From baa51277cf5dc844089ea2f6e0f78b1c5ca665d8 Mon Sep 17 00:00:00 2001 From: Dan Williams Date: Tue, 5 Apr 2016 17:40:52 -0700 Subject: libnvdimm, test: add mock SMART data payload Provide simulated SMART data to enable the ndctl implementation of SMART data retrieval and parsing. The payload is defined here, "Section 4.1 SMART and Health Info (Function Index 1)": http://pmem.io/documents/NVDIMM_DSM_Interface_Example.pdf Signed-off-by: Dan Williams --- include/uapi/linux/ndctl.h | 36 +++++++++++++++++++++++++++++++++++- 1 file changed, 35 insertions(+), 1 deletion(-) (limited to 'include/uapi') diff --git a/include/uapi/linux/ndctl.h b/include/uapi/linux/ndctl.h index 7cc28ab05b87..59c61e018a86 100644 --- a/include/uapi/linux/ndctl.h +++ b/include/uapi/linux/ndctl.h @@ -1,5 +1,5 @@ /* - * Copyright (c) 2014-2015, Intel Corporation. + * Copyright (c) 2014-2016, Intel Corporation. * * This program is free software; you can redistribute it and/or modify it * under the terms and conditions of the GNU Lesser General Public License, @@ -20,11 +20,45 @@ struct nd_cmd_smart { __u8 data[128]; } __packed; +#define ND_SMART_HEALTH_VALID (1 << 0) +#define ND_SMART_TEMP_VALID (1 << 1) +#define ND_SMART_SPARES_VALID (1 << 2) +#define ND_SMART_ALARM_VALID (1 << 3) +#define ND_SMART_USED_VALID (1 << 4) +#define ND_SMART_SHUTDOWN_VALID (1 << 5) +#define ND_SMART_VENDOR_VALID (1 << 6) +#define ND_SMART_TEMP_TRIP (1 << 0) +#define ND_SMART_SPARE_TRIP (1 << 1) +#define ND_SMART_NON_CRITICAL_HEALTH (1 << 0) +#define ND_SMART_CRITICAL_HEALTH (1 << 1) +#define ND_SMART_FATAL_HEALTH (1 << 2) + +struct nd_smart_payload { + __u32 flags; + __u8 reserved0[4]; + __u8 health; + __u16 temperature; + __u8 spares; + __u8 alarm_flags; + __u8 life_used; + __u8 shutdown_state; + __u8 reserved1; + __u32 vendor_size; + __u8 vendor_data[108]; +} __packed; + struct nd_cmd_smart_threshold { __u32 status; __u8 data[8]; } __packed; +struct nd_smart_threshold_payload { + __u16 alarm_control; + __u16 temperature; + __u8 spares; + __u8 reserved[3]; +} __packed; + struct nd_cmd_dimm_flags { __u32 status; __u32 flags; -- cgit v1.2.3 From 31eca76ba2fc988bf88f16fcf763a0ec4068cd30 Mon Sep 17 00:00:00 2001 From: Dan Williams Date: Thu, 28 Apr 2016 16:23:43 -0700 Subject: nfit, libnvdimm: limited/whitelisted dimm command marshaling mechanism There are currently 4 known similar but incompatible definitions of the command sets that can be sent to an NVDIMM through ACPI. It is also clear that future platform generations (ACPI or not) will continue to revise and extend the DIMM command set as new devices and use cases arrive. It is obviously untenable to continue to proliferate divergence of these command definitions, and to that end a standardization process has begun to provide for a unified specification. However, that leaves a problem about what to do with this first generation where vendors are already shipping divergence. The Linux kernel can support these initial diverged platforms without giving platform-firmware free reign to continue to diverge and compound kernel maintenance overhead. The kernel implementation can encourage standardization in two ways: 1/ Require that any function code that userspace wants to send be explicitly white-listed in the implementation. For ACPI this means function codes marked as supported by acpi_check_dsm() may only be invoked if they appear in the white-list. A function must be publicly documented before it is added to the white-list. 2/ The above restrictions can be trivially bypassed by using the "vendor-specific" payload command. However, since vendor-specific commands are by definition not publicly documented and have the potential to corrupt the kernel's view of the dimm state, we provide a toggle to disable vendor-specific operations. Enabling undefined behavior is a policy decision that can be made by the platform owner and encourages firmware implementations to choose public over private command implementations. Based on an initial patch from Jerry Hoemann Cc: Jerry Hoemann Cc: Christoph Hellwig Signed-off-by: Dan Williams --- drivers/acpi/nfit.c | 101 ++++++++++++++++++++++++++++++++++++++------- drivers/acpi/nfit.h | 14 ++++++- drivers/nvdimm/bus.c | 39 +++++++++++++++++ include/uapi/linux/ndctl.h | 42 +++++++++++++++++++ 4 files changed, 179 insertions(+), 17 deletions(-) (limited to 'include/uapi') diff --git a/drivers/acpi/nfit.c b/drivers/acpi/nfit.c index 1b98e9dc6138..b85a46873228 100644 --- a/drivers/acpi/nfit.c +++ b/drivers/acpi/nfit.c @@ -171,33 +171,46 @@ static int acpi_nfit_ctl(struct nvdimm_bus_descriptor *nd_desc, unsigned int buf_len, int *cmd_rc) { struct acpi_nfit_desc *acpi_desc = to_acpi_nfit_desc(nd_desc); - const struct nd_cmd_desc *desc = NULL; union acpi_object in_obj, in_buf, *out_obj; + const struct nd_cmd_desc *desc = NULL; struct device *dev = acpi_desc->dev; + struct nd_cmd_pkg *call_pkg = NULL; const char *cmd_name, *dimm_name; - unsigned long cmd_mask; + unsigned long cmd_mask, dsm_mask; acpi_handle handle; + unsigned int func; const u8 *uuid; u32 offset; int rc, i; + func = cmd; + if (cmd == ND_CMD_CALL) { + call_pkg = buf; + func = call_pkg->nd_command; + } + if (nvdimm) { struct nfit_mem *nfit_mem = nvdimm_provider_data(nvdimm); struct acpi_device *adev = nfit_mem->adev; if (!adev) return -ENOTTY; + if (call_pkg && nfit_mem->family != call_pkg->nd_family) + return -ENOTTY; + dimm_name = nvdimm_name(nvdimm); cmd_name = nvdimm_cmd_name(cmd); cmd_mask = nvdimm_cmd_mask(nvdimm); + dsm_mask = nfit_mem->dsm_mask; desc = nd_cmd_dimm_desc(cmd); - uuid = to_nfit_uuid(NFIT_DEV_DIMM); + uuid = to_nfit_uuid(nfit_mem->family); handle = adev->handle; } else { struct acpi_device *adev = to_acpi_dev(acpi_desc); cmd_name = nvdimm_bus_cmd_name(cmd); cmd_mask = nd_desc->cmd_mask; + dsm_mask = cmd_mask; desc = nd_cmd_bus_desc(cmd); uuid = to_nfit_uuid(NFIT_DEV_BUS); handle = adev->handle; @@ -207,7 +220,7 @@ static int acpi_nfit_ctl(struct nvdimm_bus_descriptor *nd_desc, if (!desc || (cmd && (desc->out_num + desc->in_num == 0))) return -ENOTTY; - if (!test_bit(cmd, &cmd_mask)) + if (!test_bit(cmd, &cmd_mask) || !test_bit(func, &dsm_mask)) return -ENOTTY; in_obj.type = ACPI_TYPE_PACKAGE; @@ -222,21 +235,44 @@ static int acpi_nfit_ctl(struct nvdimm_bus_descriptor *nd_desc, in_buf.buffer.length += nd_cmd_in_size(nvdimm, cmd, desc, i, buf); + if (call_pkg) { + /* skip over package wrapper */ + in_buf.buffer.pointer = (void *) &call_pkg->nd_payload; + in_buf.buffer.length = call_pkg->nd_size_in; + } + if (IS_ENABLED(CONFIG_ACPI_NFIT_DEBUG)) { - dev_dbg(dev, "%s:%s cmd: %s input length: %d\n", __func__, - dimm_name, cmd_name, in_buf.buffer.length); - print_hex_dump_debug(cmd_name, DUMP_PREFIX_OFFSET, 4, - 4, in_buf.buffer.pointer, min_t(u32, 128, - in_buf.buffer.length), true); + dev_dbg(dev, "%s:%s cmd: %d: func: %d input length: %d\n", + __func__, dimm_name, cmd, func, + in_buf.buffer.length); + print_hex_dump_debug("nvdimm in ", DUMP_PREFIX_OFFSET, 4, 4, + in_buf.buffer.pointer, + min_t(u32, 256, in_buf.buffer.length), true); } - out_obj = acpi_evaluate_dsm(handle, uuid, 1, cmd, &in_obj); + out_obj = acpi_evaluate_dsm(handle, uuid, 1, func, &in_obj); if (!out_obj) { dev_dbg(dev, "%s:%s _DSM failed cmd: %s\n", __func__, dimm_name, cmd_name); return -EINVAL; } + if (call_pkg) { + call_pkg->nd_fw_size = out_obj->buffer.length; + memcpy(call_pkg->nd_payload + call_pkg->nd_size_in, + out_obj->buffer.pointer, + min(call_pkg->nd_fw_size, call_pkg->nd_size_out)); + + ACPI_FREE(out_obj); + /* + * Need to support FW function w/o known size in advance. + * Caller can determine required size based upon nd_fw_size. + * If we return an error (like elsewhere) then caller wouldn't + * be able to rely upon data returned to make calculation. + */ + return 0; + } + if (out_obj->package.type != ACPI_TYPE_BUFFER) { dev_dbg(dev, "%s:%s unexpected output object type cmd: %s type: %d\n", __func__, dimm_name, cmd_name, out_obj->type); @@ -923,11 +959,13 @@ static int acpi_nfit_add_dimm(struct acpi_nfit_desc *acpi_desc, { struct acpi_device *adev, *adev_dimm; struct device *dev = acpi_desc->dev; - const u8 *uuid = to_nfit_uuid(NFIT_DEV_DIMM); + unsigned long dsm_mask; + const u8 *uuid; int i; /* nfit test assumes 1:1 relationship between commands and dsms */ nfit_mem->dsm_mask = acpi_desc->dimm_cmd_force_en; + nfit_mem->family = NVDIMM_FAMILY_INTEL; adev = to_acpi_dev(acpi_desc); if (!adev) return 0; @@ -940,7 +978,31 @@ static int acpi_nfit_add_dimm(struct acpi_nfit_desc *acpi_desc, return force_enable_dimms ? 0 : -ENODEV; } - for (i = ND_CMD_SMART; i <= ND_CMD_VENDOR; i++) + /* + * Until standardization materializes we need to consider up to 3 + * different command sets. Note, that checking for function0 (bit0) + * tells us if any commands are reachable through this uuid. + */ + for (i = NVDIMM_FAMILY_INTEL; i <= NVDIMM_FAMILY_HPE2; i++) + if (acpi_check_dsm(adev_dimm->handle, to_nfit_uuid(i), 1, 1)) + break; + + /* limit the supported commands to those that are publicly documented */ + nfit_mem->family = i; + if (nfit_mem->family == NVDIMM_FAMILY_INTEL) + dsm_mask = 0x3fe; + else if (nfit_mem->family == NVDIMM_FAMILY_HPE1) + dsm_mask = 0x1c3c76; + else if (nfit_mem->family == NVDIMM_FAMILY_HPE2) + dsm_mask = 0x1fe; + else { + dev_err(dev, "unknown dimm command family\n"); + nfit_mem->family = -1; + return force_enable_dimms ? 0 : -ENODEV; + } + + uuid = to_nfit_uuid(nfit_mem->family); + for_each_set_bit(i, &dsm_mask, BITS_PER_LONG) if (acpi_check_dsm(adev_dimm->handle, uuid, 1, 1ULL << i)) set_bit(i, &nfit_mem->dsm_mask); @@ -953,8 +1015,8 @@ static int acpi_nfit_register_dimms(struct acpi_nfit_desc *acpi_desc) int dimm_count = 0; list_for_each_entry(nfit_mem, &acpi_desc->dimms, list) { + unsigned long flags = 0, cmd_mask; struct nvdimm *nvdimm; - unsigned long flags = 0; u32 device_handle; u16 mem_flags; int rc; @@ -978,12 +1040,17 @@ static int acpi_nfit_register_dimms(struct acpi_nfit_desc *acpi_desc) continue; /* - * For now there is 1:1 relationship between cmd_mask and - * dsm_mask. + * TODO: provide translation for non-NVDIMM_FAMILY_INTEL + * devices (i.e. from nd_cmd to acpi_dsm) to standardize the + * userspace interface. */ + cmd_mask = 1UL << ND_CMD_CALL; + if (nfit_mem->family == NVDIMM_FAMILY_INTEL) + cmd_mask |= nfit_mem->dsm_mask; + nvdimm = nvdimm_create(acpi_desc->nvdimm_bus, nfit_mem, acpi_nfit_dimm_attribute_groups, - flags, nfit_mem->dsm_mask); + flags, cmd_mask); if (!nvdimm) return -ENOMEM; @@ -2468,6 +2535,8 @@ static __init int nfit_init(void) acpi_str_to_uuid(UUID_PERSISTENT_VIRTUAL_CD, nfit_uuid[NFIT_SPA_PCD]); acpi_str_to_uuid(UUID_NFIT_BUS, nfit_uuid[NFIT_DEV_BUS]); acpi_str_to_uuid(UUID_NFIT_DIMM, nfit_uuid[NFIT_DEV_DIMM]); + acpi_str_to_uuid(UUID_NFIT_DIMM_N_HPE1, nfit_uuid[NFIT_DEV_DIMM_N_HPE1]); + acpi_str_to_uuid(UUID_NFIT_DIMM_N_HPE2, nfit_uuid[NFIT_DEV_DIMM_N_HPE2]); nfit_wq = create_singlethread_workqueue("nfit"); if (!nfit_wq) diff --git a/drivers/acpi/nfit.h b/drivers/acpi/nfit.h index 332ee6f01662..f82fda55b6de 100644 --- a/drivers/acpi/nfit.h +++ b/drivers/acpi/nfit.h @@ -21,13 +21,25 @@ #include #include +/* ACPI 6.1 */ #define UUID_NFIT_BUS "2f10e7a4-9e91-11e4-89d3-123b93f75cba" + +/* http://pmem.io/documents/NVDIMM_DSM_Interface_Example.pdf */ #define UUID_NFIT_DIMM "4309ac30-0d11-11e4-9191-0800200c9a66" + +/* https://github.com/HewlettPackard/hpe-nvm/blob/master/Documentation/ */ +#define UUID_NFIT_DIMM_N_HPE1 "9002c334-acf3-4c0e-9642-a235f0d53bc6" +#define UUID_NFIT_DIMM_N_HPE2 "5008664b-b758-41a0-a03c-27c2f2d04f7e" + #define ACPI_NFIT_MEM_FAILED_MASK (ACPI_NFIT_MEM_SAVE_FAILED \ | ACPI_NFIT_MEM_RESTORE_FAILED | ACPI_NFIT_MEM_FLUSH_FAILED \ | ACPI_NFIT_MEM_NOT_ARMED) enum nfit_uuids { + /* for simplicity alias the uuid index with the family id */ + NFIT_DEV_DIMM = NVDIMM_FAMILY_INTEL, + NFIT_DEV_DIMM_N_HPE1 = NVDIMM_FAMILY_HPE1, + NFIT_DEV_DIMM_N_HPE2 = NVDIMM_FAMILY_HPE2, NFIT_SPA_VOLATILE, NFIT_SPA_PM, NFIT_SPA_DCR, @@ -37,7 +49,6 @@ enum nfit_uuids { NFIT_SPA_PDISK, NFIT_SPA_PCD, NFIT_DEV_BUS, - NFIT_DEV_DIMM, NFIT_UUID_MAX, }; @@ -110,6 +121,7 @@ struct nfit_mem { struct list_head list; struct acpi_device *adev; unsigned long dsm_mask; + int family; }; struct acpi_nfit_desc { diff --git a/drivers/nvdimm/bus.c b/drivers/nvdimm/bus.c index cb2042a12b76..395a9fbbc69d 100644 --- a/drivers/nvdimm/bus.c +++ b/drivers/nvdimm/bus.c @@ -439,6 +439,12 @@ static const struct nd_cmd_desc __nd_cmd_dimm_descs[] = { .out_num = 3, .out_sizes = { 4, 4, UINT_MAX, }, }, + [ND_CMD_CALL] = { + .in_num = 2, + .in_sizes = { sizeof(struct nd_cmd_pkg), UINT_MAX, }, + .out_num = 1, + .out_sizes = { UINT_MAX, }, + }, }; const struct nd_cmd_desc *nd_cmd_dimm_desc(int cmd) @@ -473,6 +479,12 @@ static const struct nd_cmd_desc __nd_cmd_bus_descs[] = { .out_num = 3, .out_sizes = { 4, 4, 8, }, }, + [ND_CMD_CALL] = { + .in_num = 2, + .in_sizes = { sizeof(struct nd_cmd_pkg), UINT_MAX, }, + .out_num = 1, + .out_sizes = { UINT_MAX, }, + }, }; const struct nd_cmd_desc *nd_cmd_bus_desc(int cmd) @@ -500,6 +512,10 @@ u32 nd_cmd_in_size(struct nvdimm *nvdimm, int cmd, struct nd_cmd_vendor_hdr *hdr = buf; return hdr->in_length; + } else if (cmd == ND_CMD_CALL) { + struct nd_cmd_pkg *pkg = buf; + + return pkg->nd_size_in; } return UINT_MAX; @@ -522,6 +538,12 @@ u32 nd_cmd_out_size(struct nvdimm *nvdimm, int cmd, return out_field[1]; else if (!nvdimm && cmd == ND_CMD_ARS_STATUS && idx == 2) return out_field[1] - 8; + else if (cmd == ND_CMD_CALL) { + struct nd_cmd_pkg *pkg = (struct nd_cmd_pkg *) in_field; + + return pkg->nd_size_out; + } + return UINT_MAX; } @@ -588,6 +610,7 @@ static int __nd_ioctl(struct nvdimm_bus *nvdimm_bus, struct nvdimm *nvdimm, unsigned int cmd = _IOC_NR(ioctl_cmd); void __user *p = (void __user *) arg; struct device *dev = &nvdimm_bus->dev; + struct nd_cmd_pkg pkg; const char *cmd_name, *dimm_name; unsigned long cmd_mask; void *buf; @@ -605,6 +628,11 @@ static int __nd_ioctl(struct nvdimm_bus *nvdimm_bus, struct nvdimm *nvdimm, dimm_name = "bus"; } + if (cmd == ND_CMD_CALL) { + if (copy_from_user(&pkg, p, sizeof(pkg))) + return -EFAULT; + } + if (!desc || (desc->out_num + desc->in_num == 0) || !test_bit(cmd, &cmd_mask)) return -ENOTTY; @@ -616,6 +644,7 @@ static int __nd_ioctl(struct nvdimm_bus *nvdimm_bus, struct nvdimm *nvdimm, case ND_CMD_SET_CONFIG_DATA: case ND_CMD_ARS_START: case ND_CMD_CLEAR_ERROR: + case ND_CMD_CALL: dev_dbg(&nvdimm_bus->dev, "'%s' command while read-only.\n", nvdimm ? nvdimm_cmd_name(cmd) : nvdimm_bus_cmd_name(cmd)); @@ -643,6 +672,16 @@ static int __nd_ioctl(struct nvdimm_bus *nvdimm_bus, struct nvdimm *nvdimm, in_len += in_size; } + if (cmd == ND_CMD_CALL) { + dev_dbg(dev, "%s:%s, idx: %llu, in: %zu, out: %zu, len %zu\n", + __func__, dimm_name, pkg.nd_command, + in_len, out_len, buf_len); + + for (i = 0; i < ARRAY_SIZE(pkg.nd_reserved2); i++) + if (pkg.nd_reserved2[i]) + return -EINVAL; + } + /* process an output envelope */ for (i = 0; i < desc->out_num; i++) { u32 out_size = nd_cmd_out_size(nvdimm, cmd, desc, i, diff --git a/include/uapi/linux/ndctl.h b/include/uapi/linux/ndctl.h index 7cc28ab05b87..45daa0be5ff9 100644 --- a/include/uapi/linux/ndctl.h +++ b/include/uapi/linux/ndctl.h @@ -125,6 +125,7 @@ enum { ND_CMD_VENDOR_EFFECT_LOG_SIZE = 7, ND_CMD_VENDOR_EFFECT_LOG = 8, ND_CMD_VENDOR = 9, + ND_CMD_CALL = 10, }; enum { @@ -158,6 +159,7 @@ static inline const char *nvdimm_cmd_name(unsigned cmd) [ND_CMD_VENDOR_EFFECT_LOG_SIZE] = "effect_size", [ND_CMD_VENDOR_EFFECT_LOG] = "effect_log", [ND_CMD_VENDOR] = "vendor", + [ND_CMD_CALL] = "cmd_call", }; if (cmd < ARRAY_SIZE(names) && names[cmd]) @@ -224,4 +226,44 @@ enum ars_masks { ARS_STATUS_MASK = 0x0000FFFF, ARS_EXT_STATUS_SHIFT = 16, }; + +/* + * struct nd_cmd_pkg + * + * is a wrapper to a quasi pass thru interface for invoking firmware + * associated with nvdimms. + * + * INPUT PARAMETERS + * + * nd_family corresponds to the firmware (e.g. DSM) interface. + * + * nd_command are the function index advertised by the firmware. + * + * nd_size_in is the size of the input parameters being passed to firmware + * + * OUTPUT PARAMETERS + * + * nd_fw_size is the size of the data firmware wants to return for + * the call. If nd_fw_size is greater than size of nd_size_out, only + * the first nd_size_out bytes are returned. + */ + +struct nd_cmd_pkg { + __u64 nd_family; /* family of commands */ + __u64 nd_command; + __u32 nd_size_in; /* INPUT: size of input args */ + __u32 nd_size_out; /* INPUT: size of payload */ + __u32 nd_reserved2[9]; /* reserved must be zero */ + __u32 nd_fw_size; /* OUTPUT: size fw wants to return */ + unsigned char nd_payload[]; /* Contents of call */ +}; + +/* These NVDIMM families represent pre-standardization command sets */ +#define NVDIMM_FAMILY_INTEL 0 +#define NVDIMM_FAMILY_HPE1 1 +#define NVDIMM_FAMILY_HPE2 2 + +#define ND_IOCTL_CALL _IOWR(ND_IOCTL, ND_CMD_CALL,\ + struct nd_cmd_pkg) + #endif /* __NDCTL_H__ */ -- cgit v1.2.3 From cd03412a51ac4cb3001a8cdfae4560c9602f3387 Mon Sep 17 00:00:00 2001 From: Dan Williams Date: Fri, 11 Mar 2016 10:15:36 -0800 Subject: libnvdimm, dax: introduce device-dax infrastructure Device DAX is the device-centric analogue of Filesystem DAX (CONFIG_FS_DAX). It allows persistent memory ranges to be allocated and mapped without need of an intervening file system. This initial infrastructure arranges for a libnvdimm pfn-device to be represented as a different device-type so that it can be attached to a driver other than the pmem driver. Signed-off-by: Dan Williams --- drivers/nvdimm/Kconfig | 13 ++++++ drivers/nvdimm/Makefile | 1 + drivers/nvdimm/bus.c | 4 ++ drivers/nvdimm/claim.c | 2 + drivers/nvdimm/dax_devs.c | 99 +++++++++++++++++++++++++++++++++++++++ drivers/nvdimm/namespace_devs.c | 19 +++++++- drivers/nvdimm/nd-core.h | 1 + drivers/nvdimm/nd.h | 25 ++++++++++ drivers/nvdimm/pfn_devs.c | 100 +++++++++++++++++++++++++++------------- drivers/nvdimm/region.c | 2 + drivers/nvdimm/region_devs.c | 29 ++++++++++++ include/uapi/linux/ndctl.h | 2 + tools/testing/nvdimm/Kbuild | 1 + 13 files changed, 264 insertions(+), 34 deletions(-) create mode 100644 drivers/nvdimm/dax_devs.c (limited to 'include/uapi') diff --git a/drivers/nvdimm/Kconfig b/drivers/nvdimm/Kconfig index 53c11621d5b1..7c8a3bf07884 100644 --- a/drivers/nvdimm/Kconfig +++ b/drivers/nvdimm/Kconfig @@ -88,4 +88,17 @@ config NVDIMM_PFN Select Y if unsure +config NVDIMM_DAX + bool "NVDIMM DAX: Raw access to persistent memory" + default LIBNVDIMM + depends on NVDIMM_PFN + help + Support raw device dax access to a persistent memory + namespace. For environments that want to hard partition + peristent memory, this capability provides a mechanism to + sub-divide a namespace into character devices that can only be + accessed via DAX (mmap(2)). + + Select Y if unsure + endif diff --git a/drivers/nvdimm/Makefile b/drivers/nvdimm/Makefile index ea84d3c4e8e5..909554c3f955 100644 --- a/drivers/nvdimm/Makefile +++ b/drivers/nvdimm/Makefile @@ -23,3 +23,4 @@ libnvdimm-y += label.o libnvdimm-$(CONFIG_ND_CLAIM) += claim.o libnvdimm-$(CONFIG_BTT) += btt_devs.o libnvdimm-$(CONFIG_NVDIMM_PFN) += pfn_devs.o +libnvdimm-$(CONFIG_NVDIMM_DAX) += dax_devs.o diff --git a/drivers/nvdimm/bus.c b/drivers/nvdimm/bus.c index 19f822d7f652..97589e3cb852 100644 --- a/drivers/nvdimm/bus.c +++ b/drivers/nvdimm/bus.c @@ -40,6 +40,8 @@ static int to_nd_device_type(struct device *dev) return ND_DEVICE_REGION_PMEM; else if (is_nd_blk(dev)) return ND_DEVICE_REGION_BLK; + else if (is_nd_dax(dev)) + return ND_DEVICE_DAX_PMEM; else if (is_nd_pmem(dev->parent) || is_nd_blk(dev->parent)) return nd_region_to_nstype(to_nd_region(dev->parent)); @@ -246,6 +248,8 @@ static void nd_async_device_unregister(void *d, async_cookie_t cookie) void __nd_device_register(struct device *dev) { + if (!dev) + return; dev->bus = &nvdimm_bus_type; get_device(dev); async_schedule_domain(nd_async_device_register, dev, diff --git a/drivers/nvdimm/claim.c b/drivers/nvdimm/claim.c index 6bbd0a36994a..5f53db59a058 100644 --- a/drivers/nvdimm/claim.c +++ b/drivers/nvdimm/claim.c @@ -85,6 +85,8 @@ static bool is_idle(struct device *dev, struct nd_namespace_common *ndns) seed = nd_region->btt_seed; else if (is_nd_pfn(dev)) seed = nd_region->pfn_seed; + else if (is_nd_dax(dev)) + seed = nd_region->dax_seed; if (seed == dev || ndns || dev->driver) return false; diff --git a/drivers/nvdimm/dax_devs.c b/drivers/nvdimm/dax_devs.c new file mode 100644 index 000000000000..f90f7549e7f4 --- /dev/null +++ b/drivers/nvdimm/dax_devs.c @@ -0,0 +1,99 @@ +/* + * Copyright(c) 2013-2016 Intel Corporation. All rights reserved. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of version 2 of the GNU General Public License as + * published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, but + * WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU + * General Public License for more details. + */ +#include +#include +#include +#include +#include "nd-core.h" +#include "nd.h" + +static void nd_dax_release(struct device *dev) +{ + struct nd_region *nd_region = to_nd_region(dev->parent); + struct nd_dax *nd_dax = to_nd_dax(dev); + struct nd_pfn *nd_pfn = &nd_dax->nd_pfn; + + dev_dbg(dev, "%s\n", __func__); + nd_detach_ndns(dev, &nd_pfn->ndns); + ida_simple_remove(&nd_region->dax_ida, nd_pfn->id); + kfree(nd_pfn->uuid); + kfree(nd_dax); +} + +static struct device_type nd_dax_device_type = { + .name = "nd_dax", + .release = nd_dax_release, +}; + +bool is_nd_dax(struct device *dev) +{ + return dev ? dev->type == &nd_dax_device_type : false; +} +EXPORT_SYMBOL(is_nd_dax); + +struct nd_dax *to_nd_dax(struct device *dev) +{ + struct nd_dax *nd_dax = container_of(dev, struct nd_dax, nd_pfn.dev); + + WARN_ON(!is_nd_dax(dev)); + return nd_dax; +} +EXPORT_SYMBOL(to_nd_dax); + +static const struct attribute_group *nd_dax_attribute_groups[] = { + &nd_pfn_attribute_group, + &nd_device_attribute_group, + &nd_numa_attribute_group, + NULL, +}; + +static struct nd_dax *nd_dax_alloc(struct nd_region *nd_region) +{ + struct nd_pfn *nd_pfn; + struct nd_dax *nd_dax; + struct device *dev; + + nd_dax = kzalloc(sizeof(*nd_dax), GFP_KERNEL); + if (!nd_dax) + return NULL; + + nd_pfn = &nd_dax->nd_pfn; + nd_pfn->id = ida_simple_get(&nd_region->dax_ida, 0, 0, GFP_KERNEL); + if (nd_pfn->id < 0) { + kfree(nd_dax); + return NULL; + } + + dev = &nd_pfn->dev; + dev_set_name(dev, "dax%d.