kernel-fxtec-pro1x/drivers/md/raid0.c

746 lines
20 KiB
C
Raw Normal View History

/*
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 cleanup: Update gfp.h and slab.h includes to prepare for breaking implicit slab.h inclusion from percpu.h percpu.h is included by sched.h and module.h and thus ends up being included when building most .c files. percpu.h includes slab.h which in turn includes gfp.h making everything defined by the two files universally available and complicating inclusion dependencies. percpu.h -> slab.h dependency is about to be removed. Prepare for this change by updating users of gfp and slab facilities include those headers directly instead of assuming availability. As this conversion needs to touch large number of source files, the following script is used as the basis of conversion. http://userweb.kernel.org/~tj/misc/slabh-sweep.py The script does the followings. * Scan files for gfp and slab usages and update includes such that only the necessary includes are there. ie. if only gfp is used, gfp.h, if slab is used, slab.h. * When the script inserts a new include, it looks at the include blocks and try to put the new include such that its order conforms to its surrounding. It's put in the include block which contains core kernel includes, in the same order that the rest are ordered - alphabetical, Christmas tree, rev-Xmas-tree or at the end if there doesn't seem to be any matching order. * If the script can't find a place to put a new include (mostly because the file doesn't have fitting include block), it prints out an error message indicating which .h file needs to be added to the file. The conversion was done in the following steps. 1. The initial automatic conversion of all .c files updated slightly over 4000 files, deleting around 700 includes and adding ~480 gfp.h and ~3000 slab.h inclusions. The script emitted errors for ~400 files. 2. Each error was manually checked. Some didn't need the inclusion, some needed manual addition while adding it to implementation .h or embedding .c file was more appropriate for others. This step added inclusions to around 150 files. 3. The script was run again and the output was compared to the edits from #2 to make sure no file was left behind. 4. Several build tests were done and a couple of problems were fixed. e.g. lib/decompress_*.c used malloc/free() wrappers around slab APIs requiring slab.h to be added manually. 5. The script was run on all .h files but without automatically editing them as sprinkling gfp.h and slab.h inclusions around .h files could easily lead to inclusion dependency hell. Most gfp.h inclusion directives were ignored as stuff from gfp.h was usually wildly available and often used in preprocessor macros. Each slab.h inclusion directive was examined and added manually as necessary. 6. percpu.h was updated not to include slab.h. 7. Build test were done on the following configurations and failures were fixed. CONFIG_GCOV_KERNEL was turned off for all tests (as my distributed build env didn't work with gcov compiles) and a few more options had to be turned off depending on archs to make things build (like ipr on powerpc/64 which failed due to missing writeq). * x86 and x86_64 UP and SMP allmodconfig and a custom test config. * powerpc and powerpc64 SMP allmodconfig * sparc and sparc64 SMP allmodconfig * ia64 SMP allmodconfig * s390 SMP allmodconfig * alpha SMP allmodconfig * um on x86_64 SMP allmodconfig 8. percpu.h modifications were reverted so that it could be applied as a separate patch and serve as bisection point. Given the fact that I had only a couple of failures from tests on step 6, I'm fairly confident about the coverage of this conversion patch. If there is a breakage, it's likely to be something in one of the arch headers which should be easily discoverable easily on most builds of the specific arch. Signed-off-by: Tejun Heo <tj@kernel.org> Guess-its-ok-by: Christoph Lameter <cl@linux-foundation.org> Cc: Ingo Molnar <mingo@redhat.com> Cc: Lee Schermerhorn <Lee.Schermerhorn@hp.com>
2010-03-24 02:04:11 -06:00
#include <linux/slab.h>
#include "md.h"
#include "raid0.h"
#include "raid5.h"
static int raid0_congested(void *data, int bits)
{
struct mddev *mddev = data;
struct r0conf *conf = mddev->private;
struct md_rdev **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(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;
}
printk(KERN_INFO "\n");
}
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);
bool discard_supported = false;
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;
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);
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;
disk_stack_limits(mddev->gendisk, rdev1->bdev,
rdev1->data_offset << 9);
if (rdev1->bdev->bd_disk->queue->merge_bvec_fn)
conf->has_merge_bvec = 1;
if (!smallest || (rdev1->sectors < smallest->sectors))
smallest = rdev1;
cnt++;
if (blk_queue_discard(bdev_get_queue(rdev1->bdev)))
discard_supported = true;
}
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);
}
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
*/
if ((mddev->chunk_sectors << 9) % queue_logical_block_size(mddev->queue)) {
printk(KERN_ERR "md/raid0:%s: chunk_size of %d not valid\n",
mdname(mddev),
mddev->chunk_sectors << 9);
goto abort;
}
blk_queue_io_min(mddev->queue, mddev->chunk_sectors << 9);
blk_queue_io_opt(mddev->queue,
(mddev->chunk_sectors << 9) * mddev->raid_disks);
if (!discard_supported)
queue_flag_clear_unlocked(QUEUE_FLAG_DISCARD, mddev->queue);
else
queue_flag_set_unlocked(QUEUE_FLAG_DISCARD, mddev->queue);
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 perfromance
*/
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)];
}
/**
* raid0_mergeable_bvec -- tell bio layer if two requests can be merged
* @q: request queue
* @bvm: properties of new bio
* @biovec: the request that could be merged to it.
