[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>

8 files changed, 40 insertions, 18 deletions

diff --git a/fs/afs/dir.c b/fs/afs/dir.c
index 2fc9987..cf8a2cb 100644
--- a/fs/afs/dir.c
+++ b/fs/afs/dir.c
@@ -30,7 +30,7 @@ static int afs_dir_readdir(struct file *file, void *dirent, filldir_t filldir);
 static int afs_d_revalidate(struct dentry *dentry, struct nameidata *nd);
 static int afs_d_delete(struct dentry *dentry);
 static int afs_dir_lookup_filldir(void *_cookie, const char *name, int nlen,
-				  loff_t fpos, ino_t ino, unsigned dtype);
+				  loff_t fpos, u64 ino, unsigned dtype);
 
 const struct file_operations afs_dir_file_operations = {
 	.open		= afs_dir_open,
@@ -409,7 +409,7 @@ static int afs_dir_readdir(struct file *file, void *cookie, filldir_t filldir)
  *   uniquifier through dtype
  */
 static int afs_dir_lookup_filldir(void *_cookie, const char *name, int nlen,
-				  loff_t fpos, ino_t ino, unsigned dtype)
+				  loff_t fpos, u64 ino, unsigned dtype)
 {
 	struct afs_dir_lookup_cookie *cookie = _cookie;
 
diff --git a/fs/compat.c b/fs/compat.c
index d98c96f..4d3fbcb 100644
--- a/fs/compat.c
+++ b/fs/compat.c
@@ -914,20 +914,24 @@ struct compat_readdir_callback {
 };
 
 static int compat_fillonedir(void *__buf, const char *name, int namlen,
-			loff_t offset, ino_t ino, unsigned int d_type)
+			loff_t offset, u64 ino, unsigned int d_type)
 {
 	struct compat_readdir_callback *buf = __buf;
 	struct compat_old_linux_dirent __user *dirent;
+	compat_ulong_t d_ino;
 
 	if (buf->result)
 		return -EINVAL;
+	d_ino = ino;
+	if (sizeof(d_ino) < sizeof(ino) && d_ino != ino)
+		return -EOVERFLOW;
 	buf->result++;
 	dirent = buf->dirent;
 	if (!access_ok(VERIFY_WRITE, dirent,
 			(unsigned long)(dirent->d_name + namlen + 1) -
 				(unsigned long)dirent))
 		goto efault;
-	if (	__put_user(ino, &dirent->d_ino) ||
+	if (	__put_user(d_ino, &dirent->d_ino) ||
 		__put_user(offset, &dirent->d_offset) ||
 		__put_user(namlen, &dirent->d_namlen) ||
 		__copy_to_user(dirent->d_name, name, namlen) ||
@@ -978,22 +982,26 @@ struct compat_getdents_callback {
 };
 
 static int compat_filldir(void *__buf, const char *name, int namlen,
-		loff_t offset, ino_t ino, unsigned int d_type)
+		loff_t offset, u64 ino, unsigned int d_type)
 {
 	struct compat_linux_dirent __user * dirent;
 	struct compat_getdents_callback *buf = __buf;
+	compat_ulong_t d_ino;
 	int reclen = COMPAT_ROUND_UP(NAME_OFFSET(dirent) + namlen + 2);
 
 	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) {
 		if (__put_user(offset, &dirent->d_off))
 			goto efault;
 	}
 	dirent = buf->current_dir;
-	if (__put_user(ino, &dirent->d_ino))
+	if (__put_user(d_ino, &dirent->d_ino))
 		goto efault;
 	if (__put_user(reclen, &dirent->d_reclen))
 		goto efault;
@@ -1064,7 +1072,7 @@ struct compat_getdents_callback64 {
 };
 
