vfs: Add name to file handle conversion support

The syscall also return mount id which can be used
to lookup file system specific information such as uuid
in /proc/<pid>/mountinfo

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/Kconfig b/fs/Kconfig
index 3db9caa..7cb53aa 100644 (file)
--- a/fs/Kconfig
+++ b/fs/Kconfig
@@ -47,7 +47,7 @@ config FS_POSIX_ACL
        def_bool n
 
 config EXPORTFS
-       tristate
+       bool
 
 config FILE_LOCKING
        bool "Enable POSIX file locking API" if EXPERT

diff --git a/fs/Makefile b/fs/Makefile
index a7f7cef..ba01202 100644 (file)
--- a/fs/Makefile
+++ b/fs/Makefile
@@ -48,6 +48,8 @@ obj-$(CONFIG_FS_POSIX_ACL)    += posix_acl.o xattr_acl.o
 obj-$(CONFIG_NFS_COMMON)       += nfs_common/
 obj-$(CONFIG_GENERIC_ACL)      += generic_acl.o
 
+obj-$(CONFIG_FHANDLE)          += fhandle.o
+
 obj-y                          += quota/
 
 obj-$(CONFIG_PROC_FS)          += proc/

diff --git a/fs/fhandle.c b/fs/fhandle.c
new file mode 100644 (file)
index 0000000..9f79e74
--- /dev/null
+++ b/fs/fhandle.c
@@ -0,0 +1,107 @@
+#include <linux/syscalls.h>
+#include <linux/slab.h>
+#include <linux/fs.h>
+#include <linux/file.h>
+#include <linux/mount.h>
+#include <linux/namei.h>
+#include <linux/exportfs.h>
+#include <asm/uaccess.h>
+#include "internal.h"
+
+static long do_sys_name_to_handle(struct path *path,
+                                 struct file_handle __user *ufh,
+                                 int __user *mnt_id)
+{
+       long retval;
+       struct file_handle f_handle;
+       int handle_dwords, handle_bytes;
+       struct file_handle *handle = NULL;
+
+       /*
+        * We need t make sure wether the file system
+        * support decoding of the file handle
+        */
+       if (!path->mnt->mnt_sb->s_export_op ||
+           !path->mnt->mnt_sb->s_export_op->fh_to_dentry)
+               return -EOPNOTSUPP;
+
+       if (copy_from_user(&f_handle, ufh, sizeof(struct file_handle)))
+               return -EFAULT;
+
+       if (f_handle.handle_bytes > MAX_HANDLE_SZ)
+               return -EINVAL;
+
+       handle = kmalloc(sizeof(struct file_handle) + f_handle.handle_bytes,
+                        GFP_KERNEL);
+       if (!handle)
+               return -ENOMEM;
+
+       /* convert handle size to  multiple of sizeof(u32) */
+       handle_dwords = f_handle.handle_bytes >> 2;
+
+       /* we ask for a non connected handle */
+       retval = exportfs_encode_fh(path->dentry,
+                                   (struct fid *)handle->f_handle,
+                                   &handle_dwords,  0);
+       handle->handle_type = retval;
+       /* convert handle size to bytes */
+       handle_bytes = handle_dwords * sizeof(u32);
+       handle->handle_bytes = handle_bytes;
+       if ((handle->handle_bytes > f_handle.handle_bytes) ||
+           (retval == 255) || (retval == -ENOSPC)) {
+               /* As per old exportfs_encode_fh documentation
+                * we could return ENOSPC to indicate overflow
+                * But file system returned 255 always. So handle
+                * both the values
+                */
+               /*
+                * set the handle size to zero so we copy only
+                * non variable part of the file_handle
+                */
+               handle_bytes = 0;
+               retval = -EOVERFLOW;
+       } else
+               retval = 0;
+       /* copy the mount id */
+       if (copy_to_user(mnt_id, &path->mnt->mnt_id, sizeof(*mnt_id)) ||
+           copy_to_user(ufh, handle,
+                        sizeof(struct file_handle) + handle_bytes))
+               retval = -EFAULT;
+       kfree(handle);
+       return retval;
+}
+
+/**
+ * sys_name_to_handle_at: convert name to handle
+ * @dfd: directory relative to which name is interpreted if not absolute
+ * @name: name that should be converted to handle.
+ * @handle: resulting file handle
+ * @mnt_id: mount id of the file system containing the file
+ * @flag: flag value to indicate whether to follow symlink or not
+ *
+ * @handle->handle_size indicate the space available to store the
+ * variable part of the file handle in bytes. If there is not
+ * enough space, the field is updated to return the minimum
+ * value required.
+ */
+SYSCALL_DEFINE5(name_to_handle_at, int, dfd, const char __user *, name,
+               struct file_handle __user *, handle, int __user *, mnt_id,
+               int, flag)
+{
+       struct path path;
+       int lookup_flags;
+       int err;
+
+       if ((flag & ~(AT_SYMLINK_FOLLOW | AT_EMPTY_PATH)) != 0)
+               return -EINVAL;
+
+       lookup_flags = (flag & AT_SYMLINK_FOLLOW) ? LOOKUP_FOLLOW : 0;
+       if (flag & AT_EMPTY_PATH)
+               lookup_flags |= LOOKUP_EMPTY;
+       err = user_path_at(dfd, name, lookup_flags, &path);
+       if (!err) {
+               err = do_sys_name_to_handle(&path, handle, mnt_id);
+               path_put(&path);
+       }
+       return err;
+}

