diff options
Diffstat (limited to 'arch/powerpc')
59 files changed, 2156 insertions, 236 deletions
diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig index 01f7464d9fea..d111044f41a2 100644 --- a/arch/powerpc/Kconfig +++ b/arch/powerpc/Kconfig @@ -98,7 +98,6 @@ config PPC select HAVE_FUNCTION_TRACER select HAVE_FUNCTION_GRAPH_TRACER select SYSCTL_EXCEPTION_TRACE - select ARCH_WANT_OPTIONAL_GPIOLIB select VIRT_TO_BUS if !PPC64 select HAVE_IDE select HAVE_IOREMAP_PROT @@ -128,7 +127,7 @@ config PPC select IRQ_FORCED_THREADING select HAVE_RCU_TABLE_FREE if SMP select HAVE_SYSCALL_TRACEPOINTS - select HAVE_CBPF_JIT + select HAVE_CBPF_JIT if CPU_BIG_ENDIAN select HAVE_ARCH_JUMP_LABEL select ARCH_HAVE_NMI_SAFE_CMPXCHG select ARCH_HAS_GCOV_PROFILE_ALL diff --git a/arch/powerpc/boot/dts/mpc8315erdb.dts b/arch/powerpc/boot/dts/mpc8315erdb.dts index 43546844ea5a..ca5139ee5074 100644 --- a/arch/powerpc/boot/dts/mpc8315erdb.dts +++ b/arch/powerpc/boot/dts/mpc8315erdb.dts @@ -472,7 +472,7 @@ hdd { gpios = <&mcu_pio 1 0>; - linux,default-trigger = "ide-disk"; + linux,default-trigger = "disk-activity"; }; }; }; diff --git a/arch/powerpc/boot/dts/mpc8377_rdb.dts b/arch/powerpc/boot/dts/mpc8377_rdb.dts index 2b4b6532d69c..e32613963ab0 100644 --- a/arch/powerpc/boot/dts/mpc8377_rdb.dts +++ b/arch/powerpc/boot/dts/mpc8377_rdb.dts @@ -496,7 +496,7 @@ hdd { gpios = <&mcu_pio 1 0>; - linux,default-trigger = "ide-disk"; + linux,default-trigger = "disk-activity"; }; }; }; diff --git a/arch/powerpc/boot/dts/mpc8378_rdb.dts b/arch/powerpc/boot/dts/mpc8378_rdb.dts index 74b6a535a413..71842fcd621f 100644 --- a/arch/powerpc/boot/dts/mpc8378_rdb.dts +++ b/arch/powerpc/boot/dts/mpc8378_rdb.dts @@ -480,7 +480,7 @@ hdd { gpios = <&mcu_pio 1 0>; - linux,default-trigger = "ide-disk"; + linux,default-trigger = "disk-activity"; }; }; }; diff --git a/arch/powerpc/boot/dts/mpc8379_rdb.dts b/arch/powerpc/boot/dts/mpc8379_rdb.dts index 3b5cbac85368..e442a29b2fe0 100644 --- a/arch/powerpc/boot/dts/mpc8379_rdb.dts +++ b/arch/powerpc/boot/dts/mpc8379_rdb.dts @@ -446,7 +446,7 @@ hdd { gpios = <&mcu_pio 1 0>; - linux,default-trigger = "ide-disk"; + linux,default-trigger = "disk-activity"; }; }; }; diff --git a/arch/powerpc/configs/pmac32_defconfig b/arch/powerpc/configs/pmac32_defconfig index ea8705ffcd76..3f6c9a6c815c 100644 --- a/arch/powerpc/configs/pmac32_defconfig +++ b/arch/powerpc/configs/pmac32_defconfig @@ -158,7 +158,7 @@ CONFIG_ADB=y CONFIG_ADB_CUDA=y CONFIG_ADB_PMU=y CONFIG_ADB_PMU_LED=y -CONFIG_ADB_PMU_LED_IDE=y +CONFIG_ADB_PMU_LED_DISK=y CONFIG_PMAC_APM_EMU=m CONFIG_PMAC_MEDIABAY=y CONFIG_PMAC_BACKLIGHT=y diff --git a/arch/powerpc/configs/ppc6xx_defconfig b/arch/powerpc/configs/ppc6xx_defconfig index 99ccbebabfd3..1dde0be2be30 100644 --- a/arch/powerpc/configs/ppc6xx_defconfig +++ b/arch/powerpc/configs/ppc6xx_defconfig @@ -442,7 +442,7 @@ CONFIG_ADB=y CONFIG_ADB_CUDA=y CONFIG_ADB_PMU=y CONFIG_ADB_PMU_LED=y -CONFIG_ADB_PMU_LED_IDE=y +CONFIG_ADB_PMU_LED_DISK=y CONFIG_PMAC_APM_EMU=y CONFIG_PMAC_MEDIABAY=y CONFIG_PMAC_BACKLIGHT=y diff --git a/arch/powerpc/crypto/Makefile b/arch/powerpc/crypto/Makefile index 9c221b69c181..7998c177f0a2 100644 --- a/arch/powerpc/crypto/Makefile +++ b/arch/powerpc/crypto/Makefile @@ -9,9 +9,11 @@ obj-$(CONFIG_CRYPTO_MD5_PPC) += md5-ppc.o obj-$(CONFIG_CRYPTO_SHA1_PPC) += sha1-powerpc.o obj-$(CONFIG_CRYPTO_SHA1_PPC_SPE) += sha1-ppc-spe.o obj-$(CONFIG_CRYPTO_SHA256_PPC_SPE) += sha256-ppc-spe.o +obj-$(CONFIG_CRYPT_CRC32C_VPMSUM) += crc32c-vpmsum.o aes-ppc-spe-y := aes-spe-core.o aes-spe-keys.o aes-tab-4k.o aes-spe-modes.o aes-spe-glue.o md5-ppc-y := md5-asm.o md5-glue.o sha1-powerpc-y := sha1-powerpc-asm.o sha1.o sha1-ppc-spe-y := sha1-spe-asm.o sha1-spe-glue.o sha256-ppc-spe-y := sha256-spe-asm.o sha256-spe-glue.o +crc32c-vpmsum-y := crc32c-vpmsum_asm.o crc32c-vpmsum_glue.o diff --git a/arch/powerpc/crypto/aes-spe-regs.h b/arch/powerpc/crypto/aes-spe-regs.h index 30d217b399c3..2cc3a2caadae 100644 --- a/arch/powerpc/crypto/aes-spe-regs.h +++ b/arch/powerpc/crypto/aes-spe-regs.h @@ -18,7 +18,7 @@ #define rLN r7 /* length of data to be processed */ #define rIP r8 /* potiner to IV (CBC/CTR/XTS modes) */ #define rKT r9 /* pointer to tweak key (XTS mode) */ -#define rT0 r11 /* pointers to en-/decrpytion tables */ +#define rT0 r11 /* pointers to en-/decryption tables */ #define rT1 r10 #define rD0 r9 /* data */ #define rD1 r14 diff --git a/arch/powerpc/crypto/crc32c-vpmsum_asm.S b/arch/powerpc/crypto/crc32c-vpmsum_asm.S new file mode 100644 index 000000000000..dc640b212299 --- /dev/null +++ b/arch/powerpc/crypto/crc32c-vpmsum_asm.S @@ -0,0 +1,1553 @@ +/* + * Calculate the checksum of data that is 16 byte aligned and a multiple of + * 16 bytes. + * + * The first step is to reduce it to 1024 bits. We do this in 8 parallel + * chunks in order to mask the latency of the vpmsum instructions. If we + * have more than 32 kB of data to checksum we repeat this step multiple + * times, passing in the previous 1024 bits. + * + * The next step is to reduce the 1024 bits to 64 bits. This step adds + * 32 bits of 0s to the end - this matches what a CRC does. We just + * calculate constants that land the data in this 32 bits. + * + * We then use fixed point Barrett reduction to compute a mod n over GF(2) + * for n = CRC using POWER8 instructions. We use x = 32. + * + * http://en.wikipedia.org/wiki/Barrett_reduction + * + * Copyright (C) 2015 Anton Blanchard <anton@au.ibm.com>, IBM + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version + * 2 of the License, or (at your option) any later version. + */ +#include <asm/ppc_asm.h> +#include <asm/ppc-opcode.h> + + .section .rodata +.balign 16 + +.byteswap_constant: + /* byte reverse permute constant */ + .octa 0x0F0E0D0C0B0A09080706050403020100 + +#define MAX_SIZE 32768 +.constants: + + /* Reduce 262144 kbits to 1024 bits */ + /* x^261120 mod p(x)` << 1, x^261184 mod p(x)` << 1 */ + .octa 0x00000000b6ca9e20000000009c37c408 + + /* x^260096 mod p(x)` << 1, x^260160 mod p(x)` << 1 */ + .octa 0x00000000350249a800000001b51df26c + + /* x^259072 mod p(x)` << 1, x^259136 mod p(x)` << 1 */ + .octa 0x00000001862dac54000000000724b9d0 + + /* x^258048 mod p(x)` << 1, x^258112 mod p(x)` << 1 */ + .octa 0x00000001d87fb48c00000001c00532fe + + /* x^257024 mod p(x)` << 1, x^257088 mod p(x)` << 1 */ + .octa 0x00000001f39b699e00000000f05a9362 + + /* x^256000 mod p(x)` << 1, x^256064 mod p(x)` << 1 */ + .octa 0x0000000101da11b400000001e1007970 + + /* x^254976 mod p(x)` << 1, x^255040 mod p(x)` << 1 */ + .octa 0x00000001cab571e000000000a57366ee + + /* x^253952 mod p(x)` << 1, x^254016 mod p(x)` << 1 */ + .octa 0x00000000c7020cfe0000000192011284 + + /* x^252928 mod p(x)` << 1, x^252992 mod p(x)` << 1 */ + .octa 0x00000000cdaed1ae0000000162716d9a + + /* x^251904 mod p(x)` << 1, x^251968 mod p(x)` << 1 */ + .octa 0x00000001e804effc00000000cd97ecde + + /* x^250880 mod p(x)` << 1, x^250944 mod p(x)` << 1 */ + .octa 0x0000000077c3ea3a0000000058812bc0 + + /* x^249856 mod p(x)` << 1, x^249920 mod p(x)` << 1 */ + .octa 0x0000000068df31b40000000088b8c12e + + /* x^248832 mod p(x)` << 1, x^248896 mod p(x)` << 1 */ + .octa 0x00000000b059b6c200000001230b234c + + /* x^247808 mod p(x)` << 1, x^247872 mod p(x)` << 1 */ + .octa 0x0000000145fb8ed800000001120b416e + + /* x^246784 mod p(x)` << 1, x^246848 mod p(x)` << 1 */ + .octa 0x00000000cbc0916800000001974aecb0 + + /* x^245760 mod p(x)` << 1, x^245824 mod p(x)` << 1 */ + .octa 0x000000005ceeedc2000000008ee3f226 + + /* x^244736 mod p(x)` << 1, x^244800 mod p(x)` << 1 */ + .octa 0x0000000047d74e8600000001089aba9a + + /* x^243712 mod p(x)` << 1, x^243776 mod p(x)` << 1 */ + .octa 0x00000001407e9e220000000065113872 + + /* x^242688 mod p(x)` << 1, x^242752 mod p(x)` << 1 */ + .octa 0x00000001da967bda000000005c07ec10 + + /* x^241664 mod p(x)` << 1, x^241728 mod p(x)` << 1 */ + .octa 0x000000006c8983680000000187590924 + + /* x^240640 mod p(x)` << 1, x^240704 mod p(x)` << 1 */ + .octa 0x00000000f2d14c9800000000e35da7c6 + + /* x^239616 mod p(x)` << 1, x^239680 mod p(x)` << 1 */ + .octa 0x00000001993c6ad4000000000415855a + + /* x^238592 mod p(x)` << 1, x^238656 mod p(x)` << 1 */ + .octa 0x000000014683d1ac0000000073617758 + + /* x^237568 mod p(x)` << 1, x^237632 mod p(x)` << 1 */ + .octa 0x00000001a7c93e6c0000000176021d28 + + /* x^236544 mod p(x)` << 1, x^236608 mod p(x)` << 1 */ + .octa 0x000000010211e90a00000001c358fd0a + + /* x^235520 mod p(x)` << 1, x^235584 mod p(x)` << 1 */ + .octa 0x000000001119403e00000001ff7a2c18 + + /* x^234496 mod p(x)` << 1, x^234560 mod p(x)` << 1 */ + .octa 0x000000001c3261aa00000000f2d9f7e4 + + /* x^233472 mod p(x)` << 1, x^233536 mod p(x)` << 1 */ + .octa 0x000000014e37a634000000016cf1f9c8 + + /* x^232448 mod p(x)` << 1, x^232512 mod p(x)` << 1 */ + .octa 0x0000000073786c0c000000010af9279a + + /* x^231424 mod p(x)` << 1, x^231488 mod p(x)` << 1 */ + .octa 0x000000011dc037f80000000004f101e8 + + /* x^230400 mod p(x)` << 1, x^230464 mod p(x)` << 1 */ + .octa 0x0000000031433dfc0000000070bcf184 + + /* x^229376 mod p(x)` << 1, x^229440 mod p(x)` << 1 */ + .octa 0x000000009cde8348000000000a8de642 + + /* x^228352 mod p(x)` << 1, x^228416 mod p(x)` << 1 */ + .octa 0x0000000038d3c2a60000000062ea130c + + /* x^227328 mod p(x)` << 1, x^227392 mod p(x)` << 1 */ + .octa 0x000000011b25f26000000001eb31cbb2 + + /* x^226304 mod p(x)` << 1, x^226368 mod p(x)` << 1 */ + .octa 0x000000001629e6f00000000170783448 + + /* x^225280 mod p(x)` << 1, x^225344 mod p(x)` << 1 */ + .octa 0x0000000160838b4c00000001a684b4c6 + + /* x^224256 mod p(x)` << 1, x^224320 mod p(x)` << 1 */ + .octa 0x000000007a44011c00000000253ca5b4 + + /* x^223232 mod p(x)` << 1, x^223296 mod p(x)` << 1 */ + .octa 0x00000000226f417a0000000057b4b1e2 + + /* x^222208 mod p(x)` << 1, x^222272 mod p(x)` << 1 */ + .octa 0x0000000045eb2eb400000000b6bd084c + + /* x^221184 mod p(x)` << 1, x^221248 mod p(x)` << 1 */ + .octa 0x000000014459d70c0000000123c2d592 + + /* x^220160 mod p(x)` << 1, x^220224 mod p(x)` << 1 */ + .octa 0x00000001d406ed8200000000159dafce + + /* x^219136 mod p(x)` << 1, x^219200 mod p(x)` << 1 */ + .octa 0x0000000160c8e1a80000000127e1a64e + + /* x^218112 mod p(x)` << 1, x^218176 mod p(x)` << 1 */ + .octa 0x0000000027ba80980000000056860754 + + /* x^217088 mod p(x)` << 1, x^217152 mod p(x)` << 1 */ + .octa 0x000000006d92d01800000001e661aae8 + + /* x^216064 mod p(x)` << 1, x^216128 mod p(x)` << 1 */ + .octa 0x000000012ed7e3f200000000f82c6166 + + /* x^215040 mod p(x)` << 1, x^215104 mod p(x)` << 1 */ + .octa 0x000000002dc8778800000000c4f9c7ae + + /* x^214016 mod p(x)` << 1, x^214080 mod p(x)` << 1 */ + .octa 0x0000000018240bb80000000074203d20 + + /* x^212992 mod p(x)` << 1, x^213056 mod p(x)` << 1 */ + .octa 0x000000001ad381580000000198173052 + + /* x^211968 mod p(x)` << 1, x^212032 mod p(x)` << 1 */ + .octa 0x00000001396b78f200000001ce8aba54 + + /* x^210944 mod p(x)` << 1, x^211008 mod p(x)` << 1 */ + .octa 0x000000011a68133400000001850d5d94 + + /* x^209920 mod p(x)` << 1, x^209984 mod p(x)` << 1 */ + .octa 0x000000012104732e00000001d609239c + + /* x^208896 mod p(x)` << 1, x^208960 mod p(x)` << 1 */ + .octa 0x00000000a140d90c000000001595f048 + + /* x^207872 mod p(x)` << 1, x^207936 mod p(x)` << 1 */ + .octa 0x00000001b7215eda0000000042ccee08 + + /* x^206848 mod p(x)` << 1, x^206912 mod p(x)` << 1 */ + .octa 0x00000001aaf1df3c000000010a389d74 + + /* x^205824 mod p(x)` << 1, x^205888 mod p(x)` << 1 */ + .octa 0x0000000029d15b8a000000012a840da6 + + /* x^204800 mod p(x)` << 1, x^204864 mod p(x)` << 1 */ + .octa 0x00000000f1a96922000000001d181c0c + + /* x^203776 mod p(x)` << 1, x^203840 mod p(x)` << 1 */ + .octa 0x00000001ac80d03c0000000068b7d1f6 + + /* x^202752 mod p(x)` << 1, x^202816 mod p(x)` << 1 */ + .octa 0x000000000f11d56a000000005b0f14fc + + /* x^201728 mod p(x)` << 1, x^201792 mod p(x)` << 1 */ + .octa 0x00000001f1c022a20000000179e9e730 + + /* x^200704 mod p(x)` << 1, x^200768 mod p(x)` << 1 */ + .octa 0x0000000173d00ae200000001ce1368d6 + + /* x^199680 mod p(x)` << 1, x^199744 mod p(x)` << 1 */ + .octa 0x00000001d4ffe4ac0000000112c3a84c + + /* x^198656 mod p(x)` << 1, x^198720 mod p(x)` << 1 */ + .octa 0x000000016edc5ae400000000de940fee + + /* x^197632 mod p(x)` << 1, x^197696 mod p(x)` << 1 */ + .octa 0x00000001f1a0214000000000fe896b7e + + /* x^196608 mod p(x)` << 1, x^196672 mod p(x)` << 1 */ + .octa 0x00000000ca0b28a000000001f797431c + + /* x^195584 mod p(x)` << 1, x^195648 mod p(x)` << 1 */ + .octa 0x00000001928e30a20000000053e989ba + + /* x^194560 mod p(x)` << 1, x^194624 mod p(x)` << 1 */ + .octa 0x0000000097b1b002000000003920cd16 + + /* x^193536 mod p(x)` << 1, x^193600 mod p(x)` << 1 */ + .octa 0x00000000b15bf90600000001e6f579b8 + + /* x^192512 mod p(x)` << 1, x^192576 mod p(x)` << 1 */ + .octa 0x00000000411c5d52000000007493cb0a + + /* x^191488 mod p(x)` << 1, x^191552 mod p(x)` << 1 */ + .octa 0x00000001c36f330000000001bdd376d8 + + /* x^190464 mod p(x)` << 1, x^190528 mod p(x)` << 1 */ + .octa 0x00000001119227e0000000016badfee6 + + /* x^189440 mod p(x)` << 1, x^189504 mod p(x)` << 1 */ + .octa 0x00000000114d47020000000071de5c58 + + /* x^188416 mod p(x)` << 1, x^188480 mod p(x)` << 1 */ + .octa 0x00000000458b5b9800000000453f317c + + /* x^187392 mod p(x)` << 1, x^187456 mod p(x)` << 1 */ + .octa 0x000000012e31fb8e0000000121675cce + + /* x^186368 mod p(x)` << 1, x^186432 mod p(x)` << 1 */ + .octa 0x000000005cf619d800000001f409ee92 + + /* x^185344 mod p(x)` << 1, x^185408 mod p(x)` << 1 */ + .octa 0x0000000063f4d8b200000000f36b9c88 + + /* x^184320 mod p(x)` << 1, x^184384 mod p(x)` << 1 */ + .octa 0x000000004138dc8a0000000036b398f4 + + /* x^183296 mod p(x)` << 1, x^183360 mod p(x)` << 1 */ + .octa 0x00000001d29ee8e000000001748f9adc + + /* x^182272 mod p(x)` << 1, x^182336 mod p(x)` << 1 */ + .octa 0x000000006a08ace800000001be94ec00 + + /* x^181248 mod p(x)` << 1, x^181312 mod p(x)` << 1 */ + .octa 0x0000000127d4201000000000b74370d6 + + /* x^180224 mod p(x)` << 1, x^180288 mod p(x)` << 1 */ + .octa 0x0000000019d76b6200000001174d0b98 + + /* x^179200 mod p(x)` << 1, x^179264 mod p(x)` << 1 */ + .octa 0x00000001b1471f6e00000000befc06a4 + + /* x^178176 mod p(x)` << 1, x^178240 mod p(x)` << 1 */ + .octa 0x00000001f64c19cc00000001ae125288 + + /* x^177152 mod p(x)` << 1, x^177216 mod p(x)` << 1 */ + .octa 0x00000000003c0ea00000000095c19b34 + + /* x^176128 mod p(x)` << 1, x^176192 mod p(x)` << 1 */ + .octa 0x000000014d73abf600000001a78496f2 + + /* x^175104 mod p(x)` << 1, x^175168 mod p(x)` << 1 */ + .octa 0x00000001620eb84400000001ac5390a0 + + /* x^174080 mod p(x)` << 1, x^174144 mod p(x)` << 1 */ + .octa 0x0000000147655048000000002a80ed6e + + /* x^173056 mod p(x)` << 1, x^173120 mod p(x)` << 1 */ + .octa 0x0000000067b5077e00000001fa9b0128 + + /* x^172032 mod p(x)` << 1, x^172096 mod p(x)` << 1 */ + .octa 0x0000000010ffe20600000001ea94929e + + /* x^171008 mod p(x)` << 1, x^171072 mod p(x)` << 1 */ + .octa 0x000000000fee8f1e0000000125f4305c + + /* x^169984 mod p(x)` << 1, x^170048 mod p(x)` << 1 */ + .octa 0x00000001da26fbae00000001471e2002 + + /* x^168960 mod p(x)` << 1, x^169024 mod p(x)` << 1 */ + .octa 0x00000001b3a8bd880000000132d2253a + + /* x^167936 mod p(x)` << 1, x^168000 mod p(x)` << 1 */ + .octa 0x00000000e8f3898e00000000f26b3592 + + /* x^166912 mod p(x)` << 1, x^166976 mod p(x)` << 1 */ + .octa 0x00000000b0d0d28c00000000bc8b67b0 + + /* x^165888 mod p(x)` << 1, x^165952 mod p(x)` << 1 */ + .octa 0x0000000030f2a798000000013a826ef2 + + /* x^164864 mod p(x)` << 1, x^164928 mod p(x)` << 1 */ + .octa 0x000000000fba10020000000081482c84 + + /* x^163840 mod p(x)` << 1, x^163904 mod p(x)` << 1 */ + .octa 0x00000000bdb9bd7200000000e77307c2 + + /* x^162816 mod p(x)` << 1, x^162880 mod p(x)` << 1 */ + .octa 0x0000000075d3bf5a00000000d4a07ec8 + + /* x^161792 mod p(x)` << 1, x^161856 mod p(x)` << 1 */ + .octa 0x00000000ef1f98a00000000017102100 + + /* x^160768 mod p(x)` << 1, x^160832 mod p(x)` << 1 */ + .octa 0x00000000689c760200000000db406486 + + /* x^159744 mod p(x)` << 1, x^159808 mod p(x)` << 1 */ + .octa 0x000000016d5fa5fe0000000192db7f88 + + /* x^158720 mod p(x)` << 1, x^158784 mod p(x)` << 1 */ + .octa 0x00000001d0d2b9ca000000018bf67b1e + + /* x^157696 mod p(x)` << 1, x^157760 mod p(x)` << 1 */ + .octa 0x0000000041e7b470000000007c09163e + + /* x^156672 mod p(x)` << 1, x^156736 mod p(x)` << 1 */ + .octa 0x00000001cbb6495e000000000adac060 + + /* x^155648 mod p(x)` << 1, x^155712 mod p(x)` << 1 */ + .octa 0x000000010052a0b000000000bd8316ae + + /* x^154624 mod p(x)` << 1, x^154688 mod p(x)` << 1 */ + .octa 0x00000001d8effb5c000000019f09ab54 + + /* x^153600 mod p(x)` << 1, x^153664 mod p(x)` << 1 */ + .octa 0x00000001d969853c0000000125155542 + + /* x^152576 mod p(x)` << 1, x^152640 mod p(x)` << 1 */ + .octa 0x00000000523ccce2000000018fdb5882 + + /* x^151552 mod p(x)` << 1, x^151616 mod p(x)` << 1 */ + .octa 0x000000001e2436bc00000000e794b3f4 + + /* x^150528 mod p(x)` << 1, x^150592 mod p(x)` << 1 */ + .octa 0x00000000ddd1c3a2000000016f9bb022 + + /* x^149504 mod p(x)` << 1, x^149568 mod p(x)` << 1 */ + .octa 0x0000000019fcfe3800000000290c9978 + + /* x^148480 mod p(x)` << 1, x^148544 mod p(x)` << 1 */ + .octa 0x00000001ce95db640000000083c0f350 + + /* x^147456 mod p(x)` << 1, x^147520 mod p(x)` << 1 */ + .octa 0x00000000af5828060000000173ea6628 + + /* x^146432 mod p(x)` << 1, x^146496 mod p(x)` << 1 */ + .octa 0x00000001006388f600000001c8b4e00a + + /* x^145408 mod p(x)` << 1, x^145472 mod p(x)` << 1 */ + .octa 0x0000000179eca00a00000000de95d6aa + + /* x^144384 mod p(x)` << 1, x^144448 mod p(x)` << 1 */ + .octa 0x0000000122410a6a000000010b7f7248 + + /* x^143360 mod p(x)` << 1, x^143424 mod p(x)` << 1 */ + .octa 0x000000004288e87c00000001326e3a06 + + /* x^142336 mod p(x)` << 1, x^142400 mod p(x)` << 1 */ + .octa 0x000000016c5490da00000000bb62c2e6 + + /* x^141312 mod p(x)` << 1, x^141376 mod p(x)` << 1 */ + .octa 0x00000000d1c71f6e0000000156a4b2c2 + + /* x^140288 mod p(x)` << 1, x^140352 mod p(x)` << 1 */ + .octa 0x00000001b4ce08a6000000011dfe763a + + /* x^139264 mod p(x)` << 1, x^139328 mod p(x)` << 1 */ + .octa 0x00000001466ba60c000000007bcca8e2 + + /* x^138240 mod p(x)` << 1, x^138304 mod p(x)` << 1 */ + .octa 0x00000001f6c488a40000000186118faa + + /* x^137216 mod p(x)` << 1, x^137280 mod p(x)` << 1 */ + .octa 0x000000013bfb06820000000111a65a88 + + /* x^136192 mod p(x)` << 1, x^136256 mod p(x)` << 1 */ + .octa 0x00000000690e9e54000000003565e1c4 + + /* x^135168 mod p(x)` << 1, x^135232 mod p(x)` << 1 */ + .octa 0x00000000281346b6000000012ed02a82 + + /* x^134144 mod p(x)` << 1, x^134208 mod p(x)` << 1 */ + .octa 0x000000015646402400000000c486ecfc + + /* x^133120 mod p(x)` << 1, x^133184 mod p(x)` << 1 */ + .octa 0x000000016063a8dc0000000001b951b2 + + /* x^132096 mod p(x)` << 1, x^132160 mod p(x)` << 1 */ + .octa 0x0000000116a663620000000048143916 + + /* x^131072 mod p(x)` << 1, x^131136 mod p(x)` << 1 */ + .octa 0x000000017e8aa4d200000001dc2ae124 + + /* x^130048 mod p(x)` << 1, x^130112 mod p(x)` << 1 */ + .octa 0x00000001728eb10c00000001416c58d6 + + /* x^129024 mod p(x)` << 1, x^129088 mod p(x)` << 1 */ + .octa 0x00000001b08fd7fa00000000a479744a + + /* x^128000 mod p(x)` << 1, x^128064 mod p(x)` << 1 */ + .octa 0x00000001092a16e80000000096ca3a26 + + /* x^126976 mod p(x)` << 1, x^127040 mod p(x)` << 1 */ + .octa 0x00000000a505637c00000000ff223d4e + + /* x^125952 mod p(x)` << 1, x^126016 mod p(x)` << 1 */ + .octa 0x00000000d94869b2000000010e84da42 + + /* x^124928 mod p(x)` << 1, x^124992 mod p(x)` << 1 */ + .octa 0x00000001c8b203ae00000001b61ba3d0 + + /* x^123904 mod p(x)` << 1, x^123968 mod p(x)` << 1 */ + .octa 0x000000005704aea000000000680f2de8 + + /* x^122880 mod p(x)` << 1, x^122944 mod p(x)` << 1 */ + .octa 0x000000012e295fa2000000008772a9a8 + + /* x^121856 mod p(x)` << 1, x^121920 mod p(x)` << 1 */ + .octa 0x000000011d0908bc0000000155f295bc + + /* x^120832 mod p(x)` << 1, x^120896 mod p(x)` << 1 */ + .octa 0x0000000193ed97ea00000000595f9282 + + /* x^119808 mod p(x)` << 1, x^119872 mod p(x)` << 1 */ + .octa 0x000000013a0f1c520000000164b1c25a + + /* x^118784 mod p(x)` << 1, x^118848 mod p(x)` << 1 */ + .octa 0x000000010c2c40c000000000fbd67c50 + + /* x^117760 mod p(x)` << 1, x^117824 mod p(x)` << 1 */ + .octa 0x00000000ff6fac3e0000000096076268 + + /* x^116736 mod p(x)` << 1, x^116800 mod p(x)` << 1 */ + .octa 0x000000017b3609c000000001d288e4cc + + /* x^115712 mod p(x)` << 1, x^115776 mod p(x)` << 1 */ + .octa 0x0000000088c8c92200000001eaac1bdc + + /* x^114688 mod p(x)` << 1, x^114752 mod p(x)` << 1 */ + .octa 0x00000001751baae600000001f1ea39e2 + + /* x^113664 mod p(x)` << 1, x^113728 mod p(x)` << 1 */ + .octa 0x000000010795297200000001eb6506fc + + /* x^112640 mod p(x)` << 1, x^112704 mod p(x)` << 1 */ + .octa 0x0000000162b00abe000000010f806ffe + + /* x^111616 mod p(x)` << 1, x^111680 mod p(x)` << 1 */ + .octa 0x000000000d7b404c000000010408481e + + /* x^110592 mod p(x)` << 1, x^110656 mod p(x)` << 1 */ + .octa 0x00000000763b13d40000000188260534 + + /* x^109568 mod p(x)` << 1, x^109632 mod p(x)` << 1 */ + .octa 0x00000000f6dc22d80000000058fc73e0 + + /* x^108544 mod p(x)` << 1, x^108608 mod p(x)` << 1 */ + .octa 0x000000007daae06000000000391c59b8 + + /* x^107520 mod p(x)` << 1, x^107584 mod p(x)` << 1 */ + .octa 0x000000013359ab7c000000018b638400 + + /* x^106496 mod p(x)` << 1, x^106560 mod p(x)` << 1 */ + .octa 0x000000008add438a000000011738f5c4 + + /* x^105472 mod p(x)` << 1, x^105536 mod p(x)` << 1 */ + .octa 0x00000001edbefdea000000008cf7c6da + + /* x^104448 mod p(x)` << 1, x^104512 mod p(x)` << 1 */ + .octa 0x000000004104e0f800000001ef97fb16 + + /* x^103424 mod p(x)` << 1, x^103488 mod p(x)` << 1 */ + .octa 0x00000000b48a82220000000102130e20 + + /* x^102400 mod p(x)` << 1, x^102464 mod p(x)` << 1 */ + .octa 0x00000001bcb4684400000000db968898 + + /* x^101376 mod p(x)` << 1, x^101440 mod p(x)` << 1 */ + .octa 0x000000013293ce0a00000000b5047b5e + + /* x^100352 mod p(x)` << 1, x^100416 mod p(x)` << 1 */ + .octa 0x00000001710d0844000000010b90fdb2 + + /* x^99328 mod p(x)` << 1, x^99392 mod p(x)` << 1 */ + .octa 0x0000000117907f6e000000004834a32e + + /* x^98304 mod p(x)` << 1, x^98368 mod p(x)` << 1 */ + .octa 0x0000000087ddf93e0000000059c8f2b0 + + /* x^97280 mod p(x)` << 1, x^97344 mod p(x)` << 1 */ + .octa 0x000000005970e9b00000000122cec508 + + /* x^96256 mod p(x)` << 1, x^96320 mod p(x)` << 1 */ + .octa 0x0000000185b2b7d0000000000a330cda + + /* x^95232 mod p(x)` << 1, x^95296 mod p(x)` << 1 */ + .octa 0x00000001dcee0efc000000014a47148c + + /* x^94208 mod p(x)` << 1, x^94272 mod p(x)` << 1 */ + .octa 0x0000000030da27220000000042c61cb8 + + /* x^93184 mod p(x)` << 1, x^93248 mod p(x)` << 1 */ + .octa 0x000000012f925a180000000012fe6960 + + /* x^92160 mod p(x)` << 1, x^92224 mod p(x)` << 1 */ + .octa 0x00000000dd2e357c00000000dbda2c20 + + /* x^91136 mod p(x)` << 1, x^91200 mod p(x)` << 1 */ + .octa 0x00000000071c80de000000011122410c + + /* x^90112 mod p(x)` << 1, x^90176 mod p(x)` << 1 */ + .octa 0x000000011513140a00000000977b2070 + + /* x^89088 mod p(x)` << 1, x^89152 mod p(x)` << 1 */ + .octa 0x00000001df876e8e000000014050438e + + /* x^88064 mod p(x)` << 1, x^88128 mod p(x)` << 1 */ + .octa 0x000000015f81d6ce0000000147c840e8 + + /* x^87040 mod p(x)` << 1, x^87104 mod p(x)` << 1 */ + .octa 0x000000019dd94dbe00000001cc7c88ce + + /* x^86016 mod p(x)` << 1, x^86080 mod p(x)` << 1 */ + .octa 0x00000001373d206e00000001476b35a4 + + /* x^84992 mod p(x)` << 1, x^85056 mod p(x)` << 1 */ + .octa 0x00000000668ccade000000013d52d508 + + /* x^83968 mod p(x)` << 1, x^84032 mod p(x)` << 1 */ + .octa 0x00000001b192d268000000008e4be32e + + /* x^82944 mod p(x)` << 1, x^83008 mod p(x)` << 1 */ + .octa 0x00000000e30f3a7800000000024120fe + + /* x^81920 mod p(x)` << 1, x^81984 mod p(x)` << 1 */ + .octa 0x000000010ef1f7bc00000000ddecddb4 + + /* x^80896 mod p(x)` << 1, x^80960 mod p(x)` << 1 */ + .octa 0x00000001f5ac738000000000d4d403bc + + /* x^79872 mod p(x)` << 1, x^79936 mod p(x)` << 1 */ + .octa 0x000000011822ea7000000001734b89aa + + /* x^78848 mod p(x)` << 1, x^78912 mod p(x)` << 1 */ + .octa 0x00000000c3a33848000000010e7a58d6 + + /* x^77824 mod p(x)` << 1, x^77888 mod p(x)` << 1 */ + .octa 0x00000001bd151c2400000001f9f04e9c + + /* x^76800 mod p(x)` << 1, x^76864 mod p(x)` << 1 */ + .octa 0x0000000056002d7600000000b692225e + + /* x^75776 mod p(x)` << 1, x^75840 mod p(x)` << 1 */ + .octa 0x000000014657c4f4000000019b8d3f3e + + /* x^74752 mod p(x)` << 1, x^74816 mod p(x)` << 1 */ + .octa 0x0000000113742d7c00000001a874f11e + + /* x^73728 mod p(x)` << 1, x^73792 mod p(x)` << 1 */ + .octa 0x000000019c5920ba000000010d5a4254 + + /* x^72704 mod p(x)` << 1, x^72768 mod p(x)` << 1 */ + .octa 0x000000005216d2d600000000bbb2f5d6 + + /* x^71680 mod p(x)` << 1, x^71744 mod p(x)` << 1 */ + .octa 0x0000000136f5ad8a0000000179cc0e36 + + /* x^70656 mod p(x)` << 1, x^70720 mod p(x)` << 1 */ + .octa 0x000000018b07beb600000001dca1da4a + + /* x^69632 mod p(x)` << 1, x^69696 mod p(x)` << 1 */ + .octa 0x00000000db1e93b000000000feb1a192 + + /* x^68608 mod p(x)` << 1, x^68672 mod p(x)` << 1 */ + .octa 0x000000000b96fa3a00000000d1eeedd6 + + /* x^67584 mod p(x)` << 1, x^67648 mod p(x)` << 1 */ + .octa 0x00000001d9968af0000000008fad9bb4 + + /* x^66560 mod p(x)` << 1, x^66624 mod p(x)` << 1 */ + .octa 0x000000000e4a77a200000001884938e4 + + /* x^65536 mod p(x)` << 1, x^65600 mod p(x)` << 1 */ + .octa 0x00000000508c2ac800000001bc2e9bc0 + + /* x^64512 mod p(x)` << 1, x^64576 mod p(x)` << 1 */ + .octa 0x0000000021572a8000000001f9658a68 + + /* x^63488 mod p(x)` << 1, x^63552 mod p(x)` << 1 */ + .octa 0x00000001b859daf2000000001b9224fc + + /* x^62464 mod p(x)` << 1, x^62528 mod p(x)` << 1 */ + .octa 0x000000016f7884740000000055b2fb84 + + /* x^61440 mod p(x)` << 1, x^61504 mod p(x)` << 1 */ + .octa 0x00000001b438810e000000018b090348 + + /* x^60416 mod p(x)` << 1, x^60480 mod p(x)` << 1 */ + .octa 0x0000000095ddc6f2000000011ccbd5ea + + /* x^59392 mod p(x)` << 1, x^59456 mod p(x)` << 1 */ + .octa 0x00000001d977c20c0000000007ae47f8 + + /* x^58368 mod p(x)` << 1, x^58432 