1// SPDX-License-Identifier: GPL-2.0-only
2/*
3 * Copyright (C) 2013 Red Hat
4 * Author: Rob Clark <robdclark@gmail.com>
5 */
6
7#include <linux/adreno-smmu-priv.h>
8#include <linux/io-pgtable.h>
9#include "msm_drv.h"
10#include "msm_mmu.h"
11
12struct msm_iommu {
13	struct msm_mmu base;
14	struct iommu_domain *domain;
15	atomic_t pagetables;
16};
17
18#define to_msm_iommu(x) container_of(x, struct msm_iommu, base)
19
20struct msm_iommu_pagetable {
21	struct msm_mmu base;
22	struct msm_mmu *parent;
23	struct io_pgtable_ops *pgtbl_ops;
24	const struct iommu_flush_ops *tlb;
25	struct device *iommu_dev;
26	unsigned long pgsize_bitmap;	/* Bitmap of page sizes in use */
27	phys_addr_t ttbr;
28	u32 asid;
29};
30static struct msm_iommu_pagetable *to_pagetable(struct msm_mmu *mmu)
31{
32	return container_of(mmu, struct msm_iommu_pagetable, base);
33}
34
35/* based on iommu_pgsize() in iommu.c: */
36static size_t calc_pgsize(struct msm_iommu_pagetable *pagetable,
37			   unsigned long iova, phys_addr_t paddr,
38			   size_t size, size_t *count)
39{
40	unsigned int pgsize_idx, pgsize_idx_next;
41	unsigned long pgsizes;
42	size_t offset, pgsize, pgsize_next;
43	unsigned long addr_merge = paddr | iova;
44
45	/* Page sizes supported by the hardware and small enough for @size */
46	pgsizes = pagetable->pgsize_bitmap & GENMASK(__fls(size), 0);
47
48	/* Constrain the page sizes further based on the maximum alignment */
49	if (likely(addr_merge))
50		pgsizes &= GENMASK(__ffs(addr_merge), 0);
51
52	/* Make sure we have at least one suitable page size */
53	BUG_ON(!pgsizes);
54
55	/* Pick the biggest page size remaining */
56	pgsize_idx = __fls(pgsizes);
57	pgsize = BIT(pgsize_idx);
58	if (!count)
59		return pgsize;
60
61	/* Find the next biggest support page size, if it exists */
62	pgsizes = pagetable->pgsize_bitmap & ~GENMASK(pgsize_idx, 0);
63	if (!pgsizes)
64		goto out_set_count;
65
66	pgsize_idx_next = __ffs(pgsizes);
67	pgsize_next = BIT(pgsize_idx_next);
68
69	/*
70	 * There's no point trying a bigger page size unless the virtual
71	 * and physical addresses are similarly offset within the larger page.
72	 */
73	if ((iova ^ paddr) & (pgsize_next - 1))
74		goto out_set_count;
75
76	/* Calculate the offset to the next page size alignment boundary */
77	offset = pgsize_next - (addr_merge & (pgsize_next - 1));
78
79	/*
80	 * If size is big enough to accommodate the larger page, reduce
81	 * the number of smaller pages.
82	 */
83	if (offset + pgsize_next <= size)
84		size = offset;
85
86out_set_count:
87	*count = size >> pgsize_idx;
88	return pgsize;
89}
90
91static int msm_iommu_pagetable_unmap(struct msm_mmu *mmu, u64 iova,
92		size_t size)
93{
94	struct msm_iommu_pagetable *pagetable = to_pagetable(mmu);
95	struct io_pgtable_ops *ops = pagetable->pgtbl_ops;
96
97	while (size) {
98		size_t unmapped, pgsize, count;
99
100		pgsize = calc_pgsize(pagetable, iova, iova, size, &count);
101
102		unmapped = ops->unmap_pages(ops, iova, pgsize, count, NULL);
103		if (!unmapped)
104			break;
105
106		iova += unmapped;
107		size -= unmapped;
108	}
109
110	iommu_flush_iotlb_all(to_msm_iommu(pagetable->parent)->domain);
111
112	return (size == 0) ? 0 : -EINVAL;
113}
114
115static int msm_iommu_pagetable_map(struct msm_mmu *mmu, u64 iova,
116		struct sg_table *sgt, size_t len, int prot)
117{
118	struct msm_iommu_pagetable *pagetable = to_pagetable(mmu);
119	struct io_pgtable_ops *ops = pagetable->pgtbl_ops;
120	struct scatterlist *sg;
121	u64 addr = iova;
122	unsigned int i;
123
124	for_each_sgtable_sg(sgt, sg, i) {
125		size_t size = sg->length;
126		phys_addr_t phys = sg_phys(sg);
127
128		while (size) {
129			size_t pgsize, count, mapped = 0;
130			int ret;
131
132			pgsize = calc_pgsize(pagetable, addr, phys, size, &count);
133
134			ret = ops->map_pages(ops, addr, phys, pgsize, count,
135					     prot, GFP_KERNEL, &mapped);
136
137			/* map_pages could fail after mapping some of the pages,
138			 * so update the counters before error handling.
