static void process_suspend_info(struct mddev *mddev,
int slot, sector_t lo, sector_t hi)
{
struct md_cluster_info *cinfo = mddev->cluster_info;
struct suspend_info *s;
if (!hi) {
remove_suspend_info(mddev, slot);
set_bit(MD_RECOVERY_NEEDED, &mddev->recovery);
md_wakeup_thread(mddev->thread);
return;
}
s = kzalloc(sizeof(struct suspend_info), GFP_KERNEL);
if (!s)
return;
s->slot = slot;
s->lo = lo;
s->hi = hi;
mddev->pers->quiesce(mddev, 1);
mddev->pers->quiesce(mddev, 0);
spin_lock_irq(&cinfo->suspend_lock);
/* Remove existing entry (if exists) before adding */
__remove_suspend_info(cinfo, slot);
list_add(&s->list, &cinfo->suspend_list);
spin_unlock_irq(&cinfo->suspend_lock);
mddev->pers->quiesce(mddev, 2);
}
/*
* The BAST function for the ack lock resource
* This function wakes up the receive thread in
* order to receive and process the message.
*/
static void ack_bast(void *arg, int mode)
{
struct dlm_lock_resource *res = (struct dlm_lock_resource *)arg;
struct md_cluster_info *cinfo = res->mddev->cluster_info;
if (mode == DLM_LOCK_EX)
md_wakeup_thread(cinfo->recv_thread);
}
static void process_metadata_update(struct mddev *mddev, struct cluster_msg *msg)
{
struct md_cluster_info *cinfo = mddev->cluster_info;
mddev->good_device_nr = le32_to_cpu(msg->raid_slot);
set_bit(MD_RELOAD_SB, &mddev->flags);
dlm_lock_sync(cinfo->no_new_dev_lockres, DLM_LOCK_CR);
md_wakeup_thread(mddev->thread);
}
static void recover_bitmaps(struct md_thread *thread)
{
struct mddev *mddev = thread->mddev;
struct md_cluster_info *cinfo = mddev->cluster_info;
struct dlm_lock_resource *bm_lockres;
char str[64];
int slot, ret;
struct suspend_info *s, *tmp;
sector_t lo, hi;
while (cinfo->recovery_map) {
slot = fls64((u64)cinfo->recovery_map) - 1;
/* Clear suspend_area associated with the bitmap */
spin_lock_irq(&cinfo->suspend_lock);
list_for_each_entry_safe(s, tmp, &cinfo->suspend_list, list)
if (slot == s->slot) {
list_del(&s->list);
kfree(s);
}
spin_unlock_irq(&cinfo->suspend_lock);
snprintf(str, 64, "bitmap%04d", slot);
bm_lockres = lockres_init(mddev, str, NULL, 1);
if (!bm_lockres) {
pr_err("md-cluster: Cannot initialize bitmaps\n");
goto clear_bit;
}
ret = dlm_lock_sync(bm_lockres, DLM_LOCK_PW);
if (ret) {
pr_err("md-cluster: Could not DLM lock %s: %d\n",
str, ret);
goto clear_bit;
}
ret = bitmap_copy_from_slot(mddev, slot, &lo, &hi, true);
if (ret) {
pr_err("md-cluster: Could not copy data from bitmap %d\n", slot);
goto dlm_unlock;
}
if (hi > 0) {
if (lo < mddev->recovery_cp)
mddev->recovery_cp = lo;
/* wake up thread to continue resync in case resync
* is not finished */
if (mddev->recovery_cp != MaxSector) {
set_bit(MD_RECOVERY_NEEDED, &mddev->recovery);
md_wakeup_thread(mddev->thread);
}
}
dlm_unlock:
dlm_unlock_sync(bm_lockres);
clear_bit:
lockres_free(bm_lockres);
clear_bit(slot, &cinfo->recovery_map);
}
}
static void multipath_reschedule_retry (struct multipath_bh *mp_bh)
{
unsigned long flags;
mddev_t *mddev = mp_bh->mddev;
multipath_conf_t *conf = mddev_to_conf(mddev);
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);
}
static void load_bitmaps(struct mddev *mddev, int total_slots)
{
struct md_cluster_info *cinfo = mddev->cluster_info;
/* load all the node's bitmap info for resync */
if (gather_all_resync_info(mddev, total_slots))
pr_err("md-cluster: failed to gather all resyn infos\n");
set_bit(MD_CLUSTER_ALREADY_IN_CLUSTER, &cinfo->state);
/* wake up recv thread in case something need to be handled */
if (test_and_clear_bit(MD_CLUSTER_PENDING_RECV_EVENT, &cinfo->state))
md_wakeup_thread(cinfo->recv_thread);
}
/*
* The BAST function for the ack lock resource
* This function wakes up the receive thread in
* order to receive and process the message.
