[U-Boot] [PATCH 01/12] arm: config: Introduce CONFIG_SYS_ARM_ARCH

[U-Boot] [PATCH 01/12] arm: config: Introduce CONFIG_SYS_ARM_ARCH

[Marek Vasut]

Introduce new helper Kconfig option, which is automatically set to
the version of ARM architecture for which the U-Boot is built. This
is useful when selecting tuning options in the libgcc imported from
Linux kernel.

Signed-off-by: Marek Vasut <marex@denx.de>
Cc: Albert Aribaud <albert.u.boot@aribaud.net>
Cc: Masahiro Yamada <yamada.masahiro@socionext.com>
Cc: Simon Glass <sjg@chromium.org>
Cc: Tom Rini <trini@konsulko.com>
---
 arch/arm/Kconfig | 14 ++++++++++++++
 1 file changed, 14 insertions(+)

diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig
index 729b181..b71c2bb 100644
--- a/arch/arm/Kconfig
+++ b/arch/arm/Kconfig
@@ -64,6 +64,20 @@ config SYS_CPU
         default "sa1100" if CPU_SA1100
 	default "armv8" if ARM64
 
+config SYS_ARM_ARCH
+	int
+	default 4 if CPU_ARM720T
+	default 4 if CPU_ARM920T
+	default 5 if CPU_ARM926EJS
+	default 5 if CPU_ARM946ES
+	default 6 if CPU_ARM1136
+	default 6 if CPU_ARM1176
+	default 7 if CPU_V7
+	default 7 if CPU_V7M
+	default 5 if CPU_PXA
+	default 4 if CPU_SA1100
+	default 8 if ARM64
+
 config SEMIHOSTING
 	bool "support boot from semihosting"
 	help
-- 
2.7.0

[U-Boot] [PATCH 02/12] arm: include: Import unified.h from Linux kernel

[Marek Vasut]

Import unified.h from Linux kernel 4.4.6 , commit
0d1912303e54ed1b2a371be0bba51c384dd57326 . This header file contains
macros used in libgcc functions in Linux kernel on ARM and will be
needed for the libgcc sync.

Since unified.h defines the W(instr) macro, we must drop this from
the macro from memcpy.S , otherwise this triggers a warning about
symbol redefinition. In order to keep the changes to unified.h to
the minimum, tweak arch/arm/lib/Makefile such that it defines the
CONFIG_ARM_ASM_UNIFIED macro, which places .syntax unified into all
of the assembler files. This is mandatory.

Moreover, for Thumb2 build, define CONFIG_THUMB2_KERNEL macro if and
only if Thumb2 build is enabled. This macro is checked by unified.h
and toggles between ARM and Thumb2 variant of the instructions in the
assembler source files.

Finally, this patch defines __LINUX_ARM_ARCH__=N macro based on the
new CONFIG_SYS_ARM_ARCH Kconfig option. This macro selects between
more optimal and more dense codepaths which work on armv5 and newer
and less optimal codepaths which work on armv4 and possible armv3m.
Tegra2 needs the same special handling as it does in arch/arm/Makefile
to cater for the arm720t boot core.

Signed-off-by: Marek Vasut <marex@denx.de>
Cc: Albert Aribaud <albert.u.boot@aribaud.net>
Cc: Masahiro Yamada <yamada.masahiro@socionext.com>
Cc: Simon Glass <sjg@chromium.org>
Cc: Tom Rini <trini@konsulko.com>
---
 arch/arm/include/asm/assembler.h |   1 +
 arch/arm/include/asm/unified.h   | 129 +++++++++++++++++++++++++++++++++++++++
 arch/arm/lib/Makefile            |   9 ++-
 arch/arm/lib/memcpy.S            |   6 --
 4 files changed, 138 insertions(+), 7 deletions(-)
 create mode 100644 arch/arm/include/asm/unified.h

diff --git a/arch/arm/include/asm/assembler.h b/arch/arm/include/asm/assembler.h
index 11b80fb..ae1e42f 100644
--- a/arch/arm/include/asm/assembler.h
+++ b/arch/arm/include/asm/assembler.h
@@ -15,6 +15,7 @@
  */
 
 #include <config.h>
+#include <asm/unified.h>
 
 /*
  * Endian independent macros for shifting bytes within registers.
diff --git a/arch/arm/include/asm/unified.h b/arch/arm/include/asm/unified.h
new file mode 100644
index 0000000..1b26002
--- /dev/null
+++ b/arch/arm/include/asm/unified.h
@@ -0,0 +1,129 @@
+/*
+ * include/asm-arm/unified.h - Unified Assembler Syntax helper macros
+ *
+ * Copyright (C) 2008 ARM Limited
+ *
+ * SPDX-License-Identifier:	GPL-2.0
+ */
+
+#ifndef __ASM_UNIFIED_H
+#define __ASM_UNIFIED_H
+
+#if defined(__ASSEMBLY__) && defined(CONFIG_ARM_ASM_UNIFIED)
+	.syntax unified
+#endif
+
+#ifdef CONFIG_CPU_V7M
+#define AR_CLASS(x...)
+#define M_CLASS(x...)	x
+#else
+#define AR_CLASS(x...)	x
+#define M_CLASS(x...)
+#endif
+
+#ifdef CONFIG_THUMB2_KERNEL
+
+#if __GNUC__ < 4
+#error Thumb-2 kernel requires gcc >= 4
+#endif
+
+/* The CPSR bit describing the instruction set (Thumb) */
+#define PSR_ISETSTATE	PSR_T_BIT
+
+#define ARM(x...)
+#define THUMB(x...)	x
+#ifdef __ASSEMBLY__
+#define W(instr)	instr.w
+#else
+#define WASM(instr)	#instr ".w"
+#endif
+
+#else	/* !CONFIG_THUMB2_KERNEL */
+
+/* The CPSR bit describing the instruction set (ARM) */
+#define PSR_ISETSTATE	0
+
+#define ARM(x...)	x
+#define THUMB(x...)
+#ifdef __ASSEMBLY__
+#define W(instr)	instr
+#else
+#define WASM(instr)	#instr
+#endif
+
+#endif	/* CONFIG_THUMB2_KERNEL */
+
+#ifndef CONFIG_ARM_ASM_UNIFIED
+
+/*
+ * If the unified assembly syntax isn't used (in ARM mode), these
+ * macros expand to an empty string
+ */
+#ifdef __ASSEMBLY__
+	.macro	it, cond
+	.endm
+	.macro	itt, cond
+	.endm
+	.macro	ite, cond
+	.endm
+	.macro	ittt, cond
+	.endm
+	.macro	itte, cond
+	.endm
+	.macro	itet, cond
+	.endm
+	.macro	itee, cond
+	.endm
+	.macro	itttt, cond
+	.endm
+	.macro	ittte, cond
+	.endm
+	.macro	ittet, cond
+	.endm
+	.macro	ittee, cond
+	.endm
+	.macro	itett, cond
+	.endm
+	.macro	itete, cond
+	.endm
+	.macro	iteet, cond
+	.endm
+	.macro	iteee, cond
+	.endm
+#else	/* !__ASSEMBLY__ */
+__asm__(
+"	.macro	it, cond\n"
+"	.endm\n"
+"	.macro	itt, cond\n"
+"	.endm\n"
+"	.macro	ite, cond\n"
+"	.endm\n"
+"	.macro	ittt, cond\n"
+"	.endm\n"
+"	.macro	itte, cond\n"
+"	.endm\n"
+"	.macro	itet, cond\n"
+"	.endm\n"
+"	.macro	itee, cond\n"
+"	.endm\n"
+"	.macro	itttt, cond\n"
+"	.endm\n"
+"	.macro	ittte, cond\n"
+"	.endm\n"
+"	.macro	ittet, cond\n"
+"	.endm\n"
+"	.macro	ittee, cond\n"
+"	.endm\n"
+"	.macro	itett, cond\n"
+"	.endm\n"
+"	.macro	itete, cond\n"
+"	.endm\n"
+"	.macro	iteet, cond\n"
+"	.endm\n"
+"	.macro	iteee, cond\n"
+"	.endm\n");
+#endif	/* __ASSEMBLY__ */
+
+#endif	/* CONFIG_ARM_ASM_UNIFIED */
+
+#endif	/* !__ASM_UNIFIED_H */
diff --git a/arch/arm/lib/Makefile b/arch/arm/lib/Makefile
index 7a0fb58..1112b9e 100644
--- a/arch/arm/lib/Makefile
+++ b/arch/arm/lib/Makefile
@@ -62,9 +62,17 @@ ifneq (,$(findstring -mabi=aapcs-linux,$(PLATFORM_CPPFLAGS)))
 extra-y	+= eabi_compat.o
 endif
 
+asflags-y += -DCONFIG_ARM_ASM_UNIFIED
+ifeq ($(CONFIG_SPL_BUILD)$(CONFIG_TEGRA),yy)
+asflags-y += -D__LINUX_ARM_ARCH__=4
+else
+asflags-y += -D__LINUX_ARM_ARCH__=$(CONFIG_SYS_ARM_ARCH)
+endif
+
 # some files can only build in ARM or THUMB2, not THUMB1
 
 ifdef CONFIG_SYS_THUMB_BUILD
+asflags-$(CONFIG_HAS_THUMB2) += -DCONFIG_THUMB2_KERNEL
 ifndef CONFIG_HAS_THUMB2
 
 # for C files, just apend -marm, which will override previous -mthumb*
@@ -82,6 +90,5 @@ AFLAGS_REMOVE_memset.o := -mthumb -mthumb-interwork
 AFLAGS_REMOVE_memcpy.o := -mthumb -mthumb-interwork
 AFLAGS_memset.o := -DMEMSET_NO_THUMB_BUILD
 AFLAGS_memcpy.o := -DMEMCPY_NO_THUMB_BUILD
-
 endif
 endif
diff --git a/arch/arm/lib/memcpy.S b/arch/arm/lib/memcpy.S
index 7d9fc0f..00602e9 100644
--- a/arch/arm/lib/memcpy.S
+++ b/arch/arm/lib/memcpy.S
@@ -13,12 +13,6 @@
 #include <linux/linkage.h>
 #include <asm/assembler.h>
 
-#if defined(CONFIG_SYS_THUMB_BUILD) && !defined(MEMCPY_NO_THUMB_BUILD)
-#define W(instr)	instr.w
-#else
-#define W(instr)	instr
-#endif
-
 #define LDR1W_SHIFT	0
 #define STR1W_SHIFT	0
 
-- 
2.7.0

[U-Boot] [PATCH 02/12] arm: include: Import unified.h from Linux kernel

[Tom Rini]

On Thu, May 26, 2016 at 06:01:37PM +0200, Marek Vasut wrote:

> Import unified.h from Linux kernel 4.4.6 , commit
> 0d1912303e54ed1b2a371be0bba51c384dd57326 . This header file contains
> macros used in libgcc functions in Linux kernel on ARM and will be
> needed for the libgcc sync.
> 
> Since unified.h defines the W(instr) macro, we must drop this from
> the macro from memcpy.S , otherwise this triggers a warning about
> symbol redefinition. In order to keep the changes to unified.h to
> the minimum, tweak arch/arm/lib/Makefile such that it defines the
> CONFIG_ARM_ASM_UNIFIED macro, which places .syntax unified into all
> of the assembler files. This is mandatory.
> 
> Moreover, for Thumb2 build, define CONFIG_THUMB2_KERNEL macro if and
> only if Thumb2 build is enabled. This macro is checked by unified.h
> and toggles between ARM and Thumb2 variant of the instructions in the
> assembler source files.
> 
> Finally, this patch defines __LINUX_ARM_ARCH__=N macro based on the
> new CONFIG_SYS_ARM_ARCH Kconfig option. This macro selects between
> more optimal and more dense codepaths which work on armv5 and newer
> and less optimal codepaths which work on armv4 and possible armv3m.
> Tegra2 needs the same special handling as it does in arch/arm/Makefile
> to cater for the arm720t boot core.
> 
> Signed-off-by: Marek Vasut <marex@denx.de>
> Cc: Albert Aribaud <albert.u.boot@aribaud.net>
> Cc: Masahiro Yamada <yamada.masahiro@socionext.com>
> Cc: Simon Glass <sjg@chromium.org>
> Cc: Tom Rini <trini@konsulko.com>

Reviewed-by: Tom Rini <trini@konsulko.com>

-- 
Tom
-------------- next part --------------
A non-text attachment was scrubbed...
Name: signature.asc
Type: application/pgp-signature
Size: 819 bytes
Desc: Digital signature
URL: <http://lists.denx.de/pipermail/u-boot/attachments/20160602/924b6adf/attachment.sig>

[U-Boot] [U-Boot, 02/12] arm: include: Import unified.h from Linux kernel

[Tom Rini]

On Thu, May 26, 2016 at 06:01:37PM +0200, Marek Vasut wrote:

> Import unified.h from Linux kernel 4.4.6 , commit
> 0d1912303e54ed1b2a371be0bba51c384dd57326 . This header file contains
> macros used in libgcc functions in Linux kernel on ARM and will be
> needed for the libgcc sync.
> 
> Since unified.h defines the W(instr) macro, we must drop this from
> the macro from memcpy.S , otherwise this triggers a warning about
> symbol redefinition. In order to keep the changes to unified.h to
> the minimum, tweak arch/arm/lib/Makefile such that it defines the
> CONFIG_ARM_ASM_UNIFIED macro, which places .syntax unified into all
> of the assembler files. This is mandatory.
> 
> Moreover, for Thumb2 build, define CONFIG_THUMB2_KERNEL macro if and
> only if Thumb2 build is enabled. This macro is checked by unified.h
> and toggles between ARM and Thumb2 variant of the instructions in the
> assembler source files.
> 
> Finally, this patch defines __LINUX_ARM_ARCH__=N macro based on the
> new CONFIG_SYS_ARM_ARCH Kconfig option. This macro selects between
> more optimal and more dense codepaths which work on armv5 and newer
> and less optimal codepaths which work on armv4 and possible armv3m.
> Tegra2 needs the same special handling as it does in arch/arm/Makefile
> to cater for the arm720t boot core.
> 
> Signed-off-by: Marek Vasut <marex@denx.de>
> Cc: Albert Aribaud <albert.u.boot@aribaud.net>
> Cc: Masahiro Yamada <yamada.masahiro@socionext.com>
> Cc: Simon Glass <sjg@chromium.org>
> Cc: Tom Rini <trini@konsulko.com>
> Reviewed-by: Tom Rini <trini@konsulko.com>

Applied to u-boot/master, thanks!

-- 
Tom
-------------- next part --------------
A non-text attachment was scrubbed...
Name: signature.asc
Type: application/pgp-signature
Size: 819 bytes
Desc: Digital signature
URL: <http://lists.denx.de/pipermail/u-boot/attachments/20160603/2c02fd2c/attachment.sig>

[U-Boot] [PATCH 03/12] arm: lib: Drop underscore from private libgcc filenames

[Marek Vasut]

Drop the underscore from the filenames of files implementing libgcc
routines. There is no functional change. This change is done to make
sync with Linux kernel easier.

