const char *nvdimm_namespace_disk_name(struct nd_namespace_common *ndns,
char *name)
{
struct nd_region *nd_region = to_nd_region(ndns->dev.parent);
const char *suffix = NULL;
if (ndns->claim) {
if (is_nd_btt(ndns->claim))
suffix = "s";
else if (is_nd_pfn(ndns->claim))
suffix = "m";
else
dev_WARN_ONCE(&ndns->dev, 1,
"unknown claim type by %s\n",
dev_name(ndns->claim));
}
if (is_namespace_pmem(&ndns->dev) || is_namespace_io(&ndns->dev)) {
if (!suffix && pmem_should_map_pages(&ndns->dev))
suffix = "m";
sprintf(name, "pmem%d%s", nd_region->id, suffix ? suffix : "");
} else if (is_namespace_blk(&ndns->dev)) {
struct nd_namespace_blk *nsblk;
nsblk = to_nd_namespace_blk(&ndns->dev);
sprintf(name, "ndblk%d.%d%s", nd_region->id, nsblk->id,
suffix ? suffix : "");
} else {
return NULL;
}
return name;
}
int nd_pfn_probe(struct nd_namespace_common *ndns, void *drvdata)
{
int rc;
struct device *dev;
struct nd_pfn *nd_pfn;
struct nd_pfn_sb *pfn_sb;
struct nd_region *nd_region = to_nd_region(ndns->dev.parent);
if (ndns->force_raw)
return -ENODEV;
nvdimm_bus_lock(&ndns->dev);
dev = __nd_pfn_create(nd_region, NULL, PFN_MODE_NONE, ndns);
nvdimm_bus_unlock(&ndns->dev);
if (!dev)
return -ENOMEM;
dev_set_drvdata(dev, drvdata);
pfn_sb = kzalloc(sizeof(*pfn_sb), GFP_KERNEL);
nd_pfn = to_nd_pfn(dev);
nd_pfn->pfn_sb = pfn_sb;
rc = nd_pfn_validate(nd_pfn);
nd_pfn->pfn_sb = NULL;
kfree(pfn_sb);
dev_dbg(&ndns->dev, "%s: pfn: %s\n", __func__,
rc == 0 ? dev_name(dev) : "<none>");
if (rc < 0) {
__nd_detach_ndns(dev, &nd_pfn->ndns);
put_device(dev);
} else
__nd_device_register(&nd_pfn->dev);
return rc;
}
struct nd_blk_region *to_nd_blk_region(struct device *dev)
{
struct nd_region *nd_region = to_nd_region(dev);
WARN_ON(!is_nd_blk(dev));
return container_of(nd_region, struct nd_blk_region, nd_region);
}
static ssize_t read_only_show(struct device *dev,
struct device_attribute *attr, char *buf)
{
struct nd_region *nd_region = to_nd_region(dev);
return sprintf(buf, "%d\n", nd_region->ro);
}
static ssize_t nstype_show(struct device *dev,
struct device_attribute *attr, char *buf)
{
struct nd_region *nd_region = to_nd_region(dev);
return sprintf(buf, "%d\n", nd_region_to_nstype(nd_region));
}
int nd_btt_probe(struct nd_namespace_common *ndns, void *drvdata)
{
int rc;
struct device *dev;
struct btt_sb *btt_sb;
struct nd_region *nd_region = to_nd_region(ndns->dev.parent);
if (ndns->force_raw)
return -ENODEV;
nvdimm_bus_lock(&ndns->dev);
dev = __nd_btt_create(nd_region, 0, NULL, ndns);
nvdimm_bus_unlock(&ndns->dev);
if (!dev)
return -ENOMEM;
dev_set_drvdata(dev, drvdata);
btt_sb = kzalloc(sizeof(*btt_sb), GFP_KERNEL);
rc = __nd_btt_probe(to_nd_btt(dev), ndns, btt_sb);
kfree(btt_sb);
dev_dbg(&ndns->dev, "%s: btt: %s\n", __func__,
rc == 0 ? dev_name(dev) : "<none>");
if (rc < 0) {
__nd_btt_detach_ndns(to_nd_btt(dev));
put_device(dev);
}
return rc;
}
static ssize_t mappings_show(struct device *dev,
struct device_attribute *attr, char *buf)
{
struct nd_region *nd_region = to_nd_region(dev);
return sprintf(buf, "%d\n", nd_region->ndr_mappings);
}
static int is_uuid_busy(struct device *dev, void *data)
{
struct nd_region *nd_region = to_nd_region(dev->parent);
u8 *uuid = data;
switch (nd_region_to_nstype(nd_region)) {
case ND_DEVICE_NAMESPACE_PMEM: {
struct nd_namespace_pmem *nspm = to_nd_namespace_pmem(dev);
if (!nspm->uuid)
break;
if (memcmp(uuid, nspm->uuid, NSLABEL_UUID_LEN) == 0)
return -EBUSY;
break;
}
case ND_DEVICE_NAMESPACE_BLK: {
struct nd_namespace_blk *nsblk = to_nd_namespace_blk(dev);
if (!nsblk->uuid)
break;
if (memcmp(uuid, nsblk->uuid, NSLABEL_UUID_LEN) == 0)
return -EBUSY;
break;
}
default:
break;
}
return 0;
}
/*
* Upon successful probe/remove, take/release a reference on the
* associated interleave set (if present), and plant new btt + namespace
* seeds. Also, on the removal of a BLK region, notify the provider to
* disable the region.
