1// SPDX-License-Identifier: MIT
2/*
3 * Copyright © 2020 Intel Corporation
4 */
5
6#include <asm/set_memory.h>
7#include <asm/smp.h>
8#include <linux/types.h>
9#include <linux/stop_machine.h>
10
11#include <drm/drm_managed.h>
12#include <drm/i915_drm.h>
13#include <drm/intel-gtt.h>
14
15#include "display/intel_display.h"
16#include "gem/i915_gem_lmem.h"
17
18#include "intel_ggtt_gmch.h"
19#include "intel_gt.h"
20#include "intel_gt_regs.h"
21#include "intel_pci_config.h"
22#include "i915_drv.h"
23#include "i915_pci.h"
24#include "i915_scatterlist.h"
25#include "i915_utils.h"
26#include "i915_vgpu.h"
27
28#include "intel_gtt.h"
29#include "gen8_ppgtt.h"
30
31static void i915_ggtt_color_adjust(const struct drm_mm_node *node,
32				   unsigned long color,
33				   u64 *start,
34				   u64 *end)
35{
36	if (i915_node_color_differs(node, color))
37		*start += I915_GTT_PAGE_SIZE;
38
39	/*
40	 * Also leave a space between the unallocated reserved node after the
41	 * GTT and any objects within the GTT, i.e. we use the color adjustment
42	 * to insert a guard page to prevent prefetches crossing over the
43	 * GTT boundary.
44	 */
45	node = list_next_entry(node, node_list);
46	if (node->color != color)
47		*end -= I915_GTT_PAGE_SIZE;
48}
49
50static int ggtt_init_hw(struct i915_ggtt *ggtt)
51{
52	struct drm_i915_private *i915 = ggtt->vm.i915;
53
54	i915_address_space_init(&ggtt->vm, VM_CLASS_GGTT);
55
56	ggtt->vm.is_ggtt = true;
57
58	/* Only VLV supports read-only GGTT mappings */
59	ggtt->vm.has_read_only = IS_VALLEYVIEW(i915);
60
61	if (!HAS_LLC(i915) && !HAS_PPGTT(i915))
62		ggtt->vm.mm.color_adjust = i915_ggtt_color_adjust;
63
64	if (ggtt->mappable_end) {
65		if (!io_mapping_init_wc(&ggtt->iomap,
66					ggtt->gmadr.start,
67					ggtt->mappable_end)) {
68			ggtt->vm.cleanup(&ggtt->vm);
69			return -EIO;
70		}
71
72		ggtt->mtrr = arch_phys_wc_add(ggtt->gmadr.start,
73					      ggtt->mappable_end);
74	}
75
76	intel_ggtt_init_fences(ggtt);
77
78	return 0;
79}
80
81/**
82 * i915_ggtt_init_hw - Initialize GGTT hardware
83 * @i915: i915 device
84 */
85int i915_ggtt_init_hw(struct drm_i915_private *i915)
86{
87	int ret;
88
89	/*
90	 * Note that we use page colouring to enforce a guard page at the
91	 * end of the address space. This is required as the CS may prefetch
92	 * beyond the end of the batch buffer, across the page boundary,
93	 * and beyond the end of the GTT if we do not provide a guard.
94	 */
95	ret = ggtt_init_hw(to_gt(i915)->ggtt);
96	if (ret)
97		return ret;
98
99	return 0;
100}
101
102/**
103 * i915_ggtt_suspend_vm - Suspend the memory mappings for a GGTT or DPT VM
104 * @vm: The VM to suspend the mappings for
105 *
106 * Suspend the memory mappings for all objects mapped to HW via the GGTT or a
107 * DPT page table.
108 */
109void i915_ggtt_suspend_vm(struct i915_address_space *vm)
110{
111	struct i915_vma *vma, *vn;
112	int save_skip_rewrite;
113
114	drm_WARN_ON(&vm->i915->drm, !vm->is_ggtt && !vm->is_dpt);
115
116retry:
117	i915_gem_drain_freed_objects(vm->i915);
118
119	mutex_lock(&vm->mutex);
120
121	/*
122	 * Skip rewriting PTE on VMA unbind.
123	 * FIXME: Use an argument to i915_vma_unbind() instead?
124	 */
125	save_skip_rewrite = vm->skip_pte_rewrite;
126	vm->skip_pte_rewrite = true;
127
128	list_for_each_entry_safe(vma, vn, &vm->bound_list, vm_link) {
129		struct drm_i915_gem_object *obj = vma->obj;
130
131		GEM_BUG_ON(!drm_mm_node_allocated(&vma->node));
132
133		if (i915_vma_is_pinned(vma) || !i915_vma_is_bound(vma, I915_VMA_GLOBAL_BIND))
134			continue;
135
136		/* unlikely to race when GPU is idle, so no worry about slowpath.. */
137		if (WARN_ON(!i915_gem_object_trylock(obj, NULL))) {
138			/*
139			 * No dead objects should appear here, GPU should be
140			 * completely idle, and userspace suspended
141			 */
142			i915_gem_object_get(obj);
143
144			mutex_unlock(&vm->mutex);
145
146			i915_gem_object_lock(obj, NULL);
147			GEM_WARN_ON(i915_vma_unbind(vma));
148			i915_gem_object_unlock(obj);
149			i915_gem_object_put(obj);
150
151			vm->skip_pte_rewrite = save_skip_rewrite;
152			goto retry;
153		}
154
155		if (!i915_vma_is_bound(vma, I915_VMA_GLOBAL_BIND)) {
156			i915_vma_wait_for_bind(vma);
157
158			__i915_vma_evict(vma, false);
159			drm_mm_remove_node(&vma->node);
160		}
161
162		i915_gem_object_unlock(obj);
163	}
164
165	vm->clear_range(vm, 0, vm->total);
166
167	vm->skip_pte_rewrite = save_skip_rewrite;
168
169	mutex_unlock(&vm->mutex);
170}
171
172void i915_ggtt_suspend(struct i915_ggtt *ggtt)
173{
174	struct intel_gt *gt;
175
176	i915_ggtt_suspend_vm(&ggtt->vm);
177	ggtt->invalidate(ggtt);
178
179	list_for_each_entry(gt, &ggtt->gt_list, ggtt_link)
180		intel_gt_check_and_clear_faults(gt);
181}
182
183void gen6_ggtt_invalidate(struct i915_ggtt *ggtt)
184{
185	struct intel_uncore *uncore = ggtt->vm.gt->uncore;
186
187	spin_lock_irq(&uncore->lock);
188	intel_uncore_write_fw(uncore, GFX_FLSH_CNTL_GEN6, GFX_FLSH_CNTL_EN);
189	intel_uncore_read_fw(uncore, GFX_FLSH_CNTL_GEN6);
190	spin_unlock_irq(&uncore->lock);
191}
192
193static bool needs_wc_ggtt_mapping(struct drm_i915_private *i915)
194{
195	/*
196	 * On BXT+/ICL+ writes larger than 64 bit to the GTT pagetable range
197	 * will be dropped. For WC mappings in general we have 64 byte burst
198	 * writes when the WC buffer is flushed, so we can't use it, but have to
199	 * resort to an uncached mapping. The WC issue is easily caught by the
200	 * readback check when writing GTT PTE entries.