Signed-off-by: Marek Vasut <marex@denx.de>
Cc: Albert Aribaud <albert.u.boot@aribaud.net>
Cc: Masahiro Yamada <yamada.masahiro@socionext.com>
Cc: Simon Glass <sjg@chromium.org>
Cc: Tom Rini <trini@konsulko.com>
---
 arch/arm/lib/Makefile                    | 6 +++---
 arch/arm/lib/{_ashldi3.S => ashldi3.S}   | 0
 arch/arm/lib/{_ashrdi3.S => ashrdi3.S}   | 0
 arch/arm/lib/{_divsi3.S => divsi3.S}     | 0
 arch/arm/lib/{_lshrdi3.S => lshrdi3.S}   | 0
 arch/arm/lib/{_modsi3.S => modsi3.S}     | 0
 arch/arm/lib/{_udivsi3.S => udivsi3.S}   | 0
 arch/arm/lib/{_uldivmod.S => uldivmod.S} | 0
 arch/arm/lib/{_umodsi3.S => umodsi3.S}   | 0
 9 files changed, 3 insertions(+), 3 deletions(-)
 rename arch/arm/lib/{_ashldi3.S => ashldi3.S} (100%)
 rename arch/arm/lib/{_ashrdi3.S => ashrdi3.S} (100%)
 rename arch/arm/lib/{_divsi3.S => divsi3.S} (100%)
 rename arch/arm/lib/{_lshrdi3.S => lshrdi3.S} (100%)
 rename arch/arm/lib/{_modsi3.S => modsi3.S} (100%)
 rename arch/arm/lib/{_udivsi3.S => udivsi3.S} (100%)
 rename arch/arm/lib/{_uldivmod.S => uldivmod.S} (100%)
 rename arch/arm/lib/{_umodsi3.S => umodsi3.S} (100%)

diff --git a/arch/arm/lib/Makefile b/arch/arm/lib/Makefile
index 1112b9e..cafd94d 100644
--- a/arch/arm/lib/Makefile
+++ b/arch/arm/lib/Makefile
@@ -5,9 +5,9 @@
 # SPDX-License-Identifier:	GPL-2.0+
 #
 
-lib-$(CONFIG_USE_PRIVATE_LIBGCC) += _ashldi3.o _ashrdi3.o _divsi3.o \
-			_lshrdi3.o _modsi3.o _udivsi3.o _umodsi3.o div0.o \
-			_uldivmod.o
+lib-$(CONFIG_USE_PRIVATE_LIBGCC) += ashldi3.o ashrdi3.o divsi3.o \
+			lshrdi3.o modsi3.o udivsi3.o umodsi3.o div0.o \
+			uldivmod.o
 
 ifdef CONFIG_CPU_V7M
 obj-y	+= vectors_m.o crt0.o
diff --git a/arch/arm/lib/_ashldi3.S b/arch/arm/lib/ashldi3.S
similarity index 100%
rename from arch/arm/lib/_ashldi3.S
rename to arch/arm/lib/ashldi3.S
diff --git a/arch/arm/lib/_ashrdi3.S b/arch/arm/lib/ashrdi3.S
similarity index 100%
rename from arch/arm/lib/_ashrdi3.S
rename to arch/arm/lib/ashrdi3.S
diff --git a/arch/arm/lib/_divsi3.S b/arch/arm/lib/divsi3.S
similarity index 100%
rename from arch/arm/lib/_divsi3.S
rename to arch/arm/lib/divsi3.S
diff --git a/arch/arm/lib/_lshrdi3.S b/arch/arm/lib/lshrdi3.S
similarity index 100%
rename from arch/arm/lib/_lshrdi3.S
rename to arch/arm/lib/lshrdi3.S
diff --git a/arch/arm/lib/_modsi3.S b/arch/arm/lib/modsi3.S
similarity index 100%
rename from arch/arm/lib/_modsi3.S
rename to arch/arm/lib/modsi3.S
diff --git a/arch/arm/lib/_udivsi3.S b/arch/arm/lib/udivsi3.S
similarity index 100%
rename from arch/arm/lib/_udivsi3.S
rename to arch/arm/lib/udivsi3.S
diff --git a/arch/arm/lib/_uldivmod.S b/arch/arm/lib/uldivmod.S
similarity index 100%
rename from arch/arm/lib/_uldivmod.S
rename to arch/arm/lib/uldivmod.S
diff --git a/arch/arm/lib/_umodsi3.S b/arch/arm/lib/umodsi3.S
similarity index 100%
rename from arch/arm/lib/_umodsi3.S
rename to arch/arm/lib/umodsi3.S
-- 
2.7.0

[U-Boot] [PATCH 03/12] arm: lib: Drop underscore from private libgcc filenames

[Tom Rini]

On Thu, May 26, 2016 at 06:01:38PM +0200, Marek Vasut wrote:

> Drop the underscore from the filenames of files implementing libgcc
> routines. There is no functional change. This change is done to make
> sync with Linux kernel easier.
> 
> Signed-off-by: Marek Vasut <marex@denx.de>
> Cc: Albert Aribaud <albert.u.boot@aribaud.net>
> Cc: Masahiro Yamada <yamada.masahiro@socionext.com>
> Cc: Simon Glass <sjg@chromium.org>
> Cc: Tom Rini <trini@konsulko.com>

Reviewed-by: Tom Rini <trini@konsulko.com>

-- 
Tom
-------------- next part --------------
A non-text attachment was scrubbed...
Name: signature.asc
Type: application/pgp-signature
Size: 819 bytes
Desc: Digital signature
URL: <http://lists.denx.de/pipermail/u-boot/attachments/20160602/93afa5d6/attachment.sig>

[U-Boot] [U-Boot, 03/12] arm: lib: Drop underscore from private libgcc filenames

[Tom Rini]

On Thu, May 26, 2016 at 06:01:38PM +0200, Marek Vasut wrote:

> Drop the underscore from the filenames of files implementing libgcc
> routines. There is no functional change. This change is done to make
> sync with Linux kernel easier.
> 
> Signed-off-by: Marek Vasut <marex@denx.de>
> Cc: Albert Aribaud <albert.u.boot@aribaud.net>
> Cc: Masahiro Yamada <yamada.masahiro@socionext.com>
> Cc: Simon Glass <sjg@chromium.org>
> Cc: Tom Rini <trini@konsulko.com>
> Reviewed-by: Tom Rini <trini@konsulko.com>

Applied to u-boot/master, thanks!

-- 
Tom
-------------- next part --------------
A non-text attachment was scrubbed...
Name: signature.asc
Type: application/pgp-signature
Size: 819 bytes
Desc: Digital signature
URL: <http://lists.denx.de/pipermail/u-boot/attachments/20160603/64af4291/attachment.sig>

[U-Boot] [PATCH 04/12] arm: lib: Sync libgcc shift operations

[Marek Vasut]

Sync the libgcc shift operations with Linux kernel 4.4.6 , commit
0d1912303e54ed1b2a371be0bba51c384dd57326 . Syncing these three
files is easy, as there is almost no change in them, except the
addition of Thumb support.

This patch also defines CONFIG_THUMB2_KERNEL and CONFIG_ARM_ASM_UNIFIED
which is necessary for correct build of these files both in ARM and
Thumb mode, just like Linux does.

Signed-off-by: Marek Vasut <marex@denx.de>
Cc: Albert Aribaud <albert.u.boot@aribaud.net>
Cc: Masahiro Yamada <yamada.masahiro@socionext.com>
Cc: Simon Glass <sjg@chromium.org>
Cc: Tom Rini <trini@konsulko.com>
---
 arch/arm/lib/ashldi3.S | 12 ++++++++----
 arch/arm/lib/ashrdi3.S | 12 ++++++++----
 arch/arm/lib/lshrdi3.S | 12 ++++++++----
 3 files changed, 24 insertions(+), 12 deletions(-)

diff --git a/arch/arm/lib/ashldi3.S b/arch/arm/lib/ashldi3.S
index 9c34c21..a4f5ebb 100644
--- a/arch/arm/lib/ashldi3.S
+++ b/arch/arm/lib/ashldi3.S
@@ -5,6 +5,7 @@
  */
 
 #include <linux/linkage.h>
+#include <asm/assembler.h>
 
 #ifdef __ARMEB__
 #define al r1
@@ -14,15 +15,18 @@
 #define ah r1
 #endif
 
-.globl __ashldi3
-__ashldi3:
+ENTRY(__ashldi3)
 ENTRY(__aeabi_llsl)
 
 	subs	r3, r2, #32
 	rsb	ip, r2, #32
 	movmi	ah, ah, lsl r2
 	movpl	ah, al, lsl r3
-	orrmi	ah, ah, al, lsr ip
+ ARM(	orrmi	ah, ah, al, lsr ip	)
+ THUMB(	lsrmi	r3, al, ip		)
+ THUMB(	orrmi	ah, ah, r3		)
 	mov	al, al, lsl r2
-	mov	pc, lr
+	ret	lr
+
+ENDPROC(__ashldi3)
 ENDPROC(__aeabi_llsl)
diff --git a/arch/arm/lib/ashrdi3.S b/arch/arm/lib/ashrdi3.S
index c74fd64..c6e1ed3 100644
--- a/arch/arm/lib/ashrdi3.S
+++ b/arch/arm/lib/ashrdi3.S
@@ -5,6 +5,7 @@
  */
 
 #include <linux/linkage.h>
+#include <asm/assembler.h>
 
 #ifdef __ARMEB__
 #define al r1
@@ -14,15 +15,18 @@
 #define ah r1
 #endif
 
-.globl __ashrdi3
-__ashrdi3:
+ENTRY(__ashrdi3)
 ENTRY(__aeabi_lasr)
 
 	subs	r3, r2, #32
 	rsb	ip, r2, #32
 	movmi	al, al, lsr r2
 	movpl	al, ah, asr r3
-	orrmi	al, al, ah, lsl ip
+ ARM(	orrmi	al, al, ah, lsl ip	)
+ THUMB(	lslmi	r3, ah, ip		)
+ THUMB(	orrmi	al, al, r3		)
 	mov	ah, ah, asr r2
-	mov	pc, lr
+	ret	lr
+
+ENDPROC(__ashrdi3)
 ENDPROC(__aeabi_lasr)
diff --git a/arch/arm/lib/lshrdi3.S b/arch/arm/lib/lshrdi3.S
index 1f9b916..9c51141 100644
--- a/arch/arm/lib/lshrdi3.S
+++ b/arch/arm/lib/lshrdi3.S
@@ -5,6 +5,7 @@
  */
 
 #include <linux/linkage.h>
+#include <asm/assembler.h>
 
 #ifdef __ARMEB__
 #define al r1
@@ -14,15 +15,18 @@
 #define ah r1
 #endif
 
-.globl __lshrdi3
-__lshrdi3:
+ENTRY(__lshrdi3)
 ENTRY(__aeabi_llsr)
 
 	subs	r3, r2, #32
 	rsb	ip, r2, #32
 	movmi	al, al, lsr r2
 	movpl	al, ah, lsr r3
-	orrmi	al, al, ah, lsl ip
+ ARM(	orrmi	al, al, ah, lsl ip	)
+ THUMB(	lslmi	r3, ah, ip		)
+ THUMB(	orrmi	al, al, r3		)
 	mov	ah, ah, lsr r2
-	mov	pc, lr
+	ret	lr
+
+ENDPROC(__lshrdi3)
 ENDPROC(__aeabi_llsr)
-- 
2.7.0

[U-Boot] [PATCH 04/12] arm: lib: Sync libgcc shift operations

[Tom Rini]

On Thu, May 26, 2016 at 06:01:39PM +0200, Marek Vasut wrote:

> Sync the libgcc shift operations with Linux kernel 4.4.6 , commit
> 0d1912303e54ed1b2a371be0bba51c384dd57326 . Syncing these three
> files is easy, as there is almost no change in them, except the
> addition of Thumb support.
> 
> This patch also defines CONFIG_THUMB2_KERNEL and CONFIG_ARM_ASM_UNIFIED
> which is necessary for correct build of these files both in ARM and
> Thumb mode, just like Linux does.
> 
> Signed-off-by: Marek Vasut <marex@denx.de>
> Cc: Albert Aribaud <albert.u.boot@aribaud.net>
> Cc: Masahiro Yamada <yamada.masahiro@socionext.com>
> Cc: Simon Glass <sjg@chromium.org>
> Cc: Tom Rini <trini@konsulko.com>

Reviewed-by: Tom Rini <trini@konsulko.com>

-- 
Tom
-------------- next part --------------
A non-text attachment was scrubbed...
Name: signature.asc
Type: application/pgp-signature
Size: 819 bytes
Desc: Digital signature
URL: <http://lists.denx.de/pipermail/u-boot/attachments/20160602/e9a48b20/attachment.sig>

[U-Boot] [U-Boot,04/12] arm: lib: Sync libgcc shift operations

[Tom Rini]

On Thu, May 26, 2016 at 06:01:39PM +0200, Marek Vasut wrote:

> Sync the libgcc shift operations with Linux kernel 4.4.6 , commit
> 0d1912303e54ed1b2a371be0bba51c384dd57326 . Syncing these three
> files is easy, as there is almost no change in them, except the
> addition of Thumb support.
> 
> This patch also defines CONFIG_THUMB2_KERNEL and CONFIG_ARM_ASM_UNIFIED
> which is necessary for correct build of these files both in ARM and
> Thumb mode, just like Linux does.
> 
> Signed-off-by: Marek Vasut <marex@denx.de>
> Cc: Albert Aribaud <albert.u.boot@aribaud.net>
> Cc: Masahiro Yamada <yamada.masahiro@socionext.com>
> Cc: Simon Glass <sjg@chromium.org>
> Cc: Tom Rini <trini@konsulko.com>
> Reviewed-by: Tom Rini <trini@konsulko.com>

Applied to u-boot/master, thanks!

-- 
Tom
-------------- next part --------------
A non-text attachment was scrubbed...
Name: signature.asc
Type: application/pgp-signature
Size: 819 bytes
Desc: Digital signature
URL: <http://lists.denx.de/pipermail/u-boot/attachments/20160603/40d743c9/attachment.sig>

[U-Boot] [PATCH 05/12] arm: lib: Sync libgcc 32b division/modulo operations

[Marek Vasut]

Sync the libgcc 32bit division and modulo operations with Linux 4.4.6 ,
commit 0d1912303e54ed1b2a371be0bba51c384dd57326 . The functions in these
four files are present in lib1funcs.S in Linux, so replace these files
with lib1funcs.S from Linux.

Since we do not support stack unwinding, instead of importing the whole
asm/unwind.h and all the baggage, this patch defines empty UNWIND() macro
in lib1funcs.S . Moreover, to make all of the functions available, define
CONFIG_AEABI , which is safe, because U-Boot is always compiled with ARM
EABI.

This patch also defines CONFIG_THUMB2_KERNEL and CONFIG_ARM_ASM_UNIFIED
which is necessary for correct build of these files both in ARM and
Thumb mode, just like Linux does.

