Merge branch 'for-linus' of git://neil.brown.name/md

* 'for-linus' of git://neil.brown.name/md: (24 commits)
  md: clean up do_md_stop
  md: fix another deadlock with removing sysfs attributes.
  md: move revalidate_disk() back outside open_mutex
  md/raid10: fix deadlock with unaligned read during resync
  md/bitmap:  separate out loading a bitmap from initialising the structures.
  md/bitmap: prepare for storing write-intent-bitmap via dm-dirty-log.
  md/bitmap: optimise scanning of empty bitmaps.
  md/bitmap: clean up plugging calls.
  md/bitmap: reduce dependence on sysfs.
  md/bitmap: white space clean up and similar.
  md/raid5: export raid5 unplugging interface.
  md/plug: optionally use plugger to unplug an array during resync/recovery.
  md/raid5: add simple plugging infrastructure.
  md/raid5: export is_congested test
  raid5: Don't set read-ahead when there is no queue
  md: add support for raising dm events.
  md: export various start/stop interfaces
  md: split out md_rdev_init
  md: be more careful setting MD_CHANGE_CLEAN
  md/raid5: ensure we create a unique name for kmem_cache when mddev has no gendisk
  ...

crypto/async_tx/Kconfig

@@ -22,6 +22,20 @@ config ASYNC_RAID6_RECOV
 	tristate
 	select ASYNC_CORE
 	select ASYNC_PQ
+	select ASYNC_XOR
+
+config ASYNC_RAID6_TEST
+	tristate "Self test for hardware accelerated raid6 recovery"
+	depends on ASYNC_RAID6_RECOV
+	select ASYNC_MEMCPY
+	---help---
+	  This is a one-shot self test that permutes through the
+	  recovery of all the possible two disk failure scenarios for a
+	  N-disk array.  Recovery is performed with the asynchronous
+	  raid6 recovery routines, and will optionally use an offload
+	  engine if one is available.
+
+	  If unsure, say N.
 
 config ASYNC_TX_DISABLE_PQ_VAL_DMA
 	bool

drivers/md/Kconfig

@@ -121,7 +121,7 @@ config MD_RAID10
 config MD_RAID456
 	tristate "RAID-4/RAID-5/RAID-6 mode"
 	depends on BLK_DEV_MD
-	select MD_RAID6_PQ
+	select RAID6_PQ
 	select ASYNC_MEMCPY
 	select ASYNC_XOR
 	select ASYNC_PQ
@@ -165,22 +165,6 @@ config MULTICORE_RAID456
 
 	  If unsure, say N.
 
-config MD_RAID6_PQ
-	tristate
-
-config ASYNC_RAID6_TEST
-	tristate "Self test for hardware accelerated raid6 recovery"
-	depends on MD_RAID6_PQ
-	select ASYNC_RAID6_RECOV
-	---help---
-	  This is a one-shot self test that permutes through the
-	  recovery of all the possible two disk failure scenarios for a
-	  N-disk array.  Recovery is performed with the asynchronous
-	  raid6 recovery routines, and will optionally use an offload
-	  engine if one is available.
-
-	  If unsure, say N.
-
 config MD_MULTIPATH
 	tristate "Multipath I/O support"
 	depends on BLK_DEV_MD

drivers/md/Makefile

@@ -12,13 +12,6 @@ dm-log-userspace-y \
 		+= dm-log-userspace-base.o dm-log-userspace-transfer.o
 md-mod-y	+= md.o bitmap.o
 raid456-y	+= raid5.o
-raid6_pq-y	+= raid6algos.o raid6recov.o raid6tables.o \
-		   raid6int1.o raid6int2.o raid6int4.o \
-		   raid6int8.o raid6int16.o raid6int32.o \
-		   raid6altivec1.o raid6altivec2.o raid6altivec4.o \
-		   raid6altivec8.o \
-		   raid6mmx.o raid6sse1.o raid6sse2.o
-hostprogs-y	+= mktables
 
 # Note: link order is important.  All raid personalities
 # and must come before md.o, as they each initialise 
@@ -29,7 +22,6 @@ obj-$(CONFIG_MD_LINEAR)		+= linear.o
 obj-$(CONFIG_MD_RAID0)		+= raid0.o
 obj-$(CONFIG_MD_RAID1)		+= raid1.o
 obj-$(CONFIG_MD_RAID10)		+= raid10.o
-obj-$(CONFIG_MD_RAID6_PQ)	+= raid6_pq.o
 obj-$(CONFIG_MD_RAID456)	+= raid456.o
 obj-$(CONFIG_MD_MULTIPATH)	+= multipath.o
 obj-$(CONFIG_MD_FAULTY)		+= faulty.o
@@ -45,75 +37,6 @@ obj-$(CONFIG_DM_MIRROR)		+= dm-mirror.o dm-log.o dm-region-hash.o
 obj-$(CONFIG_DM_LOG_USERSPACE)	+= dm-log-userspace.o
 obj-$(CONFIG_DM_ZERO)		+= dm-zero.o
 
-quiet_cmd_unroll = UNROLL  $@
-      cmd_unroll = $(AWK) -f$(srctree)/$(src)/unroll.awk -vN=$(UNROLL) \
-                   < $< > $@ || ( rm -f $@ && exit 1 )
-
-ifeq ($(CONFIG_ALTIVEC),y)
-altivec_flags := -maltivec -mabi=altivec
-endif
-
 ifeq ($(CONFIG_DM_UEVENT),y)
 dm-mod-objs			+= dm-uevent.o
 endif
-
-targets += raid6int1.c
-$(obj)/raid6int1.c:   UNROLL := 1
-$(obj)/raid6int1.c:   $(src)/raid6int.uc $(src)/unroll.awk FORCE
-	$(call if_changed,unroll)
-
-targets += raid6int2.c
-$(obj)/raid6int2.c:   UNROLL := 2
-$(obj)/raid6int2.c:   $(src)/raid6int.uc $(src)/unroll.awk FORCE
-	$(call if_changed,unroll)
-
-targets += raid6int4.c
-$(obj)/raid6int4.c:   UNROLL := 4
-$(obj)/raid6int4.c:   $(src)/raid6int.uc $(src)/unroll.awk FORCE
-	$(call if_changed,unroll)
-
-targets += raid6int8.c
-$(obj)/raid6int8.c:   UNROLL := 8
-$(obj)/raid6int8.c:   $(src)/raid6int.uc $(src)/unroll.awk FORCE
-	$(call if_changed,unroll)
-
-targets += raid6int16.c
-$(obj)/raid6int16.c:  UNROLL := 16
-$(obj)/raid6int16.c:  $(src)/raid6int.uc $(src)/unroll.awk FORCE
-	$(call if_changed,unroll)
-
-targets += raid6int32.c
-$(obj)/raid6int32.c:  UNROLL := 32
-$(obj)/raid6int32.c:  $(src)/raid6int.uc $(src)/unroll.awk FORCE
-	$(call if_changed,unroll)
-
-CFLAGS_raid6altivec1.o += $(altivec_flags)
-targets += raid6altivec1.c
-$(obj)/raid6altivec1.c:   UNROLL := 1
-$(obj)/raid6altivec1.c:   $(src)/raid6altivec.uc $(src)/unroll.awk FORCE
-	$(call if_changed,unroll)
-
-CFLAGS_raid6altivec2.o += $(altivec_flags)
-targets += raid6altivec2.c
-$(obj)/raid6altivec2.c:   UNROLL := 2
-$(obj)/raid6altivec2.c:   $(src)/raid6altivec.uc $(src)/unroll.awk FORCE
-	$(call if_changed,unroll)
-
-CFLAGS_raid6altivec4.o += $(altivec_flags)
-targets += raid6altivec4.c
-$(obj)/raid6altivec4.c:   UNROLL := 4
-$(obj)/raid6altivec4.c:   $(src)/raid6altivec.uc $(src)/unroll.awk FORCE
-	$(call if_changed,unroll)
-
-CFLAGS_raid6altivec8.o += $(altivec_flags)
-targets += raid6altivec8.c
-$(obj)/raid6altivec8.c:   UNROLL := 8
-$(obj)/raid6altivec8.c:   $(src)/raid6altivec.uc $(src)/unroll.awk FORCE
-	$(call if_changed,unroll)
-
-quiet_cmd_mktable = TABLE   $@
-      cmd_mktable = $(obj)/mktables > $@ || ( rm -f $@ && exit 1 )
-
-targets += raid6tables.c
-$(obj)/raid6tables.c: $(obj)/mktables FORCE
-	$(call if_changed,mktable)

drivers/md/bitmap.h

@@ -222,6 +222,10 @@ struct bitmap {
 	unsigned long file_pages; /* number of pages in the file */
 	int last_page_size; /* bytes in the last page */
 
