summaryrefslogtreecommitdiff
path: root/drivers/md/md.c
diff options
context:
space:
mode:
Diffstat (limited to 'drivers/md/md.c')
-rw-r--r--drivers/md/md.c297
1 files changed, 136 insertions, 161 deletions
diff --git a/drivers/md/md.c b/drivers/md/md.c
index 612343fdde94..09be637d52cb 100644
--- a/drivers/md/md.c
+++ b/drivers/md/md.c
@@ -440,15 +440,6 @@ static inline sector_t calc_dev_sboffset(struct block_device *bdev)
return MD_NEW_SIZE_SECTORS(num_sectors);
}
-static sector_t calc_num_sectors(mdk_rdev_t *rdev, unsigned chunk_size)
-{
- sector_t num_sectors = rdev->sb_start;
-
- if (chunk_size)
- num_sectors &= ~((sector_t)chunk_size/512 - 1);
- return num_sectors;
-}
-
static int alloc_disk_sb(mdk_rdev_t * rdev)
{
if (rdev->sb_page)
@@ -745,6 +736,24 @@ struct super_type {
};
/*
+ * Check that the given mddev has no bitmap.
+ *
+ * This function is called from the run method of all personalities that do not
+ * support bitmaps. It prints an error message and returns non-zero if mddev
+ * has a bitmap. Otherwise, it returns 0.
+ *
+ */
+int md_check_no_bitmap(mddev_t *mddev)
+{
+ if (!mddev->bitmap_file && !mddev->bitmap_offset)
+ return 0;
+ printk(KERN_ERR "%s: bitmaps are not supported for %s\n",
+ mdname(mddev), mddev->pers->name);
+ return 1;
+}
+EXPORT_SYMBOL(md_check_no_bitmap);
+
+/*
* load_super for 0.90.0
*/
static int super_90_load(mdk_rdev_t *rdev, mdk_rdev_t *refdev, int minor_version)
@@ -797,17 +806,6 @@ static int super_90_load(mdk_rdev_t *rdev, mdk_rdev_t *refdev, int minor_version
rdev->data_offset = 0;
rdev->sb_size = MD_SB_BYTES;
- if (sb->state & (1<<MD_SB_BITMAP_PRESENT)) {
- if (sb->level != 1 && sb->level != 4
- && sb->level != 5 && sb->level != 6
- && sb->level != 10) {
- /* FIXME use a better test */
- printk(KERN_WARNING
- "md: bitmaps not supported for this level.\n");
- goto abort;
- }
- }
-
if (sb->level == LEVEL_MULTIPATH)
rdev->desc_nr = -1;
else
@@ -836,7 +834,7 @@ static int super_90_load(mdk_rdev_t *rdev, mdk_rdev_t *refdev, int minor_version
else
ret = 0;
}
- rdev->sectors = calc_num_sectors(rdev, sb->chunk_size);
+ rdev->sectors = rdev->sb_start;
if (rdev->sectors < sb->size * 2 && sb->level > 1)
/* "this cannot possibly happen" ... */
@@ -866,7 +864,7 @@ static int super_90_validate(mddev_t *mddev, mdk_rdev_t *rdev)
mddev->minor_version = sb->minor_version;
mddev->patch_version = sb->patch_version;
mddev->external = 0;
- mddev->chunk_size = sb->chunk_size;
+ mddev->chunk_sectors = sb->chunk_size >> 9;
mddev->ctime = sb->ctime;
mddev->utime = sb->utime;
mddev->level = sb->level;
@@ -883,13 +881,13 @@ static int super_90_validate(mddev_t *mddev, mdk_rdev_t *rdev)
mddev->delta_disks = sb->delta_disks;
mddev->new_level = sb->new_level;
mddev->new_layout = sb->new_layout;
- mddev->new_chunk = sb->new_chunk;
+ mddev->new_chunk_sectors = sb->new_chunk >> 9;
} else {
mddev->reshape_position = MaxSector;
mddev->delta_disks = 0;
mddev->new_level = mddev->level;
mddev->new_layout = mddev->layout;
- mddev->new_chunk = mddev->chunk_size;
+ mddev->new_chunk_sectors = mddev->chunk_sectors;
}
if (sb->state & (1<<MD_SB_CLEAN))
@@ -1004,7 +1002,7 @@ static void super_90_sync(mddev_t *mddev, mdk_rdev_t *rdev)
