vfs: Add open by file handle support

[AV: duplicate of open() guts removed; file_open_root() used instead]

Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
diff --git a/fs/compat.c b/fs/compat.c
index a071775..c6d31a3 100644
--- a/fs/compat.c
+++ b/fs/compat.c
@@ -2284,3 +2284,16 @@
 }
 
 #endif /* CONFIG_TIMERFD */
+
+#ifdef CONFIG_FHANDLE
+/*
+ * Exactly like fs/open.c:sys_open_by_handle_at(), except that it
+ * doesn't set the O_LARGEFILE flag.
+ */
+asmlinkage long
+compat_sys_open_by_handle_at(int mountdirfd,
+			     struct file_handle __user *handle, int flags)
+{
+	return do_handle_open(mountdirfd, handle, flags);
+}
+#endif
diff --git a/fs/exportfs/expfs.c b/fs/exportfs/expfs.c
index cfe5573..b05acb7 100644
--- a/fs/exportfs/expfs.c
+++ b/fs/exportfs/expfs.c
@@ -374,6 +374,8 @@
 	/*
 	 * Try to get any dentry for the given file handle from the filesystem.
 	 */
+	if (!nop || !nop->fh_to_dentry)
+		return ERR_PTR(-ESTALE);
 	result = nop->fh_to_dentry(mnt->mnt_sb, fid, fh_len, fileid_type);
 	if (!result)
 		result = ERR_PTR(-ESTALE);
diff --git a/fs/fhandle.c b/fs/fhandle.c
index 9f79e74..bf93ad2 100644
--- a/fs/fhandle.c
+++ b/fs/fhandle.c
@@ -5,6 +5,8 @@
 #include <linux/mount.h>
 #include <linux/namei.h>
 #include <linux/exportfs.h>
+#include <linux/fs_struct.h>
+#include <linux/fsnotify.h>
 #include <asm/uaccess.h>
 #include "internal.h"
 
