Fixed MTP to work with TWRP

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 +1,8 @@
+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
+drbd-$(CONFIG_DEBUG_FS) += drbd_debugfs.o
+
+obj-$(CONFIG_BLK_DEV_DRBD)     += drbd.o

drivers/block/drbd/drbd_debugfs.c

@@ -0,0 +1,958 @@
+#define pr_fmt(fmt) "drbd debugfs: " fmt
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/debugfs.h>
+#include <linux/seq_file.h>
+#include <linux/stat.h>
+#include <linux/jiffies.h>
+#include <linux/list.h>
+
+#include "drbd_int.h"
+#include "drbd_req.h"
+#include "drbd_debugfs.h"
+
+
+/**********************************************************************
+ * Whenever you change the file format, remember to bump the version. *
+ **********************************************************************/
+
+static struct dentry *drbd_debugfs_root;
+static struct dentry *drbd_debugfs_version;
+static struct dentry *drbd_debugfs_resources;
+static struct dentry *drbd_debugfs_minors;
+
+static void seq_print_age_or_dash(struct seq_file *m, bool valid, unsigned long dt)
+{
+	if (valid)
+		seq_printf(m, "\t%d", jiffies_to_msecs(dt));
+	else
+		seq_printf(m, "\t-");
+}
+
+static void __seq_print_rq_state_bit(struct seq_file *m,
+	bool is_set, char *sep, const char *set_name, const char *unset_name)
+{
+	if (is_set && set_name) {
+		seq_putc(m, *sep);
+		seq_puts(m, set_name);
+		*sep = '|';
+	} else if (!is_set && unset_name) {
+		seq_putc(m, *sep);
+		seq_puts(m, unset_name);
+		*sep = '|';
+	}
+}
+
+static void seq_print_rq_state_bit(struct seq_file *m,
+	bool is_set, char *sep, const char *set_name)
+{
+	__seq_print_rq_state_bit(m, is_set, sep, set_name, NULL);
+}
+
+/* pretty print enum drbd_req_state_bits req->rq_state */
+static void seq_print_request_state(struct seq_file *m, struct drbd_request *req)
+{
+	unsigned int s = req->rq_state;
+	char sep = ' ';
+	seq_printf(m, "\t0x%08x", s);
+	seq_printf(m, "\tmaster: %s", req->master_bio ? "pending" : "completed");
+
+	/* RQ_WRITE ignored, already reported */
+	seq_puts(m, "\tlocal:");
+	seq_print_rq_state_bit(m, s & RQ_IN_ACT_LOG, &sep, "in-AL");
+	seq_print_rq_state_bit(m, s & RQ_POSTPONED, &sep, "postponed");
+	seq_print_rq_state_bit(m, s & RQ_COMPLETION_SUSP, &sep, "suspended");
+	sep = ' ';
+	seq_print_rq_state_bit(m, s & RQ_LOCAL_PENDING, &sep, "pending");
+	seq_print_rq_state_bit(m, s & RQ_LOCAL_COMPLETED, &sep, "completed");
+	seq_print_rq_state_bit(m, s & RQ_LOCAL_ABORTED, &sep, "aborted");
+	seq_print_rq_state_bit(m, s & RQ_LOCAL_OK, &sep, "ok");
+	if (sep == ' ')
+		seq_puts(m, " -");
+
+	/* for_each_connection ... */
+	seq_printf(m, "\tnet:");
+	sep = ' ';
+	seq_print_rq_state_bit(m, s & RQ_NET_PENDING, &sep, "pending");
+	seq_print_rq_state_bit(m, s & RQ_NET_QUEUED, &sep, "queued");
+	seq_print_rq_state_bit(m, s & RQ_NET_SENT, &sep, "sent");
+	seq_print_rq_state_bit(m, s & RQ_NET_DONE, &sep, "done");
+	seq_print_rq_state_bit(m, s & RQ_NET_SIS, &sep, "sis");
+	seq_print_rq_state_bit(m, s & RQ_NET_OK, &sep, "ok");
+	if (sep == ' ')
+		seq_puts(m, " -");
+
+	seq_printf(m, " :");
+	sep = ' ';
+	seq_print_rq_state_bit(m, s & RQ_EXP_RECEIVE_ACK, &sep, "B");
+	seq_print_rq_state_bit(m, s & RQ_EXP_WRITE_ACK, &sep, "C");
+	seq_print_rq_state_bit(m, s & RQ_EXP_BARR_ACK, &sep, "barr");
+	if (sep == ' ')
+		seq_puts(m, " -");
+	seq_printf(m, "\n");
+}
+
+static void seq_print_one_request(struct seq_file *m, struct drbd_request *req, unsigned long now)
+{
+	/* change anything here, fixup header below! */
+	unsigned int s = req->rq_state;
+
+#define RQ_HDR_1 "epoch\tsector\tsize\trw"
+	seq_printf(m, "0x%x\t%llu\t%u\t%s",
+		req->epoch,
+		(unsigned long long)req->i.sector, req->i.size >> 9,
+		(s & RQ_WRITE) ? "W" : "R");
+
+#define RQ_HDR_2 "\tstart\tin AL\tsubmit"
+	seq_printf(m, "\t%d", jiffies_to_msecs(now - req->start_jif));
+	seq_print_age_or_dash(m, s & RQ_IN_ACT_LOG, now - req->in_actlog_jif);
+	seq_print_age_or_dash(m, s & RQ_LOCAL_PENDING, now - req->pre_submit_jif);
+
+#define RQ_HDR_3 "\tsent\tacked\tdone"
+	seq_print_age_or_dash(m, s & RQ_NET_SENT, now - req->pre_send_jif);
+	seq_print_age_or_dash(m, (s & RQ_NET_SENT) && !(s & RQ_NET_PENDING), now - req->acked_jif);
+	seq_print_age_or_dash(m, s & RQ_NET_DONE, now - req->net_done_jif);
+
+#define RQ_HDR_4 "\tstate\n"
+	seq_print_request_state(m, req);
+}
+#define RQ_HDR RQ_HDR_1 RQ_HDR_2 RQ_HDR_3 RQ_HDR_4
+
+static void seq_print_minor_vnr_req(struct seq_file *m, struct drbd_request *req, unsigned long now)
+{
+	seq_printf(m, "%u\t%u\t", req->device->minor, req->device->vnr);
+	seq_print_one_request(m, req, now);
+}
+
+static void seq_print_resource_pending_meta_io(struct seq_file *m, struct drbd_resource *resource, unsigned long now)
+{
+	struct drbd_device *device;
+	unsigned int i;
+
+	seq_puts(m, "minor\tvnr\tstart\tsubmit\tintent\n");
+	rcu_read_lock();
+	idr_for_each_entry(&resource->devices, device, i) {
+		struct drbd_md_io tmp;
+		/* In theory this is racy,
+		 * in the sense that there could have been a
+		 * drbd_md_put_buffer(); drbd_md_get_buffer();
+		 * between accessing these members here.  */
+		tmp = device->md_io;
+		if (atomic_read(&tmp.in_use)) {
+			seq_printf(m, "%u\t%u\t%d\t",
+				device->minor, device->vnr,
+				jiffies_to_msecs(now - tmp.start_jif));
+			if (time_before(tmp.submit_jif, tmp.start_jif))
+				seq_puts(m, "-\t");
+			else
+				seq_printf(m, "%d\t", jiffies_to_msecs(now - tmp.submit_jif));
+			seq_printf(m, "%s\n", tmp.current_use);
+		}
+	}
+	rcu_read_unlock();
+}
+
+static void seq_print_waiting_for_AL(struct seq_file *m, struct drbd_resource *resource, unsigned long now)
