X-Git-Url: https://git.openpandora.org/cgi-bin/gitweb.cgi?a=blobdiff_plain;f=drivers%2Fmd%2Fmd.c;h=2887f2287aca16463aa5aea0cd6af6d3fb9566b7;hb=8f95230095324becad132fa3a2a2eff8f7de7bdb;hp=84acfe7d10e48e33ea581924d4648948d005d90c;hpb=cdaeb578aca9e017deb0f55f1af8a94a4d63efb3;p=pandora-kernel.git

diff --git a/drivers/md/md.c b/drivers/md/md.c
index 84acfe7d10e4..2887f2287aca 100644
--- a/drivers/md/md.c
+++ b/drivers/md/md.c
@@ -392,6 +392,8 @@ void mddev_suspend(struct mddev *mddev)
 	synchronize_rcu();
 	wait_event(mddev->sb_wait, atomic_read(&mddev->active_io) == 0);
 	mddev->pers->quiesce(mddev, 1);
+
+	del_timer_sync(&mddev->safemode_timer);
 }
 EXPORT_SYMBOL_GPL(mddev_suspend);
 
@@ -451,7 +453,7 @@ static void submit_flushes(struct work_struct *ws)
 			atomic_inc(&rdev->nr_pending);
 			atomic_inc(&rdev->nr_pending);
 			rcu_read_unlock();
-			bi = bio_alloc_mddev(GFP_KERNEL, 0, mddev);
+			bi = bio_alloc_mddev(GFP_NOIO, 0, mddev);
 			bi->bi_end_io = md_end_flush;
 			bi->bi_private = rdev;
 			bi->bi_bdev = rdev->bdev;
@@ -570,7 +572,7 @@ static void mddev_put(struct mddev *mddev)
 	    mddev->ctime == 0 && !mddev->hold_active) {
 		/* Array is not configured at all, and not held active,
 		 * so destroy it */
-		list_del(&mddev->all_mddevs);
+		list_del_init(&mddev->all_mddevs);
 		bs = mddev->bio_set;
 		mddev->bio_set = NULL;
 		if (mddev->gendisk) {
@@ -1142,8 +1144,11 @@ static int super_90_load(struct md_rdev *rdev, struct md_rdev *refdev, int minor
 			ret = 0;
 	}
 	rdev->sectors = rdev->sb_start;
-	/* Limit to 4TB as metadata cannot record more than that */
-	if (rdev->sectors >= (2ULL << 32))
+	/* Limit to 4TB as metadata cannot record more than that.
+	 * (not needed for Linear and RAID0 as metadata doesn't
+	 * record this size)
+	 */
+	if (rdev->sectors >= (2ULL << 32) && sb->level >= 1)
 		rdev->sectors = (2ULL << 32) - 2;
 
 	if (rdev->sectors < ((sector_t)sb->size) * 2 && sb->level >= 1)
@@ -1425,7 +1430,7 @@ super_90_rdev_size_change(struct md_rdev *rdev, sector_t num_sectors)
 	/* Limit to 4TB as metadata cannot record more than that.
 	 * 4TB == 2^32 KB, or 2*2^32 sectors.
 	 */
-	if (num_sectors >= (2ULL << 32))
+	if (num_sectors >= (2ULL << 32) && rdev->mddev->level >= 1)
 		num_sectors = (2ULL << 32) - 2;
 	md_super_write(rdev->mddev, rdev, rdev->sb_start, rdev->sb_size,
 		       rdev->sb_page);
@@ -1801,13 +1806,13 @@ retry:
 						| BB_LEN(internal_bb));
 				*bbp++ = cpu_to_le64(store_bb);
 			}
+			bb->changed = 0;
 			if (read_seqretry(&bb->lock, seq))
 				goto retry;
 
 			bb->sector = (rdev->sb_start +
 				      (int)le32_to_cpu(sb->bblog_offset));
 			bb->size = le16_to_cpu(sb->bblog_size);
-			bb->changed = 0;
 		}
 	}
 
@@ -2362,6 +2367,7 @@ repeat:
 			clear_bit(MD_CHANGE_PENDING, &mddev->flags);
 			list_for_each_entry(rdev, &mddev->disks, same_set) {
 				if (rdev->badblocks.changed) {
+					rdev->badblocks.changed = 0;
 					md_ack_all_badblocks(&rdev->badblocks);
 					md_error(mddev, rdev);
 				}
@@ -2546,7 +2552,8 @@ state_show(struct md_rdev *rdev, char *page)
 		sep = ",";
 	}
 	if (test_bit(Blocked, &rdev->flags) ||
-	    rdev->badblocks.unacked_exist) {
+	    (rdev->badblocks.unacked_exist
+	     && !test_bit(Faulty, &rdev->flags))) {
 		len += sprintf(page+len, "%sblocked", sep);
 		sep = ",";
 	}
@@ -3696,8 +3703,8 @@ array_state_show(struct mddev *mddev, char *page)
 	return sprintf(page, "%s\n", array_states[st]);
 }
 
