diff options
author | Stephen Rothwell <sfr@canb.auug.org.au> | 2015-06-26 17:20:15 +1000 |
---|---|---|
committer | Stephen Rothwell <sfr@canb.auug.org.au> | 2015-06-26 17:20:15 +1000 |
commit | 7fd49daed4d92a698239fdcaadf57f8e101be1cc (patch) | |
tree | 12cfdc3c2af24cb81e2af14811055743c9330a1b | |
parent | 0926d20039f5f33ddb2df7582ecf5340643fe967 (diff) | |
parent | 0ba1c634892b3590779803a701bcb82e8c32cc7a (diff) |
Merge remote-tracking branch 'nvdimm/libnvdimm-for-next'
Conflicts:
drivers/block/Kconfig
35 files changed, 7188 insertions, 83 deletions
diff --git a/arch/arm64/kernel/efi.c b/arch/arm64/kernel/efi.c index ab21e0d58278..9d4aa18f2a82 100644 --- a/arch/arm64/kernel/efi.c +++ b/arch/arm64/kernel/efi.c @@ -158,6 +158,7 @@ static __init int is_reserve_region(efi_memory_desc_t *md) case EFI_BOOT_SERVICES_CODE: case EFI_BOOT_SERVICES_DATA: case EFI_CONVENTIONAL_MEMORY: + case EFI_PERSISTENT_MEMORY: return 0; default: break; diff --git a/arch/ia64/kernel/efi.c b/arch/ia64/kernel/efi.c index 47e962f7ed5a..caae3f4e4341 100644 --- a/arch/ia64/kernel/efi.c +++ b/arch/ia64/kernel/efi.c @@ -1222,6 +1222,10 @@ efi_initialize_iomem_resources(struct resource *code_resource, flags |= IORESOURCE_DISABLED; break; + case EFI_PERSISTENT_MEMORY: + name = "Persistent Memory"; + break; + case EFI_RESERVED_TYPE: case EFI_RUNTIME_SERVICES_CODE: case EFI_RUNTIME_SERVICES_DATA: diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index 84dba51b5a35..805bfea1edfd 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -1419,6 +1419,9 @@ source "mm/Kconfig" config X86_PMEM_LEGACY bool "Support non-standard NVDIMMs and ADR protected memory" + depends on PHYS_ADDR_T_64BIT + depends on BLK_DEV + select LIBNVDIMM help Treat memory marked using the non-standard e820 type of 12 as used by the Intel Sandy Bridge-EP reference BIOS as protected memory. diff --git a/arch/x86/boot/compressed/eboot.c b/arch/x86/boot/compressed/eboot.c index 48304b89b601..2c82bd150d43 100644 --- a/arch/x86/boot/compressed/eboot.c +++ b/arch/x86/boot/compressed/eboot.c @@ -1224,6 +1224,10 @@ static efi_status_t setup_e820(struct boot_params *params, e820_type = E820_NVS; break; + case EFI_PERSISTENT_MEMORY: + e820_type = E820_PMEM; + break; + default: continue; } diff --git a/arch/x86/include/uapi/asm/e820.h b/arch/x86/include/uapi/asm/e820.h index 960a8a9dc4ab..0f457e6eab18 100644 --- a/arch/x86/include/uapi/asm/e820.h +++ b/arch/x86/include/uapi/asm/e820.h @@ -32,6 +32,7 @@ #define E820_ACPI 3 #define E820_NVS 4 #define E820_UNUSABLE 5 +#define E820_PMEM 7 /* * This is a non-standardized way to represent ADR or NVDIMM regions that diff --git a/arch/x86/kernel/e820.c b/arch/x86/kernel/e820.c index c8dda42cb6a3..a102564d08eb 100644 --- a/arch/x86/kernel/e820.c +++ b/arch/x86/kernel/e820.c @@ -149,6 +149,7 @@ static void __init e820_print_type(u32 type) case E820_UNUSABLE: printk(KERN_CONT "unusable"); break; + case E820_PMEM: case E820_PRAM: printk(KERN_CONT "persistent (type %u)", type); break; @@ -918,11 +919,32 @@ static inline const char *e820_type_to_string(int e820_type) case E820_ACPI: return "ACPI Tables"; case E820_NVS: return "ACPI Non-volatile Storage"; case E820_UNUSABLE: return "Unusable memory"; - case E820_PRAM: return "Persistent RAM"; + case E820_PRAM: return "Persistent Memory (legacy)"; + case E820_PMEM: return "Persistent Memory"; default: return "reserved"; } } +static bool do_mark_busy(u32 type, struct resource *res) +{ + /* this is the legacy bios/dos rom-shadow + mmio region */ + if (res->start < (1ULL<<20)) + return true; + + /* + * Treat persistent memory like device memory, i.e. reserve it + * for exclusive use of a driver + */ + switch (type) { + case E820_RESERVED: + case E820_PRAM: + case E820_PMEM: + return false; + default: + return true; + } +} + /* * Mark e820 reserved areas as busy for the resource manager. */ @@ -952,9 +974,7 @@ void __init e820_reserve_resources(void) * pci device BAR resource and insert them later in * pcibios_resource_survey() */ - if (((e820.map[i].type != E820_RESERVED) && - (e820.map[i].type != E820_PRAM)) || - res->start < (1ULL<<20)) { + if (do_mark_busy(e820.map[i].type, res)) { res->flags |= IORESOURCE_BUSY; insert_resource(&iomem_resource, res); } diff --git a/arch/x86/kernel/pmem.c b/arch/x86/kernel/pmem.c index 3420c874ddc5..0f4ef472ab9e 100644 --- a/arch/x86/kernel/pmem.c +++ b/arch/x86/kernel/pmem.c @@ -1,53 +1,81 @@ /* * Copyright (c) 2015, Christoph Hellwig. + * Copyright (c) 2015, Intel Corporation. */ -#include <linux/memblock.h> #include <linux/platform_device.h> -#include <linux/slab.h> +#include <linux/libnvdimm.h> +#include <linux/module.h> #include <asm/e820.h> -#include <asm/page_types.h> -#include <asm/setup.h> -static __init void register_pmem_device(struct resource *res) +static void e820_pmem_release(struct device *dev) { - struct platform_device *pdev; - int error; + struct nvdimm_bus *nvdimm_bus = dev->platform_data; - pdev = platform_device_alloc("pmem", PLATFORM_DEVID_AUTO); - if (!pdev) - return; + if (nvdimm_bus) + nvdimm_bus_unregister(nvdimm_bus); +} - error = platform_device_add_resources(pdev, res, 1); - if (error) - goto out_put_pdev; +static struct platform_device e820_pmem = { + .name = "e820_pmem", + .id = -1, + .dev = { + .release = e820_pmem_release, + }, +}; - error = platform_device_add(pdev); - if (error) - goto out_put_pdev; - return; +static const struct attribute_group *e820_pmem_attribute_groups[] = { + &nvdimm_bus_attribute_group, + NULL, +}; -out_put_pdev: - dev_warn(&pdev->dev, "failed to add 'pmem' (persistent memory) device!\n"); - platform_device_put(pdev); -} +static const struct attribute_group *e820_pmem_region_attribute_groups[] = { + &nd_region_attribute_group, + &nd_device_attribute_group, + NULL, +}; -static __init int register_pmem_devices(void) +static __init int register_e820_pmem(void) { - int i; + static struct nvdimm_bus_descriptor nd_desc; + struct device *dev = &e820_pmem.dev; + struct nvdimm_bus *nvdimm_bus; + int rc, i; + + rc = platform_device_register(&e820_pmem); + if (rc) + return rc; + + nd_desc.attr_groups = e820_pmem_attribute_groups; + nd_desc.provider_name = "e820"; + nvdimm_bus = nvdimm_bus_register(dev, &nd_desc); + if (!nvdimm_bus) + goto err; + dev->platform_data = nvdimm_bus; for (i = 0; i < e820.nr_map; i++) { struct e820entry *ei = &e820.map[i]; + struct resource res = { + .flags = IORESOURCE_MEM, + .start = ei->addr, + .end = ei->addr + ei->size - 1, + }; + struct nd_region_desc ndr_desc; + + if (ei->type != E820_PRAM) + continue; - if (ei->type == E820_PRAM) { - struct resource res = { - .flags = IORESOURCE_MEM, - .start = ei->addr, - .end = ei->addr + ei->size - 1, - }; - register_pmem_device(&res); - } + memset(&ndr_desc, 0, sizeof(ndr_desc)); + ndr_desc.res = &res; + ndr_desc.attr_groups = e820_pmem_region_attribute_groups; + if (!nvdimm_pmem_region_create(nvdimm_bus, &ndr_desc)) + goto err; } return 0; + + err: + dev_err(dev, "failed to register legacy persistent memory ranges\n"); + platform_device_unregister(&e820_pmem); + return -ENXIO; } -device_initcall(register_pmem_devices); +device_initcall(register_e820_pmem); diff --git a/arch/x86/platform/efi/efi.c b/arch/x86/platform/efi/efi.c index c1c382c58c60..cfba30f27392 100644 --- a/arch/x86/platform/efi/efi.c +++ b/arch/x86/platform/efi/efi.c @@ -174,6 +174,9 @@ static void __init do_add_efi_memmap(void) case EFI_UNUSABLE_MEMORY: e820_type = E820_UNUSABLE; break; + case EFI_PERSISTENT_MEMORY: + e820_type = E820_PMEM; + break; default: /* * EFI_RESERVED_TYPE EFI_RUNTIME_SERVICES_CODE diff --git a/drivers/Kconfig b/drivers/Kconfig index c0cc96bab9e7..6e973b8e3a3b 100644 --- a/drivers/Kconfig +++ b/drivers/Kconfig @@ -182,4 +182,6 @@ source "drivers/thunderbolt/Kconfig" source "drivers/android/Kconfig" +source "drivers/nvdimm/Kconfig" + endmenu diff --git a/drivers/Makefile b/drivers/Makefile index 9a02fb7c5106..b64b49f6e01b 100644 --- a/drivers/Makefile +++ b/drivers/Makefile @@ -64,6 +64,7 @@ obj-$(CONFIG_FB_INTEL) += video/fbdev/intelfb/ obj-$(CONFIG_PARPORT) += parport/ obj-y += base/ block/ misc/ mfd/ nfc/ +obj-$(CONFIG_LIBNVDIMM) += nvdimm/ obj-$(CONFIG_DMA_SHARED_BUFFER) += dma-buf/ obj-$(CONFIG_NUBUS) += nubus/ obj-y += macintosh/ diff --git a/drivers/acpi/Kconfig b/drivers/acpi/Kconfig index 35da507411a0..f15db002be8e 100644 --- a/drivers/acpi/Kconfig +++ b/drivers/acpi/Kconfig @@ -386,6 +386,32 @@ config ACPI_REDUCED_HARDWARE_ONLY If you are unsure what to do, do not enable this option. +config ACPI_NFIT + tristate "ACPI NVDIMM Firmware Interface Table (NFIT)" + depends on PHYS_ADDR_T_64BIT + depends on BLK_DEV + select LIBNVDIMM + help + Infrastructure to probe ACPI 6 compliant platforms for + NVDIMMs (NFIT) and register a libnvdimm device tree. In + addition to storage devices this also enables libnvdimm to pass + ACPI._DSM messages for platform/dimm configuration. + + To compile this driver as a module, choose M here: + the module will be called nfit. + +config ACPI_NFIT_DEBUG + bool "NFIT DSM debug" + depends on ACPI_NFIT + depends on DYNAMIC_DEBUG + default n + help + Enabling this option causes the nfit driver to dump the + input and output buffers of _DSM operations on the ACPI0012 + device and its children. This can be very verbose, so leave + it disabled unless you are debugging a hardware / firmware + issue. + source "drivers/acpi/apei/Kconfig" config ACPI_EXTLOG diff --git a/drivers/acpi/Makefile b/drivers/acpi/Makefile index 73d840bef455..8321430d7f24 100644 --- a/drivers/acpi/Makefile +++ b/drivers/acpi/Makefile @@ -68,6 +68,7 @@ obj-$(CONFIG_ACPI_PCI_SLOT) += pci_slot.o obj-$(CONFIG_ACPI_PROCESSOR) += processor.o obj-y += container.o obj-$(CONFIG_ACPI_THERMAL) += thermal.o +obj-$(CONFIG_ACPI_NFIT) += nfit.o obj-y += acpi_memhotplug.o obj-$(CONFIG_ACPI_HOTPLUG_IOAPIC) += ioapic.o obj-$(CONFIG_ACPI_BATTERY) += battery.o diff --git a/drivers/acpi/nfit.c b/drivers/acpi/nfit.c new file mode 100644 index 000000000000..35af6f7f0abd --- /dev/null +++ b/drivers/acpi/nfit.c @@ -0,0 +1,1123 @@ +/* + * Copyright(c) 2013-2015 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/list_sort.h> +#include <linux/libnvdimm.h> +#include <linux/module.h> +#include <linux/ndctl.h> +#include <linux/list.h> +#include <linux/acpi.h> +#include <linux/sort.h> +#include "nfit.h" + +static bool force_enable_dimms; +module_param(force_enable_dimms, bool, S_IRUGO|S_IWUSR); +MODULE_PARM_DESC(force_enable_dimms, "Ignore _STA (ACPI DIMM device) status"); + +static u8 nfit_uuid[NFIT_UUID_MAX][16]; + +static const u8 *to_nfit_uuid(enum nfit_uuids id) +{ + return nfit_uuid[id]; +} + +static struct acpi_nfit_desc *to_acpi_nfit_desc( + struct nvdimm_bus_descriptor *nd_desc) +{ + return container_of(nd_desc, struct acpi_nfit_desc, nd_desc); +} + +static struct acpi_device *to_acpi_dev(struct acpi_nfit_desc *acpi_desc) +{ + struct nvdimm_bus_descriptor *nd_desc = &acpi_desc->nd_desc; + + /* + * If provider == 'ACPI.NFIT' we can assume 'dev' is a struct + * acpi_device. + */ + if (!nd_desc->provider_name + || strcmp(nd_desc->provider_name, "ACPI.NFIT") != 0) + return NULL; + + return to_acpi_device(acpi_desc->dev); +} + +static int acpi_nfit_ctl(struct nvdimm_bus_descriptor *nd_desc, + struct nvdimm *nvdimm, unsigned int cmd, void *buf, + unsigned int buf_len) +{ + 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; + struct device *dev = acpi_desc->dev; + const char *cmd_name, *dimm_name; + unsigned long dsm_mask; + acpi_handle handle; + const u8 *uuid; + u32 offset; + int rc, i; + + if (nvdimm) { + struct nfit_mem *nfit_mem = nvdimm_provider_data(nvdimm); + struct acpi_device *adev = nfit_mem->adev; + + if (!adev) + return -ENOTTY; + dimm_name = dev_name(&adev->dev); + cmd_name = nvdimm_cmd_name(cmd); + dsm_mask = nfit_mem->dsm_mask; + desc = nd_cmd_dimm_desc(cmd); + uuid = to_nfit_uuid(NFIT_DEV_DIMM); + 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; + desc = nd_cmd_bus_desc(cmd); + uuid = to_nfit_uuid(NFIT_DEV_BUS); + handle = adev->handle; + dimm_name = "bus"; + } + + if (!desc || (cmd && (desc->out_num + desc->in_num == 0))) + return -ENOTTY; + + if (!test_bit(cmd, &dsm_mask)) + return -ENOTTY; + + in_obj.type = ACPI_TYPE_PACKAGE; + in_obj.package.count = 1; + in_obj.package.elements = &in_buf; + in_buf.type = ACPI_TYPE_BUFFER; + in_buf.buffer.pointer = buf; + in_buf.buffer.length = 0; + + /* libnvdimm has already validated the input envelope */ + for (i = 0; i < desc->in_num; i++) + in_buf.buffer.length += nd_cmd_in_size(nvdimm, cmd, desc, + i, buf); + + 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); + } + + out_obj = acpi_evaluate_dsm(handle, uuid, 1, cmd, &in_obj); + if (!out_obj) { + dev_dbg(dev, "%s:%s _DSM failed cmd: %s\n", __func__, dimm_name, + cmd_name); + return -EINVAL; + } + + 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); + rc = -EINVAL; + goto out; + } + + if (IS_ENABLED(CONFIG_ACPI_NFIT_DEBUG)) { + dev_dbg(dev, "%s:%s cmd: %s output length: %d\n", __func__, + dimm_name, cmd_name, out_obj->buffer.length); + print_hex_dump_debug(cmd_name, DUMP_PREFIX_OFFSET, 4, + 4, out_obj->buffer.pointer, min_t(u32, 128, + out_obj->buffer.length), true); + } + + for (i = 0, offset = 0; i < desc->out_num; i++) { + u32 out_size = nd_cmd_out_size(nvdimm, cmd, desc, i, buf, + (u32 *) out_obj->buffer.pointer); + + if (offset + out_size > out_obj->buffer.length) { + dev_dbg(dev, "%s:%s output object underflow cmd: %s field: %d\n", + __func__, dimm_name, cmd_name, i); + break; + } + + if (in_buf.buffer.length + offset + out_size > buf_len) { + dev_dbg(dev, "%s:%s output overrun cmd: %s field: %d\n", + __func__, dimm_name, cmd_name, i); + rc = -ENXIO; + goto out; + } + memcpy(buf + in_buf.buffer.length + offset, + out_obj->buffer.pointer + offset, out_size); + offset += out_size; + } + if (offset + in_buf.buffer.length < buf_len) { + if (i >= 1) { + /* + * status valid, return the number of bytes left + * unfilled in the output buffer + */ + rc = buf_len - offset - in_buf.buffer.length; + } else { + dev_err(dev, "%s:%s underrun cmd: %s buf_len: %d out_len: %d\n", + __func__, dimm_name, cmd_name, buf_len, + offset); + rc = -ENXIO; + } + } else + rc = 0; + + out: + ACPI_FREE(out_obj); + + return rc; +} + +static const char *spa_type_name(u16 type) +{ + static const char *to_name[] = { + [NFIT_SPA_VOLATILE] = "volatile", + [NFIT_SPA_PM] = "pmem", + [NFIT_SPA_DCR] = "dimm-control-region", + [NFIT_SPA_BDW] = "block-data-window", + [NFIT_SPA_VDISK] = "volatile-disk", + [NFIT_SPA_VCD] = "volatile-cd", + [NFIT_SPA_PDISK] = "persistent-disk", + [NFIT_SPA_PCD] = "persistent-cd", + + }; + + if (type > NFIT_SPA_PCD) + return "unknown"; + + return to_name[type]; +} + +static int nfit_spa_type(struct acpi_nfit_system_address *spa) +{ + int i; + + for (i = 0; i < NFIT_UUID_MAX; i++) + if (memcmp(to_nfit_uuid(i), spa->range_guid, 16) == 0) + return i; + return -1; +} + +static bool add_spa(struct acpi_nfit_desc *acpi_desc, + struct acpi_nfit_system_address *spa) +{ + struct device *dev = acpi_desc->dev; + struct nfit_spa *nfit_spa = devm_kzalloc(dev, sizeof(*nfit_spa), + GFP_KERNEL); + + if (!nfit_spa) + return false; + INIT_LIST_HEAD(&nfit_spa->list); + nfit_spa->spa = spa; + list_add_tail(&nfit_spa->list, &acpi_desc->spas); + dev_dbg(dev, "%s: spa index: %d type: %s\n", __func__, + spa->range_index, + spa_type_name(nfit_spa_type(spa))); + return true; +} + +static bool add_memdev(struct acpi_nfit_desc *acpi_desc, + struct acpi_nfit_memory_map *memdev) +{ + struct device *dev = acpi_desc->dev; + struct nfit_memdev *nfit_memdev = devm_kzalloc(dev, + sizeof(*nfit_memdev), GFP_KERNEL); + + if (!nfit_memdev) + return false; + INIT_LIST_HEAD(&nfit_memdev->list); + nfit_memdev->memdev = memdev; + list_add_tail(&nfit_memdev->list, &acpi_desc->memdevs); + dev_dbg(dev, "%s: memdev handle: %#x spa: %d dcr: %d\n", + __func__, memdev->device_handle, memdev->range_index, + memdev->region_index); + return true; +} + +static bool add_dcr(struct acpi_nfit_desc *acpi_desc, + struct acpi_nfit_control_region *dcr) +{ + struct device *dev = acpi_desc->dev; + struct nfit_dcr *nfit_dcr = devm_kzalloc(dev, sizeof(*nfit_dcr), + GFP_KERNEL); + + if (!nfit_dcr) + return false; + INIT_LIST_HEAD(&nfit_dcr->list); + nfit_dcr->dcr = dcr; + list_add_tail(&nfit_dcr->list, &acpi_desc->dcrs); + dev_dbg(dev, "%s: dcr index: %d windows: %d\n", __func__, + dcr->region_index, dcr->windows); + return true; +} + +static bool add_bdw(struct acpi_nfit_desc *acpi_desc, + struct acpi_nfit_data_region *bdw) +{ + struct device *dev = acpi_desc->dev; + struct nfit_bdw *nfit_bdw = devm_kzalloc(dev, sizeof(*nfit_bdw), + GFP_KERNEL); + + if (!nfit_bdw) + return false; + INIT_LIST_HEAD(&nfit_bdw->list); + nfit_bdw->bdw = bdw; + list_add_tail(&nfit_bdw->list, &acpi_desc->bdws); + dev_dbg(dev, "%s: bdw dcr: %d windows: %d\n", __func__, + bdw->region_index, bdw->windows); + return true; +} + +static void *add_table(struct acpi_nfit_desc *acpi_desc, void *table, + const void *end) +{ + struct device *dev = acpi_desc->dev; + struct acpi_nfit_header *hdr; + void *err = ERR_PTR(-ENOMEM); + + if (table >= end) + return NULL; + + hdr = table; + switch (hdr->type) { + case ACPI_NFIT_TYPE_SYSTEM_ADDRESS: + if (!add_spa(acpi_desc, table)) + return err; + break; + case ACPI_NFIT_TYPE_MEMORY_MAP: + if (!add_memdev(acpi_desc, table)) + return err; + break; + case ACPI_NFIT_TYPE_CONTROL_REGION: + if (!add_dcr(acpi_desc, table)) + return err; + break; + case ACPI_NFIT_TYPE_DATA_REGION: + if (!add_bdw(acpi_desc, table)) + return err; + break; + /* TODO */ + case ACPI_NFIT_TYPE_INTERLEAVE: + dev_dbg(dev, "%s: idt\n", __func__); + break; + case ACPI_NFIT_TYPE_FLUSH_ADDRESS: + dev_dbg(dev, "%s: flush\n", __func__); + break; + case ACPI_NFIT_TYPE_SMBIOS: + dev_dbg(dev, "%s: smbios\n", __func__); + break; + default: + dev_err(dev, "unknown table '%d' parsing nfit\n", hdr->type); + break; + } + + return table + hdr->length; +} + +static void nfit_mem_find_spa_bdw(struct acpi_nfit_desc *acpi_desc, + struct nfit_mem *nfit_mem) +{ + u32 device_handle = __to_nfit_memdev(nfit_mem)->device_handle; + u16 dcr = nfit_mem->dcr->region_index; + struct nfit_spa *nfit_spa; + + list_for_each_entry(nfit_spa, &acpi_desc->spas, list) { + u16 range_index = nfit_spa->spa->range_index; + int type = nfit_spa_type(nfit_spa->spa); + struct nfit_memdev *nfit_memdev; + + if (type != NFIT_SPA_BDW) + continue; + + list_for_each_entry(nfit_memdev, &acpi_desc->memdevs, list) { + if (nfit_memdev->memdev->range_index != range_index) + continue; + if (nfit_memdev->memdev->device_handle != device_handle) + continue; + if (nfit_memdev->memdev->region_index != dcr) + continue; + + nfit_mem->spa_bdw = nfit_spa->spa; + return; + } + } + + dev_dbg(acpi_desc->dev, "SPA-BDW not found for SPA-DCR %d\n", + nfit_mem->spa_dcr->range_index); + nfit_mem->bdw = NULL; +} + +static int nfit_mem_add(struct acpi_nfit_desc *acpi_desc, + struct nfit_mem *nfit_mem, struct acpi_nfit_system_address *spa) +{ + u16 dcr = __to_nfit_memdev(nfit_mem)->region_index; + struct nfit_dcr *nfit_dcr; + struct nfit_bdw *nfit_bdw; + + list_for_each_entry(nfit_dcr, &acpi_desc->dcrs, list) { + if (nfit_dcr->dcr->region_index != dcr) + continue; + nfit_mem->dcr = nfit_dcr->dcr; + break; + } + + if (!nfit_mem->dcr) { + dev_dbg(acpi_desc->dev, "SPA %d missing:%s%s\n", + spa->range_index, __to_nfit_memdev(nfit_mem) + ? "" : " MEMDEV", nfit_mem->dcr ? "" : " DCR"); + return -ENODEV; + } + + /* + * We've found enough to create an nvdimm, optionally + * find an associated BDW + */ + list_add(&nfit_mem->list, &acpi_desc->dimms); + + list_for_each_entry(nfit_bdw, &acpi_desc->bdws, list) { + if (nfit_bdw->bdw->region_index != dcr) + continue; + nfit_mem->bdw = nfit_bdw->bdw; + break; + } + + if (!nfit_mem->bdw) + return 0; + + nfit_mem_find_spa_bdw(acpi_desc, nfit_mem); + return 0; +} + +static int nfit_mem_dcr_init(struct acpi_nfit_desc *acpi_desc, + struct acpi_nfit_system_address *spa) +{ + struct nfit_mem *nfit_mem, *found; + struct nfit_memdev *nfit_memdev; + int type = nfit_spa_type(spa); + u16 dcr; + + switch (type) { + case NFIT_SPA_DCR: + case NFIT_SPA_PM: + break; + default: + return 0; + } + + list_for_each_entry(nfit_memdev, &acpi_desc->memdevs, list) { + int rc; + + if (nfit_memdev->memdev->range_index != spa->range_index) + continue; + found = NULL; + dcr = nfit_memdev->memdev->region_index; + list_for_each_entry(nfit_mem, &acpi_desc->dimms, list) + if (__to_nfit_memdev(nfit_mem)->region_index == dcr) { + found = nfit_mem; + break; + } + + if (found) + nfit_mem = found; + else { + nfit_mem = devm_kzalloc(acpi_desc->dev, + sizeof(*nfit_mem), GFP_KERNEL); + if (!nfit_mem) + return -ENOMEM; + INIT_LIST_HEAD(&nfit_mem->list); + } + + if (type == NFIT_SPA_DCR) { + /* multiple dimms may share a SPA when interleaved */ + nfit_mem->spa_dcr = spa; + nfit_mem->memdev_dcr = nfit_memdev->memdev; + } else { + /* + * A single dimm may belong to multiple SPA-PM + * ranges, record at least one in addition to + * any SPA-DCR range. + */ + nfit_mem->memdev_pmem = nfit_memdev->memdev; + } + + if (found) + continue; + + rc = nfit_mem_add(acpi_desc, nfit_mem, spa); + if (rc) + return rc; + } + + return 0; +} + +static int nfit_mem_cmp(void *priv, struct list_head *_a, struct list_head *_b) +{ + struct nfit_mem *a = container_of(_a, typeof(*a), list); + struct nfit_mem *b = container_of(_b, typeof(*b), list); + u32 handleA, handleB; + + handleA = __to_nfit_memdev(a)->device_handle; + handleB = __to_nfit_memdev(b)->device_handle; + if (handleA < handleB) + return -1; + else if (handleA > handleB) + return 1; + return 0; +} + +static int nfit_mem_init(struct acpi_nfit_desc *acpi_desc) +{ + struct nfit_spa *nfit_spa; + + /* + * For each SPA-DCR or SPA-PMEM address range find its + * corresponding MEMDEV(s). From each MEMDEV find the + * corresponding DCR. Then, if we're operating on a SPA-DCR, + * try to find a SPA-BDW and a corresponding BDW that references + * the DCR. Throw it all into an nfit_mem object. Note, that + * BDWs are optional. + */ + list_for_each_entry(nfit_spa, &acpi_desc->spas, list) { + int rc; + + rc = nfit_mem_dcr_init(acpi_desc, nfit_spa->spa); + if (rc) + return rc; + } + + list_sort(NULL, &acpi_desc->dimms, nfit_mem_cmp); + + return 0; +} + +static ssize_t revision_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + struct nvdimm_bus *nvdimm_bus = to_nvdimm_bus(dev); + struct nvdimm_bus_descriptor *nd_desc = to_nd_desc(nvdimm_bus); + struct acpi_nfit_desc *acpi_desc = to_acpi_desc(nd_desc); + + return sprintf(buf, "%d\n", acpi_desc->nfit->header.revision); +} +static DEVICE_ATTR_RO(revision); + +static struct attribute *acpi_nfit_attributes[] = { + &dev_attr_revision.attr, + NULL, +}; + +static struct attribute_group acpi_nfit_attribute_group = { + .name = "nfit", + .attrs = acpi_nfit_attributes, +}; + +static const struct attribute_group *acpi_nfit_attribute_groups[] = { + &nvdimm_bus_attribute_group, + &acpi_nfit_attribute_group, + NULL, +}; + +static struct acpi_nfit_memory_map *to_nfit_memdev(struct device *dev) +{ + struct nvdimm *nvdimm = to_nvdimm(dev); + struct nfit_mem *nfit_mem = nvdimm_provider_data(nvdimm); + + return __to_nfit_memdev(nfit_mem); +} + +static struct acpi_nfit_control_region *to_nfit_dcr(struct device *dev) +{ + struct nvdimm *nvdimm = to_nvdimm(dev); + struct nfit_mem *nfit_mem = nvdimm_provider_data(nvdimm); + + return nfit_mem->dcr; +} + +static ssize_t handle_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + struct acpi_nfit_memory_map *memdev = to_nfit_memdev(dev); + + return sprintf(buf, "%#x\n", memdev->device_handle); +} +static DEVICE_ATTR_RO(handle); + +static ssize_t phys_id_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + struct acpi_nfit_memory_map *memdev = to_nfit_memdev(dev); + + return sprintf(buf, "%#x\n", memdev->physical_id); +} +static DEVICE_ATTR_RO(phys_id); + +static ssize_t vendor_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->vendor_id); +} +static DEVICE_ATTR_RO(vendor); + +static ssize_t 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, "%#x\n", dcr->revision_id); +} +static DEVICE_ATTR_RO(rev_id); + +static ssize_t device_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->device_id); +} +static DEVICE_ATTR_RO(device); + +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); +} +static DEVICE_ATTR_RO(format); + +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); +} +static DEVICE_ATTR_RO(serial); + +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_format.attr, + &dev_attr_serial.attr, + &dev_attr_rev_id.attr, + NULL, +}; + +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); + + if (to_nfit_dcr(dev)) + return a->mode; + else + return 0; +} + +static struct attribute_group acpi_nfit_dimm_attribute_group = { + .name = "nfit", + .attrs = acpi_nfit_dimm_attributes, + .is_visible = acpi_nfit_dimm_attr_visible, +}; + +static const struct attribute_group *acpi_nfit_dimm_attribute_groups[] = { + &nvdimm_attribute_group, + &nd_device_attribute_group, + &acpi_nfit_dimm_attribute_group, + NULL, +}; + +static struct nvdimm *acpi_nfit_dimm_by_handle(struct acpi_nfit_desc *acpi_desc, + u32 device_handle) +{ + struct nfit_mem *nfit_mem; + + list_for_each_entry(nfit_mem, &acpi_desc->dimms, list) + if (__to_nfit_memdev(nfit_mem)->device_handle == device_handle) + return nfit_mem->nvdimm; + + return NULL; +} + +static int acpi_nfit_add_dimm(struct acpi_nfit_desc *acpi_desc, + struct nfit_mem *nfit_mem, u32 device_handle) +{ + struct acpi_device *adev, *adev_dimm; + struct device *dev = acpi_desc->dev; + const u8 *uuid = to_nfit_uuid(NFIT_DEV_DIMM); + unsigned long long sta; + int i, rc = -ENODEV; + acpi_status status; + + nfit_mem->dsm_mask = acpi_desc->dimm_dsm_force_en; + adev = to_acpi_dev(acpi_desc); + if (!adev) + return 0; + + adev_dimm = acpi_find_child_device(adev, device_handle, false); + nfit_mem->adev = adev_dimm; + if (!adev_dimm) { + dev_err(dev, "no ACPI.NFIT device with _ADR %#x, disabling...