+{
+	struct drbd_device *device;
+	unsigned int i;
+
+	seq_puts(m, "minor\tvnr\tage\t#waiting\n");
+	rcu_read_lock();
+	idr_for_each_entry(&resource->devices, device, i) {
+		unsigned long jif;
+		struct drbd_request *req;
+		int n = atomic_read(&device->ap_actlog_cnt);
+		if (n) {
+			spin_lock_irq(&device->resource->req_lock);
+			req = list_first_entry_or_null(&device->pending_master_completion[1],
+				struct drbd_request, req_pending_master_completion);
+			/* if the oldest request does not wait for the activity log
+			 * it is not interesting for us here */
+			if (req && !(req->rq_state & RQ_IN_ACT_LOG))
+				jif = req->start_jif;
+			else
+				req = NULL;
+			spin_unlock_irq(&device->resource->req_lock);
+		}
+		if (n) {
+			seq_printf(m, "%u\t%u\t", device->minor, device->vnr);
+			if (req)
+				seq_printf(m, "%u\t", jiffies_to_msecs(now - jif));
+			else
+				seq_puts(m, "-\t");
+			seq_printf(m, "%u\n", n);
+		}
+	}
+	rcu_read_unlock();
+}
+
+static void seq_print_device_bitmap_io(struct seq_file *m, struct drbd_device *device, unsigned long now)
+{
+	struct drbd_bm_aio_ctx *ctx;
+	unsigned long start_jif;
+	unsigned int in_flight;
+	unsigned int flags;
+	spin_lock_irq(&device->resource->req_lock);
+	ctx = list_first_entry_or_null(&device->pending_bitmap_io, struct drbd_bm_aio_ctx, list);
+	if (ctx && ctx->done)
+		ctx = NULL;
+	if (ctx) {
+		start_jif = ctx->start_jif;
+		in_flight = atomic_read(&ctx->in_flight);
+		flags = ctx->flags;
+	}
+	spin_unlock_irq(&device->resource->req_lock);
+	if (ctx) {
+		seq_printf(m, "%u\t%u\t%c\t%u\t%u\n",
+			device->minor, device->vnr,
+			(flags & BM_AIO_READ) ? 'R' : 'W',
+			jiffies_to_msecs(now - start_jif),
+			in_flight);
+	}
+}
+
+static void seq_print_resource_pending_bitmap_io(struct seq_file *m, struct drbd_resource *resource, unsigned long now)
+{
+	struct drbd_device *device;
+	unsigned int i;
+
+	seq_puts(m, "minor\tvnr\trw\tage\t#in-flight\n");
+	rcu_read_lock();
+	idr_for_each_entry(&resource->devices, device, i) {
+		seq_print_device_bitmap_io(m, device, now);
+	}
+	rcu_read_unlock();
+}
+
+/* pretty print enum peer_req->flags */
+static void seq_print_peer_request_flags(struct seq_file *m, struct drbd_peer_request *peer_req)
+{
+	unsigned long f = peer_req->flags;
+	char sep = ' ';
+
+	__seq_print_rq_state_bit(m, f & EE_SUBMITTED, &sep, "submitted", "preparing");
+	__seq_print_rq_state_bit(m, f & EE_APPLICATION, &sep, "application", "internal");
+	seq_print_rq_state_bit(m, f & EE_CALL_AL_COMPLETE_IO, &sep, "in-AL");
+	seq_print_rq_state_bit(m, f & EE_SEND_WRITE_ACK, &sep, "C");
+	seq_print_rq_state_bit(m, f & EE_MAY_SET_IN_SYNC, &sep, "set-in-sync");
+
+	if (f & EE_IS_TRIM) {
+		seq_putc(m, sep);
+		sep = '|';
+		if (f & EE_IS_TRIM_USE_ZEROOUT)
+			seq_puts(m, "zero-out");
+		else
+			seq_puts(m, "trim");
+	}
+	seq_putc(m, '\n');
+}
+
+static void seq_print_peer_request(struct seq_file *m,
+	struct drbd_device *device, struct list_head *lh,
+	unsigned long now)
+{
+	bool reported_preparing = false;
+	struct drbd_peer_request *peer_req;
+	list_for_each_entry(peer_req, lh, w.list) {
+		if (reported_preparing && !(peer_req->flags & EE_SUBMITTED))
+			continue;
+
+		if (device)
+			seq_printf(m, "%u\t%u\t", device->minor, device->vnr);
+
+		seq_printf(m, "%llu\t%u\t%c\t%u\t",
+			(unsigned long long)peer_req->i.sector, peer_req->i.size >> 9,
+			(peer_req->flags & EE_WRITE) ? 'W' : 'R',
+			jiffies_to_msecs(now - peer_req->submit_jif));
+		seq_print_peer_request_flags(m, peer_req);
+		if (peer_req->flags & EE_SUBMITTED)
+			break;
+		else
+			reported_preparing = true;
+	}
+}
+
+static void seq_print_device_peer_requests(struct seq_file *m,
+	struct drbd_device *device, unsigned long now)
+{
+	seq_puts(m, "minor\tvnr\tsector\tsize\trw\tage\tflags\n");
+	spin_lock_irq(&device->resource->req_lock);
+	seq_print_peer_request(m, device, &device->active_ee, now);
+	seq_print_peer_request(m, device, &device->read_ee, now);
+	seq_print_peer_request(m, device, &device->sync_ee, now);
+	spin_unlock_irq(&device->resource->req_lock);
+	if (test_bit(FLUSH_PENDING, &device->flags)) {
+		seq_printf(m, "%u\t%u\t-\t-\tF\t%u\tflush\n",
+			device->minor, device->vnr,
+			jiffies_to_msecs(now - device->flush_jif));
+	}
+}
+
+static void seq_print_resource_pending_peer_requests(struct seq_file *m,
+	struct drbd_resource *resource, unsigned long now)
+{
+	struct drbd_device *device;
+	unsigned int i;
+
+	rcu_read_lock();
+	idr_for_each_entry(&resource->devices, device, i) {
+		seq_print_device_peer_requests(m, device, now);
+	}
+	rcu_read_unlock();
+}
+
+static void seq_print_resource_transfer_log_summary(struct seq_file *m,
+	struct drbd_resource *resource,
+	struct drbd_connection *connection,
+	unsigned long now)
+{
+	struct drbd_request *req;
+	unsigned int count = 0;
+	unsigned int show_state = 0;
+
+	seq_puts(m, "n\tdevice\tvnr\t" RQ_HDR);
+	spin_lock_irq(&resource->req_lock);
+	list_for_each_entry(req, &connection->transfer_log, tl_requests) {
+		unsigned int tmp = 0;
+		unsigned int s;
+		++count;
+
+		/* don't disable irq "forever" */
+		if (!(count & 0x1ff)) {
+			struct drbd_request *req_next;
+			kref_get(&req->kref);
+			spin_unlock_irq(&resource->req_lock);
+			cond_resched();
+			spin_lock_irq(&resource->req_lock);
+			req_next = list_next_entry(req, tl_requests);
+			if (kref_put(&req->kref, drbd_req_destroy))
+				req = req_next;
+			if (&req->tl_requests == &connection->transfer_log)
+				break;
+		}
+
+		s = req->rq_state;
+
+		/* This is meant to summarize timing issues, to be able to tell
+		 * local disk problems from network problems.
