1/* SPDX-License-Identifier: GPL-2.0 */ 2#ifndef _ASM_IA64_SPINLOCK_H 3#define _ASM_IA64_SPINLOCK_H 4 5/* 6 * Copyright (C) 1998-2003 Hewlett-Packard Co 7 * David Mosberger-Tang <davidm@hpl.hp.com> 8 * Copyright (C) 1999 Walt Drummond <drummond@valinux.com> 9 * 10 * This file is used for SMP configurations only. 11 */ 12 13#include <linux/compiler.h> 14#include <linux/kernel.h> 15#include <linux/bitops.h> 16 17#include <linux/atomic.h> 18#include <asm/intrinsics.h> 19#include <asm/barrier.h> 20#include <asm/processor.h> 21 22#define arch_spin_lock_init(x) ((x)->lock = 0) 23 24/* 25 * Ticket locks are conceptually two parts, one indicating the current head of 26 * the queue, and the other indicating the current tail. The lock is acquired 27 * by atomically noting the tail and incrementing it by one (thus adding 28 * ourself to the queue and noting our position), then waiting until the head 29 * becomes equal to the the initial value of the tail. 30 * The pad bits in the middle are used to prevent the next_ticket number 31 * overflowing into the now_serving number. 32 * 33 * 31 17 16 15 14 0 34 * +----------------------------------------------------+ 35 * | now_serving | padding | next_ticket | 36 * +----------------------------------------------------+ 37 */ 38 39#define TICKET_SHIFT 17 40#define TICKET_BITS 15 41#define TICKET_MASK ((1 << TICKET_BITS) - 1) 42 43static __always_inline void __ticket_spin_lock(arch_spinlock_t *lock) 44{ 45 int *p = (int *)&lock->lock, ticket, serve; 46 47 ticket = ia64_fetchadd(1, p, acq); 48 49 if (!(((ticket >> TICKET_SHIFT) ^ ticket) & TICKET_MASK)) 50 return; 51 52 ia64_invala(); 53 54 for (;;) { 55 asm volatile ("ld4.c.nc %0=[%1]" : "=r"(serve) : "r"(p) : "memory"); 56 57 if (!(((serve >> TICKET_SHIFT) ^ ticket) & TICKET_MASK)) 58 return; 59 cpu_relax(); 60 } 61} 62 63static __always_inline int __ticket_spin_trylock(arch_spinlock_t *lock) 64{ 65 int tmp = READ_ONCE(lock->lock); 66 67 if (!(((tmp >> TICKET_SHIFT) ^ tmp) & TICKET_MASK)) 68 return ia64_cmpxchg(acq, &lock->lock, tmp, tmp + 1, sizeof (tmp)) == tmp; 69 return 0; 70} 71 72static __always_inline void __ticket_spin_unlock(arch_spinlock_t *lock) 73{ 74 unsigned short *p = (unsigned short *)&lock->lock + 1, tmp; 75 76 /* This could be optimised with ARCH_HAS_MMIOWB */ 77 mmiowb(); 78 asm volatile ("ld2.bias %0=[%1]" : "=r"(tmp) : "r"(p)); 79 WRITE_ONCE(*p, (tmp + 2) & ~1); 80} 81 82static inline int __ticket_spin_is_locked(arch_spinlock_t *lock) 83{ 84 long tmp = READ_ONCE(lock->lock); 85 86 return !!(((tmp >> TICKET_SHIFT) ^ tmp) & TICKET_MASK); 87} 88 89static inline int __ticket_spin_is_contended(arch_spinlock_t *lock) 90{ 91 long tmp = READ_ONCE(lock->lock); 92 93 return ((tmp - (tmp >> TICKET_SHIFT)) & TICKET_MASK) > 1; 94} 95 96static __always_inline int arch_spin_value_unlocked(arch_spinlock_t lock) 97{ 98 return !(((lock.lock >> TICKET_SHIFT) ^ lock.lock) & TICKET_MASK); 99} 100 101static inline int arch_spin_is_locked(arch_spinlock_t *lock) 102{ 103 return __ticket_spin_is_locked(lock); 104} 105 106static inline int arch_spin_is_contended(arch_spinlock_t *lock) 107{ 108 return __ticket_spin_is_contended(lock); 109} 110#define arch_spin_is_contended arch_spin_is_contended 111 112static __always_inline void arch_spin_lock(arch_spinlock_t *lock) 113{ 114 __ticket_spin_lock(lock); 115} 116 117static __always_inline int arch_spin_trylock(arch_spinlock_t *lock) 118{ 119 return __ticket_spin_trylock(lock); 120} 121 122static __always_inline void arch_spin_unlock(arch_spinlock_t *lock) 123{ 124 __ticket_spin_unlock(lock); 125} 126 127static __always_inline void arch_spin_lock_flags(arch_spinlock_t *lock, 128 unsigned long flags) 129{ 130 arch_spin_lock(lock); 131} 132#define arch_spin_lock_flags arch_spin_lock_flags 