139			 */
140			phys += mapped;
141			addr += mapped;
142			size -= mapped;
143
144			if (ret) {
145				msm_iommu_pagetable_unmap(mmu, iova, addr - iova);
146				return -EINVAL;
147			}
148		}
149	}
150
151	return 0;
152}
153
154static void msm_iommu_pagetable_destroy(struct msm_mmu *mmu)
155{
156	struct msm_iommu_pagetable *pagetable = to_pagetable(mmu);
157	struct msm_iommu *iommu = to_msm_iommu(pagetable->parent);
158	struct adreno_smmu_priv *adreno_smmu =
159		dev_get_drvdata(pagetable->parent->dev);
160
161	/*
162	 * If this is the last attached pagetable for the parent,
163	 * disable TTBR0 in the arm-smmu driver
164	 */
165	if (atomic_dec_return(&iommu->pagetables) == 0)
166		adreno_smmu->set_ttbr0_cfg(adreno_smmu->cookie, NULL);
167
168	free_io_pgtable_ops(pagetable->pgtbl_ops);
169	kfree(pagetable);
170}
171
172int msm_iommu_pagetable_params(struct msm_mmu *mmu,
173		phys_addr_t *ttbr, int *asid)
174{
175	struct msm_iommu_pagetable *pagetable;
176
177	if (mmu->type != MSM_MMU_IOMMU_PAGETABLE)
178		return -EINVAL;
179
180	pagetable = to_pagetable(mmu);
181
182	if (ttbr)
183		*ttbr = pagetable->ttbr;
184
185	if (asid)
186		*asid = pagetable->asid;
187
188	return 0;
189}
190
191struct iommu_domain_geometry *msm_iommu_get_geometry(struct msm_mmu *mmu)
192{
193	struct msm_iommu *iommu = to_msm_iommu(mmu);
194
195	return &iommu->domain->geometry;
196}
197
198static const struct msm_mmu_funcs pagetable_funcs = {
199		.map = msm_iommu_pagetable_map,
200		.unmap = msm_iommu_pagetable_unmap,
201		.destroy = msm_iommu_pagetable_destroy,
202};
203
204static void msm_iommu_tlb_flush_all(void *cookie)
205{
206	struct msm_iommu_pagetable *pagetable = cookie;
207	struct adreno_smmu_priv *adreno_smmu;
208
209	if (!pm_runtime_get_if_in_use(pagetable->iommu_dev))
210		return;
211
212	adreno_smmu = dev_get_drvdata(pagetable->parent->dev);
213
214	pagetable->tlb->tlb_flush_all((void *)adreno_smmu->cookie);
215
216	pm_runtime_put_autosuspend(pagetable->iommu_dev);
217}
218
219static void msm_iommu_tlb_flush_walk(unsigned long iova, size_t size,
220		size_t granule, void *cookie)
221{
222	struct msm_iommu_pagetable *pagetable = cookie;
223	struct adreno_smmu_priv *adreno_smmu;
224
225	if (!pm_runtime_get_if_in_use(pagetable->iommu_dev))
226		return;
227
228	adreno_smmu = dev_get_drvdata(pagetable->parent->dev);
229
230	pagetable->tlb->tlb_flush_walk(iova, size, granule, (void *)adreno_smmu->cookie);
231
232	pm_runtime_put_autosuspend(pagetable->iommu_dev);
233}
234
235static void msm_iommu_tlb_add_page(struct iommu_iotlb_gather *gather,
236		unsigned long iova, size_t granule, void *cookie)
237{
238}
239
