2022-09-11 18:02:07 +00:00
|
|
|
/*-*- mode:c;indent-tabs-mode:t;c-basic-offset:8;tab-width:8;coding:utf-8 -*-│
|
|
|
|
|
│ vi: set noet ft=c ts=8 sw=8 fenc=utf-8 :vi │
|
|
|
|
|
╞══════════════════════════════════════════════════════════════════════════════╡
|
|
|
|
|
│ Copyright 2016 Google Inc. │
|
|
|
|
|
│ │
|
|
|
|
|
│ Licensed under the Apache License, Version 2.0 (the "License"); │
|
|
|
|
|
│ you may not use this file except in compliance with the License. │
|
|
|
|
|
│ You may obtain a copy of the License at │
|
|
|
|
|
│ │
|
|
|
|
|
│ http://www.apache.org/licenses/LICENSE-2.0 │
|
|
|
|
|
│ │
|
|
|
|
|
│ Unless required by applicable law or agreed to in writing, software │
|
|
|
|
|
│ distributed under the License is distributed on an "AS IS" BASIS, │
|
|
|
|
|
│ WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. │
|
|
|
|
|
│ See the License for the specific language governing permissions and │
|
|
|
|
|
│ limitations under the License. │
|
|
|
|
|
╚─────────────────────────────────────────────────────────────────────────────*/
|
2022-11-05 01:19:05 +00:00
|
|
|
#include "libc/calls/blockcancel.internal.h"
|
2022-09-11 18:02:07 +00:00
|
|
|
#include "libc/mem/mem.h"
|
2023-09-12 04:34:53 +00:00
|
|
|
#include "libc/thread/thread.h"
|
2022-09-11 18:02:07 +00:00
|
|
|
#include "third_party/nsync/atomic.h"
|
|
|
|
|
#include "third_party/nsync/atomic.internal.h"
|
|
|
|
|
#include "third_party/nsync/common.internal.h"
|
|
|
|
|
#include "third_party/nsync/mu_semaphore.h"
|
2022-09-12 01:53:52 +00:00
|
|
|
#include "third_party/nsync/races.internal.h"
|
2022-09-11 18:02:07 +00:00
|
|
|
#include "third_party/nsync/wait_s.internal.h"
|
|
|
|
|
#include "third_party/nsync/waiter.h"
|
Release Cosmopolitan v3.3
This change upgrades to GCC 12.3 and GNU binutils 2.42. The GNU linker
appears to have changed things so that only a single de-duplicated str
table is present in the binary, and it gets placed wherever the linker
wants, regardless of what the linker script says. To cope with that we
need to stop using .ident to embed licenses. As such, this change does
significant work to revamp how third party licenses are defined in the
codebase, using `.section .notice,"aR",@progbits`.
This new GCC 12.3 toolchain has support for GNU indirect functions. It
lets us support __target_clones__ for the first time. This is used for
optimizing the performance of libc string functions such as strlen and
friends so far on x86, by ensuring AVX systems favor a second codepath
that uses VEX encoding. It shaves some latency off certain operations.
It's a useful feature to have for scientific computing for the reasons
explained by the test/libcxx/openmp_test.cc example which compiles for
fifteen different microarchitectures. Thanks to the upgrades, it's now
also possible to use newer instruction sets, such as AVX512FP16, VNNI.
Cosmo now uses the %gs register on x86 by default for TLS. Doing it is
helpful for any program that links `cosmo_dlopen()`. Such programs had
to recompile their binaries at startup to change the TLS instructions.
That's not great, since it means every page in the executable needs to
be faulted. The work of rewriting TLS-related x86 opcodes, is moved to
fixupobj.com instead. This is great news for MacOS x86 users, since we
previously needed to morph the binary every time for that platform but
now that's no longer necessary. The only platforms where we need fixup
of TLS x86 opcodes at runtime are now Windows, OpenBSD, and NetBSD. On
Windows we morph TLS to point deeper into the TIB, based on a TlsAlloc
assignment, and on OpenBSD/NetBSD we morph %gs back into %fs since the
kernels do not allow us to specify a value for the %gs register.
OpenBSD users are now required to use APE Loader to run Cosmo binaries
and assimilation is no longer possible. OpenBSD kernel needs to change
to allow programs to specify a value for the %gs register, or it needs
to stop marking executable pages loaded by the kernel as mimmutable().
This release fixes __constructor__, .ctor, .init_array, and lastly the
.preinit_array so they behave the exact same way as glibc.
