From: Hugh Dickins <hugh@veritas.com>
Date: Sat, 28 Mar 2009 23:16:03 +0000 (+0000)
Subject: compat_do_execve should unshare_files
X-Git-Url: http://pilppa.com/gitweb/?a=commitdiff_plain;h=53e9309e01277ec99c38e84e0ca16921287cf470;p=linux-2.6-omap-h63xx.git

compat_do_execve should unshare_files

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
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---

diff --git a/fs/compat.c b/fs/compat.c
index 5e374aad33f..b543363dd62 100644
--- a/fs/compat.c
+++ b/fs/compat.c
@@ -1420,12 +1420,17 @@ 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)
@@ -1487,6 +1492,8 @@ 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:
@@ -1506,6 +1513,9 @@ out_unlock:
 out_free:
 	free_bprm(bprm);
 
+out_files:
+	if (displaced)
+		reset_files_struct(displaced);
 out_ret:
 	return retval;
 }