libnvdimm: control (ioctl) messages for nvdimm_bus and nvdimm devices

Most discovery/configuration of the nvdimm-subsystem is done via sysfs
attributes.  However, some nvdimm_bus instances, particularly the
ACPI.NFIT bus, define a small set of messages that can be passed to the
platform.  For convenience we derive the initial libnvdimm-ioctl command
formats directly from the NFIT DSM Interface Example formats.

    ND_CMD_SMART: media health and diagnostics
    ND_CMD_GET_CONFIG_SIZE: size of the label space
    ND_CMD_GET_CONFIG_DATA: read label space
    ND_CMD_SET_CONFIG_DATA: write label space
    ND_CMD_VENDOR: vendor-specific command passthrough
    ND_CMD_ARS_CAP: report address-range-scrubbing capabilities
    ND_CMD_ARS_START: initiate scrubbing
    ND_CMD_ARS_STATUS: report on scrubbing state
    ND_CMD_SMART_THRESHOLD: configure alarm thresholds for smart events

If a platform later defines different commands than this set it is
straightforward to extend support to those formats.

Most of the commands target a specific dimm.  However, the
address-range-scrubbing commands target the bus.  The 'commands'
attribute in sysfs of an nvdimm_bus, or nvdimm, enumerate the supported
commands for that object.

Cc: <linux-acpi@vger.kernel.org>
Cc: Robert Moore <robert.moore@intel.com>
Cc: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Reported-by: Nicholas Moulin <nicholas.w.moulin@linux.intel.com>
Acked-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Dan Williams <dan.j.williams@intel.com>

drivers/nvdimm/bus.c

@@ -11,14 +11,18 @@
  * General Public License for more details.
  */
 #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+#include <linux/vmalloc.h>
 #include <linux/uaccess.h>
 #include <linux/fcntl.h>
 #include <linux/async.h>
+#include <linux/ndctl.h>
 #include <linux/slab.h>
 #include <linux/fs.h>
 #include <linux/io.h>
+#include <linux/mm.h>
 #include "nd-core.h"
 
+int nvdimm_major;
 static int nvdimm_bus_major;
 static struct class *nd_class;
 
@@ -47,19 +51,325 @@ void nvdimm_bus_destroy_ndctl(struct nvdimm_bus *nvdimm_bus)
 	device_destroy(nd_class, MKDEV(nvdimm_bus_major, nvdimm_bus->id));
 }
 
