Merge branch 'for-4.5/drivers' of git://git.kernel.dk/linux-block

Pull block driver updates from Jens Axboe:
 "This is the block driver pull request for 4.5, with the exception of
  NVMe, which is in a separate branch and will be posted after this one.

  This pull request contains:

   - A set of bcache stability fixes, which have been acked by Kent.
     These have been used and tested for more than a year by the
     community, so it's about time that they got in.

   - A set of drbd updates from the drbd team (Andreas, Lars, Philipp)
     and Markus Elfring, Oleg Drokin.

   - A set of fixes for xen blkback/front from the usual suspects, (Bob,
     Konrad) as well as community based fixes from Kiri, Julien, and
     Peng.

   - A 2038 time fix for sx8 from Shraddha, with a fix from me.

   - A small mtip32xx cleanup from Zhu Yanjun.

   - A null_blk division fix from Arnd"

* 'for-4.5/drivers' of git://git.kernel.dk/linux-block: (71 commits)
  null_blk: use sector_div instead of do_div
  mtip32xx: restrict variables visible in current code module
  xen/blkfront: Fix crash if backend doesn't follow the right states.
  xen/blkback: Fix two memory leaks.
  xen/blkback: make st_ statistics per ring
  xen/blkfront: Handle non-indirect grant with 64KB pages
  xen-blkfront: Introduce blkif_ring_get_request
  xen-blkback: clear PF_NOFREEZE for xen_blkif_schedule()
  xen/blkback: Free resources if connect_ring failed.
  xen/blocks: Return -EXX instead of -1
  xen/blkback: make pool of persistent grants and free pages per-queue
  xen/blkback: get the number of hardware queues/rings from blkfront
  xen/blkback: pseudo support for multi hardware queues/rings
  xen/blkback: separate ring information out of struct xen_blkif
  xen/blkfront: correct setting for xen_blkif_max_ring_order
  xen/blkfront: make persistent grants pool per-queue
  xen/blkfront: Remove duplicate setting of ->xbdev.
  xen/blkfront: Cleanup of comments, fix unaligned variables, and syntax errors.
  xen/blkfront: negotiate number of queues/rings to be used with backend
  xen/blkfront: split per device io_lock
  ...

MAINTAINERS

@@ -3665,13 +3665,12 @@ F:	drivers/scsi/dpt*
 F:	drivers/scsi/dpt/
 
 DRBD DRIVER
-P:	Philipp Reisner
-P:	Lars Ellenberg
-M:	drbd-dev@lists.linbit.com
-L:	drbd-user@lists.linbit.com
+M:	Philipp Reisner <philipp.reisner@linbit.com>
+M:	Lars Ellenberg <lars.ellenberg@linbit.com>
+L:	drbd-dev@lists.linbit.com
 W:	http://www.drbd.org
-T:	git git://git.drbd.org/linux-2.6-drbd.git drbd
-T:	git git://git.drbd.org/drbd-8.3.git
+T:	git git://git.linbit.com/linux-drbd.git
+T:	git git://git.linbit.com/drbd-8.4.git
 S:	Supported
 F:	drivers/block/drbd/
 F:	lib/lru_cache.c

drivers/block/drbd/drbd_bitmap.c

@@ -24,7 +24,7 @@
 
 #define pr_fmt(fmt)	KBUILD_MODNAME ": " fmt
 
-#include <linux/bitops.h>
+#include <linux/bitmap.h>
 #include <linux/vmalloc.h>
 #include <linux/string.h>
 #include <linux/drbd.h>
@@ -479,8 +479,14 @@ void drbd_bm_cleanup(struct drbd_device *device)
  * this masks out the remaining bits.
  * Returns the number of bits cleared.
  */
+#ifndef BITS_PER_PAGE
 #define BITS_PER_PAGE		(1UL << (PAGE_SHIFT + 3))
 #define BITS_PER_PAGE_MASK	(BITS_PER_PAGE - 1)
+#else
+# if BITS_PER_PAGE != (1UL << (PAGE_SHIFT + 3))
+#  error "ambiguous BITS_PER_PAGE"
+# endif
+#endif
 #define BITS_PER_LONG_MASK	(BITS_PER_LONG - 1)
 static int bm_clear_surplus(struct drbd_bitmap *b)
 {
@@ -559,21 +565,19 @@ static unsigned long bm_count_bits(struct drbd_bitmap *b)
 	unsigned long *p_addr;
 	unsigned long bits = 0;
 	unsigned long mask = (1UL << (b->bm_bits & BITS_PER_LONG_MASK)) -1;
-	int idx, i, last_word;
+	int idx, last_word;
 
 	/* all but last page */
 	for (idx = 0; idx < b->bm_number_of_pages - 1; idx++) {
 		p_addr = __bm_map_pidx(b, idx);
-		for (i = 0; i < LWPP; i++)
-			bits += hweight_long(p_addr[i]);
+		bits += bitmap_weight(p_addr, BITS_PER_PAGE);
 		__bm_unmap(p_addr);
 		cond_resched();
 	}
 	/* last (or only) page */
 	last_word = ((b->bm_bits - 1) & BITS_PER_PAGE_MASK) >> LN2_BPL;
 	p_addr = __bm_map_pidx(b, idx);
-	for (i = 0; i < last_word; i++)
-		bits += hweight_long(p_addr[i]);
+	bits += bitmap_weight(p_addr, last_word * BITS_PER_LONG);
 	p_addr[last_word] &= cpu_to_lel(mask);
 	bits += hweight_long(p_addr[last_word]);
 	/* 32bit arch, may have an unused padding long */
@@ -1419,6 +1423,9 @@ static inline void bm_set_full_words_within_one_page(struct drbd_bitmap *b,
 	int bits;
 	int changed = 0;
 	unsigned long *paddr = kmap_atomic(b->bm_pages[page_nr]);
+
+	/* I think it is more cache line friendly to hweight_long then set to ~0UL,
+	 * than to first bitmap_weight() all words, then bitmap_fill() all words */
 	for (i = first_word; i < last_word; i++) {
 		bits = hweight_long(paddr[i]);
 		paddr[i] = ~0UL;
@@ -1628,8 +1635,7 @@ int drbd_bm_e_weight(struct drbd_device *device, unsigned long enr)
 		int n = e-s;
 		p_addr = bm_map_pidx(b, bm_word_to_page_idx(b, s));
 		bm = p_addr + MLPP(s);
-		while (n--)
-			count += hweight_long(*bm++);
+		count += bitmap_weight(bm, n * BITS_PER_LONG);
 		bm_unmap(p_addr);
 	} else {
 		drbd_err(device, "start offset (%d) too large in drbd_bm_e_weight\n", s);

drivers/block/drbd/drbd_debugfs.c

@@ -771,6 +771,13 @@ static int device_data_gen_id_show(struct seq_file *m, void *ignored)
 	return 0;
 }
 
+static int device_ed_gen_id_show(struct seq_file *m, void *ignored)
+{
+	struct drbd_device *device = m->private;
+	seq_printf(m, "0x%016llX\n", (unsigned long long)device->ed_uuid);
+	return 0;
+}
+
 #define drbd_debugfs_device_attr(name)						\
 static int device_ ## name ## _open(struct inode *inode, struct file *file)	\
 {										\
@@ -796,6 +803,7 @@ drbd_debugfs_device_attr(oldest_requests)
 drbd_debugfs_device_attr(act_log_extents)
 drbd_debugfs_device_attr(resync_extents)
 drbd_debugfs_device_attr(data_gen_id)
+drbd_debugfs_device_attr(ed_gen_id)
 
 void drbd_debugfs_device_add(struct drbd_device *device)
 {
@@ -839,6 +847,7 @@ void drbd_debugfs_device_add(struct drbd_device *device)
 	DCF(act_log_extents);
 	DCF(resync_extents);
 	DCF(data_gen_id);
+	DCF(ed_gen_id);
 #undef DCF
 	return;
 
@@ -854,6 +863,7 @@ void drbd_debugfs_device_cleanup(struct drbd_device *device)
 	drbd_debugfs_remove(&device->debugfs_vol_act_log_extents);
 	drbd_debugfs_remove(&device->debugfs_vol_resync_extents);
 	drbd_debugfs_remove(&device->debugfs_vol_data_gen_id);
+	drbd_debugfs_remove(&device->debugfs_vol_ed_gen_id);
 	drbd_debugfs_remove(&device->debugfs_vol);
 }
 

drivers/block/drbd/drbd_int.h

@@ -77,13 +77,6 @@ extern int fault_devs;
 extern char usermode_helper[];
 
 
-/* I don't remember why XCPU ...
- * This is used to wake the asender,
- * and to interrupt sending the sending task
- * on disconnect.
- */
-#define DRBD_SIG SIGXCPU
-
 /* This is used to stop/restart our threads.
  * Cannot use SIGTERM nor SIGKILL, since these
  * are sent out by init on runlevel changes
@@ -292,6 +285,9 @@ struct drbd_device_work {
 
 extern int drbd_wait_misc(struct drbd_device *, struct drbd_interval *);
 
+extern void lock_all_resources(void);
+extern void unlock_all_resources(void);
+
 struct drbd_request {
 	struct drbd_work w;
 	struct drbd_device *device;
@@ -504,7 +500,6 @@ enum {
 
 	MD_NO_FUA,		/* Users wants us to not use FUA/FLUSH on meta data dev */
 
-	SUSPEND_IO,		/* suspend application io */
 	BITMAP_IO,		/* suspend application io;
 				   once no more io in flight, start bitmap io */
 	BITMAP_IO_QUEUED,       /* Started bitmap IO */
@@ -632,12 +627,6 @@ struct bm_io_work {
 	void (*done)(struct drbd_device *device, int rv);
 };
 
-enum write_ordering_e {
-	WO_none,
-	WO_drain_io,
-	WO_bdev_flush,
-};
-
 struct fifo_buffer {
 	unsigned int head_index;
 	unsigned int size;
@@ -650,8 +639,7 @@ extern struct fifo_buffer *fifo_alloc(int fifo_size);
 enum {
 	NET_CONGESTED,		/* The data socket is congested */
 	RESOLVE_CONFLICTS,	/* Set on one node, cleared on the peer! */
-	SEND_PING,		/* whether asender should send a ping asap */
-	SIGNAL_ASENDER,		/* whether asender wants to be interrupted */
+	SEND_PING,
 	GOT_PING_ACK,		/* set when we receive a ping_ack packet, ping_wait gets woken */
 	CONN_WD_ST_CHG_REQ,	/* A cluster wide state change on the connection is active */
 	CONN_WD_ST_CHG_OKAY,
@@ -670,6 +658,8 @@ enum {
 	DEVICE_WORK_PENDING,	/* tell worker that some device has pending work */
 };
 
