1 files changed, 82 insertions, 19 deletions

diff --git a/kernel/sys.c b/kernel/sys.c
index 1e28b40053ce..8b58eece4e58 100644
--- a/kernel/sys.c
+++ b/kernel/sys.c
@@ -1734,6 +1734,7 @@ SYSCALL_DEFINE4(prlimit64, pid_t, pid, unsigned int, resource,
 	struct rlimit old, new;
 	struct task_struct *tsk;
 	unsigned int checkflags = 0;
+	bool need_tasklist;
 	int ret;
 
 	if (old_rlim)
@@ -1760,8 +1761,25 @@ SYSCALL_DEFINE4(prlimit64, pid_t, pid, unsigned int, resource,
 	get_task_struct(tsk);
 	rcu_read_unlock();
 
-	ret = do_prlimit(tsk, resource, new_rlim ? &new : NULL,
-			old_rlim ? &old : NULL);
+	need_tasklist = !same_thread_group(tsk, current);
+	if (need_tasklist) {
+		/*
+		 * Ensure we can't race with group exit or de_thread(),
+		 * so tsk->group_leader can't be freed or changed until
+		 * read_unlock(tasklist_lock) below.
+		 */
+		read_lock(&tasklist_lock);
+		if (!pid_alive(tsk))
+			ret = -ESRCH;
+	}
+
+	if (!ret) {
+		ret = do_prlimit(tsk, resource, new_rlim ? &new : NULL,
+				old_rlim ? &old : NULL);
+	}
+
+	if (need_tasklist)
+		read_unlock(&tasklist_lock);
 
 	if (!ret && old_rlim) {
 		rlim_to_rlim64(&old, &old64);
@@ -2392,9 +2410,9 @@ static inline unsigned long get_current_mdwe(void)
 {
 	unsigned long ret = 0;
 
-	if (test_bit(MMF_HAS_MDWE, &current->mm->flags))
+	if (mm_flags_test(MMF_HAS_MDWE, current->mm))
 		ret |= PR_MDWE_REFUSE_EXEC_GAIN;
-	if (test_bit(MMF_HAS_MDWE_NO_INHERIT, &current->mm->flags))
+	if (mm_flags_test(MMF_HAS_MDWE_NO_INHERIT, current->mm))
 		ret |= PR_MDWE_NO_INHERIT;
 
 	return ret;
@@ -2427,9 +2445,9 @@ static inline int prctl_set_mdwe(unsigned long bits, unsigned long arg3,
 		return -EPERM; /* Cannot unset the flags */
 
 	if (bits & PR_MDWE_NO_INHERIT)
-		set_bit(MMF_HAS_MDWE_NO_INHERIT, &current->mm->flags);
+		mm_flags_set(MMF_HAS_MDWE_NO_INHERIT, current->mm);
 	if (bits & PR_MDWE_REFUSE_EXEC_GAIN)
-		set_bit(MMF_HAS_MDWE, &current->mm->flags);
+		mm_flags_set(MMF_HAS_MDWE, current->mm);
 
 	return 0;
 }
@@ -2452,6 +2470,51 @@ static int prctl_get_auxv(void __user *addr, unsigned long len)
 	return sizeof(mm->saved_auxv);
 }
 
