summaryrefslogtreecommitdiff
path: root/arch/arm
diff options
context:
space:
mode:
Diffstat (limited to 'arch/arm')
-rw-r--r--arch/arm/Kconfig2
-rw-r--r--arch/arm/boot/compressed/efi-header.S160
-rw-r--r--arch/arm/boot/compressed/vmlinux.lds.S30
-rw-r--r--arch/arm/boot/dts/imx6q-evi.dts16
-rw-r--r--arch/arm/boot/dts/imx7ulp-pinfunc.h468
-rw-r--r--arch/arm/boot/dts/ls1021a.dtsi8
-rw-r--r--arch/arm/boot/dts/omap3-n950-n9.dtsi14
-rw-r--r--arch/arm/boot/dts/rk3228-evb.dts34
-rw-r--r--arch/arm/boot/dts/tango4-smp8758.dtsi1
-rw-r--r--arch/arm/configs/imx_v6_v7_defconfig2
-rw-r--r--arch/arm/configs/multi_v7_defconfig1
-rw-r--r--arch/arm/configs/omap2plus_defconfig2
-rw-r--r--arch/arm/configs/sunxi_defconfig2
-rw-r--r--arch/arm/crypto/Kconfig5
-rw-r--r--arch/arm/crypto/aes-ce-glue.c4
-rw-r--r--arch/arm/crypto/aes-cipher-core.S88
-rw-r--r--arch/arm/crypto/aes-neonbs-glue.c5
-rw-r--r--arch/arm/crypto/ghash-ce-core.S234
-rw-r--r--arch/arm/crypto/ghash-ce-glue.c24
-rw-r--r--arch/arm/include/asm/arch_gicv3.h34
-rw-r--r--arch/arm/include/asm/futex.h26
-rw-r--r--arch/arm/include/asm/spinlock.h16
-rw-r--r--arch/arm/include/asm/thread_info.h15
-rw-r--r--arch/arm/include/asm/traps.h7
-rw-r--r--arch/arm/include/asm/uaccess.h2
-rw-r--r--arch/arm/kernel/entry-common.S9
-rw-r--r--arch/arm/kernel/signal.c5
-rw-r--r--arch/arm/mach-hisi/Kconfig1
-rw-r--r--arch/arm/mach-omap2/Makefile2
-rw-r--r--arch/arm/mach-omap2/board-generic.c1
-rw-r--r--arch/arm/mach-omap2/display.c119
-rw-r--r--arch/arm/mach-omap2/display.h1
-rw-r--r--arch/arm/mach-omap2/drm.c53
-rw-r--r--arch/arm/mach-omap2/io.c1
-rw-r--r--arch/arm/mach-pxa/raumfeld.c2
-rw-r--r--arch/arm/mach-tegra/cpuidle-tegra114.c4
-rw-r--r--arch/arm/net/bpf_jit_32.c2448
-rw-r--r--arch/arm/net/bpf_jit_32.h108
38 files changed, 2803 insertions, 1151 deletions
diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig
index 61a0cb15067e..f1b3f1d575d4 100644
--- a/arch/arm/Kconfig
+++ b/arch/arm/Kconfig
@@ -50,7 +50,7 @@ config ARM
select HAVE_ARCH_SECCOMP_FILTER if (AEABI && !OABI_COMPAT)
select HAVE_ARCH_TRACEHOOK
select HAVE_ARM_SMCCC if CPU_V7
- select HAVE_CBPF_JIT
+ select HAVE_EBPF_JIT if !CPU_ENDIAN_BE32
select HAVE_CC_STACKPROTECTOR
select HAVE_CONTEXT_TRACKING
select HAVE_C_RECORDMCOUNT
diff --git a/arch/arm/boot/compressed/efi-header.S b/arch/arm/boot/compressed/efi-header.S
index a17ca8d78656..c94a88ae834d 100644
--- a/arch/arm/boot/compressed/efi-header.S
+++ b/arch/arm/boot/compressed/efi-header.S
@@ -1,5 +1,5 @@
/*
- * Copyright (C) 2013-2015 Linaro Ltd
+ * Copyright (C) 2013-2017 Linaro Ltd
* Authors: Roy Franz <roy.franz@linaro.org>
* Ard Biesheuvel <ard.biesheuvel@linaro.org>
*
@@ -8,6 +8,9 @@
* published by the Free Software Foundation.
*/
+#include <linux/pe.h>
+#include <linux/sizes.h>
+
.macro __nop
#ifdef CONFIG_EFI_STUB
@ This is almost but not quite a NOP, since it does clobber the
@@ -15,7 +18,7 @@
@ PE/COFF expects the magic string "MZ" at offset 0, while the
@ ARM/Linux boot protocol expects an executable instruction
@ there.
- .inst 'M' | ('Z' << 8) | (0x1310 << 16) @ tstne r0, #0x4d000
+ .inst MZ_MAGIC | (0x1310 << 16) @ tstne r0, #0x4d000
#else
AR_CLASS( mov r0, r0 )
M_CLASS( nop.w )
@@ -34,96 +37,97 @@
@ The only 2 fields of the MSDOS header that are used are this
@ PE/COFF offset, and the "MZ" bytes at offset 0x0.
@
- .long pe_header - start @ Offset to the PE header.
+ .long pe_header - start @ Offset to the PE header.
pe_header:
- .ascii "PE\0\0"
+ .long PE_MAGIC
coff_header:
- .short 0x01c2 @ ARM or Thumb
- .short 2 @ nr_sections
- .long 0 @ TimeDateStamp
- .long 0 @ PointerToSymbolTable
- .long 1 @ NumberOfSymbols
- .short section_table - optional_header
- @ SizeOfOptionalHeader
- .short 0x306 @ Characteristics.
- @ IMAGE_FILE_32BIT_MACHINE |
- @ IMAGE_FILE_DEBUG_STRIPPED |
- @ IMAGE_FILE_EXECUTABLE_IMAGE |
- @ IMAGE_FILE_LINE_NUMS_STRIPPED
+ .short IMAGE_FILE_MACHINE_THUMB @ Machine
+ .short section_count @ NumberOfSections
+ .long 0 @ TimeDateStamp
+ .long 0 @ PointerToSymbolTable
+ .long 0 @ NumberOfSymbols
+ .short section_table - optional_header @ SizeOfOptionalHeader
+ .short IMAGE_FILE_32BIT_MACHINE | \
+ IMAGE_FILE_DEBUG_STRIPPED | \
+ IMAGE_FILE_EXECUTABLE_IMAGE | \
+ IMAGE_FILE_LINE_NUMS_STRIPPED @ Characteristics
+
+#define __pecoff_code_size (__pecoff_data_start - __efi_start)
optional_header:
- .short 0x10b @ PE32 format
- .byte 0x02 @ MajorLinkerVersion
- .byte 0x14 @ MinorLinkerVersion
- .long _end - __efi_start @ SizeOfCode
- .long 0 @ SizeOfInitializedData
- .long 0 @ SizeOfUninitializedData
- .long efi_stub_entry - start @ AddressOfEntryPoint
- .long start_offset @ BaseOfCode
- .long 0 @ data
+ .short PE_OPT_MAGIC_PE32 @ PE32 format
+ .byte 0x02 @ MajorLinkerVersion
+ .byte 0x14 @ MinorLinkerVersion
+ .long __pecoff_code_size @ SizeOfCode
+ .long __pecoff_data_size @ SizeOfInitializedData
+ .long 0 @ SizeOfUninitializedData
+ .long efi_stub_entry - start @ AddressOfEntryPoint
+ .long start_offset @ BaseOfCode
+ .long __pecoff_data_start - start @ BaseOfData
extra_header_fields:
- .long 0 @ ImageBase
- .long 0x200 @ SectionAlignment
- .long 0x200 @ FileAlignment
- .short 0 @ MajorOperatingSystemVersion
- .short 0 @ MinorOperatingSystemVersion
- .short 0 @ MajorImageVersion
- .short 0 @ MinorImageVersion
- .short 0 @ MajorSubsystemVersion
- .short 0 @ MinorSubsystemVersion
- .long 0 @ Win32VersionValue
+ .long 0 @ ImageBase
+ .long SZ_4K @ SectionAlignment
+ .long SZ_512 @ FileAlignment
+ .short 0 @ MajorOsVersion
+ .short 0 @ MinorOsVersion
+ .short 0 @ MajorImageVersion
+ .short 0 @ MinorImageVersion
+ .short 0 @ MajorSubsystemVersion
+ .short 0 @ MinorSubsystemVersion
+ .long 0 @ Win32VersionValue
- .long _end - start @ SizeOfImage
- .long start_offset @ SizeOfHeaders
- .long 0 @ CheckSum
- .short 0xa @ Subsystem (EFI application)
- .short 0 @ DllCharacteristics
- .long 0 @ SizeOfStackReserve
- .long 0 @ SizeOfStackCommit
- .long 0 @ SizeOfHeapReserve
- .long 0 @ SizeOfHeapCommit
- .long 0 @ LoaderFlags
- .long 0x6 @ NumberOfRvaAndSizes
+ .long __pecoff_end - start @ SizeOfImage
+ .long start_offset @ SizeOfHeaders
+ .long 0 @ CheckSum
+ .short IMAGE_SUBSYSTEM_EFI_APPLICATION @ Subsystem
+ .short 0 @ DllCharacteristics
+ .long 0 @ SizeOfStackReserve
+ .long 0 @ SizeOfStackCommit
+ .long 0 @ SizeOfHeapReserve
+ .long 0 @ SizeOfHeapCommit
+ .long 0 @ LoaderFlags
+ .long (section_table - .) / 8 @ NumberOfRvaAndSizes
- .quad 0 @ ExportTable
- .quad 0 @ ImportTable
- .quad 0 @ ResourceTable
- .quad 0 @ ExceptionTable
- .quad 0 @ CertificationTable
- .quad 0 @ BaseRelocationTable
+ .quad 0 @ ExportTable
+ .quad 0 @ ImportTable
+ .quad 0 @ ResourceTable
+ .quad 0 @ ExceptionTable
+ .quad 0 @ CertificationTable
+ .quad 0 @ BaseRelocationTable
section_table:
- @
- @ The EFI application loader requires a relocation section
- @ because EFI applications must be relocatable. This is a
- @ dummy section as far as we are concerned.
- @
- .ascii ".reloc\0\0"
- .long 0 @ VirtualSize
- .long 0 @ VirtualAddress
- .long 0 @ SizeOfRawData
- .long 0 @ PointerToRawData
- .long 0 @ PointerToRelocations
- .long 0 @ PointerToLineNumbers
- .short 0 @ NumberOfRelocations
- .short 0 @ NumberOfLineNumbers
- .long 0x42100040 @ Characteristics
-
.ascii ".text\0\0\0"
- .long _end - __efi_start @ VirtualSize
- .long __efi_start @ VirtualAddress
- .long _edata - __efi_start @ SizeOfRawData
- .long __efi_start @ PointerToRawData
- .long 0 @ PointerToRelocations
- .long 0 @ PointerToLineNumbers
- .short 0 @ NumberOfRelocations
- .short 0 @ NumberOfLineNumbers
- .long 0xe0500020 @ Characteristics
+ .long __pecoff_code_size @ VirtualSize
+ .long __efi_start @ VirtualAddress
+ .long __pecoff_code_size @ SizeOfRawData
+ .long __efi_start @ PointerToRawData
+ .long 0 @ PointerToRelocations
+ .long 0 @ PointerToLineNumbers
+ .short 0 @ NumberOfRelocations
+ .short 0 @ NumberOfLineNumbers
+ .long IMAGE_SCN_CNT_CODE | \
+ IMAGE_SCN_MEM_READ | \
+ IMAGE_SCN_MEM_EXECUTE @ Characteristics
+
+ .ascii ".data\0\0\0"
+ .long __pecoff_data_size @ VirtualSize
+ .long __pecoff_data_start - start @ VirtualAddress
+ .long __pecoff_data_rawsize @ SizeOfRawData
+ .long __pecoff_data_start - start @ PointerToRawData
+ .long 0 @ PointerToRelocations
+ .long 0 @ PointerToLineNumbers
+ .short 0 @ NumberOfRelocations
+ .short 0 @ NumberOfLineNumbers
+ .long IMAGE_SCN_CNT_INITIALIZED_DATA | \
+ IMAGE_SCN_MEM_READ | \
+ IMAGE_SCN_MEM_WRITE @ Characteristics
+
+ .set section_count, (. - section_table) / 40
- .align 9
+ .align 12
__efi_start:
#endif
.endm
diff --git a/arch/arm/boot/compressed/vmlinux.lds.S b/arch/arm/boot/compressed/vmlinux.lds.S
index 81c493156ce8..7a4c59154361 100644
--- a/arch/arm/boot/compressed/vmlinux.lds.S
+++ b/arch/arm/boot/compressed/vmlinux.lds.S
@@ -48,13 +48,6 @@ SECTIONS
*(.rodata)
*(.rodata.*)
}
- .data : {
- /*
- * The EFI stub always executes from RAM, and runs strictly before the
- * decompressor, so we can make an exception for its r/w data, and keep it
- */
- *(.data.efistub)
- }
.piggydata : {
*(.piggydata)
}
@@ -70,6 +63,26 @@ SECTIONS
/* ensure the zImage file size is always a multiple of 64 bits */
/* (without a dummy byte, ld just ignores the empty section) */
.pad : { BYTE(0); . = ALIGN(8); }
+
+#ifdef CONFIG_EFI_STUB
+ .data : ALIGN(4096) {
+ __pecoff_data_start = .;
+ /*
+ * The EFI stub always executes from RAM, and runs strictly before the
+ * decompressor, so we can make an exception for its r/w data, and keep it
+ */
+ *(.data.efistub)
+ __pecoff_data_end = .;
+
+ /*
+ * PE/COFF mandates a file size which is a multiple of 512 bytes if the
+ * section size equals or exceeds 4 KB
+ */
+ . = ALIGN(512);
+ }
+ __pecoff_data_rawsize = . - ADDR(.data);
+#endif
+
_edata = .;
_magic_sig = ZIMAGE_MAGIC(0x016f2818);
@@ -84,6 +97,9 @@ SECTIONS
. = ALIGN(8); /* the stack must be 64-bit aligned */
.stack : { *(.stack) }
+ PROVIDE(__pecoff_data_size = ALIGN(512) - ADDR(.data));
+ PROVIDE(__pecoff_end = ALIGN(512));
+
.stab 0 : { *(.stab) }
.stabstr 0 : { *(.stabstr) }
.stab.excl 0 : { *(.stab.excl) }
diff --git a/arch/arm/boot/dts/imx6q-evi.dts b/arch/arm/boot/dts/imx6q-evi.dts
index 1f0f950dc11e..e0aea782c666 100644
--- a/arch/arm/boot/dts/imx6q-evi.dts
+++ b/arch/arm/boot/dts/imx6q-evi.dts
@@ -94,6 +94,15 @@
pinctrl-names = "default";
pinctrl-0 = <&pinctrl_ecspi1 &pinctrl_ecspi1cs>;
status = "okay";
+
+ fpga: fpga@0 {
+ compatible = "altr,fpga-passive-serial";
+ spi-max-frequency = <20000000>;
+ reg = <0>;
+ pinctrl-0 = <&pinctrl_fpgaspi>;
+ nconfig-gpios = <&gpio4 9 GPIO_ACTIVE_LOW>;
+ nstat-gpios = <&gpio4 11 GPIO_ACTIVE_LOW>;
+ };
};
&ecspi3 {
@@ -319,6 +328,13 @@
>;
};
+ pinctrl_fpgaspi: fpgaspigrp {
+ fsl,pins = <
+ MX6QDL_PAD_KEY_ROW1__GPIO4_IO09 0x1b0b0
+ MX6QDL_PAD_KEY_ROW2__GPIO4_IO11 0x1b0b0
+ >;
+ };
+
pinctrl_gpminand: gpminandgrp {
fsl,pins = <
MX6QDL_PAD_NANDF_CLE__NAND_CLE 0xb0b1
diff --git a/arch/arm/boot/dts/imx7ulp-pinfunc.h b/arch/arm/boot/dts/imx7ulp-pinfunc.h
new file mode 100644
index 000000000000..fe511775b518
--- /dev/null
+++ b/arch/arm/boot/dts/imx7ulp-pinfunc.h
@@ -0,0 +1,468 @@
+/*
+ * Copyright 2016 Freescale Semiconductor, Inc.
+ * Copyright 2017 NXP
+ *
+ * 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.
+ *
+ */
+
+#ifndef __DTS_IMX7ULP_PINFUNC_H
+#define __DTS_IMX7ULP_PINFUNC_H
+
+/*
+ * The pin function ID is a tuple of
+ * <mux_conf_reg input_reg mux_mode input_val>
+ */
+
+#define IMX7ULP_PAD_PTC0__PTC0 0x0000 0x0000 0x1 0x0
+#define IMX7ULP_PAD_PTC0__TRACE_D15 0x0000 0x0000 0xa 0x0
+#define IMX7ULP_PAD_PTC0__LPUART4_CTS_B 0x0000 0x0244 0x4 0x1
+#define IMX7ULP_PAD_PTC0__LPI2C4_SCL 0x0000 0x0278 0x5 0x1
+#define IMX7ULP_PAD_PTC0__TPM4_CLKIN 0x0000 0x0298 0x6 0x1
+#define IMX7ULP_PAD_PTC0__FB_AD0 0x0000 0x0000 0x9 0x0
+#define IMX7ULP_PAD_PTC1__PTC1 0x0004 0x0000 0x1 0x0
+#define IMX7ULP_PAD_PTC1__TRACE_D14 0x0004 0x0000 0xa 0x0
+#define IMX7ULP_PAD_PTC1__LPUART4_RTS_B 0x0004 0x0000 0x4 0x0
+#define IMX7ULP_PAD_PTC1__LPI2C4_SDA 0x0004 0x027c 0x5 0x1
+#define IMX7ULP_PAD_PTC1__TPM4_CH0 0x0004 0x0280 0x6 0x1
+#define IMX7ULP_PAD_PTC1__FB_AD1 0x0004 0x0000 0x9 0x0
+#define IMX7ULP_PAD_PTC2__PTC2 0x0008 0x0000 0x1 0x0
+#define IMX7ULP_PAD_PTC2__TRACE_D13 0x0008 0x0000 0xa 0x0
+#define IMX7ULP_PAD_PTC2__LPUART4_TX 0x0008 0x024c 0x4 0x1
+#define IMX7ULP_PAD_PTC2__LPI2C4_HREQ 0x0008 0x0274 0x5 0x1
+#define IMX7ULP_PAD_PTC2__TPM4_CH1 0x0008 0x0284 0x6 0x1
+#define IMX7ULP_PAD_PTC2__FB_AD2 0x0008 0x0000 0x9 0x0
+#define IMX7ULP_PAD_PTC3__PTC3 0x000c 0x0000 0x1 0x0
+#define IMX7ULP_PAD_PTC3__TRACE_D12 0x000c 0x0000 0xa 0x0
+#define IMX7ULP_PAD_PTC3__LPUART4_RX 0x000c 0x0248 0x4 0x1
+#define IMX7ULP_PAD_PTC3__TPM4_CH2 0x000c 0x0288 0x6 0x1
+#define IMX7ULP_PAD_PTC3__FB_AD3 0x000c 0x0000 0x9 0x0
+#define IMX7ULP_PAD_PTC4__PTC4 0x0010 0x0000 0x1 0x0
+#define IMX7ULP_PAD_PTC4__TRACE_D11 0x0010 0x0000 0xa 0x0
+#define IMX7ULP_PAD_PTC4__FXIO1_D0 0x0010 0x0204 0x2 0x1
+#define IMX7ULP_PAD_PTC4__LPSPI2_PCS1 0x0010 0x02a0 0x3 0x1
+#define IMX7ULP_PAD_PTC4__LPUART5_CTS_B 0x0010 0x0250 0x4 0x1
+#define IMX7ULP_PAD_PTC4__LPI2C5_SCL 0x0010 0x02bc 0x5 0x1
+#define IMX7ULP_PAD_PTC4__TPM4_CH3 0x0010 0x028c 0x6 0x1
+#define IMX7ULP_PAD_PTC4__FB_AD4 0x0010 0x0000 0x9 0x0
+#define IMX7ULP_PAD_PTC5__PTC5 0x0014 0x0000 0x1 0x0
+#define IMX7ULP_PAD_PTC5__TRACE_D10 0x0014 0x0000 0xa 0x0
+#define IMX7ULP_PAD_PTC5__FXIO1_D1 0x0014 0x0208 0x2 0x1
+#define IMX7ULP_PAD_PTC5__LPSPI2_PCS2 0x0014 0x02a4 0x3 0x1
+#define IMX7ULP_PAD_PTC5__LPUART5_RTS_B 0x0014 0x0000 0x4 0x0
+#define IMX7ULP_PAD_PTC5__LPI2C5_SDA 0x0014 0x02c0 0x5 0x1
+#define IMX7ULP_PAD_PTC5__TPM4_CH4 0x0014 0x0290 0x6 0x1
+#define IMX7ULP_PAD_PTC5__FB_AD5 0x0014 0x0000 0x9 0x0
+#define IMX7ULP_PAD_PTC6__PTC6 0x0018 0x0000 0x1 0x0
+#define IMX7ULP_PAD_PTC6__TRACE_D9 0x0018 0x0000 0xa 0x0
+#define IMX7ULP_PAD_PTC6__FXIO1_D2 0x0018 0x020c 0x2 0x1
+#define IMX7ULP_PAD_PTC6__LPSPI2_PCS3 0x0018 0x02a8 0x3 0x1
+#define IMX7ULP_PAD_PTC6__LPUART5_TX 0x0018 0x0258 0x4 0x1
+#define IMX7ULP_PAD_PTC6__LPI2C5_HREQ 0x0018 0x02b8 0x5 0x1
+#define IMX7ULP_PAD_PTC6__TPM4_CH5 0x0018 0x0294 0x6 0x1
+#define IMX7ULP_PAD_PTC6__FB_AD6 0x0018 0x0000 0x9 0x0
+#define IMX7ULP_PAD_PTC7__PTC7 0x001c 0x0000 0x1 0x0
+#define IMX7ULP_PAD_PTC7__TRACE_D8 0x001c 0x0000 0xa 0x0
+#define IMX7ULP_PAD_PTC7__FXIO1_D3 0x001c 0x0210 0x2 0x1
+#define IMX7ULP_PAD_PTC7__LPUART5_RX 0x001c 0x0254 0x4 0x1
+#define IMX7ULP_PAD_PTC7__TPM5_CH1 0x001c 0x02c8 0x6 0x1
+#define IMX7ULP_PAD_PTC7__FB_AD7 0x001c 0x0000 0x9 0x0
+#define IMX7ULP_PAD_PTC8__PTC8 0x0020 0x0000 0x1 0x0
+#define IMX7ULP_PAD_PTC8__TRACE_D7 0x0020 0x0000 0xa 0x0
+#define IMX7ULP_PAD_PTC8__FXIO1_D4 0x0020 0x0214 0x2 0x1
+#define IMX7ULP_PAD_PTC8__LPSPI2_SIN 0x0020 0x02b0 0x3 0x1
+#define IMX7ULP_PAD_PTC8__LPUART6_CTS_B 0x0020 0x025c 0x4 0x1
+#define IMX7ULP_PAD_PTC8__LPI2C6_SCL 0x0020 0x02fc 0x5 0x1
+#define IMX7ULP_PAD_PTC8__TPM5_CLKIN 0x0020 0x02cc 0x6 0x1
+#define IMX7ULP_PAD_PTC8__FB_AD8 0x0020 0x0000 0x9 0x0
+#define IMX7ULP_PAD_PTC9__PTC9 0x0024 0x0000 0x1 0x0
+#define IMX7ULP_PAD_PTC9__TRACE_D6 0x0024 0x0000 0xa 0x0
+#define IMX7ULP_PAD_PTC9__FXIO1_D5 0x0024 0x0218 0x2 0x1
+#define IMX7ULP_PAD_PTC9__LPSPI2_SOUT 0x0024 0x02b4 0x3 0x1
+#define IMX7ULP_PAD_PTC9__LPUART6_RTS_B 0x0024 0x0000 0x4 0x0
+#define IMX7ULP_PAD_PTC9__LPI2C6_SDA 0x0024 0x0300 0x5 0x1
+#define IMX7ULP_PAD_PTC9__TPM5_CH0 0x0024 0x02c4 0x6 0x1
+#define IMX7ULP_PAD_PTC9__FB_AD9 0x0024 0x0000 0x9 0x0
+#define IMX7ULP_PAD_PTC10__PTC10 0x0028 0x0000 0x1 0x0
+#define IMX7ULP_PAD_PTC10__TRACE_D5 0x0028 0x0000 0xa 0x0
+#define IMX7ULP_PAD_PTC10__FXIO1_D6 0x0028 0x021c 0x2 0x1
+#define IMX7ULP_PAD_PTC10__LPSPI2_SCK 0x0028 0x02ac 0x3 0x1
+#define IMX7ULP_PAD_PTC10__LPUART6_TX 0x0028 0x0264 0x4 0x1
+#define IMX7ULP_PAD_PTC10__LPI2C6_HREQ 0x0028 0x02f8 0x5 0x1
+#define IMX7ULP_PAD_PTC10__TPM7_CH3 0x0028 0x02e8 0x6 0x1
+#define IMX7ULP_PAD_PTC10__FB_AD10 0x0028 0x0000 0x9 0x0
+#define IMX7ULP_PAD_PTC11__PTC11 0x002c 0x0000 0x1 0x0
+#define IMX7ULP_PAD_PTC11__TRACE_D4 0x002c 0x0000 0xa 0x0
+#define IMX7ULP_PAD_PTC11__FXIO1_D7 0x002c 0x0220 0x2 0x1
+#define IMX7ULP_PAD_PTC11__LPSPI2_PCS0 0x002c 0x029c 0x3 0x1
+#define IMX7ULP_PAD_PTC11__LPUART6_RX 0x002c 0x0260 0x4 0x1
+#define IMX7ULP_PAD_PTC11__TPM7_CH4 0x002c 0x02ec 0x6 0x1
+#define IMX7ULP_PAD_PTC11__FB_AD11 0x002c 0x0000 0x9 0x0
+#define IMX7ULP_PAD_PTC12__PTC12 0x0030 0x0000 0x1 0x0
+#define IMX7ULP_PAD_PTC12__TRACE_D3 0x0030 0x0000 0xa 0x0
+#define IMX7ULP_PAD_PTC12__FXIO1_D8 0x0030 0x0224 0x2 0x1
+#define IMX7ULP_PAD_PTC12__LPSPI3_PCS1 0x0030 0x0314 0x3 0x1
+#define IMX7ULP_PAD_PTC12__LPUART7_CTS_B 0x0030 0x0268 0x4 0x1
+#define IMX7ULP_PAD_PTC12__LPI2C7_SCL 0x0030 0x0308 0x5 0x1
+#define IMX7ULP_PAD_PTC12__TPM7_CH5 0x0030 0x02f0 0x6 0x1
+#define IMX7ULP_PAD_PTC12__FB_AD12 0x0030 0x0000 0x9 0x0
+#define IMX7ULP_PAD_PTC13__PTC13 0x0034 0x0000 0x1 0x0
+#define IMX7ULP_PAD_PTC13__TRACE_D2 0x0034 0x0000 0xa 0x0
+#define IMX7ULP_PAD_PTC13__FXIO1_D9 0x0034 0x0228 0x2 0x1
+#define IMX7ULP_PAD_PTC13__LPSPI3_PCS2 0x0034 0x0318 0x3 0x1
+#define IMX7ULP_PAD_PTC13__LPUART7_RTS_B 0x0034 0x0000 0x4 0x0
+#define IMX7ULP_PAD_PTC13__LPI2C7_SDA 0x0034 0x030c 0x5 0x1
+#define IMX7ULP_PAD_PTC13__TPM7_CLKIN 0x0034 0x02f4 0x6 0x1
+#define IMX7ULP_PAD_PTC13__FB_AD13 0x0034 0x0000 0x9 0x0
+#define IMX7ULP_PAD_PTC14__PTC14 0x0038 0x0000 0x1 0x0
+#define IMX7ULP_PAD_PTC14__TRACE_D1 0x0038 0x0000 0xa 0x0
+#define IMX7ULP_PAD_PTC14__FXIO1_D10 0x0038 0x022c 0x2 0x1
+#define IMX7ULP_PAD_PTC14__LPSPI3_PCS3 0x0038 0x031c 0x3 0x1
+#define IMX7ULP_PAD_PTC14__LPUART7_TX 0x0038 0x0270 0x4 0x1
+#define IMX7ULP_PAD_PTC14__LPI2C7_HREQ 0x0038 0x0304 0x5 0x1
+#define IMX7ULP_PAD_PTC14__TPM7_CH0 0x0038 0x02dc 0x6 0x1
+#define IMX7ULP_PAD_PTC14__FB_AD14 0x0038 0x0000 0x9 0x0
+#define IMX7ULP_PAD_PTC15__PTC15 0x003c 0x0000 0x1 0x0
+#define IMX7ULP_PAD_PTC15__TRACE_D0 0x003c 0x0000 0xa 0x0
+#define IMX7ULP_PAD_PTC15__FXIO1_D11 0x003c 0x0230 0x2 0x1
+#define IMX7ULP_PAD_PTC15__LPUART7_RX 0x003c 0x026c 0x4 0x1