+enum which_state { NOW, OLD = NOW, NEW };
+
 struct drbd_resource {
 	char *name;
 #ifdef CONFIG_DEBUG_FS
@@ -755,7 +745,8 @@ struct drbd_connection {
 	unsigned long last_reconnect_jif;
 	struct drbd_thread receiver;
 	struct drbd_thread worker;
-	struct drbd_thread asender;
+	struct drbd_thread ack_receiver;
+	struct workqueue_struct *ack_sender;
 
 	/* cached pointers,
 	 * so we can look up the oldest pending requests more quickly.
@@ -774,6 +765,8 @@ struct drbd_connection {
 	struct drbd_thread_timing_details r_timing_details[DRBD_THREAD_DETAILS_HIST];
 
 	struct {
+		unsigned long last_sent_barrier_jif;
+
 		/* whether this sender thread
 		 * has processed a single write yet. */
 		bool seen_any_write_yet;
@@ -788,6 +781,17 @@ struct drbd_connection {
 	} send;
 };
 
+static inline bool has_net_conf(struct drbd_connection *connection)
+{
+	bool has_net_conf;
+
+	rcu_read_lock();
+	has_net_conf = rcu_dereference(connection->net_conf);
+	rcu_read_unlock();
+
+	return has_net_conf;
+}
+
 void __update_timing_details(
 		struct drbd_thread_timing_details *tdp,
 		unsigned int *cb_nr,
@@ -811,6 +815,7 @@ struct drbd_peer_device {
 	struct list_head peer_devices;
 	struct drbd_device *device;
 	struct drbd_connection *connection;
+	struct work_struct send_acks_work;
 #ifdef CONFIG_DEBUG_FS
 	struct dentry *debugfs_peer_dev;
 #endif
@@ -829,6 +834,7 @@ struct drbd_device {
 	struct dentry *debugfs_vol_act_log_extents;
 	struct dentry *debugfs_vol_resync_extents;
 	struct dentry *debugfs_vol_data_gen_id;
+	struct dentry *debugfs_vol_ed_gen_id;
 #endif
 
 	unsigned int vnr;	/* volume number within the connection */
@@ -873,6 +879,7 @@ struct drbd_device {
 	atomic_t rs_pending_cnt; /* RS request/data packets on the wire */
 	atomic_t unacked_cnt;	 /* Need to send replies for */
 	atomic_t local_cnt;	 /* Waiting for local completion */
+	atomic_t suspend_cnt;
 
 	/* Interval tree of pending local requests */
 	struct rb_root read_requests;
@@ -1020,6 +1027,12 @@ static inline struct drbd_peer_device *first_peer_device(struct drbd_device *dev
 	return list_first_entry_or_null(&device->peer_devices, struct drbd_peer_device, peer_devices);
 }
 
+static inline struct drbd_peer_device *
+conn_peer_device(struct drbd_connection *connection, int volume_number)
+{
+	return idr_find(&connection->peer_devices, volume_number);
+}
+
 #define for_each_resource(resource, _resources) \
 	list_for_each_entry(resource, _resources, resources)
 
@@ -1113,7 +1126,7 @@ extern int drbd_send_ov_request(struct drbd_peer_device *, sector_t sector, int
 extern int drbd_send_bitmap(struct drbd_device *device);
 extern void drbd_send_sr_reply(struct drbd_peer_device *, enum drbd_state_rv retcode);
 extern void conn_send_sr_reply(struct drbd_connection *connection, enum drbd_state_rv retcode);
-extern void drbd_free_ldev(struct drbd_backing_dev *ldev);
+extern void drbd_backing_dev_free(struct drbd_device *device, struct drbd_backing_dev *ldev);
 extern void drbd_device_cleanup(struct drbd_device *device);
 void drbd_print_uuids(struct drbd_device *device, const char *text);
 
@@ -1424,7 +1437,7 @@ extern struct bio_set *drbd_md_io_bio_set;
 /* to allocate from that set */
 extern struct bio *bio_alloc_drbd(gfp_t gfp_mask);
 
-extern rwlock_t global_state_lock;
+extern struct mutex resources_mutex;
 
 extern int conn_lowest_minor(struct drbd_connection *connection);
 extern enum drbd_ret_code drbd_create_device(struct drbd_config_context *adm_ctx, unsigned int minor);
@@ -1454,6 +1467,9 @@ extern int is_valid_ar_handle(struct drbd_request *, sector_t);
 
 
 /* drbd_nl.c */
+
+extern struct mutex notification_mutex;
+
 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);
@@ -1536,7 +1552,9 @@ extern void drbd_endio_write_sec_final(struct drbd_peer_request *peer_req);
 
 /* drbd_receiver.c */
 extern int drbd_receiver(struct drbd_thread *thi);
-extern int drbd_asender(struct drbd_thread *thi);
+extern int drbd_ack_receiver(struct drbd_thread *thi);
+extern void drbd_send_ping_wf(struct work_struct *ws);
+extern void drbd_send_acks_wf(struct work_struct *ws);
 extern bool drbd_rs_c_min_rate_throttle(struct drbd_device *device);
 extern bool drbd_rs_should_slow_down(struct drbd_device *device, sector_t sector,
 		bool throttle_if_app_is_waiting);
@@ -1649,7 +1667,7 @@ extern int __drbd_change_sync(struct drbd_device *device, sector_t sector, int s
 #define drbd_rs_failed_io(device, sector, size) \
 	__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 *);
+extern int drbd_al_initialize(struct drbd_device *, void *);
 
 /* drbd_nl.c */
 /* state info broadcast */
@@ -1668,6 +1686,29 @@ struct sib_info {
 };
 void drbd_bcast_event(struct drbd_device *device, const struct sib_info *sib);
 
+extern void notify_resource_state(struct sk_buff *,
+				  unsigned int,
+				  struct drbd_resource *,
+				  struct resource_info *,
+				  enum drbd_notification_type);
+extern void notify_device_state(struct sk_buff *,
+				unsigned int,
+				struct drbd_device *,
+				struct device_info *,
+				enum drbd_notification_type);
+extern void notify_connection_state(struct sk_buff *,
+				    unsigned int,
+				    struct drbd_connection *,
+				    struct connection_info *,
+				    enum drbd_notification_type);
+extern void notify_peer_device_state(struct sk_buff *,
+				     unsigned int,
+				     struct drbd_peer_device *,
+				     struct peer_device_info *,
+				     enum drbd_notification_type);
+extern void notify_helper(enum drbd_notification_type, struct drbd_device *,
+			  struct drbd_connection *, const char *, int);
+
 /*
  * inline helper functions
  *************************/
@@ -1694,19 +1735,6 @@ static inline int drbd_peer_req_has_active_page(struct drbd_peer_request *peer_r
 	return 0;
 }
 
-static inline enum drbd_state_rv
-_drbd_set_state(struct drbd_device *device, union drbd_state ns,
-		enum chg_state_flags flags, struct completion *done)
-{
-	enum drbd_state_rv rv;
-
-	read_lock(&global_state_lock);
-	rv = __drbd_set_state(device, ns, flags, done);
-	read_unlock(&global_state_lock);
-
-	return rv;
-}
-
 static inline union drbd_state drbd_read_state(struct drbd_device *device)
 {
 	struct drbd_resource *resource = device->resource;
@@ -1937,16 +1965,21 @@ drbd_device_post_work(struct drbd_device *device, int work_bit)
 
 extern void drbd_flush_workqueue(struct drbd_work_queue *work_queue);
 
-static inline void wake_asender(struct drbd_connection *connection)
+/* To get the ack_receiver out of the blocking network stack,
+ * so it can change its sk_rcvtimeo from idle- to ping-timeout,
+ * and send a ping, we need to send a signal.
+ * Which signal we send is irrelevant. */
+static inline void wake_ack_receiver(struct drbd_connection *connection)
 {
-	if (test_bit(SIGNAL_ASENDER, &connection->flags))
-		force_sig(DRBD_SIG, connection->asender.task);
+	struct task_struct *task = connection->ack_receiver.task;
+	if (task && get_t_state(&connection->ack_receiver) == RUNNING)
+		force_sig(SIGXCPU, task);
 }
 
 static inline void request_ping(struct drbd_connection *connection)
 {
 	set_bit(SEND_PING, &connection->flags);
-	wake_asender(connection);
+	wake_ack_receiver(connection);
 }
 
 extern void *conn_prepare_command(struct drbd_connection *, struct drbd_socket *);
@@ -2230,7 +2263,7 @@ static inline bool may_inc_ap_bio(struct drbd_device *device)
 
 	if (drbd_suspended(device))
 		return false;
-	if (test_bit(SUSPEND_IO, &device->flags))
+	if (atomic_read(&device->suspend_cnt))
 		return false;
 
 	/* to avoid potential deadlock or bitmap corruption,

drivers/block/drbd/drbd_main.c

@@ -117,6 +117,7 @@ module_param_string(usermode_helper, usermode_helper, sizeof(usermode_helper), 0
  */
 struct idr drbd_devices;
 struct list_head drbd_resources;
+struct mutex resources_mutex;
 
 struct kmem_cache *drbd_request_cache;
 struct kmem_cache *drbd_ee_cache;	/* peer requests */
@@ -1435,8 +1436,8 @@ static int we_should_drop_the_connection(struct drbd_connection *connection, str
 	/* long elapsed = (long)(jiffies - device->last_received); */
 
 	drop_it =   connection->meta.socket == sock
-		|| !connection->asender.task
-		|| get_t_state(&connection->asender) != RUNNING
+		|| !connection->ack_receiver.task
+		|| get_t_state(&connection->ack_receiver) != RUNNING
 		|| connection->cstate < C_WF_REPORT_PARAMS;
 
 	if (drop_it)
@@ -1793,15 +1794,6 @@ int drbd_send(struct drbd_connection *connection, struct socket *sock,
 		drbd_update_congested(connection);
 	}
 	do {
-		/* STRANGE
-		 * tcp_sendmsg does _not_ use its size parameter at all ?
-		 *
-		 * -EAGAIN on timeout, -EINTR on signal.
-		 */
-/* THINK
- * do we need to block DRBD_SIG if sock == &meta.socket ??
- * otherwise wake_asender() might interrupt some send_*Ack !
- */
 		rv = kernel_sendmsg(sock, &msg, &iov, 1, size);
 		if (rv == -EAGAIN) {
 			if (we_should_drop_the_connection(connection, sock))
@@ -2000,7 +1992,7 @@ void drbd_device_cleanup(struct drbd_device *device)
 		drbd_bm_cleanup(device);
 	}
 
