#include <linux/memremap.h>
#include <linux/pagemap.h>
#include <linux/module.h>
#include <linux/device.h>
#include <linux/cdev.h>
#include <linux/slab.h>
#include <linux/dax.h>
#include <linux/fs.h>
#include <linux/mm.h>
#include <linux/mman.h>
#include "dax-private.h"
#include "bus.h"
static int __check_vma(struct dev_dax *dev_dax, vma_flags_t flags,
unsigned long start, unsigned long end, struct file *file,
const char *func)
{
struct device *dev = &dev_dax->dev;
unsigned long mask;
if (!dax_alive(dev_dax->dax_dev))
return -ENXIO;
if (!vma_flags_test(&flags, VMA_MAYSHARE_BIT)) {
dev_info_ratelimited(dev,
"%s: %s: fail, attempted private mapping\n",
current->comm, func);
return -EINVAL;
}
mask = dev_dax->align - 1;
if (start & mask || end & mask) {
dev_info_ratelimited(dev,
"%s: %s: fail, unaligned vma (%#lx - %#lx, %#lx)\n",
current->comm, func, start, end,
mask);
return -EINVAL;
}
if (!file_is_dax(file)) {
dev_info_ratelimited(dev,
"%s: %s: fail, vma is not DAX capable\n",
current->comm, func);
return -EINVAL;
}
return 0;
}
static int check_vma(struct dev_dax *dev_dax, struct vm_area_struct *vma,
const char *func)
{
return __check_vma(dev_dax, vma->flags, vma->vm_start, vma->vm_end,
vma->vm_file, func);
}
__weak phys_addr_t dax_pgoff_to_phys(struct dev_dax *dev_dax, pgoff_t pgoff,
unsigned long size)
{
int i;
for (i = 0; i < dev_dax->nr_range; i++) {
struct dev_dax_range *dax_range = &dev_dax->ranges[i];
struct range *range = &dax_range->range;
unsigned long long pgoff_end;
phys_addr_t phys;
pgoff_end = dax_range->pgoff + PHYS_PFN(range_len(range)) - 1;
if (pgoff < dax_range->pgoff || pgoff > pgoff_end)
continue;
phys = PFN_PHYS(pgoff - dax_range->pgoff) + range->start;
if (phys + size - 1 <= range->end)
return phys;
break;
}
return -1;
}
static void dax_set_mapping(struct vm_fault *vmf, unsigned long 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;
if (dev_dax->pgmap->vmemmap_shift)
nr_pages = 1;
pgoff = linear_page_index(vmf->vma,
ALIGN_DOWN(vmf->address, fault_size));
for (i = 0; i < nr_pages; i++) {
struct folio *folio = pfn_folio(pfn + i);
if (folio->mapping)
continue;
folio->mapping = filp->f_mapping;
folio->index = pgoff + i;
}
}
static vm_fault_t __dev_dax_pte_fault(struct dev_dax *dev_dax,
struct vm_fault *vmf)
{
struct device *dev = &dev_dax->dev;
phys_addr_t phys;
unsigned long pfn;
unsigned int fault_size = PAGE_SIZE;
if (check_vma(dev_dax, vmf->vma, __func__))
return VM_FAULT_SIGBUS;
if (dev_dax->align > PAGE_SIZE) {
dev_dbg(dev, "alignment (%#x) > fault size (%#x)\n",
dev_dax->align, fault_size);
return VM_FAULT_SIGBUS;
}
if (fault_size != dev_dax->align)
return VM_FAULT_SIGBUS;
phys = dax_pgoff_to_phys(dev_dax, vmf->pgoff, PAGE_SIZE);
if (phys == -1) {
dev_dbg(dev, "pgoff_to_phys(%#lx) failed\n", vmf->pgoff);
return VM_FAULT_SIGBUS;
}
pfn = PHYS_PFN(phys);
dax_set_mapping(vmf, pfn, fault_size);
return vmf_insert_page_mkwrite(vmf, pfn_to_page(pfn),
vmf->flags & FAULT_FLAG_WRITE);
}
static vm_fault_t __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;
phys_addr_t phys;
