[AArch64,v3,4/6] aarch64: Add out-of-line functions for LSE atomics

Message ID 20181101214648.29432-5-richard.henderson@linaro.org
State New
Headers show
Series
  • LSE atomics out-of-line
Related show

Commit Message

Richard Henderson Nov. 1, 2018, 9:46 p.m.
This is the libgcc part of the interface -- providing the functions.
Rationale is provided at the top of libgcc/config/aarch64/lse.S.

	* config/aarch64/lse-init.c: New file.
	* config/aarch64/lse.S: New file.
	* config/aarch64/t-lse: New file.
	* config.host: Add t-lse to all aarch64 tuples.
---
 libgcc/config/aarch64/lse-init.c |  45 ++++++
 libgcc/config.host               |   4 +
 libgcc/config/aarch64/lse.S      | 238 +++++++++++++++++++++++++++++++
 libgcc/config/aarch64/t-lse      |  44 ++++++
 4 files changed, 331 insertions(+)
 create mode 100644 libgcc/config/aarch64/lse-init.c
 create mode 100644 libgcc/config/aarch64/lse.S
 create mode 100644 libgcc/config/aarch64/t-lse

-- 
2.17.2

Patch

diff --git a/libgcc/config/aarch64/lse-init.c b/libgcc/config/aarch64/lse-init.c
new file mode 100644
index 00000000000..03b4e1e8ea8
--- /dev/null
+++ b/libgcc/config/aarch64/lse-init.c
@@ -0,0 +1,45 @@ 
+/* Out-of-line LSE atomics for AArch64 architecture, Init.
+   Copyright (C) 2018 Free Software Foundation, Inc.
+   Contributed by Linaro Ltd.
+
+This file is part of GCC.
+
+GCC is free software; you can redistribute it and/or modify it under
+the terms of the GNU General Public License as published by the Free
+Software Foundation; either version 3, or (at your option) any later
+version.
+
+GCC is distributed in the hope that it will be useful, but WITHOUT ANY
+WARRANTY; without even the implied warranty of MERCHANTABILITY or
+FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License
+for more details.
+
+Under Section 7 of GPL version 3, you are granted additional
+permissions described in the GCC Runtime Library Exception, version
+3.1, as published by the Free Software Foundation.
+
+You should have received a copy of the GNU General Public License and
+a copy of the GCC Runtime Library Exception along with this program;
+see the files COPYING3 and COPYING.RUNTIME respectively.  If not, see
+<http://www.gnu.org/licenses/>.  */
+
+/* Define the symbol gating the LSE implementations.  */
+extern _Bool __aa64_have_atomics
+    __attribute__((visibility("hidden"), nocommon));
+
+/* Disable initialization of __aa64_have_atomics during bootstrap.  */
+#ifndef inhibit_libc
+# include <sys/auxv.h>
+
+/* Disable initialization if the system headers are too old.  */
+# if defined(AT_HWCAP) && defined(HWCAP_ATOMICS)
+
+static void __attribute__((constructor))
+init_have_atomics (void)
+{
+  unsigned long hwcap = getauxval (AT_HWCAP);
+  __aa64_have_atomics = (hwcap & HWCAP_ATOMICS) != 0;
+}
+
+# endif /* HWCAP */
+#endif /* inhibit_libc */
diff --git a/libgcc/config.host b/libgcc/config.host
index 029f6569caf..7e9a8b6bc8f 100644
--- a/libgcc/config.host
+++ b/libgcc/config.host
@@ -340,23 +340,27 @@  aarch64*-*-elf | aarch64*-*-rtems*)
