[patch V2 12/17] entry: Provide generic syscall exit function

[Thomas Gleixner]

From: Thomas Gleixner <tglx@xxxxxxxxxxxxx>

Like syscall entry all architectures have similar and pointlessly different
code to handle pending work before returning from a syscall to user space.

Provide a generic version.

Signed-off-by: Thomas Gleixner <tglx@xxxxxxxxxxxxx>
---
 include/linux/entry-common.h |   31 ++++++++++++++++++++++++
 kernel/entry/common.c        |   55 +++++++++++++++++++++++++++++++++++++++++++
 2 files changed, 86 insertions(+)

--- a/include/linux/entry-common.h
+++ b/include/linux/entry-common.h
@@ -46,6 +46,17 @@
 	 _TIF_SYSCALL_TRACEPOINT | _TIF_SYSCALL_EMU |			\
 	 ARCH_SYSCALL_ENTER_WORK)
 
+/*
+ * TIF flags handled in syscall_exit_to_usermode()
+ */
+#ifndef ARCH_SYSCALL_EXIT_WORK
+# define ARCH_SYSCALL_EXIT_WORK		(0)
+#endif
+
+#define SYSCALL_EXIT_WORK						\
+	(_TIF_SYSCALL_TRACE | _TIF_SYSCALL_AUDIT |			\
+	 _TIF_SYSCALL_TRACEPOINT | ARCH_SYSCALL_EXIT_WORK)
+
 /**
  * arch_syscall_enter_tracehook - Wrapper around tracehook_report_syscall_entry()
  * @regs:	Pointer to currents pt_regs
@@ -129,4 +140,24 @@ static inline long syscall_enter_from_us
 	return syscall;
 }
 
+/**
+ * arch_syscall_exit_tracehook - Wrapper around tracehook_report_syscall_exit()
+ *
+ * Defaults to tracehook_report_syscall_exit(). Can be replaced by
+ * architecture specific code.
+ *
+ * Invoked from syscall_exit_to_usermode()
+ */
+static inline void arch_syscall_exit_tracehook(struct pt_regs *regs, bool step);
+
+#ifndef arch_syscall_exit_tracehook
+static inline void arch_syscall_exit_tracehook(struct pt_regs *regs, bool step)
+{
+	tracehook_report_syscall_exit(regs, step);
+}
+#endif
+
+/* Common syscall exit function */
+void syscall_exit_to_usermode(struct pt_regs *regs, long syscall, long retval);
+
 #endif
--- a/kernel/entry/common.c
+++ b/kernel/entry/common.c
@@ -31,3 +31,58 @@ long core_syscall_enter_from_usermode(st
 
 	return ret ? : syscall;
 }
+
+#ifndef _TIF_SINGLESTEP
+static inline bool report_single_step(unsigned long ti_work)
+{
+	return false;
+}
+#else
+/*
+ * If TIF_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_usermode().
+ */
+#define SYSEMU_STEP	(_TIF_SINGLESTEP | _TIF_SYSCALL_EMU)
+
+static inline bool report_single_step(unsigned long ti_work)
+{
+	return (ti_work & SYSEMU_STEP) == _TIF_SINGLESTEP;
+}
+#endif
+
+static void syscall_exit_work(struct pt_regs *regs, long retval,
+			      unsigned long ti_work)
+{
+	bool step;
+
+	audit_syscall_exit(regs);
+
+	if (ti_work & _TIF_SYSCALL_TRACEPOINT)
+		trace_sys_exit(regs, retval);
+
+	step = report_single_step(ti_work);
+	if (step || ti_work & _TIF_SYSCALL_TRACE)
+		arch_syscall_exit_tracehook(regs, step);
+}
+
+void syscall_exit_to_usermode(struct pt_regs *regs, long syscall, long retval)
+{
+	unsigned long ti_work;
+
+	CT_WARN_ON(ct_state() != CONTEXT_KERNEL);
+
+	if (IS_ENABLED(CONFIG_PROVE_LOCKING) &&
+	    WARN(irqs_disabled(), "syscall %ld left IRQs disabled", syscall))
+		local_irq_enable();
+
+	rseq_syscall(regs);
+
+	/*
+	 * Handle work which needs to run exactly once per syscall exit
+	 * with interrupts enabled.
+	 */
+	ti_work = READ_ONCE(current_thread_info()->flags);
+	if (unlikely(ti_work & SYSCALL_EXIT_WORK))
+		syscall_exit_work(regs, retval, ti_work);
+}