nhu/kernel_a52xq
Watch
1
Fork
You've already forked kernel_a52xq
 0
mirror of https://github.com/a52xq-dev/kernel.git synced 2026-10-18 21:58:11 +07:00
Code Issues Projects Releases Wiki Activity

md: rename some drivers/md/ files to have an "md-" prefix

Browse source 
Motivated by the desire to illiminate the imprecise nature of
DM-specific patches being unnecessarily sent to both the MD maintainer
and mailing-list.  Which is born out of the fact that DM files also
reside in drivers/md/

Now all MD-specific files in drivers/md/ start with either "raid" or
"md-" and the MAINTAINERS file has been updated accordingly.

Shaohua: don't change module name

Signed-off-by: Mike Snitzer <snitzer@redhat.com>
Signed-off-by: Shaohua Li <shli@fb.com>
This commit is contained in:
Mike Snitzer 2017-10-10 17:02:41 -04:00 • committed by Shaohua Li
commit 935fe0983e
16 changed files with 20 additions and 12 deletions
Download patch file Download diff file Expand all files Collapse all files

7
MAINTAINERS
View file

@ -4091,6 +4091,8 @@ T: git git://git.kernel.org/pub/scm/linux/kernel/git/device-mapper/linux-dm.git
T: quilt http://people.redhat.com/agk/patches/linux/editing/
S: Maintained
F: Documentation/device-mapper/
F: drivers/md/Makefile
F: drivers/md/Kconfig
F: drivers/md/dm*
F: drivers/md/persistent-data/
F: include/linux/device-mapper.h
@ -12446,7 +12448,10 @@ M: Shaohua Li <shli@kernel.org>
L: linux-raid@vger.kernel.org
T: git git://git.kernel.org/pub/scm/linux/kernel/git/shli/md.git
S: Supported
F: drivers/md/
F: drivers/md/Makefile
F: drivers/md/Kconfig
F: drivers/md/md*
F: drivers/md/raid*
F: include/linux/raid/
F: include/uapi/linux/raid/

5
drivers/md/Makefile
View file

@ -18,9 +18,12 @@ dm-cache-y += dm-cache-target.o dm-cache-metadata.o dm-cache-policy.o \
dm-cache-smq-y += dm-cache-policy-smq.o
dm-era-y += dm-era-target.o
dm-verity-y += dm-verity-target.o
md-mod-y += md.o bitmap.o
md-mod-y += md.o md-bitmap.o
raid456-y += raid5.o raid5-cache.o raid5-ppl.o
dm-zoned-y += dm-zoned-target.o dm-zoned-metadata.o dm-zoned-reclaim.o
linear-y += md-linear.o
multipath-y += md-multipath.o
faulty-y += md-faulty.o
# Note: link order is important. All raid personalities
# and must come before md.o, as they each initialise

2
drivers/md/dm-raid.c
View file

@ -12,7 +12,7 @@
#include "raid1.h"
#include "raid5.h"
#include "raid10.h"
#include "bitmap.h"
#include "md-bitmap.h"
#include <linux/device-mapper.h>