sb->new_level = mddev->new_level;
sb->delta_disks = mddev->delta_disks;
sb->new_layout = mddev->new_layout;
- sb->new_chunk = mddev->new_chunk;
+ sb->new_chunk = mddev->new_chunk_sectors << 9;
}
mddev->minor_version = sb->minor_version;
if (mddev->in_sync)
@@ -1018,7 +1016,7 @@ static void super_90_sync(mddev_t *mddev, mdk_rdev_t *rdev)
sb->recovery_cp = 0;
sb->layout = mddev->layout;
- sb->chunk_size = mddev->chunk_size;
+ sb->chunk_size = mddev->chunk_sectors << 9;
if (mddev->bitmap && mddev->bitmap_file == NULL)
sb->state |= (1<<MD_SB_BITMAP_PRESENT);
@@ -1185,24 +1183,13 @@ static int super_1_load(mdk_rdev_t *rdev, mdk_rdev_t *refdev, int minor_version)
bdevname(rdev->bdev,b));
return -EINVAL;
}
- if ((le32_to_cpu(sb->feature_map) & MD_FEATURE_BITMAP_OFFSET)) {
- if (sb->level != cpu_to_le32(1) &&
- sb->level != cpu_to_le32(4) &&
- sb->level != cpu_to_le32(5) &&
- sb->level != cpu_to_le32(6) &&
- sb->level != cpu_to_le32(10)) {
- printk(KERN_WARNING
- "md: bitmaps not supported for this level.\n");
- return -EINVAL;
- }
- }
rdev->preferred_minor = 0xffff;
rdev->data_offset = le64_to_cpu(sb->data_offset);
atomic_set(&rdev->corrected_errors, le32_to_cpu(sb->cnt_corrected_read));
rdev->sb_size = le32_to_cpu(sb->max_dev) * 2 + 256;
- bmask = queue_hardsect_size(rdev->bdev->bd_disk->queue)-1;
+ bmask = queue_logical_block_size(rdev->bdev->bd_disk->queue)-1;
if (rdev->sb_size & bmask)
rdev->sb_size = (rdev->sb_size | bmask) + 1;
@@ -1248,9 +1235,6 @@ static int super_1_load(mdk_rdev_t *rdev, mdk_rdev_t *refdev, int minor_version)
if (rdev->sectors < le64_to_cpu(sb->data_size))
return -EINVAL;
rdev->sectors = le64_to_cpu(sb->data_size);
- if (le32_to_cpu(sb->chunksize))
- rdev->sectors &= ~((sector_t)le32_to_cpu(sb->chunksize) - 1);
-
if (le64_to_cpu(sb->size) > rdev->sectors)
return -EINVAL;
return ret;
@@ -1271,7 +1255,7 @@ static int super_1_validate(mddev_t *mddev, mdk_rdev_t *rdev)
mddev->major_version = 1;
mddev->patch_version = 0;
mddev->external = 0;
- mddev->chunk_size = le32_to_cpu(sb->chunksize) << 9;
+ mddev->chunk_sectors = le32_to_cpu(sb->chunksize);
mddev->ctime = le64_to_cpu(sb->ctime) & ((1ULL << 32)-1);
mddev->utime = le64_to_cpu(sb->utime) & ((1ULL << 32)-1);
mddev->level = le32_to_cpu(sb->level);
@@ -1297,13 +1281,13 @@ static int super_1_validate(mddev_t *mddev, mdk_rdev_t *rdev)
mddev->delta_disks = le32_to_cpu(sb->delta_disks);
mddev->new_level = le32_to_cpu(sb->new_level);
mddev->new_layout = le32_to_cpu(sb->new_layout);
- mddev->new_chunk = le32_to_cpu(sb->new_chunk)<<9;
+ mddev->new_chunk_sectors = le32_to_cpu(sb->new_chunk);
} else {
mddev->reshape_position = MaxSector;
mddev->delta_disks = 0;
mddev->new_level = mddev->level;
mddev->new_layout = mddev->layout;
- mddev->new_chunk = mddev->chunk_size;
+ mddev->new_chunk_sectors = mddev->chunk_sectors;
}
} else if (mddev->pers == NULL) {
@@ -1375,6 +1359,9 @@ static void super_1_sync(mddev_t *mddev, mdk_rdev_t *rdev)
sb->raid_disks = cpu_to_le32(mddev->raid_disks);
sb->size = cpu_to_le64(mddev->dev_sectors);
+ sb->chunksize = cpu_to_le32(mddev->chunk_sectors);
+ sb->level = cpu_to_le32(mddev->level);
+ sb->layout = cpu_to_le32(mddev->layout);
