2022-09-05 15:26:03 +00:00
|
|
|
#ifndef COSMOPOLITAN_LIBC_THREAD_POSIXTHREAD_INTERNAL_H_
|
|
|
|
|
#define COSMOPOLITAN_LIBC_THREAD_POSIXTHREAD_INTERNAL_H_
|
2022-09-09 18:30:33 +00:00
|
|
|
#include "libc/calls/struct/sched_param.h"
|
2023-09-10 15:12:43 +00:00
|
|
|
#include "libc/calls/struct/sigaltstack.h"
|
2023-10-14 08:06:00 +00:00
|
|
|
#include "libc/intrin/atomic.h"
|
2023-07-06 13:57:28 +00:00
|
|
|
#include "libc/intrin/dll.h"
|
2022-09-05 15:26:03 +00:00
|
|
|
#include "libc/runtime/runtime.h"
|
2023-11-28 22:24:28 +00:00
|
|
|
#include "libc/thread/pt.internal.h"
|
2022-09-10 09:56:25 +00:00
|
|
|
#include "libc/thread/thread.h"
|
2022-09-13 21:57:38 +00:00
|
|
|
#include "libc/thread/tls.h"
|
2022-10-09 06:54:05 +00:00
|
|
|
|
2023-10-14 08:06:00 +00:00
|
|
|
#define PT_BLOCKER_SEM ((atomic_int *)-1)
|
|
|
|
|
#define PT_BLOCKER_IO ((atomic_int *)-2)
|
2022-10-09 06:54:05 +00:00
|
|
|
|
2022-09-05 15:26:03 +00:00
|
|
|
COSMOPOLITAN_C_START_
|
|
|
|
|
|
2022-11-05 01:19:05 +00:00
|
|
|
// LEGAL TRANSITIONS ┌──> TERMINATED ─┐
|
|
|
|
|
// pthread_create ─┬─> JOINABLE ─┴┬─> DETACHED ───┴─> ZOMBIE
|
2022-09-08 04:13:50 +00:00
|
|
|
// └──────────────┘
|
2022-09-05 15:26:03 +00:00
|
|
|
enum PosixThreadStatus {
|
2022-09-08 04:13:50 +00:00
|
|
|
|
|
|
|
|
// this is a running thread that needs pthread_join()
|
|
|
|
|
//
|
|
|
|
|
// the following transitions are possible:
|
|
|
|
|
//
|
|
|
|
|
// - kPosixThreadJoinable -> kPosixThreadTerminated if start_routine()
|
|
|
|
|
// returns, or is longjmp'd out of by pthread_exit(), and the thread
|
|
|
|
|
// is waiting to be joined.
|
|
|
|
|
//
|
|
|
|
|
// - kPosixThreadJoinable -> kPosixThreadDetached if pthread_detach()
|
|
|
|
|
// is called on this thread.
|
Make improvements
- Every unit test now passes on Apple Silicon. The final piece of this
puzzle was porting our POSIX threads cancelation support, since that
works differently on ARM64 XNU vs. AMD64. Our semaphore support on
Apple Silicon is also superior now compared to AMD64, thanks to the
grand central dispatch library which lets *NSYNC locks go faster.
- The Cosmopolitan runtime is now more stable, particularly on Windows.
To do this, thread local storage is mandatory at all runtime levels,
and the innermost packages of the C library is no longer being built
using ASAN. TLS is being bootstrapped with a 128-byte TIB during the
process startup phase, and then later on the runtime re-allocates it
either statically or dynamically to support code using _Thread_local.
fork() and execve() now do a better job cooperating with threads. We
can now check how much stack memory is left in the process or thread
when functions like kprintf() / execve() etc. call alloca(), so that
ENOMEM can be raised, reduce a buffer size, or just print a warning.
- POSIX signal emulation is now implemented the same way kernels do it
with pthread_kill() and raise(). Any thread can interrupt any other
thread, regardless of what it's doing. If it's blocked on read/write
then the killer thread will cancel its i/o operation so that EINTR can
be returned in the mark thread immediately. If it's doing a tight CPU
bound operation, then that's also interrupted by the signal delivery.
