libnvdimm, dax: introduce device-dax infrastructure

Device DAX is the device-centric analogue of Filesystem DAX
(CONFIG_FS_DAX).  It allows persistent memory ranges to be allocated and
mapped without need of an intervening file system.  This initial
infrastructure arranges for a libnvdimm pfn-device to be represented as
a different device-type so that it can be attached to a driver other
than the pmem driver.

Signed-off-by: Dan Williams <[email protected]>

Author: djbw

drivers/nvdimm/Kconfig

@@ -88,4 +88,17 @@ config NVDIMM_PFN
 
 	  Select Y if unsure
 
+config NVDIMM_DAX
+	bool "NVDIMM DAX: Raw access to persistent memory"
+	default LIBNVDIMM
+	depends on NVDIMM_PFN
+	help
+	  Support raw device dax access to a persistent memory
+	  namespace.  For environments that want to hard partition
+	  peristent memory, this capability provides a mechanism to
+	  sub-divide a namespace into character devices that can only be
+	  accessed via DAX (mmap(2)).
+
+	  Select Y if unsure
+
 endif

drivers/nvdimm/Makefile

@@ -23,3 +23,4 @@ libnvdimm-y += label.o
 libnvdimm-$(CONFIG_ND_CLAIM) += claim.o
 libnvdimm-$(CONFIG_BTT) += btt_devs.o
 libnvdimm-$(CONFIG_NVDIMM_PFN) += pfn_devs.o
+libnvdimm-$(CONFIG_NVDIMM_DAX) += dax_devs.o

drivers/nvdimm/bus.c

@@ -40,6 +40,8 @@ static int to_nd_device_type(struct device *dev)
 		return ND_DEVICE_REGION_PMEM;
 	else if (is_nd_blk(dev))
 		return ND_DEVICE_REGION_BLK;
+	else if (is_nd_dax(dev))
+		return ND_DEVICE_DAX_PMEM;
 	else if (is_nd_pmem(dev->parent) || is_nd_blk(dev->parent))
 		return nd_region_to_nstype(to_nd_region(dev->parent));
 
@@ -246,6 +248,8 @@ static void nd_async_device_unregister(void *d, async_cookie_t cookie)
 
 void __nd_device_register(struct device *dev)
 {
+	if (!dev)
+		return;
 	dev->bus = &nvdimm_bus_type;
 	get_device(dev);
 	async_schedule_domain(nd_async_device_register, dev,

drivers/nvdimm/claim.c

@@ -85,6 +85,8 @@ static bool is_idle(struct device *dev, struct nd_namespace_common *ndns)
 		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;

drivers/nvdimm/dax_devs.c

@@ -0,0 +1,99 @@
+/*
+ * Copyright(c) 2013-2016 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/device.h>
+#include <linux/sizes.h>
+#include <linux/slab.h>
+#include <linux/mm.h>
+#include "nd-core.h"
+#include "nd.h"
+
+static void nd_dax_release(struct device *dev)
+{
+	struct nd_region *nd_region = to_nd_region(dev->parent);
+	struct nd_dax *nd_dax = to_nd_dax(dev);
+	struct nd_pfn *nd_pfn = &nd_dax->nd_pfn;
+
+	dev_dbg(dev, "%s\n", __func__);
+	nd_detach_ndns(dev, &nd_pfn->ndns);
+	ida_simple_remove(&nd_region->dax_ida, nd_pfn->id);
+	kfree(nd_pfn->uuid);
+	kfree(nd_dax);
+}
+
+static struct device_type nd_dax_device_type = {
+	.name = "nd_dax",
+	.release = nd_dax_release,
+};
+
+bool is_nd_dax(struct device *dev)
+{
+	return dev ? dev->type == &nd_dax_device_type : false;
+}
+EXPORT_SYMBOL(is_nd_dax);
+
+struct nd_dax *to_nd_dax(struct device *dev)
+{
+	struct nd_dax *nd_dax = container_of(dev, struct nd_dax, nd_pfn.dev);
+
+	WARN_ON(!is_nd_dax(dev));
+	return nd_dax;
+}
+EXPORT_SYMBOL(to_nd_dax);
+
+static const struct attribute_group *nd_dax_attribute_groups[] = {
+	&nd_pfn_attribute_group,
+	&nd_device_attribute_group,
+	&nd_numa_attribute_group,
+	NULL,
+};
+
+static struct nd_dax *nd_dax_alloc(struct nd_region *nd_region)
+{
+	struct nd_pfn *nd_pfn;
+	struct nd_dax *nd_dax;
+	struct device *dev;
+
+	nd_dax = kzalloc(sizeof(*nd_dax), GFP_KERNEL);
+	if (!nd_dax)
+		return NULL;
+
+	nd_pfn = &nd_dax->nd_pfn;
+	nd_pfn->id = ida_simple_get(&nd_region->dax_ida, 0, 0, GFP_KERNEL);
+	if (nd_pfn->id < 0) {
+		kfree(nd_dax);
+		return NULL;
+	}
+
+	dev = &nd_pfn->dev;
+	dev_set_name(dev, "dax%d.%d", nd_region->id, nd_pfn->id);
+	dev->groups = nd_dax_attribute_groups;
+	dev->type = &nd_dax_device_type;
+	dev->parent = &nd_region->dev;
+
+	return nd_dax;
+}
+
+struct device *nd_dax_create(struct nd_region *nd_region)
+{
+	struct device *dev = NULL;
+	struct nd_dax *nd_dax;
+
+	if (!is_nd_pmem(&nd_region->dev))
+		return NULL;
+
+	nd_dax = nd_dax_alloc(nd_region);
+	if (nd_dax)
+		dev = nd_pfn_devinit(&nd_dax->nd_pfn, NULL);
+	__nd_device_register(dev);
+	return dev;
+}