\n", + device_handle); + return force_enable_dimms ? 0 : -ENODEV; + } + + status = acpi_evaluate_integer(adev_dimm->handle, "_STA", NULL, &sta); + if (status == AE_NOT_FOUND) { + dev_dbg(dev, "%s missing _STA, assuming enabled...\n", + dev_name(&adev_dimm->dev)); + rc = 0; + } else if (ACPI_FAILURE(status)) + dev_err(dev, "%s failed to retrieve_STA, disabling...\n", + dev_name(&adev_dimm->dev)); + else if ((sta & ACPI_STA_DEVICE_ENABLED) == 0) + dev_info(dev, "%s disabled by firmware\n", + dev_name(&adev_dimm->dev)); + else + rc = 0; + + for (i = ND_CMD_SMART; i <= ND_CMD_VENDOR; i++) + if (acpi_check_dsm(adev_dimm->handle, uuid, 1, 1ULL << i)) + set_bit(i, &nfit_mem->dsm_mask); + + return force_enable_dimms ? 0 : rc; +} + +static int acpi_nfit_register_dimms(struct acpi_nfit_desc *acpi_desc) +{ + struct nfit_mem *nfit_mem; + int dimm_count = 0; + + list_for_each_entry(nfit_mem, &acpi_desc->dimms, list) { + struct nvdimm *nvdimm; + unsigned long flags = 0; + u32 device_handle; + int rc; + + device_handle = __to_nfit_memdev(nfit_mem)->device_handle; + nvdimm = acpi_nfit_dimm_by_handle(acpi_desc, device_handle); + if (nvdimm) { + /* + * If for some reason we find multiple DCRs the + * first one wins + */ + dev_err(acpi_desc->dev, "duplicate DCR detected: %s\n", + nvdimm_name(nvdimm)); + continue; + } + + if (nfit_mem->bdw && nfit_mem->memdev_pmem) + flags |= NDD_ALIASING; + + rc = acpi_nfit_add_dimm(acpi_desc, nfit_mem, device_handle); + if (rc) + continue; + + nvdimm = nvdimm_create(acpi_desc->nvdimm_bus, nfit_mem, + acpi_nfit_dimm_attribute_groups, + flags, &nfit_mem->dsm_mask); + if (!nvdimm) + return -ENOMEM; + + nfit_mem->nvdimm = nvdimm; + dimm_count++; + } + + return nvdimm_bus_check_dimm_count(acpi_desc->nvdimm_bus, dimm_count); +} + +static void acpi_nfit_init_dsms(struct acpi_nfit_desc *acpi_desc) +{ + struct nvdimm_bus_descriptor *nd_desc = &acpi_desc->nd_desc; + const u8 *uuid = to_nfit_uuid(NFIT_DEV_BUS); + struct acpi_device *adev; + int i; + + adev = to_acpi_dev(acpi_desc); + if (!adev) + return; + + for (i = ND_CMD_ARS_CAP; i <= ND_CMD_ARS_STATUS; i++) + if (acpi_check_dsm(adev->handle, uuid, 1, 1ULL << i)) + set_bit(i, &nd_desc->dsm_mask); +} + +static ssize_t range_index_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + struct nd_region *nd_region = to_nd_region(dev); + struct nfit_spa *nfit_spa = nd_region_provider_data(nd_region); + + return sprintf(buf, "%d\n", nfit_spa->spa->range_index); +} +static DEVICE_ATTR_RO(range_index); + +static struct attribute *acpi_nfit_region_attributes[] = { + &dev_attr_range_index.attr, + NULL, +}; + +static struct attribute_group acpi_nfit_region_attribute_group = { + .name = "nfit", + .attrs = acpi_nfit_region_attributes, +}; + +static const struct attribute_group *acpi_nfit_region_attribute_groups[] = { + &nd_region_attribute_group, + &nd_mapping_attribute_group, + &nd_device_attribute_group, + &acpi_nfit_region_attribute_group, + NULL, +}; + +/* enough info to uniquely specify an interleave set */ +struct nfit_set_info { + struct nfit_set_info_map { + u64 region_offset; + u32 serial_number; + u32 pad; + } mapping[0]; +}; + +static size_t sizeof_nfit_set_info(int num_mappings) +{ + return sizeof(struct nfit_set_info) + + num_mappings * sizeof(struct nfit_set_info_map); +} + +static int cmp_map(const void *m0, const void *m1) +{ + const struct nfit_set_info_map *map0 = m0; + const struct nfit_set_info_map *map1 = m1; + + return memcmp(&map0->region_offset, &map1->region_offset, + sizeof(u64)); +} + +/* Retrieve the nth entry referencing this spa */ +static struct acpi_nfit_memory_map *memdev_from_spa( + struct acpi_nfit_desc *acpi_desc, u16 range_index, int n) +{ + struct nfit_memdev *nfit_memdev; + + list_for_each_entry(nfit_memdev, &acpi_desc->memdevs, list) + if (nfit_memdev->memdev->range_index == range_index) + if (n-- == 0) + return nfit_memdev->memdev; + return NULL; +} + +static int acpi_nfit_init_interleave_set(struct acpi_nfit_desc *acpi_desc, + struct nd_region_desc *ndr_desc, + struct acpi_nfit_system_address *spa) +{ + int i, spa_type = nfit_spa_type(spa); + struct device *dev = acpi_desc->dev; + struct nd_interleave_set *nd_set; + u16 nr = ndr_desc->num_mappings; + struct nfit_set_info *info; + + if (spa_type == NFIT_SPA_PM || spa_type == NFIT_SPA_VOLATILE) + /* pass */; + else + return 0; + + nd_set = devm_kzalloc(dev, sizeof(*nd_set), GFP_KERNEL); + if (!nd_set) + return -ENOMEM; + + info = devm_kzalloc(dev, sizeof_nfit_set_info(nr), GFP_KERNEL); + if (!info) + return -ENOMEM; + for (i = 0; i < nr; i++) { + struct nd_mapping *nd_mapping = &ndr_desc->nd_mapping[i]; + struct nfit_set_info_map *map = &info->mapping[i]; + struct nvdimm *nvdimm = nd_mapping->nvdimm; + struct nfit_mem *nfit_mem = nvdimm_provider_data(nvdimm); + struct acpi_nfit_memory_map *memdev = memdev_from_spa(acpi_desc, + spa->range_index, i); + + if (!memdev || !nfit_mem->dcr) { + dev_err(dev, "%s: failed to find DCR\n", __func__); + return -ENODEV; + } + + map->region_offset = memdev->region_offset; + map->serial_number = nfit_mem->dcr->serial_number; + } + + sort(&info->mapping[0], nr, sizeof(struct nfit_set_info_map), + cmp_map, NULL); + nd_set->cookie = nd_fletcher64(info, sizeof_nfit_set_info(nr), 0); + ndr_desc->nd_set = nd_set; + devm_kfree(dev, info); + + return 0; +} + +static int acpi_nfit_init_mapping(struct acpi_nfit_desc *acpi_desc, + struct nd_mapping *nd_mapping, struct nd_region_desc *ndr_desc, + struct acpi_nfit_memory_map *memdev, + struct acpi_nfit_system_address *spa) +{ + struct nvdimm *nvdimm = acpi_nfit_dimm_by_handle(acpi_desc, + memdev->device_handle); + struct nfit_mem *nfit_mem; + int blk_valid = 0; + + if (!nvdimm) { + dev_err(acpi_desc->dev, "spa%d dimm: %#x not found\n", + spa->range_index, memdev->device_handle); + return -ENODEV; + } + + nd_mapping->nvdimm = nvdimm; + switch (nfit_spa_type(spa)) { + case NFIT_SPA_PM: + case NFIT_SPA_VOLATILE: + nd_mapping->start = memdev->address; + nd_mapping->size = memdev->region_size; + break; + case NFIT_SPA_DCR: + nfit_mem = nvdimm_provider_data(nvdimm); + if (!nfit_mem || !nfit_mem->bdw) { + dev_dbg(acpi_desc->dev, "spa%d %s missing bdw\n", + spa->range_index, nvdimm_name(nvdimm)); + } else { + nd_mapping->size = nfit_mem->bdw->capacity; + nd_mapping->start = nfit_mem->bdw->start_address; + blk_valid = 1; + } + + ndr_desc->nd_mapping = nd_mapping; + ndr_desc->num_mappings = blk_valid; + if (!nvdimm_blk_region_create(acpi_desc->nvdimm_bus, ndr_desc)) + return -ENOMEM; + break; + } + + return 0; +} + +static int acpi_nfit_register_region(struct acpi_nfit_desc *acpi_desc, + struct nfit_spa *nfit_spa) +{ + static struct nd_mapping nd_mappings[ND_MAX_MAPPINGS]; + struct acpi_nfit_system_address *spa = nfit_spa->spa; + struct nfit_memdev *nfit_memdev; + struct nd_region_desc ndr_desc; + struct nvdimm_bus *nvdimm_bus; + struct resource res; + int count = 0, rc; + + if (spa->range_index == 0) { + dev_dbg(acpi_desc->dev, "%s: detected invalid spa index\n", + __func__); + return 0; + } + + memset(&res, 0, sizeof(res)); + memset(&nd_mappings, 0, sizeof(nd_mappings)); + memset(&ndr_desc, 0, sizeof(ndr_desc)); + res.start = spa->address; + res.end = res.start + spa->length - 1; + ndr_desc.res = &res; + ndr_desc.provider_data = nfit_spa; + ndr_desc.attr_groups = acpi_nfit_region_attribute_groups; + list_for_each_entry(nfit_memdev, &acpi_desc->memdevs, list) { + struct acpi_nfit_memory_map *memdev = nfit_memdev->memdev; + struct nd_mapping *nd_mapping; + + if (memdev->range_index != spa->range_index) + continue; + if (count >= ND_MAX_MAPPINGS) { + dev_err(acpi_desc->dev, "spa%d exceeds max mappings %d\n", + spa->range_index, ND_MAX_MAPPINGS); + return -ENXIO; + } + nd_mapping = &nd_mappings[count++]; + rc = acpi_nfit_init_mapping(acpi_desc, nd_mapping, &ndr_desc, + memdev, spa); + if (rc) + return rc; + } + + ndr_desc.nd_mapping = nd_mappings; + ndr_desc.num_mappings = count; + rc = acpi_nfit_init_interleave_set(acpi_desc, &ndr_desc, spa); + if (rc) + return rc; + + nvdimm_bus = acpi_desc->nvdimm_bus; + if (nfit_spa_type(spa) == NFIT_SPA_PM) { + if (!nvdimm_pmem_region_create(nvdimm_bus, &ndr_desc)) + return -ENOMEM; + } else if (nfit_spa_type(spa) == NFIT_SPA_VOLATILE) { + if (!nvdimm_volatile_region_create(nvdimm_bus, &ndr_desc)) + return -ENOMEM; + } + return 0; +} + +static int acpi_nfit_register_regions(struct acpi_nfit_desc *acpi_desc) +{ + struct nfit_spa *nfit_spa; + + list_for_each_entry(nfit_spa, &acpi_desc->spas, list) { + int rc = acpi_nfit_register_region(acpi_desc, nfit_spa); + + if (rc) + return rc; + } + return 0; +} + +static int acpi_nfit_init(struct acpi_nfit_desc *acpi_desc, acpi_size sz) +{ + struct device *dev = acpi_desc->dev; + const void *end; + u8 *data; + int rc; + + INIT_LIST_HEAD(&acpi_desc->spas); + INIT_LIST_HEAD(&acpi_desc->dcrs); + INIT_LIST_HEAD(&acpi_desc->bdws); + INIT_LIST_HEAD(&acpi_desc->memdevs); + INIT_LIST_HEAD(&acpi_desc->dimms); + + data = (u8 *) acpi_desc->nfit; + end = data + sz; + data += sizeof(struct acpi_table_nfit); + while (!IS_ERR_OR_NULL(data)) + data = add_table(acpi_desc, data, end); + + if (IS_ERR(data)) { + dev_dbg(dev, "%s: nfit table parsing error: %ld\n", __func__, + PTR_ERR(data)); + return PTR_ERR(data); + } + + if (nfit_mem_init(acpi_desc) != 0) + return -ENOMEM; + + acpi_nfit_init_dsms(acpi_desc); + + rc = acpi_nfit_register_dimms(acpi_desc); + if (rc) + return rc; + + return acpi_nfit_register_regions(acpi_desc); +} + +static int acpi_nfit_add(struct acpi_device *adev) +{ + struct nvdimm_bus_descriptor *nd_desc; + struct acpi_nfit_desc *acpi_desc; + struct device *dev = &adev->dev; + struct acpi_table_header *tbl; + acpi_status status = AE_OK; + acpi_size sz; + int rc; + + status = acpi_get_table_with_size("NFIT", 0, &tbl, &sz); + if (ACPI_FAILURE(status)) { + dev_err(dev, "failed to find NFIT\n"); + return -ENXIO; + } + + acpi_desc = devm_kzalloc(dev, sizeof(*acpi_desc), GFP_KERNEL); + if (!acpi_desc) + return -ENOMEM; + + dev_set_drvdata(dev, acpi_desc); + acpi_desc->dev = dev; + acpi_desc->nfit = (struct acpi_table_nfit *) tbl; + nd_desc = &acpi_desc->nd_desc; + nd_desc->provider_name = "ACPI.NFIT"; + nd_desc->ndctl = acpi_nfit_ctl; + nd_desc->attr_groups = acpi_nfit_attribute_groups; + + acpi_desc->nvdimm_bus = nvdimm_bus_register(dev, nd_desc); + if (!acpi_desc->nvdimm_bus) + return -ENXIO; + + rc = acpi_nfit_init(acpi_desc, sz); + if (rc) { + nvdimm_bus_unregister(acpi_desc->nvdimm_bus); + return rc; + } + return 0; +} + +static int acpi_nfit_remove(struct acpi_device *adev) +{ + struct acpi_nfit_desc *acpi_desc = dev_get_drvdata(&adev->dev); + + nvdimm_bus_unregister(acpi_desc->nvdimm_bus); + return 0; +} + +static const struct acpi_device_id acpi_nfit_ids[] = { + { "ACPI0012", 0 }, + { "", 0 }, +}; +MODULE_DEVICE_TABLE(acpi, acpi_nfit_ids); + +static struct acpi_driver acpi_nfit_driver = { + .name = KBUILD_MODNAME, + .ids = acpi_nfit_ids, + .ops = { + .add = acpi_nfit_add, + .remove = acpi_nfit_remove, + }, +}; + +static __init int nfit_init(void) +{ + BUILD_BUG_ON(sizeof(struct acpi_table_nfit) != 40); + BUILD_BUG_ON(sizeof(struct acpi_nfit_system_address) != 56); + BUILD_BUG_ON(sizeof(struct acpi_nfit_memory_map) != 48); + BUILD_BUG_ON(sizeof(struct acpi_nfit_interleave) != 20); + BUILD_BUG_ON(sizeof(struct acpi_nfit_smbios) != 9); + BUILD_BUG_ON(sizeof(struct acpi_nfit_control_region) != 80); + BUILD_BUG_ON(sizeof(struct acpi_nfit_data_region) != 40); + + acpi_str_to_uuid(UUID_VOLATILE_MEMORY, nfit_uuid[NFIT_SPA_VOLATILE]); + acpi_str_to_uuid(UUID_PERSISTENT_MEMORY, nfit_uuid[NFIT_SPA_PM]); + acpi_str_to_uuid(UUID_CONTROL_REGION, nfit_uuid[NFIT_SPA_DCR]); + acpi_str_to_uuid(UUID_DATA_REGION, nfit_uuid[NFIT_SPA_BDW]); + acpi_str_to_uuid(UUID_VOLATILE_VIRTUAL_DISK, nfit_uuid[NFIT_SPA_VDISK]); + acpi_str_to_uuid(UUID_VOLATILE_VIRTUAL_CD, nfit_uuid[NFIT_SPA_VCD]); + acpi_str_to_uuid(UUID_PERSISTENT_VIRTUAL_DISK, nfit_uuid[NFIT_SPA_PDISK]); + 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]); + + return acpi_bus_register_driver(&acpi_nfit_driver); +} + +static __exit void nfit_exit(void) +{ + acpi_bus_unregister_driver(&acpi_nfit_driver); +} + +module_init(nfit_init); +module_exit(nfit_exit); +MODULE_LICENSE("GPL v2"); +MODULE_AUTHOR("Intel Corporation"); diff --git a/drivers/acpi/nfit.h b/drivers/acpi/nfit.h new file mode 100644 index 000000000000..b76e33629098 --- /dev/null +++ b/drivers/acpi/nfit.h @@ -0,0 +1,100 @@ +/* + * NVDIMM Firmware Interface Table - NFIT + * + * Copyright(c) 2013-2015 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 __NFIT_H__ +#define __NFIT_H__ +#include <linux/libnvdimm.h> +#include <linux/types.h> +#include <linux/uuid.h> +#include <linux/acpi.h> +#include <acpi/acuuid.h> + +#define UUID_NFIT_BUS "2f10e7a4-9e91-11e4-89d3-123b93f75cba" +#define UUID_NFIT_DIMM "4309ac30-0d11-11e4-9191-0800200c9a66" + +enum nfit_uuids { + NFIT_SPA_VOLATILE, + NFIT_SPA_PM, + NFIT_SPA_DCR, + NFIT_SPA_BDW, + NFIT_SPA_VDISK, + NFIT_SPA_VCD, + NFIT_SPA_PDISK, + NFIT_SPA_PCD, + NFIT_DEV_BUS, + NFIT_DEV_DIMM, + NFIT_UUID_MAX, +}; + +struct nfit_spa { + struct acpi_nfit_system_address *spa; + struct list_head list; +}; + +struct nfit_dcr { + struct acpi_nfit_control_region *dcr; + struct list_head list; +}; + +struct nfit_bdw { + struct acpi_nfit_data_region *bdw; + struct list_head list; +}; + +struct nfit_memdev { + struct acpi_nfit_memory_map *memdev; + struct list_head list; +}; + +/* assembled tables for a given dimm/memory-device */ +struct nfit_mem { + struct nvdimm *nvdimm; + struct acpi_nfit_memory_map *memdev_dcr; + struct acpi_nfit_memory_map *memdev_pmem; + struct acpi_nfit_control_region *dcr; + struct acpi_nfit_data_region *bdw; + struct acpi_nfit_system_address *spa_dcr; + struct acpi_nfit_system_address *spa_bdw; + struct list_head list; + struct acpi_device *adev; + unsigned long dsm_mask; +}; + +struct acpi_nfit_desc { + struct nvdimm_bus_descriptor nd_desc; + struct acpi_table_nfit *nfit; + struct list_head memdevs; + struct list_head dimms; + struct list_head spas; + struct list_head dcrs; + struct list_head bdws; + struct nvdimm_bus *nvdimm_bus; + struct device *dev; + unsigned long dimm_dsm_force_en; +}; + +static inline struct acpi_nfit_memory_map *__to_nfit_memdev( + struct nfit_mem *nfit_mem) +{ + if (nfit_mem->memdev_dcr) + return nfit_mem->memdev_dcr; + return nfit_mem->memdev_pmem; +} + +static inline struct acpi_nfit_desc *to_acpi_desc( + struct nvdimm_bus_descriptor *nd_desc) +{ + return container_of(nd_desc, struct acpi_nfit_desc, nd_desc); +} +#endif /* __NFIT_H__ */ diff --git a/drivers/block/Kconfig b/drivers/block/Kconfig index 3ccef9eba6f9..1b8094d4d7af 100644 --- a/drivers/block/Kconfig +++ b/drivers/block/Kconfig @@ -404,18 +404,6 @@ config BLK_DEV_RAM_DAX and will prevent RAM block device backing store memory from being allocated from highmem (only a problem for highmem systems). -config BLK_DEV_PMEM - tristate "Persistent memory block device support" - depends on HAS_IOMEM - help - Saying Y here will allow you to use a contiguous range of reserved - memory as one or more persistent block devices. - - To compile this driver as a module, choose M here: the module will be - called 'pmem'. - - If unsure, say N. - config CDROM_PKTCDVD tristate "Packet writing on CD/DVD media" depends on !UML diff --git a/drivers/block/Makefile b/drivers/block/Makefile index 9cc6c18a1c7e..02b688d1438d 100644 --- a/drivers/block/Makefile +++ b/drivers/block/Makefile @@ -14,7 +14,6 @@ obj-$(CONFIG_PS3_VRAM) += ps3vram.o obj-$(CONFIG_ATARI_FLOPPY) += ataflop.o obj-$(CONFIG_AMIGA_Z2RAM) += z2ram.o obj-$(CONFIG_BLK_DEV_RAM) += brd.o -obj-$(CONFIG_BLK_DEV_PMEM) += pmem.o obj-$(CONFIG_BLK_DEV_LOOP) += loop.o obj-$(CONFIG_BLK_CPQ_DA) += cpqarray.o obj-$(CONFIG_BLK_CPQ_CISS_DA) += cciss.o diff --git a/drivers/nvdimm/Kconfig b/drivers/nvdimm/Kconfig new file mode 100644 index 000000000000..07a29113b870 --- /dev/null +++ b/drivers/nvdimm/Kconfig @@ -0,0 +1,36 @@ +menuconfig LIBNVDIMM + tristate "NVDIMM (Non-Volatile Memory Device) Support" + depends on PHYS_ADDR_T_64BIT + depends on BLK_DEV + help + Generic support for non-volatile memory devices including + ACPI-6-NFIT defined resources. On platforms that define an + NFIT, or otherwise can discover NVDIMM resources, a libnvdimm + bus is registered to advertise PMEM (persistent memory) + namespaces (/dev/pmemX) and BLK (sliding mmio window(s)) + namespaces (/dev/ndX). A PMEM namespace refers to a memory + resource that may span multiple DIMMs and support DAX (see + CONFIG_DAX). A BLK namespace refers to an NVDIMM control + region which exposes an mmio register set for windowed + access mode to non-volatile memory. + +if LIBNVDIMM + +config BLK_DEV_PMEM + tristate "PMEM: Persistent memory block device support" + default LIBNVDIMM + depends on HAS_IOMEM + help + Memory ranges for PMEM are described by either an NFIT + (NVDIMM Firmware Interface Table, see CONFIG_NFIT_ACPI), a + non-standard OEM-specific E820 memory type (type-12, see + CONFIG_X86_PMEM_LEGACY), or it is manually specified by the + 'memmap=nn[KMG]!ss[KMG]' kernel command line (see + Documentation/kernel-parameters.txt). This driver converts + these persistent memory ranges into block devices that are + capable of DAX (direct-access) file system mappings. See + Documentation/nvdimm/nvdimm.txt for more details. + + Say Y if you want to use an NVDIMM + +endif diff --git a/drivers/nvdimm/Makefile b/drivers/nvdimm/Makefile new file mode 100644 index 000000000000..abce98f87f16 --- /dev/null +++ b/drivers/nvdimm/Makefile @@ -0,0 +1,13 @@ +obj-$(CONFIG_LIBNVDIMM) += libnvdimm.o +obj-$(CONFIG_BLK_DEV_PMEM) += nd_pmem.o + +nd_pmem-y := pmem.o + +libnvdimm-y := core.o +libnvdimm-y += bus.o +libnvdimm-y += dimm_devs.o +libnvdimm-y += dimm.o +libnvdimm-y += region_devs.o +libnvdimm-y += region.o +libnvdimm-y += namespace_devs.o +libnvdimm-y += label.o diff --git a/drivers/nvdimm/bus.c b/drivers/nvdimm/bus.c new file mode 100644 index 000000000000..ca802702440e --- /dev/null +++ b/drivers/nvdimm/bus.c @@ -0,0 +1,668 @@ +/* + * Copyright(c) 2013-2015 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. + */ +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt +#include <linux/vmalloc.h> +#include <linux/uaccess.h> +#include <linux/module.h> +#include <linux/fcntl.h> +#include <linux/async.h> +#include <linux/ndctl.h> +#include <linux/sched.h> +#include <linux/slab.h> +#include <linux/fs.h> +#include <linux/io.h> +#include <linux/mm.h> +#include <linux/nd.h> +#include "nd-core.h" +#include "nd.h" + +int nvdimm_major; +static int nvdimm_bus_major; +static struct class *nd_class; + +static int to_nd_device_type(struct device *dev) +{ + if (is_nvdimm(dev)) + return ND_DEVICE_DIMM; + else if (is_nd_pmem(dev)) + return ND_DEVICE_REGION_PMEM; + else if (is_nd_blk(dev)) + return ND_DEVICE_REGION_BLK; + else if (is_nd_pmem(dev->parent) || is_nd_blk(dev->parent)) + return nd_region_to_nstype(to_nd_region(dev->parent)); + + return 0; +} + +static int nvdimm_bus_uevent(struct device *dev, struct kobj_uevent_env *env) +{ + return add_uevent_var(env, "MODALIAS=" ND_DEVICE_MODALIAS_FMT, + to_nd_device_type(dev)); +} + +static int nvdimm_bus_match(struct device *dev, struct device_driver *drv) +{ + struct nd_device_driver *nd_drv = to_nd_device_driver(drv); + + return test_bit(to_nd_device_type(dev), &nd_drv->type); +} + +static struct module *to_bus_provider(struct device *dev) +{ + /* pin bus providers while regions are enabled */ + if (is_nd_pmem(dev) || is_nd_blk(dev)) { + struct nvdimm_bus *nvdimm_bus = walk_to_nvdimm_bus(dev); + + return nvdimm_bus->module; + } + return NULL; +} + +static void nvdimm_bus_probe_start(struct nvdimm_bus *nvdimm_bus) +{ + nvdimm_bus_lock(&nvdimm_bus->dev); + nvdimm_bus->probe_active++; + nvdimm_bus_unlock(&nvdimm_bus->dev); +} + +static void nvdimm_bus_probe_end(struct nvdimm_bus *nvdimm_bus) +{ + nvdimm_bus_lock(&nvdimm_bus->dev); + if (--nvdimm_bus->probe_active == 0) + wake_up(&nvdimm_bus->probe_wait); + nvdimm_bus_unlock(&nvdimm_bus->dev); +} + +static int nvdimm_bus_probe(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; + + if (!try_module_get(provider)) + return -ENXIO; + + nvdimm_bus_probe_start(nvdimm_bus); + rc = nd_drv->probe(dev); + if (rc == 0) + nd_region_probe_success(nvdimm_bus, dev); + else + nd_region_disable(nvdimm_bus, dev); + nvdimm_bus_probe_end(nvdimm_bus); + + dev_dbg(&nvdimm_bus->dev, "%s.probe(%s) = %d\n", dev->driver->name, + dev_name(dev), rc); + if (rc != 0) + module_put(provider); + return rc; +} + +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; + + rc = nd_drv->remove(dev); + nd_region_disable(nvdimm_bus, dev); + + dev_dbg(&nvdimm_bus->dev, "%s.remove(%s) = %d\n", dev->driver->name, + dev_name(dev), rc); + module_put(provider); + return rc; +} + +static struct bus_type nvdimm_bus_type = { + .name = "nd", + .uevent = nvdimm_bus_uevent, + .match = nvdimm_bus_match, + .probe = nvdimm_bus_probe, + .remove = nvdimm_bus_remove, +}; + +static ASYNC_DOMAIN_EXCLUSIVE(nd_async_domain); + +void nd_synchronize(void) +{ + async_synchronize_full_domain(&nd_async_domain); +} +EXPORT_SYMBOL_GPL(nd_synchronize); + +static void nd_async_device_register(void *d, async_cookie_t cookie) +{ + struct device *dev = d; + + if (device_add(dev) != 0) { + dev_err(dev, "%s: failed\n", __func__); + put_device(dev); + } + put_device(dev); +} + +static void nd_async_device_unregister(void *d, async_cookie_t cookie) +{ + struct device *dev = d; + + /* flush bus operations before delete */ + nvdimm_bus_lock(dev); + nvdimm_bus_unlock(dev); + + device_unregister(dev); + put_device(dev); +} + +void nd_device_register(struct device *dev) +{ + dev->bus = &nvdimm_bus_type; + device_initialize(dev); + get_device(dev); + async_schedule_domain(nd_async_device_register, dev, + &nd_async_domain); +} +EXPORT_SYMBOL(nd_device_register); + +void nd_device_unregister(struct device *dev, enum nd_async_mode mode) +{ + switch (mode) { + case ND_ASYNC: + get_device(dev); + async_schedule_domain(nd_async_device_unregister, dev, + &nd_async_domain); + break; + case ND_SYNC: + nd_synchronize(); + device_unregister(dev); + break; + } +} +EXPORT_SYMBOL(nd_device_unregister); + +/** + * __nd_driver_register() - register a region or a namespace driver + * @nd_drv: driver to register + * @owner: automatically set by nd_driver_register() macro + * @mod_name: automatically set by nd_driver_register() macro + */ +int __nd_driver_register(struct nd_device_driver *nd_drv, struct module *owner, + const char *mod_name) +{ + struct device_driver *drv = &nd_drv->drv; + + if (!nd_drv->type) { + pr_debug("driver type bitmask not set (%pf)\n", + __builtin_return_address(0)); + return -EINVAL; + } + + if (!nd_drv->probe || !nd_drv->remove) { + pr_debug("->probe() and ->remove() must be specified\n"); + return -EINVAL; + } + + drv->bus = &nvdimm_bus_type; + drv->owner = owner; + drv->mod_name = mod_name; + + return driver_register(drv); +} +EXPORT_SYMBOL(__nd_driver_register); + +static