From 83762cb5c7c464af4cbaba5679af31c7fe534979 Mon Sep 17 00:00:00 2001 From: Dan Williams Date: Mon, 15 Nov 2021 13:20:57 -0800 Subject: dax: Kill DEV_DAX_PMEM_COMPAT The /sys/class/dax compatibility option has shipped in the kernel for 4 years now which should be sufficient time for tools to abandon the old ABI in favor of the /sys/bus/dax device-model. Delete it now and see if anyone screams. Since this compatibility option shipped there has been more reports of users being surprised by the compat ABI than surprised by the "new", so the compat infrastructure has outlived its usefulness. Recall that /sys/bus/dax device-model is required for the dax kmem driver which allows PMEM to be used as "System RAM". The following projects were known to have a dependency on /sys/class/dax and have dropped their dependency as of the listed version: - ndctl (including libndctl, daxctl, and libdaxctl): v64+ - fio: v3.13+ - pmdk: v1.5.2+ As further evidence this option is no longer needed some distributions have already stopped enabling CONFIG_DEV_DAX_PMEM_COMPAT. Cc: Ira Weiny Cc: Dave Jiang Reported-by: Vishal Verma Acked-by: Dave Hansen Reviewed-by: Jane Chu Link: https://lore.kernel.org/r/163701116195.3784476.726128179293466337.stgit@dwillia2-desk3.amr.corp.intel.com Signed-off-by: Dan Williams --- Documentation/ABI/obsolete/sysfs-class-dax | 22 ------ drivers/dax/Kconfig | 9 --- drivers/dax/Makefile | 3 +- drivers/dax/bus.c | 21 +----- drivers/dax/bus.h | 13 ---- drivers/dax/device.c | 6 +- drivers/dax/pmem.c | 103 ++++++++++++++++++++++++++++ drivers/dax/pmem/Makefile | 1 - drivers/dax/pmem/compat.c | 72 ------------------- drivers/dax/pmem/core.c | 79 --------------------- drivers/dax/pmem/pmem.c | 30 -------- tools/testing/nvdimm/Kbuild | 8 +-- tools/testing/nvdimm/dax_pmem_compat_test.c | 8 --- tools/testing/nvdimm/dax_pmem_core_test.c | 8 --- tools/testing/nvdimm/test/ndtest.c | 4 -- tools/testing/nvdimm/test/nfit.c | 4 -- 16 files changed, 109 insertions(+), 282 deletions(-) delete mode 100644 Documentation/ABI/obsolete/sysfs-class-dax create mode 100644 drivers/dax/pmem.c delete mode 100644 drivers/dax/pmem/compat.c delete mode 100644 drivers/dax/pmem/core.c delete mode 100644 tools/testing/nvdimm/dax_pmem_compat_test.c delete mode 100644 tools/testing/nvdimm/dax_pmem_core_test.c diff --git a/Documentation/ABI/obsolete/sysfs-class-dax b/Documentation/ABI/obsolete/sysfs-class-dax deleted file mode 100644 index 5bcce27458e3..000000000000 --- a/Documentation/ABI/obsolete/sysfs-class-dax +++ /dev/null @@ -1,22 +0,0 @@ -What: /sys/class/dax/ -Date: May, 2016 -KernelVersion: v4.7 -Contact: nvdimm@lists.linux.dev -Description: 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. - - The /sys/class/dax/ interface enumerates all the - device-dax instances in the system. The ABI is - deprecated and will be removed after 2020. It is - replaced with the DAX bus interface /sys/bus/dax/ where - device-dax instances can be found under - /sys/bus/dax/devices/ diff --git a/drivers/dax/Kconfig b/drivers/dax/Kconfig index d2834c2cfa10..15b442ef7b93 100644 --- a/drivers/dax/Kconfig +++ b/drivers/dax/Kconfig @@ -70,13 +70,4 @@ config DEV_DAX_KMEM Say N if unsure. -config DEV_DAX_PMEM_COMPAT - tristate "PMEM DAX: support the deprecated /sys/class/dax interface" - depends on m && DEV_DAX_PMEM=m - default DEV_DAX_PMEM - help - Older versions of the libdaxctl library expect to find all - device-dax instances under /sys/class/dax. If libdaxctl in - your distribution is older than v58 say M, otherwise say N. - endif diff --git a/drivers/dax/Makefile b/drivers/dax/Makefile index 9d4ba672d305..90a56ca3b345 100644 --- a/drivers/dax/Makefile +++ b/drivers/dax/Makefile @@ -2,10 +2,11 @@ obj-$(CONFIG_DAX) += dax.o obj-$(CONFIG_DEV_DAX) += device_dax.o obj-$(CONFIG_DEV_DAX_KMEM) += kmem.o +obj-$(CONFIG_DEV_DAX_PMEM) += dax_pmem.o dax-y := super.o dax-y += bus.o device_dax-y := device.o +dax_pmem-y := pmem.o -obj-y += pmem/ obj-y += hmem/ diff --git a/drivers/dax/bus.c b/drivers/dax/bus.c index 6cc4da4c713d..452cf7860926 100644 --- a/drivers/dax/bus.c +++ b/drivers/dax/bus.c @@ -10,8 +10,6 @@ #include "dax-private.h" #include "bus.h" -static struct class *dax_class; - static DEFINE_MUTEX(dax_bus_lock); #define DAX_NAME_LEN 30 @@ -1343,10 +1341,7 @@ struct dev_dax *devm_create_dev_dax(struct dev_dax_data *data) inode = dax_inode(dax_dev); dev->devt = inode->i_rdev; - if (data->subsys == DEV_DAX_BUS) - dev->bus = &dax_bus_type; - else - dev->class = dax_class; + dev->bus = &dax_bus_type; dev->parent = parent; dev->type = &dev_dax_type; @@ -1445,22 +1440,10 @@ EXPORT_SYMBOL_GPL(dax_driver_unregister); int __init dax_bus_init(void) { - int rc; - - if (IS_ENABLED(CONFIG_DEV_DAX_PMEM_COMPAT)) { - dax_class = class_create(THIS_MODULE, "dax"); - if (IS_ERR(dax_class)) - return PTR_ERR(dax_class); - } - - rc = bus_register(&dax_bus_type); - if (rc) - class_destroy(dax_class); - return rc; + return bus_register(&dax_bus_type); } void __exit dax_bus_exit(void) { bus_unregister(&dax_bus_type); - class_destroy(dax_class); } diff --git a/drivers/dax/bus.h b/drivers/dax/bus.h index 1e946ad7780a..381cec9ff05c 100644 --- a/drivers/dax/bus.h +++ b/drivers/dax/bus.h @@ -16,24 +16,15 @@ struct dax_region *alloc_dax_region(struct device *parent, int region_id, struct range *range, int target_node, unsigned int align, unsigned long flags); -enum dev_dax_subsys { - DEV_DAX_BUS = 0, /* zeroed dev_dax_data picks this by default */ - DEV_DAX_CLASS, -}; - struct dev_dax_data { struct dax_region *dax_region; struct dev_pagemap *pgmap; - enum dev_dax_subsys subsys; resource_size_t size; int id; }; struct dev_dax *devm_create_dev_dax(struct dev_dax_data *data); -/* to be deleted when DEV_DAX_CLASS is removed */ -struct dev_dax *__dax_pmem_probe(struct device *dev, enum dev_dax_subsys subsys); - struct dax_device_driver { struct device_driver drv; struct list_head ids; @@ -49,10 +40,6 @@ int __dax_driver_register(struct dax_device_driver *dax_drv, void dax_driver_unregister(struct dax_device_driver *dax_drv); void kill_dev_dax(struct dev_dax *dev_dax); -#if IS_ENABLED(CONFIG_DEV_DAX_PMEM_COMPAT) -int dev_dax_probe(struct dev_dax *dev_dax); -#endif - /* * While run_dax() is potentially a generic operation that could be * defined in include/linux/dax.h we don't want to grow any users diff --git a/drivers/dax/device.c b/drivers/dax/device.c index dd8222a42808..e58d597f0415 100644 --- a/drivers/dax/device.c +++ b/drivers/dax/device.c @@ -433,11 +433,7 @@ int dev_dax_probe(struct dev_dax *dev_dax) inode = dax_inode(dax_dev); cdev = inode->i_cdev; cdev_init(cdev, &dax_fops); - if (dev->class) { - /* for the CONFIG_DEV_DAX_PMEM_COMPAT case */ - cdev->owner = dev->parent->driver->owner; - } else - cdev->owner = dev->driver->owner; + cdev->owner = dev->driver->owner; cdev_set_parent(cdev, &dev->kobj); rc = cdev_add(cdev, dev->devt, 1); if (rc) diff --git a/drivers/dax/pmem.c b/drivers/dax/pmem.c new file mode 100644 index 000000000000..f050ea78bb83 --- /dev/null +++ b/drivers/dax/pmem.c @@ -0,0 +1,103 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright(c) 2016 - 2018 Intel Corporation. All rights reserved. */ +#include +#include +#include +#include "../nvdimm/pfn.h" +#include "../nvdimm/nd.h" +#include "bus.h" + +static struct dev_dax *__dax_pmem_probe(struct device *dev) +{ + struct range range; + int rc, id, region_id; + resource_size_t offset; + struct nd_pfn_sb *pfn_sb; + struct dev_dax *dev_dax; + struct dev_dax_data data; + struct nd_namespace_io *nsio; + struct dax_region *dax_region; + struct dev_pagemap pgmap = { }; + struct nd_namespace_common *ndns; + struct nd_dax *nd_dax = to_nd_dax(dev); + struct nd_pfn *nd_pfn = &nd_dax->nd_pfn; + struct nd_region *nd_region = to_nd_region(dev->parent); + + ndns = nvdimm_namespace_common_probe(dev); + if (IS_ERR(ndns)) + return ERR_CAST(ndns); + + /* parse the 'pfn' info block via ->rw_bytes */ + rc = devm_namespace_enable(dev, ndns, nd_info_block_reserve()); + if (rc) + return ERR_PTR(rc); + rc = nvdimm_setup_pfn(nd_pfn, &pgmap); + if (rc) + return ERR_PTR(rc); + devm_namespace_disable(dev, ndns); + + /* reserve the metadata area, device-dax will reserve the data */ + pfn_sb = nd_pfn->pfn_sb; + offset = le64_to_cpu(pfn_sb->dataoff); + nsio = to_nd_namespace_io(&ndns->dev); + if (!devm_request_mem_region(dev, nsio->res.start, offset, + dev_name(&ndns->dev))) { + dev_warn(dev, "could not reserve metadata\n"); + return ERR_PTR(-EBUSY); + } + + rc = sscanf(dev_name(&ndns->dev), "namespace%d.%d", ®ion_id, &id); + if (rc != 2) + return ERR_PTR(-EINVAL); + + /* adjust the dax_region range to the start of data */ + range = pgmap.range; + range.start += offset; + dax_region = alloc_dax_region(dev, region_id, &range, + nd_region->target_node, le32_to_cpu(pfn_sb->align), + IORESOURCE_DAX_STATIC); + if (!dax_region) + return ERR_PTR(-ENOMEM); + + data = (struct dev_dax_data) { + .dax_region = dax_region, + .id = id, + .pgmap = &pgmap, + .size = range_len(&range), + }; + dev_dax = devm_create_dev_dax(&data); + + /* child dev_dax instances now own the lifetime of the dax_region */ + dax_region_put(dax_region); + + return dev_dax; +} + +static int dax_pmem_probe(struct device *dev) +{ + return PTR_ERR_OR_ZERO(__dax_pmem_probe(dev)); +} + +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); diff --git a/drivers/dax/pmem/Makefile b/drivers/dax/pmem/Makefile index 010269f61d41..191c31f0d4f0 100644 --- a/drivers/dax/pmem/Makefile +++ b/drivers/dax/pmem/Makefile @@ -1,7 +1,6 @@ # SPDX-License-Identifier: GPL-2.0-only obj-$(CONFIG_DEV_DAX_PMEM) += dax_pmem.o obj-$(CONFIG_DEV_DAX_PMEM) += dax_pmem_core.o -obj-$(CONFIG_DEV_DAX_PMEM_COMPAT) += dax_pmem_compat.o dax_pmem-y := pmem.o dax_pmem_core-y := core.o diff --git a/drivers/dax/pmem/compat.c b/drivers/dax/pmem/compat.c deleted file mode 100644 index d81dc35fd65d..000000000000 --- a/drivers/dax/pmem/compat.c +++ /dev/null @@ -1,72 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -/* Copyright(c) 2016 - 2018 Intel Corporation. All rights reserved. */ -#include -#include -#include -#include -#include -#include "../bus.h" - -/* we need the private definitions to implement compat suport */ -#include "../dax-private.h" - -static int dax_pmem_compat_probe(struct device *dev) -{ - struct dev_dax *dev_dax = __dax_pmem_probe(dev, DEV_DAX_CLASS); - int rc; - - if (IS_ERR(dev_dax)) - return PTR_ERR(dev_dax); - - if (!devres_open_group(&dev_dax->dev, dev_dax, GFP_KERNEL)) - return -ENOMEM; - - device_lock(&dev_dax->dev); - rc = dev_dax_probe(dev_dax); - device_unlock(&dev_dax->dev); - - devres_close_group(&dev_dax->dev, dev_dax); - if (rc) - devres_release_group(&dev_dax->dev, dev_dax); - - return rc; -} - -static int dax_pmem_compat_release(struct device *dev, void *data) -{ - device_lock(dev); - devres_release_group(dev, to_dev_dax(dev)); - device_unlock(dev); - - return 0; -} - -static void dax_pmem_compat_remove(struct device *dev) -{ - device_for_each_child(dev, NULL, dax_pmem_compat_release); -} - -static struct nd_device_driver dax_pmem_compat_driver = { - .probe = dax_pmem_compat_probe, - .remove = dax_pmem_compat_remove, - .drv = { - .name = "dax_pmem_compat", - }, - .type = ND_DRIVER_DAX_PMEM, -}; - -static int __init dax_pmem_compat_init(void) -{ - return nd_driver_register(&dax_pmem_compat_driver); -} -module_init(dax_pmem_compat_init); - -static void __exit dax_pmem_compat_exit(void) -{ - driver_unregister(&dax_pmem_compat_driver.drv); -} -module_exit(dax_pmem_compat_exit); - -MODULE_LICENSE("GPL v2"); -MODULE_AUTHOR("Intel Corporation"); -MODULE_ALIAS_ND_DEVICE(ND_DEVICE_DAX_PMEM); diff --git a/drivers/dax/pmem/core.c b/drivers/dax/pmem/core.c deleted file mode 100644 index 062e8bc14223..000000000000 --- a/drivers/dax/pmem/core.c +++ /dev/null @@ -1,79 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -/* Copyright(c) 2016 - 2018 Intel Corporation. All rights reserved. */ -#include -#include -#include -#include "../../nvdimm/pfn.h" -#include "../../nvdimm/nd.h" -#include "../bus.h" - -struct dev_dax *__dax_pmem_probe(struct device *dev, enum dev_dax_subsys subsys) -{ - struct range range; - int rc, id, region_id; - resource_size_t offset; - struct nd_pfn_sb *pfn_sb; - struct dev_dax *dev_dax; - struct dev_dax_data data; - struct nd_namespace_io *nsio; - struct dax_region *dax_region; - struct dev_pagemap pgmap = { }; - struct nd_namespace_common *ndns; - struct nd_dax *nd_dax = to_nd_dax(dev); - struct nd_pfn *nd_pfn = &nd_dax->nd_pfn; - struct nd_region *nd_region = to_nd_region(dev->parent); - - ndns = nvdimm_namespace_common_probe(dev); - if (IS_ERR(ndns)) - return ERR_CAST(ndns); - - /* parse the 'pfn' info block via ->rw_bytes */ - rc = devm_namespace_enable(dev, ndns, nd_info_block_reserve()); - if (rc) - return ERR_PTR(rc); - rc = nvdimm_setup_pfn(nd_pfn, &pgmap); - if (rc) - return ERR_PTR(rc); - devm_namespace_disable(dev, ndns); - - /* reserve the metadata area, device-dax will reserve the data */ - pfn_sb = nd_pfn->pfn_sb; - offset = le64_to_cpu(pfn_sb->dataoff); - nsio = to_nd_namespace_io(&ndns->dev); - if (!devm_request_mem_region(dev, nsio->res.start, offset, - dev_name(&ndns->dev))) { - dev_warn(dev, "could not reserve metadata\n"); - return ERR_PTR(-EBUSY); - } - - rc = sscanf(dev_name(&ndns->dev), "namespace%d.%d", ®ion_id, &id); - if (rc != 2) - return ERR_PTR(-EINVAL); - - /* adjust the dax_region range to the start of data */ - range = pgmap.range; - range.start += offset; - dax_region = alloc_dax_region(dev, region_id, &range, - nd_region->target_node, le32_to_cpu(pfn_sb->align), - IORESOURCE_DAX_STATIC); - if (!dax_region) - return ERR_PTR(-ENOMEM); - - data = (struct dev_dax_data) { - .dax_region = dax_region, - .id = id, - .pgmap = &pgmap, - .subsys = subsys, - .size = range_len(&range), - }; - dev_dax = devm_create_dev_dax(&data); - - /* child dev_dax instances now own the lifetime of the dax_region */ - dax_region_put(dax_region); - - return dev_dax; -} -EXPORT_SYMBOL_GPL(__dax_pmem_probe); - -MODULE_LICENSE("GPL v2"); -MODULE_AUTHOR("Intel Corporation"); diff --git a/drivers/dax/pmem/pmem.c b/drivers/dax/pmem/pmem.c index 0ae4238a0ef8..dfe91a2990fe 100644 --- a/drivers/dax/pmem/pmem.c +++ b/drivers/dax/pmem/pmem.c @@ -7,34 +7,4 @@ #include #include "../bus.h" -static int dax_pmem_probe(struct device *dev) -{ - return PTR_ERR_OR_ZERO(__dax_pmem_probe(dev, DEV_DAX_BUS)); -} -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"); -#if !IS_ENABLED(CONFIG_DEV_DAX_PMEM_COMPAT) -/* For compat builds, don't load this module by default */ -MODULE_ALIAS_ND_DEVICE(ND_DEVICE_DAX_PMEM); -#endif diff --git a/tools/testing/nvdimm/Kbuild b/tools/testing/nvdimm/Kbuild index 47f9cc9dcd94..c57d9e9d4480 100644 --- a/tools/testing/nvdimm/Kbuild +++ b/tools/testing/nvdimm/Kbuild @@ -35,8 +35,6 @@ obj-$(CONFIG_DAX) += dax.o endif obj-$(CONFIG_DEV_DAX) += device_dax.o obj-$(CONFIG_DEV_DAX_PMEM) += dax_pmem.o -obj-$(CONFIG_DEV_DAX_PMEM) += dax_pmem_core.o -obj-$(CONFIG_DEV_DAX_PMEM_COMPAT) += dax_pmem_compat.o nfit-y := $(ACPI_SRC)/core.o nfit-y += $(ACPI_SRC)/intel.o @@ -67,12 +65,8 @@ device_dax-y += dax-dev.o device_dax-y += device_dax_test.o device_dax-y += config_check.o -dax_pmem-y := $(DAX_SRC)/pmem/pmem.o +dax_pmem-y := $(DAX_SRC)/pmem.o dax_pmem-y += dax_pmem_test.o -dax_pmem_core-y := $(DAX_SRC)/pmem/core.o -dax_pmem_core-y += dax_pmem_core_test.o -dax_pmem_compat-y := $(DAX_SRC)/pmem/compat.o -dax_pmem_compat-y += dax_pmem_compat_test.o dax_pmem-y += config_check.o libnvdimm-y := $(NVDIMM_SRC)/core.o diff --git a/tools/testing/nvdimm/dax_pmem_compat_test.c b/tools/testing/nvdimm/dax_pmem_compat_test.c deleted file mode 100644 index 7cd1877f3765..000000000000 --- a/tools/testing/nvdimm/dax_pmem_compat_test.c +++ /dev/null @@ -1,8 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -// Copyright(c) 2019 Intel Corporation. All rights reserved. - -#include -#include -#include "watermark.h" - -nfit_test_watermark(dax_pmem_compat); diff --git a/tools/testing/nvdimm/dax_pmem_core_test.c b/tools/testing/nvdimm/dax_pmem_core_test.c deleted file mode 100644 index a4249cdbeec1..000000000000 --- a/tools/testing/nvdimm/dax_pmem_core_test.c +++ /dev/null @@ -1,8 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -// Copyright(c) 2019 Intel Corporation. All rights reserved. - -#include -#include -#include "watermark.h" - -nfit_test_watermark(dax_pmem_core); diff --git a/tools/testing/nvdimm/test/ndtest.c b/tools/testing/nvdimm/test/ndtest.c index 6862915f1fb0..3ca7c32e9362 100644 --- a/tools/testing/nvdimm/test/ndtest.c +++ b/tools/testing/nvdimm/test/ndtest.c @@ -1054,10 +1054,6 @@ static __init int ndtest_init(void) libnvdimm_test(); device_dax_test(); dax_pmem_test(); - dax_pmem_core_test(); -#ifdef CONFIG_DEV_DAX_PMEM_COMPAT - dax_pmem_compat_test(); -#endif nfit_test_setup(ndtest_resource_lookup, NULL); diff --git a/tools/testing/nvdimm/test/nfit.c b/tools/testing/nvdimm/test/nfit.c index b1bff5fb0f65..0bc91ffee257 100644 --- a/tools/testing/nvdimm/test/nfit.c +++ b/tools/testing/nvdimm/test/nfit.c @@ -3300,10 +3300,6 @@ static __init int nfit_test_init(void) acpi_nfit_test(); device_dax_test(); dax_pmem_test(); - dax_pmem_core_test(); -#ifdef CONFIG_DEV_DAX_PMEM_COMPAT - dax_pmem_compat_test(); -#endif nfit_test_setup(nfit_test_lookup, nfit_test_evaluate_dsm); -- cgit v1.2.3 From d751939235b9b7bc4af15f90a3e99288a8b844a7 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 29 Nov 2021 11:21:35 +0100 Subject: dm: fix alloc_dax error handling in alloc_dev Make sure ->dax_dev is NULL on error so that the cleanup path doesn't trip over an ERR_PTR. Reported-by: Dan Williams Signed-off-by: Christoph Hellwig Link: https://lore.kernel.org/r/20211129102203.2243509-2-hch@lst.de Signed-off-by: Dan Williams --- drivers/md/dm.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/drivers/md/dm.c b/drivers/md/dm.c index 662742a310cb..acc84dc1bded 100644 --- a/drivers/md/dm.c +++ b/drivers/md/dm.c @@ -1786,8 +1786,10 @@ static struct mapped_device *alloc_dev(int minor) if (IS_ENABLED(CONFIG_DAX_DRIVER)) { md->dax_dev = alloc_dax(md, md->disk->disk_name, &dm_dax_ops, 0); - if (IS_ERR(md->dax_dev)) + if (IS_ERR(md->dax_dev)) { + md->dax_dev = NULL; goto bad; + } } format_dev_t(md->name, MKDEV(_major, minor)); -- cgit v1.2.3 From 5d2a228b9e1319ff188f9ea89006fbe575561921 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 29 Nov 2021 11:21:36 +0100 Subject: dm: make the DAX support depend on CONFIG_FS_DAX The device mapper DAX support is all hanging off a block device and thus can't be used with device dax. Make it depend on CONFIG_FS_DAX instead of CONFIG_DAX_DRIVER. This also means that bdev_dax_pgoff only needs to be built under CONFIG_FS_DAX now. Signed-off-by: Christoph Hellwig Acked-by: Mike Snitzer Link: https://lore.kernel.org/r/20211129102203.2243509-3-hch@lst.de Signed-off-by: Dan Williams --- drivers/dax/super.c | 6 ++---- drivers/md/dm-linear.c | 2 +- drivers/md/dm-log-writes.c | 2 +- drivers/md/dm-stripe.c | 2 +- drivers/md/dm-writecache.c | 2 +- drivers/md/dm.c | 2 +- 6 files changed, 7 insertions(+), 9 deletions(-) diff --git a/drivers/dax/super.c b/drivers/dax/super.c index b882cf8106ea..e20d0cef10a1 100644 --- a/drivers/dax/super.c +++ b/drivers/dax/super.c @@ -63,7 +63,7 @@ static int dax_host_hash(const char *host) return hashlen_hash(hashlen_string("DAX", host)) % DAX_HASH_SIZE; } -#ifdef CONFIG_BLOCK +#if defined(CONFIG_BLOCK) && defined(CONFIG_FS_DAX) #include int bdev_dax_pgoff(struct block_device *bdev, sector_t sector, size_t size, @@ -80,7 +80,6 @@ int bdev_dax_pgoff(struct block_device *bdev, sector_t sector, size_t size, } EXPORT_SYMBOL(bdev_dax_pgoff); -#if IS_ENABLED(CONFIG_FS_DAX) /** * dax_get_by_host() - temporary lookup mechanism for filesystem-dax * @host: alternate name for the device registered by a dax driver @@ -219,8 +218,7 @@ bool dax_supported(struct dax_device *dax_dev, struct block_device *bdev, return ret; } EXPORT_SYMBOL_GPL(dax_supported); -#endif /* CONFIG_FS_DAX */ -#endif /* CONFIG_BLOCK */ +#endif /* CONFIG_BLOCK && CONFIG_FS_DAX */ enum dax_device_flags { /* !alive + rcu grace period == no new operations / mappings */ diff --git a/drivers/md/dm-linear.c b/drivers/md/dm-linear.c index 66ba16713f69..0a260c35aeee 100644 --- a/drivers/md/dm-linear.c +++ b/drivers/md/dm-linear.c @@ -162,7 +162,7 @@ static int linear_iterate_devices(struct dm_target *ti, return fn(ti, lc->dev, lc->start, ti->len, data); } -#if IS_ENABLED(CONFIG_DAX_DRIVER) +#if IS_ENABLED(CONFIG_FS_DAX) static long linear_dax_direct_access(struct dm_target *ti, pgoff_t pgoff, long nr_pages, void **kaddr, pfn_t *pfn) { diff --git a/drivers/md/dm-log-writes.c b/drivers/md/dm-log-writes.c index 0b3ef977ceeb..3155875d4e5b 100644 --- a/drivers/md/dm-log-writes.c +++ b/drivers/md/dm-log-writes.c @@ -901,7 +901,7 @@ static void log_writes_io_hints(struct dm_target *ti, struct queue_limits *limit limits->io_min = limits->physical_block_size; } -#if IS_ENABLED(CONFIG_DAX_DRIVER) +#if IS_ENABLED(CONFIG_FS_DAX) static int log_dax(struct log_writes_c *lc, sector_t sector, size_t bytes, struct iov_iter *i) { diff --git a/drivers/md/dm-stripe.c b/drivers/md/dm-stripe.c index 6660b6b53d5b..f08460722029 100644 --- a/drivers/md/dm-stripe.c +++ b/drivers/md/dm-stripe.c @@ -300,7 +300,7 @@ static int stripe_map(struct dm_target *ti, struct bio *bio) return DM_MAPIO_REMAPPED; } -#if IS_ENABLED(CONFIG_DAX_DRIVER) +#if IS_ENABLED(CONFIG_FS_DAX) static long stripe_dax_direct_access(struct dm_target *ti, pgoff_t pgoff, long nr_pages, void **kaddr, pfn_t *pfn) { diff --git a/drivers/md/dm-writecache.c b/drivers/md/dm-writecache.c index 4b8991cde223..4f31591d2d25 100644 --- a/drivers/md/dm-writecache.c +++ b/drivers/md/dm-writecache.c @@ -38,7 +38,7 @@ #define