static_call/x86: Handle clang's conditional tail calls

@@ -184,6 +184,37 @@ void int3_emulate_ret(struct pt_regs *re
 	unsigned long ip = int3_emulate_pop(regs);
 	int3_emulate_jmp(regs, ip);
 }
+
+static __always_inline
+void int3_emulate_jcc(struct pt_regs *regs, u8 cc, unsigned long ip, unsigned long disp)
+{
+	static const unsigned long jcc_mask[6] = {
+		[0] = X86_EFLAGS_OF,
+		[1] = X86_EFLAGS_CF,
+		[2] = X86_EFLAGS_ZF,
+		[3] = X86_EFLAGS_CF | X86_EFLAGS_ZF,
+		[4] = X86_EFLAGS_SF,
+		[5] = X86_EFLAGS_PF,
+	};
+
+	bool invert = cc & 1;
+	bool match;
+
+	if (cc < 0xc) {
+		match = regs->flags & jcc_mask[cc >> 1];
+	} else {
+		match = ((regs->flags & X86_EFLAGS_SF) >> X86_EFLAGS_SF_BIT) ^
+			((regs->flags & X86_EFLAGS_OF) >> X86_EFLAGS_OF_BIT);
+		if (cc >= 0xe)
+			match = match || (regs->flags & X86_EFLAGS_ZF);
+	}
+
+	if ((match && !invert) || (!match && invert))
+		ip += disp;
+
+	int3_emulate_jmp(regs, ip);
+}
+
 #endif /* !CONFIG_UML_X86 */
 
 #endif /* _ASM_X86_TEXT_PATCHING_H */

@@ -464,50 +464,26 @@ static void kprobe_emulate_call(struct k
 }
 NOKPROBE_SYMBOL(kprobe_emulate_call);
 
-static nokprobe_inline
-void __kprobe_emulate_jmp(struct kprobe *p, struct pt_regs *regs, bool cond)
+static void kprobe_emulate_jmp(struct kprobe *p, struct pt_regs *regs)
 {
 	unsigned long ip = regs->ip - INT3_INSN_SIZE + p->ainsn.size;
 
-	if (cond)
-		ip += p->ainsn.rel32;
+	ip += p->ainsn.rel32;
 	int3_emulate_jmp(regs, ip);
 }
-
-static void kprobe_emulate_jmp(struct kprobe *p, struct pt_regs *regs)
-{
-	__kprobe_emulate_jmp(p, regs, true);
-}
 NOKPROBE_SYMBOL(kprobe_emulate_jmp);
 
-static const unsigned long jcc_mask[6] = {
-	[0] = X86_EFLAGS_OF,
-	[1] = X86_EFLAGS_CF,
-	[2] = X86_EFLAGS_ZF,
-	[3] = X86_EFLAGS_CF | X86_EFLAGS_ZF,
-	[4] = X86_EFLAGS_SF,
-	[5] = X86_EFLAGS_PF,
-};
-
 static void kprobe_emulate_jcc(struct kprobe *p, struct pt_regs *regs)
 {
-	bool invert = p->ainsn.jcc.type & 1;
-	bool match;
+	unsigned long ip = regs->ip - INT3_INSN_SIZE + p->ainsn.size;
 
-	if (p->ainsn.jcc.type < 0xc) {
-		match = regs->flags & jcc_mask[p->ainsn.jcc.type >> 1];
-	} else {
-		match = ((regs->flags & X86_EFLAGS_SF) >> X86_EFLAGS_SF_BIT) ^
-			((regs->flags & X86_EFLAGS_OF) >> X86_EFLAGS_OF_BIT);
-		if (p->ainsn.jcc.type >= 0xe)
-			match = match || (regs->flags & X86_EFLAGS_ZF);
-	}
-	__kprobe_emulate_jmp(p, regs, (match && !invert) || (!match && invert));
+	int3_emulate_jcc(regs, p->ainsn.jcc.type, ip, p->ainsn.rel32);
 }
 NOKPROBE_SYMBOL(kprobe_emulate_jcc);
 
 static void kprobe_emulate_loop(struct kprobe *p, struct pt_regs *regs)
 {
+	unsigned long ip = regs->ip - INT3_INSN_SIZE + p->ainsn.size;
 	bool match;
 
 	if (p->ainsn.loop.type != 3) {	/* LOOP* */

@@ -535,7 +511,9 @@ static void kprobe_emulate_loop(struct k
 	else if (p->ainsn.loop.type == 1)	/* LOOPE */
 		match = match && (regs->flags & X86_EFLAGS_ZF);
 