-	drbd_free_ldev(device->ldev);
+	drbd_backing_dev_free(device, device->ldev);
 	device->ldev = NULL;
 
 	clear_bit(AL_SUSPENDED, &device->flags);
@@ -2179,7 +2171,7 @@ void drbd_destroy_device(struct kref *kref)
 	if (device->this_bdev)
 		bdput(device->this_bdev);
 
-	drbd_free_ldev(device->ldev);
+	drbd_backing_dev_free(device, device->ldev);
 	device->ldev = NULL;
 
 	drbd_release_all_peer_reqs(device);
@@ -2563,7 +2555,7 @@ int set_resource_options(struct drbd_resource *resource, struct res_opts *res_op
 		cpumask_copy(resource->cpu_mask, new_cpu_mask);
 		for_each_connection_rcu(connection, resource) {
 			connection->receiver.reset_cpu_mask = 1;
-			connection->asender.reset_cpu_mask = 1;
+			connection->ack_receiver.reset_cpu_mask = 1;
 			connection->worker.reset_cpu_mask = 1;
 		}
 	}
@@ -2590,7 +2582,7 @@ struct drbd_resource *drbd_create_resource(const char *name)
 	kref_init(&resource->kref);
 	idr_init(&resource->devices);
 	INIT_LIST_HEAD(&resource->connections);
-	resource->write_ordering = WO_bdev_flush;
+	resource->write_ordering = WO_BDEV_FLUSH;
 	list_add_tail_rcu(&resource->resources, &drbd_resources);
 	mutex_init(&resource->conf_update);
 	mutex_init(&resource->adm_mutex);
@@ -2652,8 +2644,8 @@ struct drbd_connection *conn_create(const char *name, struct res_opts *res_opts)
 	connection->receiver.connection = connection;
 	drbd_thread_init(resource, &connection->worker, drbd_worker, "worker");
 	connection->worker.connection = connection;
-	drbd_thread_init(resource, &connection->asender, drbd_asender, "asender");
-	connection->asender.connection = connection;
+	drbd_thread_init(resource, &connection->ack_receiver, drbd_ack_receiver, "ack_recv");
+	connection->ack_receiver.connection = connection;
 
 	kref_init(&connection->kref);
 
@@ -2702,8 +2694,8 @@ static int init_submitter(struct drbd_device *device)
 {
 	/* opencoded create_singlethread_workqueue(),
 	 * to be able to say "drbd%d", ..., minor */
-	device->submit.wq = alloc_workqueue("drbd%u_submit",
-			WQ_UNBOUND | WQ_MEM_RECLAIM, 1, device->minor);
+	device->submit.wq =
+		alloc_ordered_workqueue("drbd%u_submit", WQ_MEM_RECLAIM, device->minor);
 	if (!device->submit.wq)
 		return -ENOMEM;
 
@@ -2820,6 +2812,7 @@ enum drbd_ret_code drbd_create_device(struct drbd_config_context *adm_ctx, unsig
 			goto out_idr_remove_from_resource;
 		}
 		kref_get(&connection->kref);
+		INIT_WORK(&peer_device->send_acks_work, drbd_send_acks_wf);
 	}
 
 	if (init_submitter(device)) {
@@ -2923,7 +2916,7 @@ static int __init drbd_init(void)
 	drbd_proc = NULL; /* play safe for drbd_cleanup */
 	idr_init(&drbd_devices);
 
-	rwlock_init(&global_state_lock);
+	mutex_init(&resources_mutex);
 	INIT_LIST_HEAD(&drbd_resources);
 
 	err = drbd_genl_register();
@@ -2971,18 +2964,6 @@ static int __init drbd_init(void)
 	return err;
 }
 
-void drbd_free_ldev(struct drbd_backing_dev *ldev)
-{
-	if (ldev == NULL)
-		return;
-
-	blkdev_put(ldev->backing_bdev, FMODE_READ | FMODE_WRITE | FMODE_EXCL);
-	blkdev_put(ldev->md_bdev, FMODE_READ | FMODE_WRITE | FMODE_EXCL);
-
-	kfree(ldev->disk_conf);
-	kfree(ldev);
-}
-
 static void drbd_free_one_sock(struct drbd_socket *ds)
 {
 	struct socket *s;
@@ -3277,6 +3258,10 @@ int drbd_md_read(struct drbd_device *device, struct drbd_backing_dev *bdev)
 	 * and read it. */
 	bdev->md.meta_dev_idx = bdev->disk_conf->meta_dev_idx;
 	bdev->md.md_offset = drbd_md_ss(bdev);
+	/* Even for (flexible or indexed) external meta data,
+	 * initially restrict us to the 4k superblock for now.
+	 * Affects the paranoia out-of-range access check in drbd_md_sync_page_io(). */
+	bdev->md.md_size_sect = 8;
 
 	if (drbd_md_sync_page_io(device, bdev, bdev->md.md_offset, READ)) {
 		/* NOTE: can't do normal error processing here as this is
@@ -3578,7 +3563,9 @@ void drbd_queue_bitmap_io(struct drbd_device *device,
 
 	spin_lock_irq(&device->resource->req_lock);
 	set_bit(BITMAP_IO, &device->flags);
-	if (atomic_read(&device->ap_bio_cnt) == 0) {
+	/* don't wait for pending application IO if the caller indicates that
+	 * application IO does not conflict anyways. */
+	if (flags == BM_LOCKED_CHANGE_ALLOWED || atomic_read(&device->ap_bio_cnt) == 0) {
 		if (!test_and_set_bit(BITMAP_IO_QUEUED, &device->flags))
 			drbd_queue_work(&first_peer_device(device)->connection->sender_work,
 					&device->bm_io_work.w);
@@ -3746,6 +3733,27 @@ int drbd_wait_misc(struct drbd_device *device, struct drbd_interval *i)
 	return 0;
 }
 
+void lock_all_resources(void)
+{
+	struct drbd_resource *resource;
+	int __maybe_unused i = 0;
+
+	mutex_lock(&resources_mutex);
+	local_irq_disable();
+	for_each_resource(resource, &drbd_resources)
+		spin_lock_nested(&resource->req_lock, i++);
+}
+
+void unlock_all_resources(void)
+{
+	struct drbd_resource *resource;
+
+	for_each_resource(resource, &drbd_resources)
+		spin_unlock(&resource->req_lock);
+	local_irq_enable();
+	mutex_unlock(&resources_mutex);
+}
+
 #ifdef CONFIG_DRBD_FAULT_INJECTION
 /* Fault insertion support including random number generator shamelessly
  * stolen from kernel/rcutorture.c */

drivers/block/drbd/drbd_proc.c

@@ -245,9 +245,9 @@ static int drbd_seq_show(struct seq_file *seq, void *v)
 	char wp;
 
 	static char write_ordering_chars[] = {
-		[WO_none] = 'n',
-		[WO_drain_io] = 'd',
-		[WO_bdev_flush] = 'f',
+		[WO_NONE] = 'n',
+		[WO_DRAIN_IO] = 'd',
+		[WO_BDEV_FLUSH] = 'f',
 	};
 
 	seq_printf(seq, "version: " REL_VERSION " (api:%d/proto:%d-%d)\n%s\n",

drivers/block/drbd/drbd_protocol.h

@@ -23,7 +23,7 @@ enum drbd_packet {
 	P_AUTH_RESPONSE	      = 0x11,
 	P_STATE_CHG_REQ	      = 0x12,
 
-	/* asender (meta socket */
+	/* (meta socket) */
 	P_PING		      = 0x13,
 	P_PING_ACK	      = 0x14,
 	P_RECV_ACK	      = 0x15, /* Used in protocol B */

drivers/block/drbd/drbd_req.c

@@ -453,12 +453,12 @@ static void mod_rq_state(struct drbd_request *req, struct bio_and_error *m,
 		kref_get(&req->kref); /* wait for the DONE */
 
 	if (!(s & RQ_NET_SENT) && (set & RQ_NET_SENT)) {
-		/* potentially already completed in the asender thread */
+		/* potentially already completed in the ack_receiver thread */
 		if (!(s & RQ_NET_DONE)) {
 			atomic_add(req->i.size >> 9, &device->ap_in_flight);
 			set_if_null_req_not_net_done(peer_device, req);
 		}
-		if (s & RQ_NET_PENDING)
+		if (req->rq_state & RQ_NET_PENDING)
 			set_if_null_req_ack_pending(peer_device, req);
 	}
 
@@ -1095,6 +1095,24 @@ static bool do_remote_read(struct drbd_request *req)
 	return false;
 }
 
+bool drbd_should_do_remote(union drbd_dev_state s)
+{
+	return s.pdsk == D_UP_TO_DATE ||
+		(s.pdsk >= D_INCONSISTENT &&
+		 s.conn >= C_WF_BITMAP_T &&
+		 s.conn < C_AHEAD);
+	/* Before proto 96 that was >= CONNECTED instead of >= C_WF_BITMAP_T.
+	   That is equivalent since before 96 IO was frozen in the C_WF_BITMAP*
+	   states. */
+}
+
+static bool drbd_should_send_out_of_sync(union drbd_dev_state s)
+{
+	return s.conn == C_AHEAD || s.conn == C_WF_BITMAP_S;
+	/* pdsk = D_INCONSISTENT as a consequence. Protocol 96 check not necessary
+	   since we enter state C_AHEAD only if proto >= 96 */
+}
+
 /* returns number of connections (== 1, for drbd 8.4)
  * expected to actually write this data,
  * which does NOT include those that we are L_AHEAD for. */
@@ -1149,7 +1167,6 @@ drbd_submit_req_private_bio(struct drbd_request *req)
 	 * stable storage, and this is a WRITE, we may not even submit
 	 * this bio. */
 	if (get_ldev(device)) {
-		req->pre_submit_jif = jiffies;
 		if (drbd_insert_fault(device,
 				      rw == WRITE ? DRBD_FAULT_DT_WR
 				    : rw == READ  ? DRBD_FAULT_DT_RD
@@ -1293,6 +1310,7 @@ static void drbd_send_and_submit(struct drbd_device *device, struct drbd_request
 			&device->pending_master_completion[rw == WRITE]);
 	if (req->private_bio) {
 		/* needs to be marked within the same spinlock */
+		req->pre_submit_jif = jiffies;
 		list_add_tail(&req->req_pending_local,
 			&device->pending_completion[rw == WRITE]);
 		_req_mod(req, TO_BE_SUBMITTED);
@@ -1513,6 +1531,78 @@ blk_qc_t drbd_make_request(struct request_queue *q, struct bio *bio)
 	return BLK_QC_T_NONE;
 }
 