*/
static void nd_region_notify_driver_action(struct nvdimm_bus *nvdimm_bus,
struct device *dev, bool probe)
{
struct nd_region *nd_region;
if (!probe && (is_nd_pmem(dev) || is_nd_blk(dev))) {
int i;
nd_region = to_nd_region(dev);
for (i = 0; i < nd_region->ndr_mappings; i++) {
struct nd_mapping *nd_mapping = &nd_region->mapping[i];
struct nvdimm_drvdata *ndd = nd_mapping->ndd;
struct nvdimm *nvdimm = nd_mapping->nvdimm;
kfree(nd_mapping->labels);
nd_mapping->labels = NULL;
put_ndd(ndd);
nd_mapping->ndd = NULL;
if (ndd)
atomic_dec(&nvdimm->busy);
}
if (is_nd_pmem(dev))
return;
to_nd_blk_region(dev)->disable(nvdimm_bus, dev);
}
if (dev->parent && is_nd_blk(dev->parent) && probe) {
nd_region = to_nd_region(dev->parent);
nvdimm_bus_lock(dev);
if (nd_region->ns_seed == dev)
nd_region_create_blk_seed(nd_region);
nvdimm_bus_unlock(dev);
}
if (is_nd_btt(dev) && probe) {
struct nd_btt *nd_btt = to_nd_btt(dev);
nd_region = to_nd_region(dev->parent);
nvdimm_bus_lock(dev);
if (nd_region->btt_seed == dev)
nd_region_create_btt_seed(nd_region);
if (nd_region->ns_seed == &nd_btt->ndns->dev &&
is_nd_blk(dev->parent))
nd_region_create_blk_seed(nd_region);
nvdimm_bus_unlock(dev);
}
}
static umode_t mapping_visible(struct kobject *kobj, struct attribute *a, int n)
{
struct device *dev = container_of(kobj, struct device, kobj);
struct nd_region *nd_region = to_nd_region(dev);
if (n < nd_region->ndr_mappings)
return a->mode;
return 0;
}
static bool is_nd_btt_idle(struct device *dev)
{
struct nd_region *nd_region = to_nd_region(dev->parent);
struct nd_btt *nd_btt = to_nd_btt(dev);
if (nd_region->btt_seed == dev || nd_btt->ndns || dev->driver)
return false;
return true;
}
static void nd_btt_release(struct device *dev)
{
struct nd_region *nd_region = to_nd_region(dev->parent);
struct nd_btt *nd_btt = to_nd_btt(dev);
dev_dbg(dev, "%s\n", __func__);
nd_btt_detach_ndns(nd_btt);
ida_simple_remove(&nd_region->btt_ida, nd_btt->id);
kfree(nd_btt->uuid);
kfree(nd_btt);
}
static int nd_region_probe(struct device *dev)
{
int err, rc;
static unsigned long once;
struct nd_region_namespaces *num_ns;
struct nd_region *nd_region = to_nd_region(dev);
if (nd_region->num_lanes > num_online_cpus()
&& nd_region->num_lanes < num_possible_cpus()
&& !test_and_set_bit(0, &once)) {
dev_info(dev, "online cpus (%d) < concurrent i/o lanes (%d) < possible cpus (%d)\n",
num_online_cpus(), nd_region->num_lanes,
num_possible_cpus());
dev_info(dev, "setting nr_cpus=%d may yield better libnvdimm device performance\n",
nd_region->num_lanes);
}
rc = nd_blk_region_init(nd_region);
if (rc)
return rc;
rc = nd_region_register_namespaces(nd_region, &err);
num_ns = devm_kzalloc(dev, sizeof(*num_ns), GFP_KERNEL);
if (!num_ns)
return -ENOMEM;
if (rc < 0)
return rc;
num_ns->active = rc;
num_ns->count = rc + err;
dev_set_drvdata(dev, num_ns);
if (rc && err && rc == err)
return -ENODEV;
nd_region->btt_seed = nd_btt_create(nd_region);
nd_region->pfn_seed = nd_pfn_create(nd_region);
if (err == 0)
return 0;
/*
* Given multiple namespaces per region, we do not want to
* disable all the successfully registered peer namespaces upon
* a single registration failure. If userspace is missing a
* namespace that it expects it can disable/re-enable the region
* to retry discovery after correcting the failure.