+#define IMX7ULP_PAD_PTC15__TPM7_CH1 0x003c 0x02e0 0x6 0x1
+#define IMX7ULP_PAD_PTC15__FB_AD15 0x003c 0x0000 0x9 0x0
+#define IMX7ULP_PAD_PTC16__PTC16 0x0040 0x0000 0x1 0x0
+#define IMX7ULP_PAD_PTC16__TRACE_CLKOUT 0x0040 0x0000 0xa 0x0
+#define IMX7ULP_PAD_PTC16__FXIO1_D12 0x0040 0x0234 0x2 0x1
+#define IMX7ULP_PAD_PTC16__LPSPI3_SIN 0x0040 0x0324 0x3 0x1
+#define IMX7ULP_PAD_PTC16__TPM7_CH2 0x0040 0x02e4 0x6 0x1
+#define IMX7ULP_PAD_PTC16__FB_ALE_FB_CS1_B_FB_TS_B 0x0040 0x0000 0x9 0x0
+#define IMX7ULP_PAD_PTC17__PTC17 0x0044 0x0000 0x1 0x0
+#define IMX7ULP_PAD_PTC17__FXIO1_D13 0x0044 0x0238 0x2 0x1
+#define IMX7ULP_PAD_PTC17__LPSPI3_SOUT 0x0044 0x0328 0x3 0x1
+#define IMX7ULP_PAD_PTC17__TPM6_CLKIN 0x0044 0x02d8 0x6 0x1
+#define IMX7ULP_PAD_PTC17__FB_CS0_B 0x0044 0x0000 0x9 0x0
+#define IMX7ULP_PAD_PTC18__PTC18 0x0048 0x0000 0x1 0x0
+#define IMX7ULP_PAD_PTC18__FXIO1_D14 0x0048 0x023c 0x2 0x1
+#define IMX7ULP_PAD_PTC18__LPSPI3_SCK 0x0048 0x0320 0x3 0x1
+#define IMX7ULP_PAD_PTC18__TPM6_CH0 0x0048 0x02d0 0x6 0x1
+#define IMX7ULP_PAD_PTC18__FB_OE_B 0x0048 0x0000 0x9 0x0
+#define IMX7ULP_PAD_PTC19__PTC19 0x004c 0x0000 0x1 0x0
+#define IMX7ULP_PAD_PTC19__FXIO1_D15 0x004c 0x0240 0x2 0x1
+#define IMX7ULP_PAD_PTC19__LPSPI3_PCS0 0x004c 0x0310 0x3 0x1
+#define IMX7ULP_PAD_PTC19__TPM6_CH1 0x004c 0x02d4 0x6 0x1
+#define IMX7ULP_PAD_PTC19__FB_A16 0x004c 0x0000 0x9 0x0
+#define IMX7ULP_PAD_PTD0__PTD0 0x0080 0x0000 0x1 0x0
+#define IMX7ULP_PAD_PTD0__SDHC0_RESET_B 0x0080 0x0000 0x8 0x0
+#define IMX7ULP_PAD_PTD1__PTD1 0x0084 0x0000 0x1 0x0
+#define IMX7ULP_PAD_PTD1__SDHC0_CMD 0x0084 0x0000 0x8 0x0
+#define IMX7ULP_PAD_PTD2__PTD2 0x0088 0x0000 0x1 0x0
+#define IMX7ULP_PAD_PTD2__SDHC0_CLK 0x0088 0x0000 0x8 0x0
+#define IMX7ULP_PAD_PTD3__PTD3 0x008c 0x0000 0x1 0x0
+#define IMX7ULP_PAD_PTD3__SDHC0_D7 0x008c 0x0000 0x8 0x0
+#define IMX7ULP_PAD_PTD4__PTD4 0x0090 0x0000 0x1 0x0
+#define IMX7ULP_PAD_PTD4__SDHC0_D6 0x0090 0x0000 0x8 0x0
+#define IMX7ULP_PAD_PTD5__PTD5 0x0094 0x0000 0x1 0x0
+#define IMX7ULP_PAD_PTD5__SDHC0_D5 0x0094 0x0000 0x8 0x0
+#define IMX7ULP_PAD_PTD6__PTD6 0x0098 0x0000 0x1 0x0
+#define IMX7ULP_PAD_PTD6__SDHC0_D4 0x0098 0x0000 0x8 0x0
+#define IMX7ULP_PAD_PTD7__PTD7 0x009c 0x0000 0x1 0x0
+#define IMX7ULP_PAD_PTD7__SDHC0_D3 0x009c 0x0000 0x8 0x0
+#define IMX7ULP_PAD_PTD8__PTD8 0x00a0 0x0000 0x1 0x0
+#define IMX7ULP_PAD_PTD8__TPM4_CLKIN 0x00a0 0x0298 0x6 0x2
+#define IMX7ULP_PAD_PTD8__SDHC0_D2 0x00a0 0x0000 0x8 0x0
+#define IMX7ULP_PAD_PTD9__PTD9 0x00a4 0x0000 0x1 0x0
+#define IMX7ULP_PAD_PTD9__TPM4_CH0 0x00a4 0x0280 0x6 0x2
+#define IMX7ULP_PAD_PTD9__SDHC0_D1 0x00a4 0x0000 0x8 0x0
+#define IMX7ULP_PAD_PTD10__PTD10 0x00a8 0x0000 0x1 0x0
+#define IMX7ULP_PAD_PTD10__TPM4_CH1 0x00a8 0x0284 0x6 0x2
+#define IMX7ULP_PAD_PTD10__SDHC0_D0 0x00a8 0x0000 0x8 0x0
+#define IMX7ULP_PAD_PTD11__PTD11 0x00ac 0x0000 0x1 0x0
+#define IMX7ULP_PAD_PTD11__TPM4_CH2 0x00ac 0x0288 0x6 0x2
+#define IMX7ULP_PAD_PTD11__SDHC0_DQS 0x00ac 0x0000 0x8 0x0
+#define IMX7ULP_PAD_PTE0__PTE0 0x0100 0x0000 0x1 0x0
+#define IMX7ULP_PAD_PTE0__FXIO1_D31 0x0100 0x0000 0x2 0x0
+#define IMX7ULP_PAD_PTE0__LPSPI2_PCS1 0x0100 0x02a0 0x3 0x2
+#define IMX7ULP_PAD_PTE0__LPUART4_CTS_B 0x0100 0x0244 0x4 0x2
+#define IMX7ULP_PAD_PTE0__LPI2C4_SCL 0x0100 0x0278 0x5 0x2
+#define IMX7ULP_PAD_PTE0__SDHC1_D1 0x0100 0x0000 0x8 0x0
+#define IMX7ULP_PAD_PTE0__FB_A25 0x0100 0x0000 0x9 0x0
+#define IMX7ULP_PAD_PTE1__PTE1 0x0104 0x0000 0x1 0x0
+#define IMX7ULP_PAD_PTE1__FXIO1_D30 0x0104 0x0000 0x2 0x0
+#define IMX7ULP_PAD_PTE1__LPSPI2_PCS2 0x0104 0x02a4 0x3 0x2
+#define IMX7ULP_PAD_PTE1__LPUART4_RTS_B 0x0104 0x0000 0x4 0x0
+#define IMX7ULP_PAD_PTE1__LPI2C4_SDA 0x0104 0x027c 0x5 0x2
+#define IMX7ULP_PAD_PTE1__SDHC1_D0 0x0104 0x0000 0x8 0x0
+#define IMX7ULP_PAD_PTE1__FB_A26 0x0104 0x0000 0x9 0x0
+#define IMX7ULP_PAD_PTE2__PTE2 0x0108 0x0000 0x1 0x0
+#define IMX7ULP_PAD_PTE2__FXIO1_D29 0x0108 0x0000 0x2 0x0
+#define IMX7ULP_PAD_PTE2__LPSPI2_PCS3 0x0108 0x02a8 0x3 0x2
+#define IMX7ULP_PAD_PTE2__LPUART4_TX 0x0108 0x024c 0x4 0x2
+#define IMX7ULP_PAD_PTE2__LPI2C4_HREQ 0x0108 0x0274 0x5 0x2
+#define IMX7ULP_PAD_PTE2__SDHC1_CLK 0x0108 0x0000 0x8 0x0
+#define IMX7ULP_PAD_PTE3__PTE3 0x010c 0x0000 0x1 0x0
+#define IMX7ULP_PAD_PTE3__FXIO1_D28 0x010c 0x0000 0x2 0x0
+#define IMX7ULP_PAD_PTE3__LPUART4_RX 0x010c 0x0248 0x4 0x2
+#define IMX7ULP_PAD_PTE3__TPM5_CH1 0x010c 0x02c8 0x6 0x2
+#define IMX7ULP_PAD_PTE3__SDHC1_CMD 0x010c 0x0000 0x8 0x0
+#define IMX7ULP_PAD_PTE4__PTE4 0x0110 0x0000 0x1 0x0
+#define IMX7ULP_PAD_PTE4__FXIO1_D27 0x0110 0x0000 0x2 0x0
+#define IMX7ULP_PAD_PTE4__LPSPI2_SIN 0x0110 0x02b0 0x3 0x2
+#define IMX7ULP_PAD_PTE4__LPUART5_CTS_B 0x0110 0x0250 0x4 0x2
+#define IMX7ULP_PAD_PTE4__LPI2C5_SCL 0x0110 0x02bc 0x5 0x2
+#define IMX7ULP_PAD_PTE4__TPM5_CLKIN 0x0110 0x02cc 0x6 0x2
+#define IMX7ULP_PAD_PTE4__SDHC1_D3 0x0110 0x0000 0x8 0x0
+#define IMX7ULP_PAD_PTE5__PTE5 0x0114 0x0000 0x1 0x0
+#define IMX7ULP_PAD_PTE5__FXIO1_D26 0x0114 0x0000 0x2 0x0
+#define IMX7ULP_PAD_PTE5__LPSPI2_SOUT 0x0114 0x02b4 0x3 0x2
+#define IMX7ULP_PAD_PTE5__LPUART5_RTS_B 0x0114 0x0000 0x4 0x0
+#define IMX7ULP_PAD_PTE5__LPI2C5_SDA 0x0114 0x02c0 0x5 0x2
+#define IMX7ULP_PAD_PTE5__TPM5_CH0 0x0114 0x02c4 0x6 0x2
+#define IMX7ULP_PAD_PTE5__SDHC1_D2 0x0114 0x0000 0x8 0x0
+#define IMX7ULP_PAD_PTE6__PTE6 0x0118 0x0000 0x1 0x0
+#define IMX7ULP_PAD_PTE6__FXIO1_D25 0x0118 0x0000 0x2 0x0
+#define IMX7ULP_PAD_PTE6__LPSPI2_SCK 0x0118 0x02ac 0x3 0x2
+#define IMX7ULP_PAD_PTE6__LPUART5_TX 0x0118 0x0258 0x4 0x2
+#define IMX7ULP_PAD_PTE6__LPI2C5_HREQ 0x0118 0x02b8 0x5 0x2
+#define IMX7ULP_PAD_PTE6__TPM7_CH3 0x0118 0x02e8 0x6 0x2
+#define IMX7ULP_PAD_PTE6__SDHC1_D4 0x0118 0x0000 0x8 0x0
+#define IMX7ULP_PAD_PTE6__FB_A17 0x0118 0x0000 0x9 0x0
+#define IMX7ULP_PAD_PTE7__PTE7 0x011c 0x0000 0x1 0x0
+#define IMX7ULP_PAD_PTE7__TRACE_D7 0x011c 0x0000 0xa 0x0
+#define IMX7ULP_PAD_PTE7__VIU_FID 0x011c 0x0000 0xc 0x0
+#define IMX7ULP_PAD_PTE7__FXIO1_D24 0x011c 0x0000 0x2 0x0
+#define IMX7ULP_PAD_PTE7__LPSPI2_PCS0 0x011c 0x029c 0x3 0x2
+#define IMX7ULP_PAD_PTE7__LPUART5_RX 0x011c 0x0254 0x4 0x2
+#define IMX7ULP_PAD_PTE7__TPM7_CH4 0x011c 0x02ec 0x6 0x2
+#define IMX7ULP_PAD_PTE7__SDHC1_D5 0x011c 0x0000 0x8 0x0
+#define IMX7ULP_PAD_PTE7__FB_A18 0x011c 0x0000 0x9 0x0
+#define IMX7ULP_PAD_PTE8__PTE8 0x0120 0x0000 0x1 0x0
+#define IMX7ULP_PAD_PTE8__TRACE_D6 0x0120 0x0000 0xa 0x0
+#define IMX7ULP_PAD_PTE8__VIU_D16 0x0120 0x0000 0xc 0x0
+#define IMX7ULP_PAD_PTE8__FXIO1_D23 0x0120 0x0000 0x2 0x0
+#define IMX7ULP_PAD_PTE8__LPSPI3_PCS1 0x0120 0x0314 0x3 0x2
+#define IMX7ULP_PAD_PTE8__LPUART6_CTS_B 0x0120 0x025c 0x4 0x2
+#define IMX7ULP_PAD_PTE8__LPI2C6_SCL 0x0120 0x02fc 0x5 0x2
+#define IMX7ULP_PAD_PTE8__TPM7_CH5 0x0120 0x02f0 0x6 0x2
+#define IMX7ULP_PAD_PTE8__SDHC1_WP 0x0120 0x0200 0x7 0x1
+#define IMX7ULP_PAD_PTE8__SDHC1_D6 0x0120 0x0000 0x8 0x0
+#define IMX7ULP_PAD_PTE8__FB_CS3_B_FB_BE7_0_BLS31_24_B 0x0120 0x0000 0x9 0x0
+#define IMX7ULP_PAD_PTE9__PTE9 0x0124 0x0000 0x1 0x0
+#define IMX7ULP_PAD_PTE9__TRACE_D5 0x0124 0x0000 0xa 0x0
+#define IMX7ULP_PAD_PTE9__VIU_D17 0x0124 0x0000 0xc 0x0
+#define IMX7ULP_PAD_PTE9__FXIO1_D22 0x0124 0x0000 0x2 0x0
+#define IMX7ULP_PAD_PTE9__LPSPI3_PCS2 0x0124 0x0318 0x3 0x2
+#define IMX7ULP_PAD_PTE9__LPUART6_RTS_B 0x0124 0x0000 0x4 0x0
+#define IMX7ULP_PAD_PTE9__LPI2C6_SDA 0x0124 0x0300 0x5 0x2
+#define IMX7ULP_PAD_PTE9__TPM7_CLKIN 0x0124 0x02f4 0x6 0x2
+#define IMX7ULP_PAD_PTE9__SDHC1_CD 0x0124 0x032c 0x7 0x1
+#define IMX7ULP_PAD_PTE9__SDHC1_D7 0x0124 0x0000 0x8 0x0
+#define IMX7ULP_PAD_PTE9__FB_TBST_B_FB_CS2_B_FB_BE15_8_BLS23_16_B 0x0124 0x0000 0x9 0x0
+#define IMX7ULP_PAD_PTE10__PTE10 0x0128 0x0000 0x1 0x0
+#define IMX7ULP_PAD_PTE10__TRACE_D4 0x0128 0x0000 0xa 0x0
+#define IMX7ULP_PAD_PTE10__VIU_D18 0x0128 0x0000 0xc 0x0
+#define IMX7ULP_PAD_PTE10__FXIO1_D21 0x0128 0x0000 0x2 0x0
+#define IMX7ULP_PAD_PTE10__LPSPI3_PCS3 0x0128 0x031c 0x3 0x2
+#define IMX7ULP_PAD_PTE10__LPUART6_TX 0x0128 0x0264 0x4 0x2
+#define IMX7ULP_PAD_PTE10__LPI2C6_HREQ 0x0128 0x02f8 0x5 0x2
+#define IMX7ULP_PAD_PTE10__TPM7_CH0 0x0128 0x02dc 0x6 0x2
+#define IMX7ULP_PAD_PTE10__SDHC1_VS 0x0128 0x0000 0x7 0x0
+#define IMX7ULP_PAD_PTE10__SDHC1_DQS 0x0128 0x0000 0x8 0x0
+#define IMX7ULP_PAD_PTE10__FB_A19 0x0128 0x0000 0x9 0x0
+#define IMX7ULP_PAD_PTE11__PTE11 0x012c 0x0000 0x1 0x0
+#define IMX7ULP_PAD_PTE11__TRACE_D3 0x012c 0x0000 0xa 0x0
+#define IMX7ULP_PAD_PTE11__VIU_D19 0x012c 0x0000 0xc 0x0
+#define IMX7ULP_PAD_PTE11__FXIO1_D20 0x012c 0x0000 0x2 0x0
+#define IMX7ULP_PAD_PTE11__LPUART6_RX 0x012c 0x0260 0x4 0x2
+#define IMX7ULP_PAD_PTE11__TPM7_CH1 0x012c 0x02e0 0x6 0x2
+#define IMX7ULP_PAD_PTE11__SDHC1_RESET_B 0x012c 0x0000 0x8 0x0
+#define IMX7ULP_PAD_PTE11__FB_A20 0x012c 0x0000 0x9 0x0
+#define IMX7ULP_PAD_PTE12__PTE12 0x0130 0x0000 0x1 0x0
+#define IMX7ULP_PAD_PTE12__TRACE_D2 0x0130 0x0000 0xa 0x0
+#define IMX7ULP_PAD_PTE12__VIU_D20 0x0130 0x0000 0xc 0x0
+#define IMX7ULP_PAD_PTE12__FXIO1_D19 0x0130 0x0000 0x2 0x0
+#define IMX7ULP_PAD_PTE12__LPSPI3_SIN 0x0130 0x0324 0x3 0x2
+#define IMX7ULP_PAD_PTE12__LPUART7_CTS_B 0x0130 0x0268 0x4 0x2
+#define IMX7ULP_PAD_PTE12__LPI2C7_SCL 0x0130 0x0308 0x5 0x2
+#define IMX7ULP_PAD_PTE12__TPM7_CH2 0x0130 0x02e4 0x6 0x2
+#define IMX7ULP_PAD_PTE12__SDHC1_WP 0x0130 0x0200 0x8 0x2
+#define IMX7ULP_PAD_PTE12__FB_A21 0x0130 0x0000 0x9 0x0
+#define IMX7ULP_PAD_PTE13__PTE13 0x0134 0x0000 0x1 0x0
+#define IMX7ULP_PAD_PTE13__TRACE_D1 0x0134 0x0000 0xa 0x0
+#define IMX7ULP_PAD_PTE13__VIU_D21 0x0134 0x0000 0xc 0x0
+#define IMX7ULP_PAD_PTE13__FXIO1_D18 0x0134 0x0000 0x2 0x0
+#define IMX7ULP_PAD_PTE13__LPSPI3_SOUT 0x0134 0x0328 0x3 0x2
+#define IMX7ULP_PAD_PTE13__LPUART7_RTS_B 0x0134 0x0000 0x4 0x0
+#define IMX7ULP_PAD_PTE13__LPI2C7_SDA 0x0134 0x030c 0x5 0x2
+#define IMX7ULP_PAD_PTE13__TPM6_CLKIN 0x0134 0x02d8 0x6 0x2
+#define IMX7ULP_PAD_PTE13__SDHC1_CD 0x0134 0x032c 0x8 0x2
+#define IMX7ULP_PAD_PTE13__FB_A22 0x0134 0x0000 0x9 0x0
+#define IMX7ULP_PAD_PTE14__PTE14 0x0138 0x0000 0x1 0x0
+#define IMX7ULP_PAD_PTE14__TRACE_D0 0x0138 0x0000 0xa 0x0
+#define IMX7ULP_PAD_PTE14__VIU_D22 0x0138 0x0000 0xc 0x0
+#define IMX7ULP_PAD_PTE14__FXIO1_D17 0x0138 0x0000 0x2 0x0
+#define IMX7ULP_PAD_PTE14__LPSPI3_SCK 0x0138 0x0320 0x3 0x2
+#define IMX7ULP_PAD_PTE14__LPUART7_TX 0x0138 0x0270 0x4 0x2
+#define IMX7ULP_PAD_PTE14__LPI2C7_HREQ 0x0138 0x0304 0x5 0x2
+#define IMX7ULP_PAD_PTE14__TPM6_CH0 0x0138 0x02d0 0x6 0x2
+#define IMX7ULP_PAD_PTE14__SDHC1_VS 0x0138 0x0000 0x8 0x0
+#define IMX7ULP_PAD_PTE14__FB_A23 0x0138 0x0000 0x9 0x0
+#define IMX7ULP_PAD_PTE15__PTE15 0x013c 0x0000 0x1 0x0
+#define IMX7ULP_PAD_PTE15__TRACE_CLKOUT 0x013c 0x0000 0xa 0x0
+#define IMX7ULP_PAD_PTE15__VIU_D23 0x013c 0x0000 0xc 0x0
+#define IMX7ULP_PAD_PTE15__FXIO1_D16 0x013c 0x0000 0x2 0x0
+#define IMX7ULP_PAD_PTE15__LPSPI3_PCS0 0x013c 0x0310 0x3 0x2
+#define IMX7ULP_PAD_PTE15__LPUART7_RX 0x013c 0x026c 0x4 0x2
+#define IMX7ULP_PAD_PTE15__TPM6_CH1 0x013c 0x02d4 0x6 0x2
+#define IMX7ULP_PAD_PTE15__FB_A24 0x013c 0x0000 0x9 0x0
+#define IMX7ULP_PAD_PTF0__PTF0 0x0180 0x0000 0x1 0x0
+#define IMX7ULP_PAD_PTF0__VIU_DE 0x0180 0x0000 0xc 0x0
+#define IMX7ULP_PAD_PTF0__LPUART4_CTS_B 0x0180 0x0244 0x4 0x3
+#define IMX7ULP_PAD_PTF0__LPI2C4_SCL 0x0180 0x0278 0x5 0x3
+#define IMX7ULP_PAD_PTF0__TPM4_CLKIN 0x0180 0x0298 0x6 0x3
+#define IMX7ULP_PAD_PTF0__FB_RW_B 0x0180 0x0000 0x9 0x0
+#define IMX7ULP_PAD_PTF1__PTF1 0x0184 0x0000 0x1 0x0
+#define IMX7ULP_PAD_PTF1__VIU_HSYNC 0x0184 0x0000 0xc 0x0
+#define IMX7ULP_PAD_PTF1__LPUART4_RTS_B 0x0184 0x0000 0x4 0x0
+#define IMX7ULP_PAD_PTF1__LPI2C4_SDA 0x0184 0x027c 0x5 0x3
+#define IMX7ULP_PAD_PTF1__TPM4_CH0 0x0184 0x0280 0x6 0x3
+#define IMX7ULP_PAD_PTF1__CLKOUT 0x0184 0x0000 0x9 0x0
+#define IMX7ULP_PAD_PTF2__PTF2 0x0188 0x0000 0x1 0x0
+#define IMX7ULP_PAD_PTF2__VIU_VSYNC 0x0188 0x0000 0xc 0x0
+#define IMX7ULP_PAD_PTF2__LPUART4_TX 0x0188 0x024c 0x4 0x3
+#define IMX7ULP_PAD_PTF2__LPI2C4_HREQ 0x0188 0x0274 0x5 0x3
+#define IMX7ULP_PAD_PTF2__TPM4_CH1 0x0188 0x0284 0x6 0x3
+#define IMX7ULP_PAD_PTF2__FB_TSIZ1_FB_CS5_B_FB_BE23_16_BLS15_8_B 0x0188 0x0000 0x9 0x0
+#define IMX7ULP_PAD_PTF3__PTF3 0x018c 0x0000 0x1 0x0
+#define IMX7ULP_PAD_PTF3__VIU_PCLK 0x018c 0x0000 0xc 0x0
+#define IMX7ULP_PAD_PTF3__LPUART4_RX 0x018c 0x0248 0x4 0x3
+#define IMX7ULP_PAD_PTF3__TPM4_CH2 0x018c 0x0288 0x6 0x3
+#define IMX7ULP_PAD_PTF3__FB_AD16 0x018c 0x0000 0x9 0x0
+#define IMX7ULP_PAD_PTF4__PTF4 0x0190 0x0000 0x1 0x0
+#define IMX7ULP_PAD_PTF4__VIU_D0 0x0190 0x0000 0xc 0x0
+#define IMX7ULP_PAD_PTF4__FXIO1_D0 0x0190 0x0204 0x2 0x2
+#define IMX7ULP_PAD_PTF4__LPSPI2_PCS1 0x0190 0x02a0 0x3 0x3
+#define IMX7ULP_PAD_PTF4__LPUART5_CTS_B 0x0190 0x0250 0x4 0x3
+#define IMX7ULP_PAD_PTF4__LPI2C5_SCL 0x0190 0x02bc 0x5 0x3
+#define IMX7ULP_PAD_PTF4__TPM4_CH3 0x0190 0x028c 0x6 0x2
+#define IMX7ULP_PAD_PTF4__FB_AD17 0x0190 0x0000 0x9 0x0
+#define IMX7ULP_PAD_PTF5__PTF5 0x0194 0x0000 0x1 0x0
+#define IMX7ULP_PAD_PTF5__VIU_D1 0x0194 0x0000 0xc 0x0
+#define IMX7ULP_PAD_PTF5__FXIO1_D1 0x0194 0x0208 0x2 0x2
+#define IMX7ULP_PAD_PTF5__LPSPI2_PCS2 0x0194 0x02a4 0x3 0x3
+#define IMX7ULP_PAD_PTF5__LPUART5_RTS_B 0x0194 0x0000 0x4 0x0
+#define IMX7ULP_PAD_PTF5__LPI2C5_SDA 0x0194 0x02c0 0x5 0x3
+#define IMX7ULP_PAD_PTF5__TPM4_CH4 0x0194 0x0290 0x6 0x2
+#define IMX7ULP_PAD_PTF5__FB_AD18 0x0194 0x0000 0x9 0x0
+#define IMX7ULP_PAD_PTF6__PTF6 0x0198 0x0000 0x1 0x0
+#define IMX7ULP_PAD_PTF6__VIU_D2 0x0198 0x0000 0xc 0x0
+#define IMX7ULP_PAD_PTF6__FXIO1_D2 0x0198 0x020c 0x2 0x2
+#define IMX7ULP_PAD_PTF6__LPSPI2_PCS3 0x0198 0x02a8 0x3 0x3
+#define IMX7ULP_PAD_PTF6__LPUART5_TX 0x0198 0x0258 0x4 0x3
+#define IMX7ULP_PAD_PTF6__LPI2C5_HREQ 0x0198 0x02b8 0x5 0x3
+#define IMX7ULP_PAD_PTF6__TPM4_CH5 0x0198 0x0294 0x6 0x2
+#define IMX7ULP_PAD_PTF6__FB_AD19 0x0198 0x0000 0x9 0x0
+#define IMX7ULP_PAD_PTF7__PTF7 0x019c 0x0000 0x1 0x0
+#define IMX7ULP_PAD_PTF7__VIU_D3 0x019c 0x0000 0xc 0x0
+#define IMX7ULP_PAD_PTF7__FXIO1_D3 0x019c 0x0210 0x2 0x2
+#define IMX7ULP_PAD_PTF7__LPUART5_RX 0x019c 0x0254 0x4 0x3
+#define IMX7ULP_PAD_PTF7__TPM5_CH1 0x019c 0x02c8 0x6 0x3
+#define IMX7ULP_PAD_PTF7__FB_AD20 0x019c 0x0000 0x9 0x0
+#define IMX7ULP_PAD_PTF8__PTF8 0x01a0 0x0000 0x1 0x0
+#define IMX7ULP_PAD_PTF8__USB1_ULPI_CLK 0x01a0 0x0000 0xb 0x0
+#define IMX7ULP_PAD_PTF8__VIU_D4 0x01a0 0x0000 0xc 0x0
+#define IMX7ULP_PAD_PTF8__FXIO1_D4 0x01a0 0x0214 0x2 0x2
+#define IMX7ULP_PAD_PTF8__LPSPI2_SIN 0x01a0 0x02b0 0x3 0x3
+#define IMX7ULP_PAD_PTF8__LPUART6_CTS_B 0x01a0 0x025c 0x4 0x3
+#define IMX7ULP_PAD_PTF8__LPI2C6_SCL 0x01a0 0x02fc 0x5 0x3
+#define IMX7ULP_PAD_PTF8__TPM5_CLKIN 0x01a0 0x02cc 0x6 0x3
+#define IMX7ULP_PAD_PTF8__FB_AD21 0x01a0 0x0000 0x9 0x0
+#define IMX7ULP_PAD_PTF9__PTF9 0x01a4 0x0000 0x1 0x0
+#define IMX7ULP_PAD_PTF9__USB1_ULPI_NXT 0x01a4 0x0000 0xb 0x0
+#define IMX7ULP_PAD_PTF9__VIU_D5 0x01a4 0x0000 0xc 0x0
+#define IMX7ULP_PAD_PTF9__FXIO1_D5 0x01a4 0x0218 0x2 0x2
+#define IMX7ULP_PAD_PTF9__LPSPI2_SOUT 0x01a4 0x02b4 0x3 0x3
+#define IMX7ULP_PAD_PTF9__LPUART6_RTS_B 0x01a4 0x0000 0x4 0x0
+#define IMX7ULP_PAD_PTF9__LPI2C6_SDA 0x01a4 0x0300 0x5 0x3
+#define IMX7ULP_PAD_PTF9__TPM5_CH0 0x01a4 0x02c4 0x6 0x3
+#define IMX7ULP_PAD_PTF9__FB_AD22 0x01a4 0x0000 0x9 0x0
+#define IMX7ULP_PAD_PTF10__PTF10 0x01a8 0x0000 0x1 0x0
+#define IMX7ULP_PAD_PTF10__USB1_ULPI_STP 0x01a8 0x0000 0xb 0x0
+#define IMX7ULP_PAD_PTF10__VIU_D6 0x01a8 0x0000 0xc 0x0
+#define IMX7ULP_PAD_PTF10__FXIO1_D6 0x01a8 0x021c 0x2 0x2
+#define IMX7ULP_PAD_PTF10__LPSPI2_SCK 0x01a8 0x02ac 0x3 0x3
+#define IMX7ULP_PAD_PTF10__LPUART6_TX 0x01a8 0x0264 0x4 0x3
+#define IMX7ULP_PAD_PTF10__LPI2C6_HREQ 0x01a8 0x02f8 0x5 0x3
+#define IMX7ULP_PAD_PTF10__TPM7_CH3 0x01a8 0x02e8 0x6 0x3
+#define IMX7ULP_PAD_PTF10__FB_AD23 0x01a8 0x0000 0x9 0x0
+#define IMX7ULP_PAD_PTF11__PTF11 0x01ac 0x0000 0x1 0x0
+#define IMX7ULP_PAD_PTF11__USB1_ULPI_DIR 0x01ac 0x0000 0xb 0x0
+#define IMX7ULP_PAD_PTF11__VIU_D7 0x01ac 0x0000 0xc 0x0
+#define IMX7ULP_PAD_PTF11__FXIO1_D7 0x01ac 0x0220 0x2 0x2
+#define IMX7ULP_PAD_PTF11__LPSPI2_PCS0 0x01ac 0x029c 0x3 0x3
+#define IMX7ULP_PAD_PTF11__LPUART6_RX 0x01ac 0x0260 0x4 0x3
+#define IMX7ULP_PAD_PTF11__TPM7_CH4 0x01ac 0x02ec 0x6 0x3
+#define IMX7ULP_PAD_PTF11__FB_CS4_B_FB_TSIZ0_FB_BE31_24_BLS7_0_B 0x01ac 0x0000 0x9 0x0
+#define IMX7ULP_PAD_PTF12__PTF12 0x01b0 0x0000 0x1 0x0
+#define IMX7ULP_PAD_PTF12__USB1_ULPI_DATA0 0x01b0 0x0000 0xb 0x0
+#define IMX7ULP_PAD_PTF12__VIU_D8 0x01b0 0x0000 0xc 0x0
+#define IMX7ULP_PAD_PTF12__FXIO1_D8 0x01b0 0x0224 0x2 0x2
+#define IMX7ULP_PAD_PTF12__LPSPI3_PCS1 0x01b0 0x0314 0x3 0x3
+#define IMX7ULP_PAD_PTF12__LPUART7_CTS_B 0x01b0 0x0268 0x4 0x3
+#define IMX7ULP_PAD_PTF12__LPI2C7_SCL 0x01b0 0x0308 0x5 0x3
+#define IMX7ULP_PAD_PTF12__TPM7_CH5 0x01b0 0x02f0 0x6 0x3
+#define IMX7ULP_PAD_PTF12__FB_AD24 0x01b0 0x0000 0x9 0x0
+#define IMX7ULP_PAD_PTF13__PTF13 0x01b4 0x0000 0x1 0x0
+#define IMX7ULP_PAD_PTF13__USB1_ULPI_DATA1 0x01b4 0x0000 0xb 0x0
+#define IMX7ULP_PAD_PTF13__VIU_D9 0x01b4 0x0000 0xc 0x0
+#define IMX7ULP_PAD_PTF13__FXIO1_D9 0x01b4 0x0228 0x2 0x2
+#define IMX7ULP_PAD_PTF13__LPSPI3_PCS2 0x01b4 0x0318 0x3 0x3
+#define IMX7ULP_PAD_PTF13__LPUART7_RTS_B 0x01b4 0x0000 0x4 0x0
+#define IMX7ULP_PAD_PTF13__LPI2C7_SDA 0x01b4 0x030c 0x5 0x3
+#define IMX7ULP_PAD_PTF13__TPM7_CLKIN 0x01b4 0x02f4 0x6 0x3
+#define IMX7ULP_PAD_PTF13__FB_AD25 0x01b4 0x0000 0x9 0x0
+#define IMX7ULP_PAD_PTF14__PTF14 0x01b8 0x0000 0x1 0x0
+#define IMX7ULP_PAD_PTF14__USB1_ULPI_DATA2 0x01b8 0x0000 0xb 0x0
+#define IMX7ULP_PAD_PTF14__VIU_D10 0x01b8 0x0000 0xc 0x0
+#define IMX7ULP_PAD_PTF14__FXIO1_D10 0x01b8 0x022c 0x2 0x2
+#define IMX7ULP_PAD_PTF14__LPSPI3_PCS3 0x01b8 0x031c 0x3 0x3
+#define IMX7ULP_PAD_PTF14__LPUART7_TX 0x01b8 0x0270 0x4 0x3
+#define IMX7ULP_PAD_PTF14__LPI2C7_HREQ 0x01b8 0x0304 0x5 0x3
+#define IMX7ULP_PAD_PTF14__TPM7_CH0 0x01b8 0x02dc 0x6 0x3
+#define IMX7ULP_PAD_PTF14__FB_AD26 0x01b8 0x0000 0x9 0x0
+#define IMX7ULP_PAD_PTF15__PTF15 0x01bc 0x0000 0x1 0x0
+#define IMX7ULP_PAD_PTF15__USB1_ULPI_DATA3 0x01bc 0x0000 0xb 0x0
