1// SPDX-License-Identifier: GPL-2.0-or-later
2/*
3 * Copyright (C) 2001 Mike Corrigan & Dave Engebretsen, IBM Corporation
4 *
5 * Rewrite, cleanup:
6 *
7 * Copyright (C) 2004 Olof Johansson <olof@lixom.net>, IBM Corporation
8 * Copyright (C) 2006 Olof Johansson <olof@lixom.net>
9 *
10 * Dynamic DMA mapping support, pSeries-specific parts, both SMP and LPAR.
11 */
12
13#include <linux/init.h>
14#include <linux/types.h>
15#include <linux/slab.h>
16#include <linux/mm.h>
17#include <linux/memblock.h>
18#include <linux/spinlock.h>
19#include <linux/string.h>
20#include <linux/pci.h>
21#include <linux/dma-mapping.h>
22#include <linux/crash_dump.h>
23#include <linux/memory.h>
24#include <linux/of.h>
25#include <linux/iommu.h>
26#include <linux/rculist.h>
27#include <asm/io.h>
28#include <asm/prom.h>
29#include <asm/rtas.h>
30#include <asm/iommu.h>
31#include <asm/pci-bridge.h>
32#include <asm/machdep.h>
33#include <asm/firmware.h>
34#include <asm/tce.h>
35#include <asm/ppc-pci.h>
36#include <asm/udbg.h>
37#include <asm/mmzone.h>
38#include <asm/plpar_wrappers.h>
39
40#include "pseries.h"
41
42enum {
43	DDW_QUERY_PE_DMA_WIN  = 0,
44	DDW_CREATE_PE_DMA_WIN = 1,
45	DDW_REMOVE_PE_DMA_WIN = 2,
46
47	DDW_APPLICABLE_SIZE
48};
49
50enum {
51	DDW_EXT_SIZE = 0,
52	DDW_EXT_RESET_DMA_WIN = 1,
53	DDW_EXT_QUERY_OUT_SIZE = 2
54};
55
56static struct iommu_table_group *iommu_pseries_alloc_group(int node)
57{
58	struct iommu_table_group *table_group;
59	struct iommu_table *tbl;
60
61	table_group = kzalloc_node(sizeof(struct iommu_table_group), GFP_KERNEL,
62			   node);
63	if (!table_group)
64		return NULL;
65
66	tbl = kzalloc_node(sizeof(struct iommu_table), GFP_KERNEL, node);
67	if (!tbl)
68		goto free_group;
69
70	INIT_LIST_HEAD_RCU(&tbl->it_group_list);
71	kref_init(&tbl->it_kref);
72
73	table_group->tables[0] = tbl;
74
75	return table_group;
76
77free_group:
78	kfree(table_group);
79	return NULL;
80}
81
82static void iommu_pseries_free_group(struct iommu_table_group *table_group,
83		const char *node_name)
84{
85	struct iommu_table *tbl;
86
87	if (!table_group)
88		return;
89
90	tbl = table_group->tables[0];
91#ifdef CONFIG_IOMMU_API
92	if (table_group->group) {
93		iommu_group_put(table_group->group);
94		BUG_ON(table_group->group);
95	}
96#endif
97	iommu_tce_table_put(tbl);
98
99	kfree(table_group);
100}
101
102static int tce_build_pSeries(struct iommu_table *tbl, long index,
103			      long npages, unsigned long uaddr,
104			      enum dma_data_direction direction,
105			      unsigned long attrs)
106{
107	u64 proto_tce;
108	__be64 *tcep;
109	u64 rpn;
110
111	proto_tce = TCE_PCI_READ; // Read allowed
112
113	if (direction != DMA_TO_DEVICE)
114		proto_tce |= TCE_PCI_WRITE;
115
116	tcep = ((__be64 *)tbl->it_base) + index;
117
118	while (npages--) {
119		/* can't move this out since we might cross MEMBLOCK boundary */
120		rpn = __pa(uaddr) >> TCE_SHIFT;
121		*tcep = cpu_to_be64(proto_tce | (rpn & TCE_RPN_MASK) << TCE_RPN_SHIFT);
122
123		uaddr += TCE_PAGE_SIZE;
124		tcep++;
125	}
126	return 0;
127}
128
129
130static void tce_free_pSeries(struct iommu_table *tbl, long index, long npages)
131{
132	__be64 *tcep;
133
134	tcep = ((__be64 *)tbl->it_base) + index;
135
136	while (npages--)
137		*(tcep++) = 0;
138}
139
140static unsigned long tce_get_pseries(struct iommu_table *tbl, long index)
141{
142	__be64 *tcep;
143
144	tcep = ((__be64 *)tbl->it_base) + index;
145
146	return be64_to_cpu(*tcep);
147}
148
149static void tce_free_pSeriesLP(unsigned long liobn, long, long);
150static void tce_freemulti_pSeriesLP(struct iommu_table*, long, long);
151
152static int tce_build_pSeriesLP(unsigned long liobn, long tcenum, long tceshift,
153				long npages, unsigned long uaddr,
154				enum dma_data_direction direction,
155				unsigned long attrs)
156{
157	u64 rc = 0;
158	u64 proto_tce, tce;
159	u64 rpn;
160	int ret = 0;
161	long tcenum_start = tcenum, npages_start = npages;
162
163	rpn = __pa(uaddr) >> tceshift;
164	proto_tce = TCE_PCI_READ;
165	if (direction != DMA_TO_DEVICE)
166		proto_tce |= TCE_PCI_WRITE;
167
168	while (npages--) {
169		tce = proto_tce | (rpn & TCE_RPN_MASK) << tceshift;
170		rc = plpar_tce_put((u64)liobn, (u64)tcenum << tceshift, tce);
171
172		if (unlikely(rc == H_NOT_ENOUGH_RESOURCES)) {
173			ret = (int)rc;
174			tce_free_pSeriesLP(liobn, tcenum_start,
175			                   (npages_start - (npages + 1)));
176			break;
177		}
178
179		if (rc && printk_ratelimit()) {
180			printk("tce_build_pSeriesLP: plpar_tce_put failed. rc=%lld\n", rc);
181			printk("\tindex   = 0x%llx\n", (u64)liobn);
182			printk("\ttcenum  = 0x%llx\n", (u64)tcenum);
183			printk("\ttce val = 0x%llx\n", tce );
184			dump_stack();
185		}
186
187		tcenum++;
188		rpn++;
189	}
190	return ret;
191}
192
193static DEFINE_PER_CPU(__be64 *, tce_page);
194
195static int tce_buildmulti_pSeriesLP(struct iommu_table *tbl, long tcenum,
196				     long npages, unsigned long uaddr,
197				     enum dma_data_direction direction,
198				     unsigned long attrs)
199{
200	u64 rc = 0;
201	u64 proto_tce;
202	__be64 *tcep;
203	u64 rpn;
204	long l, limit;
205	long tcenum_start = tcenum, npages_start = npages;
206	int ret = 0;
207	unsigned long flags;
208
209	if ((npages == 1) || !firmware_has_feature(FW_FEATURE_PUT_TCE_IND)) {
210		return tce_build_pSeriesLP(tbl->it_index, tcenum,
211					   tbl->it_page_shift, npages, uaddr,
212		                           direction, attrs);
213	}
214
215	local_irq_save(flags);	/* to protect tcep and the page behind it */
216
217	tcep = __this_cpu_read(tce_page);
218
219	/* This is safe to do since interrupts are off when we're called
220	 * from iommu_alloc{,_sg}()
221	 */
222	if (!tcep) {
223		tcep = (__be64 *)__get_free_page(GFP_ATOMIC);
224		/* If allocation fails, fall back to the loop implementation */
225		if (!tcep) {
226			local_irq_restore(flags);
227			return tce_build_pSeriesLP(tbl->it_index, tcenum,
228					tbl->it_page_shift,
229					npages, uaddr, direction, attrs);
230		}
231		__this_cpu_write(tce_page, tcep);
232	}
233
234	rpn = __pa(uaddr) >> TCE_SHIFT;
235	proto_tce = TCE_PCI_READ;
236	if (direction != DMA_TO_DEVICE)
237		proto_tce |= TCE_PCI_WRITE;
238
239	/* We can map max one pageful of TCEs at a time */
240	do {
241		/*
242		 * Set up the page with TCE data, looping through and setting
243		 * the values.