ssize_t modalias_show(struct device *dev, struct device_attribute *attr, + char *buf) +{ + return sprintf(buf, ND_DEVICE_MODALIAS_FMT "\n", + to_nd_device_type(dev)); +} +static DEVICE_ATTR_RO(modalias); + +static ssize_t devtype_show(struct device *dev, struct device_attribute *attr, + char *buf) +{ + return sprintf(buf, "%s\n", dev->type->name); +} +static DEVICE_ATTR_RO(devtype); + +static struct attribute *nd_device_attributes[] = { + &dev_attr_modalias.attr, + &dev_attr_devtype.attr, + NULL, +}; + +/** + * nd_device_attribute_group - generic attributes for all devices on an nd bus + */ +struct attribute_group nd_device_attribute_group = { + .attrs = nd_device_attributes, +}; +EXPORT_SYMBOL_GPL(nd_device_attribute_group); + +int nvdimm_bus_create_ndctl(struct nvdimm_bus *nvdimm_bus) +{ + dev_t devt = MKDEV(nvdimm_bus_major, nvdimm_bus->id); + struct device *dev; + + dev = device_create(nd_class, &nvdimm_bus->dev, devt, nvdimm_bus, + "ndctl%d", nvdimm_bus->id); + + if (IS_ERR(dev)) { + dev_dbg(&nvdimm_bus->dev, "failed to register ndctl%d: %ld\n", + nvdimm_bus->id, PTR_ERR(dev)); + return PTR_ERR(dev); + } + return 0; +} + +void nvdimm_bus_destroy_ndctl(struct nvdimm_bus *nvdimm_bus) +{ + device_destroy(nd_class, MKDEV(nvdimm_bus_major, nvdimm_bus->id)); +} + +static const struct nd_cmd_desc __nd_cmd_dimm_descs[] = { + [ND_CMD_IMPLEMENTED] = { }, + [ND_CMD_SMART] = { + .out_num = 2, + .out_sizes = { 4, 8, }, + }, + [ND_CMD_SMART_THRESHOLD] = { + .out_num = 2, + .out_sizes = { 4, 8, }, + }, + [ND_CMD_DIMM_FLAGS] = { + .out_num = 2, + .out_sizes = { 4, 4 }, + }, + [ND_CMD_GET_CONFIG_SIZE] = { + .out_num = 3, + .out_sizes = { 4, 4, 4, }, + }, + [ND_CMD_GET_CONFIG_DATA] = { + .in_num = 2, + .in_sizes = { 4, 4, }, + .out_num = 2, + .out_sizes = { 4, UINT_MAX, }, + }, + [ND_CMD_SET_CONFIG_DATA] = { + .in_num = 3, + .in_sizes = { 4, 4, UINT_MAX, }, + .out_num = 1, + .out_sizes = { 4, }, + }, + [ND_CMD_VENDOR] = { + .in_num = 3, + .in_sizes = { 4, 4, UINT_MAX, }, + .out_num = 3, + .out_sizes = { 4, 4, UINT_MAX, }, + }, +}; + +const struct nd_cmd_desc *nd_cmd_dimm_desc(int cmd) +{ + if (cmd < ARRAY_SIZE(__nd_cmd_dimm_descs)) + return &__nd_cmd_dimm_descs[cmd]; + return NULL; +} +EXPORT_SYMBOL_GPL(nd_cmd_dimm_desc); + +static const struct nd_cmd_desc __nd_cmd_bus_descs[] = { + [ND_CMD_IMPLEMENTED] = { }, + [ND_CMD_ARS_CAP] = { + .in_num = 2, + .in_sizes = { 8, 8, }, + .out_num = 2, + .out_sizes = { 4, 4, }, + }, + [ND_CMD_ARS_START] = { + .in_num = 4, + .in_sizes = { 8, 8, 2, 6, }, + .out_num = 1, + .out_sizes = { 4, }, + }, + [ND_CMD_ARS_STATUS] = { + .out_num = 2, + .out_sizes = { 4, UINT_MAX, }, + }, +}; + +const struct nd_cmd_desc *nd_cmd_bus_desc(int cmd) +{ + if (cmd < ARRAY_SIZE(__nd_cmd_bus_descs)) + return &__nd_cmd_bus_descs[cmd]; + return NULL; +} +EXPORT_SYMBOL_GPL(nd_cmd_bus_desc); + +u32 nd_cmd_in_size(struct nvdimm *nvdimm, int cmd, + const struct nd_cmd_desc *desc, int idx, void *buf) +{ + if (idx >= desc->in_num) + return UINT_MAX; + + if (desc->in_sizes[idx] < UINT_MAX) + return desc->in_sizes[idx]; + + if (nvdimm && cmd == ND_CMD_SET_CONFIG_DATA && idx == 2) { + struct nd_cmd_set_config_hdr *hdr = buf; + + return hdr->in_length; + } else if (nvdimm && cmd == ND_CMD_VENDOR && idx == 2) { + struct nd_cmd_vendor_hdr *hdr = buf; + + return hdr->in_length; + } + + return UINT_MAX; +} +EXPORT_SYMBOL_GPL(nd_cmd_in_size); + +u32 nd_cmd_out_size(struct nvdimm *nvdimm, int cmd, + const struct nd_cmd_desc *desc, int idx, const u32 *in_field, + const u32 *out_field) +{ + if (idx >= desc->out_num) + return UINT_MAX; + + if (desc->out_sizes[idx] < UINT_MAX) + return desc->out_sizes[idx]; + + if (nvdimm && cmd == ND_CMD_GET_CONFIG_DATA && idx == 1) + return in_field[1]; + else if (nvdimm && cmd == ND_CMD_VENDOR && idx == 2) + return out_field[1]; + else if (!nvdimm && cmd == ND_CMD_ARS_STATUS && idx == 1) + return ND_CMD_ARS_STATUS_MAX; + + return UINT_MAX; +} +EXPORT_SYMBOL_GPL(nd_cmd_out_size); + +void wait_nvdimm_bus_probe_idle(struct device *dev) +{ + struct nvdimm_bus *nvdimm_bus = walk_to_nvdimm_bus(dev); + + do { + if (nvdimm_bus->probe_active == 0) + break; + nvdimm_bus_unlock(&nvdimm_bus->dev); + wait_event(nvdimm_bus->probe_wait, + nvdimm_bus->probe_active == 0); + nvdimm_bus_lock(&nvdimm_bus->dev); + } while (true); +} + +/* set_config requires an idle interleave set */ +static int nd_cmd_clear_to_send(struct nvdimm *nvdimm, unsigned int cmd) +{ + struct nvdimm_bus *nvdimm_bus; + + if (!nvdimm || cmd != ND_CMD_SET_CONFIG_DATA) + return 0; + + nvdimm_bus = walk_to_nvdimm_bus(&nvdimm->dev); + wait_nvdimm_bus_probe_idle(&nvdimm_bus->dev); + + if (atomic_read(&nvdimm->busy)) + return -EBUSY; + return 0; +} + +static int __nd_ioctl(struct nvdimm_bus *nvdimm_bus, struct nvdimm *nvdimm, + int read_only, unsigned int ioctl_cmd, unsigned long arg) +{ + struct nvdimm_bus_descriptor *nd_desc = nvdimm_bus->nd_desc; + size_t buf_len = 0, in_len = 0, out_len = 0; + static char out_env[ND_CMD_MAX_ENVELOPE]; + static char in_env[ND_CMD_MAX_ENVELOPE]; + const struct nd_cmd_desc *desc = NULL; + unsigned int cmd = _IOC_NR(ioctl_cmd); + void __user *p = (void __user *) arg; + struct device *dev = &nvdimm_bus->dev; + const char *cmd_name, *dimm_name; + unsigned long dsm_mask; + void *buf; + int rc, i; + + if (nvdimm) { + desc = nd_cmd_dimm_desc(cmd); + cmd_name = nvdimm_cmd_name(cmd); + dsm_mask = nvdimm->dsm_mask ? *(nvdimm->dsm_mask) : 0; + dimm_name = dev_name(&nvdimm->dev); + } else { + desc = nd_cmd_bus_desc(cmd); + cmd_name = nvdimm_bus_cmd_name(cmd); + dsm_mask = nd_desc->dsm_mask; + dimm_name = "bus"; + } + + if (!desc || (desc->out_num + desc->in_num == 0) || + !test_bit(cmd, &dsm_mask)) + return -ENOTTY; + + /* fail write commands (when read-only) */ + if (read_only) + switch (ioctl_cmd) { + case ND_IOCTL_VENDOR: + case ND_IOCTL_SET_CONFIG_DATA: + case ND_IOCTL_ARS_START: + dev_dbg(&nvdimm_bus->dev, "'%s' command while read-only.\n", + nvdimm ? nvdimm_cmd_name(cmd) + : nvdimm_bus_cmd_name(cmd)); + return -EPERM; + default: + break; + } + + /* process an input envelope */ + for (i = 0; i < desc->in_num; i++) { + u32 in_size, copy; + + in_size = nd_cmd_in_size(nvdimm, cmd, desc, i, in_env); + if (in_size == UINT_MAX) { + dev_err(dev, "%s:%s unknown input size cmd: %s field: %d\n", + __func__, dimm_name, cmd_name, i); + return -ENXIO; + } + if (!access_ok(VERIFY_READ, p + in_len, in_size)) + return -EFAULT; + if (in_len < sizeof(in_env)) + copy = min_t(u32, sizeof(in_env) - in_len, in_size); + else + copy = 0; + if (copy && copy_from_user(&in_env[in_len], p + in_len, copy)) + return -EFAULT; + in_len += in_size; + } + + /* process an output envelope */ + for (i = 0; i < desc->out_num; i++) { + u32 out_size = nd_cmd_out_size(nvdimm, cmd, desc, i, + (u32 *) in_env, (u32 *) out_env); + u32 copy; + + if (out_size == UINT_MAX) { + dev_dbg(dev, "%s:%s unknown output size cmd: %s field: %d\n", + __func__, dimm_name, cmd_name, i); + return -EFAULT; + } + if (!access_ok(VERIFY_WRITE, p + in_len + out_len, out_size)) + return -EFAULT; + if (out_len < sizeof(out_env)) + copy = min_t(u32, sizeof(out_env) - out_len, out_size); + else + copy = 0; + if (copy && copy_from_user(&out_env[out_len], + p + in_len + out_len, copy)) + return -EFAULT; + out_len += out_size; + } + + buf_len = out_len + in_len; + if (!access_ok(VERIFY_WRITE, p, sizeof(buf_len))) + return -EFAULT; + + if (buf_len > ND_IOCTL_MAX_BUFLEN) { + dev_dbg(dev, "%s:%s cmd: %s buf_len: %zu > %d\n", __func__, + dimm_name, cmd_name, buf_len, + ND_IOCTL_MAX_BUFLEN); + return -EINVAL; + } + + buf = vmalloc(buf_len); + if (!buf) + return -ENOMEM; + + if (copy_from_user(buf, p, buf_len)) { + rc = -EFAULT; + goto out; + } + + nvdimm_bus_lock(&nvdimm_bus->dev); + rc = nd_cmd_clear_to_send(nvdimm, cmd); + if (rc) + goto out_unlock; + + rc = nd_desc->ndctl(nd_desc, nvdimm, cmd, buf, buf_len); + if (rc < 0) + goto out_unlock; + if (copy_to_user(p, buf, buf_len)) + rc = -EFAULT; + out_unlock: + nvdimm_bus_unlock(&nvdimm_bus->dev); + out: + vfree(buf); + return rc; +} + +static long nd_ioctl(struct file *file, unsigned int cmd, unsigned long arg) +{ + long id = (long) file->private_data; + int rc = -ENXIO, read_only; + struct nvdimm_bus *nvdimm_bus; + + read_only = (O_RDWR != (file->f_flags & O_ACCMODE)); + mutex_lock(&nvdimm_bus_list_mutex); + list_for_each_entry(nvdimm_bus, &nvdimm_bus_list, list) { + if (nvdimm_bus->id == id) { + rc = __nd_ioctl(nvdimm_bus, NULL, read_only, cmd, arg); + break; + } + } + mutex_unlock(&nvdimm_bus_list_mutex); + + return rc; +} + +static int match_dimm(struct device *dev, void *data) +{ + long id = (long) data; + + if (is_nvdimm(dev)) { + struct nvdimm *nvdimm = to_nvdimm(dev); + + return nvdimm->id == id; + } + + return 0; +} + +static long nvdimm_ioctl(struct file *file, unsigned int cmd, unsigned long arg) +{ + int rc = -ENXIO, read_only; + struct nvdimm_bus *nvdimm_bus; + + read_only = (O_RDWR != (file->f_flags & O_ACCMODE)); + mutex_lock(&nvdimm_bus_list_mutex); + list_for_each_entry(nvdimm_bus, &nvdimm_bus_list, list) { + struct device *dev = device_find_child(&nvdimm_bus->dev, + file->private_data, match_dimm); + struct nvdimm *nvdimm; + + if (!dev) + continue; + + nvdimm = to_nvdimm(dev); + rc = __nd_ioctl(nvdimm_bus, nvdimm, read_only, cmd, arg); + put_device(dev); + break; + } + mutex_unlock(&nvdimm_bus_list_mutex); + + return rc; +} + +static int nd_open(struct inode *inode, struct file *file) +{ + long minor = iminor(inode); + + file->private_data = (void *) minor; + return 0; +} + +static const struct file_operations nvdimm_bus_fops = { + .owner = THIS_MODULE, + .open = nd_open, + .unlocked_ioctl = nd_ioctl, + .compat_ioctl = nd_ioctl, + .llseek = noop_llseek, +}; + +static const struct file_operations nvdimm_fops = { + .owner = THIS_MODULE, + .open = nd_open, + .unlocked_ioctl = nvdimm_ioctl, + .compat_ioctl = nvdimm_ioctl, + .llseek = noop_llseek, +}; + +int __init nvdimm_bus_init(void) +{ + int rc; + + rc = bus_register(&nvdimm_bus_type); + if (rc) + return rc; + + rc = register_chrdev(0, "ndctl", &nvdimm_bus_fops); + if (rc < 0) + goto err_bus_chrdev; + nvdimm_bus_major = rc; + + rc = register_chrdev(0, "dimmctl", &nvdimm_fops); + if (rc < 0) + goto err_dimm_chrdev; + nvdimm_major = rc; + + nd_class = class_create(THIS_MODULE, "nd"); + if (IS_ERR(nd_class)) + goto err_class; + + return 0; + + err_class: + unregister_chrdev(nvdimm_major, "dimmctl"); + err_dimm_chrdev: + unregister_chrdev(nvdimm_bus_major, "ndctl"); + err_bus_chrdev: + bus_unregister(&nvdimm_bus_type); + + return rc; +} + +void nvdimm_bus_exit(void) +{ + class_destroy(nd_class); + unregister_chrdev(nvdimm_bus_major, "ndctl"); + unregister_chrdev(nvdimm_major, "dimmctl"); + bus_unregister(&nvdimm_bus_type); +} diff --git a/drivers/nvdimm/core.c b/drivers/nvdimm/core.c new file mode 100644 index 000000000000..dd824d7c2669 --- /dev/null +++ b/drivers/nvdimm/core.c @@ -0,0 +1,396 @@ +/* + * Copyright(c) 2013-2015 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/libnvdimm.h> +#include <linux/export.h> +#include <linux/module.h> +#include <linux/device.h> +#include <linux/ctype.h> +#include <linux/ndctl.h> +#include <linux/mutex.h> +#include <linux/slab.h> +#include "nd-core.h" +#include "nd.h" + +LIST_HEAD(nvdimm_bus_list); +DEFINE_MUTEX(nvdimm_bus_list_mutex); +static DEFINE_IDA(nd_ida); + +void nvdimm_bus_lock(struct device *dev) +{ + struct nvdimm_bus *nvdimm_bus = walk_to_nvdimm_bus(dev); + + if (!nvdimm_bus) + return; + mutex_lock(&nvdimm_bus->reconfig_mutex); +} +EXPORT_SYMBOL(nvdimm_bus_lock); + +void nvdimm_bus_unlock(struct device *dev) +{ + struct nvdimm_bus *nvdimm_bus = walk_to_nvdimm_bus(dev); + + if (!nvdimm_bus) + return; + mutex_unlock(&nvdimm_bus->reconfig_mutex); +} +EXPORT_SYMBOL(nvdimm_bus_unlock); + +bool is_nvdimm_bus_locked(struct device *dev) +{ + struct nvdimm_bus *nvdimm_bus = walk_to_nvdimm_bus(dev); + + if (!nvdimm_bus) + return false; + return mutex_is_locked(&nvdimm_bus->reconfig_mutex); +} +EXPORT_SYMBOL(is_nvdimm_bus_locked); + +u64 nd_fletcher64(void *addr, size_t len, bool le) +{ + u32 *buf = addr; + u32 lo32 = 0; + u64 hi32 = 0; + int i; + + for (i = 0; i < len / sizeof(u32); i++) { + lo32 += le ? le32_to_cpu((__le32) buf[i]) : buf[i]; + hi32 += lo32; + } + + return hi32 << 32 | lo32; +} +EXPORT_SYMBOL_GPL(nd_fletcher64); + +static void nvdimm_bus_release(struct device *dev) +{ + struct nvdimm_bus *nvdimm_bus; + + nvdimm_bus = container_of(dev, struct nvdimm_bus, dev); + ida_simple_remove(&nd_ida, nvdimm_bus->id); + kfree(nvdimm_bus); +} + +struct nvdimm_bus *to_nvdimm_bus(struct device *dev) +{ + struct nvdimm_bus *nvdimm_bus; + + nvdimm_bus = container_of(dev, struct nvdimm_bus, dev); + WARN_ON(nvdimm_bus->dev.release != nvdimm_bus_release); + return nvdimm_bus; +} +EXPORT_SYMBOL_GPL(to_nvdimm_bus); + +struct nvdimm_bus_descriptor *to_nd_desc(struct nvdimm_bus *nvdimm_bus) +{ + /* struct nvdimm_bus definition is private to libnvdimm */ + return nvdimm_bus->nd_desc; +} +EXPORT_SYMBOL_GPL(to_nd_desc); + +struct nvdimm_bus *walk_to_nvdimm_bus(struct device *nd_dev) +{ + struct device *dev; + + for (dev = nd_dev; dev; dev = dev->parent) + if (dev->release == nvdimm_bus_release) + break; + dev_WARN_ONCE(nd_dev, !dev, "invalid dev, not on nd bus\n"); + if (dev) + return to_nvdimm_bus(dev); + return NULL; +} + +static bool is_uuid_sep(char sep) +{ + if (sep == '\n' || sep == '-' || sep == ':' || sep == '\0') + return true; + return false; +} + +static int nd_uuid_parse(struct device *dev, u8 *uuid_out, const char *buf, + size_t len) +{ + const char *str = buf; + u8 uuid[16]; + int i; + + for (i = 0; i < 16; i++) { + if (!isxdigit(str[0]) || !isxdigit(str[1])) { + dev_dbg(dev, "%s: pos: %d buf[%zd]: %c buf[%zd]: %c\n", + __func__, i, str - buf, str[0], + str + 1 - buf, str[1]); + return -EINVAL; + } + + uuid[i] = (hex_to_bin(str[0]) << 4) | hex_to_bin(str[1]); + str += 2; + if (is_uuid_sep(*str)) + str++; + } + + memcpy(uuid_out, uuid, sizeof(uuid)); + return 0; +} + +/** + * nd_uuid_store: common implementation for writing 'uuid' sysfs attributes + * @dev: container device for the uuid property + * @uuid_out: uuid buffer to replace + * @buf: raw sysfs buffer to parse + * + * Enforce that uuids can only be changed while the device is disabled + * (driver detached) + * LOCKING: expects device_lock() is held on entry + */ +int nd_uuid_store(struct device *dev, u8 **uuid_out, const char *buf, + size_t len) +{ + u8 uuid[16]; + int rc; + + if (dev->driver) + return -EBUSY; + + rc = nd_uuid_parse(dev, uuid, buf, len); + if (rc) + return rc; + + kfree(*uuid_out); + *uuid_out = kmemdup(uuid, sizeof(uuid), GFP_KERNEL); + if (!(*uuid_out)) + return -ENOMEM; + + return 0; +} + +ssize_t nd_sector_size_show(unsigned long current_lbasize, + const unsigned long *supported, char *buf) +{ + ssize_t len = 0; + int i; + + for (i = 0; supported[i]; i++) + if (current_lbasize == supported[i]) + len += sprintf(buf + len, "[%ld] ", supported[i]); + else + len += sprintf(buf + len, "%ld ", supported[i]); + len += sprintf(buf + len, "\n"); + return len; +} + +ssize_t nd_sector_size_store(struct device *dev, const char *buf, + unsigned long *current_lbasize, const unsigned long *supported) +{ + unsigned long lbasize; + int rc, i; + + if (dev->driver) + return -EBUSY; + + rc = kstrtoul(buf, 0, &lbasize); + if (rc) + return rc; + + for (i = 0; supported[i]; i++) + if (lbasize == supported[i]) + break; + + if (supported[i]) { + *current_lbasize = lbasize; + return 0; + } else { + return -EINVAL; + } +} + +static ssize_t commands_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + int cmd, len = 0; + struct nvdimm_bus *nvdimm_bus = to_nvdimm_bus(dev); + struct nvdimm_bus_descriptor *nd_desc = nvdimm_bus->nd_desc; + + for_each_set_bit(cmd, &nd_desc->dsm_mask, BITS_PER_LONG) + len += sprintf(buf + len, "%s ", nvdimm_bus_cmd_name(cmd)); + len += sprintf(buf + len, "\n"); + return len; +} +static DEVICE_ATTR_RO(commands); + +static const char *nvdimm_bus_provider(struct nvdimm_bus *nvdimm_bus) +{ + struct nvdimm_bus_descriptor *nd_desc = nvdimm_bus->nd_desc; + struct device *parent = nvdimm_bus->dev.parent; + + if (nd_desc->provider_name) + return nd_desc->provider_name; + else if (parent) + return dev_name(parent); + else + return "unknown"; +} + +static ssize_t provider_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + struct nvdimm_bus *nvdimm_bus = to_nvdimm_bus(dev); + + return sprintf(buf, "%s\n", nvdimm_bus_provider(nvdimm_bus)); +} +static DEVICE_ATTR_RO(provider); + +static int flush_namespaces(struct device *dev, void *data) +{ + device_lock(dev); + device_unlock(dev); + return 0; +} + +static int flush_regions_dimms(struct device *dev, void *data) +{ + device_lock(dev); + device_unlock(dev); + device_for_each_child(dev, NULL, flush_namespaces); + return 0; +} + +static ssize_t wait_probe_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + nd_synchronize(); + device_for_each_child(dev, NULL, flush_regions_dimms); + return sprintf(buf, "1\n"); +} +static DEVICE_ATTR_RO(wait_probe); + +static struct attribute *nvdimm_bus_attributes[] = { + &dev_attr_commands.attr, + &dev_attr_wait_probe.attr, + &dev_attr_provider.attr, + NULL, +}; + +struct attribute_group nvdimm_bus_attribute_group = { + .attrs = nvdimm_bus_attributes, +}; +EXPORT_SYMBOL_GPL(nvdimm_bus_attribute_group); + +struct nvdimm_bus *__nvdimm_bus_register(struct device *parent, + struct nvdimm_bus_descriptor *nd_desc, struct module *module) +{ + struct nvdimm_bus *nvdimm_bus; + int rc; + + nvdimm_bus = kzalloc(sizeof(*nvdimm_bus), GFP_KERNEL); + if (!nvdimm_bus) + return NULL; + INIT_LIST_HEAD(&nvdimm_bus->list); + init_waitqueue_head(&nvdimm_bus->probe_wait); + nvdimm_bus->id = ida_simple_get(&nd_ida, 0, 0, GFP_KERNEL); + mutex_init(&nvdimm_bus->reconfig_mutex); + if (nvdimm_bus->id < 0) { + kfree(nvdimm_bus); + return NULL; + } + nvdimm_bus->nd_desc = nd_desc; + nvdimm_bus->module = module; + nvdimm_bus->dev.parent = parent; + nvdimm_bus->dev.release = nvdimm_bus_release; + nvdimm_bus->dev.groups = nd_desc->attr_groups; + dev_set_name(&nvdimm_bus->dev, "ndbus%d", nvdimm_bus->id); + rc = device_register(&nvdimm_bus->dev); + if (rc) { + dev_dbg(&nvdimm_bus->dev, "registration failed: %d\n", rc); + goto err; + } + + rc = nvdimm_bus_create_ndctl(nvdimm_bus); + if (rc) + goto err; + + mutex_lock(&nvdimm_bus_list_mutex); + list_add_tail(&nvdimm_bus->list, &nvdimm_bus_list); + mutex_unlock(&nvdimm_bus_list_mutex); + + return nvdimm_bus; + err: + put_device(&nvdimm_bus->dev); + return NULL; +} +EXPORT_SYMBOL_GPL(__nvdimm_bus_register); + +static int child_unregister(struct device *dev, void *data) +{ + /* + * the singular ndctl class device per bus needs to be + * "device_destroy"ed, so skip it here + * + * i.e. remove classless children + */ + if (dev->class) + /* pass */; + else + nd_device_unregister(dev, ND_SYNC); + return 0; +} + +void nvdimm_bus_unregister(struct nvdimm_bus *nvdimm_bus) +{ + if (!nvdimm_bus) + return; + + mutex_lock(&nvdimm_bus_list_mutex); + list_del_init(&nvdimm_bus->list); + mutex_unlock(&nvdimm_bus_list_mutex); + + nd_synchronize(); + device_for_each_child(&nvdimm_bus->dev, NULL, child_unregister); + nvdimm_bus_destroy_ndctl(nvdimm_bus); + + device_unregister(&nvdimm_bus->dev); +} +EXPORT_SYMBOL_GPL(nvdimm_bus_unregister); + +static __init int libnvdimm_init(void) +{ + int rc; + + rc = nvdimm_bus_init(); + if (rc) + return rc; + rc = nvdimm_init(); + if (rc) + goto err_dimm; + rc = nd_region_init(); + if (rc) + goto err_region; + return 0; + err_region: + nvdimm_exit(); + err_dimm: + nvdimm_bus_exit(); + return rc; +} + +static __exit void libnvdimm_exit(void) +{ + WARN_ON(!list_empty(&nvdimm_bus_list)); + nd_region_exit(); + nvdimm_exit(); + nvdimm_bus_exit(); +} + +MODULE_LICENSE("GPL v2"); +MODULE_AUTHOR("Intel Corporation"); +subsys_initcall(libnvdimm_init); +module_exit(libnvdimm_exit); diff --git a/drivers/nvdimm/dimm.c b/drivers/nvdimm/dimm.c new file mode 100644 index 000000000000..71d12bb67339 --- /dev/null +++ b/drivers/nvdimm/dimm.c @@ -0,0 +1,102 @@ +/* + * Copyright(c) 2013-2015 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/vmalloc.h> +#include <linux/module.h> +#include <linux/device.h> +#include <linux/sizes.h> +#include <linux/ndctl.h> +#include <linux/slab.h> +#include <linux/mm.h> +#include <linux/nd.h> +#include "label.h" +#include "nd.h" + +static int nvdimm_probe(struct device *dev) +{ + struct nvdimm_drvdata *ndd; + int rc; + + ndd = kzalloc(sizeof(*ndd), GFP_KERNEL); + if (!ndd) + return -ENOMEM; + + dev_set_drvdata(dev, ndd); + ndd->dpa.name = dev_name(dev); + ndd->ns_current = -1; + ndd->ns_next = -1; + ndd->dpa.start = 0; + ndd->dpa.end = -1; + ndd->dev = dev; + get_device(dev); + kref_init(&ndd->kref); + + rc = nvdimm_init_nsarea(ndd); + if (rc) + goto err; + + rc = nvdimm_init_config_data(ndd); + if (rc) + goto err; + + dev_dbg(dev, "config data size: %d\n", ndd->nsarea.config_size); + + nvdimm_bus_lock(dev); + ndd->ns_current = nd_label_validate(ndd); + ndd->ns_next = nd_label_next_nsindex(ndd->ns_current); + nd_label_copy(ndd, to_next_namespace_index(ndd), + to_current_namespace_index(ndd)); + rc = nd_label_reserve_dpa(ndd); + nvdimm_bus_unlock(dev); + + if (rc) + goto err; + + return 0; + + err: + put_ndd(ndd); + return rc; +} + +static int nvdimm_remove(struct device *dev) +{ + struct nvdimm_drvdata *ndd = dev_get_drvdata(dev); + + nvdimm_bus_lock(dev); + dev_set_drvdata(dev, NULL); + nvdimm_bus_unlock(dev); + put_ndd(ndd); + + return 0; +} + +static struct nd_device_driver nvdimm_driver = { + .probe = nvdimm_probe, + .remove = nvdimm_remove, + .drv = { + .name = "nvdimm", + }, + .type = ND_DRIVER_DIMM, +}; + +int __init nvdimm_init(void) +{ + return nd_driver_register(&nvdimm_driver); +} + +void nvdimm_exit(void) +{ + driver_unregister(&nvdimm_driver.drv); +} + +MODULE_ALIAS_ND_DEVICE(ND_DEVICE_DIMM); diff --git a/drivers/nvdimm/dimm_devs.c b/drivers/nvdimm/dimm_devs.c new file mode 100644 index 000000000000..83b179ed6d61 --- /dev/null +++ b/drivers/nvdimm/dimm_devs.c @@ -0,0 +1,542 @@ +/* + * Copyright(c) 2013-2015 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. + */ +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt +#include <linux/vmalloc.h> +#include <linux/device.h> +#include <linux/ndctl.h> +#include <linux/slab.h> +#include <linux/io.h> +#include <linux/fs.h> +#include <linux/mm.h> +#include "nd-core.h" +#include "label.h" +#include "nd.h" + +static DEFINE_IDA(dimm_ida); + +/* + * Retrieve bus and dimm handle and return if this bus supports + * get_config_data commands + */ +static int __validate_dimm(struct nvdimm_drvdata *ndd) +{ + struct nvdimm *nvdimm; + + if (!ndd) + return -EINVAL; + + nvdimm = to_nvdimm(ndd->dev); + + if (!nvdimm->dsm_mask) + return -ENXIO; + if (!test_bit(ND_CMD_GET_CONFIG_DATA, nvdimm->dsm_mask)) + return -ENXIO; + + return 0; +} + +static int validate_dimm(struct nvdimm_drvdata *ndd) +{ + int rc = __validate_dimm(ndd); + + if (rc && ndd) + dev_dbg(ndd->dev, "%pf: %s error: %d\n", + __builtin_return_address(0), __func__, rc); + return rc; +} + +/** + * nvdimm_init_nsarea - determine the geometry of a dimm's namespace area + * @nvdimm: dimm to initialize + */ +int nvdimm_init_nsarea(struct nvdimm_drvdata *ndd) +{ + struct nd_cmd_get_config_size *cmd = &ndd->nsarea; + struct nvdimm_bus *nvdimm_bus = walk_to_nvdimm_bus(ndd->dev); + struct nvdimm_bus_descriptor *nd_desc; + int rc = validate_dimm(ndd); + + if (rc) + return rc; + + if (cmd->config_size) + return 0; /* already valid */ + + memset(cmd, 0, sizeof(*cmd)); + nd_desc = nvdimm_bus->nd_desc; + return nd_desc->ndctl(nd_desc, to_nvdimm(ndd->dev), + ND_CMD_GET_CONFIG_SIZE, cmd, sizeof(*cmd)); +} + +int nvdimm_init_config_data(struct nvdimm_drvdata *ndd) +{ + struct nvdimm_bus *nvdimm_bus = walk_to_nvdimm_bus(ndd->dev); + struct nd_cmd_get_config_data_hdr *cmd; + struct nvdimm_bus_descriptor *nd_desc; + int rc = validate_dimm(ndd); + u32 max_cmd_size, config_size; + size_t offset; + + if (rc) + return rc; + + if (ndd->data) + return 0; + + if (ndd->nsarea.status || ndd->nsarea.max_xfer == 0 + || ndd->nsarea.config_size < ND_LABEL_MIN_SIZE) { + dev_dbg(ndd->dev, "failed to init config data area: (%d:%d)\n", + ndd->nsarea.max_xfer, ndd->nsarea.config_size); + return -ENXIO; + } + + ndd->data = kmalloc(ndd->nsarea.config_size, GFP_KERNEL); + if (!ndd->data) + ndd->data = vmalloc(ndd->nsarea.config_size); + + if (!ndd->data) + return -ENOMEM; + + max_cmd_size = min_t(u32, PAGE_SIZE, ndd->nsarea.max_xfer); + cmd = kzalloc(max_cmd_size + sizeof(*cmd), GFP_KERNEL); + if (!cmd) + return -ENOMEM; + + nd_desc = nvdimm_bus->nd_desc; + for (config_size = ndd->nsarea.config_size, offset = 0; + config_size; config_size -= cmd->in_length, + offset += cmd->in_length) { + cmd->in_length = min(config_size, max_cmd_size); + cmd->in_offset = offset; + rc = nd_desc->ndctl(nd_desc, to_nvdimm(ndd->dev), + ND_CMD_GET_CONFIG_DATA, cmd, + cmd->in_length + sizeof(*cmd)); + if (rc || cmd->status) { + rc = -ENXIO; + break; + } + memcpy(ndd->data + offset, cmd->out_buf, cmd->in_length); + } + dev_dbg(ndd->dev, "%s: len: %zu rc: %d\n", __func__, offset, rc); + kfree(cmd); + + return rc; +} + +int nvdimm_set_config_data(struct nvdimm_drvdata *ndd, size_t offset, + void *buf, size_t len) +{ + int rc = validate_dimm(ndd); + size_t max_cmd_size, buf_offset; + struct nd_cmd_set_config_hdr *cmd; + struct nvdimm_bus *nvdimm_bus = walk_to_nvdimm_bus(ndd->dev); + struct nvdimm_bus_descriptor *nd_desc = nvdimm_bus->nd_desc; + + if (rc) + return rc; + + if (!ndd->data) + return -ENXIO; + + if (offset + len > ndd->nsarea.config_size) + return -ENXIO; + + max_cmd_size = min_t(u32, PAGE_SIZE, len); + max_cmd_size = min_t(u32, max_cmd_size, ndd->nsarea.max_xfer); + cmd = kzalloc(max_cmd_size + sizeof(*cmd) + sizeof(u32), GFP_KERNEL); + if (!cmd) + return -ENOMEM; + + for (buf_offset = 0; len; len -= cmd->in_length, + buf_offset += cmd->in_length) { + size_t cmd_size; + u32 *status; + + cmd->in_offset = offset + buf_offset; + cmd->in_length = min(max_cmd_size, len); + memcpy(cmd->in_buf, buf + buf_offset, cmd->in_length); + + /* status is output in the last 4-bytes of the command buffer */ + cmd_size = sizeof(*cmd) + cmd->in_length + sizeof(u32); + status = ((void *) cmd) + cmd_size - sizeof(u32); + + rc = nd_desc->ndctl(nd_desc, to_nvdimm(ndd->dev), + ND_CMD_SET_CONFIG_DATA, cmd, cmd_size); + if (rc || *status) { + rc = rc ? rc : -ENXIO; + break; + } + } + kfree(cmd); + + return rc; +} + +static void nvdimm_release(struct device *dev) +{ + struct nvdimm *nvdimm = to_nvdimm(dev); + + ida_simple_remove(&dimm_ida, nvdimm->id); + kfree(nvdimm); +} + +static struct device_type nvdimm_device_type = { + .name = "nvdimm", + .release = nvdimm_release, +}; + +bool is_nvdimm(struct device *dev) +{ + return dev->type == &nvdimm_device_type; +} + +struct nvdimm *to_nvdimm(struct device *dev) +{ + struct nvdimm *nvdimm = container_of(dev, struct nvdimm, dev); + + WARN_ON(!is_nvdimm(dev)); + return nvdimm; +} +EXPORT_SYMBOL_GPL(to_nvdimm); + +struct nvdimm_drvdata *to_ndd(struct nd_mapping *nd_mapping) +{ + struct nvdimm *nvdimm = nd_mapping->nvdimm; + + WARN_ON_ONCE(!is_nvdimm_bus_locked(&nvdimm->dev)); + + return dev_get_drvdata(&nvdimm->dev); +} +EXPORT_SYMBOL(to_ndd); + +void nvdimm_drvdata_release(struct kref *kref) +{ + struct nvdimm_drvdata *ndd = container_of(kref, typeof(*ndd), kref); + struct device *dev = ndd->dev; + struct resource *res, *_r; + + dev_dbg(dev, "%s\n", __func__); + + nvdimm_bus_lock(dev); + for_each_dpa_resource_safe(ndd, res, _r) + nvdimm_free_dpa(ndd, res); + nvdimm_bus_unlock(dev); + + if (ndd->data && is_vmalloc_addr(ndd->data)) + vfree(ndd->data); + else + kfree(ndd->data); + kfree(ndd); + put_device(dev); +} + +void get_ndd(struct nvdimm_drvdata *ndd) +{ + kref_get(&ndd->kref); +} + +void put_ndd(struct nvdimm_drvdata *ndd) +{ + if (ndd) + kref_put(&ndd->kref, nvdimm_drvdata_release); +} + +const char *nvdimm_name(struct nvdimm *nvdimm) +{ + return dev_name(&nvdimm->dev); +} +EXPORT_SYMBOL_GPL(nvdimm_name); + +void *nvdimm_provider_data(struct nvdimm *nvdimm) +{ + if (nvdimm) + return nvdimm->provider_data; + return NULL; +} +EXPORT_SYMBOL_GPL(nvdimm_provider_data); + +static ssize_t commands_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + struct nvdimm *nvdimm = to_nvdimm(dev); + int cmd, len = 0; + + if (!nvdimm->dsm_mask) + return sprintf(buf, "\n"); + + for_each_set_bit(cmd, nvdimm->dsm_mask, BITS_PER_LONG) + len += sprintf(buf + len, "%s ", nvdimm_cmd_name(cmd)); + len += sprintf(buf + len, "\n"); + return len; +} +static DEVICE_ATTR_RO(commands); + +static ssize_t state_show(struct device *dev, struct device_attribute *attr, + char *buf) +{ + struct nvdimm *nvdimm = to_nvdimm(dev); + + /* + * The state may be in the process of changing, userspace should + * quiesce probing if it wants a static answer + */ + nvdimm_bus_lock(dev); + nvdimm_bus_unlock(dev); + return sprintf(buf, "%s\n", atomic_read(&nvdimm->busy) + ? "active" : "idle"); +} +static DEVICE_ATTR_RO(state); + +static ssize_t available_slots_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + struct nvdimm_drvdata *ndd = dev_get_drvdata(dev); + ssize_t rc; + u32 nfree; + + if (!ndd) + return -ENXIO; + + nvdimm_bus_lock(dev); + nfree = nd_label_nfree(ndd); + if (nfree - 1 > nfree) { + dev_WARN_ONCE(dev, 1, "we ate our last label?\n"); + nfree = 0; + } else + nfree--; + rc = sprintf(buf, "%d\n", nfree); + nvdimm_bus_unlock(dev); + return rc; +} +static DEVICE_ATTR_RO(available_slots); + +static struct attribute *nvdimm_attributes[] = { + &dev_attr_state.attr, + &dev_attr_commands.attr, + &dev_attr_available_slots.attr, + NULL, +}; + +struct attribute_group nvdimm_attribute_group = { + .attrs = nvdimm_attributes, +}; +EXPORT_SYMBOL_GPL(nvdimm_attribute_group); + +struct nvdimm *nvdimm_create(struct nvdimm_bus *nvdimm_bus, void *provider_data, + const struct attribute_group **groups, unsigned long flags, + unsigned long *dsm_mask) +{ + struct nvdimm *nvdimm = kzalloc(sizeof(*nvdimm), GFP_KERNEL); + struct device *dev; + + if (!nvdimm) + return NULL; + + nvdimm->id = ida_simple_get(&dimm_ida, 0, 0, GFP_KERNEL); + if (nvdimm->id < 0) { + kfree(nvdimm); + return NULL; + } + nvdimm->provider_data = provider_data; + nvdimm->flags = flags; + nvdimm->dsm_mask = dsm_mask; + atomic_set(&nvdimm->busy, 0); + dev = &nvdimm->dev; + dev_set_name(dev, "nmem%d", nvdimm->id); + dev->parent = &nvdimm_bus->dev; + dev->type = &nvdimm_device_type; + dev->devt = MKDEV(nvdimm_major, nvdimm->id); + dev->groups = groups; + nd_device_register(dev); + + return nvdimm; +} +EXPORT_SYMBOL_GPL(nvdimm_create); + +/** + * nd_blk_available_dpa - account the unused dpa of BLK region + * @nd_mapping: container of dpa-resource-root + labels + * + * Unlike PMEM, BLK namespaces can occupy discontiguous DPA ranges. + */ +resource_size_t nd_blk_available_dpa(struct nd_mapping *nd_mapping) +{ + struct nvdimm_drvdata *ndd = to_ndd(nd_mapping); + resource_size_t map_end, busy = 0, available; + struct resource *res; + + if (!ndd) + return 0; + + map_end = nd_mapping->start + nd_mapping->size - 1; + for_each_dpa_resource(ndd, res) + if (res->start >= nd_mapping->start && res->start < map_end) { + resource_size_t end = min(map_end, res->end); + + busy += end - res->start + 1; + } else if (res->end >= nd_mapping->start + && res->end <= map_end) { + busy += res->end - nd_mapping->start; + } else if (nd_mapping->start > res->start + && nd_mapping->start < res->end) { + /* total eclipse of the BLK region mapping */ + busy += nd_mapping->size; + } + + available = map_end - nd_mapping->start + 1; + if (busy < available) + return available - busy; + return 0; +} + +/** + * nd_pmem_available_dpa - for the given dimm+region account unallocated dpa + * @nd_mapping: container of dpa-resource-root + labels + * @nd_region: constrain available space check to this reference region + * @overlap: calculate available space assuming this level of overlap + * + * Validate that a PMEM label, if present, aligns with the start of an + * interleave set and truncate the available size at the lowest BLK + * overlap point. + * + * The expectation is that this routine is called multiple times as it + * probes for the largest BLK encroachment for any single member DIMM of + * the interleave set. Once that value is determined the PMEM-limit for + * the set can be established. + */ +resource_size_t nd_pmem_available_dpa(struct nd_region *nd_region, + struct nd_mapping *nd_mapping, resource_size_t *overlap) +{ + resource_size_t map_start, map_end, busy = 0, available, blk_start; + struct nvdimm_drvdata *ndd = to_ndd(nd_mapping); + struct resource *res; + const char *reason; + + if (!ndd) + return 0; + + map_start = nd_mapping->start; + map_end = map_start + nd_mapping->size - 1; + blk_start = max(map_start, map_end + 1 - *overlap); + for_each_dpa_resource(ndd, res) + if (res->start >= map_start && res->start < map_end) { + if (strncmp(res->name, "blk", 3) == 0) + blk_start = min(blk_start, res->start); + else if (res->start != map_start) { + reason = "misaligned to iset"; + goto err; + } else { + if (busy) { + reason = "duplicate overlapping PMEM reservations?"; + goto err; + } + busy += resource_size(res); + continue; + } + } else if (res->end >= map_start && res->end <= map_end) { + if (strncmp(res->name, "blk", 3) == 0) { + /* + * If a BLK allocation overlaps the start of + * PMEM the entire interleave set may now only + * be used for BLK. + */ + blk_start = map_start; + } else { + reason = "misaligned to iset"; + goto err; + } + } else if (map_start > res->start && map_start < res->end) { + /* total eclipse of the mapping */ + busy += nd_mapping->size; + blk_start = map_start; + } + + *overlap = map_end + 1 - blk_start; + available = blk_start - map_start; + if (busy < available) + return available - busy; + return 0; + + err: + /* + * Something is wrong, PMEM must align with the start of the + * interleave set, and there can only be one allocation per set. + */ + nd_dbg_dpa(nd_region, ndd, res, "%s\n", reason); + return 0; +} + +void nvdimm_free_dpa(struct nvdimm_drvdata *ndd, struct resource *res) +{ + WARN_ON_ONCE(!is_nvdimm_bus_locked(ndd->dev)); + kfree(res->name); + __release_region(&ndd->dpa, res->start, resource_size(res)); +} + +struct resource *nvdimm_allocate_dpa(struct nvdimm_drvdata *ndd, + struct nd_label_id *label_id, resource_size_t start, + resource_size_t n) +{ + char *name = kmemdup(label_id, sizeof(*label_id), GFP_KERNEL); + struct resource *res; + + if (!name) + return NULL; + + WARN_ON_ONCE(!is_nvdimm_bus_locked(ndd->dev)); + res = __request_region(&ndd->dpa, start, n, name, 0); + if (!res) + kfree(name); + return res; +} + +/** + * nvdimm_allocated_dpa - sum up the dpa currently allocated to this label_id + * @nvdimm: container of dpa-resource-root + labels + * @label_id: dpa resource name of the form {pmem|blk}-<human readable uuid> + */ +resource_size_t nvdimm_allocated_dpa(struct nvdimm_drvdata *ndd, + struct nd_label_id *label_id) +{ + resource_size_t allocated = 0; + struct resource *res; + + for_each_dpa_resource(ndd, res) + if (strcmp(res->name, label_id->id) == 0) + allocated += resource_size(res); + + return allocated; +} + +static int count_dimms(struct device *dev, void *c) +{ + int *count = c; + + if (is_nvdimm(dev)) + (*count)++; + return 0; +} + +int nvdimm_bus_check_dimm_count(struct nvdimm_bus *nvdimm_bus, int dimm_count) +{ + int count = 0; + /* Flush any possible dimm registration failures */ + nd_synchronize(); + + device_for_each_child(&nvdimm_bus->dev, &count, count_dimms); + dev_dbg(&nvdimm_bus->dev, "%s: count: %d\n", __func__, count); + if (count != dimm_count) + return -ENXIO; + return 0; +} +EXPORT_SYMBOL_GPL(nvdimm_bus_check_dimm_count); diff --git a/drivers/nvdimm/label.c b/drivers/nvdimm/label.c new file mode 100644 index 000000000000..34148003fc73 --- /dev/null +++ b/drivers/nvdimm/label.c @@ -0,0 +1,926 @@ +/* + * Copyright(c) 2013-2015 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/ndctl.h> +#include <linux/slab.h> +#include <linux/io.h> +#include <linux/nd.h> +#include "nd-core.h" +#include "label.h" +#include "nd.h" + +static u32 best_seq(u32 a, u32 b) +{ + a &= NSINDEX_SEQ_MASK; + b &= NSINDEX_SEQ_MASK; + + if (a == 0 || a == b) + return b; + else if (b == 0) + return a; + else if (nd_inc_seq(a) == b) + return b; + else + return a; +} + +size_t sizeof_namespace_index(struct nvdimm_drvdata *ndd) +{ + u32 index_span; + + if (ndd->nsindex_size) + return ndd->nsindex_size; + + /* + * The minimum index space is 512 bytes, with that amount of + * index we can describe ~1400 labels which is less than a byte + * of overhead per label. Round up to a byte of overhead per + * label and determine the size of the index region. Yes, this + * starts to waste space at larger config_sizes, but it's + * unlikely we'll ever see anything but 128K. + */ + index_span = ndd->nsarea.config_size / 129; + index_span /= NSINDEX_ALIGN * 2; + ndd->nsindex_size = index_span * NSINDEX_ALIGN; + + return ndd->nsindex_size; +} + +int nvdimm_num_label_slots(struct nvdimm_drvdata *ndd) +{ + return ndd->nsarea.config_size / 129; +} + +int nd_label_validate(struct nvdimm_drvdata *ndd) +{ + /* + * On media label format consists of two index blocks followed + * by an array of labels. None of these structures are ever + * updated in place. A sequence number tracks the current + * active index and the next one to write, while labels are + * written to free slots. + * + * +------------+ + * | | + * | nsindex0 | + * | | + * +------------+ + * | | + * | nsindex1 | + * | | + * +------------+ + * | label0 | + * +------------+ + * | label1 | + * +------------+ + * | | + * ....nslot... + * | | + * +------------+ + * | labelN | + * +------------+ + */ + struct nd_namespace_index *nsindex[] = { + to_namespace_index(ndd, 0), + to_namespace_index(ndd, 1), + }; + const int num_index = ARRAY_SIZE(nsindex); + struct device *dev = ndd->dev; + bool valid[2] = { 0 }; + int i, num_valid = 0; + u32 seq; + + for (i = 0; i < num_index; i++) { + u32 nslot; + u8 sig[NSINDEX_SIG_LEN]; + u64 sum_save, sum, size; + + memcpy(sig, nsindex[i]->sig, NSINDEX_SIG_LEN); + if (memcmp(sig, NSINDEX_SIGNATURE, NSINDEX_SIG_LEN) != 0) { + dev_dbg(dev, "%s: nsindex%d signature invalid\n", + __func__, i); + continue; + } + sum_save = __le64_to_cpu(nsindex[i]->checksum); + nsindex[i]->checksum = __cpu_to_le64(0); + sum = nd_fletcher64(nsindex[i], sizeof_namespace_index(ndd), 1); + nsindex[i]->checksum = __cpu_to_le64(sum_save); + if (sum != sum_save) { + dev_dbg(dev, "%s: nsindex%d checksum invalid\n", + __func__, i); + continue; + } + + seq = __le32_to_cpu(nsindex[i]->seq); + if ((seq & NSINDEX_SEQ_MASK) == 0) { + dev_dbg(dev, "%s: nsindex%d sequence: %#x invalid\n", + __func__, i, seq); + continue; + } + + /* sanity check the index against expected values */ + if (__le64_to_cpu(nsindex[i]->myoff) + != i * sizeof_namespace_index(ndd)) { + dev_dbg(dev, "%s: nsindex%d myoff: %#llx invalid\n", + __func__, i, (unsigned long long) + __le64_to_cpu(nsindex[i]->myoff)); + continue; + } + if (__le64_to_cpu(nsindex[i]->otheroff) + != (!i) * sizeof_namespace_index(ndd)) { + dev_dbg(dev, "%s: nsindex%d otheroff: %#llx invalid\n", + __func__, i, (unsigned long long) + __le64_to_cpu(nsindex[i]->otheroff)); + continue; + } + + size = __le64_to_cpu(nsindex[i]->mysize); + if (size > sizeof_namespace_index(ndd) + || size < sizeof(struct nd_namespace_index)) { + dev_dbg(dev, "%s: nsindex%d mysize: %#llx invalid\n", + __func__, i, size); + continue; + } + + nslot = __le32_to_cpu(nsindex[i]->nslot); + if (nslot * sizeof(struct nd_namespace_label) + + 2 * sizeof_namespace_index(ndd) + > ndd->nsarea.config_size) { + dev_dbg(dev, "%s: nsindex%d nslot: %u invalid, config_size: %#x\n", + __func__, i, nslot, + ndd->nsarea.config_size); + continue; + } + valid[i] = true; + num_valid++; + } + + switch (num_valid) { + case 0: + break; + case 1: + for (i = 0; i < num_index; i++) + if (valid[i]) + return i; + /* can't have num_valid > 0 but valid[] = { false, false } */ + WARN_ON(1); + break; + default: + /* pick the best index... */ + seq = best_seq(__le32_to_cpu(nsindex[0]->seq), + __le32_to_cpu(nsindex[1]->seq)); + if (seq == (__le32_to_cpu(nsindex[1]->seq) & NSINDEX_SEQ_MASK)) + return 1; + else + return 0; + break; + } + + return -1; +} + +void nd_label_copy(struct nvdimm_drvdata *ndd, struct nd_namespace_index *dst, + struct nd_namespace_index *src) +{ + if (dst && src) + /* pass */; + else + return; + + memcpy(dst, src, sizeof_namespace_index(ndd)); +} + +static struct nd_namespace_label *nd_label_base(struct nvdimm_drvdata *ndd) +{ + void *base = to_namespace_index(ndd, 0); + + return base + 2 * sizeof_namespace_index(ndd); +} + +static int to_slot(struct nvdimm_drvdata *ndd, + struct nd_namespace_label *nd_label) +{ + return nd_label - nd_label_base(ndd); +} + +#define for_each_clear_bit_le(bit, addr, size) \ + for ((bit) = find_next_zero_bit_le((addr), (size), 0); \ + (bit) < (size); \ + (bit) = find_next_zero_bit_le((addr), (size), (bit) + 1)) + +/** + * preamble_index - common variable initialization for nd_label_* routines + * @ndd: dimm container for the relevant label set + * @idx: namespace_index index + * @nsindex_out: on return set to the currently active namespace index + * @free: on return set to the free label bitmap in the index + * @nslot: on return set to the number of slots in the label space + */ +static bool preamble_index(struct nvdimm_drvdata *ndd, int idx, + struct nd_namespace_index **nsindex_out, + unsigned long **free, u32 *nslot) +{ + struct nd_namespace_index *nsindex; + + nsindex = to_namespace_index(ndd, idx); + if (nsindex == NULL) + return false; + + *free = (unsigned long *) nsindex->free; + *nslot = __le32_to_cpu(nsindex->nslot); + *nsindex_out = nsindex; + + return true; +} + +char *nd_label_gen_id(struct nd_label_id *label_id, u8 *uuid, u32 flags) +{ + if (!label_id || !uuid) + return NULL; + snprintf(label_id->id, ND_LABEL_ID_SIZE, "%s-%pUb", + flags & NSLABEL_FLAG_LOCAL ? "blk" : "pmem", uuid); + return label_id->id; +} + +static bool preamble_current(struct nvdimm_drvdata *ndd, + struct nd_namespace_index **nsindex, + unsigned long **free, u32 *nslot) +{ + return preamble_index(ndd, ndd->ns_current, nsindex, + free, nslot); +} + +static bool preamble_next(struct nvdimm_drvdata *ndd, + struct nd_namespace_index **nsindex, + unsigned long **free, u32 *nslot) +{ + return preamble_index(ndd, ndd->ns_next, nsindex, + free, nslot); +} + +static bool slot_valid(struct nd_namespace_label *nd_label, u32 slot) +{ + /* check that we are written where we expect to be written */ + if (slot != __le32_to_cpu(nd_label->slot)) + return false; + + /* check that DPA allocations are page aligned */ + if ((__le64_to_cpu(nd_label->dpa) + | __le64_to_cpu(nd_label->rawsize)) % SZ_4K) + return false; + + return true; +} + +int nd_label_reserve_dpa(struct nvdimm_drvdata *ndd) +{ + struct nd_namespace_index *nsindex; + unsigned long *free; + u32 nslot, slot; + + if (!preamble_current(ndd, &nsindex, &free, &nslot)) + return 0; /* no label, nothing to reserve */ + + for_each_clear_bit_le(slot, free, nslot) { + struct nd_namespace_label *nd_label; + struct nd_region *nd_region = NULL; + u8 label_uuid[NSLABEL_UUID_LEN]; + struct nd_label_id label_id; + struct resource *res; + u32 flags; + + nd_label = nd_label_base(ndd) + slot; + + if (!slot_valid(nd_label, slot)) + continue; + + memcpy(label_uuid, nd_label->uuid, NSLABEL_UUID_LEN); + flags = __le32_to_cpu(nd_label->flags); + nd_label_gen_id(&label_id, label_uuid, flags); + res = nvdimm_allocate_dpa(ndd, &label_id, + __le64_to_cpu(nd_label->dpa), + __le64_to_cpu(nd_label->rawsize)); + nd_dbg_dpa(nd_region, ndd, res, "reserve\n"); + if (!res) + return -EBUSY; + } + + return 0; +} + +int nd_label_active_count(struct nvdimm_drvdata *ndd) +{ + struct nd_namespace_index *nsindex; + unsigned long *free; + u32 nslot, slot; + int count = 0; + + if (!preamble_current(ndd, &nsindex, &free, &nslot)) + return 0; + + for_each_clear_bit_le(slot, free, nslot) { + struct nd_namespace_label *nd_label; + + nd_label = nd_label_base(ndd) + slot; + + if (!slot_valid(nd_label, slot)) { + u32 label_slot = __le32_to_cpu(nd_label->slot); + u64 size = __le64_to_cpu(nd_label->rawsize); + u64 dpa = __le64_to_cpu(nd_label->dpa); + + dev_dbg(ndd->dev, + "%s: slot%d invalid slot: %d dpa: %llx size: %llx\n", + __func__, slot, label_slot, dpa, size); + continue; + } + count++; + } + return count; +} + +struct nd_namespace_label *nd_label_active(struct nvdimm_drvdata *ndd, int n) +{ + struct nd_namespace_index *nsindex; + unsigned long *free; + u32 nslot, slot; + + if (!preamble_current(ndd, &nsindex, &free, &nslot)) + return NULL; + + for_each_clear_bit_le(slot, free, nslot) { + struct nd_namespace_label *nd_label; + + nd_label = nd_label_base(ndd) + slot; + if (!slot_valid(nd_label, slot)) + continue; + + if (n-- == 0) + return nd_label_base(ndd) + slot; + } + + return NULL; +} + +u32 nd_label_alloc_slot(struct nvdimm_drvdata *ndd) +{ + struct nd_namespace_index *nsindex; + unsigned long *free; + u32 nslot, slot; + + if (!preamble_next(ndd, &nsindex, &free, &nslot)) + return UINT_MAX; + + WARN_ON(!is_nvdimm_bus_locked(ndd->dev)); + + slot = find_next_bit_le(free, nslot, 0); + if (slot == nslot) + return UINT_MAX; + + clear_bit_le(slot, free); + + return slot; +} + +bool nd_label_free_slot(struct nvdimm_drvdata *ndd, u32 slot) +{ + struct nd_namespace_index *nsindex; + unsigned long *free; + u32 nslot; + + if (!preamble_next(ndd, &nsindex, &free, &nslot)) + return false; + + WARN_ON(!is_nvdimm_bus_locked(ndd->dev)); + + if (slot < nslot) + return !test_and_set_bit_le(slot, free); + return false; +} + +u32 nd_label_nfree(struct nvdimm_drvdata *ndd) +{ + struct nd_namespace_index *nsindex; + unsigned long *free; + u32 nslot; + + WARN_ON(!is_nvdimm_bus_locked(ndd->dev)); + + if (!preamble_next(ndd, &nsindex, &free, &nslot)) + return nvdimm_num_label_slots(ndd); + + return bitmap_weight(free, nslot); +} + +static int nd_label_write_index(struct nvdimm_drvdata *ndd, int index, u32 seq, + unsigned long flags) +{ + struct nd_namespace_index *nsindex; + unsigned long offset; + u64 checksum; + u32 nslot; + int rc; + + nsindex = to_namespace_index(ndd, index); + if (flags & ND_NSINDEX_INIT) + nslot = nvdimm_num_label_slots(ndd); + else + nslot = __le32_to_cpu(nsindex->nslot); + + memcpy(nsindex->sig, NSINDEX_SIGNATURE, NSINDEX_SIG_LEN); + nsindex->flags = __cpu_to_le32(0); + nsindex->seq = __cpu_to_le32(seq); + offset = (unsigned long) nsindex + - (unsigned long) to_namespace_index(ndd, 0); + nsindex->myoff = __cpu_to_le64(offset); + nsindex->mysize = __cpu_to_le64(sizeof_namespace_index(ndd)); + offset = (unsigned long) to_namespace_index(ndd, + nd_label_next_nsindex(index)) + - (unsigned long) to_namespace_index(ndd, 0); + nsindex->otheroff = __cpu_to_le64(offset); + offset = (unsigned long) nd_label_base(ndd) + - (unsigned long) to_namespace_index(ndd, 0); + nsindex->labeloff = __cpu_to_le64(offset); + nsindex->nslot = __cpu_to_le32(nslot); + nsindex->major = __cpu_to_le16(1); + nsindex->minor = __cpu_to_le16(1); + nsindex->checksum = __cpu_to_le64(0); + if (flags & ND_NSINDEX_INIT) { + unsigned long *free = (unsigned long *) nsindex->free; + u32 nfree = ALIGN(nslot, BITS_PER_LONG); + int last_bits, i; + + memset(nsindex->free, 0xff, nfree / 8); + for (i = 0, last_bits = nfree - nslot; i < last_bits; i++) + clear_bit_le(nslot + i, free); + } + checksum = nd_fletcher64(nsindex, sizeof_namespace_index(ndd), 1); + nsindex->checksum = __cpu_to_le64(checksum); + rc = nvdimm_set_config_data(ndd, __le64_to_cpu(nsindex->myoff), + nsindex, sizeof_namespace_index(ndd)); + if (rc < 0) + return rc; + + if (flags & ND_NSINDEX_INIT) + return 0; + + /* copy the index we just wrote to the new 'next' */ + WARN_ON(index != ndd->ns_next); + nd_label_copy(ndd, to_current_namespace_index(ndd), nsindex); + ndd->ns_current = nd_label_next_nsindex(ndd->ns_current); + ndd->ns_next = nd_label_next_nsindex(ndd->ns_next); + WARN_ON(ndd->ns_current == ndd->ns_next); + + return 0; +} + +static unsigned long nd_label_offset(struct nvdimm_drvdata *ndd, + struct nd_namespace_label *nd_label) +{ + return (unsigned long) nd_label + - (unsigned long) to_namespace_index(ndd, 0); +} + +static int __pmem_label_update(struct nd_region *nd_region, + struct nd_mapping *nd_mapping, struct nd_namespace_pmem *nspm, + int pos) +{ + u64 cookie = nd_region_interleave_set_cookie(nd_region), rawsize; + struct nvdimm_drvdata *ndd = to_ndd(nd_mapping); + struct nd_namespace_label *victim_label; + struct nd_namespace_label *nd_label; + struct nd_namespace_index *nsindex; + unsigned long *free; + u32 nslot, slot; + size_t offset; + int rc; + + if (!preamble_next(ndd, &nsindex, &free, &nslot)) + return -ENXIO; + + /* allocate and