summaryrefslogtreecommitdiff
path: root/arch/arm
diff options
context:
space:
mode:
Diffstat (limited to 'arch/arm')
-rw-r--r--arch/arm/Kconfig5
-rw-r--r--arch/arm/Kconfig.debug2
-rw-r--r--arch/arm/boot/compressed/Makefile2
-rw-r--r--arch/arm/boot/compressed/atags_to_fdt.c2
-rw-r--r--arch/arm/boot/dts/am33xx-clocks.dtsi10
-rw-r--r--arch/arm/boot/dts/am43xx-clocks.dtsi12
-rw-r--r--arch/arm/boot/dts/arm-realview-eb.dtsi2
-rw-r--r--arch/arm/boot/dts/arm-realview-pb1176.dts2
-rw-r--r--arch/arm/boot/dts/arm-realview-pb11mp.dts2
-rw-r--r--arch/arm/boot/dts/arm-realview-pbx.dtsi2
-rw-r--r--arch/arm/boot/dts/imx53-ppd.dts2
-rw-r--r--arch/arm/boot/dts/sama5d4.dtsi7
-rw-r--r--arch/arm/boot/dts/vexpress-v2m-rs1.dtsi2
-rw-r--r--arch/arm/boot/dts/vexpress-v2m.dtsi2
-rw-r--r--arch/arm/configs/footbridge_defconfig1
-rw-r--r--arch/arm/configs/pxa_defconfig2
-rw-r--r--arch/arm/crypto/Makefile10
-rw-r--r--arch/arm/crypto/poly1305-core.S_shipped1158
-rw-r--r--arch/arm/crypto/sha256-core.S_shipped2816
-rw-r--r--arch/arm/crypto/sha512-core.S_shipped1869
-rw-r--r--arch/arm/include/asm/atomic.h96
-rw-r--r--arch/arm/include/asm/cmpxchg.h20
-rw-r--r--arch/arm/include/asm/cpuidle.h10
-rw-r--r--arch/arm/include/asm/ftrace.h3
-rw-r--r--arch/arm/include/asm/insn.h8
-rw-r--r--arch/arm/include/asm/memory.h15
-rw-r--r--arch/arm/include/asm/module.h10
-rw-r--r--arch/arm/include/asm/pgalloc.h1
-rw-r--r--arch/arm/include/asm/pgtable-3level.h2
-rw-r--r--arch/arm/include/asm/pgtable.h2
-rw-r--r--arch/arm/include/asm/sync_bitops.h2
-rw-r--r--arch/arm/include/asm/system_misc.h1
-rw-r--r--arch/arm/include/asm/tlbflush.h13
-rw-r--r--arch/arm/include/asm/unaligned.h27
-rw-r--r--arch/arm/kernel/ftrace.c46
-rw-r--r--arch/arm/kernel/head.S30
-rw-r--r--arch/arm/kernel/insn.c19
-rw-r--r--arch/arm/kernel/irq.c22
-rw-r--r--arch/arm/kernel/module-plts.c49
-rw-r--r--arch/arm/kernel/perf_event_v7.c4
-rw-r--r--arch/arm/kernel/process.c2
-rw-r--r--arch/arm/kernel/reboot.c6
-rw-r--r--arch/arm/kernel/setup.c41
-rw-r--r--arch/arm/kernel/smp.c1
-rw-r--r--arch/arm/kernel/vmlinux.lds.S2
-rw-r--r--arch/arm/mach-ixp4xx/common.c26
-rw-r--r--arch/arm/mach-zynq/Kconfig2
-rw-r--r--arch/arm/mm/Kconfig2
-rw-r--r--arch/arm/mm/abort-ev7.S26
-rw-r--r--arch/arm/mm/init.c13
-rw-r--r--arch/arm/mm/ioremap.c4
-rw-r--r--arch/arm/mm/mmu.c166
-rw-r--r--arch/arm/mm/tlb-v6.S2
-rw-r--r--arch/arm/mm/tlb-v7.S2
-rw-r--r--arch/arm/probes/kprobes/core.c23
-rw-r--r--arch/arm/probes/kprobes/test-thumb.c10
-rw-r--r--arch/arm/tools/Makefile25
-rw-r--r--arch/arm/tools/syscall.tbl2
-rw-r--r--arch/arm/tools/syscallnr.sh3
-rw-r--r--arch/arm/xen/enlighten.c12
60 files changed, 489 insertions, 6171 deletions
diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig
index 819f0d08401e..3ea1c417339f 100644
--- a/arch/arm/Kconfig
+++ b/arch/arm/Kconfig
@@ -218,9 +218,6 @@ config GENERIC_CALIBRATE_DELAY
config ARCH_MAY_HAVE_PC_FDC
bool
-config ZONE_DMA
- bool
-
config ARCH_SUPPORTS_UPROBES
def_bool y
@@ -353,7 +350,6 @@ config ARCH_EP93XX
select ARM_VIC
select GENERIC_IRQ_MULTI_HANDLER
select AUTO_ZRELADDR
- select CLKDEV_LOOKUP
select CLKSRC_MMIO
select CPU_ARM920T
select GPIOLIB
@@ -505,7 +501,6 @@ config ARCH_OMAP1
bool "TI OMAP1"
depends on MMU
select ARCH_OMAP
- select CLKDEV_LOOKUP
select CLKSRC_MMIO
select GENERIC_IRQ_CHIP
select GENERIC_IRQ_MULTI_HANDLER
diff --git a/arch/arm/Kconfig.debug b/arch/arm/Kconfig.debug
index ba8514468df8..1c4384db223d 100644
--- a/arch/arm/Kconfig.debug
+++ b/arch/arm/Kconfig.debug
@@ -66,6 +66,8 @@ config UNWINDER_FRAME_POINTER
config UNWINDER_ARM
bool "ARM EABI stack unwinder"
depends on AEABI && !FUNCTION_GRAPH_TRACER
+ # https://github.com/ClangBuiltLinux/linux/issues/732
+ depends on !LD_IS_LLD || LLD_VERSION >= 110000
select ARM_UNWIND
help
This option enables stack unwinding support in the kernel
diff --git a/arch/arm/boot/compressed/Makefile b/arch/arm/boot/compressed/Makefile
index 8eb70c1febce..9d91ae1091b0 100644
--- a/arch/arm/boot/compressed/Makefile
+++ b/arch/arm/boot/compressed/Makefile
@@ -100,7 +100,7 @@ targets := vmlinux vmlinux.lds piggy_data piggy.o \
lib1funcs.o ashldi3.o bswapsdi2.o \
head.o $(OBJS)
-clean-files += piggy_data lib1funcs.S ashldi3.S bswapsdi2.S hyp-stub.S
+clean-files += lib1funcs.S ashldi3.S bswapsdi2.S hyp-stub.S
KBUILD_CFLAGS += -DDISABLE_BRANCH_PROFILING
diff --git a/arch/arm/boot/compressed/atags_to_fdt.c b/arch/arm/boot/compressed/atags_to_fdt.c
index 31927d2fe297..1feb6b0f7a1f 100644
--- a/arch/arm/boot/compressed/atags_to_fdt.c
+++ b/arch/arm/boot/compressed/atags_to_fdt.c
@@ -121,7 +121,7 @@ static void hex_str(char *out, uint32_t value)
/*
* Convert and fold provided ATAGs into the provided FDT.
*
- * REturn values:
+ * Return values:
* = 0 -> pretend success
* = 1 -> bad ATAG (may retry with another possible ATAG pointer)
* < 0 -> error from libfdt
diff --git a/arch/arm/boot/dts/am33xx-clocks.dtsi b/arch/arm/boot/dts/am33xx-clocks.dtsi
index dced92a8970e..b7b7106f2dee 100644
--- a/arch/arm/boot/dts/am33xx-clocks.dtsi
+++ b/arch/arm/boot/dts/am33xx-clocks.dtsi
@@ -164,7 +164,7 @@
#clock-cells = <0>;
compatible = "ti,am3-dpll-core-clock";
clocks = <&sys_clkin_ck>, <&sys_clkin_ck>;
- reg = <0x0490>, <0x045c>, <0x0468>;
+ reg = <0x0490>, <0x045c>, <0x0468>, <0x0460>, <0x0464>;
};
dpll_core_x2_ck: dpll_core_x2_ck {
@@ -204,7 +204,7 @@
#clock-cells = <0>;
compatible = "ti,am3-dpll-clock";
clocks = <&sys_clkin_ck>, <&sys_clkin_ck>;
- reg = <0x0488>, <0x0420>, <0x042c>;
+ reg = <0x0488>, <0x0420>, <0x042c>, <0x0424>, <0x0428>;
};
dpll_mpu_m2_ck: dpll_mpu_m2_ck@4a8 {
@@ -220,7 +220,7 @@
#clock-cells = <0>;
compatible = "ti,am3-dpll-no-gate-clock";
clocks = <&sys_clkin_ck>, <&sys_clkin_ck>;
- reg = <0x0494>, <0x0434>, <0x0440>;
+ reg = <0x0494>, <0x0434>, <0x0440>, <0x0438>, <0x043c>;
};
dpll_ddr_m2_ck: dpll_ddr_m2_ck@4a0 {
@@ -244,7 +244,7 @@
#clock-cells = <0>;
compatible = "ti,am3-dpll-no-gate-clock";
clocks = <&sys_clkin_ck>, <&sys_clkin_ck>;
- reg = <0x0498>, <0x0448>, <0x0454>;
+ reg = <0x0498>, <0x0448>, <0x0454>, <0x044c>, <0x0450>;
};
dpll_disp_m2_ck: dpll_disp_m2_ck@4a4 {
@@ -261,7 +261,7 @@
#clock-cells = <0>;
compatible = "ti,am3-dpll-no-gate-j-type-clock";
clocks = <&sys_clkin_ck>, <&sys_clkin_ck>;
- reg = <0x048c>, <0x0470>, <0x049c>;
+ reg = <0x048c>, <0x0470>, <0x049c>, <0x0474>, <0x0478>;
};
dpll_per_m2_ck: dpll_per_m2_ck@4ac {
diff --git a/arch/arm/boot/dts/am43xx-clocks.dtsi b/arch/arm/boot/dts/am43xx-clocks.dtsi
index c726cd8dbdf1..314fc5975acb 100644
--- a/arch/arm/boot/dts/am43xx-clocks.dtsi
+++ b/arch/arm/boot/dts/am43xx-clocks.dtsi
@@ -204,7 +204,7 @@
#clock-cells = <0>;
compatible = "ti,am3-dpll-core-clock";
clocks = <&sys_clkin_ck>, <&sys_clkin_ck>;
- reg = <0x2d20>, <0x2d24>, <0x2d2c>;
+ reg = <0x2d20>, <0x2d24>, <0x2d2c>, <0x2d48>, <0x2d4c>;
};
dpll_core_x2_ck: dpll_core_x2_ck {
@@ -250,7 +250,7 @@
#clock-cells = <0>;
compatible = "ti,am3-dpll-clock";
clocks = <&sys_clkin_ck>, <&sys_clkin_ck>;
- reg = <0x2d60>, <0x2d64>, <0x2d6c>;
+ reg = <0x2d60>, <0x2d64>, <0x2d6c>, <0x2d88>, <0x2d8c>;
};
dpll_mpu_m2_ck: dpll_mpu_m2_ck@2d70 {
@@ -276,7 +276,7 @@
#clock-cells = <0>;
compatible = "ti,am3-dpll-clock";
clocks = <&sys_clkin_ck>, <&sys_clkin_ck>;
- reg = <0x2da0>, <0x2da4>, <0x2dac>;
+ reg = <0x2da0>, <0x2da4>, <0x2dac>, <0x2dc8>, <0x2dcc>;
};
dpll_ddr_m2_ck: dpll_ddr_m2_ck@2db0 {
@@ -294,7 +294,7 @@
#clock-cells = <0>;
compatible = "ti,am3-dpll-clock";
clocks = <&sys_clkin_ck>, <&sys_clkin_ck>;
- reg = <0x2e20>, <0x2e24>, <0x2e2c>;
+ reg = <0x2e20>, <0x2e24>, <0x2e2c>, <0x2e48>, <0x2e4c>;
};
dpll_disp_m2_ck: dpll_disp_m2_ck@2e30 {
@@ -313,7 +313,7 @@
#clock-cells = <0>;
compatible = "ti,am3-dpll-j-type-clock";
clocks = <&sys_clkin_ck>, <&sys_clkin_ck>;
- reg = <0x2de0>, <0x2de4>, <0x2dec>;
+ reg = <0x2de0>, <0x2de4>, <0x2dec>, <0x2e08>, <0x2e0c>;
};
dpll_per_m2_ck: dpll_per_m2_ck@2df0 {
@@ -557,7 +557,7 @@
#clock-cells = <0>;
compatible = "ti,am3-dpll-clock";
clocks = <&sys_clkin_ck>, <&sys_clkin_ck>;
- reg = <0x2e60>, <0x2e64>, <0x2e6c>;
+ reg = <0x2e60>, <0x2e64>, <0x2e6c>, <0x2e88>, <0x2e8c>;
};
dpll_extdev_m2_ck: dpll_extdev_m2_ck@2e70 {
diff --git a/arch/arm/boot/dts/arm-realview-eb.dtsi b/arch/arm/boot/dts/arm-realview-eb.dtsi
index a534a8e444d9..04e8a27ba1eb 100644
--- a/arch/arm/boot/dts/arm-realview-eb.dtsi
+++ b/arch/arm/boot/dts/arm-realview-eb.dtsi
@@ -148,7 +148,7 @@
usb: usb@4f000000 {
compatible = "nxp,usb-isp1761";
reg = <0x4f000000 0x20000>;
- port1-otg;
+ dr_mode = "peripheral";
};
bridge {
diff --git a/arch/arm/boot/dts/arm-realview-pb1176.dts b/arch/arm/boot/dts/arm-realview-pb1176.dts
index f925782f8560..366687fb1ee3 100644
--- a/arch/arm/boot/dts/arm-realview-pb1176.dts
+++ b/arch/arm/boot/dts/arm-realview-pb1176.dts
@@ -166,7 +166,7 @@
reg = <0x3b000000 0x20000>;
interrupt-parent = <&intc_fpga1176>;
interrupts = <0 11 IRQ_TYPE_LEVEL_HIGH>;
- port1-otg;
+ dr_mode = "peripheral";
};
bridge {
diff --git a/arch/arm/boot/dts/arm-realview-pb11mp.dts b/arch/arm/boot/dts/arm-realview-pb11mp.dts
index 0c7dabef4a5f..228a51a38f95 100644
--- a/arch/arm/boot/dts/arm-realview-pb11mp.dts
+++ b/arch/arm/boot/dts/arm-realview-pb11mp.dts
@@ -712,7 +712,7 @@
reg = <0x4f000000 0x20000>;
interrupt-parent = <&intc_tc11mp>;
interrupts = <0 3 IRQ_TYPE_LEVEL_HIGH>;
- port1-otg;
+ dr_mode = "peripheral";
};
};
};
diff --git a/arch/arm/boot/dts/arm-realview-pbx.dtsi b/arch/arm/boot/dts/arm-realview-pbx.dtsi
index ac95667ed781..ccf6f756b6ed 100644
--- a/arch/arm/boot/dts/arm-realview-pbx.dtsi
+++ b/arch/arm/boot/dts/arm-realview-pbx.dtsi
@@ -164,7 +164,7 @@
usb: usb@4f000000 {
compatible = "nxp,usb-isp1761";
reg = <0x4f000000 0x20000>;
- port1-otg;
+ dr_mode = "peripheral";
};
bridge {
diff --git a/arch/arm/boot/dts/imx53-ppd.dts b/arch/arm/boot/dts/imx53-ppd.dts
index be040b6a02fa..5a5fa6190a52 100644
--- a/arch/arm/boot/dts/imx53-ppd.dts
+++ b/arch/arm/boot/dts/imx53-ppd.dts
@@ -651,6 +651,7 @@
&uart2 {
pinctrl-names = "default";
pinctrl-0 = <&pinctrl_uart2>;
+ fsl,dma-info = <24 20>;
status = "okay";
};
@@ -670,6 +671,7 @@
&uart5 {
pinctrl-names = "default";
pinctrl-0 = <&pinctrl_uart5>;
+ fsl,dma-info = <4096 4>;
status = "okay";
};
diff --git a/arch/arm/boot/dts/sama5d4.dtsi b/arch/arm/boot/dts/sama5d4.dtsi
index 05c55875835d..e47e1ca63043 100644
--- a/arch/arm/boot/dts/sama5d4.dtsi
+++ b/arch/arm/boot/dts/sama5d4.dtsi
@@ -101,6 +101,13 @@
ranges = <0 0x100000 0x2400>;
};
+ vdec0: vdec@300000 {
+ compatible = "microchip,sama5d4-vdec";
+ reg = <0x00300000 0x100000>;
+ interrupts = <19 IRQ_TYPE_LEVEL_HIGH 4>;
+ clocks = <&pmc PMC_TYPE_PERIPHERAL 19>;
+ };
+
usb0: gadget@400000 {
compatible = "atmel,sama5d3-udc";
reg = <0x00400000 0x100000
diff --git a/arch/arm/boot/dts/vexpress-v2m-rs1.dtsi b/arch/arm/boot/dts/vexpress-v2m-rs1.dtsi
index 4f7220b11f2d..2ad9fd7c94ec 100644
--- a/arch/arm/boot/dts/vexpress-v2m-rs1.dtsi
+++ b/arch/arm/boot/dts/vexpress-v2m-rs1.dtsi
@@ -144,7 +144,7 @@
compatible = "nxp,usb-isp1761";
reg = <2 0x03000000 0x20000>;
interrupts = <16>;
- port1-otg;
+ dr_mode = "peripheral";
};
iofpga-bus@300000000 {
diff --git a/arch/arm/boot/dts/vexpress-v2m.dtsi b/arch/arm/boot/dts/vexpress-v2m.dtsi
index 2ac41ed3a57c..ec13ceb9ed36 100644
--- a/arch/arm/boot/dts/vexpress-v2m.dtsi
+++ b/arch/arm/boot/dts/vexpress-v2m.dtsi
@@ -62,7 +62,7 @@
compatible = "nxp,usb-isp1761";
reg = <3 0x03000000 0x20000>;
interrupts = <16>;
- port1-otg;
+ dr_mode = "peripheral";
};
iofpga@7,00000000 {
diff --git a/arch/arm/configs/footbridge_defconfig b/arch/arm/configs/footbridge_defconfig
index 2aa3ebeb89d7..7a32de51f0fa 100644
--- a/arch/arm/configs/footbridge_defconfig
+++ b/arch/arm/configs/footbridge_defconfig
@@ -64,7 +64,6 @@ CONFIG_PARIDE_ON26=m
CONFIG_BLK_DEV_LOOP=m
CONFIG_BLK_DEV_NBD=m
CONFIG_BLK_DEV_RAM=y
-CONFIG_IDE=y
CONFIG_NETDEVICES=y
CONFIG_NET_ETHERNET=y
CONFIG_NET_VENDOR_3COM=y
diff --git a/arch/arm/configs/pxa_defconfig b/arch/arm/configs/pxa_defconfig
index 875a3c28a267..363f1b1b08e3 100644
--- a/arch/arm/configs/pxa_defconfig
+++ b/arch/arm/configs/pxa_defconfig
@@ -215,8 +215,6 @@ CONFIG_IIO=m
CONFIG_AD5446=m
CONFIG_EEPROM_AT24=m
CONFIG_SENSORS_LIS3_SPI=m
-CONFIG_IDE=m
-CONFIG_BLK_DEV_IDECS=m
CONFIG_SCSI=y
CONFIG_BLK_DEV_SD=m
CONFIG_CHR_DEV_ST=m
diff --git a/arch/arm/crypto/Makefile b/arch/arm/crypto/Makefile
index 8f26c454ea12..eafa898ba6a7 100644
--- a/arch/arm/crypto/Makefile
+++ b/arch/arm/crypto/Makefile
@@ -45,20 +45,12 @@ poly1305-arm-y := poly1305-core.o poly1305-glue.o
nhpoly1305-neon-y := nh-neon-core.o nhpoly1305-neon-glue.o
curve25519-neon-y := curve25519-core.o curve25519-glue.o
-ifdef REGENERATE_ARM_CRYPTO
quiet_cmd_perl = PERL $@
cmd_perl = $(PERL) $(<) > $(@)
-$(src)/poly1305-core.S_shipped: $(src)/poly1305-armv4.pl
+$(obj)/%-core.S: $(src)/%-armv4.pl
$(call cmd,perl)
-$(src)/sha256-core.S_shipped: $(src)/sha256-armv4.pl
- $(call cmd,perl)
-
-$(src)/sha512-core.S_shipped: $(src)/sha512-armv4.pl
- $(call cmd,perl)
-endif
-
clean-files += poly1305-core.S sha256-core.S sha512-core.S
# massage the perlasm code a bit so we only get the NEON routine if we need it
diff --git a/arch/arm/crypto/poly1305-core.S_shipped b/arch/arm/crypto/poly1305-core.S_shipped
deleted file mode 100644
index 37b71d990293..000000000000
--- a/arch/arm/crypto/poly1305-core.S_shipped
+++ /dev/null
@@ -1,1158 +0,0 @@
-#ifndef __KERNEL__
-# include "arm_arch.h"
-#else
-# define __ARM_ARCH__ __LINUX_ARM_ARCH__
-# define __ARM_MAX_ARCH__ __LINUX_ARM_ARCH__
-# define poly1305_init poly1305_init_arm
-# define poly1305_blocks poly1305_blocks_arm
-# define poly1305_emit poly1305_emit_arm
-.globl poly1305_blocks_neon
-#endif
-
-#if defined(__thumb2__)
-.syntax unified
-.thumb
-#else
-.code 32
-#endif
-
-.text
-
-.globl poly1305_emit
-.globl poly1305_blocks
-.globl poly1305_init
-.type poly1305_init,%function
-.align 5
-poly1305_init:
-.Lpoly1305_init:
- stmdb sp!,{r4-r11}
-
- eor r3,r3,r3
- cmp r1,#0
- str r3,[r0,#0] @ zero hash value
- str r3,[r0,#4]
- str r3,[r0,#8]
- str r3,[r0,#12]
- str r3,[r0,#16]
- str r3,[r0,#36] @ clear is_base2_26
- add r0,r0,#20
-
-#ifdef __thumb2__
- it eq
-#endif
- moveq r0,#0
- beq .Lno_key
-
-#if __ARM_MAX_ARCH__>=7
- mov r3,#-1
- str r3,[r0,#28] @ impossible key power value
-# ifndef __KERNEL__
- adr r11,.Lpoly1305_init
- ldr r12,.LOPENSSL_armcap
-# endif
-#endif
- ldrb r4,[r1,#0]
- mov r10,#0x0fffffff
- ldrb r5,[r1,#1]
- and r3,r10,#-4 @ 0x0ffffffc
- ldrb r6,[r1,#2]
- ldrb r7,[r1,#3]
- orr r4,r4,r5,lsl#8
- ldrb r5,[r1,#4]
- orr r4,r4,r6,lsl#16
- ldrb r6,[r1,#5]
- orr r4,r4,r7,lsl#24
- ldrb r7,[r1,#6]
- and r4,r4,r10
-
-#if __ARM_MAX_ARCH__>=7 && !defined(__KERNEL__)
-# if !defined(_WIN32)
- ldr r12,[r11,r12] @ OPENSSL_armcap_P
-# endif
-# if defined(__APPLE__) || defined(_WIN32)
- ldr r12,[r12]
-# endif
-#endif
- ldrb r8,[r1,#7]
- orr r5,r5,r6,lsl#8
- ldrb r6,[r1,#8]
- orr r5,r5,r7,lsl#16
- ldrb r7,[r1,#9]
- orr r5,r5,r8,lsl#24
- ldrb r8,[r1,#10]
- and r5,r5,r3
-
-#if __ARM_MAX_ARCH__>=7 && !defined(__KERNEL__)
- tst r12,#ARMV7_NEON @ check for NEON
-# ifdef __thumb2__
- adr r9,.Lpoly1305_blocks_neon
- adr r11,.Lpoly1305_blocks
- it ne
- movne r11,r9
- adr r12,.Lpoly1305_emit
- orr r11,r11,#1 @ thumb-ify addresses
- orr r12,r12,#1
-# else
- add r12,r11,#(.Lpoly1305_emit-.Lpoly1305_init)
- ite eq
- addeq r11,r11,#(.Lpoly1305_blocks-.Lpoly1305_init)
- addne r11,r11,#(.Lpoly1305_blocks_neon-.Lpoly1305_init)
-# endif
-#endif
- ldrb r9,[r1,#11]
- orr r6,r6,r7,lsl#8
- ldrb r7,[r1,#12]
- orr r6,r6,r8,lsl#16
- ldrb r8,[r1,#13]
- orr r6,r6,r9,lsl#24
- ldrb r9,[r1,#14]
- and r6,r6,r3
-
- ldrb r10,[r1,#15]
- orr r7,r7,r8,lsl#8
- str r4,[r0,#0]
- orr r7,r7,r9,lsl#16
- str r5,[r0,#4]
- orr r7,r7,r10,lsl#24
- str r6,[r0,#8]
- and r7,r7,r3
- str r7,[r0,#12]
-#if __ARM_MAX_ARCH__>=7 && !defined(__KERNEL__)
- stmia r2,{r11,r12} @ fill functions table
- mov r0,#1
-#else
- mov r0,#0
-#endif
-.Lno_key:
- ldmia sp!,{r4-r11}
-#if __ARM_ARCH__>=5
- bx lr @ bx lr
-#else
- tst lr,#1
- moveq pc,lr @ be binary compatible with V4, yet
- .word 0xe12fff1e @ interoperable with Thumb ISA:-)
-#endif
-.size poly1305_init,.-poly1305_init
-.type poly1305_blocks,%function
-.align 5
-poly1305_blocks:
-.Lpoly1305_blocks:
- stmdb sp!,{r3-r11,lr}
-
- ands r2,r2,#-16
- beq .Lno_data
-
- add r2,r2,r1 @ end pointer
- sub sp,sp,#32
-
-#if __ARM_ARCH__<7
- ldmia r0,{r4-r12} @ load context
- add r0,r0,#20
- str r2,[sp,#16] @ offload stuff
- str r0,[sp,#12]
-#else
- ldr lr,[r0,#36] @ is_base2_26
- ldmia r0!,{r4-r8} @ load hash value
- str r2,[sp,#16] @ offload stuff
- str r0,[sp,#12]
-
- adds r9,r4,r5,lsl#26 @ base 2^26 -> base 2^32
- mov r10,r5,lsr#6
- adcs r10,r10,r6,lsl#20
- mov r11,r6,lsr#12
- adcs r11,r11,r7,lsl#14
- mov r12,r7,lsr#18
- adcs r12,r12,r8,lsl#8
- mov r2,#0
- teq lr,#0
- str r2,[r0,#16] @ clear is_base2_26
- adc r2,r2,r8,lsr#24
-
- itttt ne
- movne r4,r9 @ choose between radixes
- movne r5,r10
- movne r6,r11
- movne r7,r12
- ldmia r0,{r9-r12} @ load key
- it ne
- movne r8,r2
-#endif
-
- mov lr,r1
- cmp r3,#0
- str r10,[sp,#20]
- str r11,[sp,#24]
- str r12,[sp,#28]
- b .Loop
-
-.align 4
-.Loop:
-#if __ARM_ARCH__<7
- ldrb r0,[lr],#16 @ load input
-# ifdef __thumb2__
- it hi
-# endif
- addhi r8,r8,#1 @ 1<<128
- ldrb r1,[lr,#-15]
- ldrb r2,[lr,#-14]
- ldrb r3,[lr,#-13]
- orr r1,r0,r1,lsl#8
- ldrb r0,[lr,#-12]
- orr r2,r1,r2,lsl#16
- ldrb r1,[lr,#-11]
- orr r3,r2,r3,lsl#24
- ldrb r2,[lr,#-10]
- adds r4,r4,r3 @ accumulate input
-
- ldrb r3,[lr,#-9]
- orr r1,r0,r1,lsl#8
- ldrb r0,[lr,#-8]
- orr r2,r1,r2,lsl#16
- ldrb r1,[lr,#-7]
- orr r3,r2,r3,lsl#24
- ldrb r2,[lr,#-6]
- adcs r5,r5,r3
-
- ldrb r3,[lr,#-5]
- orr r1,r0,r1,lsl#8
- ldrb r0,[lr,#-4]
- orr r2,r1,r2,lsl#16
- ldrb r1,[lr,#-3]
- orr r3,r2,r3,lsl#24
- ldrb r2,[lr,#-2]
- adcs r6,r6,r3
-
- ldrb r3,[lr,#-1]
- orr r1,r0,r1,lsl#8
- str lr,[sp,#8] @ offload input pointer
- orr r2,r1,r2,lsl#16
- add r10,r10,r10,lsr#2
- orr r3,r2,r3,lsl#24
-#else
- ldr r0,[lr],#16 @ load input
- it hi
- addhi r8,r8,#1 @ padbit
- ldr r1,[lr,#-12]
- ldr r2,[lr,#-8]
- ldr r3,[lr,#-4]
-# ifdef __ARMEB__
- rev r0,r0
- rev r1,r1
- rev r2,r2
- rev r3,r3
-# endif
- adds r4,r4,r0 @ accumulate input
- str lr,[sp,#8] @ offload input pointer
- adcs r5,r5,r1
- add r10,r10,r10,lsr#2
- adcs r6,r6,r2
-#endif
- add r11,r11,r11,lsr#2
- adcs r7,r7,r3
- add r12,r12,r12,lsr#2
-
- umull r2,r3,r5,r9
- adc r8,r8,#0
- umull r0,r1,r4,r9
- umlal r2,r3,r8,r10
- umlal r0,r1,r7,r10
- ldr r10,[sp,#20] @ reload r10
- umlal r2,r3,r6,r12
- umlal r0,r1,r5,r12
- umlal r2,r3,r7,r11
- umlal r0,r1,r6,r11
- umlal r2,r3,r4,r10
- str r0,[sp,#0] @ future r4
- mul r0,r11,r8
- ldr r11,[sp,#24] @ reload r11
- adds r2,r2,r1 @ d1+=d0>>32
- eor r1,r1,r1
- adc lr,r3,#0 @ future r6
- str r2,[sp,#4] @ future r5
-
- mul r2,r12,r8
- eor r3,r3,r3
- umlal r0,r1,r7,r12
- ldr r12,[sp,#28] @ reload r12
- umlal r2,r3,r7,r9
- umlal r0,r1,r6,r9
- umlal r2,r3,r6,r10
- umlal r0,r1,r5,r10
- umlal r2,r3,r5,r11
- umlal r0,r1,r4,r11
- umlal r2,r3,r4,r12
- ldr r4,[sp,#0]
- mul r8,r9,r8
- ldr r5,[sp,#4]
-
- adds r6,lr,r0 @ d2+=d1>>32
- ldr lr,[sp,#8] @ reload input pointer
- adc r1,r1,#0
- adds r7,r2,r1 @ d3+=d2>>32
- ldr r0,[sp,#16] @ reload end pointer
- adc r3,r3,#0
- add r8,r8,r3 @ h4+=d3>>32
-
- and r1,r8,#-4
- and r8,r8,#3
- add r1,r1,r1,lsr#2 @ *=5
- adds r4,r4,r1
- adcs r5,r5,#0
- adcs r6,r6,#0
- adcs r7,r7,#0
- adc r8,r8,#0
-
- cmp r0,lr @ done yet?
- bhi .Loop
-
- ldr r0,[sp,#12]
- add sp,sp,#32
- stmdb r0,{r4-r8} @ store the result
-
-.Lno_data:
-#if __ARM_ARCH__>=5
- ldmia sp!,{r3-r11,pc}
-#else
- ldmia sp!,{r3-r11,lr}
- tst lr,#1
- moveq pc,lr @ be binary compatible with V4, yet
- .word 0xe12fff1e @ interoperable with Thumb ISA:-)
-#endif
-.size poly1305_blocks,.-poly1305_blocks
-.type poly1305_emit,%function
-.align 5
-poly1305_emit:
-.Lpoly1305_emit:
- stmdb sp!,{r4-r11}
-
- ldmia r0,{r3-r7}
-
-#if __ARM_ARCH__>=7
- ldr ip,[r0,#36] @ is_base2_26
-
- adds r8,r3,r4,lsl#26 @ base 2^26 -> base 2^32
- mov r9,r4,lsr#6
- adcs r9,r9,r5,lsl#20
- mov r10,r5,lsr#12
- adcs r10,r10,r6,lsl#14
- mov r11,r6,lsr#18
- adcs r11,r11,r7,lsl#8
- mov r0,#0
- adc r0,r0,r7,lsr#24
-
- tst ip,ip
- itttt ne
- movne r3,r8
- movne r4,r9
- movne r5,r10
- movne r6,r11
- it ne
- movne r7,r0
-#endif
-
- adds r8,r3,#5 @ compare to modulus
- adcs r9,r4,#0
- adcs r10,r5,#0
- adcs r11,r6,#0
- adc r0,r7,#0
- tst r0,#4 @ did it carry/borrow?
-
-#ifdef __thumb2__
- it ne
-#endif
- movne r3,r8
- ldr r8,[r2,#0]
-#ifdef __thumb2__
- it ne
-#endif
- movne r4,r9
- ldr r9,[r2,#4]
-#ifdef __thumb2__
- it ne
-#endif
- movne r5,r10
- ldr r10,[r2,#8]
-#ifdef __thumb2__
- it ne
-#endif
- movne r6,r11
- ldr r11,[r2,#12]
-
- adds r3,r3,r8
- adcs r4,r4,r9
- adcs r5,r5,r10
- adc r6,r6,r11
-
-#if __ARM_ARCH__>=7
-# ifdef __ARMEB__
- rev r3,r3
- rev r4,r4
- rev r5,r5
- rev r6,r6
-# endif
- str r3,[r1,#0]
- str r4,[r1,#4]
- str r5,[r1,#8]
- str r6,[r1,#12]
-#else
- strb r3,[r1,#0]
- mov r3,r3,lsr#8
- strb r4,[r1,#4]
- mov r4,r4,lsr#8
- strb r5,[r1,#8]
- mov r5,r5,lsr#8
- strb r6,[r1,#12]
- mov r6,r6,lsr#8
-
- strb r3,[r1,#1]
- mov r3,r3,lsr#8
- strb r4,[r1,#5]
- mov r4,r4,lsr#8
- strb r5,[r1,#9]
- mov r5,r5,lsr#8
- strb r6,[r1,#13]
- mov r6,r6,lsr#8
-
- strb r3,[r1,#2]
- mov r3,r3,lsr#8
- strb r4,[r1,#6]
- mov r4,r4,lsr#8
- strb r5,[r1,#10]
- mov r5,r5,lsr#8
- strb r6,[r1,#14]
- mov r6,r6,lsr#8
-
- strb r3,[r1,#3]
- strb r4,[r1,#7]
- strb r5,[r1,#11]
- strb r6,[r1,#15]
-#endif
- ldmia sp!,{r4-r11}
-#if __ARM_ARCH__>=5
- bx lr @ bx lr
-#else
- tst lr,#1
- moveq pc,lr @ be binary compatible with V4, yet
- .word 0xe12fff1e @ interoperable with Thumb ISA:-)
-#endif
-.size poly1305_emit,.-poly1305_emit
-#if __ARM_MAX_ARCH__>=7
-.fpu neon
-
-.type poly1305_init_neon,%function
-.align 5
-poly1305_init_neon:
-.Lpoly1305_init_neon:
- ldr r3,[r0,#48] @ first table element
- cmp r3,#-1 @ is value impossible?
- bne .Lno_init_neon
-
- ldr r4,[r0,#20] @ load key base 2^32
- ldr r5,[r0,#24]
- ldr r6,[r0,#28]
- ldr r7,[r0,#32]
-
- and r2,r4,#0x03ffffff @ base 2^32 -> base 2^26
- mov r3,r4,lsr#26
- mov r4,r5,lsr#20
- orr r3,r3,r5,lsl#6
- mov r5,r6,lsr#14
- orr r4,r4,r6,lsl#12
- mov r6,r7,lsr#8
- orr r5,r5,r7,lsl#18
- and r3,r3,#0x03ffffff
- and r4,r4,#0x03ffffff
- and r5,r5,#0x03ffffff
-
- vdup.32 d0,r2 @ r^1 in both lanes
- add r2,r3,r3,lsl#2 @ *5
- vdup.32 d1,r3
- add r3,r4,r4,lsl#2
- vdup.32 d2,r2
- vdup.32 d3,r4
- add r4,r5,r5,lsl#2
- vdup.32 d4,r3
- vdup.32 d5,r5
- add r5,r6,r6,lsl#2
- vdup.32 d6,r4
- vdup.32 d7,r6
- vdup.32 d8,r5
-
- mov r5,#2 @ counter
-
-.Lsquare_neon:
- @@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@
- @ d0 = h0*r0 + h4*5*r1 + h3*5*r2 + h2*5*r3 + h1*5*r4
- @ d1 = h1*r0 + h0*r1 + h4*5*r2 + h3*5*r3 + h2*5*r4
- @ d2 = h2*r0 + h1*r1 + h0*r2 + h4*5*r3 + h3*5*r4
- @ d3 = h3*r0 + h2*r1 + h1*r2 + h0*r3 + h4*5*r4
- @ d4 = h4*r0 + h3*r1 + h2*r2 + h1*r3 + h0*r4
-
- vmull.u32 q5,d0,d0[1]
- vmull.u32 q6,d1,d0[1]
- vmull.u32 q7,d3,d0[1]
- vmull.u32 q8,d5,d0[1]
- vmull.u32 q9,d7,d0[1]
-
- vmlal.u32 q5,d7,d2[1]
- vmlal.u32 q6,d0,d1[1]
- vmlal.u32 q7,d1,d1[1]
- vmlal.u32 q8,d3,d1[1]
- vmlal.u32 q9,d5,d1[1]
-
- vmlal.u32 q5,d5,d4[1]
- vmlal.u32 q6,d7,d4[1]
- vmlal.u32 q8,d1,d3[1]
- vmlal.u32 q7,d0,d3[1]
- vmlal.u32 q9,d3,d3[1]
-
- vmlal.u32 q5,d3,d6[1]
- vmlal.u32 q8,d0,d5[1]
- vmlal.u32 q6,d5,d6[1]
- vmlal.u32 q7,d7,d6[1]
- vmlal.u32 q9,d1,d5[1]
-
- vmlal.u32 q8,d7,d8[1]
- vmlal.u32 q5,d1,d8[1]
- vmlal.u32 q6,d3,d8[1]
- vmlal.u32 q7,d5,d8[1]
- vmlal.u32 q9,d0,d7[1]
-
- @@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@
- @ lazy reduction as discussed in "NEON crypto" by D.J. Bernstein
- @ and P. Schwabe
- @
- @ H0>>+H1>>+H2>>+H3>>+H4
- @ H3>>+H4>>*5+H0>>+H1
- @
- @ Trivia.
- @
- @ Result of multiplication of n-bit number by m-bit number is
- @ n+m bits wide. However! Even though 2^n is a n+1-bit number,
- @ m-bit number multiplied by 2^n is still n+m bits wide.
- @
- @ Sum of two n-bit numbers is n+1 bits wide, sum of three - n+2,
- @ and so is sum of four. Sum of 2^m n-m-bit numbers and n-bit
- @ one is n+1 bits wide.
- @
- @ >>+ denotes Hnext += Hn>>26, Hn &= 0x3ffffff. This means that
- @ H0, H2, H3 are guaranteed to be 26 bits wide, while H1 and H4
- @ can be 27. However! In cases when their width exceeds 26 bits
- @ they are limited by 2^26+2^6. This in turn means that *sum*
- @ of the products with these values can still be viewed as sum
- @ of 52-bit numbers as long as the amount of addends is not a
- @ power of 2. For example,
- @
- @ H4 = H4*R0 + H3*R1 + H2*R2 + H1*R3 + H0 * R4,
- @
- @ which can't be larger than 5 * (2^26 + 2^6) * (2^26 + 2^6), or
- @ 5 * (2^52 + 2*2^32 + 2^12), which in turn is smaller than
- @ 8 * (2^52) or 2^55. However, the value is then multiplied by
- @ by 5, so we should be looking at 5 * 5 * (2^52 + 2^33 + 2^12),
- @ which is less than 32 * (2^52) or 2^57. And when processing
- @ data we are looking at triple as many addends...
- @
- @ In key setup procedure pre-reduced H0 is limited by 5*4+1 and
- @ 5*H4 - by 5*5 52-bit addends, or 57 bits. But when hashing the
- @ input H0 is limited by (5*4+1)*3 addends, or 58 bits, while
- @ 5*H4 by 5*5*3, or 59[!] bits. How is this relevant? vmlal.u32
- @ instruction accepts 2x32-bit input and writes 2x64-bit result.
- @ This means that result of reduction have to be compressed upon
- @ loop wrap-around. This can be done in the process of reduction
- @ to minimize amount of instructions [as well as amount of
- @ 128-bit instructions, which benefits low-end processors], but
- @ one has to watch for H2 (which is narrower than H0) and 5*H4
- @ not being wider than 58 bits, so that result of right shift
- @ by 26 bits fits in 32 bits. This is also useful on x86,
- @ because it allows to use paddd in place for paddq, which
- @ benefits Atom, where paddq is ridiculously slow.
