Merge tag 'core-entry-2020-12-14' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull core entry/exit updates from Thomas Gleixner:
 "A set of updates for entry/exit handling:

   - More generalization of entry/exit functionality

   - The consolidation work to reclaim TIF flags on x86 and also for
     non-x86 specific TIF flags which are solely relevant for syscall
     related work and have been moved into their own storage space. The
     x86 specific part had to be merged in to avoid a major conflict.

   - The TIF_NOTIFY_SIGNAL work which replaces the inefficient signal
     delivery mode of task work and results in an impressive performance
     improvement for io_uring. The non-x86 consolidation of this is
     going to come seperate via Jens.

   - The selective syscall redirection facility which provides a clean
     and efficient way to support the non-Linux syscalls of WINE by
     catching them at syscall entry and redirecting them to the user
     space emulation. This can be utilized for other purposes as well
     and has been designed carefully to avoid overhead for the regular
     fastpath. This includes the core changes and the x86 support code.

   - Simplification of the context tracking entry/exit handling for the
     users of the generic entry code which guarantee the proper ordering
     and protection.

   - Preparatory changes to make the generic entry code accomodate S390
     specific requirements which are mostly related to their syscall
     restart mechanism"

* tag 'core-entry-2020-12-14' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (36 commits)
  entry: Add syscall_exit_to_user_mode_work()
  entry: Add exit_to_user_mode() wrapper
  entry_Add_enter_from_user_mode_wrapper
  entry: Rename exit_to_user_mode()
  entry: Rename enter_from_user_mode()
  docs: Document Syscall User Dispatch
  selftests: Add benchmark for syscall user dispatch
  selftests: Add kselftest for syscall user dispatch
  entry: Support Syscall User Dispatch on common syscall entry
  kernel: Implement selective syscall userspace redirection
  signal: Expose SYS_USER_DISPATCH si_code type
  x86: vdso: Expose sigreturn address on vdso to the kernel
  MAINTAINERS: Add entry for common entry code
  entry: Fix boot for !CONFIG_GENERIC_ENTRY
  x86: Support HAVE_CONTEXT_TRACKING_OFFSTACK
  context_tracking: Only define schedule_user() on !HAVE_CONTEXT_TRACKING_OFFSTACK archs
  sched: Detect call to schedule from critical entry code
  context_tracking: Don't implement exception_enter/exit() on CONFIG_HAVE_CONTEXT_TRACKING_OFFSTACK
  context_tracking: Introduce HAVE_CONTEXT_TRACKING_OFFSTACK
  x86: Reclaim unused x86 TI flags
  ...

13 files changed, 308 insertions, 69 deletions

diff --git a/include/asm-generic/syscall.h b/include/asm-generic/syscall.h
index f3135e734387..524218ae3825 100644
--- a/include/asm-generic/syscall.h
+++ b/include/asm-generic/syscall.h
@@ -43,9 +43,9 @@ int syscall_get_nr(struct task_struct *task, struct pt_regs *regs);
  * @regs:	task_pt_regs() of @task
  *
  * It's only valid to call this when @task is stopped for system
- * call exit tracing (due to TIF_SYSCALL_TRACE or TIF_SYSCALL_AUDIT),
- * after tracehook_report_syscall_entry() returned nonzero to prevent
- * the system call from taking place.
+ * call exit tracing (due to %SYSCALL_WORK_SYSCALL_TRACE or
+ * %SYSCALL_WORK_SYSCALL_AUDIT), after tracehook_report_syscall_entry()
+ * returned nonzero to prevent the system call from taking place.
  *
  * This rolls back the register state in @regs so it's as if the
  * system call instruction was a no-op.  The registers containing
@@ -63,7 +63,8 @@ void syscall_rollback(struct task_struct *task, struct pt_regs *regs);
  * Returns 0 if the system call succeeded, or -ERRORCODE if it failed.
  *
  * It's only valid to call this when @task is stopped for tracing on exit
- * from a system call, due to %TIF_SYSCALL_TRACE or %TIF_SYSCALL_AUDIT.
+ * from a system call, due to %SYSCALL_WORK_SYSCALL_TRACE or
+ * %SYSCALL_WORK_SYSCALL_AUDIT.
  */
 long syscall_get_error(struct task_struct *task, struct pt_regs *regs);
 
@@ -76,7 +77,8 @@ long syscall_get_error(struct task_struct *task, struct pt_regs *regs);
  * This value is meaningless if syscall_get_error() returned nonzero.
  *
  * It's only valid to call this when @task is stopped for tracing on exit
- * from a system call, due to %TIF_SYSCALL_TRACE or %TIF_SYSCALL_AUDIT.
+ * from a system call, due to %SYSCALL_WORK_SYSCALL_TRACE or
+ * %SYSCALL_WORK_SYSCALL_AUDIT.
  */
 long syscall_get_return_value(struct task_struct *task, struct pt_regs *regs);
 