if (mddev->bitmap && mddev->bitmap_file == NULL) {
sb->bitmap_offset = cpu_to_le32((__u32)mddev->bitmap_offset);
@@ -1399,7 +1386,7 @@ static void super_1_sync(mddev_t *mddev, mdk_rdev_t *rdev)
sb->new_layout = cpu_to_le32(mddev->new_layout);
sb->delta_disks = cpu_to_le32(mddev->delta_disks);
sb->new_level = cpu_to_le32(mddev->new_level);
- sb->new_chunk = cpu_to_le32(mddev->new_chunk>>9);
+ sb->new_chunk = cpu_to_le32(mddev->new_chunk_sectors);
}
max_dev = 0;
@@ -1894,6 +1881,7 @@ static void md_update_sb(mddev_t * mddev, int force_change)
int sync_req;
int nospares = 0;
+ mddev->utime = get_seconds();
if (mddev->external)
return;
repeat:
@@ -1923,7 +1911,6 @@ repeat:
nospares = 0;
sync_req = mddev->in_sync;
- mddev->utime = get_seconds();
/* If this is just a dirty<->clean transition, and the array is clean
* and 'events' is odd, we can roll back to the previous clean state */
@@ -2594,15 +2581,6 @@ static void analyze_sbs(mddev_t * mddev)
clear_bit(In_sync, &rdev->flags);
}
}
-
-
-
- if (mddev->recovery_cp != MaxSector &&
- mddev->level >= 1)
- printk(KERN_ERR "md: %s: raid array is not clean"
- " -- starting background reconstruction\n",
- mdname(mddev));
-
}
static void md_safemode_timeout(unsigned long data);
@@ -2743,7 +2721,7 @@ level_store(mddev_t *mddev, const char *buf, size_t len)
if (IS_ERR(priv)) {
mddev->new_level = mddev->level;
mddev->new_layout = mddev->layout;
- mddev->new_chunk = mddev->chunk_size;
+ mddev->new_chunk_sectors = mddev->chunk_sectors;
mddev->raid_disks -= mddev->delta_disks;
mddev->delta_disks = 0;
module_put(pers->owner);
@@ -2761,7 +2739,7 @@ level_store(mddev_t *mddev, const char *buf, size_t len)
strlcpy(mddev->clevel, pers->name, sizeof(mddev->clevel));
mddev->level = mddev->new_level;
mddev->layout = mddev->new_layout;
- mddev->chunk_size = mddev->new_chunk;
+ mddev->chunk_sectors = mddev->new_chunk_sectors;
mddev->delta_disks = 0;
pers->run(mddev);
mddev_resume(mddev);
@@ -2797,11 +2775,14 @@ layout_store(mddev_t *mddev, const char *buf, size_t len)
if (mddev->pers) {
int err;
- if (mddev->pers->reconfig == NULL)
+ if (mddev->pers->check_reshape == NULL)
return -EBUSY;
- err = mddev->pers->reconfig(mddev, n, -1);
- if (err)
+ mddev->new_layout = n;
+ err = mddev->pers->check_reshape(mddev);
+ if (err) {
+ mddev->new_layout = mddev->layout;
return err;
+ }
} else {
mddev->new_layout = n;
if (mddev->reshape_position == MaxSector)
@@ -2854,10 +2835,11 @@ static ssize_t
chunk_size_show(mddev_t *mddev, char *page)
{
if (mddev->reshape_position != MaxSector &&
- mddev->chunk_size != mddev->new_chunk)
- return sprintf(page, "%d (%d)\n", mddev->new_chunk,
- mddev->chunk_size);
- return sprintf(page, "%d\n", mddev->chunk_size);
+ mddev->chunk_sectors != mddev->new_chunk_sectors)
+ return sprintf(page, "%d (%d)\n",
+ mddev->new_chunk_sectors << 9,
+ mddev->chunk_sectors << 9);
+ return sprintf(page, "%d\n", mddev->chunk_sectors << 9);
}
static ssize_t
@@ -2871,15 +2853,18 @@ chunk_size_store(mddev_t *mddev, const char *buf, size_t len)
if (mddev->pers) {
int err;
- if (mddev->pers->reconfig == NULL)
+ if (mddev->pers->check_reshape == NULL)
return -EBUSY;
- err = mddev->pers->reconfig(mddev, -1, n);
- if (err)