-
- vshr.u64 q15,q8,#26
- vmovn.i64 d16,q8
- vshr.u64 q4,q5,#26
- vmovn.i64 d10,q5
- vadd.i64 q9,q9,q15 @ h3 -> h4
- vbic.i32 d16,#0xfc000000 @ &=0x03ffffff
- vadd.i64 q6,q6,q4 @ h0 -> h1
- vbic.i32 d10,#0xfc000000
-
- vshrn.u64 d30,q9,#26
- vmovn.i64 d18,q9
- vshr.u64 q4,q6,#26
- vmovn.i64 d12,q6
- vadd.i64 q7,q7,q4 @ h1 -> h2
- vbic.i32 d18,#0xfc000000
- vbic.i32 d12,#0xfc000000
-
- vadd.i32 d10,d10,d30
- vshl.u32 d30,d30,#2
- vshrn.u64 d8,q7,#26
- vmovn.i64 d14,q7
- vadd.i32 d10,d10,d30 @ h4 -> h0
- vadd.i32 d16,d16,d8 @ h2 -> h3
- vbic.i32 d14,#0xfc000000
-
- vshr.u32 d30,d10,#26
- vbic.i32 d10,#0xfc000000
- vshr.u32 d8,d16,#26
- vbic.i32 d16,#0xfc000000
- vadd.i32 d12,d12,d30 @ h0 -> h1
- vadd.i32 d18,d18,d8 @ h3 -> h4
-
- subs r5,r5,#1
- beq .Lsquare_break_neon
-
- add r6,r0,#(48+0*9*4)
- add r7,r0,#(48+1*9*4)
-
- vtrn.32 d0,d10 @ r^2:r^1
- vtrn.32 d3,d14
- vtrn.32 d5,d16
- vtrn.32 d1,d12
- vtrn.32 d7,d18
-
- vshl.u32 d4,d3,#2 @ *5
- vshl.u32 d6,d5,#2
- vshl.u32 d2,d1,#2
- vshl.u32 d8,d7,#2
- vadd.i32 d4,d4,d3
- vadd.i32 d2,d2,d1
- vadd.i32 d6,d6,d5
- vadd.i32 d8,d8,d7
-
- vst4.32 {d0[0],d1[0],d2[0],d3[0]},[r6]!
- vst4.32 {d0[1],d1[1],d2[1],d3[1]},[r7]!
- vst4.32 {d4[0],d5[0],d6[0],d7[0]},[r6]!
- vst4.32 {d4[1],d5[1],d6[1],d7[1]},[r7]!
- vst1.32 {d8[0]},[r6,:32]
- vst1.32 {d8[1]},[r7,:32]
-
- b .Lsquare_neon
-
-.align 4
-.Lsquare_break_neon:
- add r6,r0,#(48+2*4*9)
- add r7,r0,#(48+3*4*9)
-
- vmov d0,d10 @ r^4:r^3
- vshl.u32 d2,d12,#2 @ *5
- vmov d1,d12
- vshl.u32 d4,d14,#2
- vmov d3,d14
- vshl.u32 d6,d16,#2
- vmov d5,d16
- vshl.u32 d8,d18,#2
- vmov d7,d18
- vadd.i32 d2,d2,d12
- vadd.i32 d4,d4,d14
- vadd.i32 d6,d6,d16
- vadd.i32 d8,d8,d18
-
- vst4.32 {d0[0],d1[0],d2[0],d3[0]},[r6]!
- vst4.32 {d0[1],d1[1],d2[1],d3[1]},[r7]!
- vst4.32 {d4[0],d5[0],d6[0],d7[0]},[r6]!
- vst4.32 {d4[1],d5[1],d6[1],d7[1]},[r7]!
- vst1.32 {d8[0]},[r6]
- vst1.32 {d8[1]},[r7]
-
-.Lno_init_neon:
- bx lr @ bx lr
-.size poly1305_init_neon,.-poly1305_init_neon
-
-.type poly1305_blocks_neon,%function
-.align 5
-poly1305_blocks_neon:
-.Lpoly1305_blocks_neon:
- ldr ip,[r0,#36] @ is_base2_26
-
- cmp r2,#64
- blo .Lpoly1305_blocks
-
- stmdb sp!,{r4-r7}
- vstmdb sp!,{d8-d15} @ ABI specification says so
-
- tst ip,ip @ is_base2_26?
- bne .Lbase2_26_neon
-
- stmdb sp!,{r1-r3,lr}
- bl .Lpoly1305_init_neon
-
- ldr r4,[r0,#0] @ load hash value base 2^32
- ldr r5,[r0,#4]
- ldr r6,[r0,#8]
- ldr r7,[r0,#12]
- ldr ip,[r0,#16]
-
- and r2,r4,#0x03ffffff @ base 2^32 -> base 2^26
- mov r3,r4,lsr#26
- veor d10,d10,d10
- mov r4,r5,lsr#20
- orr r3,r3,r5,lsl#6
- veor d12,d12,d12
- mov r5,r6,lsr#14
- orr r4,r4,r6,lsl#12
- veor d14,d14,d14
- mov r6,r7,lsr#8
- orr r5,r5,r7,lsl#18
- veor d16,d16,d16
- and r3,r3,#0x03ffffff
- orr r6,r6,ip,lsl#24
- veor d18,d18,d18
- and r4,r4,#0x03ffffff
- mov r1,#1
- and r5,r5,#0x03ffffff
- str r1,[r0,#36] @ set is_base2_26
-
- vmov.32 d10[0],r2
- vmov.32 d12[0],r3
- vmov.32 d14[0],r4
- vmov.32 d16[0],r5
- vmov.32 d18[0],r6
- adr r5,.Lzeros
-
- ldmia sp!,{r1-r3,lr}
- b .Lhash_loaded
-
-.align 4
-.Lbase2_26_neon:
- @@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@
- @ load hash value
-
- veor d10,d10,d10
- veor d12,d12,d12
- veor d14,d14,d14
- veor d16,d16,d16
- veor d18,d18,d18
- vld4.32 {d10[0],d12[0],d14[0],d16[0]},[r0]!
- adr r5,.Lzeros
- vld1.32 {d18[0]},[r0]
- sub r0,r0,#16 @ rewind
-
-.Lhash_loaded:
- add r4,r1,#32
- mov r3,r3,lsl#24
- tst r2,#31
- beq .Leven
-
- vld4.32 {d20[0],d22[0],d24[0],d26[0]},[r1]!
- vmov.32 d28[0],r3
- sub r2,r2,#16
- add r4,r1,#32
-
-# ifdef __ARMEB__
- vrev32.8 q10,q10
- vrev32.8 q13,q13
- vrev32.8 q11,q11
- vrev32.8 q12,q12
-# endif
- vsri.u32 d28,d26,#8 @ base 2^32 -> base 2^26
- vshl.u32 d26,d26,#18
-
- vsri.u32 d26,d24,#14
- vshl.u32 d24,d24,#12
- vadd.i32 d29,d28,d18 @ add hash value and move to #hi
-
- vbic.i32 d26,#0xfc000000
- vsri.u32 d24,d22,#20
- vshl.u32 d22,d22,#6
-
- vbic.i32 d24,#0xfc000000
- vsri.u32 d22,d20,#26
- vadd.i32 d27,d26,d16
-
- vbic.i32 d20,#0xfc000000
- vbic.i32 d22,#0xfc000000
- vadd.i32 d25,d24,d14
-
- vadd.i32 d21,d20,d10
- vadd.i32 d23,d22,d12
-
- mov r7,r5
- add r6,r0,#48
-
- cmp r2,r2
- b .Long_tail
-
-.align 4
-.Leven:
- subs r2,r2,#64
- it lo
- movlo r4,r5
-
- vmov.i32 q14,#1<<24 @ padbit, yes, always
- vld4.32 {d20,d22,d24,d26},[r1] @ inp[0:1]
- add r1,r1,#64
- vld4.32 {d21,d23,d25,d27},[r4] @ inp[2:3] (or 0)
- add r4,r4,#64
- itt hi
- addhi r7,r0,#(48+1*9*4)
- addhi r6,r0,#(48+3*9*4)
-
-# ifdef __ARMEB__
- vrev32.8 q10,q10
- vrev32.8 q13,q13
- vrev32.8 q11,q11
- vrev32.8 q12,q12
-# endif
- vsri.u32 q14,q13,#8 @ base 2^32 -> base 2^26
- vshl.u32 q13,q13,#18
-
- vsri.u32 q13,q12,#14
- vshl.u32 q12,q12,#12
-
- vbic.i32 q13,#0xfc000000
- vsri.u32 q12,q11,#20
- vshl.u32 q11,q11,#6
-
- vbic.i32 q12,#0xfc000000
- vsri.u32 q11,q10,#26
-
- vbic.i32 q10,#0xfc000000
- vbic.i32 q11,#0xfc000000
-
- bls .Lskip_loop
-
- vld4.32 {d0[1],d1[1],d2[1],d3[1]},[r7]! @ load r^2
- vld4.32 {d0[0],d1[0],d2[0],d3[0]},[r6]! @ load r^4
- vld4.32 {d4[1],d5[1],d6[1],d7[1]},[r7]!
- vld4.32 {d4[0],d5[0],d6[0],d7[0]},[r6]!
- b .Loop_neon
-
-.align 5
-.Loop_neon:
- @@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@
- @ ((inp[0]*r^4+inp[2]*r^2+inp[4])*r^4+inp[6]*r^2
- @ ((inp[1]*r^4+inp[3]*r^2+inp[5])*r^3+inp[7]*r
- @ ___________________/
- @ ((inp[0]*r^4+inp[2]*r^2+inp[4])*r^4+inp[6]*r^2+inp[8])*r^2
- @ ((inp[1]*r^4+inp[3]*r^2+inp[5])*r^4+inp[7]*r^2+inp[9])*r
- @ ___________________/ ____________________/
- @
- @ Note that we start with inp[2:3]*r^2. This is because it
- @ doesn't depend on reduction in previous iteration.
- @@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@
- @ d4 = h4*r0 + h3*r1 + h2*r2 + h1*r3 + h0*r4
- @ d3 = h3*r0 + h2*r1 + h1*r2 + h0*r3 + h4*5*r4
- @ d2 = h2*r0 + h1*r1 + h0*r2 + h4*5*r3 + h3*5*r4
- @ d1 = h1*r0 + h0*r1 + h4*5*r2 + h3*5*r3 + h2*5*r4
- @ d0 = h0*r0 + h4*5*r1 + h3*5*r2 + h2*5*r3 + h1*5*r4
-
- @@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@
- @ inp[2:3]*r^2
-
- vadd.i32 d24,d24,d14 @ accumulate inp[0:1]
- vmull.u32 q7,d25,d0[1]
- vadd.i32 d20,d20,d10
- vmull.u32 q5,d21,d0[1]
- vadd.i32 d26,d26,d16
- vmull.u32 q8,d27,d0[1]
- vmlal.u32 q7,d23,d1[1]
- vadd.i32 d22,d22,d12
- vmull.u32 q6,d23,d0[1]
-
- vadd.i32 d28,d28,d18
- vmull.u32 q9,d29,d0[1]
- subs r2,r2,#64
- vmlal.u32 q5,d29,d2[1]
- it lo
- movlo r4,r5
- vmlal.u32 q8,d25,d1[1]
- vld1.32 d8[1],[r7,:32]
- vmlal.u32 q6,d21,d1[1]
- vmlal.u32 q9,d27,d1[1]
-
- vmlal.u32 q5,d27,d4[1]
- vmlal.u32 q8,d23,d3[1]
- vmlal.u32 q9,d25,d3[1]
- vmlal.u32 q6,d29,d4[1]
- vmlal.u32 q7,d21,d3[1]
-
- vmlal.u32 q8,d21,d5[1]
- vmlal.u32 q5,d25,d6[1]
- vmlal.u32 q9,d23,d5[1]
- vmlal.u32 q6,d27,d6[1]
- vmlal.u32 q7,d29,d6[1]
-
- vmlal.u32 q8,d29,d8[1]
- vmlal.u32 q5,d23,d8[1]
- vmlal.u32 q9,d21,d7[1]
- vmlal.u32 q6,d25,d8[1]
- vmlal.u32 q7,d27,d8[1]
-
- vld4.32 {d21,d23,d25,d27},[r4] @ inp[2:3] (or 0)
- add r4,r4,#64
-
- @@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@
- @ (hash+inp[0:1])*r^4 and accumulate
-
- vmlal.u32 q8,d26,d0[0]
- vmlal.u32 q5,d20,d0[0]
- vmlal.u32 q9,d28,d0[0]
- vmlal.u32 q6,d22,d0[0]
- vmlal.u32 q7,d24,d0[0]
- vld1.32 d8[0],[r6,:32]
-
- vmlal.u32 q8,d24,d1[0]
- vmlal.u32 q5,d28,d2[0]
- vmlal.u32 q9,d26,d1[0]
- vmlal.u32 q6,d20,d1[0]
- vmlal.u32 q7,d22,d1[0]
-
- vmlal.u32 q8,d22,d3[0]
- vmlal.u32 q5,d26,d4[0]
- vmlal.u32 q9,d24,d3[0]
- vmlal.u32 q6,d28,d4[0]
- vmlal.u32 q7,d20,d3[0]
-
- vmlal.u32 q8,d20,d5[0]
- vmlal.u32 q5,d24,d6[0]
- vmlal.u32 q9,d22,d5[0]
- vmlal.u32 q6,d26,d6[0]
- vmlal.u32 q8,d28,d8[0]
-
- vmlal.u32 q7,d28,d6[0]
- vmlal.u32 q5,d22,d8[0]
- vmlal.u32 q9,d20,d7[0]
- vmov.i32 q14,#1<<24 @ padbit, yes, always
- vmlal.u32 q6,d24,d8[0]
- vmlal.u32 q7,d26,d8[0]
-
- vld4.32 {d20,d22,d24,d26},[r1] @ inp[0:1]
- add r1,r1,#64
-# ifdef __ARMEB__
- vrev32.8 q10,q10
- vrev32.8 q11,q11
- vrev32.8 q12,q12
- vrev32.8 q13,q13
-# endif
-
- @@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@
- @ lazy reduction interleaved with base 2^32 -> base 2^26 of
- @ inp[0:3] previously loaded to q10-q13 and smashed to q10-q14.
-
- vshr.u64 q15,q8,#26
- vmovn.i64 d16,q8
- vshr.u64 q4,q5,#26
- vmovn.i64 d10,q5
- vadd.i64 q9,q9,q15 @ h3 -> h4
- vbic.i32 d16,#0xfc000000
- vsri.u32 q14,q13,#8 @ base 2^32 -> base 2^26
- vadd.i64 q6,q6,q4 @ h0 -> h1
- vshl.u32 q13,q13,#18
- vbic.i32 d10,#0xfc000000
-
- vshrn.u64 d30,q9,#26
- vmovn.i64 d18,q9
- vshr.u64 q4,q6,#26
- vmovn.i64 d12,q6
- vadd.i64 q7,q7,q4 @ h1 -> h2
- vsri.u32 q13,q12,#14
- vbic.i32 d18,#0xfc000000
- vshl.u32 q12,q12,#12
- vbic.i32 d12,#0xfc000000
-
- vadd.i32 d10,d10,d30
- vshl.u32 d30,d30,#2
- vbic.i32 q13,#0xfc000000
- vshrn.u64 d8,q7,#26
- vmovn.i64 d14,q7
- vaddl.u32 q5,d10,d30 @ h4 -> h0 [widen for a sec]
- vsri.u32 q12,q11,#20
- vadd.i32 d16,d16,d8 @ h2 -> h3
- vshl.u32 q11,q11,#6
- vbic.i32 d14,#0xfc000000
- vbic.i32 q12,#0xfc000000
-
- vshrn.u64 d30,q5,#26 @ re-narrow
- vmovn.i64 d10,q5
- vsri.u32 q11,q10,#26
- vbic.i32 q10,#0xfc000000
- vshr.u32 d8,d16,#26
- vbic.i32 d16,#0xfc000000
- vbic.i32 d10,#0xfc000000
- vadd.i32 d12,d12,d30 @ h0 -> h1
- vadd.i32 d18,d18,d8 @ h3 -> h4
- vbic.i32 q11,#0xfc000000
-
- bhi .Loop_neon
-
-.Lskip_loop:
- @@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@
- @ multiply (inp[0:1]+hash) or inp[2:3] by r^2:r^1
-
- add r7,r0,#(48+0*9*4)
- add r6,r0,#(48+1*9*4)
- adds r2,r2,#32
- it ne
- movne r2,#0
- bne .Long_tail
-
- vadd.i32 d25,d24,d14 @ add hash value and move to #hi
- vadd.i32 d21,d20,d10
- vadd.i32 d27,d26,d16
- vadd.i32 d23,d22,d12
- vadd.i32 d29,d28,d18
-
-.Long_tail:
- vld4.32 {d0[1],d1[1],d2[1],d3[1]},[r7]! @ load r^1
- vld4.32 {d0[0],d1[0],d2[0],d3[0]},[r6]! @ load r^2
-
- vadd.i32 d24,d24,d14 @ can be redundant
- vmull.u32 q7,d25,d0
- vadd.i32 d20,d20,d10
- vmull.u32 q5,d21,d0
- vadd.i32 d26,d26,d16
- vmull.u32 q8,d27,d0
- vadd.i32 d22,d22,d12
- vmull.u32 q6,d23,d0
- vadd.i32 d28,d28,d18
- vmull.u32 q9,d29,d0
-
- vmlal.u32 q5,d29,d2
- vld4.32 {d4[1],d5[1],d6[1],d7[1]},[r7]!
- vmlal.u32 q8,d25,d1
- vld4.32 {d4[0],d5[0],d6[0],d7[0]},[r6]!
- vmlal.u32 q6,d21,d1
- vmlal.u32 q9,d27,d1
- vmlal.u32 q7,d23,d1
-
- vmlal.u32 q8,d23,d3
- vld1.32 d8[1],[r7,:32]
- vmlal.u32 q5,d27,d4
- vld1.32 d8[0],[r6,:32]
- vmlal.u32 q9,d25,d3
- vmlal.u32 q6,d29,d4
- vmlal.u32 q7,d21,d3
-
- vmlal.u32 q8,d21,d5
- it ne
- addne r7,r0,#(48+2*9*4)
- vmlal.u32 q5,d25,d6
- it ne
- addne r6,r0,#(48+3*9*4)
- vmlal.u32 q9,d23,d5
- vmlal.u32 q6,d27,d6
- vmlal.u32 q7,d29,d6
-
- vmlal.u32 q8,d29,d8
- vorn q0,q0,q0 @ all-ones, can be redundant
- vmlal.u32 q5,d23,d8
- vshr.u64 q0,q0,#38
- vmlal.u32 q9,d21,d7
- vmlal.u32 q6,d25,d8
- vmlal.u32 q7,d27,d8
-
- beq .Lshort_tail
-
- @@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@
- @ (hash+inp[0:1])*r^4:r^3 and accumulate
-
- vld4.32 {d0[1],d1[1],d2[1],d3[1]},[r7]! @ load r^3
- vld4.32 {d0[0],d1[0],d2[0],d3[0]},[r6]! @ load r^4
-
- vmlal.u32 q7,d24,d0
- vmlal.u32 q5,d20,d0
- vmlal.u32 q8,d26,d0
- vmlal.u32 q6,d22,d0
- vmlal.u32 q9,d28,d0
-
- vmlal.u32 q5,d28,d2
- vld4.32 {d4[1],d5[1],d6[1],d7[1]},[r7]!
- vmlal.u32 q8,d24,d1
- vld4.32 {d4[0],d5[0],d6[0],d7[0]},[r6]!
- vmlal.u32 q6,d20,d1
- vmlal.u32 q9,d26,d1
- vmlal.u32 q7,d22,d1
-
- vmlal.u32 q8,d22,d3
- vld1.32 d8[1],[r7,:32]
- vmlal.u32 q5,d26,d4
- vld1.32 d8[0],[r6,:32]
- vmlal.u32 q9,d24,d3
- vmlal.u32 q6,d28,d4
- vmlal.u32 q7,d20,d3
-
- vmlal.u32 q8,d20,d5
- vmlal.u32 q5,d24,d6
- vmlal.u32 q9,d22,d5
- vmlal.u32 q6,d26,d6
- vmlal.u32 q7,d28,d6
-
- vmlal.u32 q8,d28,d8
- vorn q0,q0,q0 @ all-ones
- vmlal.u32 q5,d22,d8
- vshr.u64 q0,q0,#38
- vmlal.u32 q9,d20,d7
- vmlal.u32 q6,d24,d8
- vmlal.u32 q7,d26,d8
-
-.Lshort_tail:
- @@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@
- @ horizontal addition
-
- vadd.i64 d16,d16,d17
- vadd.i64 d10,d10,d11
- vadd.i64 d18,d18,d19
- vadd.i64 d12,d12,d13
- vadd.i64 d14,d14,d15
-
- @@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@
- @ lazy reduction, but without narrowing
-
- vshr.u64 q15,q8,#26
- vand.i64 q8,q8,q0
- vshr.u64 q4,q5,#26
- vand.i64 q5,q5,q0
- vadd.i64 q9,q9,q15 @ h3 -> h4
- vadd.i64 q6,q6,q4 @ h0 -> h1
-
- vshr.u64 q15,q9,#26
- vand.i64 q9,q9,q0
- vshr.u64 q4,q6,#26
- vand.i64 q6,q6,q0
- vadd.i64 q7,q7,q4 @ h1 -> h2
-
- vadd.i64 q5,q5,q15
- vshl.u64 q15,q15,#2
- vshr.u64 q4,q7,#26
- vand.i64 q7,q7,q0
- vadd.i64 q5,q5,q15 @ h4 -> h0
- vadd.i64 q8,q8,q4 @ h2 -> h3
-
- vshr.u64 q15,q5,#26
- vand.i64 q5,q5,q0
- vshr.u64 q4,q8,#26
- vand.i64 q8,q8,q0
- vadd.i64 q6,q6,q15 @ h0 -> h1
- vadd.i64 q9,q9,q4 @ h3 -> h4
-
- cmp r2,#0
- bne .Leven
-
- @@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@
- @ store hash value
-
- vst4.32 {d10[0],d12[0],d14[0],d16[0]},[r0]!
- vst1.32 {d18[0]},[r0]
-
- vldmia sp!,{d8-d15} @ epilogue
- ldmia sp!,{r4-r7}
- bx lr @ bx lr
-.size poly1305_blocks_neon,.-poly1305_blocks_neon
-
-.align 5
-.Lzeros:
-.long 0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0
-#ifndef __KERNEL__
-.LOPENSSL_armcap:
-# ifdef _WIN32
-.word OPENSSL_armcap_P
-# else
-.word OPENSSL_armcap_P-.Lpoly1305_init
-# endif
-.comm OPENSSL_armcap_P,4,4
-.hidden OPENSSL_armcap_P
-#endif
-#endif
-.asciz "Poly1305 for ARMv4/NEON, CRYPTOGAMS by @dot-asm"
-.align 2
diff --git a/arch/arm/crypto/sha256-core.S_shipped b/arch/arm/crypto/sha256-core.S_shipped
deleted file mode 100644
index 6363014a50d7..000000000000
--- a/arch/arm/crypto/sha256-core.S_shipped
+++ /dev/null
@@ -1,2816 +0,0 @@
-@ SPDX-License-Identifier: GPL-2.0
-
-@ This code is taken from the OpenSSL project but the author (Andy Polyakov)
-@ has relicensed it under the GPLv2. Therefore 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.
-@
-@ The original headers, including the original license headers, are
-@ included below for completeness.
-
-@ ====================================================================
-@ Written by Andy Polyakov <appro@openssl.org> for the OpenSSL
-@ project. The module is, however, dual licensed under OpenSSL and
-@ CRYPTOGAMS licenses depending on where you obtain it. For further
-@ details see https://www.openssl.org/~appro/cryptogams/.
-@ ====================================================================
-
-@ SHA256 block procedure for ARMv4. May 2007.
-
-@ Performance is ~2x better than gcc 3.4 generated code and in "abso-
-@ lute" terms is ~2250 cycles per 64-byte block or ~35 cycles per
-@ byte [on single-issue Xscale PXA250 core].
-
-@ July 2010.
-@
-@ Rescheduling for dual-issue pipeline resulted in 22% improvement on
-@ Cortex A8 core and ~20 cycles per processed byte.
-
-@ February 2011.
-@
-@ Profiler-assisted and platform-specific optimization resulted in 16%
-@ improvement on Cortex A8 core and ~15.4 cycles per processed byte.
-
-@ September 2013.
-@
-@ Add NEON implementation. On Cortex A8 it was measured to process one
-@ byte in 12.5 cycles or 23% faster than integer-only code. Snapdragon
-@ S4 does it in 12.5 cycles too, but it's 50% faster than integer-only
-@ code (meaning that latter performs sub-optimally, nothing was done
-@ about it).
-
-@ May 2014.
-@
-@ Add ARMv8 code path performing at 2.0 cpb on Apple A7.
-
-#ifndef __KERNEL__
-# include "arm_arch.h"
-#else
-# define __ARM_ARCH__ __LINUX_ARM_ARCH__
-# define __ARM_MAX_ARCH__ 7
-#endif
-
-.text
-#if __ARM_ARCH__<7
-.code 32
-#else
-.syntax unified
-# ifdef __thumb2__
-.thumb
-# else
-.code 32
-# endif
-#endif
-
-.type K256,%object
-.align 5
-K256:
-.word 0x428a2f98,0x71374491,0xb5c0fbcf,0xe9b5dba5
-.word 0x3956c25b,0x59f111f1,0x923f82a4,0xab1c5ed5
-.word 0xd807aa98,0x12835b01,0x243185be,0x550c7dc3
-.word 0x72be5d74,0x80deb1fe,0x9bdc06a7,0xc19bf174
-.word 0xe49b69c1,0xefbe4786,0x0fc19dc6,0x240ca1cc
-.word 0x2de92c6f,0x4a7484aa,0x5cb0a9dc,0x76f988da
-.word 0x983e5152,0xa831c66d,0xb00327c8,0xbf597fc7
-.word 0xc6e00bf3,0xd5a79147,0x06ca6351,0x14292967
-.word 0x27b70a85,0x2e1b2138,0x4d2c6dfc,0x53380d13
-.word 0x650a7354,0x766a0abb,0x81c2c92e,0x92722c85
-.word 0xa2bfe8a1,0xa81a664b,0xc24b8b70,0xc76c51a3
-.word 0xd192e819,0xd6990624,0xf40e3585,0x106aa070
-.word 0x19a4c116,0x1e376c08,0x2748774c,0x34b0bcb5
-.word 0x391c0cb3,0x4ed8aa4a,0x5b9cca4f,0x682e6ff3
-.word 0x748f82ee,0x78a5636f,0x84c87814,0x8cc70208
-.word 0x90befffa,0xa4506ceb,0xbef9a3f7,0xc67178f2
-.size K256,.-K256
-.word 0 @ terminator
-#if __ARM_MAX_ARCH__>=7 && !defined(__KERNEL__)
-.LOPENSSL_armcap:
-.word OPENSSL_armcap_P-sha256_block_data_order
-#endif
-.align 5
-
-.global sha256_block_data_order
-.type sha256_block_data_order,%function
-sha256_block_data_order:
-.Lsha256_block_data_order:
-#if __ARM_ARCH__<7
- sub r3,pc,#8 @ sha256_block_data_order
-#else
- adr r3,.Lsha256_block_data_order
-#endif
-#if __ARM_MAX_ARCH__>=7 && !defined(__KERNEL__)
- ldr r12,.LOPENSSL_armcap
- ldr r12,[r3,r12] @ OPENSSL_armcap_P
- tst r12,#ARMV8_SHA256
- bne .LARMv8
- tst r12,#ARMV7_NEON
- bne .LNEON
-#endif
- add r2,r1,r2,lsl#6 @ len to point at the end of inp
- stmdb sp!,{r0,r1,r2,r4-r11,lr}
- ldmia r0,{r4,r5,r6,r7,r8,r9,r10,r11}
- sub r14,r3,#256+32 @ K256
- sub sp,sp,#16*4 @ alloca(X[16])
-.Loop:
-# if __ARM_ARCH__>=7
- ldr r2,[r1],#4
-# else
- ldrb r2,[r1,#3]
-# endif
- eor r3,r5,r6 @ magic
- eor r12,r12,r12
-#if __ARM_ARCH__>=7
- @ ldr r2,[r1],#4 @ 0
-# if 0==15
- str r1,[sp,#17*4] @ make room for r1
-# endif
- eor r0,r8,r8,ror#5
- add r4,r4,r12 @ h+=Maj(a,b,c) from the past
- eor r0,r0,r8,ror#19 @ Sigma1(e)
-# ifndef __ARMEB__
- rev r2,r2
-# endif
-#else
- @ ldrb r2,[r1,#3] @ 0
- add r4,r4,r12 @ h+=Maj(a,b,c) from the past
- ldrb r12,[r1,#2]
- ldrb r0,[r1,#1]
- orr r2,r2,r12,lsl#8
- ldrb r12,[r1],#4
- orr r2,r2,r0,lsl#16
-# if 0==15
- str r1,[sp,#17*4] @ make room for r1
-# endif
- eor r0,r8,r8,ror#5
- orr r2,r2,r12,lsl#24
- eor r0,r0,r8,ror#19 @ Sigma1(e)
-#endif
- ldr r12,[r14],#4 @ *K256++
- add r11,r11,r2 @ h+=X[i]
- str r2,[sp,#0*4]
- eor r2,r9,r10
- add r11,r11,r0,ror#6 @ h+=Sigma1(e)
- and r2,r2,r8
- add r11,r11,r12 @ h+=K256[i]
- eor r2,r2,r10 @ Ch(e,f,g)
- eor r0,r4,r4,ror#11
- add r11,r11,r2 @ h+=Ch(e,f,g)
-#if 0==31
- and r12,r12,#0xff
- cmp r12,#0xf2 @ done?
-#endif
-#if 0<15
-# if __ARM_ARCH__>=7
- ldr r2,[r1],#4 @ prefetch
-# else
- ldrb r2,[r1,#3]
-# endif
- eor r12,r4,r5 @ a^b, b^c in next round
-#else
- ldr r2,[sp,#2*4] @ from future BODY_16_xx
- eor r12,r4,r5 @ a^b, b^c in next round
- ldr r1,[sp,#15*4] @ from future BODY_16_xx
-#endif
- eor r0,r0,r4,ror#20 @ Sigma0(a)
- and r3,r3,r12 @ (b^c)&=(a^b)
- add r7,r7,r11 @ d+=h
- eor r3,r3,r5 @ Maj(a,b,c)
- add r11,r11,r0,ror#2 @ h+=Sigma0(a)
- @ add r11,r11,r3 @ h+=Maj(a,b,c)
-#if __ARM_ARCH__>=7
- @ ldr r2,[r1],#4 @ 1
-# if 1==15
- str r1,[sp,#17*4] @ make room for r1
-# endif
- eor r0,r7,r7,ror#5
- add r11,r11,r3 @ h+=Maj(a,b,c) from the past
- eor r0,r0,r7,ror#19 @ Sigma1(e)
-# ifndef __ARMEB__
- rev r2,r2
-# endif
-#else
- @ ldrb r2,[r1,#3] @ 1
- add r11,r11,r3 @ h+=Maj(a,b,c) from the past
- ldrb r3,[r1,#2]
- ldrb r0,[r1,#1]
- orr r2,r2,r3,lsl#8
- ldrb r3,[r1],#4
- orr r2,r2,r0,lsl#16
-# if 1==15
- str r1,[sp,#17*4] @ make room for r1
-# endif
- eor r0,r7,r7,ror#5
- orr r2,r2,r3,lsl#24
- eor r0,r0,r7,ror#19 @ Sigma1(e)
-#endif
- ldr r3,[r14],#4 @ *K256++
- add r10,r10,r2 @ h+=X[i]
- str r2,[sp,#1*4]
- eor r2,r8,r9
- add r10,r10,r0,ror#6 @ h+=Sigma1(e)
- and r2,r2,r7
- add r10,r10,r3 @ h+=K256[i]
- eor r2,r2,r9 @ Ch(e,f,g)
- eor r0,r11,r11,ror#11
- add r10,r10,r2 @ h+=Ch(e,f,g)
-#if 1==31
- and r3,r3,#0xff
- cmp r3,#0xf2 @ done?
-#endif
-#if 1<15
-# if __ARM_ARCH__>=7
- ldr r2,[r1],#4 @ prefetch
-# else
- ldrb r2,[r1,#3]
-# endif
- eor r3,r11,r4 @ a^b, b^c in next round
-#else
- ldr r2,[sp,#3*4] @ from future BODY_16_xx
- eor r3,r11,r4 @ a^b, b^c in next round
- ldr r1,[sp,#0*4] @ from future BODY_16_xx
-#endif
- eor r0,r0,r11,ror#20 @ Sigma0(a)
- and r12,r12,r3 @ (b^c)&=(a^b)
- add r6,r6,r10 @ d+=h
- eor r12,r12,r4 @ Maj(a,b,c)
- add r10,r10,r0,ror#2 @ h+=Sigma0(a)
- @ add r10,r10,r12 @ h+=Maj(a,b,c)
-#if __ARM_ARCH__>=7
- @ ldr r2,[r1],#4 @ 2
-# if 2==15
- str r1,[sp,#17*4] @ make room for r1
-# endif
- eor r0,r6,r6,ror#5
- add r10,r10,r12 @ h+=Maj(a,b,c) from the past
- eor r0,r0,r6,ror#19 @ Sigma1(e)
-# ifndef __ARMEB__
- rev r2,r2
-# endif
-#else
- @ ldrb r2,[r1,#3] @ 2
- add r10,r10,r12 @ h+=Maj(a,b,c) from the past
- ldrb r12,[r1,#2]
- ldrb r0,[r1,#1]
- orr r2,r2,r12,lsl#8
- ldrb r12,[r1],#4
- orr r2,r2,r0,lsl#16
-# if 2==15
- str r1,[sp,#17*4] @ make room for r1
-# endif
- eor r0,r6,r6,ror#5
- orr r2,r2,r12,lsl#24
- eor r0,r0,r6,ror#19 @ Sigma1(e)
-#endif
- ldr r12,[r14],#4 @ *K256++
- add r9,r9,r2 @ h+=X[i]
- str r2,[sp,#2*4]
- eor r2,r7,r8
- add r9,r9,r0,ror#6 @ h+=Sigma1(e)
- and r2,r2,r6
- add r9,r9,r12 @ h+=K256[i]
- eor r2,r2,r8 @ Ch(e,f,g)
- eor r0,r10,r10,ror#11
- add r9,r9,r2 @ h+=Ch(e,f,g)
-#if 2==31
- and r12,r12,#0xff
- cmp r12,#0xf2 @ done?
-#endif
-#if 2<15
-# if __ARM_ARCH__>=7
- ldr r2,[r1],#4 @ prefetch
-# else
- ldrb r2,[r1,#3]
-# endif
- eor r12,r10,r11 @ a^b, b^c in next round
-#else
- ldr r2,[sp,#4*4] @ from future BODY_16_xx
- eor r12,r10,r11 @ a^b, b^c in next round
- ldr r1,[sp,#1*4] @ from future BODY_16_xx
-#endif
- eor r0,r0,r10,ror#20 @ Sigma0(a)
- and r3,r3,r12 @ (b^c)&=(a^b)
- add r5,r5,r9 @ d+=h
- eor r3,r3,r11 @ Maj(a,b,c)
- add r9,r9,r0,ror#2 @ h+=Sigma0(a)
- @ add r9,r9,r3 @ h+=Maj(a,b,c)
-#if __ARM_ARCH__>=7
- @ ldr r2,[r1],#4 @ 3
-# if 3==15
- str r1,[sp,#17*4] @ make room for r1
-# endif
- eor r0,r5,r5,ror#5
- add r9,r9,r3 @ h+=Maj(a,b,c) from the past
- eor r0,r0,r5,ror#19 @ Sigma1(e)
-# ifndef __ARMEB__
- rev r2,r2
-# endif
-#else
- @ ldrb r2,[r1,#3] @ 3
- add r9,r9,r3 @ h+=Maj(a,b,c) from the past
- ldrb r3,[r1,#2]
- ldrb r0,[r1,#1]
- orr r2,r2,r3,lsl#8
- ldrb r3,[r1],#4
- orr r2,r2,r0,lsl#16
-# if 3==15
- str r1,[sp,#17*4] @ make room for r1
-# endif
- eor r0,r5,r5,ror#5
- orr r2,r2,r3,lsl#24
- eor r0,r0,r5,ror#19 @ Sigma1(e)
-#endif
- ldr r3,[r14],#4 @ *K256++
- add r8,r8,r2 @ h+=X[i]
- str r2,[sp,#3*4]
- eor r2,r6,r7
- add r8,r8,r0,ror#6 @ h+=Sigma1(e)
- and r2,r2,r5
- add r8,r8,r3 @ h+=K256[i]
- eor r2,r2,r7 @ Ch(e,f,g)
- eor r0,r9,r9,ror#11
- add r8,r8,r2 @ h+=Ch(e,f,g)
-#if 3==31
- and r3,r3,#0xff
- cmp r3,#0xf2 @ done?
-#endif
-#if 3<15
-# if __ARM_ARCH__>=7
- ldr r2,[r1],#4 @ prefetch
-# else
- ldrb r2,[r1,#3]
-# endif
- eor r3,r9,r10 @ a^b, b^c in next round
-#else
- ldr r2,[sp,#5*4] @ from future BODY_16_xx
- eor r3,r9,r10 @ a^b, b^c in next round
- ldr r1,[sp,#2*4] @ from future BODY_16_xx
-#endif
- eor r0,r0,r9,ror#20 @ Sigma0(a)
- and r12,r12,r3 @ (b^c)&=(a^b)
- add r4,r4,r8 @ d+=h
- eor r12,r12,r10 @ Maj(a,b,c)
- add r8,r8,r0,ror#2 @ h+=Sigma0(a)
- @ add r8,r8,r12 @ h+=Maj(a,b,c)
-#if __ARM_ARCH__>=7
- @ ldr r2,[r1],#4 @ 4
-# if 4==15
- str r1,[sp,#17*4] @ make room for r1
-# endif
- eor r0,r4,r4,ror#5
- add r8,r8,r12 @ h+=Maj(a,b,c) from the past
- eor r0,r0,r4,ror#19 @ Sigma1(e)
-# ifndef __ARMEB__
- rev r2,r2
-# endif
-#else
- @ ldrb r2,[r1,#3] @ 4
- add r8,r8,r12 @ h+=Maj(a,b,c) from the past
- ldrb r12,[r1,#2]
- ldrb r0,[r1,#1]
- orr r2,r2,r12,lsl#8
- ldrb r12,[r1],#4
- orr r2,r2,r0,lsl#16
-# if 4==15
- str r1,[sp,#17*4] @ make room for r1
-# endif
- eor r0,r4,r4,ror#5
- orr r2,r2,r12,lsl#24
- eor r0,r0,r4,ror#19 @ Sigma1(e)
-#endif
- ldr r12,[r14],#4 @ *K256++
- add r7,r7,r2 @ h+=X[i]
- str r2,[sp,#4*4]
- eor r2,r5,r6
- add r7,r7,r0,ror#6 @ h+=Sigma1(e)
- and r2,r2,r4
- add r7,r7,r12 @ h+=K256[i]
- eor r2,r2,r6 @ Ch(e,f,g)
- eor r0,r8,r8,ror#11
- add r7,r7,r2 @ h+=Ch(e,f,g)
-#if 4==31
- and r12,r12,#0xff
- cmp r12,#0xf2 @ done?
-#endif
-#if 4<15
-# if __ARM_ARCH__>=7
- ldr r2,[r1],#4 @ prefetch
-# else
- ldrb r2,[r1,#3]
-# endif
- eor r12,r8,r9 @ a^b, b^c in next round
-#else
- ldr r2,[sp,#6*4] @ from future BODY_16_xx
- eor r12,r8,r9 @ a^b, b^c in next round
- ldr r1,[sp,#3*4] @ from future BODY_16_xx
-#endif
- eor r0,r0,r8,ror#20 @ Sigma0(a)
- and r3,r3,r12 @ (b^c)&=(a^b)
- add r11,r11,r7 @ d+=h
- eor r3,r3,r9 @ Maj(a,b,c)
- add r7,r7,r0,ror#2 @ h+=Sigma0(a)
- @ add r7,r7,r3 @ h+=Maj(a,b,c)
-#if __ARM_ARCH__>=7
- @ ldr r2,[r1],#4 @ 5
-# if 5==15
- str r1,[sp,#17*4] @ make room for r1
-# endif
- eor r0,r11,r11,ror#5
- add r7,r7,r3 @ h+=Maj(a,b,c) from the past
- eor r0,r0,r11,ror#19 @ Sigma1(e)
-# ifndef __ARMEB__
- rev r2,r2
-# endif
-#else
- @ ldrb r2,[r1,#3] @ 5
- add r7,r7,r3 @ h+=Maj(a,b,c) from the past
- ldrb r3,[r1,#2]
- ldrb r0,[r1,#1]
- orr r2,r2,r3,lsl#8
- ldrb r3,[r1],#4
- orr r2,r2,r0,lsl#16
-# if 5==15
- str r1,[sp,#17*4] @ make room for r1
-# endif
- eor r0,r11,r11,ror#5
- orr r2,r2,r3,lsl#24
- eor r0,r0,r11,ror#19 @ Sigma1(e)
-#endif
- ldr r3,[r14],#4 @ *K256++
- add r6,r6,r2 @ h+=X[i]
- str r2,[sp,#5*4]
- eor r2,r4,r5
- add r6,r6,r0,ror#6 @ h+=Sigma1(e)
- and r2,r2,r11
- add r6,r6,r3 @ h+=K256[i]
- eor r2,r2,r5 @ Ch(e,f,g)
- eor r0,r7,r7,ror#11
- add r6,r6,r2 @ h+=Ch(e,f,g)
-#if 5==31
- and r3,r3,#0xff
- cmp r3,#0xf2 @ done?
