@@ -1040,11 +1040,13 @@ static int exec_mmap(struct mm_struct *mm)
return 0;
}
-static int de_thread(struct task_struct *tsk)
+static int de_thread(struct task_struct *tsk, struct linux_binprm *bprm)
{
struct signal_struct *sig = tsk->signal;
struct sighand_struct *oldsighand = tsk->sighand;
spinlock_t *lock = &oldsighand->siglock;
+ struct task_struct *t;
+ bool unsafe_execve_in_progress = false;
if (thread_group_empty(tsk))
goto no_thread_group;
@@ -1067,6 +1069,19 @@ static int de_thread(struct task_struct *tsk)
if (!thread_group_leader(tsk))
sig->notify_count--;
+ for_other_threads(tsk, t) {
+ if (unlikely(t->ptrace)
+ && (t != tsk->group_leader || !t->exit_state))
+ unsafe_execve_in_progress = true;
+ }
+
+ if (unlikely(unsafe_execve_in_progress)) {
+ spin_unlock_irq(lock);
+ sig->exec_bprm = bprm;
+ mutex_unlock(&sig->cred_guard_mutex);
+ spin_lock_irq(lock);
+ }
+
while (sig->notify_count) {
__set_current_state(TASK_KILLABLE);
spin_unlock_irq(lock);
@@ -1157,6 +1172,11 @@ static int de_thread(struct task_struct *tsk)
release_task(leader);
}
+ if (unlikely(unsafe_execve_in_progress)) {
+ mutex_lock(&sig->cred_guard_mutex);
+ sig->exec_bprm = NULL;
+ }
+
sig->group_exec_task = NULL;
sig->notify_count = 0;
@@ -1168,6 +1188,11 @@ static int de_thread(struct task_struct *tsk)
return 0;
killed:
+ if (unlikely(unsafe_execve_in_progress)) {
+ mutex_lock(&sig->cred_guard_mutex);
+ sig->exec_bprm = NULL;
+ }
+
/* protects against exit_notify() and __exit_signal() */
read_lock(&tasklist_lock);
sig->group_exec_task = NULL;
@@ -1252,6 +1277,24 @@ int begin_new_exec(struct linux_binprm * bprm)
if (retval)
return retval;
+ /* If the binary is not readable then enforce mm->dumpable=0 */
+ would_dump(bprm, bprm->file);
+ if (bprm->have_execfd)
+ would_dump(bprm, bprm->executable);
+
+ /*
+ * Figure out dumpability. Note that this checking only of current
+ * is wrong, but userspace depends on it. This should be testing
+ * bprm->secureexec instead.
+ */
+ if (bprm->interp_flags & BINPRM_FLAGS_ENFORCE_NONDUMP ||
+ is_dumpability_changed(current_cred(), bprm->cred) ||
+ !(uid_eq(current_euid(), current_uid()) &&
+ gid_eq(current_egid(), current_gid())))
+ set_dumpable(bprm->mm, suid_dumpable);
+ else
+ set_dumpable(bprm->mm, SUID_DUMP_USER);
+
/*
* Ensure all future errors are fatal.
*/
@@ -1260,7 +1303,7 @@ int begin_new_exec(struct linux_binprm * bprm)
/*
* Make this the only thread in the thread group.
*/
- retval = de_thread(me);
+ retval = de_thread(me, bprm);
if (retval)
goto out;
@@ -1283,11 +1326,6 @@ int begin_new_exec(struct linux_binprm * bprm)
if (retval)
goto out;
- /* If the binary is not readable then enforce mm->dumpable=0 */
- would_dump(bprm, bprm->file);
- if (bprm->have_execfd)
- would_dump(bprm, bprm->executable);
-
/*
* Release all of the old mmap stuff
*/
@@ -1349,18 +1387,6 @@ int begin_new_exec(struct linux_binprm * bprm)
me->sas_ss_sp = me->sas_ss_size = 0;
- /*
- * Figure out dumpability. Note that this checking only of current
- * is wrong, but userspace depends on it. This should be testing
- * bprm->secureexec instead.
