Fixed MTP to work with TWRP

fs/dlm/Kconfig

@@ -0,0 +1,16 @@
+menuconfig DLM
+	tristate "Distributed Lock Manager (DLM)"
+	depends on INET
+	depends on SYSFS && CONFIGFS_FS && (IPV6 || IPV6=n)
+	select IP_SCTP
+	help
+	A general purpose distributed lock manager for kernel or userspace
+	applications.
+
+config DLM_DEBUG
+	bool "DLM debugging"
+	depends on DLM
+	help
+	Under the debugfs mount point, the name of each lockspace will
+	appear as a file in the "dlm" directory.  The output is the
+	list of resource and locks the local node knows about.

fs/dlm/Makefile

@@ -0,0 +1,21 @@
+obj-$(CONFIG_DLM) +=		dlm.o
+dlm-y :=			ast.o \
+				config.o \
+				dir.o \
+				lock.o \
+				lockspace.o \
+				main.o \
+				member.o \
+				memory.o \
+				midcomms.o \
+				netlink.o \
+				lowcomms.o \
+				plock.o \
+				rcom.o \
+				recover.o \
+				recoverd.o \
+				requestqueue.o \
+				user.o \
+				util.o 
+dlm-$(CONFIG_DLM_DEBUG) +=	debug_fs.o
+

fs/dlm/ast.c

@@ -0,0 +1,314 @@
+/******************************************************************************
+*******************************************************************************
+**
+**  Copyright (C) Sistina Software, Inc.  1997-2003  All rights reserved.
+**  Copyright (C) 2004-2010 Red Hat, Inc.  All rights reserved.
+**
+**  This copyrighted material is made available to anyone wishing to use,
+**  modify, copy, or redistribute it subject to the terms and conditions
+**  of the GNU General Public License v.2.
+**
+*******************************************************************************
+******************************************************************************/
+
+#include "dlm_internal.h"
+#include "lock.h"
+#include "user.h"
+#include "ast.h"
+
+static uint64_t dlm_cb_seq;
+static DEFINE_SPINLOCK(dlm_cb_seq_spin);
+
+static void dlm_dump_lkb_callbacks(struct dlm_lkb *lkb)
+{
+	int i;
+
+	log_print("last_bast %x %llu flags %x mode %d sb %d %x",
+		  lkb->lkb_id,
+		  (unsigned long long)lkb->lkb_last_bast.seq,
+		  lkb->lkb_last_bast.flags,
+		  lkb->lkb_last_bast.mode,
+		  lkb->lkb_last_bast.sb_status,
+		  lkb->lkb_last_bast.sb_flags);
+
+	log_print("last_cast %x %llu flags %x mode %d sb %d %x",
+		  lkb->lkb_id,
+		  (unsigned long long)lkb->lkb_last_cast.seq,
+		  lkb->lkb_last_cast.flags,
+		  lkb->lkb_last_cast.mode,
+		  lkb->lkb_last_cast.sb_status,
+		  lkb->lkb_last_cast.sb_flags);
+
+	for (i = 0; i < DLM_CALLBACKS_SIZE; i++) {
+		log_print("cb %x %llu flags %x mode %d sb %d %x",
+			  lkb->lkb_id,
+			  (unsigned long long)lkb->lkb_callbacks[i].seq,
+			  lkb->lkb_callbacks[i].flags,
+			  lkb->lkb_callbacks[i].mode,
+			  lkb->lkb_callbacks[i].sb_status,
+			  lkb->lkb_callbacks[i].sb_flags);
+	}
+}
+
+int dlm_add_lkb_callback(struct dlm_lkb *lkb, uint32_t flags, int mode,
+			 int status, uint32_t sbflags, uint64_t seq)
+{
+	struct dlm_ls *ls = lkb->lkb_resource->res_ls;
+	uint64_t prev_seq;
+	int prev_mode;
+	int i, rv;
+
+	for (i = 0; i < DLM_CALLBACKS_SIZE; i++) {
+		if (lkb->lkb_callbacks[i].seq)
+			continue;
+
+		/*
+		 * Suppress some redundant basts here, do more on removal.
+		 * Don't even add a bast if the callback just before it
+		 * is a bast for the same mode or a more restrictive mode.
+		 * (the addional > PR check is needed for PR/CW inversion)
+		 */
+
+		if ((i > 0) && (flags & DLM_CB_BAST) &&
+		    (lkb->lkb_callbacks[i-1].flags & DLM_CB_BAST)) {
+
+			prev_seq = lkb->lkb_callbacks[i-1].seq;
+			prev_mode = lkb->lkb_callbacks[i-1].mode;
+
+			if ((prev_mode == mode) ||
+			    (prev_mode > mode && prev_mode > DLM_LOCK_PR)) {
+
+				log_debug(ls, "skip %x add bast %llu mode %d "
+					  "for bast %llu mode %d",
+					  lkb->lkb_id,
+					  (unsigned long long)seq,
+					  mode,
+					  (unsigned long long)prev_seq,
+					  prev_mode);
+				rv = 0;
+				goto out;
+			}
+		}
+
+		lkb->lkb_callbacks[i].seq = seq;
+		lkb->lkb_callbacks[i].flags = flags;
+		lkb->lkb_callbacks[i].mode = mode;
+		lkb->lkb_callbacks[i].sb_status = status;
+		lkb->lkb_callbacks[i].sb_flags = (sbflags & 0x000000FF);
+		rv = 0;
+		break;
+	}
+
+	if (i == DLM_CALLBACKS_SIZE) {
+		log_error(ls, "no callbacks %x %llu flags %x mode %d sb %d %x",
+			  lkb->lkb_id, (unsigned long long)seq,
+			  flags, mode, status, sbflags);
+		dlm_dump_lkb_callbacks(lkb);
+		rv = -1;
+		goto out;
+	}
+ out:
+	return rv;
+}
+
+int dlm_rem_lkb_callback(struct dlm_ls *ls, struct dlm_lkb *lkb,
+			 struct dlm_callback *cb, int *resid)
+{
+	int i, rv;
+
+	*resid = 0;
+
+	if (!lkb->lkb_callbacks[0].seq) {
+		rv = -ENOENT;
+		goto out;
+	}
+
+	/* oldest undelivered cb is callbacks[0] */
+
+	memcpy(cb, &lkb->lkb_callbacks[0], sizeof(struct dlm_callback));
+	memset(&lkb->lkb_callbacks[0], 0, sizeof(struct dlm_callback));
+
+	/* shift others down */
+
+	for (i = 1; i < DLM_CALLBACKS_SIZE; i++) {
+		if (!lkb->lkb_callbacks[i].seq)
+			break;
+		memcpy(&lkb->lkb_callbacks[i-1], &lkb->lkb_callbacks[i],
+		       sizeof(struct dlm_callback));
+		memset(&lkb->lkb_callbacks[i], 0, sizeof(struct dlm_callback));
+		(*resid)++;
+	}
+
+	/* if cb is a bast, it should be skipped if the blocking mode is
+	   compatible with the last granted mode */
+
+	if ((cb->flags & DLM_CB_BAST) && lkb->lkb_last_cast.seq) {
+		if (dlm_modes_compat(cb->mode, lkb->lkb_last_cast.mode)) {
+			cb->flags |= DLM_CB_SKIP;
+
+			log_debug(ls, "skip %x bast %llu mode %d "
+				  "for cast %llu mode %d",
+				  lkb->lkb_id,
+				  (unsigned long long)cb->seq,
+				  cb->mode,
+				  (unsigned long long)lkb->lkb_last_cast.seq,
+				  lkb->lkb_last_cast.mode);
+			rv = 0;
+			goto out;
+		}
+	}
+
+	if (cb->flags & DLM_CB_CAST) {
+		memcpy(&lkb->lkb_last_cast, cb, sizeof(struct dlm_callback));
+		lkb->lkb_last_cast_time = ktime_get();
+	}
+
+	if (cb->flags & DLM_CB_BAST) {
+		memcpy(&lkb->lkb_last_bast, cb, sizeof(struct dlm_callback));
+		lkb->lkb_last_bast_time = ktime_get();
+	}
+	rv = 0;
+ out:
+	return rv;
+}
+
+void dlm_add_cb(struct dlm_lkb *lkb, uint32_t flags, int mode, int status,
+		uint32_t sbflags)
+{
+	struct dlm_ls *ls = lkb->lkb_resource->res_ls;
+	uint64_t new_seq, prev_seq;
+	int rv;
+
+	spin_lock(&dlm_cb_seq_spin);
+	new_seq = ++dlm_cb_seq;
+	spin_unlock(&dlm_cb_seq_spin);
+
+	if (lkb->lkb_flags & DLM_IFL_USER) {
+		dlm_user_add_ast(lkb, flags, mode, status, sbflags, new_seq);
+		return;
+	}
+
+	mutex_lock(&lkb->lkb_cb_mutex);
+	prev_seq = lkb->lkb_callbacks[0].seq;
+
+	rv = dlm_add_lkb_callback(lkb, flags, mode, status, sbflags, new_seq);
+	if (rv < 0)
+		goto out;
+
+	if (!prev_seq) {
+		kref_get(&lkb->lkb_ref);
+
+		if (test_bit(LSFL_CB_DELAY, &ls->ls_flags)) {
+			mutex_lock(&ls->ls_cb_mutex);
+			list_add(&lkb->lkb_cb_list, &ls->ls_cb_delay);
+			mutex_unlock(&ls->ls_cb_mutex);
+		} else {
+			queue_work(ls->ls_callback_wq, &lkb->lkb_cb_work);
+		}
+	}
+ out:
+	mutex_unlock(&lkb->lkb_cb_mutex);
+}
+
+void dlm_callback_work(struct work_struct *work)
+{
+	struct dlm_lkb *lkb = container_of(work, struct dlm_lkb, lkb_cb_work);
+	struct dlm_ls *ls = lkb->lkb_resource->res_ls;
+	void (*castfn) (void *astparam);
+	void (*bastfn) (void *astparam, int mode);
+	struct dlm_callback callbacks[DLM_CALLBACKS_SIZE];
+	int i, rv, resid;
+
+	memset(&callbacks, 0, sizeof(callbacks));
+
+	mutex_lock(&lkb->lkb_cb_mutex);
+	if (!lkb->lkb_callbacks[0].seq) {
+		/* no callback work exists, shouldn't happen */
+		log_error(ls, "dlm_callback_work %x no work", lkb->lkb_id);
+		dlm_print_lkb(lkb);
+		dlm_dump_lkb_callbacks(lkb);
+	}
+
+	for (i = 0; i < DLM_CALLBACKS_SIZE; i++) {
+		rv = dlm_rem_lkb_callback(ls, lkb, &callbacks[i], &resid);
+		if (rv < 0)
+			break;
+	}
+
+	if (resid) {
+		/* cbs remain, loop should have removed all, shouldn't happen */
+		log_error(ls, "dlm_callback_work %x resid %d", lkb->lkb_id,
+			  resid);
+		dlm_print_lkb(lkb);
+		dlm_dump_lkb_callbacks(lkb);
+	}
+	mutex_unlock(&lkb->lkb_cb_mutex);
+
+	castfn = lkb->lkb_astfn;
+	bastfn = lkb->lkb_bastfn;
+
+	for (i = 0; i < DLM_CALLBACKS_SIZE; i++) {
+		if (!callbacks[i].seq)
+			break;
+		if (callbacks[i].flags & DLM_CB_SKIP) {
+			continue;
+		} else if (callbacks[i].flags & DLM_CB_BAST) {
+			bastfn(lkb->lkb_astparam, callbacks[i].mode);
+		} else if (callbacks[i].flags & DLM_CB_CAST) {
+			lkb->lkb_lksb->sb_status = callbacks[i].sb_status;
+			lkb->lkb_lksb->sb_flags = callbacks[i].sb_flags;
+			castfn(lkb->lkb_astparam);
+		}
+	}
+
+	/* undo kref_get from dlm_add_callback, may cause lkb to be freed */
+	dlm_put_lkb(lkb);
+}
+
+int dlm_callback_start(struct dlm_ls *ls)
+{
+	ls->ls_callback_wq = alloc_workqueue("dlm_callback",
+					     WQ_UNBOUND | WQ_MEM_RECLAIM, 0);
+	if (!ls->ls_callback_wq) {
+		log_print("can't start dlm_callback workqueue");
+		return -ENOMEM;
+	}
+	return 0;
+}
+
+void dlm_callback_stop(struct dlm_ls *ls)
+{
+	if (ls->ls_callback_wq)
+		destroy_workqueue(ls->ls_callback_wq);
+}
+
+void dlm_callback_suspend(struct dlm_ls *ls)
+{
+	set_bit(LSFL_CB_DELAY, &ls->ls_flags);
+
+	if (ls->ls_callback_wq)
+		flush_workqueue(ls->ls_callback_wq);
+}
+
+void dlm_callback_resume(struct dlm_ls *ls)
+{
+	struct dlm_lkb *lkb, *safe;
+	int count = 0;
+
+	clear_bit(LSFL_CB_DELAY, &ls->ls_flags);
+
+	if (!ls->ls_callback_wq)
+		return;
+
+	mutex_lock(&ls->ls_cb_mutex);
+	list_for_each_entry_safe(lkb, safe, &ls->ls_cb_delay, lkb_cb_list) {
+		list_del_init(&lkb->lkb_cb_list);
+		queue_work(ls->ls_callback_wq, &lkb->lkb_cb_work);
+		count++;
+	}
+	mutex_unlock(&ls->ls_cb_mutex);
+
+	if (count)
+		log_rinfo(ls, "dlm_callback_resume %d", count);
+}
+

fs/dlm/ast.h

@@ -0,0 +1,32 @@
+/******************************************************************************
+*******************************************************************************
+**
+**  Copyright (C) 2005-2010 Red Hat, Inc.  All rights reserved.
+**
+**  This copyrighted material is made available to anyone wishing to use,
+**  modify, copy, or redistribute it subject to the terms and conditions
+**  of the GNU General Public License v.2.
+**
+*******************************************************************************
+******************************************************************************/
+
+#ifndef __ASTD_DOT_H__
+#define __ASTD_DOT_H__
+
+void dlm_del_ast(struct dlm_lkb *lkb);
+int dlm_add_lkb_callback(struct dlm_lkb *lkb, uint32_t flags, int mode,
+                         int status, uint32_t sbflags, uint64_t seq);
+int dlm_rem_lkb_callback(struct dlm_ls *ls, struct dlm_lkb *lkb,
+                         struct dlm_callback *cb, int *resid);
+void dlm_add_cb(struct dlm_lkb *lkb, uint32_t flags, int mode, int status,
+                uint32_t sbflags);
+
+void dlm_callback_work(struct work_struct *work);
+int dlm_callback_start(struct dlm_ls *ls);
+void dlm_callback_stop(struct dlm_ls *ls);
+void dlm_callback_suspend(struct dlm_ls *ls);
+void dlm_callback_resume(struct dlm_ls *ls);
+
+#endif
+
+

fs/dlm/config.h

@@ -0,0 +1,53 @@
+/******************************************************************************
+*******************************************************************************
+**
+**  Copyright (C) Sistina Software, Inc.  1997-2003  All rights reserved.
+**  Copyright (C) 2004-2011 Red Hat, Inc.  All rights reserved.
+**
+**  This copyrighted material is made available to anyone wishing to use,
+**  modify, copy, or redistribute it subject to the terms and conditions
+**  of the GNU General Public License v.2.
+**
+*******************************************************************************
+******************************************************************************/
+
+#ifndef __CONFIG_DOT_H__
+#define __CONFIG_DOT_H__
+
+struct dlm_config_node {
+	int nodeid;
+	int weight;
+	int new;
+	uint32_t comm_seq;
+};
+
+#define DLM_MAX_ADDR_COUNT 3
+
+struct dlm_config_info {
+	int ci_tcp_port;
+	int ci_buffer_size;
+	int ci_rsbtbl_size;
+	int ci_recover_timer;
+	int ci_toss_secs;
+	int ci_scan_secs;
+	int ci_log_debug;
+	int ci_protocol;
+	int ci_timewarn_cs;
+	int ci_waitwarn_us;
+	int ci_new_rsb_count;
+	int ci_recover_callbacks;
+	char ci_cluster_name[DLM_LOCKSPACE_LEN];
+};
+
+extern struct dlm_config_info dlm_config;
+
+int dlm_config_init(void);
+void dlm_config_exit(void);
+int dlm_config_nodes(char *lsname, struct dlm_config_node **nodes_out,
+		     int *count_out);
+int dlm_comm_seq(int nodeid, uint32_t *seq);
+int dlm_our_nodeid(void);
+int dlm_our_addr(struct sockaddr_storage *addr, int num);
+
+#endif				/* __CONFIG_DOT_H__ */
+

fs/dlm/debug_fs.c

@@ -0,0 +1,810 @@
+/******************************************************************************
+*******************************************************************************
+**
+**  Copyright (C) 2005-2009 Red Hat, Inc.  All rights reserved.
+**
+**  This copyrighted material is made available to anyone wishing to use,
+**  modify, copy, or redistribute it subject to the terms and conditions
+**  of the GNU General Public License v.2.
+**
+*******************************************************************************
+******************************************************************************/
+
+#include <linux/pagemap.h>
+#include <linux/seq_file.h>
+#include <linux/module.h>
+#include <linux/ctype.h>
+#include <linux/debugfs.h>
+#include <linux/slab.h>
+
+#include "dlm_internal.h"
+#include "lock.h"
+
+#define DLM_DEBUG_BUF_LEN 4096
+static char debug_buf[DLM_DEBUG_BUF_LEN];
+static struct mutex debug_buf_lock;
+
+static struct dentry *dlm_root;
+
+static char *print_lockmode(int mode)
+{
+	switch (mode) {
+	case DLM_LOCK_IV:
+		return "--";
+	case DLM_LOCK_NL:
+		return "NL";
+	case DLM_LOCK_CR:
+		return "CR";
+	case DLM_LOCK_CW:
+		return "CW";
+	case DLM_LOCK_PR:
+		return "PR";
+	case DLM_LOCK_PW:
+		return "PW";
+	case DLM_LOCK_EX:
+		return "EX";
+	default:
+		return "??";
+	}
+}
+
+static int print_format1_lock(struct seq_file *s, struct dlm_lkb *lkb,
+			      struct dlm_rsb *res)
+{
+	seq_printf(s, "%08x %s", lkb->lkb_id, print_lockmode(lkb->lkb_grmode));
+
+	if (lkb->lkb_status == DLM_LKSTS_CONVERT ||
+	    lkb->lkb_status == DLM_LKSTS_WAITING)
+		seq_printf(s, " (%s)", print_lockmode(lkb->lkb_rqmode));
+
+	if (lkb->lkb_nodeid) {
+		if (lkb->lkb_nodeid != res->res_nodeid)
+			seq_printf(s, " Remote: %3d %08x", lkb->lkb_nodeid,
+				   lkb->lkb_remid);
+		else
+			seq_printf(s, " Master:     %08x", lkb->lkb_remid);
+	}
+
+	if (lkb->lkb_wait_type)
+		seq_printf(s, " wait_type: %d", lkb->lkb_wait_type);
+
+	return seq_puts(s, "\n");
+}
+
+static int print_format1(struct dlm_rsb *res, struct seq_file *s)
+{
+	struct dlm_lkb *lkb;
+	int i, lvblen = res->res_ls->ls_lvblen, recover_list, root_list;
+	int rv;
+
+	lock_rsb(res);
+
+	rv = seq_printf(s, "\nResource %p Name (len=%d) \"",
+			res, res->res_length);
+	if (rv)
+		goto out;
+
+	for (i = 0; i < res->res_length; i++) {
+		if (isprint(res->res_name[i]))
+			seq_printf(s, "%c", res->res_name[i]);
+		else
+			seq_printf(s, "%c", '.');
+	}
+
+	if (res->res_nodeid > 0)
+		rv = seq_printf(s, "\"\nLocal Copy, Master is node %d\n",
+				res->res_nodeid);
+	else if (res->res_nodeid == 0)
+		rv = seq_puts(s, "\"\nMaster Copy\n");
+	else if (res->res_nodeid == -1)
+		rv = seq_printf(s, "\"\nLooking up master (lkid %x)\n",
+			   	res->res_first_lkid);
+	else
+		rv = seq_printf(s, "\"\nInvalid master %d\n",
+				res->res_nodeid);
+	if (rv)
+		goto out;
+
+	/* Print the LVB: */
+	if (res->res_lvbptr) {
+		seq_puts(s, "LVB: ");
+		for (i = 0; i < lvblen; i++) {
+			if (i == lvblen / 2)
+				seq_puts(s, "\n     ");
+			seq_printf(s, "%02x ",
+				   (unsigned char) res->res_lvbptr[i]);
+		}
+		if (rsb_flag(res, RSB_VALNOTVALID))
+			seq_puts(s, " (INVALID)");
+		rv = seq_puts(s, "\n");
+		if (rv)
+			goto out;
+	}
+
+	root_list = !list_empty(&res->res_root_list);
+	recover_list = !list_empty(&res->res_recover_list);
+
+	if (root_list || recover_list) {
+		rv = seq_printf(s, "Recovery: root %d recover %d flags %lx "
+				"count %d\n", root_list, recover_list,
+			   	res->res_flags, res->res_recover_locks_count);
+		if (rv)
+			goto out;
+	}
+
+	/* Print the locks attached to this resource */
+	seq_puts(s, "Granted Queue\n");
+	list_for_each_entry(lkb, &res->res_grantqueue, lkb_statequeue) {
+		rv = print_format1_lock(s, lkb, res);
+		if (rv)
+			goto out;
+	}
+
+	seq_puts(s, "Conversion Queue\n");
+	list_for_each_entry(lkb, &res->res_convertqueue, lkb_statequeue) {
+		rv = print_format1_lock(s, lkb, res);
+		if (rv)
+			goto out;
+	}
+
+	seq_puts(s, "Waiting Queue\n");
+	list_for_each_entry(lkb, &res->res_waitqueue, lkb_statequeue) {
+		rv = print_format1_lock(s, lkb, res);
+		if (rv)
+			goto out;
+	}
+
+	if (list_empty(&res->res_lookup))
+		goto out;
+
+	seq_puts(s, "Lookup Queue\n");
+	list_for_each_entry(lkb, &res->res_lookup, lkb_rsb_lookup) {
+		rv = seq_printf(s, "%08x %s", lkb->lkb_id,
+				print_lockmode(lkb->lkb_rqmode));
+		if (lkb->lkb_wait_type)
+			seq_printf(s, " wait_type: %d", lkb->lkb_wait_type);
+		rv = seq_puts(s, "\n");
+	}
+ out:
+	unlock_rsb(res);
+	return rv;
+}
+
+static int print_format2_lock(struct seq_file *s, struct dlm_lkb *lkb,
+			      struct dlm_rsb *r)
+{
+	u64 xid = 0;
+	u64 us;
+	int rv;
+
+	if (lkb->lkb_flags & DLM_IFL_USER) {
+		if (lkb->lkb_ua)
+			xid = lkb->lkb_ua->xid;
+	}
+
+	/* microseconds since lkb was added to current queue */
+	us = ktime_to_us(ktime_sub(ktime_get(), lkb->lkb_timestamp));
+
+	/* id nodeid remid pid xid exflags flags sts grmode rqmode time_us
+	   r_nodeid r_len r_name */
+
+	rv = seq_printf(s, "%x %d %x %u %llu %x %x %d %d %d %llu %u %d \"%s\"\n",
+			lkb->lkb_id,
+			lkb->lkb_nodeid,
+			lkb->lkb_remid,
+			lkb->lkb_ownpid,
+			(unsigned long long)xid,
+			lkb->lkb_exflags,
+			lkb->lkb_flags,
+			lkb->lkb_status,
+			lkb->lkb_grmode,
+			lkb->lkb_rqmode,
+			(unsigned long long)us,
+			r->res_nodeid,
+			r->res_length,
+			r->res_name);
+	return rv;
+}
+
+static int print_format2(struct dlm_rsb *r, struct seq_file *s)
+{
+	struct dlm_lkb *lkb;
+	int rv = 0;
+
+	lock_rsb(r);
+
+	list_for_each_entry(lkb, &r->res_grantqueue, lkb_statequeue) {
+		rv = print_format2_lock(s, lkb, r);
+		if (rv)
+			goto out;
+	}
+
+	list_for_each_entry(lkb, &r->res_convertqueue, lkb_statequeue) {
+		rv = print_format2_lock(s, lkb, r);
+		if (rv)
+			goto out;
+	}
+
+	list_for_each_entry(lkb, &r->res_waitqueue, lkb_statequeue) {
+		rv = print_format2_lock(s, lkb, r);
+		if (rv)
+			goto out;
+	}
+ out:
+	unlock_rsb(r);
+	return rv;
+}
+
+static int print_format3_lock(struct seq_file *s, struct dlm_lkb *lkb,
+			      int rsb_lookup)
+{
+	u64 xid = 0;
+	int rv;
+
+	if (lkb->lkb_flags & DLM_IFL_USER) {
+		if (lkb->lkb_ua)
+			xid = lkb->lkb_ua->xid;
+	}
+
+	rv = seq_printf(s, "lkb %x %d %x %u %llu %x %x %d %d %d %d %d %d %u %llu %llu\n",
+			lkb->lkb_id,
+			lkb->lkb_nodeid,
+			lkb->lkb_remid,
+			lkb->lkb_ownpid,
+			(unsigned long long)xid,
+			lkb->lkb_exflags,
+			lkb->lkb_flags,
+			lkb->lkb_status,
+			lkb->lkb_grmode,
+			lkb->lkb_rqmode,
+			lkb->lkb_last_bast.mode,
+			rsb_lookup,
+			lkb->lkb_wait_type,
+			lkb->lkb_lvbseq,
+			(unsigned long long)ktime_to_ns(lkb->lkb_timestamp),
+			(unsigned long long)ktime_to_ns(lkb->lkb_last_bast_time));
+	return rv;
+}
+
+static int print_format3(struct dlm_rsb *r, struct seq_file *s)
+{
+	struct dlm_lkb *lkb;
+	int i, lvblen = r->res_ls->ls_lvblen;
+	int print_name = 1;
+	int rv;
+
+	lock_rsb(r);
+
+	rv = seq_printf(s, "rsb %p %d %x %lx %d %d %u %d ",
+			r,
+			r->res_nodeid,
+			r->res_first_lkid,
+			r->res_flags,
+			!list_empty(&r->res_root_list),
+			!list_empty(&r->res_recover_list),
+			r->res_recover_locks_count,
+			r->res_length);
+	if (rv)
+		goto out;
+
+	for (i = 0; i < r->res_length; i++) {
+		if (!isascii(r->res_name[i]) || !isprint(r->res_name[i]))
+			print_name = 0;
+	}
+
+	seq_printf(s, "%s", print_name ? "str " : "hex");
+
+	for (i = 0; i < r->res_length; i++) {
+		if (print_name)
+			seq_printf(s, "%c", r->res_name[i]);
+		else
+			seq_printf(s, " %02x", (unsigned char)r->res_name[i]);
+	}
+	rv = seq_puts(s, "\n");
+	if (rv)
+		goto out;
+
+	if (!r->res_lvbptr)
+		goto do_locks;
+
+	seq_printf(s, "lvb %u %d", r->res_lvbseq, lvblen);
+
+	for (i = 0; i < lvblen; i++)
+		seq_printf(s, " %02x", (unsigned char)r->res_lvbptr[i]);
+	rv = seq_puts(s, "\n");
+	if (rv)
+		goto out;
+
+ do_locks:
+	list_for_each_entry(lkb, &r->res_grantqueue, lkb_statequeue) {
+		rv = print_format3_lock(s, lkb, 0);
+		if (rv)
+			goto out;
+	}
+
+	list_for_each_entry(lkb, &r->res_convertqueue, lkb_statequeue) {
+		rv = print_format3_lock(s, lkb, 0);
+		if (rv)
+			goto out;
+	}
+
+	list_for_each_entry(lkb, &r->res_waitqueue, lkb_statequeue) {
+		rv = print_format3_lock(s, lkb, 0);
+		if (rv)
+			goto out;
+	}
+
+	list_for_each_entry(lkb, &r->res_lookup, lkb_rsb_lookup) {
+		rv = print_format3_lock(s, lkb, 1);
+		if (rv)
+			goto out;
+	}
+ out:
+	unlock_rsb(r);
+	return rv;
+}
+
+static int print_format4(struct dlm_rsb *r, struct seq_file *s)
+{
+	int our_nodeid = dlm_our_nodeid();
+	int print_name = 1;
+	int i, rv;
+
+	lock_rsb(r);
+
+	rv = seq_printf(s, "rsb %p %d %d %d %d %lu %lx %d ",
+			r,
+			r->res_nodeid,
+			r->res_master_nodeid,
+			r->res_dir_nodeid,
+			our_nodeid,
+			r->res_toss_time,
+			r->res_flags,
+			r->res_length);
+	if (rv)
+		goto out;
+
+	for (i = 0; i < r->res_length; i++) {
+		if (!isascii(r->res_name[i]) || !isprint(r->res_name[i]))
+			print_name = 0;
+	}
+
+	seq_printf(s, "%s", print_name ? "str " : "hex");
+
+	for (i = 0; i < r->res_length; i++) {
+		if (print_name)
+			seq_printf(s, "%c", r->res_name[i]);
+		else
+			seq_printf(s, " %02x", (unsigned char)r->res_name[i]);
+	}
+	rv = seq_puts(s, "\n");
+ out:
+	unlock_rsb(r);
+	return rv;
+}
+
+struct rsbtbl_iter {
+	struct dlm_rsb *rsb;
+	unsigned bucket;
+	int format;
+	int header;
+};
+
+/* seq_printf returns -1 if the buffer is full, and 0 otherwise.
+   If the buffer is full, seq_printf can be called again, but it
+   does nothing and just returns -1.  So, the these printing routines
+   periodically check the return value to avoid wasting too much time
+   trying to print to a full buffer. */
+
+static int table_seq_show(struct seq_file *seq, void *iter_ptr)
+{
+	struct rsbtbl_iter *ri = iter_ptr;
+	int rv = 0;
+
+	switch (ri->format) {
+	case 1:
+		rv = print_format1(ri->rsb, seq);
+		break;
+	case 2:
+		if (ri->header) {
+			seq_printf(seq, "id nodeid remid pid xid exflags "
+					"flags sts grmode rqmode time_ms "
+					"r_nodeid r_len r_name\n");
+			ri->header = 0;
+		}
+		rv = print_format2(ri->rsb, seq);
+		break;
+	case 3:
+		if (ri->header) {
+			seq_printf(seq, "version rsb 1.1 lvb 1.1 lkb 1.1\n");
+			ri->header = 0;
+		}
+		rv = print_format3(ri->rsb, seq);
+		break;
+	case 4:
+		if (ri->header) {
+			seq_printf(seq, "version 4 rsb 2\n");
+			ri->header = 0;
+		}
+		rv = print_format4(ri->rsb, seq);
+		break;
+	}
+
+	return rv;
+}
+
+static const struct seq_operations format1_seq_ops;
+static const struct seq_operations format2_seq_ops;
+static const struct seq_operations format3_seq_ops;
+static const struct seq_operations format4_seq_ops;
+
+static void *table_seq_start(struct seq_file *seq, loff_t *pos)
+{
+	struct rb_root *tree;
+	struct rb_node *node;
+	struct dlm_ls *ls = seq->private;
+	struct rsbtbl_iter *ri;
+	struct dlm_rsb *r;
+	loff_t n = *pos;
+	unsigned bucket, entry;
+	int toss = (seq->op == &format4_seq_ops);
+
+	bucket = n >> 32;
+	entry = n & ((1LL << 32) - 1);
+
+	if (bucket >= ls->ls_rsbtbl_size)
+		return NULL;
+
+	ri = kzalloc(sizeof(struct rsbtbl_iter), GFP_NOFS);
+	if (!ri)
+		return NULL;
+	if (n == 0)
+		ri->header = 1;
+	if (seq->op == &format1_seq_ops)
+		ri->format = 1;
+	if (seq->op == &format2_seq_ops)
+		ri->format = 2;
+	if (seq->op == &format3_seq_ops)
+		ri->format = 3;
+	if (seq->op == &format4_seq_ops)
+		ri->format = 4;
+
+	tree = toss ? &ls->ls_rsbtbl[bucket].toss : &ls->ls_rsbtbl[bucket].keep;
+
+	spin_lock(&ls->ls_rsbtbl[bucket].lock);
+	if (!RB_EMPTY_ROOT(tree)) {
+		for (node = rb_first(tree); node; node = rb_next(node)) {
+			r = rb_entry(node, struct dlm_rsb, res_hashnode);
+			if (!entry--) {
+				dlm_hold_rsb(r);
+				ri->rsb = r;
+				ri->bucket = bucket;
+				spin_unlock(&ls->ls_rsbtbl[bucket].lock);
+				return ri;
+			}
+		}
+	}
+	spin_unlock(&ls->ls_rsbtbl[bucket].lock);
+
+	/*
+	 * move to the first rsb in the next non-empty bucket
+	 */
+
+	/* zero the entry */
+	n &= ~((1LL << 32) - 1);
+
+	while (1) {
+		bucket++;
+		n += 1LL << 32;
+
+		if (bucket >= ls->ls_rsbtbl_size) {
+			kfree(ri);
+			return NULL;
+		}
+		tree = toss ? &ls->ls_rsbtbl[bucket].toss : &ls->ls_rsbtbl[bucket].keep;
+
+		spin_lock(&ls->ls_rsbtbl[bucket].lock);
+		if (!RB_EMPTY_ROOT(tree)) {
+			node = rb_first(tree);
+			r = rb_entry(node, struct dlm_rsb, res_hashnode);
+			dlm_hold_rsb(r);
+			ri->rsb = r;
+			ri->bucket = bucket;
+			spin_unlock(&ls->ls_rsbtbl[bucket].lock);
+			*pos = n;
+			return ri;
+		}
+		spin_unlock(&ls->ls_rsbtbl[bucket].lock);
+	}
+}
+
+static void *table_seq_next(struct seq_file *seq, void *iter_ptr, loff_t *pos)
+{
+	struct dlm_ls *ls = seq->private;
+	struct rsbtbl_iter *ri = iter_ptr;
+	struct rb_root *tree;
+	struct rb_node *next;
+	struct dlm_rsb *r, *rp;
+	loff_t n = *pos;
+	unsigned bucket;
+	int toss = (seq->op == &format4_seq_ops);
+
+	bucket = n >> 32;
+
+	/*
+	 * move to the next rsb in the same bucket
+	 */
+
+	spin_lock(&ls->ls_rsbtbl[bucket].lock);
+	rp = ri->rsb;
+	next = rb_next(&rp->res_hashnode);
+
+	if (next) {
+		r = rb_entry(next, struct dlm_rsb, res_hashnode);
+		dlm_hold_rsb(r);
+		ri->rsb = r;
+		spin_unlock(&ls->ls_rsbtbl[bucket].lock);
+		dlm_put_rsb(rp);
+		++*pos;
+		return ri;
+	}
+	spin_unlock(&ls->ls_rsbtbl[bucket].lock);
+	dlm_put_rsb(rp);
+
+	/*
+	 * move to the first rsb in the next non-empty bucket
+	 */
+
+	/* zero the entry */
+	n &= ~((1LL << 32) - 1);
+
+	while (1) {
+		bucket++;
+		n += 1LL << 32;
+
+		if (bucket >= ls->ls_rsbtbl_size) {
+			kfree(ri);
+			return NULL;
+		}
+		tree = toss ? &ls->ls_rsbtbl[bucket].toss : &ls->ls_rsbtbl[bucket].keep;
+
+		spin_lock(&ls->ls_rsbtbl[bucket].lock);
+		if (!RB_EMPTY_ROOT(tree)) {
+			next = rb_first(tree);
+			r = rb_entry(next, struct dlm_rsb, res_hashnode);
+			dlm_hold_rsb(r);
+			ri->rsb = r;
+			ri->bucket = bucket;
+			spin_unlock(&ls->ls_rsbtbl[bucket].lock);
+			*pos = n;
+			return ri;
+		}
+		spin_unlock(&ls->ls_rsbtbl[bucket].lock);
+	}
+}
+
+static void table_seq_stop(struct seq_file *seq, void *iter_ptr)
+{
+	struct rsbtbl_iter *ri = iter_ptr;
+
+	if (ri) {
+		dlm_put_rsb(ri->rsb);
+		kfree(ri);
+	}
+}
+
+static const struct seq_operations format1_seq_ops = {
+	.start = table_seq_start,
+	.next  = table_seq_next,
+	.stop  = table_seq_stop,
+	.show  = table_seq_show,
+};
+
+static const struct seq_operations format2_seq_ops = {
+	.start = table_seq_start,
+	.next  = table_seq_next,
+	.stop  = table_seq_stop,
+	.show  = table_seq_show,
+};
+
+static const struct seq_operations format3_seq_ops = {
+	.start = table_seq_start,
+	.next  = table_seq_next,
+	.stop  = table_seq_stop,
+	.show  = table_seq_show,
+};
+
+static const struct seq_operations format4_seq_ops = {
+	.start = table_seq_start,
+	.next  = table_seq_next,
+	.stop  = table_seq_stop,
+	.show  = table_seq_show,
+};
+
+static const struct file_operations format1_fops;
+static const struct file_operations format2_fops;
+static const struct file_operations format3_fops;
+static const struct file_operations format4_fops;
+
+static int table_open(struct inode *inode, struct file *file)
+{
+	struct seq_file *seq;
+	int ret = -1;
+
+	if (file->f_op == &format1_fops)
+		ret = seq_open(file, &format1_seq_ops);
+	else if (file->f_op == &format2_fops)
+		ret = seq_open(file, &format2_seq_ops);
+	else if (file->f_op == &format3_fops)
+		ret = seq_open(file, &format3_seq_ops);
+	else if (file->f_op == &format4_fops)
+		ret = seq_open(file, &format4_seq_ops);
+
+	if (ret)
+		return ret;
+
+	seq = file->private_data;
+	seq->private = inode->i_private; /* the dlm_ls */
+	return 0;
+}
+
+static const struct file_operations format1_fops = {
+	.owner   = THIS_MODULE,
+	.open    = table_open,
+	.read    = seq_read,
+	.llseek  = seq_lseek,
+	.release = seq_release
+};
+
+static const struct file_operations format2_fops = {
+	.owner   = THIS_MODULE,
+	.open    = table_open,
+	.read    = seq_read,
+	.llseek  = seq_lseek,
+	.release = seq_release
+};
+
+static const struct file_operations format3_fops = {
+	.owner   = THIS_MODULE,
+	.open    = table_open,
+	.read    = seq_read,
+	.llseek  = seq_lseek,
+	.release = seq_release
+};
+
+static const struct file_operations format4_fops = {
+	.owner   = THIS_MODULE,
+	.open    = table_open,
+	.read    = seq_read,
+	.llseek  = seq_lseek,
+	.release = seq_release
+};
+
+/*
+ * dump lkb's on the ls_waiters list
+ */
+static ssize_t waiters_read(struct file *file, char __user *userbuf,
+			    size_t count, loff_t *ppos)
+{
+	struct dlm_ls *ls = file->private_data;
+	struct dlm_lkb *lkb;
+	size_t len = DLM_DEBUG_BUF_LEN, pos = 0, ret, rv;
+
+	mutex_lock(&debug_buf_lock);
+	mutex_lock(&ls->ls_waiters_mutex);
+	memset(debug_buf, 0, sizeof(debug_buf));
+
+	list_for_each_entry(lkb, &ls->ls_waiters, lkb_wait_reply) {
+		ret = snprintf(debug_buf + pos, len - pos, "%x %d %d %s\n",
+			       lkb->lkb_id, lkb->lkb_wait_type,
+			       lkb->lkb_nodeid, lkb->lkb_resource->res_name);
+		if (ret >= len - pos)
+			break;
+		pos += ret;
+	}
+	mutex_unlock(&ls->ls_waiters_mutex);
+
+	rv = simple_read_from_buffer(userbuf, count, ppos, debug_buf, pos);
+	mutex_unlock(&debug_buf_lock);
+	return rv;
+}
+
+static const struct file_operations waiters_fops = {
+	.owner   = THIS_MODULE,
+	.open    = simple_open,
+	.read    = waiters_read,
+	.llseek  = default_llseek,
+};
+
+void dlm_delete_debug_file(struct dlm_ls *ls)
+{
+	debugfs_remove(ls->ls_debug_rsb_dentry);
+	debugfs_remove(ls->ls_debug_waiters_dentry);
+	debugfs_remove(ls->ls_debug_locks_dentry);
+	debugfs_remove(ls->ls_debug_all_dentry);
+	debugfs_remove(ls->ls_debug_toss_dentry);
+}
+
+int dlm_create_debug_file(struct dlm_ls *ls)
+{
+	char name[DLM_LOCKSPACE_LEN+8];
+
+	/* format 1 */
+
+	ls->ls_debug_rsb_dentry = debugfs_create_file(ls->ls_name,
+						      S_IFREG | S_IRUGO,
+						      dlm_root,
+						      ls,
+						      &format1_fops);
+	if (!ls->ls_debug_rsb_dentry)
+		goto fail;
+
+	/* format 2 */
+
+	memset(name, 0, sizeof(name));
+	snprintf(name, DLM_LOCKSPACE_LEN+8, "%s_locks", ls->ls_name);
+
+	ls->ls_debug_locks_dentry = debugfs_create_file(name,
+							S_IFREG | S_IRUGO,
+							dlm_root,
+							ls,
+							&format2_fops);
+	if (!ls->ls_debug_locks_dentry)
+		goto fail;
+
+	/* format 3 */
+
+	memset(name, 0, sizeof(name));
+	snprintf(name, DLM_LOCKSPACE_LEN+8, "%s_all", ls->ls_name);
+
+	ls->ls_debug_all_dentry = debugfs_create_file(name,
+						      S_IFREG | S_IRUGO,
+						      dlm_root,
+						      ls,
+						      &format3_fops);
+	if (!ls->ls_debug_all_dentry)
+		goto fail;
+
+	/* format 4 */
+
+	memset(name, 0, sizeof(name));
+	snprintf(name, DLM_LOCKSPACE_LEN+8, "%s_toss", ls->ls_name);
+
+	ls->ls_debug_toss_dentry = debugfs_create_file(name,
+						       S_IFREG | S_IRUGO,
+						       dlm_root,
+						       ls,
+						       &format4_fops);
+	if (!ls->ls_debug_toss_dentry)
+		goto fail;
+
+	memset(name, 0, sizeof(name));
+	snprintf(name, DLM_LOCKSPACE_LEN+8, "%s_waiters", ls->ls_name);
+
+	ls->ls_debug_waiters_dentry = debugfs_create_file(name,
+							  S_IFREG | S_IRUGO,
+							  dlm_root,
+							  ls,
+							  &waiters_fops);
+	if (!ls->ls_debug_waiters_dentry)
+		goto fail;
+
+	return 0;
+
+ fail:
+	dlm_delete_debug_file(ls);
+	return -ENOMEM;
+}
+
+int __init dlm_register_debugfs(void)
+{
+	mutex_init(&debug_buf_lock);
+	dlm_root = debugfs_create_dir("dlm", NULL);
+	return dlm_root ? 0 : -ENOMEM;
+}
+
+void dlm_unregister_debugfs(void)
+{
+	debugfs_remove(dlm_root);
+}
+

