[AArch64] Use calls for SVE TLSDEC

[Richard Sandiford <richard dot sandiford at arm dot com>]

[This follows on from:
 https://gcc.gnu.org/ml/gcc-patches/2019-09/msg00778.html
 https://gcc.gnu.org/ml/gcc-patches/2019-09/msg01456.html
 https://gcc.gnu.org/ml/gcc-patches/2019-09/msg01464.html]

One (unintended) side effect of the patches to support multiple
ABIs is that we can now represent tlsdesc calls as normal calls
on SVE targets.  This is likely to be handled more efficiently than
clobber_high, and for example fixes the long-standing failure in
gcc.target/aarch64/sve/tls_preserve_1.c.

Tested on aarch64-linux-gnu.  I'll apply if the dependencies above
are approved.

Richard


2019-09-25  Richard Sandiford  <richard.sandiford@arm.com>

gcc/
	PR target/91452
	* config/aarch64/aarch64.h (ARM_PCS_TLSDESC): New arm_pcs.
	* config/aarch64/aarch64-protos.h (aarch64_tlsdesc_abi_id): Declare.
	* config/aarch64/aarch64.c (aarch64_hard_regno_call_part_clobbered):
	Handle ARM_PCS_TLSDESC.
	(aarch64_tlsdesc_abi_id): New function.
	* config/aarch64/aarch64.md (tlsdesc_small_sve_<mode>): Use a call
	rtx instead of a list of clobbers and clobber_highs.
	(tlsdesc_small_<mode>): Update accordingly.

Index: gcc/config/aarch64/aarch64.h
===================================================================
--- gcc/config/aarch64/aarch64.h	2019-09-25 16:22:58.464627786 +0100
+++ gcc/config/aarch64/aarch64.h	2019-09-25 17:34:36.077725643 +0100
@@ -784,6 +784,7 @@ enum arm_pcs
 {
   ARM_PCS_AAPCS64,		/* Base standard AAPCS for 64 bit.  */
   ARM_PCS_SIMD,			/* For aarch64_vector_pcs functions.  */
+  ARM_PCS_TLSDESC,		/* For targets of tlsdesc calls.  */
   ARM_PCS_UNKNOWN
 };
 
Index: gcc/config/aarch64/aarch64-protos.h
===================================================================
--- gcc/config/aarch64/aarch64-protos.h	2019-09-25 17:31:04.663257639 +0100
+++ gcc/config/aarch64/aarch64-protos.h	2019-09-25 17:34:36.073725674 +0100
@@ -519,6 +519,7 @@ bool aarch64_use_return_insn_p (void);
 const char *aarch64_mangle_builtin_type (const_tree);
 const char *aarch64_output_casesi (rtx *);
 
+unsigned int aarch64_tlsdesc_abi_id ();
 enum aarch64_symbol_type aarch64_classify_symbol (rtx, HOST_WIDE_INT);
 enum aarch64_symbol_type aarch64_classify_tls_symbol (rtx);
 enum reg_class aarch64_regno_regclass (unsigned);
Index: gcc/config/aarch64/aarch64.c
===================================================================
--- gcc/config/aarch64/aarch64.c	2019-09-25 17:31:04.667257609 +0100
+++ gcc/config/aarch64/aarch64.c	2019-09-25 17:34:36.077725643 +0100
@@ -1896,12 +1896,13 @@ aarch64_hard_regno_call_part_clobbered (
 {
   if (FP_REGNUM_P (regno))
     {
-      bool simd_p = (abi_id == ARM_PCS_SIMD);
       poly_int64 per_register_size = GET_MODE_SIZE (mode);
       unsigned int nregs = hard_regno_nregs (regno, mode);
       if (nregs > 1)
 	per_register_size = exact_div (per_register_size, nregs);
-      return maybe_gt (per_register_size, simd_p ? 16 : 8);
+      if (abi_id == ARM_PCS_SIMD || abi_id == ARM_PCS_TLSDESC)
+	return maybe_gt (per_register_size, 16);
+      return maybe_gt (per_register_size, 8);
     }
   return false;
 }
@@ -13873,6 +13874,26 @@ aarch64_can_inline_p (tree caller, tree
   return true;
 }
 
+/* Return the ID of the TLDESC ABI, initializing the descriptor if hasn't
+   been already.  */
+
+unsigned int
+aarch64_tlsdesc_abi_id ()
+{
+  predefined_function_abi &tlsdesc_abi = function_abis[ARM_PCS_TLSDESC];
+  if (!tlsdesc_abi.initialized_p ())
+    {
+      HARD_REG_SET full_reg_clobbers;
+      CLEAR_HARD_REG_SET (full_reg_clobbers);
+      SET_HARD_REG_BIT (full_reg_clobbers, R0_REGNUM);
+      SET_HARD_REG_BIT (full_reg_clobbers, CC_REGNUM);
+      for (int regno = P0_REGNUM; regno <= P15_REGNUM; ++regno)
+	SET_HARD_REG_BIT (full_reg_clobbers, regno);
+      tlsdesc_abi.initialize (ARM_PCS_TLSDESC, full_reg_clobbers);
+    }
+  return tlsdesc_abi.id ();
+}
+
 /* Return true if SYMBOL_REF X binds locally.  */
 
 static bool
Index: gcc/config/aarch64/aarch64.md
===================================================================
--- gcc/config/aarch64/aarch64.md	2019-09-25 17:31:04.667257609 +0100
+++ gcc/config/aarch64/aarch64.md	2019-09-25 17:34:36.081725616 +0100
@@ -6805,7 +6805,12 @@ (define_expand "tlsdesc_small_<mode>"
   "TARGET_TLS_DESC"
   {
     if (TARGET_SVE)
-      emit_insn (gen_tlsdesc_small_sve_<mode> (operands[0]));
+      {
+	rtx abi = gen_int_mode (aarch64_tlsdesc_abi_id (), DImode);
+	rtx_insn *call
+	  = emit_call_insn (gen_tlsdesc_small_sve_<mode> (operands[0], abi));
+	RTL_CONST_CALL_P (call) = 1;
+      }
     else
       emit_insn (gen_tlsdesc_small_advsimd_<mode> (operands[0]));
     DONE;
@@ -6827,67 +6832,20 @@ (define_insn "tlsdesc_small_advsimd_<mod
   [(set_attr "type" "call")
    (set_attr "length" "16")])
 
