OpenCloudOS-Kernel/drivers/md/dm-flakey.c

527 lines
12 KiB
C
Raw Normal View History

/*
* Copyright (C) 2003 Sistina Software (UK) Limited.
* Copyright (C) 2004, 2010-2011 Red Hat, Inc. All rights reserved.
*
* This file is released under the GPL.
*/
#include <linux/device-mapper.h>
#include <linux/module.h>
#include <linux/init.h>
#include <linux/blkdev.h>
#include <linux/bio.h>
#include <linux/slab.h>
#define DM_MSG_PREFIX "flakey"
#define all_corrupt_bio_flags_match(bio, fc) \
(((bio)->bi_opf & (fc)->corrupt_bio_flags) == (fc)->corrupt_bio_flags)
/*
* Flakey: Used for testing only, simulates intermittent,
* catastrophic device failure.
*/
struct flakey_c {
struct dm_dev *dev;
unsigned long start_time;
sector_t start;
unsigned up_interval;
unsigned down_interval;
unsigned long flags;
unsigned corrupt_bio_byte;
unsigned corrupt_bio_rw;
unsigned corrupt_bio_value;
unsigned corrupt_bio_flags;
};
enum feature_flag_bits {
DROP_WRITES,
ERROR_WRITES
};
struct per_bio_data {
bool bio_submitted;
};
static int parse_features(struct dm_arg_set *as, struct flakey_c *fc,
struct dm_target *ti)
{
int r;
unsigned argc;
const char *arg_name;
static const struct dm_arg _args[] = {
{0, 6, "Invalid number of feature args"},
{1, UINT_MAX, "Invalid corrupt bio byte"},
{0, 255, "Invalid corrupt value to write into bio byte (0-255)"},
{0, UINT_MAX, "Invalid corrupt bio flags mask"},
};
/* No feature arguments supplied. */
if (!as->argc)
return 0;
r = dm_read_arg_group(_args, as, &argc, &ti->error);
if (r)
return r;
while (argc) {
arg_name = dm_shift_arg(as);
argc--;
if (!arg_name) {
ti->error = "Insufficient feature arguments";
return -EINVAL;
}
/*
* drop_writes
*/
if (!strcasecmp(arg_name, "drop_writes")) {
if (test_and_set_bit(DROP_WRITES, &fc->flags)) {
ti->error = "Feature drop_writes duplicated";
return -EINVAL;
} else if (test_bit(ERROR_WRITES, &fc->flags)) {
ti->error = "Feature drop_writes conflicts with feature error_writes";
return -EINVAL;
}
continue;
}
/*
* error_writes
*/
if (!strcasecmp(arg_name, "error_writes")) {
if (test_and_set_bit(ERROR_WRITES, &fc->flags)) {
ti->error = "Feature error_writes duplicated";
return -EINVAL;
} else if (test_bit(DROP_WRITES, &fc->flags)) {
ti->error = "Feature error_writes conflicts with feature drop_writes";
return -EINVAL;
}
continue;
}
/*
* corrupt_bio_byte <Nth_byte> <direction> <value> <bio_flags>
*/
if (!strcasecmp(arg_name, "corrupt_bio_byte")) {
if (!argc) {
ti->error = "Feature corrupt_bio_byte requires parameters";
return -EINVAL;
}
r = dm_read_arg(_args + 1, as, &fc->corrupt_bio_byte, &ti->error);
if (r)
return r;
argc--;
/*
* Direction r or w?
*/
arg_name = dm_shift_arg(as);
if (!strcasecmp(arg_name, "w"))
fc->corrupt_bio_rw = WRITE;
else if (!strcasecmp(arg_name, "r"))
fc->corrupt_bio_rw = READ;
else {
ti->error = "Invalid corrupt bio direction (r or w)";
return -EINVAL;
}
argc--;
/*
* Value of byte (0-255) to write in place of correct one.
*/
r = dm_read_arg(_args + 2, as, &fc->corrupt_bio_value, &ti->error);
if (r)
return r;
argc--;
/*
* Only corrupt bios with these flags set.
