Commit d51e4fe6 authored by NeilBrown's avatar NeilBrown

Merge branch 'cluster' into for-next

parents 47d68979 97f6cd39
The cluster MD is a shared-device RAID for a cluster.
1. On-disk format
Separate write-intent-bitmap are used for each cluster node.
The bitmaps record all writes that may have been started on that node,
and may not yet have finished. The on-disk layout is:
0 4k 8k 12k
-------------------------------------------------------------------
| idle | md super | bm super [0] + bits |
| bm bits[0, contd] | bm super[1] + bits | bm bits[1, contd] |
| bm super[2] + bits | bm bits [2, contd] | bm super[3] + bits |
| bm bits [3, contd] | | |
During "normal" functioning we assume the filesystem ensures that only one
node writes to any given block at a time, so a write
request will
- set the appropriate bit (if not already set)
- commit the write to all mirrors
- schedule the bit to be cleared after a timeout.
Reads are just handled normally. It is up to the filesystem to
ensure one node doesn't read from a location where another node (or the same
node) is writing.
2. DLM Locks for management
There are two locks for managing the device:
2.1 Bitmap lock resource (bm_lockres)
The bm_lockres protects individual node bitmaps. They are named in the
form bitmap001 for node 1, bitmap002 for node and so on. When a node
joins the cluster, it acquires the lock in PW mode and it stays so
during the lifetime the node is part of the cluster. The lock resource
number is based on the slot number returned by the DLM subsystem. Since
DLM starts node count from one and bitmap slots start from zero, one is
subtracted from the DLM slot number to arrive at the bitmap slot number.
3. Communication
Each node has to communicate with other nodes when starting or ending
resync, and metadata superblock updates.
3.1 Message Types
There are 3 types, of messages which are passed
3.1.1 METADATA_UPDATED: informs other nodes that the metadata has been
updated, and the node must re-read the md superblock. This is performed
synchronously.
3.1.2 RESYNC: informs other nodes that a resync is initiated or ended
so that each node may suspend or resume the region.
3.2 Communication mechanism
The DLM LVB is used to communicate within nodes of the cluster. There
are three resources used for the purpose:
3.2.1 Token: The resource which protects the entire communication
system. The node having the token resource is allowed to
communicate.
3.2.2 Message: The lock resource which carries the data to
communicate.
3.2.3 Ack: The resource, acquiring which means the message has been
acknowledged by all nodes in the cluster. The BAST of the resource
is used to inform the receive node that a node wants to communicate.
The algorithm is:
1. receive status
sender receiver receiver
ACK:CR ACK:CR ACK:CR
2. sender get EX of TOKEN
sender get EX of MESSAGE
sender receiver receiver
TOKEN:EX ACK:CR ACK:CR
MESSAGE:EX
ACK:CR
Sender checks that it still needs to send a message. Messages received
or other events that happened while waiting for the TOKEN may have made
this message inappropriate or redundant.
3. sender write LVB.
sender down-convert MESSAGE from EX to CR
sender try to get EX of ACK
[ wait until all receiver has *processed* the MESSAGE ]
[ triggered by bast of ACK ]
receiver get CR of MESSAGE
receiver read LVB
receiver processes the message
[ wait finish ]
receiver release ACK
sender receiver receiver
TOKEN:EX MESSAGE:CR MESSAGE:CR
MESSAGE:CR
ACK:EX
4. triggered by grant of EX on ACK (indicating all receivers have processed
message)
sender down-convert ACK from EX to CR
sender release MESSAGE
sender release TOKEN
receiver upconvert to EX of MESSAGE
receiver get CR of ACK
receiver release MESSAGE
sender receiver receiver
ACK:CR ACK:CR ACK:CR
4. Handling Failures
4.1 Node Failure
When a node fails, the DLM informs the cluster with the slot. The node
starts a cluster recovery thread. The cluster recovery thread:
- acquires the bitmap<number> lock of the failed node
- opens the bitmap
- reads the bitmap of the failed node
- copies the set bitmap to local node
- cleans the bitmap of the failed node
- releases bitmap<number> lock of the failed node
- initiates resync of the bitmap on the current node
The resync process, is the regular md resync. However, in a clustered
environment when a resync is performed, it needs to tell other nodes
of the areas which are suspended. Before a resync starts, the node
send out RESYNC_START with the (lo,hi) range of the area which needs
to be suspended. Each node maintains a suspend_list, which contains
the list of ranges which are currently suspended. On receiving
RESYNC_START, the node adds the range to the suspend_list. Similarly,
when the node performing resync finishes, it send RESYNC_FINISHED
to other nodes and other nodes remove the corresponding entry from
the suspend_list.
A helper function, should_suspend() can be used to check if a particular
I/O range should be suspended or not.
4.2 Device Failure
Device failures are handled and communicated with the metadata update
routine.
5. Adding a new Device
For adding a new device, it is necessary that all nodes "see" the new device
to be added. For this, the following algorithm is used:
1. Node 1 issues mdadm --manage /dev/mdX --add /dev/sdYY which issues
ioctl(ADD_NEW_DISC with disc.state set to MD_DISK_CLUSTER_ADD)
2. Node 1 sends NEWDISK with uuid and slot number
3. Other nodes issue kobject_uevent_env with uuid and slot number
(Steps 4,5 could be a udev rule)
4. In userspace, the node searches for the disk, perhaps
using blkid -t SUB_UUID=""
5. Other nodes issue either of the following depending on whether the disk
was found:
ioctl(ADD_NEW_DISK with disc.state set to MD_DISK_CANDIDATE and
disc.number set to slot number)
ioctl(CLUSTERED_DISK_NACK)
6. Other nodes drop lock on no-new-devs (CR) if device is found
7. Node 1 attempts EX lock on no-new-devs
8. If node 1 gets the lock, it sends METADATA_UPDATED after unmarking the disk
as SpareLocal
9. If not (get no-new-dev lock), it fails the operation and sends METADATA_UPDATED
10. Other nodes get the information whether a disk is added or not
by the following METADATA_UPDATED.
......@@ -175,6 +175,22 @@ config MD_FAULTY
In unsure, say N.
config MD_CLUSTER
tristate "Cluster Support for MD (EXPERIMENTAL)"
depends on BLK_DEV_MD
depends on DLM
default n
---help---
Clustering support for MD devices. This enables locking and
synchronization across multiple systems on the cluster, so all
nodes in the cluster can access the MD devices simultaneously.
This brings the redundancy (and uptime) of RAID levels across the
nodes of the cluster.
If unsure, say N.
source "drivers/md/bcache/Kconfig"
config BLK_DEV_DM_BUILTIN
......
......@@ -30,6 +30,7 @@ obj-$(CONFIG_MD_RAID10) += raid10.o
obj-$(CONFIG_MD_RAID456) += raid456.o
obj-$(CONFIG_MD_MULTIPATH) += multipath.o
obj-$(CONFIG_MD_FAULTY) += faulty.o
obj-$(CONFIG_MD_CLUSTER) += md-cluster.o
obj-$(CONFIG_BCACHE) += bcache/
obj-$(CONFIG_BLK_DEV_MD) += md-mod.o
obj-$(CONFIG_BLK_DEV_DM) += dm-mod.o
......
......@@ -205,6 +205,10 @@ static int write_sb_page(struct bitmap *bitmap, struct page *page, int wait)
struct block_device *bdev;
struct mddev *mddev = bitmap->mddev;
struct bitmap_storage *store = &bitmap->storage;
int node_offset = 0;
if (mddev_is_clustered(bitmap->mddev))
node_offset = bitmap->cluster_slot * store->file_pages;
while ((rdev = next_active_rdev(rdev, mddev)) != NULL) {
int size = PAGE_SIZE;
......@@ -433,6 +437,7 @@ void bitmap_update_sb(struct bitmap *bitmap)
/* This might have been changed by a reshape */
sb->sync_size = cpu_to_le64(bitmap->mddev->resync_max_sectors);
sb->chunksize = cpu_to_le32(bitmap->mddev->bitmap_info.chunksize);
sb->nodes = cpu_to_le32(bitmap->mddev->bitmap_info.nodes);
sb->sectors_reserved = cpu_to_le32(bitmap->mddev->
bitmap_info.space);
kunmap_atomic(sb);
......@@ -544,6 +549,7 @@ static int bitmap_read_sb(struct bitmap *bitmap)
bitmap_super_t *sb;
unsigned long chunksize, daemon_sleep, write_behind;
unsigned long long events;
int nodes = 0;
unsigned long sectors_reserved = 0;
int err = -EINVAL;
struct page *sb_page;
......@@ -562,6 +568,22 @@ static int bitmap_read_sb(struct bitmap *bitmap)
return -ENOMEM;
bitmap->storage.sb_page = sb_page;
re_read:
/* If cluster_slot is set, the cluster is setup */
if (bitmap->cluster_slot >= 0) {
sector_t bm_blocks = bitmap->mddev->resync_max_sectors;
sector_div(bm_blocks,
bitmap->mddev->bitmap_info.chunksize >> 9);
/* bits to bytes */
bm_blocks = ((bm_blocks+7) >> 3) + sizeof(bitmap_super_t);
/* to 4k blocks */
bm_blocks = DIV_ROUND_UP_SECTOR_T(bm_blocks, 4096);
bitmap->mddev->bitmap_info.offset += bitmap->cluster_slot * (bm_blocks << 3);
