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
  ...

5 files changed, 236 insertions, 3 deletions

diff --git a/include/linux/drbd.h b/include/linux/drbd.h
index 8723f2a99e15..d6b3c9943a2c 100644
--- a/include/linux/drbd.h
+++ b/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
diff --git a/include/linux/drbd_genl.h b/include/linux/drbd_genl.h
index 7b131ed8f9c6..2d0e5ad5de9d 100644
--- a/include/linux/drbd_genl.h
+++ b/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))
diff --git a/include/linux/idr.h b/include/linux/idr.h
index 013fd9bc4cb6..083d61e92706 100644
--- a/include/linux/idr.h
+++ b/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.
diff --git a/include/linux/lru_cache.h b/include/linux/lru_cache.h
index 46262284de47..04fc6e6c7ff0 100644
--- a/include/linux/lru_cache.h
+++ b/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 *));
diff --git a/include/xen/interface/io/blkif.h b/include/xen/interface/io/blkif.h
index c33e1c489eb2..8b8cfadf7833 100644
--- a/include/xen/interface/io/blkif.h
+++ b/include/xen/interface/io/blkif.h
@@ -28,6 +28,54 @@ 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.
  */
 #define BLKIF_OP_READ              0