Merge tag 'libnvdimm-for-4.7' of git://git.kernel.org/pub/scm/linux/kernel/git/nvdimm/nvdimm

Pull libnvdimm updates from Dan Williams:
 "The bulk of this update was stabilized before the merge window and
  appeared in -next.  The "device dax" implementation was revised this
  week in response to review feedback, and to address failures detected
  by the recently expanded ndctl unit test suite.

  Not included in this pull request are two dax topic branches (dax
  error handling, and dax radix-tree locking).  These topics were
  deferred to get a few more days of -next integration testing, and to
  coordinate a branch baseline with Ted and the ext4 tree.  Vishal and
  Ross will send the error handling and locking topics respectively in
  the next few days.

  This branch has received a positive build result from the kbuild robot
  across 226 configs.

  Summary:

   - Device DAX for persistent memory: Device DAX is the device-centric
     analogue of Filesystem DAX (CONFIG_FS_DAX).  It allows memory
     ranges to be allocated and mapped without need of an intervening
     file system.  Device DAX is strict, precise and predictable.
     Specifically this interface:

      a) Guarantees fault granularity with respect to a given page size
         (pte, pmd, or pud) set at configuration time.

      b) Enforces deterministic behavior by being strict about what
         fault scenarios are supported.

     Persistent memory is the first target, but the mechanism is also
     targeted for exclusive allocations of performance/feature
     differentiated memory ranges.

   - Support for the HPE DSM (device specific method) command formats.
     This enables management of these first generation devices until a
     unified DSM specification materializes.

   - Further ACPI 6.1 compliance with support for the common dimm
     identifier format.

   - Various fixes and cleanups across the subsystem"

* tag 'libnvdimm-for-4.7' of git://git.kernel.org/pub/scm/linux/kernel/git/nvdimm/nvdimm: (40 commits)
  libnvdimm, dax: fix deletion
  libnvdimm, dax: fix alignment validation
  libnvdimm, dax: autodetect support
  libnvdimm: release ida resources
  Revert "block: enable dax for raw block devices"
  /dev/dax, core: file operations and dax-mmap
  /dev/dax, pmem: direct access to persistent memory
  libnvdimm: stop requiring a driver ->remove() method
  libnvdimm, dax: record the specified alignment of a dax-device instance
  libnvdimm, dax: reserve space to store labels for device-dax
  libnvdimm, dax: introduce device-dax infrastructure
  nfit: add sysfs dimm 'family' and 'dsm_mask' attributes
  tools/testing/nvdimm: ND_CMD_CALL support
  nfit: disable vendor specific commands
  nfit: export subsystem ids as attributes
  nfit: fix format interface code byte order per ACPI6.1
  nfit, libnvdimm: limited/whitelisted dimm command marshaling mechanism
  nfit, libnvdimm: clarify "commands" vs "_DSMs"
  libnvdimm: increase max envelope size for ioctl
  acpi/nfit: Add sysfs "id" for NVDIMM ID
  ...

block/ioctl.c

@@ -407,35 +407,6 @@ static inline int is_unrecognized_ioctl(int ret)
 		ret == -ENOIOCTLCMD;
 }
 
-#ifdef CONFIG_FS_DAX
-bool blkdev_dax_capable(struct block_device *bdev)
-{
-	struct gendisk *disk = bdev->bd_disk;
-
-	if (!disk->fops->direct_access)
-		return false;
-
-	/*
-	 * If the partition is not aligned on a page boundary, we can't
-	 * do dax I/O to it.
-	 */
-	if ((bdev->bd_part->start_sect % (PAGE_SIZE / 512))
-			|| (bdev->bd_part->nr_sects % (PAGE_SIZE / 512)))
-		return false;
-
-	/*
-	 * If the device has known bad blocks, force all I/O through the
-	 * driver / page cache.
-	 *
-	 * TODO: support finer grained dax error handling
-	 */
-	if (disk->bb && disk->bb->count)
-		return false;
-
-	return true;
-}
-#endif
-
 static int blkdev_flushbuf(struct block_device *bdev, fmode_t mode,
 		unsigned cmd, unsigned long arg)
 {
@@ -598,9 +569,6 @@ int blkdev_ioctl(struct block_device *bdev, fmode_t mode, unsigned cmd,
 	case BLKTRACESETUP:
 	case BLKTRACETEARDOWN:
 		return blk_trace_ioctl(bdev, cmd, argp);
-	case BLKDAXGET:
-		return put_int(arg, !!(bdev->bd_inode->i_flags & S_DAX));
-		break;
 	case IOC_PR_REGISTER:
 		return blkdev_pr_register(bdev, argp);
 	case IOC_PR_RESERVE:

drivers/Kconfig

@@ -192,6 +192,8 @@ source "drivers/android/Kconfig"
 
 source "drivers/nvdimm/Kconfig"
 
+source "drivers/dax/Kconfig"
+
 source "drivers/nvmem/Kconfig"
 
 source "drivers/hwtracing/stm/Kconfig"

drivers/Makefile

@@ -66,6 +66,7 @@ obj-$(CONFIG_PARPORT)		+= parport/
 obj-$(CONFIG_NVM)		+= lightnvm/
 obj-y				+= base/ block/ misc/ mfd/ nfc/
 obj-$(CONFIG_LIBNVDIMM)		+= nvdimm/
+obj-$(CONFIG_DEV_DAX)		+= dax/
 obj-$(CONFIG_DMA_SHARED_BUFFER) += dma-buf/
 obj-$(CONFIG_NUBUS)		+= nubus/
 obj-y				+= macintosh/

drivers/acpi/nfit.c

@@ -45,6 +45,11 @@ module_param(scrub_overflow_abort, uint, S_IRUGO|S_IWUSR);
 MODULE_PARM_DESC(scrub_overflow_abort,
 		"Number of times we overflow ARS results before abort");
 
+static bool disable_vendor_specific;
+module_param(disable_vendor_specific, bool, S_IRUGO);
+MODULE_PARM_DESC(disable_vendor_specific,
+		"Limit commands to the publicly specified set\n");
+
 static struct workqueue_struct *nfit_wq;
 
 struct nfit_table_prev {
@@ -171,33 +176,46 @@ static int acpi_nfit_ctl(struct nvdimm_bus_descriptor *nd_desc,
 		unsigned int buf_len, int *cmd_rc)
 {
 	struct acpi_nfit_desc *acpi_desc = to_acpi_nfit_desc(nd_desc);
-	const struct nd_cmd_desc *desc = NULL;
 	union acpi_object in_obj, in_buf, *out_obj;
+	const struct nd_cmd_desc *desc = NULL;
 	struct device *dev = acpi_desc->dev;
+	struct nd_cmd_pkg *call_pkg = NULL;
 	const char *cmd_name, *dimm_name;
-	unsigned long dsm_mask;
+	unsigned long cmd_mask, dsm_mask;
 	acpi_handle handle;
+	unsigned int func;
 	const u8 *uuid;
 	u32 offset;
 	int rc, i;
 
+	func = cmd;
+	if (cmd == ND_CMD_CALL) {
+		call_pkg = buf;
+		func = call_pkg->nd_command;
+	}
+
 	if (nvdimm) {
 		struct nfit_mem *nfit_mem = nvdimm_provider_data(nvdimm);
 		struct acpi_device *adev = nfit_mem->adev;
 
 		if (!adev)
 			return -ENOTTY;
+		if (call_pkg && nfit_mem->family != call_pkg->nd_family)
+			return -ENOTTY;
+
 		dimm_name = nvdimm_name(nvdimm);
 		cmd_name = nvdimm_cmd_name(cmd);
+		cmd_mask = nvdimm_cmd_mask(nvdimm);
 		dsm_mask = nfit_mem->dsm_mask;
 		desc = nd_cmd_dimm_desc(cmd);
-		uuid = to_nfit_uuid(NFIT_DEV_DIMM);
+		uuid = to_nfit_uuid(nfit_mem->family);
 		handle = adev->handle;
 	} else {
 		struct acpi_device *adev = to_acpi_dev(acpi_desc);
 
 		cmd_name = nvdimm_bus_cmd_name(cmd);
-		dsm_mask = nd_desc->dsm_mask;
+		cmd_mask = nd_desc->cmd_mask;
+		dsm_mask = cmd_mask;
 		desc = nd_cmd_bus_desc(cmd);
 		uuid = to_nfit_uuid(NFIT_DEV_BUS);
 		handle = adev->handle;
@@ -207,7 +225,7 @@ static int acpi_nfit_ctl(struct nvdimm_bus_descriptor *nd_desc,
 	if (!desc || (cmd && (desc->out_num + desc->in_num == 0)))
 		return -ENOTTY;
 
-	if (!test_bit(cmd, &dsm_mask))
+	if (!test_bit(cmd, &cmd_mask) || !test_bit(func, &dsm_mask))
 		return -ENOTTY;
 
 	in_obj.type = ACPI_TYPE_PACKAGE;
@@ -222,21 +240,44 @@ static int acpi_nfit_ctl(struct nvdimm_bus_descriptor *nd_desc,
 		in_buf.buffer.length += nd_cmd_in_size(nvdimm, cmd, desc,
 				i, buf);
 
+	if (call_pkg) {
+		/* skip over package wrapper */
+		in_buf.buffer.pointer = (void *) &call_pkg->nd_payload;
+		in_buf.buffer.length = call_pkg->nd_size_in;
+	}
+
 	if (IS_ENABLED(CONFIG_ACPI_NFIT_DEBUG)) {
-		dev_dbg(dev, "%s:%s cmd: %s input length: %d\n", __func__,
-				dimm_name, cmd_name, in_buf.buffer.length);
-		print_hex_dump_debug(cmd_name, DUMP_PREFIX_OFFSET, 4,
-				4, in_buf.buffer.pointer, min_t(u32, 128,
-					in_buf.buffer.length), true);
+		dev_dbg(dev, "%s:%s cmd: %d: func: %d input length: %d\n",
+				__func__, dimm_name, cmd, func,
+				in_buf.buffer.length);
+		print_hex_dump_debug("nvdimm in  ", DUMP_PREFIX_OFFSET, 4, 4,
+			in_buf.buffer.pointer,
+			min_t(u32, 256, in_buf.buffer.length), true);
 	}
 
-	out_obj = acpi_evaluate_dsm(handle, uuid, 1, cmd, &in_obj);
+	out_obj = acpi_evaluate_dsm(handle, uuid, 1, func, &in_obj);
 	if (!out_obj) {
 		dev_dbg(dev, "%s:%s _DSM failed cmd: %s\n", __func__, dimm_name,
 				cmd_name);
 		return -EINVAL;
 	}
 
+	if (call_pkg) {
+		call_pkg->nd_fw_size = out_obj->buffer.length;
+		memcpy(call_pkg->nd_payload + call_pkg->nd_size_in,
+			out_obj->buffer.pointer,
+			min(call_pkg->nd_fw_size, call_pkg->nd_size_out));
+
+		ACPI_FREE(out_obj);
+		/*
+		 * Need to support FW function w/o known size in advance.
+		 * Caller can determine required size based upon nd_fw_size.
+		 * If we return an error (like elsewhere) then caller wouldn't
+		 * be able to rely upon data returned to make calculation.
+		 */
+		return 0;
+	}
+
 	if (out_obj->package.type != ACPI_TYPE_BUFFER) {
 		dev_dbg(dev, "%s:%s unexpected output object type cmd: %s type: %d\n",
 				__func__, dimm_name, cmd_name, out_obj->type);
@@ -658,6 +699,7 @@ static int nfit_mem_dcr_init(struct acpi_nfit_desc *acpi_desc,
 			if (!nfit_mem)
 				return -ENOMEM;
 			INIT_LIST_HEAD(&nfit_mem->list);
+			nfit_mem->acpi_desc = acpi_desc;
 			list_add(&nfit_mem->list, &acpi_desc->dimms);
 		}
 
@@ -819,7 +861,7 @@ static ssize_t vendor_show(struct device *dev,
 {
 	struct acpi_nfit_control_region *dcr = to_nfit_dcr(dev);
 
-	return sprintf(buf, "%#x\n", dcr->vendor_id);
+	return sprintf(buf, "0x%04x\n", be16_to_cpu(dcr->vendor_id));
 }
 static DEVICE_ATTR_RO(vendor);
 
@@ -828,7 +870,7 @@ static ssize_t rev_id_show(struct device *dev,
 {
 	struct acpi_nfit_control_region *dcr = to_nfit_dcr(dev);
 
-	return sprintf(buf, "%#x\n", dcr->revision_id);
+	return sprintf(buf, "0x%04x\n", be16_to_cpu(dcr->revision_id));
 }
 static DEVICE_ATTR_RO(rev_id);
 
@@ -837,28 +879,142 @@ static ssize_t device_show(struct device *dev,
 {
 	struct acpi_nfit_control_region *dcr = to_nfit_dcr(dev);
 
-	return sprintf(buf, "%#x\n", dcr->device_id);
+	return sprintf(buf, "0x%04x\n", be16_to_cpu(dcr->device_id));
 }
 static DEVICE_ATTR_RO(device);
 
+static ssize_t subsystem_vendor_show(struct device *dev,
+		struct device_attribute *attr, char *buf)
+{
+	struct acpi_nfit_control_region *dcr = to_nfit_dcr(dev);
+
+	return sprintf(buf, "0x%04x\n", be16_to_cpu(dcr->subsystem_vendor_id));
+}
+static DEVICE_ATTR_RO(subsystem_vendor);
+
+static ssize_t subsystem_rev_id_show(struct device *dev,
+		struct device_attribute *attr, char *buf)
+{
+	struct acpi_nfit_control_region *dcr = to_nfit_dcr(dev);
+
+	return sprintf(buf, "0x%04x\n",
+			be16_to_cpu(dcr->subsystem_revision_id));
+}
+static DEVICE_ATTR_RO(subsystem_rev_id);
+
+static ssize_t subsystem_device_show(struct device *dev,
+		struct device_attribute *attr, char *buf)
+{
+	struct acpi_nfit_control_region *dcr = to_nfit_dcr(dev);
+
+	return sprintf(buf, "0x%04x\n", be16_to_cpu(dcr->subsystem_device_id));
+}
+static DEVICE_ATTR_RO(subsystem_device);
+
+static int num_nvdimm_formats(struct nvdimm *nvdimm)
+{
+	struct nfit_mem *nfit_mem = nvdimm_provider_data(nvdimm);
+	int formats = 0;
+
+	if (nfit_mem->memdev_pmem)
+		formats++;
+	if (nfit_mem->memdev_bdw)
+		formats++;
+	return formats;
+}
+
 static ssize_t format_show(struct device *dev,
 		struct device_attribute *attr, char *buf)
 {
 	struct acpi_nfit_control_region *dcr = to_nfit_dcr(dev);
 
-	return sprintf(buf, "%#x\n", dcr->code);
+	return sprintf(buf, "0x%04x\n", be16_to_cpu(dcr->code));
 }
 static DEVICE_ATTR_RO(format);
 
+static ssize_t format1_show(struct device *dev,
+		struct device_attribute *attr, char *buf)
+{
+	u32 handle;
+	ssize_t rc = -ENXIO;
+	struct nfit_mem *nfit_mem;
+	struct nfit_memdev *nfit_memdev;
+	struct acpi_nfit_desc *acpi_desc;
+	struct nvdimm *nvdimm = to_nvdimm(dev);
+	struct acpi_nfit_control_region *dcr = to_nfit_dcr(dev);
+
+	nfit_mem = nvdimm_provider_data(nvdimm);
+	acpi_desc = nfit_mem->acpi_desc;
+	handle = to_nfit_memdev(dev)->device_handle;
+
+	/* assumes DIMMs have at most 2 published interface codes */
+	mutex_lock(&acpi_desc->init_mutex);
+	list_for_each_entry(nfit_memdev, &acpi_desc->memdevs, list) {
+		struct acpi_nfit_memory_map *memdev = nfit_memdev->memdev;
+		struct nfit_dcr *nfit_dcr;
+
+		if (memdev->device_handle != handle)
+			continue;
+
+		list_for_each_entry(nfit_dcr, &acpi_desc->dcrs, list) {
+			if (nfit_dcr->dcr->region_index != memdev->region_index)
+				continue;
+			if (nfit_dcr->dcr->code == dcr->code)
+				continue;
+			rc = sprintf(buf, "%#x\n",
+					be16_to_cpu(nfit_dcr->dcr->code));
+			break;
+		}
+		if (rc != ENXIO)
+			break;
+	}
+	mutex_unlock(&acpi_desc->init_mutex);
+	return rc;
+}
+static DEVICE_ATTR_RO(format1);
+
+static ssize_t formats_show(struct device *dev,
+		struct device_attribute *attr, char *buf)
+{
+	struct nvdimm *nvdimm = to_nvdimm(dev);
+
+	return sprintf(buf, "%d\n", num_nvdimm_formats(nvdimm));
+}
+static DEVICE_ATTR_RO(formats);
+
 static ssize_t serial_show(struct device *dev,
 		struct device_attribute *attr, char *buf)
 {
 	struct acpi_nfit_control_region *dcr = to_nfit_dcr(dev);
 
-	return sprintf(buf, "%#x\n", dcr->serial_number);
+	return sprintf(buf, "0x%08x\n", be32_to_cpu(dcr->serial_number));
 }
 static DEVICE_ATTR_RO(serial);
 
+static ssize_t family_show(struct device *dev,
+		struct device_attribute *attr, char *buf)
+{
+	struct nvdimm *nvdimm = to_nvdimm(dev);
+	struct nfit_mem *nfit_mem = nvdimm_provider_data(nvdimm);
+
+	if (nfit_mem->family < 0)
+		return -ENXIO;
+	return sprintf(buf, "%d\n", nfit_mem->family);
+}
+static DEVICE_ATTR_RO(family);
+
+static ssize_t dsm_mask_show(struct device *dev,
+		struct device_attribute *attr, char *buf)
+{
+	struct nvdimm *nvdimm = to_nvdimm(dev);
+	struct nfit_mem *nfit_mem = nvdimm_provider_data(nvdimm);
+
+	if (nfit_mem->family < 0)
+		return -ENXIO;
+	return sprintf(buf, "%#lx\n", nfit_mem->dsm_mask);
+}
+static DEVICE_ATTR_RO(dsm_mask);
+
 static ssize_t flags_show(struct device *dev,
 		struct device_attribute *attr, char *buf)
 {
@@ -873,15 +1029,41 @@ static ssize_t flags_show(struct device *dev,
 }
 static DEVICE_ATTR_RO(flags);
 
+static ssize_t id_show(struct device *dev,
+		struct device_attribute *attr, char *buf)
+{
+	struct acpi_nfit_control_region *dcr = to_nfit_dcr(dev);
+
+	if (dcr->valid_fields & ACPI_NFIT_CONTROL_MFG_INFO_VALID)
+		return sprintf(buf, "%04x-%02x-%04x-%08x\n",
+				be16_to_cpu(dcr->vendor_id),
+				dcr->manufacturing_location,
+				be16_to_cpu(dcr->manufacturing_date),
+				be32_to_cpu(dcr->serial_number));
+	else
+		return sprintf(buf, "%04x-%08x\n",
+				be16_to_cpu(dcr->vendor_id),
+				be32_to_cpu(dcr->serial_number));
+}
+static DEVICE_ATTR_RO(id);
+
 static struct attribute *acpi_nfit_dimm_attributes[] = {
 	&dev_attr_handle.attr,
 	&dev_attr_phys_id.attr,
 	&dev_attr_vendor.attr,
 	&dev_attr_device.attr,
+	&dev_attr_rev_id.attr,
+	&dev_attr_subsystem_vendor.attr,
+	&dev_attr_subsystem_device.attr,
+	&dev_attr_subsystem_rev_id.attr,
 	&dev_attr_format.attr,
+	&dev_attr_formats.attr,
+	&dev_attr_format1.attr,
 	&dev_attr_serial.attr,
-	&dev_attr_rev_id.attr,
 	&dev_attr_flags.attr,
+	&dev_attr_id.attr,
+	&dev_attr_family.attr,
+	&dev_attr_dsm_mask.attr,
 	NULL,
 };
 
@@ -889,11 +1071,13 @@ static umode_t acpi_nfit_dimm_attr_visible(struct kobject *kobj,
 		struct attribute *a, int n)
 {
 	struct device *dev = container_of(kobj, struct device, kobj);
+	struct nvdimm *nvdimm = to_nvdimm(dev);
 
-	if (to_nfit_dcr(dev))
-		return a->mode;
-	else
+	if (!to_nfit_dcr(dev))
 		return 0;
+	if (a == &dev_attr_format1.attr && num_nvdimm_formats(nvdimm) <= 1)
+		return 0;
+	return a->mode;
 }
 
 static struct attribute_group acpi_nfit_dimm_attribute_group = {
@@ -926,10 +1110,13 @@ static int acpi_nfit_add_dimm(struct acpi_nfit_desc *acpi_desc,
 {
 	struct acpi_device *adev, *adev_dimm;
 	struct device *dev = acpi_desc->dev;
-	const u8 *uuid = to_nfit_uuid(NFIT_DEV_DIMM);
+	unsigned long dsm_mask;
+	const u8 *uuid;
 	int i;
 
-	nfit_mem->dsm_mask = acpi_desc->dimm_dsm_force_en;
+	/* nfit test assumes 1:1 relationship between commands and dsms */
+	nfit_mem->dsm_mask = acpi_desc->dimm_cmd_force_en;
+	nfit_mem->family = NVDIMM_FAMILY_INTEL;
 	adev = to_acpi_dev(acpi_desc);
 	if (!adev)
 		return 0;
@@ -942,7 +1129,35 @@ static int acpi_nfit_add_dimm(struct acpi_nfit_desc *acpi_desc,
 		return force_enable_dimms ? 0 : -ENODEV;
 	}
 
-	for (i = ND_CMD_SMART; i <= ND_CMD_VENDOR; i++)
+	/*
+	 * Until standardization materializes we need to consider up to 3
+	 * different command sets.  Note, that checking for function0 (bit0)
+	 * tells us if any commands are reachable through this uuid.
+	 */
+	for (i = NVDIMM_FAMILY_INTEL; i <= NVDIMM_FAMILY_HPE2; i++)
+		if (acpi_check_dsm(adev_dimm->handle, to_nfit_uuid(i), 1, 1))
+			break;
+
+	/* limit the supported commands to those that are publicly documented */
+	nfit_mem->family = i;
+	if (nfit_mem->family == NVDIMM_FAMILY_INTEL) {
+		dsm_mask = 0x3fe;
+		if (disable_vendor_specific)
+			dsm_mask &= ~(1 << ND_CMD_VENDOR);
+	} else if (nfit_mem->family == NVDIMM_FAMILY_HPE1)
+		dsm_mask = 0x1c3c76;
+	else if (nfit_mem->family == NVDIMM_FAMILY_HPE2) {
+		dsm_mask = 0x1fe;
+		if (disable_vendor_specific)
+			dsm_mask &= ~(1 << 8);
+	} else {
+		dev_err(dev, "unknown dimm command family\n");
+		nfit_mem->family = -1;
+		return force_enable_dimms ? 0 : -ENODEV;
+	}
+
+	uuid = to_nfit_uuid(nfit_mem->family);
+	for_each_set_bit(i, &dsm_mask, BITS_PER_LONG)
 		if (acpi_check_dsm(adev_dimm->handle, uuid, 1, 1ULL << i))
 			set_bit(i, &nfit_mem->dsm_mask);
 
