Blame view

mm/highmem.c 8.73 KB
1da177e4c   Linus Torvalds   Linux-2.6.12-rc2
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
  /*
   * High memory handling common code and variables.
   *
   * (C) 1999 Andrea Arcangeli, SuSE GmbH, andrea@suse.de
   *          Gerhard Wichert, Siemens AG, Gerhard.Wichert@pdb.siemens.de
   *
   *
   * Redesigned the x86 32-bit VM architecture to deal with
   * 64-bit physical space. With current x86 CPUs this
   * means up to 64 Gigabytes physical RAM.
   *
   * Rewrote high memory support to move the page cache into
   * high memory. Implemented permanent (schedulable) kmaps
   * based on Linus' idea.
   *
   * Copyright (C) 1999 Ingo Molnar <mingo@redhat.com>
   */
  
  #include <linux/mm.h>
  #include <linux/module.h>
  #include <linux/swap.h>
  #include <linux/bio.h>
  #include <linux/pagemap.h>
  #include <linux/mempool.h>
  #include <linux/blkdev.h>
  #include <linux/init.h>
  #include <linux/hash.h>
  #include <linux/highmem.h>
2056a782f   Jens Axboe   [PATCH] Block que...
29
  #include <linux/blktrace_api.h>
1da177e4c   Linus Torvalds   Linux-2.6.12-rc2
30
  #include <asm/tlbflush.h>
1da177e4c   Linus Torvalds   Linux-2.6.12-rc2
31
32
33
34
35
36
37
38
39
  /*
   * Virtual_count is not a pure "count".
   *  0 means that it is not mapped, and has not been mapped
   *    since a TLB flush - it is usable.
   *  1 means that there are no users, but it has been mapped
   *    since the last TLB flush - so we can't use it.
   *  n means that there are (n-1) current users of it.
   */
  #ifdef CONFIG_HIGHMEM
260b23674   Al Viro   [PATCH] gfp_t: th...
40

c1f60a5a4   Christoph Lameter   [PATCH] reduce MA...
41
  unsigned long totalhigh_pages __read_mostly;
db7a94d60   David S. Miller   highmem: Export t...
42
  EXPORT_SYMBOL(totalhigh_pages);
c1f60a5a4   Christoph Lameter   [PATCH] reduce MA...
43
44
45
46
47
  
  unsigned int nr_free_highpages (void)
  {
  	pg_data_t *pgdat;
  	unsigned int pages = 0;
2a1e274ac   Mel Gorman   Create the ZONE_M...
48
  	for_each_online_pgdat(pgdat) {
d23ad4232   Christoph Lameter   [PATCH] Use ZVC f...
49
50
  		pages += zone_page_state(&pgdat->node_zones[ZONE_HIGHMEM],
  			NR_FREE_PAGES);
2a1e274ac   Mel Gorman   Create the ZONE_M...
51
52
53
54
55
  		if (zone_movable_is_highmem())
  			pages += zone_page_state(
  					&pgdat->node_zones[ZONE_MOVABLE],
  					NR_FREE_PAGES);
  	}
c1f60a5a4   Christoph Lameter   [PATCH] reduce MA...
56
57
58
  
  	return pages;
  }
1da177e4c   Linus Torvalds   Linux-2.6.12-rc2
59
60
61
62
63
64
65
66
67
68
69
  static int pkmap_count[LAST_PKMAP];
  static unsigned int last_pkmap_nr;
  static  __cacheline_aligned_in_smp DEFINE_SPINLOCK(kmap_lock);
  
  pte_t * pkmap_page_table;
  
  static DECLARE_WAIT_QUEUE_HEAD(pkmap_map_wait);
  
  static void flush_all_zero_pkmaps(void)
  {
  	int i;
5843d9a4d   Nick Piggin   x86, pat: avoid h...
70
  	int need_flush = 0;
1da177e4c   Linus Torvalds   Linux-2.6.12-rc2
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
  
  	flush_cache_kmaps();
  
  	for (i = 0; i < LAST_PKMAP; i++) {
  		struct page *page;
  
