[PATCH 11/21] nd_region: support for legacy nvdimms

From: Dan Williams
Date: Fri Apr 17 2015 - 21:39:02 EST


The NFIT region driver is an intermediary driver that translates NFIT
defined "region"s into "namespace" devices that are consumed by
persistent memory block drivers. A "namespace" is a sub-division of a
region.

Support for NVDIMM labels is reserved for a later patch. For now,
publish 'nd_namespace_io' devices which are simply memory ranges with no
regard for dimm boundaries, interleave, or aliasing. This also adds a
"nstype" attribute to the parent region so that userspace can know ahead
of time the type of namespaces a given region will produce.

Signed-off-by: Dan Williams <dan.j.williams@xxxxxxxxx>
---
drivers/block/nd/Makefile | 2 +
drivers/block/nd/bus.c | 26 +++++++++
drivers/block/nd/core.c | 18 ++++--
drivers/block/nd/dimm.c | 2 -
drivers/block/nd/namespace_devs.c | 111 +++++++++++++++++++++++++++++++++++++
drivers/block/nd/nd-private.h | 8 ++-
drivers/block/nd/nd.h | 7 ++
drivers/block/nd/nfit.h | 7 ++
drivers/block/nd/region.c | 88 +++++++++++++++++++++++++++++
drivers/block/nd/region_devs.c | 65 +++++++++++++++++++++-
include/linux/nd.h | 10 +++
include/uapi/linux/ndctl.h | 10 +++
12 files changed, 343 insertions(+), 11 deletions(-)
create mode 100644 drivers/block/nd/namespace_devs.c
create mode 100644 drivers/block/nd/region.c

diff --git a/drivers/block/nd/Makefile b/drivers/block/nd/Makefile
index 6698acbe7b44..769ddc34f974 100644
--- a/drivers/block/nd/Makefile
+++ b/drivers/block/nd/Makefile
@@ -24,3 +24,5 @@ nd-y += bus.o
nd-y += dimm_devs.o
nd-y += dimm.o
nd-y += region_devs.o
+nd-y += region.o
+nd-y += namespace_devs.o
diff --git a/drivers/block/nd/bus.c b/drivers/block/nd/bus.c
index c815dd425a49..c98fe05a4c9b 100644
--- a/drivers/block/nd/bus.c
+++ b/drivers/block/nd/bus.c
@@ -13,6 +13,7 @@
#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
#include <linux/vmalloc.h>
#include <linux/uaccess.h>
+#include <linux/module.h>
#include <linux/fcntl.h>
#include <linux/async.h>
#include <linux/ndctl.h>
@@ -34,6 +35,12 @@ static int to_nd_device_type(struct device *dev)
{
if (is_nd_dimm(dev))
return ND_DEVICE_DIMM;
+ else if (is_nd_pmem(dev))
+ return ND_DEVICE_REGION_PMEM;
+ else if (is_nd_blk(dev))
+ return ND_DEVICE_REGION_BLOCK;
+ else if (is_nd_pmem(dev->parent) || is_nd_blk(dev->parent))
+ return nd_region_to_namespace_type(to_nd_region(dev->parent));

return 0;
}
@@ -51,27 +58,46 @@ static int nd_bus_match(struct device *dev, struct device_driver *drv)
return test_bit(to_nd_device_type(dev), &nd_drv->type);
}

+static struct module *to_bus_provider(struct device *dev)
+{
+ /* pin bus providers while regions are enabled */
+ if (is_nd_pmem(dev) || is_nd_blk(dev)) {
+ struct nd_bus *nd_bus = walk_to_nd_bus(dev);
+
+ return nd_bus->module;
+ }
+ return NULL;
+}
+
static int nd_bus_probe(struct device *dev)
{
struct nd_device_driver *nd_drv = to_nd_device_driver(dev->driver);
+ struct module *provider = to_bus_provider(dev);
struct nd_bus *nd_bus = walk_to_nd_bus(dev);
int rc;

