[v3] x86: Add -mindirect-branch-cs-prefix

From ed12d22089b7ee75f20e504f9e7c898dd2b92215 Mon Sep 17 00:00:00 2001
From: "H.J. Lu" <hjl.tools@gmail.com>
Date: Wed, 27 Oct 2021 06:27:15 -0700
Subject: [PATCH v3] x86: Add -mindirect-branch-cs-prefix

Add -mindirect-branch-cs-prefix to add CS prefix to call and jmp to
indirect thunk with branch target in r8-r15 registers so that the call
and jmp instruction length is 6 bytes to allow them to be replaced with
"lfence; call *%r8-r15" or "lfence; jmp *%r8-r15" at run-time.

gcc/

	PR target/102952
	* config/i386/i386.c (ix86_output_jmp_thunk_or_indirect): Emit
	CS prefix for -mindirect-branch-cs-prefix.
	(ix86_output_indirect_branch_via_reg): Likewise.
	* config/i386/i386.opt: Add -mindirect-branch-cs-prefix.
	* doc/invoke.texi: Document -mindirect-branch-cs-prefix.

gcc/testsuite/

	PR target/102952
	* gcc.target/i386/indirect-thunk-cs-prefix-1.c: New test.
	* gcc.target/i386/indirect-thunk-cs-prefix-2.c: Likewise.
---
 gcc/config/i386/i386.c                            |  6 ++++++
 gcc/config/i386/i386.opt                          |  4 ++++
 gcc/doc/invoke.texi                               | 10 +++++++++-
 .../gcc.target/i386/indirect-thunk-cs-prefix-1.c  | 14 ++++++++++++++
 .../gcc.target/i386/indirect-thunk-cs-prefix-2.c  | 15 +++++++++++++++
 5 files changed, 48 insertions(+), 1 deletion(-)
 create mode 100644 gcc/testsuite/gcc.target/i386/indirect-thunk-cs-prefix-1.c
 create mode 100644 gcc/testsuite/gcc.target/i386/indirect-thunk-cs-prefix-2.c

diff --git a/gcc/config/i386/i386.c b/gcc/config/i386/i386.c
index c246c8736f5..7fe271b1b94 100644
--- a/gcc/config/i386/i386.c
+++ b/gcc/config/i386/i386.c
@@ -15982,6 +15982,9 @@  ix86_output_jmp_thunk_or_indirect (const char *thunk_name, const int regno)
 {
   if (thunk_name != NULL)
     {
+      if (REX_INT_REGNO_P (regno)
+	  && ix86_indirect_branch_cs_prefix)
+	fprintf (asm_out_file, "\tcs\n");
       fprintf (asm_out_file, "\tjmp\t");
       assemble_name (asm_out_file, thunk_name);
       putc ('\n', asm_out_file);
@@ -16031,6 +16034,9 @@  ix86_output_indirect_branch_via_reg (rtx call_op, bool sibcall_p)
     {
       if (thunk_name != NULL)
 	{
+	  if (REX_INT_REGNO_P (regno)
+	      && ix86_indirect_branch_cs_prefix)
+	    fprintf (asm_out_file, "\tcs\n");
 	  fprintf (asm_out_file, "\tcall\t");
 	  assemble_name (asm_out_file, thunk_name);
 	  putc ('\n', asm_out_file);
diff --git a/gcc/config/i386/i386.opt b/gcc/config/i386/i386.opt
index 2b6d8aab101..3e67c537bb7 100644
--- a/gcc/config/i386/i386.opt
+++ b/gcc/config/i386/i386.opt
@@ -1076,6 +1076,10 @@  Enum(indirect_branch) String(thunk-inline) Value(indirect_branch_thunk_inline)
 EnumValue
 Enum(indirect_branch) String(thunk-extern) Value(indirect_branch_thunk_extern)
 
