fs: Add VirtualBox guest shared folder (vboxsf) support

VirtualBox hosts can share folders with guests, this commit adds a
VFS driver implementing the Linux-guest side of this, allowing folders
exported by the host to be mounted under Linux.

This driver depends on the guest <-> host IPC functions exported by
the vboxguest driver.

Acked-by: Christoph Hellwig <hch@infradead.org>
Signed-off-by: Hans de Goede <hdegoede@redhat.com>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>

9 files changed, 3272 insertions, 0 deletions

diff --git a/fs/vboxsf/Kconfig b/fs/vboxsf/Kconfig
new file mode 100644
index 000000000000..b84586ae08b3
--- /dev/null
+++ b/fs/vboxsf/Kconfig
@@ -0,0 +1,10 @@
+config VBOXSF_FS
+	tristate "VirtualBox guest shared folder (vboxsf) support"
+	depends on X86 && VBOXGUEST
+	select NLS
+	help
+	  VirtualBox hosts can share folders with guests, this driver
+	  implements the Linux-guest side of this allowing folders exported
+	  by the host to be mounted under Linux.
+
+	  If you want to use shared folders in VirtualBox guests, answer Y or M.
diff --git a/fs/vboxsf/Makefile b/fs/vboxsf/Makefile
new file mode 100644
index 000000000000..9e4328e79623
--- /dev/null
+++ b/fs/vboxsf/Makefile
@@ -0,0 +1,5 @@
+# SPDX-License-Identifier: MIT
+
+obj-$(CONFIG_VBOXSF_FS) += vboxsf.o
+
+vboxsf-y := dir.o file.o utils.o vboxsf_wrappers.o super.o
diff --git a/fs/vboxsf/dir.c b/fs/vboxsf/dir.c
new file mode 100644
index 000000000000..dd147b490982
--- /dev/null
+++ b/fs/vboxsf/dir.c
@@ -0,0 +1,427 @@
+// SPDX-License-Identifier: MIT
+/*
+ * VirtualBox Guest Shared Folders support: Directory inode and file operations
+ *
+ * Copyright (C) 2006-2018 Oracle Corporation
+ */
+
+#include <linux/namei.h>
+#include <linux/vbox_utils.h>
+#include "vfsmod.h"
+
+static int vboxsf_dir_open(struct inode *inode, struct file *file)
+{
+	struct vboxsf_sbi *sbi = VBOXSF_SBI(inode->i_sb);
+	struct shfl_createparms params = {};
+	struct vboxsf_dir_info *sf_d;
+	int err;
+
+	sf_d = vboxsf_dir_info_alloc();
+	if (!sf_d)
+		return -ENOMEM;
+
+	params.handle = SHFL_HANDLE_NIL;
+	params.create_flags = SHFL_CF_DIRECTORY | SHFL_CF_ACT_OPEN_IF_EXISTS |
+			      SHFL_CF_ACT_FAIL_IF_NEW | SHFL_CF_ACCESS_READ;
+
+	err = vboxsf_create_at_dentry(file_dentry(file), &params);
+	if (err)
+		goto err_free_dir_info;
+
+	if (params.result != SHFL_FILE_EXISTS) {
+		err = -ENOENT;
+		goto err_close;
+	}
+
+	err = vboxsf_dir_read_all(sbi, sf_d, params.handle);
+	if (err)
+		goto err_close;
+
+	vboxsf_close(sbi->root, params.handle);
+	file->private_data = sf_d;
+	return 0;
+
+err_close:
+	vboxsf_close(sbi->root, params.handle);
+err_free_dir_info:
+	vboxsf_dir_info_free(sf_d);
+	return err;
+}
+
+static int vboxsf_dir_release(struct inode *inode, struct file *file)
+{
+	if (file->private_data)
+		vboxsf_dir_info_free(file->private_data);
+
+	return 0;
+}
+
+static unsigned int vboxsf_get_d_type(u32 mode)
+{
+	unsigned int d_type;
+
+	switch (mode & SHFL_TYPE_MASK) {
+	case SHFL_TYPE_FIFO:
+		d_type = DT_FIFO;
+		break;
+	case SHFL_TYPE_DEV_CHAR:
+		d_type = DT_CHR;
+		break;
+	case SHFL_TYPE_DIRECTORY:
+		d_type = DT_DIR;
+		break;
+	case SHFL_TYPE_DEV_BLOCK:
+		d_type = DT_BLK;
+		break;
+	case SHFL_TYPE_FILE:
+		d_type = DT_REG;
+		break;
+	case SHFL_TYPE_SYMLINK:
+		d_type = DT_LNK;
+		break;
+	case SHFL_TYPE_SOCKET:
+		d_type = DT_SOCK;
+		break;
+	case SHFL_TYPE_WHITEOUT:
+		d_type = DT_WHT;
+		break;
+	default:
+		d_type = DT_UNKNOWN;
+		break;
+	}
+	return d_type;
+}
+
+static bool vboxsf_dir_emit(struct file *dir, struct dir_context *ctx)
+{
+	struct vboxsf_sbi *sbi = VBOXSF_SBI(file_inode(dir)->i_sb);
+	struct vboxsf_dir_info *sf_d = dir->private_data;
+	struct shfl_dirinfo *info;
+	struct vboxsf_dir_buf *b;
+	unsigned int d_type;
+	loff_t i, cur = 0;
+	ino_t fake_ino;
+	void *end;
+	int err;
+
+	list_for_each_entry(b, &sf_d->info_list, head) {
+try_next_entry:
+		if (ctx->pos >= cur + b->entries) {
+			cur += b->entries;
+			continue;
+		}
+
+		/*
+		 * Note the vboxsf_dir_info objects we are iterating over here
+		 * are variable sized, so the info pointer may end up being
+		 * unaligned. This is how we get the data from the host.