@@ -93,7 +95,8 @@ long syscall_get_return_value(struct task_struct *task, struct pt_regs *regs);
  * code; the user sees a failed system call with this errno code.
  *
  * It's only valid to call this when @task is stopped for tracing on exit
- * from a system call, due to %TIF_SYSCALL_TRACE or %TIF_SYSCALL_AUDIT.
+ * from a system call, due to %SYSCALL_WORK_SYSCALL_TRACE or
+ * %SYSCALL_WORK_SYSCALL_AUDIT.
  */
 void syscall_set_return_value(struct task_struct *task, struct pt_regs *regs,
 			      int error, long val);
@@ -108,7 +111,8 @@ void syscall_set_return_value(struct task_struct *task, struct pt_regs *regs,
 *  @args[0], and so on.
  *
  * It's only valid to call this when @task is stopped for tracing on
- * entry to a system call, due to %TIF_SYSCALL_TRACE or %TIF_SYSCALL_AUDIT.
+ * entry to a system call, due to %SYSCALL_WORK_SYSCALL_TRACE or
+ * %SYSCALL_WORK_SYSCALL_AUDIT.
  */
 void syscall_get_arguments(struct task_struct *task, struct pt_regs *regs,
 			   unsigned long *args);
@@ -123,7 +127,8 @@ void syscall_get_arguments(struct task_struct *task, struct pt_regs *regs,
  * The first argument gets value @args[0], and so on.
  *
  * It's only valid to call this when @task is stopped for tracing on
- * entry to a system call, due to %TIF_SYSCALL_TRACE or %TIF_SYSCALL_AUDIT.
+ * entry to a system call, due to %SYSCALL_WORK_SYSCALL_TRACE or
+ * %SYSCALL_WORK_SYSCALL_AUDIT.
  */
 void syscall_set_arguments(struct task_struct *task, struct pt_regs *regs,
 			   const unsigned long *args);
@@ -135,7 +140,8 @@ void syscall_set_arguments(struct task_struct *task, struct pt_regs *regs,
  * Returns the AUDIT_ARCH_* based on the system call convention in use.
  *
  * It's only valid to call this when @task is stopped on entry to a system
- * call, due to %TIF_SYSCALL_TRACE, %TIF_SYSCALL_AUDIT, or %TIF_SECCOMP.
+ * call, due to %SYSCALL_WORK_SYSCALL_TRACE, %SYSCALL_WORK_SYSCALL_AUDIT, or
+ * %SYSCALL_WORK_SECCOMP.
  *
  * Architectures which permit CONFIG_HAVE_ARCH_SECCOMP_FILTER must
  * provide an implementation of this.
diff --git a/include/linux/context_tracking.h b/include/linux/context_tracking.h
index d53cd331c4dd..bceb06498521 100644
--- a/include/linux/context_tracking.h
+++ b/include/linux/context_tracking.h
@@ -51,7 +51,8 @@ static inline enum ctx_state exception_enter(void)
 {
 	enum ctx_state prev_ctx;
 
-	if (!context_tracking_enabled())
+	if (IS_ENABLED(CONFIG_HAVE_CONTEXT_TRACKING_OFFSTACK) ||
+	    !context_tracking_enabled())
 		return 0;
 
 	prev_ctx = this_cpu_read(context_tracking.state);
@@ -63,7 +64,8 @@ static inline enum ctx_state exception_enter(void)
 
 static inline void exception_exit(enum ctx_state prev_ctx)
 {
-	if (context_tracking_enabled()) {
+	if (!IS_ENABLED(CONFIG_HAVE_CONTEXT_TRACKING_OFFSTACK) &&
+	    context_tracking_enabled()) {
 		if (prev_ctx != CONTEXT_KERNEL)
 			context_tracking_enter(prev_ctx);
 	}
diff --git a/include/linux/entry-common.h b/include/linux/entry-common.h
index 474f29638d2c..7c581a4c3797 100644
--- a/include/linux/entry-common.h
+++ b/include/linux/entry-common.h
@@ -13,22 +13,6 @@
  * Define dummy _TIF work flags if not defined by the architecture or for
  * disabled functionality.
  */
-#ifndef _TIF_SYSCALL_EMU
-# define _TIF_SYSCALL_EMU		(0)
-#endif
-
-#ifndef _TIF_SYSCALL_TRACEPOINT
-# define _TIF_SYSCALL_TRACEPOINT	(0)
-#endif
-
-#ifndef _TIF_SECCOMP
-# define _TIF_SECCOMP			(0)
-#endif
-
-#ifndef _TIF_SYSCALL_AUDIT
-# define _TIF_SYSCALL_AUDIT		(0)
-#endif
-
 #ifndef _TIF_PATCH_PENDING
 # define _TIF_PATCH_PENDING		(0)
 #endif
@@ -37,28 +21,36 @@
 # define _TIF_UPROBE			(0)
 #endif
 
