libnvdimm, label: convert label tracking to a linked list

In preparation for enabling multiple namespaces per pmem region, convert
the label tracking to use a linked list.  In particular this will allow
select_pmem_id() to move labels from the unvalidated state to the
validated state.  Currently we only track one validated set per-region.
Signed-off-by: Dan Williams <dan.j.williams@intel.com>

drivers/nvdimm/label.c

@@ -499,6 +499,7 @@ static int __pmem_label_update(struct nd_region *nd_region,
 	struct nd_namespace_label *victim_label;
 	struct nd_namespace_label *nd_label;
 	struct nd_namespace_index *nsindex;
+	struct nd_label_ent *label_ent;
 	unsigned long *free;
 	u32 nslot, slot;
 	size_t offset;
@@ -536,8 +537,13 @@ static int __pmem_label_update(struct nd_region *nd_region,
 		return rc;
 
 	/* Garbage collect the previous label */
-	victim_label = nd_mapping->labels[0];
+	mutex_lock(&nd_mapping->lock);
+	label_ent = list_first_entry_or_null(&nd_mapping->labels,
+			typeof(*label_ent), list);
+	WARN_ON(!label_ent);
+	victim_label = label_ent ? label_ent->label : NULL;
 	if (victim_label) {
+		label_ent->label = NULL;
 		slot = to_slot(ndd, victim_label);
 		nd_label_free_slot(ndd, slot);
 		dev_dbg(ndd->dev, "%s: free: %d\n", __func__, slot);
@@ -546,28 +552,11 @@ static int __pmem_label_update(struct nd_region *nd_region,
 	/* update index */
 	rc = nd_label_write_index(ndd, ndd->ns_next,
 			nd_inc_seq(__le32_to_cpu(nsindex->seq)), 0);
-	if (rc < 0)
-		return rc;
-
-	nd_mapping->labels[0] = nd_label;
-
-	return 0;
-}
-
-static void del_label(struct nd_mapping *nd_mapping, int l)
-{
-	struct nd_namespace_label *next_label, *nd_label;
-	struct nvdimm_drvdata *ndd = to_ndd(nd_mapping);
-	unsigned int slot;
-	int j;
-
-	nd_label = nd_mapping->labels[l];
-	slot = to_slot(ndd, nd_label);
-	dev_vdbg(ndd->dev, "%s: clear: %d\n", __func__, slot);
+	if (rc == 0 && label_ent)
+		label_ent->label = nd_label;
+	mutex_unlock(&nd_mapping->lock);
 
-	for (j = l; (next_label = nd_mapping->labels[j + 1]); j++)
-		nd_mapping->labels[j] = next_label;
-	nd_mapping->labels[j] = NULL;
+	return rc;
 }
 
 static bool is_old_resource(struct resource *res, struct resource **list, int n)
@@ -607,14 +596,16 @@ static int __blk_label_update(struct nd_region *nd_region,
 		struct nd_mapping *nd_mapping, struct nd_namespace_blk *nsblk,
 		int num_labels)
 {
-	int i, l, alloc, victims, nfree, old_num_resources, nlabel, rc = -ENXIO;
+	int i, alloc, victims, nfree, old_num_resources, nlabel, rc = -ENXIO;
 	struct nvdimm_drvdata *ndd = to_ndd(nd_mapping);
 	struct nd_namespace_label *nd_label;
+	struct nd_label_ent *label_ent, *e;
 	struct nd_namespace_index *nsindex;
 	unsigned long *free, *victim_map = NULL;
 	struct resource *res, **old_res_list;
 	struct nd_label_id label_id;
 	u8 uuid[NSLABEL_UUID_LEN];
+	LIST_HEAD(list);
 	u32 nslot, slot;
 
 	if (!preamble_next(ndd, &nsindex, &free, &nslot))
@@ -736,15 +727,22 @@ static int __blk_label_update(struct nd_region *nd_region,
 	 * entries in nd_mapping->labels
 	 */
 	nlabel = 0;
-	for_each_label(l, nd_label, nd_mapping->labels) {
+	mutex_lock(&nd_mapping->lock);
+	list_for_each_entry_safe(label_ent, e, &nd_mapping->labels, list) {
+		nd_label = label_ent->label;
+		if (!nd_label)
+			continue;
 		nlabel++;
 		memcpy(uuid, nd_label->uuid, NSLABEL_UUID_LEN);
 		if (memcmp(uuid, nsblk->uuid, NSLABEL_UUID_LEN) != 0)
 			continue;
 		nlabel--;
-		del_label(nd_mapping, l);
-		l--; /* retry with the new label at this index */
+		list_move(&label_ent->list, &list);
+		label_ent->label = NULL;
 	}
+	list_splice_tail_init(&list, &nd_mapping->labels);
+	mutex_unlock(&nd_mapping->lock);
+
 	if (nlabel + nsblk->num_resources > num_labels) {
 		/*
 		 * Bug, we can't end up with more resources than
@@ -755,6 +753,15 @@ static int __blk_label_update(struct nd_region *nd_region,
 		goto out;
 	}
 