+static int prctl_get_thp_disable(unsigned long arg2, unsigned long arg3,
+				 unsigned long arg4, unsigned long arg5)
+{
+	struct mm_struct *mm = current->mm;
+
+	if (arg2 || arg3 || arg4 || arg5)
+		return -EINVAL;
+
+	/* If disabled, we return "1 | flags", otherwise 0. */
+	if (mm_flags_test(MMF_DISABLE_THP_COMPLETELY, mm))
+		return 1;
+	else if (mm_flags_test(MMF_DISABLE_THP_EXCEPT_ADVISED, mm))
+		return 1 | PR_THP_DISABLE_EXCEPT_ADVISED;
+	return 0;
+}
+
+static int prctl_set_thp_disable(bool thp_disable, unsigned long flags,
+				 unsigned long arg4, unsigned long arg5)
+{
+	struct mm_struct *mm = current->mm;
+
+	if (arg4 || arg5)
+		return -EINVAL;
+
+	/* Flags are only allowed when disabling. */
+	if ((!thp_disable && flags) || (flags & ~PR_THP_DISABLE_EXCEPT_ADVISED))
+		return -EINVAL;
+	if (mmap_write_lock_killable(current->mm))
+		return -EINTR;
+	if (thp_disable) {
+		if (flags & PR_THP_DISABLE_EXCEPT_ADVISED) {
+			mm_flags_clear(MMF_DISABLE_THP_COMPLETELY, mm);
+			mm_flags_set(MMF_DISABLE_THP_EXCEPT_ADVISED, mm);
+		} else {
+			mm_flags_set(MMF_DISABLE_THP_COMPLETELY, mm);
+			mm_flags_clear(MMF_DISABLE_THP_EXCEPT_ADVISED, mm);
+		}
+	} else {
+		mm_flags_clear(MMF_DISABLE_THP_COMPLETELY, mm);
+		mm_flags_clear(MMF_DISABLE_THP_EXCEPT_ADVISED, mm);
+	}
+	mmap_write_unlock(current->mm);
+	return 0;
+}
+
 SYSCALL_DEFINE5(prctl, int, option, unsigned long, arg2, unsigned long, arg3,
 		unsigned long, arg4, unsigned long, arg5)
 {
@@ -2470,7 +2533,17 @@ SYSCALL_DEFINE5(prctl, int, option, unsigned long, arg2, unsigned long, arg3,
 			error = -EINVAL;
 			break;
 		}
+		/*
+		 * Ensure that either:
+		 *
+		 * 1. Subsequent getppid() calls reflect the parent process having died.
+		 * 2. forget_original_parent() will send the new me->pdeath_signal.
+		 *
+		 * Also prevent the read of me->pdeath_signal from being a data race.
+		 */
+		read_lock(&tasklist_lock);
 		me->pdeath_signal = arg2;
+		read_unlock(&tasklist_lock);
 		break;
 	case PR_GET_PDEATHSIG:
 		error = put_user(me->pdeath_signal, (int __user *)arg2);
@@ -2625,20 +2698,10 @@ SYSCALL_DEFINE5(prctl, int, option, unsigned long, arg2, unsigned long, arg3,
 			return -EINVAL;
 		return task_no_new_privs(current) ? 1 : 0;
 	case PR_GET_THP_DISABLE:
-		if (arg2 || arg3 || arg4 || arg5)
-			return -EINVAL;
-		error = !!test_bit(MMF_DISABLE_THP, &me->mm->flags);
+		error = prctl_get_thp_disable(arg2, arg3, arg4, arg5);
 		break;
 	case PR_SET_THP_DISABLE:
-		if (arg3 || arg4 || arg5)
-			return -EINVAL;
-		if (mmap_write_lock_killable(me->mm))
-			return -EINTR;
-		if (arg2)
-			set_bit(MMF_DISABLE_THP, &me->mm->flags);
-		else
-			clear_bit(MMF_DISABLE_THP, &me->mm->flags);
-		mmap_write_unlock(me->mm);
+		error = prctl_set_thp_disable(arg2, arg3, arg4, arg5);
 		break;
 	case PR_MPX_ENABLE_MANAGEMENT:
 	case PR_MPX_DISABLE_MANAGEMENT:
@@ -2770,7 +2833,7 @@ SYSCALL_DEFINE5(prctl, int, option, unsigned long, arg2, unsigned long, arg3,
 		if (arg2 || arg3 || arg4 || arg5)
 			return -EINVAL;
 
-		error = !!test_bit(MMF_VM_MERGE_ANY, &me->mm->flags);
+		error = !!mm_flags_test(MMF_VM_MERGE_ANY, me->mm);
 		break;
 #endif
 	case PR_RISCV_V_SET_CONTROL: