From e60d66711185fa2e3164f5af92b9786e04c4fa19 Mon Sep 17 00:00:00 2001
From: Jacob Young <jacobly0@users.noreply.github.com>
Date: Wed, 21 Feb 2024 16:21:14 +0100
Subject: Module: fix `@embedFile` of files containing zero bytes

If an adapted string key with embedded nulls was put in a hash map with
`std.hash_map.StringIndexAdapter`, then an incorrect hash would be
entered for that entry such that it is possible that when looking for
the exact key that matches the prefix of the original key up to the
first null would sometimes match this entry due to hash collisions and
sometimes not if performed later after a grow + rehash, causing the same
key to exist with two different indices breaking every string equality
comparison ever, for example claiming that a container type doesn't
contain a field because the field name string in the struct and the
string representing the identifier to lookup might be equal strings but
have different string indices.  This could maybe be fixed by changing
`std.hash_map.StringIndexAdapter.hash` to only hash up to the first
null, therefore ensuring that the entry's hash is correct and that all
future lookups will be consistent, but I don't trust anything so instead
I assert that there are no embedded nulls.
---
 src/Module.zig | 11 ++++++-----
 1 file changed, 6 insertions(+), 5 deletions(-)

(limited to 'src/Module.zig')

diff --git a/src/Module.zig b/src/Module.zig
index 66d6aa3fe5..2f32fa8197 100644
--- a/src/Module.zig
+++ b/src/Module.zig
@@ -4400,6 +4400,7 @@ fn newEmbedFile(
     src_loc: SrcLoc,
 ) !InternPool.Index {
     const gpa = mod.gpa;
+    const ip = &mod.intern_pool;
 
     const new_file = try gpa.create(EmbedFile);
     errdefer gpa.destroy(new_file);
@@ -4414,11 +4415,11 @@ fn newEmbedFile(
         .mtime = actual_stat.mtime,
     };
     const size = std.math.cast(usize, actual_stat.size) orelse return error.Overflow;
-    const ip = &mod.intern_pool;
 
-    const ptr = try ip.string_bytes.addManyAsSlice(gpa, size);
-    const actual_read = try file.readAll(ptr);
+    const bytes = try ip.string_bytes.addManyAsSlice(gpa, try std.math.add(usize, size, 1));
+    const actual_read = try file.readAll(bytes[0..size]);
     if (actual_read != size) return error.UnexpectedEndOfFile;
+    bytes[size] = 0;
 
     const comp = mod.comp;
     switch (comp.cache_use) {
@@ -4427,7 +4428,7 @@ fn newEmbedFile(
             errdefer gpa.free(copied_resolved_path);
             whole.cache_manifest_mutex.lock();
             defer whole.cache_manifest_mutex.unlock();
-            try man.addFilePostContents(copied_resolved_path, ptr, stat);
+            try man.addFilePostContents(copied_resolved_path, bytes[0..size], stat);
         },
         .incremental => {},
     }
@@ -4437,7 +4438,7 @@ fn newEmbedFile(
         .sentinel = .zero_u8,
         .child = .u8_type,
     } });
-    const array_val = try ip.getTrailingAggregate(gpa, array_ty, size);
+    const array_val = try ip.getTrailingAggregate(gpa, array_ty, bytes.len);
 
     const ptr_ty = (try mod.ptrType(.{
         .child = array_ty,
-- 
cgit v1.2.3