22 files changed, 323 insertions, 151 deletions

diff --git a/drivers/md/bitmap.c b/drivers/md/bitmap.c
index 3319c2fec28e..6986b0059d23 100644
--- a/drivers/md/bitmap.c
+++ b/drivers/md/bitmap.c
@@ -108,6 +108,8 @@ static void bitmap_free_page(struct bitmap *bitmap, unsigned char *page)
  * allocated while we're using it
  */
 static int bitmap_checkpage(struct bitmap *bitmap, unsigned long page, int create)
+__releases(bitmap->lock)
+__acquires(bitmap->lock)
 {
         unsigned char *mappage;
 
@@ -325,7 +327,6 @@ static int write_sb_page(struct bitmap *bitmap, struct page *page, int wait)
         return 0;
 
  bad_alignment:
-        rcu_read_unlock();
         return -EINVAL;
 }
 
@@ -1207,6 +1208,8 @@ void bitmap_daemon_work(struct bitmap *bitmap)
 static bitmap_counter_t *bitmap_get_counter(struct bitmap *bitmap,
                                             sector_t offset, int *blocks,
                                             int create)
+__releases(bitmap->lock)
+__acquires(bitmap->lock)
 {
         /* If 'create', we might release the lock and reclaim it.
          * The lock must have been taken with interrupts enabled.
diff --git a/drivers/md/dm-exception-store.c b/drivers/md/dm-exception-store.c
index 3710ff88fc10..556acff3952f 100644
--- a/drivers/md/dm-exception-store.c
+++ b/drivers/md/dm-exception-store.c
@@ -171,6 +171,14 @@ static int set_chunk_size(struct dm_exception_store *store,
          */
         chunk_size_ulong = round_up(chunk_size_ulong, PAGE_SIZE >> 9);
 
+        return dm_exception_store_set_chunk_size(store, chunk_size_ulong,
+                                                 error);
+}
+
+int dm_exception_store_set_chunk_size(struct dm_exception_store *store,
+                                      unsigned long chunk_size_ulong,
+                                      char **error)
+{
         /* Check chunk_size is a power of 2 */
         if (!is_power_of_2(chunk_size_ulong)) {
                 *error = "Chunk size is not a power of 2";
@@ -183,6 +191,11 @@ static int set_chunk_size(struct dm_exception_store *store,
                 return -EINVAL;
         }
 
+        if (chunk_size_ulong > INT_MAX >> SECTOR_SHIFT) {
+                *error = "Chunk size is too high";
+                return -EINVAL;
+        }
+
         store->chunk_size = chunk_size_ulong;
         store->chunk_mask = chunk_size_ulong - 1;
         store->chunk_shift = ffs(chunk_size_ulong) - 1;
diff --git a/drivers/md/dm-exception-store.h b/drivers/md/dm-exception-store.h
index 2442c8c07898..812c71872ba0 100644
--- a/drivers/md/dm-exception-store.h
+++ b/drivers/md/dm-exception-store.h
@@ -168,6 +168,10 @@ static inline chunk_t sector_to_chunk(struct dm_exception_store *store,
 int dm_exception_store_type_register(struct dm_exception_store_type *type);
 int dm_exception_store_type_unregister(struct dm_exception_store_type *type);
 
+int dm_exception_store_set_chunk_size(struct dm_exception_store *store,
+                                      unsigned long chunk_size_ulong,
+                                      char **error);
+
 int dm_exception_store_create(struct dm_target *ti, int argc, char **argv,
                               unsigned *args_used,
                               struct dm_exception_store **store);
diff --git a/drivers/md/dm-ioctl.c b/drivers/md/dm-ioctl.c
index 7f77f18fcafa..a67942931582 100644
--- a/drivers/md/dm-ioctl.c
+++ b/drivers/md/dm-ioctl.c
@@ -1532,7 +1532,7 @@ static const struct file_operations _ctl_fops = {
 static struct miscdevice _dm_misc = {
         .minor          = MISC_DYNAMIC_MINOR,
         .name           = DM_NAME,
-        .devnode        = "mapper/control",
+        .nodename       = "mapper/control",
         .fops           = &_ctl_fops
 };
 
diff --git a/drivers/md/dm-log-userspace-base.c b/drivers/md/dm-log-userspace-base.c
index e69b96560997..652bd33109e3 100644
--- a/drivers/md/dm-log-userspace-base.c
+++ b/drivers/md/dm-log-userspace-base.c
@@ -21,6 +21,7 @@ struct log_c {
         struct dm_target *ti;
         uint32_t region_size;
         region_t region_count;
+        uint64_t luid;
         char uuid[DM_UUID_LEN];
 
         char *usr_argv_str;
@@ -63,7 +64,7 @@ static int userspace_do_request(struct log_c *lc, const char *uuid,
          * restored.
          */
 retry:
-        r = dm_consult_userspace(uuid, request_type, data,
+        r = dm_consult_userspace(uuid, lc->luid, request_type, data,
                                  data_size, rdata, rdata_size);
 
         if (r != -ESRCH)
@@ -74,14 +75,15 @@ retry:
                 set_current_state(TASK_INTERRUPTIBLE);
                 schedule_timeout(2*HZ);
                 DMWARN("Attempting to contact userspace log server...");
-                r = dm_consult_userspace(uuid, DM_ULOG_CTR, lc->usr_argv_str,
+                r = dm_consult_userspace(uuid, lc->luid, DM_ULOG_CTR,
+                                         lc->usr_argv_str,
                                          strlen(lc->usr_argv_str) + 1,
                                          NULL, NULL);
                 if (!r)
                         break;
         }
         DMINFO("Reconnected to userspace log server... DM_ULOG_CTR complete");
-        r = dm_consult_userspace(uuid, DM_ULOG_RESUME, NULL,
+        r = dm_consult_userspace(uuid, lc->luid, DM_ULOG_RESUME, NULL,
                                  0, NULL, NULL);
         if (!r)
                 goto retry;
@@ -111,10 +113,9 @@ static int build_constructor_string(struct dm_target *ti,
                 return -ENOMEM;
         }
 
-        for (i = 0, str_size = 0; i < argc; i++)
-                str_size += sprintf(str + str_size, "%s ", argv[i]);
-        str_size += sprintf(str + str_size, "%llu",
-                            (unsigned long long)ti->len);
+        str_size = sprintf(str, "%llu", (unsigned long long)ti->len);
+        for (i = 0; i < argc; i++)
+                str_size += sprintf(str + str_size, " %s", argv[i]);
 
         *ctr_str = str;
         return str_size;
@@ -154,6 +155,9 @@ static int userspace_ctr(struct dm_dirty_log *log, struct dm_target *ti,
                 return -ENOMEM;
         }
 
+        /* The ptr value is sufficient for local unique id */
+        lc->luid = (uint64_t)lc;
+
         lc->ti = ti;
 
         if (strlen(argv[0]) > (DM_UUID_LEN - 1)) {
@@ -173,7 +177,7 @@ static int userspace_ctr(struct dm_dirty_log *log, struct dm_target *ti,
         }
 
         /* Send table string */
-        r = dm_consult_userspace(lc->uuid, DM_ULOG_CTR,
+        r = dm_consult_userspace(lc->uuid, lc->luid, DM_ULOG_CTR,
                                  ctr_str, str_size, NULL, NULL);
 
         if (r == -ESRCH) {
@@ -183,7 +187,7 @@ static int userspace_ctr(struct dm_dirty_log *log, struct dm_target *ti,
 
         /* Since the region size does not change, get it now */
         rdata_size = sizeof(rdata);
-        r = dm_consult_userspace(lc->uuid, DM_ULOG_GET_REGION_SIZE,
+        r = dm_consult_userspace(lc->uuid, lc->luid, DM_ULOG_GET_REGION_SIZE,
                                  NULL, 0, (char *)&rdata, &rdata_size);
 
         if (r) {
@@ -212,7 +216,7 @@ static void userspace_dtr(struct dm_dirty_log *log)
         int r;
         struct log_c *lc = log->context;
 
-        r = dm_consult_userspace(lc->uuid, DM_ULOG_DTR,
+        r = dm_consult_userspace(lc->uuid, lc->luid, DM_ULOG_DTR,
                                  NULL, 0,
                                  NULL, NULL);
 