244		 */
245		limit = min_t(long, npages, 4096/TCE_ENTRY_SIZE);
246
247		for (l = 0; l < limit; l++) {
248			tcep[l] = cpu_to_be64(proto_tce | (rpn & TCE_RPN_MASK) << TCE_RPN_SHIFT);
249			rpn++;
250		}
251
252		rc = plpar_tce_put_indirect((u64)tbl->it_index,
253					    (u64)tcenum << 12,
254					    (u64)__pa(tcep),
255					    limit);
256
257		npages -= limit;
258		tcenum += limit;
259	} while (npages > 0 && !rc);
260
261	local_irq_restore(flags);
262
263	if (unlikely(rc == H_NOT_ENOUGH_RESOURCES)) {
264		ret = (int)rc;
265		tce_freemulti_pSeriesLP(tbl, tcenum_start,
266		                        (npages_start - (npages + limit)));
267		return ret;
268	}
269
270	if (rc && printk_ratelimit()) {
271		printk("tce_buildmulti_pSeriesLP: plpar_tce_put failed. rc=%lld\n", rc);
272		printk("\tindex   = 0x%llx\n", (u64)tbl->it_index);
273		printk("\tnpages  = 0x%llx\n", (u64)npages);
274		printk("\ttce[0] val = 0x%llx\n", tcep[0]);
275		dump_stack();
276	}
277	return ret;
278}
279
280static void tce_free_pSeriesLP(unsigned long liobn, long tcenum, long npages)
281{
282	u64 rc;
283
284	while (npages--) {
285		rc = plpar_tce_put((u64)liobn, (u64)tcenum << 12, 0);
286
287		if (rc && printk_ratelimit()) {
288			printk("tce_free_pSeriesLP: plpar_tce_put failed. rc=%lld\n", rc);
289			printk("\tindex   = 0x%llx\n", (u64)liobn);
290			printk("\ttcenum  = 0x%llx\n", (u64)tcenum);
291			dump_stack();
292		}
293
294		tcenum++;
295	}
296}
297
298
299static void tce_freemulti_pSeriesLP(struct iommu_table *tbl, long tcenum, long npages)
300{
301	u64 rc;
302
303	if (!firmware_has_feature(FW_FEATURE_STUFF_TCE))
304		return tce_free_pSeriesLP(tbl->it_index, tcenum, npages);
305
306	rc = plpar_tce_stuff((u64)tbl->it_index, (u64)tcenum << 12, 0, npages);
307
308	if (rc && printk_ratelimit()) {
309		printk("tce_freemulti_pSeriesLP: plpar_tce_stuff failed\n");
310		printk("\trc      = %lld\n", rc);
311		printk("\tindex   = 0x%llx\n", (u64)tbl->it_index);
312		printk("\tnpages  = 0x%llx\n", (u64)npages);
313		dump_stack();
314	}
315}
316
317static unsigned long tce_get_pSeriesLP(struct iommu_table *tbl, long tcenum)
318{
319	u64 rc;
320	unsigned long tce_ret;
321
322	rc = plpar_tce_get((u64)tbl->it_index, (u64)tcenum << 12, &tce_ret);
323
324	if (rc && printk_ratelimit()) {
325		printk("tce_get_pSeriesLP: plpar_tce_get failed. rc=%lld\n", rc);
326		printk("\tindex   = 0x%llx\n", (u64)tbl->it_index);
327		printk("\ttcenum  = 0x%llx\n", (u64)tcenum);
328		dump_stack();
329	}
330
331	return tce_ret;
332}
333
334/* this is compatible with cells for the device tree property */
335struct dynamic_dma_window_prop {
336	__be32	liobn;		/* tce table number */
337	__be64	dma_base;	/* address hi,lo */
338	__be32	tce_shift;	/* ilog2(tce_page_size) */
339	__be32	window_shift;	/* ilog2(tce_window_size) */
340};
341
342struct direct_window {
343	struct device_node *device;
344	const struct dynamic_dma_window_prop *prop;
345	struct list_head list;
346};
347
348/* Dynamic DMA Window support */
349struct ddw_query_response {
350	u32 windows_available;
351	u64 largest_available_block;
352	u32 page_size;
353	u32 migration_capable;
354};
355
356struct ddw_create_response {
357	u32 liobn;
358	u32 addr_hi;
359	u32 addr_lo;
360};
361
362static LIST_HEAD(direct_window_list);
363/* prevents races between memory on/offline and window creation */
364static DEFINE_SPINLOCK(direct_window_list_lock);
365/* protects initializing window twice for same device */
366static DEFINE_MUTEX(direct_window_init_mutex);
367#define DIRECT64_PROPNAME "linux,direct64-ddr-window-info"
368
369static int tce_clearrange_multi_pSeriesLP(unsigned long start_pfn,
370					unsigned long num_pfn, const void *arg)
371{
372	const struct dynamic_dma_window_prop *maprange = arg;
373	int rc;
374	u64 tce_size, num_tce, dma_offset, next;
375	u32 tce_shift;
376	long limit;
377
378	tce_shift = be32_to_cpu(maprange->tce_shift);
379	tce_size = 1ULL << tce_shift;
380	next = start_pfn << PAGE_SHIFT;
381	num_tce = num_pfn << PAGE_SHIFT;
382
383	/* round back to the beginning of the tce page size */
384	num_tce += next & (tce_size - 1);
385	next &= ~(tce_size - 1);
386
387	/* covert to number of tces */
388	num_tce |= tce_size - 1;
389	num_tce >>= tce_shift;
390
391	do {
392		/*
393		 * Set up the page with TCE data, looping through and setting
394		 * the values.