 static int compat_filldir64(void * __buf, const char * name, int namlen, loff_t offset,
-		     ino_t ino, unsigned int d_type)
+		     u64 ino, unsigned int d_type)
 {
 	struct linux_dirent64 __user *dirent;
 	struct compat_getdents_callback64 *buf = __buf;
diff --git a/fs/exportfs/expfs.c b/fs/exportfs/expfs.c
index 4c39009..93e77c3 100644
--- a/fs/exportfs/expfs.c
+++ b/fs/exportfs/expfs.c
@@ -315,7 +315,7 @@ struct getdents_callback {
  * the name matching the specified inode number.
  */
 static int filldir_one(void * __buf, const char * name, int len,
-			loff_t pos, ino_t ino, unsigned int d_type)
+			loff_t pos, u64 ino, unsigned int d_type)
 {
 	struct getdents_callback *buf = __buf;
 	int result = 0;
diff --git a/fs/fat/dir.c b/fs/fat/dir.c
index 3e50a41..69c439f 100644
--- a/fs/fat/dir.c
+++ b/fs/fat/dir.c
@@ -648,7 +648,7 @@ static int fat_readdir(struct file *filp, void *dirent, filldir_t filldir)
 }
 
 static int fat_ioctl_filldir(void *__buf, const char *name, int name_len,
-			     loff_t offset, ino_t ino, unsigned int d_type)
+			     loff_t offset, u64 ino, unsigned int d_type)
 {
 	struct fat_ioctl_filldir_callback *buf = __buf;
 	struct dirent __user *d1 = buf->dirent;
diff --git a/fs/nfsd/nfs4recover.c b/fs/nfsd/nfs4recover.c
index e35d7e5..1cbd2e4 100644
--- a/fs/nfsd/nfs4recover.c
+++ b/fs/nfsd/nfs4recover.c
@@ -184,7 +184,7 @@ struct dentry_list_arg {
 
 static int
 nfsd4_build_dentrylist(void *arg, const char *name, int namlen,
-		loff_t offset, ino_t ino, unsigned int d_type)
+		loff_t offset, u64 ino, unsigned int d_type)
 {
 	struct dentry_list_arg *dla = arg;
 	struct list_head *dentries = &dla->dentries;
diff --git a/fs/readdir.c b/fs/readdir.c
index b610932..bff3ee5 100644
--- a/fs/readdir.c
+++ b/fs/readdir.c
@@ -69,20 +69,24 @@ struct readdir_callback {
 };
 
 static int fillonedir(void * __buf, const char * name, int namlen, loff_t offset,
-		      ino_t ino, unsigned int d_type)
+		      u64 ino, unsigned int d_type)
 {
 	struct readdir_callback * buf = (struct readdir_callback *) __buf;
 	struct old_linux_dirent __user * dirent;
+	unsigned long d_ino;
 
 	if (buf->result)
 		return -EINVAL;
+	d_ino = ino;
+	if (sizeof(d_ino) < sizeof(ino) && d_ino != ino)
+		return -EOVERFLOW;
 	buf->result++;
 	dirent = buf->dirent;
 	if (!access_ok(VERIFY_WRITE, dirent,
 			(unsigned long)(dirent->d_name + namlen + 1) -
 				(unsigned long)dirent))
 		goto efault;
-	if (	__put_user(ino, &dirent->d_ino) ||
+	if (	__put_user(d_ino, &dirent->d_ino) ||
 		__put_user(offset, &dirent->d_offset) ||
 		__put_user(namlen, &dirent->d_namlen) ||
 		__copy_to_user(dirent->d_name, name, namlen) ||
@@ -138,22 +142,26 @@ struct getdents_callback {
 };
 
 static int filldir(void * __buf, const char * name, int namlen, loff_t offset,
-		   ino_t ino, unsigned int d_type)
+		   u64 ino, unsigned int d_type)
 {
 	struct linux_dirent __user * dirent;
 	struct getdents_callback * buf = (struct getdents_callback *) __buf;
+	unsigned long d_ino;
 	int reclen = ROUND_UP(NAME_OFFSET(dirent) + namlen + 2);
 