@@ -227,7 +231,7 @@ static int userspace_presuspend(struct dm_dirty_log *log)
         int r;
         struct log_c *lc = log->context;
 
-        r = dm_consult_userspace(lc->uuid, DM_ULOG_PRESUSPEND,
+        r = dm_consult_userspace(lc->uuid, lc->luid, DM_ULOG_PRESUSPEND,
                                  NULL, 0,
                                  NULL, NULL);
 
@@ -239,7 +243,7 @@ static int userspace_postsuspend(struct dm_dirty_log *log)
         int r;
         struct log_c *lc = log->context;
 
-        r = dm_consult_userspace(lc->uuid, DM_ULOG_POSTSUSPEND,
+        r = dm_consult_userspace(lc->uuid, lc->luid, DM_ULOG_POSTSUSPEND,
                                  NULL, 0,
                                  NULL, NULL);
 
@@ -252,7 +256,7 @@ static int userspace_resume(struct dm_dirty_log *log)
         struct log_c *lc = log->context;
 
         lc->in_sync_hint = 0;
-        r = dm_consult_userspace(lc->uuid, DM_ULOG_RESUME,
+        r = dm_consult_userspace(lc->uuid, lc->luid, DM_ULOG_RESUME,
                                  NULL, 0,
                                  NULL, NULL);
 
@@ -561,6 +565,7 @@ static int userspace_status(struct dm_dirty_log *log, status_type_t status_type,
                             char *result, unsigned maxlen)
 {
         int r = 0;
+        char *table_args;
         size_t sz = (size_t)maxlen;
         struct log_c *lc = log->context;
 
@@ -577,8 +582,12 @@ static int userspace_status(struct dm_dirty_log *log, status_type_t status_type,
                 break;
         case STATUSTYPE_TABLE:
                 sz = 0;
-                DMEMIT("%s %u %s %s", log->type->name, lc->usr_argc + 1,
-                       lc->uuid, lc->usr_argv_str);
+                table_args = strchr(lc->usr_argv_str, ' ');
+                BUG_ON(!table_args); /* There will always be a ' ' */
+                table_args++;
+
+                DMEMIT("%s %u %s %s ", log->type->name, lc->usr_argc,
+                       lc->uuid, table_args);
                 break;
         }
         return (r) ? 0 : (int)sz;
diff --git a/drivers/md/dm-log-userspace-transfer.c b/drivers/md/dm-log-userspace-transfer.c
index 0ca1ee768a1f..ba0edad2d048 100644
--- a/drivers/md/dm-log-userspace-transfer.c
+++ b/drivers/md/dm-log-userspace-transfer.c
@@ -108,7 +108,7 @@ static int fill_pkg(struct cn_msg *msg, struct dm_ulog_request *tfr)
                                 *(pkg->data_size) = 0;
                 } else if (tfr->data_size > *(pkg->data_size)) {
                         DMERR("Insufficient space to receive package [%u] "
-                              "(%u vs %lu)", tfr->request_type,
+                              "(%u vs %zu)", tfr->request_type,
                               tfr->data_size, *(pkg->data_size));
 
                         *(pkg->data_size) = 0;
@@ -147,7 +147,8 @@ static void cn_ulog_callback(void *data)
 
 /**
  * dm_consult_userspace
- * @uuid: log's uuid (must be DM_UUID_LEN in size)
+ * @uuid: log's universal unique identifier (must be DM_UUID_LEN in size)
+ * @luid: log's local unique identifier
  * @request_type:  found in include/linux/dm-log-userspace.h
  * @data: data to tx to the server
  * @data_size: size of data in bytes
@@ -163,7 +164,7 @@ static void cn_ulog_callback(void *data)
  *
  * Returns: 0 on success, -EXXX on failure
  **/
-int dm_consult_userspace(const char *uuid, int request_type,
+int dm_consult_userspace(const char *uuid, uint64_t luid, int request_type,
                          char *data, size_t data_size,
                          char *rdata, size_t *rdata_size)
 {
@@ -190,6 +191,7 @@ resend:
 
         memset(tfr, 0, DM_ULOG_PREALLOCED_SIZE - overhead_size);
         memcpy(tfr->uuid, uuid, DM_UUID_LEN);
+        tfr->luid = luid;
         tfr->seq = dm_ulog_seq++;
 
         /*
diff --git a/drivers/md/dm-log-userspace-transfer.h b/drivers/md/dm-log-userspace-transfer.h
index c26d8e4e2710..04ee874f9153 100644
--- a/drivers/md/dm-log-userspace-transfer.h
+++ b/drivers/md/dm-log-userspace-transfer.h
@@ -11,7 +11,7 @@
 
 int dm_ulog_tfr_init(void);
 void dm_ulog_tfr_exit(void);
-int dm_consult_userspace(const char *uuid, int request_type,
+int dm_consult_userspace(const char *uuid, uint64_t luid, int request_type,
                          char *data, size_t data_size,
                          char *rdata, size_t *rdata_size);
 
diff --git a/drivers/md/dm-mpath.c b/drivers/md/dm-mpath.c
index 6f0d90d4a541..32d0b878eccc 100644
--- a/drivers/md/dm-mpath.c
+++ b/drivers/md/dm-mpath.c
@@ -64,6 +64,7 @@ struct multipath {
         spinlock_t lock;
 
         const char *hw_handler_name;
+        char *hw_handler_params;
         unsigned nr_priority_groups;
         struct list_head priority_groups;
         unsigned pg_init_required;      /* pg_init needs calling? */
@@ -219,6 +220,7 @@ static void free_multipath(struct multipath *m)
         }
 
         kfree(m->hw_handler_name);
+        kfree(m->hw_handler_params);
         mempool_destroy(m->mpio_pool);
         kfree(m);
 }
@@ -615,6 +617,17 @@ static struct pgpath *parse_path(struct arg_set *as, struct path_selector *ps,
                         dm_put_device(ti, p->path.dev);
                         goto bad;
                 }
+
+                if (m->hw_handler_params) {
+                        r = scsi_dh_set_params(q, m->hw_handler_params);
+                        if (r < 0) {
+                                ti->error = "unable to set hardware "
+                                                        "handler parameters";
+                                scsi_dh_detach(q);
+                                dm_put_device(ti, p->path.dev);
+                                goto bad;
+                        }
+                }
         }
 
         r = ps->type->add_path(ps, &p->path, as->argc, as->argv, &ti->error);
@@ -705,6 +718,7 @@ static struct priority_group *parse_priority_group(struct arg_set *as,
 static int parse_hw_handler(struct arg_set *as, struct multipath *m)
 {
         unsigned hw_argc;
+        int ret;
         struct dm_target *ti = m->ti;
 
         static struct param _params[] = {
@@ -726,17 +740,33 @@ static int parse_hw_handler(struct arg_set *as, struct multipath *m)
         request_module("scsi_dh_%s", m->hw_handler_name);
         if (scsi_dh_handler_exist(m->hw_handler_name) == 0) {
                 ti->error = "unknown hardware handler type";
-                kfree(m->hw_handler_name);
-                m->hw_handler_name = NULL;
-                return -EINVAL;
+                ret = -EINVAL;
+                goto fail;
         }
 