@@ -955,8 +1170,8 @@ static int acpi_nfit_register_dimms(struct acpi_nfit_desc *acpi_desc)
 	int dimm_count = 0;
 
 	list_for_each_entry(nfit_mem, &acpi_desc->dimms, list) {
+		unsigned long flags = 0, cmd_mask;
 		struct nvdimm *nvdimm;
-		unsigned long flags = 0;
 		u32 device_handle;
 		u16 mem_flags;
 		int rc;
@@ -979,9 +1194,18 @@ static int acpi_nfit_register_dimms(struct acpi_nfit_desc *acpi_desc)
 		if (rc)
 			continue;
 
+		/*
+		 * TODO: provide translation for non-NVDIMM_FAMILY_INTEL
+		 * devices (i.e. from nd_cmd to acpi_dsm) to standardize the
+		 * userspace interface.
+		 */
+		cmd_mask = 1UL << ND_CMD_CALL;
+		if (nfit_mem->family == NVDIMM_FAMILY_INTEL)
+			cmd_mask |= nfit_mem->dsm_mask;
+
 		nvdimm = nvdimm_create(acpi_desc->nvdimm_bus, nfit_mem,
 				acpi_nfit_dimm_attribute_groups,
-				flags, &nfit_mem->dsm_mask);
+				flags, cmd_mask);
 		if (!nvdimm)
 			return -ENOMEM;
 
@@ -1010,14 +1234,14 @@ static void acpi_nfit_init_dsms(struct acpi_nfit_desc *acpi_desc)
 	struct acpi_device *adev;
 	int i;
 
-	nd_desc->dsm_mask = acpi_desc->bus_dsm_force_en;
+	nd_desc->cmd_mask = acpi_desc->bus_cmd_force_en;
 	adev = to_acpi_dev(acpi_desc);
 	if (!adev)
 		return;
 
 	for (i = ND_CMD_ARS_CAP; i <= ND_CMD_CLEAR_ERROR; i++)
 		if (acpi_check_dsm(adev->handle, uuid, 1, 1ULL << i))
-			set_bit(i, &nd_desc->dsm_mask);
+			set_bit(i, &nd_desc->cmd_mask);
 }
 
 static ssize_t range_index_show(struct device *dev,
@@ -2309,7 +2533,7 @@ static int acpi_nfit_add(struct acpi_device *adev)
 	acpi_size sz;
 	int rc;
 
-	status = acpi_get_table_with_size("NFIT", 0, &tbl, &sz);
+	status = acpi_get_table_with_size(ACPI_SIG_NFIT, 0, &tbl, &sz);
 	if (ACPI_FAILURE(status)) {
 		/* This is ok, we could have an nvdimm hotplugged later */
 		dev_dbg(dev, "failed to find NFIT at startup\n");
@@ -2466,6 +2690,8 @@ static __init int nfit_init(void)
 	acpi_str_to_uuid(UUID_PERSISTENT_VIRTUAL_CD, nfit_uuid[NFIT_SPA_PCD]);
 	acpi_str_to_uuid(UUID_NFIT_BUS, nfit_uuid[NFIT_DEV_BUS]);
 	acpi_str_to_uuid(UUID_NFIT_DIMM, nfit_uuid[NFIT_DEV_DIMM]);
+	acpi_str_to_uuid(UUID_NFIT_DIMM_N_HPE1, nfit_uuid[NFIT_DEV_DIMM_N_HPE1]);
+	acpi_str_to_uuid(UUID_NFIT_DIMM_N_HPE2, nfit_uuid[NFIT_DEV_DIMM_N_HPE2]);
 
 	nfit_wq = create_singlethread_workqueue("nfit");
 	if (!nfit_wq)

drivers/acpi/nfit.h

@@ -21,13 +21,25 @@
 #include <linux/acpi.h>
 #include <acpi/acuuid.h>
 
+/* ACPI 6.1 */
 #define UUID_NFIT_BUS "2f10e7a4-9e91-11e4-89d3-123b93f75cba"
+
+/* http://pmem.io/documents/NVDIMM_DSM_Interface_Example.pdf */
 #define UUID_NFIT_DIMM "4309ac30-0d11-11e4-9191-0800200c9a66"
+
+/* https://github.com/HewlettPackard/hpe-nvm/blob/master/Documentation/ */
+#define UUID_NFIT_DIMM_N_HPE1 "9002c334-acf3-4c0e-9642-a235f0d53bc6"
+#define UUID_NFIT_DIMM_N_HPE2 "5008664b-b758-41a0-a03c-27c2f2d04f7e"
+
 #define ACPI_NFIT_MEM_FAILED_MASK (ACPI_NFIT_MEM_SAVE_FAILED \
 		| ACPI_NFIT_MEM_RESTORE_FAILED | ACPI_NFIT_MEM_FLUSH_FAILED \
 		| ACPI_NFIT_MEM_NOT_ARMED)
 
 enum nfit_uuids {
+	/* for simplicity alias the uuid index with the family id */
+	NFIT_DEV_DIMM = NVDIMM_FAMILY_INTEL,
+	NFIT_DEV_DIMM_N_HPE1 = NVDIMM_FAMILY_HPE1,
+	NFIT_DEV_DIMM_N_HPE2 = NVDIMM_FAMILY_HPE2,
 	NFIT_SPA_VOLATILE,
 	NFIT_SPA_PM,
 	NFIT_SPA_DCR,
@@ -37,15 +49,16 @@ enum nfit_uuids {
 	NFIT_SPA_PDISK,
 	NFIT_SPA_PCD,
 	NFIT_DEV_BUS,
-	NFIT_DEV_DIMM,
 	NFIT_UUID_MAX,
 };
 
-enum nfit_fic {
-	NFIT_FIC_BYTE = 0x101, /* byte-addressable energy backed */
-	NFIT_FIC_BLK = 0x201, /* block-addressable non-energy backed */
-	NFIT_FIC_BYTEN = 0x301, /* byte-addressable non-energy backed */
-};
+/*
+ * Region format interface codes are stored as an array of bytes in the
+ * NFIT DIMM Control Region structure
+ */
+#define NFIT_FIC_BYTE cpu_to_be16(0x101) /* byte-addressable energy backed */
+#define NFIT_FIC_BLK cpu_to_be16(0x201) /* block-addressable non-energy backed */
+#define NFIT_FIC_BYTEN cpu_to_be16(0x301) /* byte-addressable non-energy backed */
 
 enum {
 	NFIT_BLK_READ_FLUSH = 1,
@@ -109,7 +122,9 @@ struct nfit_mem {
 	struct nfit_flush *nfit_flush;
 	struct list_head list;
 	struct acpi_device *adev;
+	struct acpi_nfit_desc *acpi_desc;
 	unsigned long dsm_mask;
+	int family;
 };
 
 struct acpi_nfit_desc {
@@ -132,8 +147,8 @@ struct acpi_nfit_desc {
 	size_t ars_status_size;
 	struct work_struct work;
 	unsigned int cancel:1;
-	unsigned long dimm_dsm_force_en;
-	unsigned long bus_dsm_force_en;
+	unsigned long dimm_cmd_force_en;
+	unsigned long bus_cmd_force_en;
 	int (*blk_do_io)(struct nd_blk_region *ndbr, resource_size_t dpa,
 			void *iobuf, u64 len, int rw);
 };

drivers/acpi/utils.c

@@ -625,7 +625,7 @@ acpi_status acpi_evaluate_lck(acpi_handle handle, int lock)
  * some old BIOSes do expect a buffer or an integer etc.
  */
 union acpi_object *
-acpi_evaluate_dsm(acpi_handle handle, const u8 *uuid, int rev, int func,
+acpi_evaluate_dsm(acpi_handle handle, const u8 *uuid, u64 rev, u64 func,
 		  union acpi_object *argv4)
 {
 	acpi_status ret;
@@ -674,7 +674,7 @@ EXPORT_SYMBOL(acpi_evaluate_dsm);
  * functions. Currently only support 64 functions at maximum, should be
  * enough for now.
  */
-bool acpi_check_dsm(acpi_handle handle, const u8 *uuid, int rev, u64 funcs)
+bool acpi_check_dsm(acpi_handle handle, const u8 *uuid, u64 rev, u64 funcs)
 {
 	int i;
 	u64 mask = 0;

drivers/dax/Kconfig

@@ -0,0 +1,26 @@
+menuconfig DEV_DAX
+	tristate "DAX: direct access to differentiated memory"
+	default m if NVDIMM_DAX
+	depends on TRANSPARENT_HUGEPAGE
+	help
+	  Support raw access to differentiated (persistence, bandwidth,
+	  latency...) memory via an mmap(2) capable character
+	  device.  Platform firmware or a device driver may identify a
+	  platform memory resource that is differentiated from the
+	  baseline memory pool.  Mappings of a /dev/daxX.Y device impose
+	  restrictions that make the mapping behavior deterministic.
+
+if DEV_DAX
+
+config DEV_DAX_PMEM
+	tristate "PMEM DAX: direct access to persistent memory"
+	depends on NVDIMM_DAX
+	default DEV_DAX
+	help
+	  Support raw access to persistent memory.  Note that this
+	  driver consumes memory ranges allocated and exported by the
+	  libnvdimm sub-system.
+
+	  Say Y if unsure
+
+endif

drivers/dax/Makefile

@@ -0,0 +1,4 @@
+obj-$(CONFIG_DEV_DAX) += dax.o
+obj-$(CONFIG_DEV_DAX_PMEM) += dax_pmem.o
+
+dax_pmem-y := pmem.o

drivers/dax/dax.c

@@ -0,0 +1,575 @@
+/*
+ * Copyright(c) 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/pagemap.h>
+#include <linux/module.h>
+#include <linux/device.h>
+#include <linux/pfn_t.h>
+#include <linux/slab.h>
+#include <linux/dax.h>
+#include <linux/fs.h>
+#include <linux/mm.h>
+
+static int dax_major;
+static struct class *dax_class;
+static DEFINE_IDA(dax_minor_ida);
+
+/**
+ * struct dax_region - mapping infrastructure for dax devices
+ * @id: kernel-wide unique region for a memory range
+ * @base: linear address corresponding to @res
+ * @kref: to pin while other agents have a need to do lookups
+ * @dev: parent device backing this region
+ * @align: allocation and mapping alignment for child dax devices
+ * @res: physical address range of the region
+ * @pfn_flags: identify whether the pfns are paged back or not
+ */
+struct dax_region {
+	int id;
+	struct ida ida;
+	void *base;
+	struct kref kref;
+	struct device *dev;
+	unsigned int align;
+	struct resource res;
+	unsigned long pfn_flags;
+};
+
+/**
+ * struct dax_dev - subdivision of a dax region
+ * @region - parent region
+ * @dev - device backing the character device
+ * @kref - enable this data to be tracked in filp->private_data
+ * @alive - !alive + rcu grace period == no new mappings can be established
+ * @id - child id in the region
+ * @num_resources - number of physical address extents in this device
+ * @res - array of physical address ranges
+ */
+struct dax_dev {
+	struct dax_region *region;
+	struct device *dev;
+	struct kref kref;
+	bool alive;
+	int id;
+	int num_resources;
+	struct resource res[0];
+};
+
+static void dax_region_free(struct kref *kref)
+{
+	struct dax_region *dax_region;
+
+	dax_region = container_of(kref, struct dax_region, kref);
+	kfree(dax_region);
+}
+
+void dax_region_put(struct dax_region *dax_region)
+{
+	kref_put(&dax_region->kref, dax_region_free);
+}
+EXPORT_SYMBOL_GPL(dax_region_put);
+
+static void dax_dev_free(struct kref *kref)
+{
+	struct dax_dev *dax_dev;
+
+	dax_dev = container_of(kref, struct dax_dev, kref);
+	dax_region_put(dax_dev->region);
+	kfree(dax_dev);
+}
+
+static void dax_dev_put(struct dax_dev *dax_dev)
+{
+	kref_put(&dax_dev->kref, dax_dev_free);
+}
+
+struct dax_region *alloc_dax_region(struct device *parent, int region_id,
+		struct resource *res, unsigned int align, void *addr,
+		unsigned long pfn_flags)
+{
+	struct dax_region *dax_region;
+
+	dax_region = kzalloc(sizeof(*dax_region), GFP_KERNEL);
+
+	if (!dax_region)
+		return NULL;
+
+	memcpy(&dax_region->res, res, sizeof(*res));
+	dax_region->pfn_flags = pfn_flags;
+	kref_init(&dax_region->kref);
+	dax_region->id = region_id;
+	ida_init(&dax_region->ida);
+	dax_region->align = align;
+	dax_region->dev = parent;
+	dax_region->base = addr;
+
+	return dax_region;
+}
+EXPORT_SYMBOL_GPL(alloc_dax_region);
+
+static ssize_t size_show(struct device *dev,
+		struct device_attribute *attr, char *buf)
+{
+	struct dax_dev *dax_dev = dev_get_drvdata(dev);
+	unsigned long long size = 0;
+	int i;
+
+	for (i = 0; i < dax_dev->num_resources; i++)
+		size += resource_size(&dax_dev->res[i]);
+
+	return sprintf(buf, "%llu\n", size);
+}
+static DEVICE_ATTR_RO(size);
+
+static struct attribute *dax_device_attributes[] = {
+	&dev_attr_size.attr,
+	NULL,
+};
+
+static const struct attribute_group dax_device_attribute_group = {
+	.attrs = dax_device_attributes,
+};
+
+static const struct attribute_group *dax_attribute_groups[] = {
+	&dax_device_attribute_group,
+	NULL,
+};
+
+static void unregister_dax_dev(void *_dev)
+{
+	struct device *dev = _dev;
+	struct dax_dev *dax_dev = dev_get_drvdata(dev);
+	struct dax_region *dax_region = dax_dev->region;
+
+	dev_dbg(dev, "%s\n", __func__);
+
+	/*
+	 * Note, rcu is not protecting the liveness of dax_dev, rcu is
+	 * ensuring that any fault handlers that might have seen
+	 * dax_dev->alive == true, have completed.  Any fault handlers
+	 * that start after synchronize_rcu() has started will abort
+	 * upon seeing dax_dev->alive == false.
+	 */
+	dax_dev->alive = false;
+	synchronize_rcu();
+
+	get_device(dev);
+	device_unregister(dev);
+	ida_simple_remove(&dax_region->ida, dax_dev->id);
+	ida_simple_remove(&dax_minor_ida, MINOR(dev->devt));
+	put_device(dev);
+	dax_dev_put(dax_dev);
+}
+
+int devm_create_dax_dev(struct dax_region *dax_region, struct resource *res,
+		int count)
+{
+	struct device *parent = dax_region->dev;
+	struct dax_dev *dax_dev;
+	struct device *dev;
+	int rc, minor;
+	dev_t dev_t;
+
+	dax_dev = kzalloc(sizeof(*dax_dev) + sizeof(*res) * count, GFP_KERNEL);
+	if (!dax_dev)
+		return -ENOMEM;
+	memcpy(dax_dev->res, res, sizeof(*res) * count);
+	dax_dev->num_resources = count;
+	kref_init(&dax_dev->kref);
+	dax_dev->alive = true;
+	dax_dev->region = dax_region;
+	kref_get(&dax_region->kref);
+
+	dax_dev->id = ida_simple_get(&dax_region->ida, 0, 0, GFP_KERNEL);
+	if (dax_dev->id < 0) {
+		rc = dax_dev->id;
+		goto err_id;
+	}
+
+	minor = ida_simple_get(&dax_minor_ida, 0, 0, GFP_KERNEL);
+	if (minor < 0) {
+		rc = minor;
+		goto err_minor;
+	}
+
+	dev_t = MKDEV(dax_major, minor);
+	dev = device_create_with_groups(dax_class, parent, dev_t, dax_dev,
+			dax_attribute_groups, "dax%d.%d", dax_region->id,
+			dax_dev->id);
+	if (IS_ERR(dev)) {
+		rc = PTR_ERR(dev);
+		goto err_create;
+	}
+	dax_dev->dev = dev;
+
+	rc = devm_add_action(dax_region->dev, unregister_dax_dev, dev);
+	if (rc) {
+		unregister_dax_dev(dev);
+		return rc;
+	}
+
+	return 0;
+
+ err_create:
+	ida_simple_remove(&dax_minor_ida, minor);
+ err_minor:
+	ida_simple_remove(&dax_region->ida, dax_dev->id);
+ err_id:
+	dax_dev_put(dax_dev);
+
+	return rc;
+}
+EXPORT_SYMBOL_GPL(devm_create_dax_dev);
+
+/* return an unmapped area aligned to the dax region specified alignment */
+static unsigned long dax_dev_get_unmapped_area(struct file *filp,
+		unsigned long addr, unsigned long len, unsigned long pgoff,
+		unsigned long flags)
+{
+	unsigned long off, off_end, off_align, len_align, addr_align, align;
+	struct dax_dev *dax_dev = filp ? filp->private_data : NULL;
+	struct dax_region *dax_region;
+
+	if (!dax_dev || addr)
+		goto out;
+
+	dax_region = dax_dev->region;
+	align = dax_region->align;
+	off = pgoff << PAGE_SHIFT;
+	off_end = off + len;
+	off_align = round_up(off, align);
+
+	if ((off_end <= off_align) || ((off_end - off_align) < align))
+		goto out;
+
+	len_align = len + align;
+	if ((off + len_align) < off)
+		goto out;
+
+	addr_align = current->mm->get_unmapped_area(filp, addr, len_align,
+			pgoff, flags);
+	if (!IS_ERR_VALUE(addr_align)) {
+		addr_align += (off - addr_align) & (align - 1);
+		return addr_align;
+	}
+ out:
+	return current->mm->get_unmapped_area(filp, addr, len, pgoff, flags);
+}
+
+static int __match_devt(struct device *dev, const void *data)
+{
+	const dev_t *devt = data;
+
+	return dev->devt == *devt;
+}
+
+static struct device *dax_dev_find(dev_t dev_t)
+{
+	return class_find_device(dax_class, NULL, &dev_t, __match_devt);
+}
+
+static int dax_dev_open(struct inode *inode, struct file *filp)
+{
+	struct dax_dev *dax_dev = NULL;
+	struct device *dev;
+
+	dev = dax_dev_find(inode->i_rdev);
+	if (!dev)
+		return -ENXIO;
+
+	device_lock(dev);
+	dax_dev = dev_get_drvdata(dev);
+	if (dax_dev) {
+		dev_dbg(dev, "%s\n", __func__);
+		filp->private_data = dax_dev;
+		kref_get(&dax_dev->kref);
+		inode->i_flags = S_DAX;
+	}
+	device_unlock(dev);
+
+	if (!dax_dev) {
+		put_device(dev);
+		return -ENXIO;
+	}
+	return 0;
+}
+
+static int dax_dev_release(struct inode *inode, struct file *filp)
+{
+	struct dax_dev *dax_dev = filp->private_data;
+	struct device *dev = dax_dev->dev;
+
+	dev_dbg(dax_dev->dev, "%s\n", __func__);
+	dax_dev_put(dax_dev);
+	put_device(dev);
+
+	return 0;
+}
+
+static int check_vma(struct dax_dev *dax_dev, struct vm_area_struct *vma,
+		const char *func)
+{
+	struct dax_region *dax_region = dax_dev->region;
+	struct device *dev = dax_dev->dev;
+	unsigned long mask;
+
+	if (!dax_dev->alive)
+		return -ENXIO;
+
+	/* prevent private / writable mappings from being established */
+	if ((vma->vm_flags & (VM_NORESERVE|VM_SHARED|VM_WRITE)) == VM_WRITE) {
+		dev_info(dev, "%s: %s: fail, attempted private mapping\n",
+				current->comm, func);
+		return -EINVAL;
+	}
+
+	mask = dax_region->align - 1;
+	if (vma->vm_start & mask || vma->vm_end & mask) {
+		dev_info(dev, "%s: %s: fail, unaligned vma (%#lx - %#lx, %#lx)\n",
+				current->comm, func, vma->vm_start, vma->vm_end,
+				mask);
+		return -EINVAL;
+	}
+
+	if ((dax_region->pfn_flags & (PFN_DEV|PFN_MAP)) == PFN_DEV
+			&& (vma->vm_flags & VM_DONTCOPY) == 0) {
+		dev_info(dev, "%s: %s: fail, dax range requires MADV_DONTFORK\n",
+				current->comm, func);
+		return -EINVAL;
+	}
+
+	if (!vma_is_dax(vma)) {
+		dev_info(dev, "%s: %s: fail, vma is not DAX capable\n",
+				current->comm, func);
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+static phys_addr_t pgoff_to_phys(struct dax_dev *dax_dev, pgoff_t pgoff,
+		unsigned long size)
+{
+	struct resource *res;
+	phys_addr_t phys;
+	int i;
+
+	for (i = 0; i < dax_dev->num_resources; i++) {
+		res = &dax_dev->res[i];
+		phys = pgoff * PAGE_SIZE + res->start;
+		if (phys >= res->start && phys <= res->end)
+			break;
+		pgoff -= PHYS_PFN(resource_size(res));
+	}
+
+	if (i < dax_dev->num_resources) {
+		res = &dax_dev->res[i];
+		if (phys + size - 1 <= res->end)
+			return phys;
+	}
+
+	return -1;
+}
+
+static int __dax_dev_fault(struct dax_dev *dax_dev, struct vm_area_struct *vma,
+		struct vm_fault *vmf)
+{
+	unsigned long vaddr = (unsigned long) vmf->virtual_address;
+	struct device *dev = dax_dev->dev;
+	struct dax_region *dax_region;
+	int rc = VM_FAULT_SIGBUS;
+	phys_addr_t phys;
+	pfn_t pfn;
+
+	if (check_vma(dax_dev, vma, __func__))
+		return VM_FAULT_SIGBUS;
+
+	dax_region = dax_dev->region;
+	if (dax_region->align > PAGE_SIZE) {
+		dev_dbg(dev, "%s: alignment > fault size\n", __func__);
+		return VM_FAULT_SIGBUS;
+	}
+
+	phys = pgoff_to_phys(dax_dev, vmf->pgoff, PAGE_SIZE);
+	if (phys == -1) {
+		dev_dbg(dev, "%s: phys_to_pgoff(%#lx) failed\n", __func__,
+				vmf->pgoff);
+		return VM_FAULT_SIGBUS;
+	}
+
+	pfn = phys_to_pfn_t(phys, dax_region->pfn_flags);
+
+	rc = vm_insert_mixed(vma, vaddr, pfn);
+
+	if (rc == -ENOMEM)
+		return VM_FAULT_OOM;
+	if (rc < 0 && rc != -EBUSY)
+		return VM_FAULT_SIGBUS;
+
+	return VM_FAULT_NOPAGE;
+}
+
+static int dax_dev_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
+{
+	int rc;
+	struct file *filp = vma->vm_file;
+	struct dax_dev *dax_dev = filp->private_data;
+
+	dev_dbg(dax_dev->dev, "%s: %s: %s (%#lx - %#lx)\n", __func__,
+			current->comm, (vmf->flags & FAULT_FLAG_WRITE)
+			? "write" : "read", vma->vm_start, vma->vm_end);
+	rcu_read_lock();
+	rc = __dax_dev_fault(dax_dev, vma, vmf);
+	rcu_read_unlock();
+
+	return rc;
+}
+
+static int __dax_dev_pmd_fault(struct dax_dev *dax_dev,
+		struct vm_area_struct *vma, unsigned long addr, pmd_t *pmd,
+		unsigned int flags)
+{
+	unsigned long pmd_addr = addr & PMD_MASK;
+	struct device *dev = dax_dev->dev;
+	struct dax_region *dax_region;
+	phys_addr_t phys;
+	pgoff_t pgoff;
+	pfn_t pfn;
+
+	if (check_vma(dax_dev, vma, __func__))
+		return VM_FAULT_SIGBUS;
+
+	dax_region = dax_dev->region;
+	if (dax_region->align > PMD_SIZE) {
+		dev_dbg(dev, "%s: alignment > fault size\n", __func__);
+		return VM_FAULT_SIGBUS;
+	}
+
+	/* dax pmd mappings require pfn_t_devmap() */
+	if ((dax_region->pfn_flags & (PFN_DEV|PFN_MAP)) != (PFN_DEV|PFN_MAP)) {
+		dev_dbg(dev, "%s: alignment > fault size\n", __func__);
+		return VM_FAULT_SIGBUS;
+	}
+
+	pgoff = linear_page_index(vma, pmd_addr);
+	phys = pgoff_to_phys(dax_dev, pgoff, PAGE_SIZE);
+	if (phys == -1) {
+		dev_dbg(dev, "%s: phys_to_pgoff(%#lx) failed\n", __func__,
+				pgoff);
+		return VM_FAULT_SIGBUS;
+	}
+
+	pfn = phys_to_pfn_t(phys, dax_region->pfn_flags);
+
+	return vmf_insert_pfn_pmd(vma, addr, pmd, pfn,
+			flags & FAULT_FLAG_WRITE);
+}
+
+static int dax_dev_pmd_fault(struct vm_area_struct *vma, unsigned long addr,
+		pmd_t *pmd, unsigned int flags)
+{
+	int rc;
+	struct file *filp = vma->vm_file;
+	struct dax_dev *dax_dev = filp->private_data;
+
+	dev_dbg(dax_dev->dev, "%s: %s: %s (%#lx - %#lx)\n", __func__,
+			current->comm, (flags & FAULT_FLAG_WRITE)
+			? "write" : "read", vma->vm_start, vma->vm_end);
+
+	rcu_read_lock();
+	rc = __dax_dev_pmd_fault(dax_dev, vma, addr, pmd, flags);
+	rcu_read_unlock();
+
+	return rc;
+}
+
+static void dax_dev_vm_open(struct vm_area_struct *vma)
+{
+	struct file *filp = vma->vm_file;
+	struct dax_dev *dax_dev = filp->private_data;
+
+	dev_dbg(dax_dev->dev, "%s\n", __func__);
+	kref_get(&dax_dev->kref);
+}
+
+static void dax_dev_vm_close(struct vm_area_struct *vma)
+{
+	struct file *filp = vma->vm_file;
+	struct dax_dev *dax_dev = filp->private_data;
+
+	dev_dbg(dax_dev->dev, "%s\n", __func__);
+	dax_dev_put(dax_dev);
+}
+
+static const struct vm_operations_struct dax_dev_vm_ops = {
+	.fault = dax_dev_fault,
+	.pmd_fault = dax_dev_pmd_fault,
+	.open = dax_dev_vm_open,
+	.close = dax_dev_vm_close,
+};
+
+static int dax_dev_mmap(struct file *filp, struct vm_area_struct *vma)
+{
+	struct dax_dev *dax_dev = filp->private_data;
+	int rc;
+
+	dev_dbg(dax_dev->dev, "%s\n", __func__);
+
+	rc = check_vma(dax_dev, vma, __func__);
+	if (rc)
+		return rc;
+
+	kref_get(&dax_dev->kref);
+	vma->vm_ops = &dax_dev_vm_ops;
+	vma->vm_flags |= VM_MIXEDMAP | VM_HUGEPAGE;
+	return 0;
+
+}
+
+static const struct file_operations dax_fops = {
+	.llseek = noop_llseek,
+	.owner = THIS_MODULE,
+	.open = dax_dev_open,
+	.release = dax_dev_release,
+	.get_unmapped_area = dax_dev_get_unmapped_area,
+	.mmap = dax_dev_mmap,
+};
+
+static int __init dax_init(void)
+{
+	int rc;
+
+	rc = register_chrdev(0, "dax", &dax_fops);
+	if (rc < 0)
+		return rc;
+	dax_major = rc;
+
+	dax_class = class_create(THIS_MODULE, "dax");
+	if (IS_ERR(dax_class)) {
+		unregister_chrdev(dax_major, "dax");
+		return PTR_ERR(dax_class);
+	}
+
+	return 0;
+}
+
+static void __exit dax_exit(void)
+{
+	class_destroy(dax_class);
+	unregister_chrdev(dax_major, "dax");
+	ida_destroy(&dax_minor_ida);
+}
+
+MODULE_AUTHOR("Intel Corporation");
+MODULE_LICENSE("GPL v2");
+subsys_initcall(dax_init);
+module_exit(dax_exit);