  		/*
  		 * zero means we don't have anything to do,
  		 * >1 means that it is still in use. Only
  		 * a count of 1 means that it is free but
  		 * needs to be unmapped
  		 */
  		if (pkmap_count[i] != 1)
  			continue;
  		pkmap_count[i] = 0;
  
  		/* sanity check */
75babcace   Eric Sesterhenn   BUG_ON() Conversi...
88
  		BUG_ON(pte_none(pkmap_page_table[i]));
1da177e4c   Linus Torvalds   Linux-2.6.12-rc2
89
90
91
92
93
94
95
96
97
98
99
100
101
  
  		/*
  		 * Don't need an atomic fetch-and-clear op here;
  		 * no-one has the page mapped, and cannot get at
  		 * its virtual address (and hence PTE) without first
  		 * getting the kmap_lock (which is held here).
  		 * So no dangers, even with speculative execution.
  		 */
  		page = pte_page(pkmap_page_table[i]);
  		pte_clear(&init_mm, (unsigned long)page_address(page),
  			  &pkmap_page_table[i]);
  
  		set_page_address(page, NULL);
5843d9a4d   Nick Piggin   x86, pat: avoid h...
102
  		need_flush = 1;
1da177e4c   Linus Torvalds   Linux-2.6.12-rc2
103
  	}
5843d9a4d   Nick Piggin   x86, pat: avoid h...
104
105
  	if (need_flush)
  		flush_tlb_kernel_range(PKMAP_ADDR(0), PKMAP_ADDR(LAST_PKMAP));
1da177e4c   Linus Torvalds   Linux-2.6.12-rc2
106
  }
77f6078aa   Randy Dunlap   mm: highmem kerne...
107
108
109
  /**
   * kmap_flush_unused - flush all unused kmap mappings in order to remove stray mappings
   */
ce6234b52   Jeremy Fitzhardinge   [PATCH] i386: PAR...
110
111
112
113
114
115
  void kmap_flush_unused(void)
  {
  	spin_lock(&kmap_lock);
  	flush_all_zero_pkmaps();
  	spin_unlock(&kmap_lock);
  }
1da177e4c   Linus Torvalds   Linux-2.6.12-rc2
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
  static inline unsigned long map_new_virtual(struct page *page)
  {
  	unsigned long vaddr;
  	int count;
  
  start:
  	count = LAST_PKMAP;
  	/* Find an empty entry */
  	for (;;) {
  		last_pkmap_nr = (last_pkmap_nr + 1) & LAST_PKMAP_MASK;
  		if (!last_pkmap_nr) {
  			flush_all_zero_pkmaps();
  			count = LAST_PKMAP;
  		}
  		if (!pkmap_count[last_pkmap_nr])
  			break;	/* Found a usable entry */
  		if (--count)
  			continue;
  
  		/*
  		 * Sleep for somebody else to unmap their entries
  		 */
  		{
  			DECLARE_WAITQUEUE(wait, current);
  
  			__set_current_state(TASK_UNINTERRUPTIBLE);
  			add_wait_queue(&pkmap_map_wait, &wait);
  			spin_unlock(&kmap_lock);
  			schedule();
  			remove_wait_queue(&pkmap_map_wait, &wait);
  			spin_lock(&kmap_lock);
  
  			/* Somebody else might have mapped it while we slept */
  			if (page_address(page))
  				return (unsigned long)page_address(page);
  
  			/* Re-start */
  			goto start;
  		}
  	}
  	vaddr = PKMAP_ADDR(last_pkmap_nr);
  	set_pte_at(&init_mm, vaddr,
  		   &(pkmap_page_table[last_pkmap_nr]), mk_pte(page, kmap_prot));
  
  	pkmap_count[last_pkmap_nr] = 1;
  	set_page_address(page, (void *)vaddr);
  
  	return vaddr;
  }
77f6078aa   Randy Dunlap   mm: highmem kerne...
165
166
167
168
169
170
171
172
  /**
   * kmap_high - map a highmem page into memory
   * @page: &struct page to map
   *
   * Returns the page's virtual memory address.
   *
   * We cannot call this from interrupts, as it may block.
   */
920c7a5d0   Harvey Harrison   mm: remove fastca...
173
  void *kmap_high(struct page *page)
1da177e4c   Linus Torvalds   Linux-2.6.12-rc2
174
175
176
177
178
179
  {
  	unsigned long vaddr;
  