Signed-off-by: Marek Vasut <marex@denx.de>
Cc: Albert Aribaud <albert.u.boot@aribaud.net>
Cc: Masahiro Yamada <yamada.masahiro@socionext.com>
Cc: Simon Glass <sjg@chromium.org>
Cc: Tom Rini <trini@konsulko.com>
---
 arch/arm/lib/Makefile    |   5 +-
 arch/arm/lib/divsi3.S    | 143 -------------------
 arch/arm/lib/lib1funcs.S | 351 +++++++++++++++++++++++++++++++++++++++++++++++
 arch/arm/lib/modsi3.S    |  99 -------------
 arch/arm/lib/udivsi3.S   |  95 -------------
 arch/arm/lib/umodsi3.S   |  90 ------------
 6 files changed, 353 insertions(+), 430 deletions(-)
 delete mode 100644 arch/arm/lib/divsi3.S
 create mode 100644 arch/arm/lib/lib1funcs.S
 delete mode 100644 arch/arm/lib/modsi3.S
 delete mode 100644 arch/arm/lib/udivsi3.S
 delete mode 100644 arch/arm/lib/umodsi3.S

diff --git a/arch/arm/lib/Makefile b/arch/arm/lib/Makefile
index cafd94d..0b0dbcb 100644
--- a/arch/arm/lib/Makefile
+++ b/arch/arm/lib/Makefile
@@ -5,9 +5,8 @@
 # SPDX-License-Identifier:	GPL-2.0+
 #
 
-lib-$(CONFIG_USE_PRIVATE_LIBGCC) += ashldi3.o ashrdi3.o divsi3.o \
-			lshrdi3.o modsi3.o udivsi3.o umodsi3.o div0.o \
-			uldivmod.o
+lib-$(CONFIG_USE_PRIVATE_LIBGCC) += ashldi3.o ashrdi3.o lshrdi3.o \
+				    lib1funcs.o uldivmod.o div0.o
 
 ifdef CONFIG_CPU_V7M
 obj-y	+= vectors_m.o crt0.o
diff --git a/arch/arm/lib/divsi3.S b/arch/arm/lib/divsi3.S
deleted file mode 100644
index c463c68..0000000
--- a/arch/arm/lib/divsi3.S
+++ /dev/null
@@ -1,143 +0,0 @@
-#include <linux/linkage.h>
-
-.macro ARM_DIV_BODY dividend, divisor, result, curbit
-
-#if __LINUX_ARM_ARCH__ >= 5
-
-	clz	\curbit, \divisor
-	clz	\result, \dividend
-	sub	\result, \curbit, \result
-	mov	\curbit, #1
-	mov	\divisor, \divisor, lsl \result
-	mov	\curbit, \curbit, lsl \result
-	mov	\result, #0
-
-#else
-
-	@ Initially shift the divisor left 3 bits if possible,
-	@ set curbit accordingly.  This allows for curbit to be located
-	@ at the left end of each 4 bit nibbles in the division loop
-	@ to save one loop in most cases.
-	tst	\divisor, #0xe0000000
-	moveq	\divisor, \divisor, lsl #3
-	moveq	\curbit, #8
-	movne	\curbit, #1
-
-	@ Unless the divisor is very big, shift it up in multiples of
-	@ four bits, since this is the amount of unwinding in the main
-	@ division loop.  Continue shifting until the divisor is
-	@ larger than the dividend.
-1:	cmp	\divisor, #0x10000000
-	cmplo	\divisor, \dividend
-	movlo	\divisor, \divisor, lsl #4
-	movlo	\curbit, \curbit, lsl #4
-	blo	1b
-
-	@ For very big divisors, we must shift it a bit at a time, or
-	@ we will be in danger of overflowing.
-1:	cmp	\divisor, #0x80000000
-	cmplo	\divisor, \dividend
-	movlo	\divisor, \divisor, lsl #1
-	movlo	\curbit, \curbit, lsl #1
-	blo	1b
-
-	mov	\result, #0
-
-#endif
-
-	@ Division loop
-1:	cmp	\dividend, \divisor
-	subhs	\dividend, \dividend, \divisor
-	orrhs	\result,   \result,   \curbit
-	cmp	\dividend, \divisor,  lsr #1
-	subhs	\dividend, \dividend, \divisor, lsr #1
-	orrhs	\result,   \result,   \curbit,  lsr #1
-	cmp	\dividend, \divisor,  lsr #2
-	subhs	\dividend, \dividend, \divisor, lsr #2
-	orrhs	\result,   \result,   \curbit,  lsr #2
-	cmp	\dividend, \divisor,  lsr #3
-	subhs	\dividend, \dividend, \divisor, lsr #3
-	orrhs	\result,   \result,   \curbit,  lsr #3
-	cmp	\dividend, #0			@ Early termination?
-	movnes	\curbit,   \curbit,  lsr #4	@ No, any more bits to do?
-	movne	\divisor,  \divisor, lsr #4
-	bne	1b
-
-.endm
-
-.macro ARM_DIV2_ORDER divisor, order
-
-#if __LINUX_ARM_ARCH__ >= 5
-
-	clz	\order, \divisor
-	rsb	\order, \order, #31
-
-#else
-
-	cmp	\divisor, #(1 << 16)
-	movhs	\divisor, \divisor, lsr #16
-	movhs	\order, #16
-	movlo	\order, #0
-
-	cmp	\divisor, #(1 << 8)
-	movhs	\divisor, \divisor, lsr #8
-	addhs	\order, \order, #8
-
-	cmp	\divisor, #(1 << 4)
-	movhs	\divisor, \divisor, lsr #4
-	addhs	\order, \order, #4
-
-	cmp	\divisor, #(1 << 2)
-	addhi	\order, \order, #3
-	addls	\order, \order, \divisor, lsr #1
-
-#endif
-
-.endm
-
-	.align	5
-.globl __divsi3
-__divsi3:
-ENTRY(__aeabi_idiv)
-	cmp	r1, #0
-	eor	ip, r0, r1			@ save the sign of the result.
-	beq	Ldiv0
-	rsbmi	r1, r1, #0			@ loops below use unsigned.
-	subs	r2, r1, #1			@ division by 1 or -1 ?
-	beq	10f
-	movs	r3, r0
-	rsbmi	r3, r0, #0			@ positive dividend value
-	cmp	r3, r1
-	bls	11f
-	tst	r1, r2				@ divisor is power of 2 ?
-	beq	12f
-
-	ARM_DIV_BODY r3, r1, r0, r2
-
-	cmp	ip, #0
-	rsbmi	r0, r0, #0
-	mov	pc, lr
-
-10:	teq	ip, r0				@ same sign ?
-	rsbmi	r0, r0, #0
-	mov	pc, lr
-
-11:	movlo	r0, #0
-	moveq	r0, ip, asr #31
-	orreq	r0, r0, #1
-	mov	pc, lr
-
-12:	ARM_DIV2_ORDER r1, r2
-
-	cmp	ip, #0
-	mov	r0, r3, lsr r2
-	rsbmi	r0, r0, #0
-	mov	pc, lr
-
-Ldiv0:
-
-	str	lr, [sp, #-4]!
-	bl	__div0
-	mov	r0, #0			@ About as wrong as it could be.
-	ldr	pc, [sp], #4
-ENDPROC(__aeabi_idiv)
diff --git a/arch/arm/lib/lib1funcs.S b/arch/arm/lib/lib1funcs.S
new file mode 100644
index 0000000..5871dbe
--- /dev/null
+++ b/arch/arm/lib/lib1funcs.S
@@ -0,0 +1,351 @@
+/*
+ * linux/arch/arm/lib/lib1funcs.S: Optimized ARM division routines
+ *
+ * Author: Nicolas Pitre <nico@fluxnic.net>
+ *   - contributed to gcc-3.4 on Sep 30, 2003
+ *   - adapted for the Linux kernel on Oct 2, 2003
+ */
+
+/* Copyright 1995, 1996, 1998, 1999, 2000, 2003 Free Software Foundation, Inc.
+
+ * SPDX-License-Identifier:	GPL-2.0+
+ */
+
+
+#include <linux/linkage.h>
+#include <asm/assembler.h>
+
+/*
+ * U-Boot compatibility bit, define empty UNWIND() macro as, since we
+ * do not support stack unwinding and define CONFIG_AEABI to make all
+ * of the functions available without diverging from Linux code.
+ */
+#ifdef __UBOOT__
+#define UNWIND(x...)
+#define CONFIG_AEABI
+#endif
+
+.macro ARM_DIV_BODY dividend, divisor, result, curbit
+
+#if __LINUX_ARM_ARCH__ >= 5
+
+	clz	\curbit, \divisor
+	clz	\result, \dividend
+	sub	\result, \curbit, \result
+	mov	\curbit, #1
+	mov	\divisor, \divisor, lsl \result
+	mov	\curbit, \curbit, lsl \result
+	mov	\result, #0
+	
+#else
+
+	@ Initially shift the divisor left 3 bits if possible,
+	@ set curbit accordingly.  This allows for curbit to be located
+	@ at the left end of each 4 bit nibbles in the division loop
+	@ to save one loop in most cases.
+	tst	\divisor, #0xe0000000
+	moveq	\divisor, \divisor, lsl #3
+	moveq	\curbit, #8
+	movne	\curbit, #1
+
+	@ Unless the divisor is very big, shift it up in multiples of
+	@ four bits, since this is the amount of unwinding in the main
+	@ division loop.  Continue shifting until the divisor is 
+	@ larger than the dividend.
+1:	cmp	\divisor, #0x10000000
+	cmplo	\divisor, \dividend
+	movlo	\divisor, \divisor, lsl #4
+	movlo	\curbit, \curbit, lsl #4
+	blo	1b
+
+	@ For very big divisors, we must shift it a bit at a time, or
+	@ we will be in danger of overflowing.
+1:	cmp	\divisor, #0x80000000
+	cmplo	\divisor, \dividend
+	movlo	\divisor, \divisor, lsl #1
+	movlo	\curbit, \curbit, lsl #1
+	blo	1b
+
+	mov	\result, #0
+
+#endif
+
+	@ Division loop
+1:	cmp	\dividend, \divisor
+	subhs	\dividend, \dividend, \divisor
+	orrhs	\result,   \result,   \curbit
+	cmp	\dividend, \divisor,  lsr #1
+	subhs	\dividend, \dividend, \divisor, lsr #1
+	orrhs	\result,   \result,   \curbit,  lsr #1
+	cmp	\dividend, \divisor,  lsr #2
+	subhs	\dividend, \dividend, \divisor, lsr #2
+	orrhs	\result,   \result,   \curbit,  lsr #2
+	cmp	\dividend, \divisor,  lsr #3
+	subhs	\dividend, \dividend, \divisor, lsr #3
+	orrhs	\result,   \result,   \curbit,  lsr #3
+	cmp	\dividend, #0			@ Early termination?
+	movnes	\curbit,   \curbit,  lsr #4	@ No, any more bits to do?
+	movne	\divisor,  \divisor, lsr #4
+	bne	1b
+
+.endm
+
+
+.macro ARM_DIV2_ORDER divisor, order
+
+#if __LINUX_ARM_ARCH__ >= 5
+
+	clz	\order, \divisor
+	rsb	\order, \order, #31
+
+#else
+
+	cmp	\divisor, #(1 << 16)
+	movhs	\divisor, \divisor, lsr #16
+	movhs	\order, #16
+	movlo	\order, #0
+
+	cmp	\divisor, #(1 << 8)
+	movhs	\divisor, \divisor, lsr #8
+	addhs	\order, \order, #8
+
+	cmp	\divisor, #(1 << 4)
+	movhs	\divisor, \divisor, lsr #4
+	addhs	\order, \order, #4
+
+	cmp	\divisor, #(1 << 2)
+	addhi	\order, \order, #3
+	addls	\order, \order, \divisor, lsr #1
+
+#endif
+
+.endm
+
+
+.macro ARM_MOD_BODY dividend, divisor, order, spare
+
+#if __LINUX_ARM_ARCH__ >= 5
+
+	clz	\order, \divisor
+	clz	\spare, \dividend
+	sub	\order, \order, \spare
+	mov	\divisor, \divisor, lsl \order
+
+#else
+
+	mov	\order, #0
+
+	@ Unless the divisor is very big, shift it up in multiples of
+	@ four bits, since this is the amount of unwinding in the main
+	@ division loop.  Continue shifting until the divisor is 
+	@ larger than the dividend.
+1:	cmp	\divisor, #0x10000000
+	cmplo	\divisor, \dividend
+	movlo	\divisor, \divisor, lsl #4
+	addlo	\order, \order, #4
+	blo	1b
+
+	@ For very big divisors, we must shift it a bit at a time, or
+	@ we will be in danger of overflowing.
+1:	cmp	\divisor, #0x80000000
+	cmplo	\divisor, \dividend
+	movlo	\divisor, \divisor, lsl #1
+	addlo	\order, \order, #1
+	blo	1b
+
+#endif
+
+	@ Perform all needed subtractions to keep only the reminder.
+	@ Do comparisons in batch of 4 first.
+	subs	\order, \order, #3		@ yes, 3 is intended here
+	blt	2f
+
+1:	cmp	\dividend, \divisor
+	subhs	\dividend, \dividend, \divisor
+	cmp	\dividend, \divisor,  lsr #1
+	subhs	\dividend, \dividend, \divisor, lsr #1
+	cmp	\dividend, \divisor,  lsr #2
+	subhs	\dividend, \dividend, \divisor, lsr #2
+	cmp	\dividend, \divisor,  lsr #3
+	subhs	\dividend, \dividend, \divisor, lsr #3
+	cmp	\dividend, #1
+	mov	\divisor, \divisor, lsr #4
+	subges	\order, \order, #4
+	bge	1b
+
+	tst	\order, #3
+	teqne	\dividend, #0
+	beq	5f
+
+	@ Either 1, 2 or 3 comparison/subtractions are left.
+2:	cmn	\order, #2
+	blt	4f
+	beq	3f
+	cmp	\dividend, \divisor
+	subhs	\dividend, \dividend, \divisor
+	mov	\divisor,  \divisor,  lsr #1
+3:	cmp	\dividend, \divisor
+	subhs	\dividend, \dividend, \divisor
+	mov	\divisor,  \divisor,  lsr #1
+4:	cmp	\dividend, \divisor
+	subhs	\dividend, \dividend, \divisor
+5:
+.endm
+
+
+ENTRY(__udivsi3)
+ENTRY(__aeabi_uidiv)
+UNWIND(.fnstart)
+
+	subs	r2, r1, #1
+	reteq	lr
+	bcc	Ldiv0
+	cmp	r0, r1
+	bls	11f
+	tst	r1, r2
+	beq	12f
+
+	ARM_DIV_BODY r0, r1, r2, r3
+
+	mov	r0, r2
+	ret	lr
+
+11:	moveq	r0, #1
+	movne	r0, #0
+	ret	lr
+
+12:	ARM_DIV2_ORDER r1, r2
+
+	mov	r0, r0, lsr r2
+	ret	lr
+
+UNWIND(.fnend)
+ENDPROC(__udivsi3)
+ENDPROC(__aeabi_uidiv)
+
+ENTRY(__umodsi3)
+UNWIND(.fnstart)
+
+	subs	r2, r1, #1			@ compare divisor with 1
+	bcc	Ldiv0
+	cmpne	r0, r1				@ compare dividend with divisor
+	moveq   r0, #0
+	tsthi	r1, r2				@ see if divisor is power of 2
+	andeq	r0, r0, r2
+	retls	lr
+
+	ARM_MOD_BODY r0, r1, r2, r3
+
+	ret	lr
+
+UNWIND(.fnend)
+ENDPROC(__umodsi3)
+
+ENTRY(__divsi3)
+ENTRY(__aeabi_idiv)
+UNWIND(.fnstart)
+
+	cmp	r1, #0
+	eor	ip, r0, r1			@ save the sign of the result.
+	beq	Ldiv0
+	rsbmi	r1, r1, #0			@ loops below use unsigned.
+	subs	r2, r1, #1			@ division by 1 or -1 ?
+	beq	10f
+	movs	r3, r0
+	rsbmi	r3, r0, #0			@ positive dividend value
+	cmp	r3, r1
+	bls	11f
+	tst	r1, r2				@ divisor is power of 2 ?
+	beq	12f
+
+	ARM_DIV_BODY r3, r1, r0, r2
+
+	cmp	ip, #0
+	rsbmi	r0, r0, #0
+	ret	lr
+
+10:	teq	ip, r0				@ same sign ?
+	rsbmi	r0, r0, #0
+	ret	lr
+
+11:	movlo	r0, #0
+	moveq	r0, ip, asr #31
+	orreq	r0, r0, #1
+	ret	lr
+
+12:	ARM_DIV2_ORDER r1, r2
+
+	cmp	ip, #0
+	mov	r0, r3, lsr r2
+	rsbmi	r0, r0, #0
+	ret	lr
+
+UNWIND(.fnend)
+ENDPROC(__divsi3)
+ENDPROC(__aeabi_idiv)
+
+ENTRY(__modsi3)
+UNWIND(.fnstart)
+
+	cmp	r1, #0
+	beq	Ldiv0
+	rsbmi	r1, r1, #0			@ loops below use unsigned.
+	movs	ip, r0				@ preserve sign of dividend
+	rsbmi	r0, r0, #0			@ if negative make positive
+	subs	r2, r1, #1			@ compare divisor with 1
+	cmpne	r0, r1				@ compare dividend with divisor
+	moveq	r0, #0
+	tsthi	r1, r2				@ see if divisor is power of 2
+	andeq	r0, r0, r2
+	bls	10f
+
+	ARM_MOD_BODY r0, r1, r2, r3
+
+10:	cmp	ip, #0
+	rsbmi	r0, r0, #0
+	ret	lr
+
+UNWIND(.fnend)
+ENDPROC(__modsi3)
+
+#ifdef CONFIG_AEABI
+
+ENTRY(__aeabi_uidivmod)
+UNWIND(.fnstart)
+UNWIND(.save {r0, r1, ip, lr}	)
+
+	stmfd	sp!, {r0, r1, ip, lr}
+	bl	__aeabi_uidiv
+	ldmfd	sp!, {r1, r2, ip, lr}
+	mul	r3, r0, r2
+	sub	r1, r1, r3
+	ret	lr
+
+UNWIND(.fnend)
+ENDPROC(__aeabi_uidivmod)
+
+ENTRY(__aeabi_idivmod)
+UNWIND(.fnstart)
+UNWIND(.save {r0, r1, ip, lr}	)
+	stmfd	sp!, {r0, r1, ip, lr}
+	bl	__aeabi_idiv
+	ldmfd	sp!, {r1, r2, ip, lr}
+	mul	r3, r0, r2
+	sub	r1, r1, r3
+	ret	lr
+
+UNWIND(.fnend)
+ENDPROC(__aeabi_idivmod)
+
+#endif
+
+Ldiv0:
+UNWIND(.fnstart)
+UNWIND(.pad #4)
+UNWIND(.save {lr})
+	str	lr, [sp, #-8]!
+	bl	__div0
+	mov	r0, #0			@ About as wrong as it could be.
+	ldr	pc, [sp], #8
+UNWIND(.fnend)
+ENDPROC(Ldiv0)
diff --git a/arch/arm/lib/modsi3.S b/arch/arm/lib/modsi3.S
deleted file mode 100644
index c5e1c22..0000000
--- a/arch/arm/lib/modsi3.S
+++ /dev/null
@@ -1,99 +0,0 @@
-#include <linux/linkage.h>
-
-.macro ARM_MOD_BODY dividend, divisor, order, spare
-
-#if __LINUX_ARM_ARCH__ >= 5
-
-	clz	\order, \divisor
-	clz	\spare, \dividend
-	sub	\order, \order, \spare
-	mov	\divisor, \divisor, lsl \order
-
-#else
-
-	mov	\order, #0
-
-	@ Unless the divisor is very big, shift it up in multiples of
-	@ four bits, since this is the amount of unwinding in the main
-	@ division loop.  Continue shifting until the divisor is
-	@ larger than the dividend.
-1:	cmp	\divisor, #0x10000000
-	cmplo	\divisor, \dividend
-	movlo	\divisor, \divisor, lsl #4
-	addlo	\order, \order, #4
-	blo	1b
-
-	@ For very big divisors, we must shift it a bit at a time, or
-	@ we will be in danger of overflowing.
-1:	cmp	\divisor, #0x80000000
-	cmplo	\divisor, \dividend
-	movlo	\divisor, \divisor, lsl #1
-	addlo	\order, \order, #1
-	blo	1b
-
-#endif
-
-	@ Perform all needed substractions to keep only the reminder.
-	@ Do comparisons in batch of 4 first.
-	subs	\order, \order, #3		@ yes, 3 is intended here
-	blt	2f
-
-1:	cmp	\dividend, \divisor
-	subhs	\dividend, \dividend, \divisor
-	cmp	\dividend, \divisor,  lsr #1
-	subhs	\dividend, \dividend, \divisor, lsr #1
-	cmp	\dividend, \divisor,  lsr #2
-	subhs	\dividend, \dividend, \divisor, lsr #2
-	cmp	\dividend, \divisor,  lsr #3
-	subhs	\dividend, \dividend, \divisor, lsr #3
-	cmp	\dividend, #1
-	mov	\divisor, \divisor, lsr #4
-	subges	\order, \order, #4
-	bge	1b
-
-	tst	\order, #3
-	teqne	\dividend, #0
-	beq	5f
-
-	@ Either 1, 2 or 3 comparison/substractions are left.
-2:	cmn	\order, #2
-	blt	4f
-	beq	3f
-	cmp	\dividend, \divisor
-	subhs	\dividend, \dividend, \divisor
-	mov	\divisor,  \divisor,  lsr #1
-3:	cmp	\dividend, \divisor
-	subhs	\dividend, \dividend, \divisor
-	mov	\divisor,  \divisor,  lsr #1
-4:	cmp	\dividend, \divisor
-	subhs	\dividend, \dividend, \divisor
-5:
-.endm
-
-	.align	5
-ENTRY(__modsi3)
-	cmp	r1, #0
-	beq	Ldiv0
-	rsbmi	r1, r1, #0			@ loops below use unsigned.
-	movs	ip, r0				@ preserve sign of dividend
-	rsbmi	r0, r0, #0			@ if negative make positive
-	subs	r2, r1, #1			@ compare divisor with 1
-	cmpne	r0, r1				@ compare dividend with divisor
-	moveq	r0, #0
-	tsthi	r1, r2				@ see if divisor is power of 2
-	andeq	r0, r0, r2
-	bls	10f
-
-	ARM_MOD_BODY r0, r1, r2, r3
-
-10:	cmp	ip, #0
-	rsbmi	r0, r0, #0
-	mov	pc, lr
-ENDPROC(__modsi3)
-
-Ldiv0:
-
-	str	lr, [sp, #-4]!
-	bl	__div0
-	mov	r0, #0			@ About as wrong as it could be.
-	ldr	pc, [sp], #4
diff --git a/arch/arm/lib/udivsi3.S b/arch/arm/lib/udivsi3.S
deleted file mode 100644
index 3b653be..0000000
--- a/arch/arm/lib/udivsi3.S
+++ /dev/null
@@ -1,95 +0,0 @@
-#include <linux/linkage.h>
-
-/* # 1 "libgcc1.S" */
-@ libgcc1 routines for ARM cpu.
-@ Division routines, written by Richard Earnshaw, (rearnsha at armltd.co.uk)
-dividend	.req	r0
-divisor		.req	r1
-result		.req	r2
-curbit		.req	r3
-/* ip		.req	r12	*/
-/* sp		.req	r13	*/
-/* lr		.req	r14	*/
-/* pc		.req	r15	*/
-	.text
-	.globl	 __udivsi3
-	.type	__udivsi3 ,function
-	.globl	__aeabi_uidiv
-	.type	__aeabi_uidiv ,function
-	.align	0
- __udivsi3:
- __aeabi_uidiv:
-	cmp	divisor, #0
-	beq	Ldiv0
-	mov	curbit, #1
-	mov	result, #0
-	cmp	dividend, divisor
-	bcc	Lgot_result
-Loop1:
-	@ Unless the divisor is very big, shift it up in multiples of
-	@ four bits, since this is the amount of unwinding in the main
-	@ division loop.  Continue shifting until the divisor is
-	@ larger than the dividend.
-	cmp	divisor, #0x10000000
-	cmpcc	divisor, dividend
-	movcc	divisor, divisor, lsl #4
-	movcc	curbit, curbit, lsl #4
-	bcc	Loop1
-Lbignum:
-	@ For very big divisors, we must shift it a bit at a time, or
-	@ we will be in danger of overflowing.
-	cmp	divisor, #0x80000000
-	cmpcc	divisor, dividend
-	movcc	divisor, divisor, lsl #1
-	movcc	curbit, curbit, lsl #1
-	bcc	Lbignum
-Loop3:
-	@ Test for possible subtractions, and note which bits
-	@ are done in the result.  On the final pass, this may subtract
-	@ too much from the dividend, but the result will be ok, since the
-	@ "bit" will have been shifted out at the bottom.
-	cmp	dividend, divisor
-	subcs	dividend, dividend, divisor
-	orrcs	result, result, curbit
-	cmp	dividend, divisor, lsr #1
-	subcs	dividend, dividend, divisor, lsr #1
-	orrcs	result, result, curbit, lsr #1
-	cmp	dividend, divisor, lsr #2
-	subcs	dividend, dividend, divisor, lsr #2
-	orrcs	result, result, curbit, lsr #2
-	cmp	dividend, divisor, lsr #3
-	subcs	dividend, dividend, divisor, lsr #3
-	orrcs	result, result, curbit, lsr #3
-	cmp	dividend, #0			@ Early termination?
-	movnes	curbit, curbit, lsr #4		@ No, any more bits to do?
-	movne	divisor, divisor, lsr #4
-	bne	Loop3
-Lgot_result:
-	mov	r0, result
-	mov	pc, lr
-Ldiv0:
-	str	lr, [sp, #-4]!
-	bl	 __div0       (PLT)
-	mov	r0, #0			@ about as wrong as it could be
-	ldmia	sp!, {pc}
-	.size  __udivsi3       , . -  __udivsi3
-
-ENTRY(__aeabi_uidivmod)
-
-	stmfd	sp!, {r0, r1, ip, lr}
-	bl	__aeabi_uidiv
-	ldmfd	sp!, {r1, r2, ip, lr}
-	mul	r3, r0, r2
-	sub	r1, r1, r3
-	mov	pc, lr
-ENDPROC(__aeabi_uidivmod)
-
-ENTRY(__aeabi_idivmod)
-
-	stmfd	sp!, {r0, r1, ip, lr}
-	bl	__aeabi_idiv
-	ldmfd	sp!, {r1, r2, ip, lr}
-	mul	r3, r0, r2
-	sub	r1, r1, r3
-	mov	pc, lr
-ENDPROC(__aeabi_idivmod)
diff --git a/arch/arm/lib/umodsi3.S b/arch/arm/lib/umodsi3.S
deleted file mode 100644
index b166737..0000000
--- a/arch/arm/lib/umodsi3.S
+++ /dev/null
@@ -1,90 +0,0 @@
-#include <linux/linkage.h>
-
-/* # 1 "libgcc1.S" */
-@ libgcc1 routines for ARM cpu.
-@ Division routines, written by Richard Earnshaw, (rearnsha at armltd.co.uk)
-/* # 145 "libgcc1.S" */
-dividend	.req	r0
-divisor		.req	r1
-overdone	.req	r2
-curbit		.req	r3
-/* ip		.req	r12	*/
-/* sp		.req	r13	*/
-/* lr		.req	r14	*/
-/* pc		.req	r15	*/
-	.text
-	.type  __umodsi3       ,function
-	.align 0
- ENTRY(__umodsi3)
-	cmp	divisor, #0
-	beq	Ldiv0
-	mov	curbit, #1
-	cmp	dividend, divisor
-	movcc	pc, lr
-Loop1:
-	@ Unless the divisor is very big, shift it up in multiples of
-	@ four bits, since this is the amount of unwinding in the main
-	@ division loop.  Continue shifting until the divisor is
-	@ larger than the dividend.
-	cmp	divisor, #0x10000000
-	cmpcc	divisor, dividend
-	movcc	divisor, divisor, lsl #4
-	movcc	curbit, curbit, lsl #4
-	bcc	Loop1
-Lbignum:
-	@ For very big divisors, we must shift it a bit at a time, or
-	@ we will be in danger of overflowing.
-	cmp	divisor, #0x80000000
-	cmpcc	divisor, dividend
-	movcc	divisor, divisor, lsl #1
-	movcc	curbit, curbit, lsl #1
-	bcc	Lbignum
-Loop3:
-	@ Test for possible subtractions.  On the final pass, this may
-	@ subtract too much from the dividend, so keep track of which
-	@ subtractions are done, we can fix them up afterwards...
-	mov	overdone, #0
-	cmp	dividend, divisor
-	subcs	dividend, dividend, divisor
-	cmp	dividend, divisor, lsr #1
-	subcs	dividend, dividend, divisor, lsr #1
-	orrcs	overdone, overdone, curbit, ror #1
-	cmp	dividend, divisor, lsr #2
-	subcs	dividend, dividend, divisor, lsr #2
-	orrcs	overdone, overdone, curbit, ror #2
-	cmp	dividend, divisor, lsr #3
-	subcs	dividend, dividend, divisor, lsr #3
-	orrcs	overdone, overdone, curbit, ror #3
-	mov	ip, curbit
-	cmp	dividend, #0			@ Early termination?
-	movnes	curbit, curbit, lsr #4		@ No, any more bits to do?
-	movne	divisor, divisor, lsr #4
-	bne	Loop3
-	@ Any subtractions that we should not have done will be recorded in
-	@ the top three bits of "overdone".  Exactly which were not needed
-	@ are governed by the position of the bit, stored in ip.
-	@ If we terminated early, because dividend became zero,
-	@ then none of the below will match, since the bit in ip will not be
-	@ in the bottom nibble.
-	ands	overdone, overdone, #0xe0000000
-	moveq	pc, lr				@ No fixups needed
-	tst	overdone, ip, ror #3
-	addne	dividend, dividend, divisor, lsr #3
-	tst	overdone, ip, ror #2
-	addne	dividend, dividend, divisor, lsr #2
-	tst	overdone, ip, ror #1
-	addne	dividend, dividend, divisor, lsr #1
-	mov	pc, lr
-Ldiv0:
-	str	lr, [sp, #-4]!
-	bl	 __div0       (PLT)
-	mov	r0, #0			@ about as wrong as it could be
-	ldmia	sp!, {pc}
-	.size  __umodsi3       , . -  __umodsi3
-/* # 320 "libgcc1.S" */
-/* # 421 "libgcc1.S" */
-/* # 433 "libgcc1.S" */
-/* # 456 "libgcc1.S" */
-/* # 500 "libgcc1.S" */
-/* # 580 "libgcc1.S" */
-ENDPROC(__umodsi3)
-- 
2.7.0

