summaryrefslogtreecommitdiff
path: root/drivers/md
diff options
context:
space:
mode:
Diffstat (limited to 'drivers/md')
-rw-r--r--drivers/md/bitmap.c28
-rw-r--r--drivers/md/bitmap.h5
-rw-r--r--drivers/md/dm-crypt.c170
-rw-r--r--drivers/md/dm-exception-store.c3
-rw-r--r--drivers/md/dm-exception-store.h2
-rw-r--r--drivers/md/dm-ioctl.c61
-rw-r--r--drivers/md/dm-log-userspace-transfer.c10
-rw-r--r--drivers/md/dm-mpath.c1
-rw-r--r--drivers/md/dm-snap.c12
-rw-r--r--drivers/md/dm-stripe.c2
-rw-r--r--drivers/md/dm-table.c20
-rw-r--r--drivers/md/dm-uevent.c9
-rw-r--r--drivers/md/dm.c25
-rw-r--r--drivers/md/linear.c12
-rw-r--r--drivers/md/md.c52
-rw-r--r--drivers/md/md.h1
-rw-r--r--drivers/md/multipath.c20
-rw-r--r--drivers/md/raid0.c13
-rw-r--r--drivers/md/raid1.c34
-rw-r--r--drivers/md/raid10.c48
-rw-r--r--drivers/md/raid5.c65
21 files changed, 390 insertions, 203 deletions
diff --git a/drivers/md/bitmap.c b/drivers/md/bitmap.c
index 60e2b322db11..47831536deb1 100644
--- a/drivers/md/bitmap.c
+++ b/drivers/md/bitmap.c
@@ -1078,23 +1078,31 @@ static bitmap_counter_t *bitmap_get_counter(struct bitmap *bitmap,
* out to disk
*/
-void bitmap_daemon_work(struct bitmap *bitmap)
+void bitmap_daemon_work(mddev_t *mddev)
{
+ struct bitmap *bitmap;
unsigned long j;
unsigned long flags;
struct page *page = NULL, *lastpage = NULL;
int blocks;
void *paddr;
- if (bitmap == NULL)
+ /* Use a mutex to guard daemon_work against
+ * bitmap_destroy.
+ */
+ mutex_lock(&mddev->bitmap_mutex);
+ bitmap = mddev->bitmap;
+ if (bitmap == NULL) {
+ mutex_unlock(&mddev->bitmap_mutex);
return;
+ }
if (time_before(jiffies, bitmap->daemon_lastrun + bitmap->daemon_sleep*HZ))
goto done;
bitmap->daemon_lastrun = jiffies;
if (bitmap->allclean) {
bitmap->mddev->thread->timeout = MAX_SCHEDULE_TIMEOUT;
- return;
+ goto done;
}
bitmap->allclean = 1;
@@ -1203,6 +1211,7 @@ void bitmap_daemon_work(struct bitmap *bitmap)
done:
if (bitmap->allclean == 0)
bitmap->mddev->thread->timeout = bitmap->daemon_sleep * HZ;
+ mutex_unlock(&mddev->bitmap_mutex);
}
static bitmap_counter_t *bitmap_get_counter(struct bitmap *bitmap,
@@ -1308,7 +1317,8 @@ void bitmap_endwrite(struct bitmap *bitmap, sector_t offset, unsigned long secto
{
if (!bitmap) return;
if (behind) {
- atomic_dec(&bitmap->behind_writes);
+ if (atomic_dec_and_test(&bitmap->behind_writes))
+ wake_up(&bitmap->behind_wait);
PRINTK(KERN_DEBUG "dec write-behind count %d/%d\n",
atomic_read(&bitmap->behind_writes), bitmap->max_write_behind);
}
@@ -1541,9 +1551,9 @@ void bitmap_flush(mddev_t *mddev)
*/
sleep = bitmap->daemon_sleep;
bitmap->daemon_sleep = 0;
- bitmap_daemon_work(bitmap);
- bitmap_daemon_work(bitmap);
- bitmap_daemon_work(bitmap);
+ bitmap_daemon_work(mddev);
+ bitmap_daemon_work(mddev);
+ bitmap_daemon_work(mddev);
bitmap->daemon_sleep = sleep;
bitmap_update_sb(bitmap);
}
@@ -1574,6 +1584,7 @@ static void bitmap_free(struct bitmap *bitmap)
kfree(bp);
kfree(bitmap);
}
+
void bitmap_destroy(mddev_t *mddev)
{
struct bitmap *bitmap = mddev->bitmap;
@@ -1581,7 +1592,9 @@ void bitmap_destroy(mddev_t *mddev)
if (!bitmap) /* there was no bitmap */
return;
+ mutex_lock(&mddev->bitmap_mutex);
mddev->bitmap = NULL; /* disconnect from the md device */
+ mutex_unlock(&mddev->bitmap_mutex);
if (mddev->thread)
mddev->thread->timeout = MAX_SCHEDULE_TIMEOUT;
@@ -1617,6 +1630,7 @@ int bitmap_create(mddev_t *mddev)
atomic_set(&bitmap->pending_writes, 0);
init_waitqueue_head(&bitmap->write_wait);
init_waitqueue_head(&bitmap->overflow_wait);
+ init_waitqueue_head(&bitmap->behind_wait);
bitmap->mddev = mddev;
diff --git a/drivers/md/bitmap.h b/drivers/md/bitmap.h
index e98900671ca9..86950bc527af 100644
--- a/drivers/md/bitmap.h
+++ b/drivers/md/bitmap.h
@@ -254,6 +254,9 @@ struct bitmap {
wait_queue_head_t write_wait;
wait_queue_head_t overflow_wait;
+#ifndef __GENKSYMS__
+ wait_queue_head_t behind_wait;
+#endif
};
/* the bitmap API */
@@ -282,7 +285,7 @@ void bitmap_close_sync(struct bitmap *bitmap);
void bitmap_cond_end_sync(struct bitmap *bitmap, sector_t sector);
void bitmap_unplug(struct bitmap *bitmap);
-void bitmap_daemon_work(struct bitmap *bitmap);
+void bitmap_daemon_work(mddev_t *mddev);
#endif
#endif
diff --git a/drivers/md/dm-crypt.c b/drivers/md/dm-crypt.c
index ed1038164019..959d6d14cee0 100644
--- a/drivers/md/dm-crypt.c
+++ b/drivers/md/dm-crypt.c
@@ -1,7 +1,7 @@
/*
* Copyright (C) 2003 Christophe Saout <christophe@saout.de>
* Copyright (C) 2004 Clemens Fruhwirth <clemens@endorphin.org>
- * Copyright (C) 2006-2008 Red Hat, Inc. All rights reserved.
+ * Copyright (C) 2006-2009 Red Hat, Inc. All rights reserved.
*
* This file is released under the GPL.
*/
@@ -71,10 +71,21 @@ struct crypt_iv_operations {
int (*ctr)(struct crypt_config *cc, struct dm_target *ti,
const char *opts);
void (*dtr)(struct crypt_config *cc);
- const char *(*status)(struct crypt_config *cc);
+ int (*init)(struct crypt_config *cc);
+ int (*wipe)(struct crypt_config *cc);
int (*generator)(struct crypt_config *cc, u8 *iv, sector_t sector);
};
+struct iv_essiv_private {
+ struct crypto_cipher *tfm;
+ struct crypto_hash *hash_tfm;
+ u8 *salt;
+};
+
+struct iv_benbi_private {
+ int shift;
+};
+
/*
* Crypt: maps a linear range of a block device
* and encrypts / decrypts at the same time.
