[RFC PATCH 0/1] nvdimm: allow exposing RAM as libnvdimm DIMMs

[RFC PATCH 0/1] nvdimm: allow exposing RAM as libnvdimm DIMMs

[Mike Rapoport]

From: "Mike Rapoport (Microsoft)" <rppt@kernel.org>

Hi,

It's not uncommon that libnvdimm/dax/ndctl are used with normal volatile
memory for a whole bunch of $reasons.

Probably the most common usecase is to back VMs memory with fsdax/devdax,
but there are others as well when there's a requirement to manage memory
separately from the kernel.

The existing mechanisms to expose normal ram as "persistent", such as
memmap=x!y on x86 or dummy pmem-region device tree nodes on DT systems lack
flexibility to dynamically partition a single region without rebooting the
system. Also, to create several DAX devices with different properties it's
necessary to repeat the memmap= command line option or add several
pmem-region nodes to the DT.

I propose a new driver that will create a DIMM device on
E820_TYPE_PRAM/pmem-region and that will allow partitioning that device
dynamically. The label area is kept in the end of that region and managed
by the driver.

Mike Rapoport (Microsoft) (1):
  nvdimm: allow exposing RAM carveouts as NVDIMM DIMM devices

 drivers/nvdimm/Kconfig  |  15 +++
 drivers/nvdimm/Makefile |   1 +
 drivers/nvdimm/ramdax.c | 279 ++++++++++++++++++++++++++++++++++++++++
 3 files changed, 295 insertions(+)
 create mode 100644 drivers/nvdimm/ramdax.c


base-commit: 19272b37aa4f83ca52bdf9c16d5d81bdd1354494
-- 
2.47.2

[RFC PATCH 1/1] nvdimm: allow exposing RAM carveouts as NVDIMM DIMM devices

[Mike Rapoport]

From: "Mike Rapoport (Microsoft)" <rppt@kernel.org>

There are use cases, for example virtual machine hosts, that create
"persistent" memory regions using memmap= option on x86 or dummy
pmem-region device tree nodes on DT based systems.

Both these options are inflexible because they create static regions and
the layout of the "persistent" memory cannot be adjusted without reboot.

Add a ramdax driver that allows creation of DIMM devices on top of
E820_TYPE_PRAM regions and devicetree pmem-region nodes.

The DIMMs support label space management on the "device" and provide a
flexible way to access RAM using fsdax and devdax.

Signed-off-by: Mike Rapoport (Mircosoft) <rppt@kernel.org>
---
 drivers/nvdimm/Kconfig  |  15 +++
 drivers/nvdimm/Makefile |   1 +
 drivers/nvdimm/ramdax.c | 279 ++++++++++++++++++++++++++++++++++++++++
 3 files changed, 295 insertions(+)
 create mode 100644 drivers/nvdimm/ramdax.c

diff --git a/drivers/nvdimm/Kconfig b/drivers/nvdimm/Kconfig
index fde3e17c836c..7aae74a29f10 100644
--- a/drivers/nvdimm/Kconfig
+++ b/drivers/nvdimm/Kconfig
@@ -97,6 +97,21 @@ config OF_PMEM
 
 	  Select Y if unsure.
 
+config RAMDAX
+	tristate "Support persistent memory interfaces on RAM carveouts"
+	depends on OF || (X86 && X86_PMEM_LEGACY=n)
+	select X86_PMEM_LEGACY_DEVICE
+	default LIBNVDIMM
+	help
+	  Allows creation of DAX devices on RAM carveouts.
+
+	  Memory ranges that are manually specified by the
+	  'memmap=nn[KMG]!ss[KMG]' kernel command line or defined by dummy
+	  pmem-region device tree nodes would be managed by this driver as DIMM
+	  devices with support for dynamic layout of namespaces.
+
+	  Select N if unsure.
+
 config NVDIMM_KEYS
 	def_bool y
 	depends on ENCRYPTED_KEYS
diff --git a/drivers/nvdimm/Makefile b/drivers/nvdimm/Makefile
index ba0296dca9db..8c268814936c 100644
--- a/drivers/nvdimm/Makefile
+++ b/drivers/nvdimm/Makefile
@@ -5,6 +5,7 @@ obj-$(CONFIG_ND_BTT) += nd_btt.o
 obj-$(CONFIG_X86_PMEM_LEGACY) += nd_e820.o
 obj-$(CONFIG_OF_PMEM) += of_pmem.o
 obj-$(CONFIG_VIRTIO_PMEM) += virtio_pmem.o nd_virtio.o
+obj-$(CONFIG_RAMDAX) += ramdax.o
 
