1 /*
2 * linux/mm/bootmem.c
3 *
4 * Copyright (C) 1999 Ingo Molnar
5 * Discontiguous memory support, Kanoj Sarcar, SGI, Nov 1999
6 *
7 * simple boot-time physical memory area allocator and
8 * free memory collector. It's used to deal with reserved
9 * system memory and memory holes as well.
10 */
11
12 #include <linux/mm.h>
13 #include <linux/kernel_stat.h>
14 #include <linux/swap.h>
15 #include <linux/swapctl.h>
16 #include <linux/interrupt.h>
17 #include <linux/init.h>
18 #include <linux/bootmem.h>
19 #include <linux/mmzone.h>
20 #include <asm/dma.h>
21 #include <asm/io.h>
22
23 /*
24 * Access to this subsystem has to be serialized externally. (this is
25 * true for the boot process anyway)
26 */
27 unsigned long max_low_pfn;
28 unsigned long min_low_pfn;
29 unsigned long max_pfn;
30
31 /* return the number of _pages_ that will be allocated for the boot bitmap */
bootmem_bootmap_pages(unsigned long pages)32 unsigned long __init bootmem_bootmap_pages (unsigned long pages)
33 {
34 unsigned long mapsize;
35
36 mapsize = (pages+7)/8;
37 mapsize = (mapsize + ~PAGE_MASK) & PAGE_MASK;
38 mapsize >>= PAGE_SHIFT;
39
40 return mapsize;
41 }
42
43 /*
44 * Called once to set up the allocator itself.
45 */
init_bootmem_core(pg_data_t * pgdat,unsigned long mapstart,unsigned long start,unsigned long end)46 static unsigned long __init init_bootmem_core (pg_data_t *pgdat,
47 unsigned long mapstart, unsigned long start, unsigned long end)
48 {
49 bootmem_data_t *bdata = pgdat->bdata;
50 unsigned long mapsize = ((end - start)+7)/8;
51
52 pgdat->node_next = pgdat_list;
53 pgdat_list = pgdat;
54
55 mapsize = (mapsize + (sizeof(long) - 1UL)) & ~(sizeof(long) - 1UL);
56 bdata->node_bootmem_map = phys_to_virt(mapstart << PAGE_SHIFT);
57 bdata->node_boot_start = (start << PAGE_SHIFT);
58 bdata->node_low_pfn = end;
59
60 /*
61 * Initially all pages are reserved - setup_arch() has to
62 * register free RAM areas explicitly.
63 */
64 memset(bdata->node_bootmem_map, 0xff, mapsize);
65
66 return mapsize;
67 }
68
69 /*
70 * Marks a particular physical memory range as unallocatable. Usable RAM
71 * might be used for boot-time allocations - or it might get added
72 * to the free page pool later on.
73 */
reserve_bootmem_core(bootmem_data_t * bdata,unsigned long addr,unsigned long size)74 static void __init reserve_bootmem_core(bootmem_data_t *bdata, unsigned long addr, unsigned long size)
75 {
76 unsigned long i;
77 /*
78 * round up, partially reserved pages are considered
79 * fully reserved.
80 */
81 unsigned long sidx = (addr - bdata->node_boot_start)/PAGE_SIZE;
82 unsigned long eidx = (addr + size - bdata->node_boot_start +
83 PAGE_SIZE-1)/PAGE_SIZE;
84 unsigned long end = (addr + size + PAGE_SIZE-1)/PAGE_SIZE;
85
86 if (!size) BUG();
87
88 if (sidx < 0)
89 BUG();
90 if (eidx < 0)
91 BUG();
92 if (sidx >= eidx)
93 BUG();
94 if ((addr >> PAGE_SHIFT) >= bdata->node_low_pfn)
95 BUG();
96 if (end > bdata->node_low_pfn)
97 BUG();
98 for (i = sidx; i < eidx; i++)
99 if (test_and_set_bit(i, bdata->node_bootmem_map))
100 printk("hm, page %08lx reserved twice.\n", i*PAGE_SIZE);
101 }
102
free_bootmem_core(bootmem_data_t * bdata,unsigned long addr,unsigned long size)103 static void __init free_bootmem_core(bootmem_data_t *bdata, unsigned long addr, unsigned long size)
104 {
105 unsigned long i;
106 unsigned long start;
107 /*
108 * round down end of usable mem, partially free pages are
109 * considered reserved.
110 */
111 unsigned long sidx;
112 unsigned long eidx = (addr + size - bdata->node_boot_start)/PAGE_SIZE;
113 unsigned long end = (addr + size)/PAGE_SIZE;
114
115 if (!size) BUG();
116 if (end > bdata->node_low_pfn)
117 BUG();
118
119 /*
120 * Round up the beginning of the address.
