1/*
2 * Copyright (c) 2005 Topspin Communications.  All rights reserved.
3 * Copyright (c) 2005 Cisco Systems.  All rights reserved.
4 * Copyright (c) 2005 Mellanox Technologies. All rights reserved.
5 *
6 * This software is available to you under a choice of one of two
7 * licenses.  You may choose to be licensed under the terms of the GNU
8 * General Public License (GPL) Version 2, available from the file
9 * COPYING in the main directory of this source tree, or the
10 * OpenIB.org BSD license below:
11 *
12 *     Redistribution and use in source and binary forms, with or
13 *     without modification, are permitted provided that the following
14 *     conditions are met:
15 *
16 *      - Redistributions of source code must retain the above
17 *        copyright notice, this list of conditions and the following
18 *        disclaimer.
19 *
20 *      - Redistributions in binary form must reproduce the above
21 *        copyright notice, this list of conditions and the following
22 *        disclaimer in the documentation and/or other materials
23 *        provided with the distribution.
24 *
25 * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
26 * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
27 * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
28 * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
29 * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
30 * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
31 * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
32 * SOFTWARE.
33 */
34
35#include <linux/mm.h>
36#include <linux/dma-mapping.h>
37#include <linux/sched/signal.h>
38#include <linux/sched/mm.h>
39#include <linux/export.h>
40#include <linux/slab.h>
41#include <linux/pagemap.h>
42#include <linux/count_zeros.h>
43#include <rdma/ib_umem_odp.h>
44
45#include "uverbs.h"
46
47static void __ib_umem_release(struct ib_device *dev, struct ib_umem *umem, int dirty)
48{
49	struct sg_page_iter sg_iter;
50	struct page *page;
51
52	if (umem->nmap > 0)
53		ib_dma_unmap_sg(dev, umem->sg_head.sgl, umem->sg_nents,
54				DMA_BIDIRECTIONAL);
55
56	for_each_sg_page(umem->sg_head.sgl, &sg_iter, umem->sg_nents, 0) {
57		page = sg_page_iter_page(&sg_iter);
58		unpin_user_pages_dirty_lock(&page, 1, umem->writable && dirty);
59	}
60
61	sg_free_table(&umem->sg_head);
62}
63
64/**
65 * ib_umem_find_best_pgsz - Find best HW page size to use for this MR
66 *
67 * @umem: umem struct
68 * @pgsz_bitmap: bitmap of HW supported page sizes
69 * @virt: IOVA
70 *
71 * This helper is intended for HW that support multiple page
72 * sizes but can do only a single page size in an MR.
73 *
74 * Returns 0 if the umem requires page sizes not supported by
75 * the driver to be mapped. Drivers always supporting PAGE_SIZE
76 * or smaller will never see a 0 result.
77 */
78unsigned long ib_umem_find_best_pgsz(struct ib_umem *umem,
79				     unsigned long pgsz_bitmap,
80				     unsigned long virt)
81{
82	struct scatterlist *sg;
83	unsigned long va, pgoff;
84	dma_addr_t mask;
85	int i;
86
87	/* rdma_for_each_block() has a bug if the page size is smaller than the
88	 * page size used to build the umem. For now prevent smaller page sizes
89	 * from being returned.
90	 */
91	pgsz_bitmap &= GENMASK(BITS_PER_LONG - 1, PAGE_SHIFT);
92
93	/* At minimum, drivers must support PAGE_SIZE or smaller */
94	if (WARN_ON(!(pgsz_bitmap & GENMASK(PAGE_SHIFT, 0))))
95		return 0;
96
97	umem->iova = va = virt;
98	/* The best result is the smallest page size that results in the minimum
99	 * number of required pages. Compute the largest page size that could
100	 * work based on VA address bits that don't change.
101	 */
102	mask = pgsz_bitmap &
103	       GENMASK(BITS_PER_LONG - 1,
104		       bits_per((umem->length - 1 + virt) ^ virt));
105	/* offset into first SGL */
106	pgoff = umem->address & ~PAGE_MASK;
107
108	for_each_sg(umem->sg_head.sgl, sg, umem->nmap, i) {
109		/* Walk SGL and reduce max page size if VA/PA bits differ
110		 * for any address.
111		 */
112		mask |= (sg_dma_address(sg) + pgoff) ^ va;
113		va += sg_dma_len(sg) - pgoff;
114		/* Except for the last entry, the ending iova alignment sets
115		 * the maximum possible page size as the low bits of the iova
116		 * must be zero when starting the next chunk.
117		 */
118		if (i != (umem->nmap - 1))
119			mask |= va;
120		pgoff = 0;
121	}
122
123	/* The mask accumulates 1's in each position where the VA and physical
124	 * address differ, thus the length of trailing 0 is the largest page
125	 * size that can pass the VA through to the physical.
126	 */
127	if (mask)
128		pgsz_bitmap &= GENMASK(count_trailing_zeros(mask), 0);
129	return pgsz_bitmap ? rounddown_pow_of_two(pgsz_bitmap) : 0;
130}
131EXPORT_SYMBOL(ib_umem_find_best_pgsz);
132
133/**
134 * ib_umem_get - Pin and DMA map userspace memory.
135 *
136 * @device: IB device to connect UMEM
137 * @addr: userspace virtual address to start at
138 * @size: length of region to pin
139 * @access: IB_ACCESS_xxx flags for memory being pinned
140 */
141struct ib_umem *ib_umem_get(struct ib_device *device, unsigned long addr,
142			    size_t size, int access)
143{
144	struct ib_umem *umem;
145	struct page **page_list;
146	unsigned long lock_limit;
147	unsigned long new_pinned;
148	unsigned long cur_base;
149	unsigned long dma_attr = 0;
150	struct mm_struct *mm;
151	unsigned long npages;
152	int ret;
153	struct scatterlist *sg = NULL;
154	unsigned int gup_flags = FOLL_WRITE;
155
156	/*
157	 * If the combination of the addr and size requested for this memory
158	 * region causes an integer overflow, return error.
