Commit 53e9309e authored Mar 28, 2009 by Hugh Dickins Committed by Linus Torvalds Mar 28, 2009

compat_do_execve should unshare_files



2.6.26's commit fd8328be
"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>

parent 07d43ba9

fs/compat.c

+11 −1

Original line number	Diff line number	Diff line
		@@ -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;
		}