blob: ebd125e968bed8657ca093e8b5cdee97cdb9a361 [file] [log] [blame]
Linus Torvalds1da177e2005-04-16 15:20:36 -07001/*
2 * Dynamic DMA mapping support for AMD Hammer.
3 *
4 * Use the integrated AGP GART in the Hammer northbridge as an IOMMU for PCI.
5 * This allows to use PCI devices that only support 32bit addresses on systems
6 * with more than 4GB.
7 *
8 * See Documentation/DMA-mapping.txt for the interface specification.
9 *
10 * Copyright 2002 Andi Kleen, SuSE Labs.
11 */
12
13#include <linux/config.h>
14#include <linux/types.h>
15#include <linux/ctype.h>
16#include <linux/agp_backend.h>
17#include <linux/init.h>
18#include <linux/mm.h>
19#include <linux/string.h>
20#include <linux/spinlock.h>
21#include <linux/pci.h>
22#include <linux/module.h>
23#include <linux/topology.h>
24#include <linux/interrupt.h>
25#include <linux/bitops.h>
26#include <asm/atomic.h>
27#include <asm/io.h>
28#include <asm/mtrr.h>
29#include <asm/pgtable.h>
30#include <asm/proto.h>
31#include <asm/cacheflush.h>
32#include <asm/kdebug.h>
Muli Ben-Yehuda17a941d2006-01-11 22:44:42 +010033#include <asm/swiotlb.h>
34#include <asm/dma.h>
Linus Torvalds1da177e2005-04-16 15:20:36 -070035
36unsigned long iommu_bus_base; /* GART remapping area (physical) */
37static unsigned long iommu_size; /* size of remapping area bytes */
38static unsigned long iommu_pages; /* .. and in pages */
39
40u32 *iommu_gatt_base; /* Remapping table */
41
Linus Torvalds1da177e2005-04-16 15:20:36 -070042/* If this is disabled the IOMMU will use an optimized flushing strategy
43 of only flushing when an mapping is reused. With it true the GART is flushed
44 for every mapping. Problem is that doing the lazy flush seems to trigger
45 bugs with some popular PCI cards, in particular 3ware (but has been also
46 also seen with Qlogic at least). */
47int iommu_fullflush = 1;
48
Linus Torvalds1da177e2005-04-16 15:20:36 -070049#define MAX_NB 8
50
51/* Allocation bitmap for the remapping area */
52static DEFINE_SPINLOCK(iommu_bitmap_lock);
53static unsigned long *iommu_gart_bitmap; /* guarded by iommu_bitmap_lock */
54
55static u32 gart_unmapped_entry;
56
57#define GPTE_VALID 1
58#define GPTE_COHERENT 2
59#define GPTE_ENCODE(x) \
60 (((x) & 0xfffff000) | (((x) >> 32) << 4) | GPTE_VALID | GPTE_COHERENT)
61#define GPTE_DECODE(x) (((x) & 0xfffff000) | (((u64)(x) & 0xff0) << 28))
62
63#define to_pages(addr,size) \
64 (round_up(((addr) & ~PAGE_MASK) + (size), PAGE_SIZE) >> PAGE_SHIFT)
65
66#define for_all_nb(dev) \
67 dev = NULL; \
68 while ((dev = pci_get_device(PCI_VENDOR_ID_AMD, 0x1103, dev))!=NULL)\
69 if (dev->bus->number == 0 && \
70 (PCI_SLOT(dev->devfn) >= 24) && (PCI_SLOT(dev->devfn) <= 31))
71
72static struct pci_dev *northbridges[MAX_NB];
73static u32 northbridge_flush_word[MAX_NB];
74
75#define EMERGENCY_PAGES 32 /* = 128KB */
76
77#ifdef CONFIG_AGP
78#define AGPEXTERN extern
79#else
80#define AGPEXTERN
81#endif
82
83/* backdoor interface to AGP driver */
84AGPEXTERN int agp_memory_reserved;
85AGPEXTERN __u32 *agp_gatt_table;
86
87static unsigned long next_bit; /* protected by iommu_bitmap_lock */
88static int need_flush; /* global flush state. set for each gart wrap */
Linus Torvalds1da177e2005-04-16 15:20:36 -070089
90static unsigned long alloc_iommu(int size)
91{