*
* Return amount of bytes we can accept at this offset
*/
static int raid0_mergeable_bvec(struct request_queue *q,
struct bvec_merge_data *bvm,
struct bio_vec *biovec)
{
struct mddev *mddev = q->queuedata;
struct r0conf *conf = mddev->private;
sector_t sector = bvm->bi_sector + get_start_sect(bvm->bi_bdev);
sector_t sector_offset = sector;
int max;
unsigned int chunk_sectors = mddev->chunk_sectors;
unsigned int bio_sectors = bvm->bi_size >> 9;
struct strip_zone *zone;
struct md_rdev *rdev;
struct request_queue *subq;
if (is_power_of_2(chunk_sectors))
max = (chunk_sectors - ((sector & (chunk_sectors-1))
+ bio_sectors)) << 9;
else
max = (chunk_sectors - (sector_div(sector, chunk_sectors)
+ bio_sectors)) << 9;
if (max < 0)
max = 0; /* bio_add cannot handle a negative return */
if (max <= biovec->bv_len && bio_sectors == 0)
return biovec->bv_len;
if (max < biovec->bv_len)
/* too small already, no need to check further */
return max;
if (!conf->has_merge_bvec)
return max;
/* May need to check subordinate device */
sector = sector_offset;
zone = find_zone(mddev->private, &sector_offset);
rdev = map_sector(mddev, zone, sector, &sector_offset);
subq = bdev_get_queue(rdev->bdev);
if (subq->merge_bvec_fn) {
bvm->bi_bdev = rdev->bdev;
bvm->bi_sector = sector_offset + zone->dev_start +
rdev->data_offset;
return min(max, subq->merge_bvec_fn(subq, bvm, biovec));
} else
return max;
}
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 int raid0_stop(struct mddev *mddev);
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;
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);
/* 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;
/* 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);
/* 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;
}
blk_queue_merge_bvec(mddev->queue, raid0_mergeable_bvec);
dump_zones(mddev);
ret = md_integrity_register(mddev);
if (ret)
raid0_stop(mddev);
return ret;
}
static int raid0_stop(struct mddev *mddev)
{
struct r0conf *conf = mddev->private;
blk_sync_queue(mddev->queue); /* the unplug fn references 'conf'*/
kfree(conf->strip_zone);
kfree(conf->devlist);
kfree(conf);
mddev->private = NULL;
return 0;
}
/*
* 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))) {
block: Abstract out bvec iterator Immutable biovecs are going to require an explicit iterator. To implement immutable bvecs, a later patch is going to add a bi_bvec_done member to this struct; for now, this patch effectively just renames things. Signed-off-by: Kent Overstreet <kmo@daterainc.com> Cc: Jens Axboe <axboe@kernel.dk> Cc: Geert Uytterhoeven <geert@linux-m68k.org> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: Paul Mackerras <paulus@samba.org> Cc: "Ed L. Cashin" <ecashin@coraid.com> Cc: Nick Piggin <npiggin@kernel.dk> Cc: Lars Ellenberg <drbd-dev@lists.linbit.com> Cc: Jiri Kosina <jkosina@suse.cz> Cc: Matthew Wilcox <willy@linux.intel.com> Cc: Geoff Levand <geoff@infradead.org> Cc: Yehuda Sadeh <yehuda@inktank.com> Cc: Sage Weil <sage@inktank.com> Cc: Alex Elder <elder@inktank.com> Cc: ceph-devel@vger.kernel.org Cc: Joshua Morris <josh.h.morris@us.ibm.com> Cc: Philip Kelleher <pjk1939@linux.vnet.ibm.com> Cc: Rusty Russell <rusty@rustcorp.com.au> Cc: "Michael S. Tsirkin" <mst@redhat.com> Cc: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com> Cc: Jeremy Fitzhardinge <jeremy@goop.org> Cc: Neil Brown <neilb@suse.de> Cc: Alasdair Kergon <agk@redhat.com> Cc: Mike Snitzer <snitzer@redhat.com> Cc: dm-devel@redhat.com Cc: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: Heiko Carstens <heiko.carstens@de.ibm.com> Cc: linux390@de.ibm.com Cc: Boaz Harrosh <bharrosh@panasas.com> Cc: Benny Halevy <bhalevy@tonian.com> Cc: "James E.J. Bottomley" <JBottomley@parallels.com> Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Cc: "Nicholas A. Bellinger" <nab@linux-iscsi.org> Cc: Alexander Viro <viro@zeniv.linux.org.uk> Cc: Chris Mason <chris.mason@fusionio.com> Cc: "Theodore Ts'o" <tytso@mit.edu> Cc: Andreas Dilger <adilger.kernel@dilger.ca> Cc: Jaegeuk Kim <jaegeuk.kim@samsung.com> Cc: Steven Whitehouse <swhiteho@redhat.com> Cc: Dave Kleikamp <shaggy@kernel.org> Cc: Joern Engel <joern@logfs.org> Cc: Prasad Joshi <prasadjoshi.linux@gmail.com> Cc: Trond Myklebust <Trond.Myklebust@netapp.com> Cc: KONISHI Ryusuke <konishi.ryusuke@lab.ntt.co.jp> Cc: Mark Fasheh <mfasheh@suse.com> Cc: Joel Becker <jlbec@evilplan.org> Cc: Ben Myers <bpm@sgi.com> Cc: xfs@oss.sgi.com Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Len Brown <len.brown@intel.com> Cc: Pavel Machek <pavel@ucw.cz> Cc: "Rafael J. Wysocki" <rjw@sisk.pl> Cc: Herton Ronaldo Krzesinski <herton.krzesinski@canonical.com> Cc: Ben Hutchings <ben@decadent.org.uk> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Guo Chao <yan@linux.vnet.ibm.com> Cc: Tejun Heo <tj@kernel.org> Cc: Asai Thambi S P <asamymuthupa@micron.com> Cc: Selvan Mani <smani@micron.com> Cc: Sam Bradshaw <sbradshaw@micron.com> Cc: Wei Yongjun <yongjun_wei@trendmicro.com.cn> Cc: "Roger Pau Monné" <roger.pau@citrix.com> Cc: Jan Beulich <jbeulich@suse.com> Cc: Stefano Stabellini <stefano.stabellini@eu.citrix.com> Cc: Ian Campbell <Ian.Campbell@citrix.com> Cc: Sebastian Ott <sebott@linux.vnet.ibm.com> Cc: Christian Borntraeger <borntraeger@de.ibm.com> Cc: Minchan Kim <minchan@kernel.org> Cc: Jiang Liu <jiang.liu@huawei.com> Cc: Nitin Gupta <ngupta@vflare.org> Cc: Jerome Marchand <jmarchand@redhat.com> Cc: Joe Perches <joe@perches.com> Cc: Peng Tao <tao.peng@emc.com> Cc: Andy Adamson <andros@netapp.com> Cc: fanchaoting <fanchaoting@cn.fujitsu.com> Cc: Jie Liu <jeff.liu@oracle.com> Cc: Sunil Mushran <sunil.mushran@gmail.com> Cc: "Martin K. Petersen" <martin.petersen@oracle.com> Cc: Namjae Jeon <namjae.jeon@samsung.com> Cc: Pankaj Kumar <pankaj.km@samsung.com> Cc: Dan Magenheimer <dan.magenheimer@oracle.com> Cc: Mel Gorman <mgorman@suse.de>6
2013-10-11 16:44:27 -06:00
return chunk_sects >=
((bio->bi_iter.bi_sector & (chunk_sects-1))
+ bio_sectors(bio));
} else{
