diff mbox

[PR58066] preferred_stack_boundary update for tls expanded call

Message ID CA+4CFy518LEBiV2aOCin9Ay0f52ONUUkaeezUqB0JjebRQtRXw@mail.gmail.com
State New
Headers show

Commit Message

Wei Mi March 13, 2014, 5:55 p.m. UTC 
> Can we combine the last two patches, both adding call explicitly in
> rtl template for tls_local_dynamic_base_32/tls_global_dynamic_32, and
> set ix86_tls_descriptor_calls_expanded_in_cfun to true only after
> reload complete?
>

Hi H.J.

I attached the patch which combined your two patches and the fix in
legitimize_tls_address. I tried pr58066.c and c.i in ia32/x32/x86_64,
the code looked fine. Do you think it is ok?

Thanks,
Wei.

Comments

H.J. Lu March 13, 2014, 6:01 p.m. UTC | #1 
On Thu, Mar 13, 2014 at 10:55 AM, Wei Mi <wmi@google.com> wrote:
>> Can we combine the last two patches, both adding call explicitly in
>> rtl template for tls_local_dynamic_base_32/tls_global_dynamic_32, and
>> set ix86_tls_descriptor_calls_expanded_in_cfun to true only after
>> reload complete?
>>
>
> Hi H.J.
>
> I attached the patch which combined your two patches and the fix in
> legitimize_tls_address. I tried pr58066.c and c.i in ia32/x32/x86_64,
> the code looked fine. Do you think it is ok?
>
> Thanks,
> Wei.

Either pr58066-3.patch or pr58066-4.patch looks good to me.

Thanks.
Wei Mi May 1, 2014, 4:42 a.m. UTC | #2 
Ping. Is pr58066-3.patch or pr58066-4.patch ok for trunk?

Thanks,
Wei.

>> I attached the patch which combined your two patches and the fix in
>> legitimize_tls_address. I tried pr58066.c and c.i in ia32/x32/x86_64,
>> the code looked fine. Do you think it is ok?
>>
>> Thanks,
>> Wei.
>
> Either pr58066-3.patch or pr58066-4.patch looks good to me.
>
> Thanks.
>
> --
> H.J.
Uros Bizjak May 1, 2014, 6:44 a.m. UTC | #3 
On Thu, May 1, 2014 at 6:42 AM, Wei Mi <wmi@google.com> wrote:
> Ping. Is pr58066-3.patch or pr58066-4.patch ok for trunk?

None of these patches have correct ChangeLog entries. Please follow
the rules, outlined in http://gcc.gnu.org/contribute.html (Submitting
Patches section), otherwise your patches will be simply ignored.

>>> I attached the patch which combined your two patches and the fix in
>>> legitimize_tls_address. I tried pr58066.c and c.i in ia32/x32/x86_64,
>>> the code looked fine. Do you think it is ok?
>>>
>>> Thanks,
>>> Wei.
>>
>> Either pr58066-3.patch or pr58066-4.patch looks good to me.

pr58066-4 patch is definitely not OK. I wonder, how it works at all,
since you can't split the insn to the same pattern. The generic code
detects this condition and forces ICE (IIRC: this is the reason for
UNSPEC_DIV_ALREADY_SPLIT tag in divmod<mode4_1>).

From pr58066-3 patch:

-;; 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))])])

Why did you remove this splitter?

Please do not write:

+{
+  ix86_tls_descriptor_calls_expanded_in_cfun = true;
+})

but use a short form:

+  "ix86_tls_descriptor_calls_expanded_in_cfun = true;")

Please also add a testcase (from one of the previous mails):

--- testsuite/gcc.dg/pr58066.c (revision 0)
+++ testsuite/gcc.dg/pr58066.c (revision 0)

Put this test to gcc.target/i386 directory ...
@@ -0,0 +1,18 @@
+/* { dg-do compile { target {{ i?86-*-* x86_64-*-* } && { ! ia32 } } } } */

... to avoid target selector.

+/* { dg-options "-fPIC -O2" } */
+
+/* Check whether the stack frame starting addresses of tls expanded calls
+   in foo and goo are 16bytes aligned.  */
+static __thread char ccc1;
+void* foo()
+{
+ return &ccc1;
+}
+
+__thread char ccc2;
+void* goo()
+{
+ return &ccc2;
+}
+
+/* { dg-final { scan-assembler-times ".cfi_def_cfa_offset 16" 2 } } */

Please repost the complete patch with a proper ChangeLog.

