 @@ static wait_queue_head_t nvme_kthread_wait;
 static struct notifier_block nvme_nb;
 
 static void nvme_reset_failed_dev(struct work_struct *ws);
+static int nvme_process_cq(struct nvme_queue *nvmeq);
 
 struct async_cmd_info {
 	struct kthread_work work;
 	struct kthread_worker *worker;
+	struct request *req;
 	u32 result;
 	int status;
 	void *ctx;
@@ -90,7 +95,7 @@ struct async_cmd_info {
  * commands and one for I/O commands).
  */
 struct nvme_queue {
-	struct rcu_head r_head;
+	struct llist_node node;
 	struct device *q_dmadev;
 	struct nvme_dev *dev;
 	char irqname[24];	/* nvme4294967295-65535\0 */
@@ -99,10 +104,6 @@ struct nvme_queue {
 	volatile struct nvme_completion *cqes;
 	dma_addr_t sq_dma_addr;
 	dma_addr_t cq_dma_addr;
-	wait_queue_head_t sq_full;
-	wait_queue_t sq_cong_wait;
-	struct bio_list sq_cong;
-	struct list_head iod_bio;
 	u32 __iomem *q_db;
 	u16 q_depth;
 	u16 cq_vector;
@@ -112,10 +113,8 @@ struct nvme_queue {
 	u16 qid;
 	u8 cq_phase;
 	u8 cqe_seen;
-	u8 q_suspended;
-	cpumask_var_t cpu_mask;
 	struct async_cmd_info cmdinfo;
-	unsigned long cmdid_data[];
+	struct blk_mq_hw_ctx *hctx;
 };
 
 /*
@@ -143,62 +142,79 @@ typedef void (*nvme_completion_fn)(struct nvme_queue *, void *,
 struct nvme_cmd_info {
 	nvme_completion_fn fn;
 	void *ctx;
-	unsigned long timeout;
 	int aborted;
+	struct nvme_queue *nvmeq;
 };
 
-static struct nvme_cmd_info *nvme_cmd_info(struct nvme_queue *nvmeq)
+static int nvme_admin_init_hctx(struct blk_mq_hw_ctx *hctx, void *data,
+				unsigned int hctx_idx)
 {
-	return (void *)&nvmeq->cmdid_data[BITS_TO_LONGS(nvmeq->q_depth)];
+	struct nvme_dev *dev = data;
+	struct nvme_queue *nvmeq = dev->queues[0];
+
+	WARN_ON(nvmeq->hctx);
+	nvmeq->hctx = hctx;
+	hctx->driver_data = nvmeq;
+	return 0;
 }
 
-static unsigned nvme_queue_extra(int depth)
+static int nvme_admin_init_request(void *data, struct request *req,
+				unsigned int hctx_idx, unsigned int rq_idx,
+				unsigned int numa_node)
 {
-	return DIV_ROUND_UP(depth, 8) + (depth * sizeof(struct nvme_cmd_info));
+	struct nvme_dev *dev = data;
+	struct nvme_cmd_info *cmd = blk_mq_rq_to_pdu(req);
+	struct nvme_queue *nvmeq = dev->queues[0];
+
+	BUG_ON(!nvmeq);
+	cmd->nvmeq = nvmeq;
+	return 0;
 }
 
-/**
- * alloc_cmdid() - Allocate a Command ID
- * @nvmeq: The queue that will be used for this command
- * @ctx: A pointer that will be passed to the handler
- * @handler: The function to call on completion
- *
- * Allocate a Command ID for a queue.  The data passed in will
- * be passed to the completion handler.  This is implemented by using
- * the bottom two bits of the ctx pointer to store the handler ID.
- * Passing in a pointer that's not 4-byte aligned will cause a BUG.
- * We can change this if it becomes a problem.
- *
- * May be called with local interrupts disabled and the q_lock held,
- * or with interrupts enabled and no locks held.
- */
-static int alloc_cmdid(struct nvme_queue *nvmeq, void *ctx,
-				nvme_completion_fn handler, unsigned timeout)
+static void nvme_exit_hctx(struct blk_mq_hw_ctx *hctx, unsigned int hctx_idx)
 {
-	int depth = nvmeq->q_depth - 1;
-	struct nvme_cmd_info *info = nvme_cmd_info(nvmeq);
-	int cmdid;
+	struct nvme_queue *nvmeq = hctx->driver_data;
 
-	do {
-		cmdid = find_first_zero_bit(nvmeq->cmdid_data, depth);
-		if (cmdid >= depth)
-			return -EBUSY;
-	} while (test_and_set_bit(cmdid, nvmeq->cmdid_data));
+	nvmeq->hctx = NULL;
+}
+
+static int nvme_init_hctx(struct blk_mq_hw_ctx *hctx, void *data,
+			  unsigned int hctx_idx)
+{
+	struct nvme_dev *dev = data;
+	struct nvme_queue *nvmeq = dev->queues[
+					(hctx_idx % dev->queue_count) + 1];
+
+	if (!nvmeq->hctx)
+		nvmeq->hctx = hctx;
 
-	info[cmdid].fn = handler;
-	info[cmdid].ctx = ctx;
-	info[cmdid].timeout = jiffies + timeout;
-	info[cmdid].aborted = 0;
-	return cmdid;
+	/* nvmeq queues are shared between namespaces. We assume here that
+	 * blk-mq map the tags so they match up with the nvme queue tags. */
+	WARN_ON(nvmeq->hctx->tags != hctx->tags);
+
+	hctx->driver_data = nvmeq;
+	return 0;
 }
 
-static int alloc_cmdid_killable(struct nvme_queue *nvmeq, void *ctx,
-				nvme_completion_fn handler, unsigned timeout)
+static int nvme_init_request(void *data, struct request *req,
+				unsigned int hctx_idx, unsigned int rq_idx,
+				unsigned int numa_node)
 {
-	int cmdid;
-	wait_event_killable(nvmeq->sq_full,
-		(cmdid = alloc_cmdid(nvmeq, ctx, handler, timeout)) >= 0);
-	return (cmdid < 0) ? -EINTR : cmdid;
+	struct nvme_dev *dev = data;
+	struct nvme_cmd_info *cmd = blk_mq_rq_to_pdu(req);
+	struct nvme_queue *nvmeq = dev->queues[hctx_idx + 1];
+
+	BUG_ON(!nvmeq);
+	cmd->nvmeq = nvmeq;
+	return 0;
+}
+
+static void nvme_set_info(struct nvme_cmd_info *cmd, void *ctx,
+				nvme_completion_fn handler)
+{
+	cmd->fn = handler;
+	cmd->ctx = ctx;
+	cmd->aborted = 0;
 }
 
 /* Special values must be less than 0x1000 */
@@ -206,17 +222,12 @@ static int alloc_cmdid_killable(struct nvme_queue *nvmeq, void *ctx,
 #define CMD_CTX_CANCELLED	(0x30C + CMD_CTX_BASE)
 #define CMD_CTX_COMPLETED	(0x310 + CMD_CTX_BASE)
 #define CMD_CTX_INVALID		(0x314 + CMD_CTX_BASE)
-#define CMD_CTX_ABORT		(0x318 + CMD_CTX_BASE)
 
 static void special_completion(struct nvme_queue *nvmeq, void *ctx,
 						struct nvme_completion *cqe)
 {
 	if (ctx == CMD_CTX_CANCELLED)
 		return;
-	if (ctx == CMD_CTX_ABORT) {
-		++nvmeq->dev->abort_limit;
-		return;
-	}
 	if (ctx == CMD_CTX_COMPLETED) {
 		dev_warn(nvmeq->q_dmadev,
 				"completed id %d twice on queue %d\n",
@@ -229,99 +240,89 @@ static void special_completion(struct nvme_queue *nvmeq, void *ctx,
 				cqe->command_id, le16_to_cpup(&cqe->sq_id));
 		return;
 	}
-
 	dev_warn(nvmeq->q_dmadev, "Unknown special completion %p\n", ctx);
 }
 
-static void async_completion(struct nvme_queue *nvmeq, void *ctx,
-						struct nvme_completion *cqe)
-{
-	struct async_cmd_info *cmdinfo = ctx;
-	cmdinfo->result = le32_to_cpup(&cqe->result);
-	cmdinfo->status = le16_to_cpup(&cqe->status) >> 1;
-	queue_kthread_work(cmdinfo->worker, &cmdinfo->work);
-}
-
-/*
- * Called with local interrupts disabled and the q_lock held.  May not sleep.
- */
-static void *free_cmdid(struct nvme_queue *nvmeq, int cmdid,
-						nvme_completion_fn *fn)
+static void *cancel_cmd_info(struct nvme_cmd_info *cmd, nvme_completion_fn *fn)
 {
 	void *ctx;
-	struct nvme_cmd_info *info = nvme_cmd_info(nvmeq);
 
-	if (cmdid >= nvmeq->q_depth || !info[cmdid].fn) {
-		if (fn)
-			*fn = special_completion;
-		return CMD_CTX_INVALID;
-	}
 	if (fn)
-		*fn = info[cmdid].fn;
-	ctx = info[cmdid].ctx;
-	info[cmdid].fn = special_completion;
-	info[cmdid].ctx = CMD_CTX_COMPLETED;
-	clear_bit(cmdid, nvmeq->cmdid_data);
-	wake_up(&nvmeq->sq_full);
+		*fn = cmd->fn;
+	ctx = cmd->ctx;
+	cmd->fn = special_completion;
+	cmd->ctx = CMD_CTX_CANCELLED;
 	return ctx;
 }
 
-static void *cancel_cmdid(struct nvme_queue *nvmeq, int cmdid,
-						nvme_completion_fn *fn)
+static void async_req_completion(struct nvme_queue *nvmeq, void *ctx,
+						struct nvme_completion *cqe)
 {
-	void *ctx;
-	struct nvme_cmd_info *info = nvme_cmd_info(nvmeq);
-	if (fn)
-		*fn = info[cmdid].fn;
-	ctx = info[cmdid].ctx;
-	info[cmdid].fn = special_completion;
-	info[cmdid].ctx = CMD_CTX_CANCELLED;
-	return ctx;
-}
+	struct request *req = ctx;
 
-static struct nvme_queue *raw_nvmeq(struct nvme_dev *dev, int qid)
-{
-	return rcu_dereference_raw(dev->queues[qid]);
+	u32 result = le32_to_cpup(&cqe->result);
+	u16 status = le16_to_cpup(&cqe->status) >> 1;
+
+	if (status == NVME_SC_SUCCESS || status == NVME_SC_ABORT_REQ)
+		++nvmeq->dev->event_limit;
+	if (status == NVME_SC_SUCCESS)
+		dev_warn(nvmeq->q_dmadev,
+			"async event result %08x\n", result);
+
+	blk_mq_free_hctx_request(nvmeq->hctx, req);
 }
 
-static struct nvme_queue *get_nvmeq(struct nvme_dev *dev) __acquires(RCU)
+static void abort_completion(struct nvme_queue *nvmeq, void *ctx,
+						struct nvme_completion *cqe)
 {
-	struct nvme_queue *nvmeq;
-	unsigned queue_id = get_cpu_var(*dev->io_queue);
+	struct request *req = ctx;
 
-	rcu_read_lock();
-	nvmeq = rcu_dereference(dev->queues[queue_id]);
-	if (nvmeq)
-		return nvmeq;
+	u16 status = le16_to_cpup(&cqe->status) >> 1;
+	u32 result = le32_to_cpup(&cqe->result);
 
-	rcu_read_unlock();
-	put_cpu_var(*dev->io_queue);
-	return NULL;
+	blk_mq_free_hctx_request(nvmeq->hctx, req);
+
+	dev_warn(nvmeq->q_dmadev, "Abort status:%x result:%x", status, result);
+	++nvmeq->dev->abort_limit;
 }
 
-static void put_nvmeq(struct nvme_queue *nvmeq) __releases(RCU)
+static void async_completion(struct nvme_queue *nvmeq, void *ctx,
+						struct nvme_completion *cqe)
 {
-	rcu_read_unlock();
-	put_cpu_var(nvmeq->dev->io_queue);
+	struct async_cmd_info *cmdinfo = ctx;
+	cmdinfo->result = le32_to_cpup(&cqe->result);
+	cmdinfo->status = le16_to_cpup(&cqe->status) >> 1;
+	queue_kthread_work(cmdinfo->worker, &cmdinfo->work);
+	blk_mq_free_hctx_request(nvmeq->hctx, cmdinfo->req);
 }
 
-static struct nvme_queue *lock_nvmeq(struct nvme_dev *dev, int q_idx)
-							__acquires(RCU)
+static inline struct nvme_cmd_info *get_cmd_from_tag(struct nvme_queue *nvmeq,
+				  unsigned int tag)
 {
-	struct nvme_queue *nvmeq;
+	struct blk_mq_hw_ctx *hctx = nvmeq->hctx;
+	struct request *req = blk_mq_tag_to_rq(hctx->tags, tag);
 
-	rcu_read_lock();
-	nvmeq = rcu_dereference(dev->queues[q_idx]);
-	if (nvmeq)
-		return nvmeq;
-
-	rcu_read_unlock();
-	return NULL;
+	return blk_mq_rq_to_pdu(req);
 }
 
-static void unlock_nvmeq(struct nvme_queue *nvmeq) __releases(RCU)
+/*
+ * Called with local interrupts disabled and the q_lock held.  May not sleep.
+ */
+static void *nvme_finish_cmd(struct nvme_queue *nvmeq, int tag,
+						nvme_completion_fn *fn)
 {
-	rcu_read_unlock();
+	struct nvme_cmd_info *cmd = get_cmd_from_tag(nvmeq, tag);
+	void *ctx;
+	if (tag >= nvmeq->q_depth) {
+		*fn = special_completion;
+		return CMD_CTX_INVALID;
+	}
+	if (fn)
+		*fn = cmd->fn;
+	ctx = cmd->ctx;
+	cmd->fn = special_completion;
+	cmd->ctx = CMD_CTX_COMPLETED;
+	return ctx;
 }
 
 /**
@@ -331,26 +332,29 @@ static void unlock_nvmeq(struct nvme_queue *nvmeq) __releases(RCU)
  *
  * Safe to use from interrupt context
  */
-static int nvme_submit_cmd(struct nvme_queue *nvmeq, struct nvme_command *cmd)
+static int __nvme_submit_cmd(struct nvme_queue *nvmeq, struct nvme_command *cmd)
 {
-	unsigned long flags;
-	u16 tail;
-	spin_lock_irqsave(&nvmeq->q_lock, flags);
-	if (nvmeq->q_suspended) {
-		spin_unlock_irqrestore(&nvmeq->q_lock, flags);
-		return -EBUSY;
-	}
-	tail = nvmeq->sq_tail;
+	u16 tail = nvmeq->sq_tail;
+
 	memcpy(&nvmeq->sq_cmds[tail], cmd, sizeof(*cmd));
 	if (++tail == nvmeq->q_depth)
 		tail = 0;
 	writel(tail, nvmeq->q_db);
 	nvmeq->sq_tail = tail;
-	spin_unlock_irqrestore(&nvmeq->q_lock, flags);
 
 	return 0;
 }
 
+static int nvme_submit_cmd(struct nvme_queue *nvmeq, struct nvme_command *cmd)
+{
+	unsigned long flags;
+	int ret;
+	spin_lock_irqsave(&nvmeq->q_lock, flags);
+	ret = __nvme_submit_cmd(nvmeq, cmd);
+	spin_unlock_irqrestore(&nvmeq->q_lock, flags);
+	return ret;
+}
+
 static __le64 **iod_list(struct nvme_iod *iod)
 {
 	return ((void *)iod) + iod->offset;
@@ -361,17 +365,17 @@ static __le64 **iod_list(struct nvme_iod *iod)
  * as it only leads to a small amount of wasted memory for the lifetime of
  * the I/O.
  */
-static int nvme_npages(unsigned size)
+static int nvme_npages(unsigned size, struct nvme_dev *dev)
 {
-	unsigned nprps = DIV_ROUND_UP(size + PAGE_SIZE, PAGE_SIZE);
-	return DIV_ROUND_UP(8 * nprps, PAGE_SIZE - 8);
+	unsigned nprps = DIV_ROUND_UP(size + dev->page_size, dev->page_size);
+	return DIV_ROUND_UP(8 * nprps, dev->page_size - 8);
 }
 
 static struct nvme_iod *
-nvme_alloc_iod(unsigned nseg, unsigned nbytes, gfp_t gfp)
+nvme_alloc_iod(unsigned nseg, unsigned nbytes, struct nvme_dev *dev, gfp_t gfp)
 {
 	struct nvme_iod *iod = kmalloc(sizeof(struct nvme_iod) +
-				sizeof(__le64 *) * nvme_npages(nbytes) +
+				sizeof(__le64 *) * nvme_npages(nbytes, dev) +
 				sizeof(struct scatterlist) * nseg, gfp);
 
 	if (iod) {
@@ -380,7 +384,6 @@ nvme_alloc_iod(unsigned nseg, unsigned nbytes, gfp_t gfp)
 		iod->length = nbytes;
 		iod->nents = 0;
 		iod->first_dma = 0ULL;
-		iod->start_time = jiffies;
 	}
 
 	return iod;
@@ -388,7 +391,7 @@ nvme_alloc_iod(unsigned nseg, unsigned nbytes, gfp_t gfp)
 
 void nvme_free_iod(struct nvme_dev *dev, struct nvme_iod *iod)
 {
-	const int last_prp = PAGE_SIZE / 8 - 1;
+	const int last_prp = dev->page_size / 8 - 1;
 	int i;
 	__le64 **list = iod_list(iod);
 	dma_addr_t prp_dma = iod->first_dma;
@@ -404,65 +407,49 @@ void nvme_free_iod(struct nvme_dev *dev, struct nvme_iod *iod)
 	kfree(iod);
 }
 
