Commit c472273f authored by Linus Torvalds's avatar Linus Torvalds

Merge branch 'for-linus' of git://neil.brown.name/md

* 'for-linus' of git://neil.brown.name/md:
  md: fix input truncation in safe_delay_store()
  md: check for memory allocation failure in faulty personality
  md: build failure due to missing delay.h
  md: Relax minimum size restrictions on chunk_size.
  md: remove space after function name in declaration and call.
  md: Remove unnecessary #includes, #defines, and function declarations.
  md: Convert remaining 1k representations in linear.c to sectors.
  md: linear.c: Make two local variables sector-based.
  md: linear: Represent dev_info->size and dev_info->offset in sectors.
  md: linear.c: Remove broken debug code.
  md: linear.c: Remove pointless initialization of curr_offset.
  md: linear.c: Fix typo in comment.
  md: Don't try to set an array to 'read-auto' if it is already in that state.
  md: Allow metadata_version to be updated for externally managed metadata.
  md: Fix rdev_size_store with size == 0
parents 36ac1d2f 97ce0a7f
......@@ -287,6 +287,8 @@ static int run(mddev_t *mddev)
int i;
conf_t *conf = kmalloc(sizeof(*conf), GFP_KERNEL);
if (!conf)
return -ENOMEM;
for (i=0; i<Modes; i++) {
atomic_set(&conf->counters[i], 0);
......
......@@ -16,16 +16,8 @@
Software Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
*/
#include <linux/module.h>
#include <linux/raid/md.h>
#include <linux/slab.h>
#include <linux/raid/linear.h>
#define MAJOR_NR MD_MAJOR
#define MD_DRIVER
#define MD_PERSONALITY
/*
* find which device holds a particular offset
*/
......@@ -33,16 +25,15 @@ static inline dev_info_t *which_dev(mddev_t *mddev, sector_t sector)
{
dev_info_t *hash;
linear_conf_t *conf = mddev_to_conf(mddev);
sector_t block = sector >> 1;
/*
* sector_div(a,b) returns the remainer and sets a to a/b
*/
block >>= conf->preshift;
(void)sector_div(block, conf->hash_spacing);
hash = conf->hash_table[block];
sector >>= conf->sector_shift;
(void)sector_div(sector, conf->spacing);
hash = conf->hash_table[sector];
while ((sector>>1) >= (hash->size + hash->offset))
while (sector >= hash->num_sectors + hash->start_sector)
hash++;
return hash;
}
......@@ -65,7 +56,7 @@ static int linear_mergeable_bvec(struct request_queue *q,
sector_t sector = bvm->bi_sector + get_start_sect(bvm->bi_bdev);
dev0 = which_dev(mddev, sector);
maxsectors = (dev0->size << 1) - (sector - (dev0->offset<<1));
maxsectors = dev0->num_sectors - (sector - dev0->start_sector);
if (maxsectors < bio_sectors)
maxsectors = 0;
......@@ -112,8 +103,8 @@ static linear_conf_t *linear_conf(mddev_t *mddev, int raid_disks)
dev_info_t **table;
mdk_rdev_t *rdev;
int i, nb_zone, cnt;
sector_t min_spacing;
sector_t curr_offset;
sector_t min_sectors;
sector_t curr_sector;
struct list_head *tmp;
conf = kzalloc (sizeof (*conf) + raid_disks*sizeof(dev_info_t),
......@@ -145,7 +136,7 @@ static linear_conf_t *linear_conf(mddev_t *mddev, int raid_disks)
mddev->queue->max_sectors > (PAGE_SIZE>>9))
blk_queue_max_sectors(mddev->queue, PAGE_SIZE>>9);
disk->size = rdev->size;
disk->num_sectors = rdev->size * 2;
conf->array_sectors += rdev->size * 2;
cnt++;
......@@ -155,34 +146,34 @@ static linear_conf_t *linear_conf(mddev_t *mddev, int raid_disks)
goto out;
}
min_spacing = conf->array_sectors / 2;
sector_div(min_spacing, PAGE_SIZE/sizeof(struct dev_info *));
min_sectors = conf->array_sectors;
sector_div(min_sectors, PAGE_SIZE/sizeof(struct dev_info *));
/* min_spacing is the minimum spacing that will fit the hash
/* min_sectors is the minimum spacing that will fit the hash
* table in one PAGE. This may be much smaller than needed.