2591
drivers/md/md-bitmap.c Normal file
View file

File diff suppressed because it is too large Load diff

277
drivers/md/md-bitmap.h Normal file
View file

@ -0,0 +1,277 @@
/*
* bitmap.h: Copyright (C) Peter T. Breuer (ptb@ot.uc3m.es) 2003
*
* additions: Copyright (C) 2003-2004, Paul Clements, SteelEye Technology, Inc.
*/
#ifndef BITMAP_H
#define BITMAP_H 1
#define BITMAP_MAJOR_LO 3
/* version 4 insists the bitmap is in little-endian order
* with version 3, it is host-endian which is non-portable
* Version 5 is currently set only for clustered devices
*/
#define BITMAP_MAJOR_HI 4
#define BITMAP_MAJOR_CLUSTERED 5
#define BITMAP_MAJOR_HOSTENDIAN 3
/*
* in-memory bitmap:
*
* Use 16 bit block counters to track pending writes to each "chunk".
* The 2 high order bits are special-purpose, the first is a flag indicating
* whether a resync is needed. The second is a flag indicating whether a
* resync is active.
* This means that the counter is actually 14 bits:
*
* +--------+--------+------------------------------------------------+
* | resync | resync | counter |
* | needed | active | |
* | (0-1) | (0-1) | (0-16383) |
* +--------+--------+------------------------------------------------+
*
* The "resync needed" bit is set when:
* a '1' bit is read from storage at startup.
* a write request fails on some drives
* a resync is aborted on a chunk with 'resync active' set
* It is cleared (and resync-active set) when a resync starts across all drives
* of the chunk.
*
*
* The "resync active" bit is set when:
* a resync is started on all drives, and resync_needed is set.
* resync_needed will be cleared (as long as resync_active wasn't already set).
* It is cleared when a resync completes.
*
* The counter counts pending write requests, plus the on-disk bit.
* When the counter is '1' and the resync bits are clear, the on-disk
* bit can be cleared as well, thus setting the counter to 0.
* When we set a bit, or in the counter (to start a write), if the fields is
* 0, we first set the disk bit and set the counter to 1.
*
* If the counter is 0, the on-disk bit is clear and the stripe is clean
* Anything that dirties the stripe pushes the counter to 2 (at least)
* and sets the on-disk bit (lazily).
* If a periodic sweep find the counter at 2, it is decremented to 1.
* If the sweep find the counter at 1, the on-disk bit is cleared and the
* counter goes to zero.
*
* Also, we'll hijack the "map" pointer itself and use it as two 16 bit block
* counters as a fallback when "page" memory cannot be allocated:
*
* Normal case (page memory allocated):
*
* page pointer (32-bit)
*
* [ ] ------+
* |
* +-------> [ ][ ]..[ ] (4096 byte page == 2048 counters)
* c1 c2 c2048
*
* Hijacked case (page memory allocation failed):
*
* hijacked page pointer (32-bit)
*
* [ ][ ] (no page memory allocated)
* counter #1 (16-bit) counter #2 (16-bit)
*
*/
#ifdef __KERNEL__
#define PAGE_BITS (PAGE_SIZE << 3)
#define PAGE_BIT_SHIFT (PAGE_SHIFT + 3)
typedef __u16 bitmap_counter_t;
#define COUNTER_BITS 16
#define COUNTER_BIT_SHIFT 4
#define COUNTER_BYTE_SHIFT (COUNTER_BIT_SHIFT - 3)
#define NEEDED_MASK ((bitmap_counter_t) (1 << (COUNTER_BITS - 1)))
#define RESYNC_MASK ((bitmap_counter_t) (1 << (COUNTER_BITS - 2)))
#define COUNTER_MAX ((bitmap_counter_t) RESYNC_MASK - 1)
#define NEEDED(x) (((bitmap_counter_t) x) & NEEDED_MASK)
#define RESYNC(x) (((bitmap_counter_t) x) & RESYNC_MASK)
#define COUNTER(x) (((bitmap_counter_t) x) & COUNTER_MAX)
/* how many counters per page? */
#define PAGE_COUNTER_RATIO (PAGE_BITS / COUNTER_BITS)
/* same, except a shift value for more efficient bitops */
#define PAGE_COUNTER_SHIFT (PAGE_BIT_SHIFT - COUNTER_BIT_SHIFT)
/* same, except a mask value for more efficient bitops */
#define PAGE_COUNTER_MASK (PAGE_COUNTER_RATIO - 1)
#define BITMAP_BLOCK_SHIFT 9
#endif
/*
* bitmap structures:
*/
#define BITMAP_MAGIC 0x6d746962
/* use these for bitmap->flags and bitmap->sb->state bit-fields */
enum bitmap_state {
BITMAP_STALE = 1, /* the bitmap file is out of date or had -EIO */
BITMAP_WRITE_ERROR = 2, /* A write error has occurred */
BITMAP_HOSTENDIAN =15,
};
/* the superblock at the front of the bitmap file -- little endian */
typedef struct bitmap_super_s {
__le32 magic; /* 0 BITMAP_MAGIC */
__le32 version; /* 4 the bitmap major for now, could change... */
__u8 uuid[16]; /* 8 128 bit uuid - must match md device uuid */
__le64 events; /* 24 event counter for the bitmap (1)*/
__le64 events_cleared;/*32 event counter when last bit cleared (2) */
__le64 sync_size; /* 40 the size of the md device's sync range(3) */
__le32 state; /* 48 bitmap state information */
__le32 chunksize; /* 52 the bitmap chunk size in bytes */
__le32 daemon_sleep; /* 56 seconds between disk flushes */
__le32 write_behind; /* 60 number of outstanding write-behind writes */
__le32 sectors_reserved; /* 64 number of 512-byte sectors that are
* reserved for the bitmap. */