@@ -105,3 +107,159 @@
 	}
 	return err;
 }
+
+static struct vfsmount *get_vfsmount_from_fd(int fd)
+{
+	struct path path;
+
+	if (fd == AT_FDCWD) {
+		struct fs_struct *fs = current->fs;
+		spin_lock(&fs->lock);
+		path = fs->pwd;
+		mntget(path.mnt);
+		spin_unlock(&fs->lock);
+	} else {
+		int fput_needed;
+		struct file *file = fget_light(fd, &fput_needed);
+		if (!file)
+			return ERR_PTR(-EBADF);
+		path = file->f_path;
+		mntget(path.mnt);
+		fput_light(file, fput_needed);
+	}
+	return path.mnt;
+}
+
+static int vfs_dentry_acceptable(void *context, struct dentry *dentry)
+{
+	return 1;
+}
+
+static int do_handle_to_path(int mountdirfd, struct file_handle *handle,
+			     struct path *path)
+{
+	int retval = 0;
+	int handle_dwords;
+
+	path->mnt = get_vfsmount_from_fd(mountdirfd);
+	if (IS_ERR(path->mnt)) {
+		retval = PTR_ERR(path->mnt);
+		goto out_err;
+	}
+	/* change the handle size to multiple of sizeof(u32) */
+	handle_dwords = handle->handle_bytes >> 2;
+	path->dentry = exportfs_decode_fh(path->mnt,
+					  (struct fid *)handle->f_handle,
+					  handle_dwords, handle->handle_type,
+					  vfs_dentry_acceptable, NULL);
+	if (IS_ERR(path->dentry)) {
+		retval = PTR_ERR(path->dentry);
+		goto out_mnt;
+	}
+	return 0;
+out_mnt:
+	mntput(path->mnt);
+out_err:
+	return retval;
+}
+
+static int handle_to_path(int mountdirfd, struct file_handle __user *ufh,
+		   struct path *path)
+{
+	int retval = 0;
+	struct file_handle f_handle;
+	struct file_handle *handle = NULL;
+
+	/*
+	 * With handle we don't look at the execute bit on the
+	 * the directory. Ideally we would like CAP_DAC_SEARCH.
+	 * But we don't have that
+	 */
+	if (!capable(CAP_DAC_READ_SEARCH)) {
+		retval = -EPERM;
+		goto out_err;
+	}
+	if (copy_from_user(&f_handle, ufh, sizeof(struct file_handle))) {
+		retval = -EFAULT;
+		goto out_err;
+	}
+	if ((f_handle.handle_bytes > MAX_HANDLE_SZ) ||
+	    (f_handle.handle_bytes == 0)) {
+		retval = -EINVAL;
+		goto out_err;
+	}
+	handle = kmalloc(sizeof(struct file_handle) + f_handle.handle_bytes,
+			 GFP_KERNEL);
+	if (!handle) {
+		retval = -ENOMEM;
+		goto out_err;
+	}
+	/* copy the full handle */
+	if (copy_from_user(handle, ufh,
+			   sizeof(struct file_handle) +
+			   f_handle.handle_bytes)) {
+		retval = -EFAULT;
+		goto out_handle;
+	}
+
+	retval = do_handle_to_path(mountdirfd, handle, path);
+
+out_handle:
+	kfree(handle);
+out_err:
+	return retval;
+}
+
+long do_handle_open(int mountdirfd,
+		    struct file_handle __user *ufh, int open_flag)
+{
+	long retval = 0;
+	struct path path;
+	struct file *file;
+	int fd;
+
+	retval = handle_to_path(mountdirfd, ufh, &path);
+	if (retval)
+		return retval;
+
+	fd = get_unused_fd_flags(open_flag);
+	if (fd < 0) {
+		path_put(&path);
+		return fd;
+	}
+	file = file_open_root(path.dentry, path.mnt, "", open_flag);
+	if (IS_ERR(file)) {
+		put_unused_fd(fd);
+		retval =  PTR_ERR(file);
+	} else {
+		retval = fd;
+		fsnotify_open(file);
+		fd_install(fd, file);
+	}
+	path_put(&path);
+	return retval;
+}
+
+/**
+ * sys_open_by_handle_at: Open the file handle
+ * @mountdirfd: directory file descriptor
+ * @handle: file handle to be opened
+ * @flag: open flags.
+ *
+ * @mountdirfd indicate the directory file descriptor
+ * of the mount point. file handle is decoded relative
+ * to the vfsmount pointed by the @mountdirfd. @flags
+ * value is same as the open(2) flags.
+ */
+SYSCALL_DEFINE3(open_by_handle_at, int, mountdirfd,
+		struct file_handle __user *, handle,
+		int, flags)
+{
+	long ret;
+
+	if (force_o_largefile())
+		flags |= O_LARGEFILE;
+
+	ret = do_handle_open(mountdirfd, handle, flags);
+	return ret;
+}
diff --git a/fs/internal.h b/fs/internal.h
index 52abc52..f3d15de 100644
--- a/fs/internal.h
+++ b/fs/internal.h
@@ -117,6 +117,9 @@
 extern struct file *do_file_open_root(struct dentry *, struct vfsmount *,
 		const char *, const struct open_flags *, int lookup_flags);
 
+extern long do_handle_open(int mountdirfd,
+			   struct file_handle __user *ufh, int open_flag);
+
 /*
  * inode.c
  */
diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h
index 9701126..2d9b79c0 100644
--- a/include/linux/syscalls.h
+++ b/include/linux/syscalls.h
@@ -836,4 +836,7 @@
 asmlinkage long sys_name_to_handle_at(int dfd, const char __user *name,
 				      struct file_handle __user *handle,
 				      int __user *mnt_id, int flag);
+asmlinkage long sys_open_by_handle_at(int mountdirfd,
+				      struct file_handle __user *handle,
+				      int flags);
 #endif
diff --git a/kernel/sys_ni.c b/kernel/sys_ni.c
index 4e01343..25cc41c 100644
--- a/kernel/sys_ni.c
+++ b/kernel/sys_ni.c
@@ -189,3 +189,5 @@
 
 /* open by handle */
 cond_syscall(sys_name_to_handle_at);
+cond_syscall(sys_open_by_handle_at);
+cond_syscall(compat_sys_open_by_handle_at);