*/
r = dm_read_arg(_args + 3, as, &fc->corrupt_bio_flags, &ti->error);
if (r)
return r;
argc--;
continue;
}
ti->error = "Unrecognised flakey feature requested";
return -EINVAL;
}
if (test_bit(DROP_WRITES, &fc->flags) && (fc->corrupt_bio_rw == WRITE)) {
ti->error = "drop_writes is incompatible with corrupt_bio_byte with the WRITE flag set";
return -EINVAL;
} else if (test_bit(ERROR_WRITES, &fc->flags) && (fc->corrupt_bio_rw == WRITE)) {
ti->error = "error_writes is incompatible with corrupt_bio_byte with the WRITE flag set";
return -EINVAL;
}
return 0;
}
/*
* Construct a flakey mapping:
* <dev_path> <offset> <up interval> <down interval> [<#feature args> [<arg>]*]
*
* Feature args:
* [drop_writes]
* [corrupt_bio_byte <Nth_byte> <direction> <value> <bio_flags>]
*
* Nth_byte starts from 1 for the first byte.
* Direction is r for READ or w for WRITE.
* bio_flags is ignored if 0.
*/
static int flakey_ctr(struct dm_target *ti, unsigned int argc, char **argv)
{
static const struct dm_arg _args[] = {
{0, UINT_MAX, "Invalid up interval"},
{0, UINT_MAX, "Invalid down interval"},
};
int r;
struct flakey_c *fc;
unsigned long long tmpll;
struct dm_arg_set as;
const char *devname;
char dummy;
as.argc = argc;
as.argv = argv;
if (argc < 4) {
ti->error = "Invalid argument count";
return -EINVAL;
}
fc = kzalloc(sizeof(*fc), GFP_KERNEL);
if (!fc) {
ti->error = "Cannot allocate context";
return -ENOMEM;
}
fc->start_time = jiffies;
devname = dm_shift_arg(&as);
r = -EINVAL;
if (sscanf(dm_shift_arg(&as), "%llu%c", &tmpll, &dummy) != 1 || tmpll != (sector_t)tmpll) {
ti->error = "Invalid device sector";
goto bad;
}
fc->start = tmpll;
r = dm_read_arg(_args, &as, &fc->up_interval, &ti->error);
if (r)
goto bad;
r = dm_read_arg(_args, &as, &fc->down_interval, &ti->error);
if (r)
goto bad;
if (!(fc->up_interval + fc->down_interval)) {
ti->error = "Total (up + down) interval is zero";
r = -EINVAL;
goto bad;
}
if (fc->up_interval + fc->down_interval < fc->up_interval) {
ti->error = "Interval overflow";
r = -EINVAL;
goto bad;
}
r = parse_features(&as, fc, ti);
if (r)
goto bad;
r = dm_get_device(ti, devname, dm_table_get_mode(ti->table), &fc->dev);
if (r) {
ti->error = "Device lookup failed";
goto bad;
}
ti->num_flush_bios = 1;
ti->num_discard_bios = 1;
ti->per_io_data_size = sizeof(struct per_bio_data);
ti->private = fc;
return 0;
bad:
kfree(fc);
return r;
}
static void flakey_dtr(struct dm_target *ti)
{
struct flakey_c *fc = ti->private;
dm_put_device(ti, fc->dev);
kfree(fc);
}
static sector_t flakey_map_sector(struct dm_target *ti, sector_t bi_sector)
{
struct flakey_c *fc = ti->private;
return fc->start + dm_target_offset(ti, bi_sector);
}
static void flakey_map_bio(struct dm_target *ti, struct bio *bio)
{
struct flakey_c *fc = ti->private;
bio_set_dev(bio, fc->dev->bdev);
if (bio_sectors(bio) || bio_op(bio) == REQ_OP_ZONE_RESET)
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
2013-10-12 06:44:27 +08:00
bio->bi_iter.bi_sector =
flakey_map_sector(ti, bio->bi_iter.bi_sector);
}
static void corrupt_bio_data(struct bio *bio, struct flakey_c *fc)
{
unsigned int corrupt_bio_byte = fc->corrupt_bio_byte - 1;
struct bvec_iter iter;
struct bio_vec bvec;
if (!bio_has_data(bio))
return;
/*
* Overwrite the Nth byte of the bio's data, on whichever page
* it falls.
