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
  ...

16 files changed, 323 insertions, 101 deletions

diff --git a/kernel/auditsc.c b/kernel/auditsc.c
index 8dba8f0983b5..c00aa5837965 100644
--- a/kernel/auditsc.c
+++ b/kernel/auditsc.c
@@ -952,7 +952,7 @@ int audit_alloc(struct task_struct *tsk)
 
 	state = audit_filter_task(tsk, &key);
 	if (state == AUDIT_DISABLED) {
-		clear_tsk_thread_flag(tsk, TIF_SYSCALL_AUDIT);
+		clear_task_syscall_work(tsk, SYSCALL_AUDIT);
 		return 0;
 	}
 
@@ -964,7 +964,7 @@ int audit_alloc(struct task_struct *tsk)
 	context->filterkey = key;
 
 	audit_set_context(tsk, context);
-	set_tsk_thread_flag(tsk, TIF_SYSCALL_AUDIT);
+	set_task_syscall_work(tsk, SYSCALL_AUDIT);
 	return 0;
 }
 
diff --git a/kernel/entry/Makefile b/kernel/entry/Makefile
index 34c8a3f1c735..095c775e001e 100644
--- a/kernel/entry/Makefile
+++ b/kernel/entry/Makefile
@@ -9,5 +9,5 @@ KCOV_INSTRUMENT := n
 CFLAGS_REMOVE_common.o	 = -fstack-protector -fstack-protector-strong
 CFLAGS_common.o		+= -fno-stack-protector
 
-obj-$(CONFIG_GENERIC_ENTRY) 		+= common.o
+obj-$(CONFIG_GENERIC_ENTRY) 		+= common.o syscall_user_dispatch.o
 obj-$(CONFIG_KVM_XFER_TO_GUEST_WORK)	+= kvm.o
diff --git a/kernel/entry/common.c b/kernel/entry/common.c
index e9e2df3f3f9e..d6b73937dab3 100644
--- a/kernel/entry/common.c
+++ b/kernel/entry/common.c
@@ -5,20 +5,13 @@
 #include <linux/livepatch.h>
 #include <linux/audit.h>
 
+#include "common.h"
+
 #define CREATE_TRACE_POINTS
 #include <trace/events/syscalls.h>
 
-/**
- * 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
- */
-static __always_inline void enter_from_user_mode(struct pt_regs *regs)
+/* See comment for enter_from_user_mode() in entry-common.h */
+static __always_inline void __enter_from_user_mode(struct pt_regs *regs)
 {
 	arch_check_user_regs(regs);
 	lockdep_hardirqs_off(CALLER_ADDR0);
@@ -31,6 +24,11 @@ static __always_inline void enter_from_user_mode(struct pt_regs *regs)
 	instrumentation_end();
 }
 
+void noinstr enter_from_user_mode(struct pt_regs *regs)
+{
+	__enter_from_user_mode(regs);
+}
+
 static inline void syscall_enter_audit(struct pt_regs *regs, long syscall)
 {
 	if (unlikely(audit_context())) {
@@ -42,19 +40,29 @@ static inline void syscall_enter_audit(struct pt_regs *regs, long syscall)
 }
 
 static long syscall_trace_enter(struct pt_regs *regs, long syscall,
-				unsigned long ti_work)
+				unsigned long work)
 {
 	long ret = 0;
 
+	/*
+	 * Handle Syscall User Dispatch.  This must comes first, since
+	 * the ABI here can be something that doesn't make sense for
+	 * other syscall_work features.
+	 */
+	if (work & SYSCALL_WORK_SYSCALL_USER_DISPATCH) {
+		if (syscall_user_dispatch(regs))
+			return -1L;
+	}
+
 	/* Handle ptrace */
-	if (ti_work & (_TIF_SYSCALL_TRACE | _TIF_SYSCALL_EMU)) {
+	if (work & (SYSCALL_WORK_SYSCALL_TRACE | SYSCALL_WORK_SYSCALL_EMU)) {
 		ret = arch_syscall_enter_tracehook(regs);
-		if (ret || (ti_work & _TIF_SYSCALL_EMU))
+		if (ret || (work & SYSCALL_WORK_SYSCALL_EMU))
 			return -1L;
 	}
 