Signal delivery works now by suspending a thread and pushing context
data structures onto its stack, and redirecting its execution to a
trampoline function, which calls SetThreadContext(GetCurrentThread())
when it's done.
- We're now doing a better job managing locks and handles. On NetBSD we
now close semaphore file descriptors in forked children. Semaphores on
Windows can now be canceled immediately, which means mutexes/condition
variables will now go faster. Apple Silicon semaphores can be canceled
too. We're now using Apple's pthread_yield() funciton. Apple _nocancel
syscalls are now used on XNU when appropriate to ensure pthread_cancel
requests aren't lost. The MbedTLS library has been updated to support
POSIX thread cancelations. See tool/build/runitd.c for an example of
how it can be used for production multi-threaded tls servers. Handles
on Windows now leak less often across processes. All i/o operations on
Windows are now overlapped, which means file pointers can no longer be
inherited across dup() and fork() for the time being.
- We now spawn a thread on Windows to deliver SIGCHLD and wakeup wait4()
which means, for example, that posix_spawn() now goes 3x faster. POSIX
spawn is also now more correct. Like Musl, it's now able to report the
failure code of execve() via a pipe although our approach favors using
shared memory to do that on systems that have a true vfork() function.
- We now spawn a thread to deliver SIGALRM to threads when setitimer()
is used. This enables the most precise wakeups the OS makes possible.
- The Cosmopolitan runtime now uses less memory. On NetBSD for example,
it turned out the kernel would actually commit the PT_GNU_STACK size
which caused RSS to be 6mb for every process. Now it's down to ~4kb.
On Apple Silicon, we reduce the mandatory upstream thread size to the
smallest possible size to reduce the memory overhead of Cosmo threads.
The examples directory has a program called greenbean which can spawn
a web server on Linux with 10,000 worker threads and have the memory
usage of the process be ~77mb. The 1024 byte overhead of POSIX-style
thread-local storage is now optional; it won't be allocated until the
pthread_setspecific/getspecific functions are called. On Windows, the
threads that get spawned which are internal to the libc implementation
use reserve rather than commit memory, which shaves a few hundred kb.
- sigaltstack() is now supported on Windows, however it's currently not
able to be used to handle stack overflows, since crash signals are
still generated by WIN32. However the crash handler will still switch
to the alt stack, which is helpful in environments with tiny threads.
- Test binaries are now smaller. Many of the mandatory dependencies of
the test runner have been removed. This ensures many programs can do a
better job only linking the the thing they're testing. This caused the
test binaries for LIBC_FMT for example, to decrease from 200kb to 50kb
- long double is no longer used in the implementation details of libc,
except in the APIs that define it. The old code that used long double
for time (instead of struct timespec) has now been thoroughly removed.
- ShowCrashReports() is now much tinier in MODE=tiny. Instead of doing
backtraces itself, it'll just print a command you can run on the shell
using our new `cosmoaddr2line` program to view the backtrace.
- Crash report signal handling now works in a much better way. Instead
of terminating the process, it now relies on SA_RESETHAND so that the
default SIG_IGN behavior can terminate the process if necessary.
- Our pledge() functionality has now been fully ported to AARCH64 Linux.
2023-09-19 03:44:45 +00:00
|
|
|
//
|
|
|
|
|
// - kPosixThreadJoinable -> kPosixThreadZombie if another thread
|
|
|
|
|
// calls fork().
|
2022-09-07 12:23:44 +00:00
|
|
|
kPosixThreadJoinable,
|
2022-09-08 04:13:50 +00:00
|
|
|
|
|
|
|
|
// this is a managed thread that'll be cleaned up by the library.
|
|
|
|
|
//
|
|
|
|
|
// the following transitions are possible:
|
|
|
|
|
//
|
|
|
|
|
// - kPosixThreadDetached -> kPosixThreadZombie if start_routine()
|
|
|
|
|
// returns, or is longjmp'd out of by pthread_exit(), and the thread
|
|
|
|
|
// is waiting to be joined.
|
Make improvements
- Every unit test now passes on Apple Silicon. The final piece of this
puzzle was porting our POSIX threads cancelation support, since that
works differently on ARM64 XNU vs. AMD64. Our semaphore support on
Apple Silicon is also superior now compared to AMD64, thanks to the
grand central dispatch library which lets *NSYNC locks go faster.
