Don't expand UNSPEC_TLS_LD_BASE to a call so that the RTL local copy
propagation pass can eliminate multiple __tls_get_addr calls.
gcc/
PR target/81501
* config/i386/i386-protos.h (ix86_split_tls_local_dynamic_base_64):
New.
* config/i386/i386.cc (ix86_split_tls_local_dynamic_base_64): New.
(legitimize_tls_address): Don't emit the 64-bit UNSPEC_TLS_LD_BASE
as a call.
* config/i386/i386.md (*tls_local_dynamic_base_64_<mode>): Renamed
to ...
(@tls_local_dynamic_base_call_64_<mode>): This. Replace
(match_operand 2) with (const_int 0).
(@tls_local_dynamic_base_64_<mode>): Change call to unspec.
(*tls_local_dynamic_base_64_<mode>): New.
gcc/testsuite/
PR target/81501
* gcc.target/i386/pr81501-1.c: New test.
OK for master?
Thanks.
--
H.J.
From d154b3bf2fb86c82a6291f1fae45fbbe0d74f4e4 Mon Sep 17 00:00:00 2001
From: "H.J. Lu" <hjl.to...@gmail.com>
Date: Fri, 19 Aug 2022 11:50:41 -0700
Subject: [PATCH] x86-64: Don't expand UNSPEC_TLS_LD_BASE to a call
Don't expand UNSPEC_TLS_LD_BASE to a call so that the RTL local copy
propagation pass can eliminate multiple __tls_get_addr calls.
gcc/
PR target/81501
* config/i386/i386-protos.h (ix86_split_tls_local_dynamic_base_64):
New.
* config/i386/i386.cc (ix86_split_tls_local_dynamic_base_64): New.
(legitimize_tls_address): Don't emit the 64-bit UNSPEC_TLS_LD_BASE
as a call.
* config/i386/i386.md (*tls_local_dynamic_base_64_<mode>): Renamed
to ...
(@tls_local_dynamic_base_call_64_<mode>): This. Replace
(match_operand 2) with (const_int 0).
(@tls_local_dynamic_base_64_<mode>): Change call to unspec.
(*tls_local_dynamic_base_64_<mode>): New.
gcc/testsuite/
PR target/81501
* gcc.target/i386/pr81501-1.c: New test.
Signed-off-by: H.J. Lu <hjl.to...@gmail.com>
---
gcc/config/i386/i386-protos.h | 1 +
gcc/config/i386/i386.cc | 42 +++++++++++++----------
gcc/config/i386/i386.md | 30 +++++++++++-----
gcc/testsuite/gcc.target/i386/pr81501-1.c | 17 +++++++++
4 files changed, 63 insertions(+), 27 deletions(-)
create mode 100644 gcc/testsuite/gcc.target/i386/pr81501-1.c
diff --git a/gcc/config/i386/i386-protos.h b/gcc/config/i386/i386-protos.h
index c59b5a67e3a..a8850cd7311 100644
--- a/gcc/config/i386/i386-protos.h
+++ b/gcc/config/i386/i386-protos.h
@@ -287,6 +287,7 @@ extern rtx ix86_tls_module_base (void);
extern bool ix86_gpr_tls_address_pattern_p (rtx);
extern bool ix86_tls_address_pattern_p (rtx);
extern rtx ix86_rewrite_tls_address (rtx);
+extern void ix86_split_tls_local_dynamic_base_64 (rtx[]);
extern void ix86_expand_vector_init (bool, rtx, rtx);
extern void ix86_expand_vector_set (bool, rtx, rtx, int);
diff --git a/gcc/config/i386/i386.cc b/gcc/config/i386/i386.cc
index ddefc0f88d9..9ad11b122de 100644
--- a/gcc/config/i386/i386.cc
+++ b/gcc/config/i386/i386.cc
@@ -12330,6 +12330,27 @@ ix86_tls_module_base (void)
return ix86_tls_module_base_symbol;
}
+/* Split to CALL INSN to properly handle scratch registers. */
+
+void
+ix86_split_tls_local_dynamic_base_64 (rtx operands[])
+{
+ rtx rax = gen_rtx_REG (Pmode, AX_REG);
+ rtx_insn *call_insn
+ = emit_call_insn (gen_tls_local_dynamic_base_call_64 (Pmode, rax,
+ operands[1]));
+ /* Indicate that this function can't jump to non-local gotos. */
+ make_reg_eh_region_note_nothrow_nononlocal (call_insn);
+ RTL_CONST_CALL_P (call_insn) = 1;
+