-#endif
-#if 5<15
-# if __ARM_ARCH__>=7
- ldr r2,[r1],#4 @ prefetch
-# else
- ldrb r2,[r1,#3]
-# endif
- eor r3,r7,r8 @ a^b, b^c in next round
-#else
- ldr r2,[sp,#7*4] @ from future BODY_16_xx
- eor r3,r7,r8 @ a^b, b^c in next round
- ldr r1,[sp,#4*4] @ from future BODY_16_xx
-#endif
- eor r0,r0,r7,ror#20 @ Sigma0(a)
- and r12,r12,r3 @ (b^c)&=(a^b)
- add r10,r10,r6 @ d+=h
- eor r12,r12,r8 @ Maj(a,b,c)
- add r6,r6,r0,ror#2 @ h+=Sigma0(a)
- @ add r6,r6,r12 @ h+=Maj(a,b,c)
-#if __ARM_ARCH__>=7
- @ ldr r2,[r1],#4 @ 6
-# if 6==15
- str r1,[sp,#17*4] @ make room for r1
-# endif
- eor r0,r10,r10,ror#5
- add r6,r6,r12 @ h+=Maj(a,b,c) from the past
- eor r0,r0,r10,ror#19 @ Sigma1(e)
-# ifndef __ARMEB__
- rev r2,r2
-# endif
-#else
- @ ldrb r2,[r1,#3] @ 6
- add r6,r6,r12 @ h+=Maj(a,b,c) from the past
- ldrb r12,[r1,#2]
- ldrb r0,[r1,#1]
- orr r2,r2,r12,lsl#8
- ldrb r12,[r1],#4
- orr r2,r2,r0,lsl#16
-# if 6==15
- str r1,[sp,#17*4] @ make room for r1
-# endif
- eor r0,r10,r10,ror#5
- orr r2,r2,r12,lsl#24
- eor r0,r0,r10,ror#19 @ Sigma1(e)
-#endif
- ldr r12,[r14],#4 @ *K256++
- add r5,r5,r2 @ h+=X[i]
- str r2,[sp,#6*4]
- eor r2,r11,r4
- add r5,r5,r0,ror#6 @ h+=Sigma1(e)
- and r2,r2,r10
- add r5,r5,r12 @ h+=K256[i]
- eor r2,r2,r4 @ Ch(e,f,g)
- eor r0,r6,r6,ror#11
- add r5,r5,r2 @ h+=Ch(e,f,g)
-#if 6==31
- and r12,r12,#0xff
- cmp r12,#0xf2 @ done?
-#endif
-#if 6<15
-# if __ARM_ARCH__>=7
- ldr r2,[r1],#4 @ prefetch
-# else
- ldrb r2,[r1,#3]
-# endif
- eor r12,r6,r7 @ a^b, b^c in next round
-#else
- ldr r2,[sp,#8*4] @ from future BODY_16_xx
- eor r12,r6,r7 @ a^b, b^c in next round
- ldr r1,[sp,#5*4] @ from future BODY_16_xx
-#endif
- eor r0,r0,r6,ror#20 @ Sigma0(a)
- and r3,r3,r12 @ (b^c)&=(a^b)
- add r9,r9,r5 @ d+=h
- eor r3,r3,r7 @ Maj(a,b,c)
- add r5,r5,r0,ror#2 @ h+=Sigma0(a)
- @ add r5,r5,r3 @ h+=Maj(a,b,c)
-#if __ARM_ARCH__>=7
- @ ldr r2,[r1],#4 @ 7
-# if 7==15
- str r1,[sp,#17*4] @ make room for r1
-# endif
- eor r0,r9,r9,ror#5
- add r5,r5,r3 @ h+=Maj(a,b,c) from the past
- eor r0,r0,r9,ror#19 @ Sigma1(e)
-# ifndef __ARMEB__
- rev r2,r2
-# endif
-#else
- @ ldrb r2,[r1,#3] @ 7
- add r5,r5,r3 @ h+=Maj(a,b,c) from the past
- ldrb r3,[r1,#2]
- ldrb r0,[r1,#1]
- orr r2,r2,r3,lsl#8
- ldrb r3,[r1],#4
- orr r2,r2,r0,lsl#16
-# if 7==15
- str r1,[sp,#17*4] @ make room for r1
-# endif
- eor r0,r9,r9,ror#5
- orr r2,r2,r3,lsl#24
- eor r0,r0,r9,ror#19 @ Sigma1(e)
-#endif
- ldr r3,[r14],#4 @ *K256++
- add r4,r4,r2 @ h+=X[i]
- str r2,[sp,#7*4]
- eor r2,r10,r11
- add r4,r4,r0,ror#6 @ h+=Sigma1(e)
- and r2,r2,r9
- add r4,r4,r3 @ h+=K256[i]
- eor r2,r2,r11 @ Ch(e,f,g)
- eor r0,r5,r5,ror#11
- add r4,r4,r2 @ h+=Ch(e,f,g)
-#if 7==31
- and r3,r3,#0xff
- cmp r3,#0xf2 @ done?
-#endif
-#if 7<15
-# if __ARM_ARCH__>=7
- ldr r2,[r1],#4 @ prefetch
-# else
- ldrb r2,[r1,#3]
-# endif
- eor r3,r5,r6 @ a^b, b^c in next round
-#else
- ldr r2,[sp,#9*4] @ from future BODY_16_xx
- eor r3,r5,r6 @ a^b, b^c in next round
- ldr r1,[sp,#6*4] @ from future BODY_16_xx
-#endif
- eor r0,r0,r5,ror#20 @ Sigma0(a)
- and r12,r12,r3 @ (b^c)&=(a^b)
- add r8,r8,r4 @ d+=h
- eor r12,r12,r6 @ Maj(a,b,c)
- add r4,r4,r0,ror#2 @ h+=Sigma0(a)
- @ add r4,r4,r12 @ h+=Maj(a,b,c)
-#if __ARM_ARCH__>=7
- @ ldr r2,[r1],#4 @ 8
-# if 8==15
- str r1,[sp,#17*4] @ make room for r1
-# endif
- eor r0,r8,r8,ror#5
- add r4,r4,r12 @ h+=Maj(a,b,c) from the past
- eor r0,r0,r8,ror#19 @ Sigma1(e)
-# ifndef __ARMEB__
- rev r2,r2
-# endif
-#else
- @ ldrb r2,[r1,#3] @ 8
- add r4,r4,r12 @ h+=Maj(a,b,c) from the past
- ldrb r12,[r1,#2]
- ldrb r0,[r1,#1]
- orr r2,r2,r12,lsl#8
- ldrb r12,[r1],#4
- orr r2,r2,r0,lsl#16
-# if 8==15
- str r1,[sp,#17*4] @ make room for r1
-# endif
- eor r0,r8,r8,ror#5
- orr r2,r2,r12,lsl#24
- eor r0,r0,r8,ror#19 @ Sigma1(e)
-#endif
- ldr r12,[r14],#4 @ *K256++
- add r11,r11,r2 @ h+=X[i]
- str r2,[sp,#8*4]
- eor r2,r9,r10
- add r11,r11,r0,ror#6 @ h+=Sigma1(e)
- and r2,r2,r8
- add r11,r11,r12 @ h+=K256[i]
- eor r2,r2,r10 @ Ch(e,f,g)
- eor r0,r4,r4,ror#11
- add r11,r11,r2 @ h+=Ch(e,f,g)
-#if 8==31
- and r12,r12,#0xff
- cmp r12,#0xf2 @ done?
-#endif
-#if 8<15
-# if __ARM_ARCH__>=7
- ldr r2,[r1],#4 @ prefetch
-# else
- ldrb r2,[r1,#3]
-# endif
- eor r12,r4,r5 @ a^b, b^c in next round
-#else
- ldr r2,[sp,#10*4] @ from future BODY_16_xx
- eor r12,r4,r5 @ a^b, b^c in next round
- ldr r1,[sp,#7*4] @ from future BODY_16_xx
-#endif
- eor r0,r0,r4,ror#20 @ Sigma0(a)
- and r3,r3,r12 @ (b^c)&=(a^b)
- add r7,r7,r11 @ d+=h
- eor r3,r3,r5 @ Maj(a,b,c)
- add r11,r11,r0,ror#2 @ h+=Sigma0(a)
- @ add r11,r11,r3 @ h+=Maj(a,b,c)
-#if __ARM_ARCH__>=7
- @ ldr r2,[r1],#4 @ 9
-# if 9==15
- str r1,[sp,#17*4] @ make room for r1
-# endif
- eor r0,r7,r7,ror#5
- add r11,r11,r3 @ h+=Maj(a,b,c) from the past
- eor r0,r0,r7,ror#19 @ Sigma1(e)
-# ifndef __ARMEB__
- rev r2,r2
-# endif
-#else
- @ ldrb r2,[r1,#3] @ 9
- add r11,r11,r3 @ h+=Maj(a,b,c) from the past
- ldrb r3,[r1,#2]
- ldrb r0,[r1,#1]
- orr r2,r2,r3,lsl#8
- ldrb r3,[r1],#4
- orr r2,r2,r0,lsl#16
-# if 9==15
- str r1,[sp,#17*4] @ make room for r1
-# endif
- eor r0,r7,r7,ror#5
- orr r2,r2,r3,lsl#24
- eor r0,r0,r7,ror#19 @ Sigma1(e)
-#endif
- ldr r3,[r14],#4 @ *K256++
- add r10,r10,r2 @ h+=X[i]
- str r2,[sp,#9*4]
- eor r2,r8,r9
- add r10,r10,r0,ror#6 @ h+=Sigma1(e)
- and r2,r2,r7
- add r10,r10,r3 @ h+=K256[i]
- eor r2,r2,r9 @ Ch(e,f,g)
- eor r0,r11,r11,ror#11
- add r10,r10,r2 @ h+=Ch(e,f,g)
-#if 9==31
- and r3,r3,#0xff
- cmp r3,#0xf2 @ done?
-#endif
-#if 9<15
-# if __ARM_ARCH__>=7
- ldr r2,[r1],#4 @ prefetch
-# else
- ldrb r2,[r1,#3]
-# endif
- eor r3,r11,r4 @ a^b, b^c in next round
-#else
- ldr r2,[sp,#11*4] @ from future BODY_16_xx
- eor r3,r11,r4 @ a^b, b^c in next round
- ldr r1,[sp,#8*4] @ from future BODY_16_xx
-#endif
- eor r0,r0,r11,ror#20 @ Sigma0(a)
- and r12,r12,r3 @ (b^c)&=(a^b)
- add r6,r6,r10 @ d+=h
- eor r12,r12,r4 @ Maj(a,b,c)
- add r10,r10,r0,ror#2 @ h+=Sigma0(a)
- @ add r10,r10,r12 @ h+=Maj(a,b,c)
-#if __ARM_ARCH__>=7
- @ ldr r2,[r1],#4 @ 10
-# if 10==15
- str r1,[sp,#17*4] @ make room for r1
-# endif
- eor r0,r6,r6,ror#5
- add r10,r10,r12 @ h+=Maj(a,b,c) from the past
- eor r0,r0,r6,ror#19 @ Sigma1(e)
-# ifndef __ARMEB__
- rev r2,r2
-# endif
-#else
- @ ldrb r2,[r1,#3] @ 10
- add r10,r10,r12 @ h+=Maj(a,b,c) from the past
- ldrb r12,[r1,#2]
- ldrb r0,[r1,#1]
- orr r2,r2,r12,lsl#8
- ldrb r12,[r1],#4
- orr r2,r2,r0,lsl#16
-# if 10==15
- str r1,[sp,#17*4] @ make room for r1
-# endif
- eor r0,r6,r6,ror#5
- orr r2,r2,r12,lsl#24
- eor r0,r0,r6,ror#19 @ Sigma1(e)
-#endif
- ldr r12,[r14],#4 @ *K256++
- add r9,r9,r2 @ h+=X[i]
- str r2,[sp,#10*4]
- eor r2,r7,r8
- add r9,r9,r0,ror#6 @ h+=Sigma1(e)
- and r2,r2,r6
- add r9,r9,r12 @ h+=K256[i]
- eor r2,r2,r8 @ Ch(e,f,g)
- eor r0,r10,r10,ror#11
- add r9,r9,r2 @ h+=Ch(e,f,g)
-#if 10==31
- and r12,r12,#0xff
- cmp r12,#0xf2 @ done?
-#endif
-#if 10<15
-# if __ARM_ARCH__>=7
- ldr r2,[r1],#4 @ prefetch
-# else
- ldrb r2,[r1,#3]
-# endif
- eor r12,r10,r11 @ a^b, b^c in next round
-#else
- ldr r2,[sp,#12*4] @ from future BODY_16_xx
- eor r12,r10,r11 @ a^b, b^c in next round
- ldr r1,[sp,#9*4] @ from future BODY_16_xx
-#endif
- eor r0,r0,r10,ror#20 @ Sigma0(a)
- and r3,r3,r12 @ (b^c)&=(a^b)
- add r5,r5,r9 @ d+=h
- eor r3,r3,r11 @ Maj(a,b,c)
- add r9,r9,r0,ror#2 @ h+=Sigma0(a)
- @ add r9,r9,r3 @ h+=Maj(a,b,c)
-#if __ARM_ARCH__>=7
- @ ldr r2,[r1],#4 @ 11
-# if 11==15
- str r1,[sp,#17*4] @ make room for r1
-# endif
- eor r0,r5,r5,ror#5
- add r9,r9,r3 @ h+=Maj(a,b,c) from the past
- eor r0,r0,r5,ror#19 @ Sigma1(e)
-# ifndef __ARMEB__
- rev r2,r2
-# endif
-#else
- @ ldrb r2,[r1,#3] @ 11
- add r9,r9,r3 @ h+=Maj(a,b,c) from the past
- ldrb r3,[r1,#2]
- ldrb r0,[r1,#1]
- orr r2,r2,r3,lsl#8
- ldrb r3,[r1],#4
- orr r2,r2,r0,lsl#16
-# if 11==15
- str r1,[sp,#17*4] @ make room for r1
-# endif
- eor r0,r5,r5,ror#5
- orr r2,r2,r3,lsl#24
- eor r0,r0,r5,ror#19 @ Sigma1(e)
-#endif
- ldr r3,[r14],#4 @ *K256++
- add r8,r8,r2 @ h+=X[i]
- str r2,[sp,#11*4]
- eor r2,r6,r7
- add r8,r8,r0,ror#6 @ h+=Sigma1(e)
- and r2,r2,r5
- add r8,r8,r3 @ h+=K256[i]
- eor r2,r2,r7 @ Ch(e,f,g)
- eor r0,r9,r9,ror#11
- add r8,r8,r2 @ h+=Ch(e,f,g)
-#if 11==31
- and r3,r3,#0xff
- cmp r3,#0xf2 @ done?
-#endif
-#if 11<15
-# if __ARM_ARCH__>=7
- ldr r2,[r1],#4 @ prefetch
-# else
- ldrb r2,[r1,#3]
-# endif
- eor r3,r9,r10 @ a^b, b^c in next round
-#else
- ldr r2,[sp,#13*4] @ from future BODY_16_xx
- eor r3,r9,r10 @ a^b, b^c in next round
- ldr r1,[sp,#10*4] @ from future BODY_16_xx
-#endif
- eor r0,r0,r9,ror#20 @ Sigma0(a)
- and r12,r12,r3 @ (b^c)&=(a^b)
- add r4,r4,r8 @ d+=h
- eor r12,r12,r10 @ Maj(a,b,c)
- add r8,r8,r0,ror#2 @ h+=Sigma0(a)
- @ add r8,r8,r12 @ h+=Maj(a,b,c)
-#if __ARM_ARCH__>=7
- @ ldr r2,[r1],#4 @ 12
-# if 12==15
- str r1,[sp,#17*4] @ make room for r1
-# endif
- eor r0,r4,r4,ror#5
- add r8,r8,r12 @ h+=Maj(a,b,c) from the past
- eor r0,r0,r4,ror#19 @ Sigma1(e)
-# ifndef __ARMEB__
- rev r2,r2
-# endif
-#else
- @ ldrb r2,[r1,#3] @ 12
- add r8,r8,r12 @ h+=Maj(a,b,c) from the past
- ldrb r12,[r1,#2]
- ldrb r0,[r1,#1]
- orr r2,r2,r12,lsl#8
- ldrb r12,[r1],#4
- orr r2,r2,r0,lsl#16
-# if 12==15
- str r1,[sp,#17*4] @ make room for r1
-# endif
- eor r0,r4,r4,ror#5
- orr r2,r2,r12,lsl#24
- eor r0,r0,r4,ror#19 @ Sigma1(e)
-#endif
- ldr r12,[r14],#4 @ *K256++
- add r7,r7,r2 @ h+=X[i]
- str r2,[sp,#12*4]
- eor r2,r5,r6
- add r7,r7,r0,ror#6 @ h+=Sigma1(e)
- and r2,r2,r4
- add r7,r7,r12 @ h+=K256[i]
- eor r2,r2,r6 @ Ch(e,f,g)
- eor r0,r8,r8,ror#11
- add r7,r7,r2 @ h+=Ch(e,f,g)
-#if 12==31
- and r12,r12,#0xff
- cmp r12,#0xf2 @ done?
-#endif
-#if 12<15
-# if __ARM_ARCH__>=7
- ldr r2,[r1],#4 @ prefetch
-# else
- ldrb r2,[r1,#3]
-# endif
- eor r12,r8,r9 @ a^b, b^c in next round
-#else
- ldr r2,[sp,#14*4] @ from future BODY_16_xx
- eor r12,r8,r9 @ a^b, b^c in next round
- ldr r1,[sp,#11*4] @ from future BODY_16_xx
-#endif
- eor r0,r0,r8,ror#20 @ Sigma0(a)
- and r3,r3,r12 @ (b^c)&=(a^b)
- add r11,r11,r7 @ d+=h
- eor r3,r3,r9 @ Maj(a,b,c)
- add r7,r7,r0,ror#2 @ h+=Sigma0(a)
- @ add r7,r7,r3 @ h+=Maj(a,b,c)
-#if __ARM_ARCH__>=7
- @ ldr r2,[r1],#4 @ 13
-# if 13==15
- str r1,[sp,#17*4] @ make room for r1
-# endif
- eor r0,r11,r11,ror#5
- add r7,r7,r3 @ h+=Maj(a,b,c) from the past
- eor r0,r0,r11,ror#19 @ Sigma1(e)
-# ifndef __ARMEB__
- rev r2,r2
-# endif
-#else
- @ ldrb r2,[r1,#3] @ 13
- add r7,r7,r3 @ h+=Maj(a,b,c) from the past
- ldrb r3,[r1,#2]
- ldrb r0,[r1,#1]
- orr r2,r2,r3,lsl#8
- ldrb r3,[r1],#4
- orr r2,r2,r0,lsl#16
-# if 13==15
- str r1,[sp,#17*4] @ make room for r1
-# endif
- eor r0,r11,r11,ror#5
- orr r2,r2,r3,lsl#24
- eor r0,r0,r11,ror#19 @ Sigma1(e)
-#endif
- ldr r3,[r14],#4 @ *K256++
- add r6,r6,r2 @ h+=X[i]
- str r2,[sp,#13*4]
- eor r2,r4,r5
- add r6,r6,r0,ror#6 @ h+=Sigma1(e)
- and r2,r2,r11
- add r6,r6,r3 @ h+=K256[i]
- eor r2,r2,r5 @ Ch(e,f,g)
- eor r0,r7,r7,ror#11
- add r6,r6,r2 @ h+=Ch(e,f,g)
-#if 13==31
- and r3,r3,#0xff
- cmp r3,#0xf2 @ done?
-#endif
-#if 13<15
-# if __ARM_ARCH__>=7
- ldr r2,[r1],#4 @ prefetch
-# else
- ldrb r2,[r1,#3]
-# endif
- eor r3,r7,r8 @ a^b, b^c in next round
-#else
- ldr r2,[sp,#15*4] @ from future BODY_16_xx
- eor r3,r7,r8 @ a^b, b^c in next round
- ldr r1,[sp,#12*4] @ from future BODY_16_xx
-#endif
- eor r0,r0,r7,ror#20 @ Sigma0(a)
- and r12,r12,r3 @ (b^c)&=(a^b)
- add r10,r10,r6 @ d+=h
- eor r12,r12,r8 @ Maj(a,b,c)
- add r6,r6,r0,ror#2 @ h+=Sigma0(a)
- @ add r6,r6,r12 @ h+=Maj(a,b,c)
-#if __ARM_ARCH__>=7
- @ ldr r2,[r1],#4 @ 14
-# if 14==15
- str r1,[sp,#17*4] @ make room for r1
-# endif
- eor r0,r10,r10,ror#5
- add r6,r6,r12 @ h+=Maj(a,b,c) from the past
- eor r0,r0,r10,ror#19 @ Sigma1(e)
-# ifndef __ARMEB__
- rev r2,r2
-# endif
-#else
- @ ldrb r2,[r1,#3] @ 14
- add r6,r6,r12 @ h+=Maj(a,b,c) from the past
- ldrb r12,[r1,#2]
- ldrb r0,[r1,#1]
- orr r2,r2,r12,lsl#8
- ldrb r12,[r1],#4
- orr r2,r2,r0,lsl#16
-# if 14==15
- str r1,[sp,#17*4] @ make room for r1
-# endif
- eor r0,r10,r10,ror#5
- orr r2,r2,r12,lsl#24
- eor r0,r0,r10,ror#19 @ Sigma1(e)
-#endif
- ldr r12,[r14],#4 @ *K256++
- add r5,r5,r2 @ h+=X[i]
- str r2,[sp,#14*4]
- eor r2,r11,r4
- add r5,r5,r0,ror#6 @ h+=Sigma1(e)
- and r2,r2,r10
- add r5,r5,r12 @ h+=K256[i]
- eor r2,r2,r4 @ Ch(e,f,g)
- eor r0,r6,r6,ror#11
- add r5,r5,r2 @ h+=Ch(e,f,g)
-#if 14==31
- and r12,r12,#0xff
- cmp r12,#0xf2 @ done?
-#endif
-#if 14<15
-# if __ARM_ARCH__>=7
- ldr r2,[r1],#4 @ prefetch
-# else
- ldrb r2,[r1,#3]
-# endif
- eor r12,r6,r7 @ a^b, b^c in next round
-#else
- ldr r2,[sp,#0*4] @ from future BODY_16_xx
- eor r12,r6,r7 @ a^b, b^c in next round
- ldr r1,[sp,#13*4] @ from future BODY_16_xx
-#endif
- eor r0,r0,r6,ror#20 @ Sigma0(a)
- and r3,r3,r12 @ (b^c)&=(a^b)
- add r9,r9,r5 @ d+=h
- eor r3,r3,r7 @ Maj(a,b,c)
- add r5,r5,r0,ror#2 @ h+=Sigma0(a)
- @ add r5,r5,r3 @ h+=Maj(a,b,c)
-#if __ARM_ARCH__>=7
- @ ldr r2,[r1],#4 @ 15
-# if 15==15
- str r1,[sp,#17*4] @ make room for r1
-# endif
- eor r0,r9,r9,ror#5
- add r5,r5,r3 @ h+=Maj(a,b,c) from the past
- eor r0,r0,r9,ror#19 @ Sigma1(e)
-# ifndef __ARMEB__
- rev r2,r2
-# endif
-#else
- @ ldrb r2,[r1,#3] @ 15
- add r5,r5,r3 @ h+=Maj(a,b,c) from the past
- ldrb r3,[r1,#2]
- ldrb r0,[r1,#1]
- orr r2,r2,r3,lsl#8
- ldrb r3,[r1],#4
- orr r2,r2,r0,lsl#16
-# if 15==15
- str r1,[sp,#17*4] @ make room for r1
-# endif
- eor r0,r9,r9,ror#5
- orr r2,r2,r3,lsl#24
- eor r0,r0,r9,ror#19 @ Sigma1(e)
-#endif
- ldr r3,[r14],#4 @ *K256++
- add r4,r4,r2 @ h+=X[i]
- str r2,[sp,#15*4]
- eor r2,r10,r11
- add r4,r4,r0,ror#6 @ h+=Sigma1(e)
- and r2,r2,r9
- add r4,r4,r3 @ h+=K256[i]
- eor r2,r2,r11 @ Ch(e,f,g)
- eor r0,r5,r5,ror#11
- add r4,r4,r2 @ h+=Ch(e,f,g)
-#if 15==31
- and r3,r3,#0xff
- cmp r3,#0xf2 @ done?
-#endif
-#if 15<15
-# if __ARM_ARCH__>=7
- ldr r2,[r1],#4 @ prefetch
-# else
- ldrb r2,[r1,#3]
-# endif
- eor r3,r5,r6 @ a^b, b^c in next round
-#else
- ldr r2,[sp,#1*4] @ from future BODY_16_xx
- eor r3,r5,r6 @ a^b, b^c in next round
- ldr r1,[sp,#14*4] @ from future BODY_16_xx
-#endif
- eor r0,r0,r5,ror#20 @ Sigma0(a)
- and r12,r12,r3 @ (b^c)&=(a^b)
- add r8,r8,r4 @ d+=h
- eor r12,r12,r6 @ Maj(a,b,c)
- add r4,r4,r0,ror#2 @ h+=Sigma0(a)
- @ add r4,r4,r12 @ h+=Maj(a,b,c)
-.Lrounds_16_xx:
- @ ldr r2,[sp,#1*4] @ 16
- @ ldr r1,[sp,#14*4]
- mov r0,r2,ror#7
- add r4,r4,r12 @ h+=Maj(a,b,c) from the past
- mov r12,r1,ror#17
- eor r0,r0,r2,ror#18
- eor r12,r12,r1,ror#19
- eor r0,r0,r2,lsr#3 @ sigma0(X[i+1])
- ldr r2,[sp,#0*4]
- eor r12,r12,r1,lsr#10 @ sigma1(X[i+14])
- ldr r1,[sp,#9*4]
-
- add r12,r12,r0
- eor r0,r8,r8,ror#5 @ from BODY_00_15
- add r2,r2,r12
- eor r0,r0,r8,ror#19 @ Sigma1(e)
- add r2,r2,r1 @ X[i]
- ldr r12,[r14],#4 @ *K256++
- add r11,r11,r2 @ h+=X[i]
- str r2,[sp,#0*4]
- eor r2,r9,r10
- add r11,r11,r0,ror#6 @ h+=Sigma1(e)
- and r2,r2,r8
- add r11,r11,r12 @ h+=K256[i]
- eor r2,r2,r10 @ Ch(e,f,g)
- eor r0,r4,r4,ror#11
- add r11,r11,r2 @ h+=Ch(e,f,g)
-#if 16==31
- and r12,r12,#0xff
- cmp r12,#0xf2 @ done?
-#endif
-#if 16<15
-# if __ARM_ARCH__>=7
- ldr r2,[r1],#4 @ prefetch
-# else
- ldrb r2,[r1,#3]
-# endif
- eor r12,r4,r5 @ a^b, b^c in next round
-#else
- ldr r2,[sp,#2*4] @ from future BODY_16_xx
- eor r12,r4,r5 @ a^b, b^c in next round
- ldr r1,[sp,#15*4] @ from future BODY_16_xx
-#endif
- eor r0,r0,r4,ror#20 @ Sigma0(a)
- and r3,r3,r12 @ (b^c)&=(a^b)
- add r7,r7,r11 @ d+=h
- eor r3,r3,r5 @ Maj(a,b,c)
- add r11,r11,r0,ror#2 @ h+=Sigma0(a)
- @ add r11,r11,r3 @ h+=Maj(a,b,c)
- @ ldr r2,[sp,#2*4] @ 17
- @ ldr r1,[sp,#15*4]
- mov r0,r2,ror#7
- add r11,r11,r3 @ h+=Maj(a,b,c) from the past
- mov r3,r1,ror#17
- eor r0,r0,r2,ror#18
- eor r3,r3,r1,ror#19
- eor r0,r0,r2,lsr#3 @ sigma0(X[i+1])
- ldr r2,[sp,#1*4]
- eor r3,r3,r1,lsr#10 @ sigma1(X[i+14])
- ldr r1,[sp,#10*4]
-
- add r3,r3,r0
- eor r0,r7,r7,ror#5 @ from BODY_00_15
- add r2,r2,r3
- eor r0,r0,r7,ror#19 @ Sigma1(e)
- add r2,r2,r1 @ X[i]
- ldr r3,[r14],#4 @ *K256++
- add r10,r10,r2 @ h+=X[i]
- str r2,[sp,#1*4]
- eor r2,r8,r9
- add r10,r10,r0,ror#6 @ h+=Sigma1(e)
- and r2,r2,r7
- add r10,r10,r3 @ h+=K256[i]
- eor r2,r2,r9 @ Ch(e,f,g)
- eor r0,r11,r11,ror#11
- add r10,r10,r2 @ h+=Ch(e,f,g)
-#if 17==31
- and r3,r3,#0xff
- cmp r3,#0xf2 @ done?
-#endif
-#if 17<15
-# if __ARM_ARCH__>=7
- ldr r2,[r1],#4 @ prefetch
-# else
- ldrb r2,[r1,#3]
-# endif
- eor r3,r11,r4 @ a^b, b^c in next round
-#else
- ldr r2,[sp,#3*4] @ from future BODY_16_xx
- eor r3,r11,r4 @ a^b, b^c in next round
- ldr r1,[sp,#0*4] @ from future BODY_16_xx
-#endif
- eor r0,r0,r11,ror#20 @ Sigma0(a)
- and r12,r12,r3 @ (b^c)&=(a^b)
- add r6,r6,r10 @ d+=h
- eor r12,r12,r4 @ Maj(a,b,c)
- add r10,r10,r0,ror#2 @ h+=Sigma0(a)
- @ add r10,r10,r12 @ h+=Maj(a,b,c)
- @ ldr r2,[sp,#3*4] @ 18
- @ ldr r1,[sp,#0*4]
- mov r0,r2,ror#7
- add r10,r10,r12 @ h+=Maj(a,b,c) from the past
- mov r12,r1,ror#17
- eor r0,r0,r2,ror#18
- eor r12,r12,r1,ror#19
- eor r0,r0,r2,lsr#3 @ sigma0(X[i+1])
- ldr r2,[sp,#2*4]
- eor r12,r12,r1,lsr#10 @ sigma1(X[i+14])
- ldr r1,[sp,#11*4]
-
- add r12,r12,r0
- eor r0,r6,r6,ror#5 @ from BODY_00_15
- add r2,r2,r12
- eor r0,r0,r6,ror#19 @ Sigma1(e)
- add r2,r2,r1 @ X[i]
- ldr r12,[r14],#4 @ *K256++
- add r9,r9,r2 @ h+=X[i]
- str r2,[sp,#2*4]
- eor r2,r7,r8
- add r9,r9,r0,ror#6 @ h+=Sigma1(e)
- and r2,r2,r6
- add r9,r9,r12 @ h+=K256[i]
- eor r2,r2,r8 @ Ch(e,f,g)
- eor r0,r10,r10,ror#11
- add r9,r9,r2 @ h+=Ch(e,f,g)
-#if 18==31
- and r12,r12,#0xff
- cmp r12,#0xf2 @ done?
-#endif
-#if 18<15
-# if __ARM_ARCH__>=7
- ldr r2,[r1],#4 @ prefetch
-# else
- ldrb r2,[r1,#3]
-# endif
- eor r12,r10,r11 @ a^b, b^c in next round
-#else
- ldr r2,[sp,#4*4] @ from future BODY_16_xx
- eor r12,r10,r11 @ a^b, b^c in next round
- ldr r1,[sp,#1*4] @ from future BODY_16_xx
-#endif
- eor r0,r0,r10,ror#20 @ Sigma0(a)
- and r3,r3,r12 @ (b^c)&=(a^b)
- add r5,r5,r9 @ d+=h
- eor r3,r3,r11 @ Maj(a,b,c)
- add r9,r9,r0,ror#2 @ h+=Sigma0(a)
- @ add r9,r9,r3 @ h+=Maj(a,b,c)
- @ ldr r2,[sp,#4*4] @ 19
- @ ldr r1,[sp,#1*4]
- mov r0,r2,ror#7
- add r9,r9,r3 @ h+=Maj(a,b,c) from the past
- mov r3,r1,ror#17
- eor r0,r0,r2,ror#18
- eor r3,r3,r1,ror#19
- eor r0,r0,r2,lsr#3 @ sigma0(X[i+1])
- ldr r2,[sp,#3*4]
- eor r3,r3,r1,lsr#10 @ sigma1(X[i+14])
- ldr r1,[sp,#12*4]
-
- add r3,r3,r0
- eor r0,r5,r5,ror#5 @ from BODY_00_15
- add r2,r2,r3
- eor r0,r0,r5,ror#19 @ Sigma1(e)
- add r2,r2,r1 @ X[i]
- ldr r3,[r14],#4 @ *K256++
- add r8,r8,r2 @ h+=X[i]
- str r2,[sp,#3*4]
- eor r2,r6,r7
- add r8,r8,r0,ror#6 @ h+=Sigma1(e)
- and r2,r2,r5
- add r8,r8,r3 @ h+=K256[i]
- eor r2,r2,r7 @ Ch(e,f,g)
- eor r0,r9,r9,ror#11
- add r8,r8,r2 @ h+=Ch(e,f,g)
-#if 19==31
- and r3,r3,#0xff
- cmp r3,#0xf2 @ done?
-#endif
-#if 19<15
-# if __ARM_ARCH__>=7
- ldr r2,[r1],#4 @ prefetch
-# else
- ldrb r2,[r1,#3]
-# endif
- eor r3,r9,r10 @ a^b, b^c in next round
-#else
- ldr r2,[sp,#5*4] @ from future BODY_16_xx
- eor r3,r9,r10 @ a^b, b^c in next round
- ldr r1,[sp,#2*4] @ from future BODY_16_xx
-#endif
- eor r0,r0,r9,ror#20 @ Sigma0(a)
- and r12,r12,r3 @ (b^c)&=(a^b)
- add r4,r4,r8 @ d+=h
- eor r12,r12,r10 @ Maj(a,b,c)
- add r8,r8,r0,ror#2 @ h+=Sigma0(a)
- @ add r8,r8,r12 @ h+=Maj(a,b,c)
- @ ldr r2,[sp,#5*4] @ 20
- @ ldr r1,[sp,#2*4]
- mov r0,r2,ror#7
- add r8,r8,r12 @ h+=Maj(a,b,c) from the past
- mov r12,r1,ror#17
- eor r0,r0,r2,ror#18
- eor r12,r12,r1,ror#19
- eor r0,r0,r2,lsr#3 @ sigma0(X[i+1])
- ldr r2,[sp,#4*4]
- eor r12,r12,r1,lsr#10 @ sigma1(X[i+14])
- ldr r1,[sp,#13*4]
-
- add r12,r12,r0
- eor r0,r4,r4,ror#5 @ from BODY_00_15
- add r2,r2,r12
- eor r0,r0,r4,ror#19 @ Sigma1(e)
- add r2,r2,r1 @ X[i]
- ldr r12,[r14],#4 @ *K256++
- add r7,r7,r2 @ h+=X[i]
- str r2,[sp,#4*4]
- eor r2,r5,r6
- add r7,r7,r0,ror#6 @ h+=Sigma1(e)
- and r2,r2,r4
- add r7,r7,r12 @ h+=K256[i]
- eor r2,r2,r6 @ Ch(e,f,g)
- eor r0,r8,r8,ror#11
- add r7,r7,r2 @ h+=Ch(e,f,g)
-#if 20==31
- and r12,r12,#0xff
- cmp r12,#0xf2 @ done?
-#endif
-#if 20<15
-# if __ARM_ARCH__>=7
- ldr r2,[r1],#4 @ prefetch
-# else
- ldrb r2,[r1,#3]
-# endif
- eor r12,r8,r9 @ a^b, b^c in next round
-#else
- ldr r2,[sp,#6*4] @ from future BODY_16_xx
- eor r12,r8,r9 @ a^b, b^c in next round
- ldr r1,[sp,#3*4] @ from future BODY_16_xx
-#endif
- eor r0,r0,r8,ror#20 @ Sigma0(a)
- and r3,r3,r12 @ (b^c)&=(a^b)
- add r11,r11,r7 @ d+=h
- eor r3,r3,r9 @ Maj(a,b,c)
- add r7,r7,r0,ror#2 @ h+=Sigma0(a)
- @ add r7,r7,r3 @ h+=Maj(a,b,c)
- @ ldr r2,[sp,#6*4] @ 21
- @ ldr r1,[sp,#3*4]
- mov r0,r2,ror#7
- add r7,r7,r3 @ h+=Maj(a,b,c) from the past
- mov r3,r1,ror#17
- eor r0,r0,r2,ror#18
- eor r3,r3,r1,ror#19
- eor r0,r0,r2,lsr#3 @ sigma0(X[i+1])
- ldr r2,[sp,#5*4]
- eor r3,r3,r1,lsr#10 @ sigma1(X[i+14])
- ldr r1,[sp,#14*4]
-
- add r3,r3,r0
- eor r0,r11,r11,ror#5 @ from BODY_00_15
- add r2,r2,r3
- eor r0,r0,r11,ror#19 @ Sigma1(e)
- add r2,r2,r1 @ X[i]
- ldr r3,[r14],#4 @ *K256++
- add r6,r6,r2 @ h+=X[i]
- str r2,[sp,#5*4]
- eor r2,r4,r5
- add r6,r6,r0,ror#6 @ h+=Sigma1(e)
- and r2,r2,r11
- add r6,r6,r3 @ h+=K256[i]
- eor r2,r2,r5 @ Ch(e,f,g)
- eor r0,r7,r7,ror#11
- add r6,r6,r2 @ h+=Ch(e,f,g)
-#if 21==31
- and r3,r3,#0xff
- cmp r3,#0xf2 @ done?
-#endif
-#if 21<15
-# if __ARM_ARCH__>=7
- ldr r2,[r1],#4 @ prefetch
-# else
- ldrb r2,[r1,#3]
-# endif
- eor r3,r7,r8 @ a^b, b^c in next round
-#else
- ldr r2,[sp,#7*4] @ from future BODY_16_xx
- eor r3,r7,r8 @ a^b, b^c in next round
- ldr r1,[sp,#4*4] @ from future BODY_16_xx
-#endif
- eor r0,r0,r7,ror#20 @ Sigma0(a)
- and r12,r12,r3 @ (b^c)&=(a^b)
- add r10,r10,r6 @ d+=h
- eor r12,r12,r8 @ Maj(a,b,c)
- add r6,r6,r0,ror#2 @ h+=Sigma0(a)
- @ add r6,r6,r12 @ h+=Maj(a,b,c)
- @ ldr r2,[sp,#7*4] @ 22
- @ ldr r1,[sp,#4*4]
- mov r0,r2,ror#7
- add r6,r6,r12 @ h+=Maj(a,b,c) from the past
- mov r12,r1,ror#17
- eor r0,r0,r2,ror#18
- eor r12,r12,r1,ror#19
- eor r0,r0,r2,lsr#3 @ sigma0(X[i+1])
- ldr r2,[sp,#6*4]
- eor r12,r12,r1,lsr#10 @ sigma1(X[i+14])
- ldr r1,[sp,#15*4]
-
- add r12,r12,r0
- eor r0,r10,r10,ror#5 @ from BODY_00_15
- add r2,r2,r12
- eor r0,r0,r10,ror#19 @ Sigma1(e)
- add r2,r2,r1 @ X[i]
- ldr r12,[r14],#4 @ *K256++
- add r5,r5,r2 @ h+=X[i]
- str r2,[sp,#6*4]
- eor r2,r11,r4
- add r5,r5,r0,ror#6 @ h+=Sigma1(e)
- and r2,r2,r10
- add r5,r5,r12 @ h+=K256[i]
- eor r2,r2,r4 @ Ch(e,f,g)
- eor r0,r6,r6,ror#11
- add r5,r5,r2 @ h+=Ch(e,f,g)
-#if 22==31
- and r12,r12,#0xff
- cmp r12,#0xf2 @ done?
-#endif
-#if 22<15
-# if __ARM_ARCH__>=7
- ldr r2,[r1],#4 @ prefetch
-# else
- ldrb r2,[r1,#3]
-# endif
- eor r12,r6,r7 @ a^b, b^c in next round
-#else
- ldr r2,[sp,#8*4] @ from future BODY_16_xx
- eor r12,r6,r7 @ a^b, b^c in next round
- ldr r1,[sp,#5*4] @ from future BODY_16_xx
-#endif
- eor r0,r0,r6,ror#20 @ Sigma0(a)
- and r3,r3,r12 @ (b^c)&=(a^b)
- add r9,r9,r5 @ d+=h
- eor r3,r3,r7 @ Maj(a,b,c)
- add r5,r5,r0,ror#2 @ h+=Sigma0(a)
- @ add r5,r5,r3 @ h+=Maj(a,b,c)
- @ ldr r2,[sp,#8*4] @ 23
- @ ldr r1,[sp,#5*4]
- mov r0,r2,ror#7
- add r5,r5,r3 @ h+=Maj(a,b,c) from the past
- mov r3,r1,ror#17
- eor r0,r0,r2,ror#18
- eor r3,r3,r1,ror#19
- eor r0,r0,r2,lsr#3 @ sigma0(X[i+1])
- ldr r2,[sp,#7*4]
- eor r3,r3,r1,lsr#10 @ sigma1(X[i+14])
- ldr r1,[sp,#0*4]
-
- add r3,r3,r0
- eor r0,r9,r9,ror#5 @ from BODY_00_15
- add r2,r2,r3
- eor r0,r0,r9,ror#19 @ Sigma1(e)
- add r2,r2,r1 @ X[i]
- ldr r3,[r14],#4 @ *K256++
- add r4,r4,r2 @ h+=X[i]
- str r2,[sp,#7*4]
- eor r2,r10,r11
- add r4,r4,r0,ror#6 @ h+=Sigma1(e)
- and r2,r2,r9
- add r4,r4,r3 @ h+=K256[i]
- eor r2,r2,r11 @ Ch(e,f,g)
- eor r0,r5,r5,ror#11
- add r4,r4,r2 @ h+=Ch(e,f,g)
-#if 23==31
- and r3,r3,#0xff
- cmp r3,#0xf2 @ done?