- The Cosmopolitan runtime is now more stable, particularly on Windows.
To do this, thread local storage is mandatory at all runtime levels,
and the innermost packages of the C library is no longer being built
using ASAN. TLS is being bootstrapped with a 128-byte TIB during the
process startup phase, and then later on the runtime re-allocates it
either statically or dynamically to support code using _Thread_local.
fork() and execve() now do a better job cooperating with threads. We
can now check how much stack memory is left in the process or thread
when functions like kprintf() / execve() etc. call alloca(), so that
ENOMEM can be raised, reduce a buffer size, or just print a warning.
- POSIX signal emulation is now implemented the same way kernels do it
with pthread_kill() and raise(). Any thread can interrupt any other
thread, regardless of what it's doing. If it's blocked on read/write
then the killer thread will cancel its i/o operation so that EINTR can
be returned in the mark thread immediately. If it's doing a tight CPU
bound operation, then that's also interrupted by the signal delivery.
Signal delivery works now by suspending a thread and pushing context
data structures onto its stack, and redirecting its execution to a
trampoline function, which calls SetThreadContext(GetCurrentThread())
when it's done.
- We're now doing a better job managing locks and handles. On NetBSD we
now close semaphore file descriptors in forked children. Semaphores on
Windows can now be canceled immediately, which means mutexes/condition
variables will now go faster. Apple Silicon semaphores can be canceled
too. We're now using Apple's pthread_yield() funciton. Apple _nocancel
syscalls are now used on XNU when appropriate to ensure pthread_cancel
requests aren't lost. The MbedTLS library has been updated to support
POSIX thread cancelations. See tool/build/runitd.c for an example of
how it can be used for production multi-threaded tls servers. Handles
on Windows now leak less often across processes. All i/o operations on
Windows are now overlapped, which means file pointers can no longer be
inherited across dup() and fork() for the time being.
- We now spawn a thread on Windows to deliver SIGCHLD and wakeup wait4()
which means, for example, that posix_spawn() now goes 3x faster. POSIX
spawn is also now more correct. Like Musl, it's now able to report the
failure code of execve() via a pipe although our approach favors using
shared memory to do that on systems that have a true vfork() function.
- We now spawn a thread to deliver SIGALRM to threads when setitimer()
is used. This enables the most precise wakeups the OS makes possible.
- The Cosmopolitan runtime now uses less memory. On NetBSD for example,
it turned out the kernel would actually commit the PT_GNU_STACK size
which caused RSS to be 6mb for every process. Now it's down to ~4kb.
On Apple Silicon, we reduce the mandatory upstream thread size to the
smallest possible size to reduce the memory overhead of Cosmo threads.
The examples directory has a program called greenbean which can spawn
a web server on Linux with 10,000 worker threads and have the memory
usage of the process be ~77mb. The 1024 byte overhead of POSIX-style
thread-local storage is now optional; it won't be allocated until the
pthread_setspecific/getspecific functions are called. On Windows, the
threads that get spawned which are internal to the libc implementation
use reserve rather than commit memory, which shaves a few hundred kb.
- sigaltstack() is now supported on Windows, however it's currently not
able to be used to handle stack overflows, since crash signals are
still generated by WIN32. However the crash handler will still switch
to the alt stack, which is helpful in environments with tiny threads.
- Test binaries are now smaller. Many of the mandatory dependencies of
the test runner have been removed. This ensures many programs can do a
better job only linking the the thing they're testing. This caused the
test binaries for LIBC_FMT for example, to decrease from 200kb to 50kb
- long double is no longer used in the implementation details of libc,
except in the APIs that define it. The old code that used long double
for time (instead of struct timespec) has now been thoroughly removed.
- ShowCrashReports() is now much tinier in MODE=tiny. Instead of doing
backtraces itself, it'll just print a command you can run on the shell
using our new `cosmoaddr2line` program to view the backtrace.