+static const struct nd_cmd_desc __nd_cmd_dimm_descs[] = {
+	[ND_CMD_IMPLEMENTED] = { },
+	[ND_CMD_SMART] = {
+		.out_num = 2,
+		.out_sizes = { 4, 8, },
+	},
+	[ND_CMD_SMART_THRESHOLD] = {
+		.out_num = 2,
+		.out_sizes = { 4, 8, },
+	},
+	[ND_CMD_DIMM_FLAGS] = {
+		.out_num = 2,
+		.out_sizes = { 4, 4 },
+	},
+	[ND_CMD_GET_CONFIG_SIZE] = {
+		.out_num = 3,
+		.out_sizes = { 4, 4, 4, },
+	},
+	[ND_CMD_GET_CONFIG_DATA] = {
+		.in_num = 2,
+		.in_sizes = { 4, 4, },
+		.out_num = 2,
+		.out_sizes = { 4, UINT_MAX, },
+	},
+	[ND_CMD_SET_CONFIG_DATA] = {
+		.in_num = 3,
+		.in_sizes = { 4, 4, UINT_MAX, },
+		.out_num = 1,
+		.out_sizes = { 4, },
+	},
+	[ND_CMD_VENDOR] = {
+		.in_num = 3,
+		.in_sizes = { 4, 4, UINT_MAX, },
+		.out_num = 3,
+		.out_sizes = { 4, 4, UINT_MAX, },
+	},
+};
+
+const struct nd_cmd_desc *nd_cmd_dimm_desc(int cmd)
+{
+	if (cmd < ARRAY_SIZE(__nd_cmd_dimm_descs))
+		return &__nd_cmd_dimm_descs[cmd];
+	return NULL;
+}
+EXPORT_SYMBOL_GPL(nd_cmd_dimm_desc);
+
+static const struct nd_cmd_desc __nd_cmd_bus_descs[] = {
+	[ND_CMD_IMPLEMENTED] = { },
+	[ND_CMD_ARS_CAP] = {
+		.in_num = 2,
+		.in_sizes = { 8, 8, },
+		.out_num = 2,
+		.out_sizes = { 4, 4, },
+	},
+	[ND_CMD_ARS_START] = {
+		.in_num = 4,
+		.in_sizes = { 8, 8, 2, 6, },
+		.out_num = 1,
+		.out_sizes = { 4, },
+	},
+	[ND_CMD_ARS_STATUS] = {
+		.out_num = 2,
+		.out_sizes = { 4, UINT_MAX, },
+	},
+};
+
+const struct nd_cmd_desc *nd_cmd_bus_desc(int cmd)
+{
+	if (cmd < ARRAY_SIZE(__nd_cmd_bus_descs))
+		return &__nd_cmd_bus_descs[cmd];
+	return NULL;
+}
+EXPORT_SYMBOL_GPL(nd_cmd_bus_desc);
+
+u32 nd_cmd_in_size(struct nvdimm *nvdimm, int cmd,
+		const struct nd_cmd_desc *desc, int idx, void *buf)
+{
+	if (idx >= desc->in_num)
+		return UINT_MAX;
+
+	if (desc->in_sizes[idx] < UINT_MAX)
+		return desc->in_sizes[idx];
+
+	if (nvdimm && cmd == ND_CMD_SET_CONFIG_DATA && idx == 2) {
+		struct nd_cmd_set_config_hdr *hdr = buf;
+
+		return hdr->in_length;
+	} else if (nvdimm && cmd == ND_CMD_VENDOR && idx == 2) {
+		struct nd_cmd_vendor_hdr *hdr = buf;
+
+		return hdr->in_length;
+	}
+
+	return UINT_MAX;
+}
+EXPORT_SYMBOL_GPL(nd_cmd_in_size);
+
+u32 nd_cmd_out_size(struct nvdimm *nvdimm, int cmd,
+		const struct nd_cmd_desc *desc, int idx, const u32 *in_field,
+		const u32 *out_field)
+{
+	if (idx >= desc->out_num)
+		return UINT_MAX;
+
+	if (desc->out_sizes[idx] < UINT_MAX)
+		return desc->out_sizes[idx];
+
+	if (nvdimm && cmd == ND_CMD_GET_CONFIG_DATA && idx == 1)
+		return in_field[1];
+	else if (nvdimm && cmd == ND_CMD_VENDOR && idx == 2)
+		return out_field[1];
+	else if (!nvdimm && cmd == ND_CMD_ARS_STATUS && idx == 1)
+		return ND_CMD_ARS_STATUS_MAX;
+
+	return UINT_MAX;
+}
+EXPORT_SYMBOL_GPL(nd_cmd_out_size);
+
+static int __nd_ioctl(struct nvdimm_bus *nvdimm_bus, struct nvdimm *nvdimm,
+		int read_only, unsigned int ioctl_cmd, unsigned long arg)
+{
+	struct nvdimm_bus_descriptor *nd_desc = nvdimm_bus->nd_desc;
+	size_t buf_len = 0, in_len = 0, out_len = 0;
+	static char out_env[ND_CMD_MAX_ENVELOPE];
+	static char in_env[ND_CMD_MAX_ENVELOPE];
+	const struct nd_cmd_desc *desc = NULL;
+	unsigned int cmd = _IOC_NR(ioctl_cmd);
+	void __user *p = (void __user *) arg;
+	struct device *dev = &nvdimm_bus->dev;
+	const char *cmd_name, *dimm_name;
+	unsigned long dsm_mask;
+	void *buf;
+	int rc, i;
+
+	if (nvdimm) {
+		desc = nd_cmd_dimm_desc(cmd);
+		cmd_name = nvdimm_cmd_name(cmd);
+		dsm_mask = nvdimm->dsm_mask ? *(nvdimm->dsm_mask) : 0;
+		dimm_name = dev_name(&nvdimm->dev);
+	} else {
+		desc = nd_cmd_bus_desc(cmd);
+		cmd_name = nvdimm_bus_cmd_name(cmd);
+		dsm_mask = nd_desc->dsm_mask;
+		dimm_name = "bus";
+	}
+
+	if (!desc || (desc->out_num + desc->in_num == 0) ||
+			!test_bit(cmd, &dsm_mask))
+		return -ENOTTY;
+
