Initial commit; kernel source import

drivers/block/drbd/Kconfig

@@ -0,0 +1,73 @@
+#
+# DRBD device driver configuration
+#
+
+comment "DRBD disabled because PROC_FS or INET not selected"
+	depends on PROC_FS='n' || INET='n'
+
+config BLK_DEV_DRBD
+	tristate "DRBD Distributed Replicated Block Device support"
+	depends on PROC_FS && INET
+	select LRU_CACHE
+	select LIBCRC32C
+	default n
+	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 N.
+
+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 peer_requests
+	  512	insert data corruption on receiving side
+
+	  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

@@ -0,0 +1,7 @@
+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-y += drbd_interval.o drbd_state.o
+drbd-y += drbd_nla.o
+
+obj-$(CONFIG_BLK_DEV_DRBD)     += drbd.o

drivers/block/drbd/drbd_interval.c

@@ -0,0 +1,207 @@
+#include <asm/bug.h>
+#include <linux/rbtree_augmented.h>
+#include "drbd_interval.h"
+
+/**
+ * interval_end  -  return end of @node
+ */
+static inline
+sector_t interval_end(struct rb_node *node)
+{
+	struct drbd_interval *this = rb_entry(node, struct drbd_interval, rb);
+	return this->end;
+}
+
+/**
+ * compute_subtree_last  -  compute end of @node
+ *
+ * The end of an interval is the highest (start + (size >> 9)) value of this
+ * node and of its children.  Called for @node and its parents whenever the end
+ * may have changed.
+ */
+static inline sector_t
+compute_subtree_last(struct drbd_interval *node)
+{
+	sector_t max = node->sector + (node->size >> 9);
+
+	if (node->rb.rb_left) {
+		sector_t left = interval_end(node->rb.rb_left);
+		if (left > max)
+			max = left;
+	}
+	if (node->rb.rb_right) {
+		sector_t right = interval_end(node->rb.rb_right);
+		if (right > max)
+			max = right;
+	}
+	return max;
+}
+
+static void augment_propagate(struct rb_node *rb, struct rb_node *stop)
+{
+	while (rb != stop) {
+		struct drbd_interval *node = rb_entry(rb, struct drbd_interval, rb);
+		sector_t subtree_last = compute_subtree_last(node);
+		if (node->end == subtree_last)
+			break;
+		node->end = subtree_last;
+		rb = rb_parent(&node->rb);
+	}
+}
+
+static void augment_copy(struct rb_node *rb_old, struct rb_node *rb_new)
+{
+	struct drbd_interval *old = rb_entry(rb_old, struct drbd_interval, rb);
+	struct drbd_interval *new = rb_entry(rb_new, struct drbd_interval, rb);
+
+	new->end = old->end;
+}
+
+static void augment_rotate(struct rb_node *rb_old, struct rb_node *rb_new)
+{
+	struct drbd_interval *old = rb_entry(rb_old, struct drbd_interval, rb);
+	struct drbd_interval *new = rb_entry(rb_new, struct drbd_interval, rb);
+
+	new->end = old->end;
+	old->end = compute_subtree_last(old);
+}
+
+static const struct rb_augment_callbacks augment_callbacks = {
+	augment_propagate,
+	augment_copy,
+	augment_rotate,
+};
+
+/**
+ * drbd_insert_interval  -  insert a new interval into a tree
+ */
+bool
+drbd_insert_interval(struct rb_root *root, struct drbd_interval *this)
+{
+	struct rb_node **new = &root->rb_node, *parent = NULL;
+
+	BUG_ON(!IS_ALIGNED(this->size, 512));
+
+	while (*new) {
+		struct drbd_interval *here =
+			rb_entry(*new, struct drbd_interval, rb);
+
+		parent = *new;
+		if (this->sector < here->sector)
+			new = &(*new)->rb_left;
+		else if (this->sector > here->sector)
+			new = &(*new)->rb_right;
+		else if (this < here)
+			new = &(*new)->rb_left;
+		else if (this > here)
+			new = &(*new)->rb_right;
+		else
+			return false;
+	}
+
+	rb_link_node(&this->rb, parent, new);
+	rb_insert_augmented(&this->rb, root, &augment_callbacks);
+	return true;
+}
+
+/**
+ * drbd_contains_interval  -  check if a tree contains a given interval
+ * @sector:	start sector of @interval
+ * @interval:	may not be a valid pointer
+ *
+ * Returns if the tree contains the node @interval with start sector @start.
+ * Does not dereference @interval until @interval is known to be a valid object
+ * in @tree.  Returns %false if @interval is in the tree but with a different
+ * sector number.
+ */
+bool
+drbd_contains_interval(struct rb_root *root, sector_t sector,
+		       struct drbd_interval *interval)
+{
+	struct rb_node *node = root->rb_node;
+
+	while (node) {
+		struct drbd_interval *here =
+			rb_entry(node, struct drbd_interval, rb);
+
+		if (sector < here->sector)
+			node = node->rb_left;
+		else if (sector > here->sector)
+			node = node->rb_right;
+		else if (interval < here)
+			node = node->rb_left;
+		else if (interval > here)
+			node = node->rb_right;
+		else
+			return true;
+	}
+	return false;
+}
+
+/**
+ * drbd_remove_interval  -  remove an interval from a tree
+ */
+void
+drbd_remove_interval(struct rb_root *root, struct drbd_interval *this)
+{
+	rb_erase_augmented(&this->rb, root, &augment_callbacks);
+}
+
+/**
+ * drbd_find_overlap  - search for an interval overlapping with [sector, sector + size)
+ * @sector:	start sector
+ * @size:	size, aligned to 512 bytes
+ *
+ * Returns an interval overlapping with [sector, sector + size), or NULL if
+ * there is none.  When there is more than one overlapping interval in the
+ * tree, the interval with the lowest start sector is returned, and all other
+ * overlapping intervals will be on the right side of the tree, reachable with
+ * rb_next().
+ */
+struct drbd_interval *
+drbd_find_overlap(struct rb_root *root, sector_t sector, unsigned int size)
+{
+	struct rb_node *node = root->rb_node;
+	struct drbd_interval *overlap = NULL;
+	sector_t end = sector + (size >> 9);
+
+	BUG_ON(!IS_ALIGNED(size, 512));
+
+	while (node) {
+		struct drbd_interval *here =
+			rb_entry(node, struct drbd_interval, rb);
+
+		if (node->rb_left &&
+		    sector < interval_end(node->rb_left)) {
+			/* Overlap if any must be on left side */
+			node = node->rb_left;
+		} else if (here->sector < end &&
+			   sector < here->sector + (here->size >> 9)) {
+			overlap = here;
+			break;
+		} else if (sector >= here->sector) {
+			/* Overlap if any must be on right side */
+			node = node->rb_right;
+		} else
+			break;
+	}
+	return overlap;
+}
+
+struct drbd_interval *
+drbd_next_overlap(struct drbd_interval *i, sector_t sector, unsigned int size)
+{
+	sector_t end = sector + (size >> 9);
+	struct rb_node *node;
+
+	for (;;) {
+		node = rb_next(&i->rb);
+		if (!node)
+			return NULL;
+		i = rb_entry(node, struct drbd_interval, rb);
+		if (i->sector >= end)
+			return NULL;
+		if (sector < i->sector + (i->size >> 9))
+			return i;
+	}
+}

