summaryrefslogtreecommitdiff
path: root/arch/powerpc/mm/mmu_context_book3s64.c
blob: 4a892d894a0f1b2d96ed319ab0f4a622104c7526 (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
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
/*
 *  MMU context allocation for 64-bit kernels.
 *
 *  Copyright (C) 2004 Anton Blanchard, IBM Corp. <anton@samba.org>
 *
 *  This program is free software; you can redistribute it and/or
 *  modify it under the terms of the GNU General Public License
 *  as published by the Free Software Foundation; either version
 *  2 of the License, or (at your option) any later version.
 *
 */

#include <linux/sched.h>
#include <linux/kernel.h>
#include <linux/errno.h>
#include <linux/string.h>
#include <linux/types.h>
#include <linux/mm.h>
#include <linux/pkeys.h>
#include <linux/spinlock.h>
#include <linux/idr.h>
#include <linux/export.h>
#include <linux/gfp.h>
#include <linux/slab.h>

#include <asm/mmu_context.h>
#include <asm/pgalloc.h>

static DEFINE_SPINLOCK(mmu_context_lock);
static DEFINE_IDA(mmu_context_ida);

static int alloc_context_id(int min_id, int max_id)
{
	int index, err;

again:
	if (!ida_pre_get(&mmu_context_ida, GFP_KERNEL))
		return -ENOMEM;

	spin_lock(&mmu_context_lock);
	err = ida_get_new_above(&mmu_context_ida, min_id, &index);
	spin_unlock(&mmu_context_lock);

	if (err == -EAGAIN)
		goto again;
	else if (err)
		return err;

	if (index > max_id) {
		spin_lock(&mmu_context_lock);
		ida_remove(&mmu_context_ida, index);
		spin_unlock(&mmu_context_lock);
		return -ENOMEM;
	}

	return index;
}

void hash__reserve_context_id(int id)
{
	int rc, result = 0;

	do {
		if (!ida_pre_get(&mmu_context_ida, GFP_KERNEL))
			break;

		spin_lock(&mmu_context_lock);
		rc = ida_get_new_above(&mmu_context_ida, id, &result);
		spin_unlock(&mmu_context_lock);
	} while (rc == -EAGAIN);

	WARN(result != id, "mmu: Failed to reserve context id %d (rc %d)\n", id, result);
}

int hash__alloc_context_id(void)
{
	unsigned long max;

	if (mmu_has_feature(MMU_FTR_68_BIT_VA))
		max = MAX_USER_CONTEXT;
	else
		max = MAX_USER_CONTEXT_65BIT_VA;

	return alloc_context_id(MIN_USER_CONTEXT, max);
}
EXPORT_SYMBOL_GPL(hash__alloc_context_id);

static int hash__init_new_context(struct mm_struct *mm)
{
	int index;

	index = hash__alloc_context_id();
	if (index < 0)
		return index;

	/*
	 * The old code would re-promote on fork, we don't do that when using
	 * slices as it could cause problem promoting slices that have been
	 * forced down to 4K.
	 *
	 * For book3s we have MMU_NO_CONTEXT set to be ~0. Hence check
	 * explicitly against context.id == 0. This ensures that we properly
	 * initialize context slice details for newly allocated mm's (which will
	 * have id == 0) and don't alter context slice inherited via fork (which
	 * will have id != 0).
	 *
	 * We should not be calling init_new_context() on init_mm. Hence a
	 * check against 0 is OK.
	 */
	if (mm->context.id == 0)
		slice_init_new_context_exec(mm);

	subpage_prot_init_new_context(mm);

	pkey_mm_init(mm);
	return index;
}

static int radix__init_new_context(struct mm_struct *mm)
{
	unsigned long rts_field;
	int index, max_id;

	max_id = (1 << mmu_pid_bits) - 1;
	index = alloc_context_id(mmu_base_pid, max_id);
	if (index < 0)
		return index;

	/*
	 * set the process table entry,
	 */
	rts_field = radix__get_tree_size();
	process_tb[index].prtb0 = cpu_to_be64(rts_field | __pa(mm->pgd) | RADIX_PGD_INDEX_SIZE);