+static bool net_timeout_reached(struct drbd_request *net_req,
+		struct drbd_connection *connection,
+		unsigned long now, unsigned long ent,
+		unsigned int ko_count, unsigned int timeout)
+{
+	struct drbd_device *device = net_req->device;
+
+	if (!time_after(now, net_req->pre_send_jif + ent))
+		return false;
+
+	if (time_in_range(now, connection->last_reconnect_jif, connection->last_reconnect_jif + ent))
+		return false;
+
+	if (net_req->rq_state & RQ_NET_PENDING) {
+		drbd_warn(device, "Remote failed to finish a request within %ums > ko-count (%u) * timeout (%u * 0.1s)\n",
+			jiffies_to_msecs(now - net_req->pre_send_jif), ko_count, timeout);
+		return true;
+	}
+
+	/* We received an ACK already (or are using protocol A),
+	 * but are waiting for the epoch closing barrier ack.
+	 * Check if we sent the barrier already.  We should not blame the peer
+	 * for being unresponsive, if we did not even ask it yet. */
+	if (net_req->epoch == connection->send.current_epoch_nr) {
+		drbd_warn(device,
+			"We did not send a P_BARRIER for %ums > ko-count (%u) * timeout (%u * 0.1s); drbd kernel thread blocked?\n",
+			jiffies_to_msecs(now - net_req->pre_send_jif), ko_count, timeout);
+		return false;
+	}
+
+	/* Worst case: we may have been blocked for whatever reason, then
+	 * suddenly are able to send a lot of requests (and epoch separating
+	 * barriers) in quick succession.
+	 * The timestamp of the net_req may be much too old and not correspond
+	 * to the sending time of the relevant unack'ed barrier packet, so
+	 * would trigger a spurious timeout.  The latest barrier packet may
+	 * have a too recent timestamp to trigger the timeout, potentially miss
+	 * a timeout.  Right now we don't have a place to conveniently store
+	 * these timestamps.
+	 * But in this particular situation, the application requests are still
+	 * completed to upper layers, DRBD should still "feel" responsive.
+	 * No need yet to kill this connection, it may still recover.
+	 * If not, eventually we will have queued enough into the network for
+	 * us to block. From that point of view, the timestamp of the last sent
+	 * barrier packet is relevant enough.
+	 */
+	if (time_after(now, connection->send.last_sent_barrier_jif + ent)) {
+		drbd_warn(device, "Remote failed to answer a P_BARRIER (sent at %lu jif; now=%lu jif) within %ums > ko-count (%u) * timeout (%u * 0.1s)\n",
+			connection->send.last_sent_barrier_jif, now,
+			jiffies_to_msecs(now - connection->send.last_sent_barrier_jif), ko_count, timeout);
+		return true;
+	}
+	return false;
+}
+
+/* A request is considered timed out, if
+ * - we have some effective timeout from the configuration,
+ *   with some state restrictions applied,
+ * - the oldest request is waiting for a response from the network
+ *   resp. the local disk,
+ * - the oldest request is in fact older than the effective timeout,
+ * - the connection was established (resp. disk was attached)
+ *   for longer than the timeout already.
+ * Note that for 32bit jiffies and very stable connections/disks,
+ * we may have a wrap around, which is catched by
+ *   !time_in_range(now, last_..._jif, last_..._jif + timeout).
+ *
+ * Side effect: once per 32bit wrap-around interval, which means every
+ * ~198 days with 250 HZ, we have a window where the timeout would need
+ * to expire twice (worst case) to become effective. Good enough.
+ */
+
 void request_timer_fn(unsigned long data)
 {
 	struct drbd_device *device = (struct drbd_device *) data;
@@ -1522,11 +1612,14 @@ void request_timer_fn(unsigned long data)
 	unsigned long oldest_submit_jif;
 	unsigned long ent = 0, dt = 0, et, nt; /* effective timeout = ko_count * timeout */
 	unsigned long now;
+	unsigned int ko_count = 0, timeout = 0;
 
 	rcu_read_lock();
 	nc = rcu_dereference(connection->net_conf);
-	if (nc && device->state.conn >= C_WF_REPORT_PARAMS)
-		ent = nc->timeout * HZ/10 * nc->ko_count;
+	if (nc && device->state.conn >= C_WF_REPORT_PARAMS) {
+		ko_count = nc->ko_count;
+		timeout = nc->timeout;
+	}
 
 	if (get_ldev(device)) { /* implicit state.disk >= D_INCONSISTENT */
 		dt = rcu_dereference(device->ldev->disk_conf)->disk_timeout * HZ / 10;
@@ -1534,6 +1627,8 @@ void request_timer_fn(unsigned long data)
 	}
 	rcu_read_unlock();
 
+
+	ent = timeout * HZ/10 * ko_count;
 	et = min_not_zero(dt, ent);
 
 	if (!et)
@@ -1545,11 +1640,22 @@ void request_timer_fn(unsigned long data)
 	spin_lock_irq(&device->resource->req_lock);
 	req_read = list_first_entry_or_null(&device->pending_completion[0], struct drbd_request, req_pending_local);
 	req_write = list_first_entry_or_null(&device->pending_completion[1], struct drbd_request, req_pending_local);
-	req_peer = connection->req_not_net_done;
+
 	/* maybe the oldest request waiting for the peer is in fact still
-	 * blocking in tcp sendmsg */
-	if (!req_peer && connection->req_next && connection->req_next->pre_send_jif)
-		req_peer = connection->req_next;
+	 * blocking in tcp sendmsg.  That's ok, though, that's handled via the
+	 * socket send timeout, requesting a ping, and bumping ko-count in
+	 * we_should_drop_the_connection().
+	 */
+
+	/* check the oldest request we did successfully sent,
+	 * but which is still waiting for an ACK. */
+	req_peer = connection->req_ack_pending;
+
+	/* if we don't have such request (e.g. protocoll A)
+	 * check the oldest requests which is still waiting on its epoch
+	 * closing barrier ack. */
+	if (!req_peer)
+		req_peer = connection->req_not_net_done;
 
 	/* evaluate the oldest peer request only in one timer! */
 	if (req_peer && req_peer->device != device)
@@ -1566,28 +1672,9 @@ void request_timer_fn(unsigned long data)
 		: req_write ? req_write->pre_submit_jif
 		: req_read ? req_read->pre_submit_jif : now;
 
-	/* The request is considered timed out, if
-	 * - we have some effective timeout from the configuration,
-	 *   with above state restrictions applied,
-	 * - the oldest request is waiting for a response from the network
-	 *   resp. the local disk,
-	 * - the oldest request is in fact older than the effective timeout,
-	 * - the connection was established (resp. disk was attached)
-	 *   for longer than the timeout already.
-	 * Note that for 32bit jiffies and very stable connections/disks,
-	 * we may have a wrap around, which is catched by
-	 *   !time_in_range(now, last_..._jif, last_..._jif + timeout).
-	 *
-	 * Side effect: once per 32bit wrap-around interval, which means every
-	 * ~198 days with 250 HZ, we have a window where the timeout would need
-	 * to expire twice (worst case) to become effective. Good enough.
-	 */
-	if (ent && req_peer &&
-		 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");
+	if (ent && req_peer && net_timeout_reached(req_peer, connection, now, ent, ko_count, timeout))
 		_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) &&
 		!time_in_range(now, device->last_reattach_jif, device->last_reattach_jif + dt)) {

drivers/block/drbd/drbd_req.h

@@ -331,21 +331,6 @@ static inline int req_mod(struct drbd_request *req,
 	return rv;
 }
 
-static inline bool drbd_should_do_remote(union drbd_dev_state s)
-{
-	return s.pdsk == D_UP_TO_DATE ||
-		(s.pdsk >= D_INCONSISTENT &&
-		 s.conn >= C_WF_BITMAP_T &&
-		 s.conn < C_AHEAD);
-	/* Before proto 96 that was >= CONNECTED instead of >= C_WF_BITMAP_T.
-	   That is equivalent since before 96 IO was frozen in the C_WF_BITMAP*
-	   states. */
-}
-static inline bool drbd_should_send_out_of_sync(union drbd_dev_state s)
-{
-	return s.conn == C_AHEAD || s.conn == C_WF_BITMAP_S;
-	/* pdsk = D_INCONSISTENT as a consequence. Protocol 96 check not necessary
-	   since we enter state C_AHEAD only if proto >= 96 */
-}
+extern bool drbd_should_do_remote(union drbd_dev_state);
 
 #endif

drivers/block/drbd/drbd_state.h

@@ -122,9 +122,9 @@ 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);
+extern enum drbd_state_rv _drbd_set_state(struct drbd_device *, union drbd_state,
+					  enum chg_state_flags,
+					  struct completion *done);
 extern void print_st_err(struct drbd_device *, union drbd_state,
 			union drbd_state, int);
 

drivers/block/drbd/drbd_state_change.h

+#ifndef DRBD_STATE_CHANGE_H
+#define DRBD_STATE_CHANGE_H
+
+struct drbd_resource_state_change {
+	struct drbd_resource *resource;
+	enum drbd_role role[2];
+	bool susp[2];
+	bool susp_nod[2];
+	bool susp_fen[2];
+};
+
+struct drbd_device_state_change {
+	struct drbd_device *device;
+	enum drbd_disk_state disk_state[2];
+};
+
+struct drbd_connection_state_change {
+	struct drbd_connection *connection;
+	enum drbd_conns cstate[2];  /* drbd9: enum drbd_conn_state */
+	enum drbd_role peer_role[2];
+};
+
+struct drbd_peer_device_state_change {
+	struct drbd_peer_device *peer_device;
+	enum drbd_disk_state disk_state[2];
+	enum drbd_conns repl_state[2];  /* drbd9: enum drbd_repl_state */
+	bool resync_susp_user[2];
+	bool resync_susp_peer[2];
+	bool resync_susp_dependency[2];
+};
+
+struct drbd_state_change {
+	struct list_head list;
+	unsigned int n_devices;
+	unsigned int n_connections;
+	struct drbd_resource_state_change resource[1];
+	struct drbd_device_state_change *devices;
+	struct drbd_connection_state_change *connections;
+	struct drbd_peer_device_state_change *peer_devices;
+};
+
+extern struct drbd_state_change *remember_old_state(struct drbd_resource *, gfp_t);
+extern void copy_old_to_new_state_change(struct drbd_state_change *);
+extern void forget_state_change(struct drbd_state_change *);
+
+extern void notify_resource_state_change(struct sk_buff *,
+					 unsigned int,
+					 struct drbd_resource_state_change *,
+					 enum drbd_notification_type type);
+extern void notify_connection_state_change(struct sk_buff *,
+					   unsigned int,
+					   struct drbd_connection_state_change *,
+					   enum drbd_notification_type type);
+extern void notify_device_state_change(struct sk_buff *,
+				       unsigned int,
+				       struct drbd_device_state_change *,
+				       enum drbd_notification_type type);
+extern void notify_peer_device_state_change(struct sk_buff *,
+					    unsigned int,
+					    struct drbd_peer_device_state_change *,
+					    enum drbd_notification_type type);
+
+#endif  /* DRBD_STATE_CHANGE_H */

drivers/block/drbd/drbd_worker.c

@@ -55,13 +55,6 @@ static int make_resync_request(struct drbd_device *, int);
  *
  */
 