-        if (hw_argc > 1)
-                DMWARN("Ignoring user-specified arguments for "
-                       "hardware handler \"%s\"", m->hw_handler_name);
+        if (hw_argc > 1) {
+                char *p;
+                int i, j, len = 4;
+
+                for (i = 0; i <= hw_argc - 2; i++)
+                        len += strlen(as->argv[i]) + 1;
+                p = m->hw_handler_params = kzalloc(len, GFP_KERNEL);
+                if (!p) {
+                        ti->error = "memory allocation failed";
+                        ret = -ENOMEM;
+                        goto fail;
+                }
+                j = sprintf(p, "%d", hw_argc - 1);
+                for (i = 0, p+=j+1; i <= hw_argc - 2; i++, p+=j+1)
+                        j = sprintf(p, "%s", as->argv[i]);
+        }
         consume(as, hw_argc - 1);
 
         return 0;
+fail:
+        kfree(m->hw_handler_name);
+        m->hw_handler_name = NULL;
+        return ret;
 }
 
 static int parse_features(struct arg_set *as, struct multipath *m)
diff --git a/drivers/md/dm-raid1.c b/drivers/md/dm-raid1.c
index 9726577cde49..cc9dc79b0784 100644
--- a/drivers/md/dm-raid1.c
+++ b/drivers/md/dm-raid1.c
@@ -648,7 +648,13 @@ static void do_writes(struct mirror_set *ms, struct bio_list *writes)
          */
         dm_rh_inc_pending(ms->rh, &sync);
         dm_rh_inc_pending(ms->rh, &nosync);
-        ms->log_failure = dm_rh_flush(ms->rh) ? 1 : 0;
+
+        /*
+         * If the flush fails on a previous call and succeeds here,
+         * we must not reset the log_failure variable.  We need
+         * userspace interaction to do that.
+         */
+        ms->log_failure = dm_rh_flush(ms->rh) ? 1 : ms->log_failure;
 
         /*
          * Dispatch io.
@@ -1123,7 +1129,7 @@ static int mirror_end_io(struct dm_target *ti, struct bio *bio,
         if (error == -EOPNOTSUPP)
                 goto out;
 
-        if ((error == -EWOULDBLOCK) && bio_rw_ahead(bio))
+        if ((error == -EWOULDBLOCK) && bio_rw_flagged(bio, BIO_RW_AHEAD))
                 goto out;
 
         if (unlikely(error)) {
diff --git a/drivers/md/dm-snap-persistent.c b/drivers/md/dm-snap-persistent.c
index 6e3fe4f14934..d5b2e08750d5 100644
--- a/drivers/md/dm-snap-persistent.c
+++ b/drivers/md/dm-snap-persistent.c
@@ -106,6 +106,13 @@ struct pstore {
         void *zero_area;
 
         /*
+         * An area used for header. The header can be written
+         * concurrently with metadata (when invalidating the snapshot),
+         * so it needs a separate buffer.
+         */
+        void *header_area;
+
+        /*
          * Used to keep track of which metadata area the data in
          * 'chunk' refers to.
          */
@@ -148,16 +155,27 @@ static int alloc_area(struct pstore *ps)
          */
         ps->area = vmalloc(len);
         if (!ps->area)
-                return r;
+                goto err_area;
 
         ps->zero_area = vmalloc(len);
-        if (!ps->zero_area) {
-                vfree(ps->area);
-                return r;
-        }
+        if (!ps->zero_area)
+                goto err_zero_area;
         memset(ps->zero_area, 0, len);
 
+        ps->header_area = vmalloc(len);
+        if (!ps->header_area)
+                goto err_header_area;
+
         return 0;
+
+err_header_area:
+        vfree(ps->zero_area);
+
+err_zero_area:
+        vfree(ps->area);
+
+err_area:
+        return r;
 }
 
 static void free_area(struct pstore *ps)
@@ -169,6 +187,10 @@ static void free_area(struct pstore *ps)
         if (ps->zero_area)
                 vfree(ps->zero_area);
         ps->zero_area = NULL;
+
+        if (ps->header_area)
+                vfree(ps->header_area);
+        ps->header_area = NULL;
 }
 
 struct mdata_req {
@@ -188,7 +210,8 @@ static void do_metadata(struct work_struct *work)
 /*
  * Read or write a chunk aligned and sized block of data from a device.
  */
-static int chunk_io(struct pstore *ps, chunk_t chunk, int rw, int metadata)
+static int chunk_io(struct pstore *ps, void *area, chunk_t chunk, int rw,
+                    int metadata)
 {
         struct dm_io_region where = {
                 .bdev = ps->store->cow->bdev,
@@ -198,7 +221,7 @@ static int chunk_io(struct pstore *ps, chunk_t chunk, int rw, int metadata)
         struct dm_io_request io_req = {
                 .bi_rw = rw,
                 .mem.type = DM_IO_VMA,
-                .mem.ptr.vma = ps->area,
+                .mem.ptr.vma = area,
                 .client = ps->io_client,
                 .notify.fn = NULL,
         };
@@ -240,7 +263,7 @@ static int area_io(struct pstore *ps, int rw)
 
         chunk = area_location(ps, ps->current_area);
 
-        r = chunk_io(ps, chunk, rw, 0);
+        r = chunk_io(ps, ps->area, chunk, rw, 0);
         if (r)
                 return r;
 
@@ -254,20 +277,7 @@ static void zero_memory_area(struct pstore *ps)
 
 static int zero_disk_area(struct pstore *ps, chunk_t area)
 {
-        struct dm_io_region where = {
-                .bdev = ps->store->cow->bdev,
-                .sector = ps->store->chunk_size * area_location(ps, area),
-                .count = ps->store->chunk_size,
-        };
-        struct dm_io_request io_req = {
-                .bi_rw = WRITE,
-                .mem.type = DM_IO_VMA,
-                .mem.ptr.vma = ps->zero_area,
-                .client = ps->io_client,
-                .notify.fn = NULL,
-        };
-
-        return dm_io(&io_req, 1, &where, NULL);
+        return chunk_io(ps, ps->zero_area, area_location(ps, area), WRITE, 0);
 }
 
 static int read_header(struct pstore *ps, int *new_snapshot)
@@ -276,6 +286,7 @@ static int read_header(struct pstore *ps, int *new_snapshot)
         struct disk_header *dh;
         chunk_t chunk_size;
         int chunk_size_supplied = 1;
+        char *chunk_err;
 
         /*
          * Use default chunk size (or hardsect_size, if larger) if none supplied
@@ -297,11 +308,11 @@ static int read_header(struct pstore *ps, int *new_snapshot)
         if (r)
                 return r;
 
-        r = chunk_io(ps, 0, READ, 1);
+        r = chunk_io(ps, ps->header_area, 0, READ, 1);
         if (r)
                 goto bad;
 
-        dh = (struct disk_header *) ps->area;
+        dh = ps->header_area;
 
         if (le32_to_cpu(dh->magic) == 0) {
                 *new_snapshot = 1;
@@ -319,20 +330,25 @@ static int read_header(struct pstore *ps, int *new_snapshot)
         ps->version = le32_to_cpu(dh->version);
         chunk_size = le32_to_cpu(dh->chunk_size);
 
-        if (!chunk_size_supplied || ps->store->chunk_size == chunk_size)
+        if (ps->store->chunk_size == chunk_size)
                 return 0;
 
-        DMWARN("chunk size %llu in device metadata overrides "
-               "table chunk size of %llu.",
-               (unsigned long long)chunk_size,
-               (unsigned long long)ps->store->chunk_size);
+        if (chunk_size_supplied)
+                DMWARN("chunk size %llu in device metadata overrides "
+                       "table chunk size of %llu.",
+                       (unsigned long long)chunk_size,
+                       (unsigned long long)ps->store->chunk_size);
 
         /* We had a bogus chunk_size. Fix stuff up. */
         free_area(ps);
 
-        ps->store->chunk_size = chunk_size;
-        ps->store->chunk_mask = chunk_size - 1;
-        ps->store->chunk_shift = ffs(chunk_size) - 1;
+        r = dm_exception_store_set_chunk_size(ps->store, chunk_size,
+                                              &chunk_err);
+        if (r) {
+                DMERR("invalid on-disk chunk size %llu: %s.",
+                      (unsigned long long)chunk_size, chunk_err);
+                return r;
+        }
 
         r = dm_io_client_resize(sectors_to_pages(ps->store->chunk_size),
                                 ps->io_client);
@@ -351,15 +367,15 @@ static int write_header(struct pstore *ps)
 {
         struct disk_header *dh;
 
-        memset(ps->area, 0, ps->store->chunk_size << SECTOR_SHIFT);
+        memset(ps->header_area, 0, ps->store->chunk_size << SECTOR_SHIFT);
 
-        dh = (struct disk_header *) ps->area;
+        dh = ps->header_area;
         dh->magic = cpu_to_le32(SNAP_MAGIC);
         dh->valid = cpu_to_le32(ps->valid);
         dh->version = cpu_to_le32(ps->version);
         dh->chunk_size = cpu_to_le32(ps->store->chunk_size);
 
