This change addresses a bug that was reported in #923 where bash on
Windows behaved strangely. It turned out that our weak linking of
malloc() caused bash's configure script to favor its own getcwd()
function, which is implemented in the most astonishing way, using
opendir() and readdir() to recursively construct the current path.
This change moves getcwd() into LIBC_STDIO so it can strongly link
malloc(). A new __getcwd() function is now introduced, so all the
low-level runtime services can still use the actual system call. It
provides the Linux Kernel API convention across platforms, and is
overall a higher-quality implementation than what we had before.
In the future, we should probably take a closer look into why bash's
getcwd() polyfill wasn't working as intended on Windows, since there
might be a potential opportunity there to improve our readdir() too.
This change gets the pledge (formerly pledge.com) command back in tip
top shape for a 3.0.1 cosmos release. It now runs on all platforms, even
though it's mostly a no-op on ones that lack the kernel security stuff.
The binary footprint is now smaller, since it no longer needs to link
malloc. It's also now able to be built as a fat binary.
Qemu appears to define O_LARGEFILE as having its x86-64 value, which is
an easy mistake to make since this is one of the few magic numbers that
Linux special-cases for AARCH64.
- You can now run `make -j8 toolchain` on Windows
- You can now run `make -j` on MacOS ARM64 and BSD OSes
- You can now use our Emacs dev environment on MacOS/Windows
- Fix bug where the x16 register was being corrupted by --ftrace
- The programs under build/bootstrap/ are updated as fat binaries
- The Makefile now explains how to download cosmocc-0.0.12 toolchain
- The build scripts under bin/ now support "cosmo" branded toolchains
- stat() now goes faster on Windows (shaves 100ms off `make` latency)
- Code cleanup and added review on the Windows signal checking code
- posix_spawnattr_setrlimit() now works around MacOS ARM64 bugs
- Landlock Make now favors posix_spawn() on non-Linux/OpenBSD
- posix_spawn() now has better --strace logging on Windows
- fstatat() can now avoid EACCES in more cases on Windows
- fchmod() can now change the readonly bit on Windows
GNU Make on Windows now appears to be working reliably. This change also
fixes a bug where, after fork the Windows thread handle wasn't reset and
that caused undefined behavior using SetThreadContext() with our signals
This change gets GNU grep working. What caused it to not work, is it
wouldn't write to an output file descriptor when its dev/ino equaled
/dev/null's. So now we invent special dev/ino values for these files
This change refactors our POSIX signals emulation for Windows so that it
performs some additional safety checks before calling SetThreadContext()
which needs to be locked and must never ever interrupt Microsoft's code.
Kudos to the the Go developers for figuring out how to do this properly.
- On Windows connect() can now be interrupted by a signal; connect() w/
O_NONBLOCK will now raise EINPROGRESS; and connect() with SO_SNDTIMEO
will raise ETIMEDOUT after the interval has elapsed.
- We now get the AcceptEx(), ConnectEx(), and TransmitFile() functions
from the WIN32 API the officially blessed way, using WSAIoctl().
- Do nothing on Windows when fsync() is called on a directory handle.
This was raising EACCES earlier becaues GENERIC_WRITE is required on
the handle. It's possible to FlushFileBuffers() a directory handle if
it's opened with write access but MSDN doesn't document what it does.
If you have any idea, please let us know!
- Prefer manual reset event objects for read() and write() on Windows.
- Do some code cleanup on our dlmalloc customizations.
- Fix errno type error in Windows blocking routines.
- Make the futex polyfill simpler and faster.
This change deletes mkfifo() so that GNU Make on Windows will work in
parallel mode using its pipe-based implementation. There's an example
called greenbean2 now, which shows how to build a scalable web server
for Windows with 10k+ threads. The accuracy of clock_nanosleep is now
significantly improved on Linux.
- 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.
It's now possible to use sigaltstack() to recover from stack overflows
on Windows. Several bugs in sigaltstack() have been fixed, for all our
supported platforms. There's a newer better example showing how to use
this, along with three independent unit tests just to further showcase
the various techniques.
Thanks to @autumnjolitz (in #876) the Cosmopolitan codebase is now
acquainted with Apple's outstanding ulock system calls which offer
something much closer to futexes than Grand Central Dispatch which
wasn't quite as good, since its wait function can't be interrupted
by signals (therefore necessitating a busy loop) and it also needs
semaphore objects to be created and freed. Even though ulock is an
internal Apple API, strictly speaking, the benefits of futexes are
so great that it's worth the risk for now especially since we have
the GCD implementation still as a quick escape hatch if it changes
Here's why this change is important for x86 XNU users. Cosmo has a
suboptimal polyfill when the operating system doesn't offer an API
that let's us implement futexes properly. Sadly we had to use that
on X86 XNU until now. The polyfill works using clock_nanosleep, to
poll the futex in a busy loop with exponential backoff. On XNU x86
clock_nanosleep suffers from us not being able to use a fast clock
gettime implementation, which had a compounding effect that's made
the polyfill function even more poorly. On X86 XNU we also need to
polyfill sched_yield() using select(), which made things even more
troublesome. Now that we have futexes we don't have any busy loops
anymore for both condition variables and thread joining so optimal
performance is attained. To demonstrate, consider these benchmarks
Before:
$ ./lockscale_test.com -b
consumed 38.8377 seconds real time and
0.087131 seconds cpu time
After:
$ ./lockscale_test.com -b
consumed 0.007955 seconds real time and
0.011515 seconds cpu time
Fixes#876
This reverts commit b01282e23e. Some tests
are broken. It's not clear how it'll impact metal yet. Let's revisit the
memory optimization benefits of this change again sometime soon.
