Auto merge of #110083 - saethlin:encode-hashes-as-bytes, r=cjgillot

Encode hashes as bytes, not varint

In a few places, we store hashes as `u64` or `u128` and then apply `derive(Decodable, Encodable)` to the enclosing struct/enum. It is more efficient to encode hashes directly than try to apply some varint encoding. This PR adds two new types `Hash64` and `Hash128` which are produced by `StableHasher` and replace every use of storing a `u64` or `u128` that represents a hash.

Distribution of the byte lengths of leb128 encodings, from `x build --stage 2` with `incremental = true`

Before:
```
(  1) 373418203 (53.7%, 53.7%): 1
(  2) 196240113 (28.2%, 81.9%): 3
(  3) 108157958 (15.6%, 97.5%): 2
(  4)  17213120 ( 2.5%, 99.9%): 4
(  5)    223614 ( 0.0%,100.0%): 9
(  6)    216262 ( 0.0%,100.0%): 10
(  7)     15447 ( 0.0%,100.0%): 5
(  8)      3633 ( 0.0%,100.0%): 19
(  9)      3030 ( 0.0%,100.0%): 8
( 10)      1167 ( 0.0%,100.0%): 18
( 11)      1032 ( 0.0%,100.0%): 7
( 12)      1003 ( 0.0%,100.0%): 6
( 13)        10 ( 0.0%,100.0%): 16
( 14)        10 ( 0.0%,100.0%): 17
( 15)         5 ( 0.0%,100.0%): 12
( 16)         4 ( 0.0%,100.0%): 14
```

After:
```
(  1) 372939136 (53.7%, 53.7%): 1
(  2) 196240140 (28.3%, 82.0%): 3
(  3) 108014969 (15.6%, 97.5%): 2
(  4)  17192375 ( 2.5%,100.0%): 4
(  5)       435 ( 0.0%,100.0%): 5
(  6)        83 ( 0.0%,100.0%): 18
(  7)        79 ( 0.0%,100.0%): 10
(  8)        50 ( 0.0%,100.0%): 9
(  9)         6 ( 0.0%,100.0%): 19
```

The remaining 9 or 10 and 18 or 19 are `u64` and `u128` respectively that have the high bits set. As far as I can tell these are coming primarily from `SwitchTargets`.

2 files changed, 5 insertions, 4 deletions

diff --git a/compiler/rustc_query_impl/src/on_disk_cache.rs b/compiler/rustc_query_impl/src/on_disk_cache.rs
index dc3cb64b3c2..d43af643b3b 100644
--- a/compiler/rustc_query_impl/src/on_disk_cache.rs
+++ b/compiler/rustc_query_impl/src/on_disk_cache.rs
@@ -1,6 +1,7 @@
 use crate::QueryCtxt;
 use rustc_data_structures::fx::{FxHashMap, FxIndexSet};
 use rustc_data_structures::memmap::Mmap;
+use rustc_data_structures::stable_hasher::Hash64;
 use rustc_data_structures::sync::{HashMapExt, Lock, Lrc, RwLock};
 use rustc_data_structures::unhash::UnhashMap;
 use rustc_data_structures::unord::UnordSet;
@@ -138,7 +139,7 @@ impl AbsoluteBytePos {
 /// is the only thing available when decoding the cache's [Footer].
 #[derive(Encodable, Decodable, Clone, Debug)]
 struct EncodedSourceFileId {
-    file_name_hash: u64,
+    file_name_hash: Hash64,
     stable_crate_id: StableCrateId,
 }
 
@@ -667,7 +668,7 @@ impl<'a, 'tcx> Decodable<CacheDecoder<'a, 'tcx>> for ExpnId {
             #[cfg(debug_assertions)]
             {
                 use rustc_data_structures::stable_hasher::{HashStable, StableHasher};
-                let local_hash: u64 = decoder.tcx.with_stable_hashing_context(|mut hcx| {
+                let local_hash = decoder.tcx.with_stable_hashing_context(|mut hcx| {
                     let mut hasher = StableHasher::new();
                     expn_id.expn_data().hash_stable(&mut hcx, &mut hasher);
                     hasher.finish()
diff --git a/compiler/rustc_query_impl/src/plumbing.rs b/compiler/rustc_query_impl/src/plumbing.rs
index afbead7d1ae..32222df25d4 100644
--- a/compiler/rustc_query_impl/src/plumbing.rs
+++ b/compiler/rustc_query_impl/src/plumbing.rs
@@ -5,7 +5,7 @@
 use crate::on_disk_cache::{CacheDecoder, CacheEncoder, EncodedDepNodeIndex};
 use crate::profiling_support::QueryKeyStringCache;
 use crate::{on_disk_cache, Queries};
-use rustc_data_structures::stable_hasher::{HashStable, StableHasher};
+use rustc_data_structures::stable_hasher::{Hash64, HashStable, StableHasher};
 use rustc_data_structures::sync::{AtomicU64, Lock};
 use rustc_errors::{Diagnostic, Handler};
 use rustc_middle::dep_graph::{
@@ -342,7 +342,7 @@ pub(crate) fn create_query_frame<
             let mut hasher = StableHasher::new();
             std::mem::discriminant(&kind).hash_stable(&mut hcx, &mut hasher);
             key.hash_stable(&mut hcx, &mut hasher);
-            hasher.finish::<u64>()
+            hasher.finish::<Hash64>()
         })
     };
     let ty_adt_id = key.ty_adt_id();