- */
- if (bprm->interp_flags & BINPRM_FLAGS_ENFORCE_NONDUMP ||
- !(uid_eq(current_euid(), current_uid()) &&
- gid_eq(current_egid(), current_gid())))
- set_dumpable(current->mm, suid_dumpable);
- else
- set_dumpable(current->mm, SUID_DUMP_USER);
-
perf_event_exec();
__set_task_comm(me, kbasename(bprm->filename), true);
@@ -1479,6 +1505,11 @@ static int prepare_bprm_creds(struct linux_binprm *bprm)
if (mutex_lock_interruptible(¤t->signal->cred_guard_mutex))
return -ERESTARTNOINTR;
+ if (unlikely(current->signal->exec_bprm)) {
+ mutex_unlock(¤t->signal->cred_guard_mutex);
+ return -ERESTARTNOINTR;
+ }
+
bprm->cred = prepare_exec_creds();
if (likely(bprm->cred))
return 0;
@@ -2785,6 +2785,12 @@ static ssize_t proc_pid_attr_write(struct file * file, const char __user * buf,
if (rv < 0)
goto out_free;
+ if (unlikely(current->signal->exec_bprm)) {
+ mutex_unlock(¤t->signal->cred_guard_mutex);
+ rv = -ERESTARTNOINTR;
+ goto out_free;
+ }
+
rv = security_setprocattr(PROC_I(inode)->op.lsmid,
file->f_path.dentry->d_name.name, page,
count);
@@ -153,6 +153,7 @@ extern const struct cred *get_task_cred(struct task_struct *);
extern struct cred *cred_alloc_blank(void);
extern struct cred *prepare_creds(void);
extern struct cred *prepare_exec_creds(void);
+extern bool is_dumpability_changed(const struct cred *, const struct cred *);
extern int commit_creds(struct cred *);
extern void abort_creds(struct cred *);
extern const struct cred *override_creds(const struct cred *);
@@ -235,9 +235,27 @@ struct signal_struct {
struct mm_struct *oom_mm; /* recorded mm when the thread group got
* killed by the oom killer */
+ struct linux_binprm *exec_bprm; /* Used to check ptrace_may_access
+ * against new credentials while
+ * de_thread is waiting for other
+ * traced threads to terminate.
+ * Set while de_thread is executing.
+ * The cred_guard_mutex is released
+ * after de_thread() has called
+ * zap_other_threads(), therefore
+ * a fatal signal is guaranteed to be
+ * already pending in the unlikely
+ * event, that
+ * current->signal->exec_bprm happens
+ * to be non-zero after the
+ * cred_guard_mutex was acquired.
+ */
+
struct mutex cred_guard_mutex; /* guard against foreign influences on
* credential calculations
* (notably. ptrace)
+ * Held while execve runs, except when
+ * a sibling thread is being traced.
* Deprecated do not use in new code.
* Use exec_update_lock instead.
*/
@@ -375,6 +375,30 @@ static bool cred_cap_issubset(const struct cred *set, const struct cred *subset)
return false;
}
+/**
+ * is_dumpability_changed - Will changing creds affect dumpability?
+ * @old: The old credentials.
+ * @new: The new credentials.
+ *
+ * If the @new credentials have no elevated privileges compared to the
+ * @old credentials, the task may remain dumpable. Otherwise we have
+ * to mark the task as undumpable to avoid information leaks from higher
+ * to lower privilege domains.
+ *
+ * Return: True if the task will become undumpable.