+#define IMX7ULP_PAD_PTF15__VIU_D11 0x01bc 0x0000 0xc 0x0
+#define IMX7ULP_PAD_PTF15__FXIO1_D11 0x01bc 0x0230 0x2 0x2
+#define IMX7ULP_PAD_PTF15__LPUART7_RX 0x01bc 0x026c 0x4 0x3
+#define IMX7ULP_PAD_PTF15__TPM7_CH1 0x01bc 0x02e0 0x6 0x3
+#define IMX7ULP_PAD_PTF15__FB_AD27 0x01bc 0x0000 0x9 0x0
+#define IMX7ULP_PAD_PTF16__PTF16 0x01c0 0x0000 0x1 0x0
+#define IMX7ULP_PAD_PTF16__USB1_ULPI_DATA4 0x01c0 0x0000 0xb 0x0
+#define IMX7ULP_PAD_PTF16__VIU_D12 0x01c0 0x0000 0xc 0x0
+#define IMX7ULP_PAD_PTF16__FXIO1_D12 0x01c0 0x0234 0x2 0x2
+#define IMX7ULP_PAD_PTF16__LPSPI3_SIN 0x01c0 0x0324 0x3 0x3
+#define IMX7ULP_PAD_PTF16__TPM7_CH2 0x01c0 0x02e4 0x6 0x3
+#define IMX7ULP_PAD_PTF16__FB_AD28 0x01c0 0x0000 0x9 0x0
+#define IMX7ULP_PAD_PTF17__PTF17 0x01c4 0x0000 0x1 0x0
+#define IMX7ULP_PAD_PTF17__USB1_ULPI_DATA5 0x01c4 0x0000 0xb 0x0
+#define IMX7ULP_PAD_PTF17__VIU_D13 0x01c4 0x0000 0xc 0x0
+#define IMX7ULP_PAD_PTF17__FXIO1_D13 0x01c4 0x0238 0x2 0x2
+#define IMX7ULP_PAD_PTF17__LPSPI3_SOUT 0x01c4 0x0328 0x3 0x3
+#define IMX7ULP_PAD_PTF17__TPM6_CLKIN 0x01c4 0x02d8 0x6 0x3
+#define IMX7ULP_PAD_PTF17__FB_AD29 0x01c4 0x0000 0x9 0x0
+#define IMX7ULP_PAD_PTF18__PTF18 0x01c8 0x0000 0x1 0x0
+#define IMX7ULP_PAD_PTF18__USB1_ULPI_DATA6 0x01c8 0x0000 0xb 0x0
+#define IMX7ULP_PAD_PTF18__VIU_D14 0x01c8 0x0000 0xc 0x0
+#define IMX7ULP_PAD_PTF18__FXIO1_D14 0x01c8 0x023c 0x2 0x2
+#define IMX7ULP_PAD_PTF18__LPSPI3_SCK 0x01c8 0x0320 0x3 0x3
+#define IMX7ULP_PAD_PTF18__TPM6_CH0 0x01c8 0x02d0 0x6 0x3
+#define IMX7ULP_PAD_PTF18__FB_AD30 0x01c8 0x0000 0x9 0x0
+#define IMX7ULP_PAD_PTF19__PTF19 0x01cc 0x0000 0x1 0x0
+#define IMX7ULP_PAD_PTF19__USB1_ULPI_DATA7 0x01cc 0x0000 0xb 0x0
+#define IMX7ULP_PAD_PTF19__VIU_D15 0x01cc 0x0000 0xc 0x0
+#define IMX7ULP_PAD_PTF19__FXIO1_D15 0x01cc 0x0240 0x2 0x2
+#define IMX7ULP_PAD_PTF19__LPSPI3_PCS0 0x01cc 0x0310 0x3 0x3
+#define IMX7ULP_PAD_PTF19__TPM6_CH1 0x01cc 0x02d4 0x6 0x3
+#define IMX7ULP_PAD_PTF19__FB_AD31 0x01cc 0x0000 0x9 0x0
+
+#endif /* __DTS_IMX7ULP_PINFUNC_H */
diff --git a/arch/arm/boot/dts/ls1021a.dtsi b/arch/arm/boot/dts/ls1021a.dtsi
index 7bb9df2c1460..9319e1f0f1d8 100644
--- a/arch/arm/boot/dts/ls1021a.dtsi
+++ b/arch/arm/boot/dts/ls1021a.dtsi
@@ -129,14 +129,14 @@
};
msi1: msi-controller@1570e00 {
- compatible = "fsl,1s1021a-msi";
+ compatible = "fsl,ls1021a-msi";
reg = <0x0 0x1570e00 0x0 0x8>;
msi-controller;
interrupts = <GIC_SPI 179 IRQ_TYPE_LEVEL_HIGH>;
};
msi2: msi-controller@1570e08 {
- compatible = "fsl,1s1021a-msi";
+ compatible = "fsl,ls1021a-msi";
reg = <0x0 0x1570e08 0x0 0x8>;
msi-controller;
interrupts = <GIC_SPI 180 IRQ_TYPE_LEVEL_HIGH>;
@@ -699,7 +699,7 @@
bus-range = <0x0 0xff>;
ranges = <0x81000000 0x0 0x00000000 0x40 0x00010000 0x0 0x00010000 /* downstream I/O */
0x82000000 0x0 0x40000000 0x40 0x40000000 0x0 0x40000000>; /* non-prefetchable memory */
- msi-parent = <&msi1>;
+ msi-parent = <&msi1>, <&msi2>;
#interrupt-cells = <1>;
interrupt-map-mask = <0 0 0 7>;
interrupt-map = <0000 0 0 1 &gic GIC_SPI 91 IRQ_TYPE_LEVEL_HIGH>,
@@ -722,7 +722,7 @@
bus-range = <0x0 0xff>;
ranges = <0x81000000 0x0 0x00000000 0x48 0x00010000 0x0 0x00010000 /* downstream I/O */
0x82000000 0x0 0x40000000 0x48 0x40000000 0x0 0x40000000>; /* non-prefetchable memory */
- msi-parent = <&msi2>;
+ msi-parent = <&msi1>, <&msi2>;
#interrupt-cells = <1>;
interrupt-map-mask = <0 0 0 7>;
interrupt-map = <0000 0 0 1 &gic GIC_SPI 92 IRQ_TYPE_LEVEL_HIGH>,
diff --git a/arch/arm/boot/dts/omap3-n950-n9.dtsi b/arch/arm/boot/dts/omap3-n950-n9.dtsi
index df3366fa5409..cb47ae79a5f9 100644
--- a/arch/arm/boot/dts/omap3-n950-n9.dtsi
+++ b/arch/arm/boot/dts/omap3-n950-n9.dtsi
@@ -265,6 +265,20 @@
&i2c2 {
clock-frequency = <400000>;
+
+ as3645a@30 {
+ reg = <0x30>;
+ compatible = "ams,as3645a";
+ flash {
+ flash-timeout-us = <150000>;
+ flash-max-microamp = <320000>;
+ led-max-microamp = <60000>;
+ peak-current-limit = <1750000>;
+ };
+ indicator {
+ led-max-microamp = <10000>;
+ };
+ };
};
&i2c3 {
diff --git a/arch/arm/boot/dts/rk3228-evb.dts b/arch/arm/boot/dts/rk3228-evb.dts
index 58834330a5ba..1be9daacc4f9 100644
--- a/arch/arm/boot/dts/rk3228-evb.dts
+++ b/arch/arm/boot/dts/rk3228-evb.dts
@@ -50,6 +50,16 @@
device_type = "memory";
reg = <0x60000000 0x40000000>;
};
+
+ vcc_phy: vcc-phy-regulator {
+ compatible = "regulator-fixed";
+ enable-active-high;
+ regulator-name = "vcc_phy";
+ regulator-min-microvolt = <1800000>;
+ regulator-max-microvolt = <1800000>;
+ regulator-always-on;
+ regulator-boot-on;
+ };
};
&emmc {
@@ -60,6 +70,30 @@
status = "okay";
};
+&gmac {
+ assigned-clocks = <&cru SCLK_MAC_SRC>;
+ assigned-clock-rates = <50000000>;
+ clock_in_out = "output";
+ phy-supply = <&vcc_phy>;
+ phy-mode = "rmii";
+ phy-handle = <&phy>;
+ status = "okay";
+
+ mdio {
+ compatible = "snps,dwmac-mdio";
+ #address-cells = <1>;
+ #size-cells = <0>;
+
+ phy: phy@0 {
+ compatible = "ethernet-phy-id1234.d400", "ethernet-phy-ieee802.3-c22";
+ reg = <0>;
+ clocks = <&cru SCLK_MAC_PHY>;
+ resets = <&cru SRST_MACPHY>;
+ phy-is-integrated;
+ };
+ };
+};
+
&tsadc {
status = "okay";
diff --git a/arch/arm/boot/dts/tango4-smp8758.dtsi b/arch/arm/boot/dts/tango4-smp8758.dtsi
index d2e65c46bcc7..eca33d568690 100644
--- a/arch/arm/boot/dts/tango4-smp8758.dtsi
+++ b/arch/arm/boot/dts/tango4-smp8758.dtsi
@@ -13,7 +13,6 @@
reg = <0>;
clocks = <&clkgen CPU_CLK>;
clock-latency = <1>;
- operating-points = <1215000 0 607500 0 405000 0 243000 0 135000 0>;
};
cpu1: cpu@1 {
diff --git a/arch/arm/configs/imx_v6_v7_defconfig b/arch/arm/configs/imx_v6_v7_defconfig
index e74de69caeab..1736813bdea7 100644
--- a/arch/arm/configs/imx_v6_v7_defconfig
+++ b/arch/arm/configs/imx_v6_v7_defconfig
@@ -226,7 +226,7 @@ CONFIG_REGULATOR_MC13892=y
CONFIG_REGULATOR_PFUZE100=y
CONFIG_MEDIA_SUPPORT=y
CONFIG_MEDIA_CAMERA_SUPPORT=y
-CONFIG_MEDIA_RC_SUPPORT=y
+CONFIG_RC_CORE=y
CONFIG_RC_DEVICES=y
CONFIG_IR_GPIO_CIR=y
CONFIG_MEDIA_USB_SUPPORT=y
diff --git a/arch/arm/configs/multi_v7_defconfig b/arch/arm/configs/multi_v7_defconfig
index 4d19c1b4b8e7..94d7e71c69c4 100644
--- a/arch/arm/configs/multi_v7_defconfig
+++ b/arch/arm/configs/multi_v7_defconfig
@@ -270,6 +270,7 @@ CONFIG_ICPLUS_PHY=y
CONFIG_REALTEK_PHY=y
CONFIG_MICREL_PHY=y
CONFIG_FIXED_PHY=y
+CONFIG_ROCKCHIP_PHY=y
CONFIG_USB_PEGASUS=y
CONFIG_USB_RTL8152=m
CONFIG_USB_USBNET=y
diff --git a/arch/arm/configs/omap2plus_defconfig b/arch/arm/configs/omap2plus_defconfig
index a120ae816260..0414acf731ce 100644
--- a/arch/arm/configs/omap2plus_defconfig
+++ b/arch/arm/configs/omap2plus_defconfig
@@ -304,7 +304,7 @@ CONFIG_REGULATOR_TPS65910=y
CONFIG_REGULATOR_TWL4030=y
CONFIG_MEDIA_SUPPORT=m
CONFIG_MEDIA_CAMERA_SUPPORT=y
-CONFIG_MEDIA_RC_SUPPORT=y
+CONFIG_RC_CORE=m
CONFIG_MEDIA_CONTROLLER=y
CONFIG_VIDEO_V4L2_SUBDEV_API=y
CONFIG_LIRC=m
diff --git a/arch/arm/configs/sunxi_defconfig b/arch/arm/configs/sunxi_defconfig
index 0ec1d1ec130f..22cd559531a9 100644
--- a/arch/arm/configs/sunxi_defconfig
+++ b/arch/arm/configs/sunxi_defconfig
@@ -95,7 +95,7 @@ CONFIG_REGULATOR_FIXED_VOLTAGE=y
CONFIG_REGULATOR_AXP20X=y
CONFIG_REGULATOR_GPIO=y
CONFIG_MEDIA_SUPPORT=y
-CONFIG_MEDIA_RC_SUPPORT=y
+CONFIG_RC_CORE=y
CONFIG_RC_DEVICES=y
CONFIG_IR_SUNXI=y
CONFIG_DRM=y
diff --git a/arch/arm/crypto/Kconfig b/arch/arm/crypto/Kconfig
index b9adedcc5b2e..ec72752d5668 100644
--- a/arch/arm/crypto/Kconfig
+++ b/arch/arm/crypto/Kconfig
@@ -94,14 +94,15 @@ config CRYPTO_AES_ARM_CE
ARMv8 Crypto Extensions
config CRYPTO_GHASH_ARM_CE
- tristate "PMULL-accelerated GHASH using ARMv8 Crypto Extensions"
+ tristate "PMULL-accelerated GHASH using NEON/ARMv8 Crypto Extensions"
depends on KERNEL_MODE_NEON
select CRYPTO_HASH
select CRYPTO_CRYPTD
help
Use an implementation of GHASH (used by the GCM AEAD chaining mode)
that uses the 64x64 to 128 bit polynomial multiplication (vmull.p64)
- that is part of the ARMv8 Crypto Extensions
+ that is part of the ARMv8 Crypto Extensions, or a slower variant that
+ uses the vmull.p8 instruction that is part of the basic NEON ISA.
config CRYPTO_CRCT10DIF_ARM_CE
tristate "CRCT10DIF digest algorithm using PMULL instructions"
diff --git a/arch/arm/crypto/aes-ce-glue.c b/arch/arm/crypto/aes-ce-glue.c
index 0f966a8ca1ce..d0a9cec73707 100644
--- a/arch/arm/crypto/aes-ce-glue.c
+++ b/arch/arm/crypto/aes-ce-glue.c
@@ -285,9 +285,7 @@ static int ctr_encrypt(struct skcipher_request *req)
ce_aes_ctr_encrypt(tail, NULL, (u8 *)ctx->key_enc,
num_rounds(ctx), blocks, walk.iv);
- if (tdst != tsrc)
- memcpy(tdst, tsrc, nbytes);
- crypto_xor(tdst, tail, nbytes);
+ crypto_xor_cpy(tdst, tsrc, tail, nbytes);
err = skcipher_walk_done(&walk, 0);
}
kernel_neon_end();
diff --git a/arch/arm/crypto/aes-cipher-core.S b/arch/arm/crypto/aes-cipher-core.S
index c817a86c4ca8..54b384084637 100644
--- a/arch/arm/crypto/aes-cipher-core.S
+++ b/arch/arm/crypto/aes-cipher-core.S
@@ -10,6 +10,7 @@
*/
#include <linux/linkage.h>
+#include <asm/cache.h>
.text
.align 5
@@ -32,19 +33,19 @@
.endif
.endm
- .macro __load, out, in, idx
+ .macro __load, out, in, idx, sz, op
.if __LINUX_ARM_ARCH__ < 7 && \idx > 0
- ldr \out, [ttab, \in, lsr #(8 * \idx) - 2]
+ ldr\op \out, [ttab, \in, lsr #(8 * \idx) - \sz]
.else
- ldr \out, [ttab, \in, lsl #2]
+ ldr\op \out, [ttab, \in, lsl #\sz]
.endif
.endm
- .macro __hround, out0, out1, in0, in1, in2, in3, t3, t4, enc
+ .macro __hround, out0, out1, in0, in1, in2, in3, t3, t4, enc, sz, op
__select \out0, \in0, 0
__select t0, \in1, 1
- __load \out0, \out0, 0
- __load t0, t0, 1
+ __load \out0, \out0, 0, \sz, \op
+ __load t0, t0, 1, \sz, \op
.if \enc
__select \out1, \in1, 0
@@ -53,10 +54,10 @@
__select \out1, \in3, 0
__select t1, \in0, 1
.endif
- __load \out1, \out1, 0
+ __load \out1, \out1, 0, \sz, \op
__select t2, \in2, 2
- __load t1, t1, 1
- __load t2, t2, 2
+ __load t1, t1, 1, \sz, \op
+ __load t2, t2, 2, \sz, \op
eor \out0, \out0, t0, ror #24
@@ -68,9 +69,9 @@
__select \t3, \in1, 2
__select \t4, \in2, 3
.endif
- __load \t3, \t3, 2
- __load t0, t0, 3
- __load \t4, \t4, 3
+ __load \t3, \t3, 2, \sz, \op
+ __load t0, t0, 3, \sz, \op
+ __load \t4, \t4, 3, \sz, \op
eor \out1, \out1, t1, ror #24
eor \out0, \out0, t2, ror #16
@@ -82,14 +83,14 @@
eor \out1, \out1, t2
.endm
- .macro fround, out0, out1, out2, out3, in0, in1, in2, in3
- __hround \out0, \out1, \in0, \in1, \in2, \in3, \out2, \out3, 1
- __hround \out2, \out3, \in2, \in3, \in0, \in1, \in1, \in2, 1
+ .macro fround, out0, out1, out2, out3, in0, in1, in2, in3, sz=2, op
+ __hround \out0, \out1, \in0, \in1, \in2, \in3, \out2, \out3, 1, \sz, \op
+ __hround \out2, \out3, \in2, \in3, \in0, \in1, \in1, \in2, 1, \sz, \op
.endm
- .macro iround, out0, out1, out2, out3, in0, in1, in2, in3
- __hround \out0, \out1, \in0, \in3, \in2, \in1, \out2, \out3, 0
- __hround \out2, \out3, \in2, \in1, \in0, \in3, \in1, \in0, 0
+ .macro iround, out0, out1, out2, out3, in0, in1, in2, in3, sz=2, op
+ __hround \out0, \out1, \in0, \in3, \in2, \in1, \out2, \out3, 0, \sz, \op
+ __hround \out2, \out3, \in2, \in1, \in0, \in3, \in1, \in0, 0, \sz, \op
.endm
.macro __rev, out, in
@@ -114,7 +115,7 @@
.endif
.endm
- .macro do_crypt, round, ttab, ltab
+ .macro do_crypt, round, ttab, ltab, bsz
push {r3-r11, lr}
ldr r4, [in]
@@ -146,9 +147,12 @@
1: subs rounds, rounds, #4
\round r8, r9, r10, r11, r4, r5, r6, r7
- __adrl ttab, \ltab, ls
+ bls 2f
\round r4, r5, r6, r7, r8, r9, r10, r11
- bhi 0b
+ b 0b
+
+2: __adrl ttab, \ltab
+ \round r4, r5, r6, r7, r8, r9, r10, r11, \bsz, b
#ifdef CONFIG_CPU_BIG_ENDIAN
__rev r4, r4
@@ -170,10 +174,48 @@
.ltorg
.endm
+ .align L1_CACHE_SHIFT
+ .type __aes_arm_inverse_sbox, %object
+__aes_arm_inverse_sbox:
+ .byte 0x52, 0x09, 0x6a, 0xd5, 0x30, 0x36, 0xa5, 0x38
+ .byte 0xbf, 0x40, 0xa3, 0x9e, 0x81, 0xf3, 0xd7, 0xfb
+ .byte 0x7c, 0xe3, 0x39, 0x82, 0x9b, 0x2f, 0xff, 0x87
+ .byte 0x34, 0x8e, 0x43, 0x44, 0xc4, 0xde, 0xe9, 0xcb
+ .byte 0x54, 0x7b, 0x94, 0x32, 0xa6, 0xc2, 0x23, 0x3d
+ .byte 0xee, 0x4c, 0x95, 0x0b, 0x42, 0xfa, 0xc3, 0x4e
+ .byte 0x08, 0x2e, 0xa1, 0x66, 0x28, 0xd9, 0x24, 0xb2
+ .byte 0x76, 0x5b, 0xa2, 0x49, 0x6d, 0x8b, 0xd1, 0x25
+ .byte 0x72, 0xf8, 0xf6, 0x64, 0x86, 0x68, 0x98, 0x16
+ .byte 0xd4, 0xa4, 0x5c, 0xcc, 0x5d, 0x65, 0xb6, 0x92
+ .byte 0x6c, 0x70, 0x48, 0x50, 0xfd, 0xed, 0xb9, 0xda
+ .byte 0x5e, 0x15, 0x46, 0x57, 0xa7, 0x8d, 0x9d, 0x84
+ .byte 0x90, 0xd8, 0xab, 0x00, 0x8c, 0xbc, 0xd3, 0x0a
+ .byte 0xf7, 0xe4, 0x58, 0x05, 0xb8, 0xb3, 0x45, 0x06
+ .byte 0xd0, 0x2c, 0x1e, 0x8f, 0xca, 0x3f, 0x0f, 0x02
+ .byte 0xc1, 0xaf, 0xbd, 0x03, 0x01, 0x13, 0x8a, 0x6b
+ .byte 0x3a, 0x91, 0x11, 0x41, 0x4f, 0x67, 0xdc, 0xea
+ .byte 0x97, 0xf2, 0xcf, 0xce, 0xf0, 0xb4, 0xe6, 0x73
+ .byte 0x96, 0xac, 0x74, 0x22, 0xe7, 0xad, 0x35, 0x85
+ .byte 0xe2, 0xf9, 0x37, 0xe8, 0x1c, 0x75, 0xdf, 0x6e
+ .byte 0x47, 0xf1, 0x1a, 0x71, 0x1d, 0x29, 0xc5, 0x89
+ .byte 0x6f, 0xb7, 0x62, 0x0e, 0xaa, 0x18, 0xbe, 0x1b
+ .byte 0xfc, 0x56, 0x3e, 0x4b, 0xc6, 0xd2, 0x79, 0x20
+ .byte 0x9a, 0xdb, 0xc0, 0xfe, 0x78, 0xcd, 0x5a, 0xf4
+ .byte 0x1f, 0xdd, 0xa8, 0x33, 0x88, 0x07, 0xc7, 0x31
+ .byte 0xb1, 0x12, 0x10, 0x59, 0x27, 0x80, 0xec, 0x5f
+ .byte 0x60, 0x51, 0x7f, 0xa9, 0x19, 0xb5, 0x4a, 0x0d
+ .byte 0x2d, 0xe5, 0x7a, 0x9f, 0x93, 0xc9, 0x9c, 0xef
+ .byte 0xa0, 0xe0, 0x3b, 0x4d, 0xae, 0x2a, 0xf5, 0xb0
+ .byte 0xc8, 0xeb, 0xbb, 0x3c, 0x83, 0x53, 0x99, 0x61
+ .byte 0x17, 0x2b, 0x04, 0x7e, 0xba, 0x77, 0xd6, 0x26
+ .byte 0xe1, 0x69, 0x14, 0x63, 0x55, 0x21, 0x0c, 0x7d
+ .size __aes_arm_inverse_sbox, . - __aes_arm_inverse_sbox
+
ENTRY(__aes_arm_encrypt)
- do_crypt fround, crypto_ft_tab, crypto_fl_tab
+ do_crypt fround, crypto_ft_tab, crypto_ft_tab + 1, 2
ENDPROC(__aes_arm_encrypt)
+ .align 5
ENTRY(__aes_arm_decrypt)
- do_crypt iround, crypto_it_tab, crypto_il_tab
+ do_crypt iround, crypto_it_tab, __aes_arm_inverse_sbox, 0
ENDPROC(__aes_arm_decrypt)
diff --git a/arch/arm/crypto/aes-neonbs-glue.c b/arch/arm/crypto/aes-neonbs-glue.c
index c76377961444..18768f330449 100644
--- a/arch/arm/crypto/aes-neonbs-glue.c
+++ b/arch/arm/crypto/aes-neonbs-glue.c
@@ -221,9 +221,8 @@ static int ctr_encrypt(struct skcipher_request *req)
u8 *dst = walk.dst.virt.addr + blocks * AES_BLOCK_SIZE;
u8 *src = walk.src.virt.addr + blocks * AES_BLOCK_SIZE;
- if (dst != src)
- memcpy(dst, src, walk.total % AES_BLOCK_SIZE);
- crypto_xor(dst, final, walk.total % AES_BLOCK_SIZE);
+ crypto_xor_cpy(dst, src, final,
+ walk.total % AES_BLOCK_SIZE);
err = skcipher_walk_done(&walk, 0);
break;
diff --git a/arch/arm/crypto/ghash-ce-core.S b/arch/arm/crypto/ghash-ce-core.S
index f6ab8bcc9efe..2f78c10b1881 100644
--- a/arch/arm/crypto/ghash-ce-core.S
+++ b/arch/arm/crypto/ghash-ce-core.S
@@ -1,7 +1,7 @@
/*
- * Accelerated GHASH implementation with ARMv8 vmull.p64 instructions.
+ * Accelerated GHASH implementation with NEON/ARMv8 vmull.p8/64 instructions.
*
- * Copyright (C) 2015 Linaro Ltd. <ard.biesheuvel@linaro.org>
+ * Copyright (C) 2015 - 2017 Linaro Ltd. <ard.biesheuvel@linaro.org>
*
* 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
@@ -12,40 +12,162 @@
#include <asm/assembler.h>
SHASH .req q0
- SHASH2 .req q1
- T1 .req q2
- T2 .req q3
- MASK .req q4
- XL .req q5
- XM .req q6
- XH .req q7
- IN1 .req q7
+ T1 .req q1
+ XL .req q2
+ XM .req q3
+ XH .req q4
+ IN1 .req q4
SHASH_L .req d0
SHASH_H .req d1
- SHASH2_L .req d2
- T1_L .req d4
- MASK_L .req d8
- XL_L .req d10
- XL_H .req d11
- XM_L .req d12
- XM_H .req d13
- XH_L .req d14
+ T1_L .req d2
+ T1_H .req d3
+ XL_L .req d4
+ XL_H .req d5
+ XM_L .req d6
+ XM_H .req d7
+ XH_L .req d8
+
+ t0l .req d10
+ t0h .req d11
+ t1l .req d12
+ t1h .req d13
+ t2l .req d14
+ t2h .req d15
+ t3l .req d16
+ t3h .req d17
+ t4l .req d18
+ t4h .req d19
+
+ t0q .req q5
+ t1q .req q6
+ t2q .req q7
+ t3q .req q8
+ t4q .req q9
+ T2 .req q9
+
+ s1l .req d20
+ s1h .req d21
+ s2l .req d22
+ s2h .req d23
+ s3l .req d24
+ s3h .req d25
+ s4l .req d26
+ s4h .req d27
+
+ MASK .req d28
+ SHASH2_p8 .req d28
+
+ k16 .req d29
+ k32 .req d30
+ k48 .req d31
+ SHASH2_p64 .req d31
.text
.fpu crypto-neon-fp-armv8
+ .macro __pmull_p64, rd, rn, rm, b1, b2, b3, b4
+ vmull.p64 \rd, \rn, \rm
+ .endm
+
/*
- * void pmull_ghash_update(int blocks, u64 dg[], const char *src,
- * struct ghash_key const *k, const char *head)
+ * This implementation of 64x64 -> 128 bit polynomial multiplication
+ * using vmull.p8 instructions (8x8 -> 16) is taken from the paper
+ * "Fast Software Polynomial Multiplication on ARM Processors Using
+ * the NEON Engine" by Danilo Camara, Conrado Gouvea, Julio Lopez and
+ * Ricardo Dahab (https://hal.inria.fr/hal-01506572)
+ *
+ * It has been slightly tweaked for in-order performance, and to allow
+ * 'rq' to overlap with 'ad' or 'bd'.
*/
-ENTRY(pmull_ghash_update)
- vld1.64 {SHASH}, [r3]
+ .macro __pmull_p8, rq, ad, bd, b1=t4l, b2=t3l, b3=t4l, b4=t3l
+ vext.8 t0l, \ad, \ad, #1 @ A1
+ .ifc \b1, t4l
+ vext.8 t4l, \bd, \bd, #1 @ B1
+ .endif
+ vmull.p8 t0q, t0l, \bd @ F = A1*B
+ vext.8 t1l, \ad, \ad, #2 @ A2
+ vmull.p8 t4q, \ad, \b1 @ E = A*B1
+ .ifc \b2, t3l
+ vext.8 t3l, \bd, \bd, #2 @ B2
+ .endif
+ vmull.p8 t1q, t1l, \bd @ H = A2*B
+ vext.8 t2l, \ad, \ad, #3 @ A3
+ vmull.p8 t3q, \ad, \b2 @ G = A*B2
+ veor t0q, t0q, t4q @ L = E + F
+ .ifc \b3, t4l
+ vext.8 t4l, \bd, \bd, #3 @ B3
+ .endif
+ vmull.p8 t2q, t2l, \bd @ J = A3*B
+ veor t0l, t0l, t0h @ t0 = (L) (P0 + P1) << 8
+ veor t1q, t1q, t3q @ M = G + H
+ .ifc \b4, t3l
+ vext.8 t3l, \bd, \bd, #4 @ B4
+ .endif
+ vmull.p8 t4q, \ad, \b3 @ I = A*B3
+ veor t1l, t1l, t1h @ t1 = (M) (P2 + P3) << 16
+ vmull.p8 t3q, \ad, \b4 @ K = A*B4
+ vand t0h, t0h, k48
+ vand t1h, t1h, k32
+ veor t2q, t2q, t4q @ N = I + J
+ veor t0l, t0l, t0h
+ veor t1l, t1l, t1h
+ veor t2l, t2l, t2h @ t2 = (N) (P4 + P5) << 24
+ vand t2h, t2h, k16
+ veor t3l, t3l, t3h @ t3 = (K) (P6 + P7) << 32
+ vmov.i64 t3h, #0
+ vext.8 t0q, t0q, t0q, #15
+ veor t2l, t2l, t2h
+ vext.8 t1q, t1q, t1q, #14
+ vmull.p8 \rq, \ad, \bd @ D = A*B
+ vext.8 t2q, t2q, t2q, #13
+ vext.8 t3q, t3q, t3q, #12
+ veor t0q, t0q, t1q
+ veor t2q, t2q, t3q
+ veor \rq, \rq, t0q
+ veor \rq, \rq, t2q
+ .endm
+
+ //
+ // PMULL (64x64->128) based reduction for CPUs that can do
+ // it in a single instruction.
