[PATCH] Use call-clobbered register for sibcall via GOT

From: H.J. Lu  <hongjiu.lu@intel.com>

Since sibcall never returns, we can only use call-clobbered register as
GOT base.  Otherwise, callee-saved register used as GOT base won't be
properly restored.  sibcall_memory_operand is changed to allow 32-bit
GOT slot only with pseudo register as GOT base for RTL expansion.  2
new patterns, *sibcall_GOT_32 and *sibcall_value_GOT_32, are added to
expose GOT base register to register allocator so that call-clobbered
register will be used for GOT base.

gcc/

	PR target/68937
	* config/i386/i386.c (ix86_function_ok_for_sibcall): Count
	call to global function via GOT slot as indirect call.
	* config/i386/i386.md (*sibcall_GOT_32): New pattern.
	(*sibcall_value_GOT_32): Likewise.
	* config/i386/predicates.md (sibcall_memory_operand): Rewrite.
	Allow 32-bit GOT slot only with pseudo register as GOT base.
	(GOT32_symbol_operand): New predicate.

gcc/testsuite/

	PR target/68937
	* gcc.target/i386/pr68937-1.c: New test.
	* gcc.target/i386/pr68937-2.c: Likewise.
	* gcc.target/i386/pr68937-3.c: Likewise.
	* gcc.target/i386/pr68937-4.c: Likewise.
	* gcc.target/i386/pr68937-5.c: Likewise.
	* gcc.target/i386/pr68937-6.c: Likewise.

From-SVN: r231903

11 files changed, 163 insertions, 9 deletions

diff --git a/gcc/ChangeLog b/gcc/ChangeLog
index 134e4fb..0cf2dc4 100644
--- a/gcc/ChangeLog
+++ b/gcc/ChangeLog
@@ -1,3 +1,14 @@
+2015-12-22  H.J. Lu  <hongjiu.lu@intel.com>
+
+	PR target/68937
+	* config/i386/i386.c (ix86_function_ok_for_sibcall): Count
+	call to global function via GOT slot as indirect call.
+	* config/i386/i386.md (*sibcall_GOT_32): New pattern.
+	(*sibcall_value_GOT_32): Likewise.
+	* config/i386/predicates.md (sibcall_memory_operand): Rewrite.
+	Allow 32-bit GOT slot only with pseudo register as GOT base.
+	(GOT32_symbol_operand): New predicate.
+
 2015-12-22  Sujoy Saraswati  <sujoy.saraswati@hpe.com>
 
 	* fold-const.c (const_binop): Convert sNaN to qNaN when
diff --git a/gcc/config/i386/i386.c b/gcc/config/i386/i386.c
index cecea24..f5d23d9 100644
--- a/gcc/config/i386/i386.c
+++ b/gcc/config/i386/i386.c
@@ -6657,6 +6657,7 @@ ix86_function_ok_for_sibcall (tree decl, tree exp)
 {
   tree type, decl_or_type;
   rtx a, b;
+  bool bind_global = decl && !targetm.binds_local_p (decl);
 
   /* If we are generating position-independent code, we cannot sibcall
      optimize direct calls to global functions, as the PLT requires
@@ -6665,7 +6666,7 @@ ix86_function_ok_for_sibcall (tree decl, tree exp)
       && !TARGET_64BIT
       && flag_pic
       && flag_plt
-      && decl && !targetm.binds_local_p (decl))
+      && bind_global)
     return false;
 
   /* If we need to align the outgoing stack, then sibcalling would
@@ -6723,8 +6724,10 @@ ix86_function_ok_for_sibcall (tree decl, tree exp)
       /* If this call is indirect, we'll need to be able to use a
 	 call-clobbered register for the address of the target function.
 	 Make sure that all such registers are not used for passing
-	 parameters.  Note that DLLIMPORT functions are indirect.  */
+	 parameters.  Note that DLLIMPORT functions and call to global
+	 function via GOT slot are indirect.  */
       if (!decl
+	  || (bind_global && flag_pic && !flag_plt)
 	  || (TARGET_DLLIMPORT_DECL_ATTRIBUTES && DECL_DLLIMPORT_P (decl)))
 	{
 	  /* Check if regparm >= 3 since arg_reg_available is set to
diff --git a/gcc/config/i386/i386.md b/gcc/config/i386/i386.md
index e8178f3..5e5c97b 100644
--- a/gcc/config/i386/i386.md
+++ b/gcc/config/i386/i386.md
@@ -11865,6 +11865,22 @@
   "* return ix86_output_call_insn (insn, operands[0]);"
   [(set_attr "type" "call")])
 