92 unsigned long offset, flags;
93
94 spin_lock_irqsave(&iommu_bitmap_lock, flags);
95 offset = find_next_zero_string(iommu_gart_bitmap,next_bit,iommu_pages,size);
96 if (offset == -1) {
97 need_flush = 1;
98 offset = find_next_zero_string(iommu_gart_bitmap,0,next_bit,size);
99 }
100 if (offset != -1) {
101 set_bit_string(iommu_gart_bitmap, offset, size);
102 next_bit = offset+size;
103 if (next_bit >= iommu_pages) {
104 next_bit = 0;
105 need_flush = 1;
106 }
107 }
108 if (iommu_fullflush)
109 need_flush = 1;
110 spin_unlock_irqrestore(&iommu_bitmap_lock, flags);
111 return offset;
112}
113
114static void free_iommu(unsigned long offset, int size)
115{
116 unsigned long flags;
117 if (size == 1) {
118 clear_bit(offset, iommu_gart_bitmap);
119 return;
120 }
121 spin_lock_irqsave(&iommu_bitmap_lock, flags);
122 __clear_bit_string(iommu_gart_bitmap, offset, size);
123 spin_unlock_irqrestore(&iommu_bitmap_lock, flags);
124}
125
126/*
127 * Use global flush state to avoid races with multiple flushers.
128 */
129static void flush_gart(struct device *dev)
130{
131 unsigned long flags;
132 int flushed = 0;
133 int i, max;
134
135 spin_lock_irqsave(&iommu_bitmap_lock, flags);
136 if (need_flush) {
137 max = 0;
138 for (i = 0; i < MAX_NB; i++) {
139 if (!northbridges[i])
140 continue;
141 pci_write_config_dword(northbridges[i], 0x9c,
142 northbridge_flush_word[i] | 1);
143 flushed++;
144 max = i;
145 }
146 for (i = 0; i <= max; i++) {
147 u32 w;
148 if (!northbridges[i])
149 continue;
150 /* Make sure the hardware actually executed the flush. */
Andi Kleen85f9eebc2006-03-25 16:29:37 +0100151 for (;;) {
Linus Torvalds1da177e2005-04-16 15:20:36 -0700152 pci_read_config_dword(northbridges[i], 0x9c, &w);
Andi Kleen85f9eebc2006-03-25 16:29:37 +0100153 if (!(w & 1))
154 break;
155 cpu_relax();
156 }
Linus Torvalds1da177e2005-04-16 15:20:36 -0700157 }
158 if (!flushed)
159 printk("nothing to flush?\n");
160 need_flush = 0;
161 }
162 spin_unlock_irqrestore(&iommu_bitmap_lock, flags);
163}
164
Linus Torvalds1da177e2005-04-16 15:20:36 -0700165
Linus Torvalds1da177e2005-04-16 15:20:36 -0700166
167#ifdef CONFIG_IOMMU_LEAK
168
169#define SET_LEAK(x) if (iommu_leak_tab) \
170 iommu_leak_tab[x] = __builtin_return_address(0);
171#define CLEAR_LEAK(x) if (iommu_leak_tab) \
172 iommu_leak_tab[x] = NULL;
173
174/* Debugging aid for drivers that don't free their IOMMU tables */
175static void **iommu_leak_tab;
176static int leak_trace;
177int iommu_leak_pages = 20;
178void dump_leak(void)
179{
180 int i;
181 static int dump;
182 if (dump || !iommu_leak_tab) return;
183 dump = 1;
184 show_stack(NULL,NULL);
185 /* Very crude. dump some from the end of the table too */
186 printk("Dumping %d pages from end of IOMMU:\n", iommu_leak_pages);
187 for (i = 0; i < iommu_leak_pages; i+=2) {
188 printk("%lu: ", iommu_pages-i);
189 printk_address((unsigned long) iommu_leak_tab[iommu_pages-i]);
190 printk("%c", (i+1)%2 == 0 ? '\n' : ' ');
191 }
192 printk("\n");
193}
194#else
195#define SET_LEAK(x)
196#define CLEAR_LEAK(x)
197#endif
198
Muli Ben-Yehuda17a941d2006-01-11 22:44:42 +0100199static void iommu_full(struct device *dev, size_t size, int dir)
Linus Torvalds1da177e2005-04-16 15:20:36 -0700200{
201 /*
202 * Ran out of IOMMU space for this operation. This is very bad.