+ //
+ .macro __pmull_reduce_p64
+ vmull.p64 T1, XL_L, MASK
+
+ veor XH_L, XH_L, XM_H
+ vext.8 T1, T1, T1, #8
+ veor XL_H, XL_H, XM_L
+ veor T1, T1, XL
+
+ vmull.p64 XL, T1_H, MASK
+ .endm
+
+ //
+ // Alternative reduction for CPUs that lack support for the
+ // 64x64->128 PMULL instruction
+ //
+ .macro __pmull_reduce_p8
+ veor XL_H, XL_H, XM_L
+ veor XH_L, XH_L, XM_H
+
+ vshl.i64 T1, XL, #57
+ vshl.i64 T2, XL, #62
+ veor T1, T1, T2
+ vshl.i64 T2, XL, #63
+ veor T1, T1, T2
+ veor XL_H, XL_H, T1_L
+ veor XH_L, XH_L, T1_H
+
+ vshr.u64 T1, XL, #1
+ veor XH, XH, XL
+ veor XL, XL, T1
+ vshr.u64 T1, T1, #6
+ vshr.u64 XL, XL, #1
+ .endm
+
+ .macro ghash_update, pn
vld1.64 {XL}, [r1]
- vmov.i8 MASK, #0xe1
- vext.8 SHASH2, SHASH, SHASH, #8
- vshl.u64 MASK, MASK, #57
- veor SHASH2, SHASH2, SHASH
/* do the head block first, if supplied */
ldr ip, [sp]
@@ -62,33 +184,59 @@ ENTRY(pmull_ghash_update)
#ifndef CONFIG_CPU_BIG_ENDIAN
vrev64.8 T1, T1
#endif
- vext.8 T2, XL, XL, #8
vext.8 IN1, T1, T1, #8
- veor T1, T1, T2
+ veor T1_L, T1_L, XL_H
veor XL, XL, IN1
- vmull.p64 XH, SHASH_H, XL_H @ a1 * b1
+ __pmull_\pn XH, XL_H, SHASH_H, s1h, s2h, s3h, s4h @ a1 * b1
veor T1, T1, XL
- vmull.p64 XL, SHASH_L, XL_L @ a0 * b0
- vmull.p64 XM, SHASH2_L, T1_L @ (a1 + a0)(b1 + b0)
+ __pmull_\pn XL, XL_L, SHASH_L, s1l, s2l, s3l, s4l @ a0 * b0
+ __pmull_\pn XM, T1_L, SHASH2_\pn @ (a1+a0)(b1+b0)
- vext.8 T1, XL, XH, #8
- veor T2, XL, XH
+ veor T1, XL, XH
veor XM, XM, T1
- veor XM, XM, T2
- vmull.p64 T2, XL_L, MASK_L
- vmov XH_L, XM_H
- vmov XM_H, XL_L
+ __pmull_reduce_\pn
- veor XL, XM, T2
- vext.8 T2, XL, XL, #8
- vmull.p64 XL, XL_L, MASK_L
- veor T2, T2, XH
- veor XL, XL, T2
+ veor T1, T1, XH
+ veor XL, XL, T1
bne 0b
vst1.64 {XL}, [r1]
bx lr
-ENDPROC(pmull_ghash_update)
+ .endm
+
+ /*
+ * void pmull_ghash_update(int blocks, u64 dg[], const char *src,
+ * struct ghash_key const *k, const char *head)
+ */
+ENTRY(pmull_ghash_update_p64)
+ vld1.64 {SHASH}, [r3]
+ veor SHASH2_p64, SHASH_L, SHASH_H
+
+ vmov.i8 MASK, #0xe1
+ vshl.u64 MASK, MASK, #57
+
+ ghash_update p64
+ENDPROC(pmull_ghash_update_p64)
+
+ENTRY(pmull_ghash_update_p8)
+ vld1.64 {SHASH}, [r3]
+ veor SHASH2_p8, SHASH_L, SHASH_H
+
+ vext.8 s1l, SHASH_L, SHASH_L, #1
+ vext.8 s2l, SHASH_L, SHASH_L, #2
+ vext.8 s3l, SHASH_L, SHASH_L, #3
+ vext.8 s4l, SHASH_L, SHASH_L, #4
+ vext.8 s1h, SHASH_H, SHASH_H, #1
+ vext.8 s2h, SHASH_H, SHASH_H, #2
+ vext.8 s3h, SHASH_H, SHASH_H, #3
+ vext.8 s4h, SHASH_H, SHASH_H, #4
+
+ vmov.i64 k16, #0xffff
+ vmov.i64 k32, #0xffffffff
+ vmov.i64 k48, #0xffffffffffff
+
+ ghash_update p8
+ENDPROC(pmull_ghash_update_p8)
diff --git a/arch/arm/crypto/ghash-ce-glue.c b/arch/arm/crypto/ghash-ce-glue.c
index 6bac8bea9f1e..d9bb52cae2ac 100644
--- a/arch/arm/crypto/ghash-ce-glue.c
+++ b/arch/arm/crypto/ghash-ce-glue.c
@@ -22,6 +22,7 @@
MODULE_DESCRIPTION("GHASH secure hash using ARMv8 Crypto Extensions");
MODULE_AUTHOR("Ard Biesheuvel <ard.biesheuvel@linaro.org>");
MODULE_LICENSE("GPL v2");
+MODULE_ALIAS_CRYPTO("ghash");
#define GHASH_BLOCK_SIZE 16
#define GHASH_DIGEST_SIZE 16
@@ -41,8 +42,17 @@ struct ghash_async_ctx {
struct cryptd_ahash *cryptd_tfm;
};
-asmlinkage void pmull_ghash_update(int blocks, u64 dg[], const char *src,
- struct ghash_key const *k, const char *head);
+asmlinkage void pmull_ghash_update_p64(int blocks, u64 dg[], const char *src,
+ struct ghash_key const *k,
+ const char *head);
+
+asmlinkage void pmull_ghash_update_p8(int blocks, u64 dg[], const char *src,
+ struct ghash_key const *k,
+ const char *head);
+
+static void (*pmull_ghash_update)(int blocks, u64 dg[], const char *src,
+ struct ghash_key const *k,
+ const char *head);
static int ghash_init(struct shash_desc *desc)
{
@@ -312,6 +322,14 @@ static int __init ghash_ce_mod_init(void)
{
int err;
+ if (!(elf_hwcap & HWCAP_NEON))
+ return -ENODEV;
+
+ if (elf_hwcap2 & HWCAP2_PMULL)
+ pmull_ghash_update = pmull_ghash_update_p64;
+ else
+ pmull_ghash_update = pmull_ghash_update_p8;
+
err = crypto_register_shash(&ghash_alg);
if (err)
return err;
@@ -332,5 +350,5 @@ static void __exit ghash_ce_mod_exit(void)
crypto_unregister_shash(&ghash_alg);
}
-module_cpu_feature_match(PMULL, ghash_ce_mod_init);
+module_init(ghash_ce_mod_init);
module_exit(ghash_ce_mod_exit);
diff --git a/arch/arm/include/asm/arch_gicv3.h b/arch/arm/include/asm/arch_gicv3.h
index 27475904e096..eee269321923 100644
--- a/arch/arm/include/asm/arch_gicv3.h
+++ b/arch/arm/include/asm/arch_gicv3.h
@@ -276,6 +276,12 @@ static inline u64 __gic_readq_nonatomic(const volatile void __iomem *addr)
#define gicr_write_pendbaser(v, c) __gic_writeq_nonatomic(v, c)
/*
+ * GICR_xLPIR - only the lower bits are significant
+ */
+#define gic_read_lpir(c) readl_relaxed(c)
+#define gic_write_lpir(v, c) writel_relaxed(lower_32_bits(v), c)
+
+/*
* GITS_TYPER is an ID register and doesn't need atomicity.
*/
#define gits_read_typer(c) __gic_readq_nonatomic(c)
@@ -291,5 +297,33 @@ static inline u64 __gic_readq_nonatomic(const volatile void __iomem *addr)
*/
#define gits_write_cwriter(v, c) __gic_writeq_nonatomic(v, c)
+/*
+ * GITS_VPROPBASER - hi and lo bits may be accessed independently.
+ */
+#define gits_write_vpropbaser(v, c) __gic_writeq_nonatomic(v, c)
+
+/*
+ * GITS_VPENDBASER - the Valid bit must be cleared before changing
+ * anything else.
+ */
+static inline void gits_write_vpendbaser(u64 val, void * __iomem addr)
+{
+ u32 tmp;
+
+ tmp = readl_relaxed(addr + 4);
+ if (tmp & (GICR_VPENDBASER_Valid >> 32)) {
+ tmp &= ~(GICR_VPENDBASER_Valid >> 32);
+ writel_relaxed(tmp, addr + 4);
+ }
+
+ /*
+ * Use the fact that __gic_writeq_nonatomic writes the second
+ * half of the 64bit quantity after the first.
+ */
+ __gic_writeq_nonatomic(val, addr);
+}
+
+#define gits_read_vpendbaser(c) __gic_readq_nonatomic(c)
+
#endif /* !__ASSEMBLY__ */
#endif /* !__ASM_ARCH_GICV3_H */
diff --git a/arch/arm/include/asm/futex.h b/arch/arm/include/asm/futex.h
index 6795368ad023..cc414382dab4 100644
--- a/arch/arm/include/asm/futex.h
+++ b/arch/arm/include/asm/futex.h
@@ -128,20 +128,10 @@ futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr,
#endif /* !SMP */
static inline int
-futex_atomic_op_inuser (int encoded_op, u32 __user *uaddr)
+arch_futex_atomic_op_inuser(int op, int oparg, int *oval, u32 __user *uaddr)
{
- int op = (encoded_op >> 28) & 7;
- int cmp = (encoded_op >> 24) & 15;
- int oparg = (encoded_op << 8) >> 20;
- int cmparg = (encoded_op << 20) >> 20;
int oldval = 0, ret, tmp;
- if (encoded_op & (FUTEX_OP_OPARG_SHIFT << 28))
- oparg = 1 << oparg;
-
- if (!access_ok(VERIFY_WRITE, uaddr, sizeof(u32)))
- return -EFAULT;
-
#ifndef CONFIG_SMP
preempt_disable();
#endif
@@ -172,17 +162,9 @@ futex_atomic_op_inuser (int encoded_op, u32 __user *uaddr)
preempt_enable();
#endif
- if (!ret) {
- switch (cmp) {
- case FUTEX_OP_CMP_EQ: ret = (oldval == cmparg); break;
- case FUTEX_OP_CMP_NE: ret = (oldval != cmparg); break;
- case FUTEX_OP_CMP_LT: ret = (oldval < cmparg); break;
- case FUTEX_OP_CMP_GE: ret = (oldval >= cmparg); break;
- case FUTEX_OP_CMP_LE: ret = (oldval <= cmparg); break;
- case FUTEX_OP_CMP_GT: ret = (oldval > cmparg); break;
- default: ret = -ENOSYS;
- }
- }
+ if (!ret)
+ *oval = oldval;
+
return ret;
}
diff --git a/arch/arm/include/asm/spinlock.h b/arch/arm/include/asm/spinlock.h
index 4bec45442072..c030143c18c6 100644
--- a/arch/arm/include/asm/spinlock.h
+++ b/arch/arm/include/asm/spinlock.h
@@ -52,22 +52,6 @@ static inline void dsb_sev(void)
* memory.
*/
-static inline void arch_spin_unlock_wait(arch_spinlock_t *lock)
-{
- u16 owner = READ_ONCE(lock->tickets.owner);
-
- for (;;) {
- arch_spinlock_t tmp = READ_ONCE(*lock);
-
- if (tmp.tickets.owner == tmp.tickets.next ||
- tmp.tickets.owner != owner)
- break;
-
- wfe();
- }
- smp_acquire__after_ctrl_dep();
-}
-
#define arch_spin_lock_flags(lock, flags) arch_spin_lock(lock)
static inline void arch_spin_lock(arch_spinlock_t *lock)
diff --git a/arch/arm/include/asm/thread_info.h b/arch/arm/include/asm/thread_info.h
index 776757d1604a..1d468b527b7b 100644
--- a/arch/arm/include/asm/thread_info.h
+++ b/arch/arm/include/asm/thread_info.h
@@ -139,10 +139,11 @@ extern int vfp_restore_user_hwstate(struct user_vfp __user *,
#define TIF_NEED_RESCHED 1 /* rescheduling necessary */
#define TIF_NOTIFY_RESUME 2 /* callback before returning to user */
#define TIF_UPROBE 3 /* breakpointed or singlestepping */
-#define TIF_SYSCALL_TRACE 4 /* syscall trace active */
-#define TIF_SYSCALL_AUDIT 5 /* syscall auditing active */
-#define TIF_SYSCALL_TRACEPOINT 6 /* syscall tracepoint instrumentation */
-#define TIF_SECCOMP 7 /* seccomp syscall filtering active */
+#define TIF_FSCHECK 4 /* Check FS is USER_DS on return */
+#define TIF_SYSCALL_TRACE 5 /* syscall trace active */
+#define TIF_SYSCALL_AUDIT 6 /* syscall auditing active */
+#define TIF_SYSCALL_TRACEPOINT 7 /* syscall tracepoint instrumentation */
+#define TIF_SECCOMP 8 /* seccomp syscall filtering active */
#define TIF_NOHZ 12 /* in adaptive nohz mode */
#define TIF_USING_IWMMXT 17
@@ -153,6 +154,7 @@ extern int vfp_restore_user_hwstate(struct user_vfp __user *,
#define _TIF_NEED_RESCHED (1 << TIF_NEED_RESCHED)
#define _TIF_NOTIFY_RESUME (1 << TIF_NOTIFY_RESUME)
#define _TIF_UPROBE (1 << TIF_UPROBE)
+#define _TIF_FSCHECK (1 << TIF_FSCHECK)
#define _TIF_SYSCALL_TRACE (1 << TIF_SYSCALL_TRACE)
#define _TIF_SYSCALL_AUDIT (1 << TIF_SYSCALL_AUDIT)
#define _TIF_SYSCALL_TRACEPOINT (1 << TIF_SYSCALL_TRACEPOINT)
@@ -166,8 +168,9 @@ extern int vfp_restore_user_hwstate(struct user_vfp __user *,
/*
* Change these and you break ASM code in entry-common.S
*/
-#define _TIF_WORK_MASK (_TIF_NEED_RESCHED | _TIF_SIGPENDING | \
- _TIF_NOTIFY_RESUME | _TIF_UPROBE)
+#define _TIF_WORK_MASK (_TIF_NEED_RESCHED | _TIF_SIGPENDING | \
+ _TIF_NOTIFY_RESUME | _TIF_UPROBE | \
+ _TIF_FSCHECK)
#endif /* __KERNEL__ */
#endif /* __ASM_ARM_THREAD_INFO_H */
diff --git a/arch/arm/include/asm/traps.h b/arch/arm/include/asm/traps.h
index f555bb3664dc..683d9230984a 100644
--- a/arch/arm/include/asm/traps.h
+++ b/arch/arm/include/asm/traps.h
@@ -18,7 +18,6 @@ struct undef_hook {
void register_undef_hook(struct undef_hook *hook);
void unregister_undef_hook(struct undef_hook *hook);
-#ifdef CONFIG_FUNCTION_GRAPH_TRACER
static inline int __in_irqentry_text(unsigned long ptr)
{
extern char __irqentry_text_start[];
@@ -27,12 +26,6 @@ static inline int __in_irqentry_text(unsigned long ptr)
return ptr >= (unsigned long)&__irqentry_text_start &&
ptr < (unsigned long)&__irqentry_text_end;
}
-#else
-static inline int __in_irqentry_text(unsigned long ptr)
-{
- return 0;
-}
-#endif
static inline int in_exception_text(unsigned long ptr)
{
diff --git a/arch/arm/include/asm/uaccess.h b/arch/arm/include/asm/uaccess.h
index 0bf2347495f1..87936dd5d151 100644
--- a/arch/arm/include/asm/uaccess.h
+++ b/arch/arm/include/asm/uaccess.h
@@ -70,6 +70,8 @@ static inline void set_fs(mm_segment_t fs)
{
current_thread_info()->addr_limit = fs;
modify_domain(DOMAIN_KERNEL, fs ? DOMAIN_CLIENT : DOMAIN_MANAGER);
+ /* On user-mode return, check fs is correct */
+ set_thread_flag(TIF_FSCHECK);
}
#define segment_eq(a, b) ((a) == (b))
diff --git a/arch/arm/kernel/entry-common.S b/arch/arm/kernel/entry-common.S
index eb5cd77bf1d8..e33c32d56193 100644
--- a/arch/arm/kernel/entry-common.S
+++ b/arch/arm/kernel/entry-common.S
@@ -41,7 +41,9 @@ ret_fast_syscall:
UNWIND(.cantunwind )
disable_irq_notrace @ disable interrupts
ldr r1, [tsk, #TI_FLAGS] @ re-check for syscall tracing
- tst r1, #_TIF_SYSCALL_WORK | _TIF_WORK_MASK
+ tst r1, #_TIF_SYSCALL_WORK
+ bne fast_work_pending
+ tst r1, #_TIF_WORK_MASK
bne fast_work_pending
/* perform architecture specific actions before user return */
@@ -67,12 +69,15 @@ ret_fast_syscall:
str r0, [sp, #S_R0 + S_OFF]! @ save returned r0
disable_irq_notrace @ disable interrupts
ldr r1, [tsk, #TI_FLAGS] @ re-check for syscall tracing
- tst r1, #_TIF_SYSCALL_WORK | _TIF_WORK_MASK
+ tst r1, #_TIF_SYSCALL_WORK
+ bne fast_work_pending
+ tst r1, #_TIF_WORK_MASK
beq no_work_pending
UNWIND(.fnend )
ENDPROC(ret_fast_syscall)
/* Slower path - fall through to work_pending */
+fast_work_pending:
#endif
tst r1, #_TIF_SYSCALL_WORK
diff --git a/arch/arm/kernel/signal.c b/arch/arm/kernel/signal.c
index 5814298ef0b7..e2de50bf8742 100644
--- a/arch/arm/kernel/signal.c
+++ b/arch/arm/kernel/signal.c
@@ -14,6 +14,7 @@
#include <linux/uaccess.h>
#include <linux/tracehook.h>
#include <linux/uprobes.h>
+#include <linux/syscalls.h>
#include <asm/elf.h>
#include <asm/cacheflush.h>
@@ -613,6 +614,10 @@ do_work_pending(struct pt_regs *regs, unsigned int thread_flags, int syscall)
* Update the trace code with the current status.
*/
trace_hardirqs_off();
+
+ /* Check valid user FS if needed */
+ addr_limit_user_check();
+
do {
if (likely(thread_flags & _TIF_NEED_RESCHED)) {
schedule();
diff --git a/arch/arm/mach-hisi/Kconfig b/arch/arm/mach-hisi/Kconfig
index a3b091a4d344..65a048fa08ec 100644
--- a/arch/arm/mach-hisi/Kconfig
+++ b/arch/arm/mach-hisi/Kconfig
@@ -39,6 +39,7 @@ config ARCH_HIP04
select HAVE_ARM_ARCH_TIMER
select MCPM if SMP
select MCPM_QUAD_CLUSTER if SMP
+ select GENERIC_IRQ_EFFECTIVE_AFF_MASK
help
Support for Hisilicon HiP04 SoC family
diff --git a/arch/arm/mach-omap2/Makefile b/arch/arm/mach-omap2/Makefile
index 779fb1f680b3..b3b3b3a19183 100644
--- a/arch/arm/mach-omap2/Makefile
+++ b/arch/arm/mach-omap2/Makefile
@@ -8,7 +8,7 @@ ccflags-y := -I$(srctree)/$(src)/include \
# Common support
obj-y := id.o io.o control.o devices.o fb.o timer.o pm.o \
common.o dma.o wd_timer.o display.o i2c.o hdq1w.o omap_hwmod.o \
- omap_device.o omap-headsmp.o sram.o drm.o
+ omap_device.o omap-headsmp.o sram.o
hwmod-common = omap_hwmod.o omap_hwmod_reset.o \
omap_hwmod_common_data.o
diff --git a/arch/arm/mach-omap2/board-generic.c b/arch/arm/mach-omap2/board-generic.c
index b1e661bb5521..583fc39d84cd 100644
--- a/arch/arm/mach-omap2/board-generic.c
+++ b/arch/arm/mach-omap2/board-generic.c
@@ -33,6 +33,7 @@ static void __init __maybe_unused omap_generic_init(void)
pdata_quirks_init(omap_dt_match_table);
omapdss_init_of();
+ omap_soc_device_init();
}
#ifdef CONFIG_SOC_OMAP2420
diff --git a/arch/arm/mach-omap2/display.c b/arch/arm/mach-omap2/display.c
index 8fa01c0ecdb2..b3f6eb5d04a2 100644
--- a/arch/arm/mach-omap2/display.c
+++ b/arch/arm/mach-omap2/display.c
@@ -66,6 +66,7 @@
*/
#define FRAMEDONE_IRQ_TIMEOUT 100
+#if defined(CONFIG_FB_OMAP2)
static struct platform_device omap_display_device = {
.name = "omapdss",
.id = -1,
@@ -163,6 +164,65 @@ static enum omapdss_version __init omap_display_get_version(void)
return OMAPDSS_VER_UNKNOWN;
}
+static int __init omapdss_init_fbdev(void)
+{
+ static struct omap_dss_board_info board_data = {
+ .dsi_enable_pads = omap_dsi_enable_pads,
+ .dsi_disable_pads = omap_dsi_disable_pads,
+ .set_min_bus_tput = omap_dss_set_min_bus_tput,
+ };
+ struct device_node *node;
+ int r;
+
+ board_data.version = omap_display_get_version();
+ if (board_data.version == OMAPDSS_VER_UNKNOWN) {
+ pr_err("DSS not supported on this SoC\n");
+ return -ENODEV;
+ }
+
+ omap_display_device.dev.platform_data = &board_data;
+
+ r = platform_device_register(&omap_display_device);
+ if (r < 0) {
+ pr_err("Unable to register omapdss device\n");
+ return r;
+ }
+
+ /* create vrfb device */
+ r = omap_init_vrfb();
+ if (r < 0) {
+ pr_err("Unable to register omapvrfb device\n");
+ return r;
+ }
+
+ /* create FB device */
+ r = omap_init_fb();
+ if (r < 0) {
+ pr_err("Unable to register omapfb device\n");
+ return r;
+ }
+
+ /* create V4L2 display device */
+ r = omap_init_vout();
+ if (r < 0) {
+ pr_err("Unable to register omap_vout device\n");
+ return r;
+ }
+
+ /* add DSI info for omap4 */
+ node = of_find_node_by_name(NULL, "omap4_padconf_global");
+ if (node)
+ omap4_dsi_mux_syscon = syscon_node_to_regmap(node);
+
+ return 0;
+}
+#else
+static inline int omapdss_init_fbdev(void)
+{
+ return 0;
+}
+#endif /* CONFIG_FB_OMAP2 */
+
static void dispc_disable_outputs(void)
{
u32 v, irq_mask = 0;
@@ -335,16 +395,9 @@ static struct device_node * __init omapdss_find_dss_of_node(void)
int __init omapdss_init_of(void)
{
int r;
- enum omapdss_version ver;
struct device_node *node;
struct platform_device *pdev;
- static struct omap_dss_board_info board_data = {
- .dsi_enable_pads = omap_dsi_enable_pads,
- .dsi_disable_pads = omap_dsi_disable_pads,
- .set_min_bus_tput = omap_dss_set_min_bus_tput,
- };
-
/* only create dss helper devices if dss is enabled in the .dts */
node = omapdss_find_dss_of_node();
@@ -354,13 +407,6 @@ int __init omapdss_init_of(void)
if (!of_device_is_available(node))
return 0;
- ver = omap_display_get_version();
-
- if (ver == OMAPDSS_VER_UNKNOWN) {
- pr_err("DSS not supported on this SoC\n");
- return -ENODEV;
- }
-
pdev = of_find_device_by_node(node);
if (!pdev) {
@@ -374,48 +420,5 @@ int __init omapdss_init_of(void)
return r;
}
- board_data.version = ver;
-
- omap_display_device.dev.platform_data = &board_data;
-
- r = platform_device_register(&omap_display_device);
- if (r < 0) {
- pr_err("Unable to register omapdss device\n");
- return r;
- }
-
- /* create DRM device */
- r = omap_init_drm();
- if (r < 0) {
- pr_err("Unable to register omapdrm device\n");
- return r;
- }
-
- /* create vrfb device */
- r = omap_init_vrfb();
- if (r < 0) {
- pr_err("Unable to register omapvrfb device\n");
- return r;
- }
-
- /* create FB device */
- r = omap_init_fb();
- if (r < 0) {
- pr_err("Unable to register omapfb device\n");
- return r;
- }
-
- /* create V4L2 display device */
- r = omap_init_vout();
- if (r < 0) {
- pr_err("Unable to register omap_vout device\n");
- return r;
- }
-
- /* add DSI info for omap4 */
- node = of_find_node_by_name(NULL, "omap4_padconf_global");
- if (node)
- omap4_dsi_mux_syscon = syscon_node_to_regmap(node);
-
- return 0;
+ return omapdss_init_fbdev();
}
diff --git a/arch/arm/mach-omap2/display.h b/arch/arm/mach-omap2/display.h
index 9a39646d4316..42ec2e99a2f4 100644
--- a/arch/arm/mach-omap2/display.h
+++ b/arch/arm/mach-omap2/display.h
@@ -26,7 +26,6 @@ struct omap_dss_dispc_dev_attr {
bool has_framedonetv_irq;
};
-int omap_init_drm(void);
int omap_init_vrfb(void);
int omap_init_fb(void);
int omap_init_vout(void);
diff --git a/arch/arm/mach-omap2/drm.c b/arch/arm/mach-omap2/drm.c
deleted file mode 100644
index 44fef961bb70..000000000000
--- a/arch/arm/mach-omap2/drm.c
+++ /dev/null
@@ -1,53 +0,0 @@
-/*
- * DRM/KMS device registration for TI OMAP platforms
- *
- * Copyright (C) 2012 Texas Instruments
- * Author: Rob Clark <rob.clark@linaro.org>
- *
- * 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.
- *
- * This program is distributed in the hope that it will be useful, but WITHOUT
- * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
- * more details.
- *
- * You should have received a copy of the GNU General Public License along with
- * this program. If not, see <http://www.gnu.org/licenses/>.
- */
-
-#include <linux/module.h>
-#include <linux/kernel.h>
-#include <linux/mm.h>
-#include <linux/init.h>
-#include <linux/platform_device.h>
-#include <linux/dma-mapping.h>
-#include <linux/platform_data/omap_drm.h>
-
-#include "soc.h"
-#include "display.h"
-
-#if IS_ENABLED(CONFIG_DRM_OMAP)
-
-static struct omap_drm_platform_data platform_data;
-
-static struct platform_device omap_drm_device = {
- .dev = {
- .coherent_dma_mask = DMA_BIT_MASK(32),
- .platform_data = &platform_data,
- },
- .name = "omapdrm",
- .id = 0,
-};
-
-int __init omap_init_drm(void)
-{
- platform_data.omaprev = GET_OMAP_TYPE;
-
- return platform_device_register(&omap_drm_device);
-
-}
-#else
-int __init omap_init_drm(void) { return 0; }
-#endif
diff --git a/arch/arm/mach-omap2/io.c b/arch/arm/mach-omap2/io.c
index 1cd20e4d56b0..cb5d7314cf99 100644
--- a/arch/arm/mach-omap2/io.c
+++ b/arch/arm/mach-omap2/io.c
@@ -428,7 +428,6 @@ static void __init __maybe_unused omap_hwmod_init_postsetup(void)
static void __init __maybe_unused omap_common_late_init(void)
{
omap2_common_pm_late_init();
- omap_soc_device_init();
}
#ifdef CONFIG_SOC_OMAP2420
diff --git a/arch/arm/mach-pxa/raumfeld.c b/arch/arm/mach-pxa/raumfeld.c
index e2c97728b3c6..9d662fed03ec 100644
--- a/arch/arm/mach-pxa/raumfeld.c
+++ b/arch/arm/mach-pxa/raumfeld.c
@@ -377,7 +377,7 @@ static struct gpiod_lookup_table raumfeld_rotary_gpios_table = {
},
};
-static struct property_entry raumfeld_rotary_properties[] = {
+static const struct property_entry raumfeld_rotary_properties[] __initconst = {
PROPERTY_ENTRY_INTEGER("rotary-encoder,steps-per-period", u32, 24),
PROPERTY_ENTRY_INTEGER("linux,axis", u32, REL_X),
PROPERTY_ENTRY_INTEGER("rotary-encoder,relative_axis", u32, 1),
diff --git a/arch/arm/mach-tegra/cpuidle-tegra114.c b/arch/arm/mach-tegra/cpuidle-tegra114.c
index d3aa9be16621..e3fbcfedf845 100644
--- a/arch/arm/mach-tegra/cpuidle-tegra114.c
+++ b/arch/arm/mach-tegra/cpuidle-tegra114.c
@@ -60,7 +60,7 @@ static int tegra114_idle_power_down(struct cpuidle_device *dev,
return index;
}
-static void tegra114_idle_enter_freeze(struct cpuidle_device *dev,
+static void tegra114_idle_enter_s2idle(struct cpuidle_device *dev,
struct cpuidle_driver *drv,
int index)
{
@@ -77,7 +77,7 @@ static struct cpuidle_driver tegra_idle_driver = {
#ifdef CONFIG_PM_SLEEP
[1] = {
.enter = tegra114_idle_power_down,
- .enter_freeze = tegra114_idle_enter_freeze,
+ .enter_s2idle = tegra114_idle_enter_s2idle,
.exit_latency = 500,
.target_residency = 1000,
.flags = CPUIDLE_FLAG_TIMER_STOP,
diff --git a/arch/arm/net/bpf_jit_32.c b/arch/arm/net/bpf_jit_32.c
index d5b9fa19b684..c199990e12b6 100644
--- a/arch/arm/net/bpf_jit_32.c
+++ b/arch/arm/net/bpf_jit_32.c
@@ -1,6 +1,7 @@
/*
- * Just-In-Time compiler for BPF filters on 32bit ARM
+ * Just-In-Time compiler for eBPF filters on 32bit ARM
*
+ * Copyright (c) 2017 Shubham Bansal <illusionist.neo@gmail.com>
* Copyright (c) 2011 Mircea Gherzan <mgherzan@gmail.com>
*
* This program is free software; you can redistribute it and/or modify it
@@ -8,6 +9,7 @@
* Free Software Foundation; version 2 of the License.
*/
+#include <linux/bpf.h>
#include <linux/bitops.h>
#include <linux/compiler.h>
#include <linux/errno.h>
@@ -18,54 +20,101 @@
#include <linux/if_vlan.h>
#include <asm/cacheflush.h>
-#include <asm/set_memory.h>
#include <asm/hwcap.h>
#include <asm/opcodes.h>
#include "bpf_jit_32.h"
+int bpf_jit_enable __read_mostly;
+
+#define STACK_OFFSET(k) (k)
+#define TMP_REG_1 (MAX_BPF_JIT_REG + 0) /* TEMP Register 1 */
+#define TMP_REG_2 (MAX_BPF_JIT_REG + 1) /* TEMP Register 2 */
+#define TCALL_CNT (MAX_BPF_JIT_REG + 2) /* Tail Call Count */
+
+/* Flags used for JIT optimization */
+#define SEEN_CALL (1 << 0)
+
+#define FLAG_IMM_OVERFLOW (1 << 0)
+
/*
- * ABI:
+ * Map eBPF registers to ARM 32bit registers or stack scratch space.
+ *
+ * 1. First argument is passed using the arm 32bit registers and rest of the
+ * arguments are passed on stack scratch space.
+ * 2. First callee-saved arugument is mapped to arm 32 bit registers and rest
+ * arguments are mapped to scratch space on stack.
+ * 3. We need two 64 bit temp registers to do complex operations on eBPF
+ * registers.
+ *
+ * As the eBPF registers are all 64 bit registers and arm has only 32 bit
+ * registers, we have to map each eBPF registers with two arm 32 bit regs or
+ * scratch memory space and we have to build eBPF 64 bit register from those.
*
- * r0 scratch register
- * r4 BPF register A
- * r5 BPF register X
- * r6 pointer to the skb
- * r7 skb->data
- * r8 skb_headlen(skb)
*/
+static const u8 bpf2a32[][2] = {
+ /* return value from in-kernel function, and exit value from eBPF */
+ [BPF_REG_0] = {ARM_R1, ARM_R0},
+ /* arguments from eBPF program to in-kernel function */
+ [BPF_REG_1] = {ARM_R3, ARM_R2},
+ /* Stored on stack scratch space */
+ [BPF_REG_2] = {STACK_OFFSET(0), STACK_OFFSET(4)},
+ [BPF_REG_3] = {STACK_OFFSET(8), STACK_OFFSET(12)},
+ [BPF_REG_4] = {STACK_OFFSET(16), STACK_OFFSET(20)},
+ [BPF_REG_5] = {STACK_OFFSET(24), STACK_OFFSET(28)},
+ /* callee saved registers that in-kernel function will preserve */
+ [BPF_REG_6] = {ARM_R5, ARM_R4},
+ /* Stored on stack scratch space */
+ [BPF_REG_7] = {STACK_OFFSET(32), STACK_OFFSET(36)},
+ [BPF_REG_8] = {STACK_OFFSET(40), STACK_OFFSET(44)},
+ [BPF_REG_9] = {STACK_OFFSET(48), STACK_OFFSET(52)},
+ /* Read only Frame Pointer to access Stack */
+ [BPF_REG_FP] = {STACK_OFFSET(56), STACK_OFFSET(60)},
+ /* Temporary Register for internal BPF JIT, can be used
+ * for constant blindings and others.
+ */
+ [TMP_REG_1] = {ARM_R7, ARM_R6},
+ [TMP_REG_2] = {ARM_R10, ARM_R8},
+ /* Tail call count. Stored on stack scratch space. */
+ [TCALL_CNT] = {STACK_OFFSET(64), STACK_OFFSET(68)},
+ /* temporary register for blinding constants.
+ * Stored on stack scratch space.