-#endif
-#if 23<15
-# if __ARM_ARCH__>=7
- ldr r2,[r1],#4 @ prefetch
-# else
- ldrb r2,[r1,#3]
-# endif
- eor r3,r5,r6 @ a^b, b^c in next round
-#else
- ldr r2,[sp,#9*4] @ from future BODY_16_xx
- eor r3,r5,r6 @ a^b, b^c in next round
- ldr r1,[sp,#6*4] @ from future BODY_16_xx
-#endif
- eor r0,r0,r5,ror#20 @ Sigma0(a)
- and r12,r12,r3 @ (b^c)&=(a^b)
- add r8,r8,r4 @ d+=h
- eor r12,r12,r6 @ Maj(a,b,c)
- add r4,r4,r0,ror#2 @ h+=Sigma0(a)
- @ add r4,r4,r12 @ h+=Maj(a,b,c)
- @ ldr r2,[sp,#9*4] @ 24
- @ ldr r1,[sp,#6*4]
- mov r0,r2,ror#7
- add r4,r4,r12 @ h+=Maj(a,b,c) from the past
- mov r12,r1,ror#17
- eor r0,r0,r2,ror#18
- eor r12,r12,r1,ror#19
- eor r0,r0,r2,lsr#3 @ sigma0(X[i+1])
- ldr r2,[sp,#8*4]
- eor r12,r12,r1,lsr#10 @ sigma1(X[i+14])
- ldr r1,[sp,#1*4]
-
- add r12,r12,r0
- eor r0,r8,r8,ror#5 @ from BODY_00_15
- add r2,r2,r12
- eor r0,r0,r8,ror#19 @ Sigma1(e)
- add r2,r2,r1 @ X[i]
- ldr r12,[r14],#4 @ *K256++
- add r11,r11,r2 @ h+=X[i]
- str r2,[sp,#8*4]
- eor r2,r9,r10
- add r11,r11,r0,ror#6 @ h+=Sigma1(e)
- and r2,r2,r8
- add r11,r11,r12 @ h+=K256[i]
- eor r2,r2,r10 @ Ch(e,f,g)
- eor r0,r4,r4,ror#11
- add r11,r11,r2 @ h+=Ch(e,f,g)
-#if 24==31
- and r12,r12,#0xff
- cmp r12,#0xf2 @ done?
-#endif
-#if 24<15
-# if __ARM_ARCH__>=7
- ldr r2,[r1],#4 @ prefetch
-# else
- ldrb r2,[r1,#3]
-# endif
- eor r12,r4,r5 @ a^b, b^c in next round
-#else
- ldr r2,[sp,#10*4] @ from future BODY_16_xx
- eor r12,r4,r5 @ a^b, b^c in next round
- ldr r1,[sp,#7*4] @ from future BODY_16_xx
-#endif
- eor r0,r0,r4,ror#20 @ Sigma0(a)
- and r3,r3,r12 @ (b^c)&=(a^b)
- add r7,r7,r11 @ d+=h
- eor r3,r3,r5 @ Maj(a,b,c)
- add r11,r11,r0,ror#2 @ h+=Sigma0(a)
- @ add r11,r11,r3 @ h+=Maj(a,b,c)
- @ ldr r2,[sp,#10*4] @ 25
- @ ldr r1,[sp,#7*4]
- mov r0,r2,ror#7
- add r11,r11,r3 @ h+=Maj(a,b,c) from the past
- mov r3,r1,ror#17
- eor r0,r0,r2,ror#18
- eor r3,r3,r1,ror#19
- eor r0,r0,r2,lsr#3 @ sigma0(X[i+1])
- ldr r2,[sp,#9*4]
- eor r3,r3,r1,lsr#10 @ sigma1(X[i+14])
- ldr r1,[sp,#2*4]
-
- add r3,r3,r0
- eor r0,r7,r7,ror#5 @ from BODY_00_15
- add r2,r2,r3
- eor r0,r0,r7,ror#19 @ Sigma1(e)
- add r2,r2,r1 @ X[i]
- ldr r3,[r14],#4 @ *K256++
- add r10,r10,r2 @ h+=X[i]
- str r2,[sp,#9*4]
- eor r2,r8,r9
- add r10,r10,r0,ror#6 @ h+=Sigma1(e)
- and r2,r2,r7
- add r10,r10,r3 @ h+=K256[i]
- eor r2,r2,r9 @ Ch(e,f,g)
- eor r0,r11,r11,ror#11
- add r10,r10,r2 @ h+=Ch(e,f,g)
-#if 25==31
- and r3,r3,#0xff
- cmp r3,#0xf2 @ done?
-#endif
-#if 25<15
-# if __ARM_ARCH__>=7
- ldr r2,[r1],#4 @ prefetch
-# else
- ldrb r2,[r1,#3]
-# endif
- eor r3,r11,r4 @ a^b, b^c in next round
-#else
- ldr r2,[sp,#11*4] @ from future BODY_16_xx
- eor r3,r11,r4 @ a^b, b^c in next round
- ldr r1,[sp,#8*4] @ from future BODY_16_xx
-#endif
- eor r0,r0,r11,ror#20 @ Sigma0(a)
- and r12,r12,r3 @ (b^c)&=(a^b)
- add r6,r6,r10 @ d+=h
- eor r12,r12,r4 @ Maj(a,b,c)
- add r10,r10,r0,ror#2 @ h+=Sigma0(a)
- @ add r10,r10,r12 @ h+=Maj(a,b,c)
- @ ldr r2,[sp,#11*4] @ 26
- @ ldr r1,[sp,#8*4]
- mov r0,r2,ror#7
- add r10,r10,r12 @ h+=Maj(a,b,c) from the past
- mov r12,r1,ror#17
- eor r0,r0,r2,ror#18
- eor r12,r12,r1,ror#19
- eor r0,r0,r2,lsr#3 @ sigma0(X[i+1])
- ldr r2,[sp,#10*4]
- eor r12,r12,r1,lsr#10 @ sigma1(X[i+14])
- ldr r1,[sp,#3*4]
-
- add r12,r12,r0
- eor r0,r6,r6,ror#5 @ from BODY_00_15
- add r2,r2,r12
- eor r0,r0,r6,ror#19 @ Sigma1(e)
- add r2,r2,r1 @ X[i]
- ldr r12,[r14],#4 @ *K256++
- add r9,r9,r2 @ h+=X[i]
- str r2,[sp,#10*4]
- eor r2,r7,r8
- add r9,r9,r0,ror#6 @ h+=Sigma1(e)
- and r2,r2,r6
- add r9,r9,r12 @ h+=K256[i]
- eor r2,r2,r8 @ Ch(e,f,g)
- eor r0,r10,r10,ror#11
- add r9,r9,r2 @ h+=Ch(e,f,g)
-#if 26==31
- and r12,r12,#0xff
- cmp r12,#0xf2 @ done?
-#endif
-#if 26<15
-# if __ARM_ARCH__>=7
- ldr r2,[r1],#4 @ prefetch
-# else
- ldrb r2,[r1,#3]
-# endif
- eor r12,r10,r11 @ a^b, b^c in next round
-#else
- ldr r2,[sp,#12*4] @ from future BODY_16_xx
- eor r12,r10,r11 @ a^b, b^c in next round
- ldr r1,[sp,#9*4] @ from future BODY_16_xx
-#endif
- eor r0,r0,r10,ror#20 @ Sigma0(a)
- and r3,r3,r12 @ (b^c)&=(a^b)
- add r5,r5,r9 @ d+=h
- eor r3,r3,r11 @ Maj(a,b,c)
- add r9,r9,r0,ror#2 @ h+=Sigma0(a)
- @ add r9,r9,r3 @ h+=Maj(a,b,c)
- @ ldr r2,[sp,#12*4] @ 27
- @ ldr r1,[sp,#9*4]
- mov r0,r2,ror#7
- add r9,r9,r3 @ h+=Maj(a,b,c) from the past
- mov r3,r1,ror#17
- eor r0,r0,r2,ror#18
- eor r3,r3,r1,ror#19
- eor r0,r0,r2,lsr#3 @ sigma0(X[i+1])
- ldr r2,[sp,#11*4]
- eor r3,r3,r1,lsr#10 @ sigma1(X[i+14])
- ldr r1,[sp,#4*4]
-
- add r3,r3,r0
- eor r0,r5,r5,ror#5 @ from BODY_00_15
- add r2,r2,r3
- eor r0,r0,r5,ror#19 @ Sigma1(e)
- add r2,r2,r1 @ X[i]
- ldr r3,[r14],#4 @ *K256++
- add r8,r8,r2 @ h+=X[i]
- str r2,[sp,#11*4]
- eor r2,r6,r7
- add r8,r8,r0,ror#6 @ h+=Sigma1(e)
- and r2,r2,r5
- add r8,r8,r3 @ h+=K256[i]
- eor r2,r2,r7 @ Ch(e,f,g)
- eor r0,r9,r9,ror#11
- add r8,r8,r2 @ h+=Ch(e,f,g)
-#if 27==31
- and r3,r3,#0xff
- cmp r3,#0xf2 @ done?
-#endif
-#if 27<15
-# if __ARM_ARCH__>=7
- ldr r2,[r1],#4 @ prefetch
-# else
- ldrb r2,[r1,#3]
-# endif
- eor r3,r9,r10 @ a^b, b^c in next round
-#else
- ldr r2,[sp,#13*4] @ from future BODY_16_xx
- eor r3,r9,r10 @ a^b, b^c in next round
- ldr r1,[sp,#10*4] @ from future BODY_16_xx
-#endif
- eor r0,r0,r9,ror#20 @ Sigma0(a)
- and r12,r12,r3 @ (b^c)&=(a^b)
- add r4,r4,r8 @ d+=h
- eor r12,r12,r10 @ Maj(a,b,c)
- add r8,r8,r0,ror#2 @ h+=Sigma0(a)
- @ add r8,r8,r12 @ h+=Maj(a,b,c)
- @ ldr r2,[sp,#13*4] @ 28
- @ ldr r1,[sp,#10*4]
- mov r0,r2,ror#7
- add r8,r8,r12 @ h+=Maj(a,b,c) from the past
- mov r12,r1,ror#17
- eor r0,r0,r2,ror#18
- eor r12,r12,r1,ror#19
- eor r0,r0,r2,lsr#3 @ sigma0(X[i+1])
- ldr r2,[sp,#12*4]
- eor r12,r12,r1,lsr#10 @ sigma1(X[i+14])
- ldr r1,[sp,#5*4]
-
- add r12,r12,r0
- eor r0,r4,r4,ror#5 @ from BODY_00_15
- add r2,r2,r12
- eor r0,r0,r4,ror#19 @ Sigma1(e)
- add r2,r2,r1 @ X[i]
- ldr r12,[r14],#4 @ *K256++
- add r7,r7,r2 @ h+=X[i]
- str r2,[sp,#12*4]
- eor r2,r5,r6
- add r7,r7,r0,ror#6 @ h+=Sigma1(e)
- and r2,r2,r4
- add r7,r7,r12 @ h+=K256[i]
- eor r2,r2,r6 @ Ch(e,f,g)
- eor r0,r8,r8,ror#11
- add r7,r7,r2 @ h+=Ch(e,f,g)
-#if 28==31
- and r12,r12,#0xff
- cmp r12,#0xf2 @ done?
-#endif
-#if 28<15
-# if __ARM_ARCH__>=7
- ldr r2,[r1],#4 @ prefetch
-# else
- ldrb r2,[r1,#3]
-# endif
- eor r12,r8,r9 @ a^b, b^c in next round
-#else
- ldr r2,[sp,#14*4] @ from future BODY_16_xx
- eor r12,r8,r9 @ a^b, b^c in next round
- ldr r1,[sp,#11*4] @ from future BODY_16_xx
-#endif
- eor r0,r0,r8,ror#20 @ Sigma0(a)
- and r3,r3,r12 @ (b^c)&=(a^b)
- add r11,r11,r7 @ d+=h
- eor r3,r3,r9 @ Maj(a,b,c)
- add r7,r7,r0,ror#2 @ h+=Sigma0(a)
- @ add r7,r7,r3 @ h+=Maj(a,b,c)
- @ ldr r2,[sp,#14*4] @ 29
- @ ldr r1,[sp,#11*4]
- mov r0,r2,ror#7
- add r7,r7,r3 @ h+=Maj(a,b,c) from the past
- mov r3,r1,ror#17
- eor r0,r0,r2,ror#18
- eor r3,r3,r1,ror#19
- eor r0,r0,r2,lsr#3 @ sigma0(X[i+1])
- ldr r2,[sp,#13*4]
- eor r3,r3,r1,lsr#10 @ sigma1(X[i+14])
- ldr r1,[sp,#6*4]
-
- add r3,r3,r0
- eor r0,r11,r11,ror#5 @ from BODY_00_15
- add r2,r2,r3
- eor r0,r0,r11,ror#19 @ Sigma1(e)
- add r2,r2,r1 @ X[i]
- ldr r3,[r14],#4 @ *K256++
- add r6,r6,r2 @ h+=X[i]
- str r2,[sp,#13*4]
- eor r2,r4,r5
- add r6,r6,r0,ror#6 @ h+=Sigma1(e)
- and r2,r2,r11
- add r6,r6,r3 @ h+=K256[i]
- eor r2,r2,r5 @ Ch(e,f,g)
- eor r0,r7,r7,ror#11
- add r6,r6,r2 @ h+=Ch(e,f,g)
-#if 29==31
- and r3,r3,#0xff
- cmp r3,#0xf2 @ done?
-#endif
-#if 29<15
-# if __ARM_ARCH__>=7
- ldr r2,[r1],#4 @ prefetch
-# else
- ldrb r2,[r1,#3]
-# endif
- eor r3,r7,r8 @ a^b, b^c in next round
-#else
- ldr r2,[sp,#15*4] @ from future BODY_16_xx
- eor r3,r7,r8 @ a^b, b^c in next round
- ldr r1,[sp,#12*4] @ from future BODY_16_xx
-#endif
- eor r0,r0,r7,ror#20 @ Sigma0(a)
- and r12,r12,r3 @ (b^c)&=(a^b)
- add r10,r10,r6 @ d+=h
- eor r12,r12,r8 @ Maj(a,b,c)
- add r6,r6,r0,ror#2 @ h+=Sigma0(a)
- @ add r6,r6,r12 @ h+=Maj(a,b,c)
- @ ldr r2,[sp,#15*4] @ 30
- @ ldr r1,[sp,#12*4]
- mov r0,r2,ror#7
- add r6,r6,r12 @ h+=Maj(a,b,c) from the past
- mov r12,r1,ror#17
- eor r0,r0,r2,ror#18
- eor r12,r12,r1,ror#19
- eor r0,r0,r2,lsr#3 @ sigma0(X[i+1])
- ldr r2,[sp,#14*4]
- eor r12,r12,r1,lsr#10 @ sigma1(X[i+14])
- ldr r1,[sp,#7*4]
-
- add r12,r12,r0
- eor r0,r10,r10,ror#5 @ from BODY_00_15
- add r2,r2,r12
- eor r0,r0,r10,ror#19 @ Sigma1(e)
- add r2,r2,r1 @ X[i]
- ldr r12,[r14],#4 @ *K256++
- add r5,r5,r2 @ h+=X[i]
- str r2,[sp,#14*4]
- eor r2,r11,r4
- add r5,r5,r0,ror#6 @ h+=Sigma1(e)
- and r2,r2,r10
- add r5,r5,r12 @ h+=K256[i]
- eor r2,r2,r4 @ Ch(e,f,g)
- eor r0,r6,r6,ror#11
- add r5,r5,r2 @ h+=Ch(e,f,g)
-#if 30==31
- and r12,r12,#0xff
- cmp r12,#0xf2 @ done?
-#endif
-#if 30<15
-# if __ARM_ARCH__>=7
- ldr r2,[r1],#4 @ prefetch
-# else
- ldrb r2,[r1,#3]
-# endif
- eor r12,r6,r7 @ a^b, b^c in next round
-#else
- ldr r2,[sp,#0*4] @ from future BODY_16_xx
- eor r12,r6,r7 @ a^b, b^c in next round
- ldr r1,[sp,#13*4] @ from future BODY_16_xx
-#endif
- eor r0,r0,r6,ror#20 @ Sigma0(a)
- and r3,r3,r12 @ (b^c)&=(a^b)
- add r9,r9,r5 @ d+=h
- eor r3,r3,r7 @ Maj(a,b,c)
- add r5,r5,r0,ror#2 @ h+=Sigma0(a)
- @ add r5,r5,r3 @ h+=Maj(a,b,c)
- @ ldr r2,[sp,#0*4] @ 31
- @ ldr r1,[sp,#13*4]
- mov r0,r2,ror#7
- add r5,r5,r3 @ h+=Maj(a,b,c) from the past
- mov r3,r1,ror#17
- eor r0,r0,r2,ror#18
- eor r3,r3,r1,ror#19
- eor r0,r0,r2,lsr#3 @ sigma0(X[i+1])
- ldr r2,[sp,#15*4]
- eor r3,r3,r1,lsr#10 @ sigma1(X[i+14])
- ldr r1,[sp,#8*4]
-
- add r3,r3,r0
- eor r0,r9,r9,ror#5 @ from BODY_00_15
- add r2,r2,r3
- eor r0,r0,r9,ror#19 @ Sigma1(e)
- add r2,r2,r1 @ X[i]
- ldr r3,[r14],#4 @ *K256++
- add r4,r4,r2 @ h+=X[i]
- str r2,[sp,#15*4]
- eor r2,r10,r11
- add r4,r4,r0,ror#6 @ h+=Sigma1(e)
- and r2,r2,r9
- add r4,r4,r3 @ h+=K256[i]
- eor r2,r2,r11 @ Ch(e,f,g)
- eor r0,r5,r5,ror#11
- add r4,r4,r2 @ h+=Ch(e,f,g)
-#if 31==31
- and r3,r3,#0xff
- cmp r3,#0xf2 @ done?
-#endif
-#if 31<15
-# if __ARM_ARCH__>=7
- ldr r2,[r1],#4 @ prefetch
-# else
- ldrb r2,[r1,#3]
-# endif
- eor r3,r5,r6 @ a^b, b^c in next round
-#else
- ldr r2,[sp,#1*4] @ from future BODY_16_xx
- eor r3,r5,r6 @ a^b, b^c in next round
- ldr r1,[sp,#14*4] @ from future BODY_16_xx
-#endif
- eor r0,r0,r5,ror#20 @ Sigma0(a)
- and r12,r12,r3 @ (b^c)&=(a^b)
- add r8,r8,r4 @ d+=h
- eor r12,r12,r6 @ Maj(a,b,c)
- add r4,r4,r0,ror#2 @ h+=Sigma0(a)
- @ add r4,r4,r12 @ h+=Maj(a,b,c)
-#if __ARM_ARCH__>=7
- ite eq @ Thumb2 thing, sanity check in ARM
-#endif
- ldreq r3,[sp,#16*4] @ pull ctx
- bne .Lrounds_16_xx
-
- add r4,r4,r12 @ h+=Maj(a,b,c) from the past
- ldr r0,[r3,#0]
- ldr r2,[r3,#4]
- ldr r12,[r3,#8]
- add r4,r4,r0
- ldr r0,[r3,#12]
- add r5,r5,r2
- ldr r2,[r3,#16]
- add r6,r6,r12
- ldr r12,[r3,#20]
- add r7,r7,r0
- ldr r0,[r3,#24]
- add r8,r8,r2
- ldr r2,[r3,#28]
- add r9,r9,r12
- ldr r1,[sp,#17*4] @ pull inp
- ldr r12,[sp,#18*4] @ pull inp+len
- add r10,r10,r0
- add r11,r11,r2
- stmia r3,{r4,r5,r6,r7,r8,r9,r10,r11}
- cmp r1,r12
- sub r14,r14,#256 @ rewind Ktbl
- bne .Loop
-
- add sp,sp,#19*4 @ destroy frame
-#if __ARM_ARCH__>=5
- ldmia sp!,{r4-r11,pc}
-#else
- ldmia sp!,{r4-r11,lr}
- tst lr,#1
- moveq pc,lr @ be binary compatible with V4, yet
- .word 0xe12fff1e @ interoperable with Thumb ISA:-)
-#endif
-.size sha256_block_data_order,.-sha256_block_data_order
-#if __ARM_MAX_ARCH__>=7
-.arch armv7-a
-.fpu neon
-
-.global sha256_block_data_order_neon
-.type sha256_block_data_order_neon,%function
-.align 4
-sha256_block_data_order_neon:
-.LNEON:
- stmdb sp!,{r4-r12,lr}
-
- sub r11,sp,#16*4+16
- adr r14,.Lsha256_block_data_order
- sub r14,r14,#.Lsha256_block_data_order-K256
- bic r11,r11,#15 @ align for 128-bit stores
- mov r12,sp
- mov sp,r11 @ alloca
- add r2,r1,r2,lsl#6 @ len to point at the end of inp
-
- vld1.8 {q0},[r1]!
- vld1.8 {q1},[r1]!
- vld1.8 {q2},[r1]!
- vld1.8 {q3},[r1]!
- vld1.32 {q8},[r14,:128]!
- vld1.32 {q9},[r14,:128]!
- vld1.32 {q10},[r14,:128]!
- vld1.32 {q11},[r14,:128]!
- vrev32.8 q0,q0 @ yes, even on
- str r0,[sp,#64]
- vrev32.8 q1,q1 @ big-endian
- str r1,[sp,#68]
- mov r1,sp
- vrev32.8 q2,q2
- str r2,[sp,#72]
- vrev32.8 q3,q3
- str r12,[sp,#76] @ save original sp
- vadd.i32 q8,q8,q0
- vadd.i32 q9,q9,q1
- vst1.32 {q8},[r1,:128]!
- vadd.i32 q10,q10,q2
- vst1.32 {q9},[r1,:128]!
- vadd.i32 q11,q11,q3
- vst1.32 {q10},[r1,:128]!
- vst1.32 {q11},[r1,:128]!
-
- ldmia r0,{r4-r11}
- sub r1,r1,#64
- ldr r2,[sp,#0]
- eor r12,r12,r12
- eor r3,r5,r6
- b .L_00_48
-
-.align 4
-.L_00_48:
- vext.8 q8,q0,q1,#4
- add r11,r11,r2
- eor r2,r9,r10
- eor r0,r8,r8,ror#5
- vext.8 q9,q2,q3,#4
- add r4,r4,r12
- and r2,r2,r8
- eor r12,r0,r8,ror#19
- vshr.u32 q10,q8,#7
- eor r0,r4,r4,ror#11
- eor r2,r2,r10
- vadd.i32 q0,q0,q9
- add r11,r11,r12,ror#6
- eor r12,r4,r5
- vshr.u32 q9,q8,#3
- eor r0,r0,r4,ror#20
- add r11,r11,r2
- vsli.32 q10,q8,#25
- ldr r2,[sp,#4]
- and r3,r3,r12
- vshr.u32 q11,q8,#18
- add r7,r7,r11
- add r11,r11,r0,ror#2
- eor r3,r3,r5
- veor q9,q9,q10
- add r10,r10,r2
- vsli.32 q11,q8,#14
- eor r2,r8,r9
- eor r0,r7,r7,ror#5
- vshr.u32 d24,d7,#17
- add r11,r11,r3
- and r2,r2,r7
- veor q9,q9,q11
- eor r3,r0,r7,ror#19
- eor r0,r11,r11,ror#11
- vsli.32 d24,d7,#15
- eor r2,r2,r9
- add r10,r10,r3,ror#6
- vshr.u32 d25,d7,#10
- eor r3,r11,r4
- eor r0,r0,r11,ror#20
- vadd.i32 q0,q0,q9
- add r10,r10,r2
- ldr r2,[sp,#8]
- veor d25,d25,d24
- and r12,r12,r3
- add r6,r6,r10
- vshr.u32 d24,d7,#19
- add r10,r10,r0,ror#2
- eor r12,r12,r4
- vsli.32 d24,d7,#13
- add r9,r9,r2
- eor r2,r7,r8
- veor d25,d25,d24
- eor r0,r6,r6,ror#5
- add r10,r10,r12
- vadd.i32 d0,d0,d25
- and r2,r2,r6
- eor r12,r0,r6,ror#19
- vshr.u32 d24,d0,#17
- eor r0,r10,r10,ror#11
- eor r2,r2,r8
- vsli.32 d24,d0,#15
- add r9,r9,r12,ror#6
- eor r12,r10,r11
- vshr.u32 d25,d0,#10
- eor r0,r0,r10,ror#20
- add r9,r9,r2
- veor d25,d25,d24
- ldr r2,[sp,#12]
- and r3,r3,r12
- vshr.u32 d24,d0,#19
- add r5,r5,r9
- add r9,r9,r0,ror#2
- eor r3,r3,r11
- vld1.32 {q8},[r14,:128]!
- add r8,r8,r2
- vsli.32 d24,d0,#13
- eor r2,r6,r7
- eor r0,r5,r5,ror#5
- veor d25,d25,d24
- add r9,r9,r3
- and r2,r2,r5
- vadd.i32 d1,d1,d25
- eor r3,r0,r5,ror#19
- eor r0,r9,r9,ror#11
- vadd.i32 q8,q8,q0
- eor r2,r2,r7
- add r8,r8,r3,ror#6
- eor r3,r9,r10
- eor r0,r0,r9,ror#20
- add r8,r8,r2
- ldr r2,[sp,#16]
- and r12,r12,r3
- add r4,r4,r8
- vst1.32 {q8},[r1,:128]!
- add r8,r8,r0,ror#2
- eor r12,r12,r10
- vext.8 q8,q1,q2,#4
- add r7,r7,r2
- eor r2,r5,r6
- eor r0,r4,r4,ror#5
- vext.8 q9,q3,q0,#4
- add r8,r8,r12
- and r2,r2,r4
- eor r12,r0,r4,ror#19
- vshr.u32 q10,q8,#7
- eor r0,r8,r8,ror#11
- eor r2,r2,r6
- vadd.i32 q1,q1,q9
- add r7,r7,r12,ror#6
- eor r12,r8,r9
- vshr.u32 q9,q8,#3
- eor r0,r0,r8,ror#20
- add r7,r7,r2
- vsli.32 q10,q8,#25
- ldr r2,[sp,#20]
- and r3,r3,r12
- vshr.u32 q11,q8,#18
- add r11,r11,r7
- add r7,r7,r0,ror#2
- eor r3,r3,r9
- veor q9,q9,q10
- add r6,r6,r2
- vsli.32 q11,q8,#14
- eor r2,r4,r5
- eor r0,r11,r11,ror#5
- vshr.u32 d24,d1,#17
- add r7,r7,r3
- and r2,r2,r11
- veor q9,q9,q11
- eor r3,r0,r11,ror#19
- eor r0,r7,r7,ror#11
- vsli.32 d24,d1,#15
- eor r2,r2,r5
- add r6,r6,r3,ror#6
- vshr.u32 d25,d1,#10
- eor r3,r7,r8
- eor r0,r0,r7,ror#20
- vadd.i32 q1,q1,q9
- add r6,r6,r2
- ldr r2,[sp,#24]
- veor d25,d25,d24
- and r12,r12,r3
- add r10,r10,r6
- vshr.u32 d24,d1,#19
- add r6,r6,r0,ror#2
- eor r12,r12,r8
- vsli.32 d24,d1,#13
- add r5,r5,r2
- eor r2,r11,r4
- veor d25,d25,d24
- eor r0,r10,r10,ror#5
- add r6,r6,r12
- vadd.i32 d2,d2,d25
- and r2,r2,r10
- eor r12,r0,r10,ror#19
- vshr.u32 d24,d2,#17
- eor r0,r6,r6,ror#11
- eor r2,r2,r4
- vsli.32 d24,d2,#15
- add r5,r5,r12,ror#6
- eor r12,r6,r7
- vshr.u32 d25,d2,#10
- eor r0,r0,r6,ror#20
- add r5,r5,r2
- veor d25,d25,d24
- ldr r2,[sp,#28]
- and r3,r3,r12
- vshr.u32 d24,d2,#19
- add r9,r9,r5
- add r5,r5,r0,ror#2
- eor r3,r3,r7
- vld1.32 {q8},[r14,:128]!
- add r4,r4,r2
- vsli.32 d24,d2,#13
- eor r2,r10,r11
- eor r0,r9,r9,ror#5
- veor d25,d25,d24
- add r5,r5,r3
- and r2,r2,r9
- vadd.i32 d3,d3,d25
- eor r3,r0,r9,ror#19
- eor r0,r5,r5,ror#11
- vadd.i32 q8,q8,q1
- eor r2,r2,r11
- add r4,r4,r3,ror#6
- eor r3,r5,r6
- eor r0,r0,r5,ror#20
- add r4,r4,r2
- ldr r2,[sp,#32]
- and r12,r12,r3
- add r8,r8,r4
- vst1.32 {q8},[r1,:128]!
- add r4,r4,r0,ror#2
- eor r12,r12,r6
- vext.8 q8,q2,q3,#4
- add r11,r11,r2
- eor r2,r9,r10
- eor r0,r8,r8,ror#5
- vext.8 q9,q0,q1,#4
- add r4,r4,r12
- and r2,r2,r8
- eor r12,r0,r8,ror#19
- vshr.u32 q10,q8,#7
- eor r0,r4,r4,ror#11
- eor r2,r2,r10
- vadd.i32 q2,q2,q9
- add r11,r11,r12,ror#6
- eor r12,r4,r5
- vshr.u32 q9,q8,#3
- eor r0,r0,r4,ror#20
- add r11,r11,r2
- vsli.32 q10,q8,#25
- ldr r2,[sp,#36]
- and r3,r3,r12
- vshr.u32 q11,q8,#18
- add r7,r7,r11
- add r11,r11,r0,ror#2
- eor r3,r3,r5
- veor q9,q9,q10
- add r10,r10,r2
- vsli.32 q11,q8,#14
- eor r2,r8,r9
- eor r0,r7,r7,ror#5
- vshr.u32 d24,d3,#17
- add r11,r11,r3
- and r2,r2,r7
- veor q9,q9,q11
- eor r3,r0,r7,ror#19
- eor r0,r11,r11,ror#11
- vsli.32 d24,d3,#15
- eor r2,r2,r9
- add r10,r10,r3,ror#6
- vshr.u32 d25,d3,#10
- eor r3,r11,r4
- eor r0,r0,r11,ror#20
- vadd.i32 q2,q2,q9
- add r10,r10,r2
- ldr r2,[sp,#40]
- veor d25,d25,d24
- and r12,r12,r3
- add r6,r6,r10
- vshr.u32 d24,d3,#19
- add r10,r10,r0,ror#2
- eor r12,r12,r4
- vsli.32 d24,d3,#13
- add r9,r9,r2
- eor r2,r7,r8
- veor d25,d25,d24
- eor r0,r6,r6,ror#5
- add r10,r10,r12
- vadd.i32 d4,d4,d25
- and r2,r2,r6
- eor r12,r0,r6,ror#19
- vshr.u32 d24,d4,#17
- eor r0,r10,r10,ror#11
- eor r2,r2,r8
- vsli.32 d24,d4,#15
- add r9,r9,r12,ror#6
- eor r12,r10,r11
- vshr.u32 d25,d4,#10
- eor r0,r0,r10,ror#20
- add r9,r9,r2
- veor d25,d25,d24
- ldr r2,[sp,#44]
- and r3,r3,r12
- vshr.u32 d24,d4,#19
- add r5,r5,r9
- add r9,r9,r0,ror#2
- eor r3,r3,r11
- vld1.32 {q8},[r14,:128]!
- add r8,r8,r2
- vsli.32 d24,d4,#13
- eor r2,r6,r7
- eor r0,r5,r5,ror#5
- veor d25,d25,d24
- add r9,r9,r3
- and r2,r2,r5
- vadd.i32 d5,d5,d25
- eor r3,r0,r5,ror#19
- eor r0,r9,r9,ror#11
- vadd.i32 q8,q8,q2
- eor r2,r2,r7
- add r8,r8,r3,ror#6
- eor r3,r9,r10
- eor r0,r0,r9,ror#20
- add r8,r8,r2
- ldr r2,[sp,#48]
- and r12,r12,r3
- add r4,r4,r8
- vst1.32 {q8},[r1,:128]!
- add r8,r8,r0,ror#2
- eor r12,r12,r10
- vext.8 q8,q3,q0,#4
- add r7,r7,r2
- eor r2,r5,r6
- eor r0,r4,r4,ror#5
- vext.8 q9,q1,q2,#4
- add r8,r8,r12
- and r2,r2,r4
- eor r12,r0,r4,ror#19
- vshr.u32 q10,q8,#7
- eor r0,r8,r8,ror#11
- eor r2,r2,r6
- vadd.i32 q3,q3,q9
- add r7,r7,r12,ror#6
- eor r12,r8,r9
- vshr.u32 q9,q8,#3
- eor r0,r0,r8,ror#20
- add r7,r7,r2
- vsli.32 q10,q8,#25
- ldr r2,[sp,#52]
- and r3,r3,r12
- vshr.u32 q11,q8,#18
- add r11,r11,r7
- add r7,r7,r0,ror#2
- eor r3,r3,r9
- veor q9,q9,q10
- add r6,r6,r2
- vsli.32 q11,q8,#14
- eor r2,r4,r5
- eor r0,r11,r11,ror#5
- vshr.u32 d24,d5,#17
- add r7,r7,r3
- and r2,r2,r11
- veor q9,q9,q11
- eor r3,r0,r11,ror#19
- eor r0,r7,r7,ror#11
- vsli.32 d24,d5,#15
- eor r2,r2,r5
- add r6,r6,r3,ror#6
- vshr.u32 d25,d5,#10
- eor r3,r7,r8
- eor r0,r0,r7,ror#20
- vadd.i32 q3,q3,q9
- add r6,r6,r2
- ldr r2,[sp,#56]
- veor d25,d25,d24
- and r12,r12,r3
- add r10,r10,r6
- vshr.u32 d24,d5,#19
- add r6,r6,r0,ror#2
- eor r12,r12,r8
- vsli.32 d24,d5,#13
- add r5,r5,r2
- eor r2,r11,r4
- veor d25,d25,d24
- eor r0,r10,r10,ror#5
- add r6,r6,r12
- vadd.i32 d6,d6,d25
- and r2,r2,r10
- eor r12,r0,r10,ror#19
- vshr.u32 d24,d6,#17
- eor r0,r6,r6,ror#11
- eor r2,r2,r4
- vsli.32 d24,d6,#15
- add r5,r5,r12,ror#6
- eor r12,r6,r7
- vshr.u32 d25,d6,#10
- eor r0,r0,r6,ror#20
- add r5,r5,r2
- veor d25,d25,d24
- ldr r2,[sp,#60]
- and r3,r3,r12
- vshr.u32 d24,d6,#19
- add r9,r9,r5
- add r5,r5,r0,ror#2
- eor r3,r3,r7
- vld1.32 {q8},[r14,:128]!
- add r4,r4,r2
- vsli.32 d24,d6,#13
- eor r2,r10,r11
- eor r0,r9,r9,ror#5
- veor d25,d25,d24
- add r5,r5,r3
- and r2,r2,r9
- vadd.i32 d7,d7,d25
- eor r3,r0,r9,ror#19
- eor r0,r5,r5,ror#11
- vadd.i32 q8,q8,q3
- eor r2,r2,r11
- add r4,r4,r3,ror#6
- eor r3,r5,r6
- eor r0,r0,r5,ror#20
- add r4,r4,r2
- ldr r2,[r14]
- and r12,r12,r3
- add r8,r8,r4
- vst1.32 {q8},[r1,:128]!
- add r4,r4,r0,ror#2
- eor r12,r12,r6
- teq r2,#0 @ check for K256 terminator
- ldr r2,[sp,#0]
- sub r1,r1,#64
- bne .L_00_48
-
- ldr r1,[sp,#68]
- ldr r0,[sp,#72]
- sub r14,r14,#256 @ rewind r14
- teq r1,r0
- it eq
- subeq r1,r1,#64 @ avoid SEGV
- vld1.8 {q0},[r1]! @ load next input block
- vld1.8 {q1},[r1]!
- vld1.8 {q2},[r1]!
- vld1.8 {q3},[r1]!
- it ne
- strne r1,[sp,#68]
- mov r1,sp
- add r11,r11,r2
- eor r2,r9,r10
- eor r0,r8,r8,ror#5
- add r4,r4,r12
- vld1.32 {q8},[r14,:128]!
- and r2,r2,r8
- eor r12,r0,r8,ror#19
- eor r0,r4,r4,ror#11
- eor r2,r2,r10
- vrev32.8 q0,q0
- add r11,r11,r12,ror#6
- eor r12,r4,r5
- eor r0,r0,r4,ror#20
- add r11,r11,r2
- vadd.i32 q8,q8,q0
- ldr r2,[sp,#4]
- and r3,r3,r12
- add r7,r7,r11
- add r11,r11,r0,ror#2
- eor r3,r3,r5
- add r10,r10,r2
- eor r2,r8,r9
- eor r0,r7,r7,ror#5
- add r11,r11,r3
- and r2,r2,r7
- eor r3,r0,r7,ror#19
- eor r0,r11,r11,ror#11
- eor r2,r2,r9
- add r10,r10,r3,ror#6
- eor r3,r11,r4
- eor r0,r0,r11,ror#20
- add r10,r10,r2
- ldr r2,[sp,#8]
- and r12,r12,r3
- add r6,r6,r10
- add r10,r10,r0,ror#2
- eor r12,r12,r4
- add r9,r9,r2
- eor r2,r7,r8
- eor r0,r6,r6,ror#5
- add r10,r10,r12
- and r2,r2,r6
- eor r12,r0,r6,ror#19
- eor r0,r10,r10,ror#11
- eor r2,r2,r8
- add r9,r9,r12,ror#6
- eor r12,r10,r11
- eor r0,r0,r10,ror#20
- add r9,r9,r2
- ldr r2,[sp,#12]
- and r3,r3,r12
- add r5,r5,r9
- add r9,r9,r0,ror#2
- eor r3,r3,r11
- add r8,r8,r2
- eor r2,r6,r7
- eor r0,r5,r5,ror#5
- add r9,r9,r3
- and r2,r2,r5
- eor r3,r0,r5,ror#19
- eor r0,r9,r9,ror#11
- eor r2,r2,r7
- add r8,r8,r3,ror#6
- eor r3,r9,r10
- eor r0,r0,r9,ror#20
- add r8,r8,r2
- ldr r2,[sp,#16]
- and r12,r12,r3
- add r4,r4,r8
- add r8,r8,r0,ror#2
- eor r12,r12,r10
- vst1.32 {q8},[r1,:128]!
- add r7,r7,r2
- eor r2,r5,r6
- eor r0,r4,r4,ror#5
- add r8,r8,r12
- vld1.32 {q8},[r14,:128]!
- and r2,r2,r4
- eor r12,r0,r4,ror#19
- eor r0,r8,r8,ror#11
- eor r2,r2,r6
- vrev32.8 q1,q1
- add r7,r7,r12,ror#6
- eor r12,r8,r9
- eor r0,r0,r8,ror#20
- add r7,r7,r2
- vadd.i32 q8,q8,q1
- ldr r2,[sp,#20]
- and r3,r3,r12
- add r11,r11,r7
- add r7,r7,r0,ror#2
- eor r3,r3,r9
- add r6,r6,r2
- eor r2,r4,r5
- eor r0,r11,r11,ror#5
- add r7,r7,r3
- and r2,r2,r11
- eor r3,r0,r11,ror#19
- eor r0,r7,r7,ror#11
- eor r2,r2,r5
- add r6,r6,r3,ror#6
- eor r3,r7,r8
- eor r0,r0,r7,ror#20
- add r6,r6,r2
- ldr r2,[sp,#24]
- and r12,r12,r3
- add r10,r10,r6
- add r6,r6,r0,ror#2
- eor r12,r12,r8
- add r5,r5,r2
- eor r2,r11,r4
- eor r0,r10,r10,ror#5
- add r6,r6,r12
- and r2,r2,r10
- eor r12,r0,r10,ror#19
- eor r0,r6,r6,ror#11
- eor r2,r2,r4
- add r5,r5,r12,ror#6
- eor r12,r6,r7
- eor r0,r0,r6,ror#20
- add r5,r5,r2
- ldr r2,[sp,#28]
- and r3,r3,r12
- add r9,r9,r5
- add r5,r5,r0,ror#2
- eor r3,r3,r7
- add r4,r4,r2
- eor r2,r10,r11
- eor r0,r9,r9,ror#5
- add r5,r5,r3
- and r2,r2,r9
- eor r3,r0,r9,ror#19
- eor r0,r5,r5,ror#11
- eor r2,r2,r11
- add r4,r4,r3,ror#6
- eor r3,r5,r6
- eor r0,r0,r5,ror#20
- add r4,r4,r2
- ldr r2,[sp,#32]
- and r12,r12,r3
- add r8,r8,r4
- add r4,r4,r0,ror#2
- eor r12,r12,r6
- vst1.32 {q8},[r1,:128]!
- add r11,r11,r2
- eor r2,r9,r10
- eor r0,r8,r8,ror#5
- add r4,r4,r12
- vld1.32 {q8},[r14,:128]!
- and r2,r2,r8
- eor r12,r0,r8,ror#19
- eor r0,r4,r4,ror#11
- eor r2,r2,r10
- vrev32.8 q2,q2
- add r11,r11,r12,ror#6
- eor r12,r4,r5
- eor r0,r0,r4,ror#20
- add r11,r11,r2
- vadd.i32 q8,q8,q2
- ldr r2,[sp,#36]
- and r3,r3,r12
- add r7,r7,r11
- add r11,r11,r0,ror#2
- eor r3,r3,r5
- add r10,r10,r2
- eor r2,r8,r9
- eor r0,r7,r7,ror#5
- add r11,r11,r3
- and r2,r2,r7
- eor r3,r0,r7,ror#19
- eor r0,r11,r11,ror#11
- eor r2,r2,r9
- add r10,r10,r3,ror#6
- eor r3,r11,r4
- eor r0,r0,r11,ror#20
- add r10,r10,r2
- ldr r2,[sp,#40]
- and r12,r12,r3
- add r6,r6,r10
- add r10,r10,r0,ror#2
- eor r12,r12,r4
- add r9,r9,r2
- eor r2,r7,r8
- eor r0,r6,r6,ror#5
- add r10,r10,r12
- and r2,r2,r6
- eor r12,r0,r6,ror#19
- eor r0,r10,r10,ror#11
- eor r2,r2,r8
- add r9,r9,r12,ror#6
- eor r12,r10,r11
- eor r0,r0,r10,ror#20
- add r9,r9,r2
- ldr r2,[sp,#44]
- and r3,r3,r12
- add r5,r5,r9
- add r9,r9,r0,ror#2
- eor r3,r3,r11
- add r8,r8,r2
- eor r2,r6,r7
- eor r0,r5,r5,ror#5
- add r9,r9,r3
- and r2,r2,r5
- eor r3,r0,r5,ror#19
- eor r0,r9,r9,ror#11
- eor r2,r2,r7
- add r8,r8,r3,ror#6
- eor r3,r9,r10
- eor r0,r0,r9,ror#20
- add r8,r8,r2
- ldr r2,[sp,#48]
- and r12,r12,r3
- add r4,r4,r8
- add r8,r8,r0,ror#2
- eor r12,r12,r10
- vst1.32 {q8},[r1,:128]!