+ /* Attach a unique REG_EQUAL, to allow the RTL optimizers to share
+ the LD_BASE result with other LD model accesses. */
+ rtx eqv = gen_rtx_UNSPEC (Pmode, gen_rtvec (1, const0_rtx),
+ UNSPEC_TLS_LD_BASE);
+ rtx_insn *set_insn = emit_move_insn (operands[0], rax);
+ set_unique_reg_note (set_insn, REG_EQUAL, eqv);
+}
+
/* A subroutine of ix86_legitimize_address and ix86_expand_move. FOR_MOV is
false if we expect this to be used for a memory address and true if
we expect to load the address into a register. */
@@ -12442,25 +12463,8 @@ legitimize_tls_address (rtx x, enum tls_model model, bool for_mov)
base = gen_reg_rtx (Pmode);
if (TARGET_64BIT)
- {
- rtx rax = gen_rtx_REG (Pmode, AX_REG);
- rtx_insn *insns;
- rtx eqv;
-
- start_sequence ();
- emit_call_insn
- (gen_tls_local_dynamic_base_64 (Pmode, 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);
-
- RTL_CONST_CALL_P (insns) = 1;
- emit_libcall_block (insns, base, rax, eqv);
- }
+ emit_insn (gen_tls_local_dynamic_base_64 (Pmode, base,
+ caddr));
else
emit_insn (gen_tls_local_dynamic_base_32 (base, pic, caddr));
}
diff --git a/gcc/config/i386/i386.md b/gcc/config/i386/i386.md
index e170da3b0e6..cf54a58ef96 100644
--- a/gcc/config/i386/i386.md
+++ b/gcc/config/i386/i386.md
@@ -23102,11 +23102,11 @@ (define_expand "tls_local_dynamic_base_32"
""
"ix86_tls_descriptor_calls_expanded_in_cfun = true;")
-(define_insn "*tls_local_dynamic_base_64_<mode>"
+(define_insn "@tls_local_dynamic_base_call_64_<mode>"
[(set (match_operand:P 0 "register_operand" "=a")
(call:P
(mem:QI (match_operand 1 "constant_call_address_operand" "Bz"))
- (match_operand 2)))
+ (const_int 0)))
(unspec:P [(reg:P SP_REG)] UNSPEC_TLS_LD_BASE)]
"TARGET_64BIT"
{
@@ -23143,15 +23143,29 @@ (define_insn "*tls_local_dynamic_base_64_largepic"
(set_attr "length" "22")])
(define_expand "@tls_local_dynamic_base_64_<mode>"
- [(parallel
- [(set (match_operand:P 0 "register_operand")
- (call:P
- (mem:QI (match_operand 1))
- (const_int 0)))
- (unspec:P [(reg:P SP_REG)] UNSPEC_TLS_LD_BASE)])]
+ [(set (match_operand:P 0 "register_operand")
+ (unspec:P
+ [(match_operand 1 "constant_call_address_operand")
+ (reg:P SP_REG)]
+ UNSPEC_TLS_LD_BASE))]
"TARGET_64BIT"
"ix86_tls_descriptor_calls_expanded_in_cfun = true;")
+;; Split to CALL INSN to properly handle scratch registers.
+(define_insn_and_split "*tls_local_dynamic_base_64_<mode>"
+ [(set (match_operand:P 0 "register_operand")
+ (unspec:P
+ [(match_operand 1 "constant_call_address_operand")
+ (reg:P SP_REG)]
+ UNSPEC_TLS_LD_BASE))]
+ "TARGET_64BIT && ix86_pre_reload_split ()"
+ "#"
+ ""
+ [(const_int 0)]
+{
+ ix86_split_tls_local_dynamic_base_64 (operands);
+})
+
;; Local dynamic of a single variable is a lose. Show combine how
;; to convert that back to global dynamic.
diff --git a/gcc/testsuite/gcc.target/i386/pr81501-1.c b/gcc/testsuite/gcc.target/i386/pr81501-1.c
new file mode 100644
index 00000000000..96d593c3e6d
--- /dev/null
+++ b/gcc/testsuite/gcc.target/i386/pr81501-1.c
@@ -0,0 +1,17 @@
+/* { dg-do compile { target { *-*-linux* && { ! ia32 } } } } */
+/* { dg-options "-O2 -fpic -fplt" } */
+
+void a(long *);
+int b(void);
+void c(void);
+static __thread long e;
+long
+d(void)
+{
+ a(&e);
+ if (b())
+ c();
+ return e;
+}
+
+/* { dg-final { scan-assembler-times "call\[ \t\]__tls_get_addr@PLT" 1 } } */
--
2.49.0
