Merge tag 'core-entry-2023-04-24' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull core entry/ptrace update from Thomas Gleixner:
 "Provide a ptrace set/get interface for syscall user dispatch. The main
  purpose is to enable checkpoint/restore (CRIU) to handle processes
  which utilize syscall user dispatch correctly"

* tag 'core-entry-2023-04-24' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  selftest, ptrace: Add selftest for syscall user dispatch config api
  ptrace: Provide set/get interface for syscall user dispatch
  syscall_user_dispatch: Untag selector address before access_ok()
  syscall_user_dispatch: Split up set_syscall_user_dispatch()

2 files changed, 74 insertions, 9 deletions

diff --git a/kernel/entry/syscall_user_dispatch.c b/kernel/entry/syscall_user_dispatch.c
index 0b6379adff6b..5340c5aa89e7 100644
--- a/kernel/entry/syscall_user_dispatch.c
+++ b/kernel/entry/syscall_user_dispatch.c
@@ -4,6 +4,7 @@
  */
 #include <linux/sched.h>
 #include <linux/prctl.h>
+#include <linux/ptrace.h>
 #include <linux/syscall_user_dispatch.h>
 #include <linux/uaccess.h>
 #include <linux/signal.h>
@@ -68,8 +69,9 @@ bool syscall_user_dispatch(struct pt_regs *regs)
 	return true;
 }
 
-int set_syscall_user_dispatch(unsigned long mode, unsigned long offset,
-			      unsigned long len, char __user *selector)
+static int task_set_syscall_user_dispatch(struct task_struct *task, unsigned long mode,
+					  unsigned long offset, unsigned long len,
+					  char __user *selector)
 {
 	switch (mode) {
 	case PR_SYS_DISPATCH_OFF:
@@ -86,7 +88,16 @@ int set_syscall_user_dispatch(unsigned long mode, unsigned long offset,
 		if (offset && offset + len <= offset)
 			return -EINVAL;
 
-		if (selector && !access_ok(selector, sizeof(*selector)))
+		/*
+		 * access_ok() will clear memory tags for tagged addresses
+		 * if current has memory tagging enabled.
+
+		 * To enable a tracer to set a tracees selector the
+		 * selector address must be untagged for access_ok(),
+		 * otherwise an untagged tracer will always fail to set a
+		 * tagged tracees selector.
+		 */
+		if (selector && !access_ok(untagged_addr(selector), sizeof(*selector)))
 			return -EFAULT;
 
 		break;
@@ -94,15 +105,60 @@ int set_syscall_user_dispatch(unsigned long mode, unsigned long offset,
 		return -EINVAL;
 	}
 
-	current->syscall_dispatch.selector = selector;
-	current->syscall_dispatch.offset = offset;
-	current->syscall_dispatch.len = len;
-	current->syscall_dispatch.on_dispatch = false;
+	task->syscall_dispatch.selector = selector;
+	task->syscall_dispatch.offset = offset;
+	task->syscall_dispatch.len = len;
+	task->syscall_dispatch.on_dispatch = false;
 
 	if (mode == PR_SYS_DISPATCH_ON)
-		set_syscall_work(SYSCALL_USER_DISPATCH);
+		set_task_syscall_work(task, SYSCALL_USER_DISPATCH);
+	else
+		clear_task_syscall_work(task, SYSCALL_USER_DISPATCH);
+
+	return 0;
+}
+
+int set_syscall_user_dispatch(unsigned long mode, unsigned long offset,
+			      unsigned long len, char __user *selector)
+{
+	return task_set_syscall_user_dispatch(current, mode, offset, len, selector);
+}
+
+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 ptrace_sud_config cfg;
+
+	if (size != sizeof(cfg))
+		return -EINVAL;
+
+	if (test_task_syscall_work(task, SYSCALL_USER_DISPATCH))
+		cfg.mode = PR_SYS_DISPATCH_ON;
 	else
-		clear_syscall_work(SYSCALL_USER_DISPATCH);
+		cfg.mode = PR_SYS_DISPATCH_OFF;
+
+	cfg.offset = sd->offset;
+	cfg.len = sd->len;
+	cfg.selector = (__u64)(uintptr_t)sd->selector;
+
+	if (copy_to_user(data, &cfg, sizeof(cfg)))
+		return -EFAULT;
 
 	return 0;
 }
+
+int syscall_user_dispatch_set_config(struct task_struct *task, unsigned long size,
+				     void __user *data)
+{
+	struct ptrace_sud_config cfg;
+
+	if (size != sizeof(cfg))
+		return -EINVAL;
+
+	if (copy_from_user(&cfg, data, sizeof(cfg)))
+		return -EFAULT;
+
+	return task_set_syscall_user_dispatch(task, cfg.mode, cfg.offset, cfg.len,
+					      (char __user *)(uintptr_t)cfg.selector);
+}
diff --git a/kernel/ptrace.c b/kernel/ptrace.c
index 0786450074c1..443057bee87c 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;
 	}