drivers/block/drbd/drbd_interval.h

@@ -0,0 +1,40 @@
+#ifndef __DRBD_INTERVAL_H
+#define __DRBD_INTERVAL_H
+
+#include <linux/types.h>
+#include <linux/rbtree.h>
+
+struct drbd_interval {
+	struct rb_node rb;
+	sector_t sector;	/* start sector of the interval */
+	unsigned int size;	/* size in bytes */
+	sector_t end;		/* highest interval end in subtree */
+	int local:1		/* local or remote request? */;
+	int waiting:1;
+};
+
+static inline void drbd_clear_interval(struct drbd_interval *i)
+{
+	RB_CLEAR_NODE(&i->rb);
+}
+
+static inline bool drbd_interval_empty(struct drbd_interval *i)
+{
+	return RB_EMPTY_NODE(&i->rb);
+}
+
+extern bool drbd_insert_interval(struct rb_root *, struct drbd_interval *);
+extern bool drbd_contains_interval(struct rb_root *, sector_t,
+				   struct drbd_interval *);
+extern void drbd_remove_interval(struct rb_root *, struct drbd_interval *);
+extern struct drbd_interval *drbd_find_overlap(struct rb_root *, sector_t,
+					unsigned int);
+extern struct drbd_interval *drbd_next_overlap(struct drbd_interval *, sector_t,
+					unsigned int);
+
+#define drbd_for_each_overlap(i, root, sector, size)		\
+	for (i = drbd_find_overlap(root, sector, size);		\
+	     i;							\
+	     i = drbd_next_overlap(i, sector, size))
+
+#endif  /* __DRBD_INTERVAL_H */

drivers/block/drbd/drbd_nla.c

@@ -0,0 +1,55 @@
+#include "drbd_wrappers.h"
+#include <linux/kernel.h>
+#include <net/netlink.h>
+#include <linux/drbd_genl_api.h>
+#include "drbd_nla.h"
+
+static int drbd_nla_check_mandatory(int maxtype, struct nlattr *nla)
+{
+	struct nlattr *head = nla_data(nla);
+	int len = nla_len(nla);
+	int rem;
+
+	/*
+	 * validate_nla (called from nla_parse_nested) ignores attributes
+	 * beyond maxtype, and does not understand the DRBD_GENLA_F_MANDATORY flag.
+	 * In order to have it validate attributes with the DRBD_GENLA_F_MANDATORY
+	 * flag set also, check and remove that flag before calling
+	 * nla_parse_nested.
+	 */
+
+	nla_for_each_attr(nla, head, len, rem) {
+		if (nla->nla_type & DRBD_GENLA_F_MANDATORY) {
+			nla->nla_type &= ~DRBD_GENLA_F_MANDATORY;
+			if (nla_type(nla) > maxtype)
+				return -EOPNOTSUPP;
+		}
+	}
+	return 0;
+}
+
+int drbd_nla_parse_nested(struct nlattr *tb[], int maxtype, struct nlattr *nla,
+			  const struct nla_policy *policy)
+{
+	int err;
+
+	err = drbd_nla_check_mandatory(maxtype, nla);
+	if (!err)
+		err = nla_parse_nested(tb, maxtype, nla, policy);
+
+	return err;
+}
+
+struct nlattr *drbd_nla_find_nested(int maxtype, struct nlattr *nla, int attrtype)
+{
+	int err;
+	/*
+	 * If any nested attribute has the DRBD_GENLA_F_MANDATORY flag set and
+	 * we don't know about that attribute, reject all the nested
+	 * attributes.
+	 */
+	err = drbd_nla_check_mandatory(maxtype, nla);
+	if (err)
+		return ERR_PTR(err);
+	return nla_find_nested(nla, attrtype);
+}

drivers/block/drbd/drbd_nla.h

@@ -0,0 +1,8 @@
+#ifndef __DRBD_NLA_H
+#define __DRBD_NLA_H
+
+extern int drbd_nla_parse_nested(struct nlattr *tb[], int maxtype, struct nlattr *nla,
+				 const struct nla_policy *policy);
+extern struct nlattr *drbd_nla_find_nested(int maxtype, struct nlattr *nla, int attrtype);
+
+#endif  /* __DRBD_NLA_H */