* We find the smallest non-terminal set of consecutive devices
* that is larger than min_spacing as use the size of that as
* that is larger than min_sectors and use the size of that as
* the actual spacing
*/
conf->hash_spacing = conf->array_sectors / 2;
conf->spacing = conf->array_sectors;
for (i=0; i < cnt-1 ; i++) {
sector_t sz = 0;
sector_t tmp = 0;
int j;
for (j = i; j < cnt - 1 && sz < min_spacing; j++)
sz += conf->disks[j].size;
if (sz >= min_spacing && sz < conf->hash_spacing)
conf->hash_spacing = sz;
for (j = i; j < cnt - 1 && tmp < min_sectors; j++)
tmp += conf->disks[j].num_sectors;
if (tmp >= min_sectors && tmp < conf->spacing)
conf->spacing = tmp;
}
/* hash_spacing may be too large for sector_div to work with,
/* spacing may be too large for sector_div to work with,
* so we might need to pre-shift
*/
conf->preshift = 0;
conf->sector_shift = 0;
if (sizeof(sector_t) > sizeof(u32)) {
sector_t space = conf->hash_spacing;
sector_t space = conf->spacing;
while (space > (sector_t)(~(u32)0)) {
space >>= 1;
conf->preshift++;
conf->sector_shift++;
}
}
/*
......@@ -194,9 +185,9 @@ static linear_conf_t *linear_conf(mddev_t *mddev, int raid_disks)
unsigned round;
unsigned long base;
sz = conf->array_sectors >> (conf->preshift + 1);
sz = conf->array_sectors >> conf->sector_shift;
sz += 1; /* force round-up */
base = conf->hash_spacing >> conf->preshift;
base = conf->spacing >> conf->sector_shift;
round = sector_div(sz, base);
nb_zone = sz + (round ? 1 : 0);
}
......@@ -211,32 +202,31 @@ static linear_conf_t *linear_conf(mddev_t *mddev, int raid_disks)
* Here we generate the linear hash table
* First calculate the device offsets.
*/
conf->disks[0].offset = 0;
conf->disks[0].start_sector = 0;
for (i = 1; i < raid_disks; i++)
conf->disks[i].offset =
conf->disks[i-1].offset +
conf->disks[i-1].size;
conf->disks[i].start_sector =
conf->disks[i-1].start_sector +
conf->disks[i-1].num_sectors;
table = conf->hash_table;
curr_offset = 0;
i = 0;
for (curr_offset = 0;
curr_offset < conf->array_sectors / 2;
curr_offset += conf->hash_spacing) {
for (curr_sector = 0;
curr_sector < conf->array_sectors;
curr_sector += conf->spacing) {
while (i < raid_disks-1 &&
curr_offset >= conf->disks[i+1].offset)
curr_sector >= conf->disks[i+1].start_sector)
i++;
*table ++ = conf->disks + i;
}
if (conf->preshift) {
conf->hash_spacing >>= conf->preshift;
/* round hash_spacing up so that when we divide by it,
if (conf->sector_shift) {
conf->spacing >>= conf->sector_shift;
/* round spacing up so that when we divide by it,
* we err on the side of "too-low", which is safest.