fs/dlm/dir.c

@@ -0,0 +1,308 @@
+/******************************************************************************
+*******************************************************************************
+**
+**  Copyright (C) Sistina Software, Inc.  1997-2003  All rights reserved.
+**  Copyright (C) 2004-2005 Red Hat, Inc.  All rights reserved.
+**
+**  This copyrighted material is made available to anyone wishing to use,
+**  modify, copy, or redistribute it subject to the terms and conditions
+**  of the GNU General Public License v.2.
+**
+*******************************************************************************
+******************************************************************************/
+
+#include "dlm_internal.h"
+#include "lockspace.h"
+#include "member.h"
+#include "lowcomms.h"
+#include "rcom.h"
+#include "config.h"
+#include "memory.h"
+#include "recover.h"
+#include "util.h"
+#include "lock.h"
+#include "dir.h"
+
+/*
+ * We use the upper 16 bits of the hash value to select the directory node.
+ * Low bits are used for distribution of rsb's among hash buckets on each node.
+ *
+ * To give the exact range wanted (0 to num_nodes-1), we apply a modulus of
+ * num_nodes to the hash value.  This value in the desired range is used as an
+ * offset into the sorted list of nodeid's to give the particular nodeid.
+ */
+
+int dlm_hash2nodeid(struct dlm_ls *ls, uint32_t hash)
+{
+	uint32_t node;
+
+	if (ls->ls_num_nodes == 1)
+		return dlm_our_nodeid();
+	else {
+		node = (hash >> 16) % ls->ls_total_weight;
+		return ls->ls_node_array[node];
+	}
+}
+
+int dlm_dir_nodeid(struct dlm_rsb *r)
+{
+	return r->res_dir_nodeid;
+}
+
+void dlm_recover_dir_nodeid(struct dlm_ls *ls)
+{
+	struct dlm_rsb *r;
+
+	down_read(&ls->ls_root_sem);
+	list_for_each_entry(r, &ls->ls_root_list, res_root_list) {
+		r->res_dir_nodeid = dlm_hash2nodeid(ls, r->res_hash);
+	}
+	up_read(&ls->ls_root_sem);
+}
+
+int dlm_recover_directory(struct dlm_ls *ls)
+{
+	struct dlm_member *memb;
+	char *b, *last_name = NULL;
+	int error = -ENOMEM, last_len, nodeid, result;
+	uint16_t namelen;
+	unsigned int count = 0, count_match = 0, count_bad = 0, count_add = 0;
+
+	log_rinfo(ls, "dlm_recover_directory");
+
+	if (dlm_no_directory(ls))
+		goto out_status;
+
+	last_name = kmalloc(DLM_RESNAME_MAXLEN, GFP_NOFS);
+	if (!last_name)
+		goto out;
+
+	list_for_each_entry(memb, &ls->ls_nodes, list) {
+		if (memb->nodeid == dlm_our_nodeid())
+			continue;
+
+		memset(last_name, 0, DLM_RESNAME_MAXLEN);
+		last_len = 0;
+
+		for (;;) {
+			int left;
+			error = dlm_recovery_stopped(ls);
+			if (error)
+				goto out_free;
+
+			error = dlm_rcom_names(ls, memb->nodeid,
+					       last_name, last_len);
+			if (error)
+				goto out_free;
+
+			cond_resched();
+
+			/*
+			 * pick namelen/name pairs out of received buffer
+			 */
+
+			b = ls->ls_recover_buf->rc_buf;
+			left = ls->ls_recover_buf->rc_header.h_length;
+			left -= sizeof(struct dlm_rcom);
+
+			for (;;) {
+				__be16 v;
+
+				error = -EINVAL;
+				if (left < sizeof(__be16))
+					goto out_free;
+
+				memcpy(&v, b, sizeof(__be16));
+				namelen = be16_to_cpu(v);
+				b += sizeof(__be16);
+				left -= sizeof(__be16);
+
+				/* namelen of 0xFFFFF marks end of names for
+				   this node; namelen of 0 marks end of the
+				   buffer */
+
+				if (namelen == 0xFFFF)
+					goto done;
+				if (!namelen)
+					break;
+
+				if (namelen > left)
+					goto out_free;
+
+				if (namelen > DLM_RESNAME_MAXLEN)
+					goto out_free;
+
+				error = dlm_master_lookup(ls, memb->nodeid,
+							  b, namelen,
+							  DLM_LU_RECOVER_DIR,
+							  &nodeid, &result);
+				if (error) {
+					log_error(ls, "recover_dir lookup %d",
+						  error);
+					goto out_free;
+				}
+
+				/* The name was found in rsbtbl, but the
+				 * master nodeid is different from
+				 * memb->nodeid which says it is the master.
+				 * This should not happen. */
+
+				if (result == DLM_LU_MATCH &&
+				    nodeid != memb->nodeid) {
+					count_bad++;
+					log_error(ls, "recover_dir lookup %d "
+						  "nodeid %d memb %d bad %u",
+						  result, nodeid, memb->nodeid,
+						  count_bad);
+					print_hex_dump_bytes("dlm_recover_dir ",
+							     DUMP_PREFIX_NONE,
+							     b, namelen);
+				}
+
+				/* The name was found in rsbtbl, and the
+				 * master nodeid matches memb->nodeid. */
+
+				if (result == DLM_LU_MATCH &&
+				    nodeid == memb->nodeid) {
+					count_match++;
+				}
+
+				/* The name was not found in rsbtbl and was
+				 * added with memb->nodeid as the master. */
+
+				if (result == DLM_LU_ADD) {
+					count_add++;
+				}
+
+				last_len = namelen;
+				memcpy(last_name, b, namelen);
+				b += namelen;
+				left -= namelen;
+				count++;
+			}
+		}
+	 done:
+		;
+	}
+
+ out_status:
+	error = 0;
+	dlm_set_recover_status(ls, DLM_RS_DIR);
+
+	log_rinfo(ls, "dlm_recover_directory %u in %u new",
+		  count, count_add);
+ out_free:
+	kfree(last_name);
+ out:
+	return error;
+}
+
+static struct dlm_rsb *find_rsb_root(struct dlm_ls *ls, char *name, int len)
+{
+	struct dlm_rsb *r;
+	uint32_t hash, bucket;
+	int rv;
+
+	hash = jhash(name, len, 0);
+	bucket = hash & (ls->ls_rsbtbl_size - 1);
+
+	spin_lock(&ls->ls_rsbtbl[bucket].lock);
+	rv = dlm_search_rsb_tree(&ls->ls_rsbtbl[bucket].keep, name, len, &r);
+	if (rv)
+		rv = dlm_search_rsb_tree(&ls->ls_rsbtbl[bucket].toss,
+					 name, len, &r);
+	spin_unlock(&ls->ls_rsbtbl[bucket].lock);
+
+	if (!rv)
+		return r;
+
+	down_read(&ls->ls_root_sem);
+	list_for_each_entry(r, &ls->ls_root_list, res_root_list) {
+		if (len == r->res_length && !memcmp(name, r->res_name, len)) {
+			up_read(&ls->ls_root_sem);
+			log_debug(ls, "find_rsb_root revert to root_list %s",
+				  r->res_name);
+			return r;
+		}
+	}
+	up_read(&ls->ls_root_sem);
+	return NULL;
+}
+
+/* Find the rsb where we left off (or start again), then send rsb names
+   for rsb's we're master of and whose directory node matches the requesting
+   node.  inbuf is the rsb name last sent, inlen is the name's length */
+
+void dlm_copy_master_names(struct dlm_ls *ls, char *inbuf, int inlen,
+ 			   char *outbuf, int outlen, int nodeid)
+{
+	struct list_head *list;
+	struct dlm_rsb *r;
+	int offset = 0, dir_nodeid;
+	__be16 be_namelen;
+
+	down_read(&ls->ls_root_sem);
+
+	if (inlen > 1) {
+		r = find_rsb_root(ls, inbuf, inlen);
+		if (!r) {
+			inbuf[inlen - 1] = '\0';
+			log_error(ls, "copy_master_names from %d start %d %s",
+				  nodeid, inlen, inbuf);
+			goto out;
+		}
+		list = r->res_root_list.next;
+	} else {
+		list = ls->ls_root_list.next;
+	}
+
+	for (offset = 0; list != &ls->ls_root_list; list = list->next) {
+		r = list_entry(list, struct dlm_rsb, res_root_list);
+		if (r->res_nodeid)
+			continue;
+
+		dir_nodeid = dlm_dir_nodeid(r);
+		if (dir_nodeid != nodeid)
+			continue;
+
+		/*
+		 * The block ends when we can't fit the following in the
+		 * remaining buffer space:
+		 * namelen (uint16_t) +
+		 * name (r->res_length) +
+		 * end-of-block record 0x0000 (uint16_t)
+		 */
+
+		if (offset + sizeof(uint16_t)*2 + r->res_length > outlen) {
+			/* Write end-of-block record */
+			be_namelen = cpu_to_be16(0);
+			memcpy(outbuf + offset, &be_namelen, sizeof(__be16));
+			offset += sizeof(__be16);
+			ls->ls_recover_dir_sent_msg++;
+			goto out;
+		}
+
+		be_namelen = cpu_to_be16(r->res_length);
+		memcpy(outbuf + offset, &be_namelen, sizeof(__be16));
+		offset += sizeof(__be16);
+		memcpy(outbuf + offset, r->res_name, r->res_length);
+		offset += r->res_length;
+		ls->ls_recover_dir_sent_res++;
+	}
+
+	/*
+	 * If we've reached the end of the list (and there's room) write a
+	 * terminating record.
+	 */
+
+	if ((list == &ls->ls_root_list) &&
+	    (offset + sizeof(uint16_t) <= outlen)) {
+		be_namelen = cpu_to_be16(0xFFFF);
+		memcpy(outbuf + offset, &be_namelen, sizeof(__be16));
+		offset += sizeof(__be16);
+		ls->ls_recover_dir_sent_msg++;
+	}
+ out:
+	up_read(&ls->ls_root_sem);
+}
+

fs/dlm/dir.h

@@ -0,0 +1,25 @@
+/******************************************************************************
+*******************************************************************************
+**
+**  Copyright (C) Sistina Software, Inc.  1997-2003  All rights reserved.
+**  Copyright (C) 2004-2005 Red Hat, Inc.  All rights reserved.
+**
+**  This copyrighted material is made available to anyone wishing to use,
+**  modify, copy, or redistribute it subject to the terms and conditions
+**  of the GNU General Public License v.2.
+**
+*******************************************************************************
+******************************************************************************/
+
+#ifndef __DIR_DOT_H__
+#define __DIR_DOT_H__
+
+int dlm_dir_nodeid(struct dlm_rsb *rsb);
+int dlm_hash2nodeid(struct dlm_ls *ls, uint32_t hash);
+void dlm_recover_dir_nodeid(struct dlm_ls *ls);
+int dlm_recover_directory(struct dlm_ls *ls);
+void dlm_copy_master_names(struct dlm_ls *ls, char *inbuf, int inlen,
+	char *outbuf, int outlen, int nodeid);
+
+#endif				/* __DIR_DOT_H__ */
+

