Merge branch 'drbd-8.4_ed6' into for-3.8-drivers-drbd-8.4_ed6

1 files changed, 601 insertions, 797 deletions

diff --git a/drivers/block/drbd/drbd_int.h b/drivers/block/drbd/drbd_int.h
index 277c69c9465..ef72a72814c 100644
--- a/drivers/block/drbd/drbd_int.h
+++ b/drivers/block/drbd/drbd_int.h
@@ -39,9 +39,13 @@
 #include <linux/major.h>
 #include <linux/blkdev.h>
 #include <linux/genhd.h>
+#include <linux/idr.h>
 #include <net/tcp.h>
 #include <linux/lru_cache.h>
 #include <linux/prefetch.h>
+#include <linux/drbd_genl_api.h>
+#include <linux/drbd.h>
+#include "drbd_state.h"
 
 #ifdef __CHECKER__
 # define __protected_by(x)       __attribute__((require_context(x,1,999,"rdwr")))
@@ -61,7 +65,6 @@
 extern unsigned int minor_count;
 extern bool disable_sendpage;
 extern bool allow_oos;
-extern unsigned int cn_idx;
 
 #ifdef CONFIG_DRBD_FAULT_INJECTION
 extern int enable_faults;
@@ -86,34 +89,44 @@ extern char usermode_helper[];
  */
 #define DRBD_SIGKILL SIGHUP
 
-/* All EEs on the free list should have ID_VACANT (== 0)
- * freshly allocated EEs get !ID_VACANT (== 1)
- * so if it says "cannot dereference null pointer at address 0x00000001",
- * it is most likely one of these :( */
-
 #define ID_IN_SYNC      (4711ULL)
 #define ID_OUT_OF_SYNC  (4712ULL)
-
 #define ID_SYNCER (-1ULL)
-#define ID_VACANT 0
-#define is_syncer_block_id(id) ((id) == ID_SYNCER)
+
 #define UUID_NEW_BM_OFFSET ((u64)0x0001000000000000ULL)
 
 struct drbd_conf;
+struct drbd_tconn;
 
 
 /* to shorten dev_warn(DEV, "msg"); and relatives statements */
 #define DEV (disk_to_dev(mdev->vdisk))
 
+#define conn_printk(LEVEL, TCONN, FMT, ARGS...) \
+	printk(LEVEL "d-con %s: " FMT, TCONN->name , ## ARGS)
+#define conn_alert(TCONN, FMT, ARGS...)  conn_printk(KERN_ALERT, TCONN, FMT, ## ARGS)
+#define conn_crit(TCONN, FMT, ARGS...)   conn_printk(KERN_CRIT, TCONN, FMT, ## ARGS)
+#define conn_err(TCONN, FMT, ARGS...)    conn_printk(KERN_ERR, TCONN, FMT, ## ARGS)
+#define conn_warn(TCONN, FMT, ARGS...)   conn_printk(KERN_WARNING, TCONN, FMT, ## ARGS)
+#define conn_notice(TCONN, FMT, ARGS...) conn_printk(KERN_NOTICE, TCONN, FMT, ## ARGS)
+#define conn_info(TCONN, FMT, ARGS...)   conn_printk(KERN_INFO, TCONN, FMT, ## ARGS)
+#define conn_dbg(TCONN, FMT, ARGS...)    conn_printk(KERN_DEBUG, TCONN, FMT, ## ARGS)
+
 #define D_ASSERT(exp)	if (!(exp)) \
 	 dev_err(DEV, "ASSERT( " #exp " ) in %s:%d\n", __FILE__, __LINE__)
 
-#define ERR_IF(exp) if (({						\
-	int _b = (exp) != 0;						\
-	if (_b) dev_err(DEV, "ASSERT FAILED: %s: (%s) in %s:%d\n",	\
-			__func__, #exp, __FILE__, __LINE__);		\
-	_b;								\
-	}))
+/**
+ * expect  -  Make an assertion
+ *
+ * Unlike the assert macro, this macro returns a boolean result.
+ */
+#define expect(exp) ({								\
+		bool _bool = (exp);						\
+		if (!_bool)							\
+			dev_err(DEV, "ASSERTION %s FAILED in %s\n",		\
+			        #exp, __func__);				\
+		_bool;								\
+		})
 
 /* Defines to control fault insertion */
 enum {
@@ -150,15 +163,12 @@ drbd_insert_fault(struct drbd_conf *mdev, unsigned int type) {
 /* usual integer division */
 #define div_floor(A, B) ((A)/(B))
 
-/* drbd_meta-data.c (still in drbd_main.c) */
-/* 4th incarnation of the disk layout. */
-#define DRBD_MD_MAGIC (DRBD_MAGIC+4)
-
-extern struct drbd_conf **minor_table;
 extern struct ratelimit_state drbd_ratelimit_state;
+extern struct idr minors; /* RCU, updates: genl_lock() */
+extern struct list_head drbd_tconns; /* RCU, updates: genl_lock() */
 
 /* on the wire */
-enum drbd_packets {
+enum drbd_packet {
 	/* receiver (data socket) */
 	P_DATA		      = 0x00,
 	P_DATA_REPLY	      = 0x01, /* Response to P_DATA_REQUEST */
@@ -186,7 +196,7 @@ enum drbd_packets {
 	P_RECV_ACK	      = 0x15, /* Used in protocol B */
 	P_WRITE_ACK	      = 0x16, /* Used in protocol C */
 	P_RS_WRITE_ACK	      = 0x17, /* Is a P_WRITE_ACK, additionally call set_in_sync(). */
-	P_DISCARD_ACK	      = 0x18, /* Used in proto C, two-primaries conflict detection */
+	P_SUPERSEDED	      = 0x18, /* Used in proto C, two-primaries conflict detection */
 	P_NEG_ACK	      = 0x19, /* Sent if local disk is unusable */
 	P_NEG_DREPLY	      = 0x1a, /* Local disk is broken... */
 	P_NEG_RS_DREPLY	      = 0x1b, /* Local disk is broken... */
@@ -207,77 +217,23 @@ enum drbd_packets {
 	P_DELAY_PROBE         = 0x27, /* is used on BOTH sockets */
 	P_OUT_OF_SYNC         = 0x28, /* Mark as out of sync (Outrunning), data socket */
 	P_RS_CANCEL           = 0x29, /* meta: Used to cancel RS_DATA_REQUEST packet by SyncSource */
+	P_CONN_ST_CHG_REQ     = 0x2a, /* data sock: Connection wide state request */
+	P_CONN_ST_CHG_REPLY   = 0x2b, /* meta sock: Connection side state req reply */
+	P_RETRY_WRITE	      = 0x2c, /* Protocol C: retry conflicting write request */
+	P_PROTOCOL_UPDATE     = 0x2d, /* data sock: is used in established connections */
 
-	P_MAX_CMD	      = 0x2A,
 	P_MAY_IGNORE	      = 0x100, /* Flag to test if (cmd > P_MAY_IGNORE) ... */
 	P_MAX_OPT_CMD	      = 0x101,
 
 	/* special command ids for handshake */
 
-	P_HAND_SHAKE_M	      = 0xfff1, /* First Packet on the MetaSock */
-	P_HAND_SHAKE_S	      = 0xfff2, /* First Packet on the Socket */
+	P_INITIAL_META	      = 0xfff1, /* First Packet on the MetaSock */
+	P_INITIAL_DATA	      = 0xfff2, /* First Packet on the Socket */
 
-	P_HAND_SHAKE	      = 0xfffe	/* FIXED for the next century! */
+	P_CONNECTION_FEATURES = 0xfffe	/* FIXED for the next century! */
 };
 
-static inline const char *cmdname(enum drbd_packets cmd)
-{
-	/* THINK may need to become several global tables
-	 * when we want to support more than
-	 * one PRO_VERSION */
-	static const char *cmdnames[] = {
-		[P_DATA]	        = "Data",
-		[P_DATA_REPLY]	        = "DataReply",
-		[P_RS_DATA_REPLY]	= "RSDataReply",
-		[P_BARRIER]	        = "Barrier",
-		[P_BITMAP]	        = "ReportBitMap",
-		[P_BECOME_SYNC_TARGET]  = "BecomeSyncTarget",
-		[P_BECOME_SYNC_SOURCE]  = "BecomeSyncSource",
-		[P_UNPLUG_REMOTE]	= "UnplugRemote",
-		[P_DATA_REQUEST]	= "DataRequest",
-		[P_RS_DATA_REQUEST]     = "RSDataRequest",
-		[P_SYNC_PARAM]	        = "SyncParam",
-		[P_SYNC_PARAM89]	= "SyncParam89",
-		[P_PROTOCOL]            = "ReportProtocol",
-		[P_UUIDS]	        = "ReportUUIDs",
-		[P_SIZES]	        = "ReportSizes",
-		[P_STATE]	        = "ReportState",
-		[P_SYNC_UUID]           = "ReportSyncUUID",
-		[P_AUTH_CHALLENGE]      = "AuthChallenge",
-		[P_AUTH_RESPONSE]	= "AuthResponse",
-		[P_PING]		= "Ping",
-		[P_PING_ACK]	        = "PingAck",
-		[P_RECV_ACK]	        = "RecvAck",
-		[P_WRITE_ACK]	        = "WriteAck",
-		[P_RS_WRITE_ACK]	= "RSWriteAck",
-		[P_DISCARD_ACK]	        = "DiscardAck",
-		[P_NEG_ACK]	        = "NegAck",
-		[P_NEG_DREPLY]	        = "NegDReply",
-		[P_NEG_RS_DREPLY]	= "NegRSDReply",
-		[P_BARRIER_ACK]	        = "BarrierAck",
-		[P_STATE_CHG_REQ]       = "StateChgRequest",
-		[P_STATE_CHG_REPLY]     = "StateChgReply",
-		[P_OV_REQUEST]          = "OVRequest",
-		[P_OV_REPLY]            = "OVReply",
-		[P_OV_RESULT]           = "OVResult",
-		[P_CSUM_RS_REQUEST]     = "CsumRSRequest",
-		[P_RS_IS_IN_SYNC]	= "CsumRSIsInSync",
-		[P_COMPRESSED_BITMAP]   = "CBitmap",
-		[P_DELAY_PROBE]         = "DelayProbe",
-		[P_OUT_OF_SYNC]		= "OutOfSync",
-		[P_MAX_CMD]	        = NULL,
-	};
-
-	if (cmd == P_HAND_SHAKE_M)
-		return "HandShakeM";
-	if (cmd == P_HAND_SHAKE_S)
-		return "HandShakeS";
-	if (cmd == P_HAND_SHAKE)
-		return "HandShake";
-	if (cmd >= P_MAX_CMD)
-		return "Unknown";
-	return cmdnames[cmd];
-}
+extern const char *cmdname(enum drbd_packet cmd);
 
 /* for sending/receiving the bitmap,
  * possibly in some encoding scheme */
@@ -337,37 +293,24 @@ struct p_header80 {
 	u32	  magic;
 	u16	  command;
 	u16	  length;	/* bytes of data after this header */
-	u8	  payload[0];
 } __packed;
 