*/
conf->hash_spacing++;
conf->spacing++;
}
BUG_ON(table - conf->hash_table > nb_zone);
......@@ -317,7 +307,6 @@ 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 block;
int cpu;
if (unlikely(bio_barrier(bio))) {
......@@ -332,29 +321,33 @@ static int linear_make_request (struct request_queue *q, struct bio *bio)
part_stat_unlock();
tmp_dev = which_dev(mddev, bio->bi_sector);
block = bio->bi_sector >> 1;
if (unlikely(block >= (tmp_dev->size + tmp_dev->offset)
|| block < tmp_dev->offset)) {
if (unlikely(bio->bi_sector >= (tmp_dev->num_sectors +
tmp_dev->start_sector)
|| (bio->bi_sector <
tmp_dev->start_sector))) {
char b[BDEVNAME_SIZE];
printk("linear_make_request: Block %llu out of bounds on "
"dev %s size %llu offset %llu\n",
(unsigned long long)block,
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->size,
(unsigned long long)tmp_dev->offset);
(unsigned long long)tmp_dev->num_sectors,
(unsigned long long)tmp_dev->start_sector);
bio_io_error(bio);
return 0;
}
if (unlikely(bio->bi_sector + (bio->bi_size >> 9) >
(tmp_dev->offset + tmp_dev->size)<<1)) {
tmp_dev->start_sector + tmp_dev->num_sectors)) {
/* This bio crosses a device boundary, so we have to
* split it.
*/
struct bio_pair *bp;
bp = bio_split(bio,
((tmp_dev->offset + tmp_dev->size)<<1) - bio->bi_sector);
tmp_dev->start_sector + tmp_dev->num_sectors
- bio->bi_sector);
if (linear_make_request(q, &bp->bio1))
generic_make_request(&bp->bio1);
if (linear_make_request(q, &bp->bio2))
......@@ -364,7 +357,8 @@ static int linear_make_request (struct request_queue *q, struct bio *bio)
}
bio->bi_bdev = tmp_dev->rdev->bdev;
bio->bi_sector = bio->bi_sector - (tmp_dev->offset << 1) + tmp_dev->rdev->data_offset;
bio->bi_sector = bio->bi_sector - tmp_dev->start_sector
+ tmp_dev->rdev->data_offset;
return 1;
}
......@@ -372,29 +366,6 @@ static int linear_make_request (struct request_queue *q, struct bio *bio)
static void linear_status (struct seq_file *seq, mddev_t *mddev)
{
#undef MD_DEBUG
#ifdef MD_DEBUG
int j;
linear_conf_t *conf = mddev_to_conf(mddev);
sector_t s = 0;
seq_printf(seq, " ");
for (j = 0; j < mddev->raid_disks; j++)
{
char b[BDEVNAME_SIZE];
s += conf->smallest_size;
seq_printf(seq, "[%s",
bdevname(conf->hash_table[j][0].rdev->bdev,b));
while (s > conf->hash_table[j][0].offset +
conf->hash_table[j][0].size)
seq_printf(seq, "/%s] ",
bdevname(conf->hash_table[j][1].rdev->bdev,b));
else
seq_printf(seq, "] ");
}
seq_printf(seq, "\n");
#endif
seq_printf(seq, " %dk rounding", mddev->chunk_size/1024);
}
......
