From 7b6be8444e0f0dd675b54d059793423d3c9b4c03 Mon Sep 17 00:00:00 2001 From: Dan Williams Date: Tue, 11 Apr 2017 09:49:49 -0700 Subject: dax: refactor dax-fs into a generic provider of 'struct dax_device' instances We want dax capable drivers to be able to publish a set of dax operations [1]. However, we do not want to further abuse block_devices to advertise these operations. Instead we will attach these operations to a dax device and add a lookup mechanism to go from block device path to a dax device. A dax capable driver like pmem or brd is responsible for registering a dax device, alongside a block device, and then a dax capable filesystem is responsible for retrieving the dax device by path name if it wants to call dax_operations. For now, we refactor the dax pseudo-fs to be a generic facility, rather than an implementation detail, of the device-dax use case. Where a "dax device" is just an inode + dax infrastructure, and "Device DAX" is a mapping service layered on top of that base 'struct dax_device'. "Filesystem DAX" is then a mapping service that layers a filesystem on top of that same base device. Filesystem DAX is associated with a block_device for now, but perhaps directly to a dax device in the future, or for new pmem-only filesystems. [1]: https://lkml.org/lkml/2017/1/19/880 Suggested-by: Christoph Hellwig Signed-off-by: Dan Williams --- drivers/dax/device.c | 709 +++++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 709 insertions(+) create mode 100644 drivers/dax/device.c (limited to 'drivers/dax/device.c') diff --git a/drivers/dax/device.c b/drivers/dax/device.c new file mode 100644 index 000000000000..19a42edbfa03 --- /dev/null +++ b/drivers/dax/device.c @@ -0,0 +1,709 @@ +/* + * Copyright(c) 2016 - 2017 Intel Corporation. All rights reserved. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of version 2 of the GNU General Public License as + * published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, but + * WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU + * General Public License for more details. + */ +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include "dax.h" + +static struct class *dax_class; + +/** + * struct dax_region - mapping infrastructure for dax devices + * @id: kernel-wide unique region for a memory range + * @base: linear address corresponding to @res + * @kref: to pin while other agents have a need to do lookups + * @dev: parent device backing this region + * @align: allocation and mapping alignment for child dax devices + * @res: physical address range of the region + * @pfn_flags: identify whether the pfns are paged back or not + */ +struct dax_region { + int id; + struct ida ida; + void *base; + struct kref kref; + struct device *dev; + unsigned int align; + struct resource res; + unsigned long pfn_flags; +}; + +/** + * struct dev_dax - instance data for a subdivision of a dax region + * @region - parent region + * @dax_dev - core dax functionality + * @dev - device core + * @id - child id in the region + * @num_resources - number of physical address extents in this device + * @res - array of physical address ranges + */ +struct dev_dax { + struct dax_region *region; + struct dax_device *dax_dev; + struct device dev; + int id; + int