[PATCH] Load external function address via GOT slot

["H.J. Lu" <hjl dot tools at gmail dot com>]

For -fno-plt, we load the external function address via the GOT slot
so that linker won't create an PLT entry for extern function address.

Tested on x86-64. I also built GCC with -fno-plt.  It removes 99% PLT
entries.  OK for trunk?

H.J.
--
gcc/

	PR target/pr67400
	* config/i386/i386-protos.h (ix86_force_load_from_GOT_p): New.
	* config/i386/i386.c (ix86_force_load_from_GOT_p): New function.
	(ix86_legitimate_address_p): Allow UNSPEC_GOTPCREL for
	ix86_force_load_from_GOT_p returns true.
	(ix86_print_operand_address): Support UNSPEC_GOTPCREL if
	ix86_force_load_from_GOT_p returns true.
	(ix86_expand_move): Load the external function address via the
	GOT slot if ix86_force_load_from_GOT_p returns true.
	* config/i386/predicates.md (x86_64_immediate_operand): Return
	false if ix86_force_load_from_GOT_p returns true.

gcc/testsuite/

	PR target/pr67400
	* gcc.target/i386/pr67400-1.c: New test.
	* gcc.target/i386/pr67400-2.c: Likewise.
	* gcc.target/i386/pr67400-3.c: Likewise.
	* gcc.target/i386/pr67400-4.c: Likewise.
---
 gcc/config/i386/i386-protos.h             |  1 +
 gcc/config/i386/i386.c                    | 42 +++++++++++++++++++++++++++++++
 gcc/config/i386/predicates.md             |  4 +++
 gcc/testsuite/gcc.target/i386/pr67400-1.c | 13 ++++++++++
 gcc/testsuite/gcc.target/i386/pr67400-2.c | 14 +++++++++++
 gcc/testsuite/gcc.target/i386/pr67400-3.c | 16 ++++++++++++
 gcc/testsuite/gcc.target/i386/pr67400-4.c | 13 ++++++++++
 7 files changed, 103 insertions(+)
 create mode 100644 gcc/testsuite/gcc.target/i386/pr67400-1.c
 create mode 100644 gcc/testsuite/gcc.target/i386/pr67400-2.c
 create mode 100644 gcc/testsuite/gcc.target/i386/pr67400-3.c
 create mode 100644 gcc/testsuite/gcc.target/i386/pr67400-4.c

diff --git a/gcc/config/i386/i386-protos.h b/gcc/config/i386/i386-protos.h
index ff47bc1..42c941d 100644
--- a/gcc/config/i386/i386-protos.h
+++ b/gcc/config/i386/i386-protos.h
@@ -69,6 +69,7 @@ extern bool ix86_expand_set_or_movmem (rtx, rtx, rtx, rtx, rtx, rtx,
 extern bool constant_address_p (rtx);
 extern bool legitimate_pic_operand_p (rtx);
 extern bool legitimate_pic_address_disp_p (rtx);
+extern bool ix86_force_load_from_GOT_p (rtx);
 extern void print_reg (rtx, int, FILE*);
 extern void ix86_print_operand (FILE *, rtx, int);
 
diff --git a/gcc/config/i386/i386.c b/gcc/config/i386/i386.c
index 6379313..499dc77 100644
--- a/gcc/config/i386/i386.c
+++ b/gcc/config/i386/i386.c
@@ -14443,6 +14443,24 @@ ix86_legitimate_constant_p (machine_mode, rtx x)
   return true;
 }
 
+/* True if operand X should be loaded from GOT.  */
+
+bool
+ix86_force_load_from_GOT_p (rtx x)
+{
+  /* External function symbol should be loaded via the GOT slot for
+     -fno-plt.  */
+  return (!flag_plt
+	  && !flag_pic
+	  && ix86_cmodel != CM_LARGE
+	  && TARGET_64BIT
+	  && !TARGET_PECOFF
+	  && !TARGET_MACHO
+	  && GET_CODE (x) == SYMBOL_REF
+	  && SYMBOL_REF_FUNCTION_P (x)
+	  && !SYMBOL_REF_LOCAL_P (x));
+}
+
 /* Determine if it's legal to put X into the constant pool.  This
    is not possible for the address of thread-local symbols, which
    is checked above.  */
@@ -14823,6 +14841,10 @@ ix86_legitimate_address_p (machine_mode, rtx addr, bool strict)
 	    return false;
 