 nd_pmem-y := pmem.o
 
diff --git a/drivers/nvdimm/ramdax.c b/drivers/nvdimm/ramdax.c
new file mode 100644
index 000000000000..67b0a240c0ae
--- /dev/null
+++ b/drivers/nvdimm/ramdax.c
@@ -0,0 +1,279 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (c) 2015, Mike Rapoport, Microsoft
+ *
+ * Based on e820 pmem driver:
+ * Copyright (c) 2015, Christoph Hellwig.
+ * Copyright (c) 2015, Intel Corporation.
+ */
+#include <linux/platform_device.h>
+#include <linux/memory_hotplug.h>
+#include <linux/libnvdimm.h>
+#include <linux/module.h>
+#include <linux/numa.h>
+#include <linux/io.h>
+#include <linux/of.h>
+
+#include <uapi/linux/ndctl.h>
+
+#define LABEL_AREA_SIZE	SZ_128K
+
+struct ramdax_dimm {
+	struct nvdimm *nvdimm;
+	void *label_area;
+};
+
+static void ramdax_remove(struct platform_device *pdev)
+{
+	struct nvdimm_bus *nvdimm_bus = platform_get_drvdata(pdev);
+
+	/* FIXME: cleanup dimm and region devices */
+
+	nvdimm_bus_unregister(nvdimm_bus);
+}
+
+static int ramdax_register_region(struct resource *res,
+				    struct nvdimm *nvdimm,
+				    struct nvdimm_bus *nvdimm_bus)
+{
+	struct nd_mapping_desc mapping;
+	struct nd_region_desc ndr_desc;
+	struct nd_interleave_set *nd_set;
+	int nid = phys_to_target_node(res->start);
+
+	nd_set = kzalloc(sizeof(*nd_set), GFP_KERNEL);
+	if (!nd_set)
+		return -ENOMEM;
+
+	nd_set->cookie1 = get_random_u64();
+	nd_set->cookie2 = nd_set->cookie1;
+
+	memset(&mapping, 0, sizeof(mapping));
+	mapping.nvdimm = nvdimm;
+	mapping.start = 0;
+	mapping.size = resource_size(res) - LABEL_AREA_SIZE;
+
+	memset(&ndr_desc, 0, sizeof(ndr_desc));
+	ndr_desc.res = res;
+	ndr_desc.numa_node = numa_map_to_online_node(nid);
+	ndr_desc.target_node = nid;
+	ndr_desc.num_mappings = 1;
+	ndr_desc.mapping = &mapping;
+	ndr_desc.nd_set = nd_set;
+
+	if (!nvdimm_pmem_region_create(nvdimm_bus, &ndr_desc))
+		goto err_free_nd_set;
+
+	return 0;
+
+err_free_nd_set:
+	kfree(nd_set);
+	return -ENXIO;
+}
+
+static int ramdax_register_dimm(struct resource *res, void *data)
+{
+	resource_size_t start = res->start;
+	resource_size_t size = resource_size(res);
+	unsigned long flags = 0, cmd_mask = 0;
+	struct nvdimm_bus *nvdimm_bus = data;
+	struct ramdax_dimm *dimm;
+	int err;
+
+	dimm = kzalloc(sizeof(*dimm), GFP_KERNEL);
+	if (!dimm)
+		return -ENOMEM;
+
+	dimm->label_area = memremap(start + size - LABEL_AREA_SIZE,
+				    LABEL_AREA_SIZE, MEMREMAP_WB);
+	if (!dimm->label_area)
+		goto err_free_dimm;
+
+	set_bit(NDD_LABELING, &flags);
+	set_bit(NDD_REGISTER_SYNC, &flags);
+	set_bit(ND_CMD_GET_CONFIG_SIZE, &cmd_mask);
+	set_bit(ND_CMD_GET_CONFIG_DATA, &cmd_mask);
+	set_bit(ND_CMD_SET_CONFIG_DATA, &cmd_mask);
+	dimm->nvdimm = nvdimm_create(nvdimm_bus, dimm,
+				     /* dimm_attribute_groups */ NULL,
+				     flags, cmd_mask, 0, NULL);
+	if (!dimm->nvdimm) {
+		err = -ENOMEM;
+		goto err_unmap_label;
+	}
+
+	err = ramdax_register_region(res, dimm->nvdimm, nvdimm_bus);
+	if (err)
+		goto err_remove_nvdimm;
+
+	return 0;
+
+err_remove_nvdimm:
+	nvdimm_delete(dimm->nvdimm);
+err_unmap_label:
+	memunmap(dimm->label_area);
+err_free_dimm:
+	kfree(dimm);
+	return err;
+}
+
+static int ramdax_get_config_size(struct nvdimm *nvdimm, int buf_len,
+				    struct nd_cmd_get_config_size *cmd)
+{
+	if (sizeof(*cmd) > buf_len)
+		return -EINVAL;
+
+	*cmd = (struct nd_cmd_get_config_size){
+		.status = 0,
+		.config_size = LABEL_AREA_SIZE,
+		.max_xfer = 8,
+	};
+
+	return 0;
+}
+
+static int ramdax_get_config_data(struct nvdimm *nvdimm, int buf_len,
+				    struct nd_cmd_get_config_data_hdr *cmd)
