Auto merge of rust-lang#115542 - saethlin:fileencoder-is-bufwriter, r=WaffleLapkin

Simplify/Optimize FileEncoder

FileEncoder is basically a BufWriter except that it exposes access to the not-written-to-yet region of the buffer so that some users can write directly to the buffer. This strategy is awesome because it lets us avoid calling memcpy for small copies, but the previous strategy was based on the writer accessing a `&mut [MaybeUninit<u8>; N]` and returning a `&[u8]` which is an API which currently mandates the use of unsafe code, making that interface in general not that appealing.

So this PR cleans up the FileEncoder implementation and builds on that general idea of direct buffer access in order to prevent `memcpy` calls in a few key places when encoding the dep graph and rmeta tables. The interface used here is now 100% safe, but with the caveat that internally we need to avoid trusting the number of bytes that the provided function claims to have written.

The original primary objective of this PR was to clean up the FileEncoder implementation so that the fix for the following issues would be easy to implement. The fix for these issues is to correctly update self.buffered even when writes fail, which I think it's easy to verify manually is now done, because all the FileEncoder methods are small.

Fixes rust-lang#115298
Fixes rust-lang#114671
Fixes rust-lang#114045
Fixes rust-lang#108100
Fixes rust-lang#106787

Author: bors

compiler/rustc_metadata/src/rmeta/table.rs

@@ -5,7 +5,6 @@ use rustc_hir::def::{CtorKind, CtorOf};
 use rustc_index::Idx;
 use rustc_middle::ty::{ParameterizedOverTcx, UnusedGenericParams};
 use rustc_serialize::opaque::FileEncoder;
-use rustc_serialize::Encoder as _;
 use rustc_span::hygiene::MacroKind;
 use std::marker::PhantomData;
 use std::num::NonZeroUsize;
@@ -468,7 +467,10 @@ impl<I: Idx, const N: usize, T: FixedSizeEncoding<ByteArray = [u8; N]>> TableBui
 
         let width = self.width;
         for block in &self.blocks {
-            buf.emit_raw_bytes(&block[..width]);
+            buf.write_with(|dest| {
+                *dest = *block;
+                width
+            });
         }
 
         LazyTable::from_position_and_encoded_size(

compiler/rustc_query_system/src/dep_graph/serialized.rs

@@ -404,16 +404,18 @@ struct NodeInfo<K: DepKind> {
 impl<K: DepKind> Encodable<FileEncoder> for NodeInfo<K> {
     fn encode(&self, e: &mut FileEncoder) {
         let header = SerializedNodeHeader::new(self);
-        e.emit_raw_bytes(&header.bytes);
+        e.write_array(header.bytes);
 
         if header.len().is_none() {
             e.emit_usize(self.edges.len());
         }
 
         let bytes_per_index = header.bytes_per_index();
         for node_index in self.edges.iter() {
-            let bytes = node_index.as_u32().to_le_bytes();
-            e.emit_raw_bytes(&bytes[..bytes_per_index]);
+            e.write_with(|dest| {
+                *dest = node_index.as_u32().to_le_bytes();
+                bytes_per_index
+            });
         }
     }
 }

compiler/rustc_serialize/src/leb128.rs

@@ -15,31 +15,28 @@ pub const fn largest_max_leb128_len() -> usize {
 macro_rules! impl_write_unsigned_leb128 {
     ($fn_name:ident, $int_ty:ty) => {
         #[inline]
-        pub fn $fn_name(
-            out: &mut [::std::mem::MaybeUninit<u8>; max_leb128_len::<$int_ty>()],
-            mut value: $int_ty,
-        ) -> &[u8] {
+        pub fn $fn_name(out: &mut [u8; max_leb128_len::<$int_ty>()], mut value: $int_ty) -> usize {
             let mut i = 0;
 
             loop {
                 if value < 0x80 {
                     unsafe {
-                        *out.get_unchecked_mut(i).as_mut_ptr() = value as u8;
+                        *out.get_unchecked_mut(i) = value as u8;
                     }
 
                     i += 1;
                     break;
                 } else {
                     unsafe {
-                        *out.get_unchecked_mut(i).as_mut_ptr() = ((value & 0x7f) | 0x80) as u8;
+                        *out.get_unchecked_mut(i) = ((value & 0x7f) | 0x80) as u8;
                     }
 
                     value >>= 7;
                     i += 1;
                 }
             }
 
-            unsafe { ::std::mem::MaybeUninit::slice_assume_init_ref(&out.get_unchecked(..i)) }
+            i
         }
     };
 }
@@ -87,10 +84,7 @@ impl_read_unsigned_leb128!(read_usize_leb128, usize);
 macro_rules! impl_write_signed_leb128 {
     ($fn_name:ident, $int_ty:ty) => {
         #[inline]
-        pub fn $fn_name(
-            out: &mut [::std::mem::MaybeUninit<u8>; max_leb128_len::<$int_ty>()],
-            mut value: $int_ty,
-        ) -> &[u8] {
+        pub fn $fn_name(out: &mut [u8; max_leb128_len::<$int_ty>()], mut value: $int_ty) -> usize {
             let mut i = 0;
 
             loop {
@@ -104,7 +98,7 @@ macro_rules! impl_write_signed_leb128 {
                 }
 
                 unsafe {
-                    *out.get_unchecked_mut(i).as_mut_ptr() = byte;
+                    *out.get_unchecked_mut(i) = byte;
                 }
 
                 i += 1;
@@ -114,7 +108,7 @@ macro_rules! impl_write_signed_leb128 {
                 }
             }
 
-            unsafe { ::std::mem::MaybeUninit::slice_assume_init_ref(&out.get_unchecked(..i)) }
+            i
         }
     };
 }

compiler/rustc_serialize/src/lib.rs

@@ -17,6 +17,9 @@ Core encoding and decoding interfaces.
 #![feature(new_uninit)]
 #![feature(allocator_api)]
 #![feature(ptr_sub_ptr)]
+#![feature(slice_first_last_chunk)]
+#![feature(inline_const)]
+#![feature(const_option)]
 #![cfg_attr(test, feature(test))]
 #![allow(rustc::internal)]
 #![deny(rustc::untranslatable_diagnostic)]