Merge branch 'next' into for-linus

Prepare first round of input updates for 4.3 merge window.

1 files changed, 175 insertions, 25 deletions

diff --git a/drivers/md/bitmap.c b/drivers/md/bitmap.c
index 3a5767968ba0..ed2346ddf4c9 100644
--- a/drivers/md/bitmap.c
+++ b/drivers/md/bitmap.c
@@ -177,11 +177,16 @@ static struct md_rdev *next_active_rdev(struct md_rdev *rdev, struct mddev *mdde
 	 * nr_pending is 0 and In_sync is clear, the entries we return will
 	 * still be in the same position on the list when we re-enter
 	 * list_for_each_entry_continue_rcu.
+	 *
+	 * Note that if entered with 'rdev == NULL' to start at the
+	 * beginning, we temporarily assign 'rdev' to an address which
+	 * isn't really an rdev, but which can be used by
+	 * list_for_each_entry_continue_rcu() to find the first entry.
 	 */
 	rcu_read_lock();
 	if (rdev == NULL)
 		/* start at the beginning */
-		rdev = list_entry_rcu(&mddev->disks, struct md_rdev, same_set);
+		rdev = list_entry(&mddev->disks, struct md_rdev, same_set);
 	else {
 		/* release the previous rdev and start from there. */
 		rdev_dec_pending(rdev, mddev);
@@ -205,6 +210,10 @@ static int write_sb_page(struct bitmap *bitmap, struct page *page, int wait)
 	struct block_device *bdev;
 	struct mddev *mddev = bitmap->mddev;
 	struct bitmap_storage *store = &bitmap->storage;
+	int node_offset = 0;
+
+	if (mddev_is_clustered(bitmap->mddev))
+		node_offset = bitmap->cluster_slot * store->file_pages;
 
 	while ((rdev = next_active_rdev(rdev, mddev)) != NULL) {
 		int size = PAGE_SIZE;
@@ -433,6 +442,7 @@ void bitmap_update_sb(struct bitmap *bitmap)
 	/* This might have been changed by a reshape */
 	sb->sync_size = cpu_to_le64(bitmap->mddev->resync_max_sectors);
 	sb->chunksize = cpu_to_le32(bitmap->mddev->bitmap_info.chunksize);
+	sb->nodes = cpu_to_le32(bitmap->mddev->bitmap_info.nodes);
 	sb->sectors_reserved = cpu_to_le32(bitmap->mddev->
 					   bitmap_info.space);
 	kunmap_atomic(sb);
@@ -544,6 +554,7 @@ static int bitmap_read_sb(struct bitmap *bitmap)
 	bitmap_super_t *sb;
 	unsigned long chunksize, daemon_sleep, write_behind;
 	unsigned long long events;
+	int nodes = 0;
 	unsigned long sectors_reserved = 0;
 	int err = -EINVAL;
 	struct page *sb_page;
@@ -562,6 +573,22 @@ static int bitmap_read_sb(struct bitmap *bitmap)
 		return -ENOMEM;
 	bitmap->storage.sb_page = sb_page;
 
+re_read:
+	/* If cluster_slot is set, the cluster is setup */
+	if (bitmap->cluster_slot >= 0) {
+		sector_t bm_blocks = bitmap->mddev->resync_max_sectors;
+
+		sector_div(bm_blocks,
+			   bitmap->mddev->bitmap_info.chunksize >> 9);
+		/* bits to bytes */
+		bm_blocks = ((bm_blocks+7) >> 3) + sizeof(bitmap_super_t);
+		/* to 4k blocks */
+		bm_blocks = DIV_ROUND_UP_SECTOR_T(bm_blocks, 4096);
+		bitmap->mddev->bitmap_info.offset += bitmap->cluster_slot * (bm_blocks << 3);
+		pr_info("%s:%d bm slot: %d offset: %llu\n", __func__, __LINE__,
+			bitmap->cluster_slot, (unsigned long long)bitmap->mddev->bitmap_info.offset);
+	}
+
 	if (bitmap->storage.file) {
 		loff_t isize = i_size_read(bitmap->storage.file->f_mapping->host);
 		int bytes = isize > PAGE_SIZE ? PAGE_SIZE : isize;
@@ -577,12 +604,15 @@ static int bitmap_read_sb(struct bitmap *bitmap)
 	if (err)
 		return err;
 
