[compiler-rt] Support Intel CET

[hjl.tools]

Summary

1. Include <cet.h> in sanitizer_common/sanitizer_asm.h to mark Intel CET support when Intel CET is enabled.
2. Add _CET_ENDBR to function entries in assembly codes so that ENDBR instruction will be generated when Intel CET is enabled.

[MaskRay]

[compiler-rt] Support Intel CET

compiler-rt consists of sanitizers, builtins (similar to libgcc), xray, orc (for JIT), and a bunch of other things.
If this is for sanitizer functions which may be called indirectly, using a [sanitizer] tag may be better.

Has this been verified on CET capable hardware by testing check-all (which includes check-asan check-msan check-tsan check-ubsan ...)?

I assume that builtins will be made CET compatible by D109811.

[hjl.tools]

In D110999#3041390, @MaskRay wrote:

[compiler-rt] Support Intel CET

compiler-rt consists of sanitizers, builtins (similar to libgcc), xray, orc (for JIT), and a bunch of other things.
If this is for sanitizer functions which may be called indirectly, using a [sanitizer] tag may be better.

I created a new one: D111185.

Has this been verified on CET capable hardware by testing check-all (which includes check-asan check-msan check-tsan check-ubsan ...)?

Yes.

I assume that builtins will be made CET compatible by D109811.

Yes,

compiler-rt/lib/hwasan/hwasan_setjmp_x86_64.S

 
 .section .text
 .file "hwasan_setjmp_x86_64.S"
 
 .global __interceptor_setjmp
 ASM_TYPE_FUNCTION(__interceptor_setjmp)
 __interceptor_setjmp:
   CFI_STARTPROC
+  _CET_ENDBR
   xorl %esi, %esi
   jmp __interceptor_sigsetjmp
   CFI_ENDPROC
 ASM_SIZE(__interceptor_setjmp)
 
 .global __interceptor_sigsetjmp
 ASM_TYPE_FUNCTION(__interceptor_sigsetjmp)
 __interceptor_sigsetjmp:
   CFI_STARTPROC
+  _CET_ENDBR
 
   // Save callee save registers.
   mov %rbx, (0*8)(%rdi)
   mov %rbp, (1*8)(%rdi)
   mov %r12, (2*8)(%rdi)
   mov %r13, (3*8)(%rdi)
   mov %r14, (4*8)(%rdi)
   mov %r15, (5*8)(%rdi)

compiler-rt/lib/sanitizer_common/sanitizer_asm.h

 #if defined(__ELF__) && (defined(__GNU__) || defined(__FreeBSD__) || \
                          defined(__Fuchsia__) || defined(__linux__))
 // clang-format off
 #define NO_EXEC_STACK_DIRECTIVE .section .note.GNU-stack,"",%progbits
 // clang-format on
 #else
 #define NO_EXEC_STACK_DIRECTIVE
 #endif
+
+#if defined(__x86_64__) || defined(__i386__)
+#include <cet.h>
+#endif

compiler-rt/lib/sanitizer_common/sanitizer_common_interceptors_vfork_i386.inc.S

 #if defined(__i386__) && defined(__linux__)
 
 #include "sanitizer_common/sanitizer_asm.h"
 
 .comm _ZN14__interception10real_vforkE,4,4
 .globl ASM_WRAPPER_NAME(vfork)
 ASM_TYPE_FUNCTION(ASM_WRAPPER_NAME(vfork))
 ASM_WRAPPER_NAME(vfork):
+        _CET_ENDBR
         // Store return address in the spill area and tear down the stack frame.
         sub     $12, %esp
         call    COMMON_INTERCEPTOR_SPILL_AREA
         mov     12(%esp), %ecx
         mov     %ecx, (%eax)
         add     $16, %esp
 
         call    .L0$pb

compiler-rt/lib/sanitizer_common/sanitizer_common_interceptors_vfork_x86_64.inc.S

 #if defined(__x86_64__) && defined(__linux__)
 
 #include "sanitizer_common/sanitizer_asm.h"
 
 .comm _ZN14__interception10real_vforkE,8,8
 .globl ASM_WRAPPER_NAME(vfork)
 ASM_TYPE_FUNCTION(ASM_WRAPPER_NAME(vfork))
 ASM_WRAPPER_NAME(vfork):
+        _CET_ENDBR
         // Store return address in the spill area and tear down the stack frame.
         push    %rcx
         call    COMMON_INTERCEPTOR_SPILL_AREA
         pop     %rcx
         pop     %rdi
         mov     %rdi, (%rax)
 
         call    *_ZN14__interception10real_vforkE(%rip)

compiler-rt/lib/tsan/rtl/tsan_rtl_amd64.S

 // The content of this file is x86_64-only:
 #if defined(__x86_64__)
 
 #include "sanitizer_common/sanitizer_asm.h"
 
