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

* 'for-linus' of git://neil.brown.name/md:
  md/raid5: remove unusual use of bio_iovec_idx()
  md/raid5: fix FUA request handling in ops_run_io()
  md/raid5: fix raid5_set_bi_hw_segments
  md:Documentation/md.txt - fix typo
  md/bitmap: remove unused fields from struct bitmap
  md/bitmap: use proper accessor macro
  md: check ->hot_remove_disk when removing disk
  md: Using poll  /proc/mdstat can monitor the events of adding a spare disks
  MD: use is_power_of_2 macro
  MD: raid5 do not set fullsync
  MD: support initial bitmap creation in-kernel
  MD: add sync_super to mddev_t struct
  MD: raid1 changes to allow use by device mapper
  MD: move thread wakeups into resume
  MD: possible typo
  MD: no sync IO while suspended
  MD: no integrity register if no gendisk

8 files changed, 152 insertions, 49 deletions

diff --git a/Documentation/md.txt b/Documentation/md.txt
index 2366b1c8cf1..f0eee83ff78 100644
--- a/Documentation/md.txt
+++ b/Documentation/md.txt
@@ -555,7 +555,7 @@ also have
    sync_min
    sync_max
      The two values, given as numbers of sectors, indicate a range
-     withing the array where 'check'/'repair' will operate. Must be
+     within the array where 'check'/'repair' will operate. Must be
      a multiple of chunk_size. When it reaches "sync_max" it will
      pause, rather than complete.
      You can use 'select' or 'poll' on "sync_completed" to wait for
diff --git a/drivers/md/bitmap.c b/drivers/md/bitmap.c
index 70bd738b8b9..574b09afedd 100644
--- a/drivers/md/bitmap.c
+++ b/drivers/md/bitmap.c
@@ -534,6 +534,82 @@ void bitmap_print_sb(struct bitmap *bitmap)
 	kunmap_atomic(sb, KM_USER0);
 }
 
+/*
+ * bitmap_new_disk_sb
+ * @bitmap
+ *
+ * This function is somewhat the reverse of bitmap_read_sb.  bitmap_read_sb
+ * reads and verifies the on-disk bitmap superblock and populates bitmap_info.
+ * This function verifies 'bitmap_info' and populates the on-disk bitmap
+ * structure, which is to be written to disk.
+ *
+ * Returns: 0 on success, -Exxx on error
+ */
+static int bitmap_new_disk_sb(struct bitmap *bitmap)
+{
+	bitmap_super_t *sb;
+	unsigned long chunksize, daemon_sleep, write_behind;
+	int err = -EINVAL;
+
+	bitmap->sb_page = alloc_page(GFP_KERNEL);
+	if (IS_ERR(bitmap->sb_page)) {
+		err = PTR_ERR(bitmap->sb_page);
+		bitmap->sb_page = NULL;
+		return err;
+	}
+	bitmap->sb_page->index = 0;
+
+	sb = kmap_atomic(bitmap->sb_page, KM_USER0);
+
+	sb->magic = cpu_to_le32(BITMAP_MAGIC);
+	sb->version = cpu_to_le32(BITMAP_MAJOR_HI);
+
+	chunksize = bitmap->mddev->bitmap_info.chunksize;
+	BUG_ON(!chunksize);
+	if (!is_power_of_2(chunksize)) {
+		kunmap_atomic(sb, KM_USER0);
+		printk(KERN_ERR "bitmap chunksize not a power of 2\n");
+		return -EINVAL;
+	}
+	sb->chunksize = cpu_to_le32(chunksize);
+
+	daemon_sleep = bitmap->mddev->bitmap_info.daemon_sleep;
+	if (!daemon_sleep ||
+	    (daemon_sleep < 1) || (daemon_sleep > MAX_SCHEDULE_TIMEOUT)) {
+		printk(KERN_INFO "Choosing daemon_sleep default (5 sec)\n");
+		daemon_sleep = 5 * HZ;
+	}
+	sb->daemon_sleep = cpu_to_le32(daemon_sleep);
+	bitmap->mddev->bitmap_info.daemon_sleep = daemon_sleep;
+
+	/*
+	 * FIXME: write_behind for RAID1.  If not specified, what
+	 * is a good choice?  We choose COUNTER_MAX / 2 arbitrarily.
+	 */
+	write_behind = bitmap->mddev->bitmap_info.max_write_behind;
+	if (write_behind > COUNTER_MAX)
+		write_behind = COUNTER_MAX / 2;
+	sb->write_behind = cpu_to_le32(write_behind);
+	bitmap->mddev->bitmap_info.max_write_behind = write_behind;
+
+	/* keep the array size field of the bitmap superblock up to date */
+	sb->sync_size = cpu_to_le64(bitmap->mddev->resync_max_sectors);
+
+	memcpy(sb->uuid, bitmap->mddev->uuid, 16);
+
+	bitmap->flags |= BITMAP_STALE;
+	sb->state |= cpu_to_le32(BITMAP_STALE);
+	bitmap->events_cleared = bitmap->mddev->events;
+	sb->events_cleared = cpu_to_le64(bitmap->mddev->events);
+
+	bitmap->flags |= BITMAP_HOSTENDIAN;
+	sb->version = cpu_to_le32(BITMAP_MAJOR_HOSTENDIAN);
+
+	kunmap_atomic(sb, KM_USER0);
+
+	return 0;
+}
+
 /* read the superblock from the bitmap file and initialize some bitmap fields */
 static int bitmap_read_sb(struct bitmap *bitmap)
 {
@@ -575,7 +651,7 @@ static int bitmap_read_sb(struct bitmap *bitmap)
 		reason = "unrecognized superblock version";
 	else if (chunksize < 512)
 		reason = "bitmap chunksize too small";
-	else if ((1 << ffz(~chunksize)) != chunksize)
+	else if (!is_power_of_2(chunksize))
 		reason = "bitmap chunksize not a power of 2";
 	else if (daemon_sleep < 1 || daemon_sleep > MAX_SCHEDULE_TIMEOUT)
 		reason = "daemon sleep period out of range";
@@ -1076,8 +1152,8 @@ static int bitmap_init_from_disk(struct bitmap *bitmap, sector_t start)
 	}
 