drivers/block/drbd/drbd_proc.c

@@ -0,0 +1,333 @@
+/*
+   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/module.h>
+
+#include <asm/uaccess.h>
+#include <linux/fs.h>
+#include <linux/file.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);
+static int drbd_proc_release(struct inode *inode, struct file *file);
+
+
+struct proc_dir_entry *drbd_proc;
+const struct file_operations drbd_proc_fops = {
+	.owner		= THIS_MODULE,
+	.open		= drbd_proc_open,
+	.read		= seq_read,
+	.llseek		= seq_lseek,
+	.release	= drbd_proc_release,
+};
+
+void seq_printf_with_thousands_grouping(struct seq_file *seq, long v)
+{
+	/* v is in kB/sec. We don't expect TiByte/sec yet. */
+	if (unlikely(v >= 1000000)) {
+		/* cool: > GiByte/s */
+		seq_printf(seq, "%ld,", v / 1000000);
+		v %= 1000000;
+		seq_printf(seq, "%03ld,%03ld", v/1000, v % 1000);
+	} else if (likely(v >= 1000))
+		seq_printf(seq, "%ld,%03ld", v/1000, v % 1000);
+	else
+		seq_printf(seq, "%ld", v);
+}
+
+/*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;
+	int stalled = 0;
+
+	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, "] ");
+
+	if (mdev->state.conn == C_VERIFY_S || mdev->state.conn == C_VERIFY_T)
+		seq_printf(seq, "verified:");
+	else
+		seq_printf(seq, "sync'ed:");
+	seq_printf(seq, "%3u.%u%% ", res / 10, res % 10);
+
+	/* if more than a few GB, display in MB */
+	if (mdev->rs_total > (4UL << (30 - BM_BLOCK_SHIFT)))
+		seq_printf(seq, "(%lu/%lu)M",
+			    (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
+	 */
+	/* Rolling marks. last_mark+1 may just now be modified.  last_mark+2 is
+	 * at least (DRBD_SYNC_MARKS-2)*DRBD_SYNC_MARK_STEP old, and has at
+	 * least DRBD_SYNC_MARK_STEP time before it will be modified. */
+	/* ------------------------ ~18s average ------------------------ */
+	i = (mdev->rs_last_mark + 2) % DRBD_SYNC_MARKS;
+	dt = (jiffies - mdev->rs_mark_time[i]) / HZ;
+	if (dt > (DRBD_SYNC_MARK_STEP * DRBD_SYNC_MARKS))
+		stalled = 1;
+
+	if (!dt)
+		dt++;
+	db = mdev->rs_mark_left[i] - 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);
+
+	dbdt = Bit2KB(db/dt);
+	seq_printf(seq, " speed: ");
+	seq_printf_with_thousands_grouping(seq, dbdt);
+	seq_printf(seq, " (");
+	/* ------------------------- ~3s average ------------------------ */
+	if (proc_details >= 1) {
+		/* this is what drbd_rs_should_slow_down() uses */
+		i = (mdev->rs_last_mark + DRBD_SYNC_MARKS-1) % DRBD_SYNC_MARKS;
+		dt = (jiffies - mdev->rs_mark_time[i]) / HZ;
+		if (!dt)
+			dt++;
+		db = mdev->rs_mark_left[i] - rs_left;
+		dbdt = Bit2KB(db/dt);
+		seq_printf_with_thousands_grouping(seq, dbdt);
+		seq_printf(seq, " -- ");
+	}
+
+	/* --------------------- long term average ---------------------- */
+	/* 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);
+	seq_printf_with_thousands_grouping(seq, dbdt);
+	seq_printf(seq, ")");
+
+	if (mdev->state.conn == C_SYNC_TARGET ||
+	    mdev->state.conn == C_VERIFY_S) {
+		seq_printf(seq, " want: ");
+		seq_printf_with_thousands_grouping(seq, mdev->c_sync_rate);
+	}
+	seq_printf(seq, " K/sec%s\n", stalled ? " (stalled)" : "");
+
+	if (proc_details >= 1) {
+		/* 64 bit:
+		 * we convert to sectors in the display below. */
+		unsigned long bm_bits = drbd_bm_bits(mdev);
+		unsigned long bit_pos;
+		unsigned long long stop_sector = 0;
+		if (mdev->state.conn == C_VERIFY_S ||
+		    mdev->state.conn == C_VERIFY_T) {
+			bit_pos = bm_bits - mdev->ov_left;
+			if (verify_can_do_stop_sector(mdev))
+				stop_sector = mdev->ov_stop_sector;
+		} else
+			bit_pos = mdev->bm_resync_fo;
+		/* Total sectors may be slightly off for oddly
+		 * sized devices. So what. */
+		seq_printf(seq,
+			"\t%3d%% sector pos: %llu/%llu",
+			(int)(bit_pos / (bm_bits/100+1)),
+			(unsigned long long)bit_pos * BM_SECT_PER_BIT,
+			(unsigned long long)bm_bits * BM_SECT_PER_BIT);
+		if (stop_sector != 0 && stop_sector != ULLONG_MAX)
+			seq_printf(seq, " stop sector: %llu", stop_sector);
+		seq_printf(seq, "\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, prev_i = -1;
+	const char *sn;
+	struct drbd_conf *mdev;
+	struct net_conf *nc;
+	char wp;
+
+	static char write_ordering_chars[] = {
+		[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",
+		   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
+	*/
+
+	rcu_read_lock();
+	idr_for_each_entry(&minors, mdev, i) {
+		if (prev_i != i - 1)
+			seq_printf(seq, "\n");
+		prev_i = i;
+
+		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 {
+			/* reset mdev->congestion_reason */
+			bdi_rw_congested(&mdev->rq_queue->backing_dev_info);
+
+			nc = rcu_dereference(mdev->tconn->net_conf);
+			wp = nc ? nc->wire_protocol - DRBD_PROT_A + 'A' : ' ';
+			seq_printf(seq,
+			   "%2d: cs:%s ro:%s/%s ds:%s/%s %c %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),
+			   wp,
+			   drbd_suspended(mdev) ? 's' : 'r',
+			   mdev->state.aftr_isp ? 'a' : '-',
+			   mdev->state.peer_isp ? 'p' : '-',
+			   mdev->state.user_isp ? 'u' : '-',
+			   mdev->congestion_reason ?: '-',
+			   test_bit(AL_SUSPENDED, &mdev->flags) ? 's' : '-',
+			   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->tconn->epochs,
+			   write_ordering_chars[mdev->tconn->write_ordering]
+			);
+			seq_printf(seq, " oos:%llu\n",
+				   Bit2KB((unsigned long long)
+					   drbd_bm_total_weight(mdev)));
+		}
+		if (mdev->state.conn == C_SYNC_SOURCE ||
+		    mdev->state.conn == C_SYNC_TARGET ||
+		    mdev->state.conn == C_VERIFY_S ||
+		    mdev->state.conn == C_VERIFY_T)
+			drbd_syncer_progress(mdev, seq);
+
+		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);
+			}
+		}
+	}
+	rcu_read_unlock();
+
+	return 0;
+}
+
+static int drbd_proc_open(struct inode *inode, struct file *file)
+{
+	int err;
+
+	if (try_module_get(THIS_MODULE)) {
+		err = single_open(file, drbd_seq_show, PDE_DATA(inode));
+		if (err)
+			module_put(THIS_MODULE);
+		return err;
+	}
+	return -ENODEV;
+}
+
+static int drbd_proc_release(struct inode *inode, struct file *file)
+{
+	module_put(THIS_MODULE);
+	return single_release(inode, file);
+}
+
+/* PROC FS stuff end */