+	err = -EINVAL;
 	sb = kmap_atomic(sb_page);
 
 	chunksize = le32_to_cpu(sb->chunksize);
 	daemon_sleep = le32_to_cpu(sb->daemon_sleep) * HZ;
 	write_behind = le32_to_cpu(sb->write_behind);
 	sectors_reserved = le32_to_cpu(sb->sectors_reserved);
+	nodes = le32_to_cpu(sb->nodes);
+	strlcpy(bitmap->mddev->bitmap_info.cluster_name, sb->cluster_name, 64);
 
 	/* verify that the bitmap-specific fields are valid */
 	if (sb->magic != cpu_to_le32(BITMAP_MAGIC))
@@ -619,7 +649,7 @@ static int bitmap_read_sb(struct bitmap *bitmap)
 			goto out;
 		}
 		events = le64_to_cpu(sb->events);
-		if (events < bitmap->mddev->events) {
+		if (!nodes && (events < bitmap->mddev->events)) {
 			printk(KERN_INFO
 			       "%s: bitmap file is out of date (%llu < %llu) "
 			       "-- forcing full recovery\n",
@@ -634,20 +664,40 @@ static int bitmap_read_sb(struct bitmap *bitmap)
 	if (le32_to_cpu(sb->version) == BITMAP_MAJOR_HOSTENDIAN)
 		set_bit(BITMAP_HOSTENDIAN, &bitmap->flags);
 	bitmap->events_cleared = le64_to_cpu(sb->events_cleared);
+	strlcpy(bitmap->mddev->bitmap_info.cluster_name, sb->cluster_name, 64);
 	err = 0;
+
 out:
 	kunmap_atomic(sb);
+	/* Assiging chunksize is required for "re_read" */
+	bitmap->mddev->bitmap_info.chunksize = chunksize;
+	if (nodes && (bitmap->cluster_slot < 0)) {
+		err = md_setup_cluster(bitmap->mddev, nodes);
+		if (err) {
+			pr_err("%s: Could not setup cluster service (%d)\n",
+					bmname(bitmap), err);
+			goto out_no_sb;
+		}
+		bitmap->cluster_slot = md_cluster_ops->slot_number(bitmap->mddev);
+		goto re_read;
+	}
+
+
 out_no_sb:
 	if (test_bit(BITMAP_STALE, &bitmap->flags))
 		bitmap->events_cleared = bitmap->mddev->events;
 	bitmap->mddev->bitmap_info.chunksize = chunksize;
 	bitmap->mddev->bitmap_info.daemon_sleep = daemon_sleep;
 	bitmap->mddev->bitmap_info.max_write_behind = write_behind;
+	bitmap->mddev->bitmap_info.nodes = nodes;
 	if (bitmap->mddev->bitmap_info.space == 0 ||
 	    bitmap->mddev->bitmap_info.space > sectors_reserved)
 		bitmap->mddev->bitmap_info.space = sectors_reserved;
-	if (err)
+	if (err) {
 		bitmap_print_sb(bitmap);
+		if (bitmap->cluster_slot < 0)
+			md_cluster_stop(bitmap->mddev);
+	}
 	return err;
 }
 
@@ -692,9 +742,10 @@ static inline struct page *filemap_get_page(struct bitmap_storage *store,
 }
 
 static int bitmap_storage_alloc(struct bitmap_storage *store,
-				unsigned long chunks, int with_super)
+				unsigned long chunks, int with_super,
+				int slot_number)
 {
-	int pnum;
+	int pnum, offset = 0;
 	unsigned long num_pages;
 	unsigned long bytes;
 