......@@ -32,31 +32,21 @@
Software Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
*/
#include <linux/module.h>
#include <linux/kernel.h>
#include <linux/kthread.h>
#include <linux/linkage.h>
#include <linux/raid/md.h>
#include <linux/raid/bitmap.h>
#include <linux/sysctl.h>
#include <linux/buffer_head.h> /* for invalidate_bdev */
#include <linux/poll.h>
#include <linux/mutex.h>
#include <linux/ctype.h>
#include <linux/freezer.h>
#include <linux/init.h>
#include <linux/hdreg.h>
#include <linux/proc_fs.h>
#include <linux/random.h>
#include <linux/reboot.h>
#include <linux/file.h>
#ifdef CONFIG_KMOD
#include <linux/kmod.h>
#endif
#include <asm/unaligned.h>
#include <linux/delay.h>
#define MAJOR_NR MD_MAJOR
#define MD_DRIVER
/* 63 partitions with the alternate major number (mdp) */
#define MdpMinorShift 6
......@@ -66,7 +56,7 @@
#ifndef MODULE
static void autostart_arrays (int part);
static void autostart_arrays(int part);
#endif
static LIST_HEAD(pers_list);
......@@ -212,7 +202,7 @@ static DEFINE_SPINLOCK(all_mddevs_lock);
)
static int md_fail_request (struct request_queue *q, struct bio *bio)
static int md_fail_request(struct request_queue *q, struct bio *bio)
{
bio_io_error(bio);
return 0;
......@@ -2106,8 +2096,6 @@ rdev_size_store(mdk_rdev_t *rdev, const char *buf, size_t len)
if (strict_strtoull(buf, 10, &size) < 0)
return -EINVAL;
if (size < my_mddev->size)
return -EINVAL;
if (my_mddev->pers && rdev->raid_disk >= 0) {
if (my_mddev->persistent) {
size = super_types[my_mddev->major_version].
......@@ -2118,9 +2106,9 @@ rdev_size_store(mdk_rdev_t *rdev, const char *buf, size_t len)
size = (rdev->bdev->bd_inode->i_size >> 10);
size -= rdev->data_offset/2;
}
if (size < my_mddev->size)
return -EINVAL; /* component must fit device */
}
if (size < my_mddev->size)
return -EINVAL; /* component must fit device */
rdev->size = size;
if (size > oldsize && my_mddev->external) {
......@@ -2406,12 +2394,11 @@ safe_delay_store(mddev_t *mddev, const char *cbuf, size_t len)
int i;
unsigned long msec;
char buf[30];
char *e;
/* remove a period, and count digits after it */
if (len >= sizeof(buf))
return -EINVAL;
strlcpy(buf, cbuf, len);
buf[len] = 0;
strlcpy(buf, cbuf, sizeof(buf));
for (i=0; i<len; i++) {
if (dot) {
if (isdigit(buf[i])) {
......@@ -2424,8 +2411,7 @@ safe_delay_store(mddev_t *mddev, const char *cbuf, size_t len)
buf[i] = 0;
}
}
msec = simple_strtoul(buf, &e, 10);
if (e == buf || (*e && *e != '\n'))
if (strict_strtoul(buf, 10, &msec) < 0)
return -EINVAL;
msec = (msec * 1000) / scale;
if (msec == 0)
......@@ -2727,9 +2713,9 @@ array_state_store(mddev_t *mddev, const char *buf, size_t len)
break;
case read_auto:
if (mddev->pers) {
if (mddev->ro != 1)
if (mddev->ro == 0)
err = do_md_stop(mddev, 1, 0);
else
else if (mddev->ro == 1)
err = restart_array(mddev);
if (err == 0) {
mddev->ro = 2;
......@@ -2945,7 +2931,13 @@ metadata_store(mddev_t *mddev, const char *buf, size_t len)
{
int major, minor;
char *e;
if (!list_empty(&mddev->disks))
/* Changing the details of 'external' metadata is
* always permitted. Otherwise there must be
* no devices attached to the array.