203 * Unfortunately the drivers cannot handle this operation properly.
204 * Return some non mapped prereserved space in the aperture and
205 * let the Northbridge deal with it. This will result in garbage
206 * in the IO operation. When the size exceeds the prereserved space
207 * memory corruption will occur or random memory will be DMAed
208 * out. Hopefully no network devices use single mappings that big.
209 */
210
211 printk(KERN_ERR
212 "PCI-DMA: Out of IOMMU space for %lu bytes at device %s\n",
213 size, dev->bus_id);
214
Muli Ben-Yehuda17a941d2006-01-11 22:44:42 +0100215 if (size > PAGE_SIZE*EMERGENCY_PAGES) {
Linus Torvalds1da177e2005-04-16 15:20:36 -0700216 if (dir == PCI_DMA_FROMDEVICE || dir == PCI_DMA_BIDIRECTIONAL)
217 panic("PCI-DMA: Memory would be corrupted\n");
218 if (dir == PCI_DMA_TODEVICE || dir == PCI_DMA_BIDIRECTIONAL)
Muli Ben-Yehuda17a941d2006-01-11 22:44:42 +0100219 panic(KERN_ERR "PCI-DMA: Random memory would be DMAed\n");
Linus Torvalds1da177e2005-04-16 15:20:36 -0700220 }
221
222#ifdef CONFIG_IOMMU_LEAK
223 dump_leak();
224#endif
225}
226
227static inline int need_iommu(struct device *dev, unsigned long addr, size_t size)
228{
229 u64 mask = *dev->dma_mask;
230 int high = addr + size >= mask;
231 int mmu = high;
232 if (force_iommu)
233 mmu = 1;
Linus Torvalds1da177e2005-04-16 15:20:36 -0700234 return mmu;
235}
236
237static inline int nonforced_iommu(struct device *dev, unsigned long addr, size_t size)
238{
239 u64 mask = *dev->dma_mask;
240 int high = addr + size >= mask;
241 int mmu = high;
Linus Torvalds1da177e2005-04-16 15:20:36 -0700242 return mmu;
243}
244
245/* Map a single continuous physical area into the IOMMU.
246 * Caller needs to check if the iommu is needed and flush.
247 */
Muli Ben-Yehuda17a941d2006-01-11 22:44:42 +0100248static dma_addr_t dma_map_area(struct device *dev, dma_addr_t phys_mem,
249 size_t size, int dir)
Linus Torvalds1da177e2005-04-16 15:20:36 -0700250{
251 unsigned long npages = to_pages(phys_mem, size);
252 unsigned long iommu_page = alloc_iommu(npages);
253 int i;
254 if (iommu_page == -1) {
255 if (!nonforced_iommu(dev, phys_mem, size))
256 return phys_mem;
257 if (panic_on_overflow)
258 panic("dma_map_area overflow %lu bytes\n", size);
Muli Ben-Yehuda17a941d2006-01-11 22:44:42 +0100259 iommu_full(dev, size, dir);
Linus Torvalds1da177e2005-04-16 15:20:36 -0700260 return bad_dma_address;
261 }
262
263 for (i = 0; i < npages; i++) {
264 iommu_gatt_base[iommu_page + i] = GPTE_ENCODE(phys_mem);
265 SET_LEAK(iommu_page + i);
266 phys_mem += PAGE_SIZE;
267 }
268 return iommu_bus_base + iommu_page*PAGE_SIZE + (phys_mem & ~PAGE_MASK);
269}
270
Muli Ben-Yehuda17a941d2006-01-11 22:44:42 +0100271static dma_addr_t gart_map_simple(struct device *dev, char *buf,
272 size_t size, int dir)
273{
274 dma_addr_t map = dma_map_area(dev, virt_to_bus(buf), size, dir);
275 flush_gart(dev);
276 return map;
277}
278
Linus Torvalds1da177e2005-04-16 15:20:36 -0700279/* Map a single area into the IOMMU */
Muli Ben-Yehuda17a941d2006-01-11 22:44:42 +0100280dma_addr_t gart_map_single(struct device *dev, void *addr, size_t size, int dir)
Linus Torvalds1da177e2005-04-16 15:20:36 -0700281{
282 unsigned long phys_mem, bus;
283
284 BUG_ON(dir == DMA_NONE);
285
Linus Torvalds1da177e2005-04-16 15:20:36 -0700286 if (!dev)
287 dev = &fallback_dev;
288
289 phys_mem = virt_to_phys(addr);
290 if (!need_iommu(dev, phys_mem, size))
291 return phys_mem;
292
Muli Ben-Yehuda17a941d2006-01-11 22:44:42 +0100293 bus = gart_map_simple(dev, addr, size, dir);
Linus Torvalds1da177e2005-04-16 15:20:36 -0700294 return bus;
Muli Ben-Yehuda17a941d2006-01-11 22:44:42 +0100295}
296
297/*
298 * Wrapper for pci_unmap_single working with scatterlists.
