Re: RFC: [PATCH] PR target/67215: -fno-plt needs improvements for x86

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

On Mon, Aug 17, 2015 at 10:08 AM, Alexander Monakov <amonakov@ispras.ru> wrote:
>> >> Perhaps add a comment that GOT slots are 64-bit on x32?
>> >>
>> >
>> > Good idea.  I will update my patch.
>> >
>>
>> How about this?
>>
>>
>> diff --git a/gcc/config/i386/i386.c b/gcc/config/i386/i386.c
>> index bf8a21d..216dee6 100644
>> --- a/gcc/config/i386/i386.c
>> +++ b/gcc/config/i386/i386.c
>> @@ -25690,6 +25690,10 @@ ix86_expand_call (rtx retval, rtx fnaddr, rtx callarg1,
>>   fnaddr);
>>   }
>>        fnaddr = gen_const_mem (Pmode, fnaddr);
>> +      /* Pmode may not be the same as word_mode for x32, which
>
> I think 'Pmode is not the same as word_mode on x32' is more appropriate here.

"-maddress-mode=long -mx32" makes Pmode == word_mode.

>> + doesn't support indirect branch va 32-bit memory slot.
>
> Typo: s/va/via.
>

Fixed.

Here is the updated patch.

Thanks.

-- 
H.J.

From 04258b418d2ea105249d371a06805122d8953816 Mon Sep 17 00:00:00 2001
From: "H.J. Lu" <hjl.tools@gmail.com>
Date: Sun, 16 Aug 2015 04:46:20 -0700
Subject: [PATCH] Properly handle -fno-plt in ix86_expand_call

prepare_call_address in calls.c is the wrong place to handle -fno-plt.
We shoudn't force function address into register and hope that load
function address via GOT and indirect call via register will be folded
into indirect call via GOT, which doesn't always happen.  Also non-PIC
case can only be handled in backend.  Instead, backend should expand
external function call into indirect call via GOT for -fno-plt.

This patch reverts -fno-plt in prepare_call_address and handles it in
ix86_expand_call.  Other backends may need similar changes to support
-fno-plt.  Alternately, we can introduce a target hook to indicate
whether an external function should be called via register for -fno-plt
so that i386 backend can disable it in prepare_call_address.

gcc/

	PR target/67215
	* calls.c (prepare_call_address): Don't handle -fno-plt here.
	* config/i386/i386.c (ix86_expand_call): Generate indirect call
	via GOT for -fno-plt.  Support indirect call via GOT for x32.

gcc/testsuite/

	PR target/67215
	* gcc.target/i386/pr67215-1.c: New test.
	* gcc.target/i386/pr67215-2.c: Likewise.
---
 gcc/calls.c                               | 12 ------
 gcc/config/i386/i386.c                    | 71 ++++++++++++++++++++++++-------
 gcc/testsuite/gcc.target/i386/pr67215-1.c | 20 +++++++++
 gcc/testsuite/gcc.target/i386/pr67215-2.c | 20 +++++++++
 4 files changed, 95 insertions(+), 28 deletions(-)
 create mode 100644 gcc/testsuite/gcc.target/i386/pr67215-1.c
 create mode 100644 gcc/testsuite/gcc.target/i386/pr67215-2.c