pr_info("%s:%d bm slot: %d offset: %llu\n", __func__, __LINE__,
bitmap->cluster_slot, (unsigned long long)bitmap->mddev->bitmap_info.offset);
}
if (bitmap->storage.file) {
loff_t isize = i_size_read(bitmap->storage.file->f_mapping->host);
int bytes = isize > PAGE_SIZE ? PAGE_SIZE : isize;
......@@ -577,12 +599,15 @@ static int bitmap_read_sb(struct bitmap *bitmap)
if (err)
return err;
err = -EINVAL;
sb = kmap_atomic(sb_page);
chunksize = le32_to_cpu(sb->chunksize);
daemon_sleep = le32_to_cpu(sb->daemon_sleep) * HZ;
write_behind = le32_to_cpu(sb->write_behind);
sectors_reserved = le32_to_cpu(sb->sectors_reserved);
nodes = le32_to_cpu(sb->nodes);
strlcpy(bitmap->mddev->bitmap_info.cluster_name, sb->cluster_name, 64);
/* verify that the bitmap-specific fields are valid */
if (sb->magic != cpu_to_le32(BITMAP_MAGIC))
......@@ -619,7 +644,7 @@ static int bitmap_read_sb(struct bitmap *bitmap)
goto out;
}
events = le64_to_cpu(sb->events);
if (events < bitmap->mddev->events) {
if (!nodes && (events < bitmap->mddev->events)) {
printk(KERN_INFO
"%s: bitmap file is out of date (%llu < %llu) "
"-- forcing full recovery\n",
......@@ -634,20 +659,40 @@ static int bitmap_read_sb(struct bitmap *bitmap)
if (le32_to_cpu(sb->version) == BITMAP_MAJOR_HOSTENDIAN)
set_bit(BITMAP_HOSTENDIAN, &bitmap->flags);
bitmap->events_cleared = le64_to_cpu(sb->events_cleared);
strlcpy(bitmap->mddev->bitmap_info.cluster_name, sb->cluster_name, 64);
err = 0;
out:
kunmap_atomic(sb);
/* Assiging chunksize is required for "re_read" */
bitmap->mddev->bitmap_info.chunksize = chunksize;
if (nodes && (bitmap->cluster_slot < 0)) {
err = md_setup_cluster(bitmap->mddev, nodes);
if (err) {
pr_err("%s: Could not setup cluster service (%d)\n",
bmname(bitmap), err);
goto out_no_sb;
}
bitmap->cluster_slot = md_cluster_ops->slot_number(bitmap->mddev);
goto re_read;
}
out_no_sb:
if (test_bit(BITMAP_STALE, &bitmap->flags))
bitmap->events_cleared = bitmap->mddev->events;
bitmap->mddev->bitmap_info.chunksize = chunksize;
bitmap->mddev->bitmap_info.daemon_sleep = daemon_sleep;
bitmap->mddev->bitmap_info.max_write_behind = write_behind;
bitmap->mddev->bitmap_info.nodes = nodes;
if (bitmap->mddev->bitmap_info.space == 0 ||
bitmap->mddev->bitmap_info.space > sectors_reserved)
bitmap->mddev->bitmap_info.space = sectors_reserved;
if (err)
if (err) {
bitmap_print_sb(bitmap);
if (bitmap->cluster_slot < 0)
md_cluster_stop(bitmap->mddev);
}
return err;
}
......@@ -692,9 +737,10 @@ static inline struct page *filemap_get_page(struct bitmap_storage *store,
}
static int bitmap_storage_alloc(struct bitmap_storage *store,
unsigned long chunks, int with_super)
unsigned long chunks, int with_super,
int slot_number)
{
int pnum;
int pnum, offset = 0;
unsigned long num_pages;
unsigned long bytes;
......@@ -703,6 +749,7 @@ static int bitmap_storage_alloc(struct bitmap_storage *store,
bytes += sizeof(bitmap_super_t);
num_pages = DIV_ROUND_UP(bytes, PAGE_SIZE);
offset = slot_number * (num_pages - 1);
store->filemap = kmalloc(sizeof(struct page *)
* num_pages, GFP_KERNEL);
......@@ -713,20 +760,22 @@ static int bitmap_storage_alloc(struct bitmap_storage *store,
store->sb_page = alloc_page(GFP_KERNEL|__GFP_ZERO);
if (store->sb_page == NULL)
return -ENOMEM;
store->sb_page->index = 0;
}
pnum = 0;
if (store->sb_page) {
store->filemap[0] = store->sb_page;
pnum = 1;
store->sb_page->index = offset;
}
for ( ; pnum < num_pages; pnum++) {
store->filemap[pnum] = alloc_page(GFP_KERNEL|__GFP_ZERO);
if (!store->filemap[pnum]) {
store->file_pages = pnum;
return -ENOMEM;
}
store->filemap[pnum]->index = pnum;
store->filemap[pnum]->index = pnum + offset;
}
store->file_pages = pnum;
......@@ -885,6 +934,28 @@ static void bitmap_file_clear_bit(struct bitmap *bitmap, sector_t block)
}
}
static int bitmap_file_test_bit(struct bitmap *bitmap, sector_t block)
{
unsigned long bit;
struct page *page;
void *paddr;
unsigned long chunk = block >> bitmap->counts.chunkshift;
int set = 0;
page = filemap_get_page(&bitmap->storage, chunk);
if (!page)
return -EINVAL;
bit = file_page_offset(&bitmap->storage, chunk);
paddr = kmap_atomic(page);
if (test_bit(BITMAP_HOSTENDIAN, &bitmap->flags))
set = test_bit(bit, paddr);
else
set = test_bit_le(bit, paddr);
kunmap_atomic(paddr);
return set;
}
/* this gets called when the md device is ready to unplug its underlying
* (slave) device queues -- before we let any writes go down, we need to
* sync the dirty pages of the bitmap file to disk */
......@@ -935,7 +1006,7 @@ static void bitmap_set_memory_bits(struct bitmap *bitmap, sector_t offset, int n
*/
static int bitmap_init_from_disk(struct bitmap *bitmap, sector_t start)
{
unsigned long i, chunks, index, oldindex, bit;
unsigned long i, chunks, index, oldindex, bit, node_offset = 0;
struct page *page = NULL;
unsigned long bit_cnt = 0;
struct file *file;
......@@ -981,6 +1052,9 @@ static int bitmap_init_from_disk(struct bitmap *bitmap, sector_t start)
if (!bitmap->mddev->bitmap_info.external)
offset = sizeof(bitmap_super_t);
if (mddev_is_clustered(bitmap->mddev))
node_offset = bitmap->cluster_slot * (DIV_ROUND_UP(store->bytes, PAGE_SIZE));
for (i = 0; i < chunks; i++) {
int b;
index = file_page_index(&bitmap->storage, i);
......@@ -1001,7 +1075,7 @@ static int bitmap_init_from_disk(struct bitmap *bitmap, sector_t start)
bitmap->mddev,
bitmap->mddev->bitmap_info.offset,
page,
index, count);
index + node_offset, count);
if (ret)
goto err;
......@@ -1207,7 +1281,6 @@ void bitmap_daemon_work(struct mddev *mddev)
j < bitmap->storage.file_pages
&& !test_bit(BITMAP_STALE, &bitmap->flags);
j++) {
if (test_page_attr(bitmap, j,
BITMAP_PAGE_DIRTY))
/* bitmap_unplug will handle the rest */
......@@ -1530,11 +1603,13 @@ static void bitmap_set_memory_bits(struct bitmap *bitmap, sector_t offset, int n
return;
}
if (!*bmc) {
*bmc = 2 | (needed ? NEEDED_MASK : 0);
*bmc = 2;
bitmap_count_page(&bitmap->counts, offset, 1);
bitmap_set_pending(&bitmap->counts, offset);
bitmap->allclean = 0;
}
if (needed)
*bmc |= NEEDED_MASK;
spin_unlock_irq(&bitmap->counts.lock);
}
......@@ -1591,6 +1666,10 @@ static void bitmap_free(struct bitmap *bitmap)
if (!bitmap) /* there was no bitmap */
return;
if (mddev_is_clustered(bitmap->mddev) && bitmap->mddev->cluster_info &&
bitmap->cluster_slot == md_cluster_ops->slot_number(bitmap->mddev))
md_cluster_stop(bitmap->mddev);
/* Shouldn't be needed - but just in case.... */
wait_event(bitmap->write_wait,
atomic_read(&bitmap->pending_writes) == 0);
......@@ -1636,7 +1715,7 @@ void bitmap_destroy(struct mddev *mddev)
* initialize the bitmap structure
* if this returns an error, bitmap_destroy must be called to do clean up
*/
int bitmap_create(struct mddev *mddev)
struct bitmap *bitmap_create(struct mddev *mddev, int slot)
{
struct bitmap *bitmap;
sector_t blocks = mddev->resync_max_sectors;
......@@ -1650,7 +1729,7 @@ int bitmap_create(struct mddev *mddev)
bitmap = kzalloc(sizeof(*bitmap), GFP_KERNEL);
if (!bitmap)
return -ENOMEM;
return ERR_PTR(-ENOMEM);
spin_lock_init(&bitmap->counts.lock);
atomic_set(&bitmap->pending_writes, 0);
......@@ -1659,6 +1738,7 @@ int bitmap_create(struct mddev *mddev)
init_waitqueue_head(&bitmap->behind_wait);
bitmap->mddev = mddev;
bitmap->cluster_slot = slot;
if (mddev->kobj.sd)
bm = sysfs_get_dirent(mddev->kobj.sd, "bitmap");
......@@ -1706,12 +1786,14 @@ int bitmap_create(struct mddev *mddev)
printk(KERN_INFO "created bitmap (%lu pages) for device %s\n",
bitmap->counts.pages, bmname(bitmap));
mddev->bitmap = bitmap;
return test_bit(BITMAP_WRITE_ERROR, &bitmap->flags) ? -EIO : 0;
err = test_bit(BITMAP_WRITE_ERROR, &bitmap->flags) ? -EIO : 0;
if (err)
goto error;
return bitmap;
error:
bitmap_free(bitmap);
return err;
return ERR_PTR(err);
}
int bitmap_load(struct mddev *mddev)
......@@ -1765,6 +1847,60 @@ int bitmap_load(struct mddev *mddev)
}
EXPORT_SYMBOL_GPL(bitmap_load);
/* Loads the bitmap associated with slot and copies the resync information
* to our bitmap
*/
int bitmap_copy_from_slot(struct mddev *mddev, int slot,
sector_t *low, sector_t *high, bool clear_bits)
{
int rv = 0, i, j;
sector_t block, lo = 0, hi = 0;
struct bitmap_counts *counts;
struct bitmap *bitmap = bitmap_create(mddev, slot);
if (IS_ERR(bitmap))
return PTR_ERR(bitmap);
rv = bitmap_read_sb(bitmap);
if (rv)
goto err;
rv = bitmap_init_from_disk(bitmap, 0);
if (rv)
goto err;
counts = &bitmap->counts;
for (j = 0; j < counts->chunks; j++) {
block = (sector_t)j << counts->chunkshift;
if (bitmap_file_test_bit(bitmap, block)) {
if (!lo)
lo = block;
hi = block;
bitmap_file_clear_bit(bitmap, block);
bitmap_set_memory_bits(mddev->bitmap, block, 1);
bitmap_file_set_bit(mddev->bitmap, block);
}
}
if (clear_bits) {
bitmap_update_sb(bitmap);
/* Setting this for the ev_page should be enough.