drivers/block/drbd/drbd_req.h

@@ -0,0 +1,348 @@
+/*
+   drbd_req.h
+
+   This file is part of DRBD by Philipp Reisner and Lars Ellenberg.
+
+   Copyright (C) 2006-2008, LINBIT Information Technologies GmbH.
+   Copyright (C) 2006-2008, Lars Ellenberg <lars.ellenberg@linbit.com>.
+   Copyright (C) 2006-2008, Philipp Reisner <philipp.reisner@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_REQ_H
+#define _DRBD_REQ_H
+
+#include <linux/module.h>
+
+#include <linux/slab.h>
+#include <linux/drbd.h>
+#include "drbd_int.h"
+#include "drbd_wrappers.h"
+
+/* The request callbacks will be called in irq context by the IDE drivers,
+   and in Softirqs/Tasklets/BH context by the SCSI drivers,
+   and by the receiver and worker in kernel-thread context.
+   Try to get the locking right :) */
+
+/*
+ * Objects of type struct drbd_request do only exist on a R_PRIMARY node, and are
+ * associated with IO requests originating from the block layer above us.
+ *
+ * There are quite a few things that may happen to a drbd request
+ * during its lifetime.
+ *
+ *  It will be created.
+ *  It will be marked with the intention to be
+ *    submitted to local disk and/or
+ *    send via the network.
+ *
+ *  It has to be placed on the transfer log and other housekeeping lists,
+ *  In case we have a network connection.
+ *
+ *  It may be identified as a concurrent (write) request
+ *    and be handled accordingly.
+ *
+ *  It may me handed over to the local disk subsystem.
+ *  It may be completed by the local disk subsystem,
+ *    either successfully or with io-error.
+ *  In case it is a READ request, and it failed locally,
+ *    it may be retried remotely.
+ *
+ *  It may be queued for sending.
+ *  It may be handed over to the network stack,
+ *    which may fail.
+ *  It may be acknowledged by the "peer" according to the wire_protocol in use.
+ *    this may be a negative ack.
+ *  It may receive a faked ack when the network connection is lost and the
+ *  transfer log is cleaned up.
+ *  Sending may be canceled due to network connection loss.
+ *  When it finally has outlived its time,
+ *    corresponding dirty bits in the resync-bitmap may be cleared or set,
+ *    it will be destroyed,
+ *    and completion will be signalled to the originator,
+ *      with or without "success".
+ */
+
+enum drbd_req_event {
+	CREATED,
+	TO_BE_SENT,
+	TO_BE_SUBMITTED,
+
+	/* XXX yes, now I am inconsistent...
+	 * these are not "events" but "actions"
+	 * oh, well... */
+	QUEUE_FOR_NET_WRITE,
+	QUEUE_FOR_NET_READ,
+	QUEUE_FOR_SEND_OOS,
+
+	/* An empty flush is queued as P_BARRIER,
+	 * which will cause it to complete "successfully",
+	 * even if the local disk flush failed.
+	 *
+	 * Just like "real" requests, empty flushes (blkdev_issue_flush()) will
+	 * only see an error if neither local nor remote data is reachable. */
+	QUEUE_AS_DRBD_BARRIER,
+
+	SEND_CANCELED,
+	SEND_FAILED,
+	HANDED_OVER_TO_NETWORK,
+	OOS_HANDED_TO_NETWORK,
+	CONNECTION_LOST_WHILE_PENDING,
+	READ_RETRY_REMOTE_CANCELED,
+	RECV_ACKED_BY_PEER,
+	WRITE_ACKED_BY_PEER,
+	WRITE_ACKED_BY_PEER_AND_SIS, /* and set_in_sync */
+	CONFLICT_RESOLVED,
+	POSTPONE_WRITE,
+	NEG_ACKED,
+	BARRIER_ACKED, /* in protocol A and B */
+	DATA_RECEIVED, /* (remote read) */
+
+	READ_COMPLETED_WITH_ERROR,
+	READ_AHEAD_COMPLETED_WITH_ERROR,
+	WRITE_COMPLETED_WITH_ERROR,
+	ABORT_DISK_IO,
+	COMPLETED_OK,
+	RESEND,
+	FAIL_FROZEN_DISK_IO,
+	RESTART_FROZEN_DISK_IO,
+	NOTHING,
+};
+
+/* encoding of request states for now.  we don't actually need that many bits.
+ * we don't need to do atomic bit operations either, since most of the time we
+ * need to look at the connection state and/or manipulate some lists at the
+ * same time, so we should hold the request lock anyways.
+ */
+enum drbd_req_state_bits {
+	/* 3210
+	 * 0000: no local possible
+	 * 0001: to be submitted
+	 *    UNUSED, we could map: 011: submitted, completion still pending
+	 * 0110: completed ok
+	 * 0010: completed with error
+	 * 1001: Aborted (before completion)
+	 * 1x10: Aborted and completed -> free
+	 */
+	__RQ_LOCAL_PENDING,
+	__RQ_LOCAL_COMPLETED,
+	__RQ_LOCAL_OK,
+	__RQ_LOCAL_ABORTED,
+
+	/* 87654
+	 * 00000: no network possible
+	 * 00001: to be send
+	 * 00011: to be send, on worker queue
+	 * 00101: sent, expecting recv_ack (B) or write_ack (C)
+	 * 11101: sent,
+	 *        recv_ack (B) or implicit "ack" (A),
+	 *        still waiting for the barrier ack.
+	 *        master_bio may already be completed and invalidated.
+	 * 11100: write acked (C),
+	 *        data received (for remote read, any protocol)
+	 *        or finally the barrier ack has arrived (B,A)...
+	 *        request can be freed
+	 * 01100: neg-acked (write, protocol C)
+	 *        or neg-d-acked (read, any protocol)
+	 *        or killed from the transfer log
+	 *        during cleanup after connection loss
+	 *        request can be freed
+	 * 01000: canceled or send failed...
+	 *        request can be freed
+	 */
+
+	/* if "SENT" is not set, yet, this can still fail or be canceled.
+	 * if "SENT" is set already, we still wait for an Ack packet.
+	 * when cleared, the master_bio may be completed.
+	 * in (B,A) the request object may still linger on the transaction log
+	 * until the corresponding barrier ack comes in */
+	__RQ_NET_PENDING,
