From ab68f26221366f92611650e8470e6a926801c7d4 Mon Sep 17 00:00:00 2001 From: Dan Williams Date: Wed, 18 May 2016 09:15:08 -0700 Subject: /dev/dax, pmem: direct access to persistent memory Device DAX is the device-centric analogue of Filesystem DAX (CONFIG_FS_DAX). It allows memory ranges to be allocated and mapped without need of an intervening file system. Device DAX is strict, precise and predictable. Specifically this interface: 1/ Guarantees fault granularity with respect to a given page size (pte, pmd, or pud) set at configuration time. 2/ Enforces deterministic behavior by being strict about what fault scenarios are supported. For example, by forcing MADV_DONTFORK semantics and omitting MAP_PRIVATE support device-dax guarantees that a mapping always behaves/performs the same once established. It is the "what you see is what you get" access mechanism to differentiated memory vs filesystem DAX which has filesystem specific implementation semantics. Persistent memory is the first target, but the mechanism is also targeted for exclusive allocations of performance differentiated memory ranges. This commit is limited to the base device driver infrastructure to associate a dax device with pmem range. Cc: Jeff Moyer Cc: Christoph Hellwig Cc: Andrew Morton Cc: Dave Hansen Cc: Ross Zwisler Reviewed-by: Johannes Thumshirn Signed-off-by: Dan Williams --- drivers/dax/pmem.c | 158 +++++++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 158 insertions(+) create mode 100644 drivers/dax/pmem.c (limited to 'drivers/dax/pmem.c') diff --git a/drivers/dax/pmem.c b/drivers/dax/pmem.c new file mode 100644 index 000000000000..55d510e36cd1 --- /dev/null +++ b/drivers/dax/pmem.c @@ -0,0 +1,158 @@ +/* + * Copyright(c) 2016 Intel Corporation. All rights reserved. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of version 2 of the GNU General Public License as + * published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, but + * WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU + * General Public License for more details. + */ +#include +#include +#include +#include +#include "../nvdimm/pfn.h" +#include "../nvdimm/nd.h" +#include "dax.h" + +struct dax_pmem { + struct device *dev; + struct percpu_ref ref; + struct completion cmp; +}; + +struct dax_pmem *to_dax_pmem(struct percpu_ref *ref) +{ + return container_of(ref, struct dax_pmem, ref); +} + +static void dax_pmem_percpu_release(struct percpu_ref *ref) +{ + struct dax_pmem *dax_pmem = to_dax_pmem(ref); + + dev_dbg(dax_pmem->dev, "%s\n", __func__); + complete(&dax_pmem->cmp); +} + +static void dax_pmem_percpu_exit(void *data) +{ + struct percpu_ref *ref = data; + struct dax_pmem *dax_pmem = to_dax_pmem(ref); + + dev_dbg(dax_pmem->dev, "%s\n", __func__); + percpu_ref_exit(ref); + wait_for_completion(&dax_pmem->cmp); +} + +static void dax_pmem_percpu_kill(void *data) +{ + struct percpu_ref *ref = data; + struct dax_pmem *dax_pmem = to_dax_pmem(ref); + + dev_dbg(dax_pmem->dev, "%s\n", __func__); + percpu_ref_kill(ref); +} + +static int dax_pmem_probe(struct device *dev) +{ + int rc; + void *addr; + struct resource res; + struct nd_pfn_sb *pfn_sb; + struct dax_pmem *dax_pmem; + struct nd_region *nd_region; + struct nd_namespace_io *nsio; + struct dax_region *dax_region; + struct nd_namespace_common *ndns; + struct nd_dax *nd_dax = to_nd_dax(dev); + struct nd_pfn *nd_pfn = &nd_dax->nd_pfn; + struct vmem_altmap __altmap, *altmap = NULL; + + ndns = nvdimm_namespace_common_probe(dev); + if (IS_ERR(ndns)) + return PTR_ERR(ndns); + nsio = to_nd_namespace_io(&ndns->dev); + + /* parse the 'pfn' info block via ->rw_bytes */ + devm_nsio_enable(dev, nsio); + altmap = nvdimm_setup_pfn(nd_pfn, &res, &__altmap); + if (IS_ERR(altmap)) + return PTR_ERR(altmap); + devm_nsio_disable(dev, nsio); + + pfn_sb = nd_pfn->pfn_sb; + + if (!devm_request_mem_region(dev, nsio->res.start, + resource_size(&nsio->res), dev_name(dev))) { + dev_warn(dev, "could not reserve region %pR\n", &nsio->res); + return -EBUSY; + } + + dax_pmem = devm_kzalloc(dev, sizeof(*dax_pmem), GFP_KERNEL); + if (!dax_pmem) + return -ENOMEM; + + dax_pmem->dev = dev; + init_completion(&dax_pmem->cmp); + rc = percpu_ref_init(&dax_pmem->ref, dax_pmem_percpu_release, 0, + GFP_KERNEL); + if (rc) + return rc; + + rc = devm_add_action(dev, dax_pmem_percpu_exit, &dax_pmem->ref); + if (rc) { + dax_pmem_percpu_exit(&dax_pmem->ref); + return rc; + } + + addr = devm_memremap_pages(dev, &res, &dax_pmem->ref, altmap); + if (IS_ERR(addr)) + return PTR_ERR(addr); + + rc = devm_add_action(dev, dax_pmem_percpu_kill, &dax_pmem->ref); + if (rc) { + dax_pmem_percpu_kill(&dax_pmem->ref); + return rc; + } + + nd_region = to_nd_region(dev->parent); + dax_region = alloc_dax_region(dev, nd_region->id, &res, + le32_to_cpu(pfn_sb->align), addr, PFN_DEV|PFN_MAP); + if (!dax_region) + return -ENOMEM; + + /* TODO: support for subdividing a dax region... */ + rc = devm_create_dax_dev(dax_region, &res, 1); + + /* child dax_dev instances now own the lifetime of the dax_region */ + dax_region_put(dax_region); + + return rc; +} + +static struct nd_device_driver dax_pmem_driver = { + .probe = dax_pmem_probe, + .drv = { + .name = "dax_pmem", + }, + .type = ND_DRIVER_DAX_PMEM, +}; + +static int __init dax_pmem_init(void) +{ + return nd_driver_register(&dax_pmem_driver); +} +module_init(dax_pmem_init); + +static void __exit dax_pmem_exit(void) +{ + driver_unregister(&dax_pmem_driver.drv); +} +module_exit(dax_pmem_exit); + +MODULE_LICENSE("GPL v2"); +MODULE_AUTHOR("Intel Corporation"); +MODULE_ALIAS_ND_DEVICE(ND_DEVICE_DAX_PMEM); -- cgit v1.2.3