We no longer use hex constants to define math.h symbols like M_PI.
2024-02-20 19:12:09 +00:00
|
|
|
__static_yoink("nsync_notice");
|
2022-09-11 18:02:07 +00:00
|
|
|
|
|
|
|
|
int nsync_wait_n (void *mu, void (*lock) (void *), void (*unlock) (void *),
|
|
|
|
|
nsync_time abs_deadline,
|
|
|
|
|
int count, struct nsync_waitable_s *waitable[]) {
|
|
|
|
|
int ready;
|
|
|
|
|
IGNORE_RACES_START ();
|
Make improvements
- We now serialize the file descriptor table when spawning / executing
processes on Windows. This means you can now inherit more stuff than
just standard i/o. It's needed by bash, which duplicates the console
to file descriptor #255. We also now do a better job serializing the
environment variables, so you're less likely to encounter E2BIG when
using your bash shell. We also no longer coerce environ to uppercase
- execve() on Windows now remotely controls its parent process to make
them spawn a replacement for itself. Then it'll be able to terminate
immediately once the spawn succeeds, without having to linger around
for the lifetime as a shell process for proxying the exit code. When
process worker thread running in the parent sees the child die, it's
given a handle to the new child, to replace it in the process table.
- execve() and posix_spawn() on Windows will now provide CreateProcess
an explicit handle list. This allows us to remove handle locks which
enables better fork/spawn concurrency, with seriously correct thread
safety. Other codebases like Go use the same technique. On the other
hand fork() still favors the conventional WIN32 inheritence approach
which can be a little bit messy, but is *controlled* by guaranteeing
perfectly clean slates at both the spawning and execution boundaries
- sigset_t is now 64 bits. Having it be 128 bits was a mistake because
there's no reason to use that and it's only supported by FreeBSD. By
using the system word size, signal mask manipulation on Windows goes
very fast. Furthermore @asyncsignalsafe funcs have been rewritten on
Windows to take advantage of signal masking, now that it's much more
pleasant to use.
- All the overlapped i/o code on Windows has been rewritten for pretty
good signal and cancelation safety. We're now able to ensure overlap
data structures are cleaned up so long as you don't longjmp() out of
out of a signal handler that interrupted an i/o operation. Latencies
are also improved thanks to the removal of lots of "busy wait" code.
Waits should be optimal for everything except poll(), which shall be
the last and final demon we slay in the win32 i/o horror show.
- getrusage() on Windows is now able to report RUSAGE_CHILDREN as well
as RUSAGE_SELF, thanks to aggregation in the process manager thread.
2023-10-08 12:36:18 +00:00
|
|
|
BLOCK_CANCELATION;
|
2022-09-11 18:02:07 +00:00
|
|
|
for (ready = 0; ready != count &&
|
|
|
|
|
nsync_time_cmp ((*waitable[ready]->funcs->ready_time) (
|
|
|
|
|
waitable[ready]->v, NULL),
|
|
|
|
|
nsync_time_zero) > 0;
|
|
|
|
|
ready++) {
|
|
|
|
|
}
|
|
|
|
|
if (ready == count && nsync_time_cmp (abs_deadline, nsync_time_zero) > 0) {
|
|
|
|
|
int i;
|
|
|
|
|
int unlocked = 0;
|
|
|
|
|
int j;
|
|
|
|
|
int enqueued = 1;
|
2023-11-10 09:42:06 +00:00
|
|
|
waiter *w = nsync_waiter_new_ ();
|
2022-09-11 18:02:07 +00:00
|
|
|
struct nsync_waiter_s nw_set[4];
|
|
|
|
|
struct nsync_waiter_s *nw = nw_set;
|
|
|
|
|
if (count > (int) (sizeof (nw_set) / sizeof (nw_set[0]))) {
|
|
|
|
|
nw = (struct nsync_waiter_s *) malloc (count * sizeof (nw[0]));
|
|
|
|
|
}
|
|
|
|
|
for (i = 0; i != count && enqueued; i++) {
|
|
|
|
|
nw[i].tag = NSYNC_WAITER_TAG;
|
|
|
|
|
nw[i].sem = &w->sem;
|
2023-07-06 13:57:28 +00:00
|
|
|
dll_init (&nw[i].q);
|
2022-09-11 18:02:07 +00:00
|
|
|
ATM_STORE (&nw[i].waiting, 0);
|
|
|
|
|
nw[i].flags = 0;
|
|
|
|
|
enqueued = (*waitable[i]->funcs->enqueue) (waitable[i]->v, &nw[i]);
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
if (i == count) {
|
|
|
|
|
nsync_time min_ntime;
|
|
|
|
|
if (mu != NULL) {
|
|
|
|
|
(*unlock) (mu);
|
|
|
|
|
unlocked = 1;
|
|
|
|
|
}
|
|
|
|
|
do {
|
|
|
|
|
min_ntime = abs_deadline;
|
|
|
|
|
for (j = 0; j != count; j++) {
|
|
|
|
|
nsync_time ntime;
|
|
|
|
|
ntime = (*waitable[j]->funcs->ready_time) (
|
|
|
|
|
waitable[j]->v, &nw[j]);
|
|
|
|
|
if (nsync_time_cmp (ntime, min_ntime) < 0) {
|
|
|
|
|
min_ntime = ntime;
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
} while (nsync_time_cmp (min_ntime, nsync_time_zero) > 0 &&
|
|
|
|
|
nsync_mu_semaphore_p_with_deadline (&w->sem,
|
|
|
|
|
min_ntime) == 0);
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
/* An attempt was made above to enqueue waitable[0..i-1].