- Crash report signal handling now works in a much better way. Instead
of terminating the process, it now relies on SA_RESETHAND so that the
default SIG_IGN behavior can terminate the process if necessary.
- Our pledge() functionality has now been fully ported to AARCH64 Linux.
2023-09-19 03:44:45 +00:00
|
|
|
//
|
|
|
|
|
// - kPosixThreadDetached -> kPosixThreadZombie if another thread
|
|
|
|
|
// calls fork().
|
2022-09-05 15:26:03 +00:00
|
|
|
kPosixThreadDetached,
|
2022-09-08 04:13:50 +00:00
|
|
|
|
|
|
|
|
// this is a joinable thread that terminated.
|
|
|
|
|
//
|
|
|
|
|
// the following transitions are possible:
|
|
|
|
|
//
|
|
|
|
|
// - kPosixThreadTerminated -> _pthread_free() will happen when
|
|
|
|
|
// pthread_join() is called by the user.
|
2022-11-05 01:19:05 +00:00
|
|
|
// - kPosixThreadTerminated -> kPosixThreadZombie will happen when
|
|
|
|
|
// pthread_detach() is called by the user.
|
Make improvements
- Every unit test now passes on Apple Silicon. The final piece of this
puzzle was porting our POSIX threads cancelation support, since that
works differently on ARM64 XNU vs. AMD64. Our semaphore support on
Apple Silicon is also superior now compared to AMD64, thanks to the
grand central dispatch library which lets *NSYNC locks go faster.
- The Cosmopolitan runtime is now more stable, particularly on Windows.
To do this, thread local storage is mandatory at all runtime levels,
and the innermost packages of the C library is no longer being built
using ASAN. TLS is being bootstrapped with a 128-byte TIB during the
process startup phase, and then later on the runtime re-allocates it
either statically or dynamically to support code using _Thread_local.
fork() and execve() now do a better job cooperating with threads. We
can now check how much stack memory is left in the process or thread
when functions like kprintf() / execve() etc. call alloca(), so that
ENOMEM can be raised, reduce a buffer size, or just print a warning.
- POSIX signal emulation is now implemented the same way kernels do it
with pthread_kill() and raise(). Any thread can interrupt any other
thread, regardless of what it's doing. If it's blocked on read/write
then the killer thread will cancel its i/o operation so that EINTR can
be returned in the mark thread immediately. If it's doing a tight CPU
bound operation, then that's also interrupted by the signal delivery.
Signal delivery works now by suspending a thread and pushing context
data structures onto its stack, and redirecting its execution to a
trampoline function, which calls SetThreadContext(GetCurrentThread())
when it's done.
- We're now doing a better job managing locks and handles. On NetBSD we
now close semaphore file descriptors in forked children. Semaphores on
Windows can now be canceled immediately, which means mutexes/condition
variables will now go faster. Apple Silicon semaphores can be canceled
too. We're now using Apple's pthread_yield() funciton. Apple _nocancel
syscalls are now used on XNU when appropriate to ensure pthread_cancel
requests aren't lost. The MbedTLS library has been updated to support
POSIX thread cancelations. See tool/build/runitd.c for an example of
how it can be used for production multi-threaded tls servers. Handles
on Windows now leak less often across processes. All i/o operations on
Windows are now overlapped, which means file pointers can no longer be
inherited across dup() and fork() for the time being.
- We now spawn a thread on Windows to deliver SIGCHLD and wakeup wait4()
which means, for example, that posix_spawn() now goes 3x faster. POSIX
spawn is also now more correct. Like Musl, it's now able to report the
failure code of execve() via a pipe although our approach favors using
shared memory to do that on systems that have a true vfork() function.
- We now spawn a thread to deliver SIGALRM to threads when setitimer()
is used. This enables the most precise wakeups the OS makes possible.
- The Cosmopolitan runtime now uses less memory. On NetBSD for example,
it turned out the kernel would actually commit the PT_GNU_STACK size
which caused RSS to be 6mb for every process. Now it's down to ~4kb.
On Apple Silicon, we reduce the mandatory upstream thread size to the
smallest possible size to reduce the memory overhead of Cosmo threads.
