dm mpath: hold io until all pg_inits completed

[safe/jmp/linux-2.6] / drivers / md / md.c

diff --git a/drivers/md/md.c b/drivers/md/md.c
index 6f91486..a20a71e 100644 (file)
--- a/drivers/md/md.c
+++ b/drivers/md/md.c
@@ -386,7 +386,9 @@ 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.
@@ -1936,15 +1938,11 @@ static void print_sb_1(struct mdp_superblock_1 *sb)
 
        uuid = sb->set_uuid;
        printk(KERN_INFO
-              "md:  SB: (V:%u) (F:0x%08x) Array-ID:<%02x%02x%02x%02x"
-              ":%02x%02x:%02x%02x:%02x%02x:%02x%02x%02x%02x%02x%02x>\n"
+              "md:  SB: (V:%u) (F:0x%08x) Array-ID:<%pU>\n"
               "md:    Name: \"%s\" CT:%llu\n",
                le32_to_cpu(sb->major_version),
                le32_to_cpu(sb->feature_map),
-               uuid[0], uuid[1], uuid[2], uuid[3],
-               uuid[4], uuid[5], uuid[6], uuid[7],
-               uuid[8], uuid[9], uuid[10], uuid[11],
-               uuid[12], uuid[13], uuid[14], uuid[15],
+               uuid,
                sb->set_name,
                (unsigned long long)le64_to_cpu(sb->ctime)
                       & MD_SUPERBLOCK_1_TIME_SEC_MASK);
@@ -1953,8 +1951,7 @@ static void print_sb_1(struct mdp_superblock_1 *sb)
        printk(KERN_INFO
               "md:       L%u SZ%llu RD:%u LO:%u CS:%u DO:%llu DS:%llu SO:%llu"
                        " RO:%llu\n"
-              "md:     Dev:%08x UUID: %02x%02x%02x%02x:%02x%02x:%02x%02x:%02x%02x"
-                       ":%02x%02x%02x%02x%02x%02x\n"
+              "md:     Dev:%08x UUID: %pU\n"
               "md:       (F:0x%08x) UT:%llu Events:%llu ResyncOffset:%llu CSUM:0x%08x\n"
               "md:         (MaxDev:%u) \n",
                le32_to_cpu(sb->level),
@@ -1967,10 +1964,7 @@ static void print_sb_1(struct mdp_superblock_1 *sb)
                (unsigned long long)le64_to_cpu(sb->super_offset),
                (unsigned long long)le64_to_cpu(sb->recovery_offset),
                le32_to_cpu(sb->dev_number),
-               uuid[0], uuid[1], uuid[2], uuid[3],
-               uuid[4], uuid[5], uuid[6], uuid[7],
-               uuid[8], uuid[9], uuid[10], uuid[11],
-               uuid[12], uuid[13], uuid[14], uuid[15],
+               uuid,
                sb->devflags,
                (unsigned long long)le64_to_cpu(sb->utime) & MD_SUPERBLOCK_1_TIME_SEC_MASK,
                (unsigned long long)le64_to_cpu(sb->events),
@@ -4081,8 +4075,10 @@ static void mddev_delayed_delete(struct work_struct *ws)
 {
        mddev_t *mddev = container_of(ws, mddev_t, del_work);
 
-       if (mddev->private == &md_redundancy_group) {
+       if (mddev->private) {
                sysfs_remove_group(&mddev->kobj, &md_redundancy_group);
+               if (mddev->private != (void*)1)
+                       sysfs_remove_group(&mddev->kobj, mddev->private);
                if (mddev->sysfs_action)
                        sysfs_put(mddev->sysfs_action);
                mddev->sysfs_action = NULL;
@@ -4293,10 +4289,7 @@ static int do_md_run(mddev_t * mddev)
                sysfs_notify_dirent(rdev->sysfs_state);
        }
 
-       md_probe(mddev->unit, NULL, NULL);
        disk = mddev->gendisk;
-       if (!disk)
-               return -ENOMEM;
 
        spin_lock(&pers_lock);
        pers = find_pers(mddev->level, mddev->clevel);
@@ -4363,7 +4356,7 @@ 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);
@@ -4427,33 +4420,6 @@ static int do_md_run(mddev_t * mddev)
 
        set_capacity(disk, mddev->array_sectors);
 
-       /* If there is a partially-recovered drive we need to
-        * start recovery here.  If we leave it to md_check_recovery,
-        * it will remove the drives and not do the right thing
-        */
-       if (mddev->degraded && !mddev->sync_thread) {
-               int spares = 0;
-               list_for_each_entry(rdev, &mddev->disks, same_set)
-                       if (rdev->raid_disk >= 0 &&
-                           !test_bit(In_sync, &rdev->flags) &&
-                           !test_bit(Faulty, &rdev->flags))
-                               /* complete an interrupted recovery */
-                               spares++;
-               if (spares && mddev->pers->sync_request) {
-                       mddev->recovery = 0;
-                       set_bit(MD_RECOVERY_RUNNING, &mddev->recovery);
-                       mddev->sync_thread = md_register_thread(md_do_sync,
-                                                               mddev,
-                                                               "resync");
-                       if (!mddev->sync_thread) {
-                               printk(KERN_ERR "%s: could not start resync"
-                                      " thread...\n",
-                                      mdname(mddev));
-                               /* leave the spares where they are, it shouldn't hurt */
-                               mddev->recovery = 0;
-                       }
-               }
-       }
        md_wakeup_thread(mddev->thread);
        md_wakeup_thread(mddev->sync_thread); /* possibly kick off a reshape */
 
@@ -4563,8 +4529,8 @@ static int do_md_stop(mddev_t * mddev, int mode, int is_open)
                        mddev->queue->unplug_fn = NULL;
                        mddev->queue->backing_dev_info.congested_fn = NULL;
                        module_put(mddev->pers->owner);
-                       if (mddev->pers->sync_request)
-                               mddev->private = &md_redundancy_group;
+                       if (mddev->pers->sync_request && mddev->private == NULL)
+                               mddev->private = (void*)1;
                        mddev->pers = NULL;
                        /* tell userspace to handle 'inactive' */
                        sysfs_notify_dirent(mddev->sysfs_state);
@@ -4611,9 +4577,6 @@ out:
                }
                mddev->bitmap_info.offset = 0;
 
-               /* make sure all md_delayed_delete calls have finished */
-               flush_scheduled_work();
-
                export_array(mddev);
 
                mddev->array_sectors = 0;
@@ -5270,6 +5233,10 @@ 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;
@@ -6502,10 +6469,11 @@ void md_do_sync(mddev_t *mddev)
                mddev->curr_resync = 2;
 
        try_again:
-               if (kthread_should_stop()) {
+               if (kthread_should_stop())
                        set_bit(MD_RECOVERY_INTR, &mddev->recovery);
+
+               if (test_bit(MD_RECOVERY_INTR, &mddev->recovery))
                        goto skip;
-               }
                for_each_mddev(mddev2, tmp) {
                        if (mddev2 == mddev)
                                continue;