+		 * Skip requests, if we have shown an even older request with
+		 * similar aspects already.  */
+		if (req->master_bio == NULL)
+			tmp |= 1;
+		if ((s & RQ_LOCAL_MASK) && (s & RQ_LOCAL_PENDING))
+			tmp |= 2;
+		if (s & RQ_NET_MASK) {
+			if (!(s & RQ_NET_SENT))
+				tmp |= 4;
+			if (s & RQ_NET_PENDING)
+				tmp |= 8;
+			if (!(s & RQ_NET_DONE))
+				tmp |= 16;
+		}
+		if ((tmp & show_state) == tmp)
+			continue;
+		show_state |= tmp;
+		seq_printf(m, "%u\t", count);
+		seq_print_minor_vnr_req(m, req, now);
+		if (show_state == 0x1f)
+			break;
+	}
+	spin_unlock_irq(&resource->req_lock);
+}
+
+/* TODO: transfer_log and friends should be moved to resource */
+static int in_flight_summary_show(struct seq_file *m, void *pos)
+{
+	struct drbd_resource *resource = m->private;
+	struct drbd_connection *connection;
+	unsigned long jif = jiffies;
+
+	connection = first_connection(resource);
+	/* This does not happen, actually.
+	 * But be robust and prepare for future code changes. */
+	if (!connection || !kref_get_unless_zero(&connection->kref))
+		return -ESTALE;
+
+	/* BUMP me if you change the file format/content/presentation */
+	seq_printf(m, "v: %u\n\n", 0);
+
+	seq_puts(m, "oldest bitmap IO\n");
+	seq_print_resource_pending_bitmap_io(m, resource, jif);
+	seq_putc(m, '\n');
+
+	seq_puts(m, "meta data IO\n");
+	seq_print_resource_pending_meta_io(m, resource, jif);
+	seq_putc(m, '\n');
+
+	seq_puts(m, "socket buffer stats\n");
+	/* for each connection ... once we have more than one */
+	rcu_read_lock();
+	if (connection->data.socket) {
+		/* open coded SIOCINQ, the "relevant" part */
+		struct tcp_sock *tp = tcp_sk(connection->data.socket->sk);
+		int answ = tp->rcv_nxt - tp->copied_seq;
+		seq_printf(m, "unread receive buffer: %u Byte\n", answ);
+		/* open coded SIOCOUTQ, the "relevant" part */
+		answ = tp->write_seq - tp->snd_una;
+		seq_printf(m, "unacked send buffer: %u Byte\n", answ);
+	}
+	rcu_read_unlock();
+	seq_putc(m, '\n');
+
+	seq_puts(m, "oldest peer requests\n");
+	seq_print_resource_pending_peer_requests(m, resource, jif);
+	seq_putc(m, '\n');
+
+	seq_puts(m, "application requests waiting for activity log\n");
+	seq_print_waiting_for_AL(m, resource, jif);
+	seq_putc(m, '\n');
+
+	seq_puts(m, "oldest application requests\n");
+	seq_print_resource_transfer_log_summary(m, resource, connection, jif);
+	seq_putc(m, '\n');
+
+	jif = jiffies - jif;
+	if (jif)
+		seq_printf(m, "generated in %d ms\n", jiffies_to_msecs(jif));
+	kref_put(&connection->kref, drbd_destroy_connection);
+	return 0;
+}
+
+/* simple_positive(file->f_dentry) respectively debugfs_positive(),
+ * but neither is "reachable" from here.
+ * So we have our own inline version of it above.  :-( */
+static inline int debugfs_positive(struct dentry *dentry)
+{
+        return dentry->d_inode && !d_unhashed(dentry);
+}
+
+/* make sure at *open* time that the respective object won't go away. */
+static int drbd_single_open(struct file *file, int (*show)(struct seq_file *, void *),
+		                void *data, struct kref *kref,
+				void (*release)(struct kref *))
+{
+	struct dentry *parent;
+	int ret = -ESTALE;
+
+	/* Are we still linked,
+	 * or has debugfs_remove() already been called? */
+	parent = file->f_dentry->d_parent;
+	/* not sure if this can happen: */
+	if (!parent || !parent->d_inode)
+		goto out;
+	/* serialize with d_delete() */
+	mutex_lock(&parent->d_inode->i_mutex);
+	/* Make sure the object is still alive */
+	if (debugfs_positive(file->f_dentry)
+	&& kref_get_unless_zero(kref))
+		ret = 0;
+	mutex_unlock(&parent->d_inode->i_mutex);
+	if (!ret) {
+		ret = single_open(file, show, data);
+		if (ret)
+			kref_put(kref, release);
+	}
+out:
+	return ret;
+}
+
+static int in_flight_summary_open(struct inode *inode, struct file *file)
+{
+	struct drbd_resource *resource = inode->i_private;
+	return drbd_single_open(file, in_flight_summary_show, resource,
+				&resource->kref, drbd_destroy_resource);
+}
+
+static int in_flight_summary_release(struct inode *inode, struct file *file)
+{
+	struct drbd_resource *resource = inode->i_private;
+	kref_put(&resource->kref, drbd_destroy_resource);
+	return single_release(inode, file);
+}
+
+static const struct file_operations in_flight_summary_fops = {
+	.owner		= THIS_MODULE,
+	.open		= in_flight_summary_open,
+	.read		= seq_read,
+	.llseek		= seq_lseek,
+	.release	= in_flight_summary_release,
+};
+
+void drbd_debugfs_resource_add(struct drbd_resource *resource)
+{
+	struct dentry *dentry;
+	if (!drbd_debugfs_resources)
+		return;
+
+	dentry = debugfs_create_dir(resource->name, drbd_debugfs_resources);
+	if (IS_ERR_OR_NULL(dentry))
+		goto fail;
+	resource->debugfs_res = dentry;
+
+	dentry = debugfs_create_dir("volumes", resource->debugfs_res);
+	if (IS_ERR_OR_NULL(dentry))
+		goto fail;
+	resource->debugfs_res_volumes = dentry;
+
+	dentry = debugfs_create_dir("connections", resource->debugfs_res);
+	if (IS_ERR_OR_NULL(dentry))
+		goto fail;
+	resource->debugfs_res_connections = dentry;
+
+	dentry = debugfs_create_file("in_flight_summary", S_IRUSR|S_IRGRP,
+			resource->debugfs_res, resource,
+			&in_flight_summary_fops);
+	if (IS_ERR_OR_NULL(dentry))
+		goto fail;
+	resource->debugfs_res_in_flight_summary = dentry;
+	return;
+
+fail:
+	drbd_debugfs_resource_cleanup(resource);
+	drbd_err(resource, "failed to create debugfs dentry\n");
+}
+
+static void drbd_debugfs_remove(struct dentry **dp)
+{
+	debugfs_remove(*dp);
+	*dp = NULL;
+}
+
+void drbd_debugfs_resource_cleanup(struct drbd_resource *resource)
+{
+	/* it is ok to call debugfs_remove(NULL) */
+	drbd_debugfs_remove(&resource->debugfs_res_in_flight_summary);
+	drbd_debugfs_remove(&resource->debugfs_res_connections);
+	drbd_debugfs_remove(&resource->debugfs_res_volumes);
+	drbd_debugfs_remove(&resource->debugfs_res);
+}
+
+static void seq_print_one_timing_detail(struct seq_file *m,
+	const struct drbd_thread_timing_details *tdp,
+	unsigned long now)
+{
+	struct drbd_thread_timing_details td;
+	/* No locking...
+	 * use temporary assignment to get at consistent data. */
+	do {
+		td = *tdp;
+	} while (td.cb_nr != tdp->cb_nr);
+	if (!td.cb_addr)
+		return;
+	seq_printf(m, "%u\t%d\t%s:%u\t%ps\n",
+			td.cb_nr,
+			jiffies_to_msecs(now - td.start_jif),
+			td.caller_fn, td.line,
+			td.cb_addr);
+}
+
+static void seq_print_timing_details(struct seq_file *m,
+		const char *title,
+		unsigned int cb_nr, struct drbd_thread_timing_details *tdp, unsigned long now)
+{
+	unsigned int start_idx;
+	unsigned int i;
+
+	seq_printf(m, "%s\n", title);
+	/* If not much is going on, this will result in natural ordering.
+	 * If it is very busy, we will possibly skip events, or even see wrap
+	 * arounds, which could only be avoided with locking.