+{
+	struct ramdax_dimm *dimm = nvdimm_provider_data(nvdimm);
+
+	if (sizeof(*cmd) > buf_len)
+		return -EINVAL;
+	if (struct_size(cmd, out_buf, cmd->in_length) > buf_len)
+		return -EINVAL;
+	if (cmd->in_offset + cmd->in_length > LABEL_AREA_SIZE)
+		return -EINVAL;
+
+	memcpy(cmd->out_buf, dimm->label_area + cmd->in_offset, buf_len);
+
+	return 0;
+}
+
+static int ramdax_set_config_data(struct nvdimm *nvdimm, int buf_len,
+				    struct nd_cmd_set_config_hdr *cmd)
+{
+	struct ramdax_dimm *dimm = nvdimm_provider_data(nvdimm);
+
+	if (sizeof(*cmd) > buf_len)
+		return -EINVAL;
+	if (struct_size(cmd, in_buf, cmd->in_length) > buf_len)
+		return -EINVAL;
+	if (cmd->in_offset + cmd->in_length > LABEL_AREA_SIZE)
+		return -EINVAL;
+
+	memcpy(dimm->label_area + cmd->in_offset, cmd->in_buf, buf_len);
+
+	return 0;
+}
+
+static int ramdax_nvdimm_ctl(struct nvdimm *nvdimm, unsigned int cmd,
+			       void *buf, unsigned int buf_len)
+{
+	unsigned long cmd_mask = nvdimm_cmd_mask(nvdimm);
+
+	if (!test_bit(cmd, &cmd_mask))
+		return -ENOTTY;
+
+	switch (cmd) {
+	case ND_CMD_GET_CONFIG_SIZE:
+		return ramdax_get_config_size(nvdimm, buf_len, buf);
+	case ND_CMD_GET_CONFIG_DATA:
+		return ramdax_get_config_data(nvdimm, buf_len, buf);
+	case ND_CMD_SET_CONFIG_DATA:
+		return ramdax_set_config_data(nvdimm, buf_len, buf);
+	default:
+		return -ENOTTY;
+	}
+}
+
+static int ramdax_ctl(struct nvdimm_bus_descriptor *nd_desc,
+			 struct nvdimm *nvdimm, unsigned int cmd, void *buf,
+			 unsigned int buf_len, int *cmd_rc)
+{
+	/*
+	 * No firmware response to translate, let the transport error
+	 * code take precedence.
+	 */
+	*cmd_rc = 0;
+
+	if (!nvdimm)
+		return -ENOTTY;
+	return ramdax_nvdimm_ctl(nvdimm, cmd, buf, buf_len);
+}
+
+static int ramdax_probe_of(struct platform_device *pdev,
+			     struct nvdimm_bus *bus, struct device_node *np)
+{
+	int err;
+
+	for (int i = 0; i < pdev->num_resources; i++) {
+		err = ramdax_register_dimm(&pdev->resource[i], bus);
+		if (err)
+			goto err_unregister;
+	}
+
+	return 0;
+
+err_unregister:
+	/*
+	 * FIXME: should we unregister the dimms that were registered
+	 * successfully
+	 */
+	return err;
+}
+
+static int ramdax_probe(struct platform_device *pdev)
+{
+	static struct nvdimm_bus_descriptor nd_desc;
+	struct device *dev = &pdev->dev;
+	struct nvdimm_bus *nvdimm_bus;
+	struct device_node *np;
+	int rc = -ENXIO;
+
+	nd_desc.provider_name = "ramdax";
+	nd_desc.module = THIS_MODULE;
+	nd_desc.ndctl = ramdax_ctl;
+	nvdimm_bus = nvdimm_bus_register(dev, &nd_desc);
+	if (!nvdimm_bus)
+		goto err;
+
+	np = dev_of_node(&pdev->dev);
+	if (np)
+		rc = ramdax_probe_of(pdev, nvdimm_bus, np);
+	else
+		rc = walk_iomem_res_desc(IORES_DESC_PERSISTENT_MEMORY_LEGACY,
+					 IORESOURCE_MEM, 0, -1, nvdimm_bus,
+					 ramdax_register_dimm);
+	if (rc)
+		goto err;
+
+	platform_set_drvdata(pdev, nvdimm_bus);
+
+	return 0;
+err:
+	nvdimm_bus_unregister(nvdimm_bus);
+	return rc;
+}
+
+#ifdef CONFIG_OF
+static const struct of_device_id ramdax_of_matches[] = {
+	{ .compatible = "pmem-region", },
+	{ },
+};
+MODULE_DEVICE_TABLE(of, ramdax_of_matches);
+#endif
+
+static struct platform_driver ramdax_driver = {
+	.probe = ramdax_probe,
+	.remove = ramdax_remove,
+	.driver = {
+		.name = "e820_pmem",
+		.of_match_table = of_match_ptr(ramdax_of_matches),
+	},
+};
+
+module_platform_driver(ramdax_driver);
+
+MODULE_DESCRIPTION("NVDIMM support for e820 type-12 memory and OF pmem-region");
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Microsoft Corporation");
-- 
2.47.2