* <regionX>/namespaces returns the current
* "<async-registered>/<total>" namespace count.
*/
dev_err(dev, "failed to register %d namespace%s, continuing...\n",
err, err == 1 ? "" : "s");
return 0;
}
static void nd_pfn_release(struct device *dev)
{
struct nd_region *nd_region = to_nd_region(dev->parent);
struct nd_pfn *nd_pfn = to_nd_pfn(dev);
dev_dbg(dev, "%s\n", __func__);
nd_detach_ndns(&nd_pfn->dev, &nd_pfn->ndns);
ida_simple_remove(&nd_region->pfn_ida, nd_pfn->id);
kfree(nd_pfn->uuid);
kfree(nd_pfn);
}
static void namespace_blk_release(struct device *dev)
{
struct nd_namespace_blk *nsblk = to_nd_namespace_blk(dev);
struct nd_region *nd_region = to_nd_region(dev->parent);
if (nsblk->id >= 0)
ida_simple_remove(&nd_region->ns_ida, nsblk->id);
kfree(nsblk->alt_name);
kfree(nsblk->uuid);
kfree(nsblk->res);
kfree(nsblk);
}
static ssize_t read_only_store(struct device *dev,
struct device_attribute *attr, const char *buf, size_t len)
{
bool ro;
int rc = strtobool(buf, &ro);
struct nd_region *nd_region = to_nd_region(dev);
if (rc)
return rc;
nd_region->ro = ro;
return len;
}
static ssize_t set_cookie_show(struct device *dev,
struct device_attribute *attr, char *buf)
{
struct nd_region *nd_region = to_nd_region(dev);
struct nd_interleave_set *nd_set = nd_region->nd_set;
if (is_nd_pmem(dev) && nd_set)
/* pass, should be precluded by region_visible */;
else
return -ENXIO;
return sprintf(buf, "%#llx\n", nd_set->cookie);
}
/**
* nvdimm_namespace_add_poison() - Convert a list of poison ranges to badblocks
* @ndns: the namespace containing poison ranges
* @bb: badblocks instance to populate
* @offset: offset at the start of the namespace before 'sector 0'
*
* The poison list generated during NFIT initialization may contain multiple,
* possibly overlapping ranges in the SPA (System Physical Address) space.