mod p(x)` << 1 */ + .octa 0x00000000ebedb99a0000000172acbec0 + + /* x^57344 mod p(x)` << 1, x^57408 mod p(x)` << 1 */ + .octa 0x00000001df9e9e9200000001c6e3ff20 + + /* x^56320 mod p(x)` << 1, x^56384 mod p(x)` << 1 */ + .octa 0x00000001a4a3f95200000000e1b38744 + + /* x^55296 mod p(x)` << 1, x^55360 mod p(x)` << 1 */ + .octa 0x00000000e2f5122000000000791585b2 + + /* x^54272 mod p(x)` << 1, x^54336 mod p(x)` << 1 */ + .octa 0x000000004aa01f3e00000000ac53b894 + + /* x^53248 mod p(x)` << 1, x^53312 mod p(x)` << 1 */ + .octa 0x00000000b3e90a5800000001ed5f2cf4 + + /* x^52224 mod p(x)` << 1, x^52288 mod p(x)` << 1 */ + .octa 0x000000000c9ca2aa00000001df48b2e0 + + /* x^51200 mod p(x)` << 1, x^51264 mod p(x)` << 1 */ + .octa 0x000000015168231600000000049c1c62 + + /* x^50176 mod p(x)` << 1, x^50240 mod p(x)` << 1 */ + .octa 0x0000000036fce78c000000017c460c12 + + /* x^49152 mod p(x)` << 1, x^49216 mod p(x)` << 1 */ + .octa 0x000000009037dc10000000015be4da7e + + /* x^48128 mod p(x)` << 1, x^48192 mod p(x)` << 1 */ + .octa 0x00000000d3298582000000010f38f668 + + /* x^47104 mod p(x)` << 1, x^47168 mod p(x)` << 1 */ + .octa 0x00000001b42e8ad60000000039f40a00 + + /* x^46080 mod p(x)` << 1, x^46144 mod p(x)` << 1 */ + .octa 0x00000000142a983800000000bd4c10c4 + + /* x^45056 mod p(x)` << 1, x^45120 mod p(x)` << 1 */ + .octa 0x0000000109c7f1900000000042db1d98 + + /* x^44032 mod p(x)` << 1, x^44096 mod p(x)` << 1 */ + .octa 0x0000000056ff931000000001c905bae6 + + /* x^43008 mod p(x)` << 1, x^43072 mod p(x)` << 1 */ + .octa 0x00000001594513aa00000000069d40ea + + /* x^41984 mod p(x)` << 1, x^42048 mod p(x)` << 1 */ + .octa 0x00000001e3b5b1e8000000008e4fbad0 + + /* x^40960 mod p(x)` << 1, x^41024 mod p(x)` << 1 */ + .octa 0x000000011dd5fc080000000047bedd46 + + /* x^39936 mod p(x)` << 1, x^40000 mod p(x)` << 1 */ + .octa 0x00000001675f0cc20000000026396bf8 + + /* x^38912 mod p(x)` << 1, x^38976 mod p(x)` << 1 */ + .octa 0x00000000d1c8dd4400000000379beb92 + + /* x^37888 mod p(x)` << 1, x^37952 mod p(x)` << 1 */ + .octa 0x0000000115ebd3d8000000000abae54a + + /* x^36864 mod p(x)` << 1, x^36928 mod p(x)` << 1 */ + .octa 0x00000001ecbd0dac0000000007e6a128 + + /* x^35840 mod p(x)` << 1, x^35904 mod p(x)` << 1 */ + .octa 0x00000000cdf67af2000000000ade29d2 + + /* x^34816 mod p(x)` << 1, x^34880 mod p(x)` << 1 */ + .octa 0x000000004c01ff4c00000000f974c45c + + /* x^33792 mod p(x)` << 1, x^33856 mod p(x)` << 1 */ + .octa 0x00000000f2d8657e00000000e77ac60a + + /* x^32768 mod p(x)` << 1, x^32832 mod p(x)` << 1 */ + .octa 0x000000006bae74c40000000145895816 + + /* x^31744 mod p(x)` << 1, x^31808 mod p(x)` << 1 */ + .octa 0x0000000152af8aa00000000038e362be + + /* x^30720 mod p(x)` << 1, x^30784 mod p(x)` << 1 */ + .octa 0x0000000004663802000000007f991a64 + + /* x^29696 mod p(x)` << 1, x^29760 mod p(x)` << 1 */ + .octa 0x00000001ab2f5afc00000000fa366d3a + + /* x^28672 mod p(x)` << 1, x^28736 mod p(x)` << 1 */ + .octa 0x0000000074a4ebd400000001a2bb34f0 + + /* x^27648 mod p(x)` << 1, x^27712 mod p(x)` << 1 */ + .octa 0x00000001d7ab3a4c0000000028a9981e + + /* x^26624 mod p(x)` << 1, x^26688 mod p(x)` << 1 */ + .octa 0x00000001a8da60c600000001dbc672be + + /* x^25600 mod p(x)` << 1, x^25664 mod p(x)` << 1 */ + .octa 0x000000013cf6382000000000b04d77f6 + + /* x^24576 mod p(x)` << 1, x^24640 mod p(x)` << 1 */ + .octa 0x00000000bec12e1e0000000124400d96 + + /* x^23552 mod p(x)` << 1, x^23616 mod p(x)` << 1 */ + .octa 0x00000001c6368010000000014ca4b414 + + /* x^22528 mod p(x)` << 1, x^22592 mod p(x)` << 1 */ + .octa 0x00000001e6e78758000000012fe2c938 + + /* x^21504 mod p(x)` << 1, x^21568 mod p(x)` << 1 */ + .octa 0x000000008d7f2b3c00000001faed01e6 + + /* x^20480 mod p(x)` << 1, x^20544 mod p(x)` << 1 */ + .octa 0x000000016b4a156e000000007e80ecfe + + /* x^19456 mod p(x)` << 1, x^19520 mod p(x)` << 1 */ + .octa 0x00000001c63cfeb60000000098daee94 + + /* x^18432 mod p(x)` << 1, x^18496 mod p(x)` << 1 */ + .octa 0x000000015f902670000000010a04edea + + /* x^17408 mod p(x)` << 1, x^17472 mod p(x)` << 1 */ + .octa 0x00000001cd5de11e00000001c00b4524 + + /* x^16384 mod p(x)` << 1, x^16448 mod p(x)` << 1 */ + .octa 0x000000001acaec540000000170296550 + + /* x^15360 mod p(x)` << 1, x^15424 mod p(x)` << 1 */ + .octa 0x000000002bd0ca780000000181afaa48 + + /* x^14336 mod p(x)` << 1, x^14400 mod p(x)` << 1 */ + .octa 0x0000000032d63d5c0000000185a31ffa + + /* x^13312 mod p(x)` << 1, x^13376 mod p(x)` << 1 */ + .octa 0x000000001c6d4e4c000000002469f608 + + /* x^12288 mod p(x)` << 1, x^12352 mod p(x)` << 1 */ + .octa 0x0000000106a60b92000000006980102a + + /* x^11264 mod p(x)` << 1, x^11328 mod p(x)` << 1 */ + .octa 0x00000000d3855e120000000111ea9ca8 + + /* x^10240 mod p(x)` << 1, x^10304 mod p(x)` << 1 */ + .octa 0x00000000e312563600000001bd1d29ce + + /* x^9216 mod p(x)` << 1, x^9280 mod p(x)` << 1 */ + .octa 0x000000009e8f7ea400000001b34b9580 + + /* x^8192 mod p(x)` << 1, x^8256 mod p(x)` << 1 */ + .octa 0x00000001c82e562c000000003076054e + + /* x^7168 mod p(x)` << 1, x^7232 mod p(x)` << 1 */ + .octa 0x00000000ca9f09ce000000012a608ea4 + + /* x^6144 mod p(x)` << 1, x^6208 mod p(x)` << 1 */ + .octa 0x00000000c63764e600000000784d05fe + + /* x^5120 mod p(x)` << 1, x^5184 mod p(x)` << 1 */ + .octa 0x0000000168d2e49e000000016ef0d82a + + /* x^4096 mod p(x)` << 1, x^4160 mod p(x)` << 1 */ + .octa 0x00000000e986c1480000000075bda454 + + /* x^3072 mod p(x)` << 1, x^3136 mod p(x)` << 1 */ + .octa 0x00000000cfb65894000000003dc0a1c4 + + /* x^2048 mod p(x)` << 1, x^2112 mod p(x)` << 1 */ + .octa 0x0000000111cadee400000000e9a5d8be + + /* x^1024 mod p(x)` << 1, x^1088 mod p(x)` << 1 */ + .octa 0x0000000171fb63ce00000001609bc4b4 + +.short_constants: + + /* Reduce final 1024-2048 bits to 64 bits, shifting 32 bits to include the trailing 32 bits of zeros */ + /* x^1952 mod p(x)`, x^1984 mod p(x)`, x^2016 mod p(x)`, x^2048 mod p(x)` */ + .octa 0x7fec2963e5bf80485cf015c388e56f72 + + /* x^1824 mod p(x)`, x^1856 mod p(x)`, x^1888 mod p(x)`, x^1920 mod p(x)` */ + .octa 0x38e888d4844752a9963a18920246e2e6 + + /* x^1696 mod p(x)`, x^1728 mod p(x)`, x^1760 mod p(x)`, x^1792 mod p(x)` */ + .octa 0x42316c00730206ad419a441956993a31 + + /* x^1568 mod p(x)`, x^1600 mod p(x)`, x^1632 mod p(x)`, x^1664 mod p(x)` */ + .octa 0x543d5c543e65ddf9924752ba2b830011 + + /* x^1440 mod p(x)`, x^1472 mod p(x)`, x^1504 mod p(x)`, x^1536 mod p(x)` */ + .octa 0x78e87aaf56767c9255bd7f9518e4a304 + + /* x^1312 mod p(x)`, x^1344 mod p(x)`, x^1376 mod p(x)`, x^1408 mod p(x)` */ + .octa 0x8f68fcec1903da7f6d76739fe0553f1e + + /* x^1184 mod p(x)`, x^1216 mod p(x)`, x^1248 mod p(x)`, x^1280 mod p(x)` */ + .octa 0x3f4840246791d588c133722b1fe0b5c3 + + /* x^1056 mod p(x)`, x^1088 mod p(x)`, x^1120 mod p(x)`, x^1152 mod p(x)` */ + .octa 0x34c96751b04de25a64b67ee0e55ef1f3 + + /* x^928 mod p(x)`, x^960 mod p(x)`, x^992 mod p(x)`, x^1024 mod p(x)` */ + .octa 0x156c8e180b4a395b069db049b8fdb1e7 + + /* x^800 mod p(x)`, x^832 mod p(x)`, x^864 mod p(x)`, x^896 mod p(x)` */ + .octa 0xe0b99ccbe661f7bea11bfaf3c9e90b9e + + /* x^672 mod p(x)`, x^704 mod p(x)`, x^736 mod p(x)`, x^768 mod p(x)` */ + .octa 0x041d37768cd75659817cdc5119b29a35 + + /* x^544 mod p(x)`, x^576 mod p(x)`, x^608 mod p(x)`, x^640 mod p(x)` */ + .octa 0x3a0777818cfaa9651ce9d94b36c41f1c + + /* x^416 mod p(x)`, x^448 mod p(x)`, x^480 mod p(x)`, x^512 mod p(x)` */ + .octa 0x0e148e8252377a554f256efcb82be955 + + /* x^288 mod p(x)`, x^320 mod p(x)`, x^352 mod p(x)`, x^384 mod p(x)` */ + .octa 0x9c25531d19e65ddeec1631edb2dea967 + + /* x^160 mod p(x)`, x^192 mod p(x)`, x^224 mod p(x)`, x^256 mod p(x)` */ + .octa 0x790606ff9957c0a65d27e147510ac59a + + /* x^32 mod p(x)`, x^64 mod p(x)`, x^96 mod p(x)`, x^128 mod p(x)` */ + .octa 0x82f63b786ea2d55ca66805eb18b8ea18 + + +.barrett_constants: + /* 33 bit reflected Barrett constant m - (4^32)/n */ + .octa 0x000000000000000000000000dea713f1 /* x^64 div p(x)` */ + /* 33 bit reflected Barrett constant n */ + .octa 0x00000000000000000000000105ec76f1 + + .text + +#if defined(__BIG_ENDIAN__) +#define BYTESWAP_DATA +#else +#undef BYTESWAP_DATA +#endif + +#define off16 r25 +#define off32 r26 +#define off48 r27 +#define off64 r28 +#define off80 r29 +#define off96 r30 +#define off112 r31 + +#define const1 v24 +#define const2 v25 + +#define byteswap v26 +#define mask_32bit v27 +#define mask_64bit v28 +#define zeroes v29 + +#ifdef BYTESWAP_DATA +#define VPERM(A, B, C, D) vperm A, B, C, D +#else +#define VPERM(A, B, C, D) +#endif + +/* unsigned int __crc32c_vpmsum(unsigned int crc, void *p, unsigned long len) */ +FUNC_START(__crc32c_vpmsum) + std r31,-8(r1) + std r30,-16(r1) + std r29,-24(r1) + std r28,-32(r1) + std r27,-40(r1) + std r26,-48(r1) + std r25,-56(r1) + + li off16,16 + li off32,32 + li off48,48 + li off64,64 + li off80,80 + li off96,96 + li off112,112 + li r0,0 + + /* Enough room for saving 10 non volatile VMX registers */ + subi r6,r1,56+10*16 + subi r7,r1,56+2*16 + + stvx v20,0,r6 + stvx v21,off16,r6 + stvx v22,off32,r6 + stvx v23,off48,r6 + stvx v24,off64,r6 + stvx v25,off80,r6 + stvx v26,off96,r6 + stvx v27,off112,r6 + stvx v28,0,r7 + stvx v29,off16,r7 + + mr r10,r3 + + vxor zeroes,zeroes,zeroes + vspltisw v0,-1 + + vsldoi mask_32bit,zeroes,v0,4 + vsldoi mask_64bit,zeroes,v0,8 + + /* Get the initial value into v8 */ + vxor v8,v8,v8 + MTVRD(v8, R3) + vsldoi v8,zeroes,v8,8 /* shift into bottom 32 bits */ + +#ifdef BYTESWAP_DATA + addis r3,r2,.byteswap_constant@toc@ha + addi r3,r3,.byteswap_constant@toc@l + + lvx byteswap,0,r3 + addi r3,r3,16 +#endif + + cmpdi r5,256 + blt .Lshort + + rldicr r6,r5,0,56 + + /* Checksum in blocks of MAX_SIZE */ +1: lis r7,MAX_SIZE@h + ori r7,r7,MAX_SIZE@l + mr r9,r7 + cmpd r6,r7 + bgt 2f + mr r7,r6 +2: subf r6,r7,r6 + + /* our main loop does 128 bytes at a time */ + srdi r7,r7,7 + + /* + * Work out the offset into the constants table to start at. Each + * constant is 16 bytes, and it is used against 128 bytes of input + * data - 128 / 16 = 8 + */ + sldi r8,r7,4 + srdi r9,r9,3 + subf r8,r8,r9 + + /* We reduce our final 128 bytes in a separate step */ + addi r7,r7,-1 + mtctr r7 + + addis r3,r2,.constants@toc@ha + addi r3,r3,.constants@toc@l + + /* Find the start of our constants */ + add r3,r3,r8 + + /* zero v0-v7 which will contain our checksums */ + vxor v0,v0,v0 + vxor v1,v1,v1 + vxor v2,v2,v2 + vxor v3,v3,v3 + vxor v4,v4,v4 + vxor v5,v5,v5 + vxor v6,v6,v6 + vxor v7,v7,v7 + + lvx const1,0,r3 + + /* + * If we are looping back to consume more data we use the values + * already in v16-v23. + */ + cmpdi r0,1 + beq 2f + + /* First warm up pass */ + lvx v16,0,r4 + lvx v17,off16,r4 + VPERM(v16,v16,v16,byteswap) + VPERM(v17,v17,v17,byteswap) + lvx v18,off32,r4 + lvx v19,off48,r4 + VPERM(v18,v18,v18,byteswap) + VPERM(v19,v19,v19,byteswap) + lvx v20,off64,r4 + lvx v21,off80,r4 + VPERM(v20,v20,v20,byteswap) + VPERM(v21,v21,v21,byteswap) + lvx v22,off96,r4 + lvx v23,off112,r4 + VPERM(v22,v22,v22,byteswap) + VPERM(v23,v23,v23,byteswap) + addi r4,r4,8*16 + + /* xor in initial value */ + vxor v16,v16,v8 + +2: bdz .Lfirst_warm_up_done + + addi r3,r3,16 + lvx const2,0,r3 + + /* Second warm up pass */ + VPMSUMD(v8,v16,const1) + lvx v16,0,r4 + VPERM(v16,v16,v16,byteswap) + ori r2,r2,0 + + VPMSUMD(v9,v17,const1) + lvx v17,off16,r4 + VPERM(v17,v17,v17,byteswap) + ori r2,r2,0 + + VPMSUMD(v10,v18,const1) + lvx v18,off32,r4 + VPERM(v18,v18,v18,byteswap) + ori r2,r2,0 + + VPMSUMD(v11,v19,const1) + lvx v19,off48,r4 + VPERM(v19,v19,v19,byteswap) + ori r2,r2,0 + + VPMSUMD(v12,v20,const1) + lvx v20,off64,r4 + VPERM(v20,v20,v20,byteswap) + ori r2,r2,0 + + VPMSUMD(v13,v21,const1) + lvx v21,off80,r4 + VPERM(v21,v21,v21,byteswap) + ori r2,r2,0 + + VPMSUMD(v14,v22,const1) + lvx v22,off96,r4 + VPERM(v22,v22,v22,byteswap) + ori r2,r2,0 + + VPMSUMD(v15,v23,const1) + lvx v23,off112,r4 + VPERM(v23,v23,v23,byteswap) + + addi r4,r4,8*16 + + bdz .Lfirst_cool_down + + /* + * main loop. We modulo schedule it such that it takes three iterations + * to complete - first iteration load, second iteration vpmsum, third + * iteration xor. + */ + .balign 16 +4: lvx const1,0,r3 + addi r3,r3,16 + ori r2,r2,0 + + vxor v0,v0,v8 + VPMSUMD(v8,v16,const2) + lvx v16,0,r4 + VPERM(v16,v16,v16,byteswap) + ori r2,r2,0 + + vxor v1,v1,v9 + VPMSUMD(v9,v17,const2) + lvx v17,off16,r4 + VPERM(v17,v17,v17,byteswap) + ori r2,r2,0 + + vxor v2,v2,v10 + VPMSUMD(v10,v18,const2) + lvx v18,off32,r4 + VPERM(v18,v18,v18,byteswap) + ori r2,r2,0 + + vxor v3,v3,v11 + VPMSUMD(v11,v19,const2) + lvx v19,off48,r4 + VPERM(v19,v19,v19,byteswap) + lvx const2,0,r3 + ori r2,r2,0 + + vxor v4,v4,v12 + VPMSUMD(v12,v20,const1) + lvx v20,off64,r4 + VPERM(v20,v20,v20,byteswap) + ori r2,r2,0 + + vxor v5,v5,v13 + VPMSUMD(v13,v21,const1) + lvx v21,off80,r4 + VPERM(v21,v21,v21,byteswap) + ori r2,r2,0 + + vxor v6,v6,v14 + VPMSUMD(v14,v22,const1) + lvx v22,off96,r4 + VPERM(v22,v22,v22,byteswap) + ori r2,r2,0 + + vxor v7,v7,v15 + VPMSUMD(v15,v23,const1) + lvx v23,off112,r4 + VPERM(v23,v23,v23,byteswap) + + addi r4,r4,8*16 + + bdnz 4b + +.Lfirst_cool_down: + /* First cool