[PATCH v6 5/9] kernel: Implement selective syscall userspace redirection

@@ -468,6 +468,27 @@ config SECCOMP_FILTER
 
 	  See Documentation/userspace-api/seccomp_filter.rst for details.
 
+config HAVE_ARCH_SYSCALL_USER_DISPATCH
+	bool
+	help
+	  An arch should select this symbol if it provides all of these things:
+	  - TIF_SYSCALL_INTERCEPT
+	  - syscall_get_arch
+	  - syscall_rollback
+	  - syscall_get_nr
+	  - SIGSYS siginfo_t support
+	  - arch_syscall_is_vdso_sigreturn
+
+config SYSCALL_USER_DISPATCH
+	bool "Support syscall redirection to userspace dispatcher"
+	depends on HAVE_ARCH_SYSCALL_USER_DISPATCH
+	help
+	  Enable tasks to ask the kernel to redirect syscalls not
+	  issued from a predefined dispatcher back to userspace,
+	  depending on a userspace memory selector.
+
+	  This option is useful to optimize games running over Wine.
+
 config HAVE_ARCH_STACKLEAK
 	bool
 	help

@@ -62,6 +62,7 @@
 #include <linux/oom.h>
 #include <linux/compat.h>
 #include <linux/vmalloc.h>
+#include <linux/syscall_intercept.h>
 
 #include <linux/uaccess.h>
 #include <asm/mmu_context.h>

@@ -1418,6 +1419,13 @@ int begin_new_exec(struct linux_binprm * bprm)
 	flush_thread();
 	me->personality &= ~bprm->per_clear;
 
+	/*
+	 * Prevent Syscall User Dispatch from crossing application
+	 * boundaries.  sighand is already unshared, so it is safe to
+	 * use the unlocked version here.
+	 */
+	__clear_tsk_syscall_intercept(me, SYSINT_USER_DISPATCH);
+
 	/*
 	 * We have to apply CLOEXEC before we change whether the process is
 	 * dumpable (in setup_new_exec) to avoid a race with a process in userspace

@@ -34,6 +34,7 @@
 #include <linux/rseq.h>
 #include <linux/seqlock.h>
 #include <linux/kcsan.h>
+#include <linux/syscall_user_dispatch.h>
 
 /* task_struct member predeclarations (sorted alphabetically): */
 struct audit_context;

@@ -963,6 +964,7 @@ struct task_struct {
 	struct {
 		unsigned int			syscall_intercept;
 		struct seccomp			seccomp;
+		struct syscall_user_dispatch	syscall_dispatch;
 	};
 
 	/* Thread group tracking: */

@@ -10,6 +10,7 @@
 #include <linux/thread_info.h>
 
 #define SYSINT_SECCOMP		0x1
+#define SYSINT_USER_DISPATCH	0x2
 
 #ifdef TIF_SYSCALL_INTERCEPT
 

@@ -0,0 +1,29 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (C) 2020 Collabora Ltd.
+ */
+#ifndef _SYSCALL_USER_DISPATCH_H
+#define _SYSCALL_USER_DISPATCH_H
+
+#ifdef CONFIG_SYSCALL_USER_DISPATCH
+struct syscall_user_dispatch {
+	char __user *selector;
+	unsigned long dispatcher_start;
+	unsigned long dispatcher_end;
+};
+
+int set_syscall_user_dispatch(int mode, unsigned long dispatcher_start,
+			      unsigned long dispatcher_end,
+			      char __user *selector);
+#else
+struct syscall_user_dispatch {};
+
+static inline int set_syscall_user_dispatch(int mode, unsigned long dispatcher_start,
+					    unsigned long dispatcher_end,
+					    char __user *selector)
+{
+	return -EINVAL;
+}
+#endif /* CONFIG_SYSCALL_USER_DISPATCH */
+
+#endif /* _SYSCALL_USER_DISPATCH_H */

@@ -238,4 +238,9 @@ struct prctl_mm_map {
 #define PR_SET_IO_FLUSHER		57
 #define PR_GET_IO_FLUSHER		58
 
+/* Dispatch syscalls to a userspace handler */
+#define PR_SET_SYSCALL_USER_DISPATCH	59
+# define PR_SYS_DISPATCH_OFF		0
+# define PR_SYS_DISPATCH_ON		1
+
 #endif /* _LINUX_PRCTL_H */

@@ -11,3 +11,4 @@ CFLAGS_common.o		+= -fno-stack-protector
 
 obj-$(CONFIG_GENERIC_ENTRY) 		+= common.o
 obj-$(CONFIG_KVM_XFER_TO_GUEST_WORK)	+= kvm.o
+obj-$(CONFIG_SYSCALL_USER_DISPATCH)	+= syscall_user_dispatch.o