+		 * Since vboxsf is only supported on x86 machines this is not
+		 * a problem.
+		 */
+		for (i = 0, info = b->buf; i < ctx->pos - cur; i++) {
+			end = &info->name.string.utf8[info->name.size];
+			/* Only happens if the host gives us corrupt data */
+			if (WARN_ON(end > (b->buf + b->used)))
+				return false;
+			info = end;
+		}
+
+		end = &info->name.string.utf8[info->name.size];
+		if (WARN_ON(end > (b->buf + b->used)))
+			return false;
+
+		/* Info now points to the right entry, emit it. */
+		d_type = vboxsf_get_d_type(info->info.attr.mode);
+
+		/*
+		 * On 32 bit systems pos is 64 signed, while ino is 32 bit
+		 * unsigned so fake_ino may overflow, check for this.
+		 */
+		if ((ino_t)(ctx->pos + 1) != (u64)(ctx->pos + 1)) {
+			vbg_err("vboxsf: fake ino overflow, truncating dir\n");
+			return false;
+		}
+		fake_ino = ctx->pos + 1;
+
+		if (sbi->nls) {
+			char d_name[NAME_MAX];
+
+			err = vboxsf_nlscpy(sbi, d_name, NAME_MAX,
+					    info->name.string.utf8,
+					    info->name.length);
+			if (err) {
+				/* skip erroneous entry and proceed */
+				ctx->pos += 1;
+				goto try_next_entry;
+			}
+
+			return dir_emit(ctx, d_name, strlen(d_name),
+					fake_ino, d_type);
+		}
+
+		return dir_emit(ctx, info->name.string.utf8, info->name.length,
+				fake_ino, d_type);
+	}
+
+	return false;
+}
+
+static int vboxsf_dir_iterate(struct file *dir, struct dir_context *ctx)
+{
+	bool emitted;
+
+	do {
+		emitted = vboxsf_dir_emit(dir, ctx);
+		if (emitted)
+			ctx->pos += 1;
+	} while (emitted);
+
+	return 0;
+}
+
+const struct file_operations vboxsf_dir_fops = {
+	.open = vboxsf_dir_open,
+	.iterate = vboxsf_dir_iterate,
+	.release = vboxsf_dir_release,
+	.read = generic_read_dir,
+	.llseek = generic_file_llseek,
+};
+
+/*
+ * This is called during name resolution/lookup to check if the @dentry in
+ * the cache is still valid. the job is handled by vboxsf_inode_revalidate.
+ */
+static int vboxsf_dentry_revalidate(struct dentry *dentry, unsigned int flags)
+{
+	if (flags & LOOKUP_RCU)
+		return -ECHILD;
+
+	if (d_really_is_positive(dentry))
+		return vboxsf_inode_revalidate(dentry) == 0;
+	else
+		return vboxsf_stat_dentry(dentry, NULL) == -ENOENT;
+}
+
+const struct dentry_operations vboxsf_dentry_ops = {
+	.d_revalidate = vboxsf_dentry_revalidate
+};
+
+/* iops */
+
+static struct dentry *vboxsf_dir_lookup(struct inode *parent,
+					struct dentry *dentry,
+					unsigned int flags)
+{
+	struct vboxsf_sbi *sbi = VBOXSF_SBI(parent->i_sb);
+	struct shfl_fsobjinfo fsinfo;
+	struct inode *inode;
+	int err;
+
+	dentry->d_time = jiffies;
+
+	err = vboxsf_stat_dentry(dentry, &fsinfo);
+	if (err) {
+		inode = (err == -ENOENT) ? NULL : ERR_PTR(err);
+	} else {
+		inode = vboxsf_new_inode(parent->i_sb);
+		if (!IS_ERR(inode))
+			vboxsf_init_inode(sbi, inode, &fsinfo);
+	}
+
+	return d_splice_alias(inode, dentry);
+}
+
+static int vboxsf_dir_instantiate(struct inode *parent, struct dentry *dentry,
+				  struct shfl_fsobjinfo *info)
+{
+	struct vboxsf_sbi *sbi = VBOXSF_SBI(parent->i_sb);
+	struct vboxsf_inode *sf_i;
+	struct inode *inode;
+
+	inode = vboxsf_new_inode(parent->i_sb);
+	if (IS_ERR(inode))
+		return PTR_ERR(inode);
+
+	sf_i = VBOXSF_I(inode);
+	/* The host may have given us different attr then requested */
+	sf_i->force_restat = 1;
+	vboxsf_init_inode(sbi, inode, info);
+
+	d_instantiate(dentry, inode);
+
+	return 0;
+}
+
+static int vboxsf_dir_create(struct inode *parent, struct dentry *dentry,
+			     umode_t mode, int is_dir)
+{
+	struct vboxsf_inode *sf_parent_i = VBOXSF_I(parent);
+	struct vboxsf_sbi *sbi = VBOXSF_SBI(parent->i_sb);
+	struct shfl_createparms params = {};
+	int err;
+
+	params.handle = SHFL_HANDLE_NIL;
+	params.create_flags = SHFL_CF_ACT_CREATE_IF_NEW |
+			      SHFL_CF_ACT_FAIL_IF_EXISTS |
+			      SHFL_CF_ACCESS_READWRITE |
+			      (is_dir ? SHFL_CF_DIRECTORY : 0);