+	unsigned long logattrs; /* used when filemap_attr doesn't exist
+				 * because we are working with a dirty_log
+				 */
+
 	unsigned long flags;
 
 	int allclean;
@@ -243,12 +247,14 @@ struct bitmap {
 	wait_queue_head_t behind_wait;
 
 	struct sysfs_dirent *sysfs_can_clear;
+
 };
 
 /* the bitmap API */
 
 /* these are used only by md/bitmap */
 int  bitmap_create(mddev_t *mddev);
+int bitmap_load(mddev_t *mddev);
 void bitmap_flush(mddev_t *mddev);
 void bitmap_destroy(mddev_t *mddev);
 

drivers/md/md.c

@@ -262,7 +262,7 @@ static int md_make_request(struct request_queue *q, struct bio *bio)
  * Once ->stop is called and completes, the module will be completely
  * unused.
  */
-static void mddev_suspend(mddev_t *mddev)
+void mddev_suspend(mddev_t *mddev)
 {
 	BUG_ON(mddev->suspended);
 	mddev->suspended = 1;
@@ -270,13 +270,15 @@ static void mddev_suspend(mddev_t *mddev)
 	wait_event(mddev->sb_wait, atomic_read(&mddev->active_io) == 0);
 	mddev->pers->quiesce(mddev, 1);
 }
+EXPORT_SYMBOL_GPL(mddev_suspend);
 
-static void mddev_resume(mddev_t *mddev)
+void mddev_resume(mddev_t *mddev)
 {
 	mddev->suspended = 0;
 	wake_up(&mddev->sb_wait);
 	mddev->pers->quiesce(mddev, 0);
 }
+EXPORT_SYMBOL_GPL(mddev_resume);
 
 int mddev_congested(mddev_t *mddev, int bits)
 {
@@ -385,6 +387,51 @@ void md_barrier_request(mddev_t *mddev, struct bio *bio)
 }
 EXPORT_SYMBOL(md_barrier_request);
 
+/* Support for plugging.
+ * This mirrors the plugging support in request_queue, but does not
+ * require having a whole queue
+ */
+static void plugger_work(struct work_struct *work)
+{
+	struct plug_handle *plug =
+		container_of(work, struct plug_handle, unplug_work);
+	plug->unplug_fn(plug);
+}
+static void plugger_timeout(unsigned long data)
+{
+	struct plug_handle *plug = (void *)data;
+	kblockd_schedule_work(NULL, &plug->unplug_work);
+}
+void plugger_init(struct plug_handle *plug,
+		  void (*unplug_fn)(struct plug_handle *))
+{
+	plug->unplug_flag = 0;
+	plug->unplug_fn = unplug_fn;
+	init_timer(&plug->unplug_timer);
+	plug->unplug_timer.function = plugger_timeout;
+	plug->unplug_timer.data = (unsigned long)plug;
+	INIT_WORK(&plug->unplug_work, plugger_work);
+}
+EXPORT_SYMBOL_GPL(plugger_init);
+
+void plugger_set_plug(struct plug_handle *plug)
+{
+	if (!test_and_set_bit(PLUGGED_FLAG, &plug->unplug_flag))
+		mod_timer(&plug->unplug_timer, jiffies + msecs_to_jiffies(3)+1);
+}
+EXPORT_SYMBOL_GPL(plugger_set_plug);
+
+int plugger_remove_plug(struct plug_handle *plug)
+{
+	if (test_and_clear_bit(PLUGGED_FLAG, &plug->unplug_flag)) {
+		del_timer(&plug->unplug_timer);
+		return 1;
+	} else
+		return 0;
+}
+EXPORT_SYMBOL_GPL(plugger_remove_plug);
+
+
 static inline mddev_t *mddev_get(mddev_t *mddev)
 {
 	atomic_inc(&mddev->active);
@@ -417,7 +464,7 @@ static void mddev_put(mddev_t *mddev)
 	spin_unlock(&all_mddevs_lock);
 }
 
-static void mddev_init(mddev_t *mddev)
+void mddev_init(mddev_t *mddev)
 {
 	mutex_init(&mddev->open_mutex);
 	mutex_init(&mddev->reconfig_mutex);
@@ -437,6 +484,7 @@ static void mddev_init(mddev_t *mddev)
 	mddev->resync_max = MaxSector;
 	mddev->level = LEVEL_NONE;
 }
+EXPORT_SYMBOL_GPL(mddev_init);
 
 static mddev_t * mddev_find(dev_t unit)
 {
@@ -533,25 +581,31 @@ static void mddev_unlock(mddev_t * mddev)
 		 * an access to the files will try to take reconfig_mutex
 		 * while holding the file unremovable, which leads to
 		 * a deadlock.
-		 * So hold open_mutex instead - we are allowed to take
-		 * it while holding reconfig_mutex, and md_run can
-		 * use it to wait for the remove to complete.
+		 * So hold set sysfs_active while the remove in happeing,
+		 * and anything else which might set ->to_remove or my
+		 * otherwise change the sysfs namespace will fail with
+		 * -EBUSY if sysfs_active is still set.
+		 * We set sysfs_active under reconfig_mutex and elsewhere
+		 * test it under the same mutex to ensure its correct value
+		 * is seen.
 		 */
 		struct attribute_group *to_remove = mddev->to_remove;
 		mddev->to_remove = NULL;
-		mutex_lock(&mddev->open_mutex);
+		mddev->sysfs_active = 1;
 		mutex_unlock(&mddev->reconfig_mutex);
 
-		if (to_remove != &md_redundancy_group)
-			sysfs_remove_group(&mddev->kobj, to_remove);
-		if (mddev->pers == NULL ||
-		    mddev->pers->sync_request == NULL) {
-			sysfs_remove_group(&mddev->kobj, &md_redundancy_group);
-			if (mddev->sysfs_action)
-				sysfs_put(mddev->sysfs_action);
-			mddev->sysfs_action = NULL;
+		if (mddev->kobj.sd) {
+			if (to_remove != &md_redundancy_group)
+				sysfs_remove_group(&mddev->kobj, to_remove);
+			if (mddev->pers == NULL ||
+			    mddev->pers->sync_request == NULL) {
+				sysfs_remove_group(&mddev->kobj, &md_redundancy_group);
+				if (mddev->sysfs_action)
+					sysfs_put(mddev->sysfs_action);
+				mddev->sysfs_action = NULL;
+			}
 		}
-		mutex_unlock(&mddev->open_mutex);
+		mddev->sysfs_active = 0;
 	} else
 		mutex_unlock(&mddev->reconfig_mutex);
 
