1 files changed, 78 insertions, 57 deletions

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)