#include <linux/module.h>
#include <linux/config.h>
+#include <linux/kthread.h>
#include <linux/linkage.h>
#include <linux/raid/md.h>
#include <linux/raid/bitmap.h>
* Current RAID-1,4,5 parallel reconstruction 'guaranteed speed limit'
* is 1000 KB/sec, so the extra system load does not show up that much.
* Increase it if you want to have more _guaranteed_ speed. Note that
- * the RAID driver will use the maximum available bandwith if the IO
+ * the RAID driver will use the maximum available bandwidth if the IO
* subsystem is idle. There is also an 'absolute maximum' reconstruction
* speed limit - in case reconstruction slows down your system despite
* idle IO detection.
return ret;
}
-static int read_disk_sb(mdk_rdev_t * rdev)
+static int read_disk_sb(mdk_rdev_t * rdev, int size)
{
char b[BDEVNAME_SIZE];
if (!rdev->sb_page) {
return 0;
- if (!sync_page_io(rdev->bdev, rdev->sb_offset<<1, MD_SB_BYTES, rdev->sb_page, READ))
+ if (!sync_page_io(rdev->bdev, rdev->sb_offset<<1, size, rdev->sb_page, READ))
goto fail;
rdev->sb_loaded = 1;
return 0;
sb_offset = calc_dev_sboffset(rdev->bdev);
rdev->sb_offset = sb_offset;
- ret = read_disk_sb(rdev);
+ ret = read_disk_sb(rdev, MD_SB_BYTES);
if (ret) return ret;
ret = -EINVAL;
rdev->preferred_minor = sb->md_minor;
rdev->data_offset = 0;
+ rdev->sb_size = MD_SB_BYTES;
if (sb->level == LEVEL_MULTIPATH)
rdev->desc_nr = -1;
if (sb->state & (1<<MD_SB_BITMAP_PRESENT) &&
mddev->bitmap_file == NULL) {
- if (mddev->level != 1) {
+ if (mddev->level != 1 && mddev->level != 5 && mddev->level != 6) {
/* FIXME use a better test */
printk(KERN_WARNING "md: bitmaps only support for raid1\n");
return -EINVAL;
int i;
int active=0, working=0,failed=0,spare=0,nr_disks=0;
+ rdev->sb_size = MD_SB_BYTES;
+
sb = (mdp_super_t*)page_address(rdev->sb_page);
memset(sb, 0, sizeof(*sb));
int ret;
sector_t sb_offset;
char b[BDEVNAME_SIZE], b2[BDEVNAME_SIZE];
+ int bmask;
/*
* Calculate the position of the superblock.
}
rdev->sb_offset = sb_offset;
- ret = read_disk_sb(rdev);
+ /* superblock is rarely larger than 1K, but it can be larger,
+ * and it is safe to read 4k, so we do that
+ */
+ ret = read_disk_sb(rdev, 4096);
if (ret) return ret;
sb->major_version != cpu_to_le32(1) ||
le32_to_cpu(sb->max_dev) > (4096-256)/2 ||
le64_to_cpu(sb->super_offset) != (rdev->sb_offset<<1) ||
- sb->feature_map != 0)
+ (le32_to_cpu(sb->feature_map) & ~MD_FEATURE_ALL) != 0)
return -EINVAL;
if (calc_sb_1_csum(sb) != sb->sb_csum) {
rdev->preferred_minor = 0xffff;
rdev->data_offset = le64_to_cpu(sb->data_offset);
+ rdev->sb_size = le32_to_cpu(sb->max_dev) * 2 + 256;
+ bmask = queue_hardsect_size(rdev->bdev->bd_disk->queue)-1;
+ if (rdev->sb_size & bmask)
+ rdev-> sb_size = (rdev->sb_size | bmask)+1;
+
if (refdev == 0)
return 1;
else {
mddev->events = le64_to_cpu(sb->events);
mddev->bitmap_offset = 0;
mddev->default_bitmap_offset = 0;
- if (mddev->minor_version == 0)
- mddev->default_bitmap_offset = -(64*1024)/512;
+ mddev->default_bitmap_offset = 1024;
mddev->recovery_cp = le64_to_cpu(sb->resync_offset);
memcpy(mddev->uuid, sb->set_uuid, 16);
mddev->max_disks = (4096-256)/2;
- if ((le32_to_cpu(sb->feature_map) & 1) &&
+ if ((le32_to_cpu(sb->feature_map) & MD_FEATURE_BITMAP_OFFSET) &&
mddev->bitmap_file == NULL ) {
if (mddev->level != 1) {
printk(KERN_WARNING "md: bitmaps only supported for raid1\n");
if (mddev->bitmap && mddev->bitmap_file == NULL) {
sb->bitmap_offset = cpu_to_le32((__u32)mddev->bitmap_offset);
- sb->feature_map = cpu_to_le32(1);
+ sb->feature_map = cpu_to_le32(MD_FEATURE_BITMAP_OFFSET);