 	/* Do seccomp after ptrace, to catch any tracer changes. */
-	if (ti_work & _TIF_SECCOMP) {
+	if (work & SYSCALL_WORK_SECCOMP) {
 		ret = __secure_computing(NULL);
 		if (ret == -1L)
 			return ret;
@@ -63,7 +71,7 @@ static long syscall_trace_enter(struct pt_regs *regs, long syscall,
 	/* Either of the above might have changed the syscall number */
 	syscall = syscall_get_nr(current, regs);
 
-	if (unlikely(ti_work & _TIF_SYSCALL_TRACEPOINT))
+	if (unlikely(work & SYSCALL_WORK_SYSCALL_TRACEPOINT))
 		trace_sys_enter(regs, syscall);
 
 	syscall_enter_audit(regs, syscall);
@@ -74,11 +82,10 @@ static long syscall_trace_enter(struct pt_regs *regs, long syscall,
 static __always_inline long
 __syscall_enter_from_user_work(struct pt_regs *regs, long syscall)
 {
-	unsigned long ti_work;
+	unsigned long work = READ_ONCE(current_thread_info()->syscall_work);
 
-	ti_work = READ_ONCE(current_thread_info()->flags);
-	if (ti_work & SYSCALL_ENTER_WORK)
-		syscall = syscall_trace_enter(regs, syscall, ti_work);
+	if (work & SYSCALL_WORK_ENTER)
+		syscall = syscall_trace_enter(regs, syscall, work);
 
 	return syscall;
 }
@@ -92,7 +99,7 @@ noinstr long syscall_enter_from_user_mode(struct pt_regs *regs, long syscall)
 {
 	long ret;
 
-	enter_from_user_mode(regs);
+	__enter_from_user_mode(regs);
 
 	instrumentation_begin();
 	local_irq_enable();
@@ -104,25 +111,14 @@ noinstr long syscall_enter_from_user_mode(struct pt_regs *regs, long syscall)
 
 noinstr void syscall_enter_from_user_mode_prepare(struct pt_regs *regs)
 {
-	enter_from_user_mode(regs);
+	__enter_from_user_mode(regs);
 	instrumentation_begin();
 	local_irq_enable();
 	instrumentation_end();
 }
 
-/**
- * exit_to_user_mode - Fixup state when exiting to user mode
- *
- * Syscall/interupt 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.
- * 4) Tell lockdep that interrupts are enabled
- */
-static __always_inline void exit_to_user_mode(void)
+/* See comment for exit_to_user_mode() in entry-common.h */
+static __always_inline void __exit_to_user_mode(void)
 {
 	instrumentation_begin();
 	trace_hardirqs_on_prepare();
@@ -134,8 +130,21 @@ static __always_inline void exit_to_user_mode(void)
 	lockdep_hardirqs_on(CALLER_ADDR0);
 }
 
+void noinstr exit_to_user_mode(void)
+{
+	__exit_to_user_mode();
+}
+
 /* Workaround to allow gradual conversion of architecture code */
-void __weak arch_do_signal(struct pt_regs *regs) { }
+void __weak arch_do_signal_or_restart(struct pt_regs *regs, bool has_signal) { }
+
+static void handle_signal_work(struct pt_regs *regs, unsigned long ti_work)
+{
+	if (ti_work & _TIF_NOTIFY_SIGNAL)
+		tracehook_notify_signal();
+
+	arch_do_signal_or_restart(regs, ti_work & _TIF_SIGPENDING);
+}
 
 static unsigned long exit_to_user_mode_loop(struct pt_regs *regs,
 					    unsigned long ti_work)
@@ -157,8 +166,8 @@ static unsigned long exit_to_user_mode_loop(struct pt_regs *regs,
 		if (ti_work & _TIF_PATCH_PENDING)
 			klp_update_patch_state(current);
 
-		if (ti_work & _TIF_SIGPENDING)
-			arch_do_signal(regs);
+		if (ti_work & (_TIF_SIGPENDING | _TIF_NOTIFY_SIGNAL))
+			handle_signal_work(regs, ti_work);
 
 		if (ti_work & _TIF_NOTIFY_RESUME) {
 			tracehook_notify_resume(regs);
@@ -199,35 +208,50 @@ static void exit_to_user_mode_prepare(struct pt_regs *regs)
 }
 