@@ -102,8 +113,8 @@ struct crypt_config {
struct crypt_iv_operations *iv_gen_ops;
char *iv_mode;
union {
- struct crypto_cipher *essiv_tfm;
- int benbi_shift;
+ struct iv_essiv_private essiv;
+ struct iv_benbi_private benbi;
} iv_gen_private;
sector_t iv_offset;
unsigned int iv_size;
@@ -169,88 +180,114 @@ static int crypt_iv_plain_gen(struct crypt_config *cc, u8 *iv, sector_t sector)
return 0;
}
-static int crypt_iv_essiv_ctr(struct crypt_config *cc, struct dm_target *ti,
- const char *opts)
+/* Initialise ESSIV - compute salt but no local memory allocations */
+static int crypt_iv_essiv_init(struct crypt_config *cc)
{
- struct crypto_cipher *essiv_tfm;
- struct crypto_hash *hash_tfm;
+ struct iv_essiv_private *essiv = &cc->iv_gen_private.essiv;
struct hash_desc desc;
struct scatterlist sg;
- unsigned int saltsize;
- u8 *salt;
int err;
- if (opts == NULL) {
+ sg_init_one(&sg, cc->key, cc->key_size);
+ desc.tfm = essiv->hash_tfm;
+ desc.flags = CRYPTO_TFM_REQ_MAY_SLEEP;
+
+ err = crypto_hash_digest(&desc, &sg, cc->key_size, essiv->salt);
+ if (err)
+ return err;
+
+ return crypto_cipher_setkey(essiv->tfm, essiv->salt,
+ crypto_hash_digestsize(essiv->hash_tfm));
+}
+
+/* Wipe salt and reset key derived from volume key */
+static int crypt_iv_essiv_wipe(struct crypt_config *cc)
+{
+ struct iv_essiv_private *essiv = &cc->iv_gen_private.essiv;
+ unsigned salt_size = crypto_hash_digestsize(essiv->hash_tfm);
+
+ memset(essiv->salt, 0, salt_size);
+
+ return crypto_cipher_setkey(essiv->tfm, essiv->salt, salt_size);
+}
+
+static void crypt_iv_essiv_dtr(struct crypt_config *cc)
+{
+ struct iv_essiv_private *essiv = &cc->iv_gen_private.essiv;
+
+ crypto_free_cipher(essiv->tfm);
+ essiv->tfm = NULL;
+
+ crypto_free_hash(essiv->hash_tfm);
+ essiv->hash_tfm = NULL;
+
+ kzfree(essiv->salt);
+ essiv->salt = NULL;
+}
+
+static int crypt_iv_essiv_ctr(struct crypt_config *cc, struct dm_target *ti,
+ const char *opts)
+{
+ struct crypto_cipher *essiv_tfm = NULL;
+ struct crypto_hash *hash_tfm = NULL;
+ u8 *salt = NULL;
+ int err;
+
+ if (!opts) {
ti->error = "Digest algorithm missing for ESSIV mode";
return -EINVAL;
}
- /* Hash the cipher key with the given hash algorithm */
+ /* Allocate hash algorithm */
hash_tfm = crypto_alloc_hash(opts, 0, CRYPTO_ALG_ASYNC);
if (IS_ERR(hash_tfm)) {
ti->error = "Error initializing ESSIV hash";
- return PTR_ERR(hash_tfm);
+ err = PTR_ERR(hash_tfm);
+ goto bad;
}
- saltsize = crypto_hash_digestsize(hash_tfm);
- salt = kmalloc(saltsize, GFP_KERNEL);
- if (salt == NULL) {
+ salt = kzalloc(crypto_hash_digestsize(hash_tfm), GFP_KERNEL);
+ if (!salt) {
ti->error = "Error kmallocing salt storage in ESSIV";
- crypto_free_hash(hash_tfm);
- return -ENOMEM;
+ err = -ENOMEM;
+ goto bad;
}
- sg_init_one(&sg, cc->key, cc->key_size);
- desc.tfm = hash_tfm;
- desc.flags = CRYPTO_TFM_REQ_MAY_SLEEP;
- err = crypto_hash_digest(&desc, &sg, cc->key_size, salt);
- crypto_free_hash(hash_tfm);
-
- if (err) {
- ti->error = "Error calculating hash in ESSIV";
- kfree(salt);
- return err;
- }
-
- /* Setup the essiv_tfm with the given salt */
+ /* Allocate essiv_tfm */
essiv_tfm = crypto_alloc_cipher(cc->cipher, 0, CRYPTO_ALG_ASYNC);
if (IS_ERR(essiv_tfm)) {
ti->error = "Error allocating crypto tfm for ESSIV";
- kfree(salt);
- return PTR_ERR(essiv_tfm);
+ err = PTR_ERR(essiv_tfm);
+ goto bad;
}
if (crypto_cipher_blocksize(essiv_tfm) !=
crypto_ablkcipher_ivsize(cc->tfm)) {
ti->error = "Block size of ESSIV cipher does "
"not match IV size of block cipher";
- crypto_free_cipher(essiv_tfm);
- kfree(salt);
- return -EINVAL;
- }
- err = crypto_cipher_setkey(essiv_tfm, salt, saltsize);
- if (err) {
- ti->error = "Failed to set key for ESSIV cipher";
- crypto_free_cipher(essiv_tfm);
- kfree(salt);
- return err;
+ err = -EINVAL;
+ goto bad;
}
- kfree(salt);
- cc->iv_gen_private.essiv_tfm = essiv_tfm;
+ cc->iv_gen_private.essiv.salt = salt;
+ cc->iv_gen_private.essiv.tfm = essiv_tfm;
+ cc->iv_gen_private.essiv.hash_tfm = hash_tfm;
+
return 0;
-}
-static void crypt_iv_essiv_dtr(struct crypt_config *cc)
-{
- crypto_free_cipher(cc->iv_gen_private.essiv_tfm);
- cc->iv_gen_private.essiv_tfm = NULL;
+bad:
+ if (essiv_tfm && !IS_ERR(essiv_tfm))
+ crypto_free_cipher(essiv_tfm);
+ if (hash_tfm && !IS_ERR(hash_tfm))
+ crypto_free_hash(hash_tfm);
+ kfree(salt);
+ return err;
}
static int crypt_iv_essiv_gen(struct crypt_config *cc, u8 *iv, sector_t sector)
{
memset(iv, 0, cc->iv_size);
*(u64 *)iv = cpu_to_le64(sector);
- crypto_cipher_encrypt_one(cc->iv_gen_private.essiv_tfm, iv, iv);
+ crypto_cipher_encrypt_one(cc->iv_gen_private.essiv.tfm, iv, iv);
return 0;
}
@@ -273,7 +310,7 @@ static int crypt_iv_benbi_ctr(struct crypt_config *cc, struct dm_target *ti,
return -EINVAL;
}
- cc->iv_gen_private.benbi_shift = 9 - log;
+ cc->iv_gen_private.benbi.shift = 9 - log;
return 0;
}
@@ -288,7 +325,7 @@ static int crypt_iv_benbi_gen(struct crypt_config *cc, u8 *iv, sector_t sector)
memset(iv, 0, cc->iv_size - sizeof(u64)); /* rest is cleared below */
- val = cpu_to_be64(((u64)sector << cc->iv_gen_private.benbi_shift) + 1);
+ val = cpu_to_be64(((u64)sector << cc->iv_gen_private.benbi.shift) + 1);