 	extra_parts="$extra_parts crtbegin.o crtend.o crti.o crtn.o"
 	extra_parts="$extra_parts crtfastmath.o"
 	tmake_file="${tmake_file} ${cpu_type}/t-aarch64"
+	tmake_file="${tmake_file} ${cpu_type}/t-lse t-slibgcc-libgcc"
 	tmake_file="${tmake_file} ${cpu_type}/t-softfp t-softfp t-crtfm"
 	md_unwind_header=aarch64/aarch64-unwind.h
 	;;
 aarch64*-*-freebsd*)
 	extra_parts="$extra_parts crtfastmath.o"
 	tmake_file="${tmake_file} ${cpu_type}/t-aarch64"
+	tmake_file="${tmake_file} ${cpu_type}/t-lse t-slibgcc-libgcc"
 	tmake_file="${tmake_file} ${cpu_type}/t-softfp t-softfp t-crtfm"
 	md_unwind_header=aarch64/freebsd-unwind.h
 	;;
 aarch64*-*-fuchsia*)
 	tmake_file="${tmake_file} ${cpu_type}/t-aarch64"
+	tmake_file="${tmake_file} ${cpu_type}/t-lse t-slibgcc-libgcc"
 	tmake_file="${tmake_file} ${cpu_type}/t-softfp t-softfp"
 	;;
 aarch64*-*-linux*)
 	extra_parts="$extra_parts crtfastmath.o"
 	md_unwind_header=aarch64/linux-unwind.h
 	tmake_file="${tmake_file} ${cpu_type}/t-aarch64"
+	tmake_file="${tmake_file} ${cpu_type}/t-lse t-slibgcc-libgcc"
 	tmake_file="${tmake_file} ${cpu_type}/t-softfp t-softfp t-crtfm"
 	;;
 alpha*-*-linux*)
diff --git a/libgcc/config/aarch64/lse.S b/libgcc/config/aarch64/lse.S
new file mode 100644
index 00000000000..3e42a6569af
--- /dev/null
+++ b/libgcc/config/aarch64/lse.S
@@ -0,0 +1,238 @@ 
+/* Out-of-line LSE atomics for AArch64 architecture.
+   Copyright (C) 2018 Free Software Foundation, Inc.
+   Contributed by Linaro Ltd.
+
+This file is part of GCC.
+
+GCC is free software; you can redistribute it and/or modify it under
+the terms of the GNU General Public License as published by the Free
+Software Foundation; either version 3, or (at your option) any later
+version.
+
+GCC is distributed in the hope that it will be useful, but WITHOUT ANY
+WARRANTY; without even the implied warranty of MERCHANTABILITY or
+FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License
+for more details.
+
+Under Section 7 of GPL version 3, you are granted additional
+permissions described in the GCC Runtime Library Exception, version
+3.1, as published by the Free Software Foundation.
+
+You should have received a copy of the GNU General Public License and
+a copy of the GCC Runtime Library Exception along with this program;
+see the files COPYING3 and COPYING.RUNTIME respectively.  If not, see
+<http://www.gnu.org/licenses/>.  */
+
+/*
+ * The problem that we are trying to solve is operating system deployment
+ * of ARMv8.1-Atomics, also known as Large System Exensions (LSE).
+ *
+ * There are a number of potential solutions for this problem which have
+ * been proposed and rejected for various reasons.  To recap:
+ *
+ * (1) Multiple builds.  The dynamic linker will examine /lib64/atomics/
+ * if HWCAP_ATOMICS is set, allowing entire libraries to be overwritten.
+ * However, not all Linux distributions are happy with multiple builds,
+ * and anyway it has no effect on main applications.
+ *
+ * (2) IFUNC.  We could put these functions into libgcc_s.so, and have
+ * a single copy of each function for all DSOs.  However, ARM is concerned