+	params.info.attr.mode = (mode & 0777) |
+				(is_dir ? SHFL_TYPE_DIRECTORY : SHFL_TYPE_FILE);
+	params.info.attr.additional = SHFLFSOBJATTRADD_NOTHING;
+
+	err = vboxsf_create_at_dentry(dentry, &params);
+	if (err)
+		return err;
+
+	if (params.result != SHFL_FILE_CREATED)
+		return -EPERM;
+
+	vboxsf_close(sbi->root, params.handle);
+
+	err = vboxsf_dir_instantiate(parent, dentry, &params.info);
+	if (err)
+		return err;
+
+	/* parent directory access/change time changed */
+	sf_parent_i->force_restat = 1;
+
+	return 0;
+}
+
+static int vboxsf_dir_mkfile(struct inode *parent, struct dentry *dentry,
+			     umode_t mode, bool excl)
+{
+	return vboxsf_dir_create(parent, dentry, mode, 0);
+}
+
+static int vboxsf_dir_mkdir(struct inode *parent, struct dentry *dentry,
+			    umode_t mode)
+{
+	return vboxsf_dir_create(parent, dentry, mode, 1);
+}
+
+static int vboxsf_dir_unlink(struct inode *parent, struct dentry *dentry)
+{
+	struct vboxsf_sbi *sbi = VBOXSF_SBI(parent->i_sb);
+	struct vboxsf_inode *sf_parent_i = VBOXSF_I(parent);
+	struct inode *inode = d_inode(dentry);
+	struct shfl_string *path;
+	u32 flags;
+	int err;
+
+	if (S_ISDIR(inode->i_mode))
+		flags = SHFL_REMOVE_DIR;
+	else
+		flags = SHFL_REMOVE_FILE;
+
+	if (S_ISLNK(inode->i_mode))
+		flags |= SHFL_REMOVE_SYMLINK;
+
+	path = vboxsf_path_from_dentry(sbi, dentry);
+	if (IS_ERR(path))
+		return PTR_ERR(path);
+
+	err = vboxsf_remove(sbi->root, path, flags);
+	__putname(path);
+	if (err)
+		return err;
+
+	/* parent directory access/change time changed */
+	sf_parent_i->force_restat = 1;
+
+	return 0;
+}
+
+static int vboxsf_dir_rename(struct inode *old_parent,
+			     struct dentry *old_dentry,
+			     struct inode *new_parent,
+			     struct dentry *new_dentry,
+			     unsigned int flags)
+{
+	struct vboxsf_sbi *sbi = VBOXSF_SBI(old_parent->i_sb);
+	struct vboxsf_inode *sf_old_parent_i = VBOXSF_I(old_parent);
+	struct vboxsf_inode *sf_new_parent_i = VBOXSF_I(new_parent);
+	u32 shfl_flags = SHFL_RENAME_FILE | SHFL_RENAME_REPLACE_IF_EXISTS;
+	struct shfl_string *old_path, *new_path;
+	int err;
+
+	if (flags)
+		return -EINVAL;
+
+	old_path = vboxsf_path_from_dentry(sbi, old_dentry);
+	if (IS_ERR(old_path))
+		return PTR_ERR(old_path);
+
+	new_path = vboxsf_path_from_dentry(sbi, new_dentry);
+	if (IS_ERR(new_path)) {
+		err = PTR_ERR(new_path);
+		goto err_put_old_path;
+	}
+
+	if (d_inode(old_dentry)->i_mode & S_IFDIR)
+		shfl_flags = 0;
+
+	err = vboxsf_rename(sbi->root, old_path, new_path, shfl_flags);
+	if (err == 0) {
+		/* parent directories access/change time changed */
+		sf_new_parent_i->force_restat = 1;
+		sf_old_parent_i->force_restat = 1;
+	}
+
+	__putname(new_path);
+err_put_old_path:
+	__putname(old_path);
+	return err;
+}
+
+static int vboxsf_dir_symlink(struct inode *parent, struct dentry *dentry,
+			      const char *symname)
+{
+	struct vboxsf_inode *sf_parent_i = VBOXSF_I(parent);
+	struct vboxsf_sbi *sbi = VBOXSF_SBI(parent->i_sb);
+	int symname_size = strlen(symname) + 1;
+	struct shfl_string *path, *ssymname;
+	struct shfl_fsobjinfo info;
+	int err;
+
+	path = vboxsf_path_from_dentry(sbi, dentry);
+	if (IS_ERR(path))
+		return PTR_ERR(path);
+
+	ssymname = kmalloc(SHFLSTRING_HEADER_SIZE + symname_size, GFP_KERNEL);
+	if (!ssymname) {
+		__putname(path);
+		return -ENOMEM;
+	}
+	ssymname->length = symname_size - 1;
+	ssymname->size = symname_size;
+	memcpy(ssymname->string.utf8, symname, symname_size);
+
+	err = vboxsf_symlink(sbi->root, path, ssymname, &info);
+	kfree(ssymname);
+	__putname(path);
+	if (err) {
+		/* -EROFS means symlinks are note support -> -EPERM */
+		return (err == -EROFS) ? -EPERM : err;
+	}
+
+	err = vboxsf_dir_instantiate(parent, dentry, &info);
+	if (err)
+		return err;
+
+	/* parent directory access/change time changed */
+	sf_parent_i->force_restat = 1;
+	return 0;
+}
+
+const struct inode_operations vboxsf_dir_iops = {
