4 files changed, 35 insertions, 100 deletions
diff --git a/kernel/entry/common.c b/kernel/entry/common.c
index 5c792b30c58a..9ef63e414791 100644
--- a/kernel/entry/common.c
+++ b/kernel/entry/common.c
@@ -17,6 +17,27 @@ void __weak arch_do_signal_or_restart(struct pt_regs *regs) { }
 #define EXIT_TO_USER_MODE_WORK_LOOP	(EXIT_TO_USER_MODE_WORK)
 #endif
 
+/* TIF bits, which prevent a time slice extension. */
+#ifdef CONFIG_PREEMPT_RT
+/*
+ * Since rseq slice ext has a direct correlation to the worst case
+ * scheduling latency (schedule is delayed after all), only have it affect
+ * LAZY reschedules on PREEMPT_RT for now.
+ *
+ * However, since this delay is only applicable to userspace, a value
+ * for rseq_slice_extension_nsec that is strictly less than the worst case
+ * kernel space preempt_disable() region, should mean the scheduling latency
+ * is not affected, even for !LAZY.
+ *
+ * However, since this value depends on the hardware at hand, it cannot be
+ * pre-determined in any sensible way. Hence punt on this problem for now.
+ */
+# define TIF_SLICE_EXT_SCHED	(_TIF_NEED_RESCHED_LAZY)
+#else
+# define TIF_SLICE_EXT_SCHED	(_TIF_NEED_RESCHED | _TIF_NEED_RESCHED_LAZY)
+#endif
+#define TIF_SLICE_EXT_DENY	(EXIT_TO_USER_MODE_WORK & ~TIF_SLICE_EXT_SCHED)
+
 static __always_inline unsigned long __exit_to_user_mode_loop(struct pt_regs *regs,
 							      unsigned long ti_work)
 {
@@ -28,8 +49,10 @@ static __always_inline unsigned long __exit_to_user_mode_loop(struct pt_regs *re
 
 		local_irq_enable_exit_to_user(ti_work);
 
-		if (ti_work & (_TIF_NEED_RESCHED | _TIF_NEED_RESCHED_LAZY))
-			schedule();
+		if (ti_work & (_TIF_NEED_RESCHED | _TIF_NEED_RESCHED_LAZY)) {
+			if (!rseq_grant_slice_extension(ti_work & TIF_SLICE_EXT_DENY))
+				schedule();
+		}
 
 		if (ti_work & _TIF_UPROBE)
 			uprobe_notify_resume(regs);
diff --git a/kernel/entry/common.h b/kernel/entry/common.h
deleted file mode 100644
index f6e6d02f07fe..000000000000
--- a/kernel/entry/common.h
+++ /dev/null
@@ -1,7 +0,0 @@
-/* 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/syscall-common.c b/kernel/entry/syscall-common.c
index 940a597ded40..cd4967a9c53e 100644
--- a/kernel/entry/syscall-common.c
+++ b/kernel/entry/syscall-common.c
@@ -1,104 +1,23 @@
 // SPDX-License-Identifier: GPL-2.0
 
-#include <linux/audit.h>
 #include <linux/entry-common.h>
-#include "common.h"
 
 #define CREATE_TRACE_POINTS
 #include <trace/events/syscalls.h>
 
-static inline void syscall_enter_audit(struct pt_regs *regs, long syscall)
-{
-	if (unlikely(audit_context())) {
-		unsigned long args[6];
-
-		syscall_get_arguments(current, regs, args);
-		audit_syscall_entry(syscall, args[0], args[1], args[2], args[3]);
-	}
-}
+/* Out of line to prevent tracepoint code duplication */
 
-long syscall_trace_enter(struct pt_regs *regs, long syscall,
-				unsigned long work)
+long trace_syscall_enter(struct pt_regs *regs, long syscall)
 {
-	long ret = 0;
-
+	trace_sys_enter(regs, syscall);
 	/*
-	 * 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.
+	 * Probes or BPF hooks in the tracepoint may have changed the
+	 * system call number. Reread it.
 	 */
-	if (work & SYSCALL_WORK_SYSCALL_USER_DISPATCH) {
-		if (syscall_user_dispatch(regs))
-			return -1L;
-	}
-
-	/* Handle ptrace */
-	if (work & (SYSCALL_WORK_SYSCALL_TRACE | SYSCALL_WORK_SYSCALL_EMU)) {
-		ret = ptrace_report_syscall_entry(regs);
-		if (ret || (work & SYSCALL_WORK_SYSCALL_EMU))
-			return -1L;
-	}
-
-	/* Do seccomp after ptrace, to catch any tracer changes. */
-	if (work & SYSCALL_WORK_SECCOMP) {
-		ret = __secure_computing();
-		if (ret == -1L)
-			return ret;
-	}
-
-	/* Either of the above might have changed the syscall number */
-	syscall = syscall_get_nr(current, regs);
-
-	if (unlikely(work & SYSCALL_WORK_SYSCALL_TRACEPOINT)) {
-		trace_sys_enter(regs, syscall);
-		/*
-		 * Probes or BPF hooks in the tracepoint may have changed the
-		 * system call number as well.
-		 */
-		syscall = syscall_get_nr(current, regs);
-	}
-
-	syscall_enter_audit(regs, syscall);
-
-	return ret ? : syscall;
+	return syscall_get_nr(current, regs);
 }
 
-/*
- * If SYSCALL_EMU is set, then the only reason to report is when
- * SINGLESTEP is set (i.e. PTRACE_SYSEMU_SINGLESTEP).  This syscall
- * instruction has been already reported in syscall_enter_from_user_mode().
- */
-static inline bool report_single_step(unsigned long work)
+void trace_syscall_exit(struct pt_regs *regs, long ret)
 {
-	if (work & SYSCALL_WORK_SYSCALL_EMU)
-		return false;
-
-	return work & SYSCALL_WORK_SYSCALL_EXIT_TRAP;
-}
-
-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 (work & SYSCALL_WORK_SYSCALL_TRACEPOINT)
-		trace_sys_exit(regs, syscall_get_return_value(current, regs));
-
-	step = report_single_step(work);
-	if (step || work & SYSCALL_WORK_SYSCALL_TRACE)
-		ptrace_report_syscall_exit(regs, step);
+	trace_sys_exit(regs, ret);
 }
diff --git a/kernel/entry/syscall_user_dispatch.c b/kernel/entry/syscall_user_dispatch.c
index a9055eccb27e..d89dffcc2d64 100644
--- a/kernel/entry/syscall_user_dispatch.c
+++ b/kernel/entry/syscall_user_dispatch.c
@@ -2,6 +2,8 @@
 /*
  * Copyright (C) 2020 Collabora Ltd.
  */
+
+#include <linux/entry-common.h>
 #include <linux/sched.h>
 #include <linux/prctl.h>
 #include <linux/ptrace.h>
@@ -15,8 +17,6 @@
 
 #include <asm/syscall.h>
 
-#include "common.h"
-
 static void trigger_sigsys(struct pt_regs *regs)
 {
 	struct kernel_siginfo info;