write the label to the staging (next) index */ + slot = nd_label_alloc_slot(ndd); + if (slot == UINT_MAX) + return -ENXIO; + dev_dbg(ndd->dev, "%s: allocated: %d\n", __func__, slot); + + nd_label = nd_label_base(ndd) + slot; + memset(nd_label, 0, sizeof(struct nd_namespace_label)); + memcpy(nd_label->uuid, nspm->uuid, NSLABEL_UUID_LEN); + if (nspm->alt_name) + memcpy(nd_label->name, nspm->alt_name, NSLABEL_NAME_LEN); + nd_label->flags = __cpu_to_le32(NSLABEL_FLAG_UPDATING); + nd_label->nlabel = __cpu_to_le16(nd_region->ndr_mappings); + nd_label->position = __cpu_to_le16(pos); + nd_label->isetcookie = __cpu_to_le64(cookie); + rawsize = div_u64(resource_size(&nspm->nsio.res), + nd_region->ndr_mappings); + nd_label->rawsize = __cpu_to_le64(rawsize); + nd_label->dpa = __cpu_to_le64(nd_mapping->start); + nd_label->slot = __cpu_to_le32(slot); + + /* update label */ + offset = nd_label_offset(ndd, nd_label); + rc = nvdimm_set_config_data(ndd, offset, nd_label, + sizeof(struct nd_namespace_label)); + if (rc < 0) + return rc; + + /* Garbage collect the previous label */ + victim_label = nd_mapping->labels[0]; + if (victim_label) { + slot = to_slot(ndd, victim_label); + nd_label_free_slot(ndd, slot); + dev_dbg(ndd->dev, "%s: free: %d\n", __func__, slot); + } + + /* update index */ + rc = nd_label_write_index(ndd, ndd->ns_next, + nd_inc_seq(__le32_to_cpu(nsindex->seq)), 0); + if (rc < 0) + return rc; + + nd_mapping->labels[0] = nd_label; + + return 0; +} + +static void del_label(struct nd_mapping *nd_mapping, int l) +{ + struct nd_namespace_label *next_label, *nd_label; + struct nvdimm_drvdata *ndd = to_ndd(nd_mapping); + unsigned int slot; + int j; + + nd_label = nd_mapping->labels[l]; + slot = to_slot(ndd, nd_label); + dev_vdbg(ndd->dev, "%s: clear: %d\n", __func__, slot); + + for (j = l; (next_label = nd_mapping->labels[j + 1]); j++) + nd_mapping->labels[j] = next_label; + nd_mapping->labels[j] = NULL; +} + +static bool is_old_resource(struct resource *res, struct resource **list, int n) +{ + int i; + + if (res->flags & DPA_RESOURCE_ADJUSTED) + return false; + for (i = 0; i < n; i++) + if (res == list[i]) + return true; + return false; +} + +static struct resource *to_resource(struct nvdimm_drvdata *ndd, + struct nd_namespace_label *nd_label) +{ + struct resource *res; + + for_each_dpa_resource(ndd, res) { + if (res->start != __le64_to_cpu(nd_label->dpa)) + continue; + if (resource_size(res) != __le64_to_cpu(nd_label->rawsize)) + continue; + return res; + } + + return NULL; +} + +/* + * 1/ Account all the labels that can be freed after this update + * 2/ Allocate and write the label to the staging (next) index + * 3/ Record the resources in the namespace device + */ +static int __blk_label_update(struct nd_region *nd_region, + struct nd_mapping *nd_mapping, struct nd_namespace_blk *nsblk, + int num_labels) +{ + int i, l, alloc, victims, nfree, old_num_resources, nlabel, rc = -ENXIO; + struct nvdimm_drvdata *ndd = to_ndd(nd_mapping); + struct nd_namespace_label *nd_label; + struct nd_namespace_index *nsindex; + unsigned long *free, *victim_map = NULL; + struct resource *res, **old_res_list; + struct nd_label_id label_id; + u8 uuid[NSLABEL_UUID_LEN]; + u32 nslot, slot; + + if (!preamble_next(ndd, &nsindex, &free, &nslot)) + return -ENXIO; + + old_res_list = nsblk->res; + nfree = nd_label_nfree(ndd); + old_num_resources = nsblk->num_resources; + nd_label_gen_id(&label_id, nsblk->uuid, NSLABEL_FLAG_LOCAL); + + /* + * We need to loop over the old resources a few times, which seems a + * bit inefficient, but we need to know that we have the label + * space before we start mutating the tracking structures. + * Otherwise the recovery method of last resort for userspace is + * disable and re-enable the parent region. + */ + alloc = 0; + for_each_dpa_resource(ndd, res) { + if (strcmp(res->name, label_id.id) != 0) + continue; + if (!is_old_resource(res, old_res_list, old_num_resources)) + alloc++; + } + + victims = 0; + if (old_num_resources) { + /* convert old local-label-map to dimm-slot victim-map */ + victim_map = kcalloc(BITS_TO_LONGS(nslot), sizeof(long), + GFP_KERNEL); + if (!victim_map) + return -ENOMEM; + + /* mark unused labels for garbage collection */ + for_each_clear_bit_le(slot, free, nslot) { + nd_label = nd_label_base(ndd) + slot; + memcpy(uuid, nd_label->uuid, NSLABEL_UUID_LEN); + if (memcmp(uuid, nsblk->uuid, NSLABEL_UUID_LEN) != 0) + continue; + res = to_resource(ndd, nd_label); + if (res && is_old_resource(res, old_res_list, + old_num_resources)) + continue; + slot = to_slot(ndd, nd_label); + set_bit(slot, victim_map); + victims++; + } + } + + /* don't allow updates that consume the last label */ + if (nfree - alloc < 0 || nfree - alloc + victims < 1) { + dev_info(&nsblk->dev, "insufficient label space\n"); + kfree(victim_map); + return -ENOSPC; + } + /* from here on we need to abort on error */ + + + /* assign all resources to the namespace before writing the labels */ + nsblk->res = NULL; + nsblk->num_resources = 0; + for_each_dpa_resource(ndd, res) { + if (strcmp(res->name, label_id.id) != 0) + continue; + if (!nsblk_add_resource(nd_region, ndd, nsblk, res->start)) { + rc = -ENOMEM; + goto abort; + } + } + + for (i = 0; i < nsblk->num_resources; i++) { + size_t offset; + + res = nsblk->res[i]; + if (is_old_resource(res, old_res_list, old_num_resources)) + continue; /* carry-over */ + slot = nd_label_alloc_slot(ndd); + if (slot == UINT_MAX) + goto abort; + dev_dbg(ndd->dev, "%s: allocated: %d\n", __func__, slot); + + nd_label = nd_label_base(ndd) + slot; + memset(nd_label, 0, sizeof(struct nd_namespace_label)); + memcpy(nd_label->uuid, nsblk->uuid, NSLABEL_UUID_LEN); + if (nsblk->alt_name) + memcpy(nd_label->name, nsblk->alt_name, + NSLABEL_NAME_LEN); + nd_label->flags = __cpu_to_le32(NSLABEL_FLAG_LOCAL); + nd_label->nlabel = __cpu_to_le16(0); /* N/A */ + nd_label->position = __cpu_to_le16(0); /* N/A */ + nd_label->isetcookie = __cpu_to_le64(0); /* N/A */ + nd_label->dpa = __cpu_to_le64(res->start); + nd_label->rawsize = __cpu_to_le64(resource_size(res)); + nd_label->lbasize = __cpu_to_le64(nsblk->lbasize); + nd_label->slot = __cpu_to_le32(slot); + + /* update label */ + offset = nd_label_offset(ndd, nd_label); + rc = nvdimm_set_config_data(ndd, offset, nd_label, + sizeof(struct nd_namespace_label)); + if (rc < 0) + goto abort; + } + + /* free up now unused slots in the new index */ + for_each_set_bit(slot, victim_map, victim_map ? nslot : 0) { + dev_dbg(ndd->dev, "%s: free: %d\n", __func__, slot); + nd_label_free_slot(ndd, slot); + } + + /* update index */ + rc = nd_label_write_index(ndd, ndd->ns_next, + nd_inc_seq(__le32_to_cpu(nsindex->seq)), 0); + if (rc) + goto abort; + + /* + * Now that the on-dimm labels are up to date, fix up the tracking + * entries in nd_mapping->labels + */ + nlabel = 0; + for_each_label(l, nd_label, nd_mapping->labels) { + nlabel++; + memcpy(uuid, nd_label->uuid, NSLABEL_UUID_LEN); + if (memcmp(uuid, nsblk->uuid, NSLABEL_UUID_LEN) != 0) + continue; + nlabel--; + del_label(nd_mapping, l); + l--; /* retry with the new label at this index */ + } + if (nlabel + nsblk->num_resources > num_labels) { + /* + * Bug, we can't end up with more resources than + * available labels + */ + WARN_ON_ONCE(1); + rc = -ENXIO; + goto out; + } + + for_each_clear_bit_le(slot, free, nslot) { + nd_label = nd_label_base(ndd) + slot; + memcpy(uuid, nd_label->uuid, NSLABEL_UUID_LEN); + if (memcmp(uuid, nsblk->uuid, NSLABEL_UUID_LEN) != 0) + continue; + res = to_resource(ndd, nd_label); + res->flags &= ~DPA_RESOURCE_ADJUSTED; + dev_vdbg(&nsblk->dev, "assign label[%d] slot: %d\n", l, slot); + nd_mapping->labels[l++] = nd_label; + } + nd_mapping->labels[l] = NULL; + + out: + kfree(old_res_list); + kfree(victim_map); + return rc; + + abort: + /* + * 1/ repair the allocated label bitmap in the index + * 2/ restore the resource list + */ + nd_label_copy(ndd, nsindex, to_current_namespace_index(ndd)); + kfree(nsblk->res); + nsblk->res = old_res_list; + nsblk->num_resources = old_num_resources; + old_res_list = NULL; + goto out; +} + +static int init_labels(struct nd_mapping *nd_mapping, int num_labels) +{ + int i, l, old_num_labels = 0; + struct nd_namespace_index *nsindex; + struct nd_namespace_label *nd_label; + struct nvdimm_drvdata *ndd = to_ndd(nd_mapping); + size_t size = (num_labels + 1) * sizeof(struct nd_namespace_label *); + + for_each_label(l, nd_label, nd_mapping->labels) + old_num_labels++; + + /* + * We need to preserve all the old labels for the mapping so + * they can be garbage collected after writing the new labels. + */ + if (num_labels > old_num_labels) { + struct nd_namespace_label **labels; + + labels = krealloc(nd_mapping->labels, size, GFP_KERNEL); + if (!labels) + return -ENOMEM; + nd_mapping->labels = labels; + } + if (!nd_mapping->labels) + return -ENOMEM; + + for (i = old_num_labels; i <= num_labels; i++) + nd_mapping->labels[i] = NULL; + + if (ndd->ns_current == -1 || ndd->ns_next == -1) + /* pass */; + else + return max(num_labels, old_num_labels); + + nsindex = to_namespace_index(ndd, 0); + memset(nsindex, 0, ndd->nsarea.config_size); + for (i = 0; i < 2; i++) { + int rc = nd_label_write_index(ndd, i, i*2, ND_NSINDEX_INIT); + + if (rc) + return rc; + } + ndd->ns_next = 1; + ndd->ns_current = 0; + + return max(num_labels, old_num_labels); +} + +static int del_labels(struct nd_mapping *nd_mapping, u8 *uuid) +{ + struct nvdimm_drvdata *ndd = to_ndd(nd_mapping); + struct nd_namespace_label *nd_label; + struct nd_namespace_index *nsindex; + u8 label_uuid[NSLABEL_UUID_LEN]; + int l, num_freed = 0; + unsigned long *free; + u32 nslot, slot; + + if (!uuid) + return 0; + + /* no index || no labels == nothing to delete */ + if (!preamble_next(ndd, &nsindex, &free, &nslot) + || !nd_mapping->labels) + return 0; + + for_each_label(l, nd_label, nd_mapping->labels) { + memcpy(label_uuid, nd_label->uuid, NSLABEL_UUID_LEN); + if (memcmp(label_uuid, uuid, NSLABEL_UUID_LEN) != 0) + continue; + slot = to_slot(ndd, nd_label); + nd_label_free_slot(ndd, slot); + dev_dbg(ndd->dev, "%s: free: %d\n", __func__, slot); + del_label(nd_mapping, l); + num_freed++; + l--; /* retry with new label at this index */ + } + + if (num_freed > l) { + /* + * num_freed will only ever be > l when we delete the last + * label + */ + kfree(nd_mapping->labels); + nd_mapping->labels = NULL; + dev_dbg(ndd->dev, "%s: no more labels\n", __func__); + } + + return nd_label_write_index(ndd, ndd->ns_next, + nd_inc_seq(__le32_to_cpu(nsindex->seq)), 0); +} + +int nd_pmem_namespace_label_update(struct nd_region *nd_region, + struct nd_namespace_pmem *nspm, resource_size_t size) +{ + int i; + + for (i = 0; i < nd_region->ndr_mappings; i++) { + struct nd_mapping *nd_mapping = &nd_region->mapping[i]; + int rc; + + if (size == 0) { + rc = del_labels(nd_mapping, nspm->uuid); + if (rc) + return rc; + continue; + } + + rc = init_labels(nd_mapping, 1); + if (rc < 0) + return rc; + + rc = __pmem_label_update(nd_region, nd_mapping, nspm, i); + if (rc) + return rc; + } + + return 0; +} + +int nd_blk_namespace_label_update(struct nd_region *nd_region, + struct nd_namespace_blk *nsblk, resource_size_t size) +{ + struct nd_mapping *nd_mapping = &nd_region->mapping[0]; + struct resource *res; + int count = 0; + + if (size == 0) + return del_labels(nd_mapping, nsblk->uuid); + + for_each_dpa_resource(to_ndd(nd_mapping), res) + count++; + + count = init_labels(nd_mapping, count); + if (count < 0) + return count; + + return __blk_label_update(nd_region, nd_mapping, nsblk, count); +} diff --git a/drivers/nvdimm/label.h b/drivers/nvdimm/label.h new file mode 100644 index 000000000000..a59ef6eef2a3 --- /dev/null +++ b/drivers/nvdimm/label.h @@ -0,0 +1,141 @@ +/* + * Copyright(c) 2013-2015 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 __LABEL_H__ +#define __LABEL_H__ + +#include <linux/ndctl.h> +#include <linux/sizes.h> +#include <linux/io.h> + +enum { + NSINDEX_SIG_LEN = 16, + NSINDEX_ALIGN = 256, + NSINDEX_SEQ_MASK = 0x3, + NSLABEL_UUID_LEN = 16, + NSLABEL_NAME_LEN = 64, + NSLABEL_FLAG_ROLABEL = 0x1, /* read-only label */ + NSLABEL_FLAG_LOCAL = 0x2, /* DIMM-local namespace */ + NSLABEL_FLAG_BTT = 0x4, /* namespace contains a BTT */ + NSLABEL_FLAG_UPDATING = 0x8, /* label being updated */ + BTT_ALIGN = 4096, /* all btt structures */ + BTTINFO_SIG_LEN = 16, + BTTINFO_UUID_LEN = 16, + BTTINFO_FLAG_ERROR = 0x1, /* error state (read-only) */ + BTTINFO_MAJOR_VERSION = 1, + ND_LABEL_MIN_SIZE = 512 * 129, /* see sizeof_namespace_index() */ + ND_LABEL_ID_SIZE = 50, + ND_NSINDEX_INIT = 0x1, +}; + +static const char NSINDEX_SIGNATURE[] = "NAMESPACE_INDEX\0"; + +/** + * struct nd_namespace_index - label set superblock + * @sig: NAMESPACE_INDEX\0 + * @flags: placeholder + * @seq: sequence number for this index + * @myoff: offset of this index in label area + * @mysize: size of this index struct + * @otheroff: offset of other index + * @labeloff: offset of first label slot + * @nslot: total number of label slots + * @major: label area major version + * @minor: label area minor version + * @checksum: fletcher64 of all fields + * @free[0]: bitmap, nlabel bits + * + * The size of free[] is rounded up so the total struct size is a + * multiple of NSINDEX_ALIGN bytes. Any bits this allocates beyond + * nlabel bits must be zero. + */ +struct nd_namespace_index { + u8 sig[NSINDEX_SIG_LEN]; + __le32 flags; + __le32 seq; + __le64 myoff; + __le64 mysize; + __le64 otheroff; + __le64 labeloff; + __le32 nslot; + __le16 major; + __le16 minor; + __le64 checksum; + u8 free[0]; +}; + +/** + * struct nd_namespace_label - namespace superblock + * @uuid: UUID per RFC 4122 + * @name: optional name (NULL-terminated) + * @flags: see NSLABEL_FLAG_* + * @nlabel: num labels to describe this ns + * @position: labels position in set + * @isetcookie: interleave set cookie + * @lbasize: LBA size in bytes or 0 for pmem + * @dpa: DPA of NVM range on this DIMM + * @rawsize: size of namespace + * @slot: slot of this label in label area + * @unused: must be zero + */ +struct nd_namespace_label { + u8 uuid[NSLABEL_UUID_LEN]; + u8 name[NSLABEL_NAME_LEN]; + __le32 flags; + __le16 nlabel; + __le16 position; + __le64 isetcookie; + __le64 lbasize; + __le64 dpa; + __le64 rawsize; + __le32 slot; + __le32 unused; +}; + +/** + * struct nd_label_id - identifier string for dpa allocation + * @id: "{blk|pmem}-<namespace uuid>" + */ +struct nd_label_id { + char id[ND_LABEL_ID_SIZE]; +}; + +/* + * If the 'best' index is invalid, so is the 'next' index. Otherwise, + * the next index is MOD(index+1, 2) + */ +static inline int nd_label_next_nsindex(int index) +{ + if (index < 0) + return -1; + + return (index + 1) % 2; +} + +struct nvdimm_drvdata; +int nd_label_validate(struct nvdimm_drvdata *ndd); +void nd_label_copy(struct nvdimm_drvdata *ndd, struct nd_namespace_index *dst, + struct nd_namespace_index *src); +size_t sizeof_namespace_index(struct nvdimm_drvdata *ndd); +int nd_label_active_count(struct nvdimm_drvdata *ndd); +struct nd_namespace_label *nd_label_active(struct nvdimm_drvdata *ndd, int n); +u32 nd_label_alloc_slot(struct nvdimm_drvdata *ndd); +bool nd_label_free_slot(struct nvdimm_drvdata *ndd, u32 slot); +u32 nd_label_nfree(struct nvdimm_drvdata *ndd); +struct nd_region; +struct nd_namespace_pmem; +struct nd_namespace_blk; +int nd_pmem_namespace_label_update(struct nd_region *nd_region, + struct nd_namespace_pmem *nspm, resource_size_t size); +int nd_blk_namespace_label_update(struct nd_region *nd_region, + struct nd_namespace_blk *nsblk, resource_size_t size); +#endif /* __LABEL_H__ */ diff --git a/drivers/nvdimm/namespace_devs.c b/drivers/nvdimm/namespace_devs.c new file mode 100644 index 000000000000..50b502b1908e --- /dev/null +++ b/drivers/nvdimm/namespace_devs.c @@ -0,0 +1,1645 @@ +/* + * Copyright(c) 2013-2015 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/module.h> +#include <linux/device.h> +#include <linux/slab.h> +#include <linux/nd.h> +#include "nd-core.h" +#include "nd.h" + +static void namespace_io_release(struct device *dev) +{ + struct nd_namespace_io *nsio = to_nd_namespace_io(dev); + + kfree(nsio); +} + +static void namespace_pmem_release(struct device *dev) +{ + struct nd_namespace_pmem *nspm = to_nd_namespace_pmem(dev); + + kfree(nspm->alt_name); + kfree(nspm->uuid); + kfree(nspm); +} + +static void namespace_blk_release(struct device *dev) +{ + struct nd_namespace_blk *nsblk = to_nd_namespace_blk(dev); + struct nd_region *nd_region = to_nd_region(dev->parent); + + if (nsblk->id >= 0) + ida_simple_remove(&nd_region->ns_ida, nsblk->id); + kfree(nsblk->alt_name); + kfree(nsblk->uuid); + kfree(nsblk->res); + kfree(nsblk); +} + +static struct device_type namespace_io_device_type = { + .name = "nd_namespace_io", + .release = namespace_io_release, +}; + +static struct device_type namespace_pmem_device_type = { + .name = "nd_namespace_pmem", + .release = namespace_pmem_release, +}; + +static struct device_type namespace_blk_device_type = { + .name = "nd_namespace_blk", + .release = namespace_blk_release, +}; + +static bool is_namespace_pmem(struct device *dev) +{ + return dev ? dev->type == &namespace_pmem_device_type : false; +} + +static bool is_namespace_blk(struct device *dev) +{ + return dev ? dev->type == &namespace_blk_device_type : false; +} + +static bool is_namespace_io(struct device *dev) +{ + return dev ? dev->type == &namespace_io_device_type : false; +} + +static ssize_t nstype_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + struct nd_region *nd_region = to_nd_region(dev->parent); + + return sprintf(buf, "%d\n", nd_region_to_nstype(nd_region)); +} +static DEVICE_ATTR_RO(nstype); + +static ssize_t __alt_name_store(struct device *dev, const char *buf, + const size_t len) +{ + char *input, *pos, *alt_name, **ns_altname; + ssize_t rc; + + if (is_namespace_pmem(dev)) { + struct nd_namespace_pmem *nspm = to_nd_namespace_pmem(dev); + + ns_altname = &nspm->alt_name; + } else if (is_namespace_blk(dev)) { + struct nd_namespace_blk *nsblk = to_nd_namespace_blk(dev); + + ns_altname = &nsblk->alt_name; + } else + return -ENXIO; + + if (dev->driver) + return -EBUSY; + + input = kmemdup(buf, len + 1, GFP_KERNEL); + if (!input) + return -ENOMEM; + + input[len] = '\0'; + pos = strim(input); + if (strlen(pos) + 1 > NSLABEL_NAME_LEN) { + rc = -EINVAL; + goto out; + } + + alt_name = kzalloc(NSLABEL_NAME_LEN, GFP_KERNEL); + if (!alt_name) { + rc = -ENOMEM; + goto out; + } + kfree(*ns_altname); + *ns_altname = alt_name; + sprintf(*ns_altname, "%s", pos); + rc = len; + +out: + kfree(input); + return rc; +} + +static resource_size_t nd_namespace_blk_size(struct nd_namespace_blk *nsblk) +{ + struct nd_region *nd_region = to_nd_region(nsblk->dev.parent); + struct nd_mapping *nd_mapping = &nd_region->mapping[0]; + struct nvdimm_drvdata *ndd = to_ndd(nd_mapping); + struct nd_label_id label_id; + resource_size_t size = 0; + struct resource *res; + + if (!nsblk->uuid) + return 0; + nd_label_gen_id(&label_id, nsblk->uuid, NSLABEL_FLAG_LOCAL); + for_each_dpa_resource(ndd, res) + if (strcmp(res->name, label_id.id) == 0) + size += resource_size(res); + return size; +} + +static int nd_namespace_label_update(struct nd_region *nd_region, + struct device *dev) +{ + dev_WARN_ONCE(dev, dev->driver, + "namespace must be idle during label update\n"); + if (dev->driver) + return 0; + + /* + * Only allow label writes that will result in a valid namespace + * or deletion of an existing namespace. + */ + if (is_namespace_pmem(dev)) { + struct nd_namespace_pmem *nspm = to_nd_namespace_pmem(dev); + resource_size_t size = resource_size(&nspm->nsio.res); + + if (size == 0 && nspm->uuid) + /* delete allocation */; + else if (!nspm->uuid) + return 0; + + return nd_pmem_namespace_label_update(nd_region, nspm, size); + } else if (is_namespace_blk(dev)) { + struct nd_namespace_blk *nsblk = to_nd_namespace_blk(dev); + resource_size_t size = nd_namespace_blk_size(nsblk); + + if (size == 0 && nsblk->uuid) + /* delete allocation */; + else if (!nsblk->uuid || !nsblk->lbasize) + return 0; + + return nd_blk_namespace_label_update(nd_region, nsblk, size); + } else + return -ENXIO; +} + +static ssize_t alt_name_store(struct device *dev, + struct device_attribute *attr, const char *buf, size_t len) +{ + struct nd_region *nd_region = to_nd_region(dev->parent); + ssize_t rc; + + device_lock(dev); + nvdimm_bus_lock(dev); + wait_nvdimm_bus_probe_idle(dev); + rc = __alt_name_store(dev, buf, len); + if (rc >= 0) + rc = nd_namespace_label_update(nd_region, dev); + dev_dbg(dev, "%s: %s(%zd)\n", __func__, rc < 0 ? "fail " : "", rc); + nvdimm_bus_unlock(dev); + device_unlock(dev); + + return rc < 0 ? rc : len; +} + +static ssize_t alt_name_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + char *ns_altname; + + if (is_namespace_pmem(dev)) { + struct nd_namespace_pmem *nspm = to_nd_namespace_pmem(dev); + + ns_altname = nspm->alt_name; + } else if (is_namespace_blk(dev)) { + struct nd_namespace_blk *nsblk = to_nd_namespace_blk(dev); + + ns_altname = nsblk->alt_name; + } else + return -ENXIO; + + return sprintf(buf, "%s\n", ns_altname ? ns_altname : ""); +} +static DEVICE_ATTR_RW(alt_name); + +static int scan_free(struct nd_region *nd_region, + struct nd_mapping *nd_mapping, struct nd_label_id *label_id, + resource_size_t n) +{ + bool is_blk = strncmp(label_id->id, "blk", 3) == 0; + struct nvdimm_drvdata *ndd = to_ndd(nd_mapping); + int rc = 0; + + while (n) { + struct resource *res, *last; + resource_size_t new_start; + + last = NULL; + for_each_dpa_resource(ndd, res) + if (strcmp(res->name, label_id->id) == 0) + last = res; + res = last; + if (!res) + return 0; + + if (n >= resource_size(res)) { + n -= resource_size(res); + nd_dbg_dpa(nd_region, ndd, res, "delete %d\n", rc); + nvdimm_free_dpa(ndd, res); + /* retry with last resource deleted */ + continue; + } + + /* + * Keep BLK allocations relegated to high DPA as much as + * possible + */ + if (is_blk) + new_start = res->start + n; + else + new_start = res->start; + + rc = adjust_resource(res, new_start, resource_size(res) - n); + if (rc == 0) + res->flags |= DPA_RESOURCE_ADJUSTED; + nd_dbg_dpa(nd_region, ndd, res, "shrink %d\n", rc); + break; + } + + return rc; +} + +/** + * shrink_dpa_allocation - for each dimm in region free n bytes for label_id + * @nd_region: the set of dimms to reclaim @n bytes from + * @label_id: unique identifier for the namespace consuming this dpa range + * @n: number of bytes per-dimm to release + * + * Assumes resources are ordered. Starting from the end try to + * adjust_resource() the allocation to @n, but if @n is larger than the + * allocation delete it and find the 'new' last allocation in the label + * set. + */ +static int shrink_dpa_allocation(struct nd_region *nd_region, + struct nd_label_id *label_id, resource_size_t n) +{ + int i; + + for (i = 0; i < nd_region->ndr_mappings; i++) { + struct nd_mapping *nd_mapping = &nd_region->mapping[i]; + int rc; + + rc = scan_free(nd_region, nd_mapping, label_id, n); + if (rc) + return rc; + } + + return 0; +} + +static resource_size_t init_dpa_allocation(struct nd_label_id *label_id, + struct nd_region *nd_region, struct nd_mapping *nd_mapping, + resource_size_t n) +{ + bool is_blk = strncmp(label_id->id, "blk", 3) == 0; + struct nvdimm_drvdata *ndd = to_ndd(nd_mapping); + resource_size_t first_dpa; + struct resource *res; + int rc = 0; + + /* allocate blk from highest dpa first */ + if (is_blk) + first_dpa = nd_mapping->start + nd_mapping->size - n; + else + first_dpa = nd_mapping->start; + + /* first resource allocation for this label-id or dimm */ + res = nvdimm_allocate_dpa(ndd, label_id, first_dpa, n); + if (!res) + rc = -EBUSY; + + nd_dbg_dpa(nd_region, ndd, res, "init %d\n", rc); + return rc ? n : 0; +} + +static bool space_valid(bool is_pmem, bool is_reserve, + struct nd_label_id *label_id, struct resource *res) +{ + /* + * For BLK-space any space is valid, for PMEM-space, it must be + * contiguous with an existing allocation unless we are + * reserving pmem. + */ + if (is_reserve || !is_pmem) + return true; + if (!res || strcmp(res->name, label_id->id) == 0) + return true; + return false; +} + +enum alloc_loc { + ALLOC_ERR = 0, ALLOC_BEFORE, ALLOC_MID, ALLOC_AFTER, +}; + +static resource_size_t scan_allocate(struct nd_region *nd_region, + struct nd_mapping *nd_mapping, struct nd_label_id *label_id, + resource_size_t n) +{ + resource_size_t mapping_end = nd_mapping->start + nd_mapping->size - 1; + bool