	/*
	 * Order the above store with subsequent update of the PID
	 * register (at which point HW can start loading/caching
	 * the entry) and the corresponding load by the MMU from
	 * the L2 cache.
	 */
	asm volatile("ptesync;isync" : : : "memory");

	mm->context.npu_context = NULL;

	return index;
}

int init_new_context(struct task_struct *tsk, struct mm_struct *mm)
{
	int index;

	if (radix_enabled())
		index = radix__init_new_context(mm);
	else
		index = hash__init_new_context(mm);

	if (index < 0)
		return index;

	mm->context.id = index;

	mm->context.pte_frag = NULL;
	mm->context.pmd_frag = NULL;
#ifdef CONFIG_SPAPR_TCE_IOMMU
	mm_iommu_init(mm);
#endif
	atomic_set(&mm->context.active_cpus, 0);
	atomic_set(&mm->context.copros, 0);

	return 0;
}

void __destroy_context(int context_id)
{
	spin_lock(&mmu_context_lock);
	ida_remove(&mmu_context_ida, context_id);
	spin_unlock(&mmu_context_lock);
}
EXPORT_SYMBOL_GPL(__destroy_context);

static void destroy_contexts(mm_context_t *ctx)
{
	int index, context_id;

	spin_lock(&mmu_context_lock);
	for (index = 0; index < ARRAY_SIZE(ctx->extended_id); index++) {
		context_id = ctx->extended_id[index];
		if (context_id)
			ida_remove(&mmu_context_ida, context_id);
	}
	spin_unlock(&mmu_context_lock);
}

static void pte_frag_destroy(void *pte_frag)
{
	int count;
	struct page *page;

	page = virt_to_page(pte_frag);
	/* drop all the pending references */
	count = ((unsigned long)pte_frag & ~PAGE_MASK) >> PTE_FRAG_SIZE_SHIFT;
	/* We allow PTE_FRAG_NR fragments from a PTE page */
	if (atomic_sub_and_test(PTE_FRAG_NR - count, &page->pt_frag_refcount)) {
		pgtable_page_dtor(page);
		__free_page(page);
	}
}

static void pmd_frag_destroy(void *pmd_frag)
{
	int count;
	struct page *page;

	page = virt_to_page(pmd_frag);
	/* drop all the pending references */
	count = ((unsigned long)pmd_frag & ~PAGE_MASK) >> PMD_FRAG_SIZE_SHIFT;
	/* We allow PTE_FRAG_NR fragments from a PTE page */
	if (atomic_sub_and_test(PMD_FRAG_NR - count, &page->pt_frag_refcount)) {
		pgtable_pmd_page_dtor(page);
		__free_page(page);
	}
}

static void destroy_pagetable_cache(struct mm_struct *mm)
{
	void *frag;

	frag = mm->context.pte_frag;
	if (frag)
		pte_frag_destroy(frag);

	frag = mm->context.pmd_frag;
	if (frag)
		pmd_frag_destroy(frag);
	return;
}

void destroy_context(struct mm_struct *mm)
{
#ifdef CONFIG_SPAPR_TCE_IOMMU
	WARN_ON_ONCE(!list_empty(&mm->context.iommu_group_mem_list));
#endif
	if (radix_enabled())
		WARN_ON(process_tb[mm->context.id].prtb0 != 0);
	else
		subpage_prot_free(mm);
	destroy_contexts(&mm->context);
	mm->context.id = MMU_NO_CONTEXT;
}

void arch_exit_mmap(struct mm_struct *mm)
{
	destroy_pagetable_cache(mm);

	if (radix_enabled()) {
		/*
		 * Radix doesn't have a valid bit in the process table
		 * entries. However we know that at least P9 implementation
		 * will avoid caching an entry with an invalid RTS field,
		 * and 0 is invalid. So this will do.
		 *
		 * This runs before the "fullmm" tlb flush in exit_mmap,
		 * which does a RIC=2 tlbie to clear the process table
		 * entry. See the "fullmm" comments in tlb-radix.c.
		 *
		 * No barrier required here after the store because
		 * this process will do the invalidate, which starts with
		 * ptesync.
		 */
		process_tb[mm->context.id].prtb0 = 0;
	}
}

#ifdef CONFIG_PPC_RADIX_MMU
void radix__switch_mmu_context(struct mm_struct *prev, struct mm_struct *next)
{
	mtspr(SPRN_PID, next->context.id);
	isync();
}
#endif