-static int do_md_stop(struct mddev * mddev, int ro, int is_open);
-static int md_set_readonly(struct mddev * mddev, int is_open);
+static int do_md_stop(struct mddev * mddev, int ro, struct block_device *bdev);
+static int md_set_readonly(struct mddev * mddev, struct block_device *bdev);
 static int do_md_run(struct mddev * mddev);
 static int restart_array(struct mddev *mddev);
 
@@ -3713,14 +3720,14 @@ array_state_store(struct mddev *mddev, const char *buf, size_t len)
 		/* stopping an active array */
 		if (atomic_read(&mddev->openers) > 0)
 			return -EBUSY;
-		err = do_md_stop(mddev, 0, 0);
+		err = do_md_stop(mddev, 0, NULL);
 		break;
 	case inactive:
 		/* stopping an active array */
 		if (mddev->pers) {
 			if (atomic_read(&mddev->openers) > 0)
 				return -EBUSY;
-			err = do_md_stop(mddev, 2, 0);
+			err = do_md_stop(mddev, 2, NULL);
 		} else
 			err = 0; /* already inactive */
 		break;
@@ -3728,7 +3735,7 @@ array_state_store(struct mddev *mddev, const char *buf, size_t len)
 		break; /* not supported yet */
 	case readonly:
 		if (mddev->pers)
-			err = md_set_readonly(mddev, 0);
+			err = md_set_readonly(mddev, NULL);
 		else {
 			mddev->ro = 1;
 			set_disk_ro(mddev->gendisk, 1);
@@ -3738,7 +3745,7 @@ array_state_store(struct mddev *mddev, const char *buf, size_t len)
 	case read_auto:
 		if (mddev->pers) {
 			if (mddev->ro == 0)
-				err = md_set_readonly(mddev, 0);
+				err = md_set_readonly(mddev, NULL);
 			else if (mddev->ro == 1)
 				err = restart_array(mddev);
 			if (err == 0) {
@@ -3788,6 +3795,8 @@ array_state_store(struct mddev *mddev, const char *buf, size_t len)
 	if (err)
 		return err;
 	else {
+		if (mddev->hold_active == UNTIL_IOCTL)
+			mddev->hold_active = 0;
 		sysfs_notify_dirent_safe(mddev->sysfs_state);
 		return len;
 	}
@@ -4487,11 +4496,20 @@ md_attr_show(struct kobject *kobj, struct attribute *attr, char *page)
 
 	if (!entry->show)
 		return -EIO;
+	spin_lock(&all_mddevs_lock);
+	if (list_empty(&mddev->all_mddevs)) {
+		spin_unlock(&all_mddevs_lock);
+		return -EBUSY;
+	}
+	mddev_get(mddev);
+	spin_unlock(&all_mddevs_lock);
+
 	rv = mddev_lock(mddev);
 	if (!rv) {
 		rv = entry->show(mddev, page);
 		mddev_unlock(mddev);
 	}
+	mddev_put(mddev);
 	return rv;
 }
 
@@ -4507,13 +4525,19 @@ md_attr_store(struct kobject *kobj, struct attribute *attr,
 		return -EIO;
 	if (!capable(CAP_SYS_ADMIN))
 		return -EACCES;
+	spin_lock(&all_mddevs_lock);
+	if (list_empty(&mddev->all_mddevs)) {
+		spin_unlock(&all_mddevs_lock);
+		return -EBUSY;
+	}
+	mddev_get(mddev);
+	spin_unlock(&all_mddevs_lock);
 	rv = mddev_lock(mddev);
-	if (mddev->hold_active == UNTIL_IOCTL)
-		mddev->hold_active = 0;
 	if (!rv) {
 		rv = entry->store(mddev, page, length);
 		mddev_unlock(mddev);
 	}
+	mddev_put(mddev);
 	return rv;
 }
 
@@ -5057,15 +5081,17 @@ void md_stop(struct mddev *mddev)
 }
 EXPORT_SYMBOL_GPL(md_stop);
 
-static int md_set_readonly(struct mddev *mddev, int is_open)
+static int md_set_readonly(struct mddev *mddev, struct block_device *bdev)
 {
 	int err = 0;
 	mutex_lock(&mddev->open_mutex);
-	if (atomic_read(&mddev->openers) > is_open) {
+	if (atomic_read(&mddev->openers) > !!bdev) {
 		printk("md: %s still in use.\n",mdname(mddev));
 		err = -EBUSY;
 		goto out;
 	}
+	if (bdev)
+		sync_blockdev(bdev);
 	if (mddev->pers) {
 		__md_stop_writes(mddev);
 