+ if (!try_module_get(provider))
+ return -ENXIO;
+
rc = nd_drv->probe(dev);
dev_dbg(&nd_bus->dev, "%s.probe(%s) = %d\n", dev->driver->name,
dev_name(dev), rc);
+ if (rc != 0)
+ module_put(provider);
return rc;
}

static int nd_bus_remove(struct device *dev)
{
struct nd_device_driver *nd_drv = to_nd_device_driver(dev->driver);
+ struct module *provider = to_bus_provider(dev);
struct nd_bus *nd_bus = walk_to_nd_bus(dev);
int rc;

rc = nd_drv->remove(dev);
dev_dbg(&nd_bus->dev, "%s.remove(%s) = %d\n", dev->driver->name,
dev_name(dev), rc);
+ module_put(provider);
return rc;
}

diff --git a/drivers/block/nd/core.c b/drivers/block/nd/core.c
index 32ecd6f05c90..c795e8057061 100644
--- a/drivers/block/nd/core.c
+++ b/drivers/block/nd/core.c
@@ -192,7 +192,7 @@ static const struct attribute_group *nd_bus_attribute_groups[] = {
};

static void *nd_bus_new(struct device *parent,
- struct nfit_bus_descriptor *nfit_desc)
+ struct nfit_bus_descriptor *nfit_desc, struct module *module)
{
struct nd_bus *nd_bus = kzalloc(sizeof(*nd_bus), GFP_KERNEL);
int rc;
@@ -212,6 +212,7 @@ static void *nd_bus_new(struct device *parent,
return NULL;
}
nd_bus->nfit_desc = nfit_desc;
+ nd_bus->module = module;
nd_bus->dev.parent = parent;
nd_bus->dev.release = nd_bus_release;
nd_bus->dev.groups = nd_bus_attribute_groups;
@@ -595,15 +596,16 @@ static struct nd_bus *nd_bus_probe(struct nd_bus *nd_bus)

}

-struct nd_bus *nfit_bus_register(struct device *parent,
- struct nfit_bus_descriptor *nfit_desc)
+struct nd_bus *__nfit_bus_register(struct device *parent,
+ struct nfit_bus_descriptor *nfit_desc,
+ struct module *module)
{
static DEFINE_MUTEX(mutex);
struct nd_bus *nd_bus;

/* enforce single bus at a time registration */
mutex_lock(&mutex);
- nd_bus = nd_bus_new(parent, nfit_desc);
+ nd_bus = nd_bus_new(parent, nfit_desc, module);
nd_bus = nd_bus_probe(nd_bus);
mutex_unlock(&mutex);

@@ -612,7 +614,7 @@ struct nd_bus *nfit_bus_register(struct device *parent,

return nd_bus;
}
-EXPORT_SYMBOL(nfit_bus_register);
+EXPORT_SYMBOL(__nfit_bus_register);

void nfit_bus_unregister(struct nd_bus *nd_bus)
{
@@ -649,7 +651,12 @@ static __init int nd_core_init(void)
rc = nd_dimm_init();
if (rc)
goto err_dimm;
+ rc = nd_region_init();
+ if (rc)
+ goto err_region;
return 0;
+ err_region:
+ nd_dimm_exit();
err_dimm:
nd_bus_exit();
return rc;
@@ -659,6 +666,7 @@ static __init int nd_core_init(void)
static __exit void nd_core_exit(void)
{
WARN_ON(!list_empty(&nd_bus_list));
+ nd_region_exit();
nd_dimm_exit();
nd_bus_exit();
}
diff --git a/drivers/block/nd/dimm.c b/drivers/block/nd/dimm.c
index fec7229afb58..7e043c0c1bf5 100644
--- a/drivers/block/nd/dimm.c
+++ b/drivers/block/nd/dimm.c
@@ -95,7 +95,7 @@ int __init nd_dimm_init(void)
return nd_driver_register(&nd_dimm_driver);
}

