From patchwork Wed Aug 30 20:56:18 2017 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Dave Jiang X-Patchwork-Id: 9930779 Return-Path: Received: from mail.wl.linuxfoundation.org (pdx-wl-mail.web.codeaurora.org [172.30.200.125]) by pdx-korg-patchwork.web.codeaurora.org (Postfix) with ESMTP id C49F0603B4 for ; Wed, 30 Aug 2017 20:56:40 +0000 (UTC) Received: from mail.wl.linuxfoundation.org (localhost [127.0.0.1]) by mail.wl.linuxfoundation.org (Postfix) with ESMTP id AF85B287BF for ; Wed, 30 Aug 2017 20:56:40 +0000 (UTC) Received: by mail.wl.linuxfoundation.org (Postfix, from userid 486) id 69CD8287B7; Wed, 30 Aug 2017 20:56:40 +0000 (UTC) X-Spam-Checker-Version: SpamAssassin 3.3.1 (2010-03-16) on pdx-wl-mail.web.codeaurora.org X-Spam-Level: X-Spam-Status: No, score=-1.9 required=2.0 tests=BAYES_00, RCVD_IN_DNSWL_NONE autolearn=ham version=3.3.1 Received: from ml01.01.org (ml01.01.org [198.145.21.10]) (using TLSv1.2 with cipher DHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (No client certificate requested) by mail.wl.linuxfoundation.org (Postfix) with ESMTPS id EE8A3287AE for ; Wed, 30 Aug 2017 20:56:35 +0000 (UTC) Received: from [127.0.0.1] (localhost [IPv6:::1]) by ml01.01.org (Postfix) with ESMTP id 03EEE21E95DEB; Wed, 30 Aug 2017 13:56:17 -0700 (PDT) X-Original-To: linux-nvdimm@lists.01.org Delivered-To: linux-nvdimm@lists.01.org Received: from mga06.intel.com (mga06.intel.com [134.134.136.31]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (No client certificate requested) by ml01.01.org (Postfix) with ESMTPS id E5E3B2095DCB3 for ; Wed, 30 Aug 2017 13:56:14 -0700 (PDT) Received: from orsmga003.jf.intel.com ([10.7.209.27]) by orsmga104.jf.intel.com with ESMTP; 30 Aug 2017 13:56:18 -0700 X-ExtLoop1: 1 X-IronPort-AV: E=Sophos; i="5.41,450,1498546800"; d="scan'208"; a="1009413647" Received: from djiang5-desk3.ch.intel.com ([143.182.137.38]) by orsmga003.jf.intel.com with ESMTP; 30 Aug 2017 13:56:18 -0700 Subject: [PATCH v7 8/9] libnvdimm: move common function for pmem to pmem_core From: Dave Jiang To: vinod.koul@intel.com, dan.j.williams@intel.com Date: Wed, 30 Aug 2017 13:56:18 -0700 Message-ID: <150412657792.69288.4657868119430253664.stgit@djiang5-desk3.ch.intel.com> In-Reply-To: <150412628764.69288.12074115435918322858.stgit@djiang5-desk3.ch.intel.com> References: <150412628764.69288.12074115435918322858.stgit@djiang5-desk3.ch.intel.com> User-Agent: StGit/0.17.1-dirty MIME-Version: 1.0 X-BeenThere: linux-nvdimm@lists.01.org X-Mailman-Version: 2.1.22 Precedence: list List-Id: "Linux-nvdimm developer list." List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Cc: dmaengine@vger.kernel.org, hch@infradead.org, linux-nvdimm@lists.01.org Errors-To: linux-nvdimm-bounces@lists.01.org Sender: "Linux-nvdimm" X-Virus-Scanned: ClamAV using ClamSMTP In preparation for adding another pmem driver, moving all common functions in pmem that will be used by new driver to a pmem_core module to share. Signed-off-by: Dave Jiang --- drivers/nvdimm/Kconfig | 10 + drivers/nvdimm/Makefile | 3 drivers/nvdimm/pmem.c | 401 +-------------------------------------- drivers/nvdimm/pmem.h | 54 +++++ drivers/nvdimm/pmem_core.c | 451 ++++++++++++++++++++++++++++++++++++++++++++ 5 files changed, 528 insertions(+), 391 deletions(-) create mode 100644 drivers/nvdimm/pmem_core.c diff --git a/drivers/nvdimm/Kconfig b/drivers/nvdimm/Kconfig index 5bdd499..01fe9e8 100644 --- a/drivers/nvdimm/Kconfig +++ b/drivers/nvdimm/Kconfig @@ -17,12 +17,16 @@ menuconfig LIBNVDIMM if LIBNVDIMM -config BLK_DEV_PMEM - tristate "PMEM: Persistent memory block device support" - default LIBNVDIMM +config BLK_DEV_PMEM_CORE + tristate select DAX select ND_BTT if BTT select ND_PFN if NVDIMM_PFN + +config BLK_DEV_PMEM + tristate "PMEM: Persistent memory block device support" + default LIBNVDIMM + select BLK_DEV_PMEM_CORE help Memory ranges for PMEM are described by either an NFIT (NVDIMM Firmware Interface