@@ -1078,14 +1078,26 @@ static int de_thread(struct task_struct *tsk)
struct signal_struct *sig = tsk->signal;
struct sighand_struct *oldsighand = tsk->sighand;
spinlock_t *lock = &oldsighand->siglock;
+ struct task_struct *t = tsk;
if (thread_group_empty(tsk))
goto no_thread_group;
+ spin_lock_irq(lock);
+ while_each_thread(tsk, t) {
+ if (unlikely(t->ptrace))
+ sig->unsafe_execve_in_progress = true;
+ }
+
+ if (unlikely(sig->unsafe_execve_in_progress)) {
+ spin_unlock_irq(lock);
+ mutex_unlock(&sig->exec_guard_mutex);
+ spin_lock_irq(lock);
+ }
+
/*
* Kill all other threads in the thread group.
*/
- spin_lock_irq(lock);
if (signal_group_exit(sig)) {
/*
* Another group action in progress, just
@@ -1429,22 +1441,30 @@ void finalize_exec(struct linux_binprm *bprm)
EXPORT_SYMBOL(finalize_exec);
/*
- * Prepare credentials and lock ->cred_guard_mutex.
+ * Prepare credentials and lock ->exec_guard_mutex.
* install_exec_creds() commits the new creds and drops the lock.
* Or, if exec fails before, free_bprm() should release ->cred and
* and unlock.
*/
static int prepare_bprm_creds(struct linux_binprm *bprm)
{
- if (mutex_lock_interruptible(¤t->signal->cred_guard_mutex))
+ int ret;
+
+ if (mutex_lock_interruptible(¤t->signal->exec_guard_mutex))
return -ERESTARTNOINTR;
+ ret = -EAGAIN;
+ if (unlikely(current->signal->unsafe_execve_in_progress))
+ goto out;
+
bprm->cred = prepare_exec_creds();
if (likely(bprm->cred))
return 0;
- mutex_unlock(¤t->signal->cred_guard_mutex);
- return -ENOMEM;
+ ret = -ENOMEM;
+out:
+ mutex_unlock(¤t->signal->exec_guard_mutex);
+ return ret;
}
static void free_bprm(struct linux_binprm *bprm)
@@ -1453,7 +1473,10 @@ static void free_bprm(struct linux_binprm *bprm)
if (bprm->cred) {
if (bprm->called_exec_mmap)
mutex_unlock(¤t->signal->exec_update_mutex);
- mutex_unlock(¤t->signal->cred_guard_mutex);
+ if (unlikely(current->signal->unsafe_execve_in_progress))
+ mutex_lock(¤t->signal->exec_guard_mutex);
+ current->signal->unsafe_execve_in_progress = false;
+ mutex_unlock(¤t->signal->exec_guard_mutex);
abort_creds(bprm->cred);
}
if (bprm->file) {
@@ -1497,19 +1520,22 @@ void install_exec_creds(struct linux_binprm *bprm)
if (get_dumpable(current->mm) != SUID_DUMP_USER)
perf_event_exit_task(current);
/*
- * cred_guard_mutex must be held at least to this point to prevent
+ * exec_guard_mutex must be held at least to this point to prevent
* ptrace_attach() from altering our determination of the task's
* credentials; any time after this it may be unlocked.
*/
security_bprm_committed_creds(bprm);
mutex_unlock(¤t->signal->exec_update_mutex);
- mutex_unlock(¤t->signal->cred_guard_mutex);
+ if (unlikely(current->signal->unsafe_execve_in_progress))
+ mutex_lock(¤t->signal->exec_guard_mutex);
+ current->signal->unsafe_execve_in_progress = false;
+ mutex_unlock(¤t->signal->exec_guard_mutex);
}
EXPORT_SYMBOL(install_exec_creds);
/*
* determine how safe it is to execute the proposed program
- * - the caller must hold ->cred_guard_mutex to protect against
+ * - the caller must hold ->exec_guard_mutex to protect against
* PTRACE_ATTACH or seccomp thread-sync
*/
static void check_unsafe_exec(struct linux_binprm *bprm)
@@ -2680,14 +2680,30 @@ static ssize_t proc_pid_attr_write(struct file * file, const char __user * buf,
}
/* Guard against adverse ptrace interaction */
- rv = mutex_lock_interruptible(¤t->signal->cred_guard_mutex);
+ rv = mutex_lock_interruptible(¤t->signal->exec_guard_mutex);
if (rv < 0)
goto out_free;
+ /*
+ * BIG FAT WARNING - Fragile code ahead.
+ * Please do not insert any code between these two
+ * if statements. It may happen that execve has to
+ * release the exec_guard_mutex in order to prevent
+ * deadlocks. In that case unsafe_execve_in_progress
+ * will be set. If that happens you cannot assume that
+ * the usual guarantees implied by exec_guard_mutex
+ * are valid. Just return -EAGAIN in that case and
+ * unlock the mutex immediately.