-void __exit nd_dimm_exit(void)
+void nd_dimm_exit(void)
{
driver_unregister(&nd_dimm_driver.drv);
}
diff --git a/drivers/block/nd/namespace_devs.c b/drivers/block/nd/namespace_devs.c
new file mode 100644
index 000000000000..6861327f4245
--- /dev/null
+++ b/drivers/block/nd/namespace_devs.c
@@ -0,0 +1,111 @@
+/*
+ * Copyright(c) 2013-2015 Intel Corporation. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of version 2 of the GNU General Public License as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
+ * General Public License for more details.
+ */
+#include <linux/module.h>
+#include <linux/device.h>
+#include <linux/slab.h>
+#include <linux/nd.h>
+#include "nd.h"
+
+static void namespace_io_release(struct device *dev)
+{
+ struct nd_namespace_io *nsio = to_nd_namespace_io(dev);
+
+ kfree(nsio);
+}
+
+static struct device_type namespace_io_device_type = {
+ .name = "nd_namespace_io",
+ .release = namespace_io_release,
+};
+
+static ssize_t type_show(struct device *dev,
+ struct device_attribute *attr, char *buf)
+{
+ struct nd_region *nd_region = to_nd_region(dev->parent);
+
+ return sprintf(buf, "%d\n", nd_region_to_namespace_type(nd_region));
+}
+static DEVICE_ATTR_RO(type);
+
+static struct attribute *nd_namespace_attributes[] = {
+ &dev_attr_type.attr,
+ NULL,
+};
+
+static struct attribute_group nd_namespace_attribute_group = {
+ .attrs = nd_namespace_attributes,
+};
+
+static const struct attribute_group *nd_namespace_attribute_groups[] = {
+ &nd_device_attribute_group,
+ &nd_namespace_attribute_group,
+ NULL,
+};
+
+static struct device **create_namespace_io(struct nd_region *nd_region)
+{
+ struct nd_namespace_io *nsio;
+ struct device *dev, **devs;
+ struct resource *res;
+
+ nsio = kzalloc(sizeof(*nsio), GFP_KERNEL);
+ if (!nsio)
+ return NULL;
+
+ devs = kcalloc(2, sizeof(struct device *), GFP_KERNEL);
+ if (!devs) {
+ kfree(nsio);
+ return NULL;
+ }
+
+ dev = &nsio->dev;
+ dev->type = &namespace_io_device_type;
+ res = &nsio->res;
+ res->name = dev_name(&nd_region->dev);
+ res->flags = IORESOURCE_MEM;
+ res->start = nd_region->ndr_start;
+ res->end = res->start + nd_region->ndr_size - 1;
+
+ devs[0] = dev;
+ return devs;
+}
+
+int nd_region_register_namespaces(struct nd_region *nd_region, int *err)
+{
+ struct device **devs = NULL;
+ int i;
+
+ *err = 0;
+ switch (nd_region_to_namespace_type(nd_region)) {
+ case ND_DEVICE_NAMESPACE_IO:
+ devs = create_namespace_io(nd_region);
+ break;
+ default:
+ break;
+ }
+
+ if (!devs)
+ return -ENODEV;
+
+ for (i = 0; devs[i]; i++) {
+ struct device *dev = devs[i];
+
+ dev_set_name(dev, "namespace%d.%d", nd_region->id, i);
+ dev->parent = &nd_region->dev;
+ dev->groups = nd_namespace_attribute_groups;
+ nd_device_register(dev);
+ }
+ kfree(devs);
+
+ return i;
+}
diff --git a/drivers/block/nd/nd-private.h b/drivers/block/nd/nd-private.h
index d254ff688ad6..db68e013b9d0 100644
--- a/drivers/block/nd/nd-private.h
+++ b/drivers/block/nd/nd-private.h
@@ -33,6 +33,7 @@ enum {
struct nd_bus {
struct nfit_bus_descriptor *nfit_desc;
struct radix_tree_root dimm_radix;
+ struct module *module;
struct list_head memdevs;
struct list_head dimms;
struct list_head spas;
@@ -89,6 +90,8 @@ const char *spa_type_name(u16 type);
int nfit_spa_type(struct nfit_spa __iomem *nfit_spa);
struct nd_dimm *nd_dimm_by_handle(struct nd_bus *nd_bus, u32 nfit_handle);
bool is_nd_dimm(struct device *dev);
+bool is_nd_blk(struct device *dev);
+bool is_nd_pmem(struct device *dev);
struct nd_bus *to_nd_bus(struct device *dev);
struct nd_dimm *to_nd_dimm(struct device *dev);
struct nd_bus *walk_to_nd_bus(struct device *nd_dev);
@@ -97,11 +100,12 @@ int __init nd_bus_init(void);
void nd_bus_exit(void);
void nd_dimm_delete(struct nd_dimm *nd_dimm);
int __init nd_dimm_init(void);
-void __exit nd_dimm_exit(void);
+int __init nd_region_init(void);
+void nd_dimm_exit(void);
+int nd_region_exit(void);
int nd_bus_create_ndctl(struct nd_bus *nd_bus);
void nd_bus_destroy_ndctl(struct nd_bus *nd_bus);
int nd_bus_register_dimms(struct nd_bus *nd_bus);
int nd_bus_register_regions(struct nd_bus *nd_bus);
int nd_match_dimm(struct device *dev, void *data);
-bool is_nd_dimm(struct device *dev);
#endif /* __ND_PRIVATE_H__ */
diff --git a/drivers/block/nd/nd.h b/drivers/block/nd/nd.h
index 13eba9bd74c7..4ac7ff2af4c8 100644
--- a/drivers/block/nd/nd.h
+++ b/drivers/block/nd/nd.h
@@ -22,6 +22,11 @@ struct nd_dimm_drvdata {
void *data;
};