Table, see CONFIG_NFIT_ACPI), a diff --git a/drivers/nvdimm/Makefile b/drivers/nvdimm/Makefile index 909554c..0ce99cf 100644 --- a/drivers/nvdimm/Makefile +++ b/drivers/nvdimm/Makefile @@ -1,9 +1,12 @@ obj-$(CONFIG_LIBNVDIMM) += libnvdimm.o +obj-$(CONFIG_BLK_DEV_PMEM_CORE) += nd_pmem_core.o obj-$(CONFIG_BLK_DEV_PMEM) += nd_pmem.o obj-$(CONFIG_ND_BTT) += nd_btt.o obj-$(CONFIG_ND_BLK) += nd_blk.o obj-$(CONFIG_X86_PMEM_LEGACY) += nd_e820.o +nd_pmem_core-y := pmem_core.o + nd_pmem-y := pmem.o nd_btt-y := btt.o diff --git a/drivers/nvdimm/pmem.c b/drivers/nvdimm/pmem.c index b1460d1..025d22d 100644 --- a/drivers/nvdimm/pmem.c +++ b/drivers/nvdimm/pmem.c @@ -15,134 +15,9 @@ * more details. */ -#include -#include -#include #include -#include #include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include #include "pmem.h" -#include "pfn.h" -#include "nd.h" - -static struct device *to_dev(struct pmem_device *pmem) -{ - /* - * nvdimm bus services need a 'dev' parameter, and we record the device - * at init in bb.dev. - */ - return pmem->bb.dev; -} - -static struct nd_region *to_region(struct pmem_device *pmem) -{ - return to_nd_region(to_dev(pmem)->parent); -} - -static blk_status_t pmem_clear_poison(struct pmem_device *pmem, - phys_addr_t offset, unsigned int len) -{ - struct device *dev = to_dev(pmem); - sector_t sector; - long cleared; - blk_status_t rc = BLK_STS_OK; - - sector = (offset - pmem->data_offset) / 512; - - cleared = nvdimm_clear_poison(dev, pmem->phys_addr + offset, len); - if (cleared < len) - rc = BLK_STS_IOERR; - if (cleared > 0 && cleared / 512) { - cleared /= 512; - dev_dbg(dev, "%s: %#llx clear %ld sector%s\n", __func__, - (unsigned long long) sector, cleared, - cleared > 1 ? "s" : ""); - badblocks_clear(&pmem->bb, sector, cleared); - if (pmem->bb_state) - sysfs_notify_dirent(pmem->bb_state); - } - - arch_invalidate_pmem(pmem->virt_addr + offset, len); - - return rc; -} - -static void write_pmem(void *pmem_addr, struct page *page, - unsigned int off, unsigned int len) -{ - void *mem = kmap_atomic(page); - - memcpy_flushcache(pmem_addr, mem + off, len); - kunmap_atomic(mem); -} - -static blk_status_t read_pmem(struct page *page, unsigned int off, - void *pmem_addr, unsigned int len) -{ - int rc; - void *mem = kmap_atomic(page); - - rc = memcpy_mcsafe(mem + off, pmem_addr, len); - kunmap_atomic(mem); - if (rc) - return BLK_STS_IOERR; - return BLK_STS_OK; -} - -static blk_status_t pmem_do_bvec(struct pmem_device *pmem, struct page *page, - unsigned int len, unsigned int off, bool is_write, - sector_t sector) -{ - blk_status_t rc = BLK_STS_OK; - bool bad_pmem = false; - phys_addr_t pmem_off = sector * 512 + pmem->data_offset; - void *pmem_addr = pmem->virt_addr + pmem_off; - - if (unlikely(is_bad_pmem(&pmem->bb, sector, len))) - bad_pmem = true; - - if (!is_write) { - if (unlikely(bad_pmem)) - rc = BLK_STS_IOERR; - else { - rc = read_pmem(page, off, pmem_addr, len); - flush_dcache_page(page); - } - } else { - /* - * Note that we write the data both before and after - * clearing poison. The write before clear poison - * handles situations where the latest written data is - * preserved and the clear poison operation simply marks - * the address range as valid without changing the data. - * In this case application software can assume that an - * interrupted write will either return the new good - * data or an error. - * - * However, if pmem_clear_poison() leaves the data in an - * indeterminate state we need to perform the write - * after clear poison. - */ - flush_dcache_page(page); - write_pmem(pmem_addr, page, off, len); - if (unlikely(bad_pmem)) { - rc = pmem_clear_poison(pmem, pmem_off, len); - write_pmem(pmem_addr, page, off, len); - } - } - - return rc; -} static blk_qc_t pmem_make_request(struct request_queue *q, struct bio *bio) { @@ -177,73 +52,12 @@ static blk_qc_t pmem_make_request(struct request_queue *q, struct bio *bio) return