+ */
+ rv = -EAGAIN;
+ if (unlikely(current->signal->unsafe_execve_in_progress))
+ goto out_unlock;
+
rv = security_setprocattr(PROC_I(inode)->op.lsm,
file->f_path.dentry->d_name.name, page,
count);
- mutex_unlock(¤t->signal->cred_guard_mutex);
+out_unlock:
+ mutex_unlock(¤t->signal->exec_guard_mutex);
out_free:
kfree(page);
out:
@@ -212,6 +212,13 @@ struct signal_struct {
#endif
/*
+ * Set while execve is executing but is *not* holding
+ * exec_guard_mutex to avoid possible dead-locks.
+ * Only valid when exec_guard_mutex is held.
+ */
+ bool unsafe_execve_in_progress;
+
+ /*
* Thread is the potential origin of an oom condition; kill first on
* oom
*/
@@ -222,11 +229,8 @@ struct signal_struct {
struct mm_struct *oom_mm; /* recorded mm when the thread group got
* killed by the oom killer */
- struct mutex cred_guard_mutex; /* guard against foreign influences on
- * credential calculations
- * (notably. ptrace)
- * Deprecated do not use in new code.
- * Use exec_update_mutex instead.
+ struct mutex exec_guard_mutex; /* Held while execve runs, except when
+ * a sibling thread is being traced.
*/
struct mutex exec_update_mutex; /* Held while task_struct is being
* updated during exec, and may have
@@ -25,7 +25,7 @@
},
.multiprocess = HLIST_HEAD_INIT,
.rlim = INIT_RLIMITS,
- .cred_guard_mutex = __MUTEX_INITIALIZER(init_signals.cred_guard_mutex),
+ .exec_guard_mutex = __MUTEX_INITIALIZER(init_signals.exec_guard_mutex),
.exec_update_mutex = __MUTEX_INITIALIZER(init_signals.exec_update_mutex),
#ifdef CONFIG_POSIX_TIMERS
.posix_timers = LIST_HEAD_INIT(init_signals.posix_timers),
@@ -295,7 +295,7 @@ struct cred *prepare_creds(void)
/*
* Prepare credentials for current to perform an execve()
- * - The caller must hold ->cred_guard_mutex
+ * - The caller must hold ->exec_guard_mutex
*/
struct cred *prepare_exec_creds(void)
{
@@ -1593,7 +1593,7 @@ static int copy_signal(unsigned long clone_flags, struct task_struct *tsk)
sig->oom_score_adj = current->signal->oom_score_adj;
sig->oom_score_adj_min = current->signal->oom_score_adj_min;
- mutex_init(&sig->cred_guard_mutex);
+ mutex_init(&sig->exec_guard_mutex);
mutex_init(&sig->exec_update_mutex);
return 0;
@@ -392,9 +392,24 @@ static int ptrace_attach(struct task_struct *task, long request,
* under ptrace.
*/
retval = -ERESTARTNOINTR;
- if (mutex_lock_interruptible(&task->signal->cred_guard_mutex))
+ if (mutex_lock_interruptible(&task->signal->exec_guard_mutex))
goto out;
+ /*
+ * BIG FAT WARNING - Fragile code ahead.
+ * Please do not insert any code between these two
+ * if statements. It may happen that execve has to
+ * release the exec_guard_mutex in order to prevent
+ * deadlocks. In that case unsafe_execve_in_progress
+ * will be set. If that happens you cannot assume that
+ * the usual guarantees implied by exec_guard_mutex
+ * are valid. Just return -EAGAIN in that case and
+ * unlock the mutex immediately.
+ */
+ retval = -EAGAIN;
+ if (unlikely(task->signal->unsafe_execve_in_progress))
+ goto unlock_creds;
+
task_lock(task);
retval = __ptrace_may_access(task, PTRACE_MODE_ATTACH_REALCREDS);
task_unlock(task);
@@ -447,7 +462,7 @@ static int ptrace_attach(struct task_struct *task, long request,
unlock_tasklist:
write_unlock_irq(&tasklist_lock);
unlock_creds:
- mutex_unlock(&task->signal->cred_guard_mutex);
+ mutex_unlock(&task->signal->exec_guard_mutex);
out:
if (!retval) {
/*
@@ -472,10 +487,29 @@ static int ptrace_attach(struct task_struct *task, long request,
*/
static int ptrace_traceme(void)
{
- int ret = -EPERM;
+ int ret;
+
+ if (mutex_lock_interruptible(¤t->signal->exec_guard_mutex))
+ return -ERESTARTNOINTR;
+
+ /*
+ * BIG FAT WARNING - Fragile code ahead.
+ * Please do not insert any code between these two
+ * if statements. It may happen that execve has to
+ * release the exec_guard_mutex in order to prevent
+ * deadlocks. In that case unsafe_execve_in_progress
+ * will be set. If that happens you cannot assume that
+ * the usual guarantees implied by exec_guard_mutex
+ * are valid. Just return -EAGAIN in that case and
+ * unlock the mutex immediately.