num_resources; + struct resource res[0]; +}; + +static ssize_t id_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + struct dax_region *dax_region; + ssize_t rc = -ENXIO; + + device_lock(dev); + dax_region = dev_get_drvdata(dev); + if (dax_region) + rc = sprintf(buf, "%d\n", dax_region->id); + device_unlock(dev); + + return rc; +} +static DEVICE_ATTR_RO(id); + +static ssize_t region_size_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + struct dax_region *dax_region; + ssize_t rc = -ENXIO; + + device_lock(dev); + dax_region = dev_get_drvdata(dev); + if (dax_region) + rc = sprintf(buf, "%llu\n", (unsigned long long) + resource_size(&dax_region->res)); + device_unlock(dev); + + return rc; +} +static struct device_attribute dev_attr_region_size = __ATTR(size, 0444, + region_size_show, NULL); + +static ssize_t align_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + struct dax_region *dax_region; + ssize_t rc = -ENXIO; + + device_lock(dev); + dax_region = dev_get_drvdata(dev); + if (dax_region) + rc = sprintf(buf, "%u\n", dax_region->align); + device_unlock(dev); + + return rc; +} +static DEVICE_ATTR_RO(align); + +static struct attribute *dax_region_attributes[] = { + &dev_attr_region_size.attr, + &dev_attr_align.attr, + &dev_attr_id.attr, + NULL, +}; + +static const struct attribute_group dax_region_attribute_group = { + .name = "dax_region", + .attrs = dax_region_attributes, +}; + +static const struct attribute_group *dax_region_attribute_groups[] = { + &dax_region_attribute_group, + NULL, +}; + +static void dax_region_free(struct kref *kref) +{ + struct dax_region *dax_region; + + dax_region = container_of(kref, struct dax_region, kref); + kfree(dax_region); +} + +void dax_region_put(struct dax_region *dax_region) +{ + kref_put(&dax_region->kref, dax_region_free); +} +EXPORT_SYMBOL_GPL(dax_region_put); + +static void dax_region_unregister(void *region) +{ + struct dax_region *dax_region = region; + + sysfs_remove_groups(&dax_region->dev->kobj, + dax_region_attribute_groups); + dax_region_put(dax_region); +} + +struct dax_region *alloc_dax_region(struct device *parent, int region_id, + struct resource *res, unsigned int align, void *addr, + unsigned long pfn_flags) +{ + struct dax_region *dax_region; + + /* + * The DAX core assumes that it can store its private data in + * parent->driver_data. This WARN is a reminder / safeguard for + * developers of device-dax drivers. + */ + if (dev_get_drvdata(parent)) { + dev_WARN(parent, "dax core failed to setup private data\n"); + return NULL; + } + + if (!IS_ALIGNED(res->start, align) + || !IS_ALIGNED(resource_size(res), align)) + return NULL; + + dax_region = kzalloc(sizeof(*dax_region), GFP_KERNEL); + if (!dax_region) + return NULL; + + dev_set_drvdata(parent, dax_region); + memcpy(&dax_region->res, res, sizeof(*res)); + dax_region->pfn_flags = pfn_flags; + kref_init(&dax_region->kref); + dax_region->id = region_id; + ida_init(&dax_region->ida); + dax_region->align = align; + dax_region->dev = parent; + dax_region->base = addr; + if (sysfs_create_groups(&parent->kobj, dax_region_attribute_groups)) { + kfree(dax_region); + return NULL;; + } + + kref_get(&dax_region->kref); + if (devm_add_action_or_reset(parent, dax_region_unregister, dax_region)) + return