Fix busy-loop when waiting for file descriptors to close

When one thread is closing a file descriptor whilst another thread is
concurrently reading it, we need to wait for the reading thread to be
done with it to prevent a potential EBADF (or, worse, file descriptor
reuse).

At the moment, that is done by keeping a list of threads still using the
file descriptor in io_close_fptr. It then continually calls
rb_thread_schedule() in fptr_finalize_flush until said list is empty.

That busy-looping seems to behave rather poorly on some OS's,
particulary FreeBSD. It can cause the TestIO#test_race_gets_and_close
test to fail (even with its very long 200 second timeout) because the
closing thread starves out the using thread.

To fix that, I introduce the concept of struct rb_io_close_wait_list; a
list of threads still using a file descriptor that we want to close. We
call `rb_notify_fd_close` to let the thread scheduler know we're closing
a FD, which fills the list with threads. Then, we call
rb_notify_fd_close_wait which will block the thread until all of the
still-using threads are done.

This is implemented with a condition variable sleep, so no busy-looping
is required.

1 files changed, 10 insertions, 0 deletions

diff --git a/internal/thread.h b/internal/thread.h
index ac7e46b9be..7a6a860aeb 100644
--- a/internal/thread.h
+++ b/internal/thread.h
@@ -10,6 +10,8 @@
  */
 #include "ruby/ruby.h"          /* for VALUE */
 #include "ruby/intern.h"        /* for rb_blocking_function_t */
+#include "ccan/list/list.h"     /* for list in rb_io_close_wait_list */
+#include "ruby/thread_native.h" /* for mutexes in rb_io_close_wait_list */
 
 struct rb_thread_struct;        /* in vm_core.h */
 
@@ -52,6 +54,14 @@ VALUE rb_exec_recursive_outer_mid(VALUE (*f)(VALUE g, VALUE h, int r), VALUE g,
 
 int rb_thread_wait_for_single_fd(int fd, int events, struct timeval * timeout);
 
+struct rb_io_close_wait_list {
+    struct ccan_list_head list;
+    rb_nativethread_lock_t mu;
+    rb_nativethread_cond_t cv;
+};
+int rb_notify_fd_close(int fd, struct rb_io_close_wait_list *busy);
+void rb_notify_fd_close_wait(struct rb_io_close_wait_list *busy);
+
 RUBY_SYMBOL_EXPORT_BEGIN
 /* Temporary.  This API will be removed (renamed). */
 VALUE rb_thread_io_blocking_region(rb_blocking_function_t *func, void *data1, int fd);