18c2ecf20Sopenharmony_ci// SPDX-License-Identifier: GPL-2.0-only 28c2ecf20Sopenharmony_ci/* 38c2ecf20Sopenharmony_ci * Copyright (C) 2012 Regents of the University of California 48c2ecf20Sopenharmony_ci */ 58c2ecf20Sopenharmony_ci 68c2ecf20Sopenharmony_ci#include <linux/delay.h> 78c2ecf20Sopenharmony_ci#include <linux/param.h> 88c2ecf20Sopenharmony_ci#include <linux/timex.h> 98c2ecf20Sopenharmony_ci#include <linux/export.h> 108c2ecf20Sopenharmony_ci 118c2ecf20Sopenharmony_ci/* 128c2ecf20Sopenharmony_ci * This is copies from arch/arm/include/asm/delay.h 138c2ecf20Sopenharmony_ci * 148c2ecf20Sopenharmony_ci * Loop (or tick) based delay: 158c2ecf20Sopenharmony_ci * 168c2ecf20Sopenharmony_ci * loops = loops_per_jiffy * jiffies_per_sec * delay_us / us_per_sec 178c2ecf20Sopenharmony_ci * 188c2ecf20Sopenharmony_ci * where: 198c2ecf20Sopenharmony_ci * 208c2ecf20Sopenharmony_ci * jiffies_per_sec = HZ 218c2ecf20Sopenharmony_ci * us_per_sec = 1000000 228c2ecf20Sopenharmony_ci * 238c2ecf20Sopenharmony_ci * Therefore the constant part is HZ / 1000000 which is a small 248c2ecf20Sopenharmony_ci * fractional number. To make this usable with integer math, we 258c2ecf20Sopenharmony_ci * scale up this constant by 2^31, perform the actual multiplication, 268c2ecf20Sopenharmony_ci * and scale the result back down by 2^31 with a simple shift: 278c2ecf20Sopenharmony_ci * 288c2ecf20Sopenharmony_ci * loops = (loops_per_jiffy * delay_us * UDELAY_MULT) >> 31 298c2ecf20Sopenharmony_ci * 308c2ecf20Sopenharmony_ci * where: 318c2ecf20Sopenharmony_ci * 328c2ecf20Sopenharmony_ci * UDELAY_MULT = 2^31 * HZ / 1000000 338c2ecf20Sopenharmony_ci * = (2^31 / 1000000) * HZ 348c2ecf20Sopenharmony_ci * = 2147.483648 * HZ 358c2ecf20Sopenharmony_ci * = 2147 * HZ + 483648 * HZ / 1000000 368c2ecf20Sopenharmony_ci * 378c2ecf20Sopenharmony_ci * 31 is the biggest scale shift value that won't overflow 32 bits for 388c2ecf20Sopenharmony_ci * delay_us * UDELAY_MULT assuming HZ <= 1000 and delay_us <= 2000. 398c2ecf20Sopenharmony_ci */ 408c2ecf20Sopenharmony_ci#define MAX_UDELAY_US 2000 418c2ecf20Sopenharmony_ci#define MAX_UDELAY_HZ 1000 428c2ecf20Sopenharmony_ci#define UDELAY_MULT (2147UL * HZ + 483648UL * HZ / 1000000UL) 438c2ecf20Sopenharmony_ci#define UDELAY_SHIFT 31 448c2ecf20Sopenharmony_ci 458c2ecf20Sopenharmony_ci#if HZ > MAX_UDELAY_HZ 468c2ecf20Sopenharmony_ci#error "HZ > MAX_UDELAY_HZ" 478c2ecf20Sopenharmony_ci#endif 488c2ecf20Sopenharmony_ci 498c2ecf20Sopenharmony_ci/* 508c2ecf20Sopenharmony_ci * RISC-V supports both UDELAY and NDELAY. This is largely the same as above, 518c2ecf20Sopenharmony_ci * but with different constants. I added 10 bits to the shift to get this, but 528c2ecf20Sopenharmony_ci * the result is that I need a 64-bit multiply, which is slow on 32-bit 538c2ecf20Sopenharmony_ci * platforms. 