*/
static void ack_bast(void *arg, int mode)
{
struct dlm_lock_resource *res = arg;
struct md_cluster_info *cinfo = res->mddev->cluster_info;
if (mode == DLM_LOCK_EX) {
if (test_bit(MD_CLUSTER_ALREADY_IN_CLUSTER, &cinfo->state))
md_wakeup_thread(cinfo->recv_thread);
else
set_bit(MD_CLUSTER_PENDING_RECV_EVENT, &cinfo->state);
}
}
static void process_suspend_info(struct mddev *mddev,
int slot, sector_t lo, sector_t hi)
{
struct md_cluster_info *cinfo = mddev->cluster_info;
struct suspend_info *s;
if (!hi) {
remove_suspend_info(mddev, slot);
set_bit(MD_RECOVERY_NEEDED, &mddev->recovery);
md_wakeup_thread(mddev->thread);
return;
}
/*
* The bitmaps are not same for different nodes
* if RESYNCING is happening in one node, then
* the node which received the RESYNCING message
* probably will perform resync with the region
* [lo, hi] again, so we could reduce resync time
* a lot if we can ensure that the bitmaps among
* different nodes are match up well.
*
* sync_low/hi is used to record the region which
* arrived in the previous RESYNCING message,
*
* Call bitmap_sync_with_cluster to clear
* NEEDED_MASK and set RESYNC_MASK since
* resync thread is running in another node,
* so we don't need to do the resync again
* with the same section */
bitmap_sync_with_cluster(mddev, cinfo->sync_low,
cinfo->sync_hi,
lo, hi);
cinfo->sync_low = lo;
cinfo->sync_hi = hi;
s = kzalloc(sizeof(struct suspend_info), GFP_KERNEL);
if (!s)
return;
s->slot = slot;
s->lo = lo;
s->hi = hi;
mddev->pers->quiesce(mddev, 1);
mddev->pers->quiesce(mddev, 0);
spin_lock_irq(&cinfo->suspend_lock);
/* Remove existing entry (if exists) before adding */
__remove_suspend_info(cinfo, slot);
list_add(&s->list, &cinfo->suspend_list);
spin_unlock_irq(&cinfo->suspend_lock);
mddev->pers->quiesce(mddev, 2);
}
static void multipath_reschedule_retry (struct multipath_bh *mp_bh)
{
unsigned long flags;
mddev_t *mddev = mp_bh->mddev;
spin_lock_irqsave(&retry_list_lock, flags);
if (multipath_retry_list == NULL)
multipath_retry_tail = &multipath_retry_list;
*multipath_retry_tail = mp_bh;
multipath_retry_tail = &mp_bh->next_mp;
mp_bh->next_mp = NULL;
spin_unlock_irqrestore(&retry_list_lock, flags);
md_wakeup_thread(mddev->thread);
}
static void process_remove_disk(struct mddev *mddev, struct cluster_msg *msg)
{
struct md_rdev *rdev = md_find_rdev_nr_rcu(mddev,
le32_to_cpu(msg->raid_slot));
if (rdev) {
set_bit(ClusterRemove, &rdev->flags);
set_bit(MD_RECOVERY_NEEDED, &mddev->recovery);
md_wakeup_thread(mddev->thread);
}
else
pr_warn("%s: %d Could not find disk(%d) to REMOVE\n",
__func__, __LINE__, le32_to_cpu(msg->raid_slot));
}