+;; Since sibcall never returns, we can only use call-clobbered register
+;; as GOT base.
+(define_insn "*sibcall_GOT_32"
+  [(call (mem:QI
+	   (mem:SI (plus:SI
+		     (match_operand:SI 0 "register_no_elim_operand" "U")
+		     (match_operand:SI 1 "GOT32_symbol_operand"))))
+	 (match_operand 2))]
+  "!TARGET_MACHO && !TARGET_64BIT && SIBLING_CALL_P (insn)"
+{
+  rtx fnaddr = gen_rtx_PLUS (Pmode, operands[0], operands[1]);
+  fnaddr = gen_const_mem (Pmode, fnaddr);
+  return ix86_output_call_insn (insn, fnaddr);
+}
+  [(set_attr "type" "call")])
+
 (define_insn "*sibcall"
   [(call (mem:QI (match_operand:W 0 "sibcall_insn_operand" "UBsBz"))
 	 (match_operand 1))]
@@ -12042,6 +12058,23 @@
   "* return ix86_output_call_insn (insn, operands[1]);"
   [(set_attr "type" "callv")])
 
+;; Since sibcall never returns, we can only use call-clobbered register
+;; as GOT base.
+(define_insn "*sibcall_value_GOT_32"
+  [(set (match_operand 0)
+        (call (mem:QI
+		(mem:SI (plus:SI
+			  (match_operand:SI 1 "register_no_elim_operand" "U")
+			  (match_operand:SI 2 "GOT32_symbol_operand"))))
+	 (match_operand 3)))]
+  "!TARGET_MACHO && !TARGET_64BIT && SIBLING_CALL_P (insn)"
+{
+  rtx fnaddr = gen_rtx_PLUS (Pmode, operands[1], operands[2]);
+  fnaddr = gen_const_mem (Pmode, fnaddr);
+  return ix86_output_call_insn (insn, fnaddr);
+}
+  [(set_attr "type" "callv")])
+
 (define_insn "*sibcall_value"
   [(set (match_operand 0)
 	(call (mem:QI (match_operand:W 1 "sibcall_insn_operand" "UBsBz"))
diff --git a/gcc/config/i386/predicates.md b/gcc/config/i386/predicates.md
index 8bdd5d8..96d946c 100644
--- a/gcc/config/i386/predicates.md
+++ b/gcc/config/i386/predicates.md
@@ -597,14 +597,28 @@
 	    (match_operand 0 "memory_operand"))))
 
 ;; Return true if OP is a memory operands that can be used in sibcalls.
+;; Since sibcall never returns, we can only use call-clobbered register
+;; as GOT base.  Allow GOT slot here only with pseudo register as GOT
+;; base.  Properly handle sibcall over GOT slot with *sibcall_GOT_32
+;; and *sibcall_value_GOT_32 patterns.
 (define_predicate "sibcall_memory_operand"
-  (and (match_operand 0 "memory_operand")
-       (match_test "CONSTANT_P (XEXP (op, 0))
-		    || (GET_CODE (XEXP (op, 0)) == PLUS
-			&& REG_P (XEXP (XEXP (op, 0), 0))
-			&& GET_CODE (XEXP (XEXP (op, 0), 1)) == CONST
-			&& GET_CODE (XEXP (XEXP (XEXP (op, 0), 1), 0)) == UNSPEC
-			&& XINT (XEXP (XEXP (XEXP (op, 0), 1), 0), 1) == UNSPEC_GOT)")))
+  (match_operand 0 "memory_operand")
+{
+  op = XEXP (op, 0);
+  if (CONSTANT_P (op))
+    return true;
+  if (GET_CODE (op) == PLUS && REG_P (XEXP (op, 0)))
+    {
+      int regno = REGNO (XEXP (op, 0));
+      if (!HARD_REGISTER_NUM_P (regno) || call_used_regs[regno])
+	{
+	  op = XEXP (op, 1);
+	  if (GOT32_symbol_operand (op, VOIDmode))
+	    return true;
+	}
+    }
+  return false;
+})
 
 ;; Test for a valid operand for a call instruction.
 ;; Allow constant call address operands in Pmode only.
@@ -633,6 +647,12 @@
 	  && XINT (XEXP (op, 0), 1) == UNSPEC_GOTPCREL);
 })
 
+;; Return true if OP is a 32-bit GOT symbol operand.
+(define_predicate "GOT32_symbol_operand"
+  (match_test "GET_CODE (op) == CONST
+               && GET_CODE (XEXP (op, 0)) == UNSPEC
+               && XINT (XEXP (op, 0), 1) == UNSPEC_GOT"))
+
 ;; Match exactly zero.
 (define_predicate "const0_operand"
   (match_code "const_int,const_wide_int,const_double,const_vector")
diff --git a/gcc/testsuite/ChangeLog b/gcc/testsuite/ChangeLog
index 50733e6..b43cfee 100644
--- a/gcc/testsuite/ChangeLog
+++ b/gcc/testsuite/ChangeLog
@@ -1,3 +1,13 @@
+2015-12-22  H.J. Lu  <hongjiu.lu@intel.com>
+
+	PR target/68937
+	* gcc.target/i386/pr68937-1.c: New test.
+	* gcc.target/i386/pr68937-2.c: Likewise.
+	* gcc.target/i386/pr68937-3.c: Likewise.
+	* gcc.target/i386/pr68937-4.c: Likewise.
+	* gcc.target/i386/pr68937-5.c: Likewise.
+	* gcc.target/i386/pr68937-6.c: Likewise.
+
 2015-12-22  Marek Polacek  <polacek@redhat.com>
 