- add r7,r7,r2
- eor r2,r5,r6
- eor r0,r4,r4,ror#5
- add r8,r8,r12
- vld1.32 {q8},[r14,:128]!
- and r2,r2,r4
- eor r12,r0,r4,ror#19
- eor r0,r8,r8,ror#11
- eor r2,r2,r6
- vrev32.8 q3,q3
- add r7,r7,r12,ror#6
- eor r12,r8,r9
- eor r0,r0,r8,ror#20
- add r7,r7,r2
- vadd.i32 q8,q8,q3
- ldr r2,[sp,#52]
- and r3,r3,r12
- add r11,r11,r7
- add r7,r7,r0,ror#2
- eor r3,r3,r9
- add r6,r6,r2
- eor r2,r4,r5
- eor r0,r11,r11,ror#5
- add r7,r7,r3
- and r2,r2,r11
- eor r3,r0,r11,ror#19
- eor r0,r7,r7,ror#11
- eor r2,r2,r5
- add r6,r6,r3,ror#6
- eor r3,r7,r8
- eor r0,r0,r7,ror#20
- add r6,r6,r2
- ldr r2,[sp,#56]
- and r12,r12,r3
- add r10,r10,r6
- add r6,r6,r0,ror#2
- eor r12,r12,r8
- add r5,r5,r2
- eor r2,r11,r4
- eor r0,r10,r10,ror#5
- add r6,r6,r12
- and r2,r2,r10
- eor r12,r0,r10,ror#19
- eor r0,r6,r6,ror#11
- eor r2,r2,r4
- add r5,r5,r12,ror#6
- eor r12,r6,r7
- eor r0,r0,r6,ror#20
- add r5,r5,r2
- ldr r2,[sp,#60]
- and r3,r3,r12
- add r9,r9,r5
- add r5,r5,r0,ror#2
- eor r3,r3,r7
- add r4,r4,r2
- eor r2,r10,r11
- eor r0,r9,r9,ror#5
- add r5,r5,r3
- and r2,r2,r9
- eor r3,r0,r9,ror#19
- eor r0,r5,r5,ror#11
- eor r2,r2,r11
- add r4,r4,r3,ror#6
- eor r3,r5,r6
- eor r0,r0,r5,ror#20
- add r4,r4,r2
- ldr r2,[sp,#64]
- and r12,r12,r3
- add r8,r8,r4
- add r4,r4,r0,ror#2
- eor r12,r12,r6
- vst1.32 {q8},[r1,:128]!
- ldr r0,[r2,#0]
- add r4,r4,r12 @ h+=Maj(a,b,c) from the past
- ldr r12,[r2,#4]
- ldr r3,[r2,#8]
- ldr r1,[r2,#12]
- add r4,r4,r0 @ accumulate
- ldr r0,[r2,#16]
- add r5,r5,r12
- ldr r12,[r2,#20]
- add r6,r6,r3
- ldr r3,[r2,#24]
- add r7,r7,r1
- ldr r1,[r2,#28]
- add r8,r8,r0
- str r4,[r2],#4
- add r9,r9,r12
- str r5,[r2],#4
- add r10,r10,r3
- str r6,[r2],#4
- add r11,r11,r1
- str r7,[r2],#4
- stmia r2,{r8-r11}
-
- ittte ne
- movne r1,sp
- ldrne r2,[sp,#0]
- eorne r12,r12,r12
- ldreq sp,[sp,#76] @ restore original sp
- itt ne
- eorne r3,r5,r6
- bne .L_00_48
-
- ldmia sp!,{r4-r12,pc}
-.size sha256_block_data_order_neon,.-sha256_block_data_order_neon
-#endif
-#if __ARM_MAX_ARCH__>=7 && !defined(__KERNEL__)
-
-# ifdef __thumb2__
-# define INST(a,b,c,d) .byte c,d|0xc,a,b
-# else
-# define INST(a,b,c,d) .byte a,b,c,d
-# endif
-
-.type sha256_block_data_order_armv8,%function
-.align 5
-sha256_block_data_order_armv8:
-.LARMv8:
- vld1.32 {q0,q1},[r0]
-# ifdef __thumb2__
- adr r3,.LARMv8
- sub r3,r3,#.LARMv8-K256
-# else
- adrl r3,K256
-# endif
- add r2,r1,r2,lsl#6 @ len to point at the end of inp
-
-.Loop_v8:
- vld1.8 {q8-q9},[r1]!
- vld1.8 {q10-q11},[r1]!
- vld1.32 {q12},[r3]!
- vrev32.8 q8,q8
- vrev32.8 q9,q9
- vrev32.8 q10,q10
- vrev32.8 q11,q11
- vmov q14,q0 @ offload
- vmov q15,q1
- teq r1,r2
- vld1.32 {q13},[r3]!
- vadd.i32 q12,q12,q8
- INST(0xe2,0x03,0xfa,0xf3) @ sha256su0 q8,q9
- vmov q2,q0
- INST(0x68,0x0c,0x02,0xf3) @ sha256h q0,q1,q12
- INST(0x68,0x2c,0x14,0xf3) @ sha256h2 q1,q2,q12
- INST(0xe6,0x0c,0x64,0xf3) @ sha256su1 q8,q10,q11
- vld1.32 {q12},[r3]!
- vadd.i32 q13,q13,q9
- INST(0xe4,0x23,0xfa,0xf3) @ sha256su0 q9,q10
- vmov q2,q0
- INST(0x6a,0x0c,0x02,0xf3) @ sha256h q0,q1,q13
- INST(0x6a,0x2c,0x14,0xf3) @ sha256h2 q1,q2,q13
- INST(0xe0,0x2c,0x66,0xf3) @ sha256su1 q9,q11,q8
- vld1.32 {q13},[r3]!
- vadd.i32 q12,q12,q10
- INST(0xe6,0x43,0xfa,0xf3) @ sha256su0 q10,q11
- vmov q2,q0
- INST(0x68,0x0c,0x02,0xf3) @ sha256h q0,q1,q12
- INST(0x68,0x2c,0x14,0xf3) @ sha256h2 q1,q2,q12
- INST(0xe2,0x4c,0x60,0xf3) @ sha256su1 q10,q8,q9
- vld1.32 {q12},[r3]!
- vadd.i32 q13,q13,q11
- INST(0xe0,0x63,0xfa,0xf3) @ sha256su0 q11,q8
- vmov q2,q0
- INST(0x6a,0x0c,0x02,0xf3) @ sha256h q0,q1,q13
- INST(0x6a,0x2c,0x14,0xf3) @ sha256h2 q1,q2,q13
- INST(0xe4,0x6c,0x62,0xf3) @ sha256su1 q11,q9,q10
- vld1.32 {q13},[r3]!
- vadd.i32 q12,q12,q8
- INST(0xe2,0x03,0xfa,0xf3) @ sha256su0 q8,q9
- vmov q2,q0
- INST(0x68,0x0c,0x02,0xf3) @ sha256h q0,q1,q12
- INST(0x68,0x2c,0x14,0xf3) @ sha256h2 q1,q2,q12
- INST(0xe6,0x0c,0x64,0xf3) @ sha256su1 q8,q10,q11
- vld1.32 {q12},[r3]!
- vadd.i32 q13,q13,q9
- INST(0xe4,0x23,0xfa,0xf3) @ sha256su0 q9,q10
- vmov q2,q0
- INST(0x6a,0x0c,0x02,0xf3) @ sha256h q0,q1,q13
- INST(0x6a,0x2c,0x14,0xf3) @ sha256h2 q1,q2,q13
- INST(0xe0,0x2c,0x66,0xf3) @ sha256su1 q9,q11,q8
- vld1.32 {q13},[r3]!
- vadd.i32 q12,q12,q10
- INST(0xe6,0x43,0xfa,0xf3) @ sha256su0 q10,q11
- vmov q2,q0
- INST(0x68,0x0c,0x02,0xf3) @ sha256h q0,q1,q12
- INST(0x68,0x2c,0x14,0xf3) @ sha256h2 q1,q2,q12
- INST(0xe2,0x4c,0x60,0xf3) @ sha256su1 q10,q8,q9
- vld1.32 {q12},[r3]!
- vadd.i32 q13,q13,q11
- INST(0xe0,0x63,0xfa,0xf3) @ sha256su0 q11,q8
- vmov q2,q0
- INST(0x6a,0x0c,0x02,0xf3) @ sha256h q0,q1,q13
- INST(0x6a,0x2c,0x14,0xf3) @ sha256h2 q1,q2,q13
- INST(0xe4,0x6c,0x62,0xf3) @ sha256su1 q11,q9,q10
- vld1.32 {q13},[r3]!
- vadd.i32 q12,q12,q8
- INST(0xe2,0x03,0xfa,0xf3) @ sha256su0 q8,q9
- vmov q2,q0
- INST(0x68,0x0c,0x02,0xf3) @ sha256h q0,q1,q12
- INST(0x68,0x2c,0x14,0xf3) @ sha256h2 q1,q2,q12
- INST(0xe6,0x0c,0x64,0xf3) @ sha256su1 q8,q10,q11
- vld1.32 {q12},[r3]!
- vadd.i32 q13,q13,q9
- INST(0xe4,0x23,0xfa,0xf3) @ sha256su0 q9,q10
- vmov q2,q0
- INST(0x6a,0x0c,0x02,0xf3) @ sha256h q0,q1,q13
- INST(0x6a,0x2c,0x14,0xf3) @ sha256h2 q1,q2,q13
- INST(0xe0,0x2c,0x66,0xf3) @ sha256su1 q9,q11,q8
- vld1.32 {q13},[r3]!
- vadd.i32 q12,q12,q10
- INST(0xe6,0x43,0xfa,0xf3) @ sha256su0 q10,q11
- vmov q2,q0
- INST(0x68,0x0c,0x02,0xf3) @ sha256h q0,q1,q12
- INST(0x68,0x2c,0x14,0xf3) @ sha256h2 q1,q2,q12
- INST(0xe2,0x4c,0x60,0xf3) @ sha256su1 q10,q8,q9
- vld1.32 {q12},[r3]!
- vadd.i32 q13,q13,q11
- INST(0xe0,0x63,0xfa,0xf3) @ sha256su0 q11,q8
- vmov q2,q0
- INST(0x6a,0x0c,0x02,0xf3) @ sha256h q0,q1,q13
- INST(0x6a,0x2c,0x14,0xf3) @ sha256h2 q1,q2,q13
- INST(0xe4,0x6c,0x62,0xf3) @ sha256su1 q11,q9,q10
- vld1.32 {q13},[r3]!
- vadd.i32 q12,q12,q8
- vmov q2,q0
- INST(0x68,0x0c,0x02,0xf3) @ sha256h q0,q1,q12
- INST(0x68,0x2c,0x14,0xf3) @ sha256h2 q1,q2,q12
-
- vld1.32 {q12},[r3]!
- vadd.i32 q13,q13,q9
- vmov q2,q0
- INST(0x6a,0x0c,0x02,0xf3) @ sha256h q0,q1,q13
- INST(0x6a,0x2c,0x14,0xf3) @ sha256h2 q1,q2,q13
-
- vld1.32 {q13},[r3]
- vadd.i32 q12,q12,q10
- sub r3,r3,#256-16 @ rewind
- vmov q2,q0
- INST(0x68,0x0c,0x02,0xf3) @ sha256h q0,q1,q12
- INST(0x68,0x2c,0x14,0xf3) @ sha256h2 q1,q2,q12
-
- vadd.i32 q13,q13,q11
- vmov q2,q0
- INST(0x6a,0x0c,0x02,0xf3) @ sha256h q0,q1,q13
- INST(0x6a,0x2c,0x14,0xf3) @ sha256h2 q1,q2,q13
-
- vadd.i32 q0,q0,q14
- vadd.i32 q1,q1,q15
- it ne
- bne .Loop_v8
-
- vst1.32 {q0,q1},[r0]
-
- bx lr @ bx lr
-.size sha256_block_data_order_armv8,.-sha256_block_data_order_armv8
-#endif
-.asciz "SHA256 block transform for ARMv4/NEON/ARMv8, CRYPTOGAMS by <appro@openssl.org>"
-.align 2
-#if __ARM_MAX_ARCH__>=7 && !defined(__KERNEL__)
-.comm OPENSSL_armcap_P,4,4
-#endif
diff --git a/arch/arm/crypto/sha512-core.S_shipped b/arch/arm/crypto/sha512-core.S_shipped
deleted file mode 100644
index 03014624f2ab..000000000000
--- a/arch/arm/crypto/sha512-core.S_shipped
+++ /dev/null
@@ -1,1869 +0,0 @@
-@ SPDX-License-Identifier: GPL-2.0
-
-@ This code is taken from the OpenSSL project but the author (Andy Polyakov)
-@ has relicensed it under the GPLv2. Therefore 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.
-@
-@ The original headers, including the original license headers, are
-@ included below for completeness.
-
-@ ====================================================================
-@ Written by Andy Polyakov <appro@openssl.org> for the OpenSSL
-@ project. The module is, however, dual licensed under OpenSSL and
-@ CRYPTOGAMS licenses depending on where you obtain it. For further
-@ details see https://www.openssl.org/~appro/cryptogams/.
-@ ====================================================================
-
-@ SHA512 block procedure for ARMv4. September 2007.
-
-@ This code is ~4.5 (four and a half) times faster than code generated
-@ by gcc 3.4 and it spends ~72 clock cycles per byte [on single-issue
-@ Xscale PXA250 core].
-@
-@ July 2010.
-@
-@ Rescheduling for dual-issue pipeline resulted in 6% improvement on
-@ Cortex A8 core and ~40 cycles per processed byte.
-
-@ February 2011.
-@
-@ Profiler-assisted and platform-specific optimization resulted in 7%
-@ improvement on Coxtex A8 core and ~38 cycles per byte.
-
-@ March 2011.
-@
-@ Add NEON implementation. On Cortex A8 it was measured to process
-@ one byte in 23.3 cycles or ~60% faster than integer-only code.
-
-@ August 2012.
-@
-@ Improve NEON performance by 12% on Snapdragon S4. In absolute
-@ terms it's 22.6 cycles per byte, which is disappointing result.
-@ Technical writers asserted that 3-way S4 pipeline can sustain
-@ multiple NEON instructions per cycle, but dual NEON issue could
-@ not be observed, see https://www.openssl.org/~appro/Snapdragon-S4.html
-@ for further details. On side note Cortex-A15 processes one byte in
-@ 16 cycles.
-
-@ Byte order [in]dependence. =========================================
-@
-@ Originally caller was expected to maintain specific *dword* order in
-@ h[0-7], namely with most significant dword at *lower* address, which
-@ was reflected in below two parameters as 0 and 4. Now caller is
-@ expected to maintain native byte order for whole 64-bit values.
-#ifndef __KERNEL__
-# include "arm_arch.h"
-# define VFP_ABI_PUSH vstmdb sp!,{d8-d15}
-# define VFP_ABI_POP vldmia sp!,{d8-d15}
-#else
-# define __ARM_ARCH__ __LINUX_ARM_ARCH__
-# define __ARM_MAX_ARCH__ 7
-# define VFP_ABI_PUSH
-# define VFP_ABI_POP
-#endif
-
-#ifdef __ARMEL__
-# define LO 0
-# define HI 4
-# define WORD64(hi0,lo0,hi1,lo1) .word lo0,hi0, lo1,hi1
-#else
-# define HI 0
-# define LO 4
-# define WORD64(hi0,lo0,hi1,lo1) .word hi0,lo0, hi1,lo1
-#endif
-
-.text
-#if __ARM_ARCH__<7
-.code 32
-#else
-.syntax unified
-# ifdef __thumb2__
-.thumb
-# else
-.code 32
-# endif
-#endif
-
-.type K512,%object
-.align 5
-K512:
-WORD64(0x428a2f98,0xd728ae22, 0x71374491,0x23ef65cd)
-WORD64(0xb5c0fbcf,0xec4d3b2f, 0xe9b5dba5,0x8189dbbc)
-WORD64(0x3956c25b,0xf348b538, 0x59f111f1,0xb605d019)
-WORD64(0x923f82a4,0xaf194f9b, 0xab1c5ed5,0xda6d8118)
-WORD64(0xd807aa98,0xa3030242, 0x12835b01,0x45706fbe)
-WORD64(0x243185be,0x4ee4b28c, 0x550c7dc3,0xd5ffb4e2)
-WORD64(0x72be5d74,0xf27b896f, 0x80deb1fe,0x3b1696b1)
-WORD64(0x9bdc06a7,0x25c71235, 0xc19bf174,0xcf692694)
-WORD64(0xe49b69c1,0x9ef14ad2, 0xefbe4786,0x384f25e3)
-WORD64(0x0fc19dc6,0x8b8cd5b5, 0x240ca1cc,0x77ac9c65)
-WORD64(0x2de92c6f,0x592b0275, 0x4a7484aa,0x6ea6e483)
-WORD64(0x5cb0a9dc,0xbd41fbd4, 0x76f988da,0x831153b5)
-WORD64(0x983e5152,0xee66dfab, 0xa831c66d,0x2db43210)
-WORD64(0xb00327c8,0x98fb213f, 0xbf597fc7,0xbeef0ee4)
-WORD64(0xc6e00bf3,0x3da88fc2, 0xd5a79147,0x930aa725)
-WORD64(0x06ca6351,0xe003826f, 0x14292967,0x0a0e6e70)
-WORD64(0x27b70a85,0x46d22ffc, 0x2e1b2138,0x5c26c926)
-WORD64(0x4d2c6dfc,0x5ac42aed, 0x53380d13,0x9d95b3df)
-WORD64(0x650a7354,0x8baf63de, 0x766a0abb,0x3c77b2a8)
-WORD64(0x81c2c92e,0x47edaee6, 0x92722c85,0x1482353b)
-WORD64(0xa2bfe8a1,0x4cf10364, 0xa81a664b,0xbc423001)
-WORD64(0xc24b8b70,0xd0f89791, 0xc76c51a3,0x0654be30)
-WORD64(0xd192e819,0xd6ef5218, 0xd6990624,0x5565a910)
-WORD64(0xf40e3585,0x5771202a, 0x106aa070,0x32bbd1b8)
-WORD64(0x19a4c116,0xb8d2d0c8, 0x1e376c08,0x5141ab53)
-WORD64(0x2748774c,0xdf8eeb99, 0x34b0bcb5,0xe19b48a8)
-WORD64(0x391c0cb3,0xc5c95a63, 0x4ed8aa4a,0xe3418acb)
-WORD64(0x5b9cca4f,0x7763e373, 0x682e6ff3,0xd6b2b8a3)
-WORD64(0x748f82ee,0x5defb2fc, 0x78a5636f,0x43172f60)
-WORD64(0x84c87814,0xa1f0ab72, 0x8cc70208,0x1a6439ec)
-WORD64(0x90befffa,0x23631e28, 0xa4506ceb,0xde82bde9)
-WORD64(0xbef9a3f7,0xb2c67915, 0xc67178f2,0xe372532b)
-WORD64(0xca273ece,0xea26619c, 0xd186b8c7,0x21c0c207)
-WORD64(0xeada7dd6,0xcde0eb1e, 0xf57d4f7f,0xee6ed178)
-WORD64(0x06f067aa,0x72176fba, 0x0a637dc5,0xa2c898a6)
-WORD64(0x113f9804,0xbef90dae, 0x1b710b35,0x131c471b)
-WORD64(0x28db77f5,0x23047d84, 0x32caab7b,0x40c72493)
-WORD64(0x3c9ebe0a,0x15c9bebc, 0x431d67c4,0x9c100d4c)
-WORD64(0x4cc5d4be,0xcb3e42b6, 0x597f299c,0xfc657e2a)
-WORD64(0x5fcb6fab,0x3ad6faec, 0x6c44198c,0x4a475817)
-.size K512,.-K512
-#if __ARM_MAX_ARCH__>=7 && !defined(__KERNEL__)
-.LOPENSSL_armcap:
-.word OPENSSL_armcap_P-sha512_block_data_order
-.skip 32-4
-#else
-.skip 32
-#endif
-
-.global sha512_block_data_order
-.type sha512_block_data_order,%function
-sha512_block_data_order:
-.Lsha512_block_data_order:
-#if __ARM_ARCH__<7
- sub r3,pc,#8 @ sha512_block_data_order
-#else
- adr r3,.Lsha512_block_data_order
-#endif
-#if __ARM_MAX_ARCH__>=7 && !defined(__KERNEL__)
- ldr r12,.LOPENSSL_armcap
- ldr r12,[r3,r12] @ OPENSSL_armcap_P
- tst r12,#1
- bne .LNEON
-#endif
- add r2,r1,r2,lsl#7 @ len to point at the end of inp
- stmdb sp!,{r4-r12,lr}
- sub r14,r3,#672 @ K512
- sub sp,sp,#9*8
-
- ldr r7,[r0,#32+LO]
- ldr r8,[r0,#32+HI]
- ldr r9, [r0,#48+LO]
- ldr r10, [r0,#48+HI]
- ldr r11, [r0,#56+LO]
- ldr r12, [r0,#56+HI]
-.Loop:
- str r9, [sp,#48+0]
- str r10, [sp,#48+4]
- str r11, [sp,#56+0]
- str r12, [sp,#56+4]
- ldr r5,[r0,#0+LO]
- ldr r6,[r0,#0+HI]
- ldr r3,[r0,#8+LO]
- ldr r4,[r0,#8+HI]
- ldr r9, [r0,#16+LO]
- ldr r10, [r0,#16+HI]
- ldr r11, [r0,#24+LO]
- ldr r12, [r0,#24+HI]
- str r3,[sp,#8+0]
- str r4,[sp,#8+4]
- str r9, [sp,#16+0]
- str r10, [sp,#16+4]
- str r11, [sp,#24+0]
- str r12, [sp,#24+4]
- ldr r3,[r0,#40+LO]
- ldr r4,[r0,#40+HI]
- str r3,[sp,#40+0]
- str r4,[sp,#40+4]
-
-.L00_15:
-#if __ARM_ARCH__<7
- ldrb r3,[r1,#7]
- ldrb r9, [r1,#6]
- ldrb r10, [r1,#5]
- ldrb r11, [r1,#4]
- ldrb r4,[r1,#3]
- ldrb r12, [r1,#2]
- orr r3,r3,r9,lsl#8
- ldrb r9, [r1,#1]
- orr r3,r3,r10,lsl#16
- ldrb r10, [r1],#8
- orr r3,r3,r11,lsl#24
- orr r4,r4,r12,lsl#8
- orr r4,r4,r9,lsl#16
- orr r4,r4,r10,lsl#24
-#else
- ldr r3,[r1,#4]
- ldr r4,[r1],#8
-#ifdef __ARMEL__
- rev r3,r3
- rev r4,r4
-#endif
-#endif
- @ Sigma1(x) (ROTR((x),14) ^ ROTR((x),18) ^ ROTR((x),41))
- @ LO lo>>14^hi<<18 ^ lo>>18^hi<<14 ^ hi>>9^lo<<23
- @ HI hi>>14^lo<<18 ^ hi>>18^lo<<14 ^ lo>>9^hi<<23
- mov r9,r7,lsr#14
- str r3,[sp,#64+0]
- mov r10,r8,lsr#14
- str r4,[sp,#64+4]
- eor r9,r9,r8,lsl#18
- ldr r11,[sp,#56+0] @ h.lo
- eor r10,r10,r7,lsl#18
- ldr r12,[sp,#56+4] @ h.hi
- eor r9,r9,r7,lsr#18
- eor r10,r10,r8,lsr#18
- eor r9,r9,r8,lsl#14
- eor r10,r10,r7,lsl#14
- eor r9,r9,r8,lsr#9
- eor r10,r10,r7,lsr#9
- eor r9,r9,r7,lsl#23
- eor r10,r10,r8,lsl#23 @ Sigma1(e)
- adds r3,r3,r9
- ldr r9,[sp,#40+0] @ f.lo
- adc r4,r4,r10 @ T += Sigma1(e)
- ldr r10,[sp,#40+4] @ f.hi
- adds r3,r3,r11
- ldr r11,[sp,#48+0] @ g.lo
- adc r4,r4,r12 @ T += h
- ldr r12,[sp,#48+4] @ g.hi
-
- eor r9,r9,r11
- str r7,[sp,#32+0]
- eor r10,r10,r12
- str r8,[sp,#32+4]
- and r9,r9,r7
- str r5,[sp,#0+0]
- and r10,r10,r8
- str r6,[sp,#0+4]
- eor r9,r9,r11
- ldr r11,[r14,#LO] @ K[i].lo
- eor r10,r10,r12 @ Ch(e,f,g)
- ldr r12,[r14,#HI] @ K[i].hi
-
- adds r3,r3,r9
- ldr r7,[sp,#24+0] @ d.lo
- adc r4,r4,r10 @ T += Ch(e,f,g)
- ldr r8,[sp,#24+4] @ d.hi
- adds r3,r3,r11
- and r9,r11,#0xff
- adc r4,r4,r12 @ T += K[i]
- adds r7,r7,r3
- ldr r11,[sp,#8+0] @ b.lo
- adc r8,r8,r4 @ d += T
- teq r9,#148
-
- ldr r12,[sp,#16+0] @ c.lo
-#if __ARM_ARCH__>=7
- it eq @ Thumb2 thing, sanity check in ARM
-#endif
- orreq r14,r14,#1
- @ Sigma0(x) (ROTR((x),28) ^ ROTR((x),34) ^ ROTR((x),39))
- @ LO lo>>28^hi<<4 ^ hi>>2^lo<<30 ^ hi>>7^lo<<25
- @ HI hi>>28^lo<<4 ^ lo>>2^hi<<30 ^ lo>>7^hi<<25
- mov r9,r5,lsr#28
- mov r10,r6,lsr#28
- eor r9,r9,r6,lsl#4
- eor r10,r10,r5,lsl#4
- eor r9,r9,r6,lsr#2
- eor r10,r10,r5,lsr#2
- eor r9,r9,r5,lsl#30
- eor r10,r10,r6,lsl#30
- eor r9,r9,r6,lsr#7
- eor r10,r10,r5,lsr#7
- eor r9,r9,r5,lsl#25
- eor r10,r10,r6,lsl#25 @ Sigma0(a)
- adds r3,r3,r9
- and r9,r5,r11
- adc r4,r4,r10 @ T += Sigma0(a)
-
- ldr r10,[sp,#8+4] @ b.hi
- orr r5,r5,r11
- ldr r11,[sp,#16+4] @ c.hi
- and r5,r5,r12
- and r12,r6,r10
- orr r6,r6,r10
- orr r5,r5,r9 @ Maj(a,b,c).lo
- and r6,r6,r11
- adds r5,r5,r3
- orr r6,r6,r12 @ Maj(a,b,c).hi
- sub sp,sp,#8
- adc r6,r6,r4 @ h += T
- tst r14,#1
- add r14,r14,#8
- tst r14,#1
- beq .L00_15
- ldr r9,[sp,#184+0]
- ldr r10,[sp,#184+4]
- bic r14,r14,#1
-.L16_79:
- @ sigma0(x) (ROTR((x),1) ^ ROTR((x),8) ^ ((x)>>7))
- @ LO lo>>1^hi<<31 ^ lo>>8^hi<<24 ^ lo>>7^hi<<25
- @ HI hi>>1^lo<<31 ^ hi>>8^lo<<24 ^ hi>>7
- mov r3,r9,lsr#1
- ldr r11,[sp,#80+0]
- mov r4,r10,lsr#1
- ldr r12,[sp,#80+4]
- eor r3,r3,r10,lsl#31
- eor r4,r4,r9,lsl#31
- eor r3,r3,r9,lsr#8
- eor r4,r4,r10,lsr#8
- eor r3,r3,r10,lsl#24
- eor r4,r4,r9,lsl#24
- eor r3,r3,r9,lsr#7
- eor r4,r4,r10,lsr#7
- eor r3,r3,r10,lsl#25
-
- @ sigma1(x) (ROTR((x),19) ^ ROTR((x),61) ^ ((x)>>6))
- @ LO lo>>19^hi<<13 ^ hi>>29^lo<<3 ^ lo>>6^hi<<26
- @ HI hi>>19^lo<<13 ^ lo>>29^hi<<3 ^ hi>>6
- mov r9,r11,lsr#19
- mov r10,r12,lsr#19
- eor r9,r9,r12,lsl#13
- eor r10,r10,r11,lsl#13
- eor r9,r9,r12,lsr#29
- eor r10,r10,r11,lsr#29
- eor r9,r9,r11,lsl#3
- eor r10,r10,r12,lsl#3
- eor r9,r9,r11,lsr#6
- eor r10,r10,r12,lsr#6
- ldr r11,[sp,#120+0]
- eor r9,r9,r12,lsl#26
-
- ldr r12,[sp,#120+4]
- adds r3,r3,r9
- ldr r9,[sp,#192+0]
- adc r4,r4,r10
-
- ldr r10,[sp,#192+4]
- adds r3,r3,r11
- adc r4,r4,r12
- adds r3,r3,r9
- adc r4,r4,r10
- @ Sigma1(x) (ROTR((x),14) ^ ROTR((x),18) ^ ROTR((x),41))
- @ LO lo>>14^hi<<18 ^ lo>>18^hi<<14 ^ hi>>9^lo<<23
- @ HI hi>>14^lo<<18 ^ hi>>18^lo<<14 ^ lo>>9^hi<<23
- mov r9,r7,lsr#14
- str r3,[sp,#64+0]
- mov r10,r8,lsr#14
- str r4,[sp,#64+4]
- eor r9,r9,r8,lsl#18
- ldr r11,[sp,#56+0] @ h.lo
- eor r10,r10,r7,lsl#18
- ldr r12,[sp,#56+4] @ h.hi
- eor r9,r9,r7,lsr#18
- eor r10,r10,r8,lsr#18
- eor r9,r9,r8,lsl#14
- eor r10,r10,r7,lsl#14
- eor r9,r9,r8,lsr#9
- eor r10,r10,r7,lsr#9
- eor r9,r9,r7,lsl#23
- eor r10,r10,r8,lsl#23 @ Sigma1(e)
- adds r3,r3,r9
- ldr r9,[sp,#40+0] @ f.lo
- adc r4,r4,r10 @ T += Sigma1(e)
- ldr r10,[sp,#40+4] @ f.hi
- adds r3,r3,r11
- ldr r11,[sp,#48+0] @ g.lo
- adc r4,r4,r12 @ T += h
- ldr r12,[sp,#48+4] @ g.hi
-
- eor r9,r9,r11
- str r7,[sp,#32+0]
- eor r10,r10,r12
- str r8,[sp,#32+4]
- and r9,r9,r7
- str r5,[sp,#0+0]
- and r10,r10,r8
- str r6,[sp,#0+4]
- eor r9,r9,r11
- ldr r11,[r14,#LO] @ K[i].lo
- eor r10,r10,r12 @ Ch(e,f,g)
- ldr r12,[r14,#HI] @ K[i].hi
-
- adds r3,r3,r9
- ldr r7,[sp,#24+0] @ d.lo
- adc r4,r4,r10 @ T += Ch(e,f,g)
- ldr r8,[sp,#24+4] @ d.hi
- adds r3,r3,r11
- and r9,r11,#0xff
- adc r4,r4,r12 @ T += K[i]
- adds r7,r7,r3
- ldr r11,[sp,#8+0] @ b.lo
- adc r8,r8,r4 @ d += T
- teq r9,#23
-
- ldr r12,[sp,#16+0] @ c.lo
-#if __ARM_ARCH__>=7
- it eq @ Thumb2 thing, sanity check in ARM
-#endif
- orreq r14,r14,#1
- @ Sigma0(x) (ROTR((x),28) ^ ROTR((x),34) ^ ROTR((x),39))
- @ LO lo>>28^hi<<4 ^ hi>>2^lo<<30 ^ hi>>7^lo<<25
- @ HI hi>>28^lo<<4 ^ lo>>2^hi<<30 ^ lo>>7^hi<<25
- mov r9,r5,lsr#28
- mov r10,r6,lsr#28
- eor r9,r9,r6,lsl#4
- eor r10,r10,r5,lsl#4
- eor r9,r9,r6,lsr#2
- eor r10,r10,r5,lsr#2
- eor r9,r9,r5,lsl#30
- eor r10,r10,r6,lsl#30
- eor r9,r9,r6,lsr#7
- eor r10,r10,r5,lsr#7
- eor r9,r9,r5,lsl#25
- eor r10,r10,r6,lsl#25 @ Sigma0(a)
- adds r3,r3,r9
- and r9,r5,r11
- adc r4,r4,r10 @ T += Sigma0(a)
-
- ldr r10,[sp,#8+4] @ b.hi
- orr r5,r5,r11
- ldr r11,[sp,#16+4] @ c.hi
- and r5,r5,r12
- and r12,r6,r10
- orr r6,r6,r10
- orr r5,r5,r9 @ Maj(a,b,c).lo
- and r6,r6,r11
- adds r5,r5,r3
- orr r6,r6,r12 @ Maj(a,b,c).hi
- sub sp,sp,#8
- adc r6,r6,r4 @ h += T
- tst r14,#1
- add r14,r14,#8
-#if __ARM_ARCH__>=7
- ittt eq @ Thumb2 thing, sanity check in ARM
-#endif
- ldreq r9,[sp,#184+0]
- ldreq r10,[sp,#184+4]
- beq .L16_79
- bic r14,r14,#1
-
- ldr r3,[sp,#8+0]
- ldr r4,[sp,#8+4]
- ldr r9, [r0,#0+LO]
- ldr r10, [r0,#0+HI]
- ldr r11, [r0,#8+LO]
- ldr r12, [r0,#8+HI]
- adds r9,r5,r9
- str r9, [r0,#0+LO]
- adc r10,r6,r10
- str r10, [r0,#0+HI]
- adds r11,r3,r11
- str r11, [r0,#8+LO]
- adc r12,r4,r12
- str r12, [r0,#8+HI]
-
- ldr r5,[sp,#16+0]
- ldr r6,[sp,#16+4]
- ldr r3,[sp,#24+0]
- ldr r4,[sp,#24+4]
- ldr r9, [r0,#16+LO]
- ldr r10, [r0,#16+HI]
- ldr r11, [r0,#24+LO]
- ldr r12, [r0,#24+HI]
- adds r9,r5,r9
- str r9, [r0,#16+LO]
- adc r10,r6,r10
- str r10, [r0,#16+HI]
- adds r11,r3,r11
- str r11, [r0,#24+LO]
- adc r12,r4,r12
- str r12, [r0,#24+HI]
-
- ldr r3,[sp,#40+0]
- ldr r4,[sp,#40+4]
- ldr r9, [r0,#32+LO]
- ldr r10, [r0,#32+HI]
- ldr r11, [r0,#40+LO]
- ldr r12, [r0,#40+HI]
- adds r7,r7,r9
- str r7,[r0,#32+LO]
- adc r8,r8,r10
- str r8,[r0,#32+HI]
- adds r11,r3,r11
- str r11, [r0,#40+LO]
- adc r12,r4,r12
- str r12, [r0,#40+HI]
-
- ldr r5,[sp,#48+0]
- ldr r6,[sp,#48+4]
- ldr r3,[sp,#56+0]
- ldr r4,[sp,#56+4]
- ldr r9, [r0,#48+LO]
- ldr r10, [r0,#48+HI]
- ldr r11, [r0,#56+LO]
- ldr r12, [r0,#56+HI]
- adds r9,r5,r9
- str r9, [r0,#48+LO]
- adc r10,r6,r10
- str r10, [r0,#48+HI]
- adds r11,r3,r11
- str r11, [r0,#56+LO]
- adc r12,r4,r12
- str r12, [r0,#56+HI]
-
- add sp,sp,#640
- sub r14,r14,#640
-
- teq r1,r2
- bne .Loop
-
- add sp,sp,#8*9 @ destroy frame
-#if __ARM_ARCH__>=5
- ldmia sp!,{r4-r12,pc}
-#else
- ldmia sp!,{r4-r12,lr}
- tst lr,#1
- moveq pc,lr @ be binary compatible with V4, yet
- .word 0xe12fff1e @ interoperable with Thumb ISA:-)
-#endif
-.size sha512_block_data_order,.-sha512_block_data_order
-#if __ARM_MAX_ARCH__>=7
-.arch armv7-a
-.fpu neon
-
-.global sha512_block_data_order_neon
-.type sha512_block_data_order_neon,%function
-.align 4
-sha512_block_data_order_neon:
-.LNEON:
- dmb @ errata #451034 on early Cortex A8
- add r2,r1,r2,lsl#7 @ len to point at the end of inp
- VFP_ABI_PUSH
- adr r3,.Lsha512_block_data_order
- sub r3,r3,.Lsha512_block_data_order-K512
- vldmia r0,{d16-d23} @ load context
-.Loop_neon:
- vshr.u64 d24,d20,#14 @ 0
-#if 0<16
- vld1.64 {d0},[r1]! @ handles unaligned
-#endif
- vshr.u64 d25,d20,#18
-#if 0>0
- vadd.i64 d16,d30 @ h+=Maj from the past
-#endif
- vshr.u64 d26,d20,#41
- vld1.64 {d28},[r3,:64]! @ K[i++]
- vsli.64 d24,d20,#50
- vsli.64 d25,d20,#46
- vmov d29,d20
- vsli.64 d26,d20,#23
-#if 0<16 && defined(__ARMEL__)
- vrev64.8 d0,d0
-#endif
- veor d25,d24
- vbsl d29,d21,d22 @ Ch(e,f,g)
- vshr.u64 d24,d16,#28
- veor d26,d25 @ Sigma1(e)
- vadd.i64 d27,d29,d23
- vshr.u64 d25,d16,#34
- vsli.64 d24,d16,#36
- vadd.i64 d27,d26
- vshr.u64 d26,d16,#39
- vadd.i64 d28,d0
- vsli.64 d25,d16,#30
- veor d30,d16,d17
- vsli.64 d26,d16,#25
- veor d23,d24,d25
- vadd.i64 d27,d28
- vbsl d30,d18,d17 @ Maj(a,b,c)
- veor d23,d26 @ Sigma0(a)
- vadd.i64 d19,d27
- vadd.i64 d30,d27
- @ vadd.i64 d23,d30
- vshr.u64 d24,d19,#14 @ 1
-#if 1<16
- vld1.64 {d1},[r1]! @ handles unaligned
-#endif
- vshr.u64 d25,d19,#18
-#if 1>0
- vadd.i64 d23,d30 @ h+=Maj from the past
-#endif
- vshr.u64 d26,d19,#41
- vld1.64 {d28},[r3,:64]! @ K[i++]
- vsli.64 d24,d19,#50
- vsli.64 d25,d19,#46
- vmov d29,d19
- vsli.64 d26,d19,#23
-#if 1<16 && defined(__ARMEL__)
- vrev64.8 d1,d1
-#endif
- veor d25,d24
- vbsl d29,d20,d21 @ Ch(e,f,g)
- vshr.u64 d24,d23,#28
- veor d26,d25 @ Sigma1(e)
- vadd.i64 d27,d29,d22
- vshr.u64 d25,d23,#34
- vsli.64 d24,d23,#36
- vadd.i64 d27,d26
- vshr.u64 d26,d23,#39
- vadd.i64 d28,d1
- vsli.64 d25,d23,#30
- veor d30,d23,d16
- vsli.64 d26,d23,#25
- veor d22,d24,d25
- vadd.i64 d27,d28
- vbsl d30,d17,d16 @ Maj(a,b,c)
- veor d22,d26 @ Sigma0(a)
- vadd.i64 d18,d27
- vadd.i64 d30,d27
- @ vadd.i64 d22,d30
- vshr.u64 d24,d18,#14 @ 2
-#if 2<16
- vld1.64 {d2},[r1]! @ handles unaligned
-#endif
- vshr.u64 d25,d18,#18
-#if 2>0
- vadd.i64 d22,d30 @ h+=Maj from the past
-#endif
- vshr.u64 d26,d18,#41
- vld1.64 {d28},[r3,:64]! @ K[i++]
- vsli.64 d24,d18,#50
- vsli.64 d25,d18,#46
- vmov d29,d18
- vsli.64 d26,d18,#23
-#if 2<16 && defined(__ARMEL__)
- vrev64.8 d2,d2
-#endif
- veor d25,d24
- vbsl d29,d19,d20 @ Ch(e,f,g)
- vshr.u64 d24,d22,#28
- veor d26,d25 @ Sigma1(e)
- vadd.i64 d27,d29,d21
- vshr.u64 d25,d22,#34
- vsli.64 d24,d22,#36
- vadd.i64 d27,d26
- vshr.u64 d26,d22,#39
- vadd.i64 d28,d2
- vsli.64 d25,d22,#30
- veor d30,d22,d23
- vsli.64 d26,d22,#25
- veor d21,d24,d25
- vadd.i64 d27,d28
- vbsl d30,d16,d23 @ Maj(a,b,c)
- veor d21,d26 @ Sigma0(a)
- vadd.i64 d17,d27
- vadd.i64 d30,d27
- @ vadd.i64 d21,d30
- vshr.u64 d24,d17,#14 @ 3
-#if 3<16
- vld1.64 {d3},[r1]! @ handles unaligned
-#endif
- vshr.u64 d25,d17,#18
-#if 3>0
- vadd.i64 d21,d30 @ h+=Maj from the past
-#endif
- vshr.u64 d26,d17,#41
- vld1.64 {d28},[r3,:64]! @ K[i++]
- vsli.64 d24,d17,#50
- vsli.64 d25,d17,#46
- vmov d29,d17
- vsli.64 d26,d17,#23
-#if 3<16 && defined(__ARMEL__)
- vrev64.8 d3,d3
-#endif
- veor d25,d24
- vbsl d29,d18,d19 @ Ch(e,f,g)
- vshr.u64 d24,d21,#28
- veor d26,d25 @ Sigma1(e)
- vadd.i64 d27,d29,d20
- vshr.u64 d25,d21,#34
- vsli.64 d24,d21,#36
- vadd.i64 d27,d26
- vshr.u64 d26,d21,#39
- vadd.i64 d28,d3
- vsli.64 d25,d21,#30
- veor d30,d21,d22
- vsli.64 d26,d21,#25
- veor d20,d24,d25
- vadd.i64 d27,d28
- vbsl d30,d23,d22 @ Maj(a,b,c)
- veor d20,d26 @ Sigma0(a)
- vadd.i64 d16,d27
- vadd.i64 d30,d27
- @ vadd.i64 d20,d30
- vshr.u64 d24,d16,#14 @ 4
-#if 4<16
- vld1.64 {d4},[r1]! @ handles unaligned
-#endif
- vshr.u64 d25,d16,#18
-#if 4>0
- vadd.i64 d20,d30 @ h+=Maj from the past
-#endif
- vshr.u64 d26,d16,#41
- vld1.64 {d28},[r3,:64]! @ K[i++]
- vsli.64 d24,d16,#50
- vsli.64 d25,d16,#46
- vmov d29,d16
- vsli.64 d26,d16,#23
-#if 4<16 && defined(__ARMEL__)
- vrev64.8 d4,d4
-#endif
- veor d25,d24
- vbsl d29,d17,d18 @ Ch(e,f,g)
- vshr.u64 d24,d20,#28
- veor d26,d25 @ Sigma1(e)
- vadd.i64 d27,d29,d19
- vshr.u64 d25,d20,#34
- vsli.64 d24,d20,#36
- vadd.i64 d27,d26
- vshr.u64 d26,d20,#39
- vadd.i64 d28,d4
- vsli.64 d25,d20,#30
- veor d30,d20,d21
- vsli.64 d26,d20,#25
- veor d19,d24,d25
- vadd.i64 d27,d28
- vbsl d30,d22,d21 @ Maj(a,b,c)
- veor d19,d26 @ Sigma0(a)
- vadd.i64 d23,d27
- vadd.i64 d30,d27
- @ vadd.i64 d19,d30
- vshr.u64 d24,d23,#14 @ 5
-#if 5<16
- vld1.64 {d5},[r1]! @ handles unaligned
-#endif
- vshr.u64 d25,d23,#18
-#if 5>0
- vadd.i64 d19,d30 @ h+=Maj from the past
-#endif
- vshr.u64 d26,d23,#41
- vld1.64 {d28},[r3,:64]! @ K[i++]
- vsli.64 d24,d23,#50
- vsli.64 d25,d23,#46
- vmov d29,d23
- vsli.64 d26,d23,#23
-#if 5<16 && defined(__ARMEL__)
- vrev64.8 d5,d5
-#endif
- veor d25,d24
- vbsl d29,d16,d17 @ Ch(e,f,g)