 	printk(KERN_INFO "%s: bitmap initialized from disk: "
-		"read %lu/%lu pages, set %lu bits\n",
-		bmname(bitmap), bitmap->file_pages, num_pages, bit_cnt);
+	       "read %lu/%lu pages, set %lu of %lu bits\n",
+	       bmname(bitmap), bitmap->file_pages, num_pages, bit_cnt, chunks);
 
 	return 0;
 
@@ -1332,7 +1408,7 @@ int bitmap_startwrite(struct bitmap *bitmap, sector_t offset, unsigned long sect
 			return 0;
 		}
 
-		if (unlikely((*bmc & COUNTER_MAX) == COUNTER_MAX)) {
+		if (unlikely(COUNTER(*bmc) == COUNTER_MAX)) {
 			DEFINE_WAIT(__wait);
 			/* note that it is safe to do the prepare_to_wait
 			 * after the test as long as we do it before dropping
@@ -1404,10 +1480,10 @@ void bitmap_endwrite(struct bitmap *bitmap, sector_t offset, unsigned long secto
 			sysfs_notify_dirent_safe(bitmap->sysfs_can_clear);
 		}
 
-		if (!success && ! (*bmc & NEEDED_MASK))
+		if (!success && !NEEDED(*bmc))
 			*bmc |= NEEDED_MASK;
 
-		if ((*bmc & COUNTER_MAX) == COUNTER_MAX)
+		if (COUNTER(*bmc) == COUNTER_MAX)
 			wake_up(&bitmap->overflow_wait);
 
 		(*bmc)--;
@@ -1728,9 +1804,16 @@ int bitmap_create(mddev_t *mddev)
 		vfs_fsync(file, 1);
 	}
 	/* read superblock from bitmap file (this sets mddev->bitmap_info.chunksize) */
-	if (!mddev->bitmap_info.external)
-		err = bitmap_read_sb(bitmap);
-	else {
+	if (!mddev->bitmap_info.external) {
+		/*
+		 * If 'MD_ARRAY_FIRST_USE' is set, then device-mapper is
+		 * instructing us to create a new on-disk bitmap instance.
+		 */
+		if (test_and_clear_bit(MD_ARRAY_FIRST_USE, &mddev->flags))
+			err = bitmap_new_disk_sb(bitmap);
+		else
+			err = bitmap_read_sb(bitmap);
+	} else {
 		err = 0;
 		if (mddev->bitmap_info.chunksize == 0 ||
 		    mddev->bitmap_info.daemon_sleep == 0)
@@ -1754,9 +1837,6 @@ int bitmap_create(mddev_t *mddev)
 	bitmap->chunks = chunks;
 	bitmap->pages = pages;
 	bitmap->missing_pages = pages;
-	bitmap->counter_bits = COUNTER_BITS;
-
-	bitmap->syncchunk = ~0UL;
 