NULL; + return dax_region; +} +EXPORT_SYMBOL_GPL(alloc_dax_region); + +static struct dev_dax *to_dev_dax(struct device *dev) +{ + return container_of(dev, struct dev_dax, dev); +} + +static ssize_t size_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + struct dev_dax *dev_dax = to_dev_dax(dev); + unsigned long long size = 0; + int i; + + for (i = 0; i < dev_dax->num_resources; i++) + size += resource_size(&dev_dax->res[i]); + + return sprintf(buf, "%llu\n", size); +} +static DEVICE_ATTR_RO(size); + +static struct attribute *dev_dax_attributes[] = { + &dev_attr_size.attr, + NULL, +}; + +static const struct attribute_group dev_dax_attribute_group = { + .attrs = dev_dax_attributes, +}; + +static const struct attribute_group *dax_attribute_groups[] = { + &dev_dax_attribute_group, + NULL, +}; + +static int check_vma(struct dev_dax *dev_dax, struct vm_area_struct *vma, + const char *func) +{ + struct dax_region *dax_region = dev_dax->region; + struct device *dev = &dev_dax->dev; + unsigned long mask; + + if (!dax_alive(dev_dax->dax_dev)) + return -ENXIO; + + /* prevent private mappings from being established */ + if ((vma->vm_flags & VM_MAYSHARE) != VM_MAYSHARE) { + dev_info(dev, "%s: %s: fail, attempted private mapping\n", + current->comm, func); + return -EINVAL; + } + + mask = dax_region->align - 1; + if (vma->vm_start & mask || vma->vm_end & mask) { + dev_info(dev, "%s: %s: fail, unaligned vma (%#lx - %#lx, %#lx)\n", + current->comm, func, vma->vm_start, vma->vm_end, + mask); + return -EINVAL; + } + + if ((dax_region->pfn_flags & (PFN_DEV|PFN_MAP)) == PFN_DEV + && (vma->vm_flags & VM_DONTCOPY) == 0) { + dev_info(dev, "%s: %s: fail, dax range requires MADV_DONTFORK\n", + current->comm, func); + return -EINVAL; + } + + if (!vma_is_dax(vma)) { + dev_info(dev, "%s: %s: fail, vma is not DAX capable\n", + current->comm, func); + return -EINVAL; + } + + return 0; +} + +static phys_addr_t pgoff_to_phys(struct dev_dax *dev_dax, pgoff_t pgoff, + unsigned long size) +{ + struct resource *res; + phys_addr_t phys; + int i; + + for (i = 0; i < dev_dax->num_resources; i++) { + res = &dev_dax->res[i]; + phys = pgoff * PAGE_SIZE + res->start; + if (phys >= res->start && phys <= res->end) + break; + pgoff -= PHYS_PFN(resource_size(res)); + } + + if (i < dev_dax->num_resources) { + res = &dev_dax->res[i]; + if (phys + size - 1 <= res->end) + return phys; + } + + return -1; +} + +static int __dev_dax_pte_fault(struct dev_dax *dev_dax, struct vm_fault *vmf) +{ + struct device *dev = &dev_dax->dev; + struct dax_region *dax_region; + int rc = VM_FAULT_SIGBUS; + phys_addr_t phys; + pfn_t pfn; + unsigned int fault_size = PAGE_SIZE; + + if (check_vma(dev_dax, vmf->vma, __func__)) + return VM_FAULT_SIGBUS; + + dax_region = dev_dax->region; + if (dax_region->align > PAGE_SIZE) { + dev_dbg(dev, "%s: alignment (%#x) > fault size (%#x)\n", + __func__, dax_region->align, fault_size); + return VM_FAULT_SIGBUS; + } + + if (fault_size != dax_region->align) + return VM_FAULT_SIGBUS; + + phys = pgoff_to_phys(dev_dax, vmf->pgoff, PAGE_SIZE); + if (phys == -1) { + dev_dbg(dev, "%s: pgoff_to_phys(%#lx) failed\n", __func__, + vmf->pgoff); + return VM_FAULT_SIGBUS; + } + + pfn = phys_to_pfn_t(phys, dax_region->pfn_flags); + + rc = vm_insert_mixed(vmf->vma, vmf->address, pfn); + + if (rc == -ENOMEM) + return VM_FAULT_OOM; + if (rc < 0 && rc != -EBUSY) + return VM_FAULT_SIGBUS; + + return VM_FAULT_NOPAGE; +} + +static int __dev_dax_pmd_fault(struct dev_dax *dev_dax, struct vm_fault *vmf) +{ + unsigned long pmd_addr = vmf->address & PMD_MASK; + struct device *dev = &dev_dax->dev; + struct dax_region *dax_region; + phys_addr_t phys; + pgoff_t pgoff; + pfn_t pfn; + unsigned int fault_size = PMD_SIZE; + + if (check_vma(dev_dax, vmf->vma, __func__)) + return VM_FAULT_SIGBUS; + + dax_region = dev_dax->region; + if (dax_region->align > PMD_SIZE) { + dev_dbg(dev, "%s: alignment (%#x) > fault size (%#x)\n", + __func__, dax_region->align, fault_size); + return VM_FAULT_SIGBUS; + } + + /* dax pmd mappings require pfn_t_devmap() */ + if ((dax_region->pfn_flags & (PFN_DEV|PFN_MAP)) != (PFN_DEV|PFN_MAP)) { + dev_dbg(dev, "%s: region lacks devmap flags\n", __func__); + return VM_FAULT_SIGBUS; + } + + if (fault_size < dax_region->align) + return VM_FAULT_SIGBUS; + else if (fault_size > dax_region->align) + return VM_FAULT_FALLBACK; + + /* if we are outside of the VMA */ + if (pmd_addr < vmf->vma->vm_start || + (pmd_addr + PMD_SIZE) > vmf->vma->vm_end) + return VM_FAULT_SIGBUS; + + pgoff = linear_page_index(vmf->vma, pmd_addr); + phys = pgoff_to_phys(dev_dax, pgoff, PMD_SIZE); + if (phys == -1) { + dev_dbg(dev, "%s: pgoff_to_phys(%#lx) failed\n", __func__, + pgoff); + return VM_FAULT_SIGBUS; + } + + pfn = phys_to_pfn_t(phys, dax_region->pfn_flags); + + return vmf_insert_pfn_pmd(vmf->vma, vmf->address, vmf->pmd, pfn, + vmf->flags & FAULT_FLAG_WRITE); +} + +#ifdef CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD +static int __dev_dax_pud_fault(struct dev_dax *dev_dax, struct vm_fault *vmf) +{ + unsigned long pud_addr = vmf->address & PUD_MASK; + struct device *dev = &dev_dax->dev; + struct dax_region *dax_region; + phys_addr_t phys; + pgoff_t pgoff; + pfn_t pfn; + unsigned int fault_size = PUD_SIZE; + + + if (check_vma(dev_dax, vmf->vma, __func__)) + return VM_FAULT_SIGBUS; + + dax_region = dev_dax->region; + if (dax_region->align > PUD_SIZE) { + dev_dbg(dev, "%s: alignment (%#x) > fault size (%#x)\n", + __func__, dax_region->align, fault_size); + return VM_FAULT_SIGBUS; + } + + /* dax pud mappings require pfn_t_devmap() */ + if ((dax_region->pfn_flags & (PFN_DEV|PFN_MAP)) != (PFN_DEV|PFN_MAP)) { + dev_dbg(dev, "%s: region lacks devmap flags\n", __func__); + return VM_FAULT_SIGBUS; + } + + if (fault_size < dax_region->align) + return VM_FAULT_SIGBUS; + else if (fault_size > dax_region->align) + return VM_FAULT_FALLBACK; + + /* if we are outside of the VMA */ + if (pud_addr < vmf->vma->vm_start || + (pud_addr + PUD_SIZE) > vmf->vma->vm_end) + return VM_FAULT_SIGBUS; + + pgoff = linear_page_index(vmf->vma, pud_addr); + phys = pgoff_to_phys(dev_dax, pgoff, PUD_SIZE); + if (phys == -1) { + dev_dbg(dev, "%s: pgoff_to_phys(%#lx) failed\n", __func__, + pgoff); + return VM_FAULT_SIGBUS; + } + + pfn = phys_to_pfn_t(phys, dax_region->pfn_flags); + + return vmf_insert_pfn_pud(vmf->vma, vmf->address, vmf->pud, pfn, + vmf->flags & FAULT_FLAG_WRITE); +} +#else +static int __dev_dax_pud_fault(struct dev_dax *dev_dax, struct vm_fault *vmf) +{ + return