Make more threading improvements

- ASAN memory morgue is now lockless
- Make C11 atomics header more portable
- Rewrote pthread keys support to be lockless
- Simplify Python's unicode table unpacking code
- Make crash report write(2) closer to being atomic
- Make it possible to strace/ftrace a single thread
- ASAN now checks nul-terminated strings fast and properly
- Windows fork() now restores TLS memory of calling thread

tool/plinko/lib/plinko.c

@@ -17,10 +17,10 @@
 │ PERFORMANCE OF THIS SOFTWARE.                                                │
 ╚─────────────────────────────────────────────────────────────────────────────*/
 #include "libc/calls/calls.h"
-#include "libc/intrin/strace.internal.h"
 #include "libc/calls/struct/sigaction.h"
 #include "libc/errno.h"
 #include "libc/intrin/likely.h"
+#include "libc/intrin/strace.internal.h"
 #include "libc/log/countbranch.h"
 #include "libc/log/countexpr.h"
 #include "libc/log/log.h"
@@ -673,9 +673,9 @@ struct T DispatchTrace(dword ea, dword tm, dword r, dword p1, dword p2,
 struct T DispatchFtrace(dword ea, dword tm, dword r, dword p1, dword p2,
                         dword d) {
   ftrace_install();
-  ++__ftrace;
+  ftrace_enabled(+1);
   ea = MAKE(recurse(MAKE(Cadr(LO(ea)), HI(ea)), p1, p2), 0);
-  --__ftrace;
+  ftrace_enabled(-1);
   return Ret(ea, tm, r);
 }
 

tool/plinko/lib/printf.c

@@ -80,8 +80,8 @@ int Vfnprintf(const char *f, va_list va, int fd, int n) {
   int b, c, i, x, y, si, prec, cols, sign;
   gotr = false;
   t = rdtsc();
-  --__ftrace;
-  --__strace;
+  ftrace_enabled(-1);
+  strace_enabled(-1);
   ++recursive;
   for (ansi = 0;;) {
     for (;;) {
@@ -290,8 +290,8 @@ int Vfnprintf(const char *f, va_list va, int fd, int n) {
     }
   }
   --recursive;
-  ++__ftrace;
-  ++__strace;
+  ftrace_enabled(+1);
+  strace_enabled(+1);
   if (!recursive) {
     u = rdtsc();
     if (gotr) {

tool/plinko/lib/read.c

@@ -17,8 +17,8 @@
 │ PERFORMANCE OF THIS SOFTWARE.                                                │
 ╚─────────────────────────────────────────────────────────────────────────────*/
 #include "libc/calls/calls.h"
-#include "libc/intrin/strace.internal.h"
 #include "libc/errno.h"
+#include "libc/intrin/strace.internal.h"
 #include "libc/log/check.h"
 #include "libc/runtime/runtime.h"
 #include "libc/str/str.h"
@@ -280,10 +280,10 @@ static int Read1(int fd) {
 
 int Read(int fd) {
   int r;
-  --__ftrace;
-  --__strace;
+  ftrace_enabled(-1);
+  strace_enabled(-1);
   r = Read1(fd);
-  ++__ftrace;
-  ++__strace;
+  strace_enabled(+1);
+  ftrace_enabled(+1);
   return r;
 }