201	 */
202	if (!IS_GEN9_LP(i915) && GRAPHICS_VER(i915) < 11)
203		return true;
204
205	return false;
206}
207
208static void gen8_ggtt_invalidate(struct i915_ggtt *ggtt)
209{
210	struct intel_uncore *uncore = ggtt->vm.gt->uncore;
211
212	/*
213	 * Note that as an uncached mmio write, this will flush the
214	 * WCB of the writes into the GGTT before it triggers the invalidate.
215	 *
216	 * Only perform this when GGTT is mapped as WC, see ggtt_probe_common().
217	 */
218	if (needs_wc_ggtt_mapping(ggtt->vm.i915))
219		intel_uncore_write_fw(uncore, GFX_FLSH_CNTL_GEN6,
220				      GFX_FLSH_CNTL_EN);
221}
222
223static void guc_ggtt_invalidate(struct i915_ggtt *ggtt)
224{
225	struct drm_i915_private *i915 = ggtt->vm.i915;
226
227	gen8_ggtt_invalidate(ggtt);
228
229	if (GRAPHICS_VER(i915) >= 12) {
230		struct intel_gt *gt;
231
232		list_for_each_entry(gt, &ggtt->gt_list, ggtt_link)
233			intel_uncore_write_fw(gt->uncore,
234					      GEN12_GUC_TLB_INV_CR,
235					      GEN12_GUC_TLB_INV_CR_INVALIDATE);
236	} else {
237		intel_uncore_write_fw(ggtt->vm.gt->uncore,
238				      GEN8_GTCR, GEN8_GTCR_INVALIDATE);
239	}
240}
241
242static u64 mtl_ggtt_pte_encode(dma_addr_t addr,
243			       unsigned int pat_index,
244			       u32 flags)
245{
246	gen8_pte_t pte = addr | GEN8_PAGE_PRESENT;
247
248	WARN_ON_ONCE(addr & ~GEN12_GGTT_PTE_ADDR_MASK);
249
250	if (flags & PTE_LM)
251		pte |= GEN12_GGTT_PTE_LM;
252
253	if (pat_index & BIT(0))
254		pte |= MTL_GGTT_PTE_PAT0;
255
256	if (pat_index & BIT(1))
257		pte |= MTL_GGTT_PTE_PAT1;
258
259	return pte;
260}
261
262u64 gen8_ggtt_pte_encode(dma_addr_t addr,
263			 unsigned int pat_index,
264			 u32 flags)
265{
266	gen8_pte_t pte = addr | GEN8_PAGE_PRESENT;
267
268	if (flags & PTE_LM)
269		pte |= GEN12_GGTT_PTE_LM;
270
271	return pte;
272}
273
274static void gen8_set_pte(void __iomem *addr, gen8_pte_t pte)
275{
276	writeq(pte, addr);
277}
278
279static void gen8_ggtt_insert_page(struct i915_address_space *vm,
280				  dma_addr_t addr,
281				  u64 offset,
282				  unsigned int pat_index,
283				  u32 flags)
284{
285	struct i915_ggtt *ggtt = i915_vm_to_ggtt(vm);
286	gen8_pte_t __iomem *pte =
287		(gen8_pte_t __iomem *)ggtt->gsm + offset / I915_GTT_PAGE_SIZE;
288
289	gen8_set_pte(pte, ggtt->vm.pte_encode(addr, pat_index, flags));
290
291	ggtt->invalidate(ggtt);
292}
293
294static void gen8_ggtt_insert_entries(struct i915_address_space *vm,
295				     struct i915_vma_resource *vma_res,
296				     unsigned int pat_index,
297				     u32 flags)
298{
299	struct i915_ggtt *ggtt = i915_vm_to_ggtt(vm);
300	const gen8_pte_t pte_encode = ggtt->vm.pte_encode(0, pat_index, flags);
301	gen8_pte_t __iomem *gte;
302	gen8_pte_t __iomem *end;
303	struct sgt_iter iter;
304	dma_addr_t addr;
305
306	/*
307	 * Note that we ignore PTE_READ_ONLY here. The caller must be careful
308	 * not to allow the user to override access to a read only page.
309	 */
310
311	gte = (gen8_pte_t __iomem *)ggtt->gsm;
312	gte += (vma_res->start - vma_res->guard) / I915_GTT_PAGE_SIZE;
313	end = gte + vma_res->guard / I915_GTT_PAGE_SIZE;
314	while (gte < end)
315		gen8_set_pte(gte++, vm->scratch[0]->encode);
316	end += (vma_res->node_size + vma_res->guard) / I915_GTT_PAGE_SIZE;
317
318	for_each_sgt_daddr(addr, iter, vma_res->bi.pages)
319		gen8_set_pte(gte++, pte_encode | addr);
320	GEM_BUG_ON(gte > end);
321
322	/* Fill the allocated but "unused" space beyond the end of the buffer */
323	while (gte < end)
324		gen8_set_pte(gte++, vm->scratch[0]->encode);
325
326	/*
327	 * We want to flush the TLBs only after we're certain all the PTE
328	 * updates have finished.
329	 */
330	ggtt->invalidate(ggtt);
331}
332
333static void gen8_ggtt_clear_range(struct i915_address_space *vm,
334				  u64 start, u64 length)
335{
336	struct i915_ggtt *ggtt = i915_vm_to_ggtt(vm);
337	unsigned int first_entry = start / I915_GTT_PAGE_SIZE;
338	unsigned int num_entries = length / I915_GTT_PAGE_SIZE;
339	const gen8_pte_t scratch_pte = vm->scratch[0]->encode;
340	gen8_pte_t __iomem *gtt_base =
341		(gen8_pte_t __iomem *)ggtt->gsm + first_entry;
342	const int max_entries = ggtt_total_entries(ggtt) - first_entry;
343	int i;
344
345	if (WARN(num_entries > max_entries,
346		 "First entry = %d; Num entries = %d (max=%d)\n",
347		 first_entry, num_entries, max_entries))
348		num_entries = max_entries;
349
350	for (i = 0; i < num_entries; i++)
351		gen8_set_pte(&gtt_base[i], scratch_pte);
352}
353
354static void gen6_ggtt_insert_page(struct i915_address_space *vm,
355				  dma_addr_t addr,
356				  u64 offset,
357				  unsigned int pat_index,
358				  u32 flags)
359{
360	struct i915_ggtt *ggtt = i915_vm_to_ggtt(vm);
361	gen6_pte_t __iomem *pte =
362		(gen6_pte_t __iomem *)ggtt->gsm + offset / I915_GTT_PAGE_SIZE;
363
364	iowrite32(vm->pte_encode(addr, pat_index, flags), pte);
365
366	ggtt->invalidate(ggtt);
367}
368
369/*
370 * Binds an object into the global gtt with the specified cache level.