+#ifndef _TIF_NOTIFY_SIGNAL
+# define _TIF_NOTIFY_SIGNAL		(0)
+#endif
+
 /*
- * TIF flags handled in syscall_enter_from_user_mode()
+ * SYSCALL_WORK flags handled in syscall_enter_from_user_mode()
  */
-#ifndef ARCH_SYSCALL_ENTER_WORK
-# define ARCH_SYSCALL_ENTER_WORK	(0)
+#ifndef ARCH_SYSCALL_WORK_ENTER
+# define ARCH_SYSCALL_WORK_ENTER	(0)
 #endif
 
-#define SYSCALL_ENTER_WORK						\
-	(_TIF_SYSCALL_TRACE | _TIF_SYSCALL_AUDIT | _TIF_SECCOMP |	\
-	 _TIF_SYSCALL_TRACEPOINT | _TIF_SYSCALL_EMU |			\
-	 ARCH_SYSCALL_ENTER_WORK)
-
 /*
- * TIF flags handled in syscall_exit_to_user_mode()
+ * SYSCALL_WORK flags handled in syscall_exit_to_user_mode()
  */
-#ifndef ARCH_SYSCALL_EXIT_WORK
-# define ARCH_SYSCALL_EXIT_WORK		(0)
+#ifndef ARCH_SYSCALL_WORK_EXIT
+# define ARCH_SYSCALL_WORK_EXIT		(0)
 #endif
 
-#define SYSCALL_EXIT_WORK						\
-	(_TIF_SYSCALL_TRACE | _TIF_SYSCALL_AUDIT |			\
-	 _TIF_SYSCALL_TRACEPOINT | ARCH_SYSCALL_EXIT_WORK)
+#define SYSCALL_WORK_ENTER	(SYSCALL_WORK_SECCOMP |			\
+				 SYSCALL_WORK_SYSCALL_TRACEPOINT |	\
+				 SYSCALL_WORK_SYSCALL_TRACE |		\
+				 SYSCALL_WORK_SYSCALL_EMU |		\
+				 SYSCALL_WORK_SYSCALL_AUDIT |		\
+				 SYSCALL_WORK_SYSCALL_USER_DISPATCH |	\
+				 ARCH_SYSCALL_WORK_ENTER)
+#define SYSCALL_WORK_EXIT	(SYSCALL_WORK_SYSCALL_TRACEPOINT |	\
+				 SYSCALL_WORK_SYSCALL_TRACE |		\
+				 SYSCALL_WORK_SYSCALL_AUDIT |		\
+				 SYSCALL_WORK_SYSCALL_USER_DISPATCH |	\
+				 ARCH_SYSCALL_WORK_EXIT)
 
 /*
  * TIF flags handled in exit_to_user_mode_loop()
@@ -69,7 +61,7 @@
 
 #define EXIT_TO_USER_MODE_WORK						\
 	(_TIF_SIGPENDING | _TIF_NOTIFY_RESUME | _TIF_UPROBE |		\
-	 _TIF_NEED_RESCHED | _TIF_PATCH_PENDING |			\
+	 _TIF_NEED_RESCHED | _TIF_PATCH_PENDING | _TIF_NOTIFY_SIGNAL |	\
 	 ARCH_EXIT_TO_USER_MODE_WORK)
 
 /**
@@ -110,6 +102,27 @@ static inline __must_check int arch_syscall_enter_tracehook(struct pt_regs *regs
 #endif
 