* Compare each of these ranges to the namespace currently being initialized,
* and add badblocks to the gendisk for all matching sub-ranges
*/
void nvdimm_namespace_add_poison(struct nd_namespace_common *ndns,
struct badblocks *bb, resource_size_t offset)
{
struct nd_namespace_io *nsio = to_nd_namespace_io(&ndns->dev);
struct nd_region *nd_region = to_nd_region(ndns->dev.parent);
struct nvdimm_bus *nvdimm_bus;
struct list_head *poison_list;
u64 ns_start, ns_end, ns_size;
struct nd_poison *pl;
ns_size = nvdimm_namespace_capacity(ndns) - offset;
ns_start = nsio->res.start + offset;
ns_end = nsio->res.end;
nvdimm_bus = to_nvdimm_bus(nd_region->dev.parent);
poison_list = &nvdimm_bus->poison_list;
if (list_empty(poison_list))
return;
list_for_each_entry(pl, poison_list, list) {
u64 pl_end = pl->start + pl->length - 1;
/* Discard intervals with no intersection */
if (pl_end < ns_start)
continue;
if (pl->start > ns_end)
continue;
/* Deal with any overlap after start of the namespace */
if (pl->start >= ns_start) {
u64 start = pl->start;
u64 len;
if (pl_end <= ns_end)
len = pl->length;
else
len = ns_start + ns_size - pl->start;
__add_badblock_range(bb, start - ns_start, len);
continue;
}
/* Deal with overlap for poison starting before the namespace */
if (pl->start < ns_start) {
u64 len;
if (pl_end < ns_end)
len = pl->start + pl->length - ns_start;
else
len = ns_size;
__add_badblock_range(bb, 0, len);
}
}
static ssize_t mappingN(struct device *dev, char *buf, int n)
{
struct nd_region *nd_region = to_nd_region(dev);
struct nd_mapping *nd_mapping;
struct nvdimm *nvdimm;
if (n >= nd_region->ndr_mappings)
return -ENXIO;
nd_mapping = &nd_region->mapping[n];
nvdimm = nd_mapping->nvdimm;
return sprintf(buf, "%s,%llu,%llu\n", dev_name(&nvdimm->dev),
nd_mapping->start, nd_mapping->size);
}
static ssize_t namespace_seed_show(struct device *dev,
struct device_attribute *attr, char *buf)
{
struct nd_region *nd_region = to_nd_region(dev);
ssize_t rc;
nvdimm_bus_lock(dev);
if (nd_region->ns_seed)
rc = sprintf(buf, "%s\n", dev_name(nd_region->ns_seed));
else
rc = sprintf(buf, "\n");
nvdimm_bus_unlock(dev);
return rc;
}
static int nd_region_remove(struct device *dev)
{
struct nd_region *nd_region = to_nd_region(dev);
/* flush attribute readers and disable */
nvdimm_bus_lock(dev);
nd_region->ns_seed = NULL;
nd_region->btt_seed = NULL;
nd_region->pfn_seed = NULL;
dev_set_drvdata(dev, NULL);
nvdimm_bus_unlock(dev);
device_for_each_child(dev, NULL, child_unregister);
return 0;
}
static ssize_t size_show(struct device *dev,
struct device_attribute *attr, char *buf)
{
struct nd_region *nd_region = to_nd_region(dev);
unsigned long long size = 0;
if (is_nd_pmem(dev)) {
size = nd_region->ndr_size;
} else if (nd_region->ndr_mappings == 1) {
struct nd_mapping *nd_mapping = &nd_region->mapping[0];
size = nd_mapping->size;
}
return sprintf(buf, "%llu\n", size);
}
static bool is_idle(struct device *dev, struct nd_namespace_common *ndns)
{
struct nd_region *nd_region = to_nd_region(dev->parent);
struct device *seed = NULL;
if (is_nd_btt(dev))
seed = nd_region->btt_seed;
else if (is_nd_pfn(dev))
seed = nd_region->pfn_seed;
else if (is_nd_dax(dev))
seed = nd_region->dax_seed;
if (seed == dev || ndns || dev->driver)
return false;
return true;
}
static resource_size_t nd_namespace_blk_size(struct nd_namespace_blk *nsblk)
{
struct nd_region *nd_region = to_nd_region(nsblk->common.dev.parent);
struct nd_mapping *nd_mapping = &nd_region->mapping[0];
struct nvdimm_drvdata *ndd = to_ndd(nd_mapping);
struct nd_label_id label_id;
resource_size_t size = 0;
struct resource *res;
if (!nsblk->uuid)
return 0;