VM_FAULT_FALLBACK; +} +#endif /* !CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD */ + +static int dev_dax_huge_fault(struct vm_fault *vmf, + enum page_entry_size pe_size) +{ + int rc, id; + struct file *filp = vmf->vma->vm_file; + struct dev_dax *dev_dax = filp->private_data; + + dev_dbg(&dev_dax->dev, "%s: %s: %s (%#lx - %#lx) size = %d\n", __func__, + current->comm, (vmf->flags & FAULT_FLAG_WRITE) + ? "write" : "read", + vmf->vma->vm_start, vmf->vma->vm_end, pe_size); + + id = dax_read_lock(); + switch (pe_size) { + case PE_SIZE_PTE: + rc = __dev_dax_pte_fault(dev_dax, vmf); + break; + case PE_SIZE_PMD: + rc = __dev_dax_pmd_fault(dev_dax, vmf); + break; + case PE_SIZE_PUD: + rc = __dev_dax_pud_fault(dev_dax, vmf); + break; + default: + rc = VM_FAULT_SIGBUS; + } + dax_read_unlock(id); + + return rc; +} + +static int dev_dax_fault(struct vm_fault *vmf) +{ + return dev_dax_huge_fault(vmf, PE_SIZE_PTE); +} + +static const struct vm_operations_struct dax_vm_ops = { + .fault = dev_dax_fault, + .huge_fault = dev_dax_huge_fault, +}; + +static int dax_mmap(struct file *filp, struct vm_area_struct *vma) +{ + struct dev_dax *dev_dax = filp->private_data; + int rc, id; + + dev_dbg(&dev_dax->dev, "%s\n", __func__); + + /* + * We lock to check dax_dev liveness and will re-check at + * fault time. + */ + id = dax_read_lock(); + rc = check_vma(dev_dax, vma, __func__); + dax_read_unlock(id); + if (rc) + return rc; + + vma->vm_ops = &dax_vm_ops; + vma->vm_flags |= VM_MIXEDMAP | VM_HUGEPAGE; + return 0; +} + +/* return an unmapped area aligned to the dax region specified alignment */ +static unsigned long dax_get_unmapped_area(struct file *filp, + unsigned long addr, unsigned long len, unsigned long pgoff, + unsigned long flags) +{ + unsigned long off, off_end, off_align, len_align, addr_align, align; + struct dev_dax *dev_dax = filp ? filp->private_data : NULL; + struct dax_region *dax_region; + + if (!dev_dax || addr) + goto out; + + dax_region = dev_dax->region; + align = dax_region->align; + off = pgoff << PAGE_SHIFT; + off_end = off + len; + off_align = round_up(off, align); + + if ((off_end <= off_align) || ((off_end - off_align) < align)) + goto out; + + len_align = len + align; + if ((off + len_align) < off) + goto out; + + addr_align = current->mm->get_unmapped_area(filp, addr, len_align, + pgoff, flags); + if (!IS_ERR_VALUE(addr_align)) { + addr_align += (off - addr_align) & (align - 1); + return addr_align; + } + out: + return current->mm->get_unmapped_area(filp, addr, len, pgoff, flags); +} + +static int dax_open(struct inode *inode, struct file *filp) +{ + struct dax_device *dax_dev = inode_dax(inode); + struct inode *__dax_inode = dax_inode(dax_dev); + struct dev_dax *dev_dax = dax_get_private(dax_dev); + + dev_dbg(&dev_dax->dev, "%s\n", __func__); + inode->i_mapping = __dax_inode->i_mapping; + inode->i_mapping->host = __dax_inode; + filp->f_mapping = inode->i_mapping; + filp->private_data = dev_dax; + inode->i_flags = S_DAX; + + return 0; +} + +static int dax_release(struct inode *inode, struct file *filp) +{ + struct dev_dax *dev_dax = filp->private_data; + + dev_dbg(&dev_dax->dev, "%s\n", __func__); + return 0; +} + +static const struct file_operations dax_fops = { + .llseek = noop_llseek, + .owner = THIS_MODULE, + .open = dax_open, + .release = dax_release, + .get_unmapped_area = dax_get_unmapped_area, + .mmap = dax_mmap, +}; + +static void dev_dax_release(struct device *dev) +{ + struct dev_dax *dev_dax = to_dev_dax(dev); + struct dax_region *dax_region = dev_dax->region; + struct dax_device *dax_dev = dev_dax->dax_dev; + + ida_simple_remove(&dax_region->ida, dev_dax->id); + dax_region_put(dax_region); + put_dax(dax_dev); + kfree(dev_dax); +} + +static void kill_dev_dax(struct dev_dax *dev_dax) +{ + struct dax_device *dax_dev = dev_dax->dax_dev; + struct inode *inode = dax_inode(dax_dev); + + kill_dax(dax_dev); + unmap_mapping_range(inode->i_mapping, 0, 0, 1); +} + +static void unregister_dev_dax(void *dev) +{ + struct dev_dax *dev_dax = to_dev_dax(dev); + struct dax_device *dax_dev = dev_dax->dax_dev; + struct inode *inode = dax_inode(dax_dev); + struct cdev *cdev = inode->i_cdev; + + dev_dbg(dev, "%s\n", __func__); + + kill_dev_dax(dev_dax); + cdev_device_del(cdev, dev); + put_device(dev); +} + +struct dev_dax *devm_create_dev_dax(struct dax_region *dax_region, + struct resource *res, int count) +{ + struct device *parent = dax_region->dev; + struct dax_device *dax_dev; + struct dev_dax *dev_dax; + struct inode *inode; + struct device *dev; + struct cdev *cdev; + int rc = 0, i; + + dev_dax = kzalloc(sizeof(*dev_dax) + sizeof(*res) * count, GFP_KERNEL); + if (!dev_dax) + return ERR_PTR(-ENOMEM); + + for (i = 0; i < count; i++) { + if (!IS_ALIGNED(res[i].start, dax_region->align) + || !IS_ALIGNED(resource_size(&res[i]), + dax_region->align)) { + rc = -EINVAL; + break; + } + dev_dax->res[i].start = res[i].start; + dev_dax->res[i].end = res[i].end; + } + + if (i < count) + goto err_id; + + dev_dax->id = ida_simple_get(&dax_region->ida, 0, 0, GFP_KERNEL); + if (dev_dax->id < 0) { + rc = dev_dax->id; + goto err_id; + } + + dax_dev = alloc_dax(dev_dax); + if (!dax_dev) + goto err_dax; + + /* from here on we're committed to teardown via dax_dev_release() */ + dev = &dev_dax->dev; + device_initialize(dev); + + inode = dax_inode(dax_dev); + cdev = inode->i_cdev; + cdev_init(cdev, &dax_fops); + cdev->owner = parent->driver->owner; + + dev_dax->num_resources = count; + dev_dax->dax_dev = dax_dev; + dev_dax->region = dax_region; + kref_get(&dax_region->kref); + + dev->devt = inode->i_rdev; + dev->class = dax_class; + dev->parent = parent; + dev->groups = dax_attribute_groups; + dev->release = dev_dax_release; + dev_set_name(dev, "dax%d.%d", dax_region->id, dev_dax->id); + + rc = cdev_device_add(cdev, dev); + if (rc) { + kill_dev_dax(dev_dax); + put_device(dev); + return ERR_PTR(rc); + } + + rc = devm_add_action_or_reset(dax_region->dev, unregister_dev_dax, dev); + if (rc) + return ERR_PTR(rc); + + return dev_dax; + + err_dax: + ida_simple_remove(&dax_region->ida, dev_dax->id); + err_id: + kfree(dev_dax); + + return ERR_PTR(rc); +} +EXPORT_SYMBOL_GPL(devm_create_dev_dax); + +static int __init dax_init(void) +{ + dax_class = class_create(THIS_MODULE, "dax"); + return PTR_ERR_OR_ZERO(dax_class); +} + +static void __exit dax_exit(void) +{ + class_destroy(dax_class); +} + +MODULE_AUTHOR("Intel Corporation"); +MODULE_LICENSE("GPL v2"); +subsys_initcall(dax_init); +module_exit(dax_exit); -- cgit v1.2.3-55-g7522