From 3cb47d8b4dc0242665219e9b86825ebdaa43fb0c Mon Sep 17 00:00:00 2001
From: "github-actions[bot]"
 <41898282+github-actions[bot]@users.noreply.github.com>
Date: Mon, 13 Mar 2023 12:57:49 +0100
Subject: [PATCH] [mono] Use `unsigned char` when computing UTF8 string hashes
 (#21633)

Backport of https://github.com/dotnet/runtime/pull/83273 to mono/mono `2020-02`

The C standard does not specify whether `char` is signed or unsigned, it is implementation defined.

Apparently Android aarch64 makes a different choice than other platforms (at least macOS arm64 and Windows x64 give different results).

Mono uses `mono_metadata_str_hash` in the AOT compiler and AOT runtime to optimize class name lookup.  As a result, classes whose names include UTF-8 continuation bytes (with the high bit = 1) will hash differently in the AOT compiler and on the device.

Contributes to https://github.com/dotnet/runtime/issues/82187
Contributes to https://github.com/dotnet/runtime/issues/78638
---
 mono/eglib/ghashtable.c  | 2 +-
 mono/metadata/metadata.c | 3 ++-
 2 files changed, 3 insertions(+), 2 deletions(-)

diff --git a/mono/eglib/ghashtable.c b/mono/eglib/ghashtable.c
index 5329fab0cab..8799ed46f8e 100644
--- a/mono/eglib/ghashtable.c
+++ b/mono/eglib/ghashtable.c
@@ -673,7 +673,7 @@ guint
 g_str_hash (gconstpointer v1)
 {
 	guint hash = 0;
-	char *p = (char *) v1;
+	unsigned char *p = (unsigned char *) v1;
 
 	while (*p++)
 		hash = (hash << 5) - (hash + *p);
diff --git a/mono/metadata/metadata.c b/mono/metadata/metadata.c
index 81217077470..47d3273548e 100644
--- a/mono/metadata/metadata.c
+++ b/mono/metadata/metadata.c
@@ -5532,7 +5532,8 @@ guint
 mono_metadata_str_hash (gconstpointer v1)
 {
 	/* Same as g_str_hash () in glib */
-	char *p = (char *) v1;
+	/* note: signed/unsigned char matters - we feed UTF-8 to this function, so the high bit will give diferent results if we don't match. */
+	unsigned char *p = (unsigned char *) v1;
 	guint hash = *p;
 
 	while (*p++) {
-- 
2.11.4.GIT