diff options
Diffstat (limited to 'lib')
| -rw-r--r-- | lib/Kconfig | 2 | ||||
| -rw-r--r-- | lib/crc-t10dif.c | 73 | ||||
| -rw-r--r-- | lib/lz4/lz4_compress.c | 4 | ||||
| -rw-r--r-- | lib/lz4/lz4_decompress.c | 6 | ||||
| -rw-r--r-- | lib/lz4/lz4hc_compress.c | 4 | ||||
| -rw-r--r-- | lib/mpi/longlong.h | 17 | ||||
| -rw-r--r-- | lib/raid6/.gitignore | 1 | ||||
| -rw-r--r-- | lib/raid6/Makefile | 40 | ||||
| -rw-r--r-- | lib/raid6/algos.c | 6 | ||||
| -rw-r--r-- | lib/raid6/neon.c | 58 | ||||
| -rw-r--r-- | lib/raid6/neon.uc | 80 | ||||
| -rw-r--r-- | lib/raid6/test/Makefile | 26 |
12 files changed, 267 insertions, 50 deletions
diff --git a/lib/Kconfig b/lib/Kconfig index 35da513..71d9f81 100644 --- a/lib/Kconfig +++ b/lib/Kconfig @@ -66,8 +66,6 @@ config CRC16 config CRC_T10DIF tristate "CRC calculation for the T10 Data Integrity Field" - select CRYPTO - select CRYPTO_CRCT10DIF help This option is only needed if a module that's not in the kernel tree needs to calculate CRC checks for use with the diff --git a/lib/crc-t10dif.c b/lib/crc-t10dif.c index fe3428c..fbbd66e 100644 --- a/lib/crc-t10dif.c +++ b/lib/crc-t10dif.c @@ -11,44 +11,57 @@ #include <linux/types.h> #include <linux/module.h> #include <linux/crc-t10dif.h> -#include <linux/err.h> -#include <linux/init.h> -#include <crypto/hash.h> -static struct crypto_shash *crct10dif_tfm; +/* Table generated using the following polynomium: + * x^16 + x^15 + x^11 + x^9 + x^8 + x^7 + x^5 + x^4 + x^2 + x + 1 + * gt: 0x8bb7 + */ +static const __u16 t10_dif_crc_table[256] = { + 0x0000, 0x8BB7, 0x9CD9, 0x176E, 0xB205, 0x39B2, 0x2EDC, 0xA56B, + 0xEFBD, 0x640A, 0x7364, 0xF8D3, 0x5DB8, 0xD60F, 0xC161, 0x4AD6, + 0x54CD, 0xDF7A, 0xC814, 0x43A3, 0xE6C8, 0x6D7F, 0x7A11, 0xF1A6, + 0xBB70, 0x30C7, 0x27A9, 0xAC1E, 0x0975, 0x82C2, 0x95AC, 0x1E1B, + 0xA99A, 0x222D, 0x3543, 0xBEF4, 0x1B9F, 0x9028, 0x8746, 0x0CF1, + 0x4627, 0xCD90, 0xDAFE, 0x5149, 0xF422, 0x7F95, 0x68FB, 0xE34C, + 0xFD57, 0x76E0, 0x618E, 0xEA39, 0x4F52, 0xC4E5, 0xD38B, 0x583C, + 0x12EA, 0x995D, 0x8E33, 0x0584, 0xA0EF, 0x2B58, 0x3C36, 0xB781, + 0xD883, 0x5334, 0x445A, 0xCFED, 0x6A86, 0xE131, 0xF65F, 0x7DE8, + 0x373E, 0xBC89, 0xABE7, 0x2050, 0x853B, 0x0E8C, 0x19E2, 0x9255, + 0x8C4E, 0x07F9, 0x1097, 0x9B20, 0x3E4B, 0xB5FC, 0xA292, 0x2925, + 0x63F3, 0xE844, 0xFF2A, 0x749D, 0xD1F6, 0x5A41, 0x4D2F, 0xC698, + 0x7119, 0xFAAE, 0xEDC0, 0x6677, 0xC31C, 0x48AB, 0x5FC5, 0xD472, + 0x9EA4, 0x1513, 0x027D, 0x89CA, 0x2CA1, 0xA716, 0xB078, 0x3BCF, + 0x25D4, 0xAE63, 0xB90D, 0x32BA, 0x97D1, 0x1C66, 0x0B08, 0x80BF, + 