Merge ../linux-2.6

4 files changed, 78 insertions, 44 deletions

diff --git a/drivers/md/md.c b/drivers/md/md.c
index 1ed5152db45..f19b874753a 100644
--- a/drivers/md/md.c
+++ b/drivers/md/md.c
@@ -163,9 +163,19 @@ void md_new_event(mddev_t *mddev)
 {
 	atomic_inc(&md_event_count);
 	wake_up(&md_event_waiters);
+	sysfs_notify(&mddev->kobj, NULL, "sync_action");
 }
 EXPORT_SYMBOL_GPL(md_new_event);
 
+/* Alternate version that can be called from interrupts
+ * when calling sysfs_notify isn't needed.
+ */
+void md_new_event_inintr(mddev_t *mddev)
+{
+	atomic_inc(&md_event_count);
+	wake_up(&md_event_waiters);
+}
+
 /*
  * Enables to iterate over all existing md arrays
  * all_mddevs_lock protects this list.
@@ -278,11 +288,6 @@ static inline int mddev_lock(mddev_t * mddev)
 	return mutex_lock_interruptible(&mddev->reconfig_mutex);
 }
 
-static inline void mddev_lock_uninterruptible(mddev_t * mddev)
-{
-	mutex_lock(&mddev->reconfig_mutex);
-}
-
 static inline int mddev_trylock(mddev_t * mddev)
 {
 	return mutex_trylock(&mddev->reconfig_mutex);
@@ -2256,7 +2261,7 @@ action_store(mddev_t *mddev, const char *page, size_t len)
 	} else {
 		if (cmd_match(page, "check"))
 			set_bit(MD_RECOVERY_CHECK, &mddev->recovery);
-		else if (cmd_match(page, "repair"))
+		else if (!cmd_match(page, "repair"))
 			return -EINVAL;
 		set_bit(MD_RECOVERY_REQUESTED, &mddev->recovery);
 		set_bit(MD_RECOVERY_SYNC, &mddev->recovery);
@@ -2457,9 +2462,11 @@ md_attr_show(struct kobject *kobj, struct attribute *attr, char *page)
 
 	if (!entry->show)
 		return -EIO;
-	mddev_lock(mddev);
-	rv = entry->show(mddev, page);
-	mddev_unlock(mddev);
+	rv = mddev_lock(mddev);
+	if (!rv) {
+		rv = entry->show(mddev, page);
+		mddev_unlock(mddev);
+	}
 	return rv;
 }
 
@@ -2473,9 +2480,11 @@ md_attr_store(struct kobject *kobj, struct attribute *attr,
 
 	if (!entry->store)
 		return -EIO;
-	mddev_lock(mddev);
-	rv = entry->store(mddev, page, length);
-	mddev_unlock(mddev);
+	rv = mddev_lock(mddev);
+	if (!rv) {
+		rv = entry->store(mddev, page, length);
+		mddev_unlock(mddev);
+	}
 	return rv;
 }
 
@@ -4149,7 +4158,7 @@ void md_error(mddev_t *mddev, mdk_rdev_t *rdev)
 	set_bit(MD_RECOVERY_INTR, &mddev->recovery);
 	set_bit(MD_RECOVERY_NEEDED, &mddev->recovery);
 	md_wakeup_thread(mddev->thread);
-	md_new_event(mddev);
+	md_new_event_inintr(mddev);
 }
 
 /* seq_file implementation /proc/mdstat */
@@ -4340,8 +4349,9 @@ static int md_seq_show(struct seq_file *seq, void *v)
 		return 0;
 	}
 
-	if (mddev_lock(mddev)!=0) 
+	if (mddev_lock(mddev) < 0)
 		return -EINTR;
+
 	if (mddev->pers || mddev->raid_disks || !list_empty(&mddev->disks)) {
 		seq_printf(seq, "%s : %sactive", mdname(mddev),
 						mddev->pers ? "" : "in");
@@ -5027,8 +5037,10 @@ static int md_notify_reboot(struct notifier_block *this,
 		printk(KERN_INFO "md: stopping all md devices.\n");
 
 		ITERATE_MDDEV(mddev,tmp)
-			if (mddev_trylock(mddev))
+			if (mddev_trylock(mddev)) {
 				do_md_stop (mddev, 1);
+				mddev_unlock(mddev);
+			}
 		/*
 		 * certain more exotic SCSI devices are known to be
 		 * volatile wrt too early system reboots. While the
diff --git a/drivers/md/raid0.c b/drivers/md/raid0.c
index 678f4dbbea1..cb8c6317e4e 100644
--- a/drivers/md/raid0.c
+++ b/drivers/md/raid0.c
@@ -331,13 +331,14 @@ static int raid0_run (mddev_t *mddev)
 		goto out_free_conf;
 	size = conf->strip_zone[cur].size;
 