-;; For SVE, model tlsdesc calls as clobbering the lower 128 bits of
-;; all vector registers, and clobber all predicate registers, on
-;; top of the usual R0 and LR.
+;; For SVE, model tlsdesc calls as normal calls, with the callee ABI
+;; describing the extra call-preserved guarantees.  This would work
+;; for non-SVE too, but avoiding a call is probably better if we can.
 (define_insn "tlsdesc_small_sve_<mode>"
   [(set (reg:PTR R0_REGNUM)
-        (unspec:PTR [(match_operand 0 "aarch64_valid_symref" "S")]
-		    UNSPEC_TLSDESC))
+	(call (mem:DI (unspec:PTR
+			[(match_operand 0 "aarch64_valid_symref")]
+			UNSPEC_TLSDESC))
+	      (const_int 0)))
+   (unspec:DI [(match_operand:DI 1 "const_int_operand")] UNSPEC_CALLEE_ABI)
    (clobber (reg:DI LR_REGNUM))
-   (clobber (reg:CC CC_REGNUM))
-   (clobber_high (reg:TI V0_REGNUM))
-   (clobber_high (reg:TI V1_REGNUM))
-   (clobber_high (reg:TI V2_REGNUM))
-   (clobber_high (reg:TI V3_REGNUM))
-   (clobber_high (reg:TI V4_REGNUM))
-   (clobber_high (reg:TI V5_REGNUM))
-   (clobber_high (reg:TI V6_REGNUM))
-   (clobber_high (reg:TI V7_REGNUM))
-   (clobber_high (reg:TI V8_REGNUM))
-   (clobber_high (reg:TI V9_REGNUM))
-   (clobber_high (reg:TI V10_REGNUM))
-   (clobber_high (reg:TI V11_REGNUM))
-   (clobber_high (reg:TI V12_REGNUM))
-   (clobber_high (reg:TI V13_REGNUM))
-   (clobber_high (reg:TI V14_REGNUM))
-   (clobber_high (reg:TI V15_REGNUM))
-   (clobber_high (reg:TI V16_REGNUM))
-   (clobber_high (reg:TI V17_REGNUM))
-   (clobber_high (reg:TI V18_REGNUM))
-   (clobber_high (reg:TI V19_REGNUM))
-   (clobber_high (reg:TI V20_REGNUM))
-   (clobber_high (reg:TI V21_REGNUM))
-   (clobber_high (reg:TI V22_REGNUM))
-   (clobber_high (reg:TI V23_REGNUM))
-   (clobber_high (reg:TI V24_REGNUM))
-   (clobber_high (reg:TI V25_REGNUM))
-   (clobber_high (reg:TI V26_REGNUM))
-   (clobber_high (reg:TI V27_REGNUM))
-   (clobber_high (reg:TI V28_REGNUM))
-   (clobber_high (reg:TI V29_REGNUM))
-   (clobber_high (reg:TI V30_REGNUM))
-   (clobber_high (reg:TI V31_REGNUM))
-   (clobber (reg:VNx2BI P0_REGNUM))
-   (clobber (reg:VNx2BI P1_REGNUM))
-   (clobber (reg:VNx2BI P2_REGNUM))
-   (clobber (reg:VNx2BI P3_REGNUM))
-   (clobber (reg:VNx2BI P4_REGNUM))
-   (clobber (reg:VNx2BI P5_REGNUM))
-   (clobber (reg:VNx2BI P6_REGNUM))
-   (clobber (reg:VNx2BI P7_REGNUM))
-   (clobber (reg:VNx2BI P8_REGNUM))
-   (clobber (reg:VNx2BI P9_REGNUM))
-   (clobber (reg:VNx2BI P10_REGNUM))
-   (clobber (reg:VNx2BI P11_REGNUM))
-   (clobber (reg:VNx2BI P12_REGNUM))
-   (clobber (reg:VNx2BI P13_REGNUM))
-   (clobber (reg:VNx2BI P14_REGNUM))
-   (clobber (reg:VNx2BI P15_REGNUM))
-   (clobber (match_scratch:DI 1 "=r"))
-   (use (reg:DI FP_REGNUM))]
+   (clobber (match_scratch:DI 2 "=r"))]
   "TARGET_TLS_DESC && TARGET_SVE"
-  "adrp\\tx0, %A0\;ldr\\t%<w>1, [x0, #%L0]\;add\\t<w>0, <w>0, %L0\;.tlsdesccall\\t%0\;blr\\t%1"
+  "adrp\\tx0, %A0\;ldr\\t%<w>2, [x0, #%L0]\;add\\t<w>0, <w>0, %L0\;.tlsdesccall\\t%0\;blr\\t%2"
   [(set_attr "type" "call")
    (set_attr "length" "16")])