 /* Header for big packets, Used for data packets exceeding 64kB */
 struct p_header95 {
 	u16	  magic;	/* use DRBD_MAGIC_BIG here */
 	u16	  command;
-	u32	  length;	/* Use only 24 bits of that. Ignore the highest 8 bit. */
-	u8	  payload[0];
+	u32	  length;
 } __packed;
 
-union p_header {
-	struct p_header80 h80;
-	struct p_header95 h95;
-};
-
-/*
- * short commands, packets without payload, plain p_header:
- *   P_PING
- *   P_PING_ACK
- *   P_BECOME_SYNC_TARGET
- *   P_BECOME_SYNC_SOURCE
- *   P_UNPLUG_REMOTE
- */
+struct p_header100 {
+	u32	  magic;
+	u16	  volume;
+	u16	  command;
+	u32	  length;
+	u32	  pad;
+} __packed;
 
-/*
- * commands with out-of-struct payload:
- *   P_BITMAP    (no additional fields)
- *   P_DATA, P_DATA_REPLY (see p_data)
- *   P_COMPRESSED_BITMAP (see receive_compressed_bitmap)
- */
+extern unsigned int drbd_header_size(struct drbd_tconn *tconn);
 
 /* these defines must not be changed without changing the protocol version */
 #define DP_HARDBARRIER	      1 /* depricated */
@@ -377,9 +320,10 @@ union p_header {
 #define DP_FUA               16 /* equals REQ_FUA     */
 #define DP_FLUSH             32 /* equals REQ_FLUSH   */
 #define DP_DISCARD           64 /* equals REQ_DISCARD */
+#define DP_SEND_RECEIVE_ACK 128 /* This is a proto B write request */
+#define DP_SEND_WRITE_ACK   256 /* This is a proto C write request */
 
 struct p_data {
-	union p_header head;
 	u64	    sector;    /* 64 bits sector number */
 	u64	    block_id;  /* to identify the request in protocol B&C */
 	u32	    seq_num;
@@ -390,21 +334,18 @@ struct p_data {
  * commands which share a struct:
  *  p_block_ack:
  *   P_RECV_ACK (proto B), P_WRITE_ACK (proto C),
- *   P_DISCARD_ACK (proto C, two-primaries conflict detection)
+ *   P_SUPERSEDED (proto C, two-primaries conflict detection)
  *  p_block_req:
  *   P_DATA_REQUEST, P_RS_DATA_REQUEST
  */
 struct p_block_ack {
-	struct p_header80 head;
 	u64	    sector;
 	u64	    block_id;
 	u32	    blksize;
 	u32	    seq_num;
 } __packed;
 
-
 struct p_block_req {
-	struct p_header80 head;
 	u64 sector;
 	u64 block_id;
 	u32 blksize;
@@ -413,59 +354,52 @@ struct p_block_req {
 
 /*
  * commands with their own struct for additional fields:
- *   P_HAND_SHAKE
+ *   P_CONNECTION_FEATURES
  *   P_BARRIER
  *   P_BARRIER_ACK
  *   P_SYNC_PARAM
  *   ReportParams
  */
 
-struct p_handshake {
-	struct p_header80 head;	/* 8 bytes */
+struct p_connection_features {
 	u32 protocol_min;
 	u32 feature_flags;
 	u32 protocol_max;
 
 	/* should be more than enough for future enhancements
-	 * for now, feature_flags and the reserverd array shall be zero.
+	 * for now, feature_flags and the reserved array shall be zero.
 	 */
 
 	u32 _pad;
-	u64 reserverd[7];
+	u64 reserved[7];
 } __packed;
-/* 80 bytes, FIXED for the next century */
 
 struct p_barrier {
-	struct p_header80 head;
 	u32 barrier;	/* barrier number _handle_ only */
 	u32 pad;	/* to multiple of 8 Byte */
 } __packed;
 
 struct p_barrier_ack {
-	struct p_header80 head;
 	u32 barrier;
 	u32 set_size;
 } __packed;
 
 struct p_rs_param {
-	struct p_header80 head;
-	u32 rate;
+	u32 resync_rate;
 
 	      /* Since protocol version 88 and higher. */
 	char verify_alg[0];
 } __packed;
 
 struct p_rs_param_89 {
-	struct p_header80 head;
-	u32 rate;
+	u32 resync_rate;
         /* protocol version 89: */
 	char verify_alg[SHARED_SECRET_MAX];
 	char csums_alg[SHARED_SECRET_MAX];
 } __packed;
 
 struct p_rs_param_95 {
-	struct p_header80 head;
-	u32 rate;
+	u32 resync_rate;
 	char verify_alg[SHARED_SECRET_MAX];
 	char csums_alg[SHARED_SECRET_MAX];
 	u32 c_plan_ahead;
@@ -475,12 +409,11 @@ struct p_rs_param_95 {
 } __packed;
 
 enum drbd_conn_flags {
-	CF_WANT_LOSE = 1,
+	CF_DISCARD_MY_DATA = 1,
 	CF_DRY_RUN = 2,
 };
 
 struct p_protocol {
-	struct p_header80 head;
 	u32 protocol;
 	u32 after_sb_0p;
 	u32 after_sb_1p;
@@ -494,17 +427,14 @@ struct p_protocol {
 } __packed;
 
 struct p_uuids {
-	struct p_header80 head;
 	u64 uuid[UI_EXTENDED_SIZE];
 } __packed;
 
 struct p_rs_uuid {
-	struct p_header80 head;
 	u64	    uuid;
 } __packed;
 
 struct p_sizes {
-	struct p_header80 head;
 	u64	    d_size;  /* size of disk */
 	u64	    u_size;  /* user requested size */
 	u64	    c_size;  /* current exported size */
@@ -514,18 +444,15 @@ struct p_sizes {
 } __packed;
 
 struct p_state {
-	struct p_header80 head;
 	u32	    state;
 } __packed;
 
 struct p_req_state {
-	struct p_header80 head;
 	u32	    mask;
 	u32	    val;
 } __packed;
 
 struct p_req_state_reply {
-	struct p_header80 head;
 	u32	    retcode;
 } __packed;
 
