summaryrefslogtreecommitdiff
path: root/arch/arm64/include/asm/percpu.h
blob: 8f1661603b788a661a9eb3910a37a2f6c3fb4c30 (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
/* SPDX-License-Identifier: GPL-2.0-only */
/*
 * Copyright (C) 2013 ARM Ltd.
 */
#ifndef __ASM_PERCPU_H
#define __ASM_PERCPU_H

#include <linux/preempt.h>

#include <asm/alternative.h>
#include <asm/cmpxchg.h>
#include <asm/stack_pointer.h>

static inline void set_my_cpu_offset(unsigned long off)
{
	asm volatile(ALTERNATIVE("msr tpidr_el1, %0",
				 "msr tpidr_el2, %0",
				 ARM64_HAS_VIRT_HOST_EXTN)
			:: "r" (off) : "memory");
}

static inline unsigned long __hyp_my_cpu_offset(void)
{
	/*
	 * Non-VHE hyp code runs with preemption disabled. No need to hazard
	 * the register access against barrier() as in __kern_my_cpu_offset.
	 */
	return read_sysreg(tpidr_el2);
}

static inline unsigned long __kern_my_cpu_offset(void)
{
	unsigned long off;

	/*
	 * We want to allow caching the value, so avoid using volatile and
	 * instead use a fake stack read to hazard against barrier().
	 */
	asm(ALTERNATIVE("mrs %0, tpidr_el1",
			"mrs %0, tpidr_el2",
			ARM64_HAS_VIRT_HOST_EXTN)
		: "=r" (off) :
		"Q" (*(const unsigned long *)current_stack_pointer));

	return off;
}

#ifdef __KVM_NVHE_HYPERVISOR__
#define __my_cpu_offset __hyp_my_cpu_offset()
#else
#define __my_cpu_offset __kern_my_cpu_offset()
#endif

#define PERCPU_RW_OPS(sz)						\
static inline unsigned long __percpu_read_##sz(void *ptr)		\
{									\
	return READ_ONCE(*(u##sz *)ptr);				\
}									\
									\
static inline void __percpu_write_##sz(void *ptr, unsigned long val)	\
{									\
	WRITE_ONCE(*(u##sz *)ptr, (u##sz)val);				\
}

#define __PERCPU_OP_CASE(w, sfx, name, sz, op_llsc, op_lse)		\
static inline void							\
__percpu_##name##_case_##sz(void *ptr, unsigned long val)		\
{									\
	unsigned int loop;						\
	u##sz tmp;							\
									\
	asm volatile (ARM64_LSE_ATOMIC_INSN(				\
	/* LL/SC */							\
	"1:	ldxr" #sfx "\t%" #w "[tmp], %[ptr]\n"			\
		#op_llsc "\t%" #w "[tmp], %" #w "[tmp], %" #w "[val]\n"	\
	"	stxr" #sfx "\t%w[loop], %" #w "[tmp], %[ptr]\n"		\
	"	cbnz	%w[loop], 1b",					\
	/* LSE atomics */						\
		#op_lse "\t%" #w "[val], %[ptr]\n"			\
		__nops(3))						\
	: [loop] "=&r" (loop), [tmp] "=&r" (tmp),			\
	  [ptr] "+Q"(*(u##sz *)ptr)					\
	: [val] "r" ((u##sz)(val)));					\
}

#define __PERCPU_RET_OP_CASE(w, sfx, name, sz, op_llsc, op_lse)		\
static inline u##sz							\
__percpu_##name##_return_case_##sz(void *ptr, unsigned long val)	\
{									\
	unsigned int loop;						\
	u##sz ret;							\
									\
	asm volatile (ARM64_LSE_ATOMIC_INSN(				\
	/* LL/SC */							\
	"1:	ldxr" #sfx "\t%" #w "[ret], %[ptr]\n"			\
		#op_llsc "\t%" #w "[ret], %" #w "[ret], %" #w "[val]\n"	\
	"	stxr" #sfx "\t%w[loop], %" #w "[ret], %[ptr]\n"		\
	"	cbnz	%w[loop], 1b",					\
	/* LSE atomics */						\
		#op_lse "\t%" #w "[val], %" #w "[ret], %[ptr]\n"	\
		#op_llsc "\t%" #w "[ret], %" #w "[ret], %" #w "[val]\n"	\
		__nops(2))						\
	: [loop] "=&r" (loop), [ret] "=&r" (ret),			\
	  [ptr] "+Q"(*(u##sz *)ptr)					\
	: [val] "r" ((u##sz)(val)));					\
									\
	return ret;							\
}