+	.lookup  = vboxsf_dir_lookup,
+	.create  = vboxsf_dir_mkfile,
+	.mkdir   = vboxsf_dir_mkdir,
+	.rmdir   = vboxsf_dir_unlink,
+	.unlink  = vboxsf_dir_unlink,
+	.rename  = vboxsf_dir_rename,
+	.symlink = vboxsf_dir_symlink,
+	.getattr = vboxsf_getattr,
+	.setattr = vboxsf_setattr,
+};
diff --git a/fs/vboxsf/file.c b/fs/vboxsf/file.c
new file mode 100644
index 000000000000..c4ab5996d97a
--- /dev/null
+++ b/fs/vboxsf/file.c
@@ -0,0 +1,379 @@
+// SPDX-License-Identifier: MIT
+/*
+ * VirtualBox Guest Shared Folders support: Regular file inode and file ops.
+ *
+ * Copyright (C) 2006-2018 Oracle Corporation
+ */
+
+#include <linux/mm.h>
+#include <linux/page-flags.h>
+#include <linux/pagemap.h>
+#include <linux/highmem.h>
+#include <linux/sizes.h>
+#include "vfsmod.h"
+
+struct vboxsf_handle {
+	u64 handle;
+	u32 root;
+	u32 access_flags;
+	struct kref refcount;
+	struct list_head head;
+};
+
+static int vboxsf_file_open(struct inode *inode, struct file *file)
+{
+	struct vboxsf_inode *sf_i = VBOXSF_I(inode);
+	struct shfl_createparms params = {};
+	struct vboxsf_handle *sf_handle;
+	u32 access_flags = 0;
+	int err;
+
+	sf_handle = kmalloc(sizeof(*sf_handle), GFP_KERNEL);
+	if (!sf_handle)
+		return -ENOMEM;
+
+	/*
+	 * We check the value of params.handle afterwards to find out if
+	 * the call succeeded or failed, as the API does not seem to cleanly
+	 * distinguish error and informational messages.
+	 *
+	 * Furthermore, we must set params.handle to SHFL_HANDLE_NIL to
+	 * make the shared folders host service use our mode parameter.
+	 */
+	params.handle = SHFL_HANDLE_NIL;
+	if (file->f_flags & O_CREAT) {
+		params.create_flags |= SHFL_CF_ACT_CREATE_IF_NEW;
+		/*
+		 * We ignore O_EXCL, as the Linux kernel seems to call create
+		 * beforehand itself, so O_EXCL should always fail.
+		 */
+		if (file->f_flags & O_TRUNC)
+			params.create_flags |= SHFL_CF_ACT_OVERWRITE_IF_EXISTS;
+		else
+			params.create_flags |= SHFL_CF_ACT_OPEN_IF_EXISTS;
+	} else {
+		params.create_flags |= SHFL_CF_ACT_FAIL_IF_NEW;
+		if (file->f_flags & O_TRUNC)
+			params.create_flags |= SHFL_CF_ACT_OVERWRITE_IF_EXISTS;
+	}
+
+	switch (file->f_flags & O_ACCMODE) {
+	case O_RDONLY:
+		access_flags |= SHFL_CF_ACCESS_READ;
+		break;
+
+	case O_WRONLY:
+		access_flags |= SHFL_CF_ACCESS_WRITE;
+		break;
+
+	case O_RDWR:
+		access_flags |= SHFL_CF_ACCESS_READWRITE;
+		break;
+
+	default:
+		WARN_ON(1);
+	}
+
+	if (file->f_flags & O_APPEND)
+		access_flags |= SHFL_CF_ACCESS_APPEND;
+
+	params.create_flags |= access_flags;
+	params.info.attr.mode = inode->i_mode;
+
+	err = vboxsf_create_at_dentry(file_dentry(file), &params);
+	if (err == 0 && params.handle == SHFL_HANDLE_NIL)
+		err = (params.result == SHFL_FILE_EXISTS) ? -EEXIST : -ENOENT;
+	if (err) {
+		kfree(sf_handle);
+		return err;
+	}
+
+	/* the host may have given us different attr then requested */
+	sf_i->force_restat = 1;
+
+	/* init our handle struct and add it to the inode's handles list */
+	sf_handle->handle = params.handle;
+	sf_handle->root = VBOXSF_SBI(inode->i_sb)->root;
+	sf_handle->access_flags = access_flags;
+	kref_init(&sf_handle->refcount);
+
+	mutex_lock(&sf_i->handle_list_mutex);
+	list_add(&sf_handle->head, &sf_i->handle_list);
+	mutex_unlock(&sf_i->handle_list_mutex);
+
+	file->private_data = sf_handle;
+	return 0;
+}
+
+static void vboxsf_handle_release(struct kref *refcount)
+{
+	struct vboxsf_handle *sf_handle =
+		container_of(refcount, struct vboxsf_handle, refcount);
+
+	vboxsf_close(sf_handle->root, sf_handle->handle);
+	kfree(sf_handle);
+}
+
+static int vboxsf_file_release(struct inode *inode, struct file *file)
+{
+	struct vboxsf_inode *sf_i = VBOXSF_I(inode);
+	struct vboxsf_handle *sf_handle = file->private_data;
+
+	/*
+	 * When a file is closed on our (the guest) side, we want any subsequent
+	 * accesses done on the host side to see all changes done from our side.