BITMAP_GRANULARITY PAGE_SIZE #endif -#if IS_ENABLED(CONFIG_ARCH_HAS_PMEM_API) && IS_ENABLED(CONFIG_DAX_DRIVER) +#if IS_ENABLED(CONFIG_ARCH_HAS_PMEM_API) && IS_ENABLED(CONFIG_FS_DAX) #define DM_WRITECACHE_HAS_PMEM #endif diff --git a/drivers/md/dm.c b/drivers/md/dm.c index acc84dc1bded..b93fcc91176e 100644 --- a/drivers/md/dm.c +++ b/drivers/md/dm.c @@ -1783,7 +1783,7 @@ static struct mapped_device *alloc_dev(int minor) md->disk->private_data = md; sprintf(md->disk->disk_name, "dm-%d", minor); - if (IS_ENABLED(CONFIG_DAX_DRIVER)) { + if (IS_ENABLED(CONFIG_FS_DAX)) { md->dax_dev = alloc_dax(md, md->disk->disk_name, &dm_dax_ops, 0); if (IS_ERR(md->dax_dev)) { -- cgit v1.2.3 From afd586f0d06ce3d81b7c474499630fec88833828 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 29 Nov 2021 11:21:37 +0100 Subject: dax: remove CONFIG_DAX_DRIVER CONFIG_DAX_DRIVER only selects CONFIG_DAX now, so remove it. Signed-off-by: Christoph Hellwig Reviewed-by: Dan Williams Link: https://lore.kernel.org/r/20211129102203.2243509-4-hch@lst.de Signed-off-by: Dan Williams --- drivers/dax/Kconfig | 4 ---- drivers/nvdimm/Kconfig | 2 +- drivers/s390/block/Kconfig | 2 +- fs/fuse/Kconfig | 2 +- 4 files changed, 3 insertions(+), 7 deletions(-) diff --git a/drivers/dax/Kconfig b/drivers/dax/Kconfig index 15b442ef7b93..5fdf269a822e 100644 --- a/drivers/dax/Kconfig +++ b/drivers/dax/Kconfig @@ -1,8 +1,4 @@ # SPDX-License-Identifier: GPL-2.0-only -config DAX_DRIVER - select DAX - bool - menuconfig DAX tristate "DAX: direct access to differentiated memory" select SRCU diff --git a/drivers/nvdimm/Kconfig b/drivers/nvdimm/Kconfig index b7d1eb38b27d..347fe7afa583 100644 --- a/drivers/nvdimm/Kconfig +++ b/drivers/nvdimm/Kconfig @@ -22,7 +22,7 @@ if LIBNVDIMM config BLK_DEV_PMEM tristate "PMEM: Persistent memory block device support" default LIBNVDIMM - select DAX_DRIVER + select DAX select ND_BTT if BTT select ND_PFN if NVDIMM_PFN help diff --git a/drivers/s390/block/Kconfig b/drivers/s390/block/Kconfig index d0416dbd0cd8..e3710a762aba 100644 --- a/drivers/s390/block/Kconfig +++ b/drivers/s390/block/Kconfig @@ -5,7 +5,7 @@ comment "S/390 block device drivers" config DCSSBLK def_tristate m select FS_DAX_LIMITED - select DAX_DRIVER + select DAX prompt "DCSSBLK support" depends on S390 && BLOCK help diff --git a/fs/fuse/Kconfig b/fs/fuse/Kconfig index 40ce9a1c12e5..038ed0b9aaa5 100644 --- a/fs/fuse/Kconfig +++ b/fs/fuse/Kconfig @@ -45,7 +45,7 @@ config FUSE_DAX select INTERVAL_TREE depends on VIRTIO_FS depends on FS_DAX - depends on DAX_DRIVER + depends on DAX help This allows bypassing guest page cache and allows mapping host page cache directly in guest address space. -- cgit v1.2.3 From fb08a1908cb119a4585611d91461ab6d27756b14 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 29 Nov 2021 11:21:38 +0100 Subject: dax: simplify the dax_device <-> gendisk association Replace the dax_host_hash with an xarray indexed by the pointer value of the gendisk, and require explicitly calls from the block drivers that want to associate their gendisk with a dax_device. Signed-off-by: Christoph Hellwig Acked-by: Mike Snitzer Reviewed-by: Darrick J. Wong Link: https://lore.kernel.org/r/20211129102203.2243509-5-hch@lst.de Signed-off-by: Dan Williams --- drivers/dax/bus.c | 6 +-- drivers/dax/super.c | 109 +++++++++++-------------------------------- drivers/md/dm.c | 6 ++- drivers/nvdimm/pmem.c | 10 +++- drivers/s390/block/dcssblk.c | 11 +++-- fs/fuse/virtio_fs.c | 2 +- include/linux/dax.h | 19 ++++++-- 7 files changed, 66 insertions(+), 97 deletions(-) diff --git a/drivers/dax/bus.c b/drivers/dax/bus.c index 452cf7860926..6683d42c32c5 100644 --- a/drivers/dax/bus.c +++ b/drivers/dax/bus.c @@ -1321,10 +1321,10 @@ struct dev_dax *devm_create_dev_dax(struct dev_dax_data *data) } /* - * No 'host' or dax_operations since there is no access to this - * device outside of mmap of the resulting character device. + * No dax_operations since there is no access to this device outside of + * mmap of the resulting character device. */ - dax_dev = alloc_dax(dev_dax, NULL, NULL, DAXDEV_F_SYNC); + dax_dev = alloc_dax(dev_dax, NULL, DAXDEV_F_SYNC); if (IS_ERR(dax_dev)) { rc = PTR_ERR(dax_dev); goto err_alloc_dax; diff --git a/drivers/dax/super.c b/drivers/dax/super.c index e20d0cef10a1..bf77c3da5d56 100644 --- a/drivers/dax/super.c +++ b/drivers/dax/super.c @@ -7,10 +7,8 @@ #include #include #include -#include #include #include -#include #include #include #include @@ -21,15 +19,12 @@ * struct dax_device - anchor object for dax services * @inode: core vfs * @cdev: optional character interface for "device dax" - * @host: optional name for lookups where the device path is not available * @private: dax driver private data * @flags: state and boolean properties */ struct dax_device { - struct hlist_node list; struct inode inode; struct cdev cdev; - const char *host; void *private; unsigned long flags; const struct dax_operations *ops; @@ -42,10 +37,6 @@ static DEFINE_IDA(dax_minor_ida); static struct kmem_cache *dax_cache __read_mostly; static struct super_block *dax_superblock __read_mostly; -#define DAX_HASH_SIZE (PAGE_SIZE / sizeof(struct hlist_head)) -static struct hlist_head dax_host_list[DAX_HASH_SIZE]; -static DEFINE_SPINLOCK(dax_host_lock); - int dax_read_lock(void) { return srcu_read_lock(&dax_srcu); @@ -58,13 +49,22 @@ void dax_read_unlock(int id) } EXPORT_SYMBOL_GPL(dax_read_unlock); -static int dax_host_hash(const char *host) +#if defined(CONFIG_BLOCK) && defined(CONFIG_FS_DAX) +#include + +static DEFINE_XARRAY(dax_hosts); + +int dax_add_host(struct dax_device *dax_dev, struct gendisk *disk) { - return hashlen_hash(hashlen_string("DAX", host)) % DAX_HASH_SIZE; + return xa_insert(&dax_hosts, (unsigned long)disk, dax_dev, GFP_KERNEL); } +EXPORT_SYMBOL_GPL(dax_add_host); -#if defined(CONFIG_BLOCK) && defined(CONFIG_FS_DAX) -#include +void dax_remove_host(struct gendisk *disk) +{ + xa_erase(&dax_hosts, (unsigned long)disk); +} +EXPORT_SYMBOL_GPL(dax_remove_host); int bdev_dax_pgoff(struct block_device *bdev, sector_t sector, size_t size, pgoff_t *pgoff) @@ -81,41 +81,24 @@ int bdev_dax_pgoff(struct block_device *bdev, sector_t sector, size_t size, EXPORT_SYMBOL(bdev_dax_pgoff); /** - * dax_get_by_host() - temporary lookup mechanism for filesystem-dax - * @host: alternate name for the device registered by a dax driver + * fs_dax_get_by_bdev() - temporary lookup mechanism for filesystem-dax + * @bdev: block device to find a dax_device for */ -static struct dax_device *dax_get_by_host(const char *host) +struct dax_device *fs_dax_get_by_bdev(struct block_device *bdev) { - struct dax_device *dax_dev, *found = NULL; - int hash, id; + struct dax_device *dax_dev; + int id; - if (!host) + if (!blk_queue_dax(bdev->bd_disk->queue)) return NULL; - hash = dax_host_hash(host); - id = dax_read_lock(); - spin_lock(&dax_host_lock); - hlist_for_each_entry(dax_dev, &dax_host_list[hash], list) { - if (!dax_alive(dax_dev) - || strcmp(host, dax_dev->host) != 0) - continue; - - if (igrab(&dax_dev->inode)) - found = dax_dev; - break; - } - spin_unlock(&dax_host_lock); + dax_dev = xa_load(&dax_hosts, (unsigned long)bdev->bd_disk); + if (!dax_dev || !dax_alive(dax_dev) || !igrab(&dax_dev->inode)) + dax_dev = NULL; dax_read_unlock(id); - return found; -} - -struct dax_device *fs_dax_get_by_bdev(struct block_device *bdev) -{ - if (!blk_queue_dax(bdev->bd_disk->queue)) - return NULL; - return dax_get_by_host(bdev->bd_disk->disk_name); + return dax_dev; } EXPORT_SYMBOL_GPL(fs_dax_get_by_bdev); @@ -361,12 +344,7 @@ void kill_dax(struct dax_device *dax_dev) return; clear_bit(DAXDEV_ALIVE, &dax_dev->flags); - synchronize_srcu(&dax_srcu); - - spin_lock(&dax_host_lock); - hlist_del_init(&dax_dev->list); - spin_unlock(&dax_host_lock); } EXPORT_SYMBOL_GPL(kill_dax); @@ -398,8 +376,6 @@ static struct dax_device *to_dax_dev(struct inode *inode) static void dax_free_inode(struct inode *inode) { struct dax_device *dax_dev = to_dax_dev(inode); - kfree(dax_dev->host); - dax_dev->host = NULL; if (inode->i_rdev) ida_simple_remove(&dax_minor_ida, iminor(inode)); kmem_cache_free(dax_cache, dax_dev); @@ -474,54 +450,25 @@ static struct dax_device *dax_dev_get(dev_t devt) return dax_dev; } -static void dax_add_host(struct dax_device *dax_dev, const char *host) -{ - int hash; - - /* - * Unconditionally init dax_dev since it's coming from a - * non-zeroed slab cache - */ - INIT_HLIST_NODE(&dax_dev->list); - dax_dev->host = host; - if (!host) - return; - - hash = dax_host_hash(host); - spin_lock(&dax_host_lock); - hlist_add_head(&dax_dev->list, &dax_host_list[hash]); - spin_unlock(&dax_host_lock); -} - -struct dax_device *alloc_dax(void *private, const char *__host, - const struct dax_operations *ops, unsigned long flags) +struct dax_device *alloc_dax(void *private, const struct dax_operations *ops, + unsigned long flags) { struct dax_device *dax_dev; - const char *host; dev_t devt; int minor; - if (ops && !ops->zero_page_range) { - pr_debug("%s: error: device does not provide dax" - " operation zero_page_range()\n", - __host ? __host : "Unknown"); + if (WARN_ON_ONCE(ops && !ops->zero_page_range)) return ERR_PTR(-EINVAL); - } - - host = kstrdup(__host, GFP_KERNEL); - if (__host && !host) - return ERR_PTR(-ENOMEM); minor = ida_simple_get(&dax_minor_ida, 0, MINORMASK+1, GFP_KERNEL); if (minor < 0) - goto err_minor; + return ERR_PTR(-ENOMEM); devt = MKDEV(MAJOR(dax_devt), minor); dax_dev = dax_dev_get(devt); if (!dax_dev) goto err_dev; - dax_add_host(dax_dev, host); dax_dev->ops = ops; dax_dev->private = private; if (flags & DAXDEV_F_SYNC) @@ -531,8 +478,6 @@ struct dax_device *alloc_dax(void *private, const char *__host, err_dev: ida_simple_remove(&dax_minor_ida, minor); - err_minor: - kfree(host); return ERR_PTR(-ENOMEM); } EXPORT_SYMBOL_GPL(alloc_dax); diff --git a/drivers/md/dm.c b/drivers/md/dm.c index b93fcc91176e..a8c650276b32 100644 --- a/drivers/md/dm.c +++ b/drivers/md/dm.c @@ -1683,6 +1683,7 @@ static void cleanup_mapped_device(struct mapped_device *md) bioset_exit(&md->io_bs); if (md->dax_dev) { + dax_remove_host(md->disk); kill_dax(md->dax_dev); put_dax(md->dax_dev); md->dax_dev = NULL; @@ -1784,12 +1785,13 @@ static struct mapped_device *alloc_dev(int minor) sprintf(md->disk->disk_name, "dm-%d", minor); if (IS_ENABLED(CONFIG_FS_DAX)) { - md->dax_dev = alloc_dax(md, md->disk->disk_name, - &dm_dax_ops, 0); + md->dax_dev = alloc_dax(md, &dm_dax_ops, 0); if (IS_ERR(md->dax_dev)) { md->dax_dev = NULL; goto bad; } + if (dax_add_host(md->dax_dev, md->disk)) + goto bad; } format_dev_t(md->name, MKDEV(_major, minor)); diff --git a/drivers/nvdimm/pmem.c b/drivers/nvdimm/pmem.c index fe7ece1534e1..1018f0d44acb 100644 --- a/drivers/nvdimm/pmem.c +++ b/drivers/nvdimm/pmem.c @@ -379,6 +379,7 @@ static void pmem_release_disk(void *__pmem) { struct pmem_device *pmem = __pmem; + dax_remove_host(pmem->disk); kill_dax(pmem->dax_dev); put_dax(pmem->dax_dev); del_gendisk(pmem->disk); @@ -497,17 +498,20 @@ static int pmem_attach_disk(struct device *dev, if (is_nvdimm_sync(nd_region)) flags = DAXDEV_F_SYNC; - dax_dev = alloc_dax(pmem, disk->disk_name, &pmem_dax_ops, flags); + dax_dev = alloc_dax(pmem, &pmem_dax_ops, flags); if (IS_ERR(dax_dev)) { rc = PTR_ERR(dax_dev); goto out; } + rc = dax_add_host(dax_dev, disk); + if (rc) + goto out_cleanup_dax; dax_write_cache(dax_dev, nvdimm_has_cache(nd_region)); pmem->dax_dev = dax_dev; rc = device_add_disk(dev, disk, pmem_attribute_groups); if (rc) - goto out_cleanup_dax; + goto out_remove_host; if (devm_add_action_or_reset(dev, pmem_release_disk, pmem)) return -ENOMEM; @@ -519,6 +523,8 @@ static int pmem_attach_disk(struct device *dev, dev_warn(dev, "'badblocks' notification disabled\n"); return 0; +out_remove_host: + dax_remove_host(pmem->disk); out_cleanup_dax: kill_dax(pmem->dax_dev); put_dax(pmem->dax_dev); diff --git a/drivers/s390/block/dcssblk.c b/drivers/s390/block/dcssblk.c index 27ab888b44d0..657e492f2bc2 100644 --- a/drivers/s390/block/dcssblk.c +++ b/drivers/s390/block/dcssblk.c @@ -687,18 +687,21 @@ dcssblk_add_store(struct device *dev, struct device_attribute *attr, const char if (rc) goto put_dev; - dev_info->dax_dev = alloc_dax(dev_info, dev_info->gd->disk_name, - &dcssblk_dax_ops, DAXDEV_F_SYNC); + dev_info->dax_dev = alloc_dax(dev_info, &dcssblk_dax_ops, + DAXDEV_F_SYNC); if (IS_ERR(dev_info->dax_dev)) { rc = PTR_ERR(dev_info->dax_dev); dev_info->dax_dev = NULL; goto put_dev; } + rc = dax_add_host(dev_info->dax_dev, dev_info->gd); + if (rc) + goto out_dax; get_device(&dev_info->dev); rc = device_add_disk(&dev_info->dev, dev_info->gd, NULL); if (rc) - goto out_dax; + goto out_dax_host; switch (dev_info->segment_type) { case SEG_TYPE_SR: @@ -714,6 +717,8 @@ dcssblk_add_store(struct device *dev, struct device_attribute *attr, const char rc = count; goto out; +out_dax_host: + dax_remove_host(dev_info->gd); out_dax: put_device(&dev_info->dev); kill_dax(dev_info->dax_dev); diff --git a/fs/fuse/virtio_fs.c b/fs/fuse/virtio_fs.c index 4cfa4bc1f579..242cc1c0d7ed 100644 --- a/fs/fuse/virtio_fs.c +++ b/fs/fuse/virtio_fs.c @@ -850,7 +850,7 @@ static int virtio_fs_setup_dax(struct virtio_device *vdev, struct virtio_fs *fs) dev_dbg(&vdev->dev, "%s: window kaddr 0x%px phys_addr 0x%llx len 0x%llx\n", __func__, fs->window_kaddr, cache_reg.addr, cache_reg.len); - fs->dax_dev = alloc_dax(fs, NULL, &virtio_fs_dax_ops, 0); + fs->dax_dev = alloc_dax(fs, &virtio_fs_dax_ops, 0); if (IS_ERR(fs->dax_dev)) return PTR_ERR(fs->dax_dev); diff --git a/include/linux/dax.h b/include/linux/dax.h index 8623caa67388..e2e9a67004cb 100644 --- a/include/linux/dax.h +++ b/include/linux/dax.h @@ -11,9 +11,11 @@ typedef unsigned long dax_entry_t; +struct dax_device; +struct gendisk; struct iomap_ops; struct iomap; -struct dax_device; + struct dax_operations { /* * direct_access: translate a device-relative @@ -39,8 +41,8 @@ struct dax_operations { }; #if IS_ENABLED(CONFIG_DAX) -struct dax_device *alloc_dax(void *private, const char *host, - const struct dax_operations *ops, unsigned long flags); +struct dax_device *alloc_dax(void *private, const struct dax_operations *ops, + unsigned long flags); void put_dax(struct dax_device *dax_dev); void kill_dax(struct dax_device *dax_dev); void dax_write_cache(struct dax_device *dax_dev, bool wc); @@ -68,7 +70,7 @@ static inline bool daxdev_mapping_supported(struct vm_area_struct *vma, return dax_synchronous(dax_dev); } #else -static inline struct dax_device *alloc_dax(void *private, const char *host, +static inline struct dax_device *alloc_dax(void *private, const struct dax_operations *ops, unsigned long flags) { /* @@ -107,6 +109,8 @@ static inline bool daxdev_mapping_supported(struct vm_area_struct *vma, struct writeback_control; int bdev_dax_pgoff(struct block_device *, sector_t, size_t, pgoff_t *pgoff); #if IS_ENABLED(CONFIG_FS_DAX) +int dax_add_host(struct dax_device *dax_dev, struct gendisk *disk); +void dax_remove_host(struct gendisk *disk); bool generic_fsdax_supported(struct dax_device *dax_dev, struct block_device *bdev, int blocksize, sector_t start, sector_t sectors); @@ -128,6 +132,13 @@ struct page *dax_layout_busy_page_range(struct address_space *mapping, loff_t st dax_entry_t dax_lock_page(struct page *page); void dax_unlock_page(struct page *page, dax_entry_t cookie); #else +static inline int dax_add_host(struct dax_device *dax_dev, struct gendisk *disk) +{ + return 0; +} +static inline void dax_remove_host(struct gendisk *disk) +{ +} #define generic_fsdax_supported NULL static inline bool dax_supported(struct dax_device *dax_dev, -- cgit v1.2.3 From 586f61682816f0cf7865b2dab7210b8f5339f834 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 29 Nov 2021 11:21:39 +0100 Subject: dax: remove the pgmap sanity checks in generic_fsdax_supported Drivers that register a dax_dev should make sure it works, no need to double check from the file system. Signed-off-by: Christoph Hellwig Reviewed-by: Dan Williams Reviewed-by: Darrick J. Wong Link: https://lore.kernel.org/r/20211129102203.2243509-6-hch@lst.de Signed-off-by: Dan Williams --- drivers/dax/super.c | 49 +------------------------------------------------ 1 file changed, 1 insertion(+), 48 deletions(-) diff --git a/drivers/dax/super.c b/drivers/dax/super.c index bf77c3da5d56..c8500b7e2d8a 100644 --- a/drivers/dax/super.c +++ b/drivers/dax/super.c @@ -106,13 +106,9 @@ bool generic_fsdax_supported(struct dax_device *dax_dev, struct block_device *bdev, int blocksize, sector_t start, sector_t sectors) { - bool dax_enabled = false; pgoff_t pgoff, pgoff_end; - void *kaddr, *end_kaddr; - pfn_t pfn, end_pfn; sector_t last_page; - long len, len2; - int err, id; + int err; if (blocksize != PAGE_SIZE) { pr_info("%pg: error: unsupported blocksize for dax\n", bdev); @@ -137,49 +133,6 @@ bool generic_fsdax_supported(struct dax_device *dax_dev, return false; } - id = dax_read_lock(); - len = dax_direct_access(dax_dev, pgoff, 1, &kaddr, &pfn); - len2 = dax_direct_access(dax_dev, pgoff_end, 1, &end_kaddr, &end_pfn); - - if (len < 1 || len2 < 1) { - pr_info("%pg: error: dax access failed (%ld)\n", - bdev, len < 1 ? len : len2); - dax_read_unlock(id); - return false; - } - - if (IS_ENABLED(CONFIG_FS_DAX_LIMITED) && pfn_t_special(pfn)) { - /* - * An arch that has enabled the pmem api should also - * have its drivers support pfn_t_devmap() - * - * This is a developer warning and should not trigger in - * production. dax_flush() will crash since it depends - * on being able to do (page_address(pfn_to_page())). - */ - WARN_ON(IS_ENABLED(CONFIG_ARCH_HAS_PMEM_API)); - dax_enabled = true; - } else if (pfn_t_devmap(pfn) && pfn_t_devmap(end_pfn)) { - struct dev_pagemap *pgmap, *end_pgmap; - - pgmap = get_dev_pagemap(pfn_t_to_pfn(pfn), NULL); - end_pgmap = get_dev_pagemap(pfn_t_to_pfn(end_pfn), NULL); - if (pgmap && pgmap == end_pgmap && pgmap->type == MEMORY_DEVICE_FS_DAX - && pfn_t_to_page(pfn)->pgmap == pgmap - && pfn_t_to_page(end_pfn)->pgmap == pgmap - && pfn_t_to_pfn(pfn) == PHYS_PFN(__pa(kaddr)) - && pfn_t_to_pfn(end_pfn) == PHYS_PFN(__pa(end_kaddr))) - dax_enabled = true; - put_dev_pagemap(pgmap); - put_dev_pagemap(end_pgmap); - - } - dax_read_unlock(id); - - if (!dax_enabled) { - pr_info("%pg: error: dax support not enabled\n", bdev); - return false; - } return true; } EXPORT_SYMBOL_GPL(generic_fsdax_supported); -- cgit v1.2.3 From 0c445871388f4bac74ea74e8c7a12c6c05c6a427 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 29 Nov 2021 11:21:40 +0100 Subject: dax: move the partition alignment check into fs_dax_get_by_bdev fs_dax_get_by_bdev is the primary interface to find a dax device for a block device, so move the partition alignment check there instead of wiring it up through ->dax_supported. Signed-off-by: Christoph Hellwig Reviewed-by: Dan Williams Reviewed-by: Darrick J. Wong Link: https://lore.kernel.org/r/20211129102203.2243509-7-hch@lst.de Signed-off-by: Dan Williams --- drivers/dax/super.c | 23 ++++++----------------- 1 file changed, 6 insertions(+), 17 deletions(-) diff --git a/drivers/dax/super.c b/drivers/dax/super.c index c8500b7e2d8a..f2cef47bdeaf 100644 --- a/drivers/dax/super.c +++ b/drivers/dax/super.c @@ -92,6 +92,12 @@ struct dax_device *fs_dax_get_by_bdev(struct block_device *bdev) if (!blk_queue_dax(bdev->bd_disk->queue)) return NULL; + if ((get_start_sect(bdev) * SECTOR_SIZE) % PAGE_SIZE || + (bdev_nr_sectors(bdev) * SECTOR_SIZE) % PAGE_SIZE) { + pr_info("%pg: error: unaligned partition for dax\n", bdev); + return NULL; + } + id = dax_read_lock(); dax_dev = xa_load(&dax_hosts, (unsigned long)bdev->bd_disk); if (!dax_dev || !dax_alive(dax_dev) || !igrab(&dax_dev->inode)) @@ -106,10 +112,6 @@ bool generic_fsdax_supported(struct dax_device *dax_dev, struct block_device *bdev, int blocksize, sector_t start, sector_t sectors) { - pgoff_t pgoff, pgoff_end; - sector_t last_page; - int err; - if (blocksize != PAGE_SIZE) { pr_info("%pg: error: unsupported blocksize for dax\n", bdev); return false; @@ -120,19 +122,6 @@ bool generic_fsdax_supported(struct dax_device *dax_dev, return false; } - err = bdev_dax_pgoff(bdev, start, PAGE_SIZE, &pgoff); - if (err) { - pr_info("%pg: error: unaligned partition for dax\n", bdev); - return false; - } - - last_page = PFN_DOWN((start + sectors - 1) * 512) * PAGE_SIZE / 512; - err = bdev_dax_pgoff(bdev, last_page, PAGE_SIZE, &pgoff_end); - if (err) { - pr_info("%pg: error: unaligned partition for dax\n", bdev); - return false; - } - return true; } EXPORT_SYMBOL_GPL(generic_fsdax_supported); -- cgit v1.2.3 From 679a99495b8fda800037b25af8cd990eb7dd72c9 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 29 Nov 2021 11:21:41 +0100 Subject: xfs: factor out a xfs_setup_dax_always helper Factor out another DAX setup helper to simplify future changes. Also move the experimental warning after the checks to not clutter the log too much if the setup failed. Signed-off-by: Christoph Hellwig Reviewed-by: Dan Williams Reviewed-by: Darrick J. Wong Link: https://lore.kernel.org/r/20211129102203.2243509-8-hch@lst.de Signed-off-by: Dan Williams --- fs/xfs/xfs_super.c | 47 ++++++++++++++++++++++++++++------------------- 1 file changed, 28 insertions(+), 19 deletions(-) diff --git a/fs/xfs/xfs_super.c b/fs/xfs/xfs_super.c index e21459f9923a..875fd3151d6c 100644 --- a/fs/xfs/xfs_super.c +++ b/fs/xfs/xfs_super.c @@ -340,6 +340,32 @@ xfs_buftarg_is_dax( bdev_nr_sectors(bt->bt_bdev)); } +static int +xfs_setup_dax_always( + struct xfs_mount *mp) +{ + struct super_block *sb = mp->m_super; + + if (!xfs_buftarg_is_dax(sb, mp->m_ddev_targp) && + (!mp->m_rtdev_targp || !xfs_buftarg_is_dax(sb, mp->m_rtdev_targp))) { + xfs_alert(mp, + "DAX unsupported by block device. Turning off DAX."); + goto disable_dax; + } + + if (xfs_has_reflink(mp)) { + xfs_alert(mp, "DAX and reflink cannot be