 #ifndef _TIF_SINGLESTEP
-static inline bool report_single_step(unsigned long ti_work)
+static inline bool report_single_step(unsigned long work)
 {
 	return false;
 }
 #else
 /*
- * If TIF_SYSCALL_EMU is set, then the only reason to report is when
+ * If SYSCALL_EMU is set, then the only reason to report is when
  * TIF_SINGLESTEP is set (i.e. PTRACE_SYSEMU_SINGLESTEP).  This syscall
  * instruction has been already reported in syscall_enter_from_user_mode().
  */
-#define SYSEMU_STEP	(_TIF_SINGLESTEP | _TIF_SYSCALL_EMU)
-
-static inline bool report_single_step(unsigned long ti_work)
+static inline bool report_single_step(unsigned long work)
 {
-	return (ti_work & SYSEMU_STEP) == _TIF_SINGLESTEP;
+	if (!(work & SYSCALL_WORK_SYSCALL_EMU))
+		return false;
+
+	return !!(current_thread_info()->flags & _TIF_SINGLESTEP);
 }
 #endif
 
-static void syscall_exit_work(struct pt_regs *regs, unsigned long ti_work)
+
+static void syscall_exit_work(struct pt_regs *regs, unsigned long work)
 {
 	bool step;
 
+	/*
+	 * If the syscall was rolled back due to syscall user dispatching,
+	 * then the tracers below are not invoked for the same reason as
+	 * the entry side was not invoked in syscall_trace_enter(): The ABI
+	 * of these syscalls is unknown.
+	 */
+	if (work & SYSCALL_WORK_SYSCALL_USER_DISPATCH) {
+		if (unlikely(current->syscall_dispatch.on_dispatch)) {
+			current->syscall_dispatch.on_dispatch = false;
+			return;
+		}
+	}
+
 	audit_syscall_exit(regs);
 
-	if (ti_work & _TIF_SYSCALL_TRACEPOINT)
+	if (work & SYSCALL_WORK_SYSCALL_TRACEPOINT)
 		trace_sys_exit(regs, syscall_get_return_value(current, regs));
 
-	step = report_single_step(ti_work);
-	if (step || ti_work & _TIF_SYSCALL_TRACE)
+	step = report_single_step(work);
+	if (step || work & SYSCALL_WORK_SYSCALL_TRACE)
 		arch_syscall_exit_tracehook(regs, step);
 }
 
@@ -237,7 +261,7 @@ static void syscall_exit_work(struct pt_regs *regs, unsigned long ti_work)
  */
 static void syscall_exit_to_user_mode_prepare(struct pt_regs *regs)
 {
-	u32 cached_flags = READ_ONCE(current_thread_info()->flags);
+	unsigned long work = READ_ONCE(current_thread_info()->syscall_work);
 	unsigned long nr = syscall_get_nr(current, regs);
 
 	CT_WARN_ON(ct_state() != CONTEXT_KERNEL);
@@ -254,23 +278,33 @@ static void syscall_exit_to_user_mode_prepare(struct pt_regs *regs)
 	 * enabled, we want to run them exactly once per syscall exit with
 	 * interrupts enabled.
 	 */
-	if (unlikely(cached_flags & SYSCALL_EXIT_WORK))
-		syscall_exit_work(regs, cached_flags);
+	if (unlikely(work & SYSCALL_WORK_EXIT))
+		syscall_exit_work(regs, work);
 }
 
-__visible noinstr void syscall_exit_to_user_mode(struct pt_regs *regs)
+static __always_inline void __syscall_exit_to_user_mode_work(struct pt_regs *regs)
 {
-	instrumentation_begin();
 	syscall_exit_to_user_mode_prepare(regs);
 	local_irq_disable_exit_to_user();
 	exit_to_user_mode_prepare(regs);
+}
+
+void syscall_exit_to_user_mode_work(struct pt_regs *regs)
+{
+	__syscall_exit_to_user_mode_work(regs);
+}
+
+__visible noinstr void syscall_exit_to_user_mode(struct pt_regs *regs)
+{
+	instrumentation_begin();
+	__syscall_exit_to_user_mode_work(regs);
 	instrumentation_end();
-	exit_to_user_mode();
+	__exit_to_user_mode();
 }
 
 noinstr void irqentry_enter_from_user_mode(struct pt_regs *regs)
 {
-	enter_from_user_mode(regs);
+	__enter_from_user_mode(regs);
 }
 
 noinstr void irqentry_exit_to_user_mode(struct pt_regs *regs)
@@ -278,7 +312,7 @@ noinstr void irqentry_exit_to_user_mode(struct pt_regs *regs)
 	instrumentation_begin();
 	exit_to_user_mode_prepare(regs);
 	instrumentation_end();
-	exit_to_user_mode();
+	__exit_to_user_mode();
 }
 
 noinstr irqentry_state_t irqentry_enter(struct pt_regs *regs)
@@ -296,7 +330,7 @@ noinstr irqentry_state_t irqentry_enter(struct pt_regs *regs)
 	 * If this entry hit the idle task invoke rcu_irq_enter() whether
 	 * RCU is watching or not.
 	 *
-	 * Interupts can nest when the first interrupt invokes softirq
+	 * Interrupts can nest when the first interrupt invokes softirq
 	 * processing on return which enables interrupts.
 	 *
 	 * Scheduler ticks in the idle task can mark quiescent state and
@@ -307,7 +341,7 @@ noinstr irqentry_state_t irqentry_enter(struct pt_regs *regs)
 	 * interrupt to invoke rcu_irq_enter(). If that nested interrupt is
 	 * the tick then rcu_flavor_sched_clock_irq() would wrongfully
 	 * assume that it is the first interupt and eventually claim
-	 * quiescient state and end grace periods prematurely.
+	 * quiescent state and end grace periods prematurely.
 	 *
 	 * Unconditionally invoke rcu_irq_enter() so RCU state stays
 	 * consistent.
@@ -319,7 +353,7 @@ noinstr irqentry_state_t irqentry_enter(struct pt_regs *regs)
 		/*
 		 * If RCU is not watching then the same careful
 		 * sequence vs. lockdep and tracing is required
-		 * as in irq_enter_from_user_mode().
+		 * as in irqentry_enter_from_user_mode().
 		 */
 		lockdep_hardirqs_off(CALLER_ADDR0);
 		rcu_irq_enter();
@@ -397,3 +431,39 @@ noinstr void irqentry_exit(struct pt_regs *regs, irqentry_state_t state)
 			rcu_irq_exit();
 	}
 }
+
+irqentry_state_t noinstr irqentry_nmi_enter(struct pt_regs *regs)
+{
+	irqentry_state_t irq_state;
+
+	irq_state.lockdep = lockdep_hardirqs_enabled();
+
+	__nmi_enter();
+	lockdep_hardirqs_off(CALLER_ADDR0);
+	lockdep_hardirq_enter();
+	rcu_nmi_enter();
+
+	instrumentation_begin();
+	trace_hardirqs_off_finish();
+	ftrace_nmi_enter();
+	instrumentation_end();
+
+	return irq_state;
+}
+
+void noinstr irqentry_nmi_exit(struct pt_regs *regs, irqentry_state_t irq_state)
+{
+	instrumentation_begin();
+	ftrace_nmi_exit();
+	if (irq_state.lockdep) {
+		trace_hardirqs_on_prepare();
+		lockdep_hardirqs_on_prepare(CALLER_ADDR0);
+	}
+	instrumentation_end();
+
+	rcu_nmi_exit();
+	lockdep_hardirq_exit();
+	if (irq_state.lockdep)
+		lockdep_hardirqs_on(CALLER_ADDR0);
+	__nmi_exit();
+}
diff --git a/kernel/entry/common.h b/kernel/entry/common.h
new file mode 100644
index 000000000000..f6e6d02f07fe
--- /dev/null
+++ b/kernel/entry/common.h
@@ -0,0 +1,7 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _COMMON_H
+#define _COMMON_H
+
+bool syscall_user_dispatch(struct pt_regs *regs);
+
+#endif
diff --git a/kernel/entry/kvm.c b/kernel/entry/kvm.c
index b6678a5e3cf6..49972ee99aff 100644
--- a/kernel/entry/kvm.c
+++ b/kernel/entry/kvm.c
@@ -8,6 +8,9 @@ static int xfer_to_guest_mode_work(struct kvm_vcpu *vcpu, unsigned long ti_work)
 	do {
 		int ret;
 