+	 */
+	filemap_write_and_wait(inode->i_mapping);
+
+	mutex_lock(&sf_i->handle_list_mutex);
+	list_del(&sf_handle->head);
+	mutex_unlock(&sf_i->handle_list_mutex);
+
+	kref_put(&sf_handle->refcount, vboxsf_handle_release);
+	return 0;
+}
+
+/*
+ * Write back dirty pages now, because there may not be any suitable
+ * open files later
+ */
+static void vboxsf_vma_close(struct vm_area_struct *vma)
+{
+	filemap_write_and_wait(vma->vm_file->f_mapping);
+}
+
+static const struct vm_operations_struct vboxsf_file_vm_ops = {
+	.close		= vboxsf_vma_close,
+	.fault		= filemap_fault,
+	.map_pages	= filemap_map_pages,
+};
+
+static int vboxsf_file_mmap(struct file *file, struct vm_area_struct *vma)
+{
+	int err;
+
+	err = generic_file_mmap(file, vma);
+	if (!err)
+		vma->vm_ops = &vboxsf_file_vm_ops;
+
+	return err;
+}
+
+/*
+ * Note that since we are accessing files on the host's filesystem, files
+ * may always be changed underneath us by the host!
+ *
+ * The vboxsf API between the guest and the host does not offer any functions
+ * to deal with this. There is no inode-generation to check for changes, no
+ * events / callback on changes and no way to lock files.
+ *
+ * To avoid returning stale data when a file gets *opened* on our (the guest)
+ * side, we do a "stat" on the host side, then compare the mtime with the
+ * last known mtime and invalidate the page-cache if they differ.
+ * This is done from vboxsf_inode_revalidate().
+ *
+ * When reads are done through the read_iter fop, it is possible to do
+ * further cache revalidation then, there are 3 options to deal with this:
+ *
+ * 1)  Rely solely on the revalidation done at open time
+ * 2)  Do another "stat" and compare mtime again. Unfortunately the vboxsf
+ *     host API does not allow stat on handles, so we would need to use
+ *     file->f_path.dentry and the stat will then fail if the file was unlinked
+ *     or renamed (and there is no thing like NFS' silly-rename). So we get:
+ * 2a) "stat" and compare mtime, on stat failure invalidate the cache
+ * 2b) "stat" and compare mtime, on stat failure do nothing
+ * 3)  Simply always call invalidate_inode_pages2_range on the range of the read
+ *
+ * Currently we are keeping things KISS and using option 1. this allows
+ * directly using generic_file_read_iter without wrapping it.
+ *
+ * This means that only data written on the host side before open() on
+ * the guest side is guaranteed to be seen by the guest. If necessary
+ * we may provide other read-cache strategies in the future and make this
+ * configurable through a mount option.
