tracepoints: Migrate to use SYSCALL_WORK flag

On architectures using the generic syscall entry code the architecture
independent syscall work is moved to flags in thread_info::syscall_work.
This removes architecture dependencies and frees up TIF bits.

Define SYSCALL_WORK_SYSCALL_TRACEPOINT, use it in the generic entry code
and convert the code which uses the TIF specific helper functions to use
the new *_syscall_work() helpers which either resolve to the new mode for
users of the generic entry code or to the TIF based functions for the other
architectures.
Signed-off-by: Gabriel Krisman Bertazi <krisman@collabora.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Reviewed-by: Andy Lutomirski <luto@kernel.org>
Link: https://lore.kernel.org/r/20201116174206.2639648-6-krisman@collabora.com

include/linux/entry-common.h

@@ -17,10 +17,6 @@
 # define _TIF_SYSCALL_EMU		(0)
 #endif
 
-#ifndef _TIF_SYSCALL_TRACEPOINT
-# define _TIF_SYSCALL_TRACEPOINT	(0)
-#endif
-
 #ifndef _TIF_SYSCALL_AUDIT
 # define _TIF_SYSCALL_AUDIT		(0)
 #endif
@@ -46,7 +42,7 @@
 
 #define SYSCALL_ENTER_WORK						\
 	(_TIF_SYSCALL_TRACE | _TIF_SYSCALL_AUDIT  |			\
-	 _TIF_SYSCALL_TRACEPOINT | _TIF_SYSCALL_EMU |			\
+	 _TIF_SYSCALL_EMU |						\
 	 ARCH_SYSCALL_ENTER_WORK)
 
 /*
@@ -58,10 +54,11 @@
 
 #define SYSCALL_EXIT_WORK						\
 	(_TIF_SYSCALL_TRACE | _TIF_SYSCALL_AUDIT |			\
-	 _TIF_SYSCALL_TRACEPOINT | ARCH_SYSCALL_EXIT_WORK)
+	 ARCH_SYSCALL_EXIT_WORK)
 
-#define SYSCALL_WORK_ENTER	(SYSCALL_WORK_SECCOMP)
-#define SYSCALL_WORK_EXIT	(0)
+#define SYSCALL_WORK_ENTER	(SYSCALL_WORK_SECCOMP |			\
+				 SYSCALL_WORK_SYSCALL_TRACEPOINT)
+#define SYSCALL_WORK_EXIT	(SYSCALL_WORK_SYSCALL_TRACEPOINT)
 
 /*
  * TIF flags handled in exit_to_user_mode_loop()

include/linux/thread_info.h

@@ -37,9 +37,11 @@ enum {
 
 enum syscall_work_bit {
 	SYSCALL_WORK_BIT_SECCOMP,
+	SYSCALL_WORK_BIT_SYSCALL_TRACEPOINT,
 };
 
 #define SYSCALL_WORK_SECCOMP		BIT(SYSCALL_WORK_BIT_SECCOMP)
+#define SYSCALL_WORK_SYSCALL_TRACEPOINT	BIT(SYSCALL_WORK_BIT_SYSCALL_TRACEPOINT)
 
 #include <asm/thread_info.h>
 

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)

kernel/entry/common.c

@@ -63,7 +63,7 @@ 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);
@@ -233,7 +233,7 @@ static void syscall_exit_work(struct pt_regs *regs, unsigned long ti_work,
 
 	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);

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)
 {

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);
 	}