drivers/dax/dax.h

@@ -0,0 +1,24 @@
+/*
+ * Copyright(c) 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.
+ */
+#ifndef __DAX_H__
+#define __DAX_H__
+struct device;
+struct resource;
+struct dax_region;
+void dax_region_put(struct dax_region *dax_region);
+struct dax_region *alloc_dax_region(struct device *parent,
+		int region_id, struct resource *res, unsigned int align,
+		void *addr, unsigned long flags);
+int devm_create_dax_dev(struct dax_region *dax_region, struct resource *res,
+		int count);
+#endif /* __DAX_H__ */

drivers/dax/pmem.c

@@ -0,0 +1,158 @@
+/*
+ * Copyright(c) 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/percpu-refcount.h>
+#include <linux/memremap.h>
+#include <linux/module.h>
+#include <linux/pfn_t.h>
+#include "../nvdimm/pfn.h"
+#include "../nvdimm/nd.h"
+#include "dax.h"
+
+struct dax_pmem {
+	struct device *dev;
+	struct percpu_ref ref;
+	struct completion cmp;
+};
+
+struct dax_pmem *to_dax_pmem(struct percpu_ref *ref)
+{
+	return container_of(ref, struct dax_pmem, ref);
+}
+
+static void dax_pmem_percpu_release(struct percpu_ref *ref)
+{
+	struct dax_pmem *dax_pmem = to_dax_pmem(ref);
+
+	dev_dbg(dax_pmem->dev, "%s\n", __func__);
+	complete(&dax_pmem->cmp);
+}
+
+static void dax_pmem_percpu_exit(void *data)
+{
+	struct percpu_ref *ref = data;
+	struct dax_pmem *dax_pmem = to_dax_pmem(ref);
+
+	dev_dbg(dax_pmem->dev, "%s\n", __func__);
+	percpu_ref_exit(ref);
+	wait_for_completion(&dax_pmem->cmp);
+}
+
+static void dax_pmem_percpu_kill(void *data)
+{
+	struct percpu_ref *ref = data;
+	struct dax_pmem *dax_pmem = to_dax_pmem(ref);
+
+	dev_dbg(dax_pmem->dev, "%s\n", __func__);
+	percpu_ref_kill(ref);
+}
+
+static int dax_pmem_probe(struct device *dev)
+{
+	int rc;
+	void *addr;
+	struct resource res;
+	struct nd_pfn_sb *pfn_sb;
+	struct dax_pmem *dax_pmem;
+	struct nd_region *nd_region;
+	struct nd_namespace_io *nsio;
+	struct dax_region *dax_region;
+	struct nd_namespace_common *ndns;
+	struct nd_dax *nd_dax = to_nd_dax(dev);
+	struct nd_pfn *nd_pfn = &nd_dax->nd_pfn;
+	struct vmem_altmap __altmap, *altmap = NULL;
+
+	ndns = nvdimm_namespace_common_probe(dev);
+	if (IS_ERR(ndns))
+		return PTR_ERR(ndns);
+	nsio = to_nd_namespace_io(&ndns->dev);
+
+	/* parse the 'pfn' info block via ->rw_bytes */
+	devm_nsio_enable(dev, nsio);
+	altmap = nvdimm_setup_pfn(nd_pfn, &res, &__altmap);
+	if (IS_ERR(altmap))
+		return PTR_ERR(altmap);
+	devm_nsio_disable(dev, nsio);
+
+	pfn_sb = nd_pfn->pfn_sb;
+
+	if (!devm_request_mem_region(dev, nsio->res.start,
+				resource_size(&nsio->res), dev_name(dev))) {
+		dev_warn(dev, "could not reserve region %pR\n", &nsio->res);
+		return -EBUSY;
+	}
+
+	dax_pmem = devm_kzalloc(dev, sizeof(*dax_pmem), GFP_KERNEL);
+	if (!dax_pmem)
+		return -ENOMEM;
+
+	dax_pmem->dev = dev;
+	init_completion(&dax_pmem->cmp);
+	rc = percpu_ref_init(&dax_pmem->ref, dax_pmem_percpu_release, 0,
+			GFP_KERNEL);
+	if (rc)
+		return rc;
+
+	rc = devm_add_action(dev, dax_pmem_percpu_exit, &dax_pmem->ref);
+	if (rc) {
+		dax_pmem_percpu_exit(&dax_pmem->ref);
+		return rc;
+	}
+
+	addr = devm_memremap_pages(dev, &res, &dax_pmem->ref, altmap);
+	if (IS_ERR(addr))
+		return PTR_ERR(addr);
+
+	rc = devm_add_action(dev, dax_pmem_percpu_kill, &dax_pmem->ref);
+	if (rc) {
+		dax_pmem_percpu_kill(&dax_pmem->ref);
+		return rc;
+	}
+
+	nd_region = to_nd_region(dev->parent);
+	dax_region = alloc_dax_region(dev, nd_region->id, &res,
+			le32_to_cpu(pfn_sb->align), addr, PFN_DEV|PFN_MAP);
+	if (!dax_region)
+		return -ENOMEM;
+
+	/* TODO: support for subdividing a dax region... */
+	rc = devm_create_dax_dev(dax_region, &res, 1);
+
+	/* child dax_dev instances now own the lifetime of the dax_region */
+	dax_region_put(dax_region);
+
+	return rc;
+}
+
+static struct nd_device_driver dax_pmem_driver = {
+	.probe = dax_pmem_probe,
+	.drv = {
+		.name = "dax_pmem",
+	},
+	.type = ND_DRIVER_DAX_PMEM,
+};
+
+static int __init dax_pmem_init(void)
+{
+	return nd_driver_register(&dax_pmem_driver);
+}
+module_init(dax_pmem_init);
+
+static void __exit dax_pmem_exit(void)
+{
+	driver_unregister(&dax_pmem_driver.drv);
+}
+module_exit(dax_pmem_exit);
+
+MODULE_LICENSE("GPL v2");
+MODULE_AUTHOR("Intel Corporation");
+MODULE_ALIAS_ND_DEVICE(ND_DEVICE_DAX_PMEM);

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/blk.c

@@ -21,19 +21,19 @@
 #include <linux/sizes.h>
 #include "nd.h"
 
-struct nd_blk_device {
-	struct request_queue *queue;
-	struct gendisk *disk;
-	struct nd_namespace_blk *nsblk;
-	struct nd_blk_region *ndbr;
-	size_t disk_size;
-	u32 sector_size;
-	u32 internal_lbasize;
-};
+static u32 nsblk_meta_size(struct nd_namespace_blk *nsblk)
+{
+	return nsblk->lbasize - ((nsblk->lbasize >= 4096) ? 4096 : 512);
+}
+
+static u32 nsblk_internal_lbasize(struct nd_namespace_blk *nsblk)
+{
+	return roundup(nsblk->lbasize, INT_LBASIZE_ALIGNMENT);
+}
 
-static u32 nd_blk_meta_size(struct nd_blk_device *blk_dev)
+static u32 nsblk_sector_size(struct nd_namespace_blk *nsblk)
 {
-	return blk_dev->nsblk->lbasize - blk_dev->sector_size;
+	return nsblk->lbasize - nsblk_meta_size(nsblk);
 }
 
 static resource_size_t to_dev_offset(struct nd_namespace_blk *nsblk,
@@ -57,20 +57,29 @@ static resource_size_t to_dev_offset(struct nd_namespace_blk *nsblk,
 	return SIZE_MAX;
 }
 
+static struct nd_blk_region *to_ndbr(struct nd_namespace_blk *nsblk)
+{
+	struct nd_region *nd_region;
+	struct device *parent;
+
+	parent = nsblk->common.dev.parent;
+	nd_region = container_of(parent, struct nd_region, dev);
+	return container_of(nd_region, struct nd_blk_region, nd_region);
+}
+
 #ifdef CONFIG_BLK_DEV_INTEGRITY
-static int nd_blk_rw_integrity(struct nd_blk_device *blk_dev,
-				struct bio_integrity_payload *bip, u64 lba,
-				int rw)
+static int nd_blk_rw_integrity(struct nd_namespace_blk *nsblk,
+		struct bio_integrity_payload *bip, u64 lba, int rw)
 {
-	unsigned int len = nd_blk_meta_size(blk_dev);
+	struct nd_blk_region *ndbr = to_ndbr(nsblk);
+	unsigned int len = nsblk_meta_size(nsblk);
 	resource_size_t	dev_offset, ns_offset;
-	struct nd_namespace_blk *nsblk;
-	struct nd_blk_region *ndbr;
+	u32 internal_lbasize, sector_size;
 	int err = 0;
 
-	nsblk = blk_dev->nsblk;
-	ndbr = blk_dev->ndbr;
-	ns_offset = lba * blk_dev->internal_lbasize + blk_dev->sector_size;
+	internal_lbasize = nsblk_internal_lbasize(nsblk);
+	sector_size = nsblk_sector_size(nsblk);
+	ns_offset = lba * internal_lbasize + sector_size;
 	dev_offset = to_dev_offset(nsblk, ns_offset, len);
 	if (dev_offset == SIZE_MAX)
 		return -EIO;
@@ -104,25 +113,26 @@ static int nd_blk_rw_integrity(struct nd_blk_device *blk_dev,
 }
 
 #else /* CONFIG_BLK_DEV_INTEGRITY */
-static int nd_blk_rw_integrity(struct nd_blk_device *blk_dev,
-				struct bio_integrity_payload *bip, u64 lba,
-				int rw)
+static int nd_blk_rw_integrity(struct nd_namespace_blk *nsblk,
+		struct bio_integrity_payload *bip, u64 lba, int rw)
 {
 	return 0;
 }
 #endif
 
-static int nd_blk_do_bvec(struct nd_blk_device *blk_dev,
-			struct bio_integrity_payload *bip, struct page *page,
-			unsigned int len, unsigned int off, int rw,
-			sector_t sector)
+static int nsblk_do_bvec(struct nd_namespace_blk *nsblk,
+		struct bio_integrity_payload *bip, struct page *page,
+		unsigned int len, unsigned int off, int rw, sector_t sector)
 {
-	struct nd_blk_region *ndbr = blk_dev->ndbr;
+	struct nd_blk_region *ndbr = to_ndbr(nsblk);
 	resource_size_t	dev_offset, ns_offset;
+	u32 internal_lbasize, sector_size;
 	int err = 0;
 	void *iobuf;
 	u64 lba;
 
+	internal_lbasize = nsblk_internal_lbasize(nsblk);
+	sector_size = nsblk_sector_size(nsblk);
 	while (len) {
 		unsigned int cur_len;
 
@@ -132,11 +142,11 @@ static int nd_blk_do_bvec(struct nd_blk_device *blk_dev,
 		 * Block Window setup/move steps. the do_io routine is capable
 		 * of handling len <= PAGE_SIZE.
 		 */
-		cur_len = bip ? min(len, blk_dev->sector_size) : len;
+		cur_len = bip ? min(len, sector_size) : len;
 
-		lba = div_u64(sector << SECTOR_SHIFT, blk_dev->sector_size);
-		ns_offset = lba * blk_dev->internal_lbasize;
-		dev_offset = to_dev_offset(blk_dev->nsblk, ns_offset, cur_len);
+		lba = div_u64(sector << SECTOR_SHIFT, sector_size);
+		ns_offset = lba * internal_lbasize;
+		dev_offset = to_dev_offset(nsblk, ns_offset, cur_len);
 		if (dev_offset == SIZE_MAX)
 			return -EIO;
 
@@ -147,13 +157,13 @@ static int nd_blk_do_bvec(struct nd_blk_device *blk_dev,
 			return err;
 
 		if (bip) {
-			err = nd_blk_rw_integrity(blk_dev, bip, lba, rw);
+			err = nd_blk_rw_integrity(nsblk, bip, lba, rw);
 			if (err)
 				return err;
 		}
 		len -= cur_len;
 		off += cur_len;
-		sector += blk_dev->sector_size >> SECTOR_SHIFT;
+		sector += sector_size >> SECTOR_SHIFT;
 	}
 
 	return err;
@@ -161,10 +171,8 @@ static int nd_blk_do_bvec(struct nd_blk_device *blk_dev,
 
 static blk_qc_t nd_blk_make_request(struct request_queue *q, struct bio *bio)
 {
-	struct block_device *bdev = bio->bi_bdev;
-	struct gendisk *disk = bdev->bd_disk;
 	struct bio_integrity_payload *bip;
-	struct nd_blk_device *blk_dev;
+	struct nd_namespace_blk *nsblk;
 	struct bvec_iter iter;
 	unsigned long start;
 	struct bio_vec bvec;
@@ -183,17 +191,17 @@ static blk_qc_t nd_blk_make_request(struct request_queue *q, struct bio *bio)
 	}
 
 	bip = bio_integrity(bio);
-	blk_dev = disk->private_data;
+	nsblk = q->queuedata;
 	rw = bio_data_dir(bio);
 	do_acct = nd_iostat_start(bio, &start);
 	bio_for_each_segment(bvec, bio, iter) {
 		unsigned int len = bvec.bv_len;
 
 		BUG_ON(len > PAGE_SIZE);
-		err = nd_blk_do_bvec(blk_dev, bip, bvec.bv_page, len,
-					bvec.bv_offset, rw, iter.bi_sector);
+		err = nsblk_do_bvec(nsblk, bip, bvec.bv_page, len,
+				bvec.bv_offset, rw, iter.bi_sector);
 		if (err) {
-			dev_info(&blk_dev->nsblk->common.dev,
+			dev_dbg(&nsblk->common.dev,
 					"io error in %s sector %lld, len %d,\n",
 					(rw == READ) ? "READ" : "WRITE",
 					(unsigned long long) iter.bi_sector, len);
@@ -209,17 +217,16 @@ static blk_qc_t nd_blk_make_request(struct request_queue *q, struct bio *bio)
 	return BLK_QC_T_NONE;
 }
 
-static int nd_blk_rw_bytes(struct nd_namespace_common *ndns,
+static int nsblk_rw_bytes(struct nd_namespace_common *ndns,
 		resource_size_t offset, void *iobuf, size_t n, int rw)
 {
-	struct nd_blk_device *blk_dev = dev_get_drvdata(ndns->claim);
-	struct nd_namespace_blk *nsblk = blk_dev->nsblk;
-	struct nd_blk_region *ndbr = blk_dev->ndbr;
+	struct nd_namespace_blk *nsblk = to_nd_namespace_blk(&ndns->dev);
+	struct nd_blk_region *ndbr = to_ndbr(nsblk);
 	resource_size_t	dev_offset;
 
 	dev_offset = to_dev_offset(nsblk, offset, n);
 
-	if (unlikely(offset + n > blk_dev->disk_size)) {
+	if (unlikely(offset + n > nsblk->size)) {
 		dev_WARN_ONCE(&ndns->dev, 1, "request out of range\n");
 		return -EFAULT;
 	}
@@ -235,51 +242,65 @@ static const struct block_device_operations nd_blk_fops = {
 	.revalidate_disk = nvdimm_revalidate_disk,
 };
 
-static int nd_blk_attach_disk(struct nd_namespace_common *ndns,
-		struct nd_blk_device *blk_dev)
+static void nd_blk_release_queue(void *q)
+{
+	blk_cleanup_queue(q);
+}
+
+static void nd_blk_release_disk(void *disk)
+{
+	del_gendisk(disk);
+	put_disk(disk);
+}
+
+static int nsblk_attach_disk(struct nd_namespace_blk *nsblk)
 {
+	struct device *dev = &nsblk->common.dev;
 	resource_size_t available_disk_size;
+	struct request_queue *q;
 	struct gendisk *disk;
 	u64 internal_nlba;
 
-	internal_nlba = div_u64(blk_dev->disk_size, blk_dev->internal_lbasize);
-	available_disk_size = internal_nlba * blk_dev->sector_size;
+	internal_nlba = div_u64(nsblk->size, nsblk_internal_lbasize(nsblk));
+	available_disk_size = internal_nlba * nsblk_sector_size(nsblk);
 
-	blk_dev->queue = blk_alloc_queue(GFP_KERNEL);
-	if (!blk_dev->queue)
+	q = blk_alloc_queue(GFP_KERNEL);
+	if (!q)
 		return -ENOMEM;
+	if (devm_add_action(dev, nd_blk_release_queue, q)) {
+		blk_cleanup_queue(q);
+		return -ENOMEM;
+	}
 
-	blk_queue_make_request(blk_dev->queue, nd_blk_make_request);
-	blk_queue_max_hw_sectors(blk_dev->queue, UINT_MAX);
-	blk_queue_bounce_limit(blk_dev->queue, BLK_BOUNCE_ANY);
-	blk_queue_logical_block_size(blk_dev->queue, blk_dev->sector_size);
-	queue_flag_set_unlocked(QUEUE_FLAG_NONROT, blk_dev->queue);
+	blk_queue_make_request(q, nd_blk_make_request);
+	blk_queue_max_hw_sectors(q, UINT_MAX);
+	blk_queue_bounce_limit(q, BLK_BOUNCE_ANY);
+	blk_queue_logical_block_size(q, nsblk_sector_size(nsblk));
+	queue_flag_set_unlocked(QUEUE_FLAG_NONROT, q);
+	q->queuedata = nsblk;
 