__le32 nodes; /* 68 the maximum number of nodes in cluster. */
__u8 cluster_name[64]; /* 72 cluster name to which this md belongs */
__u8 pad[256 - 136]; /* set to zero */
} bitmap_super_t;
/* notes:
* (1) This event counter is updated before the eventcounter in the md superblock
* When a bitmap is loaded, it is only accepted if this event counter is equal
* to, or one greater than, the event counter in the superblock.
* (2) This event counter is updated when the other one is *if*and*only*if* the
* array is not degraded. As bits are not cleared when the array is degraded,
* this represents the last time that any bits were cleared.
* If a device is being added that has an event count with this value or
* higher, it is accepted as conforming to the bitmap.
* (3)This is the number of sectors represented by the bitmap, and is the range that
* resync happens across. For raid1 and raid5/6 it is the size of individual
* devices. For raid10 it is the size of the array.
*/
#ifdef __KERNEL__
/* the in-memory bitmap is represented by bitmap_pages */
struct bitmap_page {
/*
* map points to the actual memory page
*/
char *map;
/*
* in emergencies (when map cannot be alloced), hijack the map
* pointer and use it as two counters itself
*/
unsigned int hijacked:1;
/*
* If any counter in this page is '1' or '2' - and so could be
* cleared then that page is marked as 'pending'
*/
unsigned int pending:1;
/*
* count of dirty bits on the page
*/
unsigned int count:30;
};
/* the main bitmap structure - one per mddev */
struct bitmap {
struct bitmap_counts {
spinlock_t lock;
struct bitmap_page *bp;
unsigned long pages; /* total number of pages
* in the bitmap */
unsigned long missing_pages; /* number of pages
* not yet allocated */
unsigned long chunkshift; /* chunksize = 2^chunkshift
* (for bitops) */
unsigned long chunks; /* Total number of data
* chunks for the array */
} counts;
struct mddev *mddev; /* the md device that the bitmap is for */
__u64 events_cleared;
int need_sync;
struct bitmap_storage {
struct file *file; /* backing disk file */
struct page *sb_page; /* cached copy of the bitmap
* file superblock */
struct page **filemap; /* list of cache pages for
* the file */
unsigned long *filemap_attr; /* attributes associated
* w/ filemap pages */
unsigned long file_pages; /* number of pages in the file*/
unsigned long bytes; /* total bytes in the bitmap */
} storage;
unsigned long flags;
int allclean;
atomic_t behind_writes;
unsigned long behind_writes_used; /* highest actual value at runtime */
/*
* the bitmap daemon - periodically wakes up and sweeps the bitmap
* file, cleaning up bits and flushing out pages to disk as necessary
*/
unsigned long daemon_lastrun; /* jiffies of last run */
unsigned long last_end_sync; /* when we lasted called end_sync to
* update bitmap with resync progress */
atomic_t pending_writes; /* pending writes to the bitmap file */
wait_queue_head_t write_wait;
wait_queue_head_t overflow_wait;
wait_queue_head_t behind_wait;
struct kernfs_node *sysfs_can_clear;
int cluster_slot; /* Slot offset for clustered env */
};
/* the bitmap API */
/* these are used only by md/bitmap */
struct bitmap *bitmap_create(struct mddev *mddev, int slot);
int bitmap_load(struct mddev *mddev);
void bitmap_flush(struct mddev *mddev);
void bitmap_destroy(struct mddev *mddev);
void bitmap_print_sb(struct bitmap *bitmap);
void bitmap_update_sb(struct bitmap *bitmap);
void bitmap_status(struct seq_file *seq, struct bitmap *bitmap);
int bitmap_setallbits(struct bitmap *bitmap);
void bitmap_write_all(struct bitmap *bitmap);
void bitmap_dirty_bits(struct bitmap *bitmap, unsigned long s, unsigned long e);
/* these are exported */
int bitmap_startwrite(struct bitmap *bitmap, sector_t offset,
unsigned long sectors, int behind);
void bitmap_endwrite(struct bitmap *bitmap, sector_t offset,
unsigned long sectors, int success, int behind);
int bitmap_start_sync(struct bitmap *bitmap, sector_t offset, sector_t *blocks, int degraded);
void bitmap_end_sync(struct bitmap *bitmap, sector_t offset, sector_t *blocks, int aborted);
void bitmap_close_sync(struct bitmap *bitmap);
void bitmap_cond_end_sync(struct bitmap *bitmap, sector_t sector, bool force);
void bitmap_sync_with_cluster(struct mddev *mddev,
sector_t old_lo, sector_t old_hi,
sector_t new_lo, sector_t new_hi);
void bitmap_unplug(struct bitmap *bitmap);
void bitmap_daemon_work(struct mddev *mddev);
int bitmap_resize(struct bitmap *bitmap, sector_t blocks,
int chunksize, int init);
struct bitmap *get_bitmap_from_slot(struct mddev *mddev, int slot);
int bitmap_copy_from_slot(struct mddev *mddev, int slot,
sector_t *lo, sector_t *hi, bool clear_bits);
void bitmap_free(struct bitmap *bitmap);
void bitmap_wait_behind_writes(struct mddev *mddev);
#endif
#endif