+	/* fail write commands (when read-only) */
+	if (read_only)
+		switch (ioctl_cmd) {
+		case ND_IOCTL_VENDOR:
+		case ND_IOCTL_SET_CONFIG_DATA:
+		case ND_IOCTL_ARS_START:
+			dev_dbg(&nvdimm_bus->dev, "'%s' command while read-only.\n",
+					nvdimm ? nvdimm_cmd_name(cmd)
+					: nvdimm_bus_cmd_name(cmd));
+			return -EPERM;
+		default:
+			break;
+		}
+
+	/* process an input envelope */
+	for (i = 0; i < desc->in_num; i++) {
+		u32 in_size, copy;
+
+		in_size = nd_cmd_in_size(nvdimm, cmd, desc, i, in_env);
+		if (in_size == UINT_MAX) {
+			dev_err(dev, "%s:%s unknown input size cmd: %s field: %d\n",
+					__func__, dimm_name, cmd_name, i);
+			return -ENXIO;
+		}
+		if (!access_ok(VERIFY_READ, p + in_len, in_size))
+			return -EFAULT;
+		if (in_len < sizeof(in_env))
+			copy = min_t(u32, sizeof(in_env) - in_len, in_size);
+		else
+			copy = 0;
+		if (copy && copy_from_user(&in_env[in_len], p + in_len, copy))
+			return -EFAULT;
+		in_len += in_size;
+	}
+
+	/* process an output envelope */
+	for (i = 0; i < desc->out_num; i++) {
+		u32 out_size = nd_cmd_out_size(nvdimm, cmd, desc, i,
+				(u32 *) in_env, (u32 *) out_env);
+		u32 copy;
+
+		if (out_size == UINT_MAX) {
+			dev_dbg(dev, "%s:%s unknown output size cmd: %s field: %d\n",
+					__func__, dimm_name, cmd_name, i);
+			return -EFAULT;
+		}
+		if (!access_ok(VERIFY_WRITE, p + in_len + out_len, out_size))
+			return -EFAULT;
+		if (out_len < sizeof(out_env))
+			copy = min_t(u32, sizeof(out_env) - out_len, out_size);
+		else
+			copy = 0;
+		if (copy && copy_from_user(&out_env[out_len],
+					p + in_len + out_len, copy))
+			return -EFAULT;
+		out_len += out_size;
+	}
+
+	buf_len = out_len + in_len;
+	if (!access_ok(VERIFY_WRITE, p, sizeof(buf_len)))
+		return -EFAULT;
+
+	if (buf_len > ND_IOCTL_MAX_BUFLEN) {
+		dev_dbg(dev, "%s:%s cmd: %s buf_len: %zu > %d\n", __func__,
+				dimm_name, cmd_name, buf_len,
+				ND_IOCTL_MAX_BUFLEN);
+		return -EINVAL;
+	}
+
+	buf = vmalloc(buf_len);
+	if (!buf)
+		return -ENOMEM;
+
+	if (copy_from_user(buf, p, buf_len)) {
+		rc = -EFAULT;
+		goto out;
+	}
+
+	rc = nd_desc->ndctl(nd_desc, nvdimm, cmd, buf, buf_len);
+	if (rc < 0)
+		goto out;
+	if (copy_to_user(p, buf, buf_len))
+		rc = -EFAULT;
+ out:
+	vfree(buf);
+	return rc;
+}
+
 static long nd_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
 {
-	return -ENXIO;
+	long id = (long) file->private_data;
+	int rc = -ENXIO, read_only;
+	struct nvdimm_bus *nvdimm_bus;
+
+	read_only = (O_RDWR != (file->f_flags & O_ACCMODE));
+	mutex_lock(&nvdimm_bus_list_mutex);
+	list_for_each_entry(nvdimm_bus, &nvdimm_bus_list, list) {
+		if (nvdimm_bus->id == id) {
+			rc = __nd_ioctl(nvdimm_bus, NULL, read_only, cmd, arg);
+			break;
+		}
+	}
+	mutex_unlock(&nvdimm_bus_list_mutex);
+
+	return rc;
+}
+
+static int match_dimm(struct device *dev, void *data)
+{
+	long id = (long) data;
+
+	if (is_nvdimm(dev)) {
+		struct nvdimm *nvdimm = to_nvdimm(dev);
+
+		return nvdimm->id == id;
+	}
+
+	return 0;
+}
+
+static long nvdimm_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
+{
+	int rc = -ENXIO, read_only;
+	struct nvdimm_bus *nvdimm_bus;
+
+	read_only = (O_RDWR != (file->f_flags & O_ACCMODE));
+	mutex_lock(&nvdimm_bus_list_mutex);
+	list_for_each_entry(nvdimm_bus, &nvdimm_bus_list, list) {
+		struct device *dev = device_find_child(&nvdimm_bus->dev,
+				file->private_data, match_dimm);
+		struct nvdimm *nvdimm;
+
+		if (!dev)
+			continue;
+
+		nvdimm = to_nvdimm(dev);
+		rc = __nd_ioctl(nvdimm_bus, nvdimm, read_only, cmd, arg);
+		put_device(dev);
+		break;
+	}
+	mutex_unlock(&nvdimm_bus_list_mutex);
+
+	return rc;
+}
+
+static int nd_open(struct inode *inode, struct file *file)
+{
+	long minor = iminor(inode);
+
+	file->private_data = (void *) minor;
+	return 0;
 }
 
