[PATCH v3 10/10] x86/ibt: Optimize fineibt-bhi arity 1 case

[Peter Zijlstra]

Saves a CALL to an out-of-line thunk for the common case of 1
argument.

Suggested-by: Scott Constable <scott.d.constable@xxxxxxxxx>
Signed-off-by: Peter Zijlstra (Intel) <peterz@xxxxxxxxxxxxx>
---
 arch/x86/include/asm/ibt.h    |    4 ++
 arch/x86/kernel/alternative.c |   61 +++++++++++++++++++++++++++++++++++-------
 2 files changed, 56 insertions(+), 9 deletions(-)

--- a/arch/x86/include/asm/ibt.h
+++ b/arch/x86/include/asm/ibt.h
@@ -70,6 +70,10 @@ static inline bool __is_endbr(u32 val)
 	if (val == gen_endbr_poison())
 		return true;
 
+	/* See cfi_fineibt_bhi_preamble() */
+	if (IS_ENABLED(CONFIG_FINEIBT_BHI) && val == 0x001f0ff5)
+		return true;
+
 	val &= ~0x01000000U; /* ENDBR32 -> ENDBR64 */
 	return val == gen_endbr();
 }
--- a/arch/x86/kernel/alternative.c
+++ b/arch/x86/kernel/alternative.c
@@ -1299,6 +1299,55 @@ static int cfi_rand_preamble(s32 *start,
 	return 0;
 }
 
+static void cfi_fineibt_bhi_preamble(void *addr, int arity)
+{
+	bool warn = IS_ENABLED(CONFIG_CFI_PREMISSIVE) || cfi_warn;
+
+	if (!arity)
+		return;
+
+	if (!warn && arity == 1) {
+		/*
+		 * Crazy scheme to allow arity-1 inline:
+		 *
+		 * __cfi_foo:
+		 *  0: f3 0f 1e fa             endbr64
+		 *  4: 41 81 <ea> 78 56 34 12  sub     0x12345678, %r10d
+		 *  b: 49 0f 45 fa             cmovne  %r10, %rdi
+		 *  f: 75 f5                   jne     __cfi_foo+6
+		 * 11: 0f 1f 00                nopl    (%rax)
+		 *
+		 * Code that direct calls to foo()+0, decodes the tail end as:
+		 *
+		 * foo:
+		 *  0: f5                      cmc
+		 *  1: 0f 1f 00                nopl    (%rax)
+		 *
+		 * which clobbers CF, but does not affect anything ABI
+		 * wise.
+		 *
+		 * Notably, this scheme is incompatible with permissive CFI
+		 * because the cmov is unconditional and RDI will have been
+		 * clobbered.
+		 */
+		const u8 magic[9] = {
+			0x49, 0x0f, 0x45, 0xfa,
+			0x75, 0xf5,
+			BYTES_NOP3,
+		};
+
+		text_poke_early(addr + fineibt_preamble_bhi, magic, 9);
+
+		return;
+	}
+
+	text_poke_early(addr + fineibt_preamble_bhi,
+			text_gen_insn(CALL_INSN_OPCODE,
+				      addr + fineibt_preamble_bhi,
+				      __bhi_args[arity]),
+			CALL_INSN_SIZE);
+}
+
 static int cfi_rewrite_preamble(s32 *start, s32 *end)
 {
 	s32 *s;
@@ -1329,14 +1378,8 @@ static int cfi_rewrite_preamble(s32 *sta
 			  "kCFI preamble has wrong register at: %pS %*ph\n",
 			  addr, 5, addr);
 
-		if (!cfi_bhi || !arity)
-			continue;
-
-		text_poke_early(addr + fineibt_preamble_bhi,
-				text_gen_insn(CALL_INSN_OPCODE,
-					      addr + fineibt_preamble_bhi,
-					      __bhi_args[arity]),
-				CALL_INSN_SIZE);
+		if (cfi_bhi)
+			cfi_fineibt_bhi_preamble(addr, arity);
 	}
 
 	return 0;
@@ -1349,7 +1392,7 @@ static void cfi_rewrite_endbr(s32 *start
 	for (s = start; s < end; s++) {
 		void *addr = (void *)s + *s;
 
-		if (!is_endbr(addr + 16))
+		if (!exact_endbr(addr + 16))
 			continue;
 
 		poison_endbr(addr + 16);