From: "Ard Biesheuvel" <ard.biesheuvel@arm.com>
To: devel@edk2.groups.io
Cc: glin@suse.com, leif@nuviainc.com, lersek@redhat.com,
liming.gao@intel.com, Ard Biesheuvel <ard.biesheuvel@arm.com>
Subject: [PATCH v2] ArmPkg/CompilerIntrinsicsLib: provide atomics intrinsics
Date: Wed, 20 May 2020 13:44:48 +0200 [thread overview]
Message-ID: <20200520114448.26104-1-ard.biesheuvel@arm.com> (raw)
Gary reports the GCC 10 will emit calls to atomics intrinsics routines
unless -mno-outline-atomics is specified. This means GCC-10 introduces
new intrinsics, and even though it would be possible to work around this
by specifying the command line option, this would require a new GCC10
toolchain profile to be created, which we prefer to avoid.
So instead, add the new intrinsics to our library so they are provided
when necessary.
Signed-off-by: Ard Biesheuvel <ard.biesheuvel@arm.com>
---
v2:
- add missing .globl to export the functions from the object file
- add function end markers so the size of each is visible in the ELF metadata
- add some comments to describe what is going on
ArmPkg/Library/CompilerIntrinsicsLib/CompilerIntrinsicsLib.inf | 3 +
ArmPkg/Library/CompilerIntrinsicsLib/AArch64/Atomics.S | 142 ++++++++++++++++++++
2 files changed, 145 insertions(+)
diff --git a/ArmPkg/Library/CompilerIntrinsicsLib/CompilerIntrinsicsLib.inf b/ArmPkg/Library/CompilerIntrinsicsLib/CompilerIntrinsicsLib.inf
index d5bad9467758..fcf48c678119 100644
--- a/ArmPkg/Library/CompilerIntrinsicsLib/CompilerIntrinsicsLib.inf
+++ b/ArmPkg/Library/CompilerIntrinsicsLib/CompilerIntrinsicsLib.inf
@@ -79,6 +79,9 @@ [Sources.ARM]
Arm/ldivmod.asm | MSFT
Arm/llsr.asm | MSFT
+[Sources.AARCH64]
+ AArch64/Atomics.S | GCC
+
[Packages]
MdePkg/MdePkg.dec
ArmPkg/ArmPkg.dec
diff --git a/ArmPkg/Library/CompilerIntrinsicsLib/AArch64/Atomics.S b/ArmPkg/Library/CompilerIntrinsicsLib/AArch64/Atomics.S
new file mode 100644
index 000000000000..dc61d6bb8e52
--- /dev/null
+++ b/ArmPkg/Library/CompilerIntrinsicsLib/AArch64/Atomics.S
@@ -0,0 +1,142 @@
+#------------------------------------------------------------------------------
+#
+# Copyright (c) 2020, Arm, Limited. All rights reserved.<BR>
+#
+# SPDX-License-Identifier: BSD-2-Clause-Patent
+#
+#------------------------------------------------------------------------------
+
+ /*
+ * Provide the GCC intrinsics that are required when using GCC 9 or
+ * later with the -moutline-atomics options (which became the default
+ * in GCC 10)
+ */
+ .arch armv8-a
+
+ .macro reg_alias, pfx, sz
+ r0_\sz .req \pfx\()0
+ r1_\sz .req \pfx\()1
+ tmp0_\sz .req \pfx\()16
+ tmp1_\sz .req \pfx\()17
+ .endm
+
+ /*
+ * Define register aliases of the right type for each size
+ * (xN for 8 bytes, wN for everything smaller)
+ */
+ reg_alias w, 1
+ reg_alias w, 2
+ reg_alias w, 4
+ reg_alias x, 8
+
+ .macro fn_start, name:req
+ .section .text.\name
+ .globl \name
+ .type \name, %function
+\name\():
+ .endm
+
+ .macro fn_end, name:req
+ .size \name, . - \name
+ .endm
+
+ /*
+ * Emit an atomic helper for \model with operands of size \sz, using
+ * the operation specified by \insn (which is the LSE name), and which
+ * can be implemented using the generic load-locked/store-conditional
+ * (LL/SC) sequence below, using the arithmetic operation given by
+ * \opc.
+ */
+ .macro emit_ld_sz, sz:req, insn:req, opc:req, model:req, s, a, l
+ fn_start __aarch64_\insn\()\sz\()\model
+ mov tmp0_\sz, r0_\sz
+0: ld\a\()xr\s r0_\sz, [x1]
+ .ifnc \insn, swp
+ \opc tmp1_\sz, r0_\sz, tmp0_\sz
+ .else
+ \opc tmp1_\sz, tmp0_\sz
+ .endif
+ st\l\()xr\s w15, tmp1_\sz, [x1]
+ cbnz w15, 0b
+ ret
+ fn_end __aarch64_\insn\()\sz\()\model
+ .endm
+
+ /*
+ * Emit atomic helpers for \model for operand sizes in the
+ * set {1, 2, 4, 8}, for the instruction pattern given by
+ * \insn. (This is the LSE name, but this implementation uses
+ * the generic LL/SC sequence using \opc as the arithmetic
+ * operation on the target.)
