summaryrefslogtreecommitdiffstats
path: root/arch/arm/mm/context.c
blob: 6eb97b3a7481b9b68ee806845a534cb6d278192d (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
/*
 *  linux/arch/arm/mm/context.c
 *
 *  Copyright (C) 2002-2003 Deep Blue Solutions Ltd, all rights reserved.
 *  Copyright (C) 2012 ARM Limited
 *
 *  Author: Will Deacon <will.deacon@arm.com>
 *
 * This program is free software; you can redistribute it and/or modify
 * it under the terms of the GNU General Public License version 2 as
 * published by the Free Software Foundation.
 */
#include <linux/init.h>
#include <linux/sched.h>
#include <linux/mm.h>
#include <linux/smp.h>
#include <linux/percpu.h>

#include <asm/mmu_context.h>
#include <asm/smp_plat.h>
#include <asm/thread_notify.h>
#include <asm/tlbflush.h>
#include <asm/proc-fns.h>

/*
 * On ARMv6, we have the following structure in the Context ID:
 *
 * 31                         7          0
 * +-------------------------+-----------+
 * |      process ID         |   ASID    |
 * +-------------------------+-----------+
 * |              context ID             |
 * +-------------------------------------+
 *
 * The ASID is used to tag entries in the CPU caches and TLBs.
 * The context ID is used by debuggers and trace logic, and
 * should be unique within all running processes.
 *
 * In big endian operation, the two 32 bit words are swapped if accessed
 * by non-64-bit operations.
 */
#define ASID_FIRST_VERSION	(1ULL << ASID_BITS)
#define NUM_USER_ASIDS		ASID_FIRST_VERSION

static DEFINE_RAW_SPINLOCK(cpu_asid_lock);
static atomic64_t asid_generation = ATOMIC64_INIT(ASID_FIRST_VERSION);
static DECLARE_BITMAP(asid_map, NUM_USER_ASIDS);

static DEFINE_PER_CPU(atomic64_t, active_asids);
static DEFINE_PER_CPU(u64, reserved_asids);
static cpumask_t tlb_flush_pending;

#ifdef CONFIG_ARM_ERRATA_798181
void a15_erratum_get_cpumask(int this_cpu, struct mm_struct *mm,
			     cpumask_t *mask)
{
	int cpu;
	unsigned long flags;
	u64 context_id, asid;

	raw_spin_lock_irqsave(&cpu_asid_lock, flags);
	context_id = mm->context.id.counter;
	for_each_online_cpu(cpu) {
		if (cpu == this_cpu)
			continue;
		/*
		 * We only need to send an IPI if the other CPUs are
		 * running the same ASID as the one being invalidated.
		 */
		asid = per_cpu(active_asids, cpu).counter;
		if (asid == 0)
			asid = per_cpu(reserved_asids, cpu);
		if (context_id == asid)
			cpumask_set_cpu(cpu, mask);
	}
	raw_spin_unlock_irqrestore(&cpu_asid_lock, flags);
}
#endif

#ifdef CONFIG_ARM_LPAE
/*
 * With LPAE, the ASID and page tables are updated atomicly, so there is
 * no need for a reserved set of tables (the active ASID tracking prevents
 * any issues across a rollover).
 */
#define cpu_set_reserved_ttbr0()
#else
static void cpu_set_reserved_ttbr0(void)
{
	u32 ttb;
	/*
	 * Copy TTBR1 into TTBR0.
	 * This points at swapper_pg_dir, which contains only global
	 * entries so any speculative walks are perfectly safe.
	 */
	asm volatile(
	"	mrc	p15, 0, %0, c2, c0, 1		@ read TTBR1\n"
	"	mcr	p15, 0, %0, c2, c0, 0		@ set TTBR0\n"
	: "=r" (ttb));
	isb();
}
#endif

#ifdef CONFIG_PID_IN_CONTEXTIDR
static int contextidr_notifier(struct notifier_block *unused, unsigned long cmd,
			       void *t)
{
	u32 contextidr;
	pid_t pid;
	struct thread_info *thread = t;

	if (cmd != THREAD_NOTIFY_SWITCH)
		return NOTIFY_DONE;

	pid = task_pid_nr(thread->task) << ASID_BITS;
	asm volatile(
	"	mrc	p15, 0, %0, c13, c0, 1\n"
	"	and	%0, %0, %2\n"
	"	orr	%0, %0, %1\n"
	"	mcr	p15, 0, %0, c13, c0, 1\n"
	: "=r" (contextidr), "+r" (pid)
	: "I" (~ASID_MASK));
	isb();

	return NOTIFY_OK;
}

static struct notifier_block contextidr_notifier_block = {
	.notifier_call = contextidr_notifier,
};

static int __init contextidr_notifier_init(void)
{
	return thread_register_notifier(&contextidr_notifier_block);
}
arch_initcall(contextidr_notifier_init);
#endif

static void flush_context(unsigned int cpu)
{
	int i;
	u64 asid;