@@ -1812,11 +1866,9 @@ static int bind_rdev_to_array(mdk_rdev_t * rdev, mddev_t * mddev)
 		goto fail;
 
 	ko = &part_to_dev(rdev->bdev->bd_part)->kobj;
-	if ((err = sysfs_create_link(&rdev->kobj, ko, "block"))) {
-		kobject_del(&rdev->kobj);
-		goto fail;
-	}
-	rdev->sysfs_state = sysfs_get_dirent(rdev->kobj.sd, NULL, "state");
+	if (sysfs_create_link(&rdev->kobj, ko, "block"))
+		/* failure here is OK */;
+	rdev->sysfs_state = sysfs_get_dirent_safe(rdev->kobj.sd, "state");
 
 	list_add_rcu(&rdev->same_set, &mddev->disks);
 	bd_claim_by_disk(rdev->bdev, rdev->bdev->bd_holder, mddev->gendisk);
@@ -2335,8 +2387,8 @@ state_store(mdk_rdev_t *rdev, const char *buf, size_t len)
 		set_bit(In_sync, &rdev->flags);
 		err = 0;
 	}
-	if (!err && rdev->sysfs_state)
-		sysfs_notify_dirent(rdev->sysfs_state);
+	if (!err)
+		sysfs_notify_dirent_safe(rdev->sysfs_state);
 	return err ? err : len;
 }
 static struct rdev_sysfs_entry rdev_state =
@@ -2431,14 +2483,10 @@ slot_store(mdk_rdev_t *rdev, const char *buf, size_t len)
 			rdev->raid_disk = -1;
 			return err;
 		} else
-			sysfs_notify_dirent(rdev->sysfs_state);
+			sysfs_notify_dirent_safe(rdev->sysfs_state);
 		sprintf(nm, "rd%d", rdev->raid_disk);
 		if (sysfs_create_link(&rdev->mddev->kobj, &rdev->kobj, nm))
-			printk(KERN_WARNING
-			       "md: cannot register "
-			       "%s for %s\n",
-			       nm, mdname(rdev->mddev));
-
+			/* failure here is OK */;
 		/* don't wakeup anyone, leave that to userspace. */
 	} else {
 		if (slot >= rdev->mddev->raid_disks)
@@ -2448,7 +2496,7 @@ slot_store(mdk_rdev_t *rdev, const char *buf, size_t len)
 		clear_bit(Faulty, &rdev->flags);
 		clear_bit(WriteMostly, &rdev->flags);
 		set_bit(In_sync, &rdev->flags);
-		sysfs_notify_dirent(rdev->sysfs_state);
+		sysfs_notify_dirent_safe(rdev->sysfs_state);
 	}
 	return len;
 }
@@ -2696,6 +2744,24 @@ static struct kobj_type rdev_ktype = {
 	.default_attrs	= rdev_default_attrs,
 };
 
+void md_rdev_init(mdk_rdev_t *rdev)
+{
+	rdev->desc_nr = -1;
+	rdev->saved_raid_disk = -1;
+	rdev->raid_disk = -1;
+	rdev->flags = 0;
+	rdev->data_offset = 0;
+	rdev->sb_events = 0;
+	rdev->last_read_error.tv_sec  = 0;
+	rdev->last_read_error.tv_nsec = 0;
+	atomic_set(&rdev->nr_pending, 0);
+	atomic_set(&rdev->read_errors, 0);
+	atomic_set(&rdev->corrected_errors, 0);
+
+	INIT_LIST_HEAD(&rdev->same_set);
+	init_waitqueue_head(&rdev->blocked_wait);
+}
+EXPORT_SYMBOL_GPL(md_rdev_init);
 /*
  * Import a device. If 'super_format' >= 0, then sanity check the superblock
  *
@@ -2719,6 +2785,7 @@ static mdk_rdev_t *md_import_device(dev_t newdev, int super_format, int super_mi
 		return ERR_PTR(-ENOMEM);
 	}
 
+	md_rdev_init(rdev);
 	if ((err = alloc_disk_sb(rdev)))
 		goto abort_free;
 
@@ -2728,18 +2795,6 @@ static mdk_rdev_t *md_import_device(dev_t newdev, int super_format, int super_mi
 
 	kobject_init(&rdev->kobj, &rdev_ktype);
 
-	rdev->desc_nr = -1;
-	rdev->saved_raid_disk = -1;
-	rdev->raid_disk = -1;
-	rdev->flags = 0;
-	rdev->data_offset = 0;
-	rdev->sb_events = 0;
-	rdev->last_read_error.tv_sec  = 0;
-	rdev->last_read_error.tv_nsec = 0;
-	atomic_set(&rdev->nr_pending, 0);
-	atomic_set(&rdev->read_errors, 0);
-	atomic_set(&rdev->corrected_errors, 0);
-
 	size = rdev->bdev->bd_inode->i_size >> BLOCK_SIZE_BITS;
 	if (!size) {
 		printk(KERN_WARNING 
@@ -2768,9 +2823,6 @@ static mdk_rdev_t *md_import_device(dev_t newdev, int super_format, int super_mi
 		}
 	}
 
-	INIT_LIST_HEAD(&rdev->same_set);
-	init_waitqueue_head(&rdev->blocked_wait);
-
 	return rdev;
 
 abort_free:
@@ -2961,7 +3013,9 @@ level_store(mddev_t *mddev, const char *buf, size_t len)
 	 *  - new personality will access other array.
 	 */
 
-	if (mddev->sync_thread || mddev->reshape_position != MaxSector)
+	if (mddev->sync_thread ||
+	    mddev->reshape_position != MaxSector ||
+	    mddev->sysfs_active)
 		return -EBUSY;
 
 	if (!mddev->pers->quiesce) {
@@ -3438,7 +3492,7 @@ array_state_store(mddev_t *mddev, const char *buf, size_t len)
 	if (err)
 		return err;
 	else {
-		sysfs_notify_dirent(mddev->sysfs_state);
+		sysfs_notify_dirent_safe(mddev->sysfs_state);
 		return len;
 	}
 }
@@ -3736,7 +3790,7 @@ action_store(mddev_t *mddev, const char *page, size_t len)
 	}
 	set_bit(MD_RECOVERY_NEEDED, &mddev->recovery);
 	md_wakeup_thread(mddev->thread);
-	sysfs_notify_dirent(mddev->sysfs_action);
+	sysfs_notify_dirent_safe(mddev->sysfs_action);
 	return len;
 }
 
@@ -4282,13 +4336,14 @@ static int md_alloc(dev_t dev, char *name)
 		       disk->disk_name);
 		error = 0;
 	}
-	if (sysfs_create_group(&mddev->kobj, &md_bitmap_group))
+	if (mddev->kobj.sd &&
+	    sysfs_create_group(&mddev->kobj, &md_bitmap_group))
 		printk(KERN_DEBUG "pointless warning\n");
  abort:
 	mutex_unlock(&disks_mutex);
-	if (!error) {
+	if (!error && mddev->kobj.sd) {
 		kobject_uevent(&mddev->kobj, KOBJ_ADD);
-		mddev->sysfs_state = sysfs_get_dirent(mddev->kobj.sd, NULL, "array_state");
+		mddev->sysfs_state = sysfs_get_dirent_safe(mddev->kobj.sd, "array_state");
 	}
 	mddev_put(mddev);
 	return error;
@@ -4326,14 +4381,14 @@ static void md_safemode_timeout(unsigned long data)
 	if (!atomic_read(&mddev->writes_pending)) {
 		mddev->safemode = 1;
 		if (mddev->external)
-			sysfs_notify_dirent(mddev->sysfs_state);
+			sysfs_notify_dirent_safe(mddev->sysfs_state);
 	}
 	md_wakeup_thread(mddev->thread);
 }
 
 static int start_dirty_degraded;
 
-static int md_run(mddev_t *mddev)
+int md_run(mddev_t *mddev)
 {
 	int err;
 	mdk_rdev_t *rdev;
@@ -4345,13 +4400,9 @@ static int md_run(mddev_t *mddev)
 
 	if (mddev->pers)
 		return -EBUSY;
-
-	/* These two calls synchronise us with the
-	 * sysfs_remove_group calls in mddev_unlock,
-	 * so they must have completed.
-	 */
-	mutex_lock(&mddev->open_mutex);
-	mutex_unlock(&mddev->open_mutex);
+	/* Cannot run until previous stop completes properly */
+	if (mddev->sysfs_active)
+		return -EBUSY;
 
