linux/drivers/md/raid0.c
Jens Axboe 1eff9d322a block: rename bio bi_rw to bi_opf
Since commit 63a4cc2486, bio->bi_rw contains flags in the lower
portion and the op code in the higher portions. This means that
old code that relies on manually setting bi_rw is most likely
going to be broken. Instead of letting that brokeness linger,
rename the member, to force old and out-of-tree code to break
at compile time instead of at runtime.

No intended functional changes in this commit.

Signed-off-by: Jens Axboe <axboe@fb.com>
2016-08-07 14:41:02 -06:00

697 lines
18 KiB
C

/*
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/module.h>
#include <linux/slab.h>
#include "md.h"
#include "raid0.h"
#include "raid5.h"
static int raid0_congested(struct mddev *mddev, int bits)
{
struct r0conf *conf = mddev->private;
struct md_rdev **devlist = conf->devlist;
int raid_disks = conf->strip_zone[0].nb_dev;
int i, ret = 0;
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(struct mddev *mddev)
{
int j, k;
sector_t zone_size = 0;
sector_t zone_start = 0;
char b[BDEVNAME_SIZE];
struct r0conf *conf = mddev->private;
int raid_disks = conf->strip_zone[0].nb_dev;
printk(KERN_INFO "md: RAID0 configuration for %s - %d zone%s\n",
mdname(mddev),
conf->nr_strip_zones, conf->nr_strip_zones==1?"":"s");
for (j = 0; j < conf->nr_strip_zones; j++) {
printk(KERN_INFO "md: zone%d=[", j);
for (k = 0; k < conf->strip_zone[j].nb_dev; k++)
printk(KERN_CONT "%s%s", k?"/":"",
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=%10lluKB, "
"device-offset=%10lluKB, size=%10lluKB\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;
}
}
static int create_strip_zones(struct mddev *mddev, struct r0conf **private_conf)
{
int i, c, err;
sector_t curr_zone_end, sectors;
struct md_rdev *smallest, *rdev1, *rdev2, *rdev, **dev;
struct strip_zone *zone;
int cnt;
char b[BDEVNAME_SIZE];
char b2[BDEVNAME_SIZE];
struct r0conf *conf = kzalloc(sizeof(*conf), GFP_KERNEL);
unsigned short blksize = 512;
*private_conf = ERR_PTR(-ENOMEM);
if (!conf)
return -ENOMEM;
rdev_for_each(rdev1, mddev) {
pr_debug("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;
blksize = max(blksize, queue_logical_block_size(
rdev1->bdev->bd_disk->queue));
rdev_for_each(rdev2, mddev) {
pr_debug("md/raid0:%s: comparing %s(%llu)"
" with %s(%llu)\n",
mdname(mddev),
bdevname(rdev1->bdev,b),
(unsigned long long)rdev1->sectors,
bdevname(rdev2->bdev,b2),
(unsigned long long)rdev2->sectors);
if (rdev2 == rdev1) {
pr_debug("md/raid0:%s: END\n",
mdname(mddev));
break;
}
if (rdev2->sectors == rdev1->sectors) {
/*
* Not unique, don't count it as a new
* group
*/
pr_debug("md/raid0:%s: EQUAL\n",
mdname(mddev));
c = 1;
break;
}
pr_debug("md/raid0:%s: NOT EQUAL\n",
mdname(mddev));
}
if (!c) {
pr_debug("md/raid0:%s: ==> UNIQUE\n",
mdname(mddev));
conf->nr_strip_zones++;
pr_debug("md/raid0:%s: %d zones\n",
mdname(mddev), conf->nr_strip_zones);
}
}
pr_debug("md/raid0:%s: FINAL %d zones\n",
mdname(mddev), conf->nr_strip_zones);
/*
* now since we have the hard sector sizes, we can make sure
* chunk size is a multiple of that sector size
*/
if ((mddev->chunk_sectors << 9) % blksize) {
printk(KERN_ERR "md/raid0:%s: chunk_size of %d not multiple of block size %d\n",
mdname(mddev),
mddev->chunk_sectors << 9, blksize);
err = -EINVAL;
goto abort;
}
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(struct md_rdev*)*
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;
rdev_for_each(rdev1, mddev) {
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) {
printk(KERN_ERR
"md/raid0:%s: remove inactive devices before converting to RAID0\n",
mdname(mddev));
goto abort;
}
if (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;
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;
pr_debug("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];
if (rdev->sectors <= zone->dev_start) {
pr_debug("md/raid0:%s: checking %s ... nope\n",
mdname(mddev),
bdevname(rdev->bdev, b));
continue;
}
pr_debug("md/raid0:%s: checking %s ..."