-
-/* About the global_state_lock
-   Each state transition on an device holds a read lock. In case we have
-   to evaluate the resync after dependencies, we grab a write lock, because
-   we need stable states on all devices for that.  */
-rwlock_t global_state_lock;
-
 /* used for synchronous meta data and bitmap IO
  * submitted by drbd_md_sync_page_io()
  */
@@ -120,6 +113,7 @@ void drbd_endio_write_sec_final(struct drbd_peer_request *peer_req) __releases(l
 	unsigned long flags = 0;
 	struct drbd_peer_device *peer_device = peer_req->peer_device;
 	struct drbd_device *device = peer_device->device;
+	struct drbd_connection *connection = peer_device->connection;
 	struct drbd_interval i;
 	int do_wake;
 	u64 block_id;
@@ -152,6 +146,12 @@ void drbd_endio_write_sec_final(struct drbd_peer_request *peer_req) __releases(l
 	 * ((peer_req->flags & (EE_WAS_ERROR|EE_IS_TRIM)) == EE_WAS_ERROR) */
 	if (peer_req->flags & EE_WAS_ERROR)
 		__drbd_chk_io_error(device, DRBD_WRITE_ERROR);
+
+	if (connection->cstate >= C_WF_REPORT_PARAMS) {
+		kref_get(&device->kref); /* put is in drbd_send_acks_wf() */
+		if (!queue_work(connection->ack_sender, &peer_device->send_acks_work))
+			kref_put(&device->kref, drbd_destroy_device);
+	}
 	spin_unlock_irqrestore(&device->resource->req_lock, flags);
 
 	if (block_id == ID_SYNCER)
@@ -163,7 +163,6 @@ void drbd_endio_write_sec_final(struct drbd_peer_request *peer_req) __releases(l
 	if (do_al_complete_io)
 		drbd_al_complete_io(device, &i);
 
-	wake_asender(peer_device->connection);
 	put_ldev(device);
 }
 
@@ -195,6 +194,12 @@ void drbd_peer_request_endio(struct bio *bio)
 	}
 }
 
+void drbd_panic_after_delayed_completion_of_aborted_request(struct drbd_device *device)
+{
+	panic("drbd%u %s/%u potential random memory corruption caused by delayed completion of aborted local request\n",
+		device->minor, device->resource->name, device->vnr);
+}
+
 /* read, readA or write requests on R_PRIMARY coming from drbd_make_request
  */
 void drbd_request_endio(struct bio *bio)
@@ -238,7 +243,7 @@ void drbd_request_endio(struct bio *bio)
 			drbd_emerg(device, "delayed completion of aborted local request; disk-timeout may be too aggressive\n");
 
 		if (!bio->bi_error)
-			panic("possible random memory corruption caused by delayed completion of aborted local request\n");
+			drbd_panic_after_delayed_completion_of_aborted_request(device);
 	}
 
 	/* to avoid recursion in __req_mod */
@@ -1291,6 +1296,7 @@ static int drbd_send_barrier(struct drbd_connection *connection)
 	p->barrier = connection->send.current_epoch_nr;
 	p->pad = 0;
 	connection->send.current_epoch_writes = 0;
+	connection->send.last_sent_barrier_jif = jiffies;
 
 	return conn_send_command(connection, sock, P_BARRIER, sizeof(*p), NULL, 0);
 }
@@ -1315,6 +1321,7 @@ static void re_init_if_first_write(struct drbd_connection *connection, unsigned
 		connection->send.seen_any_write_yet = true;
 		connection->send.current_epoch_nr = epoch;
 		connection->send.current_epoch_writes = 0;
+		connection->send.last_sent_barrier_jif = jiffies;
 	}
 }
 
@@ -1456,70 +1463,73 @@ static int _drbd_may_sync_now(struct drbd_device *device)
 }
 
 /**
- * _drbd_pause_after() - Pause resync on all devices that may not resync now
+ * drbd_pause_after() - Pause resync on all devices that may not resync now
  * @device:	DRBD device.
  *
  * Called from process context only (admin command and after_state_ch).
  */
-static int _drbd_pause_after(struct drbd_device *device)
+static bool drbd_pause_after(struct drbd_device *device)
 {
+	bool changed = false;
 	struct drbd_device *odev;
-	int i, rv = 0;
+	int i;
 
 	rcu_read_lock();
 	idr_for_each_entry(&drbd_devices, odev, i) {
 		if (odev->state.conn == C_STANDALONE && odev->state.disk == D_DISKLESS)
 			continue;
-		if (!_drbd_may_sync_now(odev))
-			rv |= (__drbd_set_state(_NS(odev, aftr_isp, 1), CS_HARD, NULL)
-			       != SS_NOTHING_TO_DO);
+		if (!_drbd_may_sync_now(odev) &&
+		    _drbd_set_state(_NS(odev, aftr_isp, 1),
+				    CS_HARD, NULL) != SS_NOTHING_TO_DO)
+			changed = true;
 	}
 	rcu_read_unlock();
 
-	return rv;
+	return changed;
 }
 
 /**
- * _drbd_resume_next() - Resume resync on all devices that may resync now
+ * drbd_resume_next() - Resume resync on all devices that may resync now
  * @device:	DRBD device.
  *
  * Called from process context only (admin command and worker).
  */
-static int _drbd_resume_next(struct drbd_device *device)
+static bool drbd_resume_next(struct drbd_device *device)
 {
+	bool changed = false;
 	struct drbd_device *odev;
-	int i, rv = 0;
+	int i;
 
 	rcu_read_lock();
 	idr_for_each_entry(&drbd_devices, odev, i) {
 		if (odev->state.conn == C_STANDALONE && odev->state.disk == D_DISKLESS)
 			continue;
 		if (odev->state.aftr_isp) {
-			if (_drbd_may_sync_now(odev))
-				rv |= (__drbd_set_state(_NS(odev, aftr_isp, 0),
-							CS_HARD, NULL)
-				       != SS_NOTHING_TO_DO) ;
+			if (_drbd_may_sync_now(odev) &&
+			    _drbd_set_state(_NS(odev, aftr_isp, 0),
+					    CS_HARD, NULL) != SS_NOTHING_TO_DO)
+				changed = true;
 		}
 	}
 	rcu_read_unlock();
-	return rv;
+	return changed;
 }
 
 void resume_next_sg(struct drbd_device *device)
 {
-	write_lock_irq(&global_state_lock);
-	_drbd_resume_next(device);
-	write_unlock_irq(&global_state_lock);
+	lock_all_resources();
+	drbd_resume_next(device);
+	unlock_all_resources();
 }
 
 void suspend_other_sg(struct drbd_device *device)
 {
-	write_lock_irq(&global_state_lock);
-	_drbd_pause_after(device);
-	write_unlock_irq(&global_state_lock);
+	lock_all_resources();
+	drbd_pause_after(device);
+	unlock_all_resources();
 }
 
-/* caller must hold global_state_lock */
+/* caller must lock_all_resources() */
 enum drbd_ret_code drbd_resync_after_valid(struct drbd_device *device, int o_minor)
 {
 	struct drbd_device *odev;
@@ -1557,15 +1567,15 @@ enum drbd_ret_code drbd_resync_after_valid(struct drbd_device *device, int o_min
 	}
 }
 
-/* caller must hold global_state_lock */
+/* caller must lock_all_resources() */
 void drbd_resync_after_changed(struct drbd_device *device)
 {
-	int changes;
+	int changed;
 
 	do {
-		changes  = _drbd_pause_after(device);
-		changes |= _drbd_resume_next(device);
-	} while (changes);
+		changed  = drbd_pause_after(device);
+		changed |= drbd_resume_next(device);
+	} while (changed);
 }
 
 void drbd_rs_controller_reset(struct drbd_device *device)
@@ -1685,19 +1695,14 @@ void drbd_start_resync(struct drbd_device *device, enum drbd_conns side)
 	} else {
 		mutex_lock(device->state_mutex);
 	}
-	clear_bit(B_RS_H_DONE, &device->flags);
 
-	/* req_lock: serialize with drbd_send_and_submit() and others
-	 * global_state_lock: for stable sync-after dependencies */
-	spin_lock_irq(&device->resource->req_lock);
-	write_lock(&global_state_lock);
+	lock_all_resources();
+	clear_bit(B_RS_H_DONE, &device->flags);
 	/* Did some connection breakage or IO error race with us? */
 	if (device->state.conn < C_CONNECTED
 	|| !get_ldev_if_state(device, D_NEGOTIATING)) {
-		write_unlock(&global_state_lock);
-		spin_unlock_irq(&device->resource->req_lock);
-		mutex_unlock(device->state_mutex);
-		return;
+		unlock_all_resources();
+		goto out;
 	}
 
 	ns = drbd_read_state(device);
@@ -1711,7 +1716,7 @@ void drbd_start_resync(struct drbd_device *device, enum drbd_conns side)
 	else /* side == C_SYNC_SOURCE */
 		ns.pdsk = D_INCONSISTENT;
 
-	r = __drbd_set_state(device, ns, CS_VERBOSE, NULL);
+	r = _drbd_set_state(device, ns, CS_VERBOSE, NULL);
 	ns = drbd_read_state(device);
 
 	if (ns.conn < C_CONNECTED)
@@ -1732,7 +1737,7 @@ void drbd_start_resync(struct drbd_device *device, enum drbd_conns side)
 			device->rs_mark_left[i] = tw;
 			device->rs_mark_time[i] = now;
 		}
-		_drbd_pause_after(device);
+		drbd_pause_after(device);
 		/* Forget potentially stale cached per resync extent bit-counts.
 		 * Open coded drbd_rs_cancel_all(device), we already have IRQs
 		 * disabled, and know the disk state is ok. */
@@ -1742,8 +1747,7 @@ void drbd_start_resync(struct drbd_device *device, enum drbd_conns side)
 		device->resync_wenr = LC_FREE;
 		spin_unlock(&device->al_lock);
 	}
-	write_unlock(&global_state_lock);
-	spin_unlock_irq(&device->resource->req_lock);
+	unlock_all_resources();
 
 	if (r == SS_SUCCESS) {
 		wake_up(&device->al_wait); /* for lc_reset() above */
@@ -1807,6 +1811,7 @@ void drbd_start_resync(struct drbd_device *device, enum drbd_conns side)
 		drbd_md_sync(device);
 	}
 	put_ldev(device);
+out:
 	mutex_unlock(device->state_mutex);
 }
 