 /**
+ * enter_from_user_mode - Establish state when coming from user mode
+ *
+ * Syscall/interrupt entry disables interrupts, but user mode is traced as
+ * interrupts enabled. Also with NO_HZ_FULL RCU might be idle.
+ *
+ * 1) Tell lockdep that interrupts are disabled
+ * 2) Invoke context tracking if enabled to reactivate RCU
+ * 3) Trace interrupts off state
+ *
+ * Invoked from architecture specific syscall entry code with interrupts
+ * disabled. The calling code has to be non-instrumentable. When the
+ * function returns all state is correct and interrupts are still
+ * disabled. The subsequent functions can be instrumented.
+ *
+ * This is invoked when there is architecture specific functionality to be
+ * done between establishing state and enabling interrupts. The caller must
+ * enable interrupts before invoking syscall_enter_from_user_mode_work().
+ */
+void enter_from_user_mode(struct pt_regs *regs);
+
+/**
  * syscall_enter_from_user_mode_prepare - Establish state and enable interrupts
  * @regs:	Pointer to currents pt_regs
  *
@@ -118,7 +131,8 @@ static inline __must_check int arch_syscall_enter_tracehook(struct pt_regs *regs
  * function returns all state is correct, interrupts are enabled and the
  * subsequent functions can be instrumented.
  *
- * This handles lockdep, RCU (context tracking) and tracing state.
+ * This handles lockdep, RCU (context tracking) and tracing state, i.e.
+ * the functionality provided by enter_from_user_mode().
  *
  * This is invoked when there is extra architecture specific functionality
  * to be done between establishing state and handling user mode entry work.
@@ -144,8 +158,8 @@ void syscall_enter_from_user_mode_prepare(struct pt_regs *regs);
  *
  * It handles the following work items:
  *
- *  1) TIF flag dependent invocations of arch_syscall_enter_tracehook(),
- *     __secure_computing(), trace_sys_enter()
+ *  1) syscall_work flag dependent invocations of
+ *     arch_syscall_enter_tracehook(), __secure_computing(), trace_sys_enter()
  *  2) Invocation of audit_syscall_entry()
  */
 long syscall_enter_from_user_mode_work(struct pt_regs *regs, long syscall);
@@ -259,12 +273,13 @@ static __always_inline void arch_exit_to_user_mode(void) { }
 #endif
 
 /**
- * arch_do_signal -  Architecture specific signal delivery function
+ * arch_do_signal_or_restart -  Architecture specific signal delivery function
  * @regs:	Pointer to currents pt_regs
+ * @has_signal:	actual signal to handle
  *
  * Invoked from exit_to_user_mode_loop().
  */
-void arch_do_signal(struct pt_regs *regs);
+void arch_do_signal_or_restart(struct pt_regs *regs, bool has_signal);
 
 /**
  * arch_syscall_exit_tracehook - Wrapper around tracehook_report_syscall_exit()
@@ -286,6 +301,41 @@ static inline void arch_syscall_exit_tracehook(struct pt_regs *regs, bool step)
 #endif
 
 /**
+ * exit_to_user_mode - Fixup state when exiting to user mode
+ *
+ * Syscall/interrupt exit enables interrupts, but the kernel state is
+ * interrupts disabled when this is invoked. Also tell RCU about it.
+ *
+ * 1) Trace interrupts on state
+ * 2) Invoke context tracking if enabled to adjust RCU state
+ * 3) Invoke architecture specific last minute exit code, e.g. speculation
+ *    mitigations, etc.: arch_exit_to_user_mode()
+ * 4) Tell lockdep that interrupts are enabled
+ *
+ * Invoked from architecture specific code when syscall_exit_to_user_mode()
+ * is not suitable as the last step before returning to userspace. Must be
+ * invoked with interrupts disabled and the caller must be
+ * non-instrumentable.
+ * The caller has to invoke syscall_exit_to_user_mode_work() before this.
+ */
+void exit_to_user_mode(void);
+
+/**
+ * syscall_exit_to_user_mode_work - Handle work before returning to user mode
+ * @regs:	Pointer to currents pt_regs
+ *
+ * Same as step 1 and 2 of syscall_exit_to_user_mode() but without calling
+ * exit_to_user_mode() to perform the final transition to user mode.
+ *
+ * Calling convention is the same as for syscall_exit_to_user_mode() and it
+ * returns with all work handled and interrupts disabled. The caller must
+ * invoke exit_to_user_mode() before actually switching to user mode to
+ * make the final state transitions. Interrupts must stay disabled between
+ * return from this function and the invocation of exit_to_user_mode().
+ */
+void syscall_exit_to_user_mode_work(struct pt_regs *regs);
+
+/**
  * syscall_exit_to_user_mode - Handle work before returning to user mode
  * @regs:	Pointer to currents pt_regs
  *
@@ -307,8 +357,12 @@ static inline void arch_syscall_exit_tracehook(struct pt_regs *regs, bool step)
  *	- Architecture specific one time work arch_exit_to_user_mode_prepare()
  *	- Address limit and lockdep checks
  *
- *  3) Final transition (lockdep, tracing, context tracking, RCU). Invokes
- *     arch_exit_to_user_mode() to handle e.g. speculation mitigations
+ *  3) Final transition (lockdep, tracing, context tracking, RCU), i.e. the
+ *     functionality in exit_to_user_mode().
+ *
+ * This is a combination of syscall_exit_to_user_mode_work() (1,2) and
+ * exit_to_user_mode(). This function is preferred unless there is a
+ * compelling architectural reason to use the seperate functions.
  */
 void syscall_exit_to_user_mode(struct pt_regs *regs);
 
