redonkable
/
alistair23-linux
1
0
Fork 0
Code Releases Activity

Merge branches 'fixes' and 'misc' into for-next 

Conflicts:
	arch/arm/kernel/iwmmxt.S
	arch/arm/mm/cache-l2x0.c
	arch/arm/mm/mmu.c
hifive-unleashed-5.1
Russell King 2014-08-05 10:27:13 +01:00
parent 6bf755db4d 3bb70de692
commit 7109561524
483 changed files with 6149 additions and 3473 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
CREDITS
View File

@ -9,6 +9,10 @@
Linus
----------
M: Matt Mackal
E: mpm@selenic.com
D: SLOB slab allocator
N: Matti Aarnio
E: mea@nic.funet.fi
D: Alpha systems hacking, IPv6 and other network related stuff

1
Documentation/accounting/getdelays.c
View File

@ -314,6 +314,7 @@ int main(int argc, char *argv[])
break;
case 'm':
strncpy(cpumask, optarg, sizeof(cpumask));
cpumask[sizeof(cpumask) - 1] = '\0';
maskset = 1;
printf("cpumask %s maskset %d\n", cpumask, maskset);
break;

14
Documentation/devicetree/bindings/arm/armada-38x.txt
View File

@ -6,5 +6,15 @@ following property:
Required root node property:
- compatible: must contain either "marvell,armada380" or
"marvell,armada385" depending on the variant of the SoC being used.
- compatible: must contain "marvell,armada380"
In addition, boards using the Marvell Armada 385 SoC shall have the
following property before the previous one:
Required root node property:
compatible: must contain "marvell,armada385"
Example:
compatible = "marvell,a385-rd", "marvell,armada385", "marvell,armada380";

2
Documentation/devicetree/bindings/arm/samsung/exynos-adc.txt
View File

@ -48,7 +48,7 @@ adc@12D10000 {
/* NTC thermistor is a hwmon device */
ncp15wb473@0 {
compatible = "ntc,ncp15wb473";
compatible = "murata,ncp15wb473";
pullup-uv = <1800000>;
pullup-ohm = <47000>;
pulldown-ohm = <0>;

20
Documentation/devicetree/bindings/hwmon/ntc_thermistor.txt
View File

@ -3,11 +3,19 @@ NTC Thermistor hwmon sensors
Requires node properties:
- "compatible" value : one of
"ntc,ncp15wb473"
"ntc,ncp18wb473"
"ntc,ncp21wb473"
"ntc,ncp03wb473"
"ntc,ncp15wl333"
"murata,ncp15wb473"
"murata,ncp18wb473"
"murata,ncp21wb473"
"murata,ncp03wb473"
"murata,ncp15wl333"
/* Usage of vendor name "ntc" is deprecated */
<DEPRECATED> "ntc,ncp15wb473"
<DEPRECATED> "ntc,ncp18wb473"
<DEPRECATED> "ntc,ncp21wb473"
<DEPRECATED> "ntc,ncp03wb473"
<DEPRECATED> "ntc,ncp15wl333"
- "pullup-uv" Pull up voltage in micro volts
- "pullup-ohm" Pull up resistor value in ohms
- "pulldown-ohm" Pull down resistor value in ohms
@ -21,7 +29,7 @@ Read more about iio bindings at
Example:
ncp15wb473@0 {
compatible = "ntc,ncp15wb473";
compatible = "murata,ncp15wb473";
pullup-uv = <1800000>;
pullup-ohm = <47000>;
pulldown-ohm = <0>;

6
Documentation/devicetree/bindings/spi/qcom,spi-qup.txt
View File

@ -23,6 +23,12 @@ Optional properties:
- spi-max-frequency: Specifies maximum SPI clock frequency,
Units - Hz. Definition as per
Documentation/devicetree/bindings/spi/spi-bus.txt
- num-cs: total number of chipselects
- cs-gpios: should specify GPIOs used for chipselects.
The gpios will be referred to as reg = <index> in the SPI child
nodes. If unspecified, a single SPI device without a chip
select can be used.
SPI slave nodes must be children of the SPI master node and can contain
properties described in Documentation/devicetree/bindings/spi/spi-bus.txt

1
Documentation/devicetree/bindings/vendor-prefixes.txt
View File

@ -83,6 +83,7 @@ mosaixtech Mosaix Technologies, Inc.
moxa Moxa
mpl MPL AG
mundoreader Mundo Reader S.L.
murata Murata Manufacturing Co., Ltd.
mxicy Macronix International Co., Ltd.
national National Semiconductor
neonode Neonode Inc.

11
Documentation/email-clients.txt
View File

@ -1,6 +1,17 @@
Email clients info for Linux
======================================================================
Git
----------------------------------------------------------------------
These days most developers use `git send-email` instead of regular
email clients. The man page for this is quite good. On the receiving
end, maintainers use `git am` to apply the patches.
If you are new to git then send your first patch to yourself. Save it
as raw text including all the headers. Run `git am raw_email.txt` and
then review the changelog with `git log`. When that works then send
the patch to the appropriate mailing list(s).
General Preferences
----------------------------------------------------------------------
Patches for the Linux kernel are submitted via email, preferably as

8
Documentation/hwmon/ntc_thermistor
View File

@ -1,7 +1,7 @@
Kernel driver ntc_thermistor
=================
Supported thermistors:
Supported thermistors from Murata:
* Murata NTC Thermistors NCP15WB473, NCP18WB473, NCP21WB473, NCP03WB473, NCP15WL333
Prefixes: 'ncp15wb473', 'ncp18wb473', 'ncp21wb473', 'ncp03wb473', 'ncp15wl333'
Datasheet: Publicly available at Murata
@ -15,9 +15,9 @@ Authors:
Description
-----------
The NTC thermistor is a simple thermistor that requires users to provide the
resistance and lookup the corresponding compensation table to get the
temperature input.
The NTC (Negative Temperature Coefficient) thermistor is a simple thermistor
that requires users to provide the resistance and lookup the corresponding
compensation table to get the temperature input.
The NTC driver provides lookup tables with a linear approximation function
and four circuit models with an option not to use any of the four models.

5
Documentation/kernel-parameters.txt
View File

@ -3130,6 +3130,11 @@ bytes respectively. Such letter suffixes can also be entirely omitted.
[KNL] Should the soft-lockup detector generate panics.
Format: <integer>
softlockup_all_cpu_backtrace=
[KNL] Should the soft-lockup detector generate
backtraces on all cpus.
Format: <integer>
sonypi.*= [HW] Sony Programmable I/O Control Device driver
See Documentation/laptops/sonypi.txt

15
Documentation/memory-hotplug.txt
View File

@ -209,15 +209,12 @@ If memory device is found, memory hotplug code will be called.
4.2 Notify memory hot-add event by hand
------------
On powerpc, the firmware does not notify a memory hotplug event to the kernel.
Therefore, "probe" interface is supported to notify the event to the kernel.
This interface depends on CONFIG_ARCH_MEMORY_PROBE.
CONFIG_ARCH_MEMORY_PROBE is supported on powerpc only. On x86, this config
option is disabled by default since ACPI notifies a memory hotplug event to
the kernel, which performs its hotplug operation as the result. Please
enable this option if you need the "probe" interface for testing purposes
on x86.
On some architectures, the firmware may not notify the kernel of a memory
hotplug event. Therefore, the memory "probe" interface is supported to
explicitly notify the kernel. This interface depends on
CONFIG_ARCH_MEMORY_PROBE and can be configured on powerpc, sh, and x86
if hotplug is supported, although for x86 this should be handled by ACPI
notification.
Probe interface is located at
/sys/devices/system/memory/probe

5
Documentation/ptp/testptp.c
View File

@ -17,6 +17,7 @@
* along with this program; if not, write to the Free Software
* Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
*/
#define _GNU_SOURCE
#include <errno.h>
#include <fcntl.h>
#include <inttypes.h>
@ -46,12 +47,14 @@
#define CLOCK_INVALID -1
#endif
/* When glibc offers the syscall, this will go away. */
/* clock_adjtime is not available in GLIBC < 2.14 */
#if !__GLIBC_PREREQ(2, 14)
#include <sys/syscall.h>
static int clock_adjtime(clockid_t id, struct timex *tx)
{
return syscall(__NR_clock_adjtime, id, tx);
}
#endif
static clockid_t get_clockid(int fd)
{

5
Documentation/sound/alsa/HD-Audio-Models.txt
View File

@ -286,6 +286,11 @@ STAC92HD83*
hp-inv-led HP with broken BIOS for inverted mute LED
auto BIOS setup (default)
STAC92HD95
==========
hp-led LED support for HP laptops
hp-bass Bass HPF setup for HP Spectre 13
STAC9872
========
vaio VAIO laptop without SPDIF

17
Documentation/sysctl/kernel.txt
View File

@ -75,6 +75,7 @@ show up in /proc/sys/kernel:
- shmall
- shmmax [ sysv ipc ]
- shmmni
- softlockup_all_cpu_backtrace
- stop-a [ SPARC only ]
- sysrq ==> Documentation/sysrq.txt
- sysctl_writes_strict
@ -783,6 +784,22 @@ via the /proc/sys interface:
==============================================================
softlockup_all_cpu_backtrace:
This value controls the soft lockup detector thread's behavior
when a soft lockup condition is detected as to whether or not
to gather further debug information. If enabled, each cpu will
be issued an NMI and instructed to capture stack trace.
This feature is only applicable for architectures which support
NMI.
0: do nothing. This is the default behavior.
1: on detection capture more debug information.
==============================================================
tainted:
Non-zero if the kernel has been tainted. Numeric values, which

3
Documentation/sysctl/vm.txt
View File

@ -702,7 +702,8 @@ The batch value of each per cpu pagelist is also updated as a result. It is
set to pcp->high/4. The upper limit of batch is (PAGE_SHIFT * 8)
The initial value is zero. Kernel does not use this value at boot time to set
the high water marks for each per cpu page list.
the high water marks for each per cpu page list. If the user writes '0' to this
sysctl, it will revert to this default behavior.
==============================================================

22
MAINTAINERS
View File

@ -2917,6 +2917,9 @@ L: linux-doc@vger.kernel.org
T: quilt http://www.infradead.org/~rdunlap/Doc/patches/
S: Maintained
F: Documentation/
X: Documentation/ABI/
X: Documentation/devicetree/
X: Documentation/[a-z][a-z]_[A-Z][A-Z]/
DOUBLETALK DRIVER
M: "James R. Van Zandt" <jrv@vanzandt.mv.com>
@ -3189,14 +3192,6 @@ L: linux-scsi@vger.kernel.org
S: Maintained
F: drivers/scsi/eata_pio.*
EBTABLES
L: netfilter-devel@vger.kernel.org
W: http://ebtables.sourceforge.net/
S: Orphan
F: include/linux/netfilter_bridge/ebt_*.h
F: include/uapi/linux/netfilter_bridge/ebt_*.h
F: net/bridge/netfilter/ebt*.c
EC100 MEDIA DRIVER
M: Antti Palosaari <crope@iki.fi>
L: linux-media@vger.kernel.org
@ -6105,12 +6100,11 @@ F: Documentation/networking/s2io.txt
F: Documentation/networking/vxge.txt
F: drivers/net/ethernet/neterion/
NETFILTER/IPTABLES
NETFILTER ({IP,IP6,ARP,EB,NF}TABLES)
M: Pablo Neira Ayuso <pablo@netfilter.org>
M: Patrick McHardy <kaber@trash.net>
M: Jozsef Kadlecsik <kadlec@blackhole.kfki.hu>
L: netfilter-devel@vger.kernel.org
L: netfilter@vger.kernel.org
L: coreteam@netfilter.org
W: http://www.netfilter.org/
W: http://www.iptables.org/
@ -8196,13 +8190,15 @@ S: Maintained
F: drivers/usb/misc/sisusbvga/
SLAB ALLOCATOR
M: Christoph Lameter <cl@linux-foundation.org>
M: Christoph Lameter <cl@linux.com>
M: Pekka Enberg <penberg@kernel.org>
M: Matt Mackall <mpm@selenic.com>
M: David Rientjes <rientjes@google.com>
M: Joonsoo Kim <iamjoonsoo.kim@lge.com>
M: Andrew Morton <akpm@linux-foundation.org>
L: linux-mm@kvack.org
S: Maintained
F: include/linux/sl?b*.h
F: mm/sl?b.c
F: mm/sl?b*
SLEEPABLE READ-COPY UPDATE (SRCU)
M: Lai Jiangshan <laijs@cn.fujitsu.com>

2
Makefile
View File

@ -1,7 +1,7 @@
VERSION = 3
PATCHLEVEL = 16
SUBLEVEL = 0
EXTRAVERSION = -rc2
EXTRAVERSION = -rc3
NAME = Shuffling Zombie Juror
# *DOCUMENTATION*

4
arch/arc/include/asm/cache.h
View File

@ -60,7 +60,7 @@ extern void read_decode_cache_bcr(void);
#define ARC_REG_IC_IVIC 0x10
#define ARC_REG_IC_CTRL 0x11
#define ARC_REG_IC_IVIL 0x19
#if defined(CONFIG_ARC_MMU_V3) || defined (CONFIG_ARC_MMU_V4)
#if defined(CONFIG_ARC_MMU_V3)
#define ARC_REG_IC_PTAG 0x1E
#endif
@ -74,7 +74,7 @@ extern void read_decode_cache_bcr(void);
#define ARC_REG_DC_IVDL 0x4A
#define ARC_REG_DC_FLSH 0x4B
#define ARC_REG_DC_FLDL 0x4C
#if defined(CONFIG_ARC_MMU_V3) || defined (CONFIG_ARC_MMU_V4)
#if defined(CONFIG_ARC_MMU_V3)
#define ARC_REG_DC_PTAG 0x5C
#endif

1
arch/arc/include/uapi/asm/ptrace.h
View File

@ -11,6 +11,7 @@
#ifndef _UAPI__ASM_ARC_PTRACE_H
#define _UAPI__ASM_ARC_PTRACE_H
#define PTRACE_GET_THREAD_AREA 25
#ifndef __ASSEMBLY__
/*

2
arch/arc/kernel/ctx_sw_asm.S
View File

@ -10,9 +10,9 @@
* -This is the more "natural" hand written assembler
*/
#include <linux/linkage.h>
#include <asm/entry.h> /* For the SAVE_* macros */
#include <asm/asm-offsets.h>
#include <asm/linkage.h>
#define KSP_WORD_OFF ((TASK_THREAD + THREAD_KSP) / 4)

2
arch/arc/kernel/devtree.c
View File

@ -41,7 +41,7 @@ const struct machine_desc * __init setup_machine_fdt(void *dt)
{
const struct machine_desc *mdesc;
unsigned long dt_root;
void *clk;
const void *clk;
int len;
if (!early_init_dt_scan(dt))

7
arch/arc/kernel/head.S
View File

@ -77,10 +77,11 @@ stext:
; Clear BSS before updating any globals
; XXX: use ZOL here
mov r5, __bss_start
mov r6, __bss_stop
sub r6, __bss_stop, r5
lsr.f lp_count, r6, 2
lpnz 1f
st.ab 0, [r5, 4]
1:
st.ab 0, [r5,4]
brlt r5, r6, 1b
; Uboot - kernel ABI
; r0 = [0] No uboot interaction, [1] cmdline in r2, [2] DTB in r2

4
arch/arc/kernel/ptrace.c
View File

@ -146,6 +146,10 @@ long arch_ptrace(struct task_struct *child, long request,
pr_debug("REQ=%ld: ADDR =0x%lx, DATA=0x%lx)\n", request, addr, data);
switch (request) {
case PTRACE_GET_THREAD_AREA:
ret = put_user(task_thread_info(child)->thr_ptr,
(unsigned long __user *)data);
break;
default:
ret = ptrace_request(child, request, addr, data);
break;

15
arch/arc/kernel/smp.c
View File

@ -337,8 +337,19 @@ irqreturn_t do_IPI(int irq, void *dev_id)
* API called by platform code to hookup arch-common ISR to their IPI IRQ
*/
static DEFINE_PER_CPU(int, ipi_dev);
static struct irqaction arc_ipi_irq = {
.name = "IPI Interrupt",
.flags = IRQF_PERCPU,
.handler = do_IPI,
};
int smp_ipi_irq_setup(int cpu, int irq)
{
int *dev_id = &per_cpu(ipi_dev, smp_processor_id());
return request_percpu_irq(irq, do_IPI, "IPI Interrupt", dev_id);
if (!cpu)
return setup_irq(irq, &arc_ipi_irq);
else
arch_unmask_irq(irq);
return 0;
}

2
arch/arc/kernel/vmlinux.lds.S
View File

@ -116,7 +116,7 @@ SECTIONS
_edata = .;
BSS_SECTION(0, 0, 0)
BSS_SECTION(4, 4, 4)
#ifdef CONFIG_ARC_DW2_UNWIND
. = ALIGN(PAGE_SIZE);

25
arch/arc/mm/cache_arc700.c
View File

@ -389,7 +389,7 @@ static inline void __dc_line_op(unsigned long paddr, unsigned long vaddr,
/***********************************************************
* Machine specific helper for per line I-Cache invalidate.
*/
static void __ic_line_inv_vaddr(unsigned long paddr, unsigned long vaddr,
static void __ic_line_inv_vaddr_local(unsigned long paddr, unsigned long vaddr,
unsigned long sz)
{
unsigned long flags;
@ -405,6 +405,23 @@ static inline void __ic_entire_inv(void)
read_aux_reg(ARC_REG_IC_CTRL); /* blocks */
}
struct ic_line_inv_vaddr_ipi {
unsigned long paddr, vaddr;
int sz;
};
static void __ic_line_inv_vaddr_helper(void *info)
{
struct ic_line_inv_vaddr_ipi *ic_inv = (struct ic_line_inv_vaddr_ipi*) info;
__ic_line_inv_vaddr_local(ic_inv->paddr, ic_inv->vaddr, ic_inv->sz);
}
static void __ic_line_inv_vaddr(unsigned long paddr, unsigned long vaddr,
unsigned long sz)
{
struct ic_line_inv_vaddr_ipi ic_inv = { paddr, vaddr , sz};
on_each_cpu(__ic_line_inv_vaddr_helper, &ic_inv, 1);
}
#else
#define __ic_entire_inv()
@ -553,12 +570,8 @@ void flush_icache_range(unsigned long kstart, unsigned long kend)
*/
void __sync_icache_dcache(unsigned long paddr, unsigned long vaddr, int len)
{
unsigned long flags;
local_irq_save(flags);
__ic_line_inv_vaddr(paddr, vaddr, len);
__dc_line_op(paddr, vaddr, len, OP_FLUSH_N_INV);
local_irq_restore(flags);
__ic_line_inv_vaddr(paddr, vaddr, len);
}
/* wrapper to compile time eliminate alignment checks in flush loop */

17
arch/arm/Kconfig
View File

@ -262,8 +262,22 @@ config NEED_MACH_MEMORY_H
config PHYS_OFFSET
hex "Physical address of main memory" if MMU
depends on !ARM_PATCH_PHYS_VIRT && !NEED_MACH_MEMORY_H
depends on !ARM_PATCH_PHYS_VIRT
default DRAM_BASE if !MMU
default 0x00000000 if ARCH_EBSA110 || \
EP93XX_SDCE3_SYNC_PHYS_OFFSET || \
ARCH_FOOTBRIDGE || \
ARCH_INTEGRATOR || \
ARCH_IOP13XX || \
ARCH_KS8695 || \
(ARCH_REALVIEW && !REALVIEW_HIGH_PHYS_OFFSET)
default 0x10000000 if ARCH_OMAP1 || ARCH_RPC
default 0x20000000 if ARCH_S5PV210
default 0x70000000 if REALVIEW_HIGH_PHYS_OFFSET
default 0xc0000000 if EP93XX_SDCE0_PHYS_OFFSET || ARCH_SA1100
default 0xd0000000 if EP93XX_SDCE1_PHYS_OFFSET
default 0xe0000000 if EP93XX_SDCE2_PHYS_OFFSET
default 0xf0000000 if EP93XX_SDCE3_ASYNC_PHYS_OFFSET
help
Please provide the physical address corresponding to the
location of main memory in your system.
@ -435,7 +449,6 @@ config ARCH_EP93XX
select ARM_VIC
select CLKDEV_LOOKUP
select CPU_ARM920T
select NEED_MACH_MEMORY_H
help
This enables support for the Cirrus EP93xx series of CPUs.