" contained as device %d\n",
mdname(mddev),
bdevname(rdev->bdev, b), c);
dev[c] = rdev;
c++;
if (!smallest || rdev->sectors < smallest->sectors) {
smallest = rdev;
pr_debug("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;
pr_debug("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;
pr_debug("md/raid0:%s: current zone start: %llu\n",
mdname(mddev),
(unsigned long long)smallest->sectors);
}
pr_debug("md/raid0:%s: done.\n", mdname(mddev));
*private_conf = conf;
return 0;
abort:
kfree(conf->strip_zone);
kfree(conf->devlist);
kfree(conf);
*private_conf = ERR_PTR(err);
return err;
}
/* Find the zone which holds a particular offset
* Update *sectorp to be an offset in that zone
*/
static struct strip_zone *find_zone(struct r0conf *conf,
sector_t *sectorp)
{
int i;
struct strip_zone *z = conf->strip_zone;
sector_t sector = *sectorp;
for (i = 0; i < conf->nr_strip_zones; i++)
if (sector < z[i].zone_end) {
if (i)
*sectorp = sector - z[i-1].zone_end;
return z + i;
}
BUG();
}
/*
* remaps the bio to the target device. we separate two flows.
* power 2 flow and a general flow for the sake of performance
*/
static struct md_rdev *map_sector(struct mddev *mddev, struct strip_zone *zone,
sector_t sector, sector_t *sector_offset)
{
unsigned int sect_in_chunk;
sector_t chunk;
struct r0conf *conf = mddev->private;
int raid_disks = conf->strip_zone[0].nb_dev;
unsigned int chunk_sects = mddev->chunk_sectors;
if (is_power_of_2(chunk_sects)) {
int chunksect_bits = ffz(~chunk_sects);
/* find the sector offset inside the chunk */
sect_in_chunk = sector & (chunk_sects - 1);
sector >>= chunksect_bits;
/* chunk in zone */
chunk = *sector_offset;
/* quotient is the chunk in real device*/
sector_div(chunk, zone->nb_dev << chunksect_bits);
} else{
sect_in_chunk = sector_div(sector, chunk_sects);
chunk = *sector_offset;
sector_div(chunk, chunk_sects * zone->nb_dev);
}
/*
* position the bio over the real device
* real sector = chunk in device + starting of zone
* + the position in the chunk
*/
*sector_offset = (chunk * chunk_sects) + sect_in_chunk;
return conf->devlist[(zone - conf->strip_zone)*raid_disks
+ sector_div(sector, zone->nb_dev)];
}
static sector_t raid0_size(struct mddev *mddev, sector_t sectors, int raid_disks)
{
sector_t array_sectors = 0;
struct md_rdev *rdev;
WARN_ONCE(sectors || raid_disks,
"%s does not support generic reshape\n", __func__);
rdev_for_each(rdev, mddev)
array_sectors += (rdev->sectors &
~(sector_t)(mddev->chunk_sectors-1));
return array_sectors;
}
static void raid0_free(struct mddev *mddev, void *priv);
static int raid0_run(struct mddev *mddev)
{
struct r0conf *conf;
int ret;
if (mddev->chunk_sectors == 0) {
printk(KERN_ERR "md/raid0:%s: chunk size must be set.\n",
mdname(mddev));
return -EINVAL;
}
if (md_check_no_bitmap(mddev))
return -EINVAL;
/* if private is not null, we are here after takeover */
if (mddev->private == NULL) {
ret = create_strip_zones(mddev, &conf);
if (ret < 0)
return ret;
mddev->private = conf;
}
conf = mddev->private;
if (mddev->queue) {
struct md_rdev *rdev;
bool discard_supported = false;
blk_queue_max_hw_sectors(mddev->queue, mddev->chunk_sectors);
blk_queue_max_write_same_sectors(mddev->queue, mddev->chunk_sectors);
blk_queue_max_discard_sectors(mddev->queue, mddev->chunk_sectors);
blk_queue_io_min(mddev->queue, mddev->chunk_sectors << 9);
blk_queue_io_opt(mddev->queue,
(mddev->chunk_sectors << 9) * mddev->raid_disks);
rdev_for_each(rdev, mddev) {
disk_stack_limits(mddev->gendisk, rdev->bdev,
rdev->data_offset << 9);
if (blk_queue_discard(bdev_get_queue(rdev->bdev)))
discard_supported = true;
}
if (!discard_supported)
queue_flag_clear_unlocked(QUEUE_FLAG_DISCARD, mddev->queue);
else
queue_flag_set_unlocked(QUEUE_FLAG_DISCARD, mddev->queue);
}
/* calculate array device size */
md_set_array_sectors(mddev, raid0_size(mddev, 0, 0));
printk(KERN_INFO "md/raid0:%s: md_size is %llu sectors.\n",
mdname(mddev),
(unsigned long long)mddev->array_sectors);
if (mddev->queue) {
/* calculate the max read-ahead size.