*/
if (mddev->external && strncmp(buf, "external:", 9) == 0)
;
else if (!list_empty(&mddev->disks))
return -EBUSY;
if (cmd_match(buf, "none")) {
......@@ -3527,17 +3519,12 @@ static int do_md_run(mddev_t * mddev)
return -EINVAL;
}
/*
* chunk-size has to be a power of 2 and multiples of PAGE_SIZE
* chunk-size has to be a power of 2
*/
if ( (1 << ffz(~chunk_size)) != chunk_size) {
printk(KERN_ERR "chunk_size of %d not valid\n", chunk_size);
return -EINVAL;
}
if (chunk_size < PAGE_SIZE) {
printk(KERN_ERR "too small chunk_size: %d < %ld\n",
chunk_size, PAGE_SIZE);
return -EINVAL;
}
/* devices must have minimum size of one chunk */
rdev_for_each(rdev, tmp, mddev) {
......@@ -3555,12 +3542,10 @@ static int do_md_run(mddev_t * mddev)
}
}
#ifdef CONFIG_KMOD
if (mddev->level != LEVEL_NONE)
request_module("md-level-%d", mddev->level);
else if (mddev->clevel[0])
request_module("md-%s", mddev->clevel);
#endif
/*
* Drop all container device buffers, from now on
......@@ -3971,10 +3956,10 @@ static void autorun_array(mddev_t *mddev)
}
printk("\n");
err = do_md_run (mddev);
err = do_md_run(mddev);
if (err) {
printk(KERN_WARNING "md: do_md_run() returned %d\n", err);
do_md_stop (mddev, 0, 0);
do_md_stop(mddev, 0, 0);
}
}
......@@ -4333,7 +4318,7 @@ static int add_new_disk(mddev_t * mddev, mdu_disk_info_t *info)
if (!(info->state & (1<<MD_DISK_FAULTY))) {
int err;
rdev = md_import_device (dev, -1, 0);
rdev = md_import_device(dev, -1, 0);
if (IS_ERR(rdev)) {
printk(KERN_WARNING
"md: error, md_import_device() returned %ld\n",
......@@ -4415,7 +4400,7 @@ static int hot_add_disk(mddev_t * mddev, dev_t dev)
return -EINVAL;
}
rdev = md_import_device (dev, -1, 0);
rdev = md_import_device(dev, -1, 0);
if (IS_ERR(rdev)) {
printk(KERN_WARNING
"md: error, md_import_device() returned %ld\n",
......@@ -4934,11 +4919,11 @@ static int md_ioctl(struct inode *inode, struct file *file,
goto done_unlock;
case STOP_ARRAY:
err = do_md_stop (mddev, 0, 1);
err = do_md_stop(mddev, 0, 1);
goto done_unlock;
case STOP_ARRAY_RO:
err = do_md_stop (mddev, 1, 1);
err = do_md_stop(mddev, 1, 1);
goto done_unlock;
}
......@@ -4987,7 +4972,7 @@ static int md_ioctl(struct inode *inode, struct file *file,
goto done_unlock;
case RUN_ARRAY:
err = do_md_run (mddev);
err = do_md_run(mddev);
goto done_unlock;
case SET_BITMAP_FILE:
......@@ -5425,11 +5410,11 @@ static int md_seq_show(struct seq_file *seq, void *v)
seq_printf(seq, " super non-persistent");
if (mddev->pers) {
mddev->pers->status (seq, mddev);
mddev->pers->status(seq, mddev);
seq_printf(seq, "\n ");
if (mddev->pers->sync_request) {
if (mddev->curr_resync > 2) {
status_resync (seq, mddev);
status_resync(seq, mddev);
seq_printf(seq, "\n ");
} else if (mddev->curr_resync == 1 || mddev->curr_resync == 2)
seq_printf(seq, "\tresync=DELAYED\n ");
......@@ -6260,7 +6245,7 @@ static int md_notify_reboot(struct notifier_block *this,
* appears to still be in use. Hence
* the '100'.
*/
do_md_stop (mddev, 1, 100);
do_md_stop(mddev, 1, 100);
mddev_unlock(mddev);
}
/*
......@@ -6304,7 +6289,7 @@ static int __init md_init(void)
raid_table_header = register_sysctl_table(raid_root_table);
md_geninit();
return (0);
return 0;
}
......