[U-Boot] [PATCH 05/12] arm: lib: Sync libgcc 32b division/modulo operations

[Tom Rini]

On Thu, May 26, 2016 at 06:01:40PM +0200, Marek Vasut wrote:

> Sync the libgcc 32bit division and modulo operations with Linux 4.4.6 ,
> commit 0d1912303e54ed1b2a371be0bba51c384dd57326 . The functions in these
> four files are present in lib1funcs.S in Linux, so replace these files
> with lib1funcs.S from Linux.
> 
> Since we do not support stack unwinding, instead of importing the whole
> asm/unwind.h and all the baggage, this patch defines empty UNWIND() macro
> in lib1funcs.S . Moreover, to make all of the functions available, define
> CONFIG_AEABI , which is safe, because U-Boot is always compiled with ARM
> EABI.
> 
> This patch also defines CONFIG_THUMB2_KERNEL and CONFIG_ARM_ASM_UNIFIED
> which is necessary for correct build of these files both in ARM and
> Thumb mode, just like Linux does.
> 
> Signed-off-by: Marek Vasut <marex@denx.de>
> Cc: Albert Aribaud <albert.u.boot@aribaud.net>
> Cc: Masahiro Yamada <yamada.masahiro@socionext.com>
> Cc: Simon Glass <sjg@chromium.org>
> Cc: Tom Rini <trini@konsulko.com>

Reviewed-by: Tom Rini <trini@konsulko.com>

-- 
Tom
-------------- next part --------------
A non-text attachment was scrubbed...
Name: signature.asc
Type: application/pgp-signature
Size: 819 bytes
Desc: Digital signature
URL: <http://lists.denx.de/pipermail/u-boot/attachments/20160602/60d017fa/attachment.sig>

[U-Boot] [U-Boot, 05/12] arm: lib: Sync libgcc 32b division/modulo operations

[Tom Rini]

On Thu, May 26, 2016 at 06:01:40PM +0200, Marek Vasut wrote:

> Sync the libgcc 32bit division and modulo operations with Linux 4.4.6 ,
> commit 0d1912303e54ed1b2a371be0bba51c384dd57326 . The functions in these
> four files are present in lib1funcs.S in Linux, so replace these files
> with lib1funcs.S from Linux.
> 
> Since we do not support stack unwinding, instead of importing the whole
> asm/unwind.h and all the baggage, this patch defines empty UNWIND() macro
> in lib1funcs.S . Moreover, to make all of the functions available, define
> CONFIG_AEABI , which is safe, because U-Boot is always compiled with ARM
> EABI.
> 
> This patch also defines CONFIG_THUMB2_KERNEL and CONFIG_ARM_ASM_UNIFIED
> which is necessary for correct build of these files both in ARM and
> Thumb mode, just like Linux does.
> 
> Signed-off-by: Marek Vasut <marex@denx.de>
> Cc: Albert Aribaud <albert.u.boot@aribaud.net>
> Cc: Masahiro Yamada <yamada.masahiro@socionext.com>
> Cc: Simon Glass <sjg@chromium.org>
> Cc: Tom Rini <trini@konsulko.com>
> Reviewed-by: Tom Rini <trini@konsulko.com>

Applied to u-boot/master, thanks!