* And we do not require both write_all and PAGE_DIRT either
*/
for (i = 0; i < bitmap->storage.file_pages; i++)
set_page_attr(bitmap, i, BITMAP_PAGE_DIRTY);
bitmap_write_all(bitmap);
bitmap_unplug(bitmap);
}
*low = lo;
*high = hi;
err:
bitmap_free(bitmap);
return rv;
}
EXPORT_SYMBOL_GPL(bitmap_copy_from_slot);
void bitmap_status(struct seq_file *seq, struct bitmap *bitmap)
{
unsigned long chunk_kb;
......@@ -1849,7 +1985,8 @@ int bitmap_resize(struct bitmap *bitmap, sector_t blocks,
memset(&store, 0, sizeof(store));
if (bitmap->mddev->bitmap_info.offset || bitmap->mddev->bitmap_info.file)
ret = bitmap_storage_alloc(&store, chunks,
!bitmap->mddev->bitmap_info.external);
!bitmap->mddev->bitmap_info.external,
bitmap->cluster_slot);
if (ret)
goto err;
......@@ -2021,14 +2158,19 @@ location_store(struct mddev *mddev, const char *buf, size_t len)
return -EINVAL;
mddev->bitmap_info.offset = offset;
if (mddev->pers) {
struct bitmap *bitmap;
mddev->pers->quiesce(mddev, 1);
rv = bitmap_create(mddev);
if (!rv)
bitmap = bitmap_create(mddev, -1);
if (IS_ERR(bitmap))
rv = PTR_ERR(bitmap);
else {
mddev->bitmap = bitmap;
rv = bitmap_load(mddev);
if (rv) {
bitmap_destroy(mddev);
mddev->bitmap_info.offset = 0;
}
}
mddev->pers->quiesce(mddev, 0);
if (rv)
return rv;
......@@ -2186,6 +2328,8 @@ __ATTR(chunksize, S_IRUGO|S_IWUSR, chunksize_show, chunksize_store);
static ssize_t metadata_show(struct mddev *mddev, char *page)
{
if (mddev_is_clustered(mddev))
return sprintf(page, "clustered\n");
return sprintf(page, "%s\n", (mddev->bitmap_info.external
? "external" : "internal"));
}
......@@ -2198,7 +2342,8 @@ static ssize_t metadata_store(struct mddev *mddev, const char *buf, size_t len)
return -EBUSY;
if (strncmp(buf, "external", 8) == 0)
mddev->bitmap_info.external = 1;
else if (strncmp(buf, "internal", 8) == 0)
else if ((strncmp(buf, "internal", 8) == 0) ||
(strncmp(buf, "clustered", 9) == 0))
mddev->bitmap_info.external = 0;
else
return -EINVAL;
......
......@@ -130,8 +130,9 @@ typedef struct bitmap_super_s {
__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. */
__u8 pad[256 - 68]; /* set to zero */
__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:
......@@ -226,12 +227,13 @@ struct bitmap {
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 */
int bitmap_create(struct mddev *mddev);
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);
......@@ -260,6 +262,8 @@ void bitmap_daemon_work(struct mddev *mddev);
int bitmap_resize(struct bitmap *bitmap, sector_t blocks,
int chunksize, int init);
int bitmap_copy_from_slot(struct mddev *mddev, int slot,
sector_t *lo, sector_t *hi, bool clear_bits);
#endif
#endif
/*
* Copyright (C) 2015, SUSE
*
* 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.
*
*/
#include <linux/module.h>
#include <linux/dlm.h>
#include <linux/sched.h>
#include <linux/raid/md_p.h>
#include "md.h"
#include "bitmap.h"
#include "md-cluster.h"
#define LVB_SIZE 64
#define NEW_DEV_TIMEOUT 5000
struct dlm_lock_resource {
dlm_lockspace_t *ls;
struct dlm_lksb lksb;
char *name; /* lock name. */
uint32_t flags; /* flags to pass to dlm_lock() */
struct completion completion; /* completion for synchronized locking */
void (*bast)(void *arg, int mode); /* blocking AST function pointer*/
struct mddev *mddev; /* pointing back to mddev. */
};
struct suspend_info {
int slot;
sector_t lo;
sector_t hi;
struct list_head list;
};
struct resync_info {
__le64 lo;
__le64 hi;
};
/* md_cluster_info flags */
#define MD_CLUSTER_WAITING_FOR_NEWDISK 1
struct md_cluster_info {
/* dlm lock space and resources for clustered raid. */
dlm_lockspace_t *lockspace;
int slot_number;
struct completion completion;
struct dlm_lock_resource *sb_lock;
struct mutex sb_mutex;
struct dlm_lock_resource *bitmap_lockres;
struct list_head suspend_list;
spinlock_t suspend_lock;
struct md_thread *recovery_thread;
unsigned long recovery_map;
/* communication loc resources */
struct dlm_lock_resource *ack_lockres;
struct dlm_lock_resource *message_lockres;
struct dlm_lock_resource *token_lockres;
struct dlm_lock_resource *no_new_dev_lockres;
struct md_thread *recv_thread;
struct completion newdisk_completion;
unsigned long state;
};
enum msg_type {
METADATA_UPDATED = 0,
RESYNCING,
NEWDISK,
REMOVE,
RE_ADD,
};
struct cluster_msg {
int type;
int slot;
/* TODO: Unionize this for smaller footprint */
sector_t low;
sector_t high;
char uuid[16];
int raid_slot;
};
static void sync_ast(void *arg)
{
struct dlm_lock_resource *res;
res = (struct dlm_lock_resource *) arg;
complete(&res->completion);
}
static int dlm_lock_sync(struct dlm_lock_resource *res, int mode)
{
int ret = 0;
init_completion(&res->completion);
ret = dlm_lock(res->ls, mode, &res->lksb,
res->flags, res->name, strlen(res->name),
0, sync_ast, res, res->bast);
if (ret)
return ret;
wait_for_completion(&res->completion);
return res->lksb.sb_status;
}
static int dlm_unlock_sync(struct dlm_lock_resource *res)
{
return dlm_lock_sync(res, DLM_LOCK_NL);
}
static struct dlm_lock_resource *lockres_init(struct mddev *mddev,
char *name, void (*bastfn)(void *arg, int mode), int with_lvb)
{
struct dlm_lock_resource *res = NULL;
int ret, namelen;
struct md_cluster_info *cinfo = mddev->cluster_info;
res = kzalloc(sizeof(struct dlm_lock_resource), GFP_KERNEL);
if (!res)
return NULL;
res->ls = cinfo->lockspace;
res->mddev = mddev;
namelen = strlen(name);
res->name = kzalloc(namelen + 1, GFP_KERNEL);
if (!res->name) {
pr_err("md-cluster: Unable to allocate resource name for resource %s\n", name);
goto out_err;
}
strlcpy(res->name, name, namelen + 1);
if (with_lvb) {
res->lksb.sb_lvbptr = kzalloc(LVB_SIZE, GFP_KERNEL);
if (!res->lksb.sb_lvbptr) {
pr_err("md-cluster: Unable to allocate LVB for resource %s\n", name);
goto out_err;
}
res->flags = DLM_LKF_VALBLK;
}
if (bastfn)
res->bast = bastfn;
res->flags |= DLM_LKF_EXPEDITE;
ret = dlm_lock_sync(res, DLM_LOCK_NL);
if (ret) {
pr_err("md-cluster: Unable to lock NL on new lock resource %s\n", name);
goto out_err;
}
res->flags &= ~DLM_LKF_EXPEDITE;
res->flags |= DLM_LKF_CONVERT;
return res;
out_err:
kfree(res->lksb.sb_lvbptr);
kfree(res->name);
kfree(res);
return NULL;
}
static void lockres_free(struct dlm_lock_resource *res)
{
if (!res)
return;
init_completion(&res->completion);
dlm_unlock(res->ls, res->lksb.sb_lkid, 0, &res->lksb, res);
wait_for_completion(&res->completion);
kfree(res->name);
kfree(res->lksb.sb_lvbptr);
kfree(res);
}
static char *pretty_uuid(char *dest, char *src)
{
int i, len = 0;
for (i = 0; i < 16; i++) {
if (i == 4 || i == 6 || i == 8 || i == 10)
len += sprintf(dest + len, "-");
len += sprintf(dest + len, "%02x", (__u8)src[i]);
}
return dest;
}
static void add_resync_info(struct mddev *mddev, struct dlm_lock_resource *lockres,
sector_t lo, sector_t hi)
{
struct resync_info *ri;
ri = (struct resync_info *)lockres->lksb.sb_lvbptr;
ri->lo = cpu_to_le64(lo);
ri->hi = cpu_to_le64(hi);
}
static struct suspend_info *read_resync_info(struct mddev *mddev, struct dlm_lock_resource *lockres)
{
struct resync_info ri;
struct suspend_info *s = NULL;
sector_t hi = 0;
dlm_lock_sync(lockres, DLM_LOCK_CR);
memcpy(&ri, lockres->lksb.sb_lvbptr, sizeof(struct resync_info));
hi = le64_to_cpu(ri.hi);
if (ri.hi > 0) {
s = kzalloc(sizeof(struct suspend_info), GFP_KERNEL);
if (!s)
goto out;
s->hi = hi;
s->lo = le64_to_cpu(ri.lo);
}
dlm_unlock_sync(lockres);
out:
return s;
}
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) {
/* TODO:Wait for current resync to get over */
set_bit(MD_RECOVERY_NEEDED, &mddev->recovery);
if (lo < mddev->recovery_cp)
mddev->recovery_cp = lo;
md_check_recovery(mddev);
}
dlm_unlock:
dlm_unlock_sync(bm_lockres);
clear_bit:
clear_bit(slot, &cinfo->recovery_map);
}
}
static void recover_prep(void *arg)
{
}
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);
}
static void recover_done(void *arg, struct dlm_slot *slots,
int num_slots, int our_slot,
uint32_t generation)
{
struct mddev *mddev = arg;
struct md_cluster_info *cinfo = mddev->cluster_info;
cinfo->slot_number = our_slot;
complete(&cinfo->completion);
}
static const struct dlm_lockspace_ops md_ls_ops = {
.recover_prep = recover_prep,
.recover_slot = recover_slot,
.recover_done = recover_done,
};
/*
* 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 __remove_suspend_info(struct md_cluster_info *cinfo, int slot)
{
struct suspend_info *s, *tmp;
list_for_each_entry_safe(s, tmp, &cinfo->suspend_list, list)
if (slot == s->slot) {
pr_info("%s:%d Deleting suspend_info: %d\n",
__func__, __LINE__, slot);
list_del(&s->list);
kfree(s);
break;
}
}
static void remove_suspend_info(struct md_cluster_info *cinfo, int slot)
{
spin_lock_irq(&cinfo->suspend_lock);
__remove_suspend_info(cinfo, slot);
spin_unlock_irq(&cinfo->suspend_lock);
}
static void process_suspend_info(struct md_cluster_info *cinfo,
int slot, sector_t lo, sector_t hi)
{
struct suspend_info *s;
if (!hi) {
remove_suspend_info(cinfo, slot);
return;
}
s = kzalloc(sizeof(struct suspend_info), GFP_KERNEL);
if (!s)
return;
s->slot = slot;
s->lo = lo;
s->hi = hi;
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);
}
static void process_add_new_disk(struct mddev *mddev, struct cluster_msg *cmsg)
{
char disk_uuid[64];
struct md_cluster_info *cinfo = mddev->cluster_info;
char event_name[] = "EVENT=ADD_DEVICE";
char raid_slot[16];
char *envp[] = {event_name, disk_uuid, raid_slot, NULL};
int len;
len = snprintf(disk_uuid, 64, "DEVICE_UUID=");
pretty_uuid(disk_uuid + len, cmsg->uuid);
snprintf(raid_slot, 16, "RAID_DISK=%d", cmsg->raid_slot);
pr_info("%s:%d Sending kobject change with %s and %s\n", __func__, __LINE__, disk_uuid, raid_slot);
init_completion(&cinfo->newdisk_completion);
set_bit(MD_CLUSTER_WAITING_FOR_NEWDISK, &cinfo->state);
kobject_uevent_env(&disk_to_dev(mddev->gendisk)->kobj, KOBJ_CHANGE, envp);
wait_for_completion_timeout(&cinfo->newdisk_completion,
NEW_DEV_TIMEOUT);
clear_bit(MD_CLUSTER_WAITING_FOR_NEWDISK, &cinfo->state);
}
static void process_metadata_update(struct mddev *mddev, struct cluster_msg *msg)
{
struct md_cluster_info *cinfo = mddev->cluster_info;
md_reload_sb(mddev);
dlm_lock_sync(cinfo->no_new_dev_lockres, DLM_LOCK_CR);
}
static void process_remove_disk(struct mddev *mddev, struct cluster_msg *msg)
{
struct md_rdev *rdev = md_find_rdev_nr_rcu(mddev, msg->raid_slot);
if (rdev)
md_kick_rdev_from_array(rdev);
else
pr_warn("%s: %d Could not find disk(%d) to REMOVE\n", __func__, __LINE__, msg->raid_slot);
}
static void process_readd_disk(struct mddev *mddev, struct cluster_msg *msg)
{
struct md_rdev *rdev = md_find_rdev_nr_rcu(mddev, msg->raid_slot);
if (rdev && test_bit(Faulty, &rdev->flags))
clear_bit(Faulty, &rdev->flags);
else
pr_warn("%s: %d Could not find disk(%d) which is faulty", __func__, __LINE__, msg->raid_slot);
}
static void process_recvd_msg(struct mddev *mddev, struct cluster_msg *msg)
{
switch (msg->type) {
case METADATA_UPDATED:
pr_info("%s: %d Received message: METADATA_UPDATE from %d\n",
__func__, __LINE__, msg->slot);
process_metadata_update(mddev, msg);
break;
case RESYNCING:
pr_info("%s: %d Received message: RESYNCING from %d\n",
__func__, __LINE__, msg->slot);
process_suspend_info(mddev->cluster_info, msg->slot,
msg->low, msg->high);
break;
case NEWDISK:
pr_info("%s: %d Received message: NEWDISK from %d\n",
__func__, __LINE__, msg->slot);
process_add_new_disk(mddev, msg);
break;
case REMOVE:
pr_info("%s: %d Received REMOVE from %d\n",
__func__, __LINE__, msg->slot);
process_remove_disk(mddev, msg);
break;
case RE_ADD:
pr_info("%s: %d Received RE_ADD from %d\n",
__func__, __LINE__, msg->slot);
process_readd_disk(mddev, msg);
break;
default:
pr_warn("%s:%d Received unknown message from %d\n",
__func__, __LINE__, msg->slot);
}
}
/*
* thread for receiving message
*/
static void recv_daemon(struct md_thread *thread)
{
struct md_cluster_info *cinfo = thread->mddev->cluster_info;
struct dlm_lock_resource *ack_lockres = cinfo->ack_lockres;
struct dlm_lock_resource *message_lockres = cinfo->message_lockres;
struct cluster_msg msg;
/*get CR on Message*/
if (dlm_lock_sync(message_lockres, DLM_LOCK_CR)) {
pr_err("md/raid1:failed to get CR on MESSAGE\n");
return;
}
/* read lvb and wake up thread to process this message_lockres */
memcpy(&msg, message_lockres->lksb.sb_lvbptr, sizeof(struct cluster_msg));
process_recvd_msg(thread->mddev, &msg);
/*release CR on ack_lockres*/
dlm_unlock_sync(ack_lockres);
/*up-convert to EX on message_lockres*/
dlm_lock_sync(message_lockres, DLM_LOCK_EX);
/*get CR on ack_lockres again*/
dlm_lock_sync(ack_lockres, DLM_LOCK_CR);
/*release CR on message_lockres*/
dlm_unlock_sync(message_lockres);
}
/* lock_comm()
* Takes the lock on the TOKEN lock resource so no other
* node can communicate while the operation is underway.
*/
static int lock_comm(struct md_cluster_info *cinfo)
{
int error;
error = dlm_lock_sync(cinfo->token_lockres, DLM_LOCK_EX);
if (error)
pr_err("md-cluster(%s:%d): failed to get EX on TOKEN (%d)\n",
__func__, __LINE__, error);
return error;
}
static void unlock_comm(struct md_cluster_info *cinfo)
{
dlm_unlock_sync(cinfo->token_lockres);
}
/* __sendmsg()
* This function performs the actual sending of the message. This function is
* usually called after performing the encompassing operation
* The function:
* 1. Grabs the message lockresource in EX mode
* 2. Copies the message to the message LVB
* 3. Downconverts message lockresource to CR
* 4. Upconverts ack lock resource from CR to EX. This forces the BAST on other nodes
* and the other nodes read the message. The thread will wait here until all other
* nodes have released ack lock resource.
* 5. Downconvert ack lockresource to CR
*/
static int __sendmsg(struct md_cluster_info *cinfo, struct cluster_msg *cmsg)
{
int error;
int slot = cinfo->slot_number - 1;
cmsg->slot = cpu_to_le32(slot);
/*get EX on Message*/
error = dlm_lock_sync(cinfo->message_lockres, DLM_LOCK_EX);
if (error) {
pr_err("md-cluster: failed to get EX on MESSAGE (%d)\n", error);
goto failed_message;
}
memcpy(cinfo->message_lockres->lksb.sb_lvbptr, (void *)cmsg,
sizeof(struct cluster_msg));
/*down-convert EX to CR on Message*/
error = dlm_lock_sync(cinfo->message_lockres, DLM_LOCK_CR);
if (error) {
pr_err("md-cluster: failed to convert EX to CR on MESSAGE(%d)\n",
error);
goto failed_message;
}
/*up-convert CR to EX on Ack*/
error = dlm_lock_sync(cinfo->ack_lockres, DLM_LOCK_EX);
if (error) {
pr_err("md-cluster: failed to convert CR to EX on ACK(%d)\n",
error);
goto failed_ack;
}
/*down-convert EX to CR on Ack*/
error = dlm_lock_sync(cinfo->ack_lockres, DLM_LOCK_CR);
if (error) {
pr_err("md-cluster: failed to convert EX to CR on ACK(%d)\n",
error);
goto failed_ack;
}
failed_ack:
dlm_unlock_sync(cinfo->message_lockres);
failed_message:
return error;
}
static int sendmsg(struct md_cluster_info *cinfo, struct cluster_msg *cmsg)
{
int ret;
lock_comm(cinfo);
ret = __sendmsg(cinfo, cmsg);
unlock_comm(cinfo);
return ret;
}
static int gather_all_resync_info(struct mddev *mddev, int total_slots)
{
struct md_cluster_info *cinfo = mddev->cluster_info;
int i, ret = 0;
struct dlm_lock_resource *bm_lockres;
struct suspend_info *s;
char str[64];
for (i = 0; i < total_slots; i++) {
memset(str, '\0', 64);
snprintf(str, 64, "bitmap%04d", i);
bm_lockres = lockres_init(mddev, str, NULL, 1);
if (!bm_lockres)
return -ENOMEM;
if (i == (cinfo->slot_number - 1))
continue;
bm_lockres->flags |= DLM_LKF_NOQUEUE;
ret = dlm_lock_sync(bm_lockres, DLM_LOCK_PW);
if (ret == -EAGAIN) {
memset(bm_lockres->lksb.sb_lvbptr, '\0', LVB_SIZE);
s = read_resync_info(mddev, bm_lockres);
if (s) {
pr_info("%s:%d Resync[%llu..%llu] in progress on %d\n",
__func__, __LINE__,
(unsigned long long) s->lo,
(unsigned long long) s->hi, i);
spin_lock_irq(&cinfo->suspend_lock);
s->slot = i;
list_add(&s->list, &cinfo->suspend_list);
spin_unlock_irq(&cinfo->suspend_lock);
}
ret = 0;
lockres_free(bm_lockres);
continue;
}
if (ret)
goto out;
/* TODO: Read the disk bitmap sb and check if it needs recovery */
dlm_unlock_sync(bm_lockres);
lockres_free(bm_lockres);
}
out:
return ret;
}
static int join(struct mddev *mddev, int nodes)
{
struct md_cluster_info *cinfo;
int ret, ops_rv;
char str[64];
if (!try_module_get(THIS_MODULE))
return -ENOENT;
cinfo = kzalloc(sizeof(struct md_cluster_info), GFP_KERNEL);
if (!cinfo)
return -ENOMEM;
init_completion(&cinfo->completion);
mutex_init(&cinfo->sb_mutex);
mddev->cluster_info = cinfo;
memset(str, 0, 64);
pretty_uuid(str, mddev->uuid);
ret = dlm_new_lockspace(str, mddev->bitmap_info.cluster_name,
DLM_LSFL_FS, LVB_SIZE,
&md_ls_ops, mddev, &ops_rv, &cinfo->lockspace);
if (ret)
goto err;
wait_for_completion(&cinfo->completion);
if (nodes < cinfo->slot_number) {
pr_err("md-cluster: Slot allotted(%d) is greater than available slots(%d).",
cinfo->slot_number, nodes);
ret = -ERANGE;
goto err;
}
cinfo->sb_lock = lockres_init(mddev, "cmd-super",
NULL, 0);
if (!cinfo->sb_lock) {
ret = -ENOMEM;
goto err;
}
/* Initiate the communication resources */
ret = -ENOMEM;
cinfo->recv_thread = md_register_thread(recv_daemon, mddev, "cluster_recv");
if (!cinfo->recv_thread) {
pr_err("md-cluster: cannot allocate memory for recv_thread!\n");
goto err;
}
cinfo->message_lockres = lockres_init(mddev, "message", NULL, 1);