2
drivers/md/md-cluster.c
View file

@ -15,7 +15,7 @@
#include <linux/sched.h>
#include <linux/raid/md_p.h>
#include "md.h"
#include "bitmap.h"
#include "md-bitmap.h"
#include "md-cluster.h"
#define LVB_SIZE 64

372
drivers/md/md-faulty.c Normal file
View file

@ -0,0 +1,372 @@
/*
* 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 <linux/slab.h>
#include "md.h"
#include <linux/seq_file.h>
static void faulty_fail(struct bio *bio)
{
struct bio *b = bio->bi_private;
b->bi_iter.bi_size = bio->bi_iter.bi_size;
b->bi_iter.bi_sector = bio->bi_iter.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;
}
static bool faulty_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_io_error(bio);
return true;
}
if (check_sector(conf, bio->bi_iter.bi_sector,
bio_end_sector(bio), WRITE))
failit = 1;
if (check_mode(conf, WritePersistent)) {
add_sector(conf, bio->bi_iter.bi_sector,
WritePersistent);
failit = 1;
}
if (check_mode(conf, WriteTransient))
failit = 1;
} else {
/* read request */
if (check_sector(conf, bio->bi_iter.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_iter.bi_sector,
ReadPersistent);
failit = 1;
}
if (check_mode(conf, ReadFixable)) {
add_sector(conf, bio->bi_iter.bi_sector,
ReadFixable);
failit = 1;
}
}
if (failit) {
struct bio *b = bio_clone_fast(bio, GFP_NOIO, mddev->bio_set);
bio_set_dev(b, conf->rdev->bdev);
b->bi_private = bio;
b->bi_end_io = faulty_fail;
bio = b;
} else
bio_set_dev(bio, conf->rdev->bdev);
generic_make_request(bio);
return true;
}
static void faulty_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 faulty_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 faulty_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;
faulty_reshape(mddev);
return 0;
}
static void faulty_free(struct mddev *mddev, void *priv)
{
struct faulty_conf *conf = priv;
kfree(conf);
}
static struct md_personality faulty_personality =
{
.name = "faulty",
.level = LEVEL_FAULTY,
.owner = THIS_MODULE,
.make_request = faulty_make_request,
.run = faulty_run,
.free = faulty_free,
.status = faulty_status,
.check_reshape = faulty_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");

