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()

Author: torvalds

Documentation/admin-guide/syscall-user-dispatch.rst

@@ -73,6 +73,10 @@ thread-wide, without the need to invoke the kernel directly.  selector
 can be set to SYSCALL_DISPATCH_FILTER_ALLOW or SYSCALL_DISPATCH_FILTER_BLOCK.
 Any other value should terminate the program with a SIGSYS.
 
+Additionally, a tasks syscall user dispatch configuration can be peeked
+and poked via the PTRACE_(GET|SET)_SYSCALL_USER_DISPATCH_CONFIG ptrace
+requests. This is useful for checkpoint/restart software.
+
 Security Notes
 --------------
 

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 */

include/uapi/linux/ptrace.h

@@ -112,6 +112,36 @@ struct ptrace_rseq_configuration {
 	__u32 pad;
 };
 
+#define PTRACE_SET_SYSCALL_USER_DISPATCH_CONFIG 0x4210
+#define PTRACE_GET_SYSCALL_USER_DISPATCH_CONFIG 0x4211
+
+/*
+ * struct ptrace_sud_config - Per-task configuration for Syscall User Dispatch
+ * @mode:	One of PR_SYS_DISPATCH_ON or PR_SYS_DISPATCH_OFF
+ * @selector:	Tracees user virtual address of SUD selector
+ * @offset:	SUD exclusion area (virtual address)
+ * @len:	Length of SUD exclusion area
+ *
+ * Used to get/set the syscall user dispatch configuration for a tracee.
+ * Selector is optional (may be NULL), and if invalid will produce
+ * a SIGSEGV in the tracee upon first access.
+ *
+ * If mode is PR_SYS_DISPATCH_ON, syscall dispatch will be enabled. If
+ * PR_SYS_DISPATCH_OFF, syscall dispatch will be disabled and all other
+ * parameters must be 0.  The value in *selector (if not null), also determines
+ * whether syscall dispatch will occur.
+ *
+ * The Syscall User Dispatch Exclusion area described by offset/len is the
+ * virtual address space from which syscalls will not produce a user
+ * dispatch.
+ */
+struct ptrace_sud_config {
+	__u64 mode;
+	__u64 selector;
+	__u64 offset;
+	__u64 len;
+};
+
 /*
  * These values are stored in task->ptrace_message
  * by ptrace_stop to describe the current syscall-stop.

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:
@@ -86,23 +88,77 @@ 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;
 	default:
 		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);
+}

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;
 	}

tools/testing/selftests/ptrace/.gitignore

@@ -1,4 +1,5 @@
 # SPDX-License-Identifier: GPL-2.0-only
 get_syscall_info
+get_set_sud
 peeksiginfo
 vmaccess

tools/testing/selftests/ptrace/Makefile

@@ -1,6 +1,6 @@
 # SPDX-License-Identifier: GPL-2.0-only
 CFLAGS += -std=c99 -pthread -Wall $(KHDR_INCLUDES)
 
-TEST_GEN_PROGS := get_syscall_info peeksiginfo vmaccess
+TEST_GEN_PROGS := get_syscall_info peeksiginfo vmaccess get_set_sud
 
 include ../lib.mk

tools/testing/selftests/ptrace/get_set_sud.c

@@ -0,0 +1,72 @@
+// SPDX-License-Identifier: GPL-2.0
+#define _GNU_SOURCE
+#include "../kselftest_harness.h"
+#include <stdio.h>
+#include <string.h>
+#include <errno.h>
+#include <sys/wait.h>
+#include <sys/syscall.h>
+#include <sys/prctl.h>
+
+#include "linux/ptrace.h"
+
+static int sys_ptrace(int request, pid_t pid, void *addr, void *data)
+{
+	return syscall(SYS_ptrace, request, pid, addr, data);
+}
+
+TEST(get_set_sud)
+{
+	struct ptrace_sud_config config;
+	pid_t child;
+	int ret = 0;
+	int status;
+
+	child = fork();
+	ASSERT_GE(child, 0);
+	if (child == 0) {
+		ASSERT_EQ(0, sys_ptrace(PTRACE_TRACEME, 0, 0, 0)) {
+			TH_LOG("PTRACE_TRACEME: %m");
+		}
+		kill(getpid(), SIGSTOP);
+		_exit(1);
+	}
+
+	waitpid(child, &status, 0);
+
+	memset(&config, 0xff, sizeof(config));
+	config.mode = PR_SYS_DISPATCH_ON;
+
+	ret = sys_ptrace(PTRACE_GET_SYSCALL_USER_DISPATCH_CONFIG, child,
+			 (void *)sizeof(config), &config);
+
+	ASSERT_EQ(ret, 0);
+	ASSERT_EQ(config.mode, PR_SYS_DISPATCH_OFF);
+	ASSERT_EQ(config.selector, 0);
+	ASSERT_EQ(config.offset, 0);
+	ASSERT_EQ(config.len, 0);
+
+	config.mode = PR_SYS_DISPATCH_ON;
+	config.selector = 0;
+	config.offset = 0x400000;
+	config.len = 0x1000;
+
+	ret = sys_ptrace(PTRACE_SET_SYSCALL_USER_DISPATCH_CONFIG, child,
+			 (void *)sizeof(config), &config);
+
+	ASSERT_EQ(ret, 0);
+
+	memset(&config, 1, sizeof(config));
+	ret = sys_ptrace(PTRACE_GET_SYSCALL_USER_DISPATCH_CONFIG, child,
+			 (void *)sizeof(config), &config);
+
+	ASSERT_EQ(ret, 0);
+	ASSERT_EQ(config.mode, PR_SYS_DISPATCH_ON);
+	ASSERT_EQ(config.selector, 0);
+	ASSERT_EQ(config.offset, 0x400000);
+	ASSERT_EQ(config.len, 0x1000);
+
+	kill(child, SIGKILL);
+}
+
+TEST_HARNESS_MAIN