-	disk = blk_dev->disk = alloc_disk(0);
-	if (!disk) {
-		blk_cleanup_queue(blk_dev->queue);
+	disk = alloc_disk(0);
+	if (!disk)
+		return -ENOMEM;
+	if (devm_add_action(dev, nd_blk_release_disk, disk)) {
+		put_disk(disk);
 		return -ENOMEM;
 	}
 
-	disk->driverfs_dev	= &ndns->dev;
+	disk->driverfs_dev	= dev;
 	disk->first_minor	= 0;
 	disk->fops		= &nd_blk_fops;
-	disk->private_data	= blk_dev;
-	disk->queue		= blk_dev->queue;
+	disk->queue		= q;
 	disk->flags		= GENHD_FL_EXT_DEVT;
-	nvdimm_namespace_disk_name(ndns, disk->disk_name);
+	nvdimm_namespace_disk_name(&nsblk->common, disk->disk_name);
 	set_capacity(disk, 0);
 	add_disk(disk);
 
-	if (nd_blk_meta_size(blk_dev)) {
-		int rc = nd_integrity_init(disk, nd_blk_meta_size(blk_dev));
+	if (nsblk_meta_size(nsblk)) {
+		int rc = nd_integrity_init(disk, nsblk_meta_size(nsblk));
 
-		if (rc) {
-			del_gendisk(disk);
-			put_disk(disk);
-			blk_cleanup_queue(blk_dev->queue);
+		if (rc)
 			return rc;
-		}
 	}
 
 	set_capacity(disk, available_disk_size >> SECTOR_SHIFT);
@@ -291,56 +312,29 @@ static int nd_blk_probe(struct device *dev)
 {
 	struct nd_namespace_common *ndns;
 	struct nd_namespace_blk *nsblk;
-	struct nd_blk_device *blk_dev;
-	int rc;
 
 	ndns = nvdimm_namespace_common_probe(dev);
 	if (IS_ERR(ndns))
 		return PTR_ERR(ndns);
 
-	blk_dev = kzalloc(sizeof(*blk_dev), GFP_KERNEL);
-	if (!blk_dev)
-		return -ENOMEM;
-
 	nsblk = to_nd_namespace_blk(&ndns->dev);
-	blk_dev->disk_size = nvdimm_namespace_capacity(ndns);
-	blk_dev->ndbr = to_nd_blk_region(dev->parent);
-	blk_dev->nsblk = to_nd_namespace_blk(&ndns->dev);
-	blk_dev->internal_lbasize = roundup(nsblk->lbasize,
-						INT_LBASIZE_ALIGNMENT);
-	blk_dev->sector_size = ((nsblk->lbasize >= 4096) ? 4096 : 512);
-	dev_set_drvdata(dev, blk_dev);
-
-	ndns->rw_bytes = nd_blk_rw_bytes;
+	nsblk->size = nvdimm_namespace_capacity(ndns);
+	dev_set_drvdata(dev, nsblk);
+
+	ndns->rw_bytes = nsblk_rw_bytes;
 	if (is_nd_btt(dev))
-		rc = nvdimm_namespace_attach_btt(ndns);
-	else if (nd_btt_probe(ndns, blk_dev) == 0) {
+		return nvdimm_namespace_attach_btt(ndns);
+	else if (nd_btt_probe(dev, ndns) == 0) {
 		/* we'll come back as btt-blk */
-		rc = -ENXIO;
+		return -ENXIO;
 	} else
-		rc = nd_blk_attach_disk(ndns, blk_dev);
-	if (rc)
-		kfree(blk_dev);
-	return rc;
-}
-
-static void nd_blk_detach_disk(struct nd_blk_device *blk_dev)
-{
-	del_gendisk(blk_dev->disk);
-	put_disk(blk_dev->disk);
-	blk_cleanup_queue(blk_dev->queue);
+		return nsblk_attach_disk(nsblk);
 }
 
 static int nd_blk_remove(struct device *dev)
 {
-	struct nd_blk_device *blk_dev = dev_get_drvdata(dev);
-
 	if (is_nd_btt(dev))
-		nvdimm_namespace_detach_btt(to_nd_btt(dev)->ndns);
-	else
-		nd_blk_detach_disk(blk_dev);
-	kfree(blk_dev);
-
+		nvdimm_namespace_detach_btt(to_nd_btt(dev));
 	return 0;
 }
 

drivers/nvdimm/btt.c

@@ -1306,7 +1306,7 @@ static struct btt *btt_init(struct nd_btt *nd_btt, unsigned long long rawsize,
 	struct btt *btt;
 	struct device *dev = &nd_btt->dev;
 
-	btt = kzalloc(sizeof(struct btt), GFP_KERNEL);
+	btt = devm_kzalloc(dev, sizeof(struct btt), GFP_KERNEL);
 	if (!btt)
 		return NULL;
 
@@ -1321,13 +1321,13 @@ static struct btt *btt_init(struct nd_btt *nd_btt, unsigned long long rawsize,
 	ret = discover_arenas(btt);
 	if (ret) {
 		dev_err(dev, "init: error in arena_discover: %d\n", ret);
-		goto out_free;
+		return NULL;
 	}
 
 	if (btt->init_state != INIT_READY && nd_region->ro) {
 		dev_info(dev, "%s is read-only, unable to init btt metadata\n",
 				dev_name(&nd_region->dev));
-		goto out_free;
+		return NULL;
 	} else if (btt->init_state != INIT_READY) {
 		btt->num_arenas = (rawsize / ARENA_MAX_SIZE) +
 			((rawsize % ARENA_MAX_SIZE) ? 1 : 0);
@@ -1337,29 +1337,25 @@ static struct btt *btt_init(struct nd_btt *nd_btt, unsigned long long rawsize,
 		ret = create_arenas(btt);
 		if (ret) {
 			dev_info(dev, "init: create_arenas: %d\n", ret);
-			goto out_free;
+			return NULL;
 		}
 
 		ret = btt_meta_init(btt);
 		if (ret) {
 			dev_err(dev, "init: error in meta_init: %d\n", ret);
-			goto out_free;
+			return NULL;
 		}
 	}
 
 	ret = btt_blk_init(btt);
 	if (ret) {
 		dev_err(dev, "init: error in blk_init: %d\n", ret);
-		goto out_free;
+		return NULL;
 	}
 
 	btt_debugfs_init(btt);
 
 	return btt;
-
- out_free:
-	kfree(btt);
-	return NULL;
 }
 
 /**
@@ -1377,7 +1373,6 @@ static void btt_fini(struct btt *btt)
 		btt_blk_cleanup(btt);
 		free_arenas(btt);
 		debugfs_remove_recursive(btt->debugfs_dir);
-		kfree(btt);
 	}
 }
 
@@ -1388,11 +1383,15 @@ int nvdimm_namespace_attach_btt(struct nd_namespace_common *ndns)
 	struct btt *btt;
 	size_t rawsize;
 
-	if (!nd_btt->uuid || !nd_btt->ndns || !nd_btt->lbasize)
+	if (!nd_btt->uuid || !nd_btt->ndns || !nd_btt->lbasize) {
+		dev_dbg(&nd_btt->dev, "incomplete btt configuration\n");
 		return -ENODEV;
+	}
 
 	rawsize = nvdimm_namespace_capacity(ndns) - SZ_4K;
 	if (rawsize < ARENA_MIN_SIZE) {
+		dev_dbg(&nd_btt->dev, "%s must be at least %ld bytes\n",
+				dev_name(&ndns->dev), ARENA_MIN_SIZE + SZ_4K);
 		return -ENXIO;
 	}
 	nd_region = to_nd_region(nd_btt->dev.parent);
@@ -1406,9 +1405,8 @@ int nvdimm_namespace_attach_btt(struct nd_namespace_common *ndns)
 }
 EXPORT_SYMBOL(nvdimm_namespace_attach_btt);
 
-int nvdimm_namespace_detach_btt(struct nd_namespace_common *ndns)
+int nvdimm_namespace_detach_btt(struct nd_btt *nd_btt)
 {
-	struct nd_btt *nd_btt = to_nd_btt(ndns->claim);
 	struct btt *btt = nd_btt->btt;
 
 	btt_fini(btt);

drivers/nvdimm/btt_devs.c

@@ -273,10 +273,10 @@ static int __nd_btt_probe(struct nd_btt *nd_btt,
 	return 0;
 }
 
-int nd_btt_probe(struct nd_namespace_common *ndns, void *drvdata)
+int nd_btt_probe(struct device *dev, struct nd_namespace_common *ndns)
 {
 	int rc;
-	struct device *dev;
+	struct device *btt_dev;
 	struct btt_sb *btt_sb;
 	struct nd_region *nd_region = to_nd_region(ndns->dev.parent);
 
@@ -284,21 +284,19 @@ int nd_btt_probe(struct nd_namespace_common *ndns, void *drvdata)
 		return -ENODEV;
 
 	nvdimm_bus_lock(&ndns->dev);
-	dev = __nd_btt_create(nd_region, 0, NULL, ndns);
+	btt_dev = __nd_btt_create(nd_region, 0, NULL, ndns);
 	nvdimm_bus_unlock(&ndns->dev);
-	if (!dev)
+	if (!btt_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>");
+	btt_sb = devm_kzalloc(dev, sizeof(*btt_sb), GFP_KERNEL);
+	rc = __nd_btt_probe(to_nd_btt(btt_dev), ndns, btt_sb);
+	dev_dbg(dev, "%s: btt: %s\n", __func__,
+			rc == 0 ? dev_name(btt_dev) : "<none>");
 	if (rc < 0) {
-		struct nd_btt *nd_btt = to_nd_btt(dev);
+		struct nd_btt *nd_btt = to_nd_btt(btt_dev);
 
-		__nd_detach_ndns(dev, &nd_btt->ndns);
-		put_device(dev);
+		__nd_detach_ndns(btt_dev, &nd_btt->ndns);
+		put_device(btt_dev);
 	}
 
 	return rc;

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));
 
@@ -122,9 +124,10 @@ static int nvdimm_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 nvdimm_bus *nvdimm_bus = walk_to_nvdimm_bus(dev);
-	int rc;
+	int rc = 0;
 
-	rc = nd_drv->remove(dev);
+	if (nd_drv->remove)
+		rc = nd_drv->remove(dev);
 	nd_region_disable(nvdimm_bus, dev);
 
 	dev_dbg(&nvdimm_bus->dev, "%s.remove(%s) = %d\n", dev->driver->name,
@@ -246,6 +249,8 @@ 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,
@@ -292,8 +297,8 @@ int __nd_driver_register(struct nd_device_driver *nd_drv, struct module *owner,
 		return -EINVAL;
 	}
 
-	if (!nd_drv->probe || !nd_drv->remove) {
-		pr_debug("->probe() and ->remove() must be specified\n");
+	if (!nd_drv->probe) {
+		pr_debug("%s ->probe() must be specified\n", mod_name);
 		return -EINVAL;
 	}
 
@@ -439,6 +444,12 @@ static const struct nd_cmd_desc __nd_cmd_dimm_descs[] = {
 		.out_num = 3,
 		.out_sizes = { 4, 4, UINT_MAX, },
 	},
+	[ND_CMD_CALL] = {
+		.in_num = 2,
+		.in_sizes = { sizeof(struct nd_cmd_pkg), UINT_MAX, },
+		.out_num = 1,
+		.out_sizes = { UINT_MAX, },
+	},
 };
 
 const struct nd_cmd_desc *nd_cmd_dimm_desc(int cmd)
@@ -473,6 +484,12 @@ static const struct nd_cmd_desc __nd_cmd_bus_descs[] = {
 		.out_num = 3,
 		.out_sizes = { 4, 4, 8, },
 	},
+	[ND_CMD_CALL] = {
+		.in_num = 2,
+		.in_sizes = { sizeof(struct nd_cmd_pkg), UINT_MAX, },
+		.out_num = 1,
+		.out_sizes = { UINT_MAX, },
+	},
 };
 
 const struct nd_cmd_desc *nd_cmd_bus_desc(int cmd)
@@ -500,6 +517,10 @@ u32 nd_cmd_in_size(struct nvdimm *nvdimm, int cmd,
 		struct nd_cmd_vendor_hdr *hdr = buf;
 
 		return hdr->in_length;
+	} else if (cmd == ND_CMD_CALL) {
+		struct nd_cmd_pkg *pkg = buf;
+
+		return pkg->nd_size_in;
 	}
 
 	return UINT_MAX;
@@ -522,6 +543,12 @@ u32 nd_cmd_out_size(struct nvdimm *nvdimm, int cmd,
 		return out_field[1];
 	else if (!nvdimm && cmd == ND_CMD_ARS_STATUS && idx == 2)
 		return out_field[1] - 8;
+	else if (cmd == ND_CMD_CALL) {
+		struct nd_cmd_pkg *pkg = (struct nd_cmd_pkg *) in_field;
+
+		return pkg->nd_size_out;
+	}
+
 
 	return UINT_MAX;
 }
@@ -588,25 +615,31 @@ static int __nd_ioctl(struct nvdimm_bus *nvdimm_bus, struct nvdimm *nvdimm,
 	unsigned int cmd = _IOC_NR(ioctl_cmd);
 	void __user *p = (void __user *) arg;
 	struct device *dev = &nvdimm_bus->dev;
+	struct nd_cmd_pkg pkg;
 	const char *cmd_name, *dimm_name;
-	unsigned long dsm_mask;
+	unsigned long cmd_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;
+		cmd_mask = nvdimm->cmd_mask;
 		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;
+		cmd_mask = nd_desc->cmd_mask;
 		dimm_name = "bus";
 	}
 
+	if (cmd == ND_CMD_CALL) {
+		if (copy_from_user(&pkg, p, sizeof(pkg)))
+			return -EFAULT;
+	}
+
 	if (!desc || (desc->out_num + desc->in_num == 0) ||
-			!test_bit(cmd, &dsm_mask))
+			!test_bit(cmd, &cmd_mask))
 		return -ENOTTY;
 
 	/* fail write commands (when read-only) */
@@ -616,6 +649,7 @@ static int __nd_ioctl(struct nvdimm_bus *nvdimm_bus, struct nvdimm *nvdimm,
 		case ND_CMD_SET_CONFIG_DATA:
 		case ND_CMD_ARS_START:
 		case ND_CMD_CLEAR_ERROR:
+		case ND_CMD_CALL:
 			dev_dbg(&nvdimm_bus->dev, "'%s' command while read-only.\n",
 					nvdimm ? nvdimm_cmd_name(cmd)
 					: nvdimm_bus_cmd_name(cmd));
@@ -643,6 +677,16 @@ static int __nd_ioctl(struct nvdimm_bus *nvdimm_bus, struct nvdimm *nvdimm,
 		in_len += in_size;
 	}
 
+	if (cmd == ND_CMD_CALL) {
+		dev_dbg(dev, "%s:%s, idx: %llu, in: %zu, out: %zu, len %zu\n",
+				__func__, dimm_name, pkg.nd_command,
+				in_len, out_len, buf_len);
+
+		for (i = 0; i < ARRAY_SIZE(pkg.nd_reserved2); i++)
+			if (pkg.nd_reserved2[i])
+				return -EINVAL;
+	}
+
 	/* process an output envelope */
 	for (i = 0; i < desc->out_num; i++) {
 		u32 out_size = nd_cmd_out_size(nvdimm, cmd, desc, i,
@@ -783,6 +827,9 @@ int __init nvdimm_bus_init(void)
 {
 	int rc;
 
+	BUILD_BUG_ON(sizeof(struct nd_smart_payload) != 128);
+	BUILD_BUG_ON(sizeof(struct nd_smart_threshold_payload) != 8);
+
 	rc = bus_register(&nvdimm_bus_type);
 	if (rc)
 		return rc;

drivers/nvdimm/claim.c

@@ -12,6 +12,7 @@
  */
 #include <linux/device.h>
 #include <linux/sizes.h>
+#include <linux/pmem.h>
 #include "nd-core.h"
 #include "pfn.h"
 #include "btt.h"
@@ -84,12 +85,33 @@ 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;
 	return true;
 }
 
+struct nd_pfn *to_nd_pfn_safe(struct device *dev)
+{
+	/*
+	 * pfn device attributes are re-used by dax device instances, so we
+	 * need to be careful to correct device-to-nd_pfn conversion.
+	 */
+	if (is_nd_pfn(dev))
+		return to_nd_pfn(dev);
+
+	if (is_nd_dax(dev)) {
+		struct nd_dax *nd_dax = to_nd_dax(dev);
+
+		return &nd_dax->nd_pfn;
+	}
+
+	WARN_ON(1);
+	return NULL;
+}
+
 static void nd_detach_and_reset(struct device *dev,
 		struct nd_namespace_common **_ndns)
 {
@@ -103,8 +125,8 @@ static void nd_detach_and_reset(struct device *dev,
 		nd_btt->lbasize = 0;
 		kfree(nd_btt->uuid);
 		nd_btt->uuid = NULL;
-	} else if (is_nd_pfn(dev)) {
-		struct nd_pfn *nd_pfn = to_nd_pfn(dev);
+	} else if (is_nd_pfn(dev) || is_nd_dax(dev)) {
+		struct nd_pfn *nd_pfn = to_nd_pfn_safe(dev);
 
 		kfree(nd_pfn->uuid);
 		nd_pfn->uuid = NULL;
@@ -199,3 +221,63 @@ u64 nd_sb_checksum(struct nd_gen_sb *nd_gen_sb)
 	return sum;
 }
 EXPORT_SYMBOL(nd_sb_checksum);
+
+static int nsio_rw_bytes(struct nd_namespace_common *ndns,
+		resource_size_t offset, void *buf, size_t size, int rw)
+{
+	struct nd_namespace_io *nsio = to_nd_namespace_io(&ndns->dev);
+
+	if (unlikely(offset + size > nsio->size)) {
+		dev_WARN_ONCE(&ndns->dev, 1, "request out of range\n");
+		return -EFAULT;
+	}
+
+	if (rw == READ) {
+		unsigned int sz_align = ALIGN(size + (offset & (512 - 1)), 512);
+
+		if (unlikely(is_bad_pmem(&nsio->bb, offset / 512, sz_align)))
+			return -EIO;
+		return memcpy_from_pmem(buf, nsio->addr + offset, size);
+	} else {
+		memcpy_to_pmem(nsio->addr + offset, buf, size);
+		wmb_pmem();
+	}
+
+	return 0;
+}
+
+int devm_nsio_enable(struct device *dev, struct nd_namespace_io *nsio)
+{
+	struct resource *res = &nsio->res;
+	struct nd_namespace_common *ndns = &nsio->common;
+
+	nsio->size = resource_size(res);
+	if (!devm_request_mem_region(dev, res->start, resource_size(res),
+				dev_name(dev))) {
+		dev_warn(dev, "could not reserve region %pR\n", res);
+		return -EBUSY;
+	}
+
+	ndns->rw_bytes = nsio_rw_bytes;
+	if (devm_init_badblocks(dev, &nsio->bb))
+		return -ENOMEM;
+	nvdimm_badblocks_populate(to_nd_region(ndns->dev.parent), &nsio->bb,
+			&nsio->res);
+
+	nsio->addr = devm_memremap(dev, res->start, resource_size(res),
+			ARCH_MEMREMAP_PMEM);
+	if (IS_ERR(nsio->addr))
+		return PTR_ERR(nsio->addr);
+	return 0;
+}
+EXPORT_SYMBOL_GPL(devm_nsio_enable);
+
+void devm_nsio_disable(struct device *dev, struct nd_namespace_io *nsio)
+{
+	struct resource *res = &nsio->res;
+
+	devm_memunmap(dev, nsio->addr);
+	devm_exit_badblocks(dev, &nsio->bb);
+	devm_release_mem_region(dev, res->start, resource_size(res));
+}
+EXPORT_SYMBOL_GPL(devm_nsio_disable);

drivers/nvdimm/core.c

@@ -251,7 +251,7 @@ static ssize_t commands_show(struct device *dev,
 	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)
+	for_each_set_bit(cmd, &nd_desc->cmd_mask, BITS_PER_LONG)
 		len += sprintf(buf + len, "%s ", nvdimm_bus_cmd_name(cmd));
 	len += sprintf(buf + len, "\n");
 	return len;
@@ -648,6 +648,9 @@ static __exit void libnvdimm_exit(void)
 	nd_region_exit();
 	nvdimm_exit();
 	nvdimm_bus_exit();
+	nd_region_devs_exit();
+	nvdimm_devs_exit();
+	ida_destroy(&nd_ida);
 }
 
 MODULE_LICENSE("GPL v2");

drivers/nvdimm/dax_devs.c

@@ -0,0 +1,134 @@
+/*
+ * 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 "pfn.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;
+}
+
+int nd_dax_probe(struct device *dev, struct nd_namespace_common *ndns)
+{
+	int rc;
+	struct nd_dax *nd_dax;
+	struct device *dax_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);
+	nd_dax = nd_dax_alloc(nd_region);
+	nd_pfn = &nd_dax->nd_pfn;
+	dax_dev = nd_pfn_devinit(nd_pfn, ndns);
+	nvdimm_bus_unlock(&ndns->dev);
+	if (!dax_dev)
+		return -ENOMEM;
+	pfn_sb = devm_kzalloc(dev, sizeof(*pfn_sb), GFP_KERNEL);
+	nd_pfn->pfn_sb = pfn_sb;
+	rc = nd_pfn_validate(nd_pfn, DAX_SIG);
+	dev_dbg(dev, "%s: dax: %s\n", __func__,
+			rc == 0 ? dev_name(dax_dev) : "<none>");
+	if (rc < 0) {
+		__nd_detach_ndns(dax_dev, &nd_pfn->ndns);
+		put_device(dax_dev);
+	} else
+		__nd_device_register(dax_dev);
+
+	return rc;
+}
+EXPORT_SYMBOL(nd_dax_probe);

drivers/nvdimm/dimm_devs.c

@@ -37,9 +37,9 @@ static int __validate_dimm(struct nvdimm_drvdata *ndd)
 
 	nvdimm = to_nvdimm(ndd->dev);
 
-	if (!nvdimm->dsm_mask)
+	if (!nvdimm->cmd_mask)
 		return -ENXIO;
-	if (!test_bit(ND_CMD_GET_CONFIG_DATA, nvdimm->dsm_mask))
+	if (!test_bit(ND_CMD_GET_CONFIG_DATA, &nvdimm->cmd_mask))
 		return -ENXIO;
 
 	return 0;
@@ -263,6 +263,12 @@ const char *nvdimm_name(struct nvdimm *nvdimm)
 }
 EXPORT_SYMBOL_GPL(nvdimm_name);
 