@@ -341,8 +395,26 @@ void irqentry_enter_from_user_mode(struct pt_regs *regs);
 void irqentry_exit_to_user_mode(struct pt_regs *regs);
 
 #ifndef irqentry_state
+/**
+ * struct irqentry_state - Opaque object for exception state storage
+ * @exit_rcu: Used exclusively in the irqentry_*() calls; signals whether the
+ *            exit path has to invoke rcu_irq_exit().
+ * @lockdep: Used exclusively in the irqentry_nmi_*() calls; ensures that
+ *           lockdep state is restored correctly on exit from nmi.
+ *
+ * This opaque object is filled in by the irqentry_*_enter() functions and
+ * must be passed back into the corresponding irqentry_*_exit() functions
+ * when the exception is complete.
+ *
+ * Callers of irqentry_*_[enter|exit]() must consider this structure opaque
+ * and all members private.  Descriptions of the members are provided to aid in
+ * the maintenance of the irqentry_*() functions.
+ */
 typedef struct irqentry_state {
-	bool	exit_rcu;
+	union {
+		bool	exit_rcu;
+		bool	lockdep;
+	};
 } irqentry_state_t;
 #endif
 
@@ -392,7 +464,7 @@ void irqentry_exit_cond_resched(void);
  * @state:	Return value from matching call to irqentry_enter()
  *
  * Depending on the return target (kernel/user) this runs the necessary
- * preemption and work checks if possible and reguired and returns to
+ * preemption and work checks if possible and required and returns to
  * the caller with interrupts disabled and no further work pending.
  *
  * This is the last action before returning to the low level ASM code which
@@ -402,4 +474,23 @@ void irqentry_exit_cond_resched(void);
  */
 void noinstr irqentry_exit(struct pt_regs *regs, irqentry_state_t state);
 
+/**
+ * irqentry_nmi_enter - Handle NMI entry
+ * @regs:	Pointer to currents pt_regs
+ *
+ * Similar to irqentry_enter() but taking care of the NMI constraints.
+ */
+irqentry_state_t noinstr irqentry_nmi_enter(struct pt_regs *regs);
+
+/**
+ * irqentry_nmi_exit - Handle return from NMI handling
+ * @regs:	Pointer to pt_regs (NMI entry regs)
+ * @irq_state:	Return value from matching call to irqentry_nmi_enter()
+ *
+ * Last action before returning to the low level assembly code.
+ *
+ * Counterpart to irqentry_nmi_enter().
+ */
+void noinstr irqentry_nmi_exit(struct pt_regs *regs, irqentry_state_t irq_state);
+
 #endif
diff --git a/include/linux/entry-kvm.h b/include/linux/entry-kvm.h
index 0cef17afb41a..9b93f8584ff7 100644
--- a/include/linux/entry-kvm.h
+++ b/include/linux/entry-kvm.h
@@ -11,8 +11,8 @@
 # define ARCH_XFER_TO_GUEST_MODE_WORK	(0)
 #endif
 
-#define XFER_TO_GUEST_MODE_WORK					\
-	(_TIF_NEED_RESCHED | _TIF_SIGPENDING |			\
+#define XFER_TO_GUEST_MODE_WORK						\
+	(_TIF_NEED_RESCHED | _TIF_SIGPENDING | _TIF_NOTIFY_SIGNAL |	\
 	 _TIF_NOTIFY_RESUME | ARCH_XFER_TO_GUEST_MODE_WORK)
 
 struct kvm_vcpu;
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 76cd21fa5501..1cac7efabc83 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -28,6 +28,7 @@
 #include <linux/sched/prio.h>
 #include <linux/sched/types.h>
 #include <linux/signal_types.h>
+#include <linux/syscall_user_dispatch.h>
 #include <linux/mm_types_task.h>
 #include <linux/task_io_accounting.h>
 #include <linux/posix-timers.h>
@@ -987,6 +988,7 @@ struct task_struct {
 	unsigned int			sessionid;
 #endif
 	struct seccomp			seccomp;
+	struct syscall_user_dispatch	syscall_dispatch;
 