+struct nd_region_namespaces {
+ int count;
+ int active;
+};
+
struct nd_mapping {
struct nd_dimm *nd_dimm;
u64 start;
@@ -56,4 +61,6 @@ int nd_dimm_init_nsarea(struct nd_dimm_drvdata *ndd);
int nd_dimm_init_config_data(struct nd_dimm_drvdata *ndd);
int nd_dimm_firmware_status(struct device *dev);
struct nd_region *to_nd_region(struct device *dev);
+int nd_region_to_namespace_type(struct nd_region *nd_region);
+int nd_region_register_namespaces(struct nd_region *nd_region, int *err);
#endif /* __ND_H__ */
diff --git a/drivers/block/nd/nfit.h b/drivers/block/nd/nfit.h
index 75b480f6ff03..d8d0308f55a5 100644
--- a/drivers/block/nd/nfit.h
+++ b/drivers/block/nd/nfit.h
@@ -229,7 +229,10 @@ struct nfit_bus_descriptor {
};

struct nd_bus;
-struct nd_bus *nfit_bus_register(struct device *parent,
- struct nfit_bus_descriptor *nfit_desc);
+#define nfit_bus_register(parent, desc) \
+ __nfit_bus_register(parent, desc, THIS_MODULE)
+struct nd_bus *__nfit_bus_register(struct device *parent,
+ struct nfit_bus_descriptor *nfit_desc,
+ struct module *module);
void nfit_bus_unregister(struct nd_bus *nd_bus);
#endif /* __NFIT_H__ */
diff --git a/drivers/block/nd/region.c b/drivers/block/nd/region.c
new file mode 100644
index 000000000000..29019a65808e
--- /dev/null
+++ b/drivers/block/nd/region.c
@@ -0,0 +1,88 @@
+/*
+ * Copyright(c) 2013-2015 Intel Corporation. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of version 2 of the GNU General Public License as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
+ * General Public License for more details.
+ */
+#include <linux/module.h>
+#include <linux/device.h>
+#include <linux/nd.h>
+#include "nd.h"
+
+static int nd_region_probe(struct device *dev)
+{
+ int err;
+ struct nd_region_namespaces *num_ns;
+ struct nd_region *nd_region = to_nd_region(dev);
+ int 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 (err == 0)
+ return 0;
+
+ if (rc == err)
+ return -ENODEV;
+
+ /*
+ * 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 int child_unregister(struct device *dev, void *data)
+{
+ nd_device_unregister(dev, ND_SYNC);
+ return 0;
+}
+
+static int nd_region_remove(struct device *dev)
+{
+ device_for_each_child(dev, NULL, child_unregister);
+ return 0;
+}
+
+static struct nd_device_driver nd_region_driver = {
+ .probe = nd_region_probe,
+ .remove = nd_region_remove,
+ .drv = {
+ .name = "nd_region",
+ },
+ .type = ND_DRIVER_REGION_BLOCK | ND_DRIVER_REGION_PMEM,
+};
+
+int __init nd_region_init(void)
+{
+ return nd_driver_register(&nd_region_driver);
+}
+
+void __exit nd_region_exit(void)
+{
+ driver_unregister(&nd_region_driver.drv);
+}
+
+MODULE_ALIAS_ND_DEVICE(ND_DEVICE_REGION_PMEM);
+MODULE_ALIAS_ND_DEVICE(ND_DEVICE_REGION_BLOCK);
diff --git a/drivers/block/nd/region_devs.c b/drivers/block/nd/region_devs.c
index f474c32d6dad..03b192368e1a 100644
--- a/drivers/block/nd/region_devs.c
+++ b/drivers/block/nd/region_devs.c
@@ -50,11 +50,16 @@ static struct device_type nd_volatile_device_type = {
.release = nd_region_release,
};

-static bool is_nd_pmem(struct device *dev)
+bool is_nd_pmem(struct device *dev)
{
return dev ? dev->type == &nd_pmem_device_type : false;
}

+bool is_nd_blk(struct device *dev)
+{
+ return dev ? dev->type == &nd_block_device_type : false;
+}
+
struct nd_region *to_nd_region(struct device *dev)
{
struct nd_region *nd_region = container_of(dev, struct nd_region, dev);
@@ -63,6 +68,28 @@ struct nd_region *to_nd_region(struct device *dev)
return nd_region;
}

