linux-sg2042/drivers/md/multipath.c

593 lines
15 KiB
C
Raw Normal View History

/*
* multipath.c : Multiple Devices driver for Linux
*
* Copyright (C) 1999, 2000, 2001 Ingo Molnar, Red Hat
*
* Copyright (C) 1996, 1997, 1998 Ingo Molnar, Miguel de Icaza, Gadi Oxman
*
* MULTIPATH management functions.
*
* derived from raid1.c.
*
* 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/raid/md_u.h>
#include <linux/seq_file.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 16:04:11 +08:00
#include <linux/slab.h>
#include "md.h"
#include "multipath.h"
#define MAX_WORK_PER_DISK 128
#define NR_RESERVED_BUFS 32
static int multipath_map (multipath_conf_t *conf)
{
int i, disks = conf->raid_disks;
/*
* Later we do read balancing on the read side
* now we use the first available disk.
*/
rcu_read_lock();
for (i = 0; i < disks; i++) {
mdk_rdev_t *rdev = rcu_dereference(conf->multipaths[i].rdev);
if (rdev && test_bit(In_sync, &rdev->flags)) {
atomic_inc(&rdev->nr_pending);
rcu_read_unlock();
return i;
}
}
rcu_read_unlock();
printk(KERN_ERR "multipath_map(): no more operational IO paths?\n");
return (-1);
}
static void multipath_reschedule_retry (struct multipath_bh *mp_bh)
{
unsigned long flags;
mddev_t *mddev = mp_bh->mddev;
multipath_conf_t *conf = mddev->private;
spin_lock_irqsave(&conf->device_lock, flags);
list_add(&mp_bh->retry_list, &conf->retry_list);
spin_unlock_irqrestore(&conf->device_lock, flags);
md_wakeup_thread(mddev->thread);
}
/*
* multipath_end_bh_io() is called when we have finished servicing a multipathed
* operation and are ready to return a success/failure code to the buffer
* cache layer.
*/
static void multipath_end_bh_io (struct multipath_bh *mp_bh, int err)
{
struct bio *bio = mp_bh->master_bio;
multipath_conf_t *conf = mp_bh->mddev->private;
bio_endio(bio, err);
mempool_free(mp_bh, conf->pool);
}
static void multipath_end_request(struct bio *bio, int error)
{
int uptodate = test_bit(BIO_UPTODATE, &bio->bi_flags);
struct multipath_bh * mp_bh = (struct multipath_bh *)(bio->bi_private);
multipath_conf_t *conf = mp_bh->mddev->private;
mdk_rdev_t *rdev = conf->multipaths[mp_bh->path].rdev;
if (uptodate)
multipath_end_bh_io(mp_bh, 0);
else if (!bio_rw_flagged(bio, BIO_RW_AHEAD)) {
/*
* oops, IO error:
*/
char b[BDEVNAME_SIZE];
md_error (mp_bh->mddev, rdev);
printk(KERN_ERR "multipath: %s: rescheduling sector %llu\n",
bdevname(rdev->bdev,b),
(unsigned long long)bio->bi_sector);
multipath_reschedule_retry(mp_bh);
} else
multipath_end_bh_io(mp_bh, error);
rdev_dec_pending(rdev, conf->mddev);
}
static void unplug_slaves(mddev_t *mddev)
{
multipath_conf_t *conf = mddev->private;
int i;
rcu_read_lock();
for (i=0; i<mddev->raid_disks; i++) {
mdk_rdev_t *rdev = rcu_dereference(conf->multipaths[i].rdev);
if (rdev && !test_bit(Faulty, &rdev->flags)
&& atomic_read(&rdev->nr_pending)) {
struct request_queue *r_queue = bdev_get_queue(rdev->bdev);
atomic_inc(&rdev->nr_pending);
rcu_read_unlock();
blk_unplug(r_queue);
rdev_dec_pending(rdev, mddev);
rcu_read_lock();
}
}
rcu_read_unlock();
}
static void multipath_unplug(struct request_queue *q)
{
unplug_slaves(q->queuedata);
}
static int multipath_make_request (struct request_queue *q, struct bio * bio)
{
mddev_t *mddev = q->queuedata;
multipath_conf_t *conf = mddev->private;
struct multipath_bh * mp_bh;
struct multipath_info *multipath;
const int rw = bio_data_dir(bio);
int cpu;
if (unlikely(bio_rw_flagged(bio, BIO_RW_BARRIER))) {