......@@ -19,16 +19,7 @@
* Software Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
*/
#include <linux/module.h>
#include <linux/slab.h>
#include <linux/spinlock.h>
#include <linux/raid/multipath.h>
#include <linux/buffer_head.h>
#include <asm/atomic.h>
#define MAJOR_NR MD_MAJOR
#define MD_DRIVER
#define MD_PERSONALITY
#define MAX_WORK_PER_DISK 128
......
......@@ -18,13 +18,8 @@
Software Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
*/
#include <linux/module.h>
#include <linux/raid/raid0.h>
#define MAJOR_NR MD_MAJOR
#define MD_DRIVER
#define MD_PERSONALITY
static void raid0_unplug(struct request_queue *q)
{
mddev_t *mddev = q->queuedata;
......
......@@ -32,6 +32,7 @@
*/
#include "dm-bio-list.h"
#include <linux/delay.h>
#include <linux/raid/raid1.h>
#include <linux/raid/bitmap.h>
......
......@@ -19,6 +19,7 @@
*/
#include "dm-bio-list.h"
#include <linux/delay.h>
#include <linux/raid/raid10.h>
#include <linux/raid/bitmap.h>
......@@ -2028,8 +2029,9 @@ static int run(mddev_t *mddev)
int nc, fc, fo;
sector_t stride, size;
if (mddev->chunk_size == 0) {
printk(KERN_ERR "md/raid10: non-zero chunk size required.\n");
if (mddev->chunk_size < PAGE_SIZE) {
printk(KERN_ERR "md/raid10: chunk size must be "
"at least PAGE_SIZE(%ld).\n", PAGE_SIZE);
return -EINVAL;
}
......
......@@ -43,12 +43,7 @@
* miss any bits.
*/
#include <linux/module.h>
#include <linux/slab.h>
#include <linux/highmem.h>
#include <linux/bitops.h>
#include <linux/kthread.h>
#include <asm/atomic.h>
#include "raid6.h"
#include <linux/raid/bitmap.h>
......@@ -275,7 +270,7 @@ static int grow_buffers(struct stripe_head *sh, int num)
return 0;
}
static void raid5_build_block (struct stripe_head *sh, int i);
static void raid5_build_block(struct stripe_head *sh, int i);
static void init_stripe(struct stripe_head *sh, sector_t sector, int pd_idx, int disks)
{
......@@ -1151,7 +1146,7 @@ static void raid5_end_read_request(struct bio * bi, int error)
release_stripe(sh);
}
static void raid5_end_write_request (struct bio *bi, int error)
static void raid5_end_write_request(struct bio *bi, int error)
{
struct stripe_head *sh = bi->bi_private;
raid5_conf_t *conf = sh->raid_conf;
......@@ -1183,7 +1178,7 @@ static void raid5_end_write_request (struct bio *bi, int error)
static sector_t compute_blocknr(struct stripe_head *sh, int i);
static void raid5_build_block (struct stripe_head *sh, int i)
static void raid5_build_block(struct stripe_head *sh, int i)
{
struct r5dev *dev = &sh->dev[i];
......@@ -1221,10 +1216,10 @@ static void error(mddev_t *mddev, mdk_rdev_t *rdev)
set_bit(MD_RECOVERY_INTR, &mddev->recovery);
}
set_bit(Faulty, &rdev->flags);
printk (KERN_ALERT
"raid5: Disk failure on %s, disabling device.\n"
"raid5: Operation continuing on %d devices.\n",
bdevname(rdev->bdev,b), conf->raid_disks - mddev->degraded);
printk(KERN_ALERT
"raid5: Disk failure on %s, disabling device.\n"
"raid5: Operation continuing on %d devices.\n",
bdevname(rdev->bdev,b), conf->raid_disks - mddev->degraded);
}
}
......@@ -1320,8 +1315,8 @@ static sector_t raid5_compute_sector(sector_t r_sector, unsigned int raid_disks,
*dd_idx = (*pd_idx + 2 + *dd_idx) % raid_disks;
break;
default:
printk (KERN_CRIT "raid6: unsupported algorithm %d\n",