371 * The object will be accessible to the GPU via commands whose operands
372 * reference offsets within the global GTT as well as accessible by the GPU
373 * through the GMADR mapped BAR (i915->mm.gtt->gtt).
374 */
375static void gen6_ggtt_insert_entries(struct i915_address_space *vm,
376				     struct i915_vma_resource *vma_res,
377				     unsigned int pat_index,
378				     u32 flags)
379{
380	struct i915_ggtt *ggtt = i915_vm_to_ggtt(vm);
381	gen6_pte_t __iomem *gte;
382	gen6_pte_t __iomem *end;
383	struct sgt_iter iter;
384	dma_addr_t addr;
385
386	gte = (gen6_pte_t __iomem *)ggtt->gsm;
387	gte += (vma_res->start - vma_res->guard) / I915_GTT_PAGE_SIZE;
388
389	end = gte + vma_res->guard / I915_GTT_PAGE_SIZE;
390	while (gte < end)
391		iowrite32(vm->scratch[0]->encode, gte++);
392	end += (vma_res->node_size + vma_res->guard) / I915_GTT_PAGE_SIZE;
393	for_each_sgt_daddr(addr, iter, vma_res->bi.pages)
394		iowrite32(vm->pte_encode(addr, pat_index, flags), gte++);
395	GEM_BUG_ON(gte > end);
396
397	/* Fill the allocated but "unused" space beyond the end of the buffer */
398	while (gte < end)
399		iowrite32(vm->scratch[0]->encode, gte++);
400
401	/*
402	 * We want to flush the TLBs only after we're certain all the PTE
403	 * updates have finished.
404	 */
405	ggtt->invalidate(ggtt);
406}
407
408static void nop_clear_range(struct i915_address_space *vm,
409			    u64 start, u64 length)
410{
411}
412
413static void bxt_vtd_ggtt_wa(struct i915_address_space *vm)
414{
415	/*
416	 * Make sure the internal GAM fifo has been cleared of all GTT
417	 * writes before exiting stop_machine(). This guarantees that
418	 * any aperture accesses waiting to start in another process
419	 * cannot back up behind the GTT writes causing a hang.
420	 * The register can be any arbitrary GAM register.
421	 */
422	intel_uncore_posting_read_fw(vm->gt->uncore, GFX_FLSH_CNTL_GEN6);
423}
424
425struct insert_page {
426	struct i915_address_space *vm;
427	dma_addr_t addr;
428	u64 offset;
429	unsigned int pat_index;
430};
431
432static int bxt_vtd_ggtt_insert_page__cb(void *_arg)
433{
434	struct insert_page *arg = _arg;
435
436	gen8_ggtt_insert_page(arg->vm, arg->addr, arg->offset,
437			      arg->pat_index, 0);
438	bxt_vtd_ggtt_wa(arg->vm);
439
440	return 0;
441}
442
443static void bxt_vtd_ggtt_insert_page__BKL(struct i915_address_space *vm,
444					  dma_addr_t addr,
445					  u64 offset,
446					  unsigned int pat_index,
447					  u32 unused)
448{
449	struct insert_page arg = { vm, addr, offset, pat_index };
450
451	stop_machine(bxt_vtd_ggtt_insert_page__cb, &arg, NULL);
452}
453
454struct insert_entries {
455	struct i915_address_space *vm;
456	struct i915_vma_resource *vma_res;
457	unsigned int pat_index;
458	u32 flags;
459};
460
461static int bxt_vtd_ggtt_insert_entries__cb(void *_arg)
462{
463	struct insert_entries *arg = _arg;
464
465	gen8_ggtt_insert_entries(arg->vm, arg->vma_res,
466				 arg->pat_index, arg->flags);
467	bxt_vtd_ggtt_wa(arg->vm);
468
469	return 0;
470}
471
472static void bxt_vtd_ggtt_insert_entries__BKL(struct i915_address_space *vm,
473					     struct i915_vma_resource *vma_res,
474					     unsigned int pat_index,
475					     u32 flags)
476{
477	struct insert_entries arg = { vm, vma_res, pat_index, flags };
478
479	stop_machine(bxt_vtd_ggtt_insert_entries__cb, &arg, NULL);
480}
481
482static void gen6_ggtt_clear_range(struct i915_address_space *vm,
483				  u64 start, u64 length)
484{
485	struct i915_ggtt *ggtt = i915_vm_to_ggtt(vm);
486	unsigned int first_entry = start / I915_GTT_PAGE_SIZE;
487	unsigned int num_entries = length / I915_GTT_PAGE_SIZE;
488	gen6_pte_t scratch_pte, __iomem *gtt_base =
489		(gen6_pte_t __iomem *)ggtt->gsm + first_entry;
490	const int max_entries = ggtt_total_entries(ggtt) - first_entry;
491	int i;
492
493	if (WARN(num_entries > max_entries,
494		 "First entry = %d; Num entries = %d (max=%d)\n",
495		 first_entry, num_entries, max_entries))
496		num_entries = max_entries;
497
498	scratch_pte = vm->scratch[0]->encode;
499	for (i = 0; i < num_entries; i++)
500		iowrite32(scratch_pte, &gtt_base[i]);
501}
502
503void intel_ggtt_bind_vma(struct i915_address_space *vm,
504			 struct i915_vm_pt_stash *stash,
505			 struct i915_vma_resource *vma_res,
506			 unsigned int pat_index,
507			 u32 flags)
508{
509	u32 pte_flags;
510
511	if (vma_res->bound_flags & (~flags & I915_VMA_BIND_MASK))
512		return;
513
514	vma_res->bound_flags |= flags;
515
516	/* Applicable to VLV (gen8+ do not support RO in the GGTT) */
517	pte_flags = 0;
518	if (vma_res->bi.readonly)
519		pte_flags |= PTE_READ_ONLY;
520	if (vma_res->bi.lmem)
521		pte_flags |= PTE_LM;
522
523	vm->insert_entries(vm, vma_res, pat_index, pte_flags);
524	vma_res->page_sizes_gtt = I915_GTT_PAGE_SIZE;
525}
526
527void intel_ggtt_unbind_vma(struct i915_address_space *vm,
528			   struct i915_vma_resource *vma_res)
529{
530	vm->clear_range(vm, vma_res->start, vma_res->vma_size);
531}
532
533/*
534 * Reserve the top of the GuC address space for firmware images. Addresses
535 * beyond GUC_GGTT_TOP in the GuC address space are inaccessible by GuC,
536 * which makes for a suitable range to hold GuC/HuC firmware images if the
537 * size of the GGTT is 4G. However, on a 32-bit platform the size of the GGTT
538 * is limited to 2G, which is less than GUC_GGTT_TOP, but we reserve a chunk
539 * of the same size anyway, which is far more than needed, to keep the logic
540 * in uc_fw_ggtt_offset() simple.
