Merge commit 'drbd/drbd'

Documentation/blockdev/drbd/README.txt

+Description
+
+  DRBD is a shared-nothing, synchronously replicated block device. It
+  is designed to serve as a building block for high availability
+  clusters and in this context, is a "drop-in" replacement for shared
+  storage. Simplistically, you could see it as a network RAID 1.
+
+  Please visit http://www.drbd.org to find out more.
+
+The here included files are intended to help understand the implementation
+
+DRBD-8.3-data-packets.svg, DRBD-data-packets.svg  
+  relates some functions, and write packets.
+
+conn-states-8.dot, disk-states-8.dot, node-states-8.dot
+  The sub graphs of DRBD's state transitions

Documentation/blockdev/drbd/conn-states-8.dot

+digraph conn_states {
+	StandAllone  -> WFConnection   [ label = "ioctl_set_net()" ]
+	WFConnection -> Unconnected    [ label = "unable to bind()" ]
+	WFConnection -> WFReportParams [ label = "in connect() after accept" ]
+	WFReportParams -> StandAllone  [ label = "checks in receive_param()" ]
+	WFReportParams -> Connected    [ label = "in receive_param()" ]
+	WFReportParams -> WFBitMapS    [ label = "sync_handshake()" ]
+	WFReportParams -> WFBitMapT    [ label = "sync_handshake()" ]
+	WFBitMapS -> SyncSource        [ label = "receive_bitmap()" ]
+	WFBitMapT -> SyncTarget        [ label = "receive_bitmap()" ]
+	SyncSource -> Connected
+	SyncTarget -> Connected
+	SyncSource -> PausedSyncS
+	SyncTarget -> PausedSyncT
+	PausedSyncS -> SyncSource
+	PausedSyncT -> SyncTarget
+	Connected   -> WFConnection    [ label = "* on network error" ]
+}

Documentation/blockdev/drbd/disk-states-8.dot

+digraph disk_states {
+	Diskless -> Inconsistent       [ label = "ioctl_set_disk()" ]
+	Diskless -> Consistent         [ label = "ioctl_set_disk()" ]
+	Diskless -> Outdated           [ label = "ioctl_set_disk()" ]
+	Consistent -> Outdated         [ label = "receive_param()" ]
+	Consistent -> UpToDate         [ label = "receive_param()" ]
+	Consistent -> Inconsistent     [ label = "start resync" ]
+	Outdated   -> Inconsistent     [ label = "start resync" ]
+	UpToDate   -> Inconsistent     [ label = "ioctl_replicate" ]
+	Inconsistent -> UpToDate       [ label = "resync completed" ]
+	Consistent -> Failed           [ label = "io completion error" ]
+	Outdated   -> Failed           [ label = "io completion error" ]
+	UpToDate   -> Failed           [ label = "io completion error" ]
+	Inconsistent -> Failed         [ label = "io completion error" ]
+	Failed -> Diskless             [ label = "sending notify to peer" ]
+}