+	 */
+	start_idx = cb_nr % DRBD_THREAD_DETAILS_HIST;
+	for (i = start_idx; i < DRBD_THREAD_DETAILS_HIST; i++)
+		seq_print_one_timing_detail(m, tdp+i, now);
+	for (i = 0; i < start_idx; i++)
+		seq_print_one_timing_detail(m, tdp+i, now);
+}
+
+static int callback_history_show(struct seq_file *m, void *ignored)
+{
+	struct drbd_connection *connection = m->private;
+	unsigned long jif = jiffies;
+
+	/* BUMP me if you change the file format/content/presentation */
+	seq_printf(m, "v: %u\n\n", 0);
+
+	seq_puts(m, "n\tage\tcallsite\tfn\n");
+	seq_print_timing_details(m, "worker", connection->w_cb_nr, connection->w_timing_details, jif);
+	seq_print_timing_details(m, "receiver", connection->r_cb_nr, connection->r_timing_details, jif);
+	return 0;
+}
+
+static int callback_history_open(struct inode *inode, struct file *file)
+{
+	struct drbd_connection *connection = inode->i_private;
+	return drbd_single_open(file, callback_history_show, connection,
+				&connection->kref, drbd_destroy_connection);
+}
+
+static int callback_history_release(struct inode *inode, struct file *file)
+{
+	struct drbd_connection *connection = inode->i_private;
+	kref_put(&connection->kref, drbd_destroy_connection);
+	return single_release(inode, file);
+}
+
+static const struct file_operations connection_callback_history_fops = {
+	.owner		= THIS_MODULE,
+	.open		= callback_history_open,
+	.read		= seq_read,
+	.llseek		= seq_lseek,
+	.release	= callback_history_release,
+};
+
+static int connection_oldest_requests_show(struct seq_file *m, void *ignored)
+{
+	struct drbd_connection *connection = m->private;
+	unsigned long now = jiffies;
+	struct drbd_request *r1, *r2;
+
+	/* BUMP me if you change the file format/content/presentation */
+	seq_printf(m, "v: %u\n\n", 0);
+
+	spin_lock_irq(&connection->resource->req_lock);
+	r1 = connection->req_next;
+	if (r1)
+		seq_print_minor_vnr_req(m, r1, now);
+	r2 = connection->req_ack_pending;
+	if (r2 && r2 != r1) {
+		r1 = r2;
+		seq_print_minor_vnr_req(m, r1, now);
+	}
+	r2 = connection->req_not_net_done;
+	if (r2 && r2 != r1)
+		seq_print_minor_vnr_req(m, r2, now);
+	spin_unlock_irq(&connection->resource->req_lock);
+	return 0;
+}
+
+static int connection_oldest_requests_open(struct inode *inode, struct file *file)
+{
+	struct drbd_connection *connection = inode->i_private;
+	return drbd_single_open(file, connection_oldest_requests_show, connection,
+				&connection->kref, drbd_destroy_connection);
+}
+
+static int connection_oldest_requests_release(struct inode *inode, struct file *file)
+{
+	struct drbd_connection *connection = inode->i_private;
+	kref_put(&connection->kref, drbd_destroy_connection);
+	return single_release(inode, file);
+}
+
+static const struct file_operations connection_oldest_requests_fops = {
+	.owner		= THIS_MODULE,
+	.open		= connection_oldest_requests_open,
+	.read		= seq_read,
+	.llseek		= seq_lseek,
+	.release	= connection_oldest_requests_release,
+};
+
+void drbd_debugfs_connection_add(struct drbd_connection *connection)
+{
+	struct dentry *conns_dir = connection->resource->debugfs_res_connections;
+	struct dentry *dentry;
+	if (!conns_dir)
+		return;
+
+	/* Once we enable mutliple peers,
+	 * these connections will have descriptive names.
+	 * For now, it is just the one connection to the (only) "peer". */
+	dentry = debugfs_create_dir("peer", conns_dir);
+	if (IS_ERR_OR_NULL(dentry))
+		goto fail;
+	connection->debugfs_conn = dentry;
+
+	dentry = debugfs_create_file("callback_history", S_IRUSR|S_IRGRP,
+			connection->debugfs_conn, connection,
+			&connection_callback_history_fops);
+	if (IS_ERR_OR_NULL(dentry))
+		goto fail;
+	connection->debugfs_conn_callback_history = dentry;
+
+	dentry = debugfs_create_file("oldest_requests", S_IRUSR|S_IRGRP,
+			connection->debugfs_conn, connection,
+			&connection_oldest_requests_fops);
+	if (IS_ERR_OR_NULL(dentry))
+		goto fail;
+	connection->debugfs_conn_oldest_requests = dentry;
+	return;
+
+fail:
+	drbd_debugfs_connection_cleanup(connection);
+	drbd_err(connection, "failed to create debugfs dentry\n");
+}
+
+void drbd_debugfs_connection_cleanup(struct drbd_connection *connection)
+{
+	drbd_debugfs_remove(&connection->debugfs_conn_callback_history);
+	drbd_debugfs_remove(&connection->debugfs_conn_oldest_requests);
+	drbd_debugfs_remove(&connection->debugfs_conn);
+}
+
+static void resync_dump_detail(struct seq_file *m, struct lc_element *e)
+{
+       struct bm_extent *bme = lc_entry(e, struct bm_extent, lce);
+
+       seq_printf(m, "%5d %s %s %s", bme->rs_left,
+		  test_bit(BME_NO_WRITES, &bme->flags) ? "NO_WRITES" : "---------",
+		  test_bit(BME_LOCKED, &bme->flags) ? "LOCKED" : "------",
+		  test_bit(BME_PRIORITY, &bme->flags) ? "PRIORITY" : "--------"
+		  );
+}
+
+static int device_resync_extents_show(struct seq_file *m, void *ignored)
+{
+	struct drbd_device *device = m->private;
+
+	/* BUMP me if you change the file format/content/presentation */
+	seq_printf(m, "v: %u\n\n", 0);
+
+	if (get_ldev_if_state(device, D_FAILED)) {
+		lc_seq_printf_stats(m, device->resync);
+		lc_seq_dump_details(m, device->resync, "rs_left flags", resync_dump_detail);
+		put_ldev(device);
+	}
+	return 0;
+}
+
+static int device_act_log_extents_show(struct seq_file *m, void *ignored)
+{
+	struct drbd_device *device = m->private;
+
+	/* BUMP me if you change the file format/content/presentation */
+	seq_printf(m, "v: %u\n\n", 0);
+
+	if (get_ldev_if_state(device, D_FAILED)) {
+		lc_seq_printf_stats(m, device->act_log);
+		lc_seq_dump_details(m, device->act_log, "", NULL);
+		put_ldev(device);
+	}
+	return 0;
+}
+
+static int device_oldest_requests_show(struct seq_file *m, void *ignored)
+{
+	struct drbd_device *device = m->private;
+	struct drbd_resource *resource = device->resource;
+	unsigned long now = jiffies;
+	struct drbd_request *r1, *r2;
+	int i;
+
+	/* BUMP me if you change the file format/content/presentation */
+	seq_printf(m, "v: %u\n\n", 0);
+
+	seq_puts(m, RQ_HDR);
+	spin_lock_irq(&resource->req_lock);
+	/* WRITE, then READ */
+	for (i = 1; i >= 0; --i) {
+		r1 = list_first_entry_or_null(&device->pending_master_completion[i],
+			struct drbd_request, req_pending_master_completion);
+		r2 = list_first_entry_or_null(&device->pending_completion[i],
+			struct drbd_request, req_pending_local);
+		if (r1)
+			seq_print_one_request(m, r1, now);
+		if (r2 && r2 != r1)
+			seq_print_one_request(m, r2, now);
+	}