3
arch/arm/Makefile
View File

@ -127,6 +127,9 @@ CHECKFLAGS += -D__arm__
#Default value
head-y := arch/arm/kernel/head$(MMUEXT).o
# Text offset. This list is sorted numerically by address in order to
# provide a means to avoid/resolve conflicts in multi-arch kernels.
textofs-y := 0x00008000
textofs-$(CONFIG_ARCH_CLPS711X) := 0x00028000
# We don't want the htc bootloader to corrupt kernel during resume

5
arch/arm/boot/compressed/Makefile
View File

@ -81,7 +81,7 @@ ZTEXTADDR := 0
ZBSSADDR := ALIGN(8)
endif
SEDFLAGS = s/TEXT_START/$(ZTEXTADDR)/;s/BSS_START/$(ZBSSADDR)/
CPPFLAGS_vmlinux.lds := -DTEXT_START="$(ZTEXTADDR)" -DBSS_START="$(ZBSSADDR)"
suffix_$(CONFIG_KERNEL_GZIP) = gzip
suffix_$(CONFIG_KERNEL_LZO) = lzo
@ -199,8 +199,5 @@ CFLAGS_font.o := -Dstatic=
$(obj)/font.c: $(FONTC)
$(call cmd,shipped)
$(obj)/vmlinux.lds: $(obj)/vmlinux.lds.in arch/arm/boot/Makefile $(KCONFIG_CONFIG)
@sed "$(SEDFLAGS)" < $< > $@
$(obj)/hyp-stub.S: $(srctree)/arch/$(SRCARCH)/kernel/hyp-stub.S
$(call cmd,shipped)

8
arch/arm/boot/compressed/head.S
View File

@ -125,9 +125,11 @@ start:
THUMB( adr r12, BSYM(1f) )
THUMB( bx r12 )
.word 0x016f2818 @ Magic numbers to help the loader
.word start @ absolute load/run zImage address
.word _edata @ zImage end address
.word _magic_sig @ Magic numbers to help the loader
.word _magic_start @ absolute load/run zImage address
.word _magic_end @ zImage end address
.word 0x04030201 @ endianness flag
THUMB( .thumb )
1:
ARM_BE8( setend be ) @ go BE8 if compiled for BE8

17
arch/arm/boot/compressed/vmlinux.lds.in → arch/arm/boot/compressed/vmlinux.lds.S
View File

@ -1,12 +1,20 @@
/*
* linux/arch/arm/boot/compressed/vmlinux.lds.in
*
* Copyright (C) 2000 Russell King
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License version 2 as
* published by the Free Software Foundation.
*/
#ifdef CONFIG_CPU_ENDIAN_BE8
#define ZIMAGE_MAGIC(x) ( (((x) >> 24) & 0x000000ff) | \
(((x) >> 8) & 0x0000ff00) | \
(((x) << 8) & 0x00ff0000) | \
(((x) << 24) & 0xff000000) )
#else
#define ZIMAGE_MAGIC(x) (x)
#endif
OUTPUT_ARCH(arm)
ENTRY(_start)
SECTIONS
@ -57,6 +65,10 @@ SECTIONS
.pad : { BYTE(0); . = ALIGN(8); }
_edata = .;
_magic_sig = ZIMAGE_MAGIC(0x016f2818);
_magic_start = ZIMAGE_MAGIC(_start);
_magic_end = ZIMAGE_MAGIC(_edata);
. = BSS_START;
__bss_start = .;
.bss : { *(.bss) }
@ -73,4 +85,3 @@ SECTIONS
.stab.indexstr 0 : { *(.stab.indexstr) }
.comment 0 : { *(.comment) }
}

2
arch/arm/boot/dts/Makefile
View File

@ -357,7 +357,7 @@ dtb-$(CONFIG_ARCH_STI)+= stih407-b2120.dtb \
stih415-b2020.dtb \
stih416-b2000.dtb \
stih416-b2020.dtb \
stih416-b2020-revE.dtb
stih416-b2020e.dtb
dtb-$(CONFIG_MACH_SUN4I) += \
sun4i-a10-a1000.dtb \
sun4i-a10-cubieboard.dtb \

2
arch/arm/boot/dts/armada-380.dtsi
View File

@ -16,7 +16,7 @@
/ {
model = "Marvell Armada 380 family SoC";
compatible = "marvell,armada380", "marvell,armada38x";
compatible = "marvell,armada380";
cpus {
#address-cells = <1>;

2
arch/arm/boot/dts/armada-385-db.dts
View File

@ -16,7 +16,7 @@
/ {
model = "Marvell Armada 385 Development Board";
compatible = "marvell,a385-db", "marvell,armada385", "marvell,armada38x";
compatible = "marvell,a385-db", "marvell,armada385", "marvell,armada380";
chosen {
bootargs = "console=ttyS0,115200 earlyprintk";

2
arch/arm/boot/dts/armada-385-rd.dts
View File

@ -17,7 +17,7 @@
/ {
model = "Marvell Armada 385 Reference Design";
compatible = "marvell,a385-rd", "marvell,armada385", "marvell,armada38x";
compatible = "marvell,a385-rd", "marvell,armada385", "marvell,armada380";
chosen {
bootargs = "console=ttyS0,115200 earlyprintk";

2
arch/arm/boot/dts/armada-385.dtsi
View File

@ -16,7 +16,7 @@
/ {
model = "Marvell Armada 385 family SoC";
compatible = "marvell,armada385", "marvell,armada38x";
compatible = "marvell,armada385", "marvell,armada380";
cpus {
#address-cells = <1>;

2
arch/arm/boot/dts/armada-38x.dtsi
View File

@ -20,7 +20,7 @@
/ {
model = "Marvell Armada 38x family SoC";
compatible = "marvell,armada38x";
compatible = "marvell,armada380";
aliases {
gpio0 = &gpio0;

21
arch/arm/boot/dts/at91sam9261.dtsi
View File

@ -568,24 +568,17 @@
#size-cells = <0>;
#interrupt-cells = <1>;
slow_rc_osc: slow_rc_osc {
compatible = "fixed-clock";
main_osc: main_osc {
compatible = "atmel,at91rm9200-clk-main-osc";
#clock-cells = <0>;
clock-frequency = <32768>;
clock-accuracy = <50000000>;
};
clk32k: slck {
compatible = "atmel,at91sam9260-clk-slow";
#clock-cells = <0>;
clocks = <&slow_rc_osc &slow_xtal>;
interrupts-extended = <&pmc AT91_PMC_MOSCS>;
clocks = <&main_xtal>;
};
main: mainck {
compatible = "atmel,at91rm9200-clk-main";
#clock-cells = <0>;
interrupts-extended = <&pmc AT91_PMC_MOSCS>;
clocks = <&main_xtal>;
clocks = <&main_osc>;
};
plla: pllack {
@ -615,7 +608,7 @@
compatible = "atmel,at91rm9200-clk-master";
#clock-cells = <0>;
interrupts-extended = <&pmc AT91_PMC_MCKRDY>;
clocks = <&clk32k>, <&main>, <&plla>, <&pllb>;
clocks = <&slow_xtal>, <&main>, <&plla>, <&pllb>;
atmel,clk-output-range = <0 94000000>;
atmel,clk-divisors = <1 2 4 0>;
};
@ -632,7 +625,7 @@
#address-cells = <1>;
#size-cells = <0>;
interrupt-parent = <&pmc>;
clocks = <&clk32k>, <&main>, <&plla>, <&pllb>;
clocks = <&slow_xtal>, <&main>, <&plla>, <&pllb>;
prog0: prog0 {
#clock-cells = <0>;

4
arch/arm/boot/dts/at91sam9261ek.dts
View File

@ -20,6 +20,10 @@
reg = <0x20000000 0x4000000>;
};
slow_xtal {
clock-frequency = <32768>;
};
main_xtal {
clock-frequency = <18432000>;
};

4
arch/arm/boot/dts/at91sam9n12.dtsi
View File

@ -132,8 +132,8 @@
<595000000 650000000 3 0>,
<545000000 600000000 0 1>,
<495000000 555000000 1 1>,
<445000000 500000000 1 2>,
<400000000 450000000 1 3>;
<445000000 500000000 2 1>,
<400000000 450000000 3 1>;
};
plladiv: plladivck {

4
arch/arm/boot/dts/at91sam9x5.dtsi
View File

@ -140,8 +140,8 @@
595000000 650000000 3 0
545000000 600000000 0 1
495000000 555000000 1 1
445000000 500000000 1 2
400000000 450000000 1 3>;
445000000 500000000 2 1
400000000 450000000 3 1>;
};
plladiv: plladivck {

2
arch/arm/boot/dts/exynos4.dtsi
View File

@ -113,7 +113,7 @@
compatible = "arm,cortex-a9-gic";
#interrupt-cells = <3>;
interrupt-controller;
reg = <0x10490000 0x1000>, <0x10480000 0x100>;
reg = <0x10490000 0x10000>, <0x10480000 0x10000>;
};
combiner: interrupt-controller@10440000 {

10
arch/arm/boot/dts/imx51-babbage.dts
View File

@ -315,15 +315,15 @@
&esdhc1 {
pinctrl-names = "default";
pinctrl-0 = <&pinctrl_esdhc1>;
fsl,cd-controller;
fsl,wp-controller;
cd-gpios = <&gpio1 0 GPIO_ACTIVE_LOW>;
wp-gpios = <&gpio1 1 GPIO_ACTIVE_HIGH>;
status = "okay";
};
&esdhc2 {
pinctrl-names = "default";
pinctrl-0 = <&pinctrl_esdhc2>;
cd-gpios = <&gpio1 6 GPIO_ACTIVE_HIGH>;
cd-gpios = <&gpio1 6 GPIO_ACTIVE_LOW>;
wp-gpios = <&gpio1 5 GPIO_ACTIVE_HIGH>;
status = "okay";
};
@ -468,8 +468,8 @@
MX51_PAD_SD1_DATA1__SD1_DATA1 0x20d5
MX51_PAD_SD1_DATA2__SD1_DATA2 0x20d5
MX51_PAD_SD1_DATA3__SD1_DATA3 0x20d5
MX51_PAD_GPIO1_0__SD1_CD 0x20d5
MX51_PAD_GPIO1_1__SD1_WP 0x20d5
MX51_PAD_GPIO1_0__GPIO1_0 0x100
MX51_PAD_GPIO1_1__GPIO1_1 0x100
>;
};

4
arch/arm/boot/dts/imx51-eukrea-mbimxsd51-baseboard.dts
View File

@ -107,7 +107,7 @@
&esdhc1 {
pinctrl-names = "default";
pinctrl-0 = <&pinctrl_esdhc1 &pinctrl_esdhc1_cd>;
fsl,cd-controller;
cd-gpios = <&gpio1 0 GPIO_ACTIVE_LOW>;
status = "okay";
};
@ -206,7 +206,7 @@
pinctrl_esdhc1_cd: esdhc1_cd {
fsl,pins = <
MX51_PAD_GPIO1_0__SD1_CD 0x20d5
MX51_PAD_GPIO1_0__GPIO1_0 0xd5
>;
};

38
arch/arm/boot/dts/imx53-m53evk.dts
View File

@ -21,27 +21,25 @@
<0xb0000000 0x20000000>;
};
soc {
display1: display@di1 {
compatible = "fsl,imx-parallel-display";
interface-pix-fmt = "bgr666";
pinctrl-names = "default";
pinctrl-0 = <&pinctrl_ipu_disp1>;
display1: display@di1 {
compatible = "fsl,imx-parallel-display";
interface-pix-fmt = "bgr666";
pinctrl-names = "default";
pinctrl-0 = <&pinctrl_ipu_disp1>;
display-timings {
800x480p60 {
native-mode;
clock-frequency = <31500000>;
hactive = <800>;
vactive = <480>;
hfront-porch = <40>;
hback-porch = <88>;
hsync-len = <128>;
vback-porch = <33>;
vfront-porch = <9>;
vsync-len = <3>;
vsync-active = <1>;
};
display-timings {
800x480p60 {
native-mode;
clock-frequency = <31500000>;
hactive = <800>;
vactive = <480>;
hfront-porch = <40>;
hback-porch = <88>;
hsync-len = <128>;
vback-porch = <33>;
vfront-porch = <9>;
vsync-len = <3>;
vsync-active = <1>;
};
};

10
arch/arm/boot/dts/imx6dl-hummingboard.dts
View File

@ -143,6 +143,14 @@
fsl,pins = <MX6QDL_PAD_GPIO_0__GPIO1_IO00 0x1b0b0>;
};
pinctrl_hummingboard_usbotg_id: hummingboard-usbotg-id {
/*
* Similar to pinctrl_usbotg_2, but we want it
* pulled down for a fixed host connection.
*/
fsl,pins = <MX6QDL_PAD_GPIO_1__USB_OTG_ID 0x13059>;
};
pinctrl_hummingboard_usbotg_vbus: hummingboard-usbotg-vbus {
fsl,pins = <MX6QDL_PAD_EIM_D22__GPIO3_IO22 0x1b0b0>;
};
@ -178,6 +186,8 @@
};
&usbotg {
pinctrl-names = "default";
pinctrl-0 = <&pinctrl_hummingboard_usbotg_id>;
vbus-supply = <&reg_usbotg_vbus>;
status = "okay";
};

2
arch/arm/boot/dts/imx6q-gw51xx.dts
View File

@ -11,7 +11,7 @@
/dts-v1/;
#include "imx6q.dtsi"
#include "imx6qdl-gw54xx.dtsi"
#include "imx6qdl-gw51xx.dtsi"
/ {
model = "Gateworks Ventana i.MX6 Quad GW51XX";

27
arch/arm/boot/dts/imx6qdl-cubox-i.dtsi
View File

@ -12,6 +12,19 @@
pinctrl-0 = <&pinctrl_cubox_i_ir>;
};
pwmleds {
compatible = "pwm-leds";
pinctrl-names = "default";
pinctrl-0 = <&pinctrl_cubox_i_pwm1>;
front {
active-low;
label = "imx6:red:front";
max-brightness = <248>;
pwms = <&pwm1 0 50000>;
};
};
regulators {
compatible = "simple-bus";
@ -109,6 +122,10 @@
>;
};
pinctrl_cubox_i_pwm1: cubox-i-pwm1-front-led {
fsl,pins = <MX6QDL_PAD_DISP0_DAT8__PWM1_OUT 0x1b0b0>;
};
pinctrl_cubox_i_spdif: cubox-i-spdif {
fsl,pins = <MX6QDL_PAD_GPIO_17__SPDIF_OUT 0x13091>;
};
@ -117,6 +134,14 @@
fsl,pins = <MX6QDL_PAD_GPIO_0__GPIO1_IO00 0x4001b0b0>;
};
pinctrl_cubox_i_usbotg_id: cubox-i-usbotg-id {
/*
* The Cubox-i pulls this low, but as it's pointless
* leaving it as a pull-up, even if it is just 10uA.
*/
fsl,pins = <MX6QDL_PAD_GPIO_1__USB_OTG_ID 0x13059>;
};
pinctrl_cubox_i_usbotg_vbus: cubox-i-usbotg-vbus {
fsl,pins = <MX6QDL_PAD_EIM_D22__GPIO3_IO22 0x4001b0b0>;
};
@ -153,6 +178,8 @@
};
&usbotg {
pinctrl-names = "default";
pinctrl-0 = <&pinctrl_cubox_i_usbotg_id>;
vbus-supply = <&reg_usbotg_vbus>;
status = "okay";
};

2
arch/arm/boot/dts/imx6qdl-gw51xx.dtsi
View File

@ -161,7 +161,7 @@
status = "okay";
pmic: ltc3676@3c {
compatible = "ltc,ltc3676";
compatible = "lltc,ltc3676";
reg = <0x3c>;
regulators {

4
arch/arm/boot/dts/imx6qdl-gw52xx.dtsi
View File

@ -220,7 +220,7 @@
};
pmic: ltc3676@3c {
compatible = "ltc,ltc3676";
compatible = "lltc,ltc3676";
reg = <0x3c>;
regulators {
@ -288,7 +288,7 @@
codec: sgtl5000@0a {
compatible = "fsl,sgtl5000";
reg = <0x0a>;
clocks = <&clks 169>;
clocks = <&clks 201>;
VDDA-supply = <&reg_1p8v>;
VDDIO-supply = <&reg_3p3v>;
};

2
arch/arm/boot/dts/imx6qdl-gw53xx.dtsi
View File

@ -234,7 +234,7 @@
};
pmic: ltc3676@3c {
compatible = "ltc,ltc3676";
compatible = "lltc,ltc3676";
reg = <0x3c>;
regulators {

13
arch/arm/boot/dts/imx6qdl-microsom.dtsi
View File

@ -10,14 +10,6 @@
MX6QDL_PAD_CSI0_DAT11__UART1_RX_DATA 0x1b0b1
>;
};
pinctrl_microsom_usbotg: microsom-usbotg {
/*
* Similar to pinctrl_usbotg_2, but we want it
* pulled down for a fixed host connection.
*/
fsl,pins = <MX6QDL_PAD_GPIO_1__USB_OTG_ID 0x13059>;
};
};
};
@ -26,8 +18,3 @@
pinctrl-0 = <&pinctrl_microsom_uart1>;
status = "okay";
};
&usbotg {
pinctrl-names = "default";
pinctrl-0 = <&pinctrl_microsom_usbotg>;
};

2
arch/arm/boot/dts/imx6sl.dtsi
View File

@ -686,7 +686,7 @@
compatible = "fsl,imx6sl-fec", "fsl,imx25-fec";
reg = <0x02188000 0x4000>;
interrupts = <0 114 IRQ_TYPE_LEVEL_HIGH>;
clocks = <&clks IMX6SL_CLK_ENET_REF>,
clocks = <&clks IMX6SL_CLK_ENET>,
<&clks IMX6SL_CLK_ENET_REF>;
clock-names = "ipg", "ahb";
status = "disabled";

4
arch/arm/boot/dts/kirkwood-guruplug-server-plus.dts
View File

@ -105,7 +105,6 @@
compatible = "ethernet-phy-id0141.0cb0",
"ethernet-phy-ieee802.3-c22";
reg = <0>;
phy-connection-type = "rgmii-id";
};
ethphy1: ethernet-phy@1 {
@ -113,7 +112,6 @@
compatible = "ethernet-phy-id0141.0cb0",
"ethernet-phy-ieee802.3-c22";
reg = <1>;
phy-connection-type = "rgmii-id";
};
};
@ -121,6 +119,7 @@
status = "okay";
ethernet0-port@0 {
phy-handle = <&ethphy0>;
phy-connection-type = "rgmii-id";
};
};
@ -128,5 +127,6 @@
status = "okay";
ethernet1-port@0 {
phy-handle = <&ethphy1>;
phy-connection-type = "rgmii-id";
};
};

8
arch/arm/boot/dts/stih415.dtsi
View File

@ -169,8 +169,8 @@
pinctrl-names = "default";
pinctrl-0 = <&pinctrl_mii0>;
clock-names = "stmmaceth";
clocks = <&clk_s_a1_ls CLK_GMAC0_PHY>;
clock-names = "stmmaceth", "sti-ethclk";
clocks = <&clk_s_a1_ls CLK_ICN_IF_2>, <&clk_s_a1_ls CLK_GMAC0_PHY>;
};
ethernet1: dwmac@fef08000 {
@ -192,8 +192,8 @@
reset-names = "stmmaceth";
pinctrl-names = "default";
pinctrl-0 = <&pinctrl_mii1>;
clock-names = "stmmaceth";
clocks = <&clk_s_a0_ls CLK_ETH1_PHY>;
clock-names = "stmmaceth", "sti-ethclk";
clocks = <&clk_s_a0_ls CLK_ICN_REG>, <&clk_s_a0_ls CLK_ETH1_PHY>;
};
rc: rc@fe518000 {

0
arch/arm/boot/dts/stih416-b2020-revE.dts → arch/arm/boot/dts/stih416-b2020e.dts
View File

8
arch/arm/boot/dts/stih416.dtsi
View File

@ -175,8 +175,8 @@
reset-names = "stmmaceth";
pinctrl-names = "default";
pinctrl-0 = <&pinctrl_mii0>;
clock-names = "stmmaceth";
clocks = <&clk_s_a1_ls CLK_GMAC0_PHY>;
clock-names = "stmmaceth", "sti-ethclk";
clocks = <&clk_s_a1_ls CLK_ICN_IF_2>, <&clk_s_a1_ls CLK_GMAC0_PHY>;
};
ethernet1: dwmac@fef08000 {
@ -197,8 +197,8 @@
reset-names = "stmmaceth";
pinctrl-names = "default";
pinctrl-0 = <&pinctrl_mii1>;
clock-names = "stmmaceth";
clocks = <&clk_s_a0_ls CLK_ETH1_PHY>;
clock-names = "stmmaceth", "sti-ethclk";
clocks = <&clk_s_a0_ls CLK_ICN_REG>, <&clk_s_a0_ls CLK_ETH1_PHY>;
};
rc: rc@fe518000 {