-static void nvme_start_io_acct(struct bio *bio)
-{
-	struct gendisk *disk = bio->bi_bdev->bd_disk;
-	if (blk_queue_io_stat(disk->queue)) {
-		const int rw = bio_data_dir(bio);
-		int cpu = part_stat_lock();
-		part_round_stats(cpu, &disk->part0);
-		part_stat_inc(cpu, &disk->part0, ios[rw]);
-		part_stat_add(cpu, &disk->part0, sectors[rw],
-							bio_sectors(bio));
-		part_inc_in_flight(&disk->part0, rw);
-		part_stat_unlock();
-	}
-}
-
-static void nvme_end_io_acct(struct bio *bio, unsigned long start_time)
+static int nvme_error_status(u16 status)
 {
-	struct gendisk *disk = bio->bi_bdev->bd_disk;
-	if (blk_queue_io_stat(disk->queue)) {
-		const int rw = bio_data_dir(bio);
-		unsigned long duration = jiffies - start_time;
-		int cpu = part_stat_lock();
-		part_stat_add(cpu, &disk->part0, ticks[rw], duration);
-		part_round_stats(cpu, &disk->part0);
-		part_dec_in_flight(&disk->part0, rw);
-		part_stat_unlock();
+	switch (status & 0x7ff) {
+	case NVME_SC_SUCCESS:
+		return 0;
+	case NVME_SC_CAP_EXCEEDED:
+		return -ENOSPC;
+	default:
+		return -EIO;
 	}
 }
 
-static void bio_completion(struct nvme_queue *nvmeq, void *ctx,
+static void req_completion(struct nvme_queue *nvmeq, void *ctx,
 						struct nvme_completion *cqe)
 {
 	struct nvme_iod *iod = ctx;
-	struct bio *bio = iod->private;
+	struct request *req = iod->private;
+	struct nvme_cmd_info *cmd_rq = blk_mq_rq_to_pdu(req);
+
 	u16 status = le16_to_cpup(&cqe->status) >> 1;
-	int error = 0;
 
 	if (unlikely(status)) {
-		if (!(status & NVME_SC_DNR ||
-				bio->bi_rw & REQ_FAILFAST_MASK) &&
-				(jiffies - iod->start_time) < IOD_TIMEOUT) {
-			if (!waitqueue_active(&nvmeq->sq_full))
-				add_wait_queue(&nvmeq->sq_full,
-							&nvmeq->sq_cong_wait);
-			list_add_tail(&iod->node, &nvmeq->iod_bio);
-			wake_up(&nvmeq->sq_full);
+		if (!(status & NVME_SC_DNR || blk_noretry_request(req))
+		    && (jiffies - req->start_time) < req->timeout) {
+			blk_mq_requeue_request(req);
+			blk_mq_kick_requeue_list(req->q);
 			return;
 		}
-		error = -EIO;
-	}
-	if (iod->nents) {
-		dma_unmap_sg(nvmeq->q_dmadev, iod->sg, iod->nents,
-			bio_data_dir(bio) ? DMA_TO_DEVICE : DMA_FROM_DEVICE);
-		nvme_end_io_acct(bio, iod->start_time);
-	}
+		req->errors = nvme_error_status(status);
+	} else
+		req->errors = 0;
+
+	if (cmd_rq->aborted)
+		dev_warn(&nvmeq->dev->pci_dev->dev,
+			"completing aborted command with status:%04x\n",
+			status);
+
+	if (iod->nents)
+		dma_unmap_sg(&nvmeq->dev->pci_dev->dev, iod->sg, iod->nents,
+			rq_data_dir(req) ? DMA_TO_DEVICE : DMA_FROM_DEVICE);
 	nvme_free_iod(nvmeq->dev, iod);
 
-	trace_block_bio_complete(bdev_get_queue(bio->bi_bdev), bio, error);
-	bio_endio(bio, error);
+	blk_mq_complete_request(req);
 }
 
 /* length is in bytes.  gfp flags indicates whether we may sleep. */
@@ -479,26 +466,27 @@ int nvme_setup_prps(struct nvme_dev *dev, struct nvme_iod *iod, int total_len,
 	__le64 **list = iod_list(iod);
 	dma_addr_t prp_dma;
 	int nprps, i;
+	u32 page_size = dev->page_size;
 
-	length -= (PAGE_SIZE - offset);
+	length -= (page_size - offset);
 	if (length <= 0)
 		return total_len;
 
-	dma_len -= (PAGE_SIZE - offset);
+	dma_len -= (page_size - offset);
 	if (dma_len) {
-		dma_addr += (PAGE_SIZE - offset);
+		dma_addr += (page_size - offset);
 	} else {
 		sg = sg_next(sg);
 		dma_addr = sg_dma_address(sg);
 		dma_len = sg_dma_len(sg);
 	}
 
-	if (length <= PAGE_SIZE) {
+	if (length <= page_size) {
 		iod->first_dma = dma_addr;
 		return total_len;
 	}
 
-	nprps = DIV_ROUND_UP(length, PAGE_SIZE);
+	nprps = DIV_ROUND_UP(length, page_size);
 	if (nprps <= (256 / 8)) {
 		pool = dev->prp_small_pool;
 		iod->npages = 0;
@@ -511,13 +499,13 @@ int nvme_setup_prps(struct nvme_dev *dev, struct nvme_iod *iod, int total_len,
 	if (!prp_list) {
 		iod->first_dma = dma_addr;
 		iod->npages = -1;
-		return (total_len - length) + PAGE_SIZE;
+		return (total_len - length) + page_size;
 	}
 	list[0] = prp_list;
 	iod->first_dma = prp_dma;
 	i = 0;
 	for (;;) {
-		if (i == PAGE_SIZE / 8) {
+		if (i == page_size >> 3) {
 			__le64 *old_prp_list = prp_list;
 			prp_list = dma_pool_alloc(pool, gfp, &prp_dma);
 			if (!prp_list)
@@ -528,9 +516,9 @@ int nvme_setup_prps(struct nvme_dev *dev, struct nvme_iod *iod, int total_len,
 			i = 1;
 		}
 		prp_list[i++] = cpu_to_le64(dma_addr);
-		dma_len -= PAGE_SIZE;
-		dma_addr += PAGE_SIZE;
-		length -= PAGE_SIZE;
+		dma_len -= page_size;
+		dma_addr += page_size;
+		length -= page_size;
 		if (length <= 0)
 			break;
 		if (dma_len > 0)
@@ -544,88 +532,25 @@ int nvme_setup_prps(struct nvme_dev *dev, struct nvme_iod *iod, int total_len,
 	return total_len;
 }
 
-static int nvme_split_and_submit(struct bio *bio, struct nvme_queue *nvmeq,
-				 int len)
-{
-	struct bio *split = bio_split(bio, len >> 9, GFP_ATOMIC, NULL);
-	if (!split)
-		return -ENOMEM;
-
-	trace_block_split(bdev_get_queue(bio->bi_bdev), bio,
-					split->bi_iter.bi_sector);
-	bio_chain(split, bio);
-
-	if (!waitqueue_active(&nvmeq->sq_full))
-		add_wait_queue(&nvmeq->sq_full, &nvmeq->sq_cong_wait);
-	bio_list_add(&nvmeq->sq_cong, split);
-	bio_list_add(&nvmeq->sq_cong, bio);
-	wake_up(&nvmeq->sq_full);
-
-	return 0;
-}
-
-/* NVMe scatterlists require no holes in the virtual address */
-#define BIOVEC_NOT_VIRT_MERGEABLE(vec1, vec2)	((vec2)->bv_offset || \
-			(((vec1)->bv_offset + (vec1)->bv_len) % PAGE_SIZE))
-
-static int nvme_map_bio(struct nvme_queue *nvmeq, struct nvme_iod *iod,
-		struct bio *bio, enum dma_data_direction dma_dir, int psegs)
-{
-	struct bio_vec bvec, bvprv;
-	struct bvec_iter iter;
-	struct scatterlist *sg = NULL;
-	int length = 0, nsegs = 0, split_len = bio->bi_iter.bi_size;
-	int first = 1;
-
-	if (nvmeq->dev->stripe_size)
-		split_len = nvmeq->dev->stripe_size -
-			((bio->bi_iter.bi_sector << 9) &
-			 (nvmeq->dev->stripe_size - 1));
-
-	sg_init_table(iod->sg, psegs);
-	bio_for_each_segment(bvec, bio, iter) {
-		if (!first && BIOVEC_PHYS_MERGEABLE(&bvprv, &bvec)) {
-			sg->length += bvec.bv_len;
-		} else {
-			if (!first && BIOVEC_NOT_VIRT_MERGEABLE(&bvprv, &bvec))
-				return nvme_split_and_submit(bio, nvmeq,
-							     length);
-
-			sg = sg ? sg + 1 : iod->sg;
-			sg_set_page(sg, bvec.bv_page,
-				    bvec.bv_len, bvec.bv_offset);
-			nsegs++;
-		}
-
-		if (split_len - length < bvec.bv_len)
-			return nvme_split_and_submit(bio, nvmeq, split_len);
-		length += bvec.bv_len;
-		bvprv = bvec;
-		first = 0;
-	}
-	iod->nents = nsegs;
-	sg_mark_end(sg);
-	if (dma_map_sg(nvmeq->q_dmadev, iod->sg, iod->nents, dma_dir) == 0)
-		return -ENOMEM;
-
-	BUG_ON(length != bio->bi_iter.bi_size);
-	return length;
-}
-
-static int nvme_submit_discard(struct nvme_queue *nvmeq, struct nvme_ns *ns,
-		struct bio *bio, struct nvme_iod *iod, int cmdid)
+/*
+ * We reuse the small pool to allocate the 16-byte range here as it is not
+ * worth having a special pool for these or additional cases to handle freeing
+ * the iod.
+ */
+static void nvme_submit_discard(struct nvme_queue *nvmeq, struct nvme_ns *ns,
+		struct request *req, struct nvme_iod *iod)
 {
 	struct nvme_dsm_range *range =
 				(struct nvme_dsm_range *)iod_list(iod)[0];
 	struct nvme_command *cmnd = &nvmeq->sq_cmds[nvmeq->sq_tail];
 
 	range->cattr = cpu_to_le32(0);
-	range->nlb = cpu_to_le32(bio->bi_iter.bi_size >> ns->lba_shift);
-	range->slba = cpu_to_le64(nvme_block_nr(ns, bio->bi_iter.bi_sector));
+	range->nlb = cpu_to_le32(blk_rq_bytes(req) >> ns->lba_shift);
+	range->slba = cpu_to_le64(nvme_block_nr(ns, blk_rq_pos(req)));
 
 	memset(cmnd, 0, sizeof(*cmnd));
 	cmnd->dsm.opcode = nvme_cmd_dsm;
-	cmnd->dsm.command_id = cmdid;
+	cmnd->dsm.command_id = req->tag;
 	cmnd->dsm.nsid = cpu_to_le32(ns->ns_id);
 	cmnd->dsm.prp1 = cpu_to_le64(iod->first_dma);
 	cmnd->dsm.nr = 0;
@@ -634,11 +559,9 @@ static int nvme_submit_discard(struct nvme_queue *nvmeq, struct nvme_ns *ns,
 	if (++nvmeq->sq_tail == nvmeq->q_depth)
 		nvmeq->sq_tail = 0;
 	writel(nvmeq->sq_tail, nvmeq->q_db);
-
-	return 0;
 }
 
-static int nvme_submit_flush(struct nvme_queue *nvmeq, struct nvme_ns *ns,
+static void nvme_submit_flush(struct nvme_queue *nvmeq, struct nvme_ns *ns,
 								int cmdid)
 {
 	struct nvme_command *cmnd = &nvmeq->sq_cmds[nvmeq->sq_tail];
@@ -651,49 +574,34 @@ static int nvme_submit_flush(struct nvme_queue *nvmeq, struct nvme_ns *ns,
 	if (++nvmeq->sq_tail == nvmeq->q_depth)
 		nvmeq->sq_tail = 0;
 	writel(nvmeq->sq_tail, nvmeq->q_db);
-
-	return 0;
 }
 
-static int nvme_submit_iod(struct nvme_queue *nvmeq, struct nvme_iod *iod)
+static int nvme_submit_iod(struct nvme_queue *nvmeq, struct nvme_iod *iod,
+							struct nvme_ns *ns)
 {
-	struct bio *bio = iod->private;
-	struct nvme_ns *ns = bio->bi_bdev->bd_disk->private_data;
+	struct request *req = iod->private;
 	struct nvme_command *cmnd;
-	int cmdid;
-	u16 control;
-	u32 dsmgmt;
-
-	cmdid = alloc_cmdid(nvmeq, iod, bio_completion, NVME_IO_TIMEOUT);
-	if (unlikely(cmdid < 0))
-		return cmdid;
+	u16 control = 0;
+	u32 dsmgmt = 0;
 
-	if (bio->bi_rw & REQ_DISCARD)
-		return nvme_submit_discard(nvmeq, ns, bio, iod, cmdid);
-	if (bio->bi_rw & REQ_FLUSH)
-		return nvme_submit_flush(nvmeq, ns, cmdid);
-
-	control = 0;
-	if (bio->bi_rw & REQ_FUA)
+	if (req->cmd_flags & REQ_FUA)
 		control |= NVME_RW_FUA;
-	if (bio->bi_rw & (REQ_FAILFAST_DEV | REQ_RAHEAD))
+	if (req->cmd_flags & (REQ_FAILFAST_DEV | REQ_RAHEAD))
 		control |= NVME_RW_LR;
 
-	dsmgmt = 0;
-	if (bio->bi_rw & REQ_RAHEAD)
+	if (req->cmd_flags & REQ_RAHEAD)
 		dsmgmt |= NVME_RW_DSM_FREQ_PREFETCH;
 
 	cmnd = &nvmeq->sq_cmds[nvmeq->sq_tail];
 	memset(cmnd, 0, sizeof(*cmnd));
 
-	cmnd->rw.opcode = bio_data_dir(bio) ? nvme_cmd_write : nvme_cmd_read;
-	cmnd->rw.command_id = cmdid;
+	cmnd->rw.opcode = (rq_data_dir(req) ? nvme_cmd_write : nvme_cmd_read);
+	cmnd->rw.command_id = req->tag;
 	cmnd->rw.nsid = cpu_to_le32(ns->ns_id);
 	cmnd->rw.prp1 = cpu_to_le64(sg_dma_address(iod->sg));
 	cmnd->rw.prp2 = cpu_to_le64(iod->first_dma);
-	cmnd->rw.slba = cpu_to_le64(nvme_block_nr(ns, bio->bi_iter.bi_sector));
-	cmnd->rw.length =
-		cpu_to_le16((bio->bi_iter.bi_size >> ns->lba_shift) - 1);
+	cmnd->rw.slba = cpu_to_le64(nvme_block_nr(ns, blk_rq_pos(req)));
+	cmnd->rw.length = cpu_to_le16((blk_rq_bytes(req) >> ns->lba_shift) - 1);
 	cmnd->rw.control = cpu_to_le16(control);
 	cmnd->rw.dsmgmt = cpu_to_le32(dsmgmt);
 
@@ -704,45 +612,26 @@ static int nvme_submit_iod(struct nvme_queue *nvmeq, struct nvme_iod *iod)
 	return 0;
 }
 
-static int nvme_split_flush_data(struct nvme_queue *nvmeq, struct bio *bio)
-{
-	struct bio *split = bio_clone(bio, GFP_ATOMIC);
-	if (!split)
-		return -ENOMEM;
-
-	split->bi_iter.bi_size = 0;
-	split->bi_phys_segments = 0;
-	bio->bi_rw &= ~REQ_FLUSH;
-	bio_chain(split, bio);
-
-	if (!waitqueue_active(&nvmeq->sq_full))
-		add_wait_queue(&nvmeq->sq_full, &nvmeq->sq_cong_wait);
-	bio_list_add(&nvmeq->sq_cong, split);
-	bio_list_add(&nvmeq->sq_cong, bio);
-	wake_up_process(nvme_thread);
-
-	return 0;
-}
-
-/*
- * Called with local interrupts disabled and the q_lock held.  May not sleep.
- */
-static int nvme_submit_bio_queue(struct nvme_queue *nvmeq, struct nvme_ns *ns,
-								struct bio *bio)
+static int nvme_queue_rq(struct blk_mq_hw_ctx *hctx,
+			 const struct blk_mq_queue_data *bd)
 {
+	struct nvme_ns *ns = hctx->queue->queuedata;
+	struct nvme_queue *nvmeq = hctx->driver_data;
+	struct request *req = bd->rq;
+	struct nvme_cmd_info *cmd = blk_mq_rq_to_pdu(req);
 	struct nvme_iod *iod;
-	int psegs = bio_phys_segments(ns->queue, bio);
-	int result;
+	int psegs = req->nr_phys_segments;
+	enum dma_data_direction dma_dir;
+	unsigned size = !(req->cmd_flags & REQ_DISCARD) ? blk_rq_bytes(req) :
+						sizeof(struct nvme_dsm_range);
 
-	if ((bio->bi_rw & REQ_FLUSH) && psegs)
-		return nvme_split_flush_data(nvmeq, bio);
-
-	iod = nvme_alloc_iod(psegs, bio->bi_iter.bi_size, GFP_ATOMIC);
+	iod = nvme_alloc_iod(psegs, size, ns->dev, GFP_ATOMIC);
 	if (!iod)
-		return -ENOMEM;
+		return BLK_MQ_RQ_QUEUE_BUSY;
 
