aboutsummaryrefslogtreecommitdiff
path: root/mm/mmu_gather.c
blob: f2f03c65580707669207f2b3ae17ce8227c2b43f (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
#include <linux/gfp.h>
#include <linux/highmem.h>
#include <linux/kernel.h>
#include <linux/mmdebug.h>
#include <linux/mm_types.h>
#include <linux/pagemap.h>
#include <linux/rcupdate.h>
#include <linux/smp.h>
#include <linux/swap.h>

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

#ifdef HAVE_GENERIC_MMU_GATHER

static bool tlb_next_batch(struct mmu_gather *tlb)
{
	struct mmu_gather_batch *batch;

	batch = tlb->active;
	if (batch->next) {
		tlb->active = batch->next;
		return true;
	}

	if (tlb->batch_count == MAX_GATHER_BATCH_COUNT)
		return false;

	batch = (void *)__get_free_pages(GFP_NOWAIT | __GFP_NOWARN, 0);
	if (!batch)
		return false;

	tlb->batch_count++;
	batch->next = NULL;
	batch->nr   = 0;
	batch->max  = MAX_GATHER_BATCH;

	tlb->active->next = batch;
	tlb->active = batch;

	return true;
}

void arch_tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm,
				unsigned long start, unsigned long end)
{
	tlb->mm = mm;

	/* Is it from 0 to ~0? */
	tlb->fullmm     = !(start | (end+1));
	tlb->need_flush_all = 0;
	tlb->local.next = NULL;
	tlb->local.nr   = 0;
	tlb->local.max  = ARRAY_SIZE(tlb->__pages);
	tlb->active     = &tlb->local;
	tlb->batch_count = 0;

#ifdef CONFIG_HAVE_RCU_TABLE_FREE
	tlb->batch = NULL;
#endif
	tlb->page_size = 0;

	__tlb_reset_range(tlb);
}

void tlb_flush_mmu_free(struct mmu_gather *tlb)
{
	struct mmu_gather_batch *batch;

#ifdef CONFIG_HAVE_RCU_TABLE_FREE
	tlb_table_flush(tlb);
#endif
	for (batch = &tlb->local; batch && batch->nr; batch = batch->next) {
		free_pages_and_swap_cache(batch->pages, batch->nr);
		batch->nr = 0;
	}
	tlb->active = &tlb->local;
}

void tlb_flush_mmu(struct mmu_gather *tlb)
{
	tlb_flush_mmu_tlbonly(tlb);
	tlb_flush_mmu_free(tlb);
}

/* tlb_finish_mmu
 *	Called at the end of the shootdown operation to free up any resources
 *	that were required.
 */
void arch_tlb_finish_mmu(struct mmu_gather *tlb,
		unsigned long start, unsigned long end, bool force)
{
	struct mmu_gather_batch *batch, *next;

	if (force) {
		__tlb_reset_range(tlb);
		__tlb_adjust_range(tlb, start, end - start);
	}

	tlb_flush_mmu(tlb);

	/* keep the page table cache within bounds */
	check_pgt_cache();

	for (batch = tlb->local.next; batch; batch = next) {
		next = batch->next;
		free_pages((unsigned long)batch, 0);
	}
	tlb->local.next = NULL;
}

/* __tlb_remove_page
 *	Must perform the equivalent to __free_pte(pte_get_and_clear(ptep)), while
 *	handling the additional races in SMP caused by other CPUs caching valid
 *	mappings in their TLBs. Returns the number of free page slots left.
 *	When out of page slots we must call tlb_flush_mmu().
 *returns true if the caller should flush.
 */
bool __tlb_remove_page_size(struct mmu_gather *tlb, struct page *page, int page_size)
{
	struct mmu_gather_batch *batch;