52
arch/arm/common/mcpm_entry.c
View File

@ -12,11 +12,13 @@
#include <linux/kernel.h>
#include <linux/init.h>
#include <linux/irqflags.h>
#include <linux/cpu_pm.h>
#include <asm/mcpm.h>
#include <asm/cacheflush.h>
#include <asm/idmap.h>
#include <asm/cputype.h>
#include <asm/suspend.h>
extern unsigned long mcpm_entry_vectors[MAX_NR_CLUSTERS][MAX_CPUS_PER_CLUSTER];
@ -146,6 +148,56 @@ int mcpm_cpu_powered_up(void)
return 0;
}
#ifdef CONFIG_ARM_CPU_SUSPEND
static int __init nocache_trampoline(unsigned long _arg)
{
void (*cache_disable)(void) = (void *)_arg;
unsigned int mpidr = read_cpuid_mpidr();
unsigned int cpu = MPIDR_AFFINITY_LEVEL(mpidr, 0);
unsigned int cluster = MPIDR_AFFINITY_LEVEL(mpidr, 1);
phys_reset_t phys_reset;
mcpm_set_entry_vector(cpu, cluster, cpu_resume);
setup_mm_for_reboot();
__mcpm_cpu_going_down(cpu, cluster);
BUG_ON(!__mcpm_outbound_enter_critical(cpu, cluster));
cache_disable();
__mcpm_outbound_leave_critical(cluster, CLUSTER_DOWN);
__mcpm_cpu_down(cpu, cluster);
phys_reset = (phys_reset_t)(unsigned long)virt_to_phys(cpu_reset);
phys_reset(virt_to_phys(mcpm_entry_point));
BUG();
}
int __init mcpm_loopback(void (*cache_disable)(void))
{
int ret;
/*
* We're going to soft-restart the current CPU through the
* low-level MCPM code by leveraging the suspend/resume
* infrastructure. Let's play it safe by using cpu_pm_enter()
* in case the CPU init code path resets the VFP or similar.
*/
local_irq_disable();
local_fiq_disable();
ret = cpu_pm_enter();
if (!ret) {
ret = cpu_suspend((unsigned long)cache_disable, nocache_trampoline);
cpu_pm_exit();
}
local_fiq_enable();
local_irq_enable();
if (ret)
pr_err("%s returned %d\n", __func__, ret);
return ret;
}
#endif
struct sync_struct mcpm_sync;
/*

1
arch/arm/configs/imx_v6_v7_defconfig
View File

@ -186,6 +186,7 @@ CONFIG_VIDEO_MX3=y
CONFIG_V4L_MEM2MEM_DRIVERS=y
CONFIG_VIDEO_CODA=y
CONFIG_SOC_CAMERA_OV2640=y
CONFIG_IMX_IPUV3_CORE=y
CONFIG_DRM=y
CONFIG_DRM_PANEL_SIMPLE=y
CONFIG_BACKLIGHT_LCD_SUPPORT=y

1
arch/arm/configs/multi_v7_defconfig
View File

@ -353,6 +353,7 @@ CONFIG_MFD_NVEC=y
CONFIG_KEYBOARD_NVEC=y
CONFIG_SERIO_NVEC_PS2=y
CONFIG_NVEC_POWER=y
CONFIG_QCOM_GSBI=y
CONFIG_COMMON_CLK_QCOM=y
CONFIG_MSM_GCC_8660=y
CONFIG_MSM_MMCC_8960=y

2
arch/arm/configs/mvebu_v7_defconfig
View File

@ -14,6 +14,7 @@ CONFIG_MACH_ARMADA_370=y
CONFIG_MACH_ARMADA_375=y
CONFIG_MACH_ARMADA_38X=y
CONFIG_MACH_ARMADA_XP=y
CONFIG_MACH_DOVE=y
CONFIG_NEON=y
# CONFIG_CACHE_L2X0 is not set
# CONFIG_SWP_EMULATE is not set
@ -52,6 +53,7 @@ CONFIG_INPUT_EVDEV=y
CONFIG_KEYBOARD_GPIO=y
CONFIG_SERIAL_8250=y
CONFIG_SERIAL_8250_CONSOLE=y
CONFIG_SERIAL_OF_PLATFORM=y
CONFIG_I2C=y
CONFIG_SPI=y
CONFIG_SPI_ORION=y

4
arch/arm/crypto/Makefile
View File

@ -5,10 +5,14 @@
obj-$(CONFIG_CRYPTO_AES_ARM) += aes-arm.o
obj-$(CONFIG_CRYPTO_AES_ARM_BS) += aes-arm-bs.o
obj-$(CONFIG_CRYPTO_SHA1_ARM) += sha1-arm.o
obj-$(CONFIG_CRYPTO_SHA1_ARM_NEON) += sha1-arm-neon.o
obj-$(CONFIG_CRYPTO_SHA512_ARM_NEON) += sha512-arm-neon.o
aes-arm-y := aes-armv4.o aes_glue.o
aes-arm-bs-y := aesbs-core.o aesbs-glue.o
sha1-arm-y := sha1-armv4-large.o sha1_glue.o
sha1-arm-neon-y := sha1-armv7-neon.o sha1_neon_glue.o
sha512-arm-neon-y := sha512-armv7-neon.o sha512_neon_glue.o
quiet_cmd_perl = PERL $@
cmd_perl = $(PERL) $(<) > $(@)

3
arch/arm/crypto/aes-armv4.S
View File

@ -35,6 +35,7 @@
@ that is being targetted.
#include <linux/linkage.h>
#include <asm/assembler.h>
.text
@ -648,7 +649,7 @@ _armv4_AES_set_encrypt_key:
.Ldone: mov r0,#0
ldmia sp!,{r4-r12,lr}
.Labrt: mov pc,lr
.Labrt: ret lr
ENDPROC(private_AES_set_encrypt_key)
.align 5