+ * that the branch-to-indirect-branch that is implied by using a PLT,
+ * as required by IFUNC, is too much overhead for smaller cpus.
+ *
+ * (3) Statically predicted direct branches.  This is the approach that
+ * is taken here.  These functions are linked into every DSO that uses them.
+ * All of the symbols are hidden, so that the functions are called via a
+ * direct branch.  The choice of LSE vs non-LSE is done via one byte load
+ * followed by a well-predicted direct branch.  The functions are compiled
+ * separately to minimize code size.
+ */
+
+/* Tell the assembler to accept LSE instructions.  */
+	.arch armv8-a+lse
+
+/* Declare the symbol gating the LSE implementations.  */
+	.hidden	__aa64_have_atomics
+
+/* Turn size and memory model defines into mnemonic fragments.  */
+#if SIZE == 1
+# define S     b
+# define MASK  , uxtb
+#elif SIZE == 2
+# define S     h
+# define MASK  , uxth
+#elif SIZE == 4 || SIZE == 8 || SIZE == 16
+# define S
+# define MASK
+#else
+# error
+#endif
+
+#if MODEL == 1
+# define SUFF  _relax
+# define A
+# define L
+#elif MODEL == 2
+# define SUFF  _acq
+# define A     a
+# define L
+#elif MODEL == 3
+# define SUFF  _rel
+# define A
+# define L     l
+#elif MODEL == 4
+# define SUFF  _acq_rel
+# define A     a
+# define L     l
+#else
+# error
+#endif
+
+/* Concatenate symbols.  */
+#define glue2_(A, B)		A ## B
+#define glue2(A, B)		glue2_(A, B)
+#define glue3_(A, B, C)		A ## B ## C
+#define glue3(A, B, C)		glue3_(A, B, C)
+#define glue4_(A, B, C, D)	A ## B ## C ## D
+#define glue4(A, B, C, D)	glue4_(A, B, C, D)
+
+/* Select the size of a register, given a regno.  */
+#define x(N)			glue2(x, N)
+#define w(N)			glue2(w, N)
+#if SIZE < 8
+# define s(N)			w(N)
+#else
+# define s(N)			x(N)
+#endif
+
+#define NAME(BASE)		glue4(__aa64_, BASE, SIZE, SUFF)
+#define LDXR			glue4(ld, A, xr, S)
+#define STXR			glue4(st, L, xr, S)
+
+/* Temporary registers used.  Other than these, only the return value
+   register (x0) and the flags are modified.  */
+#define tmp0	16
+#define tmp1	17
+#define tmp2	15
+
+/* Start and end a function.  */
+.macro	STARTFN name
+	.text
+	.balign	16
+	.globl	\name
+	.hidden	\name
+	.type	\name, %function
+\name:
+.endm
+
+.macro	ENDFN name
+	.size	\name, . - \name
+.endm
+
+/* Branch to LABEL if LSE is enabled.
+   The branch should be easily predicted, in that it will, after constructors,
+   always branch the same way.  The expectation is that systems that implement
+   ARMv8.1-Atomics are "beefier" than those that omit the extension.
+   By arranging for the fall-through path to use load-store-exclusive insns,
+   we aid the branch predictor of the smallest cpus.  */
+.macro	JUMP_IF_LSE label
+	adrp	x(tmp0), __aa64_have_atomics
+	ldrb	w(tmp0), [x(tmp0), :lo12:__aa64_have_atomics]
+	cbnz	w(tmp0), \label
+.endm
+
+#ifdef L_cas
+
+STARTFN	NAME(cas)
+	JUMP_IF_LSE	8f
+
+#if SIZE < 16
+#define CAS	glue4(cas, A, L, S)
+
+	mov		s(tmp0), s(0)
+0:	LDXR		s(0), [x2]
+	cmp		s(0), s(tmp0) MASK
+	bne		1f
+	STXR		w(tmp1), s(1), [x2]
+	cbnz		w(tmp1), 0b
+1:	ret
+
+8:	CAS		w(0), w(1), [x2]