+ */
+ .macro emit_ld, insn:req, opc:req, model:req, a, l
+ emit_ld_sz 1, \insn, \opc, \model, b, \a, \l
+ emit_ld_sz 2, \insn, \opc, \model, h, \a, \l
+ emit_ld_sz 4, \insn, \opc, \model, , \a, \l
+ emit_ld_sz 8, \insn, \opc, \model, , \a, \l
+ .endm
+
+ /*
+ * Emit the compare and swap helper for \model and size \sz
+ * using LL/SC instructions.
+ */
+ .macro emit_cas_sz, sz:req, model:req, uxt:req, s, a, l
+ fn_start __aarch64_cas\sz\()\model
+ \uxt tmp0_\sz, r0_\sz
+0: ld\a\()xr\s r0_\sz, [x2]
+ cmp r0_\sz, tmp0_\sz
+ bne 1f
+ st\l\()xr\s w15, r1_\sz, [x2]
+ cbnz w15, 0b
+1: ret
+ fn_end __aarch64_cas\sz\()\model
+ .endm
+
+ /*
+ * Emit compare-and-swap helpers for \model for operand sizes in the
+ * set {1, 2, 4, 8, 16}.
+ */
+ .macro emit_cas, model:req, a, l
+ emit_cas_sz 1, \model, uxtb, b, \a, \l
+ emit_cas_sz 2, \model, uxth, h, \a, \l
+ emit_cas_sz 4, \model, mov , , \a, \l
+ emit_cas_sz 8, \model, mov , , \a, \l
+
+ /*
+ * We cannot use the parameterized sequence for 16 byte CAS, so we
+ * need to define it explicitly.
+ */
+ fn_start __aarch64_cas16\model
+ mov x16, x0
+ mov x17, x1
+0: ld\a\()xp x0, x1, [x4]
+ cmp x0, x16
+ ccmp x1, x17, #0, eq
+ bne 1f
+ st\l\()xp w15, x16, x17, [x4]
+ cbnz w15, 0b
+1: ret
+ fn_end __aarch64_cas16\model
+ .endm
+
+ /*
+ * Emit the set of GCC outline atomic helper functions for
+ * the memory ordering model given by \model:
+ * - relax unordered loads and stores
+ * - acq load-acquire, unordered store
+ * - rel unordered load, store-release
+ * - acq_rel load-acquire, store-release
+ */
+ .macro emit_model, model:req, a, l
+ emit_ld ldadd, add, \model, \a, \l
+ emit_ld ldclr, bic, \model, \a, \l
+ emit_ld ldeor, eor, \model, \a, \l
+ emit_ld ldset, orr, \model, \a, \l
+ emit_ld swp, mov, \model, \a, \l
+ emit_cas \model, \a, \l
+ .endm
+
+ emit_model _relax
+ emit_model _acq, a
+ emit_model _rel,, l
+ emit_model _acq_rel, a, l
--
2.17.1
next reply other threads:[~2020-05-20 11:45 UTC|newest]
Thread overview: 25+ messages / expand[flat|nested] mbox.gz Atom feed top
2020-05-20 11:44 Ard Biesheuvel [this message]
2020-05-20 12:37 ` [edk2-devel] [PATCH v2] ArmPkg/CompilerIntrinsicsLib: provide atomics intrinsics Philippe Mathieu-Daudé
2020-05-21 16:40 ` Philippe Mathieu-Daudé
2020-05-21 16:45 ` Ard Biesheuvel
2020-05-21 16:59 ` Philippe Mathieu-Daudé
2020-05-21 17:02 ` Ard Biesheuvel
2020-05-21 17:07 ` Philippe Mathieu-Daudé
2020-05-20 15:59 ` Laszlo Ersek
2020-05-21 11:23 ` Leif Lindholm
2020-05-21 12:58 ` [edk2-devel] " Ard Biesheuvel
2020-05-21 13:16 ` Leif Lindholm
2020-05-21 13:31 ` Ard Biesheuvel
2020-05-21 14:16 ` Leif Lindholm
2020-05-21 20:22 ` Laszlo Ersek
2020-05-22 8:16 ` Ard Biesheuvel
2020-05-22 10:54 ` Leif Lindholm
2020-05-22 13:27 ` Ard Biesheuvel
2020-05-22 19:04 ` Laszlo Ersek
2020-06-02 0:50 ` Liming Gao
2020-06-02 7:09 ` Ard Biesheuvel
2020-05-28 1:36 ` Gary Lin
2020-05-28 9:49 ` Leif Lindholm
2020-05-28 15:48 ` Liming Gao
2020-05-28 20:09 ` Laszlo Ersek
2020-05-29 3:04 ` Liming Gao
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-list from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20200520114448.26104-1-ard.biesheuvel@arm.com \
--to=devel@edk2.groups.io \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox