diff options
Diffstat (limited to 'drivers/dax')
| -rw-r--r-- | drivers/dax/Kconfig | 13 | ||||
| -rw-r--r-- | drivers/dax/Makefile | 3 | ||||
| -rw-r--r-- | drivers/dax/bus.c | 62 | ||||
| -rw-r--r-- | drivers/dax/bus.h | 14 | ||||
| -rw-r--r-- | drivers/dax/device.c | 135 | ||||
| -rw-r--r-- | drivers/dax/hmem/device.c | 5 | ||||
| -rw-r--r-- | drivers/dax/kmem.c | 42 | ||||
| -rw-r--r-- | drivers/dax/pmem.c (renamed from drivers/dax/pmem/core.c) | 36 | ||||
| -rw-r--r-- | drivers/dax/pmem/Makefile | 1 | ||||
| -rw-r--r-- | drivers/dax/pmem/compat.c | 72 | ||||
| -rw-r--r-- | drivers/dax/pmem/pmem.c | 30 | ||||
| -rw-r--r-- | drivers/dax/super.c | 351 |
12 files changed, 338 insertions, 426 deletions
diff --git a/drivers/dax/Kconfig b/drivers/dax/Kconfig index d2834c2cfa10..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 @@ -70,13 +66,4 @@ 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..1dad813ee4a6 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 @@ -129,11 +127,35 @@ ATTRIBUTE_GROUPS(dax_drv); static int dax_bus_match(struct device *dev, struct device_driver *drv); +/* + * Static dax regions are regions created by an external subsystem + * nvdimm where a single range is assigned. Its boundaries are by the external + * subsystem and are usually limited to one physical memory range. For example, + * for PMEM it is usually defined by NVDIMM Namespace boundaries (i.e. a + * single contiguous range) + * + * On dynamic dax regions, the assigned region can be partitioned by dax core + * into multiple subdivisions. A subdivision is represented into one + * /dev/daxN.M device composed by one or more potentially discontiguous ranges. + * + * When allocating a dax region, drivers must set whether it's static + * (IORESOURCE_DAX_STATIC). On static dax devices, the @pgmap is pre-assigned + * to dax core when calling devm_create_dev_dax(), whereas in dynamic dax + * devices it is NULL but afterwards allocated by dax core on device ->probe(). + * Care is needed to make sure that dynamic dax devices are torn down with a + * cleared @pgmap field (see kill_dev_dax()). + */ static bool is_static(struct dax_region *dax_region) { return (dax_region->res.flags & IORESOURCE_DAX_STATIC) != 0; } +bool static_dev_dax(struct dev_dax *dev_dax) +{ + return is_static(dev_dax->region); +} +EXPORT_SYMBOL_GPL(static_dev_dax); + static u64 dev_dax_size(struct dev_dax *dev_dax) { u64 size = 0; @@ -363,6 +385,14 @@ void kill_dev_dax(struct dev_dax *dev_dax) kill_dax(dax_dev); unmap_mapping_range(inode->i_mapping, 0, 0, 1); + + /* + * Dynamic dax region have the pgmap allocated via dev_kzalloc() + * and thus freed by devm. Clear the pgmap to not have stale pgmap + * ranges on probe() from previous reconfigurations of region devices. + */ + if (!static_dev_dax(dev_dax)) + dev_dax->pgmap = NULL; } EXPORT_SYMBOL_GPL(kill_dev_dax); @@ -1323,14 +1353,17 @@ 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); if (IS_ERR(dax_dev)) { rc = PTR_ERR(dax_dev); 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); @@ -1343,10 +1376,7 @@ 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 +1475,10 @@ 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..fbb940293d6d 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; @@ -48,10 +39,7 @@ int __dax_driver_register(struct dax_device_driver *dax_drv, __dax_driver_register(driver, THIS_MODULE, KBUILD_MODNAME) 