[PATCH v7 1/1] ptrace,syscall_user_dispatch: checkpoint/restore support for SUD

[Gregory Price]

Implement ptrace getter/setter interface for syscall user dispatch.

These prctl settings are presently write-only, making it impossible to
implement transparent checkpoint/restore via software like CRIU.

'on_dispatch' field is not exposed because it is a kernel-internal
only field that cannot be 'true' when returning to userland.

Signed-off-by: Gregory Price <gregory.price@xxxxxxxxxxxx>
---
 .../admin-guide/syscall-user-dispatch.rst     |  5 ++-
 include/linux/syscall_user_dispatch.h         | 18 +++++++++
 include/uapi/linux/ptrace.h                   |  9 +++++
 kernel/entry/syscall_user_dispatch.c          | 39 +++++++++++++++++++
 kernel/ptrace.c                               |  9 +++++
 5 files changed, 79 insertions(+), 1 deletion(-)

diff --git a/Documentation/admin-guide/syscall-user-dispatch.rst b/Documentation/admin-guide/syscall-user-dispatch.rst
index 60314953c728..a23ae21a1d5b 100644
--- a/Documentation/admin-guide/syscall-user-dispatch.rst
+++ b/Documentation/admin-guide/syscall-user-dispatch.rst
@@ -43,7 +43,10 @@ doesn't rely on any of the syscall ABI to make the filtering.  It uses
 only the syscall dispatcher address and the userspace key.
 
 As the ABI of these intercepted syscalls is unknown to Linux, these
-syscalls are not instrumentable via ptrace or the syscall tracepoints.
+syscalls are not instrumentable via ptrace or the syscall tracepoints,
+however an interfaces to suspend, checkpoint, and restore syscall user
+dispatch configuration has been added to ptrace to assist userland
+checkpoint/restart software.
 
 Interface
 ---------
diff --git a/include/linux/syscall_user_dispatch.h b/include/linux/syscall_user_dispatch.h
index a0ae443fb7df..5de2d64ace19 100644
--- a/include/linux/syscall_user_dispatch.h
+++ b/include/linux/syscall_user_dispatch.h
@@ -22,6 +22,12 @@ int set_syscall_user_dispatch(unsigned long mode, unsigned long offset,
 #define clear_syscall_work_syscall_user_dispatch(tsk) \
 	clear_task_syscall_work(tsk, SYSCALL_USER_DISPATCH)
 
+int syscall_user_dispatch_get_config(struct task_struct *task, unsigned long size,
+	void __user *data);
+
+int syscall_user_dispatch_set_config(struct task_struct *task, unsigned long size,
+	void __user *data);
+
 #else
 struct syscall_user_dispatch {};
 
@@ -35,6 +41,18 @@ static inline void clear_syscall_work_syscall_user_dispatch(struct task_struct *
 {
 }
 
+static inline int syscall_user_dispatch_get_config(struct task_struct *task, unsigned long size,
+	void __user *data)
+{
+	return -EINVAL;
+}
+
+static inline int syscall_user_dispatch_set_config(struct task_struct *task, unsigned long size,
+	void __user *data)
+{
+	return -EINVAL;
+}
+
 #endif /* CONFIG_GENERIC_ENTRY */
 
 #endif /* _SYSCALL_USER_DISPATCH_H */
diff --git a/include/uapi/linux/ptrace.h b/include/uapi/linux/ptrace.h
index 195ae64a8c87..6d2f3b86f932 100644
--- a/include/uapi/linux/ptrace.h
+++ b/include/uapi/linux/ptrace.h
@@ -112,6 +112,15 @@ struct ptrace_rseq_configuration {
 	__u32 pad;
 };
 
+#define PTRACE_SET_SYSCALL_USER_DISPATCH_CONFIG 0x4210
+#define PTRACE_GET_SYSCALL_USER_DISPATCH_CONFIG 0x4211
+struct syscall_user_dispatch_config {
+	__u64 mode;
+	__s8 *selector;
+	__u64 offset;
+	__u64 len;
+};
+
 /*
  * These values are stored in task->ptrace_message
  * by ptrace_stop to describe the current syscall-stop.
diff --git a/kernel/entry/syscall_user_dispatch.c b/kernel/entry/syscall_user_dispatch.c
index 0b6379adff6b..26217fcc1c90 100644
--- a/kernel/entry/syscall_user_dispatch.c
+++ b/kernel/entry/syscall_user_dispatch.c
@@ -106,3 +106,42 @@ int set_syscall_user_dispatch(unsigned long mode, unsigned long offset,
 
 	return 0;
 }
+
+int syscall_user_dispatch_get_config(struct task_struct *task, unsigned long size,
+		void __user *data)
+{
+	struct syscall_user_dispatch *sd = &task->syscall_dispatch;
+	struct syscall_user_dispatch_config config;
+
+	if (size != sizeof(struct syscall_user_dispatch_config))
+		return -EINVAL;
+
+	if (test_syscall_work(SYSCALL_USER_DISPATCH))
+		config.mode = PR_SYS_DISPATCH_ON;
+	else
+		config.mode = PR_SYS_DISPATCH_OFF;
+
+	config.offset = sd->offset;
+	config.len = sd->len;
+	config.selector = sd->selector;
+
+	if (copy_to_user(data, &config, sizeof(config)))
+		return -EFAULT;
+
+	return 0;
+}
+
+int syscall_user_dispatch_set_config(struct task_struct *task, unsigned long size,
+		void __user *data)
+{
+	struct syscall_user_dispatch_config config;
+
+	if (size != sizeof(struct syscall_user_dispatch_config))
+		return -EINVAL;
+
+	if (copy_from_user(&config, data, sizeof(config)))
+		return -EFAULT;
+
+	return set_syscall_user_dispatch(config.mode, config.offset, config.len,
+			config.selector);
+}
diff --git a/kernel/ptrace.c b/kernel/ptrace.c
index 54482193e1ed..d99376532b56 100644
--- a/kernel/ptrace.c
+++ b/kernel/ptrace.c
@@ -32,6 +32,7 @@
 #include <linux/compat.h>
 #include <linux/sched/signal.h>
 #include <linux/minmax.h>
+#include <linux/syscall_user_dispatch.h>
 
 #include <asm/syscall.h>	/* for syscall_get_* */
 
@@ -1259,6 +1260,14 @@ int ptrace_request(struct task_struct *child, long request,
 		break;
 #endif
 
+	case PTRACE_SET_SYSCALL_USER_DISPATCH_CONFIG:
+		ret = syscall_user_dispatch_set_config(child, addr, datavp);
+		break;
+
+	case PTRACE_GET_SYSCALL_USER_DISPATCH_CONFIG:
+		ret = syscall_user_dispatch_get_config(child, addr, datavp);
+		break;
+
 	default:
 		break;
 	}
-- 
2.39.0