240static const struct iommu_flush_ops tlb_ops = {
241	.tlb_flush_all = msm_iommu_tlb_flush_all,
242	.tlb_flush_walk = msm_iommu_tlb_flush_walk,
243	.tlb_add_page = msm_iommu_tlb_add_page,
244};
245
246static int msm_fault_handler(struct iommu_domain *domain, struct device *dev,
247		unsigned long iova, int flags, void *arg);
248
249struct msm_mmu *msm_iommu_pagetable_create(struct msm_mmu *parent)
250{
251	struct adreno_smmu_priv *adreno_smmu = dev_get_drvdata(parent->dev);
252	struct msm_iommu *iommu = to_msm_iommu(parent);
253	struct msm_iommu_pagetable *pagetable;
254	const struct io_pgtable_cfg *ttbr1_cfg = NULL;
255	struct io_pgtable_cfg ttbr0_cfg;
256	int ret;
257
258	/* Get the pagetable configuration from the domain */
259	if (adreno_smmu->cookie)
260		ttbr1_cfg = adreno_smmu->get_ttbr1_cfg(adreno_smmu->cookie);
261
262	/*
263	 * If you hit this WARN_ONCE() you are probably missing an entry in
264	 * qcom_smmu_impl_of_match[] in arm-smmu-qcom.c
265	 */
266	if (WARN_ONCE(!ttbr1_cfg, "No per-process page tables"))
267		return ERR_PTR(-ENODEV);
268
269	pagetable = kzalloc(sizeof(*pagetable), GFP_KERNEL);
270	if (!pagetable)
271		return ERR_PTR(-ENOMEM);
272
273	msm_mmu_init(&pagetable->base, parent->dev, &pagetable_funcs,
274		MSM_MMU_IOMMU_PAGETABLE);
275
276	/* Clone the TTBR1 cfg as starting point for TTBR0 cfg: */
277	ttbr0_cfg = *ttbr1_cfg;
278
279	/* The incoming cfg will have the TTBR1 quirk enabled */
280	ttbr0_cfg.quirks &= ~IO_PGTABLE_QUIRK_ARM_TTBR1;
281	ttbr0_cfg.tlb = &tlb_ops;
282
283	pagetable->pgtbl_ops = alloc_io_pgtable_ops(ARM_64_LPAE_S1,
284		&ttbr0_cfg, pagetable);
285
286	if (!pagetable->pgtbl_ops) {
287		kfree(pagetable);
288		return ERR_PTR(-ENOMEM);
289	}
290
291	/*
292	 * If this is the first pagetable that we've allocated, send it back to
293	 * the arm-smmu driver as a trigger to set up TTBR0
294	 */
295	if (atomic_inc_return(&iommu->pagetables) == 1) {
296		ret = adreno_smmu->set_ttbr0_cfg(adreno_smmu->cookie, &ttbr0_cfg);
297		if (ret) {
298			free_io_pgtable_ops(pagetable->pgtbl_ops);
299			kfree(pagetable);
300			return ERR_PTR(ret);
301		}
302	}
303
304	/* Needed later for TLB flush */
305	pagetable->parent = parent;
306	pagetable->tlb = ttbr1_cfg->tlb;
307	pagetable->iommu_dev = ttbr1_cfg->iommu_dev;
308	pagetable->pgsize_bitmap = ttbr0_cfg.pgsize_bitmap;
309	pagetable->ttbr = ttbr0_cfg.arm_lpae_s1_cfg.ttbr;
310
311	/*
312	 * TODO we would like each set of page tables to have a unique ASID
313	 * to optimize TLB invalidation.  But iommu_flush_iotlb_all() will
314	 * end up flushing the ASID used for TTBR1 pagetables, which is not
315	 * what we want.  So for now just use the same ASID as TTBR1.
