libnvdimm: pmem label sets and namespace instantiation.

A complete label set is a PMEM-label per-dimm per-interleave-set where
all the UUIDs match and the interleave set cookie matches the hosting
interleave set.

Present sysfs attributes for manipulation of a PMEM-namespace's
'alt_name', 'uuid', and 'size' attributes.  A later patch will make
these settings persistent by writing back the label.

Note that PMEM allocations grow forwards from the start of an interleave
set (lowest dimm-physical-address (DPA)).  BLK-namespaces that alias
with a PMEM interleave set will grow allocations backward from the
highest DPA.

Cc: Greg KH <[email protected]>
Cc: Neil Brown <[email protected]>
Acked-by: Christoph Hellwig <[email protected]>
Signed-off-by: Dan Williams <[email protected]>

Author: djbw

drivers/nvdimm/bus.c

@@ -97,6 +97,8 @@ static int nvdimm_bus_probe(struct device *dev)
 	rc = nd_drv->probe(dev);
 	if (rc == 0)
 		nd_region_probe_success(nvdimm_bus, dev);
+	else
+		nd_region_disable(nvdimm_bus, dev);
 	nvdimm_bus_probe_end(nvdimm_bus);
 
 	dev_dbg(&nvdimm_bus->dev, "%s.probe(%s) = %d\n", dev->driver->name,
@@ -381,8 +383,10 @@ u32 nd_cmd_out_size(struct nvdimm *nvdimm, int cmd,
 }
 EXPORT_SYMBOL_GPL(nd_cmd_out_size);
 
-static void wait_nvdimm_bus_probe_idle(struct nvdimm_bus *nvdimm_bus)
+void wait_nvdimm_bus_probe_idle(struct device *dev)
 {
+	struct nvdimm_bus *nvdimm_bus = walk_to_nvdimm_bus(dev);
+
 	do {
 		if (nvdimm_bus->probe_active == 0)
 			break;
@@ -402,7 +406,7 @@ static int nd_cmd_clear_to_send(struct nvdimm *nvdimm, unsigned int cmd)
 		return 0;
 
 	nvdimm_bus = walk_to_nvdimm_bus(&nvdimm->dev);
-	wait_nvdimm_bus_probe_idle(nvdimm_bus);
+	wait_nvdimm_bus_probe_idle(&nvdimm_bus->dev);
 
 	if (atomic_read(&nvdimm->busy))
 		return -EBUSY;

drivers/nvdimm/core.c

@@ -14,6 +14,7 @@
 #include <linux/export.h>
 #include <linux/module.h>
 #include <linux/device.h>
+#include <linux/ctype.h>
 #include <linux/ndctl.h>
 #include <linux/mutex.h>
 #include <linux/slab.h>
@@ -109,6 +110,69 @@ struct nvdimm_bus *walk_to_nvdimm_bus(struct device *nd_dev)
 	return NULL;
 }
 
+static bool is_uuid_sep(char sep)
+{
+	if (sep == '\n' || sep == '-' || sep == ':' || sep == '\0')
+		return true;
+	return false;
+}
+
+static int nd_uuid_parse(struct device *dev, u8 *uuid_out, const char *buf,
+		size_t len)
+{
+	const char *str = buf;
+	u8 uuid[16];
+	int i;
+
+	for (i = 0; i < 16; i++) {
+		if (!isxdigit(str[0]) || !isxdigit(str[1])) {
+			dev_dbg(dev, "%s: pos: %d buf[%zd]: %c buf[%zd]: %c\n",
+					__func__, i, str - buf, str[0],
+					str + 1 - buf, str[1]);
+			return -EINVAL;
+		}
+
+		uuid[i] = (hex_to_bin(str[0]) << 4) | hex_to_bin(str[1]);
+		str += 2;
+		if (is_uuid_sep(*str))
+			str++;
+	}
+
+	memcpy(uuid_out, uuid, sizeof(uuid));
+	return 0;
+}
+
+/**
+ * nd_uuid_store: common implementation for writing 'uuid' sysfs attributes
+ * @dev: container device for the uuid property
+ * @uuid_out: uuid buffer to replace
+ * @buf: raw sysfs buffer to parse
+ *
+ * Enforce that uuids can only be changed while the device is disabled
+ * (driver detached)
+ * LOCKING: expects device_lock() is held on entry
+ */
+int nd_uuid_store(struct device *dev, u8 **uuid_out, const char *buf,
+		size_t len)
+{
+	u8 uuid[16];
+	int rc;
+
+	if (dev->driver)
+		return -EBUSY;
+
+	rc = nd_uuid_parse(dev, uuid, buf, len);
+	if (rc)
+		return rc;
+
+	kfree(*uuid_out);
+	*uuid_out = kmemdup(uuid, sizeof(uuid), GFP_KERNEL);
+	if (!(*uuid_out))
+		return -ENOMEM;
+
+	return 0;
+}
+
 static ssize_t commands_show(struct device *dev,
 		struct device_attribute *attr, char *buf)
 {

drivers/nvdimm/dimm.c

@@ -21,18 +21,6 @@
 #include "label.h"
 #include "nd.h"
 