Documentation/blockdev/drbd/drbd-connection-state-overview.dot

+// vim: set sw=2 sts=2 :
+digraph {
+  rankdir=BT
+  bgcolor=white
+
+  node [shape=plaintext]
+  node [fontcolor=black]
+
+  StandAlone     [ style=filled,fillcolor=gray,label=StandAlone ]
+
+  node [fontcolor=lightgray]
+
+  Unconnected    [ label=Unconnected ]
+
+  CommTrouble [ shape=record,
+    label="{communication loss|{Timeout|BrokenPipe|NetworkFailure}}" ]
+
+  node [fontcolor=gray]
+
+  subgraph cluster_try_connect {
+    label="try to connect, handshake"
+    rank=max
+    WFConnection   [ label=WFConnection ]
+    WFReportParams [ label=WFReportParams ]
+  }
+
+  TearDown       [ label=TearDown ]
+
+  Connected      [ label=Connected,style=filled,fillcolor=green,fontcolor=black ]
+
+  node [fontcolor=lightblue]
+
+  StartingSyncS  [ label=StartingSyncS ]
+  StartingSyncT  [ label=StartingSyncT ]
+
+  subgraph cluster_bitmap_exchange {
+    node [fontcolor=red]
+    fontcolor=red
+    label="new application (WRITE?) requests blocked\lwhile bitmap is exchanged"
+
+    WFBitMapT      [ label=WFBitMapT ]
+    WFSyncUUID     [ label=WFSyncUUID ]
+    WFBitMapS      [ label=WFBitMapS ]
+  }
+
+  node [fontcolor=blue]
+
+  cluster_resync [ shape=record,label="{<any>resynchronisation process running\l'concurrent' application requests allowed|{{<T>PausedSyncT\nSyncTarget}|{<S>PausedSyncS\nSyncSource}}}" ]
+
+  node [shape=box,fontcolor=black]
+
+  // drbdadm [label="drbdadm connect"]
+  // handshake [label="drbd_connect()\ndrbd_do_handshake\ndrbd_sync_handshake() etc."]
+  // comm_error [label="communication trouble"]
+
+  //
+  // edges
+  // --------------------------------------
+
+  StandAlone -> Unconnected [ label="drbdadm connect" ]
+  Unconnected -> StandAlone  [ label="drbdadm disconnect\lor serious communication trouble" ]
+  Unconnected -> WFConnection [ label="receiver thread is started" ]
+  WFConnection -> WFReportParams [ headlabel="accept()\land/or                        \lconnect()\l" ]
+
+  WFReportParams -> StandAlone [ label="during handshake\lpeers do not agree\labout something essential" ]
+  WFReportParams -> Connected [ label="data identical\lno sync needed",color=green,fontcolor=green ]
+
+    WFReportParams -> WFBitMapS
+    WFReportParams -> WFBitMapT
+    WFBitMapT -> WFSyncUUID [minlen=0.1,constraint=false]
+
+      WFBitMapS -> cluster_resync:S
+      WFSyncUUID -> cluster_resync:T
+
+  edge [color=green]
+  cluster_resync:any -> Connected [ label="resnyc done",fontcolor=green ]
+
+  edge [color=red]
+  WFReportParams -> CommTrouble
+  Connected -> CommTrouble
+  cluster_resync:any -> CommTrouble
+  edge [color=black]
+  CommTrouble -> Unconnected [label="receiver thread is stopped" ]
+
+}

Documentation/blockdev/drbd/node-states-8.dot

+digraph node_states {
+	Secondary -> Primary           [ label = "ioctl_set_state()" ]
+	Primary   -> Secondary 	       [ label = "ioctl_set_state()" ]
+}
+
+digraph peer_states {
+	Secondary -> Primary           [ label = "recv state packet" ]
+	Primary   -> Secondary 	       [ label = "recv state packet" ]
+	Primary   -> Unknown 	       [ label = "connection lost" ]
+	Secondary  -> Unknown  	       [ label = "connection lost" ]
+	Unknown   -> Primary           [ label = "connected" ]
+	Unknown   -> Secondary         [ label = "connected" ]
+}
+

MAINTAINERS

@@ -1757,6 +1757,19 @@ S:	Maintained
 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
+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
+S:     Supported
+F:     drivers/block/drbd/
+F:     lib/lru_cache.c
+F:     Documentation/blockdev/drbd/
+
 DRIVER CORE, KOBJECTS, AND SYSFS
 M:	Greg Kroah-Hartman <gregkh@suse.de>
 T:	quilt kernel.org/pub/linux/kernel/people/gregkh/gregkh-2.6/

drivers/block/Kconfig

@@ -271,6 +271,8 @@ config BLK_DEV_CRYPTOLOOP
 	  instead, which can be configured to be on-disk compatible with the
 	  cryptoloop device.
 