@@ -5087,18 +5113,26 @@ out:
  *   0 - completely stop and dis-assemble array
  *   2 - stop but do not disassemble array
  */
-static int do_md_stop(struct mddev * mddev, int mode, int is_open)
+static int do_md_stop(struct mddev * mddev, int mode,
+		      struct block_device *bdev)
 {
 	struct gendisk *disk = mddev->gendisk;
 	struct md_rdev *rdev;
 
 	mutex_lock(&mddev->open_mutex);
-	if (atomic_read(&mddev->openers) > is_open ||
+	if (atomic_read(&mddev->openers) > !!bdev ||
 	    mddev->sysfs_active) {
 		printk("md: %s still in use.\n",mdname(mddev));
 		mutex_unlock(&mddev->open_mutex);
 		return -EBUSY;
 	}
+	if (bdev)
+		/* It is possible IO was issued on some other
+		 * open file which was closed before we took ->open_mutex.
+		 * As that was not the last close __blkdev_put will not
+		 * have called sync_blockdev, so we must.
+		 */
+		sync_blockdev(bdev);
 
 	if (mddev->pers) {
 		if (mddev->ro)
@@ -5172,7 +5206,7 @@ static void autorun_array(struct mddev *mddev)
 	err = do_md_run(mddev);
 	if (err) {
 		printk(KERN_WARNING "md: do_md_run() returned %d\n", err);
-		do_md_stop(mddev, 0, 0);
+		do_md_stop(mddev, 0, NULL);
 	}
 }
 
@@ -6163,11 +6197,11 @@ static int md_ioctl(struct block_device *bdev, fmode_t mode,
 			goto done_unlock;
 
 		case STOP_ARRAY:
-			err = do_md_stop(mddev, 0, 1);
+			err = do_md_stop(mddev, 0, bdev);
 			goto done_unlock;
 
 		case STOP_ARRAY_RO:
-			err = md_set_readonly(mddev, 1);
+			err = md_set_readonly(mddev, bdev);
 			goto done_unlock;
 
 		case BLKROSET:
@@ -7342,8 +7376,7 @@ static int remove_and_add_spares(struct mddev *mddev)
 					spares++;
 					md_new_event(mddev);
 					set_bit(MD_CHANGE_DEVS, &mddev->flags);
-				} else
-					break;
+				}
 			}
 		}
 	}
@@ -7840,6 +7873,7 @@ int rdev_set_badblocks(struct md_rdev *rdev, sector_t s, int sectors,
 				  s + rdev->data_offset, sectors, acknowledged);
 	if (rv) {
 		/* Make sure they get written out promptly */
+		sysfs_notify_dirent_safe(rdev->sysfs_state);
 		set_bit(MD_CHANGE_CLEAN, &rdev->mddev->flags);
 		md_wakeup_thread(rdev->mddev->thread);
 	}
@@ -8079,30 +8113,24 @@ static int md_notify_reboot(struct notifier_block *this,
 	struct mddev *mddev;
 	int need_delay = 0;
 
-	if ((code == SYS_DOWN) || (code == SYS_HALT) || (code == SYS_POWER_OFF)) {
-
-		printk(KERN_INFO "md: stopping all md devices.\n");
-
-		for_each_mddev(mddev, tmp) {
-			if (mddev_trylock(mddev)) {
-				/* Force a switch to readonly even array
-				 * appears to still be in use.  Hence
-				 * the '100'.
-				 */
-				md_set_readonly(mddev, 100);
-				mddev_unlock(mddev);
-			}
-			need_delay = 1;
+	for_each_mddev(mddev, tmp) {
+		if (mddev_trylock(mddev)) {
+			if (mddev->pers)
+				__md_stop_writes(mddev);
+			mddev->safemode = 2;
+			mddev_unlock(mddev);
 		}
-		/*
-		 * certain more exotic SCSI devices are known to be
-		 * volatile wrt too early system reboots. While the
-		 * right place to handle this issue is the given
-		 * driver, we do want to have a safe RAID driver ...
-		 */
-		if (need_delay)
-			mdelay(1000*1);
+		need_delay = 1;
 	}
+	/*
+	 * certain more exotic SCSI devices are known to be
+	 * volatile wrt too early system reboots. While the
+	 * right place to handle this issue is the given
+	 * driver, we do want to have a safe RAID driver ...
+	 */
+	if (need_delay)
+		mdelay(1000*1);
+
 	return NOTIFY_DONE;
 }