0xCA69, 0x41DE, 0x56B0, 0xDD07, 0x786C, 0xF3DB, 0xE4B5, 0x6F02, + 0x3AB1, 0xB106, 0xA668, 0x2DDF, 0x88B4, 0x0303, 0x146D, 0x9FDA, + 0xD50C, 0x5EBB, 0x49D5, 0xC262, 0x6709, 0xECBE, 0xFBD0, 0x7067, + 0x6E7C, 0xE5CB, 0xF2A5, 0x7912, 0xDC79, 0x57CE, 0x40A0, 0xCB17, + 0x81C1, 0x0A76, 0x1D18, 0x96AF, 0x33C4, 0xB873, 0xAF1D, 0x24AA, + 0x932B, 0x189C, 0x0FF2, 0x8445, 0x212E, 0xAA99, 0xBDF7, 0x3640, + 0x7C96, 0xF721, 0xE04F, 0x6BF8, 0xCE93, 0x4524, 0x524A, 0xD9FD, + 0xC7E6, 0x4C51, 0x5B3F, 0xD088, 0x75E3, 0xFE54, 0xE93A, 0x628D, + 0x285B, 0xA3EC, 0xB482, 0x3F35, 0x9A5E, 0x11E9, 0x0687, 0x8D30, + 0xE232, 0x6985, 0x7EEB, 0xF55C, 0x5037, 0xDB80, 0xCCEE, 0x4759, + 0x0D8F, 0x8638, 0x9156, 0x1AE1, 0xBF8A, 0x343D, 0x2353, 0xA8E4, + 0xB6FF, 0x3D48, 0x2A26, 0xA191, 0x04FA, 0x8F4D, 0x9823, 0x1394, + 0x5942, 0xD2F5, 0xC59B, 0x4E2C, 0xEB47, 0x60F0, 0x779E, 0xFC29, + 0x4BA8, 0xC01F, 0xD771, 0x5CC6, 0xF9AD, 0x721A, 0x6574, 0xEEC3, + 0xA415, 0x2FA2, 0x38CC, 0xB37B, 0x1610, 0x9DA7, 0x8AC9, 0x017E, + 0x1F65, 0x94D2, 0x83BC, 0x080B, 0xAD60, 0x26D7, 0x31B9, 0xBA0E, + 0xF0D8, 0x7B6F, 0x6C01, 0xE7B6, 0x42DD, 0xC96A, 0xDE04, 0x55B3 +}; __u16 crc_t10dif(const unsigned char *buffer, size_t len) { - struct { - struct shash_desc shash; - char ctx[2]; - } desc; - int err; - - desc.shash.tfm = crct10dif_tfm; - desc.shash.flags = 0; - *(__u16 *)desc.ctx = 0; + __u16 crc = 0; + unsigned int i; - err = crypto_shash_update(&desc.shash, buffer, len); - BUG_ON(err); + for (i = 0 ; i < len ; i++) + crc = (crc << 8) ^ t10_dif_crc_table[((crc >> 8) ^ buffer[i]) & 0xff]; - return *(__u16 *)desc.ctx; + return crc; } EXPORT_SYMBOL(crc_t10dif); -static int __init crc_t10dif_mod_init(void) -{ - crct10dif_tfm = crypto_alloc_shash("crct10dif", 0, 0); - return PTR_RET(crct10dif_tfm); -} - -static void __exit crc_t10dif_mod_fini(void) -{ - crypto_free_shash(crct10dif_tfm); -} - -module_init(crc_t10dif_mod_init); -module_exit(crc_t10dif_mod_fini); - MODULE_DESCRIPTION("T10 DIF CRC calculation"); MODULE_LICENSE("GPL"); diff --git a/lib/lz4/lz4_compress.c b/lib/lz4/lz4_compress.c index fd94058..28321d8 100644 --- a/lib/lz4/lz4_compress.c +++ b/lib/lz4/lz4_compress.c @@ -437,7 +437,7 @@ int lz4_compress(const unsigned char *src, size_t src_len, exit: return ret; } -EXPORT_SYMBOL_GPL(lz4_compress); +EXPORT_SYMBOL(lz4_compress); -MODULE_LICENSE("GPL"); +MODULE_LICENSE("Dual BSD/GPL"); MODULE_DESCRIPTION("LZ4 compressor"); diff --git a/lib/lz4/lz4_decompress.c b/lib/lz4/lz4_decompress.c index d3414ea..411be80 100644 --- a/lib/lz4/lz4_decompress.c +++ b/lib/lz4/lz4_decompress.c @@ -299,7 +299,7 @@ exit_0: return ret; } #ifndef STATIC -EXPORT_SYMBOL_GPL(lz4_decompress); +EXPORT_SYMBOL(lz4_decompress); #endif int lz4_decompress_unknownoutputsize(const char *src, size_t src_len, @@ -319,8 +319,8 @@ exit_0: return ret; } #ifndef STATIC -EXPORT_SYMBOL_GPL(lz4_decompress_unknownoutputsize); +EXPORT_SYMBOL(lz4_decompress_unknownoutputsize); -MODULE_LICENSE("GPL"); +MODULE_LICENSE("Dual BSD/GPL"); MODULE_DESCRIPTION("LZ4 Decompressor"); #endif diff --git a/lib/lz4/lz4hc_compress.c b/lib/lz4/lz4hc_compress.c index eb1a74f..f344f76 100644 --- a/lib/lz4/lz4hc_compress.c +++ b/lib/lz4/lz4hc_compress.c @@ -533,7 +533,7 @@ int lz4hc_compress(const unsigned char *src, size_t src_len, exit: return ret; } -EXPORT_SYMBOL_GPL(lz4hc_compress); +EXPORT_SYMBOL(lz4hc_compress); -MODULE_LICENSE("GPL"); +MODULE_LICENSE("Dual BSD/GPL"); MODULE_DESCRIPTION("LZ4HC compressor"); diff --git a/lib/mpi/longlong.h b/lib/mpi/longlong.h index d411355..aac5114 100644 --- a/lib/mpi/longlong.h +++ b/lib/mpi/longlong.h @@ -151,15 +151,12 @@ do { \ #endif /* __a29k__ */ #if defined(__alpha) && W_TYPE_SIZE == 64 -#define umul_ppmm(ph, pl, m0, m1) \ -do { \ - UDItype __m0 = (m0), __m1 = (m1); \ - __asm__ ("umulh %r1,%2,%0" \ - : "=r" ((UDItype) ph) \ - : "%rJ" (__m0), \ - "rI" (__m1)); \ - (pl) = __m0 * __m1; \ - } while (0) +#define umul_ppmm(ph, pl, m0, m1) \ +do { \ + UDItype __m0 = (m0), __m1 = (m1); \ + (ph) = __builtin_alpha_umulh(__m0, __m1); \ + (pl) = __m0 * __m1; \ +} while (0) #define UMUL_TIME 46 #ifndef LONGLONG_STANDALONE #define udiv_qrnnd(q, r, n1, n0, d) \ @@ -167,7 +164,7 @@ do { UDItype __r; \ (q) = __udiv_qrnnd(&__r, (n1), (n0), (d)); \ (r) = __r; \ } while (0) -extern UDItype __udiv_qrnnd(); +extern UDItype __udiv_qrnnd(UDItype *, UDItype, UDItype, UDItype); #define UDIV_TIME 220 #endif /* LONGLONG_STANDALONE */ #endif /* __alpha */ diff --git a/lib/raid6/.gitignore b/lib/raid6/.gitignore index 162beca..0a7e494 100644 --- a/lib/raid6/.gitignore +++ b/lib/raid6/.gitignore @@ -2,3 +2,4 @@ mktables altivec*.c int*.c tables.c +neon?.c diff --git a/lib/raid6/Makefile b/lib/raid6/Makefile index 9f7c184..b462578 100644 --- a/lib/raid6/Makefile +++ b/lib/raid6/Makefile @@ -5,6 +5,7 @@ raid6_pq-y += algos.o recov.o tables.o int1.o int2.o int4.o \ raid6_pq-$(CONFIG_X86) += recov_ssse3.o recov_avx2.o mmx.o sse1.o sse2.o avx2.o raid6_pq-$(CONFIG_ALTIVEC) += altivec1.o altivec2.o altivec4.o altivec8.o +raid6_pq-$(CONFIG_KERNEL_MODE_NEON) += neon.o neon1.o neon2.o neon4.o neon8.o