Auto merge of #84115 - CDirkx:rt, r=m-ou-se

Rework `init` and `cleanup`

This PR reworks the code in `std` that runs before and after `main` and centralizes this code respectively in the functions `init` and `cleanup` in both `sys_common` and `sys`. This makes is easy to see what code is executed during initialization and cleanup on each platform just by looking at e.g. `sys::windows::init`.

Full list of changes:
- new module `rt` in `sys_common` to contain `init` and `cleanup` and the runtime macros.
- `at_exit` and the mechanism to register exit handlers has been completely removed. In practice this was only used for closing sockets on windows and flushing stdout, which have been moved to `cleanup`.
- <s>On windows `alloc` and `net` initialization is now done in `init`, this saves a runtime check in every allocation and network use.</s>

library/std/src/io/mod.rs

@@ -293,6 +293,10 @@ mod util;
 
 const DEFAULT_BUF_SIZE: usize = crate::sys_common::io::DEFAULT_BUF_SIZE;
 
+pub(crate) fn cleanup() {
+    stdio::cleanup()
+}
+
 struct Guard<'a> {
     buf: &'a mut Vec<u8>,
     len: usize,

library/std/src/io/stdio.rs

@@ -13,7 +13,6 @@ use crate::pin::Pin;
 use crate::sync::atomic::{AtomicBool, Ordering};
 use crate::sync::{Arc, Mutex, MutexGuard};
 use crate::sys::stdio;
-use crate::sys_common;
 use crate::sys_common::remutex::{ReentrantMutex, ReentrantMutexGuard};
 
 type LocalStream = Arc<Mutex<Vec<u8>>>;
@@ -508,6 +507,8 @@ pub struct StdoutLock<'a> {
     inner: ReentrantMutexGuard<'a, RefCell<LineWriter<StdoutRaw>>>,
 }
 
+static STDOUT: SyncOnceCell<ReentrantMutex<RefCell<LineWriter<StdoutRaw>>>> = SyncOnceCell::new();
+
 /// Constructs a new handle to the standard output of the current process.
 ///
 /// Each handle returned is a reference to a shared global buffer whose access
@@ -549,34 +550,28 @@ pub struct StdoutLock<'a> {
 /// ```
 #[stable(feature = "rust1", since = "1.0.0")]
 pub fn stdout() -> Stdout {
-    static INSTANCE: SyncOnceCell<ReentrantMutex<RefCell<LineWriter<StdoutRaw>>>> =
-        SyncOnceCell::new();
-
-    fn cleanup() {
-        if let Some(instance) = INSTANCE.get() {
-            // Flush the data and disable buffering during shutdown
-            // by replacing the line writer by one with zero
-            // buffering capacity.
-            // We use try_lock() instead of lock(), because someone
-            // might have leaked a StdoutLock, which would
-            // otherwise cause a deadlock here.
-            if let Some(lock) = Pin::static_ref(instance).try_lock() {
-                *lock.borrow_mut() = LineWriter::with_capacity(0, stdout_raw());
-            }
-        }
-    }
-
     Stdout {
-        inner: Pin::static_ref(&INSTANCE).get_or_init_pin(
-            || unsafe {
-                let _ = sys_common::at_exit(cleanup);
-                ReentrantMutex::new(RefCell::new(LineWriter::new(stdout_raw())))
-            },
+        inner: Pin::static_ref(&STDOUT).get_or_init_pin(
+            || unsafe { ReentrantMutex::new(RefCell::new(LineWriter::new(stdout_raw()))) },
             |mutex| unsafe { mutex.init() },
         ),
     }
 }
 
+pub fn cleanup() {
+    if let Some(instance) = STDOUT.get() {
+        // Flush the data and disable buffering during shutdown
+        // by replacing the line writer by one with zero
+        // buffering capacity.
+        // We use try_lock() instead of lock(), because someone
+        // might have leaked a StdoutLock, which would
+        // otherwise cause a deadlock here.
+        if let Some(lock) = Pin::static_ref(instance).try_lock() {
+            *lock.borrow_mut() = LineWriter::with_capacity(0, stdout_raw());
+        }
+    }
+}
+
 impl Stdout {
     /// Locks this handle to the standard output stream, returning a writable
     /// guard.