 #ifdef INJECT_FATAL_FAULT_1
 	bitmap->bp = NULL;
diff --git a/drivers/md/bitmap.h b/drivers/md/bitmap.h
index d0aeaf46d93..b2a127e891a 100644
--- a/drivers/md/bitmap.h
+++ b/drivers/md/bitmap.h
@@ -85,7 +85,6 @@
 typedef __u16 bitmap_counter_t;
 #define COUNTER_BITS 16
 #define COUNTER_BIT_SHIFT 4
-#define COUNTER_BYTE_RATIO (COUNTER_BITS / 8)
 #define COUNTER_BYTE_SHIFT (COUNTER_BIT_SHIFT - 3)
 
 #define NEEDED_MASK ((bitmap_counter_t) (1 << (COUNTER_BITS - 1)))
@@ -196,19 +195,10 @@ struct bitmap {
 
 	mddev_t *mddev; /* the md device that the bitmap is for */
 
-	int counter_bits; /* how many bits per block counter */
-
 	/* bitmap chunksize -- how much data does each bit represent? */
 	unsigned long chunkshift; /* chunksize = 2^chunkshift (for bitops) */
 	unsigned long chunks; /* total number of data chunks for the array */
 
-	/* We hold a count on the chunk currently being synced, and drop
-	 * it when the last block is started.  If the resync is aborted
-	 * midway, we need to be able to drop that count, so we remember
-	 * the counted chunk..
-	 */
-	unsigned long syncchunk;
-
 	__u64	events_cleared;
 	int need_sync;
 
diff --git a/drivers/md/md.c b/drivers/md/md.c
index aa640a85bb2..4332fc2f25d 100644
--- a/drivers/md/md.c
+++ b/drivers/md/md.c
@@ -351,6 +351,9 @@ void mddev_resume(mddev_t *mddev)
 	mddev->suspended = 0;
 	wake_up(&mddev->sb_wait);
 	mddev->pers->quiesce(mddev, 0);
+
+	md_wakeup_thread(mddev->thread);
+	md_wakeup_thread(mddev->sync_thread); /* possibly kick off a reshape */
 }
 EXPORT_SYMBOL_GPL(mddev_resume);
 
@@ -1750,6 +1753,18 @@ static struct super_type super_types[] = {
 	},
 };
 
+static void sync_super(mddev_t *mddev, mdk_rdev_t *rdev)
+{
+	if (mddev->sync_super) {
+		mddev->sync_super(mddev, rdev);
+		return;
+	}
+
+	BUG_ON(mddev->major_version >= ARRAY_SIZE(super_types));
+
+	super_types[mddev->major_version].sync_super(mddev, rdev);
+}
+
 static int match_mddev_units(mddev_t *mddev1, mddev_t *mddev2)
 {
 	mdk_rdev_t *rdev, *rdev2;
@@ -1781,8 +1796,8 @@ int md_integrity_register(mddev_t *mddev)
 
 	if (list_empty(&mddev->disks))
 		return 0; /* nothing to do */
-	if (blk_get_integrity(mddev->gendisk))
-		return 0; /* already registered */
+	if (!mddev->gendisk || blk_get_integrity(mddev->gendisk))
+		return 0; /* shouldn't register, or already is */
 	list_for_each_entry(rdev, &mddev->disks, same_set) {
 		/* skip spares and non-functional disks */
 		if (test_bit(Faulty, &rdev->flags))
@@ -2168,8 +2183,7 @@ static void sync_sbs(mddev_t * mddev, int nospares)
 			/* Don't update this superblock */
 			rdev->sb_loaded = 2;
 		} else {
-			super_types[mddev->major_version].
-				sync_super(mddev, rdev);
+			sync_super(mddev, rdev);
 			rdev->sb_loaded = 1;
 		}
 	}
@@ -2462,7 +2476,7 @@ slot_store(mdk_rdev_t *rdev, const char *buf, size_t len)
 		if (rdev->raid_disk == -1)
 			return -EEXIST;
 		/* personality does all needed checks */
-		if (rdev->mddev->pers->hot_add_disk == NULL)
+		if (rdev->mddev->pers->hot_remove_disk == NULL)
 			return -EINVAL;
 		err = rdev->mddev->pers->
 			hot_remove_disk(rdev->mddev, rdev->raid_disk);
@@ -4619,9 +4633,6 @@ int md_run(mddev_t *mddev)
 	if (mddev->flags)
 		md_update_sb(mddev, 0);
 