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 +bool static_dev_dax(struct dev_dax *dev_dax); /* * While run_dax() is potentially a generic operation that could be diff --git a/drivers/dax/device.c b/drivers/dax/device.c index dd8222a42808..5494d745ced5 100644 --- a/drivers/dax/device.c +++ b/drivers/dax/device.c @@ -73,11 +73,39 @@ __weak phys_addr_t dax_pgoff_to_phys(struct dev_dax *dev_dax, pgoff_t pgoff, return -1; } +static void dax_set_mapping(struct vm_fault *vmf, pfn_t pfn, + unsigned long fault_size) +{ + unsigned long i, nr_pages = fault_size / PAGE_SIZE; + struct file *filp = vmf->vma->vm_file; + struct dev_dax *dev_dax = filp->private_data; + pgoff_t pgoff; + + /* mapping is only set on the head */ + if (dev_dax->pgmap->vmemmap_shift) + nr_pages = 1; + + pgoff = linear_page_index(vmf->vma, + ALIGN(vmf->address, fault_size)); + + for (i = 0; i < nr_pages; i++) { + struct page *page = pfn_to_page(pfn_t_to_pfn(pfn) + i); + + page = compound_head(page); + if (page->mapping) + continue; + + page->mapping = filp->f_mapping; + page->index = pgoff + i; + } +} + static vm_fault_t __dev_dax_pte_fault(struct dev_dax *dev_dax, - struct vm_fault *vmf, pfn_t *pfn) + struct vm_fault *vmf) { struct device *dev = &dev_dax->dev; phys_addr_t phys; + pfn_t pfn; unsigned int fault_size = PAGE_SIZE; if (check_vma(dev_dax, vmf->vma, __func__)) @@ -98,18 +126,21 @@ static vm_fault_t __dev_dax_pte_fault(struct dev_dax *dev_dax, return VM_FAULT_SIGBUS; } - *pfn = phys_to_pfn_t(phys, PFN_DEV|PFN_MAP); + pfn = phys_to_pfn_t(phys, PFN_DEV|PFN_MAP); - return vmf_insert_mixed(vmf->vma, vmf->address, *pfn); + dax_set_mapping(vmf, pfn, fault_size); + + return vmf_insert_mixed(vmf->vma, vmf->address, pfn); } static vm_fault_t __dev_dax_pmd_fault(struct dev_dax *dev_dax, - struct vm_fault *vmf, pfn_t *pfn) + struct vm_fault *vmf) { unsigned long pmd_addr = vmf->address & PMD_MASK; struct device *dev = &dev_dax->dev; phys_addr_t phys; pgoff_t pgoff; + pfn_t pfn; unsigned int fault_size = PMD_SIZE; if (check_vma(dev_dax, vmf->vma, __func__)) @@ -138,19 +169,22 @@ static vm_fault_t __dev_dax_pmd_fault(struct dev_dax *dev_dax, return VM_FAULT_SIGBUS; } - *pfn = phys_to_pfn_t(phys, PFN_DEV|PFN_MAP); + pfn = phys_to_pfn_t(phys, PFN_DEV|PFN_MAP); - return vmf_insert_pfn_pmd(vmf, *pfn, vmf->flags & FAULT_FLAG_WRITE); + dax_set_mapping(vmf, pfn, fault_size); + + return vmf_insert_pfn_pmd(vmf, pfn, vmf->flags & FAULT_FLAG_WRITE); } #ifdef CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD static vm_fault_t __dev_dax_pud_fault(struct dev_dax *dev_dax, - struct vm_fault *vmf, pfn_t *pfn) + struct vm_fault *vmf) { unsigned long pud_addr = vmf->address & PUD_MASK; struct device *dev = &dev_dax->dev; phys_addr_t phys; pgoff_t pgoff; + pfn_t pfn; unsigned int fault_size = PUD_SIZE; @@ -180,13 +214,15 @@ static vm_fault_t __dev_dax_pud_fault(struct dev_dax *dev_dax, return VM_FAULT_SIGBUS; } - *pfn = phys_to_pfn_t(phys, PFN_DEV|PFN_MAP); + pfn = phys_to_pfn_t(phys, PFN_DEV|PFN_MAP); - return vmf_insert_pfn_pud(vmf, *pfn, vmf->flags & FAULT_FLAG_WRITE); + dax_set_mapping(vmf, pfn, fault_size); + + return vmf_insert_pfn_pud(vmf, pfn, vmf->flags & FAULT_FLAG_WRITE); } #else static vm_fault_t __dev_dax_pud_fault(struct dev_dax *dev_dax, - struct vm_fault *vmf, pfn_t *pfn) + struct vm_fault *vmf) { return