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