if (!cinfo->message_lockres)
goto err;
cinfo->token_lockres = lockres_init(mddev, "token", NULL, 0);
if (!cinfo->token_lockres)
goto err;
cinfo->ack_lockres = lockres_init(mddev, "ack", ack_bast, 0);
if (!cinfo->ack_lockres)
goto err;
cinfo->no_new_dev_lockres = lockres_init(mddev, "no-new-dev", NULL, 0);
if (!cinfo->no_new_dev_lockres)
goto err;
/* get sync CR lock on ACK. */
if (dlm_lock_sync(cinfo->ack_lockres, DLM_LOCK_CR))
pr_err("md-cluster: failed to get a sync CR lock on ACK!(%d)\n",
ret);
/* get sync CR lock on no-new-dev. */
if (dlm_lock_sync(cinfo->no_new_dev_lockres, DLM_LOCK_CR))
pr_err("md-cluster: failed to get a sync CR lock on no-new-dev!(%d)\n", ret);
pr_info("md-cluster: Joined cluster %s slot %d\n", str, cinfo->slot_number);
snprintf(str, 64, "bitmap%04d", cinfo->slot_number - 1);
cinfo->bitmap_lockres = lockres_init(mddev, str, NULL, 1);
if (!cinfo->bitmap_lockres)
goto err;
if (dlm_lock_sync(cinfo->bitmap_lockres, DLM_LOCK_PW)) {
pr_err("Failed to get bitmap lock\n");
ret = -EINVAL;
goto err;
}
INIT_LIST_HEAD(&cinfo->suspend_list);
spin_lock_init(&cinfo->suspend_lock);
ret = gather_all_resync_info(mddev, nodes);
if (ret)
goto err;
return 0;
err:
lockres_free(cinfo->message_lockres);
lockres_free(cinfo->token_lockres);
lockres_free(cinfo->ack_lockres);
lockres_free(cinfo->no_new_dev_lockres);
lockres_free(cinfo->bitmap_lockres);
lockres_free(cinfo->sb_lock);
if (cinfo->lockspace)
dlm_release_lockspace(cinfo->lockspace, 2);
mddev->cluster_info = NULL;
kfree(cinfo);
module_put(THIS_MODULE);
return ret;
}
static int leave(struct mddev *mddev)
{
struct md_cluster_info *cinfo = mddev->cluster_info;
if (!cinfo)
return 0;
md_unregister_thread(&cinfo->recovery_thread);
md_unregister_thread(&cinfo->recv_thread);
lockres_free(cinfo->message_lockres);
lockres_free(cinfo->token_lockres);
lockres_free(cinfo->ack_lockres);
lockres_free(cinfo->no_new_dev_lockres);
lockres_free(cinfo->sb_lock);
lockres_free(cinfo->bitmap_lockres);
dlm_release_lockspace(cinfo->lockspace, 2);
return 0;
}
/* slot_number(): Returns the MD slot number to use
* DLM starts the slot numbers from 1, wheras cluster-md
* wants the number to be from zero, so we deduct one
*/
static int slot_number(struct mddev *mddev)
{
struct md_cluster_info *cinfo = mddev->cluster_info;
return cinfo->slot_number - 1;
}
static void resync_info_update(struct mddev *mddev, sector_t lo, sector_t hi)
{
struct md_cluster_info *cinfo = mddev->cluster_info;
add_resync_info(mddev, cinfo->bitmap_lockres, lo, hi);
/* Re-acquire the lock to refresh LVB */
dlm_lock_sync(cinfo->bitmap_lockres, DLM_LOCK_PW);
}
static int metadata_update_start(struct mddev *mddev)
{
return lock_comm(mddev->cluster_info);
}
static int metadata_update_finish(struct mddev *mddev)
{
struct md_cluster_info *cinfo = mddev->cluster_info;
struct cluster_msg cmsg;
int ret;
memset(&cmsg, 0, sizeof(cmsg));
cmsg.type = cpu_to_le32(METADATA_UPDATED);
ret = __sendmsg(cinfo, &cmsg);
unlock_comm(cinfo);
return ret;
}
static int metadata_update_cancel(struct mddev *mddev)
{
struct md_cluster_info *cinfo = mddev->cluster_info;
return dlm_unlock_sync(cinfo->token_lockres);
}
static int resync_send(struct mddev *mddev, enum msg_type type,
sector_t lo, sector_t hi)
{
struct md_cluster_info *cinfo = mddev->cluster_info;
struct cluster_msg cmsg;
int slot = cinfo->slot_number - 1;
pr_info("%s:%d lo: %llu hi: %llu\n", __func__, __LINE__,
(unsigned long long)lo,
(unsigned long long)hi);
resync_info_update(mddev, lo, hi);
cmsg.type = cpu_to_le32(type);
cmsg.slot = cpu_to_le32(slot);
cmsg.low = cpu_to_le64(lo);
cmsg.high = cpu_to_le64(hi);
return sendmsg(cinfo, &cmsg);
}
static int resync_start(struct mddev *mddev, sector_t lo, sector_t hi)
{
pr_info("%s:%d\n", __func__, __LINE__);
return resync_send(mddev, RESYNCING, lo, hi);
}
static void resync_finish(struct mddev *mddev)
{
pr_info("%s:%d\n", __func__, __LINE__);
resync_send(mddev, RESYNCING, 0, 0);
}
static int area_resyncing(struct mddev *mddev, sector_t lo, sector_t hi)
{
struct md_cluster_info *cinfo = mddev->cluster_info;
int ret = 0;
struct suspend_info *s;
spin_lock_irq(&cinfo->suspend_lock);
if (list_empty(&cinfo->suspend_list))
goto out;
list_for_each_entry(s, &cinfo->suspend_list, list)
if (hi > s->lo && lo < s->hi) {
ret = 1;
break;
}
out:
spin_unlock_irq(&cinfo->suspend_lock);
return ret;
}
static int add_new_disk_start(struct mddev *mddev, struct md_rdev *rdev)
{
struct md_cluster_info *cinfo = mddev->cluster_info;
struct cluster_msg cmsg;
int ret = 0;
struct mdp_superblock_1 *sb = page_address(rdev->sb_page);
char *uuid = sb->device_uuid;
memset(&cmsg, 0, sizeof(cmsg));
cmsg.type = cpu_to_le32(NEWDISK);
memcpy(cmsg.uuid, uuid, 16);
cmsg.raid_slot = rdev->desc_nr;
lock_comm(cinfo);
ret = __sendmsg(cinfo, &cmsg);
if (ret)
return ret;
cinfo->no_new_dev_lockres->flags |= DLM_LKF_NOQUEUE;
ret = dlm_lock_sync(cinfo->no_new_dev_lockres, DLM_LOCK_EX);
cinfo->no_new_dev_lockres->flags &= ~DLM_LKF_NOQUEUE;
/* Some node does not "see" the device */
if (ret == -EAGAIN)
ret = -ENOENT;
else
dlm_lock_sync(cinfo->no_new_dev_lockres, DLM_LOCK_CR);
return ret;
}
static int add_new_disk_finish(struct mddev *mddev)
{
struct cluster_msg cmsg;
struct md_cluster_info *cinfo = mddev->cluster_info;
int ret;
/* Write sb and inform others */
md_update_sb(mddev, 1);
cmsg.type = METADATA_UPDATED;
ret = __sendmsg(cinfo, &cmsg);
unlock_comm(cinfo);
return ret;
}
static int new_disk_ack(struct mddev *mddev, bool ack)
{
struct md_cluster_info *cinfo = mddev->cluster_info;
if (!test_bit(MD_CLUSTER_WAITING_FOR_NEWDISK, &cinfo->state)) {
pr_warn("md-cluster(%s): Spurious cluster confirmation\n", mdname(mddev));
return -EINVAL;
}
if (ack)
dlm_unlock_sync(cinfo->no_new_dev_lockres);
complete(&cinfo->newdisk_completion);
return 0;
}
static int remove_disk(struct mddev *mddev, struct md_rdev *rdev)
{
struct cluster_msg cmsg;
struct md_cluster_info *cinfo = mddev->cluster_info;
cmsg.type = REMOVE;
cmsg.raid_slot = rdev->desc_nr;
return __sendmsg(cinfo, &cmsg);
}
static int gather_bitmaps(struct md_rdev *rdev)
{
int sn, err;
sector_t lo, hi;
struct cluster_msg cmsg;
struct mddev *mddev = rdev->mddev;
struct md_cluster_info *cinfo = mddev->cluster_info;
cmsg.type = RE_ADD;
cmsg.raid_slot = rdev->desc_nr;
err = sendmsg(cinfo, &cmsg);
if (err)
goto out;
for (sn = 0; sn < mddev->bitmap_info.nodes; sn++) {
if (sn == (cinfo->slot_number - 1))
continue;
err = bitmap_copy_from_slot(mddev, sn, &lo, &hi, false);
if (err) {
pr_warn("md-cluster: Could not gather bitmaps from slot %d", sn);
goto out;
}
if ((hi > 0) && (lo < mddev->recovery_cp))
mddev->recovery_cp = lo;
}
out:
return err;
}
static struct md_cluster_operations cluster_ops = {
.join = join,
.leave = leave,
.slot_number = slot_number,
.resync_info_update = resync_info_update,
.resync_start = resync_start,
.resync_finish = resync_finish,
.metadata_update_start = metadata_update_start,
.metadata_update_finish = metadata_update_finish,
.metadata_update_cancel = metadata_update_cancel,
.area_resyncing = area_resyncing,
.add_new_disk_start = add_new_disk_start,
.add_new_disk_finish = add_new_disk_finish,
.new_disk_ack = new_disk_ack,
.remove_disk = remove_disk,
.gather_bitmaps = gather_bitmaps,
};
static int __init cluster_init(void)
{
pr_warn("md-cluster: EXPERIMENTAL. Use with caution\n");
pr_info("Registering Cluster MD functions\n");
register_md_cluster_operations(&cluster_ops, THIS_MODULE);
return 0;
}
static void cluster_exit(void)
{
unregister_md_cluster_operations();
}
module_init(cluster_init);
module_exit(cluster_exit);
MODULE_LICENSE("GPL");
MODULE_DESCRIPTION("Clustering support for MD");
#ifndef _MD_CLUSTER_H
#define _MD_CLUSTER_H
#include "md.h"
struct mddev;
struct md_rdev;
struct md_cluster_operations {
int (*join)(struct mddev *mddev, int nodes);
int (*leave)(struct mddev *mddev);
int (*slot_number)(struct mddev *mddev);
void (*resync_info_update)(struct mddev *mddev, sector_t lo, sector_t hi);
int (*resync_start)(struct mddev *mddev, sector_t lo, sector_t hi);
void (*resync_finish)(struct mddev *mddev);
int (*metadata_update_start)(struct mddev *mddev);
int (*metadata_update_finish)(struct mddev *mddev);
int (*metadata_update_cancel)(struct mddev *mddev);
int (*area_resyncing)(struct mddev *mddev, sector_t lo, sector_t hi);
int (*add_new_disk_start)(struct mddev *mddev, struct md_rdev *rdev);
int (*add_new_disk_finish)(struct mddev *mddev);
int (*new_disk_ack)(struct mddev *mddev, bool ack);
int (*remove_disk)(struct mddev *mddev, struct md_rdev *rdev);
int (*gather_bitmaps)(struct md_rdev *rdev);
};
#endif /* _MD_CLUSTER_H */
......@@ -53,6 +53,7 @@