used together!"); + return -EINVAL; + } + + xfs_warn(mp, "DAX enabled. Warning: EXPERIMENTAL, use at your own risk"); + return 0; + +disable_dax: + xfs_mount_set_dax_mode(mp, XFS_DAX_NEVER); + return 0; +} + STATIC int xfs_blkdev_get( xfs_mount_t *mp, @@ -1593,26 +1619,9 @@ xfs_fs_fill_super( sb->s_flags |= SB_I_VERSION; if (xfs_has_dax_always(mp)) { - bool rtdev_is_dax = false, datadev_is_dax; - - xfs_warn(mp, - "DAX enabled. Warning: EXPERIMENTAL, use at your own risk"); - - datadev_is_dax = xfs_buftarg_is_dax(sb, mp->m_ddev_targp); - if (mp->m_rtdev_targp) - rtdev_is_dax = xfs_buftarg_is_dax(sb, - mp->m_rtdev_targp); - if (!rtdev_is_dax && !datadev_is_dax) { - xfs_alert(mp, - "DAX unsupported by block device. Turning off DAX."); - xfs_mount_set_dax_mode(mp, XFS_DAX_NEVER); - } - if (xfs_has_reflink(mp)) { - xfs_alert(mp, - "DAX and reflink cannot be used together!"); - error = -EINVAL; + error = xfs_setup_dax_always(mp); + if (error) goto out_filestream_unmount; - } } if (xfs_has_discard(mp)) { -- cgit v1.2.3 From 7b0800d00dae8c897398abaf61e82db0d67d7afc Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 29 Nov 2021 11:21:42 +0100 Subject: dax: remove dax_capable Just open code the block size and dax_dev == NULL checks in the callers. Signed-off-by: Christoph Hellwig Acked-by: Mike Snitzer Reviewed-by: Gao Xiang [erofs] Reviewed-by: Dan Williams Reviewed-by: Darrick J. Wong Link: https://lore.kernel.org/r/20211129102203.2243509-9-hch@lst.de Signed-off-by: Dan Williams --- drivers/dax/super.c | 36 ------------------------------------ drivers/md/dm-table.c | 22 +++++++++++----------- drivers/md/dm.c | 21 --------------------- drivers/md/dm.h | 4 ---- drivers/nvdimm/pmem.c | 1 - drivers/s390/block/dcssblk.c | 1 - fs/erofs/super.c | 11 +++++++---- fs/ext2/super.c | 6 ++++-- fs/ext4/super.c | 9 ++++++--- fs/xfs/xfs_super.c | 21 ++++++++------------- include/linux/dax.h | 14 -------------- 11 files changed, 36 insertions(+), 110 deletions(-) diff --git a/drivers/dax/super.c b/drivers/dax/super.c index f2cef47bdeaf..90b5733f5a70 100644 --- a/drivers/dax/super.c +++ b/drivers/dax/super.c @@ -107,42 +107,6 @@ struct dax_device *fs_dax_get_by_bdev(struct block_device *bdev) return dax_dev; } EXPORT_SYMBOL_GPL(fs_dax_get_by_bdev); - -bool generic_fsdax_supported(struct dax_device *dax_dev, - struct block_device *bdev, int blocksize, sector_t start, - sector_t sectors) -{ - if (blocksize != PAGE_SIZE) { - pr_info("%pg: error: unsupported blocksize for dax\n", bdev); - return false; - } - - if (!dax_dev) { - pr_debug("%pg: error: dax unsupported by block device\n", bdev); - return false; - } - - return true; -} -EXPORT_SYMBOL_GPL(generic_fsdax_supported); - -bool dax_supported(struct dax_device *dax_dev, struct block_device *bdev, - int blocksize, sector_t start, sector_t len) -{ - bool ret = false; - int id; - - if (!dax_dev) - return false; - - id = dax_read_lock(); - if (dax_alive(dax_dev) && dax_dev->ops->dax_supported) - ret = dax_dev->ops->dax_supported(dax_dev, bdev, blocksize, - start, len); - dax_read_unlock(id); - return ret; -} -EXPORT_SYMBOL_GPL(dax_supported); #endif /* CONFIG_BLOCK && CONFIG_FS_DAX */ enum dax_device_flags { diff --git a/drivers/md/dm-table.c b/drivers/md/dm-table.c index aa173f5bdc3d..e43096cfe9e2 100644 --- a/drivers/md/dm-table.c +++ b/drivers/md/dm-table.c @@ -806,12 +806,14 @@ void dm_table_set_type(struct dm_table *t, enum dm_queue_mode type) EXPORT_SYMBOL_GPL(dm_table_set_type); /* validate the dax capability of the target device span */ -int device_not_dax_capable(struct dm_target *ti, struct dm_dev *dev, +static int device_not_dax_capable(struct dm_target *ti, struct dm_dev *dev, sector_t start, sector_t len, void *data) { - int blocksize = *(int *) data; + if (dev->dax_dev) + return false; - return !dax_supported(dev->dax_dev, dev->bdev, blocksize, start, len); + DMDEBUG("%pg: error: dax unsupported by block device", dev->bdev); + return true; } /* Check devices support synchronous DAX */ @@ -821,8 +823,8 @@ static int device_not_dax_synchronous_capable(struct dm_target *ti, struct dm_de return !dev->dax_dev || !dax_synchronous(dev->dax_dev); } -bool dm_table_supports_dax(struct dm_table *t, - iterate_devices_callout_fn iterate_fn, int *blocksize) +static bool dm_table_supports_dax(struct dm_table *t, + iterate_devices_callout_fn iterate_fn) { struct dm_target *ti; unsigned i; @@ -835,7 +837,7 @@ bool dm_table_supports_dax(struct dm_table *t, return false; if (!ti->type->iterate_devices || - ti->type->iterate_devices(ti, iterate_fn, blocksize)) + ti->type->iterate_devices(ti, iterate_fn, NULL)) return false; } @@ -862,7 +864,6 @@ static int dm_table_determine_type(struct dm_table *t) struct dm_target *tgt; struct list_head *devices = dm_table_get_devices(t); enum dm_queue_mode live_md_type = dm_get_md_type(t->md); - int page_size = PAGE_SIZE; if (t->type != DM_TYPE_NONE) { /* target already set the table's type */ @@ -906,7 +907,7 @@ static int dm_table_determine_type(struct dm_table *t) verify_bio_based: /* We must use this table as bio-based */ t->type = DM_TYPE_BIO_BASED; - if (dm_table_supports_dax(t, device_not_dax_capable, &page_size) || + if (dm_table_supports_dax(t, device_not_dax_capable) || (list_empty(devices) && live_md_type == DM_TYPE_DAX_BIO_BASED)) { t->type = DM_TYPE_DAX_BIO_BASED; } @@ -1976,7 +1977,6 @@ int dm_table_set_restrictions(struct dm_table *t, struct request_queue *q, struct queue_limits *limits) { bool wc = false, fua = false; - int page_size = PAGE_SIZE; int r; /* @@ -2010,9 +2010,9 @@ int dm_table_set_restrictions(struct dm_table *t, struct request_queue *q, } blk_queue_write_cache(q, wc, fua); - if (dm_table_supports_dax(t, device_not_dax_capable, &page_size)) { + if (dm_table_supports_dax(t, device_not_dax_capable)) { blk_queue_flag_set(QUEUE_FLAG_DAX, q); - if (dm_table_supports_dax(t, device_not_dax_synchronous_capable, NULL)) + if (dm_table_supports_dax(t, device_not_dax_synchronous_capable)) set_dax_synchronous(t->md->dax_dev); } else diff --git a/drivers/md/dm.c b/drivers/md/dm.c index a8c650276b32..4eba27e75c23 100644 --- a/drivers/md/dm.c +++ b/drivers/md/dm.c @@ -1027,26 +1027,6 @@ static long dm_dax_direct_access(struct dax_device *dax_dev, pgoff_t pgoff, return ret; } -static bool dm_dax_supported(struct dax_device *dax_dev, struct block_device *bdev, - int blocksize, sector_t start, sector_t len) -{ - struct mapped_device *md = dax_get_private(dax_dev); - struct dm_table *map; - bool ret = false; - int srcu_idx; - - map = dm_get_live_table(md, &srcu_idx); - if (!map) - goto out; - - ret = dm_table_supports_dax(map, device_not_dax_capable, &blocksize); - -out: - dm_put_live_table(md, srcu_idx); - - return ret; -} - static size_t dm_dax_copy_from_iter(struct dax_device *dax_dev, pgoff_t pgoff, void *addr, size_t bytes, struct iov_iter *i) { @@ -3044,7 +3024,6 @@ static const struct block_device_operations dm_rq_blk_dops = { static const struct dax_operations dm_dax_ops = { .direct_access = dm_dax_direct_access, - .dax_supported = dm_dax_supported, .copy_from_iter = dm_dax_copy_from_iter, .copy_to_iter = dm_dax_copy_to_iter, .zero_page_range = dm_dax_zero_page_range, diff --git a/drivers/md/dm.h b/drivers/md/dm.h index 742d9c80efe1..9013dc1a7b00 100644 --- a/drivers/md/dm.h +++ b/drivers/md/dm.h @@ -73,10 +73,6 @@ bool dm_table_bio_based(struct dm_table *t); bool dm_table_request_based(struct dm_table *t); void dm_table_free_md_mempools(struct dm_table *t); struct dm_md_mempools *dm_table_get_md_mempools(struct dm_table *t); -bool dm_table_supports_dax(struct dm_table *t, iterate_devices_callout_fn fn, - int *blocksize); -int device_not_dax_capable(struct dm_target *ti, struct dm_dev *dev, - sector_t start, sector_t len, void *data); void dm_lock_md_type(struct mapped_device *md); void dm_unlock_md_type(struct mapped_device *md); diff --git a/drivers/nvdimm/pmem.c b/drivers/nvdimm/pmem.c index 1018f0d44acb..4190c8c46ca8 100644 --- a/drivers/nvdimm/pmem.c +++ b/drivers/nvdimm/pmem.c @@ -321,7 +321,6 @@ static size_t pmem_copy_to_iter(struct dax_device *dax_dev, pgoff_t pgoff, static const struct dax_operations pmem_dax_ops = { .direct_access = pmem_dax_direct_access, - .dax_supported = generic_fsdax_supported, .copy_from_iter = pmem_copy_from_iter, .copy_to_iter = pmem_copy_to_iter, .zero_page_range = pmem_dax_zero_page_range, diff --git a/drivers/s390/block/dcssblk.c b/drivers/s390/block/dcssblk.c index 657e492f2bc2..e65e83764d1c 100644 --- a/drivers/s390/block/dcssblk.c +++ b/drivers/s390/block/dcssblk.c @@ -72,7 +72,6 @@ static int dcssblk_dax_zero_page_range(struct dax_device *dax_dev, static const struct dax_operations dcssblk_dax_ops = { .direct_access = dcssblk_dax_direct_access, - .dax_supported = generic_fsdax_supported, .copy_from_iter = dcssblk_dax_copy_from_iter, .copy_to_iter = dcssblk_dax_copy_to_iter, .zero_page_range = dcssblk_dax_zero_page_range, diff --git a/fs/erofs/super.c b/fs/erofs/super.c index 6a969b1e0ee6..0aed886473c8 100644 --- a/fs/erofs/super.c +++ b/fs/erofs/super.c @@ -652,10 +652,13 @@ static int erofs_fc_fill_super(struct super_block *sb, struct fs_context *fc) if (err) return err; - if (test_opt(&sbi->opt, DAX_ALWAYS) && - !dax_supported(sbi->dax_dev, sb->s_bdev, EROFS_BLKSIZ, 0, bdev_nr_sectors(sb->s_bdev))) { - errorfc(fc, "DAX unsupported by block device. Turning off DAX."); - clear_opt(&sbi->opt, DAX_ALWAYS); + if (test_opt(&sbi->opt, DAX_ALWAYS)) { + BUILD_BUG_ON(EROFS_BLKSIZ != PAGE_SIZE); + + if (!sbi->dax_dev) { + errorfc(fc, "DAX unsupported by block device. Turning off DAX."); + clear_opt(&sbi->opt, DAX_ALWAYS); + } } sb->s_flags |= SB_RDONLY | SB_NOATIME; sb->s_maxbytes = MAX_LFS_FILESIZE; diff --git a/fs/ext2/super.c b/fs/ext2/super.c index d8d580b609ba..a964066a80aa 100644 --- a/fs/ext2/super.c +++ b/fs/ext2/super.c @@ -946,11 +946,13 @@ static int ext2_fill_super(struct super_block *sb, void *data, int silent) blocksize = BLOCK_SIZE << le32_to_cpu(sbi->s_es->s_log_block_size); if (test_opt(sb, DAX)) { - if (!dax_supported(dax_dev, sb->s_bdev, blocksize, 0, - bdev_nr_sectors(sb->s_bdev))) { + if (!dax_dev) { ext2_msg(sb, KERN_ERR, "DAX unsupported by block device. Turning off DAX."); clear_opt(sbi->s_mount_opt, DAX); + } else if (blocksize != PAGE_SIZE) { + ext2_msg(sb, KERN_ERR, "unsupported blocksize for DAX\n"); + clear_opt(sbi->s_mount_opt, DAX); } } diff --git a/fs/ext4/super.c b/fs/ext4/super.c index 4e33b5eca694..fd3d68f10ee5 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -4299,9 +4299,12 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) goto failed_mount; } - if (dax_supported(dax_dev, sb->s_bdev, blocksize, 0, - bdev_nr_sectors(sb->s_bdev))) - set_bit(EXT4_FLAGS_BDEV_IS_DAX, &sbi->s_ext4_flags); + if (dax_dev) { + if (blocksize == PAGE_SIZE) + set_bit(EXT4_FLAGS_BDEV_IS_DAX, &sbi->s_ext4_flags); + else + ext4_msg(sb, KERN_ERR, "unsupported blocksize for DAX\n"); + } if (sbi->s_mount_opt & EXT4_MOUNT_DAX_ALWAYS) { if (ext4_has_feature_inline_data(sb)) { diff --git a/fs/xfs/xfs_super.c b/fs/xfs/xfs_super.c index 875fd3151d6c..c4297206f483 100644 --- a/fs/xfs/xfs_super.c +++ b/fs/xfs/xfs_super.c @@ -331,28 +331,23 @@ xfs_set_inode_alloc( return xfs_is_inode32(mp) ? maxagi : agcount; } -static bool -xfs_buftarg_is_dax( - struct super_block *sb, - struct xfs_buftarg *bt) -{ - return dax_supported(bt->bt_daxdev, bt->bt_bdev, sb->s_blocksize, 0, - bdev_nr_sectors(bt->bt_bdev)); -} - static int xfs_setup_dax_always( struct xfs_mount *mp) { - struct super_block *sb = mp->m_super; - - if (!xfs_buftarg_is_dax(sb, mp->m_ddev_targp) && - (!mp->m_rtdev_targp || !xfs_buftarg_is_dax(sb, mp->m_rtdev_targp))) { + if (!mp->m_ddev_targp->bt_daxdev && + (!mp->m_rtdev_targp || !mp->m_rtdev_targp->bt_daxdev)) { xfs_alert(mp, "DAX unsupported by block device. Turning off DAX."); goto disable_dax; } + if (mp->m_super->s_blocksize != PAGE_SIZE) { + xfs_alert(mp, + "DAX not supported for blocksize. Turning off DAX."); + goto disable_dax; + } + if (xfs_has_reflink(mp)) { xfs_alert(mp, "DAX and reflink cannot be used together!"); return -EINVAL; diff --git a/include/linux/dax.h b/include/linux/dax.h index e2e9a67004cb..439c3c70e347 100644 --- a/include/linux/dax.h +++ b/include/linux/dax.h @@ -111,12 +111,6 @@ int bdev_dax_pgoff(struct block_device *, sector_t, size_t, pgoff_t *pgoff); #if IS_ENABLED(CONFIG_FS_DAX) int dax_add_host(struct dax_device *dax_dev, struct gendisk *disk); void dax_remove_host(struct gendisk *disk); -bool generic_fsdax_supported(struct dax_device *dax_dev, - struct block_device *bdev, int blocksize, sector_t start, - sector_t sectors); - -bool dax_supported(struct dax_device *dax_dev, struct block_device *bdev, - int blocksize, sector_t start, sector_t len); static inline void fs_put_dax(struct dax_device *dax_dev) { @@ -139,14 +133,6 @@ static inline int dax_add_host(struct dax_device *dax_dev, struct gendisk *disk) static inline void dax_remove_host(struct gendisk *disk) { } -#define generic_fsdax_supported NULL - -static inline bool dax_supported(struct dax_device *dax_dev, - struct block_device *bdev, int blocksize, sector_t start, - sector_t len) -{ - return false; -} static inline void fs_put_dax(struct dax_device *dax_dev) { -- cgit v1.2.3 From f43e0065c264b2cb001952be17c9291c68d07182 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 29 Nov 2021 11:21:43 +0100 Subject: dm-linear: add a linear_dax_pgoff helper Add a helper to perform the entire remapping for DAX accesses. This helper open codes bdev_dax_pgoff given that the alignment checks have already been done by the submitting file system and don't need to be repeated. Signed-off-by: Christoph Hellwig Acked-by: Mike Snitzer Reviewed-by: Dan Williams Link: https://lore.kernel.org/r/20211129102203.2243509-10-hch@lst.de Signed-off-by: Dan Williams --- drivers/md/dm-linear.c | 49 +++++++++++++++---------------------------------- 1 file changed, 15 insertions(+), 34 deletions(-) diff --git a/drivers/md/dm-linear.c b/drivers/md/dm-linear.c index 0a260c35aeee..90de42f6743a 100644 --- a/drivers/md/dm-linear.c +++ b/drivers/md/dm-linear.c @@ -163,63 +163,44 @@ static int linear_iterate_devices(struct dm_target *ti, } #if IS_ENABLED(CONFIG_FS_DAX) +static struct dax_device *linear_dax_pgoff(struct dm_target *ti, pgoff_t *pgoff) +{ + struct linear_c *lc = ti->private; + sector_t sector = linear_map_sector(ti, *pgoff << PAGE_SECTORS_SHIFT); + + *pgoff = (get_start_sect(lc->dev->bdev) + sector) >> PAGE_SECTORS_SHIFT; + return lc->dev->dax_dev; +} + static long linear_dax_direct_access(struct dm_target *ti, pgoff_t pgoff, long nr_pages, void **kaddr, pfn_t *pfn) { - long ret; - struct linear_c *lc = ti->private; - struct block_device *bdev = lc->dev->bdev; - struct dax_device *dax_dev = lc->dev->dax_dev; - sector_t dev_sector, sector = pgoff * PAGE_SECTORS; - - dev_sector = linear_map_sector(ti, sector); - ret = bdev_dax_pgoff(bdev, dev_sector, nr_pages * PAGE_SIZE, &pgoff); - if (ret) - return ret; + struct dax_device *dax_dev = linear_dax_pgoff(ti, &pgoff); + return dax_direct_access(dax_dev, pgoff, nr_pages, kaddr, pfn); } static size_t linear_dax_copy_from_iter(struct dm_target *ti, pgoff_t pgoff, void *addr, size_t bytes, struct iov_iter *i) { - struct linear_c *lc = ti->private; - struct block_device *bdev = lc->dev->bdev; - struct dax_device *dax_dev = lc->dev->dax_dev; - sector_t dev_sector, sector = pgoff * PAGE_SECTORS; + struct dax_device *dax_dev = linear_dax_pgoff(ti, &pgoff); - dev_sector = linear_map_sector(ti, sector); - if (bdev_dax_pgoff(bdev, dev_sector, ALIGN(bytes, PAGE_SIZE), &pgoff)) - return 0; return dax_copy_from_iter(dax_dev, pgoff, addr, bytes, i); } static size_t linear_dax_copy_to_iter(struct dm_target *ti, pgoff_t pgoff, void *addr, size_t bytes, struct iov_iter *i) { - struct linear_c *lc = ti->private; - struct block_device *bdev = lc->dev->bdev; - struct dax_device *dax_dev = lc->dev->dax_dev; - sector_t dev_sector, sector = pgoff * PAGE_SECTORS; + struct dax_device *dax_dev = linear_dax_pgoff(ti, &pgoff); - dev_sector = linear_map_sector(ti, sector); - if (bdev_dax_pgoff(bdev, dev_sector, ALIGN(bytes, PAGE_SIZE), &pgoff)) - return 0; return dax_copy_to_iter(dax_dev, pgoff, addr, bytes, i); } static int linear_dax_zero_page_range(struct dm_target *ti, pgoff_t pgoff, size_t nr_pages) { - int ret; - struct linear_c *lc = ti->private; - struct block_device *bdev = lc->dev->bdev; - struct dax_device *dax_dev = lc->dev->dax_dev; - sector_t dev_sector, sector = pgoff * PAGE_SECTORS; - - dev_sector = linear_map_sector(ti, sector); - ret = bdev_dax_pgoff(bdev, dev_sector, nr_pages << PAGE_SHIFT, &pgoff); - if (ret) - return ret; + struct dax_device *dax_dev = linear_dax_pgoff(ti, &pgoff); + return dax_zero_page_range(dax_dev, pgoff, nr_pages); } -- cgit v1.2.3 From d19bd6756e7c400e264dba853eb35c94462f4ec4 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 29 Nov 2021 11:21:44 +0100 Subject: dm-log-writes: add a log_writes_dax_pgoff helper Add a helper to perform the entire remapping for DAX accesses. This helper open codes bdev_dax_pgoff given that the alignment checks have already been done by the submitting file system and don't need to be repeated. Signed-off-by: Christoph Hellwig Acked-by: Mike Snitzer Reviewed-by: Dan Williams Link: https://lore.kernel.org/r/20211129102203.2243509-11-hch@lst.de Signed-off-by: Dan Williams --- drivers/md/dm-log-writes.c | 42 +++++++++++++++++------------------------- 1 file changed, 17 insertions(+), 25 deletions(-) diff --git a/drivers/md/dm-log-writes.c b/drivers/md/dm-log-writes.c index 3155875d4e5b..cdb22e7a1d0d 100644 --- a/drivers/md/dm-log-writes.c +++ b/drivers/md/dm-log-writes.c @@ -947,17 +947,21 @@ static int log_dax(struct log_writes_c *lc, sector_t sector, size_t bytes, return 0; } +static struct dax_device *log_writes_dax_pgoff(struct dm_target *ti, + pgoff_t *pgoff) +{ + struct log_writes_c *lc = ti->private; + + *pgoff += (get_start_sect(lc->dev->bdev) >> PAGE_SECTORS_SHIFT); + return lc->dev->dax_dev; +} + static long log_writes_dax_direct_access(struct dm_target *ti, pgoff_t pgoff, long nr_pages, void **kaddr, pfn_t *pfn) { - struct log_writes_c *lc = ti->private; - sector_t sector = pgoff * PAGE_SECTORS; - int ret; + struct dax_device *dax_dev = log_writes_dax_pgoff(ti, &pgoff); - ret = bdev_dax_pgoff(lc->dev->bdev, sector, nr_pages * PAGE_SIZE, &pgoff); - if (ret) - return ret; - return dax_direct_access(lc->dev->dax_dev, pgoff, nr_pages, kaddr, pfn); + return dax_direct_access(dax_dev, pgoff, nr_pages, kaddr, pfn); } static size_t log_writes_dax_copy_from_iter(struct dm_target *ti, @@ -966,11 +970,9 @@ static size_t log_writes_dax_copy_from_iter(struct dm_target *ti, { struct log_writes_c *lc = ti->private; sector_t sector = pgoff * PAGE_SECTORS; + struct dax_device *dax_dev = log_writes_dax_pgoff(ti, &pgoff); int err; - if (bdev_dax_pgoff(lc->dev->bdev, sector, ALIGN(bytes, PAGE_SIZE), &pgoff)) - return 0; - /* Don't bother doing anything if logging has been disabled */ if (!lc->logging_enabled) goto dax_copy; @@ -981,34 +983,24 @@ static size_t log_writes_dax_copy_from_iter(struct dm_target *ti, return 0; } dax_copy: - return dax_copy_from_iter(lc->dev->dax_dev, pgoff, addr, bytes, i); + return dax_copy_from_iter(dax_dev, pgoff, addr, bytes, i); } static size_t log_writes_dax_copy_to_iter(struct dm_target *ti, pgoff_t pgoff, void *addr, size_t bytes, struct iov_iter *i) { - struct log_writes_c *lc = ti->private; - sector_t sector = pgoff * PAGE_SECTORS; + struct dax_device *dax_dev = log_writes_dax_pgoff(ti, &pgoff); - if (bdev_dax_pgoff(lc->dev->bdev, sector, ALIGN(bytes, PAGE_SIZE), &pgoff)) - return 0; - return dax_copy_to_iter(lc->dev->dax_dev, pgoff, addr, bytes, i); + return dax_copy_to_iter(dax_dev, pgoff, addr, bytes, i); } static int log_writes_dax_zero_page_range(struct dm_target *ti, pgoff_t pgoff, size_t nr_pages) { - int ret; - struct log_writes_c *lc = ti->private; - sector_t sector = pgoff * PAGE_SECTORS; + struct dax_device *dax_dev = log_writes_dax_pgoff(ti, &pgoff); - ret = bdev_dax_pgoff(lc->dev->bdev, sector, nr_pages << PAGE_SHIFT, - &pgoff); - if (ret) - return ret; - return dax_zero_page_range(lc->dev->dax_dev, pgoff, - nr_pages << PAGE_SHIFT); + return dax_zero_page_range(dax_dev, pgoff, nr_pages << PAGE_SHIFT); } #else -- cgit v1.2.3 From 2a68553e8aeb3e88cb0b1042233613a3d08a700a Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 29 Nov 2021 11:21:45 +0100 Subject: dm-stripe: add a stripe_dax_pgoff helper Add a helper to perform the entire remapping for DAX accesses. This helper open codes bdev_dax_pgoff given that the alignment checks have already been done by the submitting file system and don't need to be repeated. Signed-off-by: Christoph Hellwig Acked-by: Mike Snitzer Reviewed-by: Dan Williams Link: https://lore.kernel.org/r/20211129102203.2243509-12-hch@lst.de Signed-off-by: Dan Williams --- drivers/md/dm-stripe.c | 63 ++++++++++++-------------------------------------- 1 file changed, 15 insertions(+), 48 deletions(-) diff --git a/drivers/md/dm-stripe.c b/drivers/md/dm-stripe.c index f08460722029..50dba3f39274 100644 --- a/drivers/md/dm-stripe.c +++ b/drivers/md/dm-stripe.c @@ -301,83 +301,50 @@ static int stripe_map(struct dm_target *ti, struct bio *bio) } #if IS_ENABLED(CONFIG_FS_DAX) -static long stripe_dax_direct_access(struct dm_target *ti, pgoff_t pgoff, - long nr_pages, void **kaddr, pfn_t *pfn) +static struct dax_device *stripe_dax_pgoff(struct dm_target *ti, pgoff_t *pgoff) { - sector_t dev_sector, sector = pgoff * PAGE_SECTORS; struct stripe_c *sc = ti->private; - struct dax_device *dax_dev; struct block_device *bdev; + sector_t dev_sector; uint32_t stripe; - long ret; - stripe_map_sector(sc, sector, &stripe, &dev_sector); + stripe_map_sector(sc, *pgoff * PAGE_SECTORS, &stripe, &dev_sector); dev_sector += sc->stripe[stripe].physical_start; - dax_dev = sc->stripe[stripe].dev->dax_dev; bdev = sc->stripe[stripe].dev->bdev; - ret = bdev_dax_pgoff(bdev, dev_sector, nr_pages * PAGE_SIZE, &pgoff); - if (ret) - return ret; + *pgoff = (get_start_sect(bdev) + dev_sector) >> PAGE_SECTORS_SHIFT; + return sc->stripe[stripe].dev->dax_dev; +} + +static long stripe_dax_direct_access(struct dm_target *ti, pgoff_t pgoff, + long nr_pages, void **kaddr, pfn_t *pfn) +{ + struct dax_device *dax_dev = stripe_dax_pgoff(ti, &pgoff); + return dax_direct_access(dax_dev, pgoff, nr_pages, kaddr, pfn); } static size_t stripe_dax_copy_from_iter(struct dm_target *ti, pgoff_t pgoff, void *addr, size_t bytes, struct iov_iter *i) { - sector_t dev_sector, sector = pgoff * PAGE_SECTORS; - struct stripe_c *sc = ti->private; - struct dax_device *dax_dev; - struct block_device *bdev; - uint32_t stripe; - - stripe_map_sector(sc, sector, &stripe, &dev_sector); - dev_sector += sc->stripe[stripe].physical_start; - dax_dev = sc->stripe[stripe].dev->dax_dev; - bdev = sc->stripe[stripe].dev->bdev; + struct dax_device *dax_dev = stripe_dax_pgoff(ti, &pgoff); - if (bdev_dax_pgoff(bdev, dev_sector, ALIGN(bytes, PAGE_SIZE), &pgoff)) - return 0; return dax_copy_from_iter(dax_dev, pgoff, addr, bytes, i); } static size_t stripe_dax_copy_to_iter(struct dm_target *ti, pgoff_t pgoff, void *addr, size_t bytes, struct iov_iter *i) { - sector_t dev_sector, sector = pgoff * PAGE_SECTORS; - struct stripe_c *sc = ti->private; - struct dax_device *dax_dev; - struct block_device *bdev; - uint32_t stripe; - - stripe_map_sector(sc, sector, &stripe, &dev_sector); - dev_sector += sc->stripe[stripe].physical_start; - dax_dev = sc->stripe[stripe].dev->dax_dev; - bdev = sc->stripe[stripe].dev->bdev; + struct dax_device *dax_dev = stripe_dax_pgoff(ti, &pgoff); - if (bdev_dax_pgoff(bdev, dev_sector, ALIGN(bytes, PAGE_SIZE), &pgoff)) - return 0; return dax_copy_to_iter(dax_dev, pgoff, addr, bytes, i); } static int stripe_dax_zero_page_range(struct dm_target *ti, pgoff_t pgoff, size_t nr_pages) { - int ret; - sector_t dev_sector, sector = pgoff * PAGE_SECTORS; - struct stripe_c *sc = ti->private; - struct dax_device *dax_dev; - struct block_device *bdev; - uint32_t stripe; + struct dax_device *dax_dev = stripe_dax_pgoff(ti, &pgoff); - stripe_map_sector(sc, sector, &stripe, &dev_sector); - dev_sector += sc->stripe[stripe].physical_start; - dax_dev = sc->stripe[stripe].dev->dax_dev; - bdev = sc->stripe[stripe].dev->bdev; - - ret = bdev_dax_pgoff(bdev, dev_sector, nr_pages << PAGE_SHIFT, &pgoff); - if (ret) - return ret; return dax_zero_page_range(dax_dev, pgoff, nr_pages); } -- cgit v1.2.3 From 9dc2f9cdc63e7db82b6b2ec17894ca1b254f5e5d Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 29 Nov 2021 11:21:46 +0100 Subject: fsdax: remove a pointless __force cast in copy_cow_page_dax Despite its name copy_user_page expected kernel addresses, which is what we already have. Signed-off-by: Christoph Hellwig Reviewed-by: Dan Williams Reviewed-by: Darrick J. Wong Link: https://lore.kernel.org/r/20211129102203.2243509-13-hch@lst.de Signed-off-by: Dan Williams --- fs/dax.