395		 */
396		limit = min_t(long, num_tce, 512);
397		dma_offset = next + be64_to_cpu(maprange->dma_base);
398
399		rc = plpar_tce_stuff((u64)be32_to_cpu(maprange->liobn),
400					     dma_offset,
401					     0, limit);
402		next += limit * tce_size;
403		num_tce -= limit;
404	} while (num_tce > 0 && !rc);
405
406	return rc;
407}
408
409static int tce_setrange_multi_pSeriesLP(unsigned long start_pfn,
410					unsigned long num_pfn, const void *arg)
411{
412	const struct dynamic_dma_window_prop *maprange = arg;
413	u64 tce_size, num_tce, dma_offset, next, proto_tce, liobn;
414	__be64 *tcep;
415	u32 tce_shift;
416	u64 rc = 0;
417	long l, limit;
418
419	if (!firmware_has_feature(FW_FEATURE_PUT_TCE_IND)) {
420		unsigned long tceshift = be32_to_cpu(maprange->tce_shift);
421		unsigned long dmastart = (start_pfn << PAGE_SHIFT) +
422				be64_to_cpu(maprange->dma_base);
423		unsigned long tcenum = dmastart >> tceshift;
424		unsigned long npages = num_pfn << PAGE_SHIFT >> tceshift;
425		void *uaddr = __va(start_pfn << PAGE_SHIFT);
426
427		return tce_build_pSeriesLP(be32_to_cpu(maprange->liobn),
428				tcenum, tceshift, npages, (unsigned long) uaddr,
429				DMA_BIDIRECTIONAL, 0);
430	}
431
432	local_irq_disable();	/* to protect tcep and the page behind it */
433	tcep = __this_cpu_read(tce_page);
434
435	if (!tcep) {
436		tcep = (__be64 *)__get_free_page(GFP_ATOMIC);
437		if (!tcep) {
438			local_irq_enable();
439			return -ENOMEM;
440		}
441		__this_cpu_write(tce_page, tcep);
442	}
443
444	proto_tce = TCE_PCI_READ | TCE_PCI_WRITE;
445
446	liobn = (u64)be32_to_cpu(maprange->liobn);
447	tce_shift = be32_to_cpu(maprange->tce_shift);
448	tce_size = 1ULL << tce_shift;
449	next = start_pfn << PAGE_SHIFT;
450	num_tce = num_pfn << PAGE_SHIFT;
451
452	/* round back to the beginning of the tce page size */
453	num_tce += next & (tce_size - 1);
454	next &= ~(tce_size - 1);
455
456	/* covert to number of tces */
457	num_tce |= tce_size - 1;
458	num_tce >>= tce_shift;
459
460	/* We can map max one pageful of TCEs at a time */
461	do {
462		/*
463		 * Set up the page with TCE data, looping through and setting
464		 * the values.
465		 */
466		limit = min_t(long, num_tce, 4096/TCE_ENTRY_SIZE);
467		dma_offset = next + be64_to_cpu(maprange->dma_base);
468
469		for (l = 0; l < limit; l++) {
470			tcep[l] = cpu_to_be64(proto_tce | next);
471			next += tce_size;
472		}
473
474		rc = plpar_tce_put_indirect(liobn,
475					    dma_offset,
476					    (u64)__pa(tcep),
477					    limit);
478
479		num_tce -= limit;
480	} while (num_tce > 0 && !rc);
481
482	/* error cleanup: caller will clear whole range */
483
484	local_irq_enable();
485	return rc;
486}
487
488static int tce_setrange_multi_pSeriesLP_walk(unsigned long start_pfn,
489		unsigned long num_pfn, void *arg)
490{
491	return tce_setrange_multi_pSeriesLP(start_pfn, num_pfn, arg);
492}
493
494static void iommu_table_setparms(struct pci_controller *phb,
495				 struct device_node *dn,
496				 struct iommu_table *tbl)
497{
498	struct device_node *node;
499	const unsigned long *basep;
500	const u32 *sizep;
501
502	node = phb->dn;
503
504	basep = of_get_property(node, "linux,tce-base", NULL);
505	sizep = of_get_property(node, "linux,tce-size", NULL);
506	if (basep == NULL || sizep == NULL) {
507		printk(KERN_ERR "PCI_DMA: iommu_table_setparms: %pOF has "
508				"missing tce entries !\n", dn);
509		return;
510	}
511
512	tbl->it_base = (unsigned long)__va(*basep);
513
514	if (!is_kdump_kernel())
515		memset((void *)tbl->it_base, 0, *sizep);
516
517	tbl->it_busno = phb->bus->number;
518	tbl->it_page_shift = IOMMU_PAGE_SHIFT_4K;
519
520	/* Units of tce entries */
521	tbl->it_offset = phb->dma_window_base_cur >> tbl->it_page_shift;
522
523	/* Test if we are going over 2GB of DMA space */
524	if (phb->dma_window_base_cur + phb->dma_window_size > 0x80000000ul) {
525		udbg_printf("PCI_DMA: Unexpected number of IOAs under this PHB.\n");
526		panic("PCI_DMA: Unexpected number of IOAs under this PHB.\n");
527	}
528
529	phb->dma_window_base_cur += phb->dma_window_size;
530
531	/* Set the tce table size - measured in entries */
532	tbl->it_size = phb->dma_window_size >> tbl->it_page_shift;
533
534	tbl->it_index = 0;
535	tbl->it_blocksize = 16;
536	tbl->it_type = TCE_PCI;
537}
538
539/*
540 * iommu_table_setparms_lpar
541 *
542 * Function: On pSeries LPAR systems, return TCE table info, given a pci bus.
543 */
544static void iommu_table_setparms_lpar(struct pci_controller *phb,
545				      struct device_node *dn,
546				      struct iommu_table *tbl,
547				      struct iommu_table_group *table_group,
548				      const __be32 *dma_window)
549{
550	unsigned long offset, size;
551
552	of_parse_dma_window(dn, dma_window, &tbl->it_index, &offset, &size);
553
554	tbl->it_busno = phb->bus->number;
555	tbl->it_page_shift = IOMMU_PAGE_SHIFT_4K;
556	tbl->it_base   = 0;
557	tbl->it_blocksize  = 16;
558	tbl->it_type = TCE_PCI;
559	tbl->it_offset = offset >> tbl->it_page_shift;
560	tbl->it_size = size >> tbl->it_page_shift;
561
562	table_group->tce32_start = offset;
563	table_group->tce32_size = size;
564}
565
566struct iommu_table_ops iommu_table_pseries_ops = {
567	.set = tce_build_pSeries,
568	.clear = tce_free_pSeries,
569	.get = tce_get_pseries
570};
571
572static void pci_dma_bus_setup_pSeries(struct pci_bus *bus)
573{
574	struct device_node *dn;
575	struct iommu_table *tbl;
576	struct device_node *isa_dn, *isa_dn_orig;
577	struct device_node *tmp;
578	struct pci_dn *pci;
579	int children;
580
581	dn = pci_bus_to_OF_node(bus);
582
583	pr_debug("pci_dma_bus_setup_pSeries: setting up bus %pOF\n", dn);
584
585	if (bus->self) {
586		/* This is not a root bus, any setup will be done for the
587		 * device-side of the bridge in iommu_dev_setup_pSeries().
588		 */
589		return;
590	}
591	pci = PCI_DN(dn);
592
593	/* Check if the ISA bus on the system is under
594	 * this PHB.