put_unaligned(val, (__be64 *)(iv + cc->iv_size - sizeof(u64)));
return 0;
@@ -308,6 +345,8 @@ static struct crypt_iv_operations crypt_iv_plain_ops = {
static struct crypt_iv_operations crypt_iv_essiv_ops = {
.ctr = crypt_iv_essiv_ctr,
.dtr = crypt_iv_essiv_dtr,
+ .init = crypt_iv_essiv_init,
+ .wipe = crypt_iv_essiv_wipe,
.generator = crypt_iv_essiv_gen
};
@@ -1039,6 +1078,12 @@ static int crypt_ctr(struct dm_target *ti, unsigned int argc, char **argv)
cc->iv_gen_ops->ctr(cc, ti, ivopts) < 0)
goto bad_ivmode;
+ if (cc->iv_gen_ops && cc->iv_gen_ops->init &&
+ cc->iv_gen_ops->init(cc) < 0) {
+ ti->error = "Error initialising IV";
+ goto bad_slab_pool;
+ }
+
cc->iv_size = crypto_ablkcipher_ivsize(tfm);
if (cc->iv_size)
/* at least a 64 bit sector number should fit in our buffer */
@@ -1278,6 +1323,7 @@ static void crypt_resume(struct dm_target *ti)
static int crypt_message(struct dm_target *ti, unsigned argc, char **argv)
{
struct crypt_config *cc = ti->private;
+ int ret = -EINVAL;
if (argc < 2)
goto error;
@@ -1287,10 +1333,22 @@ static int crypt_message(struct dm_target *ti, unsigned argc, char **argv)
DMWARN("not suspended during key manipulation.");
return -EINVAL;
}
- if (argc == 3 && !strnicmp(argv[1], MESG_STR("set")))
- return crypt_set_key(cc, argv[2]);
- if (argc == 2 && !strnicmp(argv[1], MESG_STR("wipe")))
+ if (argc == 3 && !strnicmp(argv[1], MESG_STR("set"))) {
+ ret = crypt_set_key(cc, argv[2]);
+ if (ret)
+ return ret;
+ if (cc->iv_gen_ops && cc->iv_gen_ops->init)
+ ret = cc->iv_gen_ops->init(cc);
+ return ret;
+ }
+ if (argc == 2 && !strnicmp(argv[1], MESG_STR("wipe"))) {
+ if (cc->iv_gen_ops && cc->iv_gen_ops->wipe) {
+ ret = cc->iv_gen_ops->wipe(cc);
+ if (ret)
+ return ret;
+ }
return crypt_wipe_key(cc);
+ }
}
error:
diff --git a/drivers/md/dm-exception-store.c b/drivers/md/dm-exception-store.c
index 7dbe652efb5a..205215968ff1 100644
--- a/drivers/md/dm-exception-store.c
+++ b/drivers/md/dm-exception-store.c
@@ -216,7 +216,8 @@ int dm_exception_store_create(struct dm_target *ti, int argc, char **argv,
type = get_type("N");
else {
ti->error = "Persistent flag is not P or N";
- return -EINVAL;
+ r = -EINVAL;
+ goto bad_type;
}
if (!type) {
diff --git a/drivers/md/dm-exception-store.h b/drivers/md/dm-exception-store.h
index 8a223a48802c..5f9315b32a42 100644
--- a/drivers/md/dm-exception-store.h
+++ b/drivers/md/dm-exception-store.h
@@ -162,7 +162,7 @@ static inline sector_t get_dev_size(struct block_device *bdev)
static inline chunk_t sector_to_chunk(struct dm_exception_store *store,
sector_t sector)
{
- return (sector & ~store->chunk_mask) >> store->chunk_shift;
+ return sector >> store->chunk_shift;
}
int dm_exception_store_type_register(struct dm_exception_store_type *type);
diff --git a/drivers/md/dm-ioctl.c b/drivers/md/dm-ioctl.c
index a67942931582..818b617ab3b2 100644
--- a/drivers/md/dm-ioctl.c
+++ b/drivers/md/dm-ioctl.c
@@ -56,6 +56,11 @@ static void dm_hash_remove_all(int keep_open_devices);
*/
static DECLARE_RWSEM(_hash_lock);
+/*
+ * Protects use of mdptr to obtain hash cell name and uuid from mapped device.
+ */
+static DEFINE_MUTEX(dm_hash_cells_mutex);
+
static void init_buckets(struct list_head *buckets)
{
unsigned int i;
@@ -206,7 +211,9 @@ static int dm_hash_insert(const char *name, const char *uuid, struct mapped_devi
list_add(&cell->uuid_list, _uuid_buckets + hash_str(uuid));
}
dm_get(md);
+ mutex_lock(&dm_hash_cells_mutex);
dm_set_mdptr(md, cell);
+ mutex_unlock(&dm_hash_cells_mutex);
up_write(&_hash_lock);
return 0;
@@ -224,7 +231,9 @@ static void __hash_remove(struct hash_cell *hc)
/* remove from the dev hash */
list_del(&hc->uuid_list);
list_del(&hc->name_list);
+ mutex_lock(&dm_hash_cells_mutex);
dm_set_mdptr(hc->md, NULL);
+ mutex_unlock(&dm_hash_cells_mutex);
table = dm_get_table(hc->md);
if (table) {
@@ -240,40 +249,46 @@ static void __hash_remove(struct hash_cell *hc)
static void dm_hash_remove_all(int keep_open_devices)
{
- int i, dev_skipped, dev_removed;
+ int i, dev_skipped;
struct hash_cell *hc;
- struct list_head *tmp, *n;
+ struct mapped_device *md;
+
+retry:
+ dev_skipped = 0;
down_write(&_hash_lock);
-retry:
- dev_skipped = dev_removed = 0;
for (i = 0; i < NUM_BUCKETS; i++) {
- list_for_each_safe (tmp, n, _name_buckets + i) {
- hc = list_entry(tmp, struct hash_cell, name_list);
+ list_for_each_entry(hc, _name_buckets + i, name_list) {
+ md = hc->md;
+ dm_get(md);
- if (keep_open_devices &&
- dm_lock_for_deletion(hc->md)) {
+ if (keep_open_devices && dm_lock_for_deletion(md)) {
+ dm_put(md);
dev_skipped++;
continue;
}
+
__hash_remove(hc);
- dev_removed = 1;
- }
- }
- /*
- * Some mapped devices may be using other mapped devices, so if any
- * still exist, repeat until we make no further progress.
- */
- if (dev_skipped) {
- if (dev_removed)
- goto retry;
+ up_write(&_hash_lock);
- DMWARN("remove_all left %d open device(s)", dev_skipped);
+ dm_put(md);
+
+ /*
+ * Some mapped devices may be using other mapped
+ * devices, so repeat until we make no further
+ * progress. If a new mapped device is created
+ * here it will also get removed.