548c2ecf20Sopenharmony_ci * 558c2ecf20Sopenharmony_ci * NDELAY_MULT = 2^41 * HZ / 1000000000 568c2ecf20Sopenharmony_ci * = (2^41 / 1000000000) * HZ 578c2ecf20Sopenharmony_ci * = 2199.02325555 * HZ 588c2ecf20Sopenharmony_ci * = 2199 * HZ + 23255550 * HZ / 1000000000 598c2ecf20Sopenharmony_ci * 608c2ecf20Sopenharmony_ci * The maximum here is to avoid 64-bit overflow, but it isn't checked as it 618c2ecf20Sopenharmony_ci * won't happen. 628c2ecf20Sopenharmony_ci */ 638c2ecf20Sopenharmony_ci#define MAX_NDELAY_NS (1ULL << 42) 648c2ecf20Sopenharmony_ci#define MAX_NDELAY_HZ MAX_UDELAY_HZ 658c2ecf20Sopenharmony_ci#define NDELAY_MULT ((unsigned long long)(2199ULL * HZ + 23255550ULL * HZ / 1000000000ULL)) 668c2ecf20Sopenharmony_ci#define NDELAY_SHIFT 41 678c2ecf20Sopenharmony_ci 688c2ecf20Sopenharmony_ci#if HZ > MAX_NDELAY_HZ 698c2ecf20Sopenharmony_ci#error "HZ > MAX_NDELAY_HZ" 708c2ecf20Sopenharmony_ci#endif 718c2ecf20Sopenharmony_ci 728c2ecf20Sopenharmony_civoid __delay(unsigned long cycles) 738c2ecf20Sopenharmony_ci{ 748c2ecf20Sopenharmony_ci u64 t0 = get_cycles(); 758c2ecf20Sopenharmony_ci 768c2ecf20Sopenharmony_ci while ((unsigned long)(get_cycles() - t0) < cycles) 778c2ecf20Sopenharmony_ci cpu_relax(); 788c2ecf20Sopenharmony_ci} 798c2ecf20Sopenharmony_ciEXPORT_SYMBOL(__delay); 808c2ecf20Sopenharmony_ci 818c2ecf20Sopenharmony_civoid udelay(unsigned long usecs) 828c2ecf20Sopenharmony_ci{ 838c2ecf20Sopenharmony_ci u64 ucycles = (u64)usecs * lpj_fine * UDELAY_MULT; 848c2ecf20Sopenharmony_ci u64 n; 858c2ecf20Sopenharmony_ci 868c2ecf20Sopenharmony_ci if (unlikely(usecs > MAX_UDELAY_US)) { 878c2ecf20Sopenharmony_ci n = (u64)usecs * riscv_timebase; 888c2ecf20Sopenharmony_ci do_div(n, 1000000); 898c2ecf20Sopenharmony_ci 908c2ecf20Sopenharmony_ci __delay(n); 918c2ecf20Sopenharmony_ci return; 928c2ecf20Sopenharmony_ci } 938c2ecf20Sopenharmony_ci 948c2ecf20Sopenharmony_ci __delay(ucycles >> UDELAY_SHIFT); 958c2ecf20Sopenharmony_ci} 968c2ecf20Sopenharmony_ciEXPORT_SYMBOL(udelay); 978c2ecf20Sopenharmony_ci 988c2ecf20Sopenharmony_civoid ndelay(unsigned long nsecs) 998c2ecf20Sopenharmony_ci{ 1008c2ecf20Sopenharmony_ci /* 1018c2ecf20Sopenharmony_ci * This doesn't bother checking for overflow, as it won't happen (it's 1028c2ecf20Sopenharmony_ci * an hour) of delay. 1038c2ecf20Sopenharmony_ci */ 1048c2ecf20Sopenharmony_ci unsigned long long ncycles = nsecs * lpj_fine * NDELAY_MULT; 1058c2ecf20Sopenharmony_ci __delay(ncycles >> NDELAY_SHIFT); 1068c2ecf20Sopenharmony_ci} 1078c2ecf20Sopenharmony_ciEXPORT_SYMBOL(ndelay); 108