+unsigned long nvdimm_cmd_mask(struct nvdimm *nvdimm)
+{
+	return nvdimm->cmd_mask;
+}
+EXPORT_SYMBOL_GPL(nvdimm_cmd_mask);
+
 void *nvdimm_provider_data(struct nvdimm *nvdimm)
 {
 	if (nvdimm)
@@ -277,10 +283,10 @@ static ssize_t commands_show(struct device *dev,
 	struct nvdimm *nvdimm = to_nvdimm(dev);
 	int cmd, len = 0;
 
-	if (!nvdimm->dsm_mask)
+	if (!nvdimm->cmd_mask)
 		return sprintf(buf, "\n");
 
-	for_each_set_bit(cmd, nvdimm->dsm_mask, BITS_PER_LONG)
+	for_each_set_bit(cmd, &nvdimm->cmd_mask, BITS_PER_LONG)
 		len += sprintf(buf + len, "%s ", nvdimm_cmd_name(cmd));
 	len += sprintf(buf + len, "\n");
 	return len;
@@ -340,7 +346,7 @@ 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,
-		unsigned long *dsm_mask)
+		unsigned long cmd_mask)
 {
 	struct nvdimm *nvdimm = kzalloc(sizeof(*nvdimm), GFP_KERNEL);
 	struct device *dev;
@@ -355,7 +361,7 @@ 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;
+	nvdimm->cmd_mask = cmd_mask;
 	atomic_set(&nvdimm->busy, 0);
 	dev = &nvdimm->dev;
 	dev_set_name(dev, "nmem%d", nvdimm->id);
@@ -546,3 +552,8 @@ int nvdimm_bus_check_dimm_count(struct nvdimm_bus *nvdimm_bus, int dimm_count)
 	return 0;
 }
 EXPORT_SYMBOL_GPL(nvdimm_bus_check_dimm_count);
+
+void __exit nvdimm_devs_exit(void)
+{
+	ida_destroy(&dimm_ida);
+}

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
@@ -1379,21 +1381,19 @@ 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_namespace_common *ndns;
+	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) {
-		struct device *host = NULL;
-
-		if (nd_btt) {
-			host = &nd_btt->dev;
+	if (nd_btt || nd_pfn || nd_dax) {
+		if (nd_btt)
 			ndns = nd_btt->ndns;
-		} else if (nd_pfn) {
-			host = &nd_pfn->dev;
+		else if (nd_pfn)
 			ndns = nd_pfn->ndns;
-		}
+		else if (nd_dax)
+			ndns = nd_dax->nd_pfn.ndns;
 
-		if (!ndns || !host)
+		if (!ndns)
 			return ERR_PTR(-ENODEV);
 
 		/*
@@ -1404,12 +1404,12 @@ struct nd_namespace_common *nvdimm_namespace_common_probe(struct device *dev)
 		device_unlock(&ndns->dev);
 		if (ndns->dev.driver) {
 			dev_dbg(&ndns->dev, "is active, can't bind %s\n",
-					dev_name(host));
+					dev_name(dev));
 			return ERR_PTR(-EBUSY);
 		}
-		if (dev_WARN_ONCE(&ndns->dev, ndns->claim != host,
+		if (dev_WARN_ONCE(&ndns->dev, ndns->claim != dev,
 					"host (%s) vs claim (%s) mismatch\n",
-					dev_name(host),
+					dev_name(dev),
 					dev_name(ndns->claim)))
 			return ERR_PTR(-ENXIO);
 	} else {
@@ -1784,6 +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

@@ -37,7 +37,7 @@ struct nvdimm_bus {
 struct nvdimm {
 	unsigned long flags;
 	void *provider_data;
-	unsigned long *dsm_mask;
+	unsigned long cmd_mask;
 	struct device dev;
 	atomic_t busy;
 	int id;
@@ -49,11 +49,14 @@ bool is_nd_blk(struct device *dev);
 struct nvdimm_bus *walk_to_nvdimm_bus(struct device *nd_dev);
 int __init nvdimm_bus_init(void);
 void nvdimm_bus_exit(void);
+void nvdimm_devs_exit(void);
+void nd_region_devs_exit(void);
 void nd_region_probe_success(struct nvdimm_bus *nvdimm_bus, struct device *dev);
 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);
@@ -91,4 +94,5 @@ bool __nd_attach_ndns(struct device *dev, struct nd_namespace_common *attach,
 ssize_t nd_namespace_store(struct device *dev,
 		struct nd_namespace_common **_ndns, const char *buf,
 		size_t len);
+struct nd_pfn *to_nd_pfn_safe(struct device *dev);
 #endif /* __ND_CORE_H__ */

drivers/nvdimm/nd.h

@@ -13,6 +13,7 @@
 #ifndef __ND_H__
 #define __ND_H__
 #include <linux/libnvdimm.h>
+#include <linux/badblocks.h>
 #include <linux/blkdev.h>
 #include <linux/device.h>
 #include <linux/mutex.h>
@@ -100,10 +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;
@@ -160,6 +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,
@@ -197,11 +204,12 @@ struct nd_gen_sb {
 
 u64 nd_sb_checksum(struct nd_gen_sb *sb);
 #if IS_ENABLED(CONFIG_BTT)
-int nd_btt_probe(struct nd_namespace_common *ndns, void *drvdata);
+int nd_btt_probe(struct device *dev, struct nd_namespace_common *ndns);
 bool is_nd_btt(struct device *dev);
 struct device *nd_btt_create(struct nd_region *nd_region);
 #else
-static inline int nd_btt_probe(struct nd_namespace_common *ndns, void *drvdata)
+static inline int nd_btt_probe(struct device *dev,
+		struct nd_namespace_common *ndns)
 {
 	return -ENODEV;
 }
@@ -219,12 +227,16 @@ static inline struct device *nd_btt_create(struct nd_region *nd_region)
 
 struct nd_pfn *to_nd_pfn(struct device *dev);
 #if IS_ENABLED(CONFIG_NVDIMM_PFN)
-int nd_pfn_probe(struct nd_namespace_common *ndns, void *drvdata);
+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);
-int nd_pfn_validate(struct nd_pfn *nd_pfn);
+struct device *nd_pfn_devinit(struct nd_pfn *nd_pfn,
+		struct nd_namespace_common *ndns);
+int nd_pfn_validate(struct nd_pfn *nd_pfn, const char *sig);
+extern struct attribute_group nd_pfn_attribute_group;
 #else
-static inline int nd_pfn_probe(struct nd_namespace_common *ndns, void *drvdata)
+static inline int nd_pfn_probe(struct device *dev,
+		struct nd_namespace_common *ndns)
 {
 	return -ENODEV;
 }
@@ -239,12 +251,35 @@ static inline struct device *nd_pfn_create(struct nd_region *nd_region)
 	return NULL;
 }
 
-static inline int nd_pfn_validate(struct nd_pfn *nd_pfn)
+static inline int nd_pfn_validate(struct nd_pfn *nd_pfn, const char *sig)
 {
 	return -ENODEV;
 }
 #endif
 
+struct nd_dax *to_nd_dax(struct device *dev);
+#if IS_ENABLED(CONFIG_NVDIMM_DAX)
+int nd_dax_probe(struct device *dev, struct nd_namespace_common *ndns);
+bool is_nd_dax(struct device *dev);
+struct device *nd_dax_create(struct nd_region *nd_region);
+#else
+static inline int nd_dax_probe(struct device *dev,
+		struct nd_namespace_common *ndns)
+{
+	return -ENODEV;
+}
+
+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);
@@ -263,11 +298,32 @@ struct resource *nvdimm_allocate_dpa(struct nvdimm_drvdata *ndd,
 resource_size_t nvdimm_namespace_capacity(struct nd_namespace_common *ndns);
 struct nd_namespace_common *nvdimm_namespace_common_probe(struct device *dev);
 int nvdimm_namespace_attach_btt(struct nd_namespace_common *ndns);
-int nvdimm_namespace_detach_btt(struct nd_namespace_common *ndns);
+int nvdimm_namespace_detach_btt(struct nd_btt *nd_btt);
 const char *nvdimm_namespace_disk_name(struct nd_namespace_common *ndns,
 		char *name);
 void nvdimm_badblocks_populate(struct nd_region *nd_region,
 		struct badblocks *bb, const struct resource *res);
+#if IS_ENABLED(CONFIG_ND_CLAIM)
+struct vmem_altmap *nvdimm_setup_pfn(struct nd_pfn *nd_pfn,
+		struct resource *res, struct vmem_altmap *altmap);
+int devm_nsio_enable(struct device *dev, struct nd_namespace_io *nsio);
+void devm_nsio_disable(struct device *dev, struct nd_namespace_io *nsio);
+#else
+static inline struct vmem_altmap *nvdimm_setup_pfn(struct nd_pfn *nd_pfn,
+		struct resource *res, struct vmem_altmap *altmap)
+{
+	return ERR_PTR(-ENXIO);
+}
+static inline int devm_nsio_enable(struct device *dev,
+		struct nd_namespace_io *nsio)
+{
+	return -ENXIO;
+}
+static inline void devm_nsio_disable(struct device *dev,
+		struct nd_namespace_io *nsio)
+{
+}
+#endif
 int nd_blk_region_init(struct nd_region *nd_region);
 void __nd_iostat_start(struct bio *bio, unsigned long *start);
 static inline bool nd_iostat_start(struct bio *bio, unsigned long *start)
@@ -281,6 +337,19 @@ static inline bool nd_iostat_start(struct bio *bio, unsigned long *start)
 	return true;
 }
 void nd_iostat_end(struct bio *bio, unsigned long start);
+static inline bool is_bad_pmem(struct badblocks *bb, sector_t sector,
+		unsigned int len)
+{
+	if (bb->count) {
+		sector_t first_bad;
+		int num_bad;
+
+		return !!badblocks_check(bb, sector, len / 512, &first_bad,
+				&num_bad);
+	}
+
+	return false;
+}
 resource_size_t nd_namespace_blk_validate(struct nd_namespace_blk *nsblk);
 const u8 *nd_dev_to_uuid(struct device *dev);
 bool pmem_should_map_pages(struct device *dev);

drivers/nvdimm/pfn.h

@@ -19,6 +19,7 @@
 
 #define PFN_SIG_LEN 16
 #define PFN_SIG "NVDIMM_PFN_INFO\0"
+#define DAX_SIG "NVDIMM_DAX_INFO\0"
 
 struct nd_pfn_sb {
 	u8 signature[PFN_SIG_LEN];
@@ -33,7 +34,9 @@ struct nd_pfn_sb {
 	/* minor-version-1 additions for section alignment */
 	__le32 start_pad;
 	__le32 end_trunc;
-	u8 padding[4004];
+	/* minor-version-2 record the base alignment of the mapping */
+	__le32 align;
+	u8 padding[4000];
 	__le64 checksum;
 };
 

drivers/nvdimm/pfn_devs.c

@@ -1,5 +1,5 @@
 /*
- * Copyright(c) 2013-2015 Intel Corporation. All rights reserved.
+ * 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
@@ -10,6 +10,7 @@
  * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
  * General Public License for more details.
  */
+#include <linux/memremap.h>
 #include <linux/blkdev.h>
 #include <linux/device.h>
 #include <linux/genhd.h>
@@ -56,7 +57,7 @@ EXPORT_SYMBOL(to_nd_pfn);
 static ssize_t mode_show(struct device *dev,
 		struct device_attribute *attr, char *buf)
 {
-	struct nd_pfn *nd_pfn = to_nd_pfn(dev);
+	struct nd_pfn *nd_pfn = to_nd_pfn_safe(dev);
 
 	switch (nd_pfn->mode) {
 	case PFN_MODE_RAM:
@@ -71,7 +72,7 @@ static ssize_t mode_show(struct device *dev,
 static ssize_t mode_store(struct device *dev,
 		struct device_attribute *attr, const char *buf, size_t len)
 {
-	struct nd_pfn *nd_pfn = to_nd_pfn(dev);
+	struct nd_pfn *nd_pfn = to_nd_pfn_safe(dev);
 	ssize_t rc = 0;
 
 	device_lock(dev);
@@ -105,7 +106,7 @@ static DEVICE_ATTR_RW(mode);
 static ssize_t align_show(struct device *dev,
 		struct device_attribute *attr, char *buf)
 {
-	struct nd_pfn *nd_pfn = to_nd_pfn(dev);
+	struct nd_pfn *nd_pfn = to_nd_pfn_safe(dev);
 
 	return sprintf(buf, "%lx\n", nd_pfn->align);
 }
@@ -133,7 +134,7 @@ static ssize_t __align_store(struct nd_pfn *nd_pfn, const char *buf)
 static ssize_t align_store(struct device *dev,
 		struct device_attribute *attr, const char *buf, size_t len)
 {
-	struct nd_pfn *nd_pfn = to_nd_pfn(dev);
+	struct nd_pfn *nd_pfn = to_nd_pfn_safe(dev);
 	ssize_t rc;
 
 	device_lock(dev);
@@ -151,7 +152,7 @@ static DEVICE_ATTR_RW(align);
 static ssize_t uuid_show(struct device *dev,
 		struct device_attribute *attr, char *buf)
 {
-	struct nd_pfn *nd_pfn = to_nd_pfn(dev);
+	struct nd_pfn *nd_pfn = to_nd_pfn_safe(dev);
 
 	if (nd_pfn->uuid)
 		return sprintf(buf, "%pUb\n", nd_pfn->uuid);
@@ -161,7 +162,7 @@ static ssize_t uuid_show(struct device *dev,
 static ssize_t uuid_store(struct device *dev,
 		struct device_attribute *attr, const char *buf, size_t len)
 {
-	struct nd_pfn *nd_pfn = to_nd_pfn(dev);
+	struct nd_pfn *nd_pfn = to_nd_pfn_safe(dev);
 	ssize_t rc;
 
 	device_lock(dev);
@@ -177,7 +178,7 @@ static DEVICE_ATTR_RW(uuid);
 static ssize_t namespace_show(struct device *dev,
 		struct device_attribute *attr, char *buf)
 {
-	struct nd_pfn *nd_pfn = to_nd_pfn(dev);
+	struct nd_pfn *nd_pfn = to_nd_pfn_safe(dev);
 	ssize_t rc;
 
 	nvdimm_bus_lock(dev);
@@ -190,7 +191,7 @@ static ssize_t namespace_show(struct device *dev,
 static ssize_t namespace_store(struct device *dev,
 		struct device_attribute *attr, const char *buf, size_t len)
 {
-	struct nd_pfn *nd_pfn = to_nd_pfn(dev);
+	struct nd_pfn *nd_pfn = to_nd_pfn_safe(dev);
 	ssize_t rc;
 
 	device_lock(dev);
@@ -208,7 +209,7 @@ static DEVICE_ATTR_RW(namespace);
 static ssize_t resource_show(struct device *dev,
 		struct device_attribute *attr, char *buf)
 {
-	struct nd_pfn *nd_pfn = to_nd_pfn(dev);
+	struct nd_pfn *nd_pfn = to_nd_pfn_safe(dev);
 	ssize_t rc;
 
 	device_lock(dev);
@@ -234,7 +235,7 @@ static DEVICE_ATTR_RO(resource);
 static ssize_t size_show(struct device *dev,
 		struct device_attribute *attr, char *buf)
 {
-	struct nd_pfn *nd_pfn = to_nd_pfn(dev);
+	struct nd_pfn *nd_pfn = to_nd_pfn_safe(dev);
 	ssize_t rc;
 
 	device_lock(dev);
@@ -269,7 +270,7 @@ static struct attribute *nd_pfn_attributes[] = {
 	NULL,
 };
 
-static struct attribute_group nd_pfn_attribute_group = {
+struct attribute_group nd_pfn_attribute_group = {
 	.attrs = nd_pfn_attributes,
 };
 
@@ -280,15 +281,31 @@ static const struct attribute_group *nd_pfn_attribute_groups[] = {
 	NULL,
 };
 
-static 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)
 {
-	struct nd_pfn *nd_pfn;
-	struct device *dev;
+	struct device *dev = &nd_pfn->dev;
 
-	/* we can only create pages for contiguous ranged of pmem */
-	if (!is_nd_pmem(&nd_region->dev))
+	if (!nd_pfn)
+		return NULL;
+
+	nd_pfn->mode = PFN_MODE_NONE;
+	nd_pfn->align = HPAGE_SIZE;
+	dev = &nd_pfn->dev;
+	device_initialize(&nd_pfn->dev);
+	if (ndns && !__nd_attach_ndns(&nd_pfn->dev, ndns, &nd_pfn->ndns)) {
+		dev_dbg(&ndns->dev, "%s failed, already claimed by %s\n",
+				__func__, dev_name(ndns->claim));
+		put_device(dev);
 		return NULL;
+	}
+	return dev;
+}
+
+static struct nd_pfn *nd_pfn_alloc(struct nd_region *nd_region)
+{
+	struct nd_pfn *nd_pfn;
+	struct device *dev;
 
 	nd_pfn = kzalloc(sizeof(*nd_pfn), GFP_KERNEL);
 	if (!nd_pfn)
@@ -300,33 +317,31 @@ static struct device *__nd_pfn_create(struct nd_region *nd_region,
 		return NULL;
 	}
 
-	nd_pfn->mode = PFN_MODE_NONE;
-	nd_pfn->align = HPAGE_SIZE;
 	dev = &nd_pfn->dev;
 	dev_set_name(dev, "pfn%d.%d", nd_region->id, nd_pfn->id);
-	dev->parent = &nd_region->dev;
-	dev->type = &nd_pfn_device_type;
 	dev->groups = nd_pfn_attribute_groups;
-	device_initialize(&nd_pfn->dev);
-	if (ndns && !__nd_attach_ndns(&nd_pfn->dev, ndns, &nd_pfn->ndns)) {
-		dev_dbg(&ndns->dev, "%s failed, already claimed by %s\n",
-				__func__, dev_name(ndns->claim));
-		put_device(dev);
-		return NULL;
-	}
-	return dev;
+	dev->type = &nd_pfn_device_type;
+	dev->parent = &nd_region->dev;
+
+	return nd_pfn;
 }
 
 struct device *nd_pfn_create(struct nd_region *nd_region)
 {
-	struct device *dev = __nd_pfn_create(nd_region, NULL);
+	struct nd_pfn *nd_pfn;
+	struct device *dev;
+
+	if (!is_nd_pmem(&nd_region->dev))
+		return NULL;
+
+	nd_pfn = nd_pfn_alloc(nd_region);
+	dev = nd_pfn_devinit(nd_pfn, NULL);
 
-	if (dev)
-		__nd_device_register(dev);
+	__nd_device_register(dev);
 	return dev;
 }
 
-int nd_pfn_validate(struct nd_pfn *nd_pfn)
+int nd_pfn_validate(struct nd_pfn *nd_pfn, const char *sig)
 {
 	u64 checksum, offset;
 	struct nd_namespace_io *nsio;
@@ -343,7 +358,7 @@ int nd_pfn_validate(struct nd_pfn *nd_pfn)
 	if (nvdimm_read_bytes(ndns, SZ_4K, pfn_sb, sizeof(*pfn_sb)))
 		return -ENXIO;
 
-	if (memcmp(pfn_sb->signature, PFN_SIG, PFN_SIG_LEN) != 0)
+	if (memcmp(pfn_sb->signature, sig, PFN_SIG_LEN) != 0)
 		return -ENODEV;
 
 	checksum = le64_to_cpu(pfn_sb->checksum);
@@ -360,6 +375,9 @@ int nd_pfn_validate(struct nd_pfn *nd_pfn)
 		pfn_sb->end_trunc = 0;
 	}
 
+	if (__le16_to_cpu(pfn_sb->version_minor) < 2)
+		pfn_sb->align = 0;
+
 	switch (le32_to_cpu(pfn_sb->mode)) {
 	case PFN_MODE_RAM:
 	case PFN_MODE_PMEM:
@@ -379,6 +397,8 @@ int nd_pfn_validate(struct nd_pfn *nd_pfn)
 			return -ENODEV;
 	}
 
+	if (nd_pfn->align == 0)
+		nd_pfn->align = le32_to_cpu(pfn_sb->align);
 	if (nd_pfn->align > nvdimm_namespace_capacity(ndns)) {
 		dev_err(&nd_pfn->dev, "alignment: %lx exceeds capacity %llx\n",
 				nd_pfn->align, nvdimm_namespace_capacity(ndns));
@@ -399,8 +419,8 @@ int nd_pfn_validate(struct nd_pfn *nd_pfn)
 		return -EBUSY;
 	}
 
-	nd_pfn->align = 1UL << ilog2(offset);
-	if (!is_power_of_2(offset) || offset < PAGE_SIZE) {
+	if ((nd_pfn->align && !IS_ALIGNED(offset, nd_pfn->align))
+			|| !IS_ALIGNED(offset, PAGE_SIZE)) {
 		dev_err(&nd_pfn->dev, "bad offset: %#llx dax disabled\n",
 				offset);
 		return -ENXIO;
@@ -410,11 +430,11 @@ int nd_pfn_validate(struct nd_pfn *nd_pfn)
 }
 EXPORT_SYMBOL(nd_pfn_validate);
 
-int nd_pfn_probe(struct nd_namespace_common *ndns, void *drvdata)
+int nd_pfn_probe(struct device *dev, struct nd_namespace_common *ndns)
 {
 	int rc;
-	struct device *dev;
 	struct nd_pfn *nd_pfn;
+	struct device *pfn_dev;
 	struct nd_pfn_sb *pfn_sb;
 	struct nd_region *nd_region = to_nd_region(ndns->dev.parent);
 