#define PERCPU_OP(name, op_llsc, op_lse)				\
	__PERCPU_OP_CASE(w, b, name,  8, op_llsc, op_lse)		\
	__PERCPU_OP_CASE(w, h, name, 16, op_llsc, op_lse)		\
	__PERCPU_OP_CASE(w,  , name, 32, op_llsc, op_lse)		\
	__PERCPU_OP_CASE( ,  , name, 64, op_llsc, op_lse)

#define PERCPU_RET_OP(name, op_llsc, op_lse)				\
	__PERCPU_RET_OP_CASE(w, b, name,  8, op_llsc, op_lse)		\
	__PERCPU_RET_OP_CASE(w, h, name, 16, op_llsc, op_lse)		\
	__PERCPU_RET_OP_CASE(w,  , name, 32, op_llsc, op_lse)		\
	__PERCPU_RET_OP_CASE( ,  , name, 64, op_llsc, op_lse)

PERCPU_RW_OPS(8)
PERCPU_RW_OPS(16)
PERCPU_RW_OPS(32)
PERCPU_RW_OPS(64)
PERCPU_OP(add, add, stadd)
PERCPU_OP(andnot, bic, stclr)
PERCPU_OP(or, orr, stset)
PERCPU_RET_OP(add, add, ldadd)

#undef PERCPU_RW_OPS
#undef __PERCPU_OP_CASE
#undef __PERCPU_RET_OP_CASE
#undef PERCPU_OP
#undef PERCPU_RET_OP

/*
 * It would be nice to avoid the conditional call into the scheduler when
 * re-enabling preemption for preemptible kernels, but doing that in a way
 * which builds inside a module would mean messing directly with the preempt
 * count. If you do this, peterz and tglx will hunt you down.
 */
#define this_cpu_cmpxchg_double_8(ptr1, ptr2, o1, o2, n1, n2)		\
({									\
	int __ret;							\
	preempt_disable_notrace();					\
	__ret = cmpxchg_double_local(	raw_cpu_ptr(&(ptr1)),		\
					raw_cpu_ptr(&(ptr2)),		\
					o1, o2, n1, n2);		\
	preempt_enable_notrace();					\
	__ret;								\
})

#define _pcp_protect(op, pcp, ...)					\
({									\
	preempt_disable_notrace();					\
	op(raw_cpu_ptr(&(pcp)), __VA_ARGS__);				\
	preempt_enable_notrace();					\
})

#define _pcp_protect_return(op, pcp, args...)				\
({									\
	typeof(pcp) __retval;						\
	preempt_disable_notrace();					\
	__retval = (typeof(pcp))op(raw_cpu_ptr(&(pcp)), ##args);	\
	preempt_enable_notrace();					\
	__retval;							\
})

#define this_cpu_read_1(pcp)		\
	_pcp_protect_return(__percpu_read_8, pcp)
#define this_cpu_read_2(pcp)		\
	_pcp_protect_return(__percpu_read_16, pcp)
#define this_cpu_read_4(pcp)		\
	_pcp_protect_return(__percpu_read_32, pcp)
#define this_cpu_read_8(pcp)		\
	_pcp_protect_return(__percpu_read_64, pcp)

#define this_cpu_write_1(pcp, val)	\
	_pcp_protect(__percpu_write_8, pcp, (unsigned long)val)
#define this_cpu_write_2(pcp, val)	\
	_pcp_protect(__percpu_write_16, pcp, (unsigned long)val)
#define this_cpu_write_4(pcp, val)	\
	_pcp_protect(__percpu_write_32, pcp, (unsigned long)val)
#define this_cpu_write_8(pcp, val)	\
	_pcp_protect(__percpu_write_64, pcp, (unsigned long)val)

