linux_old1/drivers/md/faulty.c

369 lines
8.8 KiB
C
Raw Normal View History

/*
* faulty.c : Multiple Devices driver for Linux
*
* Copyright (C) 2004 Neil Brown
*
* fautly-device-simulator personality for md
*
*
* 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.
*/
/*
* The "faulty" personality causes some requests to fail.
*
* Possible failure modes are:
* reads fail "randomly" but succeed on retry
* writes fail "randomly" but succeed on retry
* reads for some address fail and then persist until a write
* reads for some address fail and then persist irrespective of write
* writes for some address fail and persist
* all writes fail
*
* Different modes can be active at a time, but only
* one can be set at array creation. Others can be added later.
* A mode can be one-shot or recurrent with the recurrence being
* once in every N requests.
* The bottom 5 bits of the "layout" indicate the mode. The
* remainder indicate a period, or 0 for one-shot.
*
* There is an implementation limit on the number of concurrently
* persisting-faulty blocks. When a new fault is requested that would
* exceed the limit, it is ignored.
* All current faults can be clear using a layout of "0".
*
* Requests are always sent to the device. If they are to fail,
* we clone the bio and insert a new b_end_io into the chain.
*/
#define WriteTransient 0
#define ReadTransient 1
#define WritePersistent 2
#define ReadPersistent 3
#define WriteAll 4 /* doesn't go to device */
#define ReadFixable 5
#define Modes 6
#define ClearErrors 31
#define ClearFaults 30
#define AllPersist 100 /* internal use only */
#define NoPersist 101
#define ModeMask 0x1f
#define ModeShift 5
#define MaxFault 50
#include <linux/blkdev.h>
#include <linux/module.h>
#include <linux/raid/md_u.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 <linux/seq_file.h>
static void faulty_fail(struct bio *bio, int error)
{
struct bio *b = bio->bi_private;
b->bi_size = bio->bi_size;
b->bi_sector = bio->bi_sector;
bio_put(bio);
bio_io_error(b);
}
struct faulty_conf {
int period[Modes];
atomic_t counters[Modes];
sector_t faults[MaxFault];
int modes[MaxFault];
int nfaults;
struct md_rdev *rdev;
};
static int check_mode(struct faulty_conf *conf, int mode)
{
if (conf->period[mode] == 0 &&
atomic_read(&conf->counters[mode]) <= 0)
return 0; /* no failure, no decrement */
if (atomic_dec_and_test(&conf->counters[mode])) {
if (conf->period[mode])
atomic_set(&conf->counters[mode], conf->period[mode]);
return 1;
}
return 0;
}
static int check_sector(struct faulty_conf *conf, sector_t start, sector_t end, int dir)
{
/* If we find a ReadFixable sector, we fix it ... */
int i;
for (i=0; i<conf->nfaults; i++)
if (conf->faults[i] >= start &&
conf->faults[i] < end) {
/* found it ... */
switch (conf->modes[i] * 2 + dir) {
case WritePersistent*2+WRITE: return 1;
case ReadPersistent*2+READ: return 1;
case ReadFixable*2+READ: return 1;
case ReadFixable*2+WRITE:
conf->modes[i] = NoPersist;
return 0;
case AllPersist*2+READ:
case AllPersist*2+WRITE: return 1;
default:
return 0;
}
}
return 0;
}
static void add_sector(struct faulty_conf *conf, sector_t start, int mode)
{
int i;
int n = conf->nfaults;
for (i=0; i<conf->nfaults; i++)
if (conf->faults[i] == start) {
switch(mode) {
case NoPersist: conf->modes[i] = mode; return;
case WritePersistent:
if (conf->modes[i] == ReadPersistent ||
conf->modes[i] == ReadFixable)
conf->modes[i] = AllPersist;
else
conf->modes[i] = WritePersistent;
return;
case ReadPersistent:
if (conf->modes[i] == WritePersistent)
conf->modes[i] = AllPersist;
else
conf->modes[i] = ReadPersistent;
return;
case ReadFixable:
if (conf->modes[i] == WritePersistent ||
conf->modes[i] == ReadPersistent)
conf->modes[i] = AllPersist;
else
conf->modes[i] = ReadFixable;
return;
}
} else if (conf->modes[i] == NoPersist)
n = i;
if (n >= MaxFault)
return;
conf->faults[n] = start;
conf->modes[n] = mode;
if (conf->nfaults == n)
conf->nfaults = n+1;
}
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
2011-11-05 08:06:58 +08:00
static void make_request(struct mddev *mddev, struct bio *bio)
{
struct faulty_conf *conf = mddev->private;
int failit = 0;
