/* ----------------------------------------------------------------------- * * neon.uc - RAID-6 syndrome calculation using ARM NEON instructions * * Copyright (C) 2012 Rob Herring * Copyright (C) 2015 Linaro Ltd. * * 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 * * $#-way unrolled NEON intrinsics math RAID-6 instruction set * * This file is postprocessed using unroll.awk */ #include typedef uint8x16_t unative_t; #define NBYTES(x) ((unative_t){x,x,x,x, x,x,x,x, x,x,x,x, x,x,x,x}) #define NSIZE sizeof(unative_t) /* * The SHLBYTE() operation shifts each byte left by 1, *not* * rolling over into the next byte */ static inline unative_t SHLBYTE(unative_t v) { return vshlq_n_u8(v, 1); } /* * The MASK() operation returns 0xFF in any byte for which the high * bit is 1, 0x00 for any byte for which the high bit is 0. */ static inline unative_t MASK(unative_t v) { const uint8x16_t temp = NBYTES(0); return (unative_t)vcltq_s8((int8x16_t)v, (int8x16_t)temp); } void raid6_neon$#_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$$); } } void raid6_neon$#_xor_syndrome_real(int disks, int start, int stop, unsigned long bytes, void **ptrs) { uint8_t **dptr = (uint8_t **)ptrs; uint8_t *p, *q; int d, z, z0; register unative_t wd$$, wq$$, wp$$, w1$$, w2$$; const unative_t x1d = NBYTES(0x1d); z0 = stop; /* P/Q right side optimization */ p = dptr[disks-2]; /* XOR parity */ q = dptr[disks-1]; /* RS syndrome */ for ( d = 0 ; d < bytes ; d += NSIZE*$# ) { wq$$ = vld1q_u8(&dptr[z0][d+$$*NSIZE]); wp$$ = veorq_u8(vld1q_u8(&p[d+$$*NSIZE]), wq$$); /* P/Q data pages */ for ( z = z0-1 ; z >= start ; z-- ) { wd$$ = 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$$, wd$$); } /* P/Q left side optimization */ for ( z = start-1 ; z >= 0 ; z-- ) { w2$$ = MASK(wq$$); w1$$ = SHLBYTE(wq$$); w2$$ = vandq_u8(w2$$, x1d); wq$$ = veorq_u8(w1$$, w2$$); } w1$$ = vld1q_u8(&q[d+NSIZE*$$]); wq$$ = veorq_u8(wq$$, w1$$); vst1q_u8(&p[d+NSIZE*$$], wp$$); vst1q_u8(&q[d+NSIZE*$$], wq$$); } } af14e67e8b8702b5560aa64c888c0cd0bd66c'/>
context:
space:
mode:
authorLinus Torvalds <torvalds@linux-foundation.org>2017-01-24 16:54:39 -0800
committerLinus Torvalds <torvalds@linux-foundation.org>2017-01-24 16:54:39 -0800
commit883af14e67e8b8702b5560aa64c888c0cd0bd66c (patch)
tree74e3a6b53f5fad9f7848ab1b9f6921b7012940a4 /drivers/usb/musb/musb_gadget_ep0.c
parent0263d4ebd94b36280608e296cba39b924b6e832b (diff)
parentaab45453ff5c77200c6da4ac909f7a4392aed17e (diff)
Merge branch 'akpm' (patches from Andrew)
Merge fixes from Andrew Morton: "26 fixes" * emailed patches from Andrew Morton <akpm@linux-foundation.org>: (26 commits) MAINTAINERS: add Dan Streetman to zbud maintainers MAINTAINERS: add Dan Streetman to zswap maintainers mm: do not export ioremap_page_range symbol for external module mn10300: fix build error of missing fpu_save() romfs: use different way to generate fsid for BLOCK or MTD frv: add missing atomic64 operations mm, page_alloc: fix premature OOM when racing with cpuset mems update mm, page_alloc: move cpuset seqcount checking to slowpath mm, page_alloc: fix fast-path race with cpuset update or removal mm, page_alloc: fix check for NULL preferred_zone kernel/panic.c: add missing \n fbdev: color map copying bounds checking frv: add atomic64_add_unless() mm/mempolicy.c: do not put mempolicy before using its nodemask radix-tree: fix private list warnings Documentation/filesystems/proc.txt: add VmPin mm, memcg: do not retry precharge charges proc: add a schedule point in proc_pid_readdir() mm: alloc_contig: re-allow CMA to compact FS pages mm/slub.c: trace free objects at KERN_INFO ...
Diffstat (limited to 'drivers/usb/musb/musb_gadget_ep0.c')