595	 */
596	isa_dn = isa_dn_orig = of_find_node_by_type(NULL, "isa");
597
598	while (isa_dn && isa_dn != dn)
599		isa_dn = isa_dn->parent;
600
601	of_node_put(isa_dn_orig);
602
603	/* Count number of direct PCI children of the PHB. */
604	for (children = 0, tmp = dn->child; tmp; tmp = tmp->sibling)
605		children++;
606
607	pr_debug("Children: %d\n", children);
608
609	/* Calculate amount of DMA window per slot. Each window must be
610	 * a power of two (due to pci_alloc_consistent requirements).
611	 *
612	 * Keep 256MB aside for PHBs with ISA.
613	 */
614
615	if (!isa_dn) {
616		/* No ISA/IDE - just set window size and return */
617		pci->phb->dma_window_size = 0x80000000ul; /* To be divided */
618
619		while (pci->phb->dma_window_size * children > 0x80000000ul)
620			pci->phb->dma_window_size >>= 1;
621		pr_debug("No ISA/IDE, window size is 0x%llx\n",
622			 pci->phb->dma_window_size);
623		pci->phb->dma_window_base_cur = 0;
624
625		return;
626	}
627
628	/* If we have ISA, then we probably have an IDE
629	 * controller too. Allocate a 128MB table but
630	 * skip the first 128MB to avoid stepping on ISA
631	 * space.
632	 */
633	pci->phb->dma_window_size = 0x8000000ul;
634	pci->phb->dma_window_base_cur = 0x8000000ul;
635
636	pci->table_group = iommu_pseries_alloc_group(pci->phb->node);
637	tbl = pci->table_group->tables[0];
638
639	iommu_table_setparms(pci->phb, dn, tbl);
640	tbl->it_ops = &iommu_table_pseries_ops;
641	iommu_init_table(tbl, pci->phb->node, 0, 0);
642
643	/* Divide the rest (1.75GB) among the children */
644	pci->phb->dma_window_size = 0x80000000ul;
645	while (pci->phb->dma_window_size * children > 0x70000000ul)
646		pci->phb->dma_window_size >>= 1;
647
648	pr_debug("ISA/IDE, window size is 0x%llx\n", pci->phb->dma_window_size);
649}
650
651#ifdef CONFIG_IOMMU_API
652static int tce_exchange_pseries(struct iommu_table *tbl, long index, unsigned
653				long *tce, enum dma_data_direction *direction,
654				bool realmode)
655{
656	long rc;
657	unsigned long ioba = (unsigned long) index << tbl->it_page_shift;
658	unsigned long flags, oldtce = 0;
659	u64 proto_tce = iommu_direction_to_tce_perm(*direction);
660	unsigned long newtce = *tce | proto_tce;
661
662	spin_lock_irqsave(&tbl->large_pool.lock, flags);
663
664	rc = plpar_tce_get((u64)tbl->it_index, ioba, &oldtce);
665	if (!rc)
666		rc = plpar_tce_put((u64)tbl->it_index, ioba, newtce);
667
668	if (!rc) {
669		*direction = iommu_tce_direction(oldtce);
670		*tce = oldtce & ~(TCE_PCI_READ | TCE_PCI_WRITE);
671	}
672
673	spin_unlock_irqrestore(&tbl->large_pool.lock, flags);
674
675	return rc;
676}
677#endif
678
679struct iommu_table_ops iommu_table_lpar_multi_ops = {
680	.set = tce_buildmulti_pSeriesLP,
681#ifdef CONFIG_IOMMU_API
682	.xchg_no_kill = tce_exchange_pseries,
683#endif
684	.clear = tce_freemulti_pSeriesLP,
685	.get = tce_get_pSeriesLP
686};
687
688static void pci_dma_bus_setup_pSeriesLP(struct pci_bus *bus)
689{
690	struct iommu_table *tbl;
691	struct device_node *dn, *pdn;
692	struct pci_dn *ppci;
693	const __be32 *dma_window = NULL;
694
695	dn = pci_bus_to_OF_node(bus);
696
697	pr_debug("pci_dma_bus_setup_pSeriesLP: setting up bus %pOF\n",
698		 dn);
699
700	/* Find nearest ibm,dma-window, walking up the device tree */
701	for (pdn = dn; pdn != NULL; pdn = pdn->parent) {
702		dma_window = of_get_property(pdn, "ibm,dma-window", NULL);
703		if (dma_window != NULL)
704			break;
705	}
706
707	if (dma_window == NULL) {
708		pr_debug("  no ibm,dma-window property !\n");
709		return;
710	}
711
712	ppci = PCI_DN(pdn);
713
714	pr_debug("  parent is %pOF, iommu_table: 0x%p\n",
715		 pdn, ppci->table_group);
716
717	if (!ppci->table_group) {
718		ppci->table_group = iommu_pseries_alloc_group(ppci->phb->node);
719		tbl = ppci->table_group->tables[0];
720		iommu_table_setparms_lpar(ppci->phb, pdn, tbl,
721				ppci->table_group, dma_window);
722		tbl->it_ops = &iommu_table_lpar_multi_ops;
723		iommu_init_table(tbl, ppci->phb->node, 0, 0);
724		iommu_register_group(ppci->table_group,
725				pci_domain_nr(bus), 0);
726		pr_debug("  created table: %p\n", ppci->table_group);
727	}
728}
729
730
731static void pci_dma_dev_setup_pSeries(struct pci_dev *dev)
732{
733	struct device_node *dn;
734	struct iommu_table *tbl;
735
736	pr_debug("pci_dma_dev_setup_pSeries: %s\n", pci_name(dev));
737
738	dn = dev->dev.of_node;
739
740	/* If we're the direct child of a root bus, then we need to allocate
741	 * an iommu table ourselves. The bus setup code should have setup
742	 * the window sizes already.
743	 */
744	if (!dev->bus->self) {
745		struct pci_controller *phb = PCI_DN(dn)->phb;
746
747		pr_debug(" --> first child, no bridge. Allocating iommu table.\n");
748		PCI_DN(dn)->table_group = iommu_pseries_alloc_group(phb->node);
749		tbl = PCI_DN(dn)->table_group->tables[0];
750		iommu_table_setparms(phb, dn, tbl);
751		tbl->it_ops = &iommu_table_pseries_ops;
752		iommu_init_table(tbl, phb->node, 0, 0);
753		set_iommu_table_base(&dev->dev, tbl);
754		return;
755	}
756
757	/* If this device is further down the bus tree, search upwards until
758	 * an already allocated iommu table is found and use that.