fs/dlm/dlm_internal.h

@@ -0,0 +1,729 @@
+/******************************************************************************
+*******************************************************************************
+**
+**  Copyright (C) Sistina Software, Inc.  1997-2003  All rights reserved.
+**  Copyright (C) 2004-2011 Red Hat, Inc.  All rights reserved.
+**
+**  This copyrighted material is made available to anyone wishing to use,
+**  modify, copy, or redistribute it subject to the terms and conditions
+**  of the GNU General Public License v.2.
+**
+*******************************************************************************
+******************************************************************************/
+
+#ifndef __DLM_INTERNAL_DOT_H__
+#define __DLM_INTERNAL_DOT_H__
+
+/*
+ * This is the main header file to be included in each DLM source file.
+ */
+
+#include <linux/module.h>
+#include <linux/slab.h>
+#include <linux/sched.h>
+#include <linux/types.h>
+#include <linux/ctype.h>
+#include <linux/spinlock.h>
+#include <linux/vmalloc.h>
+#include <linux/list.h>
+#include <linux/errno.h>
+#include <linux/random.h>
+#include <linux/delay.h>
+#include <linux/socket.h>
+#include <linux/kthread.h>
+#include <linux/kobject.h>
+#include <linux/kref.h>
+#include <linux/kernel.h>
+#include <linux/jhash.h>
+#include <linux/miscdevice.h>
+#include <linux/mutex.h>
+#include <linux/idr.h>
+#include <linux/ratelimit.h>
+#include <asm/uaccess.h>
+
+#include <linux/dlm.h>
+#include "config.h"
+
+/* Size of the temp buffer midcomms allocates on the stack.
+   We try to make this large enough so most messages fit.
+   FIXME: should sctp make this unnecessary? */
+
+#define DLM_INBUF_LEN		148
+
+struct dlm_ls;
+struct dlm_lkb;
+struct dlm_rsb;
+struct dlm_member;
+struct dlm_rsbtable;
+struct dlm_recover;
+struct dlm_header;
+struct dlm_message;
+struct dlm_rcom;
+struct dlm_mhandle;
+
+#define log_print(fmt, args...) \
+	printk(KERN_ERR "dlm: "fmt"\n" , ##args)
+#define log_error(ls, fmt, args...) \
+	printk(KERN_ERR "dlm: %s: " fmt "\n", (ls)->ls_name , ##args)
+#define log_rinfo(ls, fmt, args...) \
+	printk(KERN_INFO "dlm: %s: " fmt "\n", (ls)->ls_name , ##args);
+
+#define log_debug(ls, fmt, args...) \
+do { \
+	if (dlm_config.ci_log_debug) \
+		printk(KERN_DEBUG "dlm: %s: " fmt "\n", \
+		       (ls)->ls_name , ##args); \
+} while (0)
+
+#define log_limit(ls, fmt, args...) \
+do { \
+	if (dlm_config.ci_log_debug) \
+		printk_ratelimited(KERN_DEBUG "dlm: %s: " fmt "\n", \
+			(ls)->ls_name , ##args); \
+} while (0)
+
+#define DLM_ASSERT(x, do) \
+{ \
+  if (!(x)) \
+  { \
+    printk(KERN_ERR "\nDLM:  Assertion failed on line %d of file %s\n" \
+               "DLM:  assertion:  \"%s\"\n" \
+               "DLM:  time = %lu\n", \
+               __LINE__, __FILE__, #x, jiffies); \
+    {do} \
+    printk("\n"); \
+    BUG(); \
+    panic("DLM:  Record message above and reboot.\n"); \
+  } \
+}
+
+
+#define DLM_RTF_SHRINK		0x00000001
+
+struct dlm_rsbtable {
+	struct rb_root		keep;
+	struct rb_root		toss;
+	spinlock_t		lock;
+	uint32_t		flags;
+};
+
+
+/*
+ * Lockspace member (per node in a ls)
+ */
+
+struct dlm_member {
+	struct list_head	list;
+	int			nodeid;
+	int			weight;
+	int			slot;
+	int			slot_prev;
+	int			comm_seq;
+	uint32_t		generation;
+};
+
+/*
+ * Save and manage recovery state for a lockspace.
+ */
+
+struct dlm_recover {
+	struct list_head	list;
+	struct dlm_config_node	*nodes;
+	int			nodes_count;
+	uint64_t		seq;
+};
+
+/*
+ * Pass input args to second stage locking function.
+ */
+
+struct dlm_args {
+	uint32_t		flags;
+	void			(*astfn) (void *astparam);
+	void			*astparam;
+	void			(*bastfn) (void *astparam, int mode);
+	int			mode;
+	struct dlm_lksb		*lksb;
+	unsigned long		timeout;
+};
+
+
+/*
+ * Lock block
+ *
+ * A lock can be one of three types:
+ *
+ * local copy      lock is mastered locally
+ *                 (lkb_nodeid is zero and DLM_LKF_MSTCPY is not set)
+ * process copy    lock is mastered on a remote node
+ *                 (lkb_nodeid is non-zero and DLM_LKF_MSTCPY is not set)
+ * master copy     master node's copy of a lock owned by remote node
+ *                 (lkb_nodeid is non-zero and DLM_LKF_MSTCPY is set)
+ *
+ * lkb_exflags: a copy of the most recent flags arg provided to dlm_lock or
+ * dlm_unlock.  The dlm does not modify these or use any private flags in
+ * this field; it only contains DLM_LKF_ flags from dlm.h.  These flags
+ * are sent as-is to the remote master when the lock is remote.
+ *
+ * lkb_flags: internal dlm flags (DLM_IFL_ prefix) from dlm_internal.h.
+ * Some internal flags are shared between the master and process nodes;
+ * these shared flags are kept in the lower two bytes.  One of these
+ * flags set on the master copy will be propagated to the process copy
+ * and v.v.  Other internal flags are private to the master or process
+ * node (e.g. DLM_IFL_MSTCPY).  These are kept in the high two bytes.
+ *
+ * lkb_sbflags: status block flags.  These flags are copied directly into
+ * the caller's lksb.sb_flags prior to the dlm_lock/dlm_unlock completion
+ * ast.  All defined in dlm.h with DLM_SBF_ prefix.
+ *
+ * lkb_status: the lock status indicates which rsb queue the lock is
+ * on, grant, convert, or wait.  DLM_LKSTS_ WAITING/GRANTED/CONVERT
+ *
+ * lkb_wait_type: the dlm message type (DLM_MSG_ prefix) for which a
+ * reply is needed.  Only set when the lkb is on the lockspace waiters
+ * list awaiting a reply from a remote node.
+ *
+ * lkb_nodeid: when the lkb is a local copy, nodeid is 0; when the lkb
+ * is a master copy, nodeid specifies the remote lock holder, when the
+ * lkb is a process copy, the nodeid specifies the lock master.
+ */
+
+/* lkb_status */
+
+#define DLM_LKSTS_WAITING	1
+#define DLM_LKSTS_GRANTED	2
+#define DLM_LKSTS_CONVERT	3
+
+/* lkb_flags */
+
+#define DLM_IFL_MSTCPY		0x00010000
+#define DLM_IFL_RESEND		0x00020000
+#define DLM_IFL_DEAD		0x00040000
+#define DLM_IFL_OVERLAP_UNLOCK  0x00080000
+#define DLM_IFL_OVERLAP_CANCEL  0x00100000
+#define DLM_IFL_ENDOFLIFE	0x00200000
+#define DLM_IFL_WATCH_TIMEWARN	0x00400000
+#define DLM_IFL_TIMEOUT_CANCEL	0x00800000
+#define DLM_IFL_DEADLOCK_CANCEL	0x01000000
+#define DLM_IFL_STUB_MS		0x02000000 /* magic number for m_flags */
+#define DLM_IFL_USER		0x00000001
+#define DLM_IFL_ORPHAN		0x00000002
+
+#define DLM_CALLBACKS_SIZE	6
+
+#define DLM_CB_CAST		0x00000001
+#define DLM_CB_BAST		0x00000002
+#define DLM_CB_SKIP		0x00000004
+
+struct dlm_callback {
+	uint64_t		seq;
+	uint32_t		flags;		/* DLM_CBF_ */
+	int			sb_status;	/* copy to lksb status */
+	uint8_t			sb_flags;	/* copy to lksb flags */
+	int8_t			mode; /* rq mode of bast, gr mode of cast */
+};
+
+struct dlm_lkb {
+	struct dlm_rsb		*lkb_resource;	/* the rsb */
+	struct kref		lkb_ref;
+	int			lkb_nodeid;	/* copied from rsb */
+	int			lkb_ownpid;	/* pid of lock owner */
+	uint32_t		lkb_id;		/* our lock ID */
+	uint32_t		lkb_remid;	/* lock ID on remote partner */
+	uint32_t		lkb_exflags;	/* external flags from caller */
+	uint32_t		lkb_sbflags;	/* lksb flags */
+	uint32_t		lkb_flags;	/* internal flags */
+	uint32_t		lkb_lvbseq;	/* lvb sequence number */
+
+	int8_t			lkb_status;     /* granted, waiting, convert */
+	int8_t			lkb_rqmode;	/* requested lock mode */
+	int8_t			lkb_grmode;	/* granted lock mode */
+	int8_t			lkb_highbast;	/* highest mode bast sent for */
+
+	int8_t			lkb_wait_type;	/* type of reply waiting for */
+	int8_t			lkb_wait_count;
+	int			lkb_wait_nodeid; /* for debugging */
+
+	struct list_head	lkb_statequeue;	/* rsb g/c/w list */
+	struct list_head	lkb_rsb_lookup;	/* waiting for rsb lookup */
+	struct list_head	lkb_wait_reply;	/* waiting for remote reply */
+	struct list_head	lkb_ownqueue;	/* list of locks for a process */
+	struct list_head	lkb_time_list;
+	ktime_t			lkb_timestamp;
+	ktime_t			lkb_wait_time;
+	unsigned long		lkb_timeout_cs;
+
+	struct mutex		lkb_cb_mutex;
+	struct work_struct	lkb_cb_work;
+	struct list_head	lkb_cb_list; /* for ls_cb_delay or proc->asts */
+	struct dlm_callback	lkb_callbacks[DLM_CALLBACKS_SIZE];
+	struct dlm_callback	lkb_last_cast;
+	struct dlm_callback	lkb_last_bast;
+	ktime_t			lkb_last_cast_time;	/* for debugging */
+	ktime_t			lkb_last_bast_time;	/* for debugging */
+
+	uint64_t		lkb_recover_seq; /* from ls_recover_seq */
+
+	char			*lkb_lvbptr;
+	struct dlm_lksb		*lkb_lksb;      /* caller's status block */
+	void			(*lkb_astfn) (void *astparam);
+	void			(*lkb_bastfn) (void *astparam, int mode);
+	union {
+		void			*lkb_astparam;	/* caller's ast arg */
+		struct dlm_user_args	*lkb_ua;
+	};
+};
+
+/*
+ * res_master_nodeid is "normal": 0 is unset/invalid, non-zero is the real
+ * nodeid, even when nodeid is our_nodeid.
+ *
+ * res_nodeid is "odd": -1 is unset/invalid, zero means our_nodeid,
+ * greater than zero when another nodeid.
+ *
+ * (TODO: remove res_nodeid and only use res_master_nodeid)
+ */
+
+struct dlm_rsb {
+	struct dlm_ls		*res_ls;	/* the lockspace */
+	struct kref		res_ref;
+	struct mutex		res_mutex;
+	unsigned long		res_flags;
+	int			res_length;	/* length of rsb name */
+	int			res_nodeid;
+	int			res_master_nodeid;
+	int			res_dir_nodeid;
+	int			res_id;		/* for ls_recover_idr */
+	uint32_t                res_lvbseq;
+	uint32_t		res_hash;
+	uint32_t		res_bucket;	/* rsbtbl */
+	unsigned long		res_toss_time;
+	uint32_t		res_first_lkid;
+	struct list_head	res_lookup;	/* lkbs waiting on first */
+	union {
+		struct list_head	res_hashchain;
+		struct rb_node		res_hashnode;	/* rsbtbl */
+	};
+	struct list_head	res_grantqueue;
+	struct list_head	res_convertqueue;
+	struct list_head	res_waitqueue;
+
+	struct list_head	res_root_list;	    /* used for recovery */
+	struct list_head	res_recover_list;   /* used for recovery */
+	int			res_recover_locks_count;
+
+	char			*res_lvbptr;
+	char			res_name[DLM_RESNAME_MAXLEN+1];
+};
+
+/* dlm_master_lookup() flags */
+
+#define DLM_LU_RECOVER_DIR	1
+#define DLM_LU_RECOVER_MASTER	2
+
+/* dlm_master_lookup() results */
+
+#define DLM_LU_MATCH		1
+#define DLM_LU_ADD		2
+
+/* find_rsb() flags */
+
+#define R_REQUEST		0x00000001
+#define R_RECEIVE_REQUEST	0x00000002
+#define R_RECEIVE_RECOVER	0x00000004
+
+/* rsb_flags */
+
+enum rsb_flags {
+	RSB_MASTER_UNCERTAIN,
+	RSB_VALNOTVALID,
+	RSB_VALNOTVALID_PREV,
+	RSB_NEW_MASTER,
+	RSB_NEW_MASTER2,
+	RSB_RECOVER_CONVERT,
+	RSB_RECOVER_GRANT,
+	RSB_RECOVER_LVB_INVAL,
+};
+
+static inline void rsb_set_flag(struct dlm_rsb *r, enum rsb_flags flag)
+{
+	__set_bit(flag, &r->res_flags);
+}
+
+static inline void rsb_clear_flag(struct dlm_rsb *r, enum rsb_flags flag)
+{
+	__clear_bit(flag, &r->res_flags);
+}
+
+static inline int rsb_flag(struct dlm_rsb *r, enum rsb_flags flag)
+{
+	return test_bit(flag, &r->res_flags);
+}
+
+
+/* dlm_header is first element of all structs sent between nodes */
+
+#define DLM_HEADER_MAJOR	0x00030000
+#define DLM_HEADER_MINOR	0x00000001
+
+#define DLM_HEADER_SLOTS	0x00000001
+
+#define DLM_MSG			1
+#define DLM_RCOM		2
+
+struct dlm_header {
+	uint32_t		h_version;
+	uint32_t		h_lockspace;
+	uint32_t		h_nodeid;	/* nodeid of sender */
+	uint16_t		h_length;
+	uint8_t			h_cmd;		/* DLM_MSG, DLM_RCOM */
+	uint8_t			h_pad;
+};
+
+
+#define DLM_MSG_REQUEST		1
+#define DLM_MSG_CONVERT		2
+#define DLM_MSG_UNLOCK		3
+#define DLM_MSG_CANCEL		4
+#define DLM_MSG_REQUEST_REPLY	5
+#define DLM_MSG_CONVERT_REPLY	6
+#define DLM_MSG_UNLOCK_REPLY	7
+#define DLM_MSG_CANCEL_REPLY	8
+#define DLM_MSG_GRANT		9
+#define DLM_MSG_BAST		10
+#define DLM_MSG_LOOKUP		11
+#define DLM_MSG_REMOVE		12
+#define DLM_MSG_LOOKUP_REPLY	13
+#define DLM_MSG_PURGE		14
+
+struct dlm_message {
+	struct dlm_header	m_header;
+	uint32_t		m_type;		/* DLM_MSG_ */
+	uint32_t		m_nodeid;
+	uint32_t		m_pid;
+	uint32_t		m_lkid;		/* lkid on sender */
+	uint32_t		m_remid;	/* lkid on receiver */
+	uint32_t		m_parent_lkid;
+	uint32_t		m_parent_remid;
+	uint32_t		m_exflags;
+	uint32_t		m_sbflags;
+	uint32_t		m_flags;
+	uint32_t		m_lvbseq;
+	uint32_t		m_hash;
+	int			m_status;
+	int			m_grmode;
+	int			m_rqmode;
+	int			m_bastmode;
+	int			m_asts;
+	int			m_result;	/* 0 or -EXXX */
+	char			m_extra[0];	/* name or lvb */
+};
+
+
+#define DLM_RS_NODES		0x00000001
+#define DLM_RS_NODES_ALL	0x00000002
+#define DLM_RS_DIR		0x00000004
+#define DLM_RS_DIR_ALL		0x00000008
+#define DLM_RS_LOCKS		0x00000010
+#define DLM_RS_LOCKS_ALL	0x00000020
+#define DLM_RS_DONE		0x00000040
+#define DLM_RS_DONE_ALL		0x00000080
+
+#define DLM_RCOM_STATUS		1
+#define DLM_RCOM_NAMES		2
+#define DLM_RCOM_LOOKUP		3
+#define DLM_RCOM_LOCK		4
+#define DLM_RCOM_STATUS_REPLY	5
+#define DLM_RCOM_NAMES_REPLY	6
+#define DLM_RCOM_LOOKUP_REPLY	7
+#define DLM_RCOM_LOCK_REPLY	8
+
+struct dlm_rcom {
+	struct dlm_header	rc_header;
+	uint32_t		rc_type;	/* DLM_RCOM_ */
+	int			rc_result;	/* multi-purpose */
+	uint64_t		rc_id;		/* match reply with request */
+	uint64_t		rc_seq;		/* sender's ls_recover_seq */
+	uint64_t		rc_seq_reply;	/* remote ls_recover_seq */
+	char			rc_buf[0];
+};
+
+union dlm_packet {
+	struct dlm_header	header;		/* common to other two */
+	struct dlm_message	message;
+	struct dlm_rcom		rcom;
+};
+
+#define DLM_RSF_NEED_SLOTS	0x00000001
+
+/* RCOM_STATUS data */
+struct rcom_status {
+	__le32			rs_flags;
+	__le32			rs_unused1;
+	__le64			rs_unused2;
+};
+
+/* RCOM_STATUS_REPLY data */
+struct rcom_config {
+	__le32			rf_lvblen;
+	__le32			rf_lsflags;
+
+	/* DLM_HEADER_SLOTS adds: */
+	__le32			rf_flags;
+	__le16			rf_our_slot;
+	__le16			rf_num_slots;
+	__le32			rf_generation;
+	__le32			rf_unused1;
+	__le64			rf_unused2;
+};
+
+struct rcom_slot {
+	__le32			ro_nodeid;
+	__le16			ro_slot;
+	__le16			ro_unused1;
+	__le64			ro_unused2;
+};
+
+struct rcom_lock {
+	__le32			rl_ownpid;
+	__le32			rl_lkid;
+	__le32			rl_remid;
+	__le32			rl_parent_lkid;
+	__le32			rl_parent_remid;
+	__le32			rl_exflags;
+	__le32			rl_flags;
+	__le32			rl_lvbseq;
+	__le32			rl_result;
+	int8_t			rl_rqmode;
+	int8_t			rl_grmode;
+	int8_t			rl_status;
+	int8_t			rl_asts;
+	__le16			rl_wait_type;
+	__le16			rl_namelen;
+	char			rl_name[DLM_RESNAME_MAXLEN];
+	char			rl_lvb[0];
+};
+
+/*
+ * The max number of resources per rsbtbl bucket that shrink will attempt
+ * to remove in each iteration.
+ */
+
+#define DLM_REMOVE_NAMES_MAX 8
+
+struct dlm_ls {
+	struct list_head	ls_list;	/* list of lockspaces */
+	dlm_lockspace_t		*ls_local_handle;
+	uint32_t		ls_global_id;	/* global unique lockspace ID */
+	uint32_t		ls_generation;
+	uint32_t		ls_exflags;
+	int			ls_lvblen;
+	int			ls_count;	/* refcount of processes in
+						   the dlm using this ls */
+	int			ls_create_count; /* create/release refcount */
+	unsigned long		ls_flags;	/* LSFL_ */
+	unsigned long		ls_scan_time;
+	struct kobject		ls_kobj;
+
+	struct idr		ls_lkbidr;
+	spinlock_t		ls_lkbidr_spin;
+
+	struct dlm_rsbtable	*ls_rsbtbl;
+	uint32_t		ls_rsbtbl_size;
+
+	struct mutex		ls_waiters_mutex;
+	struct list_head	ls_waiters;	/* lkbs needing a reply */
+
+	struct mutex		ls_orphans_mutex;
+	struct list_head	ls_orphans;
+
+	struct mutex		ls_timeout_mutex;
+	struct list_head	ls_timeout;
+
+	spinlock_t		ls_new_rsb_spin;
+	int			ls_new_rsb_count;
+	struct list_head	ls_new_rsb;	/* new rsb structs */
+
+	spinlock_t		ls_remove_spin;
+	char			ls_remove_name[DLM_RESNAME_MAXLEN+1];
+	char			*ls_remove_names[DLM_REMOVE_NAMES_MAX];
+	int			ls_remove_len;
+	int			ls_remove_lens[DLM_REMOVE_NAMES_MAX];
+
+	struct list_head	ls_nodes;	/* current nodes in ls */
+	struct list_head	ls_nodes_gone;	/* dead node list, recovery */
+	int			ls_num_nodes;	/* number of nodes in ls */
+	int			ls_low_nodeid;
+	int			ls_total_weight;
+	int			*ls_node_array;
+
+	int			ls_slot;
+	int			ls_num_slots;
+	int			ls_slots_size;
+	struct dlm_slot		*ls_slots;
+
+	struct dlm_rsb		ls_stub_rsb;	/* for returning errors */
+	struct dlm_lkb		ls_stub_lkb;	/* for returning errors */
+	struct dlm_message	ls_stub_ms;	/* for faking a reply */
+
+	struct dentry		*ls_debug_rsb_dentry; /* debugfs */
+	struct dentry		*ls_debug_waiters_dentry; /* debugfs */
+	struct dentry		*ls_debug_locks_dentry; /* debugfs */
+	struct dentry		*ls_debug_all_dentry; /* debugfs */
+	struct dentry		*ls_debug_toss_dentry; /* debugfs */
+
+	wait_queue_head_t	ls_uevent_wait;	/* user part of join/leave */
+	int			ls_uevent_result;
+	struct completion	ls_members_done;
+	int			ls_members_result;
+
+	struct miscdevice       ls_device;
+
+	struct workqueue_struct	*ls_callback_wq;
+
+	/* recovery related */
+
+	struct mutex		ls_cb_mutex;
+	struct list_head	ls_cb_delay; /* save for queue_work later */
+	struct timer_list	ls_timer;
+	struct task_struct	*ls_recoverd_task;
+	struct mutex		ls_recoverd_active;
+	spinlock_t		ls_recover_lock;
+	unsigned long		ls_recover_begin; /* jiffies timestamp */
+	uint32_t		ls_recover_status; /* DLM_RS_ */
+	uint64_t		ls_recover_seq;
+	struct dlm_recover	*ls_recover_args;
+	struct rw_semaphore	ls_in_recovery;	/* block local requests */
+	struct rw_semaphore	ls_recv_active;	/* block dlm_recv */
+	struct list_head	ls_requestqueue;/* queue remote requests */
+	struct mutex		ls_requestqueue_mutex;
+	struct dlm_rcom		*ls_recover_buf;
+	int			ls_recover_nodeid; /* for debugging */
+	unsigned int		ls_recover_dir_sent_res; /* for log info */
+	unsigned int		ls_recover_dir_sent_msg; /* for log info */
+	unsigned int		ls_recover_locks_in; /* for log info */
+	uint64_t		ls_rcom_seq;
+	spinlock_t		ls_rcom_spin;
+	struct list_head	ls_recover_list;
+	spinlock_t		ls_recover_list_lock;
+	int			ls_recover_list_count;
+	struct idr		ls_recover_idr;
+	spinlock_t		ls_recover_idr_lock;
+	wait_queue_head_t	ls_wait_general;
+	wait_queue_head_t	ls_recover_lock_wait;
+	struct mutex		ls_clear_proc_locks;
+
+	struct list_head	ls_root_list;	/* root resources */
+	struct rw_semaphore	ls_root_sem;	/* protect root_list */
+
+	const struct dlm_lockspace_ops *ls_ops;
+	void			*ls_ops_arg;
+
+	int			ls_namelen;
+	char			ls_name[1];
+};
+
+/*
+ * LSFL_RECOVER_STOP - dlm_ls_stop() sets this to tell dlm recovery routines
+ * that they should abort what they're doing so new recovery can be started.
+ *
+ * LSFL_RECOVER_DOWN - dlm_ls_stop() sets this to tell dlm_recoverd that it
+ * should do down_write() on the in_recovery rw_semaphore. (doing down_write
+ * within dlm_ls_stop causes complaints about the lock acquired/released
+ * in different contexts.)
+ *
+ * LSFL_RECOVER_LOCK - dlm_recoverd holds the in_recovery rw_semaphore.
+ * It sets this after it is done with down_write() on the in_recovery
+ * rw_semaphore and clears it after it has released the rw_semaphore.
+ *
+ * LSFL_RECOVER_WORK - dlm_ls_start() sets this to tell dlm_recoverd that it
+ * should begin recovery of the lockspace.
+ *
+ * LSFL_RUNNING - set when normal locking activity is enabled.
+ * dlm_ls_stop() clears this to tell dlm locking routines that they should
+ * quit what they are doing so recovery can run.  dlm_recoverd sets
+ * this after recovery is finished.
+ */
+
+#define LSFL_RECOVER_STOP	0
+#define LSFL_RECOVER_DOWN	1
+#define LSFL_RECOVER_LOCK	2
+#define LSFL_RECOVER_WORK	3
+#define LSFL_RUNNING		4
+
+#define LSFL_RCOM_READY		5
+#define LSFL_RCOM_WAIT		6
+#define LSFL_UEVENT_WAIT	7
+#define LSFL_TIMEWARN		8
+#define LSFL_CB_DELAY		9
+#define LSFL_NODIR		10
+
+/* much of this is just saving user space pointers associated with the
+   lock that we pass back to the user lib with an ast */
+
+struct dlm_user_args {
+	struct dlm_user_proc	*proc; /* each process that opens the lockspace
+					  device has private data
+					  (dlm_user_proc) on the struct file,
+					  the process's locks point back to it*/
+	struct dlm_lksb		lksb;
+	struct dlm_lksb __user	*user_lksb;
+	void __user		*castparam;
+	void __user		*castaddr;
+	void __user		*bastparam;
+	void __user		*bastaddr;
+	uint64_t		xid;
+};
+
+#define DLM_PROC_FLAGS_CLOSING 1
+#define DLM_PROC_FLAGS_COMPAT  2
+
+/* locks list is kept so we can remove all a process's locks when it
+   exits (or orphan those that are persistent) */
+
+struct dlm_user_proc {
+	dlm_lockspace_t		*lockspace;
+	unsigned long		flags; /* DLM_PROC_FLAGS */
+	struct list_head	asts;
+	spinlock_t		asts_spin;
+	struct list_head	locks;
+	spinlock_t		locks_spin;
+	struct list_head	unlocking;
+	wait_queue_head_t	wait;
+};
+
+static inline int dlm_locking_stopped(struct dlm_ls *ls)
+{
+	return !test_bit(LSFL_RUNNING, &ls->ls_flags);
+}
+
+static inline int dlm_recovery_stopped(struct dlm_ls *ls)
+{
+	return test_bit(LSFL_RECOVER_STOP, &ls->ls_flags);
+}
+
+static inline int dlm_no_directory(struct dlm_ls *ls)
+{
+	return test_bit(LSFL_NODIR, &ls->ls_flags);
+}
+
+int dlm_netlink_init(void);
+void dlm_netlink_exit(void);
+void dlm_timeout_warn(struct dlm_lkb *lkb);
+int dlm_plock_init(void);
+void dlm_plock_exit(void);
+
+#ifdef CONFIG_DLM_DEBUG
+int dlm_register_debugfs(void);
+void dlm_unregister_debugfs(void);
+int dlm_create_debug_file(struct dlm_ls *ls);
+void dlm_delete_debug_file(struct dlm_ls *ls);
+#else
+static inline int dlm_register_debugfs(void) { return 0; }
+static inline void dlm_unregister_debugfs(void) { }
+static inline int dlm_create_debug_file(struct dlm_ls *ls) { return 0; }
+static inline void dlm_delete_debug_file(struct dlm_ls *ls) { }
+#endif
+
+#endif				/* __DLM_INTERNAL_DOT_H__ */
+

fs/dlm/lock.h

@@ -0,0 +1,77 @@
+/******************************************************************************
+*******************************************************************************
+**
+**  Copyright (C) 2005-2007 Red Hat, Inc.  All rights reserved.
+**
+**  This copyrighted material is made available to anyone wishing to use,
+**  modify, copy, or redistribute it subject to the terms and conditions
+**  of the GNU General Public License v.2.
+**
+*******************************************************************************
+******************************************************************************/
+
+#ifndef __LOCK_DOT_H__
+#define __LOCK_DOT_H__
+
+void dlm_dump_rsb(struct dlm_rsb *r);
+void dlm_dump_rsb_name(struct dlm_ls *ls, char *name, int len);
+void dlm_print_lkb(struct dlm_lkb *lkb);
+void dlm_receive_message_saved(struct dlm_ls *ls, struct dlm_message *ms,
+			       uint32_t saved_seq);
+void dlm_receive_buffer(union dlm_packet *p, int nodeid);
+int dlm_modes_compat(int mode1, int mode2);
+void dlm_put_rsb(struct dlm_rsb *r);
+void dlm_hold_rsb(struct dlm_rsb *r);
+int dlm_put_lkb(struct dlm_lkb *lkb);
+void dlm_scan_rsbs(struct dlm_ls *ls);
+int dlm_lock_recovery_try(struct dlm_ls *ls);
+void dlm_unlock_recovery(struct dlm_ls *ls);
+void dlm_scan_waiters(struct dlm_ls *ls);
+void dlm_scan_timeout(struct dlm_ls *ls);
+void dlm_adjust_timeouts(struct dlm_ls *ls);
+int dlm_master_lookup(struct dlm_ls *ls, int nodeid, char *name, int len,
+		      unsigned int flags, int *r_nodeid, int *result);
+
+int dlm_search_rsb_tree(struct rb_root *tree, char *name, int len,
+			struct dlm_rsb **r_ret);
+
+void dlm_recover_purge(struct dlm_ls *ls);
+void dlm_purge_mstcpy_locks(struct dlm_rsb *r);
+void dlm_recover_grant(struct dlm_ls *ls);
+int dlm_recover_waiters_post(struct dlm_ls *ls);
+void dlm_recover_waiters_pre(struct dlm_ls *ls);
+int dlm_recover_master_copy(struct dlm_ls *ls, struct dlm_rcom *rc);
+int dlm_recover_process_copy(struct dlm_ls *ls, struct dlm_rcom *rc);
+
+int dlm_user_request(struct dlm_ls *ls, struct dlm_user_args *ua, int mode,
+	uint32_t flags, void *name, unsigned int namelen,
+	unsigned long timeout_cs);
+int dlm_user_convert(struct dlm_ls *ls, struct dlm_user_args *ua_tmp,
+	int mode, uint32_t flags, uint32_t lkid, char *lvb_in,
+	unsigned long timeout_cs);
+int dlm_user_unlock(struct dlm_ls *ls, struct dlm_user_args *ua_tmp,
+	uint32_t flags, uint32_t lkid, char *lvb_in);
+int dlm_user_cancel(struct dlm_ls *ls,  struct dlm_user_args *ua_tmp,
+	uint32_t flags, uint32_t lkid);
+int dlm_user_purge(struct dlm_ls *ls, struct dlm_user_proc *proc,
+	int nodeid, int pid);
+int dlm_user_deadlock(struct dlm_ls *ls, uint32_t flags, uint32_t lkid);
+void dlm_clear_proc_locks(struct dlm_ls *ls, struct dlm_user_proc *proc);
+
+static inline int is_master(struct dlm_rsb *r)
+{
+	return !r->res_nodeid;
+}
+
+static inline void lock_rsb(struct dlm_rsb *r)
+{
+	mutex_lock(&r->res_mutex);
+}
+
+static inline void unlock_rsb(struct dlm_rsb *r)
+{
+	mutex_unlock(&r->res_mutex);
+}
+
+#endif
+