md: support barrier requests on all personalities. Previously barriers were only supported on RAID1. This is because other levels requires synchronisation across all devices and so needed a different approach. Here is that approach. When a barrier arrives, we send a zero-length barrier to every active device. When that completes - and if the original request was not empty - we submit the barrier request itself (with the barrier flag cleared) and then submit a fresh load of zero length barriers. The barrier request itself is asynchronous, but any subsequent request will block until the barrier completes. The reason for clearing the barrier flag is that a barrier request is allowed to fail. If we pass a non-empty barrier through a striping raid level it is conceivable that part of it could succeed and part could fail. That would be way too hard to deal with. So if the first run of zero length barriers succeed, we assume all is sufficiently well that we send the request and ignore errors in the second run of barriers. RAID5 needs extra care as write requests may not have been submitted to the underlying devices yet. So we flush the stripe cache before proceeding with the barrier. Note that the second set of zero-length barriers are submitted immediately after the original request is submitted. Thus when a personality finds mddev->barrier to be set during make_request, it should not return from make_request until the corresponding per-device request(s) have been queued. That will be done in later patches. Signed-off-by: NeilBrown <neilb@suse.de> Reviewed-by: Andre Noll <maan@systemlinux.org>
2009-12-14 09:49:49 +08:00
md_barrier_request(mddev, bio);
return 0;
}
mp_bh = mempool_alloc(conf->pool, GFP_NOIO);
mp_bh->master_bio = bio;
mp_bh->mddev = mddev;
cpu = part_stat_lock();
part_stat_inc(cpu, &mddev->gendisk->part0, ios[rw]);
part_stat_add(cpu, &mddev->gendisk->part0, sectors[rw],
bio_sectors(bio));
part_stat_unlock();
mp_bh->path = multipath_map(conf);
if (mp_bh->path < 0) {
bio_endio(bio, -EIO);
mempool_free(mp_bh, conf->pool);
return 0;
}
multipath = conf->multipaths + mp_bh->path;
mp_bh->bio = *bio;
mp_bh->bio.bi_sector += multipath->rdev->data_offset;
mp_bh->bio.bi_bdev = multipath->rdev->bdev;
mp_bh->bio.bi_rw |= (1 << BIO_RW_FAILFAST_TRANSPORT);
mp_bh->bio.bi_end_io = multipath_end_request;
mp_bh->bio.bi_private = mp_bh;
generic_make_request(&mp_bh->bio);
return 0;
}
static void multipath_status (struct seq_file *seq, mddev_t *mddev)
{
multipath_conf_t *conf = mddev->private;
int i;
seq_printf (seq, " [%d/%d] [", conf->raid_disks,
conf->working_disks);
for (i = 0; i < conf->raid_disks; i++)
seq_printf (seq, "%s",
conf->multipaths[i].rdev &&
test_bit(In_sync, &conf->multipaths[i].rdev->flags) ? "U" : "_");
seq_printf (seq, "]");
}
static int multipath_congested(void *data, int bits)
{
mddev_t *mddev = data;
multipath_conf_t *conf = mddev->private;
int i, ret = 0;
if (mddev_congested(mddev, bits))
return 1;
rcu_read_lock();
for (i = 0; i < mddev->raid_disks ; i++) {
mdk_rdev_t *rdev = rcu_dereference(conf->multipaths[i].rdev);
if (rdev && !test_bit(Faulty, &rdev->flags)) {
struct request_queue *q = bdev_get_queue(rdev->bdev);
ret |= bdi_congested(&q->backing_dev_info, bits);
/* Just like multipath_map, we just check the
* first available device
*/
break;
}
}
rcu_read_unlock();
return ret;
}
/*
* Careful, this can execute in IRQ contexts as well!
*/
static void multipath_error (mddev_t *mddev, mdk_rdev_t *rdev)
{
multipath_conf_t *conf = mddev->private;
if (conf->working_disks <= 1) {
/*
* Uh oh, we can do nothing if this is our last path, but
* first check if this is a queued request for a device
* which has just failed.