759	 */
760
761	while (dn && PCI_DN(dn) && PCI_DN(dn)->table_group == NULL)
762		dn = dn->parent;
763
764	if (dn && PCI_DN(dn))
765		set_iommu_table_base(&dev->dev,
766				PCI_DN(dn)->table_group->tables[0]);
767	else
768		printk(KERN_WARNING "iommu: Device %s has no iommu table\n",
769		       pci_name(dev));
770}
771
772static int __read_mostly disable_ddw;
773
774static int __init disable_ddw_setup(char *str)
775{
776	disable_ddw = 1;
777	printk(KERN_INFO "ppc iommu: disabling ddw.\n");
778
779	return 0;
780}
781
782early_param("disable_ddw", disable_ddw_setup);
783
784static void remove_dma_window(struct device_node *np, u32 *ddw_avail,
785			      struct property *win)
786{
787	struct dynamic_dma_window_prop *dwp;
788	u64 liobn;
789	int ret;
790
791	dwp = win->value;
792	liobn = (u64)be32_to_cpu(dwp->liobn);
793
794	/* clear the whole window, note the arg is in kernel pages */
795	ret = tce_clearrange_multi_pSeriesLP(0,
796		1ULL << (be32_to_cpu(dwp->window_shift) - PAGE_SHIFT), dwp);
797	if (ret)
798		pr_warn("%pOF failed to clear tces in window.\n",
799			np);
800	else
801		pr_debug("%pOF successfully cleared tces in window.\n",
802			 np);
803
804	ret = rtas_call(ddw_avail[DDW_REMOVE_PE_DMA_WIN], 1, 1, NULL, liobn);
805	if (ret)
806		pr_warn("%pOF: failed to remove direct window: rtas returned "
807			"%d to ibm,remove-pe-dma-window(%x) %llx\n",
808			np, ret, ddw_avail[DDW_REMOVE_PE_DMA_WIN], liobn);
809	else
810		pr_debug("%pOF: successfully removed direct window: rtas returned "
811			"%d to ibm,remove-pe-dma-window(%x) %llx\n",
812			np, ret, ddw_avail[DDW_REMOVE_PE_DMA_WIN], liobn);
813}
814
815static void remove_ddw(struct device_node *np, bool remove_prop)
816{
817	struct property *win;
818	u32 ddw_avail[DDW_APPLICABLE_SIZE];
819	int ret = 0;
820
821	ret = of_property_read_u32_array(np, "ibm,ddw-applicable",
822					 &ddw_avail[0], DDW_APPLICABLE_SIZE);
823	if (ret)
824		return;
825
826	win = of_find_property(np, DIRECT64_PROPNAME, NULL);
827	if (!win)
828		return;
829
830	if (win->length >= sizeof(struct dynamic_dma_window_prop))
831		remove_dma_window(np, ddw_avail, win);
832
833	if (!remove_prop)
834		return;
835
836	ret = of_remove_property(np, win);
837	if (ret)
838		pr_warn("%pOF: failed to remove direct window property: %d\n",
839			np, ret);
840}
841
842static u64 find_existing_ddw(struct device_node *pdn)
843{
844	struct direct_window *window;
845	const struct dynamic_dma_window_prop *direct64;
846	u64 dma_addr = 0;
847
848	spin_lock(&direct_window_list_lock);
849	/* check if we already created a window and dupe that config if so */
850	list_for_each_entry(window, &direct_window_list, list) {
851		if (window->device == pdn) {
852			direct64 = window->prop;
853			dma_addr = be64_to_cpu(direct64->dma_base);
854			break;
855		}
856	}
857	spin_unlock(&direct_window_list_lock);
858
859	return dma_addr;
860}
861
862static int find_existing_ddw_windows(void)
863{
864	int len;
865	struct device_node *pdn;
866	struct direct_window *window;
867	const struct dynamic_dma_window_prop *direct64;
868
869	if (!firmware_has_feature(FW_FEATURE_LPAR))
870		return 0;
871
872	for_each_node_with_property(pdn, DIRECT64_PROPNAME) {
873		direct64 = of_get_property(pdn, DIRECT64_PROPNAME, &len);
874		if (!direct64)
875			continue;
876
877		window = kzalloc(sizeof(*window), GFP_KERNEL);
878		if (!window || len < sizeof(struct dynamic_dma_window_prop)) {
879			kfree(window);
880			remove_ddw(pdn, true);
881			continue;
882		}
883
884		window->device = pdn;
885		window->prop = direct64;
886		spin_lock(&direct_window_list_lock);
887		list_add(&window->list, &direct_window_list);
888		spin_unlock(&direct_window_list_lock);
889	}
890
891	return 0;
892}
893machine_arch_initcall(pseries, find_existing_ddw_windows);
894
895/**
896 * ddw_read_ext - Get the value of an DDW extension
897 * @np:		device node from which the extension value is to be read.
898 * @extnum:	index number of the extension.
899 * @value:	pointer to return value, modified when extension is available.
900 *
901 * Checks if "ibm,ddw-extensions" exists for this node, and get the value
902 * on index 'extnum'.
903 * It can be used only to check if a property exists, passing value == NULL.
904 *
905 * Returns:
906 *	0 if extension successfully read
907 *	-EINVAL if the "ibm,ddw-extensions" does not exist,
908 *	-ENODATA if "ibm,ddw-extensions" does not have a value, and
909 *	-EOVERFLOW if "ibm,ddw-extensions" does not contain this extension.
910 */
911static inline int ddw_read_ext(const struct device_node *np, int extnum,
912			       u32 *value)
913{
914	static const char propname[] = "ibm,ddw-extensions";
915	u32 count;
916	int ret;
917
918	ret = of_property_read_u32_index(np, propname, DDW_EXT_SIZE, &count);
919	if (ret)
920		return ret;
921
922	if (count < extnum)
923		return -EOVERFLOW;
924
925	if (!value)
926		value = &count;
927
928	return of_property_read_u32_index(np, propname, extnum, value);
929}
930
931static int query_ddw(struct pci_dev *dev, const u32 *ddw_avail,
932		     struct ddw_query_response *query,
933		     struct device_node *parent)
934{
935	struct device_node *dn;
936	struct pci_dn *pdn;
937	u32 cfg_addr, ext_query, query_out[5];
938	u64 buid;
939	int ret, out_sz;
940
941	/*
942	 * From LoPAR level 2.8, "ibm,ddw-extensions" index 3 can rule how many
943	 * output parameters ibm,query-pe-dma-windows will have, ranging from
944	 * 5 to 6.
945	 */
946	ret = ddw_read_ext(parent, DDW_EXT_QUERY_OUT_SIZE, &ext_query);
947	if (!ret && ext_query == 1)
948		out_sz = 6;
949	else
950		out_sz = 5;
951
952	/*
953	 * Get the config address and phb buid of the PE window.
954	 * Rely on eeh to retrieve this for us.
955	 * Retrieve them from the pci device, not the node with the
956	 * dma-window property
957	 */
958	dn = pci_device_to_OF_node(dev);
959	pdn = PCI_DN(dn);
960	buid = pdn->phb->buid;
961	cfg_addr = ((pdn->busno << 16) | (pdn->devfn << 8));
962
963	ret = rtas_call(ddw_avail[DDW_QUERY_PE_DMA_WIN], 3, out_sz, query_out,
964			cfg_addr, BUID_HI(buid), BUID_LO(buid));
965	dev_info(&dev->dev, "ibm,query-pe-dma-windows(%x) %x %x %x returned %d\n",
966		 ddw_avail[DDW_QUERY_PE_DMA_WIN], cfg_addr, BUID_HI(buid),
967		 BUID_LO(buid), ret);
968
969	switch (out_sz) {
970	case 5:
971		query->windows_available = query_out[0];
972		query->largest_available_block = query_out[1];
973		query->page_size = query_out[2];
974		query->migration_capable = query_out[3];
975		break;
976	case 6:
977		query->windows_available = query_out[0];
978		query->largest_available_block = ((u64)query_out[1] << 32) |
979						 query_out[2];
980		query->page_size = query_out[3];
981		query->migration_capable = query_out[4];
982		break;
983	}
984
985	return ret;
986}
987
988static int create_ddw(struct pci_dev *dev, const u32 *ddw_avail,
989			struct ddw_create_response *create, int page_shift,
990			int window_shift)
991{
992	struct device_node *dn;
993	struct pci_dn *pdn;
994	u32 cfg_addr;
995	u64 buid;
996	int ret;
997
998	/*
999	 * Get the config address and phb buid of the PE window.