hostprogs-y += mktables @@ -16,6 +17,21 @@ ifeq ($(CONFIG_ALTIVEC),y) altivec_flags := -maltivec -mabi=altivec endif +# The GCC option -ffreestanding is required in order to compile code containing +# ARM/NEON intrinsics in a non C99-compliant environment (such as the kernel) +ifeq ($(CONFIG_KERNEL_MODE_NEON),y) +NEON_FLAGS := -ffreestanding +ifeq ($(ARCH),arm) +NEON_FLAGS += -mfloat-abi=softfp -mfpu=neon +endif +ifeq ($(ARCH),arm64) +CFLAGS_REMOVE_neon1.o += -mgeneral-regs-only +CFLAGS_REMOVE_neon2.o += -mgeneral-regs-only +CFLAGS_REMOVE_neon4.o += -mgeneral-regs-only +CFLAGS_REMOVE_neon8.o += -mgeneral-regs-only +endif +endif + targets += int1.c $(obj)/int1.c: UNROLL := 1 $(obj)/int1.c: $(src)/int.uc $(src)/unroll.awk FORCE @@ -70,6 +86,30 @@ $(obj)/altivec8.c: UNROLL := 8 $(obj)/altivec8.c: $(src)/altivec.uc $(src)/unroll.awk FORCE $(call if_changed,unroll) +CFLAGS_neon1.o += $(NEON_FLAGS) +targets += neon1.c +$(obj)/neon1.c: UNROLL := 1 +$(obj)/neon1.c: $(src)/neon.uc $(src)/unroll.awk FORCE + $(call if_changed,unroll) + +CFLAGS_neon2.o += $(NEON_FLAGS) +targets += neon2.c +$(obj)/neon2.c: UNROLL := 2 +$(obj)/neon2.c: $(src)/neon.uc $(src)/unroll.awk FORCE + $(call if_changed,unroll) + +CFLAGS_neon4.o += $(NEON_FLAGS) +targets += neon4.c +$(obj)/neon4.c: UNROLL := 4 +$(obj)/neon4.c: $(src)/neon.uc $(src)/unroll.awk FORCE + $(call if_changed,unroll) + +CFLAGS_neon8.o += $(NEON_FLAGS) +targets += neon8.c +$(obj)/neon8.c: UNROLL := 8 +$(obj)/neon8.c: $(src)/neon.uc $(src)/unroll.awk FORCE + $(call if_changed,unroll) + quiet_cmd_mktable = TABLE $@ cmd_mktable = $(obj)/mktables > $@ || ( rm -f $@ && exit 1 ) diff --git a/lib/raid6/algos.c b/lib/raid6/algos.c index 6d7316f..74e6f56 100644 --- a/lib/raid6/algos.c +++ b/lib/raid6/algos.c @@ -70,6 +70,12 @@ const struct raid6_calls * const raid6_algos[] = { &raid6_intx2, &raid6_intx4, &raid6_intx8, +#ifdef CONFIG_KERNEL_MODE_NEON + &raid6_neonx1, + &raid6_neonx2, + &raid6_neonx4, + &raid6_neonx8, +#endif NULL }; diff --git a/lib/raid6/neon.c b/lib/raid6/neon.c new file mode 100644 index 0000000..36ad470 --- /dev/null +++ b/lib/raid6/neon.c @@ -0,0 +1,58 @@ +/* + * linux/lib/raid6/neon.c - RAID6 syndrome calculation using ARM NEON intrinsics + * + * Copyright (C) 2013 Linaro Ltd <ard.biesheuvel@linaro.org> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +#include <linux/raid/pq.h> + +#ifdef __KERNEL__ +#include <asm/neon.h> +#else +#define kernel_neon_begin() +#define kernel_neon_end() +#define cpu_has_neon() (1) +#endif + +/* + * There are 2 