+ */
+ [BPF_REG_AX] = {STACK_OFFSET(72), STACK_OFFSET(76)},
+};
-#define r_scratch ARM_R0
-/* r1-r3 are (also) used for the unaligned loads on the non-ARMv7 slowpath */
-#define r_off ARM_R1
-#define r_A ARM_R4
-#define r_X ARM_R5
-#define r_skb ARM_R6
-#define r_skb_data ARM_R7
-#define r_skb_hl ARM_R8
-
-#define SCRATCH_SP_OFFSET 0
-#define SCRATCH_OFF(k) (SCRATCH_SP_OFFSET + 4 * (k))
-
-#define SEEN_MEM ((1 << BPF_MEMWORDS) - 1)
-#define SEEN_MEM_WORD(k) (1 << (k))
-#define SEEN_X (1 << BPF_MEMWORDS)
-#define SEEN_CALL (1 << (BPF_MEMWORDS + 1))
-#define SEEN_SKB (1 << (BPF_MEMWORDS + 2))
-#define SEEN_DATA (1 << (BPF_MEMWORDS + 3))
+#define dst_lo dst[1]
+#define dst_hi dst[0]
+#define src_lo src[1]
+#define src_hi src[0]
-#define FLAG_NEED_X_RESET (1 << 0)
-#define FLAG_IMM_OVERFLOW (1 << 1)
+/*
+ * JIT Context:
+ *
+ * prog : bpf_prog
+ * idx : index of current last JITed instruction.
+ * prologue_bytes : bytes used in prologue.
+ * epilogue_offset : offset of epilogue starting.
+ * seen : bit mask used for JIT optimization.
+ * offsets : array of eBPF instruction offsets in
+ * JITed code.
+ * target : final JITed code.
+ * epilogue_bytes : no of bytes used in epilogue.
+ * imm_count : no of immediate counts used for global
+ * variables.
+ * imms : array of global variable addresses.
+ */
struct jit_ctx {
- const struct bpf_prog *skf;
- unsigned idx;
- unsigned prologue_bytes;
- int ret0_fp_idx;
+ const struct bpf_prog *prog;
+ unsigned int idx;
+ unsigned int prologue_bytes;
+ unsigned int epilogue_offset;
u32 seen;
u32 flags;
u32 *offsets;
u32 *target;
+ u32 stack_size;
#if __LINUX_ARM_ARCH__ < 7
u16 epilogue_bytes;
u16 imm_count;
@@ -73,68 +122,16 @@ struct jit_ctx {
#endif
};
-int bpf_jit_enable __read_mostly;
-
-static inline int call_neg_helper(struct sk_buff *skb, int offset, void *ret,
- unsigned int size)
-{
- void *ptr = bpf_internal_load_pointer_neg_helper(skb, offset, size);
-
- if (!ptr)
- return -EFAULT;
- memcpy(ret, ptr, size);
- return 0;
-}
-
-static u64 jit_get_skb_b(struct sk_buff *skb, int offset)
-{
- u8 ret;
- int err;
-
- if (offset < 0)
- err = call_neg_helper(skb, offset, &ret, 1);
- else
- err = skb_copy_bits(skb, offset, &ret, 1);
-
- return (u64)err << 32 | ret;
-}
-
-static u64 jit_get_skb_h(struct sk_buff *skb, int offset)
-{
- u16 ret;
- int err;
-
- if (offset < 0)
- err = call_neg_helper(skb, offset, &ret, 2);
- else
- err = skb_copy_bits(skb, offset, &ret, 2);
-
- return (u64)err << 32 | ntohs(ret);
-}
-
-static u64 jit_get_skb_w(struct sk_buff *skb, int offset)
-{
- u32 ret;
- int err;
-
- if (offset < 0)
- err = call_neg_helper(skb, offset, &ret, 4);
- else
- err = skb_copy_bits(skb, offset, &ret, 4);
-
- return (u64)err << 32 | ntohl(ret);
-}
-
/*
* Wrappers which handle both OABI and EABI and assures Thumb2 interworking
* (where the assembly routines like __aeabi_uidiv could cause problems).
*/
-static u32 jit_udiv(u32 dividend, u32 divisor)
+static u32 jit_udiv32(u32 dividend, u32 divisor)
{
return dividend / divisor;
}
-static u32 jit_mod(u32 dividend, u32 divisor)
+static u32 jit_mod32(u32 dividend, u32 divisor)
{
return dividend % divisor;
}
@@ -158,36 +155,22 @@ static inline void emit(u32 inst, struct jit_ctx *ctx)
_emit(ARM_COND_AL, inst, ctx);
}
-static u16 saved_regs(struct jit_ctx *ctx)
+/*
+ * Checks if immediate value can be converted to imm12(12 bits) value.
+ */
+static int16_t imm8m(u32 x)
{
- u16 ret = 0;
-
- if ((ctx->skf->len > 1) ||
- (ctx->skf->insns[0].code == (BPF_RET | BPF_A)))
- ret |= 1 << r_A;
-
-#ifdef CONFIG_FRAME_POINTER
- ret |= (1 << ARM_FP) | (1 << ARM_IP) | (1 << ARM_LR) | (1 << ARM_PC);
-#else
- if (ctx->seen & SEEN_CALL)
- ret |= 1 << ARM_LR;
-#endif
- if (ctx->seen & (SEEN_DATA | SEEN_SKB))
- ret |= 1 << r_skb;
- if (ctx->seen & SEEN_DATA)
- ret |= (1 << r_skb_data) | (1 << r_skb_hl);
- if (ctx->seen & SEEN_X)
- ret |= 1 << r_X;
-
- return ret;
-}
+ u32 rot;
-static inline int mem_words_used(struct jit_ctx *ctx)
-{
- /* yes, we do waste some stack space IF there are "holes" in the set" */
- return fls(ctx->seen & SEEN_MEM);
+ for (rot = 0; rot < 16; rot++)
+ if ((x & ~ror32(0xff, 2 * rot)) == 0)
+ return rol32(x, 2 * rot) | (rot << 8);
+ return -1;
}
+/*
+ * Initializes the JIT space with undefined instructions.
+ */
static void jit_fill_hole(void *area, unsigned int size)
{
u32 *ptr;
@@ -196,88 +179,34 @@ static void jit_fill_hole(void *area, unsigned int size)
*ptr++ = __opcode_to_mem_arm(ARM_INST_UDF);
}
-static void build_prologue(struct jit_ctx *ctx)
-{
- u16 reg_set = saved_regs(ctx);
- u16 off;
-
-#ifdef CONFIG_FRAME_POINTER
- emit(ARM_MOV_R(ARM_IP, ARM_SP), ctx);
- emit(ARM_PUSH(reg_set), ctx);
- emit(ARM_SUB_I(ARM_FP, ARM_IP, 4), ctx);
-#else
- if (reg_set)
- emit(ARM_PUSH(reg_set), ctx);
-#endif
-
- if (ctx->seen & (SEEN_DATA | SEEN_SKB))
- emit(ARM_MOV_R(r_skb, ARM_R0), ctx);
-
- if (ctx->seen & SEEN_DATA) {
- off = offsetof(struct sk_buff, data);
- emit(ARM_LDR_I(r_skb_data, r_skb, off), ctx);
- /* headlen = len - data_len */
- off = offsetof(struct sk_buff, len);
- emit(ARM_LDR_I(r_skb_hl, r_skb, off), ctx);
- off = offsetof(struct sk_buff, data_len);
- emit(ARM_LDR_I(r_scratch, r_skb, off), ctx);
- emit(ARM_SUB_R(r_skb_hl, r_skb_hl, r_scratch), ctx);
- }
-
- if (ctx->flags & FLAG_NEED_X_RESET)
- emit(ARM_MOV_I(r_X, 0), ctx);
-
- /* do not leak kernel data to userspace */
- if (bpf_needs_clear_a(&ctx->skf->insns[0]))
- emit(ARM_MOV_I(r_A, 0), ctx);
-
- /* stack space for the BPF_MEM words */
- if (ctx->seen & SEEN_MEM)
- emit(ARM_SUB_I(ARM_SP, ARM_SP, mem_words_used(ctx) * 4), ctx);
-}
-
-static void build_epilogue(struct jit_ctx *ctx)
-{
- u16 reg_set = saved_regs(ctx);
-
- if (ctx->seen & SEEN_MEM)
- emit(ARM_ADD_I(ARM_SP, ARM_SP, mem_words_used(ctx) * 4), ctx);
-
- reg_set &= ~(1 << ARM_LR);
+/* Stack must be multiples of 16 Bytes */
+#define STACK_ALIGN(sz) (((sz) + 3) & ~3)
-#ifdef CONFIG_FRAME_POINTER
- /* the first instruction of the prologue was: mov ip, sp */
- reg_set &= ~(1 << ARM_IP);
- reg_set |= (1 << ARM_SP);
- emit(ARM_LDM(ARM_SP, reg_set), ctx);
-#else
- if (reg_set) {
- if (ctx->seen & SEEN_CALL)
- reg_set |= 1 << ARM_PC;
- emit(ARM_POP(reg_set), ctx);
- }
+/* Stack space for BPF_REG_2, BPF_REG_3, BPF_REG_4,
+ * BPF_REG_5, BPF_REG_7, BPF_REG_8, BPF_REG_9,
+ * BPF_REG_FP and Tail call counts.
+ */
+#define SCRATCH_SIZE 80
- if (!(ctx->seen & SEEN_CALL))
- emit(ARM_BX(ARM_LR), ctx);
-#endif
-}
+/* total stack size used in JITed code */
+#define _STACK_SIZE \
+ (ctx->prog->aux->stack_depth + \
+ + SCRATCH_SIZE + \
+ + 4 /* extra for skb_copy_bits buffer */)
-static int16_t imm8m(u32 x)
-{
- u32 rot;
+#define STACK_SIZE STACK_ALIGN(_STACK_SIZE)
- for (rot = 0; rot < 16; rot++)
- if ((x & ~ror32(0xff, 2 * rot)) == 0)
- return rol32(x, 2 * rot) | (rot << 8);
+/* Get the offset of eBPF REGISTERs stored on scratch space. */
+#define STACK_VAR(off) (STACK_SIZE-off-4)
- return -1;
-}
+/* Offset of skb_copy_bits buffer */
+#define SKB_BUFFER STACK_VAR(SCRATCH_SIZE)
#if __LINUX_ARM_ARCH__ < 7
static u16 imm_offset(u32 k, struct jit_ctx *ctx)
{
- unsigned i = 0, offset;
+ unsigned int i = 0, offset;
u16 imm;
/* on the "fake" run we just count them (duplicates included) */
@@ -296,7 +225,7 @@ static u16 imm_offset(u32 k, struct jit_ctx *ctx)
ctx->imms[i] = k;
/* constants go just after the epilogue */
- offset = ctx->offsets[ctx->skf->len];
+ offset = ctx->offsets[ctx->prog->len - 1] * 4;
offset += ctx->prologue_bytes;
offset += ctx->epilogue_bytes;
offset += i * 4;
@@ -320,10 +249,22 @@ static u16 imm_offset(u32 k, struct jit_ctx *ctx)
#endif /* __LINUX_ARM_ARCH__ */
+static inline int bpf2a32_offset(int bpf_to, int bpf_from,
+ const struct jit_ctx *ctx) {
+ int to, from;
+
+ if (ctx->target == NULL)
+ return 0;
+ to = ctx->offsets[bpf_to];
+ from = ctx->offsets[bpf_from];
+
+ return to - from - 1;
+}
+
/*
* Move an immediate that's not an imm8m to a core register.
*/
-static inline void emit_mov_i_no8m(int rd, u32 val, struct jit_ctx *ctx)
+static inline void emit_mov_i_no8m(const u8 rd, u32 val, struct jit_ctx *ctx)
{
#if __LINUX_ARM_ARCH__ < 7
emit(ARM_LDR_I(rd, ARM_PC, imm_offset(val, ctx)), ctx);
@@ -334,7 +275,7 @@ static inline void emit_mov_i_no8m(int rd, u32 val, struct jit_ctx *ctx)
#endif
}
-static inline void emit_mov_i(int rd, u32 val, struct jit_ctx *ctx)
+static inline void emit_mov_i(const u8 rd, u32 val, struct jit_ctx *ctx)
{
int imm12 = imm8m(val);
@@ -344,676 +285,1594 @@ static inline void emit_mov_i(int rd, u32 val, struct jit_ctx *ctx)
emit_mov_i_no8m(rd, val, ctx);
}
-#if __LINUX_ARM_ARCH__ < 6
-
-static void emit_load_be32(u8 cond, u8 r_res, u8 r_addr, struct jit_ctx *ctx)
+static inline void emit_blx_r(u8 tgt_reg, struct jit_ctx *ctx)
{
- _emit(cond, ARM_LDRB_I(ARM_R3, r_addr, 1), ctx);
- _emit(cond, ARM_LDRB_I(ARM_R1, r_addr, 0), ctx);
- _emit(cond, ARM_LDRB_I(ARM_R2, r_addr, 3), ctx);
- _emit(cond, ARM_LSL_I(ARM_R3, ARM_R3, 16), ctx);
- _emit(cond, ARM_LDRB_I(ARM_R0, r_addr, 2), ctx);
- _emit(cond, ARM_ORR_S(ARM_R3, ARM_R3, ARM_R1, SRTYPE_LSL, 24), ctx);
- _emit(cond, ARM_ORR_R(ARM_R3, ARM_R3, ARM_R2), ctx);
- _emit(cond, ARM_ORR_S(r_res, ARM_R3, ARM_R0, SRTYPE_LSL, 8), ctx);
+ ctx->seen |= SEEN_CALL;
+#if __LINUX_ARM_ARCH__ < 5
+ emit(ARM_MOV_R(ARM_LR, ARM_PC), ctx);
+
+ if (elf_hwcap & HWCAP_THUMB)
+ emit(ARM_BX(tgt_reg), ctx);
+ else
+ emit(ARM_MOV_R(ARM_PC, tgt_reg), ctx);
+#else
+ emit(ARM_BLX_R(tgt_reg), ctx);
+#endif
}
-static void emit_load_be16(u8 cond, u8 r_res, u8 r_addr, struct jit_ctx *ctx)
+static inline int epilogue_offset(const struct jit_ctx *ctx)
{
- _emit(cond, ARM_LDRB_I(ARM_R1, r_addr, 0), ctx);
- _emit(cond, ARM_LDRB_I(ARM_R2, r_addr, 1), ctx);
- _emit(cond, ARM_ORR_S(r_res, ARM_R2, ARM_R1, SRTYPE_LSL, 8), ctx);
+ int to, from;
+ /* No need for 1st dummy run */
+ if (ctx->target == NULL)
+ return 0;
+ to = ctx->epilogue_offset;
+ from = ctx->idx;
+
+ return to - from - 2;
}
-static inline void emit_swap16(u8 r_dst, u8 r_src, struct jit_ctx *ctx)
+static inline void emit_udivmod(u8 rd, u8 rm, u8 rn, struct jit_ctx *ctx, u8 op)
{
- /* r_dst = (r_src << 8) | (r_src >> 8) */
- emit(ARM_LSL_I(ARM_R1, r_src, 8), ctx);
- emit(ARM_ORR_S(r_dst, ARM_R1, r_src, SRTYPE_LSR, 8), ctx);
+ const u8 *tmp = bpf2a32[TMP_REG_1];
+ s32 jmp_offset;
+
+ /* checks if divisor is zero or not. If it is, then
+ * exit directly.
+ */
+ emit(ARM_CMP_I(rn, 0), ctx);
+ _emit(ARM_COND_EQ, ARM_MOV_I(ARM_R0, 0), ctx);
+ jmp_offset = epilogue_offset(ctx);
+ _emit(ARM_COND_EQ, ARM_B(jmp_offset), ctx);
+#if __LINUX_ARM_ARCH__ == 7
+ if (elf_hwcap & HWCAP_IDIVA) {
+ if (op == BPF_DIV)
+ emit(ARM_UDIV(rd, rm, rn), ctx);
+ else {
+ emit(ARM_UDIV(ARM_IP, rm, rn), ctx);
+ emit(ARM_MLS(rd, rn, ARM_IP, rm), ctx);
+ }
+ return;
+ }
+#endif
/*
- * we need to mask out the bits set in r_dst[23:16] due to
- * the first shift instruction.
- *
- * note that 0x8ff is the encoded immediate 0x00ff0000.
+ * For BPF_ALU | BPF_DIV | BPF_K instructions
+ * As ARM_R1 and ARM_R0 contains 1st argument of bpf
+ * function, we need to save it on caller side to save
+ * it from getting destroyed within callee.
+ * After the return from the callee, we restore ARM_R0
+ * ARM_R1.
*/
- emit(ARM_BIC_I(r_dst, r_dst, 0x8ff), ctx);
-}
+ if (rn != ARM_R1) {
+ emit(ARM_MOV_R(tmp[0], ARM_R1), ctx);
+ emit(ARM_MOV_R(ARM_R1, rn), ctx);
+ }
+ if (rm != ARM_R0) {
+ emit(ARM_MOV_R(tmp[1], ARM_R0), ctx);
+ emit(ARM_MOV_R(ARM_R0, rm), ctx);
+ }
-#else /* ARMv6+ */
+ /* Call appropriate function */
+ ctx->seen |= SEEN_CALL;
+ emit_mov_i(ARM_IP, op == BPF_DIV ?
+ (u32)jit_udiv32 : (u32)jit_mod32, ctx);
+ emit_blx_r(ARM_IP, ctx);
-static void emit_load_be32(u8 cond, u8 r_res, u8 r_addr, struct jit_ctx *ctx)
-{
- _emit(cond, ARM_LDR_I(r_res, r_addr, 0), ctx);
-#ifdef __LITTLE_ENDIAN
- _emit(cond, ARM_REV(r_res, r_res), ctx);
-#endif
+ /* Save return value */
+ if (rd != ARM_R0)
+ emit(ARM_MOV_R(rd, ARM_R0), ctx);
+
+ /* Restore ARM_R0 and ARM_R1 */
+ if (rn != ARM_R1)
+ emit(ARM_MOV_R(ARM_R1, tmp[0]), ctx);
+ if (rm != ARM_R0)
+ emit(ARM_MOV_R(ARM_R0, tmp[1]), ctx);
}
-static void emit_load_be16(u8 cond, u8 r_res, u8 r_addr, struct jit_ctx *ctx)
+/* Checks whether BPF register is on scratch stack space or not. */
+static inline bool is_on_stack(u8 bpf_reg)
{
- _emit(cond, ARM_LDRH_I(r_res, r_addr, 0), ctx);
-#ifdef __LITTLE_ENDIAN
- _emit(cond, ARM_REV16(r_res, r_res), ctx);
-#endif
+ static u8 stack_regs[] = {BPF_REG_AX, BPF_REG_3, BPF_REG_4, BPF_REG_5,
+ BPF_REG_7, BPF_REG_8, BPF_REG_9, TCALL_CNT,
+ BPF_REG_2, BPF_REG_FP};
+ int i, reg_len = sizeof(stack_regs);
+
+ for (i = 0 ; i < reg_len ; i++) {
+ if (bpf_reg == stack_regs[i])
+ return true;
+ }
+ return false;
}
-static inline void emit_swap16(u8 r_dst __maybe_unused,
- u8 r_src __maybe_unused,
- struct jit_ctx *ctx __maybe_unused)
+static inline void emit_a32_mov_i(const u8 dst, const u32 val,
+ bool dstk, struct jit_ctx *ctx)
{
-#ifdef __LITTLE_ENDIAN
- emit(ARM_REV16(r_dst, r_src), ctx);
-#endif
+ const u8 *tmp = bpf2a32[TMP_REG_1];
+
+ if (dstk) {
+ emit_mov_i(tmp[1], val, ctx);
+ emit(ARM_STR_I(tmp[1], ARM_SP, STACK_VAR(dst)), ctx);
+ } else {
+ emit_mov_i(dst, val, ctx);
+ }
}
-#endif /* __LINUX_ARM_ARCH__ < 6 */
+/* Sign extended move */
+static inline void emit_a32_mov_i64(const bool is64, const u8 dst[],
+ const u32 val, bool dstk,
+ struct jit_ctx *ctx) {
+ u32 hi = 0;
+ if (is64 && (val & (1<<31)))
+ hi = (u32)~0;
+ emit_a32_mov_i(dst_lo, val, dstk, ctx);
+ emit_a32_mov_i(dst_hi, hi, dstk, ctx);
+}
-/* Compute the immediate value for a PC-relative branch. */
-static inline u32 b_imm(unsigned tgt, struct jit_ctx *ctx)
-{
- u32 imm;
+static inline void emit_a32_add_r(const u8 dst, const u8 src,
+ const bool is64, const bool hi,
+ struct jit_ctx *ctx) {
+ /* 64 bit :
+ * adds dst_lo, dst_lo, src_lo
+ * adc dst_hi, dst_hi, src_hi
+ * 32 bit :
+ * add dst_lo, dst_lo, src_lo
+ */
+ if (!hi && is64)
+ emit(ARM_ADDS_R(dst, dst, src), ctx);
+ else if (hi && is64)
+ emit(ARM_ADC_R(dst, dst, src), ctx);
+ else
+ emit(ARM_ADD_R(dst, dst, src), ctx);
+}
- if (ctx->target == NULL)
- return 0;
- /*
- * BPF allows only forward jumps and the offset of the target is
- * still the one computed during the first pass.
+static inline void emit_a32_sub_r(const u8 dst, const u8 src,
+ const bool is64, const bool hi,
+ struct jit_ctx *ctx) {
+ /* 64 bit :
+ * subs dst_lo, dst_lo, src_lo
+ * sbc dst_hi, dst_hi, src_hi
+ * 32 bit :
+ * sub dst_lo, dst_lo, src_lo
*/
- imm = ctx->offsets[tgt] + ctx->prologue_bytes - (ctx->idx * 4 + 8);
+ if (!hi && is64)
+ emit(ARM_SUBS_R(dst, dst, src), ctx);
+ else if (hi && is64)
+ emit(ARM_SBC_R(dst, dst, src), ctx);
+ else
+ emit(ARM_SUB_R(dst, dst, src), ctx);
+}
- return imm >> 2;
+static inline void emit_alu_r(const u8 dst, const u8 src, const bool is64,
+ const bool hi, const u8 op, struct jit_ctx *ctx){
+ switch (BPF_OP(op)) {
+ /* dst = dst + src */
+ case BPF_ADD:
+ emit_a32_add_r(dst, src, is64, hi, ctx);
+ break;
+ /* dst = dst - src */
+ case BPF_SUB:
+ emit_a32_sub_r(dst, src, is64, hi, ctx);
+ break;
+ /* dst = dst | src */
+ case BPF_OR:
+ emit(ARM_ORR_R(dst, dst, src), ctx);
+ break;
+ /* dst = dst & src */
+ case BPF_AND:
+ emit(ARM_AND_R(dst, dst, src), ctx);
+ break;
+ /* dst = dst ^ src */
+ case BPF_XOR:
+ emit(ARM_EOR_R(dst, dst, src), ctx);
+ break;
+ /* dst = dst * src */
+ case BPF_MUL:
+ emit(ARM_MUL(dst, dst, src), ctx);
+ break;
+ /* dst = dst << src */
+ case BPF_LSH:
+ emit(ARM_LSL_R(dst, dst, src), ctx);
+ break;
+ /* dst = dst >> src */
+ case BPF_RSH:
+ emit(ARM_LSR_R(dst, dst, src), ctx);
+ break;
+ /* dst = dst >> src (signed)*/
+ case BPF_ARSH:
+ emit(ARM_MOV_SR(dst, dst, SRTYPE_ASR, src), ctx);
+ break;
+ }
}
-#define OP_IMM3(op, r1, r2, imm_val, ctx) \
- do { \
- imm12 = imm8m(imm_val); \
- if (imm12 < 0) { \
- emit_mov_i_no8m(r_scratch, imm_val, ctx); \
- emit(op ## _R((r1), (r2), r_scratch), ctx); \
- } else { \
- emit(op ## _I((r1), (r2), imm12), ctx); \
- } \
- } while (0)
-
-static inline void emit_err_ret(u8 cond, struct jit_ctx *ctx)
-{
- if (ctx->ret0_fp_idx >= 0) {
- _emit(cond, ARM_B(b_imm(ctx->ret0_fp_idx, ctx)), ctx);
- /* NOP to keep the size constant between passes */
- emit(ARM_MOV_R(ARM_R0, ARM_R0), ctx);
+/* ALU operation (32 bit)
+ * dst = dst (op) src
+ */
+static inline void emit_a32_alu_r(const u8 dst, const u8 src,
+ bool dstk, bool sstk,
+ struct jit_ctx *ctx, const bool is64,
+ const bool hi, const u8 op) {
+ const u8 *tmp = bpf2a32[TMP_REG_1];
+ u8 rn = sstk ? tmp[1] : src;
+
+ if (sstk)
+ emit(ARM_LDR_I(rn, ARM_SP, STACK_VAR(src)), ctx);
+
+ /* ALU operation */
+ if (dstk) {
+ emit(ARM_LDR_I(tmp[0], ARM_SP, STACK_VAR(dst)), ctx);
+ emit_alu_r(tmp[0], rn, is64, hi, op, ctx);
+ emit(ARM_STR_I(tmp[0], ARM_SP, STACK_VAR(dst)), ctx);
} else {
- _emit(cond, ARM_MOV_I(ARM_R0, 0), ctx);
- _emit(cond, ARM_B(b_imm(ctx->skf->len, ctx)), ctx);
+ emit_alu_r(dst, rn, is64, hi, op, ctx);
}
}
-static inline void emit_blx_r(u8 tgt_reg, struct jit_ctx *ctx)
-{
-#if __LINUX_ARM_ARCH__ < 5
- emit(ARM_MOV_R(ARM_LR, ARM_PC), ctx);
+/* ALU operation (64 bit) */
+static inline void emit_a32_alu_r64(const bool is64, const u8 dst[],
+ const u8 src[], bool dstk,
+ bool sstk, struct jit_ctx *ctx,
+ const u8 op) {
+ emit_a32_alu_r(dst_lo, src_lo, dstk, sstk, ctx, is64, false, op);
+ if (is64)
+ emit_a32_alu_r(dst_hi, src_hi, dstk, sstk, ctx, is64, true, op);
+ else
+ emit_a32_mov_i(dst_hi, 0, dstk, ctx);
+}
- if (elf_hwcap & HWCAP_THUMB)
- emit(ARM_BX(tgt_reg), ctx);
+/* dst = imm (4 bytes)*/
+static inline void emit_a32_mov_r(const u8 dst, const u8 src,
+ bool dstk, bool sstk,
+ struct jit_ctx *ctx) {
+ const u8 *tmp = bpf2a32[TMP_REG_1];
+ u8 rt = sstk ? tmp[0] : src;
+
+ if (sstk)
+ emit(ARM_LDR_I(tmp[0], ARM_SP, STACK_VAR(src)), ctx);
+ if (dstk)
+ emit(ARM_STR_I(rt, ARM_SP, STACK_VAR(dst)), ctx);
else
- emit(ARM_MOV_R(ARM_PC, tgt_reg), ctx);
-#else
- emit(ARM_BLX_R(tgt_reg), ctx);
-#endif
+ emit(ARM_MOV_R(dst, rt), ctx);
}
-static inline void emit_udivmod(u8 rd, u8 rm, u8 rn, struct jit_ctx *ctx,
- int bpf_op)
-{
-#if __LINUX_ARM_ARCH__ == 7
- if (elf_hwcap & HWCAP_IDIVA) {
- if (bpf_op == BPF_DIV)
- emit(ARM_UDIV(rd, rm, rn), ctx);
- else {
- emit(ARM_UDIV(ARM_R3, rm, rn), ctx);
- emit(ARM_MLS(rd, rn, ARM_R3, rm), ctx);
- }
- return;
+/* dst = src */
+static inline void emit_a32_mov_r64(const bool is64, const u8 dst[],
+ const u8 src[], bool dstk,
+ bool sstk, struct jit_ctx *ctx) {
+ emit_a32_mov_r(dst_lo, src_lo, dstk, sstk, ctx);
+ if (is64) {
+ /* complete 8 byte move */
+ emit_a32_mov_r(dst_hi, src_hi, dstk, sstk, ctx);
+ } else {
+ /* Zero out high 4 bytes */
+ emit_a32_mov_i(dst_hi, 0, dstk, ctx);
}
-#endif
+}
- /*
- * For BPF_ALU | BPF_DIV | BPF_K instructions, rm is ARM_R4
- * (r_A) and rn is ARM_R0 (r_scratch) so load rn first into
- * ARM_R1 to avoid accidentally overwriting ARM_R0 with rm
- * before using it as a source for ARM_R1.
- *
- * For BPF_ALU | BPF_DIV | BPF_X rm is ARM_R4 (r_A) and rn is
- * ARM_R5 (r_X) so there is no particular register overlap
- * issues.