+ */
+ goto retry;
+ }
}
up_write(&_hash_lock);
+
+ if (dev_skipped)
+ DMWARN("remove_all left %d open device(s)", dev_skipped);
}
static int dm_hash_rename(uint32_t cookie, const char *old, const char *new)
@@ -321,7 +336,9 @@ static int dm_hash_rename(uint32_t cookie, const char *old, const char *new)
*/
list_del(&hc->name_list);
old_name = hc->name;
+ mutex_lock(&dm_hash_cells_mutex);
hc->name = new_name;
+ mutex_unlock(&dm_hash_cells_mutex);
list_add(&hc->name_list, _name_buckets + hash_str(new_name));
/*
@@ -1582,8 +1599,7 @@ int dm_copy_name_and_uuid(struct mapped_device *md, char *name, char *uuid)
if (!md)
return -ENXIO;
- dm_get(md);
- down_read(&_hash_lock);
+ mutex_lock(&dm_hash_cells_mutex);
hc = dm_get_mdptr(md);
if (!hc || hc->md != md) {
r = -ENXIO;
@@ -1596,8 +1612,7 @@ int dm_copy_name_and_uuid(struct mapped_device *md, char *name, char *uuid)
strcpy(uuid, hc->uuid ? : "");
out:
- up_read(&_hash_lock);
- dm_put(md);
+ mutex_unlock(&dm_hash_cells_mutex);
return r;
}
diff --git a/drivers/md/dm-log-userspace-transfer.c b/drivers/md/dm-log-userspace-transfer.c
index 54abf9e303b7..f1c8cae70b4b 100644
--- a/drivers/md/dm-log-userspace-transfer.c
+++ b/drivers/md/dm-log-userspace-transfer.c
@@ -172,11 +172,15 @@ int dm_consult_userspace(const char *uuid, uint64_t luid, int request_type,
{
int r = 0;
size_t dummy = 0;
- int overhead_size =
- sizeof(struct dm_ulog_request *) + sizeof(struct cn_msg);
+ int overhead_size = sizeof(struct dm_ulog_request) + sizeof(struct cn_msg);
struct dm_ulog_request *tfr = prealloced_ulog_tfr;
struct receiving_pkg pkg;
+ /*
+ * Given the space needed to hold the 'struct cn_msg' and
+ * 'struct dm_ulog_request' - do we have enough payload
+ * space remaining?
+ */
if (data_size > (DM_ULOG_PREALLOCED_SIZE - overhead_size)) {
DMINFO("Size of tfr exceeds preallocated size");
return -EINVAL;
@@ -191,7 +195,7 @@ resend:
*/
mutex_lock(&dm_ulog_lock);
- memset(tfr, 0, DM_ULOG_PREALLOCED_SIZE - overhead_size);
+ memset(tfr, 0, DM_ULOG_PREALLOCED_SIZE - sizeof(struct cn_msg));
memcpy(tfr->uuid, uuid, DM_UUID_LEN);
tfr->luid = luid;
tfr->seq = dm_ulog_seq++;
diff --git a/drivers/md/dm-mpath.c b/drivers/md/dm-mpath.c
index 32d0b878eccc..f336c6959082 100644
--- a/drivers/md/dm-mpath.c
+++ b/drivers/md/dm-mpath.c
@@ -691,6 +691,7 @@ static struct priority_group *parse_priority_group(struct arg_set *as,
if (as->argc < nr_params) {
ti->error = "not enough path parameters";
+ r = -EINVAL;
goto bad;
}
diff --git a/drivers/md/dm-snap.c b/drivers/md/dm-snap.c
index 3a3ba46e6d4b..8a4a9c838afd 100644
--- a/drivers/md/dm-snap.c
+++ b/drivers/md/dm-snap.c
@@ -553,6 +553,8 @@ static int init_hash_tables(struct dm_snapshot *s)
hash_size = min(origin_dev_size, cow_dev_size) >> s->store->chunk_shift;
hash_size = min(hash_size, max_buckets);
+ if (hash_size < 64)
+ hash_size = 64;
hash_size = rounddown_pow_of_two(hash_size);
if (init_exception_table(&s->complete, hash_size,
DM_CHUNK_CONSECUTIVE_BITS))
@@ -1152,10 +1154,11 @@ static int snapshot_status(struct dm_target *ti, status_type_t type,
unsigned sz = 0;
struct dm_snapshot *snap = ti->private;
- down_write(&snap->lock);
-
switch (type) {
case STATUSTYPE_INFO:
+
+ down_write(&snap->lock);
+
if (!snap->valid)
DMEMIT("Invalid");
else {
@@ -1171,6 +1174,9 @@ static int snapshot_status(struct dm_target *ti, status_type_t type,
else
DMEMIT("Unknown");
}
+
+ up_write(&snap->lock);
+
break;
case STATUSTYPE_TABLE:
@@ -1185,8 +1191,6 @@ static int snapshot_status(struct dm_target *ti, status_type_t type,
break;
}
- up_write(&snap->lock);
-
return 0;
}
diff --git a/drivers/md/dm-stripe.c b/drivers/md/dm-stripe.c
index e0efc1adcaff..bd58703ee8f6 100644
--- a/drivers/md/dm-stripe.c
+++ b/drivers/md/dm-stripe.c
@@ -110,7 +110,7 @@ static int stripe_ctr(struct dm_target *ti, unsigned int argc, char **argv)
}
stripes = simple_strtoul(argv[0], &end, 10);
- if (*end) {
+ if (!stripes || *end) {
ti->error = "Invalid stripe count";
return -EINVAL;
}
diff --git a/drivers/md/dm-table.c b/drivers/md/dm-table.c
index 1a6cb3c7822e..e86912864e04 100644
--- a/drivers/md/dm-table.c
+++ b/drivers/md/dm-table.c
@@ -499,16 +499,15 @@ int dm_set_device_limits(struct dm_target *ti, struct dm_dev *dev,
return 0;
}
- if (blk_stack_limits(limits, &q->limits, start << 9) < 0)
- DMWARN("%s: target device %s is misaligned: "
+ if (bdev_stack_limits(limits, bdev, start) < 0)
+ DMWARN("%s: adding target device %s caused an alignment inconsistency: "
"physical_block_size=%u, logical_block_size=%u, "
"alignment_offset=%u, start=%llu",
dm_device_name(ti->table->md), bdevname(bdev, b),
q->limits.physical_block_size,
q->limits.logical_block_size,
q->limits.alignment_offset,
- (unsigned long long) start << 9);
-
+ (unsigned long long) start << SECTOR_SHIFT);
/*
* Check if merge fn is supported.
@@ -1025,9 +1024,9 @@ combine_limits:
* for the table.
*/
if (blk_stack_limits(limits, &ti_limits, 0) < 0)
- DMWARN("%s: target device "
+ DMWARN("%s: adding target device "
"(start sect %llu len %llu) "
- "is misaligned",
+ "caused an alignment inconsistency",
dm_device_name(table->md),
(unsigned long long) ti->begin,
(unsigned long long) ti->len);
@@ -1079,15 +1078,6 @@ void dm_table_set_restrictions(struct dm_table *t, struct request_queue *q,
struct queue_limits *limits)
{
/*
- * Each target device in the table has a data area that should normally
- * be aligned such that the DM device's alignment_offset is 0.
- * FIXME: Propagate alignment_offsets up the stack and warn of
- * sub-optimal or inconsistent settings.
- */
- limits->alignment_offset = 0;
- limits->misaligned = 0;
-
- /*
* Copy table's limits to the DM device's request_queue
*/
q->limits = *limits;
diff --git a/drivers/md/dm-uevent.c b/drivers/md/dm-uevent.c
index 6f65883aef12..c7c555a8c7b2 100644
--- a/drivers/md/dm-uevent.c
+++ b/drivers/md/dm-uevent.c
@@ -139,14 +139,13 @@ void dm_send_uevents(struct list_head *events, struct kobject *kobj)
list_del_init(&event->elist);
/*
- * Need to call dm_copy_name_and_uuid from here for now.
- * Context of previous var adds and locking used for
- * hash_cell not compatable.