Re: [RFC PATCH 1/1] nvdimm: allow exposing RAM carveouts as NVDIMM DIMM devices

[jane.chu]

On 6/12/2025 1:31 AM, Mike Rapoport wrote:
> From: "Mike Rapoport (Microsoft)" <rppt@kernel.org>
> 
> There are use cases, for example virtual machine hosts, that create
> "persistent" memory regions using memmap= option on x86 or dummy
> pmem-region device tree nodes on DT based systems.
> 
> Both these options are inflexible because they create static regions and
> the layout of the "persistent" memory cannot be adjusted without reboot.
> 
> Add a ramdax driver that allows creation of DIMM devices on top of
> E820_TYPE_PRAM regions and devicetree pmem-region nodes.
> 
> The DIMMs support label space management on the "device" and provide a
> flexible way to access RAM using fsdax and devdax.

Just curious, how does the new driver work with Michal Clapinski's 
recent patch that adds 
"nd_e820.pmem=ss[KMG],nn[KMG][,mode=fsdax/devdax,align=aa[KMG]]" kernel 
parameter ?

thanks,
-jane

> 
> Signed-off-by: Mike Rapoport (Mircosoft) <rppt@kernel.org>
> ---
>   drivers/nvdimm/Kconfig  |  15 +++
>   drivers/nvdimm/Makefile |   1 +
>   drivers/nvdimm/ramdax.c | 279 ++++++++++++++++++++++++++++++++++++++++
>   3 files changed, 295 insertions(+)
>   create mode 100644 drivers/nvdimm/ramdax.c
> 
> diff --git a/drivers/nvdimm/Kconfig b/drivers/nvdimm/Kconfig
> index fde3e17c836c..7aae74a29f10 100644
> --- a/drivers/nvdimm/Kconfig
> +++ b/drivers/nvdimm/Kconfig
> @@ -97,6 +97,21 @@ config OF_PMEM
>   
>   	  Select Y if unsure.
>   
> +config RAMDAX
> +	tristate "Support persistent memory interfaces on RAM carveouts"
> +	depends on OF || (X86 && X86_PMEM_LEGACY=n)
> +	select X86_PMEM_LEGACY_DEVICE
> +	default LIBNVDIMM
> +	help
> +	  Allows creation of DAX devices on RAM carveouts.
> +
> +	  Memory ranges that are manually specified by the
> +	  'memmap=nn[KMG]!ss[KMG]' kernel command line or defined by dummy
> +	  pmem-region device tree nodes would be managed by this driver as DIMM
> +	  devices with support for dynamic layout of namespaces.
> +
> +	  Select N if unsure.
> +
>   config NVDIMM_KEYS
>   	def_bool y
>   	depends on ENCRYPTED_KEYS
> diff --git a/drivers/nvdimm/Makefile b/drivers/nvdimm/Makefile
> index ba0296dca9db..8c268814936c 100644
> --- a/drivers/nvdimm/Makefile
> +++ b/drivers/nvdimm/Makefile
> @@ -5,6 +5,7 @@ obj-$(CONFIG_ND_BTT) += nd_btt.o
>   obj-$(CONFIG_X86_PMEM_LEGACY) += nd_e820.o
>   obj-$(CONFIG_OF_PMEM) += of_pmem.o
>   obj-$(CONFIG_VIRTIO_PMEM) += virtio_pmem.o nd_virtio.o
> +obj-$(CONFIG_RAMDAX) += ramdax.o
>   
>   nd_pmem-y := pmem.o
>   
> diff --git a/drivers/nvdimm/ramdax.c b/drivers/nvdimm/ramdax.c
> new file mode 100644
> index 000000000000..67b0a240c0ae
> --- /dev/null
> +++ b/drivers/nvdimm/ramdax.c
> @@ -0,0 +1,279 @@
> +// SPDX-License-Identifier: GPL-2.0-only
> +/*
> + * Copyright (c) 2015, Mike Rapoport, Microsoft
> + *
> + * Based on e820 pmem driver:
> + * Copyright (c) 2015, Christoph Hellwig.
> + * Copyright (c) 2015, Intel Corporation.
> + */
> +#include <linux/platform_device.h>
> +#include <linux/memory_hotplug.h>
> +#include <linux/libnvdimm.h>
> +#include <linux/module.h>
> +#include <linux/numa.h>
> +#include <linux/io.h>
> +#include <linux/of.h>
> +
> +#include <uapi/linux/ndctl.h>
> +
> +#define LABEL_AREA_SIZE	SZ_128K
> +
> +struct ramdax_dimm {
> +	struct nvdimm *nvdimm;
> +	void *label_area;
> +};
> +
> +static void ramdax_remove(struct platform_device *pdev)
> +{
> +	struct nvdimm_bus *nvdimm_bus = platform_get_drvdata(pdev);
> +
> +	/* FIXME: cleanup dimm and region devices */
> +
> +	nvdimm_bus_unregister(nvdimm_bus);
> +}
> +
> +static int ramdax_register_region(struct resource *res,
> +				    struct nvdimm *nvdimm,
> +				    struct nvdimm_bus *nvdimm_bus)
> +{
> +	struct nd_mapping_desc mapping;
> +	struct nd_region_desc ndr_desc;
> +	struct nd_interleave_set *nd_set;
> +	int nid = phys_to_target_node(res->start);
> +
> +	nd_set = kzalloc(sizeof(*nd_set), GFP_KERNEL);
> +	if (!nd_set)
> +		return -ENOMEM;
> +
> +	nd_set->cookie1 = get_random_u64();
> +	nd_set->cookie2 = nd_set->cookie1;
> +
> +	memset(&mapping, 0, sizeof(mapping));
> +	mapping.nvdimm = nvdimm;
> +	mapping.start = 0;
> +	mapping.size = resource_size(res) - LABEL_AREA_SIZE;
> +
> +	memset(&ndr_desc, 0, sizeof(ndr_desc));
> +	ndr_desc.res = res;
> +	ndr_desc.numa_node = numa_map_to_online_node(nid);
> +	ndr_desc.target_node = nid;
> +	ndr_desc.num_mappings = 1;
> +	ndr_desc.mapping = &mapping;
> +	ndr_desc.nd_set = nd_set;
> +
> +	if (!nvdimm_pmem_region_create(nvdimm_bus, &ndr_desc))
> +		goto err_free_nd_set;
> +
> +	return 0;
> +
> +err_free_nd_set:
> +	kfree(nd_set);
> +	return -ENXIO;
> +}
> +
> +static int ramdax_register_dimm(struct resource *res, void *data)
> +{
> +	resource_size_t start = res->start;
> +	resource_size_t size = resource_size(res);
> +	unsigned long flags = 0, cmd_mask = 0;
> +	struct nvdimm_bus *nvdimm_bus = data;
> +	struct ramdax_dimm *dimm;
> +	int err;
> +
> +	dimm = kzalloc(sizeof(*dimm), GFP_KERNEL);
> +	if (!dimm)
> +		return -ENOMEM;
> +
> +	dimm->label_area = memremap(start + size - LABEL_AREA_SIZE,