fs/dlm/lockspace.c

@@ -0,0 +1,917 @@
+/******************************************************************************
+*******************************************************************************
+**
+**  Copyright (C) Sistina Software, Inc.  1997-2003  All rights reserved.
+**  Copyright (C) 2004-2011 Red Hat, Inc.  All rights reserved.
+**
+**  This copyrighted material is made available to anyone wishing to use,
+**  modify, copy, or redistribute it subject to the terms and conditions
+**  of the GNU General Public License v.2.
+**
+*******************************************************************************
+******************************************************************************/
+
+#include "dlm_internal.h"
+#include "lockspace.h"
+#include "member.h"
+#include "recoverd.h"
+#include "dir.h"
+#include "lowcomms.h"
+#include "config.h"
+#include "memory.h"
+#include "lock.h"
+#include "recover.h"
+#include "requestqueue.h"
+#include "user.h"
+#include "ast.h"
+
+static int			ls_count;
+static struct mutex		ls_lock;
+static struct list_head		lslist;
+static spinlock_t		lslist_lock;
+static struct task_struct *	scand_task;
+
+
+static ssize_t dlm_control_store(struct dlm_ls *ls, const char *buf, size_t len)
+{
+	ssize_t ret = len;
+	int n;
+	int rc = kstrtoint(buf, 0, &n);
+
+	if (rc)
+		return rc;
+	ls = dlm_find_lockspace_local(ls->ls_local_handle);
+	if (!ls)
+		return -EINVAL;
+
+	switch (n) {
+	case 0:
+		dlm_ls_stop(ls);
+		break;
+	case 1:
+		dlm_ls_start(ls);
+		break;
+	default:
+		ret = -EINVAL;
+	}
+	dlm_put_lockspace(ls);
+	return ret;
+}
+
+static ssize_t dlm_event_store(struct dlm_ls *ls, const char *buf, size_t len)
+{
+	int rc = kstrtoint(buf, 0, &ls->ls_uevent_result);
+
+	if (rc)
+		return rc;
+	set_bit(LSFL_UEVENT_WAIT, &ls->ls_flags);
+	wake_up(&ls->ls_uevent_wait);
+	return len;
+}
+
+static ssize_t dlm_id_show(struct dlm_ls *ls, char *buf)
+{
+	return snprintf(buf, PAGE_SIZE, "%u\n", ls->ls_global_id);
+}
+
+static ssize_t dlm_id_store(struct dlm_ls *ls, const char *buf, size_t len)
+{
+	int rc = kstrtouint(buf, 0, &ls->ls_global_id);
+
+	if (rc)
+		return rc;
+	return len;
+}
+
+static ssize_t dlm_nodir_show(struct dlm_ls *ls, char *buf)
+{
+	return snprintf(buf, PAGE_SIZE, "%u\n", dlm_no_directory(ls));
+}
+
+static ssize_t dlm_nodir_store(struct dlm_ls *ls, const char *buf, size_t len)
+{
+	int val;
+	int rc = kstrtoint(buf, 0, &val);
+
+	if (rc)
+		return rc;
+	if (val == 1)
+		set_bit(LSFL_NODIR, &ls->ls_flags);
+	return len;
+}
+
+static ssize_t dlm_recover_status_show(struct dlm_ls *ls, char *buf)
+{
+	uint32_t status = dlm_recover_status(ls);
+	return snprintf(buf, PAGE_SIZE, "%x\n", status);
+}
+
+static ssize_t dlm_recover_nodeid_show(struct dlm_ls *ls, char *buf)
+{
+	return snprintf(buf, PAGE_SIZE, "%d\n", ls->ls_recover_nodeid);
+}
+
+struct dlm_attr {
+	struct attribute attr;
+	ssize_t (*show)(struct dlm_ls *, char *);
+	ssize_t (*store)(struct dlm_ls *, const char *, size_t);
+};
+
+static struct dlm_attr dlm_attr_control = {
+	.attr  = {.name = "control", .mode = S_IWUSR},
+	.store = dlm_control_store
+};
+
+static struct dlm_attr dlm_attr_event = {
+	.attr  = {.name = "event_done", .mode = S_IWUSR},
+	.store = dlm_event_store
+};
+
+static struct dlm_attr dlm_attr_id = {
+	.attr  = {.name = "id", .mode = S_IRUGO | S_IWUSR},
+	.show  = dlm_id_show,
+	.store = dlm_id_store
+};
+
+static struct dlm_attr dlm_attr_nodir = {
+	.attr  = {.name = "nodir", .mode = S_IRUGO | S_IWUSR},
+	.show  = dlm_nodir_show,
+	.store = dlm_nodir_store
+};
+
+static struct dlm_attr dlm_attr_recover_status = {
+	.attr  = {.name = "recover_status", .mode = S_IRUGO},
+	.show  = dlm_recover_status_show
+};
+
+static struct dlm_attr dlm_attr_recover_nodeid = {
+	.attr  = {.name = "recover_nodeid", .mode = S_IRUGO},
+	.show  = dlm_recover_nodeid_show
+};
+
+static struct attribute *dlm_attrs[] = {
+	&dlm_attr_control.attr,
+	&dlm_attr_event.attr,
+	&dlm_attr_id.attr,
+	&dlm_attr_nodir.attr,
+	&dlm_attr_recover_status.attr,
+	&dlm_attr_recover_nodeid.attr,
+	NULL,
+};
+
+static ssize_t dlm_attr_show(struct kobject *kobj, struct attribute *attr,
+			     char *buf)
+{
+	struct dlm_ls *ls  = container_of(kobj, struct dlm_ls, ls_kobj);
+	struct dlm_attr *a = container_of(attr, struct dlm_attr, attr);
+	return a->show ? a->show(ls, buf) : 0;
+}
+
+static ssize_t dlm_attr_store(struct kobject *kobj, struct attribute *attr,
+			      const char *buf, size_t len)
+{
+	struct dlm_ls *ls  = container_of(kobj, struct dlm_ls, ls_kobj);
+	struct dlm_attr *a = container_of(attr, struct dlm_attr, attr);
+	return a->store ? a->store(ls, buf, len) : len;
+}
+
+static void lockspace_kobj_release(struct kobject *k)
+{
+	struct dlm_ls *ls  = container_of(k, struct dlm_ls, ls_kobj);
+	kfree(ls);
+}
+
+static const struct sysfs_ops dlm_attr_ops = {
+	.show  = dlm_attr_show,
+	.store = dlm_attr_store,
+};
+
+static struct kobj_type dlm_ktype = {
+	.default_attrs = dlm_attrs,
+	.sysfs_ops     = &dlm_attr_ops,
+	.release       = lockspace_kobj_release,
+};
+
+static struct kset *dlm_kset;
+
+static int do_uevent(struct dlm_ls *ls, int in)
+{
+	int error;
+
+	if (in)
+		kobject_uevent(&ls->ls_kobj, KOBJ_ONLINE);
+	else
+		kobject_uevent(&ls->ls_kobj, KOBJ_OFFLINE);
+
+	log_rinfo(ls, "%s the lockspace group...", in ? "joining" : "leaving");
+
+	/* dlm_controld will see the uevent, do the necessary group management
+	   and then write to sysfs to wake us */
+
+	error = wait_event_interruptible(ls->ls_uevent_wait,
+			test_and_clear_bit(LSFL_UEVENT_WAIT, &ls->ls_flags));
+
+	log_rinfo(ls, "group event done %d %d", error, ls->ls_uevent_result);
+
+	if (error)
+		goto out;
+
+	error = ls->ls_uevent_result;
+ out:
+	if (error)
+		log_error(ls, "group %s failed %d %d", in ? "join" : "leave",
+			  error, ls->ls_uevent_result);
+	return error;
+}
+
+static int dlm_uevent(struct kset *kset, struct kobject *kobj,
+		      struct kobj_uevent_env *env)
+{
+	struct dlm_ls *ls = container_of(kobj, struct dlm_ls, ls_kobj);
+
+	add_uevent_var(env, "LOCKSPACE=%s", ls->ls_name);
+	return 0;
+}
+
+static struct kset_uevent_ops dlm_uevent_ops = {
+	.uevent = dlm_uevent,
+};
+
+int __init dlm_lockspace_init(void)
+{
+	ls_count = 0;
+	mutex_init(&ls_lock);
+	INIT_LIST_HEAD(&lslist);
+	spin_lock_init(&lslist_lock);
+
+	dlm_kset = kset_create_and_add("dlm", &dlm_uevent_ops, kernel_kobj);
+	if (!dlm_kset) {
+		printk(KERN_WARNING "%s: can not create kset\n", __func__);
+		return -ENOMEM;
+	}
+	return 0;
+}
+
+void dlm_lockspace_exit(void)
+{
+	kset_unregister(dlm_kset);
+}
+
+static struct dlm_ls *find_ls_to_scan(void)
+{
+	struct dlm_ls *ls;
+
+	spin_lock(&lslist_lock);
+	list_for_each_entry(ls, &lslist, ls_list) {
+		if (time_after_eq(jiffies, ls->ls_scan_time +
+					    dlm_config.ci_scan_secs * HZ)) {
+			spin_unlock(&lslist_lock);
+			return ls;
+		}
+	}
+	spin_unlock(&lslist_lock);
+	return NULL;
+}
+
+static int dlm_scand(void *data)
+{
+	struct dlm_ls *ls;
+
+	while (!kthread_should_stop()) {
+		ls = find_ls_to_scan();
+		if (ls) {
+			if (dlm_lock_recovery_try(ls)) {
+				ls->ls_scan_time = jiffies;
+				dlm_scan_rsbs(ls);
+				dlm_scan_timeout(ls);
+				dlm_scan_waiters(ls);
+				dlm_unlock_recovery(ls);
+			} else {
+				ls->ls_scan_time += HZ;
+			}
+			continue;
+		}
+		schedule_timeout_interruptible(dlm_config.ci_scan_secs * HZ);
+	}
+	return 0;
+}
+
+static int dlm_scand_start(void)
+{
+	struct task_struct *p;
+	int error = 0;
+
+	p = kthread_run(dlm_scand, NULL, "dlm_scand");
+	if (IS_ERR(p))
+		error = PTR_ERR(p);
+	else
+		scand_task = p;
+	return error;
+}
+
+static void dlm_scand_stop(void)
+{
+	kthread_stop(scand_task);
+}
+
+struct dlm_ls *dlm_find_lockspace_global(uint32_t id)
+{
+	struct dlm_ls *ls;
+
+	spin_lock(&lslist_lock);
+
+	list_for_each_entry(ls, &lslist, ls_list) {
+		if (ls->ls_global_id == id) {
+			ls->ls_count++;
+			goto out;
+		}
+	}
+	ls = NULL;
+ out:
+	spin_unlock(&lslist_lock);
+	return ls;
+}
+
+struct dlm_ls *dlm_find_lockspace_local(dlm_lockspace_t *lockspace)
+{
+	struct dlm_ls *ls;
+
+	spin_lock(&lslist_lock);
+	list_for_each_entry(ls, &lslist, ls_list) {
+		if (ls->ls_local_handle == lockspace) {
+			ls->ls_count++;
+			goto out;
+		}
+	}
+	ls = NULL;
+ out:
+	spin_unlock(&lslist_lock);
+	return ls;
+}
+
+struct dlm_ls *dlm_find_lockspace_device(int minor)
+{
+	struct dlm_ls *ls;
+
+	spin_lock(&lslist_lock);
+	list_for_each_entry(ls, &lslist, ls_list) {
+		if (ls->ls_device.minor == minor) {
+			ls->ls_count++;
+			goto out;
+		}
+	}
+	ls = NULL;
+ out:
+	spin_unlock(&lslist_lock);
+	return ls;
+}
+
+void dlm_put_lockspace(struct dlm_ls *ls)
+{
+	spin_lock(&lslist_lock);
+	ls->ls_count--;
+	spin_unlock(&lslist_lock);
+}
+
+static void remove_lockspace(struct dlm_ls *ls)
+{
+	for (;;) {
+		spin_lock(&lslist_lock);
+		if (ls->ls_count == 0) {
+			WARN_ON(ls->ls_create_count != 0);
+			list_del(&ls->ls_list);
+			spin_unlock(&lslist_lock);
+			return;
+		}
+		spin_unlock(&lslist_lock);
+		ssleep(1);
+	}
+}
+
+static int threads_start(void)
+{
+	int error;
+
+	error = dlm_scand_start();
+	if (error) {
+		log_print("cannot start dlm_scand thread %d", error);
+		goto fail;
+	}
+
+	/* Thread for sending/receiving messages for all lockspace's */
+	error = dlm_lowcomms_start();
+	if (error) {
+		log_print("cannot start dlm lowcomms %d", error);
+		goto scand_fail;
+	}
+
+	return 0;
+
+ scand_fail:
+	dlm_scand_stop();
+ fail:
+	return error;
+}
+
+static void threads_stop(void)
+{
+	dlm_scand_stop();
+	dlm_lowcomms_stop();
+}
+
+static int new_lockspace(const char *name, const char *cluster,
+			 uint32_t flags, int lvblen,
+			 const struct dlm_lockspace_ops *ops, void *ops_arg,
+			 int *ops_result, dlm_lockspace_t **lockspace)
+{
+	struct dlm_ls *ls;
+	int i, size, error;
+	int do_unreg = 0;
+	int namelen = strlen(name);
+
+	if (namelen > DLM_LOCKSPACE_LEN)
+		return -EINVAL;
+
+	if (!lvblen || (lvblen % 8))
+		return -EINVAL;
+
+	if (!try_module_get(THIS_MODULE))
+		return -EINVAL;
+
+	if (!dlm_user_daemon_available()) {
+		log_print("dlm user daemon not available");
+		error = -EUNATCH;
+		goto out;
+	}
+
+	if (ops && ops_result) {
+	       	if (!dlm_config.ci_recover_callbacks)
+			*ops_result = -EOPNOTSUPP;
+		else
+			*ops_result = 0;
+	}
+
+	if (dlm_config.ci_recover_callbacks && cluster &&
+	    strncmp(cluster, dlm_config.ci_cluster_name, DLM_LOCKSPACE_LEN)) {
+		log_print("dlm cluster name %s mismatch %s",
+			  dlm_config.ci_cluster_name, cluster);
+		error = -EBADR;
+		goto out;
+	}
+
+	error = 0;
+
+	spin_lock(&lslist_lock);
+	list_for_each_entry(ls, &lslist, ls_list) {
+		WARN_ON(ls->ls_create_count <= 0);
+		if (ls->ls_namelen != namelen)
+			continue;
+		if (memcmp(ls->ls_name, name, namelen))
+			continue;
+		if (flags & DLM_LSFL_NEWEXCL) {
+			error = -EEXIST;
+			break;
+		}
+		ls->ls_create_count++;
+		*lockspace = ls;
+		error = 1;
+		break;
+	}
+	spin_unlock(&lslist_lock);
+
+	if (error)
+		goto out;
+
+	error = -ENOMEM;
+
+	ls = kzalloc(sizeof(struct dlm_ls) + namelen, GFP_NOFS);
+	if (!ls)
+		goto out;
+	memcpy(ls->ls_name, name, namelen);
+	ls->ls_namelen = namelen;
+	ls->ls_lvblen = lvblen;
+	ls->ls_count = 0;
+	ls->ls_flags = 0;
+	ls->ls_scan_time = jiffies;
+
+	if (ops && dlm_config.ci_recover_callbacks) {
+		ls->ls_ops = ops;
+		ls->ls_ops_arg = ops_arg;
+	}
+
+	if (flags & DLM_LSFL_TIMEWARN)
+		set_bit(LSFL_TIMEWARN, &ls->ls_flags);
+
+	/* ls_exflags are forced to match among nodes, and we don't
+	   need to require all nodes to have some flags set */
+	ls->ls_exflags = (flags & ~(DLM_LSFL_TIMEWARN | DLM_LSFL_FS |
+				    DLM_LSFL_NEWEXCL));
+
+	size = dlm_config.ci_rsbtbl_size;
+	ls->ls_rsbtbl_size = size;
+
+	ls->ls_rsbtbl = vmalloc(sizeof(struct dlm_rsbtable) * size);
+	if (!ls->ls_rsbtbl)
+		goto out_lsfree;
+	for (i = 0; i < size; i++) {
+		ls->ls_rsbtbl[i].keep.rb_node = NULL;
+		ls->ls_rsbtbl[i].toss.rb_node = NULL;
+		spin_lock_init(&ls->ls_rsbtbl[i].lock);
+	}
+
+	spin_lock_init(&ls->ls_remove_spin);
+
+	for (i = 0; i < DLM_REMOVE_NAMES_MAX; i++) {
+		ls->ls_remove_names[i] = kzalloc(DLM_RESNAME_MAXLEN+1,
+						 GFP_KERNEL);
+		if (!ls->ls_remove_names[i])
+			goto out_rsbtbl;
+	}
+
+	idr_init(&ls->ls_lkbidr);
+	spin_lock_init(&ls->ls_lkbidr_spin);
+
+	INIT_LIST_HEAD(&ls->ls_waiters);
+	mutex_init(&ls->ls_waiters_mutex);
+	INIT_LIST_HEAD(&ls->ls_orphans);
+	mutex_init(&ls->ls_orphans_mutex);
+	INIT_LIST_HEAD(&ls->ls_timeout);
+	mutex_init(&ls->ls_timeout_mutex);
+
+	INIT_LIST_HEAD(&ls->ls_new_rsb);
+	spin_lock_init(&ls->ls_new_rsb_spin);
+
+	INIT_LIST_HEAD(&ls->ls_nodes);
+	INIT_LIST_HEAD(&ls->ls_nodes_gone);
+	ls->ls_num_nodes = 0;
+	ls->ls_low_nodeid = 0;
+	ls->ls_total_weight = 0;
+	ls->ls_node_array = NULL;
+
+	memset(&ls->ls_stub_rsb, 0, sizeof(struct dlm_rsb));
+	ls->ls_stub_rsb.res_ls = ls;
+
+	ls->ls_debug_rsb_dentry = NULL;
+	ls->ls_debug_waiters_dentry = NULL;
+
+	init_waitqueue_head(&ls->ls_uevent_wait);
+	ls->ls_uevent_result = 0;
+	init_completion(&ls->ls_members_done);
+	ls->ls_members_result = -1;
+
+	mutex_init(&ls->ls_cb_mutex);
+	INIT_LIST_HEAD(&ls->ls_cb_delay);
+
+	ls->ls_recoverd_task = NULL;
+	mutex_init(&ls->ls_recoverd_active);
+	spin_lock_init(&ls->ls_recover_lock);
+	spin_lock_init(&ls->ls_rcom_spin);
+	get_random_bytes(&ls->ls_rcom_seq, sizeof(uint64_t));
+	ls->ls_recover_status = 0;
+	ls->ls_recover_seq = 0;
+	ls->ls_recover_args = NULL;
+	init_rwsem(&ls->ls_in_recovery);
+	init_rwsem(&ls->ls_recv_active);
+	INIT_LIST_HEAD(&ls->ls_requestqueue);
+	mutex_init(&ls->ls_requestqueue_mutex);
+	mutex_init(&ls->ls_clear_proc_locks);
+
+	ls->ls_recover_buf = kmalloc(dlm_config.ci_buffer_size, GFP_NOFS);
+	if (!ls->ls_recover_buf)
+		goto out_lkbidr;
+
+	ls->ls_slot = 0;
+	ls->ls_num_slots = 0;
+	ls->ls_slots_size = 0;
+	ls->ls_slots = NULL;
+
+	INIT_LIST_HEAD(&ls->ls_recover_list);
+	spin_lock_init(&ls->ls_recover_list_lock);
+	idr_init(&ls->ls_recover_idr);
+	spin_lock_init(&ls->ls_recover_idr_lock);
+	ls->ls_recover_list_count = 0;
+	ls->ls_local_handle = ls;
+	init_waitqueue_head(&ls->ls_wait_general);
+	INIT_LIST_HEAD(&ls->ls_root_list);
+	init_rwsem(&ls->ls_root_sem);
+
+	spin_lock(&lslist_lock);
+	ls->ls_create_count = 1;
+	list_add(&ls->ls_list, &lslist);
+	spin_unlock(&lslist_lock);
+
+	if (flags & DLM_LSFL_FS) {
+		error = dlm_callback_start(ls);
+		if (error) {
+			log_error(ls, "can't start dlm_callback %d", error);
+			goto out_delist;
+		}
+	}
+
+	init_waitqueue_head(&ls->ls_recover_lock_wait);
+
+	/*
+	 * Once started, dlm_recoverd first looks for ls in lslist, then
+	 * initializes ls_in_recovery as locked in "down" mode.  We need
+	 * to wait for the wakeup from dlm_recoverd because in_recovery
+	 * has to start out in down mode.
+	 */
+
+	error = dlm_recoverd_start(ls);
+	if (error) {
+		log_error(ls, "can't start dlm_recoverd %d", error);
+		goto out_callback;
+	}
+
+	wait_event(ls->ls_recover_lock_wait,
+		   test_bit(LSFL_RECOVER_LOCK, &ls->ls_flags));
+
+	ls->ls_kobj.kset = dlm_kset;
+	error = kobject_init_and_add(&ls->ls_kobj, &dlm_ktype, NULL,
+				     "%s", ls->ls_name);
+	if (error)
+		goto out_recoverd;
+	kobject_uevent(&ls->ls_kobj, KOBJ_ADD);
+
+	/* let kobject handle freeing of ls if there's an error */
+	do_unreg = 1;
+
+	/* This uevent triggers dlm_controld in userspace to add us to the
+	   group of nodes that are members of this lockspace (managed by the
+	   cluster infrastructure.)  Once it's done that, it tells us who the
+	   current lockspace members are (via configfs) and then tells the
+	   lockspace to start running (via sysfs) in dlm_ls_start(). */
+
+	error = do_uevent(ls, 1);
+	if (error)
+		goto out_recoverd;
+
+	wait_for_completion(&ls->ls_members_done);
+	error = ls->ls_members_result;
+	if (error)
+		goto out_members;
+
+	dlm_create_debug_file(ls);
+
+	log_rinfo(ls, "join complete");
+	*lockspace = ls;
+	return 0;
+
+ out_members:
+	do_uevent(ls, 0);
+	dlm_clear_members(ls);
+	kfree(ls->ls_node_array);
+ out_recoverd:
+	dlm_recoverd_stop(ls);
+ out_callback:
+	dlm_callback_stop(ls);
+ out_delist:
+	spin_lock(&lslist_lock);
+	list_del(&ls->ls_list);
+	spin_unlock(&lslist_lock);
+	idr_destroy(&ls->ls_recover_idr);
+	kfree(ls->ls_recover_buf);
+ out_lkbidr:
+	idr_destroy(&ls->ls_lkbidr);
+	for (i = 0; i < DLM_REMOVE_NAMES_MAX; i++) {
+		if (ls->ls_remove_names[i])
+			kfree(ls->ls_remove_names[i]);
+	}
+ out_rsbtbl:
+	vfree(ls->ls_rsbtbl);
+ out_lsfree:
+	if (do_unreg)
+		kobject_put(&ls->ls_kobj);
+	else
+		kfree(ls);
+ out:
+	module_put(THIS_MODULE);
+	return error;
+}
+
+int dlm_new_lockspace(const char *name, const char *cluster,
+		      uint32_t flags, int lvblen,
+		      const struct dlm_lockspace_ops *ops, void *ops_arg,
+		      int *ops_result, dlm_lockspace_t **lockspace)
+{
+	int error = 0;
+
+	mutex_lock(&ls_lock);
+	if (!ls_count)
+		error = threads_start();
+	if (error)
+		goto out;
+
+	error = new_lockspace(name, cluster, flags, lvblen, ops, ops_arg,
+			      ops_result, lockspace);
+	if (!error)
+		ls_count++;
+	if (error > 0)
+		error = 0;
+	if (!ls_count)
+		threads_stop();
+ out:
+	mutex_unlock(&ls_lock);
+	return error;
+}
+
+static int lkb_idr_is_local(int id, void *p, void *data)
+{
+	struct dlm_lkb *lkb = p;
+
+	return lkb->lkb_nodeid == 0 && lkb->lkb_grmode != DLM_LOCK_IV;
+}
+
+static int lkb_idr_is_any(int id, void *p, void *data)
+{
+	return 1;
+}
+
+static int lkb_idr_free(int id, void *p, void *data)
+{
+	struct dlm_lkb *lkb = p;
+
+	if (lkb->lkb_lvbptr && lkb->lkb_flags & DLM_IFL_MSTCPY)
+		dlm_free_lvb(lkb->lkb_lvbptr);
+
+	dlm_free_lkb(lkb);
+	return 0;
+}
+
+/* NOTE: We check the lkbidr here rather than the resource table.
+   This is because there may be LKBs queued as ASTs that have been unlinked
+   from their RSBs and are pending deletion once the AST has been delivered */
+
+static int lockspace_busy(struct dlm_ls *ls, int force)
+{
+	int rv;
+
+	spin_lock(&ls->ls_lkbidr_spin);
+	if (force == 0) {
+		rv = idr_for_each(&ls->ls_lkbidr, lkb_idr_is_any, ls);
+	} else if (force == 1) {
+		rv = idr_for_each(&ls->ls_lkbidr, lkb_idr_is_local, ls);
+	} else {
+		rv = 0;
+	}
+	spin_unlock(&ls->ls_lkbidr_spin);
+	return rv;
+}
+
+static int release_lockspace(struct dlm_ls *ls, int force)
+{
+	struct dlm_rsb *rsb;
+	struct rb_node *n;
+	int i, busy, rv;
+
+	busy = lockspace_busy(ls, force);
+
+	spin_lock(&lslist_lock);
+	if (ls->ls_create_count == 1) {
+		if (busy) {
+			rv = -EBUSY;
+		} else {
+			/* remove_lockspace takes ls off lslist */
+			ls->ls_create_count = 0;
+			rv = 0;
+		}
+	} else if (ls->ls_create_count > 1) {
+		rv = --ls->ls_create_count;
+	} else {
+		rv = -EINVAL;
+	}
+	spin_unlock(&lslist_lock);
+
+	if (rv) {
+		log_debug(ls, "release_lockspace no remove %d", rv);
+		return rv;
+	}
+
+	dlm_device_deregister(ls);
+
+	if (force < 3 && dlm_user_daemon_available())
+		do_uevent(ls, 0);
+
+	dlm_recoverd_stop(ls);
+
+	dlm_callback_stop(ls);
+
+	remove_lockspace(ls);
+
+	dlm_delete_debug_file(ls);
+
+	kfree(ls->ls_recover_buf);
+
+	/*
+	 * Free all lkb's in idr
+	 */
+
+	idr_for_each(&ls->ls_lkbidr, lkb_idr_free, ls);
+	idr_destroy(&ls->ls_lkbidr);
+
+	/*
+	 * Free all rsb's on rsbtbl[] lists
+	 */
+
+	for (i = 0; i < ls->ls_rsbtbl_size; i++) {
+		while ((n = rb_first(&ls->ls_rsbtbl[i].keep))) {
+			rsb = rb_entry(n, struct dlm_rsb, res_hashnode);
+			rb_erase(n, &ls->ls_rsbtbl[i].keep);
+			dlm_free_rsb(rsb);
+		}
+
+		while ((n = rb_first(&ls->ls_rsbtbl[i].toss))) {
+			rsb = rb_entry(n, struct dlm_rsb, res_hashnode);
+			rb_erase(n, &ls->ls_rsbtbl[i].toss);
+			dlm_free_rsb(rsb);
+		}
+	}
+
+	vfree(ls->ls_rsbtbl);
+
+	for (i = 0; i < DLM_REMOVE_NAMES_MAX; i++)
+		kfree(ls->ls_remove_names[i]);
+
+	while (!list_empty(&ls->ls_new_rsb)) {
+		rsb = list_first_entry(&ls->ls_new_rsb, struct dlm_rsb,
+				       res_hashchain);
+		list_del(&rsb->res_hashchain);
+		dlm_free_rsb(rsb);
+	}
+
+	/*
+	 * Free structures on any other lists
+	 */
+
+	dlm_purge_requestqueue(ls);
+	kfree(ls->ls_recover_args);
+	dlm_clear_members(ls);
+	dlm_clear_members_gone(ls);
+	kfree(ls->ls_node_array);
+	log_rinfo(ls, "release_lockspace final free");
+	kobject_put(&ls->ls_kobj);
+	/* The ls structure will be freed when the kobject is done with */
+
+	module_put(THIS_MODULE);
+	return 0;
+}
+
+/*
+ * Called when a system has released all its locks and is not going to use the
+ * lockspace any longer.  We free everything we're managing for this lockspace.
+ * Remaining nodes will go through the recovery process as if we'd died.  The
+ * lockspace must continue to function as usual, participating in recoveries,
+ * until this returns.
+ *
+ * Force has 4 possible values:
+ * 0 - don't destroy locksapce if it has any LKBs
+ * 1 - destroy lockspace if it has remote LKBs but not if it has local LKBs
+ * 2 - destroy lockspace regardless of LKBs
+ * 3 - destroy lockspace as part of a forced shutdown
+ */
+
+int dlm_release_lockspace(void *lockspace, int force)
+{
+	struct dlm_ls *ls;
+	int error;
+
+	ls = dlm_find_lockspace_local(lockspace);
+	if (!ls)
+		return -EINVAL;
+	dlm_put_lockspace(ls);
+
+	mutex_lock(&ls_lock);
+	error = release_lockspace(ls, force);
+	if (!error)
+		ls_count--;
+	if (!ls_count)
+		threads_stop();
+	mutex_unlock(&ls_lock);
+
+	return error;
+}
+
+void dlm_stop_lockspaces(void)
+{
+	struct dlm_ls *ls;
+	int count;
+
+ restart:
+	count = 0;
+	spin_lock(&lslist_lock);
+	list_for_each_entry(ls, &lslist, ls_list) {
+		if (!test_bit(LSFL_RUNNING, &ls->ls_flags)) {
+			count++;
+			continue;
+		}
+		spin_unlock(&lslist_lock);
+		log_error(ls, "no userland control daemon, stopping lockspace");
+		dlm_ls_stop(ls);
+		goto restart;
+	}
+	spin_unlock(&lslist_lock);
+
+	if (count)
+		log_print("dlm user daemon left %d lockspaces", count);
+}
+

fs/dlm/lockspace.h

@@ -0,0 +1,26 @@
+/******************************************************************************
+*******************************************************************************
+**
+**  Copyright (C) Sistina Software, Inc.  1997-2003  All rights reserved.
+**  Copyright (C) 2004-2005 Red Hat, Inc.  All rights reserved.
+**
+**  This copyrighted material is made available to anyone wishing to use,
+**  modify, copy, or redistribute it subject to the terms and conditions
+**  of the GNU General Public License v.2.
+**
+*******************************************************************************
+******************************************************************************/
+
+#ifndef __LOCKSPACE_DOT_H__
+#define __LOCKSPACE_DOT_H__
+
+int dlm_lockspace_init(void);
+void dlm_lockspace_exit(void);
+struct dlm_ls *dlm_find_lockspace_global(uint32_t id);
+struct dlm_ls *dlm_find_lockspace_local(void *id);
+struct dlm_ls *dlm_find_lockspace_device(int minor);
+void dlm_put_lockspace(struct dlm_ls *ls);
+void dlm_stop_lockspaces(void);
+
+#endif				/* __LOCKSPACE_DOT_H__ */
+

fs/dlm/lowcomms.h

@@ -0,0 +1,27 @@
+/******************************************************************************
+*******************************************************************************
+**
+**  Copyright (C) Sistina Software, Inc.  1997-2003  All rights reserved.
+**  Copyright (C) 2004-2009 Red Hat, Inc.  All rights reserved.
+**
+**  This copyrighted material is made available to anyone wishing to use,
+**  modify, copy, or redistribute it subject to the terms and conditions
+**  of the GNU General Public License v.2.
+**
+*******************************************************************************
+******************************************************************************/
+
+#ifndef __LOWCOMMS_DOT_H__
+#define __LOWCOMMS_DOT_H__
+
+int dlm_lowcomms_start(void);
+void dlm_lowcomms_stop(void);
+void dlm_lowcomms_exit(void);
+int dlm_lowcomms_close(int nodeid);
+void *dlm_lowcomms_get_buffer(int nodeid, int len, gfp_t allocation, char **ppc);
+void dlm_lowcomms_commit_buffer(void *mh);
+int dlm_lowcomms_connect_node(int nodeid);
+int dlm_lowcomms_addr(int nodeid, struct sockaddr_storage *addr, int len);
+
+#endif				/* __LOWCOMMS_DOT_H__ */
+

fs/dlm/lvb_table.h

@@ -0,0 +1,18 @@
+/******************************************************************************
+*******************************************************************************
+**
+**  Copyright (C) 2005 Red Hat, Inc.  All rights reserved.
+**
+**  This copyrighted material is made available to anyone wishing to use,
+**  modify, copy, or redistribute it subject to the terms and conditions
+**  of the GNU General Public License v.2.
+**
+*******************************************************************************
+******************************************************************************/
+
+#ifndef __LVB_TABLE_DOT_H__
+#define __LVB_TABLE_DOT_H__
+
+extern const int dlm_lvb_operations[8][8];
+
+#endif

fs/dlm/main.c

@@ -0,0 +1,97 @@
+/******************************************************************************
+*******************************************************************************
+**
+**  Copyright (C) Sistina Software, Inc.  1997-2003  All rights reserved.
+**  Copyright (C) 2004-2007 Red Hat, Inc.  All rights reserved.
+**
+**  This copyrighted material is made available to anyone wishing to use,
+**  modify, copy, or redistribute it subject to the terms and conditions
+**  of the GNU General Public License v.2.
+**
+*******************************************************************************
+******************************************************************************/
+
+#include "dlm_internal.h"
+#include "lockspace.h"
+#include "lock.h"
+#include "user.h"
+#include "memory.h"
+#include "config.h"
+#include "lowcomms.h"
+
+static int __init init_dlm(void)
+{
+	int error;
+
+	error = dlm_memory_init();
+	if (error)
+		goto out;
+
+	error = dlm_lockspace_init();
+	if (error)
+		goto out_mem;
+
+	error = dlm_config_init();
+	if (error)
+		goto out_lockspace;
+
+	error = dlm_register_debugfs();
+	if (error)
+		goto out_config;
+
+	error = dlm_user_init();
+	if (error)
+		goto out_debug;
+
+	error = dlm_netlink_init();
+	if (error)
+		goto out_user;
+
+	error = dlm_plock_init();
+	if (error)
+		goto out_netlink;
+
+	printk("DLM installed\n");
+
+	return 0;
+
+ out_netlink:
+	dlm_netlink_exit();
+ out_user:
+	dlm_user_exit();
+ out_debug:
+	dlm_unregister_debugfs();
+ out_config:
+	dlm_config_exit();
+ out_lockspace:
+	dlm_lockspace_exit();
+ out_mem:
+	dlm_memory_exit();
+ out:
+	return error;
+}
+
+static void __exit exit_dlm(void)
+{
+	dlm_plock_exit();
+	dlm_netlink_exit();
+	dlm_user_exit();
+	dlm_config_exit();
+	dlm_memory_exit();
+	dlm_lockspace_exit();
+	dlm_lowcomms_exit();
+	dlm_unregister_debugfs();
+}
+
+module_init(init_dlm);
+module_exit(exit_dlm);
+
+MODULE_DESCRIPTION("Distributed Lock Manager");
+MODULE_AUTHOR("Red Hat, Inc.");
+MODULE_LICENSE("GPL");
+
+EXPORT_SYMBOL_GPL(dlm_new_lockspace);
+EXPORT_SYMBOL_GPL(dlm_release_lockspace);
+EXPORT_SYMBOL_GPL(dlm_lock);
+EXPORT_SYMBOL_GPL(dlm_unlock);
+

fs/dlm/member.c

@@ -0,0 +1,722 @@
+/******************************************************************************
+*******************************************************************************
+**
+**  Copyright (C) 2005-2011 Red Hat, Inc.  All rights reserved.
+**
+**  This copyrighted material is made available to anyone wishing to use,
+**  modify, copy, or redistribute it subject to the terms and conditions
+**  of the GNU General Public License v.2.
+**
+*******************************************************************************
+******************************************************************************/
+
+#include "dlm_internal.h"
+#include "lockspace.h"
+#include "member.h"
+#include "recoverd.h"
+#include "recover.h"
+#include "rcom.h"
+#include "config.h"
+#include "lowcomms.h"
+
+int dlm_slots_version(struct dlm_header *h)
+{
+	if ((h->h_version & 0x0000FFFF) < DLM_HEADER_SLOTS)
+		return 0;
+	return 1;
+}
+
+void dlm_slot_save(struct dlm_ls *ls, struct dlm_rcom *rc,
+		   struct dlm_member *memb)
+{
+	struct rcom_config *rf = (struct rcom_config *)rc->rc_buf;
+
+	if (!dlm_slots_version(&rc->rc_header))
+		return;
+
+	memb->slot = le16_to_cpu(rf->rf_our_slot);
+	memb->generation = le32_to_cpu(rf->rf_generation);
+}
+
+void dlm_slots_copy_out(struct dlm_ls *ls, struct dlm_rcom *rc)
+{
+	struct dlm_slot *slot;
+	struct rcom_slot *ro;
+	int i;
+
+	ro = (struct rcom_slot *)(rc->rc_buf + sizeof(struct rcom_config));
+
+	/* ls_slots array is sparse, but not rcom_slots */
+
+	for (i = 0; i < ls->ls_slots_size; i++) {
+		slot = &ls->ls_slots[i];
+		if (!slot->nodeid)
+			continue;
+		ro->ro_nodeid = cpu_to_le32(slot->nodeid);
+		ro->ro_slot = cpu_to_le16(slot->slot);
+		ro++;
+	}
+}
+
+#define SLOT_DEBUG_LINE 128
+
+static void log_slots(struct dlm_ls *ls, uint32_t gen, int num_slots,
+		      struct rcom_slot *ro0, struct dlm_slot *array,
+		      int array_size)
+{
+	char line[SLOT_DEBUG_LINE];
+	int len = SLOT_DEBUG_LINE - 1;
+	int pos = 0;
+	int ret, i;
+
+	memset(line, 0, sizeof(line));
+
+	if (array) {
+		for (i = 0; i < array_size; i++) {
+			if (!array[i].nodeid)
+				continue;
+
+			ret = snprintf(line + pos, len - pos, " %d:%d",
+				       array[i].slot, array[i].nodeid);
+			if (ret >= len - pos)
+				break;
+			pos += ret;
+		}
+	} else if (ro0) {
+		for (i = 0; i < num_slots; i++) {
+			ret = snprintf(line + pos, len - pos, " %d:%d",
+				       ro0[i].ro_slot, ro0[i].ro_nodeid);
+			if (ret >= len - pos)
+				break;
+			pos += ret;
+		}
+	}
+
+	log_rinfo(ls, "generation %u slots %d%s", gen, num_slots, line);
+}
+
+int dlm_slots_copy_in(struct dlm_ls *ls)
+{
+	struct dlm_member *memb;
+	struct dlm_rcom *rc = ls->ls_recover_buf;
+	struct rcom_config *rf = (struct rcom_config *)rc->rc_buf;
+	struct rcom_slot *ro0, *ro;
+	int our_nodeid = dlm_our_nodeid();
+	int i, num_slots;
+	uint32_t gen;
+
+	if (!dlm_slots_version(&rc->rc_header))
+		return -1;
+
+	gen = le32_to_cpu(rf->rf_generation);
+	if (gen <= ls->ls_generation) {
+		log_error(ls, "dlm_slots_copy_in gen %u old %u",
+			  gen, ls->ls_generation);
+	}
+	ls->ls_generation = gen;
+
+	num_slots = le16_to_cpu(rf->rf_num_slots);
+	if (!num_slots)
+		return -1;
+
+	ro0 = (struct rcom_slot *)(rc->rc_buf + sizeof(struct rcom_config));
+
+	for (i = 0, ro = ro0; i < num_slots; i++, ro++) {
+		ro->ro_nodeid = le32_to_cpu(ro->ro_nodeid);
+		ro->ro_slot = le16_to_cpu(ro->ro_slot);
+	}
+
+	log_slots(ls, gen, num_slots, ro0, NULL, 0);
+
+	list_for_each_entry(memb, &ls->ls_nodes, list) {
+		for (i = 0, ro = ro0; i < num_slots; i++, ro++) {
+			if (ro->ro_nodeid != memb->nodeid)
+				continue;
+			memb->slot = ro->ro_slot;
+			memb->slot_prev = memb->slot;
+			break;
+		}
+
+		if (memb->nodeid == our_nodeid) {
+			if (ls->ls_slot && ls->ls_slot != memb->slot) {
+				log_error(ls, "dlm_slots_copy_in our slot "
+					  "changed %d %d", ls->ls_slot,
+					  memb->slot);
+				return -1;
+			}
+
+			if (!ls->ls_slot)
+				ls->ls_slot = memb->slot;
+		}
+
+		if (!memb->slot) {
+			log_error(ls, "dlm_slots_copy_in nodeid %d no slot",
+				   memb->nodeid);
+			return -1;
+		}
+	}
+
+	return 0;
+}
+
+/* for any nodes that do not support slots, we will not have set memb->slot
+   in wait_status_all(), so memb->slot will remain -1, and we will not
+   assign slots or set ls_num_slots here */
+
+int dlm_slots_assign(struct dlm_ls *ls, int *num_slots, int *slots_size,
+		     struct dlm_slot **slots_out, uint32_t *gen_out)
+{
+	struct dlm_member *memb;
+	struct dlm_slot *array;
+	int our_nodeid = dlm_our_nodeid();
+	int array_size, max_slots, i;
+	int need = 0;
+	int max = 0;
+	int num = 0;
+	uint32_t gen = 0;
+
+	/* our own memb struct will have slot -1 gen 0 */
+
+	list_for_each_entry(memb, &ls->ls_nodes, list) {
+		if (memb->nodeid == our_nodeid) {
+			memb->slot = ls->ls_slot;
+			memb->generation = ls->ls_generation;
+			break;
+		}
+	}
+
+	list_for_each_entry(memb, &ls->ls_nodes, list) {
+		if (memb->generation > gen)
+			gen = memb->generation;
+
+		/* node doesn't support slots */
+
+		if (memb->slot == -1)
+			return -1;
+
+		/* node needs a slot assigned */
+
+		if (!memb->slot)
+			need++;
+
+		/* node has a slot assigned */
+
+		num++;
+
+		if (!max || max < memb->slot)
+			max = memb->slot;
+
+		/* sanity check, once slot is assigned it shouldn't change */
+
+		if (memb->slot_prev && memb->slot && memb->slot_prev != memb->slot) {
+			log_error(ls, "nodeid %d slot changed %d %d",
+				  memb->nodeid, memb->slot_prev, memb->slot);
+			return -1;
+		}
+		memb->slot_prev = memb->slot;
+	}
+
+	array_size = max + need;
+
+	array = kzalloc(array_size * sizeof(struct dlm_slot), GFP_NOFS);
+	if (!array)
+		return -ENOMEM;
+
+	num = 0;
+
+	/* fill in slots (offsets) that are used */
+
+	list_for_each_entry(memb, &ls->ls_nodes, list) {
+		if (!memb->slot)
+			continue;
+
+		if (memb->slot > array_size) {
+			log_error(ls, "invalid slot number %d", memb->slot);
+			kfree(array);
+			return -1;
+		}
+
+		array[memb->slot - 1].nodeid = memb->nodeid;
+		array[memb->slot - 1].slot = memb->slot;
+		num++;
+	}
+
+	/* assign new slots from unused offsets */
+
+	list_for_each_entry(memb, &ls->ls_nodes, list) {
+		if (memb->slot)
+			continue;
+
+		for (i = 0; i < array_size; i++) {
+			if (array[i].nodeid)
+				continue;
+
+			memb->slot = i + 1;
+			memb->slot_prev = memb->slot;
+			array[i].nodeid = memb->nodeid;
+			array[i].slot = memb->slot;
+			num++;
+
+			if (!ls->ls_slot && memb->nodeid == our_nodeid)
+				ls->ls_slot = memb->slot;
+			break;
+		}
+
+		if (!memb->slot) {
+			log_error(ls, "no free slot found");
+			kfree(array);
+			return -1;
+		}
+	}
+
+	gen++;
+
+	log_slots(ls, gen, num, NULL, array, array_size);
+
+	max_slots = (dlm_config.ci_buffer_size - sizeof(struct dlm_rcom) -
+		     sizeof(struct rcom_config)) / sizeof(struct rcom_slot);
+
+	if (num > max_slots) {
+		log_error(ls, "num_slots %d exceeds max_slots %d",
+			  num, max_slots);
+		kfree(array);
+		return -1;
+	}
+
+	*gen_out = gen;
+	*slots_out = array;
+	*slots_size = array_size;
+	*num_slots = num;
+	return 0;
+}
+
+static void add_ordered_member(struct dlm_ls *ls, struct dlm_member *new)
+{
+	struct dlm_member *memb = NULL;
+	struct list_head *tmp;
+	struct list_head *newlist = &new->list;
+	struct list_head *head = &ls->ls_nodes;
+
+	list_for_each(tmp, head) {
+		memb = list_entry(tmp, struct dlm_member, list);
+		if (new->nodeid < memb->nodeid)
+			break;
+	}
+
+	if (!memb)
+		list_add_tail(newlist, head);
+	else {
+		/* FIXME: can use list macro here */
+		newlist->prev = tmp->prev;
+		newlist->next = tmp;
+		tmp->prev->next = newlist;
+		tmp->prev = newlist;
+	}
+}
+
+static int dlm_add_member(struct dlm_ls *ls, struct dlm_config_node *node)
+{
+	struct dlm_member *memb;
+	int error;
+
+	memb = kzalloc(sizeof(struct dlm_member), GFP_NOFS);
+	if (!memb)
+		return -ENOMEM;
+
+	error = dlm_lowcomms_connect_node(node->nodeid);
+	if (error < 0) {
+		kfree(memb);
+		return error;
+	}
+
+	memb->nodeid = node->nodeid;
+	memb->weight = node->weight;
+	memb->comm_seq = node->comm_seq;
+	add_ordered_member(ls, memb);
+	ls->ls_num_nodes++;
+	return 0;
+}
+
+static struct dlm_member *find_memb(struct list_head *head, int nodeid)
+{
+	struct dlm_member *memb;
+
+	list_for_each_entry(memb, head, list) {
+		if (memb->nodeid == nodeid)
+			return memb;
+	}
+	return NULL;
+}
+
+int dlm_is_member(struct dlm_ls *ls, int nodeid)
+{
+	if (find_memb(&ls->ls_nodes, nodeid))
+		return 1;
+	return 0;
+}
+
+int dlm_is_removed(struct dlm_ls *ls, int nodeid)
+{
+	if (find_memb(&ls->ls_nodes_gone, nodeid))
+		return 1;
+	return 0;
+}
+
+static void clear_memb_list(struct list_head *head)
+{
+	struct dlm_member *memb;
+
+	while (!list_empty(head)) {
+		memb = list_entry(head->next, struct dlm_member, list);
+		list_del(&memb->list);
+		kfree(memb);
+	}
+}
+
+void dlm_clear_members(struct dlm_ls *ls)
+{
+	clear_memb_list(&ls->ls_nodes);
+	ls->ls_num_nodes = 0;
+}
+
+void dlm_clear_members_gone(struct dlm_ls *ls)
+{
+	clear_memb_list(&ls->ls_nodes_gone);
+}
+
+static void make_member_array(struct dlm_ls *ls)
+{
+	struct dlm_member *memb;
+	int i, w, x = 0, total = 0, all_zero = 0, *array;
+
+	kfree(ls->ls_node_array);
+	ls->ls_node_array = NULL;
+
+	list_for_each_entry(memb, &ls->ls_nodes, list) {
+		if (memb->weight)
+			total += memb->weight;
+	}
+
+	/* all nodes revert to weight of 1 if all have weight 0 */
+
+	if (!total) {
+		total = ls->ls_num_nodes;
+		all_zero = 1;
+	}
+
+	ls->ls_total_weight = total;
+
+	array = kmalloc(sizeof(int) * total, GFP_NOFS);
+	if (!array)
+		return;
+
+	list_for_each_entry(memb, &ls->ls_nodes, list) {
+		if (!all_zero && !memb->weight)
+			continue;
+
+		if (all_zero)
+			w = 1;
+		else
+			w = memb->weight;
+
+		DLM_ASSERT(x < total, printk("total %d x %d\n", total, x););
+
+		for (i = 0; i < w; i++)
+			array[x++] = memb->nodeid;
+	}
+
+	ls->ls_node_array = array;
+}
+
+/* send a status request to all members just to establish comms connections */
+
+static int ping_members(struct dlm_ls *ls)
+{
+	struct dlm_member *memb;
+	int error = 0;
+
+	list_for_each_entry(memb, &ls->ls_nodes, list) {
+		error = dlm_recovery_stopped(ls);
+		if (error)
+			break;
+		error = dlm_rcom_status(ls, memb->nodeid, 0);
+		if (error)
+			break;
+	}
+	if (error)
+		log_rinfo(ls, "ping_members aborted %d last nodeid %d",
+			  error, ls->ls_recover_nodeid);
+	return error;
+}
+
+static void dlm_lsop_recover_prep(struct dlm_ls *ls)
+{
+	if (!ls->ls_ops || !ls->ls_ops->recover_prep)
+		return;
+	ls->ls_ops->recover_prep(ls->ls_ops_arg);
+}
+
+static void dlm_lsop_recover_slot(struct dlm_ls *ls, struct dlm_member *memb)
+{
+	struct dlm_slot slot;
+	uint32_t seq;
+	int error;
+
+	if (!ls->ls_ops || !ls->ls_ops->recover_slot)
+		return;
+
+	/* if there is no comms connection with this node
+	   or the present comms connection is newer
+	   than the one when this member was added, then
+	   we consider the node to have failed (versus
+	   being removed due to dlm_release_lockspace) */
+
+	error = dlm_comm_seq(memb->nodeid, &seq);
+
+	if (!error && seq == memb->comm_seq)
+		return;
+
+	slot.nodeid = memb->nodeid;
+	slot.slot = memb->slot;
+
+	ls->ls_ops->recover_slot(ls->ls_ops_arg, &slot);
+}
+
+void dlm_lsop_recover_done(struct dlm_ls *ls)
+{
+	struct dlm_member *memb;
+	struct dlm_slot *slots;
+	int i, num;
+
+	if (!ls->ls_ops || !ls->ls_ops->recover_done)
+		return;
+
+	num = ls->ls_num_nodes;
+
+	slots = kzalloc(num * sizeof(struct dlm_slot), GFP_KERNEL);
+	if (!slots)
+		return;
+
+	i = 0;
+	list_for_each_entry(memb, &ls->ls_nodes, list) {
+		if (i == num) {
+			log_error(ls, "dlm_lsop_recover_done bad num %d", num);
+			goto out;
+		}
+		slots[i].nodeid = memb->nodeid;
+		slots[i].slot = memb->slot;
+		i++;
+	}
+
+	ls->ls_ops->recover_done(ls->ls_ops_arg, slots, num,
+				 ls->ls_slot, ls->ls_generation);
+ out:
+	kfree(slots);
+}
+
+static struct dlm_config_node *find_config_node(struct dlm_recover *rv,
+						int nodeid)
+{
+	int i;
+
+	for (i = 0; i < rv->nodes_count; i++) {
+		if (rv->nodes[i].nodeid == nodeid)
+			return &rv->nodes[i];
+	}
+	return NULL;
+}
+
+int dlm_recover_members(struct dlm_ls *ls, struct dlm_recover *rv, int *neg_out)
+{
+	struct dlm_member *memb, *safe;
+	struct dlm_config_node *node;
+	int i, error, neg = 0, low = -1;
+
+	/* previously removed members that we've not finished removing need to
+	   count as a negative change so the "neg" recovery steps will happen */
+
+	list_for_each_entry(memb, &ls->ls_nodes_gone, list) {
+		log_rinfo(ls, "prev removed member %d", memb->nodeid);
+		neg++;
+	}
+
+	/* move departed members from ls_nodes to ls_nodes_gone */
+
+	list_for_each_entry_safe(memb, safe, &ls->ls_nodes, list) {
+		node = find_config_node(rv, memb->nodeid);
+		if (node && !node->new)
+			continue;
+
+		if (!node) {
+			log_rinfo(ls, "remove member %d", memb->nodeid);
+		} else {
+			/* removed and re-added */
+			log_rinfo(ls, "remove member %d comm_seq %u %u",
+				  memb->nodeid, memb->comm_seq, node->comm_seq);
+		}
+
+		neg++;
+		list_move(&memb->list, &ls->ls_nodes_gone);
+		ls->ls_num_nodes--;
+		dlm_lsop_recover_slot(ls, memb);
+	}
+
+	/* add new members to ls_nodes */
+
+	for (i = 0; i < rv->nodes_count; i++) {
+		node = &rv->nodes[i];
+		if (dlm_is_member(ls, node->nodeid))
+			continue;
+		dlm_add_member(ls, node);
+		log_rinfo(ls, "add member %d", node->nodeid);
+	}
+
+	list_for_each_entry(memb, &ls->ls_nodes, list) {
+		if (low == -1 || memb->nodeid < low)
+			low = memb->nodeid;
+	}
+	ls->ls_low_nodeid = low;
+
+	make_member_array(ls);
+	*neg_out = neg;
+
+	error = ping_members(ls);
+	if (!error || error == -EPROTO) {
+		/* new_lockspace() may be waiting to know if the config
+		   is good or bad */
+		ls->ls_members_result = error;
+		complete(&ls->ls_members_done);
+	}
+
+	log_rinfo(ls, "dlm_recover_members %d nodes", ls->ls_num_nodes);
+	return error;
+}
+
+/* Userspace guarantees that dlm_ls_stop() has completed on all nodes before
+   dlm_ls_start() is called on any of them to start the new recovery. */
+
+int dlm_ls_stop(struct dlm_ls *ls)
+{
+	int new;
+
+	/*
+	 * Prevent dlm_recv from being in the middle of something when we do
+	 * the stop.  This includes ensuring dlm_recv isn't processing a
+	 * recovery message (rcom), while dlm_recoverd is aborting and
+	 * resetting things from an in-progress recovery.  i.e. we want
+	 * dlm_recoverd to abort its recovery without worrying about dlm_recv
+	 * processing an rcom at the same time.  Stopping dlm_recv also makes
+	 * it easy for dlm_receive_message() to check locking stopped and add a
+	 * message to the requestqueue without races.
+	 */
+
+	down_write(&ls->ls_recv_active);
+
+	/*
+	 * Abort any recovery that's in progress (see RECOVER_STOP,
+	 * dlm_recovery_stopped()) and tell any other threads running in the
+	 * dlm to quit any processing (see RUNNING, dlm_locking_stopped()).
+	 */
+
+	spin_lock(&ls->ls_recover_lock);
+	set_bit(LSFL_RECOVER_STOP, &ls->ls_flags);
+	new = test_and_clear_bit(LSFL_RUNNING, &ls->ls_flags);
+	ls->ls_recover_seq++;
+	spin_unlock(&ls->ls_recover_lock);
+
+	/*
+	 * Let dlm_recv run again, now any normal messages will be saved on the
+	 * requestqueue for later.
+	 */
+
+	up_write(&ls->ls_recv_active);
+
+	/*
+	 * This in_recovery lock does two things:
+	 * 1) Keeps this function from returning until all threads are out
+	 *    of locking routines and locking is truly stopped.
+	 * 2) Keeps any new requests from being processed until it's unlocked
+	 *    when recovery is complete.
+	 */
+
+	if (new) {
+		set_bit(LSFL_RECOVER_DOWN, &ls->ls_flags);
+		wake_up_process(ls->ls_recoverd_task);
+		wait_event(ls->ls_recover_lock_wait,
+			   test_bit(LSFL_RECOVER_LOCK, &ls->ls_flags));
+	}
+
+	/*
+	 * The recoverd suspend/resume makes sure that dlm_recoverd (if
+	 * running) has noticed RECOVER_STOP above and quit processing the
+	 * previous recovery.
+	 */
+
+	dlm_recoverd_suspend(ls);
+
+	spin_lock(&ls->ls_recover_lock);
+	kfree(ls->ls_slots);
+	ls->ls_slots = NULL;
+	ls->ls_num_slots = 0;
+	ls->ls_slots_size = 0;
+	ls->ls_recover_status = 0;
+	spin_unlock(&ls->ls_recover_lock);
+
+	dlm_recoverd_resume(ls);
+
+	if (!ls->ls_recover_begin)
+		ls->ls_recover_begin = jiffies;
+
+	dlm_lsop_recover_prep(ls);
+	return 0;
+}
+
+int dlm_ls_start(struct dlm_ls *ls)
+{
+	struct dlm_recover *rv = NULL, *rv_old;
+	struct dlm_config_node *nodes;
+	int error, count;
+
+	rv = kzalloc(sizeof(struct dlm_recover), GFP_NOFS);
+	if (!rv)
+		return -ENOMEM;
+
+	error = dlm_config_nodes(ls->ls_name, &nodes, &count);
+	if (error < 0)
+		goto fail;
+
+	spin_lock(&ls->ls_recover_lock);
+
+	/* the lockspace needs to be stopped before it can be started */
+
+	if (!dlm_locking_stopped(ls)) {
+		spin_unlock(&ls->ls_recover_lock);
+		log_error(ls, "start ignored: lockspace running");
+		error = -EINVAL;
+		goto fail;
+	}
+
+	rv->nodes = nodes;
+	rv->nodes_count = count;
+	rv->seq = ++ls->ls_recover_seq;
+	rv_old = ls->ls_recover_args;
+	ls->ls_recover_args = rv;
+	spin_unlock(&ls->ls_recover_lock);
+
+	if (rv_old) {
+		log_error(ls, "unused recovery %llx %d",
+			  (unsigned long long)rv_old->seq, rv_old->nodes_count);
+		kfree(rv_old->nodes);
+		kfree(rv_old);
+	}
+
+	set_bit(LSFL_RECOVER_WORK, &ls->ls_flags);
+	wake_up_process(ls->ls_recoverd_task);
+	return 0;
+
+ fail:
+	kfree(rv);
+	kfree(nodes);
+	return error;
+}
+

fs/dlm/member.h

@@ -0,0 +1,33 @@
+/******************************************************************************
+*******************************************************************************
+**
+**  Copyright (C) 2005-2011 Red Hat, Inc.  All rights reserved.
+**
+**  This copyrighted material is made available to anyone wishing to use,
+**  modify, copy, or redistribute it subject to the terms and conditions
+**  of the GNU General Public License v.2.
+**
+*******************************************************************************
+******************************************************************************/
+
+#ifndef __MEMBER_DOT_H__
+#define __MEMBER_DOT_H__
+
+int dlm_ls_stop(struct dlm_ls *ls);
+int dlm_ls_start(struct dlm_ls *ls);
+void dlm_clear_members(struct dlm_ls *ls);
+void dlm_clear_members_gone(struct dlm_ls *ls);
+int dlm_recover_members(struct dlm_ls *ls, struct dlm_recover *rv,int *neg_out);
+int dlm_is_removed(struct dlm_ls *ls, int nodeid);
+int dlm_is_member(struct dlm_ls *ls, int nodeid);
+int dlm_slots_version(struct dlm_header *h);
+void dlm_slot_save(struct dlm_ls *ls, struct dlm_rcom *rc,
+		   struct dlm_member *memb);
+void dlm_slots_copy_out(struct dlm_ls *ls, struct dlm_rcom *rc);
+int dlm_slots_copy_in(struct dlm_ls *ls);
+int dlm_slots_assign(struct dlm_ls *ls, int *num_slots, int *slots_size,
+		     struct dlm_slot **slots_out, uint32_t *gen_out);
+void dlm_lsop_recover_done(struct dlm_ls *ls);
+
+#endif                          /* __MEMBER_DOT_H__ */
+

fs/dlm/memory.c

@@ -0,0 +1,96 @@
+/******************************************************************************
+*******************************************************************************
+**
+**  Copyright (C) Sistina Software, Inc.  1997-2003  All rights reserved.
+**  Copyright (C) 2004-2007 Red Hat, Inc.  All rights reserved.
+**
+**  This copyrighted material is made available to anyone wishing to use,
+**  modify, copy, or redistribute it subject to the terms and conditions
+**  of the GNU General Public License v.2.
+**
+*******************************************************************************
+******************************************************************************/
+
+#include "dlm_internal.h"
+#include "config.h"
+#include "memory.h"
+
+static struct kmem_cache *lkb_cache;
+static struct kmem_cache *rsb_cache;
+
+
+int __init dlm_memory_init(void)
+{
+	lkb_cache = kmem_cache_create("dlm_lkb", sizeof(struct dlm_lkb),
+				__alignof__(struct dlm_lkb), 0, NULL);
+	if (!lkb_cache)
+		return -ENOMEM;
+
+	rsb_cache = kmem_cache_create("dlm_rsb", sizeof(struct dlm_rsb),
+				__alignof__(struct dlm_rsb), 0, NULL);
+	if (!rsb_cache) {
+		kmem_cache_destroy(lkb_cache);
+		return -ENOMEM;
+	}
+
+	return 0;
+}
+
+void dlm_memory_exit(void)
+{
+	if (lkb_cache)
+		kmem_cache_destroy(lkb_cache);
+	if (rsb_cache)
+		kmem_cache_destroy(rsb_cache);
+}
+
+char *dlm_allocate_lvb(struct dlm_ls *ls)
+{
+	char *p;
+
+	p = kzalloc(ls->ls_lvblen, GFP_NOFS);
+	return p;
+}
+
+void dlm_free_lvb(char *p)
+{
+	kfree(p);
+}
+
+struct dlm_rsb *dlm_allocate_rsb(struct dlm_ls *ls)
+{
+	struct dlm_rsb *r;
+
+	r = kmem_cache_zalloc(rsb_cache, GFP_NOFS);
+	return r;
+}
+
+void dlm_free_rsb(struct dlm_rsb *r)
+{
+	if (r->res_lvbptr)
+		dlm_free_lvb(r->res_lvbptr);
+	kmem_cache_free(rsb_cache, r);
+}
+
+struct dlm_lkb *dlm_allocate_lkb(struct dlm_ls *ls)
+{
+	struct dlm_lkb *lkb;
+
+	lkb = kmem_cache_zalloc(lkb_cache, GFP_NOFS);
+	return lkb;
+}
+
+void dlm_free_lkb(struct dlm_lkb *lkb)
+{
+	if (lkb->lkb_flags & DLM_IFL_USER) {
+		struct dlm_user_args *ua;
+		ua = lkb->lkb_ua;
+		if (ua) {
+			if (ua->lksb.sb_lvbptr)
+				kfree(ua->lksb.sb_lvbptr);
+			kfree(ua);
+		}
+	}
+	kmem_cache_free(lkb_cache, lkb);
+}
+

fs/dlm/memory.h

@@ -0,0 +1,27 @@
+/******************************************************************************
+*******************************************************************************
+**
+**  Copyright (C) Sistina Software, Inc.  1997-2003  All rights reserved.
+**  Copyright (C) 2004-2007 Red Hat, Inc.  All rights reserved.
+**
+**  This copyrighted material is made available to anyone wishing to use,
+**  modify, copy, or redistribute it subject to the terms and conditions
+**  of the GNU General Public License v.2.
+**
+*******************************************************************************
+******************************************************************************/
+
+#ifndef __MEMORY_DOT_H__
+#define __MEMORY_DOT_H__
+
+int dlm_memory_init(void);
+void dlm_memory_exit(void);
+struct dlm_rsb *dlm_allocate_rsb(struct dlm_ls *ls);
+void dlm_free_rsb(struct dlm_rsb *r);
+struct dlm_lkb *dlm_allocate_lkb(struct dlm_ls *ls);
+void dlm_free_lkb(struct dlm_lkb *l);
+char *dlm_allocate_lvb(struct dlm_ls *ls);
+void dlm_free_lvb(char *l);
+
+#endif		/* __MEMORY_DOT_H__ */
+

fs/dlm/midcomms.c

@@ -0,0 +1,137 @@
+/******************************************************************************
+*******************************************************************************
+**
+**  Copyright (C) Sistina Software, Inc.  1997-2003  All rights reserved.
+**  Copyright (C) 2004-2008 Red Hat, Inc.  All rights reserved.
+**
+**  This copyrighted material is made available to anyone wishing to use,
+**  modify, copy, or redistribute it subject to the terms and conditions
+**  of the GNU General Public License v.2.
+**
+*******************************************************************************
+******************************************************************************/
+
+/*
+ * midcomms.c
+ *
+ * This is the appallingly named "mid-level" comms layer.
+ *
+ * Its purpose is to take packets from the "real" comms layer,
+ * split them up into packets and pass them to the interested
+ * part of the locking mechanism.
+ *
+ * It also takes messages from the locking layer, formats them
+ * into packets and sends them to the comms layer.
+ */
+
+#include "dlm_internal.h"
+#include "lowcomms.h"
+#include "config.h"
+#include "lock.h"
+#include "midcomms.h"
+
+
+static void copy_from_cb(void *dst, const void *base, unsigned offset,
+			 unsigned len, unsigned limit)
+{
+	unsigned copy = len;
+
+	if ((copy + offset) > limit)
+		copy = limit - offset;
+	memcpy(dst, base + offset, copy);
+	len -= copy;
+	if (len)
+		memcpy(dst + copy, base, len);
+}
+
+/*
+ * Called from the low-level comms layer to process a buffer of
+ * commands.
+ *
+ * Only complete messages are processed here, any "spare" bytes from
+ * the end of a buffer are saved and tacked onto the front of the next
+ * message that comes in. I doubt this will happen very often but we
+ * need to be able to cope with it and I don't want the task to be waiting
+ * for packets to come in when there is useful work to be done.
+ */
+
+int dlm_process_incoming_buffer(int nodeid, const void *base,
+				unsigned offset, unsigned len, unsigned limit)
+{
+	union {
+		unsigned char __buf[DLM_INBUF_LEN];
+		/* this is to force proper alignment on some arches */
+		union dlm_packet p;
+	} __tmp;
+	union dlm_packet *p = &__tmp.p;
+	int ret = 0;
+	int err = 0;
+	uint16_t msglen;
+	uint32_t lockspace;
+
+	while (len > sizeof(struct dlm_header)) {
+
+		/* Copy just the header to check the total length.  The
+		   message may wrap around the end of the buffer back to the
+		   start, so we need to use a temp buffer and copy_from_cb. */
+
+		copy_from_cb(p, base, offset, sizeof(struct dlm_header),
+			     limit);
+
+		msglen = le16_to_cpu(p->header.h_length);
+		lockspace = p->header.h_lockspace;
+
+		err = -EINVAL;
+		if (msglen < sizeof(struct dlm_header))
+			break;
+		if (p->header.h_cmd == DLM_MSG) {
+			if (msglen < sizeof(struct dlm_message))
+				break;
+		} else {
+			if (msglen < sizeof(struct dlm_rcom))
+				break;
+		}
+		err = -E2BIG;
+		if (msglen > dlm_config.ci_buffer_size) {
+			log_print("message size %d from %d too big, buf len %d",
+				  msglen, nodeid, len);
+			break;
+		}
+		err = 0;
+
+		/* If only part of the full message is contained in this
+		   buffer, then do nothing and wait for lowcomms to call
+		   us again later with more data.  We return 0 meaning
+		   we've consumed none of the input buffer. */
+
+		if (msglen > len)
+			break;
+
+		/* Allocate a larger temp buffer if the full message won't fit
+		   in the buffer on the stack (which should work for most
+		   ordinary messages). */
+
+		if (msglen > sizeof(__tmp) && p == &__tmp.p) {
+			p = kmalloc(dlm_config.ci_buffer_size, GFP_NOFS);
+			if (p == NULL)
+				return ret;
+		}
+
+		copy_from_cb(p, base, offset, msglen, limit);
+
+		BUG_ON(lockspace != p->header.h_lockspace);
+
+		ret += msglen;
+		offset += msglen;
+		offset &= (limit - 1);
+		len -= msglen;
+
+		dlm_receive_buffer(p, nodeid);
+	}
+
+	if (p != &__tmp.p)
+		kfree(p);
+
+	return err ? err : ret;
+}
+

fs/dlm/midcomms.h

@@ -0,0 +1,21 @@
+/******************************************************************************
+*******************************************************************************
+**
+**  Copyright (C) Sistina Software, Inc.  1997-2003  All rights reserved.
+**  Copyright (C) 2004-2005 Red Hat, Inc.  All rights reserved.
+**
+**  This copyrighted material is made available to anyone wishing to use,
+**  modify, copy, or redistribute it subject to the terms and conditions
+**  of the GNU General Public License v.2.
+**
+*******************************************************************************
+******************************************************************************/
+
+#ifndef __MIDCOMMS_DOT_H__
+#define __MIDCOMMS_DOT_H__
+
+int dlm_process_incoming_buffer(int nodeid, const void *base, unsigned offset,
+				unsigned len, unsigned limit);
+
+#endif				/* __MIDCOMMS_DOT_H__ */
+

fs/dlm/netlink.c

@@ -0,0 +1,141 @@
+/*
+ * Copyright (C) 2007 Red Hat, Inc.  All rights reserved.
+ *
+ * This copyrighted material is made available to anyone wishing to use,
+ * modify, copy, or redistribute it subject to the terms and conditions
+ * of the GNU General Public License v.2.
+ */
+
+#include <net/genetlink.h>
+#include <linux/dlm.h>
+#include <linux/dlm_netlink.h>
+#include <linux/gfp.h>
+
+#include "dlm_internal.h"
+
+static uint32_t dlm_nl_seqnum;
+static uint32_t listener_nlportid;
+
+static struct genl_family family = {
+	.id		= GENL_ID_GENERATE,
+	.name		= DLM_GENL_NAME,
+	.version	= DLM_GENL_VERSION,
+};
+
+static int prepare_data(u8 cmd, struct sk_buff **skbp, size_t size)
+{
+	struct sk_buff *skb;
+	void *data;
+
+	skb = genlmsg_new(size, GFP_NOFS);
+	if (!skb)
+		return -ENOMEM;
+
+	/* add the message headers */
+	data = genlmsg_put(skb, 0, dlm_nl_seqnum++, &family, 0, cmd);
+	if (!data) {
+		nlmsg_free(skb);
+		return -EINVAL;
+	}
+
+	*skbp = skb;
+	return 0;
+}
+
+static struct dlm_lock_data *mk_data(struct sk_buff *skb)
+{
+	struct nlattr *ret;
+
+	ret = nla_reserve(skb, DLM_TYPE_LOCK, sizeof(struct dlm_lock_data));
+	if (!ret)
+		return NULL;
+	return nla_data(ret);
+}
+
+static int send_data(struct sk_buff *skb)
+{
+	struct genlmsghdr *genlhdr = nlmsg_data((struct nlmsghdr *)skb->data);
+	void *data = genlmsg_data(genlhdr);
+	int rv;
+
+	rv = genlmsg_end(skb, data);
+	if (rv < 0) {
+		nlmsg_free(skb);
+		return rv;
+	}
+
+	return genlmsg_unicast(&init_net, skb, listener_nlportid);
+}
+
+static int user_cmd(struct sk_buff *skb, struct genl_info *info)
+{
+	listener_nlportid = info->snd_portid;
+	printk("user_cmd nlpid %u\n", listener_nlportid);
+	return 0;
+}
+
+static struct genl_ops dlm_nl_ops[] = {
+	{
+		.cmd	= DLM_CMD_HELLO,
+		.doit	= user_cmd,
+	},
+};
+
+int __init dlm_netlink_init(void)
+{
+	return genl_register_family_with_ops(&family, dlm_nl_ops);
+}
+
+void dlm_netlink_exit(void)
+{
+	genl_unregister_family(&family);
+}
+
+static void fill_data(struct dlm_lock_data *data, struct dlm_lkb *lkb)
+{
+	struct dlm_rsb *r = lkb->lkb_resource;
+
+	memset(data, 0, sizeof(struct dlm_lock_data));
+
+	data->version = DLM_LOCK_DATA_VERSION;
+	data->nodeid = lkb->lkb_nodeid;
+	data->ownpid = lkb->lkb_ownpid;
+	data->id = lkb->lkb_id;
+	data->remid = lkb->lkb_remid;
+	data->status = lkb->lkb_status;
+	data->grmode = lkb->lkb_grmode;
+	data->rqmode = lkb->lkb_rqmode;
+	if (lkb->lkb_ua)
+		data->xid = lkb->lkb_ua->xid;
+	if (r) {
+		data->lockspace_id = r->res_ls->ls_global_id;
+		data->resource_namelen = r->res_length;
+		memcpy(data->resource_name, r->res_name, r->res_length);
+	}
+}
+
+void dlm_timeout_warn(struct dlm_lkb *lkb)
+{
+	struct sk_buff *uninitialized_var(send_skb);
+	struct dlm_lock_data *data;
+	size_t size;
+	int rv;
+
+	size = nla_total_size(sizeof(struct dlm_lock_data)) +
+	       nla_total_size(0); /* why this? */
+
+	rv = prepare_data(DLM_CMD_TIMEOUT, &send_skb, size);
+	if (rv < 0)
+		return;
+
+	data = mk_data(send_skb);
+	if (!data) {
+		nlmsg_free(send_skb);
+		return;
+	}
+
+	fill_data(data, lkb);
+
+	send_data(send_skb);
+}
+