+
+	/* If it is QUEUED, and it is a WRITE, it is also registered in the
+	 * transfer log. Currently we need this flag to avoid conflicts between
+	 * worker canceling the request and tl_clear_barrier killing it from
+	 * transfer log.  We should restructure the code so this conflict does
+	 * no longer occur. */
+	__RQ_NET_QUEUED,
+
+	/* well, actually only "handed over to the network stack".
+	 *
+	 * TODO can potentially be dropped because of the similar meaning
+	 * of RQ_NET_SENT and ~RQ_NET_QUEUED.
+	 * however it is not exactly the same. before we drop it
+	 * we must ensure that we can tell a request with network part
+	 * from a request without, regardless of what happens to it. */
+	__RQ_NET_SENT,
+
+	/* when set, the request may be freed (if RQ_NET_QUEUED is clear).
+	 * basically this means the corresponding P_BARRIER_ACK was received */
+	__RQ_NET_DONE,
+
+	/* whether or not we know (C) or pretend (B,A) that the write
+	 * was successfully written on the peer.
+	 */
+	__RQ_NET_OK,
+
+	/* peer called drbd_set_in_sync() for this write */
+	__RQ_NET_SIS,
+
+	/* keep this last, its for the RQ_NET_MASK */
+	__RQ_NET_MAX,
+
+	/* Set when this is a write, clear for a read */
+	__RQ_WRITE,
+
+	/* Should call drbd_al_complete_io() for this request... */
+	__RQ_IN_ACT_LOG,
+
+	/* The peer has sent a retry ACK */
+	__RQ_POSTPONED,
+
+	/* would have been completed,
+	 * but was not, because of drbd_suspended() */
+	__RQ_COMPLETION_SUSP,
+
+	/* We expect a receive ACK (wire proto B) */
+	__RQ_EXP_RECEIVE_ACK,
+
+	/* We expect a write ACK (wite proto C) */
+	__RQ_EXP_WRITE_ACK,
+
+	/* waiting for a barrier ack, did an extra kref_get */
+	__RQ_EXP_BARR_ACK,
+};
+
+#define RQ_LOCAL_PENDING   (1UL << __RQ_LOCAL_PENDING)
+#define RQ_LOCAL_COMPLETED (1UL << __RQ_LOCAL_COMPLETED)
+#define RQ_LOCAL_OK        (1UL << __RQ_LOCAL_OK)
+#define RQ_LOCAL_ABORTED   (1UL << __RQ_LOCAL_ABORTED)
+
+#define RQ_LOCAL_MASK      ((RQ_LOCAL_ABORTED << 1)-1)
+
+#define RQ_NET_PENDING     (1UL << __RQ_NET_PENDING)
+#define RQ_NET_QUEUED      (1UL << __RQ_NET_QUEUED)
+#define RQ_NET_SENT        (1UL << __RQ_NET_SENT)
+#define RQ_NET_DONE        (1UL << __RQ_NET_DONE)
+#define RQ_NET_OK          (1UL << __RQ_NET_OK)
+#define RQ_NET_SIS         (1UL << __RQ_NET_SIS)
+
+/* 0x1f8 */
+#define RQ_NET_MASK        (((1UL << __RQ_NET_MAX)-1) & ~RQ_LOCAL_MASK)
+
+#define RQ_WRITE           (1UL << __RQ_WRITE)
+#define RQ_IN_ACT_LOG      (1UL << __RQ_IN_ACT_LOG)
+#define RQ_POSTPONED	   (1UL << __RQ_POSTPONED)
+#define RQ_COMPLETION_SUSP (1UL << __RQ_COMPLETION_SUSP)
+#define RQ_EXP_RECEIVE_ACK (1UL << __RQ_EXP_RECEIVE_ACK)
+#define RQ_EXP_WRITE_ACK   (1UL << __RQ_EXP_WRITE_ACK)
+#define RQ_EXP_BARR_ACK    (1UL << __RQ_EXP_BARR_ACK)
+
+/* For waking up the frozen transfer log mod_req() has to return if the request
+   should be counted in the epoch object*/
+#define MR_WRITE       1
+#define MR_READ        2
+
+static inline void drbd_req_make_private_bio(struct drbd_request *req, struct bio *bio_src)
+{
+	struct bio *bio;
+	bio = bio_clone(bio_src, GFP_NOIO); /* XXX cannot fail?? */
+
+	req->private_bio = bio;
+
+	bio->bi_private  = req;
+	bio->bi_end_io   = drbd_request_endio;
+	bio->bi_next     = NULL;
+}
+
+/* Short lived temporary struct on the stack.
+ * We could squirrel the error to be returned into
+ * bio->bi_size, or similar. But that would be too ugly. */
+struct bio_and_error {
+	struct bio *bio;
+	int error;
+};
+
+extern void start_new_tl_epoch(struct drbd_tconn *tconn);
+extern void drbd_req_destroy(struct kref *kref);
+extern void _req_may_be_done(struct drbd_request *req,
+		struct bio_and_error *m);
+extern int __req_mod(struct drbd_request *req, enum drbd_req_event what,
+		struct bio_and_error *m);
+extern void complete_master_bio(struct drbd_conf *mdev,
+		struct bio_and_error *m);
+extern void request_timer_fn(unsigned long data);
+extern void tl_restart(struct drbd_tconn *tconn, enum drbd_req_event what);
+extern void _tl_restart(struct drbd_tconn *tconn, enum drbd_req_event what);
+
+/* this is in drbd_main.c */
+extern void drbd_restart_request(struct drbd_request *req);
+
+/* use this if you don't want to deal with calling complete_master_bio()
+ * outside the spinlock, e.g. when walking some list on cleanup. */
+static inline int _req_mod(struct drbd_request *req, enum drbd_req_event what)
+{
+	struct drbd_conf *mdev = req->w.mdev;
+	struct bio_and_error m;
+	int rv;
+
+	/* __req_mod possibly frees req, do not touch req after that! */
+	rv = __req_mod(req, what, &m);
+	if (m.bio)
+		complete_master_bio(mdev, &m);
+
+	return rv;
+}
+
+/* completion of master bio is outside of our spinlock.
+ * We still may or may not be inside some irqs disabled section
+ * of the lower level driver completion callback, so we need to
+ * spin_lock_irqsave here. */
+static inline int req_mod(struct drbd_request *req,
+		enum drbd_req_event what)
+{
+	unsigned long flags;
+	struct drbd_conf *mdev = req->w.mdev;
+	struct bio_and_error m;
+	int rv;
+
+	spin_lock_irqsave(&mdev->tconn->req_lock, flags);
+	rv = __req_mod(req, what, &m);
+	spin_unlock_irqrestore(&mdev->tconn->req_lock, flags);
+
+	if (m.bio)
+		complete_master_bio(mdev, &m);
+
+	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 */
+}
+
+#endif