@@ -422,25 +442,218 @@ int nd_pfn_probe(struct nd_namespace_common *ndns, void *drvdata)
 		return -ENODEV;
 
 	nvdimm_bus_lock(&ndns->dev);
-	dev = __nd_pfn_create(nd_region, ndns);
+	nd_pfn = nd_pfn_alloc(nd_region);
+	pfn_dev = nd_pfn_devinit(nd_pfn, ndns);
 	nvdimm_bus_unlock(&ndns->dev);
-	if (!dev)
+	if (!pfn_dev)
 		return -ENOMEM;
-	dev_set_drvdata(dev, drvdata);
-	pfn_sb = kzalloc(sizeof(*pfn_sb), GFP_KERNEL);
-	nd_pfn = to_nd_pfn(dev);
+	pfn_sb = devm_kzalloc(dev, sizeof(*pfn_sb), GFP_KERNEL);
+	nd_pfn = to_nd_pfn(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>");
+	rc = nd_pfn_validate(nd_pfn, PFN_SIG);
+	dev_dbg(dev, "%s: pfn: %s\n", __func__,
+			rc == 0 ? dev_name(pfn_dev) : "<none>");
 	if (rc < 0) {
-		__nd_detach_ndns(dev, &nd_pfn->ndns);
-		put_device(dev);
+		__nd_detach_ndns(pfn_dev, &nd_pfn->ndns);
+		put_device(pfn_dev);
 	} else
-		__nd_device_register(&nd_pfn->dev);
+		__nd_device_register(pfn_dev);
 
 	return rc;
 }
 EXPORT_SYMBOL(nd_pfn_probe);
+
+/*
+ * We hotplug memory at section granularity, pad the reserved area from
+ * the previous section base to the namespace base address.
+ */
+static unsigned long init_altmap_base(resource_size_t base)
+{
+	unsigned long base_pfn = PHYS_PFN(base);
+
+	return PFN_SECTION_ALIGN_DOWN(base_pfn);
+}
+
+static unsigned long init_altmap_reserve(resource_size_t base)
+{
+	unsigned long reserve = PHYS_PFN(SZ_8K);
+	unsigned long base_pfn = PHYS_PFN(base);
+
+	reserve += base_pfn - PFN_SECTION_ALIGN_DOWN(base_pfn);
+	return reserve;
+}
+
+static struct vmem_altmap *__nvdimm_setup_pfn(struct nd_pfn *nd_pfn,
+		struct resource *res, struct vmem_altmap *altmap)
+{
+	struct nd_pfn_sb *pfn_sb = nd_pfn->pfn_sb;
+	u64 offset = le64_to_cpu(pfn_sb->dataoff);
+	u32 start_pad = __le32_to_cpu(pfn_sb->start_pad);
+	u32 end_trunc = __le32_to_cpu(pfn_sb->end_trunc);
+	struct nd_namespace_common *ndns = nd_pfn->ndns;
+	struct nd_namespace_io *nsio = to_nd_namespace_io(&ndns->dev);
+	resource_size_t base = nsio->res.start + start_pad;
+	struct vmem_altmap __altmap = {
+		.base_pfn = init_altmap_base(base),
+		.reserve = init_altmap_reserve(base),
+	};
+
+	memcpy(res, &nsio->res, sizeof(*res));
+	res->start += start_pad;
+	res->end -= end_trunc;
+
+	nd_pfn->mode = le32_to_cpu(nd_pfn->pfn_sb->mode);
+	if (nd_pfn->mode == PFN_MODE_RAM) {
+		if (offset < SZ_8K)
+			return ERR_PTR(-EINVAL);
+		nd_pfn->npfns = le64_to_cpu(pfn_sb->npfns);
+		altmap = NULL;
+	} else if (nd_pfn->mode == PFN_MODE_PMEM) {
+		nd_pfn->npfns = (resource_size(res) - offset) / PAGE_SIZE;
+		if (le64_to_cpu(nd_pfn->pfn_sb->npfns) > nd_pfn->npfns)
+			dev_info(&nd_pfn->dev,
+					"number of pfns truncated from %lld to %ld\n",
+					le64_to_cpu(nd_pfn->pfn_sb->npfns),
+					nd_pfn->npfns);
+		memcpy(altmap, &__altmap, sizeof(*altmap));
+		altmap->free = PHYS_PFN(offset - SZ_8K);
+		altmap->alloc = 0;
+	} else
+		return ERR_PTR(-ENXIO);
+
+	return altmap;
+}
+
+static int nd_pfn_init(struct nd_pfn *nd_pfn)
+{
+	u32 dax_label_reserve = is_nd_dax(&nd_pfn->dev) ? SZ_128K : 0;
+	struct nd_namespace_common *ndns = nd_pfn->ndns;
+	u32 start_pad = 0, end_trunc = 0;
+	resource_size_t start, size;
+	struct nd_namespace_io *nsio;
+	struct nd_region *nd_region;
+	struct nd_pfn_sb *pfn_sb;
+	unsigned long npfns;
+	phys_addr_t offset;
+	const char *sig;
+	u64 checksum;
+	int rc;
+
+	pfn_sb = devm_kzalloc(&nd_pfn->dev, sizeof(*pfn_sb), GFP_KERNEL);
+	if (!pfn_sb)
+		return -ENOMEM;
+
+	nd_pfn->pfn_sb = pfn_sb;
+	if (is_nd_dax(&nd_pfn->dev))
+		sig = DAX_SIG;
+	else
+		sig = PFN_SIG;
+	rc = nd_pfn_validate(nd_pfn, sig);
+	if (rc != -ENODEV)
+		return rc;
+
+	/* no info block, do init */;
+	nd_region = to_nd_region(nd_pfn->dev.parent);
+	if (nd_region->ro) {
+		dev_info(&nd_pfn->dev,
+				"%s is read-only, unable to init metadata\n",
+				dev_name(&nd_region->dev));
+		return -ENXIO;
+	}
+
+	memset(pfn_sb, 0, sizeof(*pfn_sb));
+
+	/*
+	 * Check if pmem collides with 'System RAM' when section aligned and
+	 * trim it accordingly
+	 */
+	nsio = to_nd_namespace_io(&ndns->dev);
+	start = PHYS_SECTION_ALIGN_DOWN(nsio->res.start);
+	size = resource_size(&nsio->res);
+	if (region_intersects(start, size, IORESOURCE_SYSTEM_RAM,
+				IORES_DESC_NONE) == REGION_MIXED) {
+		start = nsio->res.start;
+		start_pad = PHYS_SECTION_ALIGN_UP(start) - start;
+	}
+
+	start = nsio->res.start;
+	size = PHYS_SECTION_ALIGN_UP(start + size) - start;
+	if (region_intersects(start, size, IORESOURCE_SYSTEM_RAM,
+				IORES_DESC_NONE) == REGION_MIXED) {
+		size = resource_size(&nsio->res);
+		end_trunc = start + size - PHYS_SECTION_ALIGN_DOWN(start + size);
+	}
+
+	if (start_pad + end_trunc)
+		dev_info(&nd_pfn->dev, "%s section collision, truncate %d bytes\n",
+				dev_name(&ndns->dev), start_pad + end_trunc);
+
+	/*
+	 * Note, we use 64 here for the standard size of struct page,
+	 * debugging options may cause it to be larger in which case the
+	 * implementation will limit the pfns advertised through
+	 * ->direct_access() to those that are included in the memmap.
+	 */
+	start += start_pad;
+	size = resource_size(&nsio->res);
+	npfns = (size - start_pad - end_trunc - SZ_8K) / SZ_4K;
+	if (nd_pfn->mode == PFN_MODE_PMEM) {
+		unsigned long memmap_size;
+
+		/*
+		 * vmemmap_populate_hugepages() allocates the memmap array in
+		 * HPAGE_SIZE chunks.
+		 */
+		memmap_size = ALIGN(64 * npfns, HPAGE_SIZE);
+		offset = ALIGN(start + SZ_8K + memmap_size + dax_label_reserve,
+				nd_pfn->align) - start;
+	} else if (nd_pfn->mode == PFN_MODE_RAM)
+		offset = ALIGN(start + SZ_8K + dax_label_reserve,
+				nd_pfn->align) - start;
+	else
+		return -ENXIO;
+
+	if (offset + start_pad + end_trunc >= size) {
+		dev_err(&nd_pfn->dev, "%s unable to satisfy requested alignment\n",
+				dev_name(&ndns->dev));
+		return -ENXIO;
+	}
+
+	npfns = (size - offset - start_pad - end_trunc) / SZ_4K;
+	pfn_sb->mode = cpu_to_le32(nd_pfn->mode);
+	pfn_sb->dataoff = cpu_to_le64(offset);
+	pfn_sb->npfns = cpu_to_le64(npfns);
+	memcpy(pfn_sb->signature, sig, PFN_SIG_LEN);
+	memcpy(pfn_sb->uuid, nd_pfn->uuid, 16);
+	memcpy(pfn_sb->parent_uuid, nd_dev_to_uuid(&ndns->dev), 16);
+	pfn_sb->version_major = cpu_to_le16(1);
+	pfn_sb->version_minor = cpu_to_le16(2);
+	pfn_sb->start_pad = cpu_to_le32(start_pad);
+	pfn_sb->end_trunc = cpu_to_le32(end_trunc);
+	pfn_sb->align = cpu_to_le32(nd_pfn->align);
+	checksum = nd_sb_checksum((struct nd_gen_sb *) pfn_sb);
+	pfn_sb->checksum = cpu_to_le64(checksum);
+
+	return nvdimm_write_bytes(ndns, SZ_4K, pfn_sb, sizeof(*pfn_sb));
+}
+
+/*
+ * Determine the effective resource range and vmem_altmap from an nd_pfn
+ * instance.
+ */
+struct vmem_altmap *nvdimm_setup_pfn(struct nd_pfn *nd_pfn,
+		struct resource *res, struct vmem_altmap *altmap)
+{
+	int rc;
+
+	if (!nd_pfn->uuid || !nd_pfn->ndns)
+		return ERR_PTR(-ENODEV);
+
+	rc = nd_pfn_init(nd_pfn);
+	if (rc)
+		return ERR_PTR(rc);
+
+	/* we need a valid pfn_sb before we can init a vmem_altmap */
+	return __nvdimm_setup_pfn(nd_pfn, res, altmap);
+}
+EXPORT_SYMBOL_GPL(nvdimm_setup_pfn);

drivers/nvdimm/pmem.c

@@ -33,10 +33,6 @@
 #include "nd.h"
 
 struct pmem_device {
-	struct request_queue	*pmem_queue;
-	struct gendisk		*pmem_disk;
-	struct nd_namespace_common *ndns;
-
 	/* One contiguous memory region per device */
 	phys_addr_t		phys_addr;
 	/* when non-zero this device is hosting a 'pfn' instance */
@@ -50,23 +46,10 @@ struct pmem_device {
 	struct badblocks	bb;
 };
 
-static bool is_bad_pmem(struct badblocks *bb, sector_t sector, unsigned int len)
-{
-	if (bb->count) {
-		sector_t first_bad;
-		int num_bad;
-
-		return !!badblocks_check(bb, sector, len / 512, &first_bad,
-				&num_bad);
-	}
-
-	return false;
-}
-
 static void pmem_clear_poison(struct pmem_device *pmem, phys_addr_t offset,
 		unsigned int len)
 {
-	struct device *dev = disk_to_dev(pmem->pmem_disk);
+	struct device *dev = pmem->bb.dev;
 	sector_t sector;
 	long cleared;
 
@@ -136,8 +119,7 @@ static blk_qc_t pmem_make_request(struct request_queue *q, struct bio *bio)
 	unsigned long start;
 	struct bio_vec bvec;
 	struct bvec_iter iter;
-	struct block_device *bdev = bio->bi_bdev;
-	struct pmem_device *pmem = bdev->bd_disk->private_data;
+	struct pmem_device *pmem = q->queuedata;
 
 	do_acct = nd_iostat_start(bio, &start);
 	bio_for_each_segment(bvec, bio, iter) {
@@ -162,7 +144,7 @@ static blk_qc_t pmem_make_request(struct request_queue *q, struct bio *bio)
 static int pmem_rw_page(struct block_device *bdev, sector_t sector,
 		       struct page *page, int rw)
 {
-	struct pmem_device *pmem = bdev->bd_disk->private_data;
+	struct pmem_device *pmem = bdev->bd_queue->queuedata;
 	int rc;
 
 	rc = pmem_do_bvec(pmem, page, PAGE_SIZE, 0, rw, sector);
@@ -184,7 +166,7 @@ static int pmem_rw_page(struct block_device *bdev, sector_t sector,
 static long pmem_direct_access(struct block_device *bdev, sector_t sector,
 		      void __pmem **kaddr, pfn_t *pfn)
 {
-	struct pmem_device *pmem = bdev->bd_disk->private_data;
+	struct pmem_device *pmem = bdev->bd_queue->queuedata;
 	resource_size_t offset = sector * 512 + pmem->data_offset;
 
 	*kaddr = pmem->virt_addr + offset;
@@ -200,104 +182,119 @@ static const struct block_device_operations pmem_fops = {
 	.revalidate_disk =	nvdimm_revalidate_disk,
 };
 
-static struct pmem_device *pmem_alloc(struct device *dev,
-		struct resource *res, int id)
+static void pmem_release_queue(void *q)
+{
+	blk_cleanup_queue(q);
+}
+
+void pmem_release_disk(void *disk)
 {
+	del_gendisk(disk);
+	put_disk(disk);
+}
+
+static int pmem_attach_disk(struct device *dev,
+		struct nd_namespace_common *ndns)
+{
+	struct nd_namespace_io *nsio = to_nd_namespace_io(&ndns->dev);
+	struct vmem_altmap __altmap, *altmap = NULL;
+	struct resource *res = &nsio->res;
+	struct nd_pfn *nd_pfn = NULL;
+	int nid = dev_to_node(dev);
+	struct nd_pfn_sb *pfn_sb;
 	struct pmem_device *pmem;
+	struct resource pfn_res;
 	struct request_queue *q;
+	struct gendisk *disk;
+	void *addr;
+
+	/* while nsio_rw_bytes is active, parse a pfn info block if present */
+	if (is_nd_pfn(dev)) {
+		nd_pfn = to_nd_pfn(dev);
+		altmap = nvdimm_setup_pfn(nd_pfn, &pfn_res, &__altmap);
+		if (IS_ERR(altmap))
+			return PTR_ERR(altmap);
+	}
+
+	/* we're attaching a block device, disable raw namespace access */
+	devm_nsio_disable(dev, nsio);
 
 	pmem = devm_kzalloc(dev, sizeof(*pmem), GFP_KERNEL);
 	if (!pmem)
-		return ERR_PTR(-ENOMEM);
+		return -ENOMEM;
 
+	dev_set_drvdata(dev, pmem);
 	pmem->phys_addr = res->start;
 	pmem->size = resource_size(res);
 	if (!arch_has_wmb_pmem())
 		dev_warn(dev, "unable to guarantee persistence of writes\n");
 
-	if (!devm_request_mem_region(dev, pmem->phys_addr, pmem->size,
-			dev_name(dev))) {
-		dev_warn(dev, "could not reserve region [0x%pa:0x%zx]\n",
-				&pmem->phys_addr, pmem->size);
-		return ERR_PTR(-EBUSY);
+	if (!devm_request_mem_region(dev, res->start, resource_size(res),
+				dev_name(dev))) {
+		dev_warn(dev, "could not reserve region %pR\n", res);
+		return -EBUSY;
 	}
 
 	q = blk_alloc_queue_node(GFP_KERNEL, dev_to_node(dev));
 	if (!q)
-		return ERR_PTR(-ENOMEM);
+		return -ENOMEM;
 
 	pmem->pfn_flags = PFN_DEV;
-	if (pmem_should_map_pages(dev)) {
-		pmem->virt_addr = (void __pmem *) devm_memremap_pages(dev, res,
+	if (is_nd_pfn(dev)) {
+		addr = devm_memremap_pages(dev, &pfn_res, &q->q_usage_counter,
+				altmap);
+		pfn_sb = nd_pfn->pfn_sb;
+		pmem->data_offset = le64_to_cpu(pfn_sb->dataoff);
+		pmem->pfn_pad = resource_size(res) - resource_size(&pfn_res);
+		pmem->pfn_flags |= PFN_MAP;
+		res = &pfn_res; /* for badblocks populate */
+		res->start += pmem->data_offset;
+	} else if (pmem_should_map_pages(dev)) {
+		addr = devm_memremap_pages(dev, &nsio->res,
 				&q->q_usage_counter, NULL);
 		pmem->pfn_flags |= PFN_MAP;
 	} else
-		pmem->virt_addr = (void __pmem *) devm_memremap(dev,
-				pmem->phys_addr, pmem->size,
-				ARCH_MEMREMAP_PMEM);
+		addr = devm_memremap(dev, pmem->phys_addr,
+				pmem->size, ARCH_MEMREMAP_PMEM);
 
-	if (IS_ERR(pmem->virt_addr)) {
+	/*
+	 * At release time the queue must be dead before
+	 * devm_memremap_pages is unwound
+	 */
+	if (devm_add_action(dev, pmem_release_queue, q)) {
 		blk_cleanup_queue(q);
-		return (void __force *) pmem->virt_addr;
+		return -ENOMEM;
 	}
 
-	pmem->pmem_queue = q;
-	return pmem;
-}
-
-static void pmem_detach_disk(struct pmem_device *pmem)
-{
-	if (!pmem->pmem_disk)
-		return;
-
-	del_gendisk(pmem->pmem_disk);
-	put_disk(pmem->pmem_disk);
-	blk_cleanup_queue(pmem->pmem_queue);
-}
+	if (IS_ERR(addr))
+		return PTR_ERR(addr);
+	pmem->virt_addr = (void __pmem *) addr;
 
-static int pmem_attach_disk(struct device *dev,
-		struct nd_namespace_common *ndns, struct pmem_device *pmem)
-{
-	struct nd_namespace_io *nsio = to_nd_namespace_io(&ndns->dev);
-	int nid = dev_to_node(dev);
-	struct resource bb_res;
-	struct gendisk *disk;
-
-	blk_queue_make_request(pmem->pmem_queue, pmem_make_request);
-	blk_queue_physical_block_size(pmem->pmem_queue, PAGE_SIZE);
-	blk_queue_max_hw_sectors(pmem->pmem_queue, UINT_MAX);
-	blk_queue_bounce_limit(pmem->pmem_queue, BLK_BOUNCE_ANY);
-	queue_flag_set_unlocked(QUEUE_FLAG_NONROT, pmem->pmem_queue);
+	blk_queue_make_request(q, pmem_make_request);
+	blk_queue_physical_block_size(q, PAGE_SIZE);
+	blk_queue_max_hw_sectors(q, UINT_MAX);
+	blk_queue_bounce_limit(q, BLK_BOUNCE_ANY);
+	queue_flag_set_unlocked(QUEUE_FLAG_NONROT, q);
+	q->queuedata = pmem;
 
 	disk = alloc_disk_node(0, nid);
-	if (!disk) {
-		blk_cleanup_queue(pmem->pmem_queue);
+	if (!disk)
+		return -ENOMEM;
+	if (devm_add_action(dev, pmem_release_disk, disk)) {
+		put_disk(disk);
 		return -ENOMEM;
 	}
 
 	disk->fops		= &pmem_fops;
-	disk->private_data	= pmem;
-	disk->queue		= pmem->pmem_queue;
+	disk->queue		= q;
 	disk->flags		= GENHD_FL_EXT_DEVT;
 	nvdimm_namespace_disk_name(ndns, disk->disk_name);
 	disk->driverfs_dev = dev;
 	set_capacity(disk, (pmem->size - pmem->pfn_pad - pmem->data_offset)
 			/ 512);
-	pmem->pmem_disk = disk;
-	devm_exit_badblocks(dev, &pmem->bb);
 	if (devm_init_badblocks(dev, &pmem->bb))
 		return -ENOMEM;
-	bb_res.start = nsio->res.start + pmem->data_offset;
-	bb_res.end = nsio->res.end;
-	if (is_nd_pfn(dev)) {
-		struct nd_pfn *nd_pfn = to_nd_pfn(dev);
-		struct nd_pfn_sb *pfn_sb = nd_pfn->pfn_sb;
-
-		bb_res.start += __le32_to_cpu(pfn_sb->start_pad);
-		bb_res.end -= __le32_to_cpu(pfn_sb->end_trunc);
-	}
-	nvdimm_badblocks_populate(to_nd_region(dev->parent), &pmem->bb,
-			&bb_res);
+	nvdimm_badblocks_populate(to_nd_region(dev->parent), &pmem->bb, res);
 	disk->bb = &pmem->bb;
 	add_disk(disk);
 	revalidate_disk(disk);
@@ -305,346 +302,68 @@ static int pmem_attach_disk(struct device *dev,
 	return 0;
 }
 
