diff --git a/include/linux/seccomp.h b/include/linux/seccomp.h
index 4054b0994071..9ff98b4bfe2e 100644
--- a/include/linux/seccomp.h
+++ b/include/linux/seccomp.h
@@ -14,11 +14,11 @@ struct seccomp_filter;
*
* @mode: indicates one of the valid values above for controlled
* system calls available to a process.
- * @filter: The metadata and ruleset for determining what system calls
- * are allowed for a task.
+ * @filter: must always point to a valid seccomp-filter or NULL as it is
+ * accessed without locking during system call entry.
*
* @filter must only be accessed from the context of current as there
- * is no locking.
+ * is no read locking.
*/
struct seccomp {
int mode;diff --git a/kernel/fork.c b/kernel/fork.c
index d2799d1fc952..d41bdc8700b6 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -315,6 +315,15 @@ static struct task_struct *dup_task_struct(struct task_struct *orig)
goto free_ti;
tsk->stack = ti;
+#ifdef CONFIG_SECCOMP
+ /*
+ * We must handle setting up seccomp filters once we're under
+ * the sighand lock in case orig has changed between now and
+ * then. Until then, filter must be NULL to avoid messing up
+ * the usage counts on the error path calling free_task.
+ */
+ tsk->seccomp.filter = NULL;
+#endif
setup_thread_stack(tsk, orig);
clear_user_return_notifier(tsk);
@@ -1081,6 +1090,24 @@ static int copy_signal(unsigned long clone_flags, struct task_struct *tsk)
return 0;
}
+static void copy_seccomp(struct task_struct *p)
+{
+#ifdef CONFIG_SECCOMP
+ /*
+ * Must be called with sighand->lock held, which is common to
+ * all threads in the group. Regardless, nothing special is
+ * needed for the child since it is not yet in the tasklist.
+ */
+ BUG_ON(!spin_is_locked(¤t->sighand->siglock));
+
+ get_seccomp_filter(current);
+ p->seccomp = current->seccomp;
+
+ if (p->seccomp.mode != SECCOMP_MODE_DISABLED)
+ set_tsk_thread_flag(p, TIF_SECCOMP);
+#endif
+}
+
SYSCALL_DEFINE1(set_tid_address, int __user *, tidptr)
{
current->clear_child_tid = tidptr;@@ -1196,7 +1223,6 @@ static struct task_struct *copy_process(unsigned long clone_flags,
goto fork_out;
ftrace_graph_init_task(p);
- get_seccomp_filter(p);
rt_mutex_init_task(p);
@@ -1437,6 +1463,12 @@ static struct task_struct *copy_process(unsigned long clone_flags,
spin_lock(¤t->sighand->siglock);
/*
+ * Copy seccomp details explicitly here, in case they were changed
+ * before holding sighand lock.
+ */
+ copy_seccomp(p);
+
+ /*
* Process group and session signals need to be delivered to just the
* parent before the fork or both the parent and the child after the
* fork. Restart if a signal comes in before we add the new process to
diff --git a/kernel/seccomp.c b/kernel/seccomp.c
index edc8c79ed16d..405eb72dfe35 100644
--- a/kernel/seccomp.c
+++ b/kernel/seccomp.c
@@ -172,12 +172,12 @@ static int seccomp_check_filter(struct sock_filter *filter, unsigned int flen)
*/
static u32 seccomp_run_filters(int syscall)
{
- struct seccomp_filter *f;
+ struct seccomp_filter *f = smp_load_acquire(¤t->seccomp.filter);
struct seccomp_data sd;
u32 ret = SECCOMP_RET_ALLOW;
/* Ensure unexpected behavior doesn't result in failing open. */
- if (WARN_ON(current->seccomp.filter == NULL))
+ if (unlikely(WARN_ON(f == NULL)))
return SECCOMP_RET_KILL;
populate_seccomp_data(&sd);@@ -186,7 +186,7 @@ static u32 seccomp_run_filters(int syscall)
* All filters in the list are evaluated and the lowest BPF return
* value always takes priority (ignoring the DATA).
*/
- for (f = current->seccomp.filter; f; f = f->prev) {
+ for (; f; f = f->prev) {
u32 cur_ret = SK_RUN_FILTER(f->prog, (void *)&sd);
if ((cur_ret & SECCOMP_RET_ACTION) < (ret & SECCOMP_RET_ACTION))@@ -312,6 +312,8 @@ out:
* seccomp_attach_filter: validate and attach filter
* @filter: seccomp filter to add to the current process
*
+ * Caller must be holding current->sighand->siglock lock.
+ *
* Returns 0 on success, -ve on error.
*/
static long seccomp_attach_filter(struct seccomp_filter *filter)
@@ -319,6 +321,8 @@ static long seccomp_attach_filter(struct seccomp_filter *filter)
unsigned long total_insns;
struct seccomp_filter *walker;
+ BUG_ON(!spin_is_locked(¤t->sighand->siglock));
+
/* Validate resulting filter length. */
total_insns = filter->prog->len;
for (walker = current->seccomp.filter; walker; walker = walker->prev)
@@ -331,7 +335,7 @@ static long seccomp_attach_filter(struct seccomp_filter *filter)
* task reference.
*/
filter->prev = current->seccomp.filter;
- current->seccomp.filter = filter;
+ smp_store_release(¤t->seccomp.filter, filter);
return 0;
}
@@ -357,7 +361,7 @@ static inline void seccomp_filter_free(struct seccomp_filter *filter)
/* put_seccomp_filter - decrements the ref count of tsk->seccomp.filter */
void put_seccomp_filter(struct task_struct *tsk)
{
- struct seccomp_filter *orig = tsk->seccomp.filter;
+ struct seccomp_filter *orig = smp_load_acquire(&tsk->seccomp.filter);
/* Clean up single-reference branches iteratively. */
while (orig && atomic_dec_and_test(&orig->usage)) {
struct seccomp_filter *freeme = orig;@@ -513,6 +517,7 @@ long prctl_get_seccomp(void)
static long seccomp_set_mode(unsigned long seccomp_mode, char __user *filter)
{
struct seccomp_filter *prepared = NULL;
+ unsigned long irqflags;
long ret = -EINVAL;
#ifdef CONFIG_SECCOMP_FILTER@@ -524,6 +529,8 @@ static long seccomp_set_mode(unsigned long seccomp_mode, char __user *filter)
}
#endif
+ spin_lock_irqsave(¤t->sighand->siglock, irqflags);
+
if (current->seccomp.mode &&
current->seccomp.mode != seccomp_mode)
goto out;
@@ -551,6 +558,7 @@ static long seccomp_set_mode(unsigned long seccomp_mode, char __user *filter)
current->seccomp.mode = seccomp_mode;
set_thread_flag(TIF_SECCOMP);
out:
+ spin_unlock_irqrestore(¤t->sighand->siglock, irqflags);
seccomp_filter_free(prepared);
return ret;
}
--
1.7.9.5