 	PR c/69002
diff --git a/gcc/testsuite/gcc.target/i386/pr68937-1.c b/gcc/testsuite/gcc.target/i386/pr68937-1.c
new file mode 100644
index 0000000..897856b
--- /dev/null
+++ b/gcc/testsuite/gcc.target/i386/pr68937-1.c
@@ -0,0 +1,13 @@
+/* { dg-do compile { target { *-*-linux* && ia32 } } } */
+/* { dg-options "-O2 -fpic -fno-plt -mregparm=3" } */
+
+extern void bar (int);
+
+void
+foo (int b)
+{
+  bar (b);
+  bar (b);
+}
+
+/* { dg-final { scan-assembler "jmp\[ \t\]*.bar@GOT\\(%e(a|c|d)x\\)" } } */
diff --git a/gcc/testsuite/gcc.target/i386/pr68937-2.c b/gcc/testsuite/gcc.target/i386/pr68937-2.c
new file mode 100644
index 0000000..257f4e2
--- /dev/null
+++ b/gcc/testsuite/gcc.target/i386/pr68937-2.c
@@ -0,0 +1,13 @@
+/* { dg-do compile { target { *-*-linux* && ia32 } } } */
+/* { dg-options "-O2 -fpic -fno-plt -mregparm=3" } */
+
+extern void bar (int, int);
+
+void
+foo (int a, int b)
+{
+  bar (a, b);
+  bar (a, b);
+}
+
+/* { dg-final { scan-assembler "jmp\[ \t\]*.bar@GOT\\(%e(a|c|d)x\\)" } } */
diff --git a/gcc/testsuite/gcc.target/i386/pr68937-3.c b/gcc/testsuite/gcc.target/i386/pr68937-3.c
new file mode 100644
index 0000000..6d8e40f
--- /dev/null
+++ b/gcc/testsuite/gcc.target/i386/pr68937-3.c
@@ -0,0 +1,13 @@
+/* { dg-do compile { target { *-*-linux* && ia32 } } } */
+/* { dg-options "-O2 -fpic -fno-plt -mregparm=3" } */
+
+extern void bar (int, int, int);
+
+void
+foo (int a, int b, int c)
+{
+  bar (a, b, c);
+  bar (a, b, c);
+}
+
+/* { dg-final { scan-assembler-not "jmp\[ \t\]*.bar@GOT" } } */
diff --git a/gcc/testsuite/gcc.target/i386/pr68937-4.c b/gcc/testsuite/gcc.target/i386/pr68937-4.c
new file mode 100644
index 0000000..9c19956
--- /dev/null
+++ b/gcc/testsuite/gcc.target/i386/pr68937-4.c
@@ -0,0 +1,13 @@
+/* { dg-do compile { target { *-*-linux* && ia32 } } } */
+/* { dg-options "-O2 -fpic -fno-plt -mregparm=3" } */
+
+extern int bar (int, int);
+
+int
+foo (int a, int b)
+{
+  (void) bar (a, b);
+  return bar (a, b);
+}
+
+/* { dg-final { scan-assembler "jmp\[ \t\]*.bar@GOT\\(%e(a|c|d)x\\)" } } */
diff --git a/gcc/testsuite/gcc.target/i386/pr68937-5.c b/gcc/testsuite/gcc.target/i386/pr68937-5.c
new file mode 100644
index 0000000..f7e3ec5
--- /dev/null
+++ b/gcc/testsuite/gcc.target/i386/pr68937-5.c
@@ -0,0 +1,9 @@
+/* { dg-do compile { target { *-*-linux* } } } */
+/* { dg-options "-O2 -fpic -fno-plt -funroll-loops" } */
+
+extern void *f();
+void dmi_scan_machine(void) {
+  char *p = f(), *q;
+  for (q = p; q < p + 10; q++)
+    ;
+}
diff --git a/gcc/testsuite/gcc.target/i386/pr68937-6.c b/gcc/testsuite/gcc.target/i386/pr68937-6.c
new file mode 100644
index 0000000..406ce28
--- /dev/null
+++ b/gcc/testsuite/gcc.target/i386/pr68937-6.c
@@ -0,0 +1,16 @@
+/* { dg-do compile { target { *-*-linux* && ia32 } } } */
+/* { dg-options "-O2 -fpic -fno-plt -mregparm=3" } */
+
+extern void foo (int, int, int);
+extern void bar (int, int, int) __attribute__((visibility("hidden")));
+
+void
+foo (int a, int b, int c)
+{
+  foo (a, b, c);
+  bar (a, b, c);
+  foo (a, b, c);
+  bar (a, b, c);
+}
+
+/* { dg-final { scan-assembler "jmp\[ \t\]bar" } } */