Uros.
Wei Mi May 1, 2014, 6:06 p.m. UTC | #4 
On Wed, Apr 30, 2014 at 11:44 PM, Uros Bizjak <ubizjak@gmail.com> wrote:
> On Thu, May 1, 2014 at 6:42 AM, Wei Mi <wmi@google.com> wrote:
>> Ping. Is pr58066-3.patch or pr58066-4.patch ok for trunk?
>
> None of these patches have correct ChangeLog entries. Please follow
> the rules, outlined in http://gcc.gnu.org/contribute.html (Submitting
> Patches section), otherwise your patches will be simply ignored.
>

Will add Changelog in the final patch.

>
> pr58066-4 patch is definitely not OK. I wonder, how it works at all,
> since you can't split the insn to the same pattern. The generic code
> detects this condition and forces ICE (IIRC: this is the reason for
> UNSPEC_DIV_ALREADY_SPLIT tag in divmod<mode4_1>).
>

If the generic code detects same pattern, it will not ICE but return
the original insn (See the code in try_split under the comment /*
Avoid infinite loop if any insn of the result matches the original
pattern. */). ix86_tls_descriptor_calls_expanded_in_cfun will be set
to true even if original insn is returned by try_split. That is how
pr58066-4 works.

> From pr58066-3 patch:
>
> -;; 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))])])
>
> Why did you remove this splitter?
>

After we add add call into the pattern of tls_local_dynamic_base_32,
it is difficult for the pattern tls_local_dynamic_32_once to be
matched. I don't have a good way to rewrite tls_local_dynamic_32_once.
Do you have any idea?

(define_expand "tls_local_dynamic_base_32"
  [(parallel
     [(set (match_operand:SI 0 "register_operand")
           (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))])]

> Please do not write:
>
> +{
> +  ix86_tls_descriptor_calls_expanded_in_cfun = true;
> +})
>
> but use a short form:
>
> +  "ix86_tls_descriptor_calls_expanded_in_cfun = true;")
>
> Please also add a testcase (from one of the previous mails):
>
> --- testsuite/gcc.dg/pr58066.c (revision 0)
> +++ testsuite/gcc.dg/pr58066.c (revision 0)
>
> Put this test to gcc.target/i386 directory ...
> @@ -0,0 +1,18 @@
> +/* { dg-do compile { target {{ i?86-*-* x86_64-*-* } && { ! ia32 } } } } */
>
> ... to avoid target selector.
>
> +/* { dg-options "-fPIC -O2" } */
> +
> +/* Check whether the stack frame starting addresses of tls expanded calls
> +   in foo and goo are 16bytes aligned.  */
> +static __thread char ccc1;
> +void* foo()
> +{
> + return &ccc1;
> +}
> +
> +__thread char ccc2;
> +void* goo()
> +{
> + return &ccc2;
> +}
> +
> +/* { dg-final { scan-assembler-times ".cfi_def_cfa_offset 16" 2 } } */
>
> Please repost the complete patch with a proper ChangeLog.
>
> Uros.

will do that.

Thanks,
Wei.
diff mbox

Patch

Index: config/i386/i386.c
===================================================================
--- config/i386/i386.c	(revision 208410)
+++ config/i386/i386.c	(working copy)
@@ -9082,7 +9082,7 @@  ix86_frame_pointer_required (void)
      we've not got a leaf function.  */
   if (TARGET_OMIT_LEAF_FRAME_POINTER
       && (!crtl->is_leaf
-	  || ix86_current_function_calls_tls_descriptor))
+	  || ix86_tls_descriptor_calls_expanded_in_cfun))
     return true;
 
   if (crtl->profile && !flag_fentry)
@@ -9331,7 +9331,7 @@  ix86_select_alt_pic_regnum (void)
 {
   if (crtl->is_leaf
       && !crtl->profile
-      && !ix86_current_function_calls_tls_descriptor)
+      && !ix86_tls_descriptor_calls_expanded_in_cfun)
     {
       int i, drap;
       /* Can't use the same register for both PIC and DRAP.  */
@@ -9490,20 +9490,28 @@  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))
+          || ix86_tls_descriptor_calls_expanded_in_cfun))
     {
-      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 tls calls may be optimized away.  */
+  else if (ix86_tls_descriptor_calls_expanded_in_cfun
+          && 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);
@@ -9608,7 +9616,7 @@  ix86_compute_frame_layout (struct ix86_f
       || size != 0
       || !crtl->is_leaf
       || cfun->calls_alloca
-      || ix86_current_function_calls_tls_descriptor)
+      || ix86_tls_descriptor_calls_expanded_in_cfun)
     offset = (offset + stack_alignment_needed - 1) & -stack_alignment_needed;
 