-- 
Tom
-------------- next part --------------
A non-text attachment was scrubbed...
Name: signature.asc
Type: application/pgp-signature
Size: 819 bytes
Desc: Digital signature
URL: <http://lists.denx.de/pipermail/u-boot/attachments/20160603/84f49e00/attachment.sig>

[U-Boot] [PATCH 06/12] arm: lib: Fix uldivmod.S build on Thumb2

[Marek Vasut]

This assembler source won't build in Thumb2 mode, so fix it adding
the necessary Thumb2 conditional macros from unified.h .

This patch also defines CONFIG_THUMB2_KERNEL and CONFIG_ARM_ASM_UNIFIED
which is necessary for correct build of these files both in ARM and
Thumb mode, just like Linux does.

Signed-off-by: Marek Vasut <marex@denx.de>
Cc: Albert Aribaud <albert.u.boot@aribaud.net>
Cc: Masahiro Yamada <yamada.masahiro@socionext.com>
Cc: Simon Glass <sjg@chromium.org>
Cc: Tom Rini <trini@konsulko.com>
---
 arch/arm/lib/uldivmod.S | 8 +++-----
 1 file changed, 3 insertions(+), 5 deletions(-)

diff --git a/arch/arm/lib/uldivmod.S b/arch/arm/lib/uldivmod.S
index 426c2f2..2efcd73 100644
--- a/arch/arm/lib/uldivmod.S
+++ b/arch/arm/lib/uldivmod.S
@@ -9,10 +9,6 @@
 #include <linux/linkage.h>
 #include <asm/assembler.h>
 
-/* We don't use Thumb instructions for now */
-#define ARM(x...)	x
-#define THUMB(x...)
-
 /*
  * A, Q = r0 + (r1 << 32)
  * B, R = r2 + (r3 << 32)
@@ -226,7 +222,9 @@ THUMB(	orrpl	A_0, A_0, TMP		)
 	@ Shift A to the right by the appropriate amount.
 	rsb	D_1, D_0, #32
 	mov	Q_0, A_0, lsr D_0
-	orr	Q_0, A_1, lsl D_1
+ ARM(   orr     Q_0, Q_0, A_1, lsl D_1	)
+ THUMB(	lsl	A_1, D_1		)
+ THUMB(	orr	Q_0, A_1		)
 	mov	Q_1, A_1, lsr D_0
 	@ Move C to R
 	mov	R_0, C_0
-- 
2.7.0

[U-Boot] [PATCH 06/12] arm: lib: Fix uldivmod.S build on Thumb2

[Tom Rini]

On Thu, May 26, 2016 at 06:01:41PM +0200, Marek Vasut wrote:

> This assembler source won't build in Thumb2 mode, so fix it adding
> the necessary Thumb2 conditional macros from unified.h .
> 
> This patch also defines CONFIG_THUMB2_KERNEL and CONFIG_ARM_ASM_UNIFIED
> which is necessary for correct build of these files both in ARM and
> Thumb mode, just like Linux does.
> 
> Signed-off-by: Marek Vasut <marex@denx.de>
> Cc: Albert Aribaud <albert.u.boot@aribaud.net>
> Cc: Masahiro Yamada <yamada.masahiro@socionext.com>
> Cc: Simon Glass <sjg@chromium.org>
> Cc: Tom Rini <trini@konsulko.com>

Reviewed-by: Tom Rini <trini@konsulko.com>

-- 
Tom
-------------- next part --------------
A non-text attachment was scrubbed...
Name: signature.asc
Type: application/pgp-signature
Size: 819 bytes
Desc: Digital signature
URL: <http://lists.denx.de/pipermail/u-boot/attachments/20160602/2bfbdd12/attachment.sig>

[U-Boot] [U-Boot, 06/12] arm: lib: Fix uldivmod.S build on Thumb2

[Tom Rini]

On Thu, May 26, 2016 at 06:01:41PM +0200, Marek Vasut wrote:

> This assembler source won't build in Thumb2 mode, so fix it adding
> the necessary Thumb2 conditional macros from unified.h .
> 
> This patch also defines CONFIG_THUMB2_KERNEL and CONFIG_ARM_ASM_UNIFIED
> which is necessary for correct build of these files both in ARM and
> Thumb mode, just like Linux does.
> 
> Signed-off-by: Marek Vasut <marex@denx.de>
> Cc: Albert Aribaud <albert.u.boot@aribaud.net>
> Cc: Masahiro Yamada <yamada.masahiro@socionext.com>
> Cc: Simon Glass <sjg@chromium.org>
> Cc: Tom Rini <trini@konsulko.com>
> Reviewed-by: Tom Rini <trini@konsulko.com>

Applied to u-boot/master, thanks!

-- 
Tom
-------------- next part --------------
A non-text attachment was scrubbed...
Name: signature.asc
Type: application/pgp-signature
Size: 819 bytes
Desc: Digital signature
URL: <http://lists.denx.de/pipermail/u-boot/attachments/20160603/19c5f467/attachment.sig>

[U-Boot] [PATCH 07/12] arm: lib: Import __do_div64 from Linux

[Marek Vasut]

Import __do_div64 from Linux 4.4.6 , commit 0d1912303e54ed1b2a371be0bba51c384dd57326
on arm32. This function is for some toolchains, which generate _udivmoddi4()
for 64 bit division.

Since we do not support stack unwinding, instead of importing the whole
asm/unwind.h and all the baggage, this patch defines empty UNWIND() macro.

This patch also defines CONFIG_THUMB2_KERNEL and CONFIG_ARM_ASM_UNIFIED
which is necessary for correct build of these files both in ARM and
Thumb mode, just like Linux does.

Signed-off-by: Marek Vasut <marex@denx.de>
Cc: Albert Aribaud <albert.u.boot@aribaud.net>
Cc: Masahiro Yamada <yamada.masahiro@socionext.com>
Cc: Simon Glass <sjg@chromium.org>
Cc: Tom Rini <trini@konsulko.com>
---
 arch/arm/lib/Makefile |   2 +-
 arch/arm/lib/div64.S  | 212 ++++++++++++++++++++++++++++++++++++++++++++++++++
 2 files changed, 213 insertions(+), 1 deletion(-)
 create mode 100644 arch/arm/lib/div64.S

diff --git a/arch/arm/lib/Makefile b/arch/arm/lib/Makefile
index 0b0dbcb..8945915 100644
--- a/arch/arm/lib/Makefile
+++ b/arch/arm/lib/Makefile
@@ -6,7 +6,7 @@
 #
 
 lib-$(CONFIG_USE_PRIVATE_LIBGCC) += ashldi3.o ashrdi3.o lshrdi3.o \
-				    lib1funcs.o uldivmod.o div0.o
+				    lib1funcs.o uldivmod.o div0.o div64.o
 
 ifdef CONFIG_CPU_V7M
 obj-y	+= vectors_m.o crt0.o
diff --git a/arch/arm/lib/div64.S b/arch/arm/lib/div64.S
new file mode 100644
index 0000000..03986c2
--- /dev/null
+++ b/arch/arm/lib/div64.S
@@ -0,0 +1,212 @@
+/*
+ *  linux/arch/arm/lib/div64.S
+ *
+ *  Optimized computation of 64-bit dividend / 32-bit divisor
+ *
+ *  Author:	Nicolas Pitre
+ *  Created:	Oct 5, 2003
+ *  Copyright:	Monta Vista Software, Inc.
+ *
+ *  SPDX-License-Identifier:	GPL-2.0
+ */
+
+#include <linux/linkage.h>
+#include <asm/assembler.h>
+#ifdef __UBOOT__
+#define UNWIND(x...)
+#endif
+
+#ifdef __ARMEB__
+#define xh r0
+#define xl r1
+#define yh r2
+#define yl r3
+#else
+#define xl r0
+#define xh r1
+#define yl r2
+#define yh r3
+#endif
+
+/*
+ * __do_div64: perform a division with 64-bit dividend and 32-bit divisor.
+ *
+ * Note: Calling convention is totally non standard for optimal code.
+ *       This is meant to be used by do_div() from include/asm/div64.h only.
+ *
+ * Input parameters:
+ * 	xh-xl	= dividend (clobbered)
+ * 	r4	= divisor (preserved)
+ *
+ * Output values:
+ * 	yh-yl	= result
+ * 	xh	= remainder
+ *
+ * Clobbered regs: xl, ip
+ */
+
+ENTRY(__do_div64)
+UNWIND(.fnstart)
+
+	@ Test for easy paths first.
+	subs	ip, r4, #1
+	bls	9f			@ divisor is 0 or 1
+	tst	ip, r4
+	beq	8f			@ divisor is power of 2
+
+	@ See if we need to handle upper 32-bit result.
+	cmp	xh, r4
+	mov	yh, #0
+	blo	3f
+
+	@ Align divisor with upper part of dividend.
+	@ The aligned divisor is stored in yl preserving the original.
+	@ The bit position is stored in ip.
+
+#if __LINUX_ARM_ARCH__ >= 5
+
+	clz	yl, r4
+	clz	ip, xh
+	sub	yl, yl, ip
+	mov	ip, #1
+	mov	ip, ip, lsl yl
+	mov	yl, r4, lsl yl
+
+#else
+
+	mov	yl, r4
+	mov	ip, #1
+1:	cmp	yl, #0x80000000
+	cmpcc	yl, xh
+	movcc	yl, yl, lsl #1
+	movcc	ip, ip, lsl #1
+	bcc	1b
+
+#endif
+
+	@ The division loop for needed upper bit positions.
+ 	@ Break out early if dividend reaches 0.
+2:	cmp	xh, yl
+	orrcs	yh, yh, ip
+	subcss	xh, xh, yl
+	movnes	ip, ip, lsr #1
+	mov	yl, yl, lsr #1
+	bne	2b
+
+	@ See if we need to handle lower 32-bit result.
+3:	cmp	xh, #0
+	mov	yl, #0
+	cmpeq	xl, r4
+	movlo	xh, xl
+	retlo	lr
+
+	@ The division loop for lower bit positions.
+	@ Here we shift remainer bits leftwards rather than moving the
+	@ divisor for comparisons, considering the carry-out bit as well.
+	mov	ip, #0x80000000
+4:	movs	xl, xl, lsl #1
+	adcs	xh, xh, xh
+	beq	6f
+	cmpcc	xh, r4
+5:	orrcs	yl, yl, ip
+	subcs	xh, xh, r4
+	movs	ip, ip, lsr #1
+	bne	4b
+	ret	lr
+
+	@ The top part of remainder became zero.  If carry is set
+	@ (the 33th bit) this is a false positive so resume the loop.
+	@ Otherwise, if lower part is also null then we are done.
+6:	bcs	5b
+	cmp	xl, #0
+	reteq	lr
+
+	@ We still have remainer bits in the low part.  Bring them up.
+
+#if __LINUX_ARM_ARCH__ >= 5
+
+	clz	xh, xl			@ we know xh is zero here so...
+	add	xh, xh, #1
+	mov	xl, xl, lsl xh
+	mov	ip, ip, lsr xh
+
+#else
+
+7:	movs	xl, xl, lsl #1
+	mov	ip, ip, lsr #1
+	bcc	7b
+
+#endif
+
+	@ Current remainder is now 1.  It is worthless to compare with
+	@ divisor at this point since divisor can not be smaller than 3 here.
+	@ If possible, branch for another shift in the division loop.
+	@ If no bit position left then we are done.
+	movs	ip, ip, lsr #1
+	mov	xh, #1
+	bne	4b
+	ret	lr
+
+8:	@ Division by a power of 2: determine what that divisor order is
+	@ then simply shift values around
+
+#if __LINUX_ARM_ARCH__ >= 5
+
+	clz	ip, r4
+	rsb	ip, ip, #31
+
+#else
+
+	mov	yl, r4
+	cmp	r4, #(1 << 16)
+	mov	ip, #0
+	movhs	yl, yl, lsr #16
+	movhs	ip, #16
+
+	cmp	yl, #(1 << 8)
+	movhs	yl, yl, lsr #8
+	addhs	ip, ip, #8
+
+	cmp	yl, #(1 << 4)
+	movhs	yl, yl, lsr #4
+	addhs	ip, ip, #4
+
+	cmp	yl, #(1 << 2)
+	addhi	ip, ip, #3
+	addls	ip, ip, yl, lsr #1
+
+#endif
+
+	mov	yh, xh, lsr ip
+	mov	yl, xl, lsr ip
+	rsb	ip, ip, #32
+ ARM(	orr	yl, yl, xh, lsl ip	)
+ THUMB(	lsl	xh, xh, ip		)
+ THUMB(	orr	yl, yl, xh		)
+	mov	xh, xl, lsl ip
+	mov	xh, xh, lsr ip
+	ret	lr
+
+	@ eq -> division by 1: obvious enough...
+9:	moveq	yl, xl
+	moveq	yh, xh
+	moveq	xh, #0
+	reteq	lr
+UNWIND(.fnend)
+
+UNWIND(.fnstart)
+UNWIND(.pad #4)
+UNWIND(.save {lr})
+Ldiv0_64:
+	@ Division by 0:
+	str	lr, [sp, #-8]!
+	bl	__div0
+
+	@ as wrong as it could be...
+	mov	yl, #0
+	mov	yh, #0
+	mov	xh, #0
+	ldr	pc, [sp], #8
+
+UNWIND(.fnend)
+ENDPROC(__do_div64)
-- 
2.7.0

[U-Boot] [PATCH 07/12] arm: lib: Import __do_div64 from Linux

[Tom Rini]