+mindirect-branch-cs-prefix
+Target Var(ix86_indirect_branch_cs_prefix) Init(0)
+Add CS prefix to call and jmp to indirect thunk with branch target in r8-r15 registers.
+
 mindirect-branch-register
 Target Var(ix86_indirect_branch_register) Init(0)
 Force indirect call and jump via register.
diff --git a/gcc/doc/invoke.texi b/gcc/doc/invoke.texi
index d62ec08150e..5fed1dd6a31 100644
--- a/gcc/doc/invoke.texi
+++ b/gcc/doc/invoke.texi
@@ -1427,7 +1427,8 @@  See RS/6000 and PowerPC Options.
 -mstack-protector-guard-symbol=@var{symbol} @gol
 -mgeneral-regs-only  -mcall-ms2sysv-xlogues -mrelax-cmpxchg-loop @gol
 -mindirect-branch=@var{choice}  -mfunction-return=@var{choice} @gol
--mindirect-branch-register -mharden-sls=@var{choice} -mneeded}
+-mindirect-branch-register -mharden-sls=@var{choice} @gol
+-mindirect-branch-cs-prefix -mneeded}
 
 @emph{x86 Windows Options}
 @gccoptlist{-mconsole  -mcygwin  -mno-cygwin  -mdll @gol
@@ -32416,6 +32417,13 @@  hardening.  @samp{return} enables SLS hardening for function return.
 @samp{indirect-branch} enables SLS hardening for indirect branch.
 @samp{all} enables all SLS hardening.
 
+@item -mindirect-branch-cs-prefix
+@opindex mindirect-branch-cs-prefix
+Add CS prefix to call and jmp to indirect thunk with branch target in
+r8-r15 registers so that the call and jmp instruction length is 6 bytes
+to allow them to be replaced with @samp{lfence; call *%r8-r15} or
+@samp{lfence; jmp *%r8-r15} at run-time.
+
 @end table
 
 These @samp{-m} switches are supported in addition to the above
diff --git a/gcc/testsuite/gcc.target/i386/indirect-thunk-cs-prefix-1.c b/gcc/testsuite/gcc.target/i386/indirect-thunk-cs-prefix-1.c
new file mode 100644
index 00000000000..db2f3416823
--- /dev/null
+++ b/gcc/testsuite/gcc.target/i386/indirect-thunk-cs-prefix-1.c
@@ -0,0 +1,14 @@ 
+/* { dg-do compile { target { ! ia32 } } } */
+/* { dg-options "-O2 -ffixed-rax -ffixed-rbx -ffixed-rcx -ffixed-rdx -ffixed-rdi -ffixed-rsi -mindirect-branch-cs-prefix -mindirect-branch=thunk-extern" } */
+/* { dg-additional-options "-fno-pic" { target { ! *-*-darwin* } } } */
+
+extern void (*fptr) (void);
+
+void
+foo (void)
+{
+  fptr ();
+}
+
+/* { dg-final { scan-assembler-times "jmp\[ \t\]+_?__x86_indirect_thunk_r\[0-9\]+" 1 } } */
+/* { dg-final { scan-assembler-times "\tcs" 1 } } */
diff --git a/gcc/testsuite/gcc.target/i386/indirect-thunk-cs-prefix-2.c b/gcc/testsuite/gcc.target/i386/indirect-thunk-cs-prefix-2.c
new file mode 100644
index 00000000000..adfc39a49d4
--- /dev/null
+++ b/gcc/testsuite/gcc.target/i386/indirect-thunk-cs-prefix-2.c
@@ -0,0 +1,15 @@ 
+/* { dg-do compile { target { ! ia32 } } } */
+/* { dg-options "-O2 -ffixed-rax -ffixed-rbx -ffixed-rcx -ffixed-rdx -ffixed-rdi -ffixed-rsi -mindirect-branch-cs-prefix -mindirect-branch=thunk-extern" } */
+/* { dg-additional-options "-fno-pic" { target { ! *-*-darwin* } } } */
+
+extern void (*bar) (void);
+
+int
+foo (void)
+{
+  bar ();
+  return 0;
+}
+
+/* { dg-final { scan-assembler-times "call\[ \t\]+_?__x86_indirect_thunk_r\[0-9\]+" 1 } } */
+/* { dg-final { scan-assembler-times "\tcs" 1 } } */
-- 
2.33.1