BLK_QC_T_NONE; } -static int pmem_rw_page(struct block_device *bdev, sector_t sector, - struct page *page, bool is_write) -{ - struct pmem_device *pmem = bdev->bd_queue->queuedata; - blk_status_t rc; - - rc = pmem_do_bvec(pmem, page, PAGE_SIZE, 0, is_write, sector); - - /* - * The ->rw_page interface is subtle and tricky. The core - * retries on any error, so we can only invoke page_endio() in - * the successful completion case. Otherwise, we'll see crashes - * caused by double completion. - */ - if (rc == 0) - page_endio(page, is_write, 0); - - return blk_status_to_errno(rc); -} - -/* see "strong" declaration in tools/testing/nvdimm/pmem-dax.c */ -__weak long __pmem_direct_access(struct pmem_device *pmem, pgoff_t pgoff, - long nr_pages, void **kaddr, pfn_t *pfn) -{ - resource_size_t offset = PFN_PHYS(pgoff) + pmem->data_offset; - - if (unlikely(is_bad_pmem(&pmem->bb, PFN_PHYS(pgoff) / 512, - PFN_PHYS(nr_pages)))) - return -EIO; - *kaddr = pmem->virt_addr + offset; - *pfn = phys_to_pfn_t(pmem->phys_addr + offset, pmem->pfn_flags); - - /* - * If badblocks are present, limit known good range to the - * requested range. - */ - if (unlikely(pmem->bb.count)) - return nr_pages; - return PHYS_PFN(pmem->size - pmem->pfn_pad - offset); -} - static const struct block_device_operations pmem_fops = { .owner = THIS_MODULE, .rw_page = pmem_rw_page, .revalidate_disk = nvdimm_revalidate_disk, }; -static long pmem_dax_direct_access(struct dax_device *dax_dev, - pgoff_t pgoff, long nr_pages, void **kaddr, pfn_t *pfn) -{ - struct pmem_device *pmem = dax_get_private(dax_dev); - - return __pmem_direct_access(pmem, pgoff, nr_pages, kaddr, pfn); -} - -static size_t pmem_copy_from_iter(struct dax_device *dax_dev, pgoff_t pgoff, - void *addr, size_t bytes, struct iov_iter *i) -{ - return copy_from_iter_flushcache(addr, bytes, i); -} - -static void pmem_dax_flush(struct dax_device *dax_dev, pgoff_t pgoff, - void *addr, size_t size) -{ - arch_wb_cache_pmem(addr, size); -} - static const struct dax_operations pmem_dax_ops = { .direct_access = pmem_dax_direct_access, .copy_from_iter = pmem_copy_from_iter, @@ -260,152 +74,37 @@ static void pmem_release_queue(void *q) blk_cleanup_queue(q); } -static void pmem_freeze_queue(void *q) -{ - blk_freeze_queue_start(q); -} - -static void pmem_release_disk(void *__pmem) -{ - struct pmem_device *pmem = __pmem; - - kill_dax(pmem->dax_dev); - put_dax(pmem->dax_dev); - del_gendisk(pmem->disk); - put_disk(pmem->disk); -} - static int pmem_attach_disk(struct device *dev, struct nd_namespace_common *ndns) { - struct nd_namespace_io *nsio = to_nd_namespace_io(&ndns->dev); - struct nd_region *nd_region = to_nd_region(dev->parent); - struct vmem_altmap __altmap, *altmap = NULL; - int nid = dev_to_node(dev), fua, wbc; - struct resource *res = &nsio->res; - struct nd_pfn *nd_pfn = NULL; - struct dax_device *dax_dev; - struct nd_pfn_sb *pfn_sb; struct pmem_device *pmem; - struct resource pfn_res; struct request_queue *q; - struct device *gendev; - struct gendisk *disk; - void *addr; - - /* while nsio_rw_bytes is active, parse a pfn info block if present */ - if (is_nd_pfn(dev)) { - nd_pfn = to_nd_pfn(dev); - altmap = nvdimm_setup_pfn(nd_pfn, &pfn_res, &__altmap); - if (IS_ERR(altmap)) - return PTR_ERR(altmap); - } - - /* we're attaching a block device, disable raw namespace access */ - devm_nsio_disable(dev, nsio); + int rc; - pmem = devm_kzalloc(dev, sizeof(*pmem), GFP_KERNEL); + pmem = pmem_core_setup_pmem(dev, ndns); if (!pmem) - return -ENOMEM; - - dev_set_drvdata(dev, pmem); - pmem->phys_addr = res->start; - pmem->size = resource_size(res); - fua = nvdimm_has_flush(nd_region); - if (!IS_ENABLED(CONFIG_ARCH_HAS_UACCESS_FLUSHCACHE) || fua < 0) { - dev_warn(dev, "unable to guarantee persistence of writes\n"); - fua = 0; - } - wbc = nvdimm_has_cache(nd_region); - - if (!devm_request_mem_region(dev, res->start, resource_size(res), - dev_name(&ndns->dev))) { - dev_warn(dev, "could