From: Kees Cook kees@kernel.org
[ Upstream commit 543841d1806029889c2f69f040e88b247aba8e22 ]
Zbigniew mentioned at Linux Plumber's that systemd is interested in switching to execveat() for service execution, but can't, because the contents of /proc/pid/comm are the file descriptor which was used, instead of the path to the binary[1]. This makes the output of tools like top and ps useless, especially in a world where most fds are opened CLOEXEC so the number is truly meaningless.
When the filename passed in is empty (e.g. with AT_EMPTY_PATH), use the dentry's filename for "comm" instead of using the useless numeral from the synthetic fdpath construction. This way the actual exec machinery is unchanged, but cosmetically the comm looks reasonable to admins investigating things.
Instead of adding TASK_COMM_LEN more bytes to bprm, use one of the unused flag bits to indicate that we need to set "comm" from the dentry.
Suggested-by: Zbigniew Jędrzejewski-Szmek zbyszek@in.waw.pl Suggested-by: Tycho Andersen tandersen@netflix.com Suggested-by: Al Viro viro@zeniv.linux.org.uk Suggested-by: Linus Torvalds torvalds@linux-foundation.org Link: https://github.com/uapi-group/kernel-features#set-comm-field-before-exec [1] Reviewed-by: Aleksa Sarai cyphar@cyphar.com Tested-by: Zbigniew Jędrzejewski-Szmek zbyszek@in.waw.pl Signed-off-by: Kees Cook kees@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- fs/exec.c | 29 ++++++++++++++++++++++++++--- include/linux/binfmts.h | 4 +++- 2 files changed, 29 insertions(+), 4 deletions(-)
diff --git a/fs/exec.c b/fs/exec.c index 98cb7ba9983c7..b1f6b47ad20e1 100644 --- a/fs/exec.c +++ b/fs/exec.c @@ -1341,7 +1341,28 @@ int begin_new_exec(struct linux_binprm * bprm) set_dumpable(current->mm, SUID_DUMP_USER);
perf_event_exec(); - __set_task_comm(me, kbasename(bprm->filename), true); + + /* + * If the original filename was empty, alloc_bprm() made up a path + * that will probably not be useful to admins running ps or similar. + * Let's fix it up to be something reasonable. + */ + if (bprm->comm_from_dentry) { + /* + * Hold RCU lock to keep the name from being freed behind our back. + * Use acquire semantics to make sure the terminating NUL from + * __d_alloc() is seen. + * + * Note, we're deliberately sloppy here. We don't need to care about + * detecting a concurrent rename and just want a terminated name. + */ + rcu_read_lock(); + __set_task_comm(me, smp_load_acquire(&bprm->file->f_path.dentry->d_name.name), + true); + rcu_read_unlock(); + } else { + __set_task_comm(me, kbasename(bprm->filename), true); + }
/* An exec changes our domain. We are no longer part of the thread group */ @@ -1517,11 +1538,13 @@ static struct linux_binprm *alloc_bprm(int fd, struct filename *filename, int fl if (fd == AT_FDCWD || filename->name[0] == '/') { bprm->filename = filename->name; } else { - if (filename->name[0] == '\0') + if (filename->name[0] == '\0') { bprm->fdpath = kasprintf(GFP_KERNEL, "/dev/fd/%d", fd); - else + bprm->comm_from_dentry = 1; + } else { bprm->fdpath = kasprintf(GFP_KERNEL, "/dev/fd/%d/%s", fd, filename->name); + } if (!bprm->fdpath) goto out_free;
diff --git a/include/linux/binfmts.h b/include/linux/binfmts.h index e6c00e860951a..3305c849abd66 100644 --- a/include/linux/binfmts.h +++ b/include/linux/binfmts.h @@ -42,7 +42,9 @@ struct linux_binprm { * Set when errors can no longer be returned to the * original userspace. */ - point_of_no_return:1; + point_of_no_return:1, + /* Set when "comm" must come from the dentry. */ + comm_from_dentry:1; struct file *executable; /* Executable to pass to the interpreter */ struct file *interpreter; struct file *file;