}
max_dev = 0;
dprintk("%s ", bdevname(rdev->bdev,b));
if (!rdev->faulty) {
md_super_write(mddev,rdev,
- rdev->sb_offset<<1, MD_SB_BYTES,
+ rdev->sb_offset<<1, rdev->sb_size,
rdev->sb_page);
dprintk(KERN_INFO "(write) %s's sb offset: %llu\n",
bdevname(rdev->bdev,b),
mdname(mddev));
return -EINVAL;
}
- rdev = md_import_device(dev, mddev->major_version,
- mddev->minor_version);
+ if (mddev->persistent)
+ rdev = md_import_device(dev, mddev->major_version,
+ mddev->minor_version);
+ else
+ rdev = md_import_device(dev, -1, -1);
if (IS_ERR(rdev)) {
printk(KERN_WARNING
"md: md_import_device returned %ld\n",
{
mdk_thread_t *thread = arg;
- lock_kernel();
-
- /*
- * Detach thread
- */
-
- daemonize(thread->name, mdname(thread->mddev));
-
- current->exit_signal = SIGCHLD;
- allow_signal(SIGKILL);
- thread->tsk = current;
-
/*
* md_thread is a 'system-thread', it's priority should be very
* high. We avoid resource deadlocks individually in each
* bdflush, otherwise bdflush will deadlock if there are too
* many dirty RAID5 blocks.
*/
- unlock_kernel();
complete(thread->event);
- while (thread->run) {
+ while (!kthread_should_stop()) {
void (*run)(mddev_t *);
wait_event_interruptible_timeout(thread->wqueue,
- test_bit(THREAD_WAKEUP, &thread->flags),
+ test_bit(THREAD_WAKEUP, &thread->flags)
+ || kthread_should_stop(),
thread->timeout);
try_to_freeze();
run = thread->run;
if (run)
run(thread->mddev);
-
- if (signal_pending(current))
- flush_signals(current);
}
- complete(thread->event);
+
return 0;
}
const char *name)
{
mdk_thread_t *thread;
- int ret;
struct completion event;
- thread = (mdk_thread_t *) kmalloc
- (sizeof(mdk_thread_t), GFP_KERNEL);
+ thread = kmalloc(sizeof(mdk_thread_t), GFP_KERNEL);
if (!thread)
return NULL;
thread->mddev = mddev;
thread->name = name;
thread->timeout = MAX_SCHEDULE_TIMEOUT;
- ret = kernel_thread(md_thread, thread, 0);
- if (ret < 0) {
+ thread->tsk = kthread_run(md_thread, thread, mdname(thread->mddev));
+ if (IS_ERR(thread->tsk)) {
kfree(thread);
return NULL;
}
void md_unregister_thread(mdk_thread_t *thread)
{
- struct completion event;
-
- init_completion(&event);
-
- thread->event = &event;
-
- /* As soon as ->run is set to NULL, the task could disappear,
- * so we need to hold tasklist_lock until we have sent the signal
- */
dprintk("interrupting MD-thread pid %d\n", thread->tsk->pid);
- read_lock(&tasklist_lock);
- thread->run = NULL;
- send_sig(SIGKILL, thread->tsk, 1);
- read_unlock(&tasklist_lock);
- wait_for_completion(&event);
+
+ kthread_stop(thread->tsk);
kfree(thread);
}
if (rdev->faulty) {
seq_printf(seq, "(F)");
continue;
- }
+ } else if (rdev->raid_disk < 0)
+ seq_printf(seq, "(S)"); /* spare */
size += rdev->size;
}
seq_printf(seq, "\n %llu blocks",
(unsigned long long)size);
}
+ if (mddev->persistent) {
+ if (mddev->major_version != 0 ||
+ mddev->minor_version != 90) {
+ seq_printf(seq," super %d.%d",
+ mddev->major_version,
+ mddev->minor_version);
+ }
+ } else
+ seq_printf(seq, " super non-persistent");
if (mddev->pers) {
mddev->pers->status (seq, mddev);
*/
void md_write_start(mddev_t *mddev, struct bio *bi)
{
- DEFINE_WAIT(w);
if (bio_data_dir(bi) != WRITE)
return;
printk(KERN_INFO "md: syncing RAID array %s\n", mdname(mddev));
printk(KERN_INFO "md: minimum _guaranteed_ reconstruction speed:"
" %d KB/sec/disc.\n", sysctl_speed_limit_min);
- printk(KERN_INFO "md: using maximum available idle IO bandwith "
+ printk(KERN_INFO "md: using maximum available idle IO bandwidth "
"(but not more than %d KB/sec) for reconstruction.\n",
sysctl_speed_limit_max);