	VM_BUG_ON(!tlb->end);
	VM_WARN_ON(tlb->page_size != page_size);

	batch = tlb->active;
	/*
	 * Add the page and check if we are full. If so
	 * force a flush.
	 */
	batch->pages[batch->nr++] = page;
	if (batch->nr == batch->max) {
		if (!tlb_next_batch(tlb))
			return true;
		batch = tlb->active;
	}
	VM_BUG_ON_PAGE(batch->nr > batch->max, page);

	return false;
}

#endif /* HAVE_GENERIC_MMU_GATHER */

#ifdef CONFIG_HAVE_RCU_TABLE_FREE

/*
 * See the comment near struct mmu_table_batch.
 */

/*
 * If we want tlb_remove_table() to imply TLB invalidates.
 */
static inline void tlb_table_invalidate(struct mmu_gather *tlb)
{
#ifdef CONFIG_HAVE_RCU_TABLE_INVALIDATE
	/*
	 * Invalidate page-table caches used by hardware walkers. Then we still
	 * need to RCU-sched wait while freeing the pages because software
	 * walkers can still be in-flight.
	 */
	tlb_flush_mmu_tlbonly(tlb);
#endif
}

static void tlb_remove_table_smp_sync(void *arg)
{
	/* Simply deliver the interrupt */
}

static void tlb_remove_table_one(void *table)
{
	/*
	 * This isn't an RCU grace period and hence the page-tables cannot be
	 * assumed to be actually RCU-freed.
	 *
	 * It is however sufficient for software page-table walkers that rely on
	 * IRQ disabling. See the comment near struct mmu_table_batch.
	 */
	smp_call_function(tlb_remove_table_smp_sync, NULL, 1);
	__tlb_remove_table(table);
}

static void tlb_remove_table_rcu(struct rcu_head *head)
{
	struct mmu_table_batch *batch;
	int i;

	batch = container_of(head, struct mmu_table_batch, rcu);

	for (i = 0; i < batch->nr; i++)
		__tlb_remove_table(batch->tables[i]);

	free_page((unsigned long)batch);
}

void tlb_table_flush(struct mmu_gather *tlb)
{
	struct mmu_table_batch **batch = &tlb->batch;

	if (*batch) {
		tlb_table_invalidate(tlb);
		call_rcu(&(*batch)->rcu, tlb_remove_table_rcu);
		*batch = NULL;
	}
}

void tlb_remove_table(struct mmu_gather *tlb, void *table)
{
	struct mmu_table_batch **batch = &tlb->batch;

	if (*batch == NULL) {
		*batch = (struct mmu_table_batch *)__get_free_page(GFP_NOWAIT | __GFP_NOWARN);
		if (*batch == NULL) {
			tlb_table_invalidate(tlb);
			tlb_remove_table_one(table);
			return;
		}
		(*batch)->nr = 0;
	}

	(*batch)->tables[(*batch)->nr++] = table;
	if ((*batch)->nr == MAX_TABLE_BATCH)
		tlb_table_flush(tlb);
}

#endif /* CONFIG_HAVE_RCU_TABLE_FREE */

/**
 * tlb_gather_mmu - initialize an mmu_gather structure for page-table tear-down
 * @tlb: the mmu_gather structure to initialize
 * @mm: the mm_struct of the target address space
 * @start: start of the region that will be removed from the page-table
 * @end: end of the region that will be removed from the page-table
 *
 * Called to initialize an (on-stack) mmu_gather structure for page-table
 * tear-down from @mm. The @start and @end are set to 0 and -1
 * respectively when @mm is without users and we're going to destroy
 * the full address space (exit/execve).
 */
void tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm,
			unsigned long start, unsigned long end)
{
	arch_tlb_gather_mmu(tlb, mm, start, end);
	inc_tlb_flush_pending(tlb->mm);
}

void tlb_finish_mmu(struct mmu_gather *tlb,
		unsigned long start, unsigned long end)
{
	/*
	 * If there are parallel threads are doing PTE changes on same range
	 * under non-exclusive lock(e.g., mmap_sem read-side) but defer TLB
	 * flush by batching, a thread has stable TLB entry can fail to flush
	 * the TLB by observing pte_none|!pte_dirty, for example so flush TLB
	 * forcefully if we detect parallel PTE batching threads.
	 */
	bool force = mm_tlb_flush_nested(tlb->mm);

	arch_tlb_finish_mmu(tlb, start, end, force);
	dec_tlb_flush_pending(tlb->mm);
}