fs/dlm/plock.c

@@ -0,0 +1,515 @@
+/*
+ * Copyright (C) 2005-2008 Red Hat, Inc.  All rights reserved.
+ *
+ * This copyrighted material is made available to anyone wishing to use,
+ * modify, copy, or redistribute it subject to the terms and conditions
+ * of the GNU General Public License version 2.
+ */
+
+#include <linux/fs.h>
+#include <linux/miscdevice.h>
+#include <linux/poll.h>
+#include <linux/dlm.h>
+#include <linux/dlm_plock.h>
+#include <linux/slab.h>
+
+#include "dlm_internal.h"
+#include "lockspace.h"
+
+static spinlock_t ops_lock;
+static struct list_head send_list;
+static struct list_head recv_list;
+static wait_queue_head_t send_wq;
+static wait_queue_head_t recv_wq;
+
+struct plock_op {
+	struct list_head list;
+	int done;
+	struct dlm_plock_info info;
+};
+
+struct plock_xop {
+	struct plock_op xop;
+	int (*callback)(struct file_lock *fl, int result);
+	void *fl;
+	void *file;
+	struct file_lock flc;
+};
+
+
+static inline void set_version(struct dlm_plock_info *info)
+{
+	info->version[0] = DLM_PLOCK_VERSION_MAJOR;
+	info->version[1] = DLM_PLOCK_VERSION_MINOR;
+	info->version[2] = DLM_PLOCK_VERSION_PATCH;
+}
+
+static int check_version(struct dlm_plock_info *info)
+{
+	if ((DLM_PLOCK_VERSION_MAJOR != info->version[0]) ||
+	    (DLM_PLOCK_VERSION_MINOR < info->version[1])) {
+		log_print("plock device version mismatch: "
+			  "kernel (%u.%u.%u), user (%u.%u.%u)",
+			  DLM_PLOCK_VERSION_MAJOR,
+			  DLM_PLOCK_VERSION_MINOR,
+			  DLM_PLOCK_VERSION_PATCH,
+			  info->version[0],
+			  info->version[1],
+			  info->version[2]);
+		return -EINVAL;
+	}
+	return 0;
+}
+
+static void send_op(struct plock_op *op)
+{
+	set_version(&op->info);
+	INIT_LIST_HEAD(&op->list);
+	spin_lock(&ops_lock);
+	list_add_tail(&op->list, &send_list);
+	spin_unlock(&ops_lock);
+	wake_up(&send_wq);
+}
+
+/* If a process was killed while waiting for the only plock on a file,
+   locks_remove_posix will not see any lock on the file so it won't
+   send an unlock-close to us to pass on to userspace to clean up the
+   abandoned waiter.  So, we have to insert the unlock-close when the
+   lock call is interrupted. */
+
+static void do_unlock_close(struct dlm_ls *ls, u64 number,
+			    struct file *file, struct file_lock *fl)
+{
+	struct plock_op *op;
+
+	op = kzalloc(sizeof(*op), GFP_NOFS);
+	if (!op)
+		return;
+
+	op->info.optype		= DLM_PLOCK_OP_UNLOCK;
+	op->info.pid		= fl->fl_pid;
+	op->info.fsid		= ls->ls_global_id;
+	op->info.number		= number;
+	op->info.start		= 0;
+	op->info.end		= OFFSET_MAX;
+	if (fl->fl_lmops && fl->fl_lmops->lm_grant)
+		op->info.owner	= (__u64) fl->fl_pid;
+	else
+		op->info.owner	= (__u64)(long) fl->fl_owner;
+
+	op->info.flags |= DLM_PLOCK_FL_CLOSE;
+	send_op(op);
+}
+
+int dlm_posix_lock(dlm_lockspace_t *lockspace, u64 number, struct file *file,
+		   int cmd, struct file_lock *fl)
+{
+	struct dlm_ls *ls;
+	struct plock_op *op;
+	struct plock_xop *xop;
+	int rv;
+
+	ls = dlm_find_lockspace_local(lockspace);
+	if (!ls)
+		return -EINVAL;
+
+	xop = kzalloc(sizeof(*xop), GFP_NOFS);
+	if (!xop) {
+		rv = -ENOMEM;
+		goto out;
+	}
+
+	op = &xop->xop;
+	op->info.optype		= DLM_PLOCK_OP_LOCK;
+	op->info.pid		= fl->fl_pid;
+	op->info.ex		= (fl->fl_type == F_WRLCK);
+	op->info.wait		= IS_SETLKW(cmd);
+	op->info.fsid		= ls->ls_global_id;
+	op->info.number		= number;
+	op->info.start		= fl->fl_start;
+	op->info.end		= fl->fl_end;
+	if (fl->fl_lmops && fl->fl_lmops->lm_grant) {
+		/* fl_owner is lockd which doesn't distinguish
+		   processes on the nfs client */
+		op->info.owner	= (__u64) fl->fl_pid;
+		xop->callback	= fl->fl_lmops->lm_grant;
+		locks_init_lock(&xop->flc);
+		locks_copy_lock(&xop->flc, fl);
+		xop->fl		= fl;
+		xop->file	= file;
+	} else {
+		op->info.owner	= (__u64)(long) fl->fl_owner;
+		xop->callback	= NULL;
+	}
+
+	send_op(op);
+
+	if (xop->callback == NULL) {
+		rv = wait_event_killable(recv_wq, (op->done != 0));
+		if (rv == -ERESTARTSYS) {
+			log_debug(ls, "dlm_posix_lock: wait killed %llx",
+				  (unsigned long long)number);
+			spin_lock(&ops_lock);
+			list_del(&op->list);
+			spin_unlock(&ops_lock);
+			kfree(xop);
+			do_unlock_close(ls, number, file, fl);
+			goto out;
+		}
+	} else {
+		rv = FILE_LOCK_DEFERRED;
+		goto out;
+	}
+
+	spin_lock(&ops_lock);
+	if (!list_empty(&op->list)) {
+		log_error(ls, "dlm_posix_lock: op on list %llx",
+			  (unsigned long long)number);
+		list_del(&op->list);
+	}
+	spin_unlock(&ops_lock);
+
+	rv = op->info.rv;
+
+	if (!rv) {
+		if (posix_lock_file_wait(file, fl) < 0)
+			log_error(ls, "dlm_posix_lock: vfs lock error %llx",
+				  (unsigned long long)number);
+	}
+
+	kfree(xop);
+out:
+	dlm_put_lockspace(ls);
+	return rv;
+}
+EXPORT_SYMBOL_GPL(dlm_posix_lock);
+
+/* Returns failure iff a successful lock operation should be canceled */
+static int dlm_plock_callback(struct plock_op *op)
+{
+	struct file *file;
+	struct file_lock *fl;
+	struct file_lock *flc;
+	int (*notify)(struct file_lock *fl, int result) = NULL;
+	struct plock_xop *xop = (struct plock_xop *)op;
+	int rv = 0;
+
+	spin_lock(&ops_lock);
+	if (!list_empty(&op->list)) {
+		log_print("dlm_plock_callback: op on list %llx",
+			  (unsigned long long)op->info.number);
+		list_del(&op->list);
+	}
+	spin_unlock(&ops_lock);
+
+	/* check if the following 2 are still valid or make a copy */
+	file = xop->file;
+	flc = &xop->flc;
+	fl = xop->fl;
+	notify = xop->callback;
+
+	if (op->info.rv) {
+		notify(fl, op->info.rv);
+		goto out;
+	}
+
+	/* got fs lock; bookkeep locally as well: */
+	flc->fl_flags &= ~FL_SLEEP;
+	if (posix_lock_file(file, flc, NULL)) {
+		/*
+		 * This can only happen in the case of kmalloc() failure.
+		 * The filesystem's own lock is the authoritative lock,
+		 * so a failure to get the lock locally is not a disaster.
+		 * As long as the fs cannot reliably cancel locks (especially
+		 * in a low-memory situation), we're better off ignoring
+		 * this failure than trying to recover.
+		 */
+		log_print("dlm_plock_callback: vfs lock error %llx file %p fl %p",
+			  (unsigned long long)op->info.number, file, fl);
+	}
+
+	rv = notify(fl, 0);
+	if (rv) {
+		/* XXX: We need to cancel the fs lock here: */
+		log_print("dlm_plock_callback: lock granted after lock request "
+			  "failed; dangling lock!\n");
+		goto out;
+	}
+
+out:
+	kfree(xop);
+	return rv;
+}
+
+int dlm_posix_unlock(dlm_lockspace_t *lockspace, u64 number, struct file *file,
+		     struct file_lock *fl)
+{
+	struct dlm_ls *ls;
+	struct plock_op *op;
+	int rv;
+	unsigned char fl_flags = fl->fl_flags;
+
+	ls = dlm_find_lockspace_local(lockspace);
+	if (!ls)
+		return -EINVAL;
+
+	op = kzalloc(sizeof(*op), GFP_NOFS);
+	if (!op) {
+		rv = -ENOMEM;
+		goto out;
+	}
+
+	/* cause the vfs unlock to return ENOENT if lock is not found */
+	fl->fl_flags |= FL_EXISTS;
+
+	rv = posix_lock_file_wait(file, fl);
+	if (rv == -ENOENT) {
+		rv = 0;
+		goto out_free;
+	}
+	if (rv < 0) {
+		log_error(ls, "dlm_posix_unlock: vfs unlock error %d %llx",
+			  rv, (unsigned long long)number);
+	}
+
+	op->info.optype		= DLM_PLOCK_OP_UNLOCK;
+	op->info.pid		= fl->fl_pid;
+	op->info.fsid		= ls->ls_global_id;
+	op->info.number		= number;
+	op->info.start		= fl->fl_start;
+	op->info.end		= fl->fl_end;
+	if (fl->fl_lmops && fl->fl_lmops->lm_grant)
+		op->info.owner	= (__u64) fl->fl_pid;
+	else
+		op->info.owner	= (__u64)(long) fl->fl_owner;
+
+	if (fl->fl_flags & FL_CLOSE) {
+		op->info.flags |= DLM_PLOCK_FL_CLOSE;
+		send_op(op);
+		rv = 0;
+		goto out;
+	}
+
+	send_op(op);
+	wait_event(recv_wq, (op->done != 0));
+
+	spin_lock(&ops_lock);
+	if (!list_empty(&op->list)) {
+		log_error(ls, "dlm_posix_unlock: op on list %llx",
+			  (unsigned long long)number);
+		list_del(&op->list);
+	}
+	spin_unlock(&ops_lock);
+
+	rv = op->info.rv;
+
+	if (rv == -ENOENT)
+		rv = 0;
+
+out_free:
+	kfree(op);
+out:
+	dlm_put_lockspace(ls);
+	fl->fl_flags = fl_flags;
+	return rv;
+}
+EXPORT_SYMBOL_GPL(dlm_posix_unlock);
+
+int dlm_posix_get(dlm_lockspace_t *lockspace, u64 number, struct file *file,
+		  struct file_lock *fl)
+{
+	struct dlm_ls *ls;
+	struct plock_op *op;
+	int rv;
+
+	ls = dlm_find_lockspace_local(lockspace);
+	if (!ls)
+		return -EINVAL;
+
+	op = kzalloc(sizeof(*op), GFP_NOFS);
+	if (!op) {
+		rv = -ENOMEM;
+		goto out;
+	}
+
+	op->info.optype		= DLM_PLOCK_OP_GET;
+	op->info.pid		= fl->fl_pid;
+	op->info.ex		= (fl->fl_type == F_WRLCK);
+	op->info.fsid		= ls->ls_global_id;
+	op->info.number		= number;
+	op->info.start		= fl->fl_start;
+	op->info.end		= fl->fl_end;
+	if (fl->fl_lmops && fl->fl_lmops->lm_grant)
+		op->info.owner	= (__u64) fl->fl_pid;
+	else
+		op->info.owner	= (__u64)(long) fl->fl_owner;
+
+	send_op(op);
+	wait_event(recv_wq, (op->done != 0));
+
+	spin_lock(&ops_lock);
+	if (!list_empty(&op->list)) {
+		log_error(ls, "dlm_posix_get: op on list %llx",
+			  (unsigned long long)number);
+		list_del(&op->list);
+	}
+	spin_unlock(&ops_lock);
+
+	/* info.rv from userspace is 1 for conflict, 0 for no-conflict,
+	   -ENOENT if there are no locks on the file */
+
+	rv = op->info.rv;
+
+	fl->fl_type = F_UNLCK;
+	if (rv == -ENOENT)
+		rv = 0;
+	else if (rv > 0) {
+		locks_init_lock(fl);
+		fl->fl_type = (op->info.ex) ? F_WRLCK : F_RDLCK;
+		fl->fl_flags = FL_POSIX;
+		fl->fl_pid = op->info.pid;
+		fl->fl_start = op->info.start;
+		fl->fl_end = op->info.end;
+		rv = 0;
+	}
+
+	kfree(op);
+out:
+	dlm_put_lockspace(ls);
+	return rv;
+}
+EXPORT_SYMBOL_GPL(dlm_posix_get);
+
+/* a read copies out one plock request from the send list */
+static ssize_t dev_read(struct file *file, char __user *u, size_t count,
+			loff_t *ppos)
+{
+	struct dlm_plock_info info;
+	struct plock_op *op = NULL;
+
+	if (count < sizeof(info))
+		return -EINVAL;
+
+	spin_lock(&ops_lock);
+	if (!list_empty(&send_list)) {
+		op = list_entry(send_list.next, struct plock_op, list);
+		if (op->info.flags & DLM_PLOCK_FL_CLOSE)
+			list_del(&op->list);
+		else
+			list_move(&op->list, &recv_list);
+		memcpy(&info, &op->info, sizeof(info));
+	}
+	spin_unlock(&ops_lock);
+
+	if (!op)
+		return -EAGAIN;
+
+	/* there is no need to get a reply from userspace for unlocks
+	   that were generated by the vfs cleaning up for a close
+	   (the process did not make an unlock call). */
+
+	if (op->info.flags & DLM_PLOCK_FL_CLOSE)
+		kfree(op);
+
+	if (copy_to_user(u, &info, sizeof(info)))
+		return -EFAULT;
+	return sizeof(info);
+}
+
+/* a write copies in one plock result that should match a plock_op
+   on the recv list */
+static ssize_t dev_write(struct file *file, const char __user *u, size_t count,
+			 loff_t *ppos)
+{
+	struct dlm_plock_info info;
+	struct plock_op *op;
+	int found = 0, do_callback = 0;
+
+	if (count != sizeof(info))
+		return -EINVAL;
+
+	if (copy_from_user(&info, u, sizeof(info)))
+		return -EFAULT;
+
+	if (check_version(&info))
+		return -EINVAL;
+
+	spin_lock(&ops_lock);
+	list_for_each_entry(op, &recv_list, list) {
+		if (op->info.fsid == info.fsid &&
+		    op->info.number == info.number &&
+		    op->info.owner == info.owner) {
+			struct plock_xop *xop = (struct plock_xop *)op;
+			list_del_init(&op->list);
+			memcpy(&op->info, &info, sizeof(info));
+			if (xop->callback)
+				do_callback = 1;
+			else
+				op->done = 1;
+			found = 1;
+			break;
+		}
+	}
+	spin_unlock(&ops_lock);
+
+	if (found) {
+		if (do_callback)
+			dlm_plock_callback(op);
+		else
+			wake_up(&recv_wq);
+	} else
+		log_print("dev_write no op %x %llx", info.fsid,
+			  (unsigned long long)info.number);
+	return count;
+}
+
+static unsigned int dev_poll(struct file *file, poll_table *wait)
+{
+	unsigned int mask = 0;
+
+	poll_wait(file, &send_wq, wait);
+
+	spin_lock(&ops_lock);
+	if (!list_empty(&send_list))
+		mask = POLLIN | POLLRDNORM;
+	spin_unlock(&ops_lock);
+
+	return mask;
+}
+
+static const struct file_operations dev_fops = {
+	.read    = dev_read,
+	.write   = dev_write,
+	.poll    = dev_poll,
+	.owner   = THIS_MODULE,
+	.llseek  = noop_llseek,
+};
+
+static struct miscdevice plock_dev_misc = {
+	.minor = MISC_DYNAMIC_MINOR,
+	.name = DLM_PLOCK_MISC_NAME,
+	.fops = &dev_fops
+};
+
+int dlm_plock_init(void)
+{
+	int rv;
+
+	spin_lock_init(&ops_lock);
+	INIT_LIST_HEAD(&send_list);
+	INIT_LIST_HEAD(&recv_list);
+	init_waitqueue_head(&send_wq);
+	init_waitqueue_head(&recv_wq);
+
+	rv = misc_register(&plock_dev_misc);
+	if (rv)
+		log_print("dlm_plock_init: misc_register failed %d", rv);
+	return rv;
+}
+
+void dlm_plock_exit(void)
+{
+	if (misc_deregister(&plock_dev_misc) < 0)
+		log_print("dlm_plock_exit: misc_deregister failed");
+}
+

fs/dlm/rcom.c

@@ -0,0 +1,656 @@
+/******************************************************************************
+*******************************************************************************
+**
+**  Copyright (C) Sistina Software, Inc.  1997-2003  All rights reserved.
+**  Copyright (C) 2005-2008 Red Hat, Inc.  All rights reserved.
+**
+**  This copyrighted material is made available to anyone wishing to use,
+**  modify, copy, or redistribute it subject to the terms and conditions
+**  of the GNU General Public License v.2.
+**
+*******************************************************************************
+******************************************************************************/
+
+#include "dlm_internal.h"
+#include "lockspace.h"
+#include "member.h"
+#include "lowcomms.h"
+#include "midcomms.h"
+#include "rcom.h"
+#include "recover.h"
+#include "dir.h"
+#include "config.h"
+#include "memory.h"
+#include "lock.h"
+#include "util.h"
+
+static int rcom_response(struct dlm_ls *ls)
+{
+	return test_bit(LSFL_RCOM_READY, &ls->ls_flags);
+}
+
+static int create_rcom(struct dlm_ls *ls, int to_nodeid, int type, int len,
+		       struct dlm_rcom **rc_ret, struct dlm_mhandle **mh_ret)
+{
+	struct dlm_rcom *rc;
+	struct dlm_mhandle *mh;
+	char *mb;
+	int mb_len = sizeof(struct dlm_rcom) + len;
+
+	mh = dlm_lowcomms_get_buffer(to_nodeid, mb_len, GFP_NOFS, &mb);
+	if (!mh) {
+		log_print("create_rcom to %d type %d len %d ENOBUFS",
+			  to_nodeid, type, len);
+		return -ENOBUFS;
+	}
+	memset(mb, 0, mb_len);
+
+	rc = (struct dlm_rcom *) mb;
+
+	rc->rc_header.h_version = (DLM_HEADER_MAJOR | DLM_HEADER_MINOR);
+	rc->rc_header.h_lockspace = ls->ls_global_id;
+	rc->rc_header.h_nodeid = dlm_our_nodeid();
+	rc->rc_header.h_length = mb_len;
+	rc->rc_header.h_cmd = DLM_RCOM;
+
+	rc->rc_type = type;
+
+	spin_lock(&ls->ls_recover_lock);
+	rc->rc_seq = ls->ls_recover_seq;
+	spin_unlock(&ls->ls_recover_lock);
+
+	*mh_ret = mh;
+	*rc_ret = rc;
+	return 0;
+}
+
+static void send_rcom(struct dlm_ls *ls, struct dlm_mhandle *mh,
+		      struct dlm_rcom *rc)
+{
+	dlm_rcom_out(rc);
+	dlm_lowcomms_commit_buffer(mh);
+}
+
+static void set_rcom_status(struct dlm_ls *ls, struct rcom_status *rs,
+			    uint32_t flags)
+{
+	rs->rs_flags = cpu_to_le32(flags);
+}
+
+/* When replying to a status request, a node also sends back its
+   configuration values.  The requesting node then checks that the remote
+   node is configured the same way as itself. */
+
+static void set_rcom_config(struct dlm_ls *ls, struct rcom_config *rf,
+			    uint32_t num_slots)
+{
+	rf->rf_lvblen = cpu_to_le32(ls->ls_lvblen);
+	rf->rf_lsflags = cpu_to_le32(ls->ls_exflags);
+
+	rf->rf_our_slot = cpu_to_le16(ls->ls_slot);
+	rf->rf_num_slots = cpu_to_le16(num_slots);
+	rf->rf_generation =  cpu_to_le32(ls->ls_generation);
+}
+
+static int check_rcom_config(struct dlm_ls *ls, struct dlm_rcom *rc, int nodeid)
+{
+	struct rcom_config *rf = (struct rcom_config *) rc->rc_buf;
+
+	if ((rc->rc_header.h_version & 0xFFFF0000) != DLM_HEADER_MAJOR) {
+		log_error(ls, "version mismatch: %x nodeid %d: %x",
+			  DLM_HEADER_MAJOR | DLM_HEADER_MINOR, nodeid,
+			  rc->rc_header.h_version);
+		return -EPROTO;
+	}
+
+	if (le32_to_cpu(rf->rf_lvblen) != ls->ls_lvblen ||
+	    le32_to_cpu(rf->rf_lsflags) != ls->ls_exflags) {
+		log_error(ls, "config mismatch: %d,%x nodeid %d: %d,%x",
+			  ls->ls_lvblen, ls->ls_exflags, nodeid,
+			  le32_to_cpu(rf->rf_lvblen),
+			  le32_to_cpu(rf->rf_lsflags));
+		return -EPROTO;
+	}
+	return 0;
+}
+
+static void allow_sync_reply(struct dlm_ls *ls, uint64_t *new_seq)
+{
+	spin_lock(&ls->ls_rcom_spin);
+	*new_seq = ++ls->ls_rcom_seq;
+	set_bit(LSFL_RCOM_WAIT, &ls->ls_flags);
+	spin_unlock(&ls->ls_rcom_spin);
+}
+
+static void disallow_sync_reply(struct dlm_ls *ls)
+{
+	spin_lock(&ls->ls_rcom_spin);
+	clear_bit(LSFL_RCOM_WAIT, &ls->ls_flags);
+	clear_bit(LSFL_RCOM_READY, &ls->ls_flags);
+	spin_unlock(&ls->ls_rcom_spin);
+}
+
+/*
+ * low nodeid gathers one slot value at a time from each node.
+ * it sets need_slots=0, and saves rf_our_slot returned from each
+ * rcom_config.
+ *
+ * other nodes gather all slot values at once from the low nodeid.
+ * they set need_slots=1, and ignore the rf_our_slot returned from each
+ * rcom_config.  they use the rf_num_slots returned from the low
+ * node's rcom_config.
+ */
+
+int dlm_rcom_status(struct dlm_ls *ls, int nodeid, uint32_t status_flags)
+{
+	struct dlm_rcom *rc;
+	struct dlm_mhandle *mh;
+	int error = 0;
+
+	ls->ls_recover_nodeid = nodeid;
+
+	if (nodeid == dlm_our_nodeid()) {
+		rc = ls->ls_recover_buf;
+		rc->rc_result = dlm_recover_status(ls);
+		goto out;
+	}
+
+	error = create_rcom(ls, nodeid, DLM_RCOM_STATUS,
+			    sizeof(struct rcom_status), &rc, &mh);
+	if (error)
+		goto out;
+
+	set_rcom_status(ls, (struct rcom_status *)rc->rc_buf, status_flags);
+
+	allow_sync_reply(ls, &rc->rc_id);
+	memset(ls->ls_recover_buf, 0, dlm_config.ci_buffer_size);
+
+	send_rcom(ls, mh, rc);
+
+	error = dlm_wait_function(ls, &rcom_response);
+	disallow_sync_reply(ls);
+	if (error)
+		goto out;
+
+	rc = ls->ls_recover_buf;
+
+	if (rc->rc_result == -ESRCH) {
+		/* we pretend the remote lockspace exists with 0 status */
+		log_debug(ls, "remote node %d not ready", nodeid);
+		rc->rc_result = 0;
+		error = 0;
+	} else {
+		error = check_rcom_config(ls, rc, nodeid);
+	}
+
+	/* the caller looks at rc_result for the remote recovery status */
+ out:
+	return error;
+}
+
+static void receive_rcom_status(struct dlm_ls *ls, struct dlm_rcom *rc_in)
+{
+	struct dlm_rcom *rc;
+	struct dlm_mhandle *mh;
+	struct rcom_status *rs;
+	uint32_t status;
+	int nodeid = rc_in->rc_header.h_nodeid;
+	int len = sizeof(struct rcom_config);
+	int num_slots = 0;
+	int error;
+
+	if (!dlm_slots_version(&rc_in->rc_header)) {
+		status = dlm_recover_status(ls);
+		goto do_create;
+	}
+
+	rs = (struct rcom_status *)rc_in->rc_buf;
+
+	if (!(le32_to_cpu(rs->rs_flags) & DLM_RSF_NEED_SLOTS)) {
+		status = dlm_recover_status(ls);
+		goto do_create;
+	}
+
+	spin_lock(&ls->ls_recover_lock);
+	status = ls->ls_recover_status;
+	num_slots = ls->ls_num_slots;
+	spin_unlock(&ls->ls_recover_lock);
+	len += num_slots * sizeof(struct rcom_slot);
+
+ do_create:
+	error = create_rcom(ls, nodeid, DLM_RCOM_STATUS_REPLY,
+			    len, &rc, &mh);
+	if (error)
+		return;
+
+	rc->rc_id = rc_in->rc_id;
+	rc->rc_seq_reply = rc_in->rc_seq;
+	rc->rc_result = status;
+
+	set_rcom_config(ls, (struct rcom_config *)rc->rc_buf, num_slots);
+
+	if (!num_slots)
+		goto do_send;
+
+	spin_lock(&ls->ls_recover_lock);
+	if (ls->ls_num_slots != num_slots) {
+		spin_unlock(&ls->ls_recover_lock);
+		log_debug(ls, "receive_rcom_status num_slots %d to %d",
+			  num_slots, ls->ls_num_slots);
+		rc->rc_result = 0;
+		set_rcom_config(ls, (struct rcom_config *)rc->rc_buf, 0);
+		goto do_send;
+	}
+
+	dlm_slots_copy_out(ls, rc);
+	spin_unlock(&ls->ls_recover_lock);
+
+ do_send:
+	send_rcom(ls, mh, rc);
+}
+
+static void receive_sync_reply(struct dlm_ls *ls, struct dlm_rcom *rc_in)
+{
+	spin_lock(&ls->ls_rcom_spin);
+	if (!test_bit(LSFL_RCOM_WAIT, &ls->ls_flags) ||
+	    rc_in->rc_id != ls->ls_rcom_seq) {
+		log_debug(ls, "reject reply %d from %d seq %llx expect %llx",
+			  rc_in->rc_type, rc_in->rc_header.h_nodeid,
+			  (unsigned long long)rc_in->rc_id,
+			  (unsigned long long)ls->ls_rcom_seq);
+		goto out;
+	}
+	memcpy(ls->ls_recover_buf, rc_in, rc_in->rc_header.h_length);
+	set_bit(LSFL_RCOM_READY, &ls->ls_flags);
+	clear_bit(LSFL_RCOM_WAIT, &ls->ls_flags);
+	wake_up(&ls->ls_wait_general);
+ out:
+	spin_unlock(&ls->ls_rcom_spin);
+}
+
+int dlm_rcom_names(struct dlm_ls *ls, int nodeid, char *last_name, int last_len)
+{
+	struct dlm_rcom *rc;
+	struct dlm_mhandle *mh;
+	int error = 0;
+
+	ls->ls_recover_nodeid = nodeid;
+
+	error = create_rcom(ls, nodeid, DLM_RCOM_NAMES, last_len, &rc, &mh);
+	if (error)
+		goto out;
+	memcpy(rc->rc_buf, last_name, last_len);
+
+	allow_sync_reply(ls, &rc->rc_id);
+	memset(ls->ls_recover_buf, 0, dlm_config.ci_buffer_size);
+
+	send_rcom(ls, mh, rc);
+
+	error = dlm_wait_function(ls, &rcom_response);
+	disallow_sync_reply(ls);
+ out:
+	return error;
+}
+
+static void receive_rcom_names(struct dlm_ls *ls, struct dlm_rcom *rc_in)
+{
+	struct dlm_rcom *rc;
+	struct dlm_mhandle *mh;
+	int error, inlen, outlen, nodeid;
+
+	nodeid = rc_in->rc_header.h_nodeid;
+	inlen = rc_in->rc_header.h_length - sizeof(struct dlm_rcom);
+	outlen = dlm_config.ci_buffer_size - sizeof(struct dlm_rcom);
+
+	error = create_rcom(ls, nodeid, DLM_RCOM_NAMES_REPLY, outlen, &rc, &mh);
+	if (error)
+		return;
+	rc->rc_id = rc_in->rc_id;
+	rc->rc_seq_reply = rc_in->rc_seq;
+
+	dlm_copy_master_names(ls, rc_in->rc_buf, inlen, rc->rc_buf, outlen,
+			      nodeid);
+	send_rcom(ls, mh, rc);
+}
+
+int dlm_send_rcom_lookup(struct dlm_rsb *r, int dir_nodeid)
+{
+	struct dlm_rcom *rc;
+	struct dlm_mhandle *mh;
+	struct dlm_ls *ls = r->res_ls;
+	int error;
+
+	error = create_rcom(ls, dir_nodeid, DLM_RCOM_LOOKUP, r->res_length,
+			    &rc, &mh);
+	if (error)
+		goto out;
+	memcpy(rc->rc_buf, r->res_name, r->res_length);
+	rc->rc_id = (unsigned long) r->res_id;
+
+	send_rcom(ls, mh, rc);
+ out:
+	return error;
+}
+
+int dlm_send_rcom_lookup_dump(struct dlm_rsb *r, int to_nodeid)
+{
+	struct dlm_rcom *rc;
+	struct dlm_mhandle *mh;
+	struct dlm_ls *ls = r->res_ls;
+	int error;
+
+	error = create_rcom(ls, to_nodeid, DLM_RCOM_LOOKUP, r->res_length,
+			    &rc, &mh);
+	if (error)
+		goto out;
+	memcpy(rc->rc_buf, r->res_name, r->res_length);
+	rc->rc_id = 0xFFFFFFFF;
+
+	send_rcom(ls, mh, rc);
+ out:
+	return error;
+}
+
+static void receive_rcom_lookup(struct dlm_ls *ls, struct dlm_rcom *rc_in)
+{
+	struct dlm_rcom *rc;
+	struct dlm_mhandle *mh;
+	int error, ret_nodeid, nodeid = rc_in->rc_header.h_nodeid;
+	int len = rc_in->rc_header.h_length - sizeof(struct dlm_rcom);
+
+	error = create_rcom(ls, nodeid, DLM_RCOM_LOOKUP_REPLY, 0, &rc, &mh);
+	if (error)
+		return;
+
+	if (rc_in->rc_id == 0xFFFFFFFF) {
+		log_error(ls, "receive_rcom_lookup dump from %d", nodeid);
+		dlm_dump_rsb_name(ls, rc_in->rc_buf, len);
+		return;
+	}
+
+	error = dlm_master_lookup(ls, nodeid, rc_in->rc_buf, len,
+				  DLM_LU_RECOVER_MASTER, &ret_nodeid, NULL);
+	if (error)
+		ret_nodeid = error;
+	rc->rc_result = ret_nodeid;
+	rc->rc_id = rc_in->rc_id;
+	rc->rc_seq_reply = rc_in->rc_seq;
+
+	send_rcom(ls, mh, rc);
+}
+
+static void receive_rcom_lookup_reply(struct dlm_ls *ls, struct dlm_rcom *rc_in)
+{
+	dlm_recover_master_reply(ls, rc_in);
+}
+
+static void pack_rcom_lock(struct dlm_rsb *r, struct dlm_lkb *lkb,
+			   struct rcom_lock *rl)
+{
+	memset(rl, 0, sizeof(*rl));
+
+	rl->rl_ownpid = cpu_to_le32(lkb->lkb_ownpid);
+	rl->rl_lkid = cpu_to_le32(lkb->lkb_id);
+	rl->rl_exflags = cpu_to_le32(lkb->lkb_exflags);
+	rl->rl_flags = cpu_to_le32(lkb->lkb_flags);
+	rl->rl_lvbseq = cpu_to_le32(lkb->lkb_lvbseq);
+	rl->rl_rqmode = lkb->lkb_rqmode;
+	rl->rl_grmode = lkb->lkb_grmode;
+	rl->rl_status = lkb->lkb_status;
+	rl->rl_wait_type = cpu_to_le16(lkb->lkb_wait_type);
+
+	if (lkb->lkb_bastfn)
+		rl->rl_asts |= DLM_CB_BAST;
+	if (lkb->lkb_astfn)
+		rl->rl_asts |= DLM_CB_CAST;
+
+	rl->rl_namelen = cpu_to_le16(r->res_length);
+	memcpy(rl->rl_name, r->res_name, r->res_length);
+
+	/* FIXME: might we have an lvb without DLM_LKF_VALBLK set ?
+	   If so, receive_rcom_lock_args() won't take this copy. */
+
+	if (lkb->lkb_lvbptr)
+		memcpy(rl->rl_lvb, lkb->lkb_lvbptr, r->res_ls->ls_lvblen);
+}
+
+int dlm_send_rcom_lock(struct dlm_rsb *r, struct dlm_lkb *lkb)
+{
+	struct dlm_ls *ls = r->res_ls;
+	struct dlm_rcom *rc;
+	struct dlm_mhandle *mh;
+	struct rcom_lock *rl;
+	int error, len = sizeof(struct rcom_lock);
+
+	if (lkb->lkb_lvbptr)
+		len += ls->ls_lvblen;
+
+	error = create_rcom(ls, r->res_nodeid, DLM_RCOM_LOCK, len, &rc, &mh);
+	if (error)
+		goto out;
+
+	rl = (struct rcom_lock *) rc->rc_buf;
+	pack_rcom_lock(r, lkb, rl);
+	rc->rc_id = (unsigned long) r;
+
+	send_rcom(ls, mh, rc);
+ out:
+	return error;
+}
+
+/* needs at least dlm_rcom + rcom_lock */
+static void receive_rcom_lock(struct dlm_ls *ls, struct dlm_rcom *rc_in)
+{
+	struct dlm_rcom *rc;
+	struct dlm_mhandle *mh;
+	int error, nodeid = rc_in->rc_header.h_nodeid;
+
+	dlm_recover_master_copy(ls, rc_in);
+
+	error = create_rcom(ls, nodeid, DLM_RCOM_LOCK_REPLY,
+			    sizeof(struct rcom_lock), &rc, &mh);
+	if (error)
+		return;
+
+	/* We send back the same rcom_lock struct we received, but
+	   dlm_recover_master_copy() has filled in rl_remid and rl_result */
+
+	memcpy(rc->rc_buf, rc_in->rc_buf, sizeof(struct rcom_lock));
+	rc->rc_id = rc_in->rc_id;
+	rc->rc_seq_reply = rc_in->rc_seq;
+
+	send_rcom(ls, mh, rc);
+}
+
+/* If the lockspace doesn't exist then still send a status message
+   back; it's possible that it just doesn't have its global_id yet. */
+
+int dlm_send_ls_not_ready(int nodeid, struct dlm_rcom *rc_in)
+{
+	struct dlm_rcom *rc;
+	struct rcom_config *rf;
+	struct dlm_mhandle *mh;
+	char *mb;
+	int mb_len = sizeof(struct dlm_rcom) + sizeof(struct rcom_config);
+
+	mh = dlm_lowcomms_get_buffer(nodeid, mb_len, GFP_NOFS, &mb);
+	if (!mh)
+		return -ENOBUFS;
+	memset(mb, 0, mb_len);
+
+	rc = (struct dlm_rcom *) mb;
+
+	rc->rc_header.h_version = (DLM_HEADER_MAJOR | DLM_HEADER_MINOR);
+	rc->rc_header.h_lockspace = rc_in->rc_header.h_lockspace;
+	rc->rc_header.h_nodeid = dlm_our_nodeid();
+	rc->rc_header.h_length = mb_len;
+	rc->rc_header.h_cmd = DLM_RCOM;
+
+	rc->rc_type = DLM_RCOM_STATUS_REPLY;
+	rc->rc_id = rc_in->rc_id;
+	rc->rc_seq_reply = rc_in->rc_seq;
+	rc->rc_result = -ESRCH;
+
+	rf = (struct rcom_config *) rc->rc_buf;
+	rf->rf_lvblen = cpu_to_le32(~0U);
+
+	dlm_rcom_out(rc);
+	dlm_lowcomms_commit_buffer(mh);
+
+	return 0;
+}
+
+/*
+ * Ignore messages for stage Y before we set
+ * recover_status bit for stage X:
+ *
+ * recover_status = 0
+ *
+ * dlm_recover_members()
+ * - send nothing
+ * - recv nothing
+ * - ignore NAMES, NAMES_REPLY
+ * - ignore LOOKUP, LOOKUP_REPLY
+ * - ignore LOCK, LOCK_REPLY
+ *
+ * recover_status |= NODES
+ *
+ * dlm_recover_members_wait()
+ *
+ * dlm_recover_directory()
+ * - send NAMES
+ * - recv NAMES_REPLY
+ * - ignore LOOKUP, LOOKUP_REPLY
+ * - ignore LOCK, LOCK_REPLY
+ *
+ * recover_status |= DIR
+ *
+ * dlm_recover_directory_wait()
+ *
+ * dlm_recover_masters()
+ * - send LOOKUP
+ * - recv LOOKUP_REPLY
+ *
+ * dlm_recover_locks()
+ * - send LOCKS
+ * - recv LOCKS_REPLY
+ *
+ * recover_status |= LOCKS
+ *
+ * dlm_recover_locks_wait()
+ *
+ * recover_status |= DONE
+ */
+
+/* Called by dlm_recv; corresponds to dlm_receive_message() but special
+   recovery-only comms are sent through here. */
+
+void dlm_receive_rcom(struct dlm_ls *ls, struct dlm_rcom *rc, int nodeid)
+{
+	int lock_size = sizeof(struct dlm_rcom) + sizeof(struct rcom_lock);
+	int stop, reply = 0, names = 0, lookup = 0, lock = 0;
+	uint32_t status;
+	uint64_t seq;
+
+	switch (rc->rc_type) {
+	case DLM_RCOM_STATUS_REPLY:
+		reply = 1;
+		break;
+	case DLM_RCOM_NAMES:
+		names = 1;
+		break;
+	case DLM_RCOM_NAMES_REPLY:
+		names = 1;
+		reply = 1;
+		break;
+	case DLM_RCOM_LOOKUP:
+		lookup = 1;
+		break;
+	case DLM_RCOM_LOOKUP_REPLY:
+		lookup = 1;
+		reply = 1;
+		break;
+	case DLM_RCOM_LOCK:
+		lock = 1;
+		break;
+	case DLM_RCOM_LOCK_REPLY:
+		lock = 1;
+		reply = 1;
+		break;
+	};
+
+	spin_lock(&ls->ls_recover_lock);
+	status = ls->ls_recover_status;
+	stop = test_bit(LSFL_RECOVER_STOP, &ls->ls_flags);
+	seq = ls->ls_recover_seq;
+	spin_unlock(&ls->ls_recover_lock);
+
+	if (stop && (rc->rc_type != DLM_RCOM_STATUS))
+		goto ignore;
+
+	if (reply && (rc->rc_seq_reply != seq))
+		goto ignore;
+
+	if (!(status & DLM_RS_NODES) && (names || lookup || lock))
+		goto ignore;
+
+	if (!(status & DLM_RS_DIR) && (lookup || lock))
+		goto ignore;
+
+	switch (rc->rc_type) {
+	case DLM_RCOM_STATUS:
+		receive_rcom_status(ls, rc);
+		break;
+
+	case DLM_RCOM_NAMES:
+		receive_rcom_names(ls, rc);
+		break;
+
+	case DLM_RCOM_LOOKUP:
+		receive_rcom_lookup(ls, rc);
+		break;
+
+	case DLM_RCOM_LOCK:
+		if (rc->rc_header.h_length < lock_size)
+			goto Eshort;
+		receive_rcom_lock(ls, rc);
+		break;
+
+	case DLM_RCOM_STATUS_REPLY:
+		receive_sync_reply(ls, rc);
+		break;
+
+	case DLM_RCOM_NAMES_REPLY:
+		receive_sync_reply(ls, rc);
+		break;
+
+	case DLM_RCOM_LOOKUP_REPLY:
+		receive_rcom_lookup_reply(ls, rc);
+		break;
+
+	case DLM_RCOM_LOCK_REPLY:
+		if (rc->rc_header.h_length < lock_size)
+			goto Eshort;
+		dlm_recover_process_copy(ls, rc);
+		break;
+
+	default:
+		log_error(ls, "receive_rcom bad type %d", rc->rc_type);
+	}
+	return;
+
+ignore:
+	log_limit(ls, "dlm_receive_rcom ignore msg %d "
+		  "from %d %llu %llu recover seq %llu sts %x gen %u",
+		   rc->rc_type,
+		   nodeid,
+		   (unsigned long long)rc->rc_seq,
+		   (unsigned long long)rc->rc_seq_reply,
+		   (unsigned long long)seq,
+		   status, ls->ls_generation);
+	return;
+Eshort:
+	log_error(ls, "recovery message %d from %d is too short",
+		  rc->rc_type, nodeid);
+}
+

