From 2232c6382a453db73d2e723df1b52030066e135e Mon Sep 17 00:00:00 2001
From: Dan Williams <dan.j.williams@intel.com>
Date: Fri, 13 Jul 2018 21:49:40 -0700
Subject: [PATCH] device-dax: Enable page_mapping()
Git-commit: 2232c6382a453db73d2e723df1b52030066e135e
Patch-mainline: v4.19-rc1
References: bsc#1107783

In support of enabling memory_failure() handling for device-dax
mappings, set the ->mapping association of pages backing device-dax
mappings. The rmap implementation requires page_mapping() to return the
address_space hosting the vmas that map the page.

The ->mapping pointer is never cleared. There is no possibility for the
page to become associated with another address_space while the device is
enabled. When the device is disabled the 'struct page' array for the
device is destroyed / later reinitialized to zero.

Reviewed-by: Jan Kara <jack@suse.cz>
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
Signed-off-by: Dave Jiang <dave.jiang@intel.com>
Acked-by: Jan Kara <jack@suse.cz>

---
 drivers/dax/device.c |   59 ++++++++++++++++++++++++++++++++++++---------------
 1 file changed, 42 insertions(+), 17 deletions(-)

--- a/drivers/dax/device.c
+++ b/drivers/dax/device.c
@@ -243,13 +243,13 @@ __weak phys_addr_t dax_pgoff_to_phys(str
 	return -1;
 }
 
-static int __dev_dax_pte_fault(struct dev_dax *dev_dax, struct vm_fault *vmf)
+static int __dev_dax_pte_fault(struct dev_dax *dev_dax, struct vm_fault *vmf,
+			       pfn_t *pfn)
 {
 	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__))
@@ -272,9 +272,9 @@ static int __dev_dax_pte_fault(struct de
 		return VM_FAULT_SIGBUS;
 	}
 
-	pfn = phys_to_pfn_t(phys, dax_region->pfn_flags);
+	*pfn = phys_to_pfn_t(phys, dax_region->pfn_flags);
 
-	rc = vm_insert_mixed(vmf->vma, vmf->address, pfn);
+	rc = vm_insert_mixed(vmf->vma, vmf->address, *pfn);
 
 	if (rc == -ENOMEM)
 		return VM_FAULT_OOM;
@@ -284,14 +284,14 @@ static int __dev_dax_pte_fault(struct de
 	return VM_FAULT_NOPAGE;
 }
 
-static int __dev_dax_pmd_fault(struct dev_dax *dev_dax, struct vm_fault *vmf)
+static int __dev_dax_pmd_fault(struct dev_dax *dev_dax, struct vm_fault *vmf,
+			       pfn_t *pfn)
 {
 	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__))
@@ -328,21 +328,21 @@ static int __dev_dax_pmd_fault(struct de
 		return VM_FAULT_SIGBUS;
 	}
 
-	pfn = phys_to_pfn_t(phys, dax_region->pfn_flags);
+	*pfn = phys_to_pfn_t(phys, dax_region->pfn_flags);
 
-	return vmf_insert_pfn_pmd(vmf->vma, vmf->address, vmf->pmd, pfn,
+	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)
+static int __dev_dax_pud_fault(struct dev_dax *dev_dax, struct vm_fault *vmf,
+			       pfn_t *pfn)
 {
 	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;
 
 
@@ -380,13 +380,14 @@ static int __dev_dax_pud_fault(struct de
 		return VM_FAULT_SIGBUS;
 	}
 
-	pfn = phys_to_pfn_t(phys, dax_region->pfn_flags);
+	*pfn = phys_to_pfn_t(phys, dax_region->pfn_flags);
 
-	return vmf_insert_pfn_pud(vmf->vma, vmf->address, vmf->pud, pfn,
+	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)
+static int __dev_dax_pud_fault(struct dev_dax *dev_dax, struct vm_fault *vmf,
+			       pfn_t *pfn)
 {
 	return VM_FAULT_FALLBACK;
 }
@@ -395,8 +396,10 @@ static int __dev_dax_pud_fault(struct de
 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;
+	unsigned long fault_size;
+	int rc, id;
+	pfn_t pfn;
 	struct dev_dax *dev_dax = filp->private_data;
 
 	dev_dbg(&dev_dax->dev, "%s: %s: %s (%#lx - %#lx) size = %d\n", __func__,
@@ -407,17 +410,39 @@ static int dev_dax_huge_fault(struct vm_
 	id = dax_read_lock();
 	switch (pe_size) {
 	case PE_SIZE_PTE:
-		rc = __dev_dax_pte_fault(dev_dax, vmf);
+		fault_size = PAGE_SIZE;
+		rc = __dev_dax_pte_fault(dev_dax, vmf, &pfn);
 		break;
 	case PE_SIZE_PMD:
-		rc = __dev_dax_pmd_fault(dev_dax, vmf);
+		fault_size = PMD_SIZE;
+		rc = __dev_dax_pmd_fault(dev_dax, vmf, &pfn);
 		break;
 	case PE_SIZE_PUD:
-		rc = __dev_dax_pud_fault(dev_dax, vmf);
+		fault_size = PUD_SIZE;
+		rc = __dev_dax_pud_fault(dev_dax, vmf, &pfn);
 		break;
 	default:
 		rc = VM_FAULT_SIGBUS;
 	}
+
+	if (rc == VM_FAULT_NOPAGE) {
+		unsigned long i;
+
+		/*
+		 * 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.
+		 */
+		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;
+		}
+	}
 	dax_read_unlock(id);
 
 	return rc;