%d", nd_region->id, nd_pfn->id); + dev->groups = nd_dax_attribute_groups; + dev->type = &nd_dax_device_type; + dev->parent = &nd_region->dev; + + return nd_dax; +} + +struct device *nd_dax_create(struct nd_region *nd_region) +{ + struct device *dev = NULL; + struct nd_dax *nd_dax; + + if (!is_nd_pmem(&nd_region->dev)) + return NULL; + + nd_dax = nd_dax_alloc(nd_region); + if (nd_dax) + dev = nd_pfn_devinit(&nd_dax->nd_pfn, NULL); + __nd_device_register(dev); + return dev; +} diff --git a/drivers/nvdimm/namespace_devs.c b/drivers/nvdimm/namespace_devs.c index e5ad5162bf34..c5e3196c45b0 100644 --- a/drivers/nvdimm/namespace_devs.c +++ b/drivers/nvdimm/namespace_devs.c @@ -1288,6 +1288,8 @@ static ssize_t mode_show(struct device *dev, mode = "safe"; else if (claim && is_nd_pfn(claim)) mode = "memory"; + else if (claim && is_nd_dax(claim)) + mode = "dax"; else if (!claim && pmem_should_map_pages(dev)) mode = "memory"; else @@ -1379,14 +1381,17 @@ struct nd_namespace_common *nvdimm_namespace_common_probe(struct device *dev) { struct nd_btt *nd_btt = is_nd_btt(dev) ? to_nd_btt(dev) : NULL; struct nd_pfn *nd_pfn = is_nd_pfn(dev) ? to_nd_pfn(dev) : NULL; + struct nd_dax *nd_dax = is_nd_dax(dev) ? to_nd_dax(dev) : NULL; struct nd_namespace_common *ndns = NULL; resource_size_t size; - if (nd_btt || nd_pfn) { + if (nd_btt || nd_pfn || nd_dax) { if (nd_btt) ndns = nd_btt->ndns; else if (nd_pfn) ndns = nd_pfn->ndns; + else if (nd_dax) + ndns = nd_dax->nd_pfn.ndns; if (!ndns) return ERR_PTR(-ENODEV); @@ -1779,6 +1784,18 @@ void nd_region_create_blk_seed(struct nd_region *nd_region) nd_device_register(nd_region->ns_seed); } +void nd_region_create_dax_seed(struct nd_region *nd_region) +{ + WARN_ON(!is_nvdimm_bus_locked(&nd_region->dev)); + nd_region->dax_seed = nd_dax_create(nd_region); + /* + * Seed creation failures are not fatal, provisioning is simply + * disabled until memory becomes available + */ + if (!nd_region->dax_seed) + dev_err(&nd_region->dev, "failed to create dax namespace\n"); +} + void nd_region_create_pfn_seed(struct nd_region *nd_region) { WARN_ON(!is_nvdimm_bus_locked(&nd_region->dev)); diff --git a/drivers/nvdimm/nd-core.h b/drivers/nvdimm/nd-core.h index 1d1500f3d8b5..cb65308c0329 100644 --- a/drivers/nvdimm/nd-core.h +++ b/drivers/nvdimm/nd-core.h @@ -54,6 +54,7 @@ struct nd_region; void nd_region_create_blk_seed(struct nd_region *nd_region); void nd_region_create_btt_seed(struct nd_region *nd_region); void nd_region_create_pfn_seed(struct nd_region *nd_region); +void nd_region_create_dax_seed(struct nd_region *nd_region); void nd_region_disable(struct nvdimm_bus *nvdimm_bus, struct device *dev); int nvdimm_bus_create_ndctl(struct nvdimm_bus *nvdimm_bus); void nvdimm_bus_destroy_ndctl(struct nvdimm_bus *nvdimm_bus); diff --git a/drivers/nvdimm/nd.h b/drivers/nvdimm/nd.h index 6c36509662e4..46910b8f32b1 100644 --- a/drivers/nvdimm/nd.h +++ b/drivers/nvdimm/nd.h @@ -101,10 +101,12 @@ struct nd_region { struct ida ns_ida; struct ida btt_ida; struct ida pfn_ida; + struct ida dax_ida; unsigned long flags; struct device *ns_seed; struct device *btt_seed; struct device *pfn_seed; + struct device *dax_seed; u16 ndr_mappings; u64 ndr_size; u64 ndr_start; @@ -161,6 +163,10 @@ struct nd_pfn { struct nd_namespace_common *ndns; }; +struct nd_dax { + struct nd_pfn nd_pfn; +}; + enum nd_async_mode { ND_SYNC, ND_ASYNC, @@ -224,7 +230,10 @@ struct nd_pfn *to_nd_pfn(struct device *dev); int nd_pfn_probe(struct device *dev, struct nd_namespace_common *ndns); bool is_nd_pfn(struct device *dev); struct device *nd_pfn_create(struct nd_region *nd_region); +struct device *nd_pfn_devinit(struct nd_pfn *nd_pfn, + struct nd_namespace_common *ndns); int nd_pfn_validate(struct nd_pfn *nd_pfn); +extern struct attribute_group nd_pfn_attribute_group; #else static inline int nd_pfn_probe(struct device *dev, struct nd_namespace_common *ndns) @@ -248,6 +257,22 @@ static inline int nd_pfn_validate(struct nd_pfn *nd_pfn) } #endif +struct nd_dax *to_nd_dax(struct device *dev); +#if IS_ENABLED(CONFIG_NVDIMM_DAX) +bool is_nd_dax(struct device *dev); +struct device *nd_dax_create(struct nd_region *nd_region); +#else +static inline bool is_nd_dax(struct device *dev) +{ + return false; +} + +static inline struct device *nd_dax_create(struct nd_region *nd_region) +{ + return NULL; +} +#endif + struct nd_region *to_nd_region(struct device *dev); int nd_region_to_nstype(struct nd_region *nd_region); int nd_region_register_namespaces(struct nd_region *nd_region, int *err); diff --git a/drivers/nvdimm/pfn_devs.c b/drivers/nvdimm/pfn_devs.c index e8693fe65e49..6ade2eb7615d 100644 --- a/drivers/nvdimm/pfn_devs.c +++ b/drivers/nvdimm/pfn_devs.c @@ -1,5 +1,5 @@ /* - * Copyright(c) 2013-2015 Intel Corporation. All rights reserved. + * Copyright(c) 2013-2016 Intel Corporation. All rights reserved. * * This program is free software; you can redistribute it and/or modify * it under the terms of version 2 of the GNU General Public License as @@ -54,10 +54,29 @@ struct nd_pfn *to_nd_pfn(struct device *dev) } EXPORT_SYMBOL(to_nd_pfn); +static struct nd_pfn *to_nd_pfn_safe(struct device *dev) +{ + /* + * pfn device attributes are re-used by dax device instances, so we + * need to be careful to correct device-to-nd_pfn conversion. + */ + if (is_nd_pfn(dev)) + return to_nd_pfn(dev); + + if (is_nd_dax(dev)) { + struct nd_dax *nd_dax = to_nd_dax(dev); + + return &nd_dax->nd_pfn; + } + + WARN_ON(1); + return NULL; +} + static ssize_t mode_show(struct device *dev, struct device_attribute *attr, char *buf) { - struct nd_pfn *nd_pfn = to_nd_pfn(dev); + struct nd_pfn *nd_pfn = to_nd_pfn_safe(dev); switch (nd_pfn->mode) { case PFN_MODE_RAM: @@ -72,7 +91,7 @@ static ssize_t mode_show(struct device *dev, static ssize_t mode_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t len) { - struct nd_pfn *nd_pfn = to_nd_pfn(dev); + struct nd_pfn *nd_pfn = to_nd_pfn_safe(dev); ssize_t rc = 0; device_lock(dev); @@ -106,7 +125,7 @@ static DEVICE_ATTR_RW(mode); static ssize_t align_show(struct device *dev, struct device_attribute *attr, char *buf) { - struct nd_pfn *nd_pfn = to_nd_pfn(dev); + struct nd_pfn *nd_pfn = to_nd_pfn_safe(dev); return sprintf(buf, "%lx\n", nd_pfn->align); } @@ -134,7 +153,7 @@ static ssize_t __align_store(struct nd_pfn *nd_pfn, const char *buf) static ssize_t align_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t len) { - struct nd_pfn *nd_pfn = to_nd_pfn(dev); + struct nd_pfn *nd_pfn = to_nd_pfn_safe(dev); ssize_t rc; device_lock(dev); @@ -152,7 +171,7 @@ static DEVICE_ATTR_RW(align); static ssize_t uuid_show(struct device *dev, struct device_attribute *attr, char *buf) { - struct nd_pfn *nd_pfn = to_nd_pfn(dev); + struct nd_pfn *nd_pfn = to_nd_pfn_safe(dev); if (nd_pfn->uuid) return sprintf(buf, "%pUb\n", nd_pfn->uuid); @@ -162,7 +181,7 @@ static ssize_t uuid_show(struct device *dev, static ssize_t uuid_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t len) { - struct nd_pfn *nd_pfn = to_nd_pfn(dev); + struct nd_pfn *nd_pfn = to_nd_pfn_safe(dev); ssize_t rc; device_lock(dev); @@ -178,7 +197,7 @@ static DEVICE_ATTR_RW(uuid); static ssize_t namespace_show(struct device *dev, struct device_attribute *attr, char *buf) { - struct nd_pfn *nd_pfn = to_nd_pfn(dev); + struct nd_pfn *nd_pfn = to_nd_pfn_safe(dev); ssize_t rc; nvdimm_bus_lock(dev); @@ -191,7 +210,7 @@ static ssize_t namespace_show(struct device *dev, static ssize_t namespace_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t len) { - struct nd_pfn *nd_pfn = to_nd_pfn(dev); + struct nd_pfn *nd_pfn = to_nd_pfn_safe(dev); ssize_t rc; device_lock(dev); @@ -209,7 +228,7 @@ static DEVICE_ATTR_RW(namespace); static ssize_t resource_show(struct device *dev, struct device_attribute *attr, char *buf) { - struct nd_pfn *nd_pfn = to_nd_pfn(dev); + struct nd_pfn *nd_pfn = to_nd_pfn_safe(dev); ssize_t rc; device_lock(dev); @@ -235,7 +254,7 @@ static DEVICE_ATTR_RO(resource); static ssize_t size_show(struct device *dev, struct device_attribute *attr, char *buf) { - struct nd_pfn *nd_pfn = to_nd_pfn(dev); + struct nd_pfn *nd_pfn = to_nd_pfn_safe(dev); ssize_t rc; device_lock(dev); @@ -270,7 +289,7 @@ static struct attribute *nd_pfn_attributes[] = { NULL, }; -static struct attribute_group nd_pfn_attribute_group = { +struct attribute_group nd_pfn_attribute_group = { .attrs = nd_pfn_attributes, }; @@ -281,15 +300,31 @@ static const struct attribute_group *nd_pfn_attribute_groups[] = { NULL, }; -static struct device *__nd_pfn_create(struct nd_region *nd_region, +struct device *nd_pfn_devinit(struct nd_pfn *nd_pfn, struct nd_namespace_common *ndns) { - struct nd_pfn *nd_pfn; - struct device *dev; + struct device *dev = &nd_pfn->dev; - /* we can only create pages for contiguous ranged of pmem */ - if (!is_nd_pmem(&nd_region->dev)) + if (!nd_pfn) + return NULL; + + nd_pfn->mode = PFN_MODE_NONE; + nd_pfn->align = HPAGE_SIZE; + dev = &nd_pfn->dev; + device_initialize(&nd_pfn->dev); + if (ndns && !__nd_attach_ndns(&nd_pfn->dev, ndns, &nd_pfn->ndns)) { + dev_dbg(&ndns->dev, "%s failed, already claimed by %s\n", + __func__, dev_name(ndns->claim)); + put_device(dev); return NULL; + } + return dev; +} + +static struct nd_pfn *nd_pfn_alloc(struct nd_region *nd_region) +{ + struct nd_pfn *nd_pfn; + struct device *dev; nd_pfn = kzalloc(sizeof(*nd_pfn), GFP_KERNEL); if (!nd_pfn) @@ -301,29 +336,27 @@ static struct device *__nd_pfn_create(struct nd_region *nd_region, return NULL; } - nd_pfn->mode = PFN_MODE_NONE; - nd_pfn->align = HPAGE_SIZE; dev = &nd_pfn->dev; dev_set_name(dev, "pfn%d.%d", nd_region->id, nd_pfn->id); - dev->parent = &nd_region->dev; - dev->type = &nd_pfn_device_type; dev->groups = nd_pfn_attribute_groups; - device_initialize(&nd_pfn->dev); - if (ndns && !