x86/alternative: Optimize returns patching

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) <bp@alien8.de>
Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lore.kernel.org/r/20230512120952.7924-1-bp@alien8.de

1 files changed, 10 insertions, 3 deletions

diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c
index b78d55f0dfad..3bb0a5f61e8c 100644
--- a/arch/x86/kernel/alternative.c
+++ b/arch/x86/kernel/alternative.c
@@ -693,13 +693,12 @@ static int patch_return(void *addr, struct insn *insn, u8 *bytes)
 {
 	int i = 0;
 
+	/* Patch the custom return thunks... */
 	if (cpu_feature_enabled(X86_FEATURE_RETHUNK)) {
-		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;
 	}
 
@@ -712,6 +711,14 @@ 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;