> +				    LABEL_AREA_SIZE, MEMREMAP_WB);
> +	if (!dimm->label_area)
> +		goto err_free_dimm;
> +
> +	set_bit(NDD_LABELING, &flags);
> +	set_bit(NDD_REGISTER_SYNC, &flags);
> +	set_bit(ND_CMD_GET_CONFIG_SIZE, &cmd_mask);
> +	set_bit(ND_CMD_GET_CONFIG_DATA, &cmd_mask);
> +	set_bit(ND_CMD_SET_CONFIG_DATA, &cmd_mask);
> +	dimm->nvdimm = nvdimm_create(nvdimm_bus, dimm,
> +				     /* dimm_attribute_groups */ NULL,
> +				     flags, cmd_mask, 0, NULL);
> +	if (!dimm->nvdimm) {
> +		err = -ENOMEM;
> +		goto err_unmap_label;
> +	}
> +
> +	err = ramdax_register_region(res, dimm->nvdimm, nvdimm_bus);
> +	if (err)
> +		goto err_remove_nvdimm;
> +
> +	return 0;
> +
> +err_remove_nvdimm:
> +	nvdimm_delete(dimm->nvdimm);
> +err_unmap_label:
> +	memunmap(dimm->label_area);
> +err_free_dimm:
> +	kfree(dimm);
> +	return err;
> +}
> +
> +static int ramdax_get_config_size(struct nvdimm *nvdimm, int buf_len,
> +				    struct nd_cmd_get_config_size *cmd)
> +{
> +	if (sizeof(*cmd) > buf_len)
> +		return -EINVAL;
> +
> +	*cmd = (struct nd_cmd_get_config_size){
> +		.status = 0,
> +		.config_size = LABEL_AREA_SIZE,
> +		.max_xfer = 8,
> +	};
> +
> +	return 0;
> +}
> +
> +static int ramdax_get_config_data(struct nvdimm *nvdimm, int buf_len,
> +				    struct nd_cmd_get_config_data_hdr *cmd)
> +{
> +	struct ramdax_dimm *dimm = nvdimm_provider_data(nvdimm);
> +
> +	if (sizeof(*cmd) > buf_len)
> +		return -EINVAL;
> +	if (struct_size(cmd, out_buf, cmd->in_length) > buf_len)
> +		return -EINVAL;
> +	if (cmd->in_offset + cmd->in_length > LABEL_AREA_SIZE)
> +		return -EINVAL;
> +
> +	memcpy(cmd->out_buf, dimm->label_area + cmd->in_offset, buf_len);
> +
> +	return 0;
> +}
> +
> +static int ramdax_set_config_data(struct nvdimm *nvdimm, int buf_len,
> +				    struct nd_cmd_set_config_hdr *cmd)
> +{
> +	struct ramdax_dimm *dimm = nvdimm_provider_data(nvdimm);
> +
> +	if (sizeof(*cmd) > buf_len)
> +		return -EINVAL;
> +	if (struct_size(cmd, in_buf, cmd->in_length) > buf_len)
> +		return -EINVAL;
> +	if (cmd->in_offset + cmd->in_length > LABEL_AREA_SIZE)
> +		return -EINVAL;
> +
> +	memcpy(dimm->label_area + cmd->in_offset, cmd->in_buf, buf_len);
> +
> +	return 0;
> +}
> +
> +static int ramdax_nvdimm_ctl(struct nvdimm *nvdimm, unsigned int cmd,
> +			       void *buf, unsigned int buf_len)
> +{
> +	unsigned long cmd_mask = nvdimm_cmd_mask(nvdimm);
> +
> +	if (!test_bit(cmd, &cmd_mask))
> +		return -ENOTTY;
> +
> +	switch (cmd) {
> +	case ND_CMD_GET_CONFIG_SIZE:
> +		return ramdax_get_config_size(nvdimm, buf_len, buf);
> +	case ND_CMD_GET_CONFIG_DATA:
> +		return ramdax_get_config_data(nvdimm, buf_len, buf);
> +	case ND_CMD_SET_CONFIG_DATA:
> +		return ramdax_set_config_data(nvdimm, buf_len, buf);
> +	default:
> +		return -ENOTTY;
> +	}
> +}
> +
> +static int ramdax_ctl(struct nvdimm_bus_descriptor *nd_desc,
> +			 struct nvdimm *nvdimm, unsigned int cmd, void *buf,
> +			 unsigned int buf_len, int *cmd_rc)
> +{
> +	/*
> +	 * No firmware response to translate, let the transport error
> +	 * code take precedence.
> +	 */
> +	*cmd_rc = 0;
> +
> +	if (!nvdimm)
> +		return -ENOTTY;
> +	return ramdax_nvdimm_ctl(nvdimm, cmd, buf, buf_len);
> +}
> +
> +static int ramdax_probe_of(struct platform_device *pdev,
> +			     struct nvdimm_bus *bus, struct device_node *np)
> +{
> +	int err;
> +
> +	for (int i = 0; i < pdev->num_resources; i++) {
> +		err = ramdax_register_dimm(&pdev->resource[i], bus);
> +		if (err)
> +			goto err_unregister;
> +	}
> +
> +	return 0;
> +
> +err_unregister:
> +	/*
> +	 * FIXME: should we unregister the dimms that were registered
> +	 * successfully
> +	 */
> +	return err;
> +}
> +
> +static int ramdax_probe(struct platform_device *pdev)
> +{
> +	static struct nvdimm_bus_descriptor nd_desc;
> +	struct device *dev = &pdev->dev;
> +	struct nvdimm_bus *nvdimm_bus;
> +	struct device_node *np;
> +	int rc = -ENXIO;
> +
> +	nd_desc.provider_name = "ramdax";
> +	nd_desc.module = THIS_MODULE;
> +	nd_desc.ndctl = ramdax_ctl;
> +	nvdimm_bus = nvdimm_bus_register(dev, &nd_desc);
> +	if (!nvdimm_bus)
> +		goto err;
> +
> +	np = dev_of_node(&pdev->dev);
> +	if (np)
> +		rc = ramdax_probe_of(pdev, nvdimm_bus, np);
> +	else
> +		rc = walk_iomem_res_desc(IORES_DESC_PERSISTENT_MEMORY_LEGACY,
> +					 IORESOURCE_MEM, 0, -1, nvdimm_bus,
> +					 ramdax_register_dimm);
> +	if (rc)
> +		goto err;
> +
> +	platform_set_drvdata(pdev, nvdimm_bus);
> +
> +	return 0;
> +err:
> +	nvdimm_bus_unregister(nvdimm_bus);
> +	return rc;
> +}
> +
> +#ifdef CONFIG_OF
> +static const struct of_device_id ramdax_of_matches[] = {
> +	{ .compatible = "pmem-region", },
> +	{ },
> +};
> +MODULE_DEVICE_TABLE(of, ramdax_of_matches);
> +#endif
> +
> +static struct platform_driver ramdax_driver = {
> +	.probe = ramdax_probe,
> +	.remove = ramdax_remove,
> +	.driver = {
> +		.name = "e820_pmem",
> +		.of_match_table = of_match_ptr(ramdax_of_matches),
> +	},
> +};
> +
> +module_platform_driver(ramdax_driver);
> +
> +MODULE_DESCRIPTION("NVDIMM support for e820 type-12 memory and OF pmem-region");
> +MODULE_LICENSE("GPL");
> +MODULE_AUTHOR("Microsoft Corporation");