+		if (ti_work & _TIF_NOTIFY_SIGNAL)
+			tracehook_notify_signal();
+
 		if (ti_work & _TIF_SIGPENDING) {
 			kvm_handle_signal_exit(vcpu);
 			return -EINTR;
diff --git a/kernel/entry/syscall_user_dispatch.c b/kernel/entry/syscall_user_dispatch.c
new file mode 100644
index 000000000000..b0338a5625d9
--- /dev/null
+++ b/kernel/entry/syscall_user_dispatch.c
@@ -0,0 +1,104 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2020 Collabora Ltd.
+ */
+#include <linux/sched.h>
+#include <linux/prctl.h>
+#include <linux/syscall_user_dispatch.h>
+#include <linux/uaccess.h>
+#include <linux/signal.h>
+#include <linux/elf.h>
+
+#include <linux/sched/signal.h>
+#include <linux/sched/task_stack.h>
+
+#include <asm/syscall.h>
+
+#include "common.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);
+}
+
+bool syscall_user_dispatch(struct pt_regs *regs)
+{
+	struct syscall_user_dispatch *sd = &current->syscall_dispatch;
+	char state;
+
+	if (likely(instruction_pointer(regs) - sd->offset < sd->len))
+		return false;
+
+	if (unlikely(arch_syscall_is_vdso_sigreturn(regs)))
+		return false;
+
+	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 false;
+
+		if (state != PR_SYS_DISPATCH_ON)
+			do_exit(SIGSYS);
+	}
+
+	sd->on_dispatch = true;
+	syscall_rollback(current, regs);
+	trigger_sigsys(regs);
+
+	return true;
+}
+
+int set_syscall_user_dispatch(unsigned long mode, unsigned long offset,
+			      unsigned long len, char __user *selector)
+{
+	switch (mode) {
+	case PR_SYS_DISPATCH_OFF:
+		if (offset || len || selector)
+			return -EINVAL;
+		break;
+	case PR_SYS_DISPATCH_ON:
+		/*
+		 * Validate the direct dispatcher region just for basic
+		 * sanity against overflow and a 0-sized dispatcher
+		 * region.  If the user is able to submit a syscall from
+		 * an address, that address is obviously valid.
+		 */
+		if (offset && offset + len <= offset)
+			return -EINVAL;
+
+		if (selector && !access_ok(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;
+
+	if (mode == PR_SYS_DISPATCH_ON)
+		set_syscall_work(SYSCALL_USER_DISPATCH);
+	else
+		clear_syscall_work(SYSCALL_USER_DISPATCH);
+
+	return 0;
+}
diff --git a/kernel/events/uprobes.c b/kernel/events/uprobes.c
index 00b0358739ab..bf9edd8d75be 100644
--- a/kernel/events/uprobes.c
+++ b/kernel/events/uprobes.c
@@ -1973,7 +1973,7 @@ bool uprobe_deny_signal(void)
 
 	WARN_ON_ONCE(utask->state != UTASK_SSTEP);
 
-	if (signal_pending(t)) {
+	if (task_sigpending(t)) {
 		spin_lock_irq(&t->sighand->siglock);
 		clear_tsk_thread_flag(t, TIF_SIGPENDING);
 		spin_unlock_irq(&t->sighand->siglock);
diff --git a/kernel/fork.c b/kernel/fork.c
index 6d266388d380..09be1be28cde 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -906,6 +906,7 @@ static struct task_struct *dup_task_struct(struct task_struct *orig, int node)
 	clear_user_return_notifier(tsk);
 	clear_tsk_need_resched(tsk);
 	set_task_stack_end_magic(tsk);
+	clear_syscall_work_syscall_user_dispatch(tsk);
 
 #ifdef CONFIG_STACKPROTECTOR
 	tsk->stack_canary = get_random_canary();
@@ -1625,7 +1626,7 @@ static void copy_seccomp(struct task_struct *p)
 	 * to manually enable the seccomp thread flag here.
 	 */
 	if (p->seccomp.mode != SECCOMP_MODE_DISABLED)
-		set_tsk_thread_flag(p, TIF_SECCOMP);
+		set_task_syscall_work(p, SECCOMP);
 #endif
 }
 