not reserve region %pR\n", res); - return -EBUSY; - } + return -ENXIO; q = blk_alloc_queue_node(GFP_KERNEL, dev_to_node(dev)); if (!q) return -ENOMEM; - if (devm_add_action_or_reset(dev, pmem_release_queue, q)) - return -ENOMEM; - - pmem->pfn_flags = PFN_DEV; - if (is_nd_pfn(dev)) { - addr = devm_memremap_pages(dev, &pfn_res, &q->q_usage_counter, - altmap); - pfn_sb = nd_pfn->pfn_sb; - pmem->data_offset = le64_to_cpu(pfn_sb->dataoff); - pmem->pfn_pad = resource_size(res) - resource_size(&pfn_res); - pmem->pfn_flags |= PFN_MAP; - res = &pfn_res; /* for badblocks populate */ - res->start += pmem->data_offset; - } else if (pmem_should_map_pages(dev)) { - addr = devm_memremap_pages(dev, &nsio->res, - &q->q_usage_counter, NULL); - pmem->pfn_flags |= PFN_MAP; - } else - addr = devm_memremap(dev, pmem->phys_addr, - pmem->size, ARCH_MEMREMAP_PMEM); - - /* - * At release time the queue must be frozen before - * devm_memremap_pages is unwound - */ - if (devm_add_action_or_reset(dev, pmem_freeze_queue, q)) - return -ENOMEM; - - if (IS_ERR(addr)) - return PTR_ERR(addr); - pmem->virt_addr = addr; - - blk_queue_write_cache(q, wbc, fua); + pmem->q = q; + pmem_core_setup_queue(dev, pmem, ndns); blk_queue_make_request(q, pmem_make_request); - blk_queue_physical_block_size(q, PAGE_SIZE); - blk_queue_logical_block_size(q, pmem_sector_size(ndns)); blk_queue_max_hw_sectors(q, UINT_MAX); - queue_flag_set_unlocked(QUEUE_FLAG_NONROT, q); - queue_flag_set_unlocked(QUEUE_FLAG_DAX, q); - q->queuedata = pmem; - - disk = alloc_disk_node(0, nid); - if (!disk) - return -ENOMEM; - pmem->disk = disk; - - disk->fops = &pmem_fops; - disk->queue = q; - disk->flags = GENHD_FL_EXT_DEVT; - nvdimm_namespace_disk_name(ndns, disk->disk_name); - set_capacity(disk, (pmem->size - pmem->pfn_pad - pmem->data_offset) - / 512); - if (devm_init_badblocks(dev, &pmem->bb)) - return -ENOMEM; - nvdimm_badblocks_populate(nd_region, &pmem->bb, res); - disk->bb = &pmem->bb; - - dax_dev = alloc_dax(pmem, disk->disk_name, &pmem_dax_ops); - if (!dax_dev) { - put_disk(disk); - return -ENOMEM; - } - dax_write_cache(dax_dev, wbc); - pmem->dax_dev = dax_dev; - gendev = disk_to_dev(disk); - gendev->groups = pmem_attribute_groups; - - device_add_disk(dev, disk); - if (devm_add_action_or_reset(dev, pmem_release_disk, pmem)) + if (devm_add_action_or_reset(dev, pmem_release_queue, q)) return -ENOMEM; - revalidate_disk(disk); + rc = pmem_core_remap_pages(dev, pmem, ndns); + if (rc < 0) + return rc; - pmem->bb_state = sysfs_get_dirent(disk_to_dev(disk)->kobj.sd, - "badblocks"); - if (!pmem->bb_state) - dev_warn(dev, "'badblocks' notification disabled\n"); + rc = pmem_core_setup_disk(dev, pmem, ndns, &pmem_fops, + &pmem_dax_ops, pmem_attribute_groups); + if (rc < 0) + return rc; return 0; } @@ -436,80 +135,6 @@ static int nd_pmem_probe(struct device *dev) return pmem_attach_disk(dev, ndns); } -static int nd_pmem_remove(struct device *dev) -{ - struct pmem_device *pmem = dev_get_drvdata(dev); - - if (is_nd_btt(dev)) - nvdimm_namespace_detach_btt(to_nd_btt(dev)); - else { - /* - * Note, this assumes device_lock() context to not race - * nd_pmem_notify() - */ - sysfs_put(pmem->bb_state); - pmem->bb_state = NULL; - } - nvdimm_flush(to_nd_region(dev->parent)); - - return 0; -} - -static void nd_pmem_shutdown(struct device *dev) -{ - nvdimm_flush(to_nd_region(dev->parent)); -} - -static void nd_pmem_notify(struct device *dev, enum nvdimm_event event) -{ - struct nd_region *nd_region; - resource_size_t offset = 0, end_trunc = 0; - struct nd_namespace_common *ndns; - struct nd_namespace_io *nsio; - struct resource res; - struct badblocks *bb; - struct kernfs_node *bb_state; - - if (event != NVDIMM_REVALIDATE_POISON) - return; - - if (is_nd_btt(dev)) { - struct nd_btt *nd_btt = to_nd_btt(dev); - - ndns = nd_btt->ndns; - nd_region = to_nd_region(ndns->dev.parent); - nsio = to_nd_namespace_io(&ndns->dev); - bb = &nsio->bb; - bb_state = NULL; - } else { - struct pmem_device *pmem = dev_get_drvdata(dev); - - nd_region = to_region(pmem); - bb = &pmem->bb; - bb_state = pmem->bb_state; - - if (is_nd_pfn(dev)) { - struct nd_pfn *nd_pfn = to_nd_pfn(dev); - struct nd_pfn_sb *pfn_sb = nd_pfn->pfn_sb; - - ndns = nd_pfn->ndns; - offset = pmem->data_offset + - __le32_to_cpu(pfn_sb->start_pad); - end_trunc = __le32_to_cpu(pfn_sb->end_trunc); - } else { - ndns = to_ndns(dev); - } - - nsio = to_nd_namespace_io(&ndns->dev); - } - - res.start = nsio->res.start + offset; - res.end = nsio->res.end - end_trunc; - nvdimm_badblocks_populate(nd_region, bb, &res); - if (bb_state) - sysfs_notify_dirent(bb_state); -} - MODULE_ALIAS("pmem"); MODULE_ALIAS_ND_DEVICE(ND_DEVICE_NAMESPACE_IO); MODULE_ALIAS_ND_DEVICE(ND_DEVICE_NAMESPACE_PMEM); diff --git a/drivers/nvdimm/pmem.h b/drivers/nvdimm/pmem.h index 5434321..6df833e 100644 --- a/drivers/nvdimm/pmem.h +++ b/drivers/nvdimm/pmem.h @@ -4,6 +4,9 @@ #include #include #include +#include +#include +#include "nd.h" #ifdef CONFIG_ARCH_HAS_PMEM_API #define ARCH_MEMREMAP_PMEM MEMREMAP_WB @@ -35,8 +38,59 @@ struct pmem_device { struct badblocks bb; struct dax_device *dax_dev; struct gendisk *disk; + struct blk_mq_tag_set tag_set; + struct request_queue *q; }; +static inline struct device *to_dev(struct pmem_device *pmem) +{ + /* + * nvdimm bus services need a 'dev' parameter, and we record the device + * at init in bb.dev. + */ + return pmem->bb.dev; +} + +static inline struct nd_region *to_region(struct pmem_device *pmem) +{ + return to_nd_region(to_dev(pmem)->parent); +} + +struct device *to_dev(struct pmem_device *pmem); +struct nd_region *to_region(struct pmem_device *pmem); +blk_status_t pmem_clear_poison(struct pmem_device *pmem, + phys_addr_t offset, unsigned int len); +void write_pmem(void *pmem_addr, struct page *page, + unsigned int off, unsigned int len); +blk_status_t read_pmem(struct page *page, unsigned int off, + void *pmem_addr, unsigned int len); +blk_status_t pmem_do_bvec(struct pmem_device *pmem, struct page *page, + unsigned int len, unsigned int off, bool is_write, + sector_t sector); +int pmem_rw_page(struct block_device *bdev, sector_t sector, + struct page *page, bool is_write); +void nd_pmem_notify(struct device *dev, enum nvdimm_event event); +long pmem_dax_direct_access(struct dax_device *dax_dev, + pgoff_t pgoff, long nr_pages, void **kaddr, pfn_t *pfn); +size_t pmem_copy_from_iter(struct dax_device *dax_dev, pgoff_t pgoff, + void *addr, size_t bytes, struct iov_iter *i); +void pmem_dax_flush(struct dax_device *dax_dev, pgoff_t pgoff, + void *addr, size_t size); long __pmem_direct_access(struct pmem_device *pmem, pgoff_t pgoff, long nr_pages, void **kaddr, pfn_t *pfn); +int nd_pmem_remove(struct device *dev); +void nd_pmem_shutdown(struct device *dev); +int pmem_core_remap_pages(struct device *dev, + struct pmem_device *pmem, struct nd_namespace_common *ndns); +int pmem_core_setup_disk(struct device *dev, + struct pmem_device *pmem, + struct nd_namespace_common *ndns, + const struct block_device_operations *block_ops, + const struct dax_operations *dax_ops, + const struct attribute_group **attrib); +void pmem_core_setup_queue(struct device *dev, struct pmem_device *pmem, + struct nd_namespace_common *ndns); +struct pmem_device *pmem_core_setup_pmem(struct device *dev, + struct nd_namespace_common *ndns); + #endif /* __NVDIMM_PMEM_H__ */ diff --git a/drivers/nvdimm/pmem_core.c b/drivers/nvdimm/pmem_core.c new file mode 100644 index 0000000..521b61b --- /dev/null +++ b/drivers/nvdimm/pmem_core.c @@ -0,0 +1,451 @@ +/* + * Persistent Memory Block Driver shared code + * Copyright (c) 2014-2017, Intel Corporation. + * Copyright (c) 2015, Christoph Hellwig . + * Copyright (c) 2015, Boaz Harrosh . + * + * This program is free software; you can redistribute it and/or modify it + * under the terms and conditions of the GNU General Public License, + * version 