nd_label_gen_id(&label_id, nsblk->uuid, NSLABEL_FLAG_LOCAL);
for_each_dpa_resource(ndd, res)
if (strcmp(res->name, label_id.id) == 0)
size += resource_size(res);
return size;
}
static bool __nd_namespace_blk_validate(struct nd_namespace_blk *nsblk)
{
struct nd_region *nd_region = to_nd_region(nsblk->common.dev.parent);
struct nd_mapping *nd_mapping = &nd_region->mapping[0];
struct nvdimm_drvdata *ndd = to_ndd(nd_mapping);
struct nd_label_id label_id;
struct resource *res;
int count, i;
if (!nsblk->uuid || !nsblk->lbasize || !ndd)
return false;
count = 0;
nd_label_gen_id(&label_id, nsblk->uuid, NSLABEL_FLAG_LOCAL);
for_each_dpa_resource(ndd, res) {
if (strcmp(res->name, label_id.id) != 0)
continue;
/*
* Resources with unacknoweldged adjustments indicate a
* failure to update labels
*/
if (res->flags & DPA_RESOURCE_ADJUSTED)
return false;
count++;
}
/* These values match after a successful label update */
if (count != nsblk->num_resources)
return false;
for (i = 0; i < nsblk->num_resources; i++) {
struct resource *found = NULL;
for_each_dpa_resource(ndd, res)
if (res == nsblk->res[i]) {
found = res;
break;
}
/* stale resource */
if (!found)
return false;
}
return true;
}
static void nd_region_release(struct device *dev)
{
struct nd_region *nd_region = to_nd_region(dev);
u16 i;
for (i = 0; i < nd_region->ndr_mappings; i++) {
struct nd_mapping *nd_mapping = &nd_region->mapping[i];
struct nvdimm *nvdimm = nd_mapping->nvdimm;
put_device(&nvdimm->dev);
}
free_percpu(nd_region->lane);
ida_simple_remove(®ion_ida, nd_region->id);
if (is_nd_blk(dev))
kfree(to_nd_blk_region(dev));
else
kfree(nd_region);
}
static ssize_t alt_name_store(struct device *dev,
struct device_attribute *attr, const char *buf, size_t len)
{
struct nd_region *nd_region = to_nd_region(dev->parent);
ssize_t rc;
device_lock(dev);
nvdimm_bus_lock(dev);
wait_nvdimm_bus_probe_idle(dev);
rc = __alt_name_store(dev, buf, len);
if (rc >= 0)
rc = nd_namespace_label_update(nd_region, dev);
dev_dbg(dev, "%s: %s(%zd)\n", __func__, rc < 0 ? "fail " : "", rc);
nvdimm_bus_unlock(dev);
device_unlock(dev);
return rc < 0 ? rc : len;
}
bool pmem_should_map_pages(struct device *dev)
{
struct nd_region *nd_region = to_nd_region(dev->parent);
if (!IS_ENABLED(CONFIG_ZONE_DEVICE))
return false;
if (!test_bit(ND_REGION_PAGEMAP, &nd_region->flags))
return false;
if (is_nd_pfn(dev) || is_nd_btt(dev))
return false;
#ifdef ARCH_MEMREMAP_PMEM
return ARCH_MEMREMAP_PMEM == MEMREMAP_WB;
#else
return false;
#endif
}
static ssize_t available_size_show(struct device *dev,
struct device_attribute *attr, char *buf)
{
struct nd_region *nd_region = to_nd_region(dev);
unsigned long long available = 0;
/*
* Flush in-flight updates and grab a snapshot of the available
* size. Of course, this value is potentially invalidated the
* memory nvdimm_bus_lock() is dropped, but that's userspace's
* problem to not race itself.
*/
nvdimm_bus_lock(dev);
wait_nvdimm_bus_probe_idle(dev);
available = nd_region_available_dpa(nd_region);
nvdimm_bus_unlock(dev);
return sprintf(buf, "%llu\n", available);
}
static umode_t region_visible(struct kobject *kobj, struct attribute *a, int n)
{
struct device *dev = container_of(kobj, typeof(*dev), kobj);
struct nd_region *nd_region = to_nd_region(dev);
struct nd_interleave_set *nd_set = nd_region->nd_set;
int type = nd_region_to_nstype(nd_region);
if (a != &dev_attr_set_cookie.attr
&& a != &dev_attr_available_size.attr)
return a->mode;
if ((type == ND_DEVICE_NAMESPACE_PMEM
|| type == ND_DEVICE_NAMESPACE_BLK)
&& a == &dev_attr_available_size.attr)
return a->mode;
else if (is_nd_pmem(dev) && nd_set)
return a->mode;
return 0;
}