 	/* Thread group tracking: */
 	u64				parent_exec_id;
diff --git a/include/linux/sched/signal.h b/include/linux/sched/signal.h
index 1bad18a1d8ba..bd5afa076189 100644
--- a/include/linux/sched/signal.h
+++ b/include/linux/sched/signal.h
@@ -353,11 +353,25 @@ static inline int restart_syscall(void)
 	return -ERESTARTNOINTR;
 }
 
-static inline int signal_pending(struct task_struct *p)
+static inline int task_sigpending(struct task_struct *p)
 {
 	return unlikely(test_tsk_thread_flag(p,TIF_SIGPENDING));
 }
 
+static inline int signal_pending(struct task_struct *p)
+{
+#if defined(TIF_NOTIFY_SIGNAL)
+	/*
+	 * TIF_NOTIFY_SIGNAL isn't really a signal, but it requires the same
+	 * behavior in terms of ensuring that we break out of wait loops
+	 * so that notify signal callbacks can be processed.
+	 */
+	if (unlikely(test_tsk_thread_flag(p, TIF_NOTIFY_SIGNAL)))
+		return 1;
+#endif
+	return task_sigpending(p);
+}
+
 static inline int __fatal_signal_pending(struct task_struct *p)
 {
 	return unlikely(sigismember(&p->pending.signal, SIGKILL));
@@ -365,7 +379,7 @@ static inline int __fatal_signal_pending(struct task_struct *p)
 
 static inline int fatal_signal_pending(struct task_struct *p)
 {
-	return signal_pending(p) && __fatal_signal_pending(p);
+	return task_sigpending(p) && __fatal_signal_pending(p);
 }
 
 static inline int signal_pending_state(long state, struct task_struct *p)
@@ -502,7 +516,7 @@ extern int set_user_sigmask(const sigset_t __user *umask, size_t sigsetsize);
 static inline void restore_saved_sigmask_unless(bool interrupted)
 {
 	if (interrupted)
-		WARN_ON(!test_thread_flag(TIF_SIGPENDING));
+		WARN_ON(!signal_pending(current));
 	else
 		restore_saved_sigmask();
 }
diff --git a/include/linux/seccomp.h b/include/linux/seccomp.h
index 02aef2844c38..47763f3999f7 100644
--- a/include/linux/seccomp.h
+++ b/include/linux/seccomp.h
@@ -42,7 +42,7 @@ struct seccomp {
 extern int __secure_computing(const struct seccomp_data *sd);
 static inline int secure_computing(void)
 {
-	if (unlikely(test_thread_flag(TIF_SECCOMP)))
+	if (unlikely(test_syscall_work(SECCOMP)))
 		return  __secure_computing(NULL);
 	return 0;
 }
diff --git a/include/linux/syscall_user_dispatch.h b/include/linux/syscall_user_dispatch.h
new file mode 100644
index 000000000000..a0ae443fb7df
--- /dev/null
+++ b/include/linux/syscall_user_dispatch.h
@@ -0,0 +1,40 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (C) 2020 Collabora Ltd.
+ */
+#ifndef _SYSCALL_USER_DISPATCH_H
+#define _SYSCALL_USER_DISPATCH_H
+
+#include <linux/thread_info.h>
+
+#ifdef CONFIG_GENERIC_ENTRY
+
+struct syscall_user_dispatch {
+	char __user	*selector;
+	unsigned long	offset;
+	unsigned long	len;
+	bool		on_dispatch;
+};
+
+int set_syscall_user_dispatch(unsigned long mode, unsigned long offset,
+			      unsigned long len, char __user *selector);
+
+#define clear_syscall_work_syscall_user_dispatch(tsk) \
+	clear_task_syscall_work(tsk, SYSCALL_USER_DISPATCH)
+
+#else
+struct syscall_user_dispatch {};
+
+static inline int set_syscall_user_dispatch(unsigned long mode, unsigned long offset,
+					    unsigned long len, char __user *selector)
+{
+	return -EINVAL;
+}
+
+static inline void clear_syscall_work_syscall_user_dispatch(struct task_struct *tsk)
+{
+}
+
+#endif /* CONFIG_GENERIC_ENTRY */
+
+#endif /* _SYSCALL_USER_DISPATCH_H */
diff --git a/include/linux/thread_info.h b/include/linux/thread_info.h
index e93e249a4e9b..c8a974cead73 100644
--- a/include/linux/thread_info.h
+++ b/include/linux/thread_info.h
@@ -35,6 +35,24 @@ enum {
 	GOOD_STACK,
 };
 