drivers/nvdimm/namespace_devs.c

@@ -1288,6 +1288,8 @@ static ssize_t mode_show(struct device *dev,
 		mode = "safe";
 	else if (claim && is_nd_pfn(claim))
 		mode = "memory";
+	else if (claim && is_nd_dax(claim))
+		mode = "dax";
 	else if (!claim && pmem_should_map_pages(dev))
 		mode = "memory";
 	else
@@ -1379,14 +1381,17 @@ struct nd_namespace_common *nvdimm_namespace_common_probe(struct device *dev)
 {
 	struct nd_btt *nd_btt = is_nd_btt(dev) ? to_nd_btt(dev) : NULL;
 	struct nd_pfn *nd_pfn = is_nd_pfn(dev) ? to_nd_pfn(dev) : NULL;
+	struct nd_dax *nd_dax = is_nd_dax(dev) ? to_nd_dax(dev) : NULL;
 	struct nd_namespace_common *ndns = NULL;
 	resource_size_t size;
 
-	if (nd_btt || nd_pfn) {
+	if (nd_btt || nd_pfn || nd_dax) {
 		if (nd_btt)
 			ndns = nd_btt->ndns;
 		else if (nd_pfn)
 			ndns = nd_pfn->ndns;
+		else if (nd_dax)
+			ndns = nd_dax->nd_pfn.ndns;
 
 		if (!ndns)
 			return ERR_PTR(-ENODEV);
@@ -1779,6 +1784,18 @@ void nd_region_create_blk_seed(struct nd_region *nd_region)
 		nd_device_register(nd_region->ns_seed);
 }
 
+void nd_region_create_dax_seed(struct nd_region *nd_region)
+{
+	WARN_ON(!is_nvdimm_bus_locked(&nd_region->dev));
+	nd_region->dax_seed = nd_dax_create(nd_region);
+	/*
+	 * Seed creation failures are not fatal, provisioning is simply
+	 * disabled until memory becomes available
+	 */
+	if (!nd_region->dax_seed)
+		dev_err(&nd_region->dev, "failed to create dax namespace\n");
+}
+
 void nd_region_create_pfn_seed(struct nd_region *nd_region)
 {
 	WARN_ON(!is_nvdimm_bus_locked(&nd_region->dev));

drivers/nvdimm/nd-core.h

@@ -54,6 +54,7 @@ struct nd_region;
 void nd_region_create_blk_seed(struct nd_region *nd_region);
 void nd_region_create_btt_seed(struct nd_region *nd_region);
 void nd_region_create_pfn_seed(struct nd_region *nd_region);
+void nd_region_create_dax_seed(struct nd_region *nd_region);
 void nd_region_disable(struct nvdimm_bus *nvdimm_bus, struct device *dev);
 int nvdimm_bus_create_ndctl(struct nvdimm_bus *nvdimm_bus);
 void nvdimm_bus_destroy_ndctl(struct nvdimm_bus *nvdimm_bus);

drivers/nvdimm/nd.h

@@ -101,10 +101,12 @@ struct nd_region {
 	struct ida ns_ida;
 	struct ida btt_ida;
 	struct ida pfn_ida;
+	struct ida dax_ida;
 	unsigned long flags;
 	struct device *ns_seed;
 	struct device *btt_seed;
 	struct device *pfn_seed;
+	struct device *dax_seed;
 	u16 ndr_mappings;
 	u64 ndr_size;
 	u64 ndr_start;
@@ -161,6 +163,10 @@ struct nd_pfn {
 	struct nd_namespace_common *ndns;
 };
 
+struct nd_dax {
+	struct nd_pfn nd_pfn;
+};
+
 enum nd_async_mode {
 	ND_SYNC,
 	ND_ASYNC,
@@ -224,7 +230,10 @@ struct nd_pfn *to_nd_pfn(struct device *dev);
 int nd_pfn_probe(struct device *dev, struct nd_namespace_common *ndns);
 bool is_nd_pfn(struct device *dev);
 struct device *nd_pfn_create(struct nd_region *nd_region);
+struct device *nd_pfn_devinit(struct nd_pfn *nd_pfn,
+		struct nd_namespace_common *ndns);
 int nd_pfn_validate(struct nd_pfn *nd_pfn);
+extern struct attribute_group nd_pfn_attribute_group;
 #else
 static inline int nd_pfn_probe(struct device *dev,
 		struct nd_namespace_common *ndns)
@@ -248,6 +257,22 @@ static inline int nd_pfn_validate(struct nd_pfn *nd_pfn)
 }
 #endif
 
+struct nd_dax *to_nd_dax(struct device *dev);
+#if IS_ENABLED(CONFIG_NVDIMM_DAX)
+bool is_nd_dax(struct device *dev);
+struct device *nd_dax_create(struct nd_region *nd_region);
+#else
+static inline bool is_nd_dax(struct device *dev)
+{
+	return false;
+}
+
+static inline struct device *nd_dax_create(struct nd_region *nd_region)
+{
+	return NULL;
+}
+#endif
+
 struct nd_region *to_nd_region(struct device *dev);
 int nd_region_to_nstype(struct nd_region *nd_region);
 int nd_region_register_namespaces(struct nd_region *nd_region, int *err);