/*
   raid0.c : Multiple Devices driver for Linux
             Copyright (C) 1994-96 Marc ZYNGIER
	     <zyngier@ufr-info-p7.ibp.fr> or
	     <maz@gloups.fdn.fr>
             Copyright (C) 1999, 2000 Ingo Molnar, Red Hat


   RAID-0 management functions.

   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.
   
   You should have received a copy of the GNU General Public License
   (for example /usr/src/linux/COPYING); if not, write to the Free
   Software Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.  
*/

#include <linux/blkdev.h>
#include <linux/seq_file.h>
#include <linux/slab.h>
#include "md.h"
#include "raid0.h"
#include "raid5.h"

static int raid0_congested(void *data, int bits)
{
	mddev_t *mddev = data;
	raid0_conf_t *conf = mddev->private;
	mdk_rdev_t **devlist = conf->devlist;
	int raid_disks = conf->strip_zone[0].nb_dev;
	int i, ret = 0;

	if (mddev_congested(mddev, bits))
		return 1;

	for (i = 0; i < raid_disks && !ret ; i++) {
		struct request_queue *q = bdev_get_queue(devlist[i]->bdev);

		ret |= bdi_congested(&q->backing_dev_info, bits);
	}
	return ret;
}

/*
 * inform the user of the raid configuration
*/
static void dump_zones(mddev_t *mddev)
{
	int j, k, h;
	sector_t zone_size = 0;
	sector_t zone_start = 0;
	char b[BDEVNAME_SIZE];
	raid0_conf_t *conf = mddev->private;
	int raid_disks = conf->strip_zone[0].nb_dev;
	printk(KERN_INFO "******* %s configuration *********\n",
		mdname(mddev));
	h = 0;
	for (j = 0; j < conf->nr_strip_zones; j++) {
		printk(KERN_INFO "zone%d=[", j);
		for (k = 0; k < conf->strip_zone[j].nb_dev; k++)
			printk(KERN_CONT "%s/",
			bdevname(conf->devlist[j*raid_disks
						+ k]->bdev, b));
		printk(KERN_CONT "]\n");

		zone_size  = conf->strip_zone[j].zone_end - zone_start;
		printk(KERN_INFO "        zone offset=%llukb "
				"device offset=%llukb size=%llukb\n",
			(unsigned long long)zone_start>>1,
			(unsigned long long)conf->strip_zone[j].dev_start>>1,
			(unsigned long long)zone_size>>1);
		zone_start = conf->strip_zone[j].zone_end;
	}
	printk(KERN_INFO "**********************************\n\n");
}

static int create_strip_zones(mddev_t *mddev, raid0_conf_t **private_conf)
{
	int i, c, err;
	sector_t curr_zone_end, sectors;
	mdk_rdev_t *smallest, *rdev1, *rdev2, *rdev, **dev;
	struct strip_zone *zone;
	int cnt;
	char b[BDEVNAME_SIZE];
	raid0_conf_t *conf = kzalloc(sizeof(*conf), GFP_KERNEL);

	if (!conf)
		return -ENOMEM;
	list_for_each_entry(rdev1, &mddev->disks, same_set) {
		printk(KERN_INFO "md/raid0:%s: looking at %s\n",
		       mdname(mddev),
		       bdevname(rdev1->bdev, b));
		c = 0;

		/* round size to chunk_size */
		sectors = rdev1->sectors;
		sector_div(sectors, mddev->chunk_sectors);
		rdev1->sectors = sectors * mddev->chunk_sectors;

		list_for_each_entry(rdev2, &mddev->disks, same_set) {
			printk(KERN_INFO "md/raid0:%s:   comparing %s(%llu)",
			       mdname(mddev),
			       bdevname(rdev1->bdev,b),
			       (unsigned long long)rdev1->sectors);
			printk(KERN_CONT " with %s(%llu)\n",
			       bdevname(rdev2->bdev,b),
			       (unsigned long long)rdev2->sectors);
			if (rdev2 == rdev1) {
				printk(KERN_INFO "md/raid0:%s:   END\n",
				       mdname(mddev));
				break;
			}
			if (rdev2->sectors == rdev1->sectors) {
				/*
				 * Not unique, don't count it as a new
				 * group
				 */
				printk(KERN_INFO "md/raid0:%s:   EQUAL\n",
				       mdname(mddev));
				c = 1;
				break;
			}
			printk(KERN_INFO "md/raid0:%s:   NOT EQUAL\n",
			       mdname(mddev));
		}
		if (!c) {
			printk(KERN_INFO "md/raid0:%s:   ==> UNIQUE\n",
			       mdname(mddev));
			conf->nr_strip_zones++;
			printk(KERN_INFO "md/raid0:%s: %d zones\n",
			       mdname(mddev), conf->nr_strip_zones);
		}
	}
	printk(KERN_INFO "md/raid0:%s: FINAL %d zones\n",
	       mdname(mddev), conf->nr_strip_zones);
	err = -ENOMEM;
	conf->strip_zone = kzalloc(sizeof(struct strip_zone)*
				conf->nr_strip_zones, GFP_KERNEL);
	if (!conf->strip_zone)
		goto abort;
	conf->devlist = kzalloc(sizeof(mdk_rdev_t*)*
				conf->nr_strip_zones*mddev->raid_disks,
				GFP_KERNEL);
	if (!conf->devlist)
		goto abort;