-	iod->private = bio;
-	if (bio->bi_rw & REQ_DISCARD) {
+	iod->private = req;
+
+	if (req->cmd_flags & REQ_DISCARD) {
 		void *range;
 		/*
 		 * We reuse the small pool to allocate the 16-byte range here
@@ -752,35 +641,50 @@ static int nvme_submit_bio_queue(struct nvme_queue *nvmeq, struct nvme_ns *ns,
 		range = dma_pool_alloc(nvmeq->dev->prp_small_pool,
 						GFP_ATOMIC,
 						&iod->first_dma);
-		if (!range) {
-			result = -ENOMEM;
-			goto free_iod;
-		}
+		if (!range)
+			goto retry_cmd;
 		iod_list(iod)[0] = (__le64 *)range;
 		iod->npages = 0;
 	} else if (psegs) {
-		result = nvme_map_bio(nvmeq, iod, bio,
-			bio_data_dir(bio) ? DMA_TO_DEVICE : DMA_FROM_DEVICE,
-			psegs);
-		if (result <= 0)
-			goto free_iod;
-		if (nvme_setup_prps(nvmeq->dev, iod, result, GFP_ATOMIC) !=
-								result) {
-			result = -ENOMEM;
-			goto free_iod;
+		dma_dir = rq_data_dir(req) ? DMA_TO_DEVICE : DMA_FROM_DEVICE;
+
+		sg_init_table(iod->sg, psegs);
+		iod->nents = blk_rq_map_sg(req->q, req, iod->sg);
+		if (!iod->nents)
+			goto error_cmd;
+
+		if (!dma_map_sg(nvmeq->q_dmadev, iod->sg, iod->nents, dma_dir))
+			goto retry_cmd;
+
+		if (blk_rq_bytes(req) !=
+                    nvme_setup_prps(nvmeq->dev, iod, blk_rq_bytes(req), GFP_ATOMIC)) {
+			dma_unmap_sg(&nvmeq->dev->pci_dev->dev, iod->sg,
+					iod->nents, dma_dir);
+			goto retry_cmd;
 		}
-		nvme_start_io_acct(bio);
 	}
-	if (unlikely(nvme_submit_iod(nvmeq, iod))) {
-		if (!waitqueue_active(&nvmeq->sq_full))
-			add_wait_queue(&nvmeq->sq_full, &nvmeq->sq_cong_wait);
-		list_add_tail(&iod->node, &nvmeq->iod_bio);
-	}
-	return 0;
 
- free_iod:
+	blk_mq_start_request(req);
+
+	nvme_set_info(cmd, iod, req_completion);
+	spin_lock_irq(&nvmeq->q_lock);
+	if (req->cmd_flags & REQ_DISCARD)
+		nvme_submit_discard(nvmeq, ns, req, iod);
+	else if (req->cmd_flags & REQ_FLUSH)
+		nvme_submit_flush(nvmeq, ns, req->tag);
+	else
+		nvme_submit_iod(nvmeq, iod, ns);
+
+	nvme_process_cq(nvmeq);
+	spin_unlock_irq(&nvmeq->q_lock);
+	return BLK_MQ_RQ_QUEUE_OK;
+
+ error_cmd:
 	nvme_free_iod(nvmeq->dev, iod);
-	return result;
+	return BLK_MQ_RQ_QUEUE_ERROR;
+ retry_cmd:
+	nvme_free_iod(nvmeq->dev, iod);
+	return BLK_MQ_RQ_QUEUE_BUSY;
 }
 
 static int nvme_process_cq(struct nvme_queue *nvmeq)
@@ -801,8 +705,7 @@ static int nvme_process_cq(struct nvme_queue *nvmeq)
 			head = 0;
 			phase = !phase;
 		}
-
-		ctx = free_cmdid(nvmeq, cqe.command_id, &fn);
+		ctx = nvme_finish_cmd(nvmeq, cqe.command_id, &fn);
 		fn(nvmeq, ctx, &cqe);
 	}
 
@@ -823,29 +726,13 @@ static int nvme_process_cq(struct nvme_queue *nvmeq)
 	return 1;
 }
 
-static void nvme_make_request(struct request_queue *q, struct bio *bio)
+/* Admin queue isn't initialized as a request queue. If at some point this
+ * happens anyway, make sure to notify the user */
+static int nvme_admin_queue_rq(struct blk_mq_hw_ctx *hctx,
+			       const struct blk_mq_queue_data *bd)
 {
-	struct nvme_ns *ns = q->queuedata;
-	struct nvme_queue *nvmeq = get_nvmeq(ns->dev);
-	int result = -EBUSY;
-
-	if (!nvmeq) {
-		bio_endio(bio, -EIO);
-		return;
-	}
-
-	spin_lock_irq(&nvmeq->q_lock);
-	if (!nvmeq->q_suspended && bio_list_empty(&nvmeq->sq_cong))
-		result = nvme_submit_bio_queue(nvmeq, ns, bio);
-	if (unlikely(result)) {
-		if (!waitqueue_active(&nvmeq->sq_full))
-			add_wait_queue(&nvmeq->sq_full, &nvmeq->sq_cong_wait);
-		bio_list_add(&nvmeq->sq_cong, bio);
-	}
-
-	nvme_process_cq(nvmeq);
-	spin_unlock_irq(&nvmeq->q_lock);
-	put_nvmeq(nvmeq);
+	WARN_ON_ONCE(1);
+	return BLK_MQ_RQ_QUEUE_ERROR;
 }
 
 static irqreturn_t nvme_irq(int irq, void *data)
@@ -869,10 +756,11 @@ static irqreturn_t nvme_irq_check(int irq, void *data)
 	return IRQ_WAKE_THREAD;
 }
 
-static void nvme_abort_command(struct nvme_queue *nvmeq, int cmdid)
+static void nvme_abort_cmd_info(struct nvme_queue *nvmeq, struct nvme_cmd_info *
+								cmd_info)
 {
 	spin_lock_irq(&nvmeq->q_lock);
-	cancel_cmdid(nvmeq, cmdid, NULL);
+	cancel_cmd_info(cmd_info, NULL);
 	spin_unlock_irq(&nvmeq->q_lock);
 }
 
@@ -895,47 +783,40 @@ static void sync_completion(struct nvme_queue *nvmeq, void *ctx,
  * Returns 0 on success.  If the result is negative, it's a Linux error code;
  * if the result is positive, it's an NVM Express status code
  */
-static int nvme_submit_sync_cmd(struct nvme_dev *dev, int q_idx,
-						struct nvme_command *cmd,
+static int nvme_submit_sync_cmd(struct request *req, struct nvme_command *cmd,
 						u32 *result, unsigned timeout)
 {
-	int cmdid, ret;
+	int ret;
 	struct sync_cmd_info cmdinfo;
-	struct nvme_queue *nvmeq;
-
-	nvmeq = lock_nvmeq(dev, q_idx);
-	if (!nvmeq)
-		return -ENODEV;
+	struct nvme_cmd_info *cmd_rq = blk_mq_rq_to_pdu(req);
+	struct nvme_queue *nvmeq = cmd_rq->nvmeq;
 
 	cmdinfo.task = current;
 	cmdinfo.status = -EINTR;
 
-	cmdid = alloc_cmdid(nvmeq, &cmdinfo, sync_completion, timeout);
-	if (cmdid < 0) {
-		unlock_nvmeq(nvmeq);
-		return cmdid;
-	}
-	cmd->common.command_id = cmdid;
+	cmd->common.command_id = req->tag;
+
+	nvme_set_info(cmd_rq, &cmdinfo, sync_completion);
 
 	set_current_state(TASK_KILLABLE);
 	ret = nvme_submit_cmd(nvmeq, cmd);
 	if (ret) {
-		free_cmdid(nvmeq, cmdid, NULL);
-		unlock_nvmeq(nvmeq);
+		nvme_finish_cmd(nvmeq, req->tag, NULL);
 		set_current_state(TASK_RUNNING);
-		return ret;
 	}
-	unlock_nvmeq(nvmeq);
-	schedule_timeout(timeout);
-
-	if (cmdinfo.status == -EINTR) {
-		nvmeq = lock_nvmeq(dev, q_idx);
-		if (nvmeq) {
-			nvme_abort_command(nvmeq, cmdid);
-			unlock_nvmeq(nvmeq);
-		}
+	ret = schedule_timeout(timeout);
+
+	/*
+	 * Ensure that sync_completion has either run, or that it will
+	 * never run.
+	 */
+	nvme_abort_cmd_info(nvmeq, blk_mq_rq_to_pdu(req));
+
+	/*
+	 * We never got the completion
+	 */
+	if (cmdinfo.status == -EINTR)
 		return -EINTR;
-	}
 
 	if (result)
 		*result = cmdinfo.result;
@@ -943,59 +824,99 @@ static int nvme_submit_sync_cmd(struct nvme_dev *dev, int q_idx,
 	return cmdinfo.status;
 }
 
-static int nvme_submit_async_cmd(struct nvme_queue *nvmeq,
+static int nvme_submit_async_admin_req(struct nvme_dev *dev)
+{
+	struct nvme_queue *nvmeq = dev->queues[0];
+	struct nvme_command c;
+	struct nvme_cmd_info *cmd_info;
+	struct request *req;
+
+	req = blk_mq_alloc_request(dev->admin_q, WRITE, GFP_ATOMIC, false);
+	if (IS_ERR(req))
+		return PTR_ERR(req);
+
+	cmd_info = blk_mq_rq_to_pdu(req);
+	nvme_set_info(cmd_info, req, async_req_completion);
+
+	memset(&c, 0, sizeof(c));
+	c.common.opcode = nvme_admin_async_event;
+	c.common.command_id = req->tag;
+
+	return __nvme_submit_cmd(nvmeq, &c);
+}
+
+static int nvme_submit_admin_async_cmd(struct nvme_dev *dev,
 			struct nvme_command *cmd,
 			struct async_cmd_info *cmdinfo, unsigned timeout)
 {
-	int cmdid;
+	struct nvme_queue *nvmeq = dev->queues[0];
+	struct request *req;
+	struct nvme_cmd_info *cmd_rq;
+
+	req = blk_mq_alloc_request(dev->admin_q, WRITE, GFP_KERNEL, false);
+	if (IS_ERR(req))
+		return PTR_ERR(req);
 
-	cmdid = alloc_cmdid_killable(nvmeq, cmdinfo, async_completion, timeout);
-	if (cmdid < 0)
-		return cmdid;
+	req->timeout = timeout;
+	cmd_rq = blk_mq_rq_to_pdu(req);
+	cmdinfo->req = req;
+	nvme_set_info(cmd_rq, cmdinfo, async_completion);
 	cmdinfo->status = -EINTR;
-	cmd->common.command_id = cmdid;
+
+	cmd->common.command_id = req->tag;
+
 	return nvme_submit_cmd(nvmeq, cmd);
 }
 
-int nvme_submit_admin_cmd(struct nvme_dev *dev, struct nvme_command *cmd,
-								u32 *result)
+static int __nvme_submit_admin_cmd(struct nvme_dev *dev, struct nvme_command *cmd,
+						u32 *result, unsigned timeout)
 {
-	return nvme_submit_sync_cmd(dev, 0, cmd, result, ADMIN_TIMEOUT);
+	int res;
+	struct request *req;
+
+	req = blk_mq_alloc_request(dev->admin_q, WRITE, GFP_KERNEL, false);
+	if (IS_ERR(req))
+		return PTR_ERR(req);
+	res = nvme_submit_sync_cmd(req, cmd, result, timeout);
+	blk_mq_free_request(req);
+	return res;
 }
 
-int nvme_submit_io_cmd(struct nvme_dev *dev, struct nvme_command *cmd,
+int nvme_submit_admin_cmd(struct nvme_dev *dev, struct nvme_command *cmd,
 								u32 *result)
 {
-	return nvme_submit_sync_cmd(dev, smp_processor_id() + 1, cmd, result,
-							NVME_IO_TIMEOUT);
+	return __nvme_submit_admin_cmd(dev, cmd, result, ADMIN_TIMEOUT);
 }
 
-static int nvme_submit_admin_cmd_async(struct nvme_dev *dev,
-		struct nvme_command *cmd, struct async_cmd_info *cmdinfo)
+int nvme_submit_io_cmd(struct nvme_dev *dev, struct nvme_ns *ns,
+					struct nvme_command *cmd, u32 *result)
 {
-	return nvme_submit_async_cmd(raw_nvmeq(dev, 0), cmd, cmdinfo,
-								ADMIN_TIMEOUT);
+	int res;
+	struct request *req;
+
+	req = blk_mq_alloc_request(ns->queue, WRITE, (GFP_KERNEL|__GFP_WAIT),
+									false);
+	if (IS_ERR(req))
+		return PTR_ERR(req);
+	res = nvme_submit_sync_cmd(req, cmd, result, NVME_IO_TIMEOUT);
+	blk_mq_free_request(req);
+	return res;
 }
 
 static int adapter_delete_queue(struct nvme_dev *dev, u8 opcode, u16 id)
 {
-	int status;
 	struct nvme_command c;
 
 	memset(&c, 0, sizeof(c));
 	c.delete_queue.opcode = opcode;
 	c.delete_queue.qid = cpu_to_le16(id);
 
-	status = nvme_submit_admin_cmd(dev, &c, NULL);
-	if (status)
-		return -EIO;
-	return 0;
+	return nvme_submit_admin_cmd(dev, &c, NULL);
 }
 
 static int adapter_alloc_cq(struct nvme_dev *dev, u16 qid,
 						struct nvme_queue *nvmeq)
 {
-	int status;
 	struct nvme_command c;
 	int flags = NVME_QUEUE_PHYS_CONTIG | NVME_CQ_IRQ_ENABLED;
 
@@ -1007,16 +928,12 @@ static int adapter_alloc_cq(struct nvme_dev *dev, u16 qid,
 	c.create_cq.cq_flags = cpu_to_le16(flags);
 	c.create_cq.irq_vector = cpu_to_le16(nvmeq->cq_vector);
 
-	status = nvme_submit_admin_cmd(dev, &c, NULL);
-	if (status)
-		return -EIO;
-	return 0;
+	return nvme_submit_admin_cmd(dev, &c, NULL);
 }
 
 static int adapter_alloc_sq(struct nvme_dev *dev, u16 qid,
 						struct nvme_queue *nvmeq)
 {
-	int status;
 	struct nvme_command c;
 	int flags = NVME_QUEUE_PHYS_CONTIG | NVME_SQ_PRIO_MEDIUM;
 
@@ -1028,10 +945,7 @@ static int adapter_alloc_sq(struct nvme_dev *dev, u16 qid,
 	c.create_sq.sq_flags = cpu_to_le16(flags);
 	c.create_sq.cqid = cpu_to_le16(qid);
 
-	status = nvme_submit_admin_cmd(dev, &c, NULL);
-	if (status)
-		return -EIO;
-	return 0;
+	return nvme_submit_admin_cmd(dev, &c, NULL);
 }
 
 static int adapter_delete_cq(struct nvme_dev *dev, u16 cqid)
@@ -1087,28 +1001,27 @@ int nvme_set_features(struct nvme_dev *dev, unsigned fid, unsigned dword11,
 }
 
 /**
- * nvme_abort_cmd - Attempt aborting a command
- * @cmdid: Command id of a timed out IO
- * @queue: The queue with timed out IO
+ * nvme_abort_req - Attempt aborting a request
  *
  * Schedule controller reset if the command was already aborted once before and
  * still hasn't been returned to the driver, or if this is the admin queue.
  */
-static void nvme_abort_cmd(int cmdid, struct nvme_queue *nvmeq)
+static void nvme_abort_req(struct request *req)
 {
-	int a_cmdid;
-	struct nvme_command cmd;
+	struct nvme_cmd_info *cmd_rq = blk_mq_rq_to_pdu(req);
+	struct nvme_queue *nvmeq = cmd_rq->nvmeq;
 	struct nvme_dev *dev = nvmeq->dev;
-	struct nvme_cmd_info *info = nvme_cmd_info(nvmeq);
-	struct nvme_queue *adminq;
+	struct request *abort_req;
+	struct nvme_cmd_info *abort_cmd;
+	struct nvme_command cmd;
 
-	if (!nvmeq->qid || info[cmdid].aborted) {
+	if (!nvmeq->qid || cmd_rq->aborted) {
 		if (work_busy(&dev->reset_work))
 			return;
 		list_del_init(&dev->node);
 		dev_warn(&dev->pci_dev->dev,
-			"I/O %d QID %d timeout, reset controller\n", cmdid,
-								nvmeq->qid);
+			"I/O %d QID %d timeout, reset controller\n",
+							req->tag, nvmeq->qid);
 		dev->reset_workfn = nvme_reset_failed_dev;
 		queue_work(nvme_workq, &dev->reset_work);
 		return;
@@ -1117,120 +1030,110 @@ static void nvme_abort_cmd(int cmdid, struct nvme_queue *nvmeq)
 	if (!dev->abort_limit)
 		return;
 
-	adminq = rcu_dereference(dev->queues[0]);
-	a_cmdid = alloc_cmdid(adminq, CMD_CTX_ABORT, special_completion,
-								ADMIN_TIMEOUT);
-	if (a_cmdid < 0)
+	abort_req = blk_mq_alloc_request(dev->admin_q, WRITE, GFP_ATOMIC,
+									false);
+	if (IS_ERR(abort_req))
 		return;
 
+	abort_cmd = blk_mq_rq_to_pdu(abort_req);
+	nvme_set_info(abort_cmd, abort_req, abort_completion);
+
 	memset(&cmd, 0, sizeof(cmd));
 	cmd.abort.opcode = nvme_admin_abort_cmd;
-	cmd.abort.cid = cmdid;
+	cmd.abort.cid = req->tag;
 	cmd.abort.sqid = cpu_to_le16(nvmeq->qid);
-	cmd.abort.command_id = a_cmdid;
+	cmd.abort.command_id = abort_req->tag;
 
