From nobody Fri Oct 3 19:11:50 2025 Received: from smtp.kernel.org (aws-us-west-2-korg-mail-1.web.codeaurora.org [10.30.226.201]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (No client certificate requested) by smtp.subspace.kernel.org (Postfix) with ESMTPS id 8670D17B505; Tue, 26 Aug 2025 08:04:40 +0000 (UTC) Authentication-Results: smtp.subspace.kernel.org; arc=none smtp.client-ip=10.30.226.201 ARC-Seal: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1756195480; cv=none; b=b+aGK5X1cjyxA9suJuzjKJvM0QnVsdwvZrZe6Bh9jsz5Ja9D0NTrjd/rC5meTTYsoIaep+MGKTHH1pX+tzgxahccqx8CVB9tZxOWNiMnWmDEhq9IQ2uMFMT8YaZ1wuxJ25VDbUva+qD5/EO239KEtyIiXFtPpBpa5sqxz9Lbw2g= ARC-Message-Signature: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1756195480; c=relaxed/simple; bh=0wPoe/3MAh9xsVV1QEIy2QbhyZ1GWQaZL32ILILoEsU=; h=From:To:Cc:Subject:Date:Message-ID:In-Reply-To:References: MIME-Version; b=MSlTvGIfpy72JDtVaE5W/S4yF4q70nE0yQCqJTYPQ6aTxIj5NRQLmFYFf6ilJ22ht4JxJhW/jrISk2it86Q6kEMXnMVauJDdJZgoJY06rMH4tUgPWkO85FYTbh6fIM1ddbKVIhhIGx0dAAT2FLHxrhhM4elYuFXydP7BHFoZAgo= ARC-Authentication-Results: i=1; smtp.subspace.kernel.org; dkim=pass (2048-bit key) header.d=kernel.org header.i=@kernel.org header.b=BW7zhk7D; arc=none smtp.client-ip=10.30.226.201 Authentication-Results: smtp.subspace.kernel.org; dkim=pass (2048-bit key) header.d=kernel.org header.i=@kernel.org header.b="BW7zhk7D" Received: by smtp.kernel.org (Postfix) with ESMTPSA id 89854C116B1; Tue, 26 Aug 2025 08:04:37 +0000 (UTC) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/simple; d=kernel.org; s=k20201202; t=1756195480; bh=0wPoe/3MAh9xsVV1QEIy2QbhyZ1GWQaZL32ILILoEsU=; h=From:To:Cc:Subject:Date:In-Reply-To:References:From; b=BW7zhk7DmCwH3NJL7lurvl/39EkGXAydG1oUYufA1HRHqSqOOfdi7NqnNIAIqcsYv V6OxMT7A0SlsqCAZdqU7uY3+LMojflpjSkblFFR/TYusHv6e0LHiRTivTOHU66TvNQ 1AQvhKxIVVt6VxF/vwgPt/kQ7weBX9Aj6NlXvJQrP8Q5GbqAJqCFjhelLl/CcUAVp5 HJu/ctRSPtPXQlcswEkUAwnRnmFS+lJdwrr7SGr+VEanhzPMTyuaSbiJ8UCKIab6MC tUKuYV5KpHu4h9zeQj771iEX0j3xEgHz1cLBNQ9eo+8w95UkrGcW7vwAt3pcwjEJ3Q U0WmAuIx7KC3g== From: Mike Rapoport To: Dan Williams , Dave Jiang , Ira Weiny , Vishal Verma Cc: jane.chu@oracle.com, Mike Rapoport , Pasha Tatashin , Tyler Hicks , linux-kernel@vger.kernel.org, nvdimm@lists.linux.dev Subject: [PATCH 1/1] nvdimm: allow exposing RAM carveouts as NVDIMM DIMM devices Date: Tue, 26 Aug 2025 11:04:30 +0300 Message-ID: <20250826080430.1952982-2-rppt@kernel.org> X-Mailer: git-send-email 2.50.1 In-Reply-To: <20250826080430.1952982-1-rppt@kernel.org> References: <20250826080430.1952982-1-rppt@kernel.org> Precedence: bulk X-Mailing-List: linux-kernel@vger.kernel.org List-Id: List-Subscribe: List-Unsubscribe: MIME-Version: 1.0 Content-Transfer-Encoding: quoted-printable Content-Type: text/plain; charset="utf-8" From: "Mike Rapoport (Microsoft)" There are use cases, for example virtual machine hosts, that create "persistent" memory regions using memmap=3D 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 and sometimes they even require firmware update. 