+ */
+ ret = -EAGAIN;
+ if (unlikely(current->signal->unsafe_execve_in_progress))
+ goto unlock_creds;
write_lock_irq(&tasklist_lock);
/* Are we already being traced? */
+ ret = -EPERM;
if (!current->ptrace) {
ret = security_ptrace_traceme(current->parent);
/*
@@ -490,6 +524,8 @@ static int ptrace_traceme(void)
}
write_unlock_irq(&tasklist_lock);
+unlock_creds:
+ mutex_unlock(¤t->signal->exec_guard_mutex);
return ret;
}
@@ -329,7 +329,7 @@ static int is_ancestor(struct seccomp_filter *parent,
/**
* seccomp_can_sync_threads: checks if all threads can be synchronized
*
- * Expects sighand and cred_guard_mutex locks to be held.
+ * Expects sighand and exec_guard_mutex locks to be held.
*
* Returns 0 on success, -ve on error, or the pid of a thread which was
* either not in the correct seccomp mode or did not have an ancestral
@@ -339,9 +339,22 @@ static inline pid_t seccomp_can_sync_threads(void)
{
struct task_struct *thread, *caller;
- BUG_ON(!mutex_is_locked(¤t->signal->cred_guard_mutex));
+ BUG_ON(!mutex_is_locked(¤t->signal->exec_guard_mutex));
assert_spin_locked(¤t->sighand->siglock);
+ /*
+ * BIG FAT WARNING - Fragile code ahead.
+ * It may happen that execve has to release the
+ * exec_guard_mutex in order to prevent deadlocks.
+ * In that case unsafe_execve_in_progress will be set.
+ * If that happens you cannot assume that the usual
+ * guarantees implied by exec_guard_mutex are valid.
+ * Just return -EAGAIN in that case and unlock the mutex
+ * immediately.
+ */
+ if (unlikely(current->signal->unsafe_execve_in_progress))
+ return -EAGAIN;
+
/* Validate all threads being eligible for synchronization. */
caller = current;
for_each_thread(caller, thread) {
@@ -371,7 +384,7 @@ static inline pid_t seccomp_can_sync_threads(void)
/**
* seccomp_sync_threads: sets all threads to use current's filter
*
- * Expects sighand and cred_guard_mutex locks to be held, and for
+ * Expects sighand and exec_guard_mutex locks to be held, and for
* seccomp_can_sync_threads() to have returned success already
* without dropping the locks.
*
@@ -380,7 +393,7 @@ static inline void seccomp_sync_threads(unsigned long flags)
{
struct task_struct *thread, *caller;
- BUG_ON(!mutex_is_locked(¤t->signal->cred_guard_mutex));
+ BUG_ON(!mutex_is_locked(¤t->signal->exec_guard_mutex));
assert_spin_locked(¤t->sighand->siglock);
/* Synchronize all threads. */
@@ -1319,7 +1332,7 @@ static long seccomp_set_mode_filter(unsigned int flags,
* while another thread is in the middle of calling exec.
*/
if (flags & SECCOMP_FILTER_FLAG_TSYNC &&
- mutex_lock_killable(¤t->signal->cred_guard_mutex))
+ mutex_lock_killable(¤t->signal->exec_guard_mutex))
goto out_put_fd;
spin_lock_irq(¤t->sighand->siglock);
@@ -1337,7 +1350,7 @@ static long seccomp_set_mode_filter(unsigned int flags,
out:
spin_unlock_irq(¤t->sighand->siglock);
if (flags & SECCOMP_FILTER_FLAG_TSYNC)
- mutex_unlock(¤t->signal->cred_guard_mutex);
+ mutex_unlock(¤t->signal->exec_guard_mutex);
out_put_fd:
if (flags & SECCOMP_FILTER_FLAG_NEW_LISTENER) {
if (ret) {
This removes the last users of cred_guard_mutex and replaces it with a new mutex exec_guard_mutex, and a boolean unsafe_execve_in_progress. This addresses the case when at least one of the sibling threads is traced, and therefore the trace process may dead-lock in ptrace_attach, but de_thread will need to wait for the tracer to continue execution. The solution is to detect this situation and make ptrace_attach and similar functions return -EAGAIN, but only in a situation where a dead-lock is imminent. This means this is an API change, but only when the process is traced while execve happens in a multi-threaded application. See tools/testing/selftests/ptrace/vmaccess.c for a test case that gets fixed by this change. Signed-off-by: Bernd Edlinger <bernd.edlinger@hotmail.de> --- fs/exec.c | 44 +++++++++++++++++++++++++++++++++++--------- fs/proc/base.c | 20 ++++++++++++++++++-- include/linux/sched/signal.h | 14 +++++++++----- init/init_task.c | 2 +- kernel/cred.c | 2 +- kernel/fork.c | 2 +- kernel/ptrace.c | 42 +++++++++++++++++++++++++++++++++++++++--- kernel/seccomp.c | 25 +++++++++++++++++++------ 8 files changed, 123 insertions(+), 28 deletions(-) v7: Added "big fat" warning comments, made the change in proc_pid_attr_write a bit more readable.