summaryrefslogtreecommitdiff
path: root/drivers/md
diff options
context:
space:
mode:
Diffstat (limited to 'drivers/md')
-rw-r--r--drivers/md/bcache/btree.c5
-rw-r--r--drivers/md/bcache/super.c16
-rw-r--r--drivers/md/bcache/writeback.c37
-rw-r--r--drivers/md/bcache/writeback.h3
-rw-r--r--drivers/md/bitmap.c4
-rw-r--r--drivers/md/faulty.c18
-rw-r--r--drivers/md/md-cluster.c170
-rw-r--r--drivers/md/md-cluster.h2
-rw-r--r--drivers/md/md.c171
-rw-r--r--drivers/md/md.h11
-rw-r--r--drivers/md/multipath.c6
-rw-r--r--drivers/md/raid0.c4
-rw-r--r--drivers/md/raid1.c27
-rw-r--r--drivers/md/raid10.c26
-rw-r--r--drivers/md/raid5-cache.c158
-rw-r--r--drivers/md/raid5.c81
16 files changed, 526 insertions, 213 deletions
diff --git a/drivers/md/bcache/btree.c b/drivers/md/bcache/btree.c
index 83392f856dfd..22b9e34ceb75 100644
--- a/drivers/md/bcache/btree.c
+++ b/drivers/md/bcache/btree.c
@@ -1741,6 +1741,7 @@ static void bch_btree_gc(struct cache_set *c)
do {
ret = btree_root(gc_root, c, &op, &writes, &stats);
closure_sync(&writes);
+ cond_resched();
if (ret && ret != -EAGAIN)
pr_warn("gc failed!");
@@ -2162,8 +2163,10 @@ int bch_btree_insert_check_key(struct btree *b, struct btree_op *op,
rw_lock(true, b, b->level);
if (b->key.ptr[0] != btree_ptr ||
- b->seq != seq + 1)
+ b->seq != seq + 1) {
+ op->lock = b->level;
goto out;
+ }
}
SET_KEY_PTRS(check_key, 1);
diff --git a/drivers/md/bcache/super.c b/drivers/md/bcache/super.c
index 679a093a3bf6..8d0ead98eb6e 100644
--- a/drivers/md/bcache/super.c
+++ b/drivers/md/bcache/super.c
@@ -685,6 +685,8 @@ static void bcache_device_link(struct bcache_device *d, struct cache_set *c,
WARN(sysfs_create_link(&d->kobj, &c->kobj, "cache") ||
sysfs_create_link(&c->kobj, &d->kobj, d->name),
"Couldn't create device <-> cache set symlinks");
+
+ clear_bit(BCACHE_DEV_UNLINK_DONE, &d->flags);
}
static void bcache_device_detach(struct bcache_device *d)
@@ -847,8 +849,11 @@ void bch_cached_dev_run(struct cached_dev *dc)
buf[SB_LABEL_SIZE] = '\0';
env[2] = kasprintf(GFP_KERNEL, "CACHED_LABEL=%s", buf);
- if (atomic_xchg(&dc->running, 1))
+ if (atomic_xchg(&dc->running, 1)) {
+ kfree(env[1]);
+ kfree(env[2]);
return;
+ }
if (!d->c &&
BDEV_STATE(&dc->sb) != BDEV_STATE_NONE) {
@@ -1933,6 +1938,8 @@ static ssize_t register_bcache(struct kobject *k, struct kobj_attribute *attr,
else
err = "device busy";
mutex_unlock(&bch_register_lock);
+ if (attr == &ksysfs_register_quiet)
+ goto out;
}
goto err;
}
@@ -1971,8 +1978,7 @@ out:
err_close:
blkdev_put(bdev, FMODE_READ|FMODE_WRITE|FMODE_EXCL);
err:
- if (attr != &ksysfs_register_quiet)
- pr_info("error opening %s: %s", path, err);
+ pr_info("error opening %s: %s", path, err);
ret = -EINVAL;
goto out;
}
@@ -2066,8 +2072,10 @@ static int __init bcache_init(void)
closure_debug_init();
bcache_major = register_blkdev(0, "bcache");
- if (bcache_major < 0)
+ if (bcache_major < 0) {
+ unregister_reboot_notifier(&reboot);
return bcache_major;
+ }
if (!(bcache_wq = create_workqueue("bcache")) ||
!(bcache_kobj = kobject_create_and_add("bcache", fs_kobj)) ||
diff --git a/drivers/md/bcache/writeback.c b/drivers/md/bcache/writeback.c
index b23f88d9f18c..b9346cd9cda1 100644
--- a/drivers/md/bcache/writeback.c
+++ b/drivers/md/bcache/writeback.c
@@ -323,6 +323,10 @@ void bcache_dev_sectors_dirty_add(struct cache_set *c, unsigned inode,
static bool dirty_pred(struct keybuf *buf, struct bkey *k)
{
+ struct cached_dev *dc = container_of(buf, struct cached_dev, writeback_keys);
+
+ BUG_ON(KEY_INODE(k) != dc->disk.id);
+
return KEY_DIRTY(k);
}
@@ -372,11 +376,24 @@ next:
}
}
+/*
+ * Returns true if we scanned the entire disk
+ */
static bool refill_dirty(struct cached_dev *dc)
{
struct keybuf *buf = &dc->writeback_keys;
+ struct bkey start = KEY(dc->disk.id, 0, 0);
struct bkey end = KEY(dc->disk.id, MAX_KEY_OFFSET, 0);
- bool searched_from_start = false;
+ struct bkey start_pos;
+
+ /*
+ * make sure keybuf pos is inside the range for this disk - at bringup
+ * we might not be attached yet so this disk's inode nr isn't
+ * initialized then
+ */
+ if (bkey_cmp(&buf->last_scanned, &start) < 0 ||
+ bkey_cmp(&buf->last_scanned, &end) > 0)
+ buf->last_scanned = start;
if (dc->partial_stripes_expensive) {
refill_full_stripes(dc);
@@ -384,14 +401,20 @@ static bool refill_dirty(struct cached_dev *dc)
return false;
}
- if (bkey_cmp(&buf->last_scanned, &end) >= 0) {
- buf->last_scanned = KEY(dc->disk.id, 0, 0);
- searched_from_start = true;
- }
-
+ start_pos = buf->last_scanned;
bch_refill_keybuf(dc->disk.c, buf, &end, dirty_pred);
- return bkey_cmp(&buf->last_scanned, &end) >= 0 && searched_from_start;
+ if (bkey_cmp(&buf->last_scanned, &end) < 0)
+ return false;
+
+ /*
+ * If we get to the end start scanning again from the beginning, and
+ * only scan up to where we initially started scanning from:
+ */
+ buf->last_scanned = start;
+ bch_refill_keybuf(dc->disk.c, buf, &start_pos, dirty_pred);
+
+ return bkey_cmp(&buf->last_scanned, &start_pos) >= 0;
}
static int bch_writeback_thread(void *arg)
diff --git a/drivers/md/bcache/writeback.h b/drivers/md/bcache/writeback.h
index 0a9dab187b79..073a042aed24 100644
--- a/drivers/md/bcache/writeback.h
+++ b/drivers/md/bcache/writeback.h
@@ -63,7 +63,8 @@ static inline bool should_writeback(struct cached_dev *dc, struct bio *bio,
static inline void bch_writeback_queue(struct cached_dev *dc)
{
- wake_up_process(dc->writeback_thread);
+ if (!IS_ERR_OR_NULL(dc->writeback_thread))
+ wake_up_process(dc->writeback_thread);
}
static inline void bch_writeback_add(struct cached_dev *dc)
diff --git a/drivers/md/bitmap.c b/drivers/md/bitmap.c
index 4f22e919787a..d80cce499a56 100644
--- a/drivers/md/bitmap.c
+++ b/drivers/md/bitmap.c
@@ -210,10 +210,6 @@ 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;
diff --git a/drivers/md/faulty.c b/drivers/md/faulty.c
index 4a8e15058e8b..685aa2d77e25 100644
--- a/drivers/md/faulty.c
+++ b/drivers/md/faulty.c
@@ -170,7 +170,7 @@ static void add_sector(struct faulty_conf *conf, sector_t start, int mode)
conf->nfaults = n+1;
}
-static void make_request(struct mddev *mddev, struct bio *bio)
+static void faulty_make_request(struct mddev *mddev, struct bio *bio)
{
struct faulty_conf *conf = mddev->private;
int failit = 0;
@@ -226,7 +226,7 @@ static void make_request(struct mddev *mddev, struct bio *bio)
generic_make_request(bio);
}
-static void status(struct seq_file *seq, struct mddev *mddev)
+static void faulty_status(struct seq_file *seq, struct mddev *mddev)
{
struct faulty_conf *conf = mddev->private;
int n;
@@ -259,7 +259,7 @@ static void status(struct seq_file *seq, struct mddev *mddev)
}
-static int reshape(struct mddev *mddev)
+static int faulty_reshape(struct mddev *mddev)
{
int mode = mddev->new_layout & ModeMask;
int count = mddev->new_layout >> ModeShift;
@@ -299,7 +299,7 @@ static sector_t faulty_size(struct mddev *mddev, sector_t sectors, int raid_disk
return sectors;
}
-static int run(struct mddev *mddev)
+static int faulty_run(struct mddev *mddev)
{
struct md_rdev *rdev;
int i;
@@ -327,7 +327,7 @@ static int run(struct mddev *mddev)
md_set_array_sectors(mddev, faulty_size(mddev, 0, 0));
mddev->private = conf;
- reshape(mddev);
+ faulty_reshape(mddev);
return 0;
}
@@ -344,11 +344,11 @@ static struct md_personality faulty_personality =
.name = "faulty",
.level = LEVEL_FAULTY,
.owner = THIS_MODULE,
- .make_request = make_request,
- .run = run,
+ .make_request = faulty_make_request,
+ .run = faulty_run,
.free = faulty_free,
- .status = status,
- .check_reshape = reshape,
+ .status = faulty_status,
+ .check_reshape = faulty_reshape,
.size = faulty_size,
};
diff --git a/drivers/md/md-cluster.c b/drivers/md/md-cluster.c
index d6a1126d85ce..dd97d4245822 100644
--- a/drivers/md/md-cluster.c
+++ b/drivers/md/md-cluster.c
@@ -48,13 +48,29 @@ struct resync_info {
#define MD_CLUSTER_SUSPEND_READ_BALANCING 2
#define MD_CLUSTER_BEGIN_JOIN_CLUSTER 3
+/* Lock the send communication. This is done through
+ * bit manipulation as opposed to a mutex in order to
+ * accomodate lock and hold. See next comment.
+ */
+#define MD_CLUSTER_SEND_LOCK 4
+/* If cluster operations (such as adding a disk) must lock the
+ * communication channel, so as to perform extra operations
+ * (update metadata) and no other operation is allowed on the
+ * MD. Token needs to be locked and held until the operation
+ * completes witha md_update_sb(), which would eventually release
+ * the lock.
+ */
+#define MD_CLUSTER_SEND_LOCKED_ALREADY 5
+
struct md_cluster_info {
/* dlm lock space and resources for clustered raid. */
dlm_lockspace_t *lockspace;
int slot_number;
struct completion completion;
+ struct mutex recv_mutex;
struct dlm_lock_resource *bitmap_lockres;
+ struct dlm_lock_resource **other_bitmap_lockres;
struct dlm_lock_resource *resync_lockres;
struct list_head suspend_list;
spinlock_t suspend_lock;
@@ -67,6 +83,7 @@ struct md_cluster_info {
struct dlm_lock_resource *no_new_dev_lockres;
struct md_thread *recv_thread;
struct completion newdisk_completion;
+ wait_queue_head_t wait;
unsigned long state;
};
@@ -276,6 +293,7 @@ static void recover_bitmaps(struct md_thread *thread)
dlm_unlock:
dlm_unlock_sync(bm_lockres);
clear_bit:
+ lockres_free(bm_lockres);
clear_bit(slot, &cinfo->recovery_map);
}
}
@@ -431,8 +449,10 @@ static void process_add_new_disk(struct mddev *mddev, struct cluster_msg *cmsg)
static void process_metadata_update(struct mddev *mddev, struct cluster_msg *msg)
{
struct md_cluster_info *cinfo = mddev->cluster_info;
- md_reload_sb(mddev, le32_to_cpu(msg->raid_slot));
+ 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 process_remove_disk(struct mddev *mddev, struct cluster_msg *msg)
@@ -440,8 +460,11 @@ 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)
- md_kick_rdev_from_array(rdev);
+ 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));
@@ -502,9 +525,11 @@ static void recv_daemon(struct md_thread *thread)
struct cluster_msg msg;
int ret;
+ mutex_lock(&cinfo->recv_mutex);
/*get CR on Message*/
if (dlm_lock_sync(message_lockres, DLM_LOCK_CR)) {
pr_err("md/raid1:failed to get CR on MESSAGE\n");
+ mutex_unlock(&cinfo->recv_mutex);
return;
}
@@ -528,33 +553,45 @@ static void recv_daemon(struct md_thread *thread)
ret = dlm_unlock_sync(message_lockres);
if (unlikely(ret != 0))
pr_info("unlock msg failed return %d\n", ret);
+ mutex_unlock(&cinfo->recv_mutex);
}
-/* lock_comm()
+/* lock_token()
* Takes the lock on the TOKEN lock resource so no other
* node can communicate while the operation is underway.
- * If called again, and the TOKEN lock is alread in EX mode
- * return success. However, care must be taken that unlock_comm()
- * is called only once.
*/
-static int lock_comm(struct md_cluster_info *cinfo)
+static int lock_token(struct md_cluster_info *cinfo)
{
int error;
- if (cinfo->token_lockres->mode == DLM_LOCK_EX)
- return 0;
-
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);
+
+ /* Lock the receive sequence */
+ mutex_lock(&cinfo->recv_mutex);
return error;
}
+/* lock_comm()
+ * Sets the MD_CLUSTER_SEND_LOCK bit to lock the send channel.
+ */
+static int lock_comm(struct md_cluster_info *cinfo)
+{
+ wait_event(cinfo->wait,
+ !test_and_set_bit(MD_CLUSTER_SEND_LOCK, &cinfo->state));
+
+ return lock_token(cinfo);
+}
+
static void unlock_comm(struct md_cluster_info *cinfo)
{
WARN_ON(cinfo->token_lockres->mode != DLM_LOCK_EX);
+ mutex_unlock(&cinfo->recv_mutex);
dlm_unlock_sync(cinfo->token_lockres);
+ clear_bit(MD_CLUSTER_SEND_LOCK, &cinfo->state);
+ wake_up(&cinfo->wait);
}
/* __sendmsg()
@@ -646,8 +683,10 @@ static int gather_all_resync_info(struct mddev *mddev, int total_slots)
bm_lockres = lockres_init(mddev, str, NULL, 1);
if (!bm_lockres)
return -ENOMEM;
- if (i == (cinfo->slot_number - 1))
+ if (i == (cinfo->slot_number - 1)) {
+ lockres_free(bm_lockres);
continue;
+ }
bm_lockres->flags |= DLM_LKF_NOQUEUE;
ret = dlm_lock_sync(bm_lockres, DLM_LOCK_PW);
@@ -707,6 +746,8 @@ static int join(struct mddev *mddev, int nodes)
spin_lock_init(&cinfo->suspend_lock);
init_completion(&cinfo->completion);
set_bit(MD_CLUSTER_BEGIN_JOIN_CLUSTER, &cinfo->state);
+ init_waitqueue_head(&cinfo->wait);
+ mutex_init(&cinfo->recv_mutex);
mddev->cluster_info = cinfo;
@@ -800,6 +841,7 @@ static void resync_bitmap(struct mddev *mddev)
__func__, __LINE__, err);
}
+static void unlock_all_bitmaps(struct mddev *mddev);
static int leave(struct mddev *mddev)
{
struct md_cluster_info *cinfo = mddev->cluster_info;
@@ -819,7 +861,9 @@ static int leave(struct mddev *mddev)
lockres_free(cinfo->token_lockres);
lockres_free(cinfo->ack_lockres);
lockres_free(cinfo->no_new_dev_lockres);
+ lockres_free(cinfo->resync_lockres);
lockres_free(cinfo->bitmap_lockres);
+ unlock_all_bitmaps(mddev);
dlm_release_lockspace(cinfo->lockspace, 2);
return 0;
}
@@ -835,9 +879,25 @@ static int slot_number(struct mddev *mddev)
return cinfo->slot_number - 1;
}
+/*
+ * Check if the communication is already locked, else lock the communication
+ * channel.
+ * If it is already locked, token is in EX mode, and hence lock_token()
+ * should not be called.
+ */
static int metadata_update_start(struct mddev *mddev)
{
- return lock_comm(mddev->cluster_info);
+ struct md_cluster_info *cinfo = mddev->cluster_info;
+
+ wait_event(cinfo->wait,
+ !test_and_set_bit(MD_CLUSTER_SEND_LOCK, &cinfo->state) ||
+ test_and_clear_bit(MD_CLUSTER_SEND_LOCKED_ALREADY, &cinfo->state));
+
+ /* If token is already locked, return 0 */
+ if (cinfo->token_lockres->mode == DLM_LOCK_EX)
+ return 0;
+
+ return lock_token(cinfo);
}
static int metadata_update_finish(struct mddev *mddev)
@@ -862,6 +922,7 @@ static int metadata_update_finish(struct mddev *mddev)
ret = __sendmsg(cinfo, &cmsg);
} else
pr_warn("md-cluster: No good device id found to send\n");
+ clear_bit(MD_CLUSTER_SEND_LOCKED_ALREADY, &cinfo->state);
unlock_comm(cinfo);
return ret;
}
@@ -869,6 +930,7 @@ static int metadata_update_finish(struct mddev *mddev)
static void metadata_update_cancel(struct mddev *mddev)
{
struct md_cluster_info *cinfo = mddev->cluster_info;
+ clear_bit(MD_CLUSTER_SEND_LOCKED_ALREADY, &cinfo->state);
unlock_comm(cinfo);
}
@@ -882,8 +944,16 @@ static int resync_start(struct mddev *mddev)
static int resync_info_update(struct mddev *mddev, sector_t lo, sector_t hi)
{
struct md_cluster_info *cinfo = mddev->cluster_info;
+ struct resync_info ri;
struct cluster_msg cmsg = {0};
+ /* do not send zero again, if we have sent before */
+ if (hi == 0) {
+ memcpy(&ri, cinfo->bitmap_lockres->lksb.sb_lvbptr, sizeof(struct resync_info));
+ if (le64_to_cpu(ri.hi) == 0)
+ return 0;
+ }
+
add_resync_info(cinfo->bitmap_lockres, lo, hi);
/* Re-acquire the lock to refresh LVB */
dlm_lock_sync(cinfo->bitmap_lockres, DLM_LOCK_PW);
@@ -954,14 +1024,30 @@ static int add_new_disk(struct mddev *mddev, struct md_rdev *rdev)
ret = -ENOENT;
if (ret)
unlock_comm(cinfo);
- else
+ else {
dlm_lock_sync(cinfo->no_new_dev_lockres, DLM_LOCK_CR);
+ /* Since MD_CHANGE_DEVS will be set in add_bound_rdev which
+ * will run soon after add_new_disk, the below path will be
+ * invoked:
+ * md_wakeup_thread(mddev->thread)
+ * -> conf->thread (raid1d)
+ * -> md_check_recovery -> md_update_sb
+ * -> metadata_update_start/finish
+ * MD_CLUSTER_SEND_LOCKED_ALREADY will be cleared eventually.
+ *
+ * For other failure cases, metadata_update_cancel and
+ * add_new_disk_cancel also clear below bit as well.
+ * */
+ set_bit(MD_CLUSTER_SEND_LOCKED_ALREADY, &cinfo->state);
+ wake_up(&cinfo->wait);
+ }
return ret;
}
static void add_new_disk_cancel(struct mddev *mddev)
{
struct md_cluster_info *cinfo = mddev->cluster_info;
+ clear_bit(MD_CLUSTER_SEND_LOCKED_ALREADY, &cinfo->state);
unlock_comm(cinfo);
}
@@ -986,7 +1072,59 @@ static int remove_disk(struct mddev *mddev, struct md_rdev *rdev)
struct md_cluster_info *cinfo = mddev->cluster_info;
cmsg.type = cpu_to_le32(REMOVE);
cmsg.raid_slot = cpu_to_le32(rdev->desc_nr);
- return __sendmsg(cinfo, &cmsg);
+ return sendmsg(cinfo, &cmsg);
+}
+
+static int lock_all_bitmaps(struct mddev *mddev)
+{
+ int slot, my_slot, ret, held = 1, i = 0;
+ char str[64];
+ struct md_cluster_info *cinfo = mddev->cluster_info;
+
+ cinfo->other_bitmap_lockres = kzalloc((mddev->bitmap_info.nodes - 1) *
+ sizeof(struct dlm_lock_resource *),
+ GFP_KERNEL);
+ if (!cinfo->other_bitmap_lockres) {
+ pr_err("md: can't alloc mem for other bitmap locks\n");
+ return 0;
+ }
+
+ my_slot = slot_number(mddev);
+ for (slot = 0; slot < mddev->bitmap_info.nodes; slot++) {
+ if (slot == my_slot)
+ continue;
+
+ memset(str, '\0', 64);
+ snprintf(str, 64, "bitmap%04d", slot);
+ cinfo->other_bitmap_lockres[i] = lockres_init(mddev, str, NULL, 1);
+ if (!cinfo->other_bitmap_lockres[i])
+ return -ENOMEM;
+
+ cinfo->other_bitmap_lockres[i]->flags |= DLM_LKF_NOQUEUE;
+ ret = dlm_lock_sync(cinfo->other_bitmap_lockres[i], DLM_LOCK_PW);
+ if (ret)
+ held = -1;
+ i++;
+ }
+
+ return held;
+}
+
+static void unlock_all_bitmaps(struct mddev *mddev)
+{
+ struct md_cluster_info *cinfo = mddev->cluster_info;
+ int i;
+
+ /* release other node's bitmap lock if they are existed */
+ if (cinfo->other_bitmap_lockres) {
+ for (i = 0; i < mddev->bitmap_info.nodes - 1; i++) {
+ if (cinfo->other_bitmap_lockres[i]) {
+ dlm_unlock_sync(cinfo->other_bitmap_lockres[i]);
+ lockres_free(cinfo->other_bitmap_lockres[i]);
+ }
+ }
+ kfree(cinfo->other_bitmap_lockres);
+ }
}
static int gather_bitmaps(struct md_rdev *rdev)
@@ -1034,6 +1172,8 @@ static struct md_cluster_operations cluster_ops = {
.new_disk_ack = new_disk_ack,
.remove_disk = remove_disk,
.gather_bitmaps = gather_bitmaps,
+ .lock_all_bitmaps = lock_all_bitmaps,
+ .unlock_all_bitmaps = unlock_all_bitmaps,
};
static int __init cluster_init(void)
diff --git a/drivers/md/md-cluster.h b/drivers/md/md-cluster.h
index e75ea2613184..45ce6c97d8bd 100644
--- a/drivers/md/md-cluster.h
+++ b/drivers/md/md-cluster.h
@@ -24,6 +24,8 @@ struct md_cluster_operations {
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);
+ int (*lock_all_bitmaps)(struct mddev *mddev);
+ void (*unlock_all_bitmaps)(struct mddev *mddev);
};
#endif /* _MD_CLUSTER_H */
diff --git a/drivers/md/md.c b/drivers/md/md.c
index 31b595479aa5..e55e6cf9ec17 100644
--- a/drivers/md/md.c
+++ b/drivers/md/md.c
@@ -206,15 +206,6 @@ void md_new_event(struct mddev *mddev)
}
EXPORT_SYMBOL_GPL(md_new_event);
-/* Alternate version that can be called from interrupts
- * when calling sysfs_notify isn't needed.
- */
-static void md_new_event_inintr(struct mddev *mddev)
-{
- atomic_inc(&md_event_count);
- wake_up(&md_event_waiters);
-}
-
/*
* Enables to iterate over all existing md arrays
* all_mddevs_lock protects this list.
@@ -260,8 +251,7 @@ static blk_qc_t md_make_request(struct request_queue *q, struct bio *bio)
blk_queue_split(q, &bio, q->bio_split);
- if (mddev == NULL || mddev->pers == NULL
- || !mddev->ready) {
+ if (mddev == NULL || mddev->pers == NULL) {
bio_io_error(bio);
return BLK_QC_T_NONE;
}
@@ -1026,8 +1016,9 @@ static int super_90_load(struct md_rdev *rdev, struct md_rdev *refdev, int minor
* (not needed for Linear and RAID0 as metadata doesn't
* record this size)
*/
- if (rdev->sectors >= (2ULL << 32) && sb->level >= 1)
- rdev->sectors = (2ULL << 32) - 2;
+ if (IS_ENABLED(CONFIG_LBDAF) && (u64)rdev->sectors >= (2ULL << 32) &&
+ sb->level >= 1)
+ rdev->sectors = (sector_t)(2ULL << 32) - 2;
if (rdev->sectors < ((sector_t)sb->size) * 2 && sb->level >= 1)
/* "this cannot possibly happen" ... */
@@ -1199,13 +1190,13 @@ static void super_90_sync(struct mddev *mddev, struct md_rdev *rdev)
memcpy(&sb->set_uuid2, mddev->uuid+8, 4);
memcpy(&sb->set_uuid3, mddev->uuid+12,4);
- sb->ctime = mddev->ctime;
+ sb->ctime = clamp_t(time64_t, mddev->ctime, 0, U32_MAX);
sb->level = mddev->level;
sb->size = mddev->dev_sectors / 2;
sb->raid_disks = mddev->raid_disks;
sb->md_minor = mddev->md_minor;
sb->not_persistent = 0;
- sb->utime = mddev->utime;
+ sb->utime = clamp_t(time64_t, mddev->utime, 0, U32_MAX);
sb->state = 0;
sb->events_hi = (mddev->events>>32);
sb->events_lo = (u32)mddev->events;
@@ -1320,8 +1311,9 @@ super_90_rdev_size_change(struct md_rdev *rdev, sector_t num_sectors)
/* Limit to 4TB as metadata cannot record more than that.
* 4TB == 2^32 KB, or 2*2^32 sectors.
*/
- if (num_sectors >= (2ULL << 32) && rdev->mddev->level >= 1)
- num_sectors = (2ULL << 32) - 2;
+ if (IS_ENABLED(CONFIG_LBDAF) && (u64)num_sectors >= (2ULL << 32) &&
+ rdev->mddev->level >= 1)
+ num_sectors = (sector_t)(2ULL << 32) - 2;
md_super_write(rdev->mddev, rdev, rdev->sb_start, rdev->sb_size,
rdev->sb_page);
md_super_wait(rdev->mddev);
@@ -1542,8 +1534,8 @@ static int super_1_validate(struct mddev *mddev, struct md_rdev *rdev)
mddev->patch_version = 0;
mddev->external = 0;
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->ctime = le64_to_cpu(sb->ctime);
+ mddev->utime = le64_to_cpu(sb->utime);
mddev->level = le32_to_cpu(sb->level);
mddev->clevel[0] = 0;
mddev->layout = le32_to_cpu(sb->layout);
@@ -1602,6 +1594,11 @@ static int super_1_validate(struct mddev *mddev, struct md_rdev *rdev)
mddev->new_chunk_sectors = mddev->chunk_sectors;
}
+ if (le32_to_cpu(sb->feature_map) & MD_FEATURE_JOURNAL) {
+ set_bit(MD_HAS_JOURNAL, &mddev->flags);
+ if (mddev->recovery_cp == MaxSector)
+ set_bit(MD_JOURNAL_CLEAN, &mddev->flags);
+ }
} else if (mddev->pers == NULL) {
/* Insist of good event counter while assembling, except for
* spares (which don't need an event count) */
@@ -1648,8 +1645,6 @@ static int super_1_validate(struct mddev *mddev, struct md_rdev *rdev)
}
set_bit(Journal, &rdev->flags);
rdev->journal_tail = le64_to_cpu(sb->journal_tail);
- if (mddev->recovery_cp == MaxSector)
- set_bit(MD_JOURNAL_CLEAN, &mddev->flags);
rdev->raid_disk = 0;
break;
default:
@@ -1669,8 +1664,6 @@ static int super_1_validate(struct mddev *mddev, struct md_rdev *rdev)
set_bit(WriteMostly, &rdev->flags);
if (le32_to_cpu(sb->feature_map) & MD_FEATURE_REPLACEMENT)
set_bit(Replacement, &rdev->flags);
- if (le32_to_cpu(sb->feature_map) & MD_FEATURE_JOURNAL)
- set_bit(MD_HAS_JOURNAL, &mddev->flags);
} else /* MULTIPATH are always insync */
set_bit(In_sync, &rdev->flags);
@@ -2014,28 +2007,32 @@ int md_integrity_register(struct mddev *mddev)
}
EXPORT_SYMBOL(md_integrity_register);
-/* Disable data integrity if non-capable/non-matching disk is being added */
-void md_integrity_add_rdev(struct md_rdev *rdev, struct mddev *mddev)
+/*
+ * Attempt to add an rdev, but only if it is consistent with the current
+ * integrity profile
+ */
+int md_integrity_add_rdev(struct md_rdev *rdev, struct mddev *mddev)
{
struct blk_integrity *bi_rdev;
struct blk_integrity *bi_mddev;
+ char name[BDEVNAME_SIZE];
if (!mddev->gendisk)
- return;
+ return 0;
bi_rdev = bdev_get_integrity(rdev->bdev);
bi_mddev = blk_get_integrity(mddev->gendisk);
if (!bi_mddev) /* nothing to do */
- return;
- if (rdev->raid_disk < 0) /* skip spares */
- return;
- if (bi_rdev && blk_integrity_compare(mddev->gendisk,
- rdev->bdev->bd_disk) >= 0)
- return;
- WARN_ON_ONCE(!mddev->suspended);
- printk(KERN_NOTICE "disabling data integrity on %s\n", mdname(mddev));
- blk_integrity_unregister(mddev->gendisk);
+ return 0;
+
+ if (blk_integrity_compare(mddev->gendisk, rdev->bdev->bd_disk) != 0) {
+ printk(KERN_NOTICE "%s: incompatible integrity profile for %s\n",
+ mdname(mddev), bdevname(rdev->bdev, name));
+ return -ENXIO;
+ }
+
+ return 0;
}
EXPORT_SYMBOL(md_integrity_add_rdev);
@@ -2050,8 +2047,9 @@ static int bind_rdev_to_array(struct md_rdev *rdev, struct mddev *mddev)
return -EEXIST;
/* make sure rdev->sectors exceeds mddev->dev_sectors */
- if (rdev->sectors && (mddev->dev_sectors == 0 ||
- rdev->sectors < mddev->dev_sectors)) {
+ if (!test_bit(Journal, &rdev->flags) &&
+ rdev->sectors &&
+ (mddev->dev_sectors == 0 || rdev->sectors < mddev->dev_sectors)) {
if (mddev->pers) {
/* Cannot change size, so fail
* If mddev->level <= 0, then we don't care
@@ -2082,7 +2080,8 @@ static int bind_rdev_to_array(struct md_rdev *rdev, struct mddev *mddev)
}
}
rcu_read_unlock();
- if (mddev->max_disks && rdev->desc_nr >= mddev->max_disks) {
+ if (!test_bit(Journal, &rdev->flags) &&
+ mddev->max_disks && rdev->desc_nr >= mddev->max_disks) {
printk(KERN_WARNING "md: %s: array is limited to %d devices\n",
mdname(mddev), mddev->max_disks);
return -EBUSY;
@@ -2331,7 +2330,7 @@ repeat:
spin_lock(&mddev->lock);
- mddev->utime = get_seconds();
+ mddev->utime = ktime_get_real_seconds();
if (test_and_clear_bit(MD_CHANGE_DEVS, &mddev->flags))
force_change = 1;
@@ -2457,15 +2456,20 @@ static int add_bound_rdev(struct md_rdev *rdev)
{
struct mddev *mddev = rdev->mddev;
int err = 0;
+ bool add_journal = test_bit(Journal, &rdev->flags);
- if (!mddev->pers->hot_remove_disk) {
+ if (!mddev->pers->hot_remove_disk || add_journal) {
/* 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);
+ if (add_journal)
+ mddev_suspend(mddev);
err = mddev->pers->hot_add_disk(mddev, rdev);
+ if (add_journal)
+ mddev_resume(mddev);
if (err) {
unbind_rdev_from_array(rdev);
export_rdev(rdev);
@@ -5299,7 +5303,6 @@ int md_run(struct mddev *mddev)
smp_wmb();
spin_lock(&mddev->lock);
mddev->pers = pers;
- mddev->ready = 1;
spin_unlock(&mddev->lock);
rdev_for_each(rdev, mddev)
if (rdev->raid_disk >= 0)
@@ -5499,7 +5502,6 @@ static void __md_stop(struct mddev *mddev)
/* Ensure ->event_work is done */
flush_workqueue(md_misc_wq);
spin_lock(&mddev->lock);
- mddev->ready = 0;
mddev->pers = NULL;
spin_unlock(&mddev->lock);
pers->free(mddev, mddev->private);
@@ -5837,7 +5839,7 @@ static int get_array_info(struct mddev *mddev, void __user *arg)
info.major_version = mddev->major_version;
info.minor_version = mddev->minor_version;
info.patch_version = MD_PATCHLEVEL_VERSION;
- info.ctime = mddev->ctime;
+ info.ctime = clamp_t(time64_t, mddev->ctime, 0, U32_MAX);
info.level = mddev->level;
info.size = mddev->dev_sectors / 2;
if (info.size != mddev->dev_sectors / 2) /* overflow */
@@ -5847,7 +5849,7 @@ static int get_array_info(struct mddev *mddev, void __user *arg)
info.md_minor = mddev->md_minor;
info.not_persistent= !mddev->persistent;
- info.utime = mddev->utime;
+ info.utime = clamp_t(time64_t, mddev->utime, 0, U32_MAX);
info.state = 0;
if (mddev->in_sync)
info.state = (1<<MD_SB_CLEAN);
@@ -6038,8 +6040,23 @@ static int add_new_disk(struct mddev *mddev, mdu_disk_info_t *info)
else
clear_bit(WriteMostly, &rdev->flags);
- if (info->state & (1<<MD_DISK_JOURNAL))
+ if (info->state & (1<<MD_DISK_JOURNAL)) {
+ struct md_rdev *rdev2;
+ bool has_journal = false;
+
+ /* make sure no existing journal disk */
+ rdev_for_each(rdev2, mddev) {
+ if (test_bit(Journal, &rdev2->flags)) {
+ has_journal = true;
+ break;
+ }
+ }
+ if (has_journal) {
+ export_rdev(rdev);
+ return -EBUSY;
+ }
set_bit(Journal, &rdev->flags);
+ }
/*
* check whether the device shows up in other nodes
*/
@@ -6130,15 +6147,11 @@ static int hot_remove_disk(struct mddev *mddev, dev_t dev)
{
char b[BDEVNAME_SIZE];
struct md_rdev *rdev;
- int ret = -1;
rdev = find_rdev(mddev, dev);
if (!rdev)
return -ENXIO;
- if (mddev_is_clustered(mddev))
- ret = md_cluster_ops->metadata_update_start(mddev);
-
if (rdev->raid_disk < 0)
goto kick_rdev;
@@ -6149,7 +6162,7 @@ static int hot_remove_disk(struct mddev *mddev, dev_t dev)
goto busy;
kick_rdev:
- if (mddev_is_clustered(mddev) && ret == 0)
+ if (mddev_is_clustered(mddev))
md_cluster_ops->remove_disk(mddev, rdev);
md_kick_rdev_from_array(rdev);
@@ -6158,9 +6171,6 @@ kick_rdev:
return 0;
busy:
- if (mddev_is_clustered(mddev) && ret == 0)
- 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;
@@ -6354,13 +6364,13 @@ static int set_array_info(struct mddev *mddev, mdu_array_info_t *info)
/* ensure mddev_put doesn't delete this now that there
* is some minimal configuration.
*/
- mddev->ctime = get_seconds();
+ mddev->ctime = ktime_get_real_seconds();
return 0;
}
mddev->major_version = MD_MAJOR_VERSION;
mddev->minor_version = MD_MINOR_VERSION;
mddev->patch_version = MD_PATCHLEVEL_VERSION;
- mddev->ctime = get_seconds();
+ mddev->ctime = ktime_get_real_seconds();
mddev->level = info->level;
mddev->clevel[0] = 0;
@@ -6602,6 +6612,19 @@ static int update_array_info(struct mddev *mddev, mdu_array_info_t *info)
rv = -EINVAL;
goto err;
}
+ if (mddev->bitmap_info.nodes) {
+ /* hold PW on all the bitmap lock */
+ if (md_cluster_ops->lock_all_bitmaps(mddev) <= 0) {
+ printk("md: can't change bitmap to none since the"
+ " array is in use by more than one node\n");
+ rv = -EPERM;
+ md_cluster_ops->unlock_all_bitmaps(mddev);
+ goto err;
+ }
+
+ mddev->bitmap_info.nodes = 0;
+ md_cluster_ops->leave(mddev);
+ }
mddev->pers->quiesce(mddev, 1);
bitmap_destroy(mddev);
mddev->pers->quiesce(mddev, 0);
@@ -7180,7 +7203,7 @@ void md_error(struct mddev *mddev, struct md_rdev *rdev)
md_wakeup_thread(mddev->thread);
if (mddev->event_work.func)
queue_work(md_misc_wq, &mddev->event_work);
- md_new_event_inintr(mddev);
+ md_new_event(mddev);
}
EXPORT_SYMBOL(md_error);
@@ -7704,7 +7727,7 @@ EXPORT_SYMBOL(md_write_end);
* attempting a GFP_KERNEL allocation while holding the mddev lock.
* Must be called with mddev_lock held.
*
- * In the ->external case MD_CHANGE_CLEAN can not be cleared until mddev->lock
+ * In the ->external case MD_CHANGE_PENDING can not be cleared until mddev->lock
* is dropped, so return -EAGAIN after notifying userspace.
*/
int md_allow_write(struct mddev *mddev)
@@ -8169,19 +8192,20 @@ static int remove_and_add_spares(struct mddev *mddev,
continue;
if (test_bit(Faulty, &rdev->flags))
continue;
- if (test_bit(Journal, &rdev->flags))
- continue;
- if (mddev->ro &&
- ! (rdev->saved_raid_disk >= 0 &&
- !test_bit(Bitmap_sync, &rdev->flags)))
- continue;
+ if (!test_bit(Journal, &rdev->flags)) {
+ if (mddev->ro &&
+ ! (rdev->saved_raid_disk >= 0 &&
+ !test_bit(Bitmap_sync, &rdev->flags)))
+ continue;
- rdev->recovery_offset = 0;
+ rdev->recovery_offset = 0;
+ }
if (mddev->pers->
hot_add_disk(mddev, rdev) == 0) {
if (sysfs_link_rdev(mddev, rdev))
/* failure here is OK */;
- spares++;
+ if (!test_bit(Journal, &rdev->flags))
+ spares++;
md_new_event(mddev);
set_bit(MD_CHANGE_DEVS, &mddev->flags);
}
@@ -8276,6 +8300,7 @@ void md_check_recovery(struct mddev *mddev)
(mddev->flags & MD_UPDATE_SB_FLAGS & ~ (1<<MD_CHANGE_PENDING)) ||
test_bit(MD_RECOVERY_NEEDED, &mddev->recovery) ||
test_bit(MD_RECOVERY_DONE, &mddev->recovery) ||
+ test_bit(MD_RELOAD_SB, &mddev->flags) ||
(mddev->external == 0 && mddev->safemode == 1) ||
(mddev->safemode == 2 && ! atomic_read(&mddev->writes_pending)
&& !mddev->in_sync && mddev->recovery_cp == MaxSector)
@@ -8314,6 +8339,21 @@ void md_check_recovery(struct mddev *mddev)
goto unlock;
}
+ if (mddev_is_clustered(mddev)) {
+ struct md_rdev *rdev;
+ /* kick the device if another node issued a
+ * remove disk.
+ */
+ rdev_for_each(rdev, mddev) {
+ if (test_and_clear_bit(ClusterRemove, &rdev->flags) &&
+ rdev->raid_disk < 0)
+ md_kick_rdev_from_array(rdev);
+ }
+
+ if (test_and_clear_bit(MD_RELOAD_SB, &mddev->flags))
+ md_reload_sb(mddev, mddev->good_device_nr);
+ }
+
if (!mddev->external) {
int did_change = 0;
spin_lock(&mddev->lock);
@@ -8635,7 +8675,6 @@ static void check_sb_changes(struct mddev *mddev, struct md_rdev *rdev)
ret = remove_and_add_spares(mddev, rdev2);
pr_info("Activated spare: %s\n",
bdevname(rdev2->bdev,b));
- continue;
}
/* device faulty
* We just want to do the minimum to mark the disk
diff --git a/drivers/md/md.h b/drivers/md/md.h
index 75b9aaacb03f..b5c4be73e6e4 100644
--- a/drivers/md/md.h
+++ b/drivers/md/md.h
@@ -162,6 +162,7 @@ enum flag_bits {
* Usually, this device should be faster
* than other devices in the array
*/
+ ClusterRemove,
};
static inline int is_badblock(struct md_rdev *rdev, sector_t s, int sectors,
@@ -200,6 +201,9 @@ struct mddev {
*/
#define MD_JOURNAL_CLEAN 5 /* A raid with journal is already clean */
#define MD_HAS_JOURNAL 6 /* The raid array has journal feature set */
+#define MD_RELOAD_SB 7 /* Reload the superblock because another node
+ * updated it.
+ */
int suspended;
atomic_t active_io;
@@ -208,8 +212,6 @@ struct mddev {
* are happening, so run/
* takeover/stop are not safe
*/
- int ready; /* See when safe to pass
- * IO requests down */
struct gendisk *gendisk;
struct kobject kobj;
@@ -226,7 +228,7 @@ struct mddev {
* managed externally */
char metadata_type[17]; /* externally set*/
int chunk_sectors;
- time_t ctime, utime;
+ time64_t ctime, utime;
int level, layout;
char clevel[16];
int raid_disks;
@@ -430,6 +432,7 @@ struct mddev {
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;
+ unsigned int good_device_nr; /* good device num within cluster raid */
};
static inline int __must_check mddev_lock(struct mddev *mddev)
@@ -623,7 +626,7 @@ extern void md_wait_for_blocked_rdev(struct md_rdev *rdev, struct mddev *mddev);
extern void md_set_array_sectors(struct mddev *mddev, sector_t array_sectors);
extern int md_check_no_bitmap(struct mddev *mddev);
extern int md_integrity_register(struct mddev *mddev);
-extern void md_integrity_add_rdev(struct md_rdev *rdev, struct mddev *mddev);
+extern int md_integrity_add_rdev(struct md_rdev *rdev, struct mddev *mddev);
extern int strict_strtoul_scaled(const char *cp, unsigned long *res, int scale);
extern void mddev_init(struct mddev *mddev);
diff --git a/drivers/md/multipath.c b/drivers/md/multipath.c
index 7331a80d89f1..0a72ab6e6c20 100644
--- a/drivers/md/multipath.c
+++ b/drivers/md/multipath.c
@@ -257,6 +257,9 @@ static int multipath_add_disk(struct mddev *mddev, struct md_rdev *rdev)
disk_stack_limits(mddev->gendisk, rdev->bdev,
rdev->data_offset << 9);
+ err = md_integrity_add_rdev(rdev, mddev);
+ if (err)
+ break;
spin_lock_irq(&conf->device_lock);
mddev->degraded--;
rdev->raid_disk = path;
@@ -264,9 +267,6 @@ static int multipath_add_disk(struct mddev *mddev, struct md_rdev *rdev)
spin_unlock_irq(&conf->device_lock);
rcu_assign_pointer(p->rdev, rdev);
err = 0;
- mddev_suspend(mddev);
- md_integrity_add_rdev(rdev, mddev);
- mddev_resume(mddev);
break;
}
diff --git a/drivers/md/raid0.c b/drivers/md/raid0.c
index f8e5db0cb5aa..2ea12c6bf659 100644
--- a/drivers/md/raid0.c
+++ b/drivers/md/raid0.c
@@ -549,13 +549,13 @@ static void *raid0_takeover_raid10(struct mddev *mddev)
* - all mirrors must be already degraded
*/
if (mddev->layout != ((1 << 8) + 2)) {
- printk(KERN_ERR "md/raid0:%s:: Raid0 cannot takover layout: 0x%x\n",
+ printk(KERN_ERR "md/raid0:%s:: Raid0 cannot takeover layout: 0x%x\n",
mdname(mddev),
mddev->layout);
return ERR_PTR(-EINVAL);
}
if (mddev->raid_disks & 1) {
- printk(KERN_ERR "md/raid0:%s: Raid0 cannot takover Raid10 with odd disk number.\n",
+ printk(KERN_ERR "md/raid0:%s: Raid0 cannot takeover Raid10 with odd disk number.\n",
mdname(mddev));
return ERR_PTR(-EINVAL);
}
diff --git a/drivers/md/raid1.c b/drivers/md/raid1.c
index e2169ff6e0f0..4e3843f7d245 100644
--- a/drivers/md/raid1.c
+++ b/drivers/md/raid1.c
@@ -1044,7 +1044,7 @@ static void raid1_unplug(struct blk_plug_cb *cb, bool from_schedule)
kfree(plug);
}
-static void make_request(struct mddev *mddev, struct bio * bio)
+static void raid1_make_request(struct mddev *mddev, struct bio * bio)
{
struct r1conf *conf = mddev->private;
struct raid1_info *mirror;
@@ -1422,7 +1422,7 @@ read_again:
wake_up(&conf->wait_barrier);
}
-static void status(struct seq_file *seq, struct mddev *mddev)
+static void raid1_status(struct seq_file *seq, struct mddev *mddev)
{
struct r1conf *conf = mddev->private;
int i;
@@ -1439,7 +1439,7 @@ static void status(struct seq_file *seq, struct mddev *mddev)
seq_printf(seq, "]");
}
-static void error(struct mddev *mddev, struct md_rdev *rdev)
+static void raid1_error(struct mddev *mddev, struct md_rdev *rdev)
{
char b[BDEVNAME_SIZE];
struct r1conf *conf = mddev->private;
@@ -1589,6 +1589,9 @@ static int raid1_add_disk(struct mddev *mddev, struct md_rdev *rdev)
if (mddev->recovery_disabled == conf->recovery_disabled)
return -EBUSY;
+ if (md_integrity_add_rdev(rdev, mddev))
+ return -ENXIO;
+
if (rdev->raid_disk >= 0)
first = last = rdev->raid_disk;
@@ -1632,9 +1635,6 @@ static int raid1_add_disk(struct mddev *mddev, struct md_rdev *rdev)
break;
}
}
- mddev_suspend(mddev);
- md_integrity_add_rdev(rdev, mddev);
- mddev_resume(mddev);
if (mddev->queue && blk_queue_discard(bdev_get_queue(rdev->bdev)))
queue_flag_set_unlocked(QUEUE_FLAG_DISCARD, mddev->queue);
print_conf(conf);
@@ -2472,7 +2472,8 @@ static int init_resync(struct r1conf *conf)
* that can be installed to exclude normal IO requests.