 static const struct file_operations nvdimm_bus_fops = {
 	.owner = THIS_MODULE,
-	.open = nonseekable_open,
+	.open = nd_open,
 	.unlocked_ioctl = nd_ioctl,
 	.compat_ioctl = nd_ioctl,
 	.llseek = noop_llseek,
 };
 
+static const struct file_operations nvdimm_fops = {
+	.owner = THIS_MODULE,
+	.open = nd_open,
+	.unlocked_ioctl = nvdimm_ioctl,
+	.compat_ioctl = nvdimm_ioctl,
+	.llseek = noop_llseek,
+};
+
 int __init nvdimm_bus_init(void)
 {
 	int rc;
@@ -70,9 +380,14 @@ int __init nvdimm_bus_init(void)
 
 	rc = register_chrdev(0, "ndctl", &nvdimm_bus_fops);
 	if (rc < 0)
-		goto err_chrdev;
+		goto err_bus_chrdev;
 	nvdimm_bus_major = rc;
 
+	rc = register_chrdev(0, "dimmctl", &nvdimm_fops);
+	if (rc < 0)
+		goto err_dimm_chrdev;
+	nvdimm_major = rc;
+
 	nd_class = class_create(THIS_MODULE, "nd");
 	if (IS_ERR(nd_class))
 		goto err_class;
@@ -80,8 +395,10 @@ int __init nvdimm_bus_init(void)
 	return 0;
 
  err_class:
+	unregister_chrdev(nvdimm_major, "dimmctl");
+ err_dimm_chrdev:
 	unregister_chrdev(nvdimm_bus_major, "ndctl");
- err_chrdev:
+ err_bus_chrdev:
 	bus_unregister(&nvdimm_bus_type);
 
 	return rc;
@@ -91,5 +408,6 @@ void __exit nvdimm_bus_exit(void)
 {
 	class_destroy(nd_class);
 	unregister_chrdev(nvdimm_bus_major, "ndctl");
+	unregister_chrdev(nvdimm_major, "dimmctl");
 	bus_unregister(&nvdimm_bus_type);
 }

drivers/nvdimm/core.c

@@ -14,6 +14,7 @@
 #include <linux/export.h>
 #include <linux/module.h>
 #include <linux/device.h>
+#include <linux/ndctl.h>
 #include <linux/mutex.h>
 #include <linux/slab.h>
 #include "nd-core.h"
@@ -61,6 +62,20 @@ struct nvdimm_bus *walk_to_nvdimm_bus(struct device *nd_dev)
 	return NULL;
 }
 
+static ssize_t commands_show(struct device *dev,
+		struct device_attribute *attr, char *buf)
+{
+	int cmd, len = 0;
+	struct nvdimm_bus *nvdimm_bus = to_nvdimm_bus(dev);
+	struct nvdimm_bus_descriptor *nd_desc = nvdimm_bus->nd_desc;
+
+	for_each_set_bit(cmd, &nd_desc->dsm_mask, BITS_PER_LONG)
+		len += sprintf(buf + len, "%s ", nvdimm_bus_cmd_name(cmd));
+	len += sprintf(buf + len, "\n");
+	return len;
+}
+static DEVICE_ATTR_RO(commands);
+
 static const char *nvdimm_bus_provider(struct nvdimm_bus *nvdimm_bus)
 {
 	struct nvdimm_bus_descriptor *nd_desc = nvdimm_bus->nd_desc;
@@ -84,6 +99,7 @@ static ssize_t provider_show(struct device *dev,
 static DEVICE_ATTR_RO(provider);
 