*/
bio_for_each_segment(bvec, bio, iter) {
if (bio_iter_len(bio, iter) > corrupt_bio_byte) {
char *segment = (page_address(bio_iter_page(bio, iter))
+ bio_iter_offset(bio, iter));
segment[corrupt_bio_byte] = fc->corrupt_bio_value;
DMDEBUG("Corrupting data bio=%p by writing %u to byte %u "
"(rw=%c bi_opf=%u bi_sector=%llu size=%u)\n",
bio, fc->corrupt_bio_value, fc->corrupt_bio_byte,
(bio_data_dir(bio) == WRITE) ? 'w' : 'r', bio->bi_opf,
(unsigned long long)bio->bi_iter.bi_sector, bio->bi_iter.bi_size);
break;
}
corrupt_bio_byte -= bio_iter_len(bio, iter);
}
}
static int flakey_map(struct dm_target *ti, struct bio *bio)
{
struct flakey_c *fc = ti->private;
unsigned elapsed;
struct per_bio_data *pb = dm_per_bio_data(bio, sizeof(struct per_bio_data));
pb->bio_submitted = false;
/* Do not fail reset zone */
if (bio_op(bio) == REQ_OP_ZONE_RESET)
goto map_bio;
/* Are we alive ? */
elapsed = (jiffies - fc->start_time) / HZ;
if (elapsed % (fc->up_interval + fc->down_interval) >= fc->up_interval) {
/*
* Flag this bio as submitted while down.
*/
pb->bio_submitted = true;
/*
* Error reads if neither corrupt_bio_byte or drop_writes or error_writes are set.
* Otherwise, flakey_end_io() will decide if the reads should be modified.
*/
if (bio_data_dir(bio) == READ) {
if (!fc->corrupt_bio_byte && !test_bit(DROP_WRITES, &fc->flags) &&
!test_bit(ERROR_WRITES, &fc->flags))
return DM_MAPIO_KILL;
goto map_bio;
}
/*
* Drop or error writes?
*/
if (test_bit(DROP_WRITES, &fc->flags)) {
bio_endio(bio);
return DM_MAPIO_SUBMITTED;
}
else if (test_bit(ERROR_WRITES, &fc->flags)) {
bio_io_error(bio);
return DM_MAPIO_SUBMITTED;
}
/*
* Corrupt matching writes.
*/
if (fc->corrupt_bio_byte && (fc->corrupt_bio_rw == WRITE)) {
if (all_corrupt_bio_flags_match(bio, fc))
corrupt_bio_data(bio, fc);
goto map_bio;
}
/*
* By default, error all I/O.
*/
return DM_MAPIO_KILL;
}
map_bio:
flakey_map_bio(ti, bio);
return DM_MAPIO_REMAPPED;
}
static int flakey_end_io(struct dm_target *ti, struct bio *bio,
blk_status_t *error)
{
struct flakey_c *fc = ti->private;
struct per_bio_data *pb = dm_per_bio_data(bio, sizeof(struct per_bio_data));
if (bio_op(bio) == REQ_OP_ZONE_RESET)
return DM_ENDIO_DONE;
if (!*error && pb->bio_submitted && (bio_data_dir(bio) == READ)) {
if (fc->corrupt_bio_byte && (fc->corrupt_bio_rw == READ) &&
all_corrupt_bio_flags_match(bio, fc)) {
/*
* Corrupt successful matching READs while in down state.
*/
corrupt_bio_data(bio, fc);
} else if (!test_bit(DROP_WRITES, &fc->flags) &&
!test_bit(ERROR_WRITES, &fc->flags)) {
/*
* Error read during the down_interval if drop_writes
* and error_writes were not configured.
