This patch implements support for __builtin_load_no_speculate on
AArch64. On this architecture we inhibit speclation by emitting a
combination of CSEL and a hint instruction that ensures the CSEL is
full resolved when the operands to the CSEL may involve a speculative
load.
* config/aarch64/aarch64.c (aarch64_print_operand): Handle zero passed
to 'H' operand qualifier.
(aarch64_inhibit_load_speculation): New function.
(TARGET_INHIBIT_LOAD_SPECULATION): Redefine.
* config/aarch64/aarch64.md (UNSPECV_NOSPECULATE): New unspec_volatile
code.
(nospeculate<ALLI:mode>, nospeculateti): New patterns.
---
gcc/config/aarch64/aarch64.c | 91 +++++++++++++++++++++++++++++++++++++++++++
gcc/config/aarch64/aarch64.md | 28 +++++++++++++
2 files changed, 119 insertions(+)
diff --git a/gcc/config/aarch64/aarch64.c b/gcc/config/aarch64/aarch64.c
index 436091a..4a000b0 100644
--- a/gcc/config/aarch64/aarch64.c
+++ b/gcc/config/aarch64/aarch64.c
@@ -4987,6 +4987,13 @@ aarch64_print_operand (FILE *f, rtx x, int code)
case 'H':
/* Print the higher numbered register of a pair (TImode) of regs. */
+ if (x == const0_rtx
+ || (CONST_DOUBLE_P (x) && aarch64_float_const_zero_rtx_p (x)))
+ {
+ asm_fprintf (f, "xzr");
+ break;
+ }
+
if (!REG_P (x) || !GP_REGNUM_P (REGNO (x) + 1))
{
output_operand_lossage ("invalid operand for '%%%c'", code);
@@ -14708,6 +14715,87 @@ aarch64_sched_can_speculate_insn (rtx_insn *insn)
}
}
+static rtx
+aarch64_inhibit_load_speculation (machine_mode mode, rtx result, rtx mem,
+ rtx lower_bound, rtx upper_bound,
+ rtx fail_result, rtx cmpptr)
+{
+ rtx cond, comparison;
+ rtx target = gen_reg_rtx (mode);
+ rtx tgt2 = result;
+
+ if (!register_operand (cmpptr, ptr_mode))
+ cmpptr = force_reg (ptr_mode, cmpptr);
+
+ if (!register_operand (tgt2, mode))
+ tgt2 = gen_reg_rtx (mode);
+
+ if (upper_bound == NULL)
+ {
+ if (!register_operand (lower_bound, ptr_mode))
+ lower_bound = force_reg (ptr_mode, lower_bound);
+
+ cond = aarch64_gen_compare_reg (LTU, cmpptr, lower_bound);
+ comparison = gen_rtx_LTU (VOIDmode, cond, const0_rtx);
+ }
+ else if (lower_bound == NULL)
+ {
+ if (!register_operand (upper_bound, ptr_mode))
+ upper_bound = force_reg (ptr_mode, upper_bound);
+
+ cond = aarch64_gen_compare_reg (GEU, cmpptr, upper_bound);
+ comparison = gen_rtx_GEU (VOIDmode, cond, const0_rtx);
+ }
+ else
+ {
+ if (!register_operand (lower_bound, ptr_mode))
+ lower_bound = force_reg (ptr_mode, lower_bound);
+
+ if (!register_operand (upper_bound, ptr_mode))
+ upper_bound = force_reg (ptr_mode, upper_bound);
+
+ rtx cond1 = aarch64_gen_compare_reg (GEU, cmpptr, lower_bound);
+ rtx comparison1 = gen_rtx_GEU (ptr_mode, cond1, const0_rtx);
+ rtx failcond = GEN_INT (aarch64_get_condition_code (comparison1)^1);
+ cond = gen_rtx_REG (CCmode, CC_REGNUM);
+ if (ptr_mode == SImode)
+ emit_insn (gen_ccmpsi (cond1, cond, cmpptr, upper_bound, comparison1,
+ failcond));
+ else
+ emit_insn (gen_ccmpdi (cond1, cond, cmpptr, upper_bound, comparison1,
+ failcond));
+ comparison = gen_rtx_GEU (VOIDmode, cond, const0_rtx);
+ }
+
+ rtx_code_label *label = gen_label_rtx ();
+ emit_jump_insn (gen_condjump (comparison, cond, label));
+ emit_move_insn (target, mem);
+ emit_label (label);
+
+ insn_code icode;
+
+ switch (mode)
+ {
+ case QImode: icode = CODE_FOR_nospeculateqi; break;
+ case HImode: icode = CODE_FOR_nospeculatehi; break;
+ case SImode: icode = CODE_FOR_nospeculatesi; break;
+ case DImode: icode = CODE_FOR_nospeculatedi; break;
+ case TImode: icode = CODE_FOR_nospeculateti; break;
+ default:
+ gcc_unreachable ();
+ }
+
+ if (! insn_operand_matches (icode, 4, fail_result))
+ fail_result = force_reg (mode, fail_result);
+
+ emit_insn (GEN_FCN (icode) (tgt2, comparison, cond, target, fail_result));
+
+ if (tgt2 != result)
+ emit_move_insn (result, tgt2);
+
+ return result;
+}
+
/* Target-specific selftests. */
#if CHECKING_P
@@ -15136,6 +15224,9 @@ aarch64_libgcc_floating_mode_supported_p
#undef TARGET_CUSTOM_FUNCTION_DESCRIPTORS
#define TARGET_CUSTOM_FUNCTION_DESCRIPTORS 4
+#undef TARGET_INHIBIT_LOAD_SPECULATION
+#define TARGET_INHIBIT_LOAD_SPECULATION aarch64_inhibit_load_speculation
+
#if CHECKING_P
#undef TARGET_RUN_TARGET_SELFTESTS
#define TARGET_RUN_TARGET_SELFTESTS selftest::aarch64_run_selftests
diff --git a/gcc/config/aarch64/aarch64.md b/gcc/config/aarch64/aarch64.md
index 51368e2..ca91147 100644
--- a/gcc/config/aarch64/aarch64.md
+++ b/gcc/config/aarch64/aarch64.md
@@ -150,6 +150,7 @@
UNSPECV_SET_FPSR ; Represent assign of FPSR content.
UNSPECV_BLOCKAGE ; Represent a blockage
UNSPECV_PROBE_STACK_RANGE ; Represent stack range probing.
+ UNSPECV_NOSPECULATE ; Inhibit speculation
]
)
@@ -5564,6 +5565,33 @@
DONE;
})
+(define_insn "nospeculate<ALLI:mode>"
+ [(set (match_operand:ALLI 0 "register_operand" "=r")
+ (unspec_volatile:ALLI
+ [(match_operator 1 "aarch64_comparison_operator"
+ [(match_operand 2 "cc_register" "") (const_int 0)])
+ (match_operand:ALLI 3 "register_operand" "r")
+ (match_operand:ALLI 4 "aarch64_reg_or_zero" "rZ")]
+ UNSPECV_NOSPECULATE))]
+ ""
+ "csel\\t%<w>0, %<w>3, %<w>4, %M1\;hint\t#0x14\t// CSDB"
+ [(set_attr "type" "csel")
+ (set_attr "length" "8")]
+)
+
+(define_insn "nospeculateti"
+ [(set (match_operand:TI 0 "register_operand" "=r")
+ (unspec_volatile:TI
+ [(match_operator 1 "aarch64_comparison_operator"
+ [(match_operand 2 "cc_register" "") (const_int 0)])
+ (match_operand:TI 3 "register_operand" "r")
+ (match_operand:TI 4 "aarch64_reg_or_zero" "rZ")]
+ UNSPECV_NOSPECULATE))]
+ ""
+ "csel\\t%x0, %x3, %x4, %M1\;csel\\t%H0, %H3, %H4, %M1\;hint\t#0x14\t// CSDB"
+ [(set_attr "type" "csel")
+ (set_attr "length" "12")]
+)
;; AdvSIMD Stuff
(include "aarch64-simd.md")