 #if !defined(__APPLE__)
 .section .text
 #else
 .section __TEXT,__text
 #endif
 
 ASM_HIDDEN(__tsan_trace_switch)
 .globl ASM_SYMBOL(__tsan_trace_switch_thunk)
 ASM_SYMBOL(__tsan_trace_switch_thunk):
   CFI_STARTPROC
+  _CET_ENDBR
   # Save scratch registers.
   push %rax
   CFI_ADJUST_CFA_OFFSET(8)
   CFI_REL_OFFSET(%rax, 0)
   push %rcx
   CFI_ADJUST_CFA_OFFSET(8)
   CFI_REL_OFFSET(%rcx, 0)
   push %rdx
ASM_SYMBOL(__tsan_trace_switch_thunk):
   CFI_RESTORE(%r11)
   ret
   CFI_ENDPROC
 
 ASM_HIDDEN(__tsan_report_race)
 .globl ASM_SYMBOL(__tsan_report_race_thunk)
 ASM_SYMBOL(__tsan_report_race_thunk):
   CFI_STARTPROC
+  _CET_ENDBR
   # Save scratch registers.
   push %rax
   CFI_ADJUST_CFA_OFFSET(8)
   CFI_REL_OFFSET(%rax, 0)
   push %rcx
   CFI_ADJUST_CFA_OFFSET(8)
   CFI_REL_OFFSET(%rcx, 0)
   push %rdx

 ASM_TYPE_FUNCTION(ASM_SYMBOL_INTERCEPTOR(__setjmp14))
 ASM_SYMBOL_INTERCEPTOR(__setjmp14):
 #else
 .globl ASM_SYMBOL_INTERCEPTOR(setjmp)
 ASM_TYPE_FUNCTION(ASM_SYMBOL_INTERCEPTOR(setjmp))
 ASM_SYMBOL_INTERCEPTOR(setjmp):
 #endif
   CFI_STARTPROC
+  _CET_ENDBR
   // save env parameter
   push %rdi
   CFI_ADJUST_CFA_OFFSET(8)
   CFI_REL_OFFSET(%rdi, 0)
   // obtain SP, store in %rdi, first argument to `void __tsan_setjmp(uptr sp)`
 #if defined(__FreeBSD__) || defined(__NetBSD__)
   lea 8(%rsp), %rdi
 #elif defined(__linux__) || defined(__APPLE__)

 ASM_SIZE(ASM_SYMBOL_INTERCEPTOR(setjmp))
 #endif
 
 .comm _ZN14__interception12real__setjmpE,8,8
 .globl ASM_SYMBOL_INTERCEPTOR(_setjmp)
 ASM_TYPE_FUNCTION(ASM_SYMBOL_INTERCEPTOR(_setjmp))
 ASM_SYMBOL_INTERCEPTOR(_setjmp):
   CFI_STARTPROC
+  _CET_ENDBR
   // save env parameter
   push %rdi
   CFI_ADJUST_CFA_OFFSET(8)
   CFI_REL_OFFSET(%rdi, 0)
   // obtain SP, store in %rdi, first argument to `void __tsan_setjmp(uptr sp)`
 #if defined(__FreeBSD__) || defined(__NetBSD__)
   lea 8(%rsp), %rdi
 #elif defined(__linux__) || defined(__APPLE__)

 ASM_SYMBOL_INTERCEPTOR(__sigsetjmp14):
 #else
 .comm _ZN14__interception14real_sigsetjmpE,8,8
 .globl ASM_SYMBOL_INTERCEPTOR(sigsetjmp)
 ASM_TYPE_FUNCTION(ASM_SYMBOL_INTERCEPTOR(sigsetjmp))
 ASM_SYMBOL_INTERCEPTOR(sigsetjmp):
 #endif
   CFI_STARTPROC
+  _CET_ENDBR
   // save env parameter
   push %rdi
   CFI_ADJUST_CFA_OFFSET(8)
   CFI_REL_OFFSET(%rdi, 0)
   // save savesigs parameter
   push %rsi
   CFI_ADJUST_CFA_OFFSET(8)
   CFI_REL_OFFSET(%rsi, 0)

 #endif
 
 #if !defined(__APPLE__) && !defined(__NetBSD__)
 .comm _ZN14__interception16real___sigsetjmpE,8,8
 .globl ASM_SYMBOL_INTERCEPTOR(__sigsetjmp)
 ASM_TYPE_FUNCTION(ASM_SYMBOL_INTERCEPTOR(__sigsetjmp))
 ASM_SYMBOL_INTERCEPTOR(__sigsetjmp):
   CFI_STARTPROC
+  _CET_ENDBR
   // save env parameter
   push %rdi
   CFI_ADJUST_CFA_OFFSET(8)
   CFI_REL_OFFSET(%rdi, 0)
   // save savesigs parameter
   push %rsi
   CFI_ADJUST_CFA_OFFSET(8)
   CFI_REL_OFFSET(%rsi, 0)