library/std/src/process.rs

@@ -1749,7 +1749,7 @@ impl Child {
 /// [platform-specific behavior]: #platform-specific-behavior
 #[stable(feature = "rust1", since = "1.0.0")]
 pub fn exit(code: i32) -> ! {
-    crate::sys_common::cleanup();
+    crate::sys_common::rt::cleanup();
     crate::sys::os::exit(code)
 }
 

library/std/src/rt.rs

@@ -26,33 +26,16 @@ fn lang_start_internal(
     argv: *const *const u8,
 ) -> isize {
     use crate::panic;
-    use crate::sys;
     use crate::sys_common;
-    use crate::sys_common::thread_info;
-    use crate::thread::Thread;
 
-    sys::init();
+    // SAFETY: Only called once during runtime initialization.
+    unsafe { sys_common::rt::init(argc, argv) };
 
-    unsafe {
-        let main_guard = sys::thread::guard::init();
-        sys::stack_overflow::init();
+    let exit_code = panic::catch_unwind(main);
 
-        // Next, set up the current Thread with the guard information we just
-        // created. Note that this isn't necessary in general for new threads,
-        // but we just do this to name the main thread and to give it correct
-        // info about the stack bounds.
-        let thread = Thread::new(Some("main".to_owned()));
-        thread_info::set(main_guard, thread);
+    sys_common::rt::cleanup();
 
-        // Store our args if necessary in a squirreled away location
-        sys::args::init(argc, argv);
-
-        // Let's run some code!
-        let exit_code = panic::catch_unwind(main);
-
-        sys_common::cleanup();
-        exit_code.unwrap_or(101) as isize
-    }
+    exit_code.unwrap_or(101) as isize
 }
 
 #[cfg(not(test))]

library/std/src/sys/hermit/mod.rs

@@ -37,7 +37,6 @@ pub mod pipe;
 #[path = "../unsupported/process.rs"]
 pub mod process;
 pub mod rwlock;
-pub mod stack_overflow;
 pub mod stdio;
 pub mod thread;
 pub mod thread_local_dtor;
@@ -96,9 +95,17 @@ pub extern "C" fn __rust_abort() {
     abort_internal();
 }
 
-#[cfg(not(test))]
-pub fn init() {
+// SAFETY: must be called only once during runtime initialization.
+// NOTE: this is not guaranteed to run, for example when Rust code is called externally.
+pub unsafe fn init(argc: isize, argv: *const *const u8) {
     let _ = net::init();
+    args::init(argc, argv);
+}
+
+// SAFETY: must be called only once during runtime cleanup.
+// NOTE: this is not guaranteed to run, for example when the program aborts.
+pub unsafe fn cleanup() {
+    args::cleanup();
 }
 
 #[cfg(not(test))]

library/std/src/sys/sgx/args.rs

@@ -23,8 +23,6 @@ pub unsafe fn init(argc: isize, argv: *const *const u8) {
     }
 }
 
-pub unsafe fn cleanup() {}
-
 pub fn args() -> Args {
     let args = unsafe { (ARGS.load(Ordering::Relaxed) as *const ArgsStore).as_ref() };
     if let Some(args) = args { Args(args.iter()) } else { Args([].iter()) }

library/std/src/sys/sgx/mod.rs

@@ -32,16 +32,24 @@ pub mod pipe;
 #[path = "../unsupported/process.rs"]
 pub mod process;
 pub mod rwlock;
-pub mod stack_overflow;
 pub mod stdio;
 pub mod thread;
 pub mod thread_local_key;
 pub mod time;
 
 pub use crate::sys_common::os_str_bytes as os_str;
 