@@ -539,15 +466,7 @@ struct p_drbd06_param {
 	u32	  bit_map_gen[5];
 } __packed;
 
-struct p_discard {
-	struct p_header80 head;
-	u64	    block_id;
-	u32	    seq_num;
-	u32	    pad;
-} __packed;
-
 struct p_block_desc {
-	struct p_header80 head;
 	u64 sector;
 	u32 blksize;
 	u32 pad;	/* to multiple of 8 Byte */
@@ -563,7 +482,6 @@ enum drbd_bitmap_code {
 };
 
 struct p_compressed_bm {
-	struct p_header80 head;
 	/* (encoding & 0x0f): actual encoding, see enum drbd_bitmap_code
 	 * (encoding & 0x80): polarity (set/unset) of first runlength
 	 * ((encoding >> 4) & 0x07): pad_bits, number of trailing zero bits
@@ -575,90 +493,22 @@ struct p_compressed_bm {
 } __packed;
 
 struct p_delay_probe93 {
-	struct p_header80 head;
 	u32     seq_num; /* sequence number to match the two probe packets */
 	u32     offset;  /* usecs the probe got sent after the reference time point */
 } __packed;
 
-/* DCBP: Drbd Compressed Bitmap Packet ... */
-static inline enum drbd_bitmap_code
-DCBP_get_code(struct p_compressed_bm *p)
-{
-	return (enum drbd_bitmap_code)(p->encoding & 0x0f);
-}
-
-static inline void
-DCBP_set_code(struct p_compressed_bm *p, enum drbd_bitmap_code code)
-{
-	BUG_ON(code & ~0xf);
-	p->encoding = (p->encoding & ~0xf) | code;
-}
-
-static inline int
-DCBP_get_start(struct p_compressed_bm *p)
-{
-	return (p->encoding & 0x80) != 0;
-}
-
-static inline void
-DCBP_set_start(struct p_compressed_bm *p, int set)
-{
-	p->encoding = (p->encoding & ~0x80) | (set ? 0x80 : 0);
-}
-
-static inline int
-DCBP_get_pad_bits(struct p_compressed_bm *p)
-{
-	return (p->encoding >> 4) & 0x7;
-}
-
-static inline void
-DCBP_set_pad_bits(struct p_compressed_bm *p, int n)
-{
-	BUG_ON(n & ~0x7);
-	p->encoding = (p->encoding & (~0x7 << 4)) | (n << 4);
-}
-
-/* one bitmap packet, including the p_header,
- * should fit within one _architecture independend_ page.
- * so we need to use the fixed size 4KiB page size
- * most architectures have used for a long time.
+/*
+ * Bitmap packets need to fit within a single page on the sender and receiver,
+ * so we are limited to 4 KiB (and not to PAGE_SIZE, which can be bigger).
  */
-#define BM_PACKET_PAYLOAD_BYTES (4096 - sizeof(struct p_header80))
-#define BM_PACKET_WORDS (BM_PACKET_PAYLOAD_BYTES/sizeof(long))
-#define BM_PACKET_VLI_BYTES_MAX (4096 - sizeof(struct p_compressed_bm))
-#if (PAGE_SIZE < 4096)
-/* drbd_send_bitmap / receive_bitmap would break horribly */
-#error "PAGE_SIZE too small"
-#endif
-
-union p_polymorph {
-        union p_header           header;
-        struct p_handshake       handshake;
-        struct p_data            data;
-        struct p_block_ack       block_ack;
-        struct p_barrier         barrier;
-        struct p_barrier_ack     barrier_ack;
-        struct p_rs_param_89     rs_param_89;
-        struct p_rs_param_95     rs_param_95;
-        struct p_protocol        protocol;
-        struct p_sizes           sizes;
-        struct p_uuids           uuids;
-        struct p_state           state;
-        struct p_req_state       req_state;
-        struct p_req_state_reply req_state_reply;
-        struct p_block_req       block_req;
-	struct p_delay_probe93   delay_probe93;
-	struct p_rs_uuid         rs_uuid;
-	struct p_block_desc      block_desc;
-} __packed;
+#define DRBD_SOCKET_BUFFER_SIZE 4096
 
 /**********************************************************************/
 enum drbd_thread_state {
-	None,
-	Running,
-	Exiting,
-	Restarting
+	NONE,
+	RUNNING,
+	EXITING,
+	RESTARTING
 };
 
 struct drbd_thread {
@@ -667,8 +517,9 @@ struct drbd_thread {
 	struct completion stop;
 	enum drbd_thread_state t_state;
 	int (*function) (struct drbd_thread *);
-	struct drbd_conf *mdev;
+	struct drbd_tconn *tconn;
 	int reset_cpu_mask;
+	char name[9];
 };
 
 static inline enum drbd_thread_state get_t_state(struct drbd_thread *thi)
@@ -681,58 +532,54 @@ static inline enum drbd_thread_state get_t_state(struct drbd_thread *thi)
 	return thi->t_state;
 }
 
