[RFC PATCH 3/3] ovl: implement stacked mmap for shared map

[Chengguang Xu <cgxu519@xxxxxxxxxxxx>]

Implement stacked mmap for shared map to keep data
consistency.

Signed-off-by: Chengguang Xu <cgxu519@xxxxxxxxxxxx>
---
 fs/overlayfs/file.c | 120 +++++++++++++++++++++++++++++++++++++++++---
 1 file changed, 114 insertions(+), 6 deletions(-)

diff --git a/fs/overlayfs/file.c b/fs/overlayfs/file.c
index 14ab5344a918..db5ab200d984 100644
--- a/fs/overlayfs/file.c
+++ b/fs/overlayfs/file.c
@@ -21,9 +21,17 @@ struct ovl_aio_req {
 	struct fd fd;
 };
 
+static vm_fault_t ovl_fault(struct vm_fault *vmf);
+static vm_fault_t ovl_page_mkwrite(struct vm_fault *vmf);
+
+static const struct vm_operations_struct ovl_vm_ops = {
+	.fault		= ovl_fault,
+	.page_mkwrite	= ovl_page_mkwrite,
+};
+
 struct ovl_file_entry {
 	struct file *realfile;
-	void *vm_ops;
+	const struct vm_operations_struct *vm_ops;
 };
 
 struct file *ovl_get_realfile(struct file *file)
@@ -40,14 +48,15 @@ void ovl_set_realfile(struct file *file, struct file *realfile)
 	ofe->realfile = realfile;
 }
 
-void *ovl_get_real_vmops(struct file *file)
+const struct vm_operations_struct *ovl_get_real_vmops(struct file *file)
 {
 	struct ovl_file_entry *ofe = file->private_data;
 
 	return ofe->vm_ops;
 }
 
-void ovl_set_real_vmops(struct file *file, void *vm_ops)
+void ovl_set_real_vmops(struct file *file,
+			const struct vm_operations_struct *vm_ops)
 {
 	struct ovl_file_entry *ofe = file->private_data;
 
@@ -493,11 +502,104 @@ static int ovl_fsync(struct file *file, loff_t start, loff_t end, int datasync)
 	return ret;
 }
 
+vm_fault_t ovl_fault(struct vm_fault *vmf)
+{
+	struct vm_area_struct *vma = vmf->vma;
+	struct file *file = vma->vm_file;
+	struct file *realfile;
+	struct file *fpin, *tmp;
+	struct inode *inode = file_inode(file);
+	struct inode *realinode;
+	const struct cred *old_cred;
+	bool retry_allowed;
+	vm_fault_t ret;
+	int err = 0;
+
+	if (fault_flag_check(vmf, FAULT_FLAG_TRIED)) {
+		realfile = ovl_get_realfile(file);
+
+		if (!ovl_has_upperdata(inode) ||
+		    realfile->f_inode != ovl_inode_upper(inode) ||
+		    !realfile->f_op->mmap)
+			return VM_FAULT_SIGBUS;
+
+		if (!ovl_get_real_vmops(file)) {
+			old_cred = ovl_override_creds(inode->i_sb);
+			err = call_mmap(realfile, vma);
+			revert_creds(old_cred);
+
+			vma->vm_file = file;
+			if (err) {
+				vma->vm_ops = &ovl_vm_ops;
+				return VM_FAULT_SIGBUS;
+			}
+			ovl_set_real_vmops(file, vma->vm_ops);
+			vma->vm_ops = &ovl_vm_ops;
+		}
+
+		retry_allowed = fault_flag_check(vmf, FAULT_FLAG_ALLOW_RETRY);
+		if (retry_allowed)
+			vma->vm_flags &= ~FAULT_FLAG_ALLOW_RETRY;
+		vma->vm_file = realfile;
+		ret = ovl_get_real_vmops(file)->fault(vmf);
+		vma->vm_file = file;
+		if (retry_allowed)
+			vma->vm_flags |= FAULT_FLAG_ALLOW_RETRY;
+		return ret;
+
+	} else {
+		fpin = maybe_unlock_mmap_for_io(vmf, NULL);
+		if (!fpin)
+			return VM_FAULT_SIGBUS;
+
+		ret = VM_FAULT_RETRY;
+		if (!ovl_has_upperdata(inode)) {
+			err = ovl_copy_up_with_data(file->f_path.dentry);
+			if (err)
+				goto out;
+		}
+
+		realinode = ovl_inode_realdata(inode);
+		realfile = ovl_open_realfile(file, realinode);
+		if (IS_ERR(realfile))
+			goto out;
+
+		tmp = ovl_get_realfile(file);
+		ovl_set_realfile(file, realfile);
+		fput(tmp);
+
+out:
+		fput(fpin);
+		return ret;
+	}
+}
+
+static vm_fault_t ovl_page_mkwrite(struct vm_fault *vmf)
+{
+	struct vm_area_struct *vma = vmf->vma;
+	struct file *file = vma->vm_file;
+	struct file *realfile;
+	struct inode *inode = file_inode(file);
+	vm_fault_t ret;
+
+	realfile = ovl_get_realfile(file);
+
+	sb_start_pagefault(inode->i_sb);
+	file_update_time(file);
+
+	vma->vm_file = realfile;
+	ret = ovl_get_real_vmops(file)->page_mkwrite(vmf);
+	vma->vm_file = file;
+
+	sb_end_pagefault(inode->i_sb);
+	return ret;
+}
+
 static int ovl_mmap(struct file *file, struct vm_area_struct *vma)
 {
 	struct file *realfile = ovl_get_realfile(file);
 	const struct cred *old_cred;
-	int ret;
+	int ret = 0;
 
 	if (!realfile->f_op->mmap)
 		return -ENODEV;
@@ -505,6 +607,13 @@ static int ovl_mmap(struct file *file, struct vm_area_struct *vma)
 	if (WARN_ON(file != vma->vm_file))
 		return -EIO;
 
+	if (!ovl_has_upperdata(file_inode(file)) &&
+	    (vma->vm_flags & (VM_SHARED|VM_MAYSHARE))) {
+		vma->vm_ops = &ovl_vm_ops;
+		ovl_file_accessed(file);
+		return 0;
+	}
+
 	vma->vm_file = get_file(realfile);
 
 	old_cred = ovl_override_creds(file_inode(file)->i_sb);
@@ -517,10 +626,9 @@ static int ovl_mmap(struct file *file, struct vm_area_struct *vma)
 	} else {
 		/* Drop reference count from previous vm_file value */
 		fput(file);
+		ovl_file_accessed(file);
 	}
 
-	ovl_file_accessed(file);
-
 	return ret;
 }
 
-- 
2.20.1