+/**
+ * nd_region_to_namespace_type() - region to an integer namespace type
+ * @nd_region: region-device to interrogate
+ *
+ * This is the 'nstype' attribute of a region as well, an input to the
+ * MODALIAS for namespace devices, and bit number for a nd_bus to match
+ * namespace devices with namespace drivers.
+ */
+int nd_region_to_namespace_type(struct nd_region *nd_region)
+{
+ if (is_nd_pmem(&nd_region->dev)) {
+ if (nd_region->ndr_mappings)
+ return ND_DEVICE_NAMESPACE_PMEM;
+ else
+ return ND_DEVICE_NAMESPACE_IO;
+ } else if (is_nd_blk(&nd_region->dev)) {
+ return ND_DEVICE_NAMESPACE_BLOCK;
+ }
+
+ return 0;
+}
+
static ssize_t size_show(struct device *dev,
struct device_attribute *attr, char *buf)
{
@@ -90,9 +117,44 @@ static ssize_t mappings_show(struct device *dev,
}
static DEVICE_ATTR_RO(mappings);

+static ssize_t spa_index_show(struct device *dev,
+ struct device_attribute *attr, char *buf)
+{
+ struct nd_region *nd_region = to_nd_region(dev);
+ struct nd_spa *nd_spa = nd_region->nd_spa;
+ u16 spa_index = readw(&nd_spa->nfit_spa->spa_index);
+
+ return sprintf(buf, "%d\n", spa_index);
+}
+static DEVICE_ATTR_RO(spa_index);
+
+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_namespace_type(nd_region));
+}
+static DEVICE_ATTR_RO(nstype);
+
+static ssize_t init_namespaces_show(struct device *dev,
+ struct device_attribute *attr, char *buf)
+{
+ struct nd_region_namespaces *num_ns = dev_get_drvdata(dev);
+
+ if (!num_ns)
+ return -ENXIO;
+
+ return sprintf(buf, "%d/%d\n", num_ns->active, num_ns->count);
+}
+static DEVICE_ATTR_RO(init_namespaces);
+
static struct attribute *nd_region_attributes[] = {
&dev_attr_size.attr,
+ &dev_attr_nstype.attr,
&dev_attr_mappings.attr,
+ &dev_attr_spa_index.attr,
+ &dev_attr_init_namespaces.attr,
NULL,
};

@@ -256,6 +318,7 @@ static struct attribute_group nd_mapping_attribute_group = {

static const struct attribute_group *nd_region_attribute_groups[] = {
&nd_region_attribute_group,
+ &nd_device_attribute_group,
&nd_mapping_attribute_group,
NULL,
};
diff --git a/include/linux/nd.h b/include/linux/nd.h
index e074f67e53a3..da70e9962197 100644
--- a/include/linux/nd.h
+++ b/include/linux/nd.h
@@ -26,6 +26,16 @@ static inline struct nd_device_driver *to_nd_device_driver(
struct device_driver *drv)
{
return container_of(drv, struct nd_device_driver, drv);
+};
+
+struct nd_namespace_io {
+ struct device dev;
+ struct resource res;
+};
+
+static inline struct nd_namespace_io *to_nd_namespace_io(struct device *dev)
+{
+ return container_of(dev, struct nd_namespace_io, dev);
}

#define MODULE_ALIAS_ND_DEVICE(type) \
diff --git a/include/uapi/linux/ndctl.h b/include/uapi/linux/ndctl.h
index f11a9f706bbf..0ccc0f2e5765 100644
--- a/include/uapi/linux/ndctl.h
+++ b/include/uapi/linux/ndctl.h
@@ -177,8 +177,18 @@ static inline const char *nfit_dimm_cmd_name(unsigned cmd)


#define ND_DEVICE_DIMM 1 /* nd_dimm: container for "config data" */
+#define ND_DEVICE_REGION_PMEM 2 /* nd_region: (parent of pmem namespaces) */
+#define ND_DEVICE_REGION_BLOCK 3 /* nd_region: (parent of block namespaces) */
+#define ND_DEVICE_NAMESPACE_IO 4 /* legacy persistent memory */
+#define ND_DEVICE_NAMESPACE_PMEM 5 /* persistent memory namespace (may alias) */
+#define ND_DEVICE_NAMESPACE_BLOCK 6 /* block-data-window namespace (may alias) */

enum nd_driver_flags {
ND_DRIVER_DIMM = 1 << ND_DEVICE_DIMM,
+ ND_DRIVER_REGION_PMEM = 1 << ND_DEVICE_REGION_PMEM,
+ ND_DRIVER_REGION_BLOCK = 1 << ND_DEVICE_REGION_BLOCK,
+ ND_DRIVER_NAMESPACE_IO = 1 << ND_DEVICE_NAMESPACE_IO,
+ ND_DRIVER_NAMESPACE_PMEM = 1 << ND_DEVICE_NAMESPACE_PMEM,
+ ND_DRIVER_NAMESPACE_BLOCK = 1 << ND_DEVICE_NAMESPACE_BLOCK,
};
#endif /* __NDCTL_H__ */

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/