From ace9429bb58fd418f0c81d4c2835699bddf6bde6 Mon Sep 17 00:00:00 2001 From: Daniel Baumann Date: Thu, 11 Apr 2024 10:27:49 +0200 Subject: Adding upstream version 6.6.15. Signed-off-by: Daniel Baumann --- arch/hexagon/lib/checksum.c | 178 ++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 178 insertions(+) create mode 100644 arch/hexagon/lib/checksum.c (limited to 'arch/hexagon/lib/checksum.c') diff --git a/arch/hexagon/lib/checksum.c b/arch/hexagon/lib/checksum.c new file mode 100644 index 000000000..ba50822a0 --- /dev/null +++ b/arch/hexagon/lib/checksum.c @@ -0,0 +1,178 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Checksum functions for Hexagon + * + * Copyright (c) 2010-2011, The Linux Foundation. All rights reserved. + */ + +/* This was derived from arch/alpha/lib/checksum.c */ + + +#include +#include + +#include +#include +#include +#include + + +/* Vector value operations */ +#define SIGN(x, y) ((0x8000ULL*x)<> 32); + /* 33 to 32 */ + result = (result & 0xffffffffUL) + (result >> 32); + return (__force __wsum)result; +} +EXPORT_SYMBOL(csum_tcpudp_nofold); + +/* + * Do a 64-bit checksum on an arbitrary memory area.. + * + * This isn't a great routine, but it's not _horrible_ either. The + * inner loop could be unrolled a bit further, and there are better + * ways to do the carry, but this is reasonable. + */ + +/* optimized HEXAGON intrinsic version, with over read fixed */ +unsigned int do_csum(const void *voidptr, int len) +{ + u64 sum0, sum1, x0, x1, *ptr8_o, *ptr8_e, *ptr8; + int i, start, mid, end, mask; + const char *ptr = voidptr; + unsigned short *ptr2; + unsigned int *ptr4; + + if (len <= 0) + return 0; + + start = 0xF & (16-(((int) ptr) & 0xF)) ; + mask = 0x7fffffffUL >> HEXAGON_R_cl0_R(len); + start = start & mask ; + + mid = len - start; + end = mid & 0xF; + mid = mid>>4; + sum0 = mid << 18; + sum1 = 0; + + if (start & 1) + sum0 += (u64) (ptr[0] << 8); + ptr2 = (unsigned short *) &ptr[start & 1]; + if (start & 2) + sum1 += (u64) ptr2[0]; + ptr4 = (unsigned int *) &ptr[start & 3]; + if (start & 4) { + sum0 = HEXAGON_P_vrmpyhacc_PP(sum0, + VR_NEGATE(0, 0, 1, 1)^((u64)ptr4[0]), + VR_SELECT(0, 0, 1, 1)); + sum0 += VR_SELECT(0, 0, 1, 0); + } + ptr8 = (u64 *) &ptr[start & 7]; + if (start & 8) { + sum1 = HEXAGON_P_vrmpyhacc_PP(sum1, + VR_NEGATE(1, 1, 1, 1)^(ptr8[0]), + VR_SELECT(1, 1, 1, 1)); + sum1 += VR_CARRY(0, 0, 1, 0); + } + ptr8_o = (u64 *) (ptr + start); + ptr8_e = (u64 *) (ptr + start + 8); + + if (mid) { + x0 = *ptr8_e; ptr8_e += 2; + x1 = *ptr8_o; ptr8_o += 2; + if (mid > 1) + for (i = 0; i < mid-1; i++) { + sum0 = HEXAGON_P_vrmpyhacc_PP(sum0, + x0^VR_NEGATE(1, 1, 1, 1), + VR_SELECT(1, 1, 1, 1)); + sum1 = HEXAGON_P_vrmpyhacc_PP(sum1, + x1^VR_NEGATE(1, 1, 1, 1), + VR_SELECT(1, 1, 1, 1)); + x0 = *ptr8_e; ptr8_e += 2; + x1 = *ptr8_o; ptr8_o += 2; + } + sum0 = HEXAGON_P_vrmpyhacc_PP(sum0, x0^VR_NEGATE(1, 1, 1, 1), + VR_SELECT(1, 1, 1, 1)); + sum1 = HEXAGON_P_vrmpyhacc_PP(sum1, x1^VR_NEGATE(1, 1, 1, 1), + VR_SELECT(1, 1, 1, 1)); + } + + ptr4 = (unsigned int *) &ptr[start + (mid * 16) + (end & 8)]; + if (end & 4) { + sum1 = HEXAGON_P_vrmpyhacc_PP(sum1, + VR_NEGATE(0, 0, 1, 1)^((u64)ptr4[0]), + VR_SELECT(0, 0, 1, 1)); + sum1 += VR_SELECT(0, 0, 1, 0); + } + ptr2 = (unsigned short *) &ptr[start + (mid * 16) + (end & 12)]; + if (end & 2) + sum0 += (u64) ptr2[0]; + + if (end & 1) + sum1 += (u64) ptr[start + (mid * 16) + (end & 14)]; + + ptr8 = (u64 *) &ptr[start + (mid * 16)]; + if (end & 8) { + sum0 = HEXAGON_P_vrmpyhacc_PP(sum0, + VR_NEGATE(1, 1, 1, 1)^(ptr8[0]), + VR_SELECT(1, 1, 1, 1)); + sum0 += VR_CARRY(0, 0, 1, 0); + } + sum0 = HEXAGON_P_vrmpyh_PP((sum0+sum1)^VR_NEGATE(0, 0, 0, 1), + VR_SELECT(0, 0, 1, 1)); + sum0 += VR_NEGATE(0, 0, 0, 1); + sum0 = HEXAGON_P_vrmpyh_PP(sum0, VR_SELECT(0, 0, 1, 1)); + + if (start & 1) + sum0 = (sum0 << 8) | (0xFF & (sum0 >> 8)); + + return 0xFFFF & sum0; +} -- cgit v1.2.3