+source "drivers/block/drbd/Kconfig"
+
 config BLK_DEV_NBD
 	tristate "Network block device support"
 	depends on NET

drivers/block/Makefile

@@ -36,5 +36,6 @@ obj-$(CONFIG_BLK_DEV_UB)	+= ub.o
 obj-$(CONFIG_BLK_DEV_HD)	+= hd.o
 
 obj-$(CONFIG_XEN_BLKDEV_FRONTEND)	+= xen-blkfront.o
+obj-$(CONFIG_BLK_DEV_DRBD)     += drbd/
 
 swim_mod-objs	:= swim.o swim_asm.o

drivers/block/drbd/Kconfig

+#
+# DRBD device driver configuration
+#
+
+comment "DRBD disabled because PROC_FS, INET or CONNECTOR not selected"
+	depends on !PROC_FS || !INET || !CONNECTOR
+
+config BLK_DEV_DRBD
+	tristate "DRBD Distributed Replicated Block Device support"
+	depends on PROC_FS && INET && CONNECTOR
+	select LRU_CACHE
+	default m
+	help
+
+	  NOTE: In order to authenticate connections you have to select
+	  CRYPTO_HMAC and a hash function as well.
+
+	  DRBD is a shared-nothing, synchronously replicated block device. It
+	  is designed to serve as a building block for high availability
+	  clusters and in this context, is a "drop-in" replacement for shared
+	  storage. Simplistically, you could see it as a network RAID 1.
+
+	  Each minor device has a role, which can be 'primary' or 'secondary'.
+	  On the node with the primary device the application is supposed to
+	  run and to access the device (/dev/drbdX). Every write is sent to
+	  the local 'lower level block device' and, across the network, to the
+	  node with the device in 'secondary' state.  The secondary device
+	  simply writes the data to its lower level block device.
+
+	  DRBD can also be used in dual-Primary mode (device writable on both
+	  nodes), which means it can exhibit shared disk semantics in a
+	  shared-nothing cluster.  Needless to say, on top of dual-Primary
+	  DRBD utilizing a cluster file system is necessary to maintain for
+	  cache coherency.
+
+	  For automatic failover you need a cluster manager (e.g. heartbeat).
+	  See also: http://www.drbd.org/, http://www.linux-ha.org
+
+	  If unsure, say M.
+
+config DRBD_TRACE
+	tristate "DRBD tracing"
+	depends on BLK_DEV_DRBD
+	select TRACEPOINTS
+	default m
+	help
+
+	  Say Y here if you want to be able to trace various events in DRBD.
+
+	  If unsure, say M.
+
+config DRBD_FAULT_INJECTION
+	bool "DRBD fault injection"
+	depends on BLK_DEV_DRBD
+	help
+
+	  Say Y here if you want to simulate IO errors, in order to test DRBD's
+	  behavior.
+
+	  The actual simulation of IO errors is done by writing 3 values to
+	  /sys/module/drbd/parameters/
+
+	  enable_faults: bitmask of...
+	  1	meta data write
+	  2               read
+	  4	resync data write
+	  8	            read
+	  16	data write
+	  32	data read
+	  64	read ahead
+	  128	kmalloc of bitmap
+	  256	allocation of EE (epoch_entries)
+
+	  fault_devs: bitmask of minor numbers
+	  fault_rate: frequency in percent
+
+	  Example: Simulate data write errors on /dev/drbd0 with a probability of 5%.
+		echo 16 > /sys/module/drbd/parameters/enable_faults
+		echo 1 > /sys/module/drbd/parameters/fault_devs
+		echo 5 > /sys/module/drbd/parameters/fault_rate
+
+	  If unsure, say N.

drivers/block/drbd/Makefile

+drbd-y := drbd_bitmap.o drbd_proc.o
+drbd-y += drbd_worker.o drbd_receiver.o drbd_req.o drbd_actlog.o
+drbd-y += drbd_main.o drbd_strings.o drbd_nl.o
+
+drbd_trace-y := drbd_tracing.o
+
+obj-$(CONFIG_BLK_DEV_DRBD)     += drbd.o
+obj-$(CONFIG_DRBD_TRACE)       += drbd_trace.o