348
drivers/md/md-linear.c Normal file
View file

@ -0,0 +1,348 @@
/*
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 <linux/module.h>
#include <linux/slab.h>
#include <trace/events/block.h>
#include "md.h"
#include "md-linear.h"
/*
* find which device holds a particular offset
*/
static inline struct dev_info *which_dev(struct mddev *mddev, sector_t sector)
{
int lo, mid, hi;
struct linear_conf *conf;
lo = 0;
hi = mddev->raid_disks - 1;
conf = 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;
}
/*
* In linear_congested() conf->raid_disks is used as a copy of
* mddev->raid_disks to iterate conf->disks[], because conf->raid_disks
* and conf->disks[] are created in linear_conf(), they are always
* consitent with each other, but mddev->raid_disks does not.
*/
static int linear_congested(struct mddev *mddev, int bits)
{
struct linear_conf *conf;
int i, ret = 0;
rcu_read_lock();
conf = rcu_dereference(mddev->private);
for (i = 0; i < conf->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(struct mddev *mddev, sector_t sectors, int raid_disks)
{
struct linear_conf *conf;
sector_t array_sectors;
conf = mddev->private;
WARN_ONCE(sectors || raid_disks,
"%s does not support generic reshape\n", __func__);
array_sectors = conf->array_sectors;
return array_sectors;
}
static struct linear_conf *linear_conf(struct mddev *mddev, int raid_disks)
{
struct linear_conf *conf;
struct md_rdev *rdev;
int i, cnt;
bool discard_supported = false;
conf = kzalloc (sizeof (*conf) + raid_disks*sizeof(struct dev_info),
GFP_KERNEL);
if (!conf)
return NULL;
cnt = 0;
conf->array_sectors = 0;
rdev_for_each(rdev, mddev) {
int j = rdev->raid_disk;
struct dev_info *disk = conf->disks + j;
sector_t sectors;
if (j < 0 || j >= raid_disks || disk->rdev) {
pr_warn("md/linear:%s: disk numbering problem. Aborting!\n",
mdname(mddev));
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);
conf->array_sectors += rdev->sectors;
cnt++;
if (blk_queue_discard(bdev_get_queue(rdev->bdev)))
discard_supported = true;
}
if (cnt != raid_disks) {
pr_warn("md/linear:%s: not enough drives present. Aborting!\n",
mdname(mddev));
goto out;
}
if (!discard_supported)
queue_flag_clear_unlocked(QUEUE_FLAG_DISCARD, mddev->queue);
else
queue_flag_set_unlocked(QUEUE_FLAG_DISCARD, mddev->queue);
/*
* 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;
/*
* conf->raid_disks is copy of mddev->raid_disks. The reason to
* keep a copy of mddev->raid_disks in struct linear_conf is,
* mddev->raid_disks may not be consistent with pointers number of
* conf->disks[] when it is updated in linear_add() and used to
* iterate old conf->disks[] earray in linear_congested().
* Here conf->raid_disks is always consitent with number of
* pointers in conf->disks[] array, and mddev->private is updated
* with rcu_assign_pointer() in linear_addr(), such race can be
* avoided.
*/
conf->raid_disks = raid_disks;
return conf;
out:
kfree(conf);
return NULL;
}
static int linear_run (struct mddev *mddev)
{
struct linear_conf *conf;
int ret;
if (md_check_no_bitmap(mddev))
return -EINVAL;
conf = linear_conf(mddev, mddev->raid_disks);
if (!conf)
return 1;
mddev->private = conf;
md_set_array_sectors(mddev, linear_size(mddev, 0, 0));
ret = md_integrity_register(mddev);
if (ret) {
kfree(conf);
mddev->private = NULL;
}
return ret;
}
static int linear_add(struct mddev *mddev, struct md_rdev *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.
*/
struct linear_conf *newconf, *oldconf;
if (rdev->saved_raid_disk != mddev->raid_disks)
return -EINVAL;
rdev->raid_disk = rdev->saved_raid_disk;
rdev->saved_raid_disk = -1;
newconf = linear_conf(mddev,mddev->raid_disks+1);
if (!newconf)
return -ENOMEM;
/* newconf->raid_disks already keeps a copy of * the increased
* value of mddev->raid_disks, WARN_ONCE() is just used to make
* sure of this. It is possible that oldconf is still referenced
* in linear_congested(), therefore kfree_rcu() is used to free
* oldconf until no one uses it anymore.
*/
mddev_suspend(mddev);
oldconf = rcu_dereference_protected(mddev->private,
lockdep_is_held(&mddev->reconfig_mutex));
mddev->raid_disks++;
WARN_ONCE(mddev->raid_disks != newconf->raid_disks,
"copied raid_disks doesn't match 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);
mddev_resume(mddev);
revalidate_disk(mddev->gendisk);
kfree_rcu(oldconf, rcu);
return 0;
}
static void linear_free(struct mddev *mddev, void *priv)
{
struct linear_conf *conf = priv;
kfree(conf);
}
static bool linear_make_request(struct mddev *mddev, struct bio *bio)
{
char b[BDEVNAME_SIZE];
struct dev_info *tmp_dev;
sector_t start_sector, end_sector, data_offset;
sector_t bio_sector = bio->bi_iter.bi_sector;
if (unlikely(bio->bi_opf & REQ_PREFLUSH)) {
md_flush_request(mddev, bio);
return true;
}
tmp_dev = which_dev(mddev, bio_sector);
start_sector = tmp_dev->end_sector - tmp_dev->rdev->sectors;
end_sector = tmp_dev->end_sector;
data_offset = tmp_dev->rdev->data_offset;
if (unlikely(bio_sector >= end_sector ||
bio_sector < start_sector))
goto out_of_bounds;
if (unlikely(bio_end_sector(bio) > end_sector)) {
/* This bio crosses a device boundary, so we have to split it */
struct bio *split = bio_split(bio, end_sector - bio_sector,
GFP_NOIO, mddev->bio_set);
bio_chain(split, bio);
generic_make_request(bio);
bio = split;
}
bio_set_dev(bio, tmp_dev->rdev->bdev);
bio->bi_iter.bi_sector = bio->bi_iter.bi_sector -
start_sector + data_offset;
if (unlikely((bio_op(bio) == REQ_OP_DISCARD) &&
!blk_queue_discard(bio->bi_disk->queue))) {
/* Just ignore it */
bio_endio(bio);
} else {
if (mddev->gendisk)
trace_block_bio_remap(bio->bi_disk->queue,
bio, disk_devt(mddev->gendisk),
bio_sector);
mddev_check_writesame(mddev, bio);
mddev_check_write_zeroes(mddev, bio);
generic_make_request(bio);
}
return true;
out_of_bounds:
pr_err("md/linear:%s: make_request: Sector %llu out of bounds on dev %s: %llu sectors, offset %llu\n",
mdname(mddev),
(unsigned long long)bio->bi_iter.bi_sector,
bdevname(tmp_dev->rdev->bdev, b),
(unsigned long long)tmp_dev->rdev->sectors,
(unsigned long long)start_sector);
bio_io_error(bio);
return true;
}
static void linear_status (struct seq_file *seq, struct mddev *mddev)
{
seq_printf(seq, " %dk rounding", mddev->chunk_sectors / 2);
}
static void linear_quiesce(struct mddev *mddev, int state)
{
}
static struct md_personality linear_personality =
{
.name = "linear",
.level = LEVEL_LINEAR,
.owner = THIS_MODULE,
.make_request = linear_make_request,
.run = linear_run,
.free = linear_free,
.status = linear_status,
.hot_add_disk = linear_add,
.size = linear_size,
.quiesce = linear_quiesce,
.congested = linear_congested,
};
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");