-static int pmem_rw_bytes(struct nd_namespace_common *ndns,
-		resource_size_t offset, void *buf, size_t size, int rw)
-{
-	struct pmem_device *pmem = dev_get_drvdata(ndns->claim);
-
-	if (unlikely(offset + size > pmem->size)) {
-		dev_WARN_ONCE(&ndns->dev, 1, "request out of range\n");
-		return -EFAULT;
-	}
-
-	if (rw == READ) {
-		unsigned int sz_align = ALIGN(size + (offset & (512 - 1)), 512);
-
-		if (unlikely(is_bad_pmem(&pmem->bb, offset / 512, sz_align)))
-			return -EIO;
-		return memcpy_from_pmem(buf, pmem->virt_addr + offset, size);
-	} else {
-		memcpy_to_pmem(pmem->virt_addr + offset, buf, size);
-		wmb_pmem();
-	}
-
-	return 0;
-}
-
-static int nd_pfn_init(struct nd_pfn *nd_pfn)
-{
-	struct nd_pfn_sb *pfn_sb = kzalloc(sizeof(*pfn_sb), GFP_KERNEL);
-	struct pmem_device *pmem = dev_get_drvdata(&nd_pfn->dev);
-	struct nd_namespace_common *ndns = nd_pfn->ndns;
-	u32 start_pad = 0, end_trunc = 0;
-	resource_size_t start, size;
-	struct nd_namespace_io *nsio;
-	struct nd_region *nd_region;
-	unsigned long npfns;
-	phys_addr_t offset;
-	u64 checksum;
-	int rc;
-
-	if (!pfn_sb)
-		return -ENOMEM;
-
-	nd_pfn->pfn_sb = pfn_sb;
-	rc = nd_pfn_validate(nd_pfn);
-	if (rc == -ENODEV)
-		/* no info block, do init */;
-	else
-		return rc;
-
-	nd_region = to_nd_region(nd_pfn->dev.parent);
-	if (nd_region->ro) {
-		dev_info(&nd_pfn->dev,
-				"%s is read-only, unable to init metadata\n",
-				dev_name(&nd_region->dev));
-		goto err;
-	}
-
-	memset(pfn_sb, 0, sizeof(*pfn_sb));
-
-	/*
-	 * Check if pmem collides with 'System RAM' when section aligned and
-	 * trim it accordingly
-	 */
-	nsio = to_nd_namespace_io(&ndns->dev);
-	start = PHYS_SECTION_ALIGN_DOWN(nsio->res.start);
-	size = resource_size(&nsio->res);
-	if (region_intersects(start, size, IORESOURCE_SYSTEM_RAM,
-				IORES_DESC_NONE) == REGION_MIXED) {
-
-		start = nsio->res.start;
-		start_pad = PHYS_SECTION_ALIGN_UP(start) - start;
-	}
-
-	start = nsio->res.start;
-	size = PHYS_SECTION_ALIGN_UP(start + size) - start;
-	if (region_intersects(start, size, IORESOURCE_SYSTEM_RAM,
-				IORES_DESC_NONE) == REGION_MIXED) {
-		size = resource_size(&nsio->res);
-		end_trunc = start + size - PHYS_SECTION_ALIGN_DOWN(start + size);
-	}
-
-	if (start_pad + end_trunc)
-		dev_info(&nd_pfn->dev, "%s section collision, truncate %d bytes\n",
-				dev_name(&ndns->dev), start_pad + end_trunc);
-
-	/*
-	 * Note, we use 64 here for the standard size of struct page,
-	 * debugging options may cause it to be larger in which case the
-	 * implementation will limit the pfns advertised through
-	 * ->direct_access() to those that are included in the memmap.
-	 */
-	start += start_pad;
-	npfns = (pmem->size - start_pad - end_trunc - SZ_8K) / SZ_4K;
-	if (nd_pfn->mode == PFN_MODE_PMEM) {
-		unsigned long memmap_size;
-
-		/*
-		 * vmemmap_populate_hugepages() allocates the memmap array in
-		 * PMD_SIZE chunks.
-		 */
-		memmap_size = ALIGN(64 * npfns, PMD_SIZE);
-		offset = ALIGN(start + SZ_8K + memmap_size, nd_pfn->align)
-			- start;
-	} else if (nd_pfn->mode == PFN_MODE_RAM)
-		offset = ALIGN(start + SZ_8K, nd_pfn->align) - start;
-	else
-		goto err;
-
-	if (offset + start_pad + end_trunc >= pmem->size) {
-		dev_err(&nd_pfn->dev, "%s unable to satisfy requested alignment\n",
-				dev_name(&ndns->dev));
-		goto err;
-	}
-
-	npfns = (pmem->size - offset - start_pad - end_trunc) / SZ_4K;
-	pfn_sb->mode = cpu_to_le32(nd_pfn->mode);
-	pfn_sb->dataoff = cpu_to_le64(offset);
-	pfn_sb->npfns = cpu_to_le64(npfns);
-	memcpy(pfn_sb->signature, PFN_SIG, PFN_SIG_LEN);
-	memcpy(pfn_sb->uuid, nd_pfn->uuid, 16);
-	memcpy(pfn_sb->parent_uuid, nd_dev_to_uuid(&ndns->dev), 16);
-	pfn_sb->version_major = cpu_to_le16(1);
-	pfn_sb->version_minor = cpu_to_le16(1);
-	pfn_sb->start_pad = cpu_to_le32(start_pad);
-	pfn_sb->end_trunc = cpu_to_le32(end_trunc);
-	checksum = nd_sb_checksum((struct nd_gen_sb *) pfn_sb);
-	pfn_sb->checksum = cpu_to_le64(checksum);
-
-	rc = nvdimm_write_bytes(ndns, SZ_4K, pfn_sb, sizeof(*pfn_sb));
-	if (rc)
-		goto err;
-
-	return 0;
- err:
-	nd_pfn->pfn_sb = NULL;
-	kfree(pfn_sb);
-	return -ENXIO;
-}
-
-static int nvdimm_namespace_detach_pfn(struct nd_namespace_common *ndns)
-{
-	struct nd_pfn *nd_pfn = to_nd_pfn(ndns->claim);
-	struct pmem_device *pmem;
-
-	/* free pmem disk */
-	pmem = dev_get_drvdata(&nd_pfn->dev);
-	pmem_detach_disk(pmem);
-
-	/* release nd_pfn resources */
-	kfree(nd_pfn->pfn_sb);
-	nd_pfn->pfn_sb = NULL;
-
-	return 0;
-}
-
-/*
- * We hotplug memory at section granularity, pad the reserved area from
- * the previous section base to the namespace base address.
- */
-static unsigned long init_altmap_base(resource_size_t base)
-{
-	unsigned long base_pfn = PHYS_PFN(base);
-
-	return PFN_SECTION_ALIGN_DOWN(base_pfn);
-}
-
-static unsigned long init_altmap_reserve(resource_size_t base)
-{
-	unsigned long reserve = PHYS_PFN(SZ_8K);
-	unsigned long base_pfn = PHYS_PFN(base);
-
-	reserve += base_pfn - PFN_SECTION_ALIGN_DOWN(base_pfn);
-	return reserve;
-}
-
-static int __nvdimm_namespace_attach_pfn(struct nd_pfn *nd_pfn)
-{
-	int rc;
-	struct resource res;
-	struct request_queue *q;
-	struct pmem_device *pmem;
-	struct vmem_altmap *altmap;
-	struct device *dev = &nd_pfn->dev;
-	struct nd_pfn_sb *pfn_sb = nd_pfn->pfn_sb;
-	struct nd_namespace_common *ndns = nd_pfn->ndns;
-	u32 start_pad = __le32_to_cpu(pfn_sb->start_pad);
-	u32 end_trunc = __le32_to_cpu(pfn_sb->end_trunc);
-	struct nd_namespace_io *nsio = to_nd_namespace_io(&ndns->dev);
-	resource_size_t base = nsio->res.start + start_pad;
-	struct vmem_altmap __altmap = {
-		.base_pfn = init_altmap_base(base),
-		.reserve = init_altmap_reserve(base),
-	};
-
-	pmem = dev_get_drvdata(dev);
-	pmem->data_offset = le64_to_cpu(pfn_sb->dataoff);
-	pmem->pfn_pad = start_pad + end_trunc;
-	nd_pfn->mode = le32_to_cpu(nd_pfn->pfn_sb->mode);
-	if (nd_pfn->mode == PFN_MODE_RAM) {
-		if (pmem->data_offset < SZ_8K)
-			return -EINVAL;
-		nd_pfn->npfns = le64_to_cpu(pfn_sb->npfns);
-		altmap = NULL;
-	} else if (nd_pfn->mode == PFN_MODE_PMEM) {
-		nd_pfn->npfns = (pmem->size - pmem->pfn_pad - pmem->data_offset)
-			/ PAGE_SIZE;
-		if (le64_to_cpu(nd_pfn->pfn_sb->npfns) > nd_pfn->npfns)
-			dev_info(&nd_pfn->dev,
-					"number of pfns truncated from %lld to %ld\n",
-					le64_to_cpu(nd_pfn->pfn_sb->npfns),
-					nd_pfn->npfns);
-		altmap = & __altmap;
-		altmap->free = PHYS_PFN(pmem->data_offset - SZ_8K);
-		altmap->alloc = 0;
-	} else {
-		rc = -ENXIO;
-		goto err;
-	}
-
-	/* establish pfn range for lookup, and switch to direct map */
-	q = pmem->pmem_queue;
-	memcpy(&res, &nsio->res, sizeof(res));
-	res.start += start_pad;
-	res.end -= end_trunc;
-	devm_memunmap(dev, (void __force *) pmem->virt_addr);
-	pmem->virt_addr = (void __pmem *) devm_memremap_pages(dev, &res,
-			&q->q_usage_counter, altmap);
-	pmem->pfn_flags |= PFN_MAP;
-	if (IS_ERR(pmem->virt_addr)) {
-		rc = PTR_ERR(pmem->virt_addr);
-		goto err;
-	}
-
-	/* attach pmem disk in "pfn-mode" */
-	rc = pmem_attach_disk(dev, ndns, pmem);
-	if (rc)
-		goto err;
-
-	return rc;
- err:
-	nvdimm_namespace_detach_pfn(ndns);
-	return rc;
-
-}
-
-static int nvdimm_namespace_attach_pfn(struct nd_namespace_common *ndns)
-{
-	struct nd_pfn *nd_pfn = to_nd_pfn(ndns->claim);
-	int rc;
-
-	if (!nd_pfn->uuid || !nd_pfn->ndns)
-		return -ENODEV;
-
-	rc = nd_pfn_init(nd_pfn);
-	if (rc)
-		return rc;
-	/* we need a valid pfn_sb before we can init a vmem_altmap */
-	return __nvdimm_namespace_attach_pfn(nd_pfn);
-}
-
 static int nd_pmem_probe(struct device *dev)
 {
-	struct nd_region *nd_region = to_nd_region(dev->parent);
 	struct nd_namespace_common *ndns;
-	struct nd_namespace_io *nsio;
-	struct pmem_device *pmem;
 
 	ndns = nvdimm_namespace_common_probe(dev);
 	if (IS_ERR(ndns))
 		return PTR_ERR(ndns);
 
-	nsio = to_nd_namespace_io(&ndns->dev);
-	pmem = pmem_alloc(dev, &nsio->res, nd_region->id);
-	if (IS_ERR(pmem))
-		return PTR_ERR(pmem);
-
-	pmem->ndns = ndns;
-	dev_set_drvdata(dev, pmem);
-	ndns->rw_bytes = pmem_rw_bytes;
-	if (devm_init_badblocks(dev, &pmem->bb))
-		return -ENOMEM;
-	nvdimm_badblocks_populate(nd_region, &pmem->bb, &nsio->res);
+	if (devm_nsio_enable(dev, to_nd_namespace_io(&ndns->dev)))
+		return -ENXIO;
 
-	if (is_nd_btt(dev)) {
-		/* btt allocates its own request_queue */
-		blk_cleanup_queue(pmem->pmem_queue);
-		pmem->pmem_queue = NULL;
+	if (is_nd_btt(dev))
 		return nvdimm_namespace_attach_btt(ndns);
-	}
 
 	if (is_nd_pfn(dev))
-		return nvdimm_namespace_attach_pfn(ndns);
+		return pmem_attach_disk(dev, ndns);
 
-	if (nd_btt_probe(ndns, pmem) == 0 || nd_pfn_probe(ndns, pmem) == 0) {
-		/*
-		 * We'll come back as either btt-pmem, or pfn-pmem, so
-		 * drop the queue allocation for now.
-		 */
-		blk_cleanup_queue(pmem->pmem_queue);
+	/* if we find a valid info-block we'll come back as that personality */
+	if (nd_btt_probe(dev, ndns) == 0 || nd_pfn_probe(dev, ndns) == 0
+			|| nd_dax_probe(dev, ndns) == 0)
 		return -ENXIO;
-	}
 
-	return pmem_attach_disk(dev, ndns, pmem);
+	/* ...otherwise we're just a raw pmem device */
+	return pmem_attach_disk(dev, ndns);
 }
 
 static int nd_pmem_remove(struct device *dev)
 {
-	struct pmem_device *pmem = dev_get_drvdata(dev);
-
 	if (is_nd_btt(dev))
-		nvdimm_namespace_detach_btt(pmem->ndns);
-	else if (is_nd_pfn(dev))
-		nvdimm_namespace_detach_pfn(pmem->ndns);
-	else
-		pmem_detach_disk(pmem);
-
+		nvdimm_namespace_detach_btt(to_nd_btt(dev));
 	return 0;
 }
 
 static void nd_pmem_notify(struct device *dev, enum nvdimm_event event)
 {
-	struct pmem_device *pmem = dev_get_drvdata(dev);
-	struct nd_namespace_common *ndns = pmem->ndns;
 	struct nd_region *nd_region = to_nd_region(dev->parent);
-	struct nd_namespace_io *nsio = to_nd_namespace_io(&ndns->dev);
-	struct resource res = {
-		.start = nsio->res.start + pmem->data_offset,
-		.end = nsio->res.end,
-	};
+	struct pmem_device *pmem = dev_get_drvdata(dev);
+	resource_size_t offset = 0, end_trunc = 0;
+	struct nd_namespace_common *ndns;
+	struct nd_namespace_io *nsio;
+	struct resource res;
 
 	if (event != NVDIMM_REVALIDATE_POISON)
 		return;
 
-	if (is_nd_pfn(dev)) {
+	if (is_nd_btt(dev)) {
+		struct nd_btt *nd_btt = to_nd_btt(dev);
+
+		ndns = nd_btt->ndns;
+	} else if (is_nd_pfn(dev)) {
 		struct nd_pfn *nd_pfn = to_nd_pfn(dev);
 		struct nd_pfn_sb *pfn_sb = nd_pfn->pfn_sb;
 
-		res.start += __le32_to_cpu(pfn_sb->start_pad);
-		res.end -= __le32_to_cpu(pfn_sb->end_trunc);
-	}
+		ndns = nd_pfn->ndns;
+		offset = pmem->data_offset + __le32_to_cpu(pfn_sb->start_pad);
+		end_trunc = __le32_to_cpu(pfn_sb->end_trunc);
+	} else
+		ndns = to_ndns(dev);
 
+	nsio = to_nd_namespace_io(&ndns->dev);
+	res.start = nsio->res.start + offset;
+	res.end = nsio->res.end - end_trunc;
 	nvdimm_badblocks_populate(nd_region, &pmem->bb, &res);
 }
 

drivers/nvdimm/region.c

@@ -54,6 +54,7 @@ static int nd_region_probe(struct device *dev)
 
 	nd_region->btt_seed = nd_btt_create(nd_region);
 	nd_region->pfn_seed = nd_pfn_create(nd_region);
+	nd_region->dax_seed = nd_dax_create(nd_region);
 	if (err == 0)
 		return 0;
 
@@ -86,6 +87,7 @@ static int nd_region_remove(struct device *dev)
 	nd_region->ns_seed = NULL;
 	nd_region->btt_seed = NULL;
 	nd_region->pfn_seed = NULL;
+	nd_region->dax_seed = NULL;
 	dev_set_drvdata(dev, NULL);
 	nvdimm_bus_unlock(dev);
 

drivers/nvdimm/region_devs.c

@@ -306,6 +306,23 @@ static ssize_t pfn_seed_show(struct device *dev,
 }
 static DEVICE_ATTR_RO(pfn_seed);
 
+static ssize_t dax_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->dax_seed)
+		rc = sprintf(buf, "%s\n", dev_name(nd_region->dax_seed));
+	else
+		rc = sprintf(buf, "\n");
+	nvdimm_bus_unlock(dev);
+
+	return rc;
+}
+static DEVICE_ATTR_RO(dax_seed);
+
 static ssize_t read_only_show(struct device *dev,
 		struct device_attribute *attr, char *buf)
 {
@@ -335,6 +352,7 @@ static struct attribute *nd_region_attributes[] = {
 	&dev_attr_mappings.attr,
 	&dev_attr_btt_seed.attr,
 	&dev_attr_pfn_seed.attr,
+	&dev_attr_dax_seed.attr,
 	&dev_attr_read_only.attr,
 	&dev_attr_set_cookie.attr,
 	&dev_attr_available_size.attr,
@@ -353,6 +371,9 @@ static umode_t region_visible(struct kobject *kobj, struct attribute *a, int n)
 	if (!is_nd_pmem(dev) && a == &dev_attr_pfn_seed.attr)
 		return 0;
 
+	if (!is_nd_pmem(dev) && a == &dev_attr_dax_seed.attr)
+		return 0;
+
 	if (a != &dev_attr_set_cookie.attr
 			&& a != &dev_attr_available_size.attr)
 		return a->mode;
@@ -441,6 +462,13 @@ static void nd_region_notify_driver_action(struct nvdimm_bus *nvdimm_bus,
 			nd_region_create_pfn_seed(nd_region);
 		nvdimm_bus_unlock(dev);
 	}
+	if (is_nd_dax(dev) && probe) {
+		nd_region = to_nd_region(dev->parent);
+		nvdimm_bus_lock(dev);
+		if (nd_region->dax_seed == dev)
+			nd_region_create_dax_seed(nd_region);
+		nvdimm_bus_unlock(dev);
+	}
 }
 
 void nd_region_probe_success(struct nvdimm_bus *nvdimm_bus, struct device *dev)
@@ -718,6 +746,7 @@ static struct nd_region *nd_region_create(struct nvdimm_bus *nvdimm_bus,
 	ida_init(&nd_region->ns_ida);
 	ida_init(&nd_region->btt_ida);
 	ida_init(&nd_region->pfn_ida);
+	ida_init(&nd_region->dax_ida);
 	dev = &nd_region->dev;
 	dev_set_name(dev, "region%d", nd_region->id);
 	dev->parent = &nvdimm_bus->dev;
@@ -764,3 +793,8 @@ struct nd_region *nvdimm_volatile_region_create(struct nvdimm_bus *nvdimm_bus,
 			__func__);
 }
 EXPORT_SYMBOL_GPL(nvdimm_volatile_region_create);
+
+void __exit nd_region_devs_exit(void)
+{
+	ida_destroy(&region_ida);
+}

fs/block_dev.c

@@ -29,6 +29,7 @@
 #include <linux/log2.h>
 #include <linux/cleancache.h>
 #include <linux/dax.h>
+#include <linux/badblocks.h>
 #include <asm/uaccess.h>
 #include "internal.h"
 
@@ -1159,6 +1160,33 @@ void bd_set_size(struct block_device *bdev, loff_t size)
 }
 EXPORT_SYMBOL(bd_set_size);
 
+static bool blkdev_dax_capable(struct block_device *bdev)
+{
+	struct gendisk *disk = bdev->bd_disk;
+
+	if (!disk->fops->direct_access || !IS_ENABLED(CONFIG_FS_DAX))
+		return false;
+
+	/*
+	 * If the partition is not aligned on a page boundary, we can't
+	 * do dax I/O to it.
+	 */
+	if ((bdev->bd_part->start_sect % (PAGE_SIZE / 512))
+			|| (bdev->bd_part->nr_sects % (PAGE_SIZE / 512)))
+		return false;
+
+	/*
+	 * If the device has known bad blocks, force all I/O through the
+	 * driver / page cache.
+	 *
+	 * TODO: support finer grained dax error handling
+	 */
+	if (disk->bb && disk->bb->count)
+		return false;
+
+	return true;
+}
+
 static void __blkdev_put(struct block_device *bdev, fmode_t mode, int for_part);
 
 /*
@@ -1720,79 +1748,13 @@ static const struct address_space_operations def_blk_aops = {
 	.is_dirty_writeback = buffer_check_dirty_writeback,
 };
 
-#ifdef CONFIG_FS_DAX
-/*
- * In the raw block case we do not need to contend with truncation nor
- * unwritten file extents.  Without those concerns there is no need for
- * additional locking beyond the mmap_sem context that these routines
- * are already executing under.
- *
- * Note, there is no protection if the block device is dynamically
- * resized (partition grow/shrink) during a fault. A stable block device
- * size is already not enforced in the blkdev_direct_IO path.
- *
- * For DAX, it is the responsibility of the block device driver to
- * ensure the whole-disk device size is stable while requests are in
- * flight.
- *
- * Finally, unlike the filemap_page_mkwrite() case there is no
- * filesystem superblock to sync against freezing.  We still include a
- * pfn_mkwrite callback for dax drivers to receive write fault
- * notifications.
- */
-static int blkdev_dax_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
-{
-	return __dax_fault(vma, vmf, blkdev_get_block, NULL);
-}
-
-static int blkdev_dax_pfn_mkwrite(struct vm_area_struct *vma,
-		struct vm_fault *vmf)
-{
-	return dax_pfn_mkwrite(vma, vmf);
-}
-
-static int blkdev_dax_pmd_fault(struct vm_area_struct *vma, unsigned long addr,
-		pmd_t *pmd, unsigned int flags)
-{
-	return __dax_pmd_fault(vma, addr, pmd, flags, blkdev_get_block, NULL);
-}
-
-static const struct vm_operations_struct blkdev_dax_vm_ops = {
-	.fault		= blkdev_dax_fault,
-	.pmd_fault	= blkdev_dax_pmd_fault,
-	.pfn_mkwrite	= blkdev_dax_pfn_mkwrite,
-};
-
-static const struct vm_operations_struct blkdev_default_vm_ops = {
-	.fault		= filemap_fault,
-	.map_pages	= filemap_map_pages,
-};
-
-static int blkdev_mmap(struct file *file, struct vm_area_struct *vma)
-{
-	struct inode *bd_inode = bdev_file_inode(file);
-
-	file_accessed(file);
-	if (IS_DAX(bd_inode)) {
-		vma->vm_ops = &blkdev_dax_vm_ops;
-		vma->vm_flags |= VM_MIXEDMAP | VM_HUGEPAGE;
-	} else {
-		vma->vm_ops = &blkdev_default_vm_ops;
-	}
-
-	return 0;
-}
-#else
-#define blkdev_mmap generic_file_mmap
-#endif
-
 const struct file_operations def_blk_fops = {
 	.open		= blkdev_open,
 	.release	= blkdev_close,
 	.llseek		= block_llseek,
 	.read_iter	= blkdev_read_iter,
 	.write_iter	= blkdev_write_iter,
-	.mmap		= blkdev_mmap,
+	.mmap		= generic_file_mmap,
 	.fsync		= blkdev_fsync,
 	.unlocked_ioctl	= block_ioctl,
 #ifdef CONFIG_COMPAT

include/acpi/acpi_bus.h

@@ -61,12 +61,12 @@ bool acpi_ata_match(acpi_handle handle);
 bool acpi_bay_match(acpi_handle handle);
 bool acpi_dock_match(acpi_handle handle);
 
-bool acpi_check_dsm(acpi_handle handle, const u8 *uuid, int rev, u64 funcs);
+bool acpi_check_dsm(acpi_handle handle, const u8 *uuid, u64 rev, u64 funcs);
 union acpi_object *acpi_evaluate_dsm(acpi_handle handle, const u8 *uuid,
-			int rev, int func, union acpi_object *argv4);
+			u64 rev, u64 func, union acpi_object *argv4);
 
 static inline union acpi_object *
-acpi_evaluate_dsm_typed(acpi_handle handle, const u8 *uuid, int rev, int func,
+acpi_evaluate_dsm_typed(acpi_handle handle, const u8 *uuid, u64 rev, u64 func,
 			union acpi_object *argv4, acpi_object_type type)
 {
 	union acpi_object *obj;

include/linux/fs.h

@@ -2352,14 +2352,6 @@ extern struct super_block *freeze_bdev(struct block_device *);
 extern void emergency_thaw_all(void);
 extern int thaw_bdev(struct block_device *bdev, struct super_block *sb);
 extern int fsync_bdev(struct block_device *);
-#ifdef CONFIG_FS_DAX
-extern bool blkdev_dax_capable(struct block_device *bdev);
-#else
-static inline bool blkdev_dax_capable(struct block_device *bdev)
-{
-	return false;
-}
-#endif
 
 extern struct super_block *blockdev_superblock;
 

include/linux/libnvdimm.h

@@ -27,7 +27,7 @@ enum {
 	/* need to set a limit somewhere, but yes, this is likely overkill */
 	ND_IOCTL_MAX_BUFLEN = SZ_4M,
 	ND_CMD_MAX_ELEM = 5,
-	ND_CMD_MAX_ENVELOPE = 16,
+	ND_CMD_MAX_ENVELOPE = 256,
 	ND_MAX_MAPPINGS = 32,
 