drivers/block/drbd/drbd_proc.c

+/*
+   drbd_proc.c
+
+   This file is part of DRBD by Philipp Reisner and Lars Ellenberg.
+
+   Copyright (C) 2001-2008, LINBIT Information Technologies GmbH.
+   Copyright (C) 1999-2008, Philipp Reisner <philipp.reisner@linbit.com>.
+   Copyright (C) 2002-2008, Lars Ellenberg <lars.ellenberg@linbit.com>.
+
+   drbd is free software; you can redistribute it and/or modify
+   it under the terms of the GNU General Public License as published by
+   the Free Software Foundation; either version 2, or (at your option)
+   any later version.
+
+   drbd is distributed in the hope that it will be useful,
+   but WITHOUT ANY WARRANTY; without even the implied warranty of
+   MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+   GNU General Public License for more details.
+
+   You should have received a copy of the GNU General Public License
+   along with drbd; see the file COPYING.  If not, write to
+   the Free Software Foundation, 675 Mass Ave, Cambridge, MA 02139, USA.
+
+ */
+
+#include <linux/autoconf.h>
+#include <linux/module.h>
+
+#include <asm/uaccess.h>
+#include <linux/fs.h>
+#include <linux/file.h>
+#include <linux/slab.h>
+#include <linux/proc_fs.h>
+#include <linux/seq_file.h>
+#include <linux/drbd.h>
+#include "drbd_int.h"
+
+static int drbd_proc_open(struct inode *inode, struct file *file);
+
+
+struct proc_dir_entry *drbd_proc;
+struct file_operations drbd_proc_fops = {
+	.owner		= THIS_MODULE,
+	.open		= drbd_proc_open,
+	.read		= seq_read,
+	.llseek		= seq_lseek,
+	.release	= single_release,
+};
+
+
+/*lge
+ * progress bars shamelessly adapted from driver/md/md.c
+ * output looks like
+ *	[=====>..............] 33.5% (23456/123456)
+ *	finish: 2:20:20 speed: 6,345 (6,456) K/sec
+ */
+static void drbd_syncer_progress(struct drbd_conf *mdev, struct seq_file *seq)
+{
+	unsigned long db, dt, dbdt, rt, rs_left;
+	unsigned int res;
+	int i, x, y;
+
+	drbd_get_syncer_progress(mdev, &rs_left, &res);
+
+	x = res/50;
+	y = 20-x;
+	seq_printf(seq, "\t[");
+	for (i = 1; i < x; i++)
+		seq_printf(seq, "=");
+	seq_printf(seq, ">");
+	for (i = 0; i < y; i++)
+		seq_printf(seq, ".");
+	seq_printf(seq, "] ");
+
+	seq_printf(seq, "sync'ed:%3u.%u%% ", res / 10, res % 10);
+	/* if more than 1 GB display in MB */
+	if (mdev->rs_total > 0x100000L)
+		seq_printf(seq, "(%lu/%lu)M\n\t",
+			    (unsigned long) Bit2KB(rs_left >> 10),
+			    (unsigned long) Bit2KB(mdev->rs_total >> 10));
+	else
+		seq_printf(seq, "(%lu/%lu)K\n\t",
+			    (unsigned long) Bit2KB(rs_left),
+			    (unsigned long) Bit2KB(mdev->rs_total));
+