299 */
300void gart_unmap_sg(struct device *dev, struct scatterlist *sg, int nents, int dir)
301{
302 int i;
303
304 for (i = 0; i < nents; i++) {
305 struct scatterlist *s = &sg[i];
Jon Mason60b08c62006-02-26 04:18:22 +0100306 if (!s->dma_length || !s->length)
Muli Ben-Yehuda17a941d2006-01-11 22:44:42 +0100307 break;
308 dma_unmap_single(dev, s->dma_address, s->dma_length, dir);
309 }
310}
Linus Torvalds1da177e2005-04-16 15:20:36 -0700311
312/* Fallback for dma_map_sg in case of overflow */
313static int dma_map_sg_nonforce(struct device *dev, struct scatterlist *sg,
314 int nents, int dir)
315{
316 int i;
317
318#ifdef CONFIG_IOMMU_DEBUG
319 printk(KERN_DEBUG "dma_map_sg overflow\n");
320#endif
321
322 for (i = 0; i < nents; i++ ) {
323 struct scatterlist *s = &sg[i];
324 unsigned long addr = page_to_phys(s->page) + s->offset;
325 if (nonforced_iommu(dev, addr, s->length)) {
Muli Ben-Yehuda17a941d2006-01-11 22:44:42 +0100326 addr = dma_map_area(dev, addr, s->length, dir);
Linus Torvalds1da177e2005-04-16 15:20:36 -0700327 if (addr == bad_dma_address) {
328 if (i > 0)
Muli Ben-Yehuda17a941d2006-01-11 22:44:42 +0100329 gart_unmap_sg(dev, sg, i, dir);
Linus Torvalds1da177e2005-04-16 15:20:36 -0700330 nents = 0;
331 sg[0].dma_length = 0;
332 break;
333 }
334 }
335 s->dma_address = addr;
336 s->dma_length = s->length;
337 }
338 flush_gart(dev);
339 return nents;
340}
341
342/* Map multiple scatterlist entries continuous into the first. */
343static int __dma_map_cont(struct scatterlist *sg, int start, int stopat,
344 struct scatterlist *sout, unsigned long pages)
345{
346 unsigned long iommu_start = alloc_iommu(pages);
347 unsigned long iommu_page = iommu_start;
348 int i;
349
350 if (iommu_start == -1)
351 return -1;
352
353 for (i = start; i < stopat; i++) {
354 struct scatterlist *s = &sg[i];
355 unsigned long pages, addr;
356 unsigned long phys_addr = s->dma_address;
357
358 BUG_ON(i > start && s->offset);
359 if (i == start) {
Jon Mason60b08c62006-02-26 04:18:22 +0100360 *sout = *s;
Linus Torvalds1da177e2005-04-16 15:20:36 -0700361 sout->dma_address = iommu_bus_base;
362 sout->dma_address += iommu_page*PAGE_SIZE + s->offset;
363 sout->dma_length = s->length;
364 } else {
365 sout->dma_length += s->length;
366 }
367
368 addr = phys_addr;
369 pages = to_pages(s->offset, s->length);
370 while (pages--) {
371 iommu_gatt_base[iommu_page] = GPTE_ENCODE(addr);
372 SET_LEAK(iommu_page);
373 addr += PAGE_SIZE;
374 iommu_page++;
Andi Kleen0d5410642006-02-12 14:34:59 -0800375 }
Linus Torvalds1da177e2005-04-16 15:20:36 -0700376 }
377 BUG_ON(iommu_page - iommu_start != pages);
378 return 0;
379}
380
381static inline int dma_map_cont(struct scatterlist *sg, int start, int stopat,
382 struct scatterlist *sout,
383 unsigned long pages, int need)
384{
385 if (!need) {
386 BUG_ON(stopat - start != 1);
Jon Mason60b08c62006-02-26 04:18:22 +0100387 *sout = sg[start];
Linus Torvalds1da177e2005-04-16 15:20:36 -0700388 sout->dma_length = sg[start].length;
389 return 0;
390 }
391 return __dma_map_cont(sg, start, stopat, sout, pages);
392}
393
394/*
395 * DMA map all entries in a scatterlist.