-	for (i=0; i< nb_zone; i++) {
-		conf->hash_table[i] = conf->strip_zone + cur;
+	conf->hash_table[0] = conf->strip_zone + cur;
+	for (i=1; i< nb_zone; i++) {
 		while (size <= conf->hash_spacing) {
 			cur++;
 			size += conf->strip_zone[cur].size;
 		}
 		size -= conf->hash_spacing;
+		conf->hash_table[i] = conf->strip_zone + cur;
 	}
 	if (conf->preshift) {
 		conf->hash_spacing >>= conf->preshift;
diff --git a/drivers/md/raid1.c b/drivers/md/raid1.c
index 6081941de1b..4070eff6f0f 100644
--- a/drivers/md/raid1.c
+++ b/drivers/md/raid1.c
@@ -315,10 +315,11 @@ static int raid1_end_write_request(struct bio *bio, unsigned int bytes_done, int
 		if (r1_bio->bios[mirror] == bio)
 			break;
 
-	if (error == -ENOTSUPP && test_bit(R1BIO_Barrier, &r1_bio->state)) {
+	if (error == -EOPNOTSUPP && test_bit(R1BIO_Barrier, &r1_bio->state)) {
 		set_bit(BarriersNotsupp, &conf->mirrors[mirror].rdev->flags);
 		set_bit(R1BIO_BarrierRetry, &r1_bio->state);
 		r1_bio->mddev->barriers_work = 0;
+		/* Don't rdev_dec_pending in this branch - keep it for the retry */
 	} else {
 		/*
 		 * this branch is our 'one mirror IO has finished' event handler:
@@ -365,6 +366,7 @@ static int raid1_end_write_request(struct bio *bio, unsigned int bytes_done, int
 				}
 			}
 		}
+		rdev_dec_pending(conf->mirrors[mirror].rdev, conf->mddev);
 	}
 	/*
 	 *
@@ -374,11 +376,9 @@ static int raid1_end_write_request(struct bio *bio, unsigned int bytes_done, int
 	if (atomic_dec_and_test(&r1_bio->remaining)) {
 		if (test_bit(R1BIO_BarrierRetry, &r1_bio->state)) {
 			reschedule_retry(r1_bio);
-			/* Don't dec_pending yet, we want to hold
-			 * the reference over the retry
-			 */
 			goto out;
 		}
+		/* it really is the end of this request */
 		if (test_bit(R1BIO_BehindIO, &r1_bio->state)) {
 			/* free extra copy of the data pages */
 			int i = bio->bi_vcnt;
@@ -393,8 +393,6 @@ static int raid1_end_write_request(struct bio *bio, unsigned int bytes_done, int
 		md_write_end(r1_bio->mddev);
 		raid_end_bio_io(r1_bio);
 	}
-
-	rdev_dec_pending(conf->mirrors[mirror].rdev, conf->mddev);
  out:
 	if (to_put)
 		bio_put(to_put);
@@ -753,18 +751,24 @@ static int make_request(request_queue_t *q, struct bio * bio)
 	const int rw = bio_data_dir(bio);
 	int do_barriers;
 
-	if (unlikely(!mddev->barriers_work && bio_barrier(bio))) {
-		bio_endio(bio, bio->bi_size, -EOPNOTSUPP);
-		return 0;
-	}
-
 	/*
 	 * Register the new request and wait if the reconstruction
 	 * thread has put up a bar for new requests.
 	 * Continue immediately if no resync is active currently.
+	 * We test barriers_work *after* md_write_start as md_write_start
+	 * may cause the first superblock write, and that will check out
+	 * if barriers work.
 	 */
+
 	md_write_start(mddev, bio); /* wait on superblock update early */
 