- vshr.u64 d24,d19,#28
- veor d26,d25 @ Sigma1(e)
- vadd.i64 d27,d29,d18
- vshr.u64 d25,d19,#34
- vsli.64 d24,d19,#36
- vadd.i64 d27,d26
- vshr.u64 d26,d19,#39
- vadd.i64 d28,d5
- vsli.64 d25,d19,#30
- veor d30,d19,d20
- vsli.64 d26,d19,#25
- veor d18,d24,d25
- vadd.i64 d27,d28
- vbsl d30,d21,d20 @ Maj(a,b,c)
- veor d18,d26 @ Sigma0(a)
- vadd.i64 d22,d27
- vadd.i64 d30,d27
- @ vadd.i64 d18,d30
- vshr.u64 d24,d22,#14 @ 6
-#if 6<16
- vld1.64 {d6},[r1]! @ handles unaligned
-#endif
- vshr.u64 d25,d22,#18
-#if 6>0
- vadd.i64 d18,d30 @ h+=Maj from the past
-#endif
- vshr.u64 d26,d22,#41
- vld1.64 {d28},[r3,:64]! @ K[i++]
- vsli.64 d24,d22,#50
- vsli.64 d25,d22,#46
- vmov d29,d22
- vsli.64 d26,d22,#23
-#if 6<16 && defined(__ARMEL__)
- vrev64.8 d6,d6
-#endif
- veor d25,d24
- vbsl d29,d23,d16 @ Ch(e,f,g)
- vshr.u64 d24,d18,#28
- veor d26,d25 @ Sigma1(e)
- vadd.i64 d27,d29,d17
- vshr.u64 d25,d18,#34
- vsli.64 d24,d18,#36
- vadd.i64 d27,d26
- vshr.u64 d26,d18,#39
- vadd.i64 d28,d6
- vsli.64 d25,d18,#30
- veor d30,d18,d19
- vsli.64 d26,d18,#25
- veor d17,d24,d25
- vadd.i64 d27,d28
- vbsl d30,d20,d19 @ Maj(a,b,c)
- veor d17,d26 @ Sigma0(a)
- vadd.i64 d21,d27
- vadd.i64 d30,d27
- @ vadd.i64 d17,d30
- vshr.u64 d24,d21,#14 @ 7
-#if 7<16
- vld1.64 {d7},[r1]! @ handles unaligned
-#endif
- vshr.u64 d25,d21,#18
-#if 7>0
- vadd.i64 d17,d30 @ h+=Maj from the past
-#endif
- vshr.u64 d26,d21,#41
- vld1.64 {d28},[r3,:64]! @ K[i++]
- vsli.64 d24,d21,#50
- vsli.64 d25,d21,#46
- vmov d29,d21
- vsli.64 d26,d21,#23
-#if 7<16 && defined(__ARMEL__)
- vrev64.8 d7,d7
-#endif
- veor d25,d24
- vbsl d29,d22,d23 @ Ch(e,f,g)
- vshr.u64 d24,d17,#28
- veor d26,d25 @ Sigma1(e)
- vadd.i64 d27,d29,d16
- vshr.u64 d25,d17,#34
- vsli.64 d24,d17,#36
- vadd.i64 d27,d26
- vshr.u64 d26,d17,#39
- vadd.i64 d28,d7
- vsli.64 d25,d17,#30
- veor d30,d17,d18
- vsli.64 d26,d17,#25
- veor d16,d24,d25
- vadd.i64 d27,d28
- vbsl d30,d19,d18 @ Maj(a,b,c)
- veor d16,d26 @ Sigma0(a)
- vadd.i64 d20,d27
- vadd.i64 d30,d27
- @ vadd.i64 d16,d30
- vshr.u64 d24,d20,#14 @ 8
-#if 8<16
- vld1.64 {d8},[r1]! @ handles unaligned
-#endif
- vshr.u64 d25,d20,#18
-#if 8>0
- vadd.i64 d16,d30 @ h+=Maj from the past
-#endif
- vshr.u64 d26,d20,#41
- vld1.64 {d28},[r3,:64]! @ K[i++]
- vsli.64 d24,d20,#50
- vsli.64 d25,d20,#46
- vmov d29,d20
- vsli.64 d26,d20,#23
-#if 8<16 && defined(__ARMEL__)
- vrev64.8 d8,d8
-#endif
- veor d25,d24
- vbsl d29,d21,d22 @ Ch(e,f,g)
- vshr.u64 d24,d16,#28
- veor d26,d25 @ Sigma1(e)
- vadd.i64 d27,d29,d23
- vshr.u64 d25,d16,#34
- vsli.64 d24,d16,#36
- vadd.i64 d27,d26
- vshr.u64 d26,d16,#39
- vadd.i64 d28,d8
- vsli.64 d25,d16,#30
- veor d30,d16,d17
- vsli.64 d26,d16,#25
- veor d23,d24,d25
- vadd.i64 d27,d28
- vbsl d30,d18,d17 @ Maj(a,b,c)
- veor d23,d26 @ Sigma0(a)
- vadd.i64 d19,d27
- vadd.i64 d30,d27
- @ vadd.i64 d23,d30
- vshr.u64 d24,d19,#14 @ 9
-#if 9<16
- vld1.64 {d9},[r1]! @ handles unaligned
-#endif
- vshr.u64 d25,d19,#18
-#if 9>0
- vadd.i64 d23,d30 @ h+=Maj from the past
-#endif
- vshr.u64 d26,d19,#41
- vld1.64 {d28},[r3,:64]! @ K[i++]
- vsli.64 d24,d19,#50
- vsli.64 d25,d19,#46
- vmov d29,d19
- vsli.64 d26,d19,#23
-#if 9<16 && defined(__ARMEL__)
- vrev64.8 d9,d9
-#endif
- veor d25,d24
- vbsl d29,d20,d21 @ Ch(e,f,g)
- vshr.u64 d24,d23,#28
- veor d26,d25 @ Sigma1(e)
- vadd.i64 d27,d29,d22
- vshr.u64 d25,d23,#34
- vsli.64 d24,d23,#36
- vadd.i64 d27,d26
- vshr.u64 d26,d23,#39
- vadd.i64 d28,d9
- vsli.64 d25,d23,#30
- veor d30,d23,d16
- vsli.64 d26,d23,#25
- veor d22,d24,d25
- vadd.i64 d27,d28
- vbsl d30,d17,d16 @ Maj(a,b,c)
- veor d22,d26 @ Sigma0(a)
- vadd.i64 d18,d27
- vadd.i64 d30,d27
- @ vadd.i64 d22,d30
- vshr.u64 d24,d18,#14 @ 10
-#if 10<16
- vld1.64 {d10},[r1]! @ handles unaligned
-#endif
- vshr.u64 d25,d18,#18
-#if 10>0
- vadd.i64 d22,d30 @ h+=Maj from the past
-#endif
- vshr.u64 d26,d18,#41
- vld1.64 {d28},[r3,:64]! @ K[i++]
- vsli.64 d24,d18,#50
- vsli.64 d25,d18,#46
- vmov d29,d18
- vsli.64 d26,d18,#23
-#if 10<16 && defined(__ARMEL__)
- vrev64.8 d10,d10
-#endif
- veor d25,d24
- vbsl d29,d19,d20 @ Ch(e,f,g)
- vshr.u64 d24,d22,#28
- veor d26,d25 @ Sigma1(e)
- vadd.i64 d27,d29,d21
- vshr.u64 d25,d22,#34
- vsli.64 d24,d22,#36
- vadd.i64 d27,d26
- vshr.u64 d26,d22,#39
- vadd.i64 d28,d10
- vsli.64 d25,d22,#30
- veor d30,d22,d23
- vsli.64 d26,d22,#25
- veor d21,d24,d25
- vadd.i64 d27,d28
- vbsl d30,d16,d23 @ Maj(a,b,c)
- veor d21,d26 @ Sigma0(a)
- vadd.i64 d17,d27
- vadd.i64 d30,d27
- @ vadd.i64 d21,d30
- vshr.u64 d24,d17,#14 @ 11
-#if 11<16
- vld1.64 {d11},[r1]! @ handles unaligned
-#endif
- vshr.u64 d25,d17,#18
-#if 11>0
- vadd.i64 d21,d30 @ h+=Maj from the past
-#endif
- vshr.u64 d26,d17,#41
- vld1.64 {d28},[r3,:64]! @ K[i++]
- vsli.64 d24,d17,#50
- vsli.64 d25,d17,#46
- vmov d29,d17
- vsli.64 d26,d17,#23
-#if 11<16 && defined(__ARMEL__)
- vrev64.8 d11,d11
-#endif
- veor d25,d24
- vbsl d29,d18,d19 @ Ch(e,f,g)
- vshr.u64 d24,d21,#28
- veor d26,d25 @ Sigma1(e)
- vadd.i64 d27,d29,d20
- vshr.u64 d25,d21,#34
- vsli.64 d24,d21,#36
- vadd.i64 d27,d26
- vshr.u64 d26,d21,#39
- vadd.i64 d28,d11
- vsli.64 d25,d21,#30
- veor d30,d21,d22
- vsli.64 d26,d21,#25
- veor d20,d24,d25
- vadd.i64 d27,d28
- vbsl d30,d23,d22 @ Maj(a,b,c)
- veor d20,d26 @ Sigma0(a)
- vadd.i64 d16,d27
- vadd.i64 d30,d27
- @ vadd.i64 d20,d30
- vshr.u64 d24,d16,#14 @ 12
-#if 12<16
- vld1.64 {d12},[r1]! @ handles unaligned
-#endif
- vshr.u64 d25,d16,#18
-#if 12>0
- vadd.i64 d20,d30 @ h+=Maj from the past
-#endif
- vshr.u64 d26,d16,#41
- vld1.64 {d28},[r3,:64]! @ K[i++]
- vsli.64 d24,d16,#50
- vsli.64 d25,d16,#46
- vmov d29,d16
- vsli.64 d26,d16,#23
-#if 12<16 && defined(__ARMEL__)
- vrev64.8 d12,d12
-#endif
- veor d25,d24
- vbsl d29,d17,d18 @ Ch(e,f,g)
- vshr.u64 d24,d20,#28
- veor d26,d25 @ Sigma1(e)
- vadd.i64 d27,d29,d19
- vshr.u64 d25,d20,#34
- vsli.64 d24,d20,#36
- vadd.i64 d27,d26
- vshr.u64 d26,d20,#39
- vadd.i64 d28,d12
- vsli.64 d25,d20,#30
- veor d30,d20,d21
- vsli.64 d26,d20,#25
- veor d19,d24,d25
- vadd.i64 d27,d28
- vbsl d30,d22,d21 @ Maj(a,b,c)
- veor d19,d26 @ Sigma0(a)
- vadd.i64 d23,d27
- vadd.i64 d30,d27
- @ vadd.i64 d19,d30
- vshr.u64 d24,d23,#14 @ 13
-#if 13<16
- vld1.64 {d13},[r1]! @ handles unaligned
-#endif
- vshr.u64 d25,d23,#18
-#if 13>0
- vadd.i64 d19,d30 @ h+=Maj from the past
-#endif
- vshr.u64 d26,d23,#41
- vld1.64 {d28},[r3,:64]! @ K[i++]
- vsli.64 d24,d23,#50
- vsli.64 d25,d23,#46
- vmov d29,d23
- vsli.64 d26,d23,#23
-#if 13<16 && defined(__ARMEL__)
- vrev64.8 d13,d13
-#endif
- veor d25,d24
- vbsl d29,d16,d17 @ Ch(e,f,g)
- vshr.u64 d24,d19,#28
- veor d26,d25 @ Sigma1(e)
- vadd.i64 d27,d29,d18
- vshr.u64 d25,d19,#34
- vsli.64 d24,d19,#36
- vadd.i64 d27,d26
- vshr.u64 d26,d19,#39
- vadd.i64 d28,d13
- vsli.64 d25,d19,#30
- veor d30,d19,d20
- vsli.64 d26,d19,#25
- veor d18,d24,d25
- vadd.i64 d27,d28
- vbsl d30,d21,d20 @ Maj(a,b,c)
- veor d18,d26 @ Sigma0(a)
- vadd.i64 d22,d27
- vadd.i64 d30,d27
- @ vadd.i64 d18,d30
- vshr.u64 d24,d22,#14 @ 14
-#if 14<16
- vld1.64 {d14},[r1]! @ handles unaligned
-#endif
- vshr.u64 d25,d22,#18
-#if 14>0
- vadd.i64 d18,d30 @ h+=Maj from the past
-#endif
- vshr.u64 d26,d22,#41
- vld1.64 {d28},[r3,:64]! @ K[i++]
- vsli.64 d24,d22,#50
- vsli.64 d25,d22,#46
- vmov d29,d22
- vsli.64 d26,d22,#23
-#if 14<16 && defined(__ARMEL__)
- vrev64.8 d14,d14
-#endif
- veor d25,d24
- vbsl d29,d23,d16 @ Ch(e,f,g)
- vshr.u64 d24,d18,#28
- veor d26,d25 @ Sigma1(e)
- vadd.i64 d27,d29,d17
- vshr.u64 d25,d18,#34
- vsli.64 d24,d18,#36
- vadd.i64 d27,d26
- vshr.u64 d26,d18,#39
- vadd.i64 d28,d14
- vsli.64 d25,d18,#30
- veor d30,d18,d19
- vsli.64 d26,d18,#25
- veor d17,d24,d25
- vadd.i64 d27,d28
- vbsl d30,d20,d19 @ Maj(a,b,c)
- veor d17,d26 @ Sigma0(a)
- vadd.i64 d21,d27
- vadd.i64 d30,d27
- @ vadd.i64 d17,d30
- vshr.u64 d24,d21,#14 @ 15
-#if 15<16
- vld1.64 {d15},[r1]! @ handles unaligned
-#endif
- vshr.u64 d25,d21,#18
-#if 15>0
- vadd.i64 d17,d30 @ h+=Maj from the past
-#endif
- vshr.u64 d26,d21,#41
- vld1.64 {d28},[r3,:64]! @ K[i++]
- vsli.64 d24,d21,#50
- vsli.64 d25,d21,#46
- vmov d29,d21
- vsli.64 d26,d21,#23
-#if 15<16 && defined(__ARMEL__)
- vrev64.8 d15,d15
-#endif
- veor d25,d24
- vbsl d29,d22,d23 @ Ch(e,f,g)
- vshr.u64 d24,d17,#28
- veor d26,d25 @ Sigma1(e)
- vadd.i64 d27,d29,d16
- vshr.u64 d25,d17,#34
- vsli.64 d24,d17,#36
- vadd.i64 d27,d26
- vshr.u64 d26,d17,#39
- vadd.i64 d28,d15
- vsli.64 d25,d17,#30
- veor d30,d17,d18
- vsli.64 d26,d17,#25
- veor d16,d24,d25
- vadd.i64 d27,d28
- vbsl d30,d19,d18 @ Maj(a,b,c)
- veor d16,d26 @ Sigma0(a)
- vadd.i64 d20,d27
- vadd.i64 d30,d27
- @ vadd.i64 d16,d30
- mov r12,#4
-.L16_79_neon:
- subs r12,#1
- vshr.u64 q12,q7,#19
- vshr.u64 q13,q7,#61
- vadd.i64 d16,d30 @ h+=Maj from the past
- vshr.u64 q15,q7,#6
- vsli.64 q12,q7,#45
- vext.8 q14,q0,q1,#8 @ X[i+1]
- vsli.64 q13,q7,#3
- veor q15,q12
- vshr.u64 q12,q14,#1
- veor q15,q13 @ sigma1(X[i+14])
- vshr.u64 q13,q14,#8
- vadd.i64 q0,q15
- vshr.u64 q15,q14,#7
- vsli.64 q12,q14,#63
- vsli.64 q13,q14,#56
- vext.8 q14,q4,q5,#8 @ X[i+9]
- veor q15,q12
- vshr.u64 d24,d20,#14 @ from NEON_00_15
- vadd.i64 q0,q14
- vshr.u64 d25,d20,#18 @ from NEON_00_15
- veor q15,q13 @ sigma0(X[i+1])
- vshr.u64 d26,d20,#41 @ from NEON_00_15
- vadd.i64 q0,q15
- vld1.64 {d28},[r3,:64]! @ K[i++]
- vsli.64 d24,d20,#50
- vsli.64 d25,d20,#46
- vmov d29,d20
- vsli.64 d26,d20,#23
-#if 16<16 && defined(__ARMEL__)
- vrev64.8 ,
-#endif
- veor d25,d24
- vbsl d29,d21,d22 @ Ch(e,f,g)
- vshr.u64 d24,d16,#28
- veor d26,d25 @ Sigma1(e)
- vadd.i64 d27,d29,d23
- vshr.u64 d25,d16,#34
- vsli.64 d24,d16,#36
- vadd.i64 d27,d26
- vshr.u64 d26,d16,#39
- vadd.i64 d28,d0
- vsli.64 d25,d16,#30
- veor d30,d16,d17
- vsli.64 d26,d16,#25
- veor d23,d24,d25
- vadd.i64 d27,d28
- vbsl d30,d18,d17 @ Maj(a,b,c)
- veor d23,d26 @ Sigma0(a)
- vadd.i64 d19,d27
- vadd.i64 d30,d27
- @ vadd.i64 d23,d30
- vshr.u64 d24,d19,#14 @ 17
-#if 17<16
- vld1.64 {d1},[r1]! @ handles unaligned
-#endif
- vshr.u64 d25,d19,#18
-#if 17>0
- vadd.i64 d23,d30 @ h+=Maj from the past
-#endif
- vshr.u64 d26,d19,#41
- vld1.64 {d28},[r3,:64]! @ K[i++]
- vsli.64 d24,d19,#50
- vsli.64 d25,d19,#46
- vmov d29,d19
- vsli.64 d26,d19,#23
-#if 17<16 && defined(__ARMEL__)
- vrev64.8 ,
-#endif
- veor d25,d24
- vbsl d29,d20,d21 @ Ch(e,f,g)
- vshr.u64 d24,d23,#28
- veor d26,d25 @ Sigma1(e)
- vadd.i64 d27,d29,d22
- vshr.u64 d25,d23,#34
- vsli.64 d24,d23,#36
- vadd.i64 d27,d26
- vshr.u64 d26,d23,#39
- vadd.i64 d28,d1
- vsli.64 d25,d23,#30
- veor d30,d23,d16
- vsli.64 d26,d23,#25
- veor d22,d24,d25
- vadd.i64 d27,d28
- vbsl d30,d17,d16 @ Maj(a,b,c)
- veor d22,d26 @ Sigma0(a)
- vadd.i64 d18,d27
- vadd.i64 d30,d27
- @ vadd.i64 d22,d30
- vshr.u64 q12,q0,#19
- vshr.u64 q13,q0,#61
- vadd.i64 d22,d30 @ h+=Maj from the past
- vshr.u64 q15,q0,#6
- vsli.64 q12,q0,#45
- vext.8 q14,q1,q2,#8 @ X[i+1]
- vsli.64 q13,q0,#3
- veor q15,q12
- vshr.u64 q12,q14,#1
- veor q15,q13 @ sigma1(X[i+14])
- vshr.u64 q13,q14,#8
- vadd.i64 q1,q15
- vshr.u64 q15,q14,#7
- vsli.64 q12,q14,#63
- vsli.64 q13,q14,#56
- vext.8 q14,q5,q6,#8 @ X[i+9]
- veor q15,q12
- vshr.u64 d24,d18,#14 @ from NEON_00_15
- vadd.i64 q1,q14
- vshr.u64 d25,d18,#18 @ from NEON_00_15
- veor q15,q13 @ sigma0(X[i+1])
- vshr.u64 d26,d18,#41 @ from NEON_00_15
- vadd.i64 q1,q15
- vld1.64 {d28},[r3,:64]! @ K[i++]
- vsli.64 d24,d18,#50
- vsli.64 d25,d18,#46
- vmov d29,d18
- vsli.64 d26,d18,#23
-#if 18<16 && defined(__ARMEL__)
- vrev64.8 ,
-#endif
- veor d25,d24
- vbsl d29,d19,d20 @ Ch(e,f,g)
- vshr.u64 d24,d22,#28
- veor d26,d25 @ Sigma1(e)
- vadd.i64 d27,d29,d21
- vshr.u64 d25,d22,#34
- vsli.64 d24,d22,#36
- vadd.i64 d27,d26
- vshr.u64 d26,d22,#39
- vadd.i64 d28,d2
- vsli.64 d25,d22,#30
- veor d30,d22,d23
- vsli.64 d26,d22,#25
- veor d21,d24,d25
- vadd.i64 d27,d28
- vbsl d30,d16,d23 @ Maj(a,b,c)
- veor d21,d26 @ Sigma0(a)
- vadd.i64 d17,d27
- vadd.i64 d30,d27
- @ vadd.i64 d21,d30
- vshr.u64 d24,d17,#14 @ 19
-#if 19<16
- vld1.64 {d3},[r1]! @ handles unaligned
-#endif
- vshr.u64 d25,d17,#18
-#if 19>0
- vadd.i64 d21,d30 @ h+=Maj from the past
-#endif
- vshr.u64 d26,d17,#41
- vld1.64 {d28},[r3,:64]! @ K[i++]
- vsli.64 d24,d17,#50
- vsli.64 d25,d17,#46
- vmov d29,d17
- vsli.64 d26,d17,#23
-#if 19<16 && defined(__ARMEL__)
- vrev64.8 ,
-#endif
- veor d25,d24
- vbsl d29,d18,d19 @ Ch(e,f,g)
- vshr.u64 d24,d21,#28
- veor d26,d25 @ Sigma1(e)
- vadd.i64 d27,d29,d20
- vshr.u64 d25,d21,#34
- vsli.64 d24,d21,#36
- vadd.i64 d27,d26
- vshr.u64 d26,d21,#39
- vadd.i64 d28,d3
- vsli.64 d25,d21,#30
- veor d30,d21,d22
- vsli.64 d26,d21,#25
- veor d20,d24,d25
- vadd.i64 d27,d28
- vbsl d30,d23,d22 @ Maj(a,b,c)
- veor d20,d26 @ Sigma0(a)
- vadd.i64 d16,d27
- vadd.i64 d30,d27
- @ vadd.i64 d20,d30
- vshr.u64 q12,q1,#19
- vshr.u64 q13,q1,#61
- vadd.i64 d20,d30 @ h+=Maj from the past
- vshr.u64 q15,q1,#6
- vsli.64 q12,q1,#45
- vext.8 q14,q2,q3,#8 @ X[i+1]
- vsli.64 q13,q1,#3
- veor q15,q12
- vshr.u64 q12,q14,#1
- veor q15,q13 @ sigma1(X[i+14])
- vshr.u64 q13,q14,#8
- vadd.i64 q2,q15
- vshr.u64 q15,q14,#7
- vsli.64 q12,q14,#63
- vsli.64 q13,q14,#56
- vext.8 q14,q6,q7,#8 @ X[i+9]
- veor q15,q12
- vshr.u64 d24,d16,#14 @ from NEON_00_15
- vadd.i64 q2,q14
- vshr.u64 d25,d16,#18 @ from NEON_00_15
- veor q15,q13 @ sigma0(X[i+1])
- vshr.u64 d26,d16,#41 @ from NEON_00_15
- vadd.i64 q2,q15
- vld1.64 {d28},[r3,:64]! @ K[i++]
- vsli.64 d24,d16,#50
- vsli.64 d25,d16,#46
- vmov d29,d16
- vsli.64 d26,d16,#23
-#if 20<16 && defined(__ARMEL__)
- vrev64.8 ,
-#endif
- veor d25,d24
- vbsl d29,d17,d18 @ Ch(e,f,g)
- vshr.u64 d24,d20,#28
- veor d26,d25 @ Sigma1(e)
- vadd.i64 d27,d29,d19
- vshr.u64 d25,d20,#34
- vsli.64 d24,d20,#36
- vadd.i64 d27,d26
- vshr.u64 d26,d20,#39
- vadd.i64 d28,d4
- vsli.64 d25,d20,#30
- veor d30,d20,d21
- vsli.64 d26,d20,#25
- veor d19,d24,d25
- vadd.i64 d27,d28
- vbsl d30,d22,d21 @ Maj(a,b,c)
- veor d19,d26 @ Sigma0(a)
- vadd.i64 d23,d27
- vadd.i64 d30,d27
- @ vadd.i64 d19,d30
- vshr.u64 d24,d23,#14 @ 21
-#if 21<16
- vld1.64 {d5},[r1]! @ handles unaligned
-#endif
- vshr.u64 d25,d23,#18
-#if 21>0
- vadd.i64 d19,d30 @ h+=Maj from the past
-#endif
- vshr.u64 d26,d23,#41
- vld1.64 {d28},[r3,:64]! @ K[i++]
- vsli.64 d24,d23,#50
- vsli.64 d25,d23,#46
- vmov d29,d23
- vsli.64 d26,d23,#23
-#if 21<16 && defined(__ARMEL__)
- vrev64.8 ,
-#endif
- veor d25,d24
- vbsl d29,d16,d17 @ Ch(e,f,g)
- vshr.u64 d24,d19,#28
- veor d26,d25 @ Sigma1(e)
- vadd.i64 d27,d29,d18
- vshr.u64 d25,d19,#34
- vsli.64 d24,d19,#36
- vadd.i64 d27,d26
- vshr.u64 d26,d19,#39
- vadd.i64 d28,d5
- vsli.64 d25,d19,#30
- veor d30,d19,d20
- vsli.64 d26,d19,#25
- veor d18,d24,d25
- vadd.i64 d27,d28
- vbsl d30,d21,d20 @ Maj(a,b,c)
- veor d18,d26 @ Sigma0(a)
- vadd.i64 d22,d27
- vadd.i64 d30,d27
- @ vadd.i64 d18,d30
- vshr.u64 q12,q2,#19
- vshr.u64 q13,q2,#61
- vadd.i64 d18,d30 @ h+=Maj from the past
- vshr.u64 q15,q2,#6
- vsli.64 q12,q2,#45
- vext.8 q14,q3,q4,#8 @ X[i+1]
- vsli.64 q13,q2,#3
- veor q15,q12
- vshr.u64 q12,q14,#1
- veor q15,q13 @ sigma1(X[i+14])
- vshr.u64 q13,q14,#8
- vadd.i64 q3,q15
- vshr.u64 q15,q14,#7
- vsli.64 q12,q14,#63
- vsli.64 q13,q14,#56
- vext.8 q14,q7,q0,#8 @ X[i+9]
- veor q15,q12
- vshr.u64 d24,d22,#14 @ from NEON_00_15
- vadd.i64 q3,q14
- vshr.u64 d25,d22,#18 @ from NEON_00_15
- veor q15,q13 @ sigma0(X[i+1])
- vshr.u64 d26,d22,#41 @ from NEON_00_15
- vadd.i64 q3,q15
- vld1.64 {d28},[r3,:64]! @ K[i++]
- vsli.64 d24,d22,#50
- vsli.64 d25,d22,#46
- vmov d29,d22
- vsli.64 d26,d22,#23
-#if 22<16 && defined(__ARMEL__)
- vrev64.8 ,
-#endif
- veor d25,d24
- vbsl d29,d23,d16 @ Ch(e,f,g)
- vshr.u64 d24,d18,#28
- veor d26,d25 @ Sigma1(e)
- vadd.i64 d27,d29,d17
- vshr.u64 d25,d18,#34
- vsli.64 d24,d18,#36
- vadd.i64 d27,d26
- vshr.u64 d26,d18,#39
- vadd.i64 d28,d6
- vsli.64 d25,d18,#30
- veor d30,d18,d19
- vsli.64 d26,d18,#25
- veor d17,d24,d25
- vadd.i64 d27,d28
- vbsl d30,d20,d19 @ Maj(a,b,c)
- veor d17,d26 @ Sigma0(a)
- vadd.i64 d21,d27
- vadd.i64 d30,d27
- @ vadd.i64 d17,d30
- vshr.u64 d24,d21,#14 @ 23
-#if 23<16
- vld1.64 {d7},[r1]! @ handles unaligned
-#endif
- vshr.u64 d25,d21,#18
-#if 23>0
- vadd.i64 d17,d30 @ h+=Maj from the past
-#endif
- vshr.u64 d26,d21,#41
- vld1.64 {d28},[r3,:64]! @ K[i++]
- vsli.64 d24,d21,#50
- vsli.64 d25,d21,#46
- vmov d29,d21
- vsli.64 d26,d21,#23
-#if 23<16 && defined(__ARMEL__)
- vrev64.8 ,
-#endif
- veor d25,d24
- vbsl d29,d22,d23 @ Ch(e,f,g)
- vshr.u64 d24,d17,#28
- veor d26,d25 @ Sigma1(e)
- vadd.i64 d27,d29,d16
- vshr.u64 d25,d17,#34
- vsli.64 d24,d17,#36
- vadd.i64 d27,d26
- vshr.u64 d26,d17,#39
- vadd.i64 d28,d7
- vsli.64 d25,d17,#30
- veor d30,d17,d18
- vsli.64 d26,d17,#25
- veor d16,d24,d25
- vadd.i64 d27,d28
- vbsl d30,d19,d18 @ Maj(a,b,c)
- veor d16,d26 @ Sigma0(a)
- vadd.i64 d20,d27
- vadd.i64 d30,d27
- @ vadd.i64 d16,d30
- vshr.u64 q12,q3,#19
- vshr.u64 q13,q3,#61
- vadd.i64 d16,d30 @ h+=Maj from the past
- vshr.u64 q15,q3,#6
- vsli.64 q12,q3,#45
- vext.8 q14,q4,q5,#8 @ X[i+1]
- vsli.64 q13,q3,#3
- veor q15,q12
- vshr.u64 q12,q14,#1
- veor q15,q13 @ sigma1(X[i+14])
- vshr.u64 q13,q14,#8
- vadd.i64 q4,q15
- vshr.u64 q15,q14,#7
- vsli.64 q12,q14,#63
- vsli.64 q13,q14,#56
- vext.8 q14,q0,q1,#8 @ X[i+9]
- veor q15,q12
- vshr.u64 d24,d20,#14 @ from NEON_00_15
- vadd.i64 q4,q14
- vshr.u64 d25,d20,#18 @ from NEON_00_15
- veor q15,q13 @ sigma0(X[i+1])
- vshr.u64 d26,d20,#41 @ from NEON_00_15
- vadd.i64 q4,q15
- vld1.64 {d28},[r3,:64]! @ K[i++]
- vsli.64 d24,d20,#50
- vsli.64 d25,d20,#46
- vmov d29,d20
- vsli.64 d26,d20,#23
-#if 24<16 && defined(__ARMEL__)
- vrev64.8 ,
-#endif
- veor d25,d24
- vbsl d29,d21,d22 @ Ch(e,f,g)
- vshr.u64 d24,d16,#28
- veor d26,d25 @ Sigma1(e)
- vadd.i64 d27,d29,d23
- vshr.u64 d25,d16,#34
- vsli.64 d24,d16,#36
- vadd.i64 d27,d26
- vshr.u64 d26,d16,#39
- vadd.i64 d28,d8
- vsli.64 d25,d16,#30
- veor d30,d16,d17
- vsli.64 d26,d16,#25
- veor d23,d24,d25
- vadd.i64 d27,d28
- vbsl d30,d18,d17 @ Maj(a,b,c)
- veor d23,d26 @ Sigma0(a)
- vadd.i64 d19,d27
- vadd.i64 d30,d27
- @ vadd.i64 d23,d30
- vshr.u64 d24,d19,#14 @ 25
-#if 25<16
- vld1.64 {d9},[r1]! @ handles unaligned
-#endif
- vshr.u64 d25,d19,#18
-#if 25>0
- vadd.i64 d23,d30 @ h+=Maj from the past
-#endif
- vshr.u64 d26,d19,#41
- vld1.64 {d28},[r3,:64]! @ K[i++]
- vsli.64 d24,d19,#50
- vsli.64 d25,d19,#46
- vmov d29,d19
- vsli.64 d26,d19,#23
-#if 25<16 && defined(__ARMEL__)
- vrev64.8 ,
-#endif
- veor d25,d24
- vbsl d29,d20,d21 @ Ch(e,f,g)
- vshr.u64 d24,d23,#28
- veor d26,d25 @ Sigma1(e)
- vadd.i64 d27,d29,d22
- vshr.u64 d25,d23,#34
- vsli.64 d24,d23,#36
- vadd.i64 d27,d26
- vshr.u64 d26,d23,#39
- vadd.i64 d28,d9
- vsli.64 d25,d23,#30
- veor d30,d23,d16
- vsli.64 d26,d23,#25
- veor d22,d24,d25
- vadd.i64 d27,d28
- vbsl d30,d17,d16 @ Maj(a,b,c)
- veor d22,d26 @ Sigma0(a)
- vadd.i64 d18,d27
- vadd.i64 d30,d27
- @ vadd.i64 d22,d30
- vshr.u64 q12,q4,#19
- vshr.u64 q13,q4,#61
- vadd.i64 d22,d30 @ h+=Maj from the past
- vshr.u64 q15,q4,#6
- vsli.64 q12,q4,#45
- vext.8 q14,q5,q6,#8 @ X[i+1]
- vsli.64 q13,q4,#3
- veor q15,q12
- vshr.u64 q12,q14,#1
- veor q15,q13 @ sigma1(X[i+14])
- vshr.u64 q13,q14,#8
- vadd.i64 q5,q15
- vshr.u64 q15,q14,#7
- vsli.64 q12,q14,#63
- vsli.64 q13,q14,#56
- vext.8 q14,q1,q2,#8 @ X[i+9]
- veor q15,q12
- vshr.u64 d24,d18,#14 @ from NEON_00_15
- vadd.i64 q5,q14
- vshr.u64 d25,d18,#18 @ from NEON_00_15
- veor q15,q13 @ sigma0(X[i+1])
- vshr.u64 d26,d18,#41 @ from NEON_00_15
- vadd.i64 q5,q15
- vld1.64 {d28},[r3,:64]! @ K[i++]
- vsli.64 d24,d18,#50
- vsli.64 d25,d18,#46
- vmov d29,d18
- vsli.64 d26,d18,#23
-#if 26<16 && defined(__ARMEL__)
- vrev64.8 ,
-#endif
- veor d25,d24
- vbsl d29,d19,d20 @ Ch(e,f,g)
- vshr.u64 d24,d22,#28
- veor d26,d25 @ Sigma1(e)
- vadd.i64 d27,d29,d21
- vshr.u64 d25,d22,#34
- vsli.64 d24,d22,#36
- vadd.i64 d27,d26
- vshr.u64 d26,d22,#39
- vadd.i64 d28,d10
- vsli.64 d25,d22,#30
- veor d30,d22,d23
- vsli.64 d26,d22,#25
- veor d21,d24,d25
- vadd.i64 d27,d28
- vbsl d30,d16,d23 @ Maj(a,b,c)
- veor d21,d26 @ Sigma0(a)
- vadd.i64 d17,d27
- vadd.i64 d30,d27
- @ vadd.i64 d21,d30
- vshr.u64 d24,d17,#14 @ 27
-#if 27<16
- vld1.64 {d11},[r1]! @ handles unaligned
-#endif
- vshr.u64 d25,d17,#18
-#if 27>0
- vadd.i64 d21,d30 @ h+=Maj from the past
-#endif
- vshr.u64 d26,d17,#41
- vld1.64 {d28},[r3,:64]! @ K[i++]
- vsli.64 d24,d17,#50
- vsli.64 d25,d17,#46
- vmov d29,d17
- vsli.64 d26,d17,#23
-#if 27<16 && defined(__ARMEL__)
- vrev64.8 ,
-#endif
- veor d25,d24
- vbsl d29,d18,d19 @ Ch(e,f,g)
- vshr.u64 d24,d21,#28
- veor d26,d25 @ Sigma1(e)
- vadd.i64 d27,d29,d20
- vshr.u64 d25,d21,#34
- vsli.64 d24,d21,#36
- vadd.i64 d27,d26
- vshr.u64 d26,d21,#39
- vadd.i64 d28,d11
- vsli.64 d25,d21,#30
- veor d30,d21,d22
- vsli.64 d26,d21,#25
- veor d20,d24,d25
- vadd.i64 d27,d28
- vbsl d30,d23,d22 @ Maj(a,b,c)
- veor d20,d26 @ Sigma0(a)
- vadd.i64 d16,d27
- vadd.i64 d30,d27
- @ vadd.i64 d20,d30
- vshr.u64 q12,q5,#19
- vshr.u64 q13,q5,#61
- vadd.i64 d20,d30 @ h+=Maj from the past
- vshr.u64 q15,q5,#6
- vsli.64 q12,q5,#45
- vext.8 q14,q6,q7,#8 @ X[i+1]
- vsli.64 q13,q5,#3
- veor q15,q12
- vshr.u64 q12,q14,#1
- veor q15,q13 @ sigma1(X[i+14])
- vshr.u64 q13,q14,#8
- vadd.i64 q6,q15
- vshr.u64 q15,q14,#7
- vsli.64 q12,q14,#63
- vsli.64 q13,q14,#56
- vext.8 q14,q2,q3,#8 @ X[i+9]
- veor q15,q12
- vshr.u64 d24,d16,#14 @ from NEON_00_15
- vadd.i64 q6,q14
- vshr.u64 d25,d16,#18 @ from NEON_00_15
- veor q15,q13 @ sigma0(X[i+1])
- vshr.u64 d26,d16,#41 @ from NEON_00_15
- vadd.i64 q6,q15
- vld1.64 {d28},[r3,:64]! @ K[i++]
- vsli.64 d24,d16,#50
- vsli.64 d25,d16,#46
- vmov d29,d16
- vsli.64 d26,d16,#23
-#if 28<16 && defined(__ARMEL__)
- vrev64.8 ,
-#endif
- veor d25,d24
- vbsl d29,d17,d18 @ Ch(e,f,g)
- vshr.u64 d24,d20,#28
- veor d26,d25 @ Sigma1(e)
- vadd.i64 d27,d29,d19
- vshr.u64 d25,d20,#34
- vsli.64 d24,d20,#36
- vadd.i64 d27,d26
- vshr.u64 d26,d20,#39
- vadd.i64 d28,d12
- vsli.64 d25,d20,#30
- veor d30,d20,d21
- vsli.64 d26,d20,#25
- veor d19,d24,d25
- vadd.i64 d27,d28
- vbsl d30,d22,d21 @ Maj(a,b,c)
- veor d19,d26 @ Sigma0(a)
- vadd.i64 d23,d27
- vadd.i64 d30,d27
- @ vadd.i64 d19,d30
- vshr.u64 d24,d23,#14 @ 29
-#if 29<16
- vld1.64 {d13},[r1]! @ handles unaligned
-#endif
- vshr.u64 d25,d23,#18
-#if 29>0
- vadd.i64 d19,d30 @ h+=Maj from the past
-#endif
- vshr.u64 d26,d23,#41
- vld1.64 {d28},[r3,:64]! @ K[i++]
- vsli.64 d24,d23,#50
- vsli.64 d25,d23,#46
- vmov d29,d23
- vsli.64 d26,d23,#23
-#if 29<16 && defined(__ARMEL__)
- vrev64.8 ,
-#endif
- veor d25,d24
- vbsl d29,d16,d17 @ Ch(e,f,g)
- vshr.u64 d24,d19,#28
- veor d26,d25 @ Sigma1(e)
- vadd.i64 d27,d29,d18
- vshr.u64 d25,d19,#34
- vsli.64 d24,d19,#36
- vadd.i64 d27,d26
- vshr.u64 d26,d19,#39
- vadd.i64 d28,d13
- vsli.64 d25,d19,#30
- veor d30,d19,d20
- vsli.64 d26,d19,#25
- veor d18,d24,d25
- vadd.i64 d27,d28
- vbsl d30,d21,d20 @ Maj(a,b,c)
- veor d18,d26 @ Sigma0(a)
- vadd.i64 d22,d27
- vadd.i64 d30,d27
- @ vadd.i64 d18,d30
- vshr.u64 q12,q6,#19
- vshr.u64 q13,q6,#61
- vadd.i64 d18,d30 @ h+=Maj from the past
- vshr.u64 q15,q6,#6
- vsli.64 q12,q6,#45
- vext.8 q14,q7,q0,#8 @ X[i+1]
- vsli.64 q13,q6,#3
- veor q15,q12
- vshr.u64 q12,q14,#1
- veor q15,q13 @ sigma1(X[i+14])
- vshr.u64 q13,q14,#8
- vadd.i64 q7,q15
- vshr.u64 q15,q14,#7
- vsli.64 q12,q14,#63
- vsli.64 q13,q14,#56
- vext.8 q14,q3,q4,#8 @ X[i+9]
- veor q15,q12
- vshr.u64 d24,d22,#14 @ from NEON_00_15
- vadd.i64 q7,q14
- vshr.u64 d25,d22,#18 @ from NEON_00_15
- veor q15,q13 @ sigma0(X[i+1])
- vshr.u64 d26,d22,#41 @ from NEON_00_15
- vadd.i64 q7,q15
- vld1.64 {d28},[r3,:64]! @ K[i++]
- vsli.64 d24,d22,#50
- vsli.64 d25,d22,#46
- vmov d29,d22
- vsli.64 d26,d22,#23
-#if 30<16 && defined(__ARMEL__)
- vrev64.8 ,
-#endif
- veor d25,d24
- vbsl d29,d23,d16 @ Ch(e,f,g)
- vshr.u64 d24,d18,#28
- veor d26,d25 @ Sigma1(e)
- vadd.i64 d27,d29,d17
- vshr.u64 d25,d18,#34
- vsli.64 d24,d18,#36
- vadd.i64 d27,d26
- vshr.u64 d26,d18,#39
- vadd.i64 d28,d14
- vsli.64 d25,d18,#30
- veor d30,d18,d19
- vsli.64 d26,d18,#25
- veor d17,d24,d25
- vadd.i64 d27,d28
- vbsl d30,d20,d19 @ Maj(a,b,c)
- veor d17,d26 @ Sigma0(a)
- vadd.i64 d21,d27
- vadd.i64 d30,d27
- @ vadd.i64 d17,d30
- vshr.u64 d24,d21,#14 @ 31
-#if 31<16
- vld1.64 {d15},[r1]! @ handles unaligned
-#endif
- vshr.u64 d25,d21,#18
-#if 31>0
- vadd.i64 d17,d30 @ h+=Maj from the past
-#endif
- vshr.u64 d26,d21,#41
- vld1.64 {d28},[r3,:64]! @ K[i++]
- vsli.64 d24,d21,#50
- vsli.64 d25,d21,#46
- vmov d29,d21
- vsli.64 d26,d21,#23
-#if 31<16 && defined(__ARMEL__)
- vrev64.8 ,
-#endif
- veor d25,d24
- vbsl d29,d22,d23 @ Ch(e,f,g)
- vshr.u64 d24,d17,#28
- veor d26,d25 @ Sigma1(e)
- vadd.i64 d27,d29,d16
- vshr.u64 d25,d17,#34
- vsli.64 d24,d17,#36
- vadd.i64 d27,d26
- vshr.u64 d26,d17,#39
- vadd.i64 d28,d15
- vsli.64 d25,d17,#30
- veor d30,d17,d18
- vsli.64 d26,d17,#25
- veor d16,d24,d25
- vadd.i64 d27,d28
- vbsl d30,d19,d18 @ Maj(a,b,c)
- veor d16,d26 @ Sigma0(a)
- vadd.i64 d20,d27
- vadd.i64 d30,d27
- @ vadd.i64 d16,d30
- bne .L16_79_neon
-
- vadd.i64 d16,d30 @ h+=Maj from the past
- vldmia r0,{d24-d31} @ load context to temp
- vadd.i64 q8,q12 @ vectorized accumulate
- vadd.i64 q9,q13
- vadd.i64 q10,q14
- vadd.i64 q11,q15
- vstmia r0,{d16-d23} @ save context
- teq r1,r2
- sub r3,#640 @ rewind K512
- bne .Loop_neon
-
- VFP_ABI_POP
- bx lr @ .word 0xe12fff1e
-.size sha512_block_data_order_neon,.-sha512_block_data_order_neon
-#endif
-.asciz "SHA512 block transform for ARMv4/NEON, CRYPTOGAMS by <appro@openssl.org>"
-.align 2
-#if __ARM_MAX_ARCH__>=7 && !defined(__KERNEL__)
-.comm OPENSSL_armcap_P,4,4
-#endif
diff --git a/arch/arm/include/asm/atomic.h b/arch/arm/include/asm/atomic.h
index 455eb19a5ac1..db8512d9a918 100644
--- a/arch/arm/include/asm/atomic.h
+++ b/arch/arm/include/asm/atomic.h
@@ -22,8 +22,8 @@
* strex/ldrex monitor on some implementations. The reason we can use it for
* atomic_set() is the clrex or dummy strex done on every exception return.