 	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) {
 		if (__put_user(offset, &dirent->d_off))
 			goto efault;
 	}
 	dirent = buf->current_dir;
-	if (__put_user(ino, &dirent->d_ino))
+	if (__put_user(d_ino, &dirent->d_ino))
 		goto efault;
 	if (__put_user(reclen, &dirent->d_reclen))
 		goto efault;
@@ -222,7 +230,7 @@ struct getdents_callback64 {
 };
 
 static int filldir64(void * __buf, const char * name, int namlen, loff_t offset,
-		     ino_t ino, unsigned int d_type)
+		     u64 ino, unsigned int d_type)
 {
 	struct linux_dirent64 __user *dirent;
 	struct getdents_callback64 * buf = (struct getdents_callback64 *) __buf;
diff --git a/fs/reiserfs/xattr.c b/fs/reiserfs/xattr.c
index d935fb9..7bdb0ed 100644
--- a/fs/reiserfs/xattr.c
+++ b/fs/reiserfs/xattr.c
@@ -773,7 +773,7 @@ int reiserfs_xattr_del(struct inode *inode, const char *name)
 
 static int
 reiserfs_delete_xattrs_filler(void *buf, const char *name, int namelen,
-			      loff_t offset, ino_t ino, unsigned int d_type)
+			      loff_t offset, u64 ino, unsigned int d_type)
 {
 	struct dentry *xadir = (struct dentry *)buf;
 
@@ -851,7 +851,7 @@ struct reiserfs_chown_buf {
 /* XXX: If there is a better way to do this, I'd love to hear about it */
 static int
 reiserfs_chown_xattrs_filler(void *buf, const char *name, int namelen,
-			     loff_t offset, ino_t ino, unsigned int d_type)
+			     loff_t offset, u64 ino, unsigned int d_type)
 {
 	struct reiserfs_chown_buf *chown_buf = (struct reiserfs_chown_buf *)buf;
 	struct dentry *xafile, *xadir = chown_buf->xadir;
@@ -1036,7 +1036,7 @@ struct reiserfs_listxattr_buf {
 
 static int
 reiserfs_listxattr_filler(void *buf, const char *name, int namelen,
-			  loff_t offset, ino_t ino, unsigned int d_type)
+			  loff_t offset, u64 ino, unsigned int d_type)
 {
 	struct reiserfs_listxattr_buf *b = (struct reiserfs_listxattr_buf *)buf;
 	int len = 0;
diff --git a/fs/stat.c b/fs/stat.c
index 60a31d5..bca07eb 100644
--- a/fs/stat.c
+++ b/fs/stat.c
@@ -140,6 +140,8 @@ static int cp_old_stat(struct kstat *stat, struct __old_kernel_stat __user * sta
 	memset(&tmp, 0, sizeof(struct __old_kernel_stat));
 	tmp.st_dev = old_encode_dev(stat->dev);
 	tmp.st_ino = stat->ino;
+	if (sizeof(tmp.st_ino) < sizeof(stat->ino) && tmp.st_ino != stat->ino)
+		return -EOVERFLOW;
 	tmp.st_mode = stat->mode;
 	tmp.st_nlink = stat->nlink;
 	if (tmp.st_nlink != stat->nlink)
@@ -210,6 +212,8 @@ static int cp_new_stat(struct kstat *stat, struct stat __user *statbuf)
 	tmp.st_dev = new_encode_dev(stat->dev);
 #endif
 	tmp.st_ino = stat->ino;
+	if (sizeof(tmp.st_ino) < sizeof(stat->ino) && tmp.st_ino != stat->ino)
+		return -EOVERFLOW;
 	tmp.st_mode = stat->mode;
 	tmp.st_nlink = stat->nlink;
 	if (tmp.st_nlink != stat->nlink)
@@ -347,6 +351,8 @@ static long cp_new_stat64(struct kstat *stat, struct stat64 __user *statbuf)
 	tmp.st_rdev = huge_encode_dev(stat->rdev);
 #endif
 	tmp.st_ino = stat->ino;
+	if (sizeof(tmp.st_ino) < sizeof(stat->ino) && tmp.st_ino != stat->ino)
+		return -EOVERFLOW;
 #ifdef STAT64_HAS_BROKEN_ST_INO
 	tmp.__st_ino = stat->ino;
 #endif