 	--dev->abort_limit;
-	info[cmdid].aborted = 1;
-	info[cmdid].timeout = jiffies + ADMIN_TIMEOUT;
+	cmd_rq->aborted = 1;
 
-	dev_warn(nvmeq->q_dmadev, "Aborting I/O %d QID %d\n", cmdid,
+	dev_warn(nvmeq->q_dmadev, "Aborting I/O %d QID %d\n", req->tag,
 							nvmeq->qid);
-	nvme_submit_cmd(adminq, &cmd);
+	if (nvme_submit_cmd(dev->queues[0], &cmd) < 0) {
+		dev_warn(nvmeq->q_dmadev,
+				"Could not abort I/O %d QID %d",
+				req->tag, nvmeq->qid);
+		blk_mq_free_request(abort_req);
+	}
 }
 
-/**
- * nvme_cancel_ios - Cancel outstanding I/Os
- * @queue: The queue to cancel I/Os on
- * @timeout: True to only cancel I/Os which have timed out
- */
-static void nvme_cancel_ios(struct nvme_queue *nvmeq, bool timeout)
+static void nvme_cancel_queue_ios(struct blk_mq_hw_ctx *hctx,
+				struct request *req, void *data, bool reserved)
 {
-	int depth = nvmeq->q_depth - 1;
-	struct nvme_cmd_info *info = nvme_cmd_info(nvmeq);
-	unsigned long now = jiffies;
-	int cmdid;
+	struct nvme_queue *nvmeq = data;
+	void *ctx;
+	nvme_completion_fn fn;
+	struct nvme_cmd_info *cmd;
+	static struct nvme_completion cqe = {
+		.status = cpu_to_le16(NVME_SC_ABORT_REQ << 1),
+	};
 
-	for_each_set_bit(cmdid, nvmeq->cmdid_data, depth) {
-		void *ctx;
-		nvme_completion_fn fn;
-		static struct nvme_completion cqe = {
-			.status = cpu_to_le16(NVME_SC_ABORT_REQ << 1),
-		};
+	cmd = blk_mq_rq_to_pdu(req);
 
-		if (timeout && !time_after(now, info[cmdid].timeout))
-			continue;
-		if (info[cmdid].ctx == CMD_CTX_CANCELLED)
-			continue;
-		if (timeout && nvmeq->dev->initialized) {
-			nvme_abort_cmd(cmdid, nvmeq);
-			continue;
-		}
-		dev_warn(nvmeq->q_dmadev, "Cancelling I/O %d QID %d\n", cmdid,
-								nvmeq->qid);
-		ctx = cancel_cmdid(nvmeq, cmdid, &fn);
-		fn(nvmeq, ctx, &cqe);
-	}
+	if (cmd->ctx == CMD_CTX_CANCELLED)
+		return;
+
+	dev_warn(nvmeq->q_dmadev, "Cancelling I/O %d QID %d\n",
+						req->tag, nvmeq->qid);
+	ctx = cancel_cmd_info(cmd, &fn);
+	fn(nvmeq, ctx, &cqe);
 }
 
-static void nvme_free_queue(struct rcu_head *r)
+static enum blk_eh_timer_return nvme_timeout(struct request *req, bool reserved)
 {
-	struct nvme_queue *nvmeq = container_of(r, struct nvme_queue, r_head);
+	struct nvme_cmd_info *cmd = blk_mq_rq_to_pdu(req);
+	struct nvme_queue *nvmeq = cmd->nvmeq;
 
-	spin_lock_irq(&nvmeq->q_lock);
-	while (bio_list_peek(&nvmeq->sq_cong)) {
-		struct bio *bio = bio_list_pop(&nvmeq->sq_cong);
-		bio_endio(bio, -EIO);
-	}
-	while (!list_empty(&nvmeq->iod_bio)) {
-		static struct nvme_completion cqe = {
-			.status = cpu_to_le16(
-				(NVME_SC_ABORT_REQ | NVME_SC_DNR) << 1),
-		};
-		struct nvme_iod *iod = list_first_entry(&nvmeq->iod_bio,
-							struct nvme_iod,
-							node);
-		list_del(&iod->node);
-		bio_completion(nvmeq, iod, &cqe);
-	}
-	spin_unlock_irq(&nvmeq->q_lock);
+	dev_warn(nvmeq->q_dmadev, "Timeout I/O %d QID %d\n", req->tag,
+							nvmeq->qid);
+	if (nvmeq->dev->initialized)
+		nvme_abort_req(req);
+
+	/*
+	 * The aborted req will be completed on receiving the abort req.
+	 * We enable the timer again. If hit twice, it'll cause a device reset,
+	 * as the device then is in a faulty state.
+	 */
+	return BLK_EH_RESET_TIMER;
+}
 
+static void nvme_free_queue(struct nvme_queue *nvmeq)
+{
 	dma_free_coherent(nvmeq->q_dmadev, CQ_SIZE(nvmeq->q_depth),
 				(void *)nvmeq->cqes, nvmeq->cq_dma_addr);
 	dma_free_coherent(nvmeq->q_dmadev, SQ_SIZE(nvmeq->q_depth),
 					nvmeq->sq_cmds, nvmeq->sq_dma_addr);
-	if (nvmeq->qid)
-		free_cpumask_var(nvmeq->cpu_mask);
 	kfree(nvmeq);
 }
 
 static void nvme_free_queues(struct nvme_dev *dev, int lowest)
 {
+	LLIST_HEAD(q_list);
+	struct nvme_queue *nvmeq, *next;
+	struct llist_node *entry;
 	int i;
 
 	for (i = dev->queue_count - 1; i >= lowest; i--) {
-		struct nvme_queue *nvmeq = raw_nvmeq(dev, i);
-		rcu_assign_pointer(dev->queues[i], NULL);
-		call_rcu(&nvmeq->r_head, nvme_free_queue);
+		struct nvme_queue *nvmeq = dev->queues[i];
+		llist_add(&nvmeq->node, &q_list);
 		dev->queue_count--;
+		dev->queues[i] = NULL;
 	}
+	synchronize_rcu();
+	entry = llist_del_all(&q_list);
+	llist_for_each_entry_safe(nvmeq, next, entry, node)
+		nvme_free_queue(nvmeq);
 }
 
 /**
  * nvme_suspend_queue - put queue into suspended state
  * @nvmeq - queue to suspend
- *
- * Returns 1 if already suspended, 0 otherwise.
  */
 static int nvme_suspend_queue(struct nvme_queue *nvmeq)
 {
 	int vector = nvmeq->dev->entry[nvmeq->cq_vector].vector;
 
 	spin_lock_irq(&nvmeq->q_lock);
-	if (nvmeq->q_suspended) {
-		spin_unlock_irq(&nvmeq->q_lock);
-		return 1;
-	}
-	nvmeq->q_suspended = 1;
 	nvmeq->dev->online_queues--;
 	spin_unlock_irq(&nvmeq->q_lock);
 
@@ -1242,15 +1145,18 @@ static int nvme_suspend_queue(struct nvme_queue *nvmeq)
 
 static void nvme_clear_queue(struct nvme_queue *nvmeq)
 {
+	struct blk_mq_hw_ctx *hctx = nvmeq->hctx;
+
 	spin_lock_irq(&nvmeq->q_lock);
 	nvme_process_cq(nvmeq);
-	nvme_cancel_ios(nvmeq, false);
+	if (hctx && hctx->tags)
+		blk_mq_tag_busy_iter(hctx, nvme_cancel_queue_ios, nvmeq);
 	spin_unlock_irq(&nvmeq->q_lock);
 }
 
 static void nvme_disable_queue(struct nvme_dev *dev, int qid)
 {
-	struct nvme_queue *nvmeq = raw_nvmeq(dev, qid);
+	struct nvme_queue *nvmeq = dev->queues[qid];
 
 	if (!nvmeq)
 		return;
@@ -1270,25 +1176,20 @@ static struct nvme_queue *nvme_alloc_queue(struct nvme_dev *dev, int qid,
 							int depth, int vector)
 {
 	struct device *dmadev = &dev->pci_dev->dev;
-	unsigned extra = nvme_queue_extra(depth);
-	struct nvme_queue *nvmeq = kzalloc(sizeof(*nvmeq) + extra, GFP_KERNEL);
+	struct nvme_queue *nvmeq = kzalloc(sizeof(*nvmeq), GFP_KERNEL);
 	if (!nvmeq)
 		return NULL;
 
-	nvmeq->cqes = dma_alloc_coherent(dmadev, CQ_SIZE(depth),
-					&nvmeq->cq_dma_addr, GFP_KERNEL);
+	nvmeq->cqes = dma_zalloc_coherent(dmadev, CQ_SIZE(depth),
+					  &nvmeq->cq_dma_addr, GFP_KERNEL);
 	if (!nvmeq->cqes)
 		goto free_nvmeq;
-	memset((void *)nvmeq->cqes, 0, CQ_SIZE(depth));
 
 	nvmeq->sq_cmds = dma_alloc_coherent(dmadev, SQ_SIZE(depth),
 					&nvmeq->sq_dma_addr, GFP_KERNEL);
 	if (!nvmeq->sq_cmds)
 		goto free_cqdma;
 
-	if (qid && !zalloc_cpumask_var(&nvmeq->cpu_mask, GFP_KERNEL))
-		goto free_sqdma;
-
 	nvmeq->q_dmadev = dmadev;
 	nvmeq->dev = dev;
 	snprintf(nvmeq->irqname, sizeof(nvmeq->irqname), "nvme%dq%d",
@@ -1296,23 +1197,15 @@ static struct nvme_queue *nvme_alloc_queue(struct nvme_dev *dev, int qid,
 	spin_lock_init(&nvmeq->q_lock);
 	nvmeq->cq_head = 0;
 	nvmeq->cq_phase = 1;
-	init_waitqueue_head(&nvmeq->sq_full);
-	init_waitqueue_entry(&nvmeq->sq_cong_wait, nvme_thread);
-	bio_list_init(&nvmeq->sq_cong);
-	INIT_LIST_HEAD(&nvmeq->iod_bio);
 	nvmeq->q_db = &dev->dbs[qid * 2 * dev->db_stride];
 	nvmeq->q_depth = depth;
 	nvmeq->cq_vector = vector;
 	nvmeq->qid = qid;
-	nvmeq->q_suspended = 1;
 	dev->queue_count++;
-	rcu_assign_pointer(dev->queues[qid], nvmeq);
+	dev->queues[qid] = nvmeq;
 
 	return nvmeq;
 
- free_sqdma:
-	dma_free_coherent(dmadev, SQ_SIZE(depth), (void *)nvmeq->sq_cmds,
-							nvmeq->sq_dma_addr);
  free_cqdma:
 	dma_free_coherent(dmadev, CQ_SIZE(depth), (void *)nvmeq->cqes,
 							nvmeq->cq_dma_addr);
@@ -1335,17 +1228,15 @@ static int queue_request_irq(struct nvme_dev *dev, struct nvme_queue *nvmeq,
 static void nvme_init_queue(struct nvme_queue *nvmeq, u16 qid)
 {
 	struct nvme_dev *dev = nvmeq->dev;
-	unsigned extra = nvme_queue_extra(nvmeq->q_depth);
 
+	spin_lock_irq(&nvmeq->q_lock);
 	nvmeq->sq_tail = 0;
 	nvmeq->cq_head = 0;
 	nvmeq->cq_phase = 1;
 	nvmeq->q_db = &dev->dbs[qid * 2 * dev->db_stride];
-	memset(nvmeq->cmdid_data, 0, extra);
 	memset((void *)nvmeq->cqes, 0, CQ_SIZE(nvmeq->q_depth));
-	nvme_cancel_ios(nvmeq, false);
-	nvmeq->q_suspended = 0;
 	dev->online_queues++;
+	spin_unlock_irq(&nvmeq->q_lock);
 }
 
 static int nvme_create_queue(struct nvme_queue *nvmeq, int qid)
@@ -1365,10 +1256,7 @@ static int nvme_create_queue(struct nvme_queue *nvmeq, int qid)
 	if (result < 0)
 		goto release_sq;
 
-	spin_lock_irq(&nvmeq->q_lock);
 	nvme_init_queue(nvmeq, qid);
-	spin_unlock_irq(&nvmeq->q_lock);
-
 	return result;
 
  release_sq:
@@ -1408,27 +1296,32 @@ static int nvme_wait_ready(struct nvme_dev *dev, u64 cap, bool enabled)
  */
 static int nvme_disable_ctrl(struct nvme_dev *dev, u64 cap)
 {
-	u32 cc = readl(&dev->bar->cc);
+	dev->ctrl_config &= ~NVME_CC_SHN_MASK;
+	dev->ctrl_config &= ~NVME_CC_ENABLE;
+	writel(dev->ctrl_config, &dev->bar->cc);
 
-	if (cc & NVME_CC_ENABLE)
-		writel(cc & ~NVME_CC_ENABLE, &dev->bar->cc);
 	return nvme_wait_ready(dev, cap, false);
 }
 
 static int nvme_enable_ctrl(struct nvme_dev *dev, u64 cap)
 {
+	dev->ctrl_config &= ~NVME_CC_SHN_MASK;
+	dev->ctrl_config |= NVME_CC_ENABLE;
+	writel(dev->ctrl_config, &dev->bar->cc);
+
 	return nvme_wait_ready(dev, cap, true);
 }
 
 static int nvme_shutdown_ctrl(struct nvme_dev *dev)
 {
 	unsigned long timeout;
-	u32 cc;
 
-	cc = (readl(&dev->bar->cc) & ~NVME_CC_SHN_MASK) | NVME_CC_SHN_NORMAL;
-	writel(cc, &dev->bar->cc);
+	dev->ctrl_config &= ~NVME_CC_SHN_MASK;
+	dev->ctrl_config |= NVME_CC_SHN_NORMAL;
 
-	timeout = 2 * HZ + jiffies;
+	writel(dev->ctrl_config, &dev->bar->cc);
+
+	timeout = SHUTDOWN_TIMEOUT + jiffies;
 	while ((readl(&dev->bar->csts) & NVME_CSTS_SHST_MASK) !=
 							NVME_CSTS_SHST_CMPLT) {
 		msleep(100);
@@ -1444,20 +1337,86 @@ static int nvme_shutdown_ctrl(struct nvme_dev *dev)
 	return 0;
 }
 
+static struct blk_mq_ops nvme_mq_admin_ops = {
+	.queue_rq	= nvme_admin_queue_rq,
+	.map_queue	= blk_mq_map_queue,
+	.init_hctx	= nvme_admin_init_hctx,
+	.exit_hctx	= nvme_exit_hctx,
+	.init_request	= nvme_admin_init_request,
+	.timeout	= nvme_timeout,
+};
+
+static struct blk_mq_ops nvme_mq_ops = {
+	.queue_rq	= nvme_queue_rq,
+	.map_queue	= blk_mq_map_queue,
+	.init_hctx	= nvme_init_hctx,
+	.exit_hctx	= nvme_exit_hctx,
+	.init_request	= nvme_init_request,
+	.timeout	= nvme_timeout,
+};
+
+static int nvme_alloc_admin_tags(struct nvme_dev *dev)
+{
+	if (!dev->admin_q) {
+		dev->admin_tagset.ops = &nvme_mq_admin_ops;
+		dev->admin_tagset.nr_hw_queues = 1;
+		dev->admin_tagset.queue_depth = NVME_AQ_DEPTH - 1;
+		dev->admin_tagset.timeout = ADMIN_TIMEOUT;
+		dev->admin_tagset.numa_node = dev_to_node(&dev->pci_dev->dev);
+		dev->admin_tagset.cmd_size = sizeof(struct nvme_cmd_info);
+		dev->admin_tagset.driver_data = dev;
+
+		if (blk_mq_alloc_tag_set(&dev->admin_tagset))
+			return -ENOMEM;
+
+		dev->admin_q = blk_mq_init_queue(&dev->admin_tagset);
+		if (!dev->admin_q) {
+			blk_mq_free_tag_set(&dev->admin_tagset);
+			return -ENOMEM;
+		}
+	}
+
+	return 0;
+}
+
+static void nvme_free_admin_tags(struct nvme_dev *dev)
+{
+	if (dev->admin_q)
+		blk_mq_free_tag_set(&dev->admin_tagset);
+}
+
 static int nvme_configure_admin_queue(struct nvme_dev *dev)
 {
 	int result;
 	u32 aqa;
 	u64 cap = readq(&dev->bar->cap);
 	struct nvme_queue *nvmeq;
+	unsigned page_shift = PAGE_SHIFT;
+	unsigned dev_page_min = NVME_CAP_MPSMIN(cap) + 12;
+	unsigned dev_page_max = NVME_CAP_MPSMAX(cap) + 12;
+
+	if (page_shift < dev_page_min) {
+		dev_err(&dev->pci_dev->dev,
+				"Minimum device page size (%u) too large for "
+				"host (%u)\n", 1 << dev_page_min,
+				1 << page_shift);
+		return -ENODEV;
+	}
+	if (page_shift > dev_page_max) {
+		dev_info(&dev->pci_dev->dev,
+				"Device maximum page size (%u) smaller than "
+				"host (%u); enabling work-around\n",
+				1 << dev_page_max, 1 << page_shift);
+		page_shift = dev_page_max;
+	}
 
 	result = nvme_disable_ctrl(dev, cap);
 	if (result < 0)
 		return result;
 