+	if (unlikely(!mddev->barriers_work && bio_barrier(bio))) {
+		if (rw == WRITE)
+			md_write_end(mddev);
+		bio_endio(bio, bio->bi_size, -EOPNOTSUPP);
+		return 0;
+	}
+
 	wait_barrier(conf);
 
 	disk_stat_inc(mddev->gendisk, ios[rw]);
@@ -1404,10 +1408,11 @@ static void raid1d(mddev_t *mddev)
 			unplug = 1;
 		} else if (test_bit(R1BIO_BarrierRetry, &r1_bio->state)) {
 			/* some requests in the r1bio were BIO_RW_BARRIER
-			 * requests which failed with -ENOTSUPP.  Hohumm..
+			 * requests which failed with -EOPNOTSUPP.  Hohumm..
 			 * Better resubmit without the barrier.
 			 * We know which devices to resubmit for, because
 			 * all others have had their bios[] entry cleared.
+			 * We already have a nr_pending reference on these rdevs.
 			 */
 			int i;
 			clear_bit(R1BIO_BarrierRetry, &r1_bio->state);
diff --git a/drivers/md/raid10.c b/drivers/md/raid10.c
index 617012bc107..1440935414e 100644
--- a/drivers/md/raid10.c
+++ b/drivers/md/raid10.c
@@ -1407,43 +1407,54 @@ static void raid10d(mddev_t *mddev)
 				if (s > (PAGE_SIZE>>9))
 					s = PAGE_SIZE >> 9;
 
+				rcu_read_lock();
 				do {
 					int d = r10_bio->devs[sl].devnum;
-					rdev = conf->mirrors[d].rdev;
+					rdev = rcu_dereference(conf->mirrors[d].rdev);
 					if (rdev &&
-					    test_bit(In_sync, &rdev->flags) &&
-					    sync_page_io(rdev->bdev,
-							 r10_bio->devs[sl].addr +
-							 sect + rdev->data_offset,
-							 s<<9,
-							 conf->tmppage, READ))
-						success = 1;
-					else {
-						sl++;
-						if (sl == conf->copies)
-							sl = 0;
+					    test_bit(In_sync, &rdev->flags)) {
+						atomic_inc(&rdev->nr_pending);
+						rcu_read_unlock();
+						success = sync_page_io(rdev->bdev,
+								       r10_bio->devs[sl].addr +
+								       sect + rdev->data_offset,
+								       s<<9,
+								       conf->tmppage, READ);
+						rdev_dec_pending(rdev, mddev);
+						rcu_read_lock();
+						if (success)
+							break;
 					}
+					sl++;
+					if (sl == conf->copies)
+						sl = 0;
 				} while (!success && sl != r10_bio->read_slot);
+				rcu_read_unlock();
 
 				if (success) {
 					int start = sl;
 					/* write it back and re-read */
+					rcu_read_lock();
 					while (sl != r10_bio->read_slot) {
 						int d;
 						if (sl==0)
 							sl = conf->copies;
 						sl--;
 						d = r10_bio->devs[sl].devnum;
-						rdev = conf->mirrors[d].rdev;
-						atomic_add(s, &rdev->corrected_errors);
+						rdev = rcu_dereference(conf->mirrors[d].rdev);
 						if (rdev &&
 						    test_bit(In_sync, &rdev->flags)) {
+							atomic_inc(&rdev->nr_pending);
+							rcu_read_unlock();
+							atomic_add(s, &rdev->corrected_errors);
 							if (sync_page_io(rdev->bdev,
 									 r10_bio->devs[sl].addr +
 									 sect + rdev->data_offset,
 									 s<<9, conf->tmppage, WRITE) == 0)
 								/* Well, this device is dead */
 								md_error(mddev, rdev);
+							rdev_dec_pending(rdev, mddev);
+							rcu_read_lock();
 						}
 					}
 					sl = start;
@@ -1453,17 +1464,22 @@ static void raid10d(mddev_t *mddev)
 							sl = conf->copies;
 						sl--;
 						d = r10_bio->devs[sl].devnum;
-						rdev = conf->mirrors[d].rdev;
+						rdev = rcu_dereference(conf->mirrors[d].rdev);
 						if (rdev &&
 						    test_bit(In_sync, &rdev->flags)) {
+							atomic_inc(&rdev->nr_pending);
+							rcu_read_unlock();
 							if (sync_page_io(rdev->bdev,
 									 r10_bio->devs[sl].addr +
 									 sect + rdev->data_offset,
 									 s<<9, conf->tmppage, READ) == 0)
 								/* Well, this device is dead */
 								md_error(mddev, rdev);
+							rdev_dec_pending(rdev, mddev);
+							rcu_read_lock();
 						}
 					}
+					rcu_read_unlock();
 				} else {
 					/* Cannot read from anywhere -- bye bye array */
 					md_error(mddev, conf->mirrors[r10_bio->devs[r10_bio->read_slot].devnum].rdev);