+#ifdef CONFIG_GENERIC_ENTRY
+enum syscall_work_bit {
+	SYSCALL_WORK_BIT_SECCOMP,
+	SYSCALL_WORK_BIT_SYSCALL_TRACEPOINT,
+	SYSCALL_WORK_BIT_SYSCALL_TRACE,
+	SYSCALL_WORK_BIT_SYSCALL_EMU,
+	SYSCALL_WORK_BIT_SYSCALL_AUDIT,
+	SYSCALL_WORK_BIT_SYSCALL_USER_DISPATCH,
+};
+
+#define SYSCALL_WORK_SECCOMP		BIT(SYSCALL_WORK_BIT_SECCOMP)
+#define SYSCALL_WORK_SYSCALL_TRACEPOINT	BIT(SYSCALL_WORK_BIT_SYSCALL_TRACEPOINT)
+#define SYSCALL_WORK_SYSCALL_TRACE	BIT(SYSCALL_WORK_BIT_SYSCALL_TRACE)
+#define SYSCALL_WORK_SYSCALL_EMU	BIT(SYSCALL_WORK_BIT_SYSCALL_EMU)
+#define SYSCALL_WORK_SYSCALL_AUDIT	BIT(SYSCALL_WORK_BIT_SYSCALL_AUDIT)
+#define SYSCALL_WORK_SYSCALL_USER_DISPATCH BIT(SYSCALL_WORK_BIT_SYSCALL_USER_DISPATCH)
+#endif
+
 #include <asm/thread_info.h>
 
 #ifdef __KERNEL__
@@ -97,6 +115,38 @@ static inline int test_ti_thread_flag(struct thread_info *ti, int flag)
 #define test_thread_flag(flag) \
 	test_ti_thread_flag(current_thread_info(), flag)
 
+#ifdef CONFIG_GENERIC_ENTRY
+#define set_syscall_work(fl) \
+	set_bit(SYSCALL_WORK_BIT_##fl, &current_thread_info()->syscall_work)
+#define test_syscall_work(fl) \
+	test_bit(SYSCALL_WORK_BIT_##fl, &current_thread_info()->syscall_work)
+#define clear_syscall_work(fl) \
+	clear_bit(SYSCALL_WORK_BIT_##fl, &current_thread_info()->syscall_work)
+
+#define set_task_syscall_work(t, fl) \
+	set_bit(SYSCALL_WORK_BIT_##fl, &task_thread_info(t)->syscall_work)
+#define test_task_syscall_work(t, fl) \
+	test_bit(SYSCALL_WORK_BIT_##fl, &task_thread_info(t)->syscall_work)
+#define clear_task_syscall_work(t, fl) \
+	clear_bit(SYSCALL_WORK_BIT_##fl, &task_thread_info(t)->syscall_work)
+
+#else /* CONFIG_GENERIC_ENTRY */
+
+#define set_syscall_work(fl)						\
+	set_ti_thread_flag(current_thread_info(), TIF_##fl)
+#define test_syscall_work(fl) \
+	test_ti_thread_flag(current_thread_info(), TIF_##fl)
+#define clear_syscall_work(fl) \
+	clear_ti_thread_flag(current_thread_info(), TIF_##fl)
+
+#define set_task_syscall_work(t, fl) \
+	set_ti_thread_flag(task_thread_info(t), TIF_##fl)
+#define test_task_syscall_work(t, fl) \
+	test_ti_thread_flag(task_thread_info(t), TIF_##fl)
+#define clear_task_syscall_work(t, fl) \
+	clear_ti_thread_flag(task_thread_info(t), TIF_##fl)
+#endif /* !CONFIG_GENERIC_ENTRY */
+
 #define tif_need_resched() test_thread_flag(TIF_NEED_RESCHED)
 