- */
- if (rn != ARM_R1)
- emit(ARM_MOV_R(ARM_R1, rn), ctx);
- if (rm != ARM_R0)
- emit(ARM_MOV_R(ARM_R0, rm), ctx);
+/* Shift operations */
+static inline void emit_a32_alu_i(const u8 dst, const u32 val, bool dstk,
+ struct jit_ctx *ctx, const u8 op) {
+ const u8 *tmp = bpf2a32[TMP_REG_1];
+ u8 rd = dstk ? tmp[0] : dst;
+
+ if (dstk)
+ emit(ARM_LDR_I(rd, ARM_SP, STACK_VAR(dst)), ctx);
+
+ /* Do shift operation */
+ switch (op) {
+ case BPF_LSH:
+ emit(ARM_LSL_I(rd, rd, val), ctx);
+ break;
+ case BPF_RSH:
+ emit(ARM_LSR_I(rd, rd, val), ctx);
+ break;
+ case BPF_NEG:
+ emit(ARM_RSB_I(rd, rd, val), ctx);
+ break;
+ }
+ if (dstk)
+ emit(ARM_STR_I(rd, ARM_SP, STACK_VAR(dst)), ctx);
+}
+
+/* dst = ~dst (64 bit) */
+static inline void emit_a32_neg64(const u8 dst[], bool dstk,
+ struct jit_ctx *ctx){
+ const u8 *tmp = bpf2a32[TMP_REG_1];
+ u8 rd = dstk ? tmp[1] : dst[1];
+ u8 rm = dstk ? tmp[0] : dst[0];
+
+ /* Setup Operand */
+ if (dstk) {
+ emit(ARM_LDR_I(rd, ARM_SP, STACK_VAR(dst_lo)), ctx);
+ emit(ARM_LDR_I(rm, ARM_SP, STACK_VAR(dst_hi)), ctx);
+ }
+
+ /* Do Negate Operation */
+ emit(ARM_RSBS_I(rd, rd, 0), ctx);
+ emit(ARM_RSC_I(rm, rm, 0), ctx);
+
+ if (dstk) {
+ emit(ARM_STR_I(rd, ARM_SP, STACK_VAR(dst_lo)), ctx);
+ emit(ARM_STR_I(rm, ARM_SP, STACK_VAR(dst_hi)), ctx);
+ }
+}
+
+/* dst = dst << src */
+static inline void emit_a32_lsh_r64(const u8 dst[], const u8 src[], bool dstk,
+ bool sstk, struct jit_ctx *ctx) {
+ const u8 *tmp = bpf2a32[TMP_REG_1];
+ const u8 *tmp2 = bpf2a32[TMP_REG_2];
+
+ /* Setup Operands */
+ u8 rt = sstk ? tmp2[1] : src_lo;
+ u8 rd = dstk ? tmp[1] : dst_lo;
+ u8 rm = dstk ? tmp[0] : dst_hi;
+
+ if (sstk)
+ emit(ARM_LDR_I(rt, ARM_SP, STACK_VAR(src_lo)), ctx);
+ if (dstk) {
+ emit(ARM_LDR_I(rd, ARM_SP, STACK_VAR(dst_lo)), ctx);
+ emit(ARM_LDR_I(rm, ARM_SP, STACK_VAR(dst_hi)), ctx);
+ }
+
+ /* Do LSH operation */
+ emit(ARM_SUB_I(ARM_IP, rt, 32), ctx);
+ emit(ARM_RSB_I(tmp2[0], rt, 32), ctx);
+ /* As we are using ARM_LR */
ctx->seen |= SEEN_CALL;
- emit_mov_i(ARM_R3, bpf_op == BPF_DIV ? (u32)jit_udiv : (u32)jit_mod,
- ctx);
- emit_blx_r(ARM_R3, ctx);
+ emit(ARM_MOV_SR(ARM_LR, rm, SRTYPE_ASL, rt), ctx);
+ emit(ARM_ORR_SR(ARM_LR, ARM_LR, rd, SRTYPE_ASL, ARM_IP), ctx);
+ emit(ARM_ORR_SR(ARM_IP, ARM_LR, rd, SRTYPE_LSR, tmp2[0]), ctx);
+ emit(ARM_MOV_SR(ARM_LR, rd, SRTYPE_ASL, rt), ctx);
+
+ if (dstk) {
+ emit(ARM_STR_I(ARM_LR, ARM_SP, STACK_VAR(dst_lo)), ctx);
+ emit(ARM_STR_I(ARM_IP, ARM_SP, STACK_VAR(dst_hi)), ctx);
+ } else {
+ emit(ARM_MOV_R(rd, ARM_LR), ctx);
+ emit(ARM_MOV_R(rm, ARM_IP), ctx);
+ }
+}
- if (rd != ARM_R0)
- emit(ARM_MOV_R(rd, ARM_R0), ctx);
+/* dst = dst >> src (signed)*/
+static inline void emit_a32_arsh_r64(const u8 dst[], const u8 src[], bool dstk,
+ bool sstk, struct jit_ctx *ctx) {
+ const u8 *tmp = bpf2a32[TMP_REG_1];
+ const u8 *tmp2 = bpf2a32[TMP_REG_2];
+ /* Setup Operands */
+ u8 rt = sstk ? tmp2[1] : src_lo;
+ u8 rd = dstk ? tmp[1] : dst_lo;
+ u8 rm = dstk ? tmp[0] : dst_hi;
+
+ if (sstk)
+ emit(ARM_LDR_I(rt, ARM_SP, STACK_VAR(src_lo)), ctx);
+ if (dstk) {
+ emit(ARM_LDR_I(rd, ARM_SP, STACK_VAR(dst_lo)), ctx);
+ emit(ARM_LDR_I(rm, ARM_SP, STACK_VAR(dst_hi)), ctx);
+ }
+
+ /* Do the ARSH operation */
+ emit(ARM_RSB_I(ARM_IP, rt, 32), ctx);
+ emit(ARM_SUBS_I(tmp2[0], rt, 32), ctx);
+ /* As we are using ARM_LR */
+ ctx->seen |= SEEN_CALL;
+ emit(ARM_MOV_SR(ARM_LR, rd, SRTYPE_LSR, rt), ctx);
+ emit(ARM_ORR_SR(ARM_LR, ARM_LR, rm, SRTYPE_ASL, ARM_IP), ctx);
+ _emit(ARM_COND_MI, ARM_B(0), ctx);
+ emit(ARM_ORR_SR(ARM_LR, ARM_LR, rm, SRTYPE_ASR, tmp2[0]), ctx);
+ emit(ARM_MOV_SR(ARM_IP, rm, SRTYPE_ASR, rt), ctx);
+ if (dstk) {
+ emit(ARM_STR_I(ARM_LR, ARM_SP, STACK_VAR(dst_lo)), ctx);
+ emit(ARM_STR_I(ARM_IP, ARM_SP, STACK_VAR(dst_hi)), ctx);
+ } else {
+ emit(ARM_MOV_R(rd, ARM_LR), ctx);
+ emit(ARM_MOV_R(rm, ARM_IP), ctx);
+ }
+}
+
+/* dst = dst >> src */
+static inline void emit_a32_lsr_r64(const u8 dst[], const u8 src[], bool dstk,
+ bool sstk, struct jit_ctx *ctx) {
+ const u8 *tmp = bpf2a32[TMP_REG_1];
+ const u8 *tmp2 = bpf2a32[TMP_REG_2];
+ /* Setup Operands */
+ u8 rt = sstk ? tmp2[1] : src_lo;
+ u8 rd = dstk ? tmp[1] : dst_lo;
+ u8 rm = dstk ? tmp[0] : dst_hi;
+
+ if (sstk)
+ emit(ARM_LDR_I(rt, ARM_SP, STACK_VAR(src_lo)), ctx);
+ if (dstk) {
+ emit(ARM_LDR_I(rd, ARM_SP, STACK_VAR(dst_lo)), ctx);
+ emit(ARM_LDR_I(rm, ARM_SP, STACK_VAR(dst_hi)), ctx);
+ }
+
+ /* Do LSH operation */
+ emit(ARM_RSB_I(ARM_IP, rt, 32), ctx);
+ emit(ARM_SUBS_I(tmp2[0], rt, 32), ctx);
+ /* As we are using ARM_LR */
+ ctx->seen |= SEEN_CALL;
+ emit(ARM_MOV_SR(ARM_LR, rd, SRTYPE_LSR, rt), ctx);
+ emit(ARM_ORR_SR(ARM_LR, ARM_LR, rm, SRTYPE_ASL, ARM_IP), ctx);
+ emit(ARM_ORR_SR(ARM_LR, ARM_LR, rm, SRTYPE_LSR, tmp2[0]), ctx);
+ emit(ARM_MOV_SR(ARM_IP, rm, SRTYPE_LSR, rt), ctx);
+ if (dstk) {
+ emit(ARM_STR_I(ARM_LR, ARM_SP, STACK_VAR(dst_lo)), ctx);
+ emit(ARM_STR_I(ARM_IP, ARM_SP, STACK_VAR(dst_hi)), ctx);
+ } else {
+ emit(ARM_MOV_R(rd, ARM_LR), ctx);
+ emit(ARM_MOV_R(rm, ARM_IP), ctx);
+ }
}
-static inline void update_on_xread(struct jit_ctx *ctx)
+/* dst = dst << val */
+static inline void emit_a32_lsh_i64(const u8 dst[], bool dstk,
+ const u32 val, struct jit_ctx *ctx){
+ const u8 *tmp = bpf2a32[TMP_REG_1];
+ const u8 *tmp2 = bpf2a32[TMP_REG_2];
+ /* Setup operands */
+ u8 rd = dstk ? tmp[1] : dst_lo;
+ u8 rm = dstk ? tmp[0] : dst_hi;
+
+ if (dstk) {
+ emit(ARM_LDR_I(rd, ARM_SP, STACK_VAR(dst_lo)), ctx);
+ emit(ARM_LDR_I(rm, ARM_SP, STACK_VAR(dst_hi)), ctx);
+ }
+
+ /* Do LSH operation */
+ if (val < 32) {
+ emit(ARM_MOV_SI(tmp2[0], rm, SRTYPE_ASL, val), ctx);
+ emit(ARM_ORR_SI(rm, tmp2[0], rd, SRTYPE_LSR, 32 - val), ctx);
+ emit(ARM_MOV_SI(rd, rd, SRTYPE_ASL, val), ctx);
+ } else {
+ if (val == 32)
+ emit(ARM_MOV_R(rm, rd), ctx);
+ else
+ emit(ARM_MOV_SI(rm, rd, SRTYPE_ASL, val - 32), ctx);
+ emit(ARM_EOR_R(rd, rd, rd), ctx);
+ }
+
+ if (dstk) {
+ emit(ARM_STR_I(rd, ARM_SP, STACK_VAR(dst_lo)), ctx);
+ emit(ARM_STR_I(rm, ARM_SP, STACK_VAR(dst_hi)), ctx);
+ }
+}
+
+/* dst = dst >> val */
+static inline void emit_a32_lsr_i64(const u8 dst[], bool dstk,
+ const u32 val, struct jit_ctx *ctx) {
+ const u8 *tmp = bpf2a32[TMP_REG_1];
+ const u8 *tmp2 = bpf2a32[TMP_REG_2];
+ /* Setup operands */
+ u8 rd = dstk ? tmp[1] : dst_lo;
+ u8 rm = dstk ? tmp[0] : dst_hi;
+
+ if (dstk) {
+ emit(ARM_LDR_I(rd, ARM_SP, STACK_VAR(dst_lo)), ctx);
+ emit(ARM_LDR_I(rm, ARM_SP, STACK_VAR(dst_hi)), ctx);
+ }
+
+ /* Do LSR operation */
+ if (val < 32) {
+ emit(ARM_MOV_SI(tmp2[1], rd, SRTYPE_LSR, val), ctx);
+ emit(ARM_ORR_SI(rd, tmp2[1], rm, SRTYPE_ASL, 32 - val), ctx);
+ emit(ARM_MOV_SI(rm, rm, SRTYPE_LSR, val), ctx);
+ } else if (val == 32) {
+ emit(ARM_MOV_R(rd, rm), ctx);
+ emit(ARM_MOV_I(rm, 0), ctx);
+ } else {
+ emit(ARM_MOV_SI(rd, rm, SRTYPE_LSR, val - 32), ctx);
+ emit(ARM_MOV_I(rm, 0), ctx);
+ }
+
+ if (dstk) {
+ emit(ARM_STR_I(rd, ARM_SP, STACK_VAR(dst_lo)), ctx);
+ emit(ARM_STR_I(rm, ARM_SP, STACK_VAR(dst_hi)), ctx);
+ }
+}
+
+/* dst = dst >> val (signed) */
+static inline void emit_a32_arsh_i64(const u8 dst[], bool dstk,
+ const u32 val, struct jit_ctx *ctx){
+ const u8 *tmp = bpf2a32[TMP_REG_1];
+ const u8 *tmp2 = bpf2a32[TMP_REG_2];
+ /* Setup operands */
+ u8 rd = dstk ? tmp[1] : dst_lo;
+ u8 rm = dstk ? tmp[0] : dst_hi;
+
+ if (dstk) {
+ emit(ARM_LDR_I(rd, ARM_SP, STACK_VAR(dst_lo)), ctx);
+ emit(ARM_LDR_I(rm, ARM_SP, STACK_VAR(dst_hi)), ctx);
+ }
+
+ /* Do ARSH operation */
+ if (val < 32) {
+ emit(ARM_MOV_SI(tmp2[1], rd, SRTYPE_LSR, val), ctx);
+ emit(ARM_ORR_SI(rd, tmp2[1], rm, SRTYPE_ASL, 32 - val), ctx);
+ emit(ARM_MOV_SI(rm, rm, SRTYPE_ASR, val), ctx);
+ } else if (val == 32) {
+ emit(ARM_MOV_R(rd, rm), ctx);
+ emit(ARM_MOV_SI(rm, rm, SRTYPE_ASR, 31), ctx);
+ } else {
+ emit(ARM_MOV_SI(rd, rm, SRTYPE_ASR, val - 32), ctx);
+ emit(ARM_MOV_SI(rm, rm, SRTYPE_ASR, 31), ctx);
+ }
+
+ if (dstk) {
+ emit(ARM_STR_I(rd, ARM_SP, STACK_VAR(dst_lo)), ctx);
+ emit(ARM_STR_I(rm, ARM_SP, STACK_VAR(dst_hi)), ctx);
+ }
+}
+
+static inline void emit_a32_mul_r64(const u8 dst[], const u8 src[], bool dstk,
+ bool sstk, struct jit_ctx *ctx) {
+ const u8 *tmp = bpf2a32[TMP_REG_1];
+ const u8 *tmp2 = bpf2a32[TMP_REG_2];
+ /* Setup operands for multiplication */
+ u8 rd = dstk ? tmp[1] : dst_lo;
+ u8 rm = dstk ? tmp[0] : dst_hi;
+ u8 rt = sstk ? tmp2[1] : src_lo;
+ u8 rn = sstk ? tmp2[0] : src_hi;
+
+ if (dstk) {
+ emit(ARM_LDR_I(rd, ARM_SP, STACK_VAR(dst_lo)), ctx);
+ emit(ARM_LDR_I(rm, ARM_SP, STACK_VAR(dst_hi)), ctx);
+ }
+ if (sstk) {
+ emit(ARM_LDR_I(rt, ARM_SP, STACK_VAR(src_lo)), ctx);
+ emit(ARM_LDR_I(rn, ARM_SP, STACK_VAR(src_hi)), ctx);
+ }
+
+ /* Do Multiplication */
+ emit(ARM_MUL(ARM_IP, rd, rn), ctx);
+ emit(ARM_MUL(ARM_LR, rm, rt), ctx);
+ /* As we are using ARM_LR */
+ ctx->seen |= SEEN_CALL;
+ emit(ARM_ADD_R(ARM_LR, ARM_IP, ARM_LR), ctx);
+
+ emit(ARM_UMULL(ARM_IP, rm, rd, rt), ctx);
+ emit(ARM_ADD_R(rm, ARM_LR, rm), ctx);
+ if (dstk) {
+ emit(ARM_STR_I(ARM_IP, ARM_SP, STACK_VAR(dst_lo)), ctx);
+ emit(ARM_STR_I(rm, ARM_SP, STACK_VAR(dst_hi)), ctx);
+ } else {
+ emit(ARM_MOV_R(rd, ARM_IP), ctx);
+ }
+}
+
+/* *(size *)(dst + off) = src */
+static inline void emit_str_r(const u8 dst, const u8 src, bool dstk,
+ const s32 off, struct jit_ctx *ctx, const u8 sz){
+ const u8 *tmp = bpf2a32[TMP_REG_1];
+ u8 rd = dstk ? tmp[1] : dst;
+
+ if (dstk)
+ emit(ARM_LDR_I(rd, ARM_SP, STACK_VAR(dst)), ctx);
+ if (off) {
+ emit_a32_mov_i(tmp[0], off, false, ctx);
+ emit(ARM_ADD_R(tmp[0], rd, tmp[0]), ctx);
+ rd = tmp[0];
+ }
+ switch (sz) {
+ case BPF_W:
+ /* Store a Word */
+ emit(ARM_STR_I(src, rd, 0), ctx);
+ break;
+ case BPF_H:
+ /* Store a HalfWord */
+ emit(ARM_STRH_I(src, rd, 0), ctx);
+ break;
+ case BPF_B:
+ /* Store a Byte */
+ emit(ARM_STRB_I(src, rd, 0), ctx);
+ break;
+ }
+}
+
+/* dst = *(size*)(src + off) */
+static inline void emit_ldx_r(const u8 dst, const u8 src, bool dstk,
+ const s32 off, struct jit_ctx *ctx, const u8 sz){
+ const u8 *tmp = bpf2a32[TMP_REG_1];
+ u8 rd = dstk ? tmp[1] : dst;
+ u8 rm = src;
+
+ if (off) {
+ emit_a32_mov_i(tmp[0], off, false, ctx);
+ emit(ARM_ADD_R(tmp[0], tmp[0], src), ctx);
+ rm = tmp[0];
+ }
+ switch (sz) {
+ case BPF_W:
+ /* Load a Word */
+ emit(ARM_LDR_I(rd, rm, 0), ctx);
+ break;
+ case BPF_H:
+ /* Load a HalfWord */
+ emit(ARM_LDRH_I(rd, rm, 0), ctx);
+ break;
+ case BPF_B:
+ /* Load a Byte */
+ emit(ARM_LDRB_I(rd, rm, 0), ctx);
+ break;
+ }
+ if (dstk)
+ emit(ARM_STR_I(rd, ARM_SP, STACK_VAR(dst)), ctx);
+}
+
+/* Arithmatic Operation */
+static inline void emit_ar_r(const u8 rd, const u8 rt, const u8 rm,
+ const u8 rn, struct jit_ctx *ctx, u8 op) {
+ switch (op) {
+ case BPF_JSET:
+ ctx->seen |= SEEN_CALL;
+ emit(ARM_AND_R(ARM_IP, rt, rn), ctx);
+ emit(ARM_AND_R(ARM_LR, rd, rm), ctx);
+ emit(ARM_ORRS_R(ARM_IP, ARM_LR, ARM_IP), ctx);
+ break;
+ case BPF_JEQ:
+ case BPF_JNE:
+ case BPF_JGT:
+ case BPF_JGE:
+ case BPF_JLE:
+ case BPF_JLT:
+ emit(ARM_CMP_R(rd, rm), ctx);
+ _emit(ARM_COND_EQ, ARM_CMP_R(rt, rn), ctx);
+ break;
+ case BPF_JSLE:
+ case BPF_JSGT:
+ emit(ARM_CMP_R(rn, rt), ctx);
+ emit(ARM_SBCS_R(ARM_IP, rm, rd), ctx);
+ break;
+ case BPF_JSLT:
+ case BPF_JSGE:
+ emit(ARM_CMP_R(rt, rn), ctx);
+ emit(ARM_SBCS_R(ARM_IP, rd, rm), ctx);
+ break;
+ }
+}
+
+static int out_offset = -1; /* initialized on the first pass of build_body() */
+static int emit_bpf_tail_call(struct jit_ctx *ctx)
{
- if (!(ctx->seen & SEEN_X))
- ctx->flags |= FLAG_NEED_X_RESET;
- ctx->seen |= SEEN_X;
+ /* bpf_tail_call(void *prog_ctx, struct bpf_array *array, u64 index) */
+ const u8 *r2 = bpf2a32[BPF_REG_2];
+ const u8 *r3 = bpf2a32[BPF_REG_3];
+ const u8 *tmp = bpf2a32[TMP_REG_1];
+ const u8 *tmp2 = bpf2a32[TMP_REG_2];
+ const u8 *tcc = bpf2a32[TCALL_CNT];
+ const int idx0 = ctx->idx;
+#define cur_offset (ctx->idx - idx0)
+#define jmp_offset (out_offset - (cur_offset))
+ u32 off, lo, hi;
+
+ /* if (index >= array->map.max_entries)
+ * goto out;
+ */
+ off = offsetof(struct bpf_array, map.max_entries);
+ /* array->map.max_entries */
+ emit_a32_mov_i(tmp[1], off, false, ctx);
+ emit(ARM_LDR_I(tmp2[1], ARM_SP, STACK_VAR(r2[1])), ctx);
+ emit(ARM_LDR_R(tmp[1], tmp2[1], tmp[1]), ctx);
+ /* index (64 bit) */
+ emit(ARM_LDR_I(tmp2[1], ARM_SP, STACK_VAR(r3[1])), ctx);
+ /* index >= array->map.max_entries */
+ emit(ARM_CMP_R(tmp2[1], tmp[1]), ctx);
+ _emit(ARM_COND_CS, ARM_B(jmp_offset), ctx);
+
+ /* if (tail_call_cnt > MAX_TAIL_CALL_CNT)
+ * goto out;
+ * tail_call_cnt++;
+ */
+ lo = (u32)MAX_TAIL_CALL_CNT;
+ hi = (u32)((u64)MAX_TAIL_CALL_CNT >> 32);
+ emit(ARM_LDR_I(tmp[1], ARM_SP, STACK_VAR(tcc[1])), ctx);
+ emit(ARM_LDR_I(tmp[0], ARM_SP, STACK_VAR(tcc[0])), ctx);
+ emit(ARM_CMP_I(tmp[0], hi), ctx);
+ _emit(ARM_COND_EQ, ARM_CMP_I(tmp[1], lo), ctx);
+ _emit(ARM_COND_HI, ARM_B(jmp_offset), ctx);
+ emit(ARM_ADDS_I(tmp[1], tmp[1], 1), ctx);
+ emit(ARM_ADC_I(tmp[0], tmp[0], 0), ctx);
+ emit(ARM_STR_I(tmp[1], ARM_SP, STACK_VAR(tcc[1])), ctx);
+ emit(ARM_STR_I(tmp[0], ARM_SP, STACK_VAR(tcc[0])), ctx);
+
+ /* prog = array->ptrs[index]
+ * if (prog == NULL)
+ * goto out;
+ */
+ off = offsetof(struct bpf_array, ptrs);
+ emit_a32_mov_i(tmp[1], off, false, ctx);
+ emit(ARM_LDR_I(tmp2[1], ARM_SP, STACK_VAR(r2[1])), ctx);
+ emit(ARM_ADD_R(tmp[1], tmp2[1], tmp[1]), ctx);
+ emit(ARM_LDR_I(tmp2[1], ARM_SP, STACK_VAR(r3[1])), ctx);
+ emit(ARM_MOV_SI(tmp[0], tmp2[1], SRTYPE_ASL, 2), ctx);
+ emit(ARM_LDR_R(tmp[1], tmp[1], tmp[0]), ctx);
+ emit(ARM_CMP_I(tmp[1], 0), ctx);
+ _emit(ARM_COND_EQ, ARM_B(jmp_offset), ctx);
+
+ /* goto *(prog->bpf_func + prologue_size); */
+ off = offsetof(struct bpf_prog, bpf_func);
+ emit_a32_mov_i(tmp2[1], off, false, ctx);
+ emit(ARM_LDR_R(tmp[1], tmp[1], tmp2[1]), ctx);
+ emit(ARM_ADD_I(tmp[1], tmp[1], ctx->prologue_bytes), ctx);
+ emit(ARM_BX(tmp[1]), ctx);
+
+ /* out: */
+ if (out_offset == -1)
+ out_offset = cur_offset;
+ if (cur_offset != out_offset) {
+ pr_err_once("tail_call out_offset = %d, expected %d!\n",
+ cur_offset, out_offset);
+ return -1;
+ }
+ return 0;
+#undef cur_offset
+#undef jmp_offset
}
-static int build_body(struct jit_ctx *ctx)
+/* 0xabcd => 0xcdab */
+static inline void emit_rev16(const u8 rd, const u8 rn, struct jit_ctx *ctx)
{
- void *load_func[] = {jit_get_skb_b, jit_get_skb_h, jit_get_skb_w};
- const struct bpf_prog *prog = ctx->skf;
- const struct sock_filter *inst;
- unsigned i, load_order, off, condt;
- int imm12;
- u32 k;
+#if __LINUX_ARM_ARCH__ < 6
+ const u8 *tmp2 = bpf2a32[TMP_REG_2];
+
+ emit(ARM_AND_I(tmp2[1], rn, 0xff), ctx);
+ emit(ARM_MOV_SI(tmp2[0], rn, SRTYPE_LSR, 8), ctx);
+ emit(ARM_AND_I(tmp2[0], tmp2[0], 0xff), ctx);
+ emit(ARM_ORR_SI(rd, tmp2[0], tmp2[1], SRTYPE_LSL, 8), ctx);
+#else /* ARMv6+ */
+ emit(ARM_REV16(rd, rn), ctx);
+#endif
+}
- for (i = 0; i < prog->len; i++) {
- u16 code;
+/* 0xabcdefgh => 0xghefcdab */
+static inline void emit_rev32(const u8 rd, const u8 rn, struct jit_ctx *ctx)
+{
+#if __LINUX_ARM_ARCH__ < 6
+ const u8 *tmp2 = bpf2a32[TMP_REG_2];
+
+ emit(ARM_AND_I(tmp2[1], rn, 0xff), ctx);
+ emit(ARM_MOV_SI(tmp2[0], rn, SRTYPE_LSR, 24), ctx);
+ emit(ARM_ORR_SI(ARM_IP, tmp2[0], tmp2[1], SRTYPE_LSL, 24), ctx);
+
+ emit(ARM_MOV_SI(tmp2[1], rn, SRTYPE_LSR, 8), ctx);
+ emit(ARM_AND_I(tmp2[1], tmp2[1], 0xff), ctx);
+ emit(ARM_MOV_SI(tmp2[0], rn, SRTYPE_LSR, 16), ctx);
+ emit(ARM_AND_I(tmp2[0], tmp2[0], 0xff), ctx);
+ emit(ARM_MOV_SI(tmp2[0], tmp2[0], SRTYPE_LSL, 8), ctx);
+ emit(ARM_ORR_SI(tmp2[0], tmp2[0], tmp2[1], SRTYPE_LSL, 16), ctx);
+ emit(ARM_ORR_R(rd, ARM_IP, tmp2[0]), ctx);
+
+#else /* ARMv6+ */
+ emit(ARM_REV(rd, rn), ctx);
+#endif
+}
- inst = &(prog->insns[i]);
- /* K as an immediate value operand */
- k = inst->k;
- code = bpf_anc_helper(inst);
+// push the scratch stack register on top of the stack
+static inline void emit_push_r64(const u8 src[], const u8 shift,
+ struct jit_ctx *ctx)
+{
+ const u8 *tmp2 = bpf2a32[TMP_REG_2];
+ u16 reg_set = 0;
- /* compute offsets only in the fake pass */
- if (ctx->target == NULL)
- ctx->offsets[i] = ctx->idx * 4;
+ emit(ARM_LDR_I(tmp2[1], ARM_SP, STACK_VAR(src[1]+shift)), ctx);
+ emit(ARM_LDR_I(tmp2[0], ARM_SP, STACK_VAR(src[0]+shift)), ctx);
+
+ reg_set = (1 << tmp2[1]) | (1 << tmp2[0]);
+ emit(ARM_PUSH(reg_set), ctx);
+}
+
+static void build_prologue(struct jit_ctx *ctx)
+{
+ const u8 r0 = bpf2a32[BPF_REG_0][1];
+ const u8 r2 = bpf2a32[BPF_REG_1][1];
+ const u8 r3 = bpf2a32[BPF_REG_1][0];
+ const u8 r4 = bpf2a32[BPF_REG_6][1];
+ const u8 r5 = bpf2a32[BPF_REG_6][0];
+ const u8 r6 = bpf2a32[TMP_REG_1][1];
+ const u8 r7 = bpf2a32[TMP_REG_1][0];
+ const u8 r8 = bpf2a32[TMP_REG_2][1];
+ const u8 r10 = bpf2a32[TMP_REG_2][0];
+ const u8 fplo = bpf2a32[BPF_REG_FP][1];
+ const u8 fphi = bpf2a32[BPF_REG_FP][0];
+ const u8 sp = ARM_SP;
+ const u8 *tcc = bpf2a32[TCALL_CNT];
+
+ u16 reg_set = 0;
+
+ /*
+ * eBPF prog stack layout
+ *
+ * high
+ * original ARM_SP => +-----+ eBPF prologue
+ * |FP/LR|
+ * current ARM_FP => +-----+
+ * | ... | callee saved registers
+ * eBPF fp register => +-----+ <= (BPF_FP)
+ * | ... | eBPF JIT scratch space
+ * | | eBPF prog stack
+ * +-----+
+ * |RSVD | JIT scratchpad
+ * current A64_SP => +-----+ <= (BPF_FP - STACK_SIZE)
+ * | |
+ * | ... | Function call stack
+ * | |
+ * +-----+
+ * low
+ */
+
+ /* Save callee saved registers. */
+ reg_set |= (1<<r4) | (1<<r5) | (1<<r6) | (1<<r7) | (1<<r8) | (1<<r10);
+#ifdef CONFIG_FRAME_POINTER
+ reg_set |= (1<<ARM_FP) | (1<<ARM_IP) | (1<<ARM_LR) | (1<<ARM_PC);
+ emit(ARM_MOV_R(ARM_IP, sp), ctx);
+ emit(ARM_PUSH(reg_set), ctx);
+ emit(ARM_SUB_I(ARM_FP, ARM_IP, 4), ctx);
+#else
+ /* Check if call instruction exists in BPF body */
+ if (ctx->seen & SEEN_CALL)
+ reg_set |= (1<<ARM_LR);
+ emit(ARM_PUSH(reg_set), ctx);
+#endif
+ /* Save frame pointer for later */
+ emit(ARM_SUB_I(ARM_IP, sp, SCRATCH_SIZE), ctx);
+
+ ctx->stack_size = imm8m(STACK_SIZE);
+
+ /* Set up function call stack */
+ emit(ARM_SUB_I(ARM_SP, ARM_SP, ctx->stack_size), ctx);
- switch (code) {
- case BPF_LD | BPF_IMM:
- emit_mov_i(r_A, k, ctx);
+ /* Set up BPF prog stack base register */
+ emit_a32_mov_r(fplo, ARM_IP, true, false, ctx);
+ emit_a32_mov_i(fphi, 0, true, ctx);
+
+ /* mov r4, 0 */
+ emit(ARM_MOV_I(r4, 0), ctx);
+
+ /* Move BPF_CTX to BPF_R1 */
+ emit(ARM_MOV_R(r3, r4), ctx);
+ emit(ARM_MOV_R(r2, r0), ctx);
+ /* Initialize Tail Count */
+ emit(ARM_STR_I(r4, ARM_SP, STACK_VAR(tcc[0])), ctx);
+ emit(ARM_STR_I(r4, ARM_SP, STACK_VAR(tcc[1])), ctx);
+ /* end of prologue */
+}
+
+static void build_epilogue(struct jit_ctx *ctx)
+{
+ const u8 r4 = bpf2a32[BPF_REG_6][1];
+ const u8 r5 = bpf2a32[BPF_REG_6][0];
+ const u8 r6 = bpf2a32[TMP_REG_1][1];
+ const u8 r7 = bpf2a32[TMP_REG_1][0];
+ const u8 r8 = bpf2a32[TMP_REG_2][1];
+ const u8 r10 = bpf2a32[TMP_REG_2][0];
+ u16 reg_set = 0;
+
+ /* unwind function call stack */
+ emit(ARM_ADD_I(ARM_SP, ARM_SP, ctx->stack_size), ctx);
+
+ /* restore callee saved registers. */
+ reg_set |= (1<<r4) | (1<<r5) | (1<<r6) | (1<<r7) | (1<<r8) | (1<<r10);
+#ifdef CONFIG_FRAME_POINTER
+ /* the first instruction of the prologue was: mov ip, sp */
+ reg_set |= (1<<ARM_FP) | (1<<ARM_SP) | (1<<ARM_PC);
+ emit(ARM_LDM(ARM_SP, reg_set), ctx);
+#else
+ if (ctx->seen & SEEN_CALL)
+ reg_set |= (1<<ARM_PC);
+ /* Restore callee saved registers. */
+ emit(ARM_POP(reg_set), ctx);
+ /* Return back to the callee function */
+ if (!(ctx->seen & SEEN_CALL))
+ emit(ARM_BX(ARM_LR), ctx);
+#endif
+}
+
+/*
+ * Convert an eBPF instruction to native instruction, i.e
+ * JITs an eBPF instruction.
+ * Returns :
+ * 0 - Successfully JITed an 8-byte eBPF instruction
+ * >0 - Successfully JITed a 16-byte eBPF instruction
+ * <0 - Failed to JIT.