diff --git a/gcc/calls.c b/gcc/calls.c
index 5636725..7cce9be 100644
--- a/gcc/calls.c
+++ b/gcc/calls.c
@@ -203,18 +203,6 @@ prepare_call_address (tree fndecl_or_type, rtx funexp, rtx static_chain_value,
 	       && targetm.small_register_classes_for_mode_p (FUNCTION_MODE))
 	      ? force_not_mem (memory_address (FUNCTION_MODE, funexp))
 	      : memory_address (FUNCTION_MODE, funexp));
-  else if (flag_pic
-	   && fndecl_or_type
-	   && TREE_CODE (fndecl_or_type) == FUNCTION_DECL
-	   && (!flag_plt
-	       || lookup_attribute ("noplt", DECL_ATTRIBUTES (fndecl_or_type)))
-	   && !targetm.binds_local_p (fndecl_or_type))
-    {
-      /* This is done only for PIC code.  There is no easy interface to force the
-	 function address into GOT for non-PIC case.  non-PIC case needs to be
-	 handled specially by the backend.  */
-      funexp = force_reg (Pmode, funexp);
-    }
   else if (! sibcallp)
     {
       if (!NO_FUNCTION_CSE && optimize && ! flag_no_function_cse)
diff --git a/gcc/config/i386/i386.c b/gcc/config/i386/i386.c
index 05fa5e1..ac9a6c4 100644
--- a/gcc/config/i386/i386.c
+++ b/gcc/config/i386/i386.c
@@ -25649,21 +25649,54 @@ ix86_expand_call (rtx retval, rtx fnaddr, rtx callarg1,
       /* Static functions and indirect calls don't need the pic register.  Also,
 	 check if PLT was explicitly avoided via no-plt or "noplt" attribute, making
 	 it an indirect call.  */
+      rtx addr = XEXP (fnaddr, 0);
       if (flag_pic
-	  && (!TARGET_64BIT
-	      || (ix86_cmodel == CM_LARGE_PIC
-		  && DEFAULT_ABI != MS_ABI))
-	  && GET_CODE (XEXP (fnaddr, 0)) == SYMBOL_REF
-	  && !SYMBOL_REF_LOCAL_P (XEXP (fnaddr, 0))
-	  && flag_plt
-	  && (SYMBOL_REF_DECL ((XEXP (fnaddr, 0))) == NULL_TREE
-	      || !lookup_attribute ("noplt",
-		     DECL_ATTRIBUTES (SYMBOL_REF_DECL (XEXP (fnaddr, 0))))))
+	  && GET_CODE (addr) == SYMBOL_REF
+	  && !SYMBOL_REF_LOCAL_P (addr))
 	{
-	  use_reg (&use, gen_rtx_REG (Pmode, REAL_PIC_OFFSET_TABLE_REGNUM));
-	  if (ix86_use_pseudo_pic_reg ())
-	    emit_move_insn (gen_rtx_REG (Pmode, REAL_PIC_OFFSET_TABLE_REGNUM),
-			    pic_offset_table_rtx);
+	  if (flag_plt
+	      && (SYMBOL_REF_DECL (addr) == NULL_TREE
+		  || !lookup_attribute ("noplt",
+					DECL_ATTRIBUTES (SYMBOL_REF_DECL (addr)))))
+	    {
+	      if (!TARGET_64BIT
+		  || (ix86_cmodel == CM_LARGE_PIC
+		      && DEFAULT_ABI != MS_ABI))
+		{
+		  use_reg (&use, gen_rtx_REG (Pmode,
+					      REAL_PIC_OFFSET_TABLE_REGNUM));
+		  if (ix86_use_pseudo_pic_reg ())
+		    emit_move_insn (gen_rtx_REG (Pmode,
+						 REAL_PIC_OFFSET_TABLE_REGNUM),
+				    pic_offset_table_rtx);
+		}
+	    }
+	  else if (!TARGET_PECOFF && !TARGET_MACHO)
+	    {
+	      if (TARGET_64BIT)
+		{
+		  fnaddr = gen_rtx_UNSPEC (Pmode,
+					   gen_rtvec (1, addr),
+					   UNSPEC_GOTPCREL);
+		  fnaddr = gen_rtx_CONST (Pmode, fnaddr);
+		}
+	      else
+		{
+		  fnaddr = gen_rtx_UNSPEC (Pmode, gen_rtvec (1, addr),
+					   UNSPEC_GOT);
+		  fnaddr = gen_rtx_CONST (Pmode, fnaddr);
+		  fnaddr = gen_rtx_PLUS (Pmode, pic_offset_table_rtx,
+					 fnaddr);
+		}
+	      fnaddr = gen_const_mem (Pmode, fnaddr);
+	      /* Pmode may not be the same as word_mode for x32, which
+		 doesn't support indirect branch via 32-bit memory slot.
+		 Since x32 GOT slot is 64 bit with zero upper 32 bits,
+		 indirect branch via x32 GOT slot is OK.  */
+	      if (GET_MODE (fnaddr) != word_mode)
+		fnaddr = gen_rtx_ZERO_EXTEND (word_mode, fnaddr);
+	      fnaddr = gen_rtx_MEM (QImode, fnaddr);
+	    }
 	}
     }
 