-	md_wakeup_thread(mddev->thread);
-	md_wakeup_thread(mddev->sync_thread); /* possibly kick off a reshape */
-
 	md_new_event(mddev);
 	sysfs_notify_dirent_safe(mddev->sysfs_state);
 	sysfs_notify_dirent_safe(mddev->sysfs_action);
@@ -4642,6 +4653,10 @@ static int do_md_run(mddev_t *mddev)
 		bitmap_destroy(mddev);
 		goto out;
 	}
+
+	md_wakeup_thread(mddev->thread);
+	md_wakeup_thread(mddev->sync_thread); /* possibly kick off a reshape */
+
 	set_capacity(mddev->gendisk, mddev->array_sectors);
 	revalidate_disk(mddev->gendisk);
 	mddev->changed = 1;
@@ -5259,6 +5274,8 @@ static int add_new_disk(mddev_t * mddev, mdu_disk_info_t *info)
 		if (mddev->degraded)
 			set_bit(MD_RECOVERY_RECOVER, &mddev->recovery);
 		set_bit(MD_RECOVERY_NEEDED, &mddev->recovery);
+		if (!err)
+			md_new_event(mddev);
 		md_wakeup_thread(mddev->thread);
 		return err;
 	}
@@ -6866,8 +6883,8 @@ void md_do_sync(mddev_t *mddev)
 	 * Tune reconstruction:
 	 */
 	window = 32*(PAGE_SIZE/512);
-	printk(KERN_INFO "md: using %dk window, over a total of %llu blocks.\n",
-		window/2,(unsigned long long) max_sectors/2);
+	printk(KERN_INFO "md: using %dk window, over a total of %lluk.\n",
+		window/2, (unsigned long long)max_sectors/2);
 
 	atomic_set(&mddev->recovery_active, 0);
 	last_check = 0;
@@ -7045,7 +7062,6 @@ void md_do_sync(mddev_t *mddev)
 }
 EXPORT_SYMBOL_GPL(md_do_sync);
 
-
 static int remove_and_add_spares(mddev_t *mddev)
 {
 	mdk_rdev_t *rdev;
@@ -7157,6 +7173,9 @@ static void reap_sync_thread(mddev_t *mddev)
  */
 void md_check_recovery(mddev_t *mddev)
 {
+	if (mddev->suspended)
+		return;
+
 	if (mddev->bitmap)
 		bitmap_daemon_work(mddev);
 
diff --git a/drivers/md/md.h b/drivers/md/md.h
index 0b1fd3f1d85..1c26c7a08ae 100644
--- a/drivers/md/md.h
+++ b/drivers/md/md.h
@@ -124,6 +124,7 @@ struct mddev_s
 #define MD_CHANGE_DEVS	0	/* Some device status has changed */
 #define MD_CHANGE_CLEAN 1	/* transition to or from 'clean' */
 #define MD_CHANGE_PENDING 2	/* switch from 'clean' to 'active' in progress */
+#define MD_ARRAY_FIRST_USE 3    /* First use of array, needs initialization */
 
 	int				suspended;
 	atomic_t			active_io;
@@ -330,6 +331,7 @@ struct mddev_s
 	atomic_t flush_pending;
 	struct work_struct flush_work;
 	struct work_struct event_work;	/* used by dm to report failure event */
+	void (*sync_super)(mddev_t *mddev, mdk_rdev_t *rdev);
 };
 
 
diff --git a/drivers/md/raid1.c b/drivers/md/raid1.c
index 5d096096f95..f7431b6d844 100644
--- a/drivers/md/raid1.c
+++ b/drivers/md/raid1.c
@@ -497,21 +497,19 @@ static int read_balance(conf_t *conf, r1bio_t *r1_bio)
 	return best_disk;
 }
 
-static int raid1_congested(void *data, int bits)
+int md_raid1_congested(mddev_t *mddev, int bits)
 {
-	mddev_t *mddev = data;
 	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);
 		if (rdev && !test_bit(Faulty, &rdev->flags)) {
 			struct request_queue *q = bdev_get_queue(rdev->bdev);
 
+			BUG_ON(!q);
+
 			/* Note the '|| 1' - when read_balance prefers
 			 * non-congested targets, it can be removed
 			 */
@@ -524,7 +522,15 @@ static int raid1_congested(void *data, int bits)
 	rcu_read_unlock();
 	return ret;
 }
+EXPORT_SYMBOL_GPL(md_raid1_congested);
 