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) --- drivers/nvdimm/ramdax.c | 281 ++++++++++++++++++++++++++++++++++++++++ 1 file changed, 281 insertions(+) create mode 100644 drivers/nvdimm/ramdax.c diff --git a/drivers/nvdimm/ramdax.c b/drivers/nvdimm/ramdax.c new file mode 100644 index 000000000000..27c5102f600c --- /dev/null +++ b/drivers/nvdimm/ramdax.c @@ -0,0 +1,281 @@ +// 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 +#include +#include +#include +#include +#include +#include +#include + +#include + +#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 =3D 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 =3D phys_to_target_node(res->start); + + nd_set =3D kzalloc(sizeof(*nd_set), GFP_KERNEL); + if (!nd_set) + return -ENOMEM; + + nd_set->cookie1 =3D 0xcafebeefcafebeef; + nd_set->cookie2 =3D nd_set->cookie1; + nd_set->altcookie =3D nd_set->cookie1; + + memset(&mapping, 0, sizeof(mapping)); + mapping.nvdimm =3D nvdimm; + mapping.start =3D 0; + mapping.size =3D resource_size(res) - LABEL_AREA_SIZE; + + memset(&ndr_desc, 0, sizeof(ndr_desc)); + ndr_desc.res =3D res; + ndr_desc.numa_node =3D numa_map_to_online_node(nid); + ndr_desc.target_node =3D nid; + ndr_desc.num_mappings =3D 1; + ndr_desc.mapping =3D &mapping; + ndr_desc.nd_set =3D 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 =3D res->start; + resource_size_t size =3D resource_size(res); + unsigned long flags =3D 0, cmd_mask =3D 0; + struct nvdimm_bus *nvdimm_bus =3D data; + struct ramdax_dimm *dimm; + int err; + + dimm =3D kzalloc(sizeof(*dimm), GFP_KERNEL); + if (!dimm) + return -ENOMEM; + + dimm->label_area =3D 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 =3D nvdimm_create(nvdimm_bus, dimm, + /* dimm_attribute_groups */ NULL, + flags, cmd_mask, 0, NULL); + if (!dimm->nvdimm) { + err =3D -ENOMEM; + goto err_unmap_label; + } + + err =3D 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 =3D (struct nd_cmd_get_config_size){ + .status =3D 0, + .config_size =3D LABEL_AREA_SIZE, + .max_xfer =3D 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 =3D 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, cmd->in_length); + + 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 =3D 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, cmd->in_length); + + return 0; +} + +static int ramdax_nvdimm_ctl(struct nvdimm *nvdimm, unsigned int cmd, + void *buf, unsigned int buf_len) +{ + unsigned long cmd_mask =3D 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 =3D 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 =3D 0; i < pdev->num_resources; i++) { + err =3D 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 =3D &pdev->dev; + struct nvdimm_bus *nvdimm_bus; + struct device_node *np; + int rc =3D -ENXIO; + + nd_desc.provider_name =3D "ramdax"; + nd_desc.module =3D THIS_MODULE; + nd_desc.ndctl =3D ramdax_ctl; + nvdimm_bus =3D nvdimm_bus_register(dev, &nd_desc); + if (!nvdimm_bus) + goto err; + + np =3D dev_of_node(&pdev->dev); + if (np) + rc =3D ramdax_probe_of(pdev, nvdimm_bus, np); + else + rc =3D 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[] =3D { + { .compatible =3D "pmem-region", }, + { }, +}; +MODULE_DEVICE_TABLE(of, ramdax_of_matches); +#endif + +static struct platform_driver ramdax_driver =3D { + .probe =3D ramdax_probe, + .remove =3D ramdax_remove, + .driver =3D { + .name =3D "e820_pmem", + .of_match_table =3D of_match_ptr(ramdax_of_matches), + }, +}; + +module_platform_driver(ramdax_driver); + +MODULE_DESCRIPTION("NVDIMM support for e820 type-12 memory and OF pmem-reg= ion"); +MODULE_LICENSE("GPL"); +MODULE_AUTHOR("Microsoft Corporation"); --=20 2.50.1