The examples directory has a program called greenbean which can spawn
a web server on Linux with 10,000 worker threads and have the memory
usage of the process be ~77mb. The 1024 byte overhead of POSIX-style
thread-local storage is now optional; it won't be allocated until the
pthread_setspecific/getspecific functions are called. On Windows, the
threads that get spawned which are internal to the libc implementation
use reserve rather than commit memory, which shaves a few hundred kb.
- sigaltstack() is now supported on Windows, however it's currently not
able to be used to handle stack overflows, since crash signals are
still generated by WIN32. However the crash handler will still switch
to the alt stack, which is helpful in environments with tiny threads.
- Test binaries are now smaller. Many of the mandatory dependencies of
the test runner have been removed. This ensures many programs can do a
better job only linking the the thing they're testing. This caused the
test binaries for LIBC_FMT for example, to decrease from 200kb to 50kb
- long double is no longer used in the implementation details of libc,
except in the APIs that define it. The old code that used long double
for time (instead of struct timespec) has now been thoroughly removed.
- ShowCrashReports() is now much tinier in MODE=tiny. Instead of doing
backtraces itself, it'll just print a command you can run on the shell
using our new `cosmoaddr2line` program to view the backtrace.
- Crash report signal handling now works in a much better way. Instead
of terminating the process, it now relies on SA_RESETHAND so that the
default SIG_IGN behavior can terminate the process if necessary.
- Our pledge() functionality has now been fully ported to AARCH64 Linux.
2023-09-19 03:44:45 +00:00
|
|
|
// - kPosixThreadTerminated -> kPosixThreadZombie if another thread
|
|
|
|
|
// calls fork().
|
2022-09-05 15:26:03 +00:00
|
|
|
kPosixThreadTerminated,
|
2022-09-08 04:13:50 +00:00
|
|
|
|
|
|
|
|
// this is a detached thread that terminated.
|
|
|
|
|
//
|
|
|
|
|
// the following transitions are possible:
|
|
|
|
|
//
|
|
|
|
|
// - kPosixThreadZombie -> _pthread_free() will happen whenever
|
|
|
|
|
// convenient, e.g. pthread_create() entry or atexit handler.
|
2022-09-05 15:26:03 +00:00
|
|
|
kPosixThreadZombie,
|
|
|
|
|
};
|
|
|
|
|
|
2023-07-06 13:57:28 +00:00
|
|
|
#define POSIXTHREAD_CONTAINER(e) DLL_CONTAINER(struct PosixThread, list, e)
|
|
|
|
|
|
2022-09-05 15:26:03 +00:00
|
|
|
struct PosixThread {
|
2023-10-14 08:06:00 +00:00
|
|
|
int pt_flags; // 0x00: see PT_* constants
|
|
|
|
|
atomic_int pt_canceled; // 0x04: thread has bad beliefs
|
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
|
|
|
_Atomic(enum PosixThreadStatus) pt_status;
|
2023-10-14 08:06:00 +00:00
|
|
|
atomic_int ptid; // transitions 0 → tid
|
|
|
|
|
atomic_int pt_refs; // negative means free
|
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
|
|
|
void *(*pt_start)(void *); // creation callback
|
|
|
|
|
void *pt_arg; // start's parameter
|
|
|
|
|
void *pt_rc; // start's return value
|
|
|
|
|
char *pt_tls; // bottom of tls allocation
|
|
|
|
|
struct CosmoTib *tib; // middle of tls allocation
|
|
|
|
|
struct Dll list; // list of threads
|
|
|
|
|
struct _pthread_cleanup_buffer *pt_cleanup;
|
2023-10-14 08:06:00 +00:00
|
|
|
_Atomic(atomic_int *) pt_blocker;
|
2023-11-05 03:29:25 +00:00
|
|
|
uint64_t pt_blkmask;
|
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
|
|
|
int64_t pt_semaphore;
|
|
|
|
|
intptr_t pt_iohandle;
|
|
|
|
|
void *pt_ioverlap;
|
|
|
|
|
jmp_buf pt_exiter;
|
|
|
|
|
pthread_attr_t pt_attr;
|
2022-09-05 15:26:03 +00:00
|
|
|
};
|
|
|
|
|
|
2022-10-17 18:02:04 +00:00
|
|
|
typedef void (*atfork_f)(void);
|
|
|
|
|
|
2023-07-06 13:57:28 +00:00
|
|
|
extern struct Dll *_pthread_list;
|
Make improvements
- Every unit test now passes on Apple Silicon. The final piece of this
puzzle was porting our POSIX threads cancelation support, since that
works differently on ARM64 XNU vs. AMD64. Our semaphore support on
Apple Silicon is also superior now compared to AMD64, thanks to the
grand central dispatch library which lets *NSYNC locks go faster.