 	/*
 	 * Analyze all RAID superblock(s)
@@ -4398,7 +4449,7 @@ static int md_run(mddev_t *mddev)
 				return -EINVAL;
 			}
 		}
-		sysfs_notify_dirent(rdev->sysfs_state);
+		sysfs_notify_dirent_safe(rdev->sysfs_state);
 	}
 
 	spin_lock(&pers_lock);
@@ -4497,11 +4548,12 @@ static int md_run(mddev_t *mddev)
 		return err;
 	}
 	if (mddev->pers->sync_request) {
-		if (sysfs_create_group(&mddev->kobj, &md_redundancy_group))
+		if (mddev->kobj.sd &&
+		    sysfs_create_group(&mddev->kobj, &md_redundancy_group))
 			printk(KERN_WARNING
 			       "md: cannot register extra attributes for %s\n",
 			       mdname(mddev));
-		mddev->sysfs_action = sysfs_get_dirent(mddev->kobj.sd, NULL, "sync_action");
+		mddev->sysfs_action = sysfs_get_dirent_safe(mddev->kobj.sd, "sync_action");
 	} else if (mddev->ro == 2) /* auto-readonly not meaningful */
 		mddev->ro = 0;
 
@@ -4519,8 +4571,7 @@ static int md_run(mddev_t *mddev)
 			char nm[20];
 			sprintf(nm, "rd%d", rdev->raid_disk);
 			if (sysfs_create_link(&mddev->kobj, &rdev->kobj, nm))
-				printk("md: cannot register %s for %s\n",
-				       nm, mdname(mddev));
+				/* failure here is OK */;
 		}
 	
 	set_bit(MD_RECOVERY_NEEDED, &mddev->recovery);
@@ -4532,12 +4583,12 @@ static int md_run(mddev_t *mddev)
 	md_wakeup_thread(mddev->sync_thread); /* possibly kick off a reshape */
 
 	md_new_event(mddev);
-	sysfs_notify_dirent(mddev->sysfs_state);
-	if (mddev->sysfs_action)
-		sysfs_notify_dirent(mddev->sysfs_action);
+	sysfs_notify_dirent_safe(mddev->sysfs_state);
+	sysfs_notify_dirent_safe(mddev->sysfs_action);
 	sysfs_notify(&mddev->kobj, NULL, "degraded");
 	return 0;
 }
+EXPORT_SYMBOL_GPL(md_run);
 
 static int do_md_run(mddev_t *mddev)
 {
@@ -4546,7 +4597,11 @@ static int do_md_run(mddev_t *mddev)
 	err = md_run(mddev);
 	if (err)
 		goto out;
-
+	err = bitmap_load(mddev);
+	if (err) {
+		bitmap_destroy(mddev);
+		goto out;
+	}
 	set_capacity(mddev->gendisk, mddev->array_sectors);
 	revalidate_disk(mddev->gendisk);
 	kobject_uevent(&disk_to_dev(mddev->gendisk)->kobj, KOBJ_CHANGE);
@@ -4574,7 +4629,7 @@ static int restart_array(mddev_t *mddev)
 	set_bit(MD_RECOVERY_NEEDED, &mddev->recovery);
 	md_wakeup_thread(mddev->thread);
 	md_wakeup_thread(mddev->sync_thread);
-	sysfs_notify_dirent(mddev->sysfs_state);
+	sysfs_notify_dirent_safe(mddev->sysfs_state);
 	return 0;
 }
 
@@ -4645,9 +4700,10 @@ static void md_clean(mddev_t *mddev)
 	mddev->bitmap_info.chunksize = 0;
 	mddev->bitmap_info.daemon_sleep = 0;
 	mddev->bitmap_info.max_write_behind = 0;
+	mddev->plug = NULL;
 }
 
-static void md_stop_writes(mddev_t *mddev)
+void md_stop_writes(mddev_t *mddev)
 {
 	if (mddev->sync_thread) {
 		set_bit(MD_RECOVERY_FROZEN, &mddev->recovery);
@@ -4667,11 +4723,10 @@ static void md_stop_writes(mddev_t *mddev)
 		md_update_sb(mddev, 1);
 	}
 }
+EXPORT_SYMBOL_GPL(md_stop_writes);
 
-static void md_stop(mddev_t *mddev)
+void md_stop(mddev_t *mddev)
 {
-	md_stop_writes(mddev);
-
 	mddev->pers->stop(mddev);
 	if (mddev->pers->sync_request && mddev->to_remove == NULL)
 		mddev->to_remove = &md_redundancy_group;
@@ -4679,6 +4734,7 @@ static void md_stop(mddev_t *mddev)
 	mddev->pers = NULL;
 	clear_bit(MD_RECOVERY_FROZEN, &mddev->recovery);
 }
+EXPORT_SYMBOL_GPL(md_stop);
 
 static int md_set_readonly(mddev_t *mddev, int is_open)
 {
@@ -4698,7 +4754,7 @@ static int md_set_readonly(mddev_t *mddev, int is_open)
 		mddev->ro = 1;
 		set_disk_ro(mddev->gendisk, 1);
 		clear_bit(MD_RECOVERY_FROZEN, &mddev->recovery);
-		sysfs_notify_dirent(mddev->sysfs_state);
+		sysfs_notify_dirent_safe(mddev->sysfs_state);
 		err = 0;	
 	}
 out:
@@ -4712,26 +4768,29 @@ out:
  */
 static int do_md_stop(mddev_t * mddev, int mode, int is_open)
 {
-	int err = 0;
 	struct gendisk *disk = mddev->gendisk;
 	mdk_rdev_t *rdev;
 
 	mutex_lock(&mddev->open_mutex);
-	if (atomic_read(&mddev->openers) > is_open) {
+	if (atomic_read(&mddev->openers) > is_open ||
+	    mddev->sysfs_active) {
 		printk("md: %s still in use.\n",mdname(mddev));
-		err = -EBUSY;
-	} else if (mddev->pers) {
+		mutex_unlock(&mddev->open_mutex);
+		return -EBUSY;
+	}
 
+	if (mddev->pers) {
 		if (mddev->ro)
 			set_disk_ro(disk, 0);
 
+		md_stop_writes(mddev);
 		md_stop(mddev);
 		mddev->queue->merge_bvec_fn = NULL;
 		mddev->queue->unplug_fn = NULL;
 		mddev->queue->backing_dev_info.congested_fn = NULL;
 
 		/* tell userspace to handle 'inactive' */
-		sysfs_notify_dirent(mddev->sysfs_state);
+		sysfs_notify_dirent_safe(mddev->sysfs_state);
 
 		list_for_each_entry(rdev, &mddev->disks, same_set)
 			if (rdev->raid_disk >= 0) {
@@ -4741,21 +4800,17 @@ static int do_md_stop(mddev_t * mddev, int mode, int is_open)
 			}
 
 		set_capacity(disk, 0);
+		mutex_unlock(&mddev->open_mutex);
 		revalidate_disk(disk);
 
 		if (mddev->ro)
 			mddev->ro = 0;
-		
-		err = 0;
-	}
-	mutex_unlock(&mddev->open_mutex);
-	if (err)
-		return err;
+	} else
+		mutex_unlock(&mddev->open_mutex);
 	/*
 	 * Free resources if final stop
 	 */
 	if (mode == 0) {
-
 		printk(KERN_INFO "md: %s stopped.\n", mdname(mddev));
 
 		bitmap_destroy(mddev);
@@ -4772,13 +4827,11 @@ static int do_md_stop(mddev_t * mddev, int mode, int is_open)
 		kobject_uevent(&disk_to_dev(mddev->gendisk)->kobj, KOBJ_CHANGE);
 		if (mddev->hold_active == UNTIL_STOP)
 			mddev->hold_active = 0;
-
 	}
-	err = 0;
 	blk_integrity_unregister(disk);
 	md_new_event(mddev);
-	sysfs_notify_dirent(mddev->sysfs_state);
-	return err;
+	sysfs_notify_dirent_safe(mddev->sysfs_state);
+	return 0;
 }
 