down pass */ + lvx const1,0,r3 + addi r3,r3,16 + + vxor v0,v0,v8 + VPMSUMD(v8,v16,const1) + ori r2,r2,0 + + vxor v1,v1,v9 + VPMSUMD(v9,v17,const1) + ori r2,r2,0 + + vxor v2,v2,v10 + VPMSUMD(v10,v18,const1) + ori r2,r2,0 + + vxor v3,v3,v11 + VPMSUMD(v11,v19,const1) + ori r2,r2,0 + + vxor v4,v4,v12 + VPMSUMD(v12,v20,const1) + ori r2,r2,0 + + vxor v5,v5,v13 + VPMSUMD(v13,v21,const1) + ori r2,r2,0 + + vxor v6,v6,v14 + VPMSUMD(v14,v22,const1) + ori r2,r2,0 + + vxor v7,v7,v15 + VPMSUMD(v15,v23,const1) + ori r2,r2,0 + +.Lsecond_cool_down: + /* Second cool down pass */ + vxor v0,v0,v8 + vxor v1,v1,v9 + vxor v2,v2,v10 + vxor v3,v3,v11 + vxor v4,v4,v12 + vxor v5,v5,v13 + vxor v6,v6,v14 + vxor v7,v7,v15 + + /* + * vpmsumd produces a 96 bit result in the least significant bits + * of the register. Since we are bit reflected we have to shift it + * left 32 bits so it occupies the least significant bits in the + * bit reflected domain. + */ + vsldoi v0,v0,zeroes,4 + vsldoi v1,v1,zeroes,4 + vsldoi v2,v2,zeroes,4 + vsldoi v3,v3,zeroes,4 + vsldoi v4,v4,zeroes,4 + vsldoi v5,v5,zeroes,4 + vsldoi v6,v6,zeroes,4 + vsldoi v7,v7,zeroes,4 + + /* xor with last 1024 bits */ + lvx v8,0,r4 + lvx v9,off16,r4 + VPERM(v8,v8,v8,byteswap) + VPERM(v9,v9,v9,byteswap) + lvx v10,off32,r4 + lvx v11,off48,r4 + VPERM(v10,v10,v10,byteswap) + VPERM(v11,v11,v11,byteswap) + lvx v12,off64,r4 + lvx v13,off80,r4 + VPERM(v12,v12,v12,byteswap) + VPERM(v13,v13,v13,byteswap) + lvx v14,off96,r4 + lvx v15,off112,r4 + VPERM(v14,v14,v14,byteswap) + VPERM(v15,v15,v15,byteswap) + + addi r4,r4,8*16 + + vxor v16,v0,v8 + vxor v17,v1,v9 + vxor v18,v2,v10 + vxor v19,v3,v11 + vxor v20,v4,v12 + vxor v21,v5,v13 + vxor v22,v6,v14 + vxor v23,v7,v15 + + li r0,1 + cmpdi r6,0 + addi r6,r6,128 + bne 1b + + /* Work out how many bytes we have left */ + andi. r5,r5,127 + + /* Calculate where in the constant table we need to start */ + subfic r6,r5,128 + add r3,r3,r6 + + /* How many 16 byte chunks are in the tail */ + srdi r7,r5,4 + mtctr r7 + + /* + * Reduce the previously calculated 1024 bits to 64 bits, shifting + * 32 bits to include the trailing 32 bits of zeros + */ + lvx v0,0,r3 + lvx v1,off16,r3 + lvx v2,off32,r3 + lvx v3,off48,r3 + lvx v4,off64,r3 + lvx v5,off80,r3 + lvx v6,off96,r3 + lvx v7,off112,r3 + addi r3,r3,8*16 + + VPMSUMW(v0,v16,v0) + VPMSUMW(v1,v17,v1) + VPMSUMW(v2,v18,v2) + VPMSUMW(v3,v19,v3) + VPMSUMW(v4,v20,v4) + VPMSUMW(v5,v21,v5) + VPMSUMW(v6,v22,v6) + VPMSUMW(v7,v23,v7) + + /* Now reduce the tail (0 - 112 bytes) */ + cmpdi r7,0 + beq 1f + + lvx v16,0,r4 + lvx v17,0,r3 + VPERM(v16,v16,v16,byteswap) + VPMSUMW(v16,v16,v17) + vxor v0,v0,v16 + bdz 1f + + lvx v16,off16,r4 + lvx v17,off16,r3 + VPERM(v16,v16,v16,byteswap) + VPMSUMW(v16,v16,v17) + vxor v0,v0,v16 + bdz 1f + + lvx v16,off32,r4 + lvx v17,off32,r3 + VPERM(v16,v16,v16,byteswap) + VPMSUMW(v16,v16,v17) + vxor v0,v0,v16 + bdz 1f + + lvx v16,off48,r4 + lvx v17,off48,r3 + VPERM(v16,v16,v16,byteswap) + VPMSUMW(v16,v16,v17) + vxor v0,v0,v16 + bdz 1f + + lvx v16,off64,r4 + lvx v17,off64,r3 + VPERM(v16,v16,v16,byteswap) + VPMSUMW(v16,v16,v17) + vxor v0,v0,v16 + bdz 1f + + lvx v16,off80,r4 + lvx v17,off80,r3 + VPERM(v16,v16,v16,byteswap) + VPMSUMW(v16,v16,v17) + vxor v0,v0,v16 + bdz 1f + + lvx v16,off96,r4 + lvx v17,off96,r3 + VPERM(v16,v16,v16,byteswap) + VPMSUMW(v16,v16,v17) + vxor v0,v0,v16 + + /* Now xor all the parallel chunks together */ +1: vxor v0,v0,v1 + vxor v2,v2,v3 + vxor v4,v4,v5 + vxor v6,v6,v7 + + vxor v0,v0,v2 + vxor v4,v4,v6 + + vxor v0,v0,v4 + +.Lbarrett_reduction: + /* Barrett constants */ + addis r3,r2,.barrett_constants@toc@ha + addi r3,r3,.barrett_constants@toc@l + + lvx const1,0,r3 + lvx const2,off16,r3 + + vsldoi v1,v0,v0,8 + vxor v0,v0,v1 /* xor two 64 bit results together */ + + /* shift left one bit */ + vspltisb v1,1 + vsl v0,v0,v1 + + vand v0,v0,mask_64bit + + /* + * The reflected version of Barrett reduction. Instead of bit + * reflecting our data (which is expensive to do), we bit reflect our + * constants and our algorithm, which means the intermediate data in + * our vector registers goes from 0-63 instead of 63-0. We can reflect + * the algorithm because we don't carry in mod 2 arithmetic. + */ + vand v1,v0,mask_32bit /* bottom 32 bits of a */ + VPMSUMD(v1,v1,const1) /* ma */ + vand v1,v1,mask_32bit /* bottom 32bits of ma */ + VPMSUMD(v1,v1,const2) /* qn */ + vxor v0,v0,v1 /* a - qn, subtraction is xor in GF(2) */ + + /* + * Since we are bit reflected, the result (ie the low 32 bits) is in + * the high 32 bits. We just need to shift it left 4 bytes + * V0 [ 0 1 X 3 ] + * V0 [ 0 X 2 3 ] + */ + vsldoi v0,v0,zeroes,4 /* shift result into top 64 bits of */ + + /* Get it into r3 */ + MFVRD(R3, v0) + +.Lout: + subi r6,r1,56+10*16 + subi r7,r1,56+2*16 + + lvx v20,0,r6 + lvx v21,off16,r6 + lvx v22,off32,r6 + lvx v23,off48,r6 + lvx v24,off64,r6 + lvx v25,off80,r6 + lvx v26,off96,r6 + lvx v27,off112,r6 + lvx v28,0,r7 + lvx v29,off16,r7 + + ld r31,-8(r1) + ld r30,-16(r1) + ld r29,-24(r1) + ld r28,-32(r1) + ld r27,-40(r1) + ld r26,-48(r1) + ld r25,-56(r1) + + blr + +.Lfirst_warm_up_done: + lvx const1,0,r3 + addi r3,r3,16 + + VPMSUMD(v8,v16,const1) + VPMSUMD(v9,v17,const1) + VPMSUMD(v10,v18,const1) + VPMSUMD(v11,v19,const1) + VPMSUMD(v12,v20,const1) + VPMSUMD(v13,v21,const1) + VPMSUMD(v14,v22,const1) + VPMSUMD(v15,v23,const1) + + b .Lsecond_cool_down + +.Lshort: + cmpdi r5,0 + beq .Lzero + + addis r3,r2,.short_constants@toc@ha + addi r3,r3,.short_constants@toc@l + + /* Calculate where in the constant table we need to start */ + subfic r6,r5,256 + add r3,r3,r6 + + /* How many 16 byte chunks? */ + srdi r7,r5,4 + mtctr r7 + + vxor v19,v19,v19 + vxor v20,v20,v20 + + lvx v0,0,r4 + lvx v16,0,r3 + VPERM(v0,v0,v16,byteswap) + vxor v0,v0,v8 /* xor in initial value */ + VPMSUMW(v0,v0,v16) + bdz .Lv0 + + lvx v1,off16,r4 + lvx v17,off16,r3 + VPERM(v1,v1,v17,byteswap) + VPMSUMW(v1,v1,v17) + bdz .Lv1 + + lvx v2,off32,r4 + lvx v16,off32,r3 + VPERM(v2,v2,v16,byteswap) + VPMSUMW(v2,v2,v16) + bdz .Lv2 + + lvx v3,off48,r4 + lvx v17,off48,r3 + VPERM(v3,v3,v17,byteswap) + VPMSUMW(v3,v3,v17) + bdz .Lv3 + + lvx v4,off64,r4 + lvx v16,off64,r3 + VPERM(v4,v4,v16,byteswap) + VPMSUMW(v4,v4,v16) + bdz .Lv4 + + lvx v5,off80,r4 + lvx v17,off80,r3 + VPERM(v5,v5,v17,byteswap) + VPMSUMW(v5,v5,v17) + bdz .Lv5 + + lvx v6,off96,r4 + lvx v16,off96,r3 + VPERM(v6,v6,v16,byteswap) + VPMSUMW(v6,v6,v16) + bdz .Lv6 + + lvx v7,off112,r4 + lvx v17,off112,r3 + VPERM(v7,v7,v17,byteswap) + VPMSUMW(v7,v7,v17) + bdz .Lv7 + + addi r3,r3,128 + addi r4,r4,128 + + lvx v8,0,r4 + lvx v16,0,r3 + VPERM(v8,v8,v16,byteswap) + VPMSUMW(v8,v8,v16) + bdz .Lv8 + + lvx v9,off16,r4 + lvx v17,off16,r3 + VPERM(v9,v9,v17,byteswap) + VPMSUMW(v9,v9,v17) + bdz .Lv9 + + lvx v10,off32,r4 + lvx v16,off32,r3 + VPERM(v10,v10,v16,byteswap) + VPMSUMW(v10,v10,v16) + bdz .Lv10 + + lvx v11,off48,r4 + lvx v17,off48,r3 + VPERM(v11,v11,v17,byteswap) + VPMSUMW(v11,v11,v17) + bdz .Lv11 + + lvx v12,off64,r4 + lvx v16,off64,r3 + VPERM(v12,v12,v16,byteswap) + VPMSUMW(v12,v12,v16) + bdz .Lv12 + + lvx v13,off80,r4 + lvx v17,off80,r3 + VPERM(v13,v13,v17,byteswap) + VPMSUMW(v13,v13,v17) + bdz .Lv13 + + lvx v14,off96,r4 + lvx v16,off96,r3 + VPERM(v14,v14,v16,byteswap) + VPMSUMW(v14,v14,v16) + bdz .Lv14 + + lvx v15,off112,r4 + lvx v17,off112,r3 + VPERM(v15,v15,v17,byteswap) + VPMSUMW(v15,v15,v17) + +.Lv15: vxor v19,v19,v15 +.Lv14: vxor v20,v20,v14 +.Lv13: vxor v19,v19,v13 +.Lv12: vxor v20,v20,v12 +.Lv11: vxor v19,v19,v11 +.Lv10: vxor v20,v20,v10 +.Lv9: vxor v19,v19,v9 +.Lv8: vxor v20,v20,v8 +.Lv7: vxor v19,v19,v7 +.Lv6: vxor v20,v20,v6 +.Lv5: vxor v19,v19,v5 +.Lv4: vxor v20,v20,v4 +.Lv3: vxor v19,v19,v3 +.Lv2: vxor v20,v20,v2 +.Lv1: vxor v19,v19,v1 +.Lv0: vxor v20,v20,v0 + + vxor v0,v19,v20 + + b .Lbarrett_reduction + +.Lzero: + mr r3,r10 + b .Lout + +FUNC_END(__crc32_vpmsum) diff --git a/arch/powerpc/crypto/crc32c-vpmsum_glue.c b/arch/powerpc/crypto/crc32c-vpmsum_glue.c new file mode 100644 index 000000000000..bfe3d37a24ef --- /dev/null +++ b/arch/powerpc/crypto/crc32c-vpmsum_glue.c @@ -0,0 +1,167 @@ +#include <linux/crc32.h> +#include <crypto/internal/hash.h> +#include <linux/init.h> +#include <linux/module.h> +#include <linux/string.h> +#include <linux/kernel.h> +#include <asm/switch_to.h> + +#define CHKSUM_BLOCK_SIZE 1 +#define CHKSUM_DIGEST_SIZE 4 + +#define VMX_ALIGN 16 +#define VMX_ALIGN_MASK (VMX_ALIGN-1) + +#define VECTOR_BREAKPOINT 512 + +u32 __crc32c_vpmsum(u32 crc, unsigned char const *p, size_t len); + +static u32 crc32c_vpmsum(u32 crc, unsigned char const *p, size_t len) +{ + unsigned int prealign; + unsigned int tail; + + if (len < (VECTOR_BREAKPOINT + VMX_ALIGN) || in_interrupt()) + return __crc32c_le(crc, p, len); + + if ((unsigned long)p & VMX_ALIGN_MASK) { + prealign = VMX_ALIGN - ((unsigned long)p & VMX_ALIGN_MASK); + crc = __crc32c_le(crc, p, prealign); + len -= prealign; + p += prealign; + } + + if (len & ~VMX_ALIGN_MASK) { + pagefault_disable(); + enable_kernel_altivec(); + crc = __crc32c_vpmsum(crc, p, len & ~VMX_ALIGN_MASK); + pagefault_enable(); + } + + tail = len & VMX_ALIGN_MASK; + if (tail) { + p += len & ~VMX_ALIGN_MASK; + crc = __crc32c_le(crc, p, tail); + } + + return crc; +} + +static int crc32c_vpmsum_cra_init(struct crypto_tfm *tfm) +{ + u32 *key = crypto_tfm_ctx(tfm); + + *key = 0; + + return 0; +} + +/* + * Setting the seed allows arbitrary accumulators and flexible XOR policy + * If your algorithm starts with ~0, then XOR with ~0 before you set + * the seed. + */ +static int crc32c_vpmsum_setkey(struct crypto_shash *hash, const u8 *key, + unsigned int keylen) +{ + u32 *mctx = crypto_shash_ctx(hash); + + if (keylen != sizeof(u32)) { + crypto_shash_set_flags(hash, CRYPTO_TFM_RES_BAD_KEY_LEN); + return -EINVAL; + } + *mctx = le32_to_cpup((__le32 *)key); + return 0; +} + +static int crc32c_vpmsum_init(struct shash_desc *desc) +{ + u32 *mctx = crypto_shash_ctx(desc->tfm); + u32 *crcp = shash_desc_ctx(desc); + + *crcp = *mctx; + + return 0; +} + +static int crc32c_vpmsum_update(struct shash_desc *desc, const u8 *data, + unsigned int len) +{ + u32 *crcp = shash_desc_ctx(desc); + + *crcp = crc32c_vpmsum(*crcp, data, len); + + return 0; +} + +static int __crc32c_vpmsum_finup(u32 *crcp, const u8 *data, unsigned int len, + u8 *out) +{ + *(__le32 *)out = ~cpu_to_le32(crc32c_vpmsum(*crcp, data, len)); + + return 0; +} + +static int crc32c_vpmsum_finup(struct shash_desc *desc, const u8 *data, + unsigned int len, u8 *out) +{ + return __crc32c_vpmsum_finup(shash_desc_ctx(desc), data, len, out); +} + +static int crc32c_vpmsum_final(struct shash_desc *desc, u8 *out) +{ + u32 *crcp = shash_desc_ctx(desc); + + *(__le32 *)out = ~cpu_to_le32p(crcp); + + return 0; +} + +static int crc32c_vpmsum_digest(struct shash_desc *desc, const u8 *data, + unsigned int len, u8 *out) +{ + return __crc32c_vpmsum_finup(crypto_shash_ctx(desc->tfm), data, len, + out); +} + +static struct shash_alg alg = { + .setkey = crc32c_vpmsum_setkey, + .init = crc32c_vpmsum_init, + .update = crc32c_vpmsum_update, + .final = crc32c_vpmsum_final, + .finup = crc32c_vpmsum_finup, + .digest = crc32c_vpmsum_digest, + .descsize = sizeof(u32), + .digestsize = CHKSUM_DIGEST_SIZE, + .base = { + .cra_name = "crc32c", + .cra_driver_name = "crc32c-vpmsum", + .cra_priority = 200, + .cra_blocksize = CHKSUM_BLOCK_SIZE, + .cra_ctxsize = sizeof(u32), + .cra_module = THIS_MODULE, + .cra_init = crc32c_vpmsum_cra_init, + } +}; + +static int __init crc32c_vpmsum_mod_init(void) +{ + if (!cpu_has_feature(CPU_FTR_ARCH_207S)) + return -ENODEV; + + return crypto_register_shash(&alg); +} + +static void __exit crc32c_vpmsum_mod_fini(void) +{ + crypto_unregister_shash(&alg); +} + +module_init(crc32c_vpmsum_mod_init); +module_exit(crc32c_vpmsum_mod_fini); + +MODULE_AUTHOR("Anton Blanchard <anton@samba.org>"); +MODULE_DESCRIPTION("CRC32C using vector polynomial multiply-sum instructions"); +MODULE_LICENSE("GPL"); +MODULE_ALIAS_CRYPTO("crc32c"); +MODULE_ALIAS_CRYPTO("crc32c-vpmsum"); diff --git a/arch/powerpc/include/asm/atomic.h b/arch/powerpc/include/asm/atomic.h index ae0751ef8788..f08d567e0ca4 100644 --- a/arch/powerpc/include/asm/atomic.h +++ b/arch/powerpc/include/asm/atomic.h @@ -78,21 +78,53 @@ static inline int atomic_##op##_return_relaxed(int a, atomic_t *v) \ return t; \ } +#define ATOMIC_FETCH_OP_RELAXED(op, asm_op) \ +static inline int atomic_fetch_##op##_relaxed(int a, atomic_t *v) \ +{ \ + int res, t; \ + \ + __asm__ __volatile__( \ +"1: lwarx %0,0,%4 # atomic_fetch_" #op "_relaxed\n" \ + #asm_op " %1,%3,%0\n" \ + PPC405_ERR77(0, %4) \ +" stwcx. %1,0,%4\n" \ +" bne- 1b\n" \ + : "=&r" (res), "=&r" (t), "+m" (v->counter) \ + : "r" (a), "r" (&v->counter) \ + : "cc"); \ + \ + return res; \ +} + #define ATOMIC_OPS(op, asm_op) \ ATOMIC_OP(op, asm_op) \ - ATOMIC_OP_RETURN_RELAXED(op, asm_op) + ATOMIC_OP_RETURN_RELAXED(op, asm_op) \ + ATOMIC_FETCH_OP_RELAXED(op, asm_op) ATOMIC_OPS(add, add) ATOMIC_OPS(sub, subf) -ATOMIC_OP(and, and) -ATOMIC_OP(or, or) -ATOMIC_OP(xor, xor) - #define