396 * Merge chunks that have page aligned sizes into a continuous mapping.
397 */
Muli Ben-Yehuda17a941d2006-01-11 22:44:42 +0100398int gart_map_sg(struct device *dev, struct scatterlist *sg, int nents, int dir)
Linus Torvalds1da177e2005-04-16 15:20:36 -0700399{
400 int i;
401 int out;
402 int start;
403 unsigned long pages = 0;
404 int need = 0, nextneed;
405
406 BUG_ON(dir == DMA_NONE);
407 if (nents == 0)
408 return 0;
409
Linus Torvalds1da177e2005-04-16 15:20:36 -0700410 if (!dev)
411 dev = &fallback_dev;
412
413 out = 0;
414 start = 0;
415 for (i = 0; i < nents; i++) {
416 struct scatterlist *s = &sg[i];
417 dma_addr_t addr = page_to_phys(s->page) + s->offset;
418 s->dma_address = addr;
419 BUG_ON(s->length == 0);
420
421 nextneed = need_iommu(dev, addr, s->length);
422
423 /* Handle the previous not yet processed entries */
424 if (i > start) {
425 struct scatterlist *ps = &sg[i-1];
426 /* Can only merge when the last chunk ends on a page
427 boundary and the new one doesn't have an offset. */
428 if (!iommu_merge || !nextneed || !need || s->offset ||
429 (ps->offset + ps->length) % PAGE_SIZE) {
430 if (dma_map_cont(sg, start, i, sg+out, pages,
431 need) < 0)
432 goto error;
433 out++;
434 pages = 0;
435 start = i;
436 }
437 }
438
439 need = nextneed;
440 pages += to_pages(s->offset, s->length);
441 }
442 if (dma_map_cont(sg, start, i, sg+out, pages, need) < 0)
443 goto error;
444 out++;
445 flush_gart(dev);
446 if (out < nents)
447 sg[out].dma_length = 0;
448 return out;
449
450error:
451 flush_gart(NULL);
Muli Ben-Yehuda17a941d2006-01-11 22:44:42 +0100452 gart_unmap_sg(dev, sg, nents, dir);
Kevin VanMarena1002a42006-02-03 21:51:32 +0100453 /* When it was forced or merged try again in a dumb way */
454 if (force_iommu || iommu_merge) {
455 out = dma_map_sg_nonforce(dev, sg, nents, dir);
456 if (out > 0)
457 return out;
458 }
Linus Torvalds1da177e2005-04-16 15:20:36 -0700459 if (panic_on_overflow)
460 panic("dma_map_sg: overflow on %lu pages\n", pages);
Muli Ben-Yehuda17a941d2006-01-11 22:44:42 +0100461 iommu_full(dev, pages << PAGE_SHIFT, dir);
Linus Torvalds1da177e2005-04-16 15:20:36 -0700462 for (i = 0; i < nents; i++)
463 sg[i].dma_address = bad_dma_address;
464 return 0;
465}
466
467/*
468 * Free a DMA mapping.