 #ifndef MODULE
@@ -5139,7 +5192,7 @@ static int add_new_disk(mddev_t * mddev, mdu_disk_info_t *info)
 		if (err)
 			export_rdev(rdev);
 		else
-			sysfs_notify_dirent(rdev->sysfs_state);
+			sysfs_notify_dirent_safe(rdev->sysfs_state);
 
 		md_update_sb(mddev, 1);
 		if (mddev->degraded)
@@ -5332,8 +5385,11 @@ static int set_bitmap_file(mddev_t *mddev, int fd)
 	err = 0;
 	if (mddev->pers) {
 		mddev->pers->quiesce(mddev, 1);
-		if (fd >= 0)
+		if (fd >= 0) {
 			err = bitmap_create(mddev);
+			if (!err)
+				err = bitmap_load(mddev);
+		}
 		if (fd < 0 || err) {
 			bitmap_destroy(mddev);
 			fd = -1; /* make sure to put the file */
@@ -5582,6 +5638,8 @@ static int update_array_info(mddev_t *mddev, mdu_array_info_t *info)
 				mddev->bitmap_info.default_offset;
 			mddev->pers->quiesce(mddev, 1);
 			rv = bitmap_create(mddev);
+			if (!rv)
+				rv = bitmap_load(mddev);
 			if (rv)
 				bitmap_destroy(mddev);
 			mddev->pers->quiesce(mddev, 0);
@@ -5814,7 +5872,7 @@ static int md_ioctl(struct block_device *bdev, fmode_t mode,
 	if (_IOC_TYPE(cmd) == MD_MAJOR && mddev->ro && mddev->pers) {
 		if (mddev->ro == 2) {
 			mddev->ro = 0;
-			sysfs_notify_dirent(mddev->sysfs_state);
+			sysfs_notify_dirent_safe(mddev->sysfs_state);
 			set_bit(MD_RECOVERY_NEEDED, &mddev->recovery);
 			md_wakeup_thread(mddev->thread);
 		} else {
@@ -6065,10 +6123,12 @@ void md_error(mddev_t *mddev, mdk_rdev_t *rdev)
 	mddev->pers->error_handler(mddev,rdev);
 	if (mddev->degraded)
 		set_bit(MD_RECOVERY_RECOVER, &mddev->recovery);
-	sysfs_notify_dirent(rdev->sysfs_state);
+	sysfs_notify_dirent_safe(rdev->sysfs_state);
 	set_bit(MD_RECOVERY_INTR, &mddev->recovery);
 	set_bit(MD_RECOVERY_NEEDED, &mddev->recovery);
 	md_wakeup_thread(mddev->thread);
+	if (mddev->event_work.func)
+		schedule_work(&mddev->event_work);
 	md_new_event_inintr(mddev);
 }
 
@@ -6526,7 +6586,7 @@ void md_write_start(mddev_t *mddev, struct bio *bi)
 		spin_unlock_irq(&mddev->write_lock);
 	}
 	if (did_change)
-		sysfs_notify_dirent(mddev->sysfs_state);
+		sysfs_notify_dirent_safe(mddev->sysfs_state);
 	wait_event(mddev->sb_wait,
 		   !test_bit(MD_CHANGE_CLEAN, &mddev->flags) &&
 		   !test_bit(MD_CHANGE_PENDING, &mddev->flags));
@@ -6569,7 +6629,7 @@ int md_allow_write(mddev_t *mddev)
 			mddev->safemode = 1;
 		spin_unlock_irq(&mddev->write_lock);
 		md_update_sb(mddev, 0);
-		sysfs_notify_dirent(mddev->sysfs_state);
+		sysfs_notify_dirent_safe(mddev->sysfs_state);
 	} else
 		spin_unlock_irq(&mddev->write_lock);
 
@@ -6580,6 +6640,14 @@ int md_allow_write(mddev_t *mddev)
 }
 EXPORT_SYMBOL_GPL(md_allow_write);
 
+void md_unplug(mddev_t *mddev)
+{
+	if (mddev->queue)
+		blk_unplug(mddev->queue);
+	if (mddev->plug)
+		mddev->plug->unplug_fn(mddev->plug);
+}
+
 #define SYNC_MARKS	10
 #define	SYNC_MARK_STEP	(3*HZ)
 void md_do_sync(mddev_t *mddev)
@@ -6758,12 +6826,13 @@ void md_do_sync(mddev_t *mddev)
 		     >= mddev->resync_max - mddev->curr_resync_completed
 			    )) {
 			/* time to update curr_resync_completed */
-			blk_unplug(mddev->queue);
+			md_unplug(mddev);
 			wait_event(mddev->recovery_wait,
 				   atomic_read(&mddev->recovery_active) == 0);
 			mddev->curr_resync_completed =
 				mddev->curr_resync;
-			set_bit(MD_CHANGE_CLEAN, &mddev->flags);
+			if (mddev->persistent)
+				set_bit(MD_CHANGE_CLEAN, &mddev->flags);
 			sysfs_notify(&mddev->kobj, NULL, "sync_completed");
 		}
 
@@ -6835,7 +6904,7 @@ void md_do_sync(mddev_t *mddev)
 		 * about not overloading the IO subsystem. (things like an
 		 * e2fsck being done on the RAID array should execute fast)
 		 */
-		blk_unplug(mddev->queue);
+		md_unplug(mddev);
 		cond_resched();
 
 		currspeed = ((unsigned long)(io_sectors-mddev->resync_mark_cnt))/2
@@ -6854,7 +6923,7 @@ void md_do_sync(mddev_t *mddev)
 	 * this also signals 'finished resyncing' to md_stop
 	 */
  out:
-	blk_unplug(mddev->queue);
+	md_unplug(mddev);
 
 	wait_event(mddev->recovery_wait, !atomic_read(&mddev->recovery_active));
 
@@ -6956,10 +7025,7 @@ static int remove_and_add_spares(mddev_t *mddev)
 					sprintf(nm, "rd%d", rdev->raid_disk);
 					if (sysfs_create_link(&mddev->kobj,
 							      &rdev->kobj, nm))
-						printk(KERN_WARNING
-						       "md: cannot register "
-						       "%s for %s\n",
-						       nm, mdname(mddev));
+						/* failure here is OK */;
 					spares++;
 					md_new_event(mddev);
 					set_bit(MD_CHANGE_DEVS, &mddev->flags);
@@ -7052,7 +7118,7 @@ void md_check_recovery(mddev_t *mddev)
 				mddev->safemode = 0;
 			spin_unlock_irq(&mddev->write_lock);
 			if (did_change)
-				sysfs_notify_dirent(mddev->sysfs_state);
+				sysfs_notify_dirent_safe(mddev->sysfs_state);
 		}
 
 		if (mddev->flags)
@@ -7091,7 +7157,7 @@ void md_check_recovery(mddev_t *mddev)
 			mddev->recovery = 0;
 			/* flag recovery needed just to double check */
 			set_bit(MD_RECOVERY_NEEDED, &mddev->recovery);
-			sysfs_notify_dirent(mddev->sysfs_action);
+			sysfs_notify_dirent_safe(mddev->sysfs_action);
 			md_new_event(mddev);
 			goto unlock;
 		}
@@ -7153,7 +7219,7 @@ void md_check_recovery(mddev_t *mddev)
 				mddev->recovery = 0;
 			} else
 				md_wakeup_thread(mddev->sync_thread);
-			sysfs_notify_dirent(mddev->sysfs_action);
+			sysfs_notify_dirent_safe(mddev->sysfs_action);
 			md_new_event(mddev);
 		}
 	unlock:
@@ -7162,7 +7228,7 @@ void md_check_recovery(mddev_t *mddev)
 			if (test_and_clear_bit(MD_RECOVERY_RECOVER,
 					       &mddev->recovery))
 				if (mddev->sysfs_action)
-					sysfs_notify_dirent(mddev->sysfs_action);
+					sysfs_notify_dirent_safe(mddev->sysfs_action);
 		}
 		mddev_unlock(mddev);
 	}
@@ -7170,7 +7236,7 @@ void md_check_recovery(mddev_t *mddev)
 
 void md_wait_for_blocked_rdev(mdk_rdev_t *rdev, mddev_t *mddev)
 {
-	sysfs_notify_dirent(rdev->sysfs_state);
+	sysfs_notify_dirent_safe(rdev->sysfs_state);
 	wait_event_timeout(rdev->blocked_wait,
 			   !test_bit(Blocked, &rdev->flags),
 			   msecs_to_jiffies(5000));

drivers/md/md.h

@@ -29,6 +29,26 @@
 typedef struct mddev_s mddev_t;
 typedef struct mdk_rdev_s mdk_rdev_t;
 
