kernel-ark/drivers/md/linear.c

393 lines
9.4 KiB
C
Raw Normal View History

/*
linear.c : Multiple Devices driver for Linux
Copyright (C) 1994-96 Marc ZYNGIER
<zyngier@ufr-info-p7.ibp.fr> or
<maz@gloups.fdn.fr>
Linear mode 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/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 08:04:11 +00:00
#include <linux/slab.h>
#include "md.h"
#include "linear.h"
/*
* find which device holds a particular offset
*/
static inline dev_info_t *which_dev(mddev_t *mddev, sector_t sector)
{
int lo, mid, hi;
linear_conf_t *conf;
lo = 0;
hi = mddev->raid_disks - 1;
conf = rcu_dereference(mddev->private);
/*
* Binary Search
*/
while (hi > lo) {
mid = (hi + lo) / 2;
if (sector < conf->disks[mid].end_sector)
hi = mid;
else
lo = mid + 1;
}
return conf->disks + lo;
}
/**
* linear_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 take at this offset
*/
static int linear_mergeable_bvec(struct request_queue *q,
struct bvec_merge_data *bvm,
struct bio_vec *biovec)
{
mddev_t *mddev = q->queuedata;
dev_info_t *dev0;
unsigned long maxsectors, bio_sectors = bvm->bi_size >> 9;
sector_t sector = bvm->bi_sector + get_start_sect(bvm->bi_bdev);
rcu_read_lock();
dev0 = which_dev(mddev, sector);
maxsectors = dev0->end_sector - sector;
rcu_read_unlock();
if (maxsectors < bio_sectors)
maxsectors = 0;
else
maxsectors -= bio_sectors;
if (maxsectors <= (PAGE_SIZE >> 9 ) && bio_sectors == 0)
return biovec->bv_len;
/* The bytes available at this offset could be really big,
* so we cap at 2^31 to avoid overflow */
if (maxsectors > (1 << (31-9)))
return 1<<31;
return maxsectors << 9;
}
static void linear_unplug(struct request_queue *q)
{
mddev_t *mddev = q->queuedata;
linear_conf_t *conf;
int i;
rcu_read_lock();
conf = rcu_dereference(mddev->private);
for (i=0; i < mddev->raid_disks; i++) {
struct request_queue *r_queue = bdev_get_queue(conf->disks[i].rdev->bdev);
blk_unplug(r_queue);
}
rcu_read_unlock();
}
static int linear_congested(void *data, int bits)
{
mddev_t *mddev = data;
linear_conf_t *conf;
int i, ret = 0;
if (mddev_congested(mddev, bits))
return 1;
rcu_read_lock();
conf = rcu_dereference(mddev->private);
for (i = 0; i < mddev->raid_disks && !ret ; i++) {
struct request_queue *q = bdev_get_queue(conf->disks[i].rdev->bdev);
ret |= bdi_congested(&q->backing_dev_info, bits);
}
rcu_read_unlock();
return ret;
}
static sector_t linear_size(mddev_t *mddev, sector_t sectors, int raid_disks)
{
linear_conf_t *conf;
sector_t array_sectors;
rcu_read_lock();
conf = rcu_dereference(mddev->private);
WARN_ONCE(sectors || raid_disks,
"%s does not support generic reshape\n", __func__);
array_sectors = conf->array_sectors;
rcu_read_unlock();
return array_sectors;
}
static linear_conf_t *linear_conf(mddev_t *mddev, int raid_disks)
{
linear_conf_t *conf;
mdk_rdev_t *rdev;
int i, cnt;
conf = kzalloc (sizeof (*conf) + raid_disks*sizeof(dev_info_t),
GFP_KERNEL);
if (!conf)
return NULL;
cnt = 0;
conf->array_sectors = 0;
list_for_each_entry(rdev, &mddev->disks, same_set) {
int j = rdev->raid_disk;
dev_info_t *disk = conf->disks + j;
sector_t sectors;
if (j < 0 || j >= raid_disks || disk->rdev) {
printk("linear: disk numbering problem. Aborting!\n");
goto out;
}
disk->rdev = rdev;
if (mddev->chunk_sectors) {
sectors = rdev->sectors;
sector_div(sectors, mddev->chunk_sectors);
rdev->sectors = sectors * mddev->chunk_sectors;
}
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 1 lying within
* a single page.
*/
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);
}
conf->array_sectors += rdev->sectors;
cnt++;
}
if (cnt != raid_disks) {
printk("linear: not enough drives present. Aborting!\n");
goto out;
}
/*
* Here we calculate the device offsets.
*/
conf->disks[0].end_sector = conf->disks[0].rdev->sectors;
for (i = 1; i < raid_disks; i++)
conf->disks[i].end_sector =
conf->disks[i-1].end_sector +
conf->disks[i].rdev->sectors;
return conf;
out:
kfree(conf);
return NULL;
}
static int linear_run (mddev_t *mddev)
{
linear_conf_t *conf;
if (md_check_no_bitmap(mddev))
return -EINVAL;
mddev->queue->queue_lock = &mddev->queue->__queue_lock;
conf = linear_conf(mddev, mddev->raid_disks);
if (!conf)
return 1;
mddev->private = conf;
md_set_array_sectors(mddev, linear_size(mddev, 0, 0));
blk_queue_merge_bvec(mddev->queue, linear_mergeable_bvec);
mddev->queue->unplug_fn = linear_unplug;
mddev->queue->backing_dev_info.congested_fn = linear_congested;
mddev->queue->backing_dev_info.congested_data = mddev;
md_integrity_register(mddev);
return 0;
}
static void free_conf(struct rcu_head *head)
{
linear_conf_t *conf = container_of(head, linear_conf_t, rcu);
kfree(conf);
}
static int linear_add(mddev_t *mddev, mdk_rdev_t *rdev)
{
/* Adding a drive to a linear array allows the array to grow.
* It is permitted if the new drive has a matching superblock
* already on it, with raid_disk equal to raid_disks.
* It is achieved by creating a new linear_private_data structure
* and swapping it in in-place of the current one.
* The current one is never freed until the array is stopped.
* This avoids races.
*/
linear_conf_t *newconf, *oldconf;
if (rdev->saved_raid_disk != mddev->raid_disks)
return -EINVAL;
rdev->raid_disk = rdev->saved_raid_disk;
newconf = linear_conf(mddev,mddev->raid_disks+1);
if (!newconf)
return -ENOMEM;
oldconf = rcu_dereference(mddev->private);
mddev->raid_disks++;
rcu_assign_pointer(mddev->private, newconf);
md_set_array_sectors(mddev, linear_size(mddev, 0, 0));
set_capacity(mddev->gendisk, mddev->array_sectors);
revalidate_disk(mddev->gendisk);
call_rcu(&oldconf->rcu, free_conf);
return 0;
}
static int linear_stop (mddev_t *mddev)
{
linear_conf_t *conf = mddev->private;
/*
* We do not require rcu protection here since
* we hold reconfig_mutex for both linear_add and
* linear_stop, so they cannot race.
* We should make sure any old 'conf's are properly
* freed though.
*/
rcu_barrier();
blk_sync_queue(mddev->queue); /* the unplug fn references 'conf'*/
kfree(conf);
return 0;
}
static int linear_make_request (struct request_queue *q, struct bio *bio)
{
const int rw = bio_data_dir(bio);
mddev_t *mddev = q->queuedata;
dev_info_t *tmp_dev;
sector_t start_sector;
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 01:49:49 +00:00
md_barrier_request(mddev, bio);
return 0;
}
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();
rcu_read_lock();
tmp_dev = which_dev(mddev, bio->bi_sector);
start_sector = tmp_dev->end_sector - tmp_dev->rdev->sectors;
if (unlikely(bio->bi_sector >= (tmp_dev->end_sector)
|| (bio->bi_sector < start_sector))) {
char b[BDEVNAME_SIZE];
printk("linear_make_request: Sector %llu out of bounds on "
"dev %s: %llu sectors, offset %llu\n",
(unsigned long long)bio->bi_sector,
bdevname(tmp_dev->rdev->bdev, b),
(unsigned long long)tmp_dev->rdev->sectors,
(unsigned long long)start_sector);
rcu_read_unlock();
bio_io_error(bio);
return 0;
}
if (unlikely(bio->bi_sector + (bio->bi_size >> 9) >
tmp_dev->end_sector)) {
/* This bio crosses a device boundary, so we have to
* split it.
*/
struct bio_pair *bp;
sector_t end_sector = tmp_dev->end_sector;
rcu_read_unlock();
bp = bio_split(bio, end_sector - bio->bi_sector);
if (linear_make_request(q, &bp->bio1))
generic_make_request(&bp->bio1);
if (linear_make_request(q, &bp->bio2))
generic_make_request(&bp->bio2);
bio_pair_release(bp);
return 0;
}
bio->bi_bdev = tmp_dev->rdev->bdev;
bio->bi_sector = bio->bi_sector - start_sector
+ tmp_dev->rdev->data_offset;
rcu_read_unlock();
return 1;
}
static void linear_status (struct seq_file *seq, mddev_t *mddev)
{
seq_printf(seq, " %dk rounding", mddev->chunk_sectors / 2);
}
static struct mdk_personality linear_personality =
{
.name = "linear",
.level = LEVEL_LINEAR,
.owner = THIS_MODULE,
.make_request = linear_make_request,
.run = linear_run,
.stop = linear_stop,
.status = linear_status,
.hot_add_disk = linear_add,
.size = linear_size,
};
static int __init linear_init (void)
{
return register_md_personality (&linear_personality);
}
static void linear_exit (void)
{
unregister_md_personality (&linear_personality);
}
module_init(linear_init);
module_exit(linear_exit);
MODULE_LICENSE("GPL");
MODULE_DESCRIPTION("Linear device concatenation personality for MD");
MODULE_ALIAS("md-personality-1"); /* LINEAR - deprecated*/
MODULE_ALIAS("md-linear");
MODULE_ALIAS("md-level--1");