+ * When a device is being removed this copy fails and we
+ * discard these unsent events.
*/
if (dm_copy_name_and_uuid(event->md, event->name,
event->uuid)) {
- DMERR("%s: dm_copy_name_and_uuid() failed",
- __func__);
+ DMINFO("%s: skipping sending uevent for lost device",
+ __func__);
goto uevent_free;
}
diff --git a/drivers/md/dm.c b/drivers/md/dm.c
index 724efc63904d..d7786e3514cd 100644
--- a/drivers/md/dm.c
+++ b/drivers/md/dm.c
@@ -614,8 +614,10 @@ static void dec_pending(struct dm_io *io, int error)
if (!md->barrier_error && io_error != -EOPNOTSUPP)
md->barrier_error = io_error;
end_io_acct(io);
+ free_io(md, io);
} else {
end_io_acct(io);
+ free_io(md, io);
if (io_error != DM_ENDIO_REQUEUE) {
trace_block_bio_complete(md->queue, bio);
@@ -623,8 +625,6 @@ static void dec_pending(struct dm_io *io, int error)
bio_endio(bio, io_error);
}
}
-
- free_io(md, io);
}
}
@@ -1487,10 +1487,15 @@ static int dm_prep_fn(struct request_queue *q, struct request *rq)
return BLKPREP_OK;
}
-static void map_request(struct dm_target *ti, struct request *rq,
- struct mapped_device *md)
+/*
+ * Returns:
+ * 0 : the request has been processed (not requeued)
+ * !0 : the request has been requeued
+ */
+static int map_request(struct dm_target *ti, struct request *rq,
+ struct mapped_device *md)
{
- int r;
+ int r, requeued = 0;
struct request *clone = rq->special;
struct dm_rq_target_io *tio = clone->end_io_data;
@@ -1516,6 +1521,7 @@ static void map_request(struct dm_target *ti, struct request *rq,
case DM_MAPIO_REQUEUE:
/* The target wants to requeue the I/O */
dm_requeue_unmapped_request(clone);
+ requeued = 1;
break;
default:
if (r > 0) {
@@ -1527,6 +1533,8 @@ static void map_request(struct dm_target *ti, struct request *rq,
dm_kill_unmapped_request(clone, r);
break;
}
+
+ return requeued;
}
/*
@@ -1568,12 +1576,17 @@ static void dm_request_fn(struct request_queue *q)
blk_start_request(rq);
spin_unlock(q->queue_lock);
- map_request(ti, rq, md);
+ if (map_request(ti, rq, md))
+ goto requeued;
+
spin_lock_irq(q->queue_lock);
}
goto out;
+requeued:
+ spin_lock_irq(q->queue_lock);
+
plug_and_out:
if (!elv_queue_empty(q))
/* Some requests still remain, retry later */
diff --git a/drivers/md/linear.c b/drivers/md/linear.c
index 1ceceb334d5e..dff9d2f449c3 100644
--- a/drivers/md/linear.c
+++ b/drivers/md/linear.c
@@ -172,12 +172,14 @@ static linear_conf_t *linear_conf(mddev_t *mddev, int raid_disks)
disk_stack_limits(mddev->gendisk, rdev->bdev,
rdev->data_offset << 9);
/* as we don't honour merge_bvec_fn, we must never risk
- * violating it, so limit ->max_sector to one PAGE, as
- * a one page request is never in violation.
+ * violating it, so limit max_phys_segments to 1 lying within
+ * a single page.
*/
- if (rdev->bdev->bd_disk->queue->merge_bvec_fn &&
- queue_max_sectors(mddev->queue) > (PAGE_SIZE>>9))
- blk_queue_max_sectors(mddev->queue, PAGE_SIZE>>9);
+ if (rdev->bdev->bd_disk->queue->merge_bvec_fn) {
+ blk_queue_max_phys_segments(mddev->queue, 1);
+ blk_queue_segment_boundary(mddev->queue,
+ PAGE_CACHE_SIZE - 1);
+ }
conf->array_sectors += rdev->sectors;
cnt++;
diff --git a/drivers/md/md.c b/drivers/md/md.c
index b182f86a19dd..01470794d9c3 100644
--- a/drivers/md/md.c
+++ b/drivers/md/md.c
@@ -282,7 +282,9 @@ static void mddev_put(mddev_t *mddev)
if (!atomic_dec_and_lock(&mddev->active, &all_mddevs_lock))
return;
if (!mddev->raid_disks && list_empty(&mddev->disks) &&
- !mddev->hold_active) {
+ mddev->ctime == 0 && !mddev->hold_active) {
+ /* Array is not configured at all, and not held active,
+ * so destroy it */
list_del(&mddev->all_mddevs);
if (mddev->gendisk) {
/* we did a probe so need to clean up.
@@ -367,6 +369,7 @@ static mddev_t * mddev_find(dev_t unit)
mutex_init(&new->open_mutex);
mutex_init(&new->reconfig_mutex);
+ mutex_init(&new->bitmap_mutex);
INIT_LIST_HEAD(&new->disks);
INIT_LIST_HEAD(&new->all_mddevs);
init_timer(&new->safemode_timer);
@@ -2008,12 +2011,18 @@ repeat:
if (!mddev->in_sync || mddev->recovery_cp != MaxSector) { /* not clean */
/* .. if the array isn't clean, an 'even' event must also go
* to spares. */
- if ((mddev->events&1)==0)
+ if ((mddev->events&1)==0) {
nospares = 0;
+ sync_req = 2; /* force a second update to get the
+ * even/odd in sync */
+ }
} else {
/* otherwise an 'odd' event must go to spares */
- if ((mddev->events&1))
+ if ((mddev->events&1)) {
nospares = 0;
+ sync_req = 2; /* force a second update to get the
+ * even/odd in sync */
+ }
}
}
@@ -4170,7 +4179,7 @@ static int do_md_run(mddev_t * mddev)
mddev->barriers_work = 1;
mddev->ok_start_degraded = start_dirty_degraded;
- if (start_readonly)
+ if (start_readonly && mddev->ro == 0)
mddev->ro = 2; /* read-only, but switch on first write */
err = mddev->pers->run(mddev);
@@ -5070,6 +5079,10 @@ static int set_array_info(mddev_t * mddev, mdu_array_info_t *info)
mddev->minor_version = info->minor_version;
mddev->patch_version = info->patch_version;
mddev->persistent = !info->not_persistent;
+ /* ensure mddev_put doesn't delete this now that there
+ * is some minimal configuration.