-static void free_data(struct nvdimm_drvdata *ndd)
-{
-	if (!ndd)
-		return;
-
-	if (ndd->data && is_vmalloc_addr(ndd->data))
-		vfree(ndd->data);
-	else
-		kfree(ndd->data);
-	kfree(ndd);
-}
-
 static int nvdimm_probe(struct device *dev)
 {
 	struct nvdimm_drvdata *ndd;
@@ -49,6 +37,8 @@ static int nvdimm_probe(struct device *dev)
 	ndd->dpa.start = 0;
 	ndd->dpa.end = -1;
 	ndd->dev = dev;
+	get_device(dev);
+	kref_init(&ndd->kref);
 
 	rc = nvdimm_init_nsarea(ndd);
 	if (rc)
@@ -74,21 +64,18 @@ static int nvdimm_probe(struct device *dev)
 	return 0;
 
  err:
-	free_data(ndd);
+	put_ndd(ndd);
 	return rc;
 }
 
 static int nvdimm_remove(struct device *dev)
 {
 	struct nvdimm_drvdata *ndd = dev_get_drvdata(dev);
-	struct resource *res, *_r;
 
 	nvdimm_bus_lock(dev);
 	dev_set_drvdata(dev, NULL);
-	for_each_dpa_resource_safe(ndd, res, _r)
-		nvdimm_free_dpa(ndd, res);
 	nvdimm_bus_unlock(dev);
-	free_data(ndd);
+	put_ndd(ndd);
 
 	return 0;
 }

drivers/nvdimm/dimm_devs.c

@@ -159,6 +159,48 @@ struct nvdimm *to_nvdimm(struct device *dev)
 }
 EXPORT_SYMBOL_GPL(to_nvdimm);
 
+struct nvdimm_drvdata *to_ndd(struct nd_mapping *nd_mapping)
+{
+	struct nvdimm *nvdimm = nd_mapping->nvdimm;
+
+	WARN_ON_ONCE(!is_nvdimm_bus_locked(&nvdimm->dev));
+
+	return dev_get_drvdata(&nvdimm->dev);
+}
+EXPORT_SYMBOL(to_ndd);
+
+void nvdimm_drvdata_release(struct kref *kref)
+{
+	struct nvdimm_drvdata *ndd = container_of(kref, typeof(*ndd), kref);
+	struct device *dev = ndd->dev;
+	struct resource *res, *_r;
+
+	dev_dbg(dev, "%s\n", __func__);
+
+	nvdimm_bus_lock(dev);
+	for_each_dpa_resource_safe(ndd, res, _r)
+		nvdimm_free_dpa(ndd, res);
+	nvdimm_bus_unlock(dev);
+
+	if (ndd->data && is_vmalloc_addr(ndd->data))
+		vfree(ndd->data);
+	else
+		kfree(ndd->data);
+	kfree(ndd);
+	put_device(dev);
+}
+
+void get_ndd(struct nvdimm_drvdata *ndd)
+{
+	kref_get(&ndd->kref);
+}
+
+void put_ndd(struct nvdimm_drvdata *ndd)
+{
+	if (ndd)
+		kref_put(&ndd->kref, nvdimm_drvdata_release);
+}
+
 const char *nvdimm_name(struct nvdimm *nvdimm)
 {
 	return dev_name(&nvdimm->dev);
@@ -247,6 +289,83 @@ struct nvdimm *nvdimm_create(struct nvdimm_bus *nvdimm_bus, void *provider_data,
 }
 EXPORT_SYMBOL_GPL(nvdimm_create);
 
+/**
+ * nd_pmem_available_dpa - for the given dimm+region account unallocated dpa
+ * @nd_mapping: container of dpa-resource-root + labels
+ * @nd_region: constrain available space check to this reference region
+ * @overlap: calculate available space assuming this level of overlap
+ *
+ * Validate that a PMEM label, if present, aligns with the start of an
+ * interleave set and truncate the available size at the lowest BLK
+ * overlap point.
+ *
+ * The expectation is that this routine is called multiple times as it
+ * probes for the largest BLK encroachment for any single member DIMM of
+ * the interleave set.  Once that value is determined the PMEM-limit for
+ * the set can be established.
+ */
+resource_size_t nd_pmem_available_dpa(struct nd_region *nd_region,
+		struct nd_mapping *nd_mapping, resource_size_t *overlap)
+{
+	resource_size_t map_start, map_end, busy = 0, available, blk_start;
+	struct nvdimm_drvdata *ndd = to_ndd(nd_mapping);
+	struct resource *res;
+	const char *reason;
+
+	if (!ndd)
+		return 0;
+
+	map_start = nd_mapping->start;
+	map_end = map_start + nd_mapping->size - 1;
+	blk_start = max(map_start, map_end + 1 - *overlap);
+	for_each_dpa_resource(ndd, res)
+		if (res->start >= map_start && res->start < map_end) {
+			if (strncmp(res->name, "blk", 3) == 0)
+				blk_start = min(blk_start, res->start);
+			else if (res->start != map_start) {
+				reason = "misaligned to iset";
+				goto err;
+			} else {
+				if (busy) {
+					reason = "duplicate overlapping PMEM reservations?";
+					goto err;
+				}
+				busy += resource_size(res);
+				continue;
+			}
+		} else if (res->end >= map_start && res->end <= map_end) {
+			if (strncmp(res->name, "blk", 3) == 0) {
+				/*
+				 * If a BLK allocation overlaps the start of
+				 * PMEM the entire interleave set may now only
+				 * be used for BLK.
+				 */
+				blk_start = map_start;
+			} else {
+				reason = "misaligned to iset";
+				goto err;
+			}
+		} else if (map_start > res->start && map_start < res->end) {
+			/* total eclipse of the mapping */
+			busy += nd_mapping->size;
+			blk_start = map_start;
+		}
+
+	*overlap = map_end + 1 - blk_start;
+	available = blk_start - map_start;
+	if (busy < available)
+		return available - busy;
+	return 0;
+
+ err:
+	/*
+	 * Something is wrong, PMEM must align with the start of the
+	 * interleave set, and there can only be one allocation per set.
+	 */
+	nd_dbg_dpa(nd_region, ndd, res, "%s\n", reason);
+	return 0;
+}
+
 void nvdimm_free_dpa(struct nvdimm_drvdata *ndd, struct resource *res)
 {
 	WARN_ON_ONCE(!is_nvdimm_bus_locked(ndd->dev));
@@ -271,6 +390,24 @@ struct resource *nvdimm_allocate_dpa(struct nvdimm_drvdata *ndd,
 	return res;
 }
 