@@ -2158,9 +2159,9 @@ static __latent_entropy struct task_struct *copy_process(
 	 * child regardless of CLONE_PTRACE.
 	 */
 	user_disable_single_step(p);
-	clear_tsk_thread_flag(p, TIF_SYSCALL_TRACE);
-#ifdef TIF_SYSCALL_EMU
-	clear_tsk_thread_flag(p, TIF_SYSCALL_EMU);
+	clear_task_syscall_work(p, SYSCALL_TRACE);
+#if defined(CONFIG_GENERIC_ENTRY) || defined(TIF_SYSCALL_EMU)
+	clear_task_syscall_work(p, SYSCALL_EMU);
 #endif
 	clear_tsk_latency_tracing(p);
 
diff --git a/kernel/ptrace.c b/kernel/ptrace.c
index 79de1294f8eb..add677d79fcf 100644
--- a/kernel/ptrace.c
+++ b/kernel/ptrace.c
@@ -117,9 +117,9 @@ void __ptrace_unlink(struct task_struct *child)
 	const struct cred *old_cred;
 	BUG_ON(!child->ptrace);
 
-	clear_tsk_thread_flag(child, TIF_SYSCALL_TRACE);
-#ifdef TIF_SYSCALL_EMU
-	clear_tsk_thread_flag(child, TIF_SYSCALL_EMU);
+	clear_task_syscall_work(child, SYSCALL_TRACE);
+#if defined(CONFIG_GENERIC_ENTRY) || defined(TIF_SYSCALL_EMU)
+	clear_task_syscall_work(child, SYSCALL_EMU);
 #endif
 
 	child->parent = child->real_parent;
@@ -806,15 +806,15 @@ static int ptrace_resume(struct task_struct *child, long request,
 		return -EIO;
 
 	if (request == PTRACE_SYSCALL)
-		set_tsk_thread_flag(child, TIF_SYSCALL_TRACE);
+		set_task_syscall_work(child, SYSCALL_TRACE);
 	else
-		clear_tsk_thread_flag(child, TIF_SYSCALL_TRACE);
+		clear_task_syscall_work(child, SYSCALL_TRACE);
 
-#ifdef TIF_SYSCALL_EMU
+#if defined(CONFIG_GENERIC_ENTRY) || defined(TIF_SYSCALL_EMU)
 	if (request == PTRACE_SYSEMU || request == PTRACE_SYSEMU_SINGLESTEP)
-		set_tsk_thread_flag(child, TIF_SYSCALL_EMU);
+		set_task_syscall_work(child, SYSCALL_EMU);
 	else
-		clear_tsk_thread_flag(child, TIF_SYSCALL_EMU);
+		clear_task_syscall_work(child, SYSCALL_EMU);
 #endif
 
 	if (is_singleblock(request)) {
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index e7e453492cff..e0948cbb1d70 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -4296,6 +4296,7 @@ static inline void schedule_debug(struct task_struct *prev, bool preempt)
 		preempt_count_set(PREEMPT_DISABLED);
 	}
 	rcu_sleep_check();
+	SCHED_WARN_ON(ct_state() == CONTEXT_USER);
 
 	profile_hit(SCHED_PROFILING, __builtin_return_address(0));
 
@@ -4635,7 +4636,7 @@ void __sched schedule_idle(void)
 	} while (need_resched());
 }
 
-#ifdef CONFIG_CONTEXT_TRACKING
+#if defined(CONFIG_CONTEXT_TRACKING) && !defined(CONFIG_HAVE_CONTEXT_TRACKING_OFFSTACK)
 asmlinkage __visible void __sched schedule_user(void)
 {
 	/*
diff --git a/kernel/seccomp.c b/kernel/seccomp.c
index 53a7d1512dd7..15f47fc11d13 100644
--- a/kernel/seccomp.c
+++ b/kernel/seccomp.c
@@ -356,14 +356,14 @@ static inline void seccomp_assign_mode(struct task_struct *task,
 
 	task->seccomp.mode = seccomp_mode;
 	/*
-	 * Make sure TIF_SECCOMP cannot be set before the mode (and
+	 * Make sure SYSCALL_WORK_SECCOMP cannot be set before the mode (and
 	 * filter) is set.
 	 */
 	smp_mb__before_atomic();
 	/* Assume default seccomp processes want spec flaw mitigation. */
 	if ((flags & SECCOMP_FILTER_FLAG_SPEC_ALLOW) == 0)
 		arch_seccomp_spec_mitigate(task);
-	set_tsk_thread_flag(task, TIF_SECCOMP);
+	set_task_syscall_work(task, SECCOMP);
 }
 