*/
printk(KERN_ALERT
"multipath: only one IO path left and IO error.\n");
/* leave it active... it's all we have */
} else {
/*
* Mark disk as unusable
*/
if (!test_bit(Faulty, &rdev->flags)) {
char b[BDEVNAME_SIZE];
clear_bit(In_sync, &rdev->flags);
set_bit(Faulty, &rdev->flags);
set_bit(MD_CHANGE_DEVS, &mddev->flags);
conf->working_disks--;
mddev->degraded++;
printk(KERN_ALERT "multipath: IO failure on %s,"
" disabling IO path.\n"
"multipath: Operation continuing"
" on %d IO paths.\n",
bdevname (rdev->bdev,b),
conf->working_disks);
}
}
}
static void print_multipath_conf (multipath_conf_t *conf)
{
int i;
struct multipath_info *tmp;
printk("MULTIPATH conf printout:\n");
if (!conf) {
printk("(conf==NULL)\n");
return;
}
printk(" --- wd:%d rd:%d\n", conf->working_disks,
conf->raid_disks);
for (i = 0; i < conf->raid_disks; i++) {
char b[BDEVNAME_SIZE];
tmp = conf->multipaths + i;
if (tmp->rdev)
printk(" disk%d, o:%d, dev:%s\n",
i,!test_bit(Faulty, &tmp->rdev->flags),
bdevname(tmp->rdev->bdev,b));
}
}
static int multipath_add_disk(mddev_t *mddev, mdk_rdev_t *rdev)
{
multipath_conf_t *conf = mddev->private;
struct request_queue *q;
int err = -EEXIST;
int path;
struct multipath_info *p;
int first = 0;
int last = mddev->raid_disks - 1;
if (rdev->raid_disk >= 0)
first = last = rdev->raid_disk;
print_multipath_conf(conf);
for (path = first; path <= last; path++)
if ((p=conf->multipaths+path)->rdev == NULL) {
q = rdev->bdev->bd_disk->queue;
disk_stack_limits(mddev->gendisk, rdev->bdev,
rdev->data_offset << 9);
/* as we don't honour merge_bvec_fn, we must never risk
* violating it, so limit ->max_segments to one, lying
* within a single page.
* (Note: it is very unlikely that a device with
* merge_bvec_fn will be involved in multipath.)
*/
if (q->merge_bvec_fn) {
blk_queue_max_segments(mddev->queue, 1);
blk_queue_segment_boundary(mddev->queue,
PAGE_CACHE_SIZE - 1);
}
conf->working_disks++;
mddev->degraded--;
rdev->raid_disk = path;
set_bit(In_sync, &rdev->flags);
rcu_assign_pointer(p->rdev, rdev);
err = 0;
md_integrity_add_rdev(rdev, mddev);
break;
}
print_multipath_conf(conf);
return err;
}
static int multipath_remove_disk(mddev_t *mddev, int number)
{
multipath_conf_t *conf = mddev->private;
int err = 0;
mdk_rdev_t *rdev;
struct multipath_info *p = conf->multipaths + number;
print_multipath_conf(conf);
rdev = p->rdev;
if (rdev) {
if (test_bit(In_sync, &rdev->flags) ||
atomic_read(&rdev->nr_pending)) {
md: restart recovery cleanly after device failure. When we get any IO error during a recovery (rebuilding a spare), we abort the recovery and restart it. For RAID6 (and multi-drive RAID1) it may not be best to restart at the beginning: when multiple failures can be tolerated, the recovery may be able to continue and re-doing all that has already been done doesn't make sense. We already have the infrastructure to record where a recovery is up to and restart from there, but it is not being used properly. This is because: - We sometimes abort with MD_RECOVERY_ERR rather than just MD_RECOVERY_INTR, which causes the recovery not be be checkpointed. - We remove spares and then re-added them which loses important state information. The distinction between MD_RECOVERY_ERR and MD_RECOVERY_INTR really isn't needed. If there is an error, the relevant drive will be marked as Faulty, and that is enough to ensure correct handling of the error. So we first remove MD_RECOVERY_ERR, changing some of the uses of it to MD_RECOVERY_INTR. Then