+ mddev->new_chunk_sectors = n >> 9;
+ err = mddev->pers->check_reshape(mddev);
+ if (err) {
+ mddev->new_chunk_sectors = mddev->chunk_sectors;
return err;
+ }
} else {
- mddev->new_chunk = n;
+ mddev->new_chunk_sectors = n >> 9;
if (mddev->reshape_position == MaxSector)
- mddev->chunk_size = n;
+ mddev->chunk_sectors = n >> 9;
}
return len;
}
@@ -3066,11 +3051,8 @@ array_state_store(mddev_t *mddev, const char *buf, size_t len)
} else
err = -EBUSY;
spin_unlock_irq(&mddev->write_lock);
- } else {
- mddev->ro = 0;
- mddev->recovery_cp = MaxSector;
- err = do_md_run(mddev);
- }
+ } else
+ err = -EINVAL;
break;
case active:
if (mddev->pers) {
@@ -3306,7 +3288,9 @@ static ssize_t
action_show(mddev_t *mddev, char *page)
{
char *type = "idle";
- if (test_bit(MD_RECOVERY_RUNNING, &mddev->recovery) ||
+ if (test_bit(MD_RECOVERY_FROZEN, &mddev->recovery))
+ type = "frozen";
+ else if (test_bit(MD_RECOVERY_RUNNING, &mddev->recovery) ||
(!mddev->ro && test_bit(MD_RECOVERY_NEEDED, &mddev->recovery))) {
if (test_bit(MD_RECOVERY_RESHAPE, &mddev->recovery))
type = "reshape";
@@ -3329,7 +3313,12 @@ action_store(mddev_t *mddev, const char *page, size_t len)
if (!mddev->pers || !mddev->pers->sync_request)
return -EINVAL;
- if (cmd_match(page, "idle")) {
+ if (cmd_match(page, "frozen"))
+ set_bit(MD_RECOVERY_FROZEN, &mddev->recovery);
+ else
+ clear_bit(MD_RECOVERY_FROZEN, &mddev->recovery);
+
+ if (cmd_match(page, "idle") || cmd_match(page, "frozen")) {
if (mddev->sync_thread) {
set_bit(MD_RECOVERY_INTR, &mddev->recovery);
md_unregister_thread(mddev->sync_thread);
@@ -3520,8 +3509,9 @@ min_sync_store(mddev_t *mddev, const char *buf, size_t len)
return -EBUSY;
/* Must be a multiple of chunk_size */
- if (mddev->chunk_size) {
- if (min & (sector_t)((mddev->chunk_size>>9)-1))
+ if (mddev->chunk_sectors) {
+ sector_t temp = min;
+ if (sector_div(temp, mddev->chunk_sectors))
return -EINVAL;
}
mddev->resync_min = min;
@@ -3557,8 +3547,9 @@ max_sync_store(mddev_t *mddev, const char *buf, size_t len)
return -EBUSY;
/* Must be a multiple of chunk_size */
- if (mddev->chunk_size) {
- if (max & (sector_t)((mddev->chunk_size>>9)-1))
+ if (mddev->chunk_sectors) {
+ sector_t temp = max;
+ if (sector_div(temp, mddev->chunk_sectors))
return -EINVAL;
}
mddev->resync_max = max;
@@ -3649,7 +3640,7 @@ reshape_position_store(mddev_t *mddev, const char *buf, size_t len)
mddev->delta_disks = 0;
mddev->new_level = mddev->level;
mddev->new_layout = mddev->layout;
- mddev->new_chunk = mddev->chunk_size;
+ mddev->new_chunk_sectors = mddev->chunk_sectors;
return len;
}
@@ -3683,7 +3674,7 @@ array_size_store(mddev_t *mddev, const char *buf, size_t len)
if (strict_blocks_to_sectors(buf, &sectors) < 0)
return -EINVAL;
if (mddev->pers && mddev->pers->size(mddev, 0, 0) < sectors)
- return -EINVAL;
+ return -E2BIG;
mddev->external_size = 1;
}
@@ -3969,11 +3960,9 @@ static int start_dirty_degraded;
static int do_md_run(mddev_t * mddev)
{
int err;
- int chunk_size;
mdk_rdev_t *rdev;
struct gendisk *disk;
struct mdk_personality *pers;
- char b[BDEVNAME_SIZE];
if (list_empty(&mddev->disks))
/* cannot run an array with no devices.. */
@@ -3991,38 +3980,6 @@ static int do_md_run(mddev_t * mddev)