634
arch/arm/crypto/sha1-armv7-neon.S 100644
View File

@ -0,0 +1,634 @@
/* sha1-armv7-neon.S - ARM/NEON accelerated SHA-1 transform function
*
* Copyright © 2013-2014 Jussi Kivilinna <jussi.kivilinna@iki.fi>
*
* This program is free software; you can redistribute it and/or modify it
* under the terms of the GNU General Public License as published by the Free
* Software Foundation; either version 2 of the License, or (at your option)
* any later version.
*/
#include <linux/linkage.h>
.syntax unified
.code 32
.fpu neon
.text
/* Context structure */
#define state_h0 0
#define state_h1 4
#define state_h2 8
#define state_h3 12
#define state_h4 16
/* Constants */
#define K1 0x5A827999
#define K2 0x6ED9EBA1
#define K3 0x8F1BBCDC
#define K4 0xCA62C1D6
.align 4
.LK_VEC:
.LK1: .long K1, K1, K1, K1
.LK2: .long K2, K2, K2, K2
.LK3: .long K3, K3, K3, K3
.LK4: .long K4, K4, K4, K4
/* Register macros */
#define RSTATE r0
#define RDATA r1
#define RNBLKS r2
#define ROLDSTACK r3
#define RWK lr
#define _a r4
#define _b r5
#define _c r6
#define _d r7
#define _e r8
#define RT0 r9
#define RT1 r10
#define RT2 r11
#define RT3 r12
#define W0 q0
#define W1 q1
#define W2 q2
#define W3 q3
#define W4 q4
#define W5 q5
#define W6 q6
#define W7 q7
#define tmp0 q8
#define tmp1 q9
#define tmp2 q10
#define tmp3 q11
#define qK1 q12
#define qK2 q13
#define qK3 q14
#define qK4 q15
/* Round function macros. */
#define WK_offs(i) (((i) & 15) * 4)
#define _R_F1(a,b,c,d,e,i,pre1,pre2,pre3,i16,\
W,W_m04,W_m08,W_m12,W_m16,W_m20,W_m24,W_m28) \
ldr RT3, [sp, WK_offs(i)]; \
pre1(i16,W,W_m04,W_m08,W_m12,W_m16,W_m20,W_m24,W_m28); \
bic RT0, d, b; \
add e, e, a, ror #(32 - 5); \
and RT1, c, b; \
pre2(i16,W,W_m04,W_m08,W_m12,W_m16,W_m20,W_m24,W_m28); \
add RT0, RT0, RT3; \
add e, e, RT1; \
ror b, #(32 - 30); \
pre3(i16,W,W_m04,W_m08,W_m12,W_m16,W_m20,W_m24,W_m28); \
add e, e, RT0;
#define _R_F2(a,b,c,d,e,i,pre1,pre2,pre3,i16,\
W,W_m04,W_m08,W_m12,W_m16,W_m20,W_m24,W_m28) \
ldr RT3, [sp, WK_offs(i)]; \
pre1(i16,W,W_m04,W_m08,W_m12,W_m16,W_m20,W_m24,W_m28); \
eor RT0, d, b; \
add e, e, a, ror #(32 - 5); \
eor RT0, RT0, c; \
pre2(i16,W,W_m04,W_m08,W_m12,W_m16,W_m20,W_m24,W_m28); \
add e, e, RT3; \
ror b, #(32 - 30); \
pre3(i16,W,W_m04,W_m08,W_m12,W_m16,W_m20,W_m24,W_m28); \
add e, e, RT0; \
#define _R_F3(a,b,c,d,e,i,pre1,pre2,pre3,i16,\
W,W_m04,W_m08,W_m12,W_m16,W_m20,W_m24,W_m28) \
ldr RT3, [sp, WK_offs(i)]; \
pre1(i16,W,W_m04,W_m08,W_m12,W_m16,W_m20,W_m24,W_m28); \
eor RT0, b, c; \
and RT1, b, c; \
add e, e, a, ror #(32 - 5); \
pre2(i16,W,W_m04,W_m08,W_m12,W_m16,W_m20,W_m24,W_m28); \
and RT0, RT0, d; \
add RT1, RT1, RT3; \
add e, e, RT0; \
ror b, #(32 - 30); \
pre3(i16,W,W_m04,W_m08,W_m12,W_m16,W_m20,W_m24,W_m28); \
add e, e, RT1;
#define _R_F4(a,b,c,d,e,i,pre1,pre2,pre3,i16,\
W,W_m04,W_m08,W_m12,W_m16,W_m20,W_m24,W_m28) \
_R_F2(a,b,c,d,e,i,pre1,pre2,pre3,i16,\
W,W_m04,W_m08,W_m12,W_m16,W_m20,W_m24,W_m28)
#define _R(a,b,c,d,e,f,i,pre1,pre2,pre3,i16,\
W,W_m04,W_m08,W_m12,W_m16,W_m20,W_m24,W_m28) \
_R_##f(a,b,c,d,e,i,pre1,pre2,pre3,i16,\
W,W_m04,W_m08,W_m12,W_m16,W_m20,W_m24,W_m28)
#define R(a,b,c,d,e,f,i) \
_R_##f(a,b,c,d,e,i,dummy,dummy,dummy,i16,\
W,W_m04,W_m08,W_m12,W_m16,W_m20,W_m24,W_m28)
#define dummy(...)
/* Input expansion macros. */
/********* Precalc macros for rounds 0-15 *************************************/
#define W_PRECALC_00_15() \
add RWK, sp, #(WK_offs(0)); \
\
vld1.32 {tmp0, tmp1}, [RDATA]!; \
vrev32.8 W0, tmp0; /* big => little */ \
vld1.32 {tmp2, tmp3}, [RDATA]!; \
vadd.u32 tmp0, W0, curK; \
vrev32.8 W7, tmp1; /* big => little */ \
vrev32.8 W6, tmp2; /* big => little */ \
vadd.u32 tmp1, W7, curK; \
vrev32.8 W5, tmp3; /* big => little */ \
vadd.u32 tmp2, W6, curK; \
vst1.32 {tmp0, tmp1}, [RWK]!; \
vadd.u32 tmp3, W5, curK; \
vst1.32 {tmp2, tmp3}, [RWK]; \
#define WPRECALC_00_15_0(i,W,W_m04,W_m08,W_m12,W_m16,W_m20,W_m24,W_m28) \
vld1.32 {tmp0, tmp1}, [RDATA]!; \
#define WPRECALC_00_15_1(i,W,W_m04,W_m08,W_m12,W_m16,W_m20,W_m24,W_m28) \
add RWK, sp, #(WK_offs(0)); \
#define WPRECALC_00_15_2(i,W,W_m04,W_m08,W_m12,W_m16,W_m20,W_m24,W_m28) \
vrev32.8 W0, tmp0; /* big => little */ \
#define WPRECALC_00_15_3(i,W,W_m04,W_m08,W_m12,W_m16,W_m20,W_m24,W_m28) \
vld1.32 {tmp2, tmp3}, [RDATA]!; \
#define WPRECALC_00_15_4(i,W,W_m04,W_m08,W_m12,W_m16,W_m20,W_m24,W_m28) \
vadd.u32 tmp0, W0, curK; \
#define WPRECALC_00_15_5(i,W,W_m04,W_m08,W_m12,W_m16,W_m20,W_m24,W_m28) \
vrev32.8 W7, tmp1; /* big => little */ \
#define WPRECALC_00_15_6(i,W,W_m04,W_m08,W_m12,W_m16,W_m20,W_m24,W_m28) \
vrev32.8 W6, tmp2; /* big => little */ \
#define WPRECALC_00_15_7(i,W,W_m04,W_m08,W_m12,W_m16,W_m20,W_m24,W_m28) \
vadd.u32 tmp1, W7, curK; \
#define WPRECALC_00_15_8(i,W,W_m04,W_m08,W_m12,W_m16,W_m20,W_m24,W_m28) \
vrev32.8 W5, tmp3; /* big => little */ \
#define WPRECALC_00_15_9(i,W,W_m04,W_m08,W_m12,W_m16,W_m20,W_m24,W_m28) \
vadd.u32 tmp2, W6, curK; \
#define WPRECALC_00_15_10(i,W,W_m04,W_m08,W_m12,W_m16,W_m20,W_m24,W_m28) \
vst1.32 {tmp0, tmp1}, [RWK]!; \
#define WPRECALC_00_15_11(i,W,W_m04,W_m08,W_m12,W_m16,W_m20,W_m24,W_m28) \
vadd.u32 tmp3, W5, curK; \
#define WPRECALC_00_15_12(i,W,W_m04,W_m08,W_m12,W_m16,W_m20,W_m24,W_m28) \
vst1.32 {tmp2, tmp3}, [RWK]; \
/********* Precalc macros for rounds 16-31 ************************************/
#define WPRECALC_16_31_0(i,W,W_m04,W_m08,W_m12,W_m16,W_m20,W_m24,W_m28) \
veor tmp0, tmp0; \
vext.8 W, W_m16, W_m12, #8; \
#define WPRECALC_16_31_1(i,W,W_m04,W_m08,W_m12,W_m16,W_m20,W_m24,W_m28) \
add RWK, sp, #(WK_offs(i)); \
vext.8 tmp0, W_m04, tmp0, #4; \
#define WPRECALC_16_31_2(i,W,W_m04,W_m08,W_m12,W_m16,W_m20,W_m24,W_m28) \
veor tmp0, tmp0, W_m16; \
veor.32 W, W, W_m08; \
#define WPRECALC_16_31_3(i,W,W_m04,W_m08,W_m12,W_m16,W_m20,W_m24,W_m28) \
veor tmp1, tmp1; \
veor W, W, tmp0; \
#define WPRECALC_16_31_4(i,W,W_m04,W_m08,W_m12,W_m16,W_m20,W_m24,W_m28) \
vshl.u32 tmp0, W, #1; \
#define WPRECALC_16_31_5(i,W,W_m04,W_m08,W_m12,W_m16,W_m20,W_m24,W_m28) \
vext.8 tmp1, tmp1, W, #(16-12); \
vshr.u32 W, W, #31; \
#define WPRECALC_16_31_6(i,W,W_m04,W_m08,W_m12,W_m16,W_m20,W_m24,W_m28) \
vorr tmp0, tmp0, W; \
vshr.u32 W, tmp1, #30; \
#define WPRECALC_16_31_7(i,W,W_m04,W_m08,W_m12,W_m16,W_m20,W_m24,W_m28) \
vshl.u32 tmp1, tmp1, #2; \
#define WPRECALC_16_31_8(i,W,W_m04,W_m08,W_m12,W_m16,W_m20,W_m24,W_m28) \
veor tmp0, tmp0, W; \
#define WPRECALC_16_31_9(i,W,W_m04,W_m08,W_m12,W_m16,W_m20,W_m24,W_m28) \
veor W, tmp0, tmp1; \
#define WPRECALC_16_31_10(i,W,W_m04,W_m08,W_m12,W_m16,W_m20,W_m24,W_m28) \
vadd.u32 tmp0, W, curK; \
#define WPRECALC_16_31_11(i,W,W_m04,W_m08,W_m12,W_m16,W_m20,W_m24,W_m28) \
vst1.32 {tmp0}, [RWK];
/********* Precalc macros for rounds 32-79 ************************************/
#define WPRECALC_32_79_0(i,W,W_m04,W_m08,W_m12,W_m16,W_m20,W_m24,W_m28) \
veor W, W_m28; \
#define WPRECALC_32_79_1(i,W,W_m04,W_m08,W_m12,W_m16,W_m20,W_m24,W_m28) \
vext.8 tmp0, W_m08, W_m04, #8; \
#define WPRECALC_32_79_2(i,W,W_m04,W_m08,W_m12,W_m16,W_m20,W_m24,W_m28) \
veor W, W_m16; \
#define WPRECALC_32_79_3(i,W,W_m04,W_m08,W_m12,W_m16,W_m20,W_m24,W_m28) \
veor W, tmp0; \
#define WPRECALC_32_79_4(i,W,W_m04,W_m08,W_m12,W_m16,W_m20,W_m24,W_m28) \
add RWK, sp, #(WK_offs(i&~3)); \
#define WPRECALC_32_79_5(i,W,W_m04,W_m08,W_m12,W_m16,W_m20,W_m24,W_m28) \
vshl.u32 tmp1, W, #2; \
#define WPRECALC_32_79_6(i,W,W_m04,W_m08,W_m12,W_m16,W_m20,W_m24,W_m28) \
vshr.u32 tmp0, W, #30; \
#define WPRECALC_32_79_7(i,W,W_m04,W_m08,W_m12,W_m16,W_m20,W_m24,W_m28) \
vorr W, tmp0, tmp1; \
#define WPRECALC_32_79_8(i,W,W_m04,W_m08,W_m12,W_m16,W_m20,W_m24,W_m28) \
vadd.u32 tmp0, W, curK; \
#define WPRECALC_32_79_9(i,W,W_m04,W_m08,W_m12,W_m16,W_m20,W_m24,W_m28) \
vst1.32 {tmp0}, [RWK];
/*
* Transform nblks*64 bytes (nblks*16 32-bit words) at DATA.
*
* unsigned int
* sha1_transform_neon (void *ctx, const unsigned char *data,
* unsigned int nblks)
*/
.align 3
ENTRY(sha1_transform_neon)
/* input:
* r0: ctx, CTX
* r1: data (64*nblks bytes)
* r2: nblks
*/
cmp RNBLKS, #0;
beq .Ldo_nothing;
push {r4-r12, lr};
/*vpush {q4-q7};*/
adr RT3, .LK_VEC;
mov ROLDSTACK, sp;
/* Align stack. */
sub RT0, sp, #(16*4);
and RT0, #(~(16-1));
mov sp, RT0;
vld1.32 {qK1-qK2}, [RT3]!; /* Load K1,K2 */
/* Get the values of the chaining variables. */
ldm RSTATE, {_a-_e};
vld1.32 {qK3-qK4}, [RT3]; /* Load K3,K4 */
#undef curK
#define curK qK1
/* Precalc 0-15. */
W_PRECALC_00_15();
.Loop:
/* Transform 0-15 + Precalc 16-31. */
_R( _a, _b, _c, _d, _e, F1, 0,
WPRECALC_16_31_0, WPRECALC_16_31_1, WPRECALC_16_31_2, 16,
W4, W5, W6, W7, W0, _, _, _ );
_R( _e, _a, _b, _c, _d, F1, 1,
WPRECALC_16_31_3, WPRECALC_16_31_4, WPRECALC_16_31_5, 16,
W4, W5, W6, W7, W0, _, _, _ );
_R( _d, _e, _a, _b, _c, F1, 2,
WPRECALC_16_31_6, WPRECALC_16_31_7, WPRECALC_16_31_8, 16,
W4, W5, W6, W7, W0, _, _, _ );
_R( _c, _d, _e, _a, _b, F1, 3,
WPRECALC_16_31_9, WPRECALC_16_31_10,WPRECALC_16_31_11,16,
W4, W5, W6, W7, W0, _, _, _ );
#undef curK
#define curK qK2
_R( _b, _c, _d, _e, _a, F1, 4,
WPRECALC_16_31_0, WPRECALC_16_31_1, WPRECALC_16_31_2, 20,
W3, W4, W5, W6, W7, _, _, _ );
_R( _a, _b, _c, _d, _e, F1, 5,
WPRECALC_16_31_3, WPRECALC_16_31_4, WPRECALC_16_31_5, 20,
W3, W4, W5, W6, W7, _, _, _ );
_R( _e, _a, _b, _c, _d, F1, 6,
WPRECALC_16_31_6, WPRECALC_16_31_7, WPRECALC_16_31_8, 20,
W3, W4, W5, W6, W7, _, _, _ );
_R( _d, _e, _a, _b, _c, F1, 7,
WPRECALC_16_31_9, WPRECALC_16_31_10,WPRECALC_16_31_11,20,
W3, W4, W5, W6, W7, _, _, _ );
_R( _c, _d, _e, _a, _b, F1, 8,
WPRECALC_16_31_0, WPRECALC_16_31_1, WPRECALC_16_31_2, 24,
W2, W3, W4, W5, W6, _, _, _ );
_R( _b, _c, _d, _e, _a, F1, 9,
WPRECALC_16_31_3, WPRECALC_16_31_4, WPRECALC_16_31_5, 24,
W2, W3, W4, W5, W6, _, _, _ );
_R( _a, _b, _c, _d, _e, F1, 10,
WPRECALC_16_31_6, WPRECALC_16_31_7, WPRECALC_16_31_8, 24,
W2, W3, W4, W5, W6, _, _, _ );
_R( _e, _a, _b, _c, _d, F1, 11,
WPRECALC_16_31_9, WPRECALC_16_31_10,WPRECALC_16_31_11,24,
W2, W3, W4, W5, W6, _, _, _ );
_R( _d, _e, _a, _b, _c, F1, 12,
WPRECALC_16_31_0, WPRECALC_16_31_1, WPRECALC_16_31_2, 28,
W1, W2, W3, W4, W5, _, _, _ );
_R( _c, _d, _e, _a, _b, F1, 13,
WPRECALC_16_31_3, WPRECALC_16_31_4, WPRECALC_16_31_5, 28,
W1, W2, W3, W4, W5, _, _, _ );
_R( _b, _c, _d, _e, _a, F1, 14,
WPRECALC_16_31_6, WPRECALC_16_31_7, WPRECALC_16_31_8, 28,
W1, W2, W3, W4, W5, _, _, _ );
_R( _a, _b, _c, _d, _e, F1, 15,
WPRECALC_16_31_9, WPRECALC_16_31_10,WPRECALC_16_31_11,28,
W1, W2, W3, W4, W5, _, _, _ );
/* Transform 16-63 + Precalc 32-79. */
_R( _e, _a, _b, _c, _d, F1, 16,
WPRECALC_32_79_0, WPRECALC_32_79_1, WPRECALC_32_79_2, 32,
W0, W1, W2, W3, W4, W5, W6, W7);
_R( _d, _e, _a, _b, _c, F1, 17,
WPRECALC_32_79_3, WPRECALC_32_79_4, WPRECALC_32_79_5, 32,
W0, W1, W2, W3, W4, W5, W6, W7);
_R( _c, _d, _e, _a, _b, F1, 18,
WPRECALC_32_79_6, dummy, WPRECALC_32_79_7, 32,
W0, W1, W2, W3, W4, W5, W6, W7);
_R( _b, _c, _d, _e, _a, F1, 19,
WPRECALC_32_79_8, dummy, WPRECALC_32_79_9, 32,
W0, W1, W2, W3, W4, W5, W6, W7);
_R( _a, _b, _c, _d, _e, F2, 20,
WPRECALC_32_79_0, WPRECALC_32_79_1, WPRECALC_32_79_2, 36,
W7, W0, W1, W2, W3, W4, W5, W6);
_R( _e, _a, _b, _c, _d, F2, 21,
WPRECALC_32_79_3, WPRECALC_32_79_4, WPRECALC_32_79_5, 36,
W7, W0, W1, W2, W3, W4, W5, W6);
_R( _d, _e, _a, _b, _c, F2, 22,
WPRECALC_32_79_6, dummy, WPRECALC_32_79_7, 36,
W7, W0, W1, W2, W3, W4, W5, W6);
_R( _c, _d, _e, _a, _b, F2, 23,
WPRECALC_32_79_8, dummy, WPRECALC_32_79_9, 36,
W7, W0, W1, W2, W3, W4, W5, W6);
#undef curK
#define curK qK3
_R( _b, _c, _d, _e, _a, F2, 24,
WPRECALC_32_79_0, WPRECALC_32_79_1, WPRECALC_32_79_2, 40,
W6, W7, W0, W1, W2, W3, W4, W5);
_R( _a, _b, _c, _d, _e, F2, 25,
WPRECALC_32_79_3, WPRECALC_32_79_4, WPRECALC_32_79_5, 40,
W6, W7, W0, W1, W2, W3, W4, W5);
_R( _e, _a, _b, _c, _d, F2, 26,
WPRECALC_32_79_6, dummy, WPRECALC_32_79_7, 40,
W6, W7, W0, W1, W2, W3, W4, W5);
_R( _d, _e, _a, _b, _c, F2, 27,
WPRECALC_32_79_8, dummy, WPRECALC_32_79_9, 40,
W6, W7, W0, W1, W2, W3, W4, W5);
_R( _c, _d, _e, _a, _b, F2, 28,
WPRECALC_32_79_0, WPRECALC_32_79_1, WPRECALC_32_79_2, 44,
W5, W6, W7, W0, W1, W2, W3, W4);
_R( _b, _c, _d, _e, _a, F2, 29,
WPRECALC_32_79_3, WPRECALC_32_79_4, WPRECALC_32_79_5, 44,
W5, W6, W7, W0, W1, W2, W3, W4);
_R( _a, _b, _c, _d, _e, F2, 30,
WPRECALC_32_79_6, dummy, WPRECALC_32_79_7, 44,
W5, W6, W7, W0, W1, W2, W3, W4);
_R( _e, _a, _b, _c, _d, F2, 31,
WPRECALC_32_79_8, dummy, WPRECALC_32_79_9, 44,
W5, W6, W7, W0, W1, W2, W3, W4);
_R( _d, _e, _a, _b, _c, F2, 32,
WPRECALC_32_79_0, WPRECALC_32_79_1, WPRECALC_32_79_2, 48,
W4, W5, W6, W7, W0, W1, W2, W3);
_R( _c, _d, _e, _a, _b, F2, 33,
WPRECALC_32_79_3, WPRECALC_32_79_4, WPRECALC_32_79_5, 48,
W4, W5, W6, W7, W0, W1, W2, W3);
_R( _b, _c, _d, _e, _a, F2, 34,
WPRECALC_32_79_6, dummy, WPRECALC_32_79_7, 48,
W4, W5, W6, W7, W0, W1, W2, W3);
_R( _a, _b, _c, _d, _e, F2, 35,
WPRECALC_32_79_8, dummy, WPRECALC_32_79_9, 48,
W4, W5, W6, W7, W0, W1, W2, W3);
_R( _e, _a, _b, _c, _d, F2, 36,
WPRECALC_32_79_0, WPRECALC_32_79_1, WPRECALC_32_79_2, 52,
W3, W4, W5, W6, W7, W0, W1, W2);
_R( _d, _e, _a, _b, _c, F2, 37,
WPRECALC_32_79_3, WPRECALC_32_79_4, WPRECALC_32_79_5, 52,
W3, W4, W5, W6, W7, W0, W1, W2);
_R( _c, _d, _e, _a, _b, F2, 38,
WPRECALC_32_79_6, dummy, WPRECALC_32_79_7, 52,
W3, W4, W5, W6, W7, W0, W1, W2);
_R( _b, _c, _d, _e, _a, F2, 39,
WPRECALC_32_79_8, dummy, WPRECALC_32_79_9, 52,
W3, W4, W5, W6, W7, W0, W1, W2);
_R( _a, _b, _c, _d, _e, F3, 40,
WPRECALC_32_79_0, WPRECALC_32_79_1, WPRECALC_32_79_2, 56,
W2, W3, W4, W5, W6, W7, W0, W1);
_R( _e, _a, _b, _c, _d, F3, 41,
WPRECALC_32_79_3, WPRECALC_32_79_4, WPRECALC_32_79_5, 56,
W2, W3, W4, W5, W6, W7, W0, W1);
_R( _d, _e, _a, _b, _c, F3, 42,
WPRECALC_32_79_6, dummy, WPRECALC_32_79_7, 56,
W2, W3, W4, W5, W6, W7, W0, W1);
_R( _c, _d, _e, _a, _b, F3, 43,
WPRECALC_32_79_8, dummy, WPRECALC_32_79_9, 56,
W2, W3, W4, W5, W6, W7, W0, W1);
#undef curK
#define curK qK4
_R( _b, _c, _d, _e, _a, F3, 44,
WPRECALC_32_79_0, WPRECALC_32_79_1, WPRECALC_32_79_2, 60,
W1, W2, W3, W4, W5, W6, W7, W0);
_R( _a, _b, _c, _d, _e, F3, 45,
WPRECALC_32_79_3, WPRECALC_32_79_4, WPRECALC_32_79_5, 60,
W1, W2, W3, W4, W5, W6, W7, W0);
_R( _e, _a, _b, _c, _d, F3, 46,
WPRECALC_32_79_6, dummy, WPRECALC_32_79_7, 60,
W1, W2, W3, W4, W5, W6, W7, W0);
_R( _d, _e, _a, _b, _c, F3, 47,
WPRECALC_32_79_8, dummy, WPRECALC_32_79_9, 60,
W1, W2, W3, W4, W5, W6, W7, W0);
_R( _c, _d, _e, _a, _b, F3, 48,
WPRECALC_32_79_0, WPRECALC_32_79_1, WPRECALC_32_79_2, 64,
W0, W1, W2, W3, W4, W5, W6, W7);
_R( _b, _c, _d, _e, _a, F3, 49,
WPRECALC_32_79_3, WPRECALC_32_79_4, WPRECALC_32_79_5, 64,
W0, W1, W2, W3, W4, W5, W6, W7);
_R( _a, _b, _c, _d, _e, F3, 50,
WPRECALC_32_79_6, dummy, WPRECALC_32_79_7, 64,
W0, W1, W2, W3, W4, W5, W6, W7);
_R( _e, _a, _b, _c, _d, F3, 51,
WPRECALC_32_79_8, dummy, WPRECALC_32_79_9, 64,
W0, W1, W2, W3, W4, W5, W6, W7);
_R( _d, _e, _a, _b, _c, F3, 52,
WPRECALC_32_79_0, WPRECALC_32_79_1, WPRECALC_32_79_2, 68,
W7, W0, W1, W2, W3, W4, W5, W6);
_R( _c, _d, _e, _a, _b, F3, 53,
WPRECALC_32_79_3, WPRECALC_32_79_4, WPRECALC_32_79_5, 68,
W7, W0, W1, W2, W3, W4, W5, W6);
_R( _b, _c, _d, _e, _a, F3, 54,
WPRECALC_32_79_6, dummy, WPRECALC_32_79_7, 68,
W7, W0, W1, W2, W3, W4, W5, W6);
_R( _a, _b, _c, _d, _e, F3, 55,
WPRECALC_32_79_8, dummy, WPRECALC_32_79_9, 68,
W7, W0, W1, W2, W3, W4, W5, W6);
_R( _e, _a, _b, _c, _d, F3, 56,
WPRECALC_32_79_0, WPRECALC_32_79_1, WPRECALC_32_79_2, 72,
W6, W7, W0, W1, W2, W3, W4, W5);
_R( _d, _e, _a, _b, _c, F3, 57,
WPRECALC_32_79_3, WPRECALC_32_79_4, WPRECALC_32_79_5, 72,
W6, W7, W0, W1, W2, W3, W4, W5);
_R( _c, _d, _e, _a, _b, F3, 58,
WPRECALC_32_79_6, dummy, WPRECALC_32_79_7, 72,
W6, W7, W0, W1, W2, W3, W4, W5);
_R( _b, _c, _d, _e, _a, F3, 59,
WPRECALC_32_79_8, dummy, WPRECALC_32_79_9, 72,
W6, W7, W0, W1, W2, W3, W4, W5);
subs RNBLKS, #1;
_R( _a, _b, _c, _d, _e, F4, 60,
WPRECALC_32_79_0, WPRECALC_32_79_1, WPRECALC_32_79_2, 76,
W5, W6, W7, W0, W1, W2, W3, W4);
_R( _e, _a, _b, _c, _d, F4, 61,
WPRECALC_32_79_3, WPRECALC_32_79_4, WPRECALC_32_79_5, 76,
W5, W6, W7, W0, W1, W2, W3, W4);
_R( _d, _e, _a, _b, _c, F4, 62,
WPRECALC_32_79_6, dummy, WPRECALC_32_79_7, 76,
W5, W6, W7, W0, W1, W2, W3, W4);
_R( _c, _d, _e, _a, _b, F4, 63,
WPRECALC_32_79_8, dummy, WPRECALC_32_79_9, 76,
W5, W6, W7, W0, W1, W2, W3, W4);
beq .Lend;
/* Transform 64-79 + Precalc 0-15 of next block. */
#undef curK
#define curK qK1
_R( _b, _c, _d, _e, _a, F4, 64,
WPRECALC_00_15_0, dummy, dummy, _, _, _, _, _, _, _, _, _ );
_R( _a, _b, _c, _d, _e, F4, 65,
WPRECALC_00_15_1, dummy, dummy, _, _, _, _, _, _, _, _, _ );
_R( _e, _a, _b, _c, _d, F4, 66,
WPRECALC_00_15_2, dummy, dummy, _, _, _, _, _, _, _, _, _ );
_R( _d, _e, _a, _b, _c, F4, 67,
WPRECALC_00_15_3, dummy, dummy, _, _, _, _, _, _, _, _, _ );
_R( _c, _d, _e, _a, _b, F4, 68,
dummy, dummy, dummy, _, _, _, _, _, _, _, _, _ );
_R( _b, _c, _d, _e, _a, F4, 69,
dummy, dummy, dummy, _, _, _, _, _, _, _, _, _ );
_R( _a, _b, _c, _d, _e, F4, 70,
WPRECALC_00_15_4, dummy, dummy, _, _, _, _, _, _, _, _, _ );
_R( _e, _a, _b, _c, _d, F4, 71,
WPRECALC_00_15_5, dummy, dummy, _, _, _, _, _, _, _, _, _ );
_R( _d, _e, _a, _b, _c, F4, 72,
dummy, dummy, dummy, _, _, _, _, _, _, _, _, _ );
_R( _c, _d, _e, _a, _b, F4, 73,
dummy, dummy, dummy, _, _, _, _, _, _, _, _, _ );
_R( _b, _c, _d, _e, _a, F4, 74,
WPRECALC_00_15_6, dummy, dummy, _, _, _, _, _, _, _, _, _ );
_R( _a, _b, _c, _d, _e, F4, 75,
WPRECALC_00_15_7, dummy, dummy, _, _, _, _, _, _, _, _, _ );
_R( _e, _a, _b, _c, _d, F4, 76,
WPRECALC_00_15_8, dummy, dummy, _, _, _, _, _, _, _, _, _ );
_R( _d, _e, _a, _b, _c, F4, 77,
WPRECALC_00_15_9, dummy, dummy, _, _, _, _, _, _, _, _, _ );
_R( _c, _d, _e, _a, _b, F4, 78,
WPRECALC_00_15_10, dummy, dummy, _, _, _, _, _, _, _, _, _ );
_R( _b, _c, _d, _e, _a, F4, 79,
WPRECALC_00_15_11, dummy, WPRECALC_00_15_12, _, _, _, _, _, _, _, _, _ );
/* Update the chaining variables. */
ldm RSTATE, {RT0-RT3};
add _a, RT0;
ldr RT0, [RSTATE, #state_h4];
add _b, RT1;
add _c, RT2;
add _d, RT3;
add _e, RT0;
stm RSTATE, {_a-_e};
b .Loop;
.Lend:
/* Transform 64-79 */
R( _b, _c, _d, _e, _a, F4, 64 );
R( _a, _b, _c, _d, _e, F4, 65 );
R( _e, _a, _b, _c, _d, F4, 66 );
R( _d, _e, _a, _b, _c, F4, 67 );
R( _c, _d, _e, _a, _b, F4, 68 );
R( _b, _c, _d, _e, _a, F4, 69 );
R( _a, _b, _c, _d, _e, F4, 70 );
R( _e, _a, _b, _c, _d, F4, 71 );
R( _d, _e, _a, _b, _c, F4, 72 );
R( _c, _d, _e, _a, _b, F4, 73 );
R( _b, _c, _d, _e, _a, F4, 74 );
R( _a, _b, _c, _d, _e, F4, 75 );
R( _e, _a, _b, _c, _d, F4, 76 );
R( _d, _e, _a, _b, _c, F4, 77 );
R( _c, _d, _e, _a, _b, F4, 78 );
R( _b, _c, _d, _e, _a, F4, 79 );
mov sp, ROLDSTACK;
/* Update the chaining variables. */
ldm RSTATE, {RT0-RT3};
add _a, RT0;
ldr RT0, [RSTATE, #state_h4];
add _b, RT1;
add _c, RT2;
add _d, RT3;
/*vpop {q4-q7};*/
add _e, RT0;
stm RSTATE, {_a-_e};
pop {r4-r12, pc};
.Ldo_nothing:
bx lr
ENDPROC(sha1_transform_neon)

58
arch/arm/crypto/sha1_glue.c
View File

@ -23,32 +23,27 @@
#include <linux/types.h>
#include <crypto/sha.h>
#include <asm/byteorder.h>
#include <asm/crypto/sha1.h>
struct SHA1_CTX {
uint32_t h0,h1,h2,h3,h4;
u64 count;
u8 data[SHA1_BLOCK_SIZE];
};
asmlinkage void sha1_block_data_order(struct SHA1_CTX *digest,
asmlinkage void sha1_block_data_order(u32 *digest,
const unsigned char *data, unsigned int rounds);
static int sha1_init(struct shash_desc *desc)
{
struct SHA1_CTX *sctx = shash_desc_ctx(desc);
memset(sctx, 0, sizeof(*sctx));
sctx->h0 = SHA1_H0;
sctx->h1 = SHA1_H1;
sctx->h2 = SHA1_H2;
sctx->h3 = SHA1_H3;
sctx->h4 = SHA1_H4;
struct sha1_state *sctx = shash_desc_ctx(desc);
*sctx = (struct sha1_state){
.state = { SHA1_H0, SHA1_H1, SHA1_H2, SHA1_H3, SHA1_H4 },
};
return 0;
}
static int __sha1_update(struct SHA1_CTX *sctx, const u8 *data,
unsigned int len, unsigned int partial)
static int __sha1_update(struct sha1_state *sctx, const u8 *data,
unsigned int len, unsigned int partial)
{
unsigned int done = 0;
@ -56,43 +51,44 @@ static int __sha1_update(struct SHA1_CTX *sctx, const u8 *data,
if (partial) {
done = SHA1_BLOCK_SIZE - partial;
memcpy(sctx->data + partial, data, done);
sha1_block_data_order(sctx, sctx->data, 1);
memcpy(sctx->buffer + partial, data, done);
sha1_block_data_order(sctx->state, sctx->buffer, 1);
}
if (len - done >= SHA1_BLOCK_SIZE) {
const unsigned int rounds = (len - done) / SHA1_BLOCK_SIZE;
sha1_block_data_order(sctx, data + done, rounds);
sha1_block_data_order(sctx->state, data + done, rounds);
done += rounds * SHA1_BLOCK_SIZE;
}
memcpy(sctx->data, data + done, len - done);
memcpy(sctx->buffer, data + done, len - done);
return 0;
}
static int sha1_update(struct shash_desc *desc, const u8 *data,
unsigned int len)
int sha1_update_arm(struct shash_desc *desc, const u8 *data,
unsigned int len)
{
struct SHA1_CTX *sctx = shash_desc_ctx(desc);
struct sha1_state *sctx = shash_desc_ctx(desc);
unsigned int partial = sctx->count % SHA1_BLOCK_SIZE;
int res;
/* Handle the fast case right here */
if (partial + len < SHA1_BLOCK_SIZE) {
sctx->count += len;
memcpy(sctx->data + partial, data, len);
memcpy(sctx->buffer + partial, data, len);
return 0;
}
res = __sha1_update(sctx, data, len, partial);
return res;
}
EXPORT_SYMBOL_GPL(sha1_update_arm);
/* Add padding and return the message digest. */
static int sha1_final(struct shash_desc *desc, u8 *out)
{
struct SHA1_CTX *sctx = shash_desc_ctx(desc);
struct sha1_state *sctx = shash_desc_ctx(desc);
unsigned int i, index, padlen;
__be32 *dst = (__be32 *)out;
__be64 bits;
@ -106,7 +102,7 @@ static int sha1_final(struct shash_desc *desc, u8 *out)
/* We need to fill a whole block for __sha1_update() */
if (padlen <= 56) {
sctx->count += padlen;
memcpy(sctx->data + index, padding, padlen);
memcpy(sctx->buffer + index, padding, padlen);
} else {
__sha1_update(sctx, padding, padlen, index);
}
@ -114,7 +110,7 @@ static int sha1_final(struct shash_desc *desc, u8 *out)
/* Store state in digest */
for (i = 0; i < 5; i++)
dst[i] = cpu_to_be32(((u32 *)sctx)[i]);
dst[i] = cpu_to_be32(sctx->state[i]);
/* Wipe context */
memset(sctx, 0, sizeof(*sctx));
@ -124,7 +120,7 @@ static int sha1_final(struct shash_desc *desc, u8 *out)
static int sha1_export(struct shash_desc *desc, void *out)
{
struct SHA1_CTX *sctx = shash_desc_ctx(desc);
struct sha1_state *sctx = shash_desc_ctx(desc);
memcpy(out, sctx, sizeof(*sctx));
return 0;
}
@ -132,7 +128,7 @@ static int sha1_export(struct shash_desc *desc, void *out)
static int sha1_import(struct shash_desc *desc, const void *in)
{
struct SHA1_CTX *sctx = shash_desc_ctx(desc);
struct sha1_state *sctx = shash_desc_ctx(desc);
memcpy(sctx, in, sizeof(*sctx));
return 0;
}
@ -141,12 +137,12 @@ static int sha1_import(struct shash_desc *desc, const void *in)
static struct shash_alg alg = {
.digestsize = SHA1_DIGEST_SIZE,
.init = sha1_init,
.update = sha1_update,
.update = sha1_update_arm,
.final = sha1_final,
.export = sha1_export,
.import = sha1_import,
.descsize = sizeof(struct SHA1_CTX),
.statesize = sizeof(struct SHA1_CTX),
.descsize = sizeof(struct sha1_state),
.statesize = sizeof(struct sha1_state),
.base = {
.cra_name = "sha1",
.cra_driver_name= "sha1-asm",

