path: root/drivers/md/md-cluster.c

/*
 * 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>
#include <linux/dlm.h>
#include <linux/sched.h>
#include <linux/raid/md_p.h>
#include "md.h"
#include "bitmap.h"
#include "md-cluster.h"

#define LVB_SIZE	64
#define NEW_DEV_TIMEOUT 5000

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 */
	void (*bast)(void *arg, int mode); /* blocking AST function pointer*/
	struct mddev *mddev; /* pointing back to mddev. */
	int mode;
};

struct suspend_info {
	int slot;
	sector_t lo;
	sector_t hi;
	struct list_head list;
};

struct resync_info {
	__le64 lo;
	__le64 hi;
};

/* md_cluster_info flags */
#define		MD_CLUSTER_WAITING_FOR_NEWDISK		1
#define		MD_CLUSTER_SUSPEND_READ_BALANCING	2
#define		MD_CLUSTER_BEGIN_JOIN_CLUSTER		3

/* Lock the send communication. This is done through
 * bit manipulation as opposed to a mutex in order to
 * accomodate lock and hold. See next comment.
 */
#define		MD_CLUSTER_SEND_LOCK			4
/* If cluster operations (such as adding a disk) must lock the
 * communication channel, so as to perform extra operations
 * (update metadata) and no other operation is allowed on the
 * MD. Token needs to be locked and held until the operation
 * completes witha md_update_sb(), which would eventually release
 * the lock.
 */
#define		MD_CLUSTER_SEND_LOCKED_ALREADY		5


struct md_cluster_info {
	/* dlm lock space and resources for clustered raid. */
	dlm_lockspace_t *lockspace;
	int slot_number;
	struct completion completion;
	struct mutex recv_mutex;
	struct dlm_lock_resource *bitmap_lockres;
	struct dlm_lock_resource **other_bitmap_lockres;
	struct dlm_lock_resource *resync_lockres;
	struct list_head suspend_list;
	spinlock_t suspend_lock;
	struct md_thread *recovery_thread;
	unsigned long recovery_map;
	/* communication loc resources */
	struct dlm_lock_resource *ack_lockres;
	struct dlm_lock_resource *message_lockres;
	struct dlm_lock_resource *token_lockres;
	struct dlm_lock_resource *no_new_dev_lockres;
	struct md_thread *recv_thread;
	struct completion newdisk_completion;
	wait_queue_head_t wait;
	unsigned long state;
};

enum msg_type {
	METADATA_UPDATED = 0,
	RESYNCING,
	NEWDISK,
	REMOVE,
	RE_ADD,
	BITMAP_NEEDS_SYNC,
};

struct cluster_msg {
	__le32 type;
	__le32 slot;
	/* TODO: Unionize this for smaller footprint */
	__le64 low;
	__le64 high;
	char uuid[16];
	__le32 raid_slot;
};

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

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

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

	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);
	if (res->lksb.sb_status == 0)
		res->mode = mode;
	return res->lksb.sb_status;
}

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

static struct dlm_lock_resource *lockres_init(struct mddev *mddev,
		char *name, void (*bastfn)(void *arg, int mode), int with_lvb)
{
	struct dlm_lock_resource *res = NULL;
	int ret, namelen;
	struct md_cluster_info *cinfo = mddev->cluster_info;

	res = kzalloc(sizeof(struct dlm_lock_resource), GFP_KERNEL);
	if (!res)
		return NULL;
	init_completion(&res->completion);
	res->ls = cinfo->lockspace;
	res->mddev = mddev;
	res->mode = DLM_LOCK_IV;
	namelen = strlen(name);
	res->name =