-	__kprobe_emulate_jmp(p, regs, match);
+	if (match)
+		ip += p->ainsn.rel32;
+	int3_emulate_jmp(regs, ip);
 }
 NOKPROBE_SYMBOL(kprobe_emulate_loop);
 

@@ -338,6 +338,12 @@ void __init_or_module noinline apply_alt
 	}
 }
 
+static inline bool is_jcc32(struct insn *insn)
+{
+	/* Jcc.d32 second opcode byte is in the range: 0x80-0x8f */
+	return insn->opcode.bytes[0] == 0x0f && (insn->opcode.bytes[1] & 0xf0) == 0x80;
+}
+
 #if defined(CONFIG_RETPOLINE) && defined(CONFIG_OBJTOOL)
 
 /*

@@ -376,12 +382,6 @@ static int emit_indirect(int op, int reg
 	return i;
 }
 
-static inline bool is_jcc32(struct insn *insn)
-{
-	/* Jcc.d32 second opcode byte is in the range: 0x80-0x8f */
-	return insn->opcode.bytes[0] == 0x0f && (insn->opcode.bytes[1] & 0xf0) == 0x80;
-}
-
 static int emit_call_track_retpoline(void *addr, struct insn *insn, int reg, u8 *bytes)
 {
 	u8 op = insn->opcode.bytes[0];

@@ -1770,6 +1770,11 @@ void text_poke_sync(void)
 	on_each_cpu(do_sync_core, NULL, 1);
 }
 
+/*
+ * NOTE: crazy scheme to allow patching Jcc.d32 but not increase the size of
+ * this thing. When len == 6 everything is prefixed with 0x0f and we map
+ * opcode to Jcc.d8, using len to distinguish.
+ */
 struct text_poke_loc {
 	/* addr := _stext + rel_addr */
 	s32 rel_addr;

@@ -1891,6 +1896,10 @@ noinstr int poke_int3_handler(struct pt_
 		int3_emulate_jmp(regs, (long)ip + tp->disp);
 		break;
 
+	case 0x70 ... 0x7f: /* Jcc */
+		int3_emulate_jcc(regs, tp->opcode & 0xf, (long)ip, tp->disp);
+		break;
+
 	default:
 		BUG();
 	}

@@ -1964,16 +1973,26 @@ static void text_poke_bp_batch(struct te
 	 * Second step: update all but the first byte of the patched range.
 	 */
 	for (do_sync = 0, i = 0; i < nr_entries; i++) {
-		u8 old[POKE_MAX_OPCODE_SIZE] = { tp[i].old, };
+		u8 old[POKE_MAX_OPCODE_SIZE+1] = { tp[i].old, };
+		u8 _new[POKE_MAX_OPCODE_SIZE+1];
+		const u8 *new = tp[i].text;
 		int len = tp[i].len;
 
 		if (len - INT3_INSN_SIZE > 0) {
 			memcpy(old + INT3_INSN_SIZE,
 			       text_poke_addr(&tp[i]) + INT3_INSN_SIZE,
 			       len - INT3_INSN_SIZE);
+
+			if (len == 6) {
+				_new[0] = 0x0f;
+				memcpy(_new + 1, new, 5);
+				new = _new;
+			}
+
 			text_poke(text_poke_addr(&tp[i]) + INT3_INSN_SIZE,
-				  (const char *)tp[i].text + INT3_INSN_SIZE,
+				  new + INT3_INSN_SIZE,
 				  len - INT3_INSN_SIZE);
+
 			do_sync++;
 		}
 