  	/*
  	 * For highmem pages, we can't trust "virtual" until
  	 * after we have the lock.
1da177e4c   Linus Torvalds   Linux-2.6.12-rc2
180
181
182
183
184
185
  	 */
  	spin_lock(&kmap_lock);
  	vaddr = (unsigned long)page_address(page);
  	if (!vaddr)
  		vaddr = map_new_virtual(page);
  	pkmap_count[PKMAP_NR(vaddr)]++;
75babcace   Eric Sesterhenn   BUG_ON() Conversi...
186
  	BUG_ON(pkmap_count[PKMAP_NR(vaddr)] < 2);
1da177e4c   Linus Torvalds   Linux-2.6.12-rc2
187
188
189
190
191
  	spin_unlock(&kmap_lock);
  	return (void*) vaddr;
  }
  
  EXPORT_SYMBOL(kmap_high);
77f6078aa   Randy Dunlap   mm: highmem kerne...
192
193
194
195
  /**
   * kunmap_high - map a highmem page into memory
   * @page: &struct page to unmap
   */
920c7a5d0   Harvey Harrison   mm: remove fastca...
196
  void kunmap_high(struct page *page)
1da177e4c   Linus Torvalds   Linux-2.6.12-rc2
197
198
199
200
201
202
203
  {
  	unsigned long vaddr;
  	unsigned long nr;
  	int need_wakeup;
  
  	spin_lock(&kmap_lock);
  	vaddr = (unsigned long)page_address(page);
75babcace   Eric Sesterhenn   BUG_ON() Conversi...
204
  	BUG_ON(!vaddr);
1da177e4c   Linus Torvalds   Linux-2.6.12-rc2
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
  	nr = PKMAP_NR(vaddr);
  
  	/*
  	 * A count must never go down to zero
  	 * without a TLB flush!
  	 */
  	need_wakeup = 0;
  	switch (--pkmap_count[nr]) {
  	case 0:
  		BUG();
  	case 1:
  		/*
  		 * Avoid an unnecessary wake_up() function call.
  		 * The common case is pkmap_count[] == 1, but
  		 * no waiters.
  		 * The tasks queued in the wait-queue are guarded
  		 * by both the lock in the wait-queue-head and by
  		 * the kmap_lock.  As the kmap_lock is held here,
  		 * no need for the wait-queue-head's lock.  Simply
  		 * test if the queue is empty.
  		 */
  		need_wakeup = waitqueue_active(&pkmap_map_wait);
  	}
  	spin_unlock(&kmap_lock);
  
  	/* do wake-up, if needed, race-free outside of the spin lock */
  	if (need_wakeup)
  		wake_up(&pkmap_map_wait);
  }
  
  EXPORT_SYMBOL(kunmap_high);
1da177e4c   Linus Torvalds   Linux-2.6.12-rc2
236
  #endif
1da177e4c   Linus Torvalds   Linux-2.6.12-rc2
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
  #if defined(HASHED_PAGE_VIRTUAL)
  
  #define PA_HASH_ORDER	7
  
  /*
   * Describes one page->virtual association
   */
  struct page_address_map {
  	struct page *page;
  	void *virtual;
  	struct list_head list;
  };
  
  /*
   * page_address_map freelist, allocated from page_address_maps.
   */
  static struct list_head page_address_pool;	/* freelist */
  static spinlock_t pool_lock;			/* protects page_address_pool */
  