- The Cosmopolitan runtime is now more stable, particularly on Windows.
To do this, thread local storage is mandatory at all runtime levels,
and the innermost packages of the C library is no longer being built
using ASAN. TLS is being bootstrapped with a 128-byte TIB during the
process startup phase, and then later on the runtime re-allocates it
either statically or dynamically to support code using _Thread_local.
fork() and execve() now do a better job cooperating with threads. We
can now check how much stack memory is left in the process or thread
when functions like kprintf() / execve() etc. call alloca(), so that
ENOMEM can be raised, reduce a buffer size, or just print a warning.
- POSIX signal emulation is now implemented the same way kernels do it
with pthread_kill() and raise(). Any thread can interrupt any other
thread, regardless of what it's doing. If it's blocked on read/write
then the killer thread will cancel its i/o operation so that EINTR can
be returned in the mark thread immediately. If it's doing a tight CPU
bound operation, then that's also interrupted by the signal delivery.
Signal delivery works now by suspending a thread and pushing context
data structures onto its stack, and redirecting its execution to a
trampoline function, which calls SetThreadContext(GetCurrentThread())
when it's done.
- We're now doing a better job managing locks and handles. On NetBSD we
now close semaphore file descriptors in forked children. Semaphores on
Windows can now be canceled immediately, which means mutexes/condition
variables will now go faster. Apple Silicon semaphores can be canceled
too. We're now using Apple's pthread_yield() funciton. Apple _nocancel
syscalls are now used on XNU when appropriate to ensure pthread_cancel
requests aren't lost. The MbedTLS library has been updated to support
POSIX thread cancelations. See tool/build/runitd.c for an example of
how it can be used for production multi-threaded tls servers. Handles
on Windows now leak less often across processes. All i/o operations on
Windows are now overlapped, which means file pointers can no longer be
inherited across dup() and fork() for the time being.
- We now spawn a thread on Windows to deliver SIGCHLD and wakeup wait4()
which means, for example, that posix_spawn() now goes 3x faster. POSIX
spawn is also now more correct. Like Musl, it's now able to report the
failure code of execve() via a pipe although our approach favors using
shared memory to do that on systems that have a true vfork() function.
- We now spawn a thread to deliver SIGALRM to threads when setitimer()
is used. This enables the most precise wakeups the OS makes possible.
- The Cosmopolitan runtime now uses less memory. On NetBSD for example,
it turned out the kernel would actually commit the PT_GNU_STACK size
which caused RSS to be 6mb for every process. Now it's down to ~4kb.
On Apple Silicon, we reduce the mandatory upstream thread size to the
smallest possible size to reduce the memory overhead of Cosmo threads.
The examples directory has a program called greenbean which can spawn
a web server on Linux with 10,000 worker threads and have the memory
usage of the process be ~77mb. The 1024 byte overhead of POSIX-style
thread-local storage is now optional; it won't be allocated until the
pthread_setspecific/getspecific functions are called. On Windows, the
threads that get spawned which are internal to the libc implementation
use reserve rather than commit memory, which shaves a few hundred kb.
- sigaltstack() is now supported on Windows, however it's currently not
able to be used to handle stack overflows, since crash signals are
still generated by WIN32. However the crash handler will still switch
to the alt stack, which is helpful in environments with tiny threads.