197
arch/arm/crypto/sha1_neon_glue.c 100644
View File

@ -0,0 +1,197 @@
/*
* Glue code for the SHA1 Secure Hash Algorithm assembler implementation using
* ARM NEON instructions.
*
* Copyright © 2014 Jussi Kivilinna <jussi.kivilinna@iki.fi>
*
* This file is based on sha1_generic.c and sha1_ssse3_glue.c:
* Copyright (c) Alan Smithee.
* Copyright (c) Andrew McDonald <andrew@mcdonald.org.uk>
* Copyright (c) Jean-Francois Dive <jef@linuxbe.org>
* Copyright (c) Mathias Krause <minipli@googlemail.com>
* Copyright (c) Chandramouli Narayanan <mouli@linux.intel.com>
*
* This program is free software; you can redistribute it and/or modify it
* under the terms of the GNU General Public License as published by the Free
* Software Foundation; either version 2 of the License, or (at your option)
* any later version.
*
*/
#include <crypto/internal/hash.h>
#include <linux/init.h>
#include <linux/module.h>
#include <linux/mm.h>
#include <linux/cryptohash.h>
#include <linux/types.h>
#include <crypto/sha.h>
#include <asm/byteorder.h>
#include <asm/neon.h>
#include <asm/simd.h>
#include <asm/crypto/sha1.h>
asmlinkage void sha1_transform_neon(void *state_h, const char *data,
unsigned int rounds);
static int sha1_neon_init(struct shash_desc *desc)
{
struct sha1_state *sctx = shash_desc_ctx(desc);
*sctx = (struct sha1_state){
.state = { SHA1_H0, SHA1_H1, SHA1_H2, SHA1_H3, SHA1_H4 },
};
return 0;
}
static int __sha1_neon_update(struct shash_desc *desc, const u8 *data,
unsigned int len, unsigned int partial)
{
struct sha1_state *sctx = shash_desc_ctx(desc);
unsigned int done = 0;
sctx->count += len;
if (partial) {
done = SHA1_BLOCK_SIZE - partial;
memcpy(sctx->buffer + partial, data, done);
sha1_transform_neon(sctx->state, sctx->buffer, 1);
}
if (len - done >= SHA1_BLOCK_SIZE) {
const unsigned int rounds = (len - done) / SHA1_BLOCK_SIZE;
sha1_transform_neon(sctx->state, data + done, rounds);
done += rounds * SHA1_BLOCK_SIZE;
}
memcpy(sctx->buffer, data + done, len - done);
return 0;
}
static int sha1_neon_update(struct shash_desc *desc, const u8 *data,
unsigned int len)
{
struct sha1_state *sctx = shash_desc_ctx(desc);
unsigned int partial = sctx->count % SHA1_BLOCK_SIZE;
int res;
/* Handle the fast case right here */
if (partial + len < SHA1_BLOCK_SIZE) {
sctx->count += len;
memcpy(sctx->buffer + partial, data, len);
return 0;
}
if (!may_use_simd()) {
res = sha1_update_arm(desc, data, len);
} else {
kernel_neon_begin();
res = __sha1_neon_update(desc, data, len, partial);
kernel_neon_end();
}
return res;
}
/* Add padding and return the message digest. */
static int sha1_neon_final(struct shash_desc *desc, u8 *out)
{
struct sha1_state *sctx = shash_desc_ctx(desc);
unsigned int i, index, padlen;
__be32 *dst = (__be32 *)out;
__be64 bits;
static const u8 padding[SHA1_BLOCK_SIZE] = { 0x80, };
bits = cpu_to_be64(sctx->count << 3);
/* Pad out to 56 mod 64 and append length */
index = sctx->count % SHA1_BLOCK_SIZE;
padlen = (index < 56) ? (56 - index) : ((SHA1_BLOCK_SIZE+56) - index);
if (!may_use_simd()) {
sha1_update_arm(desc, padding, padlen);
sha1_update_arm(desc, (const u8 *)&bits, sizeof(bits));
} else {
kernel_neon_begin();
/* We need to fill a whole block for __sha1_neon_update() */
if (padlen <= 56) {
sctx->count += padlen;
memcpy(sctx->buffer + index, padding, padlen);
} else {
__sha1_neon_update(desc, padding, padlen, index);
}
__sha1_neon_update(desc, (const u8 *)&bits, sizeof(bits), 56);
kernel_neon_end();
}
/* Store state in digest */
for (i = 0; i < 5; i++)
dst[i] = cpu_to_be32(sctx->state[i]);
/* Wipe context */
memset(sctx, 0, sizeof(*sctx));
return 0;
}
static int sha1_neon_export(struct shash_desc *desc, void *out)
{
struct sha1_state *sctx = shash_desc_ctx(desc);
memcpy(out, sctx, sizeof(*sctx));
return 0;
}
static int sha1_neon_import(struct shash_desc *desc, const void *in)
{
struct sha1_state *sctx = shash_desc_ctx(desc);
memcpy(sctx, in, sizeof(*sctx));
return 0;
}
static struct shash_alg alg = {
.digestsize = SHA1_DIGEST_SIZE,
.init = sha1_neon_init,
.update = sha1_neon_update,
.final = sha1_neon_final,
.export = sha1_neon_export,
.import = sha1_neon_import,
.descsize = sizeof(struct sha1_state),
.statesize = sizeof(struct sha1_state),
.base = {
.cra_name = "sha1",
.cra_driver_name = "sha1-neon",
.cra_priority = 250,
.cra_flags = CRYPTO_ALG_TYPE_SHASH,
.cra_blocksize = SHA1_BLOCK_SIZE,
.cra_module = THIS_MODULE,
}
};
static int __init sha1_neon_mod_init(void)
{
if (!cpu_has_neon())
return -ENODEV;
return crypto_register_shash(&alg);
}
static void __exit sha1_neon_mod_fini(void)
{
crypto_unregister_shash(&alg);
}
module_init(sha1_neon_mod_init);
module_exit(sha1_neon_mod_fini);
MODULE_LICENSE("GPL");
MODULE_DESCRIPTION("SHA1 Secure Hash Algorithm, NEON accelerated");
MODULE_ALIAS("sha1");

455
arch/arm/crypto/sha512-armv7-neon.S 100644
View File

@ -0,0 +1,455 @@
/* sha512-armv7-neon.S - ARM/NEON assembly implementation of SHA-512 transform
*
* Copyright © 2013-2014 Jussi Kivilinna <jussi.kivilinna@iki.fi>
*
* This program is free software; you can redistribute it and/or modify it
* under the terms of the GNU General Public License as published by the Free
* Software Foundation; either version 2 of the License, or (at your option)
* any later version.
*/
#include <linux/linkage.h>
.syntax unified
.code 32
.fpu neon
.text
/* structure of SHA512_CONTEXT */
#define hd_a 0
#define hd_b ((hd_a) + 8)
#define hd_c ((hd_b) + 8)
#define hd_d ((hd_c) + 8)
#define hd_e ((hd_d) + 8)
#define hd_f ((hd_e) + 8)
#define hd_g ((hd_f) + 8)
/* register macros */
#define RK %r2
#define RA d0
#define RB d1
#define RC d2
#define RD d3
#define RE d4
#define RF d5
#define RG d6
#define RH d7
#define RT0 d8
#define RT1 d9
#define RT2 d10
#define RT3 d11
#define RT4 d12
#define RT5 d13
#define RT6 d14
#define RT7 d15
#define RT01q q4
#define RT23q q5
#define RT45q q6
#define RT67q q7
#define RW0 d16
#define RW1 d17
#define RW2 d18
#define RW3 d19
#define RW4 d20
#define RW5 d21
#define RW6 d22
#define RW7 d23
#define RW8 d24
#define RW9 d25
#define RW10 d26
#define RW11 d27
#define RW12 d28
#define RW13 d29
#define RW14 d30
#define RW15 d31
#define RW01q q8
#define RW23q q9
#define RW45q q10
#define RW67q q11
#define RW89q q12
#define RW1011q q13
#define RW1213q q14
#define RW1415q q15
/***********************************************************************
* ARM assembly implementation of sha512 transform
***********************************************************************/
#define rounds2_0_63(ra, rb, rc, rd, re, rf, rg, rh, rw0, rw1, rw01q, rw2, \
rw23q, rw1415q, rw9, rw10, interleave_op, arg1) \
/* t1 = h + Sum1 (e) + Ch (e, f, g) + k[t] + w[t]; */ \
vshr.u64 RT2, re, #14; \
vshl.u64 RT3, re, #64 - 14; \
interleave_op(arg1); \
vshr.u64 RT4, re, #18; \
vshl.u64 RT5, re, #64 - 18; \
vld1.64 {RT0}, [RK]!; \
veor.64 RT23q, RT23q, RT45q; \
vshr.u64 RT4, re, #41; \
vshl.u64 RT5, re, #64 - 41; \
vadd.u64 RT0, RT0, rw0; \
veor.64 RT23q, RT23q, RT45q; \
vmov.64 RT7, re; \
veor.64 RT1, RT2, RT3; \
vbsl.64 RT7, rf, rg; \
\
vadd.u64 RT1, RT1, rh; \
vshr.u64 RT2, ra, #28; \
vshl.u64 RT3, ra, #64 - 28; \
vadd.u64 RT1, RT1, RT0; \
vshr.u64 RT4, ra, #34; \
vshl.u64 RT5, ra, #64 - 34; \
vadd.u64 RT1, RT1, RT7; \
\
/* h = Sum0 (a) + Maj (a, b, c); */ \
veor.64 RT23q, RT23q, RT45q; \
vshr.u64 RT4, ra, #39; \
vshl.u64 RT5, ra, #64 - 39; \
veor.64 RT0, ra, rb; \
veor.64 RT23q, RT23q, RT45q; \
vbsl.64 RT0, rc, rb; \
vadd.u64 rd, rd, RT1; /* d+=t1; */ \
veor.64 rh, RT2, RT3; \
\
/* t1 = g + Sum1 (d) + Ch (d, e, f) + k[t] + w[t]; */ \
vshr.u64 RT2, rd, #14; \
vshl.u64 RT3, rd, #64 - 14; \
vadd.u64 rh, rh, RT0; \
vshr.u64 RT4, rd, #18; \
vshl.u64 RT5, rd, #64 - 18; \
vadd.u64 rh, rh, RT1; /* h+=t1; */ \
vld1.64 {RT0}, [RK]!; \
veor.64 RT23q, RT23q, RT45q; \
vshr.u64 RT4, rd, #41; \
vshl.u64 RT5, rd, #64 - 41; \
vadd.u64 RT0, RT0, rw1; \
veor.64 RT23q, RT23q, RT45q; \
vmov.64 RT7, rd; \
veor.64 RT1, RT2, RT3; \
vbsl.64 RT7, re, rf; \
\
vadd.u64 RT1, RT1, rg; \
vshr.u64 RT2, rh, #28; \
vshl.u64 RT3, rh, #64 - 28; \
vadd.u64 RT1, RT1, RT0; \
vshr.u64 RT4, rh, #34; \
vshl.u64 RT5, rh, #64 - 34; \
vadd.u64 RT1, RT1, RT7; \
\
/* g = Sum0 (h) + Maj (h, a, b); */ \
veor.64 RT23q, RT23q, RT45q; \
vshr.u64 RT4, rh, #39; \
vshl.u64 RT5, rh, #64 - 39; \
veor.64 RT0, rh, ra; \
veor.64 RT23q, RT23q, RT45q; \
vbsl.64 RT0, rb, ra; \
vadd.u64 rc, rc, RT1; /* c+=t1; */ \
veor.64 rg, RT2, RT3; \
\
/* w[0] += S1 (w[14]) + w[9] + S0 (w[1]); */ \
/* w[1] += S1 (w[15]) + w[10] + S0 (w[2]); */ \
\
/**** S0(w[1:2]) */ \
\
/* w[0:1] += w[9:10] */ \
/* RT23q = rw1:rw2 */ \
vext.u64 RT23q, rw01q, rw23q, #1; \
vadd.u64 rw0, rw9; \
vadd.u64 rg, rg, RT0; \
vadd.u64 rw1, rw10;\
vadd.u64 rg, rg, RT1; /* g+=t1; */ \
\
vshr.u64 RT45q, RT23q, #1; \
vshl.u64 RT67q, RT23q, #64 - 1; \
vshr.u64 RT01q, RT23q, #8; \
veor.u64 RT45q, RT45q, RT67q; \
vshl.u64 RT67q, RT23q, #64 - 8; \
veor.u64 RT45q, RT45q, RT01q; \
vshr.u64 RT01q, RT23q, #7; \
veor.u64 RT45q, RT45q, RT67q; \
\
/**** S1(w[14:15]) */ \
vshr.u64 RT23q, rw1415q, #6; \
veor.u64 RT01q, RT01q, RT45q; \
vshr.u64 RT45q, rw1415q, #19; \
vshl.u64 RT67q, rw1415q, #64 - 19; \
veor.u64 RT23q, RT23q, RT45q; \
vshr.u64 RT45q, rw1415q, #61; \
veor.u64 RT23q, RT23q, RT67q; \
vshl.u64 RT67q, rw1415q, #64 - 61; \
veor.u64 RT23q, RT23q, RT45q; \
vadd.u64 rw01q, RT01q; /* w[0:1] += S(w[1:2]) */ \
veor.u64 RT01q, RT23q, RT67q;
#define vadd_RT01q(rw01q) \
/* w[0:1] += S(w[14:15]) */ \
vadd.u64 rw01q, RT01q;
#define dummy(_) /*_*/
#define rounds2_64_79(ra, rb, rc, rd, re, rf, rg, rh, rw0, rw1, \
interleave_op1, arg1, interleave_op2, arg2) \
/* t1 = h + Sum1 (e) + Ch (e, f, g) + k[t] + w[t]; */ \
vshr.u64 RT2, re, #14; \
vshl.u64 RT3, re, #64 - 14; \
interleave_op1(arg1); \
vshr.u64 RT4, re, #18; \
vshl.u64 RT5, re, #64 - 18; \
interleave_op2(arg2); \
vld1.64 {RT0}, [RK]!; \
veor.64 RT23q, RT23q, RT45q; \
vshr.u64 RT4, re, #41; \
vshl.u64 RT5, re, #64 - 41; \
vadd.u64 RT0, RT0, rw0; \
veor.64 RT23q, RT23q, RT45q; \
vmov.64 RT7, re; \
veor.64 RT1, RT2, RT3; \
vbsl.64 RT7, rf, rg; \
\
vadd.u64 RT1, RT1, rh; \
vshr.u64 RT2, ra, #28; \
vshl.u64 RT3, ra, #64 - 28; \
vadd.u64 RT1, RT1, RT0; \
vshr.u64 RT4, ra, #34; \
vshl.u64 RT5, ra, #64 - 34; \
vadd.u64 RT1, RT1, RT7; \
\
/* h = Sum0 (a) + Maj (a, b, c); */ \
veor.64 RT23q, RT23q, RT45q; \
vshr.u64 RT4, ra, #39; \
vshl.u64 RT5, ra, #64 - 39; \
veor.64 RT0, ra, rb; \
veor.64 RT23q, RT23q, RT45q; \
vbsl.64 RT0, rc, rb; \
vadd.u64 rd, rd, RT1; /* d+=t1; */ \
veor.64 rh, RT2, RT3; \
\
/* t1 = g + Sum1 (d) + Ch (d, e, f) + k[t] + w[t]; */ \
vshr.u64 RT2, rd, #14; \
vshl.u64 RT3, rd, #64 - 14; \
vadd.u64 rh, rh, RT0; \
vshr.u64 RT4, rd, #18; \
vshl.u64 RT5, rd, #64 - 18; \
vadd.u64 rh, rh, RT1; /* h+=t1; */ \
vld1.64 {RT0}, [RK]!; \
veor.64 RT23q, RT23q, RT45q; \
vshr.u64 RT4, rd, #41; \
vshl.u64 RT5, rd, #64 - 41; \
vadd.u64 RT0, RT0, rw1; \
veor.64 RT23q, RT23q, RT45q; \
vmov.64 RT7, rd; \
veor.64 RT1, RT2, RT3; \
vbsl.64 RT7, re, rf; \
\
vadd.u64 RT1, RT1, rg; \
vshr.u64 RT2, rh, #28; \
vshl.u64 RT3, rh, #64 - 28; \
vadd.u64 RT1, RT1, RT0; \
vshr.u64 RT4, rh, #34; \
vshl.u64 RT5, rh, #64 - 34; \
vadd.u64 RT1, RT1, RT7; \
\
/* g = Sum0 (h) + Maj (h, a, b); */ \
veor.64 RT23q, RT23q, RT45q; \
vshr.u64 RT4, rh, #39; \
vshl.u64 RT5, rh, #64 - 39; \
veor.64 RT0, rh, ra; \
veor.64 RT23q, RT23q, RT45q; \
vbsl.64 RT0, rb, ra; \
vadd.u64 rc, rc, RT1; /* c+=t1; */ \
veor.64 rg, RT2, RT3;
#define vadd_rg_RT0(rg) \
vadd.u64 rg, rg, RT0;
#define vadd_rg_RT1(rg) \
vadd.u64 rg, rg, RT1; /* g+=t1; */
.align 3
ENTRY(sha512_transform_neon)
/* Input:
* %r0: SHA512_CONTEXT
* %r1: data
* %r2: u64 k[] constants
* %r3: nblks
*/
push {%lr};
mov %lr, #0;
/* Load context to d0-d7 */
vld1.64 {RA-RD}, [%r0]!;
vld1.64 {RE-RH}, [%r0];
sub %r0, #(4*8);
/* Load input to w[16], d16-d31 */
/* NOTE: Assumes that on ARMv7 unaligned accesses are always allowed. */
vld1.64 {RW0-RW3}, [%r1]!;
vld1.64 {RW4-RW7}, [%r1]!;
vld1.64 {RW8-RW11}, [%r1]!;
vld1.64 {RW12-RW15}, [%r1]!;
#ifdef __ARMEL__
/* byteswap */
vrev64.8 RW01q, RW01q;
vrev64.8 RW23q, RW23q;
vrev64.8 RW45q, RW45q;
vrev64.8 RW67q, RW67q;
vrev64.8 RW89q, RW89q;
vrev64.8 RW1011q, RW1011q;
vrev64.8 RW1213q, RW1213q;
vrev64.8 RW1415q, RW1415q;
#endif
/* EABI says that d8-d15 must be preserved by callee. */
/*vpush {RT0-RT7};*/
.Loop:
rounds2_0_63(RA, RB, RC, RD, RE, RF, RG, RH, RW0, RW1, RW01q, RW2,
RW23q, RW1415q, RW9, RW10, dummy, _);
b .Lenter_rounds;
.Loop_rounds:
rounds2_0_63(RA, RB, RC, RD, RE, RF, RG, RH, RW0, RW1, RW01q, RW2,
RW23q, RW1415q, RW9, RW10, vadd_RT01q, RW1415q);
.Lenter_rounds:
rounds2_0_63(RG, RH, RA, RB, RC, RD, RE, RF, RW2, RW3, RW23q, RW4,
RW45q, RW01q, RW11, RW12, vadd_RT01q, RW01q);
rounds2_0_63(RE, RF, RG, RH, RA, RB, RC, RD, RW4, RW5, RW45q, RW6,
RW67q, RW23q, RW13, RW14, vadd_RT01q, RW23q);
rounds2_0_63(RC, RD, RE, RF, RG, RH, RA, RB, RW6, RW7, RW67q, RW8,
RW89q, RW45q, RW15, RW0, vadd_RT01q, RW45q);
rounds2_0_63(RA, RB, RC, RD, RE, RF, RG, RH, RW8, RW9, RW89q, RW10,
RW1011q, RW67q, RW1, RW2, vadd_RT01q, RW67q);
rounds2_0_63(RG, RH, RA, RB, RC, RD, RE, RF, RW10, RW11, RW1011q, RW12,
RW1213q, RW89q, RW3, RW4, vadd_RT01q, RW89q);
add %lr, #16;
rounds2_0_63(RE, RF, RG, RH, RA, RB, RC, RD, RW12, RW13, RW1213q, RW14,
RW1415q, RW1011q, RW5, RW6, vadd_RT01q, RW1011q);
cmp %lr, #64;
rounds2_0_63(RC, RD, RE, RF, RG, RH, RA, RB, RW14, RW15, RW1415q, RW0,
RW01q, RW1213q, RW7, RW8, vadd_RT01q, RW1213q);
bne .Loop_rounds;
subs %r3, #1;
rounds2_64_79(RA, RB, RC, RD, RE, RF, RG, RH, RW0, RW1,
vadd_RT01q, RW1415q, dummy, _);
rounds2_64_79(RG, RH, RA, RB, RC, RD, RE, RF, RW2, RW3,
vadd_rg_RT0, RG, vadd_rg_RT1, RG);
beq .Lhandle_tail;
vld1.64 {RW0-RW3}, [%r1]!;
rounds2_64_79(RE, RF, RG, RH, RA, RB, RC, RD, RW4, RW5,
vadd_rg_RT0, RE, vadd_rg_RT1, RE);
rounds2_64_79(RC, RD, RE, RF, RG, RH, RA, RB, RW6, RW7,
vadd_rg_RT0, RC, vadd_rg_RT1, RC);
#ifdef __ARMEL__
vrev64.8 RW01q, RW01q;
vrev64.8 RW23q, RW23q;
#endif
vld1.64 {RW4-RW7}, [%r1]!;
rounds2_64_79(RA, RB, RC, RD, RE, RF, RG, RH, RW8, RW9,
vadd_rg_RT0, RA, vadd_rg_RT1, RA);
rounds2_64_79(RG, RH, RA, RB, RC, RD, RE, RF, RW10, RW11,
vadd_rg_RT0, RG, vadd_rg_RT1, RG);
#ifdef __ARMEL__
vrev64.8 RW45q, RW45q;
vrev64.8 RW67q, RW67q;
#endif
vld1.64 {RW8-RW11}, [%r1]!;
rounds2_64_79(RE, RF, RG, RH, RA, RB, RC, RD, RW12, RW13,
vadd_rg_RT0, RE, vadd_rg_RT1, RE);
rounds2_64_79(RC, RD, RE, RF, RG, RH, RA, RB, RW14, RW15,
vadd_rg_RT0, RC, vadd_rg_RT1, RC);
#ifdef __ARMEL__
vrev64.8 RW89q, RW89q;
vrev64.8 RW1011q, RW1011q;
#endif
vld1.64 {RW12-RW15}, [%r1]!;
vadd_rg_RT0(RA);
vadd_rg_RT1(RA);
/* Load context */
vld1.64 {RT0-RT3}, [%r0]!;
vld1.64 {RT4-RT7}, [%r0];
sub %r0, #(4*8);
#ifdef __ARMEL__
vrev64.8 RW1213q, RW1213q;
vrev64.8 RW1415q, RW1415q;
#endif
vadd.u64 RA, RT0;
vadd.u64 RB, RT1;
vadd.u64 RC, RT2;
vadd.u64 RD, RT3;
vadd.u64 RE, RT4;
vadd.u64 RF, RT5;
vadd.u64 RG, RT6;
vadd.u64 RH, RT7;
/* Store the first half of context */
vst1.64 {RA-RD}, [%r0]!;
sub RK, $(8*80);
vst1.64 {RE-RH}, [%r0]; /* Store the last half of context */
mov %lr, #0;
sub %r0, #(4*8);
b .Loop;
.Lhandle_tail:
rounds2_64_79(RE, RF, RG, RH, RA, RB, RC, RD, RW4, RW5,
vadd_rg_RT0, RE, vadd_rg_RT1, RE);
rounds2_64_79(RC, RD, RE, RF, RG, RH, RA, RB, RW6, RW7,
vadd_rg_RT0, RC, vadd_rg_RT1, RC);
rounds2_64_79(RA, RB, RC, RD, RE, RF, RG, RH, RW8, RW9,
vadd_rg_RT0, RA, vadd_rg_RT1, RA);
rounds2_64_79(RG, RH, RA, RB, RC, RD, RE, RF, RW10, RW11,
vadd_rg_RT0, RG, vadd_rg_RT1, RG);
rounds2_64_79(RE, RF, RG, RH, RA, RB, RC, RD, RW12, RW13,
vadd_rg_RT0, RE, vadd_rg_RT1, RE);
rounds2_64_79(RC, RD, RE, RF, RG, RH, RA, RB, RW14, RW15,
vadd_rg_RT0, RC, vadd_rg_RT1, RC);
/* Load context to d16-d23 */
vld1.64 {RW0-RW3}, [%r0]!;
vadd_rg_RT0(RA);
vld1.64 {RW4-RW7}, [%r0];
vadd_rg_RT1(RA);
sub %r0, #(4*8);
vadd.u64 RA, RW0;
vadd.u64 RB, RW1;
vadd.u64 RC, RW2;
vadd.u64 RD, RW3;
vadd.u64 RE, RW4;
vadd.u64 RF, RW5;
vadd.u64 RG, RW6;
vadd.u64 RH, RW7;
/* Store the first half of context */
vst1.64 {RA-RD}, [%r0]!;
/* Clear used registers */
/* d16-d31 */
veor.u64 RW01q, RW01q;
veor.u64 RW23q, RW23q;
veor.u64 RW45q, RW45q;
veor.u64 RW67q, RW67q;
vst1.64 {RE-RH}, [%r0]; /* Store the last half of context */
veor.u64 RW89q, RW89q;
veor.u64 RW1011q, RW1011q;
veor.u64 RW1213q, RW1213q;
veor.u64 RW1415q, RW1415q;
/* d8-d15 */
/*vpop {RT0-RT7};*/
/* d0-d7 (q0-q3) */
veor.u64 %q0, %q0;
veor.u64 %q1, %q1;
veor.u64 %q2, %q2;
veor.u64 %q3, %q3;
pop {%pc};
ENDPROC(sha512_transform_neon)