541 */
542#define GUC_TOP_RESERVE_SIZE (SZ_4G - GUC_GGTT_TOP)
543
544static int ggtt_reserve_guc_top(struct i915_ggtt *ggtt)
545{
546	u64 offset;
547	int ret;
548
549	if (!intel_uc_uses_guc(&ggtt->vm.gt->uc))
550		return 0;
551
552	GEM_BUG_ON(ggtt->vm.total <= GUC_TOP_RESERVE_SIZE);
553	offset = ggtt->vm.total - GUC_TOP_RESERVE_SIZE;
554
555	ret = i915_gem_gtt_reserve(&ggtt->vm, NULL, &ggtt->uc_fw,
556				   GUC_TOP_RESERVE_SIZE, offset,
557				   I915_COLOR_UNEVICTABLE, PIN_NOEVICT);
558	if (ret)
559		drm_dbg(&ggtt->vm.i915->drm,
560			"Failed to reserve top of GGTT for GuC\n");
561
562	return ret;
563}
564
565static void ggtt_release_guc_top(struct i915_ggtt *ggtt)
566{
567	if (drm_mm_node_allocated(&ggtt->uc_fw))
568		drm_mm_remove_node(&ggtt->uc_fw);
569}
570
571static void cleanup_init_ggtt(struct i915_ggtt *ggtt)
572{
573	ggtt_release_guc_top(ggtt);
574	if (drm_mm_node_allocated(&ggtt->error_capture))
575		drm_mm_remove_node(&ggtt->error_capture);
576	mutex_destroy(&ggtt->error_mutex);
577}
578
579static int init_ggtt(struct i915_ggtt *ggtt)
580{
581	/*
582	 * Let GEM Manage all of the aperture.
583	 *
584	 * However, leave one page at the end still bound to the scratch page.
585	 * There are a number of places where the hardware apparently prefetches
586	 * past the end of the object, and we've seen multiple hangs with the
587	 * GPU head pointer stuck in a batchbuffer bound at the last page of the
588	 * aperture.  One page should be enough to keep any prefetching inside
589	 * of the aperture.
590	 */
591	unsigned long hole_start, hole_end;
592	struct drm_mm_node *entry;
593	int ret;
594
595	/*
596	 * GuC requires all resources that we're sharing with it to be placed in
597	 * non-WOPCM memory. If GuC is not present or not in use we still need a
598	 * small bias as ring wraparound at offset 0 sometimes hangs. No idea
599	 * why.
600	 */
601	ggtt->pin_bias = max_t(u32, I915_GTT_PAGE_SIZE,
602			       intel_wopcm_guc_size(&ggtt->vm.gt->wopcm));
603
604	ret = intel_vgt_balloon(ggtt);
605	if (ret)
606		return ret;
607
608	mutex_init(&ggtt->error_mutex);
609	if (ggtt->mappable_end) {
610		/*
611		 * Reserve a mappable slot for our lockless error capture.
612		 *
613		 * We strongly prefer taking address 0x0 in order to protect
614		 * other critical buffers against accidental overwrites,
615		 * as writing to address 0 is a very common mistake.
616		 *
617		 * Since 0 may already be in use by the system (e.g. the BIOS
618		 * framebuffer), we let the reservation fail quietly and hope
619		 * 0 remains reserved always.
620		 *
621		 * If we fail to reserve 0, and then fail to find any space
622		 * for an error-capture, remain silent. We can afford not
623		 * to reserve an error_capture node as we have fallback
624		 * paths, and we trust that 0 will remain reserved. However,
625		 * the only likely reason for failure to insert is a driver
626		 * bug, which we expect to cause other failures...
627		 *
628		 * Since CPU can perform speculative reads on error capture
629		 * (write-combining allows it) add scratch page after error
630		 * capture to avoid DMAR errors.
631		 */
632		ggtt->error_capture.size = 2 * I915_GTT_PAGE_SIZE;
633		ggtt->error_capture.color = I915_COLOR_UNEVICTABLE;
634		if (drm_mm_reserve_node(&ggtt->vm.mm, &ggtt->error_capture))
635			drm_mm_insert_node_in_range(&ggtt->vm.mm,
636						    &ggtt->error_capture,
637						    ggtt->error_capture.size, 0,
638						    ggtt->error_capture.color,
639						    0, ggtt->mappable_end,
640						    DRM_MM_INSERT_LOW);
641	}
642	if (drm_mm_node_allocated(&ggtt->error_capture)) {
643		u64 start = ggtt->error_capture.start;
644		u64 size = ggtt->error_capture.size;
645
646		ggtt->vm.scratch_range(&ggtt->vm, start, size);
647		drm_dbg(&ggtt->vm.i915->drm,
648			"Reserved GGTT:[%llx, %llx] for use by error capture\n",
649			start, start + size);
650	}
651
652	/*
653	 * The upper portion of the GuC address space has a sizeable hole
654	 * (several MB) that is inaccessible by GuC. Reserve this range within
655	 * GGTT as it can comfortably hold GuC/HuC firmware images.