-        return chunk_io(ps, 0, WRITE, 1);
+        return chunk_io(ps, ps->header_area, 0, WRITE, 1);
 }
 
 /*
@@ -679,6 +695,8 @@ static int persistent_ctr(struct dm_exception_store *store,
         ps->valid = 1;
         ps->version = SNAPSHOT_DISK_VERSION;
         ps->area = NULL;
+        ps->zero_area = NULL;
+        ps->header_area = NULL;
         ps->next_free = 2;      /* skipping the header and first area */
         ps->current_committed = 0;
 
diff --git a/drivers/md/dm-snap.c b/drivers/md/dm-snap.c
index d573165cd2b7..57f1bf7f3b7a 100644
--- a/drivers/md/dm-snap.c
+++ b/drivers/md/dm-snap.c
@@ -1176,6 +1176,15 @@ static int snapshot_status(struct dm_target *ti, status_type_t type,
         return 0;
 }
 
+static int snapshot_iterate_devices(struct dm_target *ti,
+                                    iterate_devices_callout_fn fn, void *data)
+{
+        struct dm_snapshot *snap = ti->private;
+
+        return fn(ti, snap->origin, 0, ti->len, data);
+}
+
+
 /*-----------------------------------------------------------------
  * Origin methods
  *---------------------------------------------------------------*/
@@ -1410,20 +1419,29 @@ static int origin_status(struct dm_target *ti, status_type_t type, char *result,
         return 0;
 }
 
+static int origin_iterate_devices(struct dm_target *ti,
+                                  iterate_devices_callout_fn fn, void *data)
+{
+        struct dm_dev *dev = ti->private;
+
+        return fn(ti, dev, 0, ti->len, data);
+}
+
 static struct target_type origin_target = {
         .name    = "snapshot-origin",
-        .version = {1, 6, 0},
+        .version = {1, 7, 0},
         .module  = THIS_MODULE,
         .ctr     = origin_ctr,
         .dtr     = origin_dtr,
         .map     = origin_map,
         .resume  = origin_resume,
         .status  = origin_status,
+        .iterate_devices = origin_iterate_devices,
 };
 
 static struct target_type snapshot_target = {
         .name    = "snapshot",
-        .version = {1, 6, 0},
+        .version = {1, 7, 0},
         .module  = THIS_MODULE,
         .ctr     = snapshot_ctr,
         .dtr     = snapshot_dtr,
@@ -1431,6 +1449,7 @@ static struct target_type snapshot_target = {
         .end_io  = snapshot_end_io,
         .resume  = snapshot_resume,
         .status  = snapshot_status,
+        .iterate_devices = snapshot_iterate_devices,
 };
 
 static int __init dm_snapshot_init(void)
diff --git a/drivers/md/dm-stripe.c b/drivers/md/dm-stripe.c
index 4e0e5937e42a..e0efc1adcaff 100644
--- a/drivers/md/dm-stripe.c
+++ b/drivers/md/dm-stripe.c
@@ -285,7 +285,7 @@ static int stripe_end_io(struct dm_target *ti, struct bio *bio,
         if (!error)
                 return 0; /* I/O complete */
 
-        if ((error == -EWOULDBLOCK) && bio_rw_ahead(bio))
+        if ((error == -EWOULDBLOCK) && bio_rw_flagged(bio, BIO_RW_AHEAD))
                 return error;
 
         if (error == -EOPNOTSUPP)
@@ -329,9 +329,19 @@ static int stripe_iterate_devices(struct dm_target *ti,
         return ret;
 }
 
+static void stripe_io_hints(struct dm_target *ti,
+                            struct queue_limits *limits)
+{
+        struct stripe_c *sc = ti->private;
+        unsigned chunk_size = (sc->chunk_mask + 1) << 9;
+
+        blk_limits_io_min(limits, chunk_size);
+        blk_limits_io_opt(limits, chunk_size * sc->stripes);
+}
+
 static struct target_type stripe_target = {
         .name   = "striped",
-        .version = {1, 2, 0},
+        .version = {1, 3, 0},
         .module = THIS_MODULE,
         .ctr    = stripe_ctr,
         .dtr    = stripe_dtr,
@@ -339,6 +349,7 @@ static struct target_type stripe_target = {
         .end_io = stripe_end_io,
         .status = stripe_status,
         .iterate_devices = stripe_iterate_devices,
+        .io_hints = stripe_io_hints,
 };
 
 int __init dm_stripe_init(void)
diff --git a/drivers/md/dm-table.c b/drivers/md/dm-table.c
index d952b3441913..1a6cb3c7822e 100644
--- a/drivers/md/dm-table.c
+++ b/drivers/md/dm-table.c
@@ -343,10 +343,10 @@ static void close_dev(struct dm_dev_internal *d, struct mapped_device *md)
 }
 
 /*
- * If possible, this checks an area of a destination device is valid.
+ * If possible, this checks an area of a destination device is invalid.
  */
-static int device_area_is_valid(struct dm_target *ti, struct dm_dev *dev,
-                                sector_t start, sector_t len, void *data)
+static int device_area_is_invalid(struct dm_target *ti, struct dm_dev *dev,
+                                  sector_t start, sector_t len, void *data)
 {
         struct queue_limits *limits = data;
         struct block_device *bdev = dev->bdev;
@@ -357,36 +357,40 @@ static int device_area_is_valid(struct dm_target *ti, struct dm_dev *dev,
         char b[BDEVNAME_SIZE];
 
         if (!dev_size)
-                return 1;
+                return 0;
 
         if ((start >= dev_size) || (start + len > dev_size)) {
-                DMWARN("%s: %s too small for target",
-                       dm_device_name(ti->table->md), bdevname(bdev, b));
-                return 0;
+                DMWARN("%s: %s too small for target: "
+                       "start=%llu, len=%llu, dev_size=%llu",
+                       dm_device_name(ti->table->md), bdevname(bdev, b),
+                       (unsigned long long)start,
+                       (unsigned long long)len,
+                       (unsigned long long)dev_size);
+                return 1;
         }
 
         if (logical_block_size_sectors <= 1)
-                return 1;
+                return 0;
 
         if (start & (logical_block_size_sectors - 1)) {
                 DMWARN("%s: start=%llu not aligned to h/w "
-                       "logical block size %hu of %s",
+                       "logical block size %u of %s",
                        dm_device_name(ti->table->md),
                        (unsigned long long)start,
                        limits->logical_block_size, bdevname(bdev, b));
-                return 0;
+                return 1;
         }
 
         if (len & (logical_block_size_sectors - 1)) {
                 DMWARN("%s: len=%llu not aligned to h/w "
-                       "logical block size %hu of %s",
+                       "logical block size %u of %s",
                        dm_device_name(ti->table->md),
                        (unsigned long long)len,
                        limits->logical_block_size, bdevname(bdev, b));
-                return 0;
+                return 1;
         }
 
-        return 1;
+        return 0;
 }
 
 /*
@@ -496,8 +500,15 @@ int dm_set_device_limits(struct dm_target *ti, struct dm_dev *dev,
         }
 
         if (blk_stack_limits(limits, &q->limits, start << 9) < 0)
-                DMWARN("%s: target device %s is misaligned",
-                       dm_device_name(ti->table->md), bdevname(bdev, b));
+                DMWARN("%s: target device %s is misaligned: "
+                       "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);
+
 
         /*
          * Check if merge fn is supported.
@@ -698,7 +709,7 @@ static int validate_hardware_logical_block_alignment(struct dm_table *table,
 
         if (remaining) {
                 DMWARN("%s: table line %u (start sect %llu len %llu) "
-                       "not aligned to h/w logical block size %hu",
+                       "not aligned to h/w logical block size %u",
                        dm_device_name(table->md), i,
                        (unsigned long long) ti->begin,
                        (unsigned long long) ti->len,
@@ -996,12 +1007,16 @@ int dm_calculate_queue_limits(struct dm_table *table,
                 ti->type->iterate_devices(ti, dm_set_device_limits,
                                           &ti_limits);
 