-struct drbd_work;
-typedef int (*drbd_work_cb)(struct drbd_conf *, struct drbd_work *, int cancel);
 struct drbd_work {
 	struct list_head list;
-	drbd_work_cb cb;
+	int (*cb)(struct drbd_work *, int cancel);
+	union {
+		struct drbd_conf *mdev;
+		struct drbd_tconn *tconn;
+	};
 };
 
-struct drbd_tl_epoch;
+#include "drbd_interval.h"
+
+extern int drbd_wait_misc(struct drbd_conf *, struct drbd_interval *);
+
 struct drbd_request {
 	struct drbd_work w;
-	struct drbd_conf *mdev;
 
 	/* if local IO is not allowed, will be NULL.
 	 * if local IO _is_ allowed, holds the locally submitted bio clone,
 	 * or, after local IO completion, the ERR_PTR(error).
-	 * see drbd_endio_pri(). */
+	 * see drbd_request_endio(). */
 	struct bio *private_bio;
 
-	struct hlist_node collision;
-	sector_t sector;
-	unsigned int size;
-	unsigned int epoch; /* barrier_nr */
+	struct drbd_interval i;
 
-	/* barrier_nr: used to check on "completion" whether this req was in
+	/* epoch: used to check on "completion" whether this req was in
 	 * the current epoch, and we therefore have to close it,
-	 * starting a new epoch...
+	 * causing a p_barrier packet to be send, starting a new epoch.
+	 *
+	 * This corresponds to "barrier" in struct p_barrier[_ack],
+	 * and to "barrier_nr" in struct drbd_epoch (and various
+	 * comments/function parameters/local variable names).
 	 */
+	unsigned int epoch;
 
 	struct list_head tl_requests; /* ring list in the transfer log */
 	struct bio *master_bio;       /* master bio pointer */
-	unsigned long rq_state; /* see comments above _req_mod() */
 	unsigned long start_time;
-};
 
-struct drbd_tl_epoch {
-	struct drbd_work w;
-	struct list_head requests; /* requests before */
-	struct drbd_tl_epoch *next; /* pointer to the next barrier */
-	unsigned int br_number;  /* the barriers identifier. */
-	int n_writes;	/* number of requests attached before this barrier */
-};
+	/* once it hits 0, we may complete the master_bio */
+	atomic_t completion_ref;
+	/* once it hits 0, we may destroy this drbd_request object */
+	struct kref kref;
 
-struct drbd_request;
-
-/* These Tl_epoch_entries may be in one of 6 lists:
-   active_ee .. data packet being written
-   sync_ee   .. syncer block being written
-   done_ee   .. block written, need to send P_WRITE_ACK
-   read_ee   .. [RS]P_DATA_REQUEST being read
-*/
+	unsigned rq_state; /* see comments above _req_mod() */
+};
 
 struct drbd_epoch {
+	struct drbd_tconn *tconn;
 	struct list_head list;
 	unsigned int barrier_nr;
 	atomic_t epoch_size; /* increased on every request added. */
@@ -762,17 +609,14 @@ struct digest_info {
 	void *digest;
 };
 
-struct drbd_epoch_entry {
+struct drbd_peer_request {
 	struct drbd_work w;
-	struct hlist_node collision;
 	struct drbd_epoch *epoch; /* for writes */
-	struct drbd_conf *mdev;
 	struct page *pages;
 	atomic_t pending_bios;
-	unsigned int size;
+	struct drbd_interval i;
 	/* see comments on ee flag bits below */
 	unsigned long flags;
-	sector_t sector;
 	union {
 		u64 block_id;
 		struct digest_info *digest;
@@ -793,31 +637,37 @@ enum {
 	 * we need to resubmit without the barrier flag. */
 	__EE_RESUBMITTED,
 
-	/* we may have several bios per epoch entry.
+	/* we may have several bios per peer request.
 	 * if any of those fail, we set this flag atomically
 	 * from the endio callback */
 	__EE_WAS_ERROR,
 
 	/* This ee has a pointer to a digest instead of a block id */
 	__EE_HAS_DIGEST,
+
+	/* Conflicting local requests need to be restarted after this request */
+	__EE_RESTART_REQUESTS,
+
+	/* The peer wants a write ACK for this (wire proto C) */
+	__EE_SEND_WRITE_ACK,
+
+	/* Is set when net_conf had two_primaries set while creating this peer_req */
+	__EE_IN_INTERVAL_TREE,
 };
 #define EE_CALL_AL_COMPLETE_IO (1<<__EE_CALL_AL_COMPLETE_IO)
 #define EE_MAY_SET_IN_SYNC     (1<<__EE_MAY_SET_IN_SYNC)
 #define	EE_RESUBMITTED         (1<<__EE_RESUBMITTED)
 #define EE_WAS_ERROR           (1<<__EE_WAS_ERROR)
 #define EE_HAS_DIGEST          (1<<__EE_HAS_DIGEST)
+#define EE_RESTART_REQUESTS	(1<<__EE_RESTART_REQUESTS)
+#define EE_SEND_WRITE_ACK	(1<<__EE_SEND_WRITE_ACK)
+#define EE_IN_INTERVAL_TREE	(1<<__EE_IN_INTERVAL_TREE)
 