Re: [RFC PATCH 1/1] nvdimm: allow exposing RAM carveouts as NVDIMM DIMM devices

[Mike Rapoport]

On Thu, Jun 12, 2025 at 02:12:42PM -0700, jane.chu@oracle.com wrote:
> 
> On 6/12/2025 1:31 AM, Mike Rapoport wrote:
> > From: "Mike Rapoport (Microsoft)" <rppt@kernel.org>
> > 
> > There are use cases, for example virtual machine hosts, that create
> > "persistent" memory regions using memmap= option on x86 or dummy
> > pmem-region device tree nodes on DT based systems.
> > 
> > Both these options are inflexible because they create static regions and
> > the layout of the "persistent" memory cannot be adjusted without reboot.
> > 
> > Add a ramdax driver that allows creation of DIMM devices on top of
> > E820_TYPE_PRAM regions and devicetree pmem-region nodes.
> > 
> > The DIMMs support label space management on the "device" and provide a
> > flexible way to access RAM using fsdax and devdax.
> 
> Just curious, how does the new driver work with Michal Clapinski's recent
> patch that adds
> "nd_e820.pmem=ss[KMG],nn[KMG][,mode=fsdax/devdax,align=aa[KMG]]" kernel
> parameter ?

The new driver and nd_e820 are mutually exclusive. 
 