   /* Frame pointer points here.  */
@@ -9623,7 +9631,7 @@  ix86_compute_frame_layout (struct ix86_f
      of stack frame are unused.  */
   if (ACCUMULATE_OUTGOING_ARGS
       && (!crtl->is_leaf || cfun->calls_alloca
-	  || ix86_current_function_calls_tls_descriptor))
+	  || ix86_tls_descriptor_calls_expanded_in_cfun))
     {
       offset += crtl->outgoing_args_size;
       frame->outgoing_arguments_size = crtl->outgoing_args_size;
@@ -9634,7 +9642,7 @@  ix86_compute_frame_layout (struct ix86_f
   /* Align stack boundary.  Only needed if we're calling another function
      or using alloca.  */
   if (!crtl->is_leaf || cfun->calls_alloca
-      || ix86_current_function_calls_tls_descriptor)
+      || ix86_tls_descriptor_calls_expanded_in_cfun)
     offset = (offset + preferred_alignment - 1) & -preferred_alignment;
 
   /* We've reached end of stack frame.  */
@@ -9650,7 +9658,7 @@  ix86_compute_frame_layout (struct ix86_f
   if (ix86_using_red_zone ()
       && crtl->sp_is_unchanging
       && crtl->is_leaf
-      && !ix86_current_function_calls_tls_descriptor)
+      && !ix86_tls_descriptor_calls_expanded_in_cfun)
     {
       frame->red_zone_size = to_allocate;
       if (frame->save_regs_using_mov)
@@ -10623,7 +10631,7 @@  ix86_finalize_stack_realign_flags (void)
       && crtl->is_leaf
       && flag_omit_frame_pointer
       && crtl->sp_is_unchanging
-      && !ix86_current_function_calls_tls_descriptor
+      && !ix86_tls_descriptor_calls_expanded_in_cfun
       && !crtl->accesses_prior_frames
       && !cfun->calls_alloca
       && !crtl->calls_eh_return
@@ -13437,26 +13445,25 @@  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 +13497,28 @@  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);
Index: config/i386/i386.h
===================================================================
--- config/i386/i386.h	(revision 208410)
+++ config/i386/i386.h	(working copy)
@@ -2451,13 +2451,7 @@  struct GTY(()) machine_function {
 #define ix86_current_function_needs_cld (cfun->machine->needs_cld)
 #define ix86_tls_descriptor_calls_expanded_in_cfun \
   (cfun->machine->tls_descriptor_call_expanded_p)
-/* Since tls_descriptor_call_expanded is not cleared, even if all TLS
-   calls are optimized away, we try to detect cases in which it was
-   optimized away.  Since such instructions (use (reg REG_SP)), we can
-   verify whether there's any such instruction live by testing that
-   REG_SP is live.  */
-#define ix86_current_function_calls_tls_descriptor \
-  (ix86_tls_descriptor_calls_expanded_in_cfun && df_regs_ever_live_p (SP_REG))
+
 #define ix86_static_chain_on_stack (cfun->machine->static_chain_on_stack)
 
 /* Control behavior of x86_file_start.  */
Index: config/i386/i386.md
===================================================================
--- config/i386/i386.md	(revision 208410)
+++ config/i386/i386.md	(working copy)
@@ -12857,15 +12857,16 @@ 
 ;; Note that these code sequences must appear exactly as shown
 ;; in order to allow linker relaxation.
 