-/* global flag bits */
-enum drbd_flag {
-	CREATE_BARRIER,		/* next P_DATA is preceded by a P_BARRIER */
-	SIGNAL_ASENDER,		/* whether asender wants to be interrupted */
-	SEND_PING,		/* whether asender should send a ping asap */
-
+/* flag bits per mdev */
+enum {
 	UNPLUG_REMOTE,		/* sending a "UnplugRemote" could help */
 	MD_DIRTY,		/* current uuids and flags not yet on disk */
-	DISCARD_CONCURRENT,	/* Set on one node, cleared on the peer! */
 	USE_DEGR_WFC_T,		/* degr-wfc-timeout instead of wfc-timeout. */
-	CLUSTER_ST_CHANGE,	/* Cluster wide state change going on... */
 	CL_ST_CHG_SUCCESS,
 	CL_ST_CHG_FAIL,
 	CRASHED_PRIMARY,	/* This node was a crashed primary.
@@ -835,33 +685,14 @@ enum drbd_flag {
 	WAS_READ_ERROR,		/* Local disk READ failed (set additionally to the above) */
 	FORCE_DETACH,		/* Force-detach from local disk, aborting any pending local IO */
 	RESYNC_AFTER_NEG,       /* Resync after online grow after the attach&negotiate finished. */
-	NET_CONGESTED,		/* The data socket is congested */
-
-	CONFIG_PENDING,		/* serialization of (re)configuration requests.
-				 * if set, also prevents the device from dying */
-	DEVICE_DYING,		/* device became unconfigured,
-				 * but worker thread is still handling the cleanup.
-				 * reconfiguring (nl_disk_conf, nl_net_conf) is dissalowed,
-				 * while this is set. */
 	RESIZE_PENDING,		/* Size change detected locally, waiting for the response from
 				 * the peer, if it changed there as well. */
-	CONN_DRY_RUN,		/* Expect disconnect after resync handshake. */
-	GOT_PING_ACK,		/* set when we receive a ping_ack packet, misc wait gets woken */
 	NEW_CUR_UUID,		/* Create new current UUID when thawing IO */
 	AL_SUSPENDED,		/* Activity logging is currently suspended. */
 	AHEAD_TO_SYNC_SOURCE,   /* Ahead -> SyncSource queued */
-	STATE_SENT,		/* Do not change state/UUIDs while this is set */
-
-	CALLBACK_PENDING,	/* Whether we have a call_usermodehelper(, UMH_WAIT_PROC)
-				 * pending, from drbd worker context.
-				 * If set, bdi_write_congested() returns true,
-				 * so shrink_page_list() would not recurse into,
-				 * and potentially deadlock on, this drbd worker.
-				 */
-	DISCONNECT_SENT,	/* Currently the last bit in this 32bit word */
-
-	/* keep last */
-	DRBD_N_FLAGS,
+	B_RS_H_DONE,		/* Before resync handler done (already executed) */
+	DISCARD_MY_DATA,	/* discard_my_data flag per volume */
+	READ_BALANCE_RR,
 };
 
 struct drbd_bitmap; /* opaque for drbd_conf */
@@ -899,18 +730,17 @@ enum bm_flag {
 
 struct drbd_work_queue {
 	struct list_head q;
-	struct semaphore s; /* producers up it, worker down()s it */
 	spinlock_t q_lock;  /* to protect the list. */
+	wait_queue_head_t q_wait;
 };
 
 struct drbd_socket {
-	struct drbd_work_queue work;
 	struct mutex mutex;
 	struct socket    *socket;
 	/* this way we get our
 	 * send/receive buffers off the stack */
-	union p_polymorph sbuf;
-	union p_polymorph rbuf;
+	void *sbuf;
+	void *rbuf;
 };
 
 struct drbd_md {
@@ -927,24 +757,16 @@ struct drbd_md {
 	s32 bm_offset;	/* signed relative sector offset to bitmap */
 
 	/* u32 al_nr_extents;	   important for restoring the AL
-	 * is stored into  sync_conf.al_extents, which in turn
+	 * is stored into  ldev->dc.al_extents, which in turn
 	 * gets applied to act_log->nr_elements
 	 */
 };
 
-/* for sync_conf and other types... */
-#define NL_PACKET(name, number, fields) struct name { fields };
-#define NL_INTEGER(pn,pr,member) int member;
-#define NL_INT64(pn,pr,member) __u64 member;
-#define NL_BIT(pn,pr,member)   unsigned member:1;
-#define NL_STRING(pn,pr,member,len) unsigned char member[len]; int member ## _len;
-#include <linux/drbd_nl.h>
-
 struct drbd_backing_dev {
 	struct block_device *backing_bdev;
 	struct block_device *md_bdev;
 	struct drbd_md md;
-	struct disk_conf dc; /* The user provided config... */
+	struct disk_conf *disk_conf; /* RCU, for updates: mdev->tconn->conf_update */
 	sector_t known_size; /* last known size of that backing device */
 };
 
@@ -968,17 +790,116 @@ enum write_ordering_e {
 };
 