+	/* see drivers/md/md.c
+	 * We do not want to overflow, so the order of operands and
+	 * the * 100 / 100 trick are important. We do a +1 to be
+	 * safe against division by zero. We only estimate anyway.
+	 *
+	 * dt: time from mark until now
+	 * db: blocks written from mark until now
+	 * rt: remaining time
+	 */
+	dt = (jiffies - mdev->rs_mark_time) / HZ;
+
+	if (dt > 20) {
+		/* if we made no update to rs_mark_time for too long,
+		 * we are stalled. show that. */
+		seq_printf(seq, "stalled\n");
+		return;
+	}
+
+	if (!dt)
+		dt++;
+	db = mdev->rs_mark_left - rs_left;
+	rt = (dt * (rs_left / (db/100+1)))/100; /* seconds */
+
+	seq_printf(seq, "finish: %lu:%02lu:%02lu",
+		rt / 3600, (rt % 3600) / 60, rt % 60);
+
+	/* current speed average over (SYNC_MARKS * SYNC_MARK_STEP) jiffies */
+	dbdt = Bit2KB(db/dt);
+	if (dbdt > 1000)
+		seq_printf(seq, " speed: %ld,%03ld",
+			dbdt/1000, dbdt % 1000);
+	else
+		seq_printf(seq, " speed: %ld", dbdt);
+
+	/* mean speed since syncer started
+	 * we do account for PausedSync periods */
+	dt = (jiffies - mdev->rs_start - mdev->rs_paused) / HZ;
+	if (dt <= 0)
+		dt = 1;
+	db = mdev->rs_total - rs_left;
+	dbdt = Bit2KB(db/dt);
+	if (dbdt > 1000)
+		seq_printf(seq, " (%ld,%03ld)",
+			dbdt/1000, dbdt % 1000);
+	else
+		seq_printf(seq, " (%ld)", dbdt);
+
+	seq_printf(seq, " K/sec\n");
+}
+
+static void resync_dump_detail(struct seq_file *seq, struct lc_element *e)
+{
+	struct bm_extent *bme = lc_entry(e, struct bm_extent, lce);
+
+	seq_printf(seq, "%5d %s %s\n", bme->rs_left,
+		   bme->flags & BME_NO_WRITES ? "NO_WRITES" : "---------",
+		   bme->flags & BME_LOCKED ? "LOCKED" : "------"
+		   );
+}
+
+static int drbd_seq_show(struct seq_file *seq, void *v)
+{
+	int i, hole = 0;
+	const char *sn;
+	struct drbd_conf *mdev;
+
+	static char write_ordering_chars[] = {
+		[WO_none] = 'n',
+		[WO_drain_io] = 'd',
+		[WO_bdev_flush] = 'f',
+		[WO_bio_barrier] = 'b',
+	};
+
+	seq_printf(seq, "version: " REL_VERSION " (api:%d/proto:%d-%d)\n%s\n",
+		   API_VERSION, PRO_VERSION_MIN, PRO_VERSION_MAX, drbd_buildtag());
+
+	/*
+	  cs .. connection state
+	  ro .. node role (local/remote)
+	  ds .. disk state (local/remote)
+	     protocol
+	     various flags
+	  ns .. network send
+	  nr .. network receive
+	  dw .. disk write
+	  dr .. disk read
+	  al .. activity log write count
+	  bm .. bitmap update write count
+	  pe .. pending (waiting for ack or data reply)
+	  ua .. unack'd (still need to send ack or data reply)
+	  ap .. application requests accepted, but not yet completed