-(define_insn "*tls_global_dynamic_32_gnu"
+(define_insn_and_split "*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"
 {
@@ -12879,21 +12880,38 @@ 
 #endif
   return "call\t%P3";
 }
+  "reload_completed"
+  [(parallel
+    [(set (match_dup 0)
+	  (call:SI
+	   (mem:QI (match_dup 3))
+	   (match_dup 4)))
+     (unspec:SI [(match_dup 1)
+		 (match_dup 2)]
+		UNSPEC_TLS_GD)
+     (clobber (match_dup 5))
+     (clobber (match_dup 6))
+     (clobber (reg:CC FLAGS_REG))])]
+{
+  ix86_tls_descriptor_calls_expanded_in_cfun = true;
+}
   [(set_attr "type" "multi")
    (set_attr "length" "12")])
 
 (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))])])
 
-(define_insn "*tls_global_dynamic_64_<mode>"
+(define_insn_and_split "*tls_global_dynamic_64_<mode>"
   [(set (match_operand:P 0 "register_operand" "=a")
 	(call:P
 	 (mem:QI (match_operand 2 "constant_call_address_operand" "z"))
@@ -12912,11 +12930,22 @@ 
     return "call\t%p2@plt";
   return "call\t%P2";
 }
+  "reload_completed"
+  [(parallel
+    [(set (match_dup 0)
+	  (call:P
+	   (mem:QI (match_dup 2))
+	   (match_dup 3)))
+     (unspec:P [(match_dup 1)]
+	       UNSPEC_TLS_GD)])]
+{
+  ix86_tls_descriptor_calls_expanded_in_cfun = true;
+}
   [(set_attr "type" "multi")
    (set (attr "length")
 	(symbol_ref "TARGET_X32 ? 15 : 16"))])
 
-(define_insn "*tls_global_dynamic_64_largepic"
+(define_insn_and_split "*tls_global_dynamic_64_largepic"
   [(set (match_operand:DI 0 "register_operand" "=a")
 	(call:DI
 	 (mem:QI (plus:DI (match_operand:DI 2 "register_operand" "b")
@@ -12935,6 +12964,18 @@ 
   output_asm_insn ("add{q}\t{%2, %%rax|rax, %2}", operands);
   return "call\t{*%%rax|rax}";
 }
+  "reload_completed"
+  [(parallel
+    [(set (match_dup 0)
+	  (call:P
+	 (mem:QI (plus:DI (match_dup 2)
+			  (match_dup 3)))
+	 (match_operand 4)))
+     (unspec:P [(match_dup 1)]
+	       UNSPEC_TLS_GD)])]
+{
+  ix86_tls_descriptor_calls_expanded_in_cfun = true;
+}
   [(set_attr "type" "multi")
    (set_attr "length" "22")])
 
@@ -12948,14 +12989,15 @@ 
 	       UNSPEC_TLS_GD)])]
   "TARGET_64BIT")
 
-(define_insn "*tls_local_dynamic_base_32_gnu"
+(define_insn_and_split "*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"
 {
@@ -12970,21 +13012,36 @@ 
     }
   return "call\t%P2";
 }
+  "reload_completed"
+  [(parallel
+    [(set (match_dup 0)
+	  (call:SI
+	   (mem:QI (match_dup 2))
+	   (match_dup 3)))
+   (unspec:SI [(match_dup 1)]
+	      UNSPEC_TLS_LD_BASE)
+   (clobber (match_dup 4))
+   (clobber (match_dup 5))
+   (clobber (reg:CC FLAGS_REG))])]
+{
+  ix86_tls_descriptor_calls_expanded_in_cfun = true;
+}
   [(set_attr "type" "multi")
    (set_attr "length" "11")])
 
 (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))])])
 
-(define_insn "*tls_local_dynamic_base_64_<mode>"
+(define_insn_and_split "*tls_local_dynamic_base_64_<mode>"
   [(set (match_operand:P 0 "register_operand" "=a")
 	(call:P
 	 (mem:QI (match_operand 1 "constant_call_address_operand" "z"))
@@ -12998,10 +13055,20 @@ 
     return "call\t%p1@plt";
   return "call\t%P1";
 }
+  "reload_completed"
+  [(parallel
+    [(set (match_dup 0)
+	  (call:P
+	   (mem:QI (match_dup 1))
+	   (match_dup 2)))
+     (unspec:P [(const_int 0)] UNSPEC_TLS_LD_BASE)])]
+{
+  ix86_tls_descriptor_calls_expanded_in_cfun = true;
+}
   [(set_attr "type" "multi")
    (set_attr "length" "12")])
 