+	spin_unlock_irq(&resource->req_lock);
+	return 0;
+}
+
+static int device_data_gen_id_show(struct seq_file *m, void *ignored)
+{
+	struct drbd_device *device = m->private;
+	struct drbd_md *md;
+	enum drbd_uuid_index idx;
+
+	if (!get_ldev_if_state(device, D_FAILED))
+		return -ENODEV;
+
+	md = &device->ldev->md;
+	spin_lock_irq(&md->uuid_lock);
+	for (idx = UI_CURRENT; idx <= UI_HISTORY_END; idx++) {
+		seq_printf(m, "0x%016llX\n", md->uuid[idx]);
+	}
+	spin_unlock_irq(&md->uuid_lock);
+	put_ldev(device);
+	return 0;
+}
+
+#define drbd_debugfs_device_attr(name)						\
+static int device_ ## name ## _open(struct inode *inode, struct file *file)	\
+{										\
+	struct drbd_device *device = inode->i_private;				\
+	return drbd_single_open(file, device_ ## name ## _show, device,		\
+				&device->kref, drbd_destroy_device);		\
+}										\
+static int device_ ## name ## _release(struct inode *inode, struct file *file)	\
+{										\
+	struct drbd_device *device = inode->i_private;				\
+	kref_put(&device->kref, drbd_destroy_device);				\
+	return single_release(inode, file);					\
+}										\
+static const struct file_operations device_ ## name ## _fops = {		\
+	.owner		= THIS_MODULE,						\
+	.open		= device_ ## name ## _open,				\
+	.read		= seq_read,						\
+	.llseek		= seq_lseek,						\
+	.release	= device_ ## name ## _release,				\
+};
+
+drbd_debugfs_device_attr(oldest_requests)
+drbd_debugfs_device_attr(act_log_extents)
+drbd_debugfs_device_attr(resync_extents)
+drbd_debugfs_device_attr(data_gen_id)
+
+void drbd_debugfs_device_add(struct drbd_device *device)
+{
+	struct dentry *vols_dir = device->resource->debugfs_res_volumes;
+	char minor_buf[8]; /* MINORMASK, MINORBITS == 20; */
+	char vnr_buf[8];   /* volume number vnr is even 16 bit only; */
+	char *slink_name = NULL;
+
+	struct dentry *dentry;
+	if (!vols_dir || !drbd_debugfs_minors)
+		return;
+
+	snprintf(vnr_buf, sizeof(vnr_buf), "%u", device->vnr);
+	dentry = debugfs_create_dir(vnr_buf, vols_dir);
+	if (IS_ERR_OR_NULL(dentry))
+		goto fail;
+	device->debugfs_vol = dentry;
+
+	snprintf(minor_buf, sizeof(minor_buf), "%u", device->minor);
+	slink_name = kasprintf(GFP_KERNEL, "../resources/%s/volumes/%u",
+			device->resource->name, device->vnr);
+	if (!slink_name)
+		goto fail;
+	dentry = debugfs_create_symlink(minor_buf, drbd_debugfs_minors, slink_name);
+	kfree(slink_name);
+	slink_name = NULL;
+	if (IS_ERR_OR_NULL(dentry))
+		goto fail;
+	device->debugfs_minor = dentry;
+
+#define DCF(name)	do {					\
+	dentry = debugfs_create_file(#name, S_IRUSR|S_IRGRP,	\
+			device->debugfs_vol, device,		\
+			&device_ ## name ## _fops);		\
+	if (IS_ERR_OR_NULL(dentry))				\
+		goto fail;					\
+	device->debugfs_vol_ ## name = dentry;			\
+	} while (0)
+
+	DCF(oldest_requests);
+	DCF(act_log_extents);
+	DCF(resync_extents);
+	DCF(data_gen_id);
+#undef DCF
+	return;
+
+fail:
+	drbd_debugfs_device_cleanup(device);
+	drbd_err(device, "failed to create debugfs entries\n");
+}
+
+void drbd_debugfs_device_cleanup(struct drbd_device *device)
+{
+	drbd_debugfs_remove(&device->debugfs_minor);
+	drbd_debugfs_remove(&device->debugfs_vol_oldest_requests);
+	drbd_debugfs_remove(&device->debugfs_vol_act_log_extents);
+	drbd_debugfs_remove(&device->debugfs_vol_resync_extents);
+	drbd_debugfs_remove(&device->debugfs_vol_data_gen_id);
+	drbd_debugfs_remove(&device->debugfs_vol);
+}
+
+void drbd_debugfs_peer_device_add(struct drbd_peer_device *peer_device)
+{
+	struct dentry *conn_dir = peer_device->connection->debugfs_conn;
+	struct dentry *dentry;
+	char vnr_buf[8];
+
+	if (!conn_dir)
+		return;
+
+	snprintf(vnr_buf, sizeof(vnr_buf), "%u", peer_device->device->vnr);
+	dentry = debugfs_create_dir(vnr_buf, conn_dir);
+	if (IS_ERR_OR_NULL(dentry))
+		goto fail;
+	peer_device->debugfs_peer_dev = dentry;
+	return;
+
+fail:
+	drbd_debugfs_peer_device_cleanup(peer_device);
+	drbd_err(peer_device, "failed to create debugfs entries\n");
+}
+
+void drbd_debugfs_peer_device_cleanup(struct drbd_peer_device *peer_device)
+{
+	drbd_debugfs_remove(&peer_device->debugfs_peer_dev);
+}
+
+static int drbd_version_show(struct seq_file *m, void *ignored)
+{
+	seq_printf(m, "# %s\n", drbd_buildtag());
+	seq_printf(m, "VERSION=%s\n", REL_VERSION);
+	seq_printf(m, "API_VERSION=%u\n", API_VERSION);
+	seq_printf(m, "PRO_VERSION_MIN=%u\n", PRO_VERSION_MIN);
+	seq_printf(m, "PRO_VERSION_MAX=%u\n", PRO_VERSION_MAX);
+	return 0;
+}
+
+static int drbd_version_open(struct inode *inode, struct file *file)
+{
+	return single_open(file, drbd_version_show, NULL);
+}
+
+static struct file_operations drbd_version_fops = {
+	.owner = THIS_MODULE,
+	.open = drbd_version_open,
+	.llseek = seq_lseek,
+	.read = seq_read,
+	.release = single_release,
+};
+
+/* not __exit, may be indirectly called
+ * from the module-load-failure path as well. */
+void drbd_debugfs_cleanup(void)
+{
+	drbd_debugfs_remove(&drbd_debugfs_resources);
+	drbd_debugfs_remove(&drbd_debugfs_minors);
+	drbd_debugfs_remove(&drbd_debugfs_version);
+	drbd_debugfs_remove(&drbd_debugfs_root);
+}
+
+int __init drbd_debugfs_init(void)
+{
+	struct dentry *dentry;
+
+	dentry = debugfs_create_dir("drbd", NULL);
+	if (IS_ERR_OR_NULL(dentry))
+		goto fail;
+	drbd_debugfs_root = dentry;
+
+	dentry = debugfs_create_file("version", 0444, drbd_debugfs_root, NULL, &drbd_version_fops);
+	if (IS_ERR_OR_NULL(dentry))
+		goto fail;
+	drbd_debugfs_version = dentry;
+
+	dentry = debugfs_create_dir("resources", drbd_debugfs_root);
+	if (IS_ERR_OR_NULL(dentry))
+		goto fail;
+	drbd_debugfs_resources = dentry;
+
+	dentry = debugfs_create_dir("minors", drbd_debugfs_root);
+	if (IS_ERR_OR_NULL(dentry))
+		goto fail;
+	drbd_debugfs_minors = dentry;
+	return 0;
+
+fail:
+	drbd_debugfs_cleanup();
+	if (dentry)
+		return PTR_ERR(dentry);
+	else
+		return -EINVAL;
+}

drivers/block/drbd/drbd_debugfs.h

@@ -0,0 +1,39 @@
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/debugfs.h>
+
+#include "drbd_int.h"
+
+#ifdef CONFIG_DEBUG_FS
+int __init drbd_debugfs_init(void);
+void drbd_debugfs_cleanup(void);
+
+void drbd_debugfs_resource_add(struct drbd_resource *resource);
+void drbd_debugfs_resource_cleanup(struct drbd_resource *resource);
+
+void drbd_debugfs_connection_add(struct drbd_connection *connection);
+void drbd_debugfs_connection_cleanup(struct drbd_connection *connection);
+
+void drbd_debugfs_device_add(struct drbd_device *device);