656	 */
657	ret = ggtt_reserve_guc_top(ggtt);
658	if (ret)
659		goto err;
660
661	/* Clear any non-preallocated blocks */
662	drm_mm_for_each_hole(entry, &ggtt->vm.mm, hole_start, hole_end) {
663		drm_dbg(&ggtt->vm.i915->drm,
664			"clearing unused GTT space: [%lx, %lx]\n",
665			hole_start, hole_end);
666		ggtt->vm.clear_range(&ggtt->vm, hole_start,
667				     hole_end - hole_start);
668	}
669
670	/* And finally clear the reserved guard page */
671	ggtt->vm.clear_range(&ggtt->vm, ggtt->vm.total - PAGE_SIZE, PAGE_SIZE);
672
673	return 0;
674
675err:
676	cleanup_init_ggtt(ggtt);
677	return ret;
678}
679
680static void aliasing_gtt_bind_vma(struct i915_address_space *vm,
681				  struct i915_vm_pt_stash *stash,
682				  struct i915_vma_resource *vma_res,
683				  unsigned int pat_index,
684				  u32 flags)
685{
686	u32 pte_flags;
687
688	/* Currently applicable only to VLV */
689	pte_flags = 0;
690	if (vma_res->bi.readonly)
691		pte_flags |= PTE_READ_ONLY;
692
693	if (flags & I915_VMA_LOCAL_BIND)
694		ppgtt_bind_vma(&i915_vm_to_ggtt(vm)->alias->vm,
695			       stash, vma_res, pat_index, flags);
696
697	if (flags & I915_VMA_GLOBAL_BIND)
698		vm->insert_entries(vm, vma_res, pat_index, pte_flags);
699
700	vma_res->bound_flags |= flags;
701}
702
703static void aliasing_gtt_unbind_vma(struct i915_address_space *vm,
704				    struct i915_vma_resource *vma_res)
705{
706	if (vma_res->bound_flags & I915_VMA_GLOBAL_BIND)
707		vm->clear_range(vm, vma_res->start, vma_res->vma_size);
708
709	if (vma_res->bound_flags & I915_VMA_LOCAL_BIND)
710		ppgtt_unbind_vma(&i915_vm_to_ggtt(vm)->alias->vm, vma_res);
711}
712
713static int init_aliasing_ppgtt(struct i915_ggtt *ggtt)
714{
715	struct i915_vm_pt_stash stash = {};
716	struct i915_ppgtt *ppgtt;
717	int err;
718
719	ppgtt = i915_ppgtt_create(ggtt->vm.gt, 0);
720	if (IS_ERR(ppgtt))
721		return PTR_ERR(ppgtt);
722
723	if (GEM_WARN_ON(ppgtt->vm.total < ggtt->vm.total)) {
724		err = -ENODEV;
725		goto err_ppgtt;
726	}
727
728	err = i915_vm_alloc_pt_stash(&ppgtt->vm, &stash, ggtt->vm.total);
729	if (err)
730		goto err_ppgtt;
731
732	i915_gem_object_lock(ppgtt->vm.scratch[0], NULL);
733	err = i915_vm_map_pt_stash(&ppgtt->vm, &stash);
734	i915_gem_object_unlock(ppgtt->vm.scratch[0]);
735	if (err)
736		goto err_stash;
737
738	/*
739	 * Note we only pre-allocate as far as the end of the global
740	 * GTT. On 48b / 4-level page-tables, the difference is very,
741	 * very significant! We have to preallocate as GVT/vgpu does
742	 * not like the page directory disappearing.
743	 */
744	ppgtt->vm.allocate_va_range(&ppgtt->vm, &stash, 0, ggtt->vm.total);
745
746	ggtt->alias = ppgtt;
747	ggtt->vm.bind_async_flags |= ppgtt->vm.bind_async_flags;
748
749	GEM_BUG_ON(ggtt->vm.vma_ops.bind_vma != intel_ggtt_bind_vma);
750	ggtt->vm.vma_ops.bind_vma = aliasing_gtt_bind_vma;
751
752	GEM_BUG_ON(ggtt->vm.vma_ops.unbind_vma != intel_ggtt_unbind_vma);
753	ggtt->vm.vma_ops.unbind_vma = aliasing_gtt_unbind_vma;
754
755	i915_vm_free_pt_stash(&ppgtt->vm, &stash);
756	return 0;
757
758err_stash:
759	i915_vm_free_pt_stash(&ppgtt->vm, &stash);
760err_ppgtt:
761	i915_vm_put(&ppgtt->vm);
762	return err;
763}
764
765static void fini_aliasing_ppgtt(struct i915_ggtt *ggtt)
766{
767	struct i915_ppgtt *ppgtt;
768
769	ppgtt = fetch_and_zero(&ggtt->alias);
770	if (!ppgtt)
771		return;
772
773	i915_vm_put(&ppgtt->vm);
774
775	ggtt->vm.vma_ops.bind_vma   = intel_ggtt_bind_vma;
776	ggtt->vm.vma_ops.unbind_vma = intel_ggtt_unbind_vma;
777}
778
779int i915_init_ggtt(struct drm_i915_private *i915)
780{
781	int ret;
782
783	ret = init_ggtt(to_gt(i915)->ggtt);
784	if (ret)
785		return ret;
786
787	if (INTEL_PPGTT(i915) == INTEL_PPGTT_ALIASING) {
788		ret = init_aliasing_ppgtt(to_gt(i915)->ggtt);
789		if (ret)
790			cleanup_init_ggtt(to_gt(i915)->ggtt);
791	}
792
793	return 0;
794}
795
796static void ggtt_cleanup_hw(struct i915_ggtt *ggtt)
797{
798	struct i915_vma *vma, *vn;
799
800	flush_workqueue(ggtt->vm.i915->wq);
801	i915_gem_drain_freed_objects(ggtt->vm.i915);
802
803	mutex_lock(&ggtt->vm.mutex);
804
805	ggtt->vm.skip_pte_rewrite = true;
806
807	list_for_each_entry_safe(vma, vn, &ggtt->vm.bound_list, vm_link) {
808		struct drm_i915_gem_object *obj = vma->obj;
809		bool trylock;
810
811		trylock = i915_gem_object_trylock(obj, NULL);
812		WARN_ON(!trylock);
813
814		WARN_ON(__i915_vma_unbind(vma));
815		if (trylock)
816			i915_gem_object_unlock(obj);
817	}
818
819	if (drm_mm_node_allocated(&ggtt->error_capture))
820		drm_mm_remove_node(&ggtt->error_capture);
821	mutex_destroy(&ggtt->error_mutex);
822
823	ggtt_release_guc_top(ggtt);
824	intel_vgt_deballoon(ggtt);
825
826	ggtt->vm.cleanup(&ggtt->vm);
827
828	mutex_unlock(&ggtt->vm.mutex);
829	i915_address_space_fini(&ggtt->vm);
830
831	arch_phys_wc_del(ggtt->mtrr);
832
833	if (ggtt->iomap.size)
834		io_mapping_fini(&ggtt->iomap);
835}
836
837/**
838 * i915_ggtt_driver_release - Clean up GGTT hardware initialization
839 * @i915: i915 device
840 */
841void i915_ggtt_driver_release(struct drm_i915_private *i915)
842{
843	struct i915_ggtt *ggtt = to_gt(i915)->ggtt;
844
845	fini_aliasing_ppgtt(ggtt);
846
847	intel_ggtt_fini_fences(ggtt);
848	ggtt_cleanup_hw(ggtt);
849}
850
851/**
852 * i915_ggtt_driver_late_release - Cleanup of GGTT that needs to be done after
853 * all free objects have been drained.
