Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 2620:137:e000::1:20 as permitted sender) client-ip=2620:137:e000::1:20;
Message-ID: <55e9722e962a3fe535f63206ac169538f902d0f2.camel@xry111.site>
Subject: [PATCH v4 3/4] LoongArch: Remove -fplt and -Wa,-mla-* from CFLAGS
From:   Xi Ruoyao <xry111@xry111.site>
To:     loongarch@lists.linux.dev
Cc:     linux-kernel@vger.kernel.org, WANG Xuerui <kernel@xen0n.name>,
        Huacai Chen <chenhuacai@kernel.org>,
        Youling Tang <tangyouling@loongson.cn>,
        Jinyang He <hejinyang@loongson.cn>
Date:   Fri, 29 Jul 2022 16:41:32 +0800
In-Reply-To: <32a74a218c76611f897fd1df1ad0059068621133.camel@xry111.site>
References: <32a74a218c76611f897fd1df1ad0059068621133.camel@xry111.site>
Content-Type: text/plain; charset="UTF-8"
Content-Transfer-Encoding: quoted-printable
User-Agent: Evolution 3.44.3 
MIME-Version: 1.0
Precedence: bulk

-fplt is the default of all supported compilers (GCC, and maybe Clang in
the future), so it needs not to be explicitly specified.

-Wa,-mla-* options were used to prevent the assembler from generating
GOT accesses for "la.local" and "la.global" macros.  But GCC >=3D 13 will
generate GOT access explicitly without use of these macros by default if
the assembler supports explicit specification for relocations.  And,
it's not recommended to override the default as the use of assembler
macros may limit optimization.

Now we can handle GOT and GOT-based relocations properly, so we can
remove these options and use GOT access for both GCC 12 and 13
(or newer).

GAS <=3D 2.39 does not support "la.got [reg], [sym] + [offset]" with a
non-zero offset.  So in the assembly code we explicitly use "la.pcrel"
instead of "la" (now defaulted to "la.got") where a PC-relative
addressing is suitable, in order to work around this limitation and keep
the compatibility with old toolchains.

Signed-off-by: Xi Ruoyao <xry111@xry111.site>
---
 arch/loongarch/Makefile      |  4 ----
 arch/loongarch/kernel/head.S | 10 +++++-----
 2 files changed, 5 insertions(+), 9 deletions(-)

diff --git a/arch/loongarch/Makefile b/arch/loongarch/Makefile
index 039dcc4fe1f3..800349ea9310 100644
--- a/arch/loongarch/Makefile
+++ b/arch/loongarch/Makefile
@@ -40,10 +40,6 @@ endif
=20
 cflags-y			+=3D -G0 -pipe -msoft-float
 LDFLAGS_vmlinux			+=3D -G0 -static -n -nostdlib
-KBUILD_AFLAGS_KERNEL		+=3D -Wa,-mla-global-with-pcrel
-KBUILD_CFLAGS_KERNEL		+=3D -Wa,-mla-global-with-pcrel
-KBUILD_AFLAGS_MODULE		+=3D -Wa,-mla-global-with-abs
-KBUILD_CFLAGS_MODULE		+=3D -fplt -Wa,-mla-global-with-abs,-mla-local-with-=
abs
=20
 cflags-y +=3D -ffreestanding
 cflags-y +=3D $(call cc-option, -mno-check-zero-division)
diff --git a/arch/loongarch/kernel/head.S b/arch/loongarch/kernel/head.S
index 74ea7bf6c8d6..193329ed6e8c 100644
--- a/arch/loongarch/kernel/head.S
+++ b/arch/loongarch/kernel/head.S
@@ -60,17 +60,17 @@ SYM_CODE_START(kernel_entry)			# kernel entry point
 	la.abs		t0, 0f
 	jirl		zero, t0, 0
 0:
-	la		t0, __bss_start		# clear .bss
+	la.pcrel	t0, __bss_start		# clear .bss
 	st.d		zero, t0, 0
-	la		t1, __bss_stop - LONGSIZE
+	la.pcrel	t1, __bss_stop - LONGSIZE
 1:
 	addi.d		t0, t0, LONGSIZE
 	st.d		zero, t0, 0
 	bne		t0, t1, 1b
=20
-	la		t0, fw_arg0
+	la.pcrel	t0, fw_arg0
 	st.d		a0, t0, 0		# firmware arguments
-	la		t0, fw_arg1
+	la.pcrel	t0, fw_arg1
 	st.d		a1, t0, 0
=20
 	/* KSave3 used for percpu base, initialized as 0 */
@@ -78,7 +78,7 @@ SYM_CODE_START(kernel_entry)			# kernel entry point
 	/* GPR21 used for percpu base (runtime), initialized as 0 */
 	or		u0, zero, zero
=20
-	la		tp, init_thread_union
+	la.pcrel	tp, init_thread_union
 	/* Set the SP after an empty pt_regs.  */
 	PTR_LI		sp, (_THREAD_SIZE - 32 - PT_SIZE)
 	PTR_ADD		sp, sp, tp
--=20
2.37.0