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/dax.c b/fs/dax.c index 4e3e5a283a91..73bd1439d808 100644 --- a/fs/dax.c +++ b/fs/dax.c @@ -728,7 +728,7 @@ static int copy_cow_page_dax(struct block_device *bdev, struct dax_device *dax_d return rc; } vto = kmap_atomic(to); - copy_user_page(vto, (void __force *)kaddr, vaddr, to); + copy_user_page(vto, kaddr, vaddr, to); kunmap_atomic(vto); dax_read_unlock(id); return 0; -- cgit v1.2.3 From 429f8de70d9872c5ca9b3914b3c4db5659779331 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 29 Nov 2021 11:21:47 +0100 Subject: fsdax: use a saner calling convention for copy_cow_page_dax Just pass the vm_fault and iomap_iter structures, and figure out the rest locally. Note that this requires moving dax_iomap_sector up in the file. Signed-off-by: Christoph Hellwig Reviewed-by: Dan Williams Reviewed-by: Darrick J. Wong Link: https://lore.kernel.org/r/20211129102203.2243509-14-hch@lst.de Signed-off-by: Dan Williams --- fs/dax.c | 29 +++++++++++++---------------- 1 file changed, 13 insertions(+), 16 deletions(-) diff --git a/fs/dax.c b/fs/dax.c index 73bd1439d808..e51b4129d1b6 100644 --- a/fs/dax.c +++ b/fs/dax.c @@ -709,26 +709,31 @@ int dax_invalidate_mapping_entry_sync(struct address_space *mapping, return __dax_invalidate_entry(mapping, index, false); } -static int copy_cow_page_dax(struct block_device *bdev, struct dax_device *dax_dev, - sector_t sector, struct page *to, unsigned long vaddr) +static sector_t dax_iomap_sector(const struct iomap *iomap, loff_t pos) { + return (iomap->addr + (pos & PAGE_MASK) - iomap->offset) >> 9; +} + +static int copy_cow_page_dax(struct vm_fault *vmf, const struct iomap_iter *iter) +{ + sector_t sector = dax_iomap_sector(&iter->iomap, iter->pos); void *vto, *kaddr; pgoff_t pgoff; long rc; int id; - rc = bdev_dax_pgoff(bdev, sector, PAGE_SIZE, &pgoff); + rc = bdev_dax_pgoff(iter->iomap.bdev, sector, PAGE_SIZE, &pgoff); if (rc) return rc; id = dax_read_lock(); - rc = dax_direct_access(dax_dev, pgoff, 1, &kaddr, NULL); + rc = dax_direct_access(iter->iomap.dax_dev, pgoff, 1, &kaddr, NULL); if (rc < 0) { dax_read_unlock(id); return rc; } - vto = kmap_atomic(to); - copy_user_page(vto, kaddr, vaddr, to); + vto = kmap_atomic(vmf->cow_page); + copy_user_page(vto, kaddr, vmf->address, vmf->cow_page); kunmap_atomic(vto); dax_read_unlock(id); return 0; @@ -1005,11 +1010,6 @@ int dax_writeback_mapping_range(struct address_space *mapping, } EXPORT_SYMBOL_GPL(dax_writeback_mapping_range); -static sector_t dax_iomap_sector(const struct iomap *iomap, loff_t pos) -{ - return (iomap->addr + (pos & PAGE_MASK) - iomap->offset) >> 9; -} - static int dax_iomap_pfn(const struct iomap *iomap, loff_t pos, size_t size, pfn_t *pfnp) { @@ -1332,19 +1332,16 @@ static vm_fault_t dax_fault_synchronous_pfnp(pfn_t *pfnp, pfn_t pfn) static vm_fault_t dax_fault_cow_page(struct vm_fault *vmf, const struct iomap_iter *iter) { - sector_t sector = dax_iomap_sector(&iter->iomap, iter->pos); - unsigned long vaddr = vmf->address; vm_fault_t ret; int error = 0; switch (iter->iomap.type) { case IOMAP_HOLE: case IOMAP_UNWRITTEN: - clear_user_highpage(vmf->cow_page, vaddr); + clear_user_highpage(vmf->cow_page, vmf->address); break; case IOMAP_MAPPED: - error = copy_cow_page_dax(iter->iomap.bdev, iter->iomap.dax_dev, - sector, vmf->cow_page, vaddr); + error = copy_cow_page_dax(vmf, iter); break; default: WARN_ON_ONCE(1); -- cgit v1.2.3 From 60696eb26a37ab0199f7833ddbc1b75138c36d16 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 29 Nov 2021 11:21:48 +0100 Subject: fsdax: simplify the pgoff calculation Replace the two steps of dax_iomap_sector and bdev_dax_pgoff with a single dax_iomap_pgoff helper that avoids lots of cumbersome sector conversions. Signed-off-by: Christoph Hellwig Reviewed-by: Dan Williams Reviewed-by: Darrick J. Wong Link: https://lore.kernel.org/r/20211129102203.2243509-15-hch@lst.de Signed-off-by: Dan Williams --- drivers/dax/super.c | 14 -------------- fs/dax.c | 35 ++++++++++------------------------- include/linux/dax.h | 1 - 3 files changed, 10 insertions(+), 40 deletions(-) diff --git a/drivers/dax/super.c b/drivers/dax/super.c index 90b5733f5a70..45d931aefd06 100644 --- a/drivers/dax/super.c +++ b/drivers/dax/super.c @@ -66,20 +66,6 @@ void dax_remove_host(struct gendisk *disk) } EXPORT_SYMBOL_GPL(dax_remove_host); -int bdev_dax_pgoff(struct block_device *bdev, sector_t sector, size_t size, - pgoff_t *pgoff) -{ - sector_t start_sect = bdev ? get_start_sect(bdev) : 0; - phys_addr_t phys_off = (start_sect + sector) * 512; - - if (pgoff) - *pgoff = PHYS_PFN(phys_off); - if (phys_off % PAGE_SIZE || size % PAGE_SIZE) - return -EINVAL; - return 0; -} -EXPORT_SYMBOL(bdev_dax_pgoff); - /** * fs_dax_get_by_bdev() - temporary lookup mechanism for filesystem-dax * @bdev: block device to find a dax_device for diff --git a/fs/dax.c b/fs/dax.c index e51b4129d1b6..5364549d67a4 100644 --- a/fs/dax.c +++ b/fs/dax.c @@ -709,23 +709,22 @@ int dax_invalidate_mapping_entry_sync(struct address_space *mapping, return __dax_invalidate_entry(mapping, index, false); } -static sector_t dax_iomap_sector(const struct iomap *iomap, loff_t pos) +static pgoff_t dax_iomap_pgoff(const struct iomap *iomap, loff_t pos) { - return (iomap->addr + (pos & PAGE_MASK) - iomap->offset) >> 9; + phys_addr_t paddr = iomap->addr + (pos & PAGE_MASK) - iomap->offset; + + if (iomap->bdev) + paddr += (get_start_sect(iomap->bdev) << SECTOR_SHIFT); + return PHYS_PFN(paddr); } static int copy_cow_page_dax(struct vm_fault *vmf, const struct iomap_iter *iter) { - sector_t sector = dax_iomap_sector(&iter->iomap, iter->pos); + pgoff_t pgoff = dax_iomap_pgoff(&iter->iomap, iter->pos); void *vto, *kaddr; - pgoff_t pgoff; long rc; int id; - rc = bdev_dax_pgoff(iter->iomap.bdev, sector, PAGE_SIZE, &pgoff); - if (rc) - return rc; - id = dax_read_lock(); rc = dax_direct_access(iter->iomap.dax_dev, pgoff, 1, &kaddr, NULL); if (rc < 0) { @@ -1013,14 +1012,10 @@ EXPORT_SYMBOL_GPL(dax_writeback_mapping_range); static int dax_iomap_pfn(const struct iomap *iomap, loff_t pos, size_t size, pfn_t *pfnp) { - const sector_t sector = dax_iomap_sector(iomap, pos); - pgoff_t pgoff; + pgoff_t pgoff = dax_iomap_pgoff(iomap, pos); int id, rc; long length; - rc = bdev_dax_pgoff(iomap->bdev, sector, size, &pgoff); - if (rc) - return rc; id = dax_read_lock(); length = dax_direct_access(iomap->dax_dev, pgoff, PHYS_PFN(size), NULL, pfnp); @@ -1129,7 +1124,7 @@ static vm_fault_t dax_pmd_load_hole(struct xa_state *xas, struct vm_fault *vmf, s64 dax_iomap_zero(loff_t pos, u64 length, struct iomap *iomap) { sector_t sector = iomap_sector(iomap, pos & PAGE_MASK); - pgoff_t pgoff; + pgoff_t pgoff = dax_iomap_pgoff(iomap, pos); long rc, id; void *kaddr; bool page_aligned = false; @@ -1140,10 +1135,6 @@ s64 dax_iomap_zero(loff_t pos, u64 length, struct iomap *iomap) (size == PAGE_SIZE)) page_aligned = true; - rc = bdev_dax_pgoff(iomap->bdev, sector, PAGE_SIZE, &pgoff); - if (rc) - return rc; - id = dax_read_lock(); if (page_aligned) @@ -1169,7 +1160,6 @@ static loff_t dax_iomap_iter(const struct iomap_iter *iomi, const struct iomap *iomap = &iomi->iomap; loff_t length = iomap_length(iomi); loff_t pos = iomi->pos; - struct block_device *bdev = iomap->bdev; struct dax_device *dax_dev = iomap->dax_dev; loff_t end = pos + length, done = 0; ssize_t ret = 0; @@ -1203,9 +1193,8 @@ static loff_t dax_iomap_iter(const struct iomap_iter *iomi, while (pos < end) { unsigned offset = pos & (PAGE_SIZE - 1); const size_t size = ALIGN(length + offset, PAGE_SIZE); - const sector_t sector = dax_iomap_sector(iomap, pos); + pgoff_t pgoff = dax_iomap_pgoff(iomap, pos); ssize_t map_len; - pgoff_t pgoff; void *kaddr; if (fatal_signal_pending(current)) { @@ -1213,10 +1202,6 @@ static loff_t dax_iomap_iter(const struct iomap_iter *iomi, break; } - ret = bdev_dax_pgoff(bdev, sector, size, &pgoff); - if (ret) - break; - map_len = dax_direct_access(dax_dev, pgoff, PHYS_PFN(size), &kaddr, NULL); if (map_len < 0) { diff --git a/include/linux/dax.h b/include/linux/dax.h index 439c3c70e347..324363b798ec 100644 --- a/include/linux/dax.h +++ b/include/linux/dax.h @@ -107,7 +107,6 @@ static inline bool daxdev_mapping_supported(struct vm_area_struct *vma, #endif struct writeback_control; -int bdev_dax_pgoff(struct block_device *, sector_t, size_t, pgoff_t *pgoff); #if IS_ENABLED(CONFIG_FS_DAX) int dax_add_host(struct dax_device *dax_dev, struct gendisk *disk); void dax_remove_host(struct gendisk *disk); -- cgit v1.2.3 From f1ba5fafba9bfde4b040cd0d14256aed25a35c5e Mon Sep 17 00:00:00 2001 From: Shiyang Ruan Date: Mon, 29 Nov 2021 11:21:49 +0100 Subject: xfs: add xfs_zero_range and xfs_truncate_page helpers Add helpers to prepare for using different DAX operations. Signed-off-by: Shiyang Ruan [hch: split from a larger patch + slight cleanups] Signed-off-by: Christoph Hellwig Reviewed-by: Dan Williams Reviewed-by: Darrick J. Wong Link: https://lore.kernel.org/r/20211129102203.2243509-16-hch@lst.de Signed-off-by: Dan Williams --- fs/xfs/xfs_bmap_util.c | 7 +++---- fs/xfs/xfs_file.c | 3 +-- fs/xfs/xfs_iomap.c | 25 +++++++++++++++++++++++++ fs/xfs/xfs_iomap.h | 4 ++++ fs/xfs/xfs_iops.c | 7 +++---- fs/xfs/xfs_reflink.c | 3 +-- 6 files changed, 37 insertions(+), 12 deletions(-) diff --git a/fs/xfs/xfs_bmap_util.c b/fs/xfs/xfs_bmap_util.c index 73a36b7be3bd..797ea0c8b14e 100644 --- a/fs/xfs/xfs_bmap_util.c +++ b/fs/xfs/xfs_bmap_util.c @@ -1001,7 +1001,7 @@ xfs_free_file_space( /* * Now that we've unmap all full blocks we'll have to zero out any - * partial block at the beginning and/or end. iomap_zero_range is smart + * partial block at the beginning and/or end. xfs_zero_range is smart * enough to skip any holes, including those we just created, but we * must take care not to zero beyond EOF and enlarge i_size. */ @@ -1009,15 +1009,14 @@ xfs_free_file_space( return 0; if (offset + len > XFS_ISIZE(ip)) len = XFS_ISIZE(ip) - offset; - error = iomap_zero_range(VFS_I(ip), offset, len, NULL, - &xfs_buffered_write_iomap_ops); + error = xfs_zero_range(ip, offset, len, NULL); if (error) return error; /* * If we zeroed right up to EOF and EOF straddles a page boundary we * must make sure that the post-EOF area is also zeroed because the - * page could be mmap'd and iomap_zero_range doesn't do that for us. + * page could be mmap'd and xfs_zero_range doesn't do that for us. * Writeback of the eof page will do this, albeit clumsily. */ if (offset + len >= XFS_ISIZE(ip) && offset_in_page(offset + len) > 0) { diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c index 27594738b0d1..8d4c5ca261bd 100644 --- a/fs/xfs/xfs_file.c +++ b/fs/xfs/xfs_file.c @@ -437,8 +437,7 @@ restart: } trace_xfs_zero_eof(ip, isize, iocb->ki_pos - isize); - error = iomap_zero_range(inode, isize, iocb->ki_pos - isize, - NULL, &xfs_buffered_write_iomap_ops); + error = xfs_zero_range(ip, isize, iocb->ki_pos - isize, NULL); if (error) return error; } else diff --git a/fs/xfs/xfs_iomap.c b/fs/xfs/xfs_iomap.c index 093758440ad5..d6d71ae9f2ae 100644 --- a/fs/xfs/xfs_iomap.c +++ b/fs/xfs/xfs_iomap.c @@ -1311,3 +1311,28 @@ out_unlock: const struct iomap_ops xfs_xattr_iomap_ops = { .iomap_begin = xfs_xattr_iomap_begin, }; + +int +xfs_zero_range( + struct xfs_inode *ip, + loff_t pos, + loff_t len, + bool *did_zero) +{ + struct inode *inode = VFS_I(ip); + + return iomap_zero_range(inode, pos, len, did_zero, + &xfs_buffered_write_iomap_ops); +} + +int +xfs_truncate_page( + struct xfs_inode *ip, + loff_t pos, + bool *did_zero) +{ + struct inode *inode = VFS_I(ip); + + return iomap_truncate_page(inode, pos, did_zero, + &xfs_buffered_write_iomap_ops); +} diff --git a/fs/xfs/xfs_iomap.h b/fs/xfs/xfs_iomap.h index 7d3703556d0e..f1a281ab9328 100644 --- a/fs/xfs/xfs_iomap.h +++ b/fs/xfs/xfs_iomap.h @@ -20,6 +20,10 @@ xfs_fileoff_t xfs_iomap_eof_align_last_fsb(struct xfs_inode *ip, int xfs_bmbt_to_iomap(struct xfs_inode *, struct iomap *, struct xfs_bmbt_irec *, u16); +int xfs_zero_range(struct xfs_inode *ip, loff_t pos, loff_t len, + bool *did_zero); +int xfs_truncate_page(struct xfs_inode *ip, loff_t pos, bool *did_zero); + static inline xfs_filblks_t xfs_aligned_fsb_count( xfs_fileoff_t offset_fsb, diff --git a/fs/xfs/xfs_iops.c b/fs/xfs/xfs_iops.c index a607d6aca5c4..ab5ef52b2a9f 100644 --- a/fs/xfs/xfs_iops.c +++ b/fs/xfs/xfs_iops.c @@ -911,8 +911,8 @@ xfs_setattr_size( */ if (newsize > oldsize) { trace_xfs_zero_eof(ip, oldsize, newsize - oldsize); - error = iomap_zero_range(inode, oldsize, newsize - oldsize, - &did_zeroing, &xfs_buffered_write_iomap_ops); + error = xfs_zero_range(ip, oldsize, newsize - oldsize, + &did_zeroing); } else { /* * iomap won't detect a dirty page over an unwritten block (or a @@ -924,8 +924,7 @@ xfs_setattr_size( newsize); if (error) return error; - error = iomap_truncate_page(inode, newsize, &did_zeroing, - &xfs_buffered_write_iomap_ops); + error = xfs_truncate_page(ip, newsize, &did_zeroing); } if (error) diff --git a/fs/xfs/xfs_reflink.c b/fs/xfs/xfs_reflink.c index cb0edb1d68ef..facce5c076d8 100644 --- a/fs/xfs/xfs_reflink.c +++ b/fs/xfs/xfs_reflink.c @@ -1269,8 +1269,7 @@ xfs_reflink_zero_posteof( return 0; trace_xfs_zero_eof(ip, isize, pos - isize); - return iomap_zero_range(VFS_I(ip), isize, pos - isize, NULL, - &xfs_buffered_write_iomap_ops); + return xfs_zero_range(ip, isize, pos - isize, NULL); } /* -- cgit v1.2.3 From 4a2d7d5950507a27e3074e4a29dc20720235f811 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 29 Nov 2021 11:21:50 +0100 Subject: fsdax: simplify the offset check in dax_iomap_zero The file relative offset must have the same alignment as the storage offset, so use that and get rid of the call to iomap_sector. Signed-off-by: Christoph Hellwig Reviewed-by: Dan Williams Reviewed-by: Darrick J. Wong Link: https://lore.kernel.org/r/20211129102203.2243509-17-hch@lst.de Signed-off-by: Dan Williams --- fs/dax.c | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) diff --git a/fs/dax.c b/fs/dax.c index 5364549d67a4..d7a923d15224 100644 --- a/fs/dax.c +++ b/fs/dax.c @@ -1123,7 +1123,6 @@ static vm_fault_t dax_pmd_load_hole(struct xa_state *xas, struct vm_fault *vmf, s64 dax_iomap_zero(loff_t pos, u64 length, struct iomap *iomap) { - sector_t sector = iomap_sector(iomap, pos & PAGE_MASK); pgoff_t pgoff = dax_iomap_pgoff(iomap, pos); long rc, id; void *kaddr; @@ -1131,8 +1130,7 @@ s64 dax_iomap_zero(loff_t pos, u64 length, struct iomap *iomap) unsigned offset = offset_in_page(pos); unsigned size = min_t(u64, PAGE_SIZE - offset, length); - if (IS_ALIGNED(sector << SECTOR_SHIFT, PAGE_SIZE) && - (size == PAGE_SIZE)) + if (IS_ALIGNED(pos, PAGE_SIZE) && size == PAGE_SIZE) page_aligned = true; id = dax_read_lock(); -- cgit v1.2.3 From e5c71954ca11df04d258a663a8a15262be0e17f6 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 29 Nov 2021 11:21:51 +0100 Subject: fsdax: factor out a dax_memzero helper Factor out a helper for the "manual" zeroing of a DAX range to clean up dax_iomap_zero a lot. Signed-off-by: Christoph Hellwig Reviewed-by: Dan Williams Reviewed-by: Darrick J. Wong Link: https://lore.kernel.org/r/20211129102203.2243509-18-hch@lst.de Signed-off-by: Dan Williams --- fs/dax.c | 36 +++++++++++++++++++----------------- 1 file changed, 19 insertions(+), 17 deletions(-) diff --git a/fs/dax.c b/fs/dax.c index d7a923d15224..d5db1297a0bb 100644 --- a/fs/dax.c +++ b/fs/dax.c @@ -1121,34 +1121,36 @@ static vm_fault_t dax_pmd_load_hole(struct xa_state *xas, struct vm_fault *vmf, } #endif /* CONFIG_FS_DAX_PMD */ +static int dax_memzero(struct dax_device *dax_dev, pgoff_t pgoff, + unsigned int offset, size_t size) +{ + void *kaddr; + long ret; + + ret = dax_direct_access(dax_dev, pgoff, 1, &kaddr, NULL); + if (ret > 0) { + memset(kaddr + offset, 0, size); + dax_flush(dax_dev, kaddr + offset, size); + } + return ret; +} + s64 dax_iomap_zero(loff_t pos, u64 length, struct iomap *iomap) { pgoff_t pgoff = dax_iomap_pgoff(iomap, pos); long rc, id; - void *kaddr; - bool page_aligned = false; unsigned offset = offset_in_page(pos); unsigned size = min_t(u64, PAGE_SIZE - offset, length); - if (IS_ALIGNED(pos, PAGE_SIZE) && size == PAGE_SIZE) - page_aligned = true; - id = dax_read_lock(); - - if (page_aligned) + if (IS_ALIGNED(pos, PAGE_SIZE) && size == PAGE_SIZE) rc = dax_zero_page_range(iomap->dax_dev, pgoff, 1); else - rc = dax_direct_access(iomap->dax_dev, pgoff, 1, &kaddr, NULL); - if (rc < 0) { - dax_read_unlock(id); - return rc; - } - - if (!page_aligned) { - memset(kaddr + offset, 0, size); - dax_flush(iomap->dax_dev, kaddr + offset, size); - } + rc = dax_memzero(iomap->dax_dev, pgoff, offset, size); dax_read_unlock(id); + + if (rc < 0) + return rc; return size; } -- cgit v1.2.3 From c6f40468657d16e4010ef84bf32a761feb3469ea Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 29 Nov 2021 11:21:52 +0100 Subject: fsdax: decouple zeroing from the iomap buffered I/O code Unshare the DAX and iomap buffered I/O page zeroing code. This code previously did a IS_DAX check deep inside the iomap code, which in fact was the only DAX check in the code. Instead move these checks into the callers. Most callers already have DAX special casing anyway and XFS will need it for reflink support as well. Signed-off-by: Christoph Hellwig Reviewed-by: Dan Williams Reviewed-by: Darrick J. Wong Link: https://lore.kernel.org/r/20211129102203.2243509-19-hch@lst.de Signed-off-by: Dan Williams --- fs/dax.c | 77 +++++++++++++++++++++++++++++++++++++++++--------- fs/ext2/inode.c | 7 +++-- fs/ext4/inode.c | 5 ++-- fs/iomap/buffered-io.c | 35 ++++++++--------------- fs/xfs/xfs_iomap.c | 7 ++++- include/linux/dax.h | 7 ++++- 6 files changed, 94 insertions(+), 44 deletions(-) diff --git a/fs/dax.c b/fs/dax.c index d5db1297a0bb..43d58b4219fd 100644 --- a/fs/dax.c +++ b/fs/dax.c @@ -1135,24 +1135,73 @@ static int dax_memzero(struct dax_device *dax_dev, pgoff_t pgoff, return ret; } -s64 dax_iomap_zero(loff_t pos, u64 length, struct iomap *iomap) +static s64 dax_zero_iter(struct iomap_iter *iter, bool *did_zero) { - pgoff_t pgoff = dax_iomap_pgoff(iomap, pos); - long rc, id; - unsigned offset = offset_in_page(pos); - unsigned size = min_t(u64, PAGE_SIZE - offset, length); + const struct iomap *iomap = &iter->iomap; + const struct iomap *srcmap = iomap_iter_srcmap(iter); + loff_t pos = iter->pos; + u64 length = iomap_length(iter); + s64 written = 0; + + /* already zeroed? we're done. */ + if (srcmap->type == IOMAP_HOLE || srcmap->type == IOMAP_UNWRITTEN) + return length; + + do { + unsigned offset = offset_in_page(pos); + unsigned size = min_t(u64, PAGE_SIZE - offset, length); + pgoff_t pgoff = dax_iomap_pgoff(iomap, pos); + long rc; + int id; - id = dax_read_lock(); - if (IS_ALIGNED(pos, PAGE_SIZE) && size == PAGE_SIZE) - rc = dax_zero_page_range(iomap->dax_dev, pgoff, 1); - else - rc = dax_memzero(iomap->dax_dev, pgoff, offset, size); - dax_read_unlock(id); + id = dax_read_lock(); + if (IS_ALIGNED(pos, PAGE_SIZE) && size == PAGE_SIZE) + rc = dax_zero_page_range(iomap->dax_dev, pgoff, 1); + else + rc = dax_memzero(iomap->dax_dev, pgoff, offset, size); + dax_read_unlock(id); - if (rc < 0) - return rc; - return size; + if (rc < 0) + return rc; + pos += size; + length -= size; + written += size; + if (did_zero) + *did_zero = true; + } while (length > 0); + + return written; +} + +int dax_zero_range(struct inode *inode, loff_t pos, loff_t len, bool *did_zero, + const struct iomap_ops *ops) +{ + struct iomap_iter iter = { + .inode = inode, + .pos = pos, + .len = len, + .flags = IOMAP_ZERO, + }; + int ret; + + while ((ret = iomap_iter(&iter, ops)) > 0) + iter.processed = dax_zero_iter(&iter, did_zero); + return ret; +} +EXPORT_SYMBOL_GPL(dax_zero_range); + +int dax_truncate_page(struct inode *inode, loff_t pos, bool *did_zero, + const struct iomap_ops *ops) +{ + unsigned int blocksize = i_blocksize(inode); + unsigned int off = pos & (blocksize - 1); + + /* Block boundary? Nothing to do */ + if (!off) + return 0; + return dax_zero_range(inode, pos, blocksize - off, did_zero, ops); } +EXPORT_SYMBOL_GPL(dax_truncate_page); static loff_t dax_iomap_iter(const struct iomap_iter *iomi, struct iov_iter *iter) diff --git a/fs/ext2/inode.c b/fs/ext2/inode.c index 333fa62661d5..01d69618277d 100644 --- a/fs/ext2/inode.c +++ b/fs/ext2/inode.c @@ -36,6 +36,7 @@ #include #include #include +#include #include "ext2.h" #include "acl.h" #include "xattr.h" @@ -1297,9 +1298,9 @@ static int ext2_setsize(struct inode *inode, loff_t newsize) inode_dio_wait(inode); if (IS_DAX(inode)) { - error = iomap_zero_range(inode, newsize, - PAGE_ALIGN(newsize) - newsize, NULL, - &ext2_iomap_ops); + error = dax_zero_range(inode, newsize, + PAGE_ALIGN(newsize) - newsize, NULL, + &ext2_iomap_ops); } else if (test_opt(inode->i_sb, NOBH)) error = nobh_truncate_page(inode->i_mapping, newsize, ext2_get_block); diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index bfd3545f1e5d..d316a2009489 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -41,6 +41,7 @@ #include #include #include +#include #include "ext4_jbd2.h" #include "xattr.h" @@ -3780,8 +3781,8 @@ static int ext4_block_zero_page_range(handle_t *handle, length = max; if (IS_DAX(inode)) { - return iomap_zero_range(inode, from, length, NULL, - &ext4_iomap_ops); + return dax_zero_range(inode, from, length, NULL, + &ext4_iomap_ops); } return __ext4_block_zero_page_range(handle, mapping, from, length); } diff --git a/fs/iomap/buffered-io.c b/fs/iomap/buffered-io.c index 1753c26c8e76..b1511255b4df 100644 --- a/fs/iomap/buffered-io.c +++ b/fs/iomap/buffered-io.c @@ -870,26 +870,8 @@ iomap_file_unshare(struct inode *inode, loff_t pos, loff_t len, } EXPORT_SYMBOL_GPL(iomap_file_unshare); -static s64 __iomap_zero_iter(struct iomap_iter *iter, loff_t pos, u64 length) -{ - struct page *page; - int status; - unsigned offset = offset_in_page(pos); - unsigned bytes = min_t(u64, PAGE_SIZE - offset, length); - - status = iomap_write_begin(iter, pos, bytes, &page); - if (status) - return status; - - zero_user(page, offset, bytes); - mark_page_accessed(page); - - return iomap_write_end(iter, pos, bytes, bytes, page); -} - static loff_t iomap_zero_iter(struct iomap_iter *iter, bool *did_zero) { - struct iomap *iomap = &iter->iomap; const struct iomap *srcmap = iomap_iter_srcmap(iter); loff_t pos = iter->pos; loff_t length = iomap_length(iter); @@ -900,12 +882,19 @@ static loff_t iomap_zero_iter(struct iomap_iter *iter, bool *did_zero) return length; do { - s64 bytes; + unsigned offset = offset_in_page(pos); + size_t bytes = min_t(u64, PAGE_SIZE - offset, length); + struct page *page; + int status; - if (IS_DAX(iter->inode)) - bytes = dax_iomap_zero(pos, length, iomap); - else - bytes = __iomap_zero_iter(iter, pos, length); + status = iomap_write_begin(iter, pos, bytes, &page); + if (status) + return status; + + zero_user(page, offset, bytes); + mark_page_accessed(page); + + bytes = iomap_write_end(iter, pos, bytes, bytes, page); if (bytes < 0) return bytes; diff --git a/fs/xfs/xfs_iomap.c b/fs/xfs/xfs_iomap.c index d6d71ae9f2ae..6a0c3b307bd7 100644 --- a/fs/xfs/xfs_iomap.c +++ b/fs/xfs/xfs_iomap.c @@ -28,7 +28,6 @@ #include "xfs_dquot.h" #include "xfs_reflink.h" - #define XFS_ALLOC_ALIGN(mp, off) \ (((off) >> mp->m_allocsize_log) << mp->m_allocsize_log) @@ -1321,6 +1320,9 @@ xfs_zero_range( { struct inode *inode = VFS_I(ip); + if (IS_DAX(inode)) + return dax_zero_range(inode, pos, len, did_zero, + &xfs_buffered_write_iomap_ops); return iomap_zero_range(inode, pos, len, did_zero, &xfs_buffered_write_iomap_ops); } @@ -1333,6 +1335,9 @@ xfs_truncate_page( { struct inode *inode = VFS_I(ip); + if (IS_DAX(inode)) + return dax_truncate_page(inode, pos, did_zero, + &xfs_buffered_write_iomap_ops); return iomap_truncate_page(inode, pos, did_zero, &xfs_buffered_write_iomap_ops); } diff --git a/include/linux/dax.h b/include/linux/dax.h index 324363b798ec..b79036743e7f 100644 --- a/include/linux/dax.h +++ b/include/linux/dax.h @@ -14,6 +14,7 @@ typedef unsigned long dax_entry_t; struct dax_device; struct gendisk; struct iomap_ops; +struct iomap_iter; struct iomap; struct dax_operations { @@ -170,6 +171,11 @@ static inline void dax_unlock_page(struct page *page, dax_entry_t cookie) } #endif +int dax_zero_range(struct inode *inode, loff_t pos, loff_t len, bool *did_zero, + const struct iomap_ops *ops); +int dax_truncate_page(struct inode *inode, loff_t pos, bool *did_zero, + const struct iomap_ops *ops); + #if IS_ENABLED(CONFIG_DAX) int dax_read_lock(void); void dax_read_unlock(int id); @@ -204,7 +210,6 @@ vm_fault_t dax_finish_sync_fault(struct vm_fault *vmf, int dax_delete_mapping_entry(struct address_space *mapping, pgoff_t index); int dax_invalidate_mapping_entry_sync(struct address_space *mapping, pgoff_t index); -s64 dax_iomap_zero(loff_t pos, u64 length, struct iomap *iomap); static inline bool dax_mapping(struct address_space *mapping) { return mapping->host && IS_DAX(mapping->host); -- cgit v1.2.3 From cea845cdef4f5094f0471a6dbdb609c004ad8b06 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 29 Nov 2021 11:21:53 +0100 Subject: ext2: cleanup the dax handling in ext2_fill_super Only call fs_dax_get_by_bdev once the sbi has been allocated and remove the need for the dax_dev local variable. Signed-off-by: Christoph Hellwig Reviewed-by: Dan Williams Reviewed-by: Darrick J. Wong Link: https://lore.kernel.org/r/20211129102203.2243509-20-hch@lst.de Signed-off-by: Dan Williams --- fs/ext2/super.c | 12 +++++------- 1 file changed, 5 insertions(+), 7 deletions(-) diff --git a/fs/ext2/super.c b/fs/ext2/super.c index a964066a80aa..7e23482862e6 100644 --- a/fs/ext2/super.c +++ b/fs/ext2/super.c @@ -802,7 +802,6 @@ static unsigned long descriptor_loc(struct super_block *sb, static int ext2_fill_super(struct super_block *sb, void *data, int silent) { - struct dax_device *dax_dev = fs_dax_get_by_bdev(sb->s_bdev); struct buffer_head * bh; struct ext2_sb_info * sbi; struct ext2_super_block * es; @@ -822,17 +821,17 @@ static int ext2_fill_super(struct super_block *sb, void *data, int silent) sbi = kzalloc(sizeof(*sbi), GFP_KERNEL); if (!sbi) - goto failed; + return -ENOMEM; sbi->s_blockgroup_lock = kzalloc(sizeof(struct blockgroup_lock), GFP_KERNEL); if (!sbi->s_blockgroup_lock) { kfree(sbi); - goto failed; + return -ENOMEM; } sb->s_fs_info = sbi; sbi->s_sb_block = sb_block; - sbi->s_daxdev = dax_dev; + sbi->s_daxdev = fs_dax_get_by_bdev(sb->s_bdev); spin_lock_init(&sbi->s_lock); ret = -EINVAL; @@ -946,7 +945,7 @@ static int ext2_fill_super(struct super_block *sb, void *data, int silent) blocksize = BLOCK_SIZE << le32_to_cpu(sbi->s_es->s_log_block_size); if (test_opt(sb, DAX)) { - if (!dax_dev) { + if (!sbi->s_daxdev) { ext2_msg(sb, KERN_ERR, "DAX unsupported by block device. Turning off DAX."); clear_opt(sbi->s_mount_opt, DAX); @@ -1201,11 +1200,10 @@ failed_mount_group_desc: failed_mount: brelse(bh); failed_sbi: + fs_put_dax(sbi->s_daxdev); sb->s_fs_info = NULL; kfree(sbi->s_blockgroup_lock); kfree(sbi); -failed: - fs_put_dax(dax_dev); return ret; } -- cgit v1.2.3 From 89b93a7b15f75d04ed579baeb4d941e8ce7634c8 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 29 Nov 2021 11:21:54 +0100 Subject: ext4: cleanup the dax handling in ext4_fill_super Only call fs_dax_get_by_bdev once the sbi has been allocated and remove the need for the dax_dev local variable. Signed-off-by: Christoph Hellwig Reviewed-by: Dan Williams Reviewed-by: Darrick J. Wong Link: https://lore.kernel.org/r/20211129102203.2243509-21-hch@lst.de Signed-off-by: Dan Williams --- fs/ext4/super.c | 7 +++---- 1 file changed, 3 insertions(+), 4 deletions(-) diff --git a/fs/ext4/super.c b/fs/ext4/super.c index fd3d68f10ee5..8d7e3449c647 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -3878,7 +3878,6 @@ static void ext4_setup_csum_trigger(struct super_block *sb, static int ext4_fill_super(struct super_block *sb, void *data, int silent) { - struct dax_device *dax_dev = fs_dax_get_by_bdev(sb->s_bdev); char *orig_data = kstrdup(data, GFP_KERNEL); struct buffer_head *bh, **group_desc; struct ext4_super_block *es = NULL; @@ -3909,12 +3908,12 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) if ((data && !orig_data) || !sbi) goto out_free_base; - sbi->s_daxdev = dax_dev; sbi->s_blockgroup_lock = kzalloc(sizeof(struct blockgroup_lock), GFP_KERNEL); if (!sbi->s_blockgroup_lock) goto out_free_base; + sbi->s_daxdev = fs_dax_get_by_bdev(sb->s_bdev); sb->s_fs_info = sbi; sbi->s_sb = sb; sbi->s_inode_readahead_blks = EXT4_DEF_INODE_READAHEAD_BLKS; @@ -4299,7 +4298,7 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) goto failed_mount; } - if (dax_dev) { + if (sbi->s_daxdev) { if (blocksize == PAGE_SIZE) set_bit(EXT4_FLAGS_BDEV_IS_DAX, &sbi->s_ext4_flags); else @@ -5095,10 +5094,10 @@ failed_mount: out_fail: sb->s_fs_info = NULL; kfree(sbi->s_blockgroup_lock); + fs_put_dax(sbi->s_daxdev); out_free_base: kfree(sbi); kfree(orig_data); - fs_put_dax(dax_dev); return err ? err : ret; } -- cgit v1.2.3 From 5b5abbefec1bea98abba8f1cffcf72c11c32a92d Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 29 Nov 2021 11:21:55 +0100 Subject: xfs: move dax device handling into xfs_{alloc,free}_buftarg Hide the DAX device lookup from the xfs_super.c code. Signed-off-by: Christoph Hellwig Reviewed-by: Darrick J. Wong Reviewed-by: Dan Williams Link: https://lore.kernel.org/r/20211129102203.2243509-22-hch@lst.de Signed-off-by: Dan Williams --- fs/xfs/xfs_buf.c | 8 ++++---- fs/xfs/xfs_buf.h | 4 ++-- fs/xfs/xfs_super.c | 26 +++++--------------------- 3 files changed, 11 insertions(+), 27 deletions(-) diff --git a/fs/xfs/xfs_buf.c b/fs/xfs/xfs_buf.c index 631c5a61d89b..4d4553ffa705 100644 --- a/fs/xfs/xfs_buf.c +++ b/fs/xfs/xfs_buf.c @@ -1892,6 +1892,7 @@ xfs_free_buftarg( list_lru_destroy(&btp->bt_lru); blkdev_issue_flush(btp->bt_bdev); + fs_put_dax(btp->bt_daxdev); kmem_free(btp); } @@ -1932,11 +1933,10 @@ xfs_setsize_buftarg_early( return xfs_setsize_buftarg(btp, bdev_logical_block_size(bdev)); } -xfs_buftarg_t * +struct xfs_buftarg * xfs_alloc_buftarg( struct xfs_mount *mp, - struct block_device *bdev, - struct dax_device *dax_dev) + struct block_device *bdev) { xfs_buftarg_t *btp; @@ -1945,7 +1945,7 @@ xfs_alloc_buftarg( btp->bt_mount = mp; btp->bt_dev = bdev->bd_dev; btp->bt_bdev = bdev; - btp->bt_daxdev = dax_dev; + btp->bt_daxdev = fs_dax_get_by_bdev(bdev); /* * Buffer IO error rate limiting. Limit it to no more than 10 messages diff --git a/fs/xfs/xfs_buf.h b/fs/xfs/xfs_buf.h index 6b0200b8007d..bd7f709f0d23 100644 --- a/fs/xfs/xfs_buf.h +++ b/fs/xfs/xfs_buf.h @@ -338,8 +338,8 @@ xfs_buf_update_cksum(struct xfs_buf *bp, unsigned long cksum_offset) /* * Handling of buftargs. */ -extern struct xfs_buftarg *xfs_alloc_buftarg(struct xfs_mount *, - struct block_device *, struct dax_device *); +struct xfs_buftarg *xfs_alloc_buftarg(struct xfs_mount *mp, + struct block_device *bdev); extern void xfs_free_buftarg(struct xfs_buftarg *); extern void xfs_buftarg_wait(struct xfs_buftarg *); extern void xfs_buftarg_drain(struct xfs_buftarg *); diff --git a/fs/xfs/xfs_super.c b/fs/xfs/xfs_super.c index c4297206f483..3584cfc3c593 100644 --- a/fs/xfs/xfs_super.c +++ b/fs/xfs/xfs_super.c @@ -391,26 +391,19 @@ STATIC void xfs_close_devices( struct xfs_mount *mp) { - struct dax_device *dax_ddev = mp->m_ddev_targp->bt_daxdev; - if (mp->m_logdev_targp && mp->m_logdev_targp != mp->m_ddev_targp) { struct block_device *logdev = mp->m_logdev_targp->bt_bdev; - struct dax_device *dax_logdev = mp->m_logdev_targp->bt_daxdev; xfs_free_buftarg(mp->m_logdev_targp); xfs_blkdev_put(logdev); - fs_put_dax(dax_logdev); } if (mp->m_rtdev_targp) { struct block_device *rtdev = mp->m_rtdev_targp->bt_bdev; - struct dax_device *dax_rtdev = mp->m_rtdev_targp->bt_daxdev; xfs_free_buftarg(mp->m_rtdev_targp); xfs_blkdev_put(rtdev); - fs_put_dax(dax_rtdev); } xfs_free_buftarg(mp->m_ddev_targp); - fs_put_dax(dax_ddev); } /* @@ -428,8 +421,6 @@ xfs_open_devices( struct xfs_mount *mp) { struct block_device *ddev = mp->m_super->s_bdev; - struct dax_device *dax_ddev = fs_dax_get_by_bdev(ddev); - struct dax_device *dax_logdev = NULL, *dax_rtdev = NULL; struct block_device *logdev = NULL, *rtdev = NULL; int error; @@ -439,8 +430,7 @@ xfs_open_devices( if (mp->m_logname) { error = xfs_blkdev_get(mp, mp->m_logname, &logdev); if (error) - goto out; - dax_logdev = fs_dax_get_by_bdev(logdev); + return error; } if (mp->m_rtname) { @@ -454,25 +444,24 @@ xfs_open_devices( error = -EINVAL; goto out_close_rtdev; } - dax_rtdev = fs_dax_get_by_bdev(rtdev); } /* * Setup xfs_mount buffer target pointers */ error = -ENOMEM; - mp->m_ddev_targp = xfs_alloc_buftarg(mp, ddev, dax_ddev); + mp->m_ddev_targp = xfs_alloc_buftarg(mp, ddev); if (!mp->m_ddev_targp) goto out_close_rtdev; if (rtdev) { - mp->m_rtdev_targp = xfs_alloc_buftarg(mp, rtdev, dax_rtdev); + mp->m_rtdev_targp = xfs_alloc_buftarg(mp, rtdev); if (!mp->m_rtdev_targp) goto out_free_ddev_targ; } if (logdev && logdev != ddev) { - mp->m_logdev_targp = xfs_alloc_buftarg(mp, logdev, dax_logdev); + mp->m_logdev_targp = xfs_alloc_buftarg(mp, logdev); if (!mp->m_logdev_targp) goto out_free_rtdev_targ; } else { @@ -488,14 +477,9 @@ xfs_open_devices( xfs_free_buftarg(mp->m_ddev_targp); out_close_rtdev: xfs_blkdev_put(rtdev); - fs_put_dax(dax_rtdev); out_close_logdev: - if (logdev && logdev != ddev) { + if (logdev && logdev != ddev) xfs_blkdev_put(logdev); - fs_put_dax(dax_logdev); - } - out: - fs_put_dax(dax_ddev); return error; } -- cgit v1.2.3 From a50f6ab3fd31b084b851c5c196db6c900af2c7cc Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 29 Nov 2021 11:21:56 +0100 Subject: xfs: use xfs_direct_write_iomap_ops for DAX zeroing While the buffered write iomap ops do work due to the fact that zeroing never allocates blocks, the DAX zeroing should use the direct ops just like actual DAX I/O. Signed-off-by: Christoph Hellwig Reviewed-by: Dan Williams Reviewed-by: Darrick J. Wong Link: https://lore.kernel.org/r/20211129102203.2243509-23-hch@lst.de Signed-off-by: Dan Williams --- fs/xfs/xfs_iomap.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/fs/xfs/xfs_iomap.c b/fs/xfs/xfs_iomap.c index 6a0c3b307bd7..9b7f92c6aef3 100644 --- a/fs/xfs/xfs_iomap.c +++ b/fs/xfs/xfs_iomap.c @@ -1322,7 +1322,7 @@ xfs_zero_range( if (IS_DAX(inode)) return dax_zero_range(inode, pos, len, did_zero, - &xfs_buffered_write_iomap_ops); + &xfs_direct_write_iomap_ops); return iomap_zero_range(inode, pos, len, did_zero, &xfs_buffered_write_iomap_ops); } @@ -1337,7 +1337,7 @@ xfs_truncate_page( if (IS_DAX(inode)) return dax_truncate_page(inode, pos, did_zero, - &xfs_buffered_write_iomap_ops); + &xfs_direct_write_iomap_ops); return iomap_truncate_page(inode, pos, did_zero, &xfs_buffered_write_iomap_ops); } -- cgit v1.2.3 From 740fd671e04f8a977018eb9cfe440b4817850f0d Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 29 Nov 2021 11:21:57 +0100 Subject: xfs: pass the mapping flags to xfs_bmbt_to_iomap To prepare for looking at the IOMAP_DAX flag in xfs_bmbt_to_iomap pass in the input mapping flags to xfs_bmbt_to_iomap. Signed-off-by: Christoph Hellwig Reviewed-by: Darrick J. Wong Link: https://lore.kernel.org/r/20211129102203.2243509-24-hch@lst.de Signed-off-by: Dan Williams --- fs/xfs/libxfs/xfs_bmap.c | 4 ++-- fs/xfs/xfs_aops.c | 2 +- fs/xfs/xfs_iomap.c | 35 ++++++++++++++++++++--------------- fs/xfs/xfs_iomap.h | 5 +++-- fs/xfs/xfs_pnfs.c | 2 +- 5 files changed, 27 insertions(+), 21 deletions(-) diff --git a/fs/xfs/libxfs/xfs_bmap.c b/fs/xfs/libxfs/xfs_bmap.c index 4dccd4d90622..74198dd82b03 100644 --- a/fs/xfs/libxfs/xfs_bmap.c +++ b/fs/xfs/libxfs/xfs_bmap.c @@ -4551,7 +4551,7 @@ xfs_bmapi_convert_delalloc( * the extent. Just return the real extent at this offset. */ if (!isnullstartblock(bma.got.br_startblock)) { - xfs_bmbt_to_iomap(ip, iomap, &bma.got, flags); + xfs_bmbt_to_iomap(ip, iomap, &bma.got, 0, flags); *seq = READ_ONCE(ifp->if_seq); goto out_trans_cancel; } @@ -4598,7 +4598,7 @@ xfs_bmapi_convert_delalloc( XFS_STATS_INC(mp, xs_xstrat_quick); ASSERT(!isnullstartblock(bma.got.br_startblock)); - xfs_bmbt_to_iomap(ip, iomap, &bma.got, flags); + xfs_bmbt_to_iomap(ip, iomap, &bma.got, 0, flags); *seq = READ_ONCE(ifp->if_seq); if (whichfork == XFS_COW_FORK) diff --git a/fs/xfs/xfs_aops.c b/fs/xfs/xfs_aops.c index c8c15c3c3147..6ac3449a68ba 100644 --- a/fs/xfs/xfs_aops.c +++ b/fs/xfs/xfs_aops.c @@ -359,7 +359,7 @@ retry: isnullstartblock(imap.br_startblock)) goto allocate_blocks; - xfs_bmbt_to_iomap(ip, &wpc->iomap, &imap, 0); + xfs_bmbt_to_iomap(ip, &wpc->iomap, &imap, 0, 0); trace_xfs_map_blocks_found(ip, offset, count, whichfork, &imap); return 0; allocate_blocks: diff --git a/fs/xfs/xfs_iomap.c b/fs/xfs/xfs_iomap.c index 9b7f92c6aef3..d6beb1502f8b 100644 --- a/fs/xfs/xfs_iomap.c +++ b/fs/xfs/xfs_iomap.c @@ -53,7 +53,8 @@ xfs_bmbt_to_iomap( struct xfs_inode *ip, struct iomap *iomap, struct xfs_bmbt_irec *imap, - u16 flags) + unsigned int mapping_flags, + u16 iomap_flags) { struct xfs_mount *mp = ip->i_mount; struct xfs_buftarg *target = xfs_inode_buftarg(ip); @@ -79,7 +80,7 @@ xfs_bmbt_to_iomap( iomap->length = XFS_FSB_TO_B(mp, imap->br_blockcount); iomap->bdev = target->bt_bdev; iomap->dax_dev = target->bt_daxdev; - iomap->flags = flags; + iomap->flags = iomap_flags; if (xfs_ipincount(ip) && (ip->i_itemp->ili_fsync_fields & ~XFS_ILOG_TIMESTAMP)) @@ -799,7 +800,7 @@ xfs_direct_write_iomap_begin( xfs_iunlock(ip, lockmode); trace_xfs_iomap_found(ip, offset, length, XFS_DATA_FORK, &imap); - return xfs_bmbt_to_iomap(ip, iomap, &imap, iomap_flags); + return xfs_bmbt_to_iomap(ip, iomap, &imap, flags, iomap_flags); allocate_blocks: error = -EAGAIN; @@ -830,18 +831,19 @@ allocate_blocks: return error; trace_xfs_iomap_alloc(ip, offset, length, XFS_DATA_FORK, &imap); - return xfs_bmbt_to_iomap(ip, iomap, &imap, iomap_flags | IOMAP_F_NEW); + return xfs_bmbt_to_iomap(ip, iomap, &imap, flags, + iomap_flags | IOMAP_F_NEW); out_found_cow: xfs_iunlock(ip, lockmode); length = XFS_FSB_TO_B(mp, cmap.br_startoff + cmap.br_blockcount); trace_xfs_iomap_found(ip, offset, length - offset, XFS_COW_FORK, &cmap); if (imap.br_startblock != HOLESTARTBLOCK) { - error = xfs_bmbt_to_iomap(ip, srcmap, &imap, 0); + error = xfs_bmbt_to_iomap(ip, srcmap, &imap, flags, 0); if (error) return error; } - return xfs_bmbt_to_iomap(ip, iomap, &cmap, IOMAP_F_SHARED); + return xfs_bmbt_to_iomap(ip, iomap, &cmap, flags, IOMAP_F_SHARED); out_unlock: if (lockmode) @@ -1051,23 +1053,24 @@ retry: */ xfs_iunlock(ip, XFS_ILOCK_EXCL); trace_xfs_iomap_alloc(ip, offset, count, allocfork, &imap); - return xfs_bmbt_to_iomap(ip, iomap, &imap, IOMAP_F_NEW); + return xfs_bmbt_to_iomap(ip, iomap, &imap, flags, IOMAP_F_NEW); found_imap: xfs_iunlock(ip, XFS_ILOCK_EXCL); - return xfs_bmbt_to_iomap(ip, iomap, &imap, 0); + return xfs_bmbt_to_iomap(ip, iomap, &imap, flags, 0); found_cow: xfs_iunlock(ip, XFS_ILOCK_EXCL); if (imap.br_startoff <= offset_fsb) { - error = xfs_bmbt_to_iomap(ip, srcmap, &imap, 0); + error = xfs_bmbt_to_iomap(ip, srcmap, &imap, flags, 0); if (error) return error; - return xfs_bmbt_to_iomap(ip, iomap, &cmap, IOMAP_F_SHARED); + return xfs_bmbt_to_iomap(ip, iomap, &cmap, flags, + IOMAP_F_SHARED); } xfs_trim_extent(&cmap, offset_fsb, imap.br_startoff - offset_fsb); - return xfs_bmbt_to_iomap(ip, iomap, &cmap, 0); + return xfs_bmbt_to_iomap(ip, iomap, &cmap, flags, 0); out_unlock: xfs_iunlock(ip, XFS_ILOCK_EXCL); @@ -1176,7 +1179,8 @@ xfs_read_iomap_begin( if (error) return error; trace_xfs_iomap_found(ip, offset, length, XFS_DATA_FORK, &imap); - return xfs_bmbt_to_iomap(ip, iomap, &imap, shared ? IOMAP_F_SHARED : 0); + return xfs_bmbt_to_iomap(ip, iomap, &imap, flags, + shared ? IOMAP_F_SHARED : 0); } const struct iomap_ops xfs_read_iomap_ops = { @@ -1235,7 +1239,8 @@ xfs_seek_iomap_begin( if (data_fsb < cow_fsb + cmap.br_blockcount) end_fsb = min(end_fsb, data_fsb); xfs_trim_extent(&cmap, offset_fsb, end_fsb); - error = xfs_bmbt_to_iomap(ip, iomap, &cmap, IOMAP_F_SHARED); + error = xfs_bmbt_to_iomap(ip, iomap, &cmap, flags, + IOMAP_F_SHARED); /* * This is a COW extent, so we must probe the page cache * because there could be dirty page cache being backed @@ -1257,7 +1262,7 @@ xfs_seek_iomap_begin( imap.br_state = XFS_EXT_NORM; done: xfs_trim_extent(&imap, offset_fsb, end_fsb); - error = xfs_bmbt_to_iomap(ip, iomap, &imap, 0); + error = xfs_bmbt_to_iomap(ip, iomap, &imap, flags, 0); out_unlock: xfs_iunlock(ip, lockmode); return error; @@ -1304,7 +1309,7 @@ out_unlock: if (error) return error; ASSERT(nimaps); - return xfs_bmbt_to_iomap(ip, iomap, &imap, 0); + return xfs_bmbt_to_iomap(ip, iomap, &imap, flags, 0); } const struct iomap_ops xfs_xattr_iomap_ops = { diff --git a/fs/xfs/xfs_iomap.h b/fs/xfs/xfs_iomap.h index f1a281ab9328..657cc02290f2 100644 --- a/fs/xfs/xfs_iomap.h +++ b/fs/xfs/xfs_iomap.h @@ -17,8 +17,9 @@ int xfs_iomap_write_unwritten(struct xfs_inode *, xfs_off_t, xfs_off_t, bool); xfs_fileoff_t xfs_iomap_eof_align_last_fsb(struct xfs_inode *ip, xfs_fileoff_t end_fsb); -int xfs_bmbt_to_iomap(struct xfs_inode *, struct iomap *, - struct xfs_bmbt_irec *, u16); +int xfs_bmbt_to_iomap(struct xfs_inode *ip, struct iomap *iomap, + struct xfs_bmbt_irec *imap, unsigned int mapping_flags, + u16 iomap_flags); int xfs_zero_range(struct xfs_inode *ip, loff_t pos, loff_t len, bool *did_zero); diff --git a/fs/xfs/xfs_pnfs.c b/fs/xfs/xfs_pnfs.c index 5e1d29d8b2e7..7ce1ea11fc3f 100644 --- a/fs/xfs/xfs_pnfs.c +++ b/fs/xfs/xfs_pnfs.c @@ -173,7 +173,7 @@ xfs_fs_map_blocks( } xfs_iunlock(ip, XFS_IOLOCK_EXCL); - error = xfs_bmbt_to_iomap(ip, iomap, &imap, 0); + error = xfs_bmbt_to_iomap(ip, iomap, &imap, 0, 0); *device_generation = mp->m_generation; return error; out_unlock: -- cgit v1.2.3 From 952da06375c8f3aa58474fff718d9ae8442531b9 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 29 Nov 2021 11:21:58 +0100 Subject: iomap: add a IOMAP_DAX flag Add a flag so that the file system can easily detect DAX operations based just on the iomap operation requested instead of looking at inode state using IS_DAX. This will be needed to apply the to be added partition offset only for operations that actually use DAX, but not things like fiemap that are based on the block device. In the long run it should also allow turning the bdev, dax_dev and inline_data into a union. Signed-off-by: Christoph Hellwig Reviewed-by: Dan Williams Reviewed-by: Darrick J. Wong Link: https://lore.kernel.org/r/20211129102203.2243509-25-hch@lst.de Signed-off-by: Dan Williams --- fs/dax.c | 7 ++++--- fs/ext4/inode.c | 4 ++-- fs/xfs/xfs_iomap.c | 7 ++++--- fs/xfs/xfs_iomap.h | 3 ++- fs/xfs/xfs_pnfs.c | 2 +- include/linux/iomap.h | 5 +++++ 6 files changed, 18 insertions(+), 10 deletions(-) diff --git a/fs/dax.c b/fs/dax.c index 43d58b4219fd..148e8b0967f3 100644 --- a/fs/dax.c +++ b/fs/dax.c @@ -1180,7 +1180,7 @@ int dax_zero_range(struct inode *inode, loff_t pos, loff_t len, bool *did_zero, .inode = inode, .pos = pos, .len = len, - .flags = IOMAP_ZERO, + .flags = IOMAP_DAX | IOMAP_ZERO, }; int ret; @@ -1308,6 +1308,7 @@ dax_iomap_rw(struct kiocb *iocb, struct iov_iter *iter, .inode = iocb->ki_filp->f_mapping->host, .pos = iocb->ki_pos, .len = iov_iter_count(iter), + .flags = IOMAP_DAX, }; loff_t done = 0; int ret; @@ -1461,7 +1462,7 @@ static vm_fault_t dax_iomap_pte_fault(struct vm_fault *vmf, pfn_t *pfnp, .inode = mapping->host, .pos = (loff_t)vmf->pgoff << PAGE_SHIFT, .len = PAGE_SIZE, - .flags = IOMAP_FAULT, + .flags = IOMAP_DAX | IOMAP_FAULT, }; vm_fault_t ret = 0; void *entry; @@ -1570,7 +1571,7 @@ static vm_fault_t dax_iomap_pmd_fault(struct vm_fault *vmf, pfn_t *pfnp, struct iomap_iter iter = { .inode = mapping->host, .len = PMD_SIZE, - .flags = IOMAP_FAULT, + .flags = IOMAP_DAX | IOMAP_FAULT, }; vm_fault_t ret = VM_FAULT_FALLBACK; pgoff_t max_pgoff; diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index d316a2009489..89c4a174bd39 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -3349,8 +3349,8 @@ retry: * DAX and direct I/O are the only two operations that are currently * supported with IOMAP_WRITE. */ - WARN_ON(!IS_DAX(inode) && !(flags & IOMAP_DIRECT)); - if (IS_DAX(inode)) + WARN_ON(!(flags & (IOMAP_DAX | IOMAP_DIRECT))); + if (flags & IOMAP_DAX) m_flags = EXT4_GET_BLOCKS_CREATE_ZERO; /* * We use i_size instead of i_disksize here because delalloc writeback diff --git a/fs/xfs/xfs_iomap.c b/fs/xfs/xfs_iomap.c index d6beb1502f8b..0ed3e7674353 100644 --- a/fs/xfs/xfs_iomap.c +++ b/fs/xfs/xfs_iomap.c @@ -188,6 +188,7 @@ xfs_iomap_write_direct( struct xfs_inode *ip, xfs_fileoff_t offset_fsb, xfs_fileoff_t count_fsb, + unsigned int flags, struct xfs_bmbt_irec *imap) { struct xfs_mount *mp = ip->i_mount; @@ -229,7 +230,7 @@ xfs_iomap_write_direct( * the reserve block pool for bmbt block allocation if there is no space * left but we need to do unwritten extent conversion. */ - if (IS_DAX(VFS_I(ip))) { + if (flags & IOMAP_DAX) { bmapi_flags = XFS_BMAPI_CONVERT | XFS_BMAPI_ZERO; if (imap->br_state == XFS_EXT_UNWRITTEN) { force = true; @@ -620,7 +621,7 @@ imap_needs_alloc( imap->br_startblock == DELAYSTARTBLOCK) return true; /* we convert unwritten extents before copying the data for DAX */ - if (IS_DAX(inode) && imap->br_state == XFS_EXT_UNWRITTEN) + if ((flags & IOMAP_DAX) && imap->br_state == XFS_EXT_UNWRITTEN) return true; return false; } @@ -826,7 +827,7 @@ allocate_blocks: xfs_iunlock(ip, lockmode); error = xfs_iomap_write_direct(ip, offset_fsb, end_fsb - offset_fsb, - &imap); + flags, &imap); if (error) return error; diff --git a/fs/xfs/xfs_iomap.h b/fs/xfs/xfs_iomap.h index 657cc02290f2..e88dc162c785 100644 --- a/fs/xfs/xfs_iomap.h +++ b/fs/xfs/xfs_iomap.h @@ -12,7 +12,8 @@ struct xfs_inode; struct xfs_bmbt_irec; int xfs_iomap_write_direct(struct xfs_inode *ip, xfs_fileoff_t offset_fsb, - xfs_fileoff_t count_fsb, struct xfs_bmbt_irec *imap); + xfs_fileoff_t count_fsb, unsigned int flags, + struct xfs_bmbt_irec *imap); int xfs_iomap_write_unwritten(struct xfs_inode *, xfs_off_t, xfs_off_t, bool); xfs_fileoff_t xfs_iomap_eof_align_last_fsb(struct xfs_inode *ip, xfs_fileoff_t end_fsb); diff --git a/fs/xfs/xfs_pnfs.c b/fs/xfs/xfs_pnfs.c index 7ce1ea11fc3f..d6334abbc0b3 100644 --- a/fs/xfs/xfs_pnfs.c +++ b/fs/xfs/xfs_pnfs.c @@ -155,7 +155,7 @@ xfs_fs_map_blocks( xfs_iunlock(ip, lock_flags); error = xfs_iomap_write_direct(ip, offset_fsb, - end_fsb - offset_fsb, &imap); + end_fsb - offset_fsb, 0, &imap); if (error) goto out_unlock; diff --git a/include/linux/iomap.h b/include/linux/iomap.h index 6d1b08d0ae93..5b9432f9f79e 100644 --- a/include/linux/iomap.h +++ b/include/linux/iomap.h @@ -141,6 +141,11 @@ struct iomap_page_ops { #define IOMAP_NOWAIT (1 << 5) /* do not block */ #define IOMAP_OVERWRITE_ONLY (1 << 6) /* only pure overwrites allowed */ #define IOMAP_UNSHARE (1 << 7) /* unshare_file_range */ +#ifdef CONFIG_FS_DAX +#define IOMAP_DAX (1 << 8) /* DAX mapping */ +#else +#define IOMAP_DAX 0 +#endif /* CONFIG_FS_DAX */ struct iomap_ops { /* -- cgit v1.2.3 From cd913c76f489def1a388e3a5b10df94948ede3f5 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 29 Nov 2021 11:21:59 +0100 Subject: dax: return the partition offset from fs_dax_get_by_bdev Prepare for the removal of the block_device from the DAX I/O path by returning the partition offset from fs_dax_get_by_bdev so that the file systems have it at hand for use during I/O. Signed-off-by: Christoph Hellwig Reviewed-by: Dan Williams Reviewed-by: Darrick J. Wong Link: https://lore.kernel.org/r/20211129102203.2243509-26-hch@lst.de Signed-off-by: Dan Williams --- drivers/dax/super.c | 9 ++++++--- drivers/md/dm.c | 4 ++-- fs/erofs/internal.h | 2 ++ fs/erofs/super.c | 4 ++-- fs/ext2/ext2.h | 1 + fs/ext2/super.c | 2 +- fs/ext4/ext4.h | 1 + fs/ext4/super.c | 2 +- fs/xfs/xfs_buf.c | 2 +- fs/xfs/xfs_buf.h | 1 + include/linux/dax.h | 6 ++++-- 11 files changed, 22 insertions(+), 12 deletions(-) diff --git a/drivers/dax/super.c b/drivers/dax/super.c index 45d931aefd06..e7152a6c4cc4 100644 --- a/drivers/dax/super.c +++ b/drivers/dax/super.c @@ -69,17 +69,20 @@ EXPORT_SYMBOL_GPL(dax_remove_host); /** * fs_dax_get_by_bdev() - temporary lookup mechanism for filesystem-dax * @bdev: block device to find a dax_device for + * @start_off: returns the byte offset into the dax_device that @bdev starts */ -struct dax_device *fs_dax_get_by_bdev(struct block_device *bdev) +struct dax_device *fs_dax_get_by_bdev(struct block_device *bdev, u64 *start_off) { struct dax_device *dax_dev; + u64 part_size; int id; if (!blk_queue_dax(bdev->bd_disk->queue)) return NULL; - if ((get_start_sect(bdev) * SECTOR_SIZE) % PAGE_SIZE || - (bdev_nr_sectors(bdev) * SECTOR_SIZE) % PAGE_SIZE) { + *start_off = get_start_sect(bdev) * SECTOR_SIZE; + part_size = bdev_nr_sectors(bdev) * SECTOR_SIZE; + if (*start_off % PAGE_SIZE || part_size % PAGE_SIZE) { pr_info("%pg: error: unaligned partition for dax\n", bdev); return NULL; } diff --git a/drivers/md/dm.c b/drivers/md/dm.c index 4eba27e75c23..4e997c02bb0a 100644 --- a/drivers/md/dm.c +++ b/drivers/md/dm.c @@ -637,7 +637,7 @@ static int open_table_device(struct table_device *td, dev_t dev, struct mapped_device *md) { struct block_device *bdev; - + u64 part_off; int r; BUG_ON(td->dm_dev.bdev); @@ -653,7 +653,7 @@ static int open_table_device(struct table_device *td, dev_t dev, } td->dm_dev.bdev = bdev; - td->dm_dev.dax_dev = fs_dax_get_by_bdev(bdev); + td->dm_dev.dax_dev = fs_dax_get_by_bdev(bdev, &part_off); return 0; } diff --git a/fs/erofs/internal.h b/fs/erofs/internal.h index 3265688af7f9..c1e65346e9f1 100644 --- a/fs/erofs/internal.h +++ b/fs/erofs/internal.h @@ -51,6 +51,7 @@ struct erofs_device_info { char *path; struct block_device *bdev; struct dax_device *dax_dev; + u64 dax_part_off; u32 blocks; u32 mapped_blkaddr; @@ -109,6 +110,7 @@ struct erofs_sb_info { #endif /* CONFIG_EROFS_FS_ZIP */ struct erofs_dev_context *devs; struct dax_device *dax_dev; + u64 dax_part_off; u64 total_blocks; u32 primarydevice_blocks; diff --git a/fs/erofs/super.c b/fs/erofs/super.c index 0aed886473c8..71efce16024d 100644 --- a/fs/erofs/super.c +++ b/fs/erofs/super.c @@ -312,7 +312,7 @@ static int erofs_init_devices(struct super_block *sb, goto err_out; } dif->bdev = bdev; - dif->dax_dev = fs_dax_get_by_bdev(bdev); + dif->dax_dev = fs_dax_get_by_bdev(bdev, &dif->dax_part_off); dif->blocks = le32_to_cpu(dis->blocks); dif->mapped_blkaddr = le32_to_cpu(dis->mapped_blkaddr); sbi->total_blocks += dif->blocks; @@ -644,7 +644,7 @@ static int erofs_fc_fill_super(struct super_block *sb, struct fs_context *fc) sb->s_fs_info = sbi; sbi->opt = ctx->opt; - sbi->dax_dev = fs_dax_get_by_bdev(sb->s_bdev); + sbi->dax_dev = fs_dax_get_by_bdev(sb->s_bdev, &sbi->dax_part_off); sbi->devs = ctx->devs; ctx->devs = NULL; diff --git a/fs/ext2/ext2.h b/fs/ext2/ext2.h index 3be9dd6412b7..d4f306aa5ace 100644 --- a/fs/ext2/ext2.h +++ b/fs/ext2/ext2.h @@ -118,6 +118,7 @@ struct ext2_sb_info { spinlock_t s_lock; struct mb_cache *s_ea_block_cache; struct dax_device *s_daxdev; + u64 s_dax_part_off; }; static inline spinlock_t * diff --git a/fs/ext2/super.c b/fs/ext2/super.c index 7e23482862e6..94f1fbd7d3ac 100644 --- a/fs/ext2/super.c +++ b/fs/ext2/super.c @@ -831,7 +831,7 @@ static int ext2_fill_super(struct super_block *sb, void *data, int silent) } sb->s_fs_info = sbi; sbi->s_sb_block = sb_block; - sbi->s_daxdev = fs_dax_get_by_bdev(sb->s_bdev); + sbi->s_daxdev = fs_dax_get_by_bdev(sb->s_bdev, &sbi->s_dax_part_off); spin_lock_init(&sbi->s_lock); ret = -EINVAL; diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h index 404dd50856e5..9cc55bcda6ba 100644 --- a/fs/ext4/ext4.h +++ b/fs/ext4/ext4.h @@ -1697,6 +1697,7 @@ struct ext4_sb_info { */ struct percpu_rw_semaphore s_writepages_rwsem; struct dax_device *s_daxdev; + u64 s_dax_part_off; #ifdef CONFIG_EXT4_DEBUG unsigned long s_simulate_fail; #endif diff --git a/fs/ext4/super.c b/fs/ext4/super.c index 8d7e3449c647..56228e33e52a 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -3913,7 +3913,7 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) if (!sbi->s_blockgroup_lock) goto out_free_base; - sbi->s_daxdev = fs_dax_get_by_bdev(sb->s_bdev); + sbi->s_daxdev = fs_dax_get_by_bdev(sb->s_bdev, &sbi->s_dax_part_off); sb->s_fs_info = sbi; sbi->s_sb = sb; sbi->s_inode_readahead_blks = EXT4_DEF_INODE_READAHEAD_BLKS; diff --git a/fs/xfs/xfs_buf.c b/fs/xfs/xfs_buf.c index 4d4553ffa705..bbb0fbd34e64 100644 --- a/fs/xfs/xfs_buf.c +++ b/fs/xfs/xfs_buf.c @@ -1945,7 +1945,7 @@ xfs_alloc_buftarg( btp->bt_mount = mp; btp->bt_dev = bdev->bd_dev; btp->bt_bdev = bdev; - btp->bt_daxdev = fs_dax_get_by_bdev(bdev); + btp->bt_daxdev = fs_dax_get_by_bdev(bdev, &btp->bt_dax_part_off); /* * Buffer IO error rate limiting. Limit it to no more than 10 messages diff --git a/fs/xfs/xfs_buf.h b/fs/xfs/xfs_buf.h index bd7f709f0d23..edcb6254fa6a 100644 --- a/fs/xfs/xfs_buf.h +++ b/fs/xfs/xfs_buf.h @@ -89,6 +89,7 @@ typedef struct xfs_buftarg { dev_t bt_dev; struct block_device *bt_bdev; struct dax_device *bt_daxdev; + u64 bt_dax_part_off; struct xfs_mount *bt_mount; unsigned int bt_meta_sectorsize; size_t bt_meta_sectormask; diff --git a/include/linux/dax.h b/include/linux/dax.h index b79036743e7f..f6f353382cc9 100644 --- a/include/linux/dax.h +++ b/include/linux/dax.h @@ -117,7 +117,8 @@ static inline void fs_put_dax(struct dax_device *dax_dev) put_dax(dax_dev); } -struct dax_device *fs_dax_get_by_bdev(struct block_device *bdev); +struct dax_device *fs_dax_get_by_bdev(struct block_device *bdev, + u64 *start_off); int dax_writeback_mapping_range(struct address_space *mapping, struct dax_device *dax_dev, struct writeback_control *wbc); @@ -138,7 +139,8 @@ static inline void fs_put_dax(struct dax_device *dax_dev) { } -static inline struct dax_device *fs_dax_get_by_bdev(struct block_device *bdev) +static inline struct dax_device *fs_dax_get_by_bdev(struct block_device *bdev, + u64 *start_off) { return NULL; } -- cgit v1.2.3 From de2051147771017a61b62c02fd4e883c9b07712d Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 29 Nov 2021 11:22:00 +0100 Subject: fsdax: shift partition offset handling into the file systems Remove the last user of ->bdev in dax.c by requiring the file system to pass in an address that already includes the DAX offset. As part of the only set ->bdev or ->daxdev when actually required in the ->iomap_begin methods. Signed-off-by: Christoph Hellwig Reviewed-by: Gao Xiang [erofs] Reviewed-by: Darrick J. Wong Link: https://lore.kernel.org/r/20211129102203.2243509-27-hch@lst.de Signed-off-by: Dan Williams --- fs/dax.c | 6 +----- fs/erofs/data.c | 11 +++++++++-- fs/erofs/internal.h | 1 + fs/ext2/inode.c | 8 ++++++-- fs/ext4/inode.c | 16 +++++++++++----- fs/xfs/xfs_iomap.c | 10 ++++++++-- 6 files changed, 36 insertions(+), 16 deletions(-) diff --git a/fs/dax.c b/fs/dax.c index 148e8b0967f3..e0eecd8e3a8f 100644 --- a/fs/dax.c +++ b/fs/dax.c @@ -711,11 +711,7 @@ int dax_invalidate_mapping_entry_sync(struct address_space *mapping, static pgoff_t dax_iomap_pgoff(const struct iomap *iomap, loff_t pos) { - phys_addr_t paddr = iomap->addr + (pos & PAGE_MASK) - iomap->offset; - - if (iomap->bdev) - paddr += (get_start_sect(iomap->bdev) << SECTOR_SHIFT); - return PHYS_PFN(paddr); + return PHYS_PFN(iomap->addr + (pos & PAGE_MASK) - iomap->offset); } static int copy_cow_page_dax(struct vm_fault *vmf, const struct iomap_iter *iter) diff --git a/fs/erofs/data.c b/fs/erofs/data.c index 0e35ef3f9f3d..9b1bb177ce30 100644 --- a/fs/erofs/data.c +++ b/fs/erofs/data.c @@ -159,6 +159,7 @@ int erofs_map_dev(struct super_block *sb, struct erofs_map_dev *map) /* primary device by default */ map->m_bdev = sb->s_bdev; map->m_daxdev = EROFS_SB(sb)->dax_dev; + map->m_dax_part_off = EROFS_SB(sb)->dax_part_off; if (map->m_deviceid) { down_read(&devs->rwsem); @@ -169,6 +170,7 @@ int erofs_map_dev(struct super_block *sb, struct erofs_map_dev *map) } map->m_bdev = dif->bdev; map->m_daxdev = dif->dax_dev; + map->m_dax_part_off = dif->dax_part_off; up_read(&devs->rwsem); } else if (devs->extra_devices) { down_read(&devs->rwsem); @@ -185,6 +187,7 @@ int erofs_map_dev(struct super_block *sb, struct erofs_map_dev *map) map->m_pa -= startoff; map->m_bdev = dif->bdev; map->m_daxdev = dif->dax_dev; + map->m_dax_part_off = dif->dax_part_off; break; } } @@ -215,9 +218,13 @@ static int erofs_iomap_begin(struct inode *inode, loff_t offset, loff_t length, if (ret) return ret; - iomap->bdev = mdev.m_bdev; - iomap->dax_dev = mdev.m_daxdev; iomap->offset = map.m_la; + if (flags & IOMAP_DAX) { + iomap->dax_dev = mdev.m_daxdev; + iomap->offset += mdev.m_dax_part_off; + } else { + iomap->bdev = mdev.m_bdev; + } iomap->length = map.m_llen; iomap->flags = 0; iomap->private = NULL; diff --git a/fs/erofs/internal.h b/fs/erofs/internal.h index c1e65346e9f1..5c2a83876220 100644 --- a/fs/erofs/internal.h +++ b/fs/erofs/internal.h @@ -438,6 +438,7 @@ static inline int z_erofs_map_blocks_iter(struct inode *inode, struct erofs_map_dev { struct block_device *m_bdev; struct dax_device *m_daxdev; + u64 m_dax_part_off; erofs_off_t m_pa; unsigned int m_deviceid; diff --git a/fs/ext2/inode.c b/fs/ext2/inode.c index 01d69618277d..602578b72d8c 100644 --- a/fs/ext2/inode.c +++ b/fs/ext2/inode.c @@ -817,9 +817,11 @@ static int ext2_iomap_begin(struct inode *inode, loff_t offset, loff_t length, return ret; iomap->flags = 0; - iomap->bdev = inode->i_sb->s_bdev; iomap->offset = (u64)first_block << blkbits; - iomap->dax_dev = sbi->s_daxdev; + if (flags & IOMAP_DAX) + iomap->dax_dev = sbi->s_daxdev; + else + iomap->bdev = inode->i_sb->s_bdev; if (ret == 0) { iomap->type = IOMAP_HOLE; @@ -828,6 +830,8 @@ static int ext2_iomap_begin(struct inode *inode, loff_t offset, loff_t length, } else { iomap->type = IOMAP_MAPPED; iomap->addr = (u64)bno << blkbits; + if (flags & IOMAP_DAX) + iomap->addr += sbi->s_dax_part_off; iomap->length = (u64)ret << blkbits; iomap->flags |= IOMAP_F_MERGED; } diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index 89c4a174bd39..ccafcbc146d3 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -3272,7 +3272,7 @@ static bool ext4_inode_datasync_dirty(struct inode *inode) static void ext4_set_iomap(struct inode *inode, struct iomap *iomap, struct ext4_map_blocks *map, loff_t offset, - loff_t length) + loff_t length, unsigned int flags) { u8 blkbits = inode->i_blkbits; @@ -3289,8 +3289,10 @@ static void ext4_set_iomap(struct inode *inode, struct iomap *iomap, if (map->m_flags & EXT4_MAP_NEW) iomap->flags |= IOMAP_F_NEW; - iomap->bdev = inode->i_sb->s_bdev; - iomap->dax_dev = EXT4_SB(inode->i_sb)->s_daxdev; + if (flags & IOMAP_DAX) + iomap->dax_dev = EXT4_SB(inode->i_sb)->s_daxdev; + else + iomap->bdev = inode->i_sb->s_bdev; iomap->offset = (u64) map->m_lblk << blkbits; iomap->length = (u64) map->m_len << blkbits; @@ -3310,9 +3312,13 @@ static void ext4_set_iomap(struct inode *inode, struct iomap *iomap, if (map->m_flags & EXT4_MAP_UNWRITTEN) { iomap->type = IOMAP_UNWRITTEN; iomap->addr = (u64) map->m_pblk << blkbits; + if (flags & IOMAP_DAX) + iomap->addr += EXT4_SB(inode->i_sb)->s_dax_part_off; } else if (map->m_flags & EXT4_MAP_MAPPED) { iomap->type = IOMAP_MAPPED; iomap->addr = (u64) map->m_pblk << blkbits; + if (flags & IOMAP_DAX) + iomap->addr += EXT4_SB(inode->i_sb)->s_dax_part_off; } else { iomap->type = IOMAP_HOLE; iomap->addr = IOMAP_NULL_ADDR; @@ -3421,7 +3427,7 @@ static int ext4_iomap_begin(struct inode *inode, loff_t offset, loff_t length, if (ret < 0) return ret; out: - ext4_set_iomap(inode, iomap, &map, offset, length); + ext4_set_iomap(inode, iomap, &map, offset, length, flags); return 0; } @@ -3541,7 +3547,7 @@ static int ext4_iomap_begin_report(struct inode *inode, loff_t offset, delalloc = ext4_iomap_is_delalloc(inode, &map); set_iomap: - ext4_set_iomap(inode, iomap, &map, offset, length); + ext4_set_iomap(inode, iomap, &map, offset, length, flags); if (delalloc && iomap->type == IOMAP_HOLE) iomap->type = IOMAP_DELALLOC; diff --git a/fs/xfs/xfs_iomap.c b/fs/xfs/xfs_iomap.c index 0ed3e7674353..e552ce541ec2 100644 --- a/fs/xfs/xfs_iomap.c +++ b/fs/xfs/xfs_iomap.c @@ -71,15 +71,21 @@ xfs_bmbt_to_iomap( iomap->type = IOMAP_DELALLOC; } else { iomap->addr = BBTOB(xfs_fsb_to_db(ip, imap->br_startblock)); + if (mapping_flags & IOMAP_DAX) + iomap->addr += target->bt_dax_part_off; + if (imap->br_state == XFS_EXT_UNWRITTEN) iomap->type = IOMAP_UNWRITTEN; else iomap->type = IOMAP_MAPPED; + } iomap->offset = XFS_FSB_TO_B(mp, imap->br_startoff); iomap->length = XFS_FSB_TO_B(mp, imap->br_blockcount); - iomap->bdev = target->bt_bdev; - iomap->dax_dev = target->bt_daxdev; + if (mapping_flags & IOMAP_DAX) + iomap->dax_dev = target->bt_daxdev; + else + iomap->bdev = target->bt_bdev; iomap->flags = iomap_flags; if (xfs_ipincount(ip) && -- cgit v1.2.3 From 2ede892342b3c628991ff1b9060108a7edd92d94 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 29 Nov 2021 11:22:01 +0100 Subject: dax: fix up some of the block device related ifdefs The DAX device <-> block device association is only enabled if CONFIG_BLOCK is enabled. Update dax.h to account for that and use the right conditions for the fs_put_dax stub as well. Signed-off-by: Christoph Hellwig Reviewed-by: Dan Williams Reviewed-by: Darrick J. Wong Link: https://lore.kernel.org/r/20211129102203.2243509-28-hch@lst.de Signed-off-by: Dan Williams --- include/linux/dax.h | 33 ++++++++++++++++----------------- 1 file changed, 16 insertions(+), 17 deletions(-) diff --git a/include/linux/dax.h b/include/linux/dax.h index f6f353382cc9..87ae4c9b1d65 100644 --- a/include/linux/dax.h +++ b/include/linux/dax.h @@ -108,24 +108,15 @@ static inline bool daxdev_mapping_supported(struct vm_area_struct *vma, #endif struct writeback_control; -#if IS_ENABLED(CONFIG_FS_DAX) +#if defined(CONFIG_BLOCK) && defined(CONFIG_FS_DAX) int dax_add_host(struct dax_device *dax_dev, struct gendisk *disk); void dax_remove_host(struct gendisk *disk); - +struct dax_device *fs_dax_get_by_bdev(struct block_device *bdev, + u64 *start_off); static inline void fs_put_dax(struct dax_device *dax_dev) { put_dax(dax_dev); } - -struct dax_device *fs_dax_get_by_bdev(struct block_device *bdev, - u64 *start_off); -int dax_writeback_mapping_range(struct address_space *mapping, - struct dax_device *dax_dev, struct writeback_control *wbc); - -struct page *dax_layout_busy_page(struct address_space *mapping); -struct page *dax_layout_busy_page_range(struct address_space *mapping, loff_t start, loff_t end); -dax_entry_t dax_lock_page(struct page *page); -void dax_unlock_page(struct page *page, dax_entry_t cookie); #else static inline int dax_add_host(struct dax_device *dax_dev, struct gendisk *disk) { @@ -134,17 +125,25 @@ static inline int dax_add_host(struct dax_device *dax_dev, struct gendisk *disk) static inline void dax_remove_host(struct gendisk *disk) { } - -static inline void fs_put_dax(struct dax_device *dax_dev) -{ -} - static inline struct dax_device *fs_dax_get_by_bdev(struct block_device *bdev, u64 *start_off) { return NULL; } +static inline void fs_put_dax(struct dax_device *dax_dev) +{ +} +#endif /* CONFIG_BLOCK && CONFIG_FS_DAX */ +#if IS_ENABLED(CONFIG_FS_DAX) +int dax_writeback_mapping_range(struct address_space *mapping, + struct dax_device *dax_dev, struct writeback_control *wbc); + +struct page *dax_layout_busy_page(struct address_space *mapping); +struct page *dax_layout_busy_page_range(struct address_space *mapping, loff_t start, loff_t end); +dax_entry_t dax_lock_page(struct page *page); +void dax_unlock_page(struct page *page, dax_entry_t cookie); +#else static inline struct page *dax_layout_busy_page(struct address_space *mapping) { return NULL; -- cgit v1.2.3 From ca72d2210fc5b7a6bc7de1da0f9e1b84f8ee3602 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 29 Nov 2021 11:22:02 +0100 Subject: iomap: build the block based code conditionally Only build the block based iomap code if CONFIG_BLOCK is set. Currently that is always the case, but it will change soon. Signed-off-by: Christoph Hellwig Reviewed-by: Dan Williams Reviewed-by: Darrick J. Wong Link: https://lore.kernel.org/r/20211129102203.2243509-29-hch@lst.de Signed-off-by: Dan Williams --- fs/Kconfig | 4 ++-- fs/iomap/Makefile | 4 ++-- 2 files changed, 4 insertions(+), 4 deletions(-) diff --git a/fs/Kconfig b/fs/Kconfig index a6313a969bc5..6d608330a096 100644 --- a/fs/Kconfig +++ b/fs/Kconfig @@ -15,11 +15,11 @@ config VALIDATE_FS_PARSER Enable this to perform validation of the parameter description for a filesystem when it is registered. -if BLOCK - config FS_IOMAP bool +if BLOCK + source "fs/ext2/Kconfig" source "fs/ext4/Kconfig" source "fs/jbd2/Kconfig" diff --git a/fs/iomap/Makefile b/fs/iomap/Makefile index 4143a3ff89db..fc070184b7fa 100644 --- a/fs/iomap/Makefile +++ b/fs/iomap/Makefile @@ -9,9 +9,9 @@ ccflags-y += -I $(srctree)/$(src) # needed for trace events obj-$(CONFIG_FS_IOMAP) += iomap.o iomap-y += trace.o \ - buffered-io.o \ + iter.o +iomap-$(CONFIG_BLOCK) += buffered-io.o \ direct-io.o \ fiemap.o \ - iter.o \ seek.o iomap-$(CONFIG_SWAP) += swapfile.o -- cgit v1.2.3 From b842f1d14a190e217a8ee3f6dae9e1dff1817d87 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 29 Nov 2021 11:22:03 +0100 Subject: fsdax: don't require CONFIG_BLOCK The file system DAX code now does not require the block code. So allow building a kernel with fuse DAX but not block layer. Signed-off-by: Christoph Hellwig Reviewed-by: Dan Williams Reviewed-by: Darrick J. Wong Link: https://lore.kernel.org/r/20211129102203.2243509-30-hch@lst.de Signed-off-by: Dan Williams --- fs/Kconfig | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/fs/Kconfig b/fs/Kconfig index 6d608330a096..7a2b11c0b803 100644 --- a/fs/Kconfig +++ b/fs/Kconfig @@ -42,6 +42,8 @@ source "fs/nilfs2/Kconfig" source "fs/f2fs/Kconfig" source "fs/zonefs/Kconfig" +endif # BLOCK + config FS_DAX bool "File system based Direct Access (DAX) support" depends on MMU @@ -89,8 +91,6 @@ config FS_DAX_PMD config FS_DAX_LIMITED bool -endif # BLOCK - # Posix ACL utility routines # # Note: Posix ACLs can be implemented without these helpers. Never use -- cgit v1.2.3 From b80892ca022e9eb484771a66eb68e12364695a2a Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Thu, 28 Oct 2021 17:10:17 +0200 Subject: memremap: remove support for external pgmap refcounts No driver is left using the external pgmap refcount, so remove the code to support it. Signed-off-by: Christoph Hellwig Acked-by: Bjorn Helgaas Link: https://lore.kernel.org/r/20211028151017.50234-1-hch@lst.de Signed-off-by: Dan Williams --- drivers/pci/p2pdma.c | 2 +- include/linux/memremap.h | 18 ++---------- mm/memremap.c | 59 ++++++++------------------------------- tools/testing/nvdimm/test/iomap.c | 43 ++++++++-------------------- 4 files changed, 28 insertions(+), 94 deletions(-) diff --git a/drivers/pci/p2pdma.c b/drivers/pci/p2pdma.c index 8d47cb7218d1..454d5f6f16ff 100644 --- a/drivers/pci/p2pdma.c +++ b/drivers/pci/p2pdma.c @@ -219,7 +219,7 @@ int pci_p2pdma_add_resource(struct pci_dev *pdev, int bar, size_t size, error = gen_pool_add_owner(p2pdma->pool, (unsigned long)addr, pci_bus_address(pdev, bar) + offset, range_len(&pgmap->range), dev_to_node(&pdev->dev), - pgmap->ref); + &pgmap->ref); if (error) goto pages_free; diff --git a/include/linux/memremap.h b/include/linux/memremap.h index c0e9d35889e8..a8bc588fe7aa 100644 --- a/include/linux/memremap.h +++ b/include/linux/memremap.h @@ -72,16 +72,6 @@ struct dev_pagemap_ops { */ void (*page_free)(struct page *page); - /* - * Transition the refcount in struct dev_pagemap to the dead state. - */ - void (*kill)(struct dev_pagemap *pgmap); - - /* - * Wait for refcount in struct dev_pagemap to be idle and reap it. - */ - void (*cleanup)(struct dev_pagemap *pgmap); - /* * Used for private (un-addressable) device memory only. Must migrate * the page back to a CPU accessible page. @@ -95,8 +85,7 @@ struct dev_pagemap_ops { * struct dev_pagemap - metadata for ZONE_DEVICE mappings * @altmap: pre-allocated/reserved memory for vmemmap allocations * @ref: reference count that pins the devm_memremap_pages() mapping - * @internal_ref: internal reference if @ref is not provided by the caller - * @done: completion for @internal_ref + * @done: completion for @ref * @type: memory type: see MEMORY_* in memory_hotplug.h * @flags: PGMAP_* flags to specify defailed behavior * @ops: method table @@ -109,8 +98,7 @@ struct dev_pagemap_ops { */ struct dev_pagemap { struct vmem_altmap altmap; - struct percpu_ref *ref; - struct percpu_ref internal_ref; + struct percpu_ref ref; struct completion done; enum memory_type type; unsigned int flags; @@ -191,7 +179,7 @@ static inline unsigned long memremap_compat_align(void) static inline void put_dev_pagemap(struct dev_pagemap *pgmap) { if (pgmap) - percpu_ref_put(pgmap->ref); + percpu_ref_put(&pgmap->ref); } #endif /* _LINUX_MEMREMAP_H_ */ diff --git a/mm/memremap.c b/mm/memremap.c index 5a66a71ab591..643965da13a6 100644 --- a/mm/memremap.c +++ b/mm/memremap.c @@ -112,30 +112,6 @@ static unsigned long pfn_next(unsigned long pfn) #define for_each_device_pfn(pfn, map, i) \ for (pfn = pfn_first(map, i); pfn < pfn_end(map, i); pfn = pfn_next(pfn)) -static void dev_pagemap_kill(struct dev_pagemap *pgmap) -{ - if (pgmap->ops && pgmap->ops->kill) - pgmap->ops->kill(pgmap); - else - percpu_ref_kill(pgmap->ref); -} - -static void dev_pagemap_cleanup(struct dev_pagemap *pgmap) -{ - if (pgmap->ops && pgmap->ops->cleanup) { - pgmap->ops->cleanup(pgmap); - } else { - wait_for_completion(&pgmap->done); - percpu_ref_exit(pgmap->ref); - } - /* - * Undo the pgmap ref assignment for the internal case as the - * caller may re-enable the same pgmap. - */ - if (pgmap->ref == &pgmap->internal_ref) - pgmap->ref = NULL; -} - static void pageunmap_range(struct dev_pagemap *pgmap, int range_id) { struct range *range = &pgmap->ranges[range_id]; @@ -167,11 +143,12 @@ void memunmap_pages(struct dev_pagemap *pgmap) unsigned long pfn; int i; - dev_pagemap_kill(pgmap); + percpu_ref_kill(&pgmap->ref); for (i = 0; i < pgmap->nr_range; i++) for_each_device_pfn(pfn, pgmap, i) put_page(pfn_to_page(pfn)); - dev_pagemap_cleanup(pgmap); + wait_for_completion(&pgmap->done); + percpu_ref_exit(&pgmap->ref); for (i = 0; i < pgmap->nr_range; i++) pageunmap_range(pgmap, i); @@ -188,8 +165,7 @@ static void devm_memremap_pages_release(void *data) static void dev_pagemap_percpu_release(struct percpu_ref *ref) { - struct dev_pagemap *pgmap = - container_of(ref, struct dev_pagemap, internal_ref); + struct dev_pagemap *pgmap = container_of(ref, struct dev_pagemap, ref); complete(&pgmap->done); } @@ -295,8 +271,8 @@ static int pagemap_range(struct dev_pagemap *pgmap, struct mhp_params *params, memmap_init_zone_device(&NODE_DATA(nid)->node_zones[ZONE_DEVICE], PHYS_PFN(range->start), PHYS_PFN(range_len(range)), pgmap); - percpu_ref_get_many(pgmap->ref, pfn_end(pgmap, range_id) - - pfn_first(pgmap, range_id)); + percpu_ref_get_many(&pgmap->ref, + pfn_end(pgmap, range_id) - pfn_first(pgmap, range_id)); return 0; err_add_memory: @@ -362,22 +338,11 @@ void *memremap_pages(struct dev_pagemap *pgmap, int nid) break; } - if (!pgmap->ref) { - if (pgmap->ops && (pgmap->ops->kill || pgmap->ops->cleanup)) - return ERR_PTR(-EINVAL); - - init_completion(&pgmap->done); - error = percpu_ref_init(&pgmap->internal_ref, - dev_pagemap_percpu_release, 0, GFP_KERNEL); - if (error) - return ERR_PTR(error); - pgmap->ref = &pgmap->internal_ref; - } else { - if (!pgmap->ops || !pgmap->ops->kill || !pgmap->ops->cleanup) { - WARN(1, "Missing reference count teardown definition\n"); - return ERR_PTR(-EINVAL); - } - } + init_completion(&pgmap->done); + error = percpu_ref_init(&pgmap->ref, dev_pagemap_percpu_release, 0, + GFP_KERNEL); + if (error) + return ERR_PTR(error); devmap_managed_enable_get(pgmap); @@ -486,7 +451,7 @@ struct dev_pagemap *get_dev_pagemap(unsigned long pfn, /* fall back to slow path lookup */ rcu_read_lock(); pgmap = xa_load(&pgmap_array, PHYS_PFN(phys)); - if (pgmap && !percpu_ref_tryget_live(pgmap->ref)) + if (pgmap && !percpu_ref_tryget_live(&pgmap->ref)) pgmap = NULL; rcu_read_unlock(); diff --git a/tools/testing/nvdimm/test/iomap.c b/tools/testing/nvdimm/test/iomap.c index ed563bdd88f3..b752ce47ead3 100644 --- a/tools/testing/nvdimm/test/iomap.c +++ b/tools/testing/nvdimm/test/iomap.c @@ -100,25 +100,17 @@ static void nfit_test_kill(void *_pgmap) { struct dev_pagemap *pgmap = _pgmap; - WARN_ON(!pgmap || !pgmap->ref); - - if (pgmap->ops && pgmap->ops->kill) - pgmap->ops->kill(pgmap); - else - percpu_ref_kill(pgmap->ref); - - if (pgmap->ops && pgmap->ops->cleanup) { - pgmap->ops->cleanup(pgmap); - } else { - wait_for_completion(&pgmap->done); - percpu_ref_exit(pgmap->ref); - } + WARN_ON(!pgmap); + + percpu_ref_kill(&pgmap->ref); + + wait_for_completion(&pgmap->done); + percpu_ref_exit(&pgmap->ref); } static void dev_pagemap_percpu_release(struct percpu_ref *ref) { - struct dev_pagemap *pgmap = - container_of(ref, struct dev_pagemap, internal_ref); + struct dev_pagemap *pgmap = container_of(ref, struct dev_pagemap, ref); complete(&pgmap->done); } @@ -132,22 +124,11 @@ void *__wrap_devm_memremap_pages(struct device *dev, struct dev_pagemap *pgmap) if (!nfit_res) return devm_memremap_pages(dev, pgmap); - if (!pgmap->ref) { - if (pgmap->ops && (pgmap->ops->kill || pgmap->ops->cleanup)) - return ERR_PTR(-EINVAL); - - init_completion(&pgmap->done); - error = percpu_ref_init(&pgmap->internal_ref, - dev_pagemap_percpu_release, 0, GFP_KERNEL); - if (error) - return ERR_PTR(error); - pgmap->ref = &pgmap->internal_ref; - } else { - if (!pgmap->ops || !pgmap->ops->kill || !pgmap->ops->cleanup) { - WARN(1, "Missing reference count teardown definition\n"); - return ERR_PTR(-EINVAL); - } - } + init_completion(&pgmap->done); + error = percpu_ref_init(&pgmap->ref, dev_pagemap_percpu_release, 0, + GFP_KERNEL); + if (error) + return ERR_PTR(error); error = devm_add_action_or_reset(dev, nfit_test_kill, pgmap); if (error) -- cgit v1.2.3 From de291b5902860d18d6e02000808aeb833ec1feb6 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Wed, 8 Dec 2021 10:12:03 +0100 Subject: iomap: turn the byte variable in iomap_zero_iter into a ssize_t @bytes also holds the return value from iomap_write_end, which can contain a negative error value. As @bytes is always less than the page size even the signed type can hold the entire possible range. Fixes: c6f40468657d ("fsdax: decouple zeroing from the iomap buffered I/O code") Reported-by: Dan Carpenter Signed-off-by: Christoph Hellwig Link: https://lore.kernel.org/r/20211208091203.2927754-1-hch@lst.de Signed-off-by: Dan Williams --- fs/iomap/buffered-io.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/iomap/buffered-io.c b/fs/iomap/buffered-io.c index b1511255b4df..ac040d607f4f 100644 --- a/fs/iomap/buffered-io.c +++ b/fs/iomap/buffered-io.c @@ -883,7 +883,7 @@ static loff_t iomap_zero_iter(struct iomap_iter *iter, bool *did_zero) do { unsigned offset = offset_in_page(pos); - size_t bytes = min_t(u64, PAGE_SIZE - offset, length); + ssize_t bytes = min_t(u64, PAGE_SIZE - offset, length); struct page *page; int status; -- cgit v1.2.3 From e17f7a0bc4daa44a4809f5f2f947aa2aa74d1369 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Wed, 15 Dec 2021 09:45:05 +0100 Subject: uio: remove copy_from_iter_flushcache() and copy_mc_to_iter() These two wrappers are never used. Signed-off-by: Christoph Hellwig Link: https://lore.kernel.org/r/20211215084508.435401-2-hch@lst.de Signed-off-by: Dan Williams --- drivers/nvdimm/pmem.c | 4 +--- include/linux/uio.h | 20 +------------------- 2 files changed, 2 insertions(+), 22 deletions(-) diff --git a/drivers/nvdimm/pmem.c b/drivers/nvdimm/pmem.c index 4190c8c46ca8..d225bcfa67cf 100644 --- a/drivers/nvdimm/pmem.c +++ b/drivers/nvdimm/pmem.c @@ -302,9 +302,7 @@ static long pmem_dax_direct_access(struct dax_device *dax_dev, } /* - * Use the 'no check' versions of copy_from_iter_flushcache() and - * copy_mc_to_iter() to bypass HARDENED_USERCOPY overhead. Bounds - * checking, both file offset and device offset, is handled by + * Bounds checking, both file offset and device offset, is handled by * dax_iomap_actor() */ static size_t pmem_copy_from_iter(struct dax_device *dax_dev, pgoff_t pgoff, diff --git a/include/linux/uio.h b/include/linux/uio.h index 6350354f97e9..494d552c1d66 100644 --- a/include/linux/uio.h +++ b/include/linux/uio.h @@ -196,7 +196,7 @@ bool copy_from_iter_full_nocache(void *addr, size_t bytes, struct iov_iter *i) #ifdef CONFIG_ARCH_HAS_UACCESS_FLUSHCACHE /* * Note, users like pmem that depend on the stricter semantics of - * copy_from_iter_flushcache() than copy_from_iter_nocache() must check for + * _copy_from_iter_flushcache() than _copy_from_iter_nocache() must check for * IS_ENABLED(CONFIG_ARCH_HAS_UACCESS_FLUSHCACHE) before assuming that the * destination is flushed from the cache on return. */ @@ -211,24 +211,6 @@ size_t _copy_mc_to_iter(const void *addr, size_t bytes, struct iov_iter *i); #define _copy_mc_to_iter _copy_to_iter #endif -static __always_inline __must_check -size_t copy_from_iter_flushcache(void *addr, size_t bytes, struct iov_iter *i) -{ - if (unlikely(!check_copy_size(addr, bytes, false))) - return 0; - else - return _copy_from_iter_flushcache(addr, bytes, i); -} - -static __always_inline __must_check -size_t copy_mc_to_iter(void *addr, size_t bytes, struct iov_iter *i) -{ - if (unlikely(!check_copy_size(addr, bytes, true))) - return 0; - else - return _copy_mc_to_iter(addr, bytes, i); -} - size_t iov_iter_zero(size_t bytes, struct iov_iter *); unsigned long iov_iter_alignment(const struct iov_iter *i); unsigned long iov_iter_gap_alignment(const struct iov_iter *i); -- cgit v1.2.3 From fd1d00ec92002d8fe28ca981a72395eaa7ae3d11 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Wed, 15 Dec 2021 09:45:06 +0100 Subject: dax: simplify dax_synchronous and set_dax_synchronous Remove the pointless wrappers. Signed-off-by: Christoph Hellwig Reviewed-by: Pankaj Gupta Reviewed-by: Dan Williams Link: https://lore.kernel.org/r/20211215084508.435401-3-hch@lst.de Signed-off-by: Dan Williams --- drivers/dax/super.c | 8 ++++---- include/linux/dax.h | 12 ++---------- 2 files changed, 6 insertions(+), 14 deletions(-) diff --git a/drivers/dax/super.c b/drivers/dax/super.c index e7152a6c4cc4..e18155f43a63 100644 --- a/drivers/dax/super.c +++ b/drivers/dax/super.c @@ -208,17 +208,17 @@ bool dax_write_cache_enabled(struct dax_device *dax_dev) } EXPORT_SYMBOL_GPL(dax_write_cache_enabled); -bool __dax_synchronous(struct dax_device *dax_dev) +bool dax_synchronous(struct dax_device *dax_dev) { return test_bit(DAXDEV_SYNC, &dax_dev->flags); } -EXPORT_SYMBOL_GPL(__dax_synchronous); +EXPORT_SYMBOL_GPL(dax_synchronous); -void __set_dax_synchronous(struct dax_device *dax_dev) +void set_dax_synchronous(struct dax_device *dax_dev) { set_bit(DAXDEV_SYNC, &dax_dev->flags); } -EXPORT_SYMBOL_GPL(__set_dax_synchronous); +EXPORT_SYMBOL_GPL(set_dax_synchronous); bool dax_alive(struct dax_device *dax_dev) { diff --git a/include/linux/dax.h b/include/linux/dax.h index 87ae4c9b1d65..3bd1fdb5d5f4 100644 --- a/include/linux/dax.h +++ b/include/linux/dax.h @@ -48,16 +48,8 @@ void put_dax(struct dax_device *dax_dev); void kill_dax(struct dax_device *dax_dev); void dax_write_cache(struct dax_device *dax_dev, bool wc); bool dax_write_cache_enabled(struct dax_device *dax_dev); -bool __dax_synchronous(struct dax_device *dax_dev); -static inline bool dax_synchronous(struct dax_device *dax_dev) -{ - return __dax_synchronous(dax_dev); -} -void __set_dax_synchronous(struct dax_device *dax_dev); -static inline void set_dax_synchronous(struct dax_device *dax_dev) -{ - __set_dax_synchronous(dax_dev); -} +bool dax_synchronous(struct dax_device *dax_dev); +void set_dax_synchronous(struct dax_device *dax_dev); /* * Check if given mapping is supported by the file / underlying device. */ -- cgit v1.2.3 From 30c6828a17a572aeb9e3a3bacce05fdcf1106541 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Wed, 15 Dec 2021 09:45:07 +0100 Subject: dax: remove the DAXDEV_F_SYNC flag Remove the DAXDEV_F_SYNC flag and thus the flags argument to alloc_dax and just let the drivers call set_dax_synchronous directly. Signed-off-by: Christoph Hellwig Reviewed-by: Pankaj Gupta Reviewed-by: Dan Williams Link: https://lore.kernel.org/r/20211215084508.435401-4-hch@lst.de Signed-off-by: Dan Williams --- drivers/dax/bus.c | 3 ++- drivers/dax/super.c | 6 +----- drivers/md/dm.c | 2 +- drivers/nvdimm/pmem.c | 7 +++---- drivers/s390/block/dcssblk.c | 4 ++-- fs/fuse/virtio_fs.c | 2 +- include/linux/dax.h | 8 ++------ 7 files changed, 12 insertions(+), 20 deletions(-) diff --git a/drivers/dax/bus.c b/drivers/dax/bus.c index 6683d42c32c5..da2a14d096d2 100644 --- a/drivers/dax/bus.c +++ b/drivers/dax/bus.c @@ -1324,11 +1324,12 @@ struct dev_dax *devm_create_dev_dax(struct dev_dax_data *data) * No dax_operations since there is no access to this device outside of * mmap of the resulting character device. */ - dax_dev = alloc_dax(dev_dax, NULL, DAXDEV_F_SYNC); + dax_dev = alloc_dax(dev_dax, NULL); if (IS_ERR(dax_dev)) { rc = PTR_ERR(dax_dev); goto err_alloc_dax; } + set_dax_synchronous(dax_dev); /* a device_dax instance is dead while the driver is not attached */ kill_dax(dax_dev); diff --git a/drivers/dax/super.c b/drivers/dax/super.c index e18155f43a63..e81d5ee57390 100644 --- a/drivers/dax/super.c +++ b/drivers/dax/super.c @@ -345,8 +345,7 @@ static struct dax_device *dax_dev_get(dev_t devt) return dax_dev; } -struct dax_device *alloc_dax(void *private, const struct dax_operations *ops, - unsigned long flags) +struct dax_device *alloc_dax(void *private, const struct dax_operations *ops) { struct dax_device *dax_dev; dev_t devt; @@ -366,9 +365,6 @@ struct dax_device *alloc_dax(void *private, const struct dax_operations *ops, dax_dev->ops = ops; dax_dev->private = private; - if (flags & DAXDEV_F_SYNC) - set_dax_synchronous(dax_dev); - return dax_dev; err_dev: diff --git a/drivers/md/dm.c b/drivers/md/dm.c index 4e997c02bb0a..f4b972af1092 100644 --- a/drivers/md/dm.c +++ b/drivers/md/dm.c @@ -1765,7 +1765,7 @@ static struct mapped_device *alloc_dev(int minor) sprintf(md->disk->disk_name, "dm-%d", minor); if (IS_ENABLED(CONFIG_FS_DAX)) { - md->dax_dev = alloc_dax(md, &dm_dax_ops, 0); + md->dax_dev = alloc_dax(md, &dm_dax_ops); if (IS_ERR(md->dax_dev)) { md->dax_dev = NULL; goto bad; diff --git a/drivers/nvdimm/pmem.c b/drivers/nvdimm/pmem.c index d225bcfa67cf..18b1d9c55831 100644 --- a/drivers/nvdimm/pmem.c +++ b/drivers/nvdimm/pmem.c @@ -400,7 +400,6 @@ static int pmem_attach_disk(struct device *dev, struct gendisk *disk; void *addr; int rc; - unsigned long flags = 0UL; pmem = devm_kzalloc(dev, sizeof(*pmem), GFP_KERNEL); if (!pmem) @@ -493,13 +492,13 @@ static int pmem_attach_disk(struct device *dev, nvdimm_badblocks_populate(nd_region, &pmem->bb, &bb_range); disk->bb = &pmem->bb; - if (is_nvdimm_sync(nd_region)) - flags = DAXDEV_F_SYNC; - dax_dev = alloc_dax(pmem, &pmem_dax_ops, flags); + dax_dev = alloc_dax(pmem, &pmem_dax_ops); if (IS_ERR(dax_dev)) { rc = PTR_ERR(dax_dev); goto out; } + if (is_nvdimm_sync(nd_region)) + set_dax_synchronous(dax_dev); rc = dax_add_host(dax_dev, disk); if (rc) goto out_cleanup_dax; diff --git a/drivers/s390/block/dcssblk.c b/drivers/s390/block/dcssblk.c index e65e83764d1c..10823debc09b 100644 --- a/drivers/s390/block/dcssblk.c +++ b/drivers/s390/block/dcssblk.c @@ -686,13 +686,13 @@ dcssblk_add_store(struct device *dev, struct device_attribute *attr, const char if (rc) goto put_dev; - dev_info->dax_dev = alloc_dax(dev_info, &dcssblk_dax_ops, - DAXDEV_F_SYNC); + dev_info->dax_dev = alloc_dax(dev_info, &dcssblk_dax_ops); if (IS_ERR(dev_info->dax_dev)) { rc = PTR_ERR(dev_info->dax_dev); dev_info->dax_dev = NULL; goto put_dev; } + set_dax_synchronous(dev_info->dax_dev); rc = dax_add_host(dev_info->dax_dev, dev_info->gd); if (rc) goto out_dax; diff --git a/fs/fuse/virtio_fs.c b/fs/fuse/virtio_fs.c index 242cc1c0d7ed..5c03a0364a9b 100644 --- a/fs/fuse/virtio_fs.c +++ b/fs/fuse/virtio_fs.c @@ -850,7 +850,7 @@ static int virtio_fs_setup_dax(struct virtio_device *vdev, struct virtio_fs *fs) dev_dbg(&vdev->dev, "%s: window kaddr 0x%px phys_addr 0x%llx len 0x%llx\n", __func__, fs->window_kaddr, cache_reg.addr, cache_reg.len); - fs->dax_dev = alloc_dax(fs, &virtio_fs_dax_ops, 0); + fs->dax_dev = alloc_dax(fs, &virtio_fs_dax_ops); if (IS_ERR(fs->dax_dev)) return PTR_ERR(fs->dax_dev); diff --git a/include/linux/dax.h b/include/linux/dax.h index 3bd1fdb5d5f4..c04f46478e3b 100644 --- a/include/linux/dax.h +++ b/include/linux/dax.h @@ -6,9 +6,6 @@ #include #include -/* Flag for synchronous flush */ -#define DAXDEV_F_SYNC (1UL << 0) - typedef unsigned long dax_entry_t; struct dax_device; @@ -42,8 +39,7 @@ struct dax_operations { }; #if IS_ENABLED(CONFIG_DAX) -struct dax_device *alloc_dax(void *private, const struct dax_operations *ops, - unsigned long flags); +struct dax_device *alloc_dax(void *private, const struct dax_operations *ops); void put_dax(struct dax_device *dax_dev); void kill_dax(struct dax_device *dax_dev); void dax_write_cache(struct dax_device *dax_dev, bool wc); @@ -64,7 +60,7 @@ static inline bool daxdev_mapping_supported(struct vm_area_struct *vma, } #else static inline struct dax_device *alloc_dax(void *private, - const struct dax_operations *ops, unsigned long flags) + const struct dax_operations *ops) { /* * Callers should check IS_ENABLED(CONFIG_DAX) to know if this -- cgit v1.2.3 From 7ac5360cd4d02cc7e0eaf10867f599e041822f12 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Wed, 15 Dec 2021 09:45:08 +0100 Subject: dax: remove the copy_from_iter and copy_to_iter methods These methods indirect the actual DAX read/write path. In the end pmem uses magic flush and mc safe variants and fuse and dcssblk use plain ones while device mapper picks redirects to the underlying device. Add set_dax_nocache() and set_dax_nomc() APIs to control which copy routines are used to remove indirect call from the read/write fast path as well as a lot of boilerplate code. Signed-off-by: Christoph Hellwig Reviewed-by: Vivek Goyal [virtiofs] Link: https://lore.kernel.org/r/20211215084508.435401-5-hch@lst.de Signed-off-by: Dan Williams --- drivers/dax/bus.c | 2 ++ drivers/dax/super.c | 36 ++++++++++++++++--- drivers/md/dm-linear.c | 20 ----------- drivers/md/dm-log-writes.c | 80 ------------------------------------------- drivers/md/dm-stripe.c | 20 ----------- drivers/md/dm.c | 52 ++-------------------------- drivers/nvdimm/pmem.c | 20 ++--------- drivers/s390/block/dcssblk.c | 14 -------- fs/dax.c | 5 --- fs/fuse/virtio_fs.c | 16 --------- include/linux/dax.h | 9 ++--- include/linux/device-mapper.h | 4 --- 12 files changed, 41 insertions(+), 237 deletions(-) diff --git a/drivers/dax/bus.c b/drivers/dax/bus.c index da2a14d096d2..ee4568ef757c 100644 --- a/drivers/dax/bus.c +++ b/drivers/dax/bus.c @@ -1330,6 +1330,8 @@ struct dev_dax *devm_create_dev_dax(struct dev_dax_data *data) goto err_alloc_dax; } set_dax_synchronous(dax_dev); + set_dax_nocache(dax_dev); + set_dax_nomc(dax_dev); /* a device_dax instance is dead while the driver is not attached */ kill_dax(dax_dev); diff --git a/drivers/dax/super.c b/drivers/dax/super.c index e81d5ee57390..e3029389d809 100644 --- a/drivers/dax/super.c +++ b/drivers/dax/super.c @@ -105,6 +105,10 @@ enum dax_device_flags { DAXDEV_WRITE_CACHE, /* flag to check if device supports synchronous flush */ DAXDEV_SYNC, + /* do not leave the caches dirty after writes */ + DAXDEV_NOCACHE, + /* handle CPU fetch exceptions during reads */ + DAXDEV_NOMC, }; /** @@ -146,9 +150,15 @@ size_t dax_copy_from_iter(struct dax_device *dax_dev, pgoff_t pgoff, void *addr, if (!dax_alive(dax_dev)) return 0; - return dax_dev->ops->copy_from_iter(dax_dev, pgoff, addr, bytes, i); + /* + * The userspace address for the memory copy has already been validated + * via access_ok() in vfs_write, so use the 'no check' version to bypass + * the HARDENED_USERCOPY overhead. + */ + if (test_bit(DAXDEV_NOCACHE, &dax_dev->flags)) + return _copy_from_iter_flushcache(addr, bytes, i); + return _copy_from_iter(addr, bytes, i); } -EXPORT_SYMBOL_GPL(dax_copy_from_iter); size_t dax_copy_to_iter(struct dax_device *dax_dev, pgoff_t pgoff, void *addr, size_t bytes, struct iov_iter *i) @@ -156,9 +166,15 @@ size_t dax_copy_to_iter(struct dax_device *dax_dev, pgoff_t pgoff, void *addr, if (!dax_alive(dax_dev)) return 0; - return dax_dev->ops->copy_to_iter(dax_dev, pgoff, addr, bytes, i); + /* + * The userspace address for the memory copy has already been validated + * via access_ok() in vfs_red, so use the 'no check' version to bypass + * the HARDENED_USERCOPY overhead. + */ + if (test_bit(DAXDEV_NOMC, &dax_dev->flags)) + return _copy_mc_to_iter(addr, bytes, i); + return _copy_to_iter(addr, bytes, i); } -EXPORT_SYMBOL_GPL(dax_copy_to_iter); int dax_zero_page_range(struct dax_device *dax_dev, pgoff_t pgoff, size_t nr_pages) @@ -220,6 +236,18 @@ void set_dax_synchronous(struct dax_device *dax_dev) } EXPORT_SYMBOL_GPL(set_dax_synchronous); +void set_dax_nocache(struct dax_device *dax_dev) +{ + set_bit(DAXDEV_NOCACHE, &dax_dev->flags); +} +EXPORT_SYMBOL_GPL(set_dax_nocache); + +void set_dax_nomc(struct dax_device *dax_dev) +{ + set_bit(DAXDEV_NOMC, &dax_dev->flags); +} +EXPORT_SYMBOL_GPL(set_dax_nomc); + bool dax_alive(struct dax_device *dax_dev) { lockdep_assert_held(&dax_srcu); diff --git a/drivers/md/dm-linear.c b/drivers/md/dm-linear.c index 90de42f6743a..1b97a11d7151 100644 --- a/drivers/md/dm-linear.c +++ b/drivers/md/dm-linear.c @@ -180,22 +180,6 @@ static long linear_dax_direct_access(struct dm_target *ti, pgoff_t pgoff, return dax_direct_access(dax_dev, pgoff, nr_pages, kaddr, pfn); } -static size_t linear_dax_copy_from_iter(struct dm_target *ti, pgoff_t pgoff, - void *addr, size_t bytes, struct iov_iter *i) -{ - struct dax_device *dax_dev = linear_dax_pgoff(ti, &pgoff); - - return dax_copy_from_iter(dax_dev, pgoff, addr, bytes, i); -} - -static size_t linear_dax_copy_to_iter(struct dm_target *ti, pgoff_t pgoff, - void *addr, size_t bytes, struct iov_iter *i) -{ - struct dax_device *dax_dev = linear_dax_pgoff(ti, &pgoff); - - return dax_copy_to_iter(dax_dev, pgoff, addr, bytes, i); -} - static int linear_dax_zero_page_range(struct dm_target *ti, pgoff_t pgoff, size_t nr_pages) { @@ -206,8 +190,6 @@ static int linear_dax_zero_page_range(struct dm_target *ti, pgoff_t pgoff, #else #define linear_dax_direct_access NULL -#define linear_dax_copy_from_iter NULL -#define linear_dax_copy_to_iter NULL #define linear_dax_zero_page_range NULL #endif @@ -225,8 +207,6 @@ static struct target_type linear_target = { .prepare_ioctl = linear_prepare_ioctl, .iterate_devices = linear_iterate_devices, .direct_access = linear_dax_direct_access, - .dax_copy_from_iter = linear_dax_copy_from_iter, - .dax_copy_to_iter = linear_dax_copy_to_iter, .dax_zero_page_range = linear_dax_zero_page_range, }; diff --git a/drivers/md/dm-log-writes.c b/drivers/md/dm-log-writes.c index cdb22e7a1d0d..139b09b06eda 100644 --- a/drivers/md/dm-log-writes.c +++ b/drivers/md/dm-log-writes.c @@ -902,51 +902,6 @@ static void log_writes_io_hints(struct dm_target *ti, struct queue_limits *limit } #if IS_ENABLED(CONFIG_FS_DAX) -static int log_dax(struct log_writes_c *lc, sector_t sector, size_t bytes, - struct iov_iter *i) -{ - struct pending_block *block; - - if (!bytes) - return 0; - - block = kzalloc(sizeof(struct pending_block), GFP_KERNEL); - if (!block) { - DMERR("Error allocating dax pending block"); - return -ENOMEM; - } - - block->data = kzalloc(bytes, GFP_KERNEL); - if (!block->data) { - DMERR("Error allocating dax data space"); - kfree(block); - return -ENOMEM; - } - - /* write data provided via the iterator */ - if (!copy_from_iter(block->data, bytes, i)) { - DMERR("Error copying dax data"); - kfree(block->data); - kfree(block); - return -EIO; - } - - /* rewind the iterator so that the block driver can use it */ - iov_iter_revert(i, bytes); - - block->datalen = bytes; - block->sector = bio_to_dev_sectors(lc, sector); - block->nr_sectors = ALIGN(bytes, lc->sectorsize) >> lc->sectorshift; - - atomic_inc(&lc->pending_blocks); - spin_lock_irq(&lc->blocks_lock); - list_add_tail(&block->list, &lc->unflushed_blocks); - spin_unlock_irq(&lc->blocks_lock); - wake_up_process(lc->log_kthread); - - return 0; -} - static struct dax_device *log_writes_dax_pgoff(struct dm_target *ti, pgoff_t *pgoff) { @@ -964,37 +919,6 @@ static long log_writes_dax_direct_access(struct dm_target *ti, pgoff_t pgoff, return dax_direct_access(dax_dev, pgoff, nr_pages, kaddr, pfn); } -static size_t log_writes_dax_copy_from_iter(struct dm_target *ti, - pgoff_t pgoff, void *addr, size_t bytes, - struct iov_iter *i) -{ - struct log_writes_c *lc = ti->private; - sector_t sector = pgoff * PAGE_SECTORS; - struct dax_device *dax_dev = log_writes_dax_pgoff(ti, &pgoff); - int err; - - /* Don't bother doing anything if logging has been disabled */ - if (!lc->logging_enabled) - goto dax_copy; - - err = log_dax(lc, sector, bytes, i); - if (err) { - DMWARN("Error %d logging DAX write", err); - return 0; - } -dax_copy: - return dax_copy_from_iter(dax_dev, pgoff, addr, bytes, i); -} - -static size_t log_writes_dax_copy_to_iter(struct dm_target *ti, - pgoff_t pgoff, void *addr, size_t bytes, - struct iov_iter *i) -{ - struct dax_device *dax_dev = log_writes_dax_pgoff(ti, &pgoff); - - return dax_copy_to_iter(dax_dev, pgoff, addr, bytes, i); -} - static int log_writes_dax_zero_page_range(struct dm_target *ti, pgoff_t pgoff, size_t nr_pages) { @@ -1005,8 +929,6 @@ static int log_writes_dax_zero_page_range(struct dm_target *ti, pgoff_t pgoff, #else #define log_writes_dax_direct_access NULL -#define log_writes_dax_copy_from_iter NULL -#define log_writes_dax_copy_to_iter NULL #define log_writes_dax_zero_page_range NULL #endif @@ -1024,8 +946,6 @@ static struct target_type log_writes_target = { .iterate_devices = log_writes_iterate_devices, .io_hints = log_writes_io_hints, .direct_access = log_writes_dax_direct_access, - .dax_copy_from_iter = log_writes_dax_copy_from_iter, - .dax_copy_to_iter = log_writes_dax_copy_to_iter, .dax_zero_page_range = log_writes_dax_zero_page_range, }; diff --git a/drivers/md/dm-stripe.c b/drivers/md/dm-stripe.c index 50dba3f39274..e566115ec0bb 100644 --- a/drivers/md/dm-stripe.c +++ b/drivers/md/dm-stripe.c @@ -324,22 +324,6 @@ static long stripe_dax_direct_access(struct dm_target *ti, pgoff_t pgoff, return dax_direct_access(dax_dev, pgoff, nr_pages, kaddr, pfn); } -static size_t stripe_dax_copy_from_iter(struct dm_target *ti, pgoff_t pgoff, - void *addr, size_t bytes, struct iov_iter *i) -{ - struct dax_device *dax_dev = stripe_dax_pgoff(ti, &pgoff); - - return dax_copy_from_iter(dax_dev, pgoff, addr, bytes, i); -} - -static size_t stripe_dax_copy_to_iter(struct dm_target *ti, pgoff_t pgoff, - void *addr, size_t bytes, struct iov_iter *i) -{ - struct dax_device *dax_dev = stripe_dax_pgoff(ti, &pgoff); - - return dax_copy_to_iter(dax_dev, pgoff, addr, bytes, i); -} - static int stripe_dax_zero_page_range(struct dm_target *ti, pgoff_t pgoff, size_t nr_pages) { @@ -350,8 +334,6 @@ static int stripe_dax_zero_page_range(struct dm_target *ti, pgoff_t pgoff, #else #define stripe_dax_direct_access NULL -#define stripe_dax_copy_from_iter NULL -#define stripe_dax_copy_to_iter NULL #define stripe_dax_zero_page_range NULL #endif @@ -488,8 +470,6 @@ static struct target_type stripe_target = { .iterate_devices = stripe_iterate_devices, .io_hints = stripe_io_hints, .direct_access = stripe_dax_direct_access, - .dax_copy_from_iter = stripe_dax_copy_from_iter, - .dax_copy_to_iter = stripe_dax_copy_to_iter, .dax_zero_page_range = stripe_dax_zero_page_range, }; diff --git a/drivers/md/dm.c b/drivers/md/dm.c index f4b972af1092..ce250bd274f3 100644 --- a/drivers/md/dm.c +++ b/drivers/md/dm.c @@ -1027,54 +1027,6 @@ static long dm_dax_direct_access(struct dax_device *dax_dev, pgoff_t pgoff, return ret; } -static size_t dm_dax_copy_from_iter(struct dax_device *dax_dev, pgoff_t pgoff, - void *addr, size_t bytes, struct iov_iter *i) -{ - struct mapped_device *md = dax_get_private(dax_dev); - sector_t sector = pgoff * PAGE_SECTORS; - struct dm_target *ti; - long ret = 0; - int srcu_idx; - - ti = dm_dax_get_live_target(md, sector, &srcu_idx); - - if (!ti) - goto out; - if (!ti->type->dax_copy_from_iter) { - ret = copy_from_iter(addr, bytes, i); - goto out; - } - ret = ti->type->dax_copy_from_iter(ti, pgoff, addr, bytes, i); - out: - dm_put_live_table(md, srcu_idx); - - return ret; -} - -static size_t dm_dax_copy_to_iter(struct dax_device *dax_dev, pgoff_t pgoff, - void *addr, size_t bytes, struct iov_iter *i) -{ - struct mapped_device *md = dax_get_private(dax_dev); - sector_t sector = pgoff * PAGE_SECTORS; - struct dm_target *ti; - long ret = 0; - int srcu_idx; - - ti = dm_dax_get_live_target(md, sector, &srcu_idx); - - if (!ti) - goto out; - if (!ti->type->dax_copy_to_iter) { - ret = copy_to_iter(addr, bytes, i); - goto out; - } - ret = ti->type->dax_copy_to_iter(ti, pgoff, addr, bytes, i); - out: - dm_put_live_table(md, srcu_idx); - - return ret; -} - static int dm_dax_zero_page_range(struct dax_device *dax_dev, pgoff_t pgoff, size_t nr_pages) { @@ -1770,6 +1722,8 @@ static struct mapped_device *alloc_dev(int minor) md->dax_dev = NULL; goto bad; } + set_dax_nocache(md->dax_dev); + set_dax_nomc(md->dax_dev); if (dax_add_host(md->dax_dev, md->disk)) goto bad; } @@ -3024,8 +2978,6 @@ static const struct block_device_operations dm_rq_blk_dops = { static const struct dax_operations dm_dax_ops = { .direct_access = dm_dax_direct_access, - .copy_from_iter = dm_dax_copy_from_iter, - .copy_to_iter = dm_dax_copy_to_iter, .zero_page_range = dm_dax_zero_page_range, }; diff --git a/drivers/nvdimm/pmem.c b/drivers/nvdimm/pmem.c index 18b1d9c55831..58d95242a836 100644 --- a/drivers/nvdimm/pmem.c +++ b/drivers/nvdimm/pmem.c @@ -301,26 +301,8 @@ static long pmem_dax_direct_access(struct dax_device *dax_dev, return __pmem_direct_access(pmem, pgoff, nr_pages, kaddr, pfn); } -/* - * Bounds checking, both file offset and device offset, is handled by - * dax_iomap_actor() - */ -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 size_t pmem_copy_to_iter(struct dax_device *dax_dev, pgoff_t pgoff, - void *addr, size_t bytes, struct iov_iter *i) -{ - return _copy_mc_to_iter(addr, bytes, i); -} - static const struct dax_operations pmem_dax_ops = { .direct_access = pmem_dax_direct_access, - .copy_from_iter = pmem_copy_from_iter, - .copy_to_iter = pmem_copy_to_iter, .zero_page_range = pmem_dax_zero_page_range, }; @@ -497,6 +479,8 @@ static int pmem_attach_disk(struct device *dev, rc = PTR_ERR(dax_dev); goto out; } + set_dax_nocache(dax_dev); + set_dax_nomc(dax_dev); if (is_nvdimm_sync(nd_region)) set_dax_synchronous(dax_dev); rc = dax_add_host(dax_dev, disk); diff --git a/drivers/s390/block/dcssblk.c b/drivers/s390/block/dcssblk.c index 10823debc09b..d614843caf6c 100644 --- a/drivers/s390/block/dcssblk.c +++ b/drivers/s390/block/dcssblk.c @@ -44,18 +44,6 @@ static const struct block_device_operations dcssblk_devops = { .release = dcssblk_release, }; -static size_t dcssblk_dax_copy_from_iter(struct dax_device *dax_dev, - pgoff_t pgoff, void *addr, size_t bytes, struct iov_iter *i) -{ - return copy_from_iter(addr, bytes, i); -} - -static size_t dcssblk_dax_copy_to_iter(struct dax_device *dax_dev, - pgoff_t pgoff, void *addr, size_t bytes, struct iov_iter *i) -{ - return copy_to_iter(addr, bytes, i); -} - static int dcssblk_dax_zero_page_range(struct dax_device *dax_dev, pgoff_t pgoff, size_t nr_pages) { @@ -72,8 +60,6 @@ static int dcssblk_dax_zero_page_range(struct dax_device *dax_dev, static const struct dax_operations dcssblk_dax_ops = { .direct_access = dcssblk_dax_direct_access, - .copy_from_iter = dcssblk_dax_copy_from_iter, - .copy_to_iter = dcssblk_dax_copy_to_iter, .zero_page_range = dcssblk_dax_zero_page_range, }; diff --git a/fs/dax.c b/fs/dax.c index e0eecd8e3a8f..cd03485867a7 100644 --- a/fs/dax.c +++ b/fs/dax.c @@ -1260,11 +1260,6 @@ static loff_t dax_iomap_iter(const struct iomap_iter *iomi, if (map_len > end - pos) map_len = end - pos; - /* - * The userspace address for the memory copy has already been - * validated via access_ok() in either vfs_read() or - * vfs_write(), depending on which operation we are doing. - */ if (iov_iter_rw(iter) == WRITE) xfer = dax_copy_from_iter(dax_dev, pgoff, kaddr, map_len, iter); diff --git a/fs/fuse/virtio_fs.c b/fs/fuse/virtio_fs.c index 5c03a0364a9b..3928cd8ceba6 100644 --- a/fs/fuse/virtio_fs.c +++ b/fs/fuse/virtio_fs.c @@ -753,20 +753,6 @@ static long virtio_fs_direct_access(struct dax_device *dax_dev, pgoff_t pgoff, return nr_pages > max_nr_pages ? max_nr_pages : nr_pages; } -static size_t virtio_fs_copy_from_iter(struct dax_device *dax_dev, - pgoff_t pgoff, void *addr, - size_t bytes, struct iov_iter *i) -{ - return copy_from_iter(addr, bytes, i); -} - -static size_t virtio_fs_copy_to_iter(struct dax_device *dax_dev, - pgoff_t pgoff, void *addr, - size_t bytes, struct iov_iter *i) -{ - return copy_to_iter(addr, bytes, i); -} - static int virtio_fs_zero_page_range(struct dax_device *dax_dev, pgoff_t pgoff, size_t nr_pages) { @@ -783,8 +769,6 @@ static int virtio_fs_zero_page_range(struct dax_device *dax_dev, static const struct dax_operations virtio_fs_dax_ops = { .direct_access = virtio_fs_direct_access, - .copy_from_iter = virtio_fs_copy_from_iter, - .copy_to_iter = virtio_fs_copy_to_iter, .zero_page_range = virtio_fs_zero_page_range, }; diff --git a/include/linux/dax.h b/include/linux/dax.h index c04f46478e3b..9fc5f99a0ae2 100644 --- a/include/linux/dax.h +++ b/include/linux/dax.h @@ -28,12 +28,6 @@ struct dax_operations { */ bool (*dax_supported)(struct dax_device *, struct block_device *, int, sector_t, sector_t); - /* copy_from_iter: required operation for fs-dax direct-i/o */ - size_t (*copy_from_iter)(struct dax_device *, pgoff_t, void *, size_t, - struct iov_iter *); - /* copy_to_iter: required operation for fs-dax direct-i/o */ - size_t (*copy_to_iter)(struct dax_device *, pgoff_t, void *, size_t, - struct iov_iter *); /* zero_page_range: required operation. Zero page range */ int (*zero_page_range)(struct dax_device *, pgoff_t, size_t); }; @@ -95,6 +89,9 @@ static inline bool daxdev_mapping_supported(struct vm_area_struct *vma, } #endif +void set_dax_nocache(struct dax_device *dax_dev); +void set_dax_nomc(struct dax_device *dax_dev); + struct writeback_control; #if defined(CONFIG_BLOCK) && defined(CONFIG_FS_DAX) int dax_add_host(struct dax_device *dax_dev, struct gendisk *disk); diff --git a/include/linux/device-mapper.h b/include/linux/device-mapper.h index a7df155ea49b..b26fecf6c8e8 100644 --- a/include/linux/device-mapper.h +++ b/include/linux/device-mapper.h @@ -147,8 +147,6 @@ typedef int (*dm_busy_fn) (struct dm_target *ti); */ typedef long (*dm_dax_direct_access_fn) (struct dm_target *ti, pgoff_t pgoff, long nr_pages, void **kaddr, pfn_t *pfn); -typedef size_t (*dm_dax_copy_iter_fn)(struct dm_target *ti, pgoff_t pgoff, - void *addr, size_t bytes, struct iov_iter *i); typedef int (*dm_dax_zero_page_range_fn)(struct dm_target *ti, pgoff_t pgoff, size_t nr_pages); @@ -200,8 +198,6 @@ struct target_type { dm_iterate_devices_fn iterate_devices; dm_io_hints_fn io_hints; dm_dax_direct_access_fn direct_access; - dm_dax_copy_iter_fn dax_copy_from_iter; - dm_dax_copy_iter_fn dax_copy_to_iter; dm_dax_zero_page_range_fn dax_zero_page_range; /* For internal device-mapper use. */ -- cgit v1.2.3 From abc14eb1e01286819a671019e78a23542685eee2 Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Mon, 13 Dec 2021 22:46:32 +0200 Subject: ACPI: NFIT: Import GUID before use Strictly speaking the comparison between guid_t and raw buffer is not correct. Import GUID to variable of guid_t type and then compare. Signed-off-by: Andy Shevchenko Link: https://lore.kernel.org/r/20211213204632.56735-1-andriy.shevchenko@linux.intel.com Signed-off-by: Dan Williams --- drivers/acpi/nfit/core.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/drivers/acpi/nfit/core.c b/drivers/acpi/nfit/core.c index 7dd80acf92c7..e5d7f2bda13f 100644 --- a/drivers/acpi/nfit/core.c +++ b/drivers/acpi/nfit/core.c @@ -678,10 +678,12 @@ static const char *spa_type_name(u16 type) int nfit_spa_type(struct acpi_nfit_system_address *spa) { + guid_t guid; int i; + import_guid(&guid, spa->range_guid); for (i = 0; i < NFIT_UUID_MAX; i++) - if (guid_equal(to_nfit_uuid(i), (guid_t *)&spa->range_guid)) + if (guid_equal(to_nfit_uuid(i), &guid)) return i; return -1; } -- cgit v1.2.3 From 9e05e95ca8dae8de4a7a1645014e1bbd9c8a4dab Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Tue, 21 Dec 2021 04:44:50 +0000 Subject: iomap: Fix error handling in iomap_zero_iter() iomap_write_end() does not return a negative errno to indicate an error, but the number of bytes successfully copied. It cannot return an error today, so include a debugging assertion like the one in iomap_unshare_iter(). Fixes: c6f40468657d ("fsdax: decouple zeroing from the iomap buffered I/O code") Reported-by: Dan Carpenter Signed-off-by: Matthew Wilcox (Oracle) Reviewed-by: Christoph Hellwig Link: https://lore.kernel.org/r/20211221044450.517558-1-willy@infradead.org Signed-off-by: Dan Williams --- fs/iomap/buffered-io.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/fs/iomap/buffered-io.c b/fs/iomap/buffered-io.c index ac040d607f4f..49279dfa73c9 100644 --- a/fs/iomap/buffered-io.c +++ b/fs/iomap/buffered-io.c @@ -895,8 +895,8 @@ static loff_t iomap_zero_iter(struct iomap_iter *iter, bool *did_zero) mark_page_accessed(page); bytes = iomap_write_end(iter, pos, bytes, bytes, page); - if (bytes < 0) - return bytes; + if (WARN_ON_ONCE(bytes == 0)) + return -EIO; pos += bytes; length -= bytes; -- cgit v1.2.3