@@ -0,0 +1,15 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _COMMON_H
+#define _COMMON_H
+
+#ifdef CONFIG_SYSCALL_USER_DISPATCH
+int do_syscall_user_dispatch(struct pt_regs *regs);
+#else
+static inline int do_syscall_user_dispatch(struct pt_regs *regs)
+{
+	WARN_ON_ONCE(1);
+	return 0;
+}
+#endif /* CONFIG_SYSCALL_USER_DISPATCH */
+
+#endif

@@ -0,0 +1,101 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2020 Collabora Ltd.
+ */
+#include <linux/sched.h>
+#include <linux/prctl.h>
+#include <linux/syscall_intercept.h>
+#include <linux/syscall_user_dispatch.h>
+#include <linux/uaccess.h>
+#include <linux/signal.h>
+#include <linux/elf.h>
+
+#include <asm/syscall.h>
+
+#include <linux/sched/signal.h>
+#include <linux/sched/task_stack.h>
+
+static void trigger_sigsys(struct pt_regs *regs)
+{
+	struct kernel_siginfo info;
+
+	clear_siginfo(&info);
+	info.si_signo = SIGSYS;
+	info.si_code = SYS_USER_DISPATCH;
+	info.si_call_addr = (void __user *)KSTK_EIP(current);
+	info.si_errno = 0;
+	info.si_arch = syscall_get_arch(current);
+	info.si_syscall = syscall_get_nr(current, regs);
+
+	force_sig_info(&info);
+}
+
+int do_syscall_user_dispatch(struct pt_regs *regs)
+{
+	struct syscall_user_dispatch *sd = &current->syscall_dispatch;
+	unsigned long ip = instruction_pointer(regs);
+	char state;
+
+	if (likely(ip >= sd->dispatcher_start && ip <= sd->dispatcher_end))
+		return 0;
+
+	if (unlikely(arch_syscall_is_vdso_sigreturn(regs)))
+		return 0;
+
+	if (likely(sd->selector)) {
+		/*
+		 * access_ok() is performed once, at prctl time, when
+		 * the selector is loaded by userspace.
+		 */
+		if (unlikely(__get_user(state, sd->selector)))
+			do_exit(SIGSEGV);
+
+		if (likely(state == PR_SYS_DISPATCH_OFF))
+			return 0;
+
+		if (state != PR_SYS_DISPATCH_ON)
+			do_exit(SIGSYS);
+	}
+
+	syscall_rollback(current, regs);
+	trigger_sigsys(regs);
+
+	return 1;
+}
+
+int set_syscall_user_dispatch(int mode, unsigned long dispatcher_start,
+			      unsigned long dispatcher_end, char __user *selector)
+{
+	switch (mode) {
+	case PR_SYS_DISPATCH_OFF:
+		if (dispatcher_start || dispatcher_end || selector)
+			return -EINVAL;
+		break;
+	case PR_SYS_DISPATCH_ON:
+		/*
+		 * Validate the direct dispatcher region just for basic
+		 * sanity.  If the user is able to submit a syscall from
+		 * an address, that address is obviously valid.
+		 */
+		if (dispatcher_end < dispatcher_start)
+			return -EINVAL;
+
+		if (selector && !access_ok(selector, sizeof(*selector)))
+			return -EFAULT;
+
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	current->syscall_dispatch.selector = selector;
+	current->syscall_dispatch.dispatcher_start = dispatcher_start;
+	current->syscall_dispatch.dispatcher_end = dispatcher_end;
+
+	if (mode == PR_SYS_DISPATCH_ON)
+		set_tsk_syscall_intercept(current, SYSINT_USER_DISPATCH);
+	else
+		clear_tsk_syscall_intercept(current, SYSINT_USER_DISPATCH);
+
+	return 0;
+}

@@ -42,6 +42,7 @@
 #include <linux/syscore_ops.h>
 #include <linux/version.h>
 #include <linux/ctype.h>
+#include <linux/syscall_user_dispatch.h>
 
 #include <linux/compat.h>
 #include <linux/syscalls.h>

@@ -2530,6 +2531,10 @@ SYSCALL_DEFINE5(prctl, int, option, unsigned long, arg2, unsigned long, arg3,
 
 		error = (current->flags & PR_IO_FLUSHER) == PR_IO_FLUSHER;
 		break;
+	case PR_SET_SYSCALL_USER_DISPATCH:
+		error = set_syscall_user_dispatch((int) arg2, arg3, arg4,
+						  (char __user *) arg5);
+		break;
 	default:
 		error = -EINVAL;
 		break;