if (bio_data_dir(bio) == WRITE) {
/* write request */
if (atomic_read(&conf->counters[WriteAll])) {
/* special case - don't decrement, don't generic_make_request,
* just fail immediately
*/
bio_endio(bio, -EIO);
return;
}
if (check_sector(conf, bio->bi_sector, bio_end_sector(bio), WRITE))
failit = 1;
if (check_mode(conf, WritePersistent)) {
add_sector(conf, bio->bi_sector, WritePersistent);
failit = 1;
}
if (check_mode(conf, WriteTransient))
failit = 1;
} else {
/* read request */
if (check_sector(conf, bio->bi_sector, bio_end_sector(bio), READ))
failit = 1;
if (check_mode(conf, ReadTransient))
failit = 1;
if (check_mode(conf, ReadPersistent)) {
add_sector(conf, bio->bi_sector, ReadPersistent);
failit = 1;
}
if (check_mode(conf, ReadFixable)) {
add_sector(conf, bio->bi_sector, ReadFixable);
failit = 1;
}
}
if (failit) {
struct bio *b = bio_clone_mddev(bio, GFP_NOIO, mddev);
b->bi_bdev = conf->rdev->bdev;
b->bi_private = bio;
b->bi_end_io = faulty_fail;
bio = b;
} else
bio->bi_bdev = conf->rdev->bdev;
generic_make_request(bio);
}
static void status(struct seq_file *seq, struct mddev *mddev)
{
struct faulty_conf *conf = mddev->private;
int n;
if ((n=atomic_read(&conf->counters[WriteTransient])) != 0)
seq_printf(seq, " WriteTransient=%d(%d)",
n, conf->period[WriteTransient]);
if ((n=atomic_read(&conf->counters[ReadTransient])) != 0)
seq_printf(seq, " ReadTransient=%d(%d)",
n, conf->period[ReadTransient]);
if ((n=atomic_read(&conf->counters[WritePersistent])) != 0)
seq_printf(seq, " WritePersistent=%d(%d)",
n, conf->period[WritePersistent]);
if ((n=atomic_read(&conf->counters[ReadPersistent])) != 0)
seq_printf(seq, " ReadPersistent=%d(%d)",
n, conf->period[ReadPersistent]);
if ((n=atomic_read(&conf->counters[ReadFixable])) != 0)
seq_printf(seq, " ReadFixable=%d(%d)",
n, conf->period[ReadFixable]);
if ((n=atomic_read(&conf->counters[WriteAll])) != 0)
seq_printf(seq, " WriteAll");
seq_printf(seq, " nfaults=%d", conf->nfaults);
}
static int reshape(struct mddev *mddev)
{
int mode = mddev->new_layout & ModeMask;
int count = mddev->new_layout >> ModeShift;
struct faulty_conf *conf = mddev->private;
if (mddev->new_layout < 0)
return 0;
/* new layout */
if (mode == ClearFaults)
conf->nfaults = 0;
else if (mode == ClearErrors) {
int i;
for (i=0 ; i < Modes ; i++) {
conf->period[i] = 0;
atomic_set(&conf->counters[i], 0);
}
} else if (mode < Modes) {
conf->period[mode] = count;
if (!count) count++;
atomic_set(&conf->counters[mode], count);
} else
return -EINVAL;
mddev->new_layout = -1;
mddev->layout = -1; /* makes sure further changes come through */
return 0;
}
static sector_t faulty_size(struct mddev *mddev, sector_t sectors, int raid_disks)
{
WARN_ONCE(raid_disks,
"%s does not support generic reshape\n", __func__);
if (sectors == 0)
return mddev->dev_sectors;
return sectors;
}
static int run(struct mddev *mddev)
{
struct md_rdev *rdev;
int i;
struct faulty_conf *conf;
if (md_check_no_bitmap(mddev))
return -EINVAL;
conf = kmalloc(sizeof(*conf), GFP_KERNEL);
if (!conf)
return -ENOMEM;
for (i=0; i<Modes; i++) {
atomic_set(&conf->counters[i], 0);
conf->period[i] = 0;
}
conf->nfaults = 0;
rdev_for_each(rdev, mddev) {
conf->rdev = rdev;
disk_stack_limits(mddev->gendisk, rdev->bdev,
rdev->data_offset << 9);
}
md_set_array_sectors(mddev, faulty_size(mddev, 0, 0));
mddev->private = conf;
reshape(mddev);
return 0;
}
static int stop(struct mddev *mddev)
{
struct faulty_conf *conf = mddev->private;
kfree(conf);
mddev->private = NULL;
return 0;
}
static struct md_personality faulty_personality =
{
.name = "faulty",
.level = LEVEL_FAULTY,
.owner = THIS_MODULE,
.make_request = make_request,
.run = run,
.stop = stop,
.status = status,
.check_reshape = reshape,
.size = faulty_size,
};
static int __init raid_init(void)
{
return register_md_personality(&faulty_personality);
}
static void raid_exit(void)
{
unregister_md_personality(&faulty_personality);
}
module_init(raid_init);
module_exit(raid_exit);
MODULE_LICENSE("GPL");
MODULE_DESCRIPTION("Fault injection personality for MD");
MODULE_ALIAS("md-personality-10"); /* faulty */
MODULE_ALIAS("md-faulty");
MODULE_ALIAS("md-level--5");