is_reserve = strcmp(label_id->id, "pmem-reserve") == 0; + bool is_pmem = strncmp(label_id->id, "pmem", 4) == 0; + struct nvdimm_drvdata *ndd = to_ndd(nd_mapping); + const resource_size_t to_allocate = n; + struct resource *res; + int first; + + retry: + first = 0; + for_each_dpa_resource(ndd, res) { + resource_size_t allocate, available = 0, free_start, free_end; + struct resource *next = res->sibling, *new_res = NULL; + enum alloc_loc loc = ALLOC_ERR; + const char *action; + int rc = 0; + + /* ignore resources outside this nd_mapping */ + if (res->start > mapping_end) + continue; + if (res->end < nd_mapping->start) + continue; + + /* space at the beginning of the mapping */ + if (!first++ && res->start > nd_mapping->start) { + free_start = nd_mapping->start; + available = res->start - free_start; + if (space_valid(is_pmem, is_reserve, label_id, NULL)) + loc = ALLOC_BEFORE; + } + + /* space between allocations */ + if (!loc && next) { + free_start = res->start + resource_size(res); + free_end = min(mapping_end, next->start - 1); + if (space_valid(is_pmem, is_reserve, label_id, res) + && free_start < free_end) { + available = free_end + 1 - free_start; + loc = ALLOC_MID; + } + } + + /* space at the end of the mapping */ + if (!loc && !next) { + free_start = res->start + resource_size(res); + free_end = mapping_end; + if (space_valid(is_pmem, is_reserve, label_id, res) + && free_start < free_end) { + available = free_end + 1 - free_start; + loc = ALLOC_AFTER; + } + } + + if (!loc || !available) + continue; + allocate = min(available, n); + switch (loc) { + case ALLOC_BEFORE: + if (strcmp(res->name, label_id->id) == 0) { + /* adjust current resource up */ + if (is_pmem && !is_reserve) + return n; + rc = adjust_resource(res, res->start - allocate, + resource_size(res) + allocate); + action = "cur grow up"; + } else + action = "allocate"; + break; + case ALLOC_MID: + if (strcmp(next->name, label_id->id) == 0) { + /* adjust next resource up */ + if (is_pmem && !is_reserve) + return n; + rc = adjust_resource(next, next->start + - allocate, resource_size(next) + + allocate); + new_res = next; + action = "next grow up"; + } else if (strcmp(res->name, label_id->id) == 0) { + action = "grow down"; + } else + action = "allocate"; + break; + case ALLOC_AFTER: + if (strcmp(res->name, label_id->id) == 0) + action = "grow down"; + else + action = "allocate"; + break; + default: + return n; + } + + if (strcmp(action, "allocate") == 0) { + /* BLK allocate bottom up */ + if (!is_pmem) + free_start += available - allocate; + else if (!is_reserve && free_start != nd_mapping->start) + return n; + + new_res = nvdimm_allocate_dpa(ndd, label_id, + free_start, allocate); + if (!new_res) + rc = -EBUSY; + } else if (strcmp(action, "grow down") == 0) { + /* adjust current resource down */ + rc = adjust_resource(res, res->start, resource_size(res) + + allocate); + if (rc == 0) + res->flags |= DPA_RESOURCE_ADJUSTED; + } + + if (!new_res) + new_res = res; + + nd_dbg_dpa(nd_region, ndd, new_res, "%s(%d) %d\n", + action, loc, rc); + + if (rc) + return n; + + n -= allocate; + if (n) { + /* + * Retry scan with newly inserted resources. + * For example, if we did an ALLOC_BEFORE + * insertion there may also have been space + * available for an ALLOC_AFTER insertion, so we + * need to check this same resource again + */ + goto retry; + } else + return 0; + } + + /* + * If we allocated nothing in the BLK case it may be because we are in + * an initial "pmem-reserve pass". Only do an initial BLK allocation + * when none of the DPA space is reserved. + */ + if ((is_pmem || !ndd->dpa.child) && n == to_allocate) + return init_dpa_allocation(label_id, nd_region, nd_mapping, n); + return n; +} + +static int merge_dpa(struct nd_region *nd_region, + struct nd_mapping *nd_mapping, struct nd_label_id *label_id) +{ + struct nvdimm_drvdata *ndd = to_ndd(nd_mapping); + struct resource *res; + + if (strncmp("pmem", label_id->id, 4) == 0) + return 0; + retry: + for_each_dpa_resource(ndd, res) { + int rc; + struct resource *next = res->sibling; + resource_size_t end = res->start + resource_size(res); + + if (!next || strcmp(res->name, label_id->id) != 0 + || strcmp(next->name, label_id->id) != 0 + || end != next->start) + continue; + end += resource_size(next); + nvdimm_free_dpa(ndd, next); + rc = adjust_resource(res, res->start, end - res->start); + nd_dbg_dpa(nd_region, ndd, res, "merge %d\n", rc); + if (rc) + return rc; + res->flags |= DPA_RESOURCE_ADJUSTED; + goto retry; + } + + return 0; +} + +static int __reserve_free_pmem(struct device *dev, void *data) +{ + struct nvdimm *nvdimm = data; + struct nd_region *nd_region; + struct nd_label_id label_id; + int i; + + if (!is_nd_pmem(dev)) + return 0; + + nd_region = to_nd_region(dev); + if (nd_region->ndr_mappings == 0) + return 0; + + memset(&label_id, 0, sizeof(label_id)); + strcat(label_id.id, "pmem-reserve"); + for (i = 0; i < nd_region->ndr_mappings; i++) { + struct nd_mapping *nd_mapping = &nd_region->mapping[i]; + resource_size_t n, rem = 0; + + if (nd_mapping->nvdimm != nvdimm) + continue; + + n = nd_pmem_available_dpa(nd_region, nd_mapping, &rem); + if (n == 0) + return 0; + rem = scan_allocate(nd_region, nd_mapping, &label_id, n); + dev_WARN_ONCE(&nd_region->dev, rem, + "pmem reserve underrun: %#llx of %#llx bytes\n", + (unsigned long long) n - rem, + (unsigned long long) n); + return rem ? -ENXIO : 0; + } + + return 0; +} + +static void release_free_pmem(struct nvdimm_bus *nvdimm_bus, + struct nd_mapping *nd_mapping) +{ + struct nvdimm_drvdata *ndd = to_ndd(nd_mapping); + struct resource *res, *_res; + + for_each_dpa_resource_safe(ndd, res, _res) + if (strcmp(res->name, "pmem-reserve") == 0) + nvdimm_free_dpa(ndd, res); +} + +static int reserve_free_pmem(struct nvdimm_bus *nvdimm_bus, + struct nd_mapping *nd_mapping) +{ + struct nvdimm *nvdimm = nd_mapping->nvdimm; + int rc; + + rc = device_for_each_child(&nvdimm_bus->dev, nvdimm, + __reserve_free_pmem); + if (rc) + release_free_pmem(nvdimm_bus, nd_mapping); + return rc; +} + +/** + * grow_dpa_allocation - for each dimm allocate n bytes for @label_id + * @nd_region: the set of dimms to allocate @n more bytes from + * @label_id: unique identifier for the namespace consuming this dpa range + * @n: number of bytes per-dimm to add to the existing allocation + * + * Assumes resources are ordered. For BLK regions, first consume + * BLK-only available DPA free space, then consume PMEM-aliased DPA + * space starting at the highest DPA. For PMEM regions start + * allocations from the start of an interleave set and end at the first + * BLK allocation or the end of the interleave set, whichever comes + * first. + */ +static int grow_dpa_allocation(struct nd_region *nd_region, + struct nd_label_id *label_id, resource_size_t n) +{ + struct nvdimm_bus *nvdimm_bus = walk_to_nvdimm_bus(&nd_region->dev); + bool is_pmem = strncmp(label_id->id, "pmem", 4) == 0; + int i; + + for (i = 0; i < nd_region->ndr_mappings; i++) { + struct nd_mapping *nd_mapping = &nd_region->mapping[i]; + resource_size_t rem = n; + int rc, j; + + /* + * In the BLK case try once with all unallocated PMEM + * reserved, and once without + */ + for (j = is_pmem; j < 2; j++) { + bool blk_only = j == 0; + + if (blk_only) { + rc = reserve_free_pmem(nvdimm_bus, nd_mapping); + if (rc) + return rc; + } + rem = scan_allocate(nd_region, nd_mapping, + label_id, rem); + if (blk_only) + release_free_pmem(nvdimm_bus, nd_mapping); + + /* try again and allow encroachments into PMEM */ + if (rem == 0) + break; + } + + dev_WARN_ONCE(&nd_region->dev, rem, + "allocation underrun: %#llx of %#llx bytes\n", + (unsigned long long) n - rem, + (unsigned long long) n); + if (rem) + return -ENXIO; + + rc = merge_dpa(nd_region, nd_mapping, label_id); + if (rc) + return rc; + } + + return 0; +} + +static void nd_namespace_pmem_set_size(struct nd_region *nd_region, + struct nd_namespace_pmem *nspm, resource_size_t size) +{ + struct resource *res = &nspm->nsio.res; + + res->start = nd_region->ndr_start; + res->end = nd_region->ndr_start + size - 1; +} + +static ssize_t __size_store(struct device *dev, unsigned long long val) +{ + resource_size_t allocated = 0, available = 0; + struct nd_region *nd_region = to_nd_region(dev->parent); + struct nd_mapping *nd_mapping; + struct nvdimm_drvdata *ndd; + struct nd_label_id label_id; + u32 flags = 0, remainder; + u8 *uuid = NULL; + int rc, i; + + if (dev->driver) + return -EBUSY; + + if (is_namespace_pmem(dev)) { + struct nd_namespace_pmem *nspm = to_nd_namespace_pmem(dev); + + uuid = nspm->uuid; + } else if (is_namespace_blk(dev)) { + struct nd_namespace_blk *nsblk = to_nd_namespace_blk(dev); + + uuid = nsblk->uuid; + flags = NSLABEL_FLAG_LOCAL; + } + + /* + * We need a uuid for the allocation-label and dimm(s) on which + * to store the label. + */ + if (!uuid || nd_region->ndr_mappings == 0) + return -ENXIO; + + div_u64_rem(val, SZ_4K * nd_region->ndr_mappings, &remainder); + if (remainder) { + dev_dbg(dev, "%llu is not %dK aligned\n", val, + (SZ_4K * nd_region->ndr_mappings) / SZ_1K); + return -EINVAL; + } + + nd_label_gen_id(&label_id, uuid, flags); + for (i = 0; i < nd_region->ndr_mappings; i++) { + nd_mapping = &nd_region->mapping[i]; + ndd = to_ndd(nd_mapping); + + /* + * All dimms in an interleave set, or the base dimm for a blk + * region, need to be enabled for the size to be changed. + */ + if (!ndd) + return -ENXIO; + + allocated += nvdimm_allocated_dpa(ndd, &label_id); + } + available = nd_region_available_dpa(nd_region); + + if (val > available + allocated) + return -ENOSPC; + + if (val == allocated) + return 0; + + val = div_u64(val, nd_region->ndr_mappings); + allocated = div_u64(allocated, nd_region->ndr_mappings); + if (val < allocated) + rc = shrink_dpa_allocation(nd_region, &label_id, + allocated - val); + else + rc = grow_dpa_allocation(nd_region, &label_id, val - allocated); + + if (rc) + return rc; + + if (is_namespace_pmem(dev)) { + struct nd_namespace_pmem *nspm = to_nd_namespace_pmem(dev); + + nd_namespace_pmem_set_size(nd_region, nspm, + val * nd_region->ndr_mappings); + } else if (is_namespace_blk(dev)) { + /* + * Try to delete the namespace if we deleted all of its + * allocation and this is not the seed device for the + * region. + */ + if (val == 0 && nd_region->ns_seed != dev) + nd_device_unregister(dev, ND_ASYNC); + } + + return rc; +} + +static ssize_t size_store(struct device *dev, + struct device_attribute *attr, const char *buf, size_t len) +{ + struct nd_region *nd_region = to_nd_region(dev->parent); + unsigned long long val; + u8 **uuid = NULL; + int rc; + + rc = kstrtoull(buf, 0, &val); + if (rc) + return rc; + + device_lock(dev); + nvdimm_bus_lock(dev); + wait_nvdimm_bus_probe_idle(dev); + rc = __size_store(dev, val); + if (rc >= 0) + rc = nd_namespace_label_update(nd_region, dev); + + if (is_namespace_pmem(dev)) { + struct nd_namespace_pmem *nspm = to_nd_namespace_pmem(dev); + + uuid = &nspm->uuid; + } else if (is_namespace_blk(dev)) { + struct nd_namespace_blk *nsblk = to_nd_namespace_blk(dev); + + uuid = &nsblk->uuid; + } + + if (rc == 0 && val == 0 && uuid) { + /* setting size zero == 'delete namespace' */ + kfree(*uuid); + *uuid = NULL; + } + + dev_dbg(dev, "%s: %llx %s (%d)\n", __func__, val, rc < 0 + ? "fail" : "success", rc); + + nvdimm_bus_unlock(dev); + device_unlock(dev); + + return rc < 0 ? rc : len; +} + +static ssize_t size_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + unsigned long long size = 0; + + nvdimm_bus_lock(dev); + if (is_namespace_pmem(dev)) { + struct nd_namespace_pmem *nspm = to_nd_namespace_pmem(dev); + + size = resource_size(&nspm->nsio.res); + } else if (is_namespace_blk(dev)) { + size = nd_namespace_blk_size(to_nd_namespace_blk(dev)); + } else if (is_namespace_io(dev)) { + struct nd_namespace_io *nsio = to_nd_namespace_io(dev); + + size = resource_size(&nsio->res); + } + nvdimm_bus_unlock(dev); + + return sprintf(buf, "%llu\n", size); +} +static DEVICE_ATTR(size, S_IRUGO, size_show, size_store); + +static ssize_t uuid_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + u8 *uuid; + + if (is_namespace_pmem(dev)) { + struct nd_namespace_pmem *nspm = to_nd_namespace_pmem(dev); + + uuid = nspm->uuid; + } else if (is_namespace_blk(dev)) { + struct nd_namespace_blk *nsblk = to_nd_namespace_blk(dev); + + uuid = nsblk->uuid; + } else + return -ENXIO; + + if (uuid) + return sprintf(buf, "%pUb\n", uuid); + return sprintf(buf, "\n"); +} + +/** + * namespace_update_uuid - check for a unique uuid and whether we're "renaming" + * @nd_region: parent region so we can updates all dimms in the set + * @dev: namespace type for generating label_id + * @new_uuid: incoming uuid + * @old_uuid: reference to the uuid storage location in the namespace object + */ +static int namespace_update_uuid(struct nd_region *nd_region, + struct device *dev, u8 *new_uuid, u8 **old_uuid) +{ + u32 flags = is_namespace_blk(dev) ? NSLABEL_FLAG_LOCAL : 0; + struct nd_label_id old_label_id; + struct nd_label_id new_label_id; + int i; + + if (!nd_is_uuid_unique(dev, new_uuid)) + return -EINVAL; + + if (*old_uuid == NULL) + goto out; + + /* + * If we've already written a label with this uuid, then it's + * too late to rename because we can't reliably update the uuid + * without losing the old namespace. Userspace must delete this + * namespace to abandon the old uuid. + */ + for (i = 0; i < nd_region->ndr_mappings; i++) { + struct nd_mapping *nd_mapping = &nd_region->mapping[i]; + + /* + * This check by itself is sufficient because old_uuid + * would be NULL above if this uuid did not exist in the + * currently written set. + * + * FIXME: can we delete uuid with zero dpa allocated? + */ + if (nd_mapping->labels) + return -EBUSY; + } + + nd_label_gen_id(&old_label_id, *old_uuid, flags); + nd_label_gen_id(&new_label_id, new_uuid, flags); + for (i = 0; i < nd_region->ndr_mappings; i++) { + struct nd_mapping *nd_mapping = &nd_region->mapping[i]; + struct nvdimm_drvdata *ndd = to_ndd(nd_mapping); + struct resource *res; + + for_each_dpa_resource(ndd, res) + if (strcmp(res->name, old_label_id.id) == 0) + sprintf((void *) res->name, "%s", + new_label_id.id); + } + kfree(*old_uuid); + out: + *old_uuid = new_uuid; + return 0; +} + +static ssize_t uuid_store(struct device *dev, + struct device_attribute *attr, const char *buf, size_t len) +{ + struct nd_region *nd_region = to_nd_region(dev->parent); + u8 *uuid = NULL; + u8 **ns_uuid; + ssize_t rc; + + if (is_namespace_pmem(dev)) { + struct nd_namespace_pmem *nspm = to_nd_namespace_pmem(dev); + + ns_uuid = &nspm->uuid; + } else if (is_namespace_blk(dev)) { + struct nd_namespace_blk *nsblk = to_nd_namespace_blk(dev); + + ns_uuid = &nsblk->uuid; + } else + return -ENXIO; + + device_lock(dev); + nvdimm_bus_lock(dev); + wait_nvdimm_bus_probe_idle(dev); + rc = nd_uuid_store(dev, &uuid, buf, len); + if (rc >= 0) + rc = namespace_update_uuid(nd_region, dev, uuid, ns_uuid); + if (rc >= 0) + rc = nd_namespace_label_update(nd_region, dev); + else + kfree(uuid); + dev_dbg(dev, "%s: result: %zd wrote: %s%s", __func__, + rc, buf, buf[len - 1] == '\n' ? "" : "\n"); + nvdimm_bus_unlock(dev); + device_unlock(dev); + + return rc < 0 ? rc : len; +} +static DEVICE_ATTR_RW(uuid); + +static ssize_t resource_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + struct resource *res; + + if (is_namespace_pmem(dev)) { + struct nd_namespace_pmem *nspm = to_nd_namespace_pmem(dev); + + res = &nspm->nsio.res; + } else if (is_namespace_io(dev)) { + struct nd_namespace_io *nsio = to_nd_namespace_io(dev); + + res = &nsio->res; + } else + return -ENXIO; + + /* no address to convey if the namespace has no allocation */ + if (resource_size(res) == 0) + return -ENXIO; + return sprintf(buf, "%#llx\n", (unsigned long long) res->start); +} +static DEVICE_ATTR_RO(resource); + +static const unsigned long ns_lbasize_supported[] = { 512, 0 }; + +static ssize_t sector_size_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + struct nd_namespace_blk *nsblk = to_nd_namespace_blk(dev); + + if (!is_namespace_blk(dev)) + return -ENXIO; + + return nd_sector_size_show(nsblk->lbasize, ns_lbasize_supported, buf); +} + +static ssize_t sector_size_store(struct device *dev, + struct device_attribute *attr, const char *buf, size_t len) +{ + struct nd_namespace_blk *nsblk = to_nd_namespace_blk(dev); + struct nd_region *nd_region = to_nd_region(dev->parent); + ssize_t rc; + + if (!is_namespace_blk(dev)) + return -ENXIO; + + device_lock(dev); + nvdimm_bus_lock(dev); + rc = nd_sector_size_store(dev, buf, &nsblk->lbasize, + ns_lbasize_supported); + if (rc >= 0) + rc = nd_namespace_label_update(nd_region, dev); + dev_dbg(dev, "%s: result: %zd %s: %s%s", __func__, + rc, rc < 0 ? "tried" : "wrote", buf, + buf[len - 1] == '\n' ? "" : "\n"); + nvdimm_bus_unlock(dev); + device_unlock(dev); + + return rc ? rc : len; +} +static DEVICE_ATTR_RW(sector_size); + +static ssize_t dpa_extents_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + struct nd_region *nd_region = to_nd_region(dev->parent); + struct nd_label_id label_id; + int count = 0, i; + u8 *uuid = NULL; + u32 flags = 0; + + nvdimm_bus_lock(dev); + if (is_namespace_pmem(dev)) { + struct nd_namespace_pmem *nspm = to_nd_namespace_pmem(dev); + + uuid = nspm->uuid; + flags = 0; + } else if (is_namespace_blk(dev)) { + struct nd_namespace_blk *nsblk = to_nd_namespace_blk(dev); + + uuid = nsblk->uuid; + flags = NSLABEL_FLAG_LOCAL; + } + + if (!uuid) + goto out; + + nd_label_gen_id(&label_id, uuid, flags); + for (i = 0; i < nd_region->ndr_mappings; i++) { + struct nd_mapping *nd_mapping = &nd_region->mapping[i]; + struct nvdimm_drvdata *ndd = to_ndd(nd_mapping); + struct resource *res; + + for_each_dpa_resource(ndd, res) + if (strcmp(res->name, label_id.id) == 0) + count++; + } + out: + nvdimm_bus_unlock(dev); + + return sprintf(buf, "%d\n", count); +} +static DEVICE_ATTR_RO(dpa_extents); + +static struct attribute *nd_namespace_attributes[] = { + &dev_attr_nstype.attr, + &dev_attr_size.attr, + &dev_attr_uuid.attr, + &dev_attr_resource.attr, + &dev_attr_alt_name.attr, + &dev_attr_sector_size.attr, + &dev_attr_dpa_extents.attr, + NULL, +}; + +static umode_t namespace_visible(struct kobject *kobj, + struct attribute *a, int n) +{ + struct device *dev = container_of(kobj, struct device, kobj); + + if (a == &dev_attr_resource.attr) { + if (is_namespace_blk(dev)) + return 0; + return a->mode; + } + + if (is_namespace_pmem(dev) || is_namespace_blk(dev)) { + if (a == &dev_attr_size.attr) + return S_IWUSR | S_IRUGO; + + if (is_namespace_pmem(dev) && a == &dev_attr_sector_size.attr) + return 0; + + return a->mode; + } + + if (a == &dev_attr_nstype.attr || a == &dev_attr_size.attr) + return a->mode; + + return 0; +} + +static struct attribute_group nd_namespace_attribute_group = { + .attrs = nd_namespace_attributes, + .is_visible = namespace_visible, +}; + +static const struct attribute_group *nd_namespace_attribute_groups[] = { + &nd_device_attribute_group, + &nd_namespace_attribute_group, + NULL, +}; + +static struct device **create_namespace_io(struct nd_region *nd_region) +{ + struct nd_namespace_io *nsio; + struct device *dev, **devs; + struct resource *res; + + nsio = kzalloc(sizeof(*nsio), GFP_KERNEL); + if (!nsio) + return NULL; + + devs = kcalloc(2, sizeof(struct device *), GFP_KERNEL); + if (!devs) { + kfree(nsio); + return NULL; + } + + dev = &nsio->dev; + dev->type = &namespace_io_device_type; + dev->parent = &nd_region->dev; + res = &nsio->res; + res->name = dev_name(&nd_region->dev); + res->flags = IORESOURCE_MEM; + res->start = nd_region->ndr_start; + res->end = res->start + nd_region->ndr_size - 1; + + devs[0] = dev; + return devs; +} + +static bool has_uuid_at_pos(struct nd_region *nd_region, u8 *uuid, + u64 cookie, u16 pos) +{ + struct nd_namespace_label *found = NULL; + int i; + + for (i = 0; i < nd_region->ndr_mappings; i++) { + struct nd_mapping *nd_mapping = &nd_region->mapping[i]; + struct nd_namespace_label *nd_label; + bool found_uuid = false; + int l; + + for_each_label(l, nd_label, nd_mapping->labels) { + u64 isetcookie = __le64_to_cpu(nd_label->isetcookie); + u16 position = __le16_to_cpu(nd_label->position); + u16 nlabel = __le16_to_cpu(nd_label->nlabel); + + if (isetcookie != cookie) + continue; + + if (memcmp(nd_label->uuid, uuid, NSLABEL_UUID_LEN) != 0) + continue; + + if (found_uuid) { + dev_dbg(to_ndd(nd_mapping)->dev, + "%s duplicate entry for uuid\n", + __func__); + return false; + } + found_uuid = true; + if (nlabel != nd_region->ndr_mappings) + continue; + if (position != pos) + continue; + found = nd_label; + break; + } + if (found) + break; + } + return found != NULL; +} + +static int select_pmem_id(struct nd_region *nd_region, u8 *pmem_id) +{ + struct nd_namespace_label *select = NULL; + int i; + + if (!pmem_id) + return -ENODEV; + + for (i = 0; i < nd_region->ndr_mappings; i++) { + struct nd_mapping *nd_mapping = &nd_region->mapping[i]; + struct nd_namespace_label *nd_label; + u64 hw_start, hw_end, pmem_start, pmem_end; + int l; + + for_each_label(l, nd_label, nd_mapping->labels) + if (memcmp(nd_label->uuid, pmem_id, NSLABEL_UUID_LEN) == 0) + break; + + if (!nd_label) { + WARN_ON(1); + return -EINVAL; + } + + select = nd_label; + /* + * Check that this label is compliant with the dpa + * range published in NFIT + */ + hw_start = nd_mapping->start; + hw_end = hw_start + nd_mapping->size; + pmem_start = __le64_to_cpu(select->dpa); + pmem_end = pmem_start + __le64_to_cpu(select->rawsize); + if (pmem_start == hw_start && pmem_end <= hw_end) + /* pass */; + else + return -EINVAL; + + nd_mapping->labels[0] = select; + nd_mapping->labels[1] = NULL; + } + return 0; +} + +/** + * find_pmem_label_set - validate interleave set labelling, retrieve label0 + * @nd_region: region with mappings to validate + */ +static int find_pmem_label_set(struct nd_region *nd_region, + struct nd_namespace_pmem *nspm) +{ + u64 cookie = nd_region_interleave_set_cookie(nd_region); + struct nd_namespace_label *nd_label; + u8 select_id[NSLABEL_UUID_LEN]; + resource_size_t size = 0; + u8 *pmem_id = NULL; + int rc = -ENODEV, l; + u16 i; + + if (cookie == 0) + return -ENXIO; + + /* + * Find a complete set of labels by uuid. By definition we can start + * with any mapping as the reference label + */ + for_each_label(l, nd_label, nd_region->mapping[0].labels) { + u64 isetcookie = __le64_to_cpu(nd_label->isetcookie); + + if (isetcookie != cookie) + continue; + + for (i = 0; nd_region->ndr_mappings; i++) + if (!has_uuid_at_pos(nd_region, nd_label->uuid, + cookie, i)) + break; + if (i < nd_region->ndr_mappings) { + /* + * Give up if we don't find an instance of a + * uuid at each position (from 0 to + * nd_region->ndr_mappings - 1), or if we find a + * dimm with two instances of the same uuid. + */ + rc = -EINVAL; + goto err; + } else if (pmem_id) { + /* + * If there is more than one valid uuid set, we + * need userspace to clean this up. + */ + rc = -EBUSY; + goto err; + } + memcpy(select_id, nd_label->uuid, NSLABEL_UUID_LEN); + pmem_id = select_id; + } + + /* + * Fix up each mapping's 'labels' to have the validated pmem label for + * that position at labels[0], and NULL at labels[1]. In the process, + * check that the namespace aligns with interleave-set. We know + * that it does not overlap with any blk namespaces by virtue of + * the dimm being enabled (i.e. nd_label_reserve_dpa() + * succeeded). + */ + rc = select_pmem_id(nd_region, pmem_id); + if (rc) + goto err; + + /* Calculate total size and populate namespace properties from label0 */ + for (i = 0; i < nd_region->ndr_mappings; i++) { + struct nd_mapping *nd_mapping = &nd_region->mapping[i]; + struct nd_namespace_label *label0 = nd_mapping->labels[0]; + + size += __le64_to_cpu(label0->rawsize); + if (__le16_to_cpu(label0->position) != 0) + continue; + WARN_ON(nspm->alt_name || nspm->uuid); + nspm->alt_name = kmemdup((void __force *) label0->name, + NSLABEL_NAME_LEN, GFP_KERNEL); + nspm->uuid = kmemdup((void __force *) label0->uuid, + NSLABEL_UUID_LEN, GFP_KERNEL); + } + + if (!nspm->alt_name || !nspm->uuid) { + rc = -ENOMEM; + goto err; + } + + nd_namespace_pmem_set_size(nd_region, nspm, size); + + return 0; + err: + switch (rc) { + case -EINVAL: + dev_dbg(&nd_region->dev, "%s: invalid label(s)\n", __func__); + break; + case -ENODEV: + dev_dbg(&nd_region->dev, "%s: label not found\n", __func__); + break; + default: + dev_dbg(&nd_region->dev, "%s: unexpected err: %d\n", + __func__, rc); + break; + } + return rc; +} + +static struct device **create_namespace_pmem(struct nd_region *nd_region) +{ + struct nd_namespace_pmem *nspm; + struct device *dev, **devs; + struct resource *res; + int rc; + + nspm = kzalloc(sizeof(*nspm), GFP_KERNEL); + if (!nspm) + return NULL; + + dev = &nspm->nsio.dev; + dev->type = &namespace_pmem_device_type; + dev->parent = &nd_region->dev; + res = &nspm->nsio.res; + res->name = dev_name(&nd_region->dev); + res->flags = IORESOURCE_MEM; + rc = find_pmem_label_set(nd_region, nspm); + if (rc == -ENODEV) { + int i; + + /* Pass, try to permit namespace creation... */ + for (i = 0; i < nd_region->ndr_mappings; i++) { + struct nd_mapping *nd_mapping = &nd_region->mapping[i]; + + kfree(nd_mapping->labels); + nd_mapping->labels = NULL; + } + + /* Publish a zero-sized namespace for userspace to configure. */ + nd_namespace_pmem_set_size(nd_region, nspm, 0); + + rc = 0; + } else if (rc) + goto err; + + devs = kcalloc(2, sizeof(struct device *), GFP_KERNEL); + if (!devs) + goto err; + + devs[0] = dev; + return devs; + + err: + namespace_pmem_release(&nspm->nsio.dev); + return NULL; +} + +struct resource *nsblk_add_resource(struct nd_region *nd_region, + struct nvdimm_drvdata *ndd, struct nd_namespace_blk *nsblk, + resource_size_t start) +{ + struct nd_label_id label_id; + struct resource *res; + + nd_label_gen_id(&label_id, nsblk->uuid, NSLABEL_FLAG_LOCAL); + res = krealloc(nsblk->res, + sizeof(void *) * (nsblk->num_resources + 1), + GFP_KERNEL); + if (!res) + return NULL; + nsblk->res = (struct resource **) res; + for_each_dpa_resource(ndd, res) + if (strcmp(res->name, label_id.id) == 0 + && res->start == start) { + nsblk->res[nsblk->num_resources++] = res; + return res; + } + return NULL; +} + +static struct device *nd_namespace_blk_create(struct nd_region *nd_region) +{ + struct nd_namespace_blk *nsblk; + struct device *dev; + + if (!is_nd_blk(&nd_region->dev)) + return NULL; + + nsblk = kzalloc(sizeof(*nsblk), GFP_KERNEL); + if (!nsblk) + return NULL; + + dev = &nsblk->dev; + dev->type = &namespace_blk_device_type; + nsblk->id = ida_simple_get(&nd_region->ns_ida, 0, 0, GFP_KERNEL); + if (nsblk->id < 0) { + kfree(nsblk); + return NULL; + } + dev_set_name(dev, "namespace%d.