__nd_attach_ndns(&nd_pfn->dev, ndns, &nd_pfn->ndns)) { - dev_dbg(&ndns->dev, "%s failed, already claimed by %s\n", - __func__, dev_name(ndns->claim)); - put_device(dev); - return NULL; - } - return dev; + dev->type = &nd_pfn_device_type; + dev->parent = &nd_region->dev; + + return nd_pfn; } struct device *nd_pfn_create(struct nd_region *nd_region) { - struct device *dev = __nd_pfn_create(nd_region, NULL); + struct nd_pfn *nd_pfn; + struct device *dev; + + if (!is_nd_pmem(&nd_region->dev)) + return NULL; + + nd_pfn = nd_pfn_alloc(nd_region); + dev = nd_pfn_devinit(nd_pfn, NULL); - if (dev) - __nd_device_register(dev); + __nd_device_register(dev); return dev; } @@ -423,7 +456,8 @@ int nd_pfn_probe(struct device *dev, struct nd_namespace_common *ndns) return -ENODEV; nvdimm_bus_lock(&ndns->dev); - pfn_dev = __nd_pfn_create(nd_region, ndns); + nd_pfn = nd_pfn_alloc(nd_region); + pfn_dev = nd_pfn_devinit(nd_pfn, ndns); nvdimm_bus_unlock(&ndns->dev); if (!pfn_dev) return -ENOMEM; diff --git a/drivers/nvdimm/region.c b/drivers/nvdimm/region.c index 4b7715e29cff..05a912359939 100644 --- a/drivers/nvdimm/region.c +++ b/drivers/nvdimm/region.c @@ -54,6 +54,7 @@ static int nd_region_probe(struct device *dev) nd_region->btt_seed = nd_btt_create(nd_region); nd_region->pfn_seed = nd_pfn_create(nd_region); + nd_region->dax_seed = nd_dax_create(nd_region); if (err == 0) return 0; @@ -86,6 +87,7 @@ static int nd_region_remove(struct device *dev) nd_region->ns_seed = NULL; nd_region->btt_seed = NULL; nd_region->pfn_seed = NULL; + nd_region->dax_seed = NULL; dev_set_drvdata(dev, NULL); nvdimm_bus_unlock(dev); diff --git a/drivers/nvdimm/region_devs.c b/drivers/nvdimm/region_devs.c index 139bf71ca549..9e1b054e0e61 100644 --- a/drivers/nvdimm/region_devs.c +++ b/drivers/nvdimm/region_devs.c @@ -306,6 +306,23 @@ static ssize_t pfn_seed_show(struct device *dev, } static DEVICE_ATTR_RO(pfn_seed); +static ssize_t dax_seed_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + struct nd_region *nd_region = to_nd_region(dev); + ssize_t rc; + + nvdimm_bus_lock(dev); + if (nd_region->dax_seed) + rc = sprintf(buf, "%s\n", dev_name(nd_region->dax_seed)); + else + rc = sprintf(buf, "\n"); + nvdimm_bus_unlock(dev); + + return rc; +} +static DEVICE_ATTR_RO(dax_seed); + static ssize_t read_only_show(struct device *dev, struct device_attribute *attr, char *buf) { @@ -335,6 +352,7 @@ static struct attribute *nd_region_attributes[] = { &dev_attr_mappings.attr, &dev_attr_btt_seed.attr, &dev_attr_pfn_seed.attr, + &dev_attr_dax_seed.attr, &dev_attr_read_only.attr, &dev_attr_set_cookie.attr, &dev_attr_available_size.attr, @@ -353,6 +371,9 @@ static umode_t region_visible(struct kobject *kobj, struct attribute *a, int n) if (!is_nd_pmem(dev) && a == &dev_attr_pfn_seed.attr) return 0; + if (!is_nd_pmem(dev) && a == &dev_attr_dax_seed.attr) + return 0; + if (a != &dev_attr_set_cookie.attr && a != &dev_attr_available_size.attr) return a->mode; @@ -441,6 +462,13 @@ static void nd_region_notify_driver_action(struct nvdimm_bus *nvdimm_bus, nd_region_create_pfn_seed(nd_region); nvdimm_bus_unlock(dev); } + if (is_nd_dax(dev) && probe) { + nd_region = to_nd_region(dev->parent); + nvdimm_bus_lock(dev); + if (nd_region->dax_seed == dev) + nd_region_create_dax_seed(nd_region); + nvdimm_bus_unlock(dev); + } } void nd_region_probe_success(struct nvdimm_bus *nvdimm_bus, struct device *dev) @@ -718,6 +746,7 @@ static struct nd_region *nd_region_create(struct nvdimm_bus *nvdimm_bus, ida_init(&nd_region->ns_ida); ida_init(&nd_region->btt_ida); ida_init(&nd_region->pfn_ida); + ida_init(&nd_region->dax_ida); dev = &nd_region->dev; dev_set_name(dev, "region%d", nd_region->id); dev->parent = &nvdimm_bus->dev; diff --git a/include/uapi/linux/ndctl.h b/include/uapi/linux/ndctl.h index 7cc28ab05b87..4f29d247f709 100644 --- a/include/uapi/linux/ndctl.h +++ b/include/uapi/linux/ndctl.h @@ -206,6 +206,7 @@ static inline const char *nvdimm_cmd_name(unsigned cmd) #define ND_DEVICE_NAMESPACE_IO 4 /* legacy persistent memory */ #define ND_DEVICE_NAMESPACE_PMEM 5 /* PMEM namespace (may alias with BLK) */ #define ND_DEVICE_NAMESPACE_BLK 6 /* BLK namespace (may alias with PMEM) */ +#define ND_DEVICE_DAX_PMEM 7 /* Device DAX interface to pmem */ enum nd_driver_flags { ND_DRIVER_DIMM = 1 << ND_DEVICE_DIMM, @@ -214,6 +215,7 @@ enum nd_driver_flags { ND_DRIVER_NAMESPACE_IO = 1 << ND_DEVICE_NAMESPACE_IO, ND_DRIVER_NAMESPACE_PMEM = 1 << ND_DEVICE_NAMESPACE_PMEM, ND_DRIVER_NAMESPACE_BLK = 1 << ND_DEVICE_NAMESPACE_BLK, + ND_DRIVER_DAX_PMEM = 1 << ND_DEVICE_DAX_PMEM, }; enum { diff --git a/tools/testing/nvdimm/Kbuild b/tools/testing/nvdimm/Kbuild index d5bc8c080b44..5ff6d3c126a9 100644 --- a/tools/testing/nvdimm/Kbuild +++ b/tools/testing/nvdimm/Kbuild @@ -50,6 +50,7 @@ libnvdimm-y += $(NVDIMM_SRC)/label.o libnvdimm-$(CONFIG_ND_CLAIM) += $(NVDIMM_SRC)/claim.o libnvdimm-$(CONFIG_BTT) += $(NVDIMM_SRC)/btt_devs.o libnvdimm-$(CONFIG_NVDIMM_PFN) += $(NVDIMM_SRC)/pfn_devs.o +libnvdimm-$(CONFIG_NVDIMM_DAX) += $(NVDIMM_SRC)/dax_devs.o libnvdimm-y += config_check.o obj-m += test/ -- cgit v1.2.3 From acc93d30d7d43f428272c20a047389c4cbca82ba Mon Sep 17 00:00:00 2001 From: Dan Williams Date: Sat, 7 May 2016 11:40:28 -0700 Subject: Revert "block: enable dax for raw block devices" This reverts commit 5a023cdba50c5f5f2bc351783b3131699deb3937. The functionality is superseded by the new "Device DAX" facility. Cc: Jeff Moyer Cc: Christoph Hellwig Cc: Dave Chinner Cc: Andrew Morton Cc: Ross Zwisler Cc: Jan Kara Signed-off-by: Dan Williams --- block/ioctl.c | 32 ----------------- fs/block_dev.c | 96 +++++++++++++++---------------------------------- include/linux/fs.h | 8 ----- include/uapi/linux/fs.h | 1 - 4 files changed, 29 insertions(+), 108 deletions(-) (limited to 'include/uapi') diff --git a/block/ioctl.c b/block/ioctl.c index 4ff1f92f89ca..698c7933d582 100644 --- a/block/ioctl.c +++ b/block/ioctl.c @@ -407,35 +407,6 @@ static inline int is_unrecognized_ioctl(int ret) ret == -ENOIOCTLCMD; } -#ifdef CONFIG_FS_DAX -bool blkdev_dax_capable(struct block_device *bdev) -{ - struct gendisk *disk = bdev->bd_disk; - - if (!disk->fops->direct_access) - return false; - - /* - * If the partition is not aligned on a page boundary, we can't - * do dax I/O to it. - */ - if ((bdev->bd_part->start_sect % (PAGE_SIZE / 512)) - || (bdev->bd_part->nr_sects % (PAGE_SIZE / 512))) - return false; - - /* - * If the device has known bad blocks, force all I/O through the - * driver / page cache. - * - * TODO: support finer grained dax error handling - */ - if (disk->bb && disk->bb->count) - return false; - - return true; -} -#endif - static int blkdev_flushbuf(struct block_device *bdev, fmode_t mode, unsigned cmd, unsigned long arg) { @@ -598,9 +569,6 @@ int blkdev_ioctl(struct block_device *bdev, fmode_t mode, unsigned cmd, case BLKTRACESETUP: case BLKTRACETEARDOWN: return blk_trace_ioctl(bdev, cmd, argp); - case BLKDAXGET: - return put_int(arg, !!