1 files changed, 168 insertions, 156 deletions

diff --git a/drivers/dax/device.c b/drivers/dax/device.c
index 4c0af2eb7e19..22999a402e02 100644
--- a/drivers/dax/device.c
+++ b/drivers/dax/device.c
@@ -4,7 +4,6 @@
 #include <linux/pagemap.h>
 #include <linux/module.h>
 #include <linux/device.h>
-#include <linux/pfn_t.h>
 #include <linux/cdev.h>
 #include <linux/slab.h>
 #include <linux/dax.h>
@@ -14,10 +13,10 @@
 #include "dax-private.h"
 #include "bus.h"
 
-static int check_vma(struct dev_dax *dev_dax, struct vm_area_struct *vma,
-		const char *func)
+static int __check_vma(struct dev_dax *dev_dax, vm_flags_t vm_flags,
+		       unsigned long start, unsigned long end, struct file *file,
+		       const char *func)
 {
-	struct dax_region *dax_region = dev_dax->region;
 	struct device *dev = &dev_dax->dev;
 	unsigned long mask;
 
@@ -25,31 +24,23 @@ static int check_vma(struct dev_dax *dev_dax, struct vm_area_struct *vma,
 		return -ENXIO;
 
 	/* prevent private mappings from being established */
-	if ((vma->vm_flags & VM_MAYSHARE) != VM_MAYSHARE) {
+	if ((vm_flags & VM_MAYSHARE) != VM_MAYSHARE) {
 		dev_info_ratelimited(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) {
+	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, vma->vm_start, vma->vm_end,
+				current->comm, func, start, end,
 				mask);
 		return -EINVAL;
 	}
 
-	if ((dax_region->pfn_flags & (PFN_DEV|PFN_MAP)) == PFN_DEV
-			&& (vma->vm_flags & VM_DONTCOPY) == 0) {
-		dev_info_ratelimited(dev,
-				"%s: %s: fail, dax range requires MADV_DONTFORK\n",
-				current->comm, func);
-		return -EINVAL;
-	}
-
-	if (!vma_is_dax(vma)) {
+	if (!file_is_dax(file)) {
 		dev_info_ratelimited(dev,
 				"%s: %s: fail, vma is not DAX capable\n",
 				current->comm, func);
@@ -59,41 +50,80 @@ static int check_vma(struct dev_dax *dev_dax, struct vm_area_struct *vma,
 	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->vm_flags, vma->vm_start, vma->vm_end,
+			   vma->vm_file, func);
+}
+
 /* see "strong" declaration in tools/testing/nvdimm/dax-dev.c */
 __weak phys_addr_t dax_pgoff_to_phys(struct dev_dax *dev_dax, pgoff_t pgoff,
 		unsigned long size)
 {
-	struct resource *res = &dev_dax->region->res;
-	phys_addr_t phys;
-
-	phys = pgoff * PAGE_SIZE + res->start;
-	if (phys >= res->start && phys <= res->end) {
-		if (phys + size - 1 <= res->end)
+	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;
+
+	/* mapping is only set on the head */
+	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, pfn_t *pfn)
+				struct vm_fault *vmf)
 {
 	struct device *dev = &dev_dax->dev;
-	struct dax_region *dax_region;
 	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;
 
-	dax_region = dev_dax->region;
-	if (dax_region->align > PAGE_SIZE) {
+	if (dev_dax->align > PAGE_SIZE) {
 		dev_dbg(dev, "alignment (%#x) > fault size (%#x)\n",
-			dax_region->align, fault_size);
+			dev_dax->align, fault_size);
 		return VM_FAULT_SIGBUS;
 	}
 
-	if (fault_size != dax_region->align)
+	if (fault_size != dev_dax->align)
 		return VM_FAULT_SIGBUS;
 
 	phys = dax_pgoff_to_phys(dev_dax, vmf->pgoff, PAGE_SIZE);
@@ -102,40 +132,36 @@ static vm_fault_t __dev_dax_pte_fault(struct dev_dax *dev_dax,
 		return VM_FAULT_SIGBUS;
 	}
 
-	*pfn = phys_to_pfn_t(phys, dax_region->pfn_flags);
+	pfn = PHYS_PFN(phys);
 
-	return vmf_insert_mixed(vmf->vma, vmf->address, *pfn);
+	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, pfn_t *pfn)
+				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;
+	unsigned long 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) {
+	if (dev_dax->align > PMD_SIZE) {
 		dev_dbg(dev, "alignment (%#x) > fault size (%#x)\n",
-			dax_region->align, fault_size);
+			dev_dax->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, "region lacks devmap flags\n");
+	if (fault_size < dev_dax->align)
 		return VM_FAULT_SIGBUS;
-	}
-
-	if (fault_size < dax_region->align)
-		return VM_FAULT_SIGBUS;
-	else if (fault_size > dax_region->align)
+	else if (fault_size > dev_dax->align)
 		return VM_FAULT_FALLBACK;
 
 	/* if we are outside of the VMA */
@@ -150,42 +176,38 @@ static vm_fault_t __dev_dax_pmd_fault(struct dev_dax *dev_dax,
 		return VM_FAULT_SIGBUS;
 	}
 
-	*pfn = phys_to_pfn_t(phys, dax_region->pfn_flags);
+	pfn = PHYS_PFN(phys);
+
+	dax_set_mapping(vmf, pfn, fault_size);
 
-	return vmf_insert_pfn_pmd(vmf, *pfn, vmf->flags & FAULT_FLAG_WRITE);
+	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, pfn_t *pfn)
+				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;
+	unsigned long 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) {
+	if (dev_dax->align > PUD_SIZE) {
 		dev_dbg(dev, "alignment (%#x) > fault size (%#x)\n",
-			dax_region->align, fault_size);
+			dev_dax->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, "region lacks devmap flags\n");
+	if (fault_size < dev_dax->align)
 		return VM_FAULT_SIGBUS;
-	}
-
-	if (fault_size < dax_region->align)
-		return VM_FAULT_SIGBUS;
-	else if (fault_size > dax_region->align)
+	else if (fault_size > dev_dax->align)
 		return VM_FAULT_FALLBACK;
 
 	/* if we are outside of the VMA */
@@ -200,72 +222,42 @@ static vm_fault_t __dev_dax_pud_fault(struct dev_dax *dev_dax,
 		return VM_FAULT_SIGBUS;
 	}
 
-	*pfn = phys_to_pfn_t(phys, dax_region->pfn_flags);
+	pfn = PHYS_PFN(phys);
+
+	dax_set_mapping(vmf, pfn, fault_size);
 
-	return vmf_insert_pfn_pud(vmf, *pfn, vmf->flags & FAULT_FLAG_WRITE);
+	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, pfn_t *pfn)
+				struct vm_fault *vmf)
 {
 	return VM_FAULT_FALLBACK;
 }
 #endif /* !CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD */
 
-static vm_fault_t dev_dax_huge_fault(struct vm_fault *vmf,
-		enum page_entry_size pe_size)
+static vm_fault_t dev_dax_huge_fault(struct vm_fault *vmf, unsigned int order)
 {
 	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,
-			(vmf->flags & FAULT_FLAG_WRITE) ? "write" : "read",
-			vmf->vma->vm_start, vmf->vma->vm_end, pe_size);
+	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();
-	switch (pe_size) {
-	case PE_SIZE_PTE:
-		fault_size = PAGE_SIZE;
-		rc = __dev_dax_pte_fault(dev_dax, vmf, &pfn);
-		break;
-	case PE_SIZE_PMD:
-		fault_size = PMD_SIZE;
-		rc = __dev_dax_pmd_fault(dev_dax, vmf, &pfn);
-		break;
-	case PE_SIZE_PUD:
-		fault_size = PUD_SIZE;
-		rc = __dev_dax_pud_fault(dev_dax, vmf, &pfn);
-		break;
-	default:
+	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;
-	}
 
-	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;
@@ -273,16 +265,15 @@ static vm_fault_t dev_dax_huge_fault(struct vm_fault *vmf,
 
 static vm_fault_t dev_dax_fault(struct vm_fault *vmf)
 {
-	return dev_dax_huge_fault(vmf, PE_SIZE_PTE);
+	return dev_dax_huge_fault(vmf, 0);
 }
 
-static int dev_dax_split(struct vm_area_struct *vma, unsigned long addr)
+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;
-	struct dax_region *dax_region = dev_dax->region;
 
-	if (!IS_ALIGNED(addr, dax_region->align))
+	if (!IS_ALIGNED(addr, dev_dax->align))
 		return -EINVAL;
 	return 0;
 }
@@ -291,20 +282,20 @@ 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;
-	struct dax_region *dax_region = dev_dax->region;
 
-	return dax_region->align;
+	return dev_dax->align;
 }
 
 static const struct vm_operations_struct dax_vm_ops = {
 	.fault = dev_dax_fault,
 	.huge_fault = dev_dax_huge_fault,
-	.split = dev_dax_split,
+	.may_split = dev_dax_may_split,
 	.pagesize = dev_dax_pagesize,
 };
 