+ */
+const struct file_operations vboxsf_reg_fops = {
+	.llseek = generic_file_llseek,
+	.read_iter = generic_file_read_iter,
+	.write_iter = generic_file_write_iter,
+	.mmap = vboxsf_file_mmap,
+	.open = vboxsf_file_open,
+	.release = vboxsf_file_release,
+	.fsync = noop_fsync,
+	.splice_read = generic_file_splice_read,
+};
+
+const struct inode_operations vboxsf_reg_iops = {
+	.getattr = vboxsf_getattr,
+	.setattr = vboxsf_setattr
+};
+
+static int vboxsf_readpage(struct file *file, struct page *page)
+{
+	struct vboxsf_handle *sf_handle = file->private_data;
+	loff_t off = page_offset(page);
+	u32 nread = PAGE_SIZE;
+	u8 *buf;
+	int err;
+
+	buf = kmap(page);
+
+	err = vboxsf_read(sf_handle->root, sf_handle->handle, off, &nread, buf);
+	if (err == 0) {
+		memset(&buf[nread], 0, PAGE_SIZE - nread);
+		flush_dcache_page(page);
+		SetPageUptodate(page);
+	} else {
+		SetPageError(page);
+	}
+
+	kunmap(page);
+	unlock_page(page);
+	return err;
+}
+
+static struct vboxsf_handle *vboxsf_get_write_handle(struct vboxsf_inode *sf_i)
+{
+	struct vboxsf_handle *h, *sf_handle = NULL;
+
+	mutex_lock(&sf_i->handle_list_mutex);
+	list_for_each_entry(h, &sf_i->handle_list, head) {
+		if (h->access_flags == SHFL_CF_ACCESS_WRITE ||
+		    h->access_flags == SHFL_CF_ACCESS_READWRITE) {
+			kref_get(&h->refcount);
+			sf_handle = h;
+			break;
+		}
+	}
+	mutex_unlock(&sf_i->handle_list_mutex);
+
+	return sf_handle;
+}
+
+static int vboxsf_writepage(struct page *page, struct writeback_control *wbc)
+{
+	struct inode *inode = page->mapping->host;
+	struct vboxsf_inode *sf_i = VBOXSF_I(inode);
+	struct vboxsf_handle *sf_handle;
+	loff_t off = page_offset(page);
+	loff_t size = i_size_read(inode);
+	u32 nwrite = PAGE_SIZE;
+	u8 *buf;
+	int err;
+
+	if (off + PAGE_SIZE > size)
+		nwrite = size & ~PAGE_MASK;
+
+	sf_handle = vboxsf_get_write_handle(sf_i);
+	if (!sf_handle)
+		return -EBADF;
+
+	buf = kmap(page);
+	err = vboxsf_write(sf_handle->root, sf_handle->handle,
+			   off, &nwrite, buf);
+	kunmap(page);
+
+	kref_put(&sf_handle->refcount, vboxsf_handle_release);
+
+	if (err == 0) {
+		ClearPageError(page);
+		/* mtime changed */
+		sf_i->force_restat = 1;
+	} else {
+		ClearPageUptodate(page);
+	}
+
+	unlock_page(page);
+	return err;
+}
+
+static int vboxsf_write_end(struct file *file, struct address_space *mapping,
+			    loff_t pos, unsigned int len, unsigned int copied,
+			    struct page *page, void *fsdata)
+{
+	struct inode *inode = mapping->host;
+	struct vboxsf_handle *sf_handle = file->private_data;
+	unsigned int from = pos & ~PAGE_MASK;
+	u32 nwritten = len;
+	u8 *buf;
+	int err;
+
+	/* zero the stale part of the page if we did a short copy */
+	if (!PageUptodate(page) && copied < len)
+		zero_user(page, from + copied, len - copied);
+
+	buf = kmap(page);
+	err = vboxsf_write(sf_handle->root, sf_handle->handle,
+			   pos, &nwritten, buf + from);
+	kunmap(page);
+
+	if (err) {
+		nwritten = 0;
+		goto out;
+	}
+
+	/* mtime changed */
+	VBOXSF_I(inode)->force_restat = 1;
+
+	if (!PageUptodate(page) && nwritten == PAGE_SIZE)
+		SetPageUptodate(page);
+
+	pos += nwritten;
+	if (pos > inode->i_size)
+		i_size_write(inode, pos);
+
+out:
+	unlock_page(page);
+	put_page(page);
+
+	return nwritten;
+}
+
+/*
+ * Note simple_write_begin does not read the page from disk on partial writes
+ * this is ok since vboxsf_write_end only writes the written parts of the
+ * page and it does not call SetPageUptodate for partial writes.
+ */
+const struct address_space_operations vboxsf_reg_aops = {
+	.readpage = vboxsf_readpage,
+	.writepage = vboxsf_writepage,
+	.set_page_dirty = __set_page_dirty_nobuffers,
+	.write_begin = simple_write_begin,
+	.write_end = vboxsf_write_end,
+};
+
+static const char *vboxsf_get_link(struct dentry *dentry, struct inode *inode,
+				   struct delayed_call *done)
+{
+	struct vboxsf_sbi *sbi = VBOXSF_SBI(inode->i_sb);
+	struct shfl_string *path;
+	char *link;
+	int err;
+
+	if (!dentry)
+		return ERR_PTR(-ECHILD);
+
+	path = vboxsf_path_from_dentry(sbi, dentry);
+	if (IS_ERR(path))
+		return ERR_CAST(path);
+
+	link = kzalloc(PATH_MAX, GFP_KERNEL);
+	if (!link) {
+		__putname(path);
+		return ERR_PTR(-ENOMEM);
+	}
+
+	err = vboxsf_readlink(sbi->root, path, PATH_MAX, link);
+	__putname(path);
+	if (err) {
+		kfree(link);
+		return ERR_PTR(err);
+	}
+
+	set_delayed_call(done, kfree_link, link);
+	return link;
+}
+
+const struct inode_operations vboxsf_lnk_iops = {
+	.get_link = vboxsf_get_link
+};
diff --git a/fs/vboxsf/shfl_hostintf.h b/fs/vboxsf/shfl_hostintf.h
new file mode 100644
index 000000000000..aca829062c12
--- /dev/null
+++ b/fs/vboxsf/shfl_hostintf.h
@@ -0,0 +1,901 @@
+/* SPDX-License-Identifier: MIT */
+/*
+ * VirtualBox Shared Folders: host interface definition.
