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);
@@ -2825,18 +2817,15 @@ 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);
 	}
 
 	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 @@ int drbd_adm_del_minor(struct sk_buff *skb, struct genl_info *info)
 	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:
@@ -3608,35 +3618,17 @@ 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);
 	if (!adm_ctx.reply_skb)
 		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) &&