[PATCH RFC v2 2/5] exec: introduce struct task_exec_state and relocate dumpable

[Christian Brauner <brauner@kernel.org>]

Introduce struct task_exec_state, a per-task RCU-protected structure
that holds the dumpable mode and stays attached to the task for its
full lifetime.

task_exec_state_rcu() is the canonical reader: asserts RCU or
task_lock is held, WARNs on a NULL state, returns the
rcu_dereference()'d pointer.

Signed-off-by: Christian Brauner (Amutable) <brauner@kernel.org>
Signed-off-by: Christian Brauner <brauner@kernel.org>
---
 include/linux/sched.h            |   3 ++
 include/linux/sched/exec_state.h |  31 ++++++++++++
 kernel/Makefile                  |   2 +-
 kernel/exec_state.c              | 105 +++++++++++++++++++++++++++++++++++++++
 4 files changed, 140 insertions(+), 1 deletion(-)

diff --git a/include/linux/sched.h b/include/linux/sched.h
index ee06cba5c6f5..d895c3ff2154 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -962,6 +962,9 @@ struct task_struct {
 	struct mm_struct		*mm;
 	struct mm_struct		*active_mm;
 
+	/* Exec-time state outliving exit_mm(); see <linux/sched/exec_state.h>. */
+	struct task_exec_state __rcu	*exec_state;
+
 	int				exit_state;
 	int				exit_code;
 	int				exit_signal;
diff --git a/include/linux/sched/exec_state.h b/include/linux/sched/exec_state.h
new file mode 100644
index 000000000000..7a267efc34d3
--- /dev/null
+++ b/include/linux/sched/exec_state.h
@@ -0,0 +1,31 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _LINUX_SCHED_EXEC_STATE_H
+#define _LINUX_SCHED_EXEC_STATE_H
+
+#include <linux/init.h>
+#include <linux/rcupdate.h>
+#include <linux/refcount.h>
+#include <linux/sched/coredump.h>
+#include <linux/user_namespace.h>
+
+struct task_exec_state {
+	refcount_t		count;
+	enum task_dumpable	dumpable;
+	struct user_namespace	*user_ns;
+	struct rcu_head		rcu;
+};
+
+struct task_exec_state *alloc_task_exec_state(void);
+void put_task_exec_state(struct task_exec_state *es);
+struct task_exec_state *task_exec_state_rcu(const struct task_struct *tsk);
+struct task_exec_state *task_exec_state_replace(struct task_struct *tsk,
+						struct task_exec_state *exec_state);
+void task_exec_state_set_dumpable(enum task_dumpable value);
+enum task_dumpable task_exec_state_get_dumpable(struct task_struct *task);
+void copy_exec_state(struct task_struct *tsk);
+void __init exec_state_init(void);
+
+DEFINE_FREE(put_task_exec_state, struct task_exec_state *,
+	    if (_T) put_task_exec_state(_T))
+
+#endif /* _LINUX_SCHED_EXEC_STATE_H */
diff --git a/kernel/Makefile b/kernel/Makefile
index 6785982013dc..1e1a31673577 100644
--- a/kernel/Makefile
+++ b/kernel/Makefile
@@ -3,7 +3,7 @@
 # Makefile for the linux kernel.
 #
 
-obj-y     = fork.o exec_domain.o panic.o \
+obj-y     = fork.o exec_domain.o exec_state.o panic.o \
 	    cpu.o exit.o softirq.o resource.o \
 	    sysctl.o capability.o ptrace.o user.o \
 	    signal.o sys.o umh.o workqueue.o pid.o task_work.o \
diff --git a/kernel/exec_state.c b/kernel/exec_state.c
new file mode 100644
index 000000000000..85178b1d2c57
--- /dev/null
+++ b/kernel/exec_state.c
@@ -0,0 +1,105 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <linux/init.h>
+#include <linux/rcupdate.h>
+#include <linux/refcount.h>
+#include <linux/sched.h>
+#include <linux/sched/coredump.h>
+#include <linux/sched/exec_state.h>
+#include <linux/sched/signal.h>
+#include <linux/slab.h>
+
+static struct kmem_cache *task_exec_state_cachep;
+
+static void __free_task_exec_state(struct rcu_head *rcu)
+{
+	struct task_exec_state *es = container_of(rcu, struct task_exec_state, rcu);
+
+	kmem_cache_free(task_exec_state_cachep, es);
+}
+
+void put_task_exec_state(struct task_exec_state *es)
+{
+	if (es && refcount_dec_and_test(&es->count))
+		call_rcu(&es->rcu, __free_task_exec_state);
+}
+
+struct task_exec_state *alloc_task_exec_state(void)
+{
+	struct task_exec_state *es;
+
+	es = kmem_cache_alloc(task_exec_state_cachep, GFP_KERNEL);
+	if (!es)
+		return NULL;
+	refcount_set(&es->count, 1);
+	es->dumpable = TASK_DUMPABLE_OFF;
+	return es;
+}
+
+struct task_exec_state *task_exec_state_rcu(const struct task_struct *tsk)
+{
+	RCU_LOCKDEP_WARN(!rcu_read_lock_held() && !lockdep_is_held(&tsk->alloc_lock),
+			 "task_exec_state_rcu() requires RCU or task_lock");
+	WARN_ON_ONCE(!tsk->exec_state);
+	return rcu_dereference(tsk->exec_state);
+}
+
+struct task_exec_state *task_exec_state_replace(struct task_struct *tsk,
+						struct task_exec_state *exec_state)
+{
+	/*
+	 * Updates must hold both locks so callers needing a consistent
+	 * snapshot of mm + dumpability are covered.
+	 */
+	lockdep_assert_held(&tsk->alloc_lock);
+	lockdep_assert_held_write(&tsk->signal->exec_update_lock);
+
+	return rcu_replace_pointer(tsk->exec_state, exec_state, true);
+}
+
+/*
+ * exec_state is anchored to the execve() that established the current
+ * privilege domain.  All clone() variants refcount-share it; only a
+ * subsequent execve() in the child swaps in a fresh one.
+ */
+void copy_exec_state(struct task_struct *tsk)
+{
+	struct task_exec_state *es = current->exec_state;
+
+	refcount_inc(&es->count);
+	rcu_assign_pointer(tsk->exec_state, es);
+}
+
+/*
+ * Store TASK_DUMPABLE_* on current->exec_state.  All callers
+ * (commit_creds, begin_new_exec, prctl(PR_SET_DUMPABLE)) act on the
+ * running task, which guarantees ->exec_state is allocated and cannot
+ * be replaced under us.
+ */
+void task_exec_state_set_dumpable(enum task_dumpable value)
+{
+	struct task_exec_state *es;
+
+	if (WARN_ON(value > TASK_DUMPABLE_ROOT))
+		value = TASK_DUMPABLE_OFF;
+
+	es = rcu_dereference_protected(current->exec_state, true);
+	WRITE_ONCE(es->dumpable, value);
+}
+
+enum task_dumpable task_exec_state_get_dumpable(struct task_struct *task)
+{
+	struct task_exec_state *es;
+
+	guard(rcu)();
+	es = rcu_dereference(task->exec_state);
+	return READ_ONCE(es->dumpable);
+}
+
+void __init exec_state_init(void)
+{
+	task_exec_state_cachep = kmem_cache_create("task_exec_state",
+			sizeof(struct task_exec_state), 0,
+			SLAB_HWCACHE_ALIGN | SLAB_PANIC | SLAB_ACCOUNT,
+			NULL);
+}

-- 
2.47.3