*/
-static sector_t sync_request(struct mddev *mddev, sector_t sector_nr, int *skipped)
+static sector_t raid1_sync_request(struct mddev *mddev, sector_t sector_nr,
+ int *skipped)
{
struct r1conf *conf = mddev->private;
struct r1bio *r1_bio;
@@ -2890,7 +2891,7 @@ static struct r1conf *setup_conf(struct mddev *mddev)
}
static void raid1_free(struct mddev *mddev, void *priv);
-static int run(struct mddev *mddev)
+static int raid1_run(struct mddev *mddev)
{
struct r1conf *conf;
int i;
@@ -3170,15 +3171,15 @@ static struct md_personality raid1_personality =
.name = "raid1",
.level = 1,
.owner = THIS_MODULE,
- .make_request = make_request,
- .run = run,
+ .make_request = raid1_make_request,
+ .run = raid1_run,
.free = raid1_free,
- .status = status,
- .error_handler = error,
+ .status = raid1_status,
+ .error_handler = raid1_error,
.hot_add_disk = raid1_add_disk,
.hot_remove_disk= raid1_remove_disk,
.spare_active = raid1_spare_active,
- .sync_request = sync_request,
+ .sync_request = raid1_sync_request,
.resize = raid1_resize,
.size = raid1_size,
.check_reshape = raid1_reshape,
diff --git a/drivers/md/raid10.c b/drivers/md/raid10.c
index 84e597e1c489..1c1447dd3417 100644
--- a/drivers/md/raid10.c
+++ b/drivers/md/raid10.c
@@ -1442,7 +1442,7 @@ retry_write:
one_write_done(r10_bio);
}
-static void make_request(struct mddev *mddev, struct bio *bio)
+static void raid10_make_request(struct mddev *mddev, struct bio *bio)
{
struct r10conf *conf = mddev->private;
sector_t chunk_mask = (conf->geo.chunk_mask & conf->prev.chunk_mask);
@@ -1484,7 +1484,7 @@ static void make_request(struct mddev *mddev, struct bio *bio)
wake_up(&conf->wait_barrier);
}
-static void status(struct seq_file *seq, struct mddev *mddev)
+static void raid10_status(struct seq_file *seq, struct mddev *mddev)
{
struct r10conf *conf = mddev->private;
int i;
@@ -1562,7 +1562,7 @@ static int enough(struct r10conf *conf, int ignore)
_enough(conf, 1, ignore);
}
-static void error(struct mddev *mddev, struct md_rdev *rdev)
+static void raid10_error(struct mddev *mddev, struct md_rdev *rdev)
{
char b[BDEVNAME_SIZE];
struct r10conf *conf = mddev->private;
@@ -1698,6 +1698,9 @@ static int raid10_add_disk(struct mddev *mddev, struct md_rdev *rdev)
if (rdev->saved_raid_disk < 0 && !_enough(conf, 1, -1))
return -EINVAL;
+ if (md_integrity_add_rdev(rdev, mddev))
+ return -ENXIO;
+
if (rdev->raid_disk >= 0)
first = last = rdev->raid_disk;
@@ -1739,9 +1742,6 @@ static int raid10_add_disk(struct mddev *mddev, struct md_rdev *rdev)
rcu_assign_pointer(p->rdev, rdev);
break;
}
- mddev_suspend(mddev);
- md_integrity_add_rdev(rdev, mddev);
- mddev_resume(mddev);
if (mddev->queue && blk_queue_discard(bdev_get_queue(rdev->bdev)))
queue_flag_set_unlocked(QUEUE_FLAG_DISCARD, mddev->queue);
@@ -2802,7 +2802,7 @@ static int init_resync(struct r10conf *conf)
*
*/
-static sector_t sync_request(struct mddev *mddev, sector_t sector_nr,
+static sector_t raid10_sync_request(struct mddev *mddev, sector_t sector_nr,
int *skipped)
{
struct r10conf *conf = mddev->private;
@@ -3523,7 +3523,7 @@ static struct r10conf *setup_conf(struct mddev *mddev)
return ERR_PTR(err);
}
-static int run(struct mddev *mddev)
+static int raid10_run(struct mddev *mddev)
{
struct r10conf *conf;
int i, disk_idx, chunk_size;
@@ -4617,15 +4617,15 @@ static struct md_personality raid10_personality =
.name = "raid10",
.level = 10,
.owner = THIS_MODULE,
- .make_request = make_request,
- .run = run,
+ .make_request = raid10_make_request,
+ .run = raid10_run,
.free = raid10_free,
- .status = status,
- .error_handler = error,
+ .status = raid10_status,
+ .error_handler = raid10_error,
.hot_add_disk = raid10_add_disk,
.hot_remove_disk= raid10_remove_disk,
.spare_active = raid10_spare_active,
- .sync_request = sync_request,
+ .sync_request = raid10_sync_request,
.quiesce = raid10_quiesce,
.size = raid10_size,
.resize = raid10_resize,
diff --git a/drivers/md/raid5-cache.c b/drivers/md/raid5-cache.c
index b887e04d7e5c..9531f5f05b93 100644
--- a/drivers/md/raid5-cache.c
+++ b/drivers/md/raid5-cache.c
@@ -34,6 +34,12 @@
#define RECLAIM_MAX_FREE_SPACE (10 * 1024 * 1024 * 2) /* sector */
#define RECLAIM_MAX_FREE_SPACE_SHIFT (2)
+/*
+ * We only need 2 bios per I/O unit to make progress, but ensure we
+ * have a few more available to not get too tight.