+ */
+ mddev->ctime = get_seconds();
return 0;
}
mddev->major_version = MD_MAJOR_VERSION;
@@ -5321,6 +5334,7 @@ static int md_ioctl(struct block_device *bdev, fmode_t mode,
int err = 0;
void __user *argp = (void __user *)arg;
mddev_t *mddev = NULL;
+ int ro;
if (!capable(CAP_SYS_ADMIN))
return -EACCES;
@@ -5456,6 +5470,34 @@ static int md_ioctl(struct block_device *bdev, fmode_t mode,
err = do_md_stop(mddev, 1, 1);
goto done_unlock;
+ case BLKROSET:
+ if (get_user(ro, (int __user *)(arg))) {
+ err = -EFAULT;
+ goto done_unlock;
+ }
+ err = -EINVAL;
+
+ /* if the bdev is going readonly the value of mddev->ro
+ * does not matter, no writes are coming
+ */
+ if (ro)
+ goto done_unlock;
+
+ /* are we are already prepared for writes? */
+ if (mddev->ro != 1)
+ goto done_unlock;
+
+ /* transitioning to readauto need only happen for
+ * arrays that call md_write_start
+ */
+ if (mddev->pers) {
+ err = restart_array(mddev);
+ if (err == 0) {
+ mddev->ro = 2;
+ set_disk_ro(mddev->gendisk, 0);
+ }
+ }
+ goto done_unlock;
}
/*
@@ -6629,7 +6671,7 @@ void md_check_recovery(mddev_t *mddev)
if (mddev->bitmap)
- bitmap_daemon_work(mddev->bitmap);
+ bitmap_daemon_work(mddev);
if (mddev->ro)
return;
diff --git a/drivers/md/md.h b/drivers/md/md.h
index f184b69ef337..87430fea2875 100644
--- a/drivers/md/md.h
+++ b/drivers/md/md.h
@@ -289,6 +289,7 @@ struct mddev_s
* hot-adding a bitmap. It should
* eventually be settable by sysfs.
*/
+ struct mutex bitmap_mutex;
struct list_head all_mddevs;
};
diff --git a/drivers/md/multipath.c b/drivers/md/multipath.c
index ee7646f974a0..e4b11f18adc7 100644
--- a/drivers/md/multipath.c
+++ b/drivers/md/multipath.c
@@ -301,14 +301,16 @@ static int multipath_add_disk(mddev_t *mddev, mdk_rdev_t *rdev)
rdev->data_offset << 9);
/* as we don't honour merge_bvec_fn, we must never risk
- * violating it, so limit ->max_sector to one PAGE, as
- * a one page request is never in violation.
+ * violating it, so limit ->max_phys_segments to one, lying
+ * within a single page.
* (Note: it is very unlikely that a device with
* merge_bvec_fn will be involved in multipath.)
*/
- if (q->merge_bvec_fn &&
- queue_max_sectors(q) > (PAGE_SIZE>>9))
- blk_queue_max_sectors(mddev->queue, PAGE_SIZE>>9);
+ if (q->merge_bvec_fn) {
+ blk_queue_max_phys_segments(mddev->queue, 1);
+ blk_queue_segment_boundary(mddev->queue,
+ PAGE_CACHE_SIZE - 1);
+ }
conf->working_disks++;
mddev->degraded--;
@@ -476,9 +478,11 @@ static int multipath_run (mddev_t *mddev)
/* as we don't honour merge_bvec_fn, we must never risk
* violating it, not that we ever expect a device with
* a merge_bvec_fn to be involved in multipath */
- if (rdev->bdev->bd_disk->queue->merge_bvec_fn &&
- queue_max_sectors(mddev->queue) > (PAGE_SIZE>>9))
- blk_queue_max_sectors(mddev->queue, PAGE_SIZE>>9);
+ if (rdev->bdev->bd_disk->queue->merge_bvec_fn) {
+ blk_queue_max_phys_segments(mddev->queue, 1);
+ blk_queue_segment_boundary(mddev->queue,
+ PAGE_CACHE_SIZE - 1);
+ }
if (!test_bit(Faulty, &rdev->flags))
conf->working_disks++;
diff --git a/drivers/md/raid0.c b/drivers/md/raid0.c
index d3a4ce06015a..3db857cdd33e 100644
--- a/drivers/md/raid0.c
+++ b/drivers/md/raid0.c
@@ -176,14 +176,15 @@ static int create_strip_zones(mddev_t *mddev)
disk_stack_limits(mddev->gendisk, rdev1->bdev,
rdev1->data_offset << 9);
/* as we don't honour merge_bvec_fn, we must never risk
- * violating it, so limit ->max_sector to one PAGE, as
- * a one page request is never in violation.
+ * violating it, so limit ->max_phys_segments to 1, lying within
+ * a single page.
*/
- if (rdev1->bdev->bd_disk->queue->merge_bvec_fn &&
- queue_max_sectors(mddev->queue) > (PAGE_SIZE>>9))
- blk_queue_max_sectors(mddev->queue, PAGE_SIZE>>9);
-
+ if (rdev1->bdev->bd_disk->queue->merge_bvec_fn) {
+ blk_queue_max_phys_segments(mddev->queue, 1);
+ blk_queue_segment_boundary(mddev->queue,
+ PAGE_CACHE_SIZE - 1);
+ }
if (!smallest || (rdev1->sectors < smallest->sectors))
smallest = rdev1;
cnt++;
diff --git a/drivers/md/raid1.c b/drivers/md/raid1.c
index e07ce2e033a9..791e1951430a 100644
--- a/drivers/md/raid1.c
+++ b/drivers/md/raid1.c
@@ -417,7 +417,7 @@ static void raid1_end_write_request(struct bio *bio, int error)
*/
static int read_balance(conf_t *conf, r1bio_t *r1_bio)
{
- const unsigned long this_sector = r1_bio->sector;
+ const sector_t this_sector = r1_bio->sector;
int new_disk = conf->last_used, disk = new_disk;
int wonly_disk = -1;
const int sectors = r1_bio->sectors;
@@ -433,7 +433,7 @@ static int read_balance(conf_t *conf, r1bio_t *r1_bio)
retry:
if (conf->mddev->recovery_cp < MaxSector &&
(this_sector + sectors >= conf->next_resync)) {
- /* Choose the first operation device, for consistancy */
+ /* Choose the first operational device, for consistancy */
new_disk = 0;
for (rdev = rcu_dereference(conf->mirrors[new_disk].rdev);
@@ -845,6 +845,15 @@ static int make_request(struct request_queue *q, struct bio * bio)
}
mirror = conf->mirrors + rdisk;
+ if (test_bit(WriteMostly, &mirror->rdev->flags) &&
+ bitmap) {
+ /* Reading from a write-mostly device must
+ * take care not to over-take any writes
+ * that are 'behind'
+ */
+ wait_event(bitmap->behind_wait,
+ atomic_read(&bitmap->behind_writes) == 0);
+ }
r1_bio->read_disk = rdisk;
read_bio = bio_clone(bio, GFP_NOIO);
@@ -891,9 +900,10 @@ static int make_request(struct request_queue *q, struct bio * bio)
if (test_bit(Faulty, &rdev->flags)) {
rdev_dec_pending(rdev, mddev);
r1_bio->bios[i] = NULL;
- } else
+ } else {
r1_bio->bios[i] = bio;
- targets++;
+ targets++;
+ }
} else
r1_bio->bios[i] = NULL;
}
@@ -921,9 +931,13 @@ static int make_request(struct request_queue *q, struct bio * bio)
set_bit(R1BIO_Degraded, &r1_bio->state);
}
- /* do behind I/O ? */
+ /* do behind I/O ?