469 */
Muli Ben-Yehuda17a941d2006-01-11 22:44:42 +0100470void gart_unmap_single(struct device *dev, dma_addr_t dma_addr,
Linus Torvalds1da177e2005-04-16 15:20:36 -0700471 size_t size, int direction)
472{
473 unsigned long iommu_page;
474 int npages;
475 int i;
476
Linus Torvalds1da177e2005-04-16 15:20:36 -0700477 if (dma_addr < iommu_bus_base + EMERGENCY_PAGES*PAGE_SIZE ||
478 dma_addr >= iommu_bus_base + iommu_size)
479 return;
480 iommu_page = (dma_addr - iommu_bus_base)>>PAGE_SHIFT;
481 npages = to_pages(dma_addr, size);
482 for (i = 0; i < npages; i++) {
483 iommu_gatt_base[iommu_page + i] = gart_unmapped_entry;
484 CLEAR_LEAK(iommu_page + i);
485 }
486 free_iommu(iommu_page, npages);
487}
488
Muli Ben-Yehuda17a941d2006-01-11 22:44:42 +0100489static int no_agp;
Linus Torvalds1da177e2005-04-16 15:20:36 -0700490
491static __init unsigned long check_iommu_size(unsigned long aper, u64 aper_size)
492{
493 unsigned long a;
494 if (!iommu_size) {
495 iommu_size = aper_size;
496 if (!no_agp)
497 iommu_size /= 2;
498 }
499
500 a = aper + iommu_size;
501 iommu_size -= round_up(a, LARGE_PAGE_SIZE) - a;
502
503 if (iommu_size < 64*1024*1024)
504 printk(KERN_WARNING
505 "PCI-DMA: Warning: Small IOMMU %luMB. Consider increasing the AGP aperture in BIOS\n",iommu_size>>20);
506
507 return iommu_size;
508}
509
510static __init unsigned read_aperture(struct pci_dev *dev, u32 *size)
511{
512 unsigned aper_size = 0, aper_base_32;
513 u64 aper_base;
514 unsigned aper_order;
515
516 pci_read_config_dword(dev, 0x94, &aper_base_32);
517 pci_read_config_dword(dev, 0x90, &aper_order);
518 aper_order = (aper_order >> 1) & 7;
519
520 aper_base = aper_base_32 & 0x7fff;
521 aper_base <<= 25;
522
523 aper_size = (32 * 1024 * 1024) << aper_order;
524 if (aper_base + aper_size >= 0xffffffff || !aper_size)
525 aper_base = 0;
526
527 *size = aper_size;
528 return aper_base;
529}
530
531/*
532 * Private Northbridge GATT initialization in case we cannot use the
533 * AGP driver for some reason.
534 */
535static __init int init_k8_gatt(struct agp_kern_info *info)
536{
537 struct pci_dev *dev;
538 void *gatt;
539 unsigned aper_base, new_aper_base;
540 unsigned aper_size, gatt_size, new_aper_size;
541
542 printk(KERN_INFO "PCI-DMA: Disabling AGP.\n");
543 aper_size = aper_base = info->aper_size = 0;
544 for_all_nb(dev) {
545 new_aper_base = read_aperture(dev, &new_aper_size);
546 if (!new_aper_base)
547 goto nommu;
548
549 if (!aper_base) {
550 aper_size = new_aper_size;
551 aper_base = new_aper_base;
552 }
553 if (aper_size != new_aper_size || aper_base != new_aper_base)
554 goto nommu;
555 }
556 if (!aper_base)
557 goto nommu;
558 info->aper_base = aper_base;
559 info->aper_size = aper_size>>20;
560
561 gatt_size = (aper_size >> PAGE_SHIFT) * sizeof(u32);
562 gatt = (void *)__get_free_pages(GFP_KERNEL, get_order(gatt_size));
563 if (!gatt)
564 panic("Cannot allocate GATT table");
565 memset(gatt, 0, gatt_size);
566 agp_gatt_table = gatt;
567
568 for_all_nb(dev) {
569 u32 ctl;
570 u32 gatt_reg;
571
572 gatt_reg = __pa(gatt) >> 12;
573 gatt_reg <<= 4;
574 pci_write_config_dword(dev, 0x98, gatt_reg);
575 pci_read_config_dword(dev, 0x90, &ctl);
576
577 ctl |= 1;
578 ctl &= ~((1<<4) | (1<<5));
579
580 pci_write_config_dword(dev, 0x90, ctl);