pgoff_t pgoff;
unsigned long pfn;
unsigned int fault_size = PMD_SIZE;
if (check_vma(dev_dax, vmf->vma, __func__))
return VM_FAULT_SIGBUS;
if (dev_dax->align > PMD_SIZE) {
dev_dbg(dev, "alignment (%#x) > fault size (%#x)\n",
dev_dax->align, fault_size);
return VM_FAULT_SIGBUS;
}
if (fault_size < dev_dax->align)
return VM_FAULT_SIGBUS;
else if (fault_size > dev_dax->align)
return VM_FAULT_FALLBACK;
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 = dax_pgoff_to_phys(dev_dax, pgoff, PMD_SIZE);
if (phys == -1) {
dev_dbg(dev, "pgoff_to_phys(%#lx) failed\n", pgoff);
return VM_FAULT_SIGBUS;
}
pfn = PHYS_PFN(phys);
dax_set_mapping(vmf, pfn, fault_size);
return vmf_insert_folio_pmd(vmf, page_folio(pfn_to_page(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)
{
unsigned long pud_addr = vmf->address & PUD_MASK;
struct device *dev = &dev_dax->dev;
phys_addr_t phys;
pgoff_t pgoff;
unsigned long pfn;
unsigned int fault_size = PUD_SIZE;
if (check_vma(dev_dax, vmf->vma, __func__))
return VM_FAULT_SIGBUS;
if (dev_dax->align > PUD_SIZE) {
dev_dbg(dev, "alignment (%#x) > fault size (%#x)\n",
dev_dax->align, fault_size);
return VM_FAULT_SIGBUS;
}
if (fault_size < dev_dax->align)
return VM_FAULT_SIGBUS;
else if (fault_size > dev_dax->align)
return VM_FAULT_FALLBACK;
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 = dax_pgoff_to_phys(dev_dax, pgoff, PUD_SIZE);
if (phys == -1) {
dev_dbg(dev, "pgoff_to_phys(%#lx) failed\n", pgoff);
return VM_FAULT_SIGBUS;
}
pfn = PHYS_PFN(phys);
dax_set_mapping(vmf, pfn, fault_size);
return vmf_insert_folio_pud(vmf, page_folio(pfn_to_page(pfn)),
vmf->flags & FAULT_FLAG_WRITE);
}
#else
static vm_fault_t __dev_dax_pud_fault(struct dev_dax *dev_dax,
struct vm_fault *vmf)
{
return VM_FAULT_FALLBACK;
}
#endif
static vm_fault_t dev_dax_huge_fault(struct vm_fault *vmf, unsigned int order)
{
struct file *filp = vmf->vma->vm_file;
vm_fault_t rc = VM_FAULT_SIGBUS;
int id;
struct dev_dax *dev_dax = filp->private_data;
dev_dbg(&dev_dax->dev, "%s: op=%s addr=%#lx order=%d\n", current->comm,
(vmf->flags & FAULT_FLAG_WRITE) ? "write" : "read",
vmf->address & ~((1UL << (order + PAGE_SHIFT)) - 1), order);
id = dax_read_lock();
if (order == 0)
rc = __dev_dax_pte_fault(dev_dax, vmf);
else if (order == PMD_ORDER)
rc = __dev_dax_pmd_fault(dev_dax, vmf);
else if (order == PUD_ORDER)
rc = __dev_dax_pud_fault(dev_dax, vmf);
else
rc = VM_FAULT_SIGBUS;
dax_read_unlock(id);
return rc;
}
static vm_fault_t dev_dax_fault(struct vm_fault *vmf)
{
return dev_dax_huge_fault(vmf, 0);
}
static int dev_dax_may_split(struct vm_area_struct *vma, unsigned long addr)
{
struct file *filp = vma->vm_file;
struct dev_dax *dev_dax = filp->private_data;
if (!IS_ALIGNED(addr, dev_dax->align))
return -EINVAL;
return 0;
}
static unsigned long dev_dax_pagesize(struct vm_area_struct *vma)
{
struct file *filp = vma->vm_file;
struct dev_dax *dev_dax = filp->private_data;
return dev_dax->align;
}
static const struct vm_operations_struct dax_vm_ops = {
.fault = dev_dax_fault,
.huge_fault = dev_dax_huge_fault,