316	 */
317	pagetable->asid = 0;
318
319	return &pagetable->base;
320}
321
322static int msm_fault_handler(struct iommu_domain *domain, struct device *dev,
323		unsigned long iova, int flags, void *arg)
324{
325	struct msm_iommu *iommu = arg;
326	struct msm_mmu *mmu = &iommu->base;
327	struct adreno_smmu_priv *adreno_smmu = dev_get_drvdata(iommu->base.dev);
328	struct adreno_smmu_fault_info info, *ptr = NULL;
329
330	if (adreno_smmu->get_fault_info) {
331		adreno_smmu->get_fault_info(adreno_smmu->cookie, &info);
332		ptr = &info;
333	}
334
335	if (iommu->base.handler)
336		return iommu->base.handler(iommu->base.arg, iova, flags, ptr);
337
338	pr_warn_ratelimited("*** fault: iova=%16lx, flags=%d\n", iova, flags);
339
340	if (mmu->funcs->resume_translation)
341		mmu->funcs->resume_translation(mmu);
342
343	return 0;
344}
345
346static void msm_iommu_resume_translation(struct msm_mmu *mmu)
347{
348	struct adreno_smmu_priv *adreno_smmu = dev_get_drvdata(mmu->dev);
349
350	if (adreno_smmu->resume_translation)
351		adreno_smmu->resume_translation(adreno_smmu->cookie, true);
352}
353
354static void msm_iommu_detach(struct msm_mmu *mmu)
355{
356	struct msm_iommu *iommu = to_msm_iommu(mmu);
357
358	iommu_detach_device(iommu->domain, mmu->dev);
359}
360
361static int msm_iommu_map(struct msm_mmu *mmu, uint64_t iova,
362		struct sg_table *sgt, size_t len, int prot)
363{
364	struct msm_iommu *iommu = to_msm_iommu(mmu);
365	size_t ret;
366
367	/* The arm-smmu driver expects the addresses to be sign extended */
368	if (iova & BIT_ULL(48))
369		iova |= GENMASK_ULL(63, 49);
370
371	ret = iommu_map_sgtable(iommu->domain, iova, sgt, prot);
372	WARN_ON(!ret);
373
374	return (ret == len) ? 0 : -EINVAL;
375}
376
377static int msm_iommu_unmap(struct msm_mmu *mmu, uint64_t iova, size_t len)
378{
379	struct msm_iommu *iommu = to_msm_iommu(mmu);
380
381	if (iova & BIT_ULL(48))
382		iova |= GENMASK_ULL(63, 49);
383
384	iommu_unmap(iommu->domain, iova, len);
385
386	return 0;
387}
388
389static void msm_iommu_destroy(struct msm_mmu *mmu)
390{
391	struct msm_iommu *iommu = to_msm_iommu(mmu);
392	iommu_domain_free(iommu->domain);
393	kfree(iommu);
394}
395
396static const struct msm_mmu_funcs funcs = {
397		.detach = msm_iommu_detach,
398		.map = msm_iommu_map,
399		.unmap = msm_iommu_unmap,
400		.destroy = msm_iommu_destroy,
401		.resume_translation = msm_iommu_resume_translation,
402};
403
404struct msm_mmu *msm_iommu_new(struct device *dev, unsigned long quirks)
405{
406	struct iommu_domain *domain;
407	struct msm_iommu *iommu;
408	int ret;
409
410	domain = iommu_domain_alloc(dev->bus);
411	if (!domain)
412		return NULL;
413
414	iommu_set_pgtable_quirks(domain, quirks);
415
416	iommu = kzalloc(sizeof(*iommu), GFP_KERNEL);
417	if (!iommu) {
418		iommu_domain_free(domain);
419		return ERR_PTR(-ENOMEM);
420	}
421
422	iommu->domain = domain;
423	msm_mmu_init(&iommu->base, dev, &funcs, MSM_MMU_IOMMU);
424
425	atomic_set(&iommu->pagetables, 0);
426
427	ret = iommu_attach_device(iommu->domain, dev);
428	if (ret) {
429		iommu_domain_free(domain);
430		kfree(iommu);
431		return ERR_PTR(ret);
432	}
433
434	return &iommu->base;
435}
436
437struct msm_mmu *msm_iommu_gpu_new(struct device *dev, struct msm_gpu *gpu, unsigned long quirks)
438{
439	struct adreno_smmu_priv *adreno_smmu = dev_get_drvdata(dev);
440	struct msm_iommu *iommu;
441	struct msm_mmu *mmu;
442
443	mmu = msm_iommu_new(dev, quirks);
444	if (IS_ERR_OR_NULL(mmu))
445		return mmu;
446
447	iommu = to_msm_iommu(mmu);
448	iommu_set_fault_handler(iommu->domain, msm_fault_handler, iommu);
449
450	/* Enable stall on iommu fault: */
451	if (adreno_smmu->set_stall)
452		adreno_smmu->set_stall(adreno_smmu->cookie, true);
453
454	return mmu;
455}
456