+ */
+static int build_insn(const struct bpf_insn *insn, struct jit_ctx *ctx)
+{
+ const u8 code = insn->code;
+ const u8 *dst = bpf2a32[insn->dst_reg];
+ const u8 *src = bpf2a32[insn->src_reg];
+ const u8 *tmp = bpf2a32[TMP_REG_1];
+ const u8 *tmp2 = bpf2a32[TMP_REG_2];
+ const s16 off = insn->off;
+ const s32 imm = insn->imm;
+ const int i = insn - ctx->prog->insnsi;
+ const bool is64 = BPF_CLASS(code) == BPF_ALU64;
+ const bool dstk = is_on_stack(insn->dst_reg);
+ const bool sstk = is_on_stack(insn->src_reg);
+ u8 rd, rt, rm, rn;
+ s32 jmp_offset;
+
+#define check_imm(bits, imm) do { \
+ if ((((imm) > 0) && ((imm) >> (bits))) || \
+ (((imm) < 0) && (~(imm) >> (bits)))) { \
+ pr_info("[%2d] imm=%d(0x%x) out of range\n", \
+ i, imm, imm); \
+ return -EINVAL; \
+ } \
+} while (0)
+#define check_imm24(imm) check_imm(24, imm)
+
+ switch (code) {
+ /* ALU operations */
+
+ /* dst = src */
+ case BPF_ALU | BPF_MOV | BPF_K:
+ case BPF_ALU | BPF_MOV | BPF_X:
+ case BPF_ALU64 | BPF_MOV | BPF_K:
+ case BPF_ALU64 | BPF_MOV | BPF_X:
+ switch (BPF_SRC(code)) {
+ case BPF_X:
+ emit_a32_mov_r64(is64, dst, src, dstk, sstk, ctx);
break;
- case BPF_LD | BPF_W | BPF_LEN:
- ctx->seen |= SEEN_SKB;
- BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, len) != 4);
- emit(ARM_LDR_I(r_A, r_skb,
- offsetof(struct sk_buff, len)), ctx);
+ case BPF_K:
+ /* Sign-extend immediate value to destination reg */
+ emit_a32_mov_i64(is64, dst, imm, dstk, ctx);
break;
- case BPF_LD | BPF_MEM:
- /* A = scratch[k] */
- ctx->seen |= SEEN_MEM_WORD(k);
- emit(ARM_LDR_I(r_A, ARM_SP, SCRATCH_OFF(k)), ctx);
+ }
+ break;
+ /* dst = dst + src/imm */
+ /* dst = dst - src/imm */
+ /* dst = dst | src/imm */
+ /* dst = dst & src/imm */
+ /* dst = dst ^ src/imm */
+ /* dst = dst * src/imm */
+ /* dst = dst << src */
+ /* dst = dst >> src */
+ case BPF_ALU | BPF_ADD | BPF_K:
+ case BPF_ALU | BPF_ADD | BPF_X:
+ case BPF_ALU | BPF_SUB | BPF_K:
+ case BPF_ALU | BPF_SUB | BPF_X:
+ case BPF_ALU | BPF_OR | BPF_K:
+ case BPF_ALU | BPF_OR | BPF_X:
+ case BPF_ALU | BPF_AND | BPF_K:
+ case BPF_ALU | BPF_AND | BPF_X:
+ case BPF_ALU | BPF_XOR | BPF_K:
+ case BPF_ALU | BPF_XOR | BPF_X:
+ case BPF_ALU | BPF_MUL | BPF_K:
+ case BPF_ALU | BPF_MUL | BPF_X:
+ case BPF_ALU | BPF_LSH | BPF_X:
+ case BPF_ALU | BPF_RSH | BPF_X:
+ case BPF_ALU | BPF_ARSH | BPF_K:
+ case BPF_ALU | BPF_ARSH | BPF_X:
+ case BPF_ALU64 | BPF_ADD | BPF_K:
+ case BPF_ALU64 | BPF_ADD | BPF_X:
+ case BPF_ALU64 | BPF_SUB | BPF_K:
+ case BPF_ALU64 | BPF_SUB | BPF_X:
+ case BPF_ALU64 | BPF_OR | BPF_K:
+ case BPF_ALU64 | BPF_OR | BPF_X:
+ case BPF_ALU64 | BPF_AND | BPF_K:
+ case BPF_ALU64 | BPF_AND | BPF_X:
+ case BPF_ALU64 | BPF_XOR | BPF_K:
+ case BPF_ALU64 | BPF_XOR | BPF_X:
+ switch (BPF_SRC(code)) {
+ case BPF_X:
+ emit_a32_alu_r64(is64, dst, src, dstk, sstk,
+ ctx, BPF_OP(code));
break;
- case BPF_LD | BPF_W | BPF_ABS:
- load_order = 2;
- goto load;
- case BPF_LD | BPF_H | BPF_ABS:
- load_order = 1;
- goto load;
- case BPF_LD | BPF_B | BPF_ABS:
- load_order = 0;
-load:
- emit_mov_i(r_off, k, ctx);
-load_common:
- ctx->seen |= SEEN_DATA | SEEN_CALL;
-
- if (load_order > 0) {
- emit(ARM_SUB_I(r_scratch, r_skb_hl,
- 1 << load_order), ctx);
- emit(ARM_CMP_R(r_scratch, r_off), ctx);
- condt = ARM_COND_GE;
- } else {
- emit(ARM_CMP_R(r_skb_hl, r_off), ctx);
- condt = ARM_COND_HI;
- }
-
- /*
- * test for negative offset, only if we are
- * currently scheduled to take the fast
- * path. this will update the flags so that
- * the slowpath instruction are ignored if the
- * offset is negative.
- *
- * for loard_order == 0 the HI condition will
- * make loads at offset 0 take the slow path too.
+ case BPF_K:
+ /* Move immediate value to the temporary register
+ * and then do the ALU operation on the temporary
+ * register as this will sign-extend the immediate
+ * value into temporary reg and then it would be
+ * safe to do the operation on it.
*/
- _emit(condt, ARM_CMP_I(r_off, 0), ctx);
-
- _emit(condt, ARM_ADD_R(r_scratch, r_off, r_skb_data),
- ctx);
-
- if (load_order == 0)
- _emit(condt, ARM_LDRB_I(r_A, r_scratch, 0),
- ctx);
- else if (load_order == 1)
- emit_load_be16(condt, r_A, r_scratch, ctx);
- else if (load_order == 2)
- emit_load_be32(condt, r_A, r_scratch, ctx);
-
- _emit(condt, ARM_B(b_imm(i + 1, ctx)), ctx);
-
- /* the slowpath */
- emit_mov_i(ARM_R3, (u32)load_func[load_order], ctx);
- emit(ARM_MOV_R(ARM_R0, r_skb), ctx);
- /* the offset is already in R1 */
- emit_blx_r(ARM_R3, ctx);
- /* check the result of skb_copy_bits */
- emit(ARM_CMP_I(ARM_R1, 0), ctx);
- emit_err_ret(ARM_COND_NE, ctx);
- emit(ARM_MOV_R(r_A, ARM_R0), ctx);
+ emit_a32_mov_i64(is64, tmp2, imm, false, ctx);
+ emit_a32_alu_r64(is64, dst, tmp2, dstk, false,
+ ctx, BPF_OP(code));
break;
- case BPF_LD | BPF_W | BPF_IND:
- load_order = 2;
- goto load_ind;
- case BPF_LD | BPF_H | BPF_IND:
- load_order = 1;
- goto load_ind;
- case BPF_LD | BPF_B | BPF_IND:
- load_order = 0;
-load_ind:
- update_on_xread(ctx);
- OP_IMM3(ARM_ADD, r_off, r_X, k, ctx);
- goto load_common;
- case BPF_LDX | BPF_IMM:
- ctx->seen |= SEEN_X;
- emit_mov_i(r_X, k, ctx);
+ }
+ break;
+ /* dst = dst / src(imm) */
+ /* dst = dst % src(imm) */
+ case BPF_ALU | BPF_DIV | BPF_K:
+ case BPF_ALU | BPF_DIV | BPF_X:
+ case BPF_ALU | BPF_MOD | BPF_K:
+ case BPF_ALU | BPF_MOD | BPF_X:
+ rt = src_lo;
+ rd = dstk ? tmp2[1] : dst_lo;
+ if (dstk)
+ emit(ARM_LDR_I(rd, ARM_SP, STACK_VAR(dst_lo)), ctx);
+ switch (BPF_SRC(code)) {
+ case BPF_X:
+ rt = sstk ? tmp2[0] : rt;
+ if (sstk)
+ emit(ARM_LDR_I(rt, ARM_SP, STACK_VAR(src_lo)),
+ ctx);
break;
- case BPF_LDX | BPF_W | BPF_LEN:
- ctx->seen |= SEEN_X | SEEN_SKB;
- emit(ARM_LDR_I(r_X, r_skb,
- offsetof(struct sk_buff, len)), ctx);
+ case BPF_K:
+ rt = tmp2[0];
+ emit_a32_mov_i(rt, imm, false, ctx);
break;
- case BPF_LDX | BPF_MEM:
- ctx->seen |= SEEN_X | SEEN_MEM_WORD(k);
- emit(ARM_LDR_I(r_X, ARM_SP, SCRATCH_OFF(k)), ctx);
+ }
+ emit_udivmod(rd, rd, rt, ctx, BPF_OP(code));
+ if (dstk)
+ emit(ARM_STR_I(rd, ARM_SP, STACK_VAR(dst_lo)), ctx);
+ emit_a32_mov_i(dst_hi, 0, dstk, ctx);
+ break;
+ case BPF_ALU64 | BPF_DIV | BPF_K:
+ case BPF_ALU64 | BPF_DIV | BPF_X:
+ case BPF_ALU64 | BPF_MOD | BPF_K:
+ case BPF_ALU64 | BPF_MOD | BPF_X:
+ goto notyet;
+ /* dst = dst >> imm */
+ /* dst = dst << imm */
+ case BPF_ALU | BPF_RSH | BPF_K:
+ case BPF_ALU | BPF_LSH | BPF_K:
+ if (unlikely(imm > 31))
+ return -EINVAL;
+ if (imm)
+ emit_a32_alu_i(dst_lo, imm, dstk, ctx, BPF_OP(code));
+ emit_a32_mov_i(dst_hi, 0, dstk, ctx);
+ break;
+ /* dst = dst << imm */
+ case BPF_ALU64 | BPF_LSH | BPF_K:
+ if (unlikely(imm > 63))
+ return -EINVAL;
+ emit_a32_lsh_i64(dst, dstk, imm, ctx);
+ break;
+ /* dst = dst >> imm */
+ case BPF_ALU64 | BPF_RSH | BPF_K:
+ if (unlikely(imm > 63))
+ return -EINVAL;
+ emit_a32_lsr_i64(dst, dstk, imm, ctx);
+ break;
+ /* dst = dst << src */
+ case BPF_ALU64 | BPF_LSH | BPF_X:
+ emit_a32_lsh_r64(dst, src, dstk, sstk, ctx);
+ break;
+ /* dst = dst >> src */
+ case BPF_ALU64 | BPF_RSH | BPF_X:
+ emit_a32_lsr_r64(dst, src, dstk, sstk, ctx);
+ break;
+ /* dst = dst >> src (signed) */
+ case BPF_ALU64 | BPF_ARSH | BPF_X:
+ emit_a32_arsh_r64(dst, src, dstk, sstk, ctx);
+ break;
+ /* dst = dst >> imm (signed) */
+ case BPF_ALU64 | BPF_ARSH | BPF_K:
+ if (unlikely(imm > 63))
+ return -EINVAL;
+ emit_a32_arsh_i64(dst, dstk, imm, ctx);
+ break;
+ /* dst = ~dst */
+ case BPF_ALU | BPF_NEG:
+ emit_a32_alu_i(dst_lo, 0, dstk, ctx, BPF_OP(code));
+ emit_a32_mov_i(dst_hi, 0, dstk, ctx);
+ break;
+ /* dst = ~dst (64 bit) */
+ case BPF_ALU64 | BPF_NEG:
+ emit_a32_neg64(dst, dstk, ctx);
+ break;
+ /* dst = dst * src/imm */
+ case BPF_ALU64 | BPF_MUL | BPF_X:
+ case BPF_ALU64 | BPF_MUL | BPF_K:
+ switch (BPF_SRC(code)) {
+ case BPF_X:
+ emit_a32_mul_r64(dst, src, dstk, sstk, ctx);
break;
- case BPF_LDX | BPF_B | BPF_MSH:
- /* x = ((*(frame + k)) & 0xf) << 2; */
- ctx->seen |= SEEN_X | SEEN_DATA | SEEN_CALL;
- /* the interpreter should deal with the negative K */
- if ((int)k < 0)
- return -1;
- /* offset in r1: we might have to take the slow path */
- emit_mov_i(r_off, k, ctx);
- emit(ARM_CMP_R(r_skb_hl, r_off), ctx);
-
- /* load in r0: common with the slowpath */
- _emit(ARM_COND_HI, ARM_LDRB_R(ARM_R0, r_skb_data,
- ARM_R1), ctx);
- /*
- * emit_mov_i() might generate one or two instructions,
- * the same holds for emit_blx_r()
+ case BPF_K:
+ /* Move immediate value to the temporary register
+ * and then do the multiplication on it as this
+ * will sign-extend the immediate value into temp
+ * reg then it would be safe to do the operation
+ * on it.
*/
- _emit(ARM_COND_HI, ARM_B(b_imm(i + 1, ctx) - 2), ctx);
-
- emit(ARM_MOV_R(ARM_R0, r_skb), ctx);
- /* r_off is r1 */
- emit_mov_i(ARM_R3, (u32)jit_get_skb_b, ctx);
- emit_blx_r(ARM_R3, ctx);
- /* check the return value of skb_copy_bits */
- emit(ARM_CMP_I(ARM_R1, 0), ctx);
- emit_err_ret(ARM_COND_NE, ctx);
-
- emit(ARM_AND_I(r_X, ARM_R0, 0x00f), ctx);
- emit(ARM_LSL_I(r_X, r_X, 2), ctx);
- break;
- case BPF_ST:
- ctx->seen |= SEEN_MEM_WORD(k);
- emit(ARM_STR_I(r_A, ARM_SP, SCRATCH_OFF(k)), ctx);
- break;
- case BPF_STX:
- update_on_xread(ctx);
- ctx->seen |= SEEN_MEM_WORD(k);
- emit(ARM_STR_I(r_X, ARM_SP, SCRATCH_OFF(k)), ctx);
- break;
- case BPF_ALU | BPF_ADD | BPF_K:
- /* A += K */
- OP_IMM3(ARM_ADD, r_A, r_A, k, ctx);
- break;
- case BPF_ALU | BPF_ADD | BPF_X:
- update_on_xread(ctx);
- emit(ARM_ADD_R(r_A, r_A, r_X), ctx);
- break;
- case BPF_ALU | BPF_SUB | BPF_K:
- /* A -= K */
- OP_IMM3(ARM_SUB, r_A, r_A, k, ctx);
- break;
- case BPF_ALU | BPF_SUB | BPF_X:
- update_on_xread(ctx);
- emit(ARM_SUB_R(r_A, r_A, r_X), ctx);
- break;
- case BPF_ALU | BPF_MUL | BPF_K:
- /* A *= K */
- emit_mov_i(r_scratch, k, ctx);
- emit(ARM_MUL(r_A, r_A, r_scratch), ctx);
- break;
- case BPF_ALU | BPF_MUL | BPF_X:
- update_on_xread(ctx);
- emit(ARM_MUL(r_A, r_A, r_X), ctx);
+ emit_a32_mov_i64(is64, tmp2, imm, false, ctx);
+ emit_a32_mul_r64(dst, tmp2, dstk, false, ctx);
break;
- case BPF_ALU | BPF_DIV | BPF_K:
- if (k == 1)
- break;
- emit_mov_i(r_scratch, k, ctx);
- emit_udivmod(r_A, r_A, r_scratch, ctx, BPF_DIV);
- break;
- case BPF_ALU | BPF_DIV | BPF_X:
- update_on_xread(ctx);
- emit(ARM_CMP_I(r_X, 0), ctx);
- emit_err_ret(ARM_COND_EQ, ctx);
- emit_udivmod(r_A, r_A, r_X, ctx, BPF_DIV);
+ }
+ break;
+ /* dst = htole(dst) */
+ /* dst = htobe(dst) */
+ case BPF_ALU | BPF_END | BPF_FROM_LE:
+ case BPF_ALU | BPF_END | BPF_FROM_BE:
+ rd = dstk ? tmp[0] : dst_hi;
+ rt = dstk ? tmp[1] : dst_lo;
+ if (dstk) {
+ emit(ARM_LDR_I(rt, ARM_SP, STACK_VAR(dst_lo)), ctx);
+ emit(ARM_LDR_I(rd, ARM_SP, STACK_VAR(dst_hi)), ctx);
+ }
+ if (BPF_SRC(code) == BPF_FROM_LE)
+ goto emit_bswap_uxt;
+ switch (imm) {
+ case 16:
+ emit_rev16(rt, rt, ctx);
+ goto emit_bswap_uxt;
+ case 32:
+ emit_rev32(rt, rt, ctx);
+ goto emit_bswap_uxt;
+ case 64:
+ /* Because of the usage of ARM_LR */
+ ctx->seen |= SEEN_CALL;
+ emit_rev32(ARM_LR, rt, ctx);
+ emit_rev32(rt, rd, ctx);
+ emit(ARM_MOV_R(rd, ARM_LR), ctx);
break;
- case BPF_ALU | BPF_MOD | BPF_K:
- if (k == 1) {
- emit_mov_i(r_A, 0, ctx);
- break;
- }
- emit_mov_i(r_scratch, k, ctx);
- emit_udivmod(r_A, r_A, r_scratch, ctx, BPF_MOD);
+ }
+ goto exit;
+emit_bswap_uxt:
+ switch (imm) {
+ case 16:
+ /* zero-extend 16 bits into 64 bits */
+#if __LINUX_ARM_ARCH__ < 6
+ emit_a32_mov_i(tmp2[1], 0xffff, false, ctx);
+ emit(ARM_AND_R(rt, rt, tmp2[1]), ctx);
+#else /* ARMv6+ */
+ emit(ARM_UXTH(rt, rt), ctx);
+#endif
+ emit(ARM_EOR_R(rd, rd, rd), ctx);
break;
- case BPF_ALU | BPF_MOD | BPF_X:
- update_on_xread(ctx);
- emit(ARM_CMP_I(r_X, 0), ctx);
- emit_err_ret(ARM_COND_EQ, ctx);
- emit_udivmod(r_A, r_A, r_X, ctx, BPF_MOD);
+ case 32:
+ /* zero-extend 32 bits into 64 bits */
+ emit(ARM_EOR_R(rd, rd, rd), ctx);
break;
- case BPF_ALU | BPF_OR | BPF_K:
- /* A |= K */
- OP_IMM3(ARM_ORR, r_A, r_A, k, ctx);
+ case 64:
+ /* nop */
break;
- case BPF_ALU | BPF_OR | BPF_X:
- update_on_xread(ctx);
- emit(ARM_ORR_R(r_A, r_A, r_X), ctx);
+ }
+exit:
+ if (dstk) {
+ emit(ARM_STR_I(rt, ARM_SP, STACK_VAR(dst_lo)), ctx);
+ emit(ARM_STR_I(rd, ARM_SP, STACK_VAR(dst_hi)), ctx);
+ }
+ break;
+ /* dst = imm64 */
+ case BPF_LD | BPF_IMM | BPF_DW:
+ {
+ const struct bpf_insn insn1 = insn[1];
+ u32 hi, lo = imm;
+
+ hi = insn1.imm;
+ emit_a32_mov_i(dst_lo, lo, dstk, ctx);
+ emit_a32_mov_i(dst_hi, hi, dstk, ctx);
+
+ return 1;
+ }
+ /* LDX: dst = *(size *)(src + off) */
+ case BPF_LDX | BPF_MEM | BPF_W:
+ case BPF_LDX | BPF_MEM | BPF_H:
+ case BPF_LDX | BPF_MEM | BPF_B:
+ case BPF_LDX | BPF_MEM | BPF_DW:
+ rn = sstk ? tmp2[1] : src_lo;
+ if (sstk)
+ emit(ARM_LDR_I(rn, ARM_SP, STACK_VAR(src_lo)), ctx);
+ switch (BPF_SIZE(code)) {
+ case BPF_W:
+ /* Load a Word */
+ case BPF_H:
+ /* Load a Half-Word */
+ case BPF_B:
+ /* Load a Byte */
+ emit_ldx_r(dst_lo, rn, dstk, off, ctx, BPF_SIZE(code));
+ emit_a32_mov_i(dst_hi, 0, dstk, ctx);
break;
- case BPF_ALU | BPF_XOR | BPF_K:
- /* A ^= K; */
- OP_IMM3(ARM_EOR, r_A, r_A, k, ctx);
+ case BPF_DW:
+ /* Load a double word */
+ emit_ldx_r(dst_lo, rn, dstk, off, ctx, BPF_W);
+ emit_ldx_r(dst_hi, rn, dstk, off+4, ctx, BPF_W);
break;
- case BPF_ANC | SKF_AD_ALU_XOR_X:
- case BPF_ALU | BPF_XOR | BPF_X:
- /* A ^= X */
- update_on_xread(ctx);
- emit(ARM_EOR_R(r_A, r_A, r_X), ctx);
+ }
+ break;
+ /* R0 = ntohx(*(size *)(((struct sk_buff *)R6)->data + imm)) */
+ case BPF_LD | BPF_ABS | BPF_W:
+ case BPF_LD | BPF_ABS | BPF_H:
+ case BPF_LD | BPF_ABS | BPF_B:
+ /* R0 = ntohx(*(size *)(((struct sk_buff *)R6)->data + src + imm)) */
+ case BPF_LD | BPF_IND | BPF_W:
+ case BPF_LD | BPF_IND | BPF_H:
+ case BPF_LD | BPF_IND | BPF_B:
+ {
+ const u8 r4 = bpf2a32[BPF_REG_6][1]; /* r4 = ptr to sk_buff */
+ const u8 r0 = bpf2a32[BPF_REG_0][1]; /*r0: struct sk_buff *skb*/
+ /* rtn value */
+ const u8 r1 = bpf2a32[BPF_REG_0][0]; /* r1: int k */
+ const u8 r2 = bpf2a32[BPF_REG_1][1]; /* r2: unsigned int size */
+ const u8 r3 = bpf2a32[BPF_REG_1][0]; /* r3: void *buffer */
+ const u8 r6 = bpf2a32[TMP_REG_1][1]; /* r6: void *(*func)(..) */
+ int size;
+
+ /* Setting up first argument */
+ emit(ARM_MOV_R(r0, r4), ctx);
+
+ /* Setting up second argument */
+ emit_a32_mov_i(r1, imm, false, ctx);
+ if (BPF_MODE(code) == BPF_IND)
+ emit_a32_alu_r(r1, src_lo, false, sstk, ctx,
+ false, false, BPF_ADD);
+
+ /* Setting up third argument */
+ switch (BPF_SIZE(code)) {
+ case BPF_W:
+ size = 4;
break;
- case BPF_ALU | BPF_AND | BPF_K:
- /* A &= K */
- OP_IMM3(ARM_AND, r_A, r_A, k, ctx);
+ case BPF_H:
+ size = 2;
break;
- case BPF_ALU | BPF_AND | BPF_X:
- update_on_xread(ctx);
- emit(ARM_AND_R(r_A, r_A, r_X), ctx);
+ case BPF_B:
+ size = 1;
break;
- case BPF_ALU | BPF_LSH | BPF_K:
- if (unlikely(k > 31))
- return -1;
- emit(ARM_LSL_I(r_A, r_A, k), ctx);
+ default:
+ return -EINVAL;
+ }
+ emit_a32_mov_i(r2, size, false, ctx);
+
+ /* Setting up fourth argument */
+ emit(ARM_ADD_I(r3, ARM_SP, imm8m(SKB_BUFFER)), ctx);
+
+ /* Setting up function pointer to call */
+ emit_a32_mov_i(r6, (unsigned int)bpf_load_pointer, false, ctx);
+ emit_blx_r(r6, ctx);
+
+ emit(ARM_EOR_R(r1, r1, r1), ctx);
+ /* Check if return address is NULL or not.
+ * if NULL then jump to epilogue
+ * else continue to load the value from retn address
+ */
+ emit(ARM_CMP_I(r0, 0), ctx);
+ jmp_offset = epilogue_offset(ctx);
+ check_imm24(jmp_offset);
+ _emit(ARM_COND_EQ, ARM_B(jmp_offset), ctx);
+
+ /* Load value from the address */
+ switch (BPF_SIZE(code)) {
+ case BPF_W:
+ emit(ARM_LDR_I(r0, r0, 0), ctx);
+ emit_rev32(r0, r0, ctx);
break;
- case BPF_ALU | BPF_LSH | BPF_X:
- update_on_xread(ctx);
- emit(ARM_LSL_R(r_A, r_A, r_X), ctx);
+ case BPF_H:
+ emit(ARM_LDRH_I(r0, r0, 0), ctx);
+ emit_rev16(r0, r0, ctx);
break;
- case BPF_ALU | BPF_RSH | BPF_K:
- if (unlikely(k > 31))
- return -1;
- if (k)
- emit(ARM_LSR_I(r_A, r_A, k), ctx);
+ case BPF_B:
+ emit(ARM_LDRB_I(r0, r0, 0), ctx);
+ /* No need to reverse */
break;
- case BPF_ALU | BPF_RSH | BPF_X:
- update_on_xread(ctx);
- emit(ARM_LSR_R(r_A, r_A, r_X), ctx);
+ }
+ break;
+ }
+ /* ST: *(size *)(dst + off) = imm */
+ case BPF_ST | BPF_MEM | BPF_W:
+ case BPF_ST | BPF_MEM | BPF_H:
+ case BPF_ST | BPF_MEM | BPF_B:
+ case BPF_ST | BPF_MEM | BPF_DW:
+ switch (BPF_SIZE(code)) {
+ case BPF_DW:
+ /* Sign-extend immediate value into temp reg */
+ emit_a32_mov_i64(true, tmp2, imm, false, ctx);
+ emit_str_r(dst_lo, tmp2[1], dstk, off, ctx, BPF_W);
+ emit_str_r(dst_lo, tmp2[0], dstk, off+4, ctx, BPF_W);
break;
- case BPF_ALU | BPF_NEG:
- /* A = -A */
- emit(ARM_RSB_I(r_A, r_A, 0), ctx);
+ case BPF_W:
+ case BPF_H:
+ case BPF_B:
+ emit_a32_mov_i(tmp2[1], imm, false, ctx);
+ emit_str_r(dst_lo, tmp2[1], dstk, off, ctx,
+ BPF_SIZE(code));
break;
- case BPF_JMP | BPF_JA:
- /* pc += K */
- emit(ARM_B(b_imm(i + k + 1, ctx)), ctx);
+ }
+ break;
+ /* STX XADD: lock *(u32 *)(dst + off) += src */
+ case BPF_STX | BPF_XADD | BPF_W:
+ /* STX XADD: lock *(u64 *)(dst + off) += src */
+ case BPF_STX | BPF_XADD | BPF_DW:
+ goto notyet;
+ /* STX: *(size *)(dst + off) = src */
+ case BPF_STX | BPF_MEM | BPF_W:
+ case BPF_STX | BPF_MEM | BPF_H:
+ case BPF_STX | BPF_MEM | BPF_B:
+ case BPF_STX | BPF_MEM | BPF_DW:
+ {
+ u8 sz = BPF_SIZE(code);
+
+ rn = sstk ? tmp2[1] : src_lo;
+ rm = sstk ? tmp2[0] : src_hi;
+ if (sstk) {
+ emit(ARM_LDR_I(rn, ARM_SP, STACK_VAR(src_lo)), ctx);
+ emit(ARM_LDR_I(rm, ARM_SP, STACK_VAR(src_hi)), ctx);
+ }
+
+ /* Store the value */
+ if (BPF_SIZE(code) == BPF_DW) {
+ emit_str_r(dst_lo, rn, dstk, off, ctx, BPF_W);
+ emit_str_r(dst_lo, rm, dstk, off+4, ctx, BPF_W);
+ } else {
+ emit_str_r(dst_lo, rn, dstk, off, ctx, sz);
+ }
+ break;
+ }
+ /* PC += off if dst == src */
+ /* PC += off if dst > src */
+ /* PC += off if dst >= src */
+ /* PC += off if dst < src */
+ /* PC += off if dst <= src */
+ /* PC += off if dst != src */
+ /* PC += off if dst > src (signed) */
+ /* PC += off if dst >= src (signed) */
+ /* PC += off if dst < src (signed) */
+ /* PC += off if dst <= src (signed) */
+ /* PC += off if dst & src */
+ case BPF_JMP | BPF_JEQ | BPF_X:
+ case BPF_JMP | BPF_JGT | BPF_X:
+ case BPF_JMP | BPF_JGE | BPF_X:
+ case BPF_JMP | BPF_JNE | BPF_X:
+ case BPF_JMP | BPF_JSGT | BPF_X:
+ case BPF_JMP | BPF_JSGE | BPF_X:
+ case BPF_JMP | BPF_JSET | BPF_X:
+ case BPF_JMP | BPF_JLE | BPF_X:
+ case BPF_JMP | BPF_JLT | BPF_X:
+ case BPF_JMP | BPF_JSLT | BPF_X:
+ case BPF_JMP | BPF_JSLE | BPF_X:
+ /* Setup source registers */
+ rm = sstk ? tmp2[0] : src_hi;
+ rn = sstk ? tmp2[1] : src_lo;
+ if (sstk) {
+ emit(ARM_LDR_I(rn, ARM_SP, STACK_VAR(src_lo)), ctx);
+ emit(ARM_LDR_I(rm, ARM_SP, STACK_VAR(src_hi)), ctx);
+ }
+ goto go_jmp;
+ /* PC += off if dst == imm */
+ /* PC += off if dst > imm */
+ /* PC += off if dst >= imm */
+ /* PC += off if dst < imm */
+ /* PC += off if dst <= imm */
+ /* PC += off if dst != imm */
+ /* PC += off if dst > imm (signed) */
+ /* PC += off if dst >= imm (signed) */
+ /* PC += off if dst < imm (signed) */
+ /* PC += off if dst <= imm (signed) */
+ /* PC += off if dst & imm */
+ case BPF_JMP | BPF_JEQ | BPF_K:
+ case BPF_JMP | BPF_JGT | BPF_K:
+ case BPF_JMP | BPF_JGE | BPF_K:
+ case BPF_JMP | BPF_JNE | BPF_K:
+ case BPF_JMP | BPF_JSGT | BPF_K:
+ case BPF_JMP | BPF_JSGE | BPF_K:
+ case BPF_JMP | BPF_JSET | BPF_K:
+ case BPF_JMP | BPF_JLT | BPF_K:
+ case BPF_JMP | BPF_JLE | BPF_K:
+ case BPF_JMP | BPF_JSLT | BPF_K:
+ case BPF_JMP | BPF_JSLE | BPF_K:
+ if (off == 0)
break;
- case BPF_JMP | BPF_JEQ | BPF_K:
- /* pc += (A == K) ? pc->jt : pc->jf */
- condt = ARM_COND_EQ;
- goto cmp_imm;
- case BPF_JMP | BPF_JGT | BPF_K:
- /* pc += (A > K) ? pc->jt : pc->jf */
- condt = ARM_COND_HI;
- goto cmp_imm;
- case BPF_JMP | BPF_JGE | BPF_K:
- /* pc += (A >= K) ? pc->jt : pc->jf */
- condt = ARM_COND_HS;
-cmp_imm:
- imm12 = imm8m(k);
- if (imm12 < 0) {
- emit_mov_i_no8m(r_scratch, k, ctx);
- emit(ARM_CMP_R(r_A, r_scratch), ctx);
- } else {
- emit(ARM_CMP_I(r_A, imm12), ctx);
- }
-cond_jump:
- if (inst->jt)
- _emit(condt, ARM_B(b_imm(i + inst->jt + 1,
- ctx)), ctx);
- if (inst->jf)
- _emit(condt ^ 1, ARM_B(b_imm(i + inst->jf + 1,
- ctx)), ctx);
+ rm = tmp2[0];
+ rn = tmp2[1];
+ /* Sign-extend immediate value */
+ emit_a32_mov_i64(true, tmp2, imm, false, ctx);
+go_jmp:
+ /* Setup destination register */
+ rd = dstk ? tmp[0] : dst_hi;
+ rt = dstk ? tmp[1] : dst_lo;
+ if (dstk) {
+ emit(ARM_LDR_I(rt, ARM_SP, STACK_VAR(dst_lo)), ctx);
+ emit(ARM_LDR_I(rd, ARM_SP, STACK_VAR(dst_hi)), ctx);
+ }
+
+ /* Check for the condition */
+ emit_ar_r(rd, rt, rm, rn, ctx, BPF_OP(code));
+
+ /* Setup JUMP instruction */
+ jmp_offset = bpf2a32_offset(i+off, i, ctx);
+ switch (BPF_OP(code)) {
+ case BPF_JNE:
+ case BPF_JSET:
+ _emit(ARM_COND_NE, ARM_B(jmp_offset), ctx);
break;
- case BPF_JMP | BPF_JEQ | BPF_X:
- /* pc += (A == X) ? pc->jt : pc->jf */
- condt = ARM_COND_EQ;
- goto cmp_x;
- case BPF_JMP | BPF_JGT | BPF_X:
- /* pc += (A > X) ? pc->jt : pc->jf */
- condt = ARM_COND_HI;
- goto cmp_x;
- case BPF_JMP | BPF_JGE | BPF_X:
- /* pc += (A >= X) ? pc->jt : pc->jf */
- condt = ARM_COND_CS;
-cmp_x:
- update_on_xread(ctx);
- emit(ARM_CMP_R(r_A, r_X), ctx);
- goto cond_jump;
- case BPF_JMP | BPF_JSET | BPF_K:
- /* pc += (A & K) ? pc->jt : pc->jf */
- condt = ARM_COND_NE;
- /* not set iff all zeroes iff Z==1 iff EQ */
-
- imm12 = imm8m(k);
- if (imm12 < 0) {
- emit_mov_i_no8m(r_scratch, k, ctx);
- emit(ARM_TST_R(r_A, r_scratch), ctx);
- } else {
- emit(ARM_TST_I(r_A, imm12), ctx);
- }
- goto cond_jump;
- case BPF_JMP | BPF_JSET | BPF_X:
- /* pc += (A & X) ? pc->jt : pc->jf */
- update_on_xread(ctx);
- condt = ARM_COND_NE;
- emit(ARM_TST_R(r_A, r_X), ctx);
- goto cond_jump;
- case BPF_RET | BPF_A:
- emit(ARM_MOV_R(ARM_R0, r_A), ctx);
- goto b_epilogue;
- case BPF_RET | BPF_K:
- if ((k == 0) && (ctx->ret0_fp_idx < 0))
- ctx->ret0_fp_idx = i;
- emit_mov_i(ARM_R0, k, ctx);
-b_epilogue:
- if (i != ctx->skf->len - 1)
- emit(ARM_B(b_imm(prog->len, ctx)), ctx);
+ case BPF_JEQ:
+ _emit(ARM_COND_EQ, ARM_B(jmp_offset), ctx);
break;
- case BPF_MISC | BPF_TAX:
- /* X = A */
- ctx->seen |= SEEN_X;
- emit(ARM_MOV_R(r_X, r_A), ctx);
+ case BPF_JGT:
+ _emit(ARM_COND_HI, ARM_B(jmp_offset), ctx);
break;
- case BPF_MISC | BPF_TXA:
- /* A = X */
- update_on_xread(ctx);
- emit(ARM_MOV_R(r_A, r_X), ctx);
+ case BPF_JGE:
+ _emit(ARM_COND_CS, ARM_B(jmp_offset), ctx);
break;
- case BPF_ANC | SKF_AD_PROTOCOL:
- /* A = ntohs(skb->protocol) */
- ctx->seen |= SEEN_SKB;
- BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff,
- protocol) != 2);
- off = offsetof(struct sk_buff, protocol);
- emit(ARM_LDRH_I(r_scratch, r_skb, off), ctx);
- emit_swap16(r_A, r_scratch, ctx);
+ case BPF_JSGT:
+ _emit(ARM_COND_LT, ARM_B(jmp_offset), ctx);
break;
- case BPF_ANC | SKF_AD_CPU:
- /* r_scratch = current_thread_info() */
- OP_IMM3(ARM_BIC, r_scratch, ARM_SP, THREAD_SIZE - 1, ctx);
- /* A = current_thread_info()->cpu */
- BUILD_BUG_ON(FIELD_SIZEOF(struct thread_info, cpu) != 4);
- off = offsetof(struct thread_info, cpu);
- emit(ARM_LDR_I(r_A, r_scratch, off), ctx);
+ case BPF_JSGE:
+ _emit(ARM_COND_GE, ARM_B(jmp_offset), ctx);
break;
- case BPF_ANC | SKF_AD_IFINDEX:
- case BPF_ANC | SKF_AD_HATYPE:
- /* A = skb->dev->ifindex */
- /* A = skb->dev->type */
- ctx->seen |= SEEN_SKB;
- off = offsetof(struct sk_buff, dev);
- emit(ARM_LDR_I(r_scratch, r_skb, off), ctx);
-
- emit(ARM_CMP_I(r_scratch, 0), ctx);
- emit_err_ret(ARM_COND_EQ, ctx);
-
- BUILD_BUG_ON(FIELD_SIZEOF(struct net_device,
- ifindex) != 4);
- BUILD_BUG_ON(FIELD_SIZEOF(struct net_device,
- type) != 2);
-
- if (code == (BPF_ANC | SKF_AD_IFINDEX)) {
- off = offsetof(struct net_device, ifindex);
- emit(ARM_LDR_I(r_A, r_scratch, off), ctx);
- } else {
- /*
- * offset of field "type" in "struct
- * net_device" is above what can be
- * used in the ldrh rd, [rn, #imm]
- * instruction, so load the offset in
- * a register and use ldrh rd, [rn, rm]
- */
- off = offsetof(struct net_device, type);
- emit_mov_i(ARM_R3, off, ctx);
- emit(ARM_LDRH_R(r_A, r_scratch, ARM_R3), ctx);
- }
+ case BPF_JLE:
+ _emit(ARM_COND_LS, ARM_B(jmp_offset), ctx);
break;
- case BPF_ANC | SKF_AD_MARK:
- ctx->seen |= SEEN_SKB;
- BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, mark) != 4);
- off = offsetof(struct sk_buff, mark);
- emit(ARM_LDR_I(r_A, r_skb, off), ctx);
+ case BPF_JLT:
+ _emit(ARM_COND_CC, ARM_B(jmp_offset), ctx);
break;
- case BPF_ANC | SKF_AD_RXHASH:
- ctx->seen |= SEEN_SKB;
- BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, hash) != 4);
- off = offsetof(struct sk_buff, hash);
- emit(ARM_LDR_I(r_A, r_skb, off), ctx);
+ case BPF_JSLT:
+ _emit(ARM_COND_LT, ARM_B(jmp_offset), ctx);
break;
- case BPF_ANC | SKF_AD_VLAN_TAG:
- case BPF_ANC | SKF_AD_VLAN_TAG_PRESENT:
- ctx->seen |= SEEN_SKB;
- BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, vlan_tci) != 2);
- off = offsetof(struct sk_buff, vlan_tci);
- emit(ARM_LDRH_I(r_A, r_skb, off), ctx);
- if (code == (BPF_ANC | SKF_AD_VLAN_TAG))
- OP_IMM3(ARM_AND, r_A, r_A, ~VLAN_TAG_PRESENT, ctx);
- else {
- OP_IMM3(ARM_LSR, r_A, r_A, 12, ctx);
- OP_IMM3(ARM_AND, r_A, r_A, 0x1, ctx);
- }
+ case BPF_JSLE:
+ _emit(ARM_COND_GE, ARM_B(jmp_offset), ctx);
break;
- case BPF_ANC | SKF_AD_PKTTYPE:
- ctx->seen |= SEEN_SKB;
- BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff,
- __pkt_type_offset[0]) != 1);
- off = PKT_TYPE_OFFSET();
- emit(ARM_LDRB_I(r_A, r_skb, off), ctx);
- emit(ARM_AND_I(r_A, r_A, PKT_TYPE_MAX), ctx);
-#ifdef __BIG_ENDIAN_BITFIELD
- emit(ARM_LSR_I(r_A, r_A, 5), ctx);
-#endif
+ }
+ break;
+ /* JMP OFF */
+ case BPF_JMP | BPF_JA:
+ {
+ if (off == 0)
break;
- case BPF_ANC | SKF_AD_QUEUE:
- ctx->seen |= SEEN_SKB;
- BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff,
- queue_mapping) != 2);
- BUILD_BUG_ON(offsetof(struct sk_buff,
- queue_mapping) > 0xff);
- off = offsetof(struct sk_buff, queue_mapping);
- emit(ARM_LDRH_I(r_A, r_skb, off), ctx);
+ jmp_offset = bpf2a32_offset(i+off, i, ctx);
+ check_imm24(jmp_offset);
+ emit(ARM_B(jmp_offset), ctx);
+ break;
+ }
+ /* tail call */
+ case BPF_JMP | BPF_TAIL_CALL:
+ if (emit_bpf_tail_call(ctx))
+ return -EFAULT;
+ break;
+ /* function call */
+ case BPF_JMP | BPF_CALL:
+ {
+ const u8 *r0 = bpf2a32[BPF_REG_0];
+ const u8 *r1 = bpf2a32[BPF_REG_1];
+ const u8 *r2 = bpf2a32[BPF_REG_2];
+ const u8 *r3 = bpf2a32[BPF_REG_3];
+ const u8 *r4 = bpf2a32[BPF_REG_4];
+ const u8 *r5 = bpf2a32[BPF_REG_5];
+ const u32 func = (u32)__bpf_call_base + (u32)imm;
+
+ emit_a32_mov_r64(true, r0, r1, false, false, ctx);
+ emit_a32_mov_r64(true, r1, r2, false, true, ctx);
+ emit_push_r64(r5, 0, ctx);
+ emit_push_r64(r4, 8, ctx);
+ emit_push_r64(r3, 16, ctx);
+
+ emit_a32_mov_i(tmp[1], func, false, ctx);
+ emit_blx_r(tmp[1], ctx);
+
+ emit(ARM_ADD_I(ARM_SP, ARM_SP, imm8m(24)), ctx); // callee clean
+ break;
+ }
+ /* function return */
+ case BPF_JMP | BPF_EXIT:
+ /* Optimization: when last instruction is EXIT
+ * simply fallthrough to epilogue.