-static int dax_mmap(struct file *filp, struct vm_area_struct *vma)
+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;
 
@@ -315,13 +306,14 @@ static int dax_mmap(struct file *filp, struct vm_area_struct *vma)
 	 * fault time.
 	 */
 	id = dax_read_lock();
-	rc = check_vma(dev_dax, vma, __func__);
+	rc = __check_vma(dev_dax, desc->vm_flags, desc->start, desc->end, filp,
+			 __func__);
 	dax_read_unlock(id);
 	if (rc)
 		return rc;
 
-	vma->vm_ops = &dax_vm_ops;
-	vma->vm_flags |= VM_HUGEPAGE;
+	desc->vm_ops = &dax_vm_ops;
+	desc->vm_flags |= VM_HUGEPAGE;
 	return 0;
 }
 
@@ -332,13 +324,11 @@ static unsigned long dax_get_unmapped_area(struct file *filp,
 {
 	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;
+	align = dev_dax->align;
 	off = pgoff << PAGE_SHIFT;
 	off_end = off + len;
 	off_align = round_up(off, align);
@@ -350,19 +340,17 @@ static unsigned long dax_get_unmapped_area(struct file *filp,
 	if ((off + len_align) < off)
 		goto out;
 
-	addr_align = current->mm->get_unmapped_area(filp, addr, len_align,
-			pgoff, flags);
+	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 current->mm->get_unmapped_area(filp, addr, len, pgoff, flags);
+	return mm_get_unmapped_area(filp, addr, len, pgoff, flags);
 }
 
 static const struct address_space_operations dev_dax_aops = {
-	.set_page_dirty		= noop_set_page_dirty,
-	.invalidatepage		= noop_invalidatepage,
+	.dirty_folio	= noop_dirty_folio,
 };
 
 static int dax_open(struct inode *inode, struct file *filp)
@@ -398,8 +386,8 @@ static const struct file_operations dax_fops = {
 	.open = dax_open,
 	.release = dax_release,
 	.get_unmapped_area = dax_get_unmapped_area,
-	.mmap = dax_mmap,
-	.mmap_supported_flags = MAP_SYNC,
+	.mmap_prepare = dax_mmap_prepare,
+	.fop_flags = FOP_MMAP_SYNC,
 };
 
 static void dev_dax_cdev_del(void *cdev)
@@ -412,36 +400,69 @@ static void dev_dax_kill(void *dev_dax)
 	kill_dev_dax(dev_dax);
 }
 
-int dev_dax_probe(struct device *dev)
+static int dev_dax_probe(struct dev_dax *dev_dax)
 {
-	struct dev_dax *dev_dax = to_dev_dax(dev);
 	struct dax_device *dax_dev = dev_dax->dax_dev;
-	struct resource *res = &dev_dax->region->res;
+	struct device *dev = &dev_dax->dev;
+	struct dev_pagemap *pgmap;
 	struct inode *inode;
 	struct cdev *cdev;
 	void *addr;
-	int rc;
+	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;
 
-	/* 1:1 map region resource range to device-dax instance range */
-	if (!devm_request_mem_region(dev, res->start, resource_size(res),
-				dev_name(dev))) {
-		dev_warn(dev, "could not reserve region %pR\n", res);
-		return -EBUSY;
+		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;
+		}
 	}
 
-	dev_dax->pgmap.type = MEMORY_DEVICE_DEVDAX;
-	addr = devm_memremap_pages(dev, &dev_dax->pgmap);
+	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);
-	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)
@@ -454,20 +475,10 @@ int dev_dax_probe(struct device *dev)
 	run_dax(dax_dev);
 	return devm_add_action_or_reset(dev, dev_dax_kill, dev_dax);
 }
-EXPORT_SYMBOL_GPL(dev_dax_probe);
-
-static int dev_dax_remove(struct device *dev)
-{
-	/* all probe actions are unwound by devm */
-	return 0;
-}
 
 static struct dax_device_driver device_dax_driver = {
-	.drv = {
-		.probe = dev_dax_probe,
-		.remove = dev_dax_remove,
-	},
-	.match_always = 1,
+	.probe = dev_dax_probe,
+	.type = DAXDRV_DEVICE_TYPE,
 };
 
 static int __init dax_init(void)
@@ -481,6 +492,7 @@ static void __exit dax_exit(void)
 }
 
 MODULE_AUTHOR("Intel Corporation");
+MODULE_DESCRIPTION("Device DAX: direct access device driver");
 MODULE_LICENSE("GPL v2");
 module_init(dax_init);
 module_exit(dax_exit);