 	  case UNSPEC_GOTPCREL:
+	    gcc_assert (flag_pic
+			|| ix86_force_load_from_GOT_p (XVECEXP (XEXP (disp, 0), 0, 0)));
+	    goto is_legitimate_pic;
+
 	  case UNSPEC_PCREL:
 	    gcc_assert (flag_pic);
 	    goto is_legitimate_pic;
@@ -17427,6 +17449,11 @@ ix86_print_operand_address_as (FILE *file, rtx addr,
 	}
       else if (flag_pic)
 	output_pic_addr_const (file, disp, 0);
+      else if (GET_CODE (disp) == CONST
+	       && GET_CODE (XEXP (disp, 0)) == UNSPEC
+	       && XINT (XEXP (disp, 0), 1) == UNSPEC_GOTPCREL
+	       && ix86_force_load_from_GOT_p (XVECEXP (XEXP (disp, 0), 0, 0)))
+	output_pic_addr_const (file, XEXP (disp, 0), code);
       else
 	output_addr_const (file, disp);
     }
@@ -18692,6 +18719,21 @@ ix86_expand_move (machine_mode mode, rtx operands[])
 	      op1 = convert_to_mode (mode, op1, 1);
 	    }
 	}
+   }
+  else if (ix86_force_load_from_GOT_p (op1))
+    {
+      /* Load the external function address via the GOT slot to
+	 avoid PLT.  */
+      op1 = gen_rtx_UNSPEC (Pmode, gen_rtvec (1, op1),
+			    (TARGET_64BIT
+			     ? UNSPEC_GOTPCREL
+			     : UNSPEC_GOT));
+      op1 = gen_rtx_CONST (Pmode, op1);
+      op1 = gen_const_mem (Pmode, op1);
+      op1 = convert_to_mode (mode, op1, 1);
+      /* Force OP1 into register to prevent cse and fwprop from
+	 replacing a GOT load with a constant.  */
+      op1 = force_reg (mode, op1);
     }
   else
     {
diff --git a/gcc/config/i386/predicates.md b/gcc/config/i386/predicates.md
index 14e80d9..8c2e738 100644
--- a/gcc/config/i386/predicates.md
+++ b/gcc/config/i386/predicates.md
@@ -159,6 +159,10 @@
       /* TLS symbols are not constant.  */
       if (SYMBOL_REF_TLS_MODEL (op))
 	return false;
+      /* Load the external function address via the GOT slot to avoid
+	 PLT.  */
+      if (ix86_force_load_from_GOT_p (op))
+	return false;
       return (ix86_cmodel == CM_SMALL || ix86_cmodel == CM_KERNEL
 	      || (ix86_cmodel == CM_MEDIUM && !SYMBOL_REF_FAR_ADDR_P (op)));
 
diff --git a/gcc/testsuite/gcc.target/i386/pr67400-1.c b/gcc/testsuite/gcc.target/i386/pr67400-1.c
new file mode 100644
index 0000000..a875b76
--- /dev/null
+++ b/gcc/testsuite/gcc.target/i386/pr67400-1.c
@@ -0,0 +1,13 @@
+/* { dg-do compile { target *-*-linux* } } */
+/* { dg-options "-O2 -fno-pic -fno-plt" } */
+
+extern void bar (void);
+
+void *
+foo (void)
+{
+  return &bar;
+}
+
+/* { dg-final { scan-assembler "mov\(l|q\)\[ \t\]*bar@GOTPCREL" { target { ! ia32 } } } } */
+/* { dg-final { scan-assembler-not "mov\(l|q\)\[ \t\]*\\\$bar," { target { ! ia32 } } } } */
diff --git a/gcc/testsuite/gcc.target/i386/pr67400-2.c b/gcc/testsuite/gcc.target/i386/pr67400-2.c
new file mode 100644
index 0000000..9f3f4bc
--- /dev/null
+++ b/gcc/testsuite/gcc.target/i386/pr67400-2.c
@@ -0,0 +1,14 @@
+/* { dg-do compile { target *-*-linux* } } */
+/* { dg-options "-O2 -fno-pic -fno-plt" } */
+
+extern void bar (void);
+extern void *p;
+
+void
+foo (void)
+{
+  p = &bar;
+}
+
+/* { dg-final { scan-assembler "mov\(l|q\)\[ \t\]*bar@GOTPCREL" { target { ! ia32 } } } } */
+/* { dg-final { scan-assembler-not "mov\(l|q\)\[ \t\]*\\\$bar," { target { ! ia32 } } } } */
diff --git a/gcc/testsuite/gcc.target/i386/pr67400-3.c b/gcc/testsuite/gcc.target/i386/pr67400-3.c
new file mode 100644
index 0000000..045974e
--- /dev/null
+++ b/gcc/testsuite/gcc.target/i386/pr67400-3.c
@@ -0,0 +1,16 @@
+/* { dg-do compile { target *-*-linux* } } */
+/* { dg-options "-O2 -fno-pic -fno-plt" } */
+
+static void
+bar (void)
+{
+}
+
+void *
+foo (void)
+{
+  return &bar;
+}
+
+/* { dg-final { scan-assembler "mov\(l|q\)\[ \t\]*\\\$bar," } } */
+/* { dg-final { scan-assembler-not "mov\(l|q\)\[ \t\]*bar@GOTPCREL" { target { ! ia32 } } } } */
diff --git a/gcc/testsuite/gcc.target/i386/pr67400-4.c b/gcc/testsuite/gcc.target/i386/pr67400-4.c
new file mode 100644
index 0000000..fd373db
--- /dev/null
+++ b/gcc/testsuite/gcc.target/i386/pr67400-4.c
@@ -0,0 +1,13 @@
+/* { dg-do compile { target *-*-linux* } } */
+/* { dg-options "-O2 -fno-pic -fno-plt" } */
+
+extern void bar (void) __attribute__ ((visibility ("hidden")));
+
+void *
+foo (void)
+{
+  return &bar;
+}
+
+/* { dg-final { scan-assembler "mov\(l|q\)\[ \t\]*\\\$bar," } } */
+/* { dg-final { scan-assembler-not "mov\(l|q\)\[ \t\]*bar@GOTPCREL" { target { ! ia32 } } } } */
-- 
2.5.5