  /*
   * Hash table bucket
   */
  static struct page_address_slot {
  	struct list_head lh;			/* List of page_address_maps */
  	spinlock_t lock;			/* Protect this bucket's list */
  } ____cacheline_aligned_in_smp page_address_htable[1<<PA_HASH_ORDER];
  
  static struct page_address_slot *page_slot(struct page *page)
  {
  	return &page_address_htable[hash_ptr(page, PA_HASH_ORDER)];
  }
77f6078aa   Randy Dunlap   mm: highmem kerne...
268
269
270
271
272
273
  /**
   * page_address - get the mapped virtual address of a page
   * @page: &struct page to get the virtual address of
   *
   * Returns the page's virtual address.
   */
1da177e4c   Linus Torvalds   Linux-2.6.12-rc2
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
  void *page_address(struct page *page)
  {
  	unsigned long flags;
  	void *ret;
  	struct page_address_slot *pas;
  
  	if (!PageHighMem(page))
  		return lowmem_page_address(page);
  
  	pas = page_slot(page);
  	ret = NULL;
  	spin_lock_irqsave(&pas->lock, flags);
  	if (!list_empty(&pas->lh)) {
  		struct page_address_map *pam;
  
  		list_for_each_entry(pam, &pas->lh, list) {
  			if (pam->page == page) {
  				ret = pam->virtual;
  				goto done;
  			}
  		}
  	}
  done:
  	spin_unlock_irqrestore(&pas->lock, flags);
  	return ret;
  }
  
  EXPORT_SYMBOL(page_address);
77f6078aa   Randy Dunlap   mm: highmem kerne...
302
303
304
305
306
  /**
   * set_page_address - set a page's virtual address
   * @page: &struct page to set
   * @virtual: virtual address to use
   */
1da177e4c   Linus Torvalds   Linux-2.6.12-rc2
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
  void set_page_address(struct page *page, void *virtual)
  {
  	unsigned long flags;
  	struct page_address_slot *pas;
  	struct page_address_map *pam;
  
  	BUG_ON(!PageHighMem(page));
  
  	pas = page_slot(page);
  	if (virtual) {		/* Add */
  		BUG_ON(list_empty(&page_address_pool));
  
  		spin_lock_irqsave(&pool_lock, flags);
  		pam = list_entry(page_address_pool.next,
  				struct page_address_map, list);
  		list_del(&pam->list);
  		spin_unlock_irqrestore(&pool_lock, flags);
  
  		pam->page = page;
  		pam->virtual = virtual;
  
  		spin_lock_irqsave(&pas->lock, flags);
  		list_add_tail(&pam->list, &pas->lh);
  		spin_unlock_irqrestore(&pas->lock, flags);
  	} else {		/* Remove */
  		spin_lock_irqsave(&pas->lock, flags);
  		list_for_each_entry(pam, &pas->lh, list) {
  			if (pam->page == page) {
  				list_del(&pam->list);
  				spin_unlock_irqrestore(&pas->lock, flags);
  				spin_lock_irqsave(&pool_lock, flags);
  				list_add_tail(&pam->list, &page_address_pool);
  				spin_unlock_irqrestore(&pool_lock, flags);
  				goto done;
  			}
  		}
  		spin_unlock_irqrestore(&pas->lock, flags);
  	}
  done:
  	return;
  }
  
  static struct page_address_map page_address_maps[LAST_PKMAP];
  
  void __init page_address_init(void)
  {
  	int i;
  
  	INIT_LIST_HEAD(&page_address_pool);
  	for (i = 0; i < ARRAY_SIZE(page_address_maps); i++)
  		list_add(&page_address_maps[i].list, &page_address_pool);
  	for (i = 0; i < ARRAY_SIZE(page_address_htable); i++) {
  		INIT_LIST_HEAD(&page_address_htable[i].lh);
  		spin_lock_init(&page_address_htable[i].lock);
  	}
  	spin_lock_init(&pool_lock);
  }
  
  #endif	/* defined(CONFIG_HIGHMEM) && !defined(WANT_PAGE_VIRTUAL) */