+/* generic plugging support - like that provided with request_queue,
+ * but does not require a request_queue
+ */
+struct plug_handle {
+	void			(*unplug_fn)(struct plug_handle *);
+	struct timer_list	unplug_timer;
+	struct work_struct	unplug_work;
+	unsigned long		unplug_flag;
+};
+#define	PLUGGED_FLAG 1
+void plugger_init(struct plug_handle *plug,
+		  void (*unplug_fn)(struct plug_handle *));
+void plugger_set_plug(struct plug_handle *plug);
+int plugger_remove_plug(struct plug_handle *plug);
+static inline void plugger_flush(struct plug_handle *plug)
+{
+	del_timer_sync(&plug->unplug_timer);
+	cancel_work_sync(&plug->unplug_work);
+}
+
 /*
  * MD's 'extended' device
  */
@@ -125,6 +145,10 @@ struct mddev_s
 	int				suspended;
 	atomic_t			active_io;
 	int				ro;
+	int				sysfs_active; /* set when sysfs deletes
+						       * are happening, so run/
+						       * takeover/stop are not safe
+						       */
 
 	struct gendisk			*gendisk;
 
@@ -297,9 +321,14 @@ struct mddev_s
 							 * hot-adding a bitmap.  It should
 							 * eventually be settable by sysfs.
 							 */
+		/* When md is serving under dm, it might use a
+		 * dirty_log to store the bits.
+		 */
+		struct dm_dirty_log *log;
+
 		struct mutex		mutex;
 		unsigned long		chunksize;
-		unsigned long		daemon_sleep; /* how many seconds between updates? */
+		unsigned long		daemon_sleep; /* how many jiffies between updates? */
 		unsigned long		max_write_behind; /* write-behind mode */
 		int			external;
 	} bitmap_info;
@@ -308,6 +337,8 @@ struct mddev_s
 	struct list_head		all_mddevs;
 
 	struct attribute_group		*to_remove;
+	struct plug_handle		*plug; /* if used by personality */
+
 	/* Generic barrier handling.
 	 * If there is a pending barrier request, all other
 	 * writes are blocked while the devices are flushed.
@@ -318,6 +349,7 @@ struct mddev_s
 	struct bio *barrier;
 	atomic_t flush_pending;
 	struct work_struct barrier_work;
+	struct work_struct event_work;	/* used by dm to report failure event */
 };
 
 
@@ -382,6 +414,18 @@ struct md_sysfs_entry {
 };
 extern struct attribute_group md_bitmap_group;
 
+static inline struct sysfs_dirent *sysfs_get_dirent_safe(struct sysfs_dirent *sd, char *name)
+{
+	if (sd)
+		return sysfs_get_dirent(sd, NULL, name);
+	return sd;
+}
+static inline void sysfs_notify_dirent_safe(struct sysfs_dirent *sd)
+{
+	if (sd)
+		sysfs_notify_dirent(sd);
+}
+
 static inline char * mdname (mddev_t * mddev)
 {
 	return mddev->gendisk ? mddev->gendisk->disk_name : "mdX";
@@ -474,5 +518,14 @@ extern int md_integrity_register(mddev_t *mddev);
 extern void md_integrity_add_rdev(mdk_rdev_t *rdev, mddev_t *mddev);
 extern int strict_strtoul_scaled(const char *cp, unsigned long *res, int scale);
 extern void restore_bitmap_write_access(struct file *file);
+extern void md_unplug(mddev_t *mddev);
+
+extern void mddev_init(mddev_t *mddev);
+extern int md_run(mddev_t *mddev);
+extern void md_stop(mddev_t *mddev);
+extern void md_stop_writes(mddev_t *mddev);
+extern void md_rdev_init(mdk_rdev_t *rdev);
 
+extern void mddev_suspend(mddev_t *mddev);
+extern void mddev_resume(mddev_t *mddev);
 #endif /* _MD_MD_H */

drivers/md/raid10.c

@@ -825,11 +825,29 @@ static int make_request(mddev_t *mddev, 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(mddev, &bp->bio1))
 			generic_make_request(&bp->bio1);
 		if (make_request(mddev, &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:

drivers/md/raid5.c

@@ -201,11 +201,11 @@ static void __release_stripe(raid5_conf_t *conf, struct stripe_head *sh)
 		if (test_bit(STRIPE_HANDLE, &sh->state)) {
 			if (test_bit(STRIPE_DELAYED, &sh->state)) {
 				list_add_tail(&sh->lru, &conf->delayed_list);
-				blk_plug_device(conf->mddev->queue);
+				plugger_set_plug(&conf->plug);
 			} else if (test_bit(STRIPE_BIT_DELAY, &sh->state) &&
 				   sh->bm_seq - conf->seq_write > 0) {
 				list_add_tail(&sh->lru, &conf->bitmap_list);
-				blk_plug_device(conf->mddev->queue);
+				plugger_set_plug(&conf->plug);
 			} else {
 				clear_bit(STRIPE_BIT_DELAY, &sh->state);
 				list_add_tail(&sh->lru, &conf->handle_list);
@@ -434,7 +434,6 @@ static int has_failed(raid5_conf_t *conf)
 }
 
 static void unplug_slaves(mddev_t *mddev);
-static void raid5_unplug_device(struct request_queue *q);
 
 static struct stripe_head *
 get_active_stripe(raid5_conf_t *conf, sector_t sector,
@@ -464,7 +463,7 @@ get_active_stripe(raid5_conf_t *conf, sector_t sector,
 						     < (conf->max_nr_stripes *3/4)
 						     || !conf->inactive_blocked),
 						    conf->device_lock,
-						    raid5_unplug_device(conf->mddev->queue)
+						    md_raid5_unplug_device(conf)
 					);
 				conf->inactive_blocked = 0;
 			} else
@@ -1337,10 +1336,14 @@ static int grow_stripes(raid5_conf_t *conf, int num)
 	struct kmem_cache *sc;
 	int devs = max(conf->raid_disks, conf->previous_raid_disks);
 
-	sprintf(conf->cache_name[0],
-		"raid%d-%s", conf->level, mdname(conf->mddev));
-	sprintf(conf->cache_name[1],
-		"raid%d-%s-alt", conf->level, mdname(conf->mddev));
+	if (conf->mddev->gendisk)
+		sprintf(conf->cache_name[0],
+			"raid%d-%s", conf->level, mdname(conf->mddev));
+	else
+		sprintf(conf->cache_name[0],
+			"raid%d-%p", conf->level, conf->mddev);
+	sprintf(conf->cache_name[1], "%s-alt", conf->cache_name[0]);
+
 	conf->active_name = 0;
 	sc = kmem_cache_create(conf->cache_name[conf->active_name],
 			       sizeof(struct stripe_head)+(devs-1)*sizeof(struct r5dev),
@@ -3614,7 +3617,7 @@ static void raid5_activate_delayed(raid5_conf_t *conf)
 			list_add_tail(&sh->lru, &conf->hold_list);
 		}
 	} else
-		blk_plug_device(conf->mddev->queue);
+		plugger_set_plug(&conf->plug);
 }
 
 static void activate_bit_delay(raid5_conf_t *conf)
@@ -3655,36 +3658,44 @@ static void unplug_slaves(mddev_t *mddev)
 	rcu_read_unlock();
 }
 