121 */
122 start = (addr + PAGE_SIZE-1) / PAGE_SIZE;
123 sidx = start - (bdata->node_boot_start/PAGE_SIZE);
124
125 for (i = sidx; i < eidx; i++) {
126 if (!test_and_clear_bit(i, bdata->node_bootmem_map))
127 BUG();
128 }
129 }
130
131 /*
132 * We 'merge' subsequent allocations to save space. We might 'lose'
133 * some fraction of a page if allocations cannot be satisfied due to
134 * size constraints on boxes where there is physical RAM space
135 * fragmentation - in these cases * (mostly large memory boxes) this
136 * is not a problem.
137 *
138 * On low memory boxes we get it right in 100% of the cases.
139 */
140
141 /*
142 * alignment has to be a power of 2 value.
143 */
__alloc_bootmem_core(bootmem_data_t * bdata,unsigned long size,unsigned long align,unsigned long goal)144 static void * __init __alloc_bootmem_core (bootmem_data_t *bdata,
145 unsigned long size, unsigned long align, unsigned long goal)
146 {
147 unsigned long i, start = 0;
148 void *ret;
149 unsigned long offset, remaining_size;
150 unsigned long areasize, preferred, incr;
151 unsigned long eidx = bdata->node_low_pfn - (bdata->node_boot_start >>
152 PAGE_SHIFT);
153
154 if (!size) BUG();
155
156 if (align & (align-1))
157 BUG();
158
159 offset = 0;
160 if (align &&
161 (bdata->node_boot_start & (align - 1UL)) != 0)
162 offset = (align - (bdata->node_boot_start & (align - 1UL)));
163 offset >>= PAGE_SHIFT;
164
165 /*
166 * We try to allocate bootmem pages above 'goal'
167 * first, then we try to allocate lower pages.
168 */
169 if (goal && (goal >= bdata->node_boot_start) &&
170 ((goal >> PAGE_SHIFT) < bdata->node_low_pfn)) {
171 preferred = goal - bdata->node_boot_start;
172 } else
173 preferred = 0;
174
175 preferred = ((preferred + align - 1) & ~(align - 1)) >> PAGE_SHIFT;
176 preferred += offset;
177 areasize = (size+PAGE_SIZE-1)/PAGE_SIZE;
178 incr = align >> PAGE_SHIFT ? : 1;
179
180 restart_scan:
181 for (i = preferred; i < eidx; i += incr) {
182 unsigned long j;
183 if (test_bit(i, bdata->node_bootmem_map))
184 continue;
185 for (j = i + 1; j < i + areasize; ++j) {
186 if (j >= eidx)
187 goto fail_block;
188 if (test_bit (j, bdata->node_bootmem_map))
189 goto fail_block;
190 }
191 start = i;
192 goto found;
193 fail_block:;
194 }
195 if (preferred) {
196 preferred = offset;
197 goto restart_scan;
198 }
199 return NULL;
200 found:
201 if (start >= eidx)
202 BUG();
203
204 /*
205 * Is the next page of the previous allocation-end the start
206 * of this allocation's buffer? If yes then we can 'merge'
207 * the previous partial page with this allocation.
208 */
209 if (align <= PAGE_SIZE
210 && bdata->last_offset && bdata->last_pos+1 == start) {
211 offset = (bdata->last_offset+align-1) & ~(align-1);
212 if (offset > PAGE_SIZE)
213 BUG();
214 remaining_size = PAGE_SIZE-offset;
215 if (size < remaining_size) {
216 areasize = 0;
217 // last_pos unchanged
218 bdata->last_offset = offset+size;
219 ret = phys_to_virt(bdata->last_pos*PAGE_SIZE + offset +
220 bdata->node_boot_start);
221 } else {
222 remaining_size = size - remaining_size;
223 areasize = (remaining_size+PAGE_SIZE-1)/PAGE_SIZE;
224 ret = phys_to_virt(bdata->last_pos*PAGE_SIZE + offset +
225 bdata->node_boot_start);
226 bdata->last_pos = start+areasize-1;
227 bdata->last_offset = remaining_size;
228 }
229 bdata->last_offset &= ~PAGE_MASK;
230 } else {
231 bdata->last_pos = start + areasize - 1;
232 bdata->last_offset = size & ~PAGE_MASK;
233 ret = phys_to_virt(start * PAGE_SIZE + bdata->node_boot_start);
234 }
235 /*
236 * Reserve the area now:
237 */
238 for (i = start; i < start+areasize; i++)
239 if (test_and_set_bit(i, bdata->node_bootmem_map))
240 BUG();
241 memset(ret, 0, size);
242 return ret;
243 }
244
free_all_bootmem_core(pg_data_t * pgdat)245 static unsigned long __init free_all_bootmem_core(pg_data_t *pgdat)
246 {