-#[cfg(not(test))]
-pub fn init() {}
+// SAFETY: must be called only once during runtime initialization.
+// NOTE: this is not guaranteed to run, for example when Rust code is called externally.
+pub unsafe fn init(argc: isize, argv: *const *const u8) {
+    unsafe {
+        args::init(argc, argv);
+    }
+}
+
+// SAFETY: must be called only once during runtime cleanup.
+// NOTE: this is not guaranteed to run, for example when the program aborts.
+pub unsafe fn cleanup() {}
 
 /// This function is used to implement functionality that simply doesn't exist.
 /// Programs relying on this functionality will need to deal with the error.

library/std/src/sys/unix/mod.rs

@@ -44,14 +44,13 @@ pub mod time;
 
 pub use crate::sys_common::os_str_bytes as os_str;
 
-#[cfg(not(test))]
-pub fn init() {
+// SAFETY: must be called only once during runtime initialization.
+// NOTE: this is not guaranteed to run, for example when Rust code is called externally.
+pub unsafe fn init(argc: isize, argv: *const *const u8) {
     // The standard streams might be closed on application startup. To prevent
     // std::io::{stdin, stdout,stderr} objects from using other unrelated file
     // resources opened later, we reopen standards streams when they are closed.
-    unsafe {
-        sanitize_standard_fds();
-    }
+    sanitize_standard_fds();
 
     // By default, some platforms will send a *signal* when an EPIPE error
     // would otherwise be delivered. This runtime doesn't install a SIGPIPE
@@ -60,26 +59,24 @@ pub fn init() {
     //
     // Hence, we set SIGPIPE to ignore when the program starts up in order
     // to prevent this problem.
-    unsafe {
-        reset_sigpipe();
-    }
+    reset_sigpipe();
+
+    stack_overflow::init();
+    args::init(argc, argv);
 
-    cfg_if::cfg_if! {
-        if #[cfg(miri)] {
-            // The standard fds are always available in Miri.
-            unsafe fn sanitize_standard_fds() {}
-        } else if #[cfg(not(any(
-            target_os = "emscripten",
-            target_os = "fuchsia",
-            target_os = "vxworks",
-            // The poll on Darwin doesn't set POLLNVAL for closed fds.
-            target_os = "macos",
-            target_os = "ios",
-            target_os = "redox",
-        )))] {
-            // In the case when all file descriptors are open, the poll has been
-            // observed to perform better than fcntl (on GNU/Linux).
-            unsafe fn sanitize_standard_fds() {
+    unsafe fn sanitize_standard_fds() {
+        #[cfg(not(miri))]
+        // The standard fds are always available in Miri.
+        cfg_if::cfg_if! {
+            if #[cfg(not(any(
+                target_os = "emscripten",
+                target_os = "fuchsia",
+                target_os = "vxworks",
+                // The poll on Darwin doesn't set POLLNVAL for closed fds.
+                target_os = "macos",
+                target_os = "ios",
+                target_os = "redox",
+            )))] {
                 use crate::sys::os::errno;
                 let pfds: &mut [_] = &mut [
                     libc::pollfd { fd: 0, events: 0, revents: 0 },
@@ -104,9 +101,7 @@ pub fn init() {
                         libc::abort();
                     }
                 }
-            }
-        } else if #[cfg(any(target_os = "macos", target_os = "ios", target_os = "redox"))] {
-            unsafe fn sanitize_standard_fds() {
+            } else if #[cfg(any(target_os = "macos", target_os = "ios", target_os = "redox"))] {
                 use crate::sys::os::errno;
                 for fd in 0..3 {
                     if libc::fcntl(fd, libc::F_GETFD) == -1 && errno() == libc::EBADF {
@@ -116,17 +111,20 @@ pub fn init() {
                     }
                 }
             }
-        } else {
-            unsafe fn sanitize_standard_fds() {}
         }
     }
 