fs/dlm/rcom.h

@@ -0,0 +1,26 @@
+/******************************************************************************
+*******************************************************************************
+**
+**  Copyright (C) Sistina Software, Inc.  1997-2003  All rights reserved.
+**  Copyright (C) 2005-2007 Red Hat, Inc.  All rights reserved.
+**
+**  This copyrighted material is made available to anyone wishing to use,
+**  modify, copy, or redistribute it subject to the terms and conditions
+**  of the GNU General Public License v.2.
+**
+*******************************************************************************
+******************************************************************************/
+
+#ifndef __RCOM_DOT_H__
+#define __RCOM_DOT_H__
+
+int dlm_rcom_status(struct dlm_ls *ls, int nodeid, uint32_t status_flags);
+int dlm_rcom_names(struct dlm_ls *ls, int nodeid, char *last_name,int last_len);
+int dlm_send_rcom_lookup(struct dlm_rsb *r, int dir_nodeid);
+int dlm_send_rcom_lookup_dump(struct dlm_rsb *r, int to_nodeid);
+int dlm_send_rcom_lock(struct dlm_rsb *r, struct dlm_lkb *lkb);
+void dlm_receive_rcom(struct dlm_ls *ls, struct dlm_rcom *rc, int nodeid);
+int dlm_send_ls_not_ready(int nodeid, struct dlm_rcom *rc_in);
+
+#endif
+

fs/dlm/recover.c

@@ -0,0 +1,955 @@
+/******************************************************************************
+*******************************************************************************
+**
+**  Copyright (C) Sistina Software, Inc.  1997-2003  All rights reserved.
+**  Copyright (C) 2004-2005 Red Hat, Inc.  All rights reserved.
+**
+**  This copyrighted material is made available to anyone wishing to use,
+**  modify, copy, or redistribute it subject to the terms and conditions
+**  of the GNU General Public License v.2.
+**
+*******************************************************************************
+******************************************************************************/
+
+#include "dlm_internal.h"
+#include "lockspace.h"
+#include "dir.h"
+#include "config.h"
+#include "ast.h"
+#include "memory.h"
+#include "rcom.h"
+#include "lock.h"
+#include "lowcomms.h"
+#include "member.h"
+#include "recover.h"
+
+
+/*
+ * Recovery waiting routines: these functions wait for a particular reply from
+ * a remote node, or for the remote node to report a certain status.  They need
+ * to abort if the lockspace is stopped indicating a node has failed (perhaps
+ * the one being waited for).
+ */
+
+/*
+ * Wait until given function returns non-zero or lockspace is stopped
+ * (LS_RECOVERY_STOP set due to failure of a node in ls_nodes).  When another
+ * function thinks it could have completed the waited-on task, they should wake
+ * up ls_wait_general to get an immediate response rather than waiting for the
+ * timeout.  This uses a timeout so it can check periodically if the wait
+ * should abort due to node failure (which doesn't cause a wake_up).
+ * This should only be called by the dlm_recoverd thread.
+ */
+
+int dlm_wait_function(struct dlm_ls *ls, int (*testfn) (struct dlm_ls *ls))
+{
+	int error = 0;
+	int rv;
+
+	while (1) {
+		rv = wait_event_timeout(ls->ls_wait_general,
+					testfn(ls) || dlm_recovery_stopped(ls),
+					dlm_config.ci_recover_timer * HZ);
+		if (rv)
+			break;
+	}
+
+	if (dlm_recovery_stopped(ls)) {
+		log_debug(ls, "dlm_wait_function aborted");
+		error = -EINTR;
+	}
+	return error;
+}
+
+/*
+ * An efficient way for all nodes to wait for all others to have a certain
+ * status.  The node with the lowest nodeid polls all the others for their
+ * status (wait_status_all) and all the others poll the node with the low id
+ * for its accumulated result (wait_status_low).  When all nodes have set
+ * status flag X, then status flag X_ALL will be set on the low nodeid.
+ */
+
+uint32_t dlm_recover_status(struct dlm_ls *ls)
+{
+	uint32_t status;
+	spin_lock(&ls->ls_recover_lock);
+	status = ls->ls_recover_status;
+	spin_unlock(&ls->ls_recover_lock);
+	return status;
+}
+
+static void _set_recover_status(struct dlm_ls *ls, uint32_t status)
+{
+	ls->ls_recover_status |= status;
+}
+
+void dlm_set_recover_status(struct dlm_ls *ls, uint32_t status)
+{
+	spin_lock(&ls->ls_recover_lock);
+	_set_recover_status(ls, status);
+	spin_unlock(&ls->ls_recover_lock);
+}
+
+static int wait_status_all(struct dlm_ls *ls, uint32_t wait_status,
+			   int save_slots)
+{
+	struct dlm_rcom *rc = ls->ls_recover_buf;
+	struct dlm_member *memb;
+	int error = 0, delay;
+
+	list_for_each_entry(memb, &ls->ls_nodes, list) {
+		delay = 0;
+		for (;;) {
+			if (dlm_recovery_stopped(ls)) {
+				error = -EINTR;
+				goto out;
+			}
+
+			error = dlm_rcom_status(ls, memb->nodeid, 0);
+			if (error)
+				goto out;
+
+			if (save_slots)
+				dlm_slot_save(ls, rc, memb);
+
+			if (rc->rc_result & wait_status)
+				break;
+			if (delay < 1000)
+				delay += 20;
+			msleep(delay);
+		}
+	}
+ out:
+	return error;
+}
+
+static int wait_status_low(struct dlm_ls *ls, uint32_t wait_status,
+			   uint32_t status_flags)
+{
+	struct dlm_rcom *rc = ls->ls_recover_buf;
+	int error = 0, delay = 0, nodeid = ls->ls_low_nodeid;
+
+	for (;;) {
+		if (dlm_recovery_stopped(ls)) {
+			error = -EINTR;
+			goto out;
+		}
+
+		error = dlm_rcom_status(ls, nodeid, status_flags);
+		if (error)
+			break;
+
+		if (rc->rc_result & wait_status)
+			break;
+		if (delay < 1000)
+			delay += 20;
+		msleep(delay);
+	}
+ out:
+	return error;
+}
+
+static int wait_status(struct dlm_ls *ls, uint32_t status)
+{
+	uint32_t status_all = status << 1;
+	int error;
+
+	if (ls->ls_low_nodeid == dlm_our_nodeid()) {
+		error = wait_status_all(ls, status, 0);
+		if (!error)
+			dlm_set_recover_status(ls, status_all);
+	} else
+		error = wait_status_low(ls, status_all, 0);
+
+	return error;
+}
+
+int dlm_recover_members_wait(struct dlm_ls *ls)
+{
+	struct dlm_member *memb;
+	struct dlm_slot *slots;
+	int num_slots, slots_size;
+	int error, rv;
+	uint32_t gen;
+
+	list_for_each_entry(memb, &ls->ls_nodes, list) {
+		memb->slot = -1;
+		memb->generation = 0;
+	}
+
+	if (ls->ls_low_nodeid == dlm_our_nodeid()) {
+		error = wait_status_all(ls, DLM_RS_NODES, 1);
+		if (error)
+			goto out;
+
+		/* slots array is sparse, slots_size may be > num_slots */
+
+		rv = dlm_slots_assign(ls, &num_slots, &slots_size, &slots, &gen);
+		if (!rv) {
+			spin_lock(&ls->ls_recover_lock);
+			_set_recover_status(ls, DLM_RS_NODES_ALL);
+			ls->ls_num_slots = num_slots;
+			ls->ls_slots_size = slots_size;
+			ls->ls_slots = slots;
+			ls->ls_generation = gen;
+			spin_unlock(&ls->ls_recover_lock);
+		} else {
+			dlm_set_recover_status(ls, DLM_RS_NODES_ALL);
+		}
+	} else {
+		error = wait_status_low(ls, DLM_RS_NODES_ALL, DLM_RSF_NEED_SLOTS);
+		if (error)
+			goto out;
+
+		dlm_slots_copy_in(ls);
+	}
+ out:
+	return error;
+}
+
+int dlm_recover_directory_wait(struct dlm_ls *ls)
+{
+	return wait_status(ls, DLM_RS_DIR);
+}
+
+int dlm_recover_locks_wait(struct dlm_ls *ls)
+{
+	return wait_status(ls, DLM_RS_LOCKS);
+}
+
+int dlm_recover_done_wait(struct dlm_ls *ls)
+{
+	return wait_status(ls, DLM_RS_DONE);
+}
+
+/*
+ * The recover_list contains all the rsb's for which we've requested the new
+ * master nodeid.  As replies are returned from the resource directories the
+ * rsb's are removed from the list.  When the list is empty we're done.
+ *
+ * The recover_list is later similarly used for all rsb's for which we've sent
+ * new lkb's and need to receive new corresponding lkid's.
+ *
+ * We use the address of the rsb struct as a simple local identifier for the
+ * rsb so we can match an rcom reply with the rsb it was sent for.
+ */
+
+static int recover_list_empty(struct dlm_ls *ls)
+{
+	int empty;
+
+	spin_lock(&ls->ls_recover_list_lock);
+	empty = list_empty(&ls->ls_recover_list);
+	spin_unlock(&ls->ls_recover_list_lock);
+
+	return empty;
+}
+
+static void recover_list_add(struct dlm_rsb *r)
+{
+	struct dlm_ls *ls = r->res_ls;
+
+	spin_lock(&ls->ls_recover_list_lock);
+	if (list_empty(&r->res_recover_list)) {
+		list_add_tail(&r->res_recover_list, &ls->ls_recover_list);
+		ls->ls_recover_list_count++;
+		dlm_hold_rsb(r);
+	}
+	spin_unlock(&ls->ls_recover_list_lock);
+}
+
+static void recover_list_del(struct dlm_rsb *r)
+{
+	struct dlm_ls *ls = r->res_ls;
+
+	spin_lock(&ls->ls_recover_list_lock);
+	list_del_init(&r->res_recover_list);
+	ls->ls_recover_list_count--;
+	spin_unlock(&ls->ls_recover_list_lock);
+
+	dlm_put_rsb(r);
+}
+
+static void recover_list_clear(struct dlm_ls *ls)
+{
+	struct dlm_rsb *r, *s;
+
+	spin_lock(&ls->ls_recover_list_lock);
+	list_for_each_entry_safe(r, s, &ls->ls_recover_list, res_recover_list) {
+		list_del_init(&r->res_recover_list);
+		r->res_recover_locks_count = 0;
+		dlm_put_rsb(r);
+		ls->ls_recover_list_count--;
+	}
+
+	if (ls->ls_recover_list_count != 0) {
+		log_error(ls, "warning: recover_list_count %d",
+			  ls->ls_recover_list_count);
+		ls->ls_recover_list_count = 0;
+	}
+	spin_unlock(&ls->ls_recover_list_lock);
+}
+
+static int recover_idr_empty(struct dlm_ls *ls)
+{
+	int empty = 1;
+
+	spin_lock(&ls->ls_recover_idr_lock);
+	if (ls->ls_recover_list_count)
+		empty = 0;
+	spin_unlock(&ls->ls_recover_idr_lock);
+
+	return empty;
+}
+
+static int recover_idr_add(struct dlm_rsb *r)
+{
+	struct dlm_ls *ls = r->res_ls;
+	int rv;
+
+	idr_preload(GFP_NOFS);
+	spin_lock(&ls->ls_recover_idr_lock);
+	if (r->res_id) {
+		rv = -1;
+		goto out_unlock;
+	}
+	rv = idr_alloc(&ls->ls_recover_idr, r, 1, 0, GFP_NOWAIT);
+	if (rv < 0)
+		goto out_unlock;
+
+	r->res_id = rv;
+	ls->ls_recover_list_count++;
+	dlm_hold_rsb(r);
+	rv = 0;
+out_unlock:
+	spin_unlock(&ls->ls_recover_idr_lock);
+	idr_preload_end();
+	return rv;
+}
+
+static void recover_idr_del(struct dlm_rsb *r)
+{
+	struct dlm_ls *ls = r->res_ls;
+
+	spin_lock(&ls->ls_recover_idr_lock);
+	idr_remove(&ls->ls_recover_idr, r->res_id);
+	r->res_id = 0;
+	ls->ls_recover_list_count--;
+	spin_unlock(&ls->ls_recover_idr_lock);
+
+	dlm_put_rsb(r);
+}
+
+static struct dlm_rsb *recover_idr_find(struct dlm_ls *ls, uint64_t id)
+{
+	struct dlm_rsb *r;
+
+	spin_lock(&ls->ls_recover_idr_lock);
+	r = idr_find(&ls->ls_recover_idr, (int)id);
+	spin_unlock(&ls->ls_recover_idr_lock);
+	return r;
+}
+
+static void recover_idr_clear(struct dlm_ls *ls)
+{
+	struct dlm_rsb *r;
+	int id;
+
+	spin_lock(&ls->ls_recover_idr_lock);
+
+	idr_for_each_entry(&ls->ls_recover_idr, r, id) {
+		idr_remove(&ls->ls_recover_idr, id);
+		r->res_id = 0;
+		r->res_recover_locks_count = 0;
+		ls->ls_recover_list_count--;
+
+		dlm_put_rsb(r);
+	}
+
+	if (ls->ls_recover_list_count != 0) {
+		log_error(ls, "warning: recover_list_count %d",
+			  ls->ls_recover_list_count);
+		ls->ls_recover_list_count = 0;
+	}
+	spin_unlock(&ls->ls_recover_idr_lock);
+}
+
+
+/* Master recovery: find new master node for rsb's that were
+   mastered on nodes that have been removed.
+
+   dlm_recover_masters
+   recover_master
+   dlm_send_rcom_lookup            ->  receive_rcom_lookup
+                                       dlm_dir_lookup
+   receive_rcom_lookup_reply       <-
+   dlm_recover_master_reply
+   set_new_master
+   set_master_lkbs
+   set_lock_master
+*/
+
+/*
+ * Set the lock master for all LKBs in a lock queue
+ * If we are the new master of the rsb, we may have received new
+ * MSTCPY locks from other nodes already which we need to ignore
+ * when setting the new nodeid.
+ */
+
+static void set_lock_master(struct list_head *queue, int nodeid)
+{
+	struct dlm_lkb *lkb;
+
+	list_for_each_entry(lkb, queue, lkb_statequeue) {
+		if (!(lkb->lkb_flags & DLM_IFL_MSTCPY)) {
+			lkb->lkb_nodeid = nodeid;
+			lkb->lkb_remid = 0;
+		}
+	}
+}
+
+static void set_master_lkbs(struct dlm_rsb *r)
+{
+	set_lock_master(&r->res_grantqueue, r->res_nodeid);
+	set_lock_master(&r->res_convertqueue, r->res_nodeid);
+	set_lock_master(&r->res_waitqueue, r->res_nodeid);
+}
+
+/*
+ * Propagate the new master nodeid to locks
+ * The NEW_MASTER flag tells dlm_recover_locks() which rsb's to consider.
+ * The NEW_MASTER2 flag tells recover_lvb() and recover_grant() which
+ * rsb's to consider.
+ */
+
+static void set_new_master(struct dlm_rsb *r)
+{
+	set_master_lkbs(r);
+	rsb_set_flag(r, RSB_NEW_MASTER);
+	rsb_set_flag(r, RSB_NEW_MASTER2);
+}
+
+/*
+ * We do async lookups on rsb's that need new masters.  The rsb's
+ * waiting for a lookup reply are kept on the recover_list.
+ *
+ * Another node recovering the master may have sent us a rcom lookup,
+ * and our dlm_master_lookup() set it as the new master, along with
+ * NEW_MASTER so that we'll recover it here (this implies dir_nodeid
+ * equals our_nodeid below).
+ */
+
+static int recover_master(struct dlm_rsb *r, unsigned int *count)
+{
+	struct dlm_ls *ls = r->res_ls;
+	int our_nodeid, dir_nodeid;
+	int is_removed = 0;
+	int error;
+
+	if (is_master(r))
+		return 0;
+
+	is_removed = dlm_is_removed(ls, r->res_nodeid);
+
+	if (!is_removed && !rsb_flag(r, RSB_NEW_MASTER))
+		return 0;
+
+	our_nodeid = dlm_our_nodeid();
+	dir_nodeid = dlm_dir_nodeid(r);
+
+	if (dir_nodeid == our_nodeid) {
+		if (is_removed) {
+			r->res_master_nodeid = our_nodeid;
+			r->res_nodeid = 0;
+		}
+
+		/* set master of lkbs to ourself when is_removed, or to
+		   another new master which we set along with NEW_MASTER
+		   in dlm_master_lookup */
+		set_new_master(r);
+		error = 0;
+	} else {
+		recover_idr_add(r);
+		error = dlm_send_rcom_lookup(r, dir_nodeid);
+	}
+
+	(*count)++;
+	return error;
+}
+
+/*
+ * All MSTCPY locks are purged and rebuilt, even if the master stayed the same.
+ * This is necessary because recovery can be started, aborted and restarted,
+ * causing the master nodeid to briefly change during the aborted recovery, and
+ * change back to the original value in the second recovery.  The MSTCPY locks
+ * may or may not have been purged during the aborted recovery.  Another node
+ * with an outstanding request in waiters list and a request reply saved in the
+ * requestqueue, cannot know whether it should ignore the reply and resend the
+ * request, or accept the reply and complete the request.  It must do the
+ * former if the remote node purged MSTCPY locks, and it must do the later if
+ * the remote node did not.  This is solved by always purging MSTCPY locks, in
+ * which case, the request reply would always be ignored and the request
+ * resent.
+ */
+
+static int recover_master_static(struct dlm_rsb *r, unsigned int *count)
+{
+	int dir_nodeid = dlm_dir_nodeid(r);
+	int new_master = dir_nodeid;
+
+	if (dir_nodeid == dlm_our_nodeid())
+		new_master = 0;
+
+	dlm_purge_mstcpy_locks(r);
+	r->res_master_nodeid = dir_nodeid;
+	r->res_nodeid = new_master;
+	set_new_master(r);
+	(*count)++;
+	return 0;
+}
+
+/*
+ * Go through local root resources and for each rsb which has a master which
+ * has departed, get the new master nodeid from the directory.  The dir will
+ * assign mastery to the first node to look up the new master.  That means
+ * we'll discover in this lookup if we're the new master of any rsb's.
+ *
+ * We fire off all the dir lookup requests individually and asynchronously to
+ * the correct dir node.
+ */
+
+int dlm_recover_masters(struct dlm_ls *ls)
+{
+	struct dlm_rsb *r;
+	unsigned int total = 0;
+	unsigned int count = 0;
+	int nodir = dlm_no_directory(ls);
+	int error;
+
+	log_rinfo(ls, "dlm_recover_masters");
+
+	down_read(&ls->ls_root_sem);
+	list_for_each_entry(r, &ls->ls_root_list, res_root_list) {
+		if (dlm_recovery_stopped(ls)) {
+			up_read(&ls->ls_root_sem);
+			error = -EINTR;
+			goto out;
+		}
+
+		lock_rsb(r);
+		if (nodir)
+			error = recover_master_static(r, &count);
+		else
+			error = recover_master(r, &count);
+		unlock_rsb(r);
+		cond_resched();
+		total++;
+
+		if (error) {
+			up_read(&ls->ls_root_sem);
+			goto out;
+		}
+	}
+	up_read(&ls->ls_root_sem);
+
+	log_rinfo(ls, "dlm_recover_masters %u of %u", count, total);
+
+	error = dlm_wait_function(ls, &recover_idr_empty);
+ out:
+	if (error)
+		recover_idr_clear(ls);
+	return error;
+}
+
+int dlm_recover_master_reply(struct dlm_ls *ls, struct dlm_rcom *rc)
+{
+	struct dlm_rsb *r;
+	int ret_nodeid, new_master;
+
+	r = recover_idr_find(ls, rc->rc_id);
+	if (!r) {
+		log_error(ls, "dlm_recover_master_reply no id %llx",
+			  (unsigned long long)rc->rc_id);
+		goto out;
+	}
+
+	ret_nodeid = rc->rc_result;
+
+	if (ret_nodeid == dlm_our_nodeid())
+		new_master = 0;
+	else
+		new_master = ret_nodeid;
+
+	lock_rsb(r);
+	r->res_master_nodeid = ret_nodeid;
+	r->res_nodeid = new_master;
+	set_new_master(r);
+	unlock_rsb(r);
+	recover_idr_del(r);
+
+	if (recover_idr_empty(ls))
+		wake_up(&ls->ls_wait_general);
+ out:
+	return 0;
+}
+
+
+/* Lock recovery: rebuild the process-copy locks we hold on a
+   remastered rsb on the new rsb master.
+
+   dlm_recover_locks
+   recover_locks
+   recover_locks_queue
+   dlm_send_rcom_lock              ->  receive_rcom_lock
+                                       dlm_recover_master_copy
+   receive_rcom_lock_reply         <-
+   dlm_recover_process_copy
+*/
+
+
+/*
+ * keep a count of the number of lkb's we send to the new master; when we get
+ * an equal number of replies then recovery for the rsb is done
+ */
+
+static int recover_locks_queue(struct dlm_rsb *r, struct list_head *head)
+{
+	struct dlm_lkb *lkb;
+	int error = 0;
+
+	list_for_each_entry(lkb, head, lkb_statequeue) {
+	   	error = dlm_send_rcom_lock(r, lkb);
+		if (error)
+			break;
+		r->res_recover_locks_count++;
+	}
+
+	return error;
+}
+
+static int recover_locks(struct dlm_rsb *r)
+{
+	int error = 0;
+
+	lock_rsb(r);
+
+	DLM_ASSERT(!r->res_recover_locks_count, dlm_dump_rsb(r););
+
+	error = recover_locks_queue(r, &r->res_grantqueue);
+	if (error)
+		goto out;
+	error = recover_locks_queue(r, &r->res_convertqueue);
+	if (error)
+		goto out;
+	error = recover_locks_queue(r, &r->res_waitqueue);
+	if (error)
+		goto out;
+
+	if (r->res_recover_locks_count)
+		recover_list_add(r);
+	else
+		rsb_clear_flag(r, RSB_NEW_MASTER);
+ out:
+	unlock_rsb(r);
+	return error;
+}
+
+int dlm_recover_locks(struct dlm_ls *ls)
+{
+	struct dlm_rsb *r;
+	int error, count = 0;
+
+	down_read(&ls->ls_root_sem);
+	list_for_each_entry(r, &ls->ls_root_list, res_root_list) {
+		if (is_master(r)) {
+			rsb_clear_flag(r, RSB_NEW_MASTER);
+			continue;
+		}
+
+		if (!rsb_flag(r, RSB_NEW_MASTER))
+			continue;
+
+		if (dlm_recovery_stopped(ls)) {
+			error = -EINTR;
+			up_read(&ls->ls_root_sem);
+			goto out;
+		}
+
+		error = recover_locks(r);
+		if (error) {
+			up_read(&ls->ls_root_sem);
+			goto out;
+		}
+
+		count += r->res_recover_locks_count;
+	}
+	up_read(&ls->ls_root_sem);
+
+	log_rinfo(ls, "dlm_recover_locks %d out", count);
+
+	error = dlm_wait_function(ls, &recover_list_empty);
+ out:
+	if (error)
+		recover_list_clear(ls);
+	return error;
+}
+
+void dlm_recovered_lock(struct dlm_rsb *r)
+{
+	DLM_ASSERT(rsb_flag(r, RSB_NEW_MASTER), dlm_dump_rsb(r););
+
+	r->res_recover_locks_count--;
+	if (!r->res_recover_locks_count) {
+		rsb_clear_flag(r, RSB_NEW_MASTER);
+		recover_list_del(r);
+	}
+
+	if (recover_list_empty(r->res_ls))
+		wake_up(&r->res_ls->ls_wait_general);
+}
+
+/*
+ * The lvb needs to be recovered on all master rsb's.  This includes setting
+ * the VALNOTVALID flag if necessary, and determining the correct lvb contents
+ * based on the lvb's of the locks held on the rsb.
+ *
+ * RSB_VALNOTVALID is set in two cases:
+ *
+ * 1. we are master, but not new, and we purged an EX/PW lock held by a
+ * failed node (in dlm_recover_purge which set RSB_RECOVER_LVB_INVAL)
+ *
+ * 2. we are a new master, and there are only NL/CR locks left.
+ * (We could probably improve this by only invaliding in this way when
+ * the previous master left uncleanly.  VMS docs mention that.)
+ *
+ * The LVB contents are only considered for changing when this is a new master
+ * of the rsb (NEW_MASTER2).  Then, the rsb's lvb is taken from any lkb with
+ * mode > CR.  If no lkb's exist with mode above CR, the lvb contents are taken
+ * from the lkb with the largest lvb sequence number.
+ */
+
+static void recover_lvb(struct dlm_rsb *r)
+{
+	struct dlm_lkb *lkb, *high_lkb = NULL;
+	uint32_t high_seq = 0;
+	int lock_lvb_exists = 0;
+	int big_lock_exists = 0;
+	int lvblen = r->res_ls->ls_lvblen;
+
+	if (!rsb_flag(r, RSB_NEW_MASTER2) &&
+	    rsb_flag(r, RSB_RECOVER_LVB_INVAL)) {
+		/* case 1 above */
+		rsb_set_flag(r, RSB_VALNOTVALID);
+		return;
+	}
+
+	if (!rsb_flag(r, RSB_NEW_MASTER2))
+		return;
+
+	/* we are the new master, so figure out if VALNOTVALID should
+	   be set, and set the rsb lvb from the best lkb available. */
+
+	list_for_each_entry(lkb, &r->res_grantqueue, lkb_statequeue) {
+		if (!(lkb->lkb_exflags & DLM_LKF_VALBLK))
+			continue;
+
+		lock_lvb_exists = 1;
+
+		if (lkb->lkb_grmode > DLM_LOCK_CR) {
+			big_lock_exists = 1;
+			goto setflag;
+		}
+
+		if (((int)lkb->lkb_lvbseq - (int)high_seq) >= 0) {
+			high_lkb = lkb;
+			high_seq = lkb->lkb_lvbseq;
+		}
+	}
+
+	list_for_each_entry(lkb, &r->res_convertqueue, lkb_statequeue) {
+		if (!(lkb->lkb_exflags & DLM_LKF_VALBLK))
+			continue;
+
+		lock_lvb_exists = 1;
+
+		if (lkb->lkb_grmode > DLM_LOCK_CR) {
+			big_lock_exists = 1;
+			goto setflag;
+		}
+
+		if (((int)lkb->lkb_lvbseq - (int)high_seq) >= 0) {
+			high_lkb = lkb;
+			high_seq = lkb->lkb_lvbseq;
+		}
+	}
+
+ setflag:
+	if (!lock_lvb_exists)
+		goto out;
+
+	/* lvb is invalidated if only NL/CR locks remain */
+	if (!big_lock_exists)
+		rsb_set_flag(r, RSB_VALNOTVALID);
+
+	if (!r->res_lvbptr) {
+		r->res_lvbptr = dlm_allocate_lvb(r->res_ls);
+		if (!r->res_lvbptr)
+			goto out;
+	}
+
+	if (big_lock_exists) {
+		r->res_lvbseq = lkb->lkb_lvbseq;
+		memcpy(r->res_lvbptr, lkb->lkb_lvbptr, lvblen);
+	} else if (high_lkb) {
+		r->res_lvbseq = high_lkb->lkb_lvbseq;
+		memcpy(r->res_lvbptr, high_lkb->lkb_lvbptr, lvblen);
+	} else {
+		r->res_lvbseq = 0;
+		memset(r->res_lvbptr, 0, lvblen);
+	}
+ out:
+	return;
+}
+
+/* All master rsb's flagged RECOVER_CONVERT need to be looked at.  The locks
+   converting PR->CW or CW->PR need to have their lkb_grmode set. */
+
+static void recover_conversion(struct dlm_rsb *r)
+{
+	struct dlm_ls *ls = r->res_ls;
+	struct dlm_lkb *lkb;
+	int grmode = -1;
+
+	list_for_each_entry(lkb, &r->res_grantqueue, lkb_statequeue) {
+		if (lkb->lkb_grmode == DLM_LOCK_PR ||
+		    lkb->lkb_grmode == DLM_LOCK_CW) {
+			grmode = lkb->lkb_grmode;
+			break;
+		}
+	}
+
+	list_for_each_entry(lkb, &r->res_convertqueue, lkb_statequeue) {
+		if (lkb->lkb_grmode != DLM_LOCK_IV)
+			continue;
+		if (grmode == -1) {
+			log_debug(ls, "recover_conversion %x set gr to rq %d",
+				  lkb->lkb_id, lkb->lkb_rqmode);
+			lkb->lkb_grmode = lkb->lkb_rqmode;
+		} else {
+			log_debug(ls, "recover_conversion %x set gr %d",
+				  lkb->lkb_id, grmode);
+			lkb->lkb_grmode = grmode;
+		}
+	}
+}
+
+/* We've become the new master for this rsb and waiting/converting locks may
+   need to be granted in dlm_recover_grant() due to locks that may have
+   existed from a removed node. */
+
+static void recover_grant(struct dlm_rsb *r)
+{
+	if (!list_empty(&r->res_waitqueue) || !list_empty(&r->res_convertqueue))
+		rsb_set_flag(r, RSB_RECOVER_GRANT);
+}
+
+void dlm_recover_rsbs(struct dlm_ls *ls)
+{
+	struct dlm_rsb *r;
+	unsigned int count = 0;
+
+	down_read(&ls->ls_root_sem);
+	list_for_each_entry(r, &ls->ls_root_list, res_root_list) {
+		lock_rsb(r);
+		if (is_master(r)) {
+			if (rsb_flag(r, RSB_RECOVER_CONVERT))
+				recover_conversion(r);
+
+			/* recover lvb before granting locks so the updated
+			   lvb/VALNOTVALID is presented in the completion */
+			recover_lvb(r);
+
+			if (rsb_flag(r, RSB_NEW_MASTER2))
+				recover_grant(r);
+			count++;
+		} else {
+			rsb_clear_flag(r, RSB_VALNOTVALID);
+		}
+		rsb_clear_flag(r, RSB_RECOVER_CONVERT);
+		rsb_clear_flag(r, RSB_RECOVER_LVB_INVAL);
+		rsb_clear_flag(r, RSB_NEW_MASTER2);
+		unlock_rsb(r);
+	}
+	up_read(&ls->ls_root_sem);
+
+	if (count)
+		log_rinfo(ls, "dlm_recover_rsbs %d done", count);
+}
+
+/* Create a single list of all root rsb's to be used during recovery */
+
+int dlm_create_root_list(struct dlm_ls *ls)
+{
+	struct rb_node *n;
+	struct dlm_rsb *r;
+	int i, error = 0;
+
+	down_write(&ls->ls_root_sem);
+	if (!list_empty(&ls->ls_root_list)) {
+		log_error(ls, "root list not empty");
+		error = -EINVAL;
+		goto out;
+	}
+
+	for (i = 0; i < ls->ls_rsbtbl_size; i++) {
+		spin_lock(&ls->ls_rsbtbl[i].lock);
+		for (n = rb_first(&ls->ls_rsbtbl[i].keep); n; n = rb_next(n)) {
+			r = rb_entry(n, struct dlm_rsb, res_hashnode);
+			list_add(&r->res_root_list, &ls->ls_root_list);
+			dlm_hold_rsb(r);
+		}
+
+		if (!RB_EMPTY_ROOT(&ls->ls_rsbtbl[i].toss))
+			log_error(ls, "dlm_create_root_list toss not empty");
+		spin_unlock(&ls->ls_rsbtbl[i].lock);
+	}
+ out:
+	up_write(&ls->ls_root_sem);
+	return error;
+}
+
+void dlm_release_root_list(struct dlm_ls *ls)
+{
+	struct dlm_rsb *r, *safe;
+
+	down_write(&ls->ls_root_sem);
+	list_for_each_entry_safe(r, safe, &ls->ls_root_list, res_root_list) {
+		list_del_init(&r->res_root_list);
+		dlm_put_rsb(r);
+	}
+	up_write(&ls->ls_root_sem);
+}
+
+void dlm_clear_toss(struct dlm_ls *ls)
+{
+	struct rb_node *n, *next;
+	struct dlm_rsb *r;
+	unsigned int count = 0;
+	int i;
+
+	for (i = 0; i < ls->ls_rsbtbl_size; i++) {
+		spin_lock(&ls->ls_rsbtbl[i].lock);
+		for (n = rb_first(&ls->ls_rsbtbl[i].toss); n; n = next) {
+			next = rb_next(n);
+			r = rb_entry(n, struct dlm_rsb, res_hashnode);
+			rb_erase(n, &ls->ls_rsbtbl[i].toss);
+			dlm_free_rsb(r);
+			count++;
+		}
+		spin_unlock(&ls->ls_rsbtbl[i].lock);
+	}
+
+	if (count)
+		log_rinfo(ls, "dlm_clear_toss %u done", count);
+}
+

