Add leafy mode for zero-call-used-regs

Introduce 'leafy' to auto-select between 'used' and 'all' for leaf and
nonleaf functions, respectively.


for  gcc/ChangeLog

	* doc/extend.texi (zero-call-used-regs): Document leafy and
	variants thereof.
	* flag-types.h (zero_regs_flags): Add LEAFY_MODE, as well as
	LEAFY and variants.
	* function.cc (gen_call_ued_regs_seq): Set only_used for leaf
	functions in leafy mode.
	* opts.cc (zero_call_used_regs_opts): Add leafy and variants.

for  gcc/testsuite/ChangeLog

	* c-c++-common/zero-scratch-regs-leafy-1.c: New.
	* c-c++-common/zero-scratch-regs-leafy-2.c: New.
	* gcc.target/i386/zero-scratch-regs-leafy-1.c: New.
	* gcc.target/i386/zero-scratch-regs-leafy-2.c: New.

gcc/doc/extend.texi

@@ -4341,7 +4341,7 @@ through registers.
 In order to satisfy users with different security needs and control the
 run-time overhead at the same time, the @var{choice} parameter provides a
 flexible way to choose the subset of the call-used registers to be zeroed.
-The three basic values of @var{choice} are:
+The four basic values of @var{choice} are:
 
 @itemize @bullet
 @item
@@ -4354,10 +4354,16 @@ the function.
 
 @item
 @samp{all} zeros all call-used registers.
+
+@item
+@samp{leafy} behaves like @samp{used} in a leaf function, and like
+@samp{all} in a nonleaf function.  This makes for leaner zeroing in leaf
+functions, where the set of used registers is known, and that may be
+enough for some purposes of register zeroing.
 @end itemize
 
 In addition to these three basic choices, it is possible to modify
-@samp{used} or @samp{all} as follows:
+@samp{used}, @samp{all}, and @samp{leafy} as follows:
 
 @itemize @bullet
 @item
@@ -4404,10 +4410,28 @@ zeros all call-used registers that pass arguments.
 @item all-gpr-arg
 zeros all call-used general purpose registers that pass
 arguments.
+
+@item leafy
+Same as @samp{used} in a leaf function, and same as @samp{all} in a
+nonleaf function.
+
+@item leafy-gpr
+Same as @samp{used-gpr} in a leaf function, and same as @samp{all-gpr}
+in a nonleaf function.
+
+@item leafy-arg
+Same as @samp{used-arg} in a leaf function, and same as @samp{all-arg}
+in a nonleaf function.
+
+@item leafy-gpr-arg
+Same as @samp{used-gpr-arg} in a leaf function, and same as
+@samp{all-gpr-arg} in a nonleaf function.
+
 @end table
 
 Of this list, @samp{used-arg}, @samp{used-gpr-arg}, @samp{all-arg},
-and @samp{all-gpr-arg} are mainly used for ROP mitigation.
+@samp{all-gpr-arg}, @samp{leafy-arg}, and @samp{leafy-gpr-arg} are
+mainly used for ROP mitigation.
 
 The default for the attribute is controlled by @option{-fzero-call-used-regs}.
 @end table

gcc/flag-types.h

@@ -338,6 +338,7 @@ namespace zero_regs_flags {
   const unsigned int ONLY_GPR = 1UL << 2;
   const unsigned int ONLY_ARG = 1UL << 3;
   const unsigned int ENABLED = 1UL << 4;
+  const unsigned int LEAFY_MODE = 1UL << 5;
   const unsigned int USED_GPR_ARG = ENABLED | ONLY_USED | ONLY_GPR | ONLY_ARG;
   const unsigned int USED_GPR = ENABLED | ONLY_USED | ONLY_GPR;
   const unsigned int USED_ARG = ENABLED | ONLY_USED | ONLY_ARG;
@@ -346,6 +347,10 @@ namespace zero_regs_flags {
   const unsigned int ALL_GPR = ENABLED | ONLY_GPR;
   const unsigned int ALL_ARG = ENABLED | ONLY_ARG;
   const unsigned int ALL = ENABLED;
+  const unsigned int LEAFY_GPR_ARG = ENABLED | LEAFY_MODE | ONLY_GPR | ONLY_ARG;
+  const unsigned int LEAFY_GPR = ENABLED | LEAFY_MODE | ONLY_GPR;
+  const unsigned int LEAFY_ARG = ENABLED | LEAFY_MODE | ONLY_ARG;
+  const unsigned int LEAFY = ENABLED | LEAFY_MODE;
 }
 