 	/* region flag indicating to direct-map persistent memory by default */
@@ -68,7 +68,7 @@ struct nd_mapping {
 
 struct nvdimm_bus_descriptor {
 	const struct attribute_group **attr_groups;
-	unsigned long dsm_mask;
+	unsigned long cmd_mask;
 	char *provider_name;
 	ndctl_fn ndctl;
 	int (*flush_probe)(struct nvdimm_bus_descriptor *nd_desc);
@@ -130,10 +130,11 @@ struct nd_region *to_nd_region(struct device *dev);
 struct nd_blk_region *to_nd_blk_region(struct device *dev);
 struct nvdimm_bus_descriptor *to_nd_desc(struct nvdimm_bus *nvdimm_bus);
 const char *nvdimm_name(struct nvdimm *nvdimm);
+unsigned long nvdimm_cmd_mask(struct nvdimm *nvdimm);
 void *nvdimm_provider_data(struct nvdimm *nvdimm);
 struct nvdimm *nvdimm_create(struct nvdimm_bus *nvdimm_bus, void *provider_data,
 		const struct attribute_group **groups, unsigned long flags,
-		unsigned long *dsm_mask);
+		unsigned long cmd_mask);
 const struct nd_cmd_desc *nd_cmd_dimm_desc(int cmd);
 const struct nd_cmd_desc *nd_cmd_bus_desc(int cmd);
 u32 nd_cmd_in_size(struct nvdimm *nvdimm, int cmd,

include/linux/nd.h

@@ -15,6 +15,7 @@
 #include <linux/fs.h>
 #include <linux/ndctl.h>
 #include <linux/device.h>
+#include <linux/badblocks.h>
 
 enum nvdimm_event {
 	NVDIMM_REVALIDATE_POISON,
@@ -55,13 +56,19 @@ static inline struct nd_namespace_common *to_ndns(struct device *dev)
 }
 
 /**
- * struct nd_namespace_io - infrastructure for loading an nd_pmem instance
+ * struct nd_namespace_io - device representation of a persistent memory range
  * @dev: namespace device created by the nd region driver
  * @res: struct resource conversion of a NFIT SPA table
+ * @size: cached resource_size(@res) for fast path size checks
+ * @addr: virtual address to access the namespace range
+ * @bb: badblocks list for the namespace range
  */
 struct nd_namespace_io {
 	struct nd_namespace_common common;
 	struct resource res;
+	resource_size_t size;
+	void __pmem *addr;
+	struct badblocks bb;
 };
 
 /**
@@ -82,6 +89,7 @@ struct nd_namespace_pmem {
  * @uuid: namespace name supplied in the dimm label
  * @id: ida allocated id
  * @lbasize: blk namespaces have a native sector size when btt not present
+ * @size: sum of all the resource ranges allocated to this namespace
  * @num_resources: number of dpa extents to claim
  * @res: discontiguous dpa extents for given dimm
  */
@@ -91,6 +99,7 @@ struct nd_namespace_blk {
 	u8 *uuid;
 	int id;
 	unsigned long lbasize;
+	resource_size_t size;
 	int num_resources;
 	struct resource **res;
 };

include/uapi/linux/fs.h

@@ -222,7 +222,6 @@ struct fsxattr {
 #define BLKSECDISCARD _IO(0x12,125)
 #define BLKROTATIONAL _IO(0x12,126)
 #define BLKZEROOUT _IO(0x12,127)
-#define BLKDAXGET _IO(0x12,129)
 
 #define BMAP_IOCTL 1		/* obsolete - kept for compatibility */
 #define FIBMAP	   _IO(0x00,1)	/* bmap access */

include/uapi/linux/ndctl.h

@@ -1,5 +1,5 @@
 /*
- * Copyright (c) 2014-2015, Intel Corporation.
+ * Copyright (c) 2014-2016, Intel Corporation.
  *
  * This program is free software; you can redistribute it and/or modify it
  * under the terms and conditions of the GNU Lesser General Public License,
@@ -20,11 +20,45 @@ struct nd_cmd_smart {
 	__u8 data[128];
 } __packed;
 
+#define ND_SMART_HEALTH_VALID	(1 << 0)
+#define ND_SMART_TEMP_VALID 	(1 << 1)
+#define ND_SMART_SPARES_VALID	(1 << 2)
+#define ND_SMART_ALARM_VALID	(1 << 3)
+#define ND_SMART_USED_VALID	(1 << 4)
+#define ND_SMART_SHUTDOWN_VALID	(1 << 5)
+#define ND_SMART_VENDOR_VALID	(1 << 6)
+#define ND_SMART_TEMP_TRIP	(1 << 0)
+#define ND_SMART_SPARE_TRIP	(1 << 1)
+#define ND_SMART_NON_CRITICAL_HEALTH	(1 << 0)
+#define ND_SMART_CRITICAL_HEALTH	(1 << 1)
+#define ND_SMART_FATAL_HEALTH		(1 << 2)
+
+struct nd_smart_payload {
+	__u32 flags;
+	__u8 reserved0[4];
+	__u8 health;
+	__u16 temperature;
+	__u8 spares;
+	__u8 alarm_flags;
+	__u8 life_used;
+	__u8 shutdown_state;
+	__u8 reserved1;
+	__u32 vendor_size;
+	__u8 vendor_data[108];
+} __packed;
+
 struct nd_cmd_smart_threshold {
 	__u32 status;
 	__u8 data[8];
 } __packed;
 
+struct nd_smart_threshold_payload {
+	__u16 alarm_control;
+	__u16 temperature;
+	__u8 spares;
+	__u8 reserved[3];
+} __packed;
+
 struct nd_cmd_dimm_flags {
 	__u32 status;
 	__u32 flags;
@@ -125,6 +159,7 @@ enum {
 	ND_CMD_VENDOR_EFFECT_LOG_SIZE = 7,
 	ND_CMD_VENDOR_EFFECT_LOG = 8,
 	ND_CMD_VENDOR = 9,
+	ND_CMD_CALL = 10,
 };
 
 enum {
@@ -158,6 +193,7 @@ static inline const char *nvdimm_cmd_name(unsigned cmd)
 		[ND_CMD_VENDOR_EFFECT_LOG_SIZE] = "effect_size",
 		[ND_CMD_VENDOR_EFFECT_LOG] = "effect_log",
 		[ND_CMD_VENDOR] = "vendor",
+		[ND_CMD_CALL] = "cmd_call",
 	};
 
 	if (cmd < ARRAY_SIZE(names) && names[cmd])
@@ -206,6 +242,7 @@ static inline const char *nvdimm_cmd_name(unsigned cmd)
 #define ND_DEVICE_NAMESPACE_IO 4    /* legacy persistent memory */
 #define ND_DEVICE_NAMESPACE_PMEM 5  /* PMEM namespace (may alias with BLK) */
 #define ND_DEVICE_NAMESPACE_BLK 6   /* BLK namespace (may alias with PMEM) */
+#define ND_DEVICE_DAX_PMEM 7        /* Device DAX interface to pmem */
 
 enum nd_driver_flags {
 	ND_DRIVER_DIMM            = 1 << ND_DEVICE_DIMM,
@@ -214,6 +251,7 @@ enum nd_driver_flags {
 	ND_DRIVER_NAMESPACE_IO    = 1 << ND_DEVICE_NAMESPACE_IO,
 	ND_DRIVER_NAMESPACE_PMEM  = 1 << ND_DEVICE_NAMESPACE_PMEM,
 	ND_DRIVER_NAMESPACE_BLK   = 1 << ND_DEVICE_NAMESPACE_BLK,
+	ND_DRIVER_DAX_PMEM	  = 1 << ND_DEVICE_DAX_PMEM,
 };
 
 enum {
@@ -224,4 +262,44 @@ enum ars_masks {
 	ARS_STATUS_MASK = 0x0000FFFF,
 	ARS_EXT_STATUS_SHIFT = 16,
 };
+
+/*
+ * struct nd_cmd_pkg
+ *
+ * is a wrapper to a quasi pass thru interface for invoking firmware
+ * associated with nvdimms.
+ *
+ * INPUT PARAMETERS
+ *
+ * nd_family corresponds to the firmware (e.g. DSM) interface.
+ *
+ * nd_command are the function index advertised by the firmware.
+ *
+ * nd_size_in is the size of the input parameters being passed to firmware
+ *
+ * OUTPUT PARAMETERS
+ *
+ * nd_fw_size is the size of the data firmware wants to return for
+ * the call.  If nd_fw_size is greater than size of nd_size_out, only
+ * the first nd_size_out bytes are returned.
+ */
+
+struct nd_cmd_pkg {
+	__u64   nd_family;		/* family of commands */
+	__u64   nd_command;
+	__u32   nd_size_in;		/* INPUT: size of input args */
+	__u32   nd_size_out;		/* INPUT: size of payload */
+	__u32   nd_reserved2[9];	/* reserved must be zero */
+	__u32   nd_fw_size;		/* OUTPUT: size fw wants to return */
+	unsigned char nd_payload[];	/* Contents of call      */
+};
+
+/* These NVDIMM families represent pre-standardization command sets */
+#define NVDIMM_FAMILY_INTEL 0
+#define NVDIMM_FAMILY_HPE1 1
+#define NVDIMM_FAMILY_HPE2 2
+
+#define ND_IOCTL_CALL			_IOWR(ND_IOCTL, ND_CMD_CALL,\
+					struct nd_cmd_pkg)
+
 #endif /* __NDCTL_H__ */

mm/huge_memory.c

@@ -1013,6 +1013,7 @@ int vmf_insert_pfn_pmd(struct vm_area_struct *vma, unsigned long addr,
 	insert_pfn_pmd(vma, addr, pmd, pfn, pgprot, write);
 	return VM_FAULT_NOPAGE;
 }
+EXPORT_SYMBOL_GPL(vmf_insert_pfn_pmd);
 
 static void touch_pmd(struct vm_area_struct *vma, unsigned long addr,
 		pmd_t *pmd)

mm/hugetlb.c

@@ -627,6 +627,7 @@ pgoff_t linear_hugepage_index(struct vm_area_struct *vma,
 {
 	return vma_hugecache_offset(hstate_vma(vma), vma, address);
 }
+EXPORT_SYMBOL_GPL(linear_hugepage_index);
 
 /*
  * Return the size of the pages allocated when backing a VMA. In the majority

tools/testing/nvdimm/Kbuild

@@ -7,6 +7,7 @@ ldflags-y += --wrap=ioremap_nocache
 ldflags-y += --wrap=iounmap
 ldflags-y += --wrap=memunmap
 ldflags-y += --wrap=__devm_request_region
+ldflags-y += --wrap=__devm_release_region
 ldflags-y += --wrap=__request_region
 ldflags-y += --wrap=__release_region
 ldflags-y += --wrap=devm_memremap_pages
@@ -15,6 +16,7 @@ ldflags-y += --wrap=phys_to_pfn_t
 DRIVERS := ../../../drivers
 NVDIMM_SRC := $(DRIVERS)/nvdimm
 ACPI_SRC := $(DRIVERS)/acpi
+DAX_SRC := $(DRIVERS)/dax
 
 obj-$(CONFIG_LIBNVDIMM) += libnvdimm.o
 obj-$(CONFIG_BLK_DEV_PMEM) += nd_pmem.o
@@ -22,6 +24,8 @@ obj-$(CONFIG_ND_BTT) += nd_btt.o
 obj-$(CONFIG_ND_BLK) += nd_blk.o
 obj-$(CONFIG_X86_PMEM_LEGACY) += nd_e820.o
 obj-$(CONFIG_ACPI_NFIT) += nfit.o
+obj-$(CONFIG_DEV_DAX) += dax.o
+obj-$(CONFIG_DEV_DAX_PMEM) += dax_pmem.o
 
 nfit-y := $(ACPI_SRC)/nfit.o
 nfit-y += config_check.o
@@ -38,6 +42,12 @@ nd_blk-y += config_check.o
 nd_e820-y := $(NVDIMM_SRC)/e820.o
 nd_e820-y += config_check.o
 
+dax-y := $(DAX_SRC)/dax.o
+dax-y += config_check.o
+
+dax_pmem-y := $(DAX_SRC)/pmem.o
+dax_pmem-y += config_check.o
+
 libnvdimm-y := $(NVDIMM_SRC)/core.o
 libnvdimm-y += $(NVDIMM_SRC)/bus.o
 libnvdimm-y += $(NVDIMM_SRC)/dimm_devs.o
@@ -49,6 +59,7 @@ libnvdimm-y += $(NVDIMM_SRC)/label.o
 libnvdimm-$(CONFIG_ND_CLAIM) += $(NVDIMM_SRC)/claim.o
 libnvdimm-$(CONFIG_BTT) += $(NVDIMM_SRC)/btt_devs.o
 libnvdimm-$(CONFIG_NVDIMM_PFN) += $(NVDIMM_SRC)/pfn_devs.o
+libnvdimm-$(CONFIG_NVDIMM_DAX) += $(NVDIMM_SRC)/dax_devs.o
 libnvdimm-y += config_check.o
 
 obj-m += test/

tools/testing/nvdimm/config_check.c

@@ -12,4 +12,6 @@ void check(void)
 	BUILD_BUG_ON(!IS_MODULE(CONFIG_ND_BTT));
 	BUILD_BUG_ON(!IS_MODULE(CONFIG_ND_BLK));
 	BUILD_BUG_ON(!IS_MODULE(CONFIG_ACPI_NFIT));
+	BUILD_BUG_ON(!IS_MODULE(CONFIG_DEV_DAX));
+	BUILD_BUG_ON(!IS_MODULE(CONFIG_DEV_DAX_PMEM));
 }

tools/testing/nvdimm/test/iomap.c

@@ -239,13 +239,11 @@ struct resource *__wrap___devm_request_region(struct device *dev,
 }
 EXPORT_SYMBOL(__wrap___devm_request_region);
 
-void __wrap___release_region(struct resource *parent, resource_size_t start,
-				resource_size_t n)
+static bool nfit_test_release_region(struct resource *parent,
+		resource_size_t start, resource_size_t n)
 {
-	struct nfit_test_resource *nfit_res;
-
 	if (parent == &iomem_resource) {
-		nfit_res = get_nfit_res(start);
+		struct nfit_test_resource *nfit_res = get_nfit_res(start);
 		if (nfit_res) {
 			struct resource *res = nfit_res->res + 1;
 
@@ -254,11 +252,26 @@ void __wrap___release_region(struct resource *parent, resource_size_t start,
 						__func__, start, n, res);
 			else
 				memset(res, 0, sizeof(*res));
-			return;
+			return true;
 		}
 	}
-	__release_region(parent, start, n);
+	return false;
+}
+
+void __wrap___release_region(struct resource *parent, resource_size_t start,
+		resource_size_t n)
+{
+	if (!nfit_test_release_region(parent, start, n))
+		__release_region(parent, start, n);
 }
 EXPORT_SYMBOL(__wrap___release_region);
 
+void __wrap___devm_release_region(struct device *dev, struct resource *parent,
+		resource_size_t start, resource_size_t n)
+{
+	if (!nfit_test_release_region(parent, start, n))
+		__devm_release_region(dev, parent, start, n);
+}
+EXPORT_SYMBOL(__wrap___devm_release_region);
+
 MODULE_LICENSE("GPL v2");

tools/testing/nvdimm/test/nfit.c

@@ -330,12 +330,49 @@ static int nfit_test_cmd_clear_error(struct nd_cmd_clear_error *clear_err,
 	return 0;
 }
 
+static int nfit_test_cmd_smart(struct nd_cmd_smart *smart, unsigned int buf_len)
+{
+	static const struct nd_smart_payload smart_data = {
+		.flags = ND_SMART_HEALTH_VALID | ND_SMART_TEMP_VALID
+			| ND_SMART_SPARES_VALID | ND_SMART_ALARM_VALID
+			| ND_SMART_USED_VALID | ND_SMART_SHUTDOWN_VALID,
+		.health = ND_SMART_NON_CRITICAL_HEALTH,
+		.temperature = 23 * 16,
+		.spares = 75,
+		.alarm_flags = ND_SMART_SPARE_TRIP | ND_SMART_TEMP_TRIP,
+		.life_used = 5,
+		.shutdown_state = 0,
+		.vendor_size = 0,
+	};
+
+	if (buf_len < sizeof(*smart))
+		return -EINVAL;
+	memcpy(smart->data, &smart_data, sizeof(smart_data));
+	return 0;
+}
+
+static int nfit_test_cmd_smart_threshold(struct nd_cmd_smart_threshold *smart_t,
+		unsigned int buf_len)
+{
+	static const struct nd_smart_threshold_payload smart_t_data = {
+		.alarm_control = ND_SMART_SPARE_TRIP | ND_SMART_TEMP_TRIP,
+		.temperature = 40 * 16,
+		.spares = 5,
+	};
+
+	if (buf_len < sizeof(*smart_t))
+		return -EINVAL;
+	memcpy(smart_t->data, &smart_t_data, sizeof(smart_t_data));
+	return 0;
+}
+
 static int nfit_test_ctl(struct nvdimm_bus_descriptor *nd_desc,
 		struct nvdimm *nvdimm, unsigned int cmd, void *buf,
 		unsigned int buf_len, int *cmd_rc)
 {
 	struct acpi_nfit_desc *acpi_desc = to_acpi_desc(nd_desc);
 	struct nfit_test *t = container_of(acpi_desc, typeof(*t), acpi_desc);
+	unsigned int func = cmd;
 	int i, rc = 0, __cmd_rc;
 
 	if (!cmd_rc)
@@ -344,8 +381,23 @@ static int nfit_test_ctl(struct nvdimm_bus_descriptor *nd_desc,
 
 	if (nvdimm) {
 		struct nfit_mem *nfit_mem = nvdimm_provider_data(nvdimm);
+		unsigned long cmd_mask = nvdimm_cmd_mask(nvdimm);
 
-		if (!nfit_mem || !test_bit(cmd, &nfit_mem->dsm_mask))
+		if (!nfit_mem)
+			return -ENOTTY;
+
+		if (cmd == ND_CMD_CALL) {
+			struct nd_cmd_pkg *call_pkg = buf;
+
+			buf_len = call_pkg->nd_size_in + call_pkg->nd_size_out;
+			buf = (void *) call_pkg->nd_payload;
+			func = call_pkg->nd_command;
+			if (call_pkg->nd_family != nfit_mem->family)
+				return -ENOTTY;
+		}
+
+		if (!test_bit(cmd, &cmd_mask)
+				|| !test_bit(func, &nfit_mem->dsm_mask))
 			return -ENOTTY;
 
 		/* lookup label space for the given dimm */
@@ -356,7 +408,7 @@ static int nfit_test_ctl(struct nvdimm_bus_descriptor *nd_desc,
 		if (i >= ARRAY_SIZE(handle))
 			return -ENXIO;
 
-		switch (cmd) {
+		switch (func) {
 		case ND_CMD_GET_CONFIG_SIZE:
 			rc = nfit_test_cmd_get_config_size(buf, buf_len);
 			break;
@@ -368,16 +420,22 @@ static int nfit_test_ctl(struct nvdimm_bus_descriptor *nd_desc,
 			rc = nfit_test_cmd_set_config_data(buf, buf_len,
 				t->label[i]);
 			break;
+		case ND_CMD_SMART:
+			rc = nfit_test_cmd_smart(buf, buf_len);
+			break;
+		case ND_CMD_SMART_THRESHOLD:
+			rc = nfit_test_cmd_smart_threshold(buf, buf_len);
+			break;
 		default:
 			return -ENOTTY;
 		}
 	} else {
 		struct ars_state *ars_state = &t->ars_state;
 
-		if (!nd_desc || !test_bit(cmd, &nd_desc->dsm_mask))
+		if (!nd_desc || !test_bit(cmd, &nd_desc->cmd_mask))
 			return -ENOTTY;
 
-		switch (cmd) {
+		switch (func) {
 		case ND_CMD_ARS_CAP:
 			rc = nfit_test_cmd_ars_cap(buf, buf_len);
 			break;
@@ -1251,13 +1309,15 @@ static void nfit_test0_setup(struct nfit_test *t)
 	post_ars_status(&t->ars_state, t->spa_set_dma[0], SPA0_SIZE);
 
 	acpi_desc = &t->acpi_desc;
-	set_bit(ND_CMD_GET_CONFIG_SIZE, &acpi_desc->dimm_dsm_force_en);
-	set_bit(ND_CMD_GET_CONFIG_DATA, &acpi_desc->dimm_dsm_force_en);
-	set_bit(ND_CMD_SET_CONFIG_DATA, &acpi_desc->dimm_dsm_force_en);
-	set_bit(ND_CMD_ARS_CAP, &acpi_desc->bus_dsm_force_en);
-	set_bit(ND_CMD_ARS_START, &acpi_desc->bus_dsm_force_en);
-	set_bit(ND_CMD_ARS_STATUS, &acpi_desc->bus_dsm_force_en);
-	set_bit(ND_CMD_CLEAR_ERROR, &acpi_desc->bus_dsm_force_en);
+	set_bit(ND_CMD_GET_CONFIG_SIZE, &acpi_desc->dimm_cmd_force_en);
+	set_bit(ND_CMD_GET_CONFIG_DATA, &acpi_desc->dimm_cmd_force_en);
+	set_bit(ND_CMD_SET_CONFIG_DATA, &acpi_desc->dimm_cmd_force_en);
+	set_bit(ND_CMD_SMART, &acpi_desc->dimm_cmd_force_en);
+	set_bit(ND_CMD_ARS_CAP, &acpi_desc->bus_cmd_force_en);
+	set_bit(ND_CMD_ARS_START, &acpi_desc->bus_cmd_force_en);
+	set_bit(ND_CMD_ARS_STATUS, &acpi_desc->bus_cmd_force_en);
+	set_bit(ND_CMD_CLEAR_ERROR, &acpi_desc->bus_cmd_force_en);
+	set_bit(ND_CMD_SMART_THRESHOLD, &acpi_desc->dimm_cmd_force_en);
 }
 
 static void nfit_test1_setup(struct nfit_test *t)
@@ -1315,10 +1375,10 @@ static void nfit_test1_setup(struct nfit_test *t)
 	post_ars_status(&t->ars_state, t->spa_set_dma[0], SPA2_SIZE);
 
 	acpi_desc = &t->acpi_desc;
-	set_bit(ND_CMD_ARS_CAP, &acpi_desc->bus_dsm_force_en);
-	set_bit(ND_CMD_ARS_START, &acpi_desc->bus_dsm_force_en);
-	set_bit(ND_CMD_ARS_STATUS, &acpi_desc->bus_dsm_force_en);
-	set_bit(ND_CMD_CLEAR_ERROR, &acpi_desc->bus_dsm_force_en);
+	set_bit(ND_CMD_ARS_CAP, &acpi_desc->bus_cmd_force_en);
+	set_bit(ND_CMD_ARS_START, &acpi_desc->bus_cmd_force_en);
+	set_bit(ND_CMD_ARS_STATUS, &acpi_desc->bus_cmd_force_en);
+	set_bit(ND_CMD_CLEAR_ERROR, &acpi_desc->bus_cmd_force_en);
 }
 
 static int nfit_test_blk_do_io(struct nd_blk_region *ndbr, resource_size_t dpa,