block: Abstract out bvec iterator Immutable biovecs are going to require an explicit iterator. To implement immutable bvecs, a later patch is going to add a bi_bvec_done member to this struct; for now, this patch effectively just renames things. Signed-off-by: Kent Overstreet <kmo@daterainc.com> Cc: Jens Axboe <axboe@kernel.dk> Cc: Geert Uytterhoeven <geert@linux-m68k.org> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: Paul Mackerras <paulus@samba.org> Cc: "Ed L. Cashin" <ecashin@coraid.com> Cc: Nick Piggin <npiggin@kernel.dk> Cc: Lars Ellenberg <drbd-dev@lists.linbit.com> Cc: Jiri Kosina <jkosina@suse.cz> Cc: Matthew Wilcox <willy@linux.intel.com> Cc: Geoff Levand <geoff@infradead.org> Cc: Yehuda Sadeh <yehuda@inktank.com> Cc: Sage Weil <sage@inktank.com> Cc: Alex Elder <elder@inktank.com> Cc: ceph-devel@vger.kernel.org Cc: Joshua Morris <josh.h.morris@us.ibm.com> Cc: Philip Kelleher <pjk1939@linux.vnet.ibm.com> Cc: Rusty Russell <rusty@rustcorp.com.au> Cc: "Michael S. Tsirkin" <mst@redhat.com> Cc: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com> Cc: Jeremy Fitzhardinge <jeremy@goop.org> Cc: Neil Brown <neilb@suse.de> Cc: Alasdair Kergon <agk@redhat.com> Cc: Mike Snitzer <snitzer@redhat.com> Cc: dm-devel@redhat.com Cc: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: Heiko Carstens <heiko.carstens@de.ibm.com> Cc: linux390@de.ibm.com Cc: Boaz Harrosh <bharrosh@panasas.com> Cc: Benny Halevy <bhalevy@tonian.com> Cc: "James E.J. Bottomley" <JBottomley@parallels.com> Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Cc: "Nicholas A. Bellinger" <nab@linux-iscsi.org> Cc: Alexander Viro <viro@zeniv.linux.org.uk> Cc: Chris Mason <chris.mason@fusionio.com> Cc: "Theodore Ts'o" <tytso@mit.edu> Cc: Andreas Dilger <adilger.kernel@dilger.ca> Cc: Jaegeuk Kim <jaegeuk.kim@samsung.com> Cc: Steven Whitehouse <swhiteho@redhat.com> Cc: Dave Kleikamp <shaggy@kernel.org> Cc: Joern Engel <joern@logfs.org> Cc: Prasad Joshi <prasadjoshi.linux@gmail.com> Cc: Trond Myklebust <Trond.Myklebust@netapp.com> Cc: KONISHI Ryusuke <konishi.ryusuke@lab.ntt.co.jp> Cc: Mark Fasheh <mfasheh@suse.com> Cc: Joel Becker <jlbec@evilplan.org> Cc: Ben Myers <bpm@sgi.com> Cc: xfs@oss.sgi.com Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Len Brown <len.brown@intel.com> Cc: Pavel Machek <pavel@ucw.cz> Cc: "Rafael J. Wysocki" <rjw@sisk.pl> Cc: Herton Ronaldo Krzesinski <herton.krzesinski@canonical.com> Cc: Ben Hutchings <ben@decadent.org.uk> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Guo Chao <yan@linux.vnet.ibm.com> Cc: Tejun Heo <tj@kernel.org> Cc: Asai Thambi S P <asamymuthupa@micron.com> Cc: Selvan Mani <smani@micron.com> Cc: Sam Bradshaw <sbradshaw@micron.com> Cc: Wei Yongjun <yongjun_wei@trendmicro.com.cn> Cc: "Roger Pau Monné" <roger.pau@citrix.com> Cc: Jan Beulich <jbeulich@suse.com> Cc: Stefano Stabellini <stefano.stabellini@eu.citrix.com> Cc: Ian Campbell <Ian.Campbell@citrix.com> Cc: Sebastian Ott <sebott@linux.vnet.ibm.com> Cc: Christian Borntraeger <borntraeger@de.ibm.com> Cc: Minchan Kim <minchan@kernel.org> Cc: Jiang Liu <jiang.liu@huawei.com> Cc: Nitin Gupta <ngupta@vflare.org> Cc: Jerome Marchand <jmarchand@redhat.com> Cc: Joe Perches <joe@perches.com> Cc: Peng Tao <tao.peng@emc.com> Cc: Andy Adamson <andros@netapp.com> Cc: fanchaoting <fanchaoting@cn.fujitsu.com> Cc: Jie Liu <jeff.liu@oracle.com> Cc: Sunil Mushran <sunil.mushran@gmail.com> Cc: "Martin K. Petersen" <martin.petersen@oracle.com> Cc: Namjae Jeon <namjae.jeon@samsung.com> Cc: Pankaj Kumar <pankaj.km@samsung.com> Cc: Dan Magenheimer <dan.magenheimer@oracle.com> Cc: Mel Gorman <mgorman@suse.de>6