 #ifdef CONFIG_SECCOMP_FILTER
@@ -928,7 +928,7 @@ static int __seccomp_filter(int this_syscall, const struct seccomp_data *sd,
 
 	/*
 	 * Make sure that any changes to mode from another thread have
-	 * been seen after TIF_SECCOMP was seen.
+	 * been seen after SYSCALL_WORK_SECCOMP was seen.
 	 */
 	rmb();
 
diff --git a/kernel/signal.c b/kernel/signal.c
index 26018c59821d..c37170655171 100644
--- a/kernel/signal.c
+++ b/kernel/signal.c
@@ -984,7 +984,7 @@ static inline bool wants_signal(int sig, struct task_struct *p)
 	if (task_is_stopped_or_traced(p))
 		return false;
 
-	return task_curr(p) || !signal_pending(p);
+	return task_curr(p) || !task_sigpending(p);
 }
 
 static void complete_signal(int sig, struct task_struct *p, enum pid_type type)
@@ -2550,6 +2550,20 @@ bool get_signal(struct ksignal *ksig)
 	struct signal_struct *signal = current->signal;
 	int signr;
 
+	/*
+	 * For non-generic architectures, check for TIF_NOTIFY_SIGNAL so
+	 * that the arch handlers don't all have to do it. If we get here
+	 * without TIF_SIGPENDING, just exit after running signal work.
+	 */
+#ifdef TIF_NOTIFY_SIGNAL
+	if (!IS_ENABLED(CONFIG_GENERIC_ENTRY)) {
+		if (test_thread_flag(TIF_NOTIFY_SIGNAL))
+			tracehook_notify_signal();
+		if (!task_sigpending(current))
+			return false;
+	}
+#endif
+
 	if (unlikely(uprobe_deny_signal()))
 		return false;
 
@@ -2847,7 +2861,7 @@ static void retarget_shared_pending(struct task_struct *tsk, sigset_t *which)
 		/* Remove the signals this thread can handle. */
 		sigandsets(&retarget, &retarget, &t->blocked);
 
-		if (!signal_pending(t))
+		if (!task_sigpending(t))
 			signal_wake_up(t, 0);
 
 		if (sigisemptyset(&retarget))
@@ -2881,7 +2895,7 @@ void exit_signals(struct task_struct *tsk)
 
 	cgroup_threadgroup_change_end(tsk);
 
-	if (!signal_pending(tsk))
+	if (!task_sigpending(tsk))
 		goto out;
 
 	unblocked = tsk->blocked;
@@ -2925,7 +2939,7 @@ long do_no_restart_syscall(struct restart_block *param)
 
 static void __set_task_blocked(struct task_struct *tsk, const sigset_t *newset)
 {
-	if (signal_pending(tsk) && !thread_group_empty(tsk)) {
+	if (task_sigpending(tsk) && !thread_group_empty(tsk)) {
 		sigset_t newblocked;
 		/* A set of now blocked but previously unblocked signals. */
 		sigandnsets(&newblocked, newset, &current->blocked);
diff --git a/kernel/sys.c b/kernel/sys.c
index a730c03ee607..51f00fe20e4d 100644
--- a/kernel/sys.c
+++ b/kernel/sys.c
@@ -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(arg2, arg3, arg4,
+						  (char __user *) arg5);
+		break;
 	default:
 		error = -EINVAL;
 		break;
diff --git a/kernel/task_work.c b/kernel/task_work.c
index 8d6e1217c451..15b087286bea 100644
--- a/kernel/task_work.c
+++ b/kernel/task_work.c
@@ -5,6 +5,34 @@
 