On Thu, May 26, 2016 at 06:01:42PM +0200, Marek Vasut wrote:

> Import __do_div64 from Linux 4.4.6 , commit 0d1912303e54ed1b2a371be0bba51c384dd57326
> on arm32. This function is for some toolchains, which generate _udivmoddi4()
> for 64 bit division.
> 
> Since we do not support stack unwinding, instead of importing the whole
> asm/unwind.h and all the baggage, this patch defines empty UNWIND() macro.
> 
> This patch also defines CONFIG_THUMB2_KERNEL and CONFIG_ARM_ASM_UNIFIED
> which is necessary for correct build of these files both in ARM and
> Thumb mode, just like Linux does.
> 
> Signed-off-by: Marek Vasut <marex@denx.de>
> Cc: Albert Aribaud <albert.u.boot@aribaud.net>
> Cc: Masahiro Yamada <yamada.masahiro@socionext.com>
> Cc: Simon Glass <sjg@chromium.org>
> Cc: Tom Rini <trini@konsulko.com>

Reviewed-by: Tom Rini <trini@konsulko.com>

-- 
Tom
-------------- next part --------------
A non-text attachment was scrubbed...
Name: signature.asc
Type: application/pgp-signature
Size: 819 bytes
Desc: Digital signature
URL: <http://lists.denx.de/pipermail/u-boot/attachments/20160602/01172fa4/attachment.sig>

[U-Boot] [U-Boot,07/12] arm: lib: Import __do_div64 from Linux

[Tom Rini]

On Thu, May 26, 2016 at 06:01:42PM +0200, Marek Vasut wrote:

> Import __do_div64 from Linux 4.4.6 , commit 0d1912303e54ed1b2a371be0bba51c384dd57326
> on arm32. This function is for some toolchains, which generate _udivmoddi4()
> for 64 bit division.
> 
> Since we do not support stack unwinding, instead of importing the whole
> asm/unwind.h and all the baggage, this patch defines empty UNWIND() macro.
> 
> This patch also defines CONFIG_THUMB2_KERNEL and CONFIG_ARM_ASM_UNIFIED
> which is necessary for correct build of these files both in ARM and
> Thumb mode, just like Linux does.
> 
> Signed-off-by: Marek Vasut <marex@denx.de>
> Cc: Albert Aribaud <albert.u.boot@aribaud.net>
> Cc: Masahiro Yamada <yamada.masahiro@socionext.com>
> Cc: Simon Glass <sjg@chromium.org>
> Cc: Tom Rini <trini@konsulko.com>
> Reviewed-by: Tom Rini <trini@konsulko.com>

Applied to u-boot/master, thanks!

-- 
Tom
-------------- next part --------------
A non-text attachment was scrubbed...
Name: signature.asc
Type: application/pgp-signature
Size: 819 bytes
Desc: Digital signature
URL: <http://lists.denx.de/pipermail/u-boot/attachments/20160603/db00f39b/attachment.sig>

[U-Boot] [PATCH 08/12] arm: lib: Repair Warning: conditional infixes are deprecated in unified syntax

[Marek Vasut]

Fix the following warning when building for thumb2 target by tweaking the
instruction syntax:

Warning: conditional infixes are deprecated in unified syntax

Signed-off-by: Marek Vasut <marex@denx.de>
Cc: Albert Aribaud <albert.u.boot@aribaud.net>
Cc: Masahiro Yamada <yamada.masahiro@socionext.com>
Cc: Simon Glass <sjg@chromium.org>
Cc: Tom Rini <trini@konsulko.com>
---
 arch/arm/lib/div64.S     | 4 ++--
 arch/arm/lib/lib1funcs.S | 4 ++--
 2 files changed, 4 insertions(+), 4 deletions(-)

diff --git a/arch/arm/lib/div64.S b/arch/arm/lib/div64.S
index 03986c2..a42a0f0 100644
--- a/arch/arm/lib/div64.S
+++ b/arch/arm/lib/div64.S
@@ -88,8 +88,8 @@ UNWIND(.fnstart)
  	@ Break out early if dividend reaches 0.
 2:	cmp	xh, yl
 	orrcs	yh, yh, ip
-	subcss	xh, xh, yl
-	movnes	ip, ip, lsr #1
+	subscs	xh, xh, yl
+	movsne	ip, ip, lsr #1
 	mov	yl, yl, lsr #1
 	bne	2b
 
diff --git a/arch/arm/lib/lib1funcs.S b/arch/arm/lib/lib1funcs.S
index 5871dbe..c343ea9 100644
--- a/arch/arm/lib/lib1funcs.S
+++ b/arch/arm/lib/lib1funcs.S
@@ -84,7 +84,7 @@
 	subhs	\dividend, \dividend, \divisor, lsr #3
 	orrhs	\result,   \result,   \curbit,  lsr #3
 	cmp	\dividend, #0			@ Early termination?
-	movnes	\curbit,   \curbit,  lsr #4	@ No, any more bits to do?
+	movsne	\curbit,   \curbit,  lsr #4	@ No, any more bits to do?
 	movne	\divisor,  \divisor, lsr #4
 	bne	1b
 
@@ -170,7 +170,7 @@
 	subhs	\dividend, \dividend, \divisor, lsr #3
 	cmp	\dividend, #1
 	mov	\divisor, \divisor, lsr #4
-	subges	\order, \order, #4
+	subsge	\order, \order, #4
 	bge	1b
 
 	tst	\order, #3
-- 
2.7.0

[U-Boot] [PATCH 08/12] arm: lib: Repair Warning: conditional infixes are deprecated in unified syntax

[Tom Rini]

On Thu, May 26, 2016 at 06:01:43PM +0200, Marek Vasut wrote:

> Fix the following warning when building for thumb2 target by tweaking the
> instruction syntax:
> 
> Warning: conditional infixes are deprecated in unified syntax
> 
> Signed-off-by: Marek Vasut <marex@denx.de>
> Cc: Albert Aribaud <albert.u.boot@aribaud.net>
> Cc: Masahiro Yamada <yamada.masahiro@socionext.com>
> Cc: Simon Glass <sjg@chromium.org>
> Cc: Tom Rini <trini@konsulko.com>

Reviewed-by: Tom Rini <trini@konsulko.com>

-- 
Tom
-------------- next part --------------
A non-text attachment was scrubbed...
Name: signature.asc
Type: application/pgp-signature
Size: 819 bytes
Desc: Digital signature
URL: <http://lists.denx.de/pipermail/u-boot/attachments/20160602/e54ada62/attachment.sig>

[U-Boot] [U-Boot, 08/12] arm: lib: Repair Warning: conditional infixes are deprecated in unified syntax

[Tom Rini]

On Thu, May 26, 2016 at 06:01:43PM +0200, Marek Vasut wrote:

> Fix the following warning when building for thumb2 target by tweaking the
> instruction syntax:
> 
> Warning: conditional infixes are deprecated in unified syntax
> 
> Signed-off-by: Marek Vasut <marex@denx.de>
> Cc: Albert Aribaud <albert.u.boot@aribaud.net>
> Cc: Masahiro Yamada <yamada.masahiro@socionext.com>
> Cc: Simon Glass <sjg@chromium.org>
> Cc: Tom Rini <trini@konsulko.com>
> Reviewed-by: Tom Rini <trini@konsulko.com>

Applied to u-boot/master, thanks!

-- 
Tom
-------------- next part --------------
A non-text attachment was scrubbed...
Name: signature.asc
Type: application/pgp-signature
Size: 819 bytes
Desc: Digital signature
URL: <http://lists.denx.de/pipermail/u-boot/attachments/20160603/838f2eba/attachment.sig>

[U-Boot] [PATCH 09/12] arm: lib: import muldi3.S from Linux

[Marek Vasut]

Import muldi3.S from Linux 4.4.6 , commit 0d1912303e54ed1b2a371be0bba51c384dd57326
on arm32. This file implements __aeabi_lmul and it's alias __muldi3, which
is needed when doing Thumb1 builds.

This patch also defines CONFIG_THUMB2_KERNEL and CONFIG_ARM_ASM_UNIFIED
which is necessary for correct build of these files both in ARM and
Thumb mode, just like Linux does.

Signed-off-by: Marek Vasut <marex@denx.de>
Cc: Albert Aribaud <albert.u.boot@aribaud.net>
Cc: Masahiro Yamada <yamada.masahiro@socionext.com>
Cc: Simon Glass <sjg@chromium.org>
Cc: Tom Rini <trini@konsulko.com>
---
 arch/arm/lib/Makefile |  3 ++-
 arch/arm/lib/muldi3.S | 46 ++++++++++++++++++++++++++++++++++++++++++++++
 2 files changed, 48 insertions(+), 1 deletion(-)
 create mode 100644 arch/arm/lib/muldi3.S

diff --git a/arch/arm/lib/Makefile b/arch/arm/lib/Makefile
index 8945915..86489fd 100644
--- a/arch/arm/lib/Makefile
+++ b/arch/arm/lib/Makefile
@@ -6,7 +6,8 @@
 #
 
 lib-$(CONFIG_USE_PRIVATE_LIBGCC) += ashldi3.o ashrdi3.o lshrdi3.o \
-				    lib1funcs.o uldivmod.o div0.o div64.o
+				    lib1funcs.o uldivmod.o div0.o \
+				    div64.o muldi3.o
 
 ifdef CONFIG_CPU_V7M
 obj-y	+= vectors_m.o crt0.o
diff --git a/arch/arm/lib/muldi3.S b/arch/arm/lib/muldi3.S
new file mode 100644
index 0000000..daa5704
--- /dev/null
+++ b/arch/arm/lib/muldi3.S
@@ -0,0 +1,46 @@
+/*
+ *  linux/arch/arm/lib/muldi3.S
+ *
+ *  Author:     Nicolas Pitre
+ *  Created:    Oct 19, 2005
+ *  Copyright:  Monta Vista Software, Inc.
+ *
+ *  SPDX-License-Identifier:	GPL-2.0
+ */
+
+#include <linux/linkage.h>
+#include <asm/assembler.h>
+
+#ifdef __ARMEB__
+#define xh r0
+#define xl r1
+#define yh r2
+#define yl r3
+#else
+#define xl r0
+#define xh r1
+#define yl r2
+#define yh r3
+#endif
+
+ENTRY(__muldi3)
+ENTRY(__aeabi_lmul)
+
+	mul	xh, yl, xh
+	mla	xh, xl, yh, xh
+	mov	ip, xl, lsr #16
+	mov	yh, yl, lsr #16
+	bic	xl, xl, ip, lsl #16
+	bic	yl, yl, yh, lsl #16
+	mla	xh, yh, ip, xh
+	mul	yh, xl, yh
+	mul	xl, yl, xl
+	mul	ip, yl, ip
+	adds	xl, xl, yh, lsl #16
+	adc	xh, xh, yh, lsr #16
+	adds	xl, xl, ip, lsl #16
+	adc	xh, xh, ip, lsr #16
+	ret	lr
+
+ENDPROC(__muldi3)
+ENDPROC(__aeabi_lmul)
-- 
2.7.0

[U-Boot] [PATCH 09/12] arm: lib: import muldi3.S from Linux

[Tom Rini]

On Thu, May 26, 2016 at 06:01:44PM +0200, Marek Vasut wrote:

> Import muldi3.S from Linux 4.4.6 , commit 0d1912303e54ed1b2a371be0bba51c384dd57326
> on arm32. This file implements __aeabi_lmul and it's alias __muldi3, which
> is needed when doing Thumb1 builds.
> 
> This patch also defines CONFIG_THUMB2_KERNEL and CONFIG_ARM_ASM_UNIFIED
> which is necessary for correct build of these files both in ARM and
> Thumb mode, just like Linux does.
> 
> Signed-off-by: Marek Vasut <marex@denx.de>
> Cc: Albert Aribaud <albert.u.boot@aribaud.net>
> Cc: Masahiro Yamada <yamada.masahiro@socionext.com>
> Cc: Simon Glass <sjg@chromium.org>
> Cc: Tom Rini <trini@konsulko.com>

Reviewed-by: Tom Rini <trini@konsulko.com>

-- 
Tom
-------------- next part --------------
A non-text attachment was scrubbed...
Name: signature.asc
Type: application/pgp-signature
Size: 819 bytes
Desc: Digital signature
URL: <http://lists.denx.de/pipermail/u-boot/attachments/20160602/b5187b33/attachment.sig>

[U-Boot] [U-Boot,09/12] arm: lib: import muldi3.S from Linux

[Tom Rini]

On Thu, May 26, 2016 at 06:01:44PM +0200, Marek Vasut wrote:

> Import muldi3.S from Linux 4.4.6 , commit 0d1912303e54ed1b2a371be0bba51c384dd57326
> on arm32. This file implements __aeabi_lmul and it's alias __muldi3, which
> is needed when doing Thumb1 builds.
> 
> This patch also defines CONFIG_THUMB2_KERNEL and CONFIG_ARM_ASM_UNIFIED
> which is necessary for correct build of these files both in ARM and
> Thumb mode, just like Linux does.
> 
> Signed-off-by: Marek Vasut <marex@denx.de>
> Cc: Albert Aribaud <albert.u.boot@aribaud.net>
> Cc: Masahiro Yamada <yamada.masahiro@socionext.com>
> Cc: Simon Glass <sjg@chromium.org>
> Cc: Tom Rini <trini@konsulko.com>
> Reviewed-by: Tom Rini <trini@konsulko.com>

Applied to u-boot/master, thanks!

-- 
Tom
-------------- next part --------------
A non-text attachment was scrubbed...
Name: signature.asc
Type: application/pgp-signature
Size: 819 bytes
Desc: Digital signature
URL: <http://lists.denx.de/pipermail/u-boot/attachments/20160603/020e658b/attachment.sig>

[U-Boot] [PATCH 10/12] arm: lib: Import Thumb1 functions

[Marek Vasut]

Import functions into lib1funcs.S which are required for Thumb1
build. These functions come from gcc 5.3.1 release.