-(define_insn "*tls_local_dynamic_base_64_largepic"
+(define_insn_and_split "*tls_local_dynamic_base_64_largepic"
   [(set (match_operand:DI 0 "register_operand" "=a")
 	(call:DI
 	 (mem:QI (plus:DI (match_operand:DI 1 "register_operand" "b")
@@ -13019,6 +13086,17 @@ 
   output_asm_insn ("add{q}\t{%1, %%rax|rax, %1}", operands);
   return "call\t{*%%rax|rax}";
 }
+  "reload_completed"
+  [(parallel
+    [(set (match_dup 0)
+	  (call:DI
+	   (mem:QI (plus:DI (match_dup 1)
+			    (match_dup 2)))
+	   (match_dup 3)))
+     (unspec:DI [(const_int 0)] UNSPEC_TLS_LD_BASE)])]
+{
+  ix86_tls_descriptor_calls_expanded_in_cfun = true;
+}
   [(set_attr "type" "multi")
    (set_attr "length" "22")])
 
@@ -13031,32 +13109,6 @@ 
       (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))])])
-
 ;; Segment register for the thread base ptr load
 (define_mode_attr tp_seg [(SI "gs") (DI "fs")])
 
@@ -13167,7 +13219,6 @@ 
   "!TARGET_64BIT && TARGET_GNU2_TLS"
 {
   operands[3] = can_create_pseudo_p () ? gen_reg_rtx (Pmode) : operands[0];
-  ix86_tls_descriptor_calls_expanded_in_cfun = true;
 })
 
 (define_insn "*tls_dynamic_gnu2_lea_32"
@@ -13183,7 +13234,7 @@ 
    (set_attr "length" "6")
    (set_attr "length_address" "4")])
 
-(define_insn "*tls_dynamic_gnu2_call_32"
+(define_insn_and_split "*tls_dynamic_gnu2_call_32"
   [(set (match_operand:SI 0 "register_operand" "=a")
 	(unspec:SI [(match_operand 1 "tls_symbolic_operand")
 		    (match_operand:SI 2 "register_operand" "0")
@@ -13194,6 +13245,17 @@ 
    (clobber (reg:CC FLAGS_REG))]
   "!TARGET_64BIT && TARGET_GNU2_TLS"
   "call\t{*%a1@TLSCALL(%2)|[DWORD PTR [%2+%a1@TLSCALL]]}"
+  "reload_completed"
+  [(set (match_dup 0)
+	(unspec:SI [(match_dup 1)
+		    (match_dup 2)
+		    (match_dup 3)
+		    (reg:SI SP_REG)]
+		   UNSPEC_TLSDESC))
+   (clobber (reg:CC FLAGS_REG))]
+{
+  ix86_tls_descriptor_calls_expanded_in_cfun = true;
+}
   [(set_attr "type" "call")
    (set_attr "length" "2")
    (set_attr "length_address" "0")])
@@ -13231,7 +13293,6 @@ 
   "TARGET_64BIT && TARGET_GNU2_TLS"
 {
   operands[2] = can_create_pseudo_p () ? gen_reg_rtx (Pmode) : operands[0];
-  ix86_tls_descriptor_calls_expanded_in_cfun = true;
 })
 
 (define_insn "*tls_dynamic_gnu2_lea_64"
@@ -13245,7 +13306,7 @@ 
    (set_attr "length" "7")
    (set_attr "length_address" "4")])
 
-(define_insn "*tls_dynamic_gnu2_call_64"
+(define_insn_and_split "*tls_dynamic_gnu2_call_64"
   [(set (match_operand:DI 0 "register_operand" "=a")
 	(unspec:DI [(match_operand 1 "tls_symbolic_operand")
 		    (match_operand:DI 2 "register_operand" "0")
@@ -13254,6 +13315,16 @@ 
    (clobber (reg:CC FLAGS_REG))]
   "TARGET_64BIT && TARGET_GNU2_TLS"
   "call\t{*%a1@TLSCALL(%2)|[QWORD PTR [%2+%a1@TLSCALL]]}"
+  "reload_completed"
+  [(set (match_dup 0)
+	(unspec:SI [(match_dup 1)
+		    (match_dup 2)
+		    (reg:DI SP_REG)]
+		   UNSPEC_TLSDESC))
+   (clobber (reg:CC FLAGS_REG))]
+{
+  ix86_tls_descriptor_calls_expanded_in_cfun = true;
+}
   [(set_attr "type" "call")
    (set_attr "length" "2")
    (set_attr "length_address" "0")])