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
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
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
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
|
/*
* Some of the code in this file has been gleaned from the 64 bit
* discontigmem support code base.
*
* Copyright (C) 2002, IBM Corp.
*
* All rights reserved.
*
* 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.
*
* 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, GOOD TITLE or
* NON INFRINGEMENT. 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, write to the Free Software
* Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
*
* Send feedback to Pat Gaughen <gone@us.ibm.com>
*/
#include <linux/config.h>
#include <linux/mm.h>
#include <linux/bootmem.h>
#include <linux/mmzone.h>
#include <linux/acpi.h>
#include <linux/nodemask.h>
#include <asm/srat.h>
#include <asm/topology.h>
/*
* proximity macros and definitions
*/
#define NODE_ARRAY_INDEX(x) ((x) / 8) /* 8 bits/char */
#define NODE_ARRAY_OFFSET(x) ((x) % 8) /* 8 bits/char */
#define BMAP_SET(bmap, bit) ((bmap)[NODE_ARRAY_INDEX(bit)] |= 1 << NODE_ARRAY_OFFSET(bit))
#define BMAP_TEST(bmap, bit) ((bmap)[NODE_ARRAY_INDEX(bit)] & (1 << NODE_ARRAY_OFFSET(bit)))
/* bitmap length; _PXM is at most 255 */
#define PXM_BITMAP_LEN (MAX_PXM_DOMAINS / 8)
static u8 pxm_bitmap[PXM_BITMAP_LEN]; /* bitmap of proximity domains */
#define MAX_CHUNKS_PER_NODE 4
#define MAXCHUNKS (MAX_CHUNKS_PER_NODE * MAX_NUMNODES)
struct node_memory_chunk_s {
unsigned long start_pfn;
unsigned long end_pfn;
u8 pxm; // proximity domain of node
u8 nid; // which cnode contains this chunk?
u8 bank; // which mem bank on this node
};
static struct node_memory_chunk_s node_memory_chunk[MAXCHUNKS];
static int num_memory_chunks; /* total number of memory chunks */
static int zholes_size_init;
static unsigned long zholes_size[MAX_NUMNODES * MAX_NR_ZONES];
extern void * boot_ioremap(unsigned long, unsigned long);
/* Identify CPU proximity domains */
static void __init parse_cpu_affinity_structure(char *p)
{
struct acpi_table_processor_affinity *cpu_affinity =
(struct acpi_table_processor_affinity *) p;
if (!cpu_affinity->flags.enabled)
return; /* empty entry */
/* mark this node as "seen" in node bitmap */
BMAP_SET(pxm_bitmap, cpu_affinity->proximity_domain);
printk("CPU 0x%02X in proximity domain 0x%02X\n",
cpu_affinity->apic_id, cpu_affinity->proximity_domain);
}
/*
* Identify memory proximity domains and hot-remove capabilities.
* Fill node memory chunk list structure.
*/
static void __init parse_memory_affinity_structure (char *sratp)
{
unsigned long long paddr, size;
unsigned long start_pfn, end_pfn;
u8 pxm;
struct node_memory_chunk_s *p, *q, *pend;
struct acpi_table_memory_affinity *memory_affinity =
(struct acpi_table_memory_affinity *) sratp;
if (!memory_affinity->flags.enabled)
return; /* empty entry */
/* mark this node as "seen" in node bitmap */
BMAP_SET(pxm_bitmap, memory_affinity->proximity_domain);
/* calculate info for memory chunk structure */
paddr = memory_affinity->base_addr_hi;
paddr = (paddr << 32) | memory_affinity->base_addr_lo;
size = memory_affinity->length_hi;
size = (size << 32) | memory_affinity->length_lo;
start_pfn = paddr >> PAGE_SHIFT;
end_pfn = (paddr + size) >> PAGE_SHIFT;
pxm = memory_affinity->proximity_domain;
if (num_memory_chunks >= MAXCHUNKS) {
printk("Too many mem chunks in SRAT. Ignoring %lld MBytes at %llx\n",
size/(1024*1024), paddr);
return;
}
/* Insertion sort based on base address */
pend = &node_memory_chunk[num_memory_chunks];
for (p = &node_memory_chunk[0]; p < pend; p++) {
if (start_pfn < p->start_pfn)
break;
}
if (p < pend) {
for (q = pend; q >= p; q--)
*(q + 1) = *q;
}
p->start_pfn = start_pfn;
p->end_pfn = end_pfn;
p->pxm = pxm;
num_memory_chunks++;
printk("Memory range 0x%lX to 0x%lX (type 0x%X) in proximity domain 0x%02X %s\n",
start_pfn, end_pfn,
memory_affinity->memory_type,
memory_affinity->proximity_domain,
(memory_affinity->flags.hot_pluggable ?
"enabled and removable" : "enabled" ) );
}
#if MAX_NR_ZONES != 4
#error "MAX_NR_ZONES != 4, chunk_to_zone requires review"
#endif
/* Take a chunk of pages from page frame cstart to cend and count the number
* of pages in each zone, returned via zones[].
*/
static __init void chunk_to_zones(unsigned long cstart, unsigned long cend,
unsigned long *zones)
{
unsigned long max_dma;
extern unsigned long max_low_pfn;
int z;
unsigned long rend;
/* FIXME: MAX_DMA_ADDRESS and max_low_pfn are trying to provide
* similarly scoped information and should be handled in a consistant
* manner.
*/
max_dma = virt_to_phys((char *)MAX_DMA_ADDRESS) >> PAGE_SHIFT;
/* Split the hole into the zones in which it falls. Repeatedly
* take the segment in which the remaining hole starts, round it
* to the end of that zone.
*/
memset(zones, 0, MAX_NR_ZONES * sizeof(long));
while (cstart < cend) {
if (cstart < max_dma) {
z = ZONE_DMA;
rend = (cend < max_dma)? cend : max_dma;
} else if (cstart < max_low_pfn) {
z = ZONE_NORMAL;
rend = (cend < max_low_pfn)? cend : max_low_pfn;
} else {
z = ZONE_HIGHMEM;
rend = cend;
}
zones[z] += rend - cstart;
cstart = rend;
}
}
/*
* The SRAT table always lists ascending addresses, so can always
* assume that the first "start" address that you see is the real
* start of the node, and that the current "end" address is after
* the previous one.
*/
static __init void node_read_chunk(int nid, struct node_memory_chunk_s *memory_chunk)
{
/*
* Only add present memory as told by the e820.
* There is no guarantee from the SRAT that the memory it
* enumerates is present at boot time because it represents
* *possible* memory hotplug areas the same as normal RAM.
*/
if (memory_chunk->start_pfn >= max_pfn) {
printk (KERN_INFO "Ignoring SRAT pfns: 0x%08lx -> %08lx\n",
memory_chunk->start_pfn, memory_chunk->end_pfn);
return;
}
if (memory_chunk->nid != nid)
return;
if (!node_has_online_mem(nid))
node_start_pfn[nid] = memory_chunk->start_pfn;
if (node_start_pfn[nid] > memory_chunk->start_pfn)
node_start_pfn[nid] = memory_chunk->start_pfn;
if (node_end_pfn[nid] < memory_chunk->end_pfn)
node_end_pfn[nid] = memory_chunk->end_pfn;
}
/* Parse the ACPI Static Resource Affinity Table */
static int __init acpi20_parse_srat(struct acpi_table_srat *sratp)
{
u8 *start, *end, *p;
int i, j, nid;
start = (u8 *)(&(sratp->reserved) + 1); /* skip header */
p = start;
end = (u8 *)sratp + sratp->header.length;
memset(pxm_bitmap, 0, sizeof(pxm_bitmap)); /* init proximity domain bitmap */
memset(node_memory_chunk, 0, sizeof(node_memory_chunk));
memset(zholes_size, 0, sizeof(zholes_size));
num_memory_chunks = 0;
while (p < end) {
switch (*p) {
case ACPI_SRAT_PROCESSOR_AFFINITY:
parse_cpu_affinity_structure(p);
break;
case ACPI_SRAT_MEMORY_AFFINITY:
parse_memory_affinity_structure(p);
break;
default:
printk("ACPI 2.0 SRAT: unknown entry skipped: type=0x%02X, len=%d\n", p[0], p[1]);
break;
}
p += p[1];
if (p[1] == 0) {
printk("acpi20_parse_srat: Entry length value is zero;"
" can't parse any further!\n");
break;
}
}
if (num_memory_chunks == 0) {
printk("could not finy any ACPI SRAT memory areas.\n");
goto out_fail;
}
/* Calculate total number of nodes in system from PXM bitmap and create
* a set of sequential node IDs starting at zero. (ACPI doesn't seem
* to specify the range of _PXM values.)
*/
/*
* MCD - we no longer HAVE to number nodes sequentially. PXM domain
* numbers could go as high as 256, and MAX_NUMNODES for i386 is typically
* 32, so we will continue numbering them in this manner until MAX_NUMNODES
* approaches MAX_PXM_DOMAINS for i386.
*/
nodes_clear(node_online_map);
for (i = 0; i < MAX_PXM_DOMAINS; i++) {
if (BMAP_TEST(pxm_bitmap, i)) {
int nid =
|