 static struct callback_head work_exited; /* all we need is ->next == NULL */
 
+/*
+ * TWA_SIGNAL signaling - use TIF_NOTIFY_SIGNAL, if available, as it's faster
+ * than TIF_SIGPENDING as there's no dependency on ->sighand. The latter is
+ * shared for threads, and can cause contention on sighand->lock. Even for
+ * the non-threaded case TIF_NOTIFY_SIGNAL is more efficient, as no locking
+ * or IRQ disabling is involved for notification (or running) purposes.
+ */
+static void task_work_notify_signal(struct task_struct *task)
+{
+#if defined(TIF_NOTIFY_SIGNAL)
+	set_notify_signal(task);
+#else
+	unsigned long flags;
+
+	/*
+	 * Only grab the sighand lock if we don't already have some
+	 * task_work pending. This pairs with the smp_store_mb()
+	 * in get_signal(), see comment there.
+	 */
+	if (!(READ_ONCE(task->jobctl) & JOBCTL_TASK_WORK) &&
+	    lock_task_sighand(task, &flags)) {
+		task->jobctl |= JOBCTL_TASK_WORK;
+		signal_wake_up(task, 0);
+		unlock_task_sighand(task, &flags);
+	}
+#endif
+}
+
 /**
  * task_work_add - ask the @task to execute @work->func()
  * @task: the task which should run the callback
@@ -33,7 +61,6 @@ int task_work_add(struct task_struct *task, struct callback_head *work,
 		  enum task_work_notify_mode notify)
 {
 	struct callback_head *head;
-	unsigned long flags;
 
 	do {
 		head = READ_ONCE(task->task_works);
@@ -49,17 +76,7 @@ int task_work_add(struct task_struct *task, struct callback_head *work,
 		set_notify_resume(task);
 		break;
 	case TWA_SIGNAL:
-		/*
-		 * Only grab the sighand lock if we don't already have some
-		 * task_work pending. This pairs with the smp_store_mb()
-		 * in get_signal(), see comment there.
-		 */
-		if (!(READ_ONCE(task->jobctl) & JOBCTL_TASK_WORK) &&
-		    lock_task_sighand(task, &flags)) {
-			task->jobctl |= JOBCTL_TASK_WORK;
-			signal_wake_up(task, 0);
-			unlock_task_sighand(task, &flags);
-		}
+		task_work_notify_signal(task);
 		break;
 	default:
 		WARN_ON_ONCE(1);
diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c
index 47a71f96e5bc..adf65b502453 100644
--- a/kernel/trace/trace_events.c
+++ b/kernel/trace/trace_events.c
@@ -3428,10 +3428,10 @@ static __init int event_trace_enable(void)
  * initialize events and perhaps start any events that are on the
  * command line. Unfortunately, there are some events that will not
  * start this early, like the system call tracepoints that need
- * to set the TIF_SYSCALL_TRACEPOINT flag of pid 1. But event_trace_enable()
- * is called before pid 1 starts, and this flag is never set, making
- * the syscall tracepoint never get reached, but the event is enabled
- * regardless (and not doing anything).
+ * to set the %SYSCALL_WORK_SYSCALL_TRACEPOINT flag of pid 1. But
+ * event_trace_enable() is called before pid 1 starts, and this flag
+ * is never set, making the syscall tracepoint never get reached, but
+ * the event is enabled regardless (and not doing anything).
  */
 static __init int event_trace_enable_again(void)
 {
diff --git a/kernel/tracepoint.c b/kernel/tracepoint.c
index 3f659f855074..7261fa0f5e3c 100644
--- a/kernel/tracepoint.c
+++ b/kernel/tracepoint.c
@@ -594,7 +594,7 @@ int syscall_regfunc(void)
 	if (!sys_tracepoint_refcount) {
 		read_lock(&tasklist_lock);
 		for_each_process_thread(p, t) {
-			set_tsk_thread_flag(t, TIF_SYSCALL_TRACEPOINT);
+			set_task_syscall_work(t, SYSCALL_TRACEPOINT);
 		}
 		read_unlock(&tasklist_lock);
 	}
@@ -611,7 +611,7 @@ void syscall_unregfunc(void)
 	if (!sys_tracepoint_refcount) {
 		read_lock(&tasklist_lock);
 		for_each_process_thread(p, t) {
-			clear_tsk_thread_flag(t, TIF_SYSCALL_TRACEPOINT);
+			clear_task_syscall_work(t, SYSCALL_TRACEPOINT);
 		}
 		read_unlock(&tasklist_lock);
 	}