reasons these wrappers are kept in a separate compilation unit + * from the actual implementations in neonN.c (generated from neon.uc by + * unroll.awk): + * - the actual implementations use NEON intrinsics, and the GCC support header + * (arm_neon.h) is not fully compatible (type wise) with the kernel; + * - the neonN.c files are compiled with -mfpu=neon and optimization enabled, + * and we have to make sure that we never use *any* NEON/VFP instructions + * outside a kernel_neon_begin()/kernel_neon_end() pair. + */ + +#define RAID6_NEON_WRAPPER(_n) \ + static void raid6_neon ## _n ## _gen_syndrome(int disks, \ + size_t bytes, void **ptrs) \ + { \ + void raid6_neon ## _n ## _gen_syndrome_real(int, \ + unsigned long, void**); \ + kernel_neon_begin(); \ + raid6_neon ## _n ## _gen_syndrome_real(disks, \ + (unsigned long)bytes, ptrs); \ + kernel_neon_end(); \ + } \ + struct raid6_calls const raid6_neonx ## _n = { \ + raid6_neon ## _n ## _gen_syndrome, \ + raid6_have_neon, \ + "neonx" #_n, \ + 0 \ + } + +static int raid6_have_neon(void) +{ + return cpu_has_neon(); +} + +RAID6_NEON_WRAPPER(1); +RAID6_NEON_WRAPPER(2); +RAID6_NEON_WRAPPER(4); +RAID6_NEON_WRAPPER(8); diff --git a/lib/raid6/neon.uc b/lib/raid6/neon.uc new file mode 100644 index 0000000..1b9ed79 --- /dev/null +++ b/lib/raid6/neon.uc @@ -0,0 +1,80 @@ +/* ----------------------------------------------------------------------- + * + * neon.uc - RAID-6 syndrome calculation using ARM NEON instructions + * + * Copyright (C) 2012 Rob Herring + * + * Based on altivec.uc: + * Copyright 2002-2004 H. Peter Anvin - All Rights Reserved + * + * 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, Inc., 53 Temple Place Ste 330, + * Boston MA 02111-1307, USA; either version 2 of the License, or + * (at your option) any later version; incorporated herein by reference. + * + * ----------------------------------------------------------------------- */ + +/* + * neon$#.c + * + * $#-way unrolled NEON intrinsics math RAID-6 instruction set + * + * This file is postprocessed using unroll.awk + */ + +#include <arm_neon.h> + +typedef uint8x16_t unative_t; + +#define NBYTES(x) ((unative_t){x,x,x,x, x,x,x,x, x,x,x,x, x,x,x,x}) +#define NSIZE sizeof(unative_t) + +/* + * The SHLBYTE() operation shifts each byte left by 1, *not* + * rolling over into the next byte + */ +static inline unative_t SHLBYTE(unative_t v) +{ + return vshlq_n_u8(v, 1); +} + +/* + * The MASK() operation returns 0xFF in any byte for which the high + * bit is 1, 0x00 for any byte for which the