static void __recover_slot(struct mddev *mddev, int slot)
{
struct md_cluster_info *cinfo = mddev->cluster_info;
set_bit(slot, &cinfo->recovery_map);
if (!cinfo->recovery_thread) {
cinfo->recovery_thread = md_register_thread(recover_bitmaps,
mddev, "recover");
if (!cinfo->recovery_thread) {
pr_warn("md-cluster: Could not create recovery thread\n");
return;
}
}
md_wakeup_thread(cinfo->recovery_thread);
}
/*
* write out a page to a file
*/
static int write_page(struct bitmap *bitmap, struct page *page, int wait)
{
int ret = -ENOMEM;
if (bitmap->file == NULL)
return write_sb_page(bitmap->mddev, bitmap->offset, page, wait);
flush_dcache_page(page); /* make sure visible to anyone reading the file */
if (wait)
lock_page(page);
else {
if (TestSetPageLocked(page))
return -EAGAIN; /* already locked */
if (PageWriteback(page)) {
unlock_page(page);
return -EAGAIN;
}
}
ret = page->mapping->a_ops->prepare_write(bitmap->file, page, 0, PAGE_SIZE);
if (!ret)
ret = page->mapping->a_ops->commit_write(bitmap->file, page, 0,
PAGE_SIZE);
if (ret) {
unlock_page(page);
return ret;
}
set_page_dirty(page); /* force it to be written out */
if (!wait) {
/* add to list to be waited for by daemon */
struct page_list *item = mempool_alloc(bitmap->write_pool, GFP_NOIO);
item->page = page;
get_page(page);
spin_lock(&bitmap->write_lock);
list_add(&item->list, &bitmap->complete_pages);
spin_unlock(&bitmap->write_lock);
md_wakeup_thread(bitmap->writeback_daemon);
}
return write_one_page(page, wait);
}
static void recover_slot(void *arg, struct dlm_slot *slot)
{
struct mddev *mddev = arg;
struct md_cluster_info *cinfo = mddev->cluster_info;
pr_info("md-cluster: %s Node %d/%d down. My slot: %d. Initiating recovery.\n",
mddev->bitmap_info.cluster_name,
slot->nodeid, slot->slot,
cinfo->slot_number);
set_bit(slot->slot - 1, &cinfo->recovery_map);
if (!cinfo->recovery_thread) {
cinfo->recovery_thread = md_register_thread(recover_bitmaps,
mddev, "recover");
if (!cinfo->recovery_thread) {
pr_warn("md-cluster: Could not create recovery thread\n");
return;
}
}
md_wakeup_thread(cinfo->recovery_thread);
}
/* * bitmap_init_from_disk -- called at bitmap_create time to initialize
* the in-memory bitmap from the on-disk bitmap -- also, sets up the
* memory mapping of the bitmap file
* Special cases:
* if there's no bitmap file, or if the bitmap file had been
* previously kicked from the array, we mark all the bits as
* 1's in order to cause a full resync.
*
* We ignore all bits for sectors that end earlier than 'start'.
* This is used when reading an out-of-date bitmap...