+                /* Set I/O hints portion of queue limits */
+                if (ti->type->io_hints)
+                        ti->type->io_hints(ti, &ti_limits);
+
                 /*
                  * Check each device area is consistent with the target's
                  * overall queue limits.
                  */
-                if (!ti->type->iterate_devices(ti, device_area_is_valid,
-                                               &ti_limits))
+                if (ti->type->iterate_devices(ti, device_area_is_invalid,
+                                              &ti_limits))
                         return -EINVAL;
 
 combine_limits:
diff --git a/drivers/md/dm.c b/drivers/md/dm.c
index 8a311ea0d441..376f1ab48a24 100644
--- a/drivers/md/dm.c
+++ b/drivers/md/dm.c
@@ -130,7 +130,7 @@ struct mapped_device {
         /*
          * A list of ios that arrived while we were suspended.
          */
-        atomic_t pending;
+        atomic_t pending[2];
         wait_queue_head_t wait;
         struct work_struct work;
         struct bio_list deferred;
@@ -453,13 +453,14 @@ static void start_io_acct(struct dm_io *io)
 {
         struct mapped_device *md = io->md;
         int cpu;
+        int rw = bio_data_dir(io->bio);
 
         io->start_time = jiffies;
 
         cpu = part_stat_lock();
         part_round_stats(cpu, &dm_disk(md)->part0);
         part_stat_unlock();
-        dm_disk(md)->part0.in_flight = atomic_inc_return(&md->pending);
+        dm_disk(md)->part0.in_flight[rw] = atomic_inc_return(&md->pending[rw]);
 }
 
 static void end_io_acct(struct dm_io *io)
@@ -479,8 +480,9 @@ static void end_io_acct(struct dm_io *io)
          * After this is decremented the bio must not be touched if it is
          * a barrier.
          */
-        dm_disk(md)->part0.in_flight = pending =
-                atomic_dec_return(&md->pending);
+        dm_disk(md)->part0.in_flight[rw] = pending =
+                atomic_dec_return(&md->pending[rw]);
+        pending += atomic_read(&md->pending[rw^0x1]);
 
         /* nudge anyone waiting on suspend queue */
         if (!pending)
@@ -586,7 +588,7 @@ static void dec_pending(struct dm_io *io, int error)
                          */
                         spin_lock_irqsave(&md->deferred_lock, flags);
                         if (__noflush_suspending(md)) {
-                                if (!bio_barrier(io->bio))
+                                if (!bio_rw_flagged(io->bio, BIO_RW_BARRIER))
                                         bio_list_add_head(&md->deferred,
                                                           io->bio);
                         } else
@@ -598,7 +600,7 @@ static void dec_pending(struct dm_io *io, int error)
                 io_error = io->error;
                 bio = io->bio;
 
-                if (bio_barrier(bio)) {
+                if (bio_rw_flagged(bio, BIO_RW_BARRIER)) {
                         /*
                          * There can be just one barrier request so we use
                          * a per-device variable for error reporting.
@@ -738,16 +740,22 @@ static void rq_completed(struct mapped_device *md, int run_queue)
         dm_put(md);
 }
 
+static void free_rq_clone(struct request *clone)
+{
+        struct dm_rq_target_io *tio = clone->end_io_data;
+
+        blk_rq_unprep_clone(clone);
+        free_rq_tio(tio);
+}
+
 static void dm_unprep_request(struct request *rq)
 {
         struct request *clone = rq->special;
-        struct dm_rq_target_io *tio = clone->end_io_data;
 
         rq->special = NULL;
         rq->cmd_flags &= ~REQ_DONTPREP;
 
-        blk_rq_unprep_clone(clone);
-        free_rq_tio(tio);
+        free_rq_clone(clone);
 }
 
 /*
@@ -825,8 +833,7 @@ static void dm_end_request(struct request *clone, int error)
                         rq->sense_len = clone->sense_len;
         }
 
-        BUG_ON(clone->bio);
-        free_rq_tio(tio);
+        free_rq_clone(clone);
 
         blk_end_request_all(rq, error);
 
@@ -1204,7 +1211,7 @@ static void __split_and_process_bio(struct mapped_device *md, struct bio *bio)
 
         ci.map = dm_get_table(md);
         if (unlikely(!ci.map)) {
-                if (!bio_barrier(bio))
+                if (!bio_rw_flagged(bio, BIO_RW_BARRIER))
                         bio_io_error(bio);
                 else
                         if (!md->barrier_error)
@@ -1316,7 +1323,7 @@ static int _dm_request(struct request_queue *q, struct bio *bio)
          * we have to queue this io for later.
          */
         if (unlikely(test_bit(DMF_QUEUE_IO_TO_THREAD, &md->flags)) ||
-            unlikely(bio_barrier(bio))) {
+            unlikely(bio_rw_flagged(bio, BIO_RW_BARRIER))) {
                 up_read(&md->io_lock);
 
                 if (unlikely(test_bit(DMF_BLOCK_IO_FOR_SUSPEND, &md->flags)) &&
@@ -1339,7 +1346,7 @@ static int dm_make_request(struct request_queue *q, struct bio *bio)
 {
         struct mapped_device *md = q->queuedata;
 
-        if (unlikely(bio_barrier(bio))) {
+        if (unlikely(bio_rw_flagged(bio, BIO_RW_BARRIER))) {
                 bio_endio(bio, -EOPNOTSUPP);
                 return 0;
         }
@@ -1709,7 +1716,7 @@ out:
         return r;
 }
 
-static struct block_device_operations dm_blk_dops;
+static const struct block_device_operations dm_blk_dops;
 
 static void dm_wq_work(struct work_struct *work);
 
@@ -1780,7 +1787,8 @@ static struct mapped_device *alloc_dev(int minor)
         if (!md->disk)
                 goto bad_disk;
 
-        atomic_set(&md->pending, 0);
+        atomic_set(&md->pending[0], 0);
+        atomic_set(&md->pending[1], 0);
         init_waitqueue_head(&md->wait);
         INIT_WORK(&md->work, dm_wq_work);
         init_waitqueue_head(&md->eventq);
@@ -2083,7 +2091,8 @@ static int dm_wait_for_completion(struct mapped_device *md, int interruptible)
                                 break;
                         }
                         spin_unlock_irqrestore(q->queue_lock, flags);
-                } else if (!atomic_read(&md->pending))
+                } else if (!atomic_read(&md->pending[0]) &&
+                                        !atomic_read(&md->pending[1]))
                         break;
 
                 if (interruptible == TASK_INTERRUPTIBLE &&
@@ -2159,7 +2168,7 @@ static void dm_wq_work(struct work_struct *work)
                 if (dm_request_based(md))
                         generic_make_request(c);
                 else {
-                        if (bio_barrier(c))
+                        if (bio_rw_flagged(c, BIO_RW_BARRIER))
                                 process_barrier(md, c);
                         else
                                 __split_and_process_bio(md, c);
@@ -2654,7 +2663,7 @@ void dm_free_md_mempools(struct dm_md_mempools *pools)
         kfree(pools);
 }
 
-static struct block_device_operations dm_blk_dops = {
+static const struct block_device_operations dm_blk_dops = {
         .open = dm_blk_open,
         .release = dm_blk_close,
         .ioctl = dm_blk_ioctl,
diff --git a/drivers/md/linear.c b/drivers/md/linear.c
index 5fe39c2a3d2b..1ceceb334d5e 100644
--- a/drivers/md/linear.c
+++ b/drivers/md/linear.c
@@ -108,6 +108,9 @@ static int linear_congested(void *data, int bits)
         linear_conf_t *conf;
         int i, ret = 0;
 
+        if (mddev_congested(mddev, bits))
+                return 1;
+
         rcu_read_lock();
         conf = rcu_dereference(mddev->private);
 
@@ -288,7 +291,7 @@ static int linear_make_request (struct request_queue *q, struct bio *bio)
         sector_t start_sector;
         int cpu;
 