we cause the attempt to remove a non-faulty device from an array to fail (unless recovery is impossible as the array is too degraded). Then when remove_and_add_spares attempts to remove the devices on which recovery can continue, it will fail, they will remain in place, and recovery will continue on them as desired. Issue: If we are halfway through rebuilding a spare and another drive fails, and a new spare is immediately available, do we want to: 1/ complete the current rebuild, then go back and rebuild the new spare or 2/ restart the rebuild from the start and rebuild both devices in parallel. Both options can be argued for. The code currently takes option 2 as a/ this requires least code change b/ this results in a minimally-degraded array in minimal time. Cc: "Eivind Sarto" <ivan@kasenna.com> Signed-off-by: Neil Brown <neilb@suse.de> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-05-24 04:04:39 +08:00
printk(KERN_ERR "hot-remove-disk, slot %d is identified"
" but is still operational!\n", number);
err = -EBUSY;
goto abort;
}
p->rdev = NULL;
synchronize_rcu();
if (atomic_read(&rdev->nr_pending)) {
/* lost the race, try later */
err = -EBUSY;
p->rdev = rdev;
goto abort;
}
md_integrity_register(mddev);
}
abort:
print_multipath_conf(conf);
return err;
}
/*
* This is a kernel thread which:
*
* 1. Retries failed read operations on working multipaths.
* 2. Updates the raid superblock when problems encounter.
* 3. Performs writes following reads for array syncronising.
*/
static void multipathd (mddev_t *mddev)
{
struct multipath_bh *mp_bh;
struct bio *bio;
unsigned long flags;
multipath_conf_t *conf = mddev->private;
struct list_head *head = &conf->retry_list;
md_check_recovery(mddev);
for (;;) {
char b[BDEVNAME_SIZE];
spin_lock_irqsave(&conf->device_lock, flags);
if (list_empty(head))
break;
mp_bh = list_entry(head->prev, struct multipath_bh, retry_list);
list_del(head->prev);
spin_unlock_irqrestore(&conf->device_lock, flags);
bio = &mp_bh->bio;
bio->bi_sector = mp_bh->master_bio->bi_sector;
if ((mp_bh->path = multipath_map (conf))<0) {
printk(KERN_ALERT "multipath: %s: unrecoverable IO read"
" error for block %llu\n",
bdevname(bio->bi_bdev,b),
(unsigned long long)bio->bi_sector);
multipath_end_bh_io(mp_bh, -EIO);
} else {
printk(KERN_ERR "multipath: %s: redirecting sector %llu"
" to another IO path\n",
bdevname(bio->bi_bdev,b),
(unsigned long long)bio->bi_sector);
*bio = *(mp_bh->master_bio);
bio->bi_sector += conf->multipaths[mp_bh->path].rdev->data_offset;
bio->bi_bdev = conf->multipaths[mp_bh->path].rdev->bdev;
bio->bi_rw |= (1 << BIO_RW_FAILFAST_TRANSPORT);
bio->bi_end_io = multipath_end_request;
bio->bi_private = mp_bh;
generic_make_request(bio);
}
}
spin_unlock_irqrestore(&conf->device_lock, flags);
}
static sector_t multipath_size(mddev_t *mddev, sector_t sectors, int raid_disks)
{
WARN_ONCE(sectors || raid_disks,
"%s does not support generic reshape\n", __func__);
return mddev->dev_sectors;
}
static int multipath_run (mddev_t *mddev)
{
multipath_conf_t *conf;
int disk_idx;
struct multipath_info *disk;
mdk_rdev_t *rdev;
if (md_check_no_bitmap(mddev))
return -EINVAL;
if (mddev->level != LEVEL_MULTIPATH) {
printk("multipath: %s: raid level not set to multipath IO (%d)\n",
mdname(mddev), mddev->level);
goto out;
}
/*
* copy the already verified devices into our private MULTIPATH
* bookkeeping area. [whatever we allocate in multipath_run(),
* should be freed in multipath_stop()]
*/