*/
static int bitmap_init_from_disk(struct bitmap *bitmap, sector_t start)
{
unsigned long i, chunks, index, oldindex, bit;
struct page *page = NULL, *oldpage = NULL;
unsigned long num_pages, bit_cnt = 0;
struct file *file;
unsigned long bytes, offset;
int outofdate;
int ret = -ENOSPC;
void *paddr;
chunks = bitmap->chunks;
file = bitmap->file;
BUG_ON(!file && !bitmap->offset);
#ifdef INJECT_FAULTS_3
outofdate = 1;
#else
outofdate = bitmap->flags & BITMAP_STALE;
#endif
if (outofdate)
printk(KERN_INFO "%s: bitmap file is out of date, doing full "
"recovery\n", bmname(bitmap));
bytes = (chunks + 7) / 8;
num_pages = (bytes + sizeof(bitmap_super_t) + PAGE_SIZE - 1) / PAGE_SIZE;
if (file && i_size_read(file->f_mapping->host) < bytes + sizeof(bitmap_super_t)) {
printk(KERN_INFO "%s: bitmap file too short %lu < %lu\n",
bmname(bitmap),
(unsigned long) i_size_read(file->f_mapping->host),
bytes + sizeof(bitmap_super_t));
goto out;
}
ret = -ENOMEM;
bitmap->filemap = kmalloc(sizeof(struct page *) * num_pages, GFP_KERNEL);
if (!bitmap->filemap)
goto out;
/* We need 4 bits per page, rounded up to a multiple of sizeof(unsigned long) */
bitmap->filemap_attr = kzalloc(
roundup( DIV_ROUND_UP(num_pages*4, 8), sizeof(unsigned long)),
GFP_KERNEL);
if (!bitmap->filemap_attr)
goto out;
oldindex = ~0L;
for (i = 0; i < chunks; i++) {
int b;
index = file_page_index(i);
bit = file_page_offset(i);
if (index != oldindex) { /* this is a new page, read it in */
int count;
/* unmap the old page, we're done with it */
if (index == num_pages-1)
count = bytes + sizeof(bitmap_super_t)
- index * PAGE_SIZE;
else
count = PAGE_SIZE;
if (index == 0) {
/*
* if we're here then the superblock page
* contains some bits (PAGE_SIZE != sizeof sb)
* we've already read it in, so just use it
*/
page = bitmap->sb_page;
offset = sizeof(bitmap_super_t);
} else if (file) {
page = read_page(file, index, bitmap, count);
offset = 0;
} else {
page = read_sb_page(bitmap->mddev, bitmap->offset, index);
offset = 0;
}
if (IS_ERR(page)) { /* read error */
ret = PTR_ERR(page);
goto out;
}
oldindex = index;
oldpage = page;
if (outofdate) {
/*
* if bitmap is out of date, dirty the
* whole page and write it out
*/
paddr = kmap_atomic(page, KM_USER0);
memset(paddr + offset, 0xff,
PAGE_SIZE - offset);
kunmap_atomic(paddr, KM_USER0);
ret = write_page(bitmap, page, 1);
if (ret) {
/* release, page not in filemap yet */
put_page(page);
goto out;
}
}
bitmap->filemap[bitmap->file_pages++] = page;
bitmap->last_page_size = count;
}
paddr = kmap_atomic(page, KM_USER0);
if (bitmap->flags & BITMAP_HOSTENDIAN)
b = test_bit(bit, paddr);
else
b = ext2_test_bit(bit, paddr);
kunmap_atomic(paddr, KM_USER0);
if (b) {
/* if the disk bit is set, set the memory bit */
bitmap_set_memory_bits(bitmap, i << CHUNK_BLOCK_SHIFT(bitmap),
((i+1) << (CHUNK_BLOCK_SHIFT(bitmap)) >= start)
);
bit_cnt++;
set_page_attr(bitmap, page, BITMAP_PAGE_CLEAN);
}
}
/* everything went OK */
ret = 0;
bitmap_mask_state(bitmap, BITMAP_STALE, MASK_UNSET);
if (bit_cnt) { /* Kick recovery if any bits were set */
set_bit(MD_RECOVERY_NEEDED, &bitmap->mddev->recovery);
md_wakeup_thread(bitmap->mddev->thread);
}
out:
printk(KERN_INFO "%s: bitmap initialized from disk: "
"read %lu/%lu pages, set %lu bits, status: %d\n",
bmname(bitmap), bitmap->file_pages, num_pages, bit_cnt, ret);
return ret;
}