+	  ep .. number of epochs currently "on the fly", P_BARRIER_ACK pending
+	  wo .. write ordering mode currently in use
+	 oos .. known out-of-sync kB
+	*/
+
+	for (i = 0; i < minor_count; i++) {
+		mdev = minor_to_mdev(i);
+		if (!mdev) {
+			hole = 1;
+			continue;
+		}
+		if (hole) {
+			hole = 0;
+			seq_printf(seq, "\n");
+		}
+
+		sn = drbd_conn_str(mdev->state.conn);
+
+		if (mdev->state.conn == C_STANDALONE &&
+		    mdev->state.disk == D_DISKLESS &&
+		    mdev->state.role == R_SECONDARY) {
+			seq_printf(seq, "%2d: cs:Unconfigured\n", i);
+		} else {
+			seq_printf(seq,
+			   "%2d: cs:%s ro:%s/%s ds:%s/%s %c %c%c%c%c%c\n"
+			   "    ns:%u nr:%u dw:%u dr:%u al:%u bm:%u "
+			   "lo:%d pe:%d ua:%d ap:%d ep:%d wo:%c",
+			   i, sn,
+			   drbd_role_str(mdev->state.role),
+			   drbd_role_str(mdev->state.peer),
+			   drbd_disk_str(mdev->state.disk),
+			   drbd_disk_str(mdev->state.pdsk),
+			   (mdev->net_conf == NULL ? ' ' :
+			    (mdev->net_conf->wire_protocol - DRBD_PROT_A+'A')),
+			   mdev->state.susp ? 's' : 'r',
+			   mdev->state.aftr_isp ? 'a' : '-',
+			   mdev->state.peer_isp ? 'p' : '-',
+			   mdev->state.user_isp ? 'u' : '-',
+			   mdev->congestion_reason ?: '-',
+			   mdev->send_cnt/2,
+			   mdev->recv_cnt/2,
+			   mdev->writ_cnt/2,
+			   mdev->read_cnt/2,
+			   mdev->al_writ_cnt,
+			   mdev->bm_writ_cnt,
+			   atomic_read(&mdev->local_cnt),
+			   atomic_read(&mdev->ap_pending_cnt) +
+			   atomic_read(&mdev->rs_pending_cnt),
+			   atomic_read(&mdev->unacked_cnt),
+			   atomic_read(&mdev->ap_bio_cnt),
+			   mdev->epochs,
+			   write_ordering_chars[mdev->write_ordering]
+			);
+			seq_printf(seq, " oos:%lu\n",
+				   Bit2KB(drbd_bm_total_weight(mdev)));
+		}
+		if (mdev->state.conn == C_SYNC_SOURCE ||
+		    mdev->state.conn == C_SYNC_TARGET)
+			drbd_syncer_progress(mdev, seq);
+
+		if (mdev->state.conn == C_VERIFY_S || mdev->state.conn == C_VERIFY_T)
+			seq_printf(seq, "\t%3d%%      %lu/%lu\n",
+				   (int)((mdev->rs_total-mdev->ov_left) /
+					 (mdev->rs_total/100+1)),
+				   mdev->rs_total - mdev->ov_left,
+				   mdev->rs_total);
+
+		if (proc_details >= 1 && get_ldev_if_state(mdev, D_FAILED)) {
+			lc_seq_printf_stats(seq, mdev->resync);
+			lc_seq_printf_stats(seq, mdev->act_log);
+			put_ldev(mdev);
+		}
+
+		if (proc_details >= 2) {
+			if (mdev->resync) {
+				lc_seq_dump_details(seq, mdev->resync, "rs_left",
+					resync_dump_detail);
+			}
+		}
+	}
+
+	return 0;
+}
+
+static int drbd_proc_open(struct inode *inode, struct file *file)
+{
+	return single_open(file, drbd_seq_show, PDE(inode)->data);
+}
+
+/* PROC FS stuff end */