2, 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 General Public License for + * more details. + */ +#include +#include +#include +#include +#include +#include +#include +#include "pmem.h" +#include "pfn.h" + +blk_status_t pmem_clear_poison(struct pmem_device *pmem, + phys_addr_t offset, unsigned int len) +{ + struct device *dev = to_dev(pmem); + sector_t sector; + long cleared; + blk_status_t rc = BLK_STS_OK; + + sector = (offset - pmem->data_offset) / 512; + + cleared = nvdimm_clear_poison(dev, pmem->phys_addr + offset, len); + if (cleared < len) + rc = BLK_STS_IOERR; + if (cleared > 0 && cleared / 512) { + cleared /= 512; + dev_dbg(dev, "%s: %#llx clear %ld sector%s\n", __func__, + (unsigned long long) sector, cleared, + cleared > 1 ? "s" : ""); + badblocks_clear(&pmem->bb, sector, cleared); + if (pmem->bb_state) + sysfs_notify_dirent(pmem->bb_state); + } + + arch_invalidate_pmem(pmem->virt_addr + offset, len); + + return rc; +} +EXPORT_SYMBOL_GPL(pmem_clear_poison); + +void write_pmem(void *pmem_addr, struct page *page, + unsigned int off, unsigned int len) +{ + void *mem = kmap_atomic(page); + + memcpy_flushcache(pmem_addr, mem + off, len); + kunmap_atomic(mem); +} +EXPORT_SYMBOL_GPL(write_pmem); + +blk_status_t read_pmem(struct page *page, unsigned int off, + void *pmem_addr, unsigned int len) +{ + int rc; + void *mem = kmap_atomic(page); + + rc = memcpy_mcsafe(mem + off, pmem_addr, len); + kunmap_atomic(mem); + if (rc) + return BLK_STS_IOERR; + return BLK_STS_OK; +} +EXPORT_SYMBOL_GPL(read_pmem); + +blk_status_t pmem_do_bvec(struct pmem_device *pmem, struct page *page, + unsigned int len, unsigned int off, bool is_write, + sector_t sector) +{ + blk_status_t rc = BLK_STS_OK; + bool bad_pmem = false; + phys_addr_t pmem_off = sector * 512 + pmem->data_offset; + void *pmem_addr = pmem->virt_addr + pmem_off; + + if (unlikely(is_bad_pmem(&pmem->bb, sector, len))) + bad_pmem = true; + + if (!is_write) { + if (unlikely(bad_pmem)) + rc = BLK_STS_IOERR; + else { + rc = read_pmem(page, off, pmem_addr, len); + flush_dcache_page(page); + } + } else { + /* + * Note that we write the data both before and after + * clearing poison. The write before clear poison + * handles situations where the latest written data is + * preserved and the clear poison operation simply marks + * the address range as valid without changing the data. + * In this case application software can assume that an + * interrupted write will either return the new good + * data or an error. + * + * However, if pmem_clear_poison() leaves the data in an + * indeterminate state we need to perform the write + * after clear poison. + */ + flush_dcache_page(page); + write_pmem(pmem_addr, page, off, len); + if (unlikely(bad_pmem)) { + rc = pmem_clear_poison(pmem, pmem_off, len); + write_pmem(pmem_addr, page, off, len); + } + } + + return rc; +} +EXPORT_SYMBOL_GPL(pmem_do_bvec); + +int pmem_rw_page(struct block_device *bdev, sector_t sector, + struct page *page, bool is_write) +{ + struct pmem_device *pmem = bdev->bd_queue->queuedata; + blk_status_t rc; + + rc = pmem_do_bvec(pmem, page, PAGE_SIZE, 0, is_write, sector); + + /* + * The ->rw_page interface is subtle and tricky. The core + * retries on any error, so we can only invoke page_endio() in + * the successful completion case. Otherwise, we'll see crashes + * caused by double completion. + */ + if (rc == 0) + page_endio(page, is_write, 0); + + return blk_status_to_errno(rc); +} +EXPORT_SYMBOL_GPL(pmem_rw_page); + +/* see "strong" declaration in tools/testing/nvdimm/pmem-dax.c */ +__weak long __pmem_direct_access(struct pmem_device *pmem, pgoff_t pgoff, + long nr_pages, void **kaddr, pfn_t *pfn) +{ + resource_size_t offset = PFN_PHYS(pgoff) + pmem->data_offset; + + if (unlikely(is_bad_pmem(&pmem->bb, PFN_PHYS(pgoff) / 512, + PFN_PHYS(nr_pages)))) + return -EIO; + *kaddr = pmem->virt_addr + offset; + *pfn = phys_to_pfn_t(pmem->phys_addr + offset, pmem->pfn_flags); + + /* + * If badblocks are present, limit known good range to the + * requested range. + */ + if (unlikely(pmem->bb.count)) + return nr_pages; + return PHYS_PFN(pmem->size - pmem->pfn_pad - offset); +} + +long pmem_dax_direct_access(struct dax_device *dax_dev, + pgoff_t pgoff, long nr_pages, void **kaddr, pfn_t *pfn) +{ + struct pmem_device *pmem = dax_get_private(dax_dev); + + return __pmem_direct_access(pmem, pgoff, nr_pages, kaddr, pfn); +} +EXPORT_SYMBOL_GPL(pmem_dax_direct_access); + +size_t pmem_copy_from_iter(struct dax_device *dax_dev, pgoff_t pgoff, + void *addr, size_t bytes, struct iov_iter *i) +{ + return copy_from_iter_flushcache(addr, bytes, i); +} +EXPORT_SYMBOL_GPL(pmem_copy_from_iter); + +void pmem_dax_flush(struct dax_device *dax_dev, pgoff_t pgoff, + void *addr, size_t size) +{ + arch_wb_cache_pmem(addr, size); +} +EXPORT_SYMBOL_GPL(pmem_dax_flush); + +void nd_pmem_notify(struct device *dev, enum nvdimm_event event) +{ + struct nd_region *nd_region; + resource_size_t offset = 0, end_trunc = 0; + struct nd_namespace_common *ndns; + struct nd_namespace_io *nsio; + struct resource res; + struct badblocks *bb; + struct kernfs_node *bb_state; + + if (event != NVDIMM_REVALIDATE_POISON) + return; + + if (is_nd_btt(dev)) { + struct nd_btt *nd_btt = to_nd_btt(dev); + + ndns = nd_btt->ndns; + nd_region = to_nd_region(ndns->dev.parent); + nsio = to_nd_namespace_io(&ndns->dev); + bb = &nsio->bb; + bb_state = NULL; + } else { + struct pmem_device *pmem = dev_get_drvdata(dev); + + nd_region = to_region(pmem); + bb = &pmem->bb; + bb_state = pmem->bb_state; + + if (is_nd_pfn(dev)) { + struct nd_pfn *nd_pfn = to_nd_pfn(dev); + struct nd_pfn_sb *pfn_sb = nd_pfn->pfn_sb; + + ndns = nd_pfn->ndns; + offset = pmem->data_offset + + __le32_to_cpu(pfn_sb->start_pad); + end_trunc = __le32_to_cpu(pfn_sb->end_trunc); + } else { + ndns = to_ndns(dev); + } + + nsio = to_nd_namespace_io(&ndns->dev); + } + + res.start = nsio->res.start + offset; + res.end = nsio->res.end - end_trunc; + nvdimm_badblocks_populate(nd_region, bb, &res); + if (bb_state) + sysfs_notify_dirent(bb_state); +} +EXPORT_SYMBOL_GPL(nd_pmem_notify); + +static void pmem_freeze_queue(void *q) +{ + blk_freeze_queue_start(q); +} + +int pmem_core_remap_pages(struct device *dev, struct pmem_device *pmem, + struct nd_namespace_common *ndns) +{ + struct nd_namespace_io *nsio = to_nd_namespace_io(&ndns->dev); + void *addr; + struct nd_pfn_sb *pfn_sb; + struct nd_pfn *nd_pfn = NULL; + struct resource *res = &nsio->res; + struct resource pfn_res; + struct vmem_altmap __altmap, *altmap = NULL; + + /* while nsio_rw_bytes is active, parse a pfn info block if present */ + if (is_nd_pfn(dev)) { + nd_pfn = to_nd_pfn(dev); + altmap = nvdimm_setup_pfn(nd_pfn, &pfn_res, &__altmap); + if (IS_ERR(altmap)) + return PTR_ERR(altmap); + } + + pmem->pfn_flags = PFN_DEV; + if (is_nd_pfn(dev)) { + addr = devm_memremap_pages(dev, &pfn_res, + &pmem->q->q_usage_counter, altmap); + pfn_sb = nd_pfn->pfn_sb; + pmem->data_offset = le64_to_cpu(pfn_sb->dataoff); + pmem->pfn_pad = resource_size(res) - resource_size(&pfn_res); + pmem->pfn_flags |= PFN_MAP; + res = &pfn_res; /* for badblocks populate */ + res->start += pmem->data_offset; + } else if (pmem_should_map_pages(dev)) { + addr = devm_memremap_pages(dev, &nsio->res, + &pmem->q->q_usage_counter, NULL); + pmem->pfn_flags |= PFN_MAP; + } else + addr = devm_memremap(dev, pmem->phys_addr, + pmem->size, ARCH_MEMREMAP_PMEM); + + /* + * At release time the queue must be frozen before + * devm_memremap_pages is unwound + */ + if (devm_add_action_or_reset(dev, pmem_freeze_queue, pmem->q)) + return -ENXIO; + + if (IS_ERR(addr)) + return -ENXIO; + + pmem->virt_addr = addr; + return 0; +} +EXPORT_SYMBOL_GPL(pmem_core_remap_pages); + +static void pmem_release_disk(void *__pmem) +{ + struct pmem_device *pmem = __pmem; + + kill_dax(pmem->dax_dev); + put_dax(pmem->dax_dev); + del_gendisk(pmem->disk); + put_disk(pmem->disk); +} + +int