 static struct attribute *nvdimm_bus_attributes[] = {
+	&dev_attr_commands.attr,
 	&dev_attr_provider.attr,
 	NULL,
 };

drivers/nvdimm/dimm_devs.c

@@ -12,6 +12,7 @@
  */
 #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
 #include <linux/device.h>
+#include <linux/ndctl.h>
 #include <linux/slab.h>
 #include <linux/io.h>
 #include <linux/fs.h>
@@ -33,7 +34,7 @@ static struct device_type nvdimm_device_type = {
 	.release = nvdimm_release,
 };
 
-static bool is_nvdimm(struct device *dev)
+bool is_nvdimm(struct device *dev)
 {
 	return dev->type == &nvdimm_device_type;
 }
@@ -55,12 +56,41 @@ EXPORT_SYMBOL_GPL(nvdimm_name);
 
 void *nvdimm_provider_data(struct nvdimm *nvdimm)
 {
-	return nvdimm->provider_data;
+	if (nvdimm)
+		return nvdimm->provider_data;
+	return NULL;
 }
 EXPORT_SYMBOL_GPL(nvdimm_provider_data);
 
+static ssize_t commands_show(struct device *dev,
+		struct device_attribute *attr, char *buf)
+{
+	struct nvdimm *nvdimm = to_nvdimm(dev);
+	int cmd, len = 0;
+
+	if (!nvdimm->dsm_mask)
+		return sprintf(buf, "\n");
+
+	for_each_set_bit(cmd, nvdimm->dsm_mask, BITS_PER_LONG)
+		len += sprintf(buf + len, "%s ", nvdimm_cmd_name(cmd));
+	len += sprintf(buf + len, "\n");
+	return len;
+}
+static DEVICE_ATTR_RO(commands);
+
+static struct attribute *nvdimm_attributes[] = {
+	&dev_attr_commands.attr,
+	NULL,
+};
+
+struct attribute_group nvdimm_attribute_group = {
+	.attrs = nvdimm_attributes,
+};
+EXPORT_SYMBOL_GPL(nvdimm_attribute_group);
+
 struct nvdimm *nvdimm_create(struct nvdimm_bus *nvdimm_bus, void *provider_data,
-		const struct attribute_group **groups, unsigned long flags)
+		const struct attribute_group **groups, unsigned long flags,
+		unsigned long *dsm_mask)
 {
 	struct nvdimm *nvdimm = kzalloc(sizeof(*nvdimm), GFP_KERNEL);
 	struct device *dev;
@@ -75,12 +105,14 @@ struct nvdimm *nvdimm_create(struct nvdimm_bus *nvdimm_bus, void *provider_data,
 	}
 	nvdimm->provider_data = provider_data;
 	nvdimm->flags = flags;
+	nvdimm->dsm_mask = dsm_mask;
 
 	dev = &nvdimm->dev;
 	dev_set_name(dev, "nmem%d", nvdimm->id);
 	dev->parent = &nvdimm_bus->dev;
 	dev->type = &nvdimm_device_type;
 	dev->bus = &nvdimm_bus_type;
+	dev->devt = MKDEV(nvdimm_major, nvdimm->id);
 	dev->groups = groups;
 	if (device_register(dev) != 0) {
 		put_device(dev);

drivers/nvdimm/nd-core.h

@@ -18,6 +18,7 @@
 extern struct list_head nvdimm_bus_list;
 extern struct mutex nvdimm_bus_list_mutex;
 extern struct bus_type nvdimm_bus_type;
+extern int nvdimm_major;
 
 struct nvdimm_bus {
 	struct nvdimm_bus_descriptor *nd_desc;
@@ -29,10 +30,12 @@ struct nvdimm_bus {
 struct nvdimm {
 	unsigned long flags;
 	void *provider_data;
+	unsigned long *dsm_mask;
 	struct device dev;
 	int id;
 };
 
+bool is_nvdimm(struct device *dev);
 struct nvdimm_bus *walk_to_nvdimm_bus(struct device *nd_dev);
 int __init nvdimm_bus_init(void);
 void __exit nvdimm_bus_exit(void);