133 134#ifdef ASM_SUPPORTED 135 136static __always_inline void 137arch_read_lock_flags(arch_rwlock_t *lock, unsigned long flags) 138{ 139 __asm__ __volatile__ ( 140 "tbit.nz p6, p0 = %1,%2\n" 141 "br.few 3f\n" 142 "1:\n" 143 "fetchadd4.rel r2 = [%0], -1;;\n" 144 "(p6) ssm psr.i\n" 145 "2:\n" 146 "hint @pause\n" 147 "ld4 r2 = [%0];;\n" 148 "cmp4.lt p7,p0 = r2, r0\n" 149 "(p7) br.cond.spnt.few 2b\n" 150 "(p6) rsm psr.i\n" 151 ";;\n" 152 "3:\n" 153 "fetchadd4.acq r2 = [%0], 1;;\n" 154 "cmp4.lt p7,p0 = r2, r0\n" 155 "(p7) br.cond.spnt.few 1b\n" 156 : : "r"(lock), "r"(flags), "i"(IA64_PSR_I_BIT) 157 : "p6", "p7", "r2", "memory"); 158} 159 160#define arch_read_lock_flags arch_read_lock_flags 161#define arch_read_lock(lock) arch_read_lock_flags(lock, 0) 162 163#else /* !ASM_SUPPORTED */ 164 165#define arch_read_lock_flags(rw, flags) arch_read_lock(rw) 166 167#define arch_read_lock(rw) \ 168do { \ 169 arch_rwlock_t *__read_lock_ptr = (rw); \ 170 \ 171 while (unlikely(ia64_fetchadd(1, (int *) __read_lock_ptr, acq) < 0)) { \ 172 ia64_fetchadd(-1, (int *) __read_lock_ptr, rel); \ 173 while (*(volatile int *)__read_lock_ptr < 0) \ 174 cpu_relax(); \ 175 } \ 176} while (0) 177 178#endif /* !ASM_SUPPORTED */ 179 180#define arch_read_unlock(rw) \ 181do { \ 182 arch_rwlock_t *__read_lock_ptr = (rw); \ 183 ia64_fetchadd(-1, (int *) __read_lock_ptr, rel); \ 184} while (0) 185 186#ifdef ASM_SUPPORTED 187 188static __always_inline void 189arch_write_lock_flags(arch_rwlock_t *lock, unsigned long flags) 190{ 191 __asm__ __volatile__ ( 192 "tbit.nz p6, p0 = %1, %2\n" 193 "mov ar.ccv = r0\n" 194 "dep r29 = -1, r0, 31, 1\n" 195 "br.few 3f;;\n" 196 "1:\n" 197 "(p6) ssm psr.i\n" 198 "2:\n" 199 "hint @pause\n" 200 "ld4 r2 = [%0];;\n" 201 "cmp4.eq p0,p7 = r0, r2\n" 202 "(p7) br.cond.spnt.few 2b\n" 203 "(p6) rsm psr.i\n" 204 ";;\n" 205 "3:\n" 206 "cmpxchg4.acq r2 = [%0], r29, ar.ccv;;\n" 207 "cmp4.eq p0,p7 = r0, r2\n" 208 "(p7) br.cond.spnt.few 1b;;\n" 209 : : "r"(lock), "r"(flags), "i"(IA64_PSR_I_BIT) 210 : "ar.ccv", "p6", "p7", "r2", "r29", "memory"); 211} 212 213#define arch_write_lock_flags arch_write_lock_flags 214#define arch_write_lock(rw) arch_write_lock_flags(rw, 0) 215 216#define arch_write_trylock(rw) \ 217({ \ 218 register long result; \ 219 \ 220 __asm__ __volatile__ ( \ 221 "mov ar.ccv = r0\n" \ 222 "dep r29 = -1, r0, 31, 1;;\n" \ 223 "cmpxchg4.acq %0 = [%1], r29, ar.ccv\n" \ 224 : "=r"(result) : "r"(rw) : "ar.ccv", "r29", "memory"); \ 225 (result == 0); \ 226}) 227 228static inline void arch_write_unlock(arch_rwlock_t *x) 229{ 230 u8 *y = (u8 *)x; 231 barrier(); 232 asm volatile ("st1.rel.nta [%0] = r0\n\t" :: "r"(y+3) : "memory" ); 233} 234 235#else /* !ASM_SUPPORTED */ 236 237#define arch_write_lock(l) \ 238({ \ 239 __u64 ia64_val, ia64_set_val = ia64_dep_mi(-1, 0, 31, 1); \ 240 __u32 *ia64_write_lock_ptr = (__u32 *) (l); \ 241 do { \ 242 while (*ia64_write_lock_ptr) \ 243 ia64_barrier(); \ 244 ia64_val = ia64_cmpxchg4_acq(ia64_write_lock_ptr, ia64_set_val, 0); \ 245 } while (ia64_val); \ 246}) 247 248#define arch_write_trylock(rw) \ 249({ \ 250 __u64 ia64_val; \ 251 __u64 ia64_set_val = ia64_dep_mi(-1, 0, 31,1); \ 252 ia64_val = ia64_cmpxchg4_acq((__u32 *)(rw), ia64_set_val, 0); \ 253 (ia64_val == 0); \ 254}) 255 256static inline void arch_write_unlock(arch_rwlock_t *x) 257{ 258 barrier(); 259 x->write_lock = 0; 260} 261 262#endif /* !ASM_SUPPORTED */ 263 264static inline int arch_read_trylock(arch_rwlock_t *x) 265{ 266 union { 267 arch_rwlock_t lock; 268 __u32 word; 269 } old, new; 270 old.lock = new.lock = *x; 271 old.lock.write_lock = new.lock.write_lock = 0; 272 ++new.lock.read_counter; 273 return (u32)ia64_cmpxchg4_acq((__u32 *)(x), new.word, old.word) == old.word; 274} 275 276#endif /* _ASM_IA64_SPINLOCK_H */ 277