high bit is 0. + */ +static inline unative_t MASK(unative_t v) +{ + const uint8x16_t temp = NBYTES(0); + return (unative_t)vcltq_s8((int8x16_t)v, (int8x16_t)temp); +} + +void raid6_neon$#_gen_syndrome_real(int disks, unsigned long bytes, void **ptrs) +{ + uint8_t **dptr = (uint8_t **)ptrs; + uint8_t *p, *q; + int d, z, z0; + + register unative_t wd$$, wq$$, wp$$, w1$$, w2$$; + const unative_t x1d = NBYTES(0x1d); + + z0 = disks - 3; /* Highest data disk */ + p = dptr[z0+1]; /* XOR parity */ + q = dptr[z0+2]; /* RS syndrome */ + + for ( d = 0 ; d < bytes ; d += NSIZE*$# ) { + wq$$ = wp$$ = vld1q_u8(&dptr[z0][d+$$*NSIZE]); + for ( z = z0-1 ; z >= 0 ; z-- ) { + wd$$ = vld1q_u8(&dptr[z][d+$$*NSIZE]); + wp$$ = veorq_u8(wp$$, wd$$); + w2$$ = MASK(wq$$); + w1$$ = SHLBYTE(wq$$); + + w2$$ = vandq_u8(w2$$, x1d); + w1$$ = veorq_u8(w1$$, w2$$); + wq$$ = veorq_u8(w1$$, wd$$); + } + vst1q_u8(&p[d+NSIZE*$$], wp$$); + vst1q_u8(&q[d+NSIZE*$$], wq$$); + } +} diff --git a/lib/raid6/test/Makefile b/lib/raid6/test/Makefile index 087332d..28afa1a 100644 --- a/lib/raid6/test/Makefile +++ b/lib/raid6/test/Makefile @@ -22,11 +22,23 @@ ifeq ($(ARCH),x86_64) IS_X86 = yes endif +ifeq ($(ARCH),arm) + CFLAGS += -I../../../arch/arm/include -mfpu=neon + HAS_NEON = yes +endif +ifeq ($(ARCH),arm64) + CFLAGS += -I../../../arch/arm64/include + HAS_NEON = yes +endif + ifeq ($(IS_X86),yes) OBJS += mmx.o sse1.o sse2.o avx2.o recov_ssse3.o recov_avx2.o CFLAGS += $(shell echo "vpbroadcastb %xmm0, %ymm1" | \ gcc -c -x assembler - >&/dev/null && \ rm ./-.o && echo -DCONFIG_AS_AVX2=1) +else ifeq ($(HAS_NEON),yes) + OBJS += neon.o neon1.o neon2.o neon4.o neon8.o + CFLAGS += -DCONFIG_KERNEL_MODE_NEON=1 else HAS_ALTIVEC := $(shell echo -e '\#include <altivec.h>\nvector int a;' |\ gcc -c -x c - >&/dev/null && \ @@ -55,6 +67,18 @@ raid6.a: $(OBJS) raid6test: test.c raid6.a $(CC) $(CFLAGS) -o raid6test $^ +neon1.c: neon.uc ../unroll.awk + $(AWK) ../unroll.awk -vN=1 < neon.uc > $@ + +neon2.c: neon.uc ../unroll.awk + $(AWK) ../unroll.awk -vN=2 < neon.uc > $@ + +neon4.c: neon.uc ../unroll.awk + $(AWK) ../unroll.awk -vN=4 < neon.uc > $@ + +neon8.c: neon.uc ../unroll.awk + $(AWK) ../unroll.awk -vN=8 < neon.uc > $@ + altivec1.c: altivec.uc ../unroll.awk $(AWK) ../unroll.awk -vN=1 < altivec.uc > $@ @@ -89,7 +113,7 @@ tables.c: mktables ./mktables > tables.c clean: - rm -f *.o *.a mktables mktables.c *.uc int*.c altivec*.c tables.c raid6test + rm -f *.o *.a mktables mktables.c *.uc int*.c altivec*.c neon*.c tables.c raid6test spotless: clean rm -f *~ |
