[3.14] gh-128605: Add branch protections for x86_64 in asm_trampoline.S (#128606) (#135345)

Apply Intel Control-flow Technology for x86-64 on asm_trampoline.S.

Required for mitigation against return-oriented programming (ROP)
and Call or Jump Oriented Programming (COP/JOP) attacks.

Manual application is required for the assembly files.

See also: https://sourceware.org/annobin/annobin.html/Test-cf-protection.html

Author: stratakis

Python/asm_trampoline.S

@@ -9,6 +9,9 @@
 # }
 _Py_trampoline_func_start:
 #ifdef __x86_64__
+#if defined(__CET__) && (__CET__ & 1)
+    endbr64
+#endif
     sub    $8, %rsp
     call    *%rcx
     add    $8, %rsp
@@ -34,3 +37,22 @@ _Py_trampoline_func_start:
     .globl	_Py_trampoline_func_end
 _Py_trampoline_func_end:
     .section        .note.GNU-stack,"",@progbits
+# Note for indicating the assembly code supports CET
+#if defined(__x86_64__) && defined(__CET__) && (__CET__ & 1)
+    .section    .note.gnu.property,"a"
+    .align 8
+    .long    1f - 0f
+    .long    4f - 1f
+    .long    5
+0:
+    .string  "GNU"
+1:
+    .align 8
+    .long    0xc0000002
+    .long    3f - 2f
+2:
+    .long    0x3
+3:
+    .align 8
+4:
+#endif // __x86_64__

Python/perf_jit_trampoline.c

@@ -869,7 +869,11 @@ static void elf_init_ehframe(ELFObjectContext* ctx) {
          */
 #ifdef __x86_64__
         /* x86_64 calling convention unwinding rules */
+#  if defined(__CET__) && (__CET__ & 1)
+        DWRF_U8(DWRF_CFA_advance_loc | 8);    // Advance location by 8 bytes when CET protection is enabled
+#  else
         DWRF_U8(DWRF_CFA_advance_loc | 4);    // Advance location by 4 bytes
+#  endif
         DWRF_U8(DWRF_CFA_def_cfa_offset);     // Redefine CFA offset
         DWRF_UV(16);                          // New offset: SP + 16
         DWRF_U8(DWRF_CFA_advance_loc | 6);    // Advance location by 6 bytes