+ *
+ * Copyright (C) 2006-2018 Oracle Corporation
+ */
+
+#ifndef SHFL_HOSTINTF_H
+#define SHFL_HOSTINTF_H
+
+#include <linux/vbox_vmmdev_types.h>
+
+/* The max in/out buffer size for a FN_READ or FN_WRITE call */
+#define SHFL_MAX_RW_COUNT           (16 * SZ_1M)
+
+/*
+ * Structures shared between guest and the service
+ * can be relocated and use offsets to point to variable
+ * length parts.
+ *
+ * Shared folders protocol works with handles.
+ * Before doing any action on a file system object,
+ * one have to obtain the object handle via a SHFL_FN_CREATE
+ * request. A handle must be closed with SHFL_FN_CLOSE.
+ */
+
+enum {
+	SHFL_FN_QUERY_MAPPINGS = 1,	/* Query mappings changes. */
+	SHFL_FN_QUERY_MAP_NAME = 2,	/* Query map name. */
+	SHFL_FN_CREATE = 3,		/* Open/create object. */
+	SHFL_FN_CLOSE = 4,		/* Close object handle. */
+	SHFL_FN_READ = 5,		/* Read object content. */
+	SHFL_FN_WRITE = 6,		/* Write new object content. */
+	SHFL_FN_LOCK = 7,		/* Lock/unlock a range in the object. */
+	SHFL_FN_LIST = 8,		/* List object content. */
+	SHFL_FN_INFORMATION = 9,	/* Query/set object information. */
+	/* Note function number 10 is not used! */
+	SHFL_FN_REMOVE = 11,		/* Remove object */
+	SHFL_FN_MAP_FOLDER_OLD = 12,	/* Map folder (legacy) */
+	SHFL_FN_UNMAP_FOLDER = 13,	/* Unmap folder */
+	SHFL_FN_RENAME = 14,		/* Rename object */
+	SHFL_FN_FLUSH = 15,		/* Flush file */
+	SHFL_FN_SET_UTF8 = 16,		/* Select UTF8 filename encoding */
+	SHFL_FN_MAP_FOLDER = 17,	/* Map folder */
+	SHFL_FN_READLINK = 18,		/* Read symlink dest (as of VBox 4.0) */
+	SHFL_FN_SYMLINK = 19,		/* Create symlink (as of VBox 4.0) */
+	SHFL_FN_SET_SYMLINKS = 20,	/* Ask host to show symlinks (4.0+) */
+};
+
+/* Root handles for a mapping are of type u32, Root handles are unique. */
+#define SHFL_ROOT_NIL		UINT_MAX
+
+/* Shared folders handle for an opened object are of type u64. */
+#define SHFL_HANDLE_NIL		ULLONG_MAX
+
+/* Hardcoded maximum length (in chars) of a shared folder name. */
+#define SHFL_MAX_LEN         (256)
+/* Hardcoded maximum number of shared folder mapping available to the guest. */
+#define SHFL_MAX_MAPPINGS    (64)
+
+/** Shared folder string buffer structure. */
+struct shfl_string {
+	/** Allocated size of the string member in bytes. */
+	u16 size;
+
+	/** Length of string without trailing nul in bytes. */
+	u16 length;
+
+	/** UTF-8 or UTF-16 string. Nul terminated. */
+	union {
+		u8 utf8[2];
+		u16 utf16[1];
+		u16 ucs2[1]; /* misnomer, use utf16. */
+	} string;
+};
+VMMDEV_ASSERT_SIZE(shfl_string, 6);
+
+/* The size of shfl_string w/o the string part. */
+#define SHFLSTRING_HEADER_SIZE  4
+
+/* Calculate size of the string. */
+static inline u32 shfl_string_buf_size(const struct shfl_string *string)
+{
+	return string ? SHFLSTRING_HEADER_SIZE + string->size : 0;
+}
+
+/* Set user id on execution (S_ISUID). */
+#define SHFL_UNIX_ISUID             0004000U
+/* Set group id on execution (S_ISGID). */
+#define SHFL_UNIX_ISGID             0002000U
+/* Sticky bit (S_ISVTX / S_ISTXT). */
+#define SHFL_UNIX_ISTXT             0001000U
+
+/* Owner readable (S_IRUSR). */
+#define SHFL_UNIX_IRUSR             0000400U
+/* Owner writable (S_IWUSR). */
+#define SHFL_UNIX_IWUSR             0000200U
+/* Owner executable (S_IXUSR). */
+#define SHFL_UNIX_IXUSR             0000100U
+
+/* Group readable (S_IRGRP). */
+#define SHFL_UNIX_IRGRP             0000040U
+/* Group writable (S_IWGRP). */
+#define SHFL_UNIX_IWGRP             0000020U
+/* Group executable (S_IXGRP). */
+#define SHFL_UNIX_IXGRP             0000010U
+
+/* Other readable (S_IROTH). */
+#define SHFL_UNIX_IROTH             0000004U
+/* Other writable (S_IWOTH). */
+#define SHFL_UNIX_IWOTH             0000002U
+/* Other executable (S_IXOTH). */
+#define SHFL_UNIX_IXOTH             0000001U
+
+/* Named pipe (fifo) (S_IFIFO). */
+#define SHFL_TYPE_FIFO              0010000U
+/* Character device (S_IFCHR). */
+#define SHFL_TYPE_DEV_CHAR          0020000U