#include <linux/slab.h>
#include "md.h"
#include "bitmap.h"
#include "md-cluster.h"
#ifndef MODULE
static void autostart_arrays(int part);
......@@ -66,6 +67,11 @@ static void autostart_arrays(int part);
static LIST_HEAD(pers_list);
static DEFINE_SPINLOCK(pers_lock);
struct md_cluster_operations *md_cluster_ops;
EXPORT_SYMBOL(md_cluster_ops);
struct module *md_cluster_mod;
EXPORT_SYMBOL(md_cluster_mod);
static DECLARE_WAIT_QUEUE_HEAD(resync_wait);
static struct workqueue_struct *md_wq;
static struct workqueue_struct *md_misc_wq;
......@@ -640,7 +646,7 @@ void mddev_unlock(struct mddev *mddev)
}
EXPORT_SYMBOL_GPL(mddev_unlock);
static struct md_rdev *find_rdev_nr_rcu(struct mddev *mddev, int nr)
struct md_rdev *md_find_rdev_nr_rcu(struct mddev *mddev, int nr)
{
struct md_rdev *rdev;
......@@ -650,6 +656,7 @@ static struct md_rdev *find_rdev_nr_rcu(struct mddev *mddev, int nr)
return NULL;
}
EXPORT_SYMBOL_GPL(md_find_rdev_nr_rcu);
static struct md_rdev *find_rdev(struct mddev *mddev, dev_t dev)
{
......@@ -2047,11 +2054,11 @@ static int bind_rdev_to_array(struct md_rdev *rdev, struct mddev *mddev)
int choice = 0;
if (mddev->pers)
choice = mddev->raid_disks;
while (find_rdev_nr_rcu(mddev, choice))
while (md_find_rdev_nr_rcu(mddev, choice))
choice++;
rdev->desc_nr = choice;
} else {
if (find_rdev_nr_rcu(mddev, rdev->desc_nr)) {
if (md_find_rdev_nr_rcu(mddev, rdev->desc_nr)) {
rcu_read_unlock();
return -EBUSY;
}
......@@ -2166,11 +2173,12 @@ static void export_rdev(struct md_rdev *rdev)
kobject_put(&rdev->kobj);
}
static void kick_rdev_from_array(struct md_rdev *rdev)
void md_kick_rdev_from_array(struct md_rdev *rdev)
{
unbind_rdev_from_array(rdev);
export_rdev(rdev);
}
EXPORT_SYMBOL_GPL(md_kick_rdev_from_array);
static void export_array(struct mddev *mddev)
{
......@@ -2179,7 +2187,7 @@ static void export_array(struct mddev *mddev)
while (!list_empty(&mddev->disks)) {
rdev = list_first_entry(&mddev->disks, struct md_rdev,
same_set);
kick_rdev_from_array(rdev);
md_kick_rdev_from_array(rdev);
}
mddev->raid_disks = 0;
mddev->major_version = 0;
......@@ -2208,7 +2216,7 @@ static void sync_sbs(struct mddev *mddev, int nospares)
}
}
static void md_update_sb(struct mddev *mddev, int force_change)
void md_update_sb(struct mddev *mddev, int force_change)
{
struct md_rdev *rdev;
int sync_req;
......@@ -2369,6 +2377,37 @@ static void md_update_sb(struct mddev *mddev, int force_change)
wake_up(&rdev->blocked_wait);
}
}
EXPORT_SYMBOL(md_update_sb);
static int add_bound_rdev(struct md_rdev *rdev)
{
struct mddev *mddev = rdev->mddev;
int err = 0;
if (!mddev->pers->hot_remove_disk) {
/* If there is hot_add_disk but no hot_remove_disk
* then added disks for geometry changes,
* and should be added immediately.
*/
super_types[mddev->major_version].
validate_super(mddev, rdev);
err = mddev->pers->hot_add_disk(mddev, rdev);
if (err) {
unbind_rdev_from_array(rdev);
export_rdev(rdev);
return err;
}
}
sysfs_notify_dirent_safe(rdev->sysfs_state);
set_bit(MD_CHANGE_DEVS, &mddev->flags);
if (mddev->degraded)
set_bit(MD_RECOVERY_RECOVER, &mddev->recovery);
set_bit(MD_RECOVERY_NEEDED, &mddev->recovery);
md_new_event(mddev);
md_wakeup_thread(mddev->thread);
return 0;
}
/* words written to sysfs files may, or may not, be \n terminated.
* We want to accept with case. For this we use cmd_match.
......@@ -2471,10 +2510,16 @@ state_store(struct md_rdev *rdev, const char *buf, size_t len)
err = -EBUSY;
else {
struct mddev *mddev = rdev->mddev;
kick_rdev_from_array(rdev);
if (mddev_is_clustered(mddev))
md_cluster_ops->remove_disk(mddev, rdev);
md_kick_rdev_from_array(rdev);
if (mddev_is_clustered(mddev))
md_cluster_ops->metadata_update_start(mddev);
if (mddev->pers)
md_update_sb(mddev, 1);
md_new_event(mddev);
if (mddev_is_clustered(mddev))
md_cluster_ops->metadata_update_finish(mddev);
err = 0;
}
} else if (cmd_match(buf, "writemostly")) {
......@@ -2553,6 +2598,21 @@ state_store(struct md_rdev *rdev, const char *buf, size_t len)
clear_bit(Replacement, &rdev->flags);
err = 0;
}
} else if (cmd_match(buf, "re-add")) {
if (test_bit(Faulty, &rdev->flags) && (rdev->raid_disk == -1)) {
/* clear_bit is performed _after_ all the devices
* have their local Faulty bit cleared. If any writes
* happen in the meantime in the local node, they
* will land in the local bitmap, which will be synced
* by this node eventually
*/
if (!mddev_is_clustered(rdev->mddev) ||
(err = md_cluster_ops->gather_bitmaps(rdev)) == 0) {
clear_bit(Faulty, &rdev->flags);
err = add_bound_rdev(rdev);
}
} else
err = -EBUSY;
}
if (!err)
sysfs_notify_dirent_safe(rdev->sysfs_state);
......@@ -3127,7 +3187,7 @@ static void analyze_sbs(struct mddev *mddev)
"md: fatal superblock inconsistency in %s"
" -- removing from array\n",
bdevname(rdev->bdev,b));
kick_rdev_from_array(rdev);
md_kick_rdev_from_array(rdev);
}
super_types[mddev->major_version].
......@@ -3142,18 +3202,27 @@ static void analyze_sbs(struct mddev *mddev)
"md: %s: %s: only %d devices permitted\n",
mdname(mddev), bdevname(rdev->bdev, b),
mddev->max_disks);
kick_rdev_from_array(rdev);
md_kick_rdev_from_array(rdev);
continue;
}
if (rdev != freshest)
if (rdev != freshest) {
if (super_types[mddev->major_version].
validate_super(mddev, rdev)) {
printk(KERN_WARNING "md: kicking non-fresh %s"
" from array!\n",
bdevname(rdev->bdev,b));
kick_rdev_from_array(rdev);
md_kick_rdev_from_array(rdev);
continue;
}
/* No device should have a Candidate flag
* when reading devices
*/
if (test_bit(Candidate, &rdev->flags)) {
pr_info("md: kicking Cluster Candidate %s from array!\n",
bdevname(rdev->bdev, b));
md_kick_rdev_from_array(rdev);
}
}
if (mddev->level == LEVEL_MULTIPATH) {
rdev->desc_nr = i++;
rdev->raid_disk = rdev->desc_nr;
......@@ -4008,8 +4077,12 @@ size_store(struct mddev *mddev, const char *buf, size_t len)
if (err)
return err;
if (mddev->pers) {
if (mddev_is_clustered(mddev))
md_cluster_ops->metadata_update_start(mddev);
err = update_size(mddev, sectors);
md_update_sb(mddev, 1);
if (mddev_is_clustered(mddev))
md_cluster_ops->metadata_update_finish(mddev);
} else {
if (mddev->dev_sectors == 0 ||
mddev->dev_sectors > sectors)
......@@ -5077,10 +5150,16 @@ int md_run(struct mddev *mddev)
}
if (err == 0 && pers->sync_request &&
(mddev->bitmap_info.file || mddev->bitmap_info.offset)) {
err = bitmap_create(mddev);
if (err)
struct bitmap *bitmap;
bitmap = bitmap_create(mddev, -1);
if (IS_ERR(bitmap)) {
err = PTR_ERR(bitmap);
printk(KERN_ERR "%s: failed to create bitmap (%d)\n",
mdname(mddev), err);
} else
mddev->bitmap = bitmap;
}
if (err) {
mddev_detach(mddev);
......@@ -5232,6 +5311,8 @@ static void md_clean(struct mddev *mddev)
static void __md_stop_writes(struct mddev *mddev)
{
if (mddev_is_clustered(mddev))
md_cluster_ops->metadata_update_start(mddev);
set_bit(MD_RECOVERY_FROZEN, &mddev->recovery);
flush_workqueue(md_misc_wq);
if (mddev->sync_thread) {
......@@ -5250,6 +5331,8 @@ static void __md_stop_writes(struct mddev *mddev)
mddev->in_sync = 1;
md_update_sb(mddev, 1);
}
if (mddev_is_clustered(mddev))
md_cluster_ops->metadata_update_finish(mddev);
}
void md_stop_writes(struct mddev *mddev)
......@@ -5636,6 +5719,8 @@ static int get_array_info(struct mddev *mddev, void __user *arg)
info.state = (1<<MD_SB_CLEAN);
if (mddev->bitmap && mddev->bitmap_info.offset)
info.state |= (1<<MD_SB_BITMAP_PRESENT);
if (mddev_is_clustered(mddev))
info.state |= (1<<MD_SB_CLUSTERED);
info.active_disks = insync;
info.working_disks = working;
info.failed_disks = failed;
......@@ -5691,7 +5776,7 @@ static int get_disk_info(struct mddev *mddev, void __user * arg)
return -EFAULT;
rcu_read_lock();
rdev = find_rdev_nr_rcu(mddev, info.number);
rdev = md_find_rdev_nr_rcu(mddev, info.number);
if (rdev) {
info.major = MAJOR(rdev->bdev->bd_dev);
info.minor = MINOR(rdev->bdev->bd_dev);
......@@ -5724,6 +5809,13 @@ static int add_new_disk(struct mddev *mddev, mdu_disk_info_t *info)
struct md_rdev *rdev;
dev_t dev = MKDEV(info->major,info->minor);
if (mddev_is_clustered(mddev) &&
!(info->state & ((1 << MD_DISK_CLUSTER_ADD) | (1 << MD_DISK_CANDIDATE)))) {
pr_err("%s: Cannot add to clustered mddev.\n",
mdname(mddev));
return -EINVAL;
}
if (info->major != MAJOR(dev) || info->minor != MINOR(dev))
return -EOVERFLOW;
......@@ -5810,31 +5902,38 @@ static int add_new_disk(struct mddev *mddev, mdu_disk_info_t *info)
else
clear_bit(WriteMostly, &rdev->flags);
rdev->raid_disk = -1;
err = bind_rdev_to_array(rdev, mddev);
if (!err && !mddev->pers->hot_remove_disk) {
/* If there is hot_add_disk but no hot_remove_disk
* then added disks for geometry changes,
* and should be added immediately.
