Simplify TLS and reduce startup latency

This change simplifies the thread-local storage support code. On Windows
and Mac OS X the startup latency of __enable_tls() has been reduced from
30ms to 1ms. On Windows, TLS memory accesses will now go much faster due
to better self-modifying code that prevents a function call and acquires
our thread information block pointer in a single instruction.
This commit is contained in:
Justine Tunney 2022-07-18 03:33:32 -07:00
parent 38c3fa63fe
commit b1d9d11be1
15 changed files with 136 additions and 312 deletions

View file

@ -20,11 +20,13 @@
#include "libc/calls/struct/sched_param.h"
#include "libc/dce.h"
#include "libc/fmt/fmt.h"
#include "libc/intrin/kprintf.h"
#include "libc/intrin/spinlock.h"
#include "libc/intrin/wait0.internal.h"
#include "libc/math.h"
#include "libc/mem/mem.h"
#include "libc/runtime/gc.internal.h"
#include "libc/runtime/internal.h"
#include "libc/runtime/stack.h"
#include "libc/stdio/stdio.h"
#include "libc/sysv/consts/clone.h"