305
arch/arm/crypto/sha512_neon_glue.c 100644
View File

@ -0,0 +1,305 @@
/*
* Glue code for the SHA512 Secure Hash Algorithm assembly implementation
* using NEON instructions.
*
* Copyright © 2014 Jussi Kivilinna <jussi.kivilinna@iki.fi>
*
* This file is based on sha512_ssse3_glue.c:
* Copyright (C) 2013 Intel Corporation
* Author: Tim Chen <tim.c.chen@linux.intel.com>
*
* This program is free software; you can redistribute it and/or modify it
* under the terms of the GNU General Public License as published by the Free
* Software Foundation; either version 2 of the License, or (at your option)
* any later version.
*
*/
#include <crypto/internal/hash.h>
#include <linux/init.h>
#include <linux/module.h>
#include <linux/mm.h>
#include <linux/cryptohash.h>
#include <linux/types.h>
#include <linux/string.h>
#include <crypto/sha.h>
#include <asm/byteorder.h>
#include <asm/simd.h>
#include <asm/neon.h>
static const u64 sha512_k[] = {
0x428a2f98d728ae22ULL, 0x7137449123ef65cdULL,
0xb5c0fbcfec4d3b2fULL, 0xe9b5dba58189dbbcULL,
0x3956c25bf348b538ULL, 0x59f111f1b605d019ULL,
0x923f82a4af194f9bULL, 0xab1c5ed5da6d8118ULL,
0xd807aa98a3030242ULL, 0x12835b0145706fbeULL,
0x243185be4ee4b28cULL, 0x550c7dc3d5ffb4e2ULL,
0x72be5d74f27b896fULL, 0x80deb1fe3b1696b1ULL,
0x9bdc06a725c71235ULL, 0xc19bf174cf692694ULL,
0xe49b69c19ef14ad2ULL, 0xefbe4786384f25e3ULL,
0x0fc19dc68b8cd5b5ULL, 0x240ca1cc77ac9c65ULL,
0x2de92c6f592b0275ULL, 0x4a7484aa6ea6e483ULL,
0x5cb0a9dcbd41fbd4ULL, 0x76f988da831153b5ULL,
0x983e5152ee66dfabULL, 0xa831c66d2db43210ULL,
0xb00327c898fb213fULL, 0xbf597fc7beef0ee4ULL,
0xc6e00bf33da88fc2ULL, 0xd5a79147930aa725ULL,
0x06ca6351e003826fULL, 0x142929670a0e6e70ULL,
0x27b70a8546d22ffcULL, 0x2e1b21385c26c926ULL,
0x4d2c6dfc5ac42aedULL, 0x53380d139d95b3dfULL,
0x650a73548baf63deULL, 0x766a0abb3c77b2a8ULL,
0x81c2c92e47edaee6ULL, 0x92722c851482353bULL,
0xa2bfe8a14cf10364ULL, 0xa81a664bbc423001ULL,
0xc24b8b70d0f89791ULL, 0xc76c51a30654be30ULL,
0xd192e819d6ef5218ULL, 0xd69906245565a910ULL,
0xf40e35855771202aULL, 0x106aa07032bbd1b8ULL,
0x19a4c116b8d2d0c8ULL, 0x1e376c085141ab53ULL,
0x2748774cdf8eeb99ULL, 0x34b0bcb5e19b48a8ULL,
0x391c0cb3c5c95a63ULL, 0x4ed8aa4ae3418acbULL,
0x5b9cca4f7763e373ULL, 0x682e6ff3d6b2b8a3ULL,
0x748f82ee5defb2fcULL, 0x78a5636f43172f60ULL,
0x84c87814a1f0ab72ULL, 0x8cc702081a6439ecULL,
0x90befffa23631e28ULL, 0xa4506cebde82bde9ULL,
0xbef9a3f7b2c67915ULL, 0xc67178f2e372532bULL,
0xca273eceea26619cULL, 0xd186b8c721c0c207ULL,
0xeada7dd6cde0eb1eULL, 0xf57d4f7fee6ed178ULL,
0x06f067aa72176fbaULL, 0x0a637dc5a2c898a6ULL,
0x113f9804bef90daeULL, 0x1b710b35131c471bULL,
0x28db77f523047d84ULL, 0x32caab7b40c72493ULL,
0x3c9ebe0a15c9bebcULL, 0x431d67c49c100d4cULL,
0x4cc5d4becb3e42b6ULL, 0x597f299cfc657e2aULL,
0x5fcb6fab3ad6faecULL, 0x6c44198c4a475817ULL
};
asmlinkage void sha512_transform_neon(u64 *digest, const void *data,
const u64 k[], unsigned int num_blks);
static int sha512_neon_init(struct shash_desc *desc)
{
struct sha512_state *sctx = shash_desc_ctx(desc);
sctx->state[0] = SHA512_H0;
sctx->state[1] = SHA512_H1;
sctx->state[2] = SHA512_H2;
sctx->state[3] = SHA512_H3;
sctx->state[4] = SHA512_H4;
sctx->state[5] = SHA512_H5;
sctx->state[6] = SHA512_H6;
sctx->state[7] = SHA512_H7;
sctx->count[0] = sctx->count[1] = 0;
return 0;
}
static int __sha512_neon_update(struct shash_desc *desc, const u8 *data,
unsigned int len, unsigned int partial)
{
struct sha512_state *sctx = shash_desc_ctx(desc);
unsigned int done = 0;
sctx->count[0] += len;
if (sctx->count[0] < len)
sctx->count[1]++;
if (partial) {
done = SHA512_BLOCK_SIZE - partial;
memcpy(sctx->buf + partial, data, done);
sha512_transform_neon(sctx->state, sctx->buf, sha512_k, 1);
}
if (len - done >= SHA512_BLOCK_SIZE) {
const unsigned int rounds = (len - done) / SHA512_BLOCK_SIZE;
sha512_transform_neon(sctx->state, data + done, sha512_k,
rounds);
done += rounds * SHA512_BLOCK_SIZE;
}
memcpy(sctx->buf, data + done, len - done);
return 0;
}
static int sha512_neon_update(struct shash_desc *desc, const u8 *data,
unsigned int len)
{
struct sha512_state *sctx = shash_desc_ctx(desc);
unsigned int partial = sctx->count[0] % SHA512_BLOCK_SIZE;
int res;
/* Handle the fast case right here */
if (partial + len < SHA512_BLOCK_SIZE) {
sctx->count[0] += len;
if (sctx->count[0] < len)
sctx->count[1]++;
memcpy(sctx->buf + partial, data, len);
return 0;
}
if (!may_use_simd()) {
res = crypto_sha512_update(desc, data, len);
} else {
kernel_neon_begin();
res = __sha512_neon_update(desc, data, len, partial);
kernel_neon_end();
}
return res;
}
/* Add padding and return the message digest. */
static int sha512_neon_final(struct shash_desc *desc, u8 *out)
{
struct sha512_state *sctx = shash_desc_ctx(desc);
unsigned int i, index, padlen;
__be64 *dst = (__be64 *)out;
__be64 bits[2];
static const u8 padding[SHA512_BLOCK_SIZE] = { 0x80, };
/* save number of bits */
bits[1] = cpu_to_be64(sctx->count[0] << 3);
bits[0] = cpu_to_be64(sctx->count[1] << 3 | sctx->count[0] >> 61);
/* Pad out to 112 mod 128 and append length */
index = sctx->count[0] & 0x7f;
padlen = (index < 112) ? (112 - index) : ((128+112) - index);
if (!may_use_simd()) {
crypto_sha512_update(desc, padding, padlen);
crypto_sha512_update(desc, (const u8 *)&bits, sizeof(bits));
} else {
kernel_neon_begin();
/* We need to fill a whole block for __sha512_neon_update() */
if (padlen <= 112) {
sctx->count[0] += padlen;
if (sctx->count[0] < padlen)
sctx->count[1]++;
memcpy(sctx->buf + index, padding, padlen);
} else {
__sha512_neon_update(desc, padding, padlen, index);
}
__sha512_neon_update(desc, (const u8 *)&bits,
sizeof(bits), 112);
kernel_neon_end();
}
/* Store state in digest */
for (i = 0; i < 8; i++)
dst[i] = cpu_to_be64(sctx->state[i]);
/* Wipe context */
memset(sctx, 0, sizeof(*sctx));
return 0;
}
static int sha512_neon_export(struct shash_desc *desc, void *out)
{
struct sha512_state *sctx = shash_desc_ctx(desc);
memcpy(out, sctx, sizeof(*sctx));
return 0;
}
static int sha512_neon_import(struct shash_desc *desc, const void *in)
{
struct sha512_state *sctx = shash_desc_ctx(desc);
memcpy(sctx, in, sizeof(*sctx));
return 0;
}
static int sha384_neon_init(struct shash_desc *desc)
{
struct sha512_state *sctx = shash_desc_ctx(desc);
sctx->state[0] = SHA384_H0;
sctx->state[1] = SHA384_H1;
sctx->state[2] = SHA384_H2;
sctx->state[3] = SHA384_H3;
sctx->state[4] = SHA384_H4;
sctx->state[5] = SHA384_H5;
sctx->state[6] = SHA384_H6;
sctx->state[7] = SHA384_H7;
sctx->count[0] = sctx->count[1] = 0;
return 0;
}
static int sha384_neon_final(struct shash_desc *desc, u8 *hash)
{
u8 D[SHA512_DIGEST_SIZE];
sha512_neon_final(desc, D);
memcpy(hash, D, SHA384_DIGEST_SIZE);
memset(D, 0, SHA512_DIGEST_SIZE);
return 0;
}
static struct shash_alg algs[] = { {
.digestsize = SHA512_DIGEST_SIZE,
.init = sha512_neon_init,
.update = sha512_neon_update,
.final = sha512_neon_final,
.export = sha512_neon_export,
.import = sha512_neon_import,
.descsize = sizeof(struct sha512_state),
.statesize = sizeof(struct sha512_state),
.base = {
.cra_name = "sha512",
.cra_driver_name = "sha512-neon",
.cra_priority = 250,
.cra_flags = CRYPTO_ALG_TYPE_SHASH,
.cra_blocksize = SHA512_BLOCK_SIZE,
.cra_module = THIS_MODULE,
}
}, {
.digestsize = SHA384_DIGEST_SIZE,
.init = sha384_neon_init,
.update = sha512_neon_update,
.final = sha384_neon_final,
.export = sha512_neon_export,
.import = sha512_neon_import,
.descsize = sizeof(struct sha512_state),
.statesize = sizeof(struct sha512_state),
.base = {
.cra_name = "sha384",
.cra_driver_name = "sha384-neon",
.cra_priority = 250,
.cra_flags = CRYPTO_ALG_TYPE_SHASH,
.cra_blocksize = SHA384_BLOCK_SIZE,
.cra_module = THIS_MODULE,
}
} };
static int __init sha512_neon_mod_init(void)
{
if (!cpu_has_neon())
return -ENODEV;
return crypto_register_shashes(algs, ARRAY_SIZE(algs));
}
static void __exit sha512_neon_mod_fini(void)
{
crypto_unregister_shashes(algs, ARRAY_SIZE(algs));
}
module_init(sha512_neon_mod_init);
module_exit(sha512_neon_mod_fini);
MODULE_LICENSE("GPL");
MODULE_DESCRIPTION("SHA512 Secure Hash Algorithm, NEON accelerated");
MODULE_ALIAS("sha512");
MODULE_ALIAS("sha384");

29
arch/arm/include/asm/assembler.h
View File

@ -24,6 +24,8 @@
#include <asm/domain.h>
#include <asm/opcodes-virt.h>
#include <asm/asm-offsets.h>
#include <asm/page.h>
#include <asm/thread_info.h>
#define IOMEM(x) (x)
@ -179,10 +181,10 @@
* Get current thread_info.
*/
.macro get_thread_info, rd
ARM( mov \rd, sp, lsr #13 )
ARM( mov \rd, sp, lsr #THREAD_SIZE_ORDER + PAGE_SHIFT )
THUMB( mov \rd, sp )
THUMB( lsr \rd, \rd, #13 )
mov \rd, \rd, lsl #13
THUMB( lsr \rd, \rd, #THREAD_SIZE_ORDER + PAGE_SHIFT )
mov \rd, \rd, lsl #THREAD_SIZE_ORDER + PAGE_SHIFT
.endm
/*
@ -425,4 +427,25 @@ THUMB( orr \reg , \reg , #PSR_T_BIT )
#endif
.endm
.irp c,,eq,ne,cs,cc,mi,pl,vs,vc,hi,ls,ge,lt,gt,le,hs,lo
.macro ret\c, reg
#if __LINUX_ARM_ARCH__ < 6
mov\c pc, \reg
#else
.ifeqs "\reg", "lr"
bx\c \reg
.else
mov\c pc, \reg
.endif
#endif
.endm
.endr
.macro ret.w, reg
ret \reg
#ifdef CONFIG_THUMB2_KERNEL
nop
#endif
.endm
#endif /* __ASM_ASSEMBLER_H__ */