 struct fifo_buffer {
-	int *values;
 	unsigned int head_index;
 	unsigned int size;
+	int total; /* sum of all values */
+	int values[0];
+};
+extern struct fifo_buffer *fifo_alloc(int fifo_size);
+
+/* flag bits per tconn */
+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 */
+	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,
+	CONN_WD_ST_CHG_FAIL,
+	CONN_DRY_RUN,		/* Expect disconnect after resync handshake. */
+	CREATE_BARRIER,		/* next P_DATA is preceded by a P_BARRIER */
+	STATE_SENT,		/* Do not change state/UUIDs while this is set */
+	CALLBACK_PENDING,	/* Whether we have a call_usermodehelper(, UMH_WAIT_PROC)
+				 * pending, from drbd worker context.
+				 * If set, bdi_write_congested() returns true,
+				 * so shrink_page_list() would not recurse into,
+				 * and potentially deadlock on, this drbd worker.
+				 */
+	DISCONNECT_SENT,
+};
+
+struct drbd_tconn {			/* is a resource from the config file */
+	char *name;			/* Resource name */
+	struct list_head all_tconn;	/* linked on global drbd_tconns */
+	struct kref kref;
+	struct idr volumes;		/* <tconn, vnr> to mdev mapping */
+	enum drbd_conns cstate;		/* Only C_STANDALONE to C_WF_REPORT_PARAMS */
+	unsigned susp:1;		/* IO suspended by user */
+	unsigned susp_nod:1;		/* IO suspended because no data */
+	unsigned susp_fen:1;		/* IO suspended because fence peer handler runs */
+	struct mutex cstate_mutex;	/* Protects graceful disconnects */
+
+	unsigned long flags;
+	struct net_conf *net_conf;	/* content protected by rcu */
+	struct mutex conf_update;	/* mutex for ready-copy-update of net_conf and disk_conf */
+	wait_queue_head_t ping_wait;	/* Woken upon reception of a ping, and a state change */
+	struct res_opts res_opts;
+
+	struct sockaddr_storage my_addr;
+	int my_addr_len;
+	struct sockaddr_storage peer_addr;
+	int peer_addr_len;
+
+	struct drbd_socket data;	/* data/barrier/cstate/parameter packets */
+	struct drbd_socket meta;	/* ping/ack (metadata) packets */
+	int agreed_pro_version;		/* actually used protocol version */
+	unsigned long last_received;	/* in jiffies, either socket */
+	unsigned int ko_count;
+
+	spinlock_t req_lock;
+
+	struct list_head transfer_log;	/* all requests not yet fully processed */
+
+	struct crypto_hash *cram_hmac_tfm;
+	struct crypto_hash *integrity_tfm;  /* checksums we compute, updates protected by tconn->data->mutex */
+	struct crypto_hash *peer_integrity_tfm;  /* checksums we verify, only accessed from receiver thread  */
+	struct crypto_hash *csums_tfm;
+	struct crypto_hash *verify_tfm;
+	void *int_dig_in;
+	void *int_dig_vv;
+
+	/* receiver side */
+	struct drbd_epoch *current_epoch;
+	spinlock_t epoch_lock;
+	unsigned int epochs;
+	enum write_ordering_e write_ordering;
+	atomic_t current_tle_nr;	/* transfer log epoch number */
+	unsigned current_tle_writes;	/* writes seen within this tl epoch */
+
+	unsigned long last_reconnect_jif;
+	struct drbd_thread receiver;
+	struct drbd_thread worker;
+	struct drbd_thread asender;
+	cpumask_var_t cpu_mask;
+
+	/* sender side */
+	struct drbd_work_queue sender_work;
+
+	struct {
+		/* whether this sender thread
+		 * has processed a single write yet. */
+		bool seen_any_write_yet;
+
+		/* Which barrier number to send with the next P_BARRIER */
+		int current_epoch_nr;
+
+		/* how many write requests have been sent
+		 * with req->epoch == current_epoch_nr.
+		 * If none, no P_BARRIER will be sent. */
+		unsigned current_epoch_writes;
+	} send;
 };
 
 struct drbd_conf {
-	unsigned long drbd_flags[(DRBD_N_FLAGS + BITS_PER_LONG -1)/BITS_PER_LONG];
+	struct drbd_tconn *tconn;
+	int vnr;			/* volume number within the connection */
+	struct kref kref;
+
+	/* things that are stored as / read from meta data on disk */
+	unsigned long flags;
 
 	/* configured by drbdsetup */
-	struct net_conf *net_conf; /* protected by get_net_conf() and put_net_conf() */
-	struct syncer_conf sync_conf;
 	struct drbd_backing_dev *ldev __protected_by(local);
 
 	sector_t p_size;     /* partner's disk size */
@@ -986,11 +907,7 @@ struct drbd_conf {
 	struct block_device *this_bdev;
 	struct gendisk	    *vdisk;
 
-	struct drbd_socket data; /* data/barrier/cstate/parameter packets */
-	struct drbd_socket meta; /* ping/ack (metadata) packets */
-	int agreed_pro_version;  /* actually used protocol version */
-	unsigned long last_received; /* in jiffies, either socket */
-	unsigned int ko_count;
+	unsigned long last_reattach_jif;
 	struct drbd_work  resync_work,
 			  unplug_work,
 			  go_diskless,
@@ -1010,10 +927,9 @@ struct drbd_conf {
 	/* Used after attach while negotiating new disk state. */
 	union drbd_state new_state_tmp;
 
-	union drbd_state state;
+	union drbd_dev_state state;
 	wait_queue_head_t misc_wait;
 	wait_queue_head_t state_wait;  /* upon each state change. */
-	wait_queue_head_t net_cnt_wait;
 	unsigned int send_cnt;
 	unsigned int recv_cnt;
 	unsigned int read_cnt;
@@ -1023,17 +939,12 @@ struct drbd_conf {
 	atomic_t ap_bio_cnt;	 /* Requests we need to complete */
 	atomic_t ap_pending_cnt; /* AP data packets on the wire, ack expected */
 	atomic_t rs_pending_cnt; /* RS request/data packets on the wire */
-	atomic_t unacked_cnt;	 /* Need to send replys for */
+	atomic_t unacked_cnt;	 /* Need to send replies for */
 	atomic_t local_cnt;	 /* Waiting for local completion */
-	atomic_t net_cnt;	 /* Users of net_conf */
-	spinlock_t req_lock;
-	struct drbd_tl_epoch *unused_spare_tle; /* for pre-allocation */
-	struct drbd_tl_epoch *newest_tle;
-	struct drbd_tl_epoch *oldest_tle;
-	struct list_head out_of_sequence_requests;
-	struct list_head barrier_acked_requests;
-	struct hlist_head *tl_hash;
-	unsigned int tl_hash_s;
+
+	/* Interval tree of pending local requests */
+	struct rb_root read_requests;
+	struct rb_root write_requests;
 
