add enif_schedule_nif() to NIF API

In the #erlang IRC channel Anthony Ramine once mentioned the idea of
allowing a NIF to use an emulator trap, similar to a BIF trap, to schedule
another NIF for execution. This is exactly how dirty NIFs were implemented
for Erlang/OTP 17.0, so this commit refactors and generalizes that dirty
NIF code to support a new enif_schedule_nif() API function.

The enif_schedule_nif() function allows a long-running NIF to be broken
into separate NIF invocations. The NIF first executes part of the
long-running task, then calls enif_schedule_nif() to schedule a NIF for
later execution to continue the task. Any number of NIFs can be scheduled
in this manner, one after another. Since the emulator regains control
between invocations, this helps avoid problems caused by native code tying
up scheduler threads for too long.

The enif_schedule_nif() function also replaces the original experimental
dirty NIF API. The function takes a flags parameter that a caller can use
to indicate the NIF should be scheduled onto either a dirty CPU scheduler
thread, a dirty I/O scheduler thread, or scheduled as a regular NIF on a
regular scheduler thread. With this change, the original experimental
enif_schedule_dirty_nif(), enif_schedule_dirty_nif_finalizer() and
enif_dirty_nif_finalizer() API functions are no longer needed and have been
removed. Explicit scheduling of a dirty NIF finalization function is no
longer necessary; if an application wants similar functionality, it can
have a dirty NIF just invoke enif_schedule_nif() to schedule a non-dirty
NIF to complete its task.

Lift the restriction that dirty NIFs can't call enif_make_badarg() to raise
an exception. This was a problem with the original dirty NIF API because it
forced developers to get and check all incoming arguments in a regular NIF,
and then schedule the dirty NIF which then had to get all the arguments
again. Now, the argument checking can be done in the dirty NIF and it can
call enif_make_badarg() itself to flag incorrect arguments.

Extend the ErlNifFunc struct with a new flags field that allows NIFs to be
declared as dirty. The default value for this field is 0, indicating a
regular NIF, so it's backwards compatible with all existing statically
initialized ErlNifFunc struct instances, and so such instances require no
code changes. Defining the flags field with a value of
ERL_NIF_DIRTY_JOB_CPU_BOUND indicates that the NIF should execute on a
dirty CPU scheduler thread, or defining it with a value of
ERL_NIF_DIRTY_JOB_IO_BOUND indicates that the NIF should execute on a dirty
I/O scheduler thread. Any other flags field value causes a NIF library
loading error.

Extend the ErlNifEntry struct with a new options field that indicates
whether a NIF library was built with support for optional features such as
dirty NIFs. When a NIF library is loaded, the runtime checks the options
field to ensure compatibility. If a NIF library built with dirty NIF
support is loaded into a runtime that does not support dirty NIFs, and the
library defines one or more ErlNifFunc entries with non-zero flags fields
indicating dirty NIFs, a NIF library loading error results. There is no
error if a NIF library built with dirty NIF support is loaded into a
runtime that does not support dirty NIFs but the library does not have any
dirty NIFs. It is also not an error if a library without dirty NIF support
is loaded into a runtime built with dirty NIF support.

Add documentation and tests for enif_schedule_nif().

1 files changed, 9 insertions, 15 deletions

diff --git a/erts/emulator/beam/erl_process.h b/erts/emulator/beam/erl_process.h
index ed6dadbffa..31f4a09c94 100644
--- a/erts/emulator/beam/erl_process.h
+++ b/erts/emulator/beam/erl_process.h
@@ -734,13 +734,9 @@ erts_smp_reset_max_len(ErtsRunQueue *rq, ErtsRunQueueInfo *rqi)
 #define ERTS_PSD_DIST_ENTRY			3
 #define ERTS_PSD_CALL_TIME_BP			4
 #define ERTS_PSD_DELAYED_GC_TASK_QS		5
-#ifdef ERTS_DIRTY_SCHEDULERS
-#define ERTS_PSD_DIRTY_SCHED_TRAP_EXPORT	6
+#define ERTS_PSD_NIF_TRAP_EXPORT		6
 
 #define ERTS_PSD_SIZE				7
-#else
-#define ERTS_PSD_SIZE				6
-#endif
 
 typedef struct {
     void *data[ERTS_PSD_SIZE];
@@ -767,10 +763,8 @@ typedef struct {
 #define ERTS_PSD_DELAYED_GC_TASK_QS_GET_LOCKS ERTS_PROC_LOCK_MAIN
 #define ERTS_PSD_DELAYED_GC_TASK_QS_SET_LOCKS ERTS_PROC_LOCK_MAIN
 
-#ifdef ERTS_DIRTY_SCHEDULERS
-#define ERTS_PSD_DIRTY_SCHED_TRAP_EXPORT_GET_LOCKS ERTS_PROC_LOCK_MAIN
-#define ERTS_PSD_DIRTY_SCHED_TRAP_EXPORT_SET_LOCKS ERTS_PROC_LOCK_MAIN
-#endif
+#define ERTS_PSD_NIF_TRAP_EXPORT_GET_LOCKS ERTS_PROC_LOCK_MAIN
+#define ERTS_PSD_NIF_TRAP_EXPORT_SET_LOCKS ERTS_PROC_LOCK_MAIN
 
 typedef struct {
     ErtsProcLocks get_locks;
@@ -1367,6 +1361,8 @@ Uint64 erts_get_proc_interval(void);
 Uint64 erts_ensure_later_proc_interval(Uint64);
 Uint64 erts_step_proc_interval(void);
 
+int erts_setup_nif_gc(Process* proc, Eterm** objv, int* nobj); /* see erl_nif.c */
+
 ErtsProcList *erts_proclist_create(Process *);
 void erts_proclist_destroy(ErtsProcList *);
 
@@ -1817,12 +1813,10 @@ erts_psd_set(Process *p, ErtsProcLocks plocks, int ix, void *data)
 #define ERTS_PROC_SET_DELAYED_GC_TASK_QS(P, L, PBT) \
     ((ErtsProcSysTaskQs *) erts_psd_set((P), (L), ERTS_PSD_DELAYED_GC_TASK_QS, (void *) (PBT)))
 
-#ifdef ERTS_DIRTY_SCHEDULERS
-#define ERTS_PROC_GET_DIRTY_SCHED_TRAP_EXPORT(P) \
-    ((Export *) erts_psd_get((P), ERTS_PSD_DIRTY_SCHED_TRAP_EXPORT))
-#define ERTS_PROC_SET_DIRTY_SCHED_TRAP_EXPORT(P, L, DSTE) \
-    ((Export *) erts_psd_set((P), (L), ERTS_PSD_DIRTY_SCHED_TRAP_EXPORT, (void *) (DSTE)))
-#endif
+#define ERTS_PROC_GET_NIF_TRAP_EXPORT(P) \
+    ((Export *) erts_psd_get((P), ERTS_PSD_NIF_TRAP_EXPORT))
+#define ERTS_PROC_SET_NIF_TRAP_EXPORT(P, L, DSTE) \
+    ((Export *) erts_psd_set((P), (L), ERTS_PSD_NIF_TRAP_EXPORT, (void *) (DSTE)))
 
 
 ERTS_GLB_INLINE Eterm erts_proc_get_error_handler(Process *p);