-	nvmeq = raw_nvmeq(dev, 0);
+	nvmeq = dev->queues[0];
 	if (!nvmeq) {
-		nvmeq = nvme_alloc_queue(dev, 0, 64, 0);
+		nvmeq = nvme_alloc_queue(dev, 0, NVME_AQ_DEPTH, 0);
 		if (!nvmeq)
 			return -ENOMEM;
 	}
@@ -1465,27 +1424,35 @@ static int nvme_configure_admin_queue(struct nvme_dev *dev)
 	aqa = nvmeq->q_depth - 1;
 	aqa |= aqa << 16;
 
-	dev->ctrl_config = NVME_CC_ENABLE | NVME_CC_CSS_NVM;
-	dev->ctrl_config |= (PAGE_SHIFT - 12) << NVME_CC_MPS_SHIFT;
+	dev->page_size = 1 << page_shift;
+
+	dev->ctrl_config = NVME_CC_CSS_NVM;
+	dev->ctrl_config |= (page_shift - 12) << NVME_CC_MPS_SHIFT;
 	dev->ctrl_config |= NVME_CC_ARB_RR | NVME_CC_SHN_NONE;
 	dev->ctrl_config |= NVME_CC_IOSQES | NVME_CC_IOCQES;
 
 	writel(aqa, &dev->bar->aqa);
 	writeq(nvmeq->sq_dma_addr, &dev->bar->asq);
 	writeq(nvmeq->cq_dma_addr, &dev->bar->acq);
-	writel(dev->ctrl_config, &dev->bar->cc);
 
 	result = nvme_enable_ctrl(dev, cap);
 	if (result)
-		return result;
+		goto free_nvmeq;
+
+	result = nvme_alloc_admin_tags(dev);
+	if (result)
+		goto free_nvmeq;
 
 	result = queue_request_irq(dev, nvmeq, nvmeq->irqname);
 	if (result)
-		return result;
+		goto free_tags;
 
-	spin_lock_irq(&nvmeq->q_lock);
-	nvme_init_queue(nvmeq, 0);
-	spin_unlock_irq(&nvmeq->q_lock);
+	return result;
+
+ free_tags:
+	nvme_free_admin_tags(dev);
+ free_nvmeq:
+	nvme_free_queues(dev, 0);
 	return result;
 }
 
@@ -1516,7 +1483,7 @@ struct nvme_iod *nvme_map_user_pages(struct nvme_dev *dev, int write,
 	}
 
 	err = -ENOMEM;
-	iod = nvme_alloc_iod(count, length, GFP_KERNEL);
+	iod = nvme_alloc_iod(count, length, dev, GFP_KERNEL);
 	if (!iod)
 		goto put_pages;
 
@@ -1644,7 +1611,7 @@ static int nvme_submit_io(struct nvme_ns *ns, struct nvme_user_io __user *uio)
 	if (length != (io.nblocks + 1) << ns->lba_shift)
 		status = -ENOMEM;
 	else
-		status = nvme_submit_io_cmd(dev, &c, NULL);
+		status = nvme_submit_io_cmd(dev, ns, &c, NULL);
 
 	if (meta_len) {
 		if (status == NVME_SC_SUCCESS && !(io.opcode & 1)) {
@@ -1676,10 +1643,10 @@ static int nvme_submit_io(struct nvme_ns *ns, struct nvme_user_io __user *uio)
 	return status;
 }
 
-static int nvme_user_admin_cmd(struct nvme_dev *dev,
-					struct nvme_admin_cmd __user *ucmd)
+static int nvme_user_cmd(struct nvme_dev *dev, struct nvme_ns *ns,
+			struct nvme_passthru_cmd __user *ucmd)
 {
-	struct nvme_admin_cmd cmd;
+	struct nvme_passthru_cmd cmd;
 	struct nvme_command c;
 	int status, length;
 	struct nvme_iod *uninitialized_var(iod);
@@ -1716,10 +1683,23 @@ static int nvme_user_admin_cmd(struct nvme_dev *dev,
 
 	timeout = cmd.timeout_ms ? msecs_to_jiffies(cmd.timeout_ms) :
 								ADMIN_TIMEOUT;
+
 	if (length != cmd.data_len)
 		status = -ENOMEM;
-	else
-		status = nvme_submit_sync_cmd(dev, 0, &c, &cmd.result, timeout);
+	else if (ns) {
+		struct request *req;
+
+		req = blk_mq_alloc_request(ns->queue, WRITE,
+						(GFP_KERNEL|__GFP_WAIT), false);
+		if (IS_ERR(req))
+			status = PTR_ERR(req);
+		else {
+			status = nvme_submit_sync_cmd(req, &c, &cmd.result,
+								timeout);
+			blk_mq_free_request(req);
+		}
+	} else
+		status = __nvme_submit_admin_cmd(dev, &c, &cmd.result, timeout);
 
 	if (cmd.data_len) {
 		nvme_unmap_user_pages(dev, cmd.opcode & 1, iod);
@@ -1743,7 +1723,9 @@ static int nvme_ioctl(struct block_device *bdev, fmode_t mode, unsigned int cmd,
 		force_successful_syscall_return();
 		return ns->ns_id;
 	case NVME_IOCTL_ADMIN_CMD:
-		return nvme_user_admin_cmd(ns->dev, (void __user *)arg);
+		return nvme_user_cmd(ns->dev, NULL, (void __user *)arg);
+	case NVME_IOCTL_IO_CMD:
+		return nvme_user_cmd(ns->dev, ns, (void __user *)arg);
 	case NVME_IOCTL_SUBMIT_IO:
 		return nvme_submit_io(ns, (void __user *)arg);
 	case SG_GET_VERSION_NUM:
@@ -1759,11 +1741,9 @@ static int nvme_ioctl(struct block_device *bdev, fmode_t mode, unsigned int cmd,
 static int nvme_compat_ioctl(struct block_device *bdev, fmode_t mode,
 					unsigned int cmd, unsigned long arg)
 {
-	struct nvme_ns *ns = bdev->bd_disk->private_data;
-
 	switch (cmd) {
 	case SG_IO:
-		return nvme_sg_io32(ns, arg);
+		return -ENOIOCTLCMD;
 	}
 	return nvme_ioctl(bdev, mode, cmd, arg);
 }
@@ -1773,11 +1753,18 @@ static int nvme_compat_ioctl(struct block_device *bdev, fmode_t mode,
 
 static int nvme_open(struct block_device *bdev, fmode_t mode)
 {
-	struct nvme_ns *ns = bdev->bd_disk->private_data;
-	struct nvme_dev *dev = ns->dev;
+	int ret = 0;
+	struct nvme_ns *ns;
 
-	kref_get(&dev->kref);
-	return 0;
+	spin_lock(&dev_list_lock);
+	ns = bdev->bd_disk->private_data;
+	if (!ns)
+		ret = -ENXIO;
+	else if (!kref_get_unless_zero(&ns->dev->kref))
+		ret = -ENXIO;
+	spin_unlock(&dev_list_lock);
+
+	return ret;
 }
 
 static void nvme_free_dev(struct kref *kref);
@@ -1799,6 +1786,35 @@ static int nvme_getgeo(struct block_device *bd, struct hd_geometry *geo)
 	return 0;
 }
 
+static int nvme_revalidate_disk(struct gendisk *disk)
+{
+	struct nvme_ns *ns = disk->private_data;
+	struct nvme_dev *dev = ns->dev;
+	struct nvme_id_ns *id;
+	dma_addr_t dma_addr;
+	int lbaf;
+
+	id = dma_alloc_coherent(&dev->pci_dev->dev, 4096, &dma_addr,
+								GFP_KERNEL);
+	if (!id) {
+		dev_warn(&dev->pci_dev->dev, "%s: Memory alocation failure\n",
+								__func__);
+		return 0;
+	}
+
+	if (nvme_identify(dev, ns->ns_id, 0, dma_addr))
+		goto free;
+
+	lbaf = id->flbas & 0xf;
+	ns->lba_shift = id->lbaf[lbaf].ds;
+
+	blk_queue_logical_block_size(ns->queue, 1 << ns->lba_shift);
+	set_capacity(disk, le64_to_cpup(&id->nsze) << (ns->lba_shift - 9));
+ free:
+	dma_free_coherent(&dev->pci_dev->dev, 4096, id, dma_addr);
+	return 0;
+}
+
 static const struct block_device_operations nvme_fops = {
 	.owner		= THIS_MODULE,
 	.ioctl		= nvme_ioctl,
@@ -1806,43 +1822,9 @@ static const struct block_device_operations nvme_fops = {
 	.open		= nvme_open,
 	.release	= nvme_release,
 	.getgeo		= nvme_getgeo,
+	.revalidate_disk= nvme_revalidate_disk,
 };
 
-static void nvme_resubmit_iods(struct nvme_queue *nvmeq)
-{
-	struct nvme_iod *iod, *next;
-
-	list_for_each_entry_safe(iod, next, &nvmeq->iod_bio, node) {
-		if (unlikely(nvme_submit_iod(nvmeq, iod)))
-			break;
-		list_del(&iod->node);
-		if (bio_list_empty(&nvmeq->sq_cong) &&
-						list_empty(&nvmeq->iod_bio))
-			remove_wait_queue(&nvmeq->sq_full,
-						&nvmeq->sq_cong_wait);
-	}
-}
-
-static void nvme_resubmit_bios(struct nvme_queue *nvmeq)
-{
-	while (bio_list_peek(&nvmeq->sq_cong)) {
-		struct bio *bio = bio_list_pop(&nvmeq->sq_cong);
-		struct nvme_ns *ns = bio->bi_bdev->bd_disk->private_data;
-
-		if (bio_list_empty(&nvmeq->sq_cong) &&
-						list_empty(&nvmeq->iod_bio))
-			remove_wait_queue(&nvmeq->sq_full,
-							&nvmeq->sq_cong_wait);
-		if (nvme_submit_bio_queue(nvmeq, ns, bio)) {
-			if (!waitqueue_active(&nvmeq->sq_full))
-				add_wait_queue(&nvmeq->sq_full,
-							&nvmeq->sq_cong_wait);
-			bio_list_add_head(&nvmeq->sq_cong, bio);
-			break;
-		}
-	}
-}
-
 static int nvme_kthread(void *data)
 {
 	struct nvme_dev *dev, *next;
@@ -1858,28 +1840,26 @@ static int nvme_kthread(void *data)
 					continue;
 				list_del_init(&dev->node);
 				dev_warn(&dev->pci_dev->dev,
-					"Failed status, reset controller\n");
+					"Failed status: %x, reset controller\n",
+					readl(&dev->bar->csts));
 				dev->reset_workfn = nvme_reset_failed_dev;
 				queue_work(nvme_workq, &dev->reset_work);
 				continue;
 			}
-			rcu_read_lock();
 			for (i = 0; i < dev->queue_count; i++) {
-				struct nvme_queue *nvmeq =
-						rcu_dereference(dev->queues[i]);
+				struct nvme_queue *nvmeq = dev->queues[i];
 				if (!nvmeq)
 					continue;
 				spin_lock_irq(&nvmeq->q_lock);
-				if (nvmeq->q_suspended)
-					goto unlock;
 				nvme_process_cq(nvmeq);
-				nvme_cancel_ios(nvmeq, true);
-				nvme_resubmit_bios(nvmeq);
-				nvme_resubmit_iods(nvmeq);
- unlock:
+
+				while ((i == 0) && (dev->event_limit > 0)) {
+					if (nvme_submit_async_admin_req(dev))
+						break;
+					dev->event_limit--;
+				}
 				spin_unlock_irq(&nvmeq->q_lock);
 			}
-			rcu_read_unlock();
 		}
 		spin_unlock(&dev_list_lock);
 		schedule_timeout(round_jiffies_relative(HZ));
@@ -1902,28 +1882,28 @@ static struct nvme_ns *nvme_alloc_ns(struct nvme_dev *dev, unsigned nsid,
 {
 	struct nvme_ns *ns;
 	struct gendisk *disk;
+	int node = dev_to_node(&dev->pci_dev->dev);
 	int lbaf;
 
 	if (rt->attributes & NVME_LBART_ATTRIB_HIDE)
 		return NULL;
 
-	ns = kzalloc(sizeof(*ns), GFP_KERNEL);
+	ns = kzalloc_node(sizeof(*ns), GFP_KERNEL, node);
 	if (!ns)
 		return NULL;
-	ns->queue = blk_alloc_queue(GFP_KERNEL);
-	if (!ns->queue)
+	ns->queue = blk_mq_init_queue(&dev->tagset);
+	if (IS_ERR(ns->queue))
 		goto out_free_ns;
-	ns->queue->queue_flags = QUEUE_FLAG_DEFAULT;
 	queue_flag_set_unlocked(QUEUE_FLAG_NOMERGES, ns->queue);
 	queue_flag_set_unlocked(QUEUE_FLAG_NONROT, ns->queue);
-	queue_flag_clear_unlocked(QUEUE_FLAG_ADD_RANDOM, ns->queue);
-	blk_queue_make_request(ns->queue, nvme_make_request);
+	queue_flag_set_unlocked(QUEUE_FLAG_SG_GAPS, ns->queue);
 	ns->dev = dev;
 	ns->queue->queuedata = ns;
 
-	disk = alloc_disk(0);
+	disk = alloc_disk_node(0, node);
 	if (!disk)
 		goto out_free_queue;
+
 	ns->ns_id = nsid;
 	ns->disk = disk;
 	lbaf = id->flbas & 0xf;
@@ -1932,6 +1912,8 @@ static struct nvme_ns *nvme_alloc_ns(struct nvme_dev *dev, unsigned nsid,
 	blk_queue_logical_block_size(ns->queue, 1 << ns->lba_shift);
 	if (dev->max_hw_sectors)
 		blk_queue_max_hw_sectors(ns->queue, dev->max_hw_sectors);
+	if (dev->stripe_size)
+		blk_queue_chunk_sectors(ns->queue, dev->stripe_size >> 9);
 	if (dev->vwc & NVME_CTRL_VWC_PRESENT)
 		blk_queue_flush(ns->queue, REQ_FLUSH | REQ_FUA);
 
@@ -1957,143 +1939,19 @@ static struct nvme_ns *nvme_alloc_ns(struct nvme_dev *dev, unsigned nsid,
 	return NULL;
 }
 
-static int nvme_find_closest_node(int node)
-{
-	int n, val, min_val = INT_MAX, best_node = node;
-
-	for_each_online_node(n) {
-		if (n == node)
-			continue;
-		val = node_distance(node, n);
-		if (val < min_val) {
-			min_val = val;
-			best_node = n;
-		}
-	}
-	return best_node;
-}
-
-static void nvme_set_queue_cpus(cpumask_t *qmask, struct nvme_queue *nvmeq,
-								int count)
-{
-	int cpu;
-	for_each_cpu(cpu, qmask) {
-		if (cpumask_weight(nvmeq->cpu_mask) >= count)
-			break;
-		if (!cpumask_test_and_set_cpu(cpu, nvmeq->cpu_mask))
-			*per_cpu_ptr(nvmeq->dev->io_queue, cpu) = nvmeq->qid;
-	}
-}
-
-static void nvme_add_cpus(cpumask_t *mask, const cpumask_t *unassigned_cpus,
-	const cpumask_t *new_mask, struct nvme_queue *nvmeq, int cpus_per_queue)
-{
-	int next_cpu;
-	for_each_cpu(next_cpu, new_mask) {
-		cpumask_or(mask, mask, get_cpu_mask(next_cpu));
-		cpumask_or(mask, mask, topology_thread_cpumask(next_cpu));
-		cpumask_and(mask, mask, unassigned_cpus);
-		nvme_set_queue_cpus(mask, nvmeq, cpus_per_queue);
-	}
-}
-
 static void nvme_create_io_queues(struct nvme_dev *dev)
 {
-	unsigned i, max;
+	unsigned i;
 
-	max = min(dev->max_qid, num_online_cpus());
-	for (i = dev->queue_count; i <= max; i++)
+	for (i = dev->queue_count; i <= dev->max_qid; i++)
 		if (!nvme_alloc_queue(dev, i, dev->q_depth, i - 1))
 			break;
 
-	max = min(dev->queue_count - 1, num_online_cpus());
-	for (i = dev->online_queues; i <= max; i++)
-		if (nvme_create_queue(raw_nvmeq(dev, i), i))
+	for (i = dev->online_queues; i <= dev->queue_count - 1; i++)
+		if (nvme_create_queue(dev->queues[i], i))
 			break;
 }
 
