dax: Allow dax_iomap_fault() to return pfn

For synchronous page fault dax_iomap_fault() will need to return PFN
which will then need to be inserted into page tables after fsync()
completes. Add necessary parameter to dax_iomap_fault().
Reviewed-by: NChristoph Hellwig <hch@lst.de>
Reviewed-by: NRoss Zwisler <ross.zwisler@linux.intel.com>
Signed-off-by: NJan Kara <jack@suse.cz>
Signed-off-by: NDan Williams <dan.j.williams@intel.com>

fs/dax.c

@@ -1079,7 +1079,7 @@ static int dax_fault_return(int error)
 	return VM_FAULT_SIGBUS;
 }
 
-static int dax_iomap_pte_fault(struct vm_fault *vmf,
+static int dax_iomap_pte_fault(struct vm_fault *vmf, pfn_t *pfnp,
 			       const struct iomap_ops *ops)
 {
 	struct vm_area_struct *vma = vmf->vma;
@@ -1280,7 +1280,7 @@ static int dax_pmd_load_hole(struct vm_fault *vmf, struct iomap *iomap,
 	return VM_FAULT_FALLBACK;
 }
 
-static int dax_iomap_pmd_fault(struct vm_fault *vmf,
+static int dax_iomap_pmd_fault(struct vm_fault *vmf, pfn_t *pfnp,
 			       const struct iomap_ops *ops)
 {
 	struct vm_area_struct *vma = vmf->vma;
@@ -1425,7 +1425,7 @@ static int dax_iomap_pmd_fault(struct vm_fault *vmf,
 	return result;
 }
 #else
-static int dax_iomap_pmd_fault(struct vm_fault *vmf,
+static int dax_iomap_pmd_fault(struct vm_fault *vmf, pfn_t *pfnp,
 			       const struct iomap_ops *ops)
 {
 	return VM_FAULT_FALLBACK;
@@ -1436,6 +1436,7 @@ static int dax_iomap_pmd_fault(struct vm_fault *vmf,
  * dax_iomap_fault - handle a page fault on a DAX file
  * @vmf: The description of the fault
  * @pe_size: Size of the page to fault in
+ * @pfnp: PFN to insert for synchronous faults if fsync is required
  * @ops: Iomap ops passed from the file system
  *
  * When a page fault occurs, filesystems may call this helper in
@@ -1444,13 +1445,13 @@ static int dax_iomap_pmd_fault(struct vm_fault *vmf,
  * successfully.
  */
 int dax_iomap_fault(struct vm_fault *vmf, enum page_entry_size pe_size,
-		    const struct iomap_ops *ops)
+		    pfn_t *pfnp, const struct iomap_ops *ops)
 {
 	switch (pe_size) {
 	case PE_SIZE_PTE:
-		return dax_iomap_pte_fault(vmf, ops);
+		return dax_iomap_pte_fault(vmf, pfnp, ops);
 	case PE_SIZE_PMD:
-		return dax_iomap_pmd_fault(vmf, ops);
+		return dax_iomap_pmd_fault(vmf, pfnp, ops);
 	default:
 		return VM_FAULT_FALLBACK;
 	}

fs/ext2/file.c

@@ -99,7 +99,7 @@ static int ext2_dax_fault(struct vm_fault *vmf)
 	}
 	down_read(&ei->dax_sem);
 
-	ret = dax_iomap_fault(vmf, PE_SIZE_PTE, &ext2_iomap_ops);
+	ret = dax_iomap_fault(vmf, PE_SIZE_PTE, NULL, &ext2_iomap_ops);
 
 	up_read(&ei->dax_sem);
 	if (vmf->flags & FAULT_FLAG_WRITE)

fs/ext4/file.c

@@ -306,7 +306,7 @@ static int ext4_dax_huge_fault(struct vm_fault *vmf,
 		down_read(&EXT4_I(inode)->i_mmap_sem);
 	}
 	if (!IS_ERR(handle))
-		result = dax_iomap_fault(vmf, pe_size, &ext4_iomap_ops);
+		result = dax_iomap_fault(vmf, pe_size, NULL, &ext4_iomap_ops);
 	else
 		result = VM_FAULT_SIGBUS;
 	if (write) {

fs/xfs/xfs_file.c

@@ -1040,7 +1040,7 @@ __xfs_filemap_fault(
 
 	xfs_ilock(XFS_I(inode), XFS_MMAPLOCK_SHARED);
 	if (IS_DAX(inode)) {
-		ret = dax_iomap_fault(vmf, pe_size, &xfs_iomap_ops);
+		ret = dax_iomap_fault(vmf, pe_size, NULL, &xfs_iomap_ops);
 	} else {
 		if (write_fault)
 			ret = iomap_page_mkwrite(vmf, &xfs_iomap_ops);
@@ -1111,7 +1111,7 @@ xfs_filemap_pfn_mkwrite(
 	if (vmf->pgoff >= size)
 		ret = VM_FAULT_SIGBUS;
 	else if (IS_DAX(inode))
-		ret = dax_iomap_fault(vmf, PE_SIZE_PTE, &xfs_iomap_ops);
+		ret = dax_iomap_fault(vmf, PE_SIZE_PTE, NULL, &xfs_iomap_ops);
 	xfs_iunlock(ip, XFS_MMAPLOCK_SHARED);
 	sb_end_pagefault(inode->i_sb);
 	return ret;

include/linux/dax.h

@@ -95,7 +95,7 @@ bool dax_write_cache_enabled(struct dax_device *dax_dev);
 ssize_t dax_iomap_rw(struct kiocb *iocb, struct iov_iter *iter,
 		const struct iomap_ops *ops);
 int dax_iomap_fault(struct vm_fault *vmf, enum page_entry_size pe_size,
-		    const struct iomap_ops *ops);
+		    pfn_t *pfnp, const struct iomap_ops *ops);
 int dax_delete_mapping_entry(struct address_space *mapping, pgoff_t index);
 int dax_invalidate_mapping_entry_sync(struct address_space *mapping,
 				      pgoff_t index);