drivers/block/drbd/drbd_strings.c

+/*
+  drbd.h
+
+  This file is part of DRBD by Philipp Reisner and Lars Ellenberg.
+
+  Copyright (C) 2003-2008, LINBIT Information Technologies GmbH.
+  Copyright (C) 2003-2008, Philipp Reisner <philipp.reisner@linbit.com>.
+  Copyright (C) 2003-2008, Lars Ellenberg <lars.ellenberg@linbit.com>.
+
+  drbd is free software; you can redistribute it and/or modify
+  it under the terms of the GNU General Public License as published by
+  the Free Software Foundation; either version 2, or (at your option)
+  any later version.
+
+  drbd is distributed in the hope that it will be useful,
+  but WITHOUT ANY WARRANTY; without even the implied warranty of
+  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+  GNU General Public License for more details.
+
+  You should have received a copy of the GNU General Public License
+  along with drbd; see the file COPYING.  If not, write to
+  the Free Software Foundation, 675 Mass Ave, Cambridge, MA 02139, USA.
+
+*/
+
+#include <linux/drbd.h>
+
+static const char *drbd_conn_s_names[] = {
+	[C_STANDALONE]       = "StandAlone",
+	[C_DISCONNECTING]    = "Disconnecting",
+	[C_UNCONNECTED]      = "Unconnected",
+	[C_TIMEOUT]          = "Timeout",
+	[C_BROKEN_PIPE]      = "BrokenPipe",
+	[C_NETWORK_FAILURE]  = "NetworkFailure",
+	[C_PROTOCOL_ERROR]   = "ProtocolError",
+	[C_WF_CONNECTION]    = "WFConnection",
+	[C_WF_REPORT_PARAMS] = "WFReportParams",
+	[C_TEAR_DOWN]        = "TearDown",
+	[C_CONNECTED]        = "Connected",
+	[C_STARTING_SYNC_S]  = "StartingSyncS",
+	[C_STARTING_SYNC_T]  = "StartingSyncT",
+	[C_WF_BITMAP_S]      = "WFBitMapS",
+	[C_WF_BITMAP_T]      = "WFBitMapT",
+	[C_WF_SYNC_UUID]     = "WFSyncUUID",
+	[C_SYNC_SOURCE]      = "SyncSource",
+	[C_SYNC_TARGET]      = "SyncTarget",
+	[C_PAUSED_SYNC_S]    = "PausedSyncS",
+	[C_PAUSED_SYNC_T]    = "PausedSyncT",
+	[C_VERIFY_S]         = "VerifyS",
+	[C_VERIFY_T]         = "VerifyT",
+};
+
+static const char *drbd_role_s_names[] = {
+	[R_PRIMARY]   = "Primary",
+	[R_SECONDARY] = "Secondary",
+	[R_UNKNOWN]   = "Unknown"
+};
+
+static const char *drbd_disk_s_names[] = {
+	[D_DISKLESS]     = "Diskless",
+	[D_ATTACHING]    = "Attaching",
+	[D_FAILED]       = "Failed",
+	[D_NEGOTIATING]  = "Negotiating",
+	[D_INCONSISTENT] = "Inconsistent",
+	[D_OUTDATED]     = "Outdated",
+	[D_UNKNOWN]      = "DUnknown",
+	[D_CONSISTENT]   = "Consistent",
+	[D_UP_TO_DATE]   = "UpToDate",
+};
+
+static const char *drbd_state_sw_errors[] = {
+	[-SS_TWO_PRIMARIES] = "Multiple primaries not allowed by config",
+	[-SS_NO_UP_TO_DATE_DISK] = "Refusing to be Primary without at least one UpToDate disk",
+	[-SS_NO_LOCAL_DISK] = "Can not resync without local disk",
+	[-SS_NO_REMOTE_DISK] = "Can not resync without remote disk",
+	[-SS_CONNECTED_OUTDATES] = "Refusing to be Outdated while Connected",
+	[-SS_PRIMARY_NOP] = "Refusing to be Primary while peer is not outdated",
+	[-SS_RESYNC_RUNNING] = "Can not start OV/resync since it is already active",
+	[-SS_ALREADY_STANDALONE] = "Can not disconnect a StandAlone device",
+	[-SS_CW_FAILED_BY_PEER] = "State change was refused by peer node",
+	[-SS_IS_DISKLESS] = "Device is diskless, the requested operation requires a disk",
+	[-SS_DEVICE_IN_USE] = "Device is held open by someone",
+	[-SS_NO_NET_CONFIG] = "Have no net/connection configuration",
+	[-SS_NO_VERIFY_ALG] = "Need a verify algorithm to start online verify",
+	[-SS_NEED_CONNECTION] = "Need a connection to start verify or resync",
+	[-SS_NOT_SUPPORTED] = "Peer does not support protocol",
+	[-SS_LOWER_THAN_OUTDATED] = "Disk state is lower than outdated",
+	[-SS_IN_TRANSIENT_STATE] = "In transient state, retry after next state change",
+	[-SS_CONCURRENT_ST_CHG] = "Concurrent state changes detected and aborted",
+};
+
+const char *drbd_conn_str(enum drbd_conns s)
+{
+	/* enums are unsigned... */
+	return s > C_PAUSED_SYNC_T ? "TOO_LARGE" : drbd_conn_s_names[s];
+}
+
+const char *drbd_role_str(enum drbd_role s)
+{
+	return s > R_SECONDARY   ? "TOO_LARGE" : drbd_role_s_names[s];
+}
+
+const char *drbd_disk_str(enum drbd_disk_state s)
+{
+	return s > D_UP_TO_DATE    ? "TOO_LARGE" : drbd_disk_s_names[s];
+}
+
+const char *drbd_set_st_err_str(enum drbd_state_ret_codes err)
+{
+	return err <= SS_AFTER_LAST_ERROR ? "TOO_SMALL" :
+	       err > SS_TWO_PRIMARIES ? "TOO_LARGE"
+			: drbd_state_sw_errors[-err];
+}