@@ -2001,8 +2020,7 @@ static void text_poke_bp_batch(struct te
 		 * The old instruction is recorded so that the event can be
 		 * processed forwards or backwards.
 		 */
-		perf_event_text_poke(text_poke_addr(&tp[i]), old, len,
-				     tp[i].text, len);
+		perf_event_text_poke(text_poke_addr(&tp[i]), old, len, new, len);
 	}
 
 	if (do_sync) {

@@ -2019,10 +2037,15 @@ static void text_poke_bp_batch(struct te
 	 * replacing opcode.
 	 */
 	for (do_sync = 0, i = 0; i < nr_entries; i++) {
-		if (tp[i].text[0] == INT3_INSN_OPCODE)
+		u8 byte = tp[i].text[0];
+
+		if (tp[i].len == 6)
+			byte = 0x0f;
+
+		if (byte == INT3_INSN_OPCODE)
 			continue;
 
-		text_poke(text_poke_addr(&tp[i]), tp[i].text, INT3_INSN_SIZE);
+		text_poke(text_poke_addr(&tp[i]), &byte, INT3_INSN_SIZE);
 		do_sync++;
 	}
 

@@ -2040,9 +2063,11 @@ static void text_poke_loc_init(struct te
 			       const void *opcode, size_t len, const void *emulate)
 {
 	struct insn insn;
-	int ret, i;
+	int ret, i = 0;
 
-	memcpy((void *)tp->text, opcode, len);
+	if (len == 6)
+		i = 1;
+	memcpy((void *)tp->text, opcode+i, len-i);
 	if (!emulate)
 		emulate = opcode;
 

@@ -2053,6 +2078,13 @@ static void text_poke_loc_init(struct te
 	tp->len = len;
 	tp->opcode = insn.opcode.bytes[0];
 
+	if (is_jcc32(&insn)) {
+		/*
+		 * Map Jcc.d32 onto Jcc.d8 and use len to distinguish.
+		 */
+		tp->opcode = insn.opcode.bytes[1] - 0x10;
+	}
+
 	switch (tp->opcode) {
 	case RET_INSN_OPCODE:
 	case JMP32_INSN_OPCODE:

@@ -2069,7 +2101,6 @@ static void text_poke_loc_init(struct te
 		BUG_ON(len != insn.length);
 	}
 
-
 	switch (tp->opcode) {
 	case INT3_INSN_OPCODE:
 	case RET_INSN_OPCODE:

@@ -2078,6 +2109,7 @@ static void text_poke_loc_init(struct te
 	case CALL_INSN_OPCODE:
 	case JMP32_INSN_OPCODE:
 	case JMP8_INSN_OPCODE:
+	case 0x70 ... 0x7f: /* Jcc */
 		tp->disp = insn.immediate.value;
 		break;
 

@@ -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 +26,40 @@ static const u8 xor5rax[] = { 0x2e, 0x2e
 
 static const u8 retinsn[] = { RET_INSN_OPCODE, 0xcc, 0xcc, 0xcc, 0xcc };
 
+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
+     ANNOTATE_RETPOLINE_SAFE
+     "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:

@@ -57,6 +86,20 @@ static void __ref __static_call_transfor
 		else
 			code = &retinsn;
 		break;
+
+	case JCC:
+		if (!func) {
+			func = __static_call_return;
+			if (cpu_feature_enabled(X86_FEATURE_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)

@@ -68,9 +111,9 @@ static void __ref __static_call_transfor
 	text_poke_bp(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");

@@ -79,7 +122,8 @@ static void __static_call_validate(void
 
 	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 ||

@@ -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 +26,40 @@ static const u8 xor5rax[] = { 0x2e, 0x2e
 
 static const u8 retinsn[] = { RET_INSN_OPCODE, 0xcc, 0xcc, 0xcc, 0xcc };
 
+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
+     ANNOTATE_RETPOLINE_SAFE
+     "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:

@@ -57,6 +86,20 @@ static void __ref __static_call_transfor
 		else
 			code = &retinsn;
 		break;
+
+	case JCC:
+		if (!func) {
+			func = __static_call_return;
+			if (cpu_feature_enabled(X86_FEATURE_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)

@@ -68,9 +111,9 @@ static void __ref __static_call_transfor
 	text_poke_bp(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");

@@ -79,7 +122,8 @@ static void __static_call_validate(void
 
 	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 ||