-static void raid5_unplug_device(struct request_queue *q)
+void md_raid5_unplug_device(raid5_conf_t *conf)
 {
-	mddev_t *mddev = q->queuedata;
-	raid5_conf_t *conf = mddev->private;
 	unsigned long flags;
 
 	spin_lock_irqsave(&conf->device_lock, flags);
 
-	if (blk_remove_plug(q)) {
+	if (plugger_remove_plug(&conf->plug)) {
 		conf->seq_flush++;
 		raid5_activate_delayed(conf);
 	}
-	md_wakeup_thread(mddev->thread);
+	md_wakeup_thread(conf->mddev->thread);
 
 	spin_unlock_irqrestore(&conf->device_lock, flags);
 
-	unplug_slaves(mddev);
+	unplug_slaves(conf->mddev);
 }
+EXPORT_SYMBOL_GPL(md_raid5_unplug_device);
 
-static int raid5_congested(void *data, int bits)
+static void raid5_unplug(struct plug_handle *plug)
+{
+	raid5_conf_t *conf = container_of(plug, raid5_conf_t, plug);
+	md_raid5_unplug_device(conf);
+}
+
+static void raid5_unplug_queue(struct request_queue *q)
+{
+	mddev_t *mddev = q->queuedata;
+	md_raid5_unplug_device(mddev->private);
+}
+
+int md_raid5_congested(mddev_t *mddev, int bits)
 {
-	mddev_t *mddev = data;
 	raid5_conf_t *conf = mddev->private;
 
 	/* 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)
@@ -3694,6 +3705,15 @@ static int raid5_congested(void *data, int bits)
 
 	return 0;
 }
+EXPORT_SYMBOL_GPL(md_raid5_congested);
+
+static int raid5_congested(void *data, int bits)
+{
+	mddev_t *mddev = data;
+
+	return mddev_congested(mddev, bits) ||
+		md_raid5_congested(mddev, bits);
+}
 
 /* We want read requests to align with chunks where possible,
  * but write requests don't need to.
@@ -4075,7 +4095,7 @@ static int make_request(mddev_t *mddev, struct bio * bi)
 				 * add failed due to overlap.  Flush everything
 				 * and wait a while
 				 */
-				raid5_unplug_device(mddev->queue);
+				md_raid5_unplug_device(conf);
 				release_stripe(sh);
 				schedule();
 				goto retry;
@@ -4566,23 +4586,15 @@ raid5_show_stripe_cache_size(mddev_t *mddev, char *page)
 		return 0;
 }
 
-static ssize_t
-raid5_store_stripe_cache_size(mddev_t *mddev, const char *page, size_t len)
+int
+raid5_set_cache_size(mddev_t *mddev, int size)
 {
 	raid5_conf_t *conf = mddev->private;
-	unsigned long new;
 	int err;
 
-	if (len >= PAGE_SIZE)
+	if (size <= 16 || size > 32768)
 		return -EINVAL;
-	if (!conf)
-		return -ENODEV;
-
-	if (strict_strtoul(page, 10, &new))
-		return -EINVAL;
-	if (new <= 16 || new > 32768)
-		return -EINVAL;
-	while (new < conf->max_nr_stripes) {
+	while (size < conf->max_nr_stripes) {
 		if (drop_one_stripe(conf))
 			conf->max_nr_stripes--;
 		else
@@ -4591,11 +4603,32 @@ raid5_store_stripe_cache_size(mddev_t *mddev, const char *page, size_t len)
 	err = md_allow_write(mddev);
 	if (err)
 		return err;
-	while (new > conf->max_nr_stripes) {
+	while (size > conf->max_nr_stripes) {
 		if (grow_one_stripe(conf))
 			conf->max_nr_stripes++;
 		else break;
 	}
+	return 0;
+}
+EXPORT_SYMBOL(raid5_set_cache_size);
+
+static ssize_t
+raid5_store_stripe_cache_size(mddev_t *mddev, const char *page, size_t len)
+{
+	raid5_conf_t *conf = mddev->private;
+	unsigned long new;
+	int err;
+
+	if (len >= PAGE_SIZE)
+		return -EINVAL;
+	if (!conf)
+		return -ENODEV;
+
+	if (strict_strtoul(page, 10, &new))
+		return -EINVAL;
+	err = raid5_set_cache_size(mddev, new);
+	if (err)
+		return err;
 	return len;
 }
 
@@ -4958,7 +4991,7 @@ static int only_parity(int raid_disk, int algo, int raid_disks, int max_degraded
 static int run(mddev_t *mddev)
 {
 	raid5_conf_t *conf;
-	int working_disks = 0, chunk_size;
+	int working_disks = 0;
 	int dirty_parity_disks = 0;
 	mdk_rdev_t *rdev;
 	sector_t reshape_offset = 0;
@@ -5144,42 +5177,47 @@ static int run(mddev_t *mddev)
 							"reshape");
 	}
 
-	/* read-ahead size must cover two whole stripes, which is
-	 * 2 * (datadisks) * chunksize where 'n' is the number of raid devices
-	 */
-	{
-		int data_disks = conf->previous_raid_disks - conf->max_degraded;
-		int stripe = data_disks *
-			((mddev->chunk_sectors << 9) / PAGE_SIZE);
-		if (mddev->queue->backing_dev_info.ra_pages < 2 * stripe)
-			mddev->queue->backing_dev_info.ra_pages = 2 * stripe;
-	}
 
 	/* Ok, everything is just fine now */
 	if (mddev->to_remove == &raid5_attrs_group)
 		mddev->to_remove = NULL;
-	else if (sysfs_create_group(&mddev->kobj, &raid5_attrs_group))
+	else if (mddev->kobj.sd &&
+	    sysfs_create_group(&mddev->kobj, &raid5_attrs_group))
 		printk(KERN_WARNING
-		       "md/raid:%s: failed to create sysfs attributes.\n",
+		       "raid5: failed to create sysfs attributes for %s\n",
 		       mdname(mddev));
+	md_set_array_sectors(mddev, raid5_size(mddev, 0, 0));
 
-	mddev->queue->queue_lock = &conf->device_lock;
+	plugger_init(&conf->plug, raid5_unplug);
+	mddev->plug = &conf->plug;
+	if (mddev->queue) {
+		int chunk_size;
+		/* read-ahead size must cover two whole stripes, which
+		 * is 2 * (datadisks) * chunksize where 'n' is the
+		 * number of raid devices
+		 */
+		int data_disks = conf->previous_raid_disks - conf->max_degraded;
+		int stripe = data_disks *
+			((mddev->chunk_sectors << 9) / PAGE_SIZE);
+		if (mddev->queue->backing_dev_info.ra_pages < 2 * stripe)
+			mddev->queue->backing_dev_info.ra_pages = 2 * stripe;
 
-	mddev->queue->unplug_fn = raid5_unplug_device;
-	mddev->queue->backing_dev_info.congested_data = mddev;
-	mddev->queue->backing_dev_info.congested_fn = raid5_congested;
+		blk_queue_merge_bvec(mddev->queue, raid5_mergeable_bvec);
 
-	md_set_array_sectors(mddev, raid5_size(mddev, 0, 0));
+		mddev->queue->backing_dev_info.congested_data = mddev;
+		mddev->queue->backing_dev_info.congested_fn = raid5_congested;
+		mddev->queue->queue_lock = &conf->device_lock;
+		mddev->queue->unplug_fn = raid5_unplug_queue;
 
-	blk_queue_merge_bvec(mddev->queue, raid5_mergeable_bvec);
-	chunk_size = mddev->chunk_sectors << 9;
-	blk_queue_io_min(mddev->queue, chunk_size);
-	blk_queue_io_opt(mddev->queue, chunk_size *
-			 (conf->raid_disks - conf->max_degraded));
+		chunk_size = mddev->chunk_sectors << 9;
+		blk_queue_io_min(mddev->queue, chunk_size);
+		blk_queue_io_opt(mddev->queue, chunk_size *
+				 (conf->raid_disks - conf->max_degraded));
 