 	/* blocks to resync in this run [unit BM_BLOCK_SIZE] */
 	unsigned long rs_total;
@@ -1053,6 +964,7 @@ struct drbd_conf {
 	unsigned long rs_mark_time[DRBD_SYNC_MARKS];
 	/* current index into rs_mark_{left,time} */
 	int rs_last_mark;
+	unsigned long rs_last_bcast; /* [unit jiffies] */
 
 	/* where does the admin want us to start? (sector) */
 	sector_t ov_start_sector;
@@ -1064,14 +976,7 @@ struct drbd_conf {
 	/* size of out-of-sync range in sectors. */
 	sector_t ov_last_oos_size;
 	unsigned long ov_left; /* in bits */
-	struct crypto_hash *csums_tfm;
-	struct crypto_hash *verify_tfm;
 
-	unsigned long last_reattach_jif;
-	unsigned long last_reconnect_jif;
-	struct drbd_thread receiver;
-	struct drbd_thread worker;
-	struct drbd_thread asender;
 	struct drbd_bitmap *bitmap;
 	unsigned long bm_resync_fo; /* bit offset for drbd_bm_find_next */
 
@@ -1084,29 +989,19 @@ struct drbd_conf {
 
 	int open_cnt;
 	u64 *p_uuid;
-	struct drbd_epoch *current_epoch;
-	spinlock_t epoch_lock;
-	unsigned int epochs;
-	enum write_ordering_e write_ordering;
+
 	struct list_head active_ee; /* IO in progress (P_DATA gets written to disk) */
 	struct list_head sync_ee;   /* IO in progress (P_RS_DATA_REPLY gets written to disk) */
-	struct list_head done_ee;   /* send ack */
-	struct list_head read_ee;   /* IO in progress (any read) */
+	struct list_head done_ee;   /* need to send P_WRITE_ACK */
+	struct list_head read_ee;   /* [RS]P_DATA_REQUEST being read */
 	struct list_head net_ee;    /* zero-copy network send in progress */
-	struct hlist_head *ee_hash; /* is proteced by req_lock! */
-	unsigned int ee_hash_s;
-
-	/* this one is protected by ee_lock, single thread */
-	struct drbd_epoch_entry *last_write_w_barrier;
 
 	int next_barrier_nr;
-	struct hlist_head *app_reads_hash; /* is proteced by req_lock */
 	struct list_head resync_reads;
 	atomic_t pp_in_use;		/* allocated from page pool */
 	atomic_t pp_in_use_by_net;	/* sendpage()d, still referenced by tcp */
 	wait_queue_head_t ee_wait;
 	struct page *md_io_page;	/* one page buffer for md_io */
-	struct page *md_io_tmpp;	/* for logical_block_size != 512 */
 	struct drbd_md_io md_io;
 	atomic_t md_io_in_use;		/* protects the md_io, md_io_page and md_io_tmpp */
 	spinlock_t al_lock;
@@ -1115,22 +1010,16 @@ struct drbd_conf {
 	unsigned int al_tr_number;
 	int al_tr_cycle;
 	int al_tr_pos;   /* position of the next transaction in the journal */
-	struct crypto_hash *cram_hmac_tfm;
-	struct crypto_hash *integrity_w_tfm; /* to be used by the worker thread */
-	struct crypto_hash *integrity_r_tfm; /* to be used by the receiver thread */
-	void *int_dig_out;
-	void *int_dig_in;
-	void *int_dig_vv;
 	wait_queue_head_t seq_wait;
 	atomic_t packet_seq;
 	unsigned int peer_seq;
 	spinlock_t peer_seq_lock;
 	unsigned int minor;
 	unsigned long comm_bm_set; /* communicated number of set bits. */
-	cpumask_var_t cpu_mask;
 	struct bm_io_work bm_io_work;
 	u64 ed_uuid; /* UUID of the exposed data */
-	struct mutex state_mutex;
+	struct mutex own_state_mutex;
+	struct mutex *state_mutex; /* either own_state_mutex or mdev->tconn->cstate_mutex */
 	char congestion_reason;  /* Why we where congested... */
 	atomic_t rs_sect_in; /* for incoming resync data rate, SyncTarget */
 	atomic_t rs_sect_ev; /* for submitted resync data rate, both */
@@ -1138,46 +1027,16 @@ struct drbd_conf {
 	int rs_last_events;  /* counter of read or write "events" (unit sectors)
 			      * on the lower level device when we last looked. */
 	int c_sync_rate; /* current resync rate after syncer throttle magic */
-	struct fifo_buffer rs_plan_s; /* correction values of resync planer */
+	struct fifo_buffer *rs_plan_s; /* correction values of resync planer (RCU, tconn->conn_update) */
 	int rs_in_flight; /* resync sectors in flight (to proxy, in proxy and from proxy) */
-	int rs_planed;    /* resync sectors already planned */
 	atomic_t ap_in_flight; /* App sectors in flight (waiting for ack) */
 	unsigned int peer_max_bio_size;
 	unsigned int local_max_bio_size;
 };
 
-static inline void drbd_set_flag(struct drbd_conf *mdev, enum drbd_flag f)
-{
-	set_bit(f, &mdev->drbd_flags[0]);
-}
-
-static inline void drbd_clear_flag(struct drbd_conf *mdev, enum drbd_flag f)
-{