+ */
+bool is_dumpability_changed(const struct cred *old, const struct cred *new)
+{
+ if (!uid_eq(old->euid, new->euid) ||
+ !gid_eq(old->egid, new->egid) ||
+ !uid_eq(old->fsuid, new->fsuid) ||
+ !gid_eq(old->fsgid, new->fsgid) ||
+ !cred_cap_issubset(old, new))
+ return true;
+
+ return false;
+}
+
/**
* commit_creds - Install new credentials upon the current task
* @new: The credentials to be assigned
@@ -403,11 +427,7 @@ int commit_creds(struct cred *new)
get_cred(new); /* we will require a ref for the subj creds too */
/* dumpability changes */
- if (!uid_eq(old->euid, new->euid) ||
- !gid_eq(old->egid, new->egid) ||
- !uid_eq(old->fsuid, new->fsuid) ||
- !gid_eq(old->fsgid, new->fsgid) ||
- !cred_cap_issubset(old, new)) {
+ if (is_dumpability_changed(old, new)) {
if (task->mm)
set_dumpable(task->mm, suid_dumpable);
task->pdeath_signal = 0;
@@ -20,6 +20,7 @@
#include <linux/pagemap.h>
#include <linux/ptrace.h>
#include <linux/security.h>
+#include <linux/binfmts.h>
#include <linux/signal.h>
#include <linux/uio.h>
#include <linux/audit.h>
@@ -450,6 +451,27 @@ static int ptrace_attach(struct task_struct *task, long request,
return retval;
}
+ if (unlikely(task->in_execve)) {
+ retval = down_write_killable(&task->signal->exec_update_lock);
+ if (retval)
+ return retval;
+
+ scoped_guard (task_lock, task) {
+ struct linux_binprm *bprm = task->signal->exec_bprm;
+ const struct cred __rcu *old_cred = task->real_cred;
+ struct mm_struct *old_mm = task->mm;
+ rcu_assign_pointer(task->real_cred, bprm->cred);
+ task->mm = bprm->mm;
+ retval = __ptrace_may_access(task, PTRACE_MODE_ATTACH_REALCREDS);
+ rcu_assign_pointer(task->real_cred, old_cred);
+ task->mm = old_mm;
+ }
+
+ up_write(&task->signal->exec_update_lock);
+ if (retval)
+ return retval;
+ }
+
scoped_guard (write_lock_irq, &tasklist_lock) {
if (unlikely(task->exit_state))
return -EPERM;
@@ -491,6 +513,14 @@ static int ptrace_traceme(void)
{
int ret = -EPERM;
+ if (mutex_lock_interruptible(¤t->signal->cred_guard_mutex))
+ return -ERESTARTNOINTR;
+
+ if (unlikely(current->signal->exec_bprm)) {
+ mutex_unlock(¤t->signal->cred_guard_mutex);
+ return -ERESTARTNOINTR;
+ }
+
write_lock_irq(&tasklist_lock);
/* Are we already being traced? */
if (!current->ptrace) {
@@ -506,6 +536,7 @@ static int ptrace_traceme(void)
}
}
write_unlock_irq(&tasklist_lock);
+ mutex_unlock(¤t->signal->cred_guard_mutex);
return ret;
}
@@ -1955,9 +1955,15 @@ static long seccomp_set_mode_filter(unsigned int flags,
* Make sure we cannot change seccomp or nnp state via TSYNC
* while another thread is in the middle of calling exec.