+	mutex_lock(&nd_mapping->lock);
+	label_ent = list_first_entry_or_null(&nd_mapping->labels,
+			typeof(*label_ent), list);
+	if (!label_ent) {
+		WARN_ON(1);
+		mutex_unlock(&nd_mapping->lock);
+		rc = -ENXIO;
+		goto out;
+	}
 	for_each_clear_bit_le(slot, free, nslot) {
 		nd_label = nd_label_base(ndd) + slot;
 		memcpy(uuid, nd_label->uuid, NSLABEL_UUID_LEN);
@@ -762,11 +769,19 @@ static int __blk_label_update(struct nd_region *nd_region,
 			continue;
 		res = to_resource(ndd, nd_label);
 		res->flags &= ~DPA_RESOURCE_ADJUSTED;
-		dev_vdbg(&nsblk->common.dev, "assign label[%d] slot: %d\n",
-				l, slot);
-		nd_mapping->labels[l++] = nd_label;
+		dev_vdbg(&nsblk->common.dev, "assign label slot: %d\n", slot);
+		list_for_each_entry_from(label_ent, &nd_mapping->labels, list) {
+			if (label_ent->label)
+				continue;
+			label_ent->label = nd_label;
+			nd_label = NULL;
+			break;
 		}
-	nd_mapping->labels[l] = NULL;
+		if (nd_label)
+			dev_WARN(&nsblk->common.dev,
+					"failed to track label slot%d\n", slot);
+	}
+	mutex_unlock(&nd_mapping->lock);
 
  out:
 	kfree(old_res_list);
@@ -788,32 +803,28 @@ static int __blk_label_update(struct nd_region *nd_region,
 
 static int init_labels(struct nd_mapping *nd_mapping, int num_labels)
 {
-	int i, l, old_num_labels = 0;
+	int i, old_num_labels = 0;
+	struct nd_label_ent *label_ent;
 	struct nd_namespace_index *nsindex;
-	struct nd_namespace_label *nd_label;
 	struct nvdimm_drvdata *ndd = to_ndd(nd_mapping);
-	size_t size = (num_labels + 1) * sizeof(struct nd_namespace_label *);
 
-	for_each_label(l, nd_label, nd_mapping->labels)
+	mutex_lock(&nd_mapping->lock);
+	list_for_each_entry(label_ent, &nd_mapping->labels, list)
 		old_num_labels++;
+	mutex_unlock(&nd_mapping->lock);
 
 	/*
 	 * We need to preserve all the old labels for the mapping so
 	 * they can be garbage collected after writing the new labels.
 	 */
-	if (num_labels > old_num_labels) {
-		struct nd_namespace_label **labels;
-
-		labels = krealloc(nd_mapping->labels, size, GFP_KERNEL);
-		if (!labels)
+	for (i = old_num_labels; i < num_labels; i++) {
+		label_ent = kzalloc(sizeof(*label_ent), GFP_KERNEL);
+		if (!label_ent)
 			return -ENOMEM;
-		nd_mapping->labels = labels;
+		mutex_lock(&nd_mapping->lock);
+		list_add_tail(&label_ent->list, &nd_mapping->labels);
+		mutex_unlock(&nd_mapping->lock);
 	}
-	if (!nd_mapping->labels)
-		return -ENOMEM;
-
-	for (i = old_num_labels; i <= num_labels; i++)
-		nd_mapping->labels[i] = NULL;
 
 	if (ndd->ns_current == -1 || ndd->ns_next == -1)
 		/* pass */;
@@ -837,42 +848,45 @@ static int init_labels(struct nd_mapping *nd_mapping, int num_labels)
 static int del_labels(struct nd_mapping *nd_mapping, u8 *uuid)
 {
 	struct nvdimm_drvdata *ndd = to_ndd(nd_mapping);
-	struct nd_namespace_label *nd_label;
+	struct nd_label_ent *label_ent, *e;
 	struct nd_namespace_index *nsindex;
 	u8 label_uuid[NSLABEL_UUID_LEN];
-	int l, num_freed = 0;
 	unsigned long *free;
+	LIST_HEAD(list);
 	u32 nslot, slot;
+	int active = 0;
 
 	if (!uuid)
 		return 0;
 
 	/* no index || no labels == nothing to delete */
-	if (!preamble_next(ndd, &nsindex, &free, &nslot)
-			|| !nd_mapping->labels)
+	if (!preamble_next(ndd, &nsindex, &free, &nslot))
 		return 0;
 