analyze_sbs(mddev);
}
- chunk_size = mddev->chunk_size;
-
- if (chunk_size) {
- if (chunk_size > MAX_CHUNK_SIZE) {
- printk(KERN_ERR "too big chunk_size: %d > %d\n",
- chunk_size, MAX_CHUNK_SIZE);
- return -EINVAL;
- }
- /*
- * 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;
- }
-
- /* devices must have minimum size of one chunk */
- list_for_each_entry(rdev, &mddev->disks, same_set) {
- if (test_bit(Faulty, &rdev->flags))
- continue;
- if (rdev->sectors < chunk_size / 512) {
- printk(KERN_WARNING
- "md: Dev %s smaller than chunk_size:"
- " %llu < %d\n",
- bdevname(rdev->bdev,b),
- (unsigned long long)rdev->sectors,
- chunk_size / 512);
- return -EINVAL;
- }
- }
- }
-
if (mddev->level != LEVEL_NONE)
request_module("md-level-%d", mddev->level);
else if (mddev->clevel[0])
@@ -4297,6 +4254,7 @@ static int do_md_stop(mddev_t * mddev, int mode, int is_open)
{
int err = 0;
struct gendisk *disk = mddev->gendisk;
+ mdk_rdev_t *rdev;
if (atomic_read(&mddev->openers) > is_open) {
printk("md: %s still in use.\n",mdname(mddev));
@@ -4339,6 +4297,13 @@ static int do_md_stop(mddev_t * mddev, int mode, int is_open)
/* tell userspace to handle 'inactive' */
sysfs_notify_dirent(mddev->sysfs_state);
+ list_for_each_entry(rdev, &mddev->disks, same_set)
+ if (rdev->raid_disk >= 0) {
+ char nm[20];
+ sprintf(nm, "rd%d", rdev->raid_disk);
+ sysfs_remove_link(&mddev->kobj, nm);
+ }
+
set_capacity(disk, 0);
mddev->changed = 1;
@@ -4359,7 +4324,6 @@ static int do_md_stop(mddev_t * mddev, int mode, int is_open)
* Free resources if final stop
*/
if (mode == 0) {
- mdk_rdev_t *rdev;
printk(KERN_INFO "md: %s stopped.\n", mdname(mddev));
@@ -4371,13 +4335,6 @@ static int do_md_stop(mddev_t * mddev, int mode, int is_open)
}
mddev->bitmap_offset = 0;
- list_for_each_entry(rdev, &mddev->disks, same_set)
- if (rdev->raid_disk >= 0) {
- char nm[20];
- sprintf(nm, "rd%d", rdev->raid_disk);
- sysfs_remove_link(&mddev->kobj, nm);
- }
-
/* make sure all md_delayed_delete calls have finished */
flush_scheduled_work();
@@ -4398,7 +4355,7 @@ static int do_md_stop(mddev_t * mddev, int mode, int is_open)
mddev->flags = 0;
mddev->ro = 0;
mddev->metadata_type[0] = 0;
- mddev->chunk_size = 0;
+ mddev->chunk_sectors = 0;
mddev->ctime = mddev->utime = 0;
mddev->layout = 0;
mddev->max_disks = 0;
@@ -4406,7 +4363,7 @@ static int do_md_stop(mddev_t * mddev, int mode, int is_open)
mddev->delta_disks = 0;
mddev->new_level = LEVEL_NONE;
mddev->new_layout = 0;
- mddev->new_chunk = 0;
+ mddev->new_chunk_sectors = 0;
mddev->curr_resync = 0;
mddev->resync_mismatches = 0;
mddev->suspend_lo = mddev->suspend_hi = 0;
@@ -4611,7 +4568,7 @@ static int get_array_info(mddev_t * mddev, void __user * arg)
info.spare_disks = spare;
info.layout = mddev->layout;
- info.chunk_size = mddev->chunk_size;
+ info.chunk_size = mddev->chunk_sectors << 9;
if (copy_to_user(arg, &info, sizeof(info)))
return -EFAULT;
@@ -4836,7 +4793,7 @@ static int add_new_disk(mddev_t * mddev, mdu_disk_info_t *info)
rdev->sb_start = rdev->bdev->bd_inode->i_size / 512;
} else
rdev->sb_start = calc_dev_sboffset(rdev->bdev);
- rdev->sectors = calc_num_sectors(rdev, mddev->chunk_size);
+ rdev->sectors = rdev->sb_start;