* For read-ahead of large files to be effective, we need to
* readahead at least twice a whole stripe. i.e. number of devices
* multiplied by chunk size times 2.
* If an individual device has an ra_pages greater than the
* chunk size, then we will not drive that device as hard as it
* wants. We consider this a configuration error: a larger
* chunksize should be used in that case.
*/
int stripe = mddev->raid_disks *
(mddev->chunk_sectors << 9) / PAGE_SIZE;
if (mddev->queue->backing_dev_info.ra_pages < 2* stripe)
mddev->queue->backing_dev_info.ra_pages = 2* stripe;
}
dump_zones(mddev);
ret = md_integrity_register(mddev);
return ret;
}
static void raid0_free(struct mddev *mddev, void *priv)
{
struct r0conf *conf = priv;
kfree(conf->strip_zone);
kfree(conf->devlist);
kfree(conf);
}
/*
* Is io distribute over 1 or more chunks ?
*/
static inline int is_io_in_chunk_boundary(struct mddev *mddev,
unsigned int chunk_sects, struct bio *bio)
{
if (likely(is_power_of_2(chunk_sects))) {
return chunk_sects >=
((bio->bi_iter.bi_sector & (chunk_sects-1))
+ bio_sectors(bio));
} else{
sector_t sector = bio->bi_iter.bi_sector;
return chunk_sects >= (sector_div(sector, chunk_sects)
+ bio_sectors(bio));
}
}
static void raid0_make_request(struct mddev *mddev, struct bio *bio)
{
struct strip_zone *zone;
struct md_rdev *tmp_dev;
struct bio *split;
if (unlikely(bio->bi_opf & REQ_PREFLUSH)) {
md_flush_request(mddev, bio);
return;
}
do {
sector_t sector = bio->bi_iter.bi_sector;
unsigned chunk_sects = mddev->chunk_sectors;
unsigned sectors = chunk_sects -
(likely(is_power_of_2(chunk_sects))
? (sector & (chunk_sects-1))
: sector_div(sector, chunk_sects));
/* Restore due to sector_div */
sector = bio->bi_iter.bi_sector;
if (sectors < bio_sectors(bio)) {
split = bio_split(bio, sectors, GFP_NOIO, fs_bio_set);
bio_chain(split, bio);
} else {
split = bio;
}
zone = find_zone(mddev->private, &sector);
tmp_dev = map_sector(mddev, zone, sector, &sector);
split->bi_bdev = tmp_dev->bdev;
split->bi_iter.bi_sector = sector + zone->dev_start +
tmp_dev->data_offset;
if (unlikely((bio_op(split) == REQ_OP_DISCARD) &&
!blk_queue_discard(bdev_get_queue(split->bi_bdev)))) {
/* Just ignore it */
bio_endio(split);
} else
generic_make_request(split);
} while (split != bio);
}
static void raid0_status(struct seq_file *seq, struct mddev *mddev)
{
seq_printf(seq, " %dk chunks", mddev->chunk_sectors / 2);
return;
}
static void *raid0_takeover_raid45(struct mddev *mddev)
{
struct md_rdev *rdev;
struct r0conf *priv_conf;
if (mddev->degraded != 1) {
printk(KERN_ERR "md/raid0:%s: raid5 must be degraded! Degraded disks: %d\n",
mdname(mddev),
mddev->degraded);
return ERR_PTR(-EINVAL);
}
rdev_for_each(rdev, mddev) {
/* check slot number for a disk */
if (rdev->raid_disk == mddev->raid_disks-1) {
printk(KERN_ERR "md/raid0:%s: raid5 must have missing parity disk!\n",
mdname(mddev));
return ERR_PTR(-EINVAL);
}
rdev->sectors = mddev->dev_sectors;
}
/* Set new parameters */
mddev->new_level = 0;
mddev->new_layout = 0;
mddev->new_chunk_sectors = mddev->chunk_sectors;
mddev->raid_disks--;
mddev->delta_disks = -1;
/* make sure it will be not marked as dirty */
mddev->recovery_cp = MaxSector;
create_strip_zones(mddev, &priv_conf);
return priv_conf;
}
static void *raid0_takeover_raid10(struct mddev *mddev)
{
struct r0conf *priv_conf;
/* Check layout:
* - far_copies must be 1
* - near_copies must be 2
* - disks number must be even
* - all mirrors must be already degraded
*/
if (mddev->layout != ((1 << 8) + 2)) {
printk(KERN_ERR "md/raid0:%s:: Raid0 cannot takeover layout: 0x%x\n",