%d", nd_region->id, nsblk->id); + dev->parent = &nd_region->dev; + dev->groups = nd_namespace_attribute_groups; + + return &nsblk->dev; +} + +void nd_region_create_blk_seed(struct nd_region *nd_region) +{ + WARN_ON(!is_nvdimm_bus_locked(&nd_region->dev)); + nd_region->ns_seed = nd_namespace_blk_create(nd_region); + /* + * Seed creation failures are not fatal, provisioning is simply + * disabled until memory becomes available + */ + if (!nd_region->ns_seed) + dev_err(&nd_region->dev, "failed to create blk namespace\n"); + else + nd_device_register(nd_region->ns_seed); +} + +static struct device **create_namespace_blk(struct nd_region *nd_region) +{ + struct nd_mapping *nd_mapping = &nd_region->mapping[0]; + struct nd_namespace_label *nd_label; + struct device *dev, **devs = NULL; + struct nd_namespace_blk *nsblk; + struct nvdimm_drvdata *ndd; + int i, l, count = 0; + struct resource *res; + + if (nd_region->ndr_mappings == 0) + return NULL; + + ndd = to_ndd(nd_mapping); + for_each_label(l, nd_label, nd_mapping->labels) { + u32 flags = __le32_to_cpu(nd_label->flags); + char *name[NSLABEL_NAME_LEN]; + struct device **__devs; + + if (flags & NSLABEL_FLAG_LOCAL) + /* pass */; + else + continue; + + for (i = 0; i < count; i++) { + nsblk = to_nd_namespace_blk(devs[i]); + if (memcmp(nsblk->uuid, nd_label->uuid, + NSLABEL_UUID_LEN) == 0) { + res = nsblk_add_resource(nd_region, ndd, nsblk, + __le64_to_cpu(nd_label->dpa)); + if (!res) + goto err; + nd_dbg_dpa(nd_region, ndd, res, "%s assign\n", + dev_name(&nsblk->dev)); + break; + } + } + if (i < count) + continue; + __devs = kcalloc(count + 2, sizeof(dev), GFP_KERNEL); + if (!__devs) + goto err; + memcpy(__devs, devs, sizeof(dev) * count); + kfree(devs); + devs = __devs; + + nsblk = kzalloc(sizeof(*nsblk), GFP_KERNEL); + if (!nsblk) + goto err; + dev = &nsblk->dev; + dev->type = &namespace_blk_device_type; + dev->parent = &nd_region->dev; + dev_set_name(dev, "namespace%d.%d", nd_region->id, count); + devs[count++] = dev; + nsblk->id = -1; + nsblk->lbasize = __le64_to_cpu(nd_label->lbasize); + nsblk->uuid = kmemdup(nd_label->uuid, NSLABEL_UUID_LEN, + GFP_KERNEL); + if (!nsblk->uuid) + goto err; + memcpy(name, nd_label->name, NSLABEL_NAME_LEN); + if (name[0]) + nsblk->alt_name = kmemdup(name, NSLABEL_NAME_LEN, + GFP_KERNEL); + res = nsblk_add_resource(nd_region, ndd, nsblk, + __le64_to_cpu(nd_label->dpa)); + if (!res) + goto err; + nd_dbg_dpa(nd_region, ndd, res, "%s assign\n", + dev_name(&nsblk->dev)); + } + + dev_dbg(&nd_region->dev, "%s: discovered %d blk namespace%s\n", + __func__, count, count == 1 ? "" : "s"); + + if (count == 0) { + /* Publish a zero-sized namespace for userspace to configure. */ + for (i = 0; i < nd_region->ndr_mappings; i++) { + struct nd_mapping *nd_mapping = &nd_region->mapping[i]; + + kfree(nd_mapping->labels); + nd_mapping->labels = NULL; + } + + devs = kcalloc(2, sizeof(dev), GFP_KERNEL); + if (!devs) + goto err; + nsblk = kzalloc(sizeof(*nsblk), GFP_KERNEL); + if (!nsblk) + goto err; + dev = &nsblk->dev; + dev->type = &namespace_blk_device_type; + dev->parent = &nd_region->dev; + devs[count++] = dev; + } + + return devs; + +err: + for (i = 0; i < count; i++) { + nsblk = to_nd_namespace_blk(devs[i]); + namespace_blk_release(&nsblk->dev); + } + kfree(devs); + return NULL; +} + +static int init_active_labels(struct nd_region *nd_region) +{ + int i; + + for (i = 0; i < nd_region->ndr_mappings; i++) { + struct nd_mapping *nd_mapping = &nd_region->mapping[i]; + struct nvdimm_drvdata *ndd = to_ndd(nd_mapping); + struct nvdimm *nvdimm = nd_mapping->nvdimm; + int count, j; + + /* + * If the dimm is disabled then prevent the region from + * being activated if it aliases DPA. + */ + if (!ndd) { + if ((nvdimm->flags & NDD_ALIASING) == 0) + return 0; + dev_dbg(&nd_region->dev, "%s: is disabled, failing probe\n", + dev_name(&nd_mapping->nvdimm->dev)); + return -ENXIO; + } + nd_mapping->ndd = ndd; + atomic_inc(&nvdimm->busy); + get_ndd(ndd); + + count = nd_label_active_count(ndd); + dev_dbg(ndd->dev, "%s: %d\n", __func__, count); + if (!count) + continue; + nd_mapping->labels = kcalloc(count + 1, sizeof(void *), + GFP_KERNEL); + if (!nd_mapping->labels) + return -ENOMEM; + for (j = 0; j < count; j++) { + struct nd_namespace_label *label; + + label = nd_label_active(ndd, j); + nd_mapping->labels[j] = label; + } + } + + return 0; +} + +int nd_region_register_namespaces(struct nd_region *nd_region, int *err) +{ + struct device **devs = NULL; + int i, rc = 0, type; + + *err = 0; + nvdimm_bus_lock(&nd_region->dev); + rc = init_active_labels(nd_region); + if (rc) { + nvdimm_bus_unlock(&nd_region->dev); + return rc; + } + + type = nd_region_to_nstype(nd_region); + switch (type) { + case ND_DEVICE_NAMESPACE_IO: + devs = create_namespace_io(nd_region); + break; + case ND_DEVICE_NAMESPACE_PMEM: + devs = create_namespace_pmem(nd_region); + break; + case ND_DEVICE_NAMESPACE_BLK: + devs = create_namespace_blk(nd_region); + break; + default: + break; + } + nvdimm_bus_unlock(&nd_region->dev); + + if (!devs) + return -ENODEV; + + for (i = 0; devs[i]; i++) { + struct device *dev = devs[i]; + int id; + + if (type == ND_DEVICE_NAMESPACE_BLK) { + struct nd_namespace_blk *nsblk; + + nsblk = to_nd_namespace_blk(dev); + id = ida_simple_get(&nd_region->ns_ida, 0, 0, + GFP_KERNEL); + nsblk->id = id; + } else + id = i; + + if (id < 0) + break; + dev_set_name(dev, "namespace%d.%d", nd_region->id, id); + dev->groups = nd_namespace_attribute_groups; + nd_device_register(dev); + } + if (i) + nd_region->ns_seed = devs[0]; + + if (devs[i]) { + int j; + + for (j = i; devs[j]; j++) { + struct device *dev = devs[j]; + + device_initialize(dev); + put_device(dev); + } + *err = j - i; + /* + * All of the namespaces we tried to register failed, so + * fail region activation. + */ + if (*err == 0) + rc = -ENODEV; + } + kfree(devs); + + if (rc == -ENODEV) + return rc; + + return i; +} diff --git a/drivers/nvdimm/nd-core.h b/drivers/nvdimm/nd-core.h new file mode 100644 index 000000000000..78d6c51f4bac --- /dev/null +++ b/drivers/nvdimm/nd-core.h @@ -0,0 +1,80 @@ +/* + * Copyright(c) 2013-2015 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 __ND_CORE_H__ +#define __ND_CORE_H__ +#include <linux/libnvdimm.h> +#include <linux/device.h> +#include <linux/libnvdimm.h> +#include <linux/sizes.h> +#include <linux/mutex.h> +#include <linux/nd.h> + +extern struct list_head nvdimm_bus_list; +extern struct mutex nvdimm_bus_list_mutex; +extern int nvdimm_major; + +struct nvdimm_bus { + struct nvdimm_bus_descriptor *nd_desc; + wait_queue_head_t probe_wait; + struct module *module; + struct list_head list; + struct device dev; + int id, probe_active; + struct mutex reconfig_mutex; +}; + +struct nvdimm { + unsigned long flags; + void *provider_data; + unsigned long *dsm_mask; + struct device dev; + atomic_t busy; + int id; +}; + +bool is_nvdimm(struct device *dev); +bool is_nd_blk(struct device *dev); +bool is_nd_pmem(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 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_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); +void nd_synchronize(void); +int nvdimm_bus_register_dimms(struct nvdimm_bus *nvdimm_bus); +int nvdimm_bus_register_regions(struct nvdimm_bus *nvdimm_bus); +int nvdimm_bus_init_interleave_sets(struct nvdimm_bus *nvdimm_bus); +int nd_match_dimm(struct device *dev, void *data); +struct nd_label_id; +char *nd_label_gen_id(struct nd_label_id *label_id, u8 *uuid, u32 flags); +bool nd_is_uuid_unique(struct device *dev, u8 *uuid); +struct nd_region; +struct nvdimm_drvdata; +struct nd_mapping; +resource_size_t nd_pmem_available_dpa(struct nd_region *nd_region, + struct nd_mapping *nd_mapping, resource_size_t *overlap); +resource_size_t nd_blk_available_dpa(struct nd_mapping *nd_mapping); +resource_size_t nd_region_available_dpa(struct nd_region *nd_region); +resource_size_t nvdimm_allocated_dpa(struct nvdimm_drvdata *ndd, + struct nd_label_id *label_id); +struct nd_mapping; +struct resource *nsblk_add_resource(struct nd_region *nd_region, + struct nvdimm_drvdata *ndd, struct nd_namespace_blk *nsblk, + resource_size_t start); +int nvdimm_num_label_slots(struct nvdimm_drvdata *ndd); +void get_ndd(struct nvdimm_drvdata *ndd); +#endif /* __ND_CORE_H__ */ diff --git a/drivers/nvdimm/nd.h b/drivers/nvdimm/nd.h new file mode 100644 index 000000000000..bfa849617358 --- /dev/null +++ b/drivers/nvdimm/nd.h @@ -0,0 +1,135 @@ +/* + * Copyright(c) 2013-2015 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 __ND_H__ +#define __ND_H__ +#include <linux/libnvdimm.h> +#include <linux/device.h> +#include <linux/mutex.h> +#include <linux/ndctl.h> +#include <linux/types.h> +#include "label.h" + +struct nvdimm_drvdata { + struct device *dev; + int nsindex_size; + struct nd_cmd_get_config_size nsarea; + void *data; + int ns_current, ns_next; + struct resource dpa; + struct kref kref; +}; + +struct nd_region_namespaces { + int count; + int active; +}; + +static inline struct nd_namespace_index *to_namespace_index( + struct nvdimm_drvdata *ndd, int i) +{ + if (i < 0) + return NULL; + + return ndd->data + sizeof_namespace_index(ndd) * i; +} + +static inline struct nd_namespace_index *to_current_namespace_index( + struct nvdimm_drvdata *ndd) +{ + return to_namespace_index(ndd, ndd->ns_current); +} + +static inline struct nd_namespace_index *to_next_namespace_index( + struct nvdimm_drvdata *ndd) +{ + return to_namespace_index(ndd, ndd->ns_next); +} + +#define nd_dbg_dpa(r, d, res, fmt, arg...) \ + dev_dbg((r) ? &(r)->dev : (d)->dev, "%s: %.13s: %#llx @ %#llx " fmt, \ + (r) ? dev_name((d)->dev) : "", res ? res->name : "null", \ + (unsigned long long) (res ? resource_size(res) : 0), \ + (unsigned long long) (res ? res->start : 0), ##arg) + +#define for_each_label(l, label, labels) \ + for (l = 0; (label = labels ? labels[l] : NULL); l++) + +#define for_each_dpa_resource(ndd, res) \ + for (res = (ndd)->dpa.child; res; res = res->sibling) + +#define for_each_dpa_resource_safe(ndd, res, next) \ + for (res = (ndd)->dpa.child, next = res ? res->sibling : NULL; \ + res; res = next, next = next ? next->sibling : NULL) + +struct nd_region { + struct device dev; + struct ida ns_ida; + struct device *ns_seed; + u16 ndr_mappings; + u64 ndr_size; + u64 ndr_start; + int id; + void *provider_data; + struct nd_interleave_set *nd_set; + struct nd_mapping mapping[0]; +}; + +/* + * Lookup next in the repeating sequence of 01, 10, and 11. + */ +static inline unsigned nd_inc_seq(unsigned seq) +{ + static const unsigned next[] = { 0, 2, 3, 1 }; + + return next[seq & 3]; +} + +enum nd_async_mode { + ND_SYNC, + ND_ASYNC, +}; + +void wait_nvdimm_bus_probe_idle(struct device *dev); +void nd_device_register(struct device *dev); +void nd_device_unregister(struct device *dev, enum nd_async_mode mode); +int nd_uuid_store(struct device *dev, u8 **uuid_out, const char *buf, + size_t len); +ssize_t nd_sector_size_show(unsigned long current_lbasize, + const unsigned long *supported, char *buf); +ssize_t nd_sector_size_store(struct device *dev, const char *buf, + unsigned long *current_lbasize, const unsigned long *supported); +int __init nvdimm_init(void); +int __init nd_region_init(void); +void nvdimm_exit(void); +void nd_region_exit(void); +struct nvdimm; +struct nvdimm_drvdata *to_ndd(struct nd_mapping *nd_mapping); +int nvdimm_init_nsarea(struct nvdimm_drvdata *ndd); +int nvdimm_init_config_data(struct nvdimm_drvdata *ndd); +int nvdimm_set_config_data(struct nvdimm_drvdata *ndd, size_t offset, + void *buf, size_t len); +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); +u64 nd_region_interleave_set_cookie(struct nd_region *nd_region); +void nvdimm_bus_lock(struct device *dev); +void nvdimm_bus_unlock(struct device *dev); +bool is_nvdimm_bus_locked(struct device *dev); +void nvdimm_drvdata_release(struct kref *kref); +void put_ndd(struct nvdimm_drvdata *ndd); +int nd_label_reserve_dpa(struct nvdimm_drvdata *ndd); +void nvdimm_free_dpa(struct nvdimm_drvdata *ndd, struct resource *res); +struct resource *nvdimm_allocate_dpa(struct nvdimm_drvdata *ndd, + struct nd_label_id *label_id, resource_size_t start, + resource_size_t n); +#endif /* __ND_H__ */ diff --git a/drivers/block/pmem.c b/drivers/nvdimm/pmem.c index 095dfaadcaa5..8c20df45821e 100644 --- a/drivers/block/pmem.c +++ b/drivers/nvdimm/pmem.c @@ -1,7 +1,7 @@ /* * Persistent Memory Driver * - * Copyright (c) 2014, Intel Corporation. + * Copyright (c) 2014-2015, Intel Corporation. * Copyright (c) 2015, Christoph Hellwig <hch@lst.de>. * Copyright (c) 2015, Boaz Harrosh <boaz@plexistor.com>. * @@ -23,8 +23,8 @@ #include <linux/module.h> #include <linux/moduleparam.h> #include <linux/slab.h> - -#define PMEM_MINORS 16 +#include <linux/nd.h> +#include "nd.h" struct pmem_device { struct request_queue *pmem_queue; @@ -37,7 +37,6 @@ struct pmem_device { }; static int pmem_major; -static atomic_t pmem_index; static void pmem_do_bvec(struct pmem_device *pmem, struct page *page, unsigned int len, unsigned int off, int rw, @@ -118,11 +117,12 @@ static const struct block_device_operations pmem_fops = { .direct_access = pmem_direct_access, }; -static struct pmem_device *pmem_alloc(struct device *dev, struct resource *res) +static struct pmem_device *pmem_alloc(struct device *dev, + struct resource *res, int id) { struct pmem_device *pmem; struct gendisk *disk; - int idx, err; + int err; err = -ENOMEM; pmem = kzalloc(sizeof(*pmem), GFP_KERNEL); @@ -134,7 +134,8 @@ static struct pmem_device *pmem_alloc(struct device *dev, struct resource *res) err = -EINVAL; if (!request_mem_region(pmem->phys_addr, pmem->size, "pmem")) { - dev_warn(dev, "could not reserve region [0x%pa:0x%zx]\n", &pmem->phys_addr, pmem->size); + dev_warn(dev, "could not reserve region [0x%pa:0x%zx]\n", + &pmem->phys_addr, pmem->size); goto out_free_dev; } @@ -155,19 +156,17 @@ static struct pmem_device *pmem_alloc(struct device *dev, struct resource *res) blk_queue_max_hw_sectors(pmem->pmem_queue, 1024); blk_queue_bounce_limit(pmem->pmem_queue, BLK_BOUNCE_ANY); - disk = alloc_disk(PMEM_MINORS); + disk = alloc_disk(0); if (!disk) goto out_free_queue; - idx = atomic_inc_return(&pmem_index) - 1; - disk->major = pmem_major; - disk->first_minor = PMEM_MINORS * idx; + disk->first_minor = 0; disk->fops = &pmem_fops; disk->private_data = pmem; disk->queue = pmem->pmem_queue; disk->flags = GENHD_FL_EXT_DEVT; - sprintf(disk->disk_name, "pmem%d", idx); + sprintf(disk->disk_name, "pmem%d", id); disk->driverfs_dev = dev; set_capacity(disk, pmem->size >> 9); pmem->pmem_disk = disk; @@ -198,42 +197,56 @@ static void pmem_free(struct pmem_device *pmem) kfree(pmem); } -static int pmem_probe(struct platform_device *pdev) +static int nd_pmem_probe(struct device *dev) { + struct nd_region *nd_region = to_nd_region(dev->parent); + struct nd_namespace_io *nsio = to_nd_namespace_io(dev); struct pmem_device *pmem; - struct resource *res; - if (WARN_ON(pdev->num_resources > 1)) - return -ENXIO; + if (resource_size(&nsio->res) < ND_MIN_NAMESPACE_SIZE) { + resource_size_t size = resource_size(&nsio->res); + + dev_dbg(dev, "%s: size: %pa, too small must be at least %#x\n", + __func__, &size, ND_MIN_NAMESPACE_SIZE); + return -ENODEV; + } + + if (nd_region_to_nstype(nd_region) == ND_DEVICE_NAMESPACE_PMEM) { + struct nd_namespace_pmem *nspm = to_nd_namespace_pmem(dev); - res = platform_get_resource(pdev, IORESOURCE_MEM, 0); - if (!res) - return -ENXIO; + if (!nspm->uuid) { + dev_dbg(dev, "%s: uuid not set\n", __func__); + return -ENODEV; + } + } - pmem = pmem_alloc(&pdev->dev, res); + pmem = pmem_alloc(dev, &nsio->res, nd_region->id); if (IS_ERR(pmem)) return PTR_ERR(pmem); - platform_set_drvdata(pdev, pmem); + dev_set_drvdata(dev, pmem); return 0; } -static int pmem_remove(struct platform_device *pdev) +static int nd_pmem_remove(struct device *dev) { - struct pmem_device *pmem = platform_get_drvdata(pdev); + struct pmem_device *pmem = dev_get_drvdata(dev); pmem_free(pmem); return 0; } -static struct platform_driver pmem_driver = { - .probe = pmem_probe, - .remove = pmem_remove, - .driver = { - .owner = THIS_MODULE, - .name = "pmem", +MODULE_ALIAS("pmem"); +MODULE_ALIAS_ND_DEVICE(ND_DEVICE_NAMESPACE_IO); +MODULE_ALIAS_ND_DEVICE(ND_DEVICE_NAMESPACE_PMEM); +static struct nd_device_driver nd_pmem_driver = { + .probe = nd_pmem_probe, + .remove = nd_pmem_remove, + .drv = { + .name = "nd_pmem", }, + .type = ND_DRIVER_NAMESPACE_IO | ND_DRIVER_NAMESPACE_PMEM, }; static int __init pmem_init(void) @@ -244,16 +257,19 @@ static int __init pmem_init(void) if (pmem_major < 0) return pmem_major; - error = platform_driver_register(&pmem_driver); - if (error) + error = nd_driver_register(&nd_pmem_driver); + if (error) { unregister_blkdev(pmem_major, "pmem"); - return error; + return error; + } + + return 0; } module_init(pmem_init); static void pmem_exit(void) { - platform_driver_unregister(&pmem_driver); + driver_unregister(&nd_pmem_driver.drv); unregister_blkdev(pmem_major, "pmem"); } module_exit(pmem_exit); diff --git a/drivers/nvdimm/region.c b/drivers/nvdimm/region.c new file mode 100644 index 000000000000..9aba44e483e0 --- /dev/null +++ b/drivers/nvdimm/region.c @@ -0,0 +1,96 @@ +/* + * Copyright(c) 2013-2015 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/module.h> +#include <linux/device.h> +#include <linux/nd.h> +#include "nd.h" + +static int nd_region_probe(struct device *dev) +{ + int err; + struct nd_region_namespaces *num_ns; + struct nd_region *nd_region = to_nd_region(dev); + int rc = nd_region_register_namespaces(nd_region, &err); + + num_ns = devm_kzalloc(dev, sizeof(*num_ns), GFP_KERNEL); + if (!num_ns) + return -ENOMEM; + + if (rc < 0) + return rc; + + num_ns->active = rc; + num_ns->count = rc + err; + dev_set_drvdata(dev, num_ns); + + if (err == 0) + return 0; + + if (rc == err) + return -ENODEV; + + /* + * Given multiple namespaces per region, we do not want to + * disable all the successfully registered peer namespaces upon + * a single registration failure. If userspace is missing a + * namespace that it expects it can disable/re-enable the region + * to retry discovery after correcting the failure. + * <regionX>/namespaces returns the current + * "<async-registered>/<total>" namespace count. + */ + dev_err(dev, "failed to register %d namespace%s, continuing...\n", + err, err == 1 ? "" : "s"); + return 0; +} + +static int child_unregister(struct device *dev, void *data) +{ + nd_device_unregister(dev, ND_SYNC); + return 0; +} + +static int nd_region_remove(struct device *dev) +{ + struct nd_region *nd_region = to_nd_region(dev); + + /* flush attribute readers and disable */ + nvdimm_bus_lock(dev); + nd_region->ns_seed = NULL; + dev_set_drvdata(dev, NULL); + nvdimm_bus_unlock(dev); + + device_for_each_child(dev, NULL, child_unregister); + return 0; +} + +static struct nd_device_driver nd_region_driver = { + .probe = nd_region_probe, + .remove = nd_region_remove, + .drv = { + .name = "nd_region", + }, + .type = ND_DRIVER_REGION_BLK | ND_DRIVER_REGION_PMEM, +}; + +int __init nd_region_init(void) +{ + return nd_driver_register(&nd_region_driver); +} + +void nd_region_exit(void) +{ + driver_unregister(&nd_region_driver.drv); +} + +MODULE_ALIAS_ND_DEVICE(ND_DEVICE_REGION_PMEM); +MODULE_ALIAS_ND_DEVICE(ND_DEVICE_REGION_BLK); diff --git a/drivers/nvdimm/region_devs.c b/drivers/nvdimm/region_devs.c new file mode 100644 index 000000000000..ac21ce419beb --- /dev/null +++ b/drivers/nvdimm/region_devs.c @@ -0,0 +1,585 @@ +/* + * Copyright(c) 2013-2015 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/scatterlist.h> +#include <linux/sched.h> +#include <linux/slab.h> +#include <linux/sort.h> +#include <linux/io.h> +#include <linux/nd.h> +#include "nd-core.h" +#include "nd.h" + +static DEFINE_IDA(region_ida); + +static void nd_region_release(struct device *dev) +{ + struct nd_region *nd_region = to_nd_region(dev); + u16 i; + + for (i = 0; i < nd_region->ndr_mappings; i++) { + struct nd_mapping *nd_mapping = &nd_region->mapping[i]; + struct nvdimm *nvdimm = nd_mapping->nvdimm; + + put_device(&nvdimm->dev); + } + ida_simple_remove(®ion_ida, nd_region->id); + kfree(nd_region); +} + +static struct device_type nd_blk_device_type = { + .name = "nd_blk", + .release = nd_region_release, +}; + +static struct device_type nd_pmem_device_type = { + .name = "nd_pmem", + .release = nd_region_release, +}; + +static struct device_type nd_volatile_device_type = { + .name = "nd_volatile", + .release = nd_region_release, +}; + +bool is_nd_pmem(struct device *dev) +{ + return dev ? dev->type == &nd_pmem_device_type : false; +} + +bool is_nd_blk(struct device *dev) +{ + return dev ? dev->type == &nd_blk_device_type : false; +} + +struct nd_region *to_nd_region(struct device *dev) +{ + struct nd_region *nd_region = container_of(dev, struct nd_region, dev); + + WARN_ON(dev->type->release != nd_region_release); + return nd_region; +} +EXPORT_SYMBOL_GPL(to_nd_region); + +/** + * nd_region_to_nstype() - region to an integer namespace type + * @nd_region: region-device to interrogate + * + * This is the 'nstype' attribute of a region as well, an input to the + * MODALIAS for namespace devices, and bit number for a nvdimm_bus to match + * namespace devices with namespace drivers. + */ +int nd_region_to_nstype(struct nd_region *nd_region) +{ + if (is_nd_pmem(&nd_region->dev)) { + u16 i, alias; + + for (i = 0, alias = 0; i < nd_region->ndr_mappings; i++) { + struct nd_mapping *nd_mapping = &nd_region->mapping[i]; + struct nvdimm *nvdimm = nd_mapping->nvdimm; + + if (nvdimm->flags & NDD_ALIASING) + alias++; + } + if (alias) + return ND_DEVICE_NAMESPACE_PMEM; + else + return ND_DEVICE_NAMESPACE_IO; + } else if (is_nd_blk(&nd_region->dev)) { + return ND_DEVICE_NAMESPACE_BLK; + } + + return 0; +} +EXPORT_SYMBOL(nd_region_to_nstype); + +static int is_uuid_busy(struct device *dev, void *data) +{ + struct nd_region *nd_region = to_nd_region(dev->parent); + u8 *uuid = data; + + switch (nd_region_to_nstype(nd_region)) { + case ND_DEVICE_NAMESPACE_PMEM: { + struct nd_namespace_pmem *nspm = to_nd_namespace_pmem(dev); + + if (!nspm->uuid) + break; + if (memcmp(uuid, nspm->uuid, NSLABEL_UUID_LEN) == 0) + return -EBUSY; + break; + } + case ND_DEVICE_NAMESPACE_BLK: { + struct nd_namespace_blk *nsblk = to_nd_namespace_blk(dev); + + if (!nsblk->uuid) + break; + if (memcmp(uuid, nsblk->uuid, NSLABEL_UUID_LEN) == 0) + return -EBUSY; + break; + } + default: + break; + } + + return 0; +} + +static int is_namespace_uuid_busy(struct device *dev, void *data) +{ + if (is_nd_pmem(dev) || is_nd_blk(dev)) + return device_for_each_child(dev, data, is_uuid_busy); + return 0; +} + +/** + * nd_is_uuid_unique - verify that no other namespace has @uuid + * @dev: any device on a nvdimm_bus + * @uuid: uuid to check + */ +bool nd_is_uuid_unique(struct device *dev, u8 *uuid) +{ + struct nvdimm_bus *nvdimm_bus = walk_to_nvdimm_bus(dev); + + if (!nvdimm_bus) + return false; + WARN_ON_ONCE(!is_nvdimm_bus_locked(&nvdimm_bus->dev)); + if (device_for_each_child(&nvdimm_bus->dev, uuid, + is_namespace_uuid_busy) != 0) + return false; + return true; +} + +static ssize_t size_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + struct nd_region *nd_region = to_nd_region(dev); + unsigned long long size = 0; + + if (is_nd_pmem(dev)) { + size = nd_region->ndr_size; + } else if (nd_region->ndr_mappings == 1) { + struct nd_mapping *nd_mapping = &nd_region->mapping[0]; + + size = nd_mapping->size; + } + + return sprintf(buf, "%llu\n", size); +} +static DEVICE_ATTR_RO(size); + +static ssize_t mappings_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + struct nd_region *nd_region = to_nd_region(dev); + + return sprintf(buf, "%d\n", nd_region->ndr_mappings); +} +static DEVICE_ATTR_RO(mappings); + +static ssize_t nstype_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + struct nd_region *nd_region = to_nd_region(dev); + + return sprintf(buf, "%d\n", nd_region_to_nstype(nd_region)); +} +static DEVICE_ATTR_RO(nstype); + +static ssize_t set_cookie_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + struct nd_region *nd_region = to_nd_region(dev); + struct nd_interleave_set *nd_set = nd_region->nd_set; + + if (is_nd_pmem(dev) && nd_set) + /* pass, should be precluded by region_visible */; + else + return -ENXIO; + + return sprintf(buf, "%#llx\n", nd_set->cookie); +} +static DEVICE_ATTR_RO(set_cookie); + +resource_size_t nd_region_available_dpa(struct nd_region *nd_region) +{ + resource_size_t blk_max_overlap = 0, available, overlap; + int i; + + WARN_ON(!is_nvdimm_bus_locked(&nd_region->dev)); + + retry: + available = 0; + overlap = blk_max_overlap; + for (i = 0; i < nd_region->ndr_mappings; i++) { + struct nd_mapping *nd_mapping = &nd_region->mapping[i]; + struct nvdimm_drvdata *ndd = to_ndd(nd_mapping); + + /* if a dimm is disabled the available capacity is zero */ + if (!ndd) + return 0; + + if (is_nd_pmem(&nd_region->dev)) { + available += nd_pmem_available_dpa(nd_region, + nd_mapping, &overlap); + if (overlap > blk_max_overlap) { + blk_max_overlap = overlap; + goto retry; + } + } else if (is_nd_blk(&nd_region->dev)) { + available += nd_blk_available_dpa(nd_mapping); + } + } + + return available; +} + +static ssize_t available_size_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + struct nd_region *nd_region = to_nd_region(dev); + unsigned long long available = 0; + + /* + * Flush in-flight updates and grab a snapshot of the available + * size. Of course, this value is potentially invalidated the + * memory nvdimm_bus_lock() is dropped, but that's userspace's + * problem to not race itself. + */ + nvdimm_bus_lock(dev); + wait_nvdimm_bus_probe_idle(dev); + available = nd_region_available_dpa(nd_region); + nvdimm_bus_unlock(dev); + + return sprintf(buf, "%llu\n", available); +} +static DEVICE_ATTR_RO(available_size); + +static ssize_t init_namespaces_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + struct nd_region_namespaces *num_ns = dev_get_drvdata(dev); + ssize_t rc; + + nvdimm_bus_lock(dev); + if (num_ns) + rc = sprintf(buf, "%d/%d\n", num_ns->active, num_ns->count); + else + rc = -ENXIO; + nvdimm_bus_unlock(dev); + + return rc; +} +static DEVICE_ATTR_RO(init_namespaces); + +static ssize_t namespace_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->ns_seed) + rc = sprintf(buf, "%s\n", dev_name(nd_region->ns_seed)); + else + rc = sprintf(buf, "\n"); + nvdimm_bus_unlock(dev); + return rc; +} +static DEVICE_ATTR_RO(namespace_seed); + +static struct attribute *nd_region_attributes[] = { + &dev_attr_size.attr, + &dev_attr_nstype.attr, + &dev_attr_mappings.attr, + &dev_attr_set_cookie.attr, + &dev_attr_available_size.attr, + &dev_attr_namespace_seed.attr, + &dev_attr_init_namespaces.attr, + NULL, +}; + +static umode_t region_visible(struct kobject *kobj, struct attribute *a, int n) +{ + struct device *dev = container_of(kobj, typeof(*dev), kobj); + struct nd_region *nd_region = to_nd_region(dev); + struct nd_interleave_set *nd_set = nd_region->nd_set; + int type = nd_region_to_nstype(nd_region); + + if (a != &dev_attr_set_cookie.attr + && a != &dev_attr_available_size.attr) + return a->mode; + + if ((type == ND_DEVICE_NAMESPACE_PMEM + || type == ND_DEVICE_NAMESPACE_BLK) + && a == &dev_attr_available_size.attr) + return a->mode; + else if (is_nd_pmem(dev) && nd_set) + return a->mode; + + return 0; +} + +struct attribute_group nd_region_attribute_group = { + .attrs = nd_region_attributes, + .is_visible = region_visible, +}; +EXPORT_SYMBOL_GPL(nd_region_attribute_group); + +u64 nd_region_interleave_set_cookie(struct nd_region *nd_region) +{ + struct nd_interleave_set *nd_set = nd_region->nd_set; + + if (nd_set) + return nd_set->cookie; + return 0; +} + +/* + * Upon successful probe/remove, take/release a reference on the + * associated interleave set (if present) + */ +static void nd_region_notify_driver_action(struct nvdimm_bus *nvdimm_bus, + struct device *dev, bool probe) +{ + if (!probe && (is_nd_pmem(dev) || is_nd_blk(dev))) { + struct nd_region *nd_region = to_nd_region(dev); + int i; + + for (i = 0; i < nd_region->ndr_mappings; i++) { + struct nd_mapping *nd_mapping = &nd_region->mapping[i]; + struct nvdimm_drvdata *ndd = nd_mapping->ndd; + struct nvdimm *nvdimm = nd_mapping->nvdimm; + + kfree(nd_mapping->labels); + nd_mapping->labels = NULL; + put_ndd(ndd); + nd_mapping->ndd = NULL; + atomic_dec(&nvdimm->busy); + } + } else if (dev->parent && is_nd_blk(dev->parent) && probe) { + struct nd_region *nd_region = to_nd_region(dev->parent); + + nvdimm_bus_lock(dev); + if (nd_region->ns_seed == dev) + nd_region_create_blk_seed(nd_region); + nvdimm_bus_unlock(dev); + } +} + +void nd_region_probe_success(struct nvdimm_bus *nvdimm_bus, struct device *dev) +{ + nd_region_notify_driver_action(nvdimm_bus, dev, true); +} + +void nd_region_disable(struct nvdimm_bus *nvdimm_bus, struct device *dev) +{ + nd_region_notify_driver_action(nvdimm_bus, dev, false); +} + +static ssize_t mappingN(struct device *dev, char *buf, int n) +{ + struct nd_region *nd_region = to_nd_region(dev); + struct nd_mapping *nd_mapping; + struct nvdimm *nvdimm; + + if (n >= nd_region->ndr_mappings) + return -ENXIO; + nd_mapping = &nd_region->mapping[n]; + nvdimm = nd_mapping->nvdimm; + + return sprintf(buf, "%s,%llu,%llu\n", dev_name(&nvdimm->dev), + nd_mapping->start, nd_mapping->size); +} + +#define REGION_MAPPING(idx) \ +static ssize_t mapping##idx##_show(struct device *dev, \ + struct device_attribute *attr, char *buf) \ +{ \ + return mappingN(dev, buf, idx); \ +} \ +static DEVICE_ATTR_RO(mapping##idx) + +/* + * 32 should be enough for a while, even in the presence of socket + * interleave a 32-way interleave set is a degenerate case. + */ +REGION_MAPPING(0); +REGION_MAPPING(1); +REGION_MAPPING(2); +REGION_MAPPING(3); +REGION_MAPPING(4); +REGION_MAPPING(5); +REGION_MAPPING(6); +REGION_MAPPING(7); +REGION_MAPPING(8); +REGION_MAPPING(9); +REGION_MAPPING(10); +REGION_MAPPING(11); +REGION_MAPPING(12); +REGION_MAPPING(13); +REGION_MAPPING(14); +REGION_MAPPING(15); +REGION_MAPPING(16); +REGION_MAPPING(17); +REGION_MAPPING(18); +REGION_MAPPING(19); +REGION_MAPPING(20); +REGION_MAPPING(21); +REGION_MAPPING(22); +REGION_MAPPING(23); +REGION_MAPPING(24); +REGION_MAPPING(25); +REGION_MAPPING(26); +REGION_MAPPING(27); +REGION_MAPPING(28); +REGION_MAPPING(29); +REGION_MAPPING(30); +REGION_MAPPING(31); + +static umode_t mapping_visible(struct kobject *kobj, struct attribute *a, int n) +{ + struct device *dev = container_of(kobj, struct device, kobj); + struct nd_region *nd_region = to_nd_region(dev); + + if (n < nd_region->ndr_mappings) + return a->mode; + return 0; +} + +static struct attribute *mapping_attributes[] = { + &dev_attr_mapping0.attr, + &dev_attr_mapping1.attr, + &dev_attr_mapping2.attr, + &dev_attr_mapping3.attr, + &dev_attr_mapping4.attr, + &dev_attr_mapping5.attr, + &dev_attr_mapping6.attr, + &dev_attr_mapping7.attr, + &dev_attr_mapping8.attr, + &dev_attr_mapping9.attr, + &dev_attr_mapping10.attr, + &dev_attr_mapping11.attr, + &dev_attr_mapping12.attr, + &dev_attr_mapping13.attr, + &dev_attr_mapping14.attr, + &dev_attr_mapping15.attr, + &dev_attr_mapping16.attr, + &dev_attr_mapping17.attr, + &dev_attr_mapping18.attr, + &dev_attr_mapping19.attr, + &dev_attr_mapping20.attr, + &dev_attr_mapping21.attr, + &dev_attr_mapping22.attr, + &dev_attr_mapping23.attr, + &dev_attr_mapping24.attr, + &dev_attr_mapping25.attr, + &dev_attr_mapping26.attr, + &dev_attr_mapping27.attr, + &dev_attr_mapping28.attr, + &dev_attr_mapping29.attr, + &dev_attr_mapping30.attr, + &dev_attr_mapping31.attr, + NULL, +}; + +struct attribute_group nd_mapping_attribute_group = { + .is_visible = mapping_visible, + .attrs = mapping_attributes, +}; +EXPORT_SYMBOL_GPL(nd_mapping_attribute_group); + +void *nd_region_provider_data(struct nd_region *nd_region) +{ + return nd_region->provider_data; +} +EXPORT_SYMBOL_GPL(nd_region_provider_data); + +static struct nd_region *nd_region_create(struct nvdimm_bus *nvdimm_bus, + struct nd_region_desc *ndr_desc, struct device_type *dev_type, + const char *caller) +{ + struct nd_region *nd_region; + struct device *dev; + u16 i; + + for (i = 0; i < ndr_desc->num_mappings; i++) { + struct nd_mapping *nd_mapping = &ndr_desc->nd_mapping[i]; + struct nvdimm *nvdimm = nd_mapping->nvdimm; + + if ((nd_mapping->start | nd_mapping->size) % SZ_4K) { + dev_err(&nvdimm_bus->dev, "%s: %s mapping%d is not 4K aligned\n", + caller, dev_name(&nvdimm->dev), i); + + return NULL; + } + } + + nd_region = kzalloc(sizeof(struct nd_region) + + sizeof(struct nd_mapping) * ndr_desc->num_mappings, + GFP_KERNEL); + if (!nd_region) + return NULL; + nd_region->id = ida_simple_get(®ion_ida, 0, 0, GFP_KERNEL); + if (nd_region->id < 0) { + kfree(nd_region); + return NULL; + } + + memcpy(nd_region->mapping, ndr_desc->nd_mapping, + sizeof(struct nd_mapping) * ndr_desc->num_mappings); + for (i = 0; i < ndr_desc->num_mappings; i++) { + struct nd_mapping *nd_mapping = &ndr_desc->nd_mapping[i]; + struct nvdimm *nvdimm = nd_mapping->nvdimm; + + get_device(&nvdimm->dev); + } + nd_region->ndr_mappings = ndr_desc->num_mappings; + nd_region->provider_data = ndr_desc->provider_data; + nd_region->nd_set = ndr_desc->nd_set; + ida_init(&nd_region->ns_ida); + dev = &nd_region->dev; + dev_set_name(dev, "region%d", nd_region->id); + dev->parent = &nvdimm_bus->dev; + dev->type = dev_type; + dev->groups = ndr_desc->attr_groups; + nd_region->ndr_size = resource_size(ndr_desc->res); + nd_region->ndr_start = ndr_desc->res->start; + nd_device_register(dev); + + return nd_region; +} + +struct nd_region *nvdimm_pmem_region_create(struct nvdimm_bus *nvdimm_bus, + struct nd_region_desc *ndr_desc) +{ + return nd_region_create(nvdimm_bus, ndr_desc, &nd_pmem_device_type, + __func__); +} +EXPORT_SYMBOL_GPL(nvdimm_pmem_region_create); + +struct nd_region *nvdimm_blk_region_create(struct nvdimm_bus *nvdimm_bus, + struct nd_region_desc *ndr_desc) +{ + if (ndr_desc->num_mappings > 1) + return NULL; + return nd_region_create(nvdimm_bus, ndr_desc, &nd_blk_device_type, + __func__); +} +EXPORT_SYMBOL_GPL(nvdimm_blk_region_create); + +struct nd_region *nvdimm_volatile_region_create(struct nvdimm_bus *nvdimm_bus, + struct nd_region_desc *ndr_desc) +{ + return nd_region_create(nvdimm_bus, ndr_desc, &nd_volatile_device_type, + __func__); +} +EXPORT_SYMBOL_GPL(nvdimm_volatile_region_create); diff --git a/include/linux/efi.h b/include/linux/efi.h index 5f19efe4eb3f..85ef051ac6fb 100644 --- a/include/linux/efi.h +++ b/include/linux/efi.h @@ -85,7 +85,8 @@ typedef struct { #define EFI_MEMORY_MAPPED_IO 11 #define EFI_MEMORY_MAPPED_IO_PORT_SPACE 12 #define EFI_PAL_CODE 13 -#define EFI_MAX_MEMORY_TYPE 14 +#define EFI_PERSISTENT_MEMORY 14 +#define EFI_MAX_MEMORY_TYPE 15 /* Attribute values: */ #define EFI_MEMORY_UC ((u64)0x0000000000000001ULL) /* uncached */ diff --git a/include/linux/libnvdimm.h b/include/linux/libnvdimm.h new file mode 100644 index 000000000000..a59dca17b3aa --- /dev/null +++ b/include/linux/libnvdimm.h @@ -0,0 +1,123 @@ +/* + * libnvdimm - Non-volatile-memory Devices Subsystem + * + * Copyright(c) 2013-2015 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 __LIBNVDIMM_H__ +#define __LIBNVDIMM_H__ +#include <linux/sizes.h> +#include <linux/types.h> + +enum { + /* when a dimm supports both PMEM and BLK access a label is required */ + NDD_ALIASING = 1 << 0, + + /* need to set a limit somewhere, but yes, this is likely overkill */ + ND_IOCTL_MAX_BUFLEN = SZ_4M, + ND_CMD_MAX_ELEM = 4, + ND_CMD_MAX_ENVELOPE = 16, + ND_CMD_ARS_STATUS_MAX = SZ_4K, + ND_MAX_MAPPINGS = 32, + + /* mark newly adjusted resources as requiring a label update */ + DPA_RESOURCE_ADJUSTED = 1 << 0, +}; + +extern struct attribute_group nvdimm_bus_attribute_group; +extern struct attribute_group nvdimm_attribute_group; +extern struct attribute_group nd_device_attribute_group; +extern struct attribute_group nd_region_attribute_group; +extern struct attribute_group nd_mapping_attribute_group; + +struct nvdimm; +struct nvdimm_bus_descriptor; +typedef int (*ndctl_fn)(struct nvdimm_bus_descriptor *nd_desc, + struct nvdimm *nvdimm, unsigned int cmd, void *buf, + unsigned int buf_len); + +struct nd_namespace_label; +struct nvdimm_drvdata; +struct nd_mapping { + struct nvdimm *nvdimm; + struct nd_namespace_label **labels; + u64 start; + u64 size; + /* + * @ndd is for private use at region enable / disable time for + * get_ndd() + put_ndd(), all other nd_mapping to ndd + * conversions use to_ndd() which respects enabled state of the + * nvdimm. + */ + struct nvdimm_drvdata *ndd; +}; + +struct nvdimm_bus_descriptor { + const struct attribute_group **attr_groups; + unsigned long dsm_mask; + char *provider_name; + ndctl_fn ndctl; +}; + +struct nd_cmd_desc { + int in_num; + int out_num; + u32 in_sizes[ND_CMD_MAX_ELEM]; + int out_sizes[ND_CMD_MAX_ELEM]; +}; + +struct nd_interleave_set { + u64 cookie; +}; + +struct nd_region_desc { + struct resource *res; + struct nd_mapping *nd_mapping; + u16 num_mappings; + const struct attribute_group **attr_groups; + struct nd_interleave_set *nd_set; + void *provider_data; +}; + +struct nvdimm_bus; +struct device; +struct module; +struct nvdimm_bus *__nvdimm_bus_register(struct device *parent, + struct nvdimm_bus_descriptor *nfit_desc, struct module *module); +#define nvdimm_bus_register(parent, desc) \ + __nvdimm_bus_register(parent, desc, THIS_MODULE) +void nvdimm_bus_unregister(struct nvdimm_bus *nvdimm_bus); +struct nvdimm_bus *to_nvdimm_bus(struct device *dev); +struct nvdimm *to_nvdimm(struct device *dev); +struct nd_region *to_nd_region(struct device *dev); +struct nvdimm_bus_descriptor *to_nd_desc(struct nvdimm_bus *nvdimm_bus); +const char *nvdimm_name(struct nvdimm *nvdimm); +void *nvdimm_provider_data(struct nvdimm *nvdimm); +void *nd_region_provider_data(struct nd_region *nd_region); +struct nvdimm *nvdimm_create(struct nvdimm_bus *nvdimm_bus, void *provider_data, + const struct attribute_group **groups, unsigned long flags, + unsigned long *dsm_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, + const struct nd_cmd_desc *desc, int idx, void *buf); +u32 nd_cmd_out_size(struct nvdimm *nvdimm, int cmd, + const struct nd_cmd_desc *desc, int idx, const u32 *in_field, + const u32 *out_field); +int nvdimm_bus_check_dimm_count(struct nvdimm_bus *nvdimm_bus, int dimm_count); +struct nd_region *nvdimm_pmem_region_create(struct nvdimm_bus *nvdimm_bus, + struct nd_region_desc *ndr_desc); +struct nd_region *nvdimm_blk_region_create(struct nvdimm_bus *nvdimm_bus, + struct nd_region_desc *ndr_desc); +struct nd_region *nvdimm_volatile_region_create(struct nvdimm_bus *nvdimm_bus, + struct nd_region_desc *ndr_desc); +u64 nd_fletcher64(void *addr, size_t len, bool le); +#endif /* __LIBNVDIMM_H__ */ diff --git a/include/linux/nd.h b/include/linux/nd.h new file mode 100644 index 000000000000..23276ea91690 --- /dev/null +++ b/include/linux/nd.h @@ -0,0 +1,98 @@ +/* + * Copyright(c) 2013-2015 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 __LINUX_ND_H__ +#define __LINUX_ND_H__ +#include <linux/ndctl.h> +#include <linux/device.h> + +struct nd_device_driver { + struct device_driver drv; + unsigned long type; + int (*probe)(struct device *dev); + int (*remove)(struct device *dev); +}; + +static inline struct nd_device_driver *to_nd_device_driver( + struct device_driver *drv) +{ + return container_of(drv, struct nd_device_driver, drv); +}; + +/** + * struct nd_namespace_io - infrastructure for loading an nd_pmem instance + * @dev: namespace device created by the nd region driver + * @res: struct resource conversion of a NFIT SPA table + */ +struct nd_namespace_io { + struct device dev; + struct resource res; +}; + +/** + * struct nd_namespace_pmem - namespace device for dimm-backed interleaved memory + * @nsio: device and system physical address range to drive + * @alt_name: namespace name supplied in the dimm label + * @uuid: namespace name supplied in the dimm label + */ +struct nd_namespace_pmem { + struct nd_namespace_io nsio; + char *alt_name; + u8 *uuid; +}; + +/** + * struct nd_namespace_blk - namespace for dimm-bounded persistent memory + * @dev: namespace device creation by the nd region driver + * @alt_name: namespace name supplied in the dimm label + * @uuid: namespace name supplied in the dimm label + * @id: ida allocated id + * @lbasize: blk namespaces have a native sector size when btt not present + * @num_resources: number of dpa extents to claim + * @res: discontiguous dpa extents for given dimm + */ +struct nd_namespace_blk { + struct device dev; + char *alt_name; + u8 *uuid; + int id; + unsigned long lbasize; + int num_resources; + struct resource **res; +}; + +static inline struct nd_namespace_io *to_nd_namespace_io(struct device *dev) +{ + return container_of(dev, struct nd_namespace_io, dev); +} + +static inline struct nd_namespace_pmem *to_nd_namespace_pmem(struct device *dev) +{ + struct nd_namespace_io *nsio = to_nd_namespace_io(dev); + + return container_of(nsio, struct nd_namespace_pmem, nsio); +} + +static inline struct nd_namespace_blk *to_nd_namespace_blk(struct device *dev) +{ + return container_of(dev, struct nd_namespace_blk, dev); +} + +#define MODULE_ALIAS_ND_DEVICE(type) \ + MODULE_ALIAS("nd:t" __stringify(type) "*") +#define ND_DEVICE_MODALIAS_FMT "nd:t%d" + +int __must_check __nd_driver_register(struct nd_device_driver *nd_drv, + struct module *module, const char *mod_name); +#define nd_driver_register(driver) \ + __nd_driver_register(driver, THIS_MODULE, KBUILD_MODNAME) +#endif /* __LINUX_ND_H__ */ diff --git a/include/uapi/linux/Kbuild b/include/uapi/linux/Kbuild index 01cb7c921c28..67a4c60e1deb 100644 --- a/include/uapi/linux/Kbuild +++ b/include/uapi/linux/Kbuild @@ -273,6 +273,7 @@ header-y += ncp_fs.h header-y += ncp.h header-y += ncp_mount.h header-y += ncp_no.h +header-y += ndctl.h header-y += neighbour.h header-y += netconf.h header-y += netdevice.h diff --git a/include/uapi/linux/ndctl.h b/include/uapi/linux/ndctl.h new file mode 100644 index 000000000000..2b94ea2287bb --- /dev/null +++ b/include/uapi/linux/ndctl.h @@ -0,0 +1,197 @@ +/* + * Copyright (c) 2014-2015, 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, + * version 2.1, as published by the Free Software Foundation. + * + * This program is distributed in the hope it will be useful, but WITHOUT ANY + * WARRANTY; without even the implied warranty of MERCHANTABILITY or FITNESS + * FOR A PARTICULAR PURPOSE. See the GNU Lesser General Public License for + * more details. + */ +#ifndef __NDCTL_H__ +#define __NDCTL_H__ + +#include <linux/types.h> + +struct nd_cmd_smart { + __u32 status; + __u8 data[128]; +} __packed; + +struct nd_cmd_smart_threshold { + __u32 status; + __u8 data[8]; +} __packed; + +struct nd_cmd_dimm_flags { + __u32 status; + __u32 flags; +} __packed; + +struct nd_cmd_get_config_size { + __u32 status; + __u32 config_size; + __u32 max_xfer; +} __packed; + +struct nd_cmd_get_config_data_hdr { + __u32 in_offset; + __u32 in_length; + __u32 status; + __u8 out_buf[0]; +} __packed; + +struct nd_cmd_set_config_hdr { + __u32 in_offset; + __u32 in_length; + __u8 in_buf[0]; +} __packed; + +struct nd_cmd_vendor_hdr { + __u32 opcode; + __u32 in_length; + __u8 in_buf[0]; +} __packed; + +struct nd_cmd_vendor_tail { + __u32 status; + __u32 out_length; + __u8 out_buf[0]; +} __packed; + +struct nd_cmd_ars_cap { + __u64 address; + __u64 length; + __u32 status; + __u32 max_ars_out; +} __packed; + +struct nd_cmd_ars_start { + __u64 address; + __u64 length; + __u16 type; + __u8 reserved[6]; + __u32 status; +} __packed; + +struct nd_cmd_ars_status { + __u32 status; + __u32 out_length; + __u64 address; + __u64 length; + __u16 type; + __u32 num_records; + struct nd_ars_record { + __u32 handle; + __u32 flags; + __u64 err_address; + __u64 mask; + } __packed records[0]; +} __packed; + +enum { + ND_CMD_IMPLEMENTED = 0, + + /* bus commands */ + ND_CMD_ARS_CAP = 1, + ND_CMD_ARS_START = 2, + ND_CMD_ARS_STATUS = 3, + + /* per-dimm commands */ + ND_CMD_SMART = 1, + ND_CMD_SMART_THRESHOLD = 2, + ND_CMD_DIMM_FLAGS = 3, + ND_CMD_GET_CONFIG_SIZE = 4, + ND_CMD_GET_CONFIG_DATA = 5, + ND_CMD_SET_CONFIG_DATA = 6, + ND_CMD_VENDOR_EFFECT_LOG_SIZE = 7, + ND_CMD_VENDOR_EFFECT_LOG = 8, + ND_CMD_VENDOR = 9, +}; + +static inline const char *nvdimm_bus_cmd_name(unsigned cmd) +{ + static const char * const names[] = { + [ND_CMD_ARS_CAP] = "ars_cap", + [ND_CMD_ARS_START] = "ars_start", + [ND_CMD_ARS_STATUS] = "ars_status", + }; + + if (cmd < ARRAY_SIZE(names) && names[cmd]) + return names[cmd]; + return "unknown"; +} + +static inline const char *nvdimm_cmd_name(unsigned cmd) +{ + static const char * const names[] = { + [ND_CMD_SMART] = "smart", + [ND_CMD_SMART_THRESHOLD] = "smart_thresh", + [ND_CMD_DIMM_FLAGS] = "flags", + [ND_CMD_GET_CONFIG_SIZE] = "get_size", + [ND_CMD_GET_CONFIG_DATA] = "get_data", + [ND_CMD_SET_CONFIG_DATA] = "set_data", + [ND_CMD_VENDOR_EFFECT_LOG_SIZE] = "effect_size", + [ND_CMD_VENDOR_EFFECT_LOG] = "effect_log", + [ND_CMD_VENDOR] = "vendor", + }; + + if (cmd < ARRAY_SIZE(names) && names[cmd]) + return names[cmd]; + return "unknown"; +} + +#define ND_IOCTL 'N' + +#define ND_IOCTL_SMART _IOWR(ND_IOCTL, ND_CMD_SMART,\ + struct nd_cmd_smart) + +#define ND_IOCTL_SMART_THRESHOLD _IOWR(ND_IOCTL, ND_CMD_SMART_THRESHOLD,\ + struct nd_cmd_smart_threshold) + +#define ND_IOCTL_DIMM_FLAGS _IOWR(ND_IOCTL, ND_CMD_DIMM_FLAGS,\ + struct nd_cmd_dimm_flags) + +#define ND_IOCTL_GET_CONFIG_SIZE _IOWR(ND_IOCTL, ND_CMD_GET_CONFIG_SIZE,\ + struct nd_cmd_get_config_size) + +#define ND_IOCTL_GET_CONFIG_DATA _IOWR(ND_IOCTL, ND_CMD_GET_CONFIG_DATA,\ + struct nd_cmd_get_config_data_hdr) + +#define ND_IOCTL_SET_CONFIG_DATA _IOWR(ND_IOCTL, ND_CMD_SET_CONFIG_DATA,\ + struct nd_cmd_set_config_hdr) + +#define ND_IOCTL_VENDOR _IOWR(ND_IOCTL, ND_CMD_VENDOR,\ + struct nd_cmd_vendor_hdr) + +#define ND_IOCTL_ARS_CAP _IOWR(ND_IOCTL, ND_CMD_ARS_CAP,\ + struct nd_cmd_ars_cap) + +#define ND_IOCTL_ARS_START _IOWR(ND_IOCTL, ND_CMD_ARS_START,\ + struct nd_cmd_ars_start) + +#define ND_IOCTL_ARS_STATUS _IOWR(ND_IOCTL, ND_CMD_ARS_STATUS,\ + struct nd_cmd_ars_status) + +#define ND_DEVICE_DIMM 1 /* nd_dimm: container for "config data" */ +#define ND_DEVICE_REGION_PMEM 2 /* nd_region: (parent of PMEM namespaces) */ +#define ND_DEVICE_REGION_BLK 3 /* nd_region: (parent of BLK namespaces) */ +#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) */ + +enum nd_driver_flags { + ND_DRIVER_DIMM = 1 << ND_DEVICE_DIMM, + ND_DRIVER_REGION_PMEM = 1 << ND_DEVICE_REGION_PMEM, + ND_DRIVER_REGION_BLK = 1 << ND_DEVICE_REGION_BLK, + 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, +}; + +enum { + ND_MIN_NAMESPACE_SIZE = 0x00400000, +}; +#endif /* __NDCTL_H__ */ |