581 }
582 flush_gart(NULL);
583
584 printk("PCI-DMA: aperture base @ %x size %u KB\n",aper_base, aper_size>>10);
585 return 0;
586
587 nommu:
588 /* Should not happen anymore */
589 printk(KERN_ERR "PCI-DMA: More than 4GB of RAM and no IOMMU\n"
Andi Kleenf46ace62006-01-11 22:43:27 +0100590 KERN_ERR "PCI-DMA: 32bit PCI IO may malfunction.\n");
Linus Torvalds1da177e2005-04-16 15:20:36 -0700591 return -1;
592}
593
594extern int agp_amd64_init(void);
595
Muli Ben-Yehuda17a941d2006-01-11 22:44:42 +0100596static struct dma_mapping_ops gart_dma_ops = {
597 .mapping_error = NULL,
598 .map_single = gart_map_single,
599 .map_simple = gart_map_simple,
600 .unmap_single = gart_unmap_single,
601 .sync_single_for_cpu = NULL,
602 .sync_single_for_device = NULL,
603 .sync_single_range_for_cpu = NULL,
604 .sync_single_range_for_device = NULL,
605 .sync_sg_for_cpu = NULL,
606 .sync_sg_for_device = NULL,
607 .map_sg = gart_map_sg,
608 .unmap_sg = gart_unmap_sg,
609};
610
Linus Torvalds1da177e2005-04-16 15:20:36 -0700611static int __init pci_iommu_init(void)
612{
613 struct agp_kern_info info;
614 unsigned long aper_size;
615 unsigned long iommu_start;
616 struct pci_dev *dev;
617 unsigned long scratch;
618 long i;
619
620#ifndef CONFIG_AGP_AMD64
621 no_agp = 1;
622#else
623 /* Makefile puts PCI initialization via subsys_initcall first. */
624 /* Add other K8 AGP bridge drivers here */
625 no_agp = no_agp ||
626 (agp_amd64_init() < 0) ||
627 (agp_copy_info(agp_bridge, &info) < 0);
628#endif
629
Jon Mason60b08c62006-02-26 04:18:22 +0100630 if (swiotlb)
Linus Torvalds1da177e2005-04-16 15:20:36 -0700631 return -1;
Jon Mason60b08c62006-02-26 04:18:22 +0100632
Linus Torvalds1da177e2005-04-16 15:20:36 -0700633 if (no_iommu ||
Muli Ben-Yehuda17a941d2006-01-11 22:44:42 +0100634 (!force_iommu && end_pfn <= MAX_DMA32_PFN) ||
Linus Torvalds1da177e2005-04-16 15:20:36 -0700635 !iommu_aperture ||
636 (no_agp && init_k8_gatt(&info) < 0)) {
Jon Mason5b7b6442006-02-03 21:51:59 +0100637 printk(KERN_INFO "PCI-DMA: Disabling IOMMU.\n");
638 if (end_pfn > MAX_DMA32_PFN) {
639 printk(KERN_ERR "WARNING more than 4GB of memory "
640 "but IOMMU not compiled in.\n"
641 KERN_ERR "WARNING 32bit PCI may malfunction.\n"
642 KERN_ERR "You might want to enable "
643 "CONFIG_GART_IOMMU\n");
644 }
Linus Torvalds1da177e2005-04-16 15:20:36 -0700645 return -1;
646 }
647
Jon Mason5b7b6442006-02-03 21:51:59 +0100648 printk(KERN_INFO "PCI-DMA: using GART IOMMU.\n");
Linus Torvalds1da177e2005-04-16 15:20:36 -0700649 aper_size = info.aper_size * 1024 * 1024;
650 iommu_size = check_iommu_size(info.aper_base, aper_size);
651 iommu_pages = iommu_size >> PAGE_SHIFT;
652
653 iommu_gart_bitmap = (void*)__get_free_pages(GFP_KERNEL,
654 get_order(iommu_pages/8));
655 if (!iommu_gart_bitmap)
656 panic("Cannot allocate iommu bitmap\n");
657 memset(iommu_gart_bitmap, 0, iommu_pages/8);
658
659#ifdef CONFIG_IOMMU_LEAK
660 if (leak_trace) {
661 iommu_leak_tab = (void *)__get_free_pages(GFP_KERNEL,
662 get_order(iommu_pages*sizeof(void *)));
663 if (iommu_leak_tab)
664 memset(iommu_leak_tab, 0, iommu_pages * 8);
665 else
666 printk("PCI-DMA: Cannot allocate leak trace area\n");
667 }
668#endif
669
670 /*
671 * Out of IOMMU space handling.