-/*
- * If there are fewer queues than online cpus, this will try to optimally
- * assign a queue to multiple cpus by grouping cpus that are "close" together:
- * thread siblings, core, socket, closest node, then whatever else is
- * available.
- */
-static void nvme_assign_io_queues(struct nvme_dev *dev)
-{
-	unsigned cpu, cpus_per_queue, queues, remainder, i;
-	cpumask_var_t unassigned_cpus;
-
-	nvme_create_io_queues(dev);
-
-	queues = min(dev->online_queues - 1, num_online_cpus());
-	if (!queues)
-		return;
-
-	cpus_per_queue = num_online_cpus() / queues;
-	remainder = queues - (num_online_cpus() - queues * cpus_per_queue);
-
-	if (!alloc_cpumask_var(&unassigned_cpus, GFP_KERNEL))
-		return;
-
-	cpumask_copy(unassigned_cpus, cpu_online_mask);
-	cpu = cpumask_first(unassigned_cpus);
-	for (i = 1; i <= queues; i++) {
-		struct nvme_queue *nvmeq = lock_nvmeq(dev, i);
-		cpumask_t mask;
-
-		cpumask_clear(nvmeq->cpu_mask);
-		if (!cpumask_weight(unassigned_cpus)) {
-			unlock_nvmeq(nvmeq);
-			break;
-		}
-
-		mask = *get_cpu_mask(cpu);
-		nvme_set_queue_cpus(&mask, nvmeq, cpus_per_queue);
-		if (cpus_weight(mask) < cpus_per_queue)
-			nvme_add_cpus(&mask, unassigned_cpus,
-				topology_thread_cpumask(cpu),
-				nvmeq, cpus_per_queue);
-		if (cpus_weight(mask) < cpus_per_queue)
-			nvme_add_cpus(&mask, unassigned_cpus,
-				topology_core_cpumask(cpu),
-				nvmeq, cpus_per_queue);
-		if (cpus_weight(mask) < cpus_per_queue)
-			nvme_add_cpus(&mask, unassigned_cpus,
-				cpumask_of_node(cpu_to_node(cpu)),
-				nvmeq, cpus_per_queue);
-		if (cpus_weight(mask) < cpus_per_queue)
-			nvme_add_cpus(&mask, unassigned_cpus,
-				cpumask_of_node(
-					nvme_find_closest_node(
-						cpu_to_node(cpu))),
-				nvmeq, cpus_per_queue);
-		if (cpus_weight(mask) < cpus_per_queue)
-			nvme_add_cpus(&mask, unassigned_cpus,
-				unassigned_cpus,
-				nvmeq, cpus_per_queue);
-
-		WARN(cpumask_weight(nvmeq->cpu_mask) != cpus_per_queue,
-			"nvme%d qid:%d mis-matched queue-to-cpu assignment\n",
-			dev->instance, i);
-
-		irq_set_affinity_hint(dev->entry[nvmeq->cq_vector].vector,
-							nvmeq->cpu_mask);
-		cpumask_andnot(unassigned_cpus, unassigned_cpus,
-						nvmeq->cpu_mask);
-		cpu = cpumask_next(cpu, unassigned_cpus);
-		if (remainder && !--remainder)
-			cpus_per_queue++;
-		unlock_nvmeq(nvmeq);
-	}
-	WARN(cpumask_weight(unassigned_cpus), "nvme%d unassigned online cpus\n",
-								dev->instance);
-	i = 0;
-	cpumask_andnot(unassigned_cpus, cpu_possible_mask, cpu_online_mask);
-	for_each_cpu(cpu, unassigned_cpus)
-		*per_cpu_ptr(dev->io_queue, cpu) = (i++ % queues) + 1;
-	free_cpumask_var(unassigned_cpus);
-}
-
 static int set_queue_count(struct nvme_dev *dev, int count)
 {
 	int status;
@@ -2107,7 +1965,7 @@ static int set_queue_count(struct nvme_dev *dev, int count)
 	if (status > 0) {
 		dev_err(&dev->pci_dev->dev, "Could not set queue count (%d)\n",
 									status);
-		return -EBUSY;
+		return 0;
 	}
 	return min(result & 0xffff, result >> 16) + 1;
 }
@@ -2117,39 +1975,15 @@ static size_t db_bar_size(struct nvme_dev *dev, unsigned nr_io_queues)
 	return 4096 + ((nr_io_queues + 1) * 8 * dev->db_stride);
 }
 
-static void nvme_cpu_workfn(struct work_struct *work)
-{
-	struct nvme_dev *dev = container_of(work, struct nvme_dev, cpu_work);
-	if (dev->initialized)
-		nvme_assign_io_queues(dev);
-}
-
-static int nvme_cpu_notify(struct notifier_block *self,
-				unsigned long action, void *hcpu)
-{
-	struct nvme_dev *dev;
-
-	switch (action) {
-	case CPU_ONLINE:
-	case CPU_DEAD:
-		spin_lock(&dev_list_lock);
-		list_for_each_entry(dev, &dev_list, node)
-			schedule_work(&dev->cpu_work);
-		spin_unlock(&dev_list_lock);
-		break;
-	}
-	return NOTIFY_OK;
-}
-
 static int nvme_setup_io_queues(struct nvme_dev *dev)
 {
-	struct nvme_queue *adminq = raw_nvmeq(dev, 0);
+	struct nvme_queue *adminq = dev->queues[0];
 	struct pci_dev *pdev = dev->pci_dev;
 	int result, i, vecs, nr_io_queues, size;
 
 	nr_io_queues = num_possible_cpus();
 	result = set_queue_count(dev, nr_io_queues);
-	if (result < 0)
+	if (result <= 0)
 		return result;
 	if (result < nr_io_queues)
 		nr_io_queues = result;
@@ -2172,6 +2006,13 @@ static int nvme_setup_io_queues(struct nvme_dev *dev)
 	/* Deregister the admin queue's interrupt */
 	free_irq(dev->entry[0].vector, adminq);
 
+	/*
+	 * If we enable msix early due to not intx, disable it again before
+	 * setting up the full range we need.
+	 */
+	if (!pdev->irq)
+		pci_disable_msix(pdev);
+
 	for (i = 0; i < nr_io_queues; i++)
 		dev->entry[i].entry = i;
 	vecs = pci_enable_msix_range(pdev, dev->entry, 1, nr_io_queues);
@@ -2195,14 +2036,12 @@ static int nvme_setup_io_queues(struct nvme_dev *dev)
 	dev->max_qid = nr_io_queues;
 
 	result = queue_request_irq(dev, adminq, adminq->irqname);
-	if (result) {
-		adminq->q_suspended = 1;
+	if (result)
 		goto free_queues;
-	}
 
 	/* Free previously allocated queues that are no longer usable */
 	nvme_free_queues(dev, nr_io_queues + 1);
-	nvme_assign_io_queues(dev);
+	nvme_create_io_queues(dev);
 
 	return 0;
 
@@ -2245,14 +2084,37 @@ static int nvme_dev_add(struct nvme_dev *dev)
 	dev->oncs = le16_to_cpup(&ctrl->oncs);
 	dev->abort_limit = ctrl->acl + 1;
 	dev->vwc = ctrl->vwc;
+	dev->event_limit = min(ctrl->aerl + 1, 8);
 	memcpy(dev->serial, ctrl->sn, sizeof(ctrl->sn));
 	memcpy(dev->model, ctrl->mn, sizeof(ctrl->mn));
 	memcpy(dev->firmware_rev, ctrl->fr, sizeof(ctrl->fr));
 	if (ctrl->mdts)
 		dev->max_hw_sectors = 1 << (ctrl->mdts + shift - 9);
 	if ((pdev->vendor == PCI_VENDOR_ID_INTEL) &&
-			(pdev->device == 0x0953) && ctrl->vs[3])
+			(pdev->device == 0x0953) && ctrl->vs[3]) {
+		unsigned int max_hw_sectors;
+
 		dev->stripe_size = 1 << (ctrl->vs[3] + shift);
+		max_hw_sectors = dev->stripe_size >> (shift - 9);
+		if (dev->max_hw_sectors) {
+			dev->max_hw_sectors = min(max_hw_sectors,
+							dev->max_hw_sectors);
+		} else
+			dev->max_hw_sectors = max_hw_sectors;
+	}
+
+	dev->tagset.ops = &nvme_mq_ops;
+	dev->tagset.nr_hw_queues = dev->online_queues - 1;
+	dev->tagset.timeout = NVME_IO_TIMEOUT;
+	dev->tagset.numa_node = dev_to_node(&dev->pci_dev->dev);
+	dev->tagset.queue_depth =
+				min_t(int, dev->q_depth, BLK_MQ_MAX_DEPTH) - 1;
+	dev->tagset.cmd_size = sizeof(struct nvme_cmd_info);
+	dev->tagset.flags = BLK_MQ_F_SHOULD_MERGE;
+	dev->tagset.driver_data = dev;
+
+	if (blk_mq_alloc_tag_set(&dev->tagset))
+		goto out;
 
 	id_ns = mem;
 	for (i = 1; i <= nn; i++) {
@@ -2293,6 +2155,9 @@ static int nvme_dev_map(struct nvme_dev *dev)
 	dev->entry[0].vector = pdev->irq;
 	pci_set_master(pdev);
 	bars = pci_select_bars(pdev, IORESOURCE_MEM);
+	if (!bars)
+		goto disable_pci;
+
 	if (pci_request_selected_regions(pdev, bars, "nvme"))
 		goto disable_pci;
 
@@ -2303,10 +2168,22 @@ static int nvme_dev_map(struct nvme_dev *dev)
 	dev->bar = ioremap(pci_resource_start(pdev, 0), 8192);
 	if (!dev->bar)
 		goto disable;
+
 	if (readl(&dev->bar->csts) == -1) {
 		result = -ENODEV;
 		goto unmap;
 	}
+
+	/*
+	 * Some devices don't advertse INTx interrupts, pre-enable a single
+	 * MSIX vec for setup. We'll adjust this later.
+	 */
+	if (!pdev->irq) {
+		result = pci_enable_msix(pdev, dev->entry, 1);
+		if (result < 0)
+			goto unmap;
+	}
+
 	cap = readq(&dev->bar->cap);
 	dev->q_depth = min_t(int, NVME_CAP_MQES(cap) + 1, NVME_Q_DEPTH);
 	dev->db_stride = 1 << NVME_CAP_STRIDE(cap);
@@ -2402,7 +2279,8 @@ static int adapter_async_del_queue(struct nvme_queue *nvmeq, u8 opcode,
 	c.delete_queue.qid = cpu_to_le16(nvmeq->qid);
 
 	init_kthread_work(&nvmeq->cmdinfo.work, fn);
-	return nvme_submit_admin_cmd_async(nvmeq->dev, &c, &nvmeq->cmdinfo);
+	return nvme_submit_admin_async_cmd(nvmeq->dev, &c, &nvmeq->cmdinfo,
+								ADMIN_TIMEOUT);
 }
 
 static void nvme_del_cq_work_handler(struct kthread_work *work)
@@ -2465,7 +2343,7 @@ static void nvme_disable_io_queues(struct nvme_dev *dev)
 	atomic_set(&dq.refcount, 0);
 	dq.worker = &worker;
 	for (i = dev->queue_count - 1; i > 0; i--) {
-		struct nvme_queue *nvmeq = raw_nvmeq(dev, i);
+		struct nvme_queue *nvmeq = dev->queues[i];
 
 		if (nvme_suspend_queue(nvmeq))
 			continue;
@@ -2501,13 +2379,16 @@ static void nvme_dev_list_remove(struct nvme_dev *dev)
 static void nvme_dev_shutdown(struct nvme_dev *dev)
 {
 	int i;
+	u32 csts = -1;
 
 	dev->initialized = 0;
 	nvme_dev_list_remove(dev);
 
-	if (!dev->bar || (dev->bar && readl(&dev->bar->csts) == -1)) {
+	if (dev->bar)
+		csts = readl(&dev->bar->csts);
+	if (csts & NVME_CSTS_CFS || !(csts & NVME_CSTS_RDY)) {
 		for (i = dev->queue_count - 1; i >= 0; i--) {
-			struct nvme_queue *nvmeq = raw_nvmeq(dev, i);
+			struct nvme_queue *nvmeq = dev->queues[i];
 			nvme_suspend_queue(nvmeq);
 			nvme_clear_queue(nvmeq);
 		}
@@ -2519,6 +2400,12 @@ static void nvme_dev_shutdown(struct nvme_dev *dev)
 	nvme_dev_unmap(dev);
 }
 
+static void nvme_dev_remove_admin(struct nvme_dev *dev)
+{
+	if (dev->admin_q && !blk_queue_dying(dev->admin_q))
+		blk_cleanup_queue(dev->admin_q);
+}
+
 static void nvme_dev_remove(struct nvme_dev *dev)
 {
 	struct nvme_ns *ns;
@@ -2590,6 +2477,11 @@ static void nvme_free_namespaces(struct nvme_dev *dev)
 
 	list_for_each_entry_safe(ns, next, &dev->namespaces, list) {
 		list_del(&ns->list);
+
+		spin_lock(&dev_list_lock);
+		ns->disk->private_data = NULL;
+		spin_unlock(&dev_list_lock);
+
 		put_disk(ns->disk);
 		kfree(ns);
 	}
@@ -2599,8 +2491,10 @@ static void nvme_free_dev(struct kref *kref)
 {
 	struct nvme_dev *dev = container_of(kref, struct nvme_dev, kref);
 
+	pci_dev_put(dev->pci_dev);
 	nvme_free_namespaces(dev);
-	free_percpu(dev->io_queue);
+	nvme_release_instance(dev);
+	blk_mq_free_tag_set(&dev->tagset);
 	kfree(dev->queues);
 	kfree(dev->entry);
 	kfree(dev);
@@ -2625,9 +2519,16 @@ static int nvme_dev_release(struct inode *inode, struct file *f)
 static long nvme_dev_ioctl(struct file *f, unsigned int cmd, unsigned long arg)
 {
 	struct nvme_dev *dev = f->private_data;
+	struct nvme_ns *ns;
+
 	switch (cmd) {
 	case NVME_IOCTL_ADMIN_CMD:
-		return nvme_user_admin_cmd(dev, (void __user *)arg);
+		return nvme_user_cmd(dev, NULL, (void __user *)arg);
+	case NVME_IOCTL_IO_CMD:
+		if (list_empty(&dev->namespaces))
+			return -ENOTTY;
+		ns = list_first_entry(&dev->namespaces, struct nvme_ns, list);
+		return nvme_user_cmd(dev, ns, (void __user *)arg);
 	default:
 		return -ENOTTY;
 	}
@@ -2641,6 +2542,22 @@ static const struct file_operations nvme_dev_fops = {
 	.compat_ioctl	= nvme_dev_ioctl,
 };
 
+static void nvme_set_irq_hints(struct nvme_dev *dev)
+{
+	struct nvme_queue *nvmeq;
+	int i;
+
+	for (i = 0; i < dev->online_queues; i++) {
+		nvmeq = dev->queues[i];
+
+		if (!nvmeq->hctx)
+			continue;
+
+		irq_set_affinity_hint(dev->entry[nvmeq->cq_vector].vector,
+							nvmeq->hctx->cpumask);
+	}
+}
+
 static int nvme_dev_start(struct nvme_dev *dev)
 {
 	int result;
@@ -2664,7 +2581,7 @@ static int nvme_dev_start(struct nvme_dev *dev)
 
 	if (start_thread) {
 		nvme_thread = kthread_run(nvme_kthread, NULL, "nvme");
-		wake_up(&nvme_kthread_wait);
+		wake_up_all(&nvme_kthread_wait);
 	} else
 		wait_event_killable(nvme_kthread_wait, nvme_thread);
 
@@ -2673,10 +2590,14 @@ static int nvme_dev_start(struct nvme_dev *dev)
 		goto disable;
 	}
 
+	nvme_init_queue(dev->queues[0], 0);
+
 	result = nvme_setup_io_queues(dev);
-	if (result && result != -EBUSY)
+	if (result)
 		goto disable;
 
+	nvme_set_irq_hints(dev);
+
 	return result;
 
  disable:
@@ -2693,7 +2614,7 @@ static int nvme_remove_dead_ctrl(void *arg)
 	struct pci_dev *pdev = dev->pci_dev;
 
 	if (pci_get_drvdata(pdev))
-		pci_stop_and_remove_bus_device(pdev);
+		pci_stop_and_remove_bus_device_locked(pdev);
 	kref_put(&dev->kref, nvme_free_dev);
 	return 0;
 }
@@ -2702,8 +2623,8 @@ static void nvme_remove_disks(struct work_struct *ws)
 {
 	struct nvme_dev *dev = container_of(ws, struct nvme_dev, reset_work);
 
-	nvme_dev_remove(dev);
 	nvme_free_queues(dev, 1);
+	nvme_dev_remove(dev);
 }
 
 static int nvme_dev_resume(struct nvme_dev *dev)
@@ -2711,9 +2632,9 @@ static int nvme_dev_resume(struct nvme_dev *dev)
 	int ret;
 
 	ret = nvme_dev_start(dev);
-	if (ret && ret != -EBUSY)
+	if (ret)
 		return ret;
-	if (ret == -EBUSY) {
+	if (dev->online_queues < 2) {
 		spin_lock(&dev_list_lock);
 		dev->reset_workfn = nvme_remove_disks;
 		queue_work(nvme_workq, &dev->reset_work);
@@ -2727,7 +2648,7 @@ static void nvme_dev_reset(struct nvme_dev *dev)
 {
 	nvme_dev_shutdown(dev);
 	if (nvme_dev_resume(dev)) {
-		dev_err(&dev->pci_dev->dev, "Device failed to resume\n");
+		dev_warn(&dev->pci_dev->dev, "Device failed to resume\n");
 		kref_get(&dev->kref);
 		if (IS_ERR(kthread_run(nvme_remove_dead_ctrl, dev, "nvme%d",
 							dev->instance))) {
@@ -2752,33 +2673,33 @@ static void nvme_reset_workfn(struct work_struct *work)
 
 static int nvme_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 {
-	int result = -ENOMEM;
+	int node, result = -ENOMEM;
 	struct nvme_dev *dev;
 
-	dev = kzalloc(sizeof(*dev), GFP_KERNEL);
+	node = dev_to_node(&pdev->dev);
+	if (node == NUMA_NO_NODE)
+		set_dev_node(&pdev->dev, 0);
+
+	dev = kzalloc_node(sizeof(*dev), GFP_KERNEL, node);
 	if (!dev)
 		return -ENOMEM;
-	dev->entry = kcalloc(num_possible_cpus(), sizeof(*dev->entry),
-								GFP_KERNEL);
+	dev->entry = kzalloc_node(num_possible_cpus() * sizeof(*dev->entry),
+							GFP_KERNEL, node);
 	if (!dev->entry)
 		goto free;
-	dev->queues = kcalloc(num_possible_cpus() + 1, sizeof(void *),
-								GFP_KERNEL);
+	dev->queues = kzalloc_node((num_possible_cpus() + 1) * sizeof(void *),
+							GFP_KERNEL, node);
 	if (!dev->queues)
 		goto free;
-	dev->io_queue = alloc_percpu(unsigned short);
-	if (!dev->io_queue)
-		goto free;
 