/*
* check whether the device shows up in other nodes
*/
super_types[mddev->major_version].
validate_super(mddev, rdev);
err = mddev->pers->hot_add_disk(mddev, rdev);
if (err)
unbind_rdev_from_array(rdev);
if (mddev_is_clustered(mddev)) {
if (info->state & (1 << MD_DISK_CANDIDATE)) {
/* Through --cluster-confirm */
set_bit(Candidate, &rdev->flags);
err = md_cluster_ops->new_disk_ack(mddev, true);
if (err) {
export_rdev(rdev);
return err;
}
} else if (info->state & (1 << MD_DISK_CLUSTER_ADD)) {
/* --add initiated by this node */
err = md_cluster_ops->add_new_disk_start(mddev, rdev);
if (err) {
md_cluster_ops->add_new_disk_finish(mddev);
export_rdev(rdev);
return err;
}
}
}
rdev->raid_disk = -1;
err = bind_rdev_to_array(rdev, mddev);
if (err)
export_rdev(rdev);
else
sysfs_notify_dirent_safe(rdev->sysfs_state);
set_bit(MD_CHANGE_DEVS, &mddev->flags);
if (mddev->degraded)
set_bit(MD_RECOVERY_RECOVER, &mddev->recovery);
set_bit(MD_RECOVERY_NEEDED, &mddev->recovery);
if (!err)
md_new_event(mddev);
md_wakeup_thread(mddev->thread);
err = add_bound_rdev(rdev);
if (mddev_is_clustered(mddev) &&
(info->state & (1 << MD_DISK_CLUSTER_ADD)))
md_cluster_ops->add_new_disk_finish(mddev);
return err;
}
......@@ -5895,18 +5994,29 @@ static int hot_remove_disk(struct mddev *mddev, dev_t dev)
if (!rdev)
return -ENXIO;
if (mddev_is_clustered(mddev))
md_cluster_ops->metadata_update_start(mddev);
clear_bit(Blocked, &rdev->flags);
remove_and_add_spares(mddev, rdev);
if (rdev->raid_disk >= 0)
goto busy;
kick_rdev_from_array(rdev);
if (mddev_is_clustered(mddev))
md_cluster_ops->remove_disk(mddev, rdev);
md_kick_rdev_from_array(rdev);
md_update_sb(mddev, 1);
md_new_event(mddev);
if (mddev_is_clustered(mddev))
md_cluster_ops->metadata_update_finish(mddev);
return 0;
busy:
if (mddev_is_clustered(mddev))
md_cluster_ops->metadata_update_cancel(mddev);
printk(KERN_WARNING "md: cannot remove active disk %s from %s ...\n",
bdevname(rdev->bdev,b), mdname(mddev));
return -EBUSY;
......@@ -5956,12 +6066,15 @@ static int hot_add_disk(struct mddev *mddev, dev_t dev)
err = -EINVAL;
goto abort_export;
}
if (mddev_is_clustered(mddev))
md_cluster_ops->metadata_update_start(mddev);
clear_bit(In_sync, &rdev->flags);
rdev->desc_nr = -1;
rdev->saved_raid_disk = -1;
err = bind_rdev_to_array(rdev, mddev);
if (err)
goto abort_export;
goto abort_clustered;
/*
* The rest should better be atomic, we can have disk failures
......@@ -5972,6 +6085,8 @@ static int hot_add_disk(struct mddev *mddev, dev_t dev)
md_update_sb(mddev, 1);
if (mddev_is_clustered(mddev))
md_cluster_ops->metadata_update_finish(mddev);
/*
* Kick recovery, maybe this spare has to be added to the
* array immediately.
......@@ -5981,6 +6096,9 @@ static int hot_add_disk(struct mddev *mddev, dev_t dev)
md_new_event(mddev);
return 0;
abort_clustered:
if (mddev_is_clustered(mddev))
md_cluster_ops->metadata_update_cancel(mddev);
abort_export:
export_rdev(rdev);
return err;
......@@ -6038,9 +6156,14 @@ static int set_bitmap_file(struct mddev *mddev, int fd)
if (mddev->pers) {
mddev->pers->quiesce(mddev, 1);
if (fd >= 0) {
err = bitmap_create(mddev);
if (!err)
struct bitmap *bitmap;
bitmap = bitmap_create(mddev, -1);
if (!IS_ERR(bitmap)) {
mddev->bitmap = bitmap;
err = bitmap_load(mddev);
} else
err = PTR_ERR(bitmap);
}
if (fd < 0 || err) {
bitmap_destroy(mddev);
......@@ -6293,6 +6416,8 @@ static int update_array_info(struct mddev *mddev, mdu_array_info_t *info)
return rv;
}
}
if (mddev_is_clustered(mddev))
md_cluster_ops->metadata_update_start(mddev);
if (info->size >= 0 && mddev->dev_sectors / 2 != info->size)
rv = update_size(mddev, (sector_t)info->size * 2);
......@@ -6300,33 +6425,49 @@ static int update_array_info(struct mddev *mddev, mdu_array_info_t *info)
rv = update_raid_disks(mddev, info->raid_disks);
if ((state ^ info->state) & (1<<MD_SB_BITMAP_PRESENT)) {
if (mddev->pers->quiesce == NULL || mddev->thread == NULL)
return -EINVAL;
if (mddev->recovery || mddev->sync_thread)
return -EBUSY;
if (mddev->pers->quiesce == NULL || mddev->thread == NULL) {
rv = -EINVAL;
goto err;
}
if (mddev->recovery || mddev->sync_thread) {
rv = -EBUSY;
goto err;
}
if (info->state & (1<<MD_SB_BITMAP_PRESENT)) {
struct bitmap *bitmap;
/* add the bitmap */
if (mddev->bitmap)
return -EEXIST;
if (mddev->bitmap_info.default_offset == 0)
return -EINVAL;
if (mddev->bitmap) {
rv = -EEXIST;
goto err;
}
if (mddev->bitmap_info.default_offset == 0) {
rv = -EINVAL;
goto err;
}
mddev->bitmap_info.offset =
mddev->bitmap_info.default_offset;
mddev->bitmap_info.space =
mddev->bitmap_info.default_space;
mddev->pers->quiesce(mddev, 1);
rv = bitmap_create(mddev);
if (!rv)
bitmap = bitmap_create(mddev, -1);
if (!IS_ERR(bitmap)) {
mddev->bitmap = bitmap;
rv = bitmap_load(mddev);
} else
rv = PTR_ERR(bitmap);
if (rv)
bitmap_destroy(mddev);
mddev->pers->quiesce(mddev, 0);
} else {
/* remove the bitmap */
if (!mddev->bitmap)
return -ENOENT;
if (mddev->bitmap->storage.file)
return -EINVAL;
if (!mddev->bitmap) {
rv = -ENOENT;
goto err;
}
if (mddev->bitmap->storage.file) {
rv = -EINVAL;
goto err;
}
mddev->pers->quiesce(mddev, 1);
bitmap_destroy(mddev);
mddev->pers->quiesce(mddev, 0);
......@@ -6334,6 +6475,12 @@ static int update_array_info(struct mddev *mddev, mdu_array_info_t *info)
}
}
md_update_sb(mddev, 1);
if (mddev_is_clustered(mddev))
md_cluster_ops->metadata_update_finish(mddev);
return rv;
err:
if (mddev_is_clustered(mddev))
md_cluster_ops->metadata_update_cancel(mddev);
return rv;
}
......@@ -6393,6 +6540,7 @@ static inline bool md_ioctl_valid(unsigned int cmd)
case SET_DISK_FAULTY:
case STOP_ARRAY:
case STOP_ARRAY_RO:
case CLUSTERED_DISK_NACK:
return true;
default:
return false;
......@@ -6665,6 +6813,13 @@ static int md_ioctl(struct block_device *bdev, fmode_t mode,
goto unlock;
}
case CLUSTERED_DISK_NACK:
if (mddev_is_clustered(mddev))
md_cluster_ops->new_disk_ack(mddev, false);
else
err = -EINVAL;
goto unlock;
case HOT_ADD_DISK:
err = hot_add_disk(mddev, new_decode_dev(arg));
goto unlock;
......@@ -7238,6 +7393,55 @@ int unregister_md_personality(struct md_personality *p)
}
EXPORT_SYMBOL(unregister_md_personality);
int register_md_cluster_operations(struct md_cluster_operations *ops, struct module *module)
{
if (md_cluster_ops != NULL)
return -EALREADY;
spin_lock(&pers_lock);
md_cluster_ops = ops;
md_cluster_mod = module;
spin_unlock(&pers_lock);
return 0;
}
EXPORT_SYMBOL(register_md_cluster_operations);
int unregister_md_cluster_operations(void)
{
spin_lock(&pers_lock);
md_cluster_ops = NULL;
spin_unlock(&pers_lock);
return 0;
}
EXPORT_SYMBOL(unregister_md_cluster_operations);
int md_setup_cluster(struct mddev *mddev, int nodes)
{
int err;
err = request_module("md-cluster");
if (err) {
pr_err("md-cluster module not found.\n");
return err;
}
spin_lock(&pers_lock);
if (!md_cluster_ops || !try_module_get(md_cluster_mod)) {
spin_unlock(&pers_lock);
return -ENOENT;
}
spin_unlock(&pers_lock);
return md_cluster_ops->join(mddev, nodes);
}
void md_cluster_stop(struct mddev *mddev)
{
if (!md_cluster_ops)
return;
md_cluster_ops->leave(mddev);
module_put(md_cluster_mod);
}
static int is_mddev_idle(struct mddev *mddev, int init)
{
struct md_rdev *rdev;
......@@ -7375,7 +7579,11 @@ int md_allow_write(struct mddev *mddev)
mddev->safemode == 0)
mddev->safemode = 1;
spin_unlock(&mddev->lock);
if (mddev_is_clustered(mddev))
md_cluster_ops->metadata_update_start(mddev);
md_update_sb(mddev, 0);
if (mddev_is_clustered(mddev))
md_cluster_ops->metadata_update_finish(mddev);
sysfs_notify_dirent_safe(mddev->sysfs_state);
} else
spin_unlock(&mddev->lock);
......@@ -7576,6 +7784,9 @@ void md_do_sync(struct md_thread *thread)
md_new_event(mddev);
update_time = jiffies;
if (mddev_is_clustered(mddev))
md_cluster_ops->resync_start(mddev, j, max_sectors);
blk_start_plug(&plug);
while (j < max_sectors) {
sector_t sectors;
......@@ -7636,6 +7847,8 @@ void md_do_sync(struct md_thread *thread)
j += sectors;
if (j > 2)
mddev->curr_resync = j;
if (mddev_is_clustered(mddev))
md_cluster_ops->resync_info_update(mddev, j, max_sectors);