2013-10-11 16:44:27 -06:00
sector_t sector = bio->bi_iter.bi_sector;
return chunk_sects >= (sector_div(sector, chunk_sects)
+ bio_sectors(bio));
}
}
Merge branch 'for-3.2/core' of git://git.kernel.dk/linux-block * 'for-3.2/core' of git://git.kernel.dk/linux-block: (29 commits) block: don't call blk_drain_queue() if elevator is not up blk-throttle: use queue_is_locked() instead of lockdep_is_held() blk-throttle: Take blkcg->lock while traversing blkcg->policy_list blk-throttle: Free up policy node associated with deleted rule block: warn if tag is greater than real_max_depth. block: make gendisk hold a reference to its queue blk-flush: move the queue kick into blk-flush: fix invalid BUG_ON in blk_insert_flush block: Remove the control of complete cpu from bio. block: fix a typo in the blk-cgroup.h file block: initialize the bounce pool if high memory may be added later block: fix request_queue lifetime handling by making blk_queue_cleanup() properly shutdown block: drop @tsk from attempt_plug_merge() and explain sync rules block: make get_request[_wait]() fail if queue is dead block: reorganize throtl_get_tg() and blk_throtl_bio() block: reorganize queue draining block: drop unnecessary blk_get/put_queue() in scsi_cmd_ioctl() and blk_get_tg() block: pass around REQ_* flags instead of broken down booleans during request alloc/free block: move blk_throtl prototypes to block/blk.h block: fix genhd refcounting in blkio_policy_parse_and_set() ... Fix up trivial conflicts due to "mddev_t" -> "struct mddev" conversion and making the request functions be of type "void" instead of "int" in - drivers/md/{faulty.c,linear.c,md.c,md.h,multipath.c,raid0.c,raid1.c,raid10.c,raid5.c} - drivers/staging/zram/zram_drv.c
2011-11-04 18:06:58 -06:00
static void raid0_make_request(struct mddev *mddev, struct bio *bio)
{
struct strip_zone *zone;
struct md_rdev *tmp_dev;
struct bio *split;
2010-09-03 03:56:18 -06:00
if (unlikely(bio->bi_rw & REQ_FLUSH)) {
md_flush_request(mddev, bio);
return;
}
do {
block: Abstract out bvec iterator Immutable biovecs are going to require an explicit iterator. To implement immutable bvecs, a later patch is going to add a bi_bvec_done member to this struct; for now, this patch effectively just renames things. Signed-off-by: Kent Overstreet <kmo@daterainc.com> Cc: Jens Axboe <axboe@kernel.dk> Cc: Geert Uytterhoeven <geert@linux-m68k.org> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: Paul Mackerras <paulus@samba.org> Cc: "Ed L. Cashin" <ecashin@coraid.com> Cc: Nick Piggin <npiggin@kernel.dk> Cc: Lars Ellenberg <drbd-dev@lists.linbit.com> Cc: Jiri Kosina <jkosina@suse.cz> Cc: Matthew Wilcox <willy@linux.intel.com> Cc: Geoff Levand <geoff@infradead.org> Cc: Yehuda Sadeh <yehuda@inktank.com> Cc: Sage Weil <sage@inktank.com> Cc: Alex Elder <elder@inktank.com> Cc: ceph-devel@vger.kernel.org Cc: Joshua Morris <josh.h.morris@us.ibm.com> Cc: Philip Kelleher <pjk1939@linux.vnet.ibm.com> Cc: Rusty Russell <rusty@rustcorp.com.au> Cc: "Michael S. Tsirkin" <mst@redhat.com> Cc: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com> Cc: Jeremy Fitzhardinge <jeremy@goop.org> Cc: Neil Brown <neilb@suse.de> Cc: Alasdair Kergon <agk@redhat.com> Cc: Mike Snitzer <snitzer@redhat.com> Cc: dm-devel@redhat.com Cc: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: Heiko Carstens <heiko.carstens@de.ibm.com> Cc: linux390@de.ibm.com Cc: Boaz Harrosh <bharrosh@panasas.com> Cc: Benny Halevy <bhalevy@tonian.com> Cc: "James E.J. Bottomley" <JBottomley@parallels.com> Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Cc: "Nicholas A. Bellinger" <nab@linux-iscsi.org> Cc: Alexander Viro <viro@zeniv.linux.org.uk> Cc: Chris Mason <chris.mason@fusionio.com> Cc: "Theodore Ts'o" <tytso@mit.edu> Cc: Andreas Dilger <adilger.kernel@dilger.ca> Cc: Jaegeuk Kim <jaegeuk.kim@samsung.com> Cc: Steven Whitehouse <swhiteho@redhat.com> Cc: Dave Kleikamp <shaggy@kernel.org> Cc: Joern Engel <joern@logfs.org> Cc: Prasad Joshi <prasadjoshi.linux@gmail.com> Cc: Trond Myklebust <Trond.Myklebust@netapp.com> Cc: KONISHI Ryusuke <konishi.ryusuke@lab.ntt.co.jp> Cc: Mark Fasheh <mfasheh@suse.com> Cc: Joel Becker <jlbec@evilplan.org> Cc: Ben Myers <bpm@sgi.com> Cc: xfs@oss.sgi.com Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Len Brown <len.brown@intel.com> Cc: Pavel Machek <pavel@ucw.cz> Cc: "Rafael J. Wysocki" <rjw@sisk.pl> Cc: Herton Ronaldo Krzesinski <herton.krzesinski@canonical.com> Cc: Ben Hutchings <ben@decadent.org.uk> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Guo Chao <yan@linux.vnet.ibm.com> Cc: Tejun Heo <tj@kernel.org> Cc: Asai Thambi S P <asamymuthupa@micron.com> Cc: Selvan Mani <smani@micron.com> Cc: Sam Bradshaw <sbradshaw@micron.com> Cc: Wei Yongjun <yongjun_wei@trendmicro.com.cn> Cc: "Roger Pau Monné" <roger.pau@citrix.com> Cc: Jan Beulich <jbeulich@suse.com> Cc: Stefano Stabellini <stefano.stabellini@eu.citrix.com> Cc: Ian Campbell <Ian.Campbell@citrix.com> Cc: Sebastian Ott <sebott@linux.vnet.ibm.com> Cc: Christian Borntraeger <borntraeger@de.ibm.com> Cc: Minchan Kim <minchan@kernel.org> Cc: Jiang Liu <jiang.liu@huawei.com> Cc: Nitin Gupta <ngupta@vflare.org> Cc: Jerome Marchand <jmarchand@redhat.com> Cc: Joe Perches <joe@perches.com> Cc: Peng Tao <tao.peng@emc.com> Cc: Andy Adamson <andros@netapp.com> Cc: fanchaoting <fanchaoting@cn.fujitsu.com> Cc: Jie Liu <jeff.liu@oracle.com> Cc: Sunil Mushran <sunil.mushran@gmail.com> Cc: "Martin K. Petersen" <martin.petersen@oracle.com> Cc: Namjae Jeon <namjae.jeon@samsung.com> Cc: Pankaj Kumar <pankaj.km@samsung.com> Cc: Dan Magenheimer <dan.magenheimer@oracle.com> Cc: Mel Gorman <mgorman@suse.de>6
2013-10-11 16:44:27 -06:00
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));
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((split->bi_rw & REQ_DISCARD) &&
!blk_queue_discard(bdev_get_queue(split->bi_bdev)))) {
/* Just ignore it */
bio_endio(split, 0);
} 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 takover 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 takover 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->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,
.stop = raid0_stop,
.status = raid0_status,
.size = raid0_size,
.takeover = raid0_takeover,
.quiesce = raid0_quiesce,
};
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");