#define this_cpu_add_1(pcp, val)	\
	_pcp_protect(__percpu_add_case_8, pcp, val)
#define this_cpu_add_2(pcp, val)	\
	_pcp_protect(__percpu_add_case_16, pcp, val)
#define this_cpu_add_4(pcp, val)	\
	_pcp_protect(__percpu_add_case_32, pcp, val)
#define this_cpu_add_8(pcp, val)	\
	_pcp_protect(__percpu_add_case_64, pcp, val)

#define this_cpu_add_return_1(pcp, val)	\
	_pcp_protect_return(__percpu_add_return_case_8, pcp, val)
#define this_cpu_add_return_2(pcp, val)	\
	_pcp_protect_return(__percpu_add_return_case_16, pcp, val)
#define this_cpu_add_return_4(pcp, val)	\
	_pcp_protect_return(__percpu_add_return_case_32, pcp, val)
#define this_cpu_add_return_8(pcp, val)	\
	_pcp_protect_return(__percpu_add_return_case_64, pcp, val)

#define this_cpu_and_1(pcp, val)	\
	_pcp_protect(__percpu_andnot_case_8, pcp, ~val)
#define this_cpu_and_2(pcp, val)	\
	_pcp_protect(__percpu_andnot_case_16, pcp, ~val)
#define this_cpu_and_4(pcp, val)	\
	_pcp_protect(__percpu_andnot_case_32, pcp, ~val)
#define this_cpu_and_8(pcp, val)	\
	_pcp_protect(__percpu_andnot_case_64, pcp, ~val)

#define this_cpu_or_1(pcp, val)		\
	_pcp_protect(__percpu_or_case_8, pcp, val)
#define this_cpu_or_2(pcp, val)		\
	_pcp_protect(__percpu_or_case_16, pcp, val)
#define this_cpu_or_4(pcp, val)		\
	_pcp_protect(__percpu_or_case_32, pcp, val)
#define this_cpu_or_8(pcp, val)		\
	_pcp_protect(__percpu_or_case_64, pcp, val)

#define this_cpu_xchg_1(pcp, val)	\
	_pcp_protect_return(xchg_relaxed, pcp, val)
#define this_cpu_xchg_2(pcp, val)	\
	_pcp_protect_return(xchg_relaxed, pcp, val)
#define this_cpu_xchg_4(pcp, val)	\
	_pcp_protect_return(xchg_relaxed, pcp, val)
#define this_cpu_xchg_8(pcp, val)	\
	_pcp_protect_return(xchg_relaxed, pcp, val)

#define this_cpu_cmpxchg_1(pcp, o, n)	\
	_pcp_protect_return(cmpxchg_relaxed, pcp, o, n)
#define this_cpu_cmpxchg_2(pcp, o, n)	\
	_pcp_protect_return(cmpxchg_relaxed, pcp, o, n)
#define this_cpu_cmpxchg_4(pcp, o, n)	\
	_pcp_protect_return(cmpxchg_relaxed, pcp, o, n)
#define this_cpu_cmpxchg_8(pcp, o, n)	\
	_pcp_protect_return(cmpxchg_relaxed, pcp, o, n)

#ifdef __KVM_NVHE_HYPERVISOR__
extern unsigned long __hyp_per_cpu_offset(unsigned int cpu);
#define __per_cpu_offset
#define per_cpu_offset(cpu)	__hyp_per_cpu_offset((cpu))
#endif

#include <asm-generic/percpu.h>

/* Redefine macros for nVHE hyp under DEBUG_PREEMPT to avoid its dependencies. */
#if defined(__KVM_NVHE_HYPERVISOR__) && defined(CONFIG_DEBUG_PREEMPT)
#undef	this_cpu_ptr
#define	this_cpu_ptr		raw_cpu_ptr
#undef	__this_cpu_read
#define	__this_cpu_read		raw_cpu_read
#undef	__this_cpu_write
#define	__this_cpu_write	raw_cpu_write
#endif

#endif /* __ASM_PERCPU_H */