drivers/block/drbd/drbd_state.h

@@ -0,0 +1,161 @@
+#ifndef DRBD_STATE_H
+#define DRBD_STATE_H
+
+struct drbd_conf;
+struct drbd_tconn;
+
+/**
+ * DOC: DRBD State macros
+ *
+ * These macros are used to express state changes in easily readable form.
+ *
+ * The NS macros expand to a mask and a value, that can be bit ored onto the
+ * current state as soon as the spinlock (req_lock) was taken.
+ *
+ * The _NS macros are used for state functions that get called with the
+ * spinlock. These macros expand directly to the new state value.
+ *
+ * Besides the basic forms NS() and _NS() additional _?NS[23] are defined
+ * to express state changes that affect more than one aspect of the state.
+ *
+ * E.g. NS2(conn, C_CONNECTED, peer, R_SECONDARY)
+ * Means that the network connection was established and that the peer
+ * is in secondary role.
+ */
+#define role_MASK R_MASK
+#define peer_MASK R_MASK
+#define disk_MASK D_MASK
+#define pdsk_MASK D_MASK
+#define conn_MASK C_MASK
+#define susp_MASK 1
+#define user_isp_MASK 1
+#define aftr_isp_MASK 1
+#define susp_nod_MASK 1
+#define susp_fen_MASK 1
+
+#define NS(T, S) \
+	({ union drbd_state mask; mask.i = 0; mask.T = T##_MASK; mask; }), \
+	({ union drbd_state val; val.i = 0; val.T = (S); val; })
+#define NS2(T1, S1, T2, S2) \
+	({ union drbd_state mask; mask.i = 0; mask.T1 = T1##_MASK; \
+	  mask.T2 = T2##_MASK; mask; }), \
+	({ union drbd_state val; val.i = 0; val.T1 = (S1); \
+	  val.T2 = (S2); val; })
+#define NS3(T1, S1, T2, S2, T3, S3) \
+	({ union drbd_state mask; mask.i = 0; mask.T1 = T1##_MASK; \
+	  mask.T2 = T2##_MASK; mask.T3 = T3##_MASK; mask; }), \
+	({ union drbd_state val;  val.i = 0; val.T1 = (S1); \
+	  val.T2 = (S2); val.T3 = (S3); val; })
+
+#define _NS(D, T, S) \
+	D, ({ union drbd_state __ns; __ns = drbd_read_state(D); __ns.T = (S); __ns; })
+#define _NS2(D, T1, S1, T2, S2) \
+	D, ({ union drbd_state __ns; __ns = drbd_read_state(D); __ns.T1 = (S1); \
+	__ns.T2 = (S2); __ns; })
+#define _NS3(D, T1, S1, T2, S2, T3, S3) \
+	D, ({ union drbd_state __ns; __ns = drbd_read_state(D); __ns.T1 = (S1); \
+	__ns.T2 = (S2); __ns.T3 = (S3); __ns; })
+
+enum chg_state_flags {
+	CS_HARD	         = 1 << 0,
+	CS_VERBOSE       = 1 << 1,
+	CS_WAIT_COMPLETE = 1 << 2,
+	CS_SERIALIZE     = 1 << 3,
+	CS_ORDERED       = CS_WAIT_COMPLETE + CS_SERIALIZE,
+	CS_LOCAL_ONLY    = 1 << 4, /* Do not consider a device pair wide state change */
+	CS_DC_ROLE       = 1 << 5, /* DC = display as connection state change */
+	CS_DC_PEER       = 1 << 6,
+	CS_DC_CONN       = 1 << 7,
+	CS_DC_DISK       = 1 << 8,
+	CS_DC_PDSK       = 1 << 9,
+	CS_DC_SUSP       = 1 << 10,
+	CS_DC_MASK       = CS_DC_ROLE + CS_DC_PEER + CS_DC_CONN + CS_DC_DISK + CS_DC_PDSK,
+	CS_IGN_OUTD_FAIL = 1 << 11,
+};
+
+/* drbd_dev_state and drbd_state are different types. This is to stress the
+   small difference. There is no suspended flag (.susp), and no suspended
+   while fence handler runs flas (susp_fen). */
+union drbd_dev_state {
+	struct {
+#if defined(__LITTLE_ENDIAN_BITFIELD)
+		unsigned role:2 ;   /* 3/4	 primary/secondary/unknown */
+		unsigned peer:2 ;   /* 3/4	 primary/secondary/unknown */
+		unsigned conn:5 ;   /* 17/32	 cstates */
+		unsigned disk:4 ;   /* 8/16	 from D_DISKLESS to D_UP_TO_DATE */
+		unsigned pdsk:4 ;   /* 8/16	 from D_DISKLESS to D_UP_TO_DATE */
+		unsigned _unused:1 ;
+		unsigned aftr_isp:1 ; /* isp .. imposed sync pause */
+		unsigned peer_isp:1 ;
+		unsigned user_isp:1 ;
+		unsigned _pad:11;   /* 0	 unused */
+#elif defined(__BIG_ENDIAN_BITFIELD)
+		unsigned _pad:11;
+		unsigned user_isp:1 ;
+		unsigned peer_isp:1 ;
+		unsigned aftr_isp:1 ; /* isp .. imposed sync pause */
+		unsigned _unused:1 ;
+		unsigned pdsk:4 ;   /* 8/16	 from D_DISKLESS to D_UP_TO_DATE */
+		unsigned disk:4 ;   /* 8/16	 from D_DISKLESS to D_UP_TO_DATE */
+		unsigned conn:5 ;   /* 17/32	 cstates */
+		unsigned peer:2 ;   /* 3/4	 primary/secondary/unknown */
+		unsigned role:2 ;   /* 3/4	 primary/secondary/unknown */
+#else
+# error "this endianess is not supported"
+#endif
+	};
+	unsigned int i;
+};
+
+extern enum drbd_state_rv drbd_change_state(struct drbd_conf *mdev,
+					    enum chg_state_flags f,
+					    union drbd_state mask,
+					    union drbd_state val);
+extern void drbd_force_state(struct drbd_conf *, union drbd_state,
+			union drbd_state);
+extern enum drbd_state_rv _drbd_request_state(struct drbd_conf *,
+					      union drbd_state,
+					      union drbd_state,
+					      enum chg_state_flags);
+extern enum drbd_state_rv __drbd_set_state(struct drbd_conf *, union drbd_state,
+					   enum chg_state_flags,
+					   struct completion *done);
+extern void print_st_err(struct drbd_conf *, union drbd_state,
+			union drbd_state, int);
+
+enum drbd_state_rv
+_conn_request_state(struct drbd_tconn *tconn, union drbd_state mask, union drbd_state val,
+		    enum chg_state_flags flags);
+
+enum drbd_state_rv
+conn_request_state(struct drbd_tconn *tconn, union drbd_state mask, union drbd_state val,
+		   enum chg_state_flags flags);
+
+extern void drbd_resume_al(struct drbd_conf *mdev);
+extern bool conn_all_vols_unconf(struct drbd_tconn *tconn);
+
+/**
+ * drbd_request_state() - Reqest a state change
+ * @mdev:	DRBD device.
+ * @mask:	mask of state bits to change.
+ * @val:	value of new state bits.
+ *
+ * This is the most graceful way of requesting a state change. It is verbose
+ * quite verbose in case the state change is not possible, and all those
+ * state changes are globally serialized.
+ */
+static inline int drbd_request_state(struct drbd_conf *mdev,
+				     union drbd_state mask,
+				     union drbd_state val)
+{
+	return _drbd_request_state(mdev, mask, val, CS_VERBOSE + CS_ORDERED);
+}
+
+enum drbd_role conn_highest_role(struct drbd_tconn *tconn);
+enum drbd_role conn_highest_peer(struct drbd_tconn *tconn);
+enum drbd_disk_state conn_highest_disk(struct drbd_tconn *tconn);
+enum drbd_disk_state conn_lowest_disk(struct drbd_tconn *tconn);
+enum drbd_disk_state conn_highest_pdsk(struct drbd_tconn *tconn);
+enum drbd_conns conn_lowest_conn(struct drbd_tconn *tconn);
+
+#endif

drivers/block/drbd/drbd_strings.c

@@ -0,0 +1,117 @@
+/*
+  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",
+	[C_AHEAD]            = "Ahead",
+	[C_BEHIND]           = "Behind",
+};
+
+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] = "Need access to UpToDate data",
+	[-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",
+	[-SS_OUTDATE_WO_CONN] = "Need a connection for a graceful disconnect/outdate peer",
+	[-SS_O_VOL_PEER_PRI] = "Other vol primary on peer not allowed by config",
+};
+
+const char *drbd_conn_str(enum drbd_conns s)
+{
+	/* enums are unsigned... */
+	return s > C_BEHIND ? "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_rv err)
+{
+	return err <= SS_AFTER_LAST_ERROR ? "TOO_SMALL" :
+	       err > SS_TWO_PRIMARIES ? "TOO_LARGE"
+			: drbd_state_sw_errors[-err];
+}