+ */
+#define R5L_POOL_SIZE 4
+
struct r5l_log {
struct md_rdev *rdev;
@@ -69,7 +75,12 @@ struct r5l_log {
struct list_head finished_ios; /* io_units which settle down in log disk */
struct bio flush_bio;
+ struct list_head no_mem_stripes; /* pending stripes, -ENOMEM */
+
struct kmem_cache *io_kc;
+ mempool_t *io_pool;
+ struct bio_set *bs;
+ mempool_t *meta_pool;
struct md_thread *reclaim_thread;
unsigned long reclaim_target; /* number of space that need to be
@@ -150,27 +161,6 @@ static bool r5l_has_free_space(struct r5l_log *log, sector_t size)
return log->device_size > used_size + size;
}
-static void r5l_free_io_unit(struct r5l_log *log, struct r5l_io_unit *io)
-{
- __free_page(io->meta_page);
- kmem_cache_free(log->io_kc, io);
-}
-
-static void r5l_move_io_unit_list(struct list_head *from, struct list_head *to,
- enum r5l_io_unit_state state)
-{
- struct r5l_io_unit *io;
-
- while (!list_empty(from)) {
- io = list_first_entry(from, struct r5l_io_unit, log_sibling);
- /* don't change list order */
- if (io->state >= state)
- list_move_tail(&io->log_sibling, to);
- else
- break;
- }
-}
-
static void __r5l_set_io_unit_state(struct r5l_io_unit *io,
enum r5l_io_unit_state state)
{
@@ -206,6 +196,20 @@ static void r5l_log_run_stripes(struct r5l_log *log)
}
}
+static void r5l_move_to_end_ios(struct r5l_log *log)
+{
+ struct r5l_io_unit *io, *next;
+
+ assert_spin_locked(&log->io_list_lock);
+
+ list_for_each_entry_safe(io, next, &log->running_ios, log_sibling) {
+ /* don't change list order */
+ if (io->state < IO_UNIT_IO_END)
+ break;
+ list_move_tail(&io->log_sibling, &log->io_end_ios);
+ }
+}
+
static void r5l_log_endio(struct bio *bio)
{
struct r5l_io_unit *io = bio->bi_private;
@@ -216,12 +220,12 @@ static void r5l_log_endio(struct bio *bio)
md_error(log->rdev->mddev, log->rdev);
bio_put(bio);
+ mempool_free(io->meta_page, log->meta_pool);
spin_lock_irqsave(&log->io_list_lock, flags);
__r5l_set_io_unit_state(io, IO_UNIT_IO_END);
if (log->need_cache_flush)
- r5l_move_io_unit_list(&log->running_ios, &log->io_end_ios,
- IO_UNIT_IO_END);
+ r5l_move_to_end_ios(log);
else
r5l_log_run_stripes(log);
spin_unlock_irqrestore(&log->io_list_lock, flags);
@@ -255,7 +259,7 @@ static void r5l_submit_current_io(struct r5l_log *log)
static struct bio *r5l_bio_alloc(struct r5l_log *log)
{
- struct bio *bio = bio_kmalloc(GFP_NOIO | __GFP_NOFAIL, BIO_MAX_PAGES);
+ struct bio *bio = bio_alloc_bioset(GFP_NOIO, BIO_MAX_PAGES, log->bs);
bio->bi_rw = WRITE;
bio->bi_bdev = log->rdev->bdev;
@@ -286,15 +290,19 @@ static struct r5l_io_unit *r5l_new_meta(struct r5l_log *log)
struct r5l_io_unit *io;
struct r5l_meta_block *block;
- /* We can't handle memory allocate failure so far */
- io = kmem_cache_zalloc(log->io_kc, GFP_NOIO | __GFP_NOFAIL);
+ io = mempool_alloc(log->io_pool, GFP_ATOMIC);
+ if (!io)
+ return NULL;
+ memset(io, 0, sizeof(*io));
+
io->log = log;
INIT_LIST_HEAD(&io->log_sibling);
INIT_LIST_HEAD(&io->stripe_list);
io->state = IO_UNIT_RUNNING;
- io->meta_page = alloc_page(GFP_NOIO | __GFP_NOFAIL | __GFP_ZERO);
+ io->meta_page = mempool_alloc(log->meta_pool, GFP_NOIO);
block = page_address(io->meta_page);
+ clear_page(block);
block->magic = cpu_to_le32(R5LOG_MAGIC);
block->version = R5LOG_VERSION;
block->seq = cpu_to_le64(log->seq);
@@ -324,8 +332,12 @@ static int r5l_get_meta(struct r5l_log *log, unsigned int payload_size)
log->current_io->meta_offset + payload_size > PAGE_SIZE)
r5l_submit_current_io(log);
- if (!log->current_io)
+ if (!log->current_io) {
log->current_io = r5l_new_meta(log);
+ if (!log->current_io)
+ return -ENOMEM;
+ }
+
return 0;
}
@@ -370,11 +382,12 @@ static void r5l_append_payload_page(struct r5l_log *log, struct page *page)
r5_reserve_log_entry(log, io);
}
-static void r5l_log_stripe(struct r5l_log *log, struct stripe_head *sh,
+static int r5l_log_stripe(struct r5l_log *log, struct stripe_head *sh,
int data_pages, int parity_pages)
{
int i;
int meta_size;
+ int ret;
struct r5l_io_unit *io;
meta_size =
@@ -383,7 +396,10 @@ static void r5l_log_stripe(struct r5l_log *log, struct stripe_head *sh,
sizeof(struct r5l_payload_data_parity) +
sizeof(__le32) * parity_pages;
- r5l_get_meta(log, meta_size);
+ ret = r5l_get_meta(log, meta_size);
+ if (ret)
+ return ret;
+
io = log->current_io;
for (i = 0; i < sh->disks; i++) {
@@ -413,6 +429,8 @@ static void r5l_log_stripe(struct r5l_log *log, struct stripe_head *sh,
list_add_tail(&sh->log_list, &io->stripe_list);
atomic_inc(&io->pending_stripe);
sh->log_io = io;
+
+ return 0;
}
static void r5l_wake_reclaim(struct r5l_log *log, sector_t space);
@@ -427,6 +445,7 @@ int r5l_write_stripe(struct r5l_log *log, struct stripe_head *sh)
int meta_size;
int reserve;
int i;
+ int ret = 0;
if (!log)
return -EAGAIN;
@@ -475,17 +494,22 @@ int r5l_write_stripe(struct r5l_log *log, struct stripe_head *sh)
mutex_lock(&log->io_mutex);
/* meta + data */
reserve = (1 + write_disks) << (PAGE_SHIFT - 9);
- if (r5l_has_free_space(log, reserve))
- r5l_log_stripe(log, sh, data_pages, parity_pages);
- else {
+ if (!r5l_has_free_space(log, reserve)) {
spin_lock(&log->no_space_stripes_lock);
list_add_tail(&sh->log_list, &log->no_space_stripes);
spin_unlock(&log->no_space_stripes_lock);
r5l_wake_reclaim(log, reserve);
+ } else {
+ ret = r5l_log_stripe(log, sh, data_pages, parity_pages);
+ if (ret) {
+ spin_lock_irq(&log->io_list_lock);
+ list_add_tail(&sh->log_list, &log->no_mem_stripes);
+ spin_unlock_irq(&log->io_list_lock);
+ }
}
- mutex_unlock(&log->io_mutex);
+ mutex_unlock(&log->io_mutex);
return 0;
}
@@ -538,6 +562,21 @@ static sector_t r5l_reclaimable_space(struct r5l_log *log)
log->next_checkpoint);
}
+static void r5l_run_no_mem_stripe(struct r5l_log *log)
+{
+ struct stripe_head *sh;
+
+ assert_spin_locked(&log->io_list_lock);
+
+ if (!list_empty(&log->no_mem_stripes)) {
+ sh = list_first_entry(&log->no_mem_stripes,
+ struct stripe_head, log_list);
+ list_del_init(&sh->log_list);
+ set_bit(STRIPE_HANDLE, &sh->state);
+ raid5_release_stripe(sh);
+ }
+}
+
static bool r5l_complete_finished_ios(struct r5l_log *log)
{
struct r5l_io_unit *io, *next;
@@ -554,7 +593,8 @@ static bool r5l_complete_finished_ios(struct r5l_log *log)
log->next_cp_seq = io->seq;
list_del(&io->log_sibling);
- r5l_free_io_unit(log, io);
+ mempool_free(io, log->io_pool);
+ r5l_run_no_mem_stripe(log);
found = true;
}
@@ -787,6 +827,13 @@ void r5l_quiesce(struct r5l_log *log, int state)
return;
if (state == 0) {
log->in_teardown = 0;
+ /*
+ * This is a special case for hotadd. In suspend, the array has
+ * no journal. In resume, journal is initialized as well as the
+ * reclaim thread.