@@ -703,6 +754,7 @@ static int bitmap_storage_alloc(struct bitmap_storage *store,
 		bytes += sizeof(bitmap_super_t);
 
 	num_pages = DIV_ROUND_UP(bytes, PAGE_SIZE);
+	offset = slot_number * (num_pages - 1);
 
 	store->filemap = kmalloc(sizeof(struct page *)
 				 * num_pages, GFP_KERNEL);
@@ -713,20 +765,22 @@ static int bitmap_storage_alloc(struct bitmap_storage *store,
 		store->sb_page = alloc_page(GFP_KERNEL|__GFP_ZERO);
 		if (store->sb_page == NULL)
 			return -ENOMEM;
-		store->sb_page->index = 0;
 	}
+
 	pnum = 0;
 	if (store->sb_page) {
 		store->filemap[0] = store->sb_page;
 		pnum = 1;
+		store->sb_page->index = offset;
 	}
+
 	for ( ; pnum < num_pages; pnum++) {
 		store->filemap[pnum] = alloc_page(GFP_KERNEL|__GFP_ZERO);
 		if (!store->filemap[pnum]) {
 			store->file_pages = pnum;
 			return -ENOMEM;
 		}
-		store->filemap[pnum]->index = pnum;
+		store->filemap[pnum]->index = pnum + offset;
 	}
 	store->file_pages = pnum;
 
@@ -785,7 +839,7 @@ static void bitmap_file_kick(struct bitmap *bitmap)
 		if (bitmap->storage.file) {
 			path = kmalloc(PAGE_SIZE, GFP_KERNEL);
 			if (path)
-				ptr = d_path(&bitmap->storage.file->f_path,
+				ptr = file_path(bitmap->storage.file,
 					     path, PAGE_SIZE);
 
 			printk(KERN_ALERT
@@ -885,6 +939,28 @@ static void bitmap_file_clear_bit(struct bitmap *bitmap, sector_t block)
 	}
 }
 
+static int bitmap_file_test_bit(struct bitmap *bitmap, sector_t block)
+{
+	unsigned long bit;
+	struct page *page;
+	void *paddr;
+	unsigned long chunk = block >> bitmap->counts.chunkshift;
+	int set = 0;
+
+	page = filemap_get_page(&bitmap->storage, chunk);
+	if (!page)
+		return -EINVAL;
+	bit = file_page_offset(&bitmap->storage, chunk);
+	paddr = kmap_atomic(page);
+	if (test_bit(BITMAP_HOSTENDIAN, &bitmap->flags))
+		set = test_bit(bit, paddr);
+	else
+		set = test_bit_le(bit, paddr);
+	kunmap_atomic(paddr);
+	return set;
+}
+
+
 /* this gets called when the md device is ready to unplug its underlying
  * (slave) device queues -- before we let any writes go down, we need to
  * sync the dirty pages of the bitmap file to disk */
@@ -935,7 +1011,7 @@ static void bitmap_set_memory_bits(struct bitmap *bitmap, sector_t offset, int n
  */
 static int bitmap_init_from_disk(struct bitmap *bitmap, sector_t start)
 {
-	unsigned long i, chunks, index, oldindex, bit;
+	unsigned long i, chunks, index, oldindex, bit, node_offset = 0;
 	struct page *page = NULL;
 	unsigned long bit_cnt = 0;
 	struct file *file;
@@ -981,6 +1057,9 @@ static int bitmap_init_from_disk(struct bitmap *bitmap, sector_t start)
 	if (!bitmap->mddev->bitmap_info.external)
 		offset = sizeof(bitmap_super_t);
 
+	if (mddev_is_clustered(bitmap->mddev))
+		node_offset = bitmap->cluster_slot * (DIV_ROUND_UP(store->bytes, PAGE_SIZE));
+
 	for (i = 0; i < chunks; i++) {
 		int b;
 		index = file_page_index(&bitmap->storage, i);
@@ -1001,7 +1080,7 @@ static int bitmap_init_from_disk(struct bitmap *bitmap, sector_t start)
 					bitmap->mddev,
 					bitmap->mddev->bitmap_info.offset,
 					page,
-					index, count);
+					index + node_offset, count);
 