 #ifndef CONFIG_HAVE_ARCH_WITHIN_STACK_FRAMES
diff --git a/include/linux/tracehook.h b/include/linux/tracehook.h
index b480e1a07ed8..54b925224a13 100644
--- a/include/linux/tracehook.h
+++ b/include/linux/tracehook.h
@@ -83,11 +83,12 @@ static inline int ptrace_report_syscall(struct pt_regs *regs,
  * tracehook_report_syscall_entry - task is about to attempt a system call
  * @regs:		user register state of current task
  *
- * This will be called if %TIF_SYSCALL_TRACE or %TIF_SYSCALL_EMU have been set,
- * when the current task has just entered the kernel for a system call.
- * Full user register state is available here.  Changing the values
- * in @regs can affect the system call number and arguments to be tried.
- * It is safe to block here, preventing the system call from beginning.
+ * This will be called if %SYSCALL_WORK_SYSCALL_TRACE or
+ * %SYSCALL_WORK_SYSCALL_EMU have been set, when the current task has just
+ * entered the kernel for a system call.  Full user register state is
+ * available here.  Changing the values in @regs can affect the system
+ * call number and arguments to be tried.  It is safe to block here,
+ * preventing the system call from beginning.
  *
  * Returns zero normally, or nonzero if the calling arch code should abort
  * the system call.  That must prevent normal entry so no system call is
@@ -109,15 +110,15 @@ static inline __must_check int tracehook_report_syscall_entry(
  * @regs:		user register state of current task
  * @step:		nonzero if simulating single-step or block-step
  *
- * This will be called if %TIF_SYSCALL_TRACE has been set, when the
- * current task has just finished an attempted system call.  Full
+ * This will be called if %SYSCALL_WORK_SYSCALL_TRACE has been set, when
+ * the current task has just finished an attempted system call.  Full
  * user register state is available here.  It is safe to block here,
  * preventing signals from being processed.
  *
  * If @step is nonzero, this report is also in lieu of the normal
  * trap that would follow the system call instruction because
  * user_enable_block_step() or user_enable_single_step() was used.
- * In this case, %TIF_SYSCALL_TRACE might not be set.
+ * In this case, %SYSCALL_WORK_SYSCALL_TRACE might not be set.
  *
  * Called without locks, just before checking for pending signals.
  */
@@ -198,4 +199,31 @@ static inline void tracehook_notify_resume(struct pt_regs *regs)
 	blkcg_maybe_throttle_current();
 }
 
+/*
+ * called by exit_to_user_mode_loop() if ti_work & _TIF_NOTIFY_SIGNAL. This
+ * is currently used by TWA_SIGNAL based task_work, which requires breaking
+ * wait loops to ensure that task_work is noticed and run.
+ */
+static inline void tracehook_notify_signal(void)
+{
+#if defined(TIF_NOTIFY_SIGNAL)
+	clear_thread_flag(TIF_NOTIFY_SIGNAL);
+	smp_mb__after_atomic();
+	if (current->task_works)
+		task_work_run();
+#endif
+}
+
+/*
+ * Called when we have work to process from exit_to_user_mode_loop()
+ */
+static inline void set_notify_signal(struct task_struct *task)
+{
+#if defined(TIF_NOTIFY_SIGNAL)
+	if (!test_and_set_tsk_thread_flag(task, TIF_NOTIFY_SIGNAL) &&
+	    !wake_up_state(task, TASK_INTERRUPTIBLE))
+		kick_process(task);
+#endif
+}
+
 #endif	/* <linux/tracehook.h> */
diff --git a/include/trace/syscall.h b/include/trace/syscall.h
index dc8ac27d27c1..8e193f3a33b3 100644
--- a/include/trace/syscall.h
+++ b/include/trace/syscall.h
@@ -37,10 +37,10 @@ struct syscall_metadata {
 #if defined(CONFIG_TRACEPOINTS) && defined(CONFIG_HAVE_SYSCALL_TRACEPOINTS)
 static inline void syscall_tracepoint_update(struct task_struct *p)
 {
-	if (test_thread_flag(TIF_SYSCALL_TRACEPOINT))
-		set_tsk_thread_flag(p, TIF_SYSCALL_TRACEPOINT);
+	if (test_syscall_work(SYSCALL_TRACEPOINT))
+		set_task_syscall_work(p, SYSCALL_TRACEPOINT);
 	else
-		clear_tsk_thread_flag(p, TIF_SYSCALL_TRACEPOINT);
+		clear_task_syscall_work(p, SYSCALL_TRACEPOINT);
 }
 #else
 static inline void syscall_tracepoint_update(struct task_struct *p)
diff --git a/include/uapi/asm-generic/siginfo.h b/include/uapi/asm-generic/siginfo.h
index 7aacf9389010..d2597000407a 100644
--- a/include/uapi/asm-generic/siginfo.h
+++ b/include/uapi/asm-generic/siginfo.h
@@ -286,7 +286,8 @@ typedef struct siginfo {
  * SIGSYS si_codes
  */
 #define SYS_SECCOMP	1	/* seccomp triggered */
-#define NSIGSYS		1
+#define SYS_USER_DISPATCH 2	/* syscall user dispatch triggered */
+#define NSIGSYS		2
 
 /*
  * SIGEMT si_codes
diff --git a/include/uapi/linux/prctl.h b/include/uapi/linux/prctl.h
index 7f0827705c9a..90deb41c8a34 100644
--- a/include/uapi/linux/prctl.h
+++ b/include/uapi/linux/prctl.h
@@ -247,4 +247,9 @@ 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 */