+void drbd_debugfs_device_cleanup(struct drbd_device *device);
+
+void drbd_debugfs_peer_device_add(struct drbd_peer_device *peer_device);
+void drbd_debugfs_peer_device_cleanup(struct drbd_peer_device *peer_device);
+#else
+
+static inline int __init drbd_debugfs_init(void) { return -ENODEV; }
+static inline void drbd_debugfs_cleanup(void) { }
+
+static inline void drbd_debugfs_resource_add(struct drbd_resource *resource) { }
+static inline void drbd_debugfs_resource_cleanup(struct drbd_resource *resource) { }
+
+static inline void drbd_debugfs_connection_add(struct drbd_connection *connection) { }
+static inline void drbd_debugfs_connection_cleanup(struct drbd_connection *connection) { }
+
+static inline void drbd_debugfs_device_add(struct drbd_device *device) { }
+static inline void drbd_debugfs_device_cleanup(struct drbd_device *device) { }
+
+static inline void drbd_debugfs_peer_device_add(struct drbd_peer_device *peer_device) { }
+static inline void drbd_debugfs_peer_device_cleanup(struct drbd_peer_device *peer_device) { }
+
+#endif

drivers/block/drbd/drbd_interval.c

@@ -0,0 +1,179 @@
+#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;
+}
+
+RB_DECLARE_CALLBACKS(static, augment_callbacks, struct drbd_interval, rb,
+		     sector_t, end, compute_subtree_last);
+
+/**
+ * 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;
+	sector_t this_end = this->sector + (this->size >> 9);
+
+	BUG_ON(!IS_ALIGNED(this->size, 512));
+
+	while (*new) {
+		struct drbd_interval *here =
+			rb_entry(*new, struct drbd_interval, rb);
+
+		parent = *new;
+		if (here->end < this_end)
+			here->end = this_end;
+		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;
+	}
+
+	this->end = this_end;
+	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 +1,42 @@
+#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;		/* someone is waiting for this to complete */
+	int completed:1;	/* this has been completed already;
+				 * ignore for conflict detection */
+};
+
+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 +1,54 @@
+#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 +1,368 @@
+/*
+   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,
+};
+
+static 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);
+}
+
+static void drbd_get_syncer_progress(struct drbd_device *device,
+		union drbd_dev_state state, unsigned long *rs_total,
+		unsigned long *bits_left, unsigned int *per_mil_done)
+{
+	/* this is to break it at compile time when we change that, in case we
+	 * want to support more than (1<<32) bits on a 32bit arch. */
+	typecheck(unsigned long, device->rs_total);
+	*rs_total = device->rs_total;
+
+	/* note: both rs_total and rs_left are in bits, i.e. in
+	 * units of BM_BLOCK_SIZE.
+	 * for the percentage, we don't care. */
+
+	if (state.conn == C_VERIFY_S || state.conn == C_VERIFY_T)
+		*bits_left = device->ov_left;
+	else
+		*bits_left = drbd_bm_total_weight(device) - device->rs_failed;
+	/* >> 10 to prevent overflow,
+	 * +1 to prevent division by zero */
+	if (*bits_left > *rs_total) {
+		/* D'oh. Maybe a logic bug somewhere.  More likely just a race
+		 * between state change and reset of rs_total.
+		 */
+		*bits_left = *rs_total;
+		*per_mil_done = *rs_total ? 0 : 1000;
+	} else {
+		/* Make sure the division happens in long context.
+		 * We allow up to one petabyte storage right now,
+		 * at a granularity of 4k per bit that is 2**38 bits.
+		 * After shift right and multiplication by 1000,
+		 * this should still fit easily into a 32bit long,
+		 * so we don't need a 64bit division on 32bit arch.
+		 * Note: currently we don't support such large bitmaps on 32bit
+		 * arch anyways, but no harm done to be prepared for it here.
+		 */
+		unsigned int shift = *rs_total > UINT_MAX ? 16 : 10;
+		unsigned long left = *bits_left >> shift;
+		unsigned long total = 1UL + (*rs_total >> shift);
+		unsigned long tmp = 1000UL - left * 1000UL/total;
+		*per_mil_done = tmp;
+	}
+}
+
+
+/*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_device *device, struct seq_file *seq,
+		union drbd_dev_state state)
+{
+	unsigned long db, dt, dbdt, rt, rs_total, rs_left;
+	unsigned int res;
+	int i, x, y;
+	int stalled = 0;
+
+	drbd_get_syncer_progress(device, state, &rs_total, &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 (state.conn == C_VERIFY_S || 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 (rs_total > (4UL << (30 - BM_BLOCK_SHIFT)))
+		seq_printf(seq, "(%lu/%lu)M",
+			    (unsigned long) Bit2KB(rs_left >> 10),
+			    (unsigned long) Bit2KB(rs_total >> 10));
+	else
+		seq_printf(seq, "(%lu/%lu)K",
+			    (unsigned long) Bit2KB(rs_left),
+			    (unsigned long) Bit2KB(rs_total));
+
+	seq_printf(seq, "\n\t");
+
+	/* 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 = (device->rs_last_mark + 2) % DRBD_SYNC_MARKS;
+	dt = (jiffies - device->rs_mark_time[i]) / HZ;
+	if (dt > 180)
+		stalled = 1;
+
+	if (!dt)
+		dt++;
+	db = device->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 = (device->rs_last_mark + DRBD_SYNC_MARKS-1) % DRBD_SYNC_MARKS;
+		dt = (jiffies - device->rs_mark_time[i]) / HZ;
+		if (!dt)
+			dt++;
+		db = device->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 - device->rs_start - device->rs_paused) / HZ;
+	if (dt == 0)
+		dt = 1;
+	db = rs_total - rs_left;
+	dbdt = Bit2KB(db/dt);
+	seq_printf_with_thousands_grouping(seq, dbdt);
+	seq_printf(seq, ")");
+
+	if (state.conn == C_SYNC_TARGET ||
+	    state.conn == C_VERIFY_S) {
+		seq_printf(seq, " want: ");
+		seq_printf_with_thousands_grouping(seq, device->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(device);
+		unsigned long bit_pos;
+		unsigned long long stop_sector = 0;
+		if (state.conn == C_VERIFY_S ||
+		    state.conn == C_VERIFY_T) {
+			bit_pos = bm_bits - device->ov_left;
+			if (verify_can_do_stop_sector(device))
+				stop_sector = device->ov_stop_sector;
+		} else
+			bit_pos = device->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 int drbd_seq_show(struct seq_file *seq, void *v)
+{
+	int i, prev_i = -1;
+	const char *sn;
+	struct drbd_device *device;
+	struct net_conf *nc;
+	union drbd_dev_state state;
+	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(&drbd_devices, device, i) {
+		if (prev_i != i - 1)
+			seq_printf(seq, "\n");
+		prev_i = i;
+
+		state = device->state;
+		sn = drbd_conn_str(state.conn);
+
+		if (state.conn == C_STANDALONE &&
+		    state.disk == D_DISKLESS &&