diff --git a/include/linux/exportfs.h b/include/linux/exportfs.h
index 65afdfd..33a42f2 100644 (file)
--- a/include/linux/exportfs.h
+++ b/include/linux/exportfs.h
@@ -8,6 +8,9 @@ struct inode;
 struct super_block;
 struct vfsmount;
 
+/* limit the handle size to NFSv4 handle size now */
+#define MAX_HANDLE_SZ 128
+
 /*
  * The fileid_type identifies how the file within the filesystem is encoded.
  * In theory this is freely set and parsed by the filesystem, but we try to

diff --git a/include/linux/fs.h b/include/linux/fs.h
index b7178b0..3f64630 100644 (file)
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -978,6 +978,13 @@ struct file {
 #endif
 };
 
+struct file_handle {
+       __u32 handle_bytes;
+       int handle_type;
+       /* file identifier */
+       unsigned char f_handle[0];
+};
+
 #define get_file(x)    atomic_long_inc(&(x)->f_count)
 #define fput_atomic(x) atomic_long_add_unless(&(x)->f_count, -1, 1)
 #define file_count(x)  atomic_long_read(&(x)->f_count)

diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h
index 98664db..9701126 100644 (file)
--- a/include/linux/syscalls.h
+++ b/include/linux/syscalls.h
@@ -62,6 +62,7 @@ struct robust_list_head;
 struct getcpu_cache;
 struct old_linux_dirent;
 struct perf_event_attr;
+struct file_handle;
 
 #include <linux/types.h>
 #include <linux/aio_abi.h>
@@ -832,5 +833,7 @@ asmlinkage long sys_mmap_pgoff(unsigned long addr, unsigned long len,
                        unsigned long prot, unsigned long flags,
                        unsigned long fd, unsigned long pgoff);
 asmlinkage long sys_old_mmap(struct mmap_arg_struct __user *arg);
-
+asmlinkage long sys_name_to_handle_at(int dfd, const char __user *name,
+                                     struct file_handle __user *handle,
+                                     int __user *mnt_id, int flag);
 #endif

diff --git a/init/Kconfig b/init/Kconfig
index be788c0..e72fa17 100644 (file)
--- a/init/Kconfig
+++ b/init/Kconfig
@@ -287,6 +287,18 @@ config BSD_PROCESS_ACCT_V3
          for processing it. A preliminary version of these tools is available
          at <http://www.gnu.org/software/acct/>.
 
+config FHANDLE
+       bool "open by fhandle syscalls"
+       select EXPORTFS
+       help
+         If you say Y here, a user level program will be able to map
+         file names to handle and then later use the handle for
+         different file system operations. This is useful in implementing
+         userspace file servers, which now track files using handles instead
+         of names. The handle would remain the same even if file names
+         get renamed. Enables open_by_handle_at(2) and name_to_handle_at(2)
+         syscalls.
+
 config TASKSTATS
        bool "Export task/process statistics through netlink (EXPERIMENTAL)"
        depends on NET

diff --git a/kernel/sys_ni.c b/kernel/sys_ni.c
index c782fe9..4e01343 100644 (file)
--- a/kernel/sys_ni.c
+++ b/kernel/sys_ni.c
@@ -186,3 +186,6 @@ cond_syscall(sys_perf_event_open);
 /* fanotify! */
 cond_syscall(sys_fanotify_init);
 cond_syscall(sys_fanotify_mark);
+
+/* open by handle */
+cond_syscall(sys_name_to_handle_at);