[PATCH] VFS: Make filldir_t and struct kstat deal in 64-bit inode numbers

These patches make the kernel pass 64-bit inode numbers internally when
communicating to userspace, even on a 32-bit system.  They are required
because some filesystems have intrinsic 64-bit inode numbers: NFS3+ and XFS
for example.  The 64-bit inode numbers are then propagated to userspace
automatically where the arch supports it.

Problems have been seen with userspace (eg: ld.so) using the 64-bit inode
number returned by stat64() or getdents64() to differentiate files, and
failing because the 64-bit inode number space was compressed to 32-bits, and
so overlaps occur.

This patch:

Make filldir_t take a 64-bit inode number and struct kstat carry a 64-bit
inode number so that 64-bit inode numbers can be passed back to userspace.

The stat functions then returns the full 64-bit inode number where
available and where possible.  If it is not possible to represent the inode
number supplied by the filesystem in the field provided by userspace, then
error EOVERFLOW will be issued.

Similarly, the getdents/readdir functions now pass the full 64-bit inode
number to userspace where possible, returning EOVERFLOW instead when a
directory entry is encountered that can't be properly represented.

Note that this means that some inodes will not be stat'able on a 32-bit
system with old libraries where they were before - but it does mean that
there will be no ambiguity over what a 32-bit inode number refers to.

Note similarly that directory scans may be cut short with an error on a
32-bit system with old libraries where the scan would work before for the
same reasons.

It is judged unlikely that this situation will occur because modern glibc
uses 64-bit capable versions of stat and getdents class functions
exclusively, and that older systems are unlikely to encounter
unrepresentable inode numbers anyway.

[akpm: alpha build fix]
Signed-off-by: David Howells <dhowells@redhat.com>
Cc: Trond Myklebust <trond.myklebust@fys.uio.no>
Cc: Al Viro <viro@zeniv.linux.org.uk>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>

3 files changed, 21 insertions, 3 deletions

diff --git a/arch/sparc64/kernel/sys_sparc32.c b/arch/sparc64/kernel/sys_sparc32.c
index 69444f2..dbc6d1a 100644
--- a/arch/sparc64/kernel/sys_sparc32.c
+++ b/arch/sparc64/kernel/sys_sparc32.c
@@ -337,12 +337,17 @@ asmlinkage long sys32_ftruncate64(unsigned int fd, unsigned long high, unsigned
 
 int cp_compat_stat(struct kstat *stat, struct compat_stat __user *statbuf)
 {
+	compat_ino_t ino;
 	int err;
 
 	if (stat->size > MAX_NON_LFS || !old_valid_dev(stat->dev) ||
 	    !old_valid_dev(stat->rdev))
 		return -EOVERFLOW;
 
+	ino = stat->ino;
+	if (sizeof(ino) < sizeof(stat->ino) && ino != stat->ino)
+		return -EOVERFLOW;
+
 	err  = put_user(old_encode_dev(stat->dev), &statbuf->st_dev);
 	err |= put_user(stat->ino, &statbuf->st_ino);
 	err |= put_user(stat->mode, &statbuf->st_mode);
diff --git a/arch/sparc64/kernel/sys_sunos32.c b/arch/sparc64/kernel/sys_sunos32.c
index 953296b..e414c8e 100644
--- a/arch/sparc64/kernel/sys_sunos32.c
+++ b/arch/sparc64/kernel/sys_sunos32.c
@@ -280,16 +280,20 @@ static int sunos_filldir(void * __buf, const char * name, int namlen,
 	struct sunos_dirent __user *dirent;
 	struct sunos_dirent_callback * buf = (struct sunos_dirent_callback *) __buf;
 	int reclen = ROUND_UP(NAME_OFFSET(dirent) + namlen + 1);
+	u32 d_ino;
 
 	buf->error = -EINVAL;	/* only used if we fail.. */
 	if (reclen > buf->count)
 		return -EINVAL;
+	d_ino = ino;
+	if (sizeof(d_ino) < sizeof(ino) && d_ino != ino)
+		return -EOVERFLOW;
 	dirent = buf->previous;
 	if (dirent)
 		put_user(offset, &dirent->d_off);
 	dirent = buf->curr;
 	buf->previous = dirent;
-	put_user(ino, &dirent->d_ino);
+	put_user(d_ino, &dirent->d_ino);
 	put_user(namlen, &dirent->d_namlen);
 	put_user(reclen, &dirent->d_reclen);
 	if (copy_to_user(dirent->d_name, name, namlen))
@@ -363,14 +367,18 @@ static int sunos_filldirentry(void * __buf, const char * name, int namlen,
 	struct sunos_direntry_callback * buf =
 		(struct sunos_direntry_callback *) __buf;
 	int reclen = ROUND_UP(NAME_OFFSET(dirent) + namlen + 1);
+	u32 d_ino;
 
 	buf->error = -EINVAL;	/* only used if we fail.. */
 	if (reclen > buf->count)
 		return -EINVAL;
+	d_ino = ino;
+	if (sizeof(d_ino) < sizeof(ino) && d_ino != ino)
+		return -EOVERFLOW;
 	dirent = buf->previous;
 	dirent = buf->curr;
 	buf->previous = dirent;
-	put_user(ino, &dirent->d_ino);
+	put_user(d_ino, &dirent->d_ino);
 	put_user(namlen, &dirent->d_namlen);
 	put_user(reclen, &dirent->d_reclen);
 	if (copy_to_user(dirent->d_name, name, namlen))
diff --git a/arch/sparc64/solaris/fs.c b/arch/sparc64/solaris/fs.c
index 0f0eb6a..12a940c 100644
--- a/arch/sparc64/solaris/fs.c
+++ b/arch/sparc64/solaris/fs.c
@@ -82,12 +82,17 @@ struct sol_stat64 {
 
 static inline int putstat(struct sol_stat __user *ubuf, struct kstat *kbuf)
 {
+	u32 ino;
+
 	if (kbuf->size > MAX_NON_LFS ||
 	    !sysv_valid_dev(kbuf->dev) ||
 	    !sysv_valid_dev(kbuf->rdev))
 		return -EOVERFLOW;
+	ino = kbuf->ino;
+	if (sizeof(ino) < sizeof(kbuf->ino) && ino != kbuf->ino)
+		return -EOVERFLOW;
 	if (put_user (sysv_encode_dev(kbuf->dev), &ubuf->st_dev)	||
-	    __put_user (kbuf->ino, &ubuf->st_ino)		||
+	    __put_user (ino, &ubuf->st_ino)				||
 	    __put_user (kbuf->mode, &ubuf->st_mode)		||
 	    __put_user (kbuf->nlink, &ubuf->st_nlink)	||
 	    __put_user (kbuf->uid, &ubuf->st_uid)		||