+/* Directory (S_IFDIR). */
+#define SHFL_TYPE_DIRECTORY         0040000U
+/* Block device (S_IFBLK). */
+#define SHFL_TYPE_DEV_BLOCK         0060000U
+/* Regular file (S_IFREG). */
+#define SHFL_TYPE_FILE              0100000U
+/* Symbolic link (S_IFLNK). */
+#define SHFL_TYPE_SYMLINK           0120000U
+/* Socket (S_IFSOCK). */
+#define SHFL_TYPE_SOCKET            0140000U
+/* Whiteout (S_IFWHT). */
+#define SHFL_TYPE_WHITEOUT          0160000U
+/* Type mask (S_IFMT). */
+#define SHFL_TYPE_MASK              0170000U
+
+/* Checks the mode flags indicate a directory (S_ISDIR). */
+#define SHFL_IS_DIRECTORY(m)   (((m) & SHFL_TYPE_MASK) == SHFL_TYPE_DIRECTORY)
+/* Checks the mode flags indicate a symbolic link (S_ISLNK). */
+#define SHFL_IS_SYMLINK(m)     (((m) & SHFL_TYPE_MASK) == SHFL_TYPE_SYMLINK)
+
+/** The available additional information in a shfl_fsobjattr object. */
+enum shfl_fsobjattr_add {
+	/** No additional information is available / requested. */
+	SHFLFSOBJATTRADD_NOTHING = 1,
+	/**
+	 * The additional unix attributes (shfl_fsobjattr::u::unix_attr) are
+	 *  available / requested.
+	 */
+	SHFLFSOBJATTRADD_UNIX,
+	/**
+	 * The additional extended attribute size (shfl_fsobjattr::u::size) is
+	 *  available / requested.
+	 */
+	SHFLFSOBJATTRADD_EASIZE,
+	/**
+	 * The last valid item (inclusive).
+	 * The valid range is SHFLFSOBJATTRADD_NOTHING thru
+	 * SHFLFSOBJATTRADD_LAST.
+	 */
+	SHFLFSOBJATTRADD_LAST = SHFLFSOBJATTRADD_EASIZE,
+
+	/** The usual 32-bit hack. */
+	SHFLFSOBJATTRADD_32BIT_SIZE_HACK = 0x7fffffff
+};
+
+/**
+ * Additional unix Attributes, these are available when
+ * shfl_fsobjattr.additional == SHFLFSOBJATTRADD_UNIX.
+ */
+struct shfl_fsobjattr_unix {
+	/**
+	 * The user owning the filesystem object (st_uid).
+	 * This field is ~0U if not supported.
+	 */
+	u32 uid;
+
+	/**
+	 * The group the filesystem object is assigned (st_gid).
+	 * This field is ~0U if not supported.
+	 */
+	u32 gid;
+
+	/**
+	 * Number of hard links to this filesystem object (st_nlink).
+	 * This field is 1 if the filesystem doesn't support hardlinking or
+	 * the information isn't available.
+	 */
+	u32 hardlinks;
+
+	/**
+	 * The device number of the device which this filesystem object resides
+	 * on (st_dev). This field is 0 if this information is not available.
+	 */
+	u32 inode_id_device;
+
+	/**
+	 * The unique identifier (within the filesystem) of this filesystem
+	 * object (st_ino). Together with inode_id_device, this field can be
+	 * used as a OS wide unique id, when both their values are not 0.
+	 * This field is 0 if the information is not available.
+	 */
+	u64 inode_id;
+
+	/**
+	 * User flags (st_flags).
+	 * This field is 0 if this information is not available.
+	 */
+	u32 flags;
+
+	/**
+	 * The current generation number (st_gen).
+	 * This field is 0 if this information is not available.
+	 */
+	u32 generation_id;
+
+	/**
+	 * The device number of a char. or block device type object (st_rdev).
+	 * This field is 0 if the file isn't a char. or block device or when
+	 * the OS doesn't use the major+minor device idenfication scheme.
+	 */
+	u32 device;
+} __packed;
+
+/** Extended attribute size. */
+struct shfl_fsobjattr_easize {
+	/** Size of EAs. */
+	s64 cb;
+} __packed;
+
+/** Shared folder filesystem object attributes. */
+struct shfl_fsobjattr {
+	/** Mode flags (st_mode). SHFL_UNIX_*, SHFL_TYPE_*, and SHFL_DOS_*. */
+	u32 mode;
+
+	/** The additional attributes available. */
+	enum shfl_fsobjattr_add additional;
+
+	/**
+	 * Additional attributes.
+	 *
+	 * Unless explicitly specified to an API, the API can provide additional
+	 * data as it is provided by the underlying OS.
+	 */
+	union {
+		struct shfl_fsobjattr_unix unix_attr;
+		struct shfl_fsobjattr_easize size;
+	} __packed u;
+} __packed;
+VMMDEV_ASSERT_SIZE(shfl_fsobjattr, 44);
+
+struct shfl_timespec {
+	s64 ns_relative_to_unix_epoch;
+};
+
+/** Filesystem object information structure. */
+struct shfl_fsobjinfo {
+	/**