md-cluster.c 6.1 KB
Newer Older
1 2 3 4 5 6 7 8 9 10 11 12
/*
 * Copyright (C) 2015, SUSE
 *
 * This program is free software; you can redistribute it and/or modify
 * it under the terms of the GNU General Public License as published by
 * the Free Software Foundation; either version 2, or (at your option)
 * any later version.
 *
 */


#include <linux/module.h>
13 14 15
#include <linux/dlm.h>
#include <linux/sched.h>
#include "md.h"
16
#include "md-cluster.h"
17 18 19 20 21 22 23 24 25

#define LVB_SIZE	64

struct dlm_lock_resource {
	dlm_lockspace_t *ls;
	struct dlm_lksb lksb;
	char *name; /* lock name. */
	uint32_t flags; /* flags to pass to dlm_lock() */
	struct completion completion; /* completion for synchronized locking */
G
Goldwyn Rodrigues 已提交
26 27 28 29 30 31 32
	void (*bast)(void *arg, int mode); /* blocking AST function pointer*/
	struct mddev *mddev; /* pointing back to mddev. */
};

struct md_cluster_info {
	/* dlm lock space and resources for clustered raid. */
	dlm_lockspace_t *lockspace;
G
Goldwyn Rodrigues 已提交
33 34
	int slot_number;
	struct completion completion;
G
Goldwyn Rodrigues 已提交
35 36
	struct dlm_lock_resource *sb_lock;
	struct mutex sb_mutex;
37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65
};

static void sync_ast(void *arg)
{
	struct dlm_lock_resource *res;

	res = (struct dlm_lock_resource *) arg;
	complete(&res->completion);
}

static int dlm_lock_sync(struct dlm_lock_resource *res, int mode)
{
	int ret = 0;

	init_completion(&res->completion);
	ret = dlm_lock(res->ls, mode, &res->lksb,
			res->flags, res->name, strlen(res->name),
			0, sync_ast, res, res->bast);
	if (ret)
		return ret;
	wait_for_completion(&res->completion);
	return res->lksb.sb_status;
}

static int dlm_unlock_sync(struct dlm_lock_resource *res)
{
	return dlm_lock_sync(res, DLM_LOCK_NL);
}

G
Goldwyn Rodrigues 已提交
66
static struct dlm_lock_resource *lockres_init(struct mddev *mddev,
67 68 69 70
		char *name, void (*bastfn)(void *arg, int mode), int with_lvb)
{
	struct dlm_lock_resource *res = NULL;
	int ret, namelen;
G
Goldwyn Rodrigues 已提交
71
	struct md_cluster_info *cinfo = mddev->cluster_info;
72 73 74 75

	res = kzalloc(sizeof(struct dlm_lock_resource), GFP_KERNEL);
	if (!res)
		return NULL;
G
Goldwyn Rodrigues 已提交
76 77
	res->ls = cinfo->lockspace;
	res->mddev = mddev;
78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127
	namelen = strlen(name);
	res->name = kzalloc(namelen + 1, GFP_KERNEL);
	if (!res->name) {
		pr_err("md-cluster: Unable to allocate resource name for resource %s\n", name);
		goto out_err;
	}
	strlcpy(res->name, name, namelen + 1);
	if (with_lvb) {
		res->lksb.sb_lvbptr = kzalloc(LVB_SIZE, GFP_KERNEL);
		if (!res->lksb.sb_lvbptr) {
			pr_err("md-cluster: Unable to allocate LVB for resource %s\n", name);
			goto out_err;
		}
		res->flags = DLM_LKF_VALBLK;
	}

	if (bastfn)
		res->bast = bastfn;

	res->flags |= DLM_LKF_EXPEDITE;

	ret = dlm_lock_sync(res, DLM_LOCK_NL);
	if (ret) {
		pr_err("md-cluster: Unable to lock NL on new lock resource %s\n", name);
		goto out_err;
	}
	res->flags &= ~DLM_LKF_EXPEDITE;
	res->flags |= DLM_LKF_CONVERT;

	return res;
out_err:
	kfree(res->lksb.sb_lvbptr);
	kfree(res->name);
	kfree(res);
	return NULL;
}

static void lockres_free(struct dlm_lock_resource *res)
{
	if (!res)
		return;

	init_completion(&res->completion);
	dlm_unlock(res->ls, res->lksb.sb_lkid, 0, &res->lksb, res);
	wait_for_completion(&res->completion);

	kfree(res->name);
	kfree(res->lksb.sb_lvbptr);
	kfree(res);
}
128

G
Goldwyn Rodrigues 已提交
129 130 131 132 133 134 135 136 137 138 139 140
static char *pretty_uuid(char *dest, char *src)
{
	int i, len = 0;

	for (i = 0; i < 16; i++) {
		if (i == 4 || i == 6 || i == 8 || i == 10)
			len += sprintf(dest + len, "-");
		len += sprintf(dest + len, "%02x", (__u8)src[i]);
	}
	return dest;
}