1000	 * Rely on eeh to retrieve this for us.
1001	 * Retrieve them from the pci device, not the node with the
1002	 * dma-window property
1003	 */
1004	dn = pci_device_to_OF_node(dev);
1005	pdn = PCI_DN(dn);
1006	buid = pdn->phb->buid;
1007	cfg_addr = ((pdn->busno << 16) | (pdn->devfn << 8));
1008
1009	do {
1010		/* extra outputs are LIOBN and dma-addr (hi, lo) */
1011		ret = rtas_call(ddw_avail[DDW_CREATE_PE_DMA_WIN], 5, 4,
1012				(u32 *)create, cfg_addr, BUID_HI(buid),
1013				BUID_LO(buid), page_shift, window_shift);
1014	} while (rtas_busy_delay(ret));
1015	dev_info(&dev->dev,
1016		"ibm,create-pe-dma-window(%x) %x %x %x %x %x returned %d "
1017		"(liobn = 0x%x starting addr = %x %x)\n",
1018		 ddw_avail[DDW_CREATE_PE_DMA_WIN], cfg_addr, BUID_HI(buid),
1019		 BUID_LO(buid), page_shift, window_shift, ret, create->liobn,
1020		 create->addr_hi, create->addr_lo);
1021
1022	return ret;
1023}
1024
1025struct failed_ddw_pdn {
1026	struct device_node *pdn;
1027	struct list_head list;
1028};
1029
1030static LIST_HEAD(failed_ddw_pdn_list);
1031
1032static phys_addr_t ddw_memory_hotplug_max(void)
1033{
1034	phys_addr_t max_addr = memory_hotplug_max();
1035	struct device_node *memory;
1036
1037	for_each_node_by_type(memory, "memory") {
1038		unsigned long start, size;
1039		int n_mem_addr_cells, n_mem_size_cells, len;
1040		const __be32 *memcell_buf;
1041
1042		memcell_buf = of_get_property(memory, "reg", &len);
1043		if (!memcell_buf || len <= 0)
1044			continue;
1045
1046		n_mem_addr_cells = of_n_addr_cells(memory);
1047		n_mem_size_cells = of_n_size_cells(memory);
1048
1049		start = of_read_number(memcell_buf, n_mem_addr_cells);
1050		memcell_buf += n_mem_addr_cells;
1051		size = of_read_number(memcell_buf, n_mem_size_cells);
1052		memcell_buf += n_mem_size_cells;
1053
1054		max_addr = max_t(phys_addr_t, max_addr, start + size);
1055	}
1056
1057	return max_addr;
1058}
1059
1060/*
1061 * Platforms supporting the DDW option starting with LoPAR level 2.7 implement
1062 * ibm,ddw-extensions, which carries the rtas token for
1063 * ibm,reset-pe-dma-windows.
1064 * That rtas-call can be used to restore the default DMA window for the device.
1065 */
1066static void reset_dma_window(struct pci_dev *dev, struct device_node *par_dn)
1067{
1068	int ret;
1069	u32 cfg_addr, reset_dma_win;
1070	u64 buid;
1071	struct device_node *dn;
1072	struct pci_dn *pdn;
1073
1074	ret = ddw_read_ext(par_dn, DDW_EXT_RESET_DMA_WIN, &reset_dma_win);
1075	if (ret)
1076		return;
1077
1078	dn = pci_device_to_OF_node(dev);
1079	pdn = PCI_DN(dn);
1080	buid = pdn->phb->buid;
1081	cfg_addr = (pdn->busno << 16) | (pdn->devfn << 8);
1082
1083	ret = rtas_call(reset_dma_win, 3, 1, NULL, cfg_addr, BUID_HI(buid),
1084			BUID_LO(buid));
1085	if (ret)
1086		dev_info(&dev->dev,
1087			 "ibm,reset-pe-dma-windows(%x) %x %x %x returned %d ",
1088			 reset_dma_win, cfg_addr, BUID_HI(buid), BUID_LO(buid),
1089			 ret);
1090}
1091
1092/*
1093 * If the PE supports dynamic dma windows, and there is space for a table
1094 * that can map all pages in a linear offset, then setup such a table,
1095 * and record the dma-offset in the struct device.
1096 *
1097 * dev: the pci device we are checking
1098 * pdn: the parent pe node with the ibm,dma_window property
1099 * Future: also check if we can remap the base window for our base page size
1100 *
1101 * returns the dma offset for use by the direct mapped DMA code.
1102 */
1103static u64 enable_ddw(struct pci_dev *dev, struct device_node *pdn)
1104{
1105	int len, ret;
1106	struct ddw_query_response query;
1107	struct ddw_create_response create;
1108	int page_shift;
1109	u64 dma_addr, max_addr;
1110	struct device_node *dn;
1111	u32 ddw_avail[DDW_APPLICABLE_SIZE];
1112	struct direct_window *window;
1113	struct property *win64;
1114	struct dynamic_dma_window_prop *ddwprop;
1115	struct failed_ddw_pdn *fpdn;
1116	bool default_win_removed = false;
1117
1118	mutex_lock(&direct_window_init_mutex);
1119
1120	dma_addr = find_existing_ddw(pdn);
1121	if (dma_addr != 0)
1122		goto out_unlock;
1123
1124	/*
1125	 * If we already went through this for a previous function of
1126	 * the same device and failed, we don't want to muck with the
1127	 * DMA window again, as it will race with in-flight operations
1128	 * and can lead to EEHs. The above mutex protects access to the
1129	 * list.
1130	 */
1131	list_for_each_entry(fpdn, &failed_ddw_pdn_list, list) {
1132		if (fpdn->pdn == pdn)
1133			goto out_unlock;
1134	}
1135
1136	/*
1137	 * the ibm,ddw-applicable property holds the tokens for:
1138	 * ibm,query-pe-dma-window
1139	 * ibm,create-pe-dma-window
1140	 * ibm,remove-pe-dma-window
1141	 * for the given node in that order.
1142	 * the property is actually in the parent, not the PE
1143	 */
1144	ret = of_property_read_u32_array(pdn, "ibm,ddw-applicable",
1145					 &ddw_avail[0], DDW_APPLICABLE_SIZE);
1146	if (ret)
1147		goto out_failed;
1148
1149       /*
1150	 * Query if there is a second window of size to map the
1151	 * whole partition.  Query returns number of windows, largest
1152	 * block assigned to PE (partition endpoint), and two bitmasks
1153	 * of page sizes: supported and supported for migrate-dma.
1154	 */
1155	dn = pci_device_to_OF_node(dev);
1156	ret = query_ddw(dev, ddw_avail, &query, pdn);
1157	if (ret != 0)
1158		goto out_failed;
1159
1160	/*
1161	 * If there is no window available, remove the default DMA window,
1162	 * if it's present. This will make all the resources available to the
1163	 * new DDW window.