mdname(mddev),
mddev->layout);
return ERR_PTR(-EINVAL);
}
if (mddev->raid_disks & 1) {
printk(KERN_ERR "md/raid0:%s: Raid0 cannot takeover Raid10 with odd disk number.\n",
mdname(mddev));
return ERR_PTR(-EINVAL);
}
if (mddev->degraded != (mddev->raid_disks>>1)) {
printk(KERN_ERR "md/raid0:%s: All mirrors must be already degraded!\n",
mdname(mddev));
return ERR_PTR(-EINVAL);
}
/* Set new parameters */
mddev->new_level = 0;
mddev->new_layout = 0;
mddev->new_chunk_sectors = mddev->chunk_sectors;
mddev->delta_disks = - mddev->raid_disks / 2;
mddev->raid_disks += mddev->delta_disks;
mddev->degraded = 0;
/* make sure it will be not marked as dirty */
mddev->recovery_cp = MaxSector;
create_strip_zones(mddev, &priv_conf);
return priv_conf;
}
static void *raid0_takeover_raid1(struct mddev *mddev)
{
struct r0conf *priv_conf;
int chunksect;
/* Check layout:
* - (N - 1) mirror drives must be already faulty
*/
if ((mddev->raid_disks - 1) != mddev->degraded) {
printk(KERN_ERR "md/raid0:%s: (N - 1) mirrors drives must be already faulty!\n",
mdname(mddev));
return ERR_PTR(-EINVAL);
}
/*
* a raid1 doesn't have the notion of chunk size, so
* figure out the largest suitable size we can use.
*/
chunksect = 64 * 2; /* 64K by default */
/* The array must be an exact multiple of chunksize */
while (chunksect && (mddev->array_sectors & (chunksect - 1)))
chunksect >>= 1;
if ((chunksect << 9) < PAGE_SIZE)
/* array size does not allow a suitable chunk size */
return ERR_PTR(-EINVAL);
/* Set new parameters */
mddev->new_level = 0;
mddev->new_layout = 0;
mddev->new_chunk_sectors = chunksect;
mddev->chunk_sectors = chunksect;
mddev->delta_disks = 1 - mddev->raid_disks;
mddev->raid_disks = 1;
/* make sure it will be not marked as dirty */
mddev->recovery_cp = MaxSector;
create_strip_zones(mddev, &priv_conf);
return priv_conf;
}
static void *raid0_takeover(struct mddev *mddev)
{
/* raid0 can take over:
* raid4 - if all data disks are active.
* raid5 - providing it is Raid4 layout and one disk is faulty
* raid10 - assuming we have all necessary active disks
* raid1 - with (N -1) mirror drives faulty
*/
if (mddev->bitmap) {
printk(KERN_ERR "md/raid0: %s: cannot takeover array with bitmap\n",
mdname(mddev));
return ERR_PTR(-EBUSY);
}
if (mddev->level == 4)
return raid0_takeover_raid45(mddev);
if (mddev->level == 5) {
if (mddev->layout == ALGORITHM_PARITY_N)
return raid0_takeover_raid45(mddev);
printk(KERN_ERR "md/raid0:%s: Raid can only takeover Raid5 with layout: %d\n",
mdname(mddev), ALGORITHM_PARITY_N);
}
if (mddev->level == 10)
return raid0_takeover_raid10(mddev);
if (mddev->level == 1)
return raid0_takeover_raid1(mddev);
printk(KERN_ERR "Takeover from raid%i to raid0 not supported\n",
mddev->level);
return ERR_PTR(-EINVAL);
}
static void raid0_quiesce(struct mddev *mddev, int state)
{
}
static struct md_personality raid0_personality=
{
.name = "raid0",
.level = 0,
.owner = THIS_MODULE,
.make_request = raid0_make_request,
.run = raid0_run,
.free = raid0_free,
.status = raid0_status,
.size = raid0_size,
.takeover = raid0_takeover,
.quiesce = raid0_quiesce,
.congested = raid0_congested,
};
static int __init raid0_init (void)
{
return register_md_personality (&raid0_personality);
}
static void raid0_exit (void)
{
unregister_md_personality (&raid0_personality);
}
module_init(raid0_init);
module_exit(raid0_exit);
MODULE_LICENSE("GPL");
MODULE_DESCRIPTION("RAID0 (striping) personality for MD");
MODULE_ALIAS("md-personality-2"); /* RAID0 */
MODULE_ALIAS("md-raid0");
MODULE_ALIAS("md-level-0");