*/
*error = BLK_STS_IOERR;
}
}
return DM_ENDIO_DONE;
}
dm: fix truncated status strings Avoid returning a truncated table or status string instead of setting the DM_BUFFER_FULL_FLAG when the last target of a table fills the buffer. When processing a table or status request, the function retrieve_status calls ti->type->status. If ti->type->status returns non-zero, retrieve_status assumes that the buffer overflowed and sets DM_BUFFER_FULL_FLAG. However, targets don't return non-zero values from their status method on overflow. Most targets returns always zero. If a buffer overflow happens in a target that is not the last in the table, it gets noticed during the next iteration of the loop in retrieve_status; but if a buffer overflow happens in the last target, it goes unnoticed and erroneously truncated data is returned. In the current code, the targets behave in the following way: * dm-crypt returns -ENOMEM if there is not enough space to store the key, but it returns 0 on all other overflows. * dm-thin returns errors from the status method if a disk error happened. This is incorrect because retrieve_status doesn't check the error code, it assumes that all non-zero values mean buffer overflow. * all the other targets always return 0. This patch changes the ti->type->status function to return void (because most targets don't use the return code). Overflow is detected in retrieve_status: if the status method fills up the remaining space completely, it is assumed that buffer overflow happened. Cc: stable@vger.kernel.org Signed-off-by: Mikulas Patocka <mpatocka@redhat.com> Signed-off-by: Alasdair G Kergon <agk@redhat.com>
2013-03-02 06:45:44 +08:00
static void flakey_status(struct dm_target *ti, status_type_t type,
unsigned status_flags, char *result, unsigned maxlen)
{
unsigned sz = 0;
struct flakey_c *fc = ti->private;
unsigned drop_writes, error_writes;
switch (type) {
case STATUSTYPE_INFO:
result[0] = '\0';
break;
case STATUSTYPE_TABLE:
DMEMIT("%s %llu %u %u ", fc->dev->name,
(unsigned long long)fc->start, fc->up_interval,
fc->down_interval);
drop_writes = test_bit(DROP_WRITES, &fc->flags);
error_writes = test_bit(ERROR_WRITES, &fc->flags);
DMEMIT("%u ", drop_writes + error_writes + (fc->corrupt_bio_byte > 0) * 5);
if (drop_writes)
DMEMIT("drop_writes ");
else if (error_writes)
DMEMIT("error_writes ");
if (fc->corrupt_bio_byte)
DMEMIT("corrupt_bio_byte %u %c %u %u ",
fc->corrupt_bio_byte,
(fc->corrupt_bio_rw == WRITE) ? 'w' : 'r',
fc->corrupt_bio_value, fc->corrupt_bio_flags);
break;
}
}
static int flakey_prepare_ioctl(struct dm_target *ti, struct block_device **bdev)
{
struct flakey_c *fc = ti->private;
*bdev = fc->dev->bdev;
/*
* Only pass ioctls through if the device sizes match exactly.
*/
if (fc->start ||
ti->len != i_size_read((*bdev)->bd_inode) >> SECTOR_SHIFT)
return 1;
return 0;
}
#ifdef CONFIG_BLK_DEV_ZONED
static int flakey_report_zones(struct dm_target *ti, sector_t sector,
struct blk_zone *zones, unsigned int *nr_zones)
{
struct flakey_c *fc = ti->private;
int ret;
/* Do report and remap it */
ret = blkdev_report_zones(fc->dev->bdev, flakey_map_sector(ti, sector),
zones, nr_zones);
if (ret != 0)
return ret;
if (*nr_zones)
dm_remap_zone_report(ti, fc->start, zones, nr_zones);
return 0;
}
#endif
static int flakey_iterate_devices(struct dm_target *ti, iterate_devices_callout_fn fn, void *data)
{
struct flakey_c *fc = ti->private;
return fn(ti, fc->dev, fc->start, ti->len, data);
}
static struct target_type flakey_target = {
.name = "flakey",
.version = {1, 5, 0},
#ifdef CONFIG_BLK_DEV_ZONED
.features = DM_TARGET_ZONED_HM,
.report_zones = flakey_report_zones,
#endif
.module = THIS_MODULE,
.ctr = flakey_ctr,
.dtr = flakey_dtr,
.map = flakey_map,
.end_io = flakey_end_io,
.status = flakey_status,
.prepare_ioctl = flakey_prepare_ioctl,
.iterate_devices = flakey_iterate_devices,
};
static int __init dm_flakey_init(void)
{
int r = dm_register_target(&flakey_target);
if (r < 0)
DMERR("register failed %d", r);
return r;
}
static void __exit dm_flakey_exit(void)
{
dm_unregister_target(&flakey_target);
}
/* Module hooks */
module_init(dm_flakey_init);
module_exit(dm_flakey_exit);
MODULE_DESCRIPTION(DM_NAME " flakey target");
MODULE_AUTHOR("Joe Thornber <dm-devel@redhat.com>");
MODULE_LICENSE("GPL");