+ * Not if there are too many, or cannot allocate memory,
+ * or a reader on WriteMostly is waiting for behind writes
+ * to flush */
if (bitmap &&
atomic_read(&bitmap->behind_writes) < bitmap->max_write_behind &&
+ !waitqueue_active(&bitmap->behind_wait) &&
(behind_pages = alloc_behind_pages(bio)) != NULL)
set_bit(R1BIO_BehindIO, &r1_bio->state);
@@ -2104,15 +2118,13 @@ static int stop(mddev_t *mddev)
{
conf_t *conf = mddev->private;
struct bitmap *bitmap = mddev->bitmap;
- int behind_wait = 0;
/* wait for behind writes to complete */
- while (bitmap && atomic_read(&bitmap->behind_writes) > 0) {
- behind_wait++;
- printk(KERN_INFO "raid1: behind writes in progress on device %s, waiting to stop (%d)\n", mdname(mddev), behind_wait);
- set_current_state(TASK_UNINTERRUPTIBLE);
- schedule_timeout(HZ); /* wait a second */
+ if (bitmap && atomic_read(&bitmap->behind_writes) > 0) {
+ printk(KERN_INFO "raid1: behind writes in progress on device %s, waiting to stop.\n", mdname(mddev));
/* need to kick something here to make sure I/O goes? */
+ wait_event(bitmap->behind_wait,
+ atomic_read(&bitmap->behind_writes) == 0);
}
raise_barrier(conf);
diff --git a/drivers/md/raid10.c b/drivers/md/raid10.c
index c2cb7b87b440..1b4e232bce3c 100644
--- a/drivers/md/raid10.c
+++ b/drivers/md/raid10.c
@@ -493,7 +493,7 @@ static int raid10_mergeable_bvec(struct request_queue *q,
*/
static int read_balance(conf_t *conf, r10bio_t *r10_bio)
{
- const unsigned long this_sector = r10_bio->sector;
+ const sector_t this_sector = r10_bio->sector;
int disk, slot, nslot;
const int sectors = r10_bio->sectors;
sector_t new_distance, current_distance;
@@ -824,11 +824,29 @@ static int make_request(struct request_queue *q, struct bio * bio)
*/
bp = bio_split(bio,
chunk_sects - (bio->bi_sector & (chunk_sects - 1)) );
+
+ /* Each of these 'make_request' calls will call 'wait_barrier'.
+ * If the first succeeds but the second blocks due to the resync
+ * thread raising the barrier, we will deadlock because the
+ * IO to the underlying device will be queued in generic_make_request
+ * and will never complete, so will never reduce nr_pending.
+ * So increment nr_waiting here so no new raise_barriers will
+ * succeed, and so the second wait_barrier cannot block.
+ */
+ spin_lock_irq(&conf->resync_lock);
+ conf->nr_waiting++;
+ spin_unlock_irq(&conf->resync_lock);
+
if (make_request(q, &bp->bio1))
generic_make_request(&bp->bio1);
if (make_request(q, &bp->bio2))
generic_make_request(&bp->bio2);
+ spin_lock_irq(&conf->resync_lock);
+ conf->nr_waiting--;
+ wake_up(&conf->wait_barrier);
+ spin_unlock_irq(&conf->resync_lock);
+
bio_pair_release(bp);
return 0;
bad_map:
@@ -1155,13 +1173,17 @@ static int raid10_add_disk(mddev_t *mddev, mdk_rdev_t *rdev)
disk_stack_limits(mddev->gendisk, rdev->bdev,
rdev->data_offset << 9);
- /* as we don't honour merge_bvec_fn, we must never risk
- * violating it, so limit ->max_sector to one PAGE, as
- * a one page request is never in violation.
+ /* as we don't honour merge_bvec_fn, we must
+ * never risk violating it, so limit
+ * ->max_phys_segments to one lying with a single
+ * page, as a one page request is never in
+ * violation.
*/
- if (rdev->bdev->bd_disk->queue->merge_bvec_fn &&
- queue_max_sectors(mddev->queue) > (PAGE_SIZE>>9))
- blk_queue_max_sectors(mddev->queue, PAGE_SIZE>>9);
+ if (rdev->bdev->bd_disk->queue->merge_bvec_fn) {
+ blk_queue_max_phys_segments(mddev->queue, 1);
+ blk_queue_segment_boundary(mddev->queue,
+ PAGE_CACHE_SIZE - 1);
+ }
p->head_position = 0;
rdev->raid_disk = mirror;
@@ -2155,12 +2177,14 @@ static int run(mddev_t *mddev)
disk_stack_limits(mddev->gendisk, rdev->bdev,
rdev->data_offset << 9);
/* as we don't honour merge_bvec_fn, we must never risk
- * violating it, so limit ->max_sector to one PAGE, as
- * a one page request is never in violation.
+ * violating it, so limit max_phys_segments to 1 lying
+ * within a single page.
*/
- if (rdev->bdev->bd_disk->queue->merge_bvec_fn &&
- queue_max_sectors(mddev->queue) > (PAGE_SIZE>>9))
- blk_queue_max_sectors(mddev->queue, PAGE_SIZE>>9);
+ if (rdev->bdev->bd_disk->queue->merge_bvec_fn) {
+ blk_queue_max_phys_segments(mddev->queue, 1);
+ blk_queue_segment_boundary(mddev->queue,
+ PAGE_CACHE_SIZE - 1);
+ }
disk->head_position = 0;
}
diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c
index d29215d966da..23949739fc25 100644
--- a/drivers/md/raid5.c
+++ b/drivers/md/raid5.c
@@ -1526,7 +1526,7 @@ static void raid5_end_read_request(struct bio * bi, int error)
clear_bit(R5_UPTODATE, &sh->dev[i].flags);
atomic_inc(&rdev->read_errors);
- if (conf->mddev->degraded)
+ if (conf->mddev->degraded >= conf->max_degraded)
printk_rl(KERN_WARNING
"raid5:%s: read error not correctable "
"(sector %llu on %s).\n",
@@ -1649,8 +1649,8 @@ static sector_t raid5_compute_sector(raid5_conf_t *conf, sector_t r_sector,
int previous, int *dd_idx,
struct stripe_head *sh)
{
- long stripe;
- unsigned long chunk_number;
+ sector_t stripe, stripe2;
+ sector_t chunk_number;
unsigned int chunk_offset;
int pd_idx, qd_idx;
int ddf_layout = 0;
@@ -1670,18 +1670,13 @@ static sector_t raid5_compute_sector(raid5_conf_t *conf, sector_t r_sector,
*/
chunk_offset = sector_div(r_sector, sectors_per_chunk);
chunk_number = r_sector;
- BUG_ON(r_sector != chunk_number);
/*
* Compute the stripe number
*/
- stripe = chunk_number / data_disks;
-
- /*
- * Compute the data disk and parity disk indexes inside the stripe
- */
- *dd_idx = chunk_number % data_disks;
-
+ stripe = chunk_number;
+ *dd_idx = sector_div(stripe, data_disks);
+ stripe2 = stripe;
/*
* Select the parity disk based on the user selected algorithm.