@@ -1836,7 +1841,7 @@ static void drbd_ldev_destroy(struct drbd_device *device)
 	device->act_log = NULL;
 
 	__acquire(local);
-	drbd_free_ldev(device->ldev);
+	drbd_backing_dev_free(device, device->ldev);
 	device->ldev = NULL;
 	__release(local);
 

drivers/block/mtip32xx/mtip32xx.c

@@ -104,9 +104,9 @@
 /* Device instance number, incremented each time a device is probed. */
 static int instance;
 
-struct list_head online_list;
-struct list_head removing_list;
-spinlock_t dev_lock;
+static struct list_head online_list;
+static struct list_head removing_list;
+static spinlock_t dev_lock;
 
 /*
  * Global variable used to hold the major block device number

drivers/block/null_blk.c

@@ -495,17 +495,17 @@ static int null_lnvm_id(struct nvm_dev *dev, struct nvm_id *id)
 	id->ppaf.ch_offset = 56;
 	id->ppaf.ch_len = 8;
 
-	do_div(size, bs); /* convert size to pages */
-	do_div(size, 256); /* concert size to pgs pr blk */
+	sector_div(size, bs); /* convert size to pages */
+	size >>= 8; /* concert size to pgs pr blk */
 	grp = &id->groups[0];
 	grp->mtype = 0;
 	grp->fmtype = 0;
 	grp->num_ch = 1;
 	grp->num_pg = 256;
 	blksize = size;
-	do_div(size, (1 << 16));
+	size >>= 16;
 	grp->num_lun = size + 1;
-	do_div(blksize, grp->num_lun);
+	sector_div(blksize, grp->num_lun);
 	grp->num_blk = blksize;
 	grp->num_pln = 1;
 

drivers/block/sx8.c

@@ -23,7 +23,7 @@
 #include <linux/workqueue.h>
 #include <linux/bitops.h>
 #include <linux/delay.h>
-#include <linux/time.h>
+#include <linux/ktime.h>
 #include <linux/hdreg.h>
 #include <linux/dma-mapping.h>
 #include <linux/completion.h>
@@ -671,16 +671,15 @@ static int carm_send_special (struct carm_host *host, carm_sspc_t func)
 static unsigned int carm_fill_sync_time(struct carm_host *host,
 					unsigned int idx, void *mem)
 {
-	struct timeval tv;
 	struct carm_msg_sync_time *st = mem;
 
-	do_gettimeofday(&tv);
+	time64_t tv = ktime_get_real_seconds();
 
 	memset(st, 0, sizeof(*st));
 	st->type	= CARM_MSG_MISC;
 	st->subtype	= MISC_SET_TIME;
 	st->handle	= cpu_to_le32(TAG_ENCODE(idx));
-	st->timestamp	= cpu_to_le32(tv.tv_sec);
+	st->timestamp	= cpu_to_le32(tv);
 
 	return sizeof(struct carm_msg_sync_time);
 }

drivers/block/xen-blkback/common.h

@@ -46,6 +46,7 @@
 #include <xen/interface/io/protocols.h>
 
 extern unsigned int xen_blkif_max_ring_order;
+extern unsigned int xenblk_max_queues;
 /*
  * This is the maximum number of segments that would be allowed in indirect
  * requests. This value will also be passed to the frontend.
@@ -269,68 +270,79 @@ struct persistent_gnt {
 	struct list_head remove_node;
 };
 
-struct xen_blkif {
-	/* Unique identifier for this interface. */
-	domid_t			domid;
-	unsigned int		handle;
+/* Per-ring information. */
+struct xen_blkif_ring {
 	/* Physical parameters of the comms window. */
 	unsigned int		irq;
-	/* Comms information. */
-	enum blkif_protocol	blk_protocol;
 	union blkif_back_rings	blk_rings;
 	void			*blk_ring;
-	/* The VBD attached to this interface. */
-	struct xen_vbd		vbd;
-	/* Back pointer to the backend_info. */
-	struct backend_info	*be;
 	/* Private fields. */
 	spinlock_t		blk_ring_lock;
-	atomic_t		refcnt;
 
 	wait_queue_head_t	wq;
-	/* for barrier (drain) requests */
-	struct completion	drain_complete;
-	atomic_t		drain;
 	atomic_t		inflight;
-	/* One thread per one blkif. */
+	/* One thread per blkif ring. */
 	struct task_struct	*xenblkd;
 	unsigned int		waiting_reqs;
 
-	/* tree to store persistent grants */
+	/* List of all 'pending_req' available */
+	struct list_head	pending_free;
+	/* And its spinlock. */
+	spinlock_t		pending_free_lock;
+	wait_queue_head_t	pending_free_wq;
+
+	/* Tree to store persistent grants. */
+	spinlock_t		pers_gnts_lock;
 	struct rb_root		persistent_gnts;
 	unsigned int		persistent_gnt_c;
 	atomic_t		persistent_gnt_in_use;
 	unsigned long           next_lru;
 
-	/* used by the kworker that offload work from the persistent purge */
+	/* Statistics. */
+	unsigned long		st_print;
+	unsigned long long	st_rd_req;
+	unsigned long long	st_wr_req;
+	unsigned long long	st_oo_req;
+	unsigned long long	st_f_req;
+	unsigned long long	st_ds_req;
+	unsigned long long	st_rd_sect;
+	unsigned long long	st_wr_sect;
+
+	/* Used by the kworker that offload work from the persistent purge. */
 	struct list_head	persistent_purge_list;
 	struct work_struct	persistent_purge_work;
 
-	/* buffer of free pages to map grant refs */
+	/* Buffer of free pages to map grant refs. */
 	spinlock_t		free_pages_lock;
 	int			free_pages_num;
 	struct list_head	free_pages;
 
-	/* List of all 'pending_req' available */
-	struct list_head	pending_free;
-	/* And its spinlock. */
-	spinlock_t		pending_free_lock;
-	wait_queue_head_t	pending_free_wq;
-
-	/* statistics */
-	unsigned long		st_print;
-	unsigned long long			st_rd_req;
-	unsigned long long			st_wr_req;
-	unsigned long long			st_oo_req;
-	unsigned long long			st_f_req;
-	unsigned long long			st_ds_req;
-	unsigned long long			st_rd_sect;
-	unsigned long long			st_wr_sect;
-
 	struct work_struct	free_work;
 	/* Thread shutdown wait queue. */
 	wait_queue_head_t	shutdown_wq;
-	unsigned int nr_ring_pages;
+	struct xen_blkif 	*blkif;
+};
+
+struct xen_blkif {
+	/* Unique identifier for this interface. */
+	domid_t			domid;
+	unsigned int		handle;
+	/* Comms information. */
+	enum blkif_protocol	blk_protocol;
+	/* The VBD attached to this interface. */
+	struct xen_vbd		vbd;
+	/* Back pointer to the backend_info. */
+	struct backend_info	*be;
+	atomic_t		refcnt;
+	/* for barrier (drain) requests */
+	struct completion	drain_complete;
+	atomic_t		drain;
+
+	struct work_struct	free_work;
+	unsigned int 		nr_ring_pages;
+	/* All rings for this device. */
+	struct xen_blkif_ring	*rings;
+	unsigned int		nr_rings;
 };
 
 struct seg_buf {
@@ -352,7 +364,7 @@ struct grant_page {
  * response queued for it, with the saved 'id' passed back.
  */
 struct pending_req {
-	struct xen_blkif	*blkif;
+	struct xen_blkif_ring   *ring;
 	u64			id;
 	int			nr_segs;
 	atomic_t		pendcnt;
@@ -394,7 +406,7 @@ int xen_blkif_xenbus_init(void);
 irqreturn_t xen_blkif_be_int(int irq, void *dev_id);
 int xen_blkif_schedule(void *arg);
 int xen_blkif_purge_persistent(void *arg);
-void xen_blkbk_free_caches(struct xen_blkif *blkif);
+void xen_blkbk_free_caches(struct xen_blkif_ring *ring);
 
 int xen_blkbk_flush_diskcache(struct xenbus_transaction xbt,
 			      struct backend_info *be, int state);

drivers/md/bcache/btree.c

@@ -1741,6 +1741,7 @@ static void bch_btree_gc(struct cache_set *c)
 	do {
 		ret = btree_root(gc_root, c, &op, &writes, &stats);
 		closure_sync(&writes);
+		cond_resched();
 
 		if (ret && ret != -EAGAIN)
 			pr_warn("gc failed!");
@@ -2162,8 +2163,10 @@ int bch_btree_insert_check_key(struct btree *b, struct btree_op *op,
 		rw_lock(true, b, b->level);
 
 		if (b->key.ptr[0] != btree_ptr ||
-		    b->seq != seq + 1)
+                   b->seq != seq + 1) {
+                       op->lock = b->level;
 			goto out;
+               }
 	}
 
 	SET_KEY_PTRS(check_key, 1);

drivers/md/bcache/super.c

@@ -685,6 +685,8 @@ static void bcache_device_link(struct bcache_device *d, struct cache_set *c,
 	WARN(sysfs_create_link(&d->kobj, &c->kobj, "cache") ||
 	     sysfs_create_link(&c->kobj, &d->kobj, d->name),
 	     "Couldn't create device <-> cache set symlinks");
+
+	clear_bit(BCACHE_DEV_UNLINK_DONE, &d->flags);
 }
 
 static void bcache_device_detach(struct bcache_device *d)
@@ -847,8 +849,11 @@ void bch_cached_dev_run(struct cached_dev *dc)
 	buf[SB_LABEL_SIZE] = '\0';
 	env[2] = kasprintf(GFP_KERNEL, "CACHED_LABEL=%s", buf);
 
-	if (atomic_xchg(&dc->running, 1))
+	if (atomic_xchg(&dc->running, 1)) {
+		kfree(env[1]);
+		kfree(env[2]);
 		return;
+	}
 
 	if (!d->c &&
 	    BDEV_STATE(&dc->sb) != BDEV_STATE_NONE) {
@@ -1933,6 +1938,8 @@ static ssize_t register_bcache(struct kobject *k, struct kobj_attribute *attr,
 			else
 				err = "device busy";
 			mutex_unlock(&bch_register_lock);
+			if (attr == &ksysfs_register_quiet)
+				goto out;
 		}
 		goto err;
 	}
@@ -1971,8 +1978,7 @@ static ssize_t register_bcache(struct kobject *k, struct kobj_attribute *attr,
 err_close:
 	blkdev_put(bdev, FMODE_READ|FMODE_WRITE|FMODE_EXCL);
 err:
-	if (attr != &ksysfs_register_quiet)
-		pr_info("error opening %s: %s", path, err);
+	pr_info("error opening %s: %s", path, err);
 	ret = -EINVAL;
 	goto out;
 }
@@ -2066,8 +2072,10 @@ static int __init bcache_init(void)
 	closure_debug_init();
 
 	bcache_major = register_blkdev(0, "bcache");
-	if (bcache_major < 0)
+	if (bcache_major < 0) {
+		unregister_reboot_notifier(&reboot);
 		return bcache_major;
+	}
 
 	if (!(bcache_wq = create_workqueue("bcache")) ||
 	    !(bcache_kobj = kobject_create_and_add("bcache", fs_kobj)) ||

drivers/md/bcache/writeback.c

@@ -323,6 +323,10 @@ void bcache_dev_sectors_dirty_add(struct cache_set *c, unsigned inode,
 
 static bool dirty_pred(struct keybuf *buf, struct bkey *k)
 {
+	struct cached_dev *dc = container_of(buf, struct cached_dev, writeback_keys);
+
+	BUG_ON(KEY_INODE(k) != dc->disk.id);
+
 	return KEY_DIRTY(k);
 }
 
