x86/alternative: Optimize returns patching

commit d2408e0 upstream.

Instead of decoding each instruction in the return sites range only to
realize that that return site is a jump to the default return thunk
which is needed - X86_FEATURE_RETHUNK is enabled - lift that check
before the loop and get rid of that loop overhead.

Add comments about what gets patched, while at it.

Signed-off-by: Borislav Petkov (AMD) <[email protected]>
Acked-by: Peter Zijlstra (Intel) <[email protected]>
Link: https://lore.kernel.org/r/[email protected]
Signed-off-by: Pawan Gupta <[email protected]>
Signed-off-by: Greg Kroah-Hartman <[email protected]>

Author: bp3tk0v

arch/x86/kernel/alternative.c

@@ -778,13 +778,12 @@ static int patch_return(void *addr, struct insn *insn, u8 *bytes)
 {
 	int i = 0;
 
+	/* Patch the custom return thunks... */
 	if (cpu_wants_rethunk_at(addr)) {
-		if (x86_return_thunk == __x86_return_thunk)
-			return -1;
-
 		i = JMP32_INSN_SIZE;
 		__text_gen_insn(bytes, JMP32_INSN_OPCODE, addr, x86_return_thunk, i);
 	} else {
+		/* ... or patch them out if not needed. */
 		bytes[i++] = RET_INSN_OPCODE;
 	}
 
@@ -797,6 +796,14 @@ void __init_or_module noinline apply_returns(s32 *start, s32 *end)
 {
 	s32 *s;
 
+	/*
+	 * Do not patch out the default return thunks if those needed are the
+	 * ones generated by the compiler.
+	 */
+	if (cpu_feature_enabled(X86_FEATURE_RETHUNK) &&
+	    (x86_return_thunk == __x86_return_thunk))
+		return;
+
 	for (s = start; s < end; s++) {
 		void *dest = NULL, *addr = (void *)s + *s;
 		struct insn insn;