@@ -25685,9 +25718,15 @@ ix86_expand_call (rtx retval, rtx fnaddr, rtx callarg1,
       && GET_CODE (XEXP (fnaddr, 0)) == SYMBOL_REF
       && !local_symbolic_operand (XEXP (fnaddr, 0), VOIDmode))
     fnaddr = gen_rtx_MEM (QImode, construct_plt_address (XEXP (fnaddr, 0)));
-  else if (sibcall
-	   ? !sibcall_insn_operand (XEXP (fnaddr, 0), word_mode)
-	   : !call_insn_operand (XEXP (fnaddr, 0), word_mode))
+  /* Since x32 GOT slot is 64 bit with zero upper 32 bits, indirect
+     branch via x32 GOT slot is OK.  */
+  else if (!(TARGET_X32
+	     && MEM_P (fnaddr)
+	     && GET_CODE (XEXP (fnaddr, 0)) == ZERO_EXTEND
+	     && GOT_memory_operand (XEXP (XEXP (fnaddr, 0), 0), Pmode))
+	   && (sibcall
+	       ? !sibcall_insn_operand (XEXP (fnaddr, 0), word_mode)
+	       : !call_insn_operand (XEXP (fnaddr, 0), word_mode)))
     {
       fnaddr = convert_to_mode (word_mode, XEXP (fnaddr, 0), 1);
       fnaddr = gen_rtx_MEM (QImode, copy_to_mode_reg (word_mode, fnaddr));
diff --git a/gcc/testsuite/gcc.target/i386/pr67215-1.c b/gcc/testsuite/gcc.target/i386/pr67215-1.c
new file mode 100644
index 0000000..fd37f8e
--- /dev/null
+++ b/gcc/testsuite/gcc.target/i386/pr67215-1.c
@@ -0,0 +1,20 @@
+/* { dg-do compile { target *-*-linux* } } */
+/* { dg-options "-O2 -fpic -fno-plt" } */
+
+extern char* bar (int);
+extern char* arr[32];
+
+void
+foo (void)
+{
+  int i;
+
+  for (i = 0; i < 32; i++)
+    arr[i] = bar (128);
+}
+
+/* { dg-final { scan-assembler "call\[ \t\]*.bar@GOTPCREL" { target { ! ia32 } } } } */
+/* { dg-final { scan-assembler "call\[ \t\]*.bar@GOT\\(" { target ia32 } } } */
+/* { dg-final { scan-assembler-not "mov(l|q)\[ \t\]*.bar@GOTPCREL" { target { ! ia32 } } } } */
+/* { dg-final { scan-assembler-not "movl\[ \t\]*.bar@GOT\\(" { target ia32 } } } */
+/* { dg-final { scan-assembler-not "call\[ \t\]*.bar@PLT" } } */
diff --git a/gcc/testsuite/gcc.target/i386/pr67215-2.c b/gcc/testsuite/gcc.target/i386/pr67215-2.c
new file mode 100644
index 0000000..ebf2919
--- /dev/null
+++ b/gcc/testsuite/gcc.target/i386/pr67215-2.c
@@ -0,0 +1,20 @@
+/* { dg-do compile { target *-*-linux* } } */
+/* { dg-options "-O2 -fpic" } */
+
+extern char* bar (int) __attribute__ ((noplt));
+extern char* arr[32];
+
+void
+foo (void)
+{
+  int i;
+
+  for (i = 0; i < 32; i++)
+    arr[i] = bar (128);
+}
+
+/* { dg-final { scan-assembler "call\[ \t\]*.bar@GOTPCREL" { target { ! ia32 } } } } */
+/* { dg-final { scan-assembler "call\[ \t\]*.bar@GOT\\(" { target ia32 } } } */
+/* { dg-final { scan-assembler-not "mov(l|q)\[ \t\]*.bar@GOTPCREL" { target { ! ia32 } } } } */
+/* { dg-final { scan-assembler-not "movl\[ \t\]*.bar@GOT\\(" { target ia32 } } } */
+/* { dg-final { scan-assembler-not "call\[ \t\]*.bar@PLT" } } */
-- 
2.4.3