16
drivers/md/md-linear.h Normal file
View file

@ -0,0 +1,16 @@
#ifndef _LINEAR_H
#define _LINEAR_H
struct dev_info {
struct md_rdev *rdev;
sector_t end_sector;
};
struct linear_conf
{
struct rcu_head rcu;
sector_t array_sectors;
int raid_disks; /* a copy of mddev->raid_disks */
struct dev_info disks[0];
};
#endif

509
drivers/md/md-multipath.c Normal file
View file

@ -0,0 +1,509 @@
/*
* 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/module.h>
#include <linux/raid/md_u.h>
#include <linux/seq_file.h>
#include <linux/slab.h>
#include "md.h"
#include "md-multipath.h"
#define MAX_WORK_PER_DISK 128
#define NR_RESERVED_BUFS 32
static int multipath_map (struct mpconf *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++) {
struct md_rdev *rdev = rcu_dereference(conf->multipaths[i].rdev);
if (rdev && test_bit(In_sync, &rdev->flags) &&
!test_bit(Faulty, &rdev->flags)) {
atomic_inc(&rdev->nr_pending);
rcu_read_unlock();
return i;
}
}
rcu_read_unlock();
pr_crit_ratelimited("multipath_map(): no more operational IO paths?\n");
return (-1);
}
static void multipath_reschedule_retry (struct multipath_bh *mp_bh)
{
unsigned long flags;
struct mddev *mddev = mp_bh->mddev;
struct mpconf *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, blk_status_t status)
{
struct bio *bio = mp_bh->master_bio;
struct mpconf *conf = mp_bh->mddev->private;
bio->bi_status = status;
bio_endio(bio);
mempool_free(mp_bh, conf->pool);
}
static void multipath_end_request(struct bio *bio)
{
struct multipath_bh *mp_bh = bio->bi_private;
struct mpconf *conf = mp_bh->mddev->private;
struct md_rdev *rdev = conf->multipaths[mp_bh->path].rdev;
if (!bio->bi_status)
multipath_end_bh_io(mp_bh, 0);
else if (!(bio->bi_opf & REQ_RAHEAD)) {
/*
* oops, IO error:
*/
char b[BDEVNAME_SIZE];
md_error (mp_bh->mddev, rdev);
pr_info("multipath: %s: rescheduling sector %llu\n",
bdevname(rdev->bdev,b),
(unsigned long long)bio->bi_iter.bi_sector);
multipath_reschedule_retry(mp_bh);
} else
multipath_end_bh_io(mp_bh, bio->bi_status);
rdev_dec_pending(rdev, conf->mddev);
}
static bool multipath_make_request(struct mddev *mddev, struct bio * bio)
{
struct mpconf *conf = mddev->private;
struct multipath_bh * mp_bh;
struct multipath_info *multipath;
if (unlikely(bio->bi_opf & REQ_PREFLUSH)) {
md_flush_request(mddev, bio);
return true;
}
mp_bh = mempool_alloc(conf->pool, GFP_NOIO);
mp_bh->master_bio = bio;
mp_bh->mddev = mddev;
mp_bh->path = multipath_map(conf);
if (mp_bh->path < 0) {
bio_io_error(bio);
mempool_free(mp_bh, conf->pool);
return true;
}
multipath = conf->multipaths + mp_bh->path;
bio_init(&mp_bh->bio, NULL, 0);
__bio_clone_fast(&mp_bh->bio, bio);
mp_bh->bio.bi_iter.bi_sector += multipath->rdev->data_offset;
bio_set_dev(&mp_bh->bio, multipath->rdev->bdev);
mp_bh->bio.bi_opf |= REQ_FAILFAST_TRANSPORT;
mp_bh->bio.bi_end_io = multipath_end_request;
mp_bh->bio.bi_private = mp_bh;
mddev_check_writesame(mddev, &mp_bh->bio);
mddev_check_write_zeroes(mddev, &mp_bh->bio);
generic_make_request(&mp_bh->bio);
return true;
}
static void multipath_status(struct seq_file *seq, struct mddev *mddev)
{
struct mpconf *conf = mddev->private;
int i;
seq_printf (seq, " [%d/%d] [", conf->raid_disks,
conf->raid_disks - mddev->degraded);
rcu_read_lock();
for (i = 0; i < conf->raid_disks; i++) {
struct md_rdev *rdev = rcu_dereference(conf->multipaths[i].rdev);
seq_printf (seq, "%s", rdev && test_bit(In_sync, &rdev->flags) ? "U" : "_");
}
rcu_read_unlock();
seq_printf (seq, "]");
}
static int multipath_congested(struct mddev *mddev, int bits)
{
struct mpconf *conf = mddev->private;
int i, ret = 0;
rcu_read_lock();
for (i = 0; i < mddev->raid_disks ; i++) {
struct md_rdev *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 (struct mddev *mddev, struct md_rdev *rdev)
{
struct mpconf *conf = mddev->private;
char b[BDEVNAME_SIZE];
if (conf->raid_disks - mddev->degraded <= 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.
*/
pr_warn("multipath: only one IO path left and IO error.\n");
/* leave it active... it's all we have */
return;
}
/*
* Mark disk as unusable
*/
if (test_and_clear_bit(In_sync, &rdev->flags)) {
unsigned long flags;
spin_lock_irqsave(&conf->device_lock, flags);
mddev->degraded++;
spin_unlock_irqrestore(&conf->device_lock, flags);
}
set_bit(Faulty, &rdev->flags);
set_bit(MD_SB_CHANGE_DEVS, &mddev->sb_flags);
pr_err("multipath: IO failure on %s, disabling IO path.\n"
"multipath: Operation continuing on %d IO paths.\n",
bdevname(rdev->bdev, b),
conf->raid_disks - mddev->degraded);
}
static void print_multipath_conf (struct mpconf *conf)
{
int i;
struct multipath_info *tmp;
pr_debug("MULTIPATH conf printout:\n");
if (!conf) {
pr_debug("(conf==NULL)\n");