G
Goldwyn Rodrigues 已提交
141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172
static void recover_prep(void *arg)
{
}

static void recover_slot(void *arg, struct dlm_slot *slot)
{
	struct mddev *mddev = arg;
	struct md_cluster_info *cinfo = mddev->cluster_info;

	pr_info("md-cluster: %s Node %d/%d down. My slot: %d. Initiating recovery.\n",
			mddev->bitmap_info.cluster_name,
			slot->nodeid, slot->slot,
			cinfo->slot_number);
}

static void recover_done(void *arg, struct dlm_slot *slots,
		int num_slots, int our_slot,
		uint32_t generation)
{
	struct mddev *mddev = arg;
	struct md_cluster_info *cinfo = mddev->cluster_info;

	cinfo->slot_number = our_slot;
	complete(&cinfo->completion);
}

static const struct dlm_lockspace_ops md_ls_ops = {
	.recover_prep = recover_prep,
	.recover_slot = recover_slot,
	.recover_done = recover_done,
};

173 174
static int join(struct mddev *mddev, int nodes)
{
G
Goldwyn Rodrigues 已提交
175
	struct md_cluster_info *cinfo;
G
Goldwyn Rodrigues 已提交
176
	int ret, ops_rv;
G
Goldwyn Rodrigues 已提交
177 178 179 180 181 182 183 184 185
	char str[64];

	if (!try_module_get(THIS_MODULE))
		return -ENOENT;

	cinfo = kzalloc(sizeof(struct md_cluster_info), GFP_KERNEL);
	if (!cinfo)
		return -ENOMEM;

G
Goldwyn Rodrigues 已提交
186 187 188 189 190
	init_completion(&cinfo->completion);

	mutex_init(&cinfo->sb_mutex);
	mddev->cluster_info = cinfo;

G
Goldwyn Rodrigues 已提交
191 192
	memset(str, 0, 64);
	pretty_uuid(str, mddev->uuid);
G
Goldwyn Rodrigues 已提交
193 194 195
	ret = dlm_new_lockspace(str, mddev->bitmap_info.cluster_name,
				DLM_LSFL_FS, LVB_SIZE,
				&md_ls_ops, mddev, &ops_rv, &cinfo->lockspace);
G
Goldwyn Rodrigues 已提交
196 197
	if (ret)
		goto err;
G
Goldwyn Rodrigues 已提交
198
	wait_for_completion(&cinfo->completion);
199 200 201 202 203 204
	if (nodes <= cinfo->slot_number) {
		pr_err("md-cluster: Slot allotted(%d) greater than available slots(%d)", cinfo->slot_number - 1,
			nodes);
		ret = -ERANGE;
		goto err;
	}
G
Goldwyn Rodrigues 已提交
205 206 207 208 209 210
	cinfo->sb_lock = lockres_init(mddev, "cmd-super",
					NULL, 0);
	if (!cinfo->sb_lock) {
		ret = -ENOMEM;
		goto err;
	}
211
	return 0;
G
Goldwyn Rodrigues 已提交
212 213 214
err:
	if (cinfo->lockspace)
		dlm_release_lockspace(cinfo->lockspace, 2);
G
Goldwyn Rodrigues 已提交
215
	mddev->cluster_info = NULL;
G
Goldwyn Rodrigues 已提交
216 217 218
	kfree(cinfo);
	module_put(THIS_MODULE);
	return ret;
219 220 221 222
}

static int leave(struct mddev *mddev)
{
G
Goldwyn Rodrigues 已提交
223 224 225 226 227 228
	struct md_cluster_info *cinfo = mddev->cluster_info;

	if (!cinfo)
		return 0;
	lockres_free(cinfo->sb_lock);
	dlm_release_lockspace(cinfo->lockspace, 2);
229 230 231
	return 0;
}

G
Goldwyn Rodrigues 已提交
232 233 234 235 236 237 238 239 240 241 242
/* slot_number(): Returns the MD slot number to use
 * DLM starts the slot numbers from 1, wheras cluster-md
 * wants the number to be from zero, so we deduct one
 */
static int slot_number(struct mddev *mddev)
{
	struct md_cluster_info *cinfo = mddev->cluster_info;

	return cinfo->slot_number - 1;
}

243 244 245
static struct md_cluster_operations cluster_ops = {
	.join   = join,
	.leave  = leave,
G
Goldwyn Rodrigues 已提交
246
	.slot_number = slot_number,
247 248
};

249 250 251 252
static int __init cluster_init(void)
{
	pr_warn("md-cluster: EXPERIMENTAL. Use with caution\n");
	pr_info("Registering Cluster MD functions\n");
253
	register_md_cluster_operations(&cluster_ops, THIS_MODULE);
254 255 256 257 258
	return 0;
}

static void cluster_exit(void)
{
259
	unregister_md_cluster_operations();
260 261 262 263 264 265
}

module_init(cluster_init);
module_exit(cluster_exit);
MODULE_LICENSE("GPL");
MODULE_DESCRIPTION("Clustering support for MD");