pmem_core_setup_disk(struct device *dev, + struct pmem_device *pmem, + struct nd_namespace_common *ndns, + const struct block_device_operations *block_ops, + const struct dax_operations *dax_ops, + const struct attribute_group **attribs) +{ + struct device *gendev; + struct gendisk *disk; + struct dax_device *dax_dev; + struct nd_region *nd_region = to_nd_region(dev->parent); + int wbc, fua; + int nid = dev_to_node(dev); + struct nd_namespace_io *nsio = to_nd_namespace_io(&ndns->dev); + struct resource *res = &nsio->res; + + wbc = nvdimm_has_cache(nd_region); + fua = nvdimm_has_flush(nd_region); + if (!IS_ENABLED(CONFIG_ARCH_HAS_UACCESS_FLUSHCACHE) || fua < 0) { + dev_warn(dev, "unable to guarantee persistence of writes\n"); + fua = 0; + } + + disk = alloc_disk_node(0, nid); + if (!disk) + return -ENOMEM; + pmem->disk = disk; + + disk->fops = block_ops; + disk->queue = pmem->q; + disk->flags = GENHD_FL_EXT_DEVT; + nvdimm_namespace_disk_name(ndns, disk->disk_name); + set_capacity(disk, (pmem->size - pmem->pfn_pad - pmem->data_offset) + / 512); + + if (devm_init_badblocks(dev, &pmem->bb)) + return -ENXIO; + + nvdimm_badblocks_populate(nd_region, &pmem->bb, res); + disk->bb = &pmem->bb; + + dax_dev = alloc_dax(pmem, disk->disk_name, dax_ops); + if (!dax_dev) { + put_disk(disk); + return -ENOMEM; + } + + dax_write_cache(dax_dev, wbc); + pmem->dax_dev = dax_dev; + gendev = disk_to_dev(disk); + gendev->groups = attribs; + + device_add_disk(dev, disk); + if (devm_add_action_or_reset(dev, pmem_release_disk, pmem)) + return -ENOMEM; + + revalidate_disk(disk); + + pmem->bb_state = sysfs_get_dirent(disk_to_dev(disk)->kobj.sd, + "badblocks"); + if (!pmem->bb_state) + dev_warn(dev, "'badblocks' notification disabled\n"); + + return 0; +} +EXPORT_SYMBOL_GPL(pmem_core_setup_disk); + +void pmem_core_setup_queue(struct device *dev, struct pmem_device *pmem, + struct nd_namespace_common *ndns) +{ + struct nd_region *nd_region = to_nd_region(dev->parent); + int fua, wbc; + + wbc = nvdimm_has_cache(nd_region); + fua = nvdimm_has_flush(nd_region); + if (!IS_ENABLED(CONFIG_ARCH_HAS_UACCESS_FLUSHCACHE) || fua < 0) { + dev_warn(dev, "unable to guarantee persistence of writes\n"); + fua = 0; + } + + blk_queue_write_cache(pmem->q, wbc, fua); + blk_queue_physical_block_size(pmem->q, PAGE_SIZE); + blk_queue_logical_block_size(pmem->q, pmem_sector_size(ndns)); + queue_flag_set_unlocked(QUEUE_FLAG_NONROT, pmem->q); + queue_flag_set_unlocked(QUEUE_FLAG_DAX, pmem->q); + pmem->q->queuedata = pmem; +} +EXPORT_SYMBOL_GPL(pmem_core_setup_queue); + +struct pmem_device *pmem_core_setup_pmem(struct device *dev, + struct nd_namespace_common *ndns) +{ + struct nd_namespace_io *nsio = to_nd_namespace_io(&ndns->dev); + struct resource *res = &nsio->res; + struct pmem_device *pmem; + + /* we're attaching a block device, disable raw namespace access */ + devm_nsio_disable(dev, nsio); + + pmem = devm_kzalloc(dev, sizeof(*pmem), GFP_KERNEL); + if (!pmem) + return NULL; + + dev_set_drvdata(dev, pmem); + pmem->phys_addr = res->start; + pmem->size = resource_size(res); + if (!devm_request_mem_region(dev, res->start, resource_size(res), + dev_name(&ndns->dev))) { + dev_warn(dev, "could not reserve region %pR\n", res); + return NULL; + } + + + return pmem; +} +EXPORT_SYMBOL_GPL(pmem_core_setup_pmem); + +int nd_pmem_remove(struct device *dev) +{ + struct pmem_device *pmem = dev_get_drvdata(dev); + + if (is_nd_btt(dev)) + nvdimm_namespace_detach_btt(to_nd_btt(dev)); + else { + /* + * Note, this assumes device_lock() context to not race + * nd_pmem_notify() + */ + sysfs_put(pmem->bb_state); + pmem->bb_state = NULL; + } + nvdimm_flush(to_nd_region(dev->parent)); + + return 0; +} +EXPORT_SYMBOL_GPL(nd_pmem_remove); + +void nd_pmem_shutdown(struct device *dev) +{ + nvdimm_flush(to_nd_region(dev->parent)); +} +EXPORT_SYMBOL_GPL(nd_pmem_shutdown); + +MODULE_LICENSE("GPL v2");