err = bind_rdev_to_array(rdev, mddev);
if (err) {
@@ -4906,7 +4863,7 @@ static int hot_add_disk(mddev_t * mddev, dev_t dev)
else
rdev->sb_start = rdev->bdev->bd_inode->i_size / 512;
- rdev->sectors = calc_num_sectors(rdev, mddev->chunk_size);
+ rdev->sectors = rdev->sb_start;
if (test_bit(Faulty, &rdev->flags)) {
printk(KERN_WARNING
@@ -5055,7 +5012,7 @@ static int set_array_info(mddev_t * mddev, mdu_array_info_t *info)
mddev->external = 0;
mddev->layout = info->layout;
- mddev->chunk_size = info->chunk_size;
+ mddev->chunk_sectors = info->chunk_size >> 9;
mddev->max_disks = MD_SB_DISKS;
@@ -5074,7 +5031,7 @@ static int set_array_info(mddev_t * mddev, mdu_array_info_t *info)
get_random_bytes(mddev->uuid, 16);
mddev->new_level = mddev->level;
- mddev->new_chunk = mddev->chunk_size;
+ mddev->new_chunk_sectors = mddev->chunk_sectors;
mddev->new_layout = mddev->layout;
mddev->delta_disks = 0;
@@ -5184,7 +5141,7 @@ static int update_array_info(mddev_t *mddev, mdu_array_info_t *info)
mddev->level != info->level ||
/* mddev->layout != info->layout || */
!mddev->persistent != info->not_persistent||
- mddev->chunk_size != info->chunk_size ||
+ mddev->chunk_sectors != info->chunk_size >> 9 ||
/* ignore bottom 8 bits of state, and allow SB_BITMAP_PRESENT to change */
((state^info->state) & 0xfffffe00)
)
@@ -5208,10 +5165,15 @@ static int update_array_info(mddev_t *mddev, mdu_array_info_t *info)
* we don't need to do anything at the md level, the
* personality will take care of it all.
*/
- if (mddev->pers->reconfig == NULL)
+ if (mddev->pers->check_reshape == NULL)
return -EINVAL;
- else
- return mddev->pers->reconfig(mddev, info->layout, -1);
+ else {
+ mddev->new_layout = info->layout;
+ rv = mddev->pers->check_reshape(mddev);
+ if (rv)
+ mddev->new_layout = mddev->layout;
+ return rv;
+ }
}
if (info->size >= 0 && mddev->dev_sectors / 2 != info->size)
rv = update_size(mddev, (sector_t)info->size * 2);
@@ -5560,7 +5522,7 @@ static struct block_device_operations md_fops =
.owner = THIS_MODULE,
.open = md_open,
.release = md_release,
- .locked_ioctl = md_ioctl,
+ .ioctl = md_ioctl,
.getgeo = md_getgeo,
.media_changed = md_media_changed,
.revalidate_disk= md_revalidate,
@@ -5705,37 +5667,38 @@ static void status_unused(struct seq_file *seq)
static void status_resync(struct seq_file *seq, mddev_t * mddev)
{
- sector_t max_blocks, resync, res;
- unsigned long dt, db, rt;
+ sector_t max_sectors, resync, res;
+ unsigned long dt, db;
+ sector_t rt;
int scale;
unsigned int per_milli;
- resync = (mddev->curr_resync - atomic_read(&mddev->recovery_active))/2;
+ resync = mddev->curr_resync - atomic_read(&mddev->recovery_active);
if (test_bit(MD_RECOVERY_SYNC, &mddev->recovery))
- max_blocks = mddev->resync_max_sectors >> 1;
+ max_sectors = mddev->resync_max_sectors;
else
- max_blocks = mddev->dev_sectors / 2;
+ max_sectors = mddev->dev_sectors;
/*
* Should not happen.
*/
- if (!max_blocks) {
+ if (!max_sectors) {
MD_BUG();
return;
}
/* Pick 'scale' such that (resync>>scale)*1000 will fit
- * in a sector_t, and (max_blocks>>scale) will fit in a
+ * in a sector_t, and (max_sectors>>scale) will fit in a
* u32, as those are the requirements for sector_div.