- Test binaries are now smaller. Many of the mandatory dependencies of
the test runner have been removed. This ensures many programs can do a
better job only linking the the thing they're testing. This caused the
test binaries for LIBC_FMT for example, to decrease from 200kb to 50kb
- long double is no longer used in the implementation details of libc,
except in the APIs that define it. The old code that used long double
for time (instead of struct timespec) has now been thoroughly removed.
- ShowCrashReports() is now much tinier in MODE=tiny. Instead of doing
backtraces itself, it'll just print a command you can run on the shell
using our new `cosmoaddr2line` program to view the backtrace.
- Crash report signal handling now works in a much better way. Instead
of terminating the process, it now relies on SA_RESETHAND so that the
default SIG_IGN behavior can terminate the process if necessary.
- Our pledge() functionality has now been fully ported to AARCH64 Linux.
2023-09-19 03:44:45 +00:00
|
|
|
extern struct PosixThread _pthread_static;
|
2023-07-24 15:31:54 +00:00
|
|
|
extern _Atomic(pthread_key_dtor) _pthread_key_dtor[PTHREAD_KEYS_MAX];
|
2022-09-10 16:14:40 +00:00
|
|
|
|
2024-01-09 09:26:03 +00:00
|
|
|
int _pthread_atfork(atfork_f, atfork_f, atfork_f) libcesque;
|
|
|
|
|
int _pthread_reschedule(struct PosixThread *) libcesque;
|
2023-07-24 15:31:54 +00:00
|
|
|
int _pthread_setschedparam_freebsd(int, int, const struct sched_param *);
|
2024-01-09 09:26:03 +00:00
|
|
|
int _pthread_tid(struct PosixThread *) libcesque;
|
|
|
|
|
intptr_t _pthread_syshand(struct PosixThread *) libcesque;
|
|
|
|
|
long _pthread_cancel_ack(void) libcesque;
|
|
|
|
|
void _pthread_decimate(void) libcesque;
|
|
|
|
|
void _pthread_free(struct PosixThread *, bool) libcesque;
|
2024-04-26 03:01:27 +00:00
|
|
|
void _pthread_init(void) libcesque;
|
2024-01-09 09:26:03 +00:00
|
|
|
void _pthread_lock(void) libcesque;
|
|
|
|
|
void _pthread_onfork_child(void) libcesque;
|
|
|
|
|
void _pthread_onfork_parent(void) libcesque;
|
|
|
|
|
void _pthread_onfork_prepare(void) libcesque;
|
|
|
|
|
void _pthread_ungarbage(void) libcesque;
|
|
|
|
|
void _pthread_unkey(struct CosmoTib *) libcesque;
|
|
|
|
|
void _pthread_unlock(void) libcesque;
|
|
|
|
|
void _pthread_unref(struct PosixThread *) libcesque;
|
|
|
|
|
void _pthread_unwind(struct PosixThread *) libcesque;
|
|
|
|
|
void _pthread_zombify(struct PosixThread *) libcesque;
|
2022-09-05 15:26:03 +00:00
|
|
|
|
2024-01-08 18:07:35 +00:00
|
|
|
forceinline pureconst struct PosixThread *_pthread_self(void) {
|
Make improvements
- Every unit test now passes on Apple Silicon. The final piece of this
puzzle was porting our POSIX threads cancelation support, since that
works differently on ARM64 XNU vs. AMD64. Our semaphore support on
Apple Silicon is also superior now compared to AMD64, thanks to the
grand central dispatch library which lets *NSYNC locks go faster.
- The Cosmopolitan runtime is now more stable, particularly on Windows.
To do this, thread local storage is mandatory at all runtime levels,
and the innermost packages of the C library is no longer being built
using ASAN. TLS is being bootstrapped with a 128-byte TIB during the
process startup phase, and then later on the runtime re-allocates it
either statically or dynamically to support code using _Thread_local.
fork() and execve() now do a better job cooperating with threads. We
can now check how much stack memory is left in the process or thread
when functions like kprintf() / execve() etc. call alloca(), so that
ENOMEM can be raised, reduce a buffer size, or just print a warning.
- POSIX signal emulation is now implemented the same way kernels do it
with pthread_kill() and raise(). Any thread can interrupt any other
thread, regardless of what it's doing. If it's blocked on read/write
then the killer thread will cancel its i/o operation so that EINTR can
be returned in the mark thread immediately. If it's doing a tight CPU
bound operation, then that's also interrupted by the signal delivery.