	/* The first zone must contain all devices, so here we check that
	 * there is a proper alignment of slots to devices and find them all
	 */
	zone = &conf->strip_zone[0];
	cnt = 0;
	smallest = NULL;
	dev = conf->devlist;
	err = -EINVAL;
	list_for_each_entry(rdev1, &mddev->disks, same_set) {
		int j = rdev1->raid_disk;

		if (mddev->level == 10) {
			/* taking over a raid10-n2 array */
			j /= 2;
			rdev1->new_raid_disk = j;
		}

		if (mddev->level == 1) {
			/* taiking over a raid1 array-
			 * we have only one active disk
			 */
			j = 0;
			rdev1->new_raid_disk = j;
		}

		if (j < 0 || j >= mddev->raid_disks) {
			printk(KERN_ERR "md/raid0:%s: bad disk number %d - "
			       "aborting!\n", mdname(mddev), j);
			goto abort;
		}
		if (dev[j]) {
			printk(KERN_ERR "md/raid0:%s: multiple devices for %d - "
			       "aborting!\n", mdname(mddev), j);
			goto abort;
		}
		dev[j] = rdev1;

		disk_stack_limits(mddev->gendisk, rdev1->bdev,
				  rdev1->data_offset << 9);
		/* as we don't honour merge_bvec_fn, we must never risk
		 * violating it, so limit ->max_segments to 1, lying within
		 * a single page.
		 */

		if (rdev1->bdev->bd_disk->queue->merge_bvec_fn) {
			blk_queue_max_segments(mddev->queue, 1);
			blk_queue_segment_boundary(mddev->queue,
						   PAGE_CACHE_SIZE - 1);
		}
		if (!smallest || (rdev1->sectors < smallest->sectors))
			smallest = rdev1;
		cnt++;
	}
	if (cnt != mddev->raid_disks) {
		printk(KERN_ERR "md/raid0:%s: too few disks (%d of %d) - "
		       "aborting!\n", mdname(mddev), cnt, mddev->raid_disks);
		goto abort;
	}
	zone->nb_dev = cnt;
	zone->zone_end = smallest->sectors * cnt;

	curr_zone_end = zone->zone_end;

	/* now do the other zones */
	for (i = 1; i < conf->nr_strip_zones; i++)
	{
		int j;

		zone = conf->strip_zone + i;
		dev = conf->devlist + i * mddev->raid_disks;

		printk(KERN_INFO "md/raid0:%s: zone %d\n",
		       mdname(mddev), i);
		zone->dev_start = smallest->sectors;
		smallest = NULL;
		c = 0;

		for (j=0; j<cnt; j++) {
			rdev = conf->devlist[j];
			printk(KERN_INFO "md/raid0:%s: checking %s ...",
			       mdname(mddev),
			       bdevname(rdev->bdev, b));
			if (rdev->sectors <= zone->dev_start) {
				printk(KERN_CONT " nope.\n");
				continue;
			}
			printk(KERN_CONT " contained as device %d\n", c);
			dev[c] = rdev;
			c++;
			if (!smallest || rdev->sectors < smallest->sectors) {
				smallest = rdev;
				printk(KERN_INFO "md/raid0:%s:  (%llu) is smallest!.\n",
				       mdname(mddev),
				       (unsigned long long)rdev->sectors);
			}
		}

		zone->nb_dev = c;
		sectors = (smallest->sectors - zone->dev_start) * c;
		printk(KERN_INFO "md/raid0:%s: zone->nb_dev: %d, sectors: %llu\n",
		       mdname(mddev),
		       zone->nb_dev, (unsigned long long)sectors);

		curr_zone_end += sectors;
		zone->zone_end = curr_zone_end;

		printk(KERN_INFO "md/raid0:%s: current zone start: %llu\n",
		       mdname(mddev),
		       (unsigned long long)smallest->sectors);
	}
	mddev->queue->backing_dev_info.congested_fn = raid0_congested;
	mddev->queue->backing_dev_info.congested_data = mddev;

	/*
	 * now since we have the hard sector sizes, we can make sure
	 * chunk size is a multiple of that sector size