-        if (unlikely(bio_barrier(bio))) {
+        if (unlikely(bio_rw_flagged(bio, BIO_RW_BARRIER))) {
                 bio_endio(bio, -EOPNOTSUPP);
                 return 0;
         }
diff --git a/drivers/md/md.c b/drivers/md/md.c
index 9dd872000cec..26ba42a79129 100644
--- a/drivers/md/md.c
+++ b/drivers/md/md.c
@@ -138,7 +138,7 @@ static ctl_table raid_root_table[] = {
         { .ctl_name = 0 }
 };
 
-static struct block_device_operations md_fops;
+static const struct block_device_operations md_fops;
 
 static int start_readonly;
 
@@ -262,6 +262,12 @@ static void mddev_resume(mddev_t *mddev)
         mddev->pers->quiesce(mddev, 0);
 }
 
+int mddev_congested(mddev_t *mddev, int bits)
+{
+        return mddev->suspended;
+}
+EXPORT_SYMBOL(mddev_congested);
+
 
 static inline mddev_t *mddev_get(mddev_t *mddev)
 {
@@ -4218,7 +4224,7 @@ static int do_md_run(mddev_t * mddev)
                         set_bit(MD_RECOVERY_RUNNING, &mddev->recovery);
                         mddev->sync_thread = md_register_thread(md_do_sync,
                                                                 mddev,
-                                                                "%s_resync");
+                                                                "resync");
                         if (!mddev->sync_thread) {
                                 printk(KERN_ERR "%s: could not start resync"
                                        " thread...\n",
@@ -4575,10 +4581,10 @@ static int get_version(void __user * arg)
 static int get_array_info(mddev_t * mddev, void __user * arg)
 {
         mdu_array_info_t info;
-        int nr,working,active,failed,spare;
+        int nr,working,insync,failed,spare;
         mdk_rdev_t *rdev;
 
-        nr=working=active=failed=spare=0;
+        nr=working=insync=failed=spare=0;
         list_for_each_entry(rdev, &mddev->disks, same_set) {
                 nr++;
                 if (test_bit(Faulty, &rdev->flags))
@@ -4586,7 +4592,7 @@ static int get_array_info(mddev_t * mddev, void __user * arg)
                 else {
                         working++;
                         if (test_bit(In_sync, &rdev->flags))
-                                active++;       
+                                insync++;       
                         else
                                 spare++;
                 }
@@ -4611,7 +4617,7 @@ static int get_array_info(mddev_t * mddev, void __user * arg)
                 info.state = (1<<MD_SB_CLEAN);
         if (mddev->bitmap && mddev->bitmap_offset)
                 info.state = (1<<MD_SB_BITMAP_PRESENT);
-        info.active_disks  = active;
+        info.active_disks  = insync;
         info.working_disks = working;
         info.failed_disks  = failed;
         info.spare_disks   = spare;
@@ -4721,7 +4727,7 @@ static int add_new_disk(mddev_t * mddev, mdu_disk_info_t *info)
                 if (!list_empty(&mddev->disks)) {
                         mdk_rdev_t *rdev0 = list_entry(mddev->disks.next,
                                                         mdk_rdev_t, same_set);
-                        int err = super_types[mddev->major_version]
+                        err = super_types[mddev->major_version]
                                 .load_super(rdev, rdev0, mddev->minor_version);
                         if (err < 0) {
                                 printk(KERN_WARNING 
@@ -5556,7 +5562,7 @@ static int md_revalidate(struct gendisk *disk)
         mddev->changed = 0;
         return 0;
 }
-static struct block_device_operations md_fops =
+static const struct block_device_operations md_fops =
 {
         .owner          = THIS_MODULE,
         .open           = md_open,
@@ -5631,7 +5637,10 @@ mdk_thread_t *md_register_thread(void (*run) (mddev_t *), mddev_t *mddev,
         thread->run = run;
         thread->mddev = mddev;
         thread->timeout = MAX_SCHEDULE_TIMEOUT;
-        thread->tsk = kthread_run(md_thread, thread, name, mdname(thread->mddev));
+        thread->tsk = kthread_run(md_thread, thread,
+                                  "%s_%s",
+                                  mdname(thread->mddev),
+                                  name ?: mddev->pers->name);
         if (IS_ERR(thread->tsk)) {
                 kfree(thread);
                 return NULL;
@@ -6745,7 +6754,7 @@ void md_check_recovery(mddev_t *mddev)
                         }
                         mddev->sync_thread = md_register_thread(md_do_sync,
                                                                 mddev,
-                                                                "%s_resync");
+                                                                "resync");
                         if (!mddev->sync_thread) {
                                 printk(KERN_ERR "%s: could not start resync"
                                         " thread...\n", 
diff --git a/drivers/md/md.h b/drivers/md/md.h
index f8fc188bc762..f184b69ef337 100644
--- a/drivers/md/md.h
+++ b/drivers/md/md.h
@@ -201,7 +201,7 @@ struct mddev_s
          * INTR:     resync needs to be aborted for some reason
          * DONE:     thread is done and is waiting to be reaped
          * REQUEST:  user-space has requested a sync (used with SYNC)
-         * CHECK:    user-space request for for check-only, no repair
+         * CHECK:    user-space request for check-only, no repair
          * RESHAPE:  A reshape is happening
          *
          * If neither SYNC or RESHAPE are set, then it is a recovery.
@@ -430,6 +430,7 @@ extern void md_write_end(mddev_t *mddev);
 extern void md_done_sync(mddev_t *mddev, int blocks, int ok);
 extern void md_error(mddev_t *mddev, mdk_rdev_t *rdev);
 
+extern int mddev_congested(mddev_t *mddev, int bits);
 extern void md_super_write(mddev_t *mddev, mdk_rdev_t *rdev,
                            sector_t sector, int size, struct page *page);
 extern void md_super_wait(mddev_t *mddev);
diff --git a/drivers/md/multipath.c b/drivers/md/multipath.c
index 7140909f6662..ee7646f974a0 100644
--- a/drivers/md/multipath.c
+++ b/drivers/md/multipath.c
@@ -90,7 +90,7 @@ static void multipath_end_request(struct bio *bio, int error)
 
         if (uptodate)
                 multipath_end_bh_io(mp_bh, 0);
-        else if (!bio_rw_ahead(bio)) {
+        else if (!bio_rw_flagged(bio, BIO_RW_AHEAD)) {
                 /*
                  * oops, IO error:
                  */
@@ -144,7 +144,7 @@ static int multipath_make_request (struct request_queue *q, struct bio * bio)
         const int rw = bio_data_dir(bio);
         int cpu;
 
-        if (unlikely(bio_barrier(bio))) {
+        if (unlikely(bio_rw_flagged(bio, BIO_RW_BARRIER))) {
                 bio_endio(bio, -EOPNOTSUPP);
                 return 0;
         }
@@ -198,6 +198,9 @@ static int multipath_congested(void *data, int bits)
         multipath_conf_t *conf = mddev->private;
         int i, ret = 0;
 
+        if (mddev_congested(mddev, bits))
+                return 1;
+
         rcu_read_lock();
         for (i = 0; i < mddev->raid_disks ; i++) {
                 mdk_rdev_t *rdev = rcu_dereference(conf->multipaths[i].rdev);
@@ -493,7 +496,7 @@ static int multipath_run (mddev_t *mddev)
         }
         mddev->degraded = conf->raid_disks - conf->working_disks;
 
-        conf->pool = mempool_create_kzalloc_pool(NR_RESERVED_BUFS,
+        conf->pool = mempool_create_kmalloc_pool(NR_RESERVED_BUFS,
                                                  sizeof(struct multipath_bh));
         if (conf->pool == NULL) {
                 printk(KERN_ERR 
@@ -503,7 +506,7 @@ static int multipath_run (mddev_t *mddev)
         }
 
         {
-                mddev->thread = md_register_thread(multipathd, mddev, "%s_multipath");
+                mddev->thread = md_register_thread(multipathd, mddev, NULL);
                 if (!mddev->thread) {
                         printk(KERN_ERR "multipath: couldn't allocate thread"
                                 " for %s\n", mdname(mddev));
diff --git a/drivers/md/raid0.c b/drivers/md/raid0.c
index 898e2bdfee47..d3a4ce06015a 100644
--- a/drivers/md/raid0.c
+++ b/drivers/md/raid0.c
@@ -44,6 +44,9 @@ static int raid0_congested(void *data, int bits)
         mdk_rdev_t **devlist = conf->devlist;
         int i, ret = 0;
 
