Rollup merge of #76979 - fusion-engineering-forks:windows-fallback-ch…

…eck, r=dtolnay

Improve std::sys::windows::compat

Improves the compat_fn macro in sys::windows, which is used for conditionally loading APIs that might not be available.

- The module (dll) name can now be any string, not just an ident. (Not all Windows api modules are valid Rust identifiers. E.g. `WaitOnAddress` comes from `API-MS-Win-Core-Synch-l1-2-0.dll`.)
- Adds `FuncName::is_available()` for checking if a function is really available without having to do a duplicate lookup.
- Add comment explaining the lack of locking.
- Use `$_:block` to simplify the macro_rules.
- Apply `allow(unused_variables)` only to the fallback instead of everything.

---

The second point (`is_available()`) simplifies code that needs to pick an implementation depening on what is available, like `sys/windows/mutex.rs`. Before this change, it'd do its own lookup and keep its own `AtomicUsize` to track the result. Now it can just use `c::AcquireSRWLockExclusive::is_available()` directly.

This will also be useful when park/unpark/CondVar/etc. get improved implementations (e.g. from parking_lot or something else), as the best APIs for those are not available before Windows 8.

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

@@ -1032,7 +1032,7 @@ extern "system" {
 // Functions that aren't available on every version of Windows that we support,
 // but we still use them and just provide some form of a fallback implementation.
 compat_fn! {
-    kernel32:
+    "kernel32":
 
     pub fn CreateSymbolicLinkW(_lpSymlinkFileName: LPCWSTR,
                                _lpTargetFileName: LPCWSTR,

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

@@ -12,7 +12,6 @@
 //! function is available but afterwards it's just a load and a jump.
 
 use crate::ffi::CString;
-use crate::sync::atomic::{AtomicUsize, Ordering};
 use crate::sys::c;
 
 pub fn lookup(module: &str, symbol: &str) -> Option<usize> {
@@ -28,45 +27,69 @@ pub fn lookup(module: &str, symbol: &str) -> Option<usize> {
     }
 }
 
-pub fn store_func(ptr: &AtomicUsize, module: &str, symbol: &str, fallback: usize) -> usize {
-    let value = lookup(module, symbol).unwrap_or(fallback);
-    ptr.store(value, Ordering::SeqCst);
-    value
-}
-
 macro_rules! compat_fn {
-    ($module:ident: $(
+    ($module:literal: $(
         $(#[$meta:meta])*
-        pub fn $symbol:ident($($argname:ident: $argtype:ty),*)
-                                  -> $rettype:ty {
-            $($body:expr);*
-        }
+        pub fn $symbol:ident($($argname:ident: $argtype:ty),*) -> $rettype:ty $body:block
     )*) => ($(
-        #[allow(unused_variables)]
         $(#[$meta])*
-        pub unsafe fn $symbol($($argname: $argtype),*) -> $rettype {
+        pub mod $symbol {
+            use super::*;
             use crate::sync::atomic::{AtomicUsize, Ordering};
             use crate::mem;
+
             type F = unsafe extern "system" fn($($argtype),*) -> $rettype;
 
             static PTR: AtomicUsize = AtomicUsize::new(0);
 
+            #[allow(unused_variables)]
+            unsafe extern "system" fn fallback($($argname: $argtype),*) -> $rettype $body
+
+            /// This address is stored in `PTR` to incidate an unavailable API.
+            ///
+            /// This way, call() will end up calling fallback() if it is unavailable.
+            ///
+            /// This is a `static` to avoid rustc duplicating `fn fallback()`
+            /// into both load() and is_available(), which would break
+            /// is_available()'s comparison. By using the same static variable
+            /// in both places, they'll refer to the same (copy of the)
+            /// function.
+            ///
+            /// LLVM merging the address of fallback with other functions
+            /// (because of unnamed_addr) is fine, since it's only compared to
+            /// an address from GetProcAddress from an external dll.
+            static FALLBACK: F = fallback;
+
+            #[cold]
             fn load() -> usize {
-                crate::sys::compat::store_func(&PTR,
-                                          stringify!($module),
-                                          stringify!($symbol),
-                                          fallback as usize)
+                // There is no locking here. It's okay if this is executed by multiple threads in
+                // parallel. `lookup` will result in the same value, and it's okay if they overwrite
+                // eachothers result as long as they do so atomically. We don't need any guarantees
+                // about memory ordering, as this involves just a single atomic variable which is
+                // not used to protect or order anything else.
+                let addr = crate::sys::compat::lookup($module, stringify!($symbol))
+                    .unwrap_or(FALLBACK as usize);
+                PTR.store(addr, Ordering::Relaxed);
+                addr
             }
-            unsafe extern "system" fn fallback($($argname: $argtype),*)
-                                               -> $rettype {
-                $($body);*
+
+            fn addr() -> usize {
+                match PTR.load(Ordering::Relaxed) {
+                    0 => load(),
+                    addr => addr,
+                }
+            }
+
+            #[allow(dead_code)]
+            pub fn is_available() -> bool {
+                addr() != FALLBACK as usize
             }
 
-            let addr = match PTR.load(Ordering::SeqCst) {
-                0 => load(),
-                n => n,
-            };
-            mem::transmute::<usize, F>(addr)($($argname),*)
+            pub unsafe fn call($($argname: $argtype),*) -> $rettype {
+                mem::transmute::<usize, F>(addr())($($argname),*)
+            }
         }
+
+        pub use $symbol::call as $symbol;
     )*)
 }

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

@@ -23,7 +23,6 @@ use crate::cell::{Cell, UnsafeCell};
 use crate::mem::{self, MaybeUninit};
 use crate::sync::atomic::{AtomicUsize, Ordering};
 use crate::sys::c;
-use crate::sys::compat;
 
 pub struct Mutex {
     // This is either directly an SRWLOCK (if supported), or a Box<Inner> otherwise.
@@ -40,8 +39,8 @@ struct Inner {
 
 #[derive(Clone, Copy)]
 enum Kind {
-    SRWLock = 1,
-    CriticalSection = 2,
+    SRWLock,
+    CriticalSection,
 }
 
 #[inline]
@@ -130,21 +129,7 @@ impl Mutex {
 }
 
 fn kind() -> Kind {
-    static KIND: AtomicUsize = AtomicUsize::new(0);
-
-    let val = KIND.load(Ordering::SeqCst);
-    if val == Kind::SRWLock as usize {
-        return Kind::SRWLock;
-    } else if val == Kind::CriticalSection as usize {
-        return Kind::CriticalSection;
-    }
-
-    let ret = match compat::lookup("kernel32", "AcquireSRWLockExclusive") {
-        None => Kind::CriticalSection,
-        Some(..) => Kind::SRWLock,
-    };
-    KIND.store(ret as usize, Ordering::SeqCst);
-    ret
+    if c::AcquireSRWLockExclusive::is_available() { Kind::SRWLock } else { Kind::CriticalSection }
 }
 
 pub struct ReentrantMutex {