Re: [PATCH, PR58066] preferred_stack_boundary update for tls expanded call

[Wei Mi <wmi at google dot com>]

pr58066-2.patch worked for pr58066.c on ia32/x32/x86_64, but it failed
on bootstrap.

/usr/local/google/home/wmi/workarea/gcc-r208410-2/build/./gcc/xgcc
-B/usr/local/google/home/wmi/workarea/gcc-r208410-2/build/./gcc/
-B/usr/local/google/home/wmi/workarea/gcc-r208410-2/build/install/x86_64-unknown-linux-gnu/bin/
-B/usr/local/google/home/wmi/workarea/gcc-r208410-2/build/install/x86_64-unknown-linux-gnu/lib/
-isystem /usr/local/google/home/wmi/workarea/gcc-r208410-2/build/install/x86_64-unknown-linux-gnu/include
-isystem /usr/local/google/home/wmi/workarea/gcc-r208410-2/build/install/x86_64-unknown-linux-gnu/sys-include
   -g -O2 -m64 -O2  -g -O2 -DIN_GCC    -W -Wall -Wwrite-strings
-Wcast-qual -Wno-format -Wstrict-prototypes -Wmissing-prototypes
-Wold-style-definition  -isystem ./include   -fpic -mlong-double-80 -g
-DIN_LIBGCC2 -fbuilding-libgcc -fno-stack-protector   -fpic
-mlong-double-80 -I. -I. -I../../.././gcc -I../../../../src/libgcc
-I../../../../src/libgcc/. -I../../../../src/libgcc/../gcc
-I../../../../src/libgcc/../include
-I../../../../src/libgcc/config/libbid -DENABLE_DECIMAL_BID_FORMAT
-DHAVE_CC_TLS  -DUSE_TLS -o bid_decimal_globals.o -MT
bid_decimal_globals.o -MD -MP -MF bid_decimal_globals.dep -c
../../../../src/libgcc/config/libbid/bid_decimal_globals.c

(call_insn 5 2 6 2 (parallel [
            (set (reg/f:SI 85)
                (call:SI (mem:QI (symbol_ref:SI ("___tls_get_addr")) [0  S1 A8])
                    (const_int 0 [0])))
            (unspec:SI [
                    (reg:SI 3 bx)
                    (symbol_ref:SI ("__bid_IDEC_glbflags") [flags
0x10]  <var_decl 0x7ffff61c1da8 __bid_IDEC_glbflags>)
                ] UNSPEC_TLS_GD)
            (clobber (reg:SI 91))
            (clobber (reg:SI 92))
            (clobber (reg:CC 17 flags))
        ]) ../../../../src/libgcc/config/libbid/bid_decimal_globals.c:51
772 {*tls_global_dynamic_32_gnu}
     (expr_list:REG_UNUSED (reg:SI 92)
        (expr_list:REG_UNUSED (reg:SI 91)
            (nil)))
    (nil))
../../../../src/libgcc/config/libbid/bid_decimal_globals.c:52:1:
internal compiler error: in curr_insn_transform, at
lra-constraints.c:3262
0xad8453 _fatal_insn(char const*, rtx_def const*, char const*, int, char const*)
../../src/gcc/rtl-error.c:109
0x9d1221 curr_insn_transform
../../src/gcc/lra-constraints.c:3262
0x9d40e4 lra_constraints(bool)
../../src/gcc/lra-constraints.c:4157
0x9c0ad8 lra(_IO_FILE*)
../../src/gcc/lra.c:2340
0x96e310 do_reload
../../src/gcc/ira.c:5457
0x96e622 rest_of_handle_reload
../../src/gcc/ira.c:5598
0x96e66c execute
../../src/gcc/ira.c:5627

The problem is the return value of the call may be assigned to a
different hardreg than AX_REG. But LRA cannot do reload for output
operand of call. The fix is to change the above pattern to the
following pattern in legitimize_tls_address() in config/i386/i386.c.