(bdev->bd_inode->i_flags & S_DAX)); - break; case IOC_PR_REGISTER: return blkdev_pr_register(bdev, argp); case IOC_PR_RESERVE: diff --git a/fs/block_dev.c b/fs/block_dev.c index 20a2c02b77c4..36ee10ca503e 100644 --- a/fs/block_dev.c +++ b/fs/block_dev.c @@ -29,6 +29,7 @@ #include #include #include +#include #include #include "internal.h" @@ -1159,6 +1160,33 @@ void bd_set_size(struct block_device *bdev, loff_t size) } EXPORT_SYMBOL(bd_set_size); +static bool blkdev_dax_capable(struct block_device *bdev) +{ + struct gendisk *disk = bdev->bd_disk; + + if (!disk->fops->direct_access || !IS_ENABLED(CONFIG_FS_DAX)) + return false; + + /* + * If the partition is not aligned on a page boundary, we can't + * do dax I/O to it. + */ + if ((bdev->bd_part->start_sect % (PAGE_SIZE / 512)) + || (bdev->bd_part->nr_sects % (PAGE_SIZE / 512))) + return false; + + /* + * If the device has known bad blocks, force all I/O through the + * driver / page cache. + * + * TODO: support finer grained dax error handling + */ + if (disk->bb && disk->bb->count) + return false; + + return true; +} + static void __blkdev_put(struct block_device *bdev, fmode_t mode, int for_part); /* @@ -1724,79 +1752,13 @@ static const struct address_space_operations def_blk_aops = { .is_dirty_writeback = buffer_check_dirty_writeback, }; -#ifdef CONFIG_FS_DAX -/* - * In the raw block case we do not need to contend with truncation nor - * unwritten file extents. Without those concerns there is no need for - * additional locking beyond the mmap_sem context that these routines - * are already executing under. - * - * Note, there is no protection if the block device is dynamically - * resized (partition grow/shrink) during a fault. A stable block device - * size is already not enforced in the blkdev_direct_IO path. - * - * For DAX, it is the responsibility of the block device driver to - * ensure the whole-disk device size is stable while requests are in - * flight. - * - * Finally, unlike the filemap_page_mkwrite() case there is no - * filesystem superblock to sync against freezing. We still include a - * pfn_mkwrite callback for dax drivers to receive write fault - * notifications. - */ -static int blkdev_dax_fault(struct vm_area_struct *vma, struct vm_fault *vmf) -{ - return __dax_fault(vma, vmf, blkdev_get_block, NULL); -} - -static int blkdev_dax_pfn_mkwrite(struct vm_area_struct *vma, - struct vm_fault *vmf) -{ - return dax_pfn_mkwrite(vma, vmf); -} - -static int blkdev_dax_pmd_fault(struct vm_area_struct *vma, unsigned long addr, - pmd_t *pmd, unsigned int flags) -{ - return __dax_pmd_fault(vma, addr, pmd, flags, blkdev_get_block, NULL); -} - -static const struct vm_operations_struct blkdev_dax_vm_ops = { - .fault = blkdev_dax_fault, - .pmd_fault = blkdev_dax_pmd_fault, - .pfn_mkwrite = blkdev_dax_pfn_mkwrite, -}; - -static const struct vm_operations_struct blkdev_default_vm_ops = { - .fault = filemap_fault, - .map_pages = filemap_map_pages, -}; - -static int blkdev_mmap(struct file *file, struct vm_area_struct *vma) -{ - struct inode *bd_inode = bdev_file_inode(file); - - file_accessed(file); - if (IS_DAX(bd_inode)) { - vma->vm_ops = &blkdev_dax_vm_ops; - vma->vm_flags |= VM_MIXEDMAP | VM_HUGEPAGE; - } else { - vma->vm_ops = &blkdev_default_vm_ops; - } - - return 0; -} -#else -#define blkdev_mmap generic_file_mmap -#endif - const struct file_operations def_blk_fops = { .open = blkdev_open, .release = blkdev_close, .llseek = block_llseek, .read_iter = blkdev_read_iter, .write_iter = blkdev_write_iter, - .mmap = blkdev_mmap, + .mmap = generic_file_mmap, .fsync = blkdev_fsync, .unlocked_ioctl = block_ioctl, #ifdef CONFIG_COMPAT diff --git a/include/linux/fs.h b/include/linux/fs.h index 70e61b58baaf..8363a10660f6 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2320,14 +2320,6 @@ extern struct super_block *freeze_bdev(struct block_device *); extern void emergency_thaw_all(void); extern int thaw_bdev(struct block_device *bdev, struct super_block *sb); extern int fsync_bdev(struct block_device *); -#ifdef CONFIG_FS_DAX -extern bool blkdev_dax_capable(struct block_device *bdev); -#else -static inline bool blkdev_dax_capable(struct block_device *bdev) -{ - return false; -} -#endif extern struct super_block *blockdev_superblock; diff --git a/include/uapi/linux/fs.h b/include/uapi/linux/fs.h index a079d50376e1..fbff8b28aa35 100644 --- a/include/uapi/linux/fs.h +++ b/include/uapi/linux/fs.h @@ -222,7 +222,6 @@ struct fsxattr { #define BLKSECDISCARD _IO(0x12,125) #define BLKROTATIONAL _IO(0x12,126) #define BLKZEROOUT _IO(0x12,127) -#define BLKDAXGET _IO(0x12,129) #define BMAP_IOCTL 1 /* obsolete - kept for compatibility */ #define FIBMAP _IO(0x00,1) /* bmap access */ -- cgit v1.2.3