 			if (ret)
 				goto err;
@@ -1207,7 +1286,6 @@ void bitmap_daemon_work(struct mddev *mddev)
 	     j < bitmap->storage.file_pages
 		     && !test_bit(BITMAP_STALE, &bitmap->flags);
 	     j++) {
-
 		if (test_page_attr(bitmap, j,
 				   BITMAP_PAGE_DIRTY))
 			/* bitmap_unplug will handle the rest */
@@ -1530,11 +1608,13 @@ static void bitmap_set_memory_bits(struct bitmap *bitmap, sector_t offset, int n
 		return;
 	}
 	if (!*bmc) {
-		*bmc = 2 | (needed ? NEEDED_MASK : 0);
+		*bmc = 2;
 		bitmap_count_page(&bitmap->counts, offset, 1);
 		bitmap_set_pending(&bitmap->counts, offset);
 		bitmap->allclean = 0;
 	}
+	if (needed)
+		*bmc |= NEEDED_MASK;
 	spin_unlock_irq(&bitmap->counts.lock);
 }
 
@@ -1591,6 +1671,10 @@ static void bitmap_free(struct bitmap *bitmap)
 	if (!bitmap) /* there was no bitmap */
 		return;
 
+	if (mddev_is_clustered(bitmap->mddev) && bitmap->mddev->cluster_info &&
+		bitmap->cluster_slot == md_cluster_ops->slot_number(bitmap->mddev))
+		md_cluster_stop(bitmap->mddev);
+
 	/* Shouldn't be needed - but just in case.... */
 	wait_event(bitmap->write_wait,
 		   atomic_read(&bitmap->pending_writes) == 0);
@@ -1636,7 +1720,7 @@ void bitmap_destroy(struct mddev *mddev)
  * initialize the bitmap structure
  * if this returns an error, bitmap_destroy must be called to do clean up
  */
-int bitmap_create(struct mddev *mddev)
+struct bitmap *bitmap_create(struct mddev *mddev, int slot)
 {
 	struct bitmap *bitmap;
 	sector_t blocks = mddev->resync_max_sectors;
@@ -1650,7 +1734,7 @@ int bitmap_create(struct mddev *mddev)
 
 	bitmap = kzalloc(sizeof(*bitmap), GFP_KERNEL);
 	if (!bitmap)
-		return -ENOMEM;
+		return ERR_PTR(-ENOMEM);
 
 	spin_lock_init(&bitmap->counts.lock);
 	atomic_set(&bitmap->pending_writes, 0);
@@ -1659,6 +1743,7 @@ int bitmap_create(struct mddev *mddev)
 	init_waitqueue_head(&bitmap->behind_wait);
 
 	bitmap->mddev = mddev;
+	bitmap->cluster_slot = slot;
 
 	if (mddev->kobj.sd)
 		bm = sysfs_get_dirent(mddev->kobj.sd, "bitmap");
@@ -1706,12 +1791,14 @@ int bitmap_create(struct mddev *mddev)
 	printk(KERN_INFO "created bitmap (%lu pages) for device %s\n",
 	       bitmap->counts.pages, bmname(bitmap));
 
-	mddev->bitmap = bitmap;
-	return test_bit(BITMAP_WRITE_ERROR, &bitmap->flags) ? -EIO : 0;
+	err = test_bit(BITMAP_WRITE_ERROR, &bitmap->flags) ? -EIO : 0;
+	if (err)
+		goto error;
 
+	return bitmap;
  error:
 	bitmap_free(bitmap);
-	return err;
+	return ERR_PTR(err);
 }
 
 int bitmap_load(struct mddev *mddev)
@@ -1765,6 +1852,60 @@ out:
 }
 EXPORT_SYMBOL_GPL(bitmap_load);
 