Signed-off-by: Marek Vasut <marex@denx.de>
Cc: Albert Aribaud <albert.u.boot@aribaud.net>
Cc: Masahiro Yamada <yamada.masahiro@socionext.com>
Cc: Simon Glass <sjg@chromium.org>
Cc: Tom Rini <trini@konsulko.com>
---
 arch/arm/lib/lib1funcs.S | 53 ++++++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 53 insertions(+)

diff --git a/arch/arm/lib/lib1funcs.S b/arch/arm/lib/lib1funcs.S
index c343ea9..408839b 100644
--- a/arch/arm/lib/lib1funcs.S
+++ b/arch/arm/lib/lib1funcs.S
@@ -349,3 +349,56 @@ UNWIND(.save {lr})
 	ldr	pc, [sp], #8
 UNWIND(.fnend)
 ENDPROC(Ldiv0)
+
+/* Thumb-1 specialities */
+#if defined(CONFIG_SYS_THUMB_BUILD) && !defined(CONFIG_HAS_THUMB2)
+ENTRY(__gnu_thumb1_case_sqi)
+	push	{r1}
+	mov	r1, lr
+	lsrs	r1, r1, #1
+	lsls	r1, r1, #1
+	ldrsb	r1, [r1, r0]
+	lsls	r1, r1, #1
+	add	lr, lr, r1
+	pop	{r1}
+	bx	lr
+ENDPROC(__gnu_thumb1_case_sqi)
+
+ENTRY(__gnu_thumb1_case_uqi)
+	push	{r1}
+	mov	r1, lr
+	lsrs	r1, r1, #1
+	lsls	r1, r1, #1
+	ldrb	r1, [r1, r0]
+	lsls	r1, r1, #1
+	add	lr, lr, r1
+	pop	{r1}
+	bx	lr
+ENDPROC(__gnu_thumb1_case_uqi)
+
+ENTRY(__gnu_thumb1_case_shi)
+	push	{r0, r1}
+	mov	r1, lr
+	lsrs	r1, r1, #1
+	lsls	r0, r0, #1
+	lsls	r1, r1, #1
+	ldrsh	r1, [r1, r0]
+	lsls	r1, r1, #1
+	add	lr, lr, r1
+	pop	{r0, r1}
+	bx	lr
+ENDPROC(__gnu_thumb1_case_shi)
+
+ENTRY(__gnu_thumb1_case_uhi)
+	push	{r0, r1}
+	mov	r1, lr
+	lsrs	r1, r1, #1
+	lsls	r0, r0, #1
+	lsls	r1, r1, #1
+	ldrh	r1, [r1, r0]
+	lsls	r1, r1, #1
+	add	lr, lr, r1
+	pop	{r0, r1}
+	bx	lr
+ENDPROC(__gnu_thumb1_case_uhi)
+#endif
-- 
2.7.0

[U-Boot] [PATCH 10/12] arm: lib: Import Thumb1 functions

[Tom Rini]

On Thu, May 26, 2016 at 06:01:45PM +0200, Marek Vasut wrote:

> Import functions into lib1funcs.S which are required for Thumb1
> build. These functions come from gcc 5.3.1 release.
> 
> Signed-off-by: Marek Vasut <marex@denx.de>
> Cc: Albert Aribaud <albert.u.boot@aribaud.net>
> Cc: Masahiro Yamada <yamada.masahiro@socionext.com>
> Cc: Simon Glass <sjg@chromium.org>
> Cc: Tom Rini <trini@konsulko.com>

Reviewed-by: Tom Rini <trini@konsulko.com>

-- 
Tom
-------------- next part --------------
A non-text attachment was scrubbed...
Name: signature.asc
Type: application/pgp-signature
Size: 819 bytes
Desc: Digital signature
URL: <http://lists.denx.de/pipermail/u-boot/attachments/20160602/d57a3f0d/attachment.sig>

[U-Boot] [U-Boot,10/12] arm: lib: Import Thumb1 functions

[Tom Rini]

On Thu, May 26, 2016 at 06:01:45PM +0200, Marek Vasut wrote:

> Import functions into lib1funcs.S which are required for Thumb1
> build. These functions come from gcc 5.3.1 release.
> 
> Signed-off-by: Marek Vasut <marex@denx.de>
> Cc: Albert Aribaud <albert.u.boot@aribaud.net>
> Cc: Masahiro Yamada <yamada.masahiro@socionext.com>
> Cc: Simon Glass <sjg@chromium.org>
> Cc: Tom Rini <trini@konsulko.com>
> Reviewed-by: Tom Rini <trini@konsulko.com>

Applied to u-boot/master, thanks!

-- 
Tom
-------------- next part --------------
A non-text attachment was scrubbed...
Name: signature.asc
Type: application/pgp-signature
Size: 819 bytes
Desc: Digital signature
URL: <http://lists.denx.de/pipermail/u-boot/attachments/20160603/1ba4a299/attachment.sig>

[U-Boot] [PATCH 11/12] arm: lib: Split asm symbols into different .text subsections

[Marek Vasut]

Split each symbol in lib1funcs into different .text.foo section instead
of placing all of them into plain .text . This allows the linker to collect
and discard unused assembler symbols.

Signed-off-by: Marek Vasut <marex@denx.de>
Cc: Albert Aribaud <albert.u.boot@aribaud.net>
Cc: Masahiro Yamada <yamada.masahiro@socionext.com>
Cc: Simon Glass <sjg@chromium.org>
Cc: Tom Rini <trini@konsulko.com>
---
 arch/arm/lib/ashldi3.S   |  2 ++
 arch/arm/lib/ashrdi3.S   |  2 ++
 arch/arm/lib/div64.S     |  2 ++
 arch/arm/lib/lib1funcs.S | 25 +++++++++++++++++++++++++
 arch/arm/lib/lshrdi3.S   |  2 ++
 arch/arm/lib/muldi3.S    |  2 ++
 arch/arm/lib/uldivmod.S  |  3 +++
 7 files changed, 38 insertions(+)

diff --git a/arch/arm/lib/ashldi3.S b/arch/arm/lib/ashldi3.S
index a4f5ebb..6c9ae91 100644
--- a/arch/arm/lib/ashldi3.S
+++ b/arch/arm/lib/ashldi3.S
@@ -17,6 +17,7 @@
 
 ENTRY(__ashldi3)
 ENTRY(__aeabi_llsl)
+.pushsection .text.__ashldi3, "ax"
 
 	subs	r3, r2, #32
 	rsb	ip, r2, #32
@@ -28,5 +29,6 @@ ENTRY(__aeabi_llsl)
 	mov	al, al, lsl r2
 	ret	lr
 
+.popsection
 ENDPROC(__ashldi3)
 ENDPROC(__aeabi_llsl)
diff --git a/arch/arm/lib/ashrdi3.S b/arch/arm/lib/ashrdi3.S
index c6e1ed3..3eb59ec 100644
--- a/arch/arm/lib/ashrdi3.S
+++ b/arch/arm/lib/ashrdi3.S
@@ -17,6 +17,7 @@
 
 ENTRY(__ashrdi3)
 ENTRY(__aeabi_lasr)
+.pushsection .text.__ashrdi3, "ax"
 
 	subs	r3, r2, #32
 	rsb	ip, r2, #32
@@ -28,5 +29,6 @@ ENTRY(__aeabi_lasr)
 	mov	ah, ah, asr r2
 	ret	lr
 
+.popsection
 ENDPROC(__ashrdi3)
 ENDPROC(__aeabi_lasr)
diff --git a/arch/arm/lib/div64.S b/arch/arm/lib/div64.S
index a42a0f0..5bfb41d 100644
--- a/arch/arm/lib/div64.S
+++ b/arch/arm/lib/div64.S
@@ -47,6 +47,7 @@
 
 ENTRY(__do_div64)
 UNWIND(.fnstart)
+.pushsection .text.__do_div64, "ax"
 
 	@ Test for easy paths first.
 	subs	ip, r4, #1
@@ -192,6 +193,7 @@ UNWIND(.fnstart)
 	moveq	yh, xh
 	moveq	xh, #0
 	reteq	lr
+.popsection
 UNWIND(.fnend)
 
 UNWIND(.fnstart)
diff --git a/arch/arm/lib/lib1funcs.S b/arch/arm/lib/lib1funcs.S
index 408839b..f1becda 100644
--- a/arch/arm/lib/lib1funcs.S
+++ b/arch/arm/lib/lib1funcs.S
@@ -196,6 +196,7 @@
 ENTRY(__udivsi3)
 ENTRY(__aeabi_uidiv)
 UNWIND(.fnstart)
+.pushsection .text.__udivsi3, "ax"
 
 	subs	r2, r1, #1
 	reteq	lr
@@ -219,12 +220,14 @@ UNWIND(.fnstart)
 	mov	r0, r0, lsr r2
 	ret	lr
 
+.popsection
 UNWIND(.fnend)
 ENDPROC(__udivsi3)
 ENDPROC(__aeabi_uidiv)
 
 ENTRY(__umodsi3)
 UNWIND(.fnstart)
+.pushsection .text.__umodsi3, "ax"
 
 	subs	r2, r1, #1			@ compare divisor with 1
 	bcc	Ldiv0
@@ -238,12 +241,14 @@ UNWIND(.fnstart)
 
 	ret	lr
 
+.popsection
 UNWIND(.fnend)
 ENDPROC(__umodsi3)
 
 ENTRY(__divsi3)
 ENTRY(__aeabi_idiv)
 UNWIND(.fnstart)
+.pushsection .text.__divsi3, "ax"
 
 	cmp	r1, #0
 	eor	ip, r0, r1			@ save the sign of the result.
@@ -280,12 +285,14 @@ UNWIND(.fnstart)
 	rsbmi	r0, r0, #0
 	ret	lr
 
+.popsection
 UNWIND(.fnend)
 ENDPROC(__divsi3)
 ENDPROC(__aeabi_idiv)
 
 ENTRY(__modsi3)
 UNWIND(.fnstart)
+.pushsection .text.__modsi3, "ax"
 
 	cmp	r1, #0
 	beq	Ldiv0
@@ -305,6 +312,7 @@ UNWIND(.fnstart)
 	rsbmi	r0, r0, #0
 	ret	lr
 
+.popsection
 UNWIND(.fnend)
 ENDPROC(__modsi3)
 
@@ -313,6 +321,7 @@ ENDPROC(__modsi3)
 ENTRY(__aeabi_uidivmod)
 UNWIND(.fnstart)
 UNWIND(.save {r0, r1, ip, lr}	)
+.pushsection .text.__aeabi_uidivmod, "ax"
 
 	stmfd	sp!, {r0, r1, ip, lr}
 	bl	__aeabi_uidiv
@@ -321,12 +330,15 @@ UNWIND(.save {r0, r1, ip, lr}	)
 	sub	r1, r1, r3
 	ret	lr
 
+.popsection
 UNWIND(.fnend)
 ENDPROC(__aeabi_uidivmod)
 
 ENTRY(__aeabi_idivmod)
 UNWIND(.fnstart)
 UNWIND(.save {r0, r1, ip, lr}	)
+.pushsection .text.__aeabi_uidivmod, "ax"
+
 	stmfd	sp!, {r0, r1, ip, lr}
 	bl	__aeabi_idiv
 	ldmfd	sp!, {r1, r2, ip, lr}
@@ -334,6 +346,7 @@ UNWIND(.save {r0, r1, ip, lr}	)
 	sub	r1, r1, r3
 	ret	lr
 
+.popsection
 UNWIND(.fnend)
 ENDPROC(__aeabi_idivmod)
 
@@ -343,16 +356,21 @@ Ldiv0:
 UNWIND(.fnstart)
 UNWIND(.pad #4)
 UNWIND(.save {lr})
+.pushsection .text.Ldiv0, "ax"
+
 	str	lr, [sp, #-8]!
 	bl	__div0
 	mov	r0, #0			@ About as wrong as it could be.
 	ldr	pc, [sp], #8
+
+.popsection
 UNWIND(.fnend)
 ENDPROC(Ldiv0)
 
 /* Thumb-1 specialities */
 #if defined(CONFIG_SYS_THUMB_BUILD) && !defined(CONFIG_HAS_THUMB2)
 ENTRY(__gnu_thumb1_case_sqi)
+.pushsection .text.__gnu_thumb1_case_sqi, "ax"
 	push	{r1}
 	mov	r1, lr
 	lsrs	r1, r1, #1
@@ -362,9 +380,11 @@ ENTRY(__gnu_thumb1_case_sqi)
 	add	lr, lr, r1
 	pop	{r1}
 	bx	lr
+.popsection
 ENDPROC(__gnu_thumb1_case_sqi)
 
 ENTRY(__gnu_thumb1_case_uqi)
+.pushsection .text.__gnu_thumb1_case_uqi, "ax"
 	push	{r1}
 	mov	r1, lr
 	lsrs	r1, r1, #1
@@ -374,9 +394,11 @@ ENTRY(__gnu_thumb1_case_uqi)
 	add	lr, lr, r1
 	pop	{r1}
 	bx	lr
+.popsection
 ENDPROC(__gnu_thumb1_case_uqi)
 
 ENTRY(__gnu_thumb1_case_shi)
+.pushsection .text.__gnu_thumb1_case_shi, "ax"
 	push	{r0, r1}
 	mov	r1, lr
 	lsrs	r1, r1, #1
@@ -387,9 +409,11 @@ ENTRY(__gnu_thumb1_case_shi)
 	add	lr, lr, r1
 	pop	{r0, r1}
 	bx	lr
+.popsection
 ENDPROC(__gnu_thumb1_case_shi)
 
 ENTRY(__gnu_thumb1_case_uhi)
+.pushsection .text.__gnu_thumb1_case_uhi, "ax"
 	push	{r0, r1}
 	mov	r1, lr
 	lsrs	r1, r1, #1
@@ -400,5 +424,6 @@ ENTRY(__gnu_thumb1_case_uhi)
 	add	lr, lr, r1
 	pop	{r0, r1}
 	bx	lr
+.popsection
 ENDPROC(__gnu_thumb1_case_uhi)
 #endif
diff --git a/arch/arm/lib/lshrdi3.S b/arch/arm/lib/lshrdi3.S
index 9c51141..f710ccb 100644
--- a/arch/arm/lib/lshrdi3.S
+++ b/arch/arm/lib/lshrdi3.S
@@ -17,6 +17,7 @@
 
 ENTRY(__lshrdi3)
 ENTRY(__aeabi_llsr)
+.pushsection .text.__lshldi3, "ax"
 
 	subs	r3, r2, #32
 	rsb	ip, r2, #32
@@ -28,5 +29,6 @@ ENTRY(__aeabi_llsr)
 	mov	ah, ah, lsr r2
 	ret	lr
 
+.popsection
 ENDPROC(__lshrdi3)
 ENDPROC(__aeabi_llsr)
diff --git a/arch/arm/lib/muldi3.S b/arch/arm/lib/muldi3.S
index daa5704..bc255c5 100644
--- a/arch/arm/lib/muldi3.S
+++ b/arch/arm/lib/muldi3.S
@@ -25,6 +25,7 @@
 
 ENTRY(__muldi3)
 ENTRY(__aeabi_lmul)
+.pushsection .text.__muldi3, "ax"
 
 	mul	xh, yl, xh
 	mla	xh, xl, yh, xh
@@ -42,5 +43,6 @@ ENTRY(__aeabi_lmul)
 	adc	xh, xh, ip, lsr #16
 	ret	lr
 
+.popsection
 ENDPROC(__muldi3)
 ENDPROC(__aeabi_lmul)
diff --git a/arch/arm/lib/uldivmod.S b/arch/arm/lib/uldivmod.S
index 2efcd73..bbc44c6 100644
--- a/arch/arm/lib/uldivmod.S
+++ b/arch/arm/lib/uldivmod.S
@@ -34,6 +34,8 @@ TMP	.req	r8
 )
 
 ENTRY(__aeabi_uldivmod)
+.pushsection .text.__aeabi_uldivmod, "ax"
+
 	stmfd	sp!, {r4, r5, r6, r7, THUMB(TMP,) lr}
 	@ Test if B == 0
 	orrs	ip, B_0, B_1		@ Z set -> B == 0
@@ -240,4 +242,5 @@ L_div_by_0:
 	mov	R_0, #0
 	mov	R_1, #0
 	ldmfd	sp!, {r4, r5, r6, r7, THUMB(TMP,) pc}
+.popsection
 ENDPROC(__aeabi_uldivmod)
-- 
2.7.0

[U-Boot] [PATCH 11/12] arm: lib: Split asm symbols into different .text subsections

[Tom Rini]

On Thu, May 26, 2016 at 06:01:46PM +0200, Marek Vasut wrote:

> Split each symbol in lib1funcs into different .text.foo section instead
> of placing all of them into plain .text . This allows the linker to collect
> and discard unused assembler symbols.
> 
> Signed-off-by: Marek Vasut <marex@denx.de>
> Cc: Albert Aribaud <albert.u.boot@aribaud.net>
> Cc: Masahiro Yamada <yamada.masahiro@socionext.com>
> Cc: Simon Glass <sjg@chromium.org>
> Cc: Tom Rini <trini@konsulko.com>

Reviewed-by: Tom Rini <trini@konsulko.com>

-- 
Tom
-------------- next part --------------
A non-text attachment was scrubbed...
Name: signature.asc
Type: application/pgp-signature
Size: 819 bytes
Desc: Digital signature
URL: <http://lists.denx.de/pipermail/u-boot/attachments/20160602/13ef4dc6/attachment.sig>

[U-Boot] [U-Boot, 11/12] arm: lib: Split asm symbols into different .text subsections

[Tom Rini]

On Thu, May 26, 2016 at 06:01:46PM +0200, Marek Vasut wrote:

> Split each symbol in lib1funcs into different .text.foo section instead
> of placing all of them into plain .text . This allows the linker to collect
> and discard unused assembler symbols.
> 
> Signed-off-by: Marek Vasut <marex@denx.de>
> Cc: Albert Aribaud <albert.u.boot@aribaud.net>
> Cc: Masahiro Yamada <yamada.masahiro@socionext.com>
> Cc: Simon Glass <sjg@chromium.org>
> Cc: Tom Rini <trini@konsulko.com>
> Reviewed-by: Tom Rini <trini@konsulko.com>

Applied to u-boot/master, thanks!

