1 files changed, 83 insertions, 9 deletions

diff --git a/arch/x86/kernel/static_call.c b/arch/x86/kernel/static_call.c
index 2ebc338980bc..61592e41a6b1 100644
--- a/arch/x86/kernel/static_call.c
+++ b/arch/x86/kernel/static_call.c
@@ -9,6 +9,7 @@ enum insn_type {
 	NOP = 1,  /* site cond-call */
 	JMP = 2,  /* tramp / site tail-call */
 	RET = 3,  /* tramp / site cond-tail-call */
+	JCC = 4,
 };
 
 /*
@@ -25,12 +26,45 @@ static const u8 xor5rax[] = { 0x2e, 0x2e, 0x2e, 0x31, 0xc0 };
 
 static const u8 retinsn[] = { RET_INSN_OPCODE, 0xcc, 0xcc, 0xcc, 0xcc };
 
+/*
+ * ud1    (%edx),%rdi -- see __WARN_trap() / decode_bug()
+ */
+static const u8 warninsn[] = { 0x67, 0x48, 0x0f, 0xb9, 0x3a };
+
+static u8 __is_Jcc(u8 *insn) /* Jcc.d32 */
+{
+	u8 ret = 0;
+
+	if (insn[0] == 0x0f) {
+		u8 tmp = insn[1];
+		if ((tmp & 0xf0) == 0x80)
+			ret = tmp;
+	}
+
+	return ret;
+}
+
+extern void __static_call_return(void);
+
+asm (".global __static_call_return\n\t"
+     ".type __static_call_return, @function\n\t"
+     ASM_FUNC_ALIGN "\n\t"
+     "__static_call_return:\n\t"
+     ANNOTATE_NOENDBR "\n\t"
+     ANNOTATE_RETPOLINE_SAFE "\n\t"
+     "ret; int3\n\t"
+     ".size __static_call_return, . - __static_call_return \n\t");
+
 static void __ref __static_call_transform(void *insn, enum insn_type type,
 					  void *func, bool modinit)
 {
 	const void *emulate = NULL;
 	int size = CALL_INSN_SIZE;
 	const void *code;
+	u8 op, buf[6];
+
+	if ((type == JMP || type == RET) && (op = __is_Jcc(insn)))
+		type = JCC;
 
 	switch (type) {
 	case CALL:
@@ -40,7 +74,10 @@ static void __ref __static_call_transform(void *insn, enum insn_type type,
 			emulate = code;
 			code = &xor5rax;
 		}
-
+		if (func == &__WARN_trap) {
+			emulate = code;
+			code = &warninsn;
+		}
 		break;
 
 	case NOP:
@@ -52,11 +89,25 @@ static void __ref __static_call_transform(void *insn, enum insn_type type,
 		break;
 
 	case RET:
-		if (cpu_feature_enabled(X86_FEATURE_RETHUNK))
+		if (cpu_wants_rethunk_at(insn))
 			code = text_gen_insn(JMP32_INSN_OPCODE, insn, x86_return_thunk);
 		else
 			code = &retinsn;
 		break;
+
+	case JCC:
+		if (!func) {
+			func = __static_call_return;
+			if (cpu_wants_rethunk())
+				func = x86_return_thunk;
+		}
+
+		buf[0] = 0x0f;
+		__text_gen_insn(buf+1, op, insn+1, func, 5);
+		code = buf;
+		size = 6;
+
+		break;
 	}
 
 	if (memcmp(insn, code, size) == 0)
@@ -65,12 +116,12 @@ static void __ref __static_call_transform(void *insn, enum insn_type type,
 	if (system_state == SYSTEM_BOOTING || modinit)
 		return text_poke_early(insn, code, size);
 
-	text_poke_bp(insn, code, size, emulate);
+	smp_text_poke_single(insn, code, size, emulate);
 }
 
-static void __static_call_validate(void *insn, bool tail, bool tramp)
+static void __static_call_validate(u8 *insn, bool tail, bool tramp)
 {
-	u8 opcode = *(u8 *)insn;
+	u8 opcode = insn[0];
 
 	if (tramp && memcmp(insn+5, tramp_ud, 3)) {
 		pr_err("trampoline signature fail");
@@ -79,12 +130,14 @@ static void __static_call_validate(void *insn, bool tail, bool tramp)
 
 	if (tail) {
 		if (opcode == JMP32_INSN_OPCODE ||
-		    opcode == RET_INSN_OPCODE)
+		    opcode == RET_INSN_OPCODE ||
+		    __is_Jcc(insn))
 			return;
 	} else {
 		if (opcode == CALL_INSN_OPCODE ||
 		    !memcmp(insn, x86_nops[5], 5) ||
-		    !memcmp(insn, xor5rax, 5))
+		    !memcmp(insn, xor5rax, 5) ||
+		    !memcmp(insn, warninsn, 5))
 			return;
 	}
 
@@ -114,7 +167,7 @@ void arch_static_call_transform(void *site, void *tramp, void *func, bool tail)
 {
 	mutex_lock(&text_mutex);
 
-	if (tramp) {
+	if (tramp && !site) {
 		__static_call_validate(tramp, true, true);
 		__static_call_transform(tramp, __sc_insn(!func, true), func, false);
 	}
@@ -128,7 +181,15 @@ void arch_static_call_transform(void *site, void *tramp, void *func, bool tail)
 }
 EXPORT_SYMBOL_GPL(arch_static_call_transform);
 
-#ifdef CONFIG_RETHUNK
+noinstr void __static_call_update_early(void *tramp, void *func)
+{
+	BUG_ON(system_state != SYSTEM_BOOTING);
+	BUG_ON(static_call_initialized);
+	__text_gen_insn(tramp, JMP32_INSN_OPCODE, tramp, func, JMP32_INSN_SIZE);
+	sync_core();
+}
+
+#ifdef CONFIG_MITIGATION_RETHUNK
 /*
  * This is called by apply_returns() to fix up static call trampolines,
  * specifically ARCH_DEFINE_STATIC_CALL_NULL_TRAMP which is recorded as
@@ -142,6 +203,19 @@ EXPORT_SYMBOL_GPL(arch_static_call_transform);
  */
 bool __static_call_fixup(void *tramp, u8 op, void *dest)
 {
+	unsigned long addr = (unsigned long)tramp;
+	/*
+	 * Not all .return_sites are a static_call trampoline (most are not).
+	 * Check if the 3 bytes after the return are still kernel text, if not,
+	 * then this definitely is not a trampoline and we need not worry
+	 * further.
+	 *
+	 * This avoids the memcmp() below tripping over pagefaults etc..
+	 */
+	if (((addr >> PAGE_SHIFT) != ((addr + 7) >> PAGE_SHIFT)) &&
+	    !kernel_text_address(addr + 7))
+		return false;
+
 	if (memcmp(tramp+5, tramp_ud, 3)) {
 		/* Not a trampoline site, not our problem. */
 		return false;