37
arch/arm/include/asm/cputype.h
View File

@ -62,17 +62,18 @@
#define ARM_CPU_IMP_ARM 0x41
#define ARM_CPU_IMP_INTEL 0x69
#define ARM_CPU_PART_ARM1136 0xB360
#define ARM_CPU_PART_ARM1156 0xB560
#define ARM_CPU_PART_ARM1176 0xB760
#define ARM_CPU_PART_ARM11MPCORE 0xB020
#define ARM_CPU_PART_CORTEX_A8 0xC080
#define ARM_CPU_PART_CORTEX_A9 0xC090
#define ARM_CPU_PART_CORTEX_A5 0xC050
#define ARM_CPU_PART_CORTEX_A15 0xC0F0
#define ARM_CPU_PART_CORTEX_A7 0xC070
#define ARM_CPU_PART_CORTEX_A12 0xC0D0
#define ARM_CPU_PART_CORTEX_A17 0xC0E0
/* ARM implemented processors */
#define ARM_CPU_PART_ARM1136 0x4100b360
#define ARM_CPU_PART_ARM1156 0x4100b560
#define ARM_CPU_PART_ARM1176 0x4100b760
#define ARM_CPU_PART_ARM11MPCORE 0x4100b020
#define ARM_CPU_PART_CORTEX_A8 0x4100c080
#define ARM_CPU_PART_CORTEX_A9 0x4100c090
#define ARM_CPU_PART_CORTEX_A5 0x4100c050
#define ARM_CPU_PART_CORTEX_A7 0x4100c070
#define ARM_CPU_PART_CORTEX_A12 0x4100c0d0
#define ARM_CPU_PART_CORTEX_A17 0x4100c0e0
#define ARM_CPU_PART_CORTEX_A15 0x4100c0f0
#define ARM_CPU_XSCALE_ARCH_MASK 0xe000
#define ARM_CPU_XSCALE_ARCH_V1 0x2000
@ -171,14 +172,24 @@ static inline unsigned int __attribute_const__ read_cpuid_implementor(void)
return (read_cpuid_id() & 0xFF000000) >> 24;
}
static inline unsigned int __attribute_const__ read_cpuid_part_number(void)
/*
* The CPU part number is meaningless without referring to the CPU
* implementer: implementers are free to define their own part numbers
* which are permitted to clash with other implementer part numbers.
*/
static inline unsigned int __attribute_const__ read_cpuid_part(void)
{
return read_cpuid_id() & 0xff00fff0;
}
static inline unsigned int __attribute_const__ __deprecated read_cpuid_part_number(void)
{
return read_cpuid_id() & 0xFFF0;
}
static inline unsigned int __attribute_const__ xscale_cpu_arch_version(void)
{
return read_cpuid_part_number() & ARM_CPU_XSCALE_ARCH_MASK;
return read_cpuid_id() & ARM_CPU_XSCALE_ARCH_MASK;
}
static inline unsigned int __attribute_const__ read_cpuid_cachetype(void)

10
arch/arm/include/asm/crypto/sha1.h 100644
View File

@ -0,0 +1,10 @@
#ifndef ASM_ARM_CRYPTO_SHA1_H
#define ASM_ARM_CRYPTO_SHA1_H
#include <linux/crypto.h>
#include <crypto/sha.h>
extern int sha1_update_arm(struct shash_desc *desc, const u8 *data,
unsigned int len);
#endif

2
arch/arm/include/asm/entry-macro-multi.S
View File

@ -35,5 +35,5 @@
\symbol_name:
mov r8, lr
arch_irq_handler_default
mov pc, r8
ret r8
.endm

18
arch/arm/include/asm/glue-proc.h
View File

@ -221,15 +221,6 @@
# endif
#endif
#ifdef CONFIG_CPU_V7
# ifdef CPU_NAME
# undef MULTI_CPU
# define MULTI_CPU
# else
# define CPU_NAME cpu_v7
# endif
#endif
#ifdef CONFIG_CPU_V7M
# ifdef CPU_NAME
# undef MULTI_CPU
@ -248,6 +239,15 @@
# endif
#endif
#ifdef CONFIG_CPU_V7
/*
* Cortex-A9 needs a different suspend/resume function, so we need
* multiple CPU support for ARMv7 anyway.
*/
# undef MULTI_CPU
# define MULTI_CPU
#endif
#ifndef MULTI_CPU
#define cpu_proc_init __glue(CPU_NAME,_proc_init)
#define cpu_proc_fin __glue(CPU_NAME,_proc_fin)

16
arch/arm/include/asm/mcpm.h
View File

@ -217,6 +217,22 @@ int __mcpm_cluster_state(unsigned int cluster);
int __init mcpm_sync_init(
void (*power_up_setup)(unsigned int affinity_level));
/**
* mcpm_loopback - make a run through the MCPM low-level code
*
* @cache_disable: pointer to function performing cache disabling
*
* This exercises the MCPM machinery by soft resetting the CPU and branching
* to the MCPM low-level entry code before returning to the caller.
* The @cache_disable function must do the necessary cache disabling to
* let the regular kernel init code turn it back on as if the CPU was
* hotplugged in. The MCPM state machine is set as if the cluster was
* initialized meaning the power_up_setup callback passed to mcpm_sync_init()
* will be invoked for all affinity levels. This may be useful to initialize
* some resources such as enabling the CCI that requires the cache to be off, or simply for testing purposes.
*/
int __init mcpm_loopback(void (*cache_disable)(void));
void __init mcpm_smp_set_ops(void);
#else

23
arch/arm/include/asm/mcs_spinlock.h 100644
View File

@ -0,0 +1,23 @@
#ifndef __ASM_MCS_LOCK_H
#define __ASM_MCS_LOCK_H
#ifdef CONFIG_SMP
#include <asm/spinlock.h>
/* MCS spin-locking. */
#define arch_mcs_spin_lock_contended(lock) \
do { \
/* Ensure prior stores are observed before we enter wfe. */ \
smp_mb(); \
while (!(smp_load_acquire(lock))) \
wfe(); \
} while (0) \
#define arch_mcs_spin_unlock_contended(lock) \
do { \
smp_store_release(lock, 1); \
dsb_sev(); \
} while (0)
#endif /* CONFIG_SMP */
#endif /* __ASM_MCS_LOCK_H */

6
arch/arm/include/asm/memory.h
View File

@ -150,13 +150,11 @@
/*
* PLAT_PHYS_OFFSET is the offset (from zero) of the start of physical
* memory. This is used for XIP and NoMMU kernels, or by kernels which
* have their own mach/memory.h. Assembly code must always use
* memory. This is used for XIP and NoMMU kernels, and on platforms that don't
* have CONFIG_ARM_PATCH_PHYS_VIRT. Assembly code must always use
* PLAT_PHYS_OFFSET and not PHYS_OFFSET.
*/
#ifndef PLAT_PHYS_OFFSET
#define PLAT_PHYS_OFFSET UL(CONFIG_PHYS_OFFSET)
#endif
#ifndef __ASSEMBLY__

3
arch/arm/include/asm/pgtable-3level-hwdef.h
View File

@ -43,7 +43,7 @@
#define PMD_SECT_BUFFERABLE (_AT(pmdval_t, 1) << 2)
#define PMD_SECT_CACHEABLE (_AT(pmdval_t, 1) << 3)
#define PMD_SECT_USER (_AT(pmdval_t, 1) << 6) /* AP[1] */
#define PMD_SECT_RDONLY (_AT(pmdval_t, 1) << 7) /* AP[2] */
#define PMD_SECT_AP2 (_AT(pmdval_t, 1) << 7) /* read only */
#define PMD_SECT_S (_AT(pmdval_t, 3) << 8)
#define PMD_SECT_AF (_AT(pmdval_t, 1) << 10)
#define PMD_SECT_nG (_AT(pmdval_t, 1) << 11)
@ -72,6 +72,7 @@
#define PTE_TABLE_BIT (_AT(pteval_t, 1) << 1)
#define PTE_BUFFERABLE (_AT(pteval_t, 1) << 2) /* AttrIndx[0] */
#define PTE_CACHEABLE (_AT(pteval_t, 1) << 3) /* AttrIndx[1] */
#define PTE_AP2 (_AT(pteval_t, 1) << 7) /* AP[2] */
#define PTE_EXT_SHARED (_AT(pteval_t, 3) << 8) /* SH[1:0], inner shareable */
#define PTE_EXT_AF (_AT(pteval_t, 1) << 10) /* Access Flag */
#define PTE_EXT_NG (_AT(pteval_t, 1) << 11) /* nG */

49
arch/arm/include/asm/pgtable-3level.h
View File

@ -79,18 +79,19 @@
#define L_PTE_PRESENT (_AT(pteval_t, 3) << 0) /* Present */
#define L_PTE_FILE (_AT(pteval_t, 1) << 2) /* only when !PRESENT */
#define L_PTE_USER (_AT(pteval_t, 1) << 6) /* AP[1] */
#define L_PTE_RDONLY (_AT(pteval_t, 1) << 7) /* AP[2] */
#define L_PTE_SHARED (_AT(pteval_t, 3) << 8) /* SH[1:0], inner shareable */
#define L_PTE_YOUNG (_AT(pteval_t, 1) << 10) /* AF */
#define L_PTE_XN (_AT(pteval_t, 1) << 54) /* XN */
#define L_PTE_DIRTY (_AT(pteval_t, 1) << 55) /* unused */
#define L_PTE_SPECIAL (_AT(pteval_t, 1) << 56) /* unused */
#define L_PTE_DIRTY (_AT(pteval_t, 1) << 55)
#define L_PTE_SPECIAL (_AT(pteval_t, 1) << 56)
#define L_PTE_NONE (_AT(pteval_t, 1) << 57) /* PROT_NONE */
#define L_PTE_RDONLY (_AT(pteval_t, 1) << 58) /* READ ONLY */
#define PMD_SECT_VALID (_AT(pmdval_t, 1) << 0)
#define PMD_SECT_DIRTY (_AT(pmdval_t, 1) << 55)
#define PMD_SECT_SPLITTING (_AT(pmdval_t, 1) << 56)
#define PMD_SECT_NONE (_AT(pmdval_t, 1) << 57)
#define L_PMD_SECT_VALID (_AT(pmdval_t, 1) << 0)
#define L_PMD_SECT_DIRTY (_AT(pmdval_t, 1) << 55)
#define L_PMD_SECT_SPLITTING (_AT(pmdval_t, 1) << 56)
#define L_PMD_SECT_NONE (_AT(pmdval_t, 1) << 57)
#define L_PMD_SECT_RDONLY (_AT(pteval_t, 1) << 58)
/*
* To be used in assembly code with the upper page attributes.
@ -207,27 +208,32 @@ static inline pmd_t *pmd_offset(pud_t *pud, unsigned long addr)
#define pte_huge(pte) (pte_val(pte) && !(pte_val(pte) & PTE_TABLE_BIT))
#define pte_mkhuge(pte) (__pte(pte_val(pte) & ~PTE_TABLE_BIT))
#define pmd_young(pmd) (pmd_val(pmd) & PMD_SECT_AF)
#define pmd_isset(pmd, val) ((u32)(val) == (val) ? pmd_val(pmd) & (val) \
: !!(pmd_val(pmd) & (val)))
#define pmd_isclear(pmd, val) (!(pmd_val(pmd) & (val)))
#define pmd_young(pmd) (pmd_isset((pmd), PMD_SECT_AF))
#define __HAVE_ARCH_PMD_WRITE
#define pmd_write(pmd) (!(pmd_val(pmd) & PMD_SECT_RDONLY))
#define pmd_write(pmd) (pmd_isclear((pmd), L_PMD_SECT_RDONLY))
#define pmd_dirty(pmd) (pmd_isset((pmd), L_PMD_SECT_DIRTY))
#define pmd_hugewillfault(pmd) (!pmd_young(pmd) || !pmd_write(pmd))
#define pmd_thp_or_huge(pmd) (pmd_huge(pmd) || pmd_trans_huge(pmd))
#ifdef CONFIG_TRANSPARENT_HUGEPAGE
#define pmd_trans_huge(pmd) (pmd_val(pmd) && !(pmd_val(pmd) & PMD_TABLE_BIT))
#define pmd_trans_splitting(pmd) (pmd_val(pmd) & PMD_SECT_SPLITTING)
#define pmd_trans_huge(pmd) (pmd_val(pmd) && !pmd_table(pmd))
#define pmd_trans_splitting(pmd) (pmd_isset((pmd), L_PMD_SECT_SPLITTING))
#endif
#define PMD_BIT_FUNC(fn,op) \
static inline pmd_t pmd_##fn(pmd_t pmd) { pmd_val(pmd) op; return pmd; }
PMD_BIT_FUNC(wrprotect, |= PMD_SECT_RDONLY);
PMD_BIT_FUNC(wrprotect, |= L_PMD_SECT_RDONLY);
PMD_BIT_FUNC(mkold, &= ~PMD_SECT_AF);
PMD_BIT_FUNC(mksplitting, |= PMD_SECT_SPLITTING);
PMD_BIT_FUNC(mkwrite, &= ~PMD_SECT_RDONLY);
PMD_BIT_FUNC(mkdirty, |= PMD_SECT_DIRTY);
PMD_BIT_FUNC(mksplitting, |= L_PMD_SECT_SPLITTING);
PMD_BIT_FUNC(mkwrite, &= ~L_PMD_SECT_RDONLY);
PMD_BIT_FUNC(mkdirty, |= L_PMD_SECT_DIRTY);
PMD_BIT_FUNC(mkyoung, |= PMD_SECT_AF);
#define pmd_mkhuge(pmd) (__pmd(pmd_val(pmd) & ~PMD_TABLE_BIT))
@ -241,8 +247,8 @@ PMD_BIT_FUNC(mkyoung, |= PMD_SECT_AF);
static inline pmd_t pmd_modify(pmd_t pmd, pgprot_t newprot)
{
const pmdval_t mask = PMD_SECT_USER | PMD_SECT_XN | PMD_SECT_RDONLY |
PMD_SECT_VALID | PMD_SECT_NONE;
const pmdval_t mask = PMD_SECT_USER | PMD_SECT_XN | L_PMD_SECT_RDONLY |
L_PMD_SECT_VALID | L_PMD_SECT_NONE;
pmd_val(pmd) = (pmd_val(pmd) & ~mask) | (pgprot_val(newprot) & mask);
return pmd;
}
@ -253,8 +259,13 @@ static inline void set_pmd_at(struct mm_struct *mm, unsigned long addr,
BUG_ON(addr >= TASK_SIZE);
/* create a faulting entry if PROT_NONE protected */
if (pmd_val(pmd) & PMD_SECT_NONE)
pmd_val(pmd) &= ~PMD_SECT_VALID;
if (pmd_val(pmd) & L_PMD_SECT_NONE)
pmd_val(pmd) &= ~L_PMD_SECT_VALID;
if (pmd_write(pmd) && pmd_dirty(pmd))
pmd_val(pmd) &= ~PMD_SECT_AP2;
else
pmd_val(pmd) |= PMD_SECT_AP2;
*pmdp = __pmd(pmd_val(pmd) | PMD_SECT_nG);
flush_pmd_entry(pmdp);

18
arch/arm/include/asm/pgtable.h
View File

@ -214,18 +214,22 @@ static inline pte_t *pmd_page_vaddr(pmd_t pmd)
#define pte_clear(mm,addr,ptep) set_pte_ext(ptep, __pte(0), 0)
#define pte_isset(pte, val) ((u32)(val) == (val) ? pte_val(pte) & (val) \
: !!(pte_val(pte) & (val)))
#define pte_isclear(pte, val) (!(pte_val(pte) & (val)))
#define pte_none(pte) (!pte_val(pte))
#define pte_present(pte) (pte_val(pte) & L_PTE_PRESENT)
#define pte_valid(pte) (pte_val(pte) & L_PTE_VALID)
#define pte_present(pte) (pte_isset((pte), L_PTE_PRESENT))
#define pte_valid(pte) (pte_isset((pte), L_PTE_VALID))
#define pte_accessible(mm, pte) (mm_tlb_flush_pending(mm) ? pte_present(pte) : pte_valid(pte))
#define pte_write(pte) (!(pte_val(pte) & L_PTE_RDONLY))
#define pte_dirty(pte) (pte_val(pte) & L_PTE_DIRTY)
#define pte_young(pte) (pte_val(pte) & L_PTE_YOUNG)
#define pte_exec(pte) (!(pte_val(pte) & L_PTE_XN))
#define pte_write(pte) (pte_isclear((pte), L_PTE_RDONLY))
#define pte_dirty(pte) (pte_isset((pte), L_PTE_DIRTY))
#define pte_young(pte) (pte_isset((pte), L_PTE_YOUNG))
#define pte_exec(pte) (pte_isclear((pte), L_PTE_XN))
#define pte_special(pte) (0)
#define pte_valid_user(pte) \
(pte_valid(pte) && (pte_val(pte) & L_PTE_USER) && pte_young(pte))
(pte_valid(pte) && pte_isset((pte), L_PTE_USER) && pte_young(pte))
#if __LINUX_ARM_ARCH__ < 6
static inline void __sync_icache_dcache(pte_t pteval)

6
arch/arm/include/asm/ptrace.h
View File

@ -84,6 +84,12 @@ static inline long regs_return_value(struct pt_regs *regs)
#define instruction_pointer(regs) (regs)->ARM_pc
#ifdef CONFIG_THUMB2_KERNEL
#define frame_pointer(regs) (regs)->ARM_r7
#else
#define frame_pointer(regs) (regs)->ARM_fp
#endif
static inline void instruction_pointer_set(struct pt_regs *regs,
unsigned long val)
{

2
arch/arm/include/asm/smp_scu.h
View File

@ -11,7 +11,7 @@
static inline bool scu_a9_has_base(void)
{
return read_cpuid_part_number() == ARM_CPU_PART_CORTEX_A9;
return read_cpuid_part() == ARM_CPU_PART_CORTEX_A9;
}
static inline unsigned long scu_a9_get_base(void)

15
arch/arm/include/asm/stacktrace.h
View File

@ -1,13 +1,28 @@
#ifndef __ASM_STACKTRACE_H
#define __ASM_STACKTRACE_H
#include <asm/ptrace.h>
struct stackframe {
/*
* FP member should hold R7 when CONFIG_THUMB2_KERNEL is enabled
* and R11 otherwise.
*/
unsigned long fp;
unsigned long sp;
unsigned long lr;
unsigned long pc;
};
static __always_inline
void arm_get_current_stackframe(struct pt_regs *regs, struct stackframe *frame)
{
frame->fp = frame_pointer(regs);
frame->sp = regs->ARM_sp;
frame->lr = regs->ARM_lr;
frame->pc = regs->ARM_pc;
}
extern int unwind_frame(struct stackframe *frame);
extern void walk_stackframe(struct stackframe *frame,
int (*fn)(struct stackframe *, void *), void *data);

3
arch/arm/include/asm/thread_info.h
View File

@ -14,9 +14,10 @@
#include <linux/compiler.h>
#include <asm/fpstate.h>
#include <asm/page.h>
#define THREAD_SIZE_ORDER 1
#define THREAD_SIZE 8192
#define THREAD_SIZE (PAGE_SIZE << THREAD_SIZE_ORDER)
#define THREAD_START_SP (THREAD_SIZE - 8)
#ifndef __ASSEMBLY__

20
arch/arm/include/asm/uaccess.h
View File

@ -107,6 +107,8 @@ static inline void set_fs(mm_segment_t fs)
extern int __get_user_1(void *);
extern int __get_user_2(void *);
extern int __get_user_4(void *);
extern int __get_user_lo8(void *);
extern int __get_user_8(void *);
#define __GUP_CLOBBER_1 "lr", "cc"
#ifdef CONFIG_CPU_USE_DOMAINS
@ -115,6 +117,8 @@ extern int __get_user_4(void *);
#define __GUP_CLOBBER_2 "lr", "cc"
#endif
#define __GUP_CLOBBER_4 "lr", "cc"
#define __GUP_CLOBBER_lo8 "lr", "cc"
#define __GUP_CLOBBER_8 "lr", "cc"
#define __get_user_x(__r2,__p,__e,__l,__s) \
__asm__ __volatile__ ( \
@ -125,11 +129,19 @@ extern int __get_user_4(void *);
: "0" (__p), "r" (__l) \
: __GUP_CLOBBER_##__s)
/* narrowing a double-word get into a single 32bit word register: */
#ifdef __ARMEB__
#define __get_user_xb(__r2, __p, __e, __l, __s) \
__get_user_x(__r2, __p, __e, __l, lo8)
#else
#define __get_user_xb __get_user_x
#endif
#define __get_user_check(x,p) \
({ \
unsigned long __limit = current_thread_info()->addr_limit - 1; \
register const typeof(*(p)) __user *__p asm("r0") = (p);\
register unsigned long __r2 asm("r2"); \
register typeof(x) __r2 asm("r2"); \
register unsigned long __l asm("r1") = __limit; \
register int __e asm("r0"); \
switch (sizeof(*(__p))) { \
@ -142,6 +154,12 @@ extern int __get_user_4(void *);
case 4: \
__get_user_x(__r2, __p, __e, __l, 4); \
break; \
case 8: \
if (sizeof((x)) < 8) \
__get_user_xb(__r2, __p, __e, __l, 4); \
else \
__get_user_x(__r2, __p, __e, __l, 8); \
break; \
default: __e = __get_user_bad(); break; \
} \
x = (typeof(*(p))) __r2; \

10
arch/arm/include/asm/unistd.h
View File

@ -15,7 +15,17 @@
#include <uapi/asm/unistd.h>
/*
* This may need to be greater than __NR_last_syscall+1 in order to
* account for the padding in the syscall table
*/
#define __NR_syscalls (384)
/*
* *NOTE*: This is a ghost syscall private to the kernel. Only the
* __kuser_cmpxchg code in entry-armv.S should be aware of its
* existence. Don't ever use this from user code.
*/
#define __ARM_NR_cmpxchg (__ARM_NR_BASE+0x00fff0)
#define __ARCH_WANT_STAT64