(call_insn/u 5 4 6 (parallel [
            (set (reg:SI 0 ax)
                (call:SI (mem:QI (symbol_ref:SI ("___tls_get_addr")) [0  S1 A8])
                    (const_int 0 [0])))
            (unspec:SI [
                    (reg:SI 3 bx)
                    (symbol_ref:SI ("__bid_IDEC_glbflags") [flags
0x10]  <var_decl 0x7ffff5ef3da8 __bid_IDEC_glbflags>)
                ] UNSPEC_TLS_GD)
            (clobber (scratch:SI))
            (clobber (scratch:SI))
            (clobber (reg:CC 17 flags))
        ]) ../../../../src/libgcc/config/libbid/bid_decimal_globals.c:51 -1
     (expr_list:REG_EH_REGION (const_int -2147483648 [0xffffffff80000000])
        (nil))
    (nil))

(insn 6 5 7 (set (reg/f:SI 85)
        (reg:SI 0 ax))
../../../../src/libgcc/config/libbid/bid_decimal_globals.c:51 -1
     (expr_list:REG_EQUAL (symbol_ref:SI ("__bid_IDEC_glbflags")
[flags 0x10]  <var_decl 0x7ffff5ef3da8 __bid_IDEC_glbflags>)

After the problem is fixed, bootstrap and regression test on x86-64 are ok.

Thanks,
Wei.

Index: config/i386/i386.md
===================================================================
--- config/i386/i386.md	(revision 208410)
+++ config/i386/i386.md	(working copy)
@@ -12859,13 +12859,14 @@
 
 (define_insn "*tls_global_dynamic_32_gnu"
   [(set (match_operand:SI 0 "register_operand" "=a")
-	(unspec:SI
-	 [(match_operand:SI 1 "register_operand" "b")
-	  (match_operand 2 "tls_symbolic_operand")
-	  (match_operand 3 "constant_call_address_operand" "z")]
-	 UNSPEC_TLS_GD))
-   (clobber (match_scratch:SI 4 "=d"))
-   (clobber (match_scratch:SI 5 "=c"))
+	(call:SI
+	 (mem:QI (match_operand 3 "constant_call_address_operand" "z"))
+	 (match_operand 4)))
+   (unspec:SI [(match_operand:SI 1 "register_operand" "b")
+	       (match_operand 2 "tls_symbolic_operand")]
+	      UNSPEC_TLS_GD)
+   (clobber (match_scratch:SI 5 "=d"))
+   (clobber (match_scratch:SI 6 "=c"))
    (clobber (reg:CC FLAGS_REG))]
   "!TARGET_64BIT && TARGET_GNU_TLS"
 {
@@ -12885,13 +12886,19 @@
 (define_expand "tls_global_dynamic_32"
   [(parallel
     [(set (match_operand:SI 0 "register_operand")
-	  (unspec:SI [(match_operand:SI 2 "register_operand")
-		      (match_operand 1 "tls_symbolic_operand")
-		      (match_operand 3 "constant_call_address_operand")]
-		     UNSPEC_TLS_GD))
+	  (call:SI
+	   (mem:QI (match_operand 3 "constant_call_address_operand"))
+	   (const_int 0)))
+     (unspec:SI [(match_operand:SI 2 "register_operand")
+		 (match_operand 1 "tls_symbolic_operand")]
+		UNSPEC_TLS_GD)
      (clobber (match_scratch:SI 4))
      (clobber (match_scratch:SI 5))
-     (clobber (reg:CC FLAGS_REG))])])
+     (clobber (reg:CC FLAGS_REG))])]
+  ""
+{
+  ix86_tls_descriptor_calls_expanded_in_cfun = true;
+})
 
 (define_insn "*tls_global_dynamic_64_<mode>"
   [(set (match_operand:P 0 "register_operand" "=a")
@@ -12946,16 +12953,20 @@
 	   (const_int 0)))
      (unspec:P [(match_operand 1 "tls_symbolic_operand")]
 	       UNSPEC_TLS_GD)])]
-  "TARGET_64BIT")
+  "TARGET_64BIT"
+{
+  ix86_tls_descriptor_calls_expanded_in_cfun = true;
+})
 