-- 
Tom
-------------- next part --------------
A non-text attachment was scrubbed...
Name: signature.asc
Type: application/pgp-signature
Size: 819 bytes
Desc: Digital signature
URL: <http://lists.denx.de/pipermail/u-boot/attachments/20160603/2e2ed6ea/attachment.sig>

[U-Boot] [PATCH 11/12] arm: lib: Split asm symbols into different .text subsections

[Stephen Warren]

On 05/26/2016 10:01 AM, Marek Vasut wrote:
> Split each symbol in lib1funcs into different .text.foo section instead
> of placing all of them into plain .text . This allows the linker to collect
> and discard unused assembler symbols.

This patch causes Tegra-boards-that-use-SPL (i.e. all ARMv7 boards but 
not ARMv8) to fail to boot with zero output. Taking u-boot.git master 
branch and reverting this one patch is enough to make U-Boot work again.

I haven't investigated how to solve this yet. Likely relevant background:

32-bit Tegra SPL runs on an ARM1176 CPU whereas main U-Boot runs on an 
ARMv7 CPU. We need to use PRIVATE_LIBGCC (at least for SPL) since the 
libgcc in the toolchains we use is compiled for ARMv7, and hence picking 
it up in SPL breaks boot. I wonder if these section name changes are 
causing the linker to pull in the toolchain's libgcc rather than using 
U-Boot's copy compiled for ARM1176?

[U-Boot] [PATCH 12/12] lib: Enable private libgcc by default

[Marek Vasut]

This patch decouples U-Boot binary from the toolchain on systems where
private libgcc is available. Instead of pulling in functions provided
by the libgcc from the toolchain, U-Boot will use it's own set of libgcc
functions. These functions are usually imported from Linux kernel, which
also uses it's own libgcc functions instead of the ones provided by the
toolchain.

This patch solves a rather common problem. The toolchain can usually
generate code for many variants of target architecture and often even
different endianness. The libgcc on the other hand is usually compiled
for one particular configuration and the functions provided by it may
or may not be suited for use in U-Boot. This can manifest in two ways,
either the U-Boot fails to compile altogether and linker will complain
or, in the much worse case, the resulting U-Boot will build, but will
misbehave in very subtle and hard to debug ways.

Signed-off-by: Marek Vasut <marex@denx.de>
Cc: Albert Aribaud <albert.u.boot@aribaud.net>
Cc: Masahiro Yamada <yamada.masahiro@socionext.com>
Cc: Simon Glass <sjg@chromium.org>
Cc: Tom Rini <trini@konsulko.com>
---
V2: Enable the private libgcc only for ARM<=7 and MIPS
---
 lib/Kconfig | 1 +
 1 file changed, 1 insertion(+)

diff --git a/lib/Kconfig b/lib/Kconfig
index 2b97c2b..02ca405 100644
--- a/lib/Kconfig
+++ b/lib/Kconfig
@@ -14,6 +14,7 @@ config HAVE_PRIVATE_LIBGCC
 config USE_PRIVATE_LIBGCC
 	bool "Use private libgcc"
 	depends on HAVE_PRIVATE_LIBGCC
+	default y if HAVE_PRIVATE_LIBGCC && ((ARM && !ARM64) || MIPS)
 	help
 	  This option allows you to use the built-in libgcc implementation
 	  of U-Boot instead of the one provided by the compiler.
-- 
2.7.0

[U-Boot] [PATCH 12/12] lib: Enable private libgcc by default

[Tom Rini]

On Thu, May 26, 2016 at 06:01:47PM +0200, Marek Vasut wrote:

> This patch decouples U-Boot binary from the toolchain on systems where
> private libgcc is available. Instead of pulling in functions provided
> by the libgcc from the toolchain, U-Boot will use it's own set of libgcc
> functions. These functions are usually imported from Linux kernel, which
> also uses it's own libgcc functions instead of the ones provided by the
> toolchain.
> 
> This patch solves a rather common problem. The toolchain can usually
> generate code for many variants of target architecture and often even
> different endianness. The libgcc on the other hand is usually compiled
> for one particular configuration and the functions provided by it may
> or may not be suited for use in U-Boot. This can manifest in two ways,
> either the U-Boot fails to compile altogether and linker will complain
> or, in the much worse case, the resulting U-Boot will build, but will
> misbehave in very subtle and hard to debug ways.
> 
> Signed-off-by: Marek Vasut <marex@denx.de>
> Cc: Albert Aribaud <albert.u.boot@aribaud.net>
> Cc: Masahiro Yamada <yamada.masahiro@socionext.com>
> Cc: Simon Glass <sjg@chromium.org>
> Cc: Tom Rini <trini@konsulko.com>

Reviewed-by: Tom Rini <trini@konsulko.com>

-- 
Tom
-------------- next part --------------
A non-text attachment was scrubbed...
Name: signature.asc
Type: application/pgp-signature
Size: 819 bytes
Desc: Digital signature
URL: <http://lists.denx.de/pipermail/u-boot/attachments/20160602/50abc5f5/attachment.sig>

[U-Boot] [U-Boot,12/12] lib: Enable private libgcc by default

[Tom Rini]

On Thu, May 26, 2016 at 06:01:47PM +0200, Marek Vasut wrote:

> This patch decouples U-Boot binary from the toolchain on systems where
> private libgcc is available. Instead of pulling in functions provided
> by the libgcc from the toolchain, U-Boot will use it's own set of libgcc
> functions. These functions are usually imported from Linux kernel, which
> also uses it's own libgcc functions instead of the ones provided by the
> toolchain.
> 
> This patch solves a rather common problem. The toolchain can usually
> generate code for many variants of target architecture and often even
> different endianness. The libgcc on the other hand is usually compiled
> for one particular configuration and the functions provided by it may
> or may not be suited for use in U-Boot. This can manifest in two ways,
> either the U-Boot fails to compile altogether and linker will complain
> or, in the much worse case, the resulting U-Boot will build, but will
> misbehave in very subtle and hard to debug ways.
> 
> Signed-off-by: Marek Vasut <marex@denx.de>
> Cc: Albert Aribaud <albert.u.boot@aribaud.net>
> Cc: Masahiro Yamada <yamada.masahiro@socionext.com>
> Cc: Simon Glass <sjg@chromium.org>
> Cc: Tom Rini <trini@konsulko.com>
> Reviewed-by: Tom Rini <trini@konsulko.com>

Applied to u-boot/master, thanks!

And since this change was contentious when previously proposed, I'm
going to explain why I'm taking this now.  There are a number of
correctly configured toolchains out there today that fail to build
U-Boot on some platforms.  This is because we're giving the compiler
conflicting requests (build soft-float! use whatever libgcc you have!).
The era of multilib toolchains being prevalent (at least for 32bit ARM)
is long over.  The right thing to have done, always, would be to provide
the required functions ourselves so that we are in control.  So, thanks
again Marek for following up on the series as I had asked you to, this
fixes build failures for me on about a dozen platforms.

-- 
Tom
-------------- next part --------------
A non-text attachment was scrubbed...
Name: signature.asc
Type: application/pgp-signature
Size: 819 bytes
Desc: Digital signature
URL: <http://lists.denx.de/pipermail/u-boot/attachments/20160603/fd3ac1fa/attachment.sig>

[U-Boot] [U-Boot,12/12] lib: Enable private libgcc by default

[Simon Glass]

On 4 June 2016 at 02:00, Tom Rini <trini@konsulko.com> wrote:
> On Thu, May 26, 2016 at 06:01:47PM +0200, Marek Vasut wrote:
>
>> This patch decouples U-Boot binary from the toolchain on systems where
>> private libgcc is available. Instead of pulling in functions provided
>> by the libgcc from the toolchain, U-Boot will use it's own set of libgcc
>> functions. These functions are usually imported from Linux kernel, which
>> also uses it's own libgcc functions instead of the ones provided by the
>> toolchain.
>>
>> This patch solves a rather common problem. The toolchain can usually
>> generate code for many variants of target architecture and often even
>> different endianness. The libgcc on the other hand is usually compiled
>> for one particular configuration and the functions provided by it may
>> or may not be suited for use in U-Boot. This can manifest in two ways,
>> either the U-Boot fails to compile altogether and linker will complain
>> or, in the much worse case, the resulting U-Boot will build, but will
>> misbehave in very subtle and hard to debug ways.
>>
>> Signed-off-by: Marek Vasut <marex@denx.de>
>> Cc: Albert Aribaud <albert.u.boot@aribaud.net>
>> Cc: Masahiro Yamada <yamada.masahiro@socionext.com>
>> Cc: Simon Glass <sjg@chromium.org>
>> Cc: Tom Rini <trini@konsulko.com>
>> Reviewed-by: Tom Rini <trini@konsulko.com>
>
> Applied to u-boot/master, thanks!
>
> And since this change was contentious when previously proposed, I'm
> going to explain why I'm taking this now.  There are a number of
> correctly configured toolchains out there today that fail to build
> U-Boot on some platforms.  This is because we're giving the compiler
> conflicting requests (build soft-float! use whatever libgcc you have!).
> The era of multilib toolchains being prevalent (at least for 32bit ARM)
> is long over.  The right thing to have done, always, would be to provide
> the required functions ourselves so that we are in control.  So, thanks
> again Marek for following up on the series as I had asked you to, this
> fixes build failures for me on about a dozen platforms.

Thank you Marek!

- Simon

[U-Boot] [U-Boot,12/12] lib: Enable private libgcc by default

[Michael Zimmermann]

> The toolchain can usually
> generate code for many variants of target architecture and often even
> different endianness. The libgcc on the other hand is usually compiled
> for one particular configuration and the functions provided by it may
> or may not be suited for use in U-Boot.

I agree with this change but is this even true? my toolchain(linaro) has 28
different versions of libgcc.a

Thanks
Michael

On Mon, Jun 6, 2016 at 7:35 PM, Simon Glass <sjg@chromium.org> wrote:

> On 4 June 2016 at 02:00, Tom Rini <trini@konsulko.com> wrote:
> > On Thu, May 26, 2016 at 06:01:47PM +0200, Marek Vasut wrote:
> >
> >> This patch decouples U-Boot binary from the toolchain on systems where
> >> private libgcc is available. Instead of pulling in functions provided
> >> by the libgcc from the toolchain, U-Boot will use it's own set of libgcc
> >> functions. These functions are usually imported from Linux kernel, which
> >> also uses it's own libgcc functions instead of the ones provided by the
> >> toolchain.
> >>
> >> This patch solves a rather common problem. The toolchain can usually
> >> generate code for many variants of target architecture and often even
> >> different endianness. The libgcc on the other hand is usually compiled
> >> for one particular configuration and the functions provided by it may
> >> or may not be suited for use in U-Boot. This can manifest in two ways,
> >> either the U-Boot fails to compile altogether and linker will complain
> >> or, in the much worse case, the resulting U-Boot will build, but will
> >> misbehave in very subtle and hard to debug ways.
> >>
> >> Signed-off-by: Marek Vasut <marex@denx.de>
> >> Cc: Albert Aribaud <albert.u.boot@aribaud.net>
> >> Cc: Masahiro Yamada <yamada.masahiro@socionext.com>
> >> Cc: Simon Glass <sjg@chromium.org>
> >> Cc: Tom Rini <trini@konsulko.com>
> >> Reviewed-by: Tom Rini <trini@konsulko.com>
> >
> > Applied to u-boot/master, thanks!
> >
> > And since this change was contentious when previously proposed, I'm
> > going to explain why I'm taking this now.  There are a number of
> > correctly configured toolchains out there today that fail to build
> > U-Boot on some platforms.  This is because we're giving the compiler
> > conflicting requests (build soft-float! use whatever libgcc you have!).
> > The era of multilib toolchains being prevalent (at least for 32bit ARM)
> > is long over.  The right thing to have done, always, would be to provide
> > the required functions ourselves so that we are in control.  So, thanks
> > again Marek for following up on the series as I had asked you to, this
> > fixes build failures for me on about a dozen platforms.
>
> Thank you Marek!
>
> - Simon
> _______________________________________________
> U-Boot mailing list
> U-Boot at lists.denx.de
> http://lists.denx.de/mailman/listinfo/u-boot
>

[U-Boot] [PATCH 01/12] arm: config: Introduce CONFIG_SYS_ARM_ARCH

[Tom Rini]

On Thu, May 26, 2016 at 06:01:36PM +0200, Marek Vasut wrote:

> Introduce new helper Kconfig option, which is automatically set to
> the version of ARM architecture for which the U-Boot is built. This
> is useful when selecting tuning options in the libgcc imported from
> Linux kernel.
> 
> Signed-off-by: Marek Vasut <marex@denx.de>
> Cc: Albert Aribaud <albert.u.boot@aribaud.net>
> Cc: Masahiro Yamada <yamada.masahiro@socionext.com>
> Cc: Simon Glass <sjg@chromium.org>
> Cc: Tom Rini <trini@konsulko.com>

Reviewed-by: Tom Rini <trini@konsulko.com>

-- 
Tom
-------------- next part --------------
A non-text attachment was scrubbed...
Name: signature.asc
Type: application/pgp-signature
Size: 819 bytes
Desc: Digital signature
URL: <http://lists.denx.de/pipermail/u-boot/attachments/20160602/8c98e9ee/attachment.sig>

[U-Boot] [U-Boot, 01/12] arm: config: Introduce CONFIG_SYS_ARM_ARCH

[Tom Rini]

On Thu, May 26, 2016 at 06:01:36PM +0200, Marek Vasut wrote:

> Introduce new helper Kconfig option, which is automatically set to
> the version of ARM architecture for which the U-Boot is built. This
> is useful when selecting tuning options in the libgcc imported from
> Linux kernel.
> 
> Signed-off-by: Marek Vasut <marex@denx.de>
> Cc: Albert Aribaud <albert.u.boot@aribaud.net>
> Cc: Masahiro Yamada <yamada.masahiro@socionext.com>
> Cc: Simon Glass <sjg@chromium.org>
> Cc: Tom Rini <trini@konsulko.com>
> Reviewed-by: Tom Rini <trini@konsulko.com>

Applied to u-boot/master, thanks!

-- 
Tom
-------------- next part --------------
A non-text attachment was scrubbed...
Name: signature.asc
Type: application/pgp-signature
Size: 819 bytes
Desc: Digital signature
URL: <http://lists.denx.de/pipermail/u-boot/attachments/20160603/72313ed5/attachment.sig>