1164	 * If anything fails after this, we need to restore it, so also check
1165	 * for extensions presence.
1166	 */
1167	if (query.windows_available == 0) {
1168		struct property *default_win;
1169		int reset_win_ext;
1170
1171		default_win = of_find_property(pdn, "ibm,dma-window", NULL);
1172		if (!default_win)
1173			goto out_failed;
1174
1175		reset_win_ext = ddw_read_ext(pdn, DDW_EXT_RESET_DMA_WIN, NULL);
1176		if (reset_win_ext)
1177			goto out_failed;
1178
1179		remove_dma_window(pdn, ddw_avail, default_win);
1180		default_win_removed = true;
1181
1182		/* Query again, to check if the window is available */
1183		ret = query_ddw(dev, ddw_avail, &query, pdn);
1184		if (ret != 0)
1185			goto out_failed;
1186
1187		if (query.windows_available == 0) {
1188			/* no windows are available for this device. */
1189			dev_dbg(&dev->dev, "no free dynamic windows");
1190			goto out_failed;
1191		}
1192	}
1193	if (query.page_size & 4) {
1194		page_shift = 24; /* 16MB */
1195	} else if (query.page_size & 2) {
1196		page_shift = 16; /* 64kB */
1197	} else if (query.page_size & 1) {
1198		page_shift = 12; /* 4kB */
1199	} else {
1200		dev_dbg(&dev->dev, "no supported direct page size in mask %x",
1201			  query.page_size);
1202		goto out_failed;
1203	}
1204	/* verify the window * number of ptes will map the partition */
1205	/* check largest block * page size > max memory hotplug addr */
1206	max_addr = ddw_memory_hotplug_max();
1207	if (query.largest_available_block < (max_addr >> page_shift)) {
1208		dev_dbg(&dev->dev, "can't map partition max 0x%llx with %llu "
1209			  "%llu-sized pages\n", max_addr,  query.largest_available_block,
1210			  1ULL << page_shift);
1211		goto out_failed;
1212	}
1213	len = order_base_2(max_addr);
1214	win64 = kzalloc(sizeof(struct property), GFP_KERNEL);
1215	if (!win64) {
1216		dev_info(&dev->dev,
1217			"couldn't allocate property for 64bit dma window\n");
1218		goto out_failed;
1219	}
1220	win64->name = kstrdup(DIRECT64_PROPNAME, GFP_KERNEL);
1221	win64->value = ddwprop = kmalloc(sizeof(*ddwprop), GFP_KERNEL);
1222	win64->length = sizeof(*ddwprop);
1223	if (!win64->name || !win64->value) {
1224		dev_info(&dev->dev,
1225			"couldn't allocate property name and value\n");
1226		goto out_free_prop;
1227	}
1228
1229	ret = create_ddw(dev, ddw_avail, &create, page_shift, len);
1230	if (ret != 0)
1231		goto out_free_prop;
1232
1233	ddwprop->liobn = cpu_to_be32(create.liobn);
1234	ddwprop->dma_base = cpu_to_be64(((u64)create.addr_hi << 32) |
1235			create.addr_lo);
1236	ddwprop->tce_shift = cpu_to_be32(page_shift);
1237	ddwprop->window_shift = cpu_to_be32(len);
1238
1239	dev_dbg(&dev->dev, "created tce table LIOBN 0x%x for %pOF\n",
1240		  create.liobn, dn);
1241
1242	window = kzalloc(sizeof(*window), GFP_KERNEL);
1243	if (!window)
1244		goto out_clear_window;
1245
1246	ret = walk_system_ram_range(0, memblock_end_of_DRAM() >> PAGE_SHIFT,
1247			win64->value, tce_setrange_multi_pSeriesLP_walk);
1248	if (ret) {
1249		dev_info(&dev->dev, "failed to map direct window for %pOF: %d\n",
1250			 dn, ret);
1251		goto out_free_window;
1252	}
1253
1254	ret = of_add_property(pdn, win64);
1255	if (ret) {
1256		dev_err(&dev->dev, "unable to add dma window property for %pOF: %d",
1257			 pdn, ret);
1258		goto out_free_window;
1259	}
1260
1261	window->device = pdn;
1262	window->prop = ddwprop;
1263	spin_lock(&direct_window_list_lock);
1264	list_add(&window->list, &direct_window_list);
1265	spin_unlock(&direct_window_list_lock);
1266
1267	dma_addr = be64_to_cpu(ddwprop->dma_base);
1268	goto out_unlock;
1269
1270out_free_window:
1271	kfree(window);
1272
1273out_clear_window:
1274	remove_ddw(pdn, true);
1275
1276out_free_prop:
1277	kfree(win64->name);
1278	kfree(win64->value);
1279	kfree(win64);
1280
1281out_failed:
1282	if (default_win_removed)
1283		reset_dma_window(dev, pdn);
1284
1285	fpdn = kzalloc(sizeof(*fpdn), GFP_KERNEL);
1286	if (!fpdn)
1287		goto out_unlock;
1288	fpdn->pdn = pdn;
1289	list_add(&fpdn->list, &failed_ddw_pdn_list);
1290
1291out_unlock:
1292	mutex_unlock(&direct_window_init_mutex);
1293	return dma_addr;
1294}
1295
1296static void pci_dma_dev_setup_pSeriesLP(struct pci_dev *dev)
1297{
1298	struct device_node *pdn, *dn;
1299	struct iommu_table *tbl;
1300	const __be32 *dma_window = NULL;
1301	struct pci_dn *pci;
1302
1303	pr_debug("pci_dma_dev_setup_pSeriesLP: %s\n", pci_name(dev));
1304
1305	/* dev setup for LPAR is a little tricky, since the device tree might
1306	 * contain the dma-window properties per-device and not necessarily
1307	 * for the bus. So we need to search upwards in the tree until we
1308	 * either hit a dma-window property, OR find a parent with a table
1309	 * already allocated.
1310	 */
1311	dn = pci_device_to_OF_node(dev);
1312	pr_debug("  node is %pOF\n", dn);
1313
1314	for (pdn = dn; pdn && PCI_DN(pdn) && !PCI_DN(pdn)->table_group;
1315	     pdn = pdn->parent) {
1316		dma_window = of_get_property(pdn, "ibm,dma-window", NULL);
1317		if (dma_window)
1318			break;
1319	}
1320
1321	if (!pdn || !PCI_DN(pdn)) {
1322		printk(KERN_WARNING "pci_dma_dev_setup_pSeriesLP: "
1323		       "no DMA window found for pci dev=%s dn=%pOF\n",
1324				 pci_name(dev), dn);
1325		return;
1326	}
1327	pr_debug("  parent is %pOF\n", pdn);
1328
1329	pci = PCI_DN(pdn);
1330	if (!pci->table_group) {
1331		pci->table_group = iommu_pseries_alloc_group(pci->phb->node);
1332		tbl = pci->table_group->tables[0];
1333		iommu_table_setparms_lpar(pci->phb, pdn, tbl,
1334				pci->table_group, dma_window);
1335		tbl->it_ops = &iommu_table_lpar_multi_ops;
1336		iommu_init_table(tbl, pci->phb->node, 0, 0);
1337		iommu_register_group(pci->table_group,
1338				pci_domain_nr(pci->phb->bus), 0);
1339		pr_debug("  created table: %p\n", pci->table_group);
1340	} else {
1341		pr_debug("  found DMA window, table: %p\n", pci->table_group);
1342	}
1343
1344	set_iommu_table_base(&dev->dev, pci->table_group->tables[0]);
1345	iommu_add_device(pci->table_group, &dev->dev);
1346}
1347
1348static bool iommu_bypass_supported_pSeriesLP(struct pci_dev *pdev, u64 dma_mask)
1349{
1350	struct device_node *dn = pci_device_to_OF_node(pdev), *pdn;
1351	const __be32 *dma_window = NULL;
1352
1353	/* only attempt to use a new window if 64-bit DMA is requested */
1354	if (dma_mask < DMA_BIT_MASK(64))
1355		return false;
1356
1357	dev_dbg(&pdev->dev, "node is %pOF\n", dn);
1358
1359	/*
1360	 * the device tree might contain the dma-window properties
1361	 * per-device and not necessarily for the bus. So we need to
1362	 * search upwards in the tree until we either hit a dma-window
1363	 * property, OR find a parent with a table already allocated.