* Thus 'scale' must be at least 10
*/
scale = 10;
if (sizeof(sector_t) > sizeof(unsigned long)) {
- while ( max_blocks/2 > (1ULL<<(scale+32)))
+ while ( max_sectors/2 > (1ULL<<(scale+32)))
scale++;
}
res = (resync>>scale)*1000;
- sector_div(res, (u32)((max_blocks>>scale)+1));
+ sector_div(res, (u32)((max_sectors>>scale)+1));
per_milli = res;
{
@@ -5756,25 +5719,35 @@ static void status_resync(struct seq_file *seq, mddev_t * mddev)
(test_bit(MD_RECOVERY_SYNC, &mddev->recovery) ?
"resync" : "recovery"))),
per_milli/10, per_milli % 10,
- (unsigned long long) resync,
- (unsigned long long) max_blocks);
+ (unsigned long long) resync/2,
+ (unsigned long long) max_sectors/2);
/*
- * We do not want to overflow, so the order of operands and
- * the * 100 / 100 trick are important. We do a +1 to be
- * safe against division by zero. We only estimate anyway.
- *
* dt: time from mark until now
* db: blocks written from mark until now
* rt: remaining time
+ *
+ * rt is a sector_t, so could be 32bit or 64bit.
+ * So we divide before multiply in case it is 32bit and close
+ * to the limit.
+ * We scale the divisor (db) by 32 to avoid loosing precision
+ * near the end of resync when the number of remaining sectors
+ * is close to 'db'.
+ * We then divide rt by 32 after multiplying by db to compensate.
+ * The '+1' avoids division by zero if db is very small.
*/
dt = ((jiffies - mddev->resync_mark) / HZ);
if (!dt) dt++;
db = (mddev->curr_mark_cnt - atomic_read(&mddev->recovery_active))
- mddev->resync_mark_cnt;
- rt = (dt * ((unsigned long)(max_blocks-resync) / (db/2/100+1)))/100;
- seq_printf(seq, " finish=%lu.%lumin", rt / 60, (rt % 60)/6);
+ rt = max_sectors - resync; /* number of remaining sectors */
+ sector_div(rt, db/32+1);
+ rt *= dt;
+ rt >>= 5;
+
+ seq_printf(seq, " finish=%lu.%lumin", (unsigned long)rt / 60,
+ ((unsigned long)rt % 60)/6);
seq_printf(seq, " speed=%ldK/sec", db/2/dt);
}
@@ -5965,7 +5938,7 @@ static int md_seq_show(struct seq_file *seq, void *v)
return 0;
}
-static struct seq_operations md_seq_ops = {
+static const struct seq_operations md_seq_ops = {
.start = md_seq_start,
.next = md_seq_next,
.stop = md_seq_stop,
@@ -6344,12 +6317,13 @@ void md_do_sync(mddev_t *mddev)
skipped = 0;
- if ((mddev->curr_resync > mddev->curr_resync_completed &&
- (mddev->curr_resync - mddev->curr_resync_completed)
- > (max_sectors >> 4)) ||
- (j - mddev->curr_resync_completed)*2
- >= mddev->resync_max - mddev->curr_resync_completed
- ) {
+ if (!test_bit(MD_RECOVERY_RESHAPE, &mddev->recovery) &&
+ ((mddev->curr_resync > mddev->curr_resync_completed &&
+ (mddev->curr_resync - mddev->curr_resync_completed)
+ > (max_sectors >> 4)) ||
+ (j - mddev->curr_resync_completed)*2
+ >= mddev->resync_max - mddev->curr_resync_completed
+ )) {
/* time to update curr_resync_completed */
blk_unplug(mddev->queue);
wait_event(mddev->recovery_wait,
@@ -6698,7 +6672,8 @@ void md_check_recovery(mddev_t *mddev)
*/
if (mddev->reshape_position != MaxSector) {
- if (mddev->pers->check_reshape(mddev) != 0)
+ if (mddev->pers->check_reshape == NULL ||
+ mddev->pers->check_reshape(mddev) != 0)
/* Cannot proceed */
goto unlock;
set_bit(MD_RECOVERY_RESHAPE, &mddev->recovery);
generated by cgit v1.2.3 (git 2.51.0) at 2025-09-20 07:39:09 +0000