drivers/block/drbd/drbd_vli.h

@@ -0,0 +1,351 @@
+/*
+-*- linux-c -*-
+   drbd_receiver.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.
+ */
+
+#ifndef _DRBD_VLI_H
+#define _DRBD_VLI_H
+
+/*
+ * At a granularity of 4KiB storage represented per bit,
+ * and stroage sizes of several TiB,
+ * and possibly small-bandwidth replication,
+ * the bitmap transfer time can take much too long,
+ * if transmitted in plain text.
+ *
+ * We try to reduce the transferred bitmap information
+ * by encoding runlengths of bit polarity.
+ *
+ * We never actually need to encode a "zero" (runlengths are positive).
+ * But then we have to store the value of the first bit.
+ * The first bit of information thus shall encode if the first runlength
+ * gives the number of set or unset bits.
+ *
+ * We assume that large areas are either completely set or unset,
+ * which gives good compression with any runlength method,
+ * even when encoding the runlength as fixed size 32bit/64bit integers.
+ *
+ * Still, there may be areas where the polarity flips every few bits,
+ * and encoding the runlength sequence of those areas with fix size
+ * integers would be much worse than plaintext.
+ *
+ * We want to encode small runlength values with minimum code length,
+ * while still being able to encode a Huge run of all zeros.
+ *
+ * Thus we need a Variable Length Integer encoding, VLI.
+ *
+ * For some cases, we produce more code bits than plaintext input.
+ * We need to send incompressible chunks as plaintext, skip over them
+ * and then see if the next chunk compresses better.
+ *
+ * We don't care too much about "excellent" compression ratio for large
+ * runlengths (all set/all clear): whether we achieve a factor of 100
+ * or 1000 is not that much of an issue.
+ * We do not want to waste too much on short runlengths in the "noisy"
+ * parts of the bitmap, though.
+ *
+ * There are endless variants of VLI, we experimented with:
+ *  * simple byte-based
+ *  * various bit based with different code word length.
+ *
+ * To avoid yet an other configuration parameter (choice of bitmap compression
+ * algorithm) which was difficult to explain and tune, we just chose the one
+ * variant that turned out best in all test cases.
+ * Based on real world usage patterns, with device sizes ranging from a few GiB
+ * to several TiB, file server/mailserver/webserver/mysql/postgress,
+ * mostly idle to really busy, the all time winner (though sometimes only
+ * marginally better) is:
+ */
+
+/*
+ * encoding is "visualised" as
+ * __little endian__ bitstream, least significant bit first (left most)
+ *
+ * this particular encoding is chosen so that the prefix code
+ * starts as unary encoding the level, then modified so that
+ * 10 levels can be described in 8bit, with minimal overhead
+ * for the smaller levels.
+ *
+ * Number of data bits follow fibonacci sequence, with the exception of the
+ * last level (+1 data bit, so it makes 64bit total).  The only worse code when
+ * encoding bit polarity runlength is 1 plain bits => 2 code bits.
+prefix    data bits                                    max val  Nº data bits
+0 x                                                         0x2            1
+10 x                                                        0x4            1
+110 xx                                                      0x8            2
+1110 xxx                                                   0x10            3
+11110 xxx xx                                               0x30            5
+111110 xx xxxxxx                                          0x130            8
+11111100  xxxxxxxx xxxxx                                 0x2130           13
+11111110  xxxxxxxx xxxxxxxx xxxxx                      0x202130           21
+11111101  xxxxxxxx xxxxxxxx xxxxxxxx  xxxxxxxx xx   0x400202130           34
+11111111  xxxxxxxx xxxxxxxx xxxxxxxx  xxxxxxxx xxxxxxxx xxxxxxxx xxxxxxxx 56
+ * maximum encodable value: 0x100000400202130 == 2**56 + some */
+
+/* compression "table":
+ transmitted   x                                0.29
+ as plaintext x                                  ........................
+             x                                   ........................
+            x                                    ........................
+           x    0.59                         0.21........................
+          x      ........................................................
+         x       .. c ...................................................
+        x    0.44.. o ...................................................
+       x .......... d ...................................................
+      x  .......... e ...................................................
+     X.............   ...................................................
+    x.............. b ...................................................
+2.0x............... i ...................................................
+ #X................ t ...................................................
+ #................. s ...........................  plain bits  ..........
+-+-----------------------------------------------------------------------
+ 1             16              32                              64
+*/
+
+/* LEVEL: (total bits, prefix bits, prefix value),
+ * sorted ascending by number of total bits.
+ * The rest of the code table is calculated at compiletime from this. */
+
+/* fibonacci data 1, 1, ... */
+#define VLI_L_1_1() do { \
+	LEVEL( 2, 1, 0x00); \
+	LEVEL( 3, 2, 0x01); \
+	LEVEL( 5, 3, 0x03); \
+	LEVEL( 7, 4, 0x07); \
+	LEVEL(10, 5, 0x0f); \
+	LEVEL(14, 6, 0x1f); \
+	LEVEL(21, 8, 0x3f); \
+	LEVEL(29, 8, 0x7f); \
+	LEVEL(42, 8, 0xbf); \
+	LEVEL(64, 8, 0xff); \
+	} while (0)
+
+/* finds a suitable level to decode the least significant part of in.
+ * returns number of bits consumed.
+ *
+ * BUG() for bad input, as that would mean a buggy code table. */
+static inline int vli_decode_bits(u64 *out, const u64 in)
+{
+	u64 adj = 1;
+
+#define LEVEL(t,b,v)					\
+	do {						\
+		if ((in & ((1 << b) -1)) == v) {	\
+			*out = ((in & ((~0ULL) >> (64-t))) >> b) + adj;	\
+			return t;			\
+		}					\
+		adj += 1ULL << (t - b);			\
+	} while (0)
+
+	VLI_L_1_1();
+
+	/* NOT REACHED, if VLI_LEVELS code table is defined properly */
+	BUG();
+#undef LEVEL
+}
+
+/* return number of code bits needed,
+ * or negative error number */
+static inline int __vli_encode_bits(u64 *out, const u64 in)
+{
+	u64 max = 0;
+	u64 adj = 1;
+
+	if (in == 0)
+		return -EINVAL;
+
+#define LEVEL(t,b,v) do {		\
+		max += 1ULL << (t - b);	\
+		if (in <= max) {	\
+			if (out)	\
+				*out = ((in - adj) << b) | v;	\
+			return t;	\
+		}			\
+		adj = max + 1;		\
+	} while (0)
+
+	VLI_L_1_1();
+
+	return -EOVERFLOW;
+#undef LEVEL
+}
+
+#undef VLI_L_1_1
+
+/* code from here down is independend of actually used bit code */
+
+/*
+ * Code length is determined by some unique (e.g. unary) prefix.
+ * This encodes arbitrary bit length, not whole bytes: we have a bit-stream,
+ * not a byte stream.
+ */
+
+/* for the bitstream, we need a cursor */
+struct bitstream_cursor {
+	/* the current byte */
+	u8 *b;
+	/* the current bit within *b, nomalized: 0..7 */
+	unsigned int bit;
+};
+
+/* initialize cursor to point to first bit of stream */
+static inline void bitstream_cursor_reset(struct bitstream_cursor *cur, void *s)
+{
+	cur->b = s;
+	cur->bit = 0;
+}
+
+/* advance cursor by that many bits; maximum expected input value: 64,
+ * but depending on VLI implementation, it may be more. */
+static inline void bitstream_cursor_advance(struct bitstream_cursor *cur, unsigned int bits)
+{
+	bits += cur->bit;
+	cur->b = cur->b + (bits >> 3);
+	cur->bit = bits & 7;
+}
+
+/* the bitstream itself knows its length */
+struct bitstream {
+	struct bitstream_cursor cur;
+	unsigned char *buf;
+	size_t buf_len;		/* in bytes */
+
+	/* for input stream:
+	 * number of trailing 0 bits for padding
+	 * total number of valid bits in stream: buf_len * 8 - pad_bits */
+	unsigned int pad_bits;
+};
+
+static inline void bitstream_init(struct bitstream *bs, void *s, size_t len, unsigned int pad_bits)
+{
+	bs->buf = s;
+	bs->buf_len = len;
+	bs->pad_bits = pad_bits;
+	bitstream_cursor_reset(&bs->cur, bs->buf);
+}
+
+static inline void bitstream_rewind(struct bitstream *bs)
+{
+	bitstream_cursor_reset(&bs->cur, bs->buf);
+	memset(bs->buf, 0, bs->buf_len);
+}
+
+/* Put (at most 64) least significant bits of val into bitstream, and advance cursor.
+ * Ignores "pad_bits".
+ * Returns zero if bits == 0 (nothing to do).
+ * Returns number of bits used if successful.
+ *
+ * If there is not enough room left in bitstream,
+ * leaves bitstream unchanged and returns -ENOBUFS.
+ */
+static inline int bitstream_put_bits(struct bitstream *bs, u64 val, const unsigned int bits)
+{
+	unsigned char *b = bs->cur.b;
+	unsigned int tmp;
+
+	if (bits == 0)
+		return 0;
+
+	if ((bs->cur.b + ((bs->cur.bit + bits -1) >> 3)) - bs->buf >= bs->buf_len)
+		return -ENOBUFS;
+
+	/* paranoia: strip off hi bits; they should not be set anyways. */
+	if (bits < 64)
+		val &= ~0ULL >> (64 - bits);
+
+	*b++ |= (val & 0xff) << bs->cur.bit;
+
+	for (tmp = 8 - bs->cur.bit; tmp < bits; tmp += 8)
+		*b++ |= (val >> tmp) & 0xff;
+
+	bitstream_cursor_advance(&bs->cur, bits);
+	return bits;
+}
+
+/* Fetch (at most 64) bits from bitstream into *out, and advance cursor.
+ *
+ * If more than 64 bits are requested, returns -EINVAL and leave *out unchanged.
+ *
+ * If there are less than the requested number of valid bits left in the
+ * bitstream, still fetches all available bits.
+ *
+ * Returns number of actually fetched bits.
+ */
+static inline int bitstream_get_bits(struct bitstream *bs, u64 *out, int bits)
+{
+	u64 val;
+	unsigned int n;
+
+	if (bits > 64)
+		return -EINVAL;
+
+	if (bs->cur.b + ((bs->cur.bit + bs->pad_bits + bits -1) >> 3) - bs->buf >= bs->buf_len)
+		bits = ((bs->buf_len - (bs->cur.b - bs->buf)) << 3)
+			- bs->cur.bit - bs->pad_bits;
+
+	if (bits == 0) {
+		*out = 0;
+		return 0;
+	}
+
+	/* get the high bits */
+	val = 0;
+	n = (bs->cur.bit + bits + 7) >> 3;
+	/* n may be at most 9, if cur.bit + bits > 64 */
+	/* which means this copies at most 8 byte */
+	if (n) {
+		memcpy(&val, bs->cur.b+1, n - 1);
+		val = le64_to_cpu(val) << (8 - bs->cur.bit);
+	}
+
+	/* we still need the low bits */
+	val |= bs->cur.b[0] >> bs->cur.bit;
+
+	/* and mask out bits we don't want */
+	val &= ~0ULL >> (64 - bits);
+
+	bitstream_cursor_advance(&bs->cur, bits);
+	*out = val;
+
+	return bits;
+}
+
+/* encodes @in as vli into @bs;
+
+ * return values
+ *  > 0: number of bits successfully stored in bitstream
+ * -ENOBUFS @bs is full
+ * -EINVAL input zero (invalid)
+ * -EOVERFLOW input too large for this vli code (invalid)
+ */
+static inline int vli_encode_bits(struct bitstream *bs, u64 in)
+{
+	u64 code = code;
+	int bits = __vli_encode_bits(&code, in);
+
+	if (bits <= 0)
+		return bits;
+
+	return bitstream_put_bits(bs, code, bits);
+}
+
+#endif