+static int raid1_congested(void *data, int bits)
+{
+	mddev_t *mddev = data;
+
+	return mddev_congested(mddev, bits) ||
+		md_raid1_congested(mddev, bits);
+}
 
 static void flush_pending_writes(conf_t *conf)
 {
@@ -1972,6 +1978,8 @@ static int run(mddev_t *mddev)
 		return PTR_ERR(conf);
 
 	list_for_each_entry(rdev, &mddev->disks, same_set) {
+		if (!mddev->gendisk)
+			continue;
 		disk_stack_limits(mddev->gendisk, rdev->bdev,
 				  rdev->data_offset << 9);
 		/* as we don't honour merge_bvec_fn, we must never risk
@@ -2013,8 +2021,10 @@ static int run(mddev_t *mddev)
 
 	md_set_array_sectors(mddev, raid1_size(mddev, 0, 0));
 
-	mddev->queue->backing_dev_info.congested_fn = raid1_congested;
-	mddev->queue->backing_dev_info.congested_data = mddev;
+	if (mddev->queue) {
+		mddev->queue->backing_dev_info.congested_fn = raid1_congested;
+		mddev->queue->backing_dev_info.congested_data = mddev;
+	}
 	return md_integrity_register(mddev);
 }
 
diff --git a/drivers/md/raid1.h b/drivers/md/raid1.h
index 5fc4ca1af86..e743a64fac4 100644
--- a/drivers/md/raid1.h
+++ b/drivers/md/raid1.h
@@ -126,4 +126,6 @@ struct r1bio_s {
  */
 #define	R1BIO_Returned 6
 
+extern int md_raid1_congested(mddev_t *mddev, int bits);
+
 #endif
diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c
index 346e69bfdab..b72edf35ec5 100644
--- a/drivers/md/raid5.c
+++ b/drivers/md/raid5.c
@@ -129,7 +129,7 @@ static inline int raid5_dec_bi_hw_segments(struct bio *bio)
 
 static inline void raid5_set_bi_hw_segments(struct bio *bio, unsigned int cnt)
 {
-	bio->bi_phys_segments = raid5_bi_phys_segments(bio) || (cnt << 16);
+	bio->bi_phys_segments = raid5_bi_phys_segments(bio) | (cnt << 16);
 }
 
 /* Find first data disk in a raid6 stripe */
@@ -514,7 +514,7 @@ static void ops_run_io(struct stripe_head *sh, struct stripe_head_state *s)
 		bi = &sh->dev[i].req;
 
 		bi->bi_rw = rw;
-		if (rw == WRITE)
+		if (rw & WRITE)
 			bi->bi_end_io = raid5_end_write_request;
 		else
 			bi->bi_end_io = raid5_end_read_request;
@@ -548,13 +548,13 @@ static void ops_run_io(struct stripe_head *sh, struct stripe_head_state *s)
 			bi->bi_io_vec[0].bv_offset = 0;
 			bi->bi_size = STRIPE_SIZE;
 			bi->bi_next = NULL;
-			if (rw == WRITE &&
+			if ((rw & WRITE) &&
 			    test_bit(R5_ReWrite, &sh->dev[i].flags))
 				atomic_add(STRIPE_SECTORS,
 					&rdev->corrected_errors);
 			generic_make_request(bi);
 		} else {
-			if (rw == WRITE)
+			if (rw & WRITE)
 				set_bit(STRIPE_DEGRADED, &sh->state);
 			pr_debug("skip op %ld on disc %d for sector %llu\n",
 				bi->bi_rw, i, (unsigned long long)sh->sector);
@@ -585,7 +585,7 @@ async_copy_data(int frombio, struct bio *bio, struct page *page,
 	init_async_submit(&submit, flags, tx, NULL, NULL, NULL);
 
 	bio_for_each_segment(bvl, bio, i) {
-		int len = bio_iovec_idx(bio, i)->bv_len;
+		int len = bvl->bv_len;
 		int clen;
 		int b_offset = 0;
 
@@ -601,8 +601,8 @@ async_copy_data(int frombio, struct bio *bio, struct page *page,
 			clen = len;
 
 		if (clen > 0) {
-			b_offset += bio_iovec_idx(bio, i)->bv_offset;
-			bio_page = bio_iovec_idx(bio, i)->bv_page;
+			b_offset += bvl->bv_offset;
+			bio_page = bvl->bv_page;
 			if (frombio)
 				tx = async_memcpy(page, bio_page, page_offset,
 						  b_offset, clen, &submit);
@@ -4858,7 +4858,7 @@ static raid5_conf_t *setup_conf(mddev_t *mddev)
 			printk(KERN_INFO "md/raid:%s: device %s operational as raid"
 			       " disk %d\n",
 			       mdname(mddev), bdevname(rdev->bdev, b), raid_disk);
-		} else
+		} else if (rdev->saved_raid_disk != raid_disk)
 			/* Cannot rely on bitmap to complete recovery */
 			conf->fullsync = 1;
 	}