854 * @i915: i915 device
855 */
856void i915_ggtt_driver_late_release(struct drm_i915_private *i915)
857{
858	struct i915_ggtt *ggtt = to_gt(i915)->ggtt;
859
860	GEM_WARN_ON(kref_read(&ggtt->vm.resv_ref) != 1);
861	dma_resv_fini(&ggtt->vm._resv);
862}
863
864static unsigned int gen6_get_total_gtt_size(u16 snb_gmch_ctl)
865{
866	snb_gmch_ctl >>= SNB_GMCH_GGMS_SHIFT;
867	snb_gmch_ctl &= SNB_GMCH_GGMS_MASK;
868	return snb_gmch_ctl << 20;
869}
870
871static unsigned int gen8_get_total_gtt_size(u16 bdw_gmch_ctl)
872{
873	bdw_gmch_ctl >>= BDW_GMCH_GGMS_SHIFT;
874	bdw_gmch_ctl &= BDW_GMCH_GGMS_MASK;
875	if (bdw_gmch_ctl)
876		bdw_gmch_ctl = 1 << bdw_gmch_ctl;
877
878#ifdef CONFIG_X86_32
879	/* Limit 32b platforms to a 2GB GGTT: 4 << 20 / pte size * I915_GTT_PAGE_SIZE */
880	if (bdw_gmch_ctl > 4)
881		bdw_gmch_ctl = 4;
882#endif
883
884	return bdw_gmch_ctl << 20;
885}
886
887static unsigned int chv_get_total_gtt_size(u16 gmch_ctrl)
888{
889	gmch_ctrl >>= SNB_GMCH_GGMS_SHIFT;
890	gmch_ctrl &= SNB_GMCH_GGMS_MASK;
891
892	if (gmch_ctrl)
893		return 1 << (20 + gmch_ctrl);
894
895	return 0;
896}
897
898static unsigned int gen6_gttmmadr_size(struct drm_i915_private *i915)
899{
900	/*
901	 * GEN6: GTTMMADR size is 4MB and GTTADR starts at 2MB offset
902	 * GEN8: GTTMMADR size is 16MB and GTTADR starts at 8MB offset
903	 */
904	GEM_BUG_ON(GRAPHICS_VER(i915) < 6);
905	return (GRAPHICS_VER(i915) < 8) ? SZ_4M : SZ_16M;
906}
907
908static unsigned int gen6_gttadr_offset(struct drm_i915_private *i915)
909{
910	return gen6_gttmmadr_size(i915) / 2;
911}
912
913static int ggtt_probe_common(struct i915_ggtt *ggtt, u64 size)
914{
915	struct drm_i915_private *i915 = ggtt->vm.i915;
916	struct pci_dev *pdev = to_pci_dev(i915->drm.dev);
917	phys_addr_t phys_addr;
918	u32 pte_flags;
919	int ret;
920
921	GEM_WARN_ON(pci_resource_len(pdev, GEN4_GTTMMADR_BAR) != gen6_gttmmadr_size(i915));
922	phys_addr = pci_resource_start(pdev, GEN4_GTTMMADR_BAR) + gen6_gttadr_offset(i915);
923
924	if (needs_wc_ggtt_mapping(i915))
925		ggtt->gsm = ioremap_wc(phys_addr, size);
926	else
927		ggtt->gsm = ioremap(phys_addr, size);
928
929	if (!ggtt->gsm) {
930		drm_err(&i915->drm, "Failed to map the ggtt page table\n");
931		return -ENOMEM;
932	}
933
934	kref_init(&ggtt->vm.resv_ref);
935	ret = setup_scratch_page(&ggtt->vm);
936	if (ret) {
937		drm_err(&i915->drm, "Scratch setup failed\n");
938		/* iounmap will also get called at remove, but meh */
939		iounmap(ggtt->gsm);
940		return ret;
941	}
942
943	pte_flags = 0;
944	if (i915_gem_object_is_lmem(ggtt->vm.scratch[0]))
945		pte_flags |= PTE_LM;
946
947	ggtt->vm.scratch[0]->encode =
948		ggtt->vm.pte_encode(px_dma(ggtt->vm.scratch[0]),
949				    i915_gem_get_pat_index(i915,
950							   I915_CACHE_NONE),
951				    pte_flags);
952
953	return 0;
954}
955
956static void gen6_gmch_remove(struct i915_address_space *vm)
957{
958	struct i915_ggtt *ggtt = i915_vm_to_ggtt(vm);
959
960	iounmap(ggtt->gsm);
961	free_scratch(vm);
962}
963
964static struct resource pci_resource(struct pci_dev *pdev, int bar)
965{
966	return DEFINE_RES_MEM(pci_resource_start(pdev, bar),
967			      pci_resource_len(pdev, bar));
968}
969
970static int gen8_gmch_probe(struct i915_ggtt *ggtt)
971{
972	struct drm_i915_private *i915 = ggtt->vm.i915;
973	struct pci_dev *pdev = to_pci_dev(i915->drm.dev);
974	unsigned int size;
975	u16 snb_gmch_ctl;
976
977	if (!HAS_LMEM(i915) && !HAS_LMEMBAR_SMEM_STOLEN(i915)) {
978		if (!i915_pci_resource_valid(pdev, GEN4_GMADR_BAR))
979			return -ENXIO;
980
981		ggtt->gmadr = pci_resource(pdev, GEN4_GMADR_BAR);
982		ggtt->mappable_end = resource_size(&ggtt->gmadr);
983	}
984
985	pci_read_config_word(pdev, SNB_GMCH_CTRL, &snb_gmch_ctl);
986	if (IS_CHERRYVIEW(i915))
987		size = chv_get_total_gtt_size(snb_gmch_ctl);
988	else
989		size = gen8_get_total_gtt_size(snb_gmch_ctl);
990
991	ggtt->vm.alloc_pt_dma = alloc_pt_dma;
992	ggtt->vm.alloc_scratch_dma = alloc_pt_dma;
993	ggtt->vm.lmem_pt_obj_flags = I915_BO_ALLOC_PM_EARLY;
994
995	ggtt->vm.total = (size / sizeof(gen8_pte_t)) * I915_GTT_PAGE_SIZE;
996	ggtt->vm.cleanup = gen6_gmch_remove;
997	ggtt->vm.insert_page = gen8_ggtt_insert_page;
998	ggtt->vm.clear_range = nop_clear_range;
999	ggtt->vm.scratch_range = gen8_ggtt_clear_range;
1000
1001	ggtt->vm.insert_entries = gen8_ggtt_insert_entries;
1002
1003	/*
1004	 * Serialize GTT updates with aperture access on BXT if VT-d is on,
1005	 * and always on CHV.
1006	 */
1007	if (intel_vm_no_concurrent_access_wa(i915)) {
1008		ggtt->vm.insert_entries = bxt_vtd_ggtt_insert_entries__BKL;
1009		ggtt->vm.insert_page    = bxt_vtd_ggtt_insert_page__BKL;
1010
1011		/*
1012		 * Calling stop_machine() version of GGTT update function
1013		 * at error capture/reset path will raise lockdep warning.
1014		 * Allow calling gen8_ggtt_insert_* directly at reset path
1015		 * which is safe from parallel GGTT updates.