> thanks,
> -jane
> 
> > 
> > Signed-off-by: Mike Rapoport (Mircosoft) <rppt@kernel.org>
> > ---
> >   drivers/nvdimm/Kconfig  |  15 +++
> >   drivers/nvdimm/Makefile |   1 +
> >   drivers/nvdimm/ramdax.c | 279 ++++++++++++++++++++++++++++++++++++++++
> >   3 files changed, 295 insertions(+)
> >   create mode 100644 drivers/nvdimm/ramdax.c
> > 
> > diff --git a/drivers/nvdimm/Kconfig b/drivers/nvdimm/Kconfig
> > index fde3e17c836c..7aae74a29f10 100644
> > --- a/drivers/nvdimm/Kconfig
> > +++ b/drivers/nvdimm/Kconfig
> > @@ -97,6 +97,21 @@ config OF_PMEM
> >   	  Select Y if unsure.
> > +config RAMDAX
> > +	tristate "Support persistent memory interfaces on RAM carveouts"
> > +	depends on OF || (X86 && X86_PMEM_LEGACY=n)
> > +	select X86_PMEM_LEGACY_DEVICE
> > +	default LIBNVDIMM
> > +	help
> > +	  Allows creation of DAX devices on RAM carveouts.
> > +
> > +	  Memory ranges that are manually specified by the
> > +	  'memmap=nn[KMG]!ss[KMG]' kernel command line or defined by dummy
> > +	  pmem-region device tree nodes would be managed by this driver as DIMM
> > +	  devices with support for dynamic layout of namespaces.
> > +
> > +	  Select N if unsure.
> > +
> >   config NVDIMM_KEYS
> >   	def_bool y
> >   	depends on ENCRYPTED_KEYS
> > diff --git a/drivers/nvdimm/Makefile b/drivers/nvdimm/Makefile
> > index ba0296dca9db..8c268814936c 100644
> > --- a/drivers/nvdimm/Makefile
> > +++ b/drivers/nvdimm/Makefile
> > @@ -5,6 +5,7 @@ obj-$(CONFIG_ND_BTT) += nd_btt.o
> >   obj-$(CONFIG_X86_PMEM_LEGACY) += nd_e820.o
> >   obj-$(CONFIG_OF_PMEM) += of_pmem.o
> >   obj-$(CONFIG_VIRTIO_PMEM) += virtio_pmem.o nd_virtio.o
> > +obj-$(CONFIG_RAMDAX) += ramdax.o
> >   nd_pmem-y := pmem.o
> > diff --git a/drivers/nvdimm/ramdax.c b/drivers/nvdimm/ramdax.c
> > new file mode 100644
> > index 000000000000..67b0a240c0ae
> > --- /dev/null
> > +++ b/drivers/nvdimm/ramdax.c
> > @@ -0,0 +1,279 @@
> > +// SPDX-License-Identifier: GPL-2.0-only
> > +/*
> > + * Copyright (c) 2015, Mike Rapoport, Microsoft
> > + *
> > + * Based on e820 pmem driver:
> > + * Copyright (c) 2015, Christoph Hellwig.
> > + * Copyright (c) 2015, Intel Corporation.
> > + */
> > +#include <linux/platform_device.h>
> > +#include <linux/memory_hotplug.h>
> > +#include <linux/libnvdimm.h>
> > +#include <linux/module.h>
> > +#include <linux/numa.h>
> > +#include <linux/io.h>
> > +#include <linux/of.h>
> > +
> > +#include <uapi/linux/ndctl.h>
> > +
> > +#define LABEL_AREA_SIZE	SZ_128K
> > +
> > +struct ramdax_dimm {
> > +	struct nvdimm *nvdimm;
> > +	void *label_area;
> > +};
> > +
> > +static void ramdax_remove(struct platform_device *pdev)
> > +{
> > +	struct nvdimm_bus *nvdimm_bus = platform_get_drvdata(pdev);
> > +
> > +	/* FIXME: cleanup dimm and region devices */
> > +
> > +	nvdimm_bus_unregister(nvdimm_bus);
> > +}
> > +
> > +static int ramdax_register_region(struct resource *res,
> > +				    struct nvdimm *nvdimm,
> > +				    struct nvdimm_bus *nvdimm_bus)
> > +{
> > +	struct nd_mapping_desc mapping;
> > +	struct nd_region_desc ndr_desc;
> > +	struct nd_interleave_set *nd_set;
> > +	int nid = phys_to_target_node(res->start);
> > +
> > +	nd_set = kzalloc(sizeof(*nd_set), GFP_KERNEL);
> > +	if (!nd_set)
> > +		return -ENOMEM;
> > +
> > +	nd_set->cookie1 = get_random_u64();
> > +	nd_set->cookie2 = nd_set->cookie1;
> > +
> > +	memset(&mapping, 0, sizeof(mapping));
> > +	mapping.nvdimm = nvdimm;
> > +	mapping.start = 0;
> > +	mapping.size = resource_size(res) - LABEL_AREA_SIZE;
> > +
> > +	memset(&ndr_desc, 0, sizeof(ndr_desc));
> > +	ndr_desc.res = res;
> > +	ndr_desc.numa_node = numa_map_to_online_node(nid);
> > +	ndr_desc.target_node = nid;
> > +	ndr_desc.num_mappings = 1;
> > +	ndr_desc.mapping = &mapping;
> > +	ndr_desc.nd_set = nd_set;
> > +
> > +	if (!nvdimm_pmem_region_create(nvdimm_bus, &ndr_desc))
> > +		goto err_free_nd_set;
> > +
> > +	return 0;
> > +
> > +err_free_nd_set:
> > +	kfree(nd_set);
> > +	return -ENXIO;
> > +}
> > +
> > +static int ramdax_register_dimm(struct resource *res, void *data)
> > +{
> > +	resource_size_t start = res->start;
> > +	resource_size_t size = resource_size(res);
> > +	unsigned long flags = 0, cmd_mask = 0;
> > +	struct nvdimm_bus *nvdimm_bus = data;
> > +	struct ramdax_dimm *dimm;
> > +	int err;
> > +
> > +	dimm = kzalloc(sizeof(*dimm), GFP_KERNEL);
> > +	if (!dimm)
> > +		return -ENOMEM;
> > +
> > +	dimm->label_area = memremap(start + size - LABEL_AREA_SIZE,
> > +				    LABEL_AREA_SIZE, MEMREMAP_WB);
> > +	if (!dimm->label_area)
> > +		goto err_free_dimm;
> > +
> > +	set_bit(NDD_LABELING, &flags);
> > +	set_bit(NDD_REGISTER_SYNC, &flags);
> > +	set_bit(ND_CMD_GET_CONFIG_SIZE, &cmd_mask);
> > +	set_bit(ND_CMD_GET_CONFIG_DATA, &cmd_mask);
> > +	set_bit(ND_CMD_SET_CONFIG_DATA, &cmd_mask);
> > +	dimm->nvdimm = nvdimm_create(nvdimm_bus, dimm,
> > +				     /* dimm_attribute_groups */ NULL,
> > +				     flags, cmd_mask, 0, NULL);
> > +	if (!dimm->nvdimm) {
> > +		err = -ENOMEM;