*/
-#define atomic_read(v) READ_ONCE((v)->counter)
-#define atomic_set(v,i) WRITE_ONCE(((v)->counter), (i))
+#define arch_atomic_read(v) READ_ONCE((v)->counter)
+#define arch_atomic_set(v,i) WRITE_ONCE(((v)->counter), (i))
#if __LINUX_ARM_ARCH__ >= 6
@@ -34,7 +34,7 @@
*/
#define ATOMIC_OP(op, c_op, asm_op) \
-static inline void atomic_##op(int i, atomic_t *v) \
+static inline void arch_atomic_##op(int i, atomic_t *v) \
{ \
unsigned long tmp; \
int result; \
@@ -52,7 +52,7 @@ static inline void atomic_##op(int i, atomic_t *v) \
} \
#define ATOMIC_OP_RETURN(op, c_op, asm_op) \
-static inline int atomic_##op##_return_relaxed(int i, atomic_t *v) \
+static inline int arch_atomic_##op##_return_relaxed(int i, atomic_t *v) \
{ \
unsigned long tmp; \
int result; \
@@ -73,7 +73,7 @@ static inline int atomic_##op##_return_relaxed(int i, atomic_t *v) \
}
#define ATOMIC_FETCH_OP(op, c_op, asm_op) \
-static inline int atomic_fetch_##op##_relaxed(int i, atomic_t *v) \
+static inline int arch_atomic_fetch_##op##_relaxed(int i, atomic_t *v) \
{ \
unsigned long tmp; \
int result, val; \
@@ -93,17 +93,17 @@ static inline int atomic_fetch_##op##_relaxed(int i, atomic_t *v) \
return result; \
}
-#define atomic_add_return_relaxed atomic_add_return_relaxed
-#define atomic_sub_return_relaxed atomic_sub_return_relaxed
-#define atomic_fetch_add_relaxed atomic_fetch_add_relaxed
-#define atomic_fetch_sub_relaxed atomic_fetch_sub_relaxed
+#define arch_atomic_add_return_relaxed arch_atomic_add_return_relaxed
+#define arch_atomic_sub_return_relaxed arch_atomic_sub_return_relaxed
+#define arch_atomic_fetch_add_relaxed arch_atomic_fetch_add_relaxed
+#define arch_atomic_fetch_sub_relaxed arch_atomic_fetch_sub_relaxed
-#define atomic_fetch_and_relaxed atomic_fetch_and_relaxed
-#define atomic_fetch_andnot_relaxed atomic_fetch_andnot_relaxed
-#define atomic_fetch_or_relaxed atomic_fetch_or_relaxed
-#define atomic_fetch_xor_relaxed atomic_fetch_xor_relaxed
+#define arch_atomic_fetch_and_relaxed arch_atomic_fetch_and_relaxed
+#define arch_atomic_fetch_andnot_relaxed arch_atomic_fetch_andnot_relaxed
+#define arch_atomic_fetch_or_relaxed arch_atomic_fetch_or_relaxed
+#define arch_atomic_fetch_xor_relaxed arch_atomic_fetch_xor_relaxed
-static inline int atomic_cmpxchg_relaxed(atomic_t *ptr, int old, int new)
+static inline int arch_atomic_cmpxchg_relaxed(atomic_t *ptr, int old, int new)
{
int oldval;
unsigned long res;
@@ -123,9 +123,9 @@ static inline int atomic_cmpxchg_relaxed(atomic_t *ptr, int old, int new)
return oldval;
}
-#define atomic_cmpxchg_relaxed atomic_cmpxchg_relaxed
+#define arch_atomic_cmpxchg_relaxed arch_atomic_cmpxchg_relaxed
-static inline int atomic_fetch_add_unless(atomic_t *v, int a, int u)
+static inline int arch_atomic_fetch_add_unless(atomic_t *v, int a, int u)
{
int oldval, newval;
unsigned long tmp;
@@ -151,7 +151,7 @@ static inline int atomic_fetch_add_unless(atomic_t *v, int a, int u)
return oldval;
}
-#define atomic_fetch_add_unless atomic_fetch_add_unless
+#define arch_atomic_fetch_add_unless arch_atomic_fetch_add_unless
#else /* ARM_ARCH_6 */
@@ -160,7 +160,7 @@ static inline int atomic_fetch_add_unless(atomic_t *v, int a, int u)
#endif
#define ATOMIC_OP(op, c_op, asm_op) \
-static inline void atomic_##op(int i, atomic_t *v) \
+static inline void arch_atomic_##op(int i, atomic_t *v) \
{ \
unsigned long flags; \
\
@@ -170,7 +170,7 @@ static inline void atomic_##op(int i, atomic_t *v) \
} \
#define ATOMIC_OP_RETURN(op, c_op, asm_op) \
-static inline int atomic_##op##_return(int i, atomic_t *v) \
+static inline int arch_atomic_##op##_return(int i, atomic_t *v) \
{ \
unsigned long flags; \
int val; \
@@ -184,7 +184,7 @@ static inline int atomic_##op##_return(int i, atomic_t *v) \
}
#define ATOMIC_FETCH_OP(op, c_op, asm_op) \
-static inline int atomic_fetch_##op(int i, atomic_t *v) \
+static inline int arch_atomic_fetch_##op(int i, atomic_t *v) \
{ \
unsigned long flags; \
int val; \
@@ -197,7 +197,7 @@ static inline int atomic_fetch_##op(int i, atomic_t *v) \
return val; \
}
-static inline int atomic_cmpxchg(atomic_t *v, int old, int new)
+static inline int arch_atomic_cmpxchg(atomic_t *v, int old, int new)
{
int ret;
unsigned long flags;
@@ -211,7 +211,7 @@ static inline int atomic_cmpxchg(atomic_t *v, int old, int new)
return ret;
}
-#define atomic_fetch_andnot atomic_fetch_andnot
+#define arch_atomic_fetch_andnot arch_atomic_fetch_andnot
#endif /* __LINUX_ARM_ARCH__ */
@@ -223,7 +223,7 @@ static inline int atomic_cmpxchg(atomic_t *v, int old, int new)
ATOMIC_OPS(add, +=, add)
ATOMIC_OPS(sub, -=, sub)
-#define atomic_andnot atomic_andnot
+#define arch_atomic_andnot arch_atomic_andnot
#undef ATOMIC_OPS
#define ATOMIC_OPS(op, c_op, asm_op) \
@@ -240,7 +240,7 @@ ATOMIC_OPS(xor, ^=, eor)
#undef ATOMIC_OP_RETURN
#undef ATOMIC_OP
-#define atomic_xchg(v, new) (xchg(&((v)->counter), new))
+#define arch_atomic_xchg(v, new) (arch_xchg(&((v)->counter), new))
#ifndef CONFIG_GENERIC_ATOMIC64
typedef struct {
@@ -250,7 +250,7 @@ typedef struct {
#define ATOMIC64_INIT(i) { (i) }
#ifdef CONFIG_ARM_LPAE
-static inline s64 atomic64_read(const atomic64_t *v)
+static inline s64 arch_atomic64_read(const atomic64_t *v)
{
s64 result;
@@ -263,7 +263,7 @@ static inline s64 atomic64_read(const atomic64_t *v)
return result;
}
-static inline void atomic64_set(atomic64_t *v, s64 i)
+static inline void arch_atomic64_set(atomic64_t *v, s64 i)
{
__asm__ __volatile__("@ atomic64_set\n"
" strd %2, %H2, [%1]"
@@ -272,7 +272,7 @@ static inline void atomic64_set(atomic64_t *v, s64 i)
);
}
#else
-static inline s64 atomic64_read(const atomic64_t *v)
+static inline s64 arch_atomic64_read(const atomic64_t *v)
{
s64 result;
@@ -285,7 +285,7 @@ static inline s64 atomic64_read(const atomic64_t *v)
return result;
}
-static inline void atomic64_set(atomic64_t *v, s64 i)
+static inline void arch_atomic64_set(atomic64_t *v, s64 i)
{
s64 tmp;
@@ -302,7 +302,7 @@ static inline void atomic64_set(atomic64_t *v, s64 i)
#endif
#define ATOMIC64_OP(op, op1, op2) \
-static inline void atomic64_##op(s64 i, atomic64_t *v) \
+static inline void arch_atomic64_##op(s64 i, atomic64_t *v) \
{ \
s64 result; \
unsigned long tmp; \
@@ -322,7 +322,7 @@ static inline void atomic64_##op(s64 i, atomic64_t *v) \
#define ATOMIC64_OP_RETURN(op, op1, op2) \
static inline s64 \
-atomic64_##op##_return_relaxed(s64 i, atomic64_t *v) \
+arch_atomic64_##op##_return_relaxed(s64 i, atomic64_t *v) \
{ \
s64 result; \
unsigned long tmp; \
@@ -345,7 +345,7 @@ atomic64_##op##_return_relaxed(s64 i, atomic64_t *v) \
#define ATOMIC64_FETCH_OP(op, op1, op2) \
static inline s64 \
-atomic64_fetch_##op##_relaxed(s64 i, atomic64_t *v) \
+arch_atomic64_fetch_##op##_relaxed(s64 i, atomic64_t *v) \
{ \
s64 result, val; \
unsigned long tmp; \
@@ -374,34 +374,34 @@ atomic64_fetch_##op##_relaxed(s64 i, atomic64_t *v) \
ATOMIC64_OPS(add, adds, adc)
ATOMIC64_OPS(sub, subs, sbc)
-#define atomic64_add_return_relaxed atomic64_add_return_relaxed
-#define atomic64_sub_return_relaxed atomic64_sub_return_relaxed
-#define atomic64_fetch_add_relaxed atomic64_fetch_add_relaxed
-#define atomic64_fetch_sub_relaxed atomic64_fetch_sub_relaxed
+#define arch_atomic64_add_return_relaxed arch_atomic64_add_return_relaxed
+#define arch_atomic64_sub_return_relaxed arch_atomic64_sub_return_relaxed
+#define arch_atomic64_fetch_add_relaxed arch_atomic64_fetch_add_relaxed
+#define arch_atomic64_fetch_sub_relaxed arch_atomic64_fetch_sub_relaxed
#undef ATOMIC64_OPS
#define ATOMIC64_OPS(op, op1, op2) \
ATOMIC64_OP(op, op1, op2) \
ATOMIC64_FETCH_OP(op, op1, op2)
-#define atomic64_andnot atomic64_andnot
+#define arch_atomic64_andnot arch_atomic64_andnot
ATOMIC64_OPS(and, and, and)
ATOMIC64_OPS(andnot, bic, bic)
ATOMIC64_OPS(or, orr, orr)
ATOMIC64_OPS(xor, eor, eor)
-#define atomic64_fetch_and_relaxed atomic64_fetch_and_relaxed
-#define atomic64_fetch_andnot_relaxed atomic64_fetch_andnot_relaxed
-#define atomic64_fetch_or_relaxed atomic64_fetch_or_relaxed
-#define atomic64_fetch_xor_relaxed atomic64_fetch_xor_relaxed
+#define arch_atomic64_fetch_and_relaxed arch_atomic64_fetch_and_relaxed
+#define arch_atomic64_fetch_andnot_relaxed arch_atomic64_fetch_andnot_relaxed
+#define arch_atomic64_fetch_or_relaxed arch_atomic64_fetch_or_relaxed
+#define arch_atomic64_fetch_xor_relaxed arch_atomic64_fetch_xor_relaxed
#undef ATOMIC64_OPS
#undef ATOMIC64_FETCH_OP
#undef ATOMIC64_OP_RETURN
#undef ATOMIC64_OP
-static inline s64 atomic64_cmpxchg_relaxed(atomic64_t *ptr, s64 old, s64 new)
+static inline s64 arch_atomic64_cmpxchg_relaxed(atomic64_t *ptr, s64 old, s64 new)
{
s64 oldval;
unsigned long res;
@@ -422,9 +422,9 @@ static inline s64 atomic64_cmpxchg_relaxed(atomic64_t *ptr, s64 old, s64 new)
return oldval;
}
-#define atomic64_cmpxchg_relaxed atomic64_cmpxchg_relaxed
+#define arch_atomic64_cmpxchg_relaxed arch_atomic64_cmpxchg_relaxed
-static inline s64 atomic64_xchg_relaxed(atomic64_t *ptr, s64 new)
+static inline s64 arch_atomic64_xchg_relaxed(atomic64_t *ptr, s64 new)
{
s64 result;
unsigned long tmp;
@@ -442,9 +442,9 @@ static inline s64 atomic64_xchg_relaxed(atomic64_t *ptr, s64 new)
return result;
}
-#define atomic64_xchg_relaxed atomic64_xchg_relaxed
+#define arch_atomic64_xchg_relaxed arch_atomic64_xchg_relaxed
-static inline s64 atomic64_dec_if_positive(atomic64_t *v)
+static inline s64 arch_atomic64_dec_if_positive(atomic64_t *v)
{
s64 result;
unsigned long tmp;
@@ -470,9 +470,9 @@ static inline s64 atomic64_dec_if_positive(atomic64_t *v)
return result;
}
-#define atomic64_dec_if_positive atomic64_dec_if_positive
+#define arch_atomic64_dec_if_positive arch_atomic64_dec_if_positive
-static inline s64 atomic64_fetch_add_unless(atomic64_t *v, s64 a, s64 u)
+static inline s64 arch_atomic64_fetch_add_unless(atomic64_t *v, s64 a, s64 u)
{
s64 oldval, newval;
unsigned long tmp;
@@ -500,7 +500,7 @@ static inline s64 atomic64_fetch_add_unless(atomic64_t *v, s64 a, s64 u)
return oldval;
}
-#define atomic64_fetch_add_unless atomic64_fetch_add_unless
+#define arch_atomic64_fetch_add_unless arch_atomic64_fetch_add_unless
#endif /* !CONFIG_GENERIC_ATOMIC64 */
#endif
diff --git a/arch/arm/include/asm/cmpxchg.h b/arch/arm/include/asm/cmpxchg.h
index 8b701f8e175c..4dfe538dfc68 100644
--- a/arch/arm/include/asm/cmpxchg.h
+++ b/arch/arm/include/asm/cmpxchg.h
@@ -114,7 +114,7 @@ static inline unsigned long __xchg(unsigned long x, volatile void *ptr, int size
return ret;
}
-#define xchg_relaxed(ptr, x) ({ \
+#define arch_xchg_relaxed(ptr, x) ({ \
(__typeof__(*(ptr)))__xchg((unsigned long)(x), (ptr), \
sizeof(*(ptr))); \
})
@@ -128,20 +128,20 @@ static inline unsigned long __xchg(unsigned long x, volatile void *ptr, int size
#error "SMP is not supported on this platform"
#endif
-#define xchg xchg_relaxed
+#define arch_xchg arch_xchg_relaxed
/*
* cmpxchg_local and cmpxchg64_local are atomic wrt current CPU. Always make
* them available.
*/
-#define cmpxchg_local(ptr, o, n) ({ \
- (__typeof(*ptr))__cmpxchg_local_generic((ptr), \
+#define arch_cmpxchg_local(ptr, o, n) ({ \
+ (__typeof(*ptr))__generic_cmpxchg_local((ptr), \
(unsigned long)(o), \
(unsigned long)(n), \
sizeof(*(ptr))); \
})
-#define cmpxchg64_local(ptr, o, n) __cmpxchg64_local_generic((ptr), (o), (n))
+#define arch_cmpxchg64_local(ptr, o, n) __generic_cmpxchg64_local((ptr), (o), (n))
#include <asm-generic/cmpxchg.h>
@@ -207,7 +207,7 @@ static inline unsigned long __cmpxchg(volatile void *ptr, unsigned long old,
return oldval;
}
-#define cmpxchg_relaxed(ptr,o,n) ({ \
+#define arch_cmpxchg_relaxed(ptr,o,n) ({ \
(__typeof__(*(ptr)))__cmpxchg((ptr), \
(unsigned long)(o), \
(unsigned long)(n), \
@@ -224,7 +224,7 @@ static inline unsigned long __cmpxchg_local(volatile void *ptr,
#ifdef CONFIG_CPU_V6 /* min ARCH == ARMv6 */
case 1:
case 2:
- ret = __cmpxchg_local_generic(ptr, old, new, size);
+ ret = __generic_cmpxchg_local(ptr, old, new, size);
break;
#endif
default:
@@ -234,7 +234,7 @@ static inline unsigned long __cmpxchg_local(volatile void *ptr,
return ret;
}
-#define cmpxchg_local(ptr, o, n) ({ \
+#define arch_cmpxchg_local(ptr, o, n) ({ \
(__typeof(*ptr))__cmpxchg_local((ptr), \
(unsigned long)(o), \
(unsigned long)(n), \
@@ -266,13 +266,13 @@ static inline unsigned long long __cmpxchg64(unsigned long long *ptr,
return oldval;
}
-#define cmpxchg64_relaxed(ptr, o, n) ({ \
+#define arch_cmpxchg64_relaxed(ptr, o, n) ({ \
(__typeof__(*(ptr)))__cmpxchg64((ptr), \
(unsigned long long)(o), \
(unsigned long long)(n)); \
})
-#define cmpxchg64_local(ptr, o, n) cmpxchg64_relaxed((ptr), (o), (n))
+#define arch_cmpxchg64_local(ptr, o, n) arch_cmpxchg64_relaxed((ptr), (o), (n))
#endif /* __LINUX_ARM_ARCH__ >= 6 */
diff --git a/arch/arm/include/asm/cpuidle.h b/arch/arm/include/asm/cpuidle.h
index 0d67ed682e07..397be5ed30e7 100644
--- a/arch/arm/include/asm/cpuidle.h
+++ b/arch/arm/include/asm/cpuidle.h
@@ -7,9 +7,11 @@
#ifdef CONFIG_CPU_IDLE
extern int arm_cpuidle_simple_enter(struct cpuidle_device *dev,
struct cpuidle_driver *drv, int index);
+#define __cpuidle_method_section __used __section("__cpuidle_method_of_table")
#else
static inline int arm_cpuidle_simple_enter(struct cpuidle_device *dev,
struct cpuidle_driver *drv, int index) { return -ENODEV; }
+#define __cpuidle_method_section __maybe_unused /* drop silently */
#endif
/* Common ARM WFI state */
@@ -42,11 +44,15 @@ struct of_cpuidle_method {
#define CPUIDLE_METHOD_OF_DECLARE(name, _method, _ops) \
static const struct of_cpuidle_method __cpuidle_method_of_table_##name \
- __used __section("__cpuidle_method_of_table") \
- = { .method = _method, .ops = _ops }
+ __cpuidle_method_section = { .method = _method, .ops = _ops }
extern int arm_cpuidle_suspend(int index);
extern int arm_cpuidle_init(int cpu);
+struct arm_cpuidle_irq_context { };
+
+#define arm_cpuidle_save_irq_context(c) (void)c
+#define arm_cpuidle_restore_irq_context(c) (void)c
+
#endif
diff --git a/arch/arm/include/asm/ftrace.h b/arch/arm/include/asm/ftrace.h
index 48ec1d0337da..a4dbac07e4ef 100644
--- a/arch/arm/include/asm/ftrace.h
+++ b/arch/arm/include/asm/ftrace.h
@@ -15,6 +15,9 @@ extern void __gnu_mcount_nc(void);
#ifdef CONFIG_DYNAMIC_FTRACE
struct dyn_arch_ftrace {
+#ifdef CONFIG_ARM_MODULE_PLTS
+ struct module *mod;
+#endif
};
static inline unsigned long ftrace_call_adjust(unsigned long addr)
diff --git a/arch/arm/include/asm/insn.h b/arch/arm/include/asm/insn.h
index f20e08ac85ae..5475cbf9fb6b 100644
--- a/arch/arm/include/asm/insn.h
+++ b/arch/arm/include/asm/insn.h
@@ -13,18 +13,18 @@ arm_gen_nop(void)
}
unsigned long
-__arm_gen_branch(unsigned long pc, unsigned long addr, bool link);
+__arm_gen_branch(unsigned long pc, unsigned long addr, bool link, bool warn);
static inline unsigned long
arm_gen_branch(unsigned long pc, unsigned long addr)
{
- return __arm_gen_branch(pc, addr, false);
+ return __arm_gen_branch(pc, addr, false, true);
}
static inline unsigned long
-arm_gen_branch_link(unsigned long pc, unsigned long addr)
+arm_gen_branch_link(unsigned long pc, unsigned long addr, bool warn)
{
- return __arm_gen_branch(pc, addr, true);
+ return __arm_gen_branch(pc, addr, true, warn);
}
#endif
diff --git a/arch/arm/include/asm/memory.h b/arch/arm/include/asm/memory.h
index a711322d9f40..cfc9dfd70aad 100644
--- a/arch/arm/include/asm/memory.h
+++ b/arch/arm/include/asm/memory.h
@@ -20,8 +20,14 @@
#endif
#include <asm/kasan_def.h>
-/* PAGE_OFFSET - the virtual address of the start of the kernel image */
+/*
+ * PAGE_OFFSET: the virtual address of the start of lowmem, memory above
+ * the virtual address range for userspace.
+ * KERNEL_OFFSET: the virtual address of the start of the kernel image.
+ * we may further offset this with TEXT_OFFSET in practice.
+ */
#define PAGE_OFFSET UL(CONFIG_PAGE_OFFSET)
+#define KERNEL_OFFSET (PAGE_OFFSET)
#ifdef CONFIG_MMU
@@ -153,6 +159,13 @@ extern unsigned long vectors_base;
#ifndef __ASSEMBLY__
/*
+ * Physical start and end address of the kernel sections. These addresses are
+ * 2MB-aligned to match the section mappings placed over the kernel.
+ */
+extern u32 kernel_sec_start;
+extern u32 kernel_sec_end;
+
+/*
* Physical vs virtual RAM address space conversion. These are
* private definitions which should NOT be used outside memory.h
* files. Use virt_to_phys/phys_to_virt/__pa/__va instead.
diff --git a/arch/arm/include/asm/module.h b/arch/arm/include/asm/module.h
index 4b0df09cbe67..cfffae67c04e 100644
--- a/arch/arm/include/asm/module.h
+++ b/arch/arm/include/asm/module.h
@@ -19,8 +19,18 @@ enum {
};
#endif
+#define PLT_ENT_STRIDE L1_CACHE_BYTES
+#define PLT_ENT_COUNT (PLT_ENT_STRIDE / sizeof(u32))
+#define PLT_ENT_SIZE (sizeof(struct plt_entries) / PLT_ENT_COUNT)
+
+struct plt_entries {
+ u32 ldr[PLT_ENT_COUNT];
+ u32 lit[PLT_ENT_COUNT];
+};
+
struct mod_plt_sec {
struct elf32_shdr *plt;
+ struct plt_entries *plt_ent;
int plt_count;
};
diff --git a/arch/arm/include/asm/pgalloc.h b/arch/arm/include/asm/pgalloc.h
index fdee1f04f4f3..a17f01235c29 100644
--- a/arch/arm/include/asm/pgalloc.h
+++ b/arch/arm/include/asm/pgalloc.h
@@ -143,7 +143,6 @@ pmd_populate(struct mm_struct *mm, pmd_t *pmdp, pgtable_t ptep)
__pmd_populate(pmdp, page_to_phys(ptep), prot);
}
-#define pmd_pgtable(pmd) pmd_page(pmd)
#endif /* CONFIG_MMU */
diff --git a/arch/arm/include/asm/pgtable-3level.h b/arch/arm/include/asm/pgtable-3level.h
index d4edab51a77c..eabe72ff7381 100644
--- a/arch/arm/include/asm/pgtable-3level.h
+++ b/arch/arm/include/asm/pgtable-3level.h
@@ -130,7 +130,7 @@
flush_pmd_entry(pudp); \
} while (0)
-static inline pmd_t *pud_page_vaddr(pud_t pud)
+static inline pmd_t *pud_pgtable(pud_t pud)
{
return __va(pud_val(pud) & PHYS_MASK & (s32)PAGE_MASK);
}
diff --git a/arch/arm/include/asm/pgtable.h b/arch/arm/include/asm/pgtable.h
index d63a5bb6bd0c..cd1f84bb40ae 100644
--- a/arch/arm/include/asm/pgtable.h
+++ b/arch/arm/include/asm/pgtable.h
@@ -306,7 +306,7 @@ static inline pte_t pte_modify(pte_t pte, pgprot_t newprot)
#define __swp_entry(type,offset) ((swp_entry_t) { ((type) << __SWP_TYPE_SHIFT) | ((offset) << __SWP_OFFSET_SHIFT) })
#define __pte_to_swp_entry(pte) ((swp_entry_t) { pte_val(pte) })
-#define __swp_entry_to_pte(swp) ((pte_t) { (swp).val })
+#define __swp_entry_to_pte(swp) __pte((swp).val | PTE_TYPE_FAULT)
/*
* It is an error for the kernel to have more swap files than we can
diff --git a/arch/arm/include/asm/sync_bitops.h b/arch/arm/include/asm/sync_bitops.h
index 39ff217136d1..6f5d627c44a3 100644
--- a/arch/arm/include/asm/sync_bitops.h
+++ b/arch/arm/include/asm/sync_bitops.h
@@ -21,7 +21,7 @@
#define sync_test_and_clear_bit(nr, p) _test_and_clear_bit(nr, p)
#define sync_test_and_change_bit(nr, p) _test_and_change_bit(nr, p)
#define sync_test_bit(nr, addr) test_bit(nr, addr)
-#define sync_cmpxchg cmpxchg
+#define arch_sync_cmpxchg arch_cmpxchg
#endif
diff --git a/arch/arm/include/asm/system_misc.h b/arch/arm/include/asm/system_misc.h
index 66f6a3ae68d2..98b37340376b 100644
--- a/arch/arm/include/asm/system_misc.h
+++ b/arch/arm/include/asm/system_misc.h
@@ -13,7 +13,6 @@
extern void cpu_init(void);
void soft_restart(unsigned long);
-extern void (*arm_pm_restart)(enum reboot_mode reboot_mode, const char *cmd);
extern void (*arm_pm_idle)(void);
#ifdef CONFIG_HARDEN_BRANCH_PREDICTOR
diff --git a/arch/arm/include/asm/tlbflush.h b/arch/arm/include/asm/tlbflush.h
index 24cbfc112dfa..0ccc985b90af 100644
--- a/arch/arm/include/asm/tlbflush.h
+++ b/arch/arm/include/asm/tlbflush.h
@@ -253,7 +253,7 @@ extern struct cpu_tlb_fns cpu_tlb;
* space.
* - mm - mm_struct describing address space
*
- * flush_tlb_range(mm,start,end)
+ * flush_tlb_range(vma,start,end)
*
* Invalidate a range of TLB entries in the specified
* address space.
@@ -261,18 +261,11 @@ extern struct cpu_tlb_fns cpu_tlb;
* - start - start address (may not be aligned)
* - end - end address (exclusive, may not be aligned)
*
- * flush_tlb_page(vaddr,vma)
+ * flush_tlb_page(vma, uaddr)
*
* Invalidate the specified page in the specified address range.
+ * - vma - vm_area_struct describing address range
* - vaddr - virtual address (may not be aligned)
- * - vma - vma_struct describing address range
- *
- * flush_kern_tlb_page(kaddr)
- *
- * Invalidate the TLB entry for the specified page. The address
- * will be in the kernels virtual memory space. Current uses
- * only require the D-TLB to be invalidated.
- * - kaddr - Kernel virtual memory address
*/
/*
diff --git a/arch/arm/include/asm/unaligned.h b/arch/arm/include/asm/unaligned.h
deleted file mode 100644
index ab905ffcf193..000000000000
--- a/arch/arm/include/asm/unaligned.h
+++ /dev/null
@@ -1,27 +0,0 @@
-#ifndef __ASM_ARM_UNALIGNED_H
-#define __ASM_ARM_UNALIGNED_H
-
-/*
- * We generally want to set CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS on ARMv6+,
- * but we don't want to use linux/unaligned/access_ok.h since that can lead
- * to traps on unaligned stm/ldm or strd/ldrd.
- */
-#include <asm/byteorder.h>
-
-#if defined(__LITTLE_ENDIAN)
-# include <linux/unaligned/le_struct.h>
-# include <linux/unaligned/be_byteshift.h>
-# include <linux/unaligned/generic.h>
-# define get_unaligned __get_unaligned_le
-# define put_unaligned __put_unaligned_le
-#elif defined(__BIG_ENDIAN)
-# include <linux/unaligned/be_struct.h>
-# include <linux/unaligned/le_byteshift.h>
-# include <linux/unaligned/generic.h>
-# define get_unaligned __get_unaligned_be
-# define put_unaligned __put_unaligned_be
-#else
-# error need to define endianess
-#endif
-
-#endif /* __ASM_ARM_UNALIGNED_H */
diff --git a/arch/arm/kernel/ftrace.c b/arch/arm/kernel/ftrace.c
index 9a79ef6b1876..3c83b5d29697 100644
--- a/arch/arm/kernel/ftrace.c
+++ b/arch/arm/kernel/ftrace.c
@@ -68,9 +68,10 @@ int ftrace_arch_code_modify_post_process(void)
return 0;
}
-static unsigned long ftrace_call_replace(unsigned long pc, unsigned long addr)
+static unsigned long ftrace_call_replace(unsigned long pc, unsigned long addr,
+ bool warn)
{
- return arm_gen_branch_link(pc, addr);
+ return arm_gen_branch_link(pc, addr, warn);
}
static int ftrace_modify_code(unsigned long pc, unsigned long old,
@@ -104,14 +105,14 @@ int ftrace_update_ftrace_func(ftrace_func_t func)
int ret;
pc = (unsigned long)&ftrace_call;
- new = ftrace_call_replace(pc, (unsigned long)func);
+ new = ftrace_call_replace(pc, (unsigned long)func, true);
ret = ftrace_modify_code(pc, 0, new, false);
#ifdef CONFIG_DYNAMIC_FTRACE_WITH_REGS
if (!ret) {
pc = (unsigned long)&ftrace_regs_call;
- new = ftrace_call_replace(pc, (unsigned long)func);
+ new = ftrace_call_replace(pc, (unsigned long)func, true);
ret = ftrace_modify_code(pc, 0, new, false);
}
@@ -124,10 +125,22 @@ int ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr)
{
unsigned long new, old;
unsigned long ip = rec->ip;
+ unsigned long aaddr = adjust_address(rec, addr);
+ struct module *mod = NULL;
+
+#ifdef CONFIG_ARM_MODULE_PLTS
+ mod = rec->arch.mod;
+#endif
old = ftrace_nop_replace(rec);
- new = ftrace_call_replace(ip, adjust_address(rec, addr));
+ new = ftrace_call_replace(ip, aaddr, !mod);
+#ifdef CONFIG_ARM_MODULE_PLTS
+ if (!new && mod) {
+ aaddr = get_module_plt(mod, ip, aaddr);
+ new = ftrace_call_replace(ip, aaddr, true);
+ }
+#endif
return ftrace_modify_code(rec->ip, old, new, true);
}
@@ -140,9 +153,9 @@ int ftrace_modify_call(struct dyn_ftrace *rec, unsigned long old_addr,
unsigned long new, old;
unsigned long ip = rec->ip;
- old = ftrace_call_replace(ip, adjust_address(rec, old_addr));
+ old = ftrace_call_replace(ip, adjust_address(rec, old_addr), true);
- new = ftrace_call_replace(ip, adjust_address(rec, addr));
+ new = ftrace_call_replace(ip, adjust_address(rec, addr), true);
return ftrace_modify_code(rec->ip, old, new, true);
}
@@ -152,12 +165,29 @@ int ftrace_modify_call(struct dyn_ftrace *rec, unsigned long old_addr,
int ftrace_make_nop(struct module *mod,
struct dyn_ftrace *rec, unsigned long addr)
{
+ unsigned long aaddr = adjust_address(rec, addr);
unsigned long ip = rec->ip;
unsigned long old;
unsigned long new;
int ret;
- old = ftrace_call_replace(ip, adjust_address(rec, addr));
+#ifdef CONFIG_ARM_MODULE_PLTS
+ /* mod is only supplied during module loading */
+ if (!mod)
+ mod = rec->arch.mod;
+ else
+ rec->arch.mod = mod;
+#endif
+
+ old = ftrace_call_replace(ip, aaddr,
+ !IS_ENABLED(CONFIG_ARM_MODULE_PLTS) || !mod);
+#ifdef CONFIG_ARM_MODULE_PLTS
+ if (!old && mod) {
+ aaddr = get_module_plt(mod, ip, aaddr);
+ old = ftrace_call_replace(ip, aaddr, true);
+ }
+#endif
+
new = ftrace_nop_replace(rec);
ret = ftrace_modify_code(ip, old, new, true);
diff --git a/arch/arm/kernel/head.S b/arch/arm/kernel/head.S
index 7f62c5eccdf3..9eb0b4dbcc12 100644
--- a/arch/arm/kernel/head.S
+++ b/arch/arm/kernel/head.S
@@ -23,7 +23,6 @@
#if defined(CONFIG_DEBUG_LL) && !defined(CONFIG_DEBUG_SEMIHOSTING)
#include CONFIG_DEBUG_LL_INCLUDE
#endif
-
/*
* swapper_pg_dir is the virtual address of the initial page table.
* We place the page tables 16K below KERNEL_RAM_VADDR. Therefore, we must
@@ -31,7 +30,7 @@
* the least significant 16 bits to be 0x8000, but we could probably
* relax this restriction to KERNEL_RAM_VADDR >= PAGE_OFFSET + 0x4000.
*/
-#define KERNEL_RAM_VADDR (PAGE_OFFSET + TEXT_OFFSET)
+#define KERNEL_RAM_VADDR (KERNEL_OFFSET + TEXT_OFFSET)
#if (KERNEL_RAM_VADDR & 0xffff) != 0x8000
#error KERNEL_RAM_VADDR must start at 0xXXXX8000
#endif
@@ -48,6 +47,20 @@
.globl swapper_pg_dir
.equ swapper_pg_dir, KERNEL_RAM_VADDR - PG_DIR_SIZE
+ /*
+ * This needs to be assigned at runtime when the linker symbols are
+ * resolved.
+ */
+ .pushsection .data
+ .align 2
+ .globl kernel_sec_start
+ .globl kernel_sec_end
+kernel_sec_start:
+ .long 0
+kernel_sec_end:
+ .long 0
+ .popsection
+
.macro pgtbl, rd, phys
add \rd, \phys, #TEXT_OFFSET
sub \rd, \rd, #PG_DIR_SIZE
@@ -230,16 +243,23 @@ __create_page_tables:
blo 1b
/*
- * Map our RAM from the start to the end of the kernel .bss section.
+ * The main matter: map in the kernel using section mappings, and
+ * set two variables to indicate the physical start and end of the
+ * kernel.