+ */
+ if (log->reclaim_thread)
+ return;
log->reclaim_thread = md_register_thread(r5l_reclaim_thread,
log->rdev->mddev, "reclaim");
} else if (state == 1) {
@@ -806,10 +853,18 @@ void r5l_quiesce(struct r5l_log *log, int state)
bool r5l_log_disk_error(struct r5conf *conf)
{
+ struct r5l_log *log;
+ bool ret;
/* don't allow write if journal disk is missing */
- if (!conf->log)
- return test_bit(MD_HAS_JOURNAL, &conf->mddev->flags);
- return test_bit(Faulty, &conf->log->rdev->flags);
+ rcu_read_lock();
+ log = rcu_dereference(conf->log);
+
+ if (!log)
+ ret = test_bit(MD_HAS_JOURNAL, &conf->mddev->flags);
+ else
+ ret = test_bit(Faulty, &log->rdev->flags);
+ rcu_read_unlock();
+ return ret;
}
struct r5l_recovery_ctx {
@@ -1160,23 +1215,45 @@ int r5l_init_log(struct r5conf *conf, struct md_rdev *rdev)
if (!log->io_kc)
goto io_kc;
+ log->io_pool = mempool_create_slab_pool(R5L_POOL_SIZE, log->io_kc);
+ if (!log->io_pool)
+ goto io_pool;
+
+ log->bs = bioset_create(R5L_POOL_SIZE, 0);
+ if (!log->bs)
+ goto io_bs;
+
+ log->meta_pool = mempool_create_page_pool(R5L_POOL_SIZE, 0);
+ if (!log->meta_pool)
+ goto out_mempool;
+
log->reclaim_thread = md_register_thread(r5l_reclaim_thread,
log->rdev->mddev, "reclaim");
if (!log->reclaim_thread)
goto reclaim_thread;
init_waitqueue_head(&log->iounit_wait);
+ INIT_LIST_HEAD(&log->no_mem_stripes);
+
INIT_LIST_HEAD(&log->no_space_stripes);
spin_lock_init(&log->no_space_stripes_lock);
if (r5l_load_log(log))
goto error;
- conf->log = log;
+ rcu_assign_pointer(conf->log, log);
+ set_bit(MD_HAS_JOURNAL, &conf->mddev->flags);
return 0;
+
error:
md_unregister_thread(&log->reclaim_thread);
reclaim_thread:
+ mempool_destroy(log->meta_pool);
+out_mempool:
+ bioset_free(log->bs);
+io_bs:
+ mempool_destroy(log->io_pool);
+io_pool:
kmem_cache_destroy(log->io_kc);
io_kc:
kfree(log);
@@ -1186,6 +1263,9 @@ io_kc:
void r5l_exit_log(struct r5l_log *log)
{
md_unregister_thread(&log->reclaim_thread);
+ mempool_destroy(log->meta_pool);
+ bioset_free(log->bs);
+ mempool_destroy(log->io_pool);
kmem_cache_destroy(log->io_kc);
kfree(log);
}
diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c
index 704ef7fcfbf8..b4f02c9959f2 100644
--- a/drivers/md/raid5.c
+++ b/drivers/md/raid5.c
@@ -772,8 +772,6 @@ static void stripe_add_to_batch_list(struct r5conf *conf, struct stripe_head *sh
int hash;
int dd_idx;
- if (!stripe_can_batch(sh))
- return;
/* Don't cross chunks, so stripe pd_idx/qd_idx is the same */
tmp_sec = sh->sector;
if (!sector_div(tmp_sec, conf->chunk_sectors))
@@ -2498,7 +2496,7 @@ static void raid5_build_block(struct stripe_head *sh, int i, int previous)
dev->sector = raid5_compute_blocknr(sh, i, previous);
}
-static void error(struct mddev *mddev, struct md_rdev *rdev)
+static void raid5_error(struct mddev *mddev, struct md_rdev *rdev)
{
char b[BDEVNAME_SIZE];
struct r5conf *conf = mddev->private;
@@ -2960,7 +2958,7 @@ static int add_stripe_bio(struct stripe_head *sh, struct bio *bi, int dd_idx,
* If several bio share a stripe. The bio bi_phys_segments acts as a
* reference count to avoid race. The reference count should already be
* increased before this function is called (for example, in
- * make_request()), so other bio sharing this stripe will not free the
+ * raid5_make_request()), so other bio sharing this stripe will not free the
* stripe. If a stripe is owned by one stripe, the stripe lock will
* protect it.
*/
@@ -5137,7 +5135,7 @@ static void make_discard_request(struct mddev *mddev, struct bio *bi)
}
}
-static void make_request(struct mddev *mddev, struct bio * bi)
+static void raid5_make_request(struct mddev *mddev, struct bio * bi)
{
struct r5conf *conf = mddev->private;
int dd_idx;
@@ -5227,7 +5225,7 @@ static void make_request(struct mddev *mddev, struct bio * bi)
new_sector = raid5_compute_sector(conf, logical_sector,
previous,
&dd_idx, NULL);
- pr_debug("raid456: make_request, sector %llu logical %llu\n",
+ pr_debug("raid456: raid5_make_request, sector %llu logical %llu\n",
(unsigned long long)new_sector,
(unsigned long long)logical_sector);
@@ -5577,7 +5575,8 @@ ret:
return retn;
}
-static inline sector_t sync_request(struct mddev *mddev, sector_t sector_nr, int *skipped)
+static inline sector_t raid5_sync_request(struct mddev *mddev, sector_t sector_nr,
+ int *skipped)
{
struct r5conf *conf = mddev->private;
struct stripe_head *sh;
@@ -6676,7 +6675,7 @@ static int only_parity(int raid_disk, int algo, int raid_disks, int max_degraded
return 0;
}
-static int run(struct mddev *mddev)
+static int raid5_run(struct mddev *mddev)
{
struct r5conf *conf;
int working_disks = 0;
@@ -7050,7 +7049,7 @@ static void raid5_free(struct mddev *mddev, void *priv)
mddev->to_remove = &raid5_attrs_group;
}
-static void status(struct seq_file *seq, struct mddev *mddev)
+static void raid5_status(struct seq_file *seq, struct mddev *mddev)
{
struct r5conf *conf = mddev->private;
int i;
@@ -7141,14 +7140,19 @@ static int raid5_remove_disk(struct mddev *mddev, struct md_rdev *rdev)
struct disk_info *p = conf->disks + number;
print_raid5_conf(conf);
- if (test_bit(Journal, &rdev->flags)) {
+ if (test_bit(Journal, &rdev->flags) && conf->log) {
+ struct r5l_log *log;
/*
- * journal disk is not removable, but we need give a chance to
- * update superblock of other disks. Otherwise journal disk
- * will be considered as 'fresh'
+ * we can't wait pending write here, as this is called in
+ * raid5d, wait will deadlock.
*/
- set_bit(MD_CHANGE_DEVS, &mddev->flags);
- return -EINVAL;
+ if (atomic_read(&mddev->writes_pending))
+ return -EBUSY;
+ log = conf->log;
+ conf->log = NULL;
+ synchronize_rcu();
+ r5l_exit_log(log);
+ return 0;
}
if (rdev == p->rdev)
rdevp = &p->rdev;
@@ -7212,8 +7216,21 @@ static int raid5_add_disk(struct mddev *mddev, struct md_rdev *rdev)
int first = 0;
int last = conf->raid_disks - 1;
- if (test_bit(Journal, &rdev->flags))
- return -EINVAL;
+ if (test_bit(Journal, &rdev->flags)) {
+ char b[BDEVNAME_SIZE];
+ if (conf->log)
+ return -EBUSY;
+
+ rdev->raid_disk = 0;
+ /*
+ * The array is in readonly mode if journal is missing, so no
+ * write requests running. We should be safe
+ */
+ r5l_init_log(conf, rdev);
+ printk(KERN_INFO"md/raid:%s: using device %s as journal\n",
+ mdname(mddev), bdevname(rdev->bdev, b));
+ return 0;
+ }
if (mddev->recovery_disabled == conf->recovery_disabled)
return -EBUSY;
@@ -7848,15 +7865,15 @@ static struct md_personality raid6_personality =
.name = "raid6",
.level = 6,
.owner = THIS_MODULE,
- .make_request = make_request,
- .run = run,
+ .make_request = raid5_make_request,
+ .run = raid5_run,
.free = raid5_free,
- .status = status,
- .error_handler = error,
+ .status = raid5_status,
+ .error_handler = raid5_error,
.hot_add_disk = raid5_add_disk,
.hot_remove_disk= raid5_remove_disk,
.spare_active = raid5_spare_active,
- .sync_request = sync_request,
+ .sync_request = raid5_sync_request,
.resize = raid5_resize,
.size = raid5_size,
.check_reshape = raid6_check_reshape,
@@ -7871,15 +7888,15 @@ static struct md_personality raid5_personality =
.name = "raid5",
.level = 5,
.owner = THIS_MODULE,
- .make_request = make_request,
- .run = run,
+ .make_request = raid5_make_request,
+ .run = raid5_run,
.free = raid5_free,
- .status = status,
- .error_handler = error,
+ .status = raid5_status,
+ .error_handler = raid5_error,
.hot_add_disk = raid5_add_disk,
.hot_remove_disk= raid5_remove_disk,
.spare_active = raid5_spare_active,
- .sync_request = sync_request,
+ .sync_request = raid5_sync_request,
.resize = raid5_resize,
.size = raid5_size,
.check_reshape = raid5_check_reshape,
@@ -7895,15 +7912,15 @@ static struct md_personality raid4_personality =
.name = "raid4",
.level = 4,
.owner = THIS_MODULE,
- .make_request = make_request,
- .run = run,
+ .make_request = raid5_make_request,
+ .run = raid5_run,
.free = raid5_free,
- .status = status,
- .error_handler = error,
+ .status = raid5_status,
+ .error_handler = raid5_error,
.hot_add_disk = raid5_add_disk,
.hot_remove_disk= raid5_remove_disk,
.spare_active = raid5_spare_active,
- .sync_request = sync_request,
+ .sync_request = raid5_sync_request,
.resize = raid5_resize,
.size = raid5_size,
.check_reshape = raid5_check_reshape,
generated by cgit v1.2.3 (git 2.39.0) at 2024-11-20 02:25:38 +0300