@@ -372,11 +376,24 @@ static void refill_full_stripes(struct cached_dev *dc)
 	}
 }
 
+/*
+ * Returns true if we scanned the entire disk
+ */
 static bool refill_dirty(struct cached_dev *dc)
 {
 	struct keybuf *buf = &dc->writeback_keys;
+	struct bkey start = KEY(dc->disk.id, 0, 0);
 	struct bkey end = KEY(dc->disk.id, MAX_KEY_OFFSET, 0);
-	bool searched_from_start = false;
+	struct bkey start_pos;
+
+	/*
+	 * make sure keybuf pos is inside the range for this disk - at bringup
+	 * we might not be attached yet so this disk's inode nr isn't
+	 * initialized then
+	 */
+	if (bkey_cmp(&buf->last_scanned, &start) < 0 ||
+	    bkey_cmp(&buf->last_scanned, &end) > 0)
+		buf->last_scanned = start;
 
 	if (dc->partial_stripes_expensive) {
 		refill_full_stripes(dc);
@@ -384,14 +401,20 @@ static bool refill_dirty(struct cached_dev *dc)
 			return false;
 	}
 
-	if (bkey_cmp(&buf->last_scanned, &end) >= 0) {
-		buf->last_scanned = KEY(dc->disk.id, 0, 0);
-		searched_from_start = true;
-	}
-
+	start_pos = buf->last_scanned;
 	bch_refill_keybuf(dc->disk.c, buf, &end, dirty_pred);
 
-	return bkey_cmp(&buf->last_scanned, &end) >= 0 && searched_from_start;
+	if (bkey_cmp(&buf->last_scanned, &end) < 0)
+		return false;
+
+	/*
+	 * If we get to the end start scanning again from the beginning, and
+	 * only scan up to where we initially started scanning from:
+	 */
+	buf->last_scanned = start;
+	bch_refill_keybuf(dc->disk.c, buf, &start_pos, dirty_pred);
+
+	return bkey_cmp(&buf->last_scanned, &start_pos) >= 0;
 }
 
 static int bch_writeback_thread(void *arg)

drivers/md/bcache/writeback.h

@@ -63,7 +63,8 @@ static inline bool should_writeback(struct cached_dev *dc, struct bio *bio,
 
 static inline void bch_writeback_queue(struct cached_dev *dc)
 {
-	wake_up_process(dc->writeback_thread);
+	if (!IS_ERR_OR_NULL(dc->writeback_thread))
+		wake_up_process(dc->writeback_thread);
 }
 
 static inline void bch_writeback_add(struct cached_dev *dc)

include/linux/drbd.h

@@ -25,7 +25,6 @@
 */
 #ifndef DRBD_H
 #define DRBD_H
-#include <linux/connector.h>
 #include <asm/types.h>
 
 #ifdef __KERNEL__
@@ -52,7 +51,7 @@
 #endif
 
 extern const char *drbd_buildtag(void);
-#define REL_VERSION "8.4.5"
+#define REL_VERSION "8.4.6"
 #define API_VERSION 1
 #define PRO_VERSION_MIN 86
 #define PRO_VERSION_MAX 101
@@ -339,6 +338,8 @@ enum drbd_state_rv {
 #define MDF_AL_CLEAN		(1 << 7)
 #define MDF_AL_DISABLED		(1 << 8)
 
+#define MAX_PEERS 32
+
 enum drbd_uuid_index {
 	UI_CURRENT,
 	UI_BITMAP,
@@ -349,14 +350,35 @@ enum drbd_uuid_index {
 	UI_EXTENDED_SIZE   /* Everything. */
 };
 
+#define HISTORY_UUIDS MAX_PEERS
+
 enum drbd_timeout_flag {
 	UT_DEFAULT      = 0,
 	UT_DEGRADED     = 1,
 	UT_PEER_OUTDATED = 2,
 };
 
+enum drbd_notification_type {
+	NOTIFY_EXISTS,
+	NOTIFY_CREATE,
+	NOTIFY_CHANGE,
+	NOTIFY_DESTROY,
+	NOTIFY_CALL,
+	NOTIFY_RESPONSE,
+
+	NOTIFY_CONTINUES = 0x8000,
+	NOTIFY_FLAGS = NOTIFY_CONTINUES,
+};
+
 #define UUID_JUST_CREATED ((__u64)4)
 
+enum write_ordering_e {
+	WO_NONE,
+	WO_DRAIN_IO,
+	WO_BDEV_FLUSH,
+	WO_BIO_BARRIER
+};
+
 /* magic numbers used in meta data and network packets */
 #define DRBD_MAGIC 0x83740267
 #define DRBD_MAGIC_BIG 0x835a

include/linux/drbd_genl.h

@@ -250,6 +250,76 @@ GENL_struct(DRBD_NLA_DETACH_PARMS, 13, detach_parms,
 	__flg_field(1, DRBD_GENLA_F_MANDATORY,	force_detach)
 )
 