return;
}
pr_debug(" --- wd:%d rd:%d\n", conf->raid_disks - conf->mddev->degraded,
conf->raid_disks);
for (i = 0; i < conf->raid_disks; i++) {
char b[BDEVNAME_SIZE];
tmp = conf->multipaths + i;
if (tmp->rdev)
pr_debug(" disk%d, o:%d, dev:%s\n",
i,!test_bit(Faulty, &tmp->rdev->flags),
bdevname(tmp->rdev->bdev,b));
}
}
static int multipath_add_disk(struct mddev *mddev, struct md_rdev *rdev)
{
struct mpconf *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);
err = md_integrity_add_rdev(rdev, mddev);
if (err)
break;
spin_lock_irq(&conf->device_lock);
mddev->degraded--;
rdev->raid_disk = path;
set_bit(In_sync, &rdev->flags);
spin_unlock_irq(&conf->device_lock);
rcu_assign_pointer(p->rdev, rdev);
err = 0;
break;
}
print_multipath_conf(conf);
return err;
}
static int multipath_remove_disk(struct mddev *mddev, struct md_rdev *rdev)
{
struct mpconf *conf = mddev->private;
int err = 0;
int number = rdev->raid_disk;
struct multipath_info *p = conf->multipaths + number;
print_multipath_conf(conf);
if (rdev == p->rdev) {
if (test_bit(In_sync, &rdev->flags) ||
atomic_read(&rdev->nr_pending)) {
pr_warn("hot-remove-disk, slot %d is identified but is still operational!\n", number);
err = -EBUSY;
goto abort;
}
p->rdev = NULL;
if (!test_bit(RemoveSynchronized, &rdev->flags)) {
synchronize_rcu();
if (atomic_read(&rdev->nr_pending)) {
/* lost the race, try later */
err = -EBUSY;
p->rdev = rdev;
goto abort;
}
}
err = 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(struct md_thread *thread)
{
struct mddev *mddev = thread->mddev;
struct multipath_bh *mp_bh;
struct bio *bio;
unsigned long flags;
struct mpconf *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_iter.bi_sector = mp_bh->master_bio->bi_iter.bi_sector;
if ((mp_bh->path = multipath_map (conf))<0) {
pr_err("multipath: %s: unrecoverable IO read error for block %llu\n",
bio_devname(bio, b),
(unsigned long long)bio->bi_iter.bi_sector);
multipath_end_bh_io(mp_bh, BLK_STS_IOERR);
} else {
pr_err("multipath: %s: redirecting sector %llu to another IO path\n",
bio_devname(bio, b),
(unsigned long long)bio->bi_iter.bi_sector);
*bio = *(mp_bh->master_bio);
bio->bi_iter.bi_sector +=
conf->multipaths[mp_bh->path].rdev->data_offset;
bio_set_dev(bio, conf->multipaths[mp_bh->path].rdev->bdev);
bio->bi_opf |= REQ_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(struct mddev *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 (struct mddev *mddev)
{
struct mpconf *conf;
int disk_idx;
struct multipath_info *disk;
struct md_rdev *rdev;
int working_disks;
if (md_check_no_bitmap(mddev))
return -EINVAL;
if (mddev->level != LEVEL_MULTIPATH) {
pr_warn("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_free()]
*/
conf = kzalloc(sizeof(struct mpconf), GFP_KERNEL);
mddev->private = conf;
if (!conf)
goto out;
conf->multipaths = kzalloc(sizeof(struct multipath_info)*mddev->raid_disks,
GFP_KERNEL);
if (!conf->multipaths)
goto out_free_conf;
working_disks = 0;
rdev_for_each(rdev, mddev) {
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);
if (!test_bit(Faulty, &rdev->flags))
working_disks++;
}
conf->raid_disks = mddev->raid_disks;
conf->mddev = mddev;
spin_lock_init(&conf->device_lock);
INIT_LIST_HEAD(&conf->retry_list);
if (!working_disks) {
pr_warn("multipath: no operational IO paths for %s\n",
mdname(mddev));
goto out_free_conf;
}
mddev->degraded = conf->raid_disks - working_disks;
conf->pool = mempool_create_kmalloc_pool(NR_RESERVED_BUFS,
sizeof(struct multipath_bh));
if (conf->pool == NULL)
goto out_free_conf;
mddev->thread = md_register_thread(multipathd, mddev,
"multipath");
if (!mddev->thread)
goto out_free_conf;
pr_info("multipath: array %s active with %d out of %d IO paths\n",
mdname(mddev), conf->raid_disks - mddev->degraded,
mddev->raid_disks);
/*
* Ok, everything is just fine now
*/
md_set_array_sectors(mddev, multipath_size(mddev, 0, 0));
if (md_integrity_register(mddev))
goto out_free_conf;
return 0;
out_free_conf:
mempool_destroy(conf->pool);
kfree(conf->multipaths);
kfree(conf);
mddev->private = NULL;
out:
return -EIO;
}
static void multipath_free(struct mddev *mddev, void *priv)
{
struct mpconf *conf = priv;
mempool_destroy(conf->pool);
kfree(conf->multipaths);
kfree(conf);
}
static struct md_personality multipath_personality =
{
.name = "multipath",
.level = LEVEL_MULTIPATH,
.owner = THIS_MODULE,
.make_request = multipath_make_request,
.run = multipath_run,
.free = multipath_free,
.status = multipath_status,
.error_handler = multipath_error,
.hot_add_disk = multipath_add_disk,
.hot_remove_disk= multipath_remove_disk,
.size = multipath_size,
.congested = multipath_congested,
};
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");