*/
@@ -1693,21 +1688,21 @@ static sector_t raid5_compute_sector(raid5_conf_t *conf, sector_t r_sector,
case 5:
switch (algorithm) {
case ALGORITHM_LEFT_ASYMMETRIC:
- pd_idx = data_disks - stripe % raid_disks;
+ pd_idx = data_disks - sector_div(stripe2, raid_disks);
if (*dd_idx >= pd_idx)
(*dd_idx)++;
break;
case ALGORITHM_RIGHT_ASYMMETRIC:
- pd_idx = stripe % raid_disks;
+ pd_idx = sector_div(stripe2, raid_disks);
if (*dd_idx >= pd_idx)
(*dd_idx)++;
break;
case ALGORITHM_LEFT_SYMMETRIC:
- pd_idx = data_disks - stripe % raid_disks;
+ pd_idx = data_disks - sector_div(stripe2, raid_disks);
*dd_idx = (pd_idx + 1 + *dd_idx) % raid_disks;
break;
case ALGORITHM_RIGHT_SYMMETRIC:
- pd_idx = stripe % raid_disks;
+ pd_idx = sector_div(stripe2, raid_disks);
*dd_idx = (pd_idx + 1 + *dd_idx) % raid_disks;
break;
case ALGORITHM_PARITY_0:
@@ -1727,7 +1722,7 @@ static sector_t raid5_compute_sector(raid5_conf_t *conf, sector_t r_sector,
switch (algorithm) {
case ALGORITHM_LEFT_ASYMMETRIC:
- pd_idx = raid_disks - 1 - (stripe % raid_disks);
+ pd_idx = raid_disks - 1 - sector_div(stripe2, raid_disks);
qd_idx = pd_idx + 1;
if (pd_idx == raid_disks-1) {
(*dd_idx)++; /* Q D D D P */
@@ -1736,7 +1731,7 @@ static sector_t raid5_compute_sector(raid5_conf_t *conf, sector_t r_sector,
(*dd_idx) += 2; /* D D P Q D */
break;
case ALGORITHM_RIGHT_ASYMMETRIC:
- pd_idx = stripe % raid_disks;
+ pd_idx = sector_div(stripe2, raid_disks);
qd_idx = pd_idx + 1;
if (pd_idx == raid_disks-1) {
(*dd_idx)++; /* Q D D D P */
@@ -1745,12 +1740,12 @@ static sector_t raid5_compute_sector(raid5_conf_t *conf, sector_t r_sector,
(*dd_idx) += 2; /* D D P Q D */
break;
case ALGORITHM_LEFT_SYMMETRIC:
- pd_idx = raid_disks - 1 - (stripe % raid_disks);
+ pd_idx = raid_disks - 1 - sector_div(stripe2, raid_disks);
qd_idx = (pd_idx + 1) % raid_disks;
*dd_idx = (pd_idx + 2 + *dd_idx) % raid_disks;
break;
case ALGORITHM_RIGHT_SYMMETRIC:
- pd_idx = stripe % raid_disks;
+ pd_idx = sector_div(stripe2, raid_disks);
qd_idx = (pd_idx + 1) % raid_disks;
*dd_idx = (pd_idx + 2 + *dd_idx) % raid_disks;
break;
@@ -1769,7 +1764,7 @@ static sector_t raid5_compute_sector(raid5_conf_t *conf, sector_t r_sector,
/* Exactly the same as RIGHT_ASYMMETRIC, but or
* of blocks for computing Q is different.
*/
- pd_idx = stripe % raid_disks;
+ pd_idx = sector_div(stripe2, raid_disks);
qd_idx = pd_idx + 1;
if (pd_idx == raid_disks-1) {
(*dd_idx)++; /* Q D D D P */
@@ -1784,7 +1779,8 @@ static sector_t raid5_compute_sector(raid5_conf_t *conf, sector_t r_sector,
* D D D P Q rather than
* Q D D D P
*/
- pd_idx = raid_disks - 1 - ((stripe + 1) % raid_disks);
+ stripe2 += 1;
+ pd_idx = raid_disks - 1 - sector_div(stripe2, raid_disks);
qd_idx = pd_idx + 1;
if (pd_idx == raid_disks-1) {
(*dd_idx)++; /* Q D D D P */
@@ -1796,7 +1792,7 @@ static sector_t raid5_compute_sector(raid5_conf_t *conf, sector_t r_sector,
case ALGORITHM_ROTATING_N_CONTINUE:
/* Same as left_symmetric but Q is before P */
- pd_idx = raid_disks - 1 - (stripe % raid_disks);
+ pd_idx = raid_disks - 1 - sector_div(stripe2, raid_disks);
qd_idx = (pd_idx + raid_disks - 1) % raid_disks;
*dd_idx = (pd_idx + 1 + *dd_idx) % raid_disks;
ddf_layout = 1;
@@ -1804,27 +1800,27 @@ static sector_t raid5_compute_sector(raid5_conf_t *conf, sector_t r_sector,
case ALGORITHM_LEFT_ASYMMETRIC_6:
/* RAID5 left_asymmetric, with Q on last device */
- pd_idx = data_disks - stripe % (raid_disks-1);
+ pd_idx = data_disks - sector_div(stripe2, raid_disks-1);
if (*dd_idx >= pd_idx)
(*dd_idx)++;
qd_idx = raid_disks - 1;
break;
case ALGORITHM_RIGHT_ASYMMETRIC_6:
- pd_idx = stripe % (raid_disks-1);
+ pd_idx = sector_div(stripe2, raid_disks-1);
if (*dd_idx >= pd_idx)
(*dd_idx)++;
qd_idx = raid_disks - 1;
break;
case ALGORITHM_LEFT_SYMMETRIC_6:
- pd_idx = data_disks - stripe % (raid_disks-1);
+ pd_idx = data_disks - sector_div(stripe2, raid_disks-1);
*dd_idx = (pd_idx + 1 + *dd_idx) % (raid_disks-1);
qd_idx = raid_disks - 1;
break;
case ALGORITHM_RIGHT_SYMMETRIC_6:
- pd_idx = stripe % (raid_disks-1);
+ pd_idx = sector_div(stripe2, raid_disks-1);
*dd_idx = (pd_idx + 1 + *dd_idx) % (raid_disks-1);
qd_idx = raid_disks - 1;
break;
@@ -1869,14 +1865,14 @@ static sector_t compute_blocknr(struct stripe_head *sh, int i, int previous)
: conf->algorithm;
sector_t stripe;
int chunk_offset;
- int chunk_number, dummy1, dd_idx = i;
+ sector_t chunk_number;
+ int dummy1, dd_idx = i;
sector_t r_sector;
struct stripe_head sh2;
chunk_offset = sector_div(new_sector, sectors_per_chunk);
stripe = new_sector;
- BUG_ON(new_sector != stripe);
if (i == sh->pd_idx)
return 0;
@@ -1969,7 +1965,7 @@ static sector_t compute_blocknr(struct stripe_head *sh, int i, int previous)
}
chunk_number = stripe * data_disks + i;
- r_sector = (sector_t)chunk_number * sectors_per_chunk + chunk_offset;
+ r_sector = chunk_number * sectors_per_chunk + chunk_offset;
check = raid5_compute_sector(conf, r_sector,
previous, &dummy1, &sh2);
@@ -5432,11 +5428,11 @@ static int raid5_start_reshape(mddev_t *mddev)
!test_bit(Faulty, &rdev->flags)) {
if (raid5_add_disk(mddev, rdev) == 0) {
char nm[20];
- if (rdev->raid_disk >= conf->previous_raid_disks)
+ if (rdev->raid_disk >= conf->previous_raid_disks) {
set_bit(In_sync, &rdev->flags);
- else
+ added_devices++;
+ } else
rdev->recovery_offset = 0;
- added_devices++;
sprintf(nm, "rd%d", rdev->raid_disk);
if (sysfs_create_link(&mddev->kobj,
&rdev->kobj, nm))
@@ -5448,9 +5444,12 @@ static int raid5_start_reshape(mddev_t *mddev)
break;
}
+ /* When a reshape changes the number of devices, ->degraded
+ * is measured against the large of the pre and post number of
+ * devices.*/
if (mddev->delta_disks > 0) {
spin_lock_irqsave(&conf->device_lock, flags);
- mddev->degraded = (conf->raid_disks - conf->previous_raid_disks)
+ mddev->degraded += (conf->raid_disks - conf->previous_raid_disks)
- added_devices;
spin_unlock_irqrestore(&conf->device_lock, flags);
}
generated by cgit v1.2.3 (git 2.0.4) at 2024-05-26 18:35:46 +0000