*/
- if (flags & SECCOMP_FILTER_FLAG_TSYNC &&
- mutex_lock_killable(¤t->signal->cred_guard_mutex))
- goto out_put_fd;
+ if (flags & SECCOMP_FILTER_FLAG_TSYNC) {
+ if (mutex_lock_killable(¤t->signal->cred_guard_mutex))
+ goto out_put_fd;
+
+ if (unlikely(current->signal->exec_bprm)) {
+ mutex_unlock(¤t->signal->cred_guard_mutex);
+ goto out_put_fd;
+ }
+ }
spin_lock_irq(¤t->sighand->siglock);
@@ -14,6 +14,7 @@
#include <signal.h>
#include <unistd.h>
#include <sys/ptrace.h>
+#include <sys/syscall.h>
static void *thread(void *arg)
{
@@ -23,7 +24,7 @@ static void *thread(void *arg)
TEST(vmaccess)
{
- int f, pid = fork();
+ int s, f, pid = fork();
char mm[64];
if (!pid) {
@@ -31,19 +32,42 @@ TEST(vmaccess)
pthread_create(&pt, NULL, thread, NULL);
pthread_join(pt, NULL);
- execlp("true", "true", NULL);
+ execlp("false", "false", NULL);
+ return;
}
sleep(1);
sprintf(mm, "/proc/%d/mem", pid);
+ /* deadlock did happen here */
f = open(mm, O_RDONLY);
ASSERT_GE(f, 0);
close(f);
- f = kill(pid, SIGCONT);
- ASSERT_EQ(f, 0);
+ f = waitpid(-1, &s, WNOHANG);
+ ASSERT_NE(f, -1);
+ ASSERT_NE(f, 0);
+ ASSERT_NE(f, pid);
+ ASSERT_EQ(WIFEXITED(s), 1);
+ ASSERT_EQ(WEXITSTATUS(s), 0);
+ f = waitpid(-1, &s, 0);
+ ASSERT_EQ(f, pid);
+ ASSERT_EQ(WIFEXITED(s), 1);
+ ASSERT_EQ(WEXITSTATUS(s), 1);
+ f = waitpid(-1, NULL, 0);
+ ASSERT_EQ(f, -1);
+ ASSERT_EQ(errno, ECHILD);
}
-TEST(attach)
+/*
+ * Same test as previous, except that
+ * we try to ptrace the group leader,
+ * which is about to call execve,
+ * when the other thread is already ptraced.
+ * This exercises the code in de_thread
+ * where it is waiting inside the
+ * while (sig->notify_count) {
+ * loop.
+ */
+TEST(attach1)
{
int s, k, pid = fork();
@@ -52,19 +76,76 @@ TEST(attach)
pthread_create(&pt, NULL, thread, NULL);
pthread_join(pt, NULL);
- execlp("sleep", "sleep", "2", NULL);
+ execlp("false", "false", NULL);
+ return;
}
sleep(1);
+ /* deadlock may happen here */
k = ptrace(PTRACE_ATTACH, pid, 0L, 0L);
- ASSERT_EQ(errno, EAGAIN);
- ASSERT_EQ(k, -1);
+ ASSERT_EQ(k, 0);
k = waitpid(-1, &s, WNOHANG);
ASSERT_NE(k, -1);
ASSERT_NE(k, 0);
ASSERT_NE(k, pid);
ASSERT_EQ(WIFEXITED(s), 1);
ASSERT_EQ(WEXITSTATUS(s), 0);
+ k = waitpid(-1, &s, 0);
+ ASSERT_EQ(k, pid);
+ ASSERT_EQ(WIFSTOPPED(s), 1);
+ ASSERT_EQ(WSTOPSIG(s), SIGTRAP);
+ k = waitpid(-1, &s, WNOHANG);
+ ASSERT_EQ(k, 0);
+ k = ptrace(PTRACE_CONT, pid, 0L, 0L);
+ ASSERT_EQ(k, 0);
+ k = waitpid(-1, &s, 0);
+ ASSERT_EQ(k, pid);
+ ASSERT_EQ(WIFSTOPPED(s), 1);
+ ASSERT_EQ(WSTOPSIG(s), SIGSTOP);
+ k = waitpid(-1, &s, WNOHANG);
+ ASSERT_EQ(k, 0);
+ k = ptrace(PTRACE_CONT, pid, 0L, 0L);
+ ASSERT_EQ(k, 0);
+ k = waitpid(-1, &s, 0);
+ ASSERT_EQ(k, pid);
+ ASSERT_EQ(WIFEXITED(s), 1);
+ ASSERT_EQ(WEXITSTATUS(s), 1);
+ k = waitpid(-1, NULL, 0);
+ ASSERT_EQ(k, -1);
+ ASSERT_EQ(errno, ECHILD);
+}
+
+/*
+ * Same test as previous, except that
+ * the group leader is ptraced first,
+ * but this time with PTRACE_O_TRACEEXIT,
+ * and the thread that does execve is
+ * not yet ptraced. This exercises the
+ * code block in de_thread where the
+ * if (!thread_group_leader(tsk)) {
+ * is executed and enters a wait state.