 (define_insn "*tls_local_dynamic_base_32_gnu"
   [(set (match_operand:SI 0 "register_operand" "=a")
-	(unspec:SI
-	 [(match_operand:SI 1 "register_operand" "b")
-	  (match_operand 2 "constant_call_address_operand" "z")]
-	 UNSPEC_TLS_LD_BASE))
-   (clobber (match_scratch:SI 3 "=d"))
-   (clobber (match_scratch:SI 4 "=c"))
+	(call:SI
+	 (mem:QI (match_operand 2 "constant_call_address_operand" "z"))
+	 (match_operand 3)))
+   (unspec:SI [(match_operand:SI 1 "register_operand" "b")]
+	      UNSPEC_TLS_LD_BASE)
+   (clobber (match_scratch:SI 4 "=d"))
+   (clobber (match_scratch:SI 5 "=c"))
    (clobber (reg:CC FLAGS_REG))]
   "!TARGET_64BIT && TARGET_GNU_TLS"
 {
@@ -12976,13 +12987,18 @@
 (define_expand "tls_local_dynamic_base_32"
   [(parallel
      [(set (match_operand:SI 0 "register_operand")
-	   (unspec:SI
-	    [(match_operand:SI 1 "register_operand")
-	     (match_operand 2 "constant_call_address_operand")]
-	    UNSPEC_TLS_LD_BASE))
+	   (call:SI
+	    (mem:QI (match_operand 2 "constant_call_address_operand"))
+	    (const_int 0)))
+      (unspec:SI [(match_operand:SI 1 "register_operand")]
+		 UNSPEC_TLS_LD_BASE)
       (clobber (match_scratch:SI 3))
       (clobber (match_scratch:SI 4))
-      (clobber (reg:CC FLAGS_REG))])])
+      (clobber (reg:CC FLAGS_REG))])]
+  ""
+{
+  ix86_tls_descriptor_calls_expanded_in_cfun = true;
+})
 
 (define_insn "*tls_local_dynamic_base_64_<mode>"
   [(set (match_operand:P 0 "register_operand" "=a")
@@ -13029,33 +13045,10 @@
 	    (mem:QI (match_operand 1))
 	    (const_int 0)))
       (unspec:P [(const_int 0)] UNSPEC_TLS_LD_BASE)])]
-  "TARGET_64BIT")
-
-;; Local dynamic of a single variable is a lose.  Show combine how
-;; to convert that back to global dynamic.
-
-(define_insn_and_split "*tls_local_dynamic_32_once"
-  [(set (match_operand:SI 0 "register_operand" "=a")
-	(plus:SI
-	 (unspec:SI [(match_operand:SI 1 "register_operand" "b")
-		     (match_operand 2 "constant_call_address_operand" "z")]
-		    UNSPEC_TLS_LD_BASE)
-	 (const:SI (unspec:SI
-		    [(match_operand 3 "tls_symbolic_operand")]
-		    UNSPEC_DTPOFF))))
-   (clobber (match_scratch:SI 4 "=d"))
-   (clobber (match_scratch:SI 5 "=c"))
-   (clobber (reg:CC FLAGS_REG))]
-  ""
-  "#"
-  ""
-  [(parallel
-     [(set (match_dup 0)
-	   (unspec:SI [(match_dup 1) (match_dup 3) (match_dup 2)]
-		      UNSPEC_TLS_GD))
-      (clobber (match_dup 4))
-      (clobber (match_dup 5))
-      (clobber (reg:CC FLAGS_REG))])])
+  "TARGET_64BIT"
+{
+  ix86_tls_descriptor_calls_expanded_in_cfun = true;
+})
 
 ;; Segment register for the thread base ptr load
 (define_mode_attr tp_seg [(SI "gs") (DI "fs")])
Index: config/i386/i386.c
===================================================================
--- config/i386/i386.c	(revision 208410)
+++ config/i386/i386.c	(working copy)
@@ -9490,20 +9490,30 @@ ix86_compute_frame_layout (struct ix86_f
   frame->nregs = ix86_nsaved_regs ();
   frame->nsseregs = ix86_nsaved_sseregs ();
 
-  stack_alignment_needed = crtl->stack_alignment_needed / BITS_PER_UNIT;
-  preferred_alignment = crtl->preferred_stack_boundary / BITS_PER_UNIT;
-
   /* 64-bit MS ABI seem to require stack alignment to be always 16 except for
      function prologues and leaf.  */
-  if ((TARGET_64BIT_MS_ABI && preferred_alignment < 16)
+  if ((TARGET_64BIT_MS_ABI && crtl->preferred_stack_boundary < 128)
       && (!crtl->is_leaf || cfun->calls_alloca != 0
           || ix86_current_function_calls_tls_descriptor))
     {
-      preferred_alignment = 16;
-      stack_alignment_needed = 16;
       crtl->preferred_stack_boundary = 128;
       crtl->stack_alignment_needed = 128;
     }
+  /* preferred_stack_boundary is never updated for call
+     expanded from tls descriptor. Update it here. We don't update it in
+     expand stage because according to the comments before
+     ix86_current_function_calls_tls_descriptor, tls calls may be optimized
+     away.  */
+  else if (ix86_current_function_calls_tls_descriptor
+	   && crtl->preferred_stack_boundary < PREFERRED_STACK_BOUNDARY)
+    {
+      crtl->preferred_stack_boundary = PREFERRED_STACK_BOUNDARY;
+      if (crtl->stack_alignment_needed < PREFERRED_STACK_BOUNDARY)
+	crtl->stack_alignment_needed = PREFERRED_STACK_BOUNDARY;
+    }
+
+  stack_alignment_needed = crtl->stack_alignment_needed / BITS_PER_UNIT;
+  preferred_alignment = crtl->preferred_stack_boundary / BITS_PER_UNIT;
 