	/* Update the list of reserved ASIDs and the ASID bitmap. */
	bitmap_clear(asid_map, 0, NUM_USER_ASIDS);
	for_each_possible_cpu(i) {
		if (i == cpu) {
			asid = 0;
		} else {
			asid = atomic64_xchg(&per_cpu(active_asids, i), 0);
			/*
			 * If this CPU has already been through a
			 * rollover, but hasn't run another task in
			 * the meantime, we must preserve its reserved
			 * ASID, as this is the only trace we have of
			 * the process it is still running.
			 */
			if (asid == 0)
				asid = per_cpu(reserved_asids, i);
			__set_bit(asid & ~ASID_MASK, asid_map);
		}
		per_cpu(reserved_asids, i) = asid;
	}

	/* Queue a TLB invalidate and flush the I-cache if necessary. */
	cpumask_setall(&tlb_flush_pending);

	if (icache_is_vivt_asid_tagged())
		__flush_icache_all();
}

static int is_reserved_asid(u64 asid)
{
	int cpu;
	for_each_possible_cpu(cpu)
		if (per_cpu(reserved_asids, cpu) == asid)
			return 1;
	return 0;
}

static u64 new_context(struct mm_struct *mm, unsigned int cpu)
{
	static u32 cur_idx = 1;
	u64 asid = atomic64_read(&mm->context.id);
	u64 generation = atomic64_read(&asid_generation);

	if (asid != 0 && is_reserved_asid(asid)) {
		/*
		 * Our current ASID was active during a rollover, we can
		 * continue to use it and this was just a false alarm.
		 */
		asid = generation | (asid & ~ASID_MASK);
	} else {
		/*
		 * Allocate a free ASID. If we can't find one, take a
		 * note of the currently active ASIDs and mark the TLBs
		 * as requiring flushes. We always count from ASID #1,
		 * as we reserve ASID #0 to switch via TTBR0 and to
		 * avoid speculative page table walks from hitting in
		 * any partial walk caches, which could be populated
		 * from overlapping level-1 descriptors used to map both
		 * the module area and the userspace stack.
		 */
		asid = find_next_zero_bit(asid_map, NUM_USER_ASIDS, cur_idx);
		if (asid == NUM_USER_ASIDS) {
			generation = atomic64_add_return(ASID_FIRST_VERSION,
							 &asid_generation);
			flush_context(cpu);
			asid = find_next_zero_bit(asid_map, NUM_USER_ASIDS, 1);
		}
		__set_bit(asid, asid_map);
		cur_idx = asid;
		asid |= generation;
		cpumask_clear(mm_cpumask(mm));
	}

	return asid;
}

void check_and_switch_context(struct mm_struct *mm, struct task_struct *tsk)
{
	unsigned long flags;
	unsigned int cpu = smp_processor_id();
	u64 asid;

	if (unlikely(mm->context.vmalloc_seq != init_mm.context.vmalloc_seq))
		__check_vmalloc_seq(mm);

	/*
	 * We cannot update the pgd and the ASID atomicly with classic
	 * MMU, so switch exclusively to global mappings to avoid
	 * speculative page table walking with the wrong TTBR.
	 */
	cpu_set_reserved_ttbr0();

	asid = atomic64_read(&mm->context.id);
	if (!((asid ^ atomic64_read(&asid_generation)) >> ASID_BITS)
	    && atomic64_xchg(&per_cpu(active_asids, cpu), asid))
		goto switch_mm_fastpath;

	raw_spin_lock_irqsave(&cpu_asid_lock, flags);
	/* Check that our ASID belongs to the current generation. */
	asid = atomic64_read(&mm->context.id);
	if ((asid ^ atomic64_read(&asid_generation)) >> ASID_BITS) {
		asid = new_context(mm, cpu);
		atomic64_set(&mm->context.id, asid);
	}

	if (cpumask_test_and_clear_cpu(cpu, &tlb_flush_pending)) {
		local_flush_bp_all();
		local_flush_tlb_all();
	}

	atomic64_set(&per_cpu(active_asids, cpu), asid);
	cpumask_set_cpu(cpu, mm_cpumask(mm));
	raw_spin_unlock_irqrestore(&cpu_asid_lock, flags);

switch_mm_fastpath:
	cpu_switch_mm(mm->pgd, mm);
}