summaryrefslogtreecommitdiff
path: root/arch/arm64/mm/context.c
blob: e87f53ff5f583aeb47b3ec3187d229df380b2c50 (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
/*
 * Based on arch/arm/mm/context.c
 *
 * Copyright (C) 2002-2003 Deep Blue Solutions Ltd, all rights reserved.
 * Copyright (C) 2012 ARM Ltd.
 *
 * 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.
 *
 * This program is distributed in the hope that it will be useful,
 * but WITHOUT ANY WARRANTY; without even the implied warranty of
 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
 * GNU General Public License for more details.
 *
 * You should have received a copy of the GNU General Public License
 * along with this program.  If not, see <http://www.gnu.org/licenses/>.
 */

#include <linux/bitops.h>
#include <linux/sched.h>
#include <linux/slab.h>
#include <linux/mm.h>

#include <asm/cpufeature.h>
#include <asm/mmu_context.h>
#include <asm/tlbflush.h>

static u32 asid_bits;
static DEFINE_RAW_SPINLOCK(cpu_asid_lock);

static atomic64_t asid_generation;
static unsigned long *asid_map;

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

#define ASID_MASK		(~GENMASK(asid_bits - 1, 0))
#define ASID_FIRST_VERSION	(1UL << asid_bits)
#define NUM_USER_ASIDS		ASID_FIRST_VERSION

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);

	/*
	 * Ensure the generation bump is observed before we xchg the
	 * active_asids.
	 */
	smp_wmb();

	for_each_possible_cpu(i) {
		asid = atomic64_xchg_relaxed(&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_aivivt())
		__flush_icache_all();
}

static bool check_update_reserved_asid(u64 asid, u64 newasid)
{
	int cpu;
	bool hit = false;

	/*
	 * Iterate over the set of reserved ASIDs looking for a match.
	 * If we find one, then we can update our mm to use newasid
	 * (i.e. the same ASID in the current generation) but we can't
	 * exit the loop early, since we need to ensure that all copies
	 * of the old ASID are updated to reflect the mm. Failure to do
	 * so could result in us missing the reserved ASID in a future
	 * generation.
	 */
	for_each_possible_cpu(cpu) {
		if (per_cpu(reserved_asids, cpu) == asid) {
			hit = true;
			per_cpu(reserved_asids, cpu) = newasid;
		}
	}

	return hit;
}

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) {
		u64 newasid = generation | (asid & ~ASID_MASK);

		/*
		 * If our current ASID was active during a rollover, we
		 * can continue to use it and this was just a false alarm.
		 */
		if (check_update_reserved_asid(asid, newasid))
			return newasid;

		/*
		 * We had a valid ASID in a previous life, so try to re-use
		 * it if possible.
		 */
		asid &= ~ASID_MASK;
		if (!__test_and_set_bit(asid, asid_map))
			return newasid;
	}

	/*
	 * 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 use ASID #0 when setting a
	 * reserved TTBR0 for the init_mm.
	 */
	asid = find_next_zero_bit(asid_map, NUM_USER_ASIDS, cur_idx);
	if (asid != NUM_USER_ASIDS)
		goto set_asid;

	/* We're out of ASIDs, so increment the global generation count */
	generation = atomic64_add_return_relaxed(ASID_FIRST_VERSION,
						 &asid_generation);
	flush_context(cpu);

	/* We have at least 1 ASID per CPU, so this will always succeed */
	asid = find_next_zero_bit(asid_map, NUM_USER_ASIDS, 1);

set_asid:
	__set_bit(asid, asid_map);
	cur_idx = asid;
	return asid | generation;
}

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

	asid = atomic64_read(&mm->context.id);

	/*
	 * The memory ordering here is subtle. We rely on the control
	 * dependency between the generation read and the update of
	 * active_asids to ensure that we are synchronised with a
	 * parallel rollover (i.e. this pairs with the smp_wmb() in
	 * flush_context).
	 */
	if (!((asid ^ atomic64_read(&asid_generation)) >> asid_bits)
	    && atomic64_xchg_relaxed(&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_tlb_all();

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

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

static int asids_init(void)
{
	int fld = cpuid_feature_extract_field(read_cpuid(ID_AA64MMFR0_EL1), 4);

	switch (fld) {
	default:
		pr_warn("Unknown ASID size (%d); assuming 8-bit\n", fld);
		/* Fallthrough */
	case 0:
		asid_bits = 8;
		break;
	case 2:
		asid_bits = 16;
	}

	/* If we end up with more CPUs than ASIDs, expect things to crash */
	WARN_ON(NUM_USER_ASIDS < num_possible_cpus());
	atomic64_set(&asid_generation, ASID_FIRST_VERSION);
	asid_map = kzalloc(BITS_TO_LONGS(NUM_USER_ASIDS) * sizeof(*asid_map),
			   GFP_KERNEL);
	if (!asid_map)
		panic("Failed to allocate bitmap for %lu ASIDs\n",
		      NUM_USER_ASIDS);

	pr_info("ASID allocator initialised with %lu entries\n", NUM_USER_ASIDS);
	return 0;
}
early_initcall(asids_init);