+        if (mddev_congested(mddev, bits))
+                return 1;
+
         for (i = 0; i < mddev->raid_disks && !ret ; i++) {
                 struct request_queue *q = bdev_get_queue(devlist[i]->bdev);
 
@@ -86,7 +89,7 @@ static void dump_zones(mddev_t *mddev)
 
 static int create_strip_zones(mddev_t *mddev)
 {
-        int i, c, j, err;
+        int i, c, err;
         sector_t curr_zone_end, sectors;
         mdk_rdev_t *smallest, *rdev1, *rdev2, *rdev, **dev;
         struct strip_zone *zone;
@@ -198,6 +201,8 @@ static int create_strip_zones(mddev_t *mddev)
         /* now do the other zones */
         for (i = 1; i < conf->nr_strip_zones; i++)
         {
+                int j;
+
                 zone = conf->strip_zone + i;
                 dev = conf->devlist + i * mddev->raid_disks;
 
@@ -207,7 +212,6 @@ static int create_strip_zones(mddev_t *mddev)
                 c = 0;
 
                 for (j=0; j<cnt; j++) {
-                        char b[BDEVNAME_SIZE];
                         rdev = conf->devlist[j];
                         printk(KERN_INFO "raid0: checking %s ...",
                                 bdevname(rdev->bdev, b));
@@ -448,7 +452,7 @@ static int raid0_make_request(struct request_queue *q, struct bio *bio)
         const int rw = bio_data_dir(bio);
         int cpu;
 
-        if (unlikely(bio_barrier(bio))) {
+        if (unlikely(bio_rw_flagged(bio, BIO_RW_BARRIER))) {
                 bio_endio(bio, -EOPNOTSUPP);
                 return 0;
         }
diff --git a/drivers/md/raid1.c b/drivers/md/raid1.c
index 8726fd7ebce5..d1b9bd5fd4f6 100644
--- a/drivers/md/raid1.c
+++ b/drivers/md/raid1.c
@@ -576,6 +576,9 @@ static int raid1_congested(void *data, int bits)
         conf_t *conf = mddev->private;
         int i, ret = 0;
 
+        if (mddev_congested(mddev, bits))
+                return 1;
+
         rcu_read_lock();
         for (i = 0; i < mddev->raid_disks; i++) {
                 mdk_rdev_t *rdev = rcu_dereference(conf->mirrors[i].rdev);
@@ -782,8 +785,9 @@ static int make_request(struct request_queue *q, struct bio * bio)
         struct bio_list bl;
         struct page **behind_pages = NULL;
         const int rw = bio_data_dir(bio);
-        const int do_sync = bio_sync(bio);
-        int cpu, do_barriers;
+        const bool do_sync = bio_rw_flagged(bio, BIO_RW_SYNCIO);
+        int cpu;
+        bool do_barriers;
         mdk_rdev_t *blocked_rdev;
 
         /*
@@ -797,7 +801,8 @@ static int make_request(struct request_queue *q, struct bio * bio)
 
         md_write_start(mddev, bio); /* wait on superblock update early */
 
-        if (unlikely(!mddev->barriers_work && bio_barrier(bio))) {
+        if (unlikely(!mddev->barriers_work &&
+                     bio_rw_flagged(bio, BIO_RW_BARRIER))) {
                 if (rw == WRITE)
                         md_write_end(mddev);
                 bio_endio(bio, -EOPNOTSUPP);
@@ -849,7 +854,7 @@ static int make_request(struct request_queue *q, struct bio * bio)
                 read_bio->bi_sector = r1_bio->sector + mirror->rdev->data_offset;
                 read_bio->bi_bdev = mirror->rdev->bdev;
                 read_bio->bi_end_io = raid1_end_read_request;
-                read_bio->bi_rw = READ | do_sync;
+                read_bio->bi_rw = READ | (do_sync << BIO_RW_SYNCIO);
                 read_bio->bi_private = r1_bio;
 
                 generic_make_request(read_bio);
@@ -925,7 +930,7 @@ static int make_request(struct request_queue *q, struct bio * bio)
         atomic_set(&r1_bio->remaining, 0);
         atomic_set(&r1_bio->behind_remaining, 0);
 
-        do_barriers = bio_barrier(bio);
+        do_barriers = bio_rw_flagged(bio, BIO_RW_BARRIER);
         if (do_barriers)
                 set_bit(R1BIO_Barrier, &r1_bio->state);
 
@@ -941,7 +946,8 @@ static int make_request(struct request_queue *q, struct bio * bio)
                 mbio->bi_sector = r1_bio->sector + conf->mirrors[i].rdev->data_offset;
                 mbio->bi_bdev = conf->mirrors[i].rdev->bdev;
                 mbio->bi_end_io = raid1_end_write_request;
-                mbio->bi_rw = WRITE | do_barriers | do_sync;
+                mbio->bi_rw = WRITE | (do_barriers << BIO_RW_BARRIER) |
+                        (do_sync << BIO_RW_SYNCIO);
                 mbio->bi_private = r1_bio;
 
                 if (behind_pages) {
@@ -1600,7 +1606,7 @@ static void raid1d(mddev_t *mddev)
                          * We already have a nr_pending reference on these rdevs.
                          */
                         int i;
-                        const int do_sync = bio_sync(r1_bio->master_bio);
+                        const bool do_sync = bio_rw_flagged(r1_bio->master_bio, BIO_RW_SYNCIO);
                         clear_bit(R1BIO_BarrierRetry, &r1_bio->state);
                         clear_bit(R1BIO_Barrier, &r1_bio->state);
                         for (i=0; i < conf->raid_disks; i++)
@@ -1621,7 +1627,8 @@ static void raid1d(mddev_t *mddev)
                                                 conf->mirrors[i].rdev->data_offset;
                                         bio->bi_bdev = conf->mirrors[i].rdev->bdev;
                                         bio->bi_end_io = raid1_end_write_request;
-                                        bio->bi_rw = WRITE | do_sync;
+                                        bio->bi_rw = WRITE |
+                                                (do_sync << BIO_RW_SYNCIO);
                                         bio->bi_private = r1_bio;
                                         r1_bio->bios[i] = bio;
                                         generic_make_request(bio);
@@ -1654,7 +1661,7 @@ static void raid1d(mddev_t *mddev)
                                        (unsigned long long)r1_bio->sector);
                                 raid_end_bio_io(r1_bio);
                         } else {
-                                const int do_sync = bio_sync(r1_bio->master_bio);
+                                const bool do_sync = bio_rw_flagged(r1_bio->master_bio, BIO_RW_SYNCIO);
                                 r1_bio->bios[r1_bio->read_disk] =
                                         mddev->ro ? IO_BLOCKED : NULL;
                                 r1_bio->read_disk = disk;
@@ -1670,7 +1677,7 @@ static void raid1d(mddev_t *mddev)
                                 bio->bi_sector = r1_bio->sector + rdev->data_offset;
                                 bio->bi_bdev = rdev->bdev;
                                 bio->bi_end_io = raid1_end_read_request;
-                                bio->bi_rw = READ | do_sync;
+                                bio->bi_rw = READ | (do_sync << BIO_RW_SYNCIO);
                                 bio->bi_private = r1_bio;
                                 unplug = 1;
                                 generic_make_request(bio);
@@ -2045,7 +2052,7 @@ static int run(mddev_t *mddev)
         conf->last_used = j;
 
 
-        mddev->thread = md_register_thread(raid1d, mddev, "%s_raid1");
+        mddev->thread = md_register_thread(raid1d, mddev, NULL);
         if (!mddev->thread) {
                 printk(KERN_ERR
                        "raid1: couldn't allocate thread for %s\n",
diff --git a/drivers/md/raid10.c b/drivers/md/raid10.c
index 3d9020cf6f6e..51c4c5c4d87a 100644
--- a/drivers/md/raid10.c
+++ b/drivers/md/raid10.c
@@ -631,6 +631,8 @@ static int raid10_congested(void *data, int bits)
         conf_t *conf = mddev->private;
         int i, ret = 0;
 