atomic_add_return_relaxed atomic_add_return_relaxed #define atomic_sub_return_relaxed atomic_sub_return_relaxed +#define atomic_fetch_add_relaxed atomic_fetch_add_relaxed +#define atomic_fetch_sub_relaxed atomic_fetch_sub_relaxed + +#undef ATOMIC_OPS +#define ATOMIC_OPS(op, asm_op) \ + ATOMIC_OP(op, asm_op) \ + ATOMIC_FETCH_OP_RELAXED(op, asm_op) + +ATOMIC_OPS(and, and) +ATOMIC_OPS(or, or) +ATOMIC_OPS(xor, xor) + +#define atomic_fetch_and_relaxed atomic_fetch_and_relaxed +#define atomic_fetch_or_relaxed atomic_fetch_or_relaxed +#define atomic_fetch_xor_relaxed atomic_fetch_xor_relaxed + #undef ATOMIC_OPS +#undef ATOMIC_FETCH_OP_RELAXED #undef ATOMIC_OP_RETURN_RELAXED #undef ATOMIC_OP @@ -329,20 +361,53 @@ atomic64_##op##_return_relaxed(long a, atomic64_t *v) \ return t; \ } +#define ATOMIC64_FETCH_OP_RELAXED(op, asm_op) \ +static inline long \ +atomic64_fetch_##op##_relaxed(long a, atomic64_t *v) \ +{ \ + long res, t; \ + \ + __asm__ __volatile__( \ +"1: ldarx %0,0,%4 # atomic64_fetch_" #op "_relaxed\n" \ + #asm_op " %1,%3,%0\n" \ +" stdcx. %1,0,%4\n" \ +" bne- 1b\n" \ + : "=&r" (res), "=&r" (t), "+m" (v->counter) \ + : "r" (a), "r" (&v->counter) \ + : "cc"); \ + \ + return res; \ +} + #define ATOMIC64_OPS(op, asm_op) \ ATOMIC64_OP(op, asm_op) \ - ATOMIC64_OP_RETURN_RELAXED(op, asm_op) + ATOMIC64_OP_RETURN_RELAXED(op, asm_op) \ + ATOMIC64_FETCH_OP_RELAXED(op, asm_op) ATOMIC64_OPS(add, add) ATOMIC64_OPS(sub, subf) -ATOMIC64_OP(and, and) -ATOMIC64_OP(or, or) -ATOMIC64_OP(xor, xor) #define atomic64_add_return_relaxed atomic64_add_return_relaxed #define atomic64_sub_return_relaxed atomic64_sub_return_relaxed +#define atomic64_fetch_add_relaxed atomic64_fetch_add_relaxed +#define atomic64_fetch_sub_relaxed atomic64_fetch_sub_relaxed + +#undef ATOMIC64_OPS +#define ATOMIC64_OPS(op, asm_op) \ + ATOMIC64_OP(op, asm_op) \ + ATOMIC64_FETCH_OP_RELAXED(op, asm_op) + +ATOMIC64_OPS(and, and) +ATOMIC64_OPS(or, or) +ATOMIC64_OPS(xor, xor) + +#define atomic64_fetch_and_relaxed atomic64_fetch_and_relaxed +#define atomic64_fetch_or_relaxed atomic64_fetch_or_relaxed +#define atomic64_fetch_xor_relaxed atomic64_fetch_xor_relaxed + #undef ATOPIC64_OPS +#undef ATOMIC64_FETCH_OP_RELAXED #undef ATOMIC64_OP_RETURN_RELAXED #undef ATOMIC64_OP diff --git a/arch/powerpc/include/asm/book3s/32/pgalloc.h b/arch/powerpc/include/asm/book3s/32/pgalloc.h index a2350194fc76..8e21bb492dca 100644 --- a/arch/powerpc/include/asm/book3s/32/pgalloc.h +++ b/arch/powerpc/include/asm/book3s/32/pgalloc.h @@ -102,7 +102,6 @@ static inline void pgtable_free_tlb(struct mmu_gather *tlb, static inline void __pte_free_tlb(struct mmu_gather *tlb, pgtable_t table, unsigned long address) { - tlb_flush_pgtable(tlb, address); pgtable_page_dtor(table); pgtable_free_tlb(tlb, page_address(table), 0); } diff --git a/arch/powerpc/include/asm/book3s/64/mmu-hash.h b/arch/powerpc/include/asm/book3s/64/mmu-hash.h index 290157e8d5b2..74839f24f412 100644 --- a/arch/powerpc/include/asm/book3s/64/mmu-hash.h +++ b/arch/powerpc/include/asm/book3s/64/mmu-hash.h @@ -88,6 +88,7 @@ #define HPTE_R_RPN_SHIFT 12 #define HPTE_R_RPN ASM_CONST(0x0ffffffffffff000) #define HPTE_R_PP ASM_CONST(0x0000000000000003) +#define HPTE_R_PPP ASM_CONST(0x8000000000000003) #define HPTE_R_N ASM_CONST(0x0000000000000004) #define HPTE_R_G ASM_CONST(0x0000000000000008) #define HPTE_R_M ASM_CONST(0x0000000000000010) diff --git a/arch/powerpc/include/asm/book3s/64/pgalloc.h b/arch/powerpc/include/asm/book3s/64/pgalloc.h index 488279edb1f0..cd5e7aa8cc34 100644 --- a/arch/powerpc/include/asm/book3s/64/pgalloc.h +++ b/arch/powerpc/include/asm/book3s/64/pgalloc.h @@ -41,7 +41,7 @@ extern struct kmem_cache *pgtable_cache[]; pgtable_cache[(shift) - 1]; \ }) -#define PGALLOC_GFP GFP_KERNEL | __GFP_NOTRACK | __GFP_REPEAT | __GFP_ZERO +#define PGALLOC_GFP GFP_KERNEL | __GFP_NOTRACK | __GFP_ZERO extern pte_t *pte_fragment_alloc(struct mm_struct *, unsigned long, int); extern void pte_fragment_free(unsigned long *, int); @@ -56,7 +56,7 @@ static inline pgd_t *radix__pgd_alloc(struct mm_struct *mm) return (pgd_t *)__get_free_page(PGALLOC_GFP); #else struct page *page; - page = alloc_pages(PGALLOC_GFP, 4); + page = alloc_pages(PGALLOC_GFP | __GFP_REPEAT, 4); if (!page) return NULL; return (pgd_t *) page_address(page); @@ -93,8 +93,7 @@ static inline void pgd_populate(struct mm_struct *mm, pgd_t *pgd, pud_t *pud) static inline pud_t *pud_alloc_one(struct mm_struct *mm, unsigned long addr) { - return kmem_cache_alloc(PGT_CACHE(PUD_INDEX_SIZE), - GFP_KERNEL|__GFP_REPEAT); + return kmem_cache_alloc(PGT_CACHE(PUD_INDEX_SIZE), GFP_KERNEL); } static inline void pud_free(struct mm_struct *mm, pud_t *pud) @@ -110,13 +109,17 @@ static inline void pud_populate(struct mm_struct *mm, pud_t *pud, pmd_t *pmd) static inline void __pud_free_tlb(struct mmu_gather *tlb, pud_t *pud, unsigned long address) { + /* + * By now all the pud entries should be none entries. So go + * ahead and flush the page walk cache + */ + flush_tlb_pgtable(tlb, address); pgtable_free_tlb(tlb, pud, PUD_INDEX_SIZE); } static inline pmd_t *pmd_alloc_one(struct mm_struct *mm, unsigned long addr) { - return kmem_cache_alloc(PGT_CACHE(PMD_CACHE_INDEX), - GFP_KERNEL|__GFP_REPEAT); + return kmem_cache_alloc(PGT_CACHE(PMD_CACHE_INDEX), GFP_KERNEL); } static inline void pmd_free(struct mm_struct *mm, pmd_t *pmd) @@ -127,6 +130,11 @@ static inline void pmd_free(struct mm_struct *mm, pmd_t *pmd) static inline void __pmd_free_tlb(struct mmu_gather *tlb, pmd_t *pmd, unsigned long address) { + /* + * By now all the pud entries should be none entries. So go + * ahead and flush the page walk cache + */ + flush_tlb_pgtable(tlb, address); return pgtable_free_tlb(tlb, pmd, PMD_CACHE_INDEX); } @@ -151,7 +159,7 @@ static inline pgtable_t pmd_pgtable(pmd_t pmd) static inline pte_t *pte_alloc_one_kernel(struct mm_struct *mm, unsigned long address) { - return (pte_t *)__get_free_page(GFP_KERNEL | __GFP_REPEAT | __GFP_ZERO); + return (pte_t *)__get_free_page(GFP_KERNEL | __GFP_ZERO); } static inline pgtable_t pte_alloc_one(struct mm_struct *mm, @@ -198,7 +206,11 @@ static inline void pte_free(struct mm_struct *mm, pgtable_t ptepage) static inline void __pte_free_tlb(struct mmu_gather *tlb, pgtable_t table, unsigned long address) { - tlb_flush_pgtable(tlb, address); + /* + * By now all the pud entries should be none entries. So go + * ahead and flush the page walk cache + */ + flush_tlb_pgtable(tlb, address); pgtable_free_tlb(tlb, table, 0); } diff --git a/arch/powerpc/include/asm/book3s/64/pgtable.h b/arch/powerpc/include/asm/book3s/64/pgtable.h index 88a5ecaa157b..ab84c89c9e98 100644 --- a/arch/powerpc/include/asm/book3s/64/pgtable.h +++ b/arch/powerpc/include/asm/book3s/64/pgtable.h @@ -230,6 +230,7 @@ extern unsigned long __kernel_virt_size; #define KERN_VIRT_SIZE __kernel_virt_size extern struct page *vmemmap; extern unsigned long ioremap_bot; +extern unsigned long pci_io_base; #endif /* __ASSEMBLY__ */ #include <asm/book3s/64/hash.h> diff --git a/arch/powerpc/include/asm/book3s/64/radix.h b/arch/powerpc/include/asm/book3s/64/radix.h index 937d4e247ac3..df294224e280 100644 --- a/arch/powerpc/include/asm/book3s/64/radix.h +++ b/arch/powerpc/include/asm/book3s/64/radix.h @@ -228,5 +228,20 @@ extern void radix__vmemmap_remove_mapping(unsigned long start, extern int radix__map_kernel_page(unsigned long ea, unsigned long pa, pgprot_t flags, unsigned int psz); + +static inline unsigned long radix__get_tree_size(void) +{ + unsigned long rts_field; + /* + * we support 52 bits, hence 52-31 = 21, 0b10101 + * RTS encoding details + * bits 0 - 3 of rts -> bits 6 - 8 unsigned long + * bits 4 - 5 of rts -> bits 62 - 63 of unsigned long + */ + rts_field = (0x5UL << 5); /* 6 - 8 bits */ + rts_field |= (0x2UL << 61); + + return rts_field; +} #endif /* __ASSEMBLY__ */ #endif diff --git a/arch/powerpc/include/asm/book3s/64/tlbflush-radix.h b/arch/powerpc/include/asm/book3s/64/tlbflush-radix.h index 13ef38828dfe..3fa94fcac628 100644 --- a/arch/powerpc/include/asm/book3s/64/tlbflush-radix.h +++ b/arch/powerpc/include/asm/book3s/64/tlbflush-radix.h @@ -18,16 +18,19 @@ extern void radix__local_flush_tlb_mm(struct mm_struct *mm); extern void radix__local_flush_tlb_page(struct vm_area_struct *vma, unsigned long vmaddr); extern void radix___local_flush_tlb_page(struct mm_struct *mm, unsigned long vmaddr, unsigned long ap, int nid); +extern void radix__local_flush_tlb_pwc(struct mmu_gather *tlb, unsigned long addr); extern void radix__tlb_flush(struct mmu_gather *tlb); #ifdef CONFIG_SMP extern void radix__flush_tlb_mm(struct mm_struct *mm); extern void radix__flush_tlb_page(struct vm_area_struct *vma, unsigned long vmaddr); extern void radix___flush_tlb_page(struct mm_struct *mm, unsigned long vmaddr, unsigned long ap, int nid); +extern void radix__flush_tlb_pwc(struct mmu_gather *tlb, unsigned long addr); #else #define radix__flush_tlb_mm(mm) radix__local_flush_tlb_mm(mm) #define radix__flush_tlb_page(vma,addr) radix__local_flush_tlb_page(vma,addr) #define radix___flush_tlb_page(mm,addr,p,i) radix___local_flush_tlb_page(mm,addr,p,i) +#define radix__flush_tlb_pwc(tlb, addr) radix__local_flush_tlb_pwc(tlb, addr) #endif #endif diff --git a/arch/powerpc/include/asm/book3s/64/tlbflush.h b/arch/powerpc/include/asm/book3s/64/tlbflush.h index d98424ae356c..96e5769b18b0 100644 --- a/arch/powerpc/include/asm/book3s/64/tlbflush.h +++ b/arch/powerpc/include/asm/book3s/64/tlbflush.h @@ -72,5 +72,19 @@ static inline void flush_tlb_page(struct vm_area_struct *vma, #define flush_tlb_mm(mm) local_flush_tlb_mm(mm) #define flush_tlb_page(vma, addr) local_flush_tlb_page(vma, addr) #endif /* CONFIG_SMP */ +/* + * flush the page walk cache for the address + */ +static inline void flush_tlb_pgtable(struct mmu_gather *tlb, unsigned long address) +{ + /* + * Flush the page table walk cache on freeing a page table. We already + * have marked the upper/higher level page table entry none by now. + * So it is safe to flush PWC here. + */ + if (!radix_enabled()) + return; + radix__flush_tlb_pwc(tlb, address); +} #endif /* _ASM_POWERPC_BOOK3S_64_TLBFLUSH_H */ diff --git a/arch/powerpc/include/asm/book3s/pgalloc.h b/arch/powerpc/include/asm/book3s/pgalloc.h index 54f591e9572e..c0a69ae92256 100644 --- a/arch/powerpc/include/asm/book3s/pgalloc.h +++ b/arch/powerpc/include/asm/book3s/pgalloc.h @@ -4,11 +4,6 @@ #include <linux/mm.h> extern void tlb_remove_table(struct mmu_gather *tlb, void *table); -static inline void tlb_flush_pgtable(struct mmu_gather *tlb, - unsigned long address) -{ - -} #ifdef CONFIG_PPC64 #include <asm/book3s/64/pgalloc.h> diff --git a/arch/powerpc/include/asm/mutex.h b/arch/powerpc/include/asm/mutex.h index 127ab23e1f6c..078155fa1189 100644 --- a/arch/powerpc/include/asm/mutex.h +++ b/arch/powerpc/include/asm/mutex.h @@ -124,7 +124,7 @@ __mutex_fastpath_unlock(atomic_t *count, void (*fail_fn)(atomic_t *)) static inline int __mutex_fastpath_trylock(atomic_t *count, int (*fail_fn)(atomic_t *)) { - if (likely(__mutex_cmpxchg_lock(count, 1, 0) == 1)) + if (likely(atomic_read(count) == 1 && __mutex_cmpxchg_lock(count, 1, 0) == 1)) return 1; return 0; } diff --git a/arch/powerpc/include/asm/nohash/64/pgalloc.h b/arch/powerpc/include/asm/nohash/64/pgalloc.h index 0c12a3bfe2ab..897d2e1c8a9b 100644 --- a/arch/powerpc/include/asm/nohash/64/pgalloc.h +++ b/arch/powerpc/include/asm/nohash/64/pgalloc.h @@ -57,8 +57,7 @@ static inline void pgd_free(struct mm_struct *mm, pgd_t *pgd) static inline pud_t *pud_alloc_one(struct mm_struct *mm, unsigned long addr) { - return kmem_cache_alloc(PGT_CACHE(PUD_INDEX_SIZE), - GFP_KERNEL|__GFP_REPEAT); + return kmem_cache_alloc(PGT_CACHE(PUD_INDEX_SIZE), GFP_KERNEL); } static inline void pud_free(struct mm_struct *mm, pud_t *pud) @@ -88,7 +87,7 @@ static inline void pmd_populate(struct mm_struct *mm, pmd_t *pmd, static inline pte_t *pte_alloc_one_kernel(struct mm_struct *mm, unsigned long address) { - return (pte_t *)__get_free_page(GFP_KERNEL | __GFP_REPEAT | __GFP_ZERO); + return (pte_t *)__get_free_page(GFP_KERNEL | __GFP_ZERO); } static inline pgtable_t pte_alloc_one(struct mm_struct *mm, @@ -172,7 +171,7 @@ static inline pgtable_t pte_alloc_one(struct mm_struct *mm, static inline void pte_free_kernel(struct mm_struct *mm, pte_t *pte) { - pte_fragment_fre((unsigned long *)pte, 1); + pte_fragment_free((unsigned long *)pte, 1); } static inline void pte_free(struct mm_struct *mm, pgtable_t ptepage) @@ -190,8 +189,7 @@ static inline void __pte_free_tlb(struct mmu_gather *tlb, pgtable_t table, static inline pmd_t *pmd_alloc_one(struct mm_struct *mm, unsigned long addr) { - return kmem_cache_alloc(PGT_CACHE(PMD_CACHE_INDEX), - GFP_KERNEL|__GFP_REPEAT); + return kmem_cache_alloc(PGT_CACHE(PMD_CACHE_INDEX), GFP_KERNEL); } static inline void pmd_free(struct mm_struct *mm, pmd_t *pmd) diff --git a/arch/powerpc/include/asm/pgtable.h b/arch/powerpc/include/asm/pgtable.h index ee09e99097f0..9bd87f269d6d 100644 --- a/arch/powerpc/include/asm/pgtable.h +++ b/arch/powerpc/include/asm/pgtable.h @@ -71,10 +71,8 @@ pte_t *__find_linux_pte_or_hugepte(pgd_t *pgdir, unsigned long ea, static inline pte_t *find_linux_pte_or_hugepte(pgd_t *pgdir, unsigned long ea, bool *is_thp, unsigned *shift) { - if (!arch_irqs_disabled()) { - pr_info("%s called with irq enabled\n", __func__); - dump_stack(); - } + VM_WARN(!arch_irqs_disabled(), + "%s called with irq enabled\n", __func__); return __find_linux_pte_or_hugepte(pgdir, ea, is_thp, shift); } diff --git a/arch/powerpc/include/asm/ppc-opcode.h b/arch/powerpc/include/asm/ppc-opcode.h index 1d035c1cc889..49cd8760aa7c 100644 --- a/arch/powerpc/include/asm/ppc-opcode.h +++ b/arch/powerpc/include/asm/ppc-opcode.h @@ -174,6 +174,8 @@ #define PPC_INST_MFSPR_DSCR_USER_MASK 0xfc1fffff #define PPC_INST_MTSPR_DSCR_USER 0x7c0303a6 #define PPC_INST_MTSPR_DSCR_USER_MASK 0xfc1fffff +#define PPC_INST_MFVSRD 0x7c000066 +#define PPC_INST_MTVSRD 0x7c000166 #define PPC_INST_SLBFEE 0x7c0007a7 #define PPC_INST_STRING 0x7c00042a @@ -188,6 +190,8 @@ #define PPC_INST_WAIT 0x7c00007c #define PPC_INST_TLBIVAX 0x7c000624 #define PPC_INST_TLBSRX_DOT 0x7c0006a5 +#define PPC_INST_VPMSUMW 0x10000488 +#define PPC_INST_VPMSUMD 0x100004c8 #define PPC_INST_XXLOR 0xf0000510 #define PPC_INST_XXSWAPD 0xf0000250 #define PPC_INST_XVCPSGNDP 0xf0000780 @@ -359,6 +363,14 @@ VSX_XX1((s), a, b)) #define LXVD2X(s, a, b) stringify_in_c(.long PPC_INST_LXVD2X | \ VSX_XX1((s), a, b)) +#define MFVRD(a, t) stringify_in_c(.long PPC_INST_MFVSRD | \ + VSX_XX1((t)+32, a, R0)) +#define MTVRD(t, a) stringify_in_c(.long PPC_INST_MTVSRD | \ + VSX_XX1((t)+32, a, R0)) +#define VPMSUMW(t, a, b) stringify_in_c(.long PPC_INST_VPMSUMW | \ + VSX_XX3((t), a, b)) +#define VPMSUMD(t, a, b) stringify_in_c(.long PPC_INST_VPMSUMD | \ + VSX_XX3((t), a, b)) #define XXLOR(t, a, b) stringify_in_c(.long PPC_INST_XXLOR | \ VSX_XX3((t), a, b)) #define XXSWAPD(t, a) stringify_in_c(.long PPC_INST_XXSWAPD | \ diff --git a/arch/powerpc/include/asm/ppc_asm.h b/arch/powerpc/include/asm/ppc_asm.h index 2b31632376a5..051af612a7e1 100644 --- a/arch/powerpc/include/asm/ppc_asm.h +++ b/arch/powerpc/include/asm/ppc_asm.h @@ -286,6 +286,9 @@ n: #endif +#define FUNC_START(name) _GLOBAL(name) +#define FUNC_END(name) + /* * LOAD_REG_IMMEDIATE(rn, expr) * Loads the value of the constant expression 'expr' into register 'rn' diff --git a/arch/powerpc/kernel/eeh_driver.c b/arch/powerpc/kernel/eeh_driver.c index 2714a3b81d24..d70101e1e25c 100644 --- a/arch/powerpc/kernel/eeh_driver.c +++ b/arch/powerpc/kernel/eeh_driver.c @@ -642,13 +642,12 @@ static int eeh_reset_device(struct eeh_pe *pe, struct pci_bus *bus, if (pe->type & EEH_PE_VF) { eeh_pe_dev_traverse(pe, eeh_rmv_device, NULL); } else { - eeh_pe_state_clear(pe, EEH_PE_PRI_BUS); pci_lock_rescan_remove(); pci_hp_remove_devices(bus); pci_unlock_rescan_remove(); } } else if (frozen_bus) { - eeh_pe_dev_traverse(pe, eeh_rmv_device, &rmv_data); + eeh_pe_dev_traverse(pe, eeh_rmv_device, rmv_data); } /* @@ -692,10 +691,12 @@ static int eeh_reset_device(struct eeh_pe *pe, struct pci_bus *bus, */ edev = list_first_entry(&pe->edevs, struct eeh_dev, list); eeh_pe_traverse(pe, eeh_pe_detach_dev, NULL); - if (pe->type & EEH_PE_VF) + if (pe->type & EEH_PE_VF) { eeh_add_virt_device(edev, NULL); - else + } else { + eeh_pe_state_clear(pe, EEH_PE_PRI_BUS); pci_hp_add_devices(bus); + } } else if (frozen_bus && rmv_data->removed) { pr_info("EEH: Sleep 5s ahead of partial hotplug\n"); ssleep(5); diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S index 4c9440629128..8bcc1b457115 100644 --- a/arch/powerpc/kernel/exceptions-64s.S +++ b/arch/powerpc/kernel/exceptions-64s.S @@ -1399,11 +1399,12 @@ END_MMU_FTR_SECTION_IFCLR(MMU_FTR_RADIX) lwz r9,PACA_EXSLB+EX_CCR(r13) /* get saved CR */ mtlr r10 -BEGIN_MMU_FTR_SECTION - b 2f -END_MMU_FTR_SECTION_IFSET(MMU_FTR_RADIX) andi. r10,r12,MSR_RI /* check for unrecoverable exception */ +BEGIN_MMU_FTR_SECTION beq- 2f +FTR_SECTION_ELSE + b 2f +ALT_MMU_FTR_SECTION_END_IFCLR(MMU_FTR_RADIX) .machine push .machine "power4" diff --git a/arch/powerpc/kernel/iomap.c b/arch/powerpc/kernel/iomap.c index 12e48d56f771..3963f0b68d52 100644 --- a/arch/powerpc/kernel/iomap.c +++ b/arch/powerpc/kernel/iomap.c @@ -38,6 +38,18 @@ EXPORT_SYMBOL(ioread16); EXPORT_SYMBOL(ioread16be); EXPORT_SYMBOL(ioread32); EXPORT_SYMBOL(ioread32be); +#ifdef __powerpc64__ +u64 ioread64(void __iomem *addr) +{ + return readq(addr); +} +u64 ioread64be(void __iomem *addr) +{ + return readq_be(addr); +} +EXPORT_SYMBOL(ioread64); +EXPORT_SYMBOL(ioread64be); +#endif /* __powerpc64__ */ void iowrite8(u8 val, void __iomem *addr) { @@ -64,6 +76,18 @@ EXPORT_SYMBOL(iowrite16); EXPORT_SYMBOL(iowrite16be); EXPORT_SYMBOL(iowrite32); EXPORT_SYMBOL(iowrite32be); +#ifdef __powerpc64__ +void iowrite64(u64 val, void __iomem *addr) +{ + writeq(val, addr); +} +void iowrite64be(u64 val, void __iomem *addr) +{ + writeq_be(val, addr); +} +EXPORT_SYMBOL(iowrite64); +EXPORT_SYMBOL(iowrite64be); +#endif /* __powerpc64__ */ /* * These are the "repeat read/write" functions. Note the diff --git a/arch/powerpc/kernel/nvram_64.c b/arch/powerpc/kernel/nvram_64.c index 856f9a7944cd..64174bf95611 100644 --- a/arch/powerpc/kernel/nvram_64.c +++ b/arch/powerpc/kernel/nvram_64.c @@ -444,7 +444,8 @@ static int nvram_pstore_write(enum pstore_type_id type, */ static ssize_t nvram_pstore_read(u64 *id, enum pstore_type_id *type, int *count, struct timespec *time, char **buf, - bool *compressed, struct pstore_info *psi) + bool *compressed, ssize_t *ecc_notice_size, + struct pstore_info *psi) { struct oops_log_info *oops_hdr; unsigned int err_type, id_no, size = 0; @@ -545,6 +546,7 @@ static ssize_t nvram_pstore_read(u64 *id, enum pstore_type_id *type, return -ENOMEM; kfree(buff); + *ecc_notice_size = 0; if (err_type == ERR_TYPE_KERNEL_PANIC_GZ) *compressed = true; else diff --git a/arch/powerpc/kernel/pci_64.c b/arch/powerpc/kernel/pci_64.c index 3759df52bd67..a5ae49a2dcc4 100644 --- a/arch/powerpc/kernel/pci_64.c +++ b/arch/powerpc/kernel/pci_64.c @@ -47,7 +47,6 @@ static int __init pcibios_init(void) printk(KERN_INFO "PCI: Probing PCI hardware\n"); - pci_io_base = ISA_IO_BASE; /* For now, override phys_mem_access_prot. If we need it,g * later, we may move that initialization to each ppc_md */ diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c index e2f12cbcade9..0b93893424f5 100644 --- a/arch/powerpc/kernel/process.c +++ b/arch/powerpc/kernel/process.c @@ -1505,6 +1505,16 @@ void start_thread(struct pt_regs *regs, unsigned long start, unsigned long sp) current->thread.regs = regs - 1; } +#ifdef CONFIG_PPC_TRANSACTIONAL_MEM + /* + * Clear any transactional state, we're exec()ing. The cause is + * not important as there will never be a recheckpoint so it's not + * user visible. + */ + if (MSR_TM_SUSPENDED(mfmsr())) + tm_reclaim_current(0); +#endif + memset(regs->gpr, 0, sizeof(regs->gpr)); regs->ctr = 0; regs->link = 0; diff --git a/arch/powerpc/kernel/prom_init.c b/arch/powerpc/kernel/prom_init.c index ccd2037c797f..6ee4b72cda42 100644 --- a/arch/powerpc/kernel/prom_init.c +++ b/arch/powerpc/kernel/prom_init.c @@ -719,7 +719,7 @@ unsigned char ibm_architecture_vec[] = { * must match by the macro below. Update the definition if * the structure layout changes. */ -#define IBM_ARCH_VEC_NRCORES_OFFSET 125 +#define IBM_ARCH_VEC_NRCORES_OFFSET 133 W(NR_CPUS), /* number of cores supported */ 0, 0, diff --git a/arch/powerpc/kernel/ptrace.c b/arch/powerpc/kernel/ptrace.c index 5dc47ebb3840..134bee9ac664 100644 --- a/arch/powerpc/kernel/ptrace.c +++ b/arch/powerpc/kernel/ptrace.c @@ -377,7 +377,7 @@ static int fpr_get(struct task_struct *target, const struct user_regset *regset, #else BUILD_BUG_ON(offsetof(struct thread_fp_state, fpscr) != - offsetof(struct thread_fp_state, fpr[32][0])); + offsetof(struct thread_fp_state, fpr[32])); return user_regset_copyout(&pos, &count, &kbuf, &ubuf, &target->thread.fp_state, 0, -1); @@ -405,7 +405,7 @@ static int fpr_set(struct task_struct *target, const struct user_regset *regset, return 0; #else BUILD_BUG_ON(offsetof(struct thread_fp_state, fpscr) != - offsetof(struct thread_fp_state, fpr[32][0])); + offsetof(struct thread_fp_state, fpr[32])); return user_regset_copyin(&pos, &count, &kbuf, &ubuf, &target->thread.fp_state, 0, -1); diff --git a/arch/powerpc/kernel/tm.S b/arch/powerpc/kernel/tm.S index bf8f34a58670..b7019b559ddb 100644 --- a/arch/powerpc/kernel/tm.S +++ b/arch/powerpc/kernel/tm.S @@ -110,17 +110,11 @@ _GLOBAL(tm_reclaim) std r3, STK_PARAM(R3)(r1) SAVE_NVGPRS(r1) - /* We need to setup MSR for VSX register save instructions. Here we - * also clear the MSR RI since when we do the treclaim, we won't have a - * valid kernel pointer for a while. We clear RI here as it avoids - * adding another mtmsr closer to the treclaim. This makes the region - * maked as non-recoverable wider than it needs to be but it saves on - * inserting another mtmsrd later. - */ + /* We need to setup MSR for VSX register save instructions. */ mfmsr r14 mr r15, r14 ori r15, r15, MSR_FP - li r16, MSR_RI + li r16, 0 ori r16, r16, MSR_EE /* IRQs hard off */ andc r15, r15, r16 oris r15, r15, MSR_VEC@h @@ -176,7 +170,17 @@ dont_backup_fp: 1: tdeqi r6, 0 EMIT_BUG_ENTRY 1b,__FILE__,__LINE__,0 - /* The moment we treclaim, ALL of our GPRs will switch + /* Clear MSR RI since we are about to change r1, EE is already off. */ + li r4, 0 + mtmsrd r4, 1 + + /* + * BE CAREFUL HERE: + * At this point we can't take an SLB miss since we have MSR_RI + * off. Load only to/from the stack/paca which are in SLB bolted regions + * until we turn MSR RI back on. + * + * The moment we treclaim, ALL of our GPRs will switch * to user register state. (FPRs, CCR etc. also!) * Use an sprg and a tm_scratch in the PACA to shuffle. */ @@ -197,6 +201,11 @@ dont_backup_fp: /* Store the PPR in r11 and reset to decent value */ std r11, GPR11(r1) /* Temporary stash */ + + /* Reset MSR RI so we can take SLB faults again */ + li r11, MSR_RI + mtmsrd r11, 1 + mfspr r11, SPRN_PPR HMT_MEDIUM @@ -397,11 +406,6 @@ restore_gprs: ld r5, THREAD_TM_DSCR(r3) ld r6, THREAD_TM_PPR(r3) - /* Clear the MSR RI since we are about to change R1. EE is already off - */ - li r4, 0 - mtmsrd r4, 1 - REST_GPR(0, r7) /* GPR0 */ REST_2GPRS(2, r7) /* GPR2-3 */ REST_GPR(4, r7) /* GPR4 */ @@ -439,10 +443,33 @@ restore_gprs: ld r6, _CCR(r7) mtcr r6 - REST_GPR(1, r7) /* GPR1 */ - REST_GPR(5, r7) /* GPR5-7 */ REST_GPR(6, r7) - ld r7, GPR7(r7) + + /* + * Store r1 and r5 on the stack so that we can access them + * after we clear MSR RI. + */ + + REST_GPR(5, r7) + std r5, -8(r1) + ld r5, GPR1(r7) + std r5, -16(r1) + + REST_GPR(7, r7) + + /* Clear MSR RI since we are about to change r1. EE is already off */ + li r5, 0 + mtmsrd r5, 1 + + /* + * BE CAREFUL HERE: + * At this point we can't take an SLB miss since we have MSR_RI + * off. Load only to/from the stack/paca which are in SLB bolted regions + * until we turn MSR RI back on. + */ + + ld r5, -8(r1) + ld r1, -16(r1) /* Commit register state as checkpointed state: */ TRECHKPT diff --git a/arch/powerpc/mm/copro_fault.c b/arch/powerpc/mm/copro_fault.c index 6527882ce05e..bb0354222b11 100644 --- a/arch/powerpc/mm/copro_fault.c +++ b/arch/powerpc/mm/copro_fault.c @@ -75,7 +75,7 @@ int copro_handle_mm_fault(struct mm_struct *mm, unsigned long ea, } ret = 0; - *flt = handle_mm_fault(mm, vma, ea, is_write ? FAULT_FLAG_WRITE : 0); + *flt = handle_mm_fault(vma, ea, is_write ? FAULT_FLAG_WRITE : 0); if (unlikely(*flt & VM_FAULT_ERROR)) { if (*flt & VM_FAULT_OOM) { ret = -ENOMEM; diff --git a/arch/powerpc/mm/fault.c b/arch/powerpc/mm/fault.c index a67c6d781c52..a4db22f65021 100644 --- a/arch/powerpc/mm/fault.c +++ b/arch/powerpc/mm/fault.c @@ -429,7 +429,7 @@ good_area: * make sure we exit gracefully rather than endlessly redo * the fault. */ - fault = handle_mm_fault(mm, vma, address, flags); + fault = handle_mm_fault(vma, address, flags); if (unlikely(fault & (VM_FAULT_RETRY|VM_FAULT_ERROR))) { if (fault & VM_FAULT_SIGSEGV) goto bad_area; diff --git a/arch/powerpc/mm/hash_native_64.c b/arch/powerpc/mm/hash_native_64.c index d873f6507f72..f8a871a72985 100644 --- a/arch/powerpc/mm/hash_native_64.c +++ b/arch/powerpc/mm/hash_native_64.c @@ -316,8 +316,8 @@ static long native_hpte_updatepp(unsigned long slot, unsigned long newpp, DBG_LOW(" -> hit\n"); /* Update the HPTE */ hptep->r = cpu_to_be64((be64_to_cpu(hptep->r) & - ~(HPTE_R_PP | HPTE_R_N)) | - (newpp & (HPTE_R_PP | HPTE_R_N | + ~(HPTE_R_PPP | HPTE_R_N)) | + (newpp & (HPTE_R_PPP | HPTE_R_N | HPTE_R_C))); } native_unlock_hpte(hptep); @@ -385,8 +385,8 @@ static void native_hpte_updateboltedpp(unsigned long newpp, unsigned long ea, /* Update the HPTE */ hptep->r = cpu_to_be64((be64_to_cpu(hptep->r) & - ~(HPTE_R_PP | HPTE_R_N)) | - (newpp & (HPTE_R_PP | HPTE_R_N))); + ~(HPTE_R_PPP | HPTE_R_N)) | + (newpp & (HPTE_R_PPP | HPTE_R_N))); /* * Ensure it is out of the tlb too. Bolted entries base and * actual page size will be same. @@ -550,7 +550,11 @@ static void hpte_decode(struct hash_pte *hpte, unsigned long slot, } } /* This works for all page sizes, and for 256M and 1T segments */ - *ssize = hpte_v >> HPTE_V_SSIZE_SHIFT; + if (cpu_has_feature(CPU_FTR_ARCH_300)) + *ssize = hpte_r >> HPTE_R_3_0_SSIZE_SHIFT; + else + *ssize = hpte_v >> HPTE_V_SSIZE_SHIFT; + shift = mmu_psize_defs[size].shift; avpn = (HPTE_V_AVPN_VAL(hpte_v) & ~mmu_psize_defs[size].avpnm); diff --git a/arch/powerpc/mm/hash_utils_64.c b/arch/powerpc/mm/hash_utils_64.c index b2740c67e172..2971ea18c768 100644 --- a/arch/powerpc/mm/hash_utils_64.c +++ b/arch/powerpc/mm/hash_utils_64.c @@ -201,9 +201,8 @@ unsigned long htab_convert_pte_flags(unsigned long pteflags) /* * We can't allow hardware to update hpte bits. Hence always * set 'R' bit and set 'C' if it is a write fault - * Memory coherence is always enabled */ - rflags |= HPTE_R_R | HPTE_R_M; + rflags |= HPTE_R_R; if (pteflags & _PAGE_DIRTY) rflags |= HPTE_R_C; @@ -213,10 +212,15 @@ unsigned long htab_convert_pte_flags(unsigned long pteflags) if ((pteflags & _PAGE_CACHE_CTL) == _PAGE_TOLERANT) rflags |= HPTE_R_I; - if ((pteflags & _PAGE_CACHE_CTL ) == _PAGE_NON_IDEMPOTENT) + else if ((pteflags & _PAGE_CACHE_CTL) == _PAGE_NON_IDEMPOTENT) rflags |= (HPTE_R_I | HPTE_R_G); - if ((pteflags & _PAGE_CACHE_CTL) == _PAGE_SAO) - rflags |= (HPTE_R_I | HPTE_R_W); + else if ((pteflags & _PAGE_CACHE_CTL) == _PAGE_SAO) + rflags |= (HPTE_R_W | HPTE_R_I | HPTE_R_M); + else + /* + * Add memory coherence if cache inhibited is not set + */ + rflags |= HPTE_R_M; return rflags; } @@ -918,6 +922,10 @@ void __init hash__early_init_mmu(void) vmemmap = (struct page *)H_VMEMMAP_BASE; ioremap_bot = IOREMAP_BASE; +#ifdef CONFIG_PCI + pci_io_base = ISA_IO_BASE; +#endif + /* Initialize the MMU Hash table and create the linear mapping * of memory. Has to be done before SLB initialization as this is * currently where the page size encoding is obtained. diff --git a/arch/powerpc/mm/hugetlbpage.c b/arch/powerpc/mm/hugetlbpage.c index 5aac1a3f86cd..119d18611500 100644 --- a/arch/powerpc/mm/hugetlbpage.c +++ b/arch/powerpc/mm/hugetlbpage.c @@ -73,7 +73,7 @@ static int __hugepte_alloc(struct mm_struct *mm, hugepd_t *hpdp, cachep = PGT_CACHE(pdshift - pshift); #endif - new = kmem_cache_zalloc(cachep, GFP_KERNEL|__GFP_REPEAT); + new = kmem_cache_zalloc(cachep, GFP_KERNEL); BUG_ON(pshift > HUGEPD_SHIFT_MASK); BUG_ON((unsigned long)new & HUGEPD_SHIFT_MASK); diff --git a/arch/powerpc/mm/mmu_context_book3s64.c b/arch/powerpc/mm/mmu_context_book3s64.c index 227b2a6c4544..196222227e82 100644 --- a/arch/powerpc/mm/mmu_context_book3s64.c +++ b/arch/powerpc/mm/mmu_context_book3s64.c @@ -65,7 +65,7 @@ static int radix__init_new_context(struct mm_struct *mm, int index) /* * set the process table entry, */ - rts_field = 3ull << PPC_BITLSHIFT(2); + rts_field = radix__get_tree_size(); process_tb[index].prtb0 = cpu_to_be64(rts_field | __pa(mm->pgd) | RADIX_PGD_INDEX_SIZE); return 0; } diff --git a/arch/powerpc/mm/numa.c b/arch/powerpc/mm/numa.c index 669a15e7fa76..6dc07ddbfd04 100644 --- a/arch/powerpc/mm/numa.c +++ b/arch/powerpc/mm/numa.c @@ -581,30 +581,22 @@ static void verify_cpu_node_mapping(int cpu, int node) } } -static int cpu_numa_callback(struct notifier_block *nfb, unsigned long action, - void *hcpu) +/* Must run before sched domains notifier. */ +static int ppc_numa_cpu_prepare(unsigned int cpu) { - unsigned long lcpu = (unsigned long)hcpu; - int ret = NOTIFY_DONE, nid; + int nid; - switch (action) { - case CPU_UP_PREPARE: - case CPU_UP_PREPARE_FROZEN: - nid = numa_setup_cpu(lcpu); - verify_cpu_node_mapping((int)lcpu, nid); - ret = NOTIFY_OK; - break; + nid = numa_setup_cpu(cpu); + verify_cpu_node_mapping(cpu, nid); + return 0; +} + +static int ppc_numa_cpu_dead(unsigned int cpu) +{ #ifdef CONFIG_HOTPLUG_CPU - case CPU_DEAD: - case CPU_DEAD_FROZEN: - case CPU_UP_CANCELED: - case CPU_UP_CANCELED_FROZEN: - unmap_cpu_from_node(lcpu); - ret = NOTIFY_OK; - break; + unmap_cpu_from_node(cpu); #endif - } - return ret; + return 0; } /* @@ -913,11 +905,6 @@ static void __init dump_numa_memory_topology(void) } } -static struct notifier_block ppc64_numa_nb = { - .notifier_call = cpu_numa_callback, - .priority = 1 /* Must run before sched domains notifier. */ -}; - /* Initialize NODE_DATA for a node on the local memory */ static void __init setup_node_data(int nid, u64 start_pfn, u64 end_pfn) { @@ -985,15 +972,18 @@ void __init initmem_init(void) setup_node_to_cpumask_map(); reset_numa_cpu_lookup_table(); - register_cpu_notifier(&ppc64_numa_nb); + /* * We need the numa_cpu_lookup_table to be accurate for all CPUs, * even before we online them, so that we can use cpu_to_{node,mem} * early in boot, cf. smp_prepare_cpus(). + * _nocalls() + manual invocation is used because cpuhp is not yet + * initialized for the boot CPU. */ - for_each_present_cpu(cpu) { - numa_setup_cpu((unsigned long)cpu); - } + cpuhp_setup_state_nocalls(CPUHP_POWER_NUMA_PREPARE, "POWER_NUMA_PREPARE", + ppc_numa_cpu_prepare, ppc_numa_cpu_dead); + for_each_present_cpu(cpu) + numa_setup_cpu(cpu); } static int __init early_numa(char *p) diff --git a/arch/powerpc/mm/pgtable-radix.c b/arch/powerpc/mm/pgtable-radix.c index c939e6e57a9e..7931e1496f0d 100644 --- a/arch/powerpc/mm/pgtable-radix.c +++ b/arch/powerpc/mm/pgtable-radix.c @@ -160,9 +160,8 @@ redo: process_tb = early_alloc_pgtable(1UL << PRTB_SIZE_SHIFT); /* * Fill in the process table. - * we support 52 bits, hence 52-28 = 24, 11000 */ - rts_field = 3ull << PPC_BITLSHIFT(2); + rts_field = radix__get_tree_size(); process_tb->prtb0 = cpu_to_be64(rts_field | __pa(init_mm.pgd) | RADIX_PGD_INDEX_SIZE); /* * Fill in the partition table. We are suppose to use effective address @@ -176,10 +175,8 @@ redo: static void __init radix_init_partition_table(void) { unsigned long rts_field; - /* - * we support 52 bits, hence 52-28 = 24, 11000 - */ - rts_field = 3ull << PPC_BITLSHIFT(2); + + rts_field = radix__get_tree_size(); BUILD_BUG_ON_MSG((PATB_SIZE_SHIFT > 24), "Partition table size too large."); partition_tb = early_alloc_pgtable(1UL << PATB_SIZE_SHIFT); @@ -331,6 +328,11 @@ void __init radix__early_init_mmu(void) __vmalloc_end = RADIX_VMALLOC_END; vmemmap = (struct page *)RADIX_VMEMMAP_BASE; ioremap_bot = IOREMAP_BASE; + +#ifdef CONFIG_PCI + pci_io_base = ISA_IO_BASE; +#endif + /* * For now radix also use the same frag size */ diff --git a/arch/powerpc/mm/pgtable_32.c b/arch/powerpc/mm/pgtable_32.c index bf7bf32b54f8..7f922f557936 100644 --- a/arch/powerpc/mm/pgtable_32.c +++ b/arch/powerpc/mm/pgtable_32.c @@ -84,7 +84,7 @@ __init_refok pte_t *pte_alloc_one_kernel(struct mm_struct *mm, unsigned long add pte_t *pte; if (slab_is_available()) { - pte = (pte_t *)__get_free_page(GFP_KERNEL|__GFP_REPEAT|__GFP_ZERO); + pte = (pte_t *)__get_free_page(GFP_KERNEL|__GFP_ZERO); } else { pte = __va(memblock_alloc(PAGE_SIZE, PAGE_SIZE)); if (pte) @@ -97,7 +97,7 @@ pgtable_t pte_alloc_one(struct mm_struct *mm, unsigned long address) { struct page *ptepage; - gfp_t flags = GFP_KERNEL | __GFP_REPEAT | __GFP_ZERO; + gfp_t flags = GFP_KERNEL | __GFP_ZERO; ptepage = alloc_pages(flags, 0); if (!ptepage) diff --git a/arch/powerpc/mm/pgtable_64.c b/arch/powerpc/mm/pgtable_64.c index e009e0604a8a..f5e8d4edb808 100644 --- a/arch/powerpc/mm/pgtable_64.c +++ b/arch/powerpc/mm/pgtable_64.c @@ -350,8 +350,7 @@ static pte_t *get_from_cache(struct mm_struct *mm) static pte_t *__alloc_for_cache(struct mm_struct *mm, int kernel) { void *ret = NULL; - struct page *page = alloc_page(GFP_KERNEL | __GFP_NOTRACK | - __GFP_REPEAT | __GFP_ZERO); + struct page *page = alloc_page(GFP_KERNEL | __GFP_NOTRACK | __GFP_ZERO); if (!page) return NULL; if (!kernel && !pgtable_page_ctor(page)) { diff --git a/arch/powerpc/mm/tlb-radix.c b/arch/powerpc/mm/tlb-radix.c index 0fdaf93a3e09..ab2f60e812e2 100644 --- a/arch/powerpc/mm/tlb-radix.c +++ b/arch/powerpc/mm/tlb-radix.c @@ -18,16 +18,20 @@ static DEFINE_RAW_SPINLOCK(native_tlbie_lock); -static inline void __tlbiel_pid(unsigned long pid, int set) +#define RIC_FLUSH_TLB 0 +#define RIC_FLUSH_PWC 1 +#define RIC_FLUSH_ALL 2 + +static inline void __tlbiel_pid(unsigned long pid, int set, + unsigned long ric) { - unsigned long rb,rs,ric,prs,r; + unsigned long rb,rs,prs,r; rb = PPC_BIT(53); /* IS = 1 */ rb |= set << PPC_BITLSHIFT(51); rs = ((unsigned long)pid) << PPC_BITLSHIFT(31); prs = 1; /* process scoped */ r = 1; /* raidx format */ - ric = 2; /* invalidate all the caches */ asm volatile("ptesync": : :"memory"); asm volatile(".long 0x7c000224 | (%0 << 11) | (%1 << 16) |" @@ -39,25 +43,24 @@ static inline void __tlbiel_pid(unsigned long pid, int set) /* * We use 128 set in radix mode and 256 set in hpt mode. */ -static inline void _tlbiel_pid(unsigned long pid) +static inline void _tlbiel_pid(unsigned long pid, unsigned long ric) { int set; for (set = 0; set < POWER9_TLB_SETS_RADIX ; set++) { - __tlbiel_pid(pid, set); + __tlbiel_pid(pid, set, ric); } return; } -static inline void _tlbie_pid(unsigned long pid) +static inline void _tlbie_pid(unsigned long pid, unsigned long ric) { - unsigned long rb,rs,ric,prs,r; + unsigned long rb,rs,prs,r; rb = PPC_BIT(53); /* IS = 1 */ rs = pid << PPC_BITLSHIFT(31); prs = 1; /* process scoped */ r = 1; /* raidx format */ - ric = 2; /* invalidate all the caches */ asm volatile("ptesync": : :"memory"); asm volatile(".long 0x7c000264 | (%0 << 11) | (%1 << 16) |" @@ -67,16 +70,15 @@ static inline void _tlbie_pid(unsigned long pid) } static inline void _tlbiel_va(unsigned long va, unsigned long pid, - unsigned long ap) + unsigned long ap, unsigned long ric) { - unsigned long rb,rs,ric,prs,r; + unsigned long rb,rs,prs,r; rb = va & ~(PPC_BITMASK(52, 63)); rb |= ap << PPC_BITLSHIFT(58); rs = pid << PPC_BITLSHIFT(31); prs = 1; /* process scoped */ r = 1; /* raidx format */ - ric = 0; /* no cluster flush yet */ asm volatile("ptesync": : :"memory"); asm volatile(".long 0x7c000224 | (%0 << 11) | (%1 << 16) |" @@ -86,16 +88,15 @@ static inline void _tlbiel_va(unsigned long va, unsigned long pid, } static inline void _tlbie_va(unsigned long va, unsigned long pid, - unsigned long ap) + unsigned long ap, unsigned long ric) { - unsigned long rb,rs,ric,prs,r; + unsigned long rb,rs,prs,r; rb = va & ~(PPC_BITMASK(52, 63)); rb |= ap << PPC_BITLSHIFT(58); rs = pid << PPC_BITLSHIFT(31); prs = 1; /* process scoped */ r = 1; /* raidx format */ - ric = 0; /* no cluster flush yet */ asm volatile("ptesync": : :"memory"); asm volatile(".long 0x7c000264 | (%0 << 11) | (%1 << 16) |" @@ -117,25 +118,40 @@ static inline void _tlbie_va(unsigned long va, unsigned long pid, */ void radix__local_flush_tlb_mm(struct mm_struct *mm) { - unsigned int pid; + unsigned long pid; preempt_disable(); pid = mm->context.id; if (pid != MMU_NO_CONTEXT) - _tlbiel_pid(pid); + _tlbiel_pid(pid, RIC_FLUSH_ALL); preempt_enable(); } EXPORT_SYMBOL(radix__local_flush_tlb_mm); +void radix__local_flush_tlb_pwc(struct mmu_gather *tlb, unsigned long addr) +{ + unsigned long pid; + struct mm_struct *mm = tlb->mm; + + preempt_disable(); + + pid = mm->context.id; + if (pid != MMU_NO_CONTEXT) + _tlbiel_pid(pid, RIC_FLUSH_PWC); + + preempt_enable(); +} +EXPORT_SYMBOL(radix__local_flush_tlb_pwc); + void radix___local_flush_tlb_page(struct mm_struct *mm, unsigned long vmaddr, unsigned long ap, int nid) { - unsigned int pid; + unsigned long pid; preempt_disable(); pid = mm ? mm->context.id : 0; if (pid != MMU_NO_CONTEXT) - _tlbiel_va(vmaddr, pid, ap); + _tlbiel_va(vmaddr, pid, ap, RIC_FLUSH_TLB); preempt_enable(); } @@ -160,7 +176,7 @@ static int mm_is_core_local(struct mm_struct *mm) void radix__flush_tlb_mm(struct mm_struct *mm) { - unsigned int pid; + unsigned long pid; preempt_disable(); pid = mm->context.id; @@ -172,20 +188,46 @@ void radix__flush_tlb_mm(struct mm_struct *mm) if (lock_tlbie) raw_spin_lock(&native_tlbie_lock); - _tlbie_pid(pid); + _tlbie_pid(pid, RIC_FLUSH_ALL); if (lock_tlbie) raw_spin_unlock(&native_tlbie_lock); } else - _tlbiel_pid(pid); + _tlbiel_pid(pid, RIC_FLUSH_ALL); no_context: preempt_enable(); } EXPORT_SYMBOL(radix__flush_tlb_mm); +void radix__flush_tlb_pwc(struct mmu_gather *tlb, unsigned long addr) +{ + unsigned long pid; + struct mm_struct *mm = tlb->mm; + + preempt_disable(); + + pid = mm->context.id; + if (unlikely(pid == MMU_NO_CONTEXT)) + goto no_context; + + if (!mm_is_core_local(mm)) { + int lock_tlbie = !mmu_has_feature(MMU_FTR_LOCKLESS_TLBIE); + + if (lock_tlbie) + raw_spin_lock(&native_tlbie_lock); + _tlbie_pid(pid, RIC_FLUSH_PWC); + if (lock_tlbie) + raw_spin_unlock(&native_tlbie_lock); + } else + _tlbiel_pid(pid, RIC_FLUSH_PWC); +no_context: + preempt_enable(); +} +EXPORT_SYMBOL(radix__flush_tlb_pwc); + void radix___flush_tlb_page(struct mm_struct *mm, unsigned long vmaddr, unsigned long ap, int nid) { - unsigned int pid; + unsigned long pid; preempt_disable(); pid = mm ? mm->context.id : 0; @@ -196,11 +238,11 @@ void radix___flush_tlb_page(struct mm_struct *mm, unsigned long vmaddr, if (lock_tlbie) raw_spin_lock(&native_tlbie_lock); - _tlbie_va(vmaddr, pid, ap); + _tlbie_va(vmaddr, pid, ap, RIC_FLUSH_TLB); if (lock_tlbie) raw_spin_unlock(&native_tlbie_lock); } else - _tlbiel_va(vmaddr, pid, ap); + _tlbiel_va(vmaddr, pid, ap, RIC_FLUSH_TLB); bail: preempt_enable(); } @@ -224,7 +266,7 @@ void radix__flush_tlb_kernel_range(unsigned long start, unsigned long end) if (lock_tlbie) raw_spin_lock(&native_tlbie_lock); - _tlbie_pid(0); + _tlbie_pid(0, RIC_FLUSH_ALL); if (lock_tlbie) raw_spin_unlock(&native_tlbie_lock); } diff --git a/arch/powerpc/perf/core-book3s.c b/arch/powerpc/perf/core-book3s.c index 97a1d40d8696..ffd61d55fb25 100644 --- a/arch/powerpc/perf/core-book3s.c +++ b/arch/powerpc/perf/core-book3s.c @@ -2158,31 +2158,15 @@ static void perf_event_interrupt(struct pt_regs *regs) irq_exit(); } -static void power_pmu_setup(int cpu) +int power_pmu_prepare_cpu(unsigned int cpu) { struct cpu_hw_events *cpuhw = &per_cpu(cpu_hw_events, cpu); - if (!ppmu) - return; - memset(cpuhw, 0, sizeof(*cpuhw)); - cpuhw->mmcr[0] = MMCR0_FC; -} - -static int -power_pmu_notifier(struct notifier_block *self, unsigned long action, void *hcpu) -{ - unsigned int cpu = (long)hcpu; - - switch (action & ~CPU_TASKS_FROZEN) { - case CPU_UP_PREPARE: - power_pmu_setup(cpu); - break; - - default: - break; + if (ppmu) { + memset(cpuhw, 0, sizeof(*cpuhw)); + cpuhw->mmcr[0] = MMCR0_FC; } - - return NOTIFY_OK; + return 0; } int register_power_pmu(struct power_pmu *pmu) @@ -2205,7 +2189,7 @@ int register_power_pmu(struct power_pmu *pmu) #endif /* CONFIG_PPC64 */ perf_pmu_register(&power_pmu, "cpu", PERF_TYPE_RAW); - perf_cpu_notifier(power_pmu_notifier); - + cpuhp_setup_state(CPUHP_PERF_POWER, "PERF_POWER", + power_pmu_prepare_cpu, NULL); return 0; } diff --git a/arch/powerpc/platforms/40x/Kconfig b/arch/powerpc/platforms/40x/Kconfig index 6e287f1294fa..e3257f24a8a1 100644 --- a/arch/powerpc/platforms/40x/Kconfig +++ b/arch/powerpc/platforms/40x/Kconfig @@ -137,7 +137,7 @@ config STB03xxx config PPC4xx_GPIO bool "PPC4xx GPIO support" depends on 40x - select ARCH_REQUIRE_GPIOLIB + select GPIOLIB help Enable gpiolib support for ppc40x based boards diff --git a/arch/powerpc/platforms/44x/Kconfig b/arch/powerpc/platforms/44x/Kconfig index 5538e57c36c1..48fc18041ff6 100644 --- a/arch/powerpc/platforms/44x/Kconfig +++ b/arch/powerpc/platforms/44x/Kconfig @@ -273,7 +273,7 @@ config PPC44x_SIMPLE config PPC4xx_GPIO bool "PPC4xx GPIO support" depends on 44x - select ARCH_REQUIRE_GPIOLIB + select GPIOLIB help Enable gpiolib support for ppc440 based boards diff --git a/arch/powerpc/platforms/512x/Kconfig b/arch/powerpc/platforms/512x/Kconfig index f09016f6b3a6..bf7ae5cbd07a 100644 --- a/arch/powerpc/platforms/512x/Kconfig +++ b/arch/powerpc/platforms/512x/Kconfig @@ -6,7 +6,6 @@ config PPC_MPC512x select IPIC select PPC_PCI_CHOICE select FSL_PCI if PCI - select ARCH_WANT_OPTIONAL_GPIOLIB select USB_EHCI_BIG_ENDIAN_MMIO if USB_EHCI_HCD select USB_EHCI_BIG_ENDIAN_DESC if USB_EHCI_HCD diff --git a/arch/powerpc/platforms/512x/clock-commonclk.c b/arch/powerpc/platforms/512x/clock-commonclk.c index c50ea76ba66c..6081fbd75330 100644 --- a/arch/powerpc/platforms/512x/clock-commonclk.c +++ b/arch/powerpc/platforms/512x/clock-commonclk.c @@ -221,7 +221,7 @@ static bool soc_has_mclk_mux0_canin(void) /* convenience wrappers around the common clk API */ static inline struct clk *mpc512x_clk_fixed(const char *name, int rate) { - return clk_register_fixed_rate(NULL, name, NULL, CLK_IS_ROOT, rate); + return clk_register_fixed_rate(NULL, name, NULL, 0, rate); } static inline struct clk *mpc512x_clk_factor( diff --git a/arch/powerpc/platforms/83xx/Kconfig b/arch/powerpc/platforms/83xx/Kconfig index 2bdc8c862c46..4ef7f1cd05b7 100644 --- a/arch/powerpc/platforms/83xx/Kconfig +++ b/arch/powerpc/platforms/83xx/Kconfig @@ -116,7 +116,6 @@ endif # used for usb & gpio config PPC_MPC831x bool - select ARCH_WANT_OPTIONAL_GPIOLIB # used for math-emu config PPC_MPC832x @@ -125,9 +124,7 @@ config PPC_MPC832x # used for usb & gpio config PPC_MPC834x bool - select ARCH_WANT_OPTIONAL_GPIOLIB # used for usb & gpio config PPC_MPC837x bool - select ARCH_WANT_OPTIONAL_GPIOLIB diff --git a/arch/powerpc/platforms/85xx/Kconfig b/arch/powerpc/platforms/85xx/Kconfig index e626461a63bd..df25a3ed489d 100644 --- a/arch/powerpc/platforms/85xx/Kconfig +++ b/arch/powerpc/platforms/85xx/Kconfig @@ -225,7 +225,7 @@ config GE_IMP3A select DEFAULT_UIMAGE select SWIOTLB select MMIO_NVRAM - select ARCH_REQUIRE_GPIOLIB + select GPIOLIB select GE_FPGA help This option enables support for the GE Intelligent Platforms IMP3A @@ -272,7 +272,7 @@ config CORENET_GENERIC select PPC_E500MC select PHYS_64BIT select SWIOTLB - select ARCH_REQUIRE_GPIOLIB + select GPIOLIB select GPIO_MPC8XXX select HAS_RAPIDIO select PPC_EPAPR_HV_PIC diff --git a/arch/powerpc/platforms/86xx/Kconfig b/arch/powerpc/platforms/86xx/Kconfig index 1afd1e4a2dd2..3988f16e46c1 100644 --- a/arch/powerpc/platforms/86xx/Kconfig +++ b/arch/powerpc/platforms/86xx/Kconfig @@ -4,7 +4,6 @@ menuconfig PPC_86xx depends on 6xx select FSL_SOC select ALTIVEC - select ARCH_WANT_OPTIONAL_GPIOLIB help The Freescale E600 SoCs have 74xx cores. @@ -37,7 +36,7 @@ config GEF_PPC9A bool "GE PPC9A" select DEFAULT_UIMAGE select MMIO_NVRAM - select ARCH_REQUIRE_GPIOLIB + select GPIOLIB select GE_FPGA help This option enables support for the GE PPC9A. @@ -46,7 +45,7 @@ config GEF_SBC310 bool "GE SBC310" select DEFAULT_UIMAGE select MMIO_NVRAM - select ARCH_REQUIRE_GPIOLIB + select GPIOLIB select GE_FPGA help This option enables support for the GE SBC310. @@ -55,7 +54,7 @@ config GEF_SBC610 bool "GE SBC610" select DEFAULT_UIMAGE select MMIO_NVRAM - select ARCH_REQUIRE_GPIOLIB + select GPIOLIB select GE_FPGA select HAS_RAPIDIO help diff --git a/arch/powerpc/platforms/8xx/Kconfig b/arch/powerpc/platforms/8xx/Kconfig index 157250426b56..564d99bb2a26 100644 --- a/arch/powerpc/platforms/8xx/Kconfig +++ b/arch/powerpc/platforms/8xx/Kconfig @@ -109,7 +109,7 @@ config 8xx_COPYBACK config 8xx_GPIO bool "GPIO API Support" - select ARCH_REQUIRE_GPIOLIB + select GPIOLIB help Saying Y here will cause the ports on an MPC8xx processor to be used with the GPIO API. If you say N here, the kernel needs less memory. diff --git a/arch/powerpc/platforms/Kconfig b/arch/powerpc/platforms/Kconfig index 46a3533d3acb..3663f71fd913 100644 --- a/arch/powerpc/platforms/Kconfig +++ b/arch/powerpc/platforms/Kconfig @@ -275,7 +275,7 @@ config TAU_AVERAGE config QE_GPIO bool "QE GPIO support" depends on QUICC_ENGINE - select ARCH_REQUIRE_GPIOLIB + select GPIOLIB help Say Y here if you're going to use hardware that connects to the QE GPIOs. @@ -285,7 +285,7 @@ config CPM2 depends on (FSL_SOC_BOOKE && PPC32) || 8260 select CPM select PPC_PCI_CHOICE - select ARCH_REQUIRE_GPIOLIB + select GPIOLIB help The CPM2 (Communications Processor Module) is a coprocessor on embedded CPUs made by Freescale. Selecting this option means that @@ -324,7 +324,7 @@ config OF_RTC config SIMPLE_GPIO bool "Support for simple, memory-mapped GPIO controllers" depends on PPC - select ARCH_REQUIRE_GPIOLIB + select GPIOLIB help Say Y here to support simple, memory-mapped GPIO controllers. These are usually BCSRs used to control board's switches, LEDs, @@ -334,7 +334,7 @@ config SIMPLE_GPIO config MCU_MPC8349EMITX bool "MPC8349E-mITX MCU driver" depends on I2C=y && PPC_83xx - select ARCH_REQUIRE_GPIOLIB + select GPIOLIB help Say Y here to enable soft power-off functionality on the Freescale boards with the MPC8349E-mITX-compatible MCU chips. This driver will diff --git a/arch/powerpc/platforms/cell/cpufreq_spudemand.c b/arch/powerpc/platforms/cell/cpufreq_spudemand.c index 82607d621aca..88301e53f085 100644 --- a/arch/powerpc/platforms/cell/cpufreq_spudemand.c +++ b/arch/powerpc/platforms/cell/cpufreq_spudemand.c @@ -85,61 +85,57 @@ static void spu_gov_cancel_work(struct spu_gov_info_struct *info) cancel_delayed_work_sync(&info->work); } -static int spu_gov_govern(struct cpufreq_policy *policy, unsigned int event) +static int spu_gov_start(struct cpufreq_policy *policy) { unsigned int cpu = policy->cpu; - struct spu_gov_info_struct *info, *affected_info; + struct spu_gov_info_struct *info = &per_cpu(spu_gov_info, cpu); + struct spu_gov_info_struct *affected_info; int i; - int ret = 0; - info = &per_cpu(spu_gov_info, cpu); - - switch (event) { - case CPUFREQ_GOV_START: - if (!cpu_online(cpu)) { - printk(KERN_ERR "cpu %d is not online\n", cpu); - ret = -EINVAL; - break; - } + if (!cpu_online(cpu)) { + printk(KERN_ERR "cpu %d is not online\n", cpu); + return -EINVAL; + } - if (!policy->cur) { - printk(KERN_ERR "no cpu specified in policy\n"); - ret = -EINVAL; - break; - } + if (!policy->cur) { + printk(KERN_ERR "no cpu specified in policy\n"); + return -EINVAL; + } - /* initialize spu_gov_info for all affected cpus */ - for_each_cpu(i, policy->cpus) { - affected_info = &per_cpu(spu_gov_info, i); - affected_info->policy = policy; - } + /* initialize spu_gov_info for all affected cpus */ + for_each_cpu(i, policy->cpus) { + affected_info = &per_cpu(spu_gov_info, i); + affected_info->policy = policy; + } - info->poll_int = POLL_TIME; + info->poll_int = POLL_TIME; - /* setup timer */ - spu_gov_init_work(info); + /* setup timer */ + spu_gov_init_work(info); - break; + return 0; +} - case CPUFREQ_GOV_STOP: - /* cancel timer */ - spu_gov_cancel_work(info); +static void spu_gov_stop(struct cpufreq_policy *policy) +{ + unsigned int cpu = policy->cpu; + struct spu_gov_info_struct *info = &per_cpu(spu_gov_info, cpu); + int i; - /* clean spu_gov_info for all affected cpus */ - for_each_cpu (i, policy->cpus) { - info = &per_cpu(spu_gov_info, i); - info->policy = NULL; - } + /* cancel timer */ + spu_gov_cancel_work(info); - break; + /* clean spu_gov_info for all affected cpus */ + for_each_cpu (i, policy->cpus) { + info = &per_cpu(spu_gov_info, i); + info->policy = NULL; } - - return ret; } static struct cpufreq_governor spu_governor = { .name = "spudemand", - .governor = spu_gov_govern, + .start = spu_gov_start, + .stop = spu_gov_stop, .owner = THIS_MODULE, }; diff --git a/arch/powerpc/platforms/cell/spufs/coredump.c b/arch/powerpc/platforms/cell/spufs/coredump.c index 84fb984f29c1..85c85eb3e245 100644 --- a/arch/powerpc/platforms/cell/spufs/coredump.c +++ b/arch/powerpc/platforms/cell/spufs/coredump.c @@ -172,7 +172,7 @@ static int spufs_arch_write_note(struct spu_context *ctx, int i, if (rc < 0) goto out; - skip = roundup(cprm->file->f_pos - total + sz, 4) - cprm->file->f_pos; + skip = roundup(cprm->pos - total + sz, 4) - cprm->pos; if (!dump_skip(cprm, skip)) goto Eio; out: diff --git a/arch/powerpc/platforms/pseries/iommu.c b/arch/powerpc/platforms/pseries/iommu.c index b7dfc1359d01..3e8865b187de 100644 --- a/arch/powerpc/platforms/pseries/iommu.c +++ b/arch/powerpc/platforms/pseries/iommu.c @@ -927,7 +927,7 @@ static int query_ddw(struct pci_dev *dev, const u32 *ddw_avail, dn = pci_device_to_OF_node(dev); pdn = PCI_DN(dn); buid = pdn->phb->buid; - cfg_addr = (pdn->busno << 8) | pdn->devfn; + cfg_addr = ((pdn->busno << 16) | (pdn->devfn << 8)); ret = rtas_call(ddw_avail[0], 3, 5, (u32 *)query, cfg_addr, BUID_HI(buid), BUID_LO(buid)); @@ -956,7 +956,7 @@ static int create_ddw(struct pci_dev *dev, const u32 *ddw_avail, dn = pci_device_to_OF_node(dev); pdn = PCI_DN(dn); buid = pdn->phb->buid; - cfg_addr = (pdn->busno << 8) | pdn->devfn; + cfg_addr = ((pdn->busno << 16) | (pdn->devfn << 8)); do { /* extra outputs are LIOBN and dma-addr (hi, lo) */ diff --git a/arch/powerpc/sysdev/axonram.c b/arch/powerpc/sysdev/axonram.c index ff75d70f7285..9144204442eb 100644 --- a/arch/powerpc/sysdev/axonram.c +++ b/arch/powerpc/sysdev/axonram.c @@ -143,12 +143,12 @@ axon_ram_make_request(struct request_queue *queue, struct bio *bio) */ static long axon_ram_direct_access(struct block_device *device, sector_t sector, - void __pmem **kaddr, pfn_t *pfn, long size) + void **kaddr, pfn_t *pfn, long size) { struct axon_ram_bank *bank = device->bd_disk->private_data; loff_t offset = (loff_t)sector << AXON_RAM_SECTOR_SHIFT; - *kaddr = (void __pmem __force *) bank->io_addr + offset; + *kaddr = (void *) bank->io_addr + offset; *pfn = phys_to_pfn_t(bank->ph_addr + offset, PFN_DEV); return bank->size - offset; } @@ -223,7 +223,6 @@ static int axon_ram_probe(struct platform_device *device) bank->disk->first_minor = azfs_minor; bank->disk->fops = &axon_ram_devops; bank->disk->private_data = bank; - bank->disk->driverfs_dev = &device->dev; sprintf(bank->disk->disk_name, "%s%d", AXON_RAM_DEVICE_NAME, axon_ram_bank_id); @@ -238,7 +237,7 @@ static int axon_ram_probe(struct platform_device *device) set_capacity(bank->disk, bank->size >> AXON_RAM_SECTOR_SHIFT); blk_queue_make_request(bank->disk->queue, axon_ram_make_request); blk_queue_logical_block_size(bank->disk->queue, AXON_RAM_SECTOR_SIZE); - add_disk(bank->disk); + device_add_disk(&device->dev, bank->disk); bank->irq_id = irq_of_parse_and_map(device->dev.of_node, 0); if (bank->irq_id == NO_IRQ) { |