-    #[cfg(not(any(target_os = "emscripten", target_os = "fuchsia")))]
     unsafe fn reset_sigpipe() {
+        #[cfg(not(any(target_os = "emscripten", target_os = "fuchsia")))]
         assert!(signal(libc::SIGPIPE, libc::SIG_IGN) != libc::SIG_ERR);
     }
-    #[cfg(any(target_os = "emscripten", target_os = "fuchsia"))]
-    unsafe fn reset_sigpipe() {}
+}
+
+// SAFETY: must be called only once during runtime cleanup.
+// NOTE: this is not guaranteed to run, for example when the program aborts.
+pub unsafe fn cleanup() {
+    args::cleanup();
+    stack_overflow::cleanup();
 }
 
 #[cfg(target_os = "android")]

library/std/src/sys/unsupported/args.rs

@@ -1,8 +1,5 @@
 use crate::ffi::OsString;
 
-pub unsafe fn init(_argc: isize, _argv: *const *const u8) {}
-pub unsafe fn cleanup() {}
-
 pub struct Args {}
 
 pub fn args() -> Args {

library/std/src/sys/unsupported/common.rs

@@ -10,8 +10,13 @@ pub use crate::sys_common::os_str_bytes as os_str;
 // spec definition?
 use crate::os::raw::c_char;
 
-#[cfg(not(test))]
-pub fn init() {}
+// SAFETY: must be called only once during runtime initialization.
+// NOTE: this is not guaranteed to run, for example when Rust code is called externally.
+pub unsafe fn init(_argc: isize, _argv: *const *const u8) {}
+
+// SAFETY: must be called only once during runtime cleanup.
+// NOTE: this is not guaranteed to run, for example when the program aborts.
+pub unsafe fn cleanup() {}
 
 pub fn unsupported<T>() -> std_io::Result<T> {
     Err(unsupported_err())

library/std/src/sys/unsupported/mod.rs

@@ -15,7 +15,6 @@ pub mod path;
 pub mod pipe;
 pub mod process;
 pub mod rwlock;
-pub mod stack_overflow;
 pub mod stdio;
 pub mod thread;
 #[cfg(target_thread_local)]

library/std/src/sys/wasi/args.rs

@@ -5,10 +5,6 @@ use crate::fmt;
 use crate::os::wasi::ffi::OsStrExt;
 use crate::vec;
 
-pub unsafe fn init(_argc: isize, _argv: *const *const u8) {}
-
-pub unsafe fn cleanup() {}
-
 pub struct Args {
     iter: vec::IntoIter<OsString>,
 }

library/std/src/sys/wasi/mod.rs

@@ -42,8 +42,6 @@ pub mod pipe;
 pub mod process;
 #[path = "../unsupported/rwlock.rs"]
 pub mod rwlock;
-#[path = "../unsupported/stack_overflow.rs"]
-pub mod stack_overflow;
 pub mod stdio;
 pub mod thread;
 #[path = "../unsupported/thread_local_dtor.rs"]

library/std/src/sys/wasm/args.rs

@@ -2,12 +2,6 @@ use crate::ffi::OsString;
 use crate::fmt;
 use crate::vec;
 
-pub unsafe fn init(_argc: isize, _argv: *const *const u8) {
-    // On wasm these should always be null, so there's nothing for us to do here
-}
-
-pub unsafe fn cleanup() {}
-
 pub fn args() -> Args {
     Args { iter: Vec::new().into_iter() }
 }

library/std/src/sys/wasm/mod.rs

@@ -35,8 +35,6 @@ pub mod path;
 pub mod pipe;
 #[path = "../unsupported/process.rs"]
 pub mod process;
-#[path = "../unsupported/stack_overflow.rs"]
-pub mod stack_overflow;
 #[path = "../unsupported/stdio.rs"]
 pub mod stdio;
 pub mod thread;

library/std/src/sys/windows/args.rs

@@ -14,10 +14,6 @@ use crate::vec;
 
 use core::iter;
 
-pub unsafe fn init(_argc: isize, _argv: *const *const u8) {}
-
-pub unsafe fn cleanup() {}
-
 pub fn args() -> Args {
     unsafe {
         let lp_cmd_line = c::GetCommandLineW();