VM_FAULT_FALLBACK; } @@ -196,10 +232,8 @@ static vm_fault_t dev_dax_huge_fault(struct vm_fault *vmf, enum page_entry_size pe_size) { struct file *filp = vmf->vma->vm_file; - unsigned long fault_size; vm_fault_t rc = VM_FAULT_SIGBUS; int id; - pfn_t pfn; struct dev_dax *dev_dax = filp->private_data; dev_dbg(&dev_dax->dev, "%s: %s (%#lx - %#lx) size = %d\n", current->comm, @@ -209,43 +243,18 @@ static vm_fault_t dev_dax_huge_fault(struct vm_fault *vmf, id = dax_read_lock(); switch (pe_size) { case PE_SIZE_PTE: - fault_size = PAGE_SIZE; - rc = __dev_dax_pte_fault(dev_dax, vmf, &pfn); + rc = __dev_dax_pte_fault(dev_dax, vmf); break; case PE_SIZE_PMD: - fault_size = PMD_SIZE; - rc = __dev_dax_pmd_fault(dev_dax, vmf, &pfn); + rc = __dev_dax_pmd_fault(dev_dax, vmf); break; case PE_SIZE_PUD: - fault_size = PUD_SIZE; - rc = __dev_dax_pud_fault(dev_dax, vmf, &pfn); + rc = __dev_dax_pud_fault(dev_dax, vmf); break; default: rc = VM_FAULT_SIGBUS; } - if (rc == VM_FAULT_NOPAGE) { - unsigned long i; - pgoff_t pgoff; - - /* - * In the device-dax case the only possibility for a - * VM_FAULT_NOPAGE result is when device-dax capacity is - * mapped. No need to consider the zero page, or racing - * conflicting mappings. - */ - pgoff = linear_page_index(vmf->vma, vmf->address - & ~(fault_size - 1)); - for (i = 0; i < fault_size / PAGE_SIZE; i++) { - struct page *page; - - page = pfn_to_page(pfn_t_to_pfn(pfn) + i); - if (page->mapping) - continue; - page->mapping = filp->f_mapping; - page->index = pgoff + i; - } - } dax_read_unlock(id); return rc; @@ -337,8 +346,7 @@ static unsigned long dax_get_unmapped_area(struct file *filp, } static const struct address_space_operations dev_dax_aops = { - .set_page_dirty = __set_page_dirty_no_writeback, - .invalidatepage = noop_invalidatepage, + .dirty_folio = noop_dirty_folio, }; static int dax_open(struct inode *inode, struct file *filp) @@ -398,17 +406,34 @@ int dev_dax_probe(struct dev_dax *dev_dax) void *addr; int rc, i; - pgmap = dev_dax->pgmap; - if (dev_WARN_ONCE(dev, pgmap && dev_dax->nr_range > 1, - "static pgmap / multi-range device conflict\n")) - return -EINVAL; + if (static_dev_dax(dev_dax)) { + if (dev_dax->nr_range > 1) { + dev_warn(dev, + "static pgmap / multi-range device conflict\n"); + return -EINVAL; + } - if (!pgmap) { - pgmap = devm_kzalloc(dev, sizeof(*pgmap) + sizeof(struct range) - * (dev_dax->nr_range - 1), GFP_KERNEL); + pgmap = dev_dax->pgmap; + } else { + if (dev_dax->pgmap) { + dev_warn(dev, + "dynamic-dax with pre-populated page map\n"); + return -EINVAL; + } + + pgmap = devm_kzalloc(dev, + struct_size(pgmap, ranges, dev_dax->nr_range - 1), + GFP_KERNEL); if (!pgmap) return -ENOMEM; + pgmap->nr_range = dev_dax->nr_range; + dev_dax->pgmap = pgmap; + + for (i = 0; i < dev_dax->nr_range; i++) { + struct range *range = &dev_dax->ranges[i].range; + pgmap->ranges[i] = *range; + } } for (i = 0; i < dev_dax->nr_range; i++) { @@ -420,12 +445,12 @@ int dev_dax_probe(struct dev_dax *dev_dax) i, range->start, range->end); return -EBUSY; } - /* don't update the range for static pgmap */ - if (!dev_dax->pgmap) - pgmap->ranges[i] = *range; } pgmap->type = MEMORY_DEVICE_GENERIC; + if (dev_dax->align > PAGE_SIZE) + pgmap->vmemmap_shift = + order_base_2(dev_dax->align >> PAGE_SHIFT); addr = devm_memremap_pages(dev, pgmap); if (IS_ERR(addr)) return PTR_ERR(addr); @@ -433,11 +458,7 @@ 