Signal delivery works now by suspending a thread and pushing context
data structures onto its stack, and redirecting its execution to a
trampoline function, which calls SetThreadContext(GetCurrentThread())
when it's done.
- We're now doing a better job managing locks and handles. On NetBSD we
now close semaphore file descriptors in forked children. Semaphores on
Windows can now be canceled immediately, which means mutexes/condition
variables will now go faster. Apple Silicon semaphores can be canceled
too. We're now using Apple's pthread_yield() funciton. Apple _nocancel
syscalls are now used on XNU when appropriate to ensure pthread_cancel
requests aren't lost. The MbedTLS library has been updated to support
POSIX thread cancelations. See tool/build/runitd.c for an example of
how it can be used for production multi-threaded tls servers. Handles
on Windows now leak less often across processes. All i/o operations on
Windows are now overlapped, which means file pointers can no longer be
inherited across dup() and fork() for the time being.
- We now spawn a thread on Windows to deliver SIGCHLD and wakeup wait4()
which means, for example, that posix_spawn() now goes 3x faster. POSIX
spawn is also now more correct. Like Musl, it's now able to report the
failure code of execve() via a pipe although our approach favors using
shared memory to do that on systems that have a true vfork() function.
- We now spawn a thread to deliver SIGALRM to threads when setitimer()
is used. This enables the most precise wakeups the OS makes possible.
- The Cosmopolitan runtime now uses less memory. On NetBSD for example,
it turned out the kernel would actually commit the PT_GNU_STACK size
which caused RSS to be 6mb for every process. Now it's down to ~4kb.
On Apple Silicon, we reduce the mandatory upstream thread size to the
smallest possible size to reduce the memory overhead of Cosmo threads.
The examples directory has a program called greenbean which can spawn
a web server on Linux with 10,000 worker threads and have the memory
usage of the process be ~77mb. The 1024 byte overhead of POSIX-style
thread-local storage is now optional; it won't be allocated until the
pthread_setspecific/getspecific functions are called. On Windows, the
threads that get spawned which are internal to the libc implementation
use reserve rather than commit memory, which shaves a few hundred kb.
- sigaltstack() is now supported on Windows, however it's currently not
able to be used to handle stack overflows, since crash signals are
still generated by WIN32. However the crash handler will still switch
to the alt stack, which is helpful in environments with tiny threads.
- Test binaries are now smaller. Many of the mandatory dependencies of
the test runner have been removed. This ensures many programs can do a
better job only linking the the thing they're testing. This caused the
test binaries for LIBC_FMT for example, to decrease from 200kb to 50kb
- long double is no longer used in the implementation details of libc,
except in the APIs that define it. The old code that used long double
for time (instead of struct timespec) has now been thoroughly removed.
- ShowCrashReports() is now much tinier in MODE=tiny. Instead of doing
backtraces itself, it'll just print a command you can run on the shell
using our new `cosmoaddr2line` program to view the backtrace.
- Crash report signal handling now works in a much better way. Instead
of terminating the process, it now relies on SA_RESETHAND so that the
default SIG_IGN behavior can terminate the process if necessary.
- Our pledge() functionality has now been fully ported to AARCH64 Linux.
2023-09-19 03:44:45 +00:00
|
|
|
return (struct PosixThread *)__get_tls()->tib_pthread;
|
|
|
|
|
}
|
|
|
|
|
|
2024-01-08 18:07:35 +00:00
|
|
|
forceinline void _pthread_ref(struct PosixThread *pt) {
|
2023-10-14 08:06:00 +00:00
|
|
|
atomic_fetch_add_explicit(&pt->pt_refs, 1, memory_order_relaxed);
|
|
|
|
|
}
|
|
|
|
|
|
2022-09-05 15:26:03 +00:00
|
|
|
COSMOPOLITAN_C_END_
|
|
|
|
|
#endif /* COSMOPOLITAN_LIBC_THREAD_POSIXTHREAD_INTERNAL_H_ */
|