   gcc_assert (!size || stack_alignment_needed);
   gcc_assert (preferred_alignment >= STACK_BOUNDARY / BITS_PER_UNIT);
@@ -13437,26 +13447,25 @@ legitimize_tls_address (rtx x, enum tls_
       else
 	{
 	  rtx caddr = ix86_tls_get_addr ();
+	  rtx ax = gen_rtx_REG (Pmode, AX_REG);
+	  rtx insns;
+	  start_sequence ();
 
 	  if (TARGET_64BIT)
-	    {
-	      rtx rax = gen_rtx_REG (Pmode, AX_REG);
-	      rtx insns;
+	    emit_call_insn
+	      (ix86_gen_tls_global_dynamic_64 (ax, x, caddr));
+	  else
+	    emit_call_insn
+	      (gen_tls_global_dynamic_32 (ax, x, pic, caddr));
 
-	      start_sequence ();
-	      emit_call_insn
-		(ix86_gen_tls_global_dynamic_64 (rax, x, caddr));
-	      insns = get_insns ();
-	      end_sequence ();
+	  insns = get_insns ();
+	  end_sequence ();
 
-	      if (GET_MODE (x) != Pmode)
-		x = gen_rtx_ZERO_EXTEND (Pmode, x);
+	  if (GET_MODE (x) != Pmode)
+	    x = gen_rtx_ZERO_EXTEND (Pmode, x);
 
-	      RTL_CONST_CALL_P (insns) = 1;
-	      emit_libcall_block (insns, dest, rax, x);
-	    }
-	  else
-	    emit_insn (gen_tls_global_dynamic_32 (dest, x, pic, caddr));
+	  RTL_CONST_CALL_P (insns) = 1;
+	  emit_libcall_block (insns, dest, ax, x);
 	}
       break;
 
@@ -13490,28 +13499,28 @@ legitimize_tls_address (rtx x, enum tls_
       else
 	{
 	  rtx caddr = ix86_tls_get_addr ();
+	  rtx ax = gen_rtx_REG (Pmode, AX_REG);
+	  rtx insns, eqv;
+
+	  start_sequence ();
 
 	  if (TARGET_64BIT)
-	    {
-	      rtx rax = gen_rtx_REG (Pmode, AX_REG);
-	      rtx insns, eqv;
+	    emit_call_insn
+	      (ix86_gen_tls_local_dynamic_base_64 (ax, caddr));
+	  else
+	    emit_call_insn
+	      (gen_tls_local_dynamic_base_32 (ax, pic, caddr));
 
-	      start_sequence ();
-	      emit_call_insn
-		(ix86_gen_tls_local_dynamic_base_64 (rax, caddr));
-	      insns = get_insns ();
-	      end_sequence ();
-
-	      /* Attach a unique REG_EQUAL, to allow the RTL optimizers to
-		 share the LD_BASE result with other LD model accesses.  */
-	      eqv = gen_rtx_UNSPEC (Pmode, gen_rtvec (1, const0_rtx),
-				    UNSPEC_TLS_LD_BASE);
+	  insns = get_insns ();
+	  end_sequence ();
 
-	      RTL_CONST_CALL_P (insns) = 1;
-	      emit_libcall_block (insns, base, rax, eqv);
-	    }
-	  else
-	    emit_insn (gen_tls_local_dynamic_base_32 (base, pic, caddr));
+	  /* Attach a unique REG_EQUAL, to allow the RTL optimizers to
+	     share the LD_BASE result with other LD model accesses.  */
+	  eqv = gen_rtx_UNSPEC (Pmode, gen_rtvec (1, const0_rtx),
+				UNSPEC_TLS_LD_BASE);
+
+	  RTL_CONST_CALL_P (insns) = 1;
+	  emit_libcall_block (insns, base, ax, eqv);
 	}
 
       off = gen_rtx_UNSPEC (Pmode, gen_rtvec (1, x), UNSPEC_DTPOFF);