fs/dlm/recover.h

@@ -0,0 +1,34 @@
+/******************************************************************************
+*******************************************************************************
+**
+**  Copyright (C) Sistina Software, Inc.  1997-2003  All rights reserved.
+**  Copyright (C) 2004-2005 Red Hat, Inc.  All rights reserved.
+**
+**  This copyrighted material is made available to anyone wishing to use,
+**  modify, copy, or redistribute it subject to the terms and conditions
+**  of the GNU General Public License v.2.
+**
+*******************************************************************************
+******************************************************************************/
+
+#ifndef __RECOVER_DOT_H__
+#define __RECOVER_DOT_H__
+
+int dlm_wait_function(struct dlm_ls *ls, int (*testfn) (struct dlm_ls *ls));
+uint32_t dlm_recover_status(struct dlm_ls *ls);
+void dlm_set_recover_status(struct dlm_ls *ls, uint32_t status);
+int dlm_recover_members_wait(struct dlm_ls *ls);
+int dlm_recover_directory_wait(struct dlm_ls *ls);
+int dlm_recover_locks_wait(struct dlm_ls *ls);
+int dlm_recover_done_wait(struct dlm_ls *ls);
+int dlm_recover_masters(struct dlm_ls *ls);
+int dlm_recover_master_reply(struct dlm_ls *ls, struct dlm_rcom *rc);
+int dlm_recover_locks(struct dlm_ls *ls);
+void dlm_recovered_lock(struct dlm_rsb *r);
+int dlm_create_root_list(struct dlm_ls *ls);
+void dlm_release_root_list(struct dlm_ls *ls);
+void dlm_clear_toss(struct dlm_ls *ls);
+void dlm_recover_rsbs(struct dlm_ls *ls);
+
+#endif				/* __RECOVER_DOT_H__ */
+

fs/dlm/recoverd.c

@@ -0,0 +1,342 @@
+/******************************************************************************
+*******************************************************************************
+**
+**  Copyright (C) Sistina Software, Inc.  1997-2003  All rights reserved.
+**  Copyright (C) 2004-2011 Red Hat, Inc.  All rights reserved.
+**
+**  This copyrighted material is made available to anyone wishing to use,
+**  modify, copy, or redistribute it subject to the terms and conditions
+**  of the GNU General Public License v.2.
+**
+*******************************************************************************
+******************************************************************************/
+
+#include "dlm_internal.h"
+#include "lockspace.h"
+#include "member.h"
+#include "dir.h"
+#include "ast.h"
+#include "recover.h"
+#include "lowcomms.h"
+#include "lock.h"
+#include "requestqueue.h"
+#include "recoverd.h"
+
+
+/* If the start for which we're re-enabling locking (seq) has been superseded
+   by a newer stop (ls_recover_seq), we need to leave locking disabled.
+
+   We suspend dlm_recv threads here to avoid the race where dlm_recv a) sees
+   locking stopped and b) adds a message to the requestqueue, but dlm_recoverd
+   enables locking and clears the requestqueue between a and b. */
+
+static int enable_locking(struct dlm_ls *ls, uint64_t seq)
+{
+	int error = -EINTR;
+
+	down_write(&ls->ls_recv_active);
+
+	spin_lock(&ls->ls_recover_lock);
+	if (ls->ls_recover_seq == seq) {
+		set_bit(LSFL_RUNNING, &ls->ls_flags);
+		/* unblocks processes waiting to enter the dlm */
+		up_write(&ls->ls_in_recovery);
+		clear_bit(LSFL_RECOVER_LOCK, &ls->ls_flags);
+		error = 0;
+	}
+	spin_unlock(&ls->ls_recover_lock);
+
+	up_write(&ls->ls_recv_active);
+	return error;
+}
+
+static int ls_recover(struct dlm_ls *ls, struct dlm_recover *rv)
+{
+	unsigned long start;
+	int error, neg = 0;
+
+	log_rinfo(ls, "dlm_recover %llu", (unsigned long long)rv->seq);
+
+	mutex_lock(&ls->ls_recoverd_active);
+
+	dlm_callback_suspend(ls);
+
+	dlm_clear_toss(ls);
+
+	/*
+	 * This list of root rsb's will be the basis of most of the recovery
+	 * routines.
+	 */
+
+	dlm_create_root_list(ls);
+
+	/*
+	 * Add or remove nodes from the lockspace's ls_nodes list.
+	 */
+
+	error = dlm_recover_members(ls, rv, &neg);
+	if (error) {
+		log_rinfo(ls, "dlm_recover_members error %d", error);
+		goto fail;
+	}
+
+	dlm_recover_dir_nodeid(ls);
+
+	ls->ls_recover_dir_sent_res = 0;
+	ls->ls_recover_dir_sent_msg = 0;
+	ls->ls_recover_locks_in = 0;
+
+	dlm_set_recover_status(ls, DLM_RS_NODES);
+
+	error = dlm_recover_members_wait(ls);
+	if (error) {
+		log_rinfo(ls, "dlm_recover_members_wait error %d", error);
+		goto fail;
+	}
+
+	start = jiffies;
+
+	/*
+	 * Rebuild our own share of the directory by collecting from all other
+	 * nodes their master rsb names that hash to us.
+	 */
+
+	error = dlm_recover_directory(ls);
+	if (error) {
+		log_rinfo(ls, "dlm_recover_directory error %d", error);
+		goto fail;
+	}
+
+	dlm_set_recover_status(ls, DLM_RS_DIR);
+
+	error = dlm_recover_directory_wait(ls);
+	if (error) {
+		log_rinfo(ls, "dlm_recover_directory_wait error %d", error);
+		goto fail;
+	}
+
+	log_rinfo(ls, "dlm_recover_directory %u out %u messages",
+		  ls->ls_recover_dir_sent_res, ls->ls_recover_dir_sent_msg);
+
+	/*
+	 * We may have outstanding operations that are waiting for a reply from
+	 * a failed node.  Mark these to be resent after recovery.  Unlock and
+	 * cancel ops can just be completed.
+	 */
+
+	dlm_recover_waiters_pre(ls);
+
+	error = dlm_recovery_stopped(ls);
+	if (error)
+		goto fail;
+
+	if (neg || dlm_no_directory(ls)) {
+		/*
+		 * Clear lkb's for departed nodes.
+		 */
+
+		dlm_recover_purge(ls);
+
+		/*
+		 * Get new master nodeid's for rsb's that were mastered on
+		 * departed nodes.
+		 */
+
+		error = dlm_recover_masters(ls);
+		if (error) {
+			log_rinfo(ls, "dlm_recover_masters error %d", error);
+			goto fail;
+		}
+
+		/*
+		 * Send our locks on remastered rsb's to the new masters.
+		 */
+
+		error = dlm_recover_locks(ls);
+		if (error) {
+			log_rinfo(ls, "dlm_recover_locks error %d", error);
+			goto fail;
+		}
+
+		dlm_set_recover_status(ls, DLM_RS_LOCKS);
+
+		error = dlm_recover_locks_wait(ls);
+		if (error) {
+			log_rinfo(ls, "dlm_recover_locks_wait error %d", error);
+			goto fail;
+		}
+
+		log_rinfo(ls, "dlm_recover_locks %u in",
+			  ls->ls_recover_locks_in);
+
+		/*
+		 * Finalize state in master rsb's now that all locks can be
+		 * checked.  This includes conversion resolution and lvb
+		 * settings.
+		 */
+
+		dlm_recover_rsbs(ls);
+	} else {
+		/*
+		 * Other lockspace members may be going through the "neg" steps
+		 * while also adding us to the lockspace, in which case they'll
+		 * be doing the recover_locks (RS_LOCKS) barrier.
+		 */
+		dlm_set_recover_status(ls, DLM_RS_LOCKS);
+
+		error = dlm_recover_locks_wait(ls);
+		if (error) {
+			log_rinfo(ls, "dlm_recover_locks_wait error %d", error);
+			goto fail;
+		}
+	}
+
+	dlm_release_root_list(ls);
+
+	/*
+	 * Purge directory-related requests that are saved in requestqueue.
+	 * All dir requests from before recovery are invalid now due to the dir
+	 * rebuild and will be resent by the requesting nodes.
+	 */
+
+	dlm_purge_requestqueue(ls);
+
+	dlm_set_recover_status(ls, DLM_RS_DONE);
+
+	error = dlm_recover_done_wait(ls);
+	if (error) {
+		log_rinfo(ls, "dlm_recover_done_wait error %d", error);
+		goto fail;
+	}
+
+	dlm_clear_members_gone(ls);
+
+	dlm_adjust_timeouts(ls);
+
+	dlm_callback_resume(ls);
+
+	error = enable_locking(ls, rv->seq);
+	if (error) {
+		log_rinfo(ls, "enable_locking error %d", error);
+		goto fail;
+	}
+
+	error = dlm_process_requestqueue(ls);
+	if (error) {
+		log_rinfo(ls, "dlm_process_requestqueue error %d", error);
+		goto fail;
+	}
+
+	error = dlm_recover_waiters_post(ls);
+	if (error) {
+		log_rinfo(ls, "dlm_recover_waiters_post error %d", error);
+		goto fail;
+	}
+
+	dlm_recover_grant(ls);
+
+	log_rinfo(ls, "dlm_recover %llu generation %u done: %u ms",
+		  (unsigned long long)rv->seq, ls->ls_generation,
+		  jiffies_to_msecs(jiffies - start));
+	mutex_unlock(&ls->ls_recoverd_active);
+
+	dlm_lsop_recover_done(ls);
+	return 0;
+
+ fail:
+	dlm_release_root_list(ls);
+	log_rinfo(ls, "dlm_recover %llu error %d",
+		  (unsigned long long)rv->seq, error);
+	mutex_unlock(&ls->ls_recoverd_active);
+	return error;
+}
+
+/* The dlm_ls_start() that created the rv we take here may already have been
+   stopped via dlm_ls_stop(); in that case we need to leave the RECOVERY_STOP
+   flag set. */
+
+static void do_ls_recovery(struct dlm_ls *ls)
+{
+	struct dlm_recover *rv = NULL;
+
+	spin_lock(&ls->ls_recover_lock);
+	rv = ls->ls_recover_args;
+	ls->ls_recover_args = NULL;
+	if (rv && ls->ls_recover_seq == rv->seq)
+		clear_bit(LSFL_RECOVER_STOP, &ls->ls_flags);
+	spin_unlock(&ls->ls_recover_lock);
+
+	if (rv) {
+		ls_recover(ls, rv);
+		kfree(rv->nodes);
+		kfree(rv);
+	}
+}
+
+static int dlm_recoverd(void *arg)
+{
+	struct dlm_ls *ls;
+
+	ls = dlm_find_lockspace_local(arg);
+	if (!ls) {
+		log_print("dlm_recoverd: no lockspace %p", arg);
+		return -1;
+	}
+
+	down_write(&ls->ls_in_recovery);
+	set_bit(LSFL_RECOVER_LOCK, &ls->ls_flags);
+	wake_up(&ls->ls_recover_lock_wait);
+
+	while (!kthread_should_stop()) {
+		set_current_state(TASK_INTERRUPTIBLE);
+		if (!test_bit(LSFL_RECOVER_WORK, &ls->ls_flags) &&
+		    !test_bit(LSFL_RECOVER_DOWN, &ls->ls_flags))
+			schedule();
+		set_current_state(TASK_RUNNING);
+
+		if (test_and_clear_bit(LSFL_RECOVER_DOWN, &ls->ls_flags)) {
+			down_write(&ls->ls_in_recovery);
+			set_bit(LSFL_RECOVER_LOCK, &ls->ls_flags);
+			wake_up(&ls->ls_recover_lock_wait);
+		}
+
+		if (test_and_clear_bit(LSFL_RECOVER_WORK, &ls->ls_flags))
+			do_ls_recovery(ls);
+	}
+
+	if (test_bit(LSFL_RECOVER_LOCK, &ls->ls_flags))
+		up_write(&ls->ls_in_recovery);
+
+	dlm_put_lockspace(ls);
+	return 0;
+}
+
+int dlm_recoverd_start(struct dlm_ls *ls)
+{
+	struct task_struct *p;
+	int error = 0;
+
+	p = kthread_run(dlm_recoverd, ls, "dlm_recoverd");
+	if (IS_ERR(p))
+		error = PTR_ERR(p);
+	else
+                ls->ls_recoverd_task = p;
+	return error;
+}
+
+void dlm_recoverd_stop(struct dlm_ls *ls)
+{
+	kthread_stop(ls->ls_recoverd_task);
+}
+
+void dlm_recoverd_suspend(struct dlm_ls *ls)
+{
+	wake_up(&ls->ls_wait_general);
+	mutex_lock(&ls->ls_recoverd_active);
+}
+
+void dlm_recoverd_resume(struct dlm_ls *ls)
+{
+	mutex_unlock(&ls->ls_recoverd_active);
+}
+

fs/dlm/recoverd.h

@@ -0,0 +1,23 @@
+/******************************************************************************
+*******************************************************************************
+**
+**  Copyright (C) Sistina Software, Inc.  1997-2003  All rights reserved.
+**  Copyright (C) 2004-2005 Red Hat, Inc.  All rights reserved.
+**
+**  This copyrighted material is made available to anyone wishing to use,
+**  modify, copy, or redistribute it subject to the terms and conditions
+**  of the GNU General Public License v.2.
+**
+*******************************************************************************
+******************************************************************************/
+
+#ifndef __RECOVERD_DOT_H__
+#define __RECOVERD_DOT_H__
+
+void dlm_recoverd_stop(struct dlm_ls *ls);
+int dlm_recoverd_start(struct dlm_ls *ls);
+void dlm_recoverd_suspend(struct dlm_ls *ls);
+void dlm_recoverd_resume(struct dlm_ls *ls);
+
+#endif				/* __RECOVERD_DOT_H__ */
+

fs/dlm/requestqueue.c

@@ -0,0 +1,171 @@
+/******************************************************************************
+*******************************************************************************
+**
+**  Copyright (C) 2005-2007 Red Hat, Inc.  All rights reserved.
+**
+**  This copyrighted material is made available to anyone wishing to use,
+**  modify, copy, or redistribute it subject to the terms and conditions
+**  of the GNU General Public License v.2.
+**
+*******************************************************************************
+******************************************************************************/
+
+#include "dlm_internal.h"
+#include "member.h"
+#include "lock.h"
+#include "dir.h"
+#include "config.h"
+#include "requestqueue.h"
+
+struct rq_entry {
+	struct list_head list;
+	uint32_t recover_seq;
+	int nodeid;
+	struct dlm_message request;
+};
+
+/*
+ * Requests received while the lockspace is in recovery get added to the
+ * request queue and processed when recovery is complete.  This happens when
+ * the lockspace is suspended on some nodes before it is on others, or the
+ * lockspace is enabled on some while still suspended on others.
+ */
+
+void dlm_add_requestqueue(struct dlm_ls *ls, int nodeid, struct dlm_message *ms)
+{
+	struct rq_entry *e;
+	int length = ms->m_header.h_length - sizeof(struct dlm_message);
+
+	e = kmalloc(sizeof(struct rq_entry) + length, GFP_NOFS);
+	if (!e) {
+		log_print("dlm_add_requestqueue: out of memory len %d", length);
+		return;
+	}
+
+	e->recover_seq = ls->ls_recover_seq & 0xFFFFFFFF;
+	e->nodeid = nodeid;
+	memcpy(&e->request, ms, ms->m_header.h_length);
+
+	mutex_lock(&ls->ls_requestqueue_mutex);
+	list_add_tail(&e->list, &ls->ls_requestqueue);
+	mutex_unlock(&ls->ls_requestqueue_mutex);
+}
+
+/*
+ * Called by dlm_recoverd to process normal messages saved while recovery was
+ * happening.  Normal locking has been enabled before this is called.  dlm_recv
+ * upon receiving a message, will wait for all saved messages to be drained
+ * here before processing the message it got.  If a new dlm_ls_stop() arrives
+ * while we're processing these saved messages, it may block trying to suspend
+ * dlm_recv if dlm_recv is waiting for us in dlm_wait_requestqueue.  In that
+ * case, we don't abort since locking_stopped is still 0.  If dlm_recv is not
+ * waiting for us, then this processing may be aborted due to locking_stopped.
+ */
+
+int dlm_process_requestqueue(struct dlm_ls *ls)
+{
+	struct rq_entry *e;
+	struct dlm_message *ms;
+	int error = 0;
+
+	mutex_lock(&ls->ls_requestqueue_mutex);
+
+	for (;;) {
+		if (list_empty(&ls->ls_requestqueue)) {
+			mutex_unlock(&ls->ls_requestqueue_mutex);
+			error = 0;
+			break;
+		}
+		e = list_entry(ls->ls_requestqueue.next, struct rq_entry, list);
+		mutex_unlock(&ls->ls_requestqueue_mutex);
+
+		ms = &e->request;
+
+		log_limit(ls, "dlm_process_requestqueue msg %d from %d "
+			  "lkid %x remid %x result %d seq %u",
+			  ms->m_type, ms->m_header.h_nodeid,
+			  ms->m_lkid, ms->m_remid, ms->m_result,
+			  e->recover_seq);
+
+		dlm_receive_message_saved(ls, &e->request, e->recover_seq);
+
+		mutex_lock(&ls->ls_requestqueue_mutex);
+		list_del(&e->list);
+		kfree(e);
+
+		if (dlm_locking_stopped(ls)) {
+			log_debug(ls, "process_requestqueue abort running");
+			mutex_unlock(&ls->ls_requestqueue_mutex);
+			error = -EINTR;
+			break;
+		}
+		schedule();
+	}
+
+	return error;
+}
+
+/*
+ * After recovery is done, locking is resumed and dlm_recoverd takes all the
+ * saved requests and processes them as they would have been by dlm_recv.  At
+ * the same time, dlm_recv will start receiving new requests from remote nodes.
+ * We want to delay dlm_recv processing new requests until dlm_recoverd has
+ * finished processing the old saved requests.  We don't check for locking
+ * stopped here because dlm_ls_stop won't stop locking until it's suspended us
+ * (dlm_recv).
+ */
+
+void dlm_wait_requestqueue(struct dlm_ls *ls)
+{
+	for (;;) {
+		mutex_lock(&ls->ls_requestqueue_mutex);
+		if (list_empty(&ls->ls_requestqueue))
+			break;
+		mutex_unlock(&ls->ls_requestqueue_mutex);
+		schedule();
+	}
+	mutex_unlock(&ls->ls_requestqueue_mutex);
+}
+
+static int purge_request(struct dlm_ls *ls, struct dlm_message *ms, int nodeid)
+{
+	uint32_t type = ms->m_type;
+
+	/* the ls is being cleaned up and freed by release_lockspace */
+	if (!ls->ls_count)
+		return 1;
+
+	if (dlm_is_removed(ls, nodeid))
+		return 1;
+
+	/* directory operations are always purged because the directory is
+	   always rebuilt during recovery and the lookups resent */
+
+	if (type == DLM_MSG_REMOVE ||
+	    type == DLM_MSG_LOOKUP ||
+	    type == DLM_MSG_LOOKUP_REPLY)
+		return 1;
+
+	if (!dlm_no_directory(ls))
+		return 0;
+
+	return 1;
+}
+
+void dlm_purge_requestqueue(struct dlm_ls *ls)
+{
+	struct dlm_message *ms;
+	struct rq_entry *e, *safe;
+
+	mutex_lock(&ls->ls_requestqueue_mutex);
+	list_for_each_entry_safe(e, safe, &ls->ls_requestqueue, list) {
+		ms =  &e->request;
+
+		if (purge_request(ls, ms, e->nodeid)) {
+			list_del(&e->list);
+			kfree(e);
+		}
+	}
+	mutex_unlock(&ls->ls_requestqueue_mutex);
+}
+

fs/dlm/requestqueue.h

@@ -0,0 +1,22 @@
+/******************************************************************************
+*******************************************************************************
+**
+**  Copyright (C) 2005-2007 Red Hat, Inc.  All rights reserved.
+**
+**  This copyrighted material is made available to anyone wishing to use,
+**  modify, copy, or redistribute it subject to the terms and conditions
+**  of the GNU General Public License v.2.
+**
+*******************************************************************************
+******************************************************************************/
+
+#ifndef __REQUESTQUEUE_DOT_H__
+#define __REQUESTQUEUE_DOT_H__
+
+void dlm_add_requestqueue(struct dlm_ls *ls, int nodeid, struct dlm_message *ms);
+int dlm_process_requestqueue(struct dlm_ls *ls);
+void dlm_wait_requestqueue(struct dlm_ls *ls);
+void dlm_purge_requestqueue(struct dlm_ls *ls);
+
+#endif
+

fs/dlm/user.h

@@ -0,0 +1,19 @@
+/*
+ * Copyright (C) 2006-2010 Red Hat, Inc.  All rights reserved.
+ *
+ * This copyrighted material is made available to anyone wishing to use,
+ * modify, copy, or redistribute it subject to the terms and conditions
+ * of the GNU General Public License v.2.
+ */
+
+#ifndef __USER_DOT_H__
+#define __USER_DOT_H__
+
+void dlm_user_add_ast(struct dlm_lkb *lkb, uint32_t flags, int mode,
+                      int status, uint32_t sbflags, uint64_t seq);
+int dlm_user_init(void);
+void dlm_user_exit(void);
+int dlm_device_deregister(struct dlm_ls *ls);
+int dlm_user_daemon_available(void);
+
+#endif

fs/dlm/util.c

@@ -0,0 +1,154 @@
+/******************************************************************************
+*******************************************************************************
+**
+**  Copyright (C) 2005-2008 Red Hat, Inc.  All rights reserved.
+**
+**  This copyrighted material is made available to anyone wishing to use,
+**  modify, copy, or redistribute it subject to the terms and conditions
+**  of the GNU General Public License v.2.
+**
+*******************************************************************************
+******************************************************************************/
+
+#include "dlm_internal.h"
+#include "rcom.h"
+#include "util.h"
+
+#define DLM_ERRNO_EDEADLK		35
+#define DLM_ERRNO_EBADR			53
+#define DLM_ERRNO_EBADSLT		57
+#define DLM_ERRNO_EPROTO		71
+#define DLM_ERRNO_EOPNOTSUPP		95
+#define DLM_ERRNO_ETIMEDOUT	       110
+#define DLM_ERRNO_EINPROGRESS	       115
+
+static void header_out(struct dlm_header *hd)
+{
+	hd->h_version		= cpu_to_le32(hd->h_version);
+	hd->h_lockspace		= cpu_to_le32(hd->h_lockspace);
+	hd->h_nodeid		= cpu_to_le32(hd->h_nodeid);
+	hd->h_length		= cpu_to_le16(hd->h_length);
+}
+
+static void header_in(struct dlm_header *hd)
+{
+	hd->h_version		= le32_to_cpu(hd->h_version);
+	hd->h_lockspace		= le32_to_cpu(hd->h_lockspace);
+	hd->h_nodeid		= le32_to_cpu(hd->h_nodeid);
+	hd->h_length		= le16_to_cpu(hd->h_length);
+}
+
+/* higher errno values are inconsistent across architectures, so select
+   one set of values for on the wire */
+
+static int to_dlm_errno(int err)
+{
+	switch (err) {
+	case -EDEADLK:
+		return -DLM_ERRNO_EDEADLK;
+	case -EBADR:
+		return -DLM_ERRNO_EBADR;
+	case -EBADSLT:
+		return -DLM_ERRNO_EBADSLT;
+	case -EPROTO:
+		return -DLM_ERRNO_EPROTO;
+	case -EOPNOTSUPP:
+		return -DLM_ERRNO_EOPNOTSUPP;
+	case -ETIMEDOUT:
+		return -DLM_ERRNO_ETIMEDOUT;
+	case -EINPROGRESS:
+		return -DLM_ERRNO_EINPROGRESS;
+	}
+	return err;
+}
+
+static int from_dlm_errno(int err)
+{
+	switch (err) {
+	case -DLM_ERRNO_EDEADLK:
+		return -EDEADLK;
+	case -DLM_ERRNO_EBADR:
+		return -EBADR;
+	case -DLM_ERRNO_EBADSLT:
+		return -EBADSLT;
+	case -DLM_ERRNO_EPROTO:
+		return -EPROTO;
+	case -DLM_ERRNO_EOPNOTSUPP:
+		return -EOPNOTSUPP;
+	case -DLM_ERRNO_ETIMEDOUT:
+		return -ETIMEDOUT;
+	case -DLM_ERRNO_EINPROGRESS:
+		return -EINPROGRESS;
+	}
+	return err;
+}
+
+void dlm_message_out(struct dlm_message *ms)
+{
+	header_out(&ms->m_header);
+
+	ms->m_type		= cpu_to_le32(ms->m_type);
+	ms->m_nodeid		= cpu_to_le32(ms->m_nodeid);
+	ms->m_pid		= cpu_to_le32(ms->m_pid);
+	ms->m_lkid		= cpu_to_le32(ms->m_lkid);
+	ms->m_remid		= cpu_to_le32(ms->m_remid);
+	ms->m_parent_lkid	= cpu_to_le32(ms->m_parent_lkid);
+	ms->m_parent_remid	= cpu_to_le32(ms->m_parent_remid);
+	ms->m_exflags		= cpu_to_le32(ms->m_exflags);
+	ms->m_sbflags		= cpu_to_le32(ms->m_sbflags);
+	ms->m_flags		= cpu_to_le32(ms->m_flags);
+	ms->m_lvbseq		= cpu_to_le32(ms->m_lvbseq);
+	ms->m_hash		= cpu_to_le32(ms->m_hash);
+	ms->m_status		= cpu_to_le32(ms->m_status);
+	ms->m_grmode		= cpu_to_le32(ms->m_grmode);
+	ms->m_rqmode		= cpu_to_le32(ms->m_rqmode);
+	ms->m_bastmode		= cpu_to_le32(ms->m_bastmode);
+	ms->m_asts		= cpu_to_le32(ms->m_asts);
+	ms->m_result		= cpu_to_le32(to_dlm_errno(ms->m_result));
+}
+
+void dlm_message_in(struct dlm_message *ms)
+{
+	header_in(&ms->m_header);
+
+	ms->m_type		= le32_to_cpu(ms->m_type);
+	ms->m_nodeid		= le32_to_cpu(ms->m_nodeid);
+	ms->m_pid		= le32_to_cpu(ms->m_pid);
+	ms->m_lkid		= le32_to_cpu(ms->m_lkid);
+	ms->m_remid		= le32_to_cpu(ms->m_remid);
+	ms->m_parent_lkid	= le32_to_cpu(ms->m_parent_lkid);
+	ms->m_parent_remid	= le32_to_cpu(ms->m_parent_remid);
+	ms->m_exflags		= le32_to_cpu(ms->m_exflags);
+	ms->m_sbflags		= le32_to_cpu(ms->m_sbflags);
+	ms->m_flags		= le32_to_cpu(ms->m_flags);
+	ms->m_lvbseq		= le32_to_cpu(ms->m_lvbseq);
+	ms->m_hash		= le32_to_cpu(ms->m_hash);
+	ms->m_status		= le32_to_cpu(ms->m_status);
+	ms->m_grmode		= le32_to_cpu(ms->m_grmode);
+	ms->m_rqmode		= le32_to_cpu(ms->m_rqmode);
+	ms->m_bastmode		= le32_to_cpu(ms->m_bastmode);
+	ms->m_asts		= le32_to_cpu(ms->m_asts);
+	ms->m_result		= from_dlm_errno(le32_to_cpu(ms->m_result));
+}
+
+void dlm_rcom_out(struct dlm_rcom *rc)
+{
+	header_out(&rc->rc_header);
+
+	rc->rc_type		= cpu_to_le32(rc->rc_type);
+	rc->rc_result		= cpu_to_le32(rc->rc_result);
+	rc->rc_id		= cpu_to_le64(rc->rc_id);
+	rc->rc_seq		= cpu_to_le64(rc->rc_seq);
+	rc->rc_seq_reply	= cpu_to_le64(rc->rc_seq_reply);
+}
+
+void dlm_rcom_in(struct dlm_rcom *rc)
+{
+	header_in(&rc->rc_header);
+
+	rc->rc_type		= le32_to_cpu(rc->rc_type);
+	rc->rc_result		= le32_to_cpu(rc->rc_result);
+	rc->rc_id		= le64_to_cpu(rc->rc_id);
+	rc->rc_seq		= le64_to_cpu(rc->rc_seq);
+	rc->rc_seq_reply	= le64_to_cpu(rc->rc_seq_reply);
+}

fs/dlm/util.h

@@ -0,0 +1,22 @@
+/******************************************************************************
+*******************************************************************************
+**
+**  Copyright (C) 2005 Red Hat, Inc.  All rights reserved.
+**
+**  This copyrighted material is made available to anyone wishing to use,
+**  modify, copy, or redistribute it subject to the terms and conditions
+**  of the GNU General Public License v.2.
+**
+*******************************************************************************
+******************************************************************************/
+
+#ifndef __UTIL_DOT_H__
+#define __UTIL_DOT_H__
+
+void dlm_message_out(struct dlm_message *ms);
+void dlm_message_in(struct dlm_message *ms);
+void dlm_rcom_out(struct dlm_rcom *rc);
+void dlm_rcom_in(struct dlm_rcom *rc);
+
+#endif
+