+/* Loads the bitmap associated with slot and copies the resync information
+ * to our bitmap
+ */
+int bitmap_copy_from_slot(struct mddev *mddev, int slot,
+		sector_t *low, sector_t *high, bool clear_bits)
+{
+	int rv = 0, i, j;
+	sector_t block, lo = 0, hi = 0;
+	struct bitmap_counts *counts;
+	struct bitmap *bitmap = bitmap_create(mddev, slot);
+
+	if (IS_ERR(bitmap))
+		return PTR_ERR(bitmap);
+
+	rv = bitmap_read_sb(bitmap);
+	if (rv)
+		goto err;
+
+	rv = bitmap_init_from_disk(bitmap, 0);
+	if (rv)
+		goto err;
+
+	counts = &bitmap->counts;
+	for (j = 0; j < counts->chunks; j++) {
+		block = (sector_t)j << counts->chunkshift;
+		if (bitmap_file_test_bit(bitmap, block)) {
+			if (!lo)
+				lo = block;
+			hi = block;
+			bitmap_file_clear_bit(bitmap, block);
+			bitmap_set_memory_bits(mddev->bitmap, block, 1);
+			bitmap_file_set_bit(mddev->bitmap, block);
+		}
+	}
+
+	if (clear_bits) {
+		bitmap_update_sb(bitmap);
+		/* Setting this for the ev_page should be enough.
+		 * And we do not require both write_all and PAGE_DIRT either
+		 */
+		for (i = 0; i < bitmap->storage.file_pages; i++)
+			set_page_attr(bitmap, i, BITMAP_PAGE_DIRTY);
+		bitmap_write_all(bitmap);
+		bitmap_unplug(bitmap);
+	}
+	*low = lo;
+	*high = hi;
+err:
+	bitmap_free(bitmap);
+	return rv;
+}
+EXPORT_SYMBOL_GPL(bitmap_copy_from_slot);
+
+
 void bitmap_status(struct seq_file *seq, struct bitmap *bitmap)
 {
 	unsigned long chunk_kb;
@@ -1786,7 +1927,7 @@ void bitmap_status(struct seq_file *seq, struct bitmap *bitmap)
 		   chunk_kb ? "KB" : "B");
 	if (bitmap->storage.file) {
 		seq_printf(seq, ", file: ");
-		seq_path(seq, &bitmap->storage.file->f_path, " \t\n");
+		seq_file_path(seq, bitmap->storage.file, " \t\n");
 	}
 
 	seq_printf(seq, "\n");
@@ -1849,7 +1990,8 @@ int bitmap_resize(struct bitmap *bitmap, sector_t blocks,
 	memset(&store, 0, sizeof(store));
 	if (bitmap->mddev->bitmap_info.offset || bitmap->mddev->bitmap_info.file)
 		ret = bitmap_storage_alloc(&store, chunks,
-					   !bitmap->mddev->bitmap_info.external);
+					   !bitmap->mddev->bitmap_info.external,
+					   bitmap->cluster_slot);
 	if (ret)
 		goto err;
 
@@ -2021,13 +2163,18 @@ location_store(struct mddev *mddev, const char *buf, size_t len)
 				return -EINVAL;
 			mddev->bitmap_info.offset = offset;
 			if (mddev->pers) {
+				struct bitmap *bitmap;
 				mddev->pers->quiesce(mddev, 1);
-				rv = bitmap_create(mddev);
-				if (!rv)
+				bitmap = bitmap_create(mddev, -1);
+				if (IS_ERR(bitmap))
+					rv = PTR_ERR(bitmap);
+				else {
+					mddev->bitmap = bitmap;
 					rv = bitmap_load(mddev);
-				if (rv) {
-					bitmap_destroy(mddev);
-					mddev->bitmap_info.offset = 0;
+					if (rv) {
+						bitmap_destroy(mddev);
+						mddev->bitmap_info.offset = 0;
+					}
 				}
 				mddev->pers->quiesce(mddev, 0);
 				if (rv)
@@ -2186,6 +2333,8 @@ __ATTR(chunksize, S_IRUGO|S_IWUSR, chunksize_show, chunksize_store);
 
 static ssize_t metadata_show(struct mddev *mddev, char *page)
 {
+	if (mddev_is_clustered(mddev))
+		return sprintf(page, "clustered\n");
 	return sprintf(page, "%s\n", (mddev->bitmap_info.external
 				      ? "external" : "internal"));
 }
@@ -2198,7 +2347,8 @@ static ssize_t metadata_store(struct mddev *mddev, const char *buf, size_t len)
 		return -EBUSY;
 	if (strncmp(buf, "external", 8) == 0)
 		mddev->bitmap_info.external = 1;
-	else if (strncmp(buf, "internal", 8) == 0)
+	else if ((strncmp(buf, "internal", 8) == 0) ||
+			(strncmp(buf, "clustered", 9) == 0))
 		mddev->bitmap_info.external = 0;
 	else
 		return -EINVAL;