JIT: Add IBT support (#8774)

Indirect Branch Tracking (IBT) is part of Intel's Control-Flow
Enforcement Technology (CET). IBT is hardware based, forward edge
Control-Flow-Integrity mechanism where any indirect CALL/JMP must target
an ENDBR instruction or suffer #CP.

This commit adds IBT support for JIT:
1. Add endbr32/64 instruction in Dynasm.
2. Insert endbr32/64 in indirect branch target for jitted code.

gcc support CET since v8.1 and set it to default since gcc 11. With this
commit, endbr is inserted in jitted code if PHP is compiled with "gcc
-fcf-protection=full/branch".

Signed-off-by: Chen, Hu <hu1.chen@intel.com>

Author: chen-hu-97

ext/opcache/jit/dynasm/dasm_x86.lua

@@ -1147,6 +1147,8 @@ local map_op = {
   rep_0 =	"F3",
   repe_0 =	"F3",
   repz_0 =	"F3",
+  endbr32_0 =	"F30F1EFB",
+  endbr64_0 =	"F30F1EFA",
   -- F4: *hlt
   cmc_0 =	"F5",
   -- F6: test... mb,i; div... mb

ext/opcache/jit/zend_jit_x86.dasc

@@ -1623,6 +1623,22 @@ static size_t tsrm_tls_offset;
 ||	}
 |.endmacro
 
+|.macro ENDBR
+||#if defined (__CET__) && (__CET__ & 1) != 0
+|	.if X64
+|		endbr64
+|	.else
+|		endbr32
+|	.endif
+||#endif
+|.endmacro
+
+#if defined (__CET__) && (__CET__ & 1) != 0
+# define ENDBR_PADDING 4
+#else
+# define ENDBR_PADDING 0
+#endif
+
 static bool reuse_ip = 0;
 static bool delayed_call_chain = 0;
 static uint32_t  delayed_call_level = 0;
@@ -2292,6 +2308,7 @@ static int zend_jit_hybrid_hot_code_stub(dasm_State **Dst)
  */
 static int zend_jit_hybrid_hot_counter_stub(dasm_State **Dst, uint32_t cost)
 {
+	|	ENDBR
 	|	mov r0, EX->func
 	|	mov r1, aword [r0 + offsetof(zend_op_array, reserved[zend_func_info_rid])]
 	|	mov r2, aword [r1 + offsetof(zend_jit_op_array_hot_extension, counter)]
@@ -2362,6 +2379,7 @@ static int zend_jit_hybrid_hot_trace_stub(dasm_State **Dst)
 
 static int zend_jit_hybrid_trace_counter_stub(dasm_State **Dst, uint32_t cost)
 {
+	|	ENDBR
 	|	mov r0, EX->func
 	|	mov r1, aword [r0 + offsetof(zend_op_array, reserved[zend_func_info_rid])]
 	|	mov r1, aword [r1 + offsetof(zend_jit_op_array_trace_extension, offset)]
@@ -3049,6 +3067,7 @@ static int zend_jit_align_func(dasm_State **Dst)
 
 static int zend_jit_prologue(dasm_State **Dst)
 {
+	|	ENDBR
 	if (zend_jit_vm_kind == ZEND_VM_KIND_HYBRID) {
 		|	SUB_HYBRID_SPAD
 	} else if (GCC_GLOBAL_REGS) {
@@ -3456,7 +3475,7 @@ static int zend_jit_trace_link_to_root(dasm_State **Dst, zend_jit_trace_info *t,
 		prologue_size = 13;
 #endif
 	}
-	link_addr = (const void*)((const char*)t->code_start + prologue_size);
+	link_addr = (const void*)((const char*)t->code_start + prologue_size + ENDBR_PADDING);
 
 	if (timeout_exit_addr) {
 		/* Check timeout for links to LOOP */