[mono] Use unsigned char when computing UTF8 string hashes (#21633)

github-actions[bot] · web-flow · commit 3cb47d8b4dc0 · 2023-03-13T12:57:49.000+01:00
Backport of dotnet/runtime#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 dotnet/runtime#82187 Contributes to dotnet/runtime#78638
diff --git 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
@@ -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++) {

Original file line number	Diff line number	Diff line change
`@@ -673,7 +673,7 @@ guint`
`673`	`673`	`g_str_hash (gconstpointer v1)`
`674`	`674`	`{`
`675`	`675`	`guint hash = 0;`
`676`		`- char p = (char ) v1;`
	`676`	`+ unsigned char p = (unsigned char ) v1;`
`677`	`677`
`678`	`678`	`while (*p++)`
`679`	`679`	`hash = (hash << 5) - (hash + *p);`
Original file line number	Diff line number	Diff line change
`@@ -5532,7 +5532,8 @@ guint`
`5532`	`5532`	`mono_metadata_str_hash (gconstpointer v1)`
`5533`	`5533`	`{`
`5534`	`5534`	`/* Same as g_str_hash () in glib */`
`5535`		`- char p = (char ) v1;`
	`5535`	`+ /* 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. */`
	`5536`	`+ unsigned char p = (unsigned char ) v1;`
`5536`	`5537`	`guint hash = *p;`
`5537`	`5538`
`5538`	`5539`	`while (*p++) {`