159	 */
160	if (((addr + size) < addr) ||
161	    PAGE_ALIGN(addr + size) < (addr + size))
162		return ERR_PTR(-EINVAL);
163
164	if (!can_do_mlock())
165		return ERR_PTR(-EPERM);
166
167	if (access & IB_ACCESS_ON_DEMAND)
168		return ERR_PTR(-EOPNOTSUPP);
169
170	umem = kzalloc(sizeof(*umem), GFP_KERNEL);
171	if (!umem)
172		return ERR_PTR(-ENOMEM);
173	umem->ibdev      = device;
174	umem->length     = size;
175	umem->address    = addr;
176	/*
177	 * Drivers should call ib_umem_find_best_pgsz() to set the iova
178	 * correctly.
179	 */
180	umem->iova = addr;
181	umem->writable   = ib_access_writable(access);
182	umem->owning_mm = mm = current->mm;
183	mmgrab(mm);
184
185	page_list = (struct page **) __get_free_page(GFP_KERNEL);
186	if (!page_list) {
187		ret = -ENOMEM;
188		goto umem_kfree;
189	}
190
191	npages = ib_umem_num_pages(umem);
192	if (npages == 0 || npages > UINT_MAX) {
193		ret = -EINVAL;
194		goto out;
195	}
196
197	lock_limit = rlimit(RLIMIT_MEMLOCK) >> PAGE_SHIFT;
198
199	new_pinned = atomic64_add_return(npages, &mm->pinned_vm);
200	if (new_pinned > lock_limit && !capable(CAP_IPC_LOCK)) {
201		atomic64_sub(npages, &mm->pinned_vm);
202		ret = -ENOMEM;
203		goto out;
204	}
205
206	cur_base = addr & PAGE_MASK;
207
208	if (!umem->writable)
209		gup_flags |= FOLL_FORCE;
210
211	while (npages) {
212		cond_resched();
213		ret = pin_user_pages_fast(cur_base,
214					  min_t(unsigned long, npages,
215						PAGE_SIZE /
216						sizeof(struct page *)),
217					  gup_flags | FOLL_LONGTERM, page_list);
218		if (ret < 0)
219			goto umem_release;
220
221		cur_base += ret * PAGE_SIZE;
222		npages -= ret;
223		sg = __sg_alloc_table_from_pages(&umem->sg_head, page_list, ret,
224				0, ret << PAGE_SHIFT,
225				ib_dma_max_seg_size(device), sg, npages,
226				GFP_KERNEL);
227		umem->sg_nents = umem->sg_head.nents;
228		if (IS_ERR(sg)) {
229			unpin_user_pages_dirty_lock(page_list, ret, 0);
230			ret = PTR_ERR(sg);
231			goto umem_release;
232		}
233	}
234
235	if (access & IB_ACCESS_RELAXED_ORDERING)
236		dma_attr |= DMA_ATTR_WEAK_ORDERING;
237
238	umem->nmap =
239		ib_dma_map_sg_attrs(device, umem->sg_head.sgl, umem->sg_nents,
240				    DMA_BIDIRECTIONAL, dma_attr);
241
242	if (!umem->nmap) {
243		ret = -ENOMEM;
244		goto umem_release;
245	}
246
247	ret = 0;
248	goto out;
249
250umem_release:
251	__ib_umem_release(device, umem, 0);
252	atomic64_sub(ib_umem_num_pages(umem), &mm->pinned_vm);
253out:
254	free_page((unsigned long) page_list);
255umem_kfree:
256	if (ret) {
257		mmdrop(umem->owning_mm);
258		kfree(umem);
259	}
260	return ret ? ERR_PTR(ret) : umem;
261}
262EXPORT_SYMBOL(ib_umem_get);
263
264/**
265 * ib_umem_release - release memory pinned with ib_umem_get
266 * @umem: umem struct to release
267 */
268void ib_umem_release(struct ib_umem *umem)
269{
270	if (!umem)
271		return;
272	if (umem->is_odp)
273		return ib_umem_odp_release(to_ib_umem_odp(umem));
274
275	__ib_umem_release(umem->ibdev, umem, 1);
276
277	atomic64_sub(ib_umem_num_pages(umem), &umem->owning_mm->pinned_vm);
278	mmdrop(umem->owning_mm);
279	kfree(umem);
280}
281EXPORT_SYMBOL(ib_umem_release);
282
283/*
284 * Copy from the given ib_umem's pages to the given buffer.
285 *
286 * umem - the umem to copy from
287 * offset - offset to start copying from
288 * dst - destination buffer
289 * length - buffer length
290 *
291 * Returns 0 on success, or an error code.
292 */
293int ib_umem_copy_from(void *dst, struct ib_umem *umem, size_t offset,
294		      size_t length)
295{
296	size_t end = offset + length;
297	int ret;
298
299	if (offset > umem->length || length > umem->length - offset) {
300		pr_err("ib_umem_copy_from not in range. offset: %zd umem length: %zd end: %zd\n",
301		       offset, umem->length, end);
302		return -EINVAL;
303	}
304
305	ret = sg_pcopy_to_buffer(umem->sg_head.sgl, umem->sg_nents, dst, length,
306				 offset + ib_umem_offset(umem));
307
308	if (ret < 0)
309		return ret;
310	else if (ret != length)
311		return -EINVAL;
312	else
313		return 0;
314}
315EXPORT_SYMBOL(ib_umem_copy_from);
316