1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
|
// SPDX-License-Identifier: GPL-2.0-or-later
/* Iterator helpers.
*
* Copyright (C) 2022 Red Hat, Inc. All Rights Reserved.
* Written by David Howells (dhowells@redhat.com)
*/
#include <linux/export.h>
#include <linux/slab.h>
#include <linux/mm.h>
#include <linux/uio.h>
#include <linux/scatterlist.h>
#include <linux/netfs.h>
#include "internal.h"
/**
* netfs_extract_user_iter - Extract the pages from a user iterator into a bvec
* @orig: The original iterator
* @orig_len: The amount of iterator to copy
* @new: The iterator to be set up
* @extraction_flags: Flags to qualify the request
*
* Extract the page fragments from the given amount of the source iterator and
* build up a second iterator that refers to all of those bits. This allows
* the original iterator to disposed of.
*
* @extraction_flags can have ITER_ALLOW_P2PDMA set to request peer-to-peer DMA be
* allowed on the pages extracted.
*
* On success, the number of elements in the bvec is returned, the original
* iterator will have been advanced by the amount extracted.
*
* The iov_iter_extract_mode() function should be used to query how cleanup
* should be performed.
*/
ssize_t netfs_extract_user_iter(struct iov_iter *orig, size_t orig_len,
struct iov_iter *new,
iov_iter_extraction_t extraction_flags)
{
struct bio_vec *bv = NULL;
struct page **pages;
unsigned int cur_npages;
unsigned int max_pages;
unsigned int npages = 0;
unsigned int i;
ssize_t ret;
size_t count = orig_len, offset, len;
size_t bv_size, pg_size;
if (WARN_ON_ONCE(!iter_is_ubuf(orig) && !iter_is_iovec(orig)))
return -EIO;
max_pages = iov_iter_npages(orig, INT_MAX);
bv_size = array_size(max_pages, sizeof(*bv));
bv = kvmalloc(bv_size, GFP_KERNEL);
if (!bv)
return -ENOMEM;
/* Put the page list at the end of the bvec list storage. bvec
* elements are larger than page pointers, so as long as we work
* 0->last, we should be fine.
*/
pg_size = array_size(max_pages, sizeof(*pages));
pages = (void *)bv + bv_size - pg_size;
while (count && npages < max_pages) {
ret = iov_iter_extract_pages(orig, &pages, count,
max_pages - npages, extraction_flags,
&offset);
if (ret < 0) {
pr_err("Couldn't get user pages (rc=%zd)\n", ret);
break;
}
if (ret > count) {
pr_err("get_pages rc=%zd more than %zu\n", ret, count);
break;
}
count -= ret;
ret += offset;
cur_npages = DIV_ROUND_UP(ret, PAGE_SIZE);
if (npages + cur_npages > max_pages) {
pr_err("Out of bvec array capacity (%u vs %u)\n",
npages + cur_npages, max_pages);
break;
}
for (i = 0; i < cur_npages; i++) {
len = ret > PAGE_SIZE ? PAGE_SIZE : ret;
bvec_set_page(bv + npages + i, *pages++, len - offset, offset);
ret -= len;
offset = 0;
}
npages += cur_npages;
}
iov_iter_bvec(new, orig->data_source, bv, npages, orig_len - count);
return npages;
}
EXPORT_SYMBOL_GPL(netfs_extract_user_iter);
/*
* Select the span of a bvec iterator we're going to use. Limit it by both maximum
* size and maximum number of segments. Returns the size of the span in bytes.
*/
static size_t netfs_limit_bvec(const struct iov_iter *iter, size_t start_offset,
size_t max_size, size_t max_segs)
{
const struct bio_vec *bvecs = iter->bvec;
unsigned int nbv = iter->nr_segs, ix = 0, nsegs = 0;
size_t len, span = 0, n = iter->count;
size_t skip = iter->iov_offset + start_offset;
if (WARN_ON(!iov_iter_is_bvec(iter)) ||
WARN_ON(start_offset > n) ||
n == 0)
return 0;
while (n && ix < nbv && skip) {
len = bvecs[ix].bv_len;
if (skip < len)
break;
skip -= len;
n -= len;
ix++;
}
while (n && ix < nbv) {
len = min3(n, bvecs[ix].bv_len - skip, max_size);
span += len;
nsegs++;
ix++;
if (span >= max_size || nsegs >= max_segs)
break;
skip = 0;
n -= len;
}
return min(span, max_size);
}
/*
* Select the span of an xarray iterator we're going to use. Limit it by both
* maximum size and maximum number of segments. It is assumed that segments
* can be larger than a page in size, provided they're physically contiguous.
* Returns the size of the span in bytes.
*/
static size_t netfs_limit_xarray(const struct iov_iter *iter, size_t start_offset,
size_t max_size, size_t max_segs)
{
struct folio *folio;
unsigned int nsegs = 0;
loff_t pos = iter->xarray_start + iter->iov_offset;
pgoff_t index = pos / PAGE_SIZE;
size_t span = 0, n = iter->count;
XA_STATE(xas, iter->xarray, index);
if (WARN_ON(!iov_iter_is_xarray(iter)) ||
WARN_ON(start_offset > n) ||
n == 0)
return 0;
max_size = min(max_size, n - start_offset);
rcu_read_lock();
xas_for_each(&xas, folio, ULONG_MAX) {
size_t offset, flen, len;
if (xas_retry(&xas, folio))
continue;
if (WARN_ON(xa_is_value(folio)))
break;
if (WARN_ON(folio_test_hugetlb(folio)))
break;
flen = folio_size(folio);
offset = offset_in_folio(folio, pos);
len = min(max_size, flen - offset);
span += len;
nsegs++;
if (span >= max_size || nsegs >= max_segs)
break;
}
rcu_read_unlock();
return min(span, max_size);
}
size_t netfs_limit_iter(const struct iov_iter *iter, size_t start_offset,
size_t max_size, size_t max_segs)
{
if (iov_iter_is_bvec(iter))
return netfs_limit_bvec(iter, start_offset, max_size, max_segs);
if (iov_iter_is_xarray(iter))
return netfs_limit_xarray(iter, start_offset, max_size, max_segs);
BUG();
}
EXPORT_SYMBOL(netfs_limit_iter);
|