-	list_for_each_entry(rdev, &mddev->disks, same_set)
-		disk_stack_limits(mddev->gendisk, rdev->bdev,
-				  rdev->data_offset << 9);
+		list_for_each_entry(rdev, &mddev->disks, same_set)
+			disk_stack_limits(mddev->gendisk, rdev->bdev,
+					  rdev->data_offset << 9);
+	}
 
 	return 0;
 abort:
@@ -5200,8 +5238,9 @@ static int stop(mddev_t *mddev)
 
 	md_unregister_thread(mddev->thread);
 	mddev->thread = NULL;
-	mddev->queue->backing_dev_info.congested_fn = NULL;
-	blk_sync_queue(mddev->queue); /* the unplug fn references 'conf'*/
+	if (mddev->queue)
+		mddev->queue->backing_dev_info.congested_fn = NULL;
+	plugger_flush(&conf->plug); /* the unplug fn references 'conf'*/
 	free_conf(conf);
 	mddev->private = NULL;
 	mddev->to_remove = &raid5_attrs_group;
@@ -5545,10 +5584,7 @@ static int raid5_start_reshape(mddev_t *mddev)
 				sprintf(nm, "rd%d", rdev->raid_disk);
 				if (sysfs_create_link(&mddev->kobj,
 						      &rdev->kobj, nm))
-					printk(KERN_WARNING
-					       "md/raid:%s: failed to create "
-					       " link %s\n",
-					       mdname(mddev), nm);
+					/* Failure here is OK */;
 			} else
 				break;
 		}
@@ -5603,7 +5639,7 @@ static void end_reshape(raid5_conf_t *conf)
 		/* read-ahead size must cover two whole stripes, which is
 		 * 2 * (datadisks) * chunksize where 'n' is the number of raid devices
 		 */
-		{
+		if (conf->mddev->queue) {
 			int data_disks = conf->raid_disks - conf->max_degraded;
 			int stripe = data_disks * ((conf->chunk_sectors << 9)
 						   / PAGE_SIZE);

drivers/md/raid5.h

@@ -388,7 +388,7 @@ struct raid5_private_data {
 	 * two caches.
 	 */
 	int			active_name;
-	char			cache_name[2][20];
+	char			cache_name[2][32];
 	struct kmem_cache		*slab_cache; /* for allocating stripes */
 
 	int			seq_flush, seq_write;
@@ -398,6 +398,9 @@ struct raid5_private_data {
 					    * (fresh device added).
 					    * Cleared when a sync completes.
 					    */
+
+	struct plug_handle	plug;
+
 	/* per cpu variables */
 	struct raid5_percpu {
 		struct page	*spare_page; /* Used when checking P/Q in raid6 */
@@ -497,4 +500,8 @@ static inline int algorithm_is_DDF(int layout)
 {
 	return layout >= 8 && layout <= 10;
 }
+
+extern int md_raid5_congested(mddev_t *mddev, int bits);
+extern void md_raid5_unplug_device(raid5_conf_t *conf);
+extern int raid5_set_cache_size(mddev_t *mddev, int size);
 #endif

lib/Kconfig

@@ -7,6 +7,9 @@ config BINARY_PRINTF
 
 menu "Library routines"
 
+config RAID6_PQ
+	tristate
+
 config BITREVERSE
 	tristate
 

lib/Makefile

@@ -69,6 +69,7 @@ obj-$(CONFIG_ZLIB_DEFLATE) += zlib_deflate/
 obj-$(CONFIG_REED_SOLOMON) += reed_solomon/
 obj-$(CONFIG_LZO_COMPRESS) += lzo/
 obj-$(CONFIG_LZO_DECOMPRESS) += lzo/
+obj-$(CONFIG_RAID6_PQ) += raid6/
 
 lib-$(CONFIG_DECOMPRESS_GZIP) += decompress_inflate.o
 lib-$(CONFIG_DECOMPRESS_BZIP2) += decompress_bunzip2.o

lib/raid6/Makefile

@@ -0,0 +1,78 @@
+obj-$(CONFIG_RAID6_PQ)	+= raid6_pq.o
+
+raid6_pq-y	+= raid6algos.o raid6recov.o raid6tables.o \
+		   raid6int1.o raid6int2.o raid6int4.o \
+		   raid6int8.o raid6int16.o raid6int32.o \
+		   raid6altivec1.o raid6altivec2.o raid6altivec4.o \
+		   raid6altivec8.o \
+		   raid6mmx.o raid6sse1.o raid6sse2.o
+hostprogs-y	+= mktables
+
+quiet_cmd_unroll = UNROLL  $@
+      cmd_unroll = $(AWK) -f$(srctree)/$(src)/unroll.awk -vN=$(UNROLL) \
+                   < $< > $@ || ( rm -f $@ && exit 1 )
+
+ifeq ($(CONFIG_ALTIVEC),y)
+altivec_flags := -maltivec -mabi=altivec
+endif
+
+targets += raid6int1.c
+$(obj)/raid6int1.c:   UNROLL := 1
+$(obj)/raid6int1.c:   $(src)/raid6int.uc $(src)/unroll.awk FORCE
+	$(call if_changed,unroll)
+
+targets += raid6int2.c
+$(obj)/raid6int2.c:   UNROLL := 2
+$(obj)/raid6int2.c:   $(src)/raid6int.uc $(src)/unroll.awk FORCE
+	$(call if_changed,unroll)
+
+targets += raid6int4.c
+$(obj)/raid6int4.c:   UNROLL := 4
+$(obj)/raid6int4.c:   $(src)/raid6int.uc $(src)/unroll.awk FORCE
+	$(call if_changed,unroll)
+
+targets += raid6int8.c
+$(obj)/raid6int8.c:   UNROLL := 8
+$(obj)/raid6int8.c:   $(src)/raid6int.uc $(src)/unroll.awk FORCE
+	$(call if_changed,unroll)
+
+targets += raid6int16.c
+$(obj)/raid6int16.c:  UNROLL := 16
+$(obj)/raid6int16.c:  $(src)/raid6int.uc $(src)/unroll.awk FORCE
+	$(call if_changed,unroll)
+
+targets += raid6int32.c
+$(obj)/raid6int32.c:  UNROLL := 32
+$(obj)/raid6int32.c:  $(src)/raid6int.uc $(src)/unroll.awk FORCE
+	$(call if_changed,unroll)
+
+CFLAGS_raid6altivec1.o += $(altivec_flags)
+targets += raid6altivec1.c
+$(obj)/raid6altivec1.c:   UNROLL := 1
+$(obj)/raid6altivec1.c:   $(src)/raid6altivec.uc $(src)/unroll.awk FORCE
+	$(call if_changed,unroll)
+
+CFLAGS_raid6altivec2.o += $(altivec_flags)
+targets += raid6altivec2.c
+$(obj)/raid6altivec2.c:   UNROLL := 2
+$(obj)/raid6altivec2.c:   $(src)/raid6altivec.uc $(src)/unroll.awk FORCE
+	$(call if_changed,unroll)
+
+CFLAGS_raid6altivec4.o += $(altivec_flags)
+targets += raid6altivec4.c
+$(obj)/raid6altivec4.c:   UNROLL := 4
+$(obj)/raid6altivec4.c:   $(src)/raid6altivec.uc $(src)/unroll.awk FORCE
+	$(call if_changed,unroll)
+
+CFLAGS_raid6altivec8.o += $(altivec_flags)
+targets += raid6altivec8.c
+$(obj)/raid6altivec8.c:   UNROLL := 8
+$(obj)/raid6altivec8.c:   $(src)/raid6altivec.uc $(src)/unroll.awk FORCE
+	$(call if_changed,unroll)
+
+quiet_cmd_mktable = TABLE   $@
+      cmd_mktable = $(obj)/mktables > $@ || ( rm -f $@ && exit 1 )
+
+targets += raid6tables.c
+$(obj)/raid6tables.c: $(obj)/mktables FORCE
+	$(call if_changed,mktable)