 	INIT_LIST_HEAD(&dev->namespaces);
 	dev->reset_workfn = nvme_reset_failed_dev;
 	INIT_WORK(&dev->reset_work, nvme_reset_workfn);
-	INIT_WORK(&dev->cpu_work, nvme_cpu_workfn);
-	dev->pci_dev = pdev;
+	dev->pci_dev = pci_dev_get(pdev);
 	pci_set_drvdata(pdev, dev);
 	result = nvme_set_instance(dev);
 	if (result)
-		goto free;
+		goto put_pci;
 
 	result = nvme_setup_prp_pools(dev);
 	if (result)
@@ -2786,17 +2707,14 @@ static int nvme_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 
 	kref_init(&dev->kref);
 	result = nvme_dev_start(dev);
-	if (result) {
-		if (result == -EBUSY)
-			goto create_cdev;
+	if (result)
 		goto release_pools;
-	}
 
-	result = nvme_dev_add(dev);
+	if (dev->online_queues > 1)
+		result = nvme_dev_add(dev);
 	if (result)
 		goto shutdown;
 
- create_cdev:
 	scnprintf(dev->name, sizeof(dev->name), "nvme%d", dev->instance);
 	dev->miscdev.minor = MISC_DYNAMIC_MINOR;
 	dev->miscdev.parent = &pdev->dev;
@@ -2806,11 +2724,14 @@ static int nvme_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 	if (result)
 		goto remove;
 
+	nvme_set_irq_hints(dev);
+
 	dev->initialized = 1;
 	return 0;
 
  remove:
 	nvme_dev_remove(dev);
+	nvme_dev_remove_admin(dev);
 	nvme_free_namespaces(dev);
  shutdown:
 	nvme_dev_shutdown(dev);
@@ -2819,8 +2740,9 @@ static int nvme_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 	nvme_release_prp_pools(dev);
  release:
 	nvme_release_instance(dev);
+ put_pci:
+	pci_dev_put(dev->pci_dev);
  free:
-	free_percpu(dev->io_queue);
 	kfree(dev->queues);
 	kfree(dev->entry);
 	kfree(dev);
@@ -2829,12 +2751,12 @@ static int nvme_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 
 static void nvme_reset_notify(struct pci_dev *pdev, bool prepare)
 {
-       struct nvme_dev *dev = pci_get_drvdata(pdev);
+	struct nvme_dev *dev = pci_get_drvdata(pdev);
 
-       if (prepare)
-               nvme_dev_shutdown(dev);
-       else
-               nvme_dev_resume(dev);
+	if (prepare)
+		nvme_dev_shutdown(dev);
+	else
+		nvme_dev_resume(dev);
 }
 
 static void nvme_shutdown(struct pci_dev *pdev)
@@ -2853,13 +2775,12 @@ static void nvme_remove(struct pci_dev *pdev)
 
 	pci_set_drvdata(pdev, NULL);
 	flush_work(&dev->reset_work);
-	flush_work(&dev->cpu_work);
 	misc_deregister(&dev->miscdev);
 	nvme_dev_remove(dev);
 	nvme_dev_shutdown(dev);
+	nvme_dev_remove_admin(dev);
 	nvme_free_queues(dev, 0);
-	rcu_barrier();
-	nvme_release_instance(dev);
+	nvme_free_admin_tags(dev);
 	nvme_release_prp_pools(dev);
 	kref_put(&dev->kref, nvme_free_dev);
 }
@@ -2942,18 +2863,11 @@ static int __init nvme_init(void)
 	else if (result > 0)
 		nvme_major = result;
 
-	nvme_nb.notifier_call = &nvme_cpu_notify;
-	result = register_hotcpu_notifier(&nvme_nb);
-	if (result)
-		goto unregister_blkdev;
-
 	result = pci_register_driver(&nvme_driver);
 	if (result)
-		goto unregister_hotcpu;
+		goto unregister_blkdev;
 	return 0;
 
- unregister_hotcpu:
-	unregister_hotcpu_notifier(&nvme_nb);
  unregister_blkdev:
 	unregister_blkdev(nvme_major, "nvme");
  kill_workq:
@@ -2973,6 +2887,6 @@ static void __exit nvme_exit(void)
 
 MODULE_AUTHOR("Matthew Wilcox <willy@linux.intel.com>");
 MODULE_LICENSE("GPL");
-MODULE_VERSION("0.9");
+MODULE_VERSION("1.0");
 module_init(nvme_init);
 module_exit(nvme_exit);

drivers/block/nvme-scsi.c

@@ -2105,7 +2105,7 @@ static int nvme_trans_do_nvme_io(struct nvme_ns *ns, struct sg_io_hdr *hdr,
 
 		nvme_offset += unit_num_blocks;
 
-		nvme_sc = nvme_submit_io_cmd(dev, &c, NULL);
+		nvme_sc = nvme_submit_io_cmd(dev, ns, &c, NULL);
 		if (nvme_sc != NVME_SC_SUCCESS) {
 			nvme_unmap_user_pages(dev,
 				(is_write) ? DMA_TO_DEVICE : DMA_FROM_DEVICE,
@@ -2658,7 +2658,7 @@ static int nvme_trans_start_stop(struct nvme_ns *ns, struct sg_io_hdr *hdr,
 			c.common.opcode = nvme_cmd_flush;
 			c.common.nsid = cpu_to_le32(ns->ns_id);
 
-			nvme_sc = nvme_submit_io_cmd(ns->dev, &c, NULL);
+			nvme_sc = nvme_submit_io_cmd(ns->dev, ns, &c, NULL);
 			res = nvme_trans_status_code(hdr, nvme_sc);
 			if (res)
 				goto out;
@@ -2686,7 +2686,7 @@ static int nvme_trans_synchronize_cache(struct nvme_ns *ns,
 	c.common.opcode = nvme_cmd_flush;
 	c.common.nsid = cpu_to_le32(ns->ns_id);
 
-	nvme_sc = nvme_submit_io_cmd(ns->dev, &c, NULL);
+	nvme_sc = nvme_submit_io_cmd(ns->dev, ns, &c, NULL);
 
 	res = nvme_trans_status_code(hdr, nvme_sc);
 	if (res)
@@ -2894,7 +2894,7 @@ static int nvme_trans_unmap(struct nvme_ns *ns, struct sg_io_hdr *hdr,
 	c.dsm.nr = cpu_to_le32(ndesc - 1);
 	c.dsm.attributes = cpu_to_le32(NVME_DSMGMT_AD);
 
-	nvme_sc = nvme_submit_io_cmd(dev, &c, NULL);
+	nvme_sc = nvme_submit_io_cmd(dev, ns, &c, NULL);
 	res = nvme_trans_status_code(hdr, nvme_sc);
 
 	dma_free_coherent(&dev->pci_dev->dev, ndesc * sizeof(*range),
@@ -2915,6 +2915,14 @@ static int nvme_scsi_translate(struct nvme_ns *ns, struct sg_io_hdr *hdr)
 	if (copy_from_user(cmd, hdr->cmdp, hdr->cmd_len))
 		return -EFAULT;
 
+	/*
+	 * Prime the hdr with good status for scsi commands that don't require
+	 * an nvme command for translation.
+	 */
+	retcode = nvme_trans_status_code(hdr, NVME_SC_SUCCESS);
+	if (retcode)
+		return retcode;
+
 	opcode = cmd[0];
 
 	switch (opcode) {
@@ -3016,152 +3024,6 @@ int nvme_sg_io(struct nvme_ns *ns, struct sg_io_hdr __user *u_hdr)
 	return retcode;
 }
 
-#ifdef CONFIG_COMPAT
-typedef struct sg_io_hdr32 {
-	compat_int_t interface_id;	/* [i] 'S' for SCSI generic (required) */
-	compat_int_t dxfer_direction;	/* [i] data transfer direction  */
-	unsigned char cmd_len;		/* [i] SCSI command length ( <= 16 bytes) */
-	unsigned char mx_sb_len;		/* [i] max length to write to sbp */
-	unsigned short iovec_count;	/* [i] 0 implies no scatter gather */
-	compat_uint_t dxfer_len;		/* [i] byte count of data transfer */
-	compat_uint_t dxferp;		/* [i], [*io] points to data transfer memory
-					      or scatter gather list */
-	compat_uptr_t cmdp;		/* [i], [*i] points to command to perform */
-	compat_uptr_t sbp;		/* [i], [*o] points to sense_buffer memory */
-	compat_uint_t timeout;		/* [i] MAX_UINT->no timeout (unit: millisec) */
-	compat_uint_t flags;		/* [i] 0 -> default, see SG_FLAG... */
-	compat_int_t pack_id;		/* [i->o] unused internally (normally) */
-	compat_uptr_t usr_ptr;		/* [i->o] unused internally */
-	unsigned char status;		/* [o] scsi status */
-	unsigned char masked_status;	/* [o] shifted, masked scsi status */
-	unsigned char msg_status;		/* [o] messaging level data (optional) */
-	unsigned char sb_len_wr;		/* [o] byte count actually written to sbp */
-	unsigned short host_status;	/* [o] errors from host adapter */
-	unsigned short driver_status;	/* [o] errors from software driver */
-	compat_int_t resid;		/* [o] dxfer_len - actual_transferred */
-	compat_uint_t duration;		/* [o] time taken by cmd (unit: millisec) */
-	compat_uint_t info;		/* [o] auxiliary information */
-} sg_io_hdr32_t;  /* 64 bytes long (on sparc32) */
-
-typedef struct sg_iovec32 {
-	compat_uint_t iov_base;
-	compat_uint_t iov_len;
-} sg_iovec32_t;
-
-static int sg_build_iovec(sg_io_hdr_t __user *sgio, void __user *dxferp, u16 iovec_count)
-{
-	sg_iovec_t __user *iov = (sg_iovec_t __user *) (sgio + 1);
-	sg_iovec32_t __user *iov32 = dxferp;
-	int i;
-
-	for (i = 0; i < iovec_count; i++) {
-		u32 base, len;
-
-		if (get_user(base, &iov32[i].iov_base) ||
-		    get_user(len, &iov32[i].iov_len) ||
-		    put_user(compat_ptr(base), &iov[i].iov_base) ||
-		    put_user(len, &iov[i].iov_len))
-			return -EFAULT;
-	}
-
-	if (put_user(iov, &sgio->dxferp))
-		return -EFAULT;
-	return 0;
-}
-
-int nvme_sg_io32(struct nvme_ns *ns, unsigned long arg)
-{
-	sg_io_hdr32_t __user *sgio32 = (sg_io_hdr32_t __user *)arg;
-	sg_io_hdr_t __user *sgio;
-	u16 iovec_count;
-	u32 data;
-	void __user *dxferp;
-	int err;
-	int interface_id;
-
-	if (get_user(interface_id, &sgio32->interface_id))
-		return -EFAULT;
-	if (interface_id != 'S')
-		return -EINVAL;
-
-	if (get_user(iovec_count, &sgio32->iovec_count))
-		return -EFAULT;
-
-	{
-		void __user *top = compat_alloc_user_space(0);
-		void __user *new = compat_alloc_user_space(sizeof(sg_io_hdr_t) +
-				       (iovec_count * sizeof(sg_iovec_t)));
-		if (new > top)
-			return -EINVAL;
-
-		sgio = new;
-	}
-
-	/* Ok, now construct.  */
-	if (copy_in_user(&sgio->interface_id, &sgio32->interface_id,
-			 (2 * sizeof(int)) +
-			 (2 * sizeof(unsigned char)) +
-			 (1 * sizeof(unsigned short)) +
-			 (1 * sizeof(unsigned int))))
-		return -EFAULT;
-
-	if (get_user(data, &sgio32->dxferp))
-		return -EFAULT;
-	dxferp = compat_ptr(data);
-	if (iovec_count) {
-		if (sg_build_iovec(sgio, dxferp, iovec_count))
-			return -EFAULT;
-	} else {
-		if (put_user(dxferp, &sgio->dxferp))
-			return -EFAULT;
-	}
-
-	{
-		unsigned char __user *cmdp;
-		unsigned char __user *sbp;
-
-		if (get_user(data, &sgio32->cmdp))
-			return -EFAULT;
-		cmdp = compat_ptr(data);
-
-		if (get_user(data, &sgio32->sbp))
-			return -EFAULT;
-		sbp = compat_ptr(data);
-
-		if (put_user(cmdp, &sgio->cmdp) ||
-		    put_user(sbp, &sgio->sbp))
-			return -EFAULT;
-	}
-
-	if (copy_in_user(&sgio->timeout, &sgio32->timeout,
-			 3 * sizeof(int)))
-		return -EFAULT;
-
-	if (get_user(data, &sgio32->usr_ptr))
-		return -EFAULT;
-	if (put_user(compat_ptr(data), &sgio->usr_ptr))
-		return -EFAULT;
-
-	err = nvme_sg_io(ns, sgio);
-	if (err >= 0) {
-		void __user *datap;
-
-		if (copy_in_user(&sgio32->pack_id, &sgio->pack_id,
-				 sizeof(int)) ||
-		    get_user(datap, &sgio->usr_ptr) ||
-		    put_user((u32)(unsigned long)datap,
-			     &sgio32->usr_ptr) ||
-		    copy_in_user(&sgio32->status, &sgio->status,
-				 (4 * sizeof(unsigned char)) +
-				 (2 * sizeof(unsigned short)) +
-				 (3 * sizeof(int))))
-			err = -EFAULT;
-	}
-
-	return err;
-}
-#endif
-
 int nvme_sg_get_version_num(int __user *ip)
 {
 	return put_user(sg_version_num, ip);

drivers/block/rsxx/dev.c

@@ -112,37 +112,16 @@ static const struct block_device_operations rsxx_fops = {
 
 static void disk_stats_start(struct rsxx_cardinfo *card, struct bio *bio)
 {
-	struct hd_struct *part0 = &card->gendisk->part0;
-	int rw = bio_data_dir(bio);
-	int cpu;
-
-	cpu = part_stat_lock();
-
-	part_round_stats(cpu, part0);
-	part_inc_in_flight(part0, rw);
-
-	part_stat_unlock();
+	generic_start_io_acct(bio_data_dir(bio), bio_sectors(bio),
+			     &card->gendisk->part0);
 }
 
 static void disk_stats_complete(struct rsxx_cardinfo *card,
 				struct bio *bio,
 				unsigned long start_time)
 {
-	struct hd_struct *part0 = &card->gendisk->part0;
-	unsigned long duration = jiffies - start_time;
-	int rw = bio_data_dir(bio);
-	int cpu;
-
-	cpu = part_stat_lock();
-
-	part_stat_add(cpu, part0, sectors[rw], bio_sectors(bio));
-	part_stat_inc(cpu, part0, ios[rw]);
-	part_stat_add(cpu, part0, ticks[rw], duration);
-
-	part_round_stats(cpu, part0);
-	part_dec_in_flight(part0, rw);
-
-	part_stat_unlock();
+	generic_end_io_acct(bio_data_dir(bio), &card->gendisk->part0,
+			   start_time);
 }
 
 static void bio_dma_done_cb(struct rsxx_cardinfo *card,

drivers/block/xen-blkfront.c

@@ -126,7 +126,6 @@ struct blkfront_info
 	unsigned int persistent_gnts_c;
 	unsigned long shadow_free;
 	unsigned int feature_flush;
-	unsigned int flush_op;
 	unsigned int feature_discard:1;
 	unsigned int feature_secdiscard:1;
 	unsigned int discard_granularity;
@@ -479,7 +478,19 @@ static int blkif_queue_request(struct request *req)
 				 * way.  (It's also a FLUSH+FUA, since it is
 				 * guaranteed ordered WRT previous writes.)
 				 */
-				ring_req->operation = info->flush_op;
+				switch (info->feature_flush &
+					((REQ_FLUSH|REQ_FUA))) {
+				case REQ_FLUSH|REQ_FUA:
+					ring_req->operation =
+						BLKIF_OP_WRITE_BARRIER;
+					break;
+				case REQ_FLUSH:
+					ring_req->operation =
+						BLKIF_OP_FLUSH_DISKCACHE;
+					break;
+				default:
+					ring_req->operation = 0;
+				}
 			}
 			ring_req->u.rw.nr_segments = nseg;
 		}
@@ -582,12 +593,14 @@ static inline void flush_requests(struct blkfront_info *info)
 		notify_remote_via_irq(info->irq);
 }
 
-static inline bool blkif_request_flush_valid(struct request *req,
-					     struct blkfront_info *info)
+static inline bool blkif_request_flush_invalid(struct request *req,
+					       struct blkfront_info *info)
 {
 	return ((req->cmd_type != REQ_TYPE_FS) ||
-		((req->cmd_flags & (REQ_FLUSH | REQ_FUA)) &&
-		!info->flush_op));
+		((req->cmd_flags & REQ_FLUSH) &&
+		 !(info->feature_flush & REQ_FLUSH)) ||
+		((req->cmd_flags & REQ_FUA) &&
+		 !(info->feature_flush & REQ_FUA)));
 }
 
 /*
@@ -612,8 +625,8 @@ static void do_blkif_request(struct request_queue *rq)
 
 		blk_start_request(req);
 