1016		 */
1017		ggtt->vm.raw_insert_page = gen8_ggtt_insert_page;
1018		ggtt->vm.raw_insert_entries = gen8_ggtt_insert_entries;
1019
1020		ggtt->vm.bind_async_flags =
1021			I915_VMA_GLOBAL_BIND | I915_VMA_LOCAL_BIND;
1022	}
1023
1024	if (intel_uc_wants_guc(&ggtt->vm.gt->uc))
1025		ggtt->invalidate = guc_ggtt_invalidate;
1026	else
1027		ggtt->invalidate = gen8_ggtt_invalidate;
1028
1029	ggtt->vm.vma_ops.bind_vma    = intel_ggtt_bind_vma;
1030	ggtt->vm.vma_ops.unbind_vma  = intel_ggtt_unbind_vma;
1031
1032	if (GRAPHICS_VER_FULL(i915) >= IP_VER(12, 70))
1033		ggtt->vm.pte_encode = mtl_ggtt_pte_encode;
1034	else
1035		ggtt->vm.pte_encode = gen8_ggtt_pte_encode;
1036
1037	return ggtt_probe_common(ggtt, size);
1038}
1039
1040/*
1041 * For pre-gen8 platforms pat_index is the same as enum i915_cache_level,
1042 * so the switch-case statements in these PTE encode functions are still valid.
1043 * See translation table LEGACY_CACHELEVEL.
1044 */
1045static u64 snb_pte_encode(dma_addr_t addr,
1046			  unsigned int pat_index,
1047			  u32 flags)
1048{
1049	gen6_pte_t pte = GEN6_PTE_ADDR_ENCODE(addr) | GEN6_PTE_VALID;
1050
1051	switch (pat_index) {
1052	case I915_CACHE_L3_LLC:
1053	case I915_CACHE_LLC:
1054		pte |= GEN6_PTE_CACHE_LLC;
1055		break;
1056	case I915_CACHE_NONE:
1057		pte |= GEN6_PTE_UNCACHED;
1058		break;
1059	default:
1060		MISSING_CASE(pat_index);
1061	}
1062
1063	return pte;
1064}
1065
1066static u64 ivb_pte_encode(dma_addr_t addr,
1067			  unsigned int pat_index,
1068			  u32 flags)
1069{
1070	gen6_pte_t pte = GEN6_PTE_ADDR_ENCODE(addr) | GEN6_PTE_VALID;
1071
1072	switch (pat_index) {
1073	case I915_CACHE_L3_LLC:
1074		pte |= GEN7_PTE_CACHE_L3_LLC;
1075		break;
1076	case I915_CACHE_LLC:
1077		pte |= GEN6_PTE_CACHE_LLC;
1078		break;
1079	case I915_CACHE_NONE:
1080		pte |= GEN6_PTE_UNCACHED;
1081		break;
1082	default:
1083		MISSING_CASE(pat_index);
1084	}
1085
1086	return pte;
1087}
1088
1089static u64 byt_pte_encode(dma_addr_t addr,
1090			  unsigned int pat_index,
1091			  u32 flags)
1092{
1093	gen6_pte_t pte = GEN6_PTE_ADDR_ENCODE(addr) | GEN6_PTE_VALID;
1094
1095	if (!(flags & PTE_READ_ONLY))
1096		pte |= BYT_PTE_WRITEABLE;
1097
1098	if (pat_index != I915_CACHE_NONE)
1099		pte |= BYT_PTE_SNOOPED_BY_CPU_CACHES;
1100
1101	return pte;
1102}
1103
1104static u64 hsw_pte_encode(dma_addr_t addr,
1105			  unsigned int pat_index,
1106			  u32 flags)
1107{
1108	gen6_pte_t pte = HSW_PTE_ADDR_ENCODE(addr) | GEN6_PTE_VALID;
1109
1110	if (pat_index != I915_CACHE_NONE)
1111		pte |= HSW_WB_LLC_AGE3;
1112
1113	return pte;
1114}
1115
1116static u64 iris_pte_encode(dma_addr_t addr,
1117			   unsigned int pat_index,
1118			   u32 flags)
1119{
1120	gen6_pte_t pte = HSW_PTE_ADDR_ENCODE(addr) | GEN6_PTE_VALID;
1121
1122	switch (pat_index) {
1123	case I915_CACHE_NONE:
1124		break;
1125	case I915_CACHE_WT:
1126		pte |= HSW_WT_ELLC_LLC_AGE3;
1127		break;
1128	default:
1129		pte |= HSW_WB_ELLC_LLC_AGE3;
1130		break;
1131	}
1132
1133	return pte;
1134}
1135
1136static int gen6_gmch_probe(struct i915_ggtt *ggtt)
1137{
1138	struct drm_i915_private *i915 = ggtt->vm.i915;
1139	struct pci_dev *pdev = to_pci_dev(i915->drm.dev);
1140	unsigned int size;
1141	u16 snb_gmch_ctl;
1142
1143	if (!i915_pci_resource_valid(pdev, GEN4_GMADR_BAR))
1144		return -ENXIO;
1145
1146	ggtt->gmadr = pci_resource(pdev, GEN4_GMADR_BAR);
1147	ggtt->mappable_end = resource_size(&ggtt->gmadr);
1148
1149	/*
1150	 * 64/512MB is the current min/max we actually know of, but this is
1151	 * just a coarse sanity check.