+		    state.role == R_SECONDARY) {
+			seq_printf(seq, "%2d: cs:Unconfigured\n", i);
+		} else {
+			/* reset device->congestion_reason */
+			bdi_rw_congested(&device->rq_queue->backing_dev_info);
+
+			nc = rcu_dereference(first_peer_device(device)->connection->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(state.role),
+			   drbd_role_str(state.peer),
+			   drbd_disk_str(state.disk),
+			   drbd_disk_str(state.pdsk),
+			   wp,
+			   drbd_suspended(device) ? 's' : 'r',
+			   state.aftr_isp ? 'a' : '-',
+			   state.peer_isp ? 'p' : '-',
+			   state.user_isp ? 'u' : '-',
+			   device->congestion_reason ?: '-',
+			   test_bit(AL_SUSPENDED, &device->flags) ? 's' : '-',
+			   device->send_cnt/2,
+			   device->recv_cnt/2,
+			   device->writ_cnt/2,
+			   device->read_cnt/2,
+			   device->al_writ_cnt,
+			   device->bm_writ_cnt,
+			   atomic_read(&device->local_cnt),
+			   atomic_read(&device->ap_pending_cnt) +
+			   atomic_read(&device->rs_pending_cnt),
+			   atomic_read(&device->unacked_cnt),
+			   atomic_read(&device->ap_bio_cnt),
+			   first_peer_device(device)->connection->epochs,
+			   write_ordering_chars[device->resource->write_ordering]
+			);
+			seq_printf(seq, " oos:%llu\n",
+				   Bit2KB((unsigned long long)
+					   drbd_bm_total_weight(device)));
+		}
+		if (state.conn == C_SYNC_SOURCE ||
+		    state.conn == C_SYNC_TARGET ||
+		    state.conn == C_VERIFY_S ||
+		    state.conn == C_VERIFY_T)
+			drbd_syncer_progress(device, seq, state);
+
+		if (proc_details >= 1 && get_ldev_if_state(device, D_FAILED)) {
+			lc_seq_printf_stats(seq, device->resync);
+			lc_seq_printf_stats(seq, device->act_log);
+			put_ldev(device);
+		}
+
+		if (proc_details >= 2)
+			seq_printf(seq, "\tblocked on activity log: %d\n", atomic_read(&device->ap_actlog_cnt));
+	}
+	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, NULL);
+		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_protocol.h

@@ -0,0 +1,307 @@
+#ifndef __DRBD_PROTOCOL_H
+#define __DRBD_PROTOCOL_H
+
+enum drbd_packet {
+	/* receiver (data socket) */
+	P_DATA		      = 0x00,
+	P_DATA_REPLY	      = 0x01, /* Response to P_DATA_REQUEST */
+	P_RS_DATA_REPLY	      = 0x02, /* Response to P_RS_DATA_REQUEST */
+	P_BARRIER	      = 0x03,
+	P_BITMAP	      = 0x04,
+	P_BECOME_SYNC_TARGET  = 0x05,
+	P_BECOME_SYNC_SOURCE  = 0x06,
+	P_UNPLUG_REMOTE	      = 0x07, /* Used at various times to hint the peer */
+	P_DATA_REQUEST	      = 0x08, /* Used to ask for a data block */
+	P_RS_DATA_REQUEST     = 0x09, /* Used to ask for a data block for resync */
+	P_SYNC_PARAM	      = 0x0a,
+	P_PROTOCOL	      = 0x0b,
+	P_UUIDS		      = 0x0c,
+	P_SIZES		      = 0x0d,
+	P_STATE		      = 0x0e,
+	P_SYNC_UUID	      = 0x0f,
+	P_AUTH_CHALLENGE      = 0x10,
+	P_AUTH_RESPONSE	      = 0x11,
+	P_STATE_CHG_REQ	      = 0x12,
+
+	/* asender (meta socket */
+	P_PING		      = 0x13,
+	P_PING_ACK	      = 0x14,
+	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_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... */
+	P_BARRIER_ACK	      = 0x1c,
+	P_STATE_CHG_REPLY     = 0x1d,
+
+	/* "new" commands, no longer fitting into the ordering scheme above */
+
+	P_OV_REQUEST	      = 0x1e, /* data socket */
+	P_OV_REPLY	      = 0x1f,
+	P_OV_RESULT	      = 0x20, /* meta socket */
+	P_CSUM_RS_REQUEST     = 0x21, /* data socket */
+	P_RS_IS_IN_SYNC	      = 0x22, /* meta socket */
+	P_SYNC_PARAM89	      = 0x23, /* data socket, protocol version 89 replacement for P_SYNC_PARAM */
+	P_COMPRESSED_BITMAP   = 0x24, /* compressed or otherwise encoded bitmap transfer */
+	/* P_CKPT_FENCE_REQ      = 0x25, * currently reserved for protocol D */
+	/* P_CKPT_DISABLE_REQ    = 0x26, * currently reserved for protocol D */
+	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 */
+        /* 0x2e to 0x30 reserved, used in drbd 9 */
+
+	/* REQ_DISCARD. We used "discard" in different contexts before,
+	 * which is why I chose TRIM here, to disambiguate. */
+	P_TRIM                = 0x31,
+
+	P_MAY_IGNORE	      = 0x100, /* Flag to test if (cmd > P_MAY_IGNORE) ... */
+	P_MAX_OPT_CMD	      = 0x101,
+
+	/* special command ids for handshake */
+
+	P_INITIAL_META	      = 0xfff1, /* First Packet on the MetaSock */
+	P_INITIAL_DATA	      = 0xfff2, /* First Packet on the Socket */
+
+	P_CONNECTION_FEATURES = 0xfffe	/* FIXED for the next century! */
+};
+
+#ifndef __packed
+#define __packed __attribute__((packed))
+#endif
+
+/* This is the layout for a packet on the wire.
+ * The byteorder is the network byte order.
+ *     (except block_id and barrier fields.
+ *	these are pointers to local structs
+ *	and have no relevance for the partner,
+ *	which just echoes them as received.)
+ *
+ * NOTE that the payload starts at a long aligned offset,
+ * regardless of 32 or 64 bit arch!
+ */
+struct p_header80 {
+	u32	  magic;
+	u16	  command;
+	u16	  length;	/* bytes of data after this header */
+} __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;
+} __packed;
+
+struct p_header100 {
+	u32	  magic;
+	u16	  volume;
+	u16	  command;
+	u32	  length;
+	u32	  pad;
+} __packed;
+
+/* these defines must not be changed without changing the protocol version */
+#define DP_HARDBARRIER	      1 /* depricated */
+#define DP_RW_SYNC	      2 /* equals REQ_SYNC    */
+#define DP_MAY_SET_IN_SYNC    4
+#define DP_UNPLUG             8 /* not used anymore   */
+#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 {
+	u64	    sector;    /* 64 bits sector number */
+	u64	    block_id;  /* to identify the request in protocol B&C */
+	u32	    seq_num;
+	u32	    dp_flags;
+} __packed;
+
+struct p_trim {
+	struct p_data p_data;
+	u32	    size;	/* == bio->bi_size */
+} __packed;
+
+/*
+ * commands which share a struct:
+ *  p_block_ack:
+ *   P_RECV_ACK (proto B), P_WRITE_ACK (proto C),
+ *   P_SUPERSEDED (proto C, two-primaries conflict detection)
+ *  p_block_req:
+ *   P_DATA_REQUEST, P_RS_DATA_REQUEST
+ */
+struct p_block_ack {
+	u64	    sector;
+	u64	    block_id;
+	u32	    blksize;
+	u32	    seq_num;
+} __packed;
+
+struct p_block_req {
+	u64 sector;
+	u64 block_id;
+	u32 blksize;
+	u32 pad;	/* to multiple of 8 Byte */
+} __packed;
+
+/*
+ * commands with their own struct for additional fields:
+ *   P_CONNECTION_FEATURES
+ *   P_BARRIER
+ *   P_BARRIER_ACK
+ *   P_SYNC_PARAM
+ *   ReportParams
+ */
+
+#define FF_TRIM      1
+
+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 reserved array shall be zero.