31
drivers/md/md-multipath.h Normal file
View file

@ -0,0 +1,31 @@
#ifndef _MULTIPATH_H
#define _MULTIPATH_H
struct multipath_info {
struct md_rdev *rdev;
};
struct mpconf {
struct mddev *mddev;
struct multipath_info *multipaths;
int raid_disks;
spinlock_t device_lock;
struct list_head retry_list;
mempool_t *pool;
};
/*
* this is our 'private' 'collective' MULTIPATH buffer head.
* it contains information about what kind of IO operations were started
* for this MULTIPATH operation, and about their status:
*/
struct multipath_bh {
struct mddev *mddev;
struct bio *master_bio;
struct bio bio;
int path;
struct list_head retry_list;
};
#endif

2
drivers/md/md.c
View file

@ -69,7 +69,7 @@
#include <trace/events/block.h>
#include "md.h"
#include "bitmap.h"
#include "md-bitmap.h"
#include "md-cluster.h"
#ifndef MODULE

2
drivers/md/raid1.c
View file

@ -43,7 +43,7 @@
#include "md.h"
#include "raid1.h"
#include "bitmap.h"
#include "md-bitmap.h"
#define UNSUPPORTED_MDDEV_FLAGS \
((1L << MD_HAS_JOURNAL) | \

2
drivers/md/raid10.c
View file

@ -29,7 +29,7 @@
#include "md.h"
#include "raid10.h"
#include "raid0.h"
#include "bitmap.h"
#include "md-bitmap.h"
/*
* RAID10 provides a combination of RAID0 and RAID1 functionality.

2
drivers/md/raid5-cache.c
View file

@ -23,7 +23,7 @@
#include <linux/types.h>
#include "md.h"
#include "raid5.h"
#include "bitmap.h"
#include "md-bitmap.h"
#include "raid5-log.h"
/*

2
drivers/md/raid5.c
View file

@ -63,7 +63,7 @@
#include "md.h"
#include "raid5.h"
#include "raid0.h"
#include "bitmap.h"
#include "md-bitmap.h"
#include "raid5-log.h"
#define UNSUPPORTED_MDDEV_FLAGS (1L << MD_FAILFAST_SUPPORTED)