[PATCH 1/4] compat_do_execve should unshare_files

[Hugh Dickins <hugh@veritas.com>]

2.6.26's commit fd8328be874f4190a811c58cd4778ec2c74d2c05
"sanitize handling of shared descriptor tables in failing execve()"
moved the unshare_files() from flush_old_exec() and several binfmts
to the head of do_execve(); but forgot to make the same change to
compat_do_execve(), leaving a CLONE_FILES files_struct shared across
exec from a 32-bit process on a 64-bit kernel.

It's arguable whether the files_struct really ought to be unshared
across exec; but 2.6.1 made that so to stop the loading binary's fd
leaking into other threads, and a 32-bit process on a 64-bit kernel
ought to behave in the same way as 32 on 32 and 64 on 64.

Signed-off-by: Hugh Dickins <hugh@veritas.com>
Cc: stable@kernel.org
---

 fs/compat.c |   12 +++++++++++-
 1 file changed, 11 insertions(+), 1 deletion(-)

--- 2.6.29/fs/compat.c	2009-03-23 23:12:14.000000000 +0000
+++ linux/fs/compat.c	2009-03-28 18:06:02.000000000 +0000
@@ -1392,12 +1392,17 @@ int compat_do_execve(char * filename,
 {
 	struct linux_binprm *bprm;
 	struct file *file;
+	struct files_struct *displaced;
 	int retval;
 
+	retval = unshare_files(&displaced);
+	if (retval)
+		goto out_ret;
+
 	retval = -ENOMEM;
 	bprm = kzalloc(sizeof(*bprm), GFP_KERNEL);
 	if (!bprm)
-		goto out_ret;
+		goto out_files;
 
 	retval = mutex_lock_interruptible(&current->cred_exec_mutex);
 	if (retval < 0)
@@ -1457,6 +1462,8 @@ int compat_do_execve(char * filename,
 	mutex_unlock(&current->cred_exec_mutex);
 	acct_update_integrals(current);
 	free_bprm(bprm);
+	if (displaced)
+		put_files_struct(displaced);
 	return retval;
 
 out:
@@ -1475,6 +1482,9 @@ out_unlock:
 out_free:
 	free_bprm(bprm);
 
+out_files:
+	if (displaced)
+		reset_files_struct(displaced);
 out_ret:
 	return retval;
 }