+	ret
+
+#else
+#define LDXP	glue3(ld, A, xp)
+#define STXP	glue3(st, L, xp)
+#define CASP	glue3(casp, A, L)
+
+	mov		x(tmp0), x0
+	mov		x(tmp1), x1
+0:	LDXP		x0, x1, [x4]
+	cmp		x0, x(tmp0)
+	ccmp		x1, x(tmp1), #0, eq
+	bne		1f
+	STXP		w(tmp2), x(tmp0), x(tmp1), [x4]
+	cbnz		w(tmp2), 0b
+1:	ret
+
+8:	CASP		x0, x1, x2, x3, [x4]
+	ret
+
+#endif
+
+ENDFN	NAME(cas)
+#endif
+
+#ifdef L_swp
+#define SWP	glue4(swp, A, L, S)
+
+STARTFN	NAME(swp)
+	JUMP_IF_LSE	8f
+
+	mov		s(tmp0), s(0)
+0:	LDXR		s(0), [x1]
+	STXR		w(tmp1), s(tmp0), [x1]
+	cbnz		w(tmp1), 0b
+	ret
+
+8:	SWP		w(0), w(0), [x1]
+	ret
+
+ENDFN	NAME(swp)
+#endif
+
+#if defined(L_ldadd) || defined(L_ldclr) \
+    || defined(L_ldeor) || defined(L_ldset)
+
+#ifdef L_ldadd
+#define LDNM	ldadd
+#define OP	add
+#elif defined(L_ldclr)
+#define LDNM	ldclr
+#define OP	bic
+#elif defined(L_ldeor)
+#define LDNM	ldeor
+#define OP	eor
+#elif defined(L_ldset)
+#define LDNM	ldset
+#define OP	orr
+#else
+#error
+#endif
+#define LDOP	glue4(LDNM, A, L, S)
+
+STARTFN	NAME(LDNM)
+	JUMP_IF_LSE	8f
+
+	mov		s(tmp0), s(0)
+0:	LDXR		s(0), [x1]
+	OP		s(tmp1), s(0), s(tmp0)
+	STXR		w(tmp1), s(tmp1), [x1]
+	cbnz		w(tmp1), 0b
+	ret
+
+8:	LDOP		s(0), s(0), [x1]
+	ret
+
+ENDFN	NAME(LDNM)
+#endif
diff --git a/libgcc/config/aarch64/t-lse b/libgcc/config/aarch64/t-lse
new file mode 100644
index 00000000000..c7f4223cd45
--- /dev/null
+++ b/libgcc/config/aarch64/t-lse
@@ -0,0 +1,44 @@ 
+# Out-of-line LSE atomics for AArch64 architecture.
+# Copyright (C) 2018 Free Software Foundation, Inc.
+# Contributed by Linaro Ltd.
+#
+# This file is part of GCC.
+#
+# GCC is free software; you can redistribute it and/or modify it
+# under the terms of the GNU General Public License as published by
+# the Free Software Foundation; either version 3, or (at your option)
+# any later version.
+#
+# GCC is distributed in the hope that it will be useful, but
+# WITHOUT ANY WARRANTY; without even the implied warranty of
+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+# General Public License for more details.
+#
+# You should have received a copy of the GNU General Public License
+# along with GCC; see the file COPYING3.  If not see
+# <http://www.gnu.org/licenses/>.
+
+# Compare-and-swap has 5 sizes and 4 memory models.
+S0 := $(foreach s, 1 2 4 8 16, $(addsuffix _$(s), cas))
+O0 := $(foreach m, 1 2 3 4, $(addsuffix _$(m)$(objext), $(S0)))
+
+# Swap, Load-and-operate have 4 sizes and 4 memory models
+S1 := $(foreach s, 1 2 4 8, $(addsuffix _$(s), swp ldadd ldclr ldeor ldset))
+O1 := $(foreach m, 1 2 3 4, $(addsuffix _$(m)$(objext), $(S1)))
+
+LSE_OBJS := $(O0) $(O1)
+
+libgcc-objects += $(LSE_OBJS) lse-init$(objext)
+
+empty      =
+space      = $(empty) $(empty)
+PAT_SPLIT  = $(subst _,$(space),$(*F))
+PAT_BASE   = $(word 1,$(PAT_SPLIT))
+PAT_N      = $(word 2,$(PAT_SPLIT))
+PAT_M      = $(word 3,$(PAT_SPLIT))
+
+lse-init$(objext): $(srcdir)/config/aarch64/lse-init.c
+	$(gcc_compile) -c $<
+
+$(LSE_OBJS): $(srcdir)/config/aarch64/lse.S
+	$(gcc_compile) -DL_$(PAT_BASE) -DSIZE=$(PAT_N) -DMODEL=$(PAT_M) -c $<