247 struct page *page = pgdat->node_mem_map;
248 bootmem_data_t *bdata = pgdat->bdata;
249 unsigned long i, count, total = 0;
250 unsigned long idx;
251
252 if (!bdata->node_bootmem_map) BUG();
253
254 count = 0;
255 idx = bdata->node_low_pfn - (bdata->node_boot_start >> PAGE_SHIFT);
256 for (i = 0; i < idx; i++, page++) {
257 if (!test_bit(i, bdata->node_bootmem_map)) {
258 count++;
259 ClearPageReserved(page);
260 set_page_count(page, 1);
261 __free_page(page);
262 }
263 }
264 total += count;
265
266 /*
267 * Now free the allocator bitmap itself, it's not
268 * needed anymore:
269 */
270 page = virt_to_page(bdata->node_bootmem_map);
271 count = 0;
272 for (i = 0; i < ((bdata->node_low_pfn-(bdata->node_boot_start >> PAGE_SHIFT))/8 + PAGE_SIZE-1)/PAGE_SIZE; i++,page++) {
273 count++;
274 ClearPageReserved(page);
275 set_page_count(page, 1);
276 __free_page(page);
277 }
278 total += count;
279 bdata->node_bootmem_map = NULL;
280
281 return total;
282 }
283
init_bootmem_node(pg_data_t * pgdat,unsigned long freepfn,unsigned long startpfn,unsigned long endpfn)284 unsigned long __init init_bootmem_node (pg_data_t *pgdat, unsigned long freepfn, unsigned long startpfn, unsigned long endpfn)
285 {
286 return(init_bootmem_core(pgdat, freepfn, startpfn, endpfn));
287 }
288
reserve_bootmem_node(pg_data_t * pgdat,unsigned long physaddr,unsigned long size)289 void __init reserve_bootmem_node (pg_data_t *pgdat, unsigned long physaddr, unsigned long size)
290 {
291 reserve_bootmem_core(pgdat->bdata, physaddr, size);
292 }
293
free_bootmem_node(pg_data_t * pgdat,unsigned long physaddr,unsigned long size)294 void __init free_bootmem_node (pg_data_t *pgdat, unsigned long physaddr, unsigned long size)
295 {
296 return(free_bootmem_core(pgdat->bdata, physaddr, size));
297 }
298
free_all_bootmem_node(pg_data_t * pgdat)299 unsigned long __init free_all_bootmem_node (pg_data_t *pgdat)
300 {
301 return(free_all_bootmem_core(pgdat));
302 }
303
init_bootmem(unsigned long start,unsigned long pages)304 unsigned long __init init_bootmem (unsigned long start, unsigned long pages)
305 {
306 max_low_pfn = pages;
307 min_low_pfn = start;
308 return(init_bootmem_core(&contig_page_data, start, 0, pages));
309 }
310
reserve_bootmem(unsigned long addr,unsigned long size)311 void __init reserve_bootmem (unsigned long addr, unsigned long size)
312 {
313 reserve_bootmem_core(contig_page_data.bdata, addr, size);
314 }
315
free_bootmem(unsigned long addr,unsigned long size)316 void __init free_bootmem (unsigned long addr, unsigned long size)
317 {
318 return(free_bootmem_core(contig_page_data.bdata, addr, size));
319 }
320
free_all_bootmem(void)321 unsigned long __init free_all_bootmem (void)
322 {
323 return(free_all_bootmem_core(&contig_page_data));
324 }
325
__alloc_bootmem(unsigned long size,unsigned long align,unsigned long goal)326 void * __init __alloc_bootmem (unsigned long size, unsigned long align, unsigned long goal)
327 {
328 pg_data_t *pgdat;
329 void *ptr;
330
331 for_each_pgdat(pgdat)
332 if ((ptr = __alloc_bootmem_core(pgdat->bdata, size,
333 align, goal)))
334 return(ptr);
335
336 /*
337 * Whoops, we cannot satisfy the allocation request.
338 */
339 printk(KERN_ALERT "bootmem alloc of %lu bytes failed!\n", size);
340 panic("Out of memory");
341 return NULL;
342 }
343
__alloc_bootmem_node(pg_data_t * pgdat,unsigned long size,unsigned long align,unsigned long goal)344 void * __init __alloc_bootmem_node (pg_data_t *pgdat, unsigned long size, unsigned long align, unsigned long goal)
345 {
346 void *ptr;
347
348 ptr = __alloc_bootmem_core(pgdat->bdata, size, align, goal);
349 if (ptr)
350 return (ptr);
351
352 /*
353 * Whoops, we cannot satisfy the allocation request.
354 */
355 printk(KERN_ALERT "bootmem alloc of %lu bytes failed!\n", size);
356 panic("Out of memory");
357 return NULL;
358 }
359
360