> > +		goto err_unmap_label;
> > +	}
> > +
> > +	err = ramdax_register_region(res, dimm->nvdimm, nvdimm_bus);
> > +	if (err)
> > +		goto err_remove_nvdimm;
> > +
> > +	return 0;
> > +
> > +err_remove_nvdimm:
> > +	nvdimm_delete(dimm->nvdimm);
> > +err_unmap_label:
> > +	memunmap(dimm->label_area);
> > +err_free_dimm:
> > +	kfree(dimm);
> > +	return err;
> > +}
> > +
> > +static int ramdax_get_config_size(struct nvdimm *nvdimm, int buf_len,
> > +				    struct nd_cmd_get_config_size *cmd)
> > +{
> > +	if (sizeof(*cmd) > buf_len)
> > +		return -EINVAL;
> > +
> > +	*cmd = (struct nd_cmd_get_config_size){
> > +		.status = 0,
> > +		.config_size = LABEL_AREA_SIZE,
> > +		.max_xfer = 8,
> > +	};
> > +
> > +	return 0;
> > +}
> > +
> > +static int ramdax_get_config_data(struct nvdimm *nvdimm, int buf_len,
> > +				    struct nd_cmd_get_config_data_hdr *cmd)
> > +{
> > +	struct ramdax_dimm *dimm = nvdimm_provider_data(nvdimm);
> > +
> > +	if (sizeof(*cmd) > buf_len)
> > +		return -EINVAL;
> > +	if (struct_size(cmd, out_buf, cmd->in_length) > buf_len)
> > +		return -EINVAL;
> > +	if (cmd->in_offset + cmd->in_length > LABEL_AREA_SIZE)
> > +		return -EINVAL;
> > +
> > +	memcpy(cmd->out_buf, dimm->label_area + cmd->in_offset, buf_len);
> > +
> > +	return 0;
> > +}
> > +
> > +static int ramdax_set_config_data(struct nvdimm *nvdimm, int buf_len,
> > +				    struct nd_cmd_set_config_hdr *cmd)
> > +{
> > +	struct ramdax_dimm *dimm = nvdimm_provider_data(nvdimm);
> > +
> > +	if (sizeof(*cmd) > buf_len)
> > +		return -EINVAL;
> > +	if (struct_size(cmd, in_buf, cmd->in_length) > buf_len)
> > +		return -EINVAL;
> > +	if (cmd->in_offset + cmd->in_length > LABEL_AREA_SIZE)
> > +		return -EINVAL;
> > +
> > +	memcpy(dimm->label_area + cmd->in_offset, cmd->in_buf, buf_len);
> > +
> > +	return 0;
> > +}
> > +
> > +static int ramdax_nvdimm_ctl(struct nvdimm *nvdimm, unsigned int cmd,
> > +			       void *buf, unsigned int buf_len)
> > +{
> > +	unsigned long cmd_mask = nvdimm_cmd_mask(nvdimm);
> > +
> > +	if (!test_bit(cmd, &cmd_mask))
> > +		return -ENOTTY;
> > +
> > +	switch (cmd) {
> > +	case ND_CMD_GET_CONFIG_SIZE:
> > +		return ramdax_get_config_size(nvdimm, buf_len, buf);
> > +	case ND_CMD_GET_CONFIG_DATA:
> > +		return ramdax_get_config_data(nvdimm, buf_len, buf);
> > +	case ND_CMD_SET_CONFIG_DATA:
> > +		return ramdax_set_config_data(nvdimm, buf_len, buf);
> > +	default:
> > +		return -ENOTTY;
> > +	}
> > +}
> > +
> > +static int ramdax_ctl(struct nvdimm_bus_descriptor *nd_desc,
> > +			 struct nvdimm *nvdimm, unsigned int cmd, void *buf,
> > +			 unsigned int buf_len, int *cmd_rc)
> > +{
> > +	/*
> > +	 * No firmware response to translate, let the transport error
> > +	 * code take precedence.
> > +	 */
> > +	*cmd_rc = 0;
> > +
> > +	if (!nvdimm)
> > +		return -ENOTTY;
> > +	return ramdax_nvdimm_ctl(nvdimm, cmd, buf, buf_len);
> > +}
> > +
> > +static int ramdax_probe_of(struct platform_device *pdev,
> > +			     struct nvdimm_bus *bus, struct device_node *np)
> > +{
> > +	int err;
> > +
> > +	for (int i = 0; i < pdev->num_resources; i++) {
> > +		err = ramdax_register_dimm(&pdev->resource[i], bus);
> > +		if (err)
> > +			goto err_unregister;
> > +	}
> > +
> > +	return 0;
> > +
> > +err_unregister:
> > +	/*
> > +	 * FIXME: should we unregister the dimms that were registered
> > +	 * successfully
> > +	 */
> > +	return err;
> > +}
> > +
> > +static int ramdax_probe(struct platform_device *pdev)
> > +{
> > +	static struct nvdimm_bus_descriptor nd_desc;
> > +	struct device *dev = &pdev->dev;
> > +	struct nvdimm_bus *nvdimm_bus;
> > +	struct device_node *np;
> > +	int rc = -ENXIO;
> > +
> > +	nd_desc.provider_name = "ramdax";
> > +	nd_desc.module = THIS_MODULE;
> > +	nd_desc.ndctl = ramdax_ctl;
> > +	nvdimm_bus = nvdimm_bus_register(dev, &nd_desc);
> > +	if (!nvdimm_bus)
> > +		goto err;
> > +
> > +	np = dev_of_node(&pdev->dev);
> > +	if (np)
> > +		rc = ramdax_probe_of(pdev, nvdimm_bus, np);
> > +	else
> > +		rc = walk_iomem_res_desc(IORES_DESC_PERSISTENT_MEMORY_LEGACY,
> > +					 IORESOURCE_MEM, 0, -1, nvdimm_bus,
> > +					 ramdax_register_dimm);
> > +	if (rc)
> > +		goto err;
> > +
> > +	platform_set_drvdata(pdev, nvdimm_bus);
> > +
> > +	return 0;
> > +err:
> > +	nvdimm_bus_unregister(nvdimm_bus);
> > +	return rc;
> > +}
> > +
> > +#ifdef CONFIG_OF
> > +static const struct of_device_id ramdax_of_matches[] = {
> > +	{ .compatible = "pmem-region", },
> > +	{ },
> > +};
> > +MODULE_DEVICE_TABLE(of, ramdax_of_matches);
> > +#endif
> > +
> > +static struct platform_driver ramdax_driver = {
> > +	.probe = ramdax_probe,
> > +	.remove = ramdax_remove,
> > +	.driver = {
> > +		.name = "e820_pmem",
> > +		.of_match_table = of_match_ptr(ramdax_of_matches),
> > +	},
> > +};
> > +
> > +module_platform_driver(ramdax_driver);
> > +
> > +MODULE_DESCRIPTION("NVDIMM support for e820 type-12 memory and OF pmem-region");
> > +MODULE_LICENSE("GPL");
> > +MODULE_AUTHOR("Microsoft Corporation");
> 

-- 
Sincerely yours,
Mike.