mddev->queue->queue_lock = &mddev->queue->__queue_lock;
conf = kzalloc(sizeof(multipath_conf_t), GFP_KERNEL);
mddev->private = conf;
if (!conf) {
printk(KERN_ERR
"multipath: couldn't allocate memory for %s\n",
mdname(mddev));
goto out;
}
conf->multipaths = kzalloc(sizeof(struct multipath_info)*mddev->raid_disks,
GFP_KERNEL);
if (!conf->multipaths) {
printk(KERN_ERR
"multipath: couldn't allocate memory for %s\n",
mdname(mddev));
goto out_free_conf;
}
conf->working_disks = 0;
list_for_each_entry(rdev, &mddev->disks, same_set) {
disk_idx = rdev->raid_disk;
if (disk_idx < 0 ||
disk_idx >= mddev->raid_disks)
continue;
disk = conf->multipaths + disk_idx;
disk->rdev = rdev;
disk_stack_limits(mddev->gendisk, rdev->bdev,
rdev->data_offset << 9);
/* as we don't honour merge_bvec_fn, we must never risk
* violating it, not that we ever expect a device with
* a merge_bvec_fn to be involved in multipath */
if (rdev->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 (!test_bit(Faulty, &rdev->flags))
conf->working_disks++;
}
conf->raid_disks = mddev->raid_disks;
conf->mddev = mddev;
spin_lock_init(&conf->device_lock);
INIT_LIST_HEAD(&conf->retry_list);
if (!conf->working_disks) {
printk(KERN_ERR "multipath: no operational IO paths for %s\n",
mdname(mddev));
goto out_free_conf;
}
mddev->degraded = conf->raid_disks - conf->working_disks;
conf->pool = mempool_create_kmalloc_pool(NR_RESERVED_BUFS,
sizeof(struct multipath_bh));
if (conf->pool == NULL) {
printk(KERN_ERR
"multipath: couldn't allocate memory for %s\n",
mdname(mddev));
goto out_free_conf;
}
{
mddev->thread = md_register_thread(multipathd, mddev, NULL);
if (!mddev->thread) {
printk(KERN_ERR "multipath: couldn't allocate thread"
" for %s\n", mdname(mddev));
goto out_free_conf;
}
}
printk(KERN_INFO
"multipath: array %s active with %d out of %d IO paths\n",
mdname(mddev), conf->working_disks, mddev->raid_disks);
/*
* Ok, everything is just fine now
*/
md_set_array_sectors(mddev, multipath_size(mddev, 0, 0));
mddev->queue->unplug_fn = multipath_unplug;
mddev->queue->backing_dev_info.congested_fn = multipath_congested;
mddev->queue->backing_dev_info.congested_data = mddev;
md_integrity_register(mddev);
return 0;
out_free_conf:
if (conf->pool)
mempool_destroy(conf->pool);
kfree(conf->multipaths);
kfree(conf);
mddev->private = NULL;
out:
return -EIO;
}
static int multipath_stop (mddev_t *mddev)
{
multipath_conf_t *conf = mddev->private;
md_unregister_thread(mddev->thread);
mddev->thread = NULL;
blk_sync_queue(mddev->queue); /* the unplug fn references 'conf'*/
mempool_destroy(conf->pool);
kfree(conf->multipaths);
kfree(conf);
mddev->private = NULL;
return 0;
}
static struct mdk_personality multipath_personality =
{
.name = "multipath",
.level = LEVEL_MULTIPATH,
.owner = THIS_MODULE,
.make_request = multipath_make_request,
.run = multipath_run,
.stop = multipath_stop,
.status = multipath_status,
.error_handler = multipath_error,
.hot_add_disk = multipath_add_disk,
.hot_remove_disk= multipath_remove_disk,
.size = multipath_size,
};
static int __init multipath_init (void)
{
return register_md_personality (&multipath_personality);
}
static void __exit multipath_exit (void)
{
unregister_md_personality (&multipath_personality);
}
module_init(multipath_init);
module_exit(multipath_exit);
MODULE_LICENSE("GPL");
MODULE_DESCRIPTION("simple multi-path personality for MD");
MODULE_ALIAS("md-personality-7"); /* MULTIPATH */
MODULE_ALIAS("md-multipath");
MODULE_ALIAS("md-level--4");