+/**
+ * nvdimm_allocated_dpa - sum up the dpa currently allocated to this label_id
+ * @nvdimm: container of dpa-resource-root + labels
+ * @label_id: dpa resource name of the form {pmem|blk}-<human readable uuid>
+ */
+resource_size_t nvdimm_allocated_dpa(struct nvdimm_drvdata *ndd,
+		struct nd_label_id *label_id)
+{
+	resource_size_t allocated = 0;
+	struct resource *res;
+
+	for_each_dpa_resource(ndd, res)
+		if (strcmp(res->name, label_id->id) == 0)
+			allocated += resource_size(res);
+
+	return allocated;
+}
+
 static int count_dimms(struct device *dev, void *c)
 {
 	int *count = c;

drivers/nvdimm/label.c

@@ -230,7 +230,7 @@ static bool preamble_current(struct nvdimm_drvdata *ndd,
 	return true;
 }
 
-static char *nd_label_gen_id(struct nd_label_id *label_id, u8 *uuid, u32 flags)
+char *nd_label_gen_id(struct nd_label_id *label_id, u8 *uuid, u32 flags)
 {
 	if (!label_id || !uuid)
 		return NULL;
@@ -288,3 +288,56 @@ int nd_label_reserve_dpa(struct nvdimm_drvdata *ndd)
 
 	return 0;
 }
+
+int nd_label_active_count(struct nvdimm_drvdata *ndd)
+{
+	struct nd_namespace_index *nsindex;
+	unsigned long *free;
+	u32 nslot, slot;
+	int count = 0;
+
+	if (!preamble_current(ndd, &nsindex, &free, &nslot))
+		return 0;
+
+	for_each_clear_bit_le(slot, free, nslot) {
+		struct nd_namespace_label *nd_label;
+
+		nd_label = nd_label_base(ndd) + slot;
+
+		if (!slot_valid(nd_label, slot)) {
+			u32 label_slot = __le32_to_cpu(nd_label->slot);
+			u64 size = __le64_to_cpu(nd_label->rawsize);
+			u64 dpa = __le64_to_cpu(nd_label->dpa);
+
+			dev_dbg(ndd->dev,
+				"%s: slot%d invalid slot: %d dpa: %llx size: %llx\n",
+					__func__, slot, label_slot, dpa, size);
+			continue;
+		}
+		count++;
+	}
+	return count;
+}
+
+struct nd_namespace_label *nd_label_active(struct nvdimm_drvdata *ndd, int n)
+{
+	struct nd_namespace_index *nsindex;
+	unsigned long *free;
+	u32 nslot, slot;
+
+	if (!preamble_current(ndd, &nsindex, &free, &nslot))
+		return NULL;
+
+	for_each_clear_bit_le(slot, free, nslot) {
+		struct nd_namespace_label *nd_label;
+
+		nd_label = nd_label_base(ndd) + slot;
+		if (!slot_valid(nd_label, slot))
+			continue;
+
+		if (n-- == 0)
+			return nd_label_base(ndd) + slot;
+	}
+
+	return NULL;
+}

drivers/nvdimm/label.h

@@ -125,4 +125,6 @@ int nd_label_validate(struct nvdimm_drvdata *ndd);
 void nd_label_copy(struct nvdimm_drvdata *ndd, struct nd_namespace_index *dst,
 		struct nd_namespace_index *src);
 size_t sizeof_namespace_index(struct nvdimm_drvdata *ndd);
+int nd_label_active_count(struct nvdimm_drvdata *ndd);
+struct nd_namespace_label *nd_label_active(struct nvdimm_drvdata *ndd, int n);
 #endif /* __LABEL_H__ */