1152	 */
1153	if (ggtt->mappable_end < (64 << 20) ||
1154	    ggtt->mappable_end > (512 << 20)) {
1155		drm_err(&i915->drm, "Unknown GMADR size (%pa)\n",
1156			&ggtt->mappable_end);
1157		return -ENXIO;
1158	}
1159
1160	pci_read_config_word(pdev, SNB_GMCH_CTRL, &snb_gmch_ctl);
1161
1162	size = gen6_get_total_gtt_size(snb_gmch_ctl);
1163	ggtt->vm.total = (size / sizeof(gen6_pte_t)) * I915_GTT_PAGE_SIZE;
1164
1165	ggtt->vm.alloc_pt_dma = alloc_pt_dma;
1166	ggtt->vm.alloc_scratch_dma = alloc_pt_dma;
1167
1168	ggtt->vm.clear_range = nop_clear_range;
1169	if (!HAS_FULL_PPGTT(i915))
1170		ggtt->vm.clear_range = gen6_ggtt_clear_range;
1171	ggtt->vm.scratch_range = gen6_ggtt_clear_range;
1172	ggtt->vm.insert_page = gen6_ggtt_insert_page;
1173	ggtt->vm.insert_entries = gen6_ggtt_insert_entries;
1174	ggtt->vm.cleanup = gen6_gmch_remove;
1175
1176	ggtt->invalidate = gen6_ggtt_invalidate;
1177
1178	if (HAS_EDRAM(i915))
1179		ggtt->vm.pte_encode = iris_pte_encode;
1180	else if (IS_HASWELL(i915))
1181		ggtt->vm.pte_encode = hsw_pte_encode;
1182	else if (IS_VALLEYVIEW(i915))
1183		ggtt->vm.pte_encode = byt_pte_encode;
1184	else if (GRAPHICS_VER(i915) >= 7)
1185		ggtt->vm.pte_encode = ivb_pte_encode;
1186	else
1187		ggtt->vm.pte_encode = snb_pte_encode;
1188
1189	ggtt->vm.vma_ops.bind_vma    = intel_ggtt_bind_vma;
1190	ggtt->vm.vma_ops.unbind_vma  = intel_ggtt_unbind_vma;
1191
1192	return ggtt_probe_common(ggtt, size);
1193}
1194
1195static int ggtt_probe_hw(struct i915_ggtt *ggtt, struct intel_gt *gt)
1196{
1197	struct drm_i915_private *i915 = gt->i915;
1198	int ret;
1199
1200	ggtt->vm.gt = gt;
1201	ggtt->vm.i915 = i915;
1202	ggtt->vm.dma = i915->drm.dev;
1203	dma_resv_init(&ggtt->vm._resv);
1204
1205	if (GRAPHICS_VER(i915) >= 8)
1206		ret = gen8_gmch_probe(ggtt);
1207	else if (GRAPHICS_VER(i915) >= 6)
1208		ret = gen6_gmch_probe(ggtt);
1209	else
1210		ret = intel_ggtt_gmch_probe(ggtt);
1211
1212	if (ret) {
1213		dma_resv_fini(&ggtt->vm._resv);
1214		return ret;
1215	}
1216
1217	if ((ggtt->vm.total - 1) >> 32) {
1218		drm_err(&i915->drm,
1219			"We never expected a Global GTT with more than 32bits"
1220			" of address space! Found %lldM!\n",
1221			ggtt->vm.total >> 20);
1222		ggtt->vm.total = 1ULL << 32;
1223		ggtt->mappable_end =
1224			min_t(u64, ggtt->mappable_end, ggtt->vm.total);
1225	}
1226
1227	if (ggtt->mappable_end > ggtt->vm.total) {
1228		drm_err(&i915->drm,
1229			"mappable aperture extends past end of GGTT,"
1230			" aperture=%pa, total=%llx\n",
1231			&ggtt->mappable_end, ggtt->vm.total);
1232		ggtt->mappable_end = ggtt->vm.total;
1233	}
1234
1235	/* GMADR is the PCI mmio aperture into the global GTT. */
1236	drm_dbg(&i915->drm, "GGTT size = %lluM\n", ggtt->vm.total >> 20);
1237	drm_dbg(&i915->drm, "GMADR size = %lluM\n",
1238		(u64)ggtt->mappable_end >> 20);
1239	drm_dbg(&i915->drm, "DSM size = %lluM\n",
1240		(u64)resource_size(&intel_graphics_stolen_res) >> 20);
1241
1242	return 0;
1243}
1244
1245/**
1246 * i915_ggtt_probe_hw - Probe GGTT hardware location
1247 * @i915: i915 device
1248 */
1249int i915_ggtt_probe_hw(struct drm_i915_private *i915)
1250{
1251	struct intel_gt *gt;
1252	int ret, i;
1253
1254	for_each_gt(gt, i915, i) {
1255		ret = intel_gt_assign_ggtt(gt);
1256		if (ret)
1257			return ret;
1258	}
1259
1260	ret = ggtt_probe_hw(to_gt(i915)->ggtt, to_gt(i915));
1261	if (ret)
1262		return ret;
1263
1264	if (i915_vtd_active(i915))
1265		drm_info(&i915->drm, "VT-d active for gfx access\n");
1266
1267	return 0;
1268}
1269
1270struct i915_ggtt *i915_ggtt_create(struct drm_i915_private *i915)
1271{
1272	struct i915_ggtt *ggtt;
1273
1274	ggtt = drmm_kzalloc(&i915->drm, sizeof(*ggtt), GFP_KERNEL);
1275	if (!ggtt)
1276		return ERR_PTR(-ENOMEM);
1277
1278	INIT_LIST_HEAD(&ggtt->gt_list);
1279
1280	return ggtt;
1281}
1282
1283int i915_ggtt_enable_hw(struct drm_i915_private *i915)
1284{
1285	if (GRAPHICS_VER(i915) < 6)
1286		return intel_ggtt_gmch_enable_hw(i915);
1287
1288	return 0;
1289}
1290
1291/**
1292 * i915_ggtt_resume_vm - Restore the memory mappings for a GGTT or DPT VM
1293 * @vm: The VM to restore the mappings for
1294 *
1295 * Restore the memory mappings for all objects mapped to HW via the GGTT or a
1296 * DPT page table.
1297 *
1298 * Returns %true if restoring the mapping for any object that was in a write
1299 * domain before suspend.
1300 */
1301bool i915_ggtt_resume_vm(struct i915_address_space *vm)
1302{
1303	struct i915_vma *vma;
1304	bool write_domain_objs = false;
1305
1306	drm_WARN_ON(&vm->i915->drm, !vm->is_ggtt && !vm->is_dpt);
1307
1308	/* First fill our portion of the GTT with scratch pages */
1309	vm->clear_range(vm, 0, vm->total);
1310
1311	/* clflush objects bound into the GGTT and rebind them. */
1312	list_for_each_entry(vma, &vm->bound_list, vm_link) {
1313		struct drm_i915_gem_object *obj = vma->obj;
1314		unsigned int was_bound =
1315			atomic_read(&vma->flags) & I915_VMA_BIND_MASK;
1316
1317		GEM_BUG_ON(!was_bound);
1318
1319		/*
1320		 * Clear the bound flags of the vma resource to allow
1321		 * ptes to be repopulated.
1322		 */
1323		vma->resource->bound_flags = 0;
1324		vma->ops->bind_vma(vm, NULL, vma->resource,
1325				   obj ? obj->pat_index :
1326					 i915_gem_get_pat_index(vm->i915,
1327								I915_CACHE_NONE),
1328				   was_bound);
1329
1330		if (obj) { /* only used during resume => exclusive access */
1331			write_domain_objs |= fetch_and_zero(&obj->write_domain);
1332			obj->read_domains |= I915_GEM_DOMAIN_GTT;
1333		}
1334	}
1335
1336	return write_domain_objs;
1337}
1338
1339void i915_ggtt_resume(struct i915_ggtt *ggtt)
1340{
1341	struct intel_gt *gt;
1342	bool flush;
1343
1344	list_for_each_entry(gt, &ggtt->gt_list, ggtt_link)
1345		intel_gt_check_and_clear_faults(gt);
1346
1347	flush = i915_ggtt_resume_vm(&ggtt->vm);
1348
1349	if (drm_mm_node_allocated(&ggtt->error_capture))
1350		ggtt->vm.scratch_range(&ggtt->vm, ggtt->error_capture.start,
1351				       ggtt->error_capture.size);
1352
1353	list_for_each_entry(gt, &ggtt->gt_list, ggtt_link)
1354		intel_uc_resume_mappings(&gt->uc);
1355
1356	ggtt->invalidate(ggtt);
1357
1358	if (flush)
1359		wbinvd_on_all_cpus();
1360
1361	intel_ggtt_restore_fences(ggtt);
1362}
1363