drivers/block/drbd/drbd_tracing.h

+/*
+   drbd_tracing.h
+
+   This file is part of DRBD by Philipp Reisner and Lars Ellenberg.
+
+   Copyright (C) 2003-2008, LINBIT Information Technologies GmbH.
+   Copyright (C) 2003-2008, Philipp Reisner <philipp.reisner@linbit.com>.
+   Copyright (C) 2003-2008, Lars Ellenberg <lars.ellenberg@linbit.com>.
+
+   drbd is free software; you can redistribute it and/or modify
+   it under the terms of the GNU General Public License as published by
+   the Free Software Foundation; either version 2, or (at your option)
+   any later version.
+
+   drbd is distributed in the hope that it will be useful,
+   but WITHOUT ANY WARRANTY; without even the implied warranty of
+   MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+   GNU General Public License for more details.
+
+   You should have received a copy of the GNU General Public License
+   along with drbd; see the file COPYING.  If not, write to
+   the Free Software Foundation, 675 Mass Ave, Cambridge, MA 02139, USA.
+
+ */
+
+#ifndef DRBD_TRACING_H
+#define DRBD_TRACING_H
+
+#include <linux/tracepoint.h>
+#include "drbd_int.h"
+#include "drbd_req.h"
+
+enum {
+	TRACE_LVL_ALWAYS = 0,
+	TRACE_LVL_SUMMARY,
+	TRACE_LVL_METRICS,
+	TRACE_LVL_ALL,
+	TRACE_LVL_MAX
+};
+
+DECLARE_TRACE(drbd_unplug,
+	TP_PROTO(struct drbd_conf *mdev, char* msg),
+	TP_ARGS(mdev, msg));
+
+DECLARE_TRACE(drbd_uuid,
+	TP_PROTO(struct drbd_conf *mdev, enum drbd_uuid_index index),
+	TP_ARGS(mdev, index));
+
+DECLARE_TRACE(drbd_ee,
+	TP_PROTO(struct drbd_conf *mdev, struct drbd_epoch_entry *e, char* msg),
+	TP_ARGS(mdev, e, msg));
+
+DECLARE_TRACE(drbd_md_io,
+	TP_PROTO(struct drbd_conf *mdev, int rw, struct drbd_backing_dev *bdev),
+	TP_ARGS(mdev, rw, bdev));
+
+DECLARE_TRACE(drbd_epoch,
+	TP_PROTO(struct drbd_conf *mdev, struct drbd_epoch *epoch, enum epoch_event ev),
+	TP_ARGS(mdev, epoch, ev));
+
+DECLARE_TRACE(drbd_netlink,
+	TP_PROTO(void *data, int is_req),
+	TP_ARGS(data, is_req));
+
+DECLARE_TRACE(drbd_actlog,
+	TP_PROTO(struct drbd_conf *mdev, sector_t sector, char* msg),
+	TP_ARGS(mdev, sector, msg));
+
+DECLARE_TRACE(drbd_bio,
+	TP_PROTO(struct drbd_conf *mdev, const char *pfx, struct bio *bio, int complete,
+		 struct drbd_request *r),
+	TP_ARGS(mdev, pfx, bio, complete, r));
+
+DECLARE_TRACE(drbd_req,
+	TP_PROTO(struct drbd_request *req, enum drbd_req_event what, char *msg),
+	      TP_ARGS(req, what, msg));
+
+DECLARE_TRACE(drbd_packet,
+	TP_PROTO(struct drbd_conf *mdev, struct socket *sock,
+		 int recv, union p_polymorph *p, char *file, int line),
+	TP_ARGS(mdev, sock, recv, p, file, line));
+
+DECLARE_TRACE(_drbd_resync,
+	TP_PROTO(struct drbd_conf *mdev, int level, const char *fmt, va_list args),
+	TP_ARGS(mdev, level, fmt, args));
+
+#endif

lib/Kconfig

@@ -200,4 +200,7 @@ config NLATTR
 config GENERIC_ATOMIC64
        bool
 
+config LRU_CACHE
+	tristate
+
 endmenu

lib/Makefile

@@ -91,6 +91,8 @@ obj-$(CONFIG_DYNAMIC_DEBUG) += dynamic_debug.o
 
 obj-$(CONFIG_NLATTR) += nlattr.o
 
+obj-$(CONFIG_LRU_CACHE) += lru_cache.o
+
 obj-$(CONFIG_DMA_API_DEBUG) += dma-debug.o
 
 obj-$(CONFIG_GENERIC_CSUM) += checksum.o