*/
- add r0, r4, #PAGE_OFFSET >> (SECTION_SHIFT - PMD_ORDER)
+ add r0, r4, #KERNEL_OFFSET >> (SECTION_SHIFT - PMD_ORDER)
ldr r6, =(_end - 1)
- orr r3, r8, r7
+ adr_l r5, kernel_sec_start @ _pa(kernel_sec_start)
+ str r8, [r5] @ Save physical start of kernel
+ orr r3, r8, r7 @ Add the MMU flags
add r6, r4, r6, lsr #(SECTION_SHIFT - PMD_ORDER)
1: str r3, [r0], #1 << PMD_ORDER
add r3, r3, #1 << SECTION_SHIFT
cmp r0, r6
bls 1b
+ eor r3, r3, r7 @ Remove the MMU flags
+ adr_l r5, kernel_sec_end @ _pa(kernel_sec_end)
+ str r3, [r5] @ Save physical end of kernel
#ifdef CONFIG_XIP_KERNEL
/*
diff --git a/arch/arm/kernel/insn.c b/arch/arm/kernel/insn.c
index 2e844b70386b..db0acbb7d7a0 100644
--- a/arch/arm/kernel/insn.c
+++ b/arch/arm/kernel/insn.c
@@ -3,8 +3,9 @@
#include <linux/kernel.h>
#include <asm/opcodes.h>
-static unsigned long
-__arm_gen_branch_thumb2(unsigned long pc, unsigned long addr, bool link)
+static unsigned long __arm_gen_branch_thumb2(unsigned long pc,
+ unsigned long addr, bool link,
+ bool warn)
{
unsigned long s, j1, j2, i1, i2, imm10, imm11;
unsigned long first, second;
@@ -12,7 +13,7 @@ __arm_gen_branch_thumb2(unsigned long pc, unsigned long addr, bool link)
offset = (long)addr - (long)(pc + 4);
if (offset < -16777216 || offset > 16777214) {
- WARN_ON_ONCE(1);
+ WARN_ON_ONCE(warn);
return 0;
}
@@ -33,8 +34,8 @@ __arm_gen_branch_thumb2(unsigned long pc, unsigned long addr, bool link)
return __opcode_thumb32_compose(first, second);
}
-static unsigned long
-__arm_gen_branch_arm(unsigned long pc, unsigned long addr, bool link)
+static unsigned long __arm_gen_branch_arm(unsigned long pc, unsigned long addr,
+ bool link, bool warn)
{
unsigned long opcode = 0xea000000;
long offset;
@@ -44,7 +45,7 @@ __arm_gen_branch_arm(unsigned long pc, unsigned long addr, bool link)
offset = (long)addr - (long)(pc + 8);
if (unlikely(offset < -33554432 || offset > 33554428)) {
- WARN_ON_ONCE(1);
+ WARN_ON_ONCE(warn);
return 0;
}
@@ -54,10 +55,10 @@ __arm_gen_branch_arm(unsigned long pc, unsigned long addr, bool link)
}
unsigned long
-__arm_gen_branch(unsigned long pc, unsigned long addr, bool link)
+__arm_gen_branch(unsigned long pc, unsigned long addr, bool link, bool warn)
{
if (IS_ENABLED(CONFIG_THUMB2_KERNEL))
- return __arm_gen_branch_thumb2(pc, addr, link);
+ return __arm_gen_branch_thumb2(pc, addr, link, warn);
else
- return __arm_gen_branch_arm(pc, addr, link);
+ return __arm_gen_branch_arm(pc, addr, link, warn);
}
diff --git a/arch/arm/kernel/irq.c b/arch/arm/kernel/irq.c
index 698b6f636156..20ab1e607522 100644
--- a/arch/arm/kernel/irq.c
+++ b/arch/arm/kernel/irq.c
@@ -63,7 +63,27 @@ int arch_show_interrupts(struct seq_file *p, int prec)
*/
void handle_IRQ(unsigned int irq, struct pt_regs *regs)
{
- __handle_domain_irq(NULL, irq, false, regs);
+ struct pt_regs *old_regs = set_irq_regs(regs);
+ struct irq_desc *desc;
+
+ irq_enter();
+
+ /*
+ * Some hardware gives randomly wrong interrupts. Rather
+ * than crashing, do something sensible.
+ */
+ if (unlikely(!irq || irq >= nr_irqs))
+ desc = NULL;
+ else
+ desc = irq_to_desc(irq);
+
+ if (likely(desc))
+ handle_irq_desc(desc);
+ else
+ ack_bad_irq(irq);
+
+ irq_exit();
+ set_irq_regs(old_regs);
}
/*
diff --git a/arch/arm/kernel/module-plts.c b/arch/arm/kernel/module-plts.c
index 6e626abaefc5..1fc309b41f94 100644
--- a/arch/arm/kernel/module-plts.c
+++ b/arch/arm/kernel/module-plts.c
@@ -4,6 +4,7 @@
*/
#include <linux/elf.h>
+#include <linux/ftrace.h>
#include <linux/kernel.h>
#include <linux/module.h>
#include <linux/sort.h>
@@ -12,10 +13,6 @@
#include <asm/cache.h>
#include <asm/opcodes.h>
-#define PLT_ENT_STRIDE L1_CACHE_BYTES
-#define PLT_ENT_COUNT (PLT_ENT_STRIDE / sizeof(u32))
-#define PLT_ENT_SIZE (sizeof(struct plt_entries) / PLT_ENT_COUNT)
-
#ifdef CONFIG_THUMB2_KERNEL
#define PLT_ENT_LDR __opcode_to_mem_thumb32(0xf8dff000 | \
(PLT_ENT_STRIDE - 4))
@@ -24,9 +21,11 @@
(PLT_ENT_STRIDE - 8))
#endif
-struct plt_entries {
- u32 ldr[PLT_ENT_COUNT];
- u32 lit[PLT_ENT_COUNT];
+static const u32 fixed_plts[] = {
+#ifdef CONFIG_DYNAMIC_FTRACE
+ FTRACE_ADDR,
+ MCOUNT_ADDR,
+#endif
};
static bool in_init(const struct module *mod, unsigned long loc)
@@ -34,14 +33,40 @@ static bool in_init(const struct module *mod, unsigned long loc)
return loc - (u32)mod->init_layout.base < mod->init_layout.size;
}
+static void prealloc_fixed(struct mod_plt_sec *pltsec, struct plt_entries *plt)
+{
+ int i;
+
+ if (!ARRAY_SIZE(fixed_plts) || pltsec->plt_count)
+ return;
+ pltsec->plt_count = ARRAY_SIZE(fixed_plts);
+
+ for (i = 0; i < ARRAY_SIZE(plt->ldr); ++i)
+ plt->ldr[i] = PLT_ENT_LDR;
+
+ BUILD_BUG_ON(sizeof(fixed_plts) > sizeof(plt->lit));
+ memcpy(plt->lit, fixed_plts, sizeof(fixed_plts));
+}
+
u32 get_module_plt(struct module *mod, unsigned long loc, Elf32_Addr val)
{
struct mod_plt_sec *pltsec = !in_init(mod, loc) ? &mod->arch.core :
&mod->arch.init;
+ struct plt_entries *plt;
+ int idx;
+
+ /* cache the address, ELF header is available only during module load */
+ if (!pltsec->plt_ent)
+ pltsec->plt_ent = (struct plt_entries *)pltsec->plt->sh_addr;
+ plt = pltsec->plt_ent;
- struct plt_entries *plt = (struct plt_entries *)pltsec->plt->sh_addr;
- int idx = 0;
+ prealloc_fixed(pltsec, plt);
+
+ for (idx = 0; idx < ARRAY_SIZE(fixed_plts); ++idx)
+ if (plt->lit[idx] == val)
+ return (u32)&plt->ldr[idx];
+ idx = 0;
/*
* Look for an existing entry pointing to 'val'. Given that the
* relocations are sorted, this will be the last entry we allocated.
@@ -189,8 +214,8 @@ static unsigned int count_plts(const Elf32_Sym *syms, Elf32_Addr base,
int module_frob_arch_sections(Elf_Ehdr *ehdr, Elf_Shdr *sechdrs,
char *secstrings, struct module *mod)
{
- unsigned long core_plts = 0;
- unsigned long init_plts = 0;
+ unsigned long core_plts = ARRAY_SIZE(fixed_plts);
+ unsigned long init_plts = ARRAY_SIZE(fixed_plts);
Elf32_Shdr *s, *sechdrs_end = sechdrs + ehdr->e_shnum;
Elf32_Sym *syms = NULL;
@@ -245,6 +270,7 @@ int module_frob_arch_sections(Elf_Ehdr *ehdr, Elf_Shdr *sechdrs,
mod->arch.core.plt->sh_size = round_up(core_plts * PLT_ENT_SIZE,
sizeof(struct plt_entries));
mod->arch.core.plt_count = 0;
+ mod->arch.core.plt_ent = NULL;
mod->arch.init.plt->sh_type = SHT_NOBITS;
mod->arch.init.plt->sh_flags = SHF_EXECINSTR | SHF_ALLOC;
@@ -252,6 +278,7 @@ int module_frob_arch_sections(Elf_Ehdr *ehdr, Elf_Shdr *sechdrs,
mod->arch.init.plt->sh_size = round_up(init_plts * PLT_ENT_SIZE,
sizeof(struct plt_entries));
mod->arch.init.plt_count = 0;
+ mod->arch.init.plt_ent = NULL;
pr_debug("%s: plt=%x, init.plt=%x\n", __func__,
mod->arch.core.plt->sh_size, mod->arch.init.plt->sh_size);
diff --git a/arch/arm/kernel/perf_event_v7.c b/arch/arm/kernel/perf_event_v7.c
index 2924d7910b10..eb2190477da1 100644
--- a/arch/arm/kernel/perf_event_v7.c
+++ b/arch/arm/kernel/perf_event_v7.c
@@ -773,10 +773,10 @@ static inline void armv7pmu_write_counter(struct perf_event *event, u64 value)
pr_err("CPU%u writing wrong counter %d\n",
smp_processor_id(), idx);
} else if (idx == ARMV7_IDX_CYCLE_COUNTER) {
- asm volatile("mcr p15, 0, %0, c9, c13, 0" : : "r" (value));
+ asm volatile("mcr p15, 0, %0, c9, c13, 0" : : "r" ((u32)value));
} else {
armv7_pmnc_select_counter(idx);
- asm volatile("mcr p15, 0, %0, c9, c13, 2" : : "r" (value));
+ asm volatile("mcr p15, 0, %0, c9, c13, 2" : : "r" ((u32)value));
}
}
diff --git a/arch/arm/kernel/process.c b/arch/arm/kernel/process.c
index 6324f4db9b02..fc9e8b37eaa8 100644
--- a/arch/arm/kernel/process.c
+++ b/arch/arm/kernel/process.c
@@ -288,7 +288,7 @@ unsigned long get_wchan(struct task_struct *p)
struct stackframe frame;
unsigned long stack_page;
int count = 0;
- if (!p || p == current || p->state == TASK_RUNNING)
+ if (!p || p == current || task_is_running(p))
return 0;
frame.fp = thread_saved_fp(p);
diff --git a/arch/arm/kernel/reboot.c b/arch/arm/kernel/reboot.c
index 0ce388f15422..3044fcb8d073 100644
--- a/arch/arm/kernel/reboot.c
+++ b/arch/arm/kernel/reboot.c
@@ -18,7 +18,6 @@ typedef void (*phys_reset_t)(unsigned long, bool);
/*
* Function pointers to optional machine specific functions
*/
-void (*arm_pm_restart)(enum reboot_mode reboot_mode, const char *cmd);
void (*pm_power_off)(void);
EXPORT_SYMBOL(pm_power_off);
@@ -138,10 +137,7 @@ void machine_restart(char *cmd)
local_irq_disable();
smp_send_stop();
- if (arm_pm_restart)
- arm_pm_restart(reboot_mode, cmd);
- else
- do_kernel_restart(cmd);
+ do_kernel_restart(cmd);
/* Give a grace period for failure to restart of 1s */
mdelay(1000);
diff --git a/arch/arm/kernel/setup.c b/arch/arm/kernel/setup.c
index 1a5edf562e85..f97eb2371672 100644
--- a/arch/arm/kernel/setup.c
+++ b/arch/arm/kernel/setup.c
@@ -545,9 +545,11 @@ void notrace cpu_init(void)
* In Thumb-2, msr with an immediate value is not allowed.
*/
#ifdef CONFIG_THUMB2_KERNEL
-#define PLC "r"
+#define PLC_l "l"
+#define PLC_r "r"
#else
-#define PLC "I"
+#define PLC_l "I"
+#define PLC_r "I"
#endif
/*
@@ -569,15 +571,15 @@ void notrace cpu_init(void)
"msr cpsr_c, %9"
:
: "r" (stk),
- PLC (PSR_F_BIT | PSR_I_BIT | IRQ_MODE),
+ PLC_r (PSR_F_BIT | PSR_I_BIT | IRQ_MODE),
"I" (offsetof(struct stack, irq[0])),
- PLC (PSR_F_BIT | PSR_I_BIT | ABT_MODE),
+ PLC_r (PSR_F_BIT | PSR_I_BIT | ABT_MODE),
"I" (offsetof(struct stack, abt[0])),
- PLC (PSR_F_BIT | PSR_I_BIT | UND_MODE),
+ PLC_r (PSR_F_BIT | PSR_I_BIT | UND_MODE),
"I" (offsetof(struct stack, und[0])),
- PLC (PSR_F_BIT | PSR_I_BIT | FIQ_MODE),
+ PLC_r (PSR_F_BIT | PSR_I_BIT | FIQ_MODE),
"I" (offsetof(struct stack, fiq[0])),
- PLC (PSR_F_BIT | PSR_I_BIT | SVC_MODE)
+ PLC_l (PSR_F_BIT | PSR_I_BIT | SVC_MODE)
: "r14");
#endif
}
@@ -1081,6 +1083,20 @@ void __init hyp_mode_check(void)
#endif
}
+static void (*__arm_pm_restart)(enum reboot_mode reboot_mode, const char *cmd);
+
+static int arm_restart(struct notifier_block *nb, unsigned long action,
+ void *data)
+{
+ __arm_pm_restart(action, data);
+ return NOTIFY_DONE;
+}
+
+static struct notifier_block arm_restart_nb = {
+ .notifier_call = arm_restart,
+ .priority = 128,
+};
+
void __init setup_arch(char **cmdline_p)
{
const struct machine_desc *mdesc = NULL;
@@ -1114,10 +1130,7 @@ void __init setup_arch(char **cmdline_p)
if (mdesc->reboot_mode != REBOOT_HARD)
reboot_mode = mdesc->reboot_mode;
- init_mm.start_code = (unsigned long) _text;
- init_mm.end_code = (unsigned long) _etext;
- init_mm.end_data = (unsigned long) _edata;
- init_mm.brk = (unsigned long) _end;
+ setup_initial_init_mm(_text, _etext, _edata, _end);
/* populate cmd_line too for later use, preserving boot_command_line */
strlcpy(cmd_line, boot_command_line, COMMAND_LINE_SIZE);
@@ -1149,8 +1162,10 @@ void __init setup_arch(char **cmdline_p)
kasan_init();
request_standard_resources(mdesc);
- if (mdesc->restart)
- arm_pm_restart = mdesc->restart;
+ if (mdesc->restart) {
+ __arm_pm_restart = mdesc->restart;
+ register_restart_handler(&arm_restart_nb);
+ }
unflatten_device_tree();
diff --git a/arch/arm/kernel/smp.c b/arch/arm/kernel/smp.c
index 74679240a9d8..c7bb168b0d97 100644
--- a/arch/arm/kernel/smp.c
+++ b/arch/arm/kernel/smp.c
@@ -432,7 +432,6 @@ asmlinkage void secondary_start_kernel(void)
#endif
pr_debug("CPU%u: Booted secondary processor\n", cpu);
- preempt_disable();
trace_hardirqs_off();
/*
diff --git a/arch/arm/kernel/vmlinux.lds.S b/arch/arm/kernel/vmlinux.lds.S
index f7f4620d59c3..20c4f6d20c7a 100644
--- a/arch/arm/kernel/vmlinux.lds.S
+++ b/arch/arm/kernel/vmlinux.lds.S
@@ -47,7 +47,7 @@ SECTIONS
#endif
}
- . = PAGE_OFFSET + TEXT_OFFSET;
+ . = KERNEL_OFFSET + TEXT_OFFSET;
.head.text : {
_text = .;
HEAD_TEXT
diff --git a/arch/arm/mach-ixp4xx/common.c b/arch/arm/mach-ixp4xx/common.c
index aeaaa65ad757..b5eadd70d903 100644
--- a/arch/arm/mach-ixp4xx/common.c
+++ b/arch/arm/mach-ixp4xx/common.c
@@ -276,12 +276,38 @@ static struct platform_device *ixp46x_devices[] __initdata = {
unsigned long ixp4xx_exp_bus_size;
EXPORT_SYMBOL(ixp4xx_exp_bus_size);
+static struct platform_device_info ixp_dev_info __initdata = {
+ .name = "ixp4xx_crypto",
+ .id = 0,
+ .dma_mask = DMA_BIT_MASK(32),
+};
+
+static int __init ixp_crypto_register(void)
+{
+ struct platform_device *pdev;
+
+ if (!(~(*IXP4XX_EXP_CFG2) & (IXP4XX_FEATURE_HASH |
+ IXP4XX_FEATURE_AES | IXP4XX_FEATURE_DES))) {
+ printk(KERN_ERR "ixp_crypto: No HW crypto available\n");
+ return -ENODEV;
+ }
+
+ pdev = platform_device_register_full(&ixp_dev_info);
+ if (IS_ERR(pdev))
+ return PTR_ERR(pdev);
+
+ return 0;
+}
+
void __init ixp4xx_sys_init(void)
{
ixp4xx_exp_bus_size = SZ_16M;
platform_add_devices(ixp4xx_devices, ARRAY_SIZE(ixp4xx_devices));
+ if (IS_ENABLED(CONFIG_CRYPTO_DEV_IXP4XX))
+ ixp_crypto_register();
+
if (cpu_is_ixp46x()) {
int region;
diff --git a/arch/arm/mach-zynq/Kconfig b/arch/arm/mach-zynq/Kconfig
index 43fb941dcd07..a56748d671c4 100644
--- a/arch/arm/mach-zynq/Kconfig
+++ b/arch/arm/mach-zynq/Kconfig
@@ -6,7 +6,7 @@ config ARCH_ZYNQ
select ARCH_SUPPORTS_BIG_ENDIAN
select ARM_AMBA
select ARM_GIC
- select ARM_GLOBAL_TIMER if !CPU_FREQ
+ select ARM_GLOBAL_TIMER
select CADENCE_TTC_TIMER
select HAVE_ARM_SCU if SMP
select HAVE_ARM_TWD if SMP
diff --git a/arch/arm/mm/Kconfig b/arch/arm/mm/Kconfig
index 35f43d0aa056..8355c3895894 100644
--- a/arch/arm/mm/Kconfig
+++ b/arch/arm/mm/Kconfig
@@ -601,8 +601,6 @@ config CPU_TLB_V6
config CPU_TLB_V7
bool
-config VERIFY_PERMISSION_FAULT
- bool
endif
config CPU_HAS_ASID
diff --git a/arch/arm/mm/abort-ev7.S b/arch/arm/mm/abort-ev7.S
index f7cc5d68444b..f81bceacc660 100644
--- a/arch/arm/mm/abort-ev7.S
+++ b/arch/arm/mm/abort-ev7.S
@@ -17,31 +17,5 @@ ENTRY(v7_early_abort)
mrc p15, 0, r1, c5, c0, 0 @ get FSR
mrc p15, 0, r0, c6, c0, 0 @ get FAR
uaccess_disable ip @ disable userspace access
-
- /*
- * V6 code adjusts the returned DFSR.
- * New designs should not need to patch up faults.
- */
-
-#if defined(CONFIG_VERIFY_PERMISSION_FAULT)
- /*
- * Detect erroneous permission failures and fix
- */
- ldr r3, =0x40d @ On permission fault
- and r3, r1, r3
- cmp r3, #0x0d
- bne do_DataAbort
-
- mcr p15, 0, r0, c7, c8, 0 @ Retranslate FAR
- isb
- mrc p15, 0, ip, c7, c4, 0 @ Read the PAR
- and r3, ip, #0x7b @ On translation fault
- cmp r3, #0x0b
- bne do_DataAbort
- bic r1, r1, #0xf @ Fix up FSR FS[5:0]
- and ip, ip, #0x7e
- orr r1, r1, ip, LSR #1
-#endif
-
b do_DataAbort
ENDPROC(v7_early_abort)
diff --git a/arch/arm/mm/init.c b/arch/arm/mm/init.c
index 9d4744a632c6..6162a070a410 100644
--- a/arch/arm/mm/init.c
+++ b/arch/arm/mm/init.c
@@ -125,11 +125,22 @@ static void __init zone_sizes_init(unsigned long min, unsigned long max_low,
int pfn_valid(unsigned long pfn)
{
phys_addr_t addr = __pfn_to_phys(pfn);
+ unsigned long pageblock_size = PAGE_SIZE * pageblock_nr_pages;
if (__phys_to_pfn(addr) != pfn)
return 0;
- return memblock_is_map_memory(addr);
+ /*
+ * If address less than pageblock_size bytes away from a present
+ * memory chunk there still will be a memory map entry for it
+ * because we round freed memory map to the pageblock boundaries.
+ */
+ if (memblock_overlaps_region(&memblock.memory,
+ ALIGN_DOWN(addr, pageblock_size),
+ pageblock_size))
+ return 1;
+
+ return 0;
}
EXPORT_SYMBOL(pfn_valid);
#endif
diff --git a/arch/arm/mm/ioremap.c b/arch/arm/mm/ioremap.c
index 000e8210000b..80fb5a4a5c05 100644
--- a/arch/arm/mm/ioremap.c
+++ b/arch/arm/mm/ioremap.c
@@ -27,6 +27,7 @@
#include <linux/vmalloc.h>
#include <linux/io.h>
#include <linux/sizes.h>
+#include <linux/memblock.h>
#include <asm/cp15.h>
#include <asm/cputype.h>
@@ -284,7 +285,8 @@ static void __iomem * __arm_ioremap_pfn_caller(unsigned long pfn,
* Don't allow RAM to be mapped with mismatched attributes - this
* causes problems with ARMv6+
*/
- if (WARN_ON(pfn_valid(pfn) && mtype != MT_MEMORY_RW))
+ if (WARN_ON(memblock_is_map_memory(PFN_PHYS(pfn)) &&
+ mtype != MT_MEMORY_RW))
return NULL;
area = get_vm_area_caller(size, VM_IOREMAP, caller);
diff --git a/arch/arm/mm/mmu.c b/arch/arm/mm/mmu.c
index c1e12aab67b8..7583bda5ea7d 100644
--- a/arch/arm/mm/mmu.c
+++ b/arch/arm/mm/mmu.c
@@ -1121,31 +1121,32 @@ void __init debug_ll_io_init(void)
}
#endif
-static void * __initdata vmalloc_min =
- (void *)(VMALLOC_END - (240 << 20) - VMALLOC_OFFSET);
+static unsigned long __initdata vmalloc_size = 240 * SZ_1M;
/*
* vmalloc=size forces the vmalloc area to be exactly 'size'
* bytes. This can be used to increase (or decrease) the vmalloc
- * area - the default is 240m.
+ * area - the default is 240MiB.
*/
static int __init early_vmalloc(char *arg)
{
unsigned long vmalloc_reserve = memparse(arg, NULL);
+ unsigned long vmalloc_max;
if (vmalloc_reserve < SZ_16M) {
vmalloc_reserve = SZ_16M;
- pr_warn("vmalloc area too small, limiting to %luMB\n",
+ pr_warn("vmalloc area is too small, limiting to %luMiB\n",
vmalloc_reserve >> 20);
}
- if (vmalloc_reserve > VMALLOC_END - (PAGE_OFFSET + SZ_32M)) {
- vmalloc_reserve = VMALLOC_END - (PAGE_OFFSET + SZ_32M);
- pr_warn("vmalloc area is too big, limiting to %luMB\n",
+ vmalloc_max = VMALLOC_END - (PAGE_OFFSET + SZ_32M + VMALLOC_OFFSET);
+ if (vmalloc_reserve > vmalloc_max) {
+ vmalloc_reserve = vmalloc_max;
+ pr_warn("vmalloc area is too big, limiting to %luMiB\n",
vmalloc_reserve >> 20);
}
- vmalloc_min = (void *)(VMALLOC_END - vmalloc_reserve);
+ vmalloc_size = vmalloc_reserve;
return 0;
}
early_param("vmalloc", early_vmalloc);
@@ -1165,7 +1166,8 @@ void __init adjust_lowmem_bounds(void)
* and may itself be outside the valid range for which phys_addr_t
* and therefore __pa() is defined.
*/
- vmalloc_limit = (u64)(uintptr_t)vmalloc_min - PAGE_OFFSET + PHYS_OFFSET;
+ vmalloc_limit = (u64)VMALLOC_END - vmalloc_size - VMALLOC_OFFSET -
+ PAGE_OFFSET + PHYS_OFFSET;
/*
* The first usable region must be PMD aligned. Mark its start
@@ -1246,7 +1248,7 @@ void __init adjust_lowmem_bounds(void)
memblock_set_current_limit(memblock_limit);
}
-static inline void prepare_page_table(void)
+static __init void prepare_page_table(void)
{
unsigned long addr;
phys_addr_t end;
@@ -1457,8 +1459,6 @@ static void __init kmap_init(void)
static void __init map_lowmem(void)
{
- phys_addr_t kernel_x_start = round_down(__pa(KERNEL_START), SECTION_SIZE);
- phys_addr_t kernel_x_end = round_up(__pa(__init_end), SECTION_SIZE);
phys_addr_t start, end;
u64 i;
@@ -1466,55 +1466,126 @@ static void __init map_lowmem(void)
for_each_mem_range(i, &start, &end) {
struct map_desc map;
+ pr_debug("map lowmem start: 0x%08llx, end: 0x%08llx\n",
+ (long long)start, (long long)end);
if (end > arm_lowmem_limit)
end = arm_lowmem_limit;
if (start >= end)
break;
- if (end < kernel_x_start) {
- map.pfn = __phys_to_pfn(start);
- map.virtual = __phys_to_virt(start);
- map.length = end - start;
- map.type = MT_MEMORY_RWX;
+ /*
+ * If our kernel image is in the VMALLOC area we need to remove
+ * the kernel physical memory from lowmem since the kernel will
+ * be mapped separately.
+ *
+ * The kernel will typically be at the very start of lowmem,
+ * but any placement relative to memory ranges is possible.
+ *
+ * If the memblock contains the kernel, we have to chisel out
+ * the kernel memory from it and map each part separately. We
+ * get 6 different theoretical cases:
+ *
+ * +--------+ +--------+
+ * +-- start --+ +--------+ | Kernel | | Kernel |
+ * | | | Kernel | | case 2 | | case 5 |
+ * | | | case 1 | +--------+ | | +--------+
+ * | Memory | +--------+ | | | Kernel |
+ * | range | +--------+ | | | case 6 |
+ * | | | Kernel | +--------+ | | +--------+
+ * | | | case 3 | | Kernel | | |
+ * +-- end ----+ +--------+ | case 4 | | |
+ * +--------+ +--------+
+ */
- create_mapping(&map);
- } else if (start >= kernel_x_end) {
- map.pfn = __phys_to_pfn(start);
- map.virtual = __phys_to_virt(start);
- map.length = end - start;
- map.type = MT_MEMORY_RW;
+ /* Case 5: kernel covers range, don't map anything, should be rare */
+ if ((start > kernel_sec_start) && (end < kernel_sec_end))
+ break;
- create_mapping(&map);
- } else {
- /* This better cover the entire kernel */
- if (start < kernel_x_start) {
+ /* Cases where the kernel is starting inside the range */
+ if ((kernel_sec_start >= start) && (kernel_sec_start <= end)) {
+ /* Case 6: kernel is embedded in the range, we need two mappings */
+ if ((start < kernel_sec_start) && (end > kernel_sec_end)) {
+ /* Map memory below the kernel */
map.pfn = __phys_to_pfn(start);
map.virtual = __phys_to_virt(start);
- map.length = kernel_x_start - start;
+ map.length = kernel_sec_start - start;
map.type = MT_MEMORY_RW;
-
create_mapping(&map);
- }
-
- map.pfn = __phys_to_pfn(kernel_x_start);
- map.virtual = __phys_to_virt(kernel_x_start);
- map.length = kernel_x_end - kernel_x_start;
- map.type = MT_MEMORY_RWX;
-
- create_mapping(&map);
-
- if (kernel_x_end < end) {
- map.pfn = __phys_to_pfn(kernel_x_end);
- map.virtual = __phys_to_virt(kernel_x_end);
- map.length = end - kernel_x_end;
+ /* Map memory above the kernel */
+ map.pfn = __phys_to_pfn(kernel_sec_end);
+ map.virtual = __phys_to_virt(kernel_sec_end);
+ map.length = end - kernel_sec_end;
map.type = MT_MEMORY_RW;
-
create_mapping(&map);
+ break;
}
+ /* Case 1: kernel and range start at the same address, should be common */
+ if (kernel_sec_start == start)
+ start = kernel_sec_end;
+ /* Case 3: kernel and range end at the same address, should be rare */
+ if (kernel_sec_end == end)
+ end = kernel_sec_start;
+ } else if ((kernel_sec_start < start) && (kernel_sec_end > start) && (kernel_sec_end < end)) {
+ /* Case 2: kernel ends inside range, starts below it */
+ start = kernel_sec_end;
+ } else if ((kernel_sec_start > start) && (kernel_sec_start < end) && (kernel_sec_end > end)) {
+ /* Case 4: kernel starts inside range, ends above it */
+ end = kernel_sec_start;
}
+ map.pfn = __phys_to_pfn(start);
+ map.virtual = __phys_to_virt(start);
+ map.length = end - start;
+ map.type = MT_MEMORY_RW;
+ create_mapping(&map);
}
}
+static void __init map_kernel(void)
+{
+ /*
+ * We use the well known kernel section start and end and split the area in the
+ * middle like this:
+ * . .
+ * | RW memory |
+ * +----------------+ kernel_x_start
+ * | Executable |
+ * | kernel memory |
+ * +----------------+ kernel_x_end / kernel_nx_start
+ * | Non-executable |
+ * | kernel memory |
+ * +----------------+ kernel_nx_end
+ * | RW memory |
+ * . .
+ *
+ * Notice that we are dealing with section sized mappings here so all of this
+ * will be bumped to the closest section boundary. This means that some of the
+ * non-executable part of the kernel memory is actually mapped as executable.
+ * This will only persist until we turn on proper memory management later on
+ * and we remap the whole kernel with page granularity.
+ */
+ phys_addr_t kernel_x_start = kernel_sec_start;
+ phys_addr_t kernel_x_end = round_up(__pa(__init_end), SECTION_SIZE);
+ phys_addr_t kernel_nx_start = kernel_x_end;
+ phys_addr_t kernel_nx_end = kernel_sec_end;
+ struct map_desc map;
+
+ map.pfn = __phys_to_pfn(kernel_x_start);
+ map.virtual = __phys_to_virt(kernel_x_start);
+ map.length = kernel_x_end - kernel_x_start;
+ map.type = MT_MEMORY_RWX;
+ create_mapping(&map);
+
+ /* If the nx part is small it may end up covered by the tail of the RWX section */
+ if (kernel_x_end == kernel_nx_end)
+ return;
+
+ map.pfn = __phys_to_pfn(kernel_nx_start);
+ map.virtual = __phys_to_virt(kernel_nx_start);
+ map.length = kernel_nx_end - kernel_nx_start;
+ map.type = MT_MEMORY_RW;
+ create_mapping(&map);
+}
+
#ifdef CONFIG_ARM_PV_FIXUP
typedef void pgtables_remap(long long offset, unsigned long pgd);
pgtables_remap lpae_pgtables_remap_asm;
@@ -1645,9 +1716,18 @@ void __init paging_init(const struct machine_desc *mdesc)
{
void *zero_page;
+ pr_debug("physical kernel sections: 0x%08x-0x%08x\n",
+ kernel_sec_start, kernel_sec_end);
+
prepare_page_table();
map_lowmem();
memblock_set_current_limit(arm_lowmem_limit);
+ pr_debug("lowmem limit is %08llx\n", (long long)arm_lowmem_limit);
+ /*
+ * After this point early_alloc(), i.e. the memblock allocator, can
+ * be used
+ */
+ map_kernel();
dma_contiguous_remap();
early_fixmap_shutdown();
devicemaps_init(mdesc);
diff --git a/arch/arm/mm/tlb-v6.S b/arch/arm/mm/tlb-v6.S
index 5335b9687297..74f4b383afe3 100644
--- a/arch/arm/mm/tlb-v6.S
+++ b/arch/arm/mm/tlb-v6.S
@@ -24,7 +24,7 @@
*
* - start - start address (may not be aligned)
* - end - end address (exclusive, may not be aligned)
- * - vma - vma_struct describing address range
+ * - vma - vm_area_struct describing address range
*
* It is assumed that:
* - the "Invalidate single entry" instruction will invalidate
diff --git a/arch/arm/mm/tlb-v7.S b/arch/arm/mm/tlb-v7.S
index 1bb28d7db567..87bf4ab17721 100644
--- a/arch/arm/mm/tlb-v7.S
+++ b/arch/arm/mm/tlb-v7.S
@@ -23,7 +23,7 @@
*
* - start - start address (may not be aligned)
* - end - end address (exclusive, may not be aligned)
- * - vma - vma_struct describing address range
+ * - vma - vm_area_struct describing address range
*
* It is assumed that:
* - the "Invalidate single entry" instruction will invalidate
diff --git a/arch/arm/probes/kprobes/core.c b/arch/arm/probes/kprobes/core.c
index a9653117ca0d..27e0af78e88b 100644
--- a/arch/arm/probes/kprobes/core.c
+++ b/arch/arm/probes/kprobes/core.c
@@ -348,29 +348,6 @@ int __kprobes kprobe_fault_handler(struct pt_regs *regs, unsigned int fsr)
reset_current_kprobe();
}
break;
-
- case KPROBE_HIT_ACTIVE:
- case KPROBE_HIT_SSDONE:
- /*
- * We increment the nmissed count for accounting,
- * we can also use npre/npostfault count for accounting
- * these specific fault cases.
- */
- kprobes_inc_nmissed_count(cur);
-
- /*
- * We come here because instructions in the pre/post
- * handler caused the page_fault, this could happen
- * if handler tries to access user space by
- * copy_from_user(), get_user() etc. Let the
- * user-specified handler try to fix it.
- */
- if (cur->fault_handler && cur->fault_handler(cur, regs, fsr))
- return 1;
- break;
-
- default:
- break;
}
return 0;
diff --git a/arch/arm/probes/kprobes/test-thumb.c b/arch/arm/probes/kprobes/test-thumb.c
index 456c181a7bfe..4e11f0b760f8 100644
--- a/arch/arm/probes/kprobes/test-thumb.c
+++ b/arch/arm/probes/kprobes/test-thumb.c
@@ -441,21 +441,21 @@ void kprobe_thumb32_test_cases(void)
"3: mvn r0, r0 \n\t"
"2: nop \n\t")
- TEST_RX("tbh [pc, r",7, (9f-(1f+4))>>1,"]",
+ TEST_RX("tbh [pc, r",7, (9f-(1f+4))>>1,", lsl #1]",
"9: \n\t"
".short (2f-1b-4)>>1 \n\t"
".short (3f-1b-4)>>1 \n\t"
"3: mvn r0, r0 \n\t"
"2: nop \n\t")
- TEST_RX("tbh [pc, r",12, ((9f-(1f+4))>>1)+1,"]",
+ TEST_RX("tbh [pc, r",12, ((9f-(1f+4))>>1)+1,", lsl #1]",
"9: \n\t"
".short (2f-1b-4)>>1 \n\t"
".short (3f-1b-4)>>1 \n\t"
"3: mvn r0, r0 \n\t"
"2: nop \n\t")
- TEST_RRX("tbh [r",1,9f, ", r",14,1,"]",
+ TEST_RRX("tbh [r",1,9f, ", r",14,1,", lsl #1]",
"9: \n\t"
".short (2f-1b-4)>>1 \n\t"
".short (3f-1b-4)>>1 \n\t"
@@ -468,10 +468,10 @@ void kprobe_thumb32_test_cases(void)
TEST_UNSUPPORTED("strexb r0, r1, [r2]")
TEST_UNSUPPORTED("strexh r0, r1, [r2]")
- TEST_UNSUPPORTED("strexd r0, r1, [r2]")
+ TEST_UNSUPPORTED("strexd r0, r1, r2, [r2]")
TEST_UNSUPPORTED("ldrexb r0, [r1]")
TEST_UNSUPPORTED("ldrexh r0, [r1]")
- TEST_UNSUPPORTED("ldrexd r0, [r1]")
+ TEST_UNSUPPORTED("ldrexd r0, r1, [r1]")
TEST_GROUP("Data-processing (shifted register) and (modified immediate)")
diff --git a/arch/arm/tools/Makefile b/arch/arm/tools/Makefile
index 87de1f63f649..4a5c50f67ced 100644
--- a/arch/arm/tools/Makefile
+++ b/arch/arm/tools/Makefile
@@ -33,39 +33,26 @@ _dummy := $(shell [ -d '$(kapi)' ] || mkdir -p '$(kapi)') \
$(shell [ -d '$(uapi)' ] || mkdir -p '$(uapi)')
quiet_cmd_gen_mach = GEN $@
- cmd_gen_mach = mkdir -p $(dir $@) && \
- $(AWK) -f $(filter-out $(PHONY),$^) > $@
+ cmd_gen_mach = $(AWK) -f $(real-prereqs) > $@
$(kapi)/mach-types.h: $(src)/gen-mach-types $(src)/mach-types FORCE
$(call if_changed,gen_mach)
quiet_cmd_syshdr = SYSHDR $@
- cmd_syshdr = $(CONFIG_SHELL) $(syshdr) --abis $(abis) \
+ cmd_syshdr = $(CONFIG_SHELL) $(syshdr) --abis common,$* \
--offset __NR_SYSCALL_BASE $< $@
quiet_cmd_systbl = SYSTBL $@
- cmd_systbl = $(CONFIG_SHELL) $(systbl) --abis $(abis) $< $@
+ cmd_systbl = $(CONFIG_SHELL) $(systbl) --abis common,$* $< $@
quiet_cmd_sysnr = SYSNR $@
- cmd_sysnr = $(CONFIG_SHELL) '$(sysnr)' '$<' '$@' \
- '$(syshdr_abi_$(basetarget))'
+ cmd_sysnr = $(CONFIG_SHELL) $(sysnr) $< $@
-$(uapi)/unistd-oabi.h: abis := common,oabi
-$(uapi)/unistd-oabi.h: $(syscall) $(syshdr) FORCE
+$(uapi)/unistd-%.h: $(syscall) $(syshdr) FORCE
$(call if_changed,syshdr)
-$(uapi)/unistd-eabi.h: abis := common,eabi
-$(uapi)/unistd-eabi.h: $(syscall) $(syshdr) FORCE
- $(call if_changed,syshdr)
-
-sysnr_abi_unistd-nr := common,oabi,eabi,compat
$(kapi)/unistd-nr.h: $(syscall) $(sysnr) FORCE
$(call if_changed,sysnr)
-$(gen)/calls-oabi.S: abis := common,oabi
-$(gen)/calls-oabi.S: $(syscall) $(systbl) FORCE
- $(call if_changed,systbl)
-
-$(gen)/calls-eabi.S: abis := common,eabi
-$(gen)/calls-eabi.S: $(syscall) $(systbl) FORCE
+$(gen)/calls-%.S: $(syscall) $(systbl) FORCE
$(call if_changed,systbl)
diff --git a/arch/arm/tools/syscall.tbl b/arch/arm/tools/syscall.tbl
index 28e03b5fec00..c5df1179fc5d 100644
--- a/arch/arm/tools/syscall.tbl
+++ b/arch/arm/tools/syscall.tbl
@@ -456,7 +456,7 @@
440 common process_madvise sys_process_madvise
441 common epoll_pwait2 sys_epoll_pwait2
442 common mount_setattr sys_mount_setattr
-# 443 reserved for quotactl_path
+443 common quotactl_fd sys_quotactl_fd
444 common landlock_create_ruleset sys_landlock_create_ruleset
445 common landlock_add_rule sys_landlock_add_rule
446 common landlock_restrict_self sys_landlock_restrict_self
diff --git a/arch/arm/tools/syscallnr.sh b/arch/arm/tools/syscallnr.sh
index df3ccd0ca831..9e386770b6b3 100644
--- a/arch/arm/tools/syscallnr.sh
+++ b/arch/arm/tools/syscallnr.sh
@@ -2,14 +2,13 @@
# SPDX-License-Identifier: GPL-2.0
in="$1"
out="$2"
-my_abis=`echo "($3)" | tr ',' '|'`
align=1
fileguard=_ASM_ARM_`basename "$out" | sed \
-e 'y/abcdefghijklmnopqrstuvwxyz/ABCDEFGHIJKLMNOPQRSTUVWXYZ/' \
-e 's/[^A-Z0-9_]/_/g' -e 's/__/_/g'`
-grep -E "^[0-9A-Fa-fXx]+[[:space:]]+${my_abis}" "$in" | sort -n | tail -n1 | (
+grep -E "^[0-9A-Fa-fXx]+[[:space:]]+" "$in" | sort -n | tail -n1 | (
echo "#ifndef ${fileguard}
#define ${fileguard} 1
diff --git a/arch/arm/xen/enlighten.c b/arch/arm/xen/enlighten.c
index 8ad576ecd0f1..7f1c106b746f 100644
--- a/arch/arm/xen/enlighten.c
+++ b/arch/arm/xen/enlighten.c
@@ -29,6 +29,7 @@
#include <linux/cpu.h>
#include <linux/console.h>
#include <linux/pvclock_gtod.h>
+#include <linux/reboot.h>
#include <linux/time64.h>
#include <linux/timekeeping.h>
#include <linux/timekeeper_internal.h>
@@ -181,11 +182,18 @@ void xen_reboot(int reason)
BUG_ON(rc);
}
-static void xen_restart(enum reboot_mode reboot_mode, const char *cmd)
+static int xen_restart(struct notifier_block *nb, unsigned long action,
+ void *data)
{
xen_reboot(SHUTDOWN_reboot);
+
+ return NOTIFY_DONE;
}
+static struct notifier_block xen_restart_nb = {
+ .notifier_call = xen_restart,
+ .priority = 192,
+};
static void xen_power_off(void)
{
@@ -404,7 +412,7 @@ static int __init xen_pm_init(void)
return -ENODEV;
pm_power_off = xen_power_off;
- arm_pm_restart = xen_restart;
+ register_restart_handler(&xen_restart_nb);
if (!xen_initial_domain()) {
struct timespec64 ts;
xen_read_wallclock(&ts);