+        if (mddev_congested(mddev, bits))
+                return 1;
         rcu_read_lock();
         for (i = 0; i < mddev->raid_disks && ret == 0; i++) {
                 mdk_rdev_t *rdev = rcu_dereference(conf->mirrors[i].rdev);
@@ -796,12 +798,12 @@ static int make_request(struct request_queue *q, struct bio * bio)
         int i;
         int chunk_sects = conf->chunk_mask + 1;
         const int rw = bio_data_dir(bio);
-        const int do_sync = bio_sync(bio);
+        const bool do_sync = bio_rw_flagged(bio, BIO_RW_SYNCIO);
         struct bio_list bl;
         unsigned long flags;
         mdk_rdev_t *blocked_rdev;
 
-        if (unlikely(bio_barrier(bio))) {
+        if (unlikely(bio_rw_flagged(bio, BIO_RW_BARRIER))) {
                 bio_endio(bio, -EOPNOTSUPP);
                 return 0;
         }
@@ -882,7 +884,7 @@ static int make_request(struct request_queue *q, struct bio * bio)
                         mirror->rdev->data_offset;
                 read_bio->bi_bdev = mirror->rdev->bdev;
                 read_bio->bi_end_io = raid10_end_read_request;
-                read_bio->bi_rw = READ | do_sync;
+                read_bio->bi_rw = READ | (do_sync << BIO_RW_SYNCIO);
                 read_bio->bi_private = r10_bio;
 
                 generic_make_request(read_bio);
@@ -950,7 +952,7 @@ static int make_request(struct request_queue *q, struct bio * bio)
                         conf->mirrors[d].rdev->data_offset;
                 mbio->bi_bdev = conf->mirrors[d].rdev->bdev;
                 mbio->bi_end_io = raid10_end_write_request;
-                mbio->bi_rw = WRITE | do_sync;
+                mbio->bi_rw = WRITE | (do_sync << BIO_RW_SYNCIO);
                 mbio->bi_private = r10_bio;
 
                 atomic_inc(&r10_bio->remaining);
@@ -1610,7 +1612,7 @@ static void raid10d(mddev_t *mddev)
                                 raid_end_bio_io(r10_bio);
                                 bio_put(bio);
                         } else {
-                                const int do_sync = bio_sync(r10_bio->master_bio);
+                                const bool do_sync = bio_rw_flagged(r10_bio->master_bio, BIO_RW_SYNCIO);
                                 bio_put(bio);
                                 rdev = conf->mirrors[mirror].rdev;
                                 if (printk_ratelimit())
@@ -1623,7 +1625,7 @@ static void raid10d(mddev_t *mddev)
                                 bio->bi_sector = r10_bio->devs[r10_bio->read_slot].addr
                                         + rdev->data_offset;
                                 bio->bi_bdev = rdev->bdev;
-                                bio->bi_rw = READ | do_sync;
+                                bio->bi_rw = READ | (do_sync << BIO_RW_SYNCIO);
                                 bio->bi_private = r10_bio;
                                 bio->bi_end_io = raid10_end_read_request;
                                 unplug = 1;
@@ -1773,7 +1775,7 @@ static sector_t sync_request(mddev_t *mddev, sector_t sector_nr, int *skipped, i
         max_sync = RESYNC_PAGES << (PAGE_SHIFT-9);
         if (!test_bit(MD_RECOVERY_SYNC, &mddev->recovery)) {
                 /* recovery... the complicated one */
-                int i, j, k;
+                int j, k;
                 r10_bio = NULL;
 
                 for (i=0 ; i<conf->raid_disks; i++)
@@ -2188,7 +2190,7 @@ static int run(mddev_t *mddev)
         }
 
 
-        mddev->thread = md_register_thread(raid10d, mddev, "%s_raid10");
+        mddev->thread = md_register_thread(raid10d, mddev, NULL);
         if (!mddev->thread) {
                 printk(KERN_ERR
                        "raid10: couldn't allocate thread for %s\n",
diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c
index 1898eda60722..94829804ab7f 100644
--- a/drivers/md/raid5.c
+++ b/drivers/md/raid5.c
@@ -2924,7 +2924,8 @@ static bool handle_stripe5(struct stripe_head *sh)
         rcu_read_lock();
         for (i=disks; i--; ) {
                 mdk_rdev_t *rdev;
-                struct r5dev *dev = &sh->dev[i];
+
+                dev = &sh->dev[i];
                 clear_bit(R5_Insync, &dev->flags);
 
                 pr_debug("check %d: state 0x%lx toread %p read %p write %p "
@@ -3548,6 +3549,9 @@ static int raid5_congested(void *data, int bits)
         /* No difference between reads and writes.  Just check
          * how busy the stripe_cache is
          */
+
+        if (mddev_congested(mddev, bits))
+                return 1;
         if (conf->inactive_blocked)
                 return 1;
         if (conf->quiesce)
@@ -3823,7 +3827,7 @@ static int make_request(struct request_queue *q, struct bio * bi)
         const int rw = bio_data_dir(bi);
         int cpu, remaining;
 
-        if (unlikely(bio_barrier(bi))) {
+        if (unlikely(bio_rw_flagged(bi, BIO_RW_BARRIER))) {
                 bio_endio(bi, -EOPNOTSUPP);
                 return 0;
         }
@@ -4097,7 +4101,7 @@ static sector_t reshape_request(mddev_t *mddev, sector_t sector_nr, int *skipped
         INIT_LIST_HEAD(&stripes);
         for (i = 0; i < reshape_sectors; i += STRIPE_SECTORS) {
                 int j;
-                int skipped = 0;
+                int skipped_disk = 0;
                 sh = get_active_stripe(conf, stripe_addr+i, 0, 0, 1);
                 set_bit(STRIPE_EXPANDING, &sh->state);
                 atomic_inc(&conf->reshape_stripes);
@@ -4113,14 +4117,14 @@ static sector_t reshape_request(mddev_t *mddev, sector_t sector_nr, int *skipped
                                 continue;
                         s = compute_blocknr(sh, j, 0);
                         if (s < raid5_size(mddev, 0, 0)) {
-                                skipped = 1;
+                                skipped_disk = 1;
                                 continue;
                         }
                         memset(page_address(sh->dev[j].page), 0, STRIPE_SIZE);
                         set_bit(R5_Expanded, &sh->dev[j].flags);
                         set_bit(R5_UPTODATE, &sh->dev[j].flags);
                 }
-                if (!skipped) {
+                if (!skipped_disk) {
                         set_bit(STRIPE_EXPAND_READY, &sh->state);
                         set_bit(STRIPE_HANDLE, &sh->state);
                 }
@@ -4798,7 +4802,7 @@ static raid5_conf_t *setup_conf(mddev_t *mddev)
                 printk(KERN_INFO "raid5: allocated %dkB for %s\n",
                         memory, mdname(mddev));
 
-        conf->thread = md_register_thread(raid5d, mddev, "%s_raid5");
+        conf->thread = md_register_thread(raid5d, mddev, NULL);
         if (!conf->thread) {
                 printk(KERN_ERR
                        "raid5: couldn't allocate thread for %s\n",
@@ -4964,7 +4968,7 @@ static int run(mddev_t *mddev)
                 set_bit(MD_RECOVERY_RESHAPE, &mddev->recovery);
                 set_bit(MD_RECOVERY_RUNNING, &mddev->recovery);
                 mddev->sync_thread = md_register_thread(md_do_sync, mddev,
-                                                        "%s_reshape");
+                                                        "reshape");
         }
 
         /* read-ahead size must cover two whole stripes, which is
@@ -5382,7 +5386,7 @@ static int raid5_start_reshape(mddev_t *mddev)
         set_bit(MD_RECOVERY_RESHAPE, &mddev->recovery);
         set_bit(MD_RECOVERY_RUNNING, &mddev->recovery);
         mddev->sync_thread = md_register_thread(md_do_sync, mddev,
-                                                "%s_reshape");
+                                                "reshape");
         if (!mddev->sync_thread) {
                 mddev->recovery = 0;
                 spin_lock_irq(&conf->device_lock);