This reduces the virtual memory usage of Emacs for me by 30%. We now
have a simpler implementation that uses read(), rather mmap()ing the
whole executable.
- This change fixes a bug that allowed unbuffered printf() output (to
streams like stderr) to be truncated. This regression was introduced
some time between now and the last release.
- POSIX specifies all functions as thread safe by default. This change
works towards cleaning up our use of the @threadsafe / @threadunsafe
documentation annotations to reflect that. The goal is (1) to use
@threadunsafe to document functions which POSIX say needn't be thread
safe, and (2) use @threadsafe to document functions that we chose to
implement as thread safe even though POSIX didn't mandate it.
- Tidy up the clock_gettime() implementation. We're now trying out a
cleaner approach to system call support that aims to maintain the
Linux errno convention as long as possible. This also fixes bugs that
existed previously, where the vDSO errno wasn't being translated
properly. The gettimeofday() system call is now a wrapper for
clock_gettime(), which reduces bloat in apps that use both.
- The recently-introduced improvements to the execute bit on Windows has
had bugs fixed. access(X_OK) on a directory on Windows now succeeds.
fstat() will now perform the MZ/#! ReadFile() operation correctly.
- Windows.h is no longer included in libc/isystem/, because it confused
PCRE's build system into thinking Cosmopolitan is a WIN32 platform.
Cosmo's Windows.h polyfill was never even really that good, since it
only defines a subset of the subset of WIN32 APIs that Cosmo defines.
- The setlongerjmp() / longerjmp() APIs are removed. While they're nice
APIs that are superior to the standardized setjmp / longjmp functions,
they weren't superior enough to not be dead code in the monorepo. If
you use these APIs, please file an issue and they'll be restored.
- The .com appending magic has now been removed from APE Loader.
- ARM Neon headers are now exported in libc/isystem/
- stat() and access() now do a better job reporting which files are
executable which ones aren't. They do this by reading the first two
bytes in a file to see if it's `MZ` or `#!`.
Unlike CMD.EXE, CreateProcess() doesn't care if an executable name ends
with .COM or .EXE. We now have the unbourne shell and bash working well
on Windows, so we don't need DOS anymore. Making this change will grant
us better performance, particularly for builds, because commandv() will
need to make fewer system calls. Path mangling magic still happens with
WinMain() and ntspawn() in order to do things like turn \ into / so the
interop works well at the borders. But all the code in libraries, which
did that, has been removed. It's not possible for libraries to abstract
the differences between paths.
- Improved async signal safety of read() particularly for longjmp()
- Started adding cancel cleanup handlers for locks / etc on Windows
- Make /dev/tty work better particularly for uses like `foo | less`
- Eagerly read console input into a linked list, so poll can signal
- Fix some libc definitional bugs, which configure scripts detected
This change removes our use of ENABLE_VIRTUAL_TERMINAL_INPUT (which
isn't very good) in favor of having read() translate Windows Console
input events to ANSI/XTERM sequences by hand. This makes it possible to
capture important keystrokes (e.g. ctrl-space) that weren't possible
before. Most importantly this change also removes the stdin/sigwinch
worker threads, which never really worked that well. Interactive TTY
sessions will now work reliably when a Cosmo process spawns or forks
another Cosmo process, e.g. unbourne.com launching emacs.com.
- 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.
This changes *NSYNC to allocate waiters on the stack so our locks don't
need to depend on dynamic memory. This make our runtiem simpler, and it
also fixes bugs with thread cancellation support.
This change fixes bugs in the APE loader. The execve() unit tests are
now enabled for MODE=aarch64. See the README for how you need to have
binfmt_misc configured with Qemu to run them. Apple Silicon bugs have
been fixed too, e.g. tkill() now works.
The new asynchronous signal delivery technique is now also being used
for tkill(), raise(), etc. Many subtle issues have been addresesd. We
now signal handling on Windows that's remarkably similar to the POSIX
behaviors. However that's just across threads. We're lacking a way to
have the signal semantics work well, across multiple WIN32 processes.
The stdio reader thread now appears to be working recursively along
cosmopolitan subprocesses. For example, it's now possible to launch
vim.com from the unbourne.com bestline repl, thanks to hacks plus a
bug fix to select() timeouts.