-	for_each_label(l, nd_label, nd_mapping->labels) {
+	mutex_lock(&nd_mapping->lock);
+	list_for_each_entry_safe(label_ent, e, &nd_mapping->labels, list) {
+		struct nd_namespace_label *nd_label = label_ent->label;
+
+		if (!nd_label)
+			continue;
+		active++;
 		memcpy(label_uuid, nd_label->uuid, NSLABEL_UUID_LEN);
 		if (memcmp(label_uuid, uuid, NSLABEL_UUID_LEN) != 0)
 			continue;
+		active--;
 		slot = to_slot(ndd, nd_label);
 		nd_label_free_slot(ndd, slot);
 		dev_dbg(ndd->dev, "%s: free: %d\n", __func__, slot);
-		del_label(nd_mapping, l);
-		num_freed++;
-		l--; /* retry with new label at this index */
+		list_move_tail(&label_ent->list, &list);
+		label_ent->label = NULL;
 	}
+	list_splice_tail_init(&list, &nd_mapping->labels);
 
-	if (num_freed > l) {
-		/*
-		 * num_freed will only ever be > l when we delete the last
-		 * label
-		 */
-		kfree(nd_mapping->labels);
-		nd_mapping->labels = NULL;
-		dev_dbg(ndd->dev, "%s: no more labels\n", __func__);
+	if (active == 0) {
+		nd_mapping_free_labels(nd_mapping);
+		dev_dbg(ndd->dev, "%s: no more active labels\n", __func__);
 	}
+	mutex_unlock(&nd_mapping->lock);
 
 	return nd_label_write_index(ndd, ndd->ns_next,
 			nd_inc_seq(__le32_to_cpu(nsindex->seq)), 0);

drivers/nvdimm/nd-core.h

@@ -73,6 +73,7 @@ bool nd_is_uuid_unique(struct device *dev, u8 *uuid);
 struct nd_region;
 struct nvdimm_drvdata;
 struct nd_mapping;
+void nd_mapping_free_labels(struct nd_mapping *nd_mapping);
 resource_size_t nd_pmem_available_dpa(struct nd_region *nd_region,
 		struct nd_mapping *nd_mapping, resource_size_t *overlap);
 resource_size_t nd_blk_available_dpa(struct nd_mapping *nd_mapping);

drivers/nvdimm/nd.h

@@ -83,9 +83,6 @@ static inline struct nd_namespace_index *to_next_namespace_index(
 		(unsigned long long) (res ? resource_size(res) : 0), \
 		(unsigned long long) (res ? res->start : 0), ##arg)
 
-#define for_each_label(l, label, labels) \
-	for (l = 0; (label = labels ? labels[l] : NULL); l++)
-
 #define for_each_dpa_resource(ndd, res) \
 	for (res = (ndd)->dpa.child; res; res = res->sibling)
 
@@ -98,11 +95,22 @@ struct nd_percpu_lane {
 	spinlock_t lock;
 };
 
+struct nd_label_ent {
+	struct list_head list;
+	struct nd_namespace_label *label;
+};
+
+enum nd_mapping_lock_class {
+	ND_MAPPING_CLASS0,
+	ND_MAPPING_UUID_SCAN,
+};
+
 struct nd_mapping {
 	struct nvdimm *nvdimm;
-	struct nd_namespace_label **labels;
 	u64 start;
 	u64 size;
+	struct list_head labels;
+	struct mutex lock;
 	/*
 	 * @ndd is for private use at region enable / disable time for
 	 * get_ndd() + put_ndd(), all other nd_mapping to ndd

drivers/nvdimm/region_devs.c

@@ -487,6 +487,17 @@ u64 nd_region_interleave_set_cookie(struct nd_region *nd_region)
 	return 0;
 }
 
+void nd_mapping_free_labels(struct nd_mapping *nd_mapping)
+{
+	struct nd_label_ent *label_ent, *e;
+
+	WARN_ON(!mutex_is_locked(&nd_mapping->lock));
+	list_for_each_entry_safe(label_ent, e, &nd_mapping->labels, list) {
+		list_del(&label_ent->list);
+		kfree(label_ent);
+	}
+}
+
 /*
  * Upon successful probe/remove, take/release a reference on the
  * associated interleave set (if present), and plant new btt + namespace
@@ -507,8 +518,10 @@ static void nd_region_notify_driver_action(struct nvdimm_bus *nvdimm_bus,
 			struct nvdimm_drvdata *ndd = nd_mapping->ndd;
 			struct nvdimm *nvdimm = nd_mapping->nvdimm;
 
-			kfree(nd_mapping->labels);
-			nd_mapping->labels = NULL;
+			mutex_lock(&nd_mapping->lock);
+			nd_mapping_free_labels(nd_mapping);
+			mutex_unlock(&nd_mapping->lock);
+
 			put_ndd(ndd);
 			nd_mapping->ndd = NULL;
 			if (ndd)
@@ -816,6 +829,8 @@ static struct nd_region *nd_region_create(struct nvdimm_bus *nvdimm_bus,
 		nd_region->mapping[i].nvdimm = nvdimm;
 		nd_region->mapping[i].start = mapping->start;
 		nd_region->mapping[i].size = mapping->size;
+		INIT_LIST_HEAD(&nd_region->mapping[i].labels);
+		mutex_init(&nd_region->mapping[i].lock);
 
 		get_device(&nvdimm->dev);
 	}