drivers/block/drbd/drbd_wrappers.h

@@ -0,0 +1,54 @@
+#ifndef _DRBD_WRAPPERS_H
+#define _DRBD_WRAPPERS_H
+
+#include <linux/ctype.h>
+#include <linux/mm.h>
+#include "drbd_int.h"
+
+/* see get_sb_bdev and bd_claim */
+extern char *drbd_sec_holder;
+
+/* sets the number of 512 byte sectors of our virtual device */
+static inline void drbd_set_my_capacity(struct drbd_conf *mdev,
+					sector_t size)
+{
+	/* set_capacity(mdev->this_bdev->bd_disk, size); */
+	set_capacity(mdev->vdisk, size);
+	mdev->this_bdev->bd_inode->i_size = (loff_t)size << 9;
+}
+
+#define drbd_bio_uptodate(bio) bio_flagged(bio, BIO_UPTODATE)
+
+/* bi_end_io handlers */
+extern void drbd_md_io_complete(struct bio *bio, int error);
+extern void drbd_peer_request_endio(struct bio *bio, int error);
+extern void drbd_request_endio(struct bio *bio, int error);
+
+/*
+ * used to submit our private bio
+ */
+static inline void drbd_generic_make_request(struct drbd_conf *mdev,
+					     int fault_type, struct bio *bio)
+{
+	__release(local);
+	if (!bio->bi_bdev) {
+		printk(KERN_ERR "drbd%d: drbd_generic_make_request: "
+				"bio->bi_bdev == NULL\n",
+		       mdev_to_minor(mdev));
+		dump_stack();
+		bio_endio(bio, -ENODEV);
+		return;
+	}
+
+	if (drbd_insert_fault(mdev, fault_type))
+		bio_endio(bio, -EIO);
+	else
+		generic_make_request(bio);
+}
+
+#ifndef __CHECKER__
+# undef __cond_lock
+# define __cond_lock(x,c) (c)
+#endif
+
+#endif