672 * Reserve some invalid pages at the beginning of the GART.
673 */
674 set_bit_string(iommu_gart_bitmap, 0, EMERGENCY_PAGES);
675
676 agp_memory_reserved = iommu_size;
677 printk(KERN_INFO
678 "PCI-DMA: Reserving %luMB of IOMMU area in the AGP aperture\n",
679 iommu_size>>20);
680
681 iommu_start = aper_size - iommu_size;
682 iommu_bus_base = info.aper_base + iommu_start;
683 bad_dma_address = iommu_bus_base;
684 iommu_gatt_base = agp_gatt_table + (iommu_start>>PAGE_SHIFT);
685
686 /*
687 * Unmap the IOMMU part of the GART. The alias of the page is
688 * always mapped with cache enabled and there is no full cache
689 * coherency across the GART remapping. The unmapping avoids
690 * automatic prefetches from the CPU allocating cache lines in
691 * there. All CPU accesses are done via the direct mapping to
692 * the backing memory. The GART address is only used by PCI
693 * devices.
694 */
695 clear_kernel_mapping((unsigned long)__va(iommu_bus_base), iommu_size);
696
697 /*
698 * Try to workaround a bug (thanks to BenH)
699 * Set unmapped entries to a scratch page instead of 0.
700 * Any prefetches that hit unmapped entries won't get an bus abort
701 * then.
702 */
703 scratch = get_zeroed_page(GFP_KERNEL);
704 if (!scratch)
705 panic("Cannot allocate iommu scratch page");
706 gart_unmapped_entry = GPTE_ENCODE(__pa(scratch));
707 for (i = EMERGENCY_PAGES; i < iommu_pages; i++)
708 iommu_gatt_base[i] = gart_unmapped_entry;
709
710 for_all_nb(dev) {
711 u32 flag;
712 int cpu = PCI_SLOT(dev->devfn) - 24;
713 if (cpu >= MAX_NB)
714 continue;
715 northbridges[cpu] = dev;
716 pci_read_config_dword(dev, 0x9c, &flag); /* cache flush word */
717 northbridge_flush_word[cpu] = flag;
718 }
719
720 flush_gart(NULL);
721
Muli Ben-Yehuda17a941d2006-01-11 22:44:42 +0100722 dma_ops = &gart_dma_ops;
723
Linus Torvalds1da177e2005-04-16 15:20:36 -0700724 return 0;
725}
726
727/* Must execute after PCI subsystem */
728fs_initcall(pci_iommu_init);
729
Muli Ben-Yehuda17a941d2006-01-11 22:44:42 +0100730void gart_parse_options(char *p)
731{
732 int arg;
Linus Torvalds1da177e2005-04-16 15:20:36 -0700733
Linus Torvalds1da177e2005-04-16 15:20:36 -0700734#ifdef CONFIG_IOMMU_LEAK
Muli Ben-Yehuda17a941d2006-01-11 22:44:42 +0100735 if (!strncmp(p,"leak",4)) {
736 leak_trace = 1;
737 p += 4;
738 if (*p == '=') ++p;
739 if (isdigit(*p) && get_option(&p, &arg))
740 iommu_leak_pages = arg;
741 }
Linus Torvalds1da177e2005-04-16 15:20:36 -0700742#endif
Muli Ben-Yehuda17a941d2006-01-11 22:44:42 +0100743 if (isdigit(*p) && get_option(&p, &arg))
744 iommu_size = arg;
745 if (!strncmp(p, "fullflush",8))
746 iommu_fullflush = 1;
747 if (!strncmp(p, "nofullflush",11))
748 iommu_fullflush = 0;
749 if (!strncmp(p,"noagp",5))
750 no_agp = 1;
751 if (!strncmp(p, "noaperture",10))
752 fix_aperture = 0;
753 /* duplicated from pci-dma.c */
754 if (!strncmp(p,"force",5))
755 iommu_aperture_allowed = 1;
756 if (!strncmp(p,"allowed",7))
757 iommu_aperture_allowed = 1;
758 if (!strncmp(p, "memaper", 7)) {
759 fallback_aper_force = 1;
760 p += 7;
761 if (*p == '=') {
762 ++p;
763 if (get_option(&p, &arg))
764 fallback_aper_order = arg;
765 }
766 }
767}