-		if (blkif_request_flush_valid(req, info)) {
-			__blk_end_request_all(req, -EIO);
+		if (blkif_request_flush_invalid(req, info)) {
+			__blk_end_request_all(req, -EOPNOTSUPP);
 			continue;
 		}
 
@@ -683,20 +696,26 @@ static int xlvbd_init_blk_queue(struct gendisk *gd, u16 sector_size,
 	return 0;
 }
 
+static const char *flush_info(unsigned int feature_flush)
+{
+	switch (feature_flush & ((REQ_FLUSH | REQ_FUA))) {
+	case REQ_FLUSH|REQ_FUA:
+		return "barrier: enabled;";
+	case REQ_FLUSH:
+		return "flush diskcache: enabled;";
+	default:
+		return "barrier or flush: disabled;";
+	}
+}
 
 static void xlvbd_flush(struct blkfront_info *info)
 {
 	blk_queue_flush(info->rq, info->feature_flush);
-	printk(KERN_INFO "blkfront: %s: %s: %s %s %s %s %s\n",
-	       info->gd->disk_name,
-	       info->flush_op == BLKIF_OP_WRITE_BARRIER ?
-		"barrier" : (info->flush_op == BLKIF_OP_FLUSH_DISKCACHE ?
-		"flush diskcache" : "barrier or flush"),
-	       info->feature_flush ? "enabled;" : "disabled;",
-	       "persistent grants:",
-	       info->feature_persistent ? "enabled;" : "disabled;",
-	       "indirect descriptors:",
-	       info->max_indirect_segments ? "enabled;" : "disabled;");
+	pr_info("blkfront: %s: %s %s %s %s %s\n",
+		info->gd->disk_name, flush_info(info->feature_flush),
+		"persistent grants:", info->feature_persistent ?
+		"enabled;" : "disabled;", "indirect descriptors:",
+		info->max_indirect_segments ? "enabled;" : "disabled;");
 }
 
 static int xen_translate_vdev(int vdevice, int *minor, unsigned int *offset)
@@ -1188,7 +1207,6 @@ static irqreturn_t blkif_interrupt(int irq, void *dev_id)
 				if (error == -EOPNOTSUPP)
 					error = 0;
 				info->feature_flush = 0;
-				info->flush_op = 0;
 				xlvbd_flush(info);
 			}
 			/* fall through */
@@ -1808,7 +1826,6 @@ static void blkfront_connect(struct blkfront_info *info)
 		physical_sector_size = sector_size;
 
 	info->feature_flush = 0;
-	info->flush_op = 0;
 
 	err = xenbus_gather(XBT_NIL, info->xbdev->otherend,
 			    "feature-barrier", "%d", &barrier,
@@ -1821,10 +1838,8 @@ static void blkfront_connect(struct blkfront_info *info)
 	 *
 	 * If there are barriers, then we use flush.
 	 */
-	if (!err && barrier) {
+	if (!err && barrier)
 		info->feature_flush = REQ_FLUSH | REQ_FUA;
-		info->flush_op = BLKIF_OP_WRITE_BARRIER;
-	}
 	/*
 	 * And if there is "feature-flush-cache" use that above
 	 * barriers.
@@ -1833,10 +1848,8 @@ static void blkfront_connect(struct blkfront_info *info)
 			    "feature-flush-cache", "%d", &flush,
 			    NULL);
 
-	if (!err && flush) {
+	if (!err && flush)
 		info->feature_flush = REQ_FLUSH;
-		info->flush_op = BLKIF_OP_FLUSH_DISKCACHE;
-	}
 
 	err = xenbus_gather(XBT_NIL, info->xbdev->otherend,
 			    "feature-discard", "%d", &discard,

drivers/md/bcache/request.c

@@ -601,13 +601,8 @@ static void request_endio(struct bio *bio, int error)
 static void bio_complete(struct search *s)
 {
 	if (s->orig_bio) {
-		int cpu, rw = bio_data_dir(s->orig_bio);
-		unsigned long duration = jiffies - s->start_time;
-
-		cpu = part_stat_lock();
-		part_round_stats(cpu, &s->d->disk->part0);
-		part_stat_add(cpu, &s->d->disk->part0, ticks[rw], duration);
-		part_stat_unlock();
+		generic_end_io_acct(bio_data_dir(s->orig_bio),
+				    &s->d->disk->part0, s->start_time);
 
 		trace_bcache_request_end(s->d, s->orig_bio);
 		bio_endio(s->orig_bio, s->iop.error);
@@ -959,12 +954,9 @@ static void cached_dev_make_request(struct request_queue *q, struct bio *bio)
 	struct search *s;
 	struct bcache_device *d = bio->bi_bdev->bd_disk->private_data;
 	struct cached_dev *dc = container_of(d, struct cached_dev, disk);
-	int cpu, rw = bio_data_dir(bio);
+	int rw = bio_data_dir(bio);
 
-	cpu = part_stat_lock();
-	part_stat_inc(cpu, &d->disk->part0, ios[rw]);
-	part_stat_add(cpu, &d->disk->part0, sectors[rw], bio_sectors(bio));
-	part_stat_unlock();
+	generic_start_io_acct(rw, bio_sectors(bio), &d->disk->part0);
 
 	bio->bi_bdev = dc->bdev;
 	bio->bi_iter.bi_sector += dc->sb.data_offset;
@@ -1074,12 +1066,9 @@ static void flash_dev_make_request(struct request_queue *q, struct bio *bio)
 	struct search *s;
 	struct closure *cl;
 	struct bcache_device *d = bio->bi_bdev->bd_disk->private_data;
-	int cpu, rw = bio_data_dir(bio);
+	int rw = bio_data_dir(bio);
 
-	cpu = part_stat_lock();
-	part_stat_inc(cpu, &d->disk->part0, ios[rw]);
-	part_stat_add(cpu, &d->disk->part0, sectors[rw], bio_sectors(bio));
-	part_stat_unlock();
+	generic_start_io_acct(rw, bio_sectors(bio), &d->disk->part0);
 
 	s = search_alloc(bio, d);
 	cl = &s->cl;

drivers/md/dm.c

@@ -605,13 +605,10 @@ static void end_io_acct(struct dm_io *io)
 	struct mapped_device *md = io->md;
 	struct bio *bio = io->bio;
 	unsigned long duration = jiffies - io->start_time;
-	int pending, cpu;
+	int pending;
 	int rw = bio_data_dir(bio);
 
-	cpu = part_stat_lock();
-	part_round_stats(cpu, &dm_disk(md)->part0);
-	part_stat_add(cpu, &dm_disk(md)->part0, ticks[rw], duration);
-	part_stat_unlock();
+	generic_end_io_acct(rw, &dm_disk(md)->part0, io->start_time);
 
 	if (unlikely(dm_stats_used(&md->stats)))
 		dm_stats_account_io(&md->stats, bio->bi_rw, bio->bi_iter.bi_sector,
@@ -1651,16 +1648,12 @@ static void _dm_request(struct request_queue *q, struct bio *bio)
 {
 	int rw = bio_data_dir(bio);
 	struct mapped_device *md = q->queuedata;
-	int cpu;
 	int srcu_idx;
 	struct dm_table *map;
 
 	map = dm_get_live_table(md, &srcu_idx);
 
-	cpu = part_stat_lock();
-	part_stat_inc(cpu, &dm_disk(md)->part0, ios[rw]);
-	part_stat_add(cpu, &dm_disk(md)->part0, sectors[rw], bio_sectors(bio));
-	part_stat_unlock();
+	generic_start_io_acct(rw, bio_sectors(bio), &dm_disk(md)->part0);
 
 	/* if we're suspended, we have to queue this io for later */
 	if (unlikely(test_bit(DMF_BLOCK_IO_FOR_SUSPEND, &md->flags))) {

drivers/md/md.c

@@ -247,7 +247,6 @@ static void md_make_request(struct request_queue *q, struct bio *bio)
 {
 	const int rw = bio_data_dir(bio);
 	struct mddev *mddev = q->queuedata;
-	int cpu;
 	unsigned int sectors;
 
 	if (mddev == NULL || mddev->pers == NULL
@@ -284,10 +283,7 @@ static void md_make_request(struct request_queue *q, struct bio *bio)
 	sectors = bio_sectors(bio);
 	mddev->pers->make_request(mddev, bio);
 
-	cpu = part_stat_lock();
-	part_stat_inc(cpu, &mddev->gendisk->part0, ios[rw]);
-	part_stat_add(cpu, &mddev->gendisk->part0, sectors[rw], sectors);
-	part_stat_unlock();
+	generic_start_io_acct(rw, sectors, &mddev->gendisk->part0);
 
 	if (atomic_dec_and_test(&mddev->active_io) && mddev->suspended)
 		wake_up(&mddev->sb_wait);

include/linux/drbd.h

@@ -172,7 +172,7 @@ enum drbd_ret_code {
 	ERR_RES_NOT_KNOWN	= 158,
 	ERR_RES_IN_USE		= 159,
 	ERR_MINOR_CONFIGURED    = 160,
-	ERR_MINOR_EXISTS	= 161,
+	ERR_MINOR_OR_VOLUME_EXISTS = 161,
 	ERR_INVALID_REQUEST	= 162,
 	ERR_NEED_APV_100	= 163,
 	ERR_NEED_ALLOW_TWO_PRI  = 164,

include/linux/nvme.h

@@ -19,6 +19,7 @@
 #include <linux/pci.h>
 #include <linux/miscdevice.h>
 #include <linux/kref.h>
+#include <linux/blk-mq.h>
 
 struct nvme_bar {
 	__u64			cap;	/* Controller Capabilities */
@@ -38,6 +39,7 @@ struct nvme_bar {
 #define NVME_CAP_TIMEOUT(cap)	(((cap) >> 24) & 0xff)
 #define NVME_CAP_STRIDE(cap)	(((cap) >> 32) & 0xf)
 #define NVME_CAP_MPSMIN(cap)	(((cap) >> 48) & 0xf)
+#define NVME_CAP_MPSMAX(cap)	(((cap) >> 52) & 0xf)
 
 enum {
 	NVME_CC_ENABLE		= 1 << 0,
@@ -70,8 +72,10 @@ extern unsigned char nvme_io_timeout;
  */
 struct nvme_dev {
 	struct list_head node;
-	struct nvme_queue __rcu **queues;
-	unsigned short __percpu *io_queue;
+	struct nvme_queue **queues;
+	struct request_queue *admin_q;
+	struct blk_mq_tag_set tagset;
+	struct blk_mq_tag_set admin_tagset;
 	u32 __iomem *dbs;
 	struct pci_dev *pci_dev;
 	struct dma_pool *prp_page_pool;
@@ -90,15 +94,16 @@ struct nvme_dev {
 	struct miscdevice miscdev;
 	work_func_t reset_workfn;
 	struct work_struct reset_work;
-	struct work_struct cpu_work;
 	char name[12];
 	char serial[20];
 	char model[40];
 	char firmware_rev[8];
 	u32 max_hw_sectors;
 	u32 stripe_size;
+	u32 page_size;
 	u16 oncs;
 	u16 abort_limit;
+	u8 event_limit;
 	u8 vwc;
 	u8 initialized;
 };
@@ -132,7 +137,6 @@ struct nvme_iod {
 	int offset;		/* Of PRP list */
 	int nents;		/* Used in scatterlist */
 	int length;		/* Of data, in bytes */
-	unsigned long start_time;
 	dma_addr_t first_dma;
 	struct list_head node;
 	struct scatterlist sg[0];
@@ -150,12 +154,14 @@ static inline u64 nvme_block_nr(struct nvme_ns *ns, sector_t sector)
  */
 void nvme_free_iod(struct nvme_dev *dev, struct nvme_iod *iod);
 
-int nvme_setup_prps(struct nvme_dev *, struct nvme_iod *, int , gfp_t);
+int nvme_setup_prps(struct nvme_dev *, struct nvme_iod *, int, gfp_t);
 struct nvme_iod *nvme_map_user_pages(struct nvme_dev *dev, int write,
 				unsigned long addr, unsigned length);
 void nvme_unmap_user_pages(struct nvme_dev *dev, int write,
 			struct nvme_iod *iod);
-int nvme_submit_io_cmd(struct nvme_dev *, struct nvme_command *, u32 *);
+int nvme_submit_io_cmd(struct nvme_dev *, struct nvme_ns *,
+						struct nvme_command *, u32 *);
+int nvme_submit_flush_data(struct nvme_queue *nvmeq, struct nvme_ns *ns);
 int nvme_submit_admin_cmd(struct nvme_dev *, struct nvme_command *,
 							u32 *result);
 int nvme_identify(struct nvme_dev *, unsigned nsid, unsigned cns,

include/uapi/linux/nvme.h

@@ -181,6 +181,22 @@ enum {
 	NVME_LBART_ATTRIB_HIDE	= 1 << 1,
 };
 
+struct nvme_reservation_status {
+	__le32	gen;
+	__u8	rtype;
+	__u8	regctl[2];
+	__u8	resv5[2];
+	__u8	ptpls;
+	__u8	resv10[13];
+	struct {
+		__le16	cntlid;
+		__u8	rcsts;
+		__u8	resv3[5];
+		__le64	hostid;
+		__le64	rkey;
+	} regctl_ds[];
+};
+
 /* I/O commands */
 
 enum nvme_opcode {
@@ -189,7 +205,12 @@ enum nvme_opcode {
 	nvme_cmd_read		= 0x02,
 	nvme_cmd_write_uncor	= 0x04,
 	nvme_cmd_compare	= 0x05,
+	nvme_cmd_write_zeroes	= 0x08,
 	nvme_cmd_dsm		= 0x09,
+	nvme_cmd_resv_register	= 0x0d,
+	nvme_cmd_resv_report	= 0x0e,
+	nvme_cmd_resv_acquire	= 0x11,
+	nvme_cmd_resv_release	= 0x15,
 };
 
 struct nvme_common_command {
@@ -305,7 +326,11 @@ enum {
 	NVME_FEAT_IRQ_CONFIG	= 0x09,
 	NVME_FEAT_WRITE_ATOMIC	= 0x0a,
 	NVME_FEAT_ASYNC_EVENT	= 0x0b,
-	NVME_FEAT_SW_PROGRESS	= 0x0c,
+	NVME_FEAT_AUTO_PST	= 0x0c,
+	NVME_FEAT_SW_PROGRESS	= 0x80,
+	NVME_FEAT_HOST_ID	= 0x81,
+	NVME_FEAT_RESV_MASK	= 0x82,
+	NVME_FEAT_RESV_PERSIST	= 0x83,
 	NVME_LOG_ERROR		= 0x01,
 	NVME_LOG_SMART		= 0x02,
 	NVME_LOG_FW_SLOT	= 0x03,
@@ -440,9 +465,15 @@ enum {
 	NVME_SC_FUSED_MISSING		= 0xa,
 	NVME_SC_INVALID_NS		= 0xb,
 	NVME_SC_CMD_SEQ_ERROR		= 0xc,
+	NVME_SC_SGL_INVALID_LAST	= 0xd,
+	NVME_SC_SGL_INVALID_COUNT	= 0xe,
+	NVME_SC_SGL_INVALID_DATA	= 0xf,
+	NVME_SC_SGL_INVALID_METADATA	= 0x10,
+	NVME_SC_SGL_INVALID_TYPE	= 0x11,
 	NVME_SC_LBA_RANGE		= 0x80,
 	NVME_SC_CAP_EXCEEDED		= 0x81,
 	NVME_SC_NS_NOT_READY		= 0x82,
+	NVME_SC_RESERVATION_CONFLICT	= 0x83,
 	NVME_SC_CQ_INVALID		= 0x100,
 	NVME_SC_QID_INVALID		= 0x101,
 	NVME_SC_QUEUE_SIZE		= 0x102,
@@ -454,7 +485,15 @@ enum {
 	NVME_SC_INVALID_VECTOR		= 0x108,
 	NVME_SC_INVALID_LOG_PAGE	= 0x109,
 	NVME_SC_INVALID_FORMAT		= 0x10a,
+	NVME_SC_FIRMWARE_NEEDS_RESET	= 0x10b,
+	NVME_SC_INVALID_QUEUE		= 0x10c,
+	NVME_SC_FEATURE_NOT_SAVEABLE	= 0x10d,
+	NVME_SC_FEATURE_NOT_CHANGEABLE	= 0x10e,
+	NVME_SC_FEATURE_NOT_PER_NS	= 0x10f,
+	NVME_SC_FW_NEEDS_RESET_SUBSYS	= 0x110,
 	NVME_SC_BAD_ATTRIBUTES		= 0x180,
+	NVME_SC_INVALID_PI		= 0x181,
+	NVME_SC_READ_ONLY		= 0x182,
 	NVME_SC_WRITE_FAULT		= 0x280,
 	NVME_SC_READ_ERROR		= 0x281,
 	NVME_SC_GUARD_CHECK		= 0x282,
@@ -489,7 +528,7 @@ struct nvme_user_io {
 	__u16	appmask;
 };
 
-struct nvme_admin_cmd {
+struct nvme_passthru_cmd {
 	__u8	opcode;
 	__u8	flags;
 	__u16	rsvd1;
@@ -510,8 +549,11 @@ struct nvme_admin_cmd {
 	__u32	result;
 };
 
+#define nvme_admin_cmd nvme_passthru_cmd
+
 #define NVME_IOCTL_ID		_IO('N', 0x40)
 #define NVME_IOCTL_ADMIN_CMD	_IOWR('N', 0x41, struct nvme_admin_cmd)
 #define NVME_IOCTL_SUBMIT_IO	_IOW('N', 0x42, struct nvme_user_io)
+#define NVME_IOCTL_IO_CMD	_IOWR('N', 0x43, struct nvme_passthru_cmd)
 
 #endif /* _UAPI_LINUX_NVME_H */