.may_split = dev_dax_may_split,
.pagesize = dev_dax_pagesize,
};
static int dax_mmap_prepare(struct vm_area_desc *desc)
{
struct file *filp = desc->file;
struct dev_dax *dev_dax = filp->private_data;
int rc, id;
dev_dbg(&dev_dax->dev, "trace\n");
id = dax_read_lock();
rc = __check_vma(dev_dax, desc->vma_flags, desc->start, desc->end, filp,
__func__);
dax_read_unlock(id);
if (rc)
return rc;
desc->vm_ops = &dax_vm_ops;
vma_desc_set_flags(desc, VMA_HUGEPAGE_BIT);
return 0;
}
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;
if (!dev_dax || addr)
goto out;
align = dev_dax->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 = 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 mm_get_unmapped_area(filp, addr, len, pgoff, flags);
}
static const struct address_space_operations dev_dax_aops = {
.dirty_folio = noop_dirty_folio,
};
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, "trace\n");
inode->i_mapping = __dax_inode->i_mapping;
inode->i_mapping->host = __dax_inode;
inode->i_mapping->a_ops = &dev_dax_aops;
filp->f_mapping = inode->i_mapping;
filp->f_wb_err = filemap_sample_wb_err(filp->f_mapping);
filp->f_sb_err = file_sample_sb_err(filp);
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, "trace\n");
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_prepare = dax_mmap_prepare,
.fop_flags = FOP_MMAP_SYNC,
};
static void dev_dax_cdev_del(void *cdev)
{
cdev_del(cdev);
}
static void dev_dax_kill(void *dev_dax)
{
kill_dev_dax(dev_dax);
}
static int dev_dax_probe(struct dev_dax *dev_dax)
{
struct dax_device *dax_dev = dev_dax->dax_dev;
struct device *dev = &dev_dax->dev;
struct dev_pagemap *pgmap;
struct inode *inode;
struct cdev *cdev;
void *addr;
int rc, i;
if (static_dev_dax(dev_dax)) {
if (dev_dax->nr_range > 1) {
dev_warn(dev,
"static pgmap / multi-range device conflict\n");
return -EINVAL;
}
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++) {
struct range *range = &dev_dax->ranges[i].range;
if (!devm_request_mem_region(dev, range->start,
range_len(range), dev_name(dev))) {
dev_warn(dev, "mapping%d: %#llx-%#llx could not reserve range\n",
i, range->start, range->end);
return -EBUSY;
}
}
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);
inode = dax_inode(dax_dev);
cdev = inode->i_cdev;
cdev_init(cdev, &dax_fops);
cdev->owner = dev->driver->owner;
cdev_set_parent(cdev, &dev->kobj);
rc = cdev_add(cdev, dev->devt, 1);
if (rc)
return rc;
rc = devm_add_action_or_reset(dev, dev_dax_cdev_del, cdev);
if (rc)
return rc;
run_dax(dax_dev);
return devm_add_action_or_reset(dev, dev_dax_kill, dev_dax);
}
static struct dax_device_driver device_dax_driver = {
.probe = dev_dax_probe,
.type = DAXDRV_DEVICE_TYPE,
};
static int __init dax_init(void)
{
return dax_driver_register(&device_dax_driver);
}
static void __exit dax_exit(void)
{
dax_driver_unregister(&device_dax_driver);
}
MODULE_AUTHOR("Intel Corporation");
MODULE_DESCRIPTION("Device DAX: direct access device driver");
MODULE_LICENSE("GPL v2");
module_init(dax_init);
module_exit(dax_exit);
MODULE_ALIAS_DAX_DEVICE(0);