1364	 */
1365	for (pdn = dn; pdn && PCI_DN(pdn) && !PCI_DN(pdn)->table_group;
1366			pdn = pdn->parent) {
1367		dma_window = of_get_property(pdn, "ibm,dma-window", NULL);
1368		if (dma_window)
1369			break;
1370	}
1371
1372	if (pdn && PCI_DN(pdn)) {
1373		pdev->dev.archdata.dma_offset = enable_ddw(pdev, pdn);
1374		if (pdev->dev.archdata.dma_offset)
1375			return true;
1376	}
1377
1378	return false;
1379}
1380
1381static int iommu_mem_notifier(struct notifier_block *nb, unsigned long action,
1382		void *data)
1383{
1384	struct direct_window *window;
1385	struct memory_notify *arg = data;
1386	int ret = 0;
1387
1388	switch (action) {
1389	case MEM_GOING_ONLINE:
1390		spin_lock(&direct_window_list_lock);
1391		list_for_each_entry(window, &direct_window_list, list) {
1392			ret |= tce_setrange_multi_pSeriesLP(arg->start_pfn,
1393					arg->nr_pages, window->prop);
1394			/* XXX log error */
1395		}
1396		spin_unlock(&direct_window_list_lock);
1397		break;
1398	case MEM_CANCEL_ONLINE:
1399	case MEM_OFFLINE:
1400		spin_lock(&direct_window_list_lock);
1401		list_for_each_entry(window, &direct_window_list, list) {
1402			ret |= tce_clearrange_multi_pSeriesLP(arg->start_pfn,
1403					arg->nr_pages, window->prop);
1404			/* XXX log error */
1405		}
1406		spin_unlock(&direct_window_list_lock);
1407		break;
1408	default:
1409		break;
1410	}
1411	if (ret && action != MEM_CANCEL_ONLINE)
1412		return NOTIFY_BAD;
1413
1414	return NOTIFY_OK;
1415}
1416
1417static struct notifier_block iommu_mem_nb = {
1418	.notifier_call = iommu_mem_notifier,
1419};
1420
1421static int iommu_reconfig_notifier(struct notifier_block *nb, unsigned long action, void *data)
1422{
1423	int err = NOTIFY_OK;
1424	struct of_reconfig_data *rd = data;
1425	struct device_node *np = rd->dn;
1426	struct pci_dn *pci = PCI_DN(np);
1427	struct direct_window *window;
1428
1429	switch (action) {
1430	case OF_RECONFIG_DETACH_NODE:
1431		/*
1432		 * Removing the property will invoke the reconfig
1433		 * notifier again, which causes dead-lock on the
1434		 * read-write semaphore of the notifier chain. So
1435		 * we have to remove the property when releasing
1436		 * the device node.
1437		 */
1438		remove_ddw(np, false);
1439		if (pci && pci->table_group)
1440			iommu_pseries_free_group(pci->table_group,
1441					np->full_name);
1442
1443		spin_lock(&direct_window_list_lock);
1444		list_for_each_entry(window, &direct_window_list, list) {
1445			if (window->device == np) {
1446				list_del(&window->list);
1447				kfree(window);
1448				break;
1449			}
1450		}
1451		spin_unlock(&direct_window_list_lock);
1452		break;
1453	default:
1454		err = NOTIFY_DONE;
1455		break;
1456	}
1457	return err;
1458}
1459
1460static struct notifier_block iommu_reconfig_nb = {
1461	.notifier_call = iommu_reconfig_notifier,
1462};
1463
1464/* These are called very early. */
1465void iommu_init_early_pSeries(void)
1466{
1467	if (of_chosen && of_get_property(of_chosen, "linux,iommu-off", NULL))
1468		return;
1469
1470	if (firmware_has_feature(FW_FEATURE_LPAR)) {
1471		pseries_pci_controller_ops.dma_bus_setup = pci_dma_bus_setup_pSeriesLP;
1472		pseries_pci_controller_ops.dma_dev_setup = pci_dma_dev_setup_pSeriesLP;
1473		if (!disable_ddw)
1474			pseries_pci_controller_ops.iommu_bypass_supported =
1475				iommu_bypass_supported_pSeriesLP;
1476	} else {
1477		pseries_pci_controller_ops.dma_bus_setup = pci_dma_bus_setup_pSeries;
1478		pseries_pci_controller_ops.dma_dev_setup = pci_dma_dev_setup_pSeries;
1479	}
1480
1481
1482	of_reconfig_notifier_register(&iommu_reconfig_nb);
1483	register_memory_notifier(&iommu_mem_nb);
1484
1485	set_pci_dma_ops(&dma_iommu_ops);
1486}
1487
1488static int __init disable_multitce(char *str)
1489{
1490	if (strcmp(str, "off") == 0 &&
1491	    firmware_has_feature(FW_FEATURE_LPAR) &&
1492	    (firmware_has_feature(FW_FEATURE_PUT_TCE_IND) ||
1493	     firmware_has_feature(FW_FEATURE_STUFF_TCE))) {
1494		printk(KERN_INFO "Disabling MULTITCE firmware feature\n");
1495		powerpc_firmware_features &=
1496			~(FW_FEATURE_PUT_TCE_IND | FW_FEATURE_STUFF_TCE);
1497	}
1498	return 1;
1499}
1500
1501__setup("multitce=", disable_multitce);
1502
1503static int tce_iommu_bus_notifier(struct notifier_block *nb,
1504		unsigned long action, void *data)
1505{
1506	struct device *dev = data;
1507
1508	switch (action) {
1509	case BUS_NOTIFY_DEL_DEVICE:
1510		iommu_del_device(dev);
1511		return 0;
1512	default:
1513		return 0;
1514	}
1515}
1516
1517static struct notifier_block tce_iommu_bus_nb = {
1518	.notifier_call = tce_iommu_bus_notifier,
1519};
1520
1521static int __init tce_iommu_bus_notifier_init(void)
1522{
1523	bus_register_notifier(&pci_bus_type, &tce_iommu_bus_nb);
1524	return 0;
1525}
1526machine_subsys_initcall_sync(pseries, tce_iommu_bus_notifier_init);
1527