+GENL_struct(DRBD_NLA_RESOURCE_INFO, 15, resource_info,
+	__u32_field(1, 0, res_role)
+	__flg_field(2, 0, res_susp)
+	__flg_field(3, 0, res_susp_nod)
+	__flg_field(4, 0, res_susp_fen)
+	/* __flg_field(5, 0, res_weak) */
+)
+
+GENL_struct(DRBD_NLA_DEVICE_INFO, 16, device_info,
+	__u32_field(1, 0, dev_disk_state)
+)
+
+GENL_struct(DRBD_NLA_CONNECTION_INFO, 17, connection_info,
+	__u32_field(1, 0, conn_connection_state)
+	__u32_field(2, 0, conn_role)
+)
+
+GENL_struct(DRBD_NLA_PEER_DEVICE_INFO, 18, peer_device_info,
+	__u32_field(1, 0, peer_repl_state)
+	__u32_field(2, 0, peer_disk_state)
+	__u32_field(3, 0, peer_resync_susp_user)
+	__u32_field(4, 0, peer_resync_susp_peer)
+	__u32_field(5, 0, peer_resync_susp_dependency)
+)
+
+GENL_struct(DRBD_NLA_RESOURCE_STATISTICS, 19, resource_statistics,
+	__u32_field(1, 0, res_stat_write_ordering)
+)
+
+GENL_struct(DRBD_NLA_DEVICE_STATISTICS, 20, device_statistics,
+	__u64_field(1, 0, dev_size)  /* (sectors) */
+	__u64_field(2, 0, dev_read)  /* (sectors) */
+	__u64_field(3, 0, dev_write)  /* (sectors) */
+	__u64_field(4, 0, dev_al_writes)  /* activity log writes (count) */
+	__u64_field(5, 0, dev_bm_writes)  /*  bitmap writes  (count) */
+	__u32_field(6, 0, dev_upper_pending)  /* application requests in progress */
+	__u32_field(7, 0, dev_lower_pending)  /* backing device requests in progress */
+	__flg_field(8, 0, dev_upper_blocked)
+	__flg_field(9, 0, dev_lower_blocked)
+	__flg_field(10, 0, dev_al_suspended)  /* activity log suspended */
+	__u64_field(11, 0, dev_exposed_data_uuid)
+	__u64_field(12, 0, dev_current_uuid)
+	__u32_field(13, 0, dev_disk_flags)
+	__bin_field(14, 0, history_uuids, HISTORY_UUIDS * sizeof(__u64))
+)
+
+GENL_struct(DRBD_NLA_CONNECTION_STATISTICS, 21, connection_statistics,
+	__flg_field(1, 0, conn_congested)
+)
+
+GENL_struct(DRBD_NLA_PEER_DEVICE_STATISTICS, 22, peer_device_statistics,
+	__u64_field(1, 0, peer_dev_received)  /* sectors */
+	__u64_field(2, 0, peer_dev_sent)  /* sectors */
+	__u32_field(3, 0, peer_dev_pending)  /* number of requests */
+	__u32_field(4, 0, peer_dev_unacked)  /* number of requests */
+	__u64_field(5, 0, peer_dev_out_of_sync)  /* sectors */
+	__u64_field(6, 0, peer_dev_resync_failed)  /* sectors */
+	__u64_field(7, 0, peer_dev_bitmap_uuid)
+	__u32_field(9, 0, peer_dev_flags)
+)
+
+GENL_struct(DRBD_NLA_NOTIFICATION_HEADER, 23, drbd_notification_header,
+	__u32_field(1, DRBD_GENLA_F_MANDATORY, nh_type)
+)
+
+GENL_struct(DRBD_NLA_HELPER, 24, drbd_helper_info,
+	__str_field(1, DRBD_GENLA_F_MANDATORY, helper_name, 32)
+	__u32_field(2, DRBD_GENLA_F_MANDATORY, helper_status)
+)
+
 /*
  * Notifications and commands (genlmsghdr->cmd)
  */
@@ -382,3 +452,82 @@ GENL_op(DRBD_ADM_GET_TIMEOUT_TYPE, 26, GENL_doit(drbd_adm_get_timeout_type),
 	GENL_tla_expected(DRBD_NLA_CFG_CONTEXT, DRBD_F_REQUIRED))
 GENL_op(DRBD_ADM_DOWN,		27, GENL_doit(drbd_adm_down),
 	GENL_tla_expected(DRBD_NLA_CFG_CONTEXT, DRBD_F_REQUIRED))
+
+GENL_op(DRBD_ADM_GET_RESOURCES, 30,
+	 GENL_op_init(
+		 .dumpit = drbd_adm_dump_resources,
+	 ),
+	 GENL_tla_expected(DRBD_NLA_CFG_CONTEXT, DRBD_GENLA_F_MANDATORY)
+	 GENL_tla_expected(DRBD_NLA_RESOURCE_INFO, DRBD_GENLA_F_MANDATORY)
+	 GENL_tla_expected(DRBD_NLA_RESOURCE_STATISTICS, DRBD_GENLA_F_MANDATORY))
+
+GENL_op(DRBD_ADM_GET_DEVICES, 31,
+	 GENL_op_init(
+		 .dumpit = drbd_adm_dump_devices,
+		 .done = drbd_adm_dump_devices_done,
+	 ),
+	 GENL_tla_expected(DRBD_NLA_CFG_CONTEXT, DRBD_GENLA_F_MANDATORY)
+	 GENL_tla_expected(DRBD_NLA_DEVICE_INFO, DRBD_GENLA_F_MANDATORY)
+	 GENL_tla_expected(DRBD_NLA_DEVICE_STATISTICS, DRBD_GENLA_F_MANDATORY))
+
+GENL_op(DRBD_ADM_GET_CONNECTIONS, 32,
+	 GENL_op_init(
+		 .dumpit = drbd_adm_dump_connections,
+		 .done = drbd_adm_dump_connections_done,
+	 ),
+	 GENL_tla_expected(DRBD_NLA_CFG_CONTEXT, DRBD_GENLA_F_MANDATORY)
+	 GENL_tla_expected(DRBD_NLA_CONNECTION_INFO, DRBD_GENLA_F_MANDATORY)
+	 GENL_tla_expected(DRBD_NLA_CONNECTION_STATISTICS, DRBD_GENLA_F_MANDATORY))
+
+GENL_op(DRBD_ADM_GET_PEER_DEVICES, 33,
+	 GENL_op_init(
+		 .dumpit = drbd_adm_dump_peer_devices,
+		 .done = drbd_adm_dump_peer_devices_done,
+	 ),
+	 GENL_tla_expected(DRBD_NLA_CFG_CONTEXT, DRBD_GENLA_F_MANDATORY)
+	 GENL_tla_expected(DRBD_NLA_PEER_DEVICE_INFO, DRBD_GENLA_F_MANDATORY)
+	 GENL_tla_expected(DRBD_NLA_PEER_DEVICE_STATISTICS, DRBD_GENLA_F_MANDATORY))
+
+GENL_notification(
+	DRBD_RESOURCE_STATE, 34, events,
+	GENL_tla_expected(DRBD_NLA_CFG_CONTEXT, DRBD_F_REQUIRED)
+	GENL_tla_expected(DRBD_NLA_NOTIFICATION_HEADER, DRBD_F_REQUIRED)
+	GENL_tla_expected(DRBD_NLA_RESOURCE_INFO, DRBD_F_REQUIRED)
+	GENL_tla_expected(DRBD_NLA_RESOURCE_STATISTICS, DRBD_F_REQUIRED))
+
+GENL_notification(
+	DRBD_DEVICE_STATE, 35, events,
+	GENL_tla_expected(DRBD_NLA_CFG_CONTEXT, DRBD_F_REQUIRED)
+	GENL_tla_expected(DRBD_NLA_NOTIFICATION_HEADER, DRBD_F_REQUIRED)
+	GENL_tla_expected(DRBD_NLA_DEVICE_INFO, DRBD_F_REQUIRED)
+	GENL_tla_expected(DRBD_NLA_DEVICE_STATISTICS, DRBD_F_REQUIRED))
+
+GENL_notification(
+	DRBD_CONNECTION_STATE, 36, events,
+	GENL_tla_expected(DRBD_NLA_CFG_CONTEXT, DRBD_F_REQUIRED)
+	GENL_tla_expected(DRBD_NLA_NOTIFICATION_HEADER, DRBD_F_REQUIRED)
+	GENL_tla_expected(DRBD_NLA_CONNECTION_INFO, DRBD_F_REQUIRED)
+	GENL_tla_expected(DRBD_NLA_CONNECTION_STATISTICS, DRBD_F_REQUIRED))
+
+GENL_notification(
+	DRBD_PEER_DEVICE_STATE, 37, events,
+	GENL_tla_expected(DRBD_NLA_CFG_CONTEXT, DRBD_F_REQUIRED)
+	GENL_tla_expected(DRBD_NLA_NOTIFICATION_HEADER, DRBD_F_REQUIRED)
+	GENL_tla_expected(DRBD_NLA_PEER_DEVICE_INFO, DRBD_F_REQUIRED)
+	GENL_tla_expected(DRBD_NLA_PEER_DEVICE_STATISTICS, DRBD_F_REQUIRED))
+
+GENL_op(
+	DRBD_ADM_GET_INITIAL_STATE, 38,
+	GENL_op_init(
+	        .dumpit = drbd_adm_get_initial_state,
+	),
+	GENL_tla_expected(DRBD_NLA_CFG_CONTEXT, DRBD_GENLA_F_MANDATORY))
+
+GENL_notification(
+	DRBD_HELPER, 40, events,
+	GENL_tla_expected(DRBD_NLA_CFG_CONTEXT, DRBD_F_REQUIRED)
+	GENL_tla_expected(DRBD_NLA_HELPER, DRBD_F_REQUIRED))
+
+GENL_notification(
+	DRBD_INITIAL_STATE_DONE, 41, events,
+	GENL_tla_expected(DRBD_NLA_NOTIFICATION_HEADER, DRBD_F_REQUIRED))

include/linux/idr.h

@@ -135,6 +135,20 @@ static inline void *idr_find(struct idr *idr, int id)
 #define idr_for_each_entry(idp, entry, id)			\
 	for (id = 0; ((entry) = idr_get_next(idp, &(id))) != NULL; ++id)
 
+/**
+ * idr_for_each_entry - continue iteration over an idr's elements of a given type
+ * @idp:     idr handle
+ * @entry:   the type * to use as cursor
+ * @id:      id entry's key
+ *
+ * Continue to iterate over list of given type, continuing after
+ * the current position.
+ */
+#define idr_for_each_entry_continue(idp, entry, id)			\
+	for ((entry) = idr_get_next((idp), &(id));			\
+	     entry;							\
+	     ++id, (entry) = idr_get_next((idp), &(id)))
+
 /*
  * IDA - IDR based id allocator, use when translation from id to
  * pointer isn't necessary.

include/linux/lru_cache.h

@@ -264,7 +264,7 @@ extern unsigned int lc_put(struct lru_cache *lc, struct lc_element *e);
 extern void lc_committed(struct lru_cache *lc);
 
 struct seq_file;
-extern size_t lc_seq_printf_stats(struct seq_file *seq, struct lru_cache *lc);
+extern void lc_seq_printf_stats(struct seq_file *seq, struct lru_cache *lc);
 
 extern void lc_seq_dump_details(struct seq_file *seq, struct lru_cache *lc, char *utext,
 				void (*detail) (struct seq_file *, struct lc_element *));

include/xen/interface/io/blkif.h

@@ -27,6 +27,54 @@
 typedef uint16_t blkif_vdev_t;
 typedef uint64_t blkif_sector_t;
 
+/*
+ * Multiple hardware queues/rings:
+ * If supported, the backend will write the key "multi-queue-max-queues" to
+ * the directory for that vbd, and set its value to the maximum supported
+ * number of queues.
+ * Frontends that are aware of this feature and wish to use it can write the
+ * key "multi-queue-num-queues" with the number they wish to use, which must be
+ * greater than zero, and no more than the value reported by the backend in
+ * "multi-queue-max-queues".
+ *
+ * For frontends requesting just one queue, the usual event-channel and
+ * ring-ref keys are written as before, simplifying the backend processing
+ * to avoid distinguishing between a frontend that doesn't understand the
+ * multi-queue feature, and one that does, but requested only one queue.
+ *
+ * Frontends requesting two or more queues must not write the toplevel
+ * event-channel and ring-ref keys, instead writing those keys under sub-keys
+ * having the name "queue-N" where N is the integer ID of the queue/ring for
+ * which those keys belong. Queues are indexed from zero.
+ * For example, a frontend with two queues must write the following set of
+ * queue-related keys:
+ *
+ * /local/domain/1/device/vbd/0/multi-queue-num-queues = "2"
+ * /local/domain/1/device/vbd/0/queue-0 = ""
+ * /local/domain/1/device/vbd/0/queue-0/ring-ref = "<ring-ref#0>"
+ * /local/domain/1/device/vbd/0/queue-0/event-channel = "<evtchn#0>"
+ * /local/domain/1/device/vbd/0/queue-1 = ""
+ * /local/domain/1/device/vbd/0/queue-1/ring-ref = "<ring-ref#1>"
+ * /local/domain/1/device/vbd/0/queue-1/event-channel = "<evtchn#1>"
+ *
+ * It is also possible to use multiple queues/rings together with
+ * feature multi-page ring buffer.
+ * For example, a frontend requests two queues/rings and the size of each ring
+ * buffer is two pages must write the following set of related keys:
+ *
+ * /local/domain/1/device/vbd/0/multi-queue-num-queues = "2"
+ * /local/domain/1/device/vbd/0/ring-page-order = "1"
+ * /local/domain/1/device/vbd/0/queue-0 = ""
+ * /local/domain/1/device/vbd/0/queue-0/ring-ref0 = "<ring-ref#0>"
+ * /local/domain/1/device/vbd/0/queue-0/ring-ref1 = "<ring-ref#1>"
+ * /local/domain/1/device/vbd/0/queue-0/event-channel = "<evtchn#0>"
+ * /local/domain/1/device/vbd/0/queue-1 = ""
+ * /local/domain/1/device/vbd/0/queue-1/ring-ref0 = "<ring-ref#2>"
+ * /local/domain/1/device/vbd/0/queue-1/ring-ref1 = "<ring-ref#3>"
+ * /local/domain/1/device/vbd/0/queue-1/event-channel = "<evtchn#1>"
+ *
+ */
+
 /*
  * REQUEST CODES.
  */

lib/lru_cache.c

@@ -238,7 +238,7 @@ void lc_reset(struct lru_cache *lc)
  * @seq: the seq_file to print into
  * @lc: the lru cache to print statistics of
  */
-size_t lc_seq_printf_stats(struct seq_file *seq, struct lru_cache *lc)
+void lc_seq_printf_stats(struct seq_file *seq, struct lru_cache *lc)
 {
 	/* NOTE:
 	 * total calls to lc_get are
@@ -250,8 +250,6 @@ size_t lc_seq_printf_stats(struct seq_file *seq, struct lru_cache *lc)
 	seq_printf(seq, "\t%s: used:%u/%u hits:%lu misses:%lu starving:%lu locked:%lu changed:%lu\n",
 		   lc->name, lc->used, lc->nr_elements,
 		   lc->hits, lc->misses, lc->starving, lc->locked, lc->changed);
-
-	return 0;
 }
 
 static struct hlist_head *lc_hash_slot(struct lru_cache *lc, unsigned int enr)