+	 */
+
+	u32 _pad;
+	u64 reserved[7];
+} __packed;
+
+struct p_barrier {
+	u32 barrier;	/* barrier number _handle_ only */
+	u32 pad;	/* to multiple of 8 Byte */
+} __packed;
+
+struct p_barrier_ack {
+	u32 barrier;
+	u32 set_size;
+} __packed;
+
+struct p_rs_param {
+	u32 resync_rate;
+
+	      /* Since protocol version 88 and higher. */
+	char verify_alg[0];
+} __packed;
+
+struct p_rs_param_89 {
+	u32 resync_rate;
+	/* protocol version 89: */
+	char verify_alg[SHARED_SECRET_MAX];
+	char csums_alg[SHARED_SECRET_MAX];
+} __packed;
+
+struct p_rs_param_95 {
+	u32 resync_rate;
+	char verify_alg[SHARED_SECRET_MAX];
+	char csums_alg[SHARED_SECRET_MAX];
+	u32 c_plan_ahead;
+	u32 c_delay_target;
+	u32 c_fill_target;
+	u32 c_max_rate;
+} __packed;
+
+enum drbd_conn_flags {
+	CF_DISCARD_MY_DATA = 1,
+	CF_DRY_RUN = 2,
+};
+
+struct p_protocol {
+	u32 protocol;
+	u32 after_sb_0p;
+	u32 after_sb_1p;
+	u32 after_sb_2p;
+	u32 conn_flags;
+	u32 two_primaries;
+
+	/* Since protocol version 87 and higher. */
+	char integrity_alg[0];
+
+} __packed;
+
+struct p_uuids {
+	u64 uuid[UI_EXTENDED_SIZE];
+} __packed;
+
+struct p_rs_uuid {
+	u64	    uuid;
+} __packed;
+
+struct p_sizes {
+	u64	    d_size;  /* size of disk */
+	u64	    u_size;  /* user requested size */
+	u64	    c_size;  /* current exported size */
+	u32	    max_bio_size;  /* Maximal size of a BIO */
+	u16	    queue_order_type;  /* not yet implemented in DRBD*/
+	u16	    dds_flags; /* use enum dds_flags here. */
+} __packed;
+
+struct p_state {
+	u32	    state;
+} __packed;
+
+struct p_req_state {
+	u32	    mask;
+	u32	    val;
+} __packed;
+
+struct p_req_state_reply {
+	u32	    retcode;
+} __packed;
+
+struct p_drbd06_param {
+	u64	  size;
+	u32	  state;
+	u32	  blksize;
+	u32	  protocol;
+	u32	  version;
+	u32	  gen_cnt[5];
+	u32	  bit_map_gen[5];
+} __packed;
+
+struct p_block_desc {
+	u64 sector;
+	u32 blksize;
+	u32 pad;	/* to multiple of 8 Byte */
+} __packed;
+
+/* Valid values for the encoding field.
+ * Bump proto version when changing this. */
+enum drbd_bitmap_code {
+	/* RLE_VLI_Bytes = 0,
+	 * and other bit variants had been defined during
+	 * algorithm evaluation. */
+	RLE_VLI_Bits = 2,
+};
+
+struct p_compressed_bm {
+	/* (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
+	 * used to pad up to head.length bytes
+	 */
+	u8 encoding;
+
+	u8 code[0];
+} __packed;
+
+struct p_delay_probe93 {
+	u32     seq_num; /* sequence number to match the two probe packets */
+	u32     offset;  /* usecs the probe got sent after the reference time point */
+} __packed;
+
+/*
+ * 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 DRBD_SOCKET_BUFFER_SIZE 4096
+
+#endif  /* __DRBD_PROTOCOL_H */

drivers/block/drbd/drbd_req.h

@@ -0,0 +1,351 @@
+/*
+   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"
+
+/* 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) */
+
+	COMPLETED_OK,
+	READ_COMPLETED_WITH_ERROR,
+	READ_AHEAD_COMPLETED_WITH_ERROR,
+	WRITE_COMPLETED_WITH_ERROR,
+	DISCARD_COMPLETED_NOTSUPP,
+	DISCARD_COMPLETED_WITH_ERROR,
+
+	ABORT_DISK_IO,
+	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_iter.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_connection *connection);
+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_device *device,
+		struct bio_and_error *m);
+extern void request_timer_fn(unsigned long data);
+extern void tl_restart(struct drbd_connection *connection, enum drbd_req_event what);
+extern void _tl_restart(struct drbd_connection *connection, enum drbd_req_event what);
+extern void tl_abort_disk_io(struct drbd_device *device);
+
+/* 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_device *device = req->device;
+	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(device, &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_device *device = req->device;
+	struct bio_and_error m;
+	int rv;
+
+	spin_lock_irqsave(&device->resource->req_lock, flags);
+	rv = __req_mod(req, what, &m);
+	spin_unlock_irqrestore(&device->resource->req_lock, flags);
+
+	if (m.bio)
+		complete_master_bio(device, &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_device;
+struct drbd_connection;
+
+/**
+ * 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_device *device,
+					    enum chg_state_flags f,
+					    union drbd_state mask,
+					    union drbd_state val);
+extern void drbd_force_state(struct drbd_device *, union drbd_state,
+			union drbd_state);
+extern enum drbd_state_rv _drbd_request_state(struct drbd_device *,
+					      union drbd_state,
+					      union drbd_state,
+					      enum chg_state_flags);
+extern enum drbd_state_rv __drbd_set_state(struct drbd_device *, union drbd_state,
+					   enum chg_state_flags,
+					   struct completion *done);
+extern void print_st_err(struct drbd_device *, union drbd_state,
+			union drbd_state, int);
+
+enum drbd_state_rv
+_conn_request_state(struct drbd_connection *connection, union drbd_state mask, union drbd_state val,
+		    enum chg_state_flags flags);
+
+enum drbd_state_rv
+conn_request_state(struct drbd_connection *connection, union drbd_state mask, union drbd_state val,
+		   enum chg_state_flags flags);
+
+extern void drbd_resume_al(struct drbd_device *device);
+extern bool conn_all_vols_unconf(struct drbd_connection *connection);
+
+/**
+ * drbd_request_state() - Reqest a state change
+ * @device:	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_device *device,
+				     union drbd_state mask,
+				     union drbd_state val)
+{
+	return _drbd_request_state(device, mask, val, CS_VERBOSE + CS_ORDERED);
+}
+
+enum drbd_role conn_highest_role(struct drbd_connection *connection);
+enum drbd_role conn_highest_peer(struct drbd_connection *connection);
+enum drbd_disk_state conn_highest_disk(struct drbd_connection *connection);
+enum drbd_disk_state conn_lowest_disk(struct drbd_connection *connection);
+enum drbd_disk_state conn_highest_pdsk(struct drbd_connection *connection);
+enum drbd_conns conn_lowest_conn(struct drbd_connection *connection);
+
+#endif

drivers/block/drbd/drbd_strings.c

@@ -0,0 +1,118 @@
+/*
+  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>
+#include "drbd_strings.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_strings.h

@@ -0,0 +1,9 @@
+#ifndef __DRBD_STRINGS_H
+#define __DRBD_STRINGS_H
+
+extern const char *drbd_conn_str(enum drbd_conns);
+extern const char *drbd_role_str(enum drbd_role);
+extern const char *drbd_disk_str(enum drbd_disk_state);
+extern const char *drbd_set_st_err_str(enum drbd_state_rv);
+
+#endif  /* __DRBD_STRINGS_H */

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