 /* Settings of flag_incremental_link.  */

gcc/function.cc

@@ -5866,6 +5866,9 @@ gen_call_used_regs_seq (rtx_insn *ret, unsigned int zero_regs_type)
   only_used = zero_regs_type & ONLY_USED;
   only_arg = zero_regs_type & ONLY_ARG;
 
+  if ((zero_regs_type & LEAFY_MODE) && leaf_function_p ())
+    only_used = true;
+
   /* For each of the hard registers, we should zero it if:
 	    1. it is a call-used register;
 	and 2. it is not a fixed register;

gcc/opts.cc

@@ -2115,6 +2115,10 @@ const struct zero_call_used_regs_opts_s zero_call_used_regs_opts[] =
   ZERO_CALL_USED_REGS_OPT (all-gpr, zero_regs_flags::ALL_GPR),
   ZERO_CALL_USED_REGS_OPT (all-arg, zero_regs_flags::ALL_ARG),
   ZERO_CALL_USED_REGS_OPT (all, zero_regs_flags::ALL),
+  ZERO_CALL_USED_REGS_OPT (leafy-gpr-arg, zero_regs_flags::LEAFY_GPR_ARG),
+  ZERO_CALL_USED_REGS_OPT (leafy-gpr, zero_regs_flags::LEAFY_GPR),
+  ZERO_CALL_USED_REGS_OPT (leafy-arg, zero_regs_flags::LEAFY_ARG),
+  ZERO_CALL_USED_REGS_OPT (leafy, zero_regs_flags::LEAFY),
 #undef ZERO_CALL_USED_REGS_OPT
   {NULL, 0U}
 };

gcc/testsuite/c-c++-common/zero-scratch-regs-leafy-1.c

@@ -0,0 +1,15 @@
+/* { dg-do run } */
+/* { dg-options "-O2 -fzero-call-used-regs=leafy" } */
+
+volatile int result = 0;
+int 
+__attribute__((noipa))
+foo (int x)
+{
+  return x;
+}
+int main()
+{
+  result = foo (2);
+  return 0;
+}

gcc/testsuite/c-c++-common/zero-scratch-regs-leafy-2.c

@@ -0,0 +1,21 @@
+/* { dg-do compile } */
+/* { dg-options "-O2" } */
+
+#include <assert.h>
+int result = 0;
+
+int 
+__attribute__((noipa))
+__attribute__ ((zero_call_used_regs("leafy")))
+foo1 (int x)
+{
+  return (x + 1);
+}
+
+int 
+__attribute__((noipa))
+__attribute__ ((zero_call_used_regs("leafy")))
+foo2 (int x)
+{
+  return foo1 (x + 2);
+}

gcc/testsuite/gcc.target/i386/zero-scratch-regs-leafy-1.c

@@ -0,0 +1,12 @@
+/* { dg-do compile } */
+/* { dg-options "-O2 -fzero-call-used-regs=leafy -fno-stack-protector -fno-PIC" } */
+
+void
+foo (void)
+{
+}
+
+/* { dg-final { scan-assembler-not "vzeroall" } } */
+/* { dg-final { scan-assembler-not "%xmm" } } */
+/* { dg-final { scan-assembler-not "xorl\[ \t\]+%" } } */
+/* { dg-final { scan-assembler-not "movl\[ \t\]+%" } } */

gcc/testsuite/gcc.target/i386/zero-scratch-regs-leafy-2.c

@@ -0,0 +1,16 @@
+/* { dg-do compile } */
+/* { dg-options "-O2 -fzero-call-used-regs=leafy-gpr -fno-stack-protector -fno-PIC" } */
+
+extern int bar (int);
+
+void
+foo (void)
+{
+  int x = bar (0);
+  if (x)
+    bar (1);
+}
+
+/* { dg-final { scan-assembler "xorl\[ \t\]+%eax, %eax" } } */
+/* { dg-final { scan-assembler "xorl\[ \t\]+%edx, %edx" } } */
+/* { dg-final { scan-assembler "xorl\[ \t\]+%ecx, %ecx" } } */