|
|
|
|
|
Dequeue any that are still enqueued, and remember the index
|
|
|
|
|
of the first ready (i.e., not still enqueued) object, if any. */
|
|
|
|
|
for (j = 0; j != i; j++) {
|
|
|
|
|
int was_still_enqueued =
|
|
|
|
|
(*waitable[j]->funcs->dequeue) (waitable[j]->v, &nw[j]);
|
|
|
|
|
if (!was_still_enqueued && ready == count) {
|
|
|
|
|
ready = j;
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
if (nw != nw_set) {
|
|
|
|
|
free (nw);
|
|
|
|
|
}
|
2023-11-10 09:42:06 +00:00
|
|
|
nsync_waiter_free_ (w);
|
2022-09-11 18:02:07 +00:00
|
|
|
if (unlocked) {
|
|
|
|
|
(*lock) (mu);
|
|
|
|
|
}
|
|
|
|
|
}
|
Make improvements
- We now serialize the file descriptor table when spawning / executing
processes on Windows. This means you can now inherit more stuff than
just standard i/o. It's needed by bash, which duplicates the console
to file descriptor #255. We also now do a better job serializing the
environment variables, so you're less likely to encounter E2BIG when
using your bash shell. We also no longer coerce environ to uppercase
- execve() on Windows now remotely controls its parent process to make
them spawn a replacement for itself. Then it'll be able to terminate
immediately once the spawn succeeds, without having to linger around
for the lifetime as a shell process for proxying the exit code. When
process worker thread running in the parent sees the child die, it's
given a handle to the new child, to replace it in the process table.
- execve() and posix_spawn() on Windows will now provide CreateProcess
an explicit handle list. This allows us to remove handle locks which
enables better fork/spawn concurrency, with seriously correct thread
safety. Other codebases like Go use the same technique. On the other
hand fork() still favors the conventional WIN32 inheritence approach
which can be a little bit messy, but is *controlled* by guaranteeing
perfectly clean slates at both the spawning and execution boundaries
- sigset_t is now 64 bits. Having it be 128 bits was a mistake because
there's no reason to use that and it's only supported by FreeBSD. By
using the system word size, signal mask manipulation on Windows goes
very fast. Furthermore @asyncsignalsafe funcs have been rewritten on
Windows to take advantage of signal masking, now that it's much more
pleasant to use.
- All the overlapped i/o code on Windows has been rewritten for pretty
good signal and cancelation safety. We're now able to ensure overlap
data structures are cleaned up so long as you don't longjmp() out of
out of a signal handler that interrupted an i/o operation. Latencies
are also improved thanks to the removal of lots of "busy wait" code.
Waits should be optimal for everything except poll(), which shall be
the last and final demon we slay in the win32 i/o horror show.
- getrusage() on Windows is now able to report RUSAGE_CHILDREN as well
as RUSAGE_SELF, thanks to aggregation in the process manager thread.
2023-10-08 12:36:18 +00:00
|
|
|
ALLOW_CANCELATION;
|
2022-09-11 18:02:07 +00:00
|
|
|
IGNORE_RACES_END ();
|
|
|
|
|
return (ready);
|
|
|
|
|
}
|