+ */
+static long thread2_tid;
+static void *thread2(void *arg)
+{
+ thread2_tid = syscall(__NR_gettid);
+ sleep(2);
+ execlp("false", "false", NULL);
+ return NULL;
+}
+
+TEST(attach2)
+{
+ int s, k, pid = fork();
+
+ if (!pid) {
+ pthread_t pt;
+
+ pthread_create(&pt, NULL, thread2, NULL);
+ pthread_join(pt, NULL);
+ return;
+ }
+
sleep(1);
k = ptrace(PTRACE_ATTACH, pid, 0L, 0L);
ASSERT_EQ(k, 0);
@@ -72,12 +153,46 @@ TEST(attach)
ASSERT_EQ(k, pid);
ASSERT_EQ(WIFSTOPPED(s), 1);
ASSERT_EQ(WSTOPSIG(s), SIGSTOP);
- k = ptrace(PTRACE_DETACH, pid, 0L, 0L);
+ k = ptrace(PTRACE_SETOPTIONS, pid, 0L, PTRACE_O_TRACEEXIT);
+ ASSERT_EQ(k, 0);
+ thread2_tid = ptrace(PTRACE_PEEKDATA, pid, &thread2_tid, 0L);
+ ASSERT_NE(thread2_tid, -1);
+ ASSERT_NE(thread2_tid, 0);
+ ASSERT_NE(thread2_tid, pid);
+ k = waitpid(-1, &s, WNOHANG);
+ ASSERT_EQ(k, 0);
+ sleep(2);
+ /* deadlock may happen here */
+ k = ptrace(PTRACE_ATTACH, thread2_tid, 0L, 0L);
+ ASSERT_EQ(k, 0);
+ k = waitpid(-1, &s, WNOHANG);
+ ASSERT_EQ(k, pid);
+ ASSERT_EQ(WIFSTOPPED(s), 1);
+ ASSERT_EQ(WSTOPSIG(s), SIGTRAP);
+ k = waitpid(-1, &s, WNOHANG);
+ ASSERT_EQ(k, 0);
+ k = ptrace(PTRACE_CONT, pid, 0L, 0L);
+ ASSERT_EQ(k, 0);
+ k = waitpid(-1, &s, 0);
+ ASSERT_EQ(k, pid);
+ ASSERT_EQ(WIFSTOPPED(s), 1);
+ ASSERT_EQ(WSTOPSIG(s), SIGTRAP);
+ k = waitpid(-1, &s, WNOHANG);
+ ASSERT_EQ(k, 0);
+ k = ptrace(PTRACE_CONT, pid, 0L, 0L);
+ ASSERT_EQ(k, 0);
+ k = waitpid(-1, &s, 0);
+ ASSERT_EQ(k, pid);
+ ASSERT_EQ(WIFSTOPPED(s), 1);
+ ASSERT_EQ(WSTOPSIG(s), SIGSTOP);
+ k = waitpid(-1, &s, WNOHANG);
+ ASSERT_EQ(k, 0);
+ k = ptrace(PTRACE_CONT, pid, 0L, 0L);
ASSERT_EQ(k, 0);
k = waitpid(-1, &s, 0);
ASSERT_EQ(k, pid);
ASSERT_EQ(WIFEXITED(s), 1);
- ASSERT_EQ(WEXITSTATUS(s), 0);
+ ASSERT_EQ(WEXITSTATUS(s), 1);
k = waitpid(-1, NULL, 0);
ASSERT_EQ(k, -1);
ASSERT_EQ(errno, ECHILD);