+ */
+ if (i == ctx->prog->len - 1)
break;
- case BPF_ANC | SKF_AD_PAY_OFFSET:
- ctx->seen |= SEEN_SKB | SEEN_CALL;
+ jmp_offset = epilogue_offset(ctx);
+ check_imm24(jmp_offset);
+ emit(ARM_B(jmp_offset), ctx);
+ break;
+notyet:
+ pr_info_once("*** NOT YET: opcode %02x ***\n", code);
+ return -EFAULT;
+ default:
+ pr_err_once("unknown opcode %02x\n", code);
+ return -EINVAL;
+ }
- emit(ARM_MOV_R(ARM_R0, r_skb), ctx);
- emit_mov_i(ARM_R3, (unsigned int)skb_get_poff, ctx);
- emit_blx_r(ARM_R3, ctx);
- emit(ARM_MOV_R(r_A, ARM_R0), ctx);
- break;
- case BPF_LDX | BPF_W | BPF_ABS:
- /*
- * load a 32bit word from struct seccomp_data.
- * seccomp_check_filter() will already have checked
- * that k is 32bit aligned and lies within the
- * struct seccomp_data.
- */
- ctx->seen |= SEEN_SKB;
- emit(ARM_LDR_I(r_A, r_skb, k), ctx);
- break;
- default:
- return -1;
+ if (ctx->flags & FLAG_IMM_OVERFLOW)
+ /*
+ * this instruction generated an overflow when
+ * trying to access the literal pool, so
+ * delegate this filter to the kernel interpreter.
+ */
+ return -1;
+ return 0;
+}
+
+static int build_body(struct jit_ctx *ctx)
+{
+ const struct bpf_prog *prog = ctx->prog;
+ unsigned int i;
+
+ for (i = 0; i < prog->len; i++) {
+ const struct bpf_insn *insn = &(prog->insnsi[i]);
+ int ret;
+
+ ret = build_insn(insn, ctx);
+
+ /* It's used with loading the 64 bit immediate value. */
+ if (ret > 0) {
+ i++;
+ if (ctx->target == NULL)
+ ctx->offsets[i] = ctx->idx;
+ continue;
}
- if (ctx->flags & FLAG_IMM_OVERFLOW)
- /*
- * this instruction generated an overflow when
- * trying to access the literal pool, so
- * delegate this filter to the kernel interpreter.
- */
- return -1;
+ if (ctx->target == NULL)
+ ctx->offsets[i] = ctx->idx;
+
+ /* If unsuccesfull, return with error code */
+ if (ret)
+ return ret;
}
+ return 0;
+}
- /* compute offsets only during the first pass */
- if (ctx->target == NULL)
- ctx->offsets[i] = ctx->idx * 4;
+static int validate_code(struct jit_ctx *ctx)
+{
+ int i;
+
+ for (i = 0; i < ctx->idx; i++) {
+ if (ctx->target[i] == __opcode_to_mem_arm(ARM_INST_UDF))
+ return -1;
+ }
return 0;
}
+void bpf_jit_compile(struct bpf_prog *prog)
+{
+ /* Nothing to do here. We support Internal BPF. */
+}
-void bpf_jit_compile(struct bpf_prog *fp)
+struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog)
{
+ struct bpf_prog *tmp, *orig_prog = prog;
struct bpf_binary_header *header;
+ bool tmp_blinded = false;
struct jit_ctx ctx;
- unsigned tmp_idx;
- unsigned alloc_size;
- u8 *target_ptr;
+ unsigned int tmp_idx;
+ unsigned int image_size;
+ u8 *image_ptr;
+ /* If BPF JIT was not enabled then we must fall back to
+ * the interpreter.
+ */
if (!bpf_jit_enable)
- return;
+ return orig_prog;
- memset(&ctx, 0, sizeof(ctx));
- ctx.skf = fp;
- ctx.ret0_fp_idx = -1;
+ /* If constant blinding was enabled and we failed during blinding
+ * then we must fall back to the interpreter. Otherwise, we save
+ * the new JITed code.
+ */
+ tmp = bpf_jit_blind_constants(prog);
- ctx.offsets = kzalloc(4 * (ctx.skf->len + 1), GFP_KERNEL);
- if (ctx.offsets == NULL)
- return;
+ if (IS_ERR(tmp))
+ return orig_prog;
+ if (tmp != prog) {
+ tmp_blinded = true;
+ prog = tmp;
+ }
- /* fake pass to fill in the ctx->seen */
- if (unlikely(build_body(&ctx)))
+ memset(&ctx, 0, sizeof(ctx));
+ ctx.prog = prog;
+
+ /* Not able to allocate memory for offsets[] , then
+ * we must fall back to the interpreter
+ */
+ ctx.offsets = kcalloc(prog->len, sizeof(int), GFP_KERNEL);
+ if (ctx.offsets == NULL) {
+ prog = orig_prog;
goto out;
+ }
+
+ /* 1) fake pass to find in the length of the JITed code,
+ * to compute ctx->offsets and other context variables
+ * needed to compute final JITed code.
+ * Also, calculate random starting pointer/start of JITed code
+ * which is prefixed by random number of fault instructions.
+ *
+ * If the first pass fails then there is no chance of it
+ * being successful in the second pass, so just fall back
+ * to the interpreter.
+ */
+ if (build_body(&ctx)) {
+ prog = orig_prog;
+ goto out_off;
+ }
tmp_idx = ctx.idx;
build_prologue(&ctx);
ctx.prologue_bytes = (ctx.idx - tmp_idx) * 4;
+ ctx.epilogue_offset = ctx.idx;
+
#if __LINUX_ARM_ARCH__ < 7
tmp_idx = ctx.idx;
build_epilogue(&ctx);
@@ -1021,64 +1880,83 @@ void bpf_jit_compile(struct bpf_prog *fp)
ctx.idx += ctx.imm_count;
if (ctx.imm_count) {
- ctx.imms = kzalloc(4 * ctx.imm_count, GFP_KERNEL);
- if (ctx.imms == NULL)
- goto out;
+ ctx.imms = kcalloc(ctx.imm_count, sizeof(u32), GFP_KERNEL);
+ if (ctx.imms == NULL) {
+ prog = orig_prog;
+ goto out_off;
+ }
}
#else
- /* there's nothing after the epilogue on ARMv7 */
+ /* there's nothing about the epilogue on ARMv7 */
build_epilogue(&ctx);
#endif
- alloc_size = 4 * ctx.idx;
- header = bpf_jit_binary_alloc(alloc_size, &target_ptr,
- 4, jit_fill_hole);
- if (header == NULL)
- goto out;
+ /* Now we can get the actual image size of the JITed arm code.
+ * Currently, we are not considering the THUMB-2 instructions
+ * for jit, although it can decrease the size of the image.
+ *
+ * As each arm instruction is of length 32bit, we are translating
+ * number of JITed intructions into the size required to store these
+ * JITed code.
+ */
+ image_size = sizeof(u32) * ctx.idx;
- ctx.target = (u32 *) target_ptr;
+ /* Now we know the size of the structure to make */
+ header = bpf_jit_binary_alloc(image_size, &image_ptr,
+ sizeof(u32), jit_fill_hole);
+ /* Not able to allocate memory for the structure then
+ * we must fall back to the interpretation
+ */
+ if (header == NULL) {
+ prog = orig_prog;
+ goto out_imms;
+ }
+
+ /* 2.) Actual pass to generate final JIT code */
+ ctx.target = (u32 *) image_ptr;
ctx.idx = 0;
build_prologue(&ctx);
+
+ /* If building the body of the JITed code fails somehow,
+ * we fall back to the interpretation.
+ */
if (build_body(&ctx) < 0) {
-#if __LINUX_ARM_ARCH__ < 7
- if (ctx.imm_count)
- kfree(ctx.imms);
-#endif
+ image_ptr = NULL;
bpf_jit_binary_free(header);
- goto out;
+ prog = orig_prog;
+ goto out_imms;
}
build_epilogue(&ctx);
+ /* 3.) Extra pass to validate JITed Code */
+ if (validate_code(&ctx)) {
+ image_ptr = NULL;
+ bpf_jit_binary_free(header);
+ prog = orig_prog;
+ goto out_imms;
+ }
flush_icache_range((u32)header, (u32)(ctx.target + ctx.idx));
-#if __LINUX_ARM_ARCH__ < 7
- if (ctx.imm_count)
- kfree(ctx.imms);
-#endif
-
if (bpf_jit_enable > 1)
/* there are 2 passes here */
- bpf_jit_dump(fp->len, alloc_size, 2, ctx.target);
+ bpf_jit_dump(prog->len, image_size, 2, ctx.target);
set_memory_ro((unsigned long)header, header->pages);
- fp->bpf_func = (void *)ctx.target;
- fp->jited = 1;
-out:
+ prog->bpf_func = (void *)ctx.target;
+ prog->jited = 1;
+ prog->jited_len = image_size;
+
+out_imms:
+#if __LINUX_ARM_ARCH__ < 7
+ if (ctx.imm_count)
+ kfree(ctx.imms);
+#endif
+out_off:
kfree(ctx.offsets);
- return;
+out:
+ if (tmp_blinded)
+ bpf_jit_prog_release_other(prog, prog == orig_prog ?
+ tmp : orig_prog);
+ return prog;
}
-void bpf_jit_free(struct bpf_prog *fp)
-{
- unsigned long addr = (unsigned long)fp->bpf_func & PAGE_MASK;
- struct bpf_binary_header *header = (void *)addr;
-
- if (!fp->jited)
- goto free_filter;
-
- set_memory_rw(addr, header->pages);
- bpf_jit_binary_free(header);
-
-free_filter:
- bpf_prog_unlock_free(fp);
-}
diff --git a/arch/arm/net/bpf_jit_32.h b/arch/arm/net/bpf_jit_32.h
index c46fca2972f7..d5cf5f6208aa 100644
--- a/arch/arm/net/bpf_jit_32.h
+++ b/arch/arm/net/bpf_jit_32.h
@@ -11,6 +11,7 @@
#ifndef PFILTER_OPCODES_ARM_H
#define PFILTER_OPCODES_ARM_H
+/* ARM 32bit Registers */
#define ARM_R0 0
#define ARM_R1 1
#define ARM_R2 2
@@ -22,38 +23,43 @@
#define ARM_R8 8
#define ARM_R9 9
#define ARM_R10 10
-#define ARM_FP 11
-#define ARM_IP 12
-#define ARM_SP 13
-#define ARM_LR 14
-#define ARM_PC 15
-
-#define ARM_COND_EQ 0x0
-#define ARM_COND_NE 0x1
-#define ARM_COND_CS 0x2
+#define ARM_FP 11 /* Frame Pointer */
+#define ARM_IP 12 /* Intra-procedure scratch register */
+#define ARM_SP 13 /* Stack pointer: as load/store base reg */
+#define ARM_LR 14 /* Link Register */
+#define ARM_PC 15 /* Program counter */
+
+#define ARM_COND_EQ 0x0 /* == */
+#define ARM_COND_NE 0x1 /* != */
+#define ARM_COND_CS 0x2 /* unsigned >= */
#define ARM_COND_HS ARM_COND_CS
-#define ARM_COND_CC 0x3
+#define ARM_COND_CC 0x3 /* unsigned < */
#define ARM_COND_LO ARM_COND_CC
-#define ARM_COND_MI 0x4
-#define ARM_COND_PL 0x5
-#define ARM_COND_VS 0x6
-#define ARM_COND_VC 0x7
-#define ARM_COND_HI 0x8
-#define ARM_COND_LS 0x9
-#define ARM_COND_GE 0xa
-#define ARM_COND_LT 0xb
-#define ARM_COND_GT 0xc
-#define ARM_COND_LE 0xd
-#define ARM_COND_AL 0xe
+#define ARM_COND_MI 0x4 /* < 0 */
+#define ARM_COND_PL 0x5 /* >= 0 */
+#define ARM_COND_VS 0x6 /* Signed Overflow */
+#define ARM_COND_VC 0x7 /* No Signed Overflow */
+#define ARM_COND_HI 0x8 /* unsigned > */
+#define ARM_COND_LS 0x9 /* unsigned <= */
+#define ARM_COND_GE 0xa /* Signed >= */
+#define ARM_COND_LT 0xb /* Signed < */
+#define ARM_COND_GT 0xc /* Signed > */
+#define ARM_COND_LE 0xd /* Signed <= */
+#define ARM_COND_AL 0xe /* None */
/* register shift types */
#define SRTYPE_LSL 0
#define SRTYPE_LSR 1
#define SRTYPE_ASR 2
#define SRTYPE_ROR 3
+#define SRTYPE_ASL (SRTYPE_LSL)
#define ARM_INST_ADD_R 0x00800000
+#define ARM_INST_ADDS_R 0x00900000
+#define ARM_INST_ADC_R 0x00a00000
+#define ARM_INST_ADC_I 0x02a00000
#define ARM_INST_ADD_I 0x02800000
+#define ARM_INST_ADDS_I 0x02900000
#define ARM_INST_AND_R 0x00000000
#define ARM_INST_AND_I 0x02000000
@@ -76,8 +82,10 @@
#define ARM_INST_LDRH_I 0x01d000b0
#define ARM_INST_LDRH_R 0x019000b0
#define ARM_INST_LDR_I 0x05900000
+#define ARM_INST_LDR_R 0x07900000
#define ARM_INST_LDM 0x08900000
+#define ARM_INST_LDM_IA 0x08b00000
#define ARM_INST_LSL_I 0x01a00000
#define ARM_INST_LSL_R 0x01a00010
@@ -86,6 +94,7 @@
#define ARM_INST_LSR_R 0x01a00030
#define ARM_INST_MOV_R 0x01a00000
+#define ARM_INST_MOVS_R 0x01b00000
#define ARM_INST_MOV_I 0x03a00000
#define ARM_INST_MOVW 0x03000000
#define ARM_INST_MOVT 0x03400000
@@ -96,17 +105,28 @@
#define ARM_INST_PUSH 0x092d0000
#define ARM_INST_ORR_R 0x01800000
+#define ARM_INST_ORRS_R 0x01900000
#define ARM_INST_ORR_I 0x03800000
#define ARM_INST_REV 0x06bf0f30
#define ARM_INST_REV16 0x06bf0fb0
#define ARM_INST_RSB_I 0x02600000
+#define ARM_INST_RSBS_I 0x02700000
+#define ARM_INST_RSC_I 0x02e00000
#define ARM_INST_SUB_R 0x00400000
+#define ARM_INST_SUBS_R 0x00500000
+#define ARM_INST_RSB_R 0x00600000
#define ARM_INST_SUB_I 0x02400000
+#define ARM_INST_SUBS_I 0x02500000
+#define ARM_INST_SBC_I 0x02c00000
+#define ARM_INST_SBC_R 0x00c00000
+#define ARM_INST_SBCS_R 0x00d00000
#define ARM_INST_STR_I 0x05800000
+#define ARM_INST_STRB_I 0x05c00000
+#define ARM_INST_STRH_I 0x01c000b0
#define ARM_INST_TST_R 0x01100000
#define ARM_INST_TST_I 0x03100000
@@ -117,6 +137,8 @@
#define ARM_INST_MLS 0x00600090
+#define ARM_INST_UXTH 0x06ff0070
+
/*
* Use a suitable undefined instruction to use for ARM/Thumb2 faulting.
* We need to be careful not to conflict with those used by other modules
@@ -135,9 +157,15 @@
#define _AL3_R(op, rd, rn, rm) ((op ## _R) | (rd) << 12 | (rn) << 16 | (rm))
/* immediate */
#define _AL3_I(op, rd, rn, imm) ((op ## _I) | (rd) << 12 | (rn) << 16 | (imm))
+/* register with register-shift */
+#define _AL3_SR(inst) (inst | (1 << 4))
#define ARM_ADD_R(rd, rn, rm) _AL3_R(ARM_INST_ADD, rd, rn, rm)
+#define ARM_ADDS_R(rd, rn, rm) _AL3_R(ARM_INST_ADDS, rd, rn, rm)
#define ARM_ADD_I(rd, rn, imm) _AL3_I(ARM_INST_ADD, rd, rn, imm)
+#define ARM_ADDS_I(rd, rn, imm) _AL3_I(ARM_INST_ADDS, rd, rn, imm)
+#define ARM_ADC_R(rd, rn, rm) _AL3_R(ARM_INST_ADC, rd, rn, rm)
+#define ARM_ADC_I(rd, rn, imm) _AL3_I(ARM_INST_ADC, rd, rn, imm)
#define ARM_AND_R(rd, rn, rm) _AL3_R(ARM_INST_AND, rd, rn, rm)
#define ARM_AND_I(rd, rn, imm) _AL3_I(ARM_INST_AND, rd, rn, imm)
@@ -156,7 +184,9 @@
#define ARM_EOR_I(rd, rn, imm) _AL3_I(ARM_INST_EOR, rd, rn, imm)
#define ARM_LDR_I(rt, rn, off) (ARM_INST_LDR_I | (rt) << 12 | (rn) << 16 \
- | (off))
+ | ((off) & 0xfff))
+#define ARM_LDR_R(rt, rn, rm) (ARM_INST_LDR_R | (rt) << 12 | (rn) << 16 \
+ | (rm))
#define ARM_LDRB_I(rt, rn, off) (ARM_INST_LDRB_I | (rt) << 12 | (rn) << 16 \
| (off))
#define ARM_LDRB_R(rt, rn, rm) (ARM_INST_LDRB_R | (rt) << 12 | (rn) << 16 \
@@ -167,15 +197,23 @@
| (rm))
#define ARM_LDM(rn, regs) (ARM_INST_LDM | (rn) << 16 | (regs))
+#define ARM_LDM_IA(rn, regs) (ARM_INST_LDM_IA | (rn) << 16 | (regs))
#define ARM_LSL_R(rd, rn, rm) (_AL3_R(ARM_INST_LSL, rd, 0, rn) | (rm) << 8)
#define ARM_LSL_I(rd, rn, imm) (_AL3_I(ARM_INST_LSL, rd, 0, rn) | (imm) << 7)
#define ARM_LSR_R(rd, rn, rm) (_AL3_R(ARM_INST_LSR, rd, 0, rn) | (rm) << 8)
#define ARM_LSR_I(rd, rn, imm) (_AL3_I(ARM_INST_LSR, rd, 0, rn) | (imm) << 7)
+#define ARM_ASR_R(rd, rn, rm) (_AL3_R(ARM_INST_ASR, rd, 0, rn) | (rm) << 8)
+#define ARM_ASR_I(rd, rn, imm) (_AL3_I(ARM_INST_ASR, rd, 0, rn) | (imm) << 7)
#define ARM_MOV_R(rd, rm) _AL3_R(ARM_INST_MOV, rd, 0, rm)
+#define ARM_MOVS_R(rd, rm) _AL3_R(ARM_INST_MOVS, rd, 0, rm)
#define ARM_MOV_I(rd, imm) _AL3_I(ARM_INST_MOV, rd, 0, imm)
+#define ARM_MOV_SR(rd, rm, type, rs) \
+ (_AL3_SR(ARM_MOV_R(rd, rm)) | (type) << 5 | (rs) << 8)
+#define ARM_MOV_SI(rd, rm, type, imm6) \
+ (ARM_MOV_R(rd, rm) | (type) << 5 | (imm6) << 7)
#define ARM_MOVW(rd, imm) \
(ARM_INST_MOVW | ((imm) >> 12) << 16 | (rd) << 12 | ((imm) & 0x0fff))
@@ -190,19 +228,38 @@
#define ARM_ORR_R(rd, rn, rm) _AL3_R(ARM_INST_ORR, rd, rn, rm)
#define ARM_ORR_I(rd, rn, imm) _AL3_I(ARM_INST_ORR, rd, rn, imm)
-#define ARM_ORR_S(rd, rn, rm, type, rs) \
- (ARM_ORR_R(rd, rn, rm) | (type) << 5 | (rs) << 7)
+#define ARM_ORR_SR(rd, rn, rm, type, rs) \
+ (_AL3_SR(ARM_ORR_R(rd, rn, rm)) | (type) << 5 | (rs) << 8)
+#define ARM_ORRS_R(rd, rn, rm) _AL3_R(ARM_INST_ORRS, rd, rn, rm)
+#define ARM_ORRS_SR(rd, rn, rm, type, rs) \
+ (_AL3_SR(ARM_ORRS_R(rd, rn, rm)) | (type) << 5 | (rs) << 8)
+#define ARM_ORR_SI(rd, rn, rm, type, imm6) \
+ (ARM_ORR_R(rd, rn, rm) | (type) << 5 | (imm6) << 7)
+#define ARM_ORRS_SI(rd, rn, rm, type, imm6) \
+ (ARM_ORRS_R(rd, rn, rm) | (type) << 5 | (imm6) << 7)
#define ARM_REV(rd, rm) (ARM_INST_REV | (rd) << 12 | (rm))
#define ARM_REV16(rd, rm) (ARM_INST_REV16 | (rd) << 12 | (rm))
#define ARM_RSB_I(rd, rn, imm) _AL3_I(ARM_INST_RSB, rd, rn, imm)
+#define ARM_RSBS_I(rd, rn, imm) _AL3_I(ARM_INST_RSBS, rd, rn, imm)
+#define ARM_RSC_I(rd, rn, imm) _AL3_I(ARM_INST_RSC, rd, rn, imm)
#define ARM_SUB_R(rd, rn, rm) _AL3_R(ARM_INST_SUB, rd, rn, rm)
+#define ARM_SUBS_R(rd, rn, rm) _AL3_R(ARM_INST_SUBS, rd, rn, rm)
+#define ARM_RSB_R(rd, rn, rm) _AL3_R(ARM_INST_RSB, rd, rn, rm)
+#define ARM_SBC_R(rd, rn, rm) _AL3_R(ARM_INST_SBC, rd, rn, rm)
+#define ARM_SBCS_R(rd, rn, rm) _AL3_R(ARM_INST_SBCS, rd, rn, rm)
#define ARM_SUB_I(rd, rn, imm) _AL3_I(ARM_INST_SUB, rd, rn, imm)
+#define ARM_SUBS_I(rd, rn, imm) _AL3_I(ARM_INST_SUBS, rd, rn, imm)
+#define ARM_SBC_I(rd, rn, imm) _AL3_I(ARM_INST_SBC, rd, rn, imm)
#define ARM_STR_I(rt, rn, off) (ARM_INST_STR_I | (rt) << 12 | (rn) << 16 \
- | (off))
+ | ((off) & 0xfff))
+#define ARM_STRH_I(rt, rn, off) (ARM_INST_STRH_I | (rt) << 12 | (rn) << 16 \
+ | (((off) & 0xf0) << 4) | ((off) & 0xf))
+#define ARM_STRB_I(rt, rn, off) (ARM_INST_STRB_I | (rt) << 12 | (rn) << 16 \
+ | (((off) & 0xf0) << 4) | ((off) & 0xf))
#define ARM_TST_R(rn, rm) _AL3_R(ARM_INST_TST, 0, rn, rm)
#define ARM_TST_I(rn, imm) _AL3_I(ARM_INST_TST, 0, rn, imm)
@@ -214,5 +271,6 @@
#define ARM_MLS(rd, rn, rm, ra) (ARM_INST_MLS | (rd) << 16 | (rn) | (rm) << 8 \
| (ra) << 12)
+#define ARM_UXTH(rd, rm) (ARM_INST_UXTH | (rd) << 12 | (rm))
#endif /* PFILTER_OPCODES_ARM_H */