11
arch/arm/include/uapi/asm/unistd.h
View File

@ -410,11 +410,6 @@
#define __NR_sched_getattr (__NR_SYSCALL_BASE+381)
#define __NR_renameat2 (__NR_SYSCALL_BASE+382)
/*
* This may need to be greater than __NR_last_syscall+1 in order to
* account for the padding in the syscall table
*/
/*
* The following SWIs are ARM private.
*/
@ -425,12 +420,6 @@
#define __ARM_NR_usr32 (__ARM_NR_BASE+4)
#define __ARM_NR_set_tls (__ARM_NR_BASE+5)
/*
* *NOTE*: This is a ghost syscall private to the kernel. Only the
* __kuser_cmpxchg code in entry-armv.S should be aware of its
* existence. Don't ever use this from user code.
*/
/*
* The following syscalls are obsolete and no longer available for EABI.
*/

10
arch/arm/kernel/debug.S
View File

@ -90,7 +90,7 @@ ENTRY(printascii)
ldrneb r1, [r0], #1
teqne r1, #0
bne 1b
mov pc, lr
ret lr
ENDPROC(printascii)
ENTRY(printch)
@ -105,7 +105,7 @@ ENTRY(debug_ll_addr)
addruart r2, r3, ip
str r2, [r0]
str r3, [r1]
mov pc, lr
ret lr
ENDPROC(debug_ll_addr)
#endif
@ -116,7 +116,7 @@ ENTRY(printascii)
mov r0, #0x04 @ SYS_WRITE0
ARM( svc #0x123456 )
THUMB( svc #0xab )
mov pc, lr
ret lr
ENDPROC(printascii)
ENTRY(printch)
@ -125,14 +125,14 @@ ENTRY(printch)
mov r0, #0x03 @ SYS_WRITEC
ARM( svc #0x123456 )
THUMB( svc #0xab )
mov pc, lr
ret lr
ENDPROC(printch)
ENTRY(debug_ll_addr)
mov r2, #0
str r2, [r0]
str r2, [r1]
mov pc, lr
ret lr
ENDPROC(debug_ll_addr)
#endif

42
arch/arm/kernel/entry-armv.S
View File

@ -224,7 +224,7 @@ svc_preempt:
1: bl preempt_schedule_irq @ irq en/disable is done inside
ldr r0, [tsk, #TI_FLAGS] @ get new tasks TI_FLAGS
tst r0, #_TIF_NEED_RESCHED
moveq pc, r8 @ go again
reteq r8 @ go again
b 1b
#endif
@ -490,7 +490,7 @@ ENDPROC(__und_usr)
.pushsection .fixup, "ax"
.align 2
4: str r4, [sp, #S_PC] @ retry current instruction
mov pc, r9
ret r9
.popsection
.pushsection __ex_table,"a"
.long 1b, 4b
@ -552,7 +552,7 @@ call_fpe:
#endif
tst r0, #0x08000000 @ only CDP/CPRT/LDC/STC have bit 27
tstne r0, #0x04000000 @ bit 26 set on both ARM and Thumb-2
moveq pc, lr
reteq lr
and r8, r0, #0x00000f00 @ mask out CP number
THUMB( lsr r8, r8, #8 )
mov r7, #1
@ -571,33 +571,33 @@ call_fpe:
THUMB( add pc, r8 )
nop
movw_pc lr @ CP#0
ret.w lr @ CP#0
W(b) do_fpe @ CP#1 (FPE)
W(b) do_fpe @ CP#2 (FPE)
movw_pc lr @ CP#3
ret.w lr @ CP#3
#ifdef CONFIG_CRUNCH
b crunch_task_enable @ CP#4 (MaverickCrunch)
b crunch_task_enable @ CP#5 (MaverickCrunch)
b crunch_task_enable @ CP#6 (MaverickCrunch)
#else
movw_pc lr @ CP#4
movw_pc lr @ CP#5
movw_pc lr @ CP#6
ret.w lr @ CP#4
ret.w lr @ CP#5
ret.w lr @ CP#6
#endif
movw_pc lr @ CP#7
movw_pc lr @ CP#8
movw_pc lr @ CP#9
ret.w lr @ CP#7
ret.w lr @ CP#8
ret.w lr @ CP#9
#ifdef CONFIG_VFP
W(b) do_vfp @ CP#10 (VFP)
W(b) do_vfp @ CP#11 (VFP)
#else
movw_pc lr @ CP#10 (VFP)
movw_pc lr @ CP#11 (VFP)
ret.w lr @ CP#10 (VFP)
ret.w lr @ CP#11 (VFP)
#endif
movw_pc lr @ CP#12
movw_pc lr @ CP#13
movw_pc lr @ CP#14 (Debug)
movw_pc lr @ CP#15 (Control)
ret.w lr @ CP#12
ret.w lr @ CP#13
ret.w lr @ CP#14 (Debug)
ret.w lr @ CP#15 (Control)
#ifdef NEED_CPU_ARCHITECTURE
.align 2
@ -649,7 +649,7 @@ ENTRY(fp_enter)
.popsection
ENTRY(no_fp)
mov pc, lr
ret lr
ENDPROC(no_fp)
__und_usr_fault_32:
@ -745,7 +745,7 @@ ENDPROC(__switch_to)
#ifdef CONFIG_ARM_THUMB
bx \reg
#else
mov pc, \reg
ret \reg
#endif
.endm
@ -837,7 +837,7 @@ kuser_cmpxchg64_fixup:
#if __LINUX_ARM_ARCH__ < 6
bcc kuser_cmpxchg32_fixup
#endif
mov pc, lr
ret lr
.previous
#else
@ -905,7 +905,7 @@ kuser_cmpxchg32_fixup:
subs r8, r4, r7
rsbcss r8, r8, #(2b - 1b)
strcs r7, [sp, #S_PC]
mov pc, lr
ret lr
.previous
#else

13
arch/arm/kernel/entry-common.S
View File

@ -8,6 +8,7 @@
* published by the Free Software Foundation.
*/
#include <asm/assembler.h>
#include <asm/unistd.h>
#include <asm/ftrace.h>
#include <asm/unwind.h>
@ -88,7 +89,7 @@ ENTRY(ret_from_fork)
cmp r5, #0
movne r0, r4
adrne lr, BSYM(1f)
movne pc, r5
retne r5
1: get_thread_info tsk
b ret_slow_syscall
ENDPROC(ret_from_fork)
@ -290,7 +291,7 @@ ENDPROC(ftrace_graph_caller_old)
.macro mcount_exit
ldmia sp!, {r0-r3, ip, lr}
mov pc, ip
ret ip
.endm
ENTRY(__gnu_mcount_nc)
@ -298,7 +299,7 @@ UNWIND(.fnstart)
#ifdef CONFIG_DYNAMIC_FTRACE
mov ip, lr
ldmia sp!, {lr}
mov pc, ip
ret ip
#else
__mcount
#endif
@ -333,12 +334,12 @@ return_to_handler:
bl ftrace_return_to_handler
mov lr, r0 @ r0 has real ret addr
ldmia sp!, {r0-r3}
mov pc, lr
ret lr
#endif
ENTRY(ftrace_stub)
.Lftrace_stub:
mov pc, lr
ret lr
ENDPROC(ftrace_stub)
#endif /* CONFIG_FUNCTION_TRACER */
@ -561,7 +562,7 @@ sys_mmap2:
streq r5, [sp, #4]
beq sys_mmap_pgoff
mov r0, #-EINVAL
mov pc, lr
ret lr
#else
str r5, [sp, #4]
b sys_mmap_pgoff

14
arch/arm/kernel/entry-header.S
View File

@ -240,12 +240,6 @@
movs pc, lr @ return & move spsr_svc into cpsr
.endm
@
@ 32-bit wide "mov pc, reg"
@
.macro movw_pc, reg
mov pc, \reg
.endm
#else /* CONFIG_THUMB2_KERNEL */
.macro svc_exit, rpsr, irq = 0
.if \irq != 0
@ -304,14 +298,6 @@
movs pc, lr @ return & move spsr_svc into cpsr
.endm
#endif /* ifdef CONFIG_CPU_V7M / else */
@
@ 32-bit wide "mov pc, reg"
@
.macro movw_pc, reg
mov pc, \reg
nop
.endm
#endif /* !CONFIG_THUMB2_KERNEL */
/*

4
arch/arm/kernel/fiqasm.S
View File

@ -32,7 +32,7 @@ ENTRY(__set_fiq_regs)
ldr lr, [r0]
msr cpsr_c, r1 @ return to SVC mode
mov r0, r0 @ avoid hazard prior to ARMv4
mov pc, lr
ret lr
ENDPROC(__set_fiq_regs)
ENTRY(__get_fiq_regs)
@ -45,5 +45,5 @@ ENTRY(__get_fiq_regs)
str lr, [r0]
msr cpsr_c, r1 @ return to SVC mode
mov r0, r0 @ avoid hazard prior to ARMv4
mov pc, lr
ret lr
ENDPROC(__get_fiq_regs)

7
arch/arm/kernel/head-common.S
View File

@ -10,6 +10,7 @@
* published by the Free Software Foundation.
*
*/
#include <asm/assembler.h>
#define ATAG_CORE 0x54410001
#define ATAG_CORE_SIZE ((2*4 + 3*4) >> 2)
@ -61,10 +62,10 @@ __vet_atags:
cmp r5, r6
bne 1f
2: mov pc, lr @ atag/dtb pointer is ok
2: ret lr @ atag/dtb pointer is ok
1: mov r2, #0
mov pc, lr
ret lr
ENDPROC(__vet_atags)
/*
@ -162,7 +163,7 @@ __lookup_processor_type:
cmp r5, r6
blo 1b
mov r5, #0 @ unknown processor
2: mov pc, lr
2: ret lr
ENDPROC(__lookup_processor_type)
/*

8
arch/arm/kernel/head-nommu.S
View File

@ -82,7 +82,7 @@ ENTRY(stext)
adr lr, BSYM(1f) @ return (PIC) address
ARM( add pc, r10, #PROCINFO_INITFUNC )
THUMB( add r12, r10, #PROCINFO_INITFUNC )
THUMB( mov pc, r12 )
THUMB( ret r12 )
1: b __after_proc_init
ENDPROC(stext)
@ -119,7 +119,7 @@ ENTRY(secondary_startup)
mov r13, r12 @ __secondary_switched address
ARM( add pc, r10, #PROCINFO_INITFUNC )
THUMB( add r12, r10, #PROCINFO_INITFUNC )
THUMB( mov pc, r12 )
THUMB( ret r12 )
ENDPROC(secondary_startup)
ENTRY(__secondary_switched)
@ -164,7 +164,7 @@ __after_proc_init:
#endif
mcr p15, 0, r0, c1, c0, 0 @ write control reg
#endif /* CONFIG_CPU_CP15 */
mov pc, r13
ret r13
ENDPROC(__after_proc_init)
.ltorg
@ -254,7 +254,7 @@ ENTRY(__setup_mpu)
orr r0, r0, #CR_M @ Set SCTRL.M (MPU on)
mcr p15, 0, r0, c1, c0, 0 @ Enable MPU
isb
mov pc,lr
ret lr
ENDPROC(__setup_mpu)
#endif
#include "head-common.S"

18
arch/arm/kernel/head.S
View File

@ -140,7 +140,7 @@ ENTRY(stext)
mov r8, r4 @ set TTBR1 to swapper_pg_dir
ARM( add pc, r10, #PROCINFO_INITFUNC )
THUMB( add r12, r10, #PROCINFO_INITFUNC )
THUMB( mov pc, r12 )
THUMB( ret r12 )
1: b __enable_mmu
ENDPROC(stext)
.ltorg
@ -335,7 +335,7 @@ __create_page_tables:
sub r4, r4, #0x1000 @ point to the PGD table
mov r4, r4, lsr #ARCH_PGD_SHIFT
#endif
mov pc, lr
ret lr
ENDPROC(__create_page_tables)
.ltorg
.align
@ -383,7 +383,7 @@ ENTRY(secondary_startup)
ARM( add pc, r10, #PROCINFO_INITFUNC ) @ initialise processor
@ (return control reg)
THUMB( add r12, r10, #PROCINFO_INITFUNC )
THUMB( mov pc, r12 )
THUMB( ret r12 )
ENDPROC(secondary_startup)
/*
@ -468,7 +468,7 @@ ENTRY(__turn_mmu_on)
instr_sync
mov r3, r3
mov r3, r13
mov pc, r3
ret r3
__turn_mmu_on_end:
ENDPROC(__turn_mmu_on)
.popsection
@ -487,7 +487,7 @@ __fixup_smp:
orr r4, r4, #0x0000b000
orr r4, r4, #0x00000020 @ val 0x4100b020
teq r3, r4 @ ARM 11MPCore?
moveq pc, lr @ yes, assume SMP
reteq lr @ yes, assume SMP
mrc p15, 0, r0, c0, c0, 5 @ read MPIDR
and r0, r0, #0xc0000000 @ multiprocessing extensions and
@ -500,7 +500,7 @@ __fixup_smp:
orr r4, r4, #0x0000c000
orr r4, r4, #0x00000090
teq r3, r4 @ Check for ARM Cortex-A9
movne pc, lr @ Not ARM Cortex-A9,
retne lr @ Not ARM Cortex-A9,
@ If a future SoC *does* use 0x0 as the PERIPH_BASE, then the
@ below address check will need to be #ifdef'd or equivalent
@ -512,7 +512,7 @@ __fixup_smp:
ARM_BE8(rev r0, r0) @ byteswap if big endian
and r0, r0, #0x3 @ number of CPUs
teq r0, #0x0 @ is 1?
movne pc, lr
retne lr
__fixup_smp_on_up:
adr r0, 1f
@ -539,7 +539,7 @@ smp_on_up:
.text
__do_fixup_smp_on_up:
cmp r4, r5
movhs pc, lr
reths lr
ldmia r4!, {r0, r6}
ARM( str r6, [r0, r3] )
THUMB( add r0, r0, r3 )
@ -672,7 +672,7 @@ ARM_BE8(rev16 ip, ip)
2: cmp r4, r5
ldrcc r7, [r4], #4 @ use branch for delay slot
bcc 1b
mov pc, lr
ret lr
#endif
ENDPROC(__fixup_a_pv_table)

6
arch/arm/kernel/hyp-stub.S
View File

@ -99,7 +99,7 @@ ENTRY(__hyp_stub_install_secondary)
* immediately.
*/
compare_cpu_mode_with_primary r4, r5, r6, r7
movne pc, lr
retne lr
/*
* Once we have given up on one CPU, we do not try to install the
@ -111,7 +111,7 @@ ENTRY(__hyp_stub_install_secondary)
*/
cmp r4, #HYP_MODE
movne pc, lr @ give up if the CPU is not in HYP mode
retne lr @ give up if the CPU is not in HYP mode
/*
* Configure HSCTLR to set correct exception endianness/instruction set
@ -201,7 +201,7 @@ ENDPROC(__hyp_get_vectors)
@ fall through
ENTRY(__hyp_set_vectors)
__HVC(0)
mov pc, lr
ret lr
ENDPROC(__hyp_set_vectors)
#ifndef ZIMAGE

16
arch/arm/kernel/iwmmxt.S
View File

@ -100,7 +100,7 @@ ENTRY(iwmmxt_task_enable)
get_thread_info r10
#endif
4: dec_preempt_count r10, r3
mov pc, r9 @ normal exit from exception
ret r9 @ normal exit from exception
concan_save:
@ -144,7 +144,7 @@ concan_dump:
wstrd wR15, [r1, #MMX_WR15]
2: teq r0, #0 @ anything to load?
moveq pc, lr @ if not, return
reteq lr @ if not, return
concan_load:
@ -177,10 +177,10 @@ concan_load:
@ clear CUP/MUP (only if r1 != 0)
teq r1, #0
mov r2, #0
moveq pc, lr
reteq lr
tmcr wCon, r2
mov pc, lr
ret lr
/*
* Back up Concan regs to save area and disable access to them
@ -266,7 +266,7 @@ ENTRY(iwmmxt_task_copy)
mov r3, lr @ preserve return address
bl concan_dump
msr cpsr_c, ip @ restore interrupt mode
mov pc, r3
ret r3
/*
* Restore Concan state from given memory address
@ -302,7 +302,7 @@ ENTRY(iwmmxt_task_restore)
mov r3, lr @ preserve return address
bl concan_load
msr cpsr_c, ip @ restore interrupt mode
mov pc, r3
ret r3
/*
* Concan handling on task switch
@ -324,7 +324,7 @@ ENTRY(iwmmxt_task_switch)
add r3, r0, #TI_IWMMXT_STATE @ get next task Concan save area
ldr r2, [r2] @ get current Concan owner
teq r2, r3 @ next task owns it?
movne pc, lr @ no: leave Concan disabled
retne lr @ no: leave Concan disabled
1: @ flip Concan access
XSC(eor r1, r1, #0x3)
@ -351,7 +351,7 @@ ENTRY(iwmmxt_task_release)
eors r0, r0, r1 @ if equal...
streq r0, [r3] @ then clear ownership
msr cpsr_c, r2 @ restore interrupts
mov pc, lr
ret lr
.data
concan_owner:

5
arch/arm/kernel/perf_event.c
View File

@ -621,10 +621,7 @@ perf_callchain_kernel(struct perf_callchain_entry *entry, struct pt_regs *regs)
return;
}
fr.fp = regs->ARM_fp;
fr.sp = regs->ARM_sp;
fr.lr = regs->ARM_lr;
fr.pc = regs->ARM_pc;
arm_get_current_stackframe(regs, &fr);
walk_stackframe(&fr, callchain_trace, entry);
}

55
arch/arm/kernel/perf_event_cpu.c
View File

@ -250,40 +250,39 @@ static struct platform_device_id cpu_pmu_plat_device_ids[] = {
static int probe_current_pmu(struct arm_pmu *pmu)
{
int cpu = get_cpu();
unsigned long implementor = read_cpuid_implementor();
unsigned long part_number = read_cpuid_part_number();
int ret = -ENODEV;
pr_info("probing PMU on CPU %d\n", cpu);
switch (read_cpuid_part()) {
/* ARM Ltd CPUs. */
if (implementor == ARM_CPU_IMP_ARM) {
switch (part_number) {
case ARM_CPU_PART_ARM1136:
case ARM_CPU_PART_ARM1156:
case ARM_CPU_PART_ARM1176:
ret = armv6pmu_init(pmu);
break;
case ARM_CPU_PART_ARM11MPCORE:
ret = armv6mpcore_pmu_init(pmu);
break;
case ARM_CPU_PART_CORTEX_A8:
ret = armv7_a8_pmu_init(pmu);
break;
case ARM_CPU_PART_CORTEX_A9:
ret = armv7_a9_pmu_init(pmu);
break;
}
/* Intel CPUs [xscale]. */
} else if (implementor == ARM_CPU_IMP_INTEL) {
switch (xscale_cpu_arch_version()) {
case ARM_CPU_XSCALE_ARCH_V1:
ret = xscale1pmu_init(pmu);
break;
case ARM_CPU_XSCALE_ARCH_V2:
ret = xscale2pmu_init(pmu);
break;
case ARM_CPU_PART_ARM1136:
case ARM_CPU_PART_ARM1156:
case ARM_CPU_PART_ARM1176:
ret = armv6pmu_init(pmu);
break;
case ARM_CPU_PART_ARM11MPCORE:
ret = armv6mpcore_pmu_init(pmu);
break;
case ARM_CPU_PART_CORTEX_A8:
ret = armv7_a8_pmu_init(pmu);
break;
case ARM_CPU_PART_CORTEX_A9:
ret = armv7_a9_pmu_init(pmu);
break;
default:
if (read_cpuid_implementor() == ARM_CPU_IMP_INTEL) {
switch (xscale_cpu_arch_version()) {
case ARM_CPU_XSCALE_ARCH_V1:
ret = xscale1pmu_init(pmu);
break;
case ARM_CPU_XSCALE_ARCH_V2:
ret = xscale2pmu_init(pmu);
break;
}
}
break;
}
put_cpu();

3
arch/arm/kernel/relocate_kernel.S
View File

@ -3,6 +3,7 @@
*/
#include <linux/linkage.h>
#include <asm/assembler.h>
#include <asm/kexec.h>
.align 3 /* not needed for this code, but keeps fncpy() happy */
@ -59,7 +60,7 @@ ENTRY(relocate_new_kernel)
mov r0,#0
ldr r1,kexec_mach_type
ldr r2,kexec_boot_atags
ARM( mov pc, lr )
ARM( ret lr )
THUMB( bx lr )
.align

2
arch/arm/kernel/sleep.S
View File

@ -107,7 +107,7 @@ ENTRY(cpu_resume_mmu)
instr_sync
mov r0, r0
mov r0, r0
mov pc, r3 @ jump to virtual address
ret r3 @ jump to virtual address
ENDPROC(cpu_resume_mmu)
.popsection
cpu_resume_after_mmu:

Some files were not shown because too many files have changed in this diff Show More