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/hmem/device.c b/drivers/dax/hmem/device.c index cb6401c9e9a4..97086fab698e 100644 --- a/drivers/dax/hmem/device.c +++ b/drivers/dax/hmem/device.c @@ -15,6 +15,7 @@ void hmem_register_device(int target_nid, struct resource *r) .start = r->start, .end = r->end, .flags = IORESOURCE_MEM, + .desc = IORES_DESC_SOFT_RESERVED, }; struct platform_device *pdev; struct memregion_info info; @@ -47,7 +48,7 @@ void hmem_register_device(int target_nid, struct resource *r) rc = platform_device_add_data(pdev, &info, sizeof(info)); if (rc < 0) { pr_err("hmem memregion_info allocation failure for %pr\n", &res); - goto out_pdev; + goto out_resource; } rc = platform_device_add_resources(pdev, &res, 1); @@ -65,7 +66,7 @@ void hmem_register_device(int target_nid, struct resource *r) return; out_resource: - put_device(&pdev->dev); + platform_device_put(pdev); out_pdev: memregion_free(id); } diff --git a/drivers/dax/kmem.c b/drivers/dax/kmem.c index a37622060fff..4852a2dbdb27 100644 --- a/drivers/dax/kmem.c +++ b/drivers/dax/kmem.c @@ -11,9 +11,17 @@ #include <linux/fs.h> #include <linux/mm.h> #include <linux/mman.h> +#include <linux/memory-tiers.h> #include "dax-private.h" #include "bus.h" +/* + * Default abstract distance assigned to the NUMA node onlined + * by DAX/kmem if the low level platform driver didn't initialize + * one for this NUMA node. + */ +#define MEMTIER_DEFAULT_DAX_ADISTANCE (MEMTIER_ADISTANCE_DRAM * 5) + /* Memory resource name used for add_memory_driver_managed(). */ static const char *kmem_name; /* Set if any memory will remain added when the driver will be unloaded. */ @@ -41,6 +49,7 @@ struct dax_kmem_data { struct resource *res[]; }; +static struct memory_dev_type *dax_slowmem_type; static int dev_dax_kmem_probe(struct dev_dax *dev_dax) { struct device *dev = &dev_dax->dev; @@ -79,11 +88,13 @@ static int dev_dax_kmem_probe(struct dev_dax *dev_dax) return -EINVAL; } + init_node_memory_type(numa_node, dax_slowmem_type); + + rc = -ENOMEM; data = kzalloc(struct_size(data, res, dev_dax->nr_range), GFP_KERNEL); if (!data) - return -ENOMEM; + goto err_dax_kmem_data; - rc = -ENOMEM; data->res_name = kstrdup(dev_name(dev), GFP_KERNEL); if (!data->res_name) goto err_res_name; @@ -155,6 +166,8 @@ err_reg_mgid: kfree(data->res_name); err_res_name: kfree(data); +err_dax_kmem_data: + clear_node_memory_type(numa_node, dax_slowmem_type); return rc; } @@ -162,6 +175,7 @@ err_res_name: static void dev_dax_kmem_remove(struct dev_dax *dev_dax) { int i, success = 0; + int node = dev_dax->target_node; struct device *dev = &dev_dax->dev; struct dax_kmem_data *data = dev_get_drvdata(dev); @@ -198,6 +212,14 @@ static void dev_dax_kmem_remove(struct dev_dax *dev_dax) kfree(data->res_name); kfree(data); dev_set_drvdata(dev, NULL); + /* + * Clear the memtype association on successful unplug. + * If not, we have memory blocks left which can be + * offlined/onlined later. We need to keep memory_dev_type + * for that. This implies this reference will be around + * till next reboot. + */ + clear_node_memory_type(node, dax_slowmem_type); } } #else @@ -228,9 +250,22 @@ static int __init dax_kmem_init(void) if (!kmem_name) return -ENOMEM; + dax_slowmem_type = alloc_memory_type(MEMTIER_DEFAULT_DAX_ADISTANCE); + if (IS_ERR(dax_slowmem_type)) { + rc = PTR_ERR(dax_slowmem_type); + goto err_dax_slowmem_type; + } + rc = dax_driver_register(&device_dax_kmem_driver); if (rc) - kfree_const(kmem_name); + goto error_dax_driver; + + return rc; + +error_dax_driver: + destroy_memory_type(dax_slowmem_type); +err_dax_slowmem_type: + kfree_const(kmem_name); return rc; } @@ -239,6 +274,7 @@ static void __exit dax_kmem_exit(void) dax_driver_unregister(&device_dax_kmem_driver); if (!any_hotremove_failed) kfree_const(kmem_name); + destroy_memory_type(dax_slowmem_type); } MODULE_AUTHOR("Intel Corporation"); diff --git a/drivers/dax/pmem/core.c b/drivers/dax/pmem.c index 062e8bc14223..f050ea78bb83 100644 --- a/drivers/dax/pmem/core.c +++ b/drivers/dax/pmem.c @@ -3,11 +3,11 @@ #include <linux/memremap.h> #include <linux/module.h> #include <linux/pfn_t.h> -#include "../../nvdimm/pfn.h" -#include "../../nvdimm/nd.h" -#include "../bus.h" +#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) +static struct dev_dax *__dax_pmem_probe(struct device *dev) { struct range range; int rc, id, region_id; @@ -63,7 +63,6 @@ struct dev_dax *__dax_pmem_probe(struct device *dev, enum dev_dax_subsys subsys) .dax_region = dax_region, .id = id, .pgmap = &pgmap, - .subsys = subsys, .size = range_len(&range), }; dev_dax = devm_create_dev_dax(&data); @@ -73,7 +72,32 @@ struct dev_dax *__dax_pmem_probe(struct device *dev, enum dev_dax_subsys subsys) return dev_dax; } -EXPORT_SYMBOL_GPL(__dax_pmem_probe); + +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 <linux/percpu-refcount.h> -#include <linux/memremap.h> -#include <linux/module.h> -#include <linux/pfn_t.h> -#include <linux/nd.h> -#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/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 <linux/nd.h> #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/drivers/dax/super.c b/drivers/dax/super.c index b882cf8106ea..da4438f3188c 100644 --- a/drivers/dax/super.c +++ b/drivers/dax/super.c @@ -7,10 +7,8 @@ #include <linux/mount.h> #include <linux/pseudo_fs.h> #include <linux/magic.h> -#include <linux/genhd.h> #include <linux/pfn_t.h> #include <linux/cdev.h> -#include <linux/hash.h> #include <linux/slab.h> #include <linux/uio.h> #include <linux/dax.h> @@ -21,18 +19,20 @@ * 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 + * @ops: operations for this device + * @holder_data: holder of a dax_device: could be filesystem or mapped device + * @holder_ops: operations for the inner holder */ 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; + void *holder_data; + const struct dax_holder_operations *holder_ops; }; static dev_t dax_devt; @@ -42,10 +42,6 @@ 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); @@ -58,169 +54,72 @@ void dax_read_unlock(int id) } EXPORT_SYMBOL_GPL(dax_read_unlock); -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 <linux/blkdev.h> -int bdev_dax_pgoff(struct block_device *bdev, sector_t sector, size_t size, - pgoff_t *pgoff) +static DEFINE_XARRAY(dax_hosts); + +int dax_add_host(struct dax_device *dax_dev, struct gendisk *disk) { - sector_t start_sect = bdev ? get_start_sect(bdev) : 0; - phys_addr_t phys_off = (start_sect + sector) * 512; + return xa_insert(&dax_hosts, (unsigned long)disk, dax_dev, GFP_KERNEL); +} +EXPORT_SYMBOL_GPL(dax_add_host); - if (pgoff) - *pgoff = PHYS_PFN(phys_off); - if (phys_off % PAGE_SIZE || size % PAGE_SIZE) - return -EINVAL; - return 0; +void dax_remove_host(struct gendisk *disk) +{ + xa_erase(&dax_hosts, (unsigned long)disk); } -EXPORT_SYMBOL(bdev_dax_pgoff); +EXPORT_SYMBOL_GPL(dax_remove_host); -#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 + * 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 + * @holder: filesystem or mapped device inside the dax_device + * @ops: operations for the inner holder */ -static struct dax_device *dax_get_by_host(const char *host) +struct dax_device *fs_dax_get_by_bdev(struct block_device *bdev, u64 *start_off, + void *holder, const struct dax_holder_operations *ops) { - struct dax_device *dax_dev, *found = NULL; - int hash, id; - - if (!host) - 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_read_unlock(id); - - return found; -} + struct dax_device *dax_dev; + u64 part_size; + int id; -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); -} -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) -{ - 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; - - 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; - } - - err = bdev_dax_pgoff(bdev, start, PAGE_SIZE, &pgoff); - if (err) { + *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 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 NULL; } 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_dev = xa_load(&dax_hosts, (unsigned long)bdev->bd_disk); + if (!dax_dev || !dax_alive(dax_dev) || !igrab(&dax_dev->inode)) + dax_dev = NULL; + else if (holder) { + if (!cmpxchg(&dax_dev->holder_data, NULL, holder)) + dax_dev->holder_ops = ops; + else + dax_dev = NULL; } dax_read_unlock(id); - if (!dax_enabled) { - pr_info("%pg: error: dax support not enabled\n", bdev); - return false; - } - return true; + return dax_dev; } -EXPORT_SYMBOL_GPL(generic_fsdax_supported); +EXPORT_SYMBOL_GPL(fs_dax_get_by_bdev); -bool dax_supported(struct dax_device *dax_dev, struct block_device *bdev, - int blocksize, sector_t start, sector_t len) +void fs_put_dax(struct dax_device *dax_dev, void *holder) { - 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; + if (dax_dev && holder && + cmpxchg(&dax_dev->holder_data, holder, NULL) == holder) + dax_dev->holder_ops = NULL; + put_dax(dax_dev); } -EXPORT_SYMBOL_GPL(dax_supported); -#endif /* CONFIG_FS_DAX */ -#endif /* CONFIG_BLOCK */ +EXPORT_SYMBOL_GPL(fs_put_dax); +#endif /* CONFIG_BLOCK && CONFIG_FS_DAX */ enum dax_device_flags { /* !alive + rcu grace period == no new operations / mappings */ @@ -229,6 +128,10 @@ 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, }; /** @@ -236,6 +139,7 @@ enum dax_device_flags { * @dax_dev: a dax_device instance representing the logical memory range * @pgoff: offset in pages from the start of the device to translate * @nr_pages: number of consecutive pages caller can handle relative to @pfn + * @mode: indicator on normal access or recovery write * @kaddr: output parameter that returns a virtual address mapping of pfn * @pfn: output parameter that returns an absolute pfn translation of @pgoff * @@ -243,7 +147,7 @@ enum dax_device_flags { * pages accessible at the device relative @pgoff. */ long dax_direct_access(struct dax_device *dax_dev, pgoff_t pgoff, long nr_pages, - void **kaddr, pfn_t *pfn) + enum dax_access_mode mode, void **kaddr, pfn_t *pfn) { long avail; @@ -257,7 +161,7 @@ long dax_direct_access(struct dax_device *dax_dev, pgoff_t pgoff, long nr_pages, return -EINVAL; avail = dax_dev->ops->direct_access(dax_dev, pgoff, nr_pages, - kaddr, pfn); + mode, kaddr, pfn); if (!avail) return -ERANGE; return min(avail, nr_pages); @@ -270,9 +174,15 @@ 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) @@ -280,9 +190,15 @@ 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) @@ -301,6 +217,38 @@ int dax_zero_page_range(struct dax_device *dax_dev, pgoff_t pgoff, } EXPORT_SYMBOL_GPL(dax_zero_page_range); +size_t dax_recovery_write(struct dax_device *dax_dev, pgoff_t pgoff, + void *addr, size_t bytes, struct iov_iter *iter) +{ + if (!dax_dev->ops->recovery_write) + return 0; + return dax_dev->ops->recovery_write(dax_dev, pgoff, addr, bytes, iter); +} +EXPORT_SYMBOL_GPL(dax_recovery_write); + +int dax_holder_notify_failure(struct dax_device *dax_dev, u64 off, + u64 len, int mf_flags) +{ + int rc, id; + + id = dax_read_lock(); + if (!dax_alive(dax_dev)) { + rc = -ENXIO; + goto out; + } + + if (!dax_dev->holder_ops) { + rc = -EOPNOTSUPP; + goto out; + } + + rc = dax_dev->holder_ops->notify_failure(dax_dev, off, len, mf_flags); +out: + dax_read_unlock(id); + return rc; +} +EXPORT_SYMBOL_GPL(dax_holder_notify_failure); + #ifdef CONFIG_ARCH_HAS_PMEM_API void arch_wb_cache_pmem(void *addr, size_t size); void dax_flush(struct dax_device *dax_dev, void *addr, size_t size) @@ -332,17 +280,29 @@ 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); + +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) { @@ -362,13 +322,15 @@ void kill_dax(struct dax_device *dax_dev) if (!dax_dev) return; - clear_bit(DAXDEV_ALIVE, &dax_dev->flags); + if (dax_dev->holder_data != NULL) + dax_holder_notify_failure(dax_dev, 0, U64_MAX, 0); + 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); + /* clear holder data */ + dax_dev->holder_ops = NULL; + dax_dev->holder_data = NULL; } EXPORT_SYMBOL_GPL(kill_dax); @@ -383,7 +345,7 @@ static struct inode *dax_alloc_inode(struct super_block *sb) struct dax_device *dax_dev; struct inode *inode; - dax_dev = kmem_cache_alloc(dax_cache, GFP_KERNEL); + dax_dev = alloc_inode_sb(sb, dax_cache, GFP_KERNEL); if (!dax_dev) return NULL; @@ -400,10 +362,8 @@ 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)); + ida_free(&dax_minor_ida, iminor(inode)); kmem_cache_free(dax_cache, dax_dev); } @@ -476,65 +436,30 @@ 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) { 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); + minor = ida_alloc_max(&dax_minor_ida, MINORMASK, 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) - set_dax_synchronous(dax_dev); - return dax_dev; err_dev: - ida_simple_remove(&dax_minor_ida, minor); - err_minor: - kfree(host); + ida_free(&dax_minor_ida, minor); return ERR_PTR(-ENOMEM); } EXPORT_SYMBOL_GPL(alloc_dax); @@ -548,6 +473,19 @@ void put_dax(struct dax_device *dax_dev) EXPORT_SYMBOL_GPL(put_dax); /** + * dax_holder() - obtain the holder of a dax device + * @dax_dev: a dax_device instance + + * Return: the holder's data which represents the holder if registered, + * otherwize NULL. + */ +void *dax_holder(struct dax_device *dax_dev) +{ + return dax_dev->holder_data; +} +EXPORT_SYMBOL_GPL(dax_holder); + +/** * inode_dax: convert a public inode into its dax_dev * @inode: An inode with i_cdev pointing to a dax_dev * @@ -614,6 +552,7 @@ static int dax_fs_init(void) static void dax_fs_exit(void) { kern_unmount(dax_mnt); + rcu_barrier(); kmem_cache_destroy(dax_cache); } |