mddev->curr_mark_cnt = io_sectors;
if (last_check == 0)
/* this is the earliest that rebuild will be
......@@ -7696,6 +7909,9 @@ void md_do_sync(struct md_thread *thread)
/* tell personality that we are finished */
mddev->pers->sync_request(mddev, max_sectors, &skipped, 1);
if (mddev_is_clustered(mddev))
md_cluster_ops->resync_finish(mddev);
if (!test_bit(MD_RECOVERY_CHECK, &mddev->recovery) &&
mddev->curr_resync > 2) {
if (test_bit(MD_RECOVERY_SYNC, &mddev->recovery)) {
......@@ -7925,8 +8141,13 @@ void md_check_recovery(struct mddev *mddev)
sysfs_notify_dirent_safe(mddev->sysfs_state);
}
if (mddev->flags & MD_UPDATE_SB_FLAGS)
if (mddev->flags & MD_UPDATE_SB_FLAGS) {
if (mddev_is_clustered(mddev))
md_cluster_ops->metadata_update_start(mddev);
md_update_sb(mddev, 0);
if (mddev_is_clustered(mddev))
md_cluster_ops->metadata_update_finish(mddev);
}
if (test_bit(MD_RECOVERY_RUNNING, &mddev->recovery) &&
!test_bit(MD_RECOVERY_DONE, &mddev->recovery)) {
......@@ -8024,6 +8245,8 @@ void md_reap_sync_thread(struct mddev *mddev)
set_bit(MD_CHANGE_DEVS, &mddev->flags);
}
}
if (mddev_is_clustered(mddev))
md_cluster_ops->metadata_update_start(mddev);
if (test_bit(MD_RECOVERY_RESHAPE, &mddev->recovery) &&
mddev->pers->finish_reshape)
mddev->pers->finish_reshape(mddev);
......@@ -8036,6 +8259,8 @@ void md_reap_sync_thread(struct mddev *mddev)
rdev->saved_raid_disk = -1;
md_update_sb(mddev, 1);
if (mddev_is_clustered(mddev))
md_cluster_ops->metadata_update_finish(mddev);
clear_bit(MD_RECOVERY_RUNNING, &mddev->recovery);
clear_bit(MD_RECOVERY_SYNC, &mddev->recovery);
clear_bit(MD_RECOVERY_RESHAPE, &mddev->recovery);
......@@ -8656,6 +8881,28 @@ static int __init md_init(void)
return ret;
}
void md_reload_sb(struct mddev *mddev)
{
struct md_rdev *rdev, *tmp;
rdev_for_each_safe(rdev, tmp, mddev) {
rdev->sb_loaded = 0;
ClearPageUptodate(rdev->sb_page);
}
mddev->raid_disks = 0;
analyze_sbs(mddev);
rdev_for_each_safe(rdev, tmp, mddev) {
struct mdp_superblock_1 *sb = page_address(rdev->sb_page);
/* since we don't write to faulty devices, we figure out if the
* disk is faulty by comparing events
*/
if (mddev->events > sb->events)
set_bit(Faulty, &rdev->flags);
}
}
EXPORT_SYMBOL(md_reload_sb);
#ifndef MODULE
/*
......
......@@ -23,6 +23,7 @@
#include <linux/timer.h>
#include <linux/wait.h>
#include <linux/workqueue.h>
#include "md-cluster.h"
#define MaxSector (~(sector_t)0)
......@@ -170,6 +171,10 @@ enum flag_bits {
* a want_replacement device with same
* raid_disk number.
*/
Candidate, /* For clustered environments only:
* This device is seen locally but not
* by the whole cluster
*/
};
#define BB_LEN_MASK (0x00000000000001FFULL)
......@@ -202,6 +207,8 @@ extern int rdev_clear_badblocks(struct md_rdev *rdev, sector_t s, int sectors,
int is_new);
extern void md_ack_all_badblocks(struct badblocks *bb);
struct md_cluster_info;
struct mddev {
void *private;
struct md_personality *pers;
......@@ -430,6 +437,8 @@ struct mddev {
unsigned long daemon_sleep; /* how many jiffies between updates? */
unsigned long max_write_behind; /* write-behind mode */
int external;
int nodes; /* Maximum number of nodes in the cluster */
char cluster_name[64]; /* Name of the cluster */
} bitmap_info;
atomic_t max_corr_read_errors; /* max read retries */
......@@ -448,6 +457,7 @@ struct mddev {
struct work_struct flush_work;
struct work_struct event_work; /* used by dm to report failure event */
void (*sync_super)(struct mddev *mddev, struct md_rdev *rdev);
struct md_cluster_info *cluster_info;
};
static inline int __must_check mddev_lock(struct mddev *mddev)
......@@ -608,6 +618,11 @@ static inline void safe_put_page(struct page *p)
extern int register_md_personality(struct md_personality *p);
extern int unregister_md_personality(struct md_personality *p);
extern int register_md_cluster_operations(struct md_cluster_operations *ops,
struct module *module);
extern int unregister_md_cluster_operations(void);
extern int md_setup_cluster(struct mddev *mddev, int nodes);
extern void md_cluster_stop(struct mddev *mddev);
extern struct md_thread *md_register_thread(
void (*run)(struct md_thread *thread),
struct mddev *mddev,
......@@ -654,6 +669,10 @@ extern struct bio *bio_alloc_mddev(gfp_t gfp_mask, int nr_iovecs,
struct mddev *mddev);
extern void md_unplug(struct blk_plug_cb *cb, bool from_schedule);
extern void md_reload_sb(struct mddev *mddev);
extern void md_update_sb(struct mddev *mddev, int force);
extern void md_kick_rdev_from_array(struct md_rdev * rdev);
struct md_rdev *md_find_rdev_nr_rcu(struct mddev *mddev, int nr);
static inline int mddev_check_plugged(struct mddev *mddev)
{
return !!blk_check_plugged(md_unplug, mddev,
......@@ -669,4 +688,9 @@ static inline void rdev_dec_pending(struct md_rdev *rdev, struct mddev *mddev)
}
}
extern struct md_cluster_operations *md_cluster_ops;
static inline int mddev_is_clustered(struct mddev *mddev)
{
return mddev->cluster_info && mddev->bitmap_info.nodes > 1;
}
#endif /* _MD_MD_H */
......@@ -539,7 +539,13 @@ static int read_balance(struct r1conf *conf, struct r1bio *r1_bio, int *max_sect
has_nonrot_disk = 0;
choose_next_idle = 0;
choose_first = (conf->mddev->recovery_cp < this_sector + sectors);
if ((conf->mddev->recovery_cp < this_sector + sectors) ||
(mddev_is_clustered(conf->mddev) &&
md_cluster_ops->area_resyncing(conf->mddev, this_sector,
this_sector + sectors)))
choose_first = 1;
else
choose_first = 0;
for (disk = 0 ; disk < conf->raid_disks * 2 ; disk++) {
sector_t dist;
......@@ -1102,8 +1108,10 @@ static void make_request(struct mddev *mddev, struct bio * bio)
md_write_start(mddev, bio); /* wait on superblock update early */
if (bio_data_dir(bio) == WRITE &&
bio_end_sector(bio) > mddev->suspend_lo &&
bio->bi_iter.bi_sector < mddev->suspend_hi) {
((bio_end_sector(bio) > mddev->suspend_lo &&
bio->bi_iter.bi_sector < mddev->suspend_hi) ||
(mddev_is_clustered(mddev) &&
md_cluster_ops->area_resyncing(mddev, bio->bi_iter.bi_sector, bio_end_sector(bio))))) {
/* As the suspend_* range is controlled by
* userspace, we want an interruptible
* wait.
......@@ -1114,7 +1122,10 @@ static void make_request(struct mddev *mddev, struct bio * bio)
prepare_to_wait(&conf->wait_barrier,
&w, TASK_INTERRUPTIBLE);
if (bio_end_sector(bio) <= mddev->suspend_lo ||
bio->bi_iter.bi_sector >= mddev->suspend_hi)
bio->bi_iter.bi_sector >= mddev->suspend_hi ||
(mddev_is_clustered(mddev) &&
!md_cluster_ops->area_resyncing(mddev,
bio->bi_iter.bi_sector, bio_end_sector(bio))))
break;
schedule();
}
......@@ -1561,6 +1572,7 @@ static int raid1_spare_active(struct mddev *mddev)
struct md_rdev *rdev = conf->mirrors[i].rdev;
struct md_rdev *repl = conf->mirrors[conf->raid_disks + i].rdev;
if (repl
&& !test_bit(Candidate, &repl->flags)
&& repl->recovery_offset == MaxSector
&& !test_bit(Faulty, &repl->flags)
&& !test_and_set_bit(In_sync, &repl->flags)) {
......
......@@ -78,6 +78,12 @@
#define MD_DISK_ACTIVE 1 /* disk is running or spare disk */
#define MD_DISK_SYNC 2 /* disk is in sync with the raid set */
#define MD_DISK_REMOVED 3 /* disk is in sync with the raid set */
#define MD_DISK_CLUSTER_ADD 4 /* Initiate a disk add across the cluster
* For clustered enviroments only.
*/
#define MD_DISK_CANDIDATE 5 /* disk is added as spare (local) until confirmed
* For clustered enviroments only.
*/
#define MD_DISK_WRITEMOSTLY 9 /* disk is "write-mostly" is RAID1 config.
* read requests will only be sent here in
......@@ -101,6 +107,7 @@ typedef struct mdp_device_descriptor_s {
#define MD_SB_CLEAN 0
#define MD_SB_ERRORS 1
#define MD_SB_CLUSTERED 5 /* MD is clustered */
#define MD_SB_BITMAP_PRESENT 8 /* bitmap may be present nearby */
/*
......
......@@ -62,6 +62,7 @@
#define STOP_ARRAY _IO (MD_MAJOR, 0x32)
#define STOP_ARRAY_RO _IO (MD_MAJOR, 0x33)
#define RESTART_ARRAY_RW _IO (MD_MAJOR, 0x34)
#define CLUSTERED_DISK_NACK _IO (MD_MAJOR, 0x35)
/* 63 partitions with the alternate major number (mdp) */
#define MdpMinorShift 6
......
Markdown is supported
0%
or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment