Total coverage: 305097 (14%)of 2257666 

























































































































































































































   23 








   22 
   22 






   26 





























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
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
/*
 * linux/fs/nls/nls_iso8859-6.c
 *
 * Charset iso8859-6 translation tables.
 * Generated automatically from the Unicode and charset
 * tables from the Unicode Organization (www.unicode.org).
 * The Unicode to charset table has only exact mappings.
 */

#include <linux/module.h>
#include <linux/kernel.h>
#include <linux/string.h>
#include <linux/nls.h>
#include <linux/errno.h>

static const wchar_t charset2uni[256] = {
        /* 0x00*/
        0x0000, 0x0001, 0x0002, 0x0003,
        0x0004, 0x0005, 0x0006, 0x0007,
        0x0008, 0x0009, 0x000a, 0x000b,
        0x000c, 0x000d, 0x000e, 0x000f,
        /* 0x10*/
        0x0010, 0x0011, 0x0012, 0x0013,
        0x0014, 0x0015, 0x0016, 0x0017,
        0x0018, 0x0019, 0x001a, 0x001b,
        0x001c, 0x001d, 0x001e, 0x001f,
        /* 0x20*/
        0x0020, 0x0021, 0x0022, 0x0023,
        0x0024, 0x0025, 0x0026, 0x0027,
        0x0028, 0x0029, 0x002a, 0x002b,
        0x002c, 0x002d, 0x002e, 0x002f,
        /* 0x30*/
        0x0660, 0x0661, 0x0662, 0x0663,
        0x0664, 0x0665, 0x0666, 0x0667,
        0x0668, 0x0669, 0x003a, 0x003b,
        0x003c, 0x003d, 0x003e, 0x003f,
        /* 0x40*/
        0x0040, 0x0041, 0x0042, 0x0043,
        0x0044, 0x0045, 0x0046, 0x0047,
        0x0048, 0x0049, 0x004a, 0x004b,
        0x004c, 0x004d, 0x004e, 0x004f,
        /* 0x50*/
        0x0050, 0x0051, 0x0052, 0x0053,
        0x0054, 0x0055, 0x0056, 0x0057,
        0x0058, 0x0059, 0x005a, 0x005b,
        0x005c, 0x005d, 0x005e, 0x005f,
        /* 0x60*/
        0x0060, 0x0061, 0x0062, 0x0063,
        0x0064, 0x0065, 0x0066, 0x0067,
        0x0068, 0x0069, 0x006a, 0x006b,
        0x006c, 0x006d, 0x006e, 0x006f,
        /* 0x70*/
        0x0070, 0x0071, 0x0072, 0x0073,
        0x0074, 0x0075, 0x0076, 0x0077,
        0x0078, 0x0079, 0x007a, 0x007b,
        0x007c, 0x007d, 0x007e, 0x007f,
        /* 0x80*/
        0x0080, 0x0081, 0x0082, 0x0083,
        0x0084, 0x0085, 0x0086, 0x0087,
        0x0088, 0x0089, 0x008a, 0x008b,
        0x008c, 0x008d, 0x008e, 0x008f,
        /* 0x90*/
        0x0090, 0x0091, 0x0092, 0x0093,
        0x0094, 0x0095, 0x0096, 0x0097,
        0x0098, 0x0099, 0x009a, 0x009b,
        0x009c, 0x009d, 0x009e, 0x009f,
        /* 0xa0*/
        0x00a0, 0x0000, 0x0000, 0x0000,
        0x00a4, 0x0000, 0x0000, 0x0000,
        0x0000, 0x0000, 0x0000, 0x0000,
        0x060c, 0x00ad, 0x0000, 0x0000,
        /* 0xb0*/
        0x0000, 0x0000, 0x0000, 0x0000,
        0x0000, 0x0000, 0x0000, 0x0000,
        0x0000, 0x0000, 0x0000, 0x061b,
        0x0000, 0x0000, 0x0000, 0x061f,
        /* 0xc0*/
        0x0000, 0x0621, 0x0622, 0x0623,
        0x0624, 0x0625, 0x0626, 0x0627,
        0x0628, 0x0629, 0x062a, 0x062b,
        0x062c, 0x062d, 0x062e, 0x062f,
        /* 0xd0*/
        0x0630, 0x0631, 0x0632, 0x0633,
        0x0634, 0x0635, 0x0636, 0x0637,
        0x0638, 0x0639, 0x063a, 0x0000,
        0x0000, 0x0000, 0x0000, 0x0000,
        /* 0xe0*/
        0x0640, 0x0641, 0x0642, 0x0643,
        0x0644, 0x0645, 0x0646, 0x0647,
        0x0648, 0x0649, 0x064a, 0x064b,
        0x064c, 0x064d, 0x064e, 0x064f,
        /* 0xf0*/
        0x0650, 0x0651, 0x0652, 0x0000,
        0x0000, 0x0000, 0x0000, 0x0000,
        0x0000, 0x0000, 0x0000, 0x0000,
        0x0000, 0x0000, 0x0000, 0x0000,
};

static const unsigned char page00[256] = {
        0x00, 0x01, 0x02, 0x03, 0x04, 0x05, 0x06, 0x07, /* 0x00-0x07 */
        0x08, 0x09, 0x0a, 0x0b, 0x0c, 0x0d, 0x0e, 0x0f, /* 0x08-0x0f */
        0x10, 0x11, 0x12, 0x13, 0x14, 0x15, 0x16, 0x17, /* 0x10-0x17 */
        0x18, 0x19, 0x1a, 0x1b, 0x1c, 0x1d, 0x1e, 0x1f, /* 0x18-0x1f */
        0x20, 0x21, 0x22, 0x23, 0x24, 0x25, 0x26, 0x27, /* 0x20-0x27 */
        0x28, 0x29, 0x2a, 0x2b, 0x2c, 0x2d, 0x2e, 0x2f, /* 0x28-0x2f */
        0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x30-0x37 */
        0x00, 0x00, 0x3a, 0x3b, 0x3c, 0x3d, 0x3e, 0x3f, /* 0x38-0x3f */
        0x40, 0x41, 0x42, 0x43, 0x44, 0x45, 0x46, 0x47, /* 0x40-0x47 */
        0x48, 0x49, 0x4a, 0x4b, 0x4c, 0x4d, 0x4e, 0x4f, /* 0x48-0x4f */
        0x50, 0x51, 0x52, 0x53, 0x54, 0x55, 0x56, 0x57, /* 0x50-0x57 */
        0x58, 0x59, 0x5a, 0x5b, 0x5c, 0x5d, 0x5e, 0x5f, /* 0x58-0x5f */
        0x60, 0x61, 0x62, 0x63, 0x64, 0x65, 0x66, 0x67, /* 0x60-0x67 */
        0x68, 0x69, 0x6a, 0x6b, 0x6c, 0x6d, 0x6e, 0x6f, /* 0x68-0x6f */
        0x70, 0x71, 0x72, 0x73, 0x74, 0x75, 0x76, 0x77, /* 0x70-0x77 */
        0x78, 0x79, 0x7a, 0x7b, 0x7c, 0x7d, 0x7e, 0x7f, /* 0x78-0x7f */

        0x80, 0x81, 0x82, 0x83, 0x84, 0x85, 0x86, 0x87, /* 0x80-0x87 */
        0x88, 0x89, 0x8a, 0x8b, 0x8c, 0x8d, 0x8e, 0x8f, /* 0x88-0x8f */
        0x90, 0x91, 0x92, 0x93, 0x94, 0x95, 0x96, 0x97, /* 0x90-0x97 */
        0x98, 0x99, 0x9a, 0x9b, 0x9c, 0x9d, 0x9e, 0x9f, /* 0x98-0x9f */
        0xa0, 0x00, 0x00, 0x00, 0xa4, 0x00, 0x00, 0x00, /* 0xa0-0xa7 */
        0x00, 0x00, 0x00, 0x00, 0x00, 0xad, 0x00, 0x00, /* 0xa8-0xaf */
};

static const unsigned char page06[256] = {
        0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x00-0x07 */
        0x00, 0x00, 0x00, 0x00, 0xac, 0x00, 0x00, 0x00, /* 0x08-0x0f */
        0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x10-0x17 */
        0x00, 0x00, 0x00, 0xbb, 0x00, 0x00, 0x00, 0xbf, /* 0x18-0x1f */
        0x00, 0xc1, 0xc2, 0xc3, 0xc4, 0xc5, 0xc6, 0xc7, /* 0x20-0x27 */
        0xc8, 0xc9, 0xca, 0xcb, 0xcc, 0xcd, 0xce, 0xcf, /* 0x28-0x2f */
        0xd0, 0xd1, 0xd2, 0xd3, 0xd4, 0xd5, 0xd6, 0xd7, /* 0x30-0x37 */
        0xd8, 0xd9, 0xda, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x38-0x3f */
        0xe0, 0xe1, 0xe2, 0xe3, 0xe4, 0xe5, 0xe6, 0xe7, /* 0x40-0x47 */
        0xe8, 0xe9, 0xea, 0xeb, 0xec, 0xed, 0xee, 0xef, /* 0x48-0x4f */
        0xf0, 0xf1, 0xf2, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x50-0x57 */
        0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x58-0x5f */
        0x30, 0x31, 0x32, 0x33, 0x34, 0x35, 0x36, 0x37, /* 0x60-0x67 */
        0x38, 0x39, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x68-0x6f */
};

static const unsigned char *const page_uni2charset[256] = {
        page00, NULL,   NULL,   NULL,   NULL,   NULL,   page06, NULL,   
};

static const unsigned char charset2lower[256] = {
        0x00, 0x01, 0x02, 0x03, 0x04, 0x05, 0x06, 0x07, /* 0x00-0x07 */
        0x08, 0x09, 0x0a, 0x0b, 0x0c, 0x0d, 0x0e, 0x0f, /* 0x08-0x0f */
        0x10, 0x11, 0x12, 0x13, 0x14, 0x15, 0x16, 0x17, /* 0x10-0x17 */
        0x18, 0x19, 0x1a, 0x1b, 0x1c, 0x1d, 0x1e, 0x1f, /* 0x18-0x1f */
        0x20, 0x21, 0x22, 0x23, 0x24, 0x25, 0x26, 0x27, /* 0x20-0x27 */
        0x28, 0x29, 0x2a, 0x2b, 0x2c, 0x2d, 0x2e, 0x2f, /* 0x28-0x2f */
        0x30, 0x31, 0x32, 0x33, 0x34, 0x35, 0x36, 0x37, /* 0x30-0x37 */
        0x38, 0x39, 0x3a, 0x3b, 0x3c, 0x3d, 0x3e, 0x3f, /* 0x38-0x3f */
        0x40, 0x61, 0x62, 0x63, 0x64, 0x65, 0x66, 0x67, /* 0x40-0x47 */
        0x68, 0x69, 0x6a, 0x6b, 0x6c, 0x6d, 0x6e, 0x6f, /* 0x48-0x4f */
        0x70, 0x71, 0x72, 0x73, 0x74, 0x75, 0x76, 0x77, /* 0x50-0x57 */
        0x78, 0x79, 0x7a, 0x5b, 0x5c, 0x5d, 0x5e, 0x5f, /* 0x58-0x5f */
        0x60, 0x61, 0x62, 0x63, 0x64, 0x65, 0x66, 0x67, /* 0x60-0x67 */
        0x68, 0x69, 0x6a, 0x6b, 0x6c, 0x6d, 0x6e, 0x6f, /* 0x68-0x6f */
        0x70, 0x71, 0x72, 0x73, 0x74, 0x75, 0x76, 0x77, /* 0x70-0x77 */
        0x78, 0x79, 0x7a, 0x7b, 0x7c, 0x7d, 0x7e, 0x7f, /* 0x78-0x7f */

        0x80, 0x81, 0x82, 0x83, 0x84, 0x85, 0x86, 0x87, /* 0x80-0x87 */
        0x88, 0x89, 0x8a, 0x8b, 0x8c, 0x8d, 0x8e, 0x8f, /* 0x88-0x8f */
        0x90, 0x91, 0x92, 0x93, 0x94, 0x95, 0x96, 0x97, /* 0x90-0x97 */
        0x98, 0x99, 0x9a, 0x9b, 0x9c, 0x9d, 0x9e, 0x9f, /* 0x98-0x9f */
        0xa0, 0x00, 0x00, 0x00, 0xa4, 0x00, 0x00, 0x00, /* 0xa0-0xa7 */
        0x00, 0x00, 0x00, 0x00, 0xac, 0xad, 0x00, 0x00, /* 0xa8-0xaf */
        0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xb0-0xb7 */
        0x00, 0x00, 0x00, 0xbb, 0x00, 0x00, 0x00, 0xbf, /* 0xb8-0xbf */
        0x00, 0xc1, 0xc2, 0xc3, 0xc4, 0xc5, 0xc6, 0xc7, /* 0xc0-0xc7 */
        0xc8, 0xc9, 0xca, 0xcb, 0xcc, 0xcd, 0xce, 0xcf, /* 0xc8-0xcf */
        0xd0, 0xd1, 0xd2, 0xd3, 0xd4, 0xd5, 0xd6, 0xd7, /* 0xd0-0xd7 */
        0xd8, 0xd9, 0xda, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xd8-0xdf */
        0xe0, 0xe1, 0xe2, 0xe3, 0xe4, 0xe5, 0xe6, 0xe7, /* 0xe0-0xe7 */
        0xe8, 0xe9, 0xea, 0xeb, 0xec, 0xed, 0xee, 0xef, /* 0xe8-0xef */
        0xf0, 0xf1, 0xf2, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xf0-0xf7 */
        0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xf8-0xff */
};

static const unsigned char charset2upper[256] = {
        0x00, 0x01, 0x02, 0x03, 0x04, 0x05, 0x06, 0x07, /* 0x00-0x07 */
        0x08, 0x09, 0x0a, 0x0b, 0x0c, 0x0d, 0x0e, 0x0f, /* 0x08-0x0f */
        0x10, 0x11, 0x12, 0x13, 0x14, 0x15, 0x16, 0x17, /* 0x10-0x17 */
        0x18, 0x19, 0x1a, 0x1b, 0x1c, 0x1d, 0x1e, 0x1f, /* 0x18-0x1f */
        0x20, 0x21, 0x22, 0x23, 0x24, 0x25, 0x26, 0x27, /* 0x20-0x27 */
        0x28, 0x29, 0x2a, 0x2b, 0x2c, 0x2d, 0x2e, 0x2f, /* 0x28-0x2f */
        0x30, 0x31, 0x32, 0x33, 0x34, 0x35, 0x36, 0x37, /* 0x30-0x37 */
        0x38, 0x39, 0x3a, 0x3b, 0x3c, 0x3d, 0x3e, 0x3f, /* 0x38-0x3f */
        0x40, 0x41, 0x42, 0x43, 0x44, 0x45, 0x46, 0x47, /* 0x40-0x47 */
        0x48, 0x49, 0x4a, 0x4b, 0x4c, 0x4d, 0x4e, 0x4f, /* 0x48-0x4f */
        0x50, 0x51, 0x52, 0x53, 0x54, 0x55, 0x56, 0x57, /* 0x50-0x57 */
        0x58, 0x59, 0x5a, 0x5b, 0x5c, 0x5d, 0x5e, 0x5f, /* 0x58-0x5f */
        0x60, 0x41, 0x42, 0x43, 0x44, 0x45, 0x46, 0x47, /* 0x60-0x67 */
        0x48, 0x49, 0x4a, 0x4b, 0x4c, 0x4d, 0x4e, 0x4f, /* 0x68-0x6f */
        0x50, 0x51, 0x52, 0x53, 0x54, 0x55, 0x56, 0x57, /* 0x70-0x77 */
        0x58, 0x59, 0x5a, 0x7b, 0x7c, 0x7d, 0x7e, 0x7f, /* 0x78-0x7f */

        0x80, 0x81, 0x82, 0x83, 0x84, 0x85, 0x86, 0x87, /* 0x80-0x87 */
        0x88, 0x89, 0x8a, 0x8b, 0x8c, 0x8d, 0x8e, 0x8f, /* 0x88-0x8f */
        0x90, 0x91, 0x92, 0x93, 0x94, 0x95, 0x96, 0x97, /* 0x90-0x97 */
        0x98, 0x99, 0x9a, 0x9b, 0x9c, 0x9d, 0x9e, 0x9f, /* 0x98-0x9f */
        0xa0, 0x00, 0x00, 0x00, 0xa4, 0x00, 0x00, 0x00, /* 0xa0-0xa7 */
        0x00, 0x00, 0x00, 0x00, 0xac, 0xad, 0x00, 0x00, /* 0xa8-0xaf */
        0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xb0-0xb7 */
        0x00, 0x00, 0x00, 0xbb, 0x00, 0x00, 0x00, 0xbf, /* 0xb8-0xbf */
        0x00, 0xc1, 0xc2, 0xc3, 0xc4, 0xc5, 0xc6, 0xc7, /* 0xc0-0xc7 */
        0xc8, 0xc9, 0xca, 0xcb, 0xcc, 0xcd, 0xce, 0xcf, /* 0xc8-0xcf */
        0xd0, 0xd1, 0xd2, 0xd3, 0xd4, 0xd5, 0xd6, 0xd7, /* 0xd0-0xd7 */
        0xd8, 0xd9, 0xda, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xd8-0xdf */
        0xe0, 0xe1, 0xe2, 0xe3, 0xe4, 0xe5, 0xe6, 0xe7, /* 0xe0-0xe7 */
        0xe8, 0xe9, 0xea, 0xeb, 0xec, 0xed, 0xee, 0xef, /* 0xe8-0xef */
        0xf0, 0xf1, 0xf2, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xf0-0xf7 */
};

static int uni2char(wchar_t uni, unsigned char *out, int boundlen)
{
        const unsigned char *uni2charset;
        unsigned char cl = uni & 0x00ff;
        unsigned char ch = (uni & 0xff00) >> 8;

        if (boundlen <= 0)
                return -ENAMETOOLONG;

        uni2charset = page_uni2charset[ch];
        if (uni2charset && uni2charset[cl])
                out[0] = uni2charset[cl];
        else
                return -EINVAL;
        return 1;
}

static int char2uni(const unsigned char *rawstring, int boundlen, wchar_t *uni)
{
        *uni = charset2uni[*rawstring];
        if (*uni == 0x0000)
                return -EINVAL;
        return 1;
}

static struct nls_table table = {
        .charset        = "iso8859-6",
        .uni2char        = uni2char,
        .char2uni        = char2uni,
        .charset2lower        = charset2lower,
        .charset2upper        = charset2upper,
};

static int __init init_nls_iso8859_6(void)
{
        return register_nls(&table);
}

static void __exit exit_nls_iso8859_6(void)
{
        unregister_nls(&table);
}

module_init(init_nls_iso8859_6)
module_exit(exit_nls_iso8859_6)

MODULE_DESCRIPTION("NLS ISO 8859-6 (Arabic)");
MODULE_LICENSE("Dual BSD/GPL");





















   23 














   11 
   23 
   23 











   11 




    9 



   23 





   10 



    5 

    5 


    8 

    5 









   14 







   14 
   14 
   14 


    5 











    3 







   11 
   11 
   11 
   11 

    2 







    1 








    5 

    8 

    7 







    7 









    3 









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
// SPDX-License-Identifier: GPL-2.0-only
/*
 * dma-fence-util: misc functions for dma_fence objects
 *
 * Copyright (C) 2022 Advanced Micro Devices, Inc.
 * Authors:
 *        Christian König <christian.koenig@amd.com>
 */

#include <linux/dma-fence.h>
#include <linux/dma-fence-array.h>
#include <linux/dma-fence-chain.h>
#include <linux/dma-fence-unwrap.h>
#include <linux/slab.h>
#include <linux/sort.h>

/* Internal helper to start new array iteration, don't use directly */
static struct dma_fence *
__dma_fence_unwrap_array(struct dma_fence_unwrap *cursor)
{
        cursor->array = dma_fence_chain_contained(cursor->chain);
        cursor->index = 0;
        return dma_fence_array_first(cursor->array);
}

/**
 * dma_fence_unwrap_first - return the first fence from fence containers
 * @head: the entrypoint into the containers
 * @cursor: current position inside the containers
 *
 * Unwraps potential dma_fence_chain/dma_fence_array containers and return the
 * first fence.
 */
struct dma_fence *dma_fence_unwrap_first(struct dma_fence *head,
                                         struct dma_fence_unwrap *cursor)
{
        cursor->chain = dma_fence_get(head);
        return __dma_fence_unwrap_array(cursor);
}
EXPORT_SYMBOL_GPL(dma_fence_unwrap_first);

/**
 * dma_fence_unwrap_next - return the next fence from a fence containers
 * @cursor: current position inside the containers
 *
 * Continue unwrapping the dma_fence_chain/dma_fence_array containers and return
 * the next fence from them.
 */
struct dma_fence *dma_fence_unwrap_next(struct dma_fence_unwrap *cursor)
{
        struct dma_fence *tmp;

        ++cursor->index;
        tmp = dma_fence_array_next(cursor->array, cursor->index);
        if (tmp)
                return tmp;

        cursor->chain = dma_fence_chain_walk(cursor->chain);
        return __dma_fence_unwrap_array(cursor);
}
EXPORT_SYMBOL_GPL(dma_fence_unwrap_next);


static int fence_cmp(const void *_a, const void *_b)
{
        struct dma_fence *a = *(struct dma_fence **)_a;
        struct dma_fence *b = *(struct dma_fence **)_b;

        if (a->context < b->context)
                return -1;
        else if (a->context > b->context)
                return 1;

        if (dma_fence_is_later(b, a))
                return 1;
        else if (dma_fence_is_later(a, b))
                return -1;

        return 0;
}

/* Implementation for the dma_fence_merge() marco, don't use directly */
struct dma_fence *__dma_fence_unwrap_merge(unsigned int num_fences,
                                           struct dma_fence **fences,
                                           struct dma_fence_unwrap *iter)
{
        struct dma_fence_array *result;
        struct dma_fence *tmp, **array;
        ktime_t timestamp;
        int i, j, count;

        count = 0;
        timestamp = ns_to_ktime(0);
        for (i = 0; i < num_fences; ++i) {
                dma_fence_unwrap_for_each(tmp, &iter[i], fences[i]) {
                        if (!dma_fence_is_signaled(tmp)) {
                                ++count;
                        } else {
                                ktime_t t = dma_fence_timestamp(tmp);

                                if (ktime_after(t, timestamp))
                                        timestamp = t;
                        }
                }
        }

        /*
         * If we couldn't find a pending fence just return a private signaled
         * fence with the timestamp of the last signaled one.
         */
        if (count == 0)
                return dma_fence_allocate_private_stub(timestamp);

        array = kmalloc_array(count, sizeof(*array), GFP_KERNEL);
        if (!array)
                return NULL;

        count = 0;
        for (i = 0; i < num_fences; ++i) {
                dma_fence_unwrap_for_each(tmp, &iter[i], fences[i]) {
                        if (!dma_fence_is_signaled(tmp)) {
                                array[count++] = dma_fence_get(tmp);
                        } else {
                                ktime_t t = dma_fence_timestamp(tmp);

                                if (ktime_after(t, timestamp))
                                        timestamp = t;
                        }
                }
        }

        if (count == 0 || count == 1)
                goto return_fastpath;

        sort(array, count, sizeof(*array), fence_cmp, NULL);

        /*
         * Only keep the most recent fence for each context.
         */
        j = 0;
        for (i = 1; i < count; i++) {
                if (array[i]->context == array[j]->context)
                        dma_fence_put(array[i]);
                else
                        array[++j] = array[i];
        }
        count = ++j;

        if (count > 1) {
                result = dma_fence_array_create(count, array,
                                                dma_fence_context_alloc(1),
                                                1, false);
                if (!result) {
                        for (i = 0; i < count; i++)
                                dma_fence_put(array[i]);
                        tmp = NULL;
                        goto return_tmp;
                }
                return &result->base;
        }

return_fastpath:
        if (count == 0)
                tmp = dma_fence_allocate_private_stub(timestamp);
        else
                tmp = array[0];

return_tmp:
        kfree(array);
        return tmp;
}
EXPORT_SYMBOL_GPL(__dma_fence_unwrap_merge);





































































































































































































































































































  155 
  155 


























































































































    2 































































































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
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
/* SPDX-License-Identifier: GPL-2.0-only */
/*
 * Copyright (C) 2017-2018 HUAWEI, Inc.
 *             https://www.huawei.com/
 * Copyright (C) 2021, Alibaba Cloud
 */
#ifndef __EROFS_INTERNAL_H
#define __EROFS_INTERNAL_H

#include <linux/fs.h>
#include <linux/dax.h>
#include <linux/dcache.h>
#include <linux/mm.h>
#include <linux/module.h>
#include <linux/pagemap.h>
#include <linux/bio.h>
#include <linux/magic.h>
#include <linux/slab.h>
#include <linux/vmalloc.h>
#include <linux/iomap.h>
#include "erofs_fs.h"

__printf(2, 3) void _erofs_printk(struct super_block *sb, const char *fmt, ...);
#define erofs_err(sb, fmt, ...)        \
        _erofs_printk(sb, KERN_ERR fmt "\n", ##__VA_ARGS__)
#define erofs_info(sb, fmt, ...) \
        _erofs_printk(sb, KERN_INFO fmt "\n", ##__VA_ARGS__)

#ifdef CONFIG_EROFS_FS_DEBUG
#define DBG_BUGON               BUG_ON
#else
#define DBG_BUGON(x)            ((void)(x))
#endif        /* !CONFIG_EROFS_FS_DEBUG */

/* EROFS_SUPER_MAGIC_V1 to represent the whole file system */
#define EROFS_SUPER_MAGIC   EROFS_SUPER_MAGIC_V1

typedef u64 erofs_nid_t;
typedef u64 erofs_off_t;
/* data type for filesystem-wide blocks number */
typedef u32 erofs_blk_t;

struct erofs_device_info {
        char *path;
        struct erofs_fscache *fscache;
        struct file *file;
        struct dax_device *dax_dev;
        u64 dax_part_off;

        u32 blocks;
        u32 mapped_blkaddr;
};

enum {
        EROFS_SYNC_DECOMPRESS_AUTO,
        EROFS_SYNC_DECOMPRESS_FORCE_ON,
        EROFS_SYNC_DECOMPRESS_FORCE_OFF
};

struct erofs_mount_opts {
        /* current strategy of how to use managed cache */
        unsigned char cache_strategy;
        /* strategy of sync decompression (0 - auto, 1 - force on, 2 - force off) */
        unsigned int sync_decompress;
        /* threshold for decompression synchronously */
        unsigned int max_sync_decompress_pages;
        unsigned int mount_opt;
};

struct erofs_dev_context {
        struct idr tree;
        struct rw_semaphore rwsem;

        unsigned int extra_devices;
        bool flatdev;
};

/* all filesystem-wide lz4 configurations */
struct erofs_sb_lz4_info {
        /* # of pages needed for EROFS lz4 rolling decompression */
        u16 max_distance_pages;
        /* maximum possible blocks for pclusters in the filesystem */
        u16 max_pclusterblks;
};

struct erofs_domain {
        refcount_t ref;
        struct list_head list;
        struct fscache_volume *volume;
        char *domain_id;
};

struct erofs_fscache {
        struct fscache_cookie *cookie;
        struct inode *inode;        /* anonymous inode for the blob */

        /* used for share domain mode */
        struct erofs_domain *domain;
        struct list_head node;
        refcount_t ref;
        char *name;
};

struct erofs_xattr_prefix_item {
        struct erofs_xattr_long_prefix *prefix;
        u8 infix_len;
};

struct erofs_sb_info {
        struct erofs_device_info dif0;
        struct erofs_mount_opts opt;        /* options */
#ifdef CONFIG_EROFS_FS_ZIP
        /* list for all registered superblocks, mainly for shrinker */
        struct list_head list;
        struct mutex umount_mutex;

        /* managed XArray arranged in physical block number */
        struct xarray managed_pslots;

        unsigned int shrinker_run_no;
        u16 available_compr_algs;

        /* pseudo inode to manage cached pages */
        struct inode *managed_cache;

        struct erofs_sb_lz4_info lz4;
#endif        /* CONFIG_EROFS_FS_ZIP */
        struct inode *packed_inode;
        struct erofs_dev_context *devs;
        u64 total_blocks;

        u32 meta_blkaddr;
#ifdef CONFIG_EROFS_FS_XATTR
        u32 xattr_blkaddr;
        u32 xattr_prefix_start;
        u8 xattr_prefix_count;
        struct erofs_xattr_prefix_item *xattr_prefixes;
        unsigned int xattr_filter_reserved;
#endif
        u16 device_id_mask;        /* valid bits of device id to be used */

        unsigned char islotbits;        /* inode slot unit size in bit shift */
        unsigned char blkszbits;        /* filesystem block size in bit shift */

        u32 sb_size;                        /* total superblock size */
        u32 build_time_nsec;
        u64 build_time;

        /* what we really care is nid, rather than ino.. */
        erofs_nid_t root_nid;
        erofs_nid_t packed_nid;
        /* used for statfs, f_files - f_favail */
        u64 inos;

        u8 uuid[16];                    /* 128-bit uuid for volume */
        u8 volume_name[16];             /* volume name */
        u32 feature_compat;
        u32 feature_incompat;

        /* sysfs support */
        struct kobject s_kobj;                /* /sys/fs/erofs/<devname> */
        struct completion s_kobj_unregister;

        /* fscache support */
        struct fscache_volume *volume;
        struct erofs_domain *domain;
        char *fsid;
        char *domain_id;
};

#define EROFS_SB(sb) ((struct erofs_sb_info *)(sb)->s_fs_info)
#define EROFS_I_SB(inode) ((struct erofs_sb_info *)(inode)->i_sb->s_fs_info)

/* Mount flags set via mount options or defaults */
#define EROFS_MOUNT_XATTR_USER                0x00000010
#define EROFS_MOUNT_POSIX_ACL                0x00000020
#define EROFS_MOUNT_DAX_ALWAYS                0x00000040
#define EROFS_MOUNT_DAX_NEVER                0x00000080
#define EROFS_MOUNT_DIRECT_IO                0x00000100

#define clear_opt(opt, option)        ((opt)->mount_opt &= ~EROFS_MOUNT_##option)
#define set_opt(opt, option)        ((opt)->mount_opt |= EROFS_MOUNT_##option)
#define test_opt(opt, option)        ((opt)->mount_opt & EROFS_MOUNT_##option)

static inline bool erofs_is_fileio_mode(struct erofs_sb_info *sbi)
{
        return IS_ENABLED(CONFIG_EROFS_FS_BACKED_BY_FILE) && sbi->dif0.file;
}

static inline bool erofs_is_fscache_mode(struct super_block *sb)
{
        return IS_ENABLED(CONFIG_EROFS_FS_ONDEMAND) &&
                        !erofs_is_fileio_mode(EROFS_SB(sb)) && !sb->s_bdev;
}

enum {
        EROFS_ZIP_CACHE_DISABLED,
        EROFS_ZIP_CACHE_READAHEAD,
        EROFS_ZIP_CACHE_READAROUND
};

enum erofs_kmap_type {
        EROFS_NO_KMAP,                /* don't map the buffer */
        EROFS_KMAP,                /* use kmap_local_page() to map the buffer */
};

struct erofs_buf {
        struct address_space *mapping;
        struct file *file;
        struct page *page;
        void *base;
};
#define __EROFS_BUF_INITIALIZER        ((struct erofs_buf){ .page = NULL })

#define erofs_blknr(sb, addr)        ((erofs_blk_t)((addr) >> (sb)->s_blocksize_bits))
#define erofs_blkoff(sb, addr)        ((addr) & ((sb)->s_blocksize - 1))
#define erofs_pos(sb, blk)        ((erofs_off_t)(blk) << (sb)->s_blocksize_bits)
#define erofs_iblks(i)        (round_up((i)->i_size, i_blocksize(i)) >> (i)->i_blkbits)

#define EROFS_FEATURE_FUNCS(name, compat, feature) \
static inline bool erofs_sb_has_##name(struct erofs_sb_info *sbi) \
{ \
        return sbi->feature_##compat & EROFS_FEATURE_##feature; \
}

EROFS_FEATURE_FUNCS(zero_padding, incompat, INCOMPAT_ZERO_PADDING)
EROFS_FEATURE_FUNCS(compr_cfgs, incompat, INCOMPAT_COMPR_CFGS)
EROFS_FEATURE_FUNCS(big_pcluster, incompat, INCOMPAT_BIG_PCLUSTER)
EROFS_FEATURE_FUNCS(chunked_file, incompat, INCOMPAT_CHUNKED_FILE)
EROFS_FEATURE_FUNCS(device_table, incompat, INCOMPAT_DEVICE_TABLE)
EROFS_FEATURE_FUNCS(compr_head2, incompat, INCOMPAT_COMPR_HEAD2)
EROFS_FEATURE_FUNCS(ztailpacking, incompat, INCOMPAT_ZTAILPACKING)
EROFS_FEATURE_FUNCS(fragments, incompat, INCOMPAT_FRAGMENTS)
EROFS_FEATURE_FUNCS(dedupe, incompat, INCOMPAT_DEDUPE)
EROFS_FEATURE_FUNCS(xattr_prefixes, incompat, INCOMPAT_XATTR_PREFIXES)
EROFS_FEATURE_FUNCS(sb_chksum, compat, COMPAT_SB_CHKSUM)
EROFS_FEATURE_FUNCS(xattr_filter, compat, COMPAT_XATTR_FILTER)

/* atomic flag definitions */
#define EROFS_I_EA_INITED_BIT        0
#define EROFS_I_Z_INITED_BIT        1

/* bitlock definitions (arranged in reverse order) */
#define EROFS_I_BL_XATTR_BIT        (BITS_PER_LONG - 1)
#define EROFS_I_BL_Z_BIT        (BITS_PER_LONG - 2)

struct erofs_inode {
        erofs_nid_t nid;

        /* atomic flags (including bitlocks) */
        unsigned long flags;

        unsigned char datalayout;
        unsigned char inode_isize;
        unsigned int xattr_isize;

        unsigned int xattr_name_filter;
        unsigned int xattr_shared_count;
        unsigned int *xattr_shared_xattrs;

        union {
                erofs_blk_t raw_blkaddr;
                struct {
                        unsigned short        chunkformat;
                        unsigned char        chunkbits;
                };
#ifdef CONFIG_EROFS_FS_ZIP
                struct {
                        unsigned short z_advise;
                        unsigned char  z_algorithmtype[2];
                        unsigned char  z_logical_clusterbits;
                        unsigned long  z_tailextent_headlcn;
                        union {
                                struct {
                                        erofs_off_t    z_idataoff;
                                        unsigned short z_idata_size;
                                };
                                erofs_off_t z_fragmentoff;
                        };
                };
#endif        /* CONFIG_EROFS_FS_ZIP */
        };
        /* the corresponding vfs inode */
        struct inode vfs_inode;
};

#define EROFS_I(ptr)        container_of(ptr, struct erofs_inode, vfs_inode)

static inline erofs_off_t erofs_iloc(struct inode *inode)
{
        struct erofs_sb_info *sbi = EROFS_I_SB(inode);

        return erofs_pos(inode->i_sb, sbi->meta_blkaddr) +
                (EROFS_I(inode)->nid << sbi->islotbits);
}

static inline unsigned int erofs_inode_version(unsigned int ifmt)
{
        return (ifmt >> EROFS_I_VERSION_BIT) & EROFS_I_VERSION_MASK;
}

static inline unsigned int erofs_inode_datalayout(unsigned int ifmt)
{
        return (ifmt >> EROFS_I_DATALAYOUT_BIT) & EROFS_I_DATALAYOUT_MASK;
}

/* reclaiming is never triggered when allocating new folios. */
static inline struct folio *erofs_grab_folio_nowait(struct address_space *as,
                                                    pgoff_t index)
{
        return __filemap_get_folio(as, index,
                        FGP_LOCK|FGP_CREAT|FGP_NOFS|FGP_NOWAIT,
                        readahead_gfp_mask(as) & ~__GFP_RECLAIM);
}

/* Has a disk mapping */
#define EROFS_MAP_MAPPED        0x0001
/* Located in metadata (could be copied from bd_inode) */
#define EROFS_MAP_META                0x0002
/* The extent is encoded */
#define EROFS_MAP_ENCODED        0x0004
/* The length of extent is full */
#define EROFS_MAP_FULL_MAPPED        0x0008
/* Located in the special packed inode */
#define EROFS_MAP_FRAGMENT        0x0010
/* The extent refers to partial decompressed data */
#define EROFS_MAP_PARTIAL_REF        0x0020

struct erofs_map_blocks {
        struct erofs_buf buf;

        erofs_off_t m_pa, m_la;
        u64 m_plen, m_llen;

        unsigned short m_deviceid;
        char m_algorithmformat;
        unsigned int m_flags;
};

/*
 * Used to get the exact decompressed length, e.g. fiemap (consider lookback
 * approach instead if possible since it's more metadata lightweight.)
 */
#define EROFS_GET_BLOCKS_FIEMAP                0x0001
/* Used to map the whole extent if non-negligible data is requested for LZMA */
#define EROFS_GET_BLOCKS_READMORE        0x0002
/* Used to map tail extent for tailpacking inline or fragment pcluster */
#define EROFS_GET_BLOCKS_FINDTAIL        0x0004

enum {
        Z_EROFS_COMPRESSION_SHIFTED = Z_EROFS_COMPRESSION_MAX,
        Z_EROFS_COMPRESSION_INTERLACED,
        Z_EROFS_COMPRESSION_RUNTIME_MAX
};

struct erofs_map_dev {
        struct super_block *m_sb;
        struct erofs_device_info *m_dif;
        struct block_device *m_bdev;

        erofs_off_t m_pa;
        unsigned int m_deviceid;
};

extern const struct super_operations erofs_sops;

extern const struct address_space_operations erofs_aops;
extern const struct address_space_operations erofs_fileio_aops;
extern const struct address_space_operations z_erofs_aops;
extern const struct address_space_operations erofs_fscache_access_aops;

extern const struct inode_operations erofs_generic_iops;
extern const struct inode_operations erofs_symlink_iops;
extern const struct inode_operations erofs_fast_symlink_iops;
extern const struct inode_operations erofs_dir_iops;

extern const struct file_operations erofs_file_fops;
extern const struct file_operations erofs_dir_fops;

extern const struct iomap_ops z_erofs_iomap_report_ops;

/* flags for erofs_fscache_register_cookie() */
#define EROFS_REG_COOKIE_SHARE                0x0001
#define EROFS_REG_COOKIE_NEED_NOEXIST        0x0002

void *erofs_read_metadata(struct super_block *sb, struct erofs_buf *buf,
                          erofs_off_t *offset, int *lengthp);
void erofs_unmap_metabuf(struct erofs_buf *buf);
void erofs_put_metabuf(struct erofs_buf *buf);
void *erofs_bread(struct erofs_buf *buf, erofs_off_t offset,
                  enum erofs_kmap_type type);
void erofs_init_metabuf(struct erofs_buf *buf, struct super_block *sb);
void *erofs_read_metabuf(struct erofs_buf *buf, struct super_block *sb,
                         erofs_off_t offset, enum erofs_kmap_type type);
int erofs_map_dev(struct super_block *sb, struct erofs_map_dev *dev);
int erofs_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
                 u64 start, u64 len);
int erofs_map_blocks(struct inode *inode, struct erofs_map_blocks *map);
void erofs_onlinefolio_init(struct folio *folio);
void erofs_onlinefolio_split(struct folio *folio);
void erofs_onlinefolio_end(struct folio *folio, int err);
struct inode *erofs_iget(struct super_block *sb, erofs_nid_t nid);
int erofs_getattr(struct mnt_idmap *idmap, const struct path *path,
                  struct kstat *stat, u32 request_mask,
                  unsigned int query_flags);
int erofs_namei(struct inode *dir, const struct qstr *name,
                erofs_nid_t *nid, unsigned int *d_type);

static inline void *erofs_vm_map_ram(struct page **pages, unsigned int count)
{
        int retried = 0;

        while (1) {
                void *p = vm_map_ram(pages, count, -1);

                /* retry two more times (totally 3 times) */
                if (p || ++retried >= 3)
                        return p;
                vm_unmap_aliases();
        }
        return NULL;
}

int erofs_register_sysfs(struct super_block *sb);
void erofs_unregister_sysfs(struct super_block *sb);
int __init erofs_init_sysfs(void);
void erofs_exit_sysfs(void);

struct page *__erofs_allocpage(struct page **pagepool, gfp_t gfp, bool tryrsv);
static inline struct page *erofs_allocpage(struct page **pagepool, gfp_t gfp)
{
        return __erofs_allocpage(pagepool, gfp, false);
}
static inline void erofs_pagepool_add(struct page **pagepool, struct page *page)
{
        set_page_private(page, (unsigned long)*pagepool);
        *pagepool = page;
}
void erofs_release_pages(struct page **pagepool);

#ifdef CONFIG_EROFS_FS_ZIP
#define MNGD_MAPPING(sbi)        ((sbi)->managed_cache->i_mapping)

extern atomic_long_t erofs_global_shrink_cnt;
void erofs_shrinker_register(struct super_block *sb);
void erofs_shrinker_unregister(struct super_block *sb);
int __init erofs_init_shrinker(void);
void erofs_exit_shrinker(void);
int __init z_erofs_init_subsystem(void);
void z_erofs_exit_subsystem(void);
unsigned long z_erofs_shrink_scan(struct erofs_sb_info *sbi,
                                  unsigned long nr_shrink);
int z_erofs_map_blocks_iter(struct inode *inode, struct erofs_map_blocks *map,
                            int flags);
void *z_erofs_get_gbuf(unsigned int requiredpages);
void z_erofs_put_gbuf(void *ptr);
int z_erofs_gbuf_growsize(unsigned int nrpages);
int __init z_erofs_gbuf_init(void);
void z_erofs_gbuf_exit(void);
int erofs_init_managed_cache(struct super_block *sb);
int z_erofs_parse_cfgs(struct super_block *sb, struct erofs_super_block *dsb);
#else
static inline void erofs_shrinker_register(struct super_block *sb) {}
static inline void erofs_shrinker_unregister(struct super_block *sb) {}
static inline int erofs_init_shrinker(void) { return 0; }
static inline void erofs_exit_shrinker(void) {}
static inline int z_erofs_init_subsystem(void) { return 0; }
static inline void z_erofs_exit_subsystem(void) {}
static inline int erofs_init_managed_cache(struct super_block *sb) { return 0; }
#endif        /* !CONFIG_EROFS_FS_ZIP */

#ifdef CONFIG_EROFS_FS_BACKED_BY_FILE
struct bio *erofs_fileio_bio_alloc(struct erofs_map_dev *mdev);
void erofs_fileio_submit_bio(struct bio *bio);
#else
static inline struct bio *erofs_fileio_bio_alloc(struct erofs_map_dev *mdev) { return NULL; }
static inline void erofs_fileio_submit_bio(struct bio *bio) {}
#endif

#ifdef CONFIG_EROFS_FS_ONDEMAND
int erofs_fscache_register_fs(struct super_block *sb);
void erofs_fscache_unregister_fs(struct super_block *sb);

struct erofs_fscache *erofs_fscache_register_cookie(struct super_block *sb,
                                        char *name, unsigned int flags);
void erofs_fscache_unregister_cookie(struct erofs_fscache *fscache);
struct bio *erofs_fscache_bio_alloc(struct erofs_map_dev *mdev);
void erofs_fscache_submit_bio(struct bio *bio);
#else
static inline int erofs_fscache_register_fs(struct super_block *sb)
{
        return -EOPNOTSUPP;
}
static inline void erofs_fscache_unregister_fs(struct super_block *sb) {}

static inline
struct erofs_fscache *erofs_fscache_register_cookie(struct super_block *sb,
                                        char *name, unsigned int flags)
{
        return ERR_PTR(-EOPNOTSUPP);
}

static inline void erofs_fscache_unregister_cookie(struct erofs_fscache *fscache)
{
}
static inline struct bio *erofs_fscache_bio_alloc(struct erofs_map_dev *mdev) { return NULL; }
static inline void erofs_fscache_submit_bio(struct bio *bio) {}
#endif

#define EFSCORRUPTED    EUCLEAN         /* Filesystem is corrupted */

#endif        /* __EROFS_INTERNAL_H */









































































































































































































































































































































































































































































































































































































































































































































































































































































































































































































































































































































































































































































































































































































































































































































































































































































































































































































































































































































































































































































































































































































































   16 






   16 












   16 
























   16 




































































































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
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
1187
1188
1189
1190
1191
1192
1193
1194
1195
1196
1197
1198
1199
1200
1201
1202
1203
1204
1205
1206
1207
1208
1209
1210
1211
1212
1213
1214
1215
1216
1217
1218
1219
1220
1221
1222
1223
1224
1225
1226
1227
1228
1229
1230
1231
1232
1233
1234
1235
1236
1237
1238
1239
1240
1241
1242
1243
1244
1245
1246
1247
1248
1249
1250
1251
1252
1253
1254
1255
1256
1257
1258
1259
1260
1261
1262
1263
1264
1265
1266
1267
1268
1269
1270
1271
1272
1273
1274
1275
1276
1277
1278
1279
1280
1281
1282
1283
1284
1285
1286
1287
1288
1289
1290
1291
1292
1293
1294
1295
1296
1297
1298
1299
1300
1301
1302
1303
1304
1305
1306
1307
1308
1309
1310
1311
1312
1313
1314
1315
1316
1317
1318
1319
1320
1321
1322
1323
1324
1325
1326
1327
1328
1329
1330
1331
1332
1333
1334
1335
1336
1337
1338
1339
1340
1341
1342
1343
1344
1345
1346
1347
1348
1349
1350
1351
1352
1353
1354
1355
1356
1357
1358
1359
1360
1361
1362
1363
1364
1365
1366
1367
1368
1369
1370
1371
1372
1373
1374
1375
1376
1377
1378
1379
1380
1381
1382
1383
1384
1385
1386
1387
1388
1389
1390
1391
1392
1393
1394
1395
1396
1397
1398
1399
1400
1401
1402
1403
1404
1405
1406
1407
1408
1409
1410
1411
1412
1413
1414
1415
1416
1417
1418
1419
1420
1421
1422
1423
1424
1425
1426
1427
1428
1429
1430
1431
1432
1433
1434
1435
1436
1437
1438
1439
1440
1441
1442
1443
1444
1445
1446
1447
1448
1449
1450
1451
1452
1453
1454
1455
1456
1457
1458
1459
1460
1461
1462
1463
1464
1465
1466
1467
1468
1469
1470
1471
1472
1473
1474
1475
1476
1477
1478
1479
1480
1481
1482
1483
1484
1485
1486
1487
1488
1489
1490
1491
1492
1493
1494
1495
1496
1497
1498
1499
1500
1501
1502
1503
1504
1505
1506
1507
1508
1509
1510
1511
1512
1513
1514
1515
1516
1517
1518
1519
1520
1521
1522
1523
1524
1525
1526
1527
1528
1529
1530
1531
1532
1533
1534
1535
1536
1537
1538
1539
1540
1541
1542
1543
1544
1545
1546
1547
1548
1549
1550
1551
1552
1553
1554
1555
1556
1557
1558
1559
1560
1561
1562
1563
1564
1565
1566
1567
1568
1569
1570
1571
1572
1573
1574
1575
1576
1577
1578
1579
1580
1581
1582
1583
1584
1585
1586
1587
1588
1589
1590
1591
1592
1593
1594
1595
1596
1597
1598
1599
1600
1601
1602
1603
1604
1605
1606
1607
1608
1609
1610
1611
1612
1613
1614
1615
1616
1617
1618
1619
1620
1621
1622
1623
1624
1625
1626
1627
1628
1629
1630
1631
1632
1633
1634
1635
1636
1637
1638
1639
1640
1641
1642
1643
1644
1645
1646
1647
1648
1649
1650
1651
1652
1653
1654
1655
1656
1657
1658
1659
1660
1661
1662
1663
1664
1665
1666
1667
1668
1669
1670
1671
1672
1673
1674
1675
1676
1677
1678
1679
1680
1681
1682
1683
1684
1685
1686
1687
1688
1689
1690
1691
1692
1693
1694
1695
1696
1697
1698
1699
1700
1701
1702
1703
1704
1705
1706
1707
1708
1709
1710
1711
1712
1713
1714
1715
1716
1717
1718
1719
1720
1721
1722
1723
1724
1725
1726
1727
1728
1729
1730
1731
1732
1733
1734
1735
1736
1737
1738
1739
1740
1741
1742
1743
1744
1745
1746
1747
1748
1749
1750
1751
1752
1753
1754
1755
1756
1757
1758
1759
1760
1761
1762
1763
1764
1765
1766
1767
1768
1769
1770
1771
1772
1773
1774
1775
1776
1777
1778
1779
1780
1781
1782
1783
1784
1785
1786
1787
1788
1789
1790
1791
1792
1793
1794
1795
1796
1797
1798
1799
1800
1801
1802
1803
1804
1805
1806
1807
1808
1809
1810
1811
1812
1813
1814
1815
1816
1817
1818
1819
1820
1821
1822
1823
1824
1825
1826
1827
1828
1829
1830
1831
1832
1833
1834
1835
1836
1837
1838
1839
1840
1841
1842
1843
1844
1845
1846
1847
1848
1849
1850
1851
1852
1853
1854
1855
1856
1857
1858
1859
1860
1861
1862
1863
1864
1865
1866
1867
1868
1869
1870
1871
1872
1873
1874
1875
1876
1877
1878
1879
1880
1881
1882
1883
1884
1885
1886
1887
1888
1889
1890
1891
1892
1893
1894
1895
1896
1897
1898
1899
1900
1901
1902
1903
1904
1905
1906
1907
1908
1909
1910
1911
1912
1913
1914
1915
1916
1917
1918
1919
1920
1921
1922
1923
1924
1925
1926
1927
1928
1929
1930
1931
1932
1933
1934
1935
1936
1937
1938
1939
1940
1941
1942
1943
1944
1945
1946
1947
1948
1949
1950
1951
1952
1953
1954
1955
1956
1957
1958
1959
1960
1961
1962
1963
1964
1965
1966
1967
1968
1969
1970
1971
1972
1973
1974
1975
1976
1977
1978
1979
1980
1981
1982
1983
1984
1985
1986
1987
1988
1989
1990
1991
1992
1993
1994
1995
1996
1997
1998
1999
2000
2001
2002
2003
2004
2005
2006
2007
2008
2009
2010
2011
2012
2013
2014
2015
2016
2017
2018
2019
2020
2021
2022
2023
2024
2025
2026
2027
2028
2029
2030
2031
2032
2033
2034
2035
2036
2037
2038
2039
2040
2041
2042
2043
2044
2045
2046
2047
2048
2049
2050
2051
2052
2053
2054
2055
2056
2057
2058
2059
2060
2061
2062
2063
2064
2065
2066
2067
2068
2069
2070
2071
2072
2073
2074
2075
2076
2077
2078
2079
2080
2081
2082
2083
2084
2085
2086
2087
2088
2089
2090
2091
2092
2093
2094
2095
2096
2097
2098
2099
2100
2101
2102
2103
2104
2105
2106
2107
2108
2109
2110
2111
2112
2113
2114
2115
2116
2117
2118
2119
2120
2121
2122
2123
2124
2125
2126
2127
2128
2129
2130
2131
2132
2133
2134
2135
2136
2137
2138
2139
2140
2141
2142
2143
2144
2145
2146
2147
2148
2149
2150
2151
2152
2153
2154
2155
2156
2157
2158
2159
2160
2161
2162
2163
2164
2165
2166
2167
2168
2169
2170
2171
2172
2173
2174
2175
2176
2177
2178
2179
2180
2181
2182
2183
2184
2185
2186
2187
2188
2189
2190
2191
2192
2193
2194
2195
2196
2197
2198
2199
2200
2201
2202
2203
2204
2205
2206
2207
2208
2209
2210
2211
2212
2213
2214
2215
2216
2217
2218
2219
2220
2221
2222
2223
2224
2225
2226
2227
2228
2229
2230
2231
2232
2233
2234
2235
2236
2237
2238
2239
2240
2241
2242
2243
2244
2245
2246
2247
2248
2249
2250
2251
2252
2253
2254
2255
2256
2257
2258
2259
2260
2261
2262
2263
2264
2265
2266
2267
2268
2269
2270
2271
2272
2273
2274
2275
2276
2277
2278
2279
2280
2281
2282
2283
2284
2285
2286
2287
2288
2289
2290
2291
2292
2293
2294
2295
2296
2297
2298
/*
 * Copyright (c) 2004 Topspin Communications.  All rights reserved.
 * Copyright (c) 2005 Voltaire, Inc.  All rights reserved.
 * Copyright (c) 2006 Intel Corporation.  All rights reserved.
 *
 * This software is available to you under a choice of one of two
 * licenses.  You may choose to be licensed under the terms of the GNU
 * General Public License (GPL) Version 2, available from the file
 * COPYING in the main directory of this source tree, or the
 * OpenIB.org BSD license below:
 *
 *     Redistribution and use in source and binary forms, with or
 *     without modification, are permitted provided that the following
 *     conditions are met:
 *
 *      - Redistributions of source code must retain the above
 *        copyright notice, this list of conditions and the following
 *        disclaimer.
 *
 *      - Redistributions in binary form must reproduce the above
 *        copyright notice, this list of conditions and the following
 *        disclaimer in the documentation and/or other materials
 *        provided with the distribution.
 *
 * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
 * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
 * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
 * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
 * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
 * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
 * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
 * SOFTWARE.
 */

#include <linux/init.h>
#include <linux/err.h>
#include <linux/random.h>
#include <linux/spinlock.h>
#include <linux/slab.h>
#include <linux/dma-mapping.h>
#include <linux/kref.h>
#include <linux/xarray.h>
#include <linux/workqueue.h>
#include <uapi/linux/if_ether.h>
#include <rdma/ib_pack.h>
#include <rdma/ib_cache.h>
#include <rdma/rdma_netlink.h>
#include <net/netlink.h>
#include <uapi/rdma/ib_user_sa.h>
#include <rdma/ib_marshall.h>
#include <rdma/ib_addr.h>
#include <rdma/opa_addr.h>
#include <rdma/rdma_cm.h>
#include "sa.h"
#include "core_priv.h"

#define IB_SA_LOCAL_SVC_TIMEOUT_MIN                100
#define IB_SA_LOCAL_SVC_TIMEOUT_DEFAULT                2000
#define IB_SA_LOCAL_SVC_TIMEOUT_MAX                200000
#define IB_SA_CPI_MAX_RETRY_CNT                        3
#define IB_SA_CPI_RETRY_WAIT                        1000 /*msecs */
static int sa_local_svc_timeout_ms = IB_SA_LOCAL_SVC_TIMEOUT_DEFAULT;

struct ib_sa_sm_ah {
        struct ib_ah        *ah;
        struct kref          ref;
        u16                     pkey_index;
        u8                     src_path_mask;
};

enum rdma_class_port_info_type {
        RDMA_CLASS_PORT_INFO_IB,
        RDMA_CLASS_PORT_INFO_OPA
};

struct rdma_class_port_info {
        enum rdma_class_port_info_type type;
        union {
                struct ib_class_port_info ib;
                struct opa_class_port_info opa;
        };
};

struct ib_sa_classport_cache {
        bool valid;
        int retry_cnt;
        struct rdma_class_port_info data;
};

struct ib_sa_port {
        struct ib_mad_agent *agent;
        struct ib_sa_sm_ah  *sm_ah;
        struct work_struct   update_task;
        struct ib_sa_classport_cache classport_info;
        struct delayed_work ib_cpi_work;
        spinlock_t                   classport_lock; /* protects class port info set */
        spinlock_t           ah_lock;
        u32                     port_num;
};

struct ib_sa_device {
        int                     start_port, end_port;
        struct ib_event_handler event_handler;
        struct ib_sa_port port[];
};

struct ib_sa_query {
        void (*callback)(struct ib_sa_query *sa_query, int status,
                         struct ib_sa_mad *mad);
        void (*release)(struct ib_sa_query *);
        struct ib_sa_client    *client;
        struct ib_sa_port      *port;
        struct ib_mad_send_buf *mad_buf;
        struct ib_sa_sm_ah     *sm_ah;
        int                        id;
        u32                        flags;
        struct list_head        list; /* Local svc request list */
        u32                        seq; /* Local svc request sequence number */
        unsigned long                timeout; /* Local svc timeout */
        u8                        path_use; /* How will the pathrecord be used */
};

#define IB_SA_ENABLE_LOCAL_SERVICE        0x00000001
#define IB_SA_CANCEL                        0x00000002
#define IB_SA_QUERY_OPA                        0x00000004

struct ib_sa_path_query {
        void (*callback)(int status, struct sa_path_rec *rec,
                         unsigned int num_paths, void *context);
        void *context;
        struct ib_sa_query sa_query;
        struct sa_path_rec *conv_pr;
};

struct ib_sa_guidinfo_query {
        void (*callback)(int, struct ib_sa_guidinfo_rec *, void *);
        void *context;
        struct ib_sa_query sa_query;
};

struct ib_sa_classport_info_query {
        void (*callback)(void *);
        void *context;
        struct ib_sa_query sa_query;
};

struct ib_sa_mcmember_query {
        void (*callback)(int, struct ib_sa_mcmember_rec *, void *);
        void *context;
        struct ib_sa_query sa_query;
};

static LIST_HEAD(ib_nl_request_list);
static DEFINE_SPINLOCK(ib_nl_request_lock);
static atomic_t ib_nl_sa_request_seq;
static struct workqueue_struct *ib_nl_wq;
static struct delayed_work ib_nl_timed_work;
static const struct nla_policy ib_nl_policy[LS_NLA_TYPE_MAX] = {
        [LS_NLA_TYPE_PATH_RECORD]        = {.type = NLA_BINARY,
                .len = sizeof(struct ib_path_rec_data)},
        [LS_NLA_TYPE_TIMEOUT]                = {.type = NLA_U32},
        [LS_NLA_TYPE_SERVICE_ID]        = {.type = NLA_U64},
        [LS_NLA_TYPE_DGID]                = {.type = NLA_BINARY,
                .len = sizeof(struct rdma_nla_ls_gid)},
        [LS_NLA_TYPE_SGID]                = {.type = NLA_BINARY,
                .len = sizeof(struct rdma_nla_ls_gid)},
        [LS_NLA_TYPE_TCLASS]                = {.type = NLA_U8},
        [LS_NLA_TYPE_PKEY]                = {.type = NLA_U16},
        [LS_NLA_TYPE_QOS_CLASS]                = {.type = NLA_U16},
};


static int ib_sa_add_one(struct ib_device *device);
static void ib_sa_remove_one(struct ib_device *device, void *client_data);

static struct ib_client sa_client = {
        .name   = "sa",
        .add    = ib_sa_add_one,
        .remove = ib_sa_remove_one
};

static DEFINE_XARRAY_FLAGS(queries, XA_FLAGS_ALLOC | XA_FLAGS_LOCK_IRQ);

static DEFINE_SPINLOCK(tid_lock);
static u32 tid;

#define PATH_REC_FIELD(field) \
        .struct_offset_bytes = offsetof(struct sa_path_rec, field),        \
        .struct_size_bytes   = sizeof_field(struct sa_path_rec, field),        \
        .field_name          = "sa_path_rec:" #field

static const struct ib_field path_rec_table[] = {
        { PATH_REC_FIELD(service_id),
          .offset_words = 0,
          .offset_bits  = 0,
          .size_bits    = 64 },
        { PATH_REC_FIELD(dgid),
          .offset_words = 2,
          .offset_bits  = 0,
          .size_bits    = 128 },
        { PATH_REC_FIELD(sgid),
          .offset_words = 6,
          .offset_bits  = 0,
          .size_bits    = 128 },
        { PATH_REC_FIELD(ib.dlid),
          .offset_words = 10,
          .offset_bits  = 0,
          .size_bits    = 16 },
        { PATH_REC_FIELD(ib.slid),
          .offset_words = 10,
          .offset_bits  = 16,
          .size_bits    = 16 },
        { PATH_REC_FIELD(ib.raw_traffic),
          .offset_words = 11,
          .offset_bits  = 0,
          .size_bits    = 1 },
        { RESERVED,
          .offset_words = 11,
          .offset_bits  = 1,
          .size_bits    = 3 },
        { PATH_REC_FIELD(flow_label),
          .offset_words = 11,
          .offset_bits  = 4,
          .size_bits    = 20 },
        { PATH_REC_FIELD(hop_limit),
          .offset_words = 11,
          .offset_bits  = 24,
          .size_bits    = 8 },
        { PATH_REC_FIELD(traffic_class),
          .offset_words = 12,
          .offset_bits  = 0,
          .size_bits    = 8 },
        { PATH_REC_FIELD(reversible),
          .offset_words = 12,
          .offset_bits  = 8,
          .size_bits    = 1 },
        { PATH_REC_FIELD(numb_path),
          .offset_words = 12,
          .offset_bits  = 9,
          .size_bits    = 7 },
        { PATH_REC_FIELD(pkey),
          .offset_words = 12,
          .offset_bits  = 16,
          .size_bits    = 16 },
        { PATH_REC_FIELD(qos_class),
          .offset_words = 13,
          .offset_bits  = 0,
          .size_bits    = 12 },
        { PATH_REC_FIELD(sl),
          .offset_words = 13,
          .offset_bits  = 12,
          .size_bits    = 4 },
        { PATH_REC_FIELD(mtu_selector),
          .offset_words = 13,
          .offset_bits  = 16,
          .size_bits    = 2 },
        { PATH_REC_FIELD(mtu),
          .offset_words = 13,
          .offset_bits  = 18,
          .size_bits    = 6 },
        { PATH_REC_FIELD(rate_selector),
          .offset_words = 13,
          .offset_bits  = 24,
          .size_bits    = 2 },
        { PATH_REC_FIELD(rate),
          .offset_words = 13,
          .offset_bits  = 26,
          .size_bits    = 6 },
        { PATH_REC_FIELD(packet_life_time_selector),
          .offset_words = 14,
          .offset_bits  = 0,
          .size_bits    = 2 },
        { PATH_REC_FIELD(packet_life_time),
          .offset_words = 14,
          .offset_bits  = 2,
          .size_bits    = 6 },
        { PATH_REC_FIELD(preference),
          .offset_words = 14,
          .offset_bits  = 8,
          .size_bits    = 8 },
        { RESERVED,
          .offset_words = 14,
          .offset_bits  = 16,
          .size_bits    = 48 },
};

#define OPA_PATH_REC_FIELD(field) \
        .struct_offset_bytes = \
                offsetof(struct sa_path_rec, field), \
        .struct_size_bytes   = \
                sizeof_field(struct sa_path_rec, field),        \
        .field_name          = "sa_path_rec:" #field

static const struct ib_field opa_path_rec_table[] = {
        { OPA_PATH_REC_FIELD(service_id),
          .offset_words = 0,
          .offset_bits  = 0,
          .size_bits    = 64 },
        { OPA_PATH_REC_FIELD(dgid),
          .offset_words = 2,
          .offset_bits  = 0,
          .size_bits    = 128 },
        { OPA_PATH_REC_FIELD(sgid),
          .offset_words = 6,
          .offset_bits  = 0,
          .size_bits    = 128 },
        { OPA_PATH_REC_FIELD(opa.dlid),
          .offset_words = 10,
          .offset_bits  = 0,
          .size_bits    = 32 },
        { OPA_PATH_REC_FIELD(opa.slid),
          .offset_words = 11,
          .offset_bits  = 0,
          .size_bits    = 32 },
        { OPA_PATH_REC_FIELD(opa.raw_traffic),
          .offset_words = 12,
          .offset_bits  = 0,
          .size_bits    = 1 },
        { RESERVED,
          .offset_words = 12,
          .offset_bits  = 1,
          .size_bits    = 3 },
        { OPA_PATH_REC_FIELD(flow_label),
          .offset_words = 12,
          .offset_bits  = 4,
          .size_bits    = 20 },
        { OPA_PATH_REC_FIELD(hop_limit),
          .offset_words = 12,
          .offset_bits  = 24,
          .size_bits    = 8 },
        { OPA_PATH_REC_FIELD(traffic_class),
          .offset_words = 13,
          .offset_bits  = 0,
          .size_bits    = 8 },
        { OPA_PATH_REC_FIELD(reversible),
          .offset_words = 13,
          .offset_bits  = 8,
          .size_bits    = 1 },
        { OPA_PATH_REC_FIELD(numb_path),
          .offset_words = 13,
          .offset_bits  = 9,
          .size_bits    = 7 },
        { OPA_PATH_REC_FIELD(pkey),
          .offset_words = 13,
          .offset_bits  = 16,
          .size_bits    = 16 },
        { OPA_PATH_REC_FIELD(opa.l2_8B),
          .offset_words = 14,
          .offset_bits  = 0,
          .size_bits    = 1 },
        { OPA_PATH_REC_FIELD(opa.l2_10B),
          .offset_words = 14,
          .offset_bits  = 1,
          .size_bits    = 1 },
        { OPA_PATH_REC_FIELD(opa.l2_9B),
          .offset_words = 14,
          .offset_bits  = 2,
          .size_bits    = 1 },
        { OPA_PATH_REC_FIELD(opa.l2_16B),
          .offset_words = 14,
          .offset_bits  = 3,
          .size_bits    = 1 },
        { RESERVED,
          .offset_words = 14,
          .offset_bits  = 4,
          .size_bits    = 2 },
        { OPA_PATH_REC_FIELD(opa.qos_type),
          .offset_words = 14,
          .offset_bits  = 6,
          .size_bits    = 2 },
        { OPA_PATH_REC_FIELD(opa.qos_priority),
          .offset_words = 14,
          .offset_bits  = 8,
          .size_bits    = 8 },
        { RESERVED,
          .offset_words = 14,
          .offset_bits  = 16,
          .size_bits    = 3 },
        { OPA_PATH_REC_FIELD(sl),
          .offset_words = 14,
          .offset_bits  = 19,
          .size_bits    = 5 },
        { RESERVED,
          .offset_words = 14,
          .offset_bits  = 24,
          .size_bits    = 8 },
        { OPA_PATH_REC_FIELD(mtu_selector),
          .offset_words = 15,
          .offset_bits  = 0,
          .size_bits    = 2 },
        { OPA_PATH_REC_FIELD(mtu),
          .offset_words = 15,
          .offset_bits  = 2,
          .size_bits    = 6 },
        { OPA_PATH_REC_FIELD(rate_selector),
          .offset_words = 15,
          .offset_bits  = 8,
          .size_bits    = 2 },
        { OPA_PATH_REC_FIELD(rate),
          .offset_words = 15,
          .offset_bits  = 10,
          .size_bits    = 6 },
        { OPA_PATH_REC_FIELD(packet_life_time_selector),
          .offset_words = 15,
          .offset_bits  = 16,
          .size_bits    = 2 },
        { OPA_PATH_REC_FIELD(packet_life_time),
          .offset_words = 15,
          .offset_bits  = 18,
          .size_bits    = 6 },
        { OPA_PATH_REC_FIELD(preference),
          .offset_words = 15,
          .offset_bits  = 24,
          .size_bits    = 8 },
};

#define MCMEMBER_REC_FIELD(field) \
        .struct_offset_bytes = offsetof(struct ib_sa_mcmember_rec, field),        \
        .struct_size_bytes   = sizeof_field(struct ib_sa_mcmember_rec, field),        \
        .field_name          = "sa_mcmember_rec:" #field

static const struct ib_field mcmember_rec_table[] = {
        { MCMEMBER_REC_FIELD(mgid),
          .offset_words = 0,
          .offset_bits  = 0,
          .size_bits    = 128 },
        { MCMEMBER_REC_FIELD(port_gid),
          .offset_words = 4,
          .offset_bits  = 0,
          .size_bits    = 128 },
        { MCMEMBER_REC_FIELD(qkey),
          .offset_words = 8,
          .offset_bits  = 0,
          .size_bits    = 32 },
        { MCMEMBER_REC_FIELD(mlid),
          .offset_words = 9,
          .offset_bits  = 0,
          .size_bits    = 16 },
        { MCMEMBER_REC_FIELD(mtu_selector),
          .offset_words = 9,
          .offset_bits  = 16,
          .size_bits    = 2 },
        { MCMEMBER_REC_FIELD(mtu),
          .offset_words = 9,
          .offset_bits  = 18,
          .size_bits    = 6 },
        { MCMEMBER_REC_FIELD(traffic_class),
          .offset_words = 9,
          .offset_bits  = 24,
          .size_bits    = 8 },
        { MCMEMBER_REC_FIELD(pkey),
          .offset_words = 10,
          .offset_bits  = 0,
          .size_bits    = 16 },
        { MCMEMBER_REC_FIELD(rate_selector),
          .offset_words = 10,
          .offset_bits  = 16,
          .size_bits    = 2 },
        { MCMEMBER_REC_FIELD(rate),
          .offset_words = 10,
          .offset_bits  = 18,
          .size_bits    = 6 },
        { MCMEMBER_REC_FIELD(packet_life_time_selector),
          .offset_words = 10,
          .offset_bits  = 24,
          .size_bits    = 2 },
        { MCMEMBER_REC_FIELD(packet_life_time),
          .offset_words = 10,
          .offset_bits  = 26,
          .size_bits    = 6 },
        { MCMEMBER_REC_FIELD(sl),
          .offset_words = 11,
          .offset_bits  = 0,
          .size_bits    = 4 },
        { MCMEMBER_REC_FIELD(flow_label),
          .offset_words = 11,
          .offset_bits  = 4,
          .size_bits    = 20 },
        { MCMEMBER_REC_FIELD(hop_limit),
          .offset_words = 11,
          .offset_bits  = 24,
          .size_bits    = 8 },
        { MCMEMBER_REC_FIELD(scope),
          .offset_words = 12,
          .offset_bits  = 0,
          .size_bits    = 4 },
        { MCMEMBER_REC_FIELD(join_state),
          .offset_words = 12,
          .offset_bits  = 4,
          .size_bits    = 4 },
        { MCMEMBER_REC_FIELD(proxy_join),
          .offset_words = 12,
          .offset_bits  = 8,
          .size_bits    = 1 },
        { RESERVED,
          .offset_words = 12,
          .offset_bits  = 9,
          .size_bits    = 23 },
};

#define CLASSPORTINFO_REC_FIELD(field) \
        .struct_offset_bytes = offsetof(struct ib_class_port_info, field),        \
        .struct_size_bytes   = sizeof_field(struct ib_class_port_info, field),        \
        .field_name          = "ib_class_port_info:" #field

static const struct ib_field ib_classport_info_rec_table[] = {
        { CLASSPORTINFO_REC_FIELD(base_version),
          .offset_words = 0,
          .offset_bits  = 0,
          .size_bits    = 8 },
        { CLASSPORTINFO_REC_FIELD(class_version),
          .offset_words = 0,
          .offset_bits  = 8,
          .size_bits    = 8 },
        { CLASSPORTINFO_REC_FIELD(capability_mask),
          .offset_words = 0,
          .offset_bits  = 16,
          .size_bits    = 16 },
        { CLASSPORTINFO_REC_FIELD(cap_mask2_resp_time),
          .offset_words = 1,
          .offset_bits  = 0,
          .size_bits    = 32 },
        { CLASSPORTINFO_REC_FIELD(redirect_gid),
          .offset_words = 2,
          .offset_bits  = 0,
          .size_bits    = 128 },
        { CLASSPORTINFO_REC_FIELD(redirect_tcslfl),
          .offset_words = 6,
          .offset_bits  = 0,
          .size_bits    = 32 },
        { CLASSPORTINFO_REC_FIELD(redirect_lid),
          .offset_words = 7,
          .offset_bits  = 0,
          .size_bits    = 16 },
        { CLASSPORTINFO_REC_FIELD(redirect_pkey),
          .offset_words = 7,
          .offset_bits  = 16,
          .size_bits    = 16 },

        { CLASSPORTINFO_REC_FIELD(redirect_qp),
          .offset_words = 8,
          .offset_bits  = 0,
          .size_bits    = 32 },
        { CLASSPORTINFO_REC_FIELD(redirect_qkey),
          .offset_words = 9,
          .offset_bits  = 0,
          .size_bits    = 32 },

        { CLASSPORTINFO_REC_FIELD(trap_gid),
          .offset_words = 10,
          .offset_bits  = 0,
          .size_bits    = 128 },
        { CLASSPORTINFO_REC_FIELD(trap_tcslfl),
          .offset_words = 14,
          .offset_bits  = 0,
          .size_bits    = 32 },

        { CLASSPORTINFO_REC_FIELD(trap_lid),
          .offset_words = 15,
          .offset_bits  = 0,
          .size_bits    = 16 },
        { CLASSPORTINFO_REC_FIELD(trap_pkey),
          .offset_words = 15,
          .offset_bits  = 16,
          .size_bits    = 16 },

        { CLASSPORTINFO_REC_FIELD(trap_hlqp),
          .offset_words = 16,
          .offset_bits  = 0,
          .size_bits    = 32 },
        { CLASSPORTINFO_REC_FIELD(trap_qkey),
          .offset_words = 17,
          .offset_bits  = 0,
          .size_bits    = 32 },
};

#define OPA_CLASSPORTINFO_REC_FIELD(field) \
        .struct_offset_bytes =\
                offsetof(struct opa_class_port_info, field),        \
        .struct_size_bytes   = \
                sizeof_field(struct opa_class_port_info, field),        \
        .field_name          = "opa_class_port_info:" #field

static const struct ib_field opa_classport_info_rec_table[] = {
        { OPA_CLASSPORTINFO_REC_FIELD(base_version),
          .offset_words = 0,
          .offset_bits  = 0,
          .size_bits    = 8 },
        { OPA_CLASSPORTINFO_REC_FIELD(class_version),
          .offset_words = 0,
          .offset_bits  = 8,
          .size_bits    = 8 },
        { OPA_CLASSPORTINFO_REC_FIELD(cap_mask),
          .offset_words = 0,
          .offset_bits  = 16,
          .size_bits    = 16 },
        { OPA_CLASSPORTINFO_REC_FIELD(cap_mask2_resp_time),
          .offset_words = 1,
          .offset_bits  = 0,
          .size_bits    = 32 },
        { OPA_CLASSPORTINFO_REC_FIELD(redirect_gid),
          .offset_words = 2,
          .offset_bits  = 0,
          .size_bits    = 128 },
        { OPA_CLASSPORTINFO_REC_FIELD(redirect_tc_fl),
          .offset_words = 6,
          .offset_bits  = 0,
          .size_bits    = 32 },
        { OPA_CLASSPORTINFO_REC_FIELD(redirect_lid),
          .offset_words = 7,
          .offset_bits  = 0,
          .size_bits    = 32 },
        { OPA_CLASSPORTINFO_REC_FIELD(redirect_sl_qp),
          .offset_words = 8,
          .offset_bits  = 0,
          .size_bits    = 32 },
        { OPA_CLASSPORTINFO_REC_FIELD(redirect_qkey),
          .offset_words = 9,
          .offset_bits  = 0,
          .size_bits    = 32 },
        { OPA_CLASSPORTINFO_REC_FIELD(trap_gid),
          .offset_words = 10,
          .offset_bits  = 0,
          .size_bits    = 128 },
        { OPA_CLASSPORTINFO_REC_FIELD(trap_tc_fl),
          .offset_words = 14,
          .offset_bits  = 0,
          .size_bits    = 32 },
        { OPA_CLASSPORTINFO_REC_FIELD(trap_lid),
          .offset_words = 15,
          .offset_bits  = 0,
          .size_bits    = 32 },
        { OPA_CLASSPORTINFO_REC_FIELD(trap_hl_qp),
          .offset_words = 16,
          .offset_bits  = 0,
          .size_bits    = 32 },
        { OPA_CLASSPORTINFO_REC_FIELD(trap_qkey),
          .offset_words = 17,
          .offset_bits  = 0,
          .size_bits    = 32 },
        { OPA_CLASSPORTINFO_REC_FIELD(trap_pkey),
          .offset_words = 18,
          .offset_bits  = 0,
          .size_bits    = 16 },
        { OPA_CLASSPORTINFO_REC_FIELD(redirect_pkey),
          .offset_words = 18,
          .offset_bits  = 16,
          .size_bits    = 16 },
        { OPA_CLASSPORTINFO_REC_FIELD(trap_sl_rsvd),
          .offset_words = 19,
          .offset_bits  = 0,
          .size_bits    = 8 },
        { RESERVED,
          .offset_words = 19,
          .offset_bits  = 8,
          .size_bits    = 24 },
};

#define GUIDINFO_REC_FIELD(field) \
        .struct_offset_bytes = offsetof(struct ib_sa_guidinfo_rec, field),        \
        .struct_size_bytes   = sizeof_field(struct ib_sa_guidinfo_rec, field),        \
        .field_name          = "sa_guidinfo_rec:" #field

static const struct ib_field guidinfo_rec_table[] = {
        { GUIDINFO_REC_FIELD(lid),
          .offset_words = 0,
          .offset_bits  = 0,
          .size_bits    = 16 },
        { GUIDINFO_REC_FIELD(block_num),
          .offset_words = 0,
          .offset_bits  = 16,
          .size_bits    = 8 },
        { GUIDINFO_REC_FIELD(res1),
          .offset_words = 0,
          .offset_bits  = 24,
          .size_bits    = 8 },
        { GUIDINFO_REC_FIELD(res2),
          .offset_words = 1,
          .offset_bits  = 0,
          .size_bits    = 32 },
        { GUIDINFO_REC_FIELD(guid_info_list),
          .offset_words = 2,
          .offset_bits  = 0,
          .size_bits    = 512 },
};

#define RDMA_PRIMARY_PATH_MAX_REC_NUM 3

static inline void ib_sa_disable_local_svc(struct ib_sa_query *query)
{
        query->flags &= ~IB_SA_ENABLE_LOCAL_SERVICE;
}

static inline int ib_sa_query_cancelled(struct ib_sa_query *query)
{
        return (query->flags & IB_SA_CANCEL);
}

static void ib_nl_set_path_rec_attrs(struct sk_buff *skb,
                                     struct ib_sa_query *query)
{
        struct sa_path_rec *sa_rec = query->mad_buf->context[1];
        struct ib_sa_mad *mad = query->mad_buf->mad;
        ib_sa_comp_mask comp_mask = mad->sa_hdr.comp_mask;
        u16 val16;
        u64 val64;
        struct rdma_ls_resolve_header *header;

        query->mad_buf->context[1] = NULL;

        /* Construct the family header first */
        header = skb_put(skb, NLMSG_ALIGN(sizeof(*header)));
        strscpy_pad(header->device_name,
                    dev_name(&query->port->agent->device->dev),
                    LS_DEVICE_NAME_MAX);
        header->port_num = query->port->port_num;

        if ((comp_mask & IB_SA_PATH_REC_REVERSIBLE) &&
            sa_rec->reversible != 0)
                query->path_use = LS_RESOLVE_PATH_USE_ALL;
        else
                query->path_use = LS_RESOLVE_PATH_USE_UNIDIRECTIONAL;
        header->path_use = query->path_use;

        /* Now build the attributes */
        if (comp_mask & IB_SA_PATH_REC_SERVICE_ID) {
                val64 = be64_to_cpu(sa_rec->service_id);
                nla_put(skb, RDMA_NLA_F_MANDATORY | LS_NLA_TYPE_SERVICE_ID,
                        sizeof(val64), &val64);
        }
        if (comp_mask & IB_SA_PATH_REC_DGID)
                nla_put(skb, RDMA_NLA_F_MANDATORY | LS_NLA_TYPE_DGID,
                        sizeof(sa_rec->dgid), &sa_rec->dgid);
        if (comp_mask & IB_SA_PATH_REC_SGID)
                nla_put(skb, RDMA_NLA_F_MANDATORY | LS_NLA_TYPE_SGID,
                        sizeof(sa_rec->sgid), &sa_rec->sgid);
        if (comp_mask & IB_SA_PATH_REC_TRAFFIC_CLASS)
                nla_put(skb, RDMA_NLA_F_MANDATORY | LS_NLA_TYPE_TCLASS,
                        sizeof(sa_rec->traffic_class), &sa_rec->traffic_class);

        if (comp_mask & IB_SA_PATH_REC_PKEY) {
                val16 = be16_to_cpu(sa_rec->pkey);
                nla_put(skb, RDMA_NLA_F_MANDATORY | LS_NLA_TYPE_PKEY,
                        sizeof(val16), &val16);
        }
        if (comp_mask & IB_SA_PATH_REC_QOS_CLASS) {
                val16 = be16_to_cpu(sa_rec->qos_class);
                nla_put(skb, RDMA_NLA_F_MANDATORY | LS_NLA_TYPE_QOS_CLASS,
                        sizeof(val16), &val16);
        }
}

static int ib_nl_get_path_rec_attrs_len(ib_sa_comp_mask comp_mask)
{
        int len = 0;

        if (comp_mask & IB_SA_PATH_REC_SERVICE_ID)
                len += nla_total_size(sizeof(u64));
        if (comp_mask & IB_SA_PATH_REC_DGID)
                len += nla_total_size(sizeof(struct rdma_nla_ls_gid));
        if (comp_mask & IB_SA_PATH_REC_SGID)
                len += nla_total_size(sizeof(struct rdma_nla_ls_gid));
        if (comp_mask & IB_SA_PATH_REC_TRAFFIC_CLASS)
                len += nla_total_size(sizeof(u8));
        if (comp_mask & IB_SA_PATH_REC_PKEY)
                len += nla_total_size(sizeof(u16));
        if (comp_mask & IB_SA_PATH_REC_QOS_CLASS)
                len += nla_total_size(sizeof(u16));

        /*
         * Make sure that at least some of the required comp_mask bits are
         * set.
         */
        if (WARN_ON(len == 0))
                return len;

        /* Add the family header */
        len += NLMSG_ALIGN(sizeof(struct rdma_ls_resolve_header));

        return len;
}

static int ib_nl_make_request(struct ib_sa_query *query, gfp_t gfp_mask)
{
        struct sk_buff *skb = NULL;
        struct nlmsghdr *nlh;
        void *data;
        struct ib_sa_mad *mad;
        int len;
        unsigned long flags;
        unsigned long delay;
        gfp_t gfp_flag;
        int ret;

        INIT_LIST_HEAD(&query->list);
        query->seq = (u32)atomic_inc_return(&ib_nl_sa_request_seq);

        mad = query->mad_buf->mad;
        len = ib_nl_get_path_rec_attrs_len(mad->sa_hdr.comp_mask);
        if (len <= 0)
                return -EMSGSIZE;

        skb = nlmsg_new(len, gfp_mask);
        if (!skb)
                return -ENOMEM;

        /* Put nlmsg header only for now */
        data = ibnl_put_msg(skb, &nlh, query->seq, 0, RDMA_NL_LS,
                            RDMA_NL_LS_OP_RESOLVE, NLM_F_REQUEST);
        if (!data) {
                nlmsg_free(skb);
                return -EMSGSIZE;
        }

        /* Add attributes */
        ib_nl_set_path_rec_attrs(skb, query);

        /* Repair the nlmsg header length */
        nlmsg_end(skb, nlh);

        gfp_flag = ((gfp_mask & GFP_ATOMIC) == GFP_ATOMIC) ? GFP_ATOMIC :
                GFP_NOWAIT;

        spin_lock_irqsave(&ib_nl_request_lock, flags);
        ret = rdma_nl_multicast(&init_net, skb, RDMA_NL_GROUP_LS, gfp_flag);

        if (ret)
                goto out;

        /* Put the request on the list.*/
        delay = msecs_to_jiffies(sa_local_svc_timeout_ms);
        query->timeout = delay + jiffies;
        list_add_tail(&query->list, &ib_nl_request_list);
        /* Start the timeout if this is the only request */
        if (ib_nl_request_list.next == &query->list)
                queue_delayed_work(ib_nl_wq, &ib_nl_timed_work, delay);

out:
        spin_unlock_irqrestore(&ib_nl_request_lock, flags);

        return ret;
}

static int ib_nl_cancel_request(struct ib_sa_query *query)
{
        unsigned long flags;
        struct ib_sa_query *wait_query;
        int found = 0;

        spin_lock_irqsave(&ib_nl_request_lock, flags);
        list_for_each_entry(wait_query, &ib_nl_request_list, list) {
                /* Let the timeout to take care of the callback */
                if (query == wait_query) {
                        query->flags |= IB_SA_CANCEL;
                        query->timeout = jiffies;
                        list_move(&query->list, &ib_nl_request_list);
                        found = 1;
                        mod_delayed_work(ib_nl_wq, &ib_nl_timed_work, 1);
                        break;
                }
        }
        spin_unlock_irqrestore(&ib_nl_request_lock, flags);

        return found;
}

static void send_handler(struct ib_mad_agent *agent,
                         struct ib_mad_send_wc *mad_send_wc);

static void ib_nl_process_good_resolve_rsp(struct ib_sa_query *query,
                                           const struct nlmsghdr *nlh)
{
        struct sa_path_rec recs[RDMA_PRIMARY_PATH_MAX_REC_NUM];
        struct ib_sa_path_query *path_query;
        struct ib_path_rec_data *rec_data;
        struct ib_mad_send_wc mad_send_wc;
        const struct nlattr *head, *curr;
        struct ib_sa_mad *mad = NULL;
        int len, rem, status = -EIO;
        unsigned int num_prs = 0;
        u32 mask = 0;

        if (!query->callback)
                goto out;

        path_query = container_of(query, struct ib_sa_path_query, sa_query);
        mad = query->mad_buf->mad;

        head = (const struct nlattr *) nlmsg_data(nlh);
        len = nlmsg_len(nlh);
        switch (query->path_use) {
        case LS_RESOLVE_PATH_USE_UNIDIRECTIONAL:
                mask = IB_PATH_PRIMARY | IB_PATH_OUTBOUND;
                break;

        case LS_RESOLVE_PATH_USE_ALL:
                mask = IB_PATH_PRIMARY;
                break;

        case LS_RESOLVE_PATH_USE_GMP:
        default:
                mask = IB_PATH_PRIMARY | IB_PATH_GMP |
                        IB_PATH_BIDIRECTIONAL;
                break;
        }

        nla_for_each_attr(curr, head, len, rem) {
                if (curr->nla_type != LS_NLA_TYPE_PATH_RECORD)
                        continue;

                rec_data = nla_data(curr);
                if ((rec_data->flags & mask) != mask)
                        continue;

                if ((query->flags & IB_SA_QUERY_OPA) ||
                    path_query->conv_pr) {
                        mad->mad_hdr.method |= IB_MGMT_METHOD_RESP;
                        memcpy(mad->data, rec_data->path_rec,
                               sizeof(rec_data->path_rec));
                        query->callback(query, 0, mad);
                        goto out;
                }

                status = 0;
                ib_unpack(path_rec_table, ARRAY_SIZE(path_rec_table),
                          rec_data->path_rec, &recs[num_prs]);
                recs[num_prs].flags = rec_data->flags;
                recs[num_prs].rec_type = SA_PATH_REC_TYPE_IB;
                sa_path_set_dmac_zero(&recs[num_prs]);

                num_prs++;
                if (num_prs >= RDMA_PRIMARY_PATH_MAX_REC_NUM)
                        break;
        }

        if (!status) {
                mad->mad_hdr.method |= IB_MGMT_METHOD_RESP;
                path_query->callback(status, recs, num_prs,
                                     path_query->context);
        } else
                query->callback(query, status, mad);

out:
        mad_send_wc.send_buf = query->mad_buf;
        mad_send_wc.status = IB_WC_SUCCESS;
        send_handler(query->mad_buf->mad_agent, &mad_send_wc);
}

static void ib_nl_request_timeout(struct work_struct *work)
{
        unsigned long flags;
        struct ib_sa_query *query;
        unsigned long delay;
        struct ib_mad_send_wc mad_send_wc;
        int ret;

        spin_lock_irqsave(&ib_nl_request_lock, flags);
        while (!list_empty(&ib_nl_request_list)) {
                query = list_entry(ib_nl_request_list.next,
                                   struct ib_sa_query, list);

                if (time_after(query->timeout, jiffies)) {
                        delay = query->timeout - jiffies;
                        if ((long)delay <= 0)
                                delay = 1;
                        queue_delayed_work(ib_nl_wq, &ib_nl_timed_work, delay);
                        break;
                }

                list_del(&query->list);
                ib_sa_disable_local_svc(query);
                /* Hold the lock to protect against query cancellation */
                if (ib_sa_query_cancelled(query))
                        ret = -1;
                else
                        ret = ib_post_send_mad(query->mad_buf, NULL);
                if (ret) {
                        mad_send_wc.send_buf = query->mad_buf;
                        mad_send_wc.status = IB_WC_WR_FLUSH_ERR;
                        spin_unlock_irqrestore(&ib_nl_request_lock, flags);
                        send_handler(query->port->agent, &mad_send_wc);
                        spin_lock_irqsave(&ib_nl_request_lock, flags);
                }
        }
        spin_unlock_irqrestore(&ib_nl_request_lock, flags);
}

int ib_nl_handle_set_timeout(struct sk_buff *skb,
                             struct nlmsghdr *nlh,
                             struct netlink_ext_ack *extack)
{
        int timeout, delta, abs_delta;
        const struct nlattr *attr;
        unsigned long flags;
        struct ib_sa_query *query;
        long delay = 0;
        struct nlattr *tb[LS_NLA_TYPE_MAX];
        int ret;

        if (!(nlh->nlmsg_flags & NLM_F_REQUEST) ||
            !(NETLINK_CB(skb).sk))
                return -EPERM;

        ret = nla_parse_deprecated(tb, LS_NLA_TYPE_MAX - 1, nlmsg_data(nlh),
                                   nlmsg_len(nlh), ib_nl_policy, NULL);
        attr = (const struct nlattr *)tb[LS_NLA_TYPE_TIMEOUT];
        if (ret || !attr)
                goto settimeout_out;

        timeout = *(int *) nla_data(attr);
        if (timeout < IB_SA_LOCAL_SVC_TIMEOUT_MIN)
                timeout = IB_SA_LOCAL_SVC_TIMEOUT_MIN;
        if (timeout > IB_SA_LOCAL_SVC_TIMEOUT_MAX)
                timeout = IB_SA_LOCAL_SVC_TIMEOUT_MAX;

        delta = timeout - sa_local_svc_timeout_ms;
        if (delta < 0)
                abs_delta = -delta;
        else
                abs_delta = delta;

        if (delta != 0) {
                spin_lock_irqsave(&ib_nl_request_lock, flags);
                sa_local_svc_timeout_ms = timeout;
                list_for_each_entry(query, &ib_nl_request_list, list) {
                        if (delta < 0 && abs_delta > query->timeout)
                                query->timeout = 0;
                        else
                                query->timeout += delta;

                        /* Get the new delay from the first entry */
                        if (!delay) {
                                delay = query->timeout - jiffies;
                                if (delay <= 0)
                                        delay = 1;
                        }
                }
                if (delay)
                        mod_delayed_work(ib_nl_wq, &ib_nl_timed_work,
                                         (unsigned long)delay);
                spin_unlock_irqrestore(&ib_nl_request_lock, flags);
        }

settimeout_out:
        return 0;
}

static inline int ib_nl_is_good_resolve_resp(const struct nlmsghdr *nlh)
{
        struct nlattr *tb[LS_NLA_TYPE_MAX];
        int ret;

        if (nlh->nlmsg_flags & RDMA_NL_LS_F_ERR)
                return 0;

        ret = nla_parse_deprecated(tb, LS_NLA_TYPE_MAX - 1, nlmsg_data(nlh),
                                   nlmsg_len(nlh), ib_nl_policy, NULL);
        if (ret)
                return 0;

        return 1;
}

int ib_nl_handle_resolve_resp(struct sk_buff *skb,
                              struct nlmsghdr *nlh,
                              struct netlink_ext_ack *extack)
{
        unsigned long flags;
        struct ib_sa_query *query = NULL, *iter;
        struct ib_mad_send_buf *send_buf;
        struct ib_mad_send_wc mad_send_wc;
        int ret;

        if ((nlh->nlmsg_flags & NLM_F_REQUEST) ||
            !(NETLINK_CB(skb).sk))
                return -EPERM;

        spin_lock_irqsave(&ib_nl_request_lock, flags);
        list_for_each_entry(iter, &ib_nl_request_list, list) {
                /*
                 * If the query is cancelled, let the timeout routine
                 * take care of it.
                 */
                if (nlh->nlmsg_seq == iter->seq) {
                        if (!ib_sa_query_cancelled(iter)) {
                                list_del(&iter->list);
                                query = iter;
                        }
                        break;
                }
        }

        if (!query) {
                spin_unlock_irqrestore(&ib_nl_request_lock, flags);
                goto resp_out;
        }

        send_buf = query->mad_buf;

        if (!ib_nl_is_good_resolve_resp(nlh)) {
                /* if the result is a failure, send out the packet via IB */
                ib_sa_disable_local_svc(query);
                ret = ib_post_send_mad(query->mad_buf, NULL);
                spin_unlock_irqrestore(&ib_nl_request_lock, flags);
                if (ret) {
                        mad_send_wc.send_buf = send_buf;
                        mad_send_wc.status = IB_WC_GENERAL_ERR;
                        send_handler(query->port->agent, &mad_send_wc);
                }
        } else {
                spin_unlock_irqrestore(&ib_nl_request_lock, flags);
                ib_nl_process_good_resolve_rsp(query, nlh);
        }

resp_out:
        return 0;
}

static void free_sm_ah(struct kref *kref)
{
        struct ib_sa_sm_ah *sm_ah = container_of(kref, struct ib_sa_sm_ah, ref);

        rdma_destroy_ah(sm_ah->ah, 0);
        kfree(sm_ah);
}

void ib_sa_register_client(struct ib_sa_client *client)
{
        atomic_set(&client->users, 1);
        init_completion(&client->comp);
}
EXPORT_SYMBOL(ib_sa_register_client);

void ib_sa_unregister_client(struct ib_sa_client *client)
{
        ib_sa_client_put(client);
        wait_for_completion(&client->comp);
}
EXPORT_SYMBOL(ib_sa_unregister_client);

/**
 * ib_sa_cancel_query - try to cancel an SA query
 * @id:ID of query to cancel
 * @query:query pointer to cancel
 *
 * Try to cancel an SA query.  If the id and query don't match up or
 * the query has already completed, nothing is done.  Otherwise the
 * query is canceled and will complete with a status of -EINTR.
 */
void ib_sa_cancel_query(int id, struct ib_sa_query *query)
{
        unsigned long flags;
        struct ib_mad_send_buf *mad_buf;

        xa_lock_irqsave(&queries, flags);
        if (xa_load(&queries, id) != query) {
                xa_unlock_irqrestore(&queries, flags);
                return;
        }
        mad_buf = query->mad_buf;
        xa_unlock_irqrestore(&queries, flags);

        /*
         * If the query is still on the netlink request list, schedule
         * it to be cancelled by the timeout routine. Otherwise, it has been
         * sent to the MAD layer and has to be cancelled from there.
         */
        if (!ib_nl_cancel_request(query))
                ib_cancel_mad(mad_buf);
}
EXPORT_SYMBOL(ib_sa_cancel_query);

static u8 get_src_path_mask(struct ib_device *device, u32 port_num)
{
        struct ib_sa_device *sa_dev;
        struct ib_sa_port   *port;
        unsigned long flags;
        u8 src_path_mask;

        sa_dev = ib_get_client_data(device, &sa_client);
        if (!sa_dev)
                return 0x7f;

        port  = &sa_dev->port[port_num - sa_dev->start_port];
        spin_lock_irqsave(&port->ah_lock, flags);
        src_path_mask = port->sm_ah ? port->sm_ah->src_path_mask : 0x7f;
        spin_unlock_irqrestore(&port->ah_lock, flags);

        return src_path_mask;
}

static int init_ah_attr_grh_fields(struct ib_device *device, u32 port_num,
                                   struct sa_path_rec *rec,
                                   struct rdma_ah_attr *ah_attr,
                                   const struct ib_gid_attr *gid_attr)
{
        enum ib_gid_type type = sa_conv_pathrec_to_gid_type(rec);

        if (!gid_attr) {
                gid_attr = rdma_find_gid_by_port(device, &rec->sgid, type,
                                                 port_num, NULL);
                if (IS_ERR(gid_attr))
                        return PTR_ERR(gid_attr);
        } else
                rdma_hold_gid_attr(gid_attr);

        rdma_move_grh_sgid_attr(ah_attr, &rec->dgid,
                                be32_to_cpu(rec->flow_label),
                                rec->hop_limit,        rec->traffic_class,
                                gid_attr);
        return 0;
}

/**
 * ib_init_ah_attr_from_path - Initialize address handle attributes based on
 *   an SA path record.
 * @device: Device associated ah attributes initialization.
 * @port_num: Port on the specified device.
 * @rec: path record entry to use for ah attributes initialization.
 * @ah_attr: address handle attributes to initialization from path record.
 * @gid_attr: SGID attribute to consider during initialization.
 *
 * When ib_init_ah_attr_from_path() returns success,
 * (a) for IB link layer it optionally contains a reference to SGID attribute
 * when GRH is present for IB link layer.
 * (b) for RoCE link layer it contains a reference to SGID attribute.
 * User must invoke rdma_destroy_ah_attr() to release reference to SGID
 * attributes which are initialized using ib_init_ah_attr_from_path().
 */
int ib_init_ah_attr_from_path(struct ib_device *device, u32 port_num,
                              struct sa_path_rec *rec,
                              struct rdma_ah_attr *ah_attr,
                              const struct ib_gid_attr *gid_attr)
{
        int ret = 0;

        memset(ah_attr, 0, sizeof(*ah_attr));
        ah_attr->type = rdma_ah_find_type(device, port_num);
        rdma_ah_set_sl(ah_attr, rec->sl);
        rdma_ah_set_port_num(ah_attr, port_num);
        rdma_ah_set_static_rate(ah_attr, rec->rate);

        if (sa_path_is_roce(rec)) {
                ret = roce_resolve_route_from_path(rec, gid_attr);
                if (ret)
                        return ret;

                memcpy(ah_attr->roce.dmac, sa_path_get_dmac(rec), ETH_ALEN);
        } else {
                rdma_ah_set_dlid(ah_attr, be32_to_cpu(sa_path_get_dlid(rec)));
                if (sa_path_is_opa(rec) &&
                    rdma_ah_get_dlid(ah_attr) == be16_to_cpu(IB_LID_PERMISSIVE))
                        rdma_ah_set_make_grd(ah_attr, true);

                rdma_ah_set_path_bits(ah_attr,
                                      be32_to_cpu(sa_path_get_slid(rec)) &
                                      get_src_path_mask(device, port_num));
        }

        if (rec->hop_limit > 0 || sa_path_is_roce(rec))
                ret = init_ah_attr_grh_fields(device, port_num,
                                              rec, ah_attr, gid_attr);
        return ret;
}
EXPORT_SYMBOL(ib_init_ah_attr_from_path);

static int alloc_mad(struct ib_sa_query *query, gfp_t gfp_mask)
{
        struct rdma_ah_attr ah_attr;
        unsigned long flags;

        spin_lock_irqsave(&query->port->ah_lock, flags);
        if (!query->port->sm_ah) {
                spin_unlock_irqrestore(&query->port->ah_lock, flags);
                return -EAGAIN;
        }
        kref_get(&query->port->sm_ah->ref);
        query->sm_ah = query->port->sm_ah;
        spin_unlock_irqrestore(&query->port->ah_lock, flags);

        /*
         * Always check if sm_ah has valid dlid assigned,
         * before querying for class port info
         */
        if ((rdma_query_ah(query->sm_ah->ah, &ah_attr) < 0) ||
            !rdma_is_valid_unicast_lid(&ah_attr)) {
                kref_put(&query->sm_ah->ref, free_sm_ah);
                return -EAGAIN;
        }
        query->mad_buf = ib_create_send_mad(query->port->agent, 1,
                                            query->sm_ah->pkey_index,
                                            0, IB_MGMT_SA_HDR, IB_MGMT_SA_DATA,
                                            gfp_mask,
                                            ((query->flags & IB_SA_QUERY_OPA) ?
                                             OPA_MGMT_BASE_VERSION :
                                             IB_MGMT_BASE_VERSION));
        if (IS_ERR(query->mad_buf)) {
                kref_put(&query->sm_ah->ref, free_sm_ah);
                return -ENOMEM;
        }

        query->mad_buf->ah = query->sm_ah->ah;

        return 0;
}

static void free_mad(struct ib_sa_query *query)
{
        ib_free_send_mad(query->mad_buf);
        kref_put(&query->sm_ah->ref, free_sm_ah);
}

static void init_mad(struct ib_sa_query *query, struct ib_mad_agent *agent)
{
        struct ib_sa_mad *mad = query->mad_buf->mad;
        unsigned long flags;

        memset(mad, 0, sizeof *mad);

        if (query->flags & IB_SA_QUERY_OPA) {
                mad->mad_hdr.base_version  = OPA_MGMT_BASE_VERSION;
                mad->mad_hdr.class_version = OPA_SA_CLASS_VERSION;
        } else {
                mad->mad_hdr.base_version  = IB_MGMT_BASE_VERSION;
                mad->mad_hdr.class_version = IB_SA_CLASS_VERSION;
        }
        mad->mad_hdr.mgmt_class    = IB_MGMT_CLASS_SUBN_ADM;
        spin_lock_irqsave(&tid_lock, flags);
        mad->mad_hdr.tid           =
                cpu_to_be64(((u64) agent->hi_tid) << 32 | tid++);
        spin_unlock_irqrestore(&tid_lock, flags);
}

static int send_mad(struct ib_sa_query *query, unsigned long timeout_ms,
                    gfp_t gfp_mask)
{
        unsigned long flags;
        int ret, id;
        const int nmbr_sa_query_retries = 10;

        xa_lock_irqsave(&queries, flags);
        ret = __xa_alloc(&queries, &id, query, xa_limit_32b, gfp_mask);
        xa_unlock_irqrestore(&queries, flags);
        if (ret < 0)
                return ret;

        query->mad_buf->timeout_ms  = timeout_ms / nmbr_sa_query_retries;
        query->mad_buf->retries = nmbr_sa_query_retries;
        if (!query->mad_buf->timeout_ms) {
                /* Special case, very small timeout_ms */
                query->mad_buf->timeout_ms = 1;
                query->mad_buf->retries = timeout_ms;
        }
        query->mad_buf->context[0] = query;
        query->id = id;

        if ((query->flags & IB_SA_ENABLE_LOCAL_SERVICE) &&
            (!(query->flags & IB_SA_QUERY_OPA))) {
                if (rdma_nl_chk_listeners(RDMA_NL_GROUP_LS)) {
                        if (!ib_nl_make_request(query, gfp_mask))
                                return id;
                }
                ib_sa_disable_local_svc(query);
        }

        ret = ib_post_send_mad(query->mad_buf, NULL);
        if (ret) {
                xa_lock_irqsave(&queries, flags);
                __xa_erase(&queries, id);
                xa_unlock_irqrestore(&queries, flags);
        }

        /*
         * It's not safe to dereference query any more, because the
         * send may already have completed and freed the query in
         * another context.
         */
        return ret ? ret : id;
}

void ib_sa_unpack_path(void *attribute, struct sa_path_rec *rec)
{
        ib_unpack(path_rec_table, ARRAY_SIZE(path_rec_table), attribute, rec);
}
EXPORT_SYMBOL(ib_sa_unpack_path);

void ib_sa_pack_path(struct sa_path_rec *rec, void *attribute)
{
        ib_pack(path_rec_table, ARRAY_SIZE(path_rec_table), rec, attribute);
}
EXPORT_SYMBOL(ib_sa_pack_path);

static bool ib_sa_opa_pathrecord_support(struct ib_sa_client *client,
                                         struct ib_sa_device *sa_dev,
                                         u32 port_num)
{
        struct ib_sa_port *port;
        unsigned long flags;
        bool ret = false;

        port = &sa_dev->port[port_num - sa_dev->start_port];
        spin_lock_irqsave(&port->classport_lock, flags);
        if (!port->classport_info.valid)
                goto ret;

        if (port->classport_info.data.type == RDMA_CLASS_PORT_INFO_OPA)
                ret = opa_get_cpi_capmask2(&port->classport_info.data.opa) &
                        OPA_CLASS_PORT_INFO_PR_SUPPORT;
ret:
        spin_unlock_irqrestore(&port->classport_lock, flags);
        return ret;
}

enum opa_pr_supported {
        PR_NOT_SUPPORTED,
        PR_OPA_SUPPORTED,
        PR_IB_SUPPORTED
};

/*
 * opa_pr_query_possible - Check if current PR query can be an OPA query.
 *
 * Returns PR_NOT_SUPPORTED if a path record query is not
 * possible, PR_OPA_SUPPORTED if an OPA path record query
 * is possible and PR_IB_SUPPORTED if an IB path record
 * query is possible.
 */
static int opa_pr_query_possible(struct ib_sa_client *client,
                                 struct ib_sa_device *sa_dev,
                                 struct ib_device *device, u32 port_num)
{
        struct ib_port_attr port_attr;

        if (ib_query_port(device, port_num, &port_attr))
                return PR_NOT_SUPPORTED;

        if (ib_sa_opa_pathrecord_support(client, sa_dev, port_num))
                return PR_OPA_SUPPORTED;

        if (port_attr.lid >= be16_to_cpu(IB_MULTICAST_LID_BASE))
                return PR_NOT_SUPPORTED;
        else
                return PR_IB_SUPPORTED;
}

static void ib_sa_path_rec_callback(struct ib_sa_query *sa_query,
                                    int status, struct ib_sa_mad *mad)
{
        struct ib_sa_path_query *query =
                container_of(sa_query, struct ib_sa_path_query, sa_query);
        struct sa_path_rec rec = {};

        if (!mad) {
                query->callback(status, NULL, 0, query->context);
                return;
        }

        if (sa_query->flags & IB_SA_QUERY_OPA) {
                ib_unpack(opa_path_rec_table, ARRAY_SIZE(opa_path_rec_table),
                          mad->data, &rec);
                rec.rec_type = SA_PATH_REC_TYPE_OPA;
                query->callback(status, &rec, 1, query->context);
                return;
        }

        ib_unpack(path_rec_table, ARRAY_SIZE(path_rec_table),
                  mad->data, &rec);
        rec.rec_type = SA_PATH_REC_TYPE_IB;
        sa_path_set_dmac_zero(&rec);

        if (query->conv_pr) {
                struct sa_path_rec opa;

                memset(&opa, 0, sizeof(struct sa_path_rec));
                sa_convert_path_ib_to_opa(&opa, &rec);
                query->callback(status, &opa, 1, query->context);
        } else {
                query->callback(status, &rec, 1, query->context);
        }
}

static void ib_sa_path_rec_release(struct ib_sa_query *sa_query)
{
        struct ib_sa_path_query *query =
                container_of(sa_query, struct ib_sa_path_query, sa_query);

        kfree(query->conv_pr);
        kfree(query);
}

/**
 * ib_sa_path_rec_get - Start a Path get query
 * @client:SA client
 * @device:device to send query on
 * @port_num: port number to send query on
 * @rec:Path Record to send in query
 * @comp_mask:component mask to send in query
 * @timeout_ms:time to wait for response
 * @gfp_mask:GFP mask to use for internal allocations
 * @callback:function called when query completes, times out or is
 * canceled
 * @context:opaque user context passed to callback
 * @sa_query:query context, used to cancel query
 *
 * Send a Path Record Get query to the SA to look up a path.  The
 * callback function will be called when the query completes (or
 * fails); status is 0 for a successful response, -EINTR if the query
 * is canceled, -ETIMEDOUT is the query timed out, or -EIO if an error
 * occurred sending the query.  The resp parameter of the callback is
 * only valid if status is 0.
 *
 * If the return value of ib_sa_path_rec_get() is negative, it is an
 * error code.  Otherwise it is a query ID that can be used to cancel
 * the query.
 */
int ib_sa_path_rec_get(struct ib_sa_client *client,
                       struct ib_device *device, u32 port_num,
                       struct sa_path_rec *rec,
                       ib_sa_comp_mask comp_mask,
                       unsigned long timeout_ms, gfp_t gfp_mask,
                       void (*callback)(int status,
                                        struct sa_path_rec *resp,
                                        unsigned int num_paths, void *context),
                       void *context,
                       struct ib_sa_query **sa_query)
{
        struct ib_sa_path_query *query;
        struct ib_sa_device *sa_dev = ib_get_client_data(device, &sa_client);
        struct ib_sa_port   *port;
        struct ib_mad_agent *agent;
        struct ib_sa_mad *mad;
        enum opa_pr_supported status;
        int ret;

        if (!sa_dev)
                return -ENODEV;

        if ((rec->rec_type != SA_PATH_REC_TYPE_IB) &&
            (rec->rec_type != SA_PATH_REC_TYPE_OPA))
                return -EINVAL;

        port  = &sa_dev->port[port_num - sa_dev->start_port];
        agent = port->agent;

        query = kzalloc(sizeof(*query), gfp_mask);
        if (!query)
                return -ENOMEM;

        query->sa_query.port     = port;
        if (rec->rec_type == SA_PATH_REC_TYPE_OPA) {
                status = opa_pr_query_possible(client, sa_dev, device, port_num);
                if (status == PR_NOT_SUPPORTED) {
                        ret = -EINVAL;
                        goto err1;
                } else if (status == PR_OPA_SUPPORTED) {
                        query->sa_query.flags |= IB_SA_QUERY_OPA;
                } else {
                        query->conv_pr =
                                kmalloc(sizeof(*query->conv_pr), gfp_mask);
                        if (!query->conv_pr) {
                                ret = -ENOMEM;
                                goto err1;
                        }
                }
        }

        ret = alloc_mad(&query->sa_query, gfp_mask);
        if (ret)
                goto err2;

        ib_sa_client_get(client);
        query->sa_query.client = client;
        query->callback        = callback;
        query->context         = context;

        mad = query->sa_query.mad_buf->mad;
        init_mad(&query->sa_query, agent);

        query->sa_query.callback = callback ? ib_sa_path_rec_callback : NULL;
        query->sa_query.release  = ib_sa_path_rec_release;
        mad->mad_hdr.method         = IB_MGMT_METHOD_GET;
        mad->mad_hdr.attr_id         = cpu_to_be16(IB_SA_ATTR_PATH_REC);
        mad->sa_hdr.comp_mask         = comp_mask;

        if (query->sa_query.flags & IB_SA_QUERY_OPA) {
                ib_pack(opa_path_rec_table, ARRAY_SIZE(opa_path_rec_table),
                        rec, mad->data);
        } else if (query->conv_pr) {
                sa_convert_path_opa_to_ib(query->conv_pr, rec);
                ib_pack(path_rec_table, ARRAY_SIZE(path_rec_table),
                        query->conv_pr, mad->data);
        } else {
                ib_pack(path_rec_table, ARRAY_SIZE(path_rec_table),
                        rec, mad->data);
        }

        *sa_query = &query->sa_query;

        query->sa_query.flags |= IB_SA_ENABLE_LOCAL_SERVICE;
        query->sa_query.mad_buf->context[1] = (query->conv_pr) ?
                                                query->conv_pr : rec;

        ret = send_mad(&query->sa_query, timeout_ms, gfp_mask);
        if (ret < 0)
                goto err3;

        return ret;

err3:
        *sa_query = NULL;
        ib_sa_client_put(query->sa_query.client);
        free_mad(&query->sa_query);
err2:
        kfree(query->conv_pr);
err1:
        kfree(query);
        return ret;
}
EXPORT_SYMBOL(ib_sa_path_rec_get);

static void ib_sa_mcmember_rec_callback(struct ib_sa_query *sa_query,
                                        int status, struct ib_sa_mad *mad)
{
        struct ib_sa_mcmember_query *query =
                container_of(sa_query, struct ib_sa_mcmember_query, sa_query);

        if (mad) {
                struct ib_sa_mcmember_rec rec;

                ib_unpack(mcmember_rec_table, ARRAY_SIZE(mcmember_rec_table),
                          mad->data, &rec);
                query->callback(status, &rec, query->context);
        } else
                query->callback(status, NULL, query->context);
}

static void ib_sa_mcmember_rec_release(struct ib_sa_query *sa_query)
{
        kfree(container_of(sa_query, struct ib_sa_mcmember_query, sa_query));
}

int ib_sa_mcmember_rec_query(struct ib_sa_client *client,
                             struct ib_device *device, u32 port_num,
                             u8 method,
                             struct ib_sa_mcmember_rec *rec,
                             ib_sa_comp_mask comp_mask,
                             unsigned long timeout_ms, gfp_t gfp_mask,
                             void (*callback)(int status,
                                              struct ib_sa_mcmember_rec *resp,
                                              void *context),
                             void *context,
                             struct ib_sa_query **sa_query)
{
        struct ib_sa_mcmember_query *query;
        struct ib_sa_device *sa_dev = ib_get_client_data(device, &sa_client);
        struct ib_sa_port   *port;
        struct ib_mad_agent *agent;
        struct ib_sa_mad *mad;
        int ret;

        if (!sa_dev)
                return -ENODEV;

        port  = &sa_dev->port[port_num - sa_dev->start_port];
        agent = port->agent;

        query = kzalloc(sizeof(*query), gfp_mask);
        if (!query)
                return -ENOMEM;

        query->sa_query.port     = port;
        ret = alloc_mad(&query->sa_query, gfp_mask);
        if (ret)
                goto err1;

        ib_sa_client_get(client);
        query->sa_query.client = client;
        query->callback        = callback;
        query->context         = context;

        mad = query->sa_query.mad_buf->mad;
        init_mad(&query->sa_query, agent);

        query->sa_query.callback = callback ? ib_sa_mcmember_rec_callback : NULL;
        query->sa_query.release  = ib_sa_mcmember_rec_release;
        mad->mad_hdr.method         = method;
        mad->mad_hdr.attr_id         = cpu_to_be16(IB_SA_ATTR_MC_MEMBER_REC);
        mad->sa_hdr.comp_mask         = comp_mask;

        ib_pack(mcmember_rec_table, ARRAY_SIZE(mcmember_rec_table),
                rec, mad->data);

        *sa_query = &query->sa_query;

        ret = send_mad(&query->sa_query, timeout_ms, gfp_mask);
        if (ret < 0)
                goto err2;

        return ret;

err2:
        *sa_query = NULL;
        ib_sa_client_put(query->sa_query.client);
        free_mad(&query->sa_query);

err1:
        kfree(query);
        return ret;
}

/* Support GuidInfoRecord */
static void ib_sa_guidinfo_rec_callback(struct ib_sa_query *sa_query,
                                        int status, struct ib_sa_mad *mad)
{
        struct ib_sa_guidinfo_query *query =
                container_of(sa_query, struct ib_sa_guidinfo_query, sa_query);

        if (mad) {
                struct ib_sa_guidinfo_rec rec;

                ib_unpack(guidinfo_rec_table, ARRAY_SIZE(guidinfo_rec_table),
                          mad->data, &rec);
                query->callback(status, &rec, query->context);
        } else
                query->callback(status, NULL, query->context);
}

static void ib_sa_guidinfo_rec_release(struct ib_sa_query *sa_query)
{
        kfree(container_of(sa_query, struct ib_sa_guidinfo_query, sa_query));
}

int ib_sa_guid_info_rec_query(struct ib_sa_client *client,
                              struct ib_device *device, u32 port_num,
                              struct ib_sa_guidinfo_rec *rec,
                              ib_sa_comp_mask comp_mask, u8 method,
                              unsigned long timeout_ms, gfp_t gfp_mask,
                              void (*callback)(int status,
                                               struct ib_sa_guidinfo_rec *resp,
                                               void *context),
                              void *context,
                              struct ib_sa_query **sa_query)
{
        struct ib_sa_guidinfo_query *query;
        struct ib_sa_device *sa_dev = ib_get_client_data(device, &sa_client);
        struct ib_sa_port *port;
        struct ib_mad_agent *agent;
        struct ib_sa_mad *mad;
        int ret;

        if (!sa_dev)
                return -ENODEV;

        if (method != IB_MGMT_METHOD_GET &&
            method != IB_MGMT_METHOD_SET &&
            method != IB_SA_METHOD_DELETE) {
                return -EINVAL;
        }

        port  = &sa_dev->port[port_num - sa_dev->start_port];
        agent = port->agent;

        query = kzalloc(sizeof(*query), gfp_mask);
        if (!query)
                return -ENOMEM;

        query->sa_query.port = port;
        ret = alloc_mad(&query->sa_query, gfp_mask);
        if (ret)
                goto err1;

        ib_sa_client_get(client);
        query->sa_query.client = client;
        query->callback        = callback;
        query->context         = context;

        mad = query->sa_query.mad_buf->mad;
        init_mad(&query->sa_query, agent);

        query->sa_query.callback = callback ? ib_sa_guidinfo_rec_callback : NULL;
        query->sa_query.release  = ib_sa_guidinfo_rec_release;

        mad->mad_hdr.method         = method;
        mad->mad_hdr.attr_id         = cpu_to_be16(IB_SA_ATTR_GUID_INFO_REC);
        mad->sa_hdr.comp_mask         = comp_mask;

        ib_pack(guidinfo_rec_table, ARRAY_SIZE(guidinfo_rec_table), rec,
                mad->data);

        *sa_query = &query->sa_query;

        ret = send_mad(&query->sa_query, timeout_ms, gfp_mask);
        if (ret < 0)
                goto err2;

        return ret;

err2:
        *sa_query = NULL;
        ib_sa_client_put(query->sa_query.client);
        free_mad(&query->sa_query);

err1:
        kfree(query);
        return ret;
}
EXPORT_SYMBOL(ib_sa_guid_info_rec_query);

struct ib_classport_info_context {
        struct completion        done;
        struct ib_sa_query        *sa_query;
};

static void ib_classportinfo_cb(void *context)
{
        struct ib_classport_info_context *cb_ctx = context;

        complete(&cb_ctx->done);
}

static void ib_sa_classport_info_rec_callback(struct ib_sa_query *sa_query,
                                              int status, struct ib_sa_mad *mad)
{
        unsigned long flags;
        struct ib_sa_classport_info_query *query =
                container_of(sa_query, struct ib_sa_classport_info_query, sa_query);
        struct ib_sa_classport_cache *info = &sa_query->port->classport_info;

        if (mad) {
                if (sa_query->flags & IB_SA_QUERY_OPA) {
                        struct opa_class_port_info rec;

                        ib_unpack(opa_classport_info_rec_table,
                                  ARRAY_SIZE(opa_classport_info_rec_table),
                                  mad->data, &rec);

                        spin_lock_irqsave(&sa_query->port->classport_lock,
                                          flags);
                        if (!status && !info->valid) {
                                memcpy(&info->data.opa, &rec,
                                       sizeof(info->data.opa));

                                info->valid = true;
                                info->data.type = RDMA_CLASS_PORT_INFO_OPA;
                        }
                        spin_unlock_irqrestore(&sa_query->port->classport_lock,
                                               flags);

                } else {
                        struct ib_class_port_info rec;

                        ib_unpack(ib_classport_info_rec_table,
                                  ARRAY_SIZE(ib_classport_info_rec_table),
                                  mad->data, &rec);

                        spin_lock_irqsave(&sa_query->port->classport_lock,
                                          flags);
                        if (!status && !info->valid) {
                                memcpy(&info->data.ib, &rec,
                                       sizeof(info->data.ib));

                                info->valid = true;
                                info->data.type = RDMA_CLASS_PORT_INFO_IB;
                        }
                        spin_unlock_irqrestore(&sa_query->port->classport_lock,
                                               flags);
                }
        }
        query->callback(query->context);
}

static void ib_sa_classport_info_rec_release(struct ib_sa_query *sa_query)
{
        kfree(container_of(sa_query, struct ib_sa_classport_info_query,
                           sa_query));
}

static int ib_sa_classport_info_rec_query(struct ib_sa_port *port,
                                          unsigned long timeout_ms,
                                          void (*callback)(void *context),
                                          void *context,
                                          struct ib_sa_query **sa_query)
{
        struct ib_mad_agent *agent;
        struct ib_sa_classport_info_query *query;
        struct ib_sa_mad *mad;
        gfp_t gfp_mask = GFP_KERNEL;
        int ret;

        agent = port->agent;

        query = kzalloc(sizeof(*query), gfp_mask);
        if (!query)
                return -ENOMEM;

        query->sa_query.port = port;
        query->sa_query.flags |= rdma_cap_opa_ah(port->agent->device,
                                                 port->port_num) ?
                                 IB_SA_QUERY_OPA : 0;
        ret = alloc_mad(&query->sa_query, gfp_mask);
        if (ret)
                goto err_free;

        query->callback = callback;
        query->context = context;

        mad = query->sa_query.mad_buf->mad;
        init_mad(&query->sa_query, agent);

        query->sa_query.callback = ib_sa_classport_info_rec_callback;
        query->sa_query.release  = ib_sa_classport_info_rec_release;
        mad->mad_hdr.method         = IB_MGMT_METHOD_GET;
        mad->mad_hdr.attr_id         = cpu_to_be16(IB_SA_ATTR_CLASS_PORTINFO);
        mad->sa_hdr.comp_mask         = 0;
        *sa_query = &query->sa_query;

        ret = send_mad(&query->sa_query, timeout_ms, gfp_mask);
        if (ret < 0)
                goto err_free_mad;

        return ret;

err_free_mad:
        *sa_query = NULL;
        free_mad(&query->sa_query);

err_free:
        kfree(query);
        return ret;
}

static void update_ib_cpi(struct work_struct *work)
{
        struct ib_sa_port *port =
                container_of(work, struct ib_sa_port, ib_cpi_work.work);
        struct ib_classport_info_context *cb_context;
        unsigned long flags;
        int ret;

        /* If the classport info is valid, nothing
         * to do here.
         */
        spin_lock_irqsave(&port->classport_lock, flags);
        if (port->classport_info.valid) {
                spin_unlock_irqrestore(&port->classport_lock, flags);
                return;
        }
        spin_unlock_irqrestore(&port->classport_lock, flags);

        cb_context = kmalloc(sizeof(*cb_context), GFP_KERNEL);
        if (!cb_context)
                goto err_nomem;

        init_completion(&cb_context->done);

        ret = ib_sa_classport_info_rec_query(port, 3000,
                                             ib_classportinfo_cb, cb_context,
                                             &cb_context->sa_query);
        if (ret < 0)
                goto free_cb_err;
        wait_for_completion(&cb_context->done);
free_cb_err:
        kfree(cb_context);
        spin_lock_irqsave(&port->classport_lock, flags);

        /* If the classport info is still not valid, the query should have
         * failed for some reason. Retry issuing the query
         */
        if (!port->classport_info.valid) {
                port->classport_info.retry_cnt++;
                if (port->classport_info.retry_cnt <=
                    IB_SA_CPI_MAX_RETRY_CNT) {
                        unsigned long delay =
                                msecs_to_jiffies(IB_SA_CPI_RETRY_WAIT);

                        queue_delayed_work(ib_wq, &port->ib_cpi_work, delay);
                }
        }
        spin_unlock_irqrestore(&port->classport_lock, flags);

err_nomem:
        return;
}

static void send_handler(struct ib_mad_agent *agent,
                         struct ib_mad_send_wc *mad_send_wc)
{
        struct ib_sa_query *query = mad_send_wc->send_buf->context[0];
        unsigned long flags;

        if (query->callback)
                switch (mad_send_wc->status) {
                case IB_WC_SUCCESS:
                        /* No callback -- already got recv */
                        break;
                case IB_WC_RESP_TIMEOUT_ERR:
                        query->callback(query, -ETIMEDOUT, NULL);
                        break;
                case IB_WC_WR_FLUSH_ERR:
                        query->callback(query, -EINTR, NULL);
                        break;
                default:
                        query->callback(query, -EIO, NULL);
                        break;
                }

        xa_lock_irqsave(&queries, flags);
        __xa_erase(&queries, query->id);
        xa_unlock_irqrestore(&queries, flags);

        free_mad(query);
        if (query->client)
                ib_sa_client_put(query->client);
        query->release(query);
}

static void recv_handler(struct ib_mad_agent *mad_agent,
                         struct ib_mad_send_buf *send_buf,
                         struct ib_mad_recv_wc *mad_recv_wc)
{
        struct ib_sa_query *query;

        if (!send_buf)
                return;

        query = send_buf->context[0];
        if (query->callback) {
                if (mad_recv_wc->wc->status == IB_WC_SUCCESS)
                        query->callback(query,
                                        mad_recv_wc->recv_buf.mad->mad_hdr.status ?
                                        -EINVAL : 0,
                                        (struct ib_sa_mad *) mad_recv_wc->recv_buf.mad);
                else
                        query->callback(query, -EIO, NULL);
        }

        ib_free_recv_mad(mad_recv_wc);
}

static void update_sm_ah(struct work_struct *work)
{
        struct ib_sa_port *port =
                container_of(work, struct ib_sa_port, update_task);
        struct ib_sa_sm_ah *new_ah;
        struct ib_port_attr port_attr;
        struct rdma_ah_attr   ah_attr;
        bool grh_required;

        if (ib_query_port(port->agent->device, port->port_num, &port_attr)) {
                pr_warn("Couldn't query port\n");
                return;
        }

        new_ah = kmalloc(sizeof(*new_ah), GFP_KERNEL);
        if (!new_ah)
                return;

        kref_init(&new_ah->ref);
        new_ah->src_path_mask = (1 << port_attr.lmc) - 1;

        new_ah->pkey_index = 0;
        if (ib_find_pkey(port->agent->device, port->port_num,
                         IB_DEFAULT_PKEY_FULL, &new_ah->pkey_index))
                pr_err("Couldn't find index for default PKey\n");

        memset(&ah_attr, 0, sizeof(ah_attr));
        ah_attr.type = rdma_ah_find_type(port->agent->device,
                                         port->port_num);
        rdma_ah_set_dlid(&ah_attr, port_attr.sm_lid);
        rdma_ah_set_sl(&ah_attr, port_attr.sm_sl);
        rdma_ah_set_port_num(&ah_attr, port->port_num);

        grh_required = rdma_is_grh_required(port->agent->device,
                                            port->port_num);

        /*
         * The OPA sm_lid of 0xFFFF needs special handling so that it can be
         * differentiated from a permissive LID of 0xFFFF.  We set the
         * grh_required flag here so the SA can program the DGID in the
         * address handle appropriately
         */
        if (ah_attr.type == RDMA_AH_ATTR_TYPE_OPA &&
            (grh_required ||
             port_attr.sm_lid == be16_to_cpu(IB_LID_PERMISSIVE)))
                rdma_ah_set_make_grd(&ah_attr, true);

        if (ah_attr.type == RDMA_AH_ATTR_TYPE_IB && grh_required) {
                rdma_ah_set_ah_flags(&ah_attr, IB_AH_GRH);
                rdma_ah_set_subnet_prefix(&ah_attr,
                                          cpu_to_be64(port_attr.subnet_prefix));
                rdma_ah_set_interface_id(&ah_attr,
                                         cpu_to_be64(IB_SA_WELL_KNOWN_GUID));
        }

        new_ah->ah = rdma_create_ah(port->agent->qp->pd, &ah_attr,
                                    RDMA_CREATE_AH_SLEEPABLE);
        if (IS_ERR(new_ah->ah)) {
                pr_warn("Couldn't create new SM AH\n");
                kfree(new_ah);
                return;
        }

        spin_lock_irq(&port->ah_lock);
        if (port->sm_ah)
                kref_put(&port->sm_ah->ref, free_sm_ah);
        port->sm_ah = new_ah;
        spin_unlock_irq(&port->ah_lock);
}

static void ib_sa_event(struct ib_event_handler *handler,
                        struct ib_event *event)
{
        if (event->event == IB_EVENT_PORT_ERR    ||
            event->event == IB_EVENT_PORT_ACTIVE ||
            event->event == IB_EVENT_LID_CHANGE  ||
            event->event == IB_EVENT_PKEY_CHANGE ||
            event->event == IB_EVENT_SM_CHANGE   ||
            event->event == IB_EVENT_CLIENT_REREGISTER) {
                unsigned long flags;
                struct ib_sa_device *sa_dev =
                        container_of(handler, typeof(*sa_dev), event_handler);
                u32 port_num = event->element.port_num - sa_dev->start_port;
                struct ib_sa_port *port = &sa_dev->port[port_num];

                if (!rdma_cap_ib_sa(handler->device, port->port_num))
                        return;

                spin_lock_irqsave(&port->ah_lock, flags);
                if (port->sm_ah)
                        kref_put(&port->sm_ah->ref, free_sm_ah);
                port->sm_ah = NULL;
                spin_unlock_irqrestore(&port->ah_lock, flags);

                if (event->event == IB_EVENT_SM_CHANGE ||
                    event->event == IB_EVENT_CLIENT_REREGISTER ||
                    event->event == IB_EVENT_LID_CHANGE ||
                    event->event == IB_EVENT_PORT_ACTIVE) {
                        unsigned long delay =
                                msecs_to_jiffies(IB_SA_CPI_RETRY_WAIT);

                        spin_lock_irqsave(&port->classport_lock, flags);
                        port->classport_info.valid = false;
                        port->classport_info.retry_cnt = 0;
                        spin_unlock_irqrestore(&port->classport_lock, flags);
                        queue_delayed_work(ib_wq,
                                           &port->ib_cpi_work, delay);
                }
                queue_work(ib_wq, &sa_dev->port[port_num].update_task);
        }
}

static int ib_sa_add_one(struct ib_device *device)
{
        struct ib_sa_device *sa_dev;
        int s, e, i;
        int count = 0;
        int ret;

        s = rdma_start_port(device);
        e = rdma_end_port(device);

        sa_dev = kzalloc(struct_size(sa_dev, port,
                                     size_add(size_sub(e, s), 1)),
                         GFP_KERNEL);
        if (!sa_dev)
                return -ENOMEM;

        sa_dev->start_port = s;
        sa_dev->end_port   = e;

        for (i = 0; i <= e - s; ++i) {
                spin_lock_init(&sa_dev->port[i].ah_lock);
                if (!rdma_cap_ib_sa(device, i + 1))
                        continue;

                sa_dev->port[i].sm_ah    = NULL;
                sa_dev->port[i].port_num = i + s;

                spin_lock_init(&sa_dev->port[i].classport_lock);
                sa_dev->port[i].classport_info.valid = false;

                sa_dev->port[i].agent =
                        ib_register_mad_agent(device, i + s, IB_QPT_GSI,
                                              NULL, 0, send_handler,
                                              recv_handler, sa_dev, 0);
                if (IS_ERR(sa_dev->port[i].agent)) {
                        ret = PTR_ERR(sa_dev->port[i].agent);
                        goto err;
                }

                INIT_WORK(&sa_dev->port[i].update_task, update_sm_ah);
                INIT_DELAYED_WORK(&sa_dev->port[i].ib_cpi_work,
                                  update_ib_cpi);

                count++;
        }

        if (!count) {
                ret = -EOPNOTSUPP;
                goto free;
        }

        ib_set_client_data(device, &sa_client, sa_dev);

        /*
         * We register our event handler after everything is set up,
         * and then update our cached info after the event handler is
         * registered to avoid any problems if a port changes state
         * during our initialization.
         */

        INIT_IB_EVENT_HANDLER(&sa_dev->event_handler, device, ib_sa_event);
        ib_register_event_handler(&sa_dev->event_handler);

        for (i = 0; i <= e - s; ++i) {
                if (rdma_cap_ib_sa(device, i + 1))
                        update_sm_ah(&sa_dev->port[i].update_task);
        }

        return 0;

err:
        while (--i >= 0) {
                if (rdma_cap_ib_sa(device, i + 1))
                        ib_unregister_mad_agent(sa_dev->port[i].agent);
        }
free:
        kfree(sa_dev);
        return ret;
}

static void ib_sa_remove_one(struct ib_device *device, void *client_data)
{
        struct ib_sa_device *sa_dev = client_data;
        int i;

        ib_unregister_event_handler(&sa_dev->event_handler);
        flush_workqueue(ib_wq);

        for (i = 0; i <= sa_dev->end_port - sa_dev->start_port; ++i) {
                if (rdma_cap_ib_sa(device, i + 1)) {
                        cancel_delayed_work_sync(&sa_dev->port[i].ib_cpi_work);
                        ib_unregister_mad_agent(sa_dev->port[i].agent);
                        if (sa_dev->port[i].sm_ah)
                                kref_put(&sa_dev->port[i].sm_ah->ref, free_sm_ah);
                }

        }

        kfree(sa_dev);
}

int ib_sa_init(void)
{
        int ret;

        get_random_bytes(&tid, sizeof tid);

        atomic_set(&ib_nl_sa_request_seq, 0);

        ret = ib_register_client(&sa_client);
        if (ret) {
                pr_err("Couldn't register ib_sa client\n");
                goto err1;
        }

        ret = mcast_init();
        if (ret) {
                pr_err("Couldn't initialize multicast handling\n");
                goto err2;
        }

        ib_nl_wq = alloc_ordered_workqueue("ib_nl_sa_wq", WQ_MEM_RECLAIM);
        if (!ib_nl_wq) {
                ret = -ENOMEM;
                goto err3;
        }

        INIT_DELAYED_WORK(&ib_nl_timed_work, ib_nl_request_timeout);

        return 0;

err3:
        mcast_cleanup();
err2:
        ib_unregister_client(&sa_client);
err1:
        return ret;
}

void ib_sa_cleanup(void)
{
        cancel_delayed_work(&ib_nl_timed_work);
        destroy_workqueue(ib_nl_wq);
        mcast_cleanup();
        ib_unregister_client(&sa_client);
        WARN_ON(!xa_empty(&queries));
}






























































    5 

    1 

    4 







































    5 

    2 

    3 




    2 









    2 









    1 





    2 








    2 
















    1 
    6 

















































































    1 
















    6 


    7 




    1 


    1 





    1 
    2 












   10 









    6 

    4 







   10 























    4 





    5 






    5 





    5 




















    1 






    3 







    7 














    5 
    3 
    2 

    1 









    5 




    5 



    2 




    9 


    8 
    8 




    8 










    6 





    6 
    6 



    5 












   21 

















    1 





    1 


    2 








    1 






    7 








    6 
    3 




































    2 




    5 
    4 
    2 








    2 

    4 


    2 

    4 







    6 








    5 



   11 





   11 

   11 

   11 














    8 












    8 






    8 



    6 
    2 



    6 
    2 






    8 






















































































































































































































   27 


   27 






























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
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
// SPDX-License-Identifier: GPL-2.0-or-later
/*
 * net/sched/ife.c        Inter-FE action based on ForCES WG InterFE LFB
 *
 *                Refer to:
 *                draft-ietf-forces-interfelfb-03
 *                and
 *                netdev01 paper:
 *                "Distributing Linux Traffic Control Classifier-Action
 *                Subsystem"
 *                Authors: Jamal Hadi Salim and Damascene M. Joachimpillai
 *
 * copyright Jamal Hadi Salim (2015)
*/

#include <linux/types.h>
#include <linux/kernel.h>
#include <linux/string.h>
#include <linux/errno.h>
#include <linux/skbuff.h>
#include <linux/rtnetlink.h>
#include <linux/module.h>
#include <linux/init.h>
#include <net/net_namespace.h>
#include <net/netlink.h>
#include <net/pkt_sched.h>
#include <net/pkt_cls.h>
#include <uapi/linux/tc_act/tc_ife.h>
#include <net/tc_act/tc_ife.h>
#include <linux/etherdevice.h>
#include <net/ife.h>
#include <net/tc_wrapper.h>

static int max_metacnt = IFE_META_MAX + 1;
static struct tc_action_ops act_ife_ops;

static const struct nla_policy ife_policy[TCA_IFE_MAX + 1] = {
        [TCA_IFE_PARMS] = { .len = sizeof(struct tc_ife)},
        [TCA_IFE_DMAC] = { .len = ETH_ALEN},
        [TCA_IFE_SMAC] = { .len = ETH_ALEN},
        [TCA_IFE_TYPE] = { .type = NLA_U16},
};

int ife_encode_meta_u16(u16 metaval, void *skbdata, struct tcf_meta_info *mi)
{
        u16 edata = 0;

        if (mi->metaval)
                edata = *(u16 *)mi->metaval;
        else if (metaval)
                edata = metaval;

        if (!edata) /* will not encode */
                return 0;

        edata = htons(edata);
        return ife_tlv_meta_encode(skbdata, mi->metaid, 2, &edata);
}
EXPORT_SYMBOL_GPL(ife_encode_meta_u16);

int ife_get_meta_u32(struct sk_buff *skb, struct tcf_meta_info *mi)
{
        if (mi->metaval)
                return nla_put_u32(skb, mi->metaid, *(u32 *)mi->metaval);
        else
                return nla_put(skb, mi->metaid, 0, NULL);
}
EXPORT_SYMBOL_GPL(ife_get_meta_u32);

int ife_check_meta_u32(u32 metaval, struct tcf_meta_info *mi)
{
        if (metaval || mi->metaval)
                return 8; /* T+L+V == 2+2+4 */

        return 0;
}
EXPORT_SYMBOL_GPL(ife_check_meta_u32);

int ife_check_meta_u16(u16 metaval, struct tcf_meta_info *mi)
{
        if (metaval || mi->metaval)
                return 8; /* T+L+(V) == 2+2+(2+2bytepad) */

        return 0;
}
EXPORT_SYMBOL_GPL(ife_check_meta_u16);

int ife_encode_meta_u32(u32 metaval, void *skbdata, struct tcf_meta_info *mi)
{
        u32 edata = metaval;

        if (mi->metaval)
                edata = *(u32 *)mi->metaval;
        else if (metaval)
                edata = metaval;

        if (!edata) /* will not encode */
                return 0;

        edata = htonl(edata);
        return ife_tlv_meta_encode(skbdata, mi->metaid, 4, &edata);
}
EXPORT_SYMBOL_GPL(ife_encode_meta_u32);

int ife_get_meta_u16(struct sk_buff *skb, struct tcf_meta_info *mi)
{
        if (mi->metaval)
                return nla_put_u16(skb, mi->metaid, *(u16 *)mi->metaval);
        else
                return nla_put(skb, mi->metaid, 0, NULL);
}
EXPORT_SYMBOL_GPL(ife_get_meta_u16);

int ife_alloc_meta_u32(struct tcf_meta_info *mi, void *metaval, gfp_t gfp)
{
        mi->metaval = kmemdup(metaval, sizeof(u32), gfp);
        if (!mi->metaval)
                return -ENOMEM;

        return 0;
}
EXPORT_SYMBOL_GPL(ife_alloc_meta_u32);

int ife_alloc_meta_u16(struct tcf_meta_info *mi, void *metaval, gfp_t gfp)
{
        mi->metaval = kmemdup(metaval, sizeof(u16), gfp);
        if (!mi->metaval)
                return -ENOMEM;

        return 0;
}
EXPORT_SYMBOL_GPL(ife_alloc_meta_u16);

void ife_release_meta_gen(struct tcf_meta_info *mi)
{
        kfree(mi->metaval);
}
EXPORT_SYMBOL_GPL(ife_release_meta_gen);

int ife_validate_meta_u32(void *val, int len)
{
        if (len == sizeof(u32))
                return 0;

        return -EINVAL;
}
EXPORT_SYMBOL_GPL(ife_validate_meta_u32);

int ife_validate_meta_u16(void *val, int len)
{
        /* length will not include padding */
        if (len == sizeof(u16))
                return 0;

        return -EINVAL;
}
EXPORT_SYMBOL_GPL(ife_validate_meta_u16);

static LIST_HEAD(ifeoplist);
static DEFINE_RWLOCK(ife_mod_lock);

static struct tcf_meta_ops *find_ife_oplist(u16 metaid)
{
        struct tcf_meta_ops *o;

        read_lock(&ife_mod_lock);
        list_for_each_entry(o, &ifeoplist, list) {
                if (o->metaid == metaid) {
                        if (!try_module_get(o->owner))
                                o = NULL;
                        read_unlock(&ife_mod_lock);
                        return o;
                }
        }
        read_unlock(&ife_mod_lock);

        return NULL;
}

int register_ife_op(struct tcf_meta_ops *mops)
{
        struct tcf_meta_ops *m;

        if (!mops->metaid || !mops->metatype || !mops->name ||
            !mops->check_presence || !mops->encode || !mops->decode ||
            !mops->get || !mops->alloc)
                return -EINVAL;

        write_lock(&ife_mod_lock);

        list_for_each_entry(m, &ifeoplist, list) {
                if (m->metaid == mops->metaid ||
                    (strcmp(mops->name, m->name) == 0)) {
                        write_unlock(&ife_mod_lock);
                        return -EEXIST;
                }
        }

        if (!mops->release)
                mops->release = ife_release_meta_gen;

        list_add_tail(&mops->list, &ifeoplist);
        write_unlock(&ife_mod_lock);
        return 0;
}
EXPORT_SYMBOL_GPL(unregister_ife_op);

int unregister_ife_op(struct tcf_meta_ops *mops)
{
        struct tcf_meta_ops *m;
        int err = -ENOENT;

        write_lock(&ife_mod_lock);
        list_for_each_entry(m, &ifeoplist, list) {
                if (m->metaid == mops->metaid) {
                        list_del(&mops->list);
                        err = 0;
                        break;
                }
        }
        write_unlock(&ife_mod_lock);

        return err;
}
EXPORT_SYMBOL_GPL(register_ife_op);

static int ife_validate_metatype(struct tcf_meta_ops *ops, void *val, int len)
{
        int ret = 0;
        /* XXX: unfortunately cant use nla_policy at this point
        * because a length of 0 is valid in the case of
        * "allow". "use" semantics do enforce for proper
        * length and i couldve use nla_policy but it makes it hard
        * to use it just for that..
        */
        if (ops->validate)
                return ops->validate(val, len);

        if (ops->metatype == NLA_U32)
                ret = ife_validate_meta_u32(val, len);
        else if (ops->metatype == NLA_U16)
                ret = ife_validate_meta_u16(val, len);

        return ret;
}

#ifdef CONFIG_MODULES
static const char *ife_meta_id2name(u32 metaid)
{
        switch (metaid) {
        case IFE_META_SKBMARK:
                return "skbmark";
        case IFE_META_PRIO:
                return "skbprio";
        case IFE_META_TCINDEX:
                return "tcindex";
        default:
                return "unknown";
        }
}
#endif

/* called when adding new meta information
*/
static int load_metaops_and_vet(u32 metaid, void *val, int len, bool rtnl_held)
{
        struct tcf_meta_ops *ops = find_ife_oplist(metaid);
        int ret = 0;

        if (!ops) {
                ret = -ENOENT;
#ifdef CONFIG_MODULES
                if (rtnl_held)
                        rtnl_unlock();
                request_module("ife-meta-%s", ife_meta_id2name(metaid));
                if (rtnl_held)
                        rtnl_lock();
                ops = find_ife_oplist(metaid);
#endif
        }

        if (ops) {
                ret = 0;
                if (len)
                        ret = ife_validate_metatype(ops, val, len);

                module_put(ops->owner);
        }

        return ret;
}

/* called when adding new meta information
*/
static int __add_metainfo(const struct tcf_meta_ops *ops,
                          struct tcf_ife_info *ife, u32 metaid, void *metaval,
                          int len, bool atomic, bool exists)
{
        struct tcf_meta_info *mi = NULL;
        int ret = 0;

        mi = kzalloc(sizeof(*mi), atomic ? GFP_ATOMIC : GFP_KERNEL);
        if (!mi)
                return -ENOMEM;

        mi->metaid = metaid;
        mi->ops = ops;
        if (len > 0) {
                ret = ops->alloc(mi, metaval, atomic ? GFP_ATOMIC : GFP_KERNEL);
                if (ret != 0) {
                        kfree(mi);
                        return ret;
                }
        }

        if (exists)
                spin_lock_bh(&ife->tcf_lock);
        list_add_tail(&mi->metalist, &ife->metalist);
        if (exists)
                spin_unlock_bh(&ife->tcf_lock);

        return ret;
}

static int add_metainfo_and_get_ops(const struct tcf_meta_ops *ops,
                                    struct tcf_ife_info *ife, u32 metaid,
                                    bool exists)
{
        int ret;

        if (!try_module_get(ops->owner))
                return -ENOENT;
        ret = __add_metainfo(ops, ife, metaid, NULL, 0, true, exists);
        if (ret)
                module_put(ops->owner);
        return ret;
}

static int add_metainfo(struct tcf_ife_info *ife, u32 metaid, void *metaval,
                        int len, bool exists)
{
        const struct tcf_meta_ops *ops = find_ife_oplist(metaid);
        int ret;

        if (!ops)
                return -ENOENT;
        ret = __add_metainfo(ops, ife, metaid, metaval, len, false, exists);
        if (ret)
                /*put back what find_ife_oplist took */
                module_put(ops->owner);
        return ret;
}

static int use_all_metadata(struct tcf_ife_info *ife, bool exists)
{
        struct tcf_meta_ops *o;
        int rc = 0;
        int installed = 0;

        read_lock(&ife_mod_lock);
        list_for_each_entry(o, &ifeoplist, list) {
                rc = add_metainfo_and_get_ops(o, ife, o->metaid, exists);
                if (rc == 0)
                        installed += 1;
        }
        read_unlock(&ife_mod_lock);

        if (installed)
                return 0;
        else
                return -EINVAL;
}

static int dump_metalist(struct sk_buff *skb, struct tcf_ife_info *ife)
{
        struct tcf_meta_info *e;
        struct nlattr *nest;
        unsigned char *b = skb_tail_pointer(skb);
        int total_encoded = 0;

        /*can only happen on decode */
        if (list_empty(&ife->metalist))
                return 0;

        nest = nla_nest_start_noflag(skb, TCA_IFE_METALST);
        if (!nest)
                goto out_nlmsg_trim;

        list_for_each_entry(e, &ife->metalist, metalist) {
                if (!e->ops->get(skb, e))
                        total_encoded += 1;
        }

        if (!total_encoded)
                goto out_nlmsg_trim;

        nla_nest_end(skb, nest);

        return 0;

out_nlmsg_trim:
        nlmsg_trim(skb, b);
        return -1;
}

/* under ife->tcf_lock */
static void _tcf_ife_cleanup(struct tc_action *a)
{
        struct tcf_ife_info *ife = to_ife(a);
        struct tcf_meta_info *e, *n;

        list_for_each_entry_safe(e, n, &ife->metalist, metalist) {
                list_del(&e->metalist);
                if (e->metaval) {
                        if (e->ops->release)
                                e->ops->release(e);
                        else
                                kfree(e->metaval);
                }
                module_put(e->ops->owner);
                kfree(e);
        }
}

static void tcf_ife_cleanup(struct tc_action *a)
{
        struct tcf_ife_info *ife = to_ife(a);
        struct tcf_ife_params *p;

        spin_lock_bh(&ife->tcf_lock);
        _tcf_ife_cleanup(a);
        spin_unlock_bh(&ife->tcf_lock);

        p = rcu_dereference_protected(ife->params, 1);
        if (p)
                kfree_rcu(p, rcu);
}

static int load_metalist(struct nlattr **tb, bool rtnl_held)
{
        int i;

        for (i = 1; i < max_metacnt; i++) {
                if (tb[i]) {
                        void *val = nla_data(tb[i]);
                        int len = nla_len(tb[i]);
                        int rc;

                        rc = load_metaops_and_vet(i, val, len, rtnl_held);
                        if (rc != 0)
                                return rc;
                }
        }

        return 0;
}

static int populate_metalist(struct tcf_ife_info *ife, struct nlattr **tb,
                             bool exists, bool rtnl_held)
{
        int len = 0;
        int rc = 0;
        int i = 0;
        void *val;

        for (i = 1; i < max_metacnt; i++) {
                if (tb[i]) {
                        val = nla_data(tb[i]);
                        len = nla_len(tb[i]);

                        rc = add_metainfo(ife, i, val, len, exists);
                        if (rc)
                                return rc;
                }
        }

        return rc;
}

static int tcf_ife_init(struct net *net, struct nlattr *nla,
                        struct nlattr *est, struct tc_action **a,
                        struct tcf_proto *tp, u32 flags,
                        struct netlink_ext_ack *extack)
{
        struct tc_action_net *tn = net_generic(net, act_ife_ops.net_id);
        bool bind = flags & TCA_ACT_FLAGS_BIND;
        struct nlattr *tb[TCA_IFE_MAX + 1];
        struct nlattr *tb2[IFE_META_MAX + 1];
        struct tcf_chain *goto_ch = NULL;
        struct tcf_ife_params *p;
        struct tcf_ife_info *ife;
        u16 ife_type = ETH_P_IFE;
        struct tc_ife *parm;
        u8 *daddr = NULL;
        u8 *saddr = NULL;
        bool exists = false;
        int ret = 0;
        u32 index;
        int err;

        if (!nla) {
                NL_SET_ERR_MSG_MOD(extack, "IFE requires attributes to be passed");
                return -EINVAL;
        }

        err = nla_parse_nested_deprecated(tb, TCA_IFE_MAX, nla, ife_policy,
                                          NULL);
        if (err < 0)
                return err;

        if (!tb[TCA_IFE_PARMS])
                return -EINVAL;

        parm = nla_data(tb[TCA_IFE_PARMS]);

        /* IFE_DECODE is 0 and indicates the opposite of IFE_ENCODE because
         * they cannot run as the same time. Check on all other values which
         * are not supported right now.
         */
        if (parm->flags & ~IFE_ENCODE)
                return -EINVAL;

        p = kzalloc(sizeof(*p), GFP_KERNEL);
        if (!p)
                return -ENOMEM;

        if (tb[TCA_IFE_METALST]) {
                err = nla_parse_nested_deprecated(tb2, IFE_META_MAX,
                                                  tb[TCA_IFE_METALST], NULL,
                                                  NULL);
                if (err) {
                        kfree(p);
                        return err;
                }
                err = load_metalist(tb2, !(flags & TCA_ACT_FLAGS_NO_RTNL));
                if (err) {
                        kfree(p);
                        return err;
                }
        }

        index = parm->index;
        err = tcf_idr_check_alloc(tn, &index, a, bind);
        if (err < 0) {
                kfree(p);
                return err;
        }
        exists = err;
        if (exists && bind) {
                kfree(p);
                return ACT_P_BOUND;
        }

        if (!exists) {
                ret = tcf_idr_create(tn, index, est, a, &act_ife_ops,
                                     bind, true, flags);
                if (ret) {
                        tcf_idr_cleanup(tn, index);
                        kfree(p);
                        return ret;
                }
                ret = ACT_P_CREATED;
        } else if (!(flags & TCA_ACT_FLAGS_REPLACE)) {
                tcf_idr_release(*a, bind);
                kfree(p);
                return -EEXIST;
        }

        ife = to_ife(*a);
        if (ret == ACT_P_CREATED)
                INIT_LIST_HEAD(&ife->metalist);

        err = tcf_action_check_ctrlact(parm->action, tp, &goto_ch, extack);
        if (err < 0)
                goto release_idr;

        p->flags = parm->flags;

        if (parm->flags & IFE_ENCODE) {
                if (tb[TCA_IFE_TYPE])
                        ife_type = nla_get_u16(tb[TCA_IFE_TYPE]);
                if (tb[TCA_IFE_DMAC])
                        daddr = nla_data(tb[TCA_IFE_DMAC]);
                if (tb[TCA_IFE_SMAC])
                        saddr = nla_data(tb[TCA_IFE_SMAC]);
        }

        if (parm->flags & IFE_ENCODE) {
                if (daddr)
                        ether_addr_copy(p->eth_dst, daddr);
                else
                        eth_zero_addr(p->eth_dst);

                if (saddr)
                        ether_addr_copy(p->eth_src, saddr);
                else
                        eth_zero_addr(p->eth_src);

                p->eth_type = ife_type;
        }

        if (tb[TCA_IFE_METALST]) {
                err = populate_metalist(ife, tb2, exists,
                                        !(flags & TCA_ACT_FLAGS_NO_RTNL));
                if (err)
                        goto metadata_parse_err;
        } else {
                /* if no passed metadata allow list or passed allow-all
                 * then here we process by adding as many supported metadatum
                 * as we can. You better have at least one else we are
                 * going to bail out
                 */
                err = use_all_metadata(ife, exists);
                if (err)
                        goto metadata_parse_err;
        }

        if (exists)
                spin_lock_bh(&ife->tcf_lock);
        /* protected by tcf_lock when modifying existing action */
        goto_ch = tcf_action_set_ctrlact(*a, parm->action, goto_ch);
        p = rcu_replace_pointer(ife->params, p, 1);

        if (exists)
                spin_unlock_bh(&ife->tcf_lock);
        if (goto_ch)
                tcf_chain_put_by_act(goto_ch);
        if (p)
                kfree_rcu(p, rcu);

        return ret;
metadata_parse_err:
        if (goto_ch)
                tcf_chain_put_by_act(goto_ch);
release_idr:
        kfree(p);
        tcf_idr_release(*a, bind);
        return err;
}

static int tcf_ife_dump(struct sk_buff *skb, struct tc_action *a, int bind,
                        int ref)
{
        unsigned char *b = skb_tail_pointer(skb);
        struct tcf_ife_info *ife = to_ife(a);
        struct tcf_ife_params *p;
        struct tc_ife opt = {
                .index = ife->tcf_index,
                .refcnt = refcount_read(&ife->tcf_refcnt) - ref,
                .bindcnt = atomic_read(&ife->tcf_bindcnt) - bind,
        };
        struct tcf_t t;

        spin_lock_bh(&ife->tcf_lock);
        opt.action = ife->tcf_action;
        p = rcu_dereference_protected(ife->params,
                                      lockdep_is_held(&ife->tcf_lock));
        opt.flags = p->flags;

        if (nla_put(skb, TCA_IFE_PARMS, sizeof(opt), &opt))
                goto nla_put_failure;

        tcf_tm_dump(&t, &ife->tcf_tm);
        if (nla_put_64bit(skb, TCA_IFE_TM, sizeof(t), &t, TCA_IFE_PAD))
                goto nla_put_failure;

        if (!is_zero_ether_addr(p->eth_dst)) {
                if (nla_put(skb, TCA_IFE_DMAC, ETH_ALEN, p->eth_dst))
                        goto nla_put_failure;
        }

        if (!is_zero_ether_addr(p->eth_src)) {
                if (nla_put(skb, TCA_IFE_SMAC, ETH_ALEN, p->eth_src))
                        goto nla_put_failure;
        }

        if (nla_put(skb, TCA_IFE_TYPE, 2, &p->eth_type))
                goto nla_put_failure;

        if (dump_metalist(skb, ife)) {
                /*ignore failure to dump metalist */
                pr_info("Failed to dump metalist\n");
        }

        spin_unlock_bh(&ife->tcf_lock);
        return skb->len;

nla_put_failure:
        spin_unlock_bh(&ife->tcf_lock);
        nlmsg_trim(skb, b);
        return -1;
}

static int find_decode_metaid(struct sk_buff *skb, struct tcf_ife_info *ife,
                              u16 metaid, u16 mlen, void *mdata)
{
        struct tcf_meta_info *e;

        /* XXX: use hash to speed up */
        list_for_each_entry(e, &ife->metalist, metalist) {
                if (metaid == e->metaid) {
                        if (e->ops) {
                                /* We check for decode presence already */
                                return e->ops->decode(skb, mdata, mlen);
                        }
                }
        }

        return -ENOENT;
}

static int tcf_ife_decode(struct sk_buff *skb, const struct tc_action *a,
                          struct tcf_result *res)
{
        struct tcf_ife_info *ife = to_ife(a);
        int action = ife->tcf_action;
        u8 *ifehdr_end;
        u8 *tlv_data;
        u16 metalen;

        bstats_update(this_cpu_ptr(ife->common.cpu_bstats), skb);
        tcf_lastuse_update(&ife->tcf_tm);

        if (skb_at_tc_ingress(skb))
                skb_push(skb, skb->dev->hard_header_len);

        tlv_data = ife_decode(skb, &metalen);
        if (unlikely(!tlv_data)) {
                qstats_drop_inc(this_cpu_ptr(ife->common.cpu_qstats));
                return TC_ACT_SHOT;
        }

        ifehdr_end = tlv_data + metalen;
        for (; tlv_data < ifehdr_end; tlv_data = ife_tlv_meta_next(tlv_data)) {
                u8 *curr_data;
                u16 mtype;
                u16 dlen;

                curr_data = ife_tlv_meta_decode(tlv_data, ifehdr_end, &mtype,
                                                &dlen, NULL);
                if (!curr_data) {
                        qstats_drop_inc(this_cpu_ptr(ife->common.cpu_qstats));
                        return TC_ACT_SHOT;
                }

                if (find_decode_metaid(skb, ife, mtype, dlen, curr_data)) {
                        /* abuse overlimits to count when we receive metadata
                         * but dont have an ops for it
                         */
                        pr_info_ratelimited("Unknown metaid %d dlen %d\n",
                                            mtype, dlen);
                        qstats_overlimit_inc(this_cpu_ptr(ife->common.cpu_qstats));
                }
        }

        if (WARN_ON(tlv_data != ifehdr_end)) {
                qstats_drop_inc(this_cpu_ptr(ife->common.cpu_qstats));
                return TC_ACT_SHOT;
        }

        skb->protocol = eth_type_trans(skb, skb->dev);
        skb_reset_network_header(skb);

        return action;
}

/*XXX: check if we can do this at install time instead of current
 * send data path
**/
static int ife_get_sz(struct sk_buff *skb, struct tcf_ife_info *ife)
{
        struct tcf_meta_info *e, *n;
        int tot_run_sz = 0, run_sz = 0;

        list_for_each_entry_safe(e, n, &ife->metalist, metalist) {
                if (e->ops->check_presence) {
                        run_sz = e->ops->check_presence(skb, e);
                        tot_run_sz += run_sz;
                }
        }

        return tot_run_sz;
}

static int tcf_ife_encode(struct sk_buff *skb, const struct tc_action *a,
                          struct tcf_result *res, struct tcf_ife_params *p)
{
        struct tcf_ife_info *ife = to_ife(a);
        int action = ife->tcf_action;
        struct ethhdr *oethh;        /* outer ether header */
        struct tcf_meta_info *e;
        /*
           OUTERHDR:TOTMETALEN:{TLVHDR:Metadatum:TLVHDR..}:ORIGDATA
           where ORIGDATA = original ethernet header ...
         */
        u16 metalen = ife_get_sz(skb, ife);
        int hdrm = metalen + skb->dev->hard_header_len + IFE_METAHDRLEN;
        unsigned int skboff = 0;
        int new_len = skb->len + hdrm;
        bool exceed_mtu = false;
        void *ife_meta;
        int err = 0;

        if (!skb_at_tc_ingress(skb)) {
                if (new_len > skb->dev->mtu)
                        exceed_mtu = true;
        }

        bstats_update(this_cpu_ptr(ife->common.cpu_bstats), skb);
        tcf_lastuse_update(&ife->tcf_tm);

        if (!metalen) {                /* no metadata to send */
                /* abuse overlimits to count when we allow packet
                 * with no metadata
                 */
                qstats_overlimit_inc(this_cpu_ptr(ife->common.cpu_qstats));
                return action;
        }
        /* could be stupid policy setup or mtu config
         * so lets be conservative.. */
        if ((action == TC_ACT_SHOT) || exceed_mtu) {
                qstats_drop_inc(this_cpu_ptr(ife->common.cpu_qstats));
                return TC_ACT_SHOT;
        }

        if (skb_at_tc_ingress(skb))
                skb_push(skb, skb->dev->hard_header_len);

        ife_meta = ife_encode(skb, metalen);

        spin_lock(&ife->tcf_lock);

        /* XXX: we dont have a clever way of telling encode to
         * not repeat some of the computations that are done by
         * ops->presence_check...
         */
        list_for_each_entry(e, &ife->metalist, metalist) {
                if (e->ops->encode) {
                        err = e->ops->encode(skb, (void *)(ife_meta + skboff),
                                             e);
                }
                if (err < 0) {
                        /* too corrupt to keep around if overwritten */
                        spin_unlock(&ife->tcf_lock);
                        qstats_drop_inc(this_cpu_ptr(ife->common.cpu_qstats));
                        return TC_ACT_SHOT;
                }
                skboff += err;
        }
        spin_unlock(&ife->tcf_lock);
        oethh = (struct ethhdr *)skb->data;

        if (!is_zero_ether_addr(p->eth_src))
                ether_addr_copy(oethh->h_source, p->eth_src);
        if (!is_zero_ether_addr(p->eth_dst))
                ether_addr_copy(oethh->h_dest, p->eth_dst);
        oethh->h_proto = htons(p->eth_type);

        if (skb_at_tc_ingress(skb))
                skb_pull(skb, skb->dev->hard_header_len);

        return action;
}

TC_INDIRECT_SCOPE int tcf_ife_act(struct sk_buff *skb,
                                  const struct tc_action *a,
                                  struct tcf_result *res)
{
        struct tcf_ife_info *ife = to_ife(a);
        struct tcf_ife_params *p;
        int ret;

        p = rcu_dereference_bh(ife->params);
        if (p->flags & IFE_ENCODE) {
                ret = tcf_ife_encode(skb, a, res, p);
                return ret;
        }

        return tcf_ife_decode(skb, a, res);
}

static struct tc_action_ops act_ife_ops = {
        .kind = "ife",
        .id = TCA_ID_IFE,
        .owner = THIS_MODULE,
        .act = tcf_ife_act,
        .dump = tcf_ife_dump,
        .cleanup = tcf_ife_cleanup,
        .init = tcf_ife_init,
        .size =        sizeof(struct tcf_ife_info),
};
MODULE_ALIAS_NET_ACT("ife");

static __net_init int ife_init_net(struct net *net)
{
        struct tc_action_net *tn = net_generic(net, act_ife_ops.net_id);

        return tc_action_net_init(net, tn, &act_ife_ops);
}

static void __net_exit ife_exit_net(struct list_head *net_list)
{
        tc_action_net_exit(net_list, act_ife_ops.net_id);
}

static struct pernet_operations ife_net_ops = {
        .init = ife_init_net,
        .exit_batch = ife_exit_net,
        .id   = &act_ife_ops.net_id,
        .size = sizeof(struct tc_action_net),
};

static int __init ife_init_module(void)
{
        return tcf_register_action(&act_ife_ops, &ife_net_ops);
}

static void __exit ife_cleanup_module(void)
{
        tcf_unregister_action(&act_ife_ops, &ife_net_ops);
}

module_init(ife_init_module);
module_exit(ife_cleanup_module);

MODULE_AUTHOR("Jamal Hadi Salim(2015)");
MODULE_DESCRIPTION("Inter-FE LFB action");
MODULE_LICENSE("GPL");

























































































































  593 
  598 




    3 




    7 

































   12 
    3 










   17 




   16 
    9 





















   16 
   11 

   13 















   14 



   12 

    3 







    6 






    6 
    5 
    1 





    6 







   21 

















  530 



  530 
    4 
















    4 








    4 



    4 











  528 




 1710 



 1713 









  532 



















    6 












    4 














    2 




















   12 






   13 


   12 


   12 






    2 


    8 








    8 
    8 



































    4 





    4 


    1 


    3 



    1 



    1 
    1 































    4 






    4 

















   14 





    1 










    5 
    8 















   13 







   13 






   25 












    1 


    1 




   23 





   22 






   18 


    8 

    4 
    4 














    7 



    1 





    2 










    2 
















   15 








    1 
    4 







    3 















   37 





    1 


    1 



    6 









    1 



    5 












    6 









    1 



    2 





   14 





    5 






    3 


    3 







    1 















   24 











    2 












    1 












   24 







   23 

    2 






   23 



















    3 






















    3 



    3 











    3 

















    3 


































    6 




    1 




    5 




    2 






























































































































   26 










































































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
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
1187
1188
1189
1190
1191
1192
1193
1194
1195
1196
1197
1198
1199
1200
1201
1202
1203
1204
1205
1206
1207
1208
1209
1210
1211
1212
1213
1214
1215
1216
1217
1218
1219
1220
1221
// SPDX-License-Identifier: GPL-2.0-or-later
/** -*- linux-c -*- ***********************************************************
 * Linux PPP over Ethernet (PPPoX/PPPoE) Sockets
 *
 * PPPoX --- Generic PPP encapsulation socket family
 * PPPoE --- PPP over Ethernet (RFC 2516)
 *
 * Version:        0.7.0
 *
 * 070228 :        Fix to allow multiple sessions with same remote MAC and same
 *                session id by including the local device ifindex in the
 *                tuple identifying a session. This also ensures packets can't
 *                be injected into a session from interfaces other than the one
 *                specified by userspace. Florian Zumbiehl <florz@florz.de>
 *                (Oh, BTW, this one is YYMMDD, in case you were wondering ...)
 * 220102 :        Fix module use count on failure in pppoe_create, pppox_sk -acme
 * 030700 :        Fixed connect logic to allow for disconnect.
 * 270700 :        Fixed potential SMP problems; we must protect against
 *                simultaneous invocation of ppp_input
 *                and ppp_unregister_channel.
 * 040800 :        Respect reference count mechanisms on net-devices.
 * 200800 :        fix kfree(skb) in pppoe_rcv (acme)
 *                Module reference count is decremented in the right spot now,
 *                guards against sock_put not actually freeing the sk
 *                in pppoe_release.
 * 051000 :        Initialization cleanup.
 * 111100 :        Fix recvmsg.
 * 050101 :        Fix PADT processing.
 * 140501 :        Use pppoe_rcv_core to handle all backlog. (Alexey)
 * 170701 :        Do not lock_sock with rwlock held. (DaveM)
 *                Ignore discovery frames if user has socket
 *                locked. (DaveM)
 *                Ignore return value of dev_queue_xmit in __pppoe_xmit
 *                or else we may kfree an SKB twice. (DaveM)
 * 190701 :        When doing copies of skb's in __pppoe_xmit, always delete
 *                the original skb that was passed in on success, never on
 *                failure.  Delete the copy of the skb on failure to avoid
 *                a memory leak.
 * 081001 :        Misc. cleanup (licence string, non-blocking, prevent
 *                reference of device on close).
 * 121301 :        New ppp channels interface; cannot unregister a channel
 *                from interrupts.  Thus, we mark the socket as a ZOMBIE
 *                and do the unregistration later.
 * 081002 :        seq_file support for proc stuff -acme
 * 111602 :        Merge all 2.4 fixes into 2.5/2.6 tree.  Label 2.5/2.6
 *                as version 0.7.  Spacing cleanup.
 * Author:        Michal Ostrowski <mostrows@speakeasy.net>
 * Contributors:
 *                 Arnaldo Carvalho de Melo <acme@conectiva.com.br>
 *                David S. Miller (davem@redhat.com)
 *
 * License:
 */

#include <linux/string.h>
#include <linux/module.h>
#include <linux/kernel.h>
#include <linux/slab.h>
#include <linux/errno.h>
#include <linux/netdevice.h>
#include <linux/net.h>
#include <linux/inetdevice.h>
#include <linux/etherdevice.h>
#include <linux/skbuff.h>
#include <linux/init.h>
#include <linux/if_ether.h>
#include <linux/if_pppox.h>
#include <linux/ppp_channel.h>
#include <linux/ppp_defs.h>
#include <linux/ppp-ioctl.h>
#include <linux/notifier.h>
#include <linux/file.h>
#include <linux/proc_fs.h>
#include <linux/seq_file.h>

#include <linux/nsproxy.h>
#include <net/net_namespace.h>
#include <net/netns/generic.h>
#include <net/sock.h>

#include <linux/uaccess.h>

#define PPPOE_HASH_BITS CONFIG_PPPOE_HASH_BITS
#define PPPOE_HASH_SIZE (1 << PPPOE_HASH_BITS)
#define PPPOE_HASH_MASK        (PPPOE_HASH_SIZE - 1)

static int __pppoe_xmit(struct sock *sk, struct sk_buff *skb);

static const struct proto_ops pppoe_ops;
static const struct ppp_channel_ops pppoe_chan_ops;

/* per-net private data for this module */
static unsigned int pppoe_net_id __read_mostly;
struct pppoe_net {
        /*
         * we could use _single_ hash table for all
         * nets by injecting net id into the hash but
         * it would increase hash chains and add
         * a few additional math comparisons messy
         * as well, moreover in case of SMP less locking
         * controversy here
         */
        struct pppox_sock *hash_table[PPPOE_HASH_SIZE];
        rwlock_t hash_lock;
};

/*
 * PPPoE could be in the following stages:
 * 1) Discovery stage (to obtain remote MAC and Session ID)
 * 2) Session stage (MAC and SID are known)
 *
 * Ethernet frames have a special tag for this but
 * we use simpler approach based on session id
 */
static inline bool stage_session(__be16 sid)
{
        return sid != 0;
}

static inline struct pppoe_net *pppoe_pernet(struct net *net)
{
        return net_generic(net, pppoe_net_id);
}

static inline int cmp_2_addr(struct pppoe_addr *a, struct pppoe_addr *b)
{
        return a->sid == b->sid && ether_addr_equal(a->remote, b->remote);
}

static inline int cmp_addr(struct pppoe_addr *a, __be16 sid, char *addr)
{
        return a->sid == sid && ether_addr_equal(a->remote, addr);
}

#if 8 % PPPOE_HASH_BITS
#error 8 must be a multiple of PPPOE_HASH_BITS
#endif

static int hash_item(__be16 sid, unsigned char *addr)
{
        unsigned char hash = 0;
        unsigned int i;

        for (i = 0; i < ETH_ALEN; i++)
                hash ^= addr[i];
        for (i = 0; i < sizeof(sid_t) * 8; i += 8)
                hash ^= (__force __u32)sid >> i;
        for (i = 8; (i >>= 1) >= PPPOE_HASH_BITS;)
                hash ^= hash >> i;

        return hash & PPPOE_HASH_MASK;
}

/**********************************************************************
 *
 *  Set/get/delete/rehash items  (internal versions)
 *
 **********************************************************************/
static struct pppox_sock *__get_item(struct pppoe_net *pn, __be16 sid,
                                unsigned char *addr, int ifindex)
{
        int hash = hash_item(sid, addr);
        struct pppox_sock *ret;

        ret = pn->hash_table[hash];
        while (ret) {
                if (cmp_addr(&ret->pppoe_pa, sid, addr) &&
                    ret->pppoe_ifindex == ifindex)
                        return ret;

                ret = ret->next;
        }

        return NULL;
}

static int __set_item(struct pppoe_net *pn, struct pppox_sock *po)
{
        int hash = hash_item(po->pppoe_pa.sid, po->pppoe_pa.remote);
        struct pppox_sock *ret;

        ret = pn->hash_table[hash];
        while (ret) {
                if (cmp_2_addr(&ret->pppoe_pa, &po->pppoe_pa) &&
                    ret->pppoe_ifindex == po->pppoe_ifindex)
                        return -EALREADY;

                ret = ret->next;
        }

        po->next = pn->hash_table[hash];
        pn->hash_table[hash] = po;

        return 0;
}

static void __delete_item(struct pppoe_net *pn, __be16 sid,
                                        char *addr, int ifindex)
{
        int hash = hash_item(sid, addr);
        struct pppox_sock *ret, **src;

        ret = pn->hash_table[hash];
        src = &pn->hash_table[hash];

        while (ret) {
                if (cmp_addr(&ret->pppoe_pa, sid, addr) &&
                    ret->pppoe_ifindex == ifindex) {
                        *src = ret->next;
                        break;
                }

                src = &ret->next;
                ret = ret->next;
        }
}

/**********************************************************************
 *
 *  Set/get/delete/rehash items
 *
 **********************************************************************/
static inline struct pppox_sock *get_item(struct pppoe_net *pn, __be16 sid,
                                        unsigned char *addr, int ifindex)
{
        struct pppox_sock *po;

        read_lock_bh(&pn->hash_lock);
        po = __get_item(pn, sid, addr, ifindex);
        if (po)
                sock_hold(sk_pppox(po));
        read_unlock_bh(&pn->hash_lock);

        return po;
}

static inline struct pppox_sock *get_item_by_addr(struct net *net,
                                                struct sockaddr_pppox *sp)
{
        struct net_device *dev;
        struct pppoe_net *pn;
        struct pppox_sock *pppox_sock = NULL;

        int ifindex;

        rcu_read_lock();
        dev = dev_get_by_name_rcu(net, sp->sa_addr.pppoe.dev);
        if (dev) {
                ifindex = dev->ifindex;
                pn = pppoe_pernet(net);
                pppox_sock = get_item(pn, sp->sa_addr.pppoe.sid,
                                sp->sa_addr.pppoe.remote, ifindex);
        }
        rcu_read_unlock();
        return pppox_sock;
}

static inline void delete_item(struct pppoe_net *pn, __be16 sid,
                                        char *addr, int ifindex)
{
        write_lock_bh(&pn->hash_lock);
        __delete_item(pn, sid, addr, ifindex);
        write_unlock_bh(&pn->hash_lock);
}

/***************************************************************************
 *
 *  Handler for device events.
 *  Certain device events require that sockets be unconnected.
 *
 **************************************************************************/

static void pppoe_flush_dev(struct net_device *dev)
{
        struct pppoe_net *pn;
        int i;

        pn = pppoe_pernet(dev_net(dev));
        write_lock_bh(&pn->hash_lock);
        for (i = 0; i < PPPOE_HASH_SIZE; i++) {
                struct pppox_sock *po = pn->hash_table[i];
                struct sock *sk;

                while (po) {
                        while (po && po->pppoe_dev != dev) {
                                po = po->next;
                        }

                        if (!po)
                                break;

                        sk = sk_pppox(po);

                        /* We always grab the socket lock, followed by the
                         * hash_lock, in that order.  Since we should hold the
                         * sock lock while doing any unbinding, we need to
                         * release the lock we're holding.  Hold a reference to
                         * the sock so it doesn't disappear as we're jumping
                         * between locks.
                         */

                        sock_hold(sk);
                        write_unlock_bh(&pn->hash_lock);
                        lock_sock(sk);

                        if (po->pppoe_dev == dev &&
                            sk->sk_state & (PPPOX_CONNECTED | PPPOX_BOUND)) {
                                pppox_unbind_sock(sk);
                                sk->sk_state_change(sk);
                                po->pppoe_dev = NULL;
                                dev_put(dev);
                        }

                        release_sock(sk);
                        sock_put(sk);

                        /* Restart the process from the start of the current
                         * hash chain. We dropped locks so the world may have
                         * change from underneath us.
                         */

                        BUG_ON(pppoe_pernet(dev_net(dev)) == NULL);
                        write_lock_bh(&pn->hash_lock);
                        po = pn->hash_table[i];
                }
        }
        write_unlock_bh(&pn->hash_lock);
}

static int pppoe_device_event(struct notifier_block *this,
                              unsigned long event, void *ptr)
{
        struct net_device *dev = netdev_notifier_info_to_dev(ptr);

        /* Only look at sockets that are using this specific device. */
        switch (event) {
        case NETDEV_CHANGEADDR:
        case NETDEV_CHANGEMTU:
                /* A change in mtu or address is a bad thing, requiring
                 * LCP re-negotiation.
                 */

        case NETDEV_GOING_DOWN:
        case NETDEV_DOWN:
                /* Find every socket on this device and kill it. */
                pppoe_flush_dev(dev);
                break;

        default:
                break;
        }

        return NOTIFY_DONE;
}

static struct notifier_block pppoe_notifier = {
        .notifier_call = pppoe_device_event,
};

/************************************************************************
 *
 * Do the real work of receiving a PPPoE Session frame.
 *
 ***********************************************************************/
static int pppoe_rcv_core(struct sock *sk, struct sk_buff *skb)
{
        struct pppox_sock *po = pppox_sk(sk);
        struct pppox_sock *relay_po;

        /* Backlog receive. Semantics of backlog rcv preclude any code from
         * executing in lock_sock()/release_sock() bounds; meaning sk->sk_state
         * can't change.
         */

        if (skb->pkt_type == PACKET_OTHERHOST)
                goto abort_kfree;

        if (sk->sk_state & PPPOX_BOUND) {
                ppp_input(&po->chan, skb);
        } else if (sk->sk_state & PPPOX_RELAY) {
                relay_po = get_item_by_addr(sock_net(sk),
                                            &po->pppoe_relay);
                if (relay_po == NULL)
                        goto abort_kfree;

                if ((sk_pppox(relay_po)->sk_state & PPPOX_CONNECTED) == 0)
                        goto abort_put;

                if (!__pppoe_xmit(sk_pppox(relay_po), skb))
                        goto abort_put;

                sock_put(sk_pppox(relay_po));
        } else {
                if (sock_queue_rcv_skb(sk, skb))
                        goto abort_kfree;
        }

        return NET_RX_SUCCESS;

abort_put:
        sock_put(sk_pppox(relay_po));

abort_kfree:
        kfree_skb(skb);
        return NET_RX_DROP;
}

/************************************************************************
 *
 * Receive wrapper called in BH context.
 *
 ***********************************************************************/
static int pppoe_rcv(struct sk_buff *skb, struct net_device *dev,
                     struct packet_type *pt, struct net_device *orig_dev)
{
        struct pppoe_hdr *ph;
        struct pppox_sock *po;
        struct pppoe_net *pn;
        int len;

        skb = skb_share_check(skb, GFP_ATOMIC);
        if (!skb)
                goto out;

        if (skb_mac_header_len(skb) < ETH_HLEN)
                goto drop;

        if (!pskb_may_pull(skb, sizeof(struct pppoe_hdr)))
                goto drop;

        ph = pppoe_hdr(skb);
        len = ntohs(ph->length);

        skb_pull_rcsum(skb, sizeof(*ph));
        if (skb->len < len)
                goto drop;

        if (pskb_trim_rcsum(skb, len))
                goto drop;

        ph = pppoe_hdr(skb);
        pn = pppoe_pernet(dev_net(dev));

        /* Note that get_item does a sock_hold(), so sk_pppox(po)
         * is known to be safe.
         */
        po = get_item(pn, ph->sid, eth_hdr(skb)->h_source, dev->ifindex);
        if (!po)
                goto drop;

        return sk_receive_skb(sk_pppox(po), skb, 0);

drop:
        kfree_skb(skb);
out:
        return NET_RX_DROP;
}

static void pppoe_unbind_sock_work(struct work_struct *work)
{
        struct pppox_sock *po = container_of(work, struct pppox_sock,
                                             proto.pppoe.padt_work);
        struct sock *sk = sk_pppox(po);

        lock_sock(sk);
        if (po->pppoe_dev) {
                dev_put(po->pppoe_dev);
                po->pppoe_dev = NULL;
        }
        pppox_unbind_sock(sk);
        release_sock(sk);
        sock_put(sk);
}

/************************************************************************
 *
 * Receive a PPPoE Discovery frame.
 * This is solely for detection of PADT frames
 *
 ***********************************************************************/
static int pppoe_disc_rcv(struct sk_buff *skb, struct net_device *dev,
                          struct packet_type *pt, struct net_device *orig_dev)

{
        struct pppoe_hdr *ph;
        struct pppox_sock *po;
        struct pppoe_net *pn;

        skb = skb_share_check(skb, GFP_ATOMIC);
        if (!skb)
                goto out;

        if (skb->pkt_type != PACKET_HOST)
                goto abort;

        if (!pskb_may_pull(skb, sizeof(struct pppoe_hdr)))
                goto abort;

        ph = pppoe_hdr(skb);
        if (ph->code != PADT_CODE)
                goto abort;

        pn = pppoe_pernet(dev_net(dev));
        po = get_item(pn, ph->sid, eth_hdr(skb)->h_source, dev->ifindex);
        if (po)
                if (!schedule_work(&po->proto.pppoe.padt_work))
                        sock_put(sk_pppox(po));

abort:
        kfree_skb(skb);
out:
        return NET_RX_SUCCESS; /* Lies... :-) */
}

static struct packet_type pppoes_ptype __read_mostly = {
        .type        = cpu_to_be16(ETH_P_PPP_SES),
        .func        = pppoe_rcv,
};

static struct packet_type pppoed_ptype __read_mostly = {
        .type        = cpu_to_be16(ETH_P_PPP_DISC),
        .func        = pppoe_disc_rcv,
};

static struct proto pppoe_sk_proto __read_mostly = {
        .name          = "PPPOE",
        .owner          = THIS_MODULE,
        .obj_size = sizeof(struct pppox_sock),
};

/***********************************************************************
 *
 * Initialize a new struct sock.
 *
 **********************************************************************/
static int pppoe_create(struct net *net, struct socket *sock, int kern)
{
        struct sock *sk;

        sk = sk_alloc(net, PF_PPPOX, GFP_KERNEL, &pppoe_sk_proto, kern);
        if (!sk)
                return -ENOMEM;

        sock_init_data(sock, sk);

        sock->state        = SS_UNCONNECTED;
        sock->ops        = &pppoe_ops;

        sk->sk_backlog_rcv        = pppoe_rcv_core;
        sk->sk_state                = PPPOX_NONE;
        sk->sk_type                = SOCK_STREAM;
        sk->sk_family                = PF_PPPOX;
        sk->sk_protocol                = PX_PROTO_OE;

        INIT_WORK(&pppox_sk(sk)->proto.pppoe.padt_work,
                  pppoe_unbind_sock_work);

        return 0;
}

static int pppoe_release(struct socket *sock)
{
        struct sock *sk = sock->sk;
        struct pppox_sock *po;
        struct pppoe_net *pn;
        struct net *net = NULL;

        if (!sk)
                return 0;

        lock_sock(sk);
        if (sock_flag(sk, SOCK_DEAD)) {
                release_sock(sk);
                return -EBADF;
        }

        po = pppox_sk(sk);

        if (po->pppoe_dev) {
                dev_put(po->pppoe_dev);
                po->pppoe_dev = NULL;
        }

        pppox_unbind_sock(sk);

        /* Signal the death of the socket. */
        sk->sk_state = PPPOX_DEAD;

        net = sock_net(sk);
        pn = pppoe_pernet(net);

        /*
         * protect "po" from concurrent updates
         * on pppoe_flush_dev
         */
        delete_item(pn, po->pppoe_pa.sid, po->pppoe_pa.remote,
                    po->pppoe_ifindex);

        sock_orphan(sk);
        sock->sk = NULL;

        skb_queue_purge(&sk->sk_receive_queue);
        release_sock(sk);
        sock_put(sk);

        return 0;
}

static int pppoe_connect(struct socket *sock, struct sockaddr *uservaddr,
                  int sockaddr_len, int flags)
{
        struct sock *sk = sock->sk;
        struct sockaddr_pppox *sp = (struct sockaddr_pppox *)uservaddr;
        struct pppox_sock *po = pppox_sk(sk);
        struct net_device *dev = NULL;
        struct pppoe_net *pn;
        struct net *net = NULL;
        int error;

        lock_sock(sk);

        error = -EINVAL;

        if (sockaddr_len != sizeof(struct sockaddr_pppox))
                goto end;

        if (sp->sa_protocol != PX_PROTO_OE)
                goto end;

        /* Check for already bound sockets */
        error = -EBUSY;
        if ((sk->sk_state & PPPOX_CONNECTED) &&
             stage_session(sp->sa_addr.pppoe.sid))
                goto end;

        /* Check for already disconnected sockets, on attempts to disconnect */
        error = -EALREADY;
        if ((sk->sk_state & PPPOX_DEAD) &&
             !stage_session(sp->sa_addr.pppoe.sid))
                goto end;

        error = 0;

        /* Delete the old binding */
        if (stage_session(po->pppoe_pa.sid)) {
                pppox_unbind_sock(sk);
                pn = pppoe_pernet(sock_net(sk));
                delete_item(pn, po->pppoe_pa.sid,
                            po->pppoe_pa.remote, po->pppoe_ifindex);
                if (po->pppoe_dev) {
                        dev_put(po->pppoe_dev);
                        po->pppoe_dev = NULL;
                }

                po->pppoe_ifindex = 0;
                memset(&po->pppoe_pa, 0, sizeof(po->pppoe_pa));
                memset(&po->pppoe_relay, 0, sizeof(po->pppoe_relay));
                memset(&po->chan, 0, sizeof(po->chan));
                po->next = NULL;
                po->num = 0;

                sk->sk_state = PPPOX_NONE;
        }

        /* Re-bind in session stage only */
        if (stage_session(sp->sa_addr.pppoe.sid)) {
                error = -ENODEV;
                net = sock_net(sk);
                dev = dev_get_by_name(net, sp->sa_addr.pppoe.dev);
                if (!dev)
                        goto err_put;

                po->pppoe_dev = dev;
                po->pppoe_ifindex = dev->ifindex;
                pn = pppoe_pernet(net);
                if (!(dev->flags & IFF_UP)) {
                        goto err_put;
                }

                memcpy(&po->pppoe_pa,
                       &sp->sa_addr.pppoe,
                       sizeof(struct pppoe_addr));

                write_lock_bh(&pn->hash_lock);
                error = __set_item(pn, po);
                write_unlock_bh(&pn->hash_lock);
                if (error < 0)
                        goto err_put;

                po->chan.hdrlen = (sizeof(struct pppoe_hdr) +
                                   dev->hard_header_len);

                po->chan.mtu = dev->mtu - sizeof(struct pppoe_hdr) - 2;
                po->chan.private = sk;
                po->chan.ops = &pppoe_chan_ops;

                error = ppp_register_net_channel(dev_net(dev), &po->chan);
                if (error) {
                        delete_item(pn, po->pppoe_pa.sid,
                                    po->pppoe_pa.remote, po->pppoe_ifindex);
                        goto err_put;
                }

                sk->sk_state = PPPOX_CONNECTED;
        }

        po->num = sp->sa_addr.pppoe.sid;

end:
        release_sock(sk);
        return error;
err_put:
        if (po->pppoe_dev) {
                dev_put(po->pppoe_dev);
                po->pppoe_dev = NULL;
        }
        goto end;
}

static int pppoe_getname(struct socket *sock, struct sockaddr *uaddr,
                  int peer)
{
        int len = sizeof(struct sockaddr_pppox);
        struct sockaddr_pppox sp;

        sp.sa_family        = AF_PPPOX;
        sp.sa_protocol        = PX_PROTO_OE;
        memcpy(&sp.sa_addr.pppoe, &pppox_sk(sock->sk)->pppoe_pa,
               sizeof(struct pppoe_addr));

        memcpy(uaddr, &sp, len);

        return len;
}

static int pppoe_ioctl(struct socket *sock, unsigned int cmd,
                unsigned long arg)
{
        struct sock *sk = sock->sk;
        struct pppox_sock *po = pppox_sk(sk);
        int val;
        int err;

        switch (cmd) {
        case PPPIOCGMRU:
                err = -ENXIO;
                if (!(sk->sk_state & PPPOX_CONNECTED))
                        break;

                err = -EFAULT;
                if (put_user(po->pppoe_dev->mtu -
                             sizeof(struct pppoe_hdr) -
                             PPP_HDRLEN,
                             (int __user *)arg))
                        break;
                err = 0;
                break;

        case PPPIOCSMRU:
                err = -ENXIO;
                if (!(sk->sk_state & PPPOX_CONNECTED))
                        break;

                err = -EFAULT;
                if (get_user(val, (int __user *)arg))
                        break;

                if (val < (po->pppoe_dev->mtu
                           - sizeof(struct pppoe_hdr)
                           - PPP_HDRLEN))
                        err = 0;
                else
                        err = -EINVAL;
                break;

        case PPPIOCSFLAGS:
                err = -EFAULT;
                if (get_user(val, (int __user *)arg))
                        break;
                err = 0;
                break;

        case PPPOEIOCSFWD:
        {
                struct pppox_sock *relay_po;

                err = -EBUSY;
                if (sk->sk_state & (PPPOX_BOUND | PPPOX_DEAD))
                        break;

                err = -ENOTCONN;
                if (!(sk->sk_state & PPPOX_CONNECTED))
                        break;

                /* PPPoE address from the user specifies an outbound
                   PPPoE address which frames are forwarded to */
                err = -EFAULT;
                if (copy_from_user(&po->pppoe_relay,
                                   (void __user *)arg,
                                   sizeof(struct sockaddr_pppox)))
                        break;

                err = -EINVAL;
                if (po->pppoe_relay.sa_family != AF_PPPOX ||
                    po->pppoe_relay.sa_protocol != PX_PROTO_OE)
                        break;

                /* Check that the socket referenced by the address
                   actually exists. */
                relay_po = get_item_by_addr(sock_net(sk), &po->pppoe_relay);
                if (!relay_po)
                        break;

                sock_put(sk_pppox(relay_po));
                sk->sk_state |= PPPOX_RELAY;
                err = 0;
                break;
        }

        case PPPOEIOCDFWD:
                err = -EALREADY;
                if (!(sk->sk_state & PPPOX_RELAY))
                        break;

                sk->sk_state &= ~PPPOX_RELAY;
                err = 0;
                break;

        default:
                err = -ENOTTY;
        }

        return err;
}

static int pppoe_sendmsg(struct socket *sock, struct msghdr *m,
                         size_t total_len)
{
        struct sk_buff *skb;
        struct sock *sk = sock->sk;
        struct pppox_sock *po = pppox_sk(sk);
        int error;
        struct pppoe_hdr hdr;
        struct pppoe_hdr *ph;
        struct net_device *dev;
        char *start;
        int hlen;

        lock_sock(sk);
        if (sock_flag(sk, SOCK_DEAD) || !(sk->sk_state & PPPOX_CONNECTED)) {
                error = -ENOTCONN;
                goto end;
        }

        hdr.ver = 1;
        hdr.type = 1;
        hdr.code = 0;
        hdr.sid = po->num;

        dev = po->pppoe_dev;

        error = -EMSGSIZE;
        if (total_len > (dev->mtu + dev->hard_header_len))
                goto end;

        hlen = LL_RESERVED_SPACE(dev);
        skb = sock_wmalloc(sk, hlen + sizeof(*ph) + total_len +
                           dev->needed_tailroom, 0, GFP_KERNEL);
        if (!skb) {
                error = -ENOMEM;
                goto end;
        }

        /* Reserve space for headers. */
        skb_reserve(skb, hlen);
        skb_reset_network_header(skb);

        skb->dev = dev;

        skb->priority = READ_ONCE(sk->sk_priority);
        skb->protocol = cpu_to_be16(ETH_P_PPP_SES);

        ph = skb_put(skb, total_len + sizeof(struct pppoe_hdr));
        start = (char *)&ph->tag[0];

        error = memcpy_from_msg(start, m, total_len);
        if (error < 0) {
                kfree_skb(skb);
                goto end;
        }

        error = total_len;
        dev_hard_header(skb, dev, ETH_P_PPP_SES,
                        po->pppoe_pa.remote, NULL, total_len);

        memcpy(ph, &hdr, sizeof(struct pppoe_hdr));

        ph->length = htons(total_len);

        dev_queue_xmit(skb);

end:
        release_sock(sk);
        return error;
}

/************************************************************************
 *
 * xmit function for internal use.
 *
 ***********************************************************************/
static int __pppoe_xmit(struct sock *sk, struct sk_buff *skb)
{
        struct pppox_sock *po = pppox_sk(sk);
        struct net_device *dev = po->pppoe_dev;
        struct pppoe_hdr *ph;
        int data_len = skb->len;

        /* The higher-level PPP code (ppp_unregister_channel()) ensures the PPP
         * xmit operations conclude prior to an unregistration call.  Thus
         * sk->sk_state cannot change, so we don't need to do lock_sock().
         * But, we also can't do a lock_sock since that introduces a potential
         * deadlock as we'd reverse the lock ordering used when calling
         * ppp_unregister_channel().
         */

        if (sock_flag(sk, SOCK_DEAD) || !(sk->sk_state & PPPOX_CONNECTED))
                goto abort;

        if (!dev)
                goto abort;

        /* Copy the data if there is no space for the header or if it's
         * read-only.
         */
        if (skb_cow_head(skb, LL_RESERVED_SPACE(dev) + sizeof(*ph)))
                goto abort;

        __skb_push(skb, sizeof(*ph));
        skb_reset_network_header(skb);

        ph = pppoe_hdr(skb);
        ph->ver        = 1;
        ph->type = 1;
        ph->code = 0;
        ph->sid        = po->num;
        ph->length = htons(data_len);

        skb->protocol = cpu_to_be16(ETH_P_PPP_SES);
        skb->dev = dev;

        dev_hard_header(skb, dev, ETH_P_PPP_SES,
                        po->pppoe_pa.remote, NULL, data_len);

        dev_queue_xmit(skb);
        return 1;

abort:
        kfree_skb(skb);
        return 1;
}

/************************************************************************
 *
 * xmit function called by generic PPP driver
 * sends PPP frame over PPPoE socket
 *
 ***********************************************************************/
static int pppoe_xmit(struct ppp_channel *chan, struct sk_buff *skb)
{
        struct sock *sk = chan->private;
        return __pppoe_xmit(sk, skb);
}

static int pppoe_fill_forward_path(struct net_device_path_ctx *ctx,
                                   struct net_device_path *path,
                                   const struct ppp_channel *chan)
{
        struct sock *sk = chan->private;
        struct pppox_sock *po = pppox_sk(sk);
        struct net_device *dev = po->pppoe_dev;

        if (sock_flag(sk, SOCK_DEAD) ||
            !(sk->sk_state & PPPOX_CONNECTED) || !dev)
                return -1;

        path->type = DEV_PATH_PPPOE;
        path->encap.proto = htons(ETH_P_PPP_SES);
        path->encap.id = be16_to_cpu(po->num);
        memcpy(path->encap.h_dest, po->pppoe_pa.remote, ETH_ALEN);
        memcpy(ctx->daddr, po->pppoe_pa.remote, ETH_ALEN);
        path->dev = ctx->dev;
        ctx->dev = dev;

        return 0;
}

static const struct ppp_channel_ops pppoe_chan_ops = {
        .start_xmit = pppoe_xmit,
        .fill_forward_path = pppoe_fill_forward_path,
};

static int pppoe_recvmsg(struct socket *sock, struct msghdr *m,
                         size_t total_len, int flags)
{
        struct sock *sk = sock->sk;
        struct sk_buff *skb;
        int error = 0;

        if (sk->sk_state & PPPOX_BOUND)
                return -EIO;

        skb = skb_recv_datagram(sk, flags, &error);
        if (!skb)
                return error;

        total_len = min_t(size_t, total_len, skb->len);
        error = skb_copy_datagram_msg(skb, 0, m, total_len);
        if (error == 0) {
                consume_skb(skb);
                return total_len;
        }

        kfree_skb(skb);
        return error;
}

#ifdef CONFIG_PROC_FS
static int pppoe_seq_show(struct seq_file *seq, void *v)
{
        struct pppox_sock *po;
        char *dev_name;

        if (v == SEQ_START_TOKEN) {
                seq_puts(seq, "Id       Address              Device\n");
                goto out;
        }

        po = v;
        dev_name = po->pppoe_pa.dev;

        seq_printf(seq, "%08X %pM %8s\n",
                po->pppoe_pa.sid, po->pppoe_pa.remote, dev_name);
out:
        return 0;
}

static inline struct pppox_sock *pppoe_get_idx(struct pppoe_net *pn, loff_t pos)
{
        struct pppox_sock *po;
        int i;

        for (i = 0; i < PPPOE_HASH_SIZE; i++) {
                po = pn->hash_table[i];
                while (po) {
                        if (!pos--)
                                goto out;
                        po = po->next;
                }
        }

out:
        return po;
}

static void *pppoe_seq_start(struct seq_file *seq, loff_t *pos)
        __acquires(pn->hash_lock)
{
        struct pppoe_net *pn = pppoe_pernet(seq_file_net(seq));
        loff_t l = *pos;

        read_lock_bh(&pn->hash_lock);
        return l ? pppoe_get_idx(pn, --l) : SEQ_START_TOKEN;
}

static void *pppoe_seq_next(struct seq_file *seq, void *v, loff_t *pos)
{
        struct pppoe_net *pn = pppoe_pernet(seq_file_net(seq));
        struct pppox_sock *po;

        ++*pos;
        if (v == SEQ_START_TOKEN) {
                po = pppoe_get_idx(pn, 0);
                goto out;
        }
        po = v;
        if (po->next)
                po = po->next;
        else {
                int hash = hash_item(po->pppoe_pa.sid, po->pppoe_pa.remote);

                po = NULL;
                while (++hash < PPPOE_HASH_SIZE) {
                        po = pn->hash_table[hash];
                        if (po)
                                break;
                }
        }

out:
        return po;
}

static void pppoe_seq_stop(struct seq_file *seq, void *v)
        __releases(pn->hash_lock)
{
        struct pppoe_net *pn = pppoe_pernet(seq_file_net(seq));
        read_unlock_bh(&pn->hash_lock);
}

static const struct seq_operations pppoe_seq_ops = {
        .start                = pppoe_seq_start,
        .next                = pppoe_seq_next,
        .stop                = pppoe_seq_stop,
        .show                = pppoe_seq_show,
};
#endif /* CONFIG_PROC_FS */

static const struct proto_ops pppoe_ops = {
        .family                = AF_PPPOX,
        .owner                = THIS_MODULE,
        .release        = pppoe_release,
        .bind                = sock_no_bind,
        .connect        = pppoe_connect,
        .socketpair        = sock_no_socketpair,
        .accept                = sock_no_accept,
        .getname        = pppoe_getname,
        .poll                = datagram_poll,
        .listen                = sock_no_listen,
        .shutdown        = sock_no_shutdown,
        .sendmsg        = pppoe_sendmsg,
        .recvmsg        = pppoe_recvmsg,
        .mmap                = sock_no_mmap,
        .ioctl                = pppox_ioctl,
#ifdef CONFIG_COMPAT
        .compat_ioctl        = pppox_compat_ioctl,
#endif
};

static const struct pppox_proto pppoe_proto = {
        .create        = pppoe_create,
        .ioctl        = pppoe_ioctl,
        .owner        = THIS_MODULE,
};

static __net_init int pppoe_init_net(struct net *net)
{
        struct pppoe_net *pn = pppoe_pernet(net);
        struct proc_dir_entry *pde;

        rwlock_init(&pn->hash_lock);

        pde = proc_create_net("pppoe", 0444, net->proc_net,
                        &pppoe_seq_ops, sizeof(struct seq_net_private));
#ifdef CONFIG_PROC_FS
        if (!pde)
                return -ENOMEM;
#endif

        return 0;
}

static __net_exit void pppoe_exit_net(struct net *net)
{
        remove_proc_entry("pppoe", net->proc_net);
}

static struct pernet_operations pppoe_net_ops = {
        .init = pppoe_init_net,
        .exit = pppoe_exit_net,
        .id   = &pppoe_net_id,
        .size = sizeof(struct pppoe_net),
};

static int __init pppoe_init(void)
{
        int err;

        err = register_pernet_device(&pppoe_net_ops);
        if (err)
                goto out;

        err = proto_register(&pppoe_sk_proto, 0);
        if (err)
                goto out_unregister_net_ops;

        err = register_pppox_proto(PX_PROTO_OE, &pppoe_proto);
        if (err)
                goto out_unregister_pppoe_proto;

        dev_add_pack(&pppoes_ptype);
        dev_add_pack(&pppoed_ptype);
        register_netdevice_notifier(&pppoe_notifier);

        return 0;

out_unregister_pppoe_proto:
        proto_unregister(&pppoe_sk_proto);
out_unregister_net_ops:
        unregister_pernet_device(&pppoe_net_ops);
out:
        return err;
}

static void __exit pppoe_exit(void)
{
        unregister_netdevice_notifier(&pppoe_notifier);
        dev_remove_pack(&pppoed_ptype);
        dev_remove_pack(&pppoes_ptype);
        unregister_pppox_proto(PX_PROTO_OE);
        proto_unregister(&pppoe_sk_proto);
        unregister_pernet_device(&pppoe_net_ops);
}

module_init(pppoe_init);
module_exit(pppoe_exit);

MODULE_AUTHOR("Michal Ostrowski <mostrows@speakeasy.net>");
MODULE_DESCRIPTION("PPP over Ethernet driver");
MODULE_LICENSE("GPL");
MODULE_ALIAS_NET_PF_PROTO(PF_PPPOX, PX_PROTO_OE);































  184 
























  184 








  176 
























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
// SPDX-License-Identifier: LGPL-2.0+
/* Copyright (C) 1993, 1994, 1995, 1996, 1997 Free Software Foundation, Inc.
   This file is part of the GNU C Library.
   Contributed by Paul Eggert (eggert@twinsun.com). */

/*
 * dgb 10/02/98: ripped this from glibc source to help convert timestamps
 *               to unix time
 *     10/04/98: added new table-based lookup after seeing how ugly
 *               the gnu code is
 * blf 09/27/99: ripped out all the old code and inserted new table from
 *                 John Brockmeyer (without leap second corrections)
 *                 rewrote udf_stamp_to_time and fixed timezone accounting in
 *                 udf_time_to_stamp.
 */

/*
 * We don't take into account leap seconds. This may be correct or incorrect.
 * For more NIST information (especially dealing with leap seconds), see:
 * http://www.boulder.nist.gov/timefreq/pubs/bulletin/leapsecond.htm
 */

#include "udfdecl.h"

#include <linux/types.h>
#include <linux/kernel.h>
#include <linux/time.h>

void
udf_disk_stamp_to_time(struct timespec64 *dest, struct timestamp src)
{
        u16 typeAndTimezone = le16_to_cpu(src.typeAndTimezone);
        u16 year = le16_to_cpu(src.year);
        uint8_t type = typeAndTimezone >> 12;
        int16_t offset;

        if (type == 1) {
                offset = typeAndTimezone << 4;
                /* sign extent offset */
                offset = (offset >> 4);
                if (offset == -2047) /* unspecified offset */
                        offset = 0;
        } else
                offset = 0;

        dest->tv_sec = mktime64(year, src.month, src.day, src.hour, src.minute,
                        src.second);
        dest->tv_sec -= offset * 60;

        /*
         * Sanitize nanosecond field since reportedly some filesystems are
         * recorded with bogus sub-second values.
         */
        if (src.centiseconds < 100 && src.hundredsOfMicroseconds < 100 &&
            src.microseconds < 100) {
                dest->tv_nsec = 1000 * (src.centiseconds * 10000 +
                        src.hundredsOfMicroseconds * 100 + src.microseconds);
        } else {
                dest->tv_nsec = 0;
        }
}

void
udf_time_to_disk_stamp(struct timestamp *dest, struct timespec64 ts)
{
        time64_t seconds;
        int16_t offset;
        struct tm tm;

        offset = -sys_tz.tz_minuteswest;

        dest->typeAndTimezone = cpu_to_le16(0x1000 | (offset & 0x0FFF));

        seconds = ts.tv_sec + offset * 60;
        time64_to_tm(seconds, 0, &tm);
        dest->year = cpu_to_le16(tm.tm_year + 1900);
        dest->month = tm.tm_mon + 1;
        dest->day = tm.tm_mday;
        dest->hour = tm.tm_hour;
        dest->minute = tm.tm_min;
        dest->second = tm.tm_sec;
        dest->centiseconds = ts.tv_nsec / 10000000;
        dest->hundredsOfMicroseconds = (ts.tv_nsec / 1000 -
                                        dest->centiseconds * 10000) / 100;
        dest->microseconds = (ts.tv_nsec / 1000 - dest->centiseconds * 10000 -
                              dest->hundredsOfMicroseconds * 100);
}

/* EOF */











  143 






































  143 








































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
/* SPDX-License-Identifier: GPL-2.0 */
#undef TRACE_SYSTEM
#define TRACE_SYSTEM sctp

#if !defined(_TRACE_SCTP_H) || defined(TRACE_HEADER_MULTI_READ)
#define _TRACE_SCTP_H

#include <net/sctp/structs.h>
#include <linux/tracepoint.h>

TRACE_EVENT(sctp_probe_path,

        TP_PROTO(struct sctp_transport *sp,
                 const struct sctp_association *asoc),

        TP_ARGS(sp, asoc),

        TP_STRUCT__entry(
                __field(__u64, asoc)
                __field(__u32, primary)
                __array(__u8, ipaddr, sizeof(union sctp_addr))
                __field(__u32, state)
                __field(__u32, cwnd)
                __field(__u32, ssthresh)
                __field(__u32, flight_size)
                __field(__u32, partial_bytes_acked)
                __field(__u32, pathmtu)
        ),

        TP_fast_assign(
                __entry->asoc = (unsigned long)asoc;
                __entry->primary = (sp == asoc->peer.primary_path);
                memcpy(__entry->ipaddr, &sp->ipaddr, sizeof(union sctp_addr));
                __entry->state = sp->state;
                __entry->cwnd = sp->cwnd;
                __entry->ssthresh = sp->ssthresh;
                __entry->flight_size = sp->flight_size;
                __entry->partial_bytes_acked = sp->partial_bytes_acked;
                __entry->pathmtu = sp->pathmtu;
        ),

        TP_printk("asoc=%#llx%s ipaddr=%pISpc state=%u cwnd=%u ssthresh=%u "
                  "flight_size=%u partial_bytes_acked=%u pathmtu=%u",
                  __entry->asoc, __entry->primary ? "(*)" : "",
                  __entry->ipaddr, __entry->state, __entry->cwnd,
                  __entry->ssthresh, __entry->flight_size,
                  __entry->partial_bytes_acked, __entry->pathmtu)
);

TRACE_EVENT(sctp_probe,

        TP_PROTO(const struct sctp_endpoint *ep,
                 const struct sctp_association *asoc,
                 struct sctp_chunk *chunk),

        TP_ARGS(ep, asoc, chunk),

        TP_STRUCT__entry(
                __field(__u64, asoc)
                __field(__u32, mark)
                __field(__u16, bind_port)
                __field(__u16, peer_port)
                __field(__u32, pathmtu)
                __field(__u32, rwnd)
                __field(__u16, unack_data)
        ),

        TP_fast_assign(
                struct sk_buff *skb = chunk->skb;

                __entry->asoc = (unsigned long)asoc;
                __entry->mark = skb->mark;
                __entry->bind_port = ep->base.bind_addr.port;
                __entry->peer_port = asoc->peer.port;
                __entry->pathmtu = asoc->pathmtu;
                __entry->rwnd = asoc->peer.rwnd;
                __entry->unack_data = asoc->unack_data;
        ),

        TP_printk("asoc=%#llx mark=%#x bind_port=%d peer_port=%d pathmtu=%d "
                  "rwnd=%u unack_data=%d",
                  __entry->asoc, __entry->mark, __entry->bind_port,
                  __entry->peer_port, __entry->pathmtu, __entry->rwnd,
                  __entry->unack_data)
);

#endif /* _TRACE_SCTP_H */

/* This part must be outside protection */
#include <trace/define_trace.h>


























    2 


































































    2 





    2 









































































    2 



    2 

































    2 



    1 


    1 

















    1 



    1 



    1 




























































   24 










    1 



























   23 



   21 
    2 














   17 



   13 
    4 








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
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
// SPDX-License-Identifier: GPL-2.0-or-later
/*
 *  Force feedback support for Linux input subsystem
 *
 *  Copyright (c) 2006 Anssi Hannula <anssi.hannula@gmail.com>
 *  Copyright (c) 2006 Dmitry Torokhov <dtor@mail.ru>
 */

/* #define DEBUG */

#include <linux/input.h>
#include <linux/limits.h>
#include <linux/module.h>
#include <linux/mutex.h>
#include <linux/overflow.h>
#include <linux/sched.h>
#include <linux/slab.h>

/*
 * Check that the effect_id is a valid effect and whether the user
 * is the owner
 */
static int check_effect_access(struct ff_device *ff, int effect_id,
                                struct file *file)
{
        if (effect_id < 0 || effect_id >= ff->max_effects ||
            !ff->effect_owners[effect_id])
                return -EINVAL;

        if (file && ff->effect_owners[effect_id] != file)
                return -EACCES;

        return 0;
}

/*
 * Checks whether 2 effects can be combined together
 */
static inline int check_effects_compatible(struct ff_effect *e1,
                                           struct ff_effect *e2)
{
        return e1->type == e2->type &&
               (e1->type != FF_PERIODIC ||
                e1->u.periodic.waveform == e2->u.periodic.waveform);
}

/*
 * Convert an effect into compatible one
 */
static int compat_effect(struct ff_device *ff, struct ff_effect *effect)
{
        int magnitude;

        switch (effect->type) {
        case FF_RUMBLE:
                if (!test_bit(FF_PERIODIC, ff->ffbit))
                        return -EINVAL;

                /*
                 * calculate magnitude of sine wave as average of rumble's
                 * 2/3 of strong magnitude and 1/3 of weak magnitude
                 */
                magnitude = effect->u.rumble.strong_magnitude / 3 +
                            effect->u.rumble.weak_magnitude / 6;

                effect->type = FF_PERIODIC;
                effect->u.periodic.waveform = FF_SINE;
                effect->u.periodic.period = 50;
                effect->u.periodic.magnitude = magnitude;
                effect->u.periodic.offset = 0;
                effect->u.periodic.phase = 0;
                effect->u.periodic.envelope.attack_length = 0;
                effect->u.periodic.envelope.attack_level = 0;
                effect->u.periodic.envelope.fade_length = 0;
                effect->u.periodic.envelope.fade_level = 0;

                return 0;

        default:
                /* Let driver handle conversion */
                return 0;
        }
}

/**
 * input_ff_upload() - upload effect into force-feedback device
 * @dev: input device
 * @effect: effect to be uploaded
 * @file: owner of the effect
 */
int input_ff_upload(struct input_dev *dev, struct ff_effect *effect,
                    struct file *file)
{
        struct ff_device *ff = dev->ff;
        struct ff_effect *old;
        int ret = 0;
        int id;

        if (!test_bit(EV_FF, dev->evbit))
                return -ENOSYS;

        if (effect->type < FF_EFFECT_MIN || effect->type > FF_EFFECT_MAX ||
            !test_bit(effect->type, dev->ffbit)) {
                dev_dbg(&dev->dev, "invalid or not supported effect type in upload\n");
                return -EINVAL;
        }

        if (effect->type == FF_PERIODIC &&
            (effect->u.periodic.waveform < FF_WAVEFORM_MIN ||
             effect->u.periodic.waveform > FF_WAVEFORM_MAX ||
             !test_bit(effect->u.periodic.waveform, dev->ffbit))) {
                dev_dbg(&dev->dev, "invalid or not supported wave form in upload\n");
                return -EINVAL;
        }

        if (!test_bit(effect->type, ff->ffbit)) {
                ret = compat_effect(ff, effect);
                if (ret)
                        return ret;
        }

        mutex_lock(&ff->mutex);

        if (effect->id == -1) {
                for (id = 0; id < ff->max_effects; id++)
                        if (!ff->effect_owners[id])
                                break;

                if (id >= ff->max_effects) {
                        ret = -ENOSPC;
                        goto out;
                }

                effect->id = id;
                old = NULL;

        } else {
                id = effect->id;

                ret = check_effect_access(ff, id, file);
                if (ret)
                        goto out;

                old = &ff->effects[id];

                if (!check_effects_compatible(effect, old)) {
                        ret = -EINVAL;
                        goto out;
                }
        }

        ret = ff->upload(dev, effect, old);
        if (ret)
                goto out;

        spin_lock_irq(&dev->event_lock);
        ff->effects[id] = *effect;
        ff->effect_owners[id] = file;
        spin_unlock_irq(&dev->event_lock);

 out:
        mutex_unlock(&ff->mutex);
        return ret;
}
EXPORT_SYMBOL_GPL(input_ff_upload);

/*
 * Erases the effect if the requester is also the effect owner. The mutex
 * should already be locked before calling this function.
 */
static int erase_effect(struct input_dev *dev, int effect_id,
                        struct file *file)
{
        struct ff_device *ff = dev->ff;
        int error;

        error = check_effect_access(ff, effect_id, file);
        if (error)
                return error;

        spin_lock_irq(&dev->event_lock);
        ff->playback(dev, effect_id, 0);
        ff->effect_owners[effect_id] = NULL;
        spin_unlock_irq(&dev->event_lock);

        if (ff->erase) {
                error = ff->erase(dev, effect_id);
                if (error) {
                        spin_lock_irq(&dev->event_lock);
                        ff->effect_owners[effect_id] = file;
                        spin_unlock_irq(&dev->event_lock);

                        return error;
                }
        }

        return 0;
}

/**
 * input_ff_erase - erase a force-feedback effect from device
 * @dev: input device to erase effect from
 * @effect_id: id of the effect to be erased
 * @file: purported owner of the request
 *
 * This function erases a force-feedback effect from specified device.
 * The effect will only be erased if it was uploaded through the same
 * file handle that is requesting erase.
 */
int input_ff_erase(struct input_dev *dev, int effect_id, struct file *file)
{
        struct ff_device *ff = dev->ff;
        int ret;

        if (!test_bit(EV_FF, dev->evbit))
                return -ENOSYS;

        mutex_lock(&ff->mutex);
        ret = erase_effect(dev, effect_id, file);
        mutex_unlock(&ff->mutex);

        return ret;
}
EXPORT_SYMBOL_GPL(input_ff_erase);

/*
 * input_ff_flush - erase all effects owned by a file handle
 * @dev: input device to erase effect from
 * @file: purported owner of the effects
 *
 * This function erases all force-feedback effects associated with
 * the given owner from specified device. Note that @file may be %NULL,
 * in which case all effects will be erased.
 */
int input_ff_flush(struct input_dev *dev, struct file *file)
{
        struct ff_device *ff = dev->ff;
        int i;

        dev_dbg(&dev->dev, "flushing now\n");

        mutex_lock(&ff->mutex);

        for (i = 0; i < ff->max_effects; i++)
                erase_effect(dev, i, file);

        mutex_unlock(&ff->mutex);

        return 0;
}
EXPORT_SYMBOL_GPL(input_ff_flush);

/**
 * input_ff_event() - generic handler for force-feedback events
 * @dev: input device to send the effect to
 * @type: event type (anything but EV_FF is ignored)
 * @code: event code
 * @value: event value
 */
int input_ff_event(struct input_dev *dev, unsigned int type,
                   unsigned int code, int value)
{
        struct ff_device *ff = dev->ff;

        if (type != EV_FF)
                return 0;

        switch (code) {
        case FF_GAIN:
                if (!test_bit(FF_GAIN, dev->ffbit) || value > 0xffffU)
                        break;

                ff->set_gain(dev, value);
                break;

        case FF_AUTOCENTER:
                if (!test_bit(FF_AUTOCENTER, dev->ffbit) || value > 0xffffU)
                        break;

                ff->set_autocenter(dev, value);
                break;

        default:
                if (check_effect_access(ff, code, NULL) == 0)
                        ff->playback(dev, code, value);
                break;
        }

        return 0;
}
EXPORT_SYMBOL_GPL(input_ff_event);

/**
 * input_ff_create() - create force-feedback device
 * @dev: input device supporting force-feedback
 * @max_effects: maximum number of effects supported by the device
 *
 * This function allocates all necessary memory for a force feedback
 * portion of an input device and installs all default handlers.
 * @dev->ffbit should be already set up before calling this function.
 * Once ff device is created you need to setup its upload, erase,
 * playback and other handlers before registering input device
 */
int input_ff_create(struct input_dev *dev, unsigned int max_effects)
{
        struct ff_device *ff;
        size_t ff_dev_size;
        int i;

        if (!max_effects) {
                dev_err(&dev->dev, "cannot allocate device without any effects\n");
                return -EINVAL;
        }

        if (max_effects > FF_MAX_EFFECTS) {
                dev_err(&dev->dev, "cannot allocate more than FF_MAX_EFFECTS effects\n");
                return -EINVAL;
        }

        ff_dev_size = struct_size(ff, effect_owners, max_effects);
        if (ff_dev_size == SIZE_MAX) /* overflow */
                return -EINVAL;

        ff = kzalloc(ff_dev_size, GFP_KERNEL);
        if (!ff)
                return -ENOMEM;

        ff->effects = kcalloc(max_effects, sizeof(struct ff_effect),
                              GFP_KERNEL);
        if (!ff->effects) {
                kfree(ff);
                return -ENOMEM;
        }

        ff->max_effects = max_effects;
        mutex_init(&ff->mutex);

        dev->ff = ff;
        dev->flush = input_ff_flush;
        dev->event = input_ff_event;
        __set_bit(EV_FF, dev->evbit);

        /* Copy "true" bits into ff device bitmap */
        for_each_set_bit(i, dev->ffbit, FF_CNT)
                __set_bit(i, ff->ffbit);

        /* we can emulate RUMBLE with periodic effects */
        if (test_bit(FF_PERIODIC, ff->ffbit))
                __set_bit(FF_RUMBLE, dev->ffbit);

        return 0;
}
EXPORT_SYMBOL_GPL(input_ff_create);

/**
 * input_ff_destroy() - frees force feedback portion of input device
 * @dev: input device supporting force feedback
 *
 * This function is only needed in error path as input core will
 * automatically free force feedback structures when device is
 * destroyed.
 */
void input_ff_destroy(struct input_dev *dev)
{
        struct ff_device *ff = dev->ff;

        __clear_bit(EV_FF, dev->evbit);
        if (ff) {
                if (ff->destroy)
                        ff->destroy(ff);
                kfree(ff->private);
                kfree(ff->effects);
                kfree(ff);
                dev->ff = NULL;
        }
}
EXPORT_SYMBOL_GPL(input_ff_destroy);









































    7 




    1 




    6 




























































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
// SPDX-License-Identifier: GPL-2.0-only
/*
 *  ebt_mark
 *
 *        Authors:
 *        Bart De Schuymer <bdschuym@pandora.be>
 *
 *  July, 2002
 *
 */

/* The mark target can be used in any chain,
 * I believe adding a mangle table just for marking is total overkill.
 * Marking a frame doesn't really change anything in the frame anyway.
 */

#include <linux/module.h>
#include <linux/netfilter/x_tables.h>
#include <linux/netfilter_bridge/ebtables.h>
#include <linux/netfilter_bridge/ebt_mark_t.h>

static unsigned int
ebt_mark_tg(struct sk_buff *skb, const struct xt_action_param *par)
{
        const struct ebt_mark_t_info *info = par->targinfo;
        int action = info->target & -16;

        if (action == MARK_SET_VALUE)
                skb->mark = info->mark;
        else if (action == MARK_OR_VALUE)
                skb->mark |= info->mark;
        else if (action == MARK_AND_VALUE)
                skb->mark &= info->mark;
        else
                skb->mark ^= info->mark;

        return info->target | ~EBT_VERDICT_BITS;
}

static int ebt_mark_tg_check(const struct xt_tgchk_param *par)
{
        const struct ebt_mark_t_info *info = par->targinfo;
        int tmp;

        tmp = info->target | ~EBT_VERDICT_BITS;
        if (BASE_CHAIN && tmp == EBT_RETURN)
                return -EINVAL;
        if (ebt_invalid_target(tmp))
                return -EINVAL;
        tmp = info->target & ~EBT_VERDICT_BITS;
        if (tmp != MARK_SET_VALUE && tmp != MARK_OR_VALUE &&
            tmp != MARK_AND_VALUE && tmp != MARK_XOR_VALUE)
                return -EINVAL;
        return 0;
}
#ifdef CONFIG_NETFILTER_XTABLES_COMPAT
struct compat_ebt_mark_t_info {
        compat_ulong_t mark;
        compat_uint_t target;
};

static void mark_tg_compat_from_user(void *dst, const void *src)
{
        const struct compat_ebt_mark_t_info *user = src;
        struct ebt_mark_t_info *kern = dst;

        kern->mark = user->mark;
        kern->target = user->target;
}

static int mark_tg_compat_to_user(void __user *dst, const void *src)
{
        struct compat_ebt_mark_t_info __user *user = dst;
        const struct ebt_mark_t_info *kern = src;

        if (put_user(kern->mark, &user->mark) ||
            put_user(kern->target, &user->target))
                return -EFAULT;
        return 0;
}
#endif

static struct xt_target ebt_mark_tg_reg __read_mostly = {
        .name                = "mark",
        .revision        = 0,
        .family                = NFPROTO_BRIDGE,
        .target                = ebt_mark_tg,
        .checkentry        = ebt_mark_tg_check,
        .targetsize        = sizeof(struct ebt_mark_t_info),
#ifdef CONFIG_NETFILTER_XTABLES_COMPAT
        .compatsize        = sizeof(struct compat_ebt_mark_t_info),
        .compat_from_user = mark_tg_compat_from_user,
        .compat_to_user        = mark_tg_compat_to_user,
#endif
        .me                = THIS_MODULE,
};

static int __init ebt_mark_init(void)
{
        return xt_register_target(&ebt_mark_tg_reg);
}

static void __exit ebt_mark_fini(void)
{
        xt_unregister_target(&ebt_mark_tg_reg);
}

module_init(ebt_mark_init);
module_exit(ebt_mark_fini);
MODULE_DESCRIPTION("Ebtables: Packet mark modification");
MODULE_LICENSE("GPL");
































































  167 


    6 








  173 




  173 

    2 
  167 






  166 



  166 








  166 




    1 







    3 














































  163 
  163 
    1 




  162 





  161 




















   79 


   79 




















   74 
    4 



























































  128 














  128 




  180 



  180 











  168 
   24 



  132 


  132 

    6 

  130 





  224 







  224 







  221 















  163 



  221 



  102 

  163 



















   44 
   44 




    5 






    5 











































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
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
// SPDX-License-Identifier: GPL-2.0-only
/*
 *        vfsv0 quota IO operations on file
 */

#include <linux/errno.h>
#include <linux/fs.h>
#include <linux/mount.h>
#include <linux/dqblk_v2.h>
#include <linux/kernel.h>
#include <linux/init.h>
#include <linux/module.h>
#include <linux/slab.h>
#include <linux/quotaops.h>

#include <asm/byteorder.h>

#include "quota_tree.h"
#include "quotaio_v2.h"

MODULE_AUTHOR("Jan Kara");
MODULE_DESCRIPTION("Quota format v2 support");
MODULE_LICENSE("GPL");

static void v2r0_mem2diskdqb(void *dp, struct dquot *dquot);
static void v2r0_disk2memdqb(struct dquot *dquot, void *dp);
static int v2r0_is_id(void *dp, struct dquot *dquot);
static void v2r1_mem2diskdqb(void *dp, struct dquot *dquot);
static void v2r1_disk2memdqb(struct dquot *dquot, void *dp);
static int v2r1_is_id(void *dp, struct dquot *dquot);

static const struct qtree_fmt_operations v2r0_qtree_ops = {
        .mem2disk_dqblk = v2r0_mem2diskdqb,
        .disk2mem_dqblk = v2r0_disk2memdqb,
        .is_id = v2r0_is_id,
};

static const struct qtree_fmt_operations v2r1_qtree_ops = {
        .mem2disk_dqblk = v2r1_mem2diskdqb,
        .disk2mem_dqblk = v2r1_disk2memdqb,
        .is_id = v2r1_is_id,
};

#define QUOTABLOCK_BITS 10
#define QUOTABLOCK_SIZE (1 << QUOTABLOCK_BITS)

static inline qsize_t v2_stoqb(qsize_t space)
{
        return (space + QUOTABLOCK_SIZE - 1) >> QUOTABLOCK_BITS;
}

static inline qsize_t v2_qbtos(qsize_t blocks)
{
        return blocks << QUOTABLOCK_BITS;
}

static int v2_read_header(struct super_block *sb, int type,
                          struct v2_disk_dqheader *dqhead)
{
        ssize_t size;

        size = sb->s_op->quota_read(sb, type, (char *)dqhead,
                                    sizeof(struct v2_disk_dqheader), 0);
        if (size != sizeof(struct v2_disk_dqheader)) {
                quota_error(sb, "Failed header read: expected=%zd got=%zd",
                            sizeof(struct v2_disk_dqheader), size);
                if (size < 0)
                        return size;
                return -EIO;
        }
        return 0;
}

/* Check whether given file is really vfsv0 quotafile */
static int v2_check_quota_file(struct super_block *sb, int type)
{
        struct v2_disk_dqheader dqhead;
        static const uint quota_magics[] = V2_INITQMAGICS;
        static const uint quota_versions[] = V2_INITQVERSIONS;

        if (v2_read_header(sb, type, &dqhead))
                return 0;
        if (le32_to_cpu(dqhead.dqh_magic) != quota_magics[type] ||
            le32_to_cpu(dqhead.dqh_version) > quota_versions[type])
                return 0;
        return 1;
}

/* Read information header from quota file */
static int v2_read_file_info(struct super_block *sb, int type)
{
        struct v2_disk_dqinfo dinfo;
        struct v2_disk_dqheader dqhead;
        struct quota_info *dqopt = sb_dqopt(sb);
        struct mem_dqinfo *info = &dqopt->info[type];
        struct qtree_mem_dqinfo *qinfo;
        ssize_t size;
        unsigned int version;
        unsigned int memalloc;
        int ret;

        down_read(&dqopt->dqio_sem);
        memalloc = memalloc_nofs_save();
        ret = v2_read_header(sb, type, &dqhead);
        if (ret < 0)
                goto out;
        version = le32_to_cpu(dqhead.dqh_version);
        if ((info->dqi_fmt_id == QFMT_VFS_V0 && version != 0) ||
            (info->dqi_fmt_id == QFMT_VFS_V1 && version != 1)) {
                ret = -EINVAL;
                goto out;
        }

        size = sb->s_op->quota_read(sb, type, (char *)&dinfo,
               sizeof(struct v2_disk_dqinfo), V2_DQINFOOFF);
        if (size != sizeof(struct v2_disk_dqinfo)) {
                quota_error(sb, "Can't read info structure");
                if (size < 0)
                        ret = size;
                else
                        ret = -EIO;
                goto out;
        }
        info->dqi_priv = kmalloc(sizeof(struct qtree_mem_dqinfo), GFP_KERNEL);
        if (!info->dqi_priv) {
                ret = -ENOMEM;
                goto out;
        }
        qinfo = info->dqi_priv;
        if (version == 0) {
                /* limits are stored as unsigned 32-bit data */
                info->dqi_max_spc_limit = 0xffffffffLL << QUOTABLOCK_BITS;
                info->dqi_max_ino_limit = 0xffffffff;
        } else {
                /*
                 * Used space is stored as unsigned 64-bit value in bytes but
                 * quota core supports only signed 64-bit values so use that
                 * as a limit
                 */
                info->dqi_max_spc_limit = 0x7fffffffffffffffLL; /* 2^63-1 */
                info->dqi_max_ino_limit = 0x7fffffffffffffffLL;
        }
        info->dqi_bgrace = le32_to_cpu(dinfo.dqi_bgrace);
        info->dqi_igrace = le32_to_cpu(dinfo.dqi_igrace);
        /* No flags currently supported */
        info->dqi_flags = 0;
        qinfo->dqi_sb = sb;
        qinfo->dqi_type = type;
        qinfo->dqi_blocks = le32_to_cpu(dinfo.dqi_blocks);
        qinfo->dqi_free_blk = le32_to_cpu(dinfo.dqi_free_blk);
        qinfo->dqi_free_entry = le32_to_cpu(dinfo.dqi_free_entry);
        qinfo->dqi_blocksize_bits = V2_DQBLKSIZE_BITS;
        qinfo->dqi_usable_bs = 1 << V2_DQBLKSIZE_BITS;
        qinfo->dqi_qtree_depth = qtree_depth(qinfo);
        if (version == 0) {
                qinfo->dqi_entry_size = sizeof(struct v2r0_disk_dqblk);
                qinfo->dqi_ops = &v2r0_qtree_ops;
        } else {
                qinfo->dqi_entry_size = sizeof(struct v2r1_disk_dqblk);
                qinfo->dqi_ops = &v2r1_qtree_ops;
        }
        ret = -EUCLEAN;
        /* Some sanity checks of the read headers... */
        if ((loff_t)qinfo->dqi_blocks << qinfo->dqi_blocksize_bits >
            i_size_read(sb_dqopt(sb)->files[type])) {
                quota_error(sb, "Number of blocks too big for quota file size (%llu > %llu).",
                    (loff_t)qinfo->dqi_blocks << qinfo->dqi_blocksize_bits,
                    i_size_read(sb_dqopt(sb)->files[type]));
                goto out_free;
        }
        if (qinfo->dqi_free_blk && (qinfo->dqi_free_blk <= QT_TREEOFF ||
            qinfo->dqi_free_blk >= qinfo->dqi_blocks)) {
                quota_error(sb, "Free block number %u out of range (%u, %u).",
                            qinfo->dqi_free_blk, QT_TREEOFF, qinfo->dqi_blocks);
                goto out_free;
        }
        if (qinfo->dqi_free_entry && (qinfo->dqi_free_entry <= QT_TREEOFF ||
            qinfo->dqi_free_entry >= qinfo->dqi_blocks)) {
                quota_error(sb, "Block with free entry %u out of range (%u, %u).",
                            qinfo->dqi_free_entry, QT_TREEOFF,
                            qinfo->dqi_blocks);
                goto out_free;
        }
        ret = 0;
out_free:
        if (ret) {
                kfree(info->dqi_priv);
                info->dqi_priv = NULL;
        }
out:
        memalloc_nofs_restore(memalloc);
        up_read(&dqopt->dqio_sem);
        return ret;
}

/* Write information header to quota file */
static int v2_write_file_info(struct super_block *sb, int type)
{
        struct v2_disk_dqinfo dinfo;
        struct quota_info *dqopt = sb_dqopt(sb);
        struct mem_dqinfo *info = &dqopt->info[type];
        struct qtree_mem_dqinfo *qinfo = info->dqi_priv;
        ssize_t size;
        unsigned int memalloc;

        down_write(&dqopt->dqio_sem);
        memalloc = memalloc_nofs_save();
        spin_lock(&dq_data_lock);
        info->dqi_flags &= ~DQF_INFO_DIRTY;
        dinfo.dqi_bgrace = cpu_to_le32(info->dqi_bgrace);
        dinfo.dqi_igrace = cpu_to_le32(info->dqi_igrace);
        /* No flags currently supported */
        dinfo.dqi_flags = cpu_to_le32(0);
        spin_unlock(&dq_data_lock);
        dinfo.dqi_blocks = cpu_to_le32(qinfo->dqi_blocks);
        dinfo.dqi_free_blk = cpu_to_le32(qinfo->dqi_free_blk);
        dinfo.dqi_free_entry = cpu_to_le32(qinfo->dqi_free_entry);
        size = sb->s_op->quota_write(sb, type, (char *)&dinfo,
               sizeof(struct v2_disk_dqinfo), V2_DQINFOOFF);
        memalloc_nofs_restore(memalloc);
        up_write(&dqopt->dqio_sem);
        if (size != sizeof(struct v2_disk_dqinfo)) {
                quota_error(sb, "Can't write info structure");
                return size < 0 ? size : -EIO;
        }
        return 0;
}

static void v2r0_disk2memdqb(struct dquot *dquot, void *dp)
{
        struct v2r0_disk_dqblk *d = dp, empty;
        struct mem_dqblk *m = &dquot->dq_dqb;

        m->dqb_ihardlimit = le32_to_cpu(d->dqb_ihardlimit);
        m->dqb_isoftlimit = le32_to_cpu(d->dqb_isoftlimit);
        m->dqb_curinodes = le32_to_cpu(d->dqb_curinodes);
        m->dqb_itime = le64_to_cpu(d->dqb_itime);
        m->dqb_bhardlimit = v2_qbtos(le32_to_cpu(d->dqb_bhardlimit));
        m->dqb_bsoftlimit = v2_qbtos(le32_to_cpu(d->dqb_bsoftlimit));
        m->dqb_curspace = le64_to_cpu(d->dqb_curspace);
        m->dqb_btime = le64_to_cpu(d->dqb_btime);
        /* We need to escape back all-zero structure */
        memset(&empty, 0, sizeof(struct v2r0_disk_dqblk));
        empty.dqb_itime = cpu_to_le64(1);
        if (!memcmp(&empty, dp, sizeof(struct v2r0_disk_dqblk)))
                m->dqb_itime = 0;
}

static void v2r0_mem2diskdqb(void *dp, struct dquot *dquot)
{
        struct v2r0_disk_dqblk *d = dp;
        struct mem_dqblk *m = &dquot->dq_dqb;
        struct qtree_mem_dqinfo *info =
                        sb_dqinfo(dquot->dq_sb, dquot->dq_id.type)->dqi_priv;

        d->dqb_ihardlimit = cpu_to_le32(m->dqb_ihardlimit);
        d->dqb_isoftlimit = cpu_to_le32(m->dqb_isoftlimit);
        d->dqb_curinodes = cpu_to_le32(m->dqb_curinodes);
        d->dqb_itime = cpu_to_le64(m->dqb_itime);
        d->dqb_bhardlimit = cpu_to_le32(v2_stoqb(m->dqb_bhardlimit));
        d->dqb_bsoftlimit = cpu_to_le32(v2_stoqb(m->dqb_bsoftlimit));
        d->dqb_curspace = cpu_to_le64(m->dqb_curspace);
        d->dqb_btime = cpu_to_le64(m->dqb_btime);
        d->dqb_id = cpu_to_le32(from_kqid(&init_user_ns, dquot->dq_id));
        if (qtree_entry_unused(info, dp))
                d->dqb_itime = cpu_to_le64(1);
}

static int v2r0_is_id(void *dp, struct dquot *dquot)
{
        struct v2r0_disk_dqblk *d = dp;
        struct qtree_mem_dqinfo *info =
                        sb_dqinfo(dquot->dq_sb, dquot->dq_id.type)->dqi_priv;

        if (qtree_entry_unused(info, dp))
                return 0;
        return qid_eq(make_kqid(&init_user_ns, dquot->dq_id.type,
                                le32_to_cpu(d->dqb_id)),
                      dquot->dq_id);
}

static void v2r1_disk2memdqb(struct dquot *dquot, void *dp)
{
        struct v2r1_disk_dqblk *d = dp, empty;
        struct mem_dqblk *m = &dquot->dq_dqb;

        m->dqb_ihardlimit = le64_to_cpu(d->dqb_ihardlimit);
        m->dqb_isoftlimit = le64_to_cpu(d->dqb_isoftlimit);
        m->dqb_curinodes = le64_to_cpu(d->dqb_curinodes);
        m->dqb_itime = le64_to_cpu(d->dqb_itime);
        m->dqb_bhardlimit = v2_qbtos(le64_to_cpu(d->dqb_bhardlimit));
        m->dqb_bsoftlimit = v2_qbtos(le64_to_cpu(d->dqb_bsoftlimit));
        m->dqb_curspace = le64_to_cpu(d->dqb_curspace);
        m->dqb_btime = le64_to_cpu(d->dqb_btime);
        /* We need to escape back all-zero structure */
        memset(&empty, 0, sizeof(struct v2r1_disk_dqblk));
        empty.dqb_itime = cpu_to_le64(1);
        if (!memcmp(&empty, dp, sizeof(struct v2r1_disk_dqblk)))
                m->dqb_itime = 0;
}

static void v2r1_mem2diskdqb(void *dp, struct dquot *dquot)
{
        struct v2r1_disk_dqblk *d = dp;
        struct mem_dqblk *m = &dquot->dq_dqb;
        struct qtree_mem_dqinfo *info =
                        sb_dqinfo(dquot->dq_sb, dquot->dq_id.type)->dqi_priv;

        d->dqb_ihardlimit = cpu_to_le64(m->dqb_ihardlimit);
        d->dqb_isoftlimit = cpu_to_le64(m->dqb_isoftlimit);
        d->dqb_curinodes = cpu_to_le64(m->dqb_curinodes);
        d->dqb_itime = cpu_to_le64(m->dqb_itime);
        d->dqb_bhardlimit = cpu_to_le64(v2_stoqb(m->dqb_bhardlimit));
        d->dqb_bsoftlimit = cpu_to_le64(v2_stoqb(m->dqb_bsoftlimit));
        d->dqb_curspace = cpu_to_le64(m->dqb_curspace);
        d->dqb_btime = cpu_to_le64(m->dqb_btime);
        d->dqb_id = cpu_to_le32(from_kqid(&init_user_ns, dquot->dq_id));
        d->dqb_pad = 0;
        if (qtree_entry_unused(info, dp))
                d->dqb_itime = cpu_to_le64(1);
}

static int v2r1_is_id(void *dp, struct dquot *dquot)
{
        struct v2r1_disk_dqblk *d = dp;
        struct qtree_mem_dqinfo *info =
                        sb_dqinfo(dquot->dq_sb, dquot->dq_id.type)->dqi_priv;

        if (qtree_entry_unused(info, dp))
                return 0;
        return qid_eq(make_kqid(&init_user_ns, dquot->dq_id.type,
                                le32_to_cpu(d->dqb_id)),
                      dquot->dq_id);
}

static int v2_read_dquot(struct dquot *dquot)
{
        struct quota_info *dqopt = sb_dqopt(dquot->dq_sb);
        int ret;
        unsigned int memalloc;

        down_read(&dqopt->dqio_sem);
        memalloc = memalloc_nofs_save();
        ret = qtree_read_dquot(
                        sb_dqinfo(dquot->dq_sb, dquot->dq_id.type)->dqi_priv,
                        dquot);
        memalloc_nofs_restore(memalloc);
        up_read(&dqopt->dqio_sem);
        return ret;
}

static int v2_write_dquot(struct dquot *dquot)
{
        struct quota_info *dqopt = sb_dqopt(dquot->dq_sb);
        int ret;
        bool alloc = false;
        unsigned int memalloc;

        /*
         * If space for dquot is already allocated, we don't need any
         * protection as we'll only overwrite the place of dquot. We are
         * still protected by concurrent writes of the same dquot by
         * dquot->dq_lock.
         */
        if (!dquot->dq_off) {
                alloc = true;
                down_write(&dqopt->dqio_sem);
        } else {
                down_read(&dqopt->dqio_sem);
        }
        memalloc = memalloc_nofs_save();
        ret = qtree_write_dquot(
                        sb_dqinfo(dquot->dq_sb, dquot->dq_id.type)->dqi_priv,
                        dquot);
        memalloc_nofs_restore(memalloc);
        if (alloc)
                up_write(&dqopt->dqio_sem);
        else
                up_read(&dqopt->dqio_sem);
        return ret;
}

static int v2_release_dquot(struct dquot *dquot)
{
        struct quota_info *dqopt = sb_dqopt(dquot->dq_sb);
        unsigned int memalloc;
        int ret;

        down_write(&dqopt->dqio_sem);
        memalloc = memalloc_nofs_save();
        ret = qtree_release_dquot(sb_dqinfo(dquot->dq_sb, dquot->dq_id.type)->dqi_priv, dquot);
        memalloc_nofs_restore(memalloc);
        up_write(&dqopt->dqio_sem);

        return ret;
}

static int v2_free_file_info(struct super_block *sb, int type)
{
        kfree(sb_dqinfo(sb, type)->dqi_priv);
        return 0;
}

static int v2_get_next_id(struct super_block *sb, struct kqid *qid)
{
        struct quota_info *dqopt = sb_dqopt(sb);
        unsigned int memalloc;
        int ret;

        down_read(&dqopt->dqio_sem);
        memalloc = memalloc_nofs_save();
        ret = qtree_get_next_id(sb_dqinfo(sb, qid->type)->dqi_priv, qid);
        memalloc_nofs_restore(memalloc);
        up_read(&dqopt->dqio_sem);
        return ret;
}

static const struct quota_format_ops v2_format_ops = {
        .check_quota_file        = v2_check_quota_file,
        .read_file_info                = v2_read_file_info,
        .write_file_info        = v2_write_file_info,
        .free_file_info                = v2_free_file_info,
        .read_dqblk                = v2_read_dquot,
        .commit_dqblk                = v2_write_dquot,
        .release_dqblk                = v2_release_dquot,
        .get_next_id                = v2_get_next_id,
};

static struct quota_format_type v2r0_quota_format = {
        .qf_fmt_id        = QFMT_VFS_V0,
        .qf_ops                = &v2_format_ops,
        .qf_owner        = THIS_MODULE
};

static struct quota_format_type v2r1_quota_format = {
        .qf_fmt_id        = QFMT_VFS_V1,
        .qf_ops                = &v2_format_ops,
        .qf_owner        = THIS_MODULE
};

static int __init init_v2_quota_format(void)
{
        register_quota_format(&v2r0_quota_format);
        register_quota_format(&v2r1_quota_format);
        return 0;
}

static void __exit exit_v2_quota_format(void)
{
        unregister_quota_format(&v2r0_quota_format);
        unregister_quota_format(&v2r1_quota_format);
}

module_init(init_v2_quota_format);
module_exit(exit_v2_quota_format);














































































































































































































   26 




















  213 





  213 





  212 




  116 












   76 





  121 


























  159 






   58 
   58 
   45 




   25 














  212 
  202 
   11 
























  221 

























  220 







  160 





   84 

   82 












  160 
   44 



  160 

    1 












    1 




   30 


  158 





















  160 



  160 













    8 









    6 











  221 

  160 





















  160 




  221 



  220 




























   38 



















   12 
































   26 




















































  160 












  160 

   32 
  144 

  138 
   32 
    6 







   36 


  144 










    5 











   32 








































   60 
   20 

















   26 









   39 

































    3 







    3 



    3 


    2 

    1 



    3 






    3 














    1 



    3 


















    3 






































   22 












    4 

   22 









   22 
















   11 








   20 











   11 























   11 






   22 

    8 
    8 



















   15 

   15 

















   71 






    9 


   60 














































    2 

































    2 













   60 


   60 









    3 



   57 










    3 












    8 








    9 


























   70 








   70 



















   70 


   60 
   10 








    8 












    2 






    1 






    1 



   58 

























   58 








   58 























    1 









   57 










   65 





















    5 

    5 

















   10 





   10 



   10 













    8 




    2 












    2 















   10 















   25 




    1 


   24 



   23 













    1 
    2 



    4 




    1 

    3 



   24 

   18 



   23 



    2 







   20 


   10 





   10 


    3 
    3 







    9 






















   10 

















    8 








    8 
































    8 


    8 






    8 

    8 









































































































   70 




















   70 






   70 






































    5 


   13 














  108 







  109 









  109 












    1 




    2 






   62 










































   64 







   64 




   64 










   64 


   64 






















  123 



  124 



  124 

















   72 

   68 




    2 







    2 









   60 

   67 













   57 
   59 









   59 


















  123 




  124 

    4 
  120 



  124 








    4 


  119 









   60 



   60 



   60 



   58 
   59 



   60 









    7 








    7 





    4 


    3 








    3 









































    3 
    2 








































    1 










    3 











    1 


























































































































































































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
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
1187
1188
1189
1190
1191
1192
1193
1194
1195
1196
1197
1198
1199
1200
1201
1202
1203
1204
1205
1206
1207
1208
1209
1210
1211
1212
1213
1214
1215
1216
1217
1218
1219
1220
1221
1222
1223
1224
1225
1226
1227
1228
1229
1230
1231
1232
1233
1234
1235
1236
1237
1238
1239
1240
1241
1242
1243
1244
1245
1246
1247
1248
1249
1250
1251
1252
1253
1254
1255
1256
1257
1258
1259
1260
1261
1262
1263
1264
1265
1266
1267
1268
1269
1270
1271
1272
1273
1274
1275
1276
1277
1278
1279
1280
1281
1282
1283
1284
1285
1286
1287
1288
1289
1290
1291
1292
1293
1294
1295
1296
1297
1298
1299
1300
1301
1302
1303
1304
1305
1306
1307
1308
1309
1310
1311
1312
1313
1314
1315
1316
1317
1318
1319
1320
1321
1322
1323
1324
1325
1326
1327
1328
1329
1330
1331
1332
1333
1334
1335
1336
1337
1338
1339
1340
1341
1342
1343
1344
1345
1346
1347
1348
1349
1350
1351
1352
1353
1354
1355
1356
1357
1358
1359
1360
1361
1362
1363
1364
1365
1366
1367
1368
1369
1370
1371
1372
1373
1374
1375
1376
1377
1378
1379
1380
1381
1382
1383
1384
1385
1386
1387
1388
1389
1390
1391
1392
1393
1394
1395
1396
1397
1398
1399
1400
1401
1402
1403
1404
1405
1406
1407
1408
1409
1410
1411
1412
1413
1414
1415
1416
1417
1418
1419
1420
1421
1422
1423
1424
1425
1426
1427
1428
1429
1430
1431
1432
1433
1434
1435
1436
1437
1438
1439
1440
1441
1442
1443
1444
1445
1446
1447
1448
1449
1450
1451
1452
1453
1454
1455
1456
1457
1458
1459
1460
1461
1462
1463
1464
1465
1466
1467
1468
1469
1470
1471
1472
1473
1474
1475
1476
1477
1478
1479
1480
1481
1482
1483
1484
1485
1486
1487
1488
1489
1490
1491
1492
1493
1494
1495
1496
1497
1498
1499
1500
1501
1502
1503
1504
1505
1506
1507
1508
1509
1510
1511
1512
1513
1514
1515
1516
1517
1518
1519
1520
1521
1522
1523
1524
1525
1526
1527
1528
1529
1530
1531
1532
1533
1534
1535
1536
1537
1538
1539
1540
1541
1542
1543
1544
1545
1546
1547
1548
1549
1550
1551
1552
1553
1554
1555
1556
1557
1558
1559
1560
1561
1562
1563
1564
1565
1566
1567
1568
1569
1570
1571
1572
1573
1574
1575
1576
1577
1578
1579
1580
1581
1582
1583
1584
1585
1586
1587
1588
1589
1590
1591
1592
1593
1594
1595
1596
1597
1598
1599
1600
1601
1602
1603
1604
1605
1606
1607
1608
1609
1610
1611
1612
1613
1614
1615
1616
1617
1618
1619
1620
1621
1622
1623
1624
1625
1626
1627
1628
1629
1630
1631
1632
1633
1634
1635
1636
1637
1638
1639
1640
1641
1642
1643
1644
1645
1646
1647
1648
1649
1650
1651
1652
1653
1654
1655
1656
1657
1658
1659
1660
1661
1662
1663
1664
1665
1666
1667
1668
1669
1670
1671
1672
1673
1674
1675
1676
1677
1678
1679
1680
1681
1682
1683
1684
1685
1686
1687
1688
1689
1690
1691
1692
1693
1694
1695
1696
1697
1698
1699
1700
1701
1702
1703
1704
1705
1706
1707
1708
1709
1710
1711
1712
1713
1714
1715
1716
1717
1718
1719
1720
1721
1722
1723
1724
1725
1726
1727
1728
1729
1730
1731
1732
1733
1734
1735
1736
1737
1738
1739
1740
1741
1742
1743
1744
1745
1746
1747
1748
1749
1750
1751
1752
1753
1754
1755
1756
1757
1758
1759
1760
1761
1762
1763
1764
1765
1766
1767
1768
1769
1770
1771
1772
1773
1774
1775
1776
1777
1778
1779
1780
1781
1782
1783
1784
1785
1786
1787
1788
1789
1790
1791
1792
1793
1794
1795
1796
1797
1798
1799
1800
1801
1802
1803
1804
1805
1806
1807
1808
1809
1810
1811
1812
1813
1814
1815
1816
1817
1818
1819
1820
1821
1822
1823
1824
1825
1826
1827
1828
1829
1830
1831
1832
1833
1834
1835
1836
1837
1838
1839
1840
1841
1842
1843
1844
1845
1846
1847
1848
1849
1850
1851
1852
1853
1854
1855
1856
1857
1858
1859
1860
1861
1862
1863
1864
1865
1866
1867
1868
1869
1870
1871
1872
1873
1874
1875
1876
1877
1878
1879
1880
1881
1882
1883
1884
1885
1886
1887
1888
1889
1890
1891
1892
1893
1894
1895
1896
1897
1898
1899
1900
1901
1902
1903
1904
1905
1906
1907
1908
1909
1910
1911
1912
1913
1914
1915
1916
1917
1918
1919
1920
1921
1922
1923
1924
1925
1926
1927
1928
1929
1930
1931
1932
1933
1934
1935
1936
1937
1938
1939
1940
1941
1942
1943
1944
1945
1946
1947
1948
1949
1950
1951
1952
1953
1954
1955
1956
1957
1958
1959
1960
1961
1962
1963
1964
1965
1966
1967
1968
1969
1970
1971
1972
1973
1974
1975
1976
1977
1978
1979
1980
1981
1982
1983
1984
1985
1986
1987
1988
1989
1990
1991
1992
1993
1994
1995
1996
1997
1998
1999
2000
2001
2002
2003
2004
2005
2006
2007
2008
2009
2010
2011
2012
2013
2014
2015
2016
2017
2018
2019
2020
2021
2022
2023
2024
2025
2026
2027
2028
2029
2030
2031
2032
2033
2034
2035
2036
2037
2038
2039
2040
2041
2042
2043
2044
2045
2046
2047
2048
2049
2050
2051
2052
2053
2054
2055
2056
2057
2058
2059
2060
2061
2062
2063
2064
2065
2066
2067
2068
2069
2070
2071
2072
2073
2074
2075
2076
2077
2078
2079
2080
2081
2082
2083
2084
2085
2086
2087
2088
2089
2090
2091
2092
2093
2094
2095
2096
2097
2098
2099
2100
2101
2102
2103
2104
2105
2106
2107
2108
2109
2110
2111
2112
2113
2114
2115
2116
2117
2118
2119
2120
2121
2122
2123
2124
2125
2126
2127
2128
2129
2130
2131
2132
2133
2134
2135
2136
2137
2138
2139
2140
2141
2142
2143
2144
2145
2146
2147
2148
2149
2150
2151
2152
2153
2154
2155
2156
2157
2158
2159
2160
2161
2162
2163
2164
2165
2166
2167
2168
2169
2170
2171
2172
2173
2174
2175
2176
2177
2178
2179
2180
2181
2182
2183
2184
2185
2186
2187
2188
2189
2190
2191
2192
2193
2194
2195
2196
2197
2198
2199
2200
2201
2202
2203
2204
2205
2206
2207
2208
2209
2210
2211
2212
2213
2214
2215
2216
2217
2218
2219
2220
2221
2222
2223
2224
2225
2226
2227
2228
2229
2230
2231
2232
2233
2234
2235
2236
2237
2238
2239
2240
2241
2242
2243
2244
2245
2246
2247
2248
2249
2250
2251
2252
2253
2254
2255
2256
2257
2258
2259
2260
2261
2262
2263
2264
2265
2266
2267
2268
2269
2270
2271
2272
2273
2274
2275
2276
2277
2278
2279
2280
2281
2282
2283
2284
2285
2286
2287
2288
2289
2290
2291
2292
2293
2294
2295
2296
2297
2298
2299
2300
2301
2302
2303
2304
2305
2306
2307
2308
2309
2310
2311
2312
2313
2314
2315
2316
2317
2318
2319
2320
2321
2322
2323
2324
2325
2326
2327
2328
2329
2330
2331
2332
2333
2334
2335
2336
2337
2338
2339
2340
2341
2342
2343
2344
2345
2346
2347
2348
2349
2350
2351
2352
2353
2354
2355
2356
2357
2358
2359
2360
2361
2362
2363
2364
2365
2366
2367
2368
2369
2370
2371
2372
2373
2374
2375
2376
2377
2378
2379
2380
2381
2382
2383
2384
2385
2386
2387
2388
2389
2390
2391
2392
2393
2394
2395
2396
2397
2398
2399
2400
2401
2402
2403
2404
2405
2406
2407
2408
2409
2410
2411
2412
2413
2414
2415
2416
2417
2418
2419
2420
2421
2422
2423
2424
2425
2426
2427
2428
2429
2430
2431
2432
2433
2434
2435
2436
2437
2438
2439
2440
2441
2442
2443
2444
2445
2446
2447
2448
2449
2450
2451
2452
2453
2454
2455
2456
2457
2458
2459
2460
2461
2462
2463
2464
2465
2466
2467
2468
2469
2470
2471
2472
2473
2474
2475
2476
2477
2478
2479
2480
2481
2482
2483
2484
2485
2486
2487
2488
2489
2490
2491
// SPDX-License-Identifier: GPL-2.0-or-later
/*
 *   Copyright (C) International Business Machines Corp., 2000-2004
 *   Portions Copyright (C) Christoph Hellwig, 2001-2002
 */

/*
 *        jfs_logmgr.c: log manager
 *
 * for related information, see transaction manager (jfs_txnmgr.c), and
 * recovery manager (jfs_logredo.c).
 *
 * note: for detail, RTFS.
 *
 *        log buffer manager:
 * special purpose buffer manager supporting log i/o requirements.
 * per log serial pageout of logpage
 * queuing i/o requests and redrive i/o at iodone
 * maintain current logpage buffer
 * no caching since append only
 * appropriate jfs buffer cache buffers as needed
 *
 *        group commit:
 * transactions which wrote COMMIT records in the same in-memory
 * log page during the pageout of previous/current log page(s) are
 * committed together by the pageout of the page.
 *
 *        TBD lazy commit:
 * transactions are committed asynchronously when the log page
 * containing it COMMIT is paged out when it becomes full;
 *
 *        serialization:
 * . a per log lock serialize log write.
 * . a per log lock serialize group commit.
 * . a per log lock serialize log open/close;
 *
 *        TBD log integrity:
 * careful-write (ping-pong) of last logpage to recover from crash
 * in overwrite.
 * detection of split (out-of-order) write of physical sectors
 * of last logpage via timestamp at end of each sector
 * with its mirror data array at trailer).
 *
 *        alternatives:
 * lsn - 64-bit monotonically increasing integer vs
 * 32-bit lspn and page eor.
 */

#include <linux/fs.h>
#include <linux/blkdev.h>
#include <linux/interrupt.h>
#include <linux/completion.h>
#include <linux/kthread.h>
#include <linux/buffer_head.h>                /* for sync_blockdev() */
#include <linux/bio.h>
#include <linux/freezer.h>
#include <linux/export.h>
#include <linux/delay.h>
#include <linux/mutex.h>
#include <linux/seq_file.h>
#include <linux/slab.h>
#include "jfs_incore.h"
#include "jfs_filsys.h"
#include "jfs_metapage.h"
#include "jfs_superblock.h"
#include "jfs_txnmgr.h"
#include "jfs_debug.h"


/*
 * lbuf's ready to be redriven.  Protected by log_redrive_lock (jfsIO thread)
 */
static struct lbuf *log_redrive_list;
static DEFINE_SPINLOCK(log_redrive_lock);


/*
 *        log read/write serialization (per log)
 */
#define LOG_LOCK_INIT(log)        mutex_init(&(log)->loglock)
#define LOG_LOCK(log)                mutex_lock(&((log)->loglock))
#define LOG_UNLOCK(log)                mutex_unlock(&((log)->loglock))


/*
 *        log group commit serialization (per log)
 */

#define LOGGC_LOCK_INIT(log)        spin_lock_init(&(log)->gclock)
#define LOGGC_LOCK(log)                spin_lock_irq(&(log)->gclock)
#define LOGGC_UNLOCK(log)        spin_unlock_irq(&(log)->gclock)
#define LOGGC_WAKEUP(tblk)        wake_up_all(&(tblk)->gcwait)

/*
 *        log sync serialization (per log)
 */
#define        LOGSYNC_DELTA(logsize)                min((logsize)/8, 128*LOGPSIZE)
#define        LOGSYNC_BARRIER(logsize)        ((logsize)/4)
/*
#define        LOGSYNC_DELTA(logsize)                min((logsize)/4, 256*LOGPSIZE)
#define        LOGSYNC_BARRIER(logsize)        ((logsize)/2)
*/


/*
 *        log buffer cache synchronization
 */
static DEFINE_SPINLOCK(jfsLCacheLock);

#define        LCACHE_LOCK(flags)        spin_lock_irqsave(&jfsLCacheLock, flags)
#define        LCACHE_UNLOCK(flags)        spin_unlock_irqrestore(&jfsLCacheLock, flags)

/*
 * See __SLEEP_COND in jfs_locks.h
 */
#define LCACHE_SLEEP_COND(wq, cond, flags)        \
do {                                                \
        if (cond)                                \
                break;                                \
        __SLEEP_COND(wq, cond, LCACHE_LOCK(flags), LCACHE_UNLOCK(flags)); \
} while (0)

#define        LCACHE_WAKEUP(event)        wake_up(event)


/*
 *        lbuf buffer cache (lCache) control
 */
/* log buffer manager pageout control (cumulative, inclusive) */
#define        lbmREAD                0x0001
#define        lbmWRITE        0x0002        /* enqueue at tail of write queue;
                                 * init pageout if at head of queue;
                                 */
#define        lbmRELEASE        0x0004        /* remove from write queue
                                 * at completion of pageout;
                                 * do not free/recycle it yet:
                                 * caller will free it;
                                 */
#define        lbmSYNC                0x0008        /* do not return to freelist
                                 * when removed from write queue;
                                 */
#define lbmFREE                0x0010        /* return to freelist
                                 * at completion of pageout;
                                 * the buffer may be recycled;
                                 */
#define        lbmDONE                0x0020
#define        lbmERROR        0x0040
#define lbmGC                0x0080        /* lbmIODone to perform post-GC processing
                                 * of log page
                                 */
#define lbmDIRECT        0x0100

/*
 * Global list of active external journals
 */
static LIST_HEAD(jfs_external_logs);
static struct jfs_log *dummy_log;
static DEFINE_MUTEX(jfs_log_mutex);

/*
 * forward references
 */
static int lmWriteRecord(struct jfs_log * log, struct tblock * tblk,
                         struct lrd * lrd, struct tlock * tlck);

static int lmNextPage(struct jfs_log * log);
static int lmLogFileSystem(struct jfs_log * log, struct jfs_sb_info *sbi,
                           int activate);

static int open_inline_log(struct super_block *sb);
static int open_dummy_log(struct super_block *sb);
static int lbmLogInit(struct jfs_log * log);
static void lbmLogShutdown(struct jfs_log * log);
static struct lbuf *lbmAllocate(struct jfs_log * log, int);
static void lbmFree(struct lbuf * bp);
static void lbmfree(struct lbuf * bp);
static int lbmRead(struct jfs_log * log, int pn, struct lbuf ** bpp);
static void lbmWrite(struct jfs_log * log, struct lbuf * bp, int flag, int cant_block);
static void lbmDirectWrite(struct jfs_log * log, struct lbuf * bp, int flag);
static int lbmIOWait(struct lbuf * bp, int flag);
static bio_end_io_t lbmIODone;
static void lbmStartIO(struct lbuf * bp);
static void lmGCwrite(struct jfs_log * log, int cant_block);
static int lmLogSync(struct jfs_log * log, int hard_sync);



/*
 *        statistics
 */
#ifdef CONFIG_JFS_STATISTICS
static struct lmStat {
        uint commit;                /* # of commit */
        uint pagedone;                /* # of page written */
        uint submitted;                /* # of pages submitted */
        uint full_page;                /* # of full pages submitted */
        uint partial_page;        /* # of partial pages submitted */
} lmStat;
#endif

static void write_special_inodes(struct jfs_log *log,
                                 int (*writer)(struct address_space *))
{
        struct jfs_sb_info *sbi;

        list_for_each_entry(sbi, &log->sb_list, log_list) {
                writer(sbi->ipbmap->i_mapping);
                writer(sbi->ipimap->i_mapping);
                writer(sbi->direct_inode->i_mapping);
        }
}

/*
 * NAME:        lmLog()
 *
 * FUNCTION:        write a log record;
 *
 * PARAMETER:
 *
 * RETURN:        lsn - offset to the next log record to write (end-of-log);
 *                -1  - error;
 *
 * note: todo: log error handler
 */
int lmLog(struct jfs_log * log, struct tblock * tblk, struct lrd * lrd,
          struct tlock * tlck)
{
        int lsn;
        int diffp, difft;
        struct metapage *mp = NULL;
        unsigned long flags;

        jfs_info("lmLog: log:0x%p tblk:0x%p, lrd:0x%p tlck:0x%p",
                 log, tblk, lrd, tlck);

        LOG_LOCK(log);

        /* log by (out-of-transaction) JFS ? */
        if (tblk == NULL)
                goto writeRecord;

        /* log from page ? */
        if (tlck == NULL ||
            tlck->type & tlckBTROOT || (mp = tlck->mp) == NULL)
                goto writeRecord;

        /*
         *        initialize/update page/transaction recovery lsn
         */
        lsn = log->lsn;

        LOGSYNC_LOCK(log, flags);

        /*
         * initialize page lsn if first log write of the page
         */
        if (mp->lsn == 0) {
                mp->log = log;
                mp->lsn = lsn;
                log->count++;

                /* insert page at tail of logsynclist */
                list_add_tail(&mp->synclist, &log->synclist);
        }

        /*
         *        initialize/update lsn of tblock of the page
         *
         * transaction inherits oldest lsn of pages associated
         * with allocation/deallocation of resources (their
         * log records are used to reconstruct allocation map
         * at recovery time: inode for inode allocation map,
         * B+-tree index of extent descriptors for block
         * allocation map);
         * allocation map pages inherit transaction lsn at
         * commit time to allow forwarding log syncpt past log
         * records associated with allocation/deallocation of
         * resources only after persistent map of these map pages
         * have been updated and propagated to home.
         */
        /*
         * initialize transaction lsn:
         */
        if (tblk->lsn == 0) {
                /* inherit lsn of its first page logged */
                tblk->lsn = mp->lsn;
                log->count++;

                /* insert tblock after the page on logsynclist */
                list_add(&tblk->synclist, &mp->synclist);
        }
        /*
         * update transaction lsn:
         */
        else {
                /* inherit oldest/smallest lsn of page */
                logdiff(diffp, mp->lsn, log);
                logdiff(difft, tblk->lsn, log);
                if (diffp < difft) {
                        /* update tblock lsn with page lsn */
                        tblk->lsn = mp->lsn;

                        /* move tblock after page on logsynclist */
                        list_move(&tblk->synclist, &mp->synclist);
                }
        }

        LOGSYNC_UNLOCK(log, flags);

        /*
         *        write the log record
         */
      writeRecord:
        lsn = lmWriteRecord(log, tblk, lrd, tlck);

        /*
         * forward log syncpt if log reached next syncpt trigger
         */
        logdiff(diffp, lsn, log);
        if (diffp >= log->nextsync)
                lsn = lmLogSync(log, 0);

        /* update end-of-log lsn */
        log->lsn = lsn;

        LOG_UNLOCK(log);

        /* return end-of-log address */
        return lsn;
}

/*
 * NAME:        lmWriteRecord()
 *
 * FUNCTION:        move the log record to current log page
 *
 * PARAMETER:        cd        - commit descriptor
 *
 * RETURN:        end-of-log address
 *
 * serialization: LOG_LOCK() held on entry/exit
 */
static int
lmWriteRecord(struct jfs_log * log, struct tblock * tblk, struct lrd * lrd,
              struct tlock * tlck)
{
        int lsn = 0;                /* end-of-log address */
        struct lbuf *bp;        /* dst log page buffer */
        struct logpage *lp;        /* dst log page */
        caddr_t dst;                /* destination address in log page */
        int dstoffset;                /* end-of-log offset in log page */
        int freespace;                /* free space in log page */
        caddr_t p;                /* src meta-data page */
        caddr_t src;
        int srclen;
        int nbytes;                /* number of bytes to move */
        int i;
        int len;
        struct linelock *linelock;
        struct lv *lv;
        struct lvd *lvd;
        int l2linesize;

        len = 0;

        /* retrieve destination log page to write */
        bp = (struct lbuf *) log->bp;
        lp = (struct logpage *) bp->l_ldata;
        dstoffset = log->eor;

        /* any log data to write ? */
        if (tlck == NULL)
                goto moveLrd;

        /*
         *        move log record data
         */
        /* retrieve source meta-data page to log */
        if (tlck->flag & tlckPAGELOCK) {
                p = (caddr_t) (tlck->mp->data);
                linelock = (struct linelock *) & tlck->lock;
        }
        /* retrieve source in-memory inode to log */
        else if (tlck->flag & tlckINODELOCK) {
                if (tlck->type & tlckDTREE)
                        p = (caddr_t) &JFS_IP(tlck->ip)->i_dtroot;
                else
                        p = (caddr_t) &JFS_IP(tlck->ip)->i_xtroot;
                linelock = (struct linelock *) & tlck->lock;
        }
        else {
                jfs_err("lmWriteRecord: UFO tlck:0x%p", tlck);
                return 0;        /* Probably should trap */
        }
        l2linesize = linelock->l2linesize;

      moveData:
        ASSERT(linelock->index <= linelock->maxcnt);

        lv = linelock->lv;
        for (i = 0; i < linelock->index; i++, lv++) {
                if (lv->length == 0)
                        continue;

                /* is page full ? */
                if (dstoffset >= LOGPSIZE - LOGPTLRSIZE) {
                        /* page become full: move on to next page */
                        lmNextPage(log);

                        bp = log->bp;
                        lp = (struct logpage *) bp->l_ldata;
                        dstoffset = LOGPHDRSIZE;
                }

                /*
                 * move log vector data
                 */
                src = (u8 *) p + (lv->offset << l2linesize);
                srclen = lv->length << l2linesize;
                len += srclen;
                while (srclen > 0) {
                        freespace = (LOGPSIZE - LOGPTLRSIZE) - dstoffset;
                        nbytes = min(freespace, srclen);
                        dst = (caddr_t) lp + dstoffset;
                        memcpy(dst, src, nbytes);
                        dstoffset += nbytes;

                        /* is page not full ? */
                        if (dstoffset < LOGPSIZE - LOGPTLRSIZE)
                                break;

                        /* page become full: move on to next page */
                        lmNextPage(log);

                        bp = (struct lbuf *) log->bp;
                        lp = (struct logpage *) bp->l_ldata;
                        dstoffset = LOGPHDRSIZE;

                        srclen -= nbytes;
                        src += nbytes;
                }

                /*
                 * move log vector descriptor
                 */
                len += 4;
                lvd = (struct lvd *) ((caddr_t) lp + dstoffset);
                lvd->offset = cpu_to_le16(lv->offset);
                lvd->length = cpu_to_le16(lv->length);
                dstoffset += 4;
                jfs_info("lmWriteRecord: lv offset:%d length:%d",
                         lv->offset, lv->length);
        }

        if ((i = linelock->next)) {
                linelock = (struct linelock *) lid_to_tlock(i);
                goto moveData;
        }

        /*
         *        move log record descriptor
         */
      moveLrd:
        lrd->length = cpu_to_le16(len);

        src = (caddr_t) lrd;
        srclen = LOGRDSIZE;

        while (srclen > 0) {
                freespace = (LOGPSIZE - LOGPTLRSIZE) - dstoffset;
                nbytes = min(freespace, srclen);
                dst = (caddr_t) lp + dstoffset;
                memcpy(dst, src, nbytes);

                dstoffset += nbytes;
                srclen -= nbytes;

                /* are there more to move than freespace of page ? */
                if (srclen)
                        goto pageFull;

                /*
                 * end of log record descriptor
                 */

                /* update last log record eor */
                log->eor = dstoffset;
                bp->l_eor = dstoffset;
                lsn = (log->page << L2LOGPSIZE) + dstoffset;

                if (lrd->type & cpu_to_le16(LOG_COMMIT)) {
                        tblk->clsn = lsn;
                        jfs_info("wr: tclsn:0x%x, beor:0x%x", tblk->clsn,
                                 bp->l_eor);

                        INCREMENT(lmStat.commit);        /* # of commit */

                        /*
                         * enqueue tblock for group commit:
                         *
                         * enqueue tblock of non-trivial/synchronous COMMIT
                         * at tail of group commit queue
                         * (trivial/asynchronous COMMITs are ignored by
                         * group commit.)
                         */
                        LOGGC_LOCK(log);

                        /* init tblock gc state */
                        tblk->flag = tblkGC_QUEUE;
                        tblk->bp = log->bp;
                        tblk->pn = log->page;
                        tblk->eor = log->eor;

                        /* enqueue transaction to commit queue */
                        list_add_tail(&tblk->cqueue, &log->cqueue);

                        LOGGC_UNLOCK(log);
                }

                jfs_info("lmWriteRecord: lrd:0x%04x bp:0x%p pn:%d eor:0x%x",
                        le16_to_cpu(lrd->type), log->bp, log->page, dstoffset);

                /* page not full ? */
                if (dstoffset < LOGPSIZE - LOGPTLRSIZE)
                        return lsn;

              pageFull:
                /* page become full: move on to next page */
                lmNextPage(log);

                bp = (struct lbuf *) log->bp;
                lp = (struct logpage *) bp->l_ldata;
                dstoffset = LOGPHDRSIZE;
                src += nbytes;
        }

        return lsn;
}


/*
 * NAME:        lmNextPage()
 *
 * FUNCTION:        write current page and allocate next page.
 *
 * PARAMETER:        log
 *
 * RETURN:        0
 *
 * serialization: LOG_LOCK() held on entry/exit
 */
static int lmNextPage(struct jfs_log * log)
{
        struct logpage *lp;
        int lspn;                /* log sequence page number */
        int pn;                        /* current page number */
        struct lbuf *bp;
        struct lbuf *nextbp;
        struct tblock *tblk;

        /* get current log page number and log sequence page number */
        pn = log->page;
        bp = log->bp;
        lp = (struct logpage *) bp->l_ldata;
        lspn = le32_to_cpu(lp->h.page);

        LOGGC_LOCK(log);

        /*
         *        write or queue the full page at the tail of write queue
         */
        /* get the tail tblk on commit queue */
        if (list_empty(&log->cqueue))
                tblk = NULL;
        else
                tblk = list_entry(log->cqueue.prev, struct tblock, cqueue);

        /* every tblk who has COMMIT record on the current page,
         * and has not been committed, must be on commit queue
         * since tblk is queued at commit queueu at the time
         * of writing its COMMIT record on the page before
         * page becomes full (even though the tblk thread
         * who wrote COMMIT record may have been suspended
         * currently);
         */

        /* is page bound with outstanding tail tblk ? */
        if (tblk && tblk->pn == pn) {
                /* mark tblk for end-of-page */
                tblk->flag |= tblkGC_EOP;

                if (log->cflag & logGC_PAGEOUT) {
                        /* if page is not already on write queue,
                         * just enqueue (no lbmWRITE to prevent redrive)
                         * buffer to wqueue to ensure correct serial order
                         * of the pages since log pages will be added
                         * continuously
                         */
                        if (bp->l_wqnext == NULL)
                                lbmWrite(log, bp, 0, 0);
                } else {
                        /*
                         * No current GC leader, initiate group commit
                         */
                        log->cflag |= logGC_PAGEOUT;
                        lmGCwrite(log, 0);
                }
        }
        /* page is not bound with outstanding tblk:
         * init write or mark it to be redriven (lbmWRITE)
         */
        else {
                /* finalize the page */
                bp->l_ceor = bp->l_eor;
                lp->h.eor = lp->t.eor = cpu_to_le16(bp->l_ceor);
                lbmWrite(log, bp, lbmWRITE | lbmRELEASE | lbmFREE, 0);
        }
        LOGGC_UNLOCK(log);

        /*
         *        allocate/initialize next page
         */
        /* if log wraps, the first data page of log is 2
         * (0 never used, 1 is superblock).
         */
        log->page = (pn == log->size - 1) ? 2 : pn + 1;
        log->eor = LOGPHDRSIZE;        /* ? valid page empty/full at logRedo() */

        /* allocate/initialize next log page buffer */
        nextbp = lbmAllocate(log, log->page);
        nextbp->l_eor = log->eor;
        log->bp = nextbp;

        /* initialize next log page */
        lp = (struct logpage *) nextbp->l_ldata;
        lp->h.page = lp->t.page = cpu_to_le32(lspn + 1);
        lp->h.eor = lp->t.eor = cpu_to_le16(LOGPHDRSIZE);

        return 0;
}


/*
 * NAME:        lmGroupCommit()
 *
 * FUNCTION:        group commit
 *        initiate pageout of the pages with COMMIT in the order of
 *        page number - redrive pageout of the page at the head of
 *        pageout queue until full page has been written.
 *
 * RETURN:
 *
 * NOTE:
 *        LOGGC_LOCK serializes log group commit queue, and
 *        transaction blocks on the commit queue.
 *        N.B. LOG_LOCK is NOT held during lmGroupCommit().
 */
int lmGroupCommit(struct jfs_log * log, struct tblock * tblk)
{
        int rc = 0;

        LOGGC_LOCK(log);

        /* group committed already ? */
        if (tblk->flag & tblkGC_COMMITTED) {
                if (tblk->flag & tblkGC_ERROR)
                        rc = -EIO;

                LOGGC_UNLOCK(log);
                return rc;
        }
        jfs_info("lmGroup Commit: tblk = 0x%p, gcrtc = %d", tblk, log->gcrtc);

        if (tblk->xflag & COMMIT_LAZY)
                tblk->flag |= tblkGC_LAZY;

        if ((!(log->cflag & logGC_PAGEOUT)) && (!list_empty(&log->cqueue)) &&
            (!(tblk->xflag & COMMIT_LAZY) || test_bit(log_FLUSH, &log->flag)
             || jfs_tlocks_low)) {
                /*
                 * No pageout in progress
                 *
                 * start group commit as its group leader.
                 */
                log->cflag |= logGC_PAGEOUT;

                lmGCwrite(log, 0);
        }

        if (tblk->xflag & COMMIT_LAZY) {
                /*
                 * Lazy transactions can leave now
                 */
                LOGGC_UNLOCK(log);
                return 0;
        }

        /* lmGCwrite gives up LOGGC_LOCK, check again */

        if (tblk->flag & tblkGC_COMMITTED) {
                if (tblk->flag & tblkGC_ERROR)
                        rc = -EIO;

                LOGGC_UNLOCK(log);
                return rc;
        }

        /* upcount transaction waiting for completion
         */
        log->gcrtc++;
        tblk->flag |= tblkGC_READY;

        __SLEEP_COND(tblk->gcwait, (tblk->flag & tblkGC_COMMITTED),
                     LOGGC_LOCK(log), LOGGC_UNLOCK(log));

        /* removed from commit queue */
        if (tblk->flag & tblkGC_ERROR)
                rc = -EIO;

        LOGGC_UNLOCK(log);
        return rc;
}

/*
 * NAME:        lmGCwrite()
 *
 * FUNCTION:        group commit write
 *        initiate write of log page, building a group of all transactions
 *        with commit records on that page.
 *
 * RETURN:        None
 *
 * NOTE:
 *        LOGGC_LOCK must be held by caller.
 *        N.B. LOG_LOCK is NOT held during lmGroupCommit().
 */
static void lmGCwrite(struct jfs_log * log, int cant_write)
{
        struct lbuf *bp;
        struct logpage *lp;
        int gcpn;                /* group commit page number */
        struct tblock *tblk;
        struct tblock *xtblk = NULL;

        /*
         * build the commit group of a log page
         *
         * scan commit queue and make a commit group of all
         * transactions with COMMIT records on the same log page.
         */
        /* get the head tblk on the commit queue */
        gcpn = list_entry(log->cqueue.next, struct tblock, cqueue)->pn;

        list_for_each_entry(tblk, &log->cqueue, cqueue) {
                if (tblk->pn != gcpn)
                        break;

                xtblk = tblk;

                /* state transition: (QUEUE, READY) -> COMMIT */
                tblk->flag |= tblkGC_COMMIT;
        }
        tblk = xtblk;                /* last tblk of the page */

        /*
         * pageout to commit transactions on the log page.
         */
        bp = (struct lbuf *) tblk->bp;
        lp = (struct logpage *) bp->l_ldata;
        /* is page already full ? */
        if (tblk->flag & tblkGC_EOP) {
                /* mark page to free at end of group commit of the page */
                tblk->flag &= ~tblkGC_EOP;
                tblk->flag |= tblkGC_FREE;
                bp->l_ceor = bp->l_eor;
                lp->h.eor = lp->t.eor = cpu_to_le16(bp->l_ceor);
                lbmWrite(log, bp, lbmWRITE | lbmRELEASE | lbmGC,
                         cant_write);
                INCREMENT(lmStat.full_page);
        }
        /* page is not yet full */
        else {
                bp->l_ceor = tblk->eor;        /* ? bp->l_ceor = bp->l_eor; */
                lp->h.eor = lp->t.eor = cpu_to_le16(bp->l_ceor);
                lbmWrite(log, bp, lbmWRITE | lbmGC, cant_write);
                INCREMENT(lmStat.partial_page);
        }
}

/*
 * NAME:        lmPostGC()
 *
 * FUNCTION:        group commit post-processing
 *        Processes transactions after their commit records have been written
 *        to disk, redriving log I/O if necessary.
 *
 * RETURN:        None
 *
 * NOTE:
 *        This routine is called a interrupt time by lbmIODone
 */
static void lmPostGC(struct lbuf * bp)
{
        unsigned long flags;
        struct jfs_log *log = bp->l_log;
        struct logpage *lp;
        struct tblock *tblk, *temp;

        //LOGGC_LOCK(log);
        spin_lock_irqsave(&log->gclock, flags);
        /*
         * current pageout of group commit completed.
         *
         * remove/wakeup transactions from commit queue who were
         * group committed with the current log page
         */
        list_for_each_entry_safe(tblk, temp, &log->cqueue, cqueue) {
                if (!(tblk->flag & tblkGC_COMMIT))
                        break;
                /* if transaction was marked GC_COMMIT then
                 * it has been shipped in the current pageout
                 * and made it to disk - it is committed.
                 */

                if (bp->l_flag & lbmERROR)
                        tblk->flag |= tblkGC_ERROR;

                /* remove it from the commit queue */
                list_del(&tblk->cqueue);
                tblk->flag &= ~tblkGC_QUEUE;

                if (tblk == log->flush_tblk) {
                        /* we can stop flushing the log now */
                        clear_bit(log_FLUSH, &log->flag);
                        log->flush_tblk = NULL;
                }

                jfs_info("lmPostGC: tblk = 0x%p, flag = 0x%x", tblk,
                         tblk->flag);

                if (!(tblk->xflag & COMMIT_FORCE))
                        /*
                         * Hand tblk over to lazy commit thread
                         */
                        txLazyUnlock(tblk);
                else {
                        /* state transition: COMMIT -> COMMITTED */
                        tblk->flag |= tblkGC_COMMITTED;

                        if (tblk->flag & tblkGC_READY)
                                log->gcrtc--;

                        LOGGC_WAKEUP(tblk);
                }

                /* was page full before pageout ?
                 * (and this is the last tblk bound with the page)
                 */
                if (tblk->flag & tblkGC_FREE)
                        lbmFree(bp);
                /* did page become full after pageout ?
                 * (and this is the last tblk bound with the page)
                 */
                else if (tblk->flag & tblkGC_EOP) {
                        /* finalize the page */
                        lp = (struct logpage *) bp->l_ldata;
                        bp->l_ceor = bp->l_eor;
                        lp->h.eor = lp->t.eor = cpu_to_le16(bp->l_eor);
                        jfs_info("lmPostGC: calling lbmWrite");
                        lbmWrite(log, bp, lbmWRITE | lbmRELEASE | lbmFREE,
                                 1);
                }

        }

        /* are there any transactions who have entered lnGroupCommit()
         * (whose COMMITs are after that of the last log page written.
         * They are waiting for new group commit (above at (SLEEP 1))
         * or lazy transactions are on a full (queued) log page,
         * select the latest ready transaction as new group leader and
         * wake her up to lead her group.
         */
        if ((!list_empty(&log->cqueue)) &&
            ((log->gcrtc > 0) || (tblk->bp->l_wqnext != NULL) ||
             test_bit(log_FLUSH, &log->flag) || jfs_tlocks_low))
                /*
                 * Call lmGCwrite with new group leader
                 */
                lmGCwrite(log, 1);

        /* no transaction are ready yet (transactions are only just
         * queued (GC_QUEUE) and not entered for group commit yet).
         * the first transaction entering group commit
         * will elect herself as new group leader.
         */
        else
                log->cflag &= ~logGC_PAGEOUT;

        //LOGGC_UNLOCK(log);
        spin_unlock_irqrestore(&log->gclock, flags);
        return;
}

/*
 * NAME:        lmLogSync()
 *
 * FUNCTION:        write log SYNCPT record for specified log
 *        if new sync address is available
 *        (normally the case if sync() is executed by back-ground
 *        process).
 *        calculate new value of i_nextsync which determines when
 *        this code is called again.
 *
 * PARAMETERS:        log        - log structure
 *                hard_sync - 1 to force all metadata to be written
 *
 * RETURN:        0
 *
 * serialization: LOG_LOCK() held on entry/exit
 */
static int lmLogSync(struct jfs_log * log, int hard_sync)
{
        int logsize;
        int written;                /* written since last syncpt */
        int free;                /* free space left available */
        int delta;                /* additional delta to write normally */
        int more;                /* additional write granted */
        struct lrd lrd;
        int lsn;
        struct logsyncblk *lp;
        unsigned long flags;

        /* push dirty metapages out to disk */
        if (hard_sync)
                write_special_inodes(log, filemap_fdatawrite);
        else
                write_special_inodes(log, filemap_flush);

        /*
         *        forward syncpt
         */
        /* if last sync is same as last syncpt,
         * invoke sync point forward processing to update sync.
         */

        if (log->sync == log->syncpt) {
                LOGSYNC_LOCK(log, flags);
                if (list_empty(&log->synclist))
                        log->sync = log->lsn;
                else {
                        lp = list_entry(log->synclist.next,
                                        struct logsyncblk, synclist);
                        log->sync = lp->lsn;
                }
                LOGSYNC_UNLOCK(log, flags);

        }

        /* if sync is different from last syncpt,
         * write a SYNCPT record with syncpt = sync.
         * reset syncpt = sync
         */
        if (log->sync != log->syncpt) {
                lrd.logtid = 0;
                lrd.backchain = 0;
                lrd.type = cpu_to_le16(LOG_SYNCPT);
                lrd.length = 0;
                lrd.log.syncpt.sync = cpu_to_le32(log->sync);
                lsn = lmWriteRecord(log, NULL, &lrd, NULL);

                log->syncpt = log->sync;
        } else
                lsn = log->lsn;

        /*
         *        setup next syncpt trigger (SWAG)
         */
        logsize = log->logsize;

        logdiff(written, lsn, log);
        free = logsize - written;
        delta = LOGSYNC_DELTA(logsize);
        more = min(free / 2, delta);
        if (more < 2 * LOGPSIZE) {
                jfs_warn("\n ... Log Wrap ... Log Wrap ... Log Wrap ...\n");
                /*
                 *        log wrapping
                 *
                 * option 1 - panic ? No.!
                 * option 2 - shutdown file systems
                 *              associated with log ?
                 * option 3 - extend log ?
                 * option 4 - second chance
                 *
                 * mark log wrapped, and continue.
                 * when all active transactions are completed,
                 * mark log valid for recovery.
                 * if crashed during invalid state, log state
                 * implies invalid log, forcing fsck().
                 */
                /* mark log state log wrap in log superblock */
                /* log->state = LOGWRAP; */

                /* reset sync point computation */
                log->syncpt = log->sync = lsn;
                log->nextsync = delta;
        } else
                /* next syncpt trigger = written + more */
                log->nextsync = written + more;

        /* if number of bytes written from last sync point is more
         * than 1/4 of the log size, stop new transactions from
         * starting until all current transactions are completed
         * by setting syncbarrier flag.
         */
        if (!test_bit(log_SYNCBARRIER, &log->flag) &&
            (written > LOGSYNC_BARRIER(logsize)) && log->active) {
                set_bit(log_SYNCBARRIER, &log->flag);
                jfs_info("log barrier on: lsn=0x%x syncpt=0x%x", lsn,
                         log->syncpt);
                /*
                 * We may have to initiate group commit
                 */
                jfs_flush_journal(log, 0);
        }

        return lsn;
}

/*
 * NAME:        jfs_syncpt
 *
 * FUNCTION:        write log SYNCPT record for specified log
 *
 * PARAMETERS:        log          - log structure
 *                hard_sync - set to 1 to force metadata to be written
 */
void jfs_syncpt(struct jfs_log *log, int hard_sync)
{        LOG_LOCK(log);
        if (!test_bit(log_QUIESCE, &log->flag))
                lmLogSync(log, hard_sync);
        LOG_UNLOCK(log);
}

/*
 * NAME:        lmLogOpen()
 *
 * FUNCTION:        open the log on first open;
 *        insert filesystem in the active list of the log.
 *
 * PARAMETER:        ipmnt        - file system mount inode
 *                iplog        - log inode (out)
 *
 * RETURN:
 *
 * serialization:
 */
int lmLogOpen(struct super_block *sb)
{
        int rc;
        struct file *bdev_file;
        struct jfs_log *log;
        struct jfs_sb_info *sbi = JFS_SBI(sb);

        if (sbi->flag & JFS_NOINTEGRITY)
                return open_dummy_log(sb);

        if (sbi->mntflag & JFS_INLINELOG)
                return open_inline_log(sb);

        mutex_lock(&jfs_log_mutex);
        list_for_each_entry(log, &jfs_external_logs, journal_list) {
                if (file_bdev(log->bdev_file)->bd_dev == sbi->logdev) {
                        if (!uuid_equal(&log->uuid, &sbi->loguuid)) {
                                jfs_warn("wrong uuid on JFS journal");
                                mutex_unlock(&jfs_log_mutex);
                                return -EINVAL;
                        }
                        /*
                         * add file system to log active file system list
                         */
                        if ((rc = lmLogFileSystem(log, sbi, 1))) {
                                mutex_unlock(&jfs_log_mutex);
                                return rc;
                        }
                        goto journal_found;
                }
        }

        if (!(log = kzalloc(sizeof(struct jfs_log), GFP_KERNEL))) {
                mutex_unlock(&jfs_log_mutex);
                return -ENOMEM;
        }
        INIT_LIST_HEAD(&log->sb_list);
        init_waitqueue_head(&log->syncwait);

        /*
         *        external log as separate logical volume
         *
         * file systems to log may have n-to-1 relationship;
         */

        bdev_file = bdev_file_open_by_dev(sbi->logdev,
                        BLK_OPEN_READ | BLK_OPEN_WRITE, log, NULL);
        if (IS_ERR(bdev_file)) {
                rc = PTR_ERR(bdev_file);
                goto free;
        }

        log->bdev_file = bdev_file;
        uuid_copy(&log->uuid, &sbi->loguuid);

        /*
         * initialize log:
         */
        if ((rc = lmLogInit(log)))
                goto close;

        list_add(&log->journal_list, &jfs_external_logs);

        /*
         * add file system to log active file system list
         */
        if ((rc = lmLogFileSystem(log, sbi, 1)))
                goto shutdown;

journal_found:
        LOG_LOCK(log);
        list_add(&sbi->log_list, &log->sb_list);
        sbi->log = log;
        LOG_UNLOCK(log);

        mutex_unlock(&jfs_log_mutex);
        return 0;

        /*
         *        unwind on error
         */
      shutdown:                /* unwind lbmLogInit() */
        list_del(&log->journal_list);
        lbmLogShutdown(log);

      close:                /* close external log device */
        bdev_fput(bdev_file);

      free:                /* free log descriptor */
        mutex_unlock(&jfs_log_mutex);
        kfree(log);

        jfs_warn("lmLogOpen: exit(%d)", rc);
        return rc;
}

static int open_inline_log(struct super_block *sb)
{
        struct jfs_log *log;
        int rc;

        if (!(log = kzalloc(sizeof(struct jfs_log), GFP_KERNEL)))
                return -ENOMEM;
        INIT_LIST_HEAD(&log->sb_list);
        init_waitqueue_head(&log->syncwait);

        set_bit(log_INLINELOG, &log->flag);
        log->bdev_file = sb->s_bdev_file;
        log->base = addressPXD(&JFS_SBI(sb)->logpxd);
        log->size = lengthPXD(&JFS_SBI(sb)->logpxd) >>
            (L2LOGPSIZE - sb->s_blocksize_bits);
        log->l2bsize = sb->s_blocksize_bits;
        ASSERT(L2LOGPSIZE >= sb->s_blocksize_bits);

        /*
         * initialize log.
         */
        if ((rc = lmLogInit(log))) {
                kfree(log);
                jfs_warn("lmLogOpen: exit(%d)", rc);
                return rc;
        }

        list_add(&JFS_SBI(sb)->log_list, &log->sb_list);
        JFS_SBI(sb)->log = log;

        return rc;
}

static int open_dummy_log(struct super_block *sb)
{
        int rc;

        mutex_lock(&jfs_log_mutex);
        if (!dummy_log) {
                dummy_log = kzalloc(sizeof(struct jfs_log), GFP_KERNEL);
                if (!dummy_log) {
                        mutex_unlock(&jfs_log_mutex);
                        return -ENOMEM;
                }
                INIT_LIST_HEAD(&dummy_log->sb_list);
                init_waitqueue_head(&dummy_log->syncwait);
                dummy_log->no_integrity = 1;
                /* Make up some stuff */
                dummy_log->base = 0;
                dummy_log->size = 1024;
                rc = lmLogInit(dummy_log);
                if (rc) {
                        kfree(dummy_log);
                        dummy_log = NULL;
                        mutex_unlock(&jfs_log_mutex);
                        return rc;
                }
        }

        LOG_LOCK(dummy_log);
        list_add(&JFS_SBI(sb)->log_list, &dummy_log->sb_list);
        JFS_SBI(sb)->log = dummy_log;
        LOG_UNLOCK(dummy_log);
        mutex_unlock(&jfs_log_mutex);

        return 0;
}

/*
 * NAME:        lmLogInit()
 *
 * FUNCTION:        log initialization at first log open.
 *
 *        logredo() (or logformat()) should have been run previously.
 *        initialize the log from log superblock.
 *        set the log state in the superblock to LOGMOUNT and
 *        write SYNCPT log record.
 *
 * PARAMETER:        log        - log structure
 *
 * RETURN:        0        - if ok
 *                -EINVAL        - bad log magic number or superblock dirty
 *                error returned from logwait()
 *
 * serialization: single first open thread
 */
int lmLogInit(struct jfs_log * log)
{
        int rc = 0;
        struct lrd lrd;
        struct logsuper *logsuper;
        struct lbuf *bpsuper;
        struct lbuf *bp;
        struct logpage *lp;
        int lsn = 0;

        jfs_info("lmLogInit: log:0x%p", log);

        /* initialize the group commit serialization lock */
        LOGGC_LOCK_INIT(log);

        /* allocate/initialize the log write serialization lock */
        LOG_LOCK_INIT(log);

        LOGSYNC_LOCK_INIT(log);

        INIT_LIST_HEAD(&log->synclist);

        INIT_LIST_HEAD(&log->cqueue);
        log->flush_tblk = NULL;

        log->count = 0;

        /*
         * initialize log i/o
         */
        if ((rc = lbmLogInit(log)))
                return rc;

        if (!test_bit(log_INLINELOG, &log->flag))
                log->l2bsize = L2LOGPSIZE;

        /* check for disabled journaling to disk */
        if (log->no_integrity) {
                /*
                 * Journal pages will still be filled.  When the time comes
                 * to actually do the I/O, the write is not done, and the
                 * endio routine is called directly.
                 */
                bp = lbmAllocate(log , 0);
                log->bp = bp;
                bp->l_pn = bp->l_eor = 0;
        } else {
                /*
                 * validate log superblock
                 */
                if ((rc = lbmRead(log, 1, &bpsuper)))
                        goto errout10;

                logsuper = (struct logsuper *) bpsuper->l_ldata;

                if (logsuper->magic != cpu_to_le32(LOGMAGIC)) {
                        jfs_warn("*** Log Format Error ! ***");
                        rc = -EINVAL;
                        goto errout20;
                }

                /* logredo() should have been run successfully. */
                if (logsuper->state != cpu_to_le32(LOGREDONE)) {
                        jfs_warn("*** Log Is Dirty ! ***");
                        rc = -EINVAL;
                        goto errout20;
                }

                /* initialize log from log superblock */
                if (test_bit(log_INLINELOG,&log->flag)) {
                        if (log->size != le32_to_cpu(logsuper->size)) {
                                rc = -EINVAL;
                                goto errout20;
                        }
                        jfs_info("lmLogInit: inline log:0x%p base:0x%Lx size:0x%x",
                                 log, (unsigned long long)log->base, log->size);
                } else {
                        if (!uuid_equal(&logsuper->uuid, &log->uuid)) {
                                jfs_warn("wrong uuid on JFS log device");
                                rc = -EINVAL;
                                goto errout20;
                        }
                        log->size = le32_to_cpu(logsuper->size);
                        log->l2bsize = le32_to_cpu(logsuper->l2bsize);
                        jfs_info("lmLogInit: external log:0x%p base:0x%Lx size:0x%x",
                                 log, (unsigned long long)log->base, log->size);
                }

                log->page = le32_to_cpu(logsuper->end) / LOGPSIZE;
                log->eor = le32_to_cpu(logsuper->end) - (LOGPSIZE * log->page);

                /*
                 * initialize for log append write mode
                 */
                /* establish current/end-of-log page/buffer */
                if ((rc = lbmRead(log, log->page, &bp)))
                        goto errout20;

                lp = (struct logpage *) bp->l_ldata;

                jfs_info("lmLogInit: lsn:0x%x page:%d eor:%d:%d",
                         le32_to_cpu(logsuper->end), log->page, log->eor,
                         le16_to_cpu(lp->h.eor));

                log->bp = bp;
                bp->l_pn = log->page;
                bp->l_eor = log->eor;

                /* if current page is full, move on to next page */
                if (log->eor >= LOGPSIZE - LOGPTLRSIZE)
                        lmNextPage(log);

                /*
                 * initialize log syncpoint
                 */
                /*
                 * write the first SYNCPT record with syncpoint = 0
                 * (i.e., log redo up to HERE !);
                 * remove current page from lbm write queue at end of pageout
                 * (to write log superblock update), but do not release to
                 * freelist;
                 */
                lrd.logtid = 0;
                lrd.backchain = 0;
                lrd.type = cpu_to_le16(LOG_SYNCPT);
                lrd.length = 0;
                lrd.log.syncpt.sync = 0;
                lsn = lmWriteRecord(log, NULL, &lrd, NULL);
                bp = log->bp;
                bp->l_ceor = bp->l_eor;
                lp = (struct logpage *) bp->l_ldata;
                lp->h.eor = lp->t.eor = cpu_to_le16(bp->l_eor);
                lbmWrite(log, bp, lbmWRITE | lbmSYNC, 0);
                if ((rc = lbmIOWait(bp, 0)))
                        goto errout30;

                /*
                 * update/write superblock
                 */
                logsuper->state = cpu_to_le32(LOGMOUNT);
                log->serial = le32_to_cpu(logsuper->serial) + 1;
                logsuper->serial = cpu_to_le32(log->serial);
                lbmDirectWrite(log, bpsuper, lbmWRITE | lbmRELEASE | lbmSYNC);
                if ((rc = lbmIOWait(bpsuper, lbmFREE)))
                        goto errout30;
        }

        /* initialize logsync parameters */
        log->logsize = (log->size - 2) << L2LOGPSIZE;
        log->lsn = lsn;
        log->syncpt = lsn;
        log->sync = log->syncpt;
        log->nextsync = LOGSYNC_DELTA(log->logsize);

        jfs_info("lmLogInit: lsn:0x%x syncpt:0x%x sync:0x%x",
                 log->lsn, log->syncpt, log->sync);

        /*
         * initialize for lazy/group commit
         */
        log->clsn = lsn;

        return 0;

        /*
         *        unwind on error
         */
      errout30:                /* release log page */
        log->wqueue = NULL;
        bp->l_wqnext = NULL;
        lbmFree(bp);

      errout20:                /* release log superblock */
        lbmFree(bpsuper);

      errout10:                /* unwind lbmLogInit() */
        lbmLogShutdown(log);

        jfs_warn("lmLogInit: exit(%d)", rc);
        return rc;
}


/*
 * NAME:        lmLogClose()
 *
 * FUNCTION:        remove file system <ipmnt> from active list of log <iplog>
 *                and close it on last close.
 *
 * PARAMETER:        sb        - superblock
 *
 * RETURN:        errors from subroutines
 *
 * serialization:
 */
int lmLogClose(struct super_block *sb)
{
        struct jfs_sb_info *sbi = JFS_SBI(sb);
        struct jfs_log *log = sbi->log;
        struct file *bdev_file;
        int rc = 0;

        jfs_info("lmLogClose: log:0x%p", log);

        mutex_lock(&jfs_log_mutex);
        LOG_LOCK(log);
        list_del(&sbi->log_list);
        LOG_UNLOCK(log);
        sbi->log = NULL;

        /*
         * We need to make sure all of the "written" metapages
         * actually make it to disk
         */
        sync_blockdev(sb->s_bdev);

        if (test_bit(log_INLINELOG, &log->flag)) {
                /*
                 *        in-line log in host file system
                 */
                rc = lmLogShutdown(log);
                kfree(log);
                goto out;
        }

        if (!log->no_integrity)
                lmLogFileSystem(log, sbi, 0);

        if (!list_empty(&log->sb_list))
                goto out;

        /*
         * TODO: ensure that the dummy_log is in a state to allow
         * lbmLogShutdown to deallocate all the buffers and call
         * kfree against dummy_log.  For now, leave dummy_log & its
         * buffers in memory, and resuse if another no-integrity mount
         * is requested.
         */
        if (log->no_integrity)
                goto out;

        /*
         *        external log as separate logical volume
         */
        list_del(&log->journal_list);
        bdev_file = log->bdev_file;
        rc = lmLogShutdown(log);

        bdev_fput(bdev_file);

        kfree(log);

      out:
        mutex_unlock(&jfs_log_mutex);
        jfs_info("lmLogClose: exit(%d)", rc);
        return rc;
}


/*
 * NAME:        jfs_flush_journal()
 *
 * FUNCTION:        initiate write of any outstanding transactions to the journal
 *                and optionally wait until they are all written to disk
 *
 *                wait == 0  flush until latest txn is committed, don't wait
 *                wait == 1  flush until latest txn is committed, wait
 *                wait > 1   flush until all txn's are complete, wait
 */
void jfs_flush_journal(struct jfs_log *log, int wait)
{
        int i;
        struct tblock *target = NULL;

        /* jfs_write_inode may call us during read-only mount */
        if (!log)
                return;

        jfs_info("jfs_flush_journal: log:0x%p wait=%d", log, wait);

        LOGGC_LOCK(log);

        if (!list_empty(&log->cqueue)) {
                /*
                 * This ensures that we will keep writing to the journal as long
                 * as there are unwritten commit records
                 */
                target = list_entry(log->cqueue.prev, struct tblock, cqueue);

                if (test_bit(log_FLUSH, &log->flag)) {
                        /*
                         * We're already flushing.
                         * if flush_tblk is NULL, we are flushing everything,
                         * so leave it that way.  Otherwise, update it to the
                         * latest transaction
                         */
                        if (log->flush_tblk)
                                log->flush_tblk = target;
                } else {
                        /* Only flush until latest transaction is committed */
                        log->flush_tblk = target;
                        set_bit(log_FLUSH, &log->flag);

                        /*
                         * Initiate I/O on outstanding transactions
                         */
                        if (!(log->cflag & logGC_PAGEOUT)) {
                                log->cflag |= logGC_PAGEOUT;
                                lmGCwrite(log, 0);
                        }
                }
        }
        if ((wait > 1) || test_bit(log_SYNCBARRIER, &log->flag)) {
                /* Flush until all activity complete */
                set_bit(log_FLUSH, &log->flag);
                log->flush_tblk = NULL;
        }

        if (wait && target && !(target->flag & tblkGC_COMMITTED)) {
                DECLARE_WAITQUEUE(__wait, current);

                add_wait_queue(&target->gcwait, &__wait);
                set_current_state(TASK_UNINTERRUPTIBLE);
                LOGGC_UNLOCK(log);
                schedule();
                LOGGC_LOCK(log);
                remove_wait_queue(&target->gcwait, &__wait);
        }
        LOGGC_UNLOCK(log);

        if (wait < 2)
                return;

        write_special_inodes(log, filemap_fdatawrite);

        /*
         * If there was recent activity, we may need to wait
         * for the lazycommit thread to catch up
         */
        if ((!list_empty(&log->cqueue)) || !list_empty(&log->synclist)) {
                for (i = 0; i < 200; i++) {        /* Too much? */
                        msleep(250);
                        write_special_inodes(log, filemap_fdatawrite);
                        if (list_empty(&log->cqueue) &&
                            list_empty(&log->synclist))
                                break;
                }
        }
        assert(list_empty(&log->cqueue));

#ifdef CONFIG_JFS_DEBUG
        if (!list_empty(&log->synclist)) {
                struct logsyncblk *lp;

                printk(KERN_ERR "jfs_flush_journal: synclist not empty\n");
                list_for_each_entry(lp, &log->synclist, synclist) {
                        if (lp->xflag & COMMIT_PAGE) {
                                struct metapage *mp = (struct metapage *)lp;
                                print_hex_dump(KERN_ERR, "metapage: ",
                                               DUMP_PREFIX_ADDRESS, 16, 4,
                                               mp, sizeof(struct metapage), 0);
                                print_hex_dump(KERN_ERR, "page: ",
                                               DUMP_PREFIX_ADDRESS, 16,
                                               sizeof(long), mp->folio,
                                               sizeof(struct page), 0);
                        } else
                                print_hex_dump(KERN_ERR, "tblock:",
                                               DUMP_PREFIX_ADDRESS, 16, 4,
                                               lp, sizeof(struct tblock), 0);
                }
        }
#else
        WARN_ON(!list_empty(&log->synclist));
#endif
        clear_bit(log_FLUSH, &log->flag);
}

/*
 * NAME:        lmLogShutdown()
 *
 * FUNCTION:        log shutdown at last LogClose().
 *
 *                write log syncpt record.
 *                update super block to set redone flag to 0.
 *
 * PARAMETER:        log        - log inode
 *
 * RETURN:        0        - success
 *
 * serialization: single last close thread
 */
int lmLogShutdown(struct jfs_log * log)
{
        int rc;
        struct lrd lrd;
        int lsn;
        struct logsuper *logsuper;
        struct lbuf *bpsuper;
        struct lbuf *bp;
        struct logpage *lp;

        jfs_info("lmLogShutdown: log:0x%p", log);

        jfs_flush_journal(log, 2);

        /*
         * write the last SYNCPT record with syncpoint = 0
         * (i.e., log redo up to HERE !)
         */
        lrd.logtid = 0;
        lrd.backchain = 0;
        lrd.type = cpu_to_le16(LOG_SYNCPT);
        lrd.length = 0;
        lrd.log.syncpt.sync = 0;

        lsn = lmWriteRecord(log, NULL, &lrd, NULL);
        bp = log->bp;
        lp = (struct logpage *) bp->l_ldata;
        lp->h.eor = lp->t.eor = cpu_to_le16(bp->l_eor);
        lbmWrite(log, log->bp, lbmWRITE | lbmRELEASE | lbmSYNC, 0);
        lbmIOWait(log->bp, lbmFREE);
        log->bp = NULL;

        /*
         * synchronous update log superblock
         * mark log state as shutdown cleanly
         * (i.e., Log does not need to be replayed).
         */
        if ((rc = lbmRead(log, 1, &bpsuper)))
                goto out;

        logsuper = (struct logsuper *) bpsuper->l_ldata;
        logsuper->state = cpu_to_le32(LOGREDONE);
        logsuper->end = cpu_to_le32(lsn);
        lbmDirectWrite(log, bpsuper, lbmWRITE | lbmRELEASE | lbmSYNC);
        rc = lbmIOWait(bpsuper, lbmFREE);

        jfs_info("lmLogShutdown: lsn:0x%x page:%d eor:%d",
                 lsn, log->page, log->eor);

      out:
        /*
         * shutdown per log i/o
         */
        lbmLogShutdown(log);

        if (rc) {
                jfs_warn("lmLogShutdown: exit(%d)", rc);
        }
        return rc;
}


/*
 * NAME:        lmLogFileSystem()
 *
 * FUNCTION:        insert (<activate> = true)/remove (<activate> = false)
 *        file system into/from log active file system list.
 *
 * PARAMETE:        log        - pointer to logs inode.
 *                fsdev        - kdev_t of filesystem.
 *                serial        - pointer to returned log serial number
 *                activate - insert/remove device from active list.
 *
 * RETURN:        0        - success
 *                errors returned by vms_iowait().
 */
static int lmLogFileSystem(struct jfs_log * log, struct jfs_sb_info *sbi,
                           int activate)
{
        int rc = 0;
        int i;
        struct logsuper *logsuper;
        struct lbuf *bpsuper;
        uuid_t *uuid = &sbi->uuid;

        /*
         * insert/remove file system device to log active file system list.
         */
        if ((rc = lbmRead(log, 1, &bpsuper)))
                return rc;

        logsuper = (struct logsuper *) bpsuper->l_ldata;
        if (activate) {
                for (i = 0; i < MAX_ACTIVE; i++)
                        if (uuid_is_null(&logsuper->active[i].uuid)) {
                                uuid_copy(&logsuper->active[i].uuid, uuid);
                                sbi->aggregate = i;
                                break;
                        }
                if (i == MAX_ACTIVE) {
                        jfs_warn("Too many file systems sharing journal!");
                        lbmFree(bpsuper);
                        return -EMFILE;        /* Is there a better rc? */
                }
        } else {
                for (i = 0; i < MAX_ACTIVE; i++)
                        if (uuid_equal(&logsuper->active[i].uuid, uuid)) {
                                uuid_copy(&logsuper->active[i].uuid,
                                          &uuid_null);
                                break;
                        }
                if (i == MAX_ACTIVE) {
                        jfs_warn("Somebody stomped on the journal!");
                        lbmFree(bpsuper);
                        return -EIO;
                }

        }

        /*
         * synchronous write log superblock:
         *
         * write sidestream bypassing write queue:
         * at file system mount, log super block is updated for
         * activation of the file system before any log record
         * (MOUNT record) of the file system, and at file system
         * unmount, all meta data for the file system has been
         * flushed before log super block is updated for deactivation
         * of the file system.
         */
        lbmDirectWrite(log, bpsuper, lbmWRITE | lbmRELEASE | lbmSYNC);
        rc = lbmIOWait(bpsuper, lbmFREE);

        return rc;
}

/*
 *                log buffer manager (lbm)
 *                ------------------------
 *
 * special purpose buffer manager supporting log i/o requirements.
 *
 * per log write queue:
 * log pageout occurs in serial order by fifo write queue and
 * restricting to a single i/o in pregress at any one time.
 * a circular singly-linked list
 * (log->wrqueue points to the tail, and buffers are linked via
 * bp->wrqueue field), and
 * maintains log page in pageout ot waiting for pageout in serial pageout.
 */

/*
 *        lbmLogInit()
 *
 * initialize per log I/O setup at lmLogInit()
 */
static int lbmLogInit(struct jfs_log * log)
{                                /* log inode */
        int i;
        struct lbuf *lbuf;

        jfs_info("lbmLogInit: log:0x%p", log);

        /* initialize current buffer cursor */
        log->bp = NULL;

        /* initialize log device write queue */
        log->wqueue = NULL;

        /*
         * Each log has its own buffer pages allocated to it.  These are
         * not managed by the page cache.  This ensures that a transaction
         * writing to the log does not block trying to allocate a page from
         * the page cache (for the log).  This would be bad, since page
         * allocation waits on the kswapd thread that may be committing inodes
         * which would cause log activity.  Was that clear?  I'm trying to
         * avoid deadlock here.
         */
        init_waitqueue_head(&log->free_wait);

        log->lbuf_free = NULL;

        for (i = 0; i < LOGPAGES;) {
                char *buffer;
                uint offset;
                struct page *page = alloc_page(GFP_KERNEL | __GFP_ZERO);

                if (!page)
                        goto error;
                buffer = page_address(page);
                for (offset = 0; offset < PAGE_SIZE; offset += LOGPSIZE) {
                        lbuf = kmalloc(sizeof(struct lbuf), GFP_KERNEL);
                        if (lbuf == NULL) {
                                if (offset == 0)
                                        __free_page(page);
                                goto error;
                        }
                        if (offset) /* we already have one reference */
                                get_page(page);
                        lbuf->l_offset = offset;
                        lbuf->l_ldata = buffer + offset;
                        lbuf->l_page = page;
                        lbuf->l_log = log;
                        init_waitqueue_head(&lbuf->l_ioevent);

                        lbuf->l_freelist = log->lbuf_free;
                        log->lbuf_free = lbuf;
                        i++;
                }
        }

        return (0);

      error:
        lbmLogShutdown(log);
        return -ENOMEM;
}


/*
 *        lbmLogShutdown()
 *
 * finalize per log I/O setup at lmLogShutdown()
 */
static void lbmLogShutdown(struct jfs_log * log)
{
        struct lbuf *lbuf;

        jfs_info("lbmLogShutdown: log:0x%p", log);

        lbuf = log->lbuf_free;
        while (lbuf) {
                struct lbuf *next = lbuf->l_freelist;
                __free_page(lbuf->l_page);
                kfree(lbuf);
                lbuf = next;
        }
}


/*
 *        lbmAllocate()
 *
 * allocate an empty log buffer
 */
static struct lbuf *lbmAllocate(struct jfs_log * log, int pn)
{
        struct lbuf *bp;
        unsigned long flags;

        /*
         * recycle from log buffer freelist if any
         */
        LCACHE_LOCK(flags);
        LCACHE_SLEEP_COND(log->free_wait, (bp = log->lbuf_free), flags);
        log->lbuf_free = bp->l_freelist;
        LCACHE_UNLOCK(flags);

        bp->l_flag = 0;

        bp->l_wqnext = NULL;
        bp->l_freelist = NULL;

        bp->l_pn = pn;
        bp->l_blkno = log->base + (pn << (L2LOGPSIZE - log->l2bsize));
        bp->l_ceor = 0;

        return bp;
}


/*
 *        lbmFree()
 *
 * release a log buffer to freelist
 */
static void lbmFree(struct lbuf * bp)
{
        unsigned long flags;

        LCACHE_LOCK(flags);

        lbmfree(bp);

        LCACHE_UNLOCK(flags);
}

static void lbmfree(struct lbuf * bp)
{
        struct jfs_log *log = bp->l_log;

        assert(bp->l_wqnext == NULL);

        /*
         * return the buffer to head of freelist
         */
        bp->l_freelist = log->lbuf_free;
        log->lbuf_free = bp;

        wake_up(&log->free_wait);
        return;
}


/*
 * NAME:        lbmRedrive
 *
 * FUNCTION:        add a log buffer to the log redrive list
 *
 * PARAMETER:
 *        bp        - log buffer
 *
 * NOTES:
 *        Takes log_redrive_lock.
 */
static inline void lbmRedrive(struct lbuf *bp)
{
        unsigned long flags;

        spin_lock_irqsave(&log_redrive_lock, flags);
        bp->l_redrive_next = log_redrive_list;
        log_redrive_list = bp;
        spin_unlock_irqrestore(&log_redrive_lock, flags);

        wake_up_process(jfsIOthread);
}


/*
 *        lbmRead()
 */
static int lbmRead(struct jfs_log * log, int pn, struct lbuf ** bpp)
{
        struct bio *bio;
        struct lbuf *bp;

        /*
         * allocate a log buffer
         */
        *bpp = bp = lbmAllocate(log, pn);
        jfs_info("lbmRead: bp:0x%p pn:0x%x", bp, pn);

        bp->l_flag |= lbmREAD;

        bio = bio_alloc(file_bdev(log->bdev_file), 1, REQ_OP_READ, GFP_NOFS);
        bio->bi_iter.bi_sector = bp->l_blkno << (log->l2bsize - 9);
        __bio_add_page(bio, bp->l_page, LOGPSIZE, bp->l_offset);
        BUG_ON(bio->bi_iter.bi_size != LOGPSIZE);

        bio->bi_end_io = lbmIODone;
        bio->bi_private = bp;
        /*check if journaling to disk has been disabled*/
        if (log->no_integrity) {
                bio->bi_iter.bi_size = 0;
                lbmIODone(bio);
        } else {
                submit_bio(bio);
        }

        wait_event(bp->l_ioevent, (bp->l_flag != lbmREAD));

        return 0;
}


/*
 *        lbmWrite()
 *
 * buffer at head of pageout queue stays after completion of
 * partial-page pageout and redriven by explicit initiation of
 * pageout by caller until full-page pageout is completed and
 * released.
 *
 * device driver i/o done redrives pageout of new buffer at
 * head of pageout queue when current buffer at head of pageout
 * queue is released at the completion of its full-page pageout.
 *
 * LOGGC_LOCK() serializes lbmWrite() by lmNextPage() and lmGroupCommit().
 * LCACHE_LOCK() serializes xflag between lbmWrite() and lbmIODone()
 */
static void lbmWrite(struct jfs_log * log, struct lbuf * bp, int flag,
                     int cant_block)
{
        struct lbuf *tail;
        unsigned long flags;

        jfs_info("lbmWrite: bp:0x%p flag:0x%x pn:0x%x", bp, flag, bp->l_pn);

        /* map the logical block address to physical block address */
        bp->l_blkno =
            log->base + (bp->l_pn << (L2LOGPSIZE - log->l2bsize));

        LCACHE_LOCK(flags);                /* disable+lock */

        /*
         * initialize buffer for device driver
         */
        bp->l_flag = flag;

        /*
         *        insert bp at tail of write queue associated with log
         *
         * (request is either for bp already/currently at head of queue
         * or new bp to be inserted at tail)
         */
        tail = log->wqueue;

        /* is buffer not already on write queue ? */
        if (bp->l_wqnext == NULL) {
                /* insert at tail of wqueue */
                if (tail == NULL) {
                        log->wqueue = bp;
                        bp->l_wqnext = bp;
                } else {
                        log->wqueue = bp;
                        bp->l_wqnext = tail->l_wqnext;
                        tail->l_wqnext = bp;
                }

                tail = bp;
        }

        /* is buffer at head of wqueue and for write ? */
        if ((bp != tail->l_wqnext) || !(flag & lbmWRITE)) {
                LCACHE_UNLOCK(flags);        /* unlock+enable */
                return;
        }

        LCACHE_UNLOCK(flags);        /* unlock+enable */

        if (cant_block)
                lbmRedrive(bp);
        else if (flag & lbmSYNC)
                lbmStartIO(bp);
        else {
                LOGGC_UNLOCK(log);
                lbmStartIO(bp);
                LOGGC_LOCK(log);
        }
}


/*
 *        lbmDirectWrite()
 *
 * initiate pageout bypassing write queue for sidestream
 * (e.g., log superblock) write;
 */
static void lbmDirectWrite(struct jfs_log * log, struct lbuf * bp, int flag)
{
        jfs_info("lbmDirectWrite: bp:0x%p flag:0x%x pn:0x%x",
                 bp, flag, bp->l_pn);

        /*
         * initialize buffer for device driver
         */
        bp->l_flag = flag | lbmDIRECT;

        /* map the logical block address to physical block address */
        bp->l_blkno =
            log->base + (bp->l_pn << (L2LOGPSIZE - log->l2bsize));

        /*
         *        initiate pageout of the page
         */
        lbmStartIO(bp);
}


/*
 * NAME:        lbmStartIO()
 *
 * FUNCTION:        Interface to DD strategy routine
 *
 * RETURN:        none
 *
 * serialization: LCACHE_LOCK() is NOT held during log i/o;
 */
static void lbmStartIO(struct lbuf * bp)
{
        struct bio *bio;
        struct jfs_log *log = bp->l_log;
        struct block_device *bdev = NULL;

        jfs_info("lbmStartIO");

        if (!log->no_integrity)
                bdev = file_bdev(log->bdev_file);

        bio = bio_alloc(bdev, 1, REQ_OP_WRITE | REQ_SYNC,
                        GFP_NOFS);
        bio->bi_iter.bi_sector = bp->l_blkno << (log->l2bsize - 9);
        __bio_add_page(bio, bp->l_page, LOGPSIZE, bp->l_offset);
        BUG_ON(bio->bi_iter.bi_size != LOGPSIZE);

        bio->bi_end_io = lbmIODone;
        bio->bi_private = bp;

        /* check if journaling to disk has been disabled */
        if (log->no_integrity) {
                bio->bi_iter.bi_size = 0;
                lbmIODone(bio);
        } else {
                submit_bio(bio);
                INCREMENT(lmStat.submitted);
        }
}


/*
 *        lbmIOWait()
 */
static int lbmIOWait(struct lbuf * bp, int flag)
{
        unsigned long flags;
        int rc = 0;

        jfs_info("lbmIOWait1: bp:0x%p flag:0x%x:0x%x", bp, bp->l_flag, flag);

        LCACHE_LOCK(flags);                /* disable+lock */

        LCACHE_SLEEP_COND(bp->l_ioevent, (bp->l_flag & lbmDONE), flags);

        rc = (bp->l_flag & lbmERROR) ? -EIO : 0;

        if (flag & lbmFREE)
                lbmfree(bp);

        LCACHE_UNLOCK(flags);        /* unlock+enable */

        jfs_info("lbmIOWait2: bp:0x%p flag:0x%x:0x%x", bp, bp->l_flag, flag);
        return rc;
}

/*
 *        lbmIODone()
 *
 * executed at INTIODONE level
 */
static void lbmIODone(struct bio *bio)
{
        struct lbuf *bp = bio->bi_private;
        struct lbuf *nextbp, *tail;
        struct jfs_log *log;
        unsigned long flags;

        /*
         * get back jfs buffer bound to the i/o buffer
         */
        jfs_info("lbmIODone: bp:0x%p flag:0x%x", bp, bp->l_flag);

        LCACHE_LOCK(flags);                /* disable+lock */

        bp->l_flag |= lbmDONE;

        if (bio->bi_status) {
                bp->l_flag |= lbmERROR;

                jfs_err("lbmIODone: I/O error in JFS log");
        }

        bio_put(bio);

        /*
         *        pagein completion
         */
        if (bp->l_flag & lbmREAD) {
                bp->l_flag &= ~lbmREAD;

                LCACHE_UNLOCK(flags);        /* unlock+enable */

                /* wakeup I/O initiator */
                LCACHE_WAKEUP(&bp->l_ioevent);

                return;
        }

        /*
         *        pageout completion
         *
         * the bp at the head of write queue has completed pageout.
         *
         * if single-commit/full-page pageout, remove the current buffer
         * from head of pageout queue, and redrive pageout with
         * the new buffer at head of pageout queue;
         * otherwise, the partial-page pageout buffer stays at
         * the head of pageout queue to be redriven for pageout
         * by lmGroupCommit() until full-page pageout is completed.
         */
        bp->l_flag &= ~lbmWRITE;
        INCREMENT(lmStat.pagedone);

        /* update committed lsn */
        log = bp->l_log;
        log->clsn = (bp->l_pn << L2LOGPSIZE) + bp->l_ceor;

        if (bp->l_flag & lbmDIRECT) {
                LCACHE_WAKEUP(&bp->l_ioevent);
                LCACHE_UNLOCK(flags);
                return;
        }

        tail = log->wqueue;

        /* single element queue */
        if (bp == tail) {
                /* remove head buffer of full-page pageout
                 * from log device write queue
                 */
                if (bp->l_flag & lbmRELEASE) {
                        log->wqueue = NULL;
                        bp->l_wqnext = NULL;
                }
        }
        /* multi element queue */
        else {
                /* remove head buffer of full-page pageout
                 * from log device write queue
                 */
                if (bp->l_flag & lbmRELEASE) {
                        nextbp = tail->l_wqnext = bp->l_wqnext;
                        bp->l_wqnext = NULL;

                        /*
                         * redrive pageout of next page at head of write queue:
                         * redrive next page without any bound tblk
                         * (i.e., page w/o any COMMIT records), or
                         * first page of new group commit which has been
                         * queued after current page (subsequent pageout
                         * is performed synchronously, except page without
                         * any COMMITs) by lmGroupCommit() as indicated
                         * by lbmWRITE flag;
                         */
                        if (nextbp->l_flag & lbmWRITE) {
                                /*
                                 * We can't do the I/O at interrupt time.
                                 * The jfsIO thread can do it
                                 */
                                lbmRedrive(nextbp);
                        }
                }
        }

        /*
         *        synchronous pageout:
         *
         * buffer has not necessarily been removed from write queue
         * (e.g., synchronous write of partial-page with COMMIT):
         * leave buffer for i/o initiator to dispose
         */
        if (bp->l_flag & lbmSYNC) {
                LCACHE_UNLOCK(flags);        /* unlock+enable */

                /* wakeup I/O initiator */
                LCACHE_WAKEUP(&bp->l_ioevent);
        }

        /*
         *        Group Commit pageout:
         */
        else if (bp->l_flag & lbmGC) {
                LCACHE_UNLOCK(flags);
                lmPostGC(bp);
        }

        /*
         *        asynchronous pageout:
         *
         * buffer must have been removed from write queue:
         * insert buffer at head of freelist where it can be recycled
         */
        else {
                assert(bp->l_flag & lbmRELEASE);
                assert(bp->l_flag & lbmFREE);
                lbmfree(bp);

                LCACHE_UNLOCK(flags);        /* unlock+enable */
        }
}

int jfsIOWait(void *arg)
{
        struct lbuf *bp;

        do {
                spin_lock_irq(&log_redrive_lock);
                while ((bp = log_redrive_list)) {
                        log_redrive_list = bp->l_redrive_next;
                        bp->l_redrive_next = NULL;
                        spin_unlock_irq(&log_redrive_lock);
                        lbmStartIO(bp);
                        spin_lock_irq(&log_redrive_lock);
                }

                if (freezing(current)) {
                        spin_unlock_irq(&log_redrive_lock);
                        try_to_freeze();
                } else {
                        set_current_state(TASK_INTERRUPTIBLE);
                        spin_unlock_irq(&log_redrive_lock);
                        schedule();
                }
        } while (!kthread_should_stop());

        jfs_info("jfsIOWait being killed!");
        return 0;
}

/*
 * NAME:        lmLogFormat()/jfs_logform()
 *
 * FUNCTION:        format file system log
 *
 * PARAMETERS:
 *        log        - volume log
 *        logAddress - start address of log space in FS block
 *        logSize        - length of log space in FS block;
 *
 * RETURN:        0        - success
 *                -EIO        - i/o error
 *
 * XXX: We're synchronously writing one page at a time.  This needs to
 *        be improved by writing multiple pages at once.
 */
int lmLogFormat(struct jfs_log *log, s64 logAddress, int logSize)
{
        int rc = -EIO;
        struct jfs_sb_info *sbi;
        struct logsuper *logsuper;
        struct logpage *lp;
        int lspn;                /* log sequence page number */
        struct lrd *lrd_ptr;
        int npages = 0;
        struct lbuf *bp;

        jfs_info("lmLogFormat: logAddress:%Ld logSize:%d",
                 (long long)logAddress, logSize);

        sbi = list_entry(log->sb_list.next, struct jfs_sb_info, log_list);

        /* allocate a log buffer */
        bp = lbmAllocate(log, 1);

        npages = logSize >> sbi->l2nbperpage;

        /*
         *        log space:
         *
         * page 0 - reserved;
         * page 1 - log superblock;
         * page 2 - log data page: A SYNC log record is written
         *            into this page at logform time;
         * pages 3-N - log data page: set to empty log data pages;
         */
        /*
         *        init log superblock: log page 1
         */
        logsuper = (struct logsuper *) bp->l_ldata;

        logsuper->magic = cpu_to_le32(LOGMAGIC);
        logsuper->version = cpu_to_le32(LOGVERSION);
        logsuper->state = cpu_to_le32(LOGREDONE);
        logsuper->flag = cpu_to_le32(sbi->mntflag);        /* ? */
        logsuper->size = cpu_to_le32(npages);
        logsuper->bsize = cpu_to_le32(sbi->bsize);
        logsuper->l2bsize = cpu_to_le32(sbi->l2bsize);
        logsuper->end = cpu_to_le32(2 * LOGPSIZE + LOGPHDRSIZE + LOGRDSIZE);

        bp->l_flag = lbmWRITE | lbmSYNC | lbmDIRECT;
        bp->l_blkno = logAddress + sbi->nbperpage;
        lbmStartIO(bp);
        if ((rc = lbmIOWait(bp, 0)))
                goto exit;

        /*
         *        init pages 2 to npages-1 as log data pages:
         *
         * log page sequence number (lpsn) initialization:
         *
         * pn:   0     1     2     3                 n-1
         *       +-----+-----+=====+=====+===.....===+=====+
         * lspn:             N-1   0     1           N-2
         *                   <--- N page circular file ---->
         *
         * the N (= npages-2) data pages of the log is maintained as
         * a circular file for the log records;
         * lpsn grows by 1 monotonically as each log page is written
         * to the circular file of the log;
         * and setLogpage() will not reset the page number even if
         * the eor is equal to LOGPHDRSIZE. In order for binary search
         * still work in find log end process, we have to simulate the
         * log wrap situation at the log format time.
         * The 1st log page written will have the highest lpsn. Then
         * the succeeding log pages will have ascending order of
         * the lspn starting from 0, ... (N-2)
         */
        lp = (struct logpage *) bp->l_ldata;
        /*
         * initialize 1st log page to be written: lpsn = N - 1,
         * write a SYNCPT log record is written to this page
         */
        lp->h.page = lp->t.page = cpu_to_le32(npages - 3);
        lp->h.eor = lp->t.eor = cpu_to_le16(LOGPHDRSIZE + LOGRDSIZE);

        lrd_ptr = (struct lrd *) &lp->data;
        lrd_ptr->logtid = 0;
        lrd_ptr->backchain = 0;
        lrd_ptr->type = cpu_to_le16(LOG_SYNCPT);
        lrd_ptr->length = 0;
        lrd_ptr->log.syncpt.sync = 0;

        bp->l_blkno += sbi->nbperpage;
        bp->l_flag = lbmWRITE | lbmSYNC | lbmDIRECT;
        lbmStartIO(bp);
        if ((rc = lbmIOWait(bp, 0)))
                goto exit;

        /*
         *        initialize succeeding log pages: lpsn = 0, 1, ..., (N-2)
         */
        for (lspn = 0; lspn < npages - 3; lspn++) {
                lp->h.page = lp->t.page = cpu_to_le32(lspn);
                lp->h.eor = lp->t.eor = cpu_to_le16(LOGPHDRSIZE);

                bp->l_blkno += sbi->nbperpage;
                bp->l_flag = lbmWRITE | lbmSYNC | lbmDIRECT;
                lbmStartIO(bp);
                if ((rc = lbmIOWait(bp, 0)))
                        goto exit;
        }

        rc = 0;
exit:
        /*
         *        finalize log
         */
        /* release the buffer */
        lbmFree(bp);

        return rc;
}

#ifdef CONFIG_JFS_STATISTICS
int jfs_lmstats_proc_show(struct seq_file *m, void *v)
{
        seq_printf(m,
                       "JFS Logmgr stats\n"
                       "================\n"
                       "commits = %d\n"
                       "writes submitted = %d\n"
                       "writes completed = %d\n"
                       "full pages submitted = %d\n"
                       "partial pages submitted = %d\n",
                       lmStat.commit,
                       lmStat.submitted,
                       lmStat.pagedone,
                       lmStat.full_page,
                       lmStat.partial_page);
        return 0;
}
#endif /* CONFIG_JFS_STATISTICS */



























































































































































    1 



    1 































    1 








    1 



















    1 





























    1 








    1 



















    1 























    1 








    1 
















    1 






















    1 








    1 








    1 




















    1 























    1 







    1 







    1 

















    1 


























    5 
    5 















    5 







    5 

















    5 



















    1 










































































































































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
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
// SPDX-License-Identifier: GPL-2.0-or-later
/*
 * ChaCha20-Poly1305 AEAD, RFC7539
 *
 * Copyright (C) 2015 Martin Willi
 */

#include <crypto/internal/aead.h>
#include <crypto/internal/hash.h>
#include <crypto/internal/skcipher.h>
#include <crypto/scatterwalk.h>
#include <crypto/chacha.h>
#include <crypto/poly1305.h>
#include <linux/err.h>
#include <linux/init.h>
#include <linux/kernel.h>
#include <linux/module.h>

struct chachapoly_instance_ctx {
        struct crypto_skcipher_spawn chacha;
        struct crypto_ahash_spawn poly;
        unsigned int saltlen;
};

struct chachapoly_ctx {
        struct crypto_skcipher *chacha;
        struct crypto_ahash *poly;
        /* key bytes we use for the ChaCha20 IV */
        unsigned int saltlen;
        u8 salt[] __counted_by(saltlen);
};

struct poly_req {
        /* zero byte padding for AD/ciphertext, as needed */
        u8 pad[POLY1305_BLOCK_SIZE];
        /* tail data with AD/ciphertext lengths */
        struct {
                __le64 assoclen;
                __le64 cryptlen;
        } tail;
        struct scatterlist src[1];
        struct ahash_request req; /* must be last member */
};

struct chacha_req {
        u8 iv[CHACHA_IV_SIZE];
        struct scatterlist src[1];
        struct skcipher_request req; /* must be last member */
};

struct chachapoly_req_ctx {
        struct scatterlist src[2];
        struct scatterlist dst[2];
        /* the key we generate for Poly1305 using Chacha20 */
        u8 key[POLY1305_KEY_SIZE];
        /* calculated Poly1305 tag */
        u8 tag[POLY1305_DIGEST_SIZE];
        /* length of data to en/decrypt, without ICV */
        unsigned int cryptlen;
        /* Actual AD, excluding IV */
        unsigned int assoclen;
        /* request flags, with MAY_SLEEP cleared if needed */
        u32 flags;
        union {
                struct poly_req poly;
                struct chacha_req chacha;
        } u;
};

static inline void async_done_continue(struct aead_request *req, int err,
                                       int (*cont)(struct aead_request *))
{
        if (!err) {
                struct chachapoly_req_ctx *rctx = aead_request_ctx(req);

                rctx->flags &= ~CRYPTO_TFM_REQ_MAY_SLEEP;
                err = cont(req);
        }

        if (err != -EINPROGRESS && err != -EBUSY)
                aead_request_complete(req, err);
}

static void chacha_iv(u8 *iv, struct aead_request *req, u32 icb)
{
        struct chachapoly_ctx *ctx = crypto_aead_ctx(crypto_aead_reqtfm(req));
        __le32 leicb = cpu_to_le32(icb);

        memcpy(iv, &leicb, sizeof(leicb));
        memcpy(iv + sizeof(leicb), ctx->salt, ctx->saltlen);
        memcpy(iv + sizeof(leicb) + ctx->saltlen, req->iv,
               CHACHA_IV_SIZE - sizeof(leicb) - ctx->saltlen);
}

static int poly_verify_tag(struct aead_request *req)
{
        struct chachapoly_req_ctx *rctx = aead_request_ctx(req);
        u8 tag[sizeof(rctx->tag)];

        scatterwalk_map_and_copy(tag, req->src,
                                 req->assoclen + rctx->cryptlen,
                                 sizeof(tag), 0);
        if (crypto_memneq(tag, rctx->tag, sizeof(tag)))
                return -EBADMSG;
        return 0;
}

static int poly_copy_tag(struct aead_request *req)
{
        struct chachapoly_req_ctx *rctx = aead_request_ctx(req);

        scatterwalk_map_and_copy(rctx->tag, req->dst,
                                 req->assoclen + rctx->cryptlen,
                                 sizeof(rctx->tag), 1);
        return 0;
}

static void chacha_decrypt_done(void *data, int err)
{
        async_done_continue(data, err, poly_verify_tag);
}

static int chacha_decrypt(struct aead_request *req)
{
        struct chachapoly_ctx *ctx = crypto_aead_ctx(crypto_aead_reqtfm(req));
        struct chachapoly_req_ctx *rctx = aead_request_ctx(req);
        struct chacha_req *creq = &rctx->u.chacha;
        struct scatterlist *src, *dst;
        int err;

        if (rctx->cryptlen == 0)
                goto skip;

        chacha_iv(creq->iv, req, 1);

        src = scatterwalk_ffwd(rctx->src, req->src, req->assoclen);
        dst = src;
        if (req->src != req->dst)
                dst = scatterwalk_ffwd(rctx->dst, req->dst, req->assoclen);

        skcipher_request_set_callback(&creq->req, rctx->flags,
                                      chacha_decrypt_done, req);
        skcipher_request_set_tfm(&creq->req, ctx->chacha);
        skcipher_request_set_crypt(&creq->req, src, dst,
                                   rctx->cryptlen, creq->iv);
        err = crypto_skcipher_decrypt(&creq->req);
        if (err)
                return err;

skip:
        return poly_verify_tag(req);
}

static int poly_tail_continue(struct aead_request *req)
{
        struct chachapoly_req_ctx *rctx = aead_request_ctx(req);

        if (rctx->cryptlen == req->cryptlen) /* encrypting */
                return poly_copy_tag(req);

        return chacha_decrypt(req);
}

static void poly_tail_done(void *data, int err)
{
        async_done_continue(data, err, poly_tail_continue);
}

static int poly_tail(struct aead_request *req)
{
        struct crypto_aead *tfm = crypto_aead_reqtfm(req);
        struct chachapoly_ctx *ctx = crypto_aead_ctx(tfm);
        struct chachapoly_req_ctx *rctx = aead_request_ctx(req);
        struct poly_req *preq = &rctx->u.poly;
        int err;

        preq->tail.assoclen = cpu_to_le64(rctx->assoclen);
        preq->tail.cryptlen = cpu_to_le64(rctx->cryptlen);
        sg_init_one(preq->src, &preq->tail, sizeof(preq->tail));

        ahash_request_set_callback(&preq->req, rctx->flags,
                                   poly_tail_done, req);
        ahash_request_set_tfm(&preq->req, ctx->poly);
        ahash_request_set_crypt(&preq->req, preq->src,
                                rctx->tag, sizeof(preq->tail));

        err = crypto_ahash_finup(&preq->req);
        if (err)
                return err;

        return poly_tail_continue(req);
}

static void poly_cipherpad_done(void *data, int err)
{
        async_done_continue(data, err, poly_tail);
}

static int poly_cipherpad(struct aead_request *req)
{
        struct chachapoly_ctx *ctx = crypto_aead_ctx(crypto_aead_reqtfm(req));
        struct chachapoly_req_ctx *rctx = aead_request_ctx(req);
        struct poly_req *preq = &rctx->u.poly;
        unsigned int padlen;
        int err;

        padlen = -rctx->cryptlen % POLY1305_BLOCK_SIZE;
        memset(preq->pad, 0, sizeof(preq->pad));
        sg_init_one(preq->src, preq->pad, padlen);

        ahash_request_set_callback(&preq->req, rctx->flags,
                                   poly_cipherpad_done, req);
        ahash_request_set_tfm(&preq->req, ctx->poly);
        ahash_request_set_crypt(&preq->req, preq->src, NULL, padlen);

        err = crypto_ahash_update(&preq->req);
        if (err)
                return err;

        return poly_tail(req);
}

static void poly_cipher_done(void *data, int err)
{
        async_done_continue(data, err, poly_cipherpad);
}

static int poly_cipher(struct aead_request *req)
{
        struct chachapoly_ctx *ctx = crypto_aead_ctx(crypto_aead_reqtfm(req));
        struct chachapoly_req_ctx *rctx = aead_request_ctx(req);
        struct poly_req *preq = &rctx->u.poly;
        struct scatterlist *crypt = req->src;
        int err;

        if (rctx->cryptlen == req->cryptlen) /* encrypting */
                crypt = req->dst;

        crypt = scatterwalk_ffwd(rctx->src, crypt, req->assoclen);

        ahash_request_set_callback(&preq->req, rctx->flags,
                                   poly_cipher_done, req);
        ahash_request_set_tfm(&preq->req, ctx->poly);
        ahash_request_set_crypt(&preq->req, crypt, NULL, rctx->cryptlen);

        err = crypto_ahash_update(&preq->req);
        if (err)
                return err;

        return poly_cipherpad(req);
}

static void poly_adpad_done(void *data, int err)
{
        async_done_continue(data, err, poly_cipher);
}

static int poly_adpad(struct aead_request *req)
{
        struct chachapoly_ctx *ctx = crypto_aead_ctx(crypto_aead_reqtfm(req));
        struct chachapoly_req_ctx *rctx = aead_request_ctx(req);
        struct poly_req *preq = &rctx->u.poly;
        unsigned int padlen;
        int err;

        padlen = -rctx->assoclen % POLY1305_BLOCK_SIZE;
        memset(preq->pad, 0, sizeof(preq->pad));
        sg_init_one(preq->src, preq->pad, padlen);

        ahash_request_set_callback(&preq->req, rctx->flags,
                                   poly_adpad_done, req);
        ahash_request_set_tfm(&preq->req, ctx->poly);
        ahash_request_set_crypt(&preq->req, preq->src, NULL, padlen);

        err = crypto_ahash_update(&preq->req);
        if (err)
                return err;

        return poly_cipher(req);
}

static void poly_ad_done(void *data, int err)
{
        async_done_continue(data, err, poly_adpad);
}

static int poly_ad(struct aead_request *req)
{
        struct chachapoly_ctx *ctx = crypto_aead_ctx(crypto_aead_reqtfm(req));
        struct chachapoly_req_ctx *rctx = aead_request_ctx(req);
        struct poly_req *preq = &rctx->u.poly;
        int err;

        ahash_request_set_callback(&preq->req, rctx->flags,
                                   poly_ad_done, req);
        ahash_request_set_tfm(&preq->req, ctx->poly);
        ahash_request_set_crypt(&preq->req, req->src, NULL, rctx->assoclen);

        err = crypto_ahash_update(&preq->req);
        if (err)
                return err;

        return poly_adpad(req);
}

static void poly_setkey_done(void *data, int err)
{
        async_done_continue(data, err, poly_ad);
}

static int poly_setkey(struct aead_request *req)
{
        struct chachapoly_ctx *ctx = crypto_aead_ctx(crypto_aead_reqtfm(req));
        struct chachapoly_req_ctx *rctx = aead_request_ctx(req);
        struct poly_req *preq = &rctx->u.poly;
        int err;

        sg_init_one(preq->src, rctx->key, sizeof(rctx->key));

        ahash_request_set_callback(&preq->req, rctx->flags,
                                   poly_setkey_done, req);
        ahash_request_set_tfm(&preq->req, ctx->poly);
        ahash_request_set_crypt(&preq->req, preq->src, NULL, sizeof(rctx->key));

        err = crypto_ahash_update(&preq->req);
        if (err)
                return err;

        return poly_ad(req);
}

static void poly_init_done(void *data, int err)
{
        async_done_continue(data, err, poly_setkey);
}

static int poly_init(struct aead_request *req)
{
        struct chachapoly_ctx *ctx = crypto_aead_ctx(crypto_aead_reqtfm(req));
        struct chachapoly_req_ctx *rctx = aead_request_ctx(req);
        struct poly_req *preq = &rctx->u.poly;
        int err;

        ahash_request_set_callback(&preq->req, rctx->flags,
                                   poly_init_done, req);
        ahash_request_set_tfm(&preq->req, ctx->poly);

        err = crypto_ahash_init(&preq->req);
        if (err)
                return err;

        return poly_setkey(req);
}

static void poly_genkey_done(void *data, int err)
{
        async_done_continue(data, err, poly_init);
}

static int poly_genkey(struct aead_request *req)
{
        struct crypto_aead *tfm = crypto_aead_reqtfm(req);
        struct chachapoly_ctx *ctx = crypto_aead_ctx(tfm);
        struct chachapoly_req_ctx *rctx = aead_request_ctx(req);
        struct chacha_req *creq = &rctx->u.chacha;
        int err;

        rctx->assoclen = req->assoclen;

        if (crypto_aead_ivsize(tfm) == 8) {
                if (rctx->assoclen < 8)
                        return -EINVAL;
                rctx->assoclen -= 8;
        }

        memset(rctx->key, 0, sizeof(rctx->key));
        sg_init_one(creq->src, rctx->key, sizeof(rctx->key));

        chacha_iv(creq->iv, req, 0);

        skcipher_request_set_callback(&creq->req, rctx->flags,
                                      poly_genkey_done, req);
        skcipher_request_set_tfm(&creq->req, ctx->chacha);
        skcipher_request_set_crypt(&creq->req, creq->src, creq->src,
                                   POLY1305_KEY_SIZE, creq->iv);

        err = crypto_skcipher_decrypt(&creq->req);
        if (err)
                return err;

        return poly_init(req);
}

static void chacha_encrypt_done(void *data, int err)
{
        async_done_continue(data, err, poly_genkey);
}

static int chacha_encrypt(struct aead_request *req)
{
        struct chachapoly_ctx *ctx = crypto_aead_ctx(crypto_aead_reqtfm(req));
        struct chachapoly_req_ctx *rctx = aead_request_ctx(req);
        struct chacha_req *creq = &rctx->u.chacha;
        struct scatterlist *src, *dst;
        int err;

        if (req->cryptlen == 0)
                goto skip;

        chacha_iv(creq->iv, req, 1);

        src = scatterwalk_ffwd(rctx->src, req->src, req->assoclen);
        dst = src;
        if (req->src != req->dst)
                dst = scatterwalk_ffwd(rctx->dst, req->dst, req->assoclen);

        skcipher_request_set_callback(&creq->req, rctx->flags,
                                      chacha_encrypt_done, req);
        skcipher_request_set_tfm(&creq->req, ctx->chacha);
        skcipher_request_set_crypt(&creq->req, src, dst,
                                   req->cryptlen, creq->iv);
        err = crypto_skcipher_encrypt(&creq->req);
        if (err)
                return err;

skip:
        return poly_genkey(req);
}

static int chachapoly_encrypt(struct aead_request *req)
{
        struct chachapoly_req_ctx *rctx = aead_request_ctx(req);

        rctx->cryptlen = req->cryptlen;
        rctx->flags = aead_request_flags(req);

        /* encrypt call chain:
         * - chacha_encrypt/done()
         * - poly_genkey/done()
         * - poly_init/done()
         * - poly_setkey/done()
         * - poly_ad/done()
         * - poly_adpad/done()
         * - poly_cipher/done()
         * - poly_cipherpad/done()
         * - poly_tail/done/continue()
         * - poly_copy_tag()
         */
        return chacha_encrypt(req);
}

static int chachapoly_decrypt(struct aead_request *req)
{
        struct chachapoly_req_ctx *rctx = aead_request_ctx(req);

        rctx->cryptlen = req->cryptlen - POLY1305_DIGEST_SIZE;
        rctx->flags = aead_request_flags(req);

        /* decrypt call chain:
         * - poly_genkey/done()
         * - poly_init/done()
         * - poly_setkey/done()
         * - poly_ad/done()
         * - poly_adpad/done()
         * - poly_cipher/done()
         * - poly_cipherpad/done()
         * - poly_tail/done/continue()
         * - chacha_decrypt/done()
         * - poly_verify_tag()
         */
        return poly_genkey(req);
}

static int chachapoly_setkey(struct crypto_aead *aead, const u8 *key,
                             unsigned int keylen)
{
        struct chachapoly_ctx *ctx = crypto_aead_ctx(aead);

        if (keylen != ctx->saltlen + CHACHA_KEY_SIZE)
                return -EINVAL;

        keylen -= ctx->saltlen;
        memcpy(ctx->salt, key + keylen, ctx->saltlen);

        crypto_skcipher_clear_flags(ctx->chacha, CRYPTO_TFM_REQ_MASK);
        crypto_skcipher_set_flags(ctx->chacha, crypto_aead_get_flags(aead) &
                                               CRYPTO_TFM_REQ_MASK);
        return crypto_skcipher_setkey(ctx->chacha, key, keylen);
}

static int chachapoly_setauthsize(struct crypto_aead *tfm,
                                  unsigned int authsize)
{
        if (authsize != POLY1305_DIGEST_SIZE)
                return -EINVAL;

        return 0;
}

static int chachapoly_init(struct crypto_aead *tfm)
{
        struct aead_instance *inst = aead_alg_instance(tfm);
        struct chachapoly_instance_ctx *ictx = aead_instance_ctx(inst);
        struct chachapoly_ctx *ctx = crypto_aead_ctx(tfm);
        struct crypto_skcipher *chacha;
        struct crypto_ahash *poly;
        unsigned long align;

        poly = crypto_spawn_ahash(&ictx->poly);
        if (IS_ERR(poly))
                return PTR_ERR(poly);

        chacha = crypto_spawn_skcipher(&ictx->chacha);
        if (IS_ERR(chacha)) {
                crypto_free_ahash(poly);
                return PTR_ERR(chacha);
        }

        ctx->chacha = chacha;
        ctx->poly = poly;
        ctx->saltlen = ictx->saltlen;

        align = crypto_aead_alignmask(tfm);
        align &= ~(crypto_tfm_ctx_alignment() - 1);
        crypto_aead_set_reqsize(
                tfm,
                align + offsetof(struct chachapoly_req_ctx, u) +
                max(offsetof(struct chacha_req, req) +
                    sizeof(struct skcipher_request) +
                    crypto_skcipher_reqsize(chacha),
                    offsetof(struct poly_req, req) +
                    sizeof(struct ahash_request) +
                    crypto_ahash_reqsize(poly)));

        return 0;
}

static void chachapoly_exit(struct crypto_aead *tfm)
{
        struct chachapoly_ctx *ctx = crypto_aead_ctx(tfm);

        crypto_free_ahash(ctx->poly);
        crypto_free_skcipher(ctx->chacha);
}

static void chachapoly_free(struct aead_instance *inst)
{
        struct chachapoly_instance_ctx *ctx = aead_instance_ctx(inst);

        crypto_drop_skcipher(&ctx->chacha);
        crypto_drop_ahash(&ctx->poly);
        kfree(inst);
}

static int chachapoly_create(struct crypto_template *tmpl, struct rtattr **tb,
                             const char *name, unsigned int ivsize)
{
        u32 mask;
        struct aead_instance *inst;
        struct chachapoly_instance_ctx *ctx;
        struct skcipher_alg_common *chacha;
        struct hash_alg_common *poly;
        int err;

        if (ivsize > CHACHAPOLY_IV_SIZE)
                return -EINVAL;

        err = crypto_check_attr_type(tb, CRYPTO_ALG_TYPE_AEAD, &mask);
        if (err)
                return err;

        inst = kzalloc(sizeof(*inst) + sizeof(*ctx), GFP_KERNEL);
        if (!inst)
                return -ENOMEM;
        ctx = aead_instance_ctx(inst);
        ctx->saltlen = CHACHAPOLY_IV_SIZE - ivsize;

        err = crypto_grab_skcipher(&ctx->chacha, aead_crypto_instance(inst),
                                   crypto_attr_alg_name(tb[1]), 0, mask);
        if (err)
                goto err_free_inst;
        chacha = crypto_spawn_skcipher_alg_common(&ctx->chacha);

        err = crypto_grab_ahash(&ctx->poly, aead_crypto_instance(inst),
                                crypto_attr_alg_name(tb[2]), 0, mask);
        if (err)
                goto err_free_inst;
        poly = crypto_spawn_ahash_alg(&ctx->poly);

        err = -EINVAL;
        if (poly->digestsize != POLY1305_DIGEST_SIZE)
                goto err_free_inst;
        /* Need 16-byte IV size, including Initial Block Counter value */
        if (chacha->ivsize != CHACHA_IV_SIZE)
                goto err_free_inst;
        /* Not a stream cipher? */
        if (chacha->base.cra_blocksize != 1)
                goto err_free_inst;

        err = -ENAMETOOLONG;
        if (snprintf(inst->alg.base.cra_name, CRYPTO_MAX_ALG_NAME,
                     "%s(%s,%s)", name, chacha->base.cra_name,
                     poly->base.cra_name) >= CRYPTO_MAX_ALG_NAME)
                goto err_free_inst;
        if (snprintf(inst->alg.base.cra_driver_name, CRYPTO_MAX_ALG_NAME,
                     "%s(%s,%s)", name, chacha->base.cra_driver_name,
                     poly->base.cra_driver_name) >= CRYPTO_MAX_ALG_NAME)
                goto err_free_inst;

        inst->alg.base.cra_priority = (chacha->base.cra_priority +
                                       poly->base.cra_priority) / 2;
        inst->alg.base.cra_blocksize = 1;
        inst->alg.base.cra_alignmask = chacha->base.cra_alignmask;
        inst->alg.base.cra_ctxsize = sizeof(struct chachapoly_ctx) +
                                     ctx->saltlen;
        inst->alg.ivsize = ivsize;
        inst->alg.chunksize = chacha->chunksize;
        inst->alg.maxauthsize = POLY1305_DIGEST_SIZE;
        inst->alg.init = chachapoly_init;
        inst->alg.exit = chachapoly_exit;
        inst->alg.encrypt = chachapoly_encrypt;
        inst->alg.decrypt = chachapoly_decrypt;
        inst->alg.setkey = chachapoly_setkey;
        inst->alg.setauthsize = chachapoly_setauthsize;

        inst->free = chachapoly_free;

        err = aead_register_instance(tmpl, inst);
        if (err) {
err_free_inst:
                chachapoly_free(inst);
        }
        return err;
}

static int rfc7539_create(struct crypto_template *tmpl, struct rtattr **tb)
{
        return chachapoly_create(tmpl, tb, "rfc7539", 12);
}

static int rfc7539esp_create(struct crypto_template *tmpl, struct rtattr **tb)
{
        return chachapoly_create(tmpl, tb, "rfc7539esp", 8);
}

static struct crypto_template rfc7539_tmpls[] = {
        {
                .name = "rfc7539",
                .create = rfc7539_create,
                .module = THIS_MODULE,
        }, {
                .name = "rfc7539esp",
                .create = rfc7539esp_create,
                .module = THIS_MODULE,
        },
};

static int __init chacha20poly1305_module_init(void)
{
        return crypto_register_templates(rfc7539_tmpls,
                                         ARRAY_SIZE(rfc7539_tmpls));
}

static void __exit chacha20poly1305_module_exit(void)
{
        crypto_unregister_templates(rfc7539_tmpls,
                                    ARRAY_SIZE(rfc7539_tmpls));
}

subsys_initcall(chacha20poly1305_module_init);
module_exit(chacha20poly1305_module_exit);

MODULE_LICENSE("GPL");
MODULE_AUTHOR("Martin Willi <martin@strongswan.org>");
MODULE_DESCRIPTION("ChaCha20-Poly1305 AEAD");
MODULE_ALIAS_CRYPTO("rfc7539");
MODULE_ALIAS_CRYPTO("rfc7539esp");

























































   19 

  109 


   59 
















































































    1 


    1 
















































    6 
  170 



  127 
   69 

















































































































































   18 


   17 





    5 


    6 





































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
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
/* SPDX-License-Identifier: GPL-2.0 */
#ifndef __NET_UDP_TUNNEL_H
#define __NET_UDP_TUNNEL_H

#include <net/ip_tunnels.h>
#include <net/udp.h>

#if IS_ENABLED(CONFIG_IPV6)
#include <net/ipv6.h>
#include <net/ipv6_stubs.h>
#endif

struct udp_port_cfg {
        u8                        family;

        /* Used only for kernel-created sockets */
        union {
                struct in_addr                local_ip;
#if IS_ENABLED(CONFIG_IPV6)
                struct in6_addr                local_ip6;
#endif
        };

        union {
                struct in_addr                peer_ip;
#if IS_ENABLED(CONFIG_IPV6)
                struct in6_addr                peer_ip6;
#endif
        };

        __be16                        local_udp_port;
        __be16                        peer_udp_port;
        int                        bind_ifindex;
        unsigned int                use_udp_checksums:1,
                                use_udp6_tx_checksums:1,
                                use_udp6_rx_checksums:1,
                                ipv6_v6only:1;
};

int udp_sock_create4(struct net *net, struct udp_port_cfg *cfg,
                     struct socket **sockp);

#if IS_ENABLED(CONFIG_IPV6)
int udp_sock_create6(struct net *net, struct udp_port_cfg *cfg,
                     struct socket **sockp);
#else
static inline int udp_sock_create6(struct net *net, struct udp_port_cfg *cfg,
                                   struct socket **sockp)
{
        return 0;
}
#endif

static inline int udp_sock_create(struct net *net,
                                  struct udp_port_cfg *cfg,
                                  struct socket **sockp)
{
        if (cfg->family == AF_INET)
                return udp_sock_create4(net, cfg, sockp);

        if (cfg->family == AF_INET6)
                return udp_sock_create6(net, cfg, sockp);

        return -EPFNOSUPPORT;
}

typedef int (*udp_tunnel_encap_rcv_t)(struct sock *sk, struct sk_buff *skb);
typedef int (*udp_tunnel_encap_err_lookup_t)(struct sock *sk,
                                             struct sk_buff *skb);
typedef void (*udp_tunnel_encap_err_rcv_t)(struct sock *sk,
                                           struct sk_buff *skb, int err,
                                           __be16 port, u32 info, u8 *payload);
typedef void (*udp_tunnel_encap_destroy_t)(struct sock *sk);
typedef struct sk_buff *(*udp_tunnel_gro_receive_t)(struct sock *sk,
                                                    struct list_head *head,
                                                    struct sk_buff *skb);
typedef int (*udp_tunnel_gro_complete_t)(struct sock *sk, struct sk_buff *skb,
                                         int nhoff);

struct udp_tunnel_sock_cfg {
        void *sk_user_data;     /* user data used by encap_rcv call back */
        /* Used for setting up udp_sock fields, see udp.h for details */
        __u8  encap_type;
        udp_tunnel_encap_rcv_t encap_rcv;
        udp_tunnel_encap_err_lookup_t encap_err_lookup;
        udp_tunnel_encap_err_rcv_t encap_err_rcv;
        udp_tunnel_encap_destroy_t encap_destroy;
        udp_tunnel_gro_receive_t gro_receive;
        udp_tunnel_gro_complete_t gro_complete;
};

/* Setup the given (UDP) sock to receive UDP encapsulated packets */
void setup_udp_tunnel_sock(struct net *net, struct socket *sock,
                           struct udp_tunnel_sock_cfg *sock_cfg);

/* -- List of parsable UDP tunnel types --
 *
 * Adding to this list will result in serious debate.  The main issue is
 * that this list is essentially a list of workarounds for either poorly
 * designed tunnels, or poorly designed device offloads.
 *
 * The parsing supported via these types should really be used for Rx
 * traffic only as the network stack will have already inserted offsets for
 * the location of the headers in the skb.  In addition any ports that are
 * pushed should be kept within the namespace without leaking to other
 * devices such as VFs or other ports on the same device.
 *
 * It is strongly encouraged to use CHECKSUM_COMPLETE for Rx to avoid the
 * need to use this for Rx checksum offload.  It should not be necessary to
 * call this function to perform Tx offloads on outgoing traffic.
 */
enum udp_parsable_tunnel_type {
        UDP_TUNNEL_TYPE_VXLAN          = BIT(0), /* RFC 7348 */
        UDP_TUNNEL_TYPE_GENEVE          = BIT(1), /* draft-ietf-nvo3-geneve */
        UDP_TUNNEL_TYPE_VXLAN_GPE = BIT(2), /* draft-ietf-nvo3-vxlan-gpe */
};

struct udp_tunnel_info {
        unsigned short type;
        sa_family_t sa_family;
        __be16 port;
        u8 hw_priv;
};

/* Notify network devices of offloadable types */
void udp_tunnel_push_rx_port(struct net_device *dev, struct socket *sock,
                             unsigned short type);
void udp_tunnel_drop_rx_port(struct net_device *dev, struct socket *sock,
                             unsigned short type);
void udp_tunnel_notify_add_rx_port(struct socket *sock, unsigned short type);
void udp_tunnel_notify_del_rx_port(struct socket *sock, unsigned short type);

static inline void udp_tunnel_get_rx_info(struct net_device *dev)
{
        ASSERT_RTNL();
        if (!(dev->features & NETIF_F_RX_UDP_TUNNEL_PORT))
                return;
        call_netdevice_notifiers(NETDEV_UDP_TUNNEL_PUSH_INFO, dev);
}

static inline void udp_tunnel_drop_rx_info(struct net_device *dev)
{
        ASSERT_RTNL();
        if (!(dev->features & NETIF_F_RX_UDP_TUNNEL_PORT))
                return;
        call_netdevice_notifiers(NETDEV_UDP_TUNNEL_DROP_INFO, dev);
}

/* Transmit the skb using UDP encapsulation. */
void udp_tunnel_xmit_skb(struct rtable *rt, struct sock *sk, struct sk_buff *skb,
                         __be32 src, __be32 dst, __u8 tos, __u8 ttl,
                         __be16 df, __be16 src_port, __be16 dst_port,
                         bool xnet, bool nocheck);

int udp_tunnel6_xmit_skb(struct dst_entry *dst, struct sock *sk,
                         struct sk_buff *skb,
                         struct net_device *dev,
                         const struct in6_addr *saddr,
                         const struct in6_addr *daddr,
                         __u8 prio, __u8 ttl, __be32 label,
                         __be16 src_port, __be16 dst_port, bool nocheck);

void udp_tunnel_sock_release(struct socket *sock);

struct rtable *udp_tunnel_dst_lookup(struct sk_buff *skb,
                                     struct net_device *dev,
                                     struct net *net, int oif,
                                     __be32 *saddr,
                                     const struct ip_tunnel_key *key,
                                     __be16 sport, __be16 dport, u8 tos,
                                     struct dst_cache *dst_cache);
struct dst_entry *udp_tunnel6_dst_lookup(struct sk_buff *skb,
                                         struct net_device *dev,
                                         struct net *net,
                                         struct socket *sock, int oif,
                                         struct in6_addr *saddr,
                                         const struct ip_tunnel_key *key,
                                         __be16 sport, __be16 dport, u8 dsfield,
                                         struct dst_cache *dst_cache);

struct metadata_dst *udp_tun_rx_dst(struct sk_buff *skb, unsigned short family,
                                    const unsigned long *flags,
                                    __be64 tunnel_id, int md_size);

#ifdef CONFIG_INET
static inline int udp_tunnel_handle_offloads(struct sk_buff *skb, bool udp_csum)
{
        int type = udp_csum ? SKB_GSO_UDP_TUNNEL_CSUM : SKB_GSO_UDP_TUNNEL;

        return iptunnel_handle_offloads(skb, type);
}
#endif

static inline void udp_tunnel_encap_enable(struct sock *sk)
{
        if (udp_test_and_set_bit(ENCAP_ENABLED, sk))
                return;

#if IS_ENABLED(CONFIG_IPV6)
        if (READ_ONCE(sk->sk_family) == PF_INET6)
                ipv6_stub->udpv6_encap_enable();
#endif
        udp_encap_enable();
}

#define UDP_TUNNEL_NIC_MAX_TABLES        4

enum udp_tunnel_nic_info_flags {
        /* Device callbacks may sleep */
        UDP_TUNNEL_NIC_INFO_MAY_SLEEP        = BIT(0),
        /* Device only supports offloads when it's open, all ports
         * will be removed before close and re-added after open.
         */
        UDP_TUNNEL_NIC_INFO_OPEN_ONLY        = BIT(1),
        /* Device supports only IPv4 tunnels */
        UDP_TUNNEL_NIC_INFO_IPV4_ONLY        = BIT(2),
        /* Device has hard-coded the IANA VXLAN port (4789) as VXLAN.
         * This port must not be counted towards n_entries of any table.
         * Driver will not receive any callback associated with port 4789.
         */
        UDP_TUNNEL_NIC_INFO_STATIC_IANA_VXLAN        = BIT(3),
};

struct udp_tunnel_nic;

#define UDP_TUNNEL_NIC_MAX_SHARING_DEVICES        (U16_MAX / 2)

struct udp_tunnel_nic_shared {
        struct udp_tunnel_nic *udp_tunnel_nic_info;

        struct list_head devices;
};

struct udp_tunnel_nic_shared_node {
        struct net_device *dev;
        struct list_head list;
};

/**
 * struct udp_tunnel_nic_info - driver UDP tunnel offload information
 * @set_port:        callback for adding a new port
 * @unset_port:        callback for removing a port
 * @sync_table:        callback for syncing the entire port table at once
 * @shared:        reference to device global state (optional)
 * @flags:        device flags from enum udp_tunnel_nic_info_flags
 * @tables:        UDP port tables this device has
 * @tables.n_entries:                number of entries in this table
 * @tables.tunnel_types:        types of tunnels this table accepts
 *
 * Drivers are expected to provide either @set_port and @unset_port callbacks
 * or the @sync_table callback. Callbacks are invoked with rtnl lock held.
 *
 * Devices which (misguidedly) share the UDP tunnel port table across multiple
 * netdevs should allocate an instance of struct udp_tunnel_nic_shared and
 * point @shared at it.
 * There must never be more than %UDP_TUNNEL_NIC_MAX_SHARING_DEVICES devices
 * sharing a table.
 *
 * Known limitations:
 *  - UDP tunnel port notifications are fundamentally best-effort -
 *    it is likely the driver will both see skbs which use a UDP tunnel port,
 *    while not being a tunneled skb, and tunnel skbs from other ports -
 *    drivers should only use these ports for non-critical RX-side offloads,
 *    e.g. the checksum offload;
 *  - none of the devices care about the socket family at present, so we don't
 *    track it. Please extend this code if you care.
 */
struct udp_tunnel_nic_info {
        /* one-by-one */
        int (*set_port)(struct net_device *dev,
                        unsigned int table, unsigned int entry,
                        struct udp_tunnel_info *ti);
        int (*unset_port)(struct net_device *dev,
                          unsigned int table, unsigned int entry,
                          struct udp_tunnel_info *ti);

        /* all at once */
        int (*sync_table)(struct net_device *dev, unsigned int table);

        struct udp_tunnel_nic_shared *shared;

        unsigned int flags;

        struct udp_tunnel_nic_table_info {
                unsigned int n_entries;
                unsigned int tunnel_types;
        } tables[UDP_TUNNEL_NIC_MAX_TABLES];
};

/* UDP tunnel module dependencies
 *
 * Tunnel drivers are expected to have a hard dependency on the udp_tunnel
 * module. NIC drivers are not, they just attach their
 * struct udp_tunnel_nic_info to the netdev and wait for callbacks to come.
 * Loading a tunnel driver will cause the udp_tunnel module to be loaded
 * and only then will all the required state structures be allocated.
 * Since we want a weak dependency from the drivers and the core to udp_tunnel
 * we call things through the following stubs.
 */
struct udp_tunnel_nic_ops {
        void (*get_port)(struct net_device *dev, unsigned int table,
                         unsigned int idx, struct udp_tunnel_info *ti);
        void (*set_port_priv)(struct net_device *dev, unsigned int table,
                              unsigned int idx, u8 priv);
        void (*add_port)(struct net_device *dev, struct udp_tunnel_info *ti);
        void (*del_port)(struct net_device *dev, struct udp_tunnel_info *ti);
        void (*reset_ntf)(struct net_device *dev);

        size_t (*dump_size)(struct net_device *dev, unsigned int table);
        int (*dump_write)(struct net_device *dev, unsigned int table,
                          struct sk_buff *skb);
};

#ifdef CONFIG_INET
extern const struct udp_tunnel_nic_ops *udp_tunnel_nic_ops;
#else
#define udp_tunnel_nic_ops        ((struct udp_tunnel_nic_ops *)NULL)
#endif

static inline void
udp_tunnel_nic_get_port(struct net_device *dev, unsigned int table,
                        unsigned int idx, struct udp_tunnel_info *ti)
{
        /* This helper is used from .sync_table, we indicate empty entries
         * by zero'ed @ti. Drivers which need to know the details of a port
         * when it gets deleted should use the .set_port / .unset_port
         * callbacks.
         * Zero out here, otherwise !CONFIG_INET causes uninitilized warnings.
         */
        memset(ti, 0, sizeof(*ti));

        if (udp_tunnel_nic_ops)
                udp_tunnel_nic_ops->get_port(dev, table, idx, ti);
}

static inline void
udp_tunnel_nic_set_port_priv(struct net_device *dev, unsigned int table,
                             unsigned int idx, u8 priv)
{
        if (udp_tunnel_nic_ops)
                udp_tunnel_nic_ops->set_port_priv(dev, table, idx, priv);
}

static inline void
udp_tunnel_nic_add_port(struct net_device *dev, struct udp_tunnel_info *ti)
{
        if (!(dev->features & NETIF_F_RX_UDP_TUNNEL_PORT))
                return;
        if (udp_tunnel_nic_ops)
                udp_tunnel_nic_ops->add_port(dev, ti);
}

static inline void
udp_tunnel_nic_del_port(struct net_device *dev, struct udp_tunnel_info *ti)
{
        if (!(dev->features & NETIF_F_RX_UDP_TUNNEL_PORT))
                return;
        if (udp_tunnel_nic_ops)
                udp_tunnel_nic_ops->del_port(dev, ti);
}

/**
 * udp_tunnel_nic_reset_ntf() - device-originating reset notification
 * @dev: network interface device structure
 *
 * Called by the driver to inform the core that the entire UDP tunnel port
 * state has been lost, usually due to device reset. Core will assume device
 * forgot all the ports and issue .set_port and .sync_table callbacks as
 * necessary.
 *
 * This function must be called with rtnl lock held, and will issue all
 * the callbacks before returning.
 */
static inline void udp_tunnel_nic_reset_ntf(struct net_device *dev)
{
        if (udp_tunnel_nic_ops)
                udp_tunnel_nic_ops->reset_ntf(dev);
}

static inline size_t
udp_tunnel_nic_dump_size(struct net_device *dev, unsigned int table)
{
        if (!udp_tunnel_nic_ops)
                return 0;
        return udp_tunnel_nic_ops->dump_size(dev, table);
}

static inline int
udp_tunnel_nic_dump_write(struct net_device *dev, unsigned int table,
                          struct sk_buff *skb)
{
        if (!udp_tunnel_nic_ops)
                return 0;
        return udp_tunnel_nic_ops->dump_write(dev, table, skb);
}
#endif























   82 


   82 











   82 






























   25 
   11 








  101 

   18 



















   89 

































   13 
  100 
   36 
    3 














































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
/* SPDX-License-Identifier: GPL-2.0 */
#ifndef _BCACHEFS_FS_IO_H
#define _BCACHEFS_FS_IO_H

#ifndef NO_BCACHEFS_FS

#include "buckets.h"
#include "fs.h"
#include "io_write_types.h"
#include "quota.h"

#include <linux/uio.h>

struct folio_vec {
        struct folio        *fv_folio;
        size_t                fv_offset;
        size_t                fv_len;
};

static inline struct folio_vec biovec_to_foliovec(struct bio_vec bv)
{

        struct folio *folio        = page_folio(bv.bv_page);
        size_t offset                = (folio_page_idx(folio, bv.bv_page) << PAGE_SHIFT) +
                bv.bv_offset;
        size_t len = min_t(size_t, folio_size(folio) - offset, bv.bv_len);

        return (struct folio_vec) {
                .fv_folio        = folio,
                .fv_offset        = offset,
                .fv_len                = len,
        };
}

static inline struct folio_vec bio_iter_iovec_folio(struct bio *bio,
                                                    struct bvec_iter iter)
{
        return biovec_to_foliovec(bio_iter_iovec(bio, iter));
}

#define __bio_for_each_folio(bvl, bio, iter, start)                        \
        for (iter = (start);                                                \
             (iter).bi_size &&                                                \
                ((bvl = bio_iter_iovec_folio((bio), (iter))), 1);        \
             bio_advance_iter_single((bio), &(iter), (bvl).fv_len))

/**
 * bio_for_each_folio - iterate over folios within a bio
 *
 * Like other non-_all versions, this iterates over what bio->bi_iter currently
 * points to. This version is for drivers, where the bio may have previously
 * been split or cloned.
 */
#define bio_for_each_folio(bvl, bio, iter)                                \
        __bio_for_each_folio(bvl, bio, iter, (bio)->bi_iter)

struct quota_res {
        u64                                sectors;
};

#ifdef CONFIG_BCACHEFS_QUOTA

static inline void __bch2_quota_reservation_put(struct bch_fs *c,
                                         struct bch_inode_info *inode,
                                         struct quota_res *res)
{
        BUG_ON(res->sectors > inode->ei_quota_reserved);

        bch2_quota_acct(c, inode->ei_qid, Q_SPC,
                        -((s64) res->sectors), KEY_TYPE_QUOTA_PREALLOC);
        inode->ei_quota_reserved -= res->sectors;
        res->sectors = 0;
}

static inline void bch2_quota_reservation_put(struct bch_fs *c,
                                       struct bch_inode_info *inode,
                                       struct quota_res *res)
{
        if (res->sectors) {
                mutex_lock(&inode->ei_quota_lock);
                __bch2_quota_reservation_put(c, inode, res);
                mutex_unlock(&inode->ei_quota_lock);
        }
}

static inline int bch2_quota_reservation_add(struct bch_fs *c,
                                      struct bch_inode_info *inode,
                                      struct quota_res *res,
                                      u64 sectors,
                                      bool check_enospc)
{
        int ret;

        if (test_bit(EI_INODE_SNAPSHOT, &inode->ei_flags))
                return 0;

        mutex_lock(&inode->ei_quota_lock);
        ret = bch2_quota_acct(c, inode->ei_qid, Q_SPC, sectors,
                              check_enospc ? KEY_TYPE_QUOTA_PREALLOC : KEY_TYPE_QUOTA_NOCHECK);
        if (likely(!ret)) {
                inode->ei_quota_reserved += sectors;
                res->sectors += sectors;
        }
        mutex_unlock(&inode->ei_quota_lock);

        return ret;
}

#else

static inline void __bch2_quota_reservation_put(struct bch_fs *c,
                                         struct bch_inode_info *inode,
                                         struct quota_res *res) {}

static inline void bch2_quota_reservation_put(struct bch_fs *c,
                                       struct bch_inode_info *inode,
                                       struct quota_res *res) {}

static inline int bch2_quota_reservation_add(struct bch_fs *c,
                                      struct bch_inode_info *inode,
                                      struct quota_res *res,
                                      unsigned sectors,
                                      bool check_enospc)
{
        return 0;
}

#endif

void __bch2_i_sectors_acct(struct bch_fs *, struct bch_inode_info *,
                           struct quota_res *, s64);

static inline void bch2_i_sectors_acct(struct bch_fs *c, struct bch_inode_info *inode,
                                       struct quota_res *quota_res, s64 sectors)
{
        if (sectors) {
                mutex_lock(&inode->ei_quota_lock);
                __bch2_i_sectors_acct(c, inode, quota_res, sectors);
                mutex_unlock(&inode->ei_quota_lock);
        }
}

static inline struct address_space *faults_disabled_mapping(void)
{
        return (void *) (((unsigned long) current->faults_disabled_mapping) & ~1UL);
}

static inline void set_fdm_dropped_locks(void)
{
        current->faults_disabled_mapping =
                (void *) (((unsigned long) current->faults_disabled_mapping)|1);
}

static inline bool fdm_dropped_locks(void)
{
        return ((unsigned long) current->faults_disabled_mapping) & 1;
}

void bch2_inode_flush_nocow_writes_async(struct bch_fs *,
                        struct bch_inode_info *, struct closure *);

int __must_check bch2_write_inode_size(struct bch_fs *,
                                       struct bch_inode_info *,
                                       loff_t, unsigned);

int bch2_fsync(struct file *, loff_t, loff_t, int);

int bchfs_truncate(struct mnt_idmap *,
                  struct bch_inode_info *, struct iattr *);
long bch2_fallocate_dispatch(struct file *, int, loff_t, loff_t);

loff_t bch2_remap_file_range(struct file *, loff_t, struct file *,
                             loff_t, loff_t, unsigned);

loff_t bch2_llseek(struct file *, loff_t, int);

void bch2_fs_fsio_exit(struct bch_fs *);
int bch2_fs_fsio_init(struct bch_fs *);
#else
static inline void bch2_fs_fsio_exit(struct bch_fs *c) {}
static inline int bch2_fs_fsio_init(struct bch_fs *c) { return 0; }
#endif

#endif /* _BCACHEFS_FS_IO_H */
































    3 
    3 
    3 









    3 


    1 
    2 





    3 


    1 







   17 











   17 



    9 

    9 
































    8 





    8 







    8 







   24 








    6 

    6 























   18 



   17 







    3 



   18 


   18 






   18 











   18 
    1 
    1 

   18 















    6 











    5 



    5 




















    5 






    6 





































    6 


























































    4 






    4 


    2 



























































































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
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
// SPDX-License-Identifier: GPL-2.0
/*
 * Copyright (C) 2015-2019 Jason A. Donenfeld <Jason@zx2c4.com>. All Rights Reserved.
 */

#include "queueing.h"
#include "socket.h"
#include "timers.h"
#include "device.h"
#include "ratelimiter.h"
#include "peer.h"
#include "messages.h"

#include <linux/module.h>
#include <linux/rtnetlink.h>
#include <linux/inet.h>
#include <linux/netdevice.h>
#include <linux/inetdevice.h>
#include <linux/if_arp.h>
#include <linux/icmp.h>
#include <linux/suspend.h>
#include <net/dst_metadata.h>
#include <net/gso.h>
#include <net/icmp.h>
#include <net/rtnetlink.h>
#include <net/ip_tunnels.h>
#include <net/addrconf.h>

static LIST_HEAD(device_list);

static int wg_open(struct net_device *dev)
{
        struct in_device *dev_v4 = __in_dev_get_rtnl(dev);
        struct inet6_dev *dev_v6 = __in6_dev_get(dev);
        struct wg_device *wg = netdev_priv(dev);
        struct wg_peer *peer;
        int ret;

        if (dev_v4) {
                /* At some point we might put this check near the ip_rt_send_
                 * redirect call of ip_forward in net/ipv4/ip_forward.c, similar
                 * to the current secpath check.
                 */
                IN_DEV_CONF_SET(dev_v4, SEND_REDIRECTS, false);
                IPV4_DEVCONF_ALL(dev_net(dev), SEND_REDIRECTS) = false;
        }
        if (dev_v6)
                dev_v6->cnf.addr_gen_mode = IN6_ADDR_GEN_MODE_NONE;

        mutex_lock(&wg->device_update_lock);
        ret = wg_socket_init(wg, wg->incoming_port);
        if (ret < 0)
                goto out;
        list_for_each_entry(peer, &wg->peer_list, peer_list) {
                wg_packet_send_staged_packets(peer);
                if (peer->persistent_keepalive_interval)
                        wg_packet_send_keepalive(peer);
        }
out:
        mutex_unlock(&wg->device_update_lock);
        return ret;
}

static int wg_pm_notification(struct notifier_block *nb, unsigned long action, void *data)
{
        struct wg_device *wg;
        struct wg_peer *peer;

        /* If the machine is constantly suspending and resuming, as part of
         * its normal operation rather than as a somewhat rare event, then we
         * don't actually want to clear keys.
         */
        if (IS_ENABLED(CONFIG_PM_AUTOSLEEP) ||
            IS_ENABLED(CONFIG_PM_USERSPACE_AUTOSLEEP))
                return 0;

        if (action != PM_HIBERNATION_PREPARE && action != PM_SUSPEND_PREPARE)
                return 0;

        rtnl_lock();
        list_for_each_entry(wg, &device_list, device_list) {
                mutex_lock(&wg->device_update_lock);
                list_for_each_entry(peer, &wg->peer_list, peer_list) {
                        del_timer(&peer->timer_zero_key_material);
                        wg_noise_handshake_clear(&peer->handshake);
                        wg_noise_keypairs_clear(&peer->keypairs);
                }
                mutex_unlock(&wg->device_update_lock);
        }
        rtnl_unlock();
        rcu_barrier();
        return 0;
}

static struct notifier_block pm_notifier = { .notifier_call = wg_pm_notification };

static int wg_vm_notification(struct notifier_block *nb, unsigned long action, void *data)
{
        struct wg_device *wg;
        struct wg_peer *peer;

        rtnl_lock();
        list_for_each_entry(wg, &device_list, device_list) {
                mutex_lock(&wg->device_update_lock);
                list_for_each_entry(peer, &wg->peer_list, peer_list)
                        wg_noise_expire_current_peer_keypairs(peer);
                mutex_unlock(&wg->device_update_lock);
        }
        rtnl_unlock();
        return 0;
}

static struct notifier_block vm_notifier = { .notifier_call = wg_vm_notification };

static int wg_stop(struct net_device *dev)
{
        struct wg_device *wg = netdev_priv(dev);
        struct wg_peer *peer;
        struct sk_buff *skb;

        mutex_lock(&wg->device_update_lock);
        list_for_each_entry(peer, &wg->peer_list, peer_list) {
                wg_packet_purge_staged_packets(peer);
                wg_timers_stop(peer);
                wg_noise_handshake_clear(&peer->handshake);
                wg_noise_keypairs_clear(&peer->keypairs);
                wg_noise_reset_last_sent_handshake(&peer->last_sent_handshake);
        }
        mutex_unlock(&wg->device_update_lock);
        while ((skb = ptr_ring_consume(&wg->handshake_queue.ring)) != NULL)
                kfree_skb(skb);
        atomic_set(&wg->handshake_queue_len, 0);
        wg_socket_reinit(wg, NULL, NULL);
        return 0;
}

static netdev_tx_t wg_xmit(struct sk_buff *skb, struct net_device *dev)
{
        struct wg_device *wg = netdev_priv(dev);
        struct sk_buff_head packets;
        struct wg_peer *peer;
        struct sk_buff *next;
        sa_family_t family;
        u32 mtu;
        int ret;

        if (unlikely(!wg_check_packet_protocol(skb))) {
                ret = -EPROTONOSUPPORT;
                net_dbg_ratelimited("%s: Invalid IP packet\n", dev->name);
                goto err;
        }

        peer = wg_allowedips_lookup_dst(&wg->peer_allowedips, skb);
        if (unlikely(!peer)) {
                ret = -ENOKEY;
                if (skb->protocol == htons(ETH_P_IP))
                        net_dbg_ratelimited("%s: No peer has allowed IPs matching %pI4\n",
                                            dev->name, &ip_hdr(skb)->daddr);
                else if (skb->protocol == htons(ETH_P_IPV6))
                        net_dbg_ratelimited("%s: No peer has allowed IPs matching %pI6\n",
                                            dev->name, &ipv6_hdr(skb)->daddr);
                goto err_icmp;
        }

        family = READ_ONCE(peer->endpoint.addr.sa_family);
        if (unlikely(family != AF_INET && family != AF_INET6)) {
                ret = -EDESTADDRREQ;
                net_dbg_ratelimited("%s: No valid endpoint has been configured or discovered for peer %llu\n",
                                    dev->name, peer->internal_id);
                goto err_peer;
        }

        mtu = skb_valid_dst(skb) ? dst_mtu(skb_dst(skb)) : dev->mtu;

        __skb_queue_head_init(&packets);
        if (!skb_is_gso(skb)) {
                skb_mark_not_on_list(skb);
        } else {
                struct sk_buff *segs = skb_gso_segment(skb, 0);

                if (IS_ERR(segs)) {
                        ret = PTR_ERR(segs);
                        goto err_peer;
                }
                dev_kfree_skb(skb);
                skb = segs;
        }

        skb_list_walk_safe(skb, skb, next) {
                skb_mark_not_on_list(skb);

                skb = skb_share_check(skb, GFP_ATOMIC);
                if (unlikely(!skb))
                        continue;

                /* We only need to keep the original dst around for icmp,
                 * so at this point we're in a position to drop it.
                 */
                skb_dst_drop(skb);

                PACKET_CB(skb)->mtu = mtu;

                __skb_queue_tail(&packets, skb);
        }

        spin_lock_bh(&peer->staged_packet_queue.lock);
        /* If the queue is getting too big, we start removing the oldest packets
         * until it's small again. We do this before adding the new packet, so
         * we don't remove GSO segments that are in excess.
         */
        while (skb_queue_len(&peer->staged_packet_queue) > MAX_STAGED_PACKETS) {
                dev_kfree_skb(__skb_dequeue(&peer->staged_packet_queue));
                DEV_STATS_INC(dev, tx_dropped);
        }
        skb_queue_splice_tail(&packets, &peer->staged_packet_queue);
        spin_unlock_bh(&peer->staged_packet_queue.lock);

        wg_packet_send_staged_packets(peer);

        wg_peer_put(peer);
        return NETDEV_TX_OK;

err_peer:
        wg_peer_put(peer);
err_icmp:
        if (skb->protocol == htons(ETH_P_IP))
                icmp_ndo_send(skb, ICMP_DEST_UNREACH, ICMP_HOST_UNREACH, 0);
        else if (skb->protocol == htons(ETH_P_IPV6))
                icmpv6_ndo_send(skb, ICMPV6_DEST_UNREACH, ICMPV6_ADDR_UNREACH, 0);
err:
        DEV_STATS_INC(dev, tx_errors);
        kfree_skb(skb);
        return ret;
}

static const struct net_device_ops netdev_ops = {
        .ndo_open                = wg_open,
        .ndo_stop                = wg_stop,
        .ndo_start_xmit                = wg_xmit,
};

static void wg_destruct(struct net_device *dev)
{
        struct wg_device *wg = netdev_priv(dev);

        rtnl_lock();
        list_del(&wg->device_list);
        rtnl_unlock();
        mutex_lock(&wg->device_update_lock);
        rcu_assign_pointer(wg->creating_net, NULL);
        wg->incoming_port = 0;
        wg_socket_reinit(wg, NULL, NULL);
        /* The final references are cleared in the below calls to destroy_workqueue. */
        wg_peer_remove_all(wg);
        destroy_workqueue(wg->handshake_receive_wq);
        destroy_workqueue(wg->handshake_send_wq);
        destroy_workqueue(wg->packet_crypt_wq);
        wg_packet_queue_free(&wg->handshake_queue, true);
        wg_packet_queue_free(&wg->decrypt_queue, false);
        wg_packet_queue_free(&wg->encrypt_queue, false);
        rcu_barrier(); /* Wait for all the peers to be actually freed. */
        wg_ratelimiter_uninit();
        memzero_explicit(&wg->static_identity, sizeof(wg->static_identity));
        kvfree(wg->index_hashtable);
        kvfree(wg->peer_hashtable);
        mutex_unlock(&wg->device_update_lock);

        pr_debug("%s: Interface destroyed\n", dev->name);
        free_netdev(dev);
}

static const struct device_type device_type = { .name = KBUILD_MODNAME };

static void wg_setup(struct net_device *dev)
{
        struct wg_device *wg = netdev_priv(dev);
        enum { WG_NETDEV_FEATURES = NETIF_F_HW_CSUM | NETIF_F_RXCSUM |
                                    NETIF_F_SG | NETIF_F_GSO |
                                    NETIF_F_GSO_SOFTWARE | NETIF_F_HIGHDMA };
        const int overhead = MESSAGE_MINIMUM_LENGTH + sizeof(struct udphdr) +
                             max(sizeof(struct ipv6hdr), sizeof(struct iphdr));

        dev->netdev_ops = &netdev_ops;
        dev->header_ops = &ip_tunnel_header_ops;
        dev->hard_header_len = 0;
        dev->addr_len = 0;
        dev->needed_headroom = DATA_PACKET_HEAD_ROOM;
        dev->needed_tailroom = noise_encrypted_len(MESSAGE_PADDING_MULTIPLE);
        dev->type = ARPHRD_NONE;
        dev->flags = IFF_POINTOPOINT | IFF_NOARP;
        dev->priv_flags |= IFF_NO_QUEUE;
        dev->lltx = true;
        dev->features |= WG_NETDEV_FEATURES;
        dev->hw_features |= WG_NETDEV_FEATURES;
        dev->hw_enc_features |= WG_NETDEV_FEATURES;
        dev->mtu = ETH_DATA_LEN - overhead;
        dev->max_mtu = round_down(INT_MAX, MESSAGE_PADDING_MULTIPLE) - overhead;
        dev->pcpu_stat_type = NETDEV_PCPU_STAT_TSTATS;

        SET_NETDEV_DEVTYPE(dev, &device_type);

        /* We need to keep the dst around in case of icmp replies. */
        netif_keep_dst(dev);

        netif_set_tso_max_size(dev, GSO_MAX_SIZE);

        wg->dev = dev;
}

static int wg_newlink(struct net *src_net, struct net_device *dev,
                      struct nlattr *tb[], struct nlattr *data[],
                      struct netlink_ext_ack *extack)
{
        struct wg_device *wg = netdev_priv(dev);
        int ret = -ENOMEM;

        rcu_assign_pointer(wg->creating_net, src_net);
        init_rwsem(&wg->static_identity.lock);
        mutex_init(&wg->socket_update_lock);
        mutex_init(&wg->device_update_lock);
        wg_allowedips_init(&wg->peer_allowedips);
        wg_cookie_checker_init(&wg->cookie_checker, wg);
        INIT_LIST_HEAD(&wg->peer_list);
        wg->device_update_gen = 1;

        wg->peer_hashtable = wg_pubkey_hashtable_alloc();
        if (!wg->peer_hashtable)
                return ret;

        wg->index_hashtable = wg_index_hashtable_alloc();
        if (!wg->index_hashtable)
                goto err_free_peer_hashtable;

        wg->handshake_receive_wq = alloc_workqueue("wg-kex-%s",
                        WQ_CPU_INTENSIVE | WQ_FREEZABLE, 0, dev->name);
        if (!wg->handshake_receive_wq)
                goto err_free_index_hashtable;

        wg->handshake_send_wq = alloc_workqueue("wg-kex-%s",
                        WQ_UNBOUND | WQ_FREEZABLE, 0, dev->name);
        if (!wg->handshake_send_wq)
                goto err_destroy_handshake_receive;

        wg->packet_crypt_wq = alloc_workqueue("wg-crypt-%s",
                        WQ_CPU_INTENSIVE | WQ_MEM_RECLAIM, 0, dev->name);
        if (!wg->packet_crypt_wq)
                goto err_destroy_handshake_send;

        ret = wg_packet_queue_init(&wg->encrypt_queue, wg_packet_encrypt_worker,
                                   MAX_QUEUED_PACKETS);
        if (ret < 0)
                goto err_destroy_packet_crypt;

        ret = wg_packet_queue_init(&wg->decrypt_queue, wg_packet_decrypt_worker,
                                   MAX_QUEUED_PACKETS);
        if (ret < 0)
                goto err_free_encrypt_queue;

        ret = wg_packet_queue_init(&wg->handshake_queue, wg_packet_handshake_receive_worker,
                                   MAX_QUEUED_INCOMING_HANDSHAKES);
        if (ret < 0)
                goto err_free_decrypt_queue;

        ret = wg_ratelimiter_init();
        if (ret < 0)
                goto err_free_handshake_queue;

        ret = register_netdevice(dev);
        if (ret < 0)
                goto err_uninit_ratelimiter;

        list_add(&wg->device_list, &device_list);

        /* We wait until the end to assign priv_destructor, so that
         * register_netdevice doesn't call it for us if it fails.
         */
        dev->priv_destructor = wg_destruct;

        pr_debug("%s: Interface created\n", dev->name);
        return ret;

err_uninit_ratelimiter:
        wg_ratelimiter_uninit();
err_free_handshake_queue:
        wg_packet_queue_free(&wg->handshake_queue, false);
err_free_decrypt_queue:
        wg_packet_queue_free(&wg->decrypt_queue, false);
err_free_encrypt_queue:
        wg_packet_queue_free(&wg->encrypt_queue, false);
err_destroy_packet_crypt:
        destroy_workqueue(wg->packet_crypt_wq);
err_destroy_handshake_send:
        destroy_workqueue(wg->handshake_send_wq);
err_destroy_handshake_receive:
        destroy_workqueue(wg->handshake_receive_wq);
err_free_index_hashtable:
        kvfree(wg->index_hashtable);
err_free_peer_hashtable:
        kvfree(wg->peer_hashtable);
        return ret;
}

static struct rtnl_link_ops link_ops __read_mostly = {
        .kind                        = KBUILD_MODNAME,
        .priv_size                = sizeof(struct wg_device),
        .setup                        = wg_setup,
        .newlink                = wg_newlink,
};

static void wg_netns_pre_exit(struct net *net)
{
        struct wg_device *wg;
        struct wg_peer *peer;

        rtnl_lock();
        list_for_each_entry(wg, &device_list, device_list) {
                if (rcu_access_pointer(wg->creating_net) == net) {
                        pr_debug("%s: Creating namespace exiting\n", wg->dev->name);
                        netif_carrier_off(wg->dev);
                        mutex_lock(&wg->device_update_lock);
                        rcu_assign_pointer(wg->creating_net, NULL);
                        wg_socket_reinit(wg, NULL, NULL);
                        list_for_each_entry(peer, &wg->peer_list, peer_list)
                                wg_socket_clear_peer_endpoint_src(peer);
                        mutex_unlock(&wg->device_update_lock);
                }
        }
        rtnl_unlock();
}

static struct pernet_operations pernet_ops = {
        .pre_exit = wg_netns_pre_exit
};

int __init wg_device_init(void)
{
        int ret;

        ret = register_pm_notifier(&pm_notifier);
        if (ret)
                return ret;

        ret = register_random_vmfork_notifier(&vm_notifier);
        if (ret)
                goto error_pm;

        ret = register_pernet_device(&pernet_ops);
        if (ret)
                goto error_vm;

        ret = rtnl_link_register(&link_ops);
        if (ret)
                goto error_pernet;

        return 0;

error_pernet:
        unregister_pernet_device(&pernet_ops);
error_vm:
        unregister_random_vmfork_notifier(&vm_notifier);
error_pm:
        unregister_pm_notifier(&pm_notifier);
        return ret;
}

void wg_device_uninit(void)
{
        rtnl_link_unregister(&link_ops);
        unregister_pernet_device(&pernet_ops);
        unregister_random_vmfork_notifier(&vm_notifier);
        unregister_pm_notifier(&pm_notifier);
        rcu_barrier();
}





























   43 






   40 









   25 



   19 







    7 

    7 






    7 








   11 
















   21 
   21 


   17 




































   11 
   11 




   39 


   14 



   25 



    2 









    3 



   20 























   11 























   54 


   54 

   21 



   50 






   38 




   21 


















   36 




   36 


































    3 
































   29 




    3 



























    7 




    8 


















  217 



  233 



    9 



  233 





















   26 




   24 








   26 











  180 











    2 


   99 


   88 










    8 











    6 

   47 



   22 





















   19 












    2 

    1 





























    4 









































    8 














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
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
// SPDX-License-Identifier: GPL-2.0-only
/*
 * Copyright (C) Neil Brown 2002
 * Copyright (C) Christoph Hellwig 2007
 *
 * This file contains the code mapping from inodes to NFS file handles,
 * and for mapping back from file handles to dentries.
 *
 * For details on why we do all the strange and hairy things in here
 * take a look at Documentation/filesystems/nfs/exporting.rst.
 */
#include <linux/exportfs.h>
#include <linux/fs.h>
#include <linux/file.h>
#include <linux/module.h>
#include <linux/mount.h>
#include <linux/namei.h>
#include <linux/sched.h>
#include <linux/cred.h>

#define dprintk(fmt, args...) pr_debug(fmt, ##args)


static int get_name(const struct path *path, char *name, struct dentry *child);


static int exportfs_get_name(struct vfsmount *mnt, struct dentry *dir,
                char *name, struct dentry *child)
{
        const struct export_operations *nop = dir->d_sb->s_export_op;
        struct path path = {.mnt = mnt, .dentry = dir};

        if (nop->get_name)
                return nop->get_name(dir, name, child);
        else
                return get_name(&path, name, child);
}

/*
 * Check if the dentry or any of it's aliases is acceptable.
 */
static struct dentry *
find_acceptable_alias(struct dentry *result,
                int (*acceptable)(void *context, struct dentry *dentry),
                void *context)
{
        struct dentry *dentry, *toput = NULL;
        struct inode *inode;

        if (acceptable(context, result))
                return result;

        inode = result->d_inode;
        spin_lock(&inode->i_lock);
        hlist_for_each_entry(dentry, &inode->i_dentry, d_u.d_alias) {
                dget(dentry);
                spin_unlock(&inode->i_lock);
                if (toput)
                        dput(toput);
                if (dentry != result && acceptable(context, dentry)) {
                        dput(result);
                        return dentry;
                }
                spin_lock(&inode->i_lock);
                toput = dentry;
        }
        spin_unlock(&inode->i_lock);

        if (toput)
                dput(toput);
        return NULL;
}

static bool dentry_connected(struct dentry *dentry)
{
        dget(dentry);
        while (dentry->d_flags & DCACHE_DISCONNECTED) {
                struct dentry *parent = dget_parent(dentry);

                dput(dentry);
                if (dentry == parent) {
                        dput(parent);
                        return false;
                }
                dentry = parent;
        }
        dput(dentry);
        return true;
}

static void clear_disconnected(struct dentry *dentry)
{
        dget(dentry);
        while (dentry->d_flags & DCACHE_DISCONNECTED) {
                struct dentry *parent = dget_parent(dentry);

                WARN_ON_ONCE(IS_ROOT(dentry));

                spin_lock(&dentry->d_lock);
                dentry->d_flags &= ~DCACHE_DISCONNECTED;
                spin_unlock(&dentry->d_lock);

                dput(dentry);
                dentry = parent;
        }
        dput(dentry);
}

/*
 * Reconnect a directory dentry with its parent.
 *
 * This can return a dentry, or NULL, or an error.
 *
 * In the first case the returned dentry is the parent of the given
 * dentry, and may itself need to be reconnected to its parent.
 *
 * In the NULL case, a concurrent VFS operation has either renamed or
 * removed this directory.  The concurrent operation has reconnected our
 * dentry, so we no longer need to.
 */
static struct dentry *reconnect_one(struct vfsmount *mnt,
                struct dentry *dentry, char *nbuf)
{
        struct dentry *parent;
        struct dentry *tmp;
        int err;

        parent = ERR_PTR(-EACCES);
        inode_lock(dentry->d_inode);
        if (mnt->mnt_sb->s_export_op->get_parent)
                parent = mnt->mnt_sb->s_export_op->get_parent(dentry);
        inode_unlock(dentry->d_inode);

        if (IS_ERR(parent)) {
                dprintk("get_parent of %lu failed, err %ld\n",
                        dentry->d_inode->i_ino, PTR_ERR(parent));
                return parent;
        }

        dprintk("%s: find name of %lu in %lu\n", __func__,
                dentry->d_inode->i_ino, parent->d_inode->i_ino);
        err = exportfs_get_name(mnt, parent, nbuf, dentry);
        if (err == -ENOENT)
                goto out_reconnected;
        if (err)
                goto out_err;
        dprintk("%s: found name: %s\n", __func__, nbuf);
        tmp = lookup_one_unlocked(mnt_idmap(mnt), nbuf, parent, strlen(nbuf));
        if (IS_ERR(tmp)) {
                dprintk("lookup failed: %ld\n", PTR_ERR(tmp));
                err = PTR_ERR(tmp);
                goto out_err;
        }
        if (tmp != dentry) {
                /*
                 * Somebody has renamed it since exportfs_get_name();
                 * great, since it could've only been renamed if it
                 * got looked up and thus connected, and it would
                 * remain connected afterwards.  We are done.
                 */
                dput(tmp);
                goto out_reconnected;
        }
        dput(tmp);
        if (IS_ROOT(dentry)) {
                err = -ESTALE;
                goto out_err;
        }
        return parent;

out_err:
        dput(parent);
        return ERR_PTR(err);
out_reconnected:
        dput(parent);
        /*
         * Someone must have renamed our entry into another parent, in
         * which case it has been reconnected by the rename.
         *
         * Or someone removed it entirely, in which case filehandle
         * lookup will succeed but the directory is now IS_DEAD and
         * subsequent operations on it will fail.
         *
         * Alternatively, maybe there was no race at all, and the
         * filesystem is just corrupt and gave us a parent that doesn't
         * actually contain any entry pointing to this inode.  So,
         * double check that this worked and return -ESTALE if not:
         */
        if (!dentry_connected(dentry))
                return ERR_PTR(-ESTALE);
        return NULL;
}

/*
 * Make sure target_dir is fully connected to the dentry tree.
 *
 * On successful return, DCACHE_DISCONNECTED will be cleared on
 * target_dir, and target_dir->d_parent->...->d_parent will reach the
 * root of the filesystem.
 *
 * Whenever DCACHE_DISCONNECTED is unset, target_dir is fully connected.
 * But the converse is not true: target_dir may have DCACHE_DISCONNECTED
 * set but already be connected.  In that case we'll verify the
 * connection to root and then clear the flag.
 *
 * Note that target_dir could be removed by a concurrent operation.  In
 * that case reconnect_path may still succeed with target_dir fully
 * connected, but further operations using the filehandle will fail when
 * necessary (due to S_DEAD being set on the directory).
 */
static int
reconnect_path(struct vfsmount *mnt, struct dentry *target_dir, char *nbuf)
{
        struct dentry *dentry, *parent;

        dentry = dget(target_dir);

        while (dentry->d_flags & DCACHE_DISCONNECTED) {
                BUG_ON(dentry == mnt->mnt_sb->s_root);

                if (IS_ROOT(dentry))
                        parent = reconnect_one(mnt, dentry, nbuf);
                else
                        parent = dget_parent(dentry);

                if (!parent)
                        break;
                dput(dentry);
                if (IS_ERR(parent))
                        return PTR_ERR(parent);
                dentry = parent;
        }
        dput(dentry);
        clear_disconnected(target_dir);
        return 0;
}

struct getdents_callback {
        struct dir_context ctx;
        char *name;                /* name that was found. It already points to a
                                   buffer NAME_MAX+1 is size */
        u64 ino;                /* the inum we are looking for */
        int found;                /* inode matched? */
        int sequence;                /* sequence counter */
};

/*
 * A rather strange filldir function to capture
 * the name matching the specified inode number.
 */
static bool filldir_one(struct dir_context *ctx, const char *name, int len,
                        loff_t pos, u64 ino, unsigned int d_type)
{
        struct getdents_callback *buf =
                container_of(ctx, struct getdents_callback, ctx);

        buf->sequence++;
        if (buf->ino == ino && len <= NAME_MAX && !is_dot_dotdot(name, len)) {
                memcpy(buf->name, name, len);
                buf->name[len] = '\0';
                buf->found = 1;
                return false;        // no more
        }
        return true;
}

/**
 * get_name - default export_operations->get_name function
 * @path:   the directory in which to find a name
 * @name:   a pointer to a %NAME_MAX+1 char buffer to store the name
 * @child:  the dentry for the child directory.
 *
 * calls readdir on the parent until it finds an entry with
 * the same inode number as the child, and returns that.
 */
static int get_name(const struct path *path, char *name, struct dentry *child)
{
        const struct cred *cred = current_cred();
        struct inode *dir = path->dentry->d_inode;
        int error;
        struct file *file;
        struct kstat stat;
        struct path child_path = {
                .mnt = path->mnt,
                .dentry = child,
        };
        struct getdents_callback buffer = {
                .ctx.actor = filldir_one,
                .name = name,
        };

        error = -ENOTDIR;
        if (!dir || !S_ISDIR(dir->i_mode))
                goto out;
        error = -EINVAL;
        if (!dir->i_fop)
                goto out;
        /*
         * inode->i_ino is unsigned long, kstat->ino is u64, so the
         * former would be insufficient on 32-bit hosts when the
         * filesystem supports 64-bit inode numbers.  So we need to
         * actually call ->getattr, not just read i_ino:
         */
        error = vfs_getattr_nosec(&child_path, &stat,
                                  STATX_INO, AT_STATX_SYNC_AS_STAT);
        if (error)
                return error;
        buffer.ino = stat.ino;
        /*
         * Open the directory ...
         */
        file = dentry_open(path, O_RDONLY, cred);
        error = PTR_ERR(file);
        if (IS_ERR(file))
                goto out;

        error = -EINVAL;
        if (!file->f_op->iterate_shared)
                goto out_close;

        buffer.sequence = 0;
        while (1) {
                int old_seq = buffer.sequence;

                error = iterate_dir(file, &buffer.ctx);
                if (buffer.found) {
                        error = 0;
                        break;
                }

                if (error < 0)
                        break;

                error = -ENOENT;
                if (old_seq == buffer.sequence)
                        break;
        }

out_close:
        fput(file);
out:
        return error;
}

#define FILEID_INO64_GEN_LEN 3

/**
 * exportfs_encode_ino64_fid - encode non-decodeable 64bit ino file id
 * @inode:   the object to encode
 * @fid:     where to store the file handle fragment
 * @max_len: maximum length to store there (in 4 byte units)
 *
 * This generic function is used to encode a non-decodeable file id for
 * fanotify for filesystems that do not support NFS export.
 */
static int exportfs_encode_ino64_fid(struct inode *inode, struct fid *fid,
                                     int *max_len)
{
        if (*max_len < FILEID_INO64_GEN_LEN) {
                *max_len = FILEID_INO64_GEN_LEN;
                return FILEID_INVALID;
        }

        fid->i64.ino = inode->i_ino;
        fid->i64.gen = inode->i_generation;
        *max_len = FILEID_INO64_GEN_LEN;

        return FILEID_INO64_GEN;
}

/**
 * exportfs_encode_inode_fh - encode a file handle from inode
 * @inode:   the object to encode
 * @fid:     where to store the file handle fragment
 * @max_len: maximum length to store there
 * @parent:  parent directory inode, if wanted
 * @flags:   properties of the requested file handle
 *
 * Returns an enum fid_type or a negative errno.
 */
int exportfs_encode_inode_fh(struct inode *inode, struct fid *fid,
                             int *max_len, struct inode *parent, int flags)
{
        const struct export_operations *nop = inode->i_sb->s_export_op;
        enum fid_type type;

        if (!exportfs_can_encode_fh(nop, flags))
                return -EOPNOTSUPP;

        if (!nop && (flags & EXPORT_FH_FID))
                type = exportfs_encode_ino64_fid(inode, fid, max_len);
        else
                type = nop->encode_fh(inode, fid->raw, max_len, parent);

        if (type > 0 && FILEID_USER_FLAGS(type)) {
                pr_warn_once("%s: unexpected fh type value 0x%x from fstype %s.\n",
                             __func__, type, inode->i_sb->s_type->name);
                return -EINVAL;
        }

        return type;

}
EXPORT_SYMBOL_GPL(exportfs_encode_inode_fh);

/**
 * exportfs_encode_fh - encode a file handle from dentry
 * @dentry:  the object to encode
 * @fid:     where to store the file handle fragment
 * @max_len: maximum length to store there
 * @flags:   properties of the requested file handle
 *
 * Returns an enum fid_type or a negative errno.
 */
int exportfs_encode_fh(struct dentry *dentry, struct fid *fid, int *max_len,
                       int flags)
{
        int error;
        struct dentry *p = NULL;
        struct inode *inode = dentry->d_inode, *parent = NULL;

        if ((flags & EXPORT_FH_CONNECTABLE) && !S_ISDIR(inode->i_mode)) {
                p = dget_parent(dentry);
                /*
                 * note that while p might've ceased to be our parent already,
                 * it's still pinned by and still positive.
                 */
                parent = p->d_inode;
        }

        error = exportfs_encode_inode_fh(inode, fid, max_len, parent, flags);
        dput(p);

        return error;
}
EXPORT_SYMBOL_GPL(exportfs_encode_fh);

struct dentry *
exportfs_decode_fh_raw(struct vfsmount *mnt, struct fid *fid, int fh_len,
                       int fileid_type, unsigned int flags,
                       int (*acceptable)(void *, struct dentry *),
                       void *context)
{
        const struct export_operations *nop = mnt->mnt_sb->s_export_op;
        struct dentry *result, *alias;
        char nbuf[NAME_MAX+1];
        int err;

        if (fileid_type < 0 || FILEID_USER_FLAGS(fileid_type))
                return ERR_PTR(-EINVAL);

        /*
         * Try to get any dentry for the given file handle from the filesystem.
         */
        if (!exportfs_can_decode_fh(nop))
                return ERR_PTR(-ESTALE);
        result = nop->fh_to_dentry(mnt->mnt_sb, fid, fh_len, fileid_type);
        if (IS_ERR_OR_NULL(result))
                return result;

        if ((flags & EXPORT_FH_DIR_ONLY) && !d_is_dir(result)) {
                err = -ENOTDIR;
                goto err_result;
        }

        /*
         * If no acceptance criteria was specified by caller, a disconnected
         * dentry is also accepatable. Callers may use this mode to query if
         * file handle is stale or to get a reference to an inode without
         * risking the high overhead caused by directory reconnect.
         */
        if (!acceptable)
                return result;

        if (d_is_dir(result)) {
                /*
                 * This request is for a directory.
                 *
                 * On the positive side there is only one dentry for each
                 * directory inode.  On the negative side this implies that we
                 * to ensure our dentry is connected all the way up to the
                 * filesystem root.
                 */
                if (result->d_flags & DCACHE_DISCONNECTED) {
                        err = reconnect_path(mnt, result, nbuf);
                        if (err)
                                goto err_result;
                }

                if (!acceptable(context, result)) {
                        err = -EACCES;
                        goto err_result;
                }

                return result;
        } else {
                /*
                 * It's not a directory.  Life is a little more complicated.
                 */
                struct dentry *target_dir, *nresult;

                /*
                 * See if either the dentry we just got from the filesystem
                 * or any alias for it is acceptable.  This is always true
                 * if this filesystem is exported without the subtreecheck
                 * option.  If the filesystem is exported with the subtree
                 * check option there's a fair chance we need to look at
                 * the parent directory in the file handle and make sure
                 * it's connected to the filesystem root.
                 */
                alias = find_acceptable_alias(result, acceptable, context);
                if (alias)
                        return alias;

                /*
                 * Try to extract a dentry for the parent directory from the
                 * file handle.  If this fails we'll have to give up.
                 */
                err = -ESTALE;
                if (!nop->fh_to_parent)
                        goto err_result;

                target_dir = nop->fh_to_parent(mnt->mnt_sb, fid,
                                fh_len, fileid_type);
                if (!target_dir)
                        goto err_result;
                err = PTR_ERR(target_dir);
                if (IS_ERR(target_dir))
                        goto err_result;

                /*
                 * And as usual we need to make sure the parent directory is
                 * connected to the filesystem root.  The VFS really doesn't
                 * like disconnected directories..
                 */
                err = reconnect_path(mnt, target_dir, nbuf);
                if (err) {
                        dput(target_dir);
                        goto err_result;
                }

                /*
                 * Now that we've got both a well-connected parent and a
                 * dentry for the inode we're after, make sure that our
                 * inode is actually connected to the parent.
                 */
                err = exportfs_get_name(mnt, target_dir, nbuf, result);
                if (err) {
                        dput(target_dir);
                        goto err_result;
                }

                inode_lock(target_dir->d_inode);
                nresult = lookup_one(mnt_idmap(mnt), nbuf,
                                     target_dir, strlen(nbuf));
                if (!IS_ERR(nresult)) {
                        if (unlikely(nresult->d_inode != result->d_inode)) {
                                dput(nresult);
                                nresult = ERR_PTR(-ESTALE);
                        }
                }
                inode_unlock(target_dir->d_inode);
                /*
                 * At this point we are done with the parent, but it's pinned
                 * by the child dentry anyway.
                 */
                dput(target_dir);

                if (IS_ERR(nresult)) {
                        err = PTR_ERR(nresult);
                        goto err_result;
                }
                dput(result);
                result = nresult;

                /*
                 * And finally make sure the dentry is actually acceptable
                 * to NFSD.
                 */
                alias = find_acceptable_alias(result, acceptable, context);
                if (!alias) {
                        err = -EACCES;
                        goto err_result;
                }

                return alias;
        }

 err_result:
        dput(result);
        return ERR_PTR(err);
}
EXPORT_SYMBOL_GPL(exportfs_decode_fh_raw);

struct dentry *exportfs_decode_fh(struct vfsmount *mnt, struct fid *fid,
                                  int fh_len, int fileid_type,
                                  int (*acceptable)(void *, struct dentry *),
                                  void *context)
{
        struct dentry *ret;

        ret = exportfs_decode_fh_raw(mnt, fid, fh_len, fileid_type, 0,
                                     acceptable, context);
        if (IS_ERR_OR_NULL(ret)) {
                if (ret == ERR_PTR(-ENOMEM))
                        return ret;
                return ERR_PTR(-ESTALE);
        }
        return ret;
}
EXPORT_SYMBOL_GPL(exportfs_decode_fh);

MODULE_LICENSE("GPL");




















































































































































  134 




  134 
  135 



  135 





























  151 




  135 
   17 
   13 







  151 








  144 





































































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
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
// SPDX-License-Identifier: MIT
/*
 * Copyright (C) 2019 Google, Inc.
 *
 * Authors:
 * Sean Paul <seanpaul@chromium.org>
 */
#include <linux/average.h>
#include <linux/bitops.h>
#include <linux/slab.h>
#include <linux/workqueue.h>

#include <drm/drm_atomic.h>
#include <drm/drm_atomic_helper.h>
#include <drm/drm_connector.h>
#include <drm/drm_crtc.h>
#include <drm/drm_device.h>
#include <drm/drm_mode_config.h>
#include <drm/drm_modeset_lock.h>
#include <drm/drm_print.h>
#include <drm/drm_self_refresh_helper.h>

/**
 * DOC: overview
 *
 * This helper library provides an easy way for drivers to leverage the atomic
 * framework to implement panel self refresh (SR) support. Drivers are
 * responsible for initializing and cleaning up the SR helpers on load/unload
 * (see &drm_self_refresh_helper_init/&drm_self_refresh_helper_cleanup).
 * The connector is responsible for setting
 * &drm_connector_state.self_refresh_aware to true at runtime if it is SR-aware
 * (meaning it knows how to initiate self refresh on the panel).
 *
 * Once a crtc has enabled SR using &drm_self_refresh_helper_init, the
 * helpers will monitor activity and call back into the driver to enable/disable
 * SR as appropriate. The best way to think about this is that it's a DPMS
 * on/off request with &drm_crtc_state.self_refresh_active set in crtc state
 * that tells you to disable/enable SR on the panel instead of power-cycling it.
 *
 * During SR, drivers may choose to fully disable their crtc/encoder/bridge
 * hardware (in which case no driver changes are necessary), or they can inspect
 * &drm_crtc_state.self_refresh_active if they want to enter low power mode
 * without full disable (in case full disable/enable is too slow).
 *
 * SR will be deactivated if there are any atomic updates affecting the
 * pipe that is in SR mode. If a crtc is driving multiple connectors, all
 * connectors must be SR aware and all will enter/exit SR mode at the same time.
 *
 * If the crtc and connector are SR aware, but the panel connected does not
 * support it (or is otherwise unable to enter SR), the driver should fail
 * atomic_check when &drm_crtc_state.self_refresh_active is true.
 */

#define SELF_REFRESH_AVG_SEED_MS 200

DECLARE_EWMA(psr_time, 4, 4)

struct drm_self_refresh_data {
        struct drm_crtc *crtc;
        struct delayed_work entry_work;

        struct mutex avg_mutex;
        struct ewma_psr_time entry_avg_ms;
        struct ewma_psr_time exit_avg_ms;
};

static void drm_self_refresh_helper_entry_work(struct work_struct *work)
{
        struct drm_self_refresh_data *sr_data = container_of(
                                to_delayed_work(work),
                                struct drm_self_refresh_data, entry_work);
        struct drm_crtc *crtc = sr_data->crtc;
        struct drm_device *dev = crtc->dev;
        struct drm_modeset_acquire_ctx ctx;
        struct drm_atomic_state *state;
        struct drm_connector *conn;
        struct drm_connector_state *conn_state;
        struct drm_crtc_state *crtc_state;
        int i, ret = 0;

        drm_modeset_acquire_init(&ctx, 0);

        state = drm_atomic_state_alloc(dev);
        if (!state) {
                ret = -ENOMEM;
                goto out_drop_locks;
        }

retry:
        state->acquire_ctx = &ctx;

        crtc_state = drm_atomic_get_crtc_state(state, crtc);
        if (IS_ERR(crtc_state)) {
                ret = PTR_ERR(crtc_state);
                goto out;
        }

        if (!crtc_state->enable)
                goto out;

        ret = drm_atomic_add_affected_connectors(state, crtc);
        if (ret)
                goto out;

        for_each_new_connector_in_state(state, conn, conn_state, i) {
                if (!conn_state->self_refresh_aware)
                        goto out;
        }

        crtc_state->active = false;
        crtc_state->self_refresh_active = true;

        ret = drm_atomic_commit(state);
        if (ret)
                goto out;

out:
        if (ret == -EDEADLK) {
                drm_atomic_state_clear(state);
                ret = drm_modeset_backoff(&ctx);
                if (!ret)
                        goto retry;
        }

        drm_atomic_state_put(state);

out_drop_locks:
        drm_modeset_drop_locks(&ctx);
        drm_modeset_acquire_fini(&ctx);
}

/**
 * drm_self_refresh_helper_update_avg_times - Updates a crtc's SR time averages
 * @state: the state which has just been applied to hardware
 * @commit_time_ms: the amount of time in ms that this commit took to complete
 * @new_self_refresh_mask: bitmask of crtc's that have self_refresh_active in
 *    new state
 *
 * Called after &drm_mode_config_funcs.atomic_commit_tail, this function will
 * update the average entry/exit self refresh times on self refresh transitions.
 * These averages will be used when calculating how long to delay before
 * entering self refresh mode after activity.
 */
void
drm_self_refresh_helper_update_avg_times(struct drm_atomic_state *state,
                                         unsigned int commit_time_ms,
                                         unsigned int new_self_refresh_mask)
{
        struct drm_crtc *crtc;
        struct drm_crtc_state *old_crtc_state;
        int i;

        for_each_old_crtc_in_state(state, crtc, old_crtc_state, i) {
                bool new_self_refresh_active = new_self_refresh_mask & BIT(i);
                struct drm_self_refresh_data *sr_data = crtc->self_refresh_data;
                struct ewma_psr_time *time;

                if (old_crtc_state->self_refresh_active ==
                    new_self_refresh_active)
                        continue;

                if (new_self_refresh_active)
                        time = &sr_data->entry_avg_ms;
                else
                        time = &sr_data->exit_avg_ms;

                mutex_lock(&sr_data->avg_mutex);
                ewma_psr_time_add(time, commit_time_ms);
                mutex_unlock(&sr_data->avg_mutex);
        }
}
EXPORT_SYMBOL(drm_self_refresh_helper_update_avg_times);

/**
 * drm_self_refresh_helper_alter_state - Alters the atomic state for SR exit
 * @state: the state currently being checked
 *
 * Called at the end of atomic check. This function checks the state for flags
 * incompatible with self refresh exit and changes them. This is a bit
 * disingenuous since userspace is expecting one thing and we're giving it
 * another. However in order to keep self refresh entirely hidden from
 * userspace, this is required.
 *
 * At the end, we queue up the self refresh entry work so we can enter PSR after
 * the desired delay.
 */
void drm_self_refresh_helper_alter_state(struct drm_atomic_state *state)
{
        struct drm_crtc *crtc;
        struct drm_crtc_state *crtc_state;
        int i;

        if (state->async_update || !state->allow_modeset) {
                for_each_old_crtc_in_state(state, crtc, crtc_state, i) {
                        if (crtc_state->self_refresh_active) {
                                state->async_update = false;
                                state->allow_modeset = true;
                                break;
                        }
                }
        }

        for_each_new_crtc_in_state(state, crtc, crtc_state, i) {
                struct drm_self_refresh_data *sr_data;
                unsigned int delay;

                /* Don't trigger the entry timer when we're already in SR */
                if (crtc_state->self_refresh_active)
                        continue;

                sr_data = crtc->self_refresh_data;
                if (!sr_data)
                        continue;

                mutex_lock(&sr_data->avg_mutex);
                delay = (ewma_psr_time_read(&sr_data->entry_avg_ms) +
                         ewma_psr_time_read(&sr_data->exit_avg_ms)) * 2;
                mutex_unlock(&sr_data->avg_mutex);

                mod_delayed_work(system_wq, &sr_data->entry_work,
                                 msecs_to_jiffies(delay));
        }
}
EXPORT_SYMBOL(drm_self_refresh_helper_alter_state);

/**
 * drm_self_refresh_helper_init - Initializes self refresh helpers for a crtc
 * @crtc: the crtc which supports self refresh supported displays
 *
 * Returns zero if successful or -errno on failure
 */
int drm_self_refresh_helper_init(struct drm_crtc *crtc)
{
        struct drm_self_refresh_data *sr_data = crtc->self_refresh_data;

        /* Helper is already initialized */
        if (WARN_ON(sr_data))
                return -EINVAL;

        sr_data = kzalloc(sizeof(*sr_data), GFP_KERNEL);
        if (!sr_data)
                return -ENOMEM;

        INIT_DELAYED_WORK(&sr_data->entry_work,
                          drm_self_refresh_helper_entry_work);
        sr_data->crtc = crtc;
        mutex_init(&sr_data->avg_mutex);
        ewma_psr_time_init(&sr_data->entry_avg_ms);
        ewma_psr_time_init(&sr_data->exit_avg_ms);

        /*
         * Seed the averages so they're non-zero (and sufficiently large
         * for even poorly performing panels). As time goes on, this will be
         * averaged out and the values will trend to their true value.
         */
        ewma_psr_time_add(&sr_data->entry_avg_ms, SELF_REFRESH_AVG_SEED_MS);
        ewma_psr_time_add(&sr_data->exit_avg_ms, SELF_REFRESH_AVG_SEED_MS);

        crtc->self_refresh_data = sr_data;
        return 0;
}
EXPORT_SYMBOL(drm_self_refresh_helper_init);

/**
 * drm_self_refresh_helper_cleanup - Cleans up self refresh helpers for a crtc
 * @crtc: the crtc to cleanup
 */
void drm_self_refresh_helper_cleanup(struct drm_crtc *crtc)
{
        struct drm_self_refresh_data *sr_data = crtc->self_refresh_data;

        /* Helper is already uninitialized */
        if (!sr_data)
                return;

        crtc->self_refresh_data = NULL;

        cancel_delayed_work_sync(&sr_data->entry_work);
        kfree(sr_data);
}
EXPORT_SYMBOL(drm_self_refresh_helper_cleanup);































































  321 






  321 





































   26 



   26 























  329 




  329 

















  333 






























  328 
    2 
    4 
















    1 
    1 








    1 
























  323 



























































  322 
  321 






    1 








































  320 

















  321 













  323 



















  321 




  321 
  321 




  320 


    1 




  320 
























   23 









    5 


   18 




    3 



















  287 























  287 
















  287 


   25 















  286 












    1 


    2 



































   15 




   15 





























































  322 

























  322 







  322 












    1 

























































  321 









  320 

  195 












    1 






























































  204 
  117 







  321 
  321 

   11 








  289 
   13 





  302 














  301 






  302 












    4 


























    1 





    1 







  286 












  191 







   95 
















  279 


















  252 
    7 




   79 

  179 















   18 

  205 





  190 





    5 









   11 


























   22 






























    4 

















    4 





















    3 


    3 





    3 






























    4 










  714 







  709 







    3 

  212 












  731 




































  732 

  716 











   35 




    2 

















   29 















  209 


  209 




































































































   33 




   32 







































  148 


  149 










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
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
1187
1188
1189
1190
1191
1192
1193
1194
1195
1196
1197
1198
1199
1200
1201
1202
1203
1204
1205
1206
1207
1208
1209
1210
1211
1212
1213
1214
1215
1216
1217
1218
1219
1220
1221
1222
1223
1224
1225
1226
1227
1228
1229
1230
1231
1232
1233
1234
1235
1236
1237
1238
1239
1240
1241
1242
1243
1244
1245
1246
1247
1248
1249
1250
1251
1252
1253
1254
1255
1256
1257
1258
1259
1260
1261
1262
1263
1264
1265
1266
1267
1268
1269
1270
1271
1272
1273
1274
1275
1276
1277
1278
1279
1280
1281
1282
1283
1284
1285
1286
1287
1288
1289
1290
1291
1292
1293
1294
1295
1296
1297
1298
1299
1300
1301
1302
1303
1304
1305
1306
1307
1308
1309
1310
1311
1312
1313
1314
1315
1316
1317
1318
1319
1320
1321
1322
1323
1324
1325
1326
1327
1328
1329
1330
1331
1332
1333
1334
1335
1336
1337
1338
1339
1340
1341
1342
1343
1344
1345
1346
1347
1348
1349
1350
1351
1352
1353
1354
1355
1356
1357
1358
1359
1360
1361
1362
1363
1364
1365
1366
1367
1368
1369
1370
1371
1372
1373
1374
1375
1376
1377
1378
1379
1380
1381
1382
1383
1384
1385
1386
1387
1388
1389
1390
1391
1392
1393
1394
1395
1396
1397
1398
1399
1400
1401
1402
1403
1404
1405
1406
1407
1408
1409
1410
1411
1412
1413
1414
1415
1416
1417
1418
1419
1420
1421
1422
1423
1424
1425
1426
1427
1428
1429
1430
1431
1432
1433
1434
1435
1436
1437
1438
1439
1440
1441
1442
1443
1444
1445
1446
1447
1448
1449
1450
1451
1452
1453
1454
1455
1456
1457
1458
1459
1460
1461
1462
1463
1464
1465
1466
1467
1468
1469
1470
1471
1472
1473
1474
1475
1476
1477
1478
1479
1480
1481
1482
1483
1484
1485
1486
1487
1488
1489
1490
1491
1492
1493
1494
1495
1496
1497
1498
1499
1500
// SPDX-License-Identifier: GPL-2.0
/*
 * Copyright (c) 2000-2005 Silicon Graphics, Inc.
 * All Rights Reserved.
 */
#include "xfs.h"
#include "xfs_fs.h"
#include "xfs_shared.h"
#include "xfs_format.h"
#include "xfs_log_format.h"
#include "xfs_trans_resv.h"
#include "xfs_bit.h"
#include "xfs_sb.h"
#include "xfs_mount.h"
#include "xfs_inode.h"
#include "xfs_dir2.h"
#include "xfs_ialloc.h"
#include "xfs_alloc.h"
#include "xfs_rtalloc.h"
#include "xfs_bmap.h"
#include "xfs_trans.h"
#include "xfs_trans_priv.h"
#include "xfs_log.h"
#include "xfs_log_priv.h"
#include "xfs_error.h"
#include "xfs_quota.h"
#include "xfs_fsops.h"
#include "xfs_icache.h"
#include "xfs_sysfs.h"
#include "xfs_rmap_btree.h"
#include "xfs_refcount_btree.h"
#include "xfs_reflink.h"
#include "xfs_extent_busy.h"
#include "xfs_health.h"
#include "xfs_trace.h"
#include "xfs_ag.h"
#include "xfs_rtbitmap.h"
#include "xfs_metafile.h"
#include "xfs_rtgroup.h"
#include "scrub/stats.h"

static DEFINE_MUTEX(xfs_uuid_table_mutex);
static int xfs_uuid_table_size;
static uuid_t *xfs_uuid_table;

void
xfs_uuid_table_free(void)
{
        if (xfs_uuid_table_size == 0)
                return;
        kfree(xfs_uuid_table);
        xfs_uuid_table = NULL;
        xfs_uuid_table_size = 0;
}

/*
 * See if the UUID is unique among mounted XFS filesystems.
 * Mount fails if UUID is nil or a FS with the same UUID is already mounted.
 */
STATIC int
xfs_uuid_mount(
        struct xfs_mount        *mp)
{
        uuid_t                        *uuid = &mp->m_sb.sb_uuid;
        int                        hole, i;

        /* Publish UUID in struct super_block */
        super_set_uuid(mp->m_super, uuid->b, sizeof(*uuid));

        if (xfs_has_nouuid(mp))
                return 0;

        if (uuid_is_null(uuid)) {
                xfs_warn(mp, "Filesystem has null UUID - can't mount");
                return -EINVAL;
        }

        mutex_lock(&xfs_uuid_table_mutex);
        for (i = 0, hole = -1; i < xfs_uuid_table_size; i++) {
                if (uuid_is_null(&xfs_uuid_table[i])) {
                        hole = i;
                        continue;
                }
                if (uuid_equal(uuid, &xfs_uuid_table[i]))
                        goto out_duplicate;
        }

        if (hole < 0) {
                xfs_uuid_table = krealloc(xfs_uuid_table,
                        (xfs_uuid_table_size + 1) * sizeof(*xfs_uuid_table),
                        GFP_KERNEL | __GFP_NOFAIL);
                hole = xfs_uuid_table_size++;
        }
        xfs_uuid_table[hole] = *uuid;
        mutex_unlock(&xfs_uuid_table_mutex);

        return 0;

 out_duplicate:
        mutex_unlock(&xfs_uuid_table_mutex);
        xfs_warn(mp, "Filesystem has duplicate UUID %pU - can't mount", uuid);
        return -EINVAL;
}

STATIC void
xfs_uuid_unmount(
        struct xfs_mount        *mp)
{
        uuid_t                        *uuid = &mp->m_sb.sb_uuid;
        int                        i;

        if (xfs_has_nouuid(mp))
                return;

        mutex_lock(&xfs_uuid_table_mutex);
        for (i = 0; i < xfs_uuid_table_size; i++) {
                if (uuid_is_null(&xfs_uuid_table[i]))
                        continue;
                if (!uuid_equal(uuid, &xfs_uuid_table[i]))
                        continue;
                memset(&xfs_uuid_table[i], 0, sizeof(uuid_t));
                break;
        }
        ASSERT(i < xfs_uuid_table_size);
        mutex_unlock(&xfs_uuid_table_mutex);
}

/*
 * Check size of device based on the (data/realtime) block count.
 * Note: this check is used by the growfs code as well as mount.
 */
int
xfs_sb_validate_fsb_count(
        xfs_sb_t        *sbp,
        uint64_t        nblocks)
{
        uint64_t                max_bytes;

        ASSERT(sbp->sb_blocklog >= BBSHIFT);

        if (check_shl_overflow(nblocks, sbp->sb_blocklog, &max_bytes))
                return -EFBIG;

        /* Limited by ULONG_MAX of page cache index */
        if (max_bytes >> PAGE_SHIFT > ULONG_MAX)
                return -EFBIG;
        return 0;
}

/*
 * xfs_readsb
 *
 * Does the initial read of the superblock.
 */
int
xfs_readsb(
        struct xfs_mount *mp,
        int                flags)
{
        unsigned int        sector_size;
        struct xfs_buf        *bp;
        struct xfs_sb        *sbp = &mp->m_sb;
        int                error;
        int                loud = !(flags & XFS_MFSI_QUIET);
        const struct xfs_buf_ops *buf_ops;

        ASSERT(mp->m_sb_bp == NULL);
        ASSERT(mp->m_ddev_targp != NULL);

        /*
         * For the initial read, we must guess at the sector
         * size based on the block device.  It's enough to
         * get the sb_sectsize out of the superblock and
         * then reread with the proper length.
         * We don't verify it yet, because it may not be complete.
         */
        sector_size = xfs_getsize_buftarg(mp->m_ddev_targp);
        buf_ops = NULL;

        /*
         * Allocate a (locked) buffer to hold the superblock. This will be kept
         * around at all times to optimize access to the superblock. Therefore,
         * set XBF_NO_IOACCT to make sure it doesn't hold the buftarg count
         * elevated.
         */
reread:
        error = xfs_buf_read_uncached(mp->m_ddev_targp, XFS_SB_DADDR,
                                      BTOBB(sector_size), XBF_NO_IOACCT, &bp,
                                      buf_ops);
        if (error) {
                if (loud)
                        xfs_warn(mp, "SB validate failed with error %d.", error);
                /* bad CRC means corrupted metadata */
                if (error == -EFSBADCRC)
                        error = -EFSCORRUPTED;
                return error;
        }

        /*
         * Initialize the mount structure from the superblock.
         */
        xfs_sb_from_disk(sbp, bp->b_addr);

        /*
         * If we haven't validated the superblock, do so now before we try
         * to check the sector size and reread the superblock appropriately.
         */
        if (sbp->sb_magicnum != XFS_SB_MAGIC) {
                if (loud)
                        xfs_warn(mp, "Invalid superblock magic number");
                error = -EINVAL;
                goto release_buf;
        }

        /*
         * We must be able to do sector-sized and sector-aligned IO.
         */
        if (sector_size > sbp->sb_sectsize) {
                if (loud)
                        xfs_warn(mp, "device supports %u byte sectors (not %u)",
                                sector_size, sbp->sb_sectsize);
                error = -ENOSYS;
                goto release_buf;
        }

        if (buf_ops == NULL) {
                /*
                 * Re-read the superblock so the buffer is correctly sized,
                 * and properly verified.
                 */
                xfs_buf_relse(bp);
                sector_size = sbp->sb_sectsize;
                buf_ops = loud ? &xfs_sb_buf_ops : &xfs_sb_quiet_buf_ops;
                goto reread;
        }

        mp->m_features |= xfs_sb_version_to_features(sbp);
        xfs_reinit_percpu_counters(mp);

        /*
         * If logged xattrs are enabled after log recovery finishes, then set
         * the opstate so that log recovery will work properly.
         */
        if (xfs_sb_version_haslogxattrs(&mp->m_sb))
                xfs_set_using_logged_xattrs(mp);

        /* no need to be quiet anymore, so reset the buf ops */
        bp->b_ops = &xfs_sb_buf_ops;

        mp->m_sb_bp = bp;
        xfs_buf_unlock(bp);
        return 0;

release_buf:
        xfs_buf_relse(bp);
        return error;
}

/*
 * If the sunit/swidth change would move the precomputed root inode value, we
 * must reject the ondisk change because repair will stumble over that.
 * However, we allow the mount to proceed because we never rejected this
 * combination before.  Returns true to update the sb, false otherwise.
 */
static inline int
xfs_check_new_dalign(
        struct xfs_mount        *mp,
        int                        new_dalign,
        bool                        *update_sb)
{
        struct xfs_sb                *sbp = &mp->m_sb;
        xfs_ino_t                calc_ino;

        calc_ino = xfs_ialloc_calc_rootino(mp, new_dalign);
        trace_xfs_check_new_dalign(mp, new_dalign, calc_ino);

        if (sbp->sb_rootino == calc_ino) {
                *update_sb = true;
                return 0;
        }

        xfs_warn(mp,
"Cannot change stripe alignment; would require moving root inode.");

        /*
         * XXX: Next time we add a new incompat feature, this should start
         * returning -EINVAL to fail the mount.  Until then, spit out a warning
         * that we're ignoring the administrator's instructions.
         */
        xfs_warn(mp, "Skipping superblock stripe alignment update.");
        *update_sb = false;
        return 0;
}

/*
 * If we were provided with new sunit/swidth values as mount options, make sure
 * that they pass basic alignment and superblock feature checks, and convert
 * them into the same units (FSB) that everything else expects.  This step
 * /must/ be done before computing the inode geometry.
 */
STATIC int
xfs_validate_new_dalign(
        struct xfs_mount        *mp)
{
        if (mp->m_dalign == 0)
                return 0;

        /*
         * If stripe unit and stripe width are not multiples
         * of the fs blocksize turn off alignment.
         */
        if ((BBTOB(mp->m_dalign) & mp->m_blockmask) ||
            (BBTOB(mp->m_swidth) & mp->m_blockmask)) {
                xfs_warn(mp,
        "alignment check failed: sunit/swidth vs. blocksize(%d)",
                        mp->m_sb.sb_blocksize);
                return -EINVAL;
        }

        /*
         * Convert the stripe unit and width to FSBs.
         */
        mp->m_dalign = XFS_BB_TO_FSBT(mp, mp->m_dalign);
        if (mp->m_dalign && (mp->m_sb.sb_agblocks % mp->m_dalign)) {
                xfs_warn(mp,
        "alignment check failed: sunit/swidth vs. agsize(%d)",
                        mp->m_sb.sb_agblocks);
                return -EINVAL;
        }

        if (!mp->m_dalign) {
                xfs_warn(mp,
        "alignment check failed: sunit(%d) less than bsize(%d)",
                        mp->m_dalign, mp->m_sb.sb_blocksize);
                return -EINVAL;
        }

        mp->m_swidth = XFS_BB_TO_FSBT(mp, mp->m_swidth);

        if (!xfs_has_dalign(mp)) {
                xfs_warn(mp,
"cannot change alignment: superblock does not support data alignment");
                return -EINVAL;
        }

        return 0;
}

/* Update alignment values based on mount options and sb values. */
STATIC int
xfs_update_alignment(
        struct xfs_mount        *mp)
{
        struct xfs_sb                *sbp = &mp->m_sb;

        if (mp->m_dalign) {
                bool                update_sb;
                int                error;

                if (sbp->sb_unit == mp->m_dalign &&
                    sbp->sb_width == mp->m_swidth)
                        return 0;

                error = xfs_check_new_dalign(mp, mp->m_dalign, &update_sb);
                if (error || !update_sb)
                        return error;

                sbp->sb_unit = mp->m_dalign;
                sbp->sb_width = mp->m_swidth;
                mp->m_update_sb = true;
        } else if (!xfs_has_noalign(mp) && xfs_has_dalign(mp)) {
                mp->m_dalign = sbp->sb_unit;
                mp->m_swidth = sbp->sb_width;
        }

        return 0;
}

/*
 * precalculate the low space thresholds for dynamic speculative preallocation.
 */
void
xfs_set_low_space_thresholds(
        struct xfs_mount        *mp)
{
        uint64_t                dblocks = mp->m_sb.sb_dblocks;
        uint64_t                rtexts = mp->m_sb.sb_rextents;
        int                        i;

        do_div(dblocks, 100);
        do_div(rtexts, 100);

        for (i = 0; i < XFS_LOWSP_MAX; i++) {
                mp->m_low_space[i] = dblocks * (i + 1);
                mp->m_low_rtexts[i] = rtexts * (i + 1);
        }
}

/*
 * Check that the data (and log if separate) is an ok size.
 */
STATIC int
xfs_check_sizes(
        struct xfs_mount *mp)
{
        struct xfs_buf        *bp;
        xfs_daddr_t        d;
        int                error;

        d = (xfs_daddr_t)XFS_FSB_TO_BB(mp, mp->m_sb.sb_dblocks);
        if (XFS_BB_TO_FSB(mp, d) != mp->m_sb.sb_dblocks) {
                xfs_warn(mp, "filesystem size mismatch detected");
                return -EFBIG;
        }
        error = xfs_buf_read_uncached(mp->m_ddev_targp,
                                        d - XFS_FSS_TO_BB(mp, 1),
                                        XFS_FSS_TO_BB(mp, 1), 0, &bp, NULL);
        if (error) {
                xfs_warn(mp, "last sector read failed");
                return error;
        }
        xfs_buf_relse(bp);

        if (mp->m_logdev_targp == mp->m_ddev_targp)
                return 0;

        d = (xfs_daddr_t)XFS_FSB_TO_BB(mp, mp->m_sb.sb_logblocks);
        if (XFS_BB_TO_FSB(mp, d) != mp->m_sb.sb_logblocks) {
                xfs_warn(mp, "log size mismatch detected");
                return -EFBIG;
        }
        error = xfs_buf_read_uncached(mp->m_logdev_targp,
                                        d - XFS_FSB_TO_BB(mp, 1),
                                        XFS_FSB_TO_BB(mp, 1), 0, &bp, NULL);
        if (error) {
                xfs_warn(mp, "log device read failed");
                return error;
        }
        xfs_buf_relse(bp);
        return 0;
}

/*
 * Clear the quotaflags in memory and in the superblock.
 */
int
xfs_mount_reset_sbqflags(
        struct xfs_mount        *mp)
{
        mp->m_qflags = 0;

        /* It is OK to look at sb_qflags in the mount path without m_sb_lock. */
        if (mp->m_sb.sb_qflags == 0)
                return 0;
        spin_lock(&mp->m_sb_lock);
        mp->m_sb.sb_qflags = 0;
        spin_unlock(&mp->m_sb_lock);

        if (!xfs_fs_writable(mp, SB_FREEZE_WRITE))
                return 0;

        return xfs_sync_sb(mp, false);
}

uint64_t
xfs_default_resblks(xfs_mount_t *mp)
{
        uint64_t resblks;

        /*
         * We default to 5% or 8192 fsbs of space reserved, whichever is
         * smaller.  This is intended to cover concurrent allocation
         * transactions when we initially hit enospc. These each require a 4
         * block reservation. Hence by default we cover roughly 2000 concurrent
         * allocation reservations.
         */
        resblks = mp->m_sb.sb_dblocks;
        do_div(resblks, 20);
        resblks = min_t(uint64_t, resblks, 8192);
        return resblks;
}

/* Ensure the summary counts are correct. */
STATIC int
xfs_check_summary_counts(
        struct xfs_mount        *mp)
{
        int                        error = 0;

        /*
         * The AG0 superblock verifier rejects in-progress filesystems,
         * so we should never see the flag set this far into mounting.
         */
        if (mp->m_sb.sb_inprogress) {
                xfs_err(mp, "sb_inprogress set after log recovery??");
                WARN_ON(1);
                return -EFSCORRUPTED;
        }

        /*
         * Now the log is mounted, we know if it was an unclean shutdown or
         * not. If it was, with the first phase of recovery has completed, we
         * have consistent AG blocks on disk. We have not recovered EFIs yet,
         * but they are recovered transactionally in the second recovery phase
         * later.
         *
         * If the log was clean when we mounted, we can check the summary
         * counters.  If any of them are obviously incorrect, we can recompute
         * them from the AGF headers in the next step.
         */
        if (xfs_is_clean(mp) &&
            (mp->m_sb.sb_fdblocks > mp->m_sb.sb_dblocks ||
             !xfs_verify_icount(mp, mp->m_sb.sb_icount) ||
             mp->m_sb.sb_ifree > mp->m_sb.sb_icount))
                xfs_fs_mark_sick(mp, XFS_SICK_FS_COUNTERS);

        /*
         * We can safely re-initialise incore superblock counters from the
         * per-ag data. These may not be correct if the filesystem was not
         * cleanly unmounted, so we waited for recovery to finish before doing
         * this.
         *
         * If the filesystem was cleanly unmounted or the previous check did
         * not flag anything weird, then we can trust the values in the
         * superblock to be correct and we don't need to do anything here.
         * Otherwise, recalculate the summary counters.
         */
        if ((xfs_has_lazysbcount(mp) && !xfs_is_clean(mp)) ||
            xfs_fs_has_sickness(mp, XFS_SICK_FS_COUNTERS)) {
                error = xfs_initialize_perag_data(mp, mp->m_sb.sb_agcount);
                if (error)
                        return error;
        }

        /*
         * Older kernels misused sb_frextents to reflect both incore
         * reservations made by running transactions and the actual count of
         * free rt extents in the ondisk metadata.  Transactions committed
         * during runtime can therefore contain a superblock update that
         * undercounts the number of free rt extents tracked in the rt bitmap.
         * A clean unmount record will have the correct frextents value since
         * there can be no other transactions running at that point.
         *
         * If we're mounting the rt volume after recovering the log, recompute
         * frextents from the rtbitmap file to fix the inconsistency.
         */
        if (xfs_has_realtime(mp) && !xfs_is_clean(mp)) {
                error = xfs_rtalloc_reinit_frextents(mp);
                if (error)
                        return error;
        }

        return 0;
}

static void
xfs_unmount_check(
        struct xfs_mount        *mp)
{
        if (xfs_is_shutdown(mp))
                return;

        if (percpu_counter_sum(&mp->m_ifree) >
                        percpu_counter_sum(&mp->m_icount)) {
                xfs_alert(mp, "ifree/icount mismatch at unmount");
                xfs_fs_mark_sick(mp, XFS_SICK_FS_COUNTERS);
        }
}

/*
 * Flush and reclaim dirty inodes in preparation for unmount. Inodes and
 * internal inode structures can be sitting in the CIL and AIL at this point,
 * so we need to unpin them, write them back and/or reclaim them before unmount
 * can proceed.  In other words, callers are required to have inactivated all
 * inodes.
 *
 * An inode cluster that has been freed can have its buffer still pinned in
 * memory because the transaction is still sitting in a iclog. The stale inodes
 * on that buffer will be pinned to the buffer until the transaction hits the
 * disk and the callbacks run. Pushing the AIL will skip the stale inodes and
 * may never see the pinned buffer, so nothing will push out the iclog and
 * unpin the buffer.
 *
 * Hence we need to force the log to unpin everything first. However, log
 * forces don't wait for the discards they issue to complete, so we have to
 * explicitly wait for them to complete here as well.
 *
 * Then we can tell the world we are unmounting so that error handling knows
 * that the filesystem is going away and we should error out anything that we
 * have been retrying in the background.  This will prevent never-ending
 * retries in AIL pushing from hanging the unmount.
 *
 * Finally, we can push the AIL to clean all the remaining dirty objects, then
 * reclaim the remaining inodes that are still in memory at this point in time.
 */
static void
xfs_unmount_flush_inodes(
        struct xfs_mount        *mp)
{
        xfs_log_force(mp, XFS_LOG_SYNC);
        xfs_extent_busy_wait_all(mp);
        flush_workqueue(xfs_discard_wq);

        xfs_set_unmounting(mp);

        xfs_ail_push_all_sync(mp->m_ail);
        xfs_inodegc_stop(mp);
        cancel_delayed_work_sync(&mp->m_reclaim_work);
        xfs_reclaim_inodes(mp);
        xfs_health_unmount(mp);
}

static void
xfs_mount_setup_inode_geom(
        struct xfs_mount        *mp)
{
        struct xfs_ino_geometry *igeo = M_IGEO(mp);

        igeo->attr_fork_offset = xfs_bmap_compute_attr_offset(mp);
        ASSERT(igeo->attr_fork_offset < XFS_LITINO(mp));

        xfs_ialloc_setup_geometry(mp);
}

/* Mount the metadata directory tree root. */
STATIC int
xfs_mount_setup_metadir(
        struct xfs_mount        *mp)
{
        int                        error;

        /* Load the metadata directory root inode into memory. */
        error = xfs_metafile_iget(mp, mp->m_sb.sb_metadirino, XFS_METAFILE_DIR,
                        &mp->m_metadirip);
        if (error)
                xfs_warn(mp, "Failed to load metadir root directory, error %d",
                                error);
        return error;
}

/* Compute maximum possible height for per-AG btree types for this fs. */
static inline void
xfs_agbtree_compute_maxlevels(
        struct xfs_mount        *mp)
{
        unsigned int                levels;

        levels = max(mp->m_alloc_maxlevels, M_IGEO(mp)->inobt_maxlevels);
        levels = max(levels, mp->m_rmap_maxlevels);
        mp->m_agbtree_maxlevels = max(levels, mp->m_refc_maxlevels);
}

/*
 * This function does the following on an initial mount of a file system:
 *        - reads the superblock from disk and init the mount struct
 *        - if we're a 32-bit kernel, do a size check on the superblock
 *                so we don't mount terabyte filesystems
 *        - init mount struct realtime fields
 *        - allocate inode hash table for fs
 *        - init directory manager
 *        - perform recovery and init the log manager
 */
int
xfs_mountfs(
        struct xfs_mount        *mp)
{
        struct xfs_sb                *sbp = &(mp->m_sb);
        struct xfs_inode        *rip;
        struct xfs_ino_geometry        *igeo = M_IGEO(mp);
        uint                        quotamount = 0;
        uint                        quotaflags = 0;
        int                        error = 0;

        xfs_sb_mount_common(mp, sbp);

        /*
         * Check for a mismatched features2 values.  Older kernels read & wrote
         * into the wrong sb offset for sb_features2 on some platforms due to
         * xfs_sb_t not being 64bit size aligned when sb_features2 was added,
         * which made older superblock reading/writing routines swap it as a
         * 64-bit value.
         *
         * For backwards compatibility, we make both slots equal.
         *
         * If we detect a mismatched field, we OR the set bits into the existing
         * features2 field in case it has already been modified; we don't want
         * to lose any features.  We then update the bad location with the ORed
         * value so that older kernels will see any features2 flags. The
         * superblock writeback code ensures the new sb_features2 is copied to
         * sb_bad_features2 before it is logged or written to disk.
         */
        if (xfs_sb_has_mismatched_features2(sbp)) {
                xfs_warn(mp, "correcting sb_features alignment problem");
                sbp->sb_features2 |= sbp->sb_bad_features2;
                mp->m_update_sb = true;
        }


        /* always use v2 inodes by default now */
        if (!(mp->m_sb.sb_versionnum & XFS_SB_VERSION_NLINKBIT)) {
                mp->m_sb.sb_versionnum |= XFS_SB_VERSION_NLINKBIT;
                mp->m_features |= XFS_FEAT_NLINK;
                mp->m_update_sb = true;
        }

        /*
         * If we were given new sunit/swidth options, do some basic validation
         * checks and convert the incore dalign and swidth values to the
         * same units (FSB) that everything else uses.  This /must/ happen
         * before computing the inode geometry.
         */
        error = xfs_validate_new_dalign(mp);
        if (error)
                goto out;

        xfs_alloc_compute_maxlevels(mp);
        xfs_bmap_compute_maxlevels(mp, XFS_DATA_FORK);
        xfs_bmap_compute_maxlevels(mp, XFS_ATTR_FORK);
        xfs_mount_setup_inode_geom(mp);
        xfs_rmapbt_compute_maxlevels(mp);
        xfs_refcountbt_compute_maxlevels(mp);

        xfs_agbtree_compute_maxlevels(mp);

        /*
         * Check if sb_agblocks is aligned at stripe boundary.  If sb_agblocks
         * is NOT aligned turn off m_dalign since allocator alignment is within
         * an ag, therefore ag has to be aligned at stripe boundary.  Note that
         * we must compute the free space and rmap btree geometry before doing
         * this.
         */
        error = xfs_update_alignment(mp);
        if (error)
                goto out;

        /* enable fail_at_unmount as default */
        mp->m_fail_unmount = true;

        super_set_sysfs_name_id(mp->m_super);

        error = xfs_sysfs_init(&mp->m_kobj, &xfs_mp_ktype,
                               NULL, mp->m_super->s_id);
        if (error)
                goto out;

        error = xfs_sysfs_init(&mp->m_stats.xs_kobj, &xfs_stats_ktype,
                               &mp->m_kobj, "stats");
        if (error)
                goto out_remove_sysfs;

        xchk_stats_register(mp->m_scrub_stats, mp->m_debugfs);

        error = xfs_error_sysfs_init(mp);
        if (error)
                goto out_remove_scrub_stats;

        error = xfs_errortag_init(mp);
        if (error)
                goto out_remove_error_sysfs;

        error = xfs_uuid_mount(mp);
        if (error)
                goto out_remove_errortag;

        /*
         * Update the preferred write size based on the information from the
         * on-disk superblock.
         */
        mp->m_allocsize_log =
                max_t(uint32_t, sbp->sb_blocklog, mp->m_allocsize_log);
        mp->m_allocsize_blocks = 1U << (mp->m_allocsize_log - sbp->sb_blocklog);

        /* set the low space thresholds for dynamic preallocation */
        xfs_set_low_space_thresholds(mp);

        /*
         * If enabled, sparse inode chunk alignment is expected to match the
         * cluster size. Full inode chunk alignment must match the chunk size,
         * but that is checked on sb read verification...
         */
        if (xfs_has_sparseinodes(mp) &&
            mp->m_sb.sb_spino_align !=
                        XFS_B_TO_FSBT(mp, igeo->inode_cluster_size_raw)) {
                xfs_warn(mp,
        "Sparse inode block alignment (%u) must match cluster size (%llu).",
                         mp->m_sb.sb_spino_align,
                         XFS_B_TO_FSBT(mp, igeo->inode_cluster_size_raw));
                error = -EINVAL;
                goto out_remove_uuid;
        }

        /*
         * Check that the data (and log if separate) is an ok size.
         */
        error = xfs_check_sizes(mp);
        if (error)
                goto out_remove_uuid;

        /*
         * Initialize realtime fields in the mount structure
         */
        error = xfs_rtmount_init(mp);
        if (error) {
                xfs_warn(mp, "RT mount failed");
                goto out_remove_uuid;
        }

        /*
         *  Copies the low order bits of the timestamp and the randomly
         *  set "sequence" number out of a UUID.
         */
        mp->m_fixedfsid[0] =
                (get_unaligned_be16(&sbp->sb_uuid.b[8]) << 16) |
                 get_unaligned_be16(&sbp->sb_uuid.b[4]);
        mp->m_fixedfsid[1] = get_unaligned_be32(&sbp->sb_uuid.b[0]);

        error = xfs_da_mount(mp);
        if (error) {
                xfs_warn(mp, "Failed dir/attr init: %d", error);
                goto out_remove_uuid;
        }

        /*
         * Initialize the precomputed transaction reservations values.
         */
        xfs_trans_init(mp);

        /*
         * Allocate and initialize the per-ag data.
         */
        error = xfs_initialize_perag(mp, 0, sbp->sb_agcount,
                        mp->m_sb.sb_dblocks, &mp->m_maxagi);
        if (error) {
                xfs_warn(mp, "Failed per-ag init: %d", error);
                goto out_free_dir;
        }

        error = xfs_initialize_rtgroups(mp, 0, sbp->sb_rgcount,
                        mp->m_sb.sb_rextents);
        if (error) {
                xfs_warn(mp, "Failed rtgroup init: %d", error);
                goto out_free_perag;
        }

        if (XFS_IS_CORRUPT(mp, !sbp->sb_logblocks)) {
                xfs_warn(mp, "no log defined");
                error = -EFSCORRUPTED;
                goto out_free_rtgroup;
        }

        error = xfs_inodegc_register_shrinker(mp);
        if (error)
                goto out_fail_wait;

        /*
         * If we're resuming quota status, pick up the preliminary qflags from
         * the ondisk superblock so that we know if we should recover dquots.
         */
        if (xfs_is_resuming_quotaon(mp))
                xfs_qm_resume_quotaon(mp);

        /*
         * Log's mount-time initialization. The first part of recovery can place
         * some items on the AIL, to be handled when recovery is finished or
         * cancelled.
         */
        error = xfs_log_mount(mp, mp->m_logdev_targp,
                              XFS_FSB_TO_DADDR(mp, sbp->sb_logstart),
                              XFS_FSB_TO_BB(mp, sbp->sb_logblocks));
        if (error) {
                xfs_warn(mp, "log mount failed");
                goto out_inodegc_shrinker;
        }

        /*
         * If we're resuming quota status and recovered the log, re-sample the
         * qflags from the ondisk superblock now that we've recovered it, just
         * in case someone shut down enforcement just before a crash.
         */
        if (xfs_clear_resuming_quotaon(mp) && xlog_recovery_needed(mp->m_log))
                xfs_qm_resume_quotaon(mp);

        /*
         * If logged xattrs are still enabled after log recovery finishes, then
         * they'll be available until unmount.  Otherwise, turn them off.
         */
        if (xfs_sb_version_haslogxattrs(&mp->m_sb))
                xfs_set_using_logged_xattrs(mp);
        else
                xfs_clear_using_logged_xattrs(mp);

        /* Enable background inode inactivation workers. */
        xfs_inodegc_start(mp);
        xfs_blockgc_start(mp);

        /*
         * Now that we've recovered any pending superblock feature bit
         * additions, we can finish setting up the attr2 behaviour for the
         * mount. The noattr2 option overrides the superblock flag, so only
         * check the superblock feature flag if the mount option is not set.
         */
        if (xfs_has_noattr2(mp)) {
                mp->m_features &= ~XFS_FEAT_ATTR2;
        } else if (!xfs_has_attr2(mp) &&
                   (mp->m_sb.sb_features2 & XFS_SB_VERSION2_ATTR2BIT)) {
                mp->m_features |= XFS_FEAT_ATTR2;
        }

        if (xfs_has_metadir(mp)) {
                error = xfs_mount_setup_metadir(mp);
                if (error)
                        goto out_free_metadir;
        }

        /*
         * Get and sanity-check the root inode.
         * Save the pointer to it in the mount structure.
         */
        error = xfs_iget(mp, NULL, sbp->sb_rootino, XFS_IGET_UNTRUSTED,
                         XFS_ILOCK_EXCL, &rip);
        if (error) {
                xfs_warn(mp,
                        "Failed to read root inode 0x%llx, error %d",
                        sbp->sb_rootino, -error);
                goto out_free_metadir;
        }

        ASSERT(rip != NULL);

        if (XFS_IS_CORRUPT(mp, !S_ISDIR(VFS_I(rip)->i_mode))) {
                xfs_warn(mp, "corrupted root inode %llu: not a directory",
                        (unsigned long long)rip->i_ino);
                xfs_iunlock(rip, XFS_ILOCK_EXCL);
                error = -EFSCORRUPTED;
                goto out_rele_rip;
        }
        mp->m_rootip = rip;        /* save it */

        xfs_iunlock(rip, XFS_ILOCK_EXCL);

        /*
         * Initialize realtime inode pointers in the mount structure
         */
        error = xfs_rtmount_inodes(mp);
        if (error) {
                /*
                 * Free up the root inode.
                 */
                xfs_warn(mp, "failed to read RT inodes");
                goto out_rele_rip;
        }

        /* Make sure the summary counts are ok. */
        error = xfs_check_summary_counts(mp);
        if (error)
                goto out_rtunmount;

        /*
         * If this is a read-only mount defer the superblock updates until
         * the next remount into writeable mode.  Otherwise we would never
         * perform the update e.g. for the root filesystem.
         */
        if (mp->m_update_sb && !xfs_is_readonly(mp)) {
                error = xfs_sync_sb(mp, false);
                if (error) {
                        xfs_warn(mp, "failed to write sb changes");
                        goto out_rtunmount;
                }
        }

        /*
         * Initialise the XFS quota management subsystem for this mount
         */
        if (XFS_IS_QUOTA_ON(mp)) {
                error = xfs_qm_newmount(mp, &quotamount, &quotaflags);
                if (error)
                        goto out_rtunmount;
        } else {
                /*
                 * If a file system had quotas running earlier, but decided to
                 * mount without -o uquota/pquota/gquota options, revoke the
                 * quotachecked license.
                 */
                if (mp->m_sb.sb_qflags & XFS_ALL_QUOTA_ACCT) {
                        xfs_notice(mp, "resetting quota flags");
                        error = xfs_mount_reset_sbqflags(mp);
                        if (error)
                                goto out_rtunmount;
                }
        }

        /*
         * Finish recovering the file system.  This part needed to be delayed
         * until after the root and real-time bitmap inodes were consistently
         * read in.  Temporarily create per-AG space reservations for metadata
         * btree shape changes because space freeing transactions (for inode
         * inactivation) require the per-AG reservation in lieu of reserving
         * blocks.
         */
        error = xfs_fs_reserve_ag_blocks(mp);
        if (error && error == -ENOSPC)
                xfs_warn(mp,
        "ENOSPC reserving per-AG metadata pool, log recovery may fail.");
        error = xfs_log_mount_finish(mp);
        xfs_fs_unreserve_ag_blocks(mp);
        if (error) {
                xfs_warn(mp, "log mount finish failed");
                goto out_rtunmount;
        }

        /*
         * Now the log is fully replayed, we can transition to full read-only
         * mode for read-only mounts. This will sync all the metadata and clean
         * the log so that the recovery we just performed does not have to be
         * replayed again on the next mount.
         *
         * We use the same quiesce mechanism as the rw->ro remount, as they are
         * semantically identical operations.
         */
        if (xfs_is_readonly(mp) && !xfs_has_norecovery(mp))
                xfs_log_clean(mp);

        /*
         * Complete the quota initialisation, post-log-replay component.
         */
        if (quotamount) {
                ASSERT(mp->m_qflags == 0);
                mp->m_qflags = quotaflags;

                xfs_qm_mount_quotas(mp);
        }

        /*
         * Now we are mounted, reserve a small amount of unused space for
         * privileged transactions. This is needed so that transaction
         * space required for critical operations can dip into this pool
         * when at ENOSPC. This is needed for operations like create with
         * attr, unwritten extent conversion at ENOSPC, etc. Data allocations
         * are not allowed to use this reserved space.
         *
         * This may drive us straight to ENOSPC on mount, but that implies
         * we were already there on the last unmount. Warn if this occurs.
         */
        if (!xfs_is_readonly(mp)) {
                error = xfs_reserve_blocks(mp, xfs_default_resblks(mp));
                if (error)
                        xfs_warn(mp,
        "Unable to allocate reserve blocks. Continuing without reserve pool.");

                /* Reserve AG blocks for future btree expansion. */
                error = xfs_fs_reserve_ag_blocks(mp);
                if (error && error != -ENOSPC)
                        goto out_agresv;
        }

        return 0;

 out_agresv:
        xfs_fs_unreserve_ag_blocks(mp);
        xfs_qm_unmount_quotas(mp);
 out_rtunmount:
        xfs_rtunmount_inodes(mp);
 out_rele_rip:
        xfs_irele(rip);
        /* Clean out dquots that might be in memory after quotacheck. */
        xfs_qm_unmount(mp);
 out_free_metadir:
        if (mp->m_metadirip)
                xfs_irele(mp->m_metadirip);

        /*
         * Inactivate all inodes that might still be in memory after a log
         * intent recovery failure so that reclaim can free them.  Metadata
         * inodes and the root directory shouldn't need inactivation, but the
         * mount failed for some reason, so pull down all the state and flee.
         */
        xfs_inodegc_flush(mp);

        /*
         * Flush all inode reclamation work and flush the log.
         * We have to do this /after/ rtunmount and qm_unmount because those
         * two will have scheduled delayed reclaim for the rt/quota inodes.
         *
         * This is slightly different from the unmountfs call sequence
         * because we could be tearing down a partially set up mount.  In
         * particular, if log_mount_finish fails we bail out without calling
         * qm_unmount_quotas and therefore rely on qm_unmount to release the
         * quota inodes.
         */
        xfs_unmount_flush_inodes(mp);
        xfs_log_mount_cancel(mp);
 out_inodegc_shrinker:
        shrinker_free(mp->m_inodegc_shrinker);
 out_fail_wait:
        if (mp->m_logdev_targp && mp->m_logdev_targp != mp->m_ddev_targp)
                xfs_buftarg_drain(mp->m_logdev_targp);
        xfs_buftarg_drain(mp->m_ddev_targp);
 out_free_rtgroup:
        xfs_free_rtgroups(mp, 0, mp->m_sb.sb_rgcount);
 out_free_perag:
        xfs_free_perag_range(mp, 0, mp->m_sb.sb_agcount);
 out_free_dir:
        xfs_da_unmount(mp);
 out_remove_uuid:
        xfs_uuid_unmount(mp);
 out_remove_errortag:
        xfs_errortag_del(mp);
 out_remove_error_sysfs:
        xfs_error_sysfs_del(mp);
 out_remove_scrub_stats:
        xchk_stats_unregister(mp->m_scrub_stats);
        xfs_sysfs_del(&mp->m_stats.xs_kobj);
 out_remove_sysfs:
        xfs_sysfs_del(&mp->m_kobj);
 out:
        return error;
}

/*
 * This flushes out the inodes,dquots and the superblock, unmounts the
 * log and makes sure that incore structures are freed.
 */
void
xfs_unmountfs(
        struct xfs_mount        *mp)
{
        int                        error;

        /*
         * Perform all on-disk metadata updates required to inactivate inodes
         * that the VFS evicted earlier in the unmount process.  Freeing inodes
         * and discarding CoW fork preallocations can cause shape changes to
         * the free inode and refcount btrees, respectively, so we must finish
         * this before we discard the metadata space reservations.  Metadata
         * inodes and the root directory do not require inactivation.
         */
        xfs_inodegc_flush(mp);

        xfs_blockgc_stop(mp);
        xfs_fs_unreserve_ag_blocks(mp);
        xfs_qm_unmount_quotas(mp);
        xfs_rtunmount_inodes(mp);
        xfs_irele(mp->m_rootip);
        if (mp->m_metadirip)
                xfs_irele(mp->m_metadirip);

        xfs_unmount_flush_inodes(mp);

        xfs_qm_unmount(mp);

        /*
         * Unreserve any blocks we have so that when we unmount we don't account
         * the reserved free space as used. This is really only necessary for
         * lazy superblock counting because it trusts the incore superblock
         * counters to be absolutely correct on clean unmount.
         *
         * We don't bother correcting this elsewhere for lazy superblock
         * counting because on mount of an unclean filesystem we reconstruct the
         * correct counter value and this is irrelevant.
         *
         * For non-lazy counter filesystems, this doesn't matter at all because
         * we only every apply deltas to the superblock and hence the incore
         * value does not matter....
         */
        error = xfs_reserve_blocks(mp, 0);
        if (error)
                xfs_warn(mp, "Unable to free reserved block pool. "
                                "Freespace may not be correct on next mount.");
        xfs_unmount_check(mp);

        /*
         * Indicate that it's ok to clear log incompat bits before cleaning
         * the log and writing the unmount record.
         */
        xfs_set_done_with_log_incompat(mp);
        xfs_log_unmount(mp);
        xfs_da_unmount(mp);
        xfs_uuid_unmount(mp);

#if defined(DEBUG)
        xfs_errortag_clearall(mp);
#endif
        shrinker_free(mp->m_inodegc_shrinker);
        xfs_free_rtgroups(mp, 0, mp->m_sb.sb_rgcount);
        xfs_free_perag_range(mp, 0, mp->m_sb.sb_agcount);
        xfs_errortag_del(mp);
        xfs_error_sysfs_del(mp);
        xchk_stats_unregister(mp->m_scrub_stats);
        xfs_sysfs_del(&mp->m_stats.xs_kobj);
        xfs_sysfs_del(&mp->m_kobj);
}

/*
 * Determine whether modifications can proceed. The caller specifies the minimum
 * freeze level for which modifications should not be allowed. This allows
 * certain operations to proceed while the freeze sequence is in progress, if
 * necessary.
 */
bool
xfs_fs_writable(
        struct xfs_mount        *mp,
        int                        level)
{
        ASSERT(level > SB_UNFROZEN);
        if ((mp->m_super->s_writers.frozen >= level) ||
            xfs_is_shutdown(mp) || xfs_is_readonly(mp))
                return false;

        return true;
}

void
xfs_add_freecounter(
        struct xfs_mount        *mp,
        struct percpu_counter        *counter,
        uint64_t                delta)
{
        bool                        has_resv_pool = (counter == &mp->m_fdblocks);
        uint64_t                res_used;

        /*
         * If the reserve pool is depleted, put blocks back into it first.
         * Most of the time the pool is full.
         */
        if (!has_resv_pool || mp->m_resblks == mp->m_resblks_avail) {
                percpu_counter_add(counter, delta);
                return;
        }

        spin_lock(&mp->m_sb_lock);
        res_used = mp->m_resblks - mp->m_resblks_avail;
        if (res_used > delta) {
                mp->m_resblks_avail += delta;
        } else {
                delta -= res_used;
                mp->m_resblks_avail = mp->m_resblks;
                percpu_counter_add(counter, delta);
        }
        spin_unlock(&mp->m_sb_lock);
}

int
xfs_dec_freecounter(
        struct xfs_mount        *mp,
        struct percpu_counter        *counter,
        uint64_t                delta,
        bool                        rsvd)
{
        int64_t                        lcounter;
        uint64_t                set_aside = 0;
        s32                        batch;
        bool                        has_resv_pool;

        ASSERT(counter == &mp->m_fdblocks || counter == &mp->m_frextents);
        has_resv_pool = (counter == &mp->m_fdblocks);
        if (rsvd)
                ASSERT(has_resv_pool);

        /*
         * Taking blocks away, need to be more accurate the closer we
         * are to zero.
         *
         * If the counter has a value of less than 2 * max batch size,
         * then make everything serialise as we are real close to
         * ENOSPC.
         */
        if (__percpu_counter_compare(counter, 2 * XFS_FDBLOCKS_BATCH,
                                     XFS_FDBLOCKS_BATCH) < 0)
                batch = 1;
        else
                batch = XFS_FDBLOCKS_BATCH;

        /*
         * Set aside allocbt blocks because these blocks are tracked as free
         * space but not available for allocation. Technically this means that a
         * single reservation cannot consume all remaining free space, but the
         * ratio of allocbt blocks to usable free blocks should be rather small.
         * The tradeoff without this is that filesystems that maintain high
         * perag block reservations can over reserve physical block availability
         * and fail physical allocation, which leads to much more serious
         * problems (i.e. transaction abort, pagecache discards, etc.) than
         * slightly premature -ENOSPC.
         */
        if (has_resv_pool)
                set_aside = xfs_fdblocks_unavailable(mp);
        percpu_counter_add_batch(counter, -((int64_t)delta), batch);
        if (__percpu_counter_compare(counter, set_aside,
                                     XFS_FDBLOCKS_BATCH) >= 0) {
                /* we had space! */
                return 0;
        }

        /*
         * lock up the sb for dipping into reserves before releasing the space
         * that took us to ENOSPC.
         */
        spin_lock(&mp->m_sb_lock);
        percpu_counter_add(counter, delta);
        if (!has_resv_pool || !rsvd)
                goto fdblocks_enospc;

        lcounter = (long long)mp->m_resblks_avail - delta;
        if (lcounter >= 0) {
                mp->m_resblks_avail = lcounter;
                spin_unlock(&mp->m_sb_lock);
                return 0;
        }
        xfs_warn_once(mp,
"Reserve blocks depleted! Consider increasing reserve pool size.");

fdblocks_enospc:
        spin_unlock(&mp->m_sb_lock);
        return -ENOSPC;
}

/*
 * Used to free the superblock along various error paths.
 */
void
xfs_freesb(
        struct xfs_mount        *mp)
{
        struct xfs_buf                *bp = mp->m_sb_bp;

        xfs_buf_lock(bp);
        mp->m_sb_bp = NULL;
        xfs_buf_relse(bp);
}

/*
 * If the underlying (data/log/rt) device is readonly, there are some
 * operations that cannot proceed.
 */
int
xfs_dev_is_read_only(
        struct xfs_mount        *mp,
        char                        *message)
{
        if (xfs_readonly_buftarg(mp->m_ddev_targp) ||
            xfs_readonly_buftarg(mp->m_logdev_targp) ||
            (mp->m_rtdev_targp && xfs_readonly_buftarg(mp->m_rtdev_targp))) {
                xfs_notice(mp, "%s required on read-only device.", message);
                xfs_notice(mp, "write access unavailable, cannot proceed.");
                return -EROFS;
        }
        return 0;
}

/* Force the summary counters to be recalculated at next mount. */
void
xfs_force_summary_recalc(
        struct xfs_mount        *mp)
{
        if (!xfs_has_lazysbcount(mp))
                return;

        xfs_fs_mark_sick(mp, XFS_SICK_FS_COUNTERS);
}

/*
 * Enable a log incompat feature flag in the primary superblock.  The caller
 * cannot have any other transactions in progress.
 */
int
xfs_add_incompat_log_feature(
        struct xfs_mount        *mp,
        uint32_t                feature)
{
        struct xfs_dsb                *dsb;
        int                        error;

        ASSERT(hweight32(feature) == 1);
        ASSERT(!(feature & XFS_SB_FEAT_INCOMPAT_LOG_UNKNOWN));

        /*
         * Force the log to disk and kick the background AIL thread to reduce
         * the chances that the bwrite will stall waiting for the AIL to unpin
         * the primary superblock buffer.  This isn't a data integrity
         * operation, so we don't need a synchronous push.
         */
        error = xfs_log_force(mp, XFS_LOG_SYNC);
        if (error)
                return error;
        xfs_ail_push_all(mp->m_ail);

        /*
         * Lock the primary superblock buffer to serialize all callers that
         * are trying to set feature bits.
         */
        xfs_buf_lock(mp->m_sb_bp);
        xfs_buf_hold(mp->m_sb_bp);

        if (xfs_is_shutdown(mp)) {
                error = -EIO;
                goto rele;
        }

        if (xfs_sb_has_incompat_log_feature(&mp->m_sb, feature))
                goto rele;

        /*
         * Write the primary superblock to disk immediately, because we need
         * the log_incompat bit to be set in the primary super now to protect
         * the log items that we're going to commit later.
         */
        dsb = mp->m_sb_bp->b_addr;
        xfs_sb_to_disk(dsb, &mp->m_sb);
        dsb->sb_features_log_incompat |= cpu_to_be32(feature);
        error = xfs_bwrite(mp->m_sb_bp);
        if (error)
                goto shutdown;

        /*
         * Add the feature bits to the incore superblock before we unlock the
         * buffer.
         */
        xfs_sb_add_incompat_log_features(&mp->m_sb, feature);
        xfs_buf_relse(mp->m_sb_bp);

        /* Log the superblock to disk. */
        return xfs_sync_sb(mp, false);
shutdown:
        xfs_force_shutdown(mp, SHUTDOWN_META_IO_ERROR);
rele:
        xfs_buf_relse(mp->m_sb_bp);
        return error;
}

/*
 * Clear all the log incompat flags from the superblock.
 *
 * The caller cannot be in a transaction, must ensure that the log does not
 * contain any log items protected by any log incompat bit, and must ensure
 * that there are no other threads that depend on the state of the log incompat
 * feature flags in the primary super.
 *
 * Returns true if the superblock is dirty.
 */
bool
xfs_clear_incompat_log_features(
        struct xfs_mount        *mp)
{
        bool                        ret = false;

        if (!xfs_has_crc(mp) ||
            !xfs_sb_has_incompat_log_feature(&mp->m_sb,
                                XFS_SB_FEAT_INCOMPAT_LOG_ALL) ||
            xfs_is_shutdown(mp) ||
            !xfs_is_done_with_log_incompat(mp))
                return false;

        /*
         * Update the incore superblock.  We synchronize on the primary super
         * buffer lock to be consistent with the add function, though at least
         * in theory this shouldn't be necessary.
         */
        xfs_buf_lock(mp->m_sb_bp);
        xfs_buf_hold(mp->m_sb_bp);

        if (xfs_sb_has_incompat_log_feature(&mp->m_sb,
                                XFS_SB_FEAT_INCOMPAT_LOG_ALL)) {
                xfs_sb_remove_incompat_log_features(&mp->m_sb);
                ret = true;
        }

        xfs_buf_relse(mp->m_sb_bp);
        return ret;
}

/*
 * Update the in-core delayed block counter.
 *
 * We prefer to update the counter without having to take a spinlock for every
 * counter update (i.e. batching).  Each change to delayed allocation
 * reservations can change can easily exceed the default percpu counter
 * batching, so we use a larger batch factor here.
 *
 * Note that we don't currently have any callers requiring fast summation
 * (e.g. percpu_counter_read) so we can use a big batch value here.
 */
#define XFS_DELALLOC_BATCH        (4096)
void
xfs_mod_delalloc(
        struct xfs_inode        *ip,
        int64_t                        data_delta,
        int64_t                        ind_delta)
{
        struct xfs_mount        *mp = ip->i_mount;

        if (XFS_IS_REALTIME_INODE(ip)) {
                percpu_counter_add_batch(&mp->m_delalloc_rtextents,
                                xfs_blen_to_rtbxlen(mp, data_delta),
                                XFS_DELALLOC_BATCH);
                if (!ind_delta)
                        return;
                data_delta = 0;
        }
        percpu_counter_add_batch(&mp->m_delalloc_blks, data_delta + ind_delta,
                        XFS_DELALLOC_BATCH);
}









































































































































































































   10 














































    2 






   12 

















   10 
   10 

    1 
   10 



    3 
    3 


    3 




   34 













   25 
   25 










   25 

   25 





    6 
    6 






    9 
   10 

   10 
   10 
    9 







    3 

    3 

    3 

    1 
    2 






   14 
    1 
















   14 


    2 


   12 


   12 
    4 
   10 







   10 


   10 













   10 












   14 




   14 






    1 




    1 








    4 




    4 


    4 




    4 






    4 






    3 
    1 
















    3 






    5 




    5 




    2 






    1 

    1 
    4 













   11 




    1 



   10 


    4 





















    9 




    9 








































































































   10 





   10 













   10 




   10 





    3 


    3 

    3 

    3 




    3 








   24 


   29 



































   10 

   10 


















   10 

















    8 


    3 





















    1 








    1 

    1 































    1 


    1 






    1 































































































































































































































































































































































































































































































































































































































































































































































































































































































































































































































































































































































































































































































   55 




    7 



    5 

    7 














































































































































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
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
1187
1188
1189
1190
1191
1192
1193
1194
1195
1196
1197
1198
1199
1200
1201
1202
1203
1204
1205
1206
1207
1208
1209
1210
1211
1212
1213
1214
1215
1216
1217
1218
1219
1220
1221
1222
1223
1224
1225
1226
1227
1228
1229
1230
1231
1232
1233
1234
1235
1236
1237
1238
1239
1240
1241
1242
1243
1244
1245
1246
1247
1248
1249
1250
1251
1252
1253
1254
1255
1256
1257
1258
1259
1260
1261
1262
1263
1264
1265
1266
1267
1268
1269
1270
1271
1272
1273
1274
1275
1276
1277
1278
1279
1280
1281
1282
1283
1284
1285
1286
1287
1288
1289
1290
1291
1292
1293
1294
1295
1296
1297
1298
1299
1300
1301
1302
1303
1304
1305
1306
1307
1308
1309
1310
1311
1312
1313
1314
1315
1316
1317
1318
1319
1320
1321
1322
1323
1324
1325
1326
1327
1328
1329
1330
1331
1332
1333
1334
1335
1336
1337
1338
1339
1340
1341
1342
1343
1344
1345
1346
1347
1348
1349
1350
1351
1352
1353
1354
1355
1356
1357
1358
1359
1360
1361
1362
1363
1364
1365
1366
1367
1368
1369
1370
1371
1372
1373
1374
1375
1376
1377
1378
1379
1380
1381
1382
1383
1384
1385
1386
1387
1388
1389
1390
1391
1392
1393
1394
1395
1396
1397
1398
1399
1400
1401
1402
1403
1404
1405
1406
1407
1408
1409
1410
1411
1412
1413
1414
1415
1416
1417
1418
1419
1420
1421
1422
1423
1424
1425
1426
1427
1428
1429
1430
1431
1432
1433
1434
1435
1436
1437
1438
1439
1440
1441
1442
1443
1444
1445
1446
1447
1448
1449
1450
1451
1452
1453
1454
1455
1456
1457
1458
1459
1460
1461
1462
1463
1464
1465
1466
1467
1468
1469
1470
1471
1472
1473
1474
1475
1476
1477
1478
1479
1480
1481
1482
1483
1484
1485
1486
1487
1488
1489
1490
1491
1492
1493
1494
1495
1496
1497
1498
1499
1500
1501
1502
1503
1504
1505
1506
1507
1508
1509
1510
1511
1512
1513
1514
1515
1516
1517
1518
1519
1520
1521
1522
1523
1524
1525
1526
1527
1528
1529
1530
1531
1532
1533
1534
1535
1536
1537
1538
1539
1540
1541
1542
1543
1544
1545
1546
1547
1548
1549
1550
1551
1552
1553
1554
1555
1556
1557
1558
1559
1560
1561
1562
1563
1564
1565
1566
1567
1568
1569
1570
1571
1572
1573
1574
1575
1576
1577
1578
1579
1580
1581
1582
1583
1584
1585
1586
1587
1588
1589
1590
1591
1592
1593
1594
1595
1596
1597
1598
1599
1600
1601
1602
1603
1604
1605
1606
1607
1608
1609
1610
1611
1612
1613
1614
1615
1616
1617
1618
1619
1620
1621
1622
1623
1624
1625
1626
1627
1628
1629
1630
1631
1632
1633
1634
1635
1636
1637
1638
1639
1640
1641
1642
1643
1644
1645
1646
1647
1648
1649
1650
1651
1652
1653
1654
1655
1656
1657
1658
1659
1660
1661
1662
1663
1664
1665
1666
1667
1668
1669
1670
1671
1672
1673
1674
1675
1676
1677
1678
1679
1680
1681
1682
1683
1684
1685
1686
1687
1688
1689
1690
1691
1692
1693
1694
1695
1696
1697
1698
1699
1700
1701
1702
1703
1704
1705
1706
1707
1708
1709
1710
1711
1712
1713
1714
1715
1716
1717
1718
1719
1720
1721
1722
1723
1724
1725
1726
1727
1728
1729
1730
1731
1732
1733
1734
1735
1736
1737
1738
1739
1740
1741
1742
1743
1744
1745
1746
1747
1748
1749
1750
1751
1752
1753
1754
1755
1756
1757
1758
1759
1760
1761
1762
1763
1764
1765
1766
1767
1768
1769
1770
1771
1772
1773
1774
1775
1776
1777
1778
1779
1780
1781
1782
1783
1784
1785
1786
1787
1788
1789
1790
1791
1792
1793
1794
1795
1796
1797
1798
1799
1800
1801
1802
1803
1804
1805
1806
1807
1808
1809
1810
1811
1812
1813
1814
1815
1816
1817
1818
1819
1820
1821
1822
1823
1824
1825
1826
1827
1828
1829
1830
1831
1832
1833
1834
1835
1836
1837
1838
1839
1840
1841
1842
1843
1844
1845
1846
1847
1848
1849
1850
1851
1852
1853
1854
1855
1856
1857
1858
1859
1860
1861
1862
1863
1864
1865
1866
1867
1868
1869
1870
1871
1872
1873
1874
1875
1876
1877
1878
1879
1880
1881
1882
1883
1884
1885
1886
1887
1888
1889
1890
1891
1892
1893
1894
1895
1896
1897
1898
1899
1900
1901
1902
1903
1904
1905
1906
1907
1908
1909
1910
1911
1912
1913
1914
1915
1916
1917
1918
1919
1920
1921
1922
1923
1924
1925
1926
1927
1928
1929
1930
1931
1932
1933
1934
1935
1936
1937
1938
1939
1940
1941
1942
1943
1944
1945
1946
1947
1948
1949
1950
1951
1952
1953
1954
1955
1956
1957
1958
1959
1960
1961
1962
1963
1964
1965
1966
1967
1968
1969
1970
1971
1972
1973
1974
1975
1976
1977
1978
1979
1980
1981
1982
1983
1984
1985
1986
1987
1988
1989
1990
1991
1992
1993
1994
1995
1996
1997
1998
1999
2000
2001
2002
2003
2004
2005
2006
2007
2008
2009
2010
2011
2012
2013
2014
2015
2016
2017
2018
2019
2020
2021
2022
2023
2024
2025
2026
2027
2028
2029
2030
2031
2032
2033
2034
2035
2036
2037
2038
2039
2040
2041
2042
2043
2044
2045
2046
2047
2048
2049
2050
2051
2052
2053
2054
2055
2056
2057
2058
2059
2060
2061
2062
2063
2064
2065
2066
2067
2068
2069
2070
2071
2072
2073
2074
2075
2076
2077
2078
2079
2080
2081
2082
2083
2084
2085
2086
2087
2088
2089
2090
2091
2092
2093
2094
2095
2096
2097
2098
2099
2100
2101
2102
2103
2104
2105
2106
2107
2108
2109
2110
2111
2112
2113
2114
2115
2116
2117
2118
2119
2120
2121
2122
2123
2124
2125
2126
2127
2128
2129
2130
2131
2132
2133
2134
2135
2136
2137
2138
2139
2140
2141
2142
2143
2144
2145
2146
2147
2148
2149
2150
2151
2152
2153
2154
2155
2156
2157
2158
2159
2160
2161
2162
2163
2164
2165
2166
2167
2168
2169
2170
2171
2172
2173
2174
2175
2176
2177
2178
2179
2180
2181
2182
2183
2184
2185
2186
2187
2188
2189
2190
2191
2192
2193
2194
2195
2196
2197
2198
2199
2200
2201
2202
2203
2204
2205
2206
2207
2208
2209
2210
2211
2212
2213
2214
2215
2216
2217
2218
2219
2220
2221
2222
2223
2224
2225
2226
2227
2228
2229
2230
2231
2232
2233
2234
2235
2236
2237
2238
2239
2240
2241
2242
2243
2244
2245
2246
2247
2248
2249
2250
2251
2252
2253
2254
2255
2256
2257
2258
2259
2260
2261
2262
2263
2264
2265
2266
2267
2268
2269
2270
2271
2272
2273
2274
2275
2276
2277
2278
2279
2280
2281
2282
2283
2284
2285
2286
2287
2288
2289
2290
2291
/*
   RFCOMM implementation for Linux Bluetooth stack (BlueZ).
   Copyright (C) 2002 Maxim Krasnyansky <maxk@qualcomm.com>
   Copyright (C) 2002 Marcel Holtmann <marcel@holtmann.org>

   This program is free software; you can redistribute it and/or modify
   it under the terms of the GNU General Public License version 2 as
   published by the Free Software Foundation;

   THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS
   OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
   FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT OF THIRD PARTY RIGHTS.
   IN NO EVENT SHALL THE COPYRIGHT HOLDER(S) AND AUTHOR(S) BE LIABLE FOR ANY
   CLAIM, OR ANY SPECIAL INDIRECT OR CONSEQUENTIAL DAMAGES, OR ANY DAMAGES
   WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS, WHETHER IN AN
   ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION, ARISING OUT OF
   OR IN CONNECTION WITH THE USE OR PERFORMANCE OF THIS SOFTWARE.

   ALL LIABILITY, INCLUDING LIABILITY FOR INFRINGEMENT OF ANY PATENTS,
   COPYRIGHTS, TRADEMARKS OR OTHER RIGHTS, RELATING TO USE OF THIS
   SOFTWARE IS DISCLAIMED.
*/

/*
 * Bluetooth RFCOMM core.
 */

#include <linux/module.h>
#include <linux/debugfs.h>
#include <linux/kthread.h>
#include <linux/unaligned.h>

#include <net/bluetooth/bluetooth.h>
#include <net/bluetooth/hci_core.h>
#include <net/bluetooth/l2cap.h>
#include <net/bluetooth/rfcomm.h>

#include <trace/events/sock.h>

#define VERSION "1.11"

static bool disable_cfc;
static bool l2cap_ertm;
static int channel_mtu = -1;

static struct task_struct *rfcomm_thread;

static DEFINE_MUTEX(rfcomm_mutex);
#define rfcomm_lock()        mutex_lock(&rfcomm_mutex)
#define rfcomm_unlock()        mutex_unlock(&rfcomm_mutex)


static LIST_HEAD(session_list);

static int rfcomm_send_frame(struct rfcomm_session *s, u8 *data, int len);
static int rfcomm_send_sabm(struct rfcomm_session *s, u8 dlci);
static int rfcomm_send_disc(struct rfcomm_session *s, u8 dlci);
static int rfcomm_queue_disc(struct rfcomm_dlc *d);
static int rfcomm_send_nsc(struct rfcomm_session *s, int cr, u8 type);
static int rfcomm_send_pn(struct rfcomm_session *s, int cr, struct rfcomm_dlc *d);
static int rfcomm_send_msc(struct rfcomm_session *s, int cr, u8 dlci, u8 v24_sig);
static int rfcomm_send_test(struct rfcomm_session *s, int cr, u8 *pattern, int len);
static int rfcomm_send_credits(struct rfcomm_session *s, u8 addr, u8 credits);
static void rfcomm_make_uih(struct sk_buff *skb, u8 addr);

static void rfcomm_process_connect(struct rfcomm_session *s);

static struct rfcomm_session *rfcomm_session_create(bdaddr_t *src,
                                                        bdaddr_t *dst,
                                                        u8 sec_level,
                                                        int *err);
static struct rfcomm_session *rfcomm_session_get(bdaddr_t *src, bdaddr_t *dst);
static struct rfcomm_session *rfcomm_session_del(struct rfcomm_session *s);

/* ---- RFCOMM frame parsing macros ---- */
#define __get_dlci(b)     ((b & 0xfc) >> 2)
#define __get_type(b)     ((b & 0xef))

#define __test_ea(b)      ((b & 0x01))
#define __test_cr(b)      (!!(b & 0x02))
#define __test_pf(b)      (!!(b & 0x10))

#define __session_dir(s)  ((s)->initiator ? 0x00 : 0x01)

#define __addr(cr, dlci)       (((dlci & 0x3f) << 2) | (cr << 1) | 0x01)
#define __ctrl(type, pf)       (((type & 0xef) | (pf << 4)))
#define __dlci(dir, chn)       (((chn & 0x1f) << 1) | dir)
#define __srv_channel(dlci)    (dlci >> 1)

#define __len8(len)       (((len) << 1) | 1)
#define __len16(len)      ((len) << 1)

/* MCC macros */
#define __mcc_type(cr, type)   (((type << 2) | (cr << 1) | 0x01))
#define __get_mcc_type(b) ((b & 0xfc) >> 2)
#define __get_mcc_len(b)  ((b & 0xfe) >> 1)

/* RPN macros */
#define __rpn_line_settings(data, stop, parity)  ((data & 0x3) | ((stop & 0x1) << 2) | ((parity & 0x7) << 3))
#define __get_rpn_data_bits(line) ((line) & 0x3)
#define __get_rpn_stop_bits(line) (((line) >> 2) & 0x1)
#define __get_rpn_parity(line)    (((line) >> 3) & 0x7)

static DECLARE_WAIT_QUEUE_HEAD(rfcomm_wq);

static void rfcomm_schedule(void)
{
        wake_up_all(&rfcomm_wq);
}

/* ---- RFCOMM FCS computation ---- */

/* reversed, 8-bit, poly=0x07 */
static unsigned char rfcomm_crc_table[256] = {
        0x00, 0x91, 0xe3, 0x72, 0x07, 0x96, 0xe4, 0x75,
        0x0e, 0x9f, 0xed, 0x7c, 0x09, 0x98, 0xea, 0x7b,
        0x1c, 0x8d, 0xff, 0x6e, 0x1b, 0x8a, 0xf8, 0x69,
        0x12, 0x83, 0xf1, 0x60, 0x15, 0x84, 0xf6, 0x67,

        0x38, 0xa9, 0xdb, 0x4a, 0x3f, 0xae, 0xdc, 0x4d,
        0x36, 0xa7, 0xd5, 0x44, 0x31, 0xa0, 0xd2, 0x43,
        0x24, 0xb5, 0xc7, 0x56, 0x23, 0xb2, 0xc0, 0x51,
        0x2a, 0xbb, 0xc9, 0x58, 0x2d, 0xbc, 0xce, 0x5f,

        0x70, 0xe1, 0x93, 0x02, 0x77, 0xe6, 0x94, 0x05,
        0x7e, 0xef, 0x9d, 0x0c, 0x79, 0xe8, 0x9a, 0x0b,
        0x6c, 0xfd, 0x8f, 0x1e, 0x6b, 0xfa, 0x88, 0x19,
        0x62, 0xf3, 0x81, 0x10, 0x65, 0xf4, 0x86, 0x17,

        0x48, 0xd9, 0xab, 0x3a, 0x4f, 0xde, 0xac, 0x3d,
        0x46, 0xd7, 0xa5, 0x34, 0x41, 0xd0, 0xa2, 0x33,
        0x54, 0xc5, 0xb7, 0x26, 0x53, 0xc2, 0xb0, 0x21,
        0x5a, 0xcb, 0xb9, 0x28, 0x5d, 0xcc, 0xbe, 0x2f,

        0xe0, 0x71, 0x03, 0x92, 0xe7, 0x76, 0x04, 0x95,
        0xee, 0x7f, 0x0d, 0x9c, 0xe9, 0x78, 0x0a, 0x9b,
        0xfc, 0x6d, 0x1f, 0x8e, 0xfb, 0x6a, 0x18, 0x89,
        0xf2, 0x63, 0x11, 0x80, 0xf5, 0x64, 0x16, 0x87,

        0xd8, 0x49, 0x3b, 0xaa, 0xdf, 0x4e, 0x3c, 0xad,
        0xd6, 0x47, 0x35, 0xa4, 0xd1, 0x40, 0x32, 0xa3,
        0xc4, 0x55, 0x27, 0xb6, 0xc3, 0x52, 0x20, 0xb1,
        0xca, 0x5b, 0x29, 0xb8, 0xcd, 0x5c, 0x2e, 0xbf,

        0x90, 0x01, 0x73, 0xe2, 0x97, 0x06, 0x74, 0xe5,
        0x9e, 0x0f, 0x7d, 0xec, 0x99, 0x08, 0x7a, 0xeb,
        0x8c, 0x1d, 0x6f, 0xfe, 0x8b, 0x1a, 0x68, 0xf9,
        0x82, 0x13, 0x61, 0xf0, 0x85, 0x14, 0x66, 0xf7,

        0xa8, 0x39, 0x4b, 0xda, 0xaf, 0x3e, 0x4c, 0xdd,
        0xa6, 0x37, 0x45, 0xd4, 0xa1, 0x30, 0x42, 0xd3,
        0xb4, 0x25, 0x57, 0xc6, 0xb3, 0x22, 0x50, 0xc1,
        0xba, 0x2b, 0x59, 0xc8, 0xbd, 0x2c, 0x5e, 0xcf
};

/* CRC on 2 bytes */
#define __crc(data) (rfcomm_crc_table[rfcomm_crc_table[0xff ^ data[0]] ^ data[1]])

/* FCS on 2 bytes */
static inline u8 __fcs(u8 *data)
{
        return 0xff - __crc(data);
}

/* FCS on 3 bytes */
static inline u8 __fcs2(u8 *data)
{
        return 0xff - rfcomm_crc_table[__crc(data) ^ data[2]];
}

/* Check FCS */
static inline int __check_fcs(u8 *data, int type, u8 fcs)
{
        u8 f = __crc(data);

        if (type != RFCOMM_UIH)
                f = rfcomm_crc_table[f ^ data[2]];

        return rfcomm_crc_table[f ^ fcs] != 0xcf;
}

/* ---- L2CAP callbacks ---- */
static void rfcomm_l2state_change(struct sock *sk)
{
        BT_DBG("%p state %d", sk, sk->sk_state);
        rfcomm_schedule();
}

static void rfcomm_l2data_ready(struct sock *sk)
{
        trace_sk_data_ready(sk);

        BT_DBG("%p", sk);
        rfcomm_schedule();
}

static int rfcomm_l2sock_create(struct socket **sock)
{
        int err;

        BT_DBG("");

        err = sock_create_kern(&init_net, PF_BLUETOOTH, SOCK_SEQPACKET, BTPROTO_L2CAP, sock);
        if (!err) {
                struct sock *sk = (*sock)->sk;
                sk->sk_data_ready   = rfcomm_l2data_ready;
                sk->sk_state_change = rfcomm_l2state_change;
        }
        return err;
}

static int rfcomm_check_security(struct rfcomm_dlc *d)
{
        struct sock *sk = d->session->sock->sk;
        struct l2cap_conn *conn = l2cap_pi(sk)->chan->conn;

        __u8 auth_type;

        switch (d->sec_level) {
        case BT_SECURITY_HIGH:
        case BT_SECURITY_FIPS:
                auth_type = HCI_AT_GENERAL_BONDING_MITM;
                break;
        case BT_SECURITY_MEDIUM:
                auth_type = HCI_AT_GENERAL_BONDING;
                break;
        default:
                auth_type = HCI_AT_NO_BONDING;
                break;
        }

        return hci_conn_security(conn->hcon, d->sec_level, auth_type,
                                 d->out);
}

static void rfcomm_session_timeout(struct timer_list *t)
{
        struct rfcomm_session *s = from_timer(s, t, timer);

        BT_DBG("session %p state %ld", s, s->state);

        set_bit(RFCOMM_TIMED_OUT, &s->flags);
        rfcomm_schedule();
}

static void rfcomm_session_set_timer(struct rfcomm_session *s, long timeout)
{
        BT_DBG("session %p state %ld timeout %ld", s, s->state, timeout);

        mod_timer(&s->timer, jiffies + timeout);
}

static void rfcomm_session_clear_timer(struct rfcomm_session *s)
{
        BT_DBG("session %p state %ld", s, s->state);

        del_timer_sync(&s->timer);
}

/* ---- RFCOMM DLCs ---- */
static void rfcomm_dlc_timeout(struct timer_list *t)
{
        struct rfcomm_dlc *d = from_timer(d, t, timer);

        BT_DBG("dlc %p state %ld", d, d->state);

        set_bit(RFCOMM_TIMED_OUT, &d->flags);
        rfcomm_dlc_put(d);
        rfcomm_schedule();
}

static void rfcomm_dlc_set_timer(struct rfcomm_dlc *d, long timeout)
{
        BT_DBG("dlc %p state %ld timeout %ld", d, d->state, timeout);

        if (!mod_timer(&d->timer, jiffies + timeout))
                rfcomm_dlc_hold(d);
}

static void rfcomm_dlc_clear_timer(struct rfcomm_dlc *d)
{
        BT_DBG("dlc %p state %ld", d, d->state);

        if (del_timer(&d->timer))
                rfcomm_dlc_put(d);
}

static void rfcomm_dlc_clear_state(struct rfcomm_dlc *d)
{
        BT_DBG("%p", d);

        d->state      = BT_OPEN;
        d->flags      = 0;
        d->mscex      = 0;
        d->sec_level  = BT_SECURITY_LOW;
        d->mtu        = RFCOMM_DEFAULT_MTU;
        d->v24_sig    = RFCOMM_V24_RTC | RFCOMM_V24_RTR | RFCOMM_V24_DV;

        d->cfc        = RFCOMM_CFC_DISABLED;
        d->rx_credits = RFCOMM_DEFAULT_CREDITS;
}

struct rfcomm_dlc *rfcomm_dlc_alloc(gfp_t prio)
{
        struct rfcomm_dlc *d = kzalloc(sizeof(*d), prio);

        if (!d)
                return NULL;

        timer_setup(&d->timer, rfcomm_dlc_timeout, 0);

        skb_queue_head_init(&d->tx_queue);
        mutex_init(&d->lock);
        refcount_set(&d->refcnt, 1);

        rfcomm_dlc_clear_state(d);

        BT_DBG("%p", d);

        return d;
}

void rfcomm_dlc_free(struct rfcomm_dlc *d)
{
        BT_DBG("%p", d);

        skb_queue_purge(&d->tx_queue);
        kfree(d);
}

static void rfcomm_dlc_link(struct rfcomm_session *s, struct rfcomm_dlc *d)
{
        BT_DBG("dlc %p session %p", d, s);

        rfcomm_session_clear_timer(s);
        rfcomm_dlc_hold(d);
        list_add(&d->list, &s->dlcs);
        d->session = s;
}

static void rfcomm_dlc_unlink(struct rfcomm_dlc *d)
{
        struct rfcomm_session *s = d->session;

        BT_DBG("dlc %p refcnt %d session %p", d, refcount_read(&d->refcnt), s);

        list_del(&d->list);
        d->session = NULL;
        rfcomm_dlc_put(d);

        if (list_empty(&s->dlcs))
                rfcomm_session_set_timer(s, RFCOMM_IDLE_TIMEOUT);
}

static struct rfcomm_dlc *rfcomm_dlc_get(struct rfcomm_session *s, u8 dlci)
{
        struct rfcomm_dlc *d;

        list_for_each_entry(d, &s->dlcs, list)
                if (d->dlci == dlci)
                        return d;

        return NULL;
}

static int rfcomm_check_channel(u8 channel)
{
        return channel < 1 || channel > 30;
}

static int __rfcomm_dlc_open(struct rfcomm_dlc *d, bdaddr_t *src, bdaddr_t *dst, u8 channel)
{
        struct rfcomm_session *s;
        int err = 0;
        u8 dlci;

        BT_DBG("dlc %p state %ld %pMR -> %pMR channel %d",
               d, d->state, src, dst, channel);

        if (rfcomm_check_channel(channel))
                return -EINVAL;

        if (d->state != BT_OPEN && d->state != BT_CLOSED)
                return 0;

        s = rfcomm_session_get(src, dst);
        if (!s) {
                s = rfcomm_session_create(src, dst, d->sec_level, &err);
                if (!s)
                        return err;
        }

        dlci = __dlci(__session_dir(s), channel);

        /* Check if DLCI already exists */
        if (rfcomm_dlc_get(s, dlci))
                return -EBUSY;

        rfcomm_dlc_clear_state(d);

        d->dlci     = dlci;
        d->addr     = __addr(s->initiator, dlci);
        d->priority = 7;

        d->state = BT_CONFIG;
        rfcomm_dlc_link(s, d);

        d->out = 1;

        d->mtu = s->mtu;
        d->cfc = (s->cfc == RFCOMM_CFC_UNKNOWN) ? 0 : s->cfc;

        if (s->state == BT_CONNECTED) {
                if (rfcomm_check_security(d))
                        rfcomm_send_pn(s, 1, d);
                else
                        set_bit(RFCOMM_AUTH_PENDING, &d->flags);
        }

        rfcomm_dlc_set_timer(d, RFCOMM_CONN_TIMEOUT);

        return 0;
}

int rfcomm_dlc_open(struct rfcomm_dlc *d, bdaddr_t *src, bdaddr_t *dst, u8 channel)
{
        int r;

        rfcomm_lock();

        r = __rfcomm_dlc_open(d, src, dst, channel);

        rfcomm_unlock();
        return r;
}

static void __rfcomm_dlc_disconn(struct rfcomm_dlc *d)
{
        struct rfcomm_session *s = d->session;

        d->state = BT_DISCONN;
        if (skb_queue_empty(&d->tx_queue)) {
                rfcomm_send_disc(s, d->dlci);
                rfcomm_dlc_set_timer(d, RFCOMM_DISC_TIMEOUT);
        } else {
                rfcomm_queue_disc(d);
                rfcomm_dlc_set_timer(d, RFCOMM_DISC_TIMEOUT * 2);
        }
}

static int __rfcomm_dlc_close(struct rfcomm_dlc *d, int err)
{
        struct rfcomm_session *s = d->session;
        if (!s)
                return 0;

        BT_DBG("dlc %p state %ld dlci %d err %d session %p",
                        d, d->state, d->dlci, err, s);

        switch (d->state) {
        case BT_CONNECT:
        case BT_CONFIG:
        case BT_OPEN:
        case BT_CONNECT2:
                if (test_and_clear_bit(RFCOMM_DEFER_SETUP, &d->flags)) {
                        set_bit(RFCOMM_AUTH_REJECT, &d->flags);
                        rfcomm_schedule();
                        return 0;
                }
        }

        switch (d->state) {
        case BT_CONNECT:
        case BT_CONNECTED:
                __rfcomm_dlc_disconn(d);
                break;

        case BT_CONFIG:
                if (s->state != BT_BOUND) {
                        __rfcomm_dlc_disconn(d);
                        break;
                }
                /* if closing a dlc in a session that hasn't been started,
                 * just close and unlink the dlc
                 */
                fallthrough;

        default:
                rfcomm_dlc_clear_timer(d);

                rfcomm_dlc_lock(d);
                d->state = BT_CLOSED;
                d->state_change(d, err);
                rfcomm_dlc_unlock(d);

                skb_queue_purge(&d->tx_queue);
                rfcomm_dlc_unlink(d);
        }

        return 0;
}

int rfcomm_dlc_close(struct rfcomm_dlc *d, int err)
{
        int r = 0;
        struct rfcomm_dlc *d_list;
        struct rfcomm_session *s, *s_list;

        BT_DBG("dlc %p state %ld dlci %d err %d", d, d->state, d->dlci, err);

        rfcomm_lock();

        s = d->session;
        if (!s)
                goto no_session;

        /* after waiting on the mutex check the session still exists
         * then check the dlc still exists
         */
        list_for_each_entry(s_list, &session_list, list) {
                if (s_list == s) {
                        list_for_each_entry(d_list, &s->dlcs, list) {
                                if (d_list == d) {
                                        r = __rfcomm_dlc_close(d, err);
                                        break;
                                }
                        }
                        break;
                }
        }

no_session:
        rfcomm_unlock();
        return r;
}

struct rfcomm_dlc *rfcomm_dlc_exists(bdaddr_t *src, bdaddr_t *dst, u8 channel)
{
        struct rfcomm_session *s;
        struct rfcomm_dlc *dlc = NULL;
        u8 dlci;

        if (rfcomm_check_channel(channel))
                return ERR_PTR(-EINVAL);

        rfcomm_lock();
        s = rfcomm_session_get(src, dst);
        if (s) {
                dlci = __dlci(__session_dir(s), channel);
                dlc = rfcomm_dlc_get(s, dlci);
        }
        rfcomm_unlock();
        return dlc;
}

static int rfcomm_dlc_send_frag(struct rfcomm_dlc *d, struct sk_buff *frag)
{
        int len = frag->len;

        BT_DBG("dlc %p mtu %d len %d", d, d->mtu, len);

        if (len > d->mtu)
                return -EINVAL;

        rfcomm_make_uih(frag, d->addr);
        __skb_queue_tail(&d->tx_queue, frag);

        return len;
}

int rfcomm_dlc_send(struct rfcomm_dlc *d, struct sk_buff *skb)
{
        unsigned long flags;
        struct sk_buff *frag, *next;
        int len;

        if (d->state != BT_CONNECTED)
                return -ENOTCONN;

        frag = skb_shinfo(skb)->frag_list;
        skb_shinfo(skb)->frag_list = NULL;

        /* Queue all fragments atomically. */
        spin_lock_irqsave(&d->tx_queue.lock, flags);

        len = rfcomm_dlc_send_frag(d, skb);
        if (len < 0 || !frag)
                goto unlock;

        for (; frag; frag = next) {
                int ret;

                next = frag->next;

                ret = rfcomm_dlc_send_frag(d, frag);
                if (ret < 0) {
                        dev_kfree_skb_irq(frag);
                        goto unlock;
                }

                len += ret;
        }

unlock:
        spin_unlock_irqrestore(&d->tx_queue.lock, flags);

        if (len > 0 && !test_bit(RFCOMM_TX_THROTTLED, &d->flags))
                rfcomm_schedule();
        return len;
}

void rfcomm_dlc_send_noerror(struct rfcomm_dlc *d, struct sk_buff *skb)
{
        int len = skb->len;

        BT_DBG("dlc %p mtu %d len %d", d, d->mtu, len);

        rfcomm_make_uih(skb, d->addr);
        skb_queue_tail(&d->tx_queue, skb);

        if (d->state == BT_CONNECTED &&
            !test_bit(RFCOMM_TX_THROTTLED, &d->flags))
                rfcomm_schedule();
}

void __rfcomm_dlc_throttle(struct rfcomm_dlc *d)
{
        BT_DBG("dlc %p state %ld", d, d->state);

        if (!d->cfc) {
                d->v24_sig |= RFCOMM_V24_FC;
                set_bit(RFCOMM_MSC_PENDING, &d->flags);
        }
        rfcomm_schedule();
}

void __rfcomm_dlc_unthrottle(struct rfcomm_dlc *d)
{
        BT_DBG("dlc %p state %ld", d, d->state);

        if (!d->cfc) {
                d->v24_sig &= ~RFCOMM_V24_FC;
                set_bit(RFCOMM_MSC_PENDING, &d->flags);
        }
        rfcomm_schedule();
}

/*
   Set/get modem status functions use _local_ status i.e. what we report
   to the other side.
   Remote status is provided by dlc->modem_status() callback.
 */
int rfcomm_dlc_set_modem_status(struct rfcomm_dlc *d, u8 v24_sig)
{
        BT_DBG("dlc %p state %ld v24_sig 0x%x",
                        d, d->state, v24_sig);

        if (test_bit(RFCOMM_RX_THROTTLED, &d->flags))
                v24_sig |= RFCOMM_V24_FC;
        else
                v24_sig &= ~RFCOMM_V24_FC;

        d->v24_sig = v24_sig;

        if (!test_and_set_bit(RFCOMM_MSC_PENDING, &d->flags))
                rfcomm_schedule();

        return 0;
}

int rfcomm_dlc_get_modem_status(struct rfcomm_dlc *d, u8 *v24_sig)
{
        BT_DBG("dlc %p state %ld v24_sig 0x%x",
                        d, d->state, d->v24_sig);

        *v24_sig = d->v24_sig;
        return 0;
}

/* ---- RFCOMM sessions ---- */
static struct rfcomm_session *rfcomm_session_add(struct socket *sock, int state)
{
        struct rfcomm_session *s = kzalloc(sizeof(*s), GFP_KERNEL);

        if (!s)
                return NULL;

        BT_DBG("session %p sock %p", s, sock);

        timer_setup(&s->timer, rfcomm_session_timeout, 0);

        INIT_LIST_HEAD(&s->dlcs);
        s->state = state;
        s->sock  = sock;

        s->mtu = RFCOMM_DEFAULT_MTU;
        s->cfc = disable_cfc ? RFCOMM_CFC_DISABLED : RFCOMM_CFC_UNKNOWN;

        /* Do not increment module usage count for listening sessions.
         * Otherwise we won't be able to unload the module. */
        if (state != BT_LISTEN)
                if (!try_module_get(THIS_MODULE)) {
                        kfree(s);
                        return NULL;
                }

        list_add(&s->list, &session_list);

        return s;
}

static struct rfcomm_session *rfcomm_session_del(struct rfcomm_session *s)
{
        int state = s->state;

        BT_DBG("session %p state %ld", s, s->state);

        list_del(&s->list);

        rfcomm_session_clear_timer(s);
        sock_release(s->sock);
        kfree(s);

        if (state != BT_LISTEN)
                module_put(THIS_MODULE);

        return NULL;
}

static struct rfcomm_session *rfcomm_session_get(bdaddr_t *src, bdaddr_t *dst)
{
        struct rfcomm_session *s, *n;
        struct l2cap_chan *chan;
        list_for_each_entry_safe(s, n, &session_list, list) {
                chan = l2cap_pi(s->sock->sk)->chan;

                if ((!bacmp(src, BDADDR_ANY) || !bacmp(&chan->src, src)) &&
                    !bacmp(&chan->dst, dst))
                        return s;
        }
        return NULL;
}

static struct rfcomm_session *rfcomm_session_close(struct rfcomm_session *s,
                                                   int err)
{
        struct rfcomm_dlc *d, *n;

        s->state = BT_CLOSED;

        BT_DBG("session %p state %ld err %d", s, s->state, err);

        /* Close all dlcs */
        list_for_each_entry_safe(d, n, &s->dlcs, list) {
                d->state = BT_CLOSED;
                __rfcomm_dlc_close(d, err);
        }

        rfcomm_session_clear_timer(s);
        return rfcomm_session_del(s);
}

static struct rfcomm_session *rfcomm_session_create(bdaddr_t *src,
                                                        bdaddr_t *dst,
                                                        u8 sec_level,
                                                        int *err)
{
        struct rfcomm_session *s = NULL;
        struct sockaddr_l2 addr;
        struct socket *sock;
        struct sock *sk;

        BT_DBG("%pMR -> %pMR", src, dst);

        *err = rfcomm_l2sock_create(&sock);
        if (*err < 0)
                return NULL;

        bacpy(&addr.l2_bdaddr, src);
        addr.l2_family = AF_BLUETOOTH;
        addr.l2_psm    = 0;
        addr.l2_cid    = 0;
        addr.l2_bdaddr_type = BDADDR_BREDR;
        *err = kernel_bind(sock, (struct sockaddr *) &addr, sizeof(addr));
        if (*err < 0)
                goto failed;

        /* Set L2CAP options */
        sk = sock->sk;
        lock_sock(sk);
        /* Set MTU to 0 so L2CAP can auto select the MTU */
        l2cap_pi(sk)->chan->imtu = 0;
        l2cap_pi(sk)->chan->sec_level = sec_level;
        if (l2cap_ertm)
                l2cap_pi(sk)->chan->mode = L2CAP_MODE_ERTM;
        release_sock(sk);

        s = rfcomm_session_add(sock, BT_BOUND);
        if (!s) {
                *err = -ENOMEM;
                goto failed;
        }

        s->initiator = 1;

        bacpy(&addr.l2_bdaddr, dst);
        addr.l2_family = AF_BLUETOOTH;
        addr.l2_psm    = cpu_to_le16(L2CAP_PSM_RFCOMM);
        addr.l2_cid    = 0;
        addr.l2_bdaddr_type = BDADDR_BREDR;
        *err = kernel_connect(sock, (struct sockaddr *) &addr, sizeof(addr), O_NONBLOCK);
        if (*err == 0 || *err == -EINPROGRESS)
                return s;

        return rfcomm_session_del(s);

failed:
        sock_release(sock);
        return NULL;
}

void rfcomm_session_getaddr(struct rfcomm_session *s, bdaddr_t *src, bdaddr_t *dst)
{
        struct l2cap_chan *chan = l2cap_pi(s->sock->sk)->chan;
        if (src)
                bacpy(src, &chan->src);
        if (dst)
                bacpy(dst, &chan->dst);
}

/* ---- RFCOMM frame sending ---- */
static int rfcomm_send_frame(struct rfcomm_session *s, u8 *data, int len)
{
        struct kvec iv = { data, len };
        struct msghdr msg;

        BT_DBG("session %p len %d", s, len);

        memset(&msg, 0, sizeof(msg));

        return kernel_sendmsg(s->sock, &msg, &iv, 1, len);
}

static int rfcomm_send_cmd(struct rfcomm_session *s, struct rfcomm_cmd *cmd)
{
        BT_DBG("%p cmd %u", s, cmd->ctrl);

        return rfcomm_send_frame(s, (void *) cmd, sizeof(*cmd));
}

static int rfcomm_send_sabm(struct rfcomm_session *s, u8 dlci)
{
        struct rfcomm_cmd cmd;

        BT_DBG("%p dlci %d", s, dlci);

        cmd.addr = __addr(s->initiator, dlci);
        cmd.ctrl = __ctrl(RFCOMM_SABM, 1);
        cmd.len  = __len8(0);
        cmd.fcs  = __fcs2((u8 *) &cmd);

        return rfcomm_send_cmd(s, &cmd);
}

static int rfcomm_send_ua(struct rfcomm_session *s, u8 dlci)
{
        struct rfcomm_cmd cmd;

        BT_DBG("%p dlci %d", s, dlci);

        cmd.addr = __addr(!s->initiator, dlci);
        cmd.ctrl = __ctrl(RFCOMM_UA, 1);
        cmd.len  = __len8(0);
        cmd.fcs  = __fcs2((u8 *) &cmd);

        return rfcomm_send_cmd(s, &cmd);
}

static int rfcomm_send_disc(struct rfcomm_session *s, u8 dlci)
{
        struct rfcomm_cmd cmd;

        BT_DBG("%p dlci %d", s, dlci);

        cmd.addr = __addr(s->initiator, dlci);
        cmd.ctrl = __ctrl(RFCOMM_DISC, 1);
        cmd.len  = __len8(0);
        cmd.fcs  = __fcs2((u8 *) &cmd);

        return rfcomm_send_cmd(s, &cmd);
}

static int rfcomm_queue_disc(struct rfcomm_dlc *d)
{
        struct rfcomm_cmd *cmd;
        struct sk_buff *skb;

        BT_DBG("dlc %p dlci %d", d, d->dlci);

        skb = alloc_skb(sizeof(*cmd), GFP_KERNEL);
        if (!skb)
                return -ENOMEM;

        cmd = __skb_put(skb, sizeof(*cmd));
        cmd->addr = d->addr;
        cmd->ctrl = __ctrl(RFCOMM_DISC, 1);
        cmd->len  = __len8(0);
        cmd->fcs  = __fcs2((u8 *) cmd);

        skb_queue_tail(&d->tx_queue, skb);
        rfcomm_schedule();
        return 0;
}

static int rfcomm_send_dm(struct rfcomm_session *s, u8 dlci)
{
        struct rfcomm_cmd cmd;

        BT_DBG("%p dlci %d", s, dlci);

        cmd.addr = __addr(!s->initiator, dlci);
        cmd.ctrl = __ctrl(RFCOMM_DM, 1);
        cmd.len  = __len8(0);
        cmd.fcs  = __fcs2((u8 *) &cmd);

        return rfcomm_send_cmd(s, &cmd);
}

static int rfcomm_send_nsc(struct rfcomm_session *s, int cr, u8 type)
{
        struct rfcomm_hdr *hdr;
        struct rfcomm_mcc *mcc;
        u8 buf[16], *ptr = buf;

        BT_DBG("%p cr %d type %d", s, cr, type);

        hdr = (void *) ptr; ptr += sizeof(*hdr);
        hdr->addr = __addr(s->initiator, 0);
        hdr->ctrl = __ctrl(RFCOMM_UIH, 0);
        hdr->len  = __len8(sizeof(*mcc) + 1);

        mcc = (void *) ptr; ptr += sizeof(*mcc);
        mcc->type = __mcc_type(0, RFCOMM_NSC);
        mcc->len  = __len8(1);

        /* Type that we didn't like */
        *ptr = __mcc_type(cr, type); ptr++;

        *ptr = __fcs(buf); ptr++;

        return rfcomm_send_frame(s, buf, ptr - buf);
}

static int rfcomm_send_pn(struct rfcomm_session *s, int cr, struct rfcomm_dlc *d)
{
        struct rfcomm_hdr *hdr;
        struct rfcomm_mcc *mcc;
        struct rfcomm_pn  *pn;
        u8 buf[16], *ptr = buf;

        BT_DBG("%p cr %d dlci %d mtu %d", s, cr, d->dlci, d->mtu);

        hdr = (void *) ptr; ptr += sizeof(*hdr);
        hdr->addr = __addr(s->initiator, 0);
        hdr->ctrl = __ctrl(RFCOMM_UIH, 0);
        hdr->len  = __len8(sizeof(*mcc) + sizeof(*pn));

        mcc = (void *) ptr; ptr += sizeof(*mcc);
        mcc->type = __mcc_type(cr, RFCOMM_PN);
        mcc->len  = __len8(sizeof(*pn));

        pn = (void *) ptr; ptr += sizeof(*pn);
        pn->dlci        = d->dlci;
        pn->priority    = d->priority;
        pn->ack_timer   = 0;
        pn->max_retrans = 0;

        if (s->cfc) {
                pn->flow_ctrl = cr ? 0xf0 : 0xe0;
                pn->credits = RFCOMM_DEFAULT_CREDITS;
        } else {
                pn->flow_ctrl = 0;
                pn->credits   = 0;
        }

        if (cr && channel_mtu >= 0)
                pn->mtu = cpu_to_le16(channel_mtu);
        else
                pn->mtu = cpu_to_le16(d->mtu);

        *ptr = __fcs(buf); ptr++;

        return rfcomm_send_frame(s, buf, ptr - buf);
}

int rfcomm_send_rpn(struct rfcomm_session *s, int cr, u8 dlci,
                        u8 bit_rate, u8 data_bits, u8 stop_bits,
                        u8 parity, u8 flow_ctrl_settings,
                        u8 xon_char, u8 xoff_char, u16 param_mask)
{
        struct rfcomm_hdr *hdr;
        struct rfcomm_mcc *mcc;
        struct rfcomm_rpn *rpn;
        u8 buf[16], *ptr = buf;

        BT_DBG("%p cr %d dlci %d bit_r 0x%x data_b 0x%x stop_b 0x%x parity 0x%x"
                        " flwc_s 0x%x xon_c 0x%x xoff_c 0x%x p_mask 0x%x",
                s, cr, dlci, bit_rate, data_bits, stop_bits, parity,
                flow_ctrl_settings, xon_char, xoff_char, param_mask);

        hdr = (void *) ptr; ptr += sizeof(*hdr);
        hdr->addr = __addr(s->initiator, 0);
        hdr->ctrl = __ctrl(RFCOMM_UIH, 0);
        hdr->len  = __len8(sizeof(*mcc) + sizeof(*rpn));

        mcc = (void *) ptr; ptr += sizeof(*mcc);
        mcc->type = __mcc_type(cr, RFCOMM_RPN);
        mcc->len  = __len8(sizeof(*rpn));

        rpn = (void *) ptr; ptr += sizeof(*rpn);
        rpn->dlci          = __addr(1, dlci);
        rpn->bit_rate      = bit_rate;
        rpn->line_settings = __rpn_line_settings(data_bits, stop_bits, parity);
        rpn->flow_ctrl     = flow_ctrl_settings;
        rpn->xon_char      = xon_char;
        rpn->xoff_char     = xoff_char;
        rpn->param_mask    = cpu_to_le16(param_mask);

        *ptr = __fcs(buf); ptr++;

        return rfcomm_send_frame(s, buf, ptr - buf);
}

static int rfcomm_send_rls(struct rfcomm_session *s, int cr, u8 dlci, u8 status)
{
        struct rfcomm_hdr *hdr;
        struct rfcomm_mcc *mcc;
        struct rfcomm_rls *rls;
        u8 buf[16], *ptr = buf;

        BT_DBG("%p cr %d status 0x%x", s, cr, status);

        hdr = (void *) ptr; ptr += sizeof(*hdr);
        hdr->addr = __addr(s->initiator, 0);
        hdr->ctrl = __ctrl(RFCOMM_UIH, 0);
        hdr->len  = __len8(sizeof(*mcc) + sizeof(*rls));

        mcc = (void *) ptr; ptr += sizeof(*mcc);
        mcc->type = __mcc_type(cr, RFCOMM_RLS);
        mcc->len  = __len8(sizeof(*rls));

        rls = (void *) ptr; ptr += sizeof(*rls);
        rls->dlci   = __addr(1, dlci);
        rls->status = status;

        *ptr = __fcs(buf); ptr++;

        return rfcomm_send_frame(s, buf, ptr - buf);
}

static int rfcomm_send_msc(struct rfcomm_session *s, int cr, u8 dlci, u8 v24_sig)
{
        struct rfcomm_hdr *hdr;
        struct rfcomm_mcc *mcc;
        struct rfcomm_msc *msc;
        u8 buf[16], *ptr = buf;

        BT_DBG("%p cr %d v24 0x%x", s, cr, v24_sig);

        hdr = (void *) ptr; ptr += sizeof(*hdr);
        hdr->addr = __addr(s->initiator, 0);
        hdr->ctrl = __ctrl(RFCOMM_UIH, 0);
        hdr->len  = __len8(sizeof(*mcc) + sizeof(*msc));

        mcc = (void *) ptr; ptr += sizeof(*mcc);
        mcc->type = __mcc_type(cr, RFCOMM_MSC);
        mcc->len  = __len8(sizeof(*msc));

        msc = (void *) ptr; ptr += sizeof(*msc);
        msc->dlci    = __addr(1, dlci);
        msc->v24_sig = v24_sig | 0x01;

        *ptr = __fcs(buf); ptr++;

        return rfcomm_send_frame(s, buf, ptr - buf);
}

static int rfcomm_send_fcoff(struct rfcomm_session *s, int cr)
{
        struct rfcomm_hdr *hdr;
        struct rfcomm_mcc *mcc;
        u8 buf[16], *ptr = buf;

        BT_DBG("%p cr %d", s, cr);

        hdr = (void *) ptr; ptr += sizeof(*hdr);
        hdr->addr = __addr(s->initiator, 0);
        hdr->ctrl = __ctrl(RFCOMM_UIH, 0);
        hdr->len  = __len8(sizeof(*mcc));

        mcc = (void *) ptr; ptr += sizeof(*mcc);
        mcc->type = __mcc_type(cr, RFCOMM_FCOFF);
        mcc->len  = __len8(0);

        *ptr = __fcs(buf); ptr++;

        return rfcomm_send_frame(s, buf, ptr - buf);
}

static int rfcomm_send_fcon(struct rfcomm_session *s, int cr)
{
        struct rfcomm_hdr *hdr;
        struct rfcomm_mcc *mcc;
        u8 buf[16], *ptr = buf;

        BT_DBG("%p cr %d", s, cr);

        hdr = (void *) ptr; ptr += sizeof(*hdr);
        hdr->addr = __addr(s->initiator, 0);
        hdr->ctrl = __ctrl(RFCOMM_UIH, 0);
        hdr->len  = __len8(sizeof(*mcc));

        mcc = (void *) ptr; ptr += sizeof(*mcc);
        mcc->type = __mcc_type(cr, RFCOMM_FCON);
        mcc->len  = __len8(0);

        *ptr = __fcs(buf); ptr++;

        return rfcomm_send_frame(s, buf, ptr - buf);
}

static int rfcomm_send_test(struct rfcomm_session *s, int cr, u8 *pattern, int len)
{
        struct socket *sock = s->sock;
        struct kvec iv[3];
        struct msghdr msg;
        unsigned char hdr[5], crc[1];

        if (len > 125)
                return -EINVAL;

        BT_DBG("%p cr %d", s, cr);

        hdr[0] = __addr(s->initiator, 0);
        hdr[1] = __ctrl(RFCOMM_UIH, 0);
        hdr[2] = 0x01 | ((len + 2) << 1);
        hdr[3] = 0x01 | ((cr & 0x01) << 1) | (RFCOMM_TEST << 2);
        hdr[4] = 0x01 | (len << 1);

        crc[0] = __fcs(hdr);

        iv[0].iov_base = hdr;
        iv[0].iov_len  = 5;
        iv[1].iov_base = pattern;
        iv[1].iov_len  = len;
        iv[2].iov_base = crc;
        iv[2].iov_len  = 1;

        memset(&msg, 0, sizeof(msg));

        return kernel_sendmsg(sock, &msg, iv, 3, 6 + len);
}

static int rfcomm_send_credits(struct rfcomm_session *s, u8 addr, u8 credits)
{
        struct rfcomm_hdr *hdr;
        u8 buf[16], *ptr = buf;

        BT_DBG("%p addr %d credits %d", s, addr, credits);

        hdr = (void *) ptr; ptr += sizeof(*hdr);
        hdr->addr = addr;
        hdr->ctrl = __ctrl(RFCOMM_UIH, 1);
        hdr->len  = __len8(0);

        *ptr = credits; ptr++;

        *ptr = __fcs(buf); ptr++;

        return rfcomm_send_frame(s, buf, ptr - buf);
}

static void rfcomm_make_uih(struct sk_buff *skb, u8 addr)
{
        struct rfcomm_hdr *hdr;
        int len = skb->len;
        u8 *crc;

        if (len > 127) {
                hdr = skb_push(skb, 4);
                put_unaligned(cpu_to_le16(__len16(len)), (__le16 *) &hdr->len);
        } else {
                hdr = skb_push(skb, 3);
                hdr->len = __len8(len);
        }
        hdr->addr = addr;
        hdr->ctrl = __ctrl(RFCOMM_UIH, 0);

        crc = skb_put(skb, 1);
        *crc = __fcs((void *) hdr);
}

/* ---- RFCOMM frame reception ---- */
static struct rfcomm_session *rfcomm_recv_ua(struct rfcomm_session *s, u8 dlci)
{
        BT_DBG("session %p state %ld dlci %d", s, s->state, dlci);

        if (dlci) {
                /* Data channel */
                struct rfcomm_dlc *d = rfcomm_dlc_get(s, dlci);
                if (!d) {
                        rfcomm_send_dm(s, dlci);
                        return s;
                }

                switch (d->state) {
                case BT_CONNECT:
                        rfcomm_dlc_clear_timer(d);

                        rfcomm_dlc_lock(d);
                        d->state = BT_CONNECTED;
                        d->state_change(d, 0);
                        rfcomm_dlc_unlock(d);

                        rfcomm_send_msc(s, 1, dlci, d->v24_sig);
                        break;

                case BT_DISCONN:
                        d->state = BT_CLOSED;
                        __rfcomm_dlc_close(d, 0);

                        if (list_empty(&s->dlcs)) {
                                s->state = BT_DISCONN;
                                rfcomm_send_disc(s, 0);
                                rfcomm_session_clear_timer(s);
                        }

                        break;
                }
        } else {
                /* Control channel */
                switch (s->state) {
                case BT_CONNECT:
                        s->state = BT_CONNECTED;
                        rfcomm_process_connect(s);
                        break;

                case BT_DISCONN:
                        s = rfcomm_session_close(s, ECONNRESET);
                        break;
                }
        }
        return s;
}

static struct rfcomm_session *rfcomm_recv_dm(struct rfcomm_session *s, u8 dlci)
{
        int err = 0;

        BT_DBG("session %p state %ld dlci %d", s, s->state, dlci);

        if (dlci) {
                /* Data DLC */
                struct rfcomm_dlc *d = rfcomm_dlc_get(s, dlci);
                if (d) {
                        if (d->state == BT_CONNECT || d->state == BT_CONFIG)
                                err = ECONNREFUSED;
                        else
                                err = ECONNRESET;

                        d->state = BT_CLOSED;
                        __rfcomm_dlc_close(d, err);
                }
        } else {
                if (s->state == BT_CONNECT)
                        err = ECONNREFUSED;
                else
                        err = ECONNRESET;

                s = rfcomm_session_close(s, err);
        }
        return s;
}

static struct rfcomm_session *rfcomm_recv_disc(struct rfcomm_session *s,
                                               u8 dlci)
{
        int err = 0;

        BT_DBG("session %p state %ld dlci %d", s, s->state, dlci);

        if (dlci) {
                struct rfcomm_dlc *d = rfcomm_dlc_get(s, dlci);
                if (d) {
                        rfcomm_send_ua(s, dlci);

                        if (d->state == BT_CONNECT || d->state == BT_CONFIG)
                                err = ECONNREFUSED;
                        else
                                err = ECONNRESET;

                        d->state = BT_CLOSED;
                        __rfcomm_dlc_close(d, err);
                } else
                        rfcomm_send_dm(s, dlci);

        } else {
                rfcomm_send_ua(s, 0);

                if (s->state == BT_CONNECT)
                        err = ECONNREFUSED;
                else
                        err = ECONNRESET;

                s = rfcomm_session_close(s, err);
        }
        return s;
}

void rfcomm_dlc_accept(struct rfcomm_dlc *d)
{
        struct sock *sk = d->session->sock->sk;
        struct l2cap_conn *conn = l2cap_pi(sk)->chan->conn;

        BT_DBG("dlc %p", d);

        rfcomm_send_ua(d->session, d->dlci);

        rfcomm_dlc_clear_timer(d);

        rfcomm_dlc_lock(d);
        d->state = BT_CONNECTED;
        d->state_change(d, 0);
        rfcomm_dlc_unlock(d);

        if (d->role_switch)
                hci_conn_switch_role(conn->hcon, 0x00);

        rfcomm_send_msc(d->session, 1, d->dlci, d->v24_sig);
}

static void rfcomm_check_accept(struct rfcomm_dlc *d)
{
        if (rfcomm_check_security(d)) {
                if (d->defer_setup) {
                        set_bit(RFCOMM_DEFER_SETUP, &d->flags);
                        rfcomm_dlc_set_timer(d, RFCOMM_AUTH_TIMEOUT);

                        rfcomm_dlc_lock(d);
                        d->state = BT_CONNECT2;
                        d->state_change(d, 0);
                        rfcomm_dlc_unlock(d);
                } else
                        rfcomm_dlc_accept(d);
        } else {
                set_bit(RFCOMM_AUTH_PENDING, &d->flags);
                rfcomm_dlc_set_timer(d, RFCOMM_AUTH_TIMEOUT);
        }
}

static int rfcomm_recv_sabm(struct rfcomm_session *s, u8 dlci)
{
        struct rfcomm_dlc *d;
        u8 channel;

        BT_DBG("session %p state %ld dlci %d", s, s->state, dlci);

        if (!dlci) {
                rfcomm_send_ua(s, 0);

                if (s->state == BT_OPEN) {
                        s->state = BT_CONNECTED;
                        rfcomm_process_connect(s);
                }
                return 0;
        }

        /* Check if DLC exists */
        d = rfcomm_dlc_get(s, dlci);
        if (d) {
                if (d->state == BT_OPEN) {
                        /* DLC was previously opened by PN request */
                        rfcomm_check_accept(d);
                }
                return 0;
        }

        /* Notify socket layer about incoming connection */
        channel = __srv_channel(dlci);
        if (rfcomm_connect_ind(s, channel, &d)) {
                d->dlci = dlci;
                d->addr = __addr(s->initiator, dlci);
                rfcomm_dlc_link(s, d);

                rfcomm_check_accept(d);
        } else {
                rfcomm_send_dm(s, dlci);
        }

        return 0;
}

static int rfcomm_apply_pn(struct rfcomm_dlc *d, int cr, struct rfcomm_pn *pn)
{
        struct rfcomm_session *s = d->session;

        BT_DBG("dlc %p state %ld dlci %d mtu %d fc 0x%x credits %d",
                        d, d->state, d->dlci, pn->mtu, pn->flow_ctrl, pn->credits);

        if ((pn->flow_ctrl == 0xf0 && s->cfc != RFCOMM_CFC_DISABLED) ||
                                                pn->flow_ctrl == 0xe0) {
                d->cfc = RFCOMM_CFC_ENABLED;
                d->tx_credits = pn->credits;
        } else {
                d->cfc = RFCOMM_CFC_DISABLED;
                set_bit(RFCOMM_TX_THROTTLED, &d->flags);
        }

        if (s->cfc == RFCOMM_CFC_UNKNOWN)
                s->cfc = d->cfc;

        d->priority = pn->priority;

        d->mtu = __le16_to_cpu(pn->mtu);

        if (cr && d->mtu > s->mtu)
                d->mtu = s->mtu;

        return 0;
}

static int rfcomm_recv_pn(struct rfcomm_session *s, int cr, struct sk_buff *skb)
{
        struct rfcomm_pn *pn = (void *) skb->data;
        struct rfcomm_dlc *d;
        u8 dlci = pn->dlci;

        BT_DBG("session %p state %ld dlci %d", s, s->state, dlci);

        if (!dlci)
                return 0;

        d = rfcomm_dlc_get(s, dlci);
        if (d) {
                if (cr) {
                        /* PN request */
                        rfcomm_apply_pn(d, cr, pn);
                        rfcomm_send_pn(s, 0, d);
                } else {
                        /* PN response */
                        switch (d->state) {
                        case BT_CONFIG:
                                rfcomm_apply_pn(d, cr, pn);

                                d->state = BT_CONNECT;
                                rfcomm_send_sabm(s, d->dlci);
                                break;
                        }
                }
        } else {
                u8 channel = __srv_channel(dlci);

                if (!cr)
                        return 0;

                /* PN request for non existing DLC.
                 * Assume incoming connection. */
                if (rfcomm_connect_ind(s, channel, &d)) {
                        d->dlci = dlci;
                        d->addr = __addr(s->initiator, dlci);
                        rfcomm_dlc_link(s, d);

                        rfcomm_apply_pn(d, cr, pn);

                        d->state = BT_OPEN;
                        rfcomm_send_pn(s, 0, d);
                } else {
                        rfcomm_send_dm(s, dlci);
                }
        }
        return 0;
}

static int rfcomm_recv_rpn(struct rfcomm_session *s, int cr, int len, struct sk_buff *skb)
{
        struct rfcomm_rpn *rpn = (void *) skb->data;
        u8 dlci = __get_dlci(rpn->dlci);

        u8 bit_rate  = 0;
        u8 data_bits = 0;
        u8 stop_bits = 0;
        u8 parity    = 0;
        u8 flow_ctrl = 0;
        u8 xon_char  = 0;
        u8 xoff_char = 0;
        u16 rpn_mask = RFCOMM_RPN_PM_ALL;

        BT_DBG("dlci %d cr %d len 0x%x bitr 0x%x line 0x%x flow 0x%x xonc 0x%x xoffc 0x%x pm 0x%x",
                dlci, cr, len, rpn->bit_rate, rpn->line_settings, rpn->flow_ctrl,
                rpn->xon_char, rpn->xoff_char, rpn->param_mask);

        if (!cr)
                return 0;

        if (len == 1) {
                /* This is a request, return default (according to ETSI TS 07.10) settings */
                bit_rate  = RFCOMM_RPN_BR_9600;
                data_bits = RFCOMM_RPN_DATA_8;
                stop_bits = RFCOMM_RPN_STOP_1;
                parity    = RFCOMM_RPN_PARITY_NONE;
                flow_ctrl = RFCOMM_RPN_FLOW_NONE;
                xon_char  = RFCOMM_RPN_XON_CHAR;
                xoff_char = RFCOMM_RPN_XOFF_CHAR;
                goto rpn_out;
        }

        /* Check for sane values, ignore/accept bit_rate, 8 bits, 1 stop bit,
         * no parity, no flow control lines, normal XON/XOFF chars */

        if (rpn->param_mask & cpu_to_le16(RFCOMM_RPN_PM_BITRATE)) {
                bit_rate = rpn->bit_rate;
                if (bit_rate > RFCOMM_RPN_BR_230400) {
                        BT_DBG("RPN bit rate mismatch 0x%x", bit_rate);
                        bit_rate = RFCOMM_RPN_BR_9600;
                        rpn_mask ^= RFCOMM_RPN_PM_BITRATE;
                }
        }

        if (rpn->param_mask & cpu_to_le16(RFCOMM_RPN_PM_DATA)) {
                data_bits = __get_rpn_data_bits(rpn->line_settings);
                if (data_bits != RFCOMM_RPN_DATA_8) {
                        BT_DBG("RPN data bits mismatch 0x%x", data_bits);
                        data_bits = RFCOMM_RPN_DATA_8;
                        rpn_mask ^= RFCOMM_RPN_PM_DATA;
                }
        }

        if (rpn->param_mask & cpu_to_le16(RFCOMM_RPN_PM_STOP)) {
                stop_bits = __get_rpn_stop_bits(rpn->line_settings);
                if (stop_bits != RFCOMM_RPN_STOP_1) {
                        BT_DBG("RPN stop bits mismatch 0x%x", stop_bits);
                        stop_bits = RFCOMM_RPN_STOP_1;
                        rpn_mask ^= RFCOMM_RPN_PM_STOP;
                }
        }

        if (rpn->param_mask & cpu_to_le16(RFCOMM_RPN_PM_PARITY)) {
                parity = __get_rpn_parity(rpn->line_settings);
                if (parity != RFCOMM_RPN_PARITY_NONE) {
                        BT_DBG("RPN parity mismatch 0x%x", parity);
                        parity = RFCOMM_RPN_PARITY_NONE;
                        rpn_mask ^= RFCOMM_RPN_PM_PARITY;
                }
        }

        if (rpn->param_mask & cpu_to_le16(RFCOMM_RPN_PM_FLOW)) {
                flow_ctrl = rpn->flow_ctrl;
                if (flow_ctrl != RFCOMM_RPN_FLOW_NONE) {
                        BT_DBG("RPN flow ctrl mismatch 0x%x", flow_ctrl);
                        flow_ctrl = RFCOMM_RPN_FLOW_NONE;
                        rpn_mask ^= RFCOMM_RPN_PM_FLOW;
                }
        }

        if (rpn->param_mask & cpu_to_le16(RFCOMM_RPN_PM_XON)) {
                xon_char = rpn->xon_char;
                if (xon_char != RFCOMM_RPN_XON_CHAR) {
                        BT_DBG("RPN XON char mismatch 0x%x", xon_char);
                        xon_char = RFCOMM_RPN_XON_CHAR;
                        rpn_mask ^= RFCOMM_RPN_PM_XON;
                }
        }

        if (rpn->param_mask & cpu_to_le16(RFCOMM_RPN_PM_XOFF)) {
                xoff_char = rpn->xoff_char;
                if (xoff_char != RFCOMM_RPN_XOFF_CHAR) {
                        BT_DBG("RPN XOFF char mismatch 0x%x", xoff_char);
                        xoff_char = RFCOMM_RPN_XOFF_CHAR;
                        rpn_mask ^= RFCOMM_RPN_PM_XOFF;
                }
        }

rpn_out:
        rfcomm_send_rpn(s, 0, dlci, bit_rate, data_bits, stop_bits,
                        parity, flow_ctrl, xon_char, xoff_char, rpn_mask);

        return 0;
}

static int rfcomm_recv_rls(struct rfcomm_session *s, int cr, struct sk_buff *skb)
{
        struct rfcomm_rls *rls = (void *) skb->data;
        u8 dlci = __get_dlci(rls->dlci);

        BT_DBG("dlci %d cr %d status 0x%x", dlci, cr, rls->status);

        if (!cr)
                return 0;

        /* We should probably do something with this information here. But
         * for now it's sufficient just to reply -- Bluetooth 1.1 says it's
         * mandatory to recognise and respond to RLS */

        rfcomm_send_rls(s, 0, dlci, rls->status);

        return 0;
}

static int rfcomm_recv_msc(struct rfcomm_session *s, int cr, struct sk_buff *skb)
{
        struct rfcomm_msc *msc = (void *) skb->data;
        struct rfcomm_dlc *d;
        u8 dlci = __get_dlci(msc->dlci);

        BT_DBG("dlci %d cr %d v24 0x%x", dlci, cr, msc->v24_sig);

        d = rfcomm_dlc_get(s, dlci);
        if (!d)
                return 0;

        if (cr) {
                if (msc->v24_sig & RFCOMM_V24_FC && !d->cfc)
                        set_bit(RFCOMM_TX_THROTTLED, &d->flags);
                else
                        clear_bit(RFCOMM_TX_THROTTLED, &d->flags);

                rfcomm_dlc_lock(d);

                d->remote_v24_sig = msc->v24_sig;

                if (d->modem_status)
                        d->modem_status(d, msc->v24_sig);

                rfcomm_dlc_unlock(d);

                rfcomm_send_msc(s, 0, dlci, msc->v24_sig);

                d->mscex |= RFCOMM_MSCEX_RX;
        } else
                d->mscex |= RFCOMM_MSCEX_TX;

        return 0;
}

static int rfcomm_recv_mcc(struct rfcomm_session *s, struct sk_buff *skb)
{
        struct rfcomm_mcc *mcc = (void *) skb->data;
        u8 type, cr, len;

        cr   = __test_cr(mcc->type);
        type = __get_mcc_type(mcc->type);
        len  = __get_mcc_len(mcc->len);

        BT_DBG("%p type 0x%x cr %d", s, type, cr);

        skb_pull(skb, 2);

        switch (type) {
        case RFCOMM_PN:
                rfcomm_recv_pn(s, cr, skb);
                break;

        case RFCOMM_RPN:
                rfcomm_recv_rpn(s, cr, len, skb);
                break;

        case RFCOMM_RLS:
                rfcomm_recv_rls(s, cr, skb);
                break;

        case RFCOMM_MSC:
                rfcomm_recv_msc(s, cr, skb);
                break;

        case RFCOMM_FCOFF:
                if (cr) {
                        set_bit(RFCOMM_TX_THROTTLED, &s->flags);
                        rfcomm_send_fcoff(s, 0);
                }
                break;

        case RFCOMM_FCON:
                if (cr) {
                        clear_bit(RFCOMM_TX_THROTTLED, &s->flags);
                        rfcomm_send_fcon(s, 0);
                }
                break;

        case RFCOMM_TEST:
                if (cr)
                        rfcomm_send_test(s, 0, skb->data, skb->len);
                break;

        case RFCOMM_NSC:
                break;

        default:
                BT_ERR("Unknown control type 0x%02x", type);
                rfcomm_send_nsc(s, cr, type);
                break;
        }
        return 0;
}

static int rfcomm_recv_data(struct rfcomm_session *s, u8 dlci, int pf, struct sk_buff *skb)
{
        struct rfcomm_dlc *d;

        BT_DBG("session %p state %ld dlci %d pf %d", s, s->state, dlci, pf);

        d = rfcomm_dlc_get(s, dlci);
        if (!d) {
                rfcomm_send_dm(s, dlci);
                goto drop;
        }

        if (pf && d->cfc) {
                u8 credits = *(u8 *) skb->data; skb_pull(skb, 1);

                d->tx_credits += credits;
                if (d->tx_credits)
                        clear_bit(RFCOMM_TX_THROTTLED, &d->flags);
        }

        if (skb->len && d->state == BT_CONNECTED) {
                rfcomm_dlc_lock(d);
                d->rx_credits--;
                d->data_ready(d, skb);
                rfcomm_dlc_unlock(d);
                return 0;
        }

drop:
        kfree_skb(skb);
        return 0;
}

static struct rfcomm_session *rfcomm_recv_frame(struct rfcomm_session *s,
                                                struct sk_buff *skb)
{
        struct rfcomm_hdr *hdr = (void *) skb->data;
        u8 type, dlci, fcs;

        if (!s) {
                /* no session, so free socket data */
                kfree_skb(skb);
                return s;
        }

        dlci = __get_dlci(hdr->addr);
        type = __get_type(hdr->ctrl);

        /* Trim FCS */
        skb->len--; skb->tail--;
        fcs = *(u8 *)skb_tail_pointer(skb);

        if (__check_fcs(skb->data, type, fcs)) {
                BT_ERR("bad checksum in packet");
                kfree_skb(skb);
                return s;
        }

        if (__test_ea(hdr->len))
                skb_pull(skb, 3);
        else
                skb_pull(skb, 4);

        switch (type) {
        case RFCOMM_SABM:
                if (__test_pf(hdr->ctrl))
                        rfcomm_recv_sabm(s, dlci);
                break;

        case RFCOMM_DISC:
                if (__test_pf(hdr->ctrl))
                        s = rfcomm_recv_disc(s, dlci);
                break;

        case RFCOMM_UA:
                if (__test_pf(hdr->ctrl))
                        s = rfcomm_recv_ua(s, dlci);
                break;

        case RFCOMM_DM:
                s = rfcomm_recv_dm(s, dlci);
                break;

        case RFCOMM_UIH:
                if (dlci) {
                        rfcomm_recv_data(s, dlci, __test_pf(hdr->ctrl), skb);
                        return s;
                }
                rfcomm_recv_mcc(s, skb);
                break;

        default:
                BT_ERR("Unknown packet type 0x%02x", type);
                break;
        }
        kfree_skb(skb);
        return s;
}

/* ---- Connection and data processing ---- */

static void rfcomm_process_connect(struct rfcomm_session *s)
{
        struct rfcomm_dlc *d, *n;

        BT_DBG("session %p state %ld", s, s->state);

        list_for_each_entry_safe(d, n, &s->dlcs, list) {
                if (d->state == BT_CONFIG) {
                        d->mtu = s->mtu;
                        if (rfcomm_check_security(d)) {
                                rfcomm_send_pn(s, 1, d);
                        } else {
                                set_bit(RFCOMM_AUTH_PENDING, &d->flags);
                                rfcomm_dlc_set_timer(d, RFCOMM_AUTH_TIMEOUT);
                        }
                }
        }
}

/* Send data queued for the DLC.
 * Return number of frames left in the queue.
 */
static int rfcomm_process_tx(struct rfcomm_dlc *d)
{
        struct sk_buff *skb;
        int err;

        BT_DBG("dlc %p state %ld cfc %d rx_credits %d tx_credits %d",
                        d, d->state, d->cfc, d->rx_credits, d->tx_credits);

        /* Send pending MSC */
        if (test_and_clear_bit(RFCOMM_MSC_PENDING, &d->flags))
                rfcomm_send_msc(d->session, 1, d->dlci, d->v24_sig);

        if (d->cfc) {
                /* CFC enabled.
                 * Give them some credits */
                if (!test_bit(RFCOMM_RX_THROTTLED, &d->flags) &&
                                d->rx_credits <= (d->cfc >> 2)) {
                        rfcomm_send_credits(d->session, d->addr, d->cfc - d->rx_credits);
                        d->rx_credits = d->cfc;
                }
        } else {
                /* CFC disabled.
                 * Give ourselves some credits */
                d->tx_credits = 5;
        }

        if (test_bit(RFCOMM_TX_THROTTLED, &d->flags))
                return skb_queue_len(&d->tx_queue);

        while (d->tx_credits && (skb = skb_dequeue(&d->tx_queue))) {
                err = rfcomm_send_frame(d->session, skb->data, skb->len);
                if (err < 0) {
                        skb_queue_head(&d->tx_queue, skb);
                        break;
                }
                kfree_skb(skb);
                d->tx_credits--;
        }

        if (d->cfc && !d->tx_credits) {
                /* We're out of TX credits.
                 * Set TX_THROTTLED flag to avoid unnesary wakeups by dlc_send. */
                set_bit(RFCOMM_TX_THROTTLED, &d->flags);
        }

        return skb_queue_len(&d->tx_queue);
}

static void rfcomm_process_dlcs(struct rfcomm_session *s)
{
        struct rfcomm_dlc *d, *n;

        BT_DBG("session %p state %ld", s, s->state);

        list_for_each_entry_safe(d, n, &s->dlcs, list) {
                if (test_bit(RFCOMM_TIMED_OUT, &d->flags)) {
                        __rfcomm_dlc_close(d, ETIMEDOUT);
                        continue;
                }

                if (test_bit(RFCOMM_ENC_DROP, &d->flags)) {
                        __rfcomm_dlc_close(d, ECONNREFUSED);
                        continue;
                }

                if (test_and_clear_bit(RFCOMM_AUTH_ACCEPT, &d->flags)) {
                        rfcomm_dlc_clear_timer(d);
                        if (d->out) {
                                rfcomm_send_pn(s, 1, d);
                                rfcomm_dlc_set_timer(d, RFCOMM_CONN_TIMEOUT);
                        } else {
                                if (d->defer_setup) {
                                        set_bit(RFCOMM_DEFER_SETUP, &d->flags);
                                        rfcomm_dlc_set_timer(d, RFCOMM_AUTH_TIMEOUT);

                                        rfcomm_dlc_lock(d);
                                        d->state = BT_CONNECT2;
                                        d->state_change(d, 0);
                                        rfcomm_dlc_unlock(d);
                                } else
                                        rfcomm_dlc_accept(d);
                        }
                        continue;
                } else if (test_and_clear_bit(RFCOMM_AUTH_REJECT, &d->flags)) {
                        rfcomm_dlc_clear_timer(d);
                        if (!d->out)
                                rfcomm_send_dm(s, d->dlci);
                        else
                                d->state = BT_CLOSED;
                        __rfcomm_dlc_close(d, ECONNREFUSED);
                        continue;
                }

                if (test_bit(RFCOMM_SEC_PENDING, &d->flags))
                        continue;

                if (test_bit(RFCOMM_TX_THROTTLED, &s->flags))
                        continue;

                if ((d->state == BT_CONNECTED || d->state == BT_DISCONN) &&
                                                d->mscex == RFCOMM_MSCEX_OK)
                        rfcomm_process_tx(d);
        }
}

static struct rfcomm_session *rfcomm_process_rx(struct rfcomm_session *s)
{
        struct socket *sock = s->sock;
        struct sock *sk = sock->sk;
        struct sk_buff *skb;

        BT_DBG("session %p state %ld qlen %d", s, s->state, skb_queue_len(&sk->sk_receive_queue));

        /* Get data directly from socket receive queue without copying it. */
        while ((skb = skb_dequeue(&sk->sk_receive_queue))) {
                skb_orphan(skb);
                if (!skb_linearize(skb) && sk->sk_state != BT_CLOSED) {
                        s = rfcomm_recv_frame(s, skb);
                        if (!s)
                                break;
                } else {
                        kfree_skb(skb);
                }
        }

        if (s && (sk->sk_state == BT_CLOSED))
                s = rfcomm_session_close(s, sk->sk_err);

        return s;
}

static void rfcomm_accept_connection(struct rfcomm_session *s)
{
        struct socket *sock = s->sock, *nsock;
        int err;

        /* Fast check for a new connection.
         * Avoids unnesesary socket allocations. */
        if (list_empty(&bt_sk(sock->sk)->accept_q))
                return;

        BT_DBG("session %p", s);

        err = kernel_accept(sock, &nsock, O_NONBLOCK);
        if (err < 0)
                return;

        /* Set our callbacks */
        nsock->sk->sk_data_ready   = rfcomm_l2data_ready;
        nsock->sk->sk_state_change = rfcomm_l2state_change;

        s = rfcomm_session_add(nsock, BT_OPEN);
        if (s) {
                /* We should adjust MTU on incoming sessions.
                 * L2CAP MTU minus UIH header and FCS. */
                s->mtu = min(l2cap_pi(nsock->sk)->chan->omtu,
                                l2cap_pi(nsock->sk)->chan->imtu) - 5;

                rfcomm_schedule();
        } else
                sock_release(nsock);
}

static struct rfcomm_session *rfcomm_check_connection(struct rfcomm_session *s)
{
        struct sock *sk = s->sock->sk;

        BT_DBG("%p state %ld", s, s->state);

        switch (sk->sk_state) {
        case BT_CONNECTED:
                s->state = BT_CONNECT;

                /* We can adjust MTU on outgoing sessions.
                 * L2CAP MTU minus UIH header and FCS. */
                s->mtu = min(l2cap_pi(sk)->chan->omtu, l2cap_pi(sk)->chan->imtu) - 5;

                rfcomm_send_sabm(s, 0);
                break;

        case BT_CLOSED:
                s = rfcomm_session_close(s, sk->sk_err);
                break;
        }
        return s;
}

static void rfcomm_process_sessions(void)
{
        struct rfcomm_session *s, *n;

        rfcomm_lock();

        list_for_each_entry_safe(s, n, &session_list, list) {
                if (test_and_clear_bit(RFCOMM_TIMED_OUT, &s->flags)) {
                        s->state = BT_DISCONN;
                        rfcomm_send_disc(s, 0);
                        continue;
                }

                switch (s->state) {
                case BT_LISTEN:
                        rfcomm_accept_connection(s);
                        continue;

                case BT_BOUND:
                        s = rfcomm_check_connection(s);
                        break;

                default:
                        s = rfcomm_process_rx(s);
                        break;
                }

                if (s)
                        rfcomm_process_dlcs(s);
        }

        rfcomm_unlock();
}

static int rfcomm_add_listener(bdaddr_t *ba)
{
        struct sockaddr_l2 addr;
        struct socket *sock;
        struct sock *sk;
        struct rfcomm_session *s;
        int    err = 0;

        /* Create socket */
        err = rfcomm_l2sock_create(&sock);
        if (err < 0) {
                BT_ERR("Create socket failed %d", err);
                return err;
        }

        /* Bind socket */
        bacpy(&addr.l2_bdaddr, ba);
        addr.l2_family = AF_BLUETOOTH;
        addr.l2_psm    = cpu_to_le16(L2CAP_PSM_RFCOMM);
        addr.l2_cid    = 0;
        addr.l2_bdaddr_type = BDADDR_BREDR;
        err = kernel_bind(sock, (struct sockaddr *) &addr, sizeof(addr));
        if (err < 0) {
                BT_ERR("Bind failed %d", err);
                goto failed;
        }

        /* Set L2CAP options */
        sk = sock->sk;
        lock_sock(sk);
        /* Set MTU to 0 so L2CAP can auto select the MTU */
        l2cap_pi(sk)->chan->imtu = 0;
        release_sock(sk);

        /* Start listening on the socket */
        err = kernel_listen(sock, 10);
        if (err) {
                BT_ERR("Listen failed %d", err);
                goto failed;
        }

        /* Add listening session */
        s = rfcomm_session_add(sock, BT_LISTEN);
        if (!s) {
                err = -ENOMEM;
                goto failed;
        }

        return 0;
failed:
        sock_release(sock);
        return err;
}

static void rfcomm_kill_listener(void)
{
        struct rfcomm_session *s, *n;

        BT_DBG("");

        list_for_each_entry_safe(s, n, &session_list, list)
                rfcomm_session_del(s);
}

static int rfcomm_run(void *unused)
{
        DEFINE_WAIT_FUNC(wait, woken_wake_function);
        BT_DBG("");

        set_user_nice(current, -10);

        rfcomm_add_listener(BDADDR_ANY);

        add_wait_queue(&rfcomm_wq, &wait);
        while (!kthread_should_stop()) {

                /* Process stuff */
                rfcomm_process_sessions();

                wait_woken(&wait, TASK_INTERRUPTIBLE, MAX_SCHEDULE_TIMEOUT);
        }
        remove_wait_queue(&rfcomm_wq, &wait);

        rfcomm_kill_listener();

        return 0;
}

static bool rfcomm_match(struct hci_conn *hcon)
{
        return hcon->type == ACL_LINK;
}

static void rfcomm_security_cfm(struct hci_conn *conn, u8 status, u8 encrypt)
{
        struct rfcomm_session *s;
        struct rfcomm_dlc *d, *n;

        BT_DBG("conn %p status 0x%02x encrypt 0x%02x", conn, status, encrypt);

        s = rfcomm_session_get(&conn->hdev->bdaddr, &conn->dst);
        if (!s)
                return;

        list_for_each_entry_safe(d, n, &s->dlcs, list) {
                if (test_and_clear_bit(RFCOMM_SEC_PENDING, &d->flags)) {
                        rfcomm_dlc_clear_timer(d);
                        if (status || encrypt == 0x00) {
                                set_bit(RFCOMM_ENC_DROP, &d->flags);
                                continue;
                        }
                }

                if (d->state == BT_CONNECTED && !status && encrypt == 0x00) {
                        if (d->sec_level == BT_SECURITY_MEDIUM) {
                                set_bit(RFCOMM_SEC_PENDING, &d->flags);
                                rfcomm_dlc_set_timer(d, RFCOMM_AUTH_TIMEOUT);
                                continue;
                        } else if (d->sec_level == BT_SECURITY_HIGH ||
                                   d->sec_level == BT_SECURITY_FIPS) {
                                set_bit(RFCOMM_ENC_DROP, &d->flags);
                                continue;
                        }
                }

                if (!test_and_clear_bit(RFCOMM_AUTH_PENDING, &d->flags))
                        continue;

                if (!status && hci_conn_check_secure(conn, d->sec_level))
                        set_bit(RFCOMM_AUTH_ACCEPT, &d->flags);
                else
                        set_bit(RFCOMM_AUTH_REJECT, &d->flags);
        }

        rfcomm_schedule();
}

static struct hci_cb rfcomm_cb = {
        .name                = "RFCOMM",
        .match                = rfcomm_match,
        .security_cfm        = rfcomm_security_cfm
};

static int rfcomm_dlc_debugfs_show(struct seq_file *f, void *x)
{
        struct rfcomm_session *s;

        rfcomm_lock();

        list_for_each_entry(s, &session_list, list) {
                struct l2cap_chan *chan = l2cap_pi(s->sock->sk)->chan;
                struct rfcomm_dlc *d;
                list_for_each_entry(d, &s->dlcs, list) {
                        seq_printf(f, "%pMR %pMR %ld %d %d %d %d\n",
                                   &chan->src, &chan->dst,
                                   d->state, d->dlci, d->mtu,
                                   d->rx_credits, d->tx_credits);
                }
        }

        rfcomm_unlock();

        return 0;
}

DEFINE_SHOW_ATTRIBUTE(rfcomm_dlc_debugfs);

static struct dentry *rfcomm_dlc_debugfs;

/* ---- Initialization ---- */
static int __init rfcomm_init(void)
{
        int err;

        hci_register_cb(&rfcomm_cb);

        rfcomm_thread = kthread_run(rfcomm_run, NULL, "krfcommd");
        if (IS_ERR(rfcomm_thread)) {
                err = PTR_ERR(rfcomm_thread);
                goto unregister;
        }

        err = rfcomm_init_ttys();
        if (err < 0)
                goto stop;

        err = rfcomm_init_sockets();
        if (err < 0)
                goto cleanup;

        BT_INFO("RFCOMM ver %s", VERSION);

        if (IS_ERR_OR_NULL(bt_debugfs))
                return 0;

        rfcomm_dlc_debugfs = debugfs_create_file("rfcomm_dlc", 0444,
                                                 bt_debugfs, NULL,
                                                 &rfcomm_dlc_debugfs_fops);

        return 0;

cleanup:
        rfcomm_cleanup_ttys();

stop:
        kthread_stop(rfcomm_thread);

unregister:
        hci_unregister_cb(&rfcomm_cb);

        return err;
}

static void __exit rfcomm_exit(void)
{
        debugfs_remove(rfcomm_dlc_debugfs);

        hci_unregister_cb(&rfcomm_cb);

        kthread_stop(rfcomm_thread);

        rfcomm_cleanup_ttys();

        rfcomm_cleanup_sockets();
}

module_init(rfcomm_init);
module_exit(rfcomm_exit);

module_param(disable_cfc, bool, 0644);
MODULE_PARM_DESC(disable_cfc, "Disable credit based flow control");

module_param(channel_mtu, int, 0644);
MODULE_PARM_DESC(channel_mtu, "Default MTU for the RFCOMM channel");

module_param(l2cap_ertm, bool, 0644);
MODULE_PARM_DESC(l2cap_ertm, "Use L2CAP ERTM mode for connection");

MODULE_AUTHOR("Marcel Holtmann <marcel@holtmann.org>");
MODULE_DESCRIPTION("Bluetooth RFCOMM ver " VERSION);
MODULE_VERSION(VERSION);
MODULE_LICENSE("GPL");
MODULE_ALIAS("bt-proto-3");























    4 
    4 













    4 
    4 
























    4 



















    4 
    4 


























































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
// SPDX-License-Identifier: GPL-2.0
/*
 * linux/net/sunrpc/auth_null.c
 *
 * AUTH_NULL authentication. Really :-)
 *
 * Copyright (C) 1996, Olaf Kirch <okir@monad.swb.de>
 */

#include <linux/types.h>
#include <linux/module.h>
#include <linux/sunrpc/clnt.h>

#if IS_ENABLED(CONFIG_SUNRPC_DEBUG)
# define RPCDBG_FACILITY        RPCDBG_AUTH
#endif

static struct rpc_auth null_auth;
static struct rpc_cred null_cred;

static struct rpc_auth *
nul_create(const struct rpc_auth_create_args *args, struct rpc_clnt *clnt)
{
        refcount_inc(&null_auth.au_count);
        return &null_auth;
}

static void
nul_destroy(struct rpc_auth *auth)
{
}

/*
 * Lookup NULL creds for current process
 */
static struct rpc_cred *
nul_lookup_cred(struct rpc_auth *auth, struct auth_cred *acred, int flags)
{
        return get_rpccred(&null_cred);
}

/*
 * Destroy cred handle.
 */
static void
nul_destroy_cred(struct rpc_cred *cred)
{
}

/*
 * Match cred handle against current process
 */
static int
nul_match(struct auth_cred *acred, struct rpc_cred *cred, int taskflags)
{
        return 1;
}

/*
 * Marshal credential.
 */
static int
nul_marshal(struct rpc_task *task, struct xdr_stream *xdr)
{
        __be32 *p;

        p = xdr_reserve_space(xdr, 4 * sizeof(*p));
        if (!p)
                return -EMSGSIZE;
        /* Credential */
        *p++ = rpc_auth_null;
        *p++ = xdr_zero;
        /* Verifier */
        *p++ = rpc_auth_null;
        *p   = xdr_zero;
        return 0;
}

/*
 * Refresh credential. This is a no-op for AUTH_NULL
 */
static int
nul_refresh(struct rpc_task *task)
{
        set_bit(RPCAUTH_CRED_UPTODATE, &task->tk_rqstp->rq_cred->cr_flags);
        return 0;
}

static int
nul_validate(struct rpc_task *task, struct xdr_stream *xdr)
{
        __be32 *p;

        p = xdr_inline_decode(xdr, 2 * sizeof(*p));
        if (!p)
                return -EIO;
        if (*p++ != rpc_auth_null)
                return -EIO;
        if (*p != xdr_zero)
                return -EIO;
        return 0;
}

const struct rpc_authops authnull_ops = {
        .owner                = THIS_MODULE,
        .au_flavor        = RPC_AUTH_NULL,
        .au_name        = "NULL",
        .create                = nul_create,
        .destroy        = nul_destroy,
        .lookup_cred        = nul_lookup_cred,
};

static
struct rpc_auth null_auth = {
        .au_cslack        = NUL_CALLSLACK,
        .au_rslack        = NUL_REPLYSLACK,
        .au_verfsize        = NUL_REPLYSLACK,
        .au_ralign        = NUL_REPLYSLACK,
        .au_ops                = &authnull_ops,
        .au_flavor        = RPC_AUTH_NULL,
        .au_count        = REFCOUNT_INIT(1),
};

static
const struct rpc_credops null_credops = {
        .cr_name        = "AUTH_NULL",
        .crdestroy        = nul_destroy_cred,
        .crmatch        = nul_match,
        .crmarshal        = nul_marshal,
        .crwrap_req        = rpcauth_wrap_req_encode,
        .crrefresh        = nul_refresh,
        .crvalidate        = nul_validate,
        .crunwrap_resp        = rpcauth_unwrap_resp_decode,
};

static
struct rpc_cred null_cred = {
        .cr_lru                = LIST_HEAD_INIT(null_cred.cr_lru),
        .cr_auth        = &null_auth,
        .cr_ops                = &null_credops,
        .cr_count        = REFCOUNT_INIT(2),
        .cr_flags        = 1UL << RPCAUTH_CRED_UPTODATE,
};













































































































   27 
   27 





   27 


















  296 




  296 
  296 


  227 







  233 



  296 






   10 




  296 



  296 





    7 





    7 
    7 
    7 









    7 





















   70 

   70 





   70 


   31 







    6 








  107 





   18 







   48 



   47 












  227 






















  294 
  171 

    5 

  280 







   69 








  245 













  225 

  222 



   12 



  213 







   31 







  116 

    8 



























  324 



   20 

  302 

    1 

  311 


   23 














  197 











  178 





   21 





  177 

  176 
   21 


  199 












  199 









  122 
   83 
  122 



  122 


    8 











   74 
   75 




   34 









   68 







    4 





    1 




    3 







  177 

   72 
  122 



   93 









  177 
  120 


   72 







   29 
   29 



   29 
   29 




   31 







    3 


















    3 









   15 












  103 
  105 




















































































    4 
    2 


    4 



    3 








  589 


















  590 






    5 

    2 
    3 



    3 













    4 

    4 


    4 















  149 














   49 






  123 

  124 




  130 






  129 






















   27 




   27 






































































































  814 
  581 



  600 



















    2 


    1 













    3 
    2 
    1 










  142 








   12 

    2 

    3 


    7 









   90 
   90 






  109 








   85 






  105 
  105 






  104 







  103 

  105 


















































































   32 










































  173 
   37 



  136 



























































































   27 

























































































































   27 








































   27 



   27 












































































































































































































































































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
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
1187
1188
1189
1190
1191
1192
1193
1194
1195
1196
1197
1198
1199
1200
1201
1202
1203
1204
1205
1206
1207
1208
1209
1210
1211
1212
1213
1214
1215
1216
1217
1218
1219
1220
1221
1222
1223
1224
1225
1226
1227
1228
1229
1230
1231
1232
1233
1234
1235
1236
1237
1238
1239
1240
1241
1242
1243
1244
1245
1246
1247
1248
1249
1250
1251
1252
1253
1254
1255
1256
1257
1258
1259
1260
1261
1262
1263
1264
1265
1266
1267
1268
1269
1270
1271
1272
1273
1274
1275
1276
1277
1278
1279
1280
1281
1282
1283
1284
1285
1286
1287
1288
1289
1290
1291
1292
1293
1294
1295
1296
1297
1298
1299
1300
1301
1302
1303
1304
1305
1306
1307
1308
1309
1310
1311
1312
1313
1314
1315
1316
1317
1318
1319
1320
1321
1322
1323
1324
1325
1326
1327
1328
1329
1330
1331
1332
1333
1334
1335
1336
1337
1338
1339
1340
1341
1342
1343
1344
1345
1346
1347
1348
1349
1350
1351
1352
1353
1354
1355
1356
1357
1358
1359
1360
1361
1362
1363
1364
1365
1366
1367
1368
1369
1370
1371
1372
1373
1374
1375
1376
1377
1378
1379
1380
1381
1382
1383
1384
1385
1386
1387
1388
1389
1390
1391
1392
1393
1394
1395
1396
1397
1398
1399
1400
1401
1402
1403
1404
1405
1406
1407
1408
1409
1410
1411
1412
1413
1414
1415
1416
1417
1418
1419
1420
1421
1422
1423
1424
1425
1426
1427
1428
1429
1430
1431
1432
1433
1434
1435
1436
1437
1438
1439
1440
1441
1442
1443
1444
1445
1446
1447
1448
1449
1450
1451
1452
1453
1454
1455
1456
1457
1458
1459
1460
1461
1462
1463
1464
1465
1466
1467
1468
1469
1470
1471
1472
1473
1474
1475
1476
1477
1478
1479
1480
1481
1482
1483
1484
1485
1486
1487
1488
1489
1490
1491
1492
1493
1494
1495
1496
1497
1498
1499
1500
1501
1502
1503
1504
1505
1506
1507
1508
1509
1510
1511
1512
1513
1514
1515
1516
1517
1518
1519
1520
1521
1522
1523
1524
1525
1526
1527
1528
1529
1530
1531
1532
1533
1534
1535
1536
1537
1538
1539
1540
1541
1542
1543
1544
1545
1546
1547
1548
1549
1550
1551
1552
1553
1554
1555
1556
1557
1558
1559
1560
1561
1562
1563
1564
1565
1566
1567
1568
1569
1570
1571
1572
1573
1574
1575
1576
1577
1578
1579
1580
1581
1582
1583
1584
1585
1586
1587
1588
1589
1590
1591
1592
1593
1594
1595
1596
1597
1598
1599
1600
1601
1602
1603
1604
1605
1606
1607
1608
1609
1610
1611
1612
1613
1614
1615
1616
1617
1618
1619
1620
1621
1622
1623
1624
1625
1626
1627
1628
1629
1630
1631
1632
1633
1634
1635
1636
1637
1638
1639
1640
1641
1642
1643
1644
1645
1646
1647
1648
1649
1650
1651
1652
1653
1654
1655
1656
1657
1658
1659
1660
1661
1662
1663
1664
1665
1666
1667
1668
1669
1670
1671
1672
1673
1674
1675
1676
1677
1678
1679
1680
1681
1682
1683
1684
1685
1686
1687
1688
1689
1690
1691
1692
1693
1694
1695
1696
1697
1698
1699
1700
1701
1702
1703
1704
1705
1706
1707
1708
1709
1710
1711
1712
1713
1714
1715
1716
1717
1718
1719
1720
1721
1722
1723
1724
1725
1726
1727
1728
1729
1730
1731
1732
1733
1734
1735
1736
1737
1738
1739
1740
1741
1742
1743
1744
1745
1746
// SPDX-License-Identifier: GPL-2.0-or-later
/* SCTP kernel implementation
 * (C) Copyright IBM Corp. 2001, 2004
 * Copyright (c) 1999-2000 Cisco, Inc.
 * Copyright (c) 1999-2001 Motorola, Inc.
 * Copyright (c) 2001 Intel Corp.
 * Copyright (c) 2001 Nokia, Inc.
 * Copyright (c) 2001 La Monte H.P. Yarroll
 *
 * This file is part of the SCTP kernel implementation
 *
 * Initialization/cleanup for SCTP protocol support.
 *
 * Please send any bug reports or fixes you make to the
 * email address(es):
 *    lksctp developers <linux-sctp@vger.kernel.org>
 *
 * Written or modified by:
 *    La Monte H.P. Yarroll <piggy@acm.org>
 *    Karl Knutson <karl@athena.chicago.il.us>
 *    Jon Grimm <jgrimm@us.ibm.com>
 *    Sridhar Samudrala <sri@us.ibm.com>
 *    Daisy Chang <daisyc@us.ibm.com>
 *    Ardelle Fan <ardelle.fan@intel.com>
 */

#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt

#include <linux/module.h>
#include <linux/init.h>
#include <linux/netdevice.h>
#include <linux/inetdevice.h>
#include <linux/seq_file.h>
#include <linux/memblock.h>
#include <linux/highmem.h>
#include <linux/slab.h>
#include <net/net_namespace.h>
#include <net/protocol.h>
#include <net/ip.h>
#include <net/ipv6.h>
#include <net/route.h>
#include <net/sctp/sctp.h>
#include <net/addrconf.h>
#include <net/inet_common.h>
#include <net/inet_ecn.h>
#include <net/udp_tunnel.h>
#include <net/inet_dscp.h>

#define MAX_SCTP_PORT_HASH_ENTRIES (64 * 1024)

/* Global data structures. */
struct sctp_globals sctp_globals __read_mostly;

struct idr sctp_assocs_id;
DEFINE_SPINLOCK(sctp_assocs_id_lock);

static struct sctp_pf *sctp_pf_inet6_specific;
static struct sctp_pf *sctp_pf_inet_specific;
static struct sctp_af *sctp_af_v4_specific;
static struct sctp_af *sctp_af_v6_specific;

struct kmem_cache *sctp_chunk_cachep __read_mostly;
struct kmem_cache *sctp_bucket_cachep __read_mostly;

long sysctl_sctp_mem[3];
int sysctl_sctp_rmem[3];
int sysctl_sctp_wmem[3];

/* Private helper to extract ipv4 address and stash them in
 * the protocol structure.
 */
static void sctp_v4_copy_addrlist(struct list_head *addrlist,
                                  struct net_device *dev)
{
        struct in_device *in_dev;
        struct in_ifaddr *ifa;
        struct sctp_sockaddr_entry *addr;

        rcu_read_lock();
        if ((in_dev = __in_dev_get_rcu(dev)) == NULL) {
                rcu_read_unlock();
                return;
        }

        in_dev_for_each_ifa_rcu(ifa, in_dev) {
                /* Add the address to the local list.  */
                addr = kzalloc(sizeof(*addr), GFP_ATOMIC);
                if (addr) {
                        addr->a.v4.sin_family = AF_INET;
                        addr->a.v4.sin_addr.s_addr = ifa->ifa_local;
                        addr->valid = 1;
                        INIT_LIST_HEAD(&addr->list);
                        list_add_tail(&addr->list, addrlist);
                }
        }

        rcu_read_unlock();
}

/* Extract our IP addresses from the system and stash them in the
 * protocol structure.
 */
static void sctp_get_local_addr_list(struct net *net)
{
        struct net_device *dev;
        struct list_head *pos;
        struct sctp_af *af;

        rcu_read_lock();
        for_each_netdev_rcu(net, dev) {
                list_for_each(pos, &sctp_address_families) {
                        af = list_entry(pos, struct sctp_af, list);
                        af->copy_addrlist(&net->sctp.local_addr_list, dev);
                }
        }
        rcu_read_unlock();
}

/* Free the existing local addresses.  */
static void sctp_free_local_addr_list(struct net *net)
{
        struct sctp_sockaddr_entry *addr;
        struct list_head *pos, *temp;

        list_for_each_safe(pos, temp, &net->sctp.local_addr_list) {
                addr = list_entry(pos, struct sctp_sockaddr_entry, list);
                list_del(pos);
                kfree(addr);
        }
}

/* Copy the local addresses which are valid for 'scope' into 'bp'.  */
int sctp_copy_local_addr_list(struct net *net, struct sctp_bind_addr *bp,
                              enum sctp_scope scope, gfp_t gfp, int copy_flags)
{
        struct sctp_sockaddr_entry *addr;
        union sctp_addr laddr;
        int error = 0;

        rcu_read_lock();
        list_for_each_entry_rcu(addr, &net->sctp.local_addr_list, list) {
                if (!addr->valid)
                        continue;
                if (!sctp_in_scope(net, &addr->a, scope))
                        continue;

                /* Now that the address is in scope, check to see if
                 * the address type is really supported by the local
                 * sock as well as the remote peer.
                 */
                if (addr->a.sa.sa_family == AF_INET &&
                    (!(copy_flags & SCTP_ADDR4_ALLOWED) ||
                     !(copy_flags & SCTP_ADDR4_PEERSUPP)))
                        continue;
                if (addr->a.sa.sa_family == AF_INET6 &&
                    (!(copy_flags & SCTP_ADDR6_ALLOWED) ||
                     !(copy_flags & SCTP_ADDR6_PEERSUPP)))
                        continue;

                laddr = addr->a;
                /* also works for setting ipv6 address port */
                laddr.v4.sin_port = htons(bp->port);
                if (sctp_bind_addr_state(bp, &laddr) != -1)
                        continue;

                error = sctp_add_bind_addr(bp, &addr->a, sizeof(addr->a),
                                           SCTP_ADDR_SRC, GFP_ATOMIC);
                if (error)
                        break;
        }

        rcu_read_unlock();
        return error;
}

/* Copy over any ip options */
static void sctp_v4_copy_ip_options(struct sock *sk, struct sock *newsk)
{
        struct inet_sock *newinet, *inet = inet_sk(sk);
        struct ip_options_rcu *inet_opt, *newopt = NULL;

        newinet = inet_sk(newsk);

        rcu_read_lock();
        inet_opt = rcu_dereference(inet->inet_opt);
        if (inet_opt) {
                newopt = sock_kmalloc(newsk, sizeof(*inet_opt) +
                                      inet_opt->opt.optlen, GFP_ATOMIC);
                if (newopt)
                        memcpy(newopt, inet_opt, sizeof(*inet_opt) +
                               inet_opt->opt.optlen);
                else
                        pr_err("%s: Failed to copy ip options\n", __func__);
        }
        RCU_INIT_POINTER(newinet->inet_opt, newopt);
        rcu_read_unlock();
}

/* Account for the IP options */
static int sctp_v4_ip_options_len(struct sock *sk)
{
        struct inet_sock *inet = inet_sk(sk);
        struct ip_options_rcu *inet_opt;
        int len = 0;

        rcu_read_lock();
        inet_opt = rcu_dereference(inet->inet_opt);
        if (inet_opt)
                len = inet_opt->opt.optlen;

        rcu_read_unlock();
        return len;
}

/* Initialize a sctp_addr from in incoming skb.  */
static void sctp_v4_from_skb(union sctp_addr *addr, struct sk_buff *skb,
                             int is_saddr)
{
        /* Always called on head skb, so this is safe */
        struct sctphdr *sh = sctp_hdr(skb);
        struct sockaddr_in *sa = &addr->v4;

        addr->v4.sin_family = AF_INET;

        if (is_saddr) {
                sa->sin_port = sh->source;
                sa->sin_addr.s_addr = ip_hdr(skb)->saddr;
        } else {
                sa->sin_port = sh->dest;
                sa->sin_addr.s_addr = ip_hdr(skb)->daddr;
        }
        memset(sa->sin_zero, 0, sizeof(sa->sin_zero));
}

/* Initialize an sctp_addr from a socket. */
static void sctp_v4_from_sk(union sctp_addr *addr, struct sock *sk)
{
        addr->v4.sin_family = AF_INET;
        addr->v4.sin_port = 0;
        addr->v4.sin_addr.s_addr = inet_sk(sk)->inet_rcv_saddr;
        memset(addr->v4.sin_zero, 0, sizeof(addr->v4.sin_zero));
}

/* Initialize sk->sk_rcv_saddr from sctp_addr. */
static void sctp_v4_to_sk_saddr(union sctp_addr *addr, struct sock *sk)
{
        inet_sk(sk)->inet_rcv_saddr = addr->v4.sin_addr.s_addr;
}

/* Initialize sk->sk_daddr from sctp_addr. */
static void sctp_v4_to_sk_daddr(union sctp_addr *addr, struct sock *sk)
{
        inet_sk(sk)->inet_daddr = addr->v4.sin_addr.s_addr;
}

/* Initialize a sctp_addr from an address parameter. */
static bool sctp_v4_from_addr_param(union sctp_addr *addr,
                                    union sctp_addr_param *param,
                                    __be16 port, int iif)
{
        if (ntohs(param->v4.param_hdr.length) < sizeof(struct sctp_ipv4addr_param))
                return false;

        addr->v4.sin_family = AF_INET;
        addr->v4.sin_port = port;
        addr->v4.sin_addr.s_addr = param->v4.addr.s_addr;
        memset(addr->v4.sin_zero, 0, sizeof(addr->v4.sin_zero));

        return true;
}

/* Initialize an address parameter from a sctp_addr and return the length
 * of the address parameter.
 */
static int sctp_v4_to_addr_param(const union sctp_addr *addr,
                                 union sctp_addr_param *param)
{
        int length = sizeof(struct sctp_ipv4addr_param);

        param->v4.param_hdr.type = SCTP_PARAM_IPV4_ADDRESS;
        param->v4.param_hdr.length = htons(length);
        param->v4.addr.s_addr = addr->v4.sin_addr.s_addr;

        return length;
}

/* Initialize a sctp_addr from a dst_entry. */
static void sctp_v4_dst_saddr(union sctp_addr *saddr, struct flowi4 *fl4,
                              __be16 port)
{
        saddr->v4.sin_family = AF_INET;
        saddr->v4.sin_port = port;
        saddr->v4.sin_addr.s_addr = fl4->saddr;
        memset(saddr->v4.sin_zero, 0, sizeof(saddr->v4.sin_zero));
}

/* Compare two addresses exactly. */
static int sctp_v4_cmp_addr(const union sctp_addr *addr1,
                            const union sctp_addr *addr2)
{
        if (addr1->sa.sa_family != addr2->sa.sa_family)
                return 0;
        if (addr1->v4.sin_port != addr2->v4.sin_port)
                return 0;
        if (addr1->v4.sin_addr.s_addr != addr2->v4.sin_addr.s_addr)
                return 0;

        return 1;
}

/* Initialize addr struct to INADDR_ANY. */
static void sctp_v4_inaddr_any(union sctp_addr *addr, __be16 port)
{
        addr->v4.sin_family = AF_INET;
        addr->v4.sin_addr.s_addr = htonl(INADDR_ANY);
        addr->v4.sin_port = port;
        memset(addr->v4.sin_zero, 0, sizeof(addr->v4.sin_zero));
}

/* Is this a wildcard address? */
static int sctp_v4_is_any(const union sctp_addr *addr)
{
        return htonl(INADDR_ANY) == addr->v4.sin_addr.s_addr;
}

/* This function checks if the address is a valid address to be used for
 * SCTP binding.
 *
 * Output:
 * Return 0 - If the address is a non-unicast or an illegal address.
 * Return 1 - If the address is a unicast.
 */
static int sctp_v4_addr_valid(union sctp_addr *addr,
                              struct sctp_sock *sp,
                              const struct sk_buff *skb)
{
        /* IPv4 addresses not allowed */
        if (sp && ipv6_only_sock(sctp_opt2sk(sp)))
                return 0;

        /* Is this a non-unicast address or a unusable SCTP address? */
        if (IS_IPV4_UNUSABLE_ADDRESS(addr->v4.sin_addr.s_addr))
                return 0;

        /* Is this a broadcast address? */
        if (skb && skb_rtable(skb)->rt_flags & RTCF_BROADCAST)
                return 0;

        return 1;
}

/* Should this be available for binding?   */
static int sctp_v4_available(union sctp_addr *addr, struct sctp_sock *sp)
{
        struct sock *sk = &sp->inet.sk;
        struct net *net = sock_net(sk);
        int tb_id = RT_TABLE_LOCAL;
        int ret;

        tb_id = l3mdev_fib_table_by_index(net, sk->sk_bound_dev_if) ?: tb_id;
        ret = inet_addr_type_table(net, addr->v4.sin_addr.s_addr, tb_id);
        if (addr->v4.sin_addr.s_addr != htonl(INADDR_ANY) &&
           ret != RTN_LOCAL &&
           !inet_test_bit(FREEBIND, sk) &&
            !READ_ONCE(net->ipv4.sysctl_ip_nonlocal_bind))
                return 0;

        if (ipv6_only_sock(sctp_opt2sk(sp)))
                return 0;

        return 1;
}

/* Checking the loopback, private and other address scopes as defined in
 * RFC 1918.   The IPv4 scoping is based on the draft for SCTP IPv4
 * scoping <draft-stewart-tsvwg-sctp-ipv4-00.txt>.
 *
 * Level 0 - unusable SCTP addresses
 * Level 1 - loopback address
 * Level 2 - link-local addresses
 * Level 3 - private addresses.
 * Level 4 - global addresses
 * For INIT and INIT-ACK address list, let L be the level of
 * requested destination address, sender and receiver
 * SHOULD include all of its addresses with level greater
 * than or equal to L.
 *
 * IPv4 scoping can be controlled through sysctl option
 * net.sctp.addr_scope_policy
 */
static enum sctp_scope sctp_v4_scope(union sctp_addr *addr)
{
        enum sctp_scope retval;

        /* Check for unusable SCTP addresses. */
        if (IS_IPV4_UNUSABLE_ADDRESS(addr->v4.sin_addr.s_addr)) {
                retval =  SCTP_SCOPE_UNUSABLE;
        } else if (ipv4_is_loopback(addr->v4.sin_addr.s_addr)) {
                retval = SCTP_SCOPE_LOOPBACK;
        } else if (ipv4_is_linklocal_169(addr->v4.sin_addr.s_addr)) {
                retval = SCTP_SCOPE_LINK;
        } else if (ipv4_is_private_10(addr->v4.sin_addr.s_addr) ||
                   ipv4_is_private_172(addr->v4.sin_addr.s_addr) ||
                   ipv4_is_private_192(addr->v4.sin_addr.s_addr) ||
                   ipv4_is_test_198(addr->v4.sin_addr.s_addr)) {
                retval = SCTP_SCOPE_PRIVATE;
        } else {
                retval = SCTP_SCOPE_GLOBAL;
        }

        return retval;
}

/* Returns a valid dst cache entry for the given source and destination ip
 * addresses. If an association is passed, trys to get a dst entry with a
 * source address that matches an address in the bind address list.
 */
static void sctp_v4_get_dst(struct sctp_transport *t, union sctp_addr *saddr,
                                struct flowi *fl, struct sock *sk)
{
        struct sctp_association *asoc = t->asoc;
        struct rtable *rt;
        struct flowi _fl;
        struct flowi4 *fl4 = &_fl.u.ip4;
        struct sctp_bind_addr *bp;
        struct sctp_sockaddr_entry *laddr;
        struct dst_entry *dst = NULL;
        union sctp_addr *daddr = &t->ipaddr;
        union sctp_addr dst_saddr;
        u8 tos = READ_ONCE(inet_sk(sk)->tos);

        if (t->dscp & SCTP_DSCP_SET_MASK)
                tos = t->dscp & SCTP_DSCP_VAL_MASK;
        memset(&_fl, 0x0, sizeof(_fl));
        fl4->daddr  = daddr->v4.sin_addr.s_addr;
        fl4->fl4_dport = daddr->v4.sin_port;
        fl4->flowi4_proto = IPPROTO_SCTP;
        if (asoc) {
                fl4->flowi4_tos = tos & INET_DSCP_MASK;
                fl4->flowi4_scope = ip_sock_rt_scope(asoc->base.sk);
                fl4->flowi4_oif = asoc->base.sk->sk_bound_dev_if;
                fl4->fl4_sport = htons(asoc->base.bind_addr.port);
        }
        if (saddr) {
                fl4->saddr = saddr->v4.sin_addr.s_addr;
                if (!fl4->fl4_sport)
                        fl4->fl4_sport = saddr->v4.sin_port;
        }

        pr_debug("%s: dst:%pI4, src:%pI4 - ", __func__, &fl4->daddr,
                 &fl4->saddr);

        rt = ip_route_output_key(sock_net(sk), fl4);
        if (!IS_ERR(rt)) {
                dst = &rt->dst;
                t->dst = dst;
                memcpy(fl, &_fl, sizeof(_fl));
        }

        /* If there is no association or if a source address is passed, no
         * more validation is required.
         */
        if (!asoc || saddr)
                goto out;

        bp = &asoc->base.bind_addr;

        if (dst) {
                /* Walk through the bind address list and look for a bind
                 * address that matches the source address of the returned dst.
                 */
                sctp_v4_dst_saddr(&dst_saddr, fl4, htons(bp->port));
                rcu_read_lock();
                list_for_each_entry_rcu(laddr, &bp->address_list, list) {
                        if (!laddr->valid || (laddr->state == SCTP_ADDR_DEL) ||
                            (laddr->state != SCTP_ADDR_SRC &&
                            !asoc->src_out_of_asoc_ok))
                                continue;
                        if (sctp_v4_cmp_addr(&dst_saddr, &laddr->a))
                                goto out_unlock;
                }
                rcu_read_unlock();

                /* None of the bound addresses match the source address of the
                 * dst. So release it.
                 */
                dst_release(dst);
                dst = NULL;
        }

        /* Walk through the bind address list and try to get a dst that
         * matches a bind address as the source address.
         */
        rcu_read_lock();
        list_for_each_entry_rcu(laddr, &bp->address_list, list) {
                struct net_device *odev;

                if (!laddr->valid)
                        continue;
                if (laddr->state != SCTP_ADDR_SRC ||
                    AF_INET != laddr->a.sa.sa_family)
                        continue;

                fl4->fl4_sport = laddr->a.v4.sin_port;
                flowi4_update_output(fl4, asoc->base.sk->sk_bound_dev_if,
                                     daddr->v4.sin_addr.s_addr,
                                     laddr->a.v4.sin_addr.s_addr);

                rt = ip_route_output_key(sock_net(sk), fl4);
                if (IS_ERR(rt))
                        continue;

                /* Ensure the src address belongs to the output
                 * interface.
                 */
                odev = __ip_dev_find(sock_net(sk), laddr->a.v4.sin_addr.s_addr,
                                     false);
                if (!odev || odev->ifindex != fl4->flowi4_oif) {
                        if (!dst) {
                                dst = &rt->dst;
                                t->dst = dst;
                                memcpy(fl, &_fl, sizeof(_fl));
                        } else {
                                dst_release(&rt->dst);
                        }
                        continue;
                }

                dst_release(dst);
                dst = &rt->dst;
                t->dst = dst;
                memcpy(fl, &_fl, sizeof(_fl));
                break;
        }

out_unlock:
        rcu_read_unlock();
out:
        if (dst) {
                pr_debug("rt_dst:%pI4, rt_src:%pI4\n",
                         &fl->u.ip4.daddr, &fl->u.ip4.saddr);
        } else {
                t->dst = NULL;
                pr_debug("no route\n");
        }
}

/* For v4, the source address is cached in the route entry(dst). So no need
 * to cache it separately and hence this is an empty routine.
 */
static void sctp_v4_get_saddr(struct sctp_sock *sk,
                              struct sctp_transport *t,
                              struct flowi *fl)
{
        union sctp_addr *saddr = &t->saddr;
        struct rtable *rt = dst_rtable(t->dst);

        if (rt) {
                saddr->v4.sin_family = AF_INET;
                saddr->v4.sin_addr.s_addr = fl->u.ip4.saddr;
        }
}

/* What interface did this skb arrive on? */
static int sctp_v4_skb_iif(const struct sk_buff *skb)
{
        return inet_iif(skb);
}

static int sctp_v4_skb_sdif(const struct sk_buff *skb)
{
        return inet_sdif(skb);
}

/* Was this packet marked by Explicit Congestion Notification? */
static int sctp_v4_is_ce(const struct sk_buff *skb)
{
        return INET_ECN_is_ce(ip_hdr(skb)->tos);
}

/* Create and initialize a new sk for the socket returned by accept(). */
static struct sock *sctp_v4_create_accept_sk(struct sock *sk,
                                             struct sctp_association *asoc,
                                             bool kern)
{
        struct sock *newsk = sk_alloc(sock_net(sk), PF_INET, GFP_KERNEL,
                        sk->sk_prot, kern);
        struct inet_sock *newinet;

        if (!newsk)
                goto out;

        sock_init_data(NULL, newsk);

        sctp_copy_sock(newsk, sk, asoc);
        sock_reset_flag(newsk, SOCK_ZAPPED);

        sctp_v4_copy_ip_options(sk, newsk);

        newinet = inet_sk(newsk);

        newinet->inet_daddr = asoc->peer.primary_addr.v4.sin_addr.s_addr;

        if (newsk->sk_prot->init(newsk)) {
                sk_common_release(newsk);
                newsk = NULL;
        }

out:
        return newsk;
}

static int sctp_v4_addr_to_user(struct sctp_sock *sp, union sctp_addr *addr)
{
        /* No address mapping for V4 sockets */
        memset(addr->v4.sin_zero, 0, sizeof(addr->v4.sin_zero));
        return sizeof(struct sockaddr_in);
}

/* Dump the v4 addr to the seq file. */
static void sctp_v4_seq_dump_addr(struct seq_file *seq, union sctp_addr *addr)
{
        seq_printf(seq, "%pI4 ", &addr->v4.sin_addr);
}

static void sctp_v4_ecn_capable(struct sock *sk)
{
        INET_ECN_xmit(sk);
}

static void sctp_addr_wq_timeout_handler(struct timer_list *t)
{
        struct net *net = from_timer(net, t, sctp.addr_wq_timer);
        struct sctp_sockaddr_entry *addrw, *temp;
        struct sctp_sock *sp;

        spin_lock_bh(&net->sctp.addr_wq_lock);

        list_for_each_entry_safe(addrw, temp, &net->sctp.addr_waitq, list) {
                pr_debug("%s: the first ent in wq:%p is addr:%pISc for cmd:%d at "
                         "entry:%p\n", __func__, &net->sctp.addr_waitq, &addrw->a.sa,
                         addrw->state, addrw);

#if IS_ENABLED(CONFIG_IPV6)
                /* Now we send an ASCONF for each association */
                /* Note. we currently don't handle link local IPv6 addressees */
                if (addrw->a.sa.sa_family == AF_INET6) {
                        struct in6_addr *in6;

                        if (ipv6_addr_type(&addrw->a.v6.sin6_addr) &
                            IPV6_ADDR_LINKLOCAL)
                                goto free_next;

                        in6 = (struct in6_addr *)&addrw->a.v6.sin6_addr;
                        if (ipv6_chk_addr(net, in6, NULL, 0) == 0 &&
                            addrw->state == SCTP_ADDR_NEW) {
                                unsigned long timeo_val;

                                pr_debug("%s: this is on DAD, trying %d sec "
                                         "later\n", __func__,
                                         SCTP_ADDRESS_TICK_DELAY);

                                timeo_val = jiffies;
                                timeo_val += msecs_to_jiffies(SCTP_ADDRESS_TICK_DELAY);
                                mod_timer(&net->sctp.addr_wq_timer, timeo_val);
                                break;
                        }
                }
#endif
                list_for_each_entry(sp, &net->sctp.auto_asconf_splist, auto_asconf_list) {
                        struct sock *sk;

                        sk = sctp_opt2sk(sp);
                        /* ignore bound-specific endpoints */
                        if (!sctp_is_ep_boundall(sk))
                                continue;
                        bh_lock_sock(sk);
                        if (sctp_asconf_mgmt(sp, addrw) < 0)
                                pr_debug("%s: sctp_asconf_mgmt failed\n", __func__);
                        bh_unlock_sock(sk);
                }
#if IS_ENABLED(CONFIG_IPV6)
free_next:
#endif
                list_del(&addrw->list);
                kfree(addrw);
        }
        spin_unlock_bh(&net->sctp.addr_wq_lock);
}

static void sctp_free_addr_wq(struct net *net)
{
        struct sctp_sockaddr_entry *addrw;
        struct sctp_sockaddr_entry *temp;

        spin_lock_bh(&net->sctp.addr_wq_lock);
        del_timer(&net->sctp.addr_wq_timer);
        list_for_each_entry_safe(addrw, temp, &net->sctp.addr_waitq, list) {
                list_del(&addrw->list);
                kfree(addrw);
        }
        spin_unlock_bh(&net->sctp.addr_wq_lock);
}

/* lookup the entry for the same address in the addr_waitq
 * sctp_addr_wq MUST be locked
 */
static struct sctp_sockaddr_entry *sctp_addr_wq_lookup(struct net *net,
                                        struct sctp_sockaddr_entry *addr)
{
        struct sctp_sockaddr_entry *addrw;

        list_for_each_entry(addrw, &net->sctp.addr_waitq, list) {
                if (addrw->a.sa.sa_family != addr->a.sa.sa_family)
                        continue;
                if (addrw->a.sa.sa_family == AF_INET) {
                        if (addrw->a.v4.sin_addr.s_addr ==
                            addr->a.v4.sin_addr.s_addr)
                                return addrw;
                } else if (addrw->a.sa.sa_family == AF_INET6) {
                        if (ipv6_addr_equal(&addrw->a.v6.sin6_addr,
                            &addr->a.v6.sin6_addr))
                                return addrw;
                }
        }
        return NULL;
}

void sctp_addr_wq_mgmt(struct net *net, struct sctp_sockaddr_entry *addr, int cmd)
{
        struct sctp_sockaddr_entry *addrw;
        unsigned long timeo_val;

        /* first, we check if an opposite message already exist in the queue.
         * If we found such message, it is removed.
         * This operation is a bit stupid, but the DHCP client attaches the
         * new address after a couple of addition and deletion of that address
         */

        spin_lock_bh(&net->sctp.addr_wq_lock);

        /* Avoid searching the queue or modifying it if there are no consumers,
         * as it can lead to performance degradation if addresses are modified
         * en-masse.
         *
         * If the queue already contains some events, update it anyway to avoid
         * ugly races between new sessions and new address events.
         */
        if (list_empty(&net->sctp.auto_asconf_splist) &&
            list_empty(&net->sctp.addr_waitq)) {
                spin_unlock_bh(&net->sctp.addr_wq_lock);
                return;
        }

        /* Offsets existing events in addr_wq */
        addrw = sctp_addr_wq_lookup(net, addr);
        if (addrw) {
                if (addrw->state != cmd) {
                        pr_debug("%s: offsets existing entry for %d, addr:%pISc "
                                 "in wq:%p\n", __func__, addrw->state, &addrw->a.sa,
                                 &net->sctp.addr_waitq);

                        list_del(&addrw->list);
                        kfree(addrw);
                }
                spin_unlock_bh(&net->sctp.addr_wq_lock);
                return;
        }

        /* OK, we have to add the new address to the wait queue */
        addrw = kmemdup(addr, sizeof(struct sctp_sockaddr_entry), GFP_ATOMIC);
        if (addrw == NULL) {
                spin_unlock_bh(&net->sctp.addr_wq_lock);
                return;
        }
        addrw->state = cmd;
        list_add_tail(&addrw->list, &net->sctp.addr_waitq);

        pr_debug("%s: add new entry for cmd:%d, addr:%pISc in wq:%p\n",
                 __func__, addrw->state, &addrw->a.sa, &net->sctp.addr_waitq);

        if (!timer_pending(&net->sctp.addr_wq_timer)) {
                timeo_val = jiffies;
                timeo_val += msecs_to_jiffies(SCTP_ADDRESS_TICK_DELAY);
                mod_timer(&net->sctp.addr_wq_timer, timeo_val);
        }
        spin_unlock_bh(&net->sctp.addr_wq_lock);
}

/* Event handler for inet address addition/deletion events.
 * The sctp_local_addr_list needs to be protocted by a spin lock since
 * multiple notifiers (say IPv4 and IPv6) may be running at the same
 * time and thus corrupt the list.
 * The reader side is protected with RCU.
 */
static int sctp_inetaddr_event(struct notifier_block *this, unsigned long ev,
                               void *ptr)
{
        struct in_ifaddr *ifa = (struct in_ifaddr *)ptr;
        struct sctp_sockaddr_entry *addr = NULL;
        struct sctp_sockaddr_entry *temp;
        struct net *net = dev_net(ifa->ifa_dev->dev);
        int found = 0;

        switch (ev) {
        case NETDEV_UP:
                addr = kzalloc(sizeof(*addr), GFP_ATOMIC);
                if (addr) {
                        addr->a.v4.sin_family = AF_INET;
                        addr->a.v4.sin_addr.s_addr = ifa->ifa_local;
                        addr->valid = 1;
                        spin_lock_bh(&net->sctp.local_addr_lock);
                        list_add_tail_rcu(&addr->list, &net->sctp.local_addr_list);
                        sctp_addr_wq_mgmt(net, addr, SCTP_ADDR_NEW);
                        spin_unlock_bh(&net->sctp.local_addr_lock);
                }
                break;
        case NETDEV_DOWN:
                spin_lock_bh(&net->sctp.local_addr_lock);
                list_for_each_entry_safe(addr, temp,
                                        &net->sctp.local_addr_list, list) {
                        if (addr->a.sa.sa_family == AF_INET &&
                                        addr->a.v4.sin_addr.s_addr ==
                                        ifa->ifa_local) {
                                found = 1;
                                addr->valid = 0;
                                list_del_rcu(&addr->list);
                                sctp_addr_wq_mgmt(net, addr, SCTP_ADDR_DEL);
                                break;
                        }
                }
                spin_unlock_bh(&net->sctp.local_addr_lock);
                if (found)
                        kfree_rcu(addr, rcu);
                break;
        }

        return NOTIFY_DONE;
}

/*
 * Initialize the control inode/socket with a control endpoint data
 * structure.  This endpoint is reserved exclusively for the OOTB processing.
 */
static int sctp_ctl_sock_init(struct net *net)
{
        int err;
        sa_family_t family = PF_INET;

        if (sctp_get_pf_specific(PF_INET6))
                family = PF_INET6;

        err = inet_ctl_sock_create(&net->sctp.ctl_sock, family,
                                   SOCK_SEQPACKET, IPPROTO_SCTP, net);

        /* If IPv6 socket could not be created, try the IPv4 socket */
        if (err < 0 && family == PF_INET6)
                err = inet_ctl_sock_create(&net->sctp.ctl_sock, AF_INET,
                                           SOCK_SEQPACKET, IPPROTO_SCTP,
                                           net);

        if (err < 0) {
                pr_err("Failed to create the SCTP control socket\n");
                return err;
        }
        return 0;
}

static int sctp_udp_rcv(struct sock *sk, struct sk_buff *skb)
{
        SCTP_INPUT_CB(skb)->encap_port = udp_hdr(skb)->source;

        skb_set_transport_header(skb, sizeof(struct udphdr));
        sctp_rcv(skb);
        return 0;
}

int sctp_udp_sock_start(struct net *net)
{
        struct udp_tunnel_sock_cfg tuncfg = {NULL};
        struct udp_port_cfg udp_conf = {0};
        struct socket *sock;
        int err;

        udp_conf.family = AF_INET;
        udp_conf.local_ip.s_addr = htonl(INADDR_ANY);
        udp_conf.local_udp_port = htons(net->sctp.udp_port);
        err = udp_sock_create(net, &udp_conf, &sock);
        if (err) {
                pr_err("Failed to create the SCTP UDP tunneling v4 sock\n");
                return err;
        }

        tuncfg.encap_type = 1;
        tuncfg.encap_rcv = sctp_udp_rcv;
        tuncfg.encap_err_lookup = sctp_udp_v4_err;
        setup_udp_tunnel_sock(net, sock, &tuncfg);
        net->sctp.udp4_sock = sock->sk;

#if IS_ENABLED(CONFIG_IPV6)
        memset(&udp_conf, 0, sizeof(udp_conf));

        udp_conf.family = AF_INET6;
        udp_conf.local_ip6 = in6addr_any;
        udp_conf.local_udp_port = htons(net->sctp.udp_port);
        udp_conf.use_udp6_rx_checksums = true;
        udp_conf.ipv6_v6only = true;
        err = udp_sock_create(net, &udp_conf, &sock);
        if (err) {
                pr_err("Failed to create the SCTP UDP tunneling v6 sock\n");
                udp_tunnel_sock_release(net->sctp.udp4_sock->sk_socket);
                net->sctp.udp4_sock = NULL;
                return err;
        }

        tuncfg.encap_type = 1;
        tuncfg.encap_rcv = sctp_udp_rcv;
        tuncfg.encap_err_lookup = sctp_udp_v6_err;
        setup_udp_tunnel_sock(net, sock, &tuncfg);
        net->sctp.udp6_sock = sock->sk;
#endif

        return 0;
}

void sctp_udp_sock_stop(struct net *net)
{
        if (net->sctp.udp4_sock) {
                udp_tunnel_sock_release(net->sctp.udp4_sock->sk_socket);
                net->sctp.udp4_sock = NULL;
        }
        if (net->sctp.udp6_sock) {
                udp_tunnel_sock_release(net->sctp.udp6_sock->sk_socket);
                net->sctp.udp6_sock = NULL;
        }
}

/* Register address family specific functions. */
int sctp_register_af(struct sctp_af *af)
{
        switch (af->sa_family) {
        case AF_INET:
                if (sctp_af_v4_specific)
                        return 0;
                sctp_af_v4_specific = af;
                break;
        case AF_INET6:
                if (sctp_af_v6_specific)
                        return 0;
                sctp_af_v6_specific = af;
                break;
        default:
                return 0;
        }

        INIT_LIST_HEAD(&af->list);
        list_add_tail(&af->list, &sctp_address_families);
        return 1;
}

/* Get the table of functions for manipulating a particular address
 * family.
 */
struct sctp_af *sctp_get_af_specific(sa_family_t family)
{
        switch (family) {
        case AF_INET:
                return sctp_af_v4_specific;
        case AF_INET6:
                return sctp_af_v6_specific;
        default:
                return NULL;
        }
}

/* Common code to initialize a AF_INET msg_name. */
static void sctp_inet_msgname(char *msgname, int *addr_len)
{
        struct sockaddr_in *sin;

        sin = (struct sockaddr_in *)msgname;
        *addr_len = sizeof(struct sockaddr_in);
        sin->sin_family = AF_INET;
        memset(sin->sin_zero, 0, sizeof(sin->sin_zero));
}

/* Copy the primary address of the peer primary address as the msg_name. */
static void sctp_inet_event_msgname(struct sctp_ulpevent *event, char *msgname,
                                    int *addr_len)
{
        struct sockaddr_in *sin, *sinfrom;

        if (msgname) {
                struct sctp_association *asoc;

                asoc = event->asoc;
                sctp_inet_msgname(msgname, addr_len);
                sin = (struct sockaddr_in *)msgname;
                sinfrom = &asoc->peer.primary_addr.v4;
                sin->sin_port = htons(asoc->peer.port);
                sin->sin_addr.s_addr = sinfrom->sin_addr.s_addr;
        }
}

/* Initialize and copy out a msgname from an inbound skb. */
static void sctp_inet_skb_msgname(struct sk_buff *skb, char *msgname, int *len)
{
        if (msgname) {
                struct sctphdr *sh = sctp_hdr(skb);
                struct sockaddr_in *sin = (struct sockaddr_in *)msgname;

                sctp_inet_msgname(msgname, len);
                sin->sin_port = sh->source;
                sin->sin_addr.s_addr = ip_hdr(skb)->saddr;
        }
}

/* Do we support this AF? */
static int sctp_inet_af_supported(sa_family_t family, struct sctp_sock *sp)
{
        /* PF_INET only supports AF_INET addresses. */
        return AF_INET == family;
}

/* Address matching with wildcards allowed. */
static int sctp_inet_cmp_addr(const union sctp_addr *addr1,
                              const union sctp_addr *addr2,
                              struct sctp_sock *opt)
{
        /* PF_INET only supports AF_INET addresses. */
        if (addr1->sa.sa_family != addr2->sa.sa_family)
                return 0;
        if (htonl(INADDR_ANY) == addr1->v4.sin_addr.s_addr ||
            htonl(INADDR_ANY) == addr2->v4.sin_addr.s_addr)
                return 1;
        if (addr1->v4.sin_addr.s_addr == addr2->v4.sin_addr.s_addr)
                return 1;

        return 0;
}

/* Verify that provided sockaddr looks bindable.  Common verification has
 * already been taken care of.
 */
static int sctp_inet_bind_verify(struct sctp_sock *opt, union sctp_addr *addr)
{
        return sctp_v4_available(addr, opt);
}

/* Verify that sockaddr looks sendable.  Common verification has already
 * been taken care of.
 */
static int sctp_inet_send_verify(struct sctp_sock *opt, union sctp_addr *addr)
{
        return 1;
}

/* Fill in Supported Address Type information for INIT and INIT-ACK
 * chunks.  Returns number of addresses supported.
 */
static int sctp_inet_supported_addrs(const struct sctp_sock *opt,
                                     __be16 *types)
{
        types[0] = SCTP_PARAM_IPV4_ADDRESS;
        return 1;
}

/* Wrapper routine that calls the ip transmit routine. */
static inline int sctp_v4_xmit(struct sk_buff *skb, struct sctp_transport *t)
{
        struct dst_entry *dst = dst_clone(t->dst);
        struct flowi4 *fl4 = &t->fl.u.ip4;
        struct sock *sk = skb->sk;
        struct inet_sock *inet = inet_sk(sk);
        __u8 dscp = READ_ONCE(inet->tos);
        __be16 df = 0;

        pr_debug("%s: skb:%p, len:%d, src:%pI4, dst:%pI4\n", __func__, skb,
                 skb->len, &fl4->saddr, &fl4->daddr);

        if (t->dscp & SCTP_DSCP_SET_MASK)
                dscp = t->dscp & SCTP_DSCP_VAL_MASK;

        inet->pmtudisc = t->param_flags & SPP_PMTUD_ENABLE ? IP_PMTUDISC_DO
                                                           : IP_PMTUDISC_DONT;
        SCTP_INC_STATS(sock_net(sk), SCTP_MIB_OUTSCTPPACKS);

        if (!t->encap_port || !sctp_sk(sk)->udp_port) {
                skb_dst_set(skb, dst);
                return __ip_queue_xmit(sk, skb, &t->fl, dscp);
        }

        if (skb_is_gso(skb))
                skb_shinfo(skb)->gso_type |= SKB_GSO_UDP_TUNNEL_CSUM;

        if (ip_dont_fragment(sk, dst) && !skb->ignore_df)
                df = htons(IP_DF);

        skb->encapsulation = 1;
        skb_reset_inner_mac_header(skb);
        skb_reset_inner_transport_header(skb);
        skb_set_inner_ipproto(skb, IPPROTO_SCTP);
        udp_tunnel_xmit_skb(dst_rtable(dst), sk, skb, fl4->saddr,
                            fl4->daddr, dscp, ip4_dst_hoplimit(dst), df,
                            sctp_sk(sk)->udp_port, t->encap_port, false, false);
        return 0;
}

static struct sctp_af sctp_af_inet;

static struct sctp_pf sctp_pf_inet = {
        .event_msgname = sctp_inet_event_msgname,
        .skb_msgname   = sctp_inet_skb_msgname,
        .af_supported  = sctp_inet_af_supported,
        .cmp_addr      = sctp_inet_cmp_addr,
        .bind_verify   = sctp_inet_bind_verify,
        .send_verify   = sctp_inet_send_verify,
        .supported_addrs = sctp_inet_supported_addrs,
        .create_accept_sk = sctp_v4_create_accept_sk,
        .addr_to_user  = sctp_v4_addr_to_user,
        .to_sk_saddr   = sctp_v4_to_sk_saddr,
        .to_sk_daddr   = sctp_v4_to_sk_daddr,
        .copy_ip_options = sctp_v4_copy_ip_options,
        .af            = &sctp_af_inet
};

/* Notifier for inetaddr addition/deletion events.  */
static struct notifier_block sctp_inetaddr_notifier = {
        .notifier_call = sctp_inetaddr_event,
};

/* Socket operations.  */
static const struct proto_ops inet_seqpacket_ops = {
        .family                   = PF_INET,
        .owner                   = THIS_MODULE,
        .release           = inet_release,        /* Needs to be wrapped... */
        .bind                   = inet_bind,
        .connect           = sctp_inet_connect,
        .socketpair           = sock_no_socketpair,
        .accept                   = inet_accept,
        .getname           = inet_getname,        /* Semantics are different.  */
        .poll                   = sctp_poll,
        .ioctl                   = inet_ioctl,
        .gettstamp           = sock_gettstamp,
        .listen                   = sctp_inet_listen,
        .shutdown           = inet_shutdown,        /* Looks harmless.  */
        .setsockopt           = sock_common_setsockopt, /* IP_SOL IP_OPTION is a problem */
        .getsockopt           = sock_common_getsockopt,
        .sendmsg           = inet_sendmsg,
        .recvmsg           = inet_recvmsg,
        .mmap                   = sock_no_mmap,
};

/* Registration with AF_INET family.  */
static struct inet_protosw sctp_seqpacket_protosw = {
        .type       = SOCK_SEQPACKET,
        .protocol   = IPPROTO_SCTP,
        .prot       = &sctp_prot,
        .ops        = &inet_seqpacket_ops,
        .flags      = SCTP_PROTOSW_FLAG
};
static struct inet_protosw sctp_stream_protosw = {
        .type       = SOCK_STREAM,
        .protocol   = IPPROTO_SCTP,
        .prot       = &sctp_prot,
        .ops        = &inet_seqpacket_ops,
        .flags      = SCTP_PROTOSW_FLAG
};

static int sctp4_rcv(struct sk_buff *skb)
{
        SCTP_INPUT_CB(skb)->encap_port = 0;
        return sctp_rcv(skb);
}

/* Register with IP layer.  */
static const struct net_protocol sctp_protocol = {
        .handler     = sctp4_rcv,
        .err_handler = sctp_v4_err,
        .no_policy   = 1,
        .icmp_strict_tag_validation = 1,
};

/* IPv4 address related functions.  */
static struct sctp_af sctp_af_inet = {
        .sa_family           = AF_INET,
        .sctp_xmit           = sctp_v4_xmit,
        .setsockopt           = ip_setsockopt,
        .getsockopt           = ip_getsockopt,
        .get_dst           = sctp_v4_get_dst,
        .get_saddr           = sctp_v4_get_saddr,
        .copy_addrlist           = sctp_v4_copy_addrlist,
        .from_skb           = sctp_v4_from_skb,
        .from_sk           = sctp_v4_from_sk,
        .from_addr_param   = sctp_v4_from_addr_param,
        .to_addr_param           = sctp_v4_to_addr_param,
        .cmp_addr           = sctp_v4_cmp_addr,
        .addr_valid           = sctp_v4_addr_valid,
        .inaddr_any           = sctp_v4_inaddr_any,
        .is_any                   = sctp_v4_is_any,
        .available           = sctp_v4_available,
        .scope                   = sctp_v4_scope,
        .skb_iif           = sctp_v4_skb_iif,
        .skb_sdif           = sctp_v4_skb_sdif,
        .is_ce                   = sctp_v4_is_ce,
        .seq_dump_addr           = sctp_v4_seq_dump_addr,
        .ecn_capable           = sctp_v4_ecn_capable,
        .net_header_len           = sizeof(struct iphdr),
        .sockaddr_len           = sizeof(struct sockaddr_in),
        .ip_options_len           = sctp_v4_ip_options_len,
};

struct sctp_pf *sctp_get_pf_specific(sa_family_t family)
{
        switch (family) {
        case PF_INET:
                return sctp_pf_inet_specific;
        case PF_INET6:
                return sctp_pf_inet6_specific;
        default:
                return NULL;
        }
}

/* Register the PF specific function table.  */
int sctp_register_pf(struct sctp_pf *pf, sa_family_t family)
{
        switch (family) {
        case PF_INET:
                if (sctp_pf_inet_specific)
                        return 0;
                sctp_pf_inet_specific = pf;
                break;
        case PF_INET6:
                if (sctp_pf_inet6_specific)
                        return 0;
                sctp_pf_inet6_specific = pf;
                break;
        default:
                return 0;
        }
        return 1;
}

static inline int init_sctp_mibs(struct net *net)
{
        net->sctp.sctp_statistics = alloc_percpu(struct sctp_mib);
        if (!net->sctp.sctp_statistics)
                return -ENOMEM;
        return 0;
}

static inline void cleanup_sctp_mibs(struct net *net)
{
        free_percpu(net->sctp.sctp_statistics);
}

static void sctp_v4_pf_init(void)
{
        /* Initialize the SCTP specific PF functions. */
        sctp_register_pf(&sctp_pf_inet, PF_INET);
        sctp_register_af(&sctp_af_inet);
}

static void sctp_v4_pf_exit(void)
{
        list_del(&sctp_af_inet.list);
}

static int sctp_v4_protosw_init(void)
{
        int rc;

        rc = proto_register(&sctp_prot, 1);
        if (rc)
                return rc;

        /* Register SCTP(UDP and TCP style) with socket layer.  */
        inet_register_protosw(&sctp_seqpacket_protosw);
        inet_register_protosw(&sctp_stream_protosw);

        return 0;
}

static void sctp_v4_protosw_exit(void)
{
        inet_unregister_protosw(&sctp_stream_protosw);
        inet_unregister_protosw(&sctp_seqpacket_protosw);
        proto_unregister(&sctp_prot);
}

static int sctp_v4_add_protocol(void)
{
        /* Register notifier for inet address additions/deletions. */
        register_inetaddr_notifier(&sctp_inetaddr_notifier);

        /* Register SCTP with inet layer.  */
        if (inet_add_protocol(&sctp_protocol, IPPROTO_SCTP) < 0)
                return -EAGAIN;

        return 0;
}

static void sctp_v4_del_protocol(void)
{
        inet_del_protocol(&sctp_protocol, IPPROTO_SCTP);
        unregister_inetaddr_notifier(&sctp_inetaddr_notifier);
}

static int __net_init sctp_defaults_init(struct net *net)
{
        int status;

        /*
         * 14. Suggested SCTP Protocol Parameter Values
         */
        /* The following protocol parameters are RECOMMENDED:  */
        /* RTO.Initial              - 3  seconds */
        net->sctp.rto_initial                        = SCTP_RTO_INITIAL;
        /* RTO.Min                  - 1  second */
        net->sctp.rto_min                         = SCTP_RTO_MIN;
        /* RTO.Max                 -  60 seconds */
        net->sctp.rto_max                         = SCTP_RTO_MAX;
        /* RTO.Alpha                - 1/8 */
        net->sctp.rto_alpha                        = SCTP_RTO_ALPHA;
        /* RTO.Beta                 - 1/4 */
        net->sctp.rto_beta                        = SCTP_RTO_BETA;

        /* Valid.Cookie.Life        - 60  seconds */
        net->sctp.valid_cookie_life                = SCTP_DEFAULT_COOKIE_LIFE;

        /* Whether Cookie Preservative is enabled(1) or not(0) */
        net->sctp.cookie_preserve_enable         = 1;

        /* Default sctp sockets to use md5 as their hmac alg */
#if defined (CONFIG_SCTP_DEFAULT_COOKIE_HMAC_MD5)
        net->sctp.sctp_hmac_alg                        = "md5";
#elif defined (CONFIG_SCTP_DEFAULT_COOKIE_HMAC_SHA1)
        net->sctp.sctp_hmac_alg                        = "sha1";
#else
        net->sctp.sctp_hmac_alg                        = NULL;
#endif

        /* Max.Burst                    - 4 */
        net->sctp.max_burst                        = SCTP_DEFAULT_MAX_BURST;

        /* Disable of Primary Path Switchover by default */
        net->sctp.ps_retrans = SCTP_PS_RETRANS_MAX;

        /* Enable pf state by default */
        net->sctp.pf_enable = 1;

        /* Ignore pf exposure feature by default */
        net->sctp.pf_expose = SCTP_PF_EXPOSE_UNSET;

        /* Association.Max.Retrans  - 10 attempts
         * Path.Max.Retrans         - 5  attempts (per destination address)
         * Max.Init.Retransmits     - 8  attempts
         */
        net->sctp.max_retrans_association        = 10;
        net->sctp.max_retrans_path                = 5;
        net->sctp.max_retrans_init                = 8;

        /* Sendbuffer growth            - do per-socket accounting */
        net->sctp.sndbuf_policy                        = 0;

        /* Rcvbuffer growth            - do per-socket accounting */
        net->sctp.rcvbuf_policy                        = 0;

        /* HB.interval              - 30 seconds */
        net->sctp.hb_interval                        = SCTP_DEFAULT_TIMEOUT_HEARTBEAT;

        /* delayed SACK timeout */
        net->sctp.sack_timeout                        = SCTP_DEFAULT_TIMEOUT_SACK;

        /* Disable ADDIP by default. */
        net->sctp.addip_enable = 0;
        net->sctp.addip_noauth = 0;
        net->sctp.default_auto_asconf = 0;

        /* Enable PR-SCTP by default. */
        net->sctp.prsctp_enable = 1;

        /* Disable RECONF by default. */
        net->sctp.reconf_enable = 0;

        /* Disable AUTH by default. */
        net->sctp.auth_enable = 0;

        /* Enable ECN by default. */
        net->sctp.ecn_enable = 1;

        /* Set UDP tunneling listening port to 0 by default */
        net->sctp.udp_port = 0;

        /* Set remote encap port to 0 by default */
        net->sctp.encap_port = 0;

        /* Set SCOPE policy to enabled */
        net->sctp.scope_policy = SCTP_SCOPE_POLICY_ENABLE;

        /* Set the default rwnd update threshold */
        net->sctp.rwnd_upd_shift = SCTP_DEFAULT_RWND_SHIFT;

        /* Initialize maximum autoclose timeout. */
        net->sctp.max_autoclose                = INT_MAX / HZ;

#ifdef CONFIG_NET_L3_MASTER_DEV
        net->sctp.l3mdev_accept = 1;
#endif

        status = sctp_sysctl_net_register(net);
        if (status)
                goto err_sysctl_register;

        /* Allocate and initialise sctp mibs.  */
        status = init_sctp_mibs(net);
        if (status)
                goto err_init_mibs;

#ifdef CONFIG_PROC_FS
        /* Initialize proc fs directory.  */
        status = sctp_proc_init(net);
        if (status)
                goto err_init_proc;
#endif

        sctp_dbg_objcnt_init(net);

        /* Initialize the local address list. */
        INIT_LIST_HEAD(&net->sctp.local_addr_list);
        spin_lock_init(&net->sctp.local_addr_lock);
        sctp_get_local_addr_list(net);

        /* Initialize the address event list */
        INIT_LIST_HEAD(&net->sctp.addr_waitq);
        INIT_LIST_HEAD(&net->sctp.auto_asconf_splist);
        spin_lock_init(&net->sctp.addr_wq_lock);
        net->sctp.addr_wq_timer.expires = 0;
        timer_setup(&net->sctp.addr_wq_timer, sctp_addr_wq_timeout_handler, 0);

        return 0;

#ifdef CONFIG_PROC_FS
err_init_proc:
        cleanup_sctp_mibs(net);
#endif
err_init_mibs:
        sctp_sysctl_net_unregister(net);
err_sysctl_register:
        return status;
}

static void __net_exit sctp_defaults_exit(struct net *net)
{
        /* Free the local address list */
        sctp_free_addr_wq(net);
        sctp_free_local_addr_list(net);

#ifdef CONFIG_PROC_FS
        remove_proc_subtree("sctp", net->proc_net);
        net->sctp.proc_net_sctp = NULL;
#endif
        cleanup_sctp_mibs(net);
        sctp_sysctl_net_unregister(net);
}

static struct pernet_operations sctp_defaults_ops = {
        .init = sctp_defaults_init,
        .exit = sctp_defaults_exit,
};

static int __net_init sctp_ctrlsock_init(struct net *net)
{
        int status;

        /* Initialize the control inode/socket for handling OOTB packets.  */
        status = sctp_ctl_sock_init(net);
        if (status)
                pr_err("Failed to initialize the SCTP control sock\n");

        return status;
}

static void __net_exit sctp_ctrlsock_exit(struct net *net)
{
        /* Free the control endpoint.  */
        inet_ctl_sock_destroy(net->sctp.ctl_sock);
}

static struct pernet_operations sctp_ctrlsock_ops = {
        .init = sctp_ctrlsock_init,
        .exit = sctp_ctrlsock_exit,
};

/* Initialize the universe into something sensible.  */
static __init int sctp_init(void)
{
        unsigned long nr_pages = totalram_pages();
        unsigned long limit;
        unsigned long goal;
        int max_entry_order;
        int num_entries;
        int max_share;
        int status;
        int order;
        int i;

        sock_skb_cb_check_size(sizeof(struct sctp_ulpevent));

        /* Allocate bind_bucket and chunk caches. */
        status = -ENOBUFS;
        sctp_bucket_cachep = KMEM_CACHE(sctp_bind_bucket, SLAB_HWCACHE_ALIGN);
        if (!sctp_bucket_cachep)
                goto out;

        sctp_chunk_cachep = KMEM_CACHE(sctp_chunk, SLAB_HWCACHE_ALIGN);
        if (!sctp_chunk_cachep)
                goto err_chunk_cachep;

        status = percpu_counter_init(&sctp_sockets_allocated, 0, GFP_KERNEL);
        if (status)
                goto err_percpu_counter_init;

        /* Implementation specific variables. */

        /* Initialize default stream count setup information. */
        sctp_max_instreams                    = SCTP_DEFAULT_INSTREAMS;
        sctp_max_outstreams                   = SCTP_DEFAULT_OUTSTREAMS;

        /* Initialize handle used for association ids. */
        idr_init(&sctp_assocs_id);

        limit = nr_free_buffer_pages() / 8;
        limit = max(limit, 128UL);
        sysctl_sctp_mem[0] = limit / 4 * 3;
        sysctl_sctp_mem[1] = limit;
        sysctl_sctp_mem[2] = sysctl_sctp_mem[0] * 2;

        /* Set per-socket limits to no more than 1/128 the pressure threshold*/
        limit = (sysctl_sctp_mem[1]) << (PAGE_SHIFT - 7);
        max_share = min(4UL*1024*1024, limit);

        sysctl_sctp_rmem[0] = PAGE_SIZE; /* give each asoc 1 page min */
        sysctl_sctp_rmem[1] = 1500 * SKB_TRUESIZE(1);
        sysctl_sctp_rmem[2] = max(sysctl_sctp_rmem[1], max_share);

        sysctl_sctp_wmem[0] = PAGE_SIZE;
        sysctl_sctp_wmem[1] = 16*1024;
        sysctl_sctp_wmem[2] = max(64*1024, max_share);

        /* Size and allocate the association hash table.
         * The methodology is similar to that of the tcp hash tables.
         * Though not identical.  Start by getting a goal size
         */
        if (nr_pages >= (128 * 1024))
                goal = nr_pages >> (22 - PAGE_SHIFT);
        else
                goal = nr_pages >> (24 - PAGE_SHIFT);

        /* Then compute the page order for said goal */
        order = get_order(goal);

        /* Now compute the required page order for the maximum sized table we
         * want to create
         */
        max_entry_order = get_order(MAX_SCTP_PORT_HASH_ENTRIES *
                                    sizeof(struct sctp_bind_hashbucket));

        /* Limit the page order by that maximum hash table size */
        order = min(order, max_entry_order);

        /* Allocate and initialize the endpoint hash table.  */
        sctp_ep_hashsize = 64;
        sctp_ep_hashtable =
                kmalloc_array(64, sizeof(struct sctp_hashbucket), GFP_KERNEL);
        if (!sctp_ep_hashtable) {
                pr_err("Failed endpoint_hash alloc\n");
                status = -ENOMEM;
                goto err_ehash_alloc;
        }
        for (i = 0; i < sctp_ep_hashsize; i++) {
                rwlock_init(&sctp_ep_hashtable[i].lock);
                INIT_HLIST_HEAD(&sctp_ep_hashtable[i].chain);
        }

        /* Allocate and initialize the SCTP port hash table.
         * Note that order is initalized to start at the max sized
         * table we want to support.  If we can't get that many pages
         * reduce the order and try again
         */
        do {
                sctp_port_hashtable = (struct sctp_bind_hashbucket *)
                        __get_free_pages(GFP_KERNEL | __GFP_NOWARN, order);
        } while (!sctp_port_hashtable && --order > 0);

        if (!sctp_port_hashtable) {
                pr_err("Failed bind hash alloc\n");
                status = -ENOMEM;
                goto err_bhash_alloc;
        }

        /* Now compute the number of entries that will fit in the
         * port hash space we allocated
         */
        num_entries = (1UL << order) * PAGE_SIZE /
                      sizeof(struct sctp_bind_hashbucket);

        /* And finish by rounding it down to the nearest power of two.
         * This wastes some memory of course, but it's needed because
         * the hash function operates based on the assumption that
         * the number of entries is a power of two.
         */
        sctp_port_hashsize = rounddown_pow_of_two(num_entries);

        for (i = 0; i < sctp_port_hashsize; i++) {
                spin_lock_init(&sctp_port_hashtable[i].lock);
                INIT_HLIST_HEAD(&sctp_port_hashtable[i].chain);
        }

        status = sctp_transport_hashtable_init();
        if (status)
                goto err_thash_alloc;

        pr_info("Hash tables configured (bind %d/%d)\n", sctp_port_hashsize,
                num_entries);

        sctp_sysctl_register();

        INIT_LIST_HEAD(&sctp_address_families);
        sctp_v4_pf_init();
        sctp_v6_pf_init();
        sctp_sched_ops_init();

        status = register_pernet_subsys(&sctp_defaults_ops);
        if (status)
                goto err_register_defaults;

        status = sctp_v4_protosw_init();
        if (status)
                goto err_protosw_init;

        status = sctp_v6_protosw_init();
        if (status)
                goto err_v6_protosw_init;

        status = register_pernet_subsys(&sctp_ctrlsock_ops);
        if (status)
                goto err_register_ctrlsock;

        status = sctp_v4_add_protocol();
        if (status)
                goto err_add_protocol;

        /* Register SCTP with inet6 layer.  */
        status = sctp_v6_add_protocol();
        if (status)
                goto err_v6_add_protocol;

        if (sctp_offload_init() < 0)
                pr_crit("%s: Cannot add SCTP protocol offload\n", __func__);

out:
        return status;
err_v6_add_protocol:
        sctp_v4_del_protocol();
err_add_protocol:
        unregister_pernet_subsys(&sctp_ctrlsock_ops);
err_register_ctrlsock:
        sctp_v6_protosw_exit();
err_v6_protosw_init:
        sctp_v4_protosw_exit();
err_protosw_init:
        unregister_pernet_subsys(&sctp_defaults_ops);
err_register_defaults:
        sctp_v4_pf_exit();
        sctp_v6_pf_exit();
        sctp_sysctl_unregister();
        free_pages((unsigned long)sctp_port_hashtable,
                   get_order(sctp_port_hashsize *
                             sizeof(struct sctp_bind_hashbucket)));
err_bhash_alloc:
        sctp_transport_hashtable_destroy();
err_thash_alloc:
        kfree(sctp_ep_hashtable);
err_ehash_alloc:
        percpu_counter_destroy(&sctp_sockets_allocated);
err_percpu_counter_init:
        kmem_cache_destroy(sctp_chunk_cachep);
err_chunk_cachep:
        kmem_cache_destroy(sctp_bucket_cachep);
        goto out;
}

/* Exit handler for the SCTP protocol.  */
static __exit void sctp_exit(void)
{
        /* BUG.  This should probably do something useful like clean
         * up all the remaining associations and all that memory.
         */

        /* Unregister with inet6/inet layers. */
        sctp_v6_del_protocol();
        sctp_v4_del_protocol();

        unregister_pernet_subsys(&sctp_ctrlsock_ops);

        /* Free protosw registrations */
        sctp_v6_protosw_exit();
        sctp_v4_protosw_exit();

        unregister_pernet_subsys(&sctp_defaults_ops);

        /* Unregister with socket layer. */
        sctp_v6_pf_exit();
        sctp_v4_pf_exit();

        sctp_sysctl_unregister();

        free_pages((unsigned long)sctp_port_hashtable,
                   get_order(sctp_port_hashsize *
                             sizeof(struct sctp_bind_hashbucket)));
        kfree(sctp_ep_hashtable);
        sctp_transport_hashtable_destroy();

        percpu_counter_destroy(&sctp_sockets_allocated);

        rcu_barrier(); /* Wait for completion of call_rcu()'s */

        kmem_cache_destroy(sctp_chunk_cachep);
        kmem_cache_destroy(sctp_bucket_cachep);
}

module_init(sctp_init);
module_exit(sctp_exit);

/*
 * __stringify doesn't likes enums, so use IPPROTO_SCTP value (132) directly.
 */
MODULE_ALIAS("net-pf-" __stringify(PF_INET) "-proto-132");
MODULE_ALIAS("net-pf-" __stringify(PF_INET6) "-proto-132");
MODULE_AUTHOR("Linux Kernel SCTP developers <linux-sctp@vger.kernel.org>");
MODULE_DESCRIPTION("Support for the SCTP protocol (RFC2960)");
module_param_named(no_checksums, sctp_checksum_disable, bool, 0644);
MODULE_PARM_DESC(no_checksums, "Disable checksums computing and verification");
MODULE_LICENSE("GPL");



































































































































   93 





    4 






































































































































 5619 









   43 




































































































































































































































   83 






















































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
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
/* SPDX-License-Identifier: GPL-2.0 */
#ifndef __LINUX_NODEMASK_H
#define __LINUX_NODEMASK_H

/*
 * Nodemasks provide a bitmap suitable for representing the
 * set of Node's in a system, one bit position per Node number.
 *
 * See detailed comments in the file linux/bitmap.h describing the
 * data type on which these nodemasks are based.
 *
 * For details of nodemask_parse_user(), see bitmap_parse_user() in
 * lib/bitmap.c.  For details of nodelist_parse(), see bitmap_parselist(),
 * also in bitmap.c.  For details of node_remap(), see bitmap_bitremap in
 * lib/bitmap.c.  For details of nodes_remap(), see bitmap_remap in
 * lib/bitmap.c.  For details of nodes_onto(), see bitmap_onto in
 * lib/bitmap.c.  For details of nodes_fold(), see bitmap_fold in
 * lib/bitmap.c.
 *
 * The available nodemask operations are:
 *
 * void node_set(node, mask)                turn on bit 'node' in mask
 * void node_clear(node, mask)                turn off bit 'node' in mask
 * void nodes_setall(mask)                set all bits
 * void nodes_clear(mask)                clear all bits
 * int node_isset(node, mask)                true iff bit 'node' set in mask
 * int node_test_and_set(node, mask)        test and set bit 'node' in mask
 *
 * void nodes_and(dst, src1, src2)        dst = src1 & src2  [intersection]
 * void nodes_or(dst, src1, src2)        dst = src1 | src2  [union]
 * void nodes_xor(dst, src1, src2)        dst = src1 ^ src2
 * void nodes_andnot(dst, src1, src2)        dst = src1 & ~src2
 * void nodes_complement(dst, src)        dst = ~src
 *
 * int nodes_equal(mask1, mask2)        Does mask1 == mask2?
 * int nodes_intersects(mask1, mask2)        Do mask1 and mask2 intersect?
 * int nodes_subset(mask1, mask2)        Is mask1 a subset of mask2?
 * int nodes_empty(mask)                Is mask empty (no bits sets)?
 * int nodes_full(mask)                        Is mask full (all bits sets)?
 * int nodes_weight(mask)                Hamming weight - number of set bits
 *
 * void nodes_shift_right(dst, src, n)        Shift right
 * void nodes_shift_left(dst, src, n)        Shift left
 *
 * unsigned int first_node(mask)        Number lowest set bit, or MAX_NUMNODES
 * unsigend int next_node(node, mask)        Next node past 'node', or MAX_NUMNODES
 * unsigned int next_node_in(node, mask) Next node past 'node', or wrap to first,
 *                                        or MAX_NUMNODES
 * unsigned int first_unset_node(mask)        First node not set in mask, or
 *                                        MAX_NUMNODES
 *
 * nodemask_t nodemask_of_node(node)        Return nodemask with bit 'node' set
 * NODE_MASK_ALL                        Initializer - all bits set
 * NODE_MASK_NONE                        Initializer - no bits set
 * unsigned long *nodes_addr(mask)        Array of unsigned long's in mask
 *
 * int nodemask_parse_user(ubuf, ulen, mask)        Parse ascii string as nodemask
 * int nodelist_parse(buf, map)                Parse ascii string as nodelist
 * int node_remap(oldbit, old, new)        newbit = map(old, new)(oldbit)
 * void nodes_remap(dst, src, old, new)        *dst = map(old, new)(src)
 * void nodes_onto(dst, orig, relmap)        *dst = orig relative to relmap
 * void nodes_fold(dst, orig, sz)        dst bits = orig bits mod sz
 *
 * for_each_node_mask(node, mask)        for-loop node over mask
 *
 * int num_online_nodes()                Number of online Nodes
 * int num_possible_nodes()                Number of all possible Nodes
 *
 * int node_random(mask)                Random node with set bit in mask
 *
 * int node_online(node)                Is some node online?
 * int node_possible(node)                Is some node possible?
 *
 * node_set_online(node)                set bit 'node' in node_online_map
 * node_set_offline(node)                clear bit 'node' in node_online_map
 *
 * for_each_node(node)                        for-loop node over node_possible_map
 * for_each_online_node(node)                for-loop node over node_online_map
 *
 * Subtlety:
 * 1) The 'type-checked' form of node_isset() causes gcc (3.3.2, anyway)
 *    to generate slightly worse code.  So use a simple one-line #define
 *    for node_isset(), instead of wrapping an inline inside a macro, the
 *    way we do the other calls.
 *
 * NODEMASK_SCRATCH
 * When doing above logical AND, OR, XOR, Remap operations the callers tend to
 * need temporary nodemask_t's on the stack. But if NODES_SHIFT is large,
 * nodemask_t's consume too much stack space.  NODEMASK_SCRATCH is a helper
 * for such situations. See below and CPUMASK_ALLOC also.
 */

#include <linux/threads.h>
#include <linux/bitmap.h>
#include <linux/minmax.h>
#include <linux/nodemask_types.h>
#include <linux/numa.h>
#include <linux/random.h>

extern nodemask_t _unused_nodemask_arg_;

/**
 * nodemask_pr_args - printf args to output a nodemask
 * @maskp: nodemask to be printed
 *
 * Can be used to provide arguments for '%*pb[l]' when printing a nodemask.
 */
#define nodemask_pr_args(maskp)        __nodemask_pr_numnodes(maskp), \
                                __nodemask_pr_bits(maskp)
static __always_inline unsigned int __nodemask_pr_numnodes(const nodemask_t *m)
{
        return m ? MAX_NUMNODES : 0;
}
static __always_inline const unsigned long *__nodemask_pr_bits(const nodemask_t *m)
{
        return m ? m->bits : NULL;
}

/*
 * The inline keyword gives the compiler room to decide to inline, or
 * not inline a function as it sees best.  However, as these functions
 * are called in both __init and non-__init functions, if they are not
 * inlined we will end up with a section mismatch error (of the type of
 * freeable items not being freed).  So we must use __always_inline here
 * to fix the problem.  If other functions in the future also end up in
 * this situation they will also need to be annotated as __always_inline
 */
#define node_set(node, dst) __node_set((node), &(dst))
static __always_inline void __node_set(int node, volatile nodemask_t *dstp)
{
        set_bit(node, dstp->bits);
}

#define node_clear(node, dst) __node_clear((node), &(dst))
static __always_inline void __node_clear(int node, volatile nodemask_t *dstp)
{
        clear_bit(node, dstp->bits);
}

#define nodes_setall(dst) __nodes_setall(&(dst), MAX_NUMNODES)
static __always_inline void __nodes_setall(nodemask_t *dstp, unsigned int nbits)
{
        bitmap_fill(dstp->bits, nbits);
}

#define nodes_clear(dst) __nodes_clear(&(dst), MAX_NUMNODES)
static __always_inline void __nodes_clear(nodemask_t *dstp, unsigned int nbits)
{
        bitmap_zero(dstp->bits, nbits);
}

/* No static inline type checking - see Subtlety (1) above. */
#define node_isset(node, nodemask) test_bit((node), (nodemask).bits)

#define node_test_and_set(node, nodemask) \
                        __node_test_and_set((node), &(nodemask))
static __always_inline bool __node_test_and_set(int node, nodemask_t *addr)
{
        return test_and_set_bit(node, addr->bits);
}

#define nodes_and(dst, src1, src2) \
                        __nodes_and(&(dst), &(src1), &(src2), MAX_NUMNODES)
static __always_inline void __nodes_and(nodemask_t *dstp, const nodemask_t *src1p,
                                        const nodemask_t *src2p, unsigned int nbits)
{
        bitmap_and(dstp->bits, src1p->bits, src2p->bits, nbits);
}

#define nodes_or(dst, src1, src2) \
                        __nodes_or(&(dst), &(src1), &(src2), MAX_NUMNODES)
static __always_inline void __nodes_or(nodemask_t *dstp, const nodemask_t *src1p,
                                        const nodemask_t *src2p, unsigned int nbits)
{
        bitmap_or(dstp->bits, src1p->bits, src2p->bits, nbits);
}

#define nodes_xor(dst, src1, src2) \
                        __nodes_xor(&(dst), &(src1), &(src2), MAX_NUMNODES)
static __always_inline void __nodes_xor(nodemask_t *dstp, const nodemask_t *src1p,
                                        const nodemask_t *src2p, unsigned int nbits)
{
        bitmap_xor(dstp->bits, src1p->bits, src2p->bits, nbits);
}

#define nodes_andnot(dst, src1, src2) \
                        __nodes_andnot(&(dst), &(src1), &(src2), MAX_NUMNODES)
static __always_inline void __nodes_andnot(nodemask_t *dstp, const nodemask_t *src1p,
                                        const nodemask_t *src2p, unsigned int nbits)
{
        bitmap_andnot(dstp->bits, src1p->bits, src2p->bits, nbits);
}

#define nodes_complement(dst, src) \
                        __nodes_complement(&(dst), &(src), MAX_NUMNODES)
static __always_inline void __nodes_complement(nodemask_t *dstp,
                                        const nodemask_t *srcp, unsigned int nbits)
{
        bitmap_complement(dstp->bits, srcp->bits, nbits);
}

#define nodes_equal(src1, src2) \
                        __nodes_equal(&(src1), &(src2), MAX_NUMNODES)
static __always_inline bool __nodes_equal(const nodemask_t *src1p,
                                        const nodemask_t *src2p, unsigned int nbits)
{
        return bitmap_equal(src1p->bits, src2p->bits, nbits);
}

#define nodes_intersects(src1, src2) \
                        __nodes_intersects(&(src1), &(src2), MAX_NUMNODES)
static __always_inline bool __nodes_intersects(const nodemask_t *src1p,
                                        const nodemask_t *src2p, unsigned int nbits)
{
        return bitmap_intersects(src1p->bits, src2p->bits, nbits);
}

#define nodes_subset(src1, src2) \
                        __nodes_subset(&(src1), &(src2), MAX_NUMNODES)
static __always_inline bool __nodes_subset(const nodemask_t *src1p,
                                        const nodemask_t *src2p, unsigned int nbits)
{
        return bitmap_subset(src1p->bits, src2p->bits, nbits);
}

#define nodes_empty(src) __nodes_empty(&(src), MAX_NUMNODES)
static __always_inline bool __nodes_empty(const nodemask_t *srcp, unsigned int nbits)
{
        return bitmap_empty(srcp->bits, nbits);
}

#define nodes_full(nodemask) __nodes_full(&(nodemask), MAX_NUMNODES)
static __always_inline bool __nodes_full(const nodemask_t *srcp, unsigned int nbits)
{
        return bitmap_full(srcp->bits, nbits);
}

#define nodes_weight(nodemask) __nodes_weight(&(nodemask), MAX_NUMNODES)
static __always_inline int __nodes_weight(const nodemask_t *srcp, unsigned int nbits)
{
        return bitmap_weight(srcp->bits, nbits);
}

#define nodes_shift_right(dst, src, n) \
                        __nodes_shift_right(&(dst), &(src), (n), MAX_NUMNODES)
static __always_inline void __nodes_shift_right(nodemask_t *dstp,
                                        const nodemask_t *srcp, int n, int nbits)
{
        bitmap_shift_right(dstp->bits, srcp->bits, n, nbits);
}

#define nodes_shift_left(dst, src, n) \
                        __nodes_shift_left(&(dst), &(src), (n), MAX_NUMNODES)
static __always_inline void __nodes_shift_left(nodemask_t *dstp,
                                        const nodemask_t *srcp, int n, int nbits)
{
        bitmap_shift_left(dstp->bits, srcp->bits, n, nbits);
}

/* FIXME: better would be to fix all architectures to never return
          > MAX_NUMNODES, then the silly min_ts could be dropped. */

#define first_node(src) __first_node(&(src))
static __always_inline unsigned int __first_node(const nodemask_t *srcp)
{
        return min_t(unsigned int, MAX_NUMNODES, find_first_bit(srcp->bits, MAX_NUMNODES));
}

#define next_node(n, src) __next_node((n), &(src))
static __always_inline unsigned int __next_node(int n, const nodemask_t *srcp)
{
        return min_t(unsigned int, MAX_NUMNODES, find_next_bit(srcp->bits, MAX_NUMNODES, n+1));
}

/*
 * Find the next present node in src, starting after node n, wrapping around to
 * the first node in src if needed.  Returns MAX_NUMNODES if src is empty.
 */
#define next_node_in(n, src) __next_node_in((n), &(src))
static __always_inline unsigned int __next_node_in(int node, const nodemask_t *srcp)
{
        unsigned int ret = __next_node(node, srcp);

        if (ret == MAX_NUMNODES)
                ret = __first_node(srcp);
        return ret;
}

static __always_inline void init_nodemask_of_node(nodemask_t *mask, int node)
{
        nodes_clear(*mask);
        node_set(node, *mask);
}

#define nodemask_of_node(node)                                                \
({                                                                        \
        typeof(_unused_nodemask_arg_) m;                                \
        if (sizeof(m) == sizeof(unsigned long)) {                        \
                m.bits[0] = 1UL << (node);                                \
        } else {                                                        \
                init_nodemask_of_node(&m, (node));                        \
        }                                                                \
        m;                                                                \
})

#define first_unset_node(mask) __first_unset_node(&(mask))
static __always_inline unsigned int __first_unset_node(const nodemask_t *maskp)
{
        return min_t(unsigned int, MAX_NUMNODES,
                        find_first_zero_bit(maskp->bits, MAX_NUMNODES));
}

#define NODE_MASK_LAST_WORD BITMAP_LAST_WORD_MASK(MAX_NUMNODES)

#if MAX_NUMNODES <= BITS_PER_LONG

#define NODE_MASK_ALL                                                        \
((nodemask_t) { {                                                        \
        [BITS_TO_LONGS(MAX_NUMNODES)-1] = NODE_MASK_LAST_WORD                \
} })

#else

#define NODE_MASK_ALL                                                        \
((nodemask_t) { {                                                        \
        [0 ... BITS_TO_LONGS(MAX_NUMNODES)-2] = ~0UL,                        \
        [BITS_TO_LONGS(MAX_NUMNODES)-1] = NODE_MASK_LAST_WORD                \
} })

#endif

#define NODE_MASK_NONE                                                        \
((nodemask_t) { {                                                        \
        [0 ... BITS_TO_LONGS(MAX_NUMNODES)-1] =  0UL                        \
} })

#define nodes_addr(src) ((src).bits)

#define nodemask_parse_user(ubuf, ulen, dst) \
                __nodemask_parse_user((ubuf), (ulen), &(dst), MAX_NUMNODES)
static __always_inline int __nodemask_parse_user(const char __user *buf, int len,
                                        nodemask_t *dstp, int nbits)
{
        return bitmap_parse_user(buf, len, dstp->bits, nbits);
}

#define nodelist_parse(buf, dst) __nodelist_parse((buf), &(dst), MAX_NUMNODES)
static __always_inline int __nodelist_parse(const char *buf, nodemask_t *dstp, int nbits)
{
        return bitmap_parselist(buf, dstp->bits, nbits);
}

#define node_remap(oldbit, old, new) \
                __node_remap((oldbit), &(old), &(new), MAX_NUMNODES)
static __always_inline int __node_remap(int oldbit,
                const nodemask_t *oldp, const nodemask_t *newp, int nbits)
{
        return bitmap_bitremap(oldbit, oldp->bits, newp->bits, nbits);
}

#define nodes_remap(dst, src, old, new) \
                __nodes_remap(&(dst), &(src), &(old), &(new), MAX_NUMNODES)
static __always_inline void __nodes_remap(nodemask_t *dstp, const nodemask_t *srcp,
                const nodemask_t *oldp, const nodemask_t *newp, int nbits)
{
        bitmap_remap(dstp->bits, srcp->bits, oldp->bits, newp->bits, nbits);
}

#define nodes_onto(dst, orig, relmap) \
                __nodes_onto(&(dst), &(orig), &(relmap), MAX_NUMNODES)
static __always_inline void __nodes_onto(nodemask_t *dstp, const nodemask_t *origp,
                const nodemask_t *relmapp, int nbits)
{
        bitmap_onto(dstp->bits, origp->bits, relmapp->bits, nbits);
}

#define nodes_fold(dst, orig, sz) \
                __nodes_fold(&(dst), &(orig), sz, MAX_NUMNODES)
static __always_inline void __nodes_fold(nodemask_t *dstp, const nodemask_t *origp,
                int sz, int nbits)
{
        bitmap_fold(dstp->bits, origp->bits, sz, nbits);
}

#if MAX_NUMNODES > 1
#define for_each_node_mask(node, mask)                                    \
        for ((node) = first_node(mask);                                    \
             (node) < MAX_NUMNODES;                                    \
             (node) = next_node((node), (mask)))
#else /* MAX_NUMNODES == 1 */
#define for_each_node_mask(node, mask)                                  \
        for ((node) = 0; (node) < 1 && !nodes_empty(mask); (node)++)
#endif /* MAX_NUMNODES */

/*
 * Bitmasks that are kept for all the nodes.
 */
enum node_states {
        N_POSSIBLE,                /* The node could become online at some point */
        N_ONLINE,                /* The node is online */
        N_NORMAL_MEMORY,        /* The node has regular memory */
#ifdef CONFIG_HIGHMEM
        N_HIGH_MEMORY,                /* The node has regular or high memory */
#else
        N_HIGH_MEMORY = N_NORMAL_MEMORY,
#endif
        N_MEMORY,                /* The node has memory(regular, high, movable) */
        N_CPU,                /* The node has one or more cpus */
        N_GENERIC_INITIATOR,        /* The node has one or more Generic Initiators */
        NR_NODE_STATES
};

/*
 * The following particular system nodemasks and operations
 * on them manage all possible and online nodes.
 */

extern nodemask_t node_states[NR_NODE_STATES];

#if MAX_NUMNODES > 1
static __always_inline int node_state(int node, enum node_states state)
{
        return node_isset(node, node_states[state]);
}

static __always_inline void node_set_state(int node, enum node_states state)
{
        __node_set(node, &node_states[state]);
}

static __always_inline void node_clear_state(int node, enum node_states state)
{
        __node_clear(node, &node_states[state]);
}

static __always_inline int num_node_state(enum node_states state)
{
        return nodes_weight(node_states[state]);
}

#define for_each_node_state(__node, __state) \
        for_each_node_mask((__node), node_states[__state])

#define first_online_node        first_node(node_states[N_ONLINE])
#define first_memory_node        first_node(node_states[N_MEMORY])
static __always_inline unsigned int next_online_node(int nid)
{
        return next_node(nid, node_states[N_ONLINE]);
}
static __always_inline unsigned int next_memory_node(int nid)
{
        return next_node(nid, node_states[N_MEMORY]);
}

extern unsigned int nr_node_ids;
extern unsigned int nr_online_nodes;

static __always_inline void node_set_online(int nid)
{
        node_set_state(nid, N_ONLINE);
        nr_online_nodes = num_node_state(N_ONLINE);
}

static __always_inline void node_set_offline(int nid)
{
        node_clear_state(nid, N_ONLINE);
        nr_online_nodes = num_node_state(N_ONLINE);
}

#else

static __always_inline int node_state(int node, enum node_states state)
{
        return node == 0;
}

static __always_inline void node_set_state(int node, enum node_states state)
{
}

static __always_inline void node_clear_state(int node, enum node_states state)
{
}

static __always_inline int num_node_state(enum node_states state)
{
        return 1;
}

#define for_each_node_state(node, __state) \
        for ( (node) = 0; (node) == 0; (node) = 1)

#define first_online_node        0
#define first_memory_node        0
#define next_online_node(nid)        (MAX_NUMNODES)
#define next_memory_node(nid)        (MAX_NUMNODES)
#define nr_node_ids                1U
#define nr_online_nodes                1U

#define node_set_online(node)           node_set_state((node), N_ONLINE)
#define node_set_offline(node)           node_clear_state((node), N_ONLINE)

#endif

static __always_inline int node_random(const nodemask_t *maskp)
{
#if defined(CONFIG_NUMA) && (MAX_NUMNODES > 1)
        int w, bit;

        w = nodes_weight(*maskp);
        switch (w) {
        case 0:
                bit = NUMA_NO_NODE;
                break;
        case 1:
                bit = first_node(*maskp);
                break;
        default:
                bit = find_nth_bit(maskp->bits, MAX_NUMNODES, get_random_u32_below(w));
                break;
        }
        return bit;
#else
        return 0;
#endif
}

#define node_online_map         node_states[N_ONLINE]
#define node_possible_map         node_states[N_POSSIBLE]

#define num_online_nodes()        num_node_state(N_ONLINE)
#define num_possible_nodes()        num_node_state(N_POSSIBLE)
#define node_online(node)        node_state((node), N_ONLINE)
#define node_possible(node)        node_state((node), N_POSSIBLE)

#define for_each_node(node)           for_each_node_state(node, N_POSSIBLE)
#define for_each_online_node(node) for_each_node_state(node, N_ONLINE)

/*
 * For nodemask scratch area.
 * NODEMASK_ALLOC(type, name) allocates an object with a specified type and
 * name.
 */
#if NODES_SHIFT > 8 /* nodemask_t > 32 bytes */
#define NODEMASK_ALLOC(type, name, gfp_flags)        \
                        type *name = kmalloc(sizeof(*name), gfp_flags)
#define NODEMASK_FREE(m)                        kfree(m)
#else
#define NODEMASK_ALLOC(type, name, gfp_flags)        type _##name, *name = &_##name
#define NODEMASK_FREE(m)                        do {} while (0)
#endif

/* Example structure for using NODEMASK_ALLOC, used in mempolicy. */
struct nodemask_scratch {
        nodemask_t        mask1;
        nodemask_t        mask2;
};

#define NODEMASK_SCRATCH(x)                                                \
                        NODEMASK_ALLOC(struct nodemask_scratch, x,        \
                                        GFP_KERNEL | __GFP_NORETRY)
#define NODEMASK_SCRATCH_FREE(x)        NODEMASK_FREE(x)


#endif /* __LINUX_NODEMASK_H */




































  313 


   51 














  314 



  314 
  291 




  314 

  314 














  314 
  313 






  314 







  316 



  316 

  316 





  314 


























  314 

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
// SPDX-License-Identifier: GPL-2.0
/*
 * fs/f2fs/hash.c
 *
 * Copyright (c) 2012 Samsung Electronics Co., Ltd.
 *             http://www.samsung.com/
 *
 * Portions of this code from linux/fs/ext3/hash.c
 *
 * Copyright (C) 2002 by Theodore Ts'o
 */
#include <linux/types.h>
#include <linux/fs.h>
#include <linux/f2fs_fs.h>
#include <linux/pagemap.h>
#include <linux/unicode.h>

#include "f2fs.h"

/*
 * Hashing code copied from ext3
 */
#define DELTA 0x9E3779B9

static void TEA_transform(unsigned int buf[4], unsigned int const in[])
{
        __u32 sum = 0;
        __u32 b0 = buf[0], b1 = buf[1];
        __u32 a = in[0], b = in[1], c = in[2], d = in[3];
        int n = 16;

        do {
                sum += DELTA;
                b0 += ((b1 << 4)+a) ^ (b1+sum) ^ ((b1 >> 5)+b);
                b1 += ((b0 << 4)+c) ^ (b0+sum) ^ ((b0 >> 5)+d);
        } while (--n);

        buf[0] += b0;
        buf[1] += b1;
}

static void str2hashbuf(const unsigned char *msg, size_t len,
                                unsigned int *buf, int num)
{
        unsigned pad, val;
        int i;

        pad = (__u32)len | ((__u32)len << 8);
        pad |= pad << 16;

        val = pad;
        if (len > num * 4)
                len = num * 4;
        for (i = 0; i < len; i++) {
                if ((i % 4) == 0)
                        val = pad;
                val = msg[i] + (val << 8);
                if ((i % 4) == 3) {
                        *buf++ = val;
                        val = pad;
                        num--;
                }
        }
        if (--num >= 0)
                *buf++ = val;
        while (--num >= 0)
                *buf++ = pad;
}

static u32 TEA_hash_name(const u8 *p, size_t len)
{
        __u32 in[8], buf[4];

        /* Initialize the default seed for the hash checksum functions */
        buf[0] = 0x67452301;
        buf[1] = 0xefcdab89;
        buf[2] = 0x98badcfe;
        buf[3] = 0x10325476;

        while (1) {
                str2hashbuf(p, len, in, 4);
                TEA_transform(buf, in);
                p += 16;
                if (len <= 16)
                        break;
                len -= 16;
        }
        return buf[0] & ~F2FS_HASH_COL_BIT;
}

/*
 * Compute @fname->hash.  For all directories, @fname->disk_name must be set.
 * For casefolded directories, @fname->usr_fname must be set, and also
 * @fname->cf_name if the filename is valid Unicode and is not "." or "..".
 */
void f2fs_hash_filename(const struct inode *dir, struct f2fs_filename *fname)
{
        const u8 *name = fname->disk_name.name;
        size_t len = fname->disk_name.len;

        WARN_ON_ONCE(!name);

        if (is_dot_dotdot(name, len)) {
                fname->hash = 0;
                return;
        }

#if IS_ENABLED(CONFIG_UNICODE)
        if (IS_CASEFOLDED(dir)) {
                /*
                 * If the casefolded name is provided, hash it instead of the
                 * on-disk name.  If the casefolded name is *not* provided, that
                 * should only be because the name wasn't valid Unicode or was
                 * "." or "..", so fall back to treating the name as an opaque
                 * byte sequence.  Note that to handle encrypted directories,
                 * the fallback must use usr_fname (plaintext) rather than
                 * disk_name (ciphertext).
                 */
                WARN_ON_ONCE(!fname->usr_fname->name);
                if (fname->cf_name.name) {
                        name = fname->cf_name.name;
                        len = fname->cf_name.len;
                } else {
                        name = fname->usr_fname->name;
                        len = fname->usr_fname->len;
                }
                if (IS_ENCRYPTED(dir)) {
                        struct qstr tmp = QSTR_INIT(name, len);

                        fname->hash =
                                cpu_to_le32(fscrypt_fname_siphash(dir, &tmp));
                        return;
                }
        }
#endif
        fname->hash = cpu_to_le32(TEA_hash_name(name, len));
}










































    2 





































































    6 


  186 








  195 







  194 









  187 


  186 




































  606 





















   74 
  398 
  438 








  601 





  438 
  348 
   24 




  607 








































  507 








  505 































  504 



  294 
    3 
  239 
  504 
























































































































   14 

   14 





   13 

   14 










    2 

    2 




    1 
















    9 





    1 



    4 





    4 






















  181 





    1 

  180 



























    6 








  194 







  489 








   18 





  384 


    8 






  199 








   40 





  481 










    9 






  486 




















  499 

   17 








  499 






















  500 




  190 
  379 

   38 














    7 






  501 










   21 



  121 


















  243 



















  205 
  240 







  205 













  150 





  151 















  197 























  220 






  110 









    4 


  486 
   60 









































  499 










    1 



    3 
  500 




  213 
  490 

















  123 













  103 
   19 
  107 

   10 
    5 


  116 

  117 

  111 
    7 













    2 

















    9 

    2 




















   18 








    1 



    2 




    1 

    1 




   12 


    4 







    1 

   10 



    8 





    8 
    3 




    2 
   14 





















   82 











   65 







    1 




   17 
















    6 











    6 



    1 


    6 







    3 







    2 

    2 











    4 







    1 


    4 
























   23 

   23 










  173 
    3 







  154 
   43 













    2 


















   11 
    8 










  171 












    1 

















   35 


  175 





















   50 
   27 


   23 













  134 
  134 



  134 












  170 



  134 
   31 

   47 





  164 
   50 







   50 


























   55 








   53 



   53 




   44 
    9 

    2 



   53 












    1 





















   22 













    6 












    5 
   14 





















    4 






    1 



    3 

    2 


































   23 





    2 






   21 


   19 


   18 




    1 


    6 
   11 


    2 


    4 


   19 
   19 















    4 



    1 








    2 
    2 
    3 















    5 




    3 
    2 













































































































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
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
1187
1188
1189
1190
1191
1192
1193
1194
1195
1196
1197
1198
1199
1200
1201
1202
1203
1204
1205
1206
1207
1208
1209
1210
1211
1212
1213
1214
1215
1216
1217
1218
1219
1220
1221
1222
1223
1224
1225
1226
1227
1228
1229
1230
1231
1232
1233
1234
1235
1236
1237
1238
1239
1240
1241
1242
1243
1244
1245
1246
1247
1248
1249
1250
1251
1252
1253
1254
1255
1256
1257
1258
1259
1260
1261
1262
1263
1264
1265
1266
1267
1268
1269
1270
1271
1272
1273
1274
1275
1276
1277
1278
1279
1280
1281
1282
1283
1284
1285
1286
1287
1288
1289
1290
1291
1292
1293
1294
1295
1296
1297
1298
1299
1300
1301
1302
1303
1304
1305
1306
1307
1308
1309
1310
1311
1312
1313
1314
1315
1316
1317
1318
1319
1320
1321
1322
1323
1324
1325
1326
1327
1328
1329
1330
1331
1332
1333
1334
1335
1336
1337
1338
1339
1340
1341
1342
1343
1344
1345
1346
1347
1348
1349
1350
1351
1352
1353
1354
1355
1356
1357
1358
1359
1360
1361
1362
1363
1364
1365
1366
1367
1368
1369
1370
1371
1372
1373
1374
1375
1376
1377
1378
1379
1380
1381
1382
1383
1384
1385
1386
1387
1388
1389
1390
1391
1392
1393
1394
1395
1396
1397
1398
1399
1400
1401
1402
1403
1404
1405
1406
1407
1408
1409
1410
1411
1412
1413
1414
1415
1416
1417
1418
1419
1420
1421
1422
1423
1424
1425
1426
1427
1428
1429
1430
1431
1432
1433
1434
1435
1436
1437
1438
1439
1440
1441
1442
1443
1444
1445
1446
1447
1448
1449
1450
1451
1452
1453
1454
1455
1456
1457
1458
1459
1460
1461
1462
1463
1464
1465
1466
1467
1468
1469
1470
1471
1472
1473
1474
1475
1476
1477
1478
1479
1480
1481
1482
1483
1484
1485
1486
1487
1488
1489
1490
1491
1492
1493
1494
1495
1496
1497
1498
1499
1500
1501
1502
1503
1504
1505
1506
1507
1508
1509
1510
1511
1512
1513
1514
1515
1516
1517
1518
1519
1520
1521
1522
1523
1524
1525
1526
1527
1528
1529
1530
1531
1532
1533
1534
1535
1536
1537
1538
1539
1540
1541
1542
1543
1544
1545
1546
1547
1548
1549
1550
1551
1552
1553
1554
1555
1556
1557
1558
1559
1560
1561
1562
1563
1564
1565
1566
1567
1568
1569
1570
1571
1572
1573
1574
1575
1576
1577
1578
1579
1580
1581
1582
1583
1584
1585
1586
1587
1588
1589
1590
1591
1592
1593
1594
1595
1596
1597
1598
1599
1600
1601
1602
1603
1604
1605
1606
1607
1608
1609
1610
1611
1612
1613
1614
1615
1616
1617
1618
1619
1620
1621
1622
1623
1624
1625
1626
1627
1628
1629
1630
1631
1632
1633
1634
1635
1636
1637
1638
1639
1640
1641
1642
1643
1644
1645
1646
1647
1648
1649
1650
1651
1652
1653
1654
1655
1656
1657
1658
1659
1660
1661
1662
1663
1664
1665
1666
1667
1668
1669
1670
1671
1672
1673
1674
1675
1676
1677
1678
1679
1680
1681
1682
1683
1684
1685
1686
1687
1688
1689
1690
1691
1692
1693
1694
1695
1696
1697
1698
1699
1700
1701
1702
1703
1704
1705
1706
1707
1708
1709
1710
1711
1712
1713
1714
1715
1716
1717
1718
1719
1720
1721
1722
1723
1724
1725
1726
1727
1728
1729
1730
1731
1732
1733
1734
1735
1736
1737
1738
1739
1740
1741
1742
1743
1744
1745
1746
1747
1748
1749
1750
1751
1752
1753
1754
1755
1756
1757
1758
1759
1760
1761
1762
1763
1764
1765
1766
1767
1768
1769
1770
1771
1772
1773
1774
1775
1776
1777
1778
1779
1780
1781
1782
1783
1784
1785
1786
1787
1788
1789
1790
1791
1792
1793
1794
1795
1796
1797
// SPDX-License-Identifier: GPL-2.0-or-later
/* Keyring handling
 *
 * Copyright (C) 2004-2005, 2008, 2013 Red Hat, Inc. All Rights Reserved.
 * Written by David Howells (dhowells@redhat.com)
 */

#include <linux/export.h>
#include <linux/init.h>
#include <linux/sched.h>
#include <linux/slab.h>
#include <linux/security.h>
#include <linux/seq_file.h>
#include <linux/err.h>
#include <linux/user_namespace.h>
#include <linux/nsproxy.h>
#include <keys/keyring-type.h>
#include <keys/user-type.h>
#include <linux/assoc_array_priv.h>
#include <linux/uaccess.h>
#include <net/net_namespace.h>
#include "internal.h"

/*
 * When plumbing the depths of the key tree, this sets a hard limit
 * set on how deep we're willing to go.
 */
#define KEYRING_SEARCH_MAX_DEPTH 6

/*
 * We mark pointers we pass to the associative array with bit 1 set if
 * they're keyrings and clear otherwise.
 */
#define KEYRING_PTR_SUBTYPE        0x2UL

static inline bool keyring_ptr_is_keyring(const struct assoc_array_ptr *x)
{
        return (unsigned long)x & KEYRING_PTR_SUBTYPE;
}
static inline struct key *keyring_ptr_to_key(const struct assoc_array_ptr *x)
{
        void *object = assoc_array_ptr_to_leaf(x);
        return (struct key *)((unsigned long)object & ~KEYRING_PTR_SUBTYPE);
}
static inline void *keyring_key_to_ptr(struct key *key)
{
        if (key->type == &key_type_keyring)
                return (void *)((unsigned long)key | KEYRING_PTR_SUBTYPE);
        return key;
}

static DEFINE_RWLOCK(keyring_name_lock);

/*
 * Clean up the bits of user_namespace that belong to us.
 */
void key_free_user_ns(struct user_namespace *ns)
{
        write_lock(&keyring_name_lock);
        list_del_init(&ns->keyring_name_list);
        write_unlock(&keyring_name_lock);

        key_put(ns->user_keyring_register);
#ifdef CONFIG_PERSISTENT_KEYRINGS
        key_put(ns->persistent_keyring_register);
#endif
}

/*
 * The keyring key type definition.  Keyrings are simply keys of this type and
 * can be treated as ordinary keys in addition to having their own special
 * operations.
 */
static int keyring_preparse(struct key_preparsed_payload *prep);
static void keyring_free_preparse(struct key_preparsed_payload *prep);
static int keyring_instantiate(struct key *keyring,
                               struct key_preparsed_payload *prep);
static void keyring_revoke(struct key *keyring);
static void keyring_destroy(struct key *keyring);
static void keyring_describe(const struct key *keyring, struct seq_file *m);
static long keyring_read(const struct key *keyring,
                         char *buffer, size_t buflen);

struct key_type key_type_keyring = {
        .name                = "keyring",
        .def_datalen        = 0,
        .preparse        = keyring_preparse,
        .free_preparse        = keyring_free_preparse,
        .instantiate        = keyring_instantiate,
        .revoke                = keyring_revoke,
        .destroy        = keyring_destroy,
        .describe        = keyring_describe,
        .read                = keyring_read,
};
EXPORT_SYMBOL(key_type_keyring);

/*
 * Semaphore to serialise link/link calls to prevent two link calls in parallel
 * introducing a cycle.
 */
static DEFINE_MUTEX(keyring_serialise_link_lock);

/*
 * Publish the name of a keyring so that it can be found by name (if it has
 * one and it doesn't begin with a dot).
 */
static void keyring_publish_name(struct key *keyring)
{
        struct user_namespace *ns = current_user_ns();

        if (keyring->description &&
            keyring->description[0] &&
            keyring->description[0] != '.') {
                write_lock(&keyring_name_lock);
                list_add_tail(&keyring->name_link, &ns->keyring_name_list);
                write_unlock(&keyring_name_lock);
        }
}

/*
 * Preparse a keyring payload
 */
static int keyring_preparse(struct key_preparsed_payload *prep)
{
        return prep->datalen != 0 ? -EINVAL : 0;
}

/*
 * Free a preparse of a user defined key payload
 */
static void keyring_free_preparse(struct key_preparsed_payload *prep)
{
}

/*
 * Initialise a keyring.
 *
 * Returns 0 on success, -EINVAL if given any data.
 */
static int keyring_instantiate(struct key *keyring,
                               struct key_preparsed_payload *prep)
{
        assoc_array_init(&keyring->keys);
        /* make the keyring available by name if it has one */
        keyring_publish_name(keyring);
        return 0;
}

/*
 * Multiply 64-bits by 32-bits to 96-bits and fold back to 64-bit.  Ideally we'd
 * fold the carry back too, but that requires inline asm.
 */
static u64 mult_64x32_and_fold(u64 x, u32 y)
{
        u64 hi = (u64)(u32)(x >> 32) * y;
        u64 lo = (u64)(u32)(x) * y;
        return lo + ((u64)(u32)hi << 32) + (u32)(hi >> 32);
}

/*
 * Hash a key type and description.
 */
static void hash_key_type_and_desc(struct keyring_index_key *index_key)
{
        const unsigned level_shift = ASSOC_ARRAY_LEVEL_STEP;
        const unsigned long fan_mask = ASSOC_ARRAY_FAN_MASK;
        const char *description = index_key->description;
        unsigned long hash, type;
        u32 piece;
        u64 acc;
        int n, desc_len = index_key->desc_len;

        type = (unsigned long)index_key->type;
        acc = mult_64x32_and_fold(type, desc_len + 13);
        acc = mult_64x32_and_fold(acc, 9207);
        piece = (unsigned long)index_key->domain_tag;
        acc = mult_64x32_and_fold(acc, piece);
        acc = mult_64x32_and_fold(acc, 9207);

        for (;;) {
                n = desc_len;
                if (n <= 0)
                        break;
                if (n > 4)
                        n = 4;
                piece = 0;
                memcpy(&piece, description, n);
                description += n;
                desc_len -= n;
                acc = mult_64x32_and_fold(acc, piece);
                acc = mult_64x32_and_fold(acc, 9207);
        }

        /* Fold the hash down to 32 bits if need be. */
        hash = acc;
        if (ASSOC_ARRAY_KEY_CHUNK_SIZE == 32)
                hash ^= acc >> 32;

        /* Squidge all the keyrings into a separate part of the tree to
         * ordinary keys by making sure the lowest level segment in the hash is
         * zero for keyrings and non-zero otherwise.
         */
        if (index_key->type != &key_type_keyring && (hash & fan_mask) == 0)
                hash |= (hash >> (ASSOC_ARRAY_KEY_CHUNK_SIZE - level_shift)) | 1;
        else if (index_key->type == &key_type_keyring && (hash & fan_mask) != 0)
                hash = (hash + (hash << level_shift)) & ~fan_mask;
        index_key->hash = hash;
}

/*
 * Finalise an index key to include a part of the description actually in the
 * index key, to set the domain tag and to calculate the hash.
 */
void key_set_index_key(struct keyring_index_key *index_key)
{
        static struct key_tag default_domain_tag = { .usage = REFCOUNT_INIT(1), };
        size_t n = min_t(size_t, index_key->desc_len, sizeof(index_key->desc));

        memcpy(index_key->desc, index_key->description, n);

        if (!index_key->domain_tag) {
                if (index_key->type->flags & KEY_TYPE_NET_DOMAIN)
                        index_key->domain_tag = current->nsproxy->net_ns->key_domain;
                else
                        index_key->domain_tag = &default_domain_tag;
        }

        hash_key_type_and_desc(index_key);
}

/**
 * key_put_tag - Release a ref on a tag.
 * @tag: The tag to release.
 *
 * This releases a reference the given tag and returns true if that ref was the
 * last one.
 */
bool key_put_tag(struct key_tag *tag)
{
        if (refcount_dec_and_test(&tag->usage)) {
                kfree_rcu(tag, rcu);
                return true;
        }

        return false;
}

/**
 * key_remove_domain - Kill off a key domain and gc its keys
 * @domain_tag: The domain tag to release.
 *
 * This marks a domain tag as being dead and releases a ref on it.  If that
 * wasn't the last reference, the garbage collector is poked to try and delete
 * all keys that were in the domain.
 */
void key_remove_domain(struct key_tag *domain_tag)
{
        domain_tag->removed = true;
        if (!key_put_tag(domain_tag))
                key_schedule_gc_links();
}

/*
 * Build the next index key chunk.
 *
 * We return it one word-sized chunk at a time.
 */
static unsigned long keyring_get_key_chunk(const void *data, int level)
{
        const struct keyring_index_key *index_key = data;
        unsigned long chunk = 0;
        const u8 *d;
        int desc_len = index_key->desc_len, n = sizeof(chunk);

        level /= ASSOC_ARRAY_KEY_CHUNK_SIZE;
        switch (level) {
        case 0:
                return index_key->hash;
        case 1:
                return index_key->x;
        case 2:
                return (unsigned long)index_key->type;
        case 3:
                return (unsigned long)index_key->domain_tag;
        default:
                level -= 4;
                if (desc_len <= sizeof(index_key->desc))
                        return 0;

                d = index_key->description + sizeof(index_key->desc);
                d += level * sizeof(long);
                desc_len -= sizeof(index_key->desc);
                if (desc_len > n)
                        desc_len = n;
                do {
                        chunk <<= 8;
                        chunk |= *d++;
                } while (--desc_len > 0);
                return chunk;
        }
}

static unsigned long keyring_get_object_key_chunk(const void *object, int level)
{
        const struct key *key = keyring_ptr_to_key(object);
        return keyring_get_key_chunk(&key->index_key, level);
}

static bool keyring_compare_object(const void *object, const void *data)
{
        const struct keyring_index_key *index_key = data;
        const struct key *key = keyring_ptr_to_key(object);

        return key->index_key.type == index_key->type &&
                key->index_key.domain_tag == index_key->domain_tag &&
                key->index_key.desc_len == index_key->desc_len &&
                memcmp(key->index_key.description, index_key->description,
                       index_key->desc_len) == 0;
}

/*
 * Compare the index keys of a pair of objects and determine the bit position
 * at which they differ - if they differ.
 */
static int keyring_diff_objects(const void *object, const void *data)
{
        const struct key *key_a = keyring_ptr_to_key(object);
        const struct keyring_index_key *a = &key_a->index_key;
        const struct keyring_index_key *b = data;
        unsigned long seg_a, seg_b;
        int level, i;

        level = 0;
        seg_a = a->hash;
        seg_b = b->hash;
        if ((seg_a ^ seg_b) != 0)
                goto differ;
        level += ASSOC_ARRAY_KEY_CHUNK_SIZE / 8;

        /* The number of bits contributed by the hash is controlled by a
         * constant in the assoc_array headers.  Everything else thereafter we
         * can deal with as being machine word-size dependent.
         */
        seg_a = a->x;
        seg_b = b->x;
        if ((seg_a ^ seg_b) != 0)
                goto differ;
        level += sizeof(unsigned long);

        /* The next bit may not work on big endian */
        seg_a = (unsigned long)a->type;
        seg_b = (unsigned long)b->type;
        if ((seg_a ^ seg_b) != 0)
                goto differ;
        level += sizeof(unsigned long);

        seg_a = (unsigned long)a->domain_tag;
        seg_b = (unsigned long)b->domain_tag;
        if ((seg_a ^ seg_b) != 0)
                goto differ;
        level += sizeof(unsigned long);

        i = sizeof(a->desc);
        if (a->desc_len <= i)
                goto same;

        for (; i < a->desc_len; i++) {
                seg_a = *(unsigned char *)(a->description + i);
                seg_b = *(unsigned char *)(b->description + i);
                if ((seg_a ^ seg_b) != 0)
                        goto differ_plus_i;
        }

same:
        return -1;

differ_plus_i:
        level += i;
differ:
        i = level * 8 + __ffs(seg_a ^ seg_b);
        return i;
}

/*
 * Free an object after stripping the keyring flag off of the pointer.
 */
static void keyring_free_object(void *object)
{
        key_put(keyring_ptr_to_key(object));
}

/*
 * Operations for keyring management by the index-tree routines.
 */
static const struct assoc_array_ops keyring_assoc_array_ops = {
        .get_key_chunk                = keyring_get_key_chunk,
        .get_object_key_chunk        = keyring_get_object_key_chunk,
        .compare_object                = keyring_compare_object,
        .diff_objects                = keyring_diff_objects,
        .free_object                = keyring_free_object,
};

/*
 * Clean up a keyring when it is destroyed.  Unpublish its name if it had one
 * and dispose of its data.
 *
 * The garbage collector detects the final key_put(), removes the keyring from
 * the serial number tree and then does RCU synchronisation before coming here,
 * so we shouldn't need to worry about code poking around here with the RCU
 * readlock held by this time.
 */
static void keyring_destroy(struct key *keyring)
{
        if (keyring->description) {
                write_lock(&keyring_name_lock);

                if (keyring->name_link.next != NULL &&
                    !list_empty(&keyring->name_link))
                        list_del(&keyring->name_link);

                write_unlock(&keyring_name_lock);
        }

        if (keyring->restrict_link) {
                struct key_restriction *keyres = keyring->restrict_link;

                key_put(keyres->key);
                kfree(keyres);
        }

        assoc_array_destroy(&keyring->keys, &keyring_assoc_array_ops);
}

/*
 * Describe a keyring for /proc.
 */
static void keyring_describe(const struct key *keyring, struct seq_file *m)
{
        if (keyring->description)
                seq_puts(m, keyring->description);
        else
                seq_puts(m, "[anon]");

        if (key_is_positive(keyring)) {
                if (keyring->keys.nr_leaves_on_tree != 0)
                        seq_printf(m, ": %lu", keyring->keys.nr_leaves_on_tree);
                else
                        seq_puts(m, ": empty");
        }
}

struct keyring_read_iterator_context {
        size_t                        buflen;
        size_t                        count;
        key_serial_t                *buffer;
};

static int keyring_read_iterator(const void *object, void *data)
{
        struct keyring_read_iterator_context *ctx = data;
        const struct key *key = keyring_ptr_to_key(object);

        kenter("{%s,%d},,{%zu/%zu}",
               key->type->name, key->serial, ctx->count, ctx->buflen);

        if (ctx->count >= ctx->buflen)
                return 1;

        *ctx->buffer++ = key->serial;
        ctx->count += sizeof(key->serial);
        return 0;
}

/*
 * Read a list of key IDs from the keyring's contents in binary form
 *
 * The keyring's semaphore is read-locked by the caller.  This prevents someone
 * from modifying it under us - which could cause us to read key IDs multiple
 * times.
 */
static long keyring_read(const struct key *keyring,
                         char *buffer, size_t buflen)
{
        struct keyring_read_iterator_context ctx;
        long ret;

        kenter("{%d},,%zu", key_serial(keyring), buflen);

        if (buflen & (sizeof(key_serial_t) - 1))
                return -EINVAL;

        /* Copy as many key IDs as fit into the buffer */
        if (buffer && buflen) {
                ctx.buffer = (key_serial_t *)buffer;
                ctx.buflen = buflen;
                ctx.count = 0;
                ret = assoc_array_iterate(&keyring->keys,
                                          keyring_read_iterator, &ctx);
                if (ret < 0) {
                        kleave(" = %ld [iterate]", ret);
                        return ret;
                }
        }

        /* Return the size of the buffer needed */
        ret = keyring->keys.nr_leaves_on_tree * sizeof(key_serial_t);
        if (ret <= buflen)
                kleave("= %ld [ok]", ret);
        else
                kleave("= %ld [buffer too small]", ret);
        return ret;
}

/*
 * Allocate a keyring and link into the destination keyring.
 */
struct key *keyring_alloc(const char *description, kuid_t uid, kgid_t gid,
                          const struct cred *cred, key_perm_t perm,
                          unsigned long flags,
                          struct key_restriction *restrict_link,
                          struct key *dest)
{
        struct key *keyring;
        int ret;

        keyring = key_alloc(&key_type_keyring, description,
                            uid, gid, cred, perm, flags, restrict_link);
        if (!IS_ERR(keyring)) {
                ret = key_instantiate_and_link(keyring, NULL, 0, dest, NULL);
                if (ret < 0) {
                        key_put(keyring);
                        keyring = ERR_PTR(ret);
                }
        }

        return keyring;
}
EXPORT_SYMBOL(keyring_alloc);

/**
 * restrict_link_reject - Give -EPERM to restrict link
 * @keyring: The keyring being added to.
 * @type: The type of key being added.
 * @payload: The payload of the key intended to be added.
 * @restriction_key: Keys providing additional data for evaluating restriction.
 *
 * Reject the addition of any links to a keyring.  It can be overridden by
 * passing KEY_ALLOC_BYPASS_RESTRICTION to key_instantiate_and_link() when
 * adding a key to a keyring.
 *
 * This is meant to be stored in a key_restriction structure which is passed
 * in the restrict_link parameter to keyring_alloc().
 */
int restrict_link_reject(struct key *keyring,
                         const struct key_type *type,
                         const union key_payload *payload,
                         struct key *restriction_key)
{
        return -EPERM;
}

/*
 * By default, we keys found by getting an exact match on their descriptions.
 */
bool key_default_cmp(const struct key *key,
                     const struct key_match_data *match_data)
{
        return strcmp(key->description, match_data->raw_data) == 0;
}

/*
 * Iteration function to consider each key found.
 */
static int keyring_search_iterator(const void *object, void *iterator_data)
{
        struct keyring_search_context *ctx = iterator_data;
        const struct key *key = keyring_ptr_to_key(object);
        unsigned long kflags = READ_ONCE(key->flags);
        short state = READ_ONCE(key->state);

        kenter("{%d}", key->serial);

        /* ignore keys not of this type */
        if (key->type != ctx->index_key.type) {
                kleave(" = 0 [!type]");
                return 0;
        }

        /* skip invalidated, revoked and expired keys */
        if (ctx->flags & KEYRING_SEARCH_DO_STATE_CHECK) {
                time64_t expiry = READ_ONCE(key->expiry);

                if (kflags & ((1 << KEY_FLAG_INVALIDATED) |
                              (1 << KEY_FLAG_REVOKED))) {
                        ctx->result = ERR_PTR(-EKEYREVOKED);
                        kleave(" = %d [invrev]", ctx->skipped_ret);
                        goto skipped;
                }

                if (expiry && ctx->now >= expiry) {
                        if (!(ctx->flags & KEYRING_SEARCH_SKIP_EXPIRED))
                                ctx->result = ERR_PTR(-EKEYEXPIRED);
                        kleave(" = %d [expire]", ctx->skipped_ret);
                        goto skipped;
                }
        }

        /* keys that don't match */
        if (!ctx->match_data.cmp(key, &ctx->match_data)) {
                kleave(" = 0 [!match]");
                return 0;
        }

        /* key must have search permissions */
        if (!(ctx->flags & KEYRING_SEARCH_NO_CHECK_PERM) &&
            key_task_permission(make_key_ref(key, ctx->possessed),
                                ctx->cred, KEY_NEED_SEARCH) < 0) {
                ctx->result = ERR_PTR(-EACCES);
                kleave(" = %d [!perm]", ctx->skipped_ret);
                goto skipped;
        }

        if (ctx->flags & KEYRING_SEARCH_DO_STATE_CHECK) {
                /* we set a different error code if we pass a negative key */
                if (state < 0) {
                        ctx->result = ERR_PTR(state);
                        kleave(" = %d [neg]", ctx->skipped_ret);
                        goto skipped;
                }
        }

        /* Found */
        ctx->result = make_key_ref(key, ctx->possessed);
        kleave(" = 1 [found]");
        return 1;

skipped:
        return ctx->skipped_ret;
}

/*
 * Search inside a keyring for a key.  We can search by walking to it
 * directly based on its index-key or we can iterate over the entire
 * tree looking for it, based on the match function.
 */
static int search_keyring(struct key *keyring, struct keyring_search_context *ctx)
{
        if (ctx->match_data.lookup_type == KEYRING_SEARCH_LOOKUP_DIRECT) {
                const void *object;

                object = assoc_array_find(&keyring->keys,
                                          &keyring_assoc_array_ops,
                                          &ctx->index_key);
                return object ? ctx->iterator(object, ctx) : 0;
        }
        return assoc_array_iterate(&keyring->keys, ctx->iterator, ctx);
}

/*
 * Search a tree of keyrings that point to other keyrings up to the maximum
 * depth.
 */
static bool search_nested_keyrings(struct key *keyring,
                                   struct keyring_search_context *ctx)
{
        struct {
                struct key *keyring;
                struct assoc_array_node *node;
                int slot;
        } stack[KEYRING_SEARCH_MAX_DEPTH];

        struct assoc_array_shortcut *shortcut;
        struct assoc_array_node *node;
        struct assoc_array_ptr *ptr;
        struct key *key;
        int sp = 0, slot;

        kenter("{%d},{%s,%s}",
               keyring->serial,
               ctx->index_key.type->name,
               ctx->index_key.description);

#define STATE_CHECKS (KEYRING_SEARCH_NO_STATE_CHECK | KEYRING_SEARCH_DO_STATE_CHECK)
        BUG_ON((ctx->flags & STATE_CHECKS) == 0 ||
               (ctx->flags & STATE_CHECKS) == STATE_CHECKS);

        if (ctx->index_key.description)
                key_set_index_key(&ctx->index_key);

        /* Check to see if this top-level keyring is what we are looking for
         * and whether it is valid or not.
         */
        if (ctx->match_data.lookup_type == KEYRING_SEARCH_LOOKUP_ITERATE ||
            keyring_compare_object(keyring, &ctx->index_key)) {
                ctx->skipped_ret = 2;
                switch (ctx->iterator(keyring_key_to_ptr(keyring), ctx)) {
                case 1:
                        goto found;
                case 2:
                        return false;
                default:
                        break;
                }
        }

        ctx->skipped_ret = 0;

        /* Start processing a new keyring */
descend_to_keyring:
        kdebug("descend to %d", keyring->serial);
        if (keyring->flags & ((1 << KEY_FLAG_INVALIDATED) |
                              (1 << KEY_FLAG_REVOKED)))
                goto not_this_keyring;

        /* Search through the keys in this keyring before its searching its
         * subtrees.
         */
        if (search_keyring(keyring, ctx))
                goto found;

        /* Then manually iterate through the keyrings nested in this one.
         *
         * Start from the root node of the index tree.  Because of the way the
         * hash function has been set up, keyrings cluster on the leftmost
         * branch of the root node (root slot 0) or in the root node itself.
         * Non-keyrings avoid the leftmost branch of the root entirely (root
         * slots 1-15).
         */
        if (!(ctx->flags & KEYRING_SEARCH_RECURSE))
                goto not_this_keyring;

        ptr = READ_ONCE(keyring->keys.root);
        if (!ptr)
                goto not_this_keyring;

        if (assoc_array_ptr_is_shortcut(ptr)) {
                /* If the root is a shortcut, either the keyring only contains
                 * keyring pointers (everything clusters behind root slot 0) or
                 * doesn't contain any keyring pointers.
                 */
                shortcut = assoc_array_ptr_to_shortcut(ptr);
                if ((shortcut->index_key[0] & ASSOC_ARRAY_FAN_MASK) != 0)
                        goto not_this_keyring;

                ptr = READ_ONCE(shortcut->next_node);
                node = assoc_array_ptr_to_node(ptr);
                goto begin_node;
        }

        node = assoc_array_ptr_to_node(ptr);
        ptr = node->slots[0];
        if (!assoc_array_ptr_is_meta(ptr))
                goto begin_node;

descend_to_node:
        /* Descend to a more distal node in this keyring's content tree and go
         * through that.
         */
        kdebug("descend");
        if (assoc_array_ptr_is_shortcut(ptr)) {
                shortcut = assoc_array_ptr_to_shortcut(ptr);
                ptr = READ_ONCE(shortcut->next_node);
                BUG_ON(!assoc_array_ptr_is_node(ptr));
        }
        node = assoc_array_ptr_to_node(ptr);

begin_node:
        kdebug("begin_node");
        slot = 0;
ascend_to_node:
        /* Go through the slots in a node */
        for (; slot < ASSOC_ARRAY_FAN_OUT; slot++) {
                ptr = READ_ONCE(node->slots[slot]);

                if (assoc_array_ptr_is_meta(ptr)) {
                        if (node->back_pointer ||
                            assoc_array_ptr_is_shortcut(ptr))
                                goto descend_to_node;
                }

                if (!keyring_ptr_is_keyring(ptr))
                        continue;

                key = keyring_ptr_to_key(ptr);

                if (sp >= KEYRING_SEARCH_MAX_DEPTH) {
                        if (ctx->flags & KEYRING_SEARCH_DETECT_TOO_DEEP) {
                                ctx->result = ERR_PTR(-ELOOP);
                                return false;
                        }
                        goto not_this_keyring;
                }

                /* Search a nested keyring */
                if (!(ctx->flags & KEYRING_SEARCH_NO_CHECK_PERM) &&
                    key_task_permission(make_key_ref(key, ctx->possessed),
                                        ctx->cred, KEY_NEED_SEARCH) < 0)
                        continue;

                /* stack the current position */
                stack[sp].keyring = keyring;
                stack[sp].node = node;
                stack[sp].slot = slot;
                sp++;

                /* begin again with the new keyring */
                keyring = key;
                goto descend_to_keyring;
        }

        /* We've dealt with all the slots in the current node, so now we need
         * to ascend to the parent and continue processing there.
         */
        ptr = READ_ONCE(node->back_pointer);
        slot = node->parent_slot;

        if (ptr && assoc_array_ptr_is_shortcut(ptr)) {
                shortcut = assoc_array_ptr_to_shortcut(ptr);
                ptr = READ_ONCE(shortcut->back_pointer);
                slot = shortcut->parent_slot;
        }
        if (!ptr)
                goto not_this_keyring;
        node = assoc_array_ptr_to_node(ptr);
        slot++;

        /* If we've ascended to the root (zero backpointer), we must have just
         * finished processing the leftmost branch rather than the root slots -
         * so there can't be any more keyrings for us to find.
         */
        if (node->back_pointer) {
                kdebug("ascend %d", slot);
                goto ascend_to_node;
        }

        /* The keyring we're looking at was disqualified or didn't contain a
         * matching key.
         */
not_this_keyring:
        kdebug("not_this_keyring %d", sp);
        if (sp <= 0) {
                kleave(" = false");
                return false;
        }

        /* Resume the processing of a keyring higher up in the tree */
        sp--;
        keyring = stack[sp].keyring;
        node = stack[sp].node;
        slot = stack[sp].slot + 1;
        kdebug("ascend to %d [%d]", keyring->serial, slot);
        goto ascend_to_node;

        /* We found a viable match */
found:
        key = key_ref_to_ptr(ctx->result);
        key_check(key);
        if (!(ctx->flags & KEYRING_SEARCH_NO_UPDATE_TIME)) {
                key->last_used_at = ctx->now;
                keyring->last_used_at = ctx->now;
                while (sp > 0)
                        stack[--sp].keyring->last_used_at = ctx->now;
        }
        kleave(" = true");
        return true;
}

/**
 * keyring_search_rcu - Search a keyring tree for a matching key under RCU
 * @keyring_ref: A pointer to the keyring with possession indicator.
 * @ctx: The keyring search context.
 *
 * Search the supplied keyring tree for a key that matches the criteria given.
 * The root keyring and any linked keyrings must grant Search permission to the
 * caller to be searchable and keys can only be found if they too grant Search
 * to the caller. The possession flag on the root keyring pointer controls use
 * of the possessor bits in permissions checking of the entire tree.  In
 * addition, the LSM gets to forbid keyring searches and key matches.
 *
 * The search is performed as a breadth-then-depth search up to the prescribed
 * limit (KEYRING_SEARCH_MAX_DEPTH).  The caller must hold the RCU read lock to
 * prevent keyrings from being destroyed or rearranged whilst they are being
 * searched.
 *
 * Keys are matched to the type provided and are then filtered by the match
 * function, which is given the description to use in any way it sees fit.  The
 * match function may use any attributes of a key that it wishes to
 * determine the match.  Normally the match function from the key type would be
 * used.
 *
 * RCU can be used to prevent the keyring key lists from disappearing without
 * the need to take lots of locks.
 *
 * Returns a pointer to the found key and increments the key usage count if
 * successful; -EAGAIN if no matching keys were found, or if expired or revoked
 * keys were found; -ENOKEY if only negative keys were found; -ENOTDIR if the
 * specified keyring wasn't a keyring.
 *
 * In the case of a successful return, the possession attribute from
 * @keyring_ref is propagated to the returned key reference.
 */
key_ref_t keyring_search_rcu(key_ref_t keyring_ref,
                             struct keyring_search_context *ctx)
{
        struct key *keyring;
        long err;

        ctx->iterator = keyring_search_iterator;
        ctx->possessed = is_key_possessed(keyring_ref);
        ctx->result = ERR_PTR(-EAGAIN);

        keyring = key_ref_to_ptr(keyring_ref);
        key_check(keyring);

        if (keyring->type != &key_type_keyring)
                return ERR_PTR(-ENOTDIR);

        if (!(ctx->flags & KEYRING_SEARCH_NO_CHECK_PERM)) {
                err = key_task_permission(keyring_ref, ctx->cred, KEY_NEED_SEARCH);
                if (err < 0)
                        return ERR_PTR(err);
        }

        ctx->now = ktime_get_real_seconds();
        if (search_nested_keyrings(keyring, ctx))
                __key_get(key_ref_to_ptr(ctx->result));
        return ctx->result;
}

/**
 * keyring_search - Search the supplied keyring tree for a matching key
 * @keyring: The root of the keyring tree to be searched.
 * @type: The type of keyring we want to find.
 * @description: The name of the keyring we want to find.
 * @recurse: True to search the children of @keyring also
 *
 * As keyring_search_rcu() above, but using the current task's credentials and
 * type's default matching function and preferred search method.
 */
key_ref_t keyring_search(key_ref_t keyring,
                         struct key_type *type,
                         const char *description,
                         bool recurse)
{
        struct keyring_search_context ctx = {
                .index_key.type                = type,
                .index_key.description        = description,
                .index_key.desc_len        = strlen(description),
                .cred                        = current_cred(),
                .match_data.cmp                = key_default_cmp,
                .match_data.raw_data        = description,
                .match_data.lookup_type        = KEYRING_SEARCH_LOOKUP_DIRECT,
                .flags                        = KEYRING_SEARCH_DO_STATE_CHECK,
        };
        key_ref_t key;
        int ret;

        if (recurse)
                ctx.flags |= KEYRING_SEARCH_RECURSE;
        if (type->match_preparse) {
                ret = type->match_preparse(&ctx.match_data);
                if (ret < 0)
                        return ERR_PTR(ret);
        }

        rcu_read_lock();
        key = keyring_search_rcu(keyring, &ctx);
        rcu_read_unlock();

        if (type->match_free)
                type->match_free(&ctx.match_data);
        return key;
}
EXPORT_SYMBOL(keyring_search);

static struct key_restriction *keyring_restriction_alloc(
        key_restrict_link_func_t check)
{
        struct key_restriction *keyres =
                kzalloc(sizeof(struct key_restriction), GFP_KERNEL);

        if (!keyres)
                return ERR_PTR(-ENOMEM);

        keyres->check = check;

        return keyres;
}

/*
 * Semaphore to serialise restriction setup to prevent reference count
 * cycles through restriction key pointers.
 */
static DECLARE_RWSEM(keyring_serialise_restrict_sem);

/*
 * Check for restriction cycles that would prevent keyring garbage collection.
 * keyring_serialise_restrict_sem must be held.
 */
static bool keyring_detect_restriction_cycle(const struct key *dest_keyring,
                                             struct key_restriction *keyres)
{
        while (keyres && keyres->key &&
               keyres->key->type == &key_type_keyring) {
                if (keyres->key == dest_keyring)
                        return true;

                keyres = keyres->key->restrict_link;
        }

        return false;
}

/**
 * keyring_restrict - Look up and apply a restriction to a keyring
 * @keyring_ref: The keyring to be restricted
 * @type: The key type that will provide the restriction checker.
 * @restriction: The restriction options to apply to the keyring
 *
 * Look up a keyring and apply a restriction to it.  The restriction is managed
 * by the specific key type, but can be configured by the options specified in
 * the restriction string.
 */
int keyring_restrict(key_ref_t keyring_ref, const char *type,
                     const char *restriction)
{
        struct key *keyring;
        struct key_type *restrict_type = NULL;
        struct key_restriction *restrict_link;
        int ret = 0;

        keyring = key_ref_to_ptr(keyring_ref);
        key_check(keyring);

        if (keyring->type != &key_type_keyring)
                return -ENOTDIR;

        if (!type) {
                restrict_link = keyring_restriction_alloc(restrict_link_reject);
        } else {
                restrict_type = key_type_lookup(type);

                if (IS_ERR(restrict_type))
                        return PTR_ERR(restrict_type);

                if (!restrict_type->lookup_restriction) {
                        ret = -ENOENT;
                        goto error;
                }

                restrict_link = restrict_type->lookup_restriction(restriction);
        }

        if (IS_ERR(restrict_link)) {
                ret = PTR_ERR(restrict_link);
                goto error;
        }

        down_write(&keyring->sem);
        down_write(&keyring_serialise_restrict_sem);

        if (keyring->restrict_link) {
                ret = -EEXIST;
        } else if (keyring_detect_restriction_cycle(keyring, restrict_link)) {
                ret = -EDEADLK;
        } else {
                keyring->restrict_link = restrict_link;
                notify_key(keyring, NOTIFY_KEY_SETATTR, 0);
        }

        up_write(&keyring_serialise_restrict_sem);
        up_write(&keyring->sem);

        if (ret < 0) {
                key_put(restrict_link->key);
                kfree(restrict_link);
        }

error:
        if (restrict_type)
                key_type_put(restrict_type);

        return ret;
}
EXPORT_SYMBOL(keyring_restrict);

/*
 * Search the given keyring for a key that might be updated.
 *
 * The caller must guarantee that the keyring is a keyring and that the
 * permission is granted to modify the keyring as no check is made here.  The
 * caller must also hold a lock on the keyring semaphore.
 *
 * Returns a pointer to the found key with usage count incremented if
 * successful and returns NULL if not found.  Revoked and invalidated keys are
 * skipped over.
 *
 * If successful, the possession indicator is propagated from the keyring ref
 * to the returned key reference.
 */
key_ref_t find_key_to_update(key_ref_t keyring_ref,
                             const struct keyring_index_key *index_key)
{
        struct key *keyring, *key;
        const void *object;

        keyring = key_ref_to_ptr(keyring_ref);

        kenter("{%d},{%s,%s}",
               keyring->serial, index_key->type->name, index_key->description);

        object = assoc_array_find(&keyring->keys, &keyring_assoc_array_ops,
                                  index_key);

        if (object)
                goto found;

        kleave(" = NULL");
        return NULL;

found:
        key = keyring_ptr_to_key(object);
        if (key->flags & ((1 << KEY_FLAG_INVALIDATED) |
                          (1 << KEY_FLAG_REVOKED))) {
                kleave(" = NULL [x]");
                return NULL;
        }
        __key_get(key);
        kleave(" = {%d}", key->serial);
        return make_key_ref(key, is_key_possessed(keyring_ref));
}

/*
 * Find a keyring with the specified name.
 *
 * Only keyrings that have nonzero refcount, are not revoked, and are owned by a
 * user in the current user namespace are considered.  If @uid_keyring is %true,
 * the keyring additionally must have been allocated as a user or user session
 * keyring; otherwise, it must grant Search permission directly to the caller.
 *
 * Returns a pointer to the keyring with the keyring's refcount having being
 * incremented on success.  -ENOKEY is returned if a key could not be found.
 */
struct key *find_keyring_by_name(const char *name, bool uid_keyring)
{
        struct user_namespace *ns = current_user_ns();
        struct key *keyring;

        if (!name)
                return ERR_PTR(-EINVAL);

        read_lock(&keyring_name_lock);

        /* Search this hash bucket for a keyring with a matching name that
         * grants Search permission and that hasn't been revoked
         */
        list_for_each_entry(keyring, &ns->keyring_name_list, name_link) {
                if (!kuid_has_mapping(ns, keyring->user->uid))
                        continue;

                if (test_bit(KEY_FLAG_REVOKED, &keyring->flags))
                        continue;

                if (strcmp(keyring->description, name) != 0)
                        continue;

                if (uid_keyring) {
                        if (!test_bit(KEY_FLAG_UID_KEYRING,
                                      &keyring->flags))
                                continue;
                } else {
                        if (key_permission(make_key_ref(keyring, 0),
                                           KEY_NEED_SEARCH) < 0)
                                continue;
                }

                /* we've got a match but we might end up racing with
                 * key_cleanup() if the keyring is currently 'dead'
                 * (ie. it has a zero usage count) */
                if (!refcount_inc_not_zero(&keyring->usage))
                        continue;
                keyring->last_used_at = ktime_get_real_seconds();
                goto out;
        }

        keyring = ERR_PTR(-ENOKEY);
out:
        read_unlock(&keyring_name_lock);
        return keyring;
}

static int keyring_detect_cycle_iterator(const void *object,
                                         void *iterator_data)
{
        struct keyring_search_context *ctx = iterator_data;
        const struct key *key = keyring_ptr_to_key(object);

        kenter("{%d}", key->serial);

        /* We might get a keyring with matching index-key that is nonetheless a
         * different keyring. */
        if (key != ctx->match_data.raw_data)
                return 0;

        ctx->result = ERR_PTR(-EDEADLK);
        return 1;
}

/*
 * See if a cycle will be created by inserting acyclic tree B in acyclic
 * tree A at the topmost level (ie: as a direct child of A).
 *
 * Since we are adding B to A at the top level, checking for cycles should just
 * be a matter of seeing if node A is somewhere in tree B.
 */
static int keyring_detect_cycle(struct key *A, struct key *B)
{
        struct keyring_search_context ctx = {
                .index_key                = A->index_key,
                .match_data.raw_data        = A,
                .match_data.lookup_type = KEYRING_SEARCH_LOOKUP_DIRECT,
                .iterator                = keyring_detect_cycle_iterator,
                .flags                        = (KEYRING_SEARCH_NO_STATE_CHECK |
                                           KEYRING_SEARCH_NO_UPDATE_TIME |
                                           KEYRING_SEARCH_NO_CHECK_PERM |
                                           KEYRING_SEARCH_DETECT_TOO_DEEP |
                                           KEYRING_SEARCH_RECURSE),
        };

        rcu_read_lock();
        search_nested_keyrings(B, &ctx);
        rcu_read_unlock();
        return PTR_ERR(ctx.result) == -EAGAIN ? 0 : PTR_ERR(ctx.result);
}

/*
 * Lock keyring for link.
 */
int __key_link_lock(struct key *keyring,
                    const struct keyring_index_key *index_key)
        __acquires(&keyring->sem)
        __acquires(&keyring_serialise_link_lock)
{
        if (keyring->type != &key_type_keyring)
                return -ENOTDIR;

        down_write(&keyring->sem);

        /* Serialise link/link calls to prevent parallel calls causing a cycle
         * when linking two keyring in opposite orders.
         */
        if (index_key->type == &key_type_keyring)
                mutex_lock(&keyring_serialise_link_lock);

        return 0;
}

/*
 * Lock keyrings for move (link/unlink combination).
 */
int __key_move_lock(struct key *l_keyring, struct key *u_keyring,
                    const struct keyring_index_key *index_key)
        __acquires(&l_keyring->sem)
        __acquires(&u_keyring->sem)
        __acquires(&keyring_serialise_link_lock)
{
        if (l_keyring->type != &key_type_keyring ||
            u_keyring->type != &key_type_keyring)
                return -ENOTDIR;

        /* We have to be very careful here to take the keyring locks in the
         * right order, lest we open ourselves to deadlocking against another
         * move operation.
         */
        if (l_keyring < u_keyring) {
                down_write(&l_keyring->sem);
                down_write_nested(&u_keyring->sem, 1);
        } else {
                down_write(&u_keyring->sem);
                down_write_nested(&l_keyring->sem, 1);
        }

        /* Serialise link/link calls to prevent parallel calls causing a cycle
         * when linking two keyring in opposite orders.
         */
        if (index_key->type == &key_type_keyring)
                mutex_lock(&keyring_serialise_link_lock);

        return 0;
}

/*
 * Preallocate memory so that a key can be linked into to a keyring.
 */
int __key_link_begin(struct key *keyring,
                     const struct keyring_index_key *index_key,
                     struct assoc_array_edit **_edit)
{
        struct assoc_array_edit *edit;
        int ret;

        kenter("%d,%s,%s,",
               keyring->serial, index_key->type->name, index_key->description);

        BUG_ON(index_key->desc_len == 0);
        BUG_ON(*_edit != NULL);

        *_edit = NULL;

        ret = -EKEYREVOKED;
        if (test_bit(KEY_FLAG_REVOKED, &keyring->flags))
                goto error;

        /* Create an edit script that will insert/replace the key in the
         * keyring tree.
         */
        edit = assoc_array_insert(&keyring->keys,
                                  &keyring_assoc_array_ops,
                                  index_key,
                                  NULL);
        if (IS_ERR(edit)) {
                ret = PTR_ERR(edit);
                goto error;
        }

        /* If we're not replacing a link in-place then we're going to need some
         * extra quota.
         */
        if (!edit->dead_leaf) {
                ret = key_payload_reserve(keyring,
                                          keyring->datalen + KEYQUOTA_LINK_BYTES);
                if (ret < 0)
                        goto error_cancel;
        }

        *_edit = edit;
        kleave(" = 0");
        return 0;

error_cancel:
        assoc_array_cancel_edit(edit);
error:
        kleave(" = %d", ret);
        return ret;
}

/*
 * Check already instantiated keys aren't going to be a problem.
 *
 * The caller must have called __key_link_begin(). Don't need to call this for
 * keys that were created since __key_link_begin() was called.
 */
int __key_link_check_live_key(struct key *keyring, struct key *key)
{
        if (key->type == &key_type_keyring)
                /* check that we aren't going to create a cycle by linking one
                 * keyring to another */
                return keyring_detect_cycle(keyring, key);
        return 0;
}

/*
 * Link a key into to a keyring.
 *
 * Must be called with __key_link_begin() having being called.  Discards any
 * already extant link to matching key if there is one, so that each keyring
 * holds at most one link to any given key of a particular type+description
 * combination.
 */
void __key_link(struct key *keyring, struct key *key,
                struct assoc_array_edit **_edit)
{
        __key_get(key);
        assoc_array_insert_set_object(*_edit, keyring_key_to_ptr(key));
        assoc_array_apply_edit(*_edit);
        *_edit = NULL;
        notify_key(keyring, NOTIFY_KEY_LINKED, key_serial(key));
}

/*
 * Finish linking a key into to a keyring.
 *
 * Must be called with __key_link_begin() having being called.
 */
void __key_link_end(struct key *keyring,
                    const struct keyring_index_key *index_key,
                    struct assoc_array_edit *edit)
        __releases(&keyring->sem)
        __releases(&keyring_serialise_link_lock)
{
        BUG_ON(index_key->type == NULL);
        kenter("%d,%s,", keyring->serial, index_key->type->name);

        if (edit) {
                if (!edit->dead_leaf) {
                        key_payload_reserve(keyring,
                                keyring->datalen - KEYQUOTA_LINK_BYTES);
                }
                assoc_array_cancel_edit(edit);
        }
        up_write(&keyring->sem);

        if (index_key->type == &key_type_keyring)
                mutex_unlock(&keyring_serialise_link_lock);
}

/*
 * Check addition of keys to restricted keyrings.
 */
static int __key_link_check_restriction(struct key *keyring, struct key *key)
{
        if (!keyring->restrict_link || !keyring->restrict_link->check)
                return 0;
        return keyring->restrict_link->check(keyring, key->type, &key->payload,
                                             keyring->restrict_link->key);
}

/**
 * key_link - Link a key to a keyring
 * @keyring: The keyring to make the link in.
 * @key: The key to link to.
 *
 * Make a link in a keyring to a key, such that the keyring holds a reference
 * on that key and the key can potentially be found by searching that keyring.
 *
 * This function will write-lock the keyring's semaphore and will consume some
 * of the user's key data quota to hold the link.
 *
 * Returns 0 if successful, -ENOTDIR if the keyring isn't a keyring,
 * -EKEYREVOKED if the keyring has been revoked, -ENFILE if the keyring is
 * full, -EDQUOT if there is insufficient key data quota remaining to add
 * another link or -ENOMEM if there's insufficient memory.
 *
 * It is assumed that the caller has checked that it is permitted for a link to
 * be made (the keyring should have Write permission and the key Link
 * permission).
 */
int key_link(struct key *keyring, struct key *key)
{
        struct assoc_array_edit *edit = NULL;
        int ret;

        kenter("{%d,%d}", keyring->serial, refcount_read(&keyring->usage));

        key_check(keyring);
        key_check(key);

        ret = __key_link_lock(keyring, &key->index_key);
        if (ret < 0)
                goto error;

        ret = __key_link_begin(keyring, &key->index_key, &edit);
        if (ret < 0)
                goto error_end;

        kdebug("begun {%d,%d}", keyring->serial, refcount_read(&keyring->usage));
        ret = __key_link_check_restriction(keyring, key);
        if (ret == 0)
                ret = __key_link_check_live_key(keyring, key);
        if (ret == 0)
                __key_link(keyring, key, &edit);

error_end:
        __key_link_end(keyring, &key->index_key, edit);
error:
        kleave(" = %d {%d,%d}", ret, keyring->serial, refcount_read(&keyring->usage));
        return ret;
}
EXPORT_SYMBOL(key_link);

/*
 * Lock a keyring for unlink.
 */
static int __key_unlink_lock(struct key *keyring)
        __acquires(&keyring->sem)
{
        if (keyring->type != &key_type_keyring)
                return -ENOTDIR;

        down_write(&keyring->sem);
        return 0;
}

/*
 * Begin the process of unlinking a key from a keyring.
 */
static int __key_unlink_begin(struct key *keyring, struct key *key,
                              struct assoc_array_edit **_edit)
{
        struct assoc_array_edit *edit;

        BUG_ON(*_edit != NULL);

        edit = assoc_array_delete(&keyring->keys, &keyring_assoc_array_ops,
                                  &key->index_key);
        if (IS_ERR(edit))
                return PTR_ERR(edit);

        if (!edit)
                return -ENOENT;

        *_edit = edit;
        return 0;
}

/*
 * Apply an unlink change.
 */
static void __key_unlink(struct key *keyring, struct key *key,
                         struct assoc_array_edit **_edit)
{
        assoc_array_apply_edit(*_edit);
        notify_key(keyring, NOTIFY_KEY_UNLINKED, key_serial(key));
        *_edit = NULL;
        key_payload_reserve(keyring, keyring->datalen - KEYQUOTA_LINK_BYTES);
}

/*
 * Finish unlinking a key from to a keyring.
 */
static void __key_unlink_end(struct key *keyring,
                             struct key *key,
                             struct assoc_array_edit *edit)
        __releases(&keyring->sem)
{
        if (edit)
                assoc_array_cancel_edit(edit);
        up_write(&keyring->sem);
}

/**
 * key_unlink - Unlink the first link to a key from a keyring.
 * @keyring: The keyring to remove the link from.
 * @key: The key the link is to.
 *
 * Remove a link from a keyring to a key.
 *
 * This function will write-lock the keyring's semaphore.
 *
 * Returns 0 if successful, -ENOTDIR if the keyring isn't a keyring, -ENOENT if
 * the key isn't linked to by the keyring or -ENOMEM if there's insufficient
 * memory.
 *
 * It is assumed that the caller has checked that it is permitted for a link to
 * be removed (the keyring should have Write permission; no permissions are
 * required on the key).
 */
int key_unlink(struct key *keyring, struct key *key)
{
        struct assoc_array_edit *edit = NULL;
        int ret;

        key_check(keyring);
        key_check(key);

        ret = __key_unlink_lock(keyring);
        if (ret < 0)
                return ret;

        ret = __key_unlink_begin(keyring, key, &edit);
        if (ret == 0)
                __key_unlink(keyring, key, &edit);
        __key_unlink_end(keyring, key, edit);
        return ret;
}
EXPORT_SYMBOL(key_unlink);

/**
 * key_move - Move a key from one keyring to another
 * @key: The key to move
 * @from_keyring: The keyring to remove the link from.
 * @to_keyring: The keyring to make the link in.
 * @flags: Qualifying flags, such as KEYCTL_MOVE_EXCL.
 *
 * Make a link in @to_keyring to a key, such that the keyring holds a reference
 * on that key and the key can potentially be found by searching that keyring
 * whilst simultaneously removing a link to the key from @from_keyring.
 *
 * This function will write-lock both keyring's semaphores and will consume
 * some of the user's key data quota to hold the link on @to_keyring.
 *
 * Returns 0 if successful, -ENOTDIR if either keyring isn't a keyring,
 * -EKEYREVOKED if either keyring has been revoked, -ENFILE if the second
 * keyring is full, -EDQUOT if there is insufficient key data quota remaining
 * to add another link or -ENOMEM if there's insufficient memory.  If
 * KEYCTL_MOVE_EXCL is set, then -EEXIST will be returned if there's already a
 * matching key in @to_keyring.
 *
 * It is assumed that the caller has checked that it is permitted for a link to
 * be made (the keyring should have Write permission and the key Link
 * permission).
 */
int key_move(struct key *key,
             struct key *from_keyring,
             struct key *to_keyring,
             unsigned int flags)
{
        struct assoc_array_edit *from_edit = NULL, *to_edit = NULL;
        int ret;

        kenter("%d,%d,%d", key->serial, from_keyring->serial, to_keyring->serial);

        if (from_keyring == to_keyring)
                return 0;

        key_check(key);
        key_check(from_keyring);
        key_check(to_keyring);

        ret = __key_move_lock(from_keyring, to_keyring, &key->index_key);
        if (ret < 0)
                goto out;
        ret = __key_unlink_begin(from_keyring, key, &from_edit);
        if (ret < 0)
                goto error;
        ret = __key_link_begin(to_keyring, &key->index_key, &to_edit);
        if (ret < 0)
                goto error;

        ret = -EEXIST;
        if (to_edit->dead_leaf && (flags & KEYCTL_MOVE_EXCL))
                goto error;

        ret = __key_link_check_restriction(to_keyring, key);
        if (ret < 0)
                goto error;
        ret = __key_link_check_live_key(to_keyring, key);
        if (ret < 0)
                goto error;

        __key_unlink(from_keyring, key, &from_edit);
        __key_link(to_keyring, key, &to_edit);
error:
        __key_link_end(to_keyring, &key->index_key, to_edit);
        __key_unlink_end(from_keyring, key, from_edit);
out:
        kleave(" = %d", ret);
        return ret;
}
EXPORT_SYMBOL(key_move);

/**
 * keyring_clear - Clear a keyring
 * @keyring: The keyring to clear.
 *
 * Clear the contents of the specified keyring.
 *
 * Returns 0 if successful or -ENOTDIR if the keyring isn't a keyring.
 */
int keyring_clear(struct key *keyring)
{
        struct assoc_array_edit *edit;
        int ret;

        if (keyring->type != &key_type_keyring)
                return -ENOTDIR;

        down_write(&keyring->sem);

        edit = assoc_array_clear(&keyring->keys, &keyring_assoc_array_ops);
        if (IS_ERR(edit)) {
                ret = PTR_ERR(edit);
        } else {
                if (edit)
                        assoc_array_apply_edit(edit);
                notify_key(keyring, NOTIFY_KEY_CLEARED, 0);
                key_payload_reserve(keyring, 0);
                ret = 0;
        }

        up_write(&keyring->sem);
        return ret;
}
EXPORT_SYMBOL(keyring_clear);

/*
 * Dispose of the links from a revoked keyring.
 *
 * This is called with the key sem write-locked.
 */
static void keyring_revoke(struct key *keyring)
{
        struct assoc_array_edit *edit;

        edit = assoc_array_clear(&keyring->keys, &keyring_assoc_array_ops);
        if (!IS_ERR(edit)) {
                if (edit)
                        assoc_array_apply_edit(edit);
                key_payload_reserve(keyring, 0);
        }
}

static bool keyring_gc_select_iterator(void *object, void *iterator_data)
{
        struct key *key = keyring_ptr_to_key(object);
        time64_t *limit = iterator_data;

        if (key_is_dead(key, *limit))
                return false;
        key_get(key);
        return true;
}

static int keyring_gc_check_iterator(const void *object, void *iterator_data)
{
        const struct key *key = keyring_ptr_to_key(object);
        time64_t *limit = iterator_data;

        key_check(key);
        return key_is_dead(key, *limit);
}

/*
 * Garbage collect pointers from a keyring.
 *
 * Not called with any locks held.  The keyring's key struct will not be
 * deallocated under us as only our caller may deallocate it.
 */
void keyring_gc(struct key *keyring, time64_t limit)
{
        int result;

        kenter("%x{%s}", keyring->serial, keyring->description ?: "");

        if (keyring->flags & ((1 << KEY_FLAG_INVALIDATED) |
                              (1 << KEY_FLAG_REVOKED)))
                goto dont_gc;

        /* scan the keyring looking for dead keys */
        rcu_read_lock();
        result = assoc_array_iterate(&keyring->keys,
                                     keyring_gc_check_iterator, &limit);
        rcu_read_unlock();
        if (result == true)
                goto do_gc;

dont_gc:
        kleave(" [no gc]");
        return;

do_gc:
        down_write(&keyring->sem);
        assoc_array_gc(&keyring->keys, &keyring_assoc_array_ops,
                       keyring_gc_select_iterator, &limit);
        up_write(&keyring->sem);
        kleave(" [gc]");
}

/*
 * Garbage collect restriction pointers from a keyring.
 *
 * Keyring restrictions are associated with a key type, and must be cleaned
 * up if the key type is unregistered. The restriction is altered to always
 * reject additional keys so a keyring cannot be opened up by unregistering
 * a key type.
 *
 * Not called with any keyring locks held. The keyring's key struct will not
 * be deallocated under us as only our caller may deallocate it.
 *
 * The caller is required to hold key_types_sem and dead_type->sem. This is
 * fulfilled by key_gc_keytype() holding the locks on behalf of
 * key_garbage_collector(), which it invokes on a workqueue.
 */
void keyring_restriction_gc(struct key *keyring, struct key_type *dead_type)
{
        struct key_restriction *keyres;

        kenter("%x{%s}", keyring->serial, keyring->description ?: "");

        /*
         * keyring->restrict_link is only assigned at key allocation time
         * or with the key type locked, so the only values that could be
         * concurrently assigned to keyring->restrict_link are for key
         * types other than dead_type. Given this, it's ok to check
         * the key type before acquiring keyring->sem.
         */
        if (!dead_type || !keyring->restrict_link ||
            keyring->restrict_link->keytype != dead_type) {
                kleave(" [no restriction gc]");
                return;
        }

        /* Lock the keyring to ensure that a link is not in progress */
        down_write(&keyring->sem);

        keyres = keyring->restrict_link;

        keyres->check = restrict_link_reject;

        key_put(keyres->key);
        keyres->key = NULL;
        keyres->keytype = NULL;

        up_write(&keyring->sem);

        kleave(" [restriction gc]");
}

























































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
/* SPDX-License-Identifier: GPL-2.0 */
#ifndef _BCACHEFS_LRU_H
#define _BCACHEFS_LRU_H

static inline u64 lru_pos_id(struct bpos pos)
{
        return pos.inode >> LRU_TIME_BITS;
}

static inline u64 lru_pos_time(struct bpos pos)
{
        return pos.inode & ~(~0ULL << LRU_TIME_BITS);
}

static inline struct bpos lru_pos(u16 lru_id, u64 dev_bucket, u64 time)
{
        struct bpos pos = POS(((u64) lru_id << LRU_TIME_BITS)|time, dev_bucket);

        EBUG_ON(time > LRU_TIME_MAX);
        EBUG_ON(lru_pos_id(pos) != lru_id);
        EBUG_ON(lru_pos_time(pos) != time);
        EBUG_ON(pos.offset != dev_bucket);

        return pos;
}

static inline enum bch_lru_type lru_type(struct bkey_s_c l)
{
        u16 lru_id = l.k->p.inode >> 48;

        if (lru_id == BCH_LRU_FRAGMENTATION_START)
                return BCH_LRU_fragmentation;
        return BCH_LRU_read;
}

int bch2_lru_validate(struct bch_fs *, struct bkey_s_c, enum bch_validate_flags);
void bch2_lru_to_text(struct printbuf *, struct bch_fs *, struct bkey_s_c);

void bch2_lru_pos_to_text(struct printbuf *, struct bpos);

#define bch2_bkey_ops_lru ((struct bkey_ops) {        \
        .key_validate        = bch2_lru_validate,        \
        .val_to_text        = bch2_lru_to_text,        \
        .min_val_size        = 8,                        \
})

int bch2_lru_del(struct btree_trans *, u16, u64, u64);
int bch2_lru_set(struct btree_trans *, u16, u64, u64);
int bch2_lru_change(struct btree_trans *, u16, u64, u64, u64);

struct bkey_buf;
int bch2_lru_check_set(struct btree_trans *, u16, u64, struct bkey_s_c, struct bkey_buf *);

int bch2_check_lrus(struct bch_fs *);

#endif /* _BCACHEFS_LRU_H */






















































































   38 



















































  133 














































































































































    5 







    1 
    4 

























    5 



























    5 



















    5 





    5 





    1 















    5 
    5 


    5 












    5 









































































































   18 

















   17 
























   18 
   18 















   18 










   18 

    5 




   16 






   18 
   18 























    4 





















    4 














































































    4 







    3 




    4 



    4 










    4 
    4 





    4 



    4 

    4 







    4 




    4 





















    6 










    1 




    5 









    4 



    4 
















    4 



    4 




















    5 

















    5 










    2 




    5 


    5 





    5 




    5 






























    7 













    5 
    2 
    1 

    6 


















    4 



    4 
    1 

    4 
    1 

    4 





    2 




























    4 










    4 


    2 
    2 



    4 

    4 






















   10 












   10 





   10 


    8 

















    8 













    7 


    7 
    6 


    6 





















    1 












    2 










    7 



    1 








    2 
    4 











    8 












  101 


































    1 












  100 












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
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
1187
1188
1189
1190
1191
1192
1193
1194
1195
1196
1197
1198
1199
1200
1201
1202
1203
1204
1205
1206
1207
1208
1209
1210
1211
1212
1213
1214
1215
1216
1217
1218
1219
1220
1221
1222
1223
1224
1225
1226
1227
1228
1229
1230
1231
1232
1233
1234
1235
1236
1237
1238
1239
1240
1241
1242
1243
1244
1245
1246
1247
1248
1249
1250
1251
1252
1253
1254
1255
1256
1257
1258
1259
1260
1261
1262
1263
1264
1265
1266
1267
1268
1269
1270
1271
1272
1273
1274
1275
1276
1277
1278
1279
1280
1281
1282
1283
1284
1285
// SPDX-License-Identifier: GPL-2.0+
/*
 * NILFS segment usage file.
 *
 * Copyright (C) 2006-2008 Nippon Telegraph and Telephone Corporation.
 *
 * Written by Koji Sato.
 * Revised by Ryusuke Konishi.
 */

#include <linux/kernel.h>
#include <linux/fs.h>
#include <linux/string.h>
#include <linux/buffer_head.h>
#include <linux/errno.h>
#include "mdt.h"
#include "sufile.h"

#include <trace/events/nilfs2.h>

/**
 * struct nilfs_sufile_info - on-memory private data of sufile
 * @mi: on-memory private data of metadata file
 * @ncleansegs: number of clean segments
 * @allocmin: lower limit of allocatable segment range
 * @allocmax: upper limit of allocatable segment range
 */
struct nilfs_sufile_info {
        struct nilfs_mdt_info mi;
        unsigned long ncleansegs;/* number of clean segments */
        __u64 allocmin;                /* lower limit of allocatable segment range */
        __u64 allocmax;                /* upper limit of allocatable segment range */
};

static inline struct nilfs_sufile_info *NILFS_SUI(struct inode *sufile)
{
        return (struct nilfs_sufile_info *)NILFS_MDT(sufile);
}

static inline unsigned long
nilfs_sufile_segment_usages_per_block(const struct inode *sufile)
{
        return NILFS_MDT(sufile)->mi_entries_per_block;
}

static unsigned long
nilfs_sufile_get_blkoff(const struct inode *sufile, __u64 segnum)
{
        __u64 t = segnum + NILFS_MDT(sufile)->mi_first_entry_offset;

        t = div64_ul(t, nilfs_sufile_segment_usages_per_block(sufile));
        return (unsigned long)t;
}

static unsigned long
nilfs_sufile_get_offset(const struct inode *sufile, __u64 segnum)
{
        __u64 t = segnum + NILFS_MDT(sufile)->mi_first_entry_offset;

        return do_div(t, nilfs_sufile_segment_usages_per_block(sufile));
}

static unsigned long
nilfs_sufile_segment_usages_in_block(const struct inode *sufile, __u64 curr,
                                     __u64 max)
{
        return min_t(unsigned long,
                     nilfs_sufile_segment_usages_per_block(sufile) -
                     nilfs_sufile_get_offset(sufile, curr),
                     max - curr + 1);
}

/**
 * nilfs_sufile_segment_usage_offset - calculate the byte offset of a segment
 *                                     usage entry in the folio containing it
 * @sufile: segment usage file inode
 * @segnum: number of segment usage
 * @bh:     buffer head of block containing segment usage indexed by @segnum
 *
 * Return: Byte offset in the folio of the segment usage entry.
 */
static size_t nilfs_sufile_segment_usage_offset(const struct inode *sufile,
                                                __u64 segnum,
                                                struct buffer_head *bh)
{
        return offset_in_folio(bh->b_folio, bh->b_data) +
                nilfs_sufile_get_offset(sufile, segnum) *
                NILFS_MDT(sufile)->mi_entry_size;
}

static int nilfs_sufile_get_header_block(struct inode *sufile,
                                         struct buffer_head **bhp)
{
        int err = nilfs_mdt_get_block(sufile, 0, 0, NULL, bhp);

        if (unlikely(err == -ENOENT)) {
                nilfs_error(sufile->i_sb,
                            "missing header block in segment usage metadata");
                err = -EIO;
        }
        return err;
}

static inline int
nilfs_sufile_get_segment_usage_block(struct inode *sufile, __u64 segnum,
                                     int create, struct buffer_head **bhp)
{
        return nilfs_mdt_get_block(sufile,
                                   nilfs_sufile_get_blkoff(sufile, segnum),
                                   create, NULL, bhp);
}

static int nilfs_sufile_delete_segment_usage_block(struct inode *sufile,
                                                   __u64 segnum)
{
        return nilfs_mdt_delete_block(sufile,
                                      nilfs_sufile_get_blkoff(sufile, segnum));
}

static void nilfs_sufile_mod_counter(struct buffer_head *header_bh,
                                     u64 ncleanadd, u64 ndirtyadd)
{
        struct nilfs_sufile_header *header;

        header = kmap_local_folio(header_bh->b_folio, 0);
        le64_add_cpu(&header->sh_ncleansegs, ncleanadd);
        le64_add_cpu(&header->sh_ndirtysegs, ndirtyadd);
        kunmap_local(header);

        mark_buffer_dirty(header_bh);
}

/**
 * nilfs_sufile_get_ncleansegs - return the number of clean segments
 * @sufile: inode of segment usage file
 */
unsigned long nilfs_sufile_get_ncleansegs(struct inode *sufile)
{
        return NILFS_SUI(sufile)->ncleansegs;
}

/**
 * nilfs_sufile_updatev - modify multiple segment usages at a time
 * @sufile: inode of segment usage file
 * @segnumv: array of segment numbers
 * @nsegs: size of @segnumv array
 * @create: creation flag
 * @ndone: place to store number of modified segments on @segnumv
 * @dofunc: primitive operation for the update
 *
 * Description: nilfs_sufile_updatev() repeatedly calls @dofunc
 * against the given array of segments.  The @dofunc is called with
 * buffers of a header block and the sufile block in which the target
 * segment usage entry is contained.  If @ndone is given, the number
 * of successfully modified segments from the head is stored in the
 * place @ndone points to.
 *
 * Return Value: On success, zero is returned.  On error, one of the
 * following negative error codes is returned.
 *
 * %-EIO - I/O error.
 *
 * %-ENOMEM - Insufficient amount of memory available.
 *
 * %-ENOENT - Given segment usage is in hole block (may be returned if
 *            @create is zero)
 *
 * %-EINVAL - Invalid segment usage number
 */
int nilfs_sufile_updatev(struct inode *sufile, __u64 *segnumv, size_t nsegs,
                         int create, size_t *ndone,
                         void (*dofunc)(struct inode *, __u64,
                                        struct buffer_head *,
                                        struct buffer_head *))
{
        struct buffer_head *header_bh, *bh;
        unsigned long blkoff, prev_blkoff;
        __u64 *seg;
        size_t nerr = 0, n = 0;
        int ret = 0;

        if (unlikely(nsegs == 0))
                goto out;

        down_write(&NILFS_MDT(sufile)->mi_sem);
        for (seg = segnumv; seg < segnumv + nsegs; seg++) {
                if (unlikely(*seg >= nilfs_sufile_get_nsegments(sufile))) {
                        nilfs_warn(sufile->i_sb,
                                   "%s: invalid segment number: %llu",
                                   __func__, (unsigned long long)*seg);
                        nerr++;
                }
        }
        if (nerr > 0) {
                ret = -EINVAL;
                goto out_sem;
        }

        ret = nilfs_sufile_get_header_block(sufile, &header_bh);
        if (ret < 0)
                goto out_sem;

        seg = segnumv;
        blkoff = nilfs_sufile_get_blkoff(sufile, *seg);
        ret = nilfs_mdt_get_block(sufile, blkoff, create, NULL, &bh);
        if (ret < 0)
                goto out_header;

        for (;;) {
                dofunc(sufile, *seg, header_bh, bh);

                if (++seg >= segnumv + nsegs)
                        break;
                prev_blkoff = blkoff;
                blkoff = nilfs_sufile_get_blkoff(sufile, *seg);
                if (blkoff == prev_blkoff)
                        continue;

                /* get different block */
                brelse(bh);
                ret = nilfs_mdt_get_block(sufile, blkoff, create, NULL, &bh);
                if (unlikely(ret < 0))
                        goto out_header;
        }
        brelse(bh);

 out_header:
        n = seg - segnumv;
        brelse(header_bh);
 out_sem:
        up_write(&NILFS_MDT(sufile)->mi_sem);
 out:
        if (ndone)
                *ndone = n;
        return ret;
}

int nilfs_sufile_update(struct inode *sufile, __u64 segnum, int create,
                        void (*dofunc)(struct inode *, __u64,
                                       struct buffer_head *,
                                       struct buffer_head *))
{
        struct buffer_head *header_bh, *bh;
        int ret;

        if (unlikely(segnum >= nilfs_sufile_get_nsegments(sufile))) {
                nilfs_warn(sufile->i_sb, "%s: invalid segment number: %llu",
                           __func__, (unsigned long long)segnum);
                return -EINVAL;
        }
        down_write(&NILFS_MDT(sufile)->mi_sem);

        ret = nilfs_sufile_get_header_block(sufile, &header_bh);
        if (ret < 0)
                goto out_sem;

        ret = nilfs_sufile_get_segment_usage_block(sufile, segnum, create, &bh);
        if (!ret) {
                dofunc(sufile, segnum, header_bh, bh);
                brelse(bh);
        }
        brelse(header_bh);

 out_sem:
        up_write(&NILFS_MDT(sufile)->mi_sem);
        return ret;
}

/**
 * nilfs_sufile_set_alloc_range - limit range of segment to be allocated
 * @sufile: inode of segment usage file
 * @start: minimum segment number of allocatable region (inclusive)
 * @end: maximum segment number of allocatable region (inclusive)
 *
 * Return Value: On success, 0 is returned.  On error, one of the
 * following negative error codes is returned.
 *
 * %-ERANGE - invalid segment region
 */
int nilfs_sufile_set_alloc_range(struct inode *sufile, __u64 start, __u64 end)
{
        struct nilfs_sufile_info *sui = NILFS_SUI(sufile);
        __u64 nsegs;
        int ret = -ERANGE;

        down_write(&NILFS_MDT(sufile)->mi_sem);
        nsegs = nilfs_sufile_get_nsegments(sufile);

        if (start <= end && end < nsegs) {
                sui->allocmin = start;
                sui->allocmax = end;
                ret = 0;
        }
        up_write(&NILFS_MDT(sufile)->mi_sem);
        return ret;
}

/**
 * nilfs_sufile_alloc - allocate a segment
 * @sufile: inode of segment usage file
 * @segnump: pointer to segment number
 *
 * Description: nilfs_sufile_alloc() allocates a clean segment.
 *
 * Return Value: On success, 0 is returned and the segment number of the
 * allocated segment is stored in the place pointed by @segnump. On error, one
 * of the following negative error codes is returned.
 *
 * %-EIO - I/O error.
 *
 * %-ENOMEM - Insufficient amount of memory available.
 *
 * %-ENOSPC - No clean segment left.
 */
int nilfs_sufile_alloc(struct inode *sufile, __u64 *segnump)
{
        struct buffer_head *header_bh, *su_bh;
        struct nilfs_sufile_header *header;
        struct nilfs_segment_usage *su;
        struct nilfs_sufile_info *sui = NILFS_SUI(sufile);
        size_t susz = NILFS_MDT(sufile)->mi_entry_size;
        __u64 segnum, maxsegnum, last_alloc;
        size_t offset;
        void *kaddr;
        unsigned long nsegments, nsus, cnt;
        int ret, j;

        down_write(&NILFS_MDT(sufile)->mi_sem);

        ret = nilfs_sufile_get_header_block(sufile, &header_bh);
        if (ret < 0)
                goto out_sem;
        header = kmap_local_folio(header_bh->b_folio, 0);
        last_alloc = le64_to_cpu(header->sh_last_alloc);
        kunmap_local(header);

        nsegments = nilfs_sufile_get_nsegments(sufile);
        maxsegnum = sui->allocmax;
        segnum = last_alloc + 1;
        if (segnum < sui->allocmin || segnum > sui->allocmax)
                segnum = sui->allocmin;

        for (cnt = 0; cnt < nsegments; cnt += nsus) {
                if (segnum > maxsegnum) {
                        if (cnt < sui->allocmax - sui->allocmin + 1) {
                                /*
                                 * wrap around in the limited region.
                                 * if allocation started from
                                 * sui->allocmin, this never happens.
                                 */
                                segnum = sui->allocmin;
                                maxsegnum = last_alloc;
                        } else if (segnum > sui->allocmin &&
                                   sui->allocmax + 1 < nsegments) {
                                segnum = sui->allocmax + 1;
                                maxsegnum = nsegments - 1;
                        } else if (sui->allocmin > 0)  {
                                segnum = 0;
                                maxsegnum = sui->allocmin - 1;
                        } else {
                                break; /* never happens */
                        }
                }
                trace_nilfs2_segment_usage_check(sufile, segnum, cnt);
                ret = nilfs_sufile_get_segment_usage_block(sufile, segnum, 1,
                                                           &su_bh);
                if (ret < 0)
                        goto out_header;

                offset = nilfs_sufile_segment_usage_offset(sufile, segnum,
                                                           su_bh);
                su = kaddr = kmap_local_folio(su_bh->b_folio, offset);

                nsus = nilfs_sufile_segment_usages_in_block(
                        sufile, segnum, maxsegnum);
                for (j = 0; j < nsus; j++, su = (void *)su + susz, segnum++) {
                        if (!nilfs_segment_usage_clean(su))
                                continue;
                        /* found a clean segment */
                        nilfs_segment_usage_set_dirty(su);
                        kunmap_local(kaddr);

                        header = kmap_local_folio(header_bh->b_folio, 0);
                        le64_add_cpu(&header->sh_ncleansegs, -1);
                        le64_add_cpu(&header->sh_ndirtysegs, 1);
                        header->sh_last_alloc = cpu_to_le64(segnum);
                        kunmap_local(header);

                        sui->ncleansegs--;
                        mark_buffer_dirty(header_bh);
                        mark_buffer_dirty(su_bh);
                        nilfs_mdt_mark_dirty(sufile);
                        brelse(su_bh);
                        *segnump = segnum;

                        trace_nilfs2_segment_usage_allocated(sufile, segnum);

                        goto out_header;
                }

                kunmap_local(kaddr);
                brelse(su_bh);
        }

        /* no segments left */
        ret = -ENOSPC;

 out_header:
        brelse(header_bh);

 out_sem:
        up_write(&NILFS_MDT(sufile)->mi_sem);
        return ret;
}

void nilfs_sufile_do_cancel_free(struct inode *sufile, __u64 segnum,
                                 struct buffer_head *header_bh,
                                 struct buffer_head *su_bh)
{
        struct nilfs_segment_usage *su;
        size_t offset;

        offset = nilfs_sufile_segment_usage_offset(sufile, segnum, su_bh);
        su = kmap_local_folio(su_bh->b_folio, offset);
        if (unlikely(!nilfs_segment_usage_clean(su))) {
                nilfs_warn(sufile->i_sb, "%s: segment %llu must be clean",
                           __func__, (unsigned long long)segnum);
                kunmap_local(su);
                return;
        }
        nilfs_segment_usage_set_dirty(su);
        kunmap_local(su);

        nilfs_sufile_mod_counter(header_bh, -1, 1);
        NILFS_SUI(sufile)->ncleansegs--;

        mark_buffer_dirty(su_bh);
        nilfs_mdt_mark_dirty(sufile);
}

void nilfs_sufile_do_scrap(struct inode *sufile, __u64 segnum,
                           struct buffer_head *header_bh,
                           struct buffer_head *su_bh)
{
        struct nilfs_segment_usage *su;
        size_t offset;
        int clean, dirty;

        offset = nilfs_sufile_segment_usage_offset(sufile, segnum, su_bh);
        su = kmap_local_folio(su_bh->b_folio, offset);
        if (su->su_flags == cpu_to_le32(BIT(NILFS_SEGMENT_USAGE_DIRTY)) &&
            su->su_nblocks == cpu_to_le32(0)) {
                kunmap_local(su);
                return;
        }
        clean = nilfs_segment_usage_clean(su);
        dirty = nilfs_segment_usage_dirty(su);

        /* make the segment garbage */
        su->su_lastmod = cpu_to_le64(0);
        su->su_nblocks = cpu_to_le32(0);
        su->su_flags = cpu_to_le32(BIT(NILFS_SEGMENT_USAGE_DIRTY));
        kunmap_local(su);

        nilfs_sufile_mod_counter(header_bh, clean ? (u64)-1 : 0, dirty ? 0 : 1);
        NILFS_SUI(sufile)->ncleansegs -= clean;

        mark_buffer_dirty(su_bh);
        nilfs_mdt_mark_dirty(sufile);
}

void nilfs_sufile_do_free(struct inode *sufile, __u64 segnum,
                          struct buffer_head *header_bh,
                          struct buffer_head *su_bh)
{
        struct nilfs_segment_usage *su;
        size_t offset;
        int sudirty;

        offset = nilfs_sufile_segment_usage_offset(sufile, segnum, su_bh);
        su = kmap_local_folio(su_bh->b_folio, offset);
        if (nilfs_segment_usage_clean(su)) {
                nilfs_warn(sufile->i_sb, "%s: segment %llu is already clean",
                           __func__, (unsigned long long)segnum);
                kunmap_local(su);
                return;
        }
        if (unlikely(nilfs_segment_usage_error(su)))
                nilfs_warn(sufile->i_sb, "free segment %llu marked in error",
                           (unsigned long long)segnum);

        sudirty = nilfs_segment_usage_dirty(su);
        if (unlikely(!sudirty))
                nilfs_warn(sufile->i_sb, "free unallocated segment %llu",
                           (unsigned long long)segnum);

        nilfs_segment_usage_set_clean(su);
        kunmap_local(su);
        mark_buffer_dirty(su_bh);

        nilfs_sufile_mod_counter(header_bh, 1, sudirty ? (u64)-1 : 0);
        NILFS_SUI(sufile)->ncleansegs++;

        nilfs_mdt_mark_dirty(sufile);

        trace_nilfs2_segment_usage_freed(sufile, segnum);
}

/**
 * nilfs_sufile_mark_dirty - mark the buffer having a segment usage dirty
 * @sufile: inode of segment usage file
 * @segnum: segment number
 */
int nilfs_sufile_mark_dirty(struct inode *sufile, __u64 segnum)
{
        struct buffer_head *bh;
        size_t offset;
        struct nilfs_segment_usage *su;
        int ret;

        down_write(&NILFS_MDT(sufile)->mi_sem);
        ret = nilfs_sufile_get_segment_usage_block(sufile, segnum, 0, &bh);
        if (unlikely(ret)) {
                if (ret == -ENOENT) {
                        nilfs_error(sufile->i_sb,
                                    "segment usage for segment %llu is unreadable due to a hole block",
                                    (unsigned long long)segnum);
                        ret = -EIO;
                }
                goto out_sem;
        }

        offset = nilfs_sufile_segment_usage_offset(sufile, segnum, bh);
        su = kmap_local_folio(bh->b_folio, offset);
        if (unlikely(nilfs_segment_usage_error(su))) {
                struct the_nilfs *nilfs = sufile->i_sb->s_fs_info;

                kunmap_local(su);
                brelse(bh);
                if (nilfs_segment_is_active(nilfs, segnum)) {
                        nilfs_error(sufile->i_sb,
                                    "active segment %llu is erroneous",
                                    (unsigned long long)segnum);
                } else {
                        /*
                         * Segments marked erroneous are never allocated by
                         * nilfs_sufile_alloc(); only active segments, ie,
                         * the segments indexed by ns_segnum or ns_nextnum,
                         * can be erroneous here.
                         */
                        WARN_ON_ONCE(1);
                }
                ret = -EIO;
        } else {
                nilfs_segment_usage_set_dirty(su);
                kunmap_local(su);
                mark_buffer_dirty(bh);
                nilfs_mdt_mark_dirty(sufile);
                brelse(bh);
        }
out_sem:
        up_write(&NILFS_MDT(sufile)->mi_sem);
        return ret;
}

/**
 * nilfs_sufile_set_segment_usage - set usage of a segment
 * @sufile: inode of segment usage file
 * @segnum: segment number
 * @nblocks: number of live blocks in the segment
 * @modtime: modification time (option)
 */
int nilfs_sufile_set_segment_usage(struct inode *sufile, __u64 segnum,
                                   unsigned long nblocks, time64_t modtime)
{
        struct buffer_head *bh;
        struct nilfs_segment_usage *su;
        size_t offset;
        int ret;

        down_write(&NILFS_MDT(sufile)->mi_sem);
        ret = nilfs_sufile_get_segment_usage_block(sufile, segnum, 0, &bh);
        if (ret < 0)
                goto out_sem;

        offset = nilfs_sufile_segment_usage_offset(sufile, segnum, bh);
        su = kmap_local_folio(bh->b_folio, offset);
        if (modtime) {
                /*
                 * Check segusage error and set su_lastmod only when updating
                 * this entry with a valid timestamp, not for cancellation.
                 */
                WARN_ON_ONCE(nilfs_segment_usage_error(su));
                su->su_lastmod = cpu_to_le64(modtime);
        }
        su->su_nblocks = cpu_to_le32(nblocks);
        kunmap_local(su);

        mark_buffer_dirty(bh);
        nilfs_mdt_mark_dirty(sufile);
        brelse(bh);

 out_sem:
        up_write(&NILFS_MDT(sufile)->mi_sem);
        return ret;
}

/**
 * nilfs_sufile_get_stat - get segment usage statistics
 * @sufile: inode of segment usage file
 * @sustat: pointer to a structure of segment usage statistics
 *
 * Description: nilfs_sufile_get_stat() returns information about segment
 * usage.
 *
 * Return Value: On success, 0 is returned, and segment usage information is
 * stored in the place pointed by @sustat. On error, one of the following
 * negative error codes is returned.
 *
 * %-EIO - I/O error.
 *
 * %-ENOMEM - Insufficient amount of memory available.
 */
int nilfs_sufile_get_stat(struct inode *sufile, struct nilfs_sustat *sustat)
{
        struct buffer_head *header_bh;
        struct nilfs_sufile_header *header;
        struct the_nilfs *nilfs = sufile->i_sb->s_fs_info;
        int ret;

        down_read(&NILFS_MDT(sufile)->mi_sem);

        ret = nilfs_sufile_get_header_block(sufile, &header_bh);
        if (ret < 0)
                goto out_sem;

        header = kmap_local_folio(header_bh->b_folio, 0);
        sustat->ss_nsegs = nilfs_sufile_get_nsegments(sufile);
        sustat->ss_ncleansegs = le64_to_cpu(header->sh_ncleansegs);
        sustat->ss_ndirtysegs = le64_to_cpu(header->sh_ndirtysegs);
        sustat->ss_ctime = nilfs->ns_ctime;
        sustat->ss_nongc_ctime = nilfs->ns_nongc_ctime;
        spin_lock(&nilfs->ns_last_segment_lock);
        sustat->ss_prot_seq = nilfs->ns_prot_seq;
        spin_unlock(&nilfs->ns_last_segment_lock);
        kunmap_local(header);
        brelse(header_bh);

 out_sem:
        up_read(&NILFS_MDT(sufile)->mi_sem);
        return ret;
}

void nilfs_sufile_do_set_error(struct inode *sufile, __u64 segnum,
                               struct buffer_head *header_bh,
                               struct buffer_head *su_bh)
{
        struct nilfs_segment_usage *su;
        size_t offset;
        int suclean;

        offset = nilfs_sufile_segment_usage_offset(sufile, segnum, su_bh);
        su = kmap_local_folio(su_bh->b_folio, offset);
        if (nilfs_segment_usage_error(su)) {
                kunmap_local(su);
                return;
        }
        suclean = nilfs_segment_usage_clean(su);
        nilfs_segment_usage_set_error(su);
        kunmap_local(su);

        if (suclean) {
                nilfs_sufile_mod_counter(header_bh, -1, 0);
                NILFS_SUI(sufile)->ncleansegs--;
        }
        mark_buffer_dirty(su_bh);
        nilfs_mdt_mark_dirty(sufile);
}

/**
 * nilfs_sufile_truncate_range - truncate range of segment array
 * @sufile: inode of segment usage file
 * @start: start segment number (inclusive)
 * @end: end segment number (inclusive)
 *
 * Return Value: On success, 0 is returned.  On error, one of the
 * following negative error codes is returned.
 *
 * %-EIO - I/O error.
 *
 * %-ENOMEM - Insufficient amount of memory available.
 *
 * %-EINVAL - Invalid number of segments specified
 *
 * %-EBUSY - Dirty or active segments are present in the range
 */
static int nilfs_sufile_truncate_range(struct inode *sufile,
                                       __u64 start, __u64 end)
{
        struct the_nilfs *nilfs = sufile->i_sb->s_fs_info;
        struct buffer_head *header_bh;
        struct buffer_head *su_bh;
        struct nilfs_segment_usage *su, *su2;
        size_t susz = NILFS_MDT(sufile)->mi_entry_size;
        unsigned long segusages_per_block;
        unsigned long nsegs, ncleaned;
        __u64 segnum;
        size_t offset;
        ssize_t n, nc;
        int ret;
        int j;

        nsegs = nilfs_sufile_get_nsegments(sufile);

        ret = -EINVAL;
        if (start > end || start >= nsegs)
                goto out;

        ret = nilfs_sufile_get_header_block(sufile, &header_bh);
        if (ret < 0)
                goto out;

        segusages_per_block = nilfs_sufile_segment_usages_per_block(sufile);
        ncleaned = 0;

        for (segnum = start; segnum <= end; segnum += n) {
                n = min_t(unsigned long,
                          segusages_per_block -
                                  nilfs_sufile_get_offset(sufile, segnum),
                          end - segnum + 1);
                ret = nilfs_sufile_get_segment_usage_block(sufile, segnum, 0,
                                                           &su_bh);
                if (ret < 0) {
                        if (ret != -ENOENT)
                                goto out_header;
                        /* hole */
                        continue;
                }
                offset = nilfs_sufile_segment_usage_offset(sufile, segnum,
                                                           su_bh);
                su = kmap_local_folio(su_bh->b_folio, offset);
                su2 = su;
                for (j = 0; j < n; j++, su = (void *)su + susz) {
                        if ((le32_to_cpu(su->su_flags) &
                             ~BIT(NILFS_SEGMENT_USAGE_ERROR)) ||
                            nilfs_segment_is_active(nilfs, segnum + j)) {
                                ret = -EBUSY;
                                kunmap_local(su2);
                                brelse(su_bh);
                                goto out_header;
                        }
                }
                nc = 0;
                for (su = su2, j = 0; j < n; j++, su = (void *)su + susz) {
                        if (nilfs_segment_usage_error(su)) {
                                nilfs_segment_usage_set_clean(su);
                                nc++;
                        }
                }
                kunmap_local(su2);
                if (nc > 0) {
                        mark_buffer_dirty(su_bh);
                        ncleaned += nc;
                }
                brelse(su_bh);

                if (n == segusages_per_block) {
                        /* make hole */
                        nilfs_sufile_delete_segment_usage_block(sufile, segnum);
                }
        }
        ret = 0;

out_header:
        if (ncleaned > 0) {
                NILFS_SUI(sufile)->ncleansegs += ncleaned;
                nilfs_sufile_mod_counter(header_bh, ncleaned, 0);
                nilfs_mdt_mark_dirty(sufile);
        }
        brelse(header_bh);
out:
        return ret;
}

/**
 * nilfs_sufile_resize - resize segment array
 * @sufile: inode of segment usage file
 * @newnsegs: new number of segments
 *
 * Return Value: On success, 0 is returned.  On error, one of the
 * following negative error codes is returned.
 *
 * %-EIO - I/O error.
 *
 * %-ENOMEM - Insufficient amount of memory available.
 *
 * %-ENOSPC - Enough free space is not left for shrinking
 *
 * %-EBUSY - Dirty or active segments exist in the region to be truncated
 */
int nilfs_sufile_resize(struct inode *sufile, __u64 newnsegs)
{
        struct the_nilfs *nilfs = sufile->i_sb->s_fs_info;
        struct buffer_head *header_bh;
        struct nilfs_sufile_header *header;
        struct nilfs_sufile_info *sui = NILFS_SUI(sufile);
        unsigned long nsegs, nrsvsegs;
        int ret = 0;

        down_write(&NILFS_MDT(sufile)->mi_sem);

        nsegs = nilfs_sufile_get_nsegments(sufile);
        if (nsegs == newnsegs)
                goto out;

        ret = -ENOSPC;
        nrsvsegs = nilfs_nrsvsegs(nilfs, newnsegs);
        if (newnsegs < nsegs && nsegs - newnsegs + nrsvsegs > sui->ncleansegs)
                goto out;

        ret = nilfs_sufile_get_header_block(sufile, &header_bh);
        if (ret < 0)
                goto out;

        if (newnsegs > nsegs) {
                sui->ncleansegs += newnsegs - nsegs;
        } else /* newnsegs < nsegs */ {
                ret = nilfs_sufile_truncate_range(sufile, newnsegs, nsegs - 1);
                if (ret < 0)
                        goto out_header;

                sui->ncleansegs -= nsegs - newnsegs;

                /*
                 * If the sufile is successfully truncated, immediately adjust
                 * the segment allocation space while locking the semaphore
                 * "mi_sem" so that nilfs_sufile_alloc() never allocates
                 * segments in the truncated space.
                 */
                sui->allocmax = newnsegs - 1;
                sui->allocmin = 0;
        }

        header = kmap_local_folio(header_bh->b_folio, 0);
        header->sh_ncleansegs = cpu_to_le64(sui->ncleansegs);
        kunmap_local(header);

        mark_buffer_dirty(header_bh);
        nilfs_mdt_mark_dirty(sufile);
        nilfs_set_nsegments(nilfs, newnsegs);

out_header:
        brelse(header_bh);
out:
        up_write(&NILFS_MDT(sufile)->mi_sem);
        return ret;
}

/**
 * nilfs_sufile_get_suinfo - get segment usage information
 * @sufile: inode of segment usage file
 * @segnum: segment number to start looking
 * @buf:    array of suinfo
 * @sisz:   byte size of suinfo
 * @nsi:    size of suinfo array
 *
 * Return: Count of segment usage info items stored in the output buffer on
 * success, or the following negative error code on failure.
 * * %-EIO        - I/O error (including metadata corruption).
 * * %-ENOMEM        - Insufficient memory available.
 */
ssize_t nilfs_sufile_get_suinfo(struct inode *sufile, __u64 segnum, void *buf,
                                unsigned int sisz, size_t nsi)
{
        struct buffer_head *su_bh;
        struct nilfs_segment_usage *su;
        struct nilfs_suinfo *si = buf;
        size_t susz = NILFS_MDT(sufile)->mi_entry_size;
        struct the_nilfs *nilfs = sufile->i_sb->s_fs_info;
        size_t offset;
        void *kaddr;
        unsigned long nsegs, segusages_per_block;
        ssize_t n;
        int ret, i, j;

        down_read(&NILFS_MDT(sufile)->mi_sem);

        segusages_per_block = nilfs_sufile_segment_usages_per_block(sufile);
        nsegs = min_t(unsigned long,
                      nilfs_sufile_get_nsegments(sufile) - segnum,
                      nsi);
        for (i = 0; i < nsegs; i += n, segnum += n) {
                n = min_t(unsigned long,
                          segusages_per_block -
                                  nilfs_sufile_get_offset(sufile, segnum),
                          nsegs - i);
                ret = nilfs_sufile_get_segment_usage_block(sufile, segnum, 0,
                                                           &su_bh);
                if (ret < 0) {
                        if (ret != -ENOENT)
                                goto out;
                        /* hole */
                        memset(si, 0, sisz * n);
                        si = (void *)si + sisz * n;
                        continue;
                }

                offset = nilfs_sufile_segment_usage_offset(sufile, segnum,
                                                           su_bh);
                su = kaddr = kmap_local_folio(su_bh->b_folio, offset);
                for (j = 0; j < n;
                     j++, su = (void *)su + susz, si = (void *)si + sisz) {
                        si->sui_lastmod = le64_to_cpu(su->su_lastmod);
                        si->sui_nblocks = le32_to_cpu(su->su_nblocks);
                        si->sui_flags = le32_to_cpu(su->su_flags) &
                                ~BIT(NILFS_SEGMENT_USAGE_ACTIVE);
                        if (nilfs_segment_is_active(nilfs, segnum + j))
                                si->sui_flags |=
                                        BIT(NILFS_SEGMENT_USAGE_ACTIVE);
                }
                kunmap_local(kaddr);
                brelse(su_bh);
        }
        ret = nsegs;

 out:
        up_read(&NILFS_MDT(sufile)->mi_sem);
        return ret;
}

/**
 * nilfs_sufile_set_suinfo - sets segment usage info
 * @sufile: inode of segment usage file
 * @buf: array of suinfo_update
 * @supsz: byte size of suinfo_update
 * @nsup: size of suinfo_update array
 *
 * Description: Takes an array of nilfs_suinfo_update structs and updates
 * segment usage accordingly. Only the fields indicated by the sup_flags
 * are updated.
 *
 * Return Value: On success, 0 is returned. On error, one of the
 * following negative error codes is returned.
 *
 * %-EIO - I/O error.
 *
 * %-ENOMEM - Insufficient amount of memory available.
 *
 * %-EINVAL - Invalid values in input (segment number, flags or nblocks)
 */
ssize_t nilfs_sufile_set_suinfo(struct inode *sufile, void *buf,
                                unsigned int supsz, size_t nsup)
{
        struct the_nilfs *nilfs = sufile->i_sb->s_fs_info;
        struct buffer_head *header_bh, *bh;
        struct nilfs_suinfo_update *sup, *supend = buf + supsz * nsup;
        struct nilfs_segment_usage *su;
        size_t offset;
        unsigned long blkoff, prev_blkoff;
        int cleansi, cleansu, dirtysi, dirtysu;
        long ncleaned = 0, ndirtied = 0;
        int ret = 0;

        if (unlikely(nsup == 0))
                return ret;

        for (sup = buf; sup < supend; sup = (void *)sup + supsz) {
                if (sup->sup_segnum >= nilfs->ns_nsegments
                        || (sup->sup_flags &
                                (~0UL << __NR_NILFS_SUINFO_UPDATE_FIELDS))
                        || (nilfs_suinfo_update_nblocks(sup) &&
                                sup->sup_sui.sui_nblocks >
                                nilfs->ns_blocks_per_segment))
                        return -EINVAL;
        }

        down_write(&NILFS_MDT(sufile)->mi_sem);

        ret = nilfs_sufile_get_header_block(sufile, &header_bh);
        if (ret < 0)
                goto out_sem;

        sup = buf;
        blkoff = nilfs_sufile_get_blkoff(sufile, sup->sup_segnum);
        ret = nilfs_mdt_get_block(sufile, blkoff, 1, NULL, &bh);
        if (ret < 0)
                goto out_header;

        for (;;) {
                offset = nilfs_sufile_segment_usage_offset(
                        sufile, sup->sup_segnum, bh);
                su = kmap_local_folio(bh->b_folio, offset);

                if (nilfs_suinfo_update_lastmod(sup))
                        su->su_lastmod = cpu_to_le64(sup->sup_sui.sui_lastmod);

                if (nilfs_suinfo_update_nblocks(sup))
                        su->su_nblocks = cpu_to_le32(sup->sup_sui.sui_nblocks);

                if (nilfs_suinfo_update_flags(sup)) {
                        /*
                         * Active flag is a virtual flag projected by running
                         * nilfs kernel code - drop it not to write it to
                         * disk.
                         */
                        sup->sup_sui.sui_flags &=
                                        ~BIT(NILFS_SEGMENT_USAGE_ACTIVE);

                        cleansi = nilfs_suinfo_clean(&sup->sup_sui);
                        cleansu = nilfs_segment_usage_clean(su);
                        dirtysi = nilfs_suinfo_dirty(&sup->sup_sui);
                        dirtysu = nilfs_segment_usage_dirty(su);

                        if (cleansi && !cleansu)
                                ++ncleaned;
                        else if (!cleansi && cleansu)
                                --ncleaned;

                        if (dirtysi && !dirtysu)
                                ++ndirtied;
                        else if (!dirtysi && dirtysu)
                                --ndirtied;

                        su->su_flags = cpu_to_le32(sup->sup_sui.sui_flags);
                }

                kunmap_local(su);

                sup = (void *)sup + supsz;
                if (sup >= supend)
                        break;

                prev_blkoff = blkoff;
                blkoff = nilfs_sufile_get_blkoff(sufile, sup->sup_segnum);
                if (blkoff == prev_blkoff)
                        continue;

                /* get different block */
                mark_buffer_dirty(bh);
                put_bh(bh);
                ret = nilfs_mdt_get_block(sufile, blkoff, 1, NULL, &bh);
                if (unlikely(ret < 0))
                        goto out_mark;
        }
        mark_buffer_dirty(bh);
        put_bh(bh);

 out_mark:
        if (ncleaned || ndirtied) {
                nilfs_sufile_mod_counter(header_bh, (u64)ncleaned,
                                (u64)ndirtied);
                NILFS_SUI(sufile)->ncleansegs += ncleaned;
        }
        nilfs_mdt_mark_dirty(sufile);
 out_header:
        put_bh(header_bh);
 out_sem:
        up_write(&NILFS_MDT(sufile)->mi_sem);
        return ret;
}

/**
 * nilfs_sufile_trim_fs() - trim ioctl handle function
 * @sufile: inode of segment usage file
 * @range: fstrim_range structure
 *
 * start:        First Byte to trim
 * len:                number of Bytes to trim from start
 * minlen:        minimum extent length in Bytes
 *
 * Decription: nilfs_sufile_trim_fs goes through all segments containing bytes
 * from start to start+len. start is rounded up to the next block boundary
 * and start+len is rounded down. For each clean segment blkdev_issue_discard
 * function is invoked.
 *
 * Return Value: On success, 0 is returned or negative error code, otherwise.
 */
int nilfs_sufile_trim_fs(struct inode *sufile, struct fstrim_range *range)
{
        struct the_nilfs *nilfs = sufile->i_sb->s_fs_info;
        struct buffer_head *su_bh;
        struct nilfs_segment_usage *su;
        size_t offset;
        void *kaddr;
        size_t n, i, susz = NILFS_MDT(sufile)->mi_entry_size;
        sector_t seg_start, seg_end, start_block, end_block;
        sector_t start = 0, nblocks = 0;
        u64 segnum, segnum_end, minlen, len, max_blocks, ndiscarded = 0;
        int ret = 0;
        unsigned int sects_per_block;

        sects_per_block = (1 << nilfs->ns_blocksize_bits) /
                        bdev_logical_block_size(nilfs->ns_bdev);
        len = range->len >> nilfs->ns_blocksize_bits;
        minlen = range->minlen >> nilfs->ns_blocksize_bits;
        max_blocks = ((u64)nilfs->ns_nsegments * nilfs->ns_blocks_per_segment);

        if (!len || range->start >= max_blocks << nilfs->ns_blocksize_bits)
                return -EINVAL;

        start_block = (range->start + nilfs->ns_blocksize - 1) >>
                        nilfs->ns_blocksize_bits;

        /*
         * range->len can be very large (actually, it is set to
         * ULLONG_MAX by default) - truncate upper end of the range
         * carefully so as not to overflow.
         */
        if (max_blocks - start_block < len)
                end_block = max_blocks - 1;
        else
                end_block = start_block + len - 1;

        segnum = nilfs_get_segnum_of_block(nilfs, start_block);
        segnum_end = nilfs_get_segnum_of_block(nilfs, end_block);

        down_read(&NILFS_MDT(sufile)->mi_sem);

        while (segnum <= segnum_end) {
                n = nilfs_sufile_segment_usages_in_block(sufile, segnum,
                                segnum_end);

                ret = nilfs_sufile_get_segment_usage_block(sufile, segnum, 0,
                                                           &su_bh);
                if (ret < 0) {
                        if (ret != -ENOENT)
                                goto out_sem;
                        /* hole */
                        segnum += n;
                        continue;
                }

                offset = nilfs_sufile_segment_usage_offset(sufile, segnum,
                                                           su_bh);
                su = kaddr = kmap_local_folio(su_bh->b_folio, offset);
                for (i = 0; i < n; ++i, ++segnum, su = (void *)su + susz) {
                        if (!nilfs_segment_usage_clean(su))
                                continue;

                        nilfs_get_segment_range(nilfs, segnum, &seg_start,
                                                &seg_end);

                        if (!nblocks) {
                                /* start new extent */
                                start = seg_start;
                                nblocks = seg_end - seg_start + 1;
                                continue;
                        }

                        if (start + nblocks == seg_start) {
                                /* add to previous extent */
                                nblocks += seg_end - seg_start + 1;
                                continue;
                        }

                        /* discard previous extent */
                        if (start < start_block) {
                                nblocks -= start_block - start;
                                start = start_block;
                        }

                        if (nblocks >= minlen) {
                                kunmap_local(kaddr);

                                ret = blkdev_issue_discard(nilfs->ns_bdev,
                                                start * sects_per_block,
                                                nblocks * sects_per_block,
                                                GFP_NOFS);
                                if (ret < 0) {
                                        put_bh(su_bh);
                                        goto out_sem;
                                }

                                ndiscarded += nblocks;
                                offset = nilfs_sufile_segment_usage_offset(
                                        sufile, segnum, su_bh);
                                su = kaddr = kmap_local_folio(su_bh->b_folio,
                                                              offset);
                        }

                        /* start new extent */
                        start = seg_start;
                        nblocks = seg_end - seg_start + 1;
                }
                kunmap_local(kaddr);
                put_bh(su_bh);
        }


        if (nblocks) {
                /* discard last extent */
                if (start < start_block) {
                        nblocks -= start_block - start;
                        start = start_block;
                }
                if (start + nblocks > end_block + 1)
                        nblocks = end_block - start + 1;

                if (nblocks >= minlen) {
                        ret = blkdev_issue_discard(nilfs->ns_bdev,
                                        start * sects_per_block,
                                        nblocks * sects_per_block,
                                        GFP_NOFS);
                        if (!ret)
                                ndiscarded += nblocks;
                }
        }

out_sem:
        up_read(&NILFS_MDT(sufile)->mi_sem);

        range->len = ndiscarded << nilfs->ns_blocksize_bits;
        return ret;
}

/**
 * nilfs_sufile_read - read or get sufile inode
 * @sb: super block instance
 * @susize: size of a segment usage entry
 * @raw_inode: on-disk sufile inode
 * @inodep: buffer to store the inode
 */
int nilfs_sufile_read(struct super_block *sb, size_t susize,
                      struct nilfs_inode *raw_inode, struct inode **inodep)
{
        struct inode *sufile;
        struct nilfs_sufile_info *sui;
        struct buffer_head *header_bh;
        struct nilfs_sufile_header *header;
        int err;

        if (susize > sb->s_blocksize) {
                nilfs_err(sb, "too large segment usage size: %zu bytes",
                          susize);
                return -EINVAL;
        } else if (susize < NILFS_MIN_SEGMENT_USAGE_SIZE) {
                nilfs_err(sb, "too small segment usage size: %zu bytes",
                          susize);
                return -EINVAL;
        }

        sufile = nilfs_iget_locked(sb, NULL, NILFS_SUFILE_INO);
        if (unlikely(!sufile))
                return -ENOMEM;
        if (!(sufile->i_state & I_NEW))
                goto out;

        err = nilfs_mdt_init(sufile, NILFS_MDT_GFP, sizeof(*sui));
        if (err)
                goto failed;

        nilfs_mdt_set_entry_size(sufile, susize,
                                 sizeof(struct nilfs_sufile_header));

        err = nilfs_read_inode_common(sufile, raw_inode);
        if (err)
                goto failed;

        err = nilfs_mdt_get_block(sufile, 0, 0, NULL, &header_bh);
        if (unlikely(err)) {
                if (err == -ENOENT) {
                        nilfs_err(sb,
                                  "missing header block in segment usage metadata");
                        err = -EINVAL;
                }
                goto failed;
        }

        sui = NILFS_SUI(sufile);
        header = kmap_local_folio(header_bh->b_folio, 0);
        sui->ncleansegs = le64_to_cpu(header->sh_ncleansegs);
        kunmap_local(header);
        brelse(header_bh);

        sui->allocmax = nilfs_sufile_get_nsegments(sufile) - 1;
        sui->allocmin = 0;

        unlock_new_inode(sufile);
 out:
        *inodep = sufile;
        return 0;
 failed:
        iget_failed(sufile);
        return err;
}



























































   92 
   92 
    4 
   89 
   92 





   92 


























   59 





































   38 



   37 





   38 
   38 

   38 


















   38 

   38 






   38 









   38 





























   94 







































































   93 

    3 























   66 
   40 









   59 



















































































    1 
   59 














    1 


    1 















































    6 


   32 










































































   38 

   59 







   88 
    4 


















   24 

   65 
   65 



   89 

   31 
   33 
   32 
   19 
   41 
   38 






   93 





    4 



   89 
   35 

   89 

   89 
   41 















































   89 









   93 











   93 












   48 

   55 

   55 

    1 








   93 












   93 










   64 
   36 





   93 















   92 
    7 

















   93 




   93 




    7 


   92 


   92 
































    4 


    2 









   59 














   35 






   64 
   29 












    2 

















































































   92 


































































   64 




   32 


   32 






   92 
   92 































   92 





   92 

    1 

   92 







   92 
















































































    1 



   26 


    6 




















   94 























    1 





   88 
    5 

   59 
   39 




   93 






    2 
    1 

    1 


    2 











   59 


   40 


   59 
   39 





   66 
   32 






















   28 

    5 
   68 
   24 
   44 




   25 









   24 


   25 










   28 































   28 













































   28 



























   28 

   28 













   28 










































   52 









   44 












    7 











    8 




   78 




   78 



   78 
   76 
   78 



    3 

    2 

   38 


    3 

   37 


    2 

   38 



   37 






   37 











   37 


   37 


   37 
















   37 


   37 





    2 






    2 







   93 



   93 







   93 




   28 

   28 









   68 




   67 












   66 



    1 





















    2 




    2 
























   68 












   67 


   68 




























   68 













   94 









   94 
   94 
   92 
   92 






    6 








   91 







   92 




   92 








   92 
   92 

   92 


   92 







































































   94 






















   94 


   92 

    6 


   27 



   67 
















   95 




   72 



   32 

   64 



   95 
    5 


   95 




   20 










   94 


   89 



    4 





















   94 







































































































































































































































































































































































































































   27 


   28 












   22 



    9 














































    2 






    2 














    2 



































   27 























   27 










   27 

    2 






























    2 









    2 











































































































































   27 










    1 






   27 














   26 








   27 















   25 










   25 









    2 



   23 























   25 



    5 






    5 
   20 


   25 














   24 

   25 





   23 
    2 





   21 























































   12 










   12 















   12 




    1 








    1 



   10 




    8 

    7 




    8 











    8 


















































































    8 








    8 
    1 

    7 









    1 























































    7 








   12 


    1 





    5 


    5 
    5 

    5 



   86 



   86 

   87 
    5 





   87 



   75 



   77 






















































































































    4 































































































































    4 





    4 



    4 


    4 


    4 







    4 





    4 




    4 
    4 

    4 



























    4 










   28 













   28 


   28 
























    4 









    4 



    4 




























    4 

















    4 


































    1 







    4 




    4 
    4 










    4 



    4 










   28 










   28 



   28 






   28 






















   28 
















   24 





    7 

























   27 



















    4 





    4 







   27 


   27 






   28 







   28 
































   28 


























    7 









   24 



    7 







   24 



    7 






   28 







   28 



   28 


   28 












   24 



    7 








    7 






   27 


   28 
   28 



   28 







   27 




   28 

   28 

   28 







   28 





   28 
   28 

   28 


   28 







   28 



   28 




























   28 




   28 

































































   27 


   28 



   27 














   29 







    1 



   28 

   27 

   28 











   28 

   26 


    5 


    5 













   24 








    3 



   25 








   28 
   26 
   28 



















   21 





   21 



































































































































   24 



    6 
















   21 

























































































































































































































































   23 



   24 
   23 
















































































































































































































































































































































































































































































































































































































































































































































































































































































































































































































































































    4 
























    3 
    1 














































































































































































































   69 




   69 









   69 








































   53 



   53 

   53 

   53 





   53 








   53 






    6 










    6 




    1 





























    5 























    5 
    5 








    5 







    3 








    2 


    5 






































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
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
1187
1188
1189
1190
1191
1192
1193
1194
1195
1196
1197
1198
1199
1200
1201
1202
1203
1204
1205
1206
1207
1208
1209
1210
1211
1212
1213
1214
1215
1216
1217
1218
1219
1220
1221
1222
1223
1224
1225
1226
1227
1228
1229
1230
1231
1232
1233
1234
1235
1236
1237
1238
1239
1240
1241
1242
1243
1244
1245
1246
1247
1248
1249
1250
1251
1252
1253
1254
1255
1256
1257
1258
1259
1260
1261
1262
1263
1264
1265
1266
1267
1268
1269
1270
1271
1272
1273
1274
1275
1276
1277
1278
1279
1280
1281
1282
1283
1284
1285
1286
1287
1288
1289
1290
1291
1292
1293
1294
1295
1296
1297
1298
1299
1300
1301
1302
1303
1304
1305
1306
1307
1308
1309
1310
1311
1312
1313
1314
1315
1316
1317
1318
1319
1320
1321
1322
1323
1324
1325
1326
1327
1328
1329
1330
1331
1332
1333
1334
1335
1336
1337
1338
1339
1340
1341
1342
1343
1344
1345
1346
1347
1348
1349
1350
1351
1352
1353
1354
1355
1356
1357
1358
1359
1360
1361
1362
1363
1364
1365
1366
1367
1368
1369
1370
1371
1372
1373
1374
1375
1376
1377
1378
1379
1380
1381
1382
1383
1384
1385
1386
1387
1388
1389
1390
1391
1392
1393
1394
1395
1396
1397
1398
1399
1400
1401
1402
1403
1404
1405
1406
1407
1408
1409
1410
1411
1412
1413
1414
1415
1416
1417
1418
1419
1420
1421
1422
1423
1424
1425
1426
1427
1428
1429
1430
1431
1432
1433
1434
1435
1436
1437
1438
1439
1440
1441
1442
1443
1444
1445
1446
1447
1448
1449
1450
1451
1452
1453
1454
1455
1456
1457
1458
1459
1460
1461
1462
1463
1464
1465
1466
1467
1468
1469
1470
1471
1472
1473
1474
1475
1476
1477
1478
1479
1480
1481
1482
1483
1484
1485
1486
1487
1488
1489
1490
1491
1492
1493
1494
1495
1496
1497
1498
1499
1500
1501
1502
1503
1504
1505
1506
1507
1508
1509
1510
1511
1512
1513
1514
1515
1516
1517
1518
1519
1520
1521
1522
1523
1524
1525
1526
1527
1528
1529
1530
1531
1532
1533
1534
1535
1536
1537
1538
1539
1540
1541
1542
1543
1544
1545
1546
1547
1548
1549
1550
1551
1552
1553
1554
1555
1556
1557
1558
1559
1560
1561
1562
1563
1564
1565
1566
1567
1568
1569
1570
1571
1572
1573
1574
1575
1576
1577
1578
1579
1580
1581
1582
1583
1584
1585
1586
1587
1588
1589
1590
1591
1592
1593
1594
1595
1596
1597
1598
1599
1600
1601
1602
1603
1604
1605
1606
1607
1608
1609
1610
1611
1612
1613
1614
1615
1616
1617
1618
1619
1620
1621
1622
1623
1624
1625
1626
1627
1628
1629
1630
1631
1632
1633
1634
1635
1636
1637
1638
1639
1640
1641
1642
1643
1644
1645
1646
1647
1648
1649
1650
1651
1652
1653
1654
1655
1656
1657
1658
1659
1660
1661
1662
1663
1664
1665
1666
1667
1668
1669
1670
1671
1672
1673
1674
1675
1676
1677
1678
1679
1680
1681
1682
1683
1684
1685
1686
1687
1688
1689
1690
1691
1692
1693
1694
1695
1696
1697
1698
1699
1700
1701
1702
1703
1704
1705
1706
1707
1708
1709
1710
1711
1712
1713
1714
1715
1716
1717
1718
1719
1720
1721
1722
1723
1724
1725
1726
1727
1728
1729
1730
1731
1732
1733
1734
1735
1736
1737
1738
1739
1740
1741
1742
1743
1744
1745
1746
1747
1748
1749
1750
1751
1752
1753
1754
1755
1756
1757
1758
1759
1760
1761
1762
1763
1764
1765
1766
1767
1768
1769
1770
1771
1772
1773
1774
1775
1776
1777
1778
1779
1780
1781
1782
1783
1784
1785
1786
1787
1788
1789
1790
1791
1792
1793
1794
1795
1796
1797
1798
1799
1800
1801
1802
1803
1804
1805
1806
1807
1808
1809
1810
1811
1812
1813
1814
1815
1816
1817
1818
1819
1820
1821
1822
1823
1824
1825
1826
1827
1828
1829
1830
1831
1832
1833
1834
1835
1836
1837
1838
1839
1840
1841
1842
1843
1844
1845
1846
1847
1848
1849
1850
1851
1852
1853
1854
1855
1856
1857
1858
1859
1860
1861
1862
1863
1864
1865
1866
1867
1868
1869
1870
1871
1872
1873
1874
1875
1876
1877
1878
1879
1880
1881
1882
1883
1884
1885
1886
1887
1888
1889
1890
1891
1892
1893
1894
1895
1896
1897
1898
1899
1900
1901
1902
1903
1904
1905
1906
1907
1908
1909
1910
1911
1912
1913
1914
1915
1916
1917
1918
1919
1920
1921
1922
1923
1924
1925
1926
1927
1928
1929
1930
1931
1932
1933
1934
1935
1936
1937
1938
1939
1940
1941
1942
1943
1944
1945
1946
1947
1948
1949
1950
1951
1952
1953
1954
1955
1956
1957
1958
1959
1960
1961
1962
1963
1964
1965
1966
1967
1968
1969
1970
1971
1972
1973
1974
1975
1976
1977
1978
1979
1980
1981
1982
1983
1984
1985
1986
1987
1988
1989
1990
1991
1992
1993
1994
1995
1996
1997
1998
1999
2000
2001
2002
2003
2004
2005
2006
2007
2008
2009
2010
2011
2012
2013
2014
2015
2016
2017
2018
2019
2020
2021
2022
2023
2024
2025
2026
2027
2028
2029
2030
2031
2032
2033
2034
2035
2036
2037
2038
2039
2040
2041
2042
2043
2044
2045
2046
2047
2048
2049
2050
2051
2052
2053
2054
2055
2056
2057
2058
2059
2060
2061
2062
2063
2064
2065
2066
2067
2068
2069
2070
2071
2072
2073
2074
2075
2076
2077
2078
2079
2080
2081
2082
2083
2084
2085
2086
2087
2088
2089
2090
2091
2092
2093
2094
2095
2096
2097
2098
2099
2100
2101
2102
2103
2104
2105
2106
2107
2108
2109
2110
2111
2112
2113
2114
2115
2116
2117
2118
2119
2120
2121
2122
2123
2124
2125
2126
2127
2128
2129
2130
2131
2132
2133
2134
2135
2136
2137
2138
2139
2140
2141
2142
2143
2144
2145
2146
2147
2148
2149
2150
2151
2152
2153
2154
2155
2156
2157
2158
2159
2160
2161
2162
2163
2164
2165
2166
2167
2168
2169
2170
2171
2172
2173
2174
2175
2176
2177
2178
2179
2180
2181
2182
2183
2184
2185
2186
2187
2188
2189
2190
2191
2192
2193
2194
2195
2196
2197
2198
2199
2200
2201
2202
2203
2204
2205
2206
2207
2208
2209
2210
2211
2212
2213
2214
2215
2216
2217
2218
2219
2220
2221
2222
2223
2224
2225
2226
2227
2228
2229
2230
2231
2232
2233
2234
2235
2236
2237
2238
2239
2240
2241
2242
2243
2244
2245
2246
2247
2248
2249
2250
2251
2252
2253
2254
2255
2256
2257
2258
2259
2260
2261
2262
2263
2264
2265
2266
2267
2268
2269
2270
2271
2272
2273
2274
2275
2276
2277
2278
2279
2280
2281
2282
2283
2284
2285
2286
2287
2288
2289
2290
2291
2292
2293
2294
2295
2296
2297
2298
2299
2300
2301
2302
2303
2304
2305
2306
2307
2308
2309
2310
2311
2312
2313
2314
2315
2316
2317
2318
2319
2320
2321
2322
2323
2324
2325
2326
2327
2328
2329
2330
2331
2332
2333
2334
2335
2336
2337
2338
2339
2340
2341
2342
2343
2344
2345
2346
2347
2348
2349
2350
2351
2352
2353
2354
2355
2356
2357
2358
2359
2360
2361
2362
2363
2364
2365
2366
2367
2368
2369
2370
2371
2372
2373
2374
2375
2376
2377
2378
2379
2380
2381
2382
2383
2384
2385
2386
2387
2388
2389
2390
2391
2392
2393
2394
2395
2396
2397
2398
2399
2400
2401
2402
2403
2404
2405
2406
2407
2408
2409
2410
2411
2412
2413
2414
2415
2416
2417
2418
2419
2420
2421
2422
2423
2424
2425
2426
2427
2428
2429
2430
2431
2432
2433
2434
2435
2436
2437
2438
2439
2440
2441
2442
2443
2444
2445
2446
2447
2448
2449
2450
2451
2452
2453
2454
2455
2456
2457
2458
2459
2460
2461
2462
2463
2464
2465
2466
2467
2468
2469
2470
2471
2472
2473
2474
2475
2476
2477
2478
2479
2480
2481
2482
2483
2484
2485
2486
2487
2488
2489
2490
2491
2492
2493
2494
2495
2496
2497
2498
2499
2500
2501
2502
2503
2504
2505
2506
2507
2508
2509
2510
2511
2512
2513
2514
2515
2516
2517
2518
2519
2520
2521
2522
2523
2524
2525
2526
2527
2528
2529
2530
2531
2532
2533
2534
2535
2536
2537
2538
2539
2540
2541
2542
2543
2544
2545
2546
2547
2548
2549
2550
2551
2552
2553
2554
2555
2556
2557
2558
2559
2560
2561
2562
2563
2564
2565
2566
2567
2568
2569
2570
2571
2572
2573
2574
2575
2576
2577
2578
2579
2580
2581
2582
2583
2584
2585
2586
2587
2588
2589
2590
2591
2592
2593
2594
2595
2596
2597
2598
2599
2600
2601
2602
2603
2604
2605
2606
2607
2608
2609
2610
2611
2612
2613
2614
2615
2616
2617
2618
2619
2620
2621
2622
2623
2624
2625
2626
2627
2628
2629
2630
2631
2632
2633
2634
2635
2636
2637
2638
2639
2640
2641
2642
2643
2644
2645
2646
2647
2648
2649
2650
2651
2652
2653
2654
2655
2656
2657
2658
2659
2660
2661
2662
2663
2664
2665
2666
2667
2668
2669
2670
2671
2672
2673
2674
2675
2676
2677
2678
2679
2680
2681
2682
2683
2684
2685
2686
2687
2688
2689
2690
2691
2692
2693
2694
2695
2696
2697
2698
2699
2700
2701
2702
2703
2704
2705
2706
2707
2708
2709
2710
2711
2712
2713
2714
2715
2716
2717
2718
2719
2720
2721
2722
2723
2724
2725
2726
2727
2728
2729
2730
2731
2732
2733
2734
2735
2736
2737
2738
2739
2740
2741
2742
2743
2744
2745
2746
2747
2748
2749
2750
2751
2752
2753
2754
2755
2756
2757
2758
2759
2760
2761
2762
2763
2764
2765
2766
2767
2768
2769
2770
2771
2772
2773
2774
2775
2776
2777
2778
2779
2780
2781
2782
2783
2784
2785
2786
2787
2788
2789
2790
2791
2792
2793
2794
2795
2796
2797
2798
2799
2800
2801
2802
2803
2804
2805
2806
2807
2808
2809
2810
2811
2812
2813
2814
2815
2816
2817
2818
2819
2820
2821
2822
2823
2824
2825
2826
2827
2828
2829
2830
2831
2832
2833
2834
2835
2836
2837
2838
2839
2840
2841
2842
2843
2844
2845
2846
2847
2848
2849
2850
2851
2852
2853
2854
2855
2856
2857
2858
2859
2860
2861
2862
2863
2864
2865
2866
2867
2868
2869
2870
2871
2872
2873
2874
2875
2876
2877
2878
2879
2880
2881
2882
2883
2884
2885
2886
2887
2888
2889
2890
2891
2892
2893
2894
2895
2896
2897
2898
2899
2900
2901
2902
2903
2904
2905
2906
2907
2908
2909
2910
2911
2912
2913
2914
2915
2916
2917
2918
2919
2920
2921
2922
2923
2924
2925
2926
2927
2928
2929
2930
2931
2932
2933
2934
2935
2936
2937
2938
2939
2940
2941
2942
2943
2944
2945
2946
2947
2948
2949
2950
2951
2952
2953
2954
2955
2956
2957
2958
2959
2960
2961
2962
2963
2964
2965
2966
2967
2968
2969
2970
2971
2972
2973
2974
2975
2976
2977
2978
2979
2980
2981
2982
2983
2984
2985
2986
2987
2988
2989
2990
2991
2992
2993
2994
2995
2996
2997
2998
2999
3000
3001
3002
3003
3004
3005
3006
3007
3008
3009
3010
3011
3012
3013
3014
3015
3016
3017
3018
3019
3020
3021
3022
3023
3024
3025
3026
3027
3028
3029
3030
3031
3032
3033
3034
3035
3036
3037
3038
3039
3040
3041
3042
3043
3044
3045
3046
3047
3048
3049
3050
3051
3052
3053
3054
3055
3056
3057
3058
3059
3060
3061
3062
3063
3064
3065
3066
3067
3068
3069
3070
3071
3072
3073
3074
3075
3076
3077
3078
3079
3080
3081
3082
3083
3084
3085
3086
3087
3088
3089
3090
3091
3092
3093
3094
3095
3096
3097
3098
3099
3100
3101
3102
3103
3104
3105
3106
3107
3108
3109
3110
3111
3112
3113
3114
3115
3116
3117
3118
3119
3120
3121
3122
3123
3124
3125
3126
3127
3128
3129
3130
3131
3132
3133
3134
3135
3136
3137
3138
3139
3140
3141
3142
3143
3144
3145
3146
3147
3148
3149
3150
3151
3152
3153
3154
3155
3156
3157
3158
3159
3160
3161
3162
3163
3164
3165
3166
3167
3168
3169
3170
3171
3172
3173
3174
3175
3176
3177
3178
3179
3180
3181
3182
3183
3184
3185
3186
3187
3188
3189
3190
3191
3192
3193
3194
3195
3196
3197
3198
3199
3200
3201
3202
3203
3204
3205
3206
3207
3208
3209
3210
3211
3212
3213
3214
3215
3216
3217
3218
3219
3220
3221
3222
3223
3224
3225
3226
3227
3228
3229
3230
3231
3232
3233
3234
3235
3236
3237
3238
3239
3240
3241
3242
3243
3244
3245
3246
3247
3248
3249
3250
3251
3252
3253
3254
3255
3256
3257
3258
3259
3260
3261
3262
3263
3264
3265
3266
3267
3268
3269
3270
3271
3272
3273
3274
3275
3276
3277
3278
3279
3280
3281
3282
3283
3284
3285
3286
3287
3288
3289
3290
3291
3292
3293
3294
3295
3296
3297
3298
3299
3300
3301
3302
3303
3304
3305
3306
3307
3308
3309
3310
3311
3312
3313
3314
3315
3316
3317
3318
3319
3320
3321
3322
3323
3324
3325
3326
3327
3328
3329
3330
3331
3332
3333
3334
3335
3336
3337
3338
3339
3340
3341
3342
3343
3344
3345
3346
3347
3348
3349
3350
3351
3352
3353
3354
3355
3356
3357
3358
3359
3360
3361
3362
3363
3364
3365
3366
3367
3368
3369
3370
3371
3372
3373
3374
3375
3376
3377
3378
3379
3380
3381
3382
3383
3384
3385
3386
3387
3388
3389
3390
3391
3392
3393
3394
3395
3396
3397
3398
3399
3400
3401
3402
3403
3404
3405
3406
3407
3408
3409
3410
3411
3412
3413
3414
3415
3416
3417
3418
3419
3420
3421
3422
3423
3424
3425
3426
3427
3428
3429
3430
3431
3432
3433
3434
3435
3436
3437
3438
3439
3440
3441
3442
3443
3444
3445
3446
3447
3448
3449
3450
3451
3452
3453
3454
3455
3456
3457
3458
3459
3460
3461
3462
3463
3464
3465
3466
3467
3468
3469
3470
3471
3472
3473
3474
3475
3476
3477
3478
3479
3480
3481
3482
3483
3484
3485
3486
3487
3488
3489
3490
3491
3492
3493
3494
3495
3496
3497
3498
3499
3500
3501
3502
3503
3504
3505
3506
3507
3508
3509
3510
3511
3512
3513
3514
3515
3516
3517
3518
3519
3520
3521
3522
3523
3524
3525
3526
3527
3528
3529
3530
3531
3532
3533
3534
3535
3536
3537
3538
3539
3540
3541
3542
3543
3544
3545
3546
3547
3548
3549
3550
3551
3552
3553
3554
3555
3556
3557
3558
3559
3560
3561
3562
3563
3564
3565
3566
3567
3568
3569
3570
3571
3572
3573
3574
3575
3576
3577
3578
3579
3580
3581
3582
3583
3584
3585
3586
3587
3588
3589
3590
3591
3592
3593
3594
3595
3596
3597
3598
3599
3600
3601
3602
3603
3604
3605
3606
3607
3608
3609
3610
3611
3612
3613
3614
3615
3616
3617
3618
3619
3620
3621
3622
3623
3624
3625
3626
3627
3628
3629
3630
3631
3632
3633
3634
3635
3636
3637
3638
3639
3640
3641
3642
3643
3644
3645
3646
3647
3648
3649
3650
3651
3652
3653
3654
3655
3656
3657
3658
3659
3660
3661
3662
3663
3664
3665
3666
3667
3668
3669
3670
3671
3672
3673
3674
3675
3676
3677
3678
3679
3680
3681
3682
3683
3684
3685
3686
3687
3688
3689
3690
3691
3692
3693
3694
3695
3696
3697
3698
3699
3700
3701
3702
3703
3704
3705
3706
3707
3708
3709
3710
3711
3712
3713
3714
3715
3716
3717
3718
3719
3720
3721
3722
3723
3724
3725
3726
3727
3728
3729
3730
3731
3732
3733
3734
3735
3736
3737
3738
3739
3740
3741
3742
3743
3744
3745
3746
3747
3748
3749
3750
3751
3752
3753
3754
3755
3756
3757
3758
3759
3760
3761
3762
3763
3764
3765
3766
3767
3768
3769
3770
3771
3772
3773
3774
3775
3776
3777
3778
3779
3780
3781
3782
3783
3784
3785
3786
3787
3788
3789
3790
3791
3792
3793
3794
3795
3796
3797
3798
3799
3800
3801
3802
3803
3804
3805
3806
3807
3808
3809
3810
3811
3812
3813
3814
3815
3816
3817
3818
3819
3820
3821
3822
3823
3824
3825
3826
3827
3828
3829
3830
3831
3832
3833
3834
3835
3836
3837
3838
3839
3840
3841
3842
3843
3844
3845
3846
3847
3848
3849
3850
3851
3852
3853
3854
3855
3856
3857
3858
3859
3860
3861
3862
3863
3864
3865
3866
3867
3868
3869
3870
3871
3872
3873
3874
3875
3876
3877
3878
3879
3880
3881
3882
3883
3884
3885
3886
3887
3888
3889
3890
3891
3892
3893
3894
3895
3896
3897
3898
3899
3900
3901
3902
3903
3904
3905
3906
3907
3908
3909
3910
3911
3912
3913
3914
3915
3916
3917
3918
3919
3920
3921
3922
3923
3924
3925
3926
3927
3928
3929
3930
3931
3932
3933
3934
3935
3936
3937
3938
3939
3940
3941
3942
3943
3944
3945
3946
3947
3948
3949
3950
3951
3952
3953
3954
3955
3956
3957
3958
3959
3960
3961
3962
3963
3964
3965
3966
3967
3968
3969
3970
3971
3972
3973
3974
3975
3976
3977
3978
3979
3980
3981
3982
3983
3984
3985
3986
3987
3988
3989
3990
3991
3992
3993
3994
3995
3996
3997
3998
3999
4000
4001
4002
4003
4004
4005
4006
4007
4008
4009
4010
4011
4012
4013
4014
4015
4016
4017
4018
4019
4020
4021
4022
4023
4024
4025
4026
4027
4028
4029
4030
4031
4032
4033
4034
4035
4036
4037
4038
4039
4040
4041
4042
4043
4044
4045
4046
4047
4048
4049
4050
4051
4052
4053
4054
4055
4056
4057
4058
4059
4060
4061
4062
4063
4064
4065
4066
4067
4068
4069
4070
4071
4072
4073
4074
4075
4076
4077
4078
4079
4080
4081
4082
4083
4084
4085
4086
4087
4088
4089
4090
4091
4092
4093
4094
4095
4096
4097
4098
4099
4100
4101
4102
4103
4104
4105
4106
4107
4108
4109
4110
4111
4112
4113
4114
4115
4116
4117
4118
4119
4120
4121
4122
4123
4124
4125
4126
4127
4128
4129
4130
4131
4132
4133
4134
4135
4136
4137
4138
4139
4140
4141
4142
4143
4144
4145
4146
4147
4148
4149
4150
4151
4152
4153
4154
4155
4156
4157
4158
4159
4160
4161
4162
4163
4164
4165
4166
4167
4168
4169
4170
4171
4172
4173
4174
4175
4176
4177
4178
4179
4180
4181
4182
4183
4184
4185
4186
4187
4188
4189
4190
4191
4192
4193
4194
4195
4196
4197
4198
4199
4200
4201
4202
4203
4204
4205
4206
4207
4208
4209
4210
4211
4212
4213
4214
4215
4216
4217
4218
4219
4220
4221
4222
4223
4224
4225
4226
4227
4228
4229
4230
4231
4232
4233
4234
4235
4236
4237
4238
4239
4240
4241
4242
4243
4244
4245
4246
4247
4248
4249
4250
4251
4252
4253
4254
4255
4256
4257
4258
4259
4260
4261
4262
4263
4264
4265
4266
4267
4268
4269
4270
4271
4272
4273
4274
4275
4276
4277
4278
4279
4280
4281
4282
4283
4284
4285
4286
4287
4288
4289
4290
4291
4292
4293
4294
4295
4296
4297
4298
4299
4300
4301
4302
4303
4304
4305
4306
4307
4308
4309
4310
4311
4312
4313
4314
4315
4316
4317
4318
4319
4320
4321
4322
4323
4324
4325
4326
4327
4328
4329
4330
4331
4332
4333
4334
4335
4336
4337
4338
4339
4340
4341
4342
4343
4344
4345
4346
4347
4348
4349
4350
4351
4352
4353
4354
4355
4356
4357
4358
4359
4360
4361
4362
4363
4364
4365
4366
4367
4368
4369
4370
4371
4372
4373
4374
4375
4376
4377
4378
4379
4380
4381
4382
4383
4384
4385
4386
4387
4388
4389
4390
4391
4392
4393
4394
4395
4396
4397
4398
4399
4400
4401
4402
4403
4404
4405
4406
4407
4408
4409
4410
4411
4412
4413
4414
4415
4416
4417
4418
4419
4420
4421
4422
4423
4424
4425
4426
4427
4428
4429
4430
4431
4432
4433
4434
4435
4436
4437
4438
4439
4440
4441
4442
4443
4444
4445
4446
4447
4448
4449
4450
4451
4452
4453
4454
4455
4456
4457
4458
4459
4460
4461
4462
4463
4464
4465
4466
4467
4468
4469
4470
4471
4472
4473
4474
4475
4476
4477
4478
4479
4480
4481
4482
4483
4484
4485
4486
4487
4488
4489
4490
4491
4492
4493
4494
4495
4496
4497
4498
4499
4500
4501
4502
4503
4504
4505
4506
4507
4508
4509
4510
4511
4512
4513
4514
4515
4516
4517
4518
4519
4520
4521
4522
4523
4524
4525
4526
4527
4528
4529
4530
4531
4532
4533
4534
4535
4536
4537
4538
4539
4540
4541
4542
4543
4544
4545
4546
4547
4548
4549
4550
4551
4552
4553
4554
4555
4556
4557
4558
4559
4560
4561
4562
4563
4564
4565
4566
4567
4568
4569
4570
4571
4572
4573
4574
4575
4576
4577
4578
4579
4580
4581
4582
4583
4584
4585
4586
4587
4588
4589
4590
4591
4592
4593
4594
4595
4596
4597
4598
4599
4600
4601
4602
4603
4604
4605
4606
4607
4608
4609
4610
4611
4612
4613
4614
4615
4616
4617
4618
4619
4620
4621
4622
4623
4624
4625
4626
4627
4628
4629
4630
4631
4632
4633
4634
4635
4636
4637
4638
4639
4640
4641
4642
4643
4644
4645
4646
4647
4648
4649
4650
4651
4652
4653
4654
4655
4656
4657
4658
4659
4660
4661
4662
4663
4664
4665
4666
4667
4668
4669
4670
4671
4672
4673
4674
4675
4676
4677
4678
4679
4680
4681
4682
4683
4684
4685
4686
4687
4688
4689
4690
4691
4692
4693
4694
4695
4696
4697
4698
4699
4700
4701
4702
4703
4704
4705
4706
4707
4708
4709
4710
4711
4712
4713
4714
4715
4716
4717
4718
4719
4720
4721
4722
4723
4724
4725
4726
4727
4728
4729
4730
4731
4732
4733
4734
4735
4736
4737
4738
4739
4740
4741
4742
4743
4744
4745
4746
4747
4748
4749
4750
4751
4752
4753
4754
4755
4756
4757
4758
4759
4760
4761
4762
4763
4764
4765
4766
4767
4768
4769
4770
4771
4772
4773
4774
4775
4776
4777
4778
4779
4780
4781
4782
4783
4784
4785
4786
4787
4788
4789
4790
4791
4792
4793
4794
4795
4796
4797
4798
4799
4800
4801
4802
4803
4804
4805
4806
4807
4808
4809
4810
4811
4812
4813
4814
4815
4816
4817
4818
4819
4820
4821
4822
4823
4824
4825
4826
4827
4828
4829
4830
4831
4832
4833
4834
4835
4836
4837
4838
4839
4840
4841
4842
4843
4844
4845
4846
4847
4848
4849
4850
4851
4852
4853
4854
4855
4856
4857
4858
4859
4860
4861
4862
4863
4864
4865
4866
4867
4868
4869
4870
4871
4872
4873
4874
4875
4876
4877
4878
4879
4880
4881
4882
4883
4884
4885
4886
4887
4888
4889
4890
4891
4892
4893
4894
4895
4896
4897
4898
4899
4900
4901
4902
4903
4904
4905
4906
4907
4908
4909
4910
4911
4912
4913
4914
4915
4916
4917
4918
4919
4920
4921
4922
4923
4924
4925
4926
4927
4928
4929
4930
4931
4932
4933
4934
4935
4936
4937
4938
4939
4940
4941
4942
4943
4944
4945
4946
4947
4948
4949
4950
4951
4952
4953
4954
4955
4956
4957
4958
4959
4960
4961
4962
4963
4964
4965
4966
4967
4968
4969
4970
4971
4972
4973
4974
4975
4976
4977
4978
4979
4980
4981
4982
4983
4984
4985
4986
4987
4988
4989
4990
4991
4992
4993
4994
4995
4996
4997
4998
4999
5000
5001
5002
5003
5004
5005
5006
5007
5008
5009
5010
5011
5012
5013
5014
5015
5016
5017
5018
5019
5020
5021
5022
5023
5024
5025
5026
5027
5028
5029
5030
5031
5032
5033
5034
5035
5036
5037
5038
5039
5040
5041
5042
5043
5044
5045
5046
5047
5048
5049
5050
5051
5052
5053
5054
5055
5056
5057
5058
5059
5060
5061
5062
5063
5064
5065
5066
5067
5068
5069
5070
5071
5072
5073
5074
5075
5076
5077
5078
5079
5080
5081
5082
5083
5084
5085
5086
5087
5088
5089
5090
5091
5092
5093
5094
5095
5096
5097
5098
5099
5100
5101
5102
5103
5104
5105
5106
5107
5108
5109
5110
5111
5112
5113
5114
5115
5116
5117
5118
5119
5120
5121
5122
5123
5124
5125
5126
5127
5128
5129
5130
5131
5132
5133
5134
5135
5136
5137
5138
5139
5140
5141
5142
5143
5144
5145
5146
5147
5148
5149
5150
5151
5152
5153
5154
5155
5156
5157
5158
5159
5160
5161
5162
5163
5164
5165
5166
5167
5168
5169
5170
5171
5172
5173
5174
5175
5176
5177
5178
5179
5180
5181
5182
5183
5184
5185
5186
5187
5188
5189
5190
5191
5192
5193
5194
5195
5196
5197
5198
5199
5200
5201
5202
5203
5204
5205
5206
5207
5208
5209
5210
5211
5212
5213
5214
5215
5216
5217
5218
5219
5220
5221
5222
5223
5224
5225
5226
5227
5228
5229
5230
5231
5232
5233
5234
5235
5236
5237
5238
5239
5240
5241
5242
5243
5244
5245
5246
5247
5248
5249
5250
5251
5252
5253
5254
5255
5256
5257
5258
5259
5260
5261
5262
5263
5264
5265
5266
5267
5268
5269
5270
5271
5272
5273
5274
5275
5276
5277
5278
5279
5280
5281
5282
5283
5284
5285
5286
5287
5288
5289
5290
5291
5292
5293
5294
5295
5296
5297
5298
5299
5300
5301
5302
5303
5304
5305
5306
5307
5308
5309
5310
5311
5312
5313
5314
5315
5316
5317
5318
5319
5320
5321
5322
5323
5324
5325
5326
5327
5328
5329
5330
5331
5332
5333
5334
5335
5336
5337
5338
5339
5340
5341
5342
5343
5344
5345
5346
5347
5348
5349
5350
5351
5352
5353
5354
5355
5356
5357
5358
5359
5360
5361
5362
5363
5364
5365
5366
5367
5368
5369
5370
5371
5372
5373
5374
5375
5376
5377
5378
5379
5380
5381
5382
5383
5384
5385
5386
5387
5388
5389
5390
5391
5392
5393
5394
5395
5396
5397
5398
5399
5400
5401
5402
5403
5404
5405
5406
5407
5408
5409
5410
5411
5412
5413
5414
5415
5416
5417
5418
5419
5420
5421
5422
5423
5424
5425
5426
5427
5428
5429
5430
5431
5432
5433
5434
5435
5436
5437
5438
5439
5440
5441
5442
5443
5444
5445
5446
5447
5448
5449
5450
5451
5452
5453
5454
5455
5456
5457
5458
5459
5460
5461
5462
5463
5464
5465
5466
5467
5468
5469
5470
5471
5472
5473
5474
5475
5476
5477
5478
5479
5480
5481
5482
5483
5484
5485
5486
5487
5488
5489
5490
5491
5492
5493
5494
5495
5496
5497
5498
5499
5500
5501
5502
5503
5504
5505
5506
5507
5508
5509
5510
5511
5512
5513
5514
5515
5516
5517
5518
5519
5520
5521
5522
5523
5524
5525
5526
5527
5528
5529
5530
5531
5532
5533
5534
5535
5536
5537
5538
5539
5540
5541
5542
5543
5544
5545
5546
5547
5548
5549
5550
5551
5552
5553
5554
5555
5556
5557
5558
5559
5560
5561
5562
5563
5564
5565
5566
5567
5568
5569
5570
5571
5572
5573
5574
5575
5576
5577
5578
5579
5580
5581
5582
5583
5584
5585
5586
5587
5588
5589
5590
5591
5592
5593
5594
5595
5596
5597
5598
5599
5600
5601
5602
5603
5604
5605
5606
5607
5608
5609
5610
5611
5612
5613
5614
5615
5616
5617
5618
5619
5620
5621
5622
5623
5624
5625
5626
5627
5628
5629
5630
5631
5632
5633
5634
5635
5636
5637
5638
5639
5640
5641
5642
5643
5644
5645
5646
5647
5648
5649
5650
5651
5652
5653
5654
5655
5656
5657
5658
5659
5660
5661
5662
5663
5664
5665
5666
5667
5668
5669
5670
5671
5672
5673
5674
5675
5676
5677
5678
5679
5680
5681
5682
5683
5684
5685
5686
5687
5688
5689
5690
5691
5692
5693
5694
5695
5696
5697
5698
5699
5700
5701
5702
5703
5704
5705
5706
5707
5708
5709
5710
5711
5712
5713
5714
5715
5716
5717
5718
5719
5720
5721
5722
5723
5724
5725
5726
5727
5728
5729
5730
5731
5732
5733
5734
5735
5736
5737
5738
5739
5740
5741
5742
5743
5744
5745
5746
5747
5748
5749
5750
5751
5752
5753
5754
5755
5756
5757
5758
5759
5760
5761
5762
5763
5764
5765
5766
5767
5768
5769
5770
5771
5772
5773
5774
5775
5776
5777
5778
5779
5780
5781
5782
5783
5784
5785
5786
5787
5788
5789
5790
5791
5792
5793
5794
5795
5796
5797
5798
5799
5800
5801
5802
5803
5804
5805
5806
5807
5808
5809
5810
5811
5812
5813
5814
5815
5816
5817
5818
5819
5820
5821
5822
5823
5824
5825
5826
5827
5828
5829
5830
5831
5832
5833
5834
5835
5836
5837
5838
5839
5840
5841
5842
5843
5844
5845
5846
5847
5848
5849
5850
5851
5852
5853
5854
5855
5856
5857
5858
5859
5860
5861
5862
5863
5864
5865
5866
5867
5868
5869
5870
5871
5872
5873
5874
5875
5876
5877
5878
5879
5880
5881
5882
5883
5884
5885
5886
5887
5888
5889
5890
5891
5892
5893
5894
5895
5896
5897
5898
5899
5900
5901
5902
5903
5904
5905
5906
5907
5908
5909
5910
5911
5912
5913
5914
5915
5916
5917
5918
5919
5920
5921
5922
5923
5924
5925
5926
5927
5928
5929
5930
5931
5932
5933
5934
5935
5936
5937
5938
5939
5940
5941
5942
5943
5944
5945
5946
5947
5948
5949
5950
5951
5952
5953
5954
5955
5956
5957
5958
5959
5960
5961
5962
5963
5964
5965
5966
5967
5968
5969
5970
5971
5972
5973
5974
5975
5976
5977
5978
5979
5980
5981
5982
5983
5984
5985
5986
5987
5988
5989
5990
5991
5992
5993
5994
5995
5996
5997
5998
5999
6000
6001
6002
6003
6004
6005
6006
6007
6008
6009
6010
6011
6012
6013
6014
6015
6016
6017
6018
6019
6020
6021
6022
6023
6024
6025
6026
6027
6028
6029
6030
6031
6032
6033
6034
6035
6036
6037
6038
6039
6040
6041
6042
6043
6044
6045
6046
6047
6048
6049
6050
6051
6052
6053
6054
6055
6056
6057
6058
6059
6060
6061
6062
6063
6064
6065
6066
6067
6068
6069
6070
6071
6072
6073
6074
6075
6076
6077
6078
6079
6080
6081
6082
6083
6084
6085
6086
6087
6088
6089
6090
6091
6092
6093
6094
6095
6096
6097
6098
6099
6100
6101
6102
6103
6104
6105
6106
6107
6108
6109
6110
6111
6112
6113
6114
6115
6116
6117
6118
6119
6120
6121
6122
6123
6124
6125
6126
6127
6128
6129
6130
6131
6132
6133
6134
6135
6136
6137
6138
6139
6140
6141
6142
6143
6144
6145
6146
6147
6148
6149
6150
6151
6152
6153
6154
6155
6156
6157
6158
6159
6160
6161
6162
6163
6164
6165
6166
6167
6168
6169
6170
6171
6172
6173
6174
6175
6176
6177
6178
6179
6180
6181
6182
6183
6184
6185
6186
6187
6188
6189
6190
6191
6192
6193
6194
6195
6196
6197
6198
6199
6200
6201
6202
6203
6204
6205
6206
6207
6208
6209
6210
6211
6212
6213
6214
6215
6216
6217
6218
6219
6220
6221
6222
6223
6224
6225
6226
6227
6228
6229
6230
6231
6232
6233
6234
6235
6236
6237
6238
6239
6240
6241
6242
6243
6244
6245
6246
6247
6248
6249
6250
6251
6252
6253
6254
6255
6256
6257
6258
6259
6260
6261
6262
6263
6264
6265
6266
6267
6268
6269
6270
6271
6272
6273
6274
6275
6276
6277
6278
6279
6280
// SPDX-License-Identifier: GPL-2.0-only
/*
 * Copyright 2002-2005, Instant802 Networks, Inc.
 * Copyright 2005-2006, Devicescape Software, Inc.
 * Copyright 2006-2007        Jiri Benc <jbenc@suse.cz>
 * Copyright 2007        Johannes Berg <johannes@sipsolutions.net>
 * Copyright 2013-2014  Intel Mobile Communications GmbH
 * Copyright (C) 2018-2024 Intel Corporation
 *
 * Transmit and frame generation functions.
 */

#include <linux/kernel.h>
#include <linux/slab.h>
#include <linux/skbuff.h>
#include <linux/if_vlan.h>
#include <linux/etherdevice.h>
#include <linux/bitmap.h>
#include <linux/rcupdate.h>
#include <linux/export.h>
#include <net/net_namespace.h>
#include <net/ieee80211_radiotap.h>
#include <net/cfg80211.h>
#include <net/mac80211.h>
#include <net/codel.h>
#include <net/codel_impl.h>
#include <linux/unaligned.h>
#include <net/fq_impl.h>
#include <net/gso.h>

#include "ieee80211_i.h"
#include "driver-ops.h"
#include "led.h"
#include "mesh.h"
#include "wep.h"
#include "wpa.h"
#include "wme.h"
#include "rate.h"

/* misc utils */

static __le16 ieee80211_duration(struct ieee80211_tx_data *tx,
                                 struct sk_buff *skb, int group_addr,
                                 int next_frag_len)
{
        int rate, mrate, erp, dur, i;
        struct ieee80211_rate *txrate;
        struct ieee80211_local *local = tx->local;
        struct ieee80211_supported_band *sband;
        struct ieee80211_hdr *hdr;
        struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb);
        struct ieee80211_chanctx_conf *chanctx_conf;
        u32 rate_flags = 0;

        /* assume HW handles this */
        if (tx->rate.flags & (IEEE80211_TX_RC_MCS | IEEE80211_TX_RC_VHT_MCS))
                return 0;

        rcu_read_lock();
        chanctx_conf = rcu_dereference(tx->sdata->vif.bss_conf.chanctx_conf);
        if (chanctx_conf)
                rate_flags = ieee80211_chandef_rate_flags(&chanctx_conf->def);
        rcu_read_unlock();

        /* uh huh? */
        if (WARN_ON_ONCE(tx->rate.idx < 0))
                return 0;

        sband = local->hw.wiphy->bands[info->band];
        txrate = &sband->bitrates[tx->rate.idx];

        erp = txrate->flags & IEEE80211_RATE_ERP_G;

        /* device is expected to do this */
        if (sband->band == NL80211_BAND_S1GHZ)
                return 0;

        /*
         * data and mgmt (except PS Poll):
         * - during CFP: 32768
         * - during contention period:
         *   if addr1 is group address: 0
         *   if more fragments = 0 and addr1 is individual address: time to
         *      transmit one ACK plus SIFS
         *   if more fragments = 1 and addr1 is individual address: time to
         *      transmit next fragment plus 2 x ACK plus 3 x SIFS
         *
         * IEEE 802.11, 9.6:
         * - control response frame (CTS or ACK) shall be transmitted using the
         *   same rate as the immediately previous frame in the frame exchange
         *   sequence, if this rate belongs to the PHY mandatory rates, or else
         *   at the highest possible rate belonging to the PHY rates in the
         *   BSSBasicRateSet
         */
        hdr = (struct ieee80211_hdr *)skb->data;
        if (ieee80211_is_ctl(hdr->frame_control)) {
                /* TODO: These control frames are not currently sent by
                 * mac80211, but should they be implemented, this function
                 * needs to be updated to support duration field calculation.
                 *
                 * RTS: time needed to transmit pending data/mgmt frame plus
                 *    one CTS frame plus one ACK frame plus 3 x SIFS
                 * CTS: duration of immediately previous RTS minus time
                 *    required to transmit CTS and its SIFS
                 * ACK: 0 if immediately previous directed data/mgmt had
                 *    more=0, with more=1 duration in ACK frame is duration
                 *    from previous frame minus time needed to transmit ACK
                 *    and its SIFS
                 * PS Poll: BIT(15) | BIT(14) | aid
                 */
                return 0;
        }

        /* data/mgmt */
        if (0 /* FIX: data/mgmt during CFP */)
                return cpu_to_le16(32768);

        if (group_addr) /* Group address as the destination - no ACK */
                return 0;

        /* Individual destination address:
         * IEEE 802.11, Ch. 9.6 (after IEEE 802.11g changes)
         * CTS and ACK frames shall be transmitted using the highest rate in
         * basic rate set that is less than or equal to the rate of the
         * immediately previous frame and that is using the same modulation
         * (CCK or OFDM). If no basic rate set matches with these requirements,
         * the highest mandatory rate of the PHY that is less than or equal to
         * the rate of the previous frame is used.
         * Mandatory rates for IEEE 802.11g PHY: 1, 2, 5.5, 11, 6, 12, 24 Mbps
         */
        rate = -1;
        /* use lowest available if everything fails */
        mrate = sband->bitrates[0].bitrate;
        for (i = 0; i < sband->n_bitrates; i++) {
                struct ieee80211_rate *r = &sband->bitrates[i];
                u32 flag;

                if (r->bitrate > txrate->bitrate)
                        break;

                if ((rate_flags & r->flags) != rate_flags)
                        continue;

                if (tx->sdata->vif.bss_conf.basic_rates & BIT(i))
                        rate = r->bitrate;

                switch (sband->band) {
                case NL80211_BAND_2GHZ:
                case NL80211_BAND_LC:
                        if (tx->sdata->deflink.operating_11g_mode)
                                flag = IEEE80211_RATE_MANDATORY_G;
                        else
                                flag = IEEE80211_RATE_MANDATORY_B;
                        break;
                case NL80211_BAND_5GHZ:
                case NL80211_BAND_6GHZ:
                        flag = IEEE80211_RATE_MANDATORY_A;
                        break;
                default:
                        flag = 0;
                        WARN_ON(1);
                        break;
                }

                if (r->flags & flag)
                        mrate = r->bitrate;
        }
        if (rate == -1) {
                /* No matching basic rate found; use highest suitable mandatory
                 * PHY rate */
                rate = mrate;
        }

        /* Don't calculate ACKs for QoS Frames with NoAck Policy set */
        if (ieee80211_is_data_qos(hdr->frame_control) &&
            *(ieee80211_get_qos_ctl(hdr)) & IEEE80211_QOS_CTL_ACK_POLICY_NOACK)
                dur = 0;
        else
                /* Time needed to transmit ACK
                 * (10 bytes + 4-byte FCS = 112 bits) plus SIFS; rounded up
                 * to closest integer */
                dur = ieee80211_frame_duration(sband->band, 10, rate, erp,
                                tx->sdata->vif.bss_conf.use_short_preamble);

        if (next_frag_len) {
                /* Frame is fragmented: duration increases with time needed to
                 * transmit next fragment plus ACK and 2 x SIFS. */
                dur *= 2; /* ACK + SIFS */
                /* next fragment */
                dur += ieee80211_frame_duration(sband->band, next_frag_len,
                                txrate->bitrate, erp,
                                tx->sdata->vif.bss_conf.use_short_preamble);
        }

        return cpu_to_le16(dur);
}

/* tx handlers */
static ieee80211_tx_result debug_noinline
ieee80211_tx_h_dynamic_ps(struct ieee80211_tx_data *tx)
{
        struct ieee80211_local *local = tx->local;
        struct ieee80211_if_managed *ifmgd;
        struct ieee80211_tx_info *info = IEEE80211_SKB_CB(tx->skb);

        /* driver doesn't support power save */
        if (!ieee80211_hw_check(&local->hw, SUPPORTS_PS))
                return TX_CONTINUE;

        /* hardware does dynamic power save */
        if (ieee80211_hw_check(&local->hw, SUPPORTS_DYNAMIC_PS))
                return TX_CONTINUE;

        /* dynamic power save disabled */
        if (local->hw.conf.dynamic_ps_timeout <= 0)
                return TX_CONTINUE;

        /* we are scanning, don't enable power save */
        if (local->scanning)
                return TX_CONTINUE;

        if (!local->ps_sdata)
                return TX_CONTINUE;

        /* No point if we're going to suspend */
        if (local->quiescing)
                return TX_CONTINUE;

        /* dynamic ps is supported only in managed mode */
        if (tx->sdata->vif.type != NL80211_IFTYPE_STATION)
                return TX_CONTINUE;

        if (unlikely(info->flags & IEEE80211_TX_INTFL_OFFCHAN_TX_OK))
                return TX_CONTINUE;

        ifmgd = &tx->sdata->u.mgd;

        /*
         * Don't wakeup from power save if u-apsd is enabled, voip ac has
         * u-apsd enabled and the frame is in voip class. This effectively
         * means that even if all access categories have u-apsd enabled, in
         * practise u-apsd is only used with the voip ac. This is a
         * workaround for the case when received voip class packets do not
         * have correct qos tag for some reason, due the network or the
         * peer application.
         *
         * Note: ifmgd->uapsd_queues access is racy here. If the value is
         * changed via debugfs, user needs to reassociate manually to have
         * everything in sync.
         */
        if ((ifmgd->flags & IEEE80211_STA_UAPSD_ENABLED) &&
            (ifmgd->uapsd_queues & IEEE80211_WMM_IE_STA_QOSINFO_AC_VO) &&
            skb_get_queue_mapping(tx->skb) == IEEE80211_AC_VO)
                return TX_CONTINUE;

        if (local->hw.conf.flags & IEEE80211_CONF_PS) {
                ieee80211_stop_queues_by_reason(&local->hw,
                                                IEEE80211_MAX_QUEUE_MAP,
                                                IEEE80211_QUEUE_STOP_REASON_PS,
                                                false);
                ifmgd->flags &= ~IEEE80211_STA_NULLFUNC_ACKED;
                wiphy_work_queue(local->hw.wiphy,
                                 &local->dynamic_ps_disable_work);
        }

        /* Don't restart the timer if we're not disassociated */
        if (!ifmgd->associated)
                return TX_CONTINUE;

        mod_timer(&local->dynamic_ps_timer, jiffies +
                  msecs_to_jiffies(local->hw.conf.dynamic_ps_timeout));

        return TX_CONTINUE;
}

static ieee80211_tx_result debug_noinline
ieee80211_tx_h_check_assoc(struct ieee80211_tx_data *tx)
{

        struct ieee80211_hdr *hdr = (struct ieee80211_hdr *)tx->skb->data;
        struct ieee80211_tx_info *info = IEEE80211_SKB_CB(tx->skb);
        bool assoc = false;

        if (unlikely(info->flags & IEEE80211_TX_CTL_INJECTED))
                return TX_CONTINUE;

        if (unlikely(test_bit(SCAN_SW_SCANNING, &tx->local->scanning)) &&
            test_bit(SDATA_STATE_OFFCHANNEL, &tx->sdata->state) &&
            !ieee80211_is_probe_req(hdr->frame_control) &&
            !ieee80211_is_any_nullfunc(hdr->frame_control))
                /*
                 * When software scanning only nullfunc frames (to notify
                 * the sleep state to the AP) and probe requests (for the
                 * active scan) are allowed, all other frames should not be
                 * sent and we should not get here, but if we do
                 * nonetheless, drop them to avoid sending them
                 * off-channel. See the link below and
                 * ieee80211_start_scan() for more.
                 *
                 * http://article.gmane.org/gmane.linux.kernel.wireless.general/30089
                 */
                return TX_DROP;

        if (tx->sdata->vif.type == NL80211_IFTYPE_OCB)
                return TX_CONTINUE;

        if (tx->flags & IEEE80211_TX_PS_BUFFERED)
                return TX_CONTINUE;

        if (tx->sta)
                assoc = test_sta_flag(tx->sta, WLAN_STA_ASSOC);

        if (likely(tx->flags & IEEE80211_TX_UNICAST)) {
                if (unlikely(!assoc &&
                             ieee80211_is_data(hdr->frame_control))) {
#ifdef CONFIG_MAC80211_VERBOSE_DEBUG
                        sdata_info(tx->sdata,
                                   "dropped data frame to not associated station %pM\n",
                                   hdr->addr1);
#endif
                        I802_DEBUG_INC(tx->local->tx_handlers_drop_not_assoc);
                        return TX_DROP;
                }
        } else if (unlikely(ieee80211_is_data(hdr->frame_control) &&
                            ieee80211_vif_get_num_mcast_if(tx->sdata) == 0)) {
                /*
                 * No associated STAs - no need to send multicast
                 * frames.
                 */
                return TX_DROP;
        }

        return TX_CONTINUE;
}

/* This function is called whenever the AP is about to exceed the maximum limit
 * of buffered frames for power saving STAs. This situation should not really
 * happen often during normal operation, so dropping the oldest buffered packet
 * from each queue should be OK to make some room for new frames. */
static void purge_old_ps_buffers(struct ieee80211_local *local)
{
        int total = 0, purged = 0;
        struct sk_buff *skb;
        struct ieee80211_sub_if_data *sdata;
        struct sta_info *sta;

        list_for_each_entry_rcu(sdata, &local->interfaces, list) {
                struct ps_data *ps;

                if (sdata->vif.type == NL80211_IFTYPE_AP)
                        ps = &sdata->u.ap.ps;
                else if (ieee80211_vif_is_mesh(&sdata->vif))
                        ps = &sdata->u.mesh.ps;
                else
                        continue;

                skb = skb_dequeue(&ps->bc_buf);
                if (skb) {
                        purged++;
                        ieee80211_free_txskb(&local->hw, skb);
                }
                total += skb_queue_len(&ps->bc_buf);
        }

        /*
         * Drop one frame from each station from the lowest-priority
         * AC that has frames at all.
         */
        list_for_each_entry_rcu(sta, &local->sta_list, list) {
                int ac;

                for (ac = IEEE80211_AC_BK; ac >= IEEE80211_AC_VO; ac--) {
                        skb = skb_dequeue(&sta->ps_tx_buf[ac]);
                        total += skb_queue_len(&sta->ps_tx_buf[ac]);
                        if (skb) {
                                purged++;
                                ieee80211_free_txskb(&local->hw, skb);
                                break;
                        }
                }
        }

        local->total_ps_buffered = total;
        ps_dbg_hw(&local->hw, "PS buffers full - purged %d frames\n", purged);
}

static ieee80211_tx_result
ieee80211_tx_h_multicast_ps_buf(struct ieee80211_tx_data *tx)
{
        struct ieee80211_tx_info *info = IEEE80211_SKB_CB(tx->skb);
        struct ieee80211_hdr *hdr = (struct ieee80211_hdr *)tx->skb->data;
        struct ps_data *ps;

        /*
         * broadcast/multicast frame
         *
         * If any of the associated/peer stations is in power save mode,
         * the frame is buffered to be sent after DTIM beacon frame.
         * This is done either by the hardware or us.
         */

        /* powersaving STAs currently only in AP/VLAN/mesh mode */
        if (tx->sdata->vif.type == NL80211_IFTYPE_AP ||
            tx->sdata->vif.type == NL80211_IFTYPE_AP_VLAN) {
                if (!tx->sdata->bss)
                        return TX_CONTINUE;

                ps = &tx->sdata->bss->ps;
        } else if (ieee80211_vif_is_mesh(&tx->sdata->vif)) {
                ps = &tx->sdata->u.mesh.ps;
        } else {
                return TX_CONTINUE;
        }


        /* no buffering for ordered frames */
        if (ieee80211_has_order(hdr->frame_control))
                return TX_CONTINUE;

        if (ieee80211_is_probe_req(hdr->frame_control))
                return TX_CONTINUE;

        if (ieee80211_hw_check(&tx->local->hw, QUEUE_CONTROL))
                info->hw_queue = tx->sdata->vif.cab_queue;

        /* no stations in PS mode and no buffered packets */
        if (!atomic_read(&ps->num_sta_ps) && skb_queue_empty(&ps->bc_buf))
                return TX_CONTINUE;

        info->flags |= IEEE80211_TX_CTL_SEND_AFTER_DTIM;

        /* device releases frame after DTIM beacon */
        if (!ieee80211_hw_check(&tx->local->hw, HOST_BROADCAST_PS_BUFFERING))
                return TX_CONTINUE;

        /* buffered in mac80211 */
        if (tx->local->total_ps_buffered >= TOTAL_MAX_TX_BUFFER)
                purge_old_ps_buffers(tx->local);

        if (skb_queue_len(&ps->bc_buf) >= AP_MAX_BC_BUFFER) {
                ps_dbg(tx->sdata,
                       "BC TX buffer full - dropping the oldest frame\n");
                ieee80211_free_txskb(&tx->local->hw, skb_dequeue(&ps->bc_buf));
        } else
                tx->local->total_ps_buffered++;

        skb_queue_tail(&ps->bc_buf, tx->skb);

        return TX_QUEUED;
}

static int ieee80211_use_mfp(__le16 fc, struct sta_info *sta,
                             struct sk_buff *skb)
{
        if (!ieee80211_is_mgmt(fc))
                return 0;

        if (sta == NULL || !test_sta_flag(sta, WLAN_STA_MFP))
                return 0;

        if (!ieee80211_is_robust_mgmt_frame(skb))
                return 0;

        return 1;
}

static ieee80211_tx_result
ieee80211_tx_h_unicast_ps_buf(struct ieee80211_tx_data *tx)
{
        struct sta_info *sta = tx->sta;
        struct ieee80211_tx_info *info = IEEE80211_SKB_CB(tx->skb);
        struct ieee80211_hdr *hdr = (struct ieee80211_hdr *)tx->skb->data;
        struct ieee80211_local *local = tx->local;

        if (unlikely(!sta))
                return TX_CONTINUE;

        if (unlikely((test_sta_flag(sta, WLAN_STA_PS_STA) ||
                      test_sta_flag(sta, WLAN_STA_PS_DRIVER) ||
                      test_sta_flag(sta, WLAN_STA_PS_DELIVER)) &&
                     !(info->flags & IEEE80211_TX_CTL_NO_PS_BUFFER))) {
                int ac = skb_get_queue_mapping(tx->skb);

                if (ieee80211_is_mgmt(hdr->frame_control) &&
                    !ieee80211_is_bufferable_mmpdu(tx->skb)) {
                        info->flags |= IEEE80211_TX_CTL_NO_PS_BUFFER;
                        return TX_CONTINUE;
                }

                ps_dbg(sta->sdata, "STA %pM aid %d: PS buffer for AC %d\n",
                       sta->sta.addr, sta->sta.aid, ac);
                if (tx->local->total_ps_buffered >= TOTAL_MAX_TX_BUFFER)
                        purge_old_ps_buffers(tx->local);

                /* sync with ieee80211_sta_ps_deliver_wakeup */
                spin_lock(&sta->ps_lock);
                /*
                 * STA woke up the meantime and all the frames on ps_tx_buf have
                 * been queued to pending queue. No reordering can happen, go
                 * ahead and Tx the packet.
                 */
                if (!test_sta_flag(sta, WLAN_STA_PS_STA) &&
                    !test_sta_flag(sta, WLAN_STA_PS_DRIVER) &&
                    !test_sta_flag(sta, WLAN_STA_PS_DELIVER)) {
                        spin_unlock(&sta->ps_lock);
                        return TX_CONTINUE;
                }

                if (skb_queue_len(&sta->ps_tx_buf[ac]) >= STA_MAX_TX_BUFFER) {
                        struct sk_buff *old = skb_dequeue(&sta->ps_tx_buf[ac]);
                        ps_dbg(tx->sdata,
                               "STA %pM TX buffer for AC %d full - dropping oldest frame\n",
                               sta->sta.addr, ac);
                        ieee80211_free_txskb(&local->hw, old);
                } else
                        tx->local->total_ps_buffered++;

                info->control.jiffies = jiffies;
                info->control.vif = &tx->sdata->vif;
                info->control.flags |= IEEE80211_TX_INTCFL_NEED_TXPROCESSING;
                info->flags &= ~IEEE80211_TX_TEMPORARY_FLAGS;
                skb_queue_tail(&sta->ps_tx_buf[ac], tx->skb);
                spin_unlock(&sta->ps_lock);

                if (!timer_pending(&local->sta_cleanup))
                        mod_timer(&local->sta_cleanup,
                                  round_jiffies(jiffies +
                                                STA_INFO_CLEANUP_INTERVAL));

                /*
                 * We queued up some frames, so the TIM bit might
                 * need to be set, recalculate it.
                 */
                sta_info_recalc_tim(sta);

                return TX_QUEUED;
        } else if (unlikely(test_sta_flag(sta, WLAN_STA_PS_STA))) {
                ps_dbg(tx->sdata,
                       "STA %pM in PS mode, but polling/in SP -> send frame\n",
                       sta->sta.addr);
        }

        return TX_CONTINUE;
}

static ieee80211_tx_result debug_noinline
ieee80211_tx_h_ps_buf(struct ieee80211_tx_data *tx)
{
        if (unlikely(tx->flags & IEEE80211_TX_PS_BUFFERED))
                return TX_CONTINUE;

        if (tx->flags & IEEE80211_TX_UNICAST)
                return ieee80211_tx_h_unicast_ps_buf(tx);
        else
                return ieee80211_tx_h_multicast_ps_buf(tx);
}

static ieee80211_tx_result debug_noinline
ieee80211_tx_h_check_control_port_protocol(struct ieee80211_tx_data *tx)
{
        struct ieee80211_tx_info *info = IEEE80211_SKB_CB(tx->skb);

        if (unlikely(tx->sdata->control_port_protocol == tx->skb->protocol)) {
                if (tx->sdata->control_port_no_encrypt)
                        info->flags |= IEEE80211_TX_INTFL_DONT_ENCRYPT;
                info->control.flags |= IEEE80211_TX_CTRL_PORT_CTRL_PROTO;
                info->flags |= IEEE80211_TX_CTL_USE_MINRATE;
        }

        return TX_CONTINUE;
}

static struct ieee80211_key *
ieee80211_select_link_key(struct ieee80211_tx_data *tx)
{
        struct ieee80211_hdr *hdr = (struct ieee80211_hdr *)tx->skb->data;
        struct ieee80211_tx_info *info = IEEE80211_SKB_CB(tx->skb);
        struct ieee80211_link_data *link;
        unsigned int link_id;

        link_id = u32_get_bits(info->control.flags, IEEE80211_TX_CTRL_MLO_LINK);
        if (link_id == IEEE80211_LINK_UNSPECIFIED) {
                link = &tx->sdata->deflink;
        } else {
                link = rcu_dereference(tx->sdata->link[link_id]);
                if (!link)
                        return NULL;
        }

        if (ieee80211_is_group_privacy_action(tx->skb))
                return rcu_dereference(link->default_multicast_key);
        else if (ieee80211_is_mgmt(hdr->frame_control) &&
                 is_multicast_ether_addr(hdr->addr1) &&
                 ieee80211_is_robust_mgmt_frame(tx->skb))
                return rcu_dereference(link->default_mgmt_key);
        else if (is_multicast_ether_addr(hdr->addr1))
                return rcu_dereference(link->default_multicast_key);

        return NULL;
}

static ieee80211_tx_result debug_noinline
ieee80211_tx_h_select_key(struct ieee80211_tx_data *tx)
{
        struct ieee80211_key *key;
        struct ieee80211_tx_info *info = IEEE80211_SKB_CB(tx->skb);
        struct ieee80211_hdr *hdr = (struct ieee80211_hdr *)tx->skb->data;

        if (unlikely(info->flags & IEEE80211_TX_INTFL_DONT_ENCRYPT)) {
                tx->key = NULL;
                return TX_CONTINUE;
        }

        if (tx->sta &&
            (key = rcu_dereference(tx->sta->ptk[tx->sta->ptk_idx])))
                tx->key = key;
        else if ((key = ieee80211_select_link_key(tx)))
                tx->key = key;
        else if (!is_multicast_ether_addr(hdr->addr1) &&
                 (key = rcu_dereference(tx->sdata->default_unicast_key)))
                tx->key = key;
        else
                tx->key = NULL;

        if (tx->key) {
                bool skip_hw = false;

                /* TODO: add threshold stuff again */

                switch (tx->key->conf.cipher) {
                case WLAN_CIPHER_SUITE_WEP40:
                case WLAN_CIPHER_SUITE_WEP104:
                case WLAN_CIPHER_SUITE_TKIP:
                        if (!ieee80211_is_data_present(hdr->frame_control))
                                tx->key = NULL;
                        break;
                case WLAN_CIPHER_SUITE_CCMP:
                case WLAN_CIPHER_SUITE_CCMP_256:
                case WLAN_CIPHER_SUITE_GCMP:
                case WLAN_CIPHER_SUITE_GCMP_256:
                        if (!ieee80211_is_data_present(hdr->frame_control) &&
                            !ieee80211_use_mfp(hdr->frame_control, tx->sta,
                                               tx->skb) &&
                            !ieee80211_is_group_privacy_action(tx->skb))
                                tx->key = NULL;
                        else
                                skip_hw = (tx->key->conf.flags &
                                           IEEE80211_KEY_FLAG_SW_MGMT_TX) &&
                                        ieee80211_is_mgmt(hdr->frame_control);
                        break;
                case WLAN_CIPHER_SUITE_AES_CMAC:
                case WLAN_CIPHER_SUITE_BIP_CMAC_256:
                case WLAN_CIPHER_SUITE_BIP_GMAC_128:
                case WLAN_CIPHER_SUITE_BIP_GMAC_256:
                        if (!ieee80211_is_mgmt(hdr->frame_control))
                                tx->key = NULL;
                        break;
                }

                if (unlikely(tx->key && tx->key->flags & KEY_FLAG_TAINTED &&
                             !ieee80211_is_deauth(hdr->frame_control)) &&
                             tx->skb->protocol != tx->sdata->control_port_protocol)
                        return TX_DROP;

                if (!skip_hw && tx->key &&
                    tx->key->flags & KEY_FLAG_UPLOADED_TO_HARDWARE)
                        info->control.hw_key = &tx->key->conf;
        } else if (ieee80211_is_data_present(hdr->frame_control) && tx->sta &&
                   test_sta_flag(tx->sta, WLAN_STA_USES_ENCRYPTION)) {
                return TX_DROP;
        }

        return TX_CONTINUE;
}

static ieee80211_tx_result debug_noinline
ieee80211_tx_h_rate_ctrl(struct ieee80211_tx_data *tx)
{
        struct ieee80211_tx_info *info = IEEE80211_SKB_CB(tx->skb);
        struct ieee80211_hdr *hdr = (void *)tx->skb->data;
        struct ieee80211_supported_band *sband;
        u32 len;
        struct ieee80211_tx_rate_control txrc;
        struct ieee80211_sta_rates *ratetbl = NULL;
        bool encap = info->flags & IEEE80211_TX_CTL_HW_80211_ENCAP;
        bool assoc = false;

        memset(&txrc, 0, sizeof(txrc));

        sband = tx->local->hw.wiphy->bands[info->band];

        len = min_t(u32, tx->skb->len + FCS_LEN,
                         tx->local->hw.wiphy->frag_threshold);

        /* set up the tx rate control struct we give the RC algo */
        txrc.hw = &tx->local->hw;
        txrc.sband = sband;
        txrc.bss_conf = &tx->sdata->vif.bss_conf;
        txrc.skb = tx->skb;
        txrc.reported_rate.idx = -1;

        if (unlikely(info->control.flags & IEEE80211_TX_CTRL_DONT_USE_RATE_MASK)) {
                txrc.rate_idx_mask = ~0;
        } else {
                txrc.rate_idx_mask = tx->sdata->rc_rateidx_mask[info->band];

                if (tx->sdata->rc_has_mcs_mask[info->band])
                        txrc.rate_idx_mcs_mask =
                                tx->sdata->rc_rateidx_mcs_mask[info->band];
        }

        txrc.bss = (tx->sdata->vif.type == NL80211_IFTYPE_AP ||
                    tx->sdata->vif.type == NL80211_IFTYPE_MESH_POINT ||
                    tx->sdata->vif.type == NL80211_IFTYPE_ADHOC ||
                    tx->sdata->vif.type == NL80211_IFTYPE_OCB);

        /* set up RTS protection if desired */
        if (len > tx->local->hw.wiphy->rts_threshold) {
                txrc.rts = true;
        }

        info->control.use_rts = txrc.rts;
        info->control.use_cts_prot = tx->sdata->vif.bss_conf.use_cts_prot;

        /*
         * Use short preamble if the BSS can handle it, but not for
         * management frames unless we know the receiver can handle
         * that -- the management frame might be to a station that
         * just wants a probe response.
         */
        if (tx->sdata->vif.bss_conf.use_short_preamble &&
            (ieee80211_is_tx_data(tx->skb) ||
             (tx->sta && test_sta_flag(tx->sta, WLAN_STA_SHORT_PREAMBLE))))
                txrc.short_preamble = true;

        info->control.short_preamble = txrc.short_preamble;

        /* don't ask rate control when rate already injected via radiotap */
        if (info->control.flags & IEEE80211_TX_CTRL_RATE_INJECT)
                return TX_CONTINUE;

        if (tx->sta)
                assoc = test_sta_flag(tx->sta, WLAN_STA_ASSOC);

        /*
         * Lets not bother rate control if we're associated and cannot
         * talk to the sta. This should not happen.
         */
        if (WARN(test_bit(SCAN_SW_SCANNING, &tx->local->scanning) && assoc &&
                 !rate_usable_index_exists(sband, &tx->sta->sta),
                 "%s: Dropped data frame as no usable bitrate found while "
                 "scanning and associated. Target station: "
                 "%pM on %d GHz band\n",
                 tx->sdata->name,
                 encap ? ((struct ethhdr *)hdr)->h_dest : hdr->addr1,
                 info->band ? 5 : 2))
                return TX_DROP;

        /*
         * If we're associated with the sta at this point we know we can at
         * least send the frame at the lowest bit rate.
         */
        rate_control_get_rate(tx->sdata, tx->sta, &txrc);

        if (tx->sta && !info->control.skip_table)
                ratetbl = rcu_dereference(tx->sta->sta.rates);

        if (unlikely(info->control.rates[0].idx < 0)) {
                if (ratetbl) {
                        struct ieee80211_tx_rate rate = {
                                .idx = ratetbl->rate[0].idx,
                                .flags = ratetbl->rate[0].flags,
                                .count = ratetbl->rate[0].count
                        };

                        if (ratetbl->rate[0].idx < 0)
                                return TX_DROP;

                        tx->rate = rate;
                } else {
                        return TX_DROP;
                }
        } else {
                tx->rate = info->control.rates[0];
        }

        if (txrc.reported_rate.idx < 0) {
                txrc.reported_rate = tx->rate;
                if (tx->sta && ieee80211_is_tx_data(tx->skb))
                        tx->sta->deflink.tx_stats.last_rate = txrc.reported_rate;
        } else if (tx->sta)
                tx->sta->deflink.tx_stats.last_rate = txrc.reported_rate;

        if (ratetbl)
                return TX_CONTINUE;

        if (unlikely(!info->control.rates[0].count))
                info->control.rates[0].count = 1;

        if (WARN_ON_ONCE((info->control.rates[0].count > 1) &&
                         (info->flags & IEEE80211_TX_CTL_NO_ACK)))
                info->control.rates[0].count = 1;

        return TX_CONTINUE;
}

static __le16 ieee80211_tx_next_seq(struct sta_info *sta, int tid)
{
        u16 *seq = &sta->tid_seq[tid];
        __le16 ret = cpu_to_le16(*seq);

        /* Increase the sequence number. */
        *seq = (*seq + 0x10) & IEEE80211_SCTL_SEQ;

        return ret;
}

static ieee80211_tx_result debug_noinline
ieee80211_tx_h_sequence(struct ieee80211_tx_data *tx)
{
        struct ieee80211_tx_info *info = IEEE80211_SKB_CB(tx->skb);
        struct ieee80211_hdr *hdr = (struct ieee80211_hdr *)tx->skb->data;
        int tid;

        /*
         * Packet injection may want to control the sequence
         * number, if we have no matching interface then we
         * neither assign one ourselves nor ask the driver to.
         */
        if (unlikely(info->control.vif->type == NL80211_IFTYPE_MONITOR))
                return TX_CONTINUE;

        if (unlikely(ieee80211_is_ctl(hdr->frame_control)))
                return TX_CONTINUE;

        if (ieee80211_hdrlen(hdr->frame_control) < 24)
                return TX_CONTINUE;

        if (ieee80211_is_qos_nullfunc(hdr->frame_control))
                return TX_CONTINUE;

        if (info->control.flags & IEEE80211_TX_CTRL_NO_SEQNO)
                return TX_CONTINUE;

        /* SNS11 from 802.11be 10.3.2.14 */
        if (unlikely(is_multicast_ether_addr(hdr->addr1) &&
                     ieee80211_vif_is_mld(info->control.vif) &&
                     info->control.vif->type == NL80211_IFTYPE_AP)) {
                if (info->control.flags & IEEE80211_TX_CTRL_MCAST_MLO_FIRST_TX)
                        tx->sdata->mld_mcast_seq += 0x10;
                hdr->seq_ctrl = cpu_to_le16(tx->sdata->mld_mcast_seq);
                return TX_CONTINUE;
        }

        /*
         * Anything but QoS data that has a sequence number field
         * (is long enough) gets a sequence number from the global
         * counter.  QoS data frames with a multicast destination
         * also use the global counter (802.11-2012 9.3.2.10).
         */
        if (!ieee80211_is_data_qos(hdr->frame_control) ||
            is_multicast_ether_addr(hdr->addr1)) {
                /* driver should assign sequence number */
                info->flags |= IEEE80211_TX_CTL_ASSIGN_SEQ;
                /* for pure STA mode without beacons, we can do it */
                hdr->seq_ctrl = cpu_to_le16(tx->sdata->sequence_number);
                tx->sdata->sequence_number += 0x10;
                if (tx->sta)
                        tx->sta->deflink.tx_stats.msdu[IEEE80211_NUM_TIDS]++;
                return TX_CONTINUE;
        }

        /*
         * This should be true for injected/management frames only, for
         * management frames we have set the IEEE80211_TX_CTL_ASSIGN_SEQ
         * above since they are not QoS-data frames.
         */
        if (!tx->sta)
                return TX_CONTINUE;

        /* include per-STA, per-TID sequence counter */
        tid = ieee80211_get_tid(hdr);
        tx->sta->deflink.tx_stats.msdu[tid]++;

        hdr->seq_ctrl = ieee80211_tx_next_seq(tx->sta, tid);

        return TX_CONTINUE;
}

static int ieee80211_fragment(struct ieee80211_tx_data *tx,
                              struct sk_buff *skb, int hdrlen,
                              int frag_threshold)
{
        struct ieee80211_local *local = tx->local;
        struct ieee80211_tx_info *info;
        struct sk_buff *tmp;
        int per_fragm = frag_threshold - hdrlen - FCS_LEN;
        int pos = hdrlen + per_fragm;
        int rem = skb->len - hdrlen - per_fragm;

        if (WARN_ON(rem < 0))
                return -EINVAL;

        /* first fragment was already added to queue by caller */

        while (rem) {
                int fraglen = per_fragm;

                if (fraglen > rem)
                        fraglen = rem;
                rem -= fraglen;
                tmp = dev_alloc_skb(local->tx_headroom +
                                    frag_threshold +
                                    IEEE80211_ENCRYPT_HEADROOM +
                                    IEEE80211_ENCRYPT_TAILROOM);
                if (!tmp)
                        return -ENOMEM;

                __skb_queue_tail(&tx->skbs, tmp);

                skb_reserve(tmp,
                            local->tx_headroom + IEEE80211_ENCRYPT_HEADROOM);

                /* copy control information */
                memcpy(tmp->cb, skb->cb, sizeof(tmp->cb));

                info = IEEE80211_SKB_CB(tmp);
                info->flags &= ~(IEEE80211_TX_CTL_CLEAR_PS_FILT |
                                 IEEE80211_TX_CTL_FIRST_FRAGMENT);

                if (rem)
                        info->flags |= IEEE80211_TX_CTL_MORE_FRAMES;

                skb_copy_queue_mapping(tmp, skb);
                tmp->priority = skb->priority;
                tmp->dev = skb->dev;

                /* copy header and data */
                skb_put_data(tmp, skb->data, hdrlen);
                skb_put_data(tmp, skb->data + pos, fraglen);

                pos += fraglen;
        }

        /* adjust first fragment's length */
        skb_trim(skb, hdrlen + per_fragm);
        return 0;
}

static ieee80211_tx_result debug_noinline
ieee80211_tx_h_fragment(struct ieee80211_tx_data *tx)
{
        struct sk_buff *skb = tx->skb;
        struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb);
        struct ieee80211_hdr *hdr = (void *)skb->data;
        int frag_threshold = tx->local->hw.wiphy->frag_threshold;
        int hdrlen;
        int fragnum;

        /* no matter what happens, tx->skb moves to tx->skbs */
        __skb_queue_tail(&tx->skbs, skb);
        tx->skb = NULL;

        if (info->flags & IEEE80211_TX_CTL_DONTFRAG)
                return TX_CONTINUE;

        if (ieee80211_hw_check(&tx->local->hw, SUPPORTS_TX_FRAG))
                return TX_CONTINUE;

        /*
         * Warn when submitting a fragmented A-MPDU frame and drop it.
         * This scenario is handled in ieee80211_tx_prepare but extra
         * caution taken here as fragmented ampdu may cause Tx stop.
         */
        if (WARN_ON(info->flags & IEEE80211_TX_CTL_AMPDU))
                return TX_DROP;

        hdrlen = ieee80211_hdrlen(hdr->frame_control);

        /* internal error, why isn't DONTFRAG set? */
        if (WARN_ON(skb->len + FCS_LEN <= frag_threshold))
                return TX_DROP;

        /*
         * Now fragment the frame. This will allocate all the fragments and
         * chain them (using skb as the first fragment) to skb->next.
         * During transmission, we will remove the successfully transmitted
         * fragments from this list. When the low-level driver rejects one
         * of the fragments then we will simply pretend to accept the skb
         * but store it away as pending.
         */
        if (ieee80211_fragment(tx, skb, hdrlen, frag_threshold))
                return TX_DROP;

        /* update duration/seq/flags of fragments */
        fragnum = 0;

        skb_queue_walk(&tx->skbs, skb) {
                const __le16 morefrags = cpu_to_le16(IEEE80211_FCTL_MOREFRAGS);

                hdr = (void *)skb->data;
                info = IEEE80211_SKB_CB(skb);

                if (!skb_queue_is_last(&tx->skbs, skb)) {
                        hdr->frame_control |= morefrags;
                        /*
                         * No multi-rate retries for fragmented frames, that
                         * would completely throw off the NAV at other STAs.
                         */
                        info->control.rates[1].idx = -1;
                        info->control.rates[2].idx = -1;
                        info->control.rates[3].idx = -1;
                        BUILD_BUG_ON(IEEE80211_TX_MAX_RATES != 4);
                        info->flags &= ~IEEE80211_TX_CTL_RATE_CTRL_PROBE;
                } else {
                        hdr->frame_control &= ~morefrags;
                }
                hdr->seq_ctrl |= cpu_to_le16(fragnum & IEEE80211_SCTL_FRAG);
                fragnum++;
        }

        return TX_CONTINUE;
}

static ieee80211_tx_result debug_noinline
ieee80211_tx_h_stats(struct ieee80211_tx_data *tx)
{
        struct sk_buff *skb;
        int ac = -1;

        if (!tx->sta)
                return TX_CONTINUE;

        skb_queue_walk(&tx->skbs, skb) {
                ac = skb_get_queue_mapping(skb);
                tx->sta->deflink.tx_stats.bytes[ac] += skb->len;
        }
        if (ac >= 0)
                tx->sta->deflink.tx_stats.packets[ac]++;

        return TX_CONTINUE;
}

static ieee80211_tx_result debug_noinline
ieee80211_tx_h_encrypt(struct ieee80211_tx_data *tx)
{
        if (!tx->key)
                return TX_CONTINUE;

        switch (tx->key->conf.cipher) {
        case WLAN_CIPHER_SUITE_WEP40:
        case WLAN_CIPHER_SUITE_WEP104:
                return ieee80211_crypto_wep_encrypt(tx);
        case WLAN_CIPHER_SUITE_TKIP:
                return ieee80211_crypto_tkip_encrypt(tx);
        case WLAN_CIPHER_SUITE_CCMP:
                return ieee80211_crypto_ccmp_encrypt(
                        tx, IEEE80211_CCMP_MIC_LEN);
        case WLAN_CIPHER_SUITE_CCMP_256:
                return ieee80211_crypto_ccmp_encrypt(
                        tx, IEEE80211_CCMP_256_MIC_LEN);
        case WLAN_CIPHER_SUITE_AES_CMAC:
                return ieee80211_crypto_aes_cmac_encrypt(tx);
        case WLAN_CIPHER_SUITE_BIP_CMAC_256:
                return ieee80211_crypto_aes_cmac_256_encrypt(tx);
        case WLAN_CIPHER_SUITE_BIP_GMAC_128:
        case WLAN_CIPHER_SUITE_BIP_GMAC_256:
                return ieee80211_crypto_aes_gmac_encrypt(tx);
        case WLAN_CIPHER_SUITE_GCMP:
        case WLAN_CIPHER_SUITE_GCMP_256:
                return ieee80211_crypto_gcmp_encrypt(tx);
        }

        return TX_DROP;
}

static ieee80211_tx_result debug_noinline
ieee80211_tx_h_calculate_duration(struct ieee80211_tx_data *tx)
{
        struct sk_buff *skb;
        struct ieee80211_hdr *hdr;
        int next_len;
        bool group_addr;

        skb_queue_walk(&tx->skbs, skb) {
                hdr = (void *) skb->data;
                if (unlikely(ieee80211_is_pspoll(hdr->frame_control)))
                        break; /* must not overwrite AID */
                if (!skb_queue_is_last(&tx->skbs, skb)) {
                        struct sk_buff *next = skb_queue_next(&tx->skbs, skb);
                        next_len = next->len;
                } else
                        next_len = 0;
                group_addr = is_multicast_ether_addr(hdr->addr1);

                hdr->duration_id =
                        ieee80211_duration(tx, skb, group_addr, next_len);
        }

        return TX_CONTINUE;
}

/* actual transmit path */

static bool ieee80211_tx_prep_agg(struct ieee80211_tx_data *tx,
                                  struct sk_buff *skb,
                                  struct ieee80211_tx_info *info,
                                  struct tid_ampdu_tx *tid_tx,
                                  int tid)
{
        bool queued = false;
        bool reset_agg_timer = false;
        struct sk_buff *purge_skb = NULL;

        if (test_bit(HT_AGG_STATE_OPERATIONAL, &tid_tx->state)) {
                reset_agg_timer = true;
        } else if (test_bit(HT_AGG_STATE_WANT_START, &tid_tx->state)) {
                /*
                 * nothing -- this aggregation session is being started
                 * but that might still fail with the driver
                 */
        } else if (!tx->sta->sta.txq[tid]) {
                spin_lock(&tx->sta->lock);
                /*
                 * Need to re-check now, because we may get here
                 *
                 *  1) in the window during which the setup is actually
                 *     already done, but not marked yet because not all
                 *     packets are spliced over to the driver pending
                 *     queue yet -- if this happened we acquire the lock
                 *     either before or after the splice happens, but
                 *     need to recheck which of these cases happened.
                 *
                 *  2) during session teardown, if the OPERATIONAL bit
                 *     was cleared due to the teardown but the pointer
                 *     hasn't been assigned NULL yet (or we loaded it
                 *     before it was assigned) -- in this case it may
                 *     now be NULL which means we should just let the
                 *     packet pass through because splicing the frames
                 *     back is already done.
                 */
                tid_tx = rcu_dereference_protected_tid_tx(tx->sta, tid);

                if (!tid_tx) {
                        /* do nothing, let packet pass through */
                } else if (test_bit(HT_AGG_STATE_OPERATIONAL, &tid_tx->state)) {
                        reset_agg_timer = true;
                } else {
                        queued = true;
                        if (info->flags & IEEE80211_TX_CTL_NO_PS_BUFFER) {
                                clear_sta_flag(tx->sta, WLAN_STA_SP);
                                ps_dbg(tx->sta->sdata,
                                       "STA %pM aid %d: SP frame queued, close the SP w/o telling the peer\n",
                                       tx->sta->sta.addr, tx->sta->sta.aid);
                        }
                        info->control.vif = &tx->sdata->vif;
                        info->control.flags |= IEEE80211_TX_INTCFL_NEED_TXPROCESSING;
                        info->flags &= ~IEEE80211_TX_TEMPORARY_FLAGS;
                        __skb_queue_tail(&tid_tx->pending, skb);
                        if (skb_queue_len(&tid_tx->pending) > STA_MAX_TX_BUFFER)
                                purge_skb = __skb_dequeue(&tid_tx->pending);
                }
                spin_unlock(&tx->sta->lock);

                if (purge_skb)
                        ieee80211_free_txskb(&tx->local->hw, purge_skb);
        }

        /* reset session timer */
        if (reset_agg_timer)
                tid_tx->last_tx = jiffies;

        return queued;
}

void ieee80211_aggr_check(struct ieee80211_sub_if_data *sdata,
                          struct sta_info *sta, struct sk_buff *skb)
{
        struct rate_control_ref *ref = sdata->local->rate_ctrl;
        u16 tid;

        if (!ref || !(ref->ops->capa & RATE_CTRL_CAPA_AMPDU_TRIGGER))
                return;

        if (!sta || !sta->sta.deflink.ht_cap.ht_supported ||
            !sta->sta.wme || skb_get_queue_mapping(skb) == IEEE80211_AC_VO ||
            skb->protocol == sdata->control_port_protocol)
                return;

        tid = skb->priority & IEEE80211_QOS_CTL_TID_MASK;
        if (likely(sta->ampdu_mlme.tid_tx[tid]))
                return;

        ieee80211_start_tx_ba_session(&sta->sta, tid, 0);
}

/*
 * initialises @tx
 * pass %NULL for the station if unknown, a valid pointer if known
 * or an ERR_PTR() if the station is known not to exist
 */
static ieee80211_tx_result
ieee80211_tx_prepare(struct ieee80211_sub_if_data *sdata,
                     struct ieee80211_tx_data *tx,
                     struct sta_info *sta, struct sk_buff *skb)
{
        struct ieee80211_local *local = sdata->local;
        struct ieee80211_hdr *hdr;
        struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb);
        bool aggr_check = false;
        int tid;

        memset(tx, 0, sizeof(*tx));
        tx->skb = skb;
        tx->local = local;
        tx->sdata = sdata;
        __skb_queue_head_init(&tx->skbs);

        /*
         * If this flag is set to true anywhere, and we get here,
         * we are doing the needed processing, so remove the flag
         * now.
         */
        info->control.flags &= ~IEEE80211_TX_INTCFL_NEED_TXPROCESSING;

        hdr = (struct ieee80211_hdr *) skb->data;

        if (likely(sta)) {
                if (!IS_ERR(sta))
                        tx->sta = sta;
        } else {
                if (sdata->vif.type == NL80211_IFTYPE_AP_VLAN) {
                        tx->sta = rcu_dereference(sdata->u.vlan.sta);
                        if (!tx->sta && sdata->wdev.use_4addr)
                                return TX_DROP;
                } else if (tx->sdata->control_port_protocol == tx->skb->protocol) {
                        tx->sta = sta_info_get_bss(sdata, hdr->addr1);
                }
                if (!tx->sta && !is_multicast_ether_addr(hdr->addr1)) {
                        tx->sta = sta_info_get(sdata, hdr->addr1);
                        aggr_check = true;
                }
        }

        if (tx->sta && ieee80211_is_data_qos(hdr->frame_control) &&
            !ieee80211_is_qos_nullfunc(hdr->frame_control) &&
            ieee80211_hw_check(&local->hw, AMPDU_AGGREGATION) &&
            !ieee80211_hw_check(&local->hw, TX_AMPDU_SETUP_IN_HW)) {
                struct tid_ampdu_tx *tid_tx;

                tid = ieee80211_get_tid(hdr);
                tid_tx = rcu_dereference(tx->sta->ampdu_mlme.tid_tx[tid]);
                if (!tid_tx && aggr_check) {
                        ieee80211_aggr_check(sdata, tx->sta, skb);
                        tid_tx = rcu_dereference(tx->sta->ampdu_mlme.tid_tx[tid]);
                }

                if (tid_tx) {
                        bool queued;

                        queued = ieee80211_tx_prep_agg(tx, skb, info,
                                                       tid_tx, tid);

                        if (unlikely(queued))
                                return TX_QUEUED;
                }
        }

        if (is_multicast_ether_addr(hdr->addr1)) {
                tx->flags &= ~IEEE80211_TX_UNICAST;
                info->flags |= IEEE80211_TX_CTL_NO_ACK;
        } else
                tx->flags |= IEEE80211_TX_UNICAST;

        if (!(info->flags & IEEE80211_TX_CTL_DONTFRAG)) {
                if (!(tx->flags & IEEE80211_TX_UNICAST) ||
                    skb->len + FCS_LEN <= local->hw.wiphy->frag_threshold ||
                    info->flags & IEEE80211_TX_CTL_AMPDU)
                        info->flags |= IEEE80211_TX_CTL_DONTFRAG;
        }

        if (!tx->sta)
                info->flags |= IEEE80211_TX_CTL_CLEAR_PS_FILT;
        else if (test_and_clear_sta_flag(tx->sta, WLAN_STA_CLEAR_PS_FILT)) {
                info->flags |= IEEE80211_TX_CTL_CLEAR_PS_FILT;
                ieee80211_check_fast_xmit(tx->sta);
        }

        info->flags |= IEEE80211_TX_CTL_FIRST_FRAGMENT;

        return TX_CONTINUE;
}

static struct txq_info *ieee80211_get_txq(struct ieee80211_local *local,
                                          struct ieee80211_vif *vif,
                                          struct sta_info *sta,
                                          struct sk_buff *skb)
{
        struct ieee80211_hdr *hdr = (struct ieee80211_hdr *) skb->data;
        struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb);
        struct ieee80211_txq *txq = NULL;

        if ((info->flags & IEEE80211_TX_CTL_SEND_AFTER_DTIM) ||
            (info->control.flags & IEEE80211_TX_CTRL_PS_RESPONSE))
                return NULL;

        if (!(info->flags & IEEE80211_TX_CTL_HW_80211_ENCAP) &&
            unlikely(!ieee80211_is_data_present(hdr->frame_control))) {
                if ((!ieee80211_is_mgmt(hdr->frame_control) ||
                     ieee80211_is_bufferable_mmpdu(skb) ||
                     vif->type == NL80211_IFTYPE_STATION) &&
                    sta && sta->uploaded) {
                        /*
                         * This will be NULL if the driver didn't set the
                         * opt-in hardware flag.
                         */
                        txq = sta->sta.txq[IEEE80211_NUM_TIDS];
                }
        } else if (sta) {
                u8 tid = skb->priority & IEEE80211_QOS_CTL_TID_MASK;

                if (!sta->uploaded)
                        return NULL;

                txq = sta->sta.txq[tid];
        } else {
                txq = vif->txq;
        }

        if (!txq)
                return NULL;

        return to_txq_info(txq);
}

static void ieee80211_set_skb_enqueue_time(struct sk_buff *skb)
{
        struct sk_buff *next;
        codel_time_t now = codel_get_time();

        skb_list_walk_safe(skb, skb, next)
                IEEE80211_SKB_CB(skb)->control.enqueue_time = now;
}

static u32 codel_skb_len_func(const struct sk_buff *skb)
{
        return skb->len;
}

static codel_time_t codel_skb_time_func(const struct sk_buff *skb)
{
        const struct ieee80211_tx_info *info;

        info = (const struct ieee80211_tx_info *)skb->cb;
        return info->control.enqueue_time;
}

static struct sk_buff *codel_dequeue_func(struct codel_vars *cvars,
                                          void *ctx)
{
        struct ieee80211_local *local;
        struct txq_info *txqi;
        struct fq *fq;
        struct fq_flow *flow;

        txqi = ctx;
        local = vif_to_sdata(txqi->txq.vif)->local;
        fq = &local->fq;

        if (cvars == &txqi->def_cvars)
                flow = &txqi->tin.default_flow;
        else
                flow = &fq->flows[cvars - local->cvars];

        return fq_flow_dequeue(fq, flow);
}

static void codel_drop_func(struct sk_buff *skb,
                            void *ctx)
{
        struct ieee80211_local *local;
        struct ieee80211_hw *hw;
        struct txq_info *txqi;

        txqi = ctx;
        local = vif_to_sdata(txqi->txq.vif)->local;
        hw = &local->hw;

        ieee80211_free_txskb(hw, skb);
}

static struct sk_buff *fq_tin_dequeue_func(struct fq *fq,
                                           struct fq_tin *tin,
                                           struct fq_flow *flow)
{
        struct ieee80211_local *local;
        struct txq_info *txqi;
        struct codel_vars *cvars;
        struct codel_params *cparams;
        struct codel_stats *cstats;

        local = container_of(fq, struct ieee80211_local, fq);
        txqi = container_of(tin, struct txq_info, tin);
        cstats = &txqi->cstats;

        if (txqi->txq.sta) {
                struct sta_info *sta = container_of(txqi->txq.sta,
                                                    struct sta_info, sta);
                cparams = &sta->cparams;
        } else {
                cparams = &local->cparams;
        }

        if (flow == &tin->default_flow)
                cvars = &txqi->def_cvars;
        else
                cvars = &local->cvars[flow - fq->flows];

        return codel_dequeue(txqi,
                             &flow->backlog,
                             cparams,
                             cvars,
                             cstats,
                             codel_skb_len_func,
                             codel_skb_time_func,
                             codel_drop_func,
                             codel_dequeue_func);
}

static void fq_skb_free_func(struct fq *fq,
                             struct fq_tin *tin,
                             struct fq_flow *flow,
                             struct sk_buff *skb)
{
        struct ieee80211_local *local;

        local = container_of(fq, struct ieee80211_local, fq);
        ieee80211_free_txskb(&local->hw, skb);
}

static void ieee80211_txq_enqueue(struct ieee80211_local *local,
                                  struct txq_info *txqi,
                                  struct sk_buff *skb)
{
        struct fq *fq = &local->fq;
        struct fq_tin *tin = &txqi->tin;
        u32 flow_idx = fq_flow_idx(fq, skb);

        ieee80211_set_skb_enqueue_time(skb);

        spin_lock_bh(&fq->lock);
        /*
         * For management frames, don't really apply codel etc.,
         * we don't want to apply any shaping or anything we just
         * want to simplify the driver API by having them on the
         * txqi.
         */
        if (unlikely(txqi->txq.tid == IEEE80211_NUM_TIDS)) {
                IEEE80211_SKB_CB(skb)->control.flags |=
                        IEEE80211_TX_INTCFL_NEED_TXPROCESSING;
                __skb_queue_tail(&txqi->frags, skb);
        } else {
                fq_tin_enqueue(fq, tin, flow_idx, skb,
                               fq_skb_free_func);
        }
        spin_unlock_bh(&fq->lock);
}

static bool fq_vlan_filter_func(struct fq *fq, struct fq_tin *tin,
                                struct fq_flow *flow, struct sk_buff *skb,
                                void *data)
{
        struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb);

        return info->control.vif == data;
}

void ieee80211_txq_remove_vlan(struct ieee80211_local *local,
                               struct ieee80211_sub_if_data *sdata)
{
        struct fq *fq = &local->fq;
        struct txq_info *txqi;
        struct fq_tin *tin;
        struct ieee80211_sub_if_data *ap;

        if (WARN_ON(sdata->vif.type != NL80211_IFTYPE_AP_VLAN))
                return;

        ap = container_of(sdata->bss, struct ieee80211_sub_if_data, u.ap);

        if (!ap->vif.txq)
                return;

        txqi = to_txq_info(ap->vif.txq);
        tin = &txqi->tin;

        spin_lock_bh(&fq->lock);
        fq_tin_filter(fq, tin, fq_vlan_filter_func, &sdata->vif,
                      fq_skb_free_func);
        spin_unlock_bh(&fq->lock);
}

void ieee80211_txq_init(struct ieee80211_sub_if_data *sdata,
                        struct sta_info *sta,
                        struct txq_info *txqi, int tid)
{
        fq_tin_init(&txqi->tin);
        codel_vars_init(&txqi->def_cvars);
        codel_stats_init(&txqi->cstats);
        __skb_queue_head_init(&txqi->frags);
        INIT_LIST_HEAD(&txqi->schedule_order);

        txqi->txq.vif = &sdata->vif;

        if (!sta) {
                sdata->vif.txq = &txqi->txq;
                txqi->txq.tid = 0;
                txqi->txq.ac = IEEE80211_AC_BE;

                return;
        }

        if (tid == IEEE80211_NUM_TIDS) {
                if (sdata->vif.type == NL80211_IFTYPE_STATION) {
                        /* Drivers need to opt in to the management MPDU TXQ */
                        if (!ieee80211_hw_check(&sdata->local->hw,
                                                STA_MMPDU_TXQ))
                                return;
                } else if (!ieee80211_hw_check(&sdata->local->hw,
                                               BUFF_MMPDU_TXQ)) {
                        /* Drivers need to opt in to the bufferable MMPDU TXQ */
                        return;
                }
                txqi->txq.ac = IEEE80211_AC_VO;
        } else {
                txqi->txq.ac = ieee80211_ac_from_tid(tid);
        }

        txqi->txq.sta = &sta->sta;
        txqi->txq.tid = tid;
        sta->sta.txq[tid] = &txqi->txq;
}

void ieee80211_txq_purge(struct ieee80211_local *local,
                         struct txq_info *txqi)
{
        struct fq *fq = &local->fq;
        struct fq_tin *tin = &txqi->tin;

        spin_lock_bh(&fq->lock);
        fq_tin_reset(fq, tin, fq_skb_free_func);
        ieee80211_purge_tx_queue(&local->hw, &txqi->frags);
        spin_unlock_bh(&fq->lock);

        spin_lock_bh(&local->active_txq_lock[txqi->txq.ac]);
        list_del_init(&txqi->schedule_order);
        spin_unlock_bh(&local->active_txq_lock[txqi->txq.ac]);
}

void ieee80211_txq_set_params(struct ieee80211_local *local)
{
        if (local->hw.wiphy->txq_limit)
                local->fq.limit = local->hw.wiphy->txq_limit;
        else
                local->hw.wiphy->txq_limit = local->fq.limit;

        if (local->hw.wiphy->txq_memory_limit)
                local->fq.memory_limit = local->hw.wiphy->txq_memory_limit;
        else
                local->hw.wiphy->txq_memory_limit = local->fq.memory_limit;

        if (local->hw.wiphy->txq_quantum)
                local->fq.quantum = local->hw.wiphy->txq_quantum;
        else
                local->hw.wiphy->txq_quantum = local->fq.quantum;
}

int ieee80211_txq_setup_flows(struct ieee80211_local *local)
{
        struct fq *fq = &local->fq;
        int ret;
        int i;
        bool supp_vht = false;
        enum nl80211_band band;

        ret = fq_init(fq, 4096);
        if (ret)
                return ret;

        /*
         * If the hardware doesn't support VHT, it is safe to limit the maximum
         * queue size. 4 Mbytes is 64 max-size aggregates in 802.11n.
         */
        for (band = 0; band < NUM_NL80211_BANDS; band++) {
                struct ieee80211_supported_band *sband;

                sband = local->hw.wiphy->bands[band];
                if (!sband)
                        continue;

                supp_vht = supp_vht || sband->vht_cap.vht_supported;
        }

        if (!supp_vht)
                fq->memory_limit = 4 << 20; /* 4 Mbytes */

        codel_params_init(&local->cparams);
        local->cparams.interval = MS2TIME(100);
        local->cparams.target = MS2TIME(20);
        local->cparams.ecn = true;

        local->cvars = kvcalloc(fq->flows_cnt, sizeof(local->cvars[0]),
                                GFP_KERNEL);
        if (!local->cvars) {
                spin_lock_bh(&fq->lock);
                fq_reset(fq, fq_skb_free_func);
                spin_unlock_bh(&fq->lock);
                return -ENOMEM;
        }

        for (i = 0; i < fq->flows_cnt; i++)
                codel_vars_init(&local->cvars[i]);

        ieee80211_txq_set_params(local);

        return 0;
}

void ieee80211_txq_teardown_flows(struct ieee80211_local *local)
{
        struct fq *fq = &local->fq;

        kvfree(local->cvars);
        local->cvars = NULL;

        spin_lock_bh(&fq->lock);
        fq_reset(fq, fq_skb_free_func);
        spin_unlock_bh(&fq->lock);
}

static bool ieee80211_queue_skb(struct ieee80211_local *local,
                                struct ieee80211_sub_if_data *sdata,
                                struct sta_info *sta,
                                struct sk_buff *skb)
{
        struct ieee80211_vif *vif;
        struct txq_info *txqi;

        if (sdata->vif.type == NL80211_IFTYPE_MONITOR)
                return false;

        if (sdata->vif.type == NL80211_IFTYPE_AP_VLAN)
                sdata = container_of(sdata->bss,
                                     struct ieee80211_sub_if_data, u.ap);

        vif = &sdata->vif;
        txqi = ieee80211_get_txq(local, vif, sta, skb);

        if (!txqi)
                return false;

        ieee80211_txq_enqueue(local, txqi, skb);

        schedule_and_wake_txq(local, txqi);

        return true;
}

static bool ieee80211_tx_frags(struct ieee80211_local *local,
                               struct ieee80211_vif *vif,
                               struct sta_info *sta,
                               struct sk_buff_head *skbs,
                               bool txpending)
{
        struct ieee80211_tx_control control = {};
        struct sk_buff *skb, *tmp;
        unsigned long flags;

        skb_queue_walk_safe(skbs, skb, tmp) {
                struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb);
                int q = info->hw_queue;

#ifdef CONFIG_MAC80211_VERBOSE_DEBUG
                if (WARN_ON_ONCE(q >= local->hw.queues)) {
                        __skb_unlink(skb, skbs);
                        ieee80211_free_txskb(&local->hw, skb);
                        continue;
                }
#endif

                spin_lock_irqsave(&local->queue_stop_reason_lock, flags);
                if (local->queue_stop_reasons[q] ||
                    (!txpending && !skb_queue_empty(&local->pending[q]))) {
                        if (unlikely(info->flags &
                                     IEEE80211_TX_INTFL_OFFCHAN_TX_OK)) {
                                if (local->queue_stop_reasons[q] &
                                    ~BIT(IEEE80211_QUEUE_STOP_REASON_OFFCHANNEL)) {
                                        /*
                                         * Drop off-channel frames if queues
                                         * are stopped for any reason other
                                         * than off-channel operation. Never
                                         * queue them.
                                         */
                                        spin_unlock_irqrestore(
                                                &local->queue_stop_reason_lock,
                                                flags);
                                        ieee80211_purge_tx_queue(&local->hw,
                                                                 skbs);
                                        return true;
                                }
                        } else {

                                /*
                                 * Since queue is stopped, queue up frames for
                                 * later transmission from the tx-pending
                                 * tasklet when the queue is woken again.
                                 */
                                if (txpending)
                                        skb_queue_splice_init(skbs,
                                                              &local->pending[q]);
                                else
                                        skb_queue_splice_tail_init(skbs,
                                                                   &local->pending[q]);

                                spin_unlock_irqrestore(&local->queue_stop_reason_lock,
                                                       flags);
                                return false;
                        }
                }
                spin_unlock_irqrestore(&local->queue_stop_reason_lock, flags);

                info->control.vif = vif;
                control.sta = sta ? &sta->sta : NULL;

                __skb_unlink(skb, skbs);
                drv_tx(local, &control, skb);
        }

        return true;
}

/*
 * Returns false if the frame couldn't be transmitted but was queued instead.
 */
static bool __ieee80211_tx(struct ieee80211_local *local,
                           struct sk_buff_head *skbs, struct sta_info *sta,
                           bool txpending)
{
        struct ieee80211_tx_info *info;
        struct ieee80211_sub_if_data *sdata;
        struct ieee80211_vif *vif;
        struct sk_buff *skb;
        bool result;

        if (WARN_ON(skb_queue_empty(skbs)))
                return true;

        skb = skb_peek(skbs);
        info = IEEE80211_SKB_CB(skb);
        sdata = vif_to_sdata(info->control.vif);
        if (sta && !sta->uploaded)
                sta = NULL;

        switch (sdata->vif.type) {
        case NL80211_IFTYPE_MONITOR:
                if ((sdata->u.mntr.flags & MONITOR_FLAG_ACTIVE) ||
                    ieee80211_hw_check(&local->hw, NO_VIRTUAL_MONITOR)) {
                        vif = &sdata->vif;
                        break;
                }
                sdata = rcu_dereference(local->monitor_sdata);
                if (sdata && ieee80211_hw_check(&local->hw, WANT_MONITOR_VIF)) {
                        vif = &sdata->vif;
                        info->hw_queue =
                                vif->hw_queue[skb_get_queue_mapping(skb)];
                } else if (ieee80211_hw_check(&local->hw, QUEUE_CONTROL)) {
                        ieee80211_purge_tx_queue(&local->hw, skbs);
                        return true;
                } else
                        vif = NULL;
                break;
        case NL80211_IFTYPE_AP_VLAN:
                sdata = container_of(sdata->bss,
                                     struct ieee80211_sub_if_data, u.ap);
                fallthrough;
        default:
                vif = &sdata->vif;
                break;
        }

        result = ieee80211_tx_frags(local, vif, sta, skbs, txpending);

        WARN_ON_ONCE(!skb_queue_empty(skbs));

        return result;
}

/*
 * Invoke TX handlers, return 0 on success and non-zero if the
 * frame was dropped or queued.
 *
 * The handlers are split into an early and late part. The latter is everything
 * that can be sensitive to reordering, and will be deferred to after packets
 * are dequeued from the intermediate queues (when they are enabled).
 */
static int invoke_tx_handlers_early(struct ieee80211_tx_data *tx)
{
        ieee80211_tx_result res = TX_DROP;

#define CALL_TXH(txh) \
        do {                                \
                res = txh(tx);                \
                if (res != TX_CONTINUE)        \
                        goto txh_done;        \
        } while (0)

        CALL_TXH(ieee80211_tx_h_dynamic_ps);
        CALL_TXH(ieee80211_tx_h_check_assoc);
        CALL_TXH(ieee80211_tx_h_ps_buf);
        CALL_TXH(ieee80211_tx_h_check_control_port_protocol);
        CALL_TXH(ieee80211_tx_h_select_key);

 txh_done:
        if (unlikely(res == TX_DROP)) {
                I802_DEBUG_INC(tx->local->tx_handlers_drop);
                if (tx->skb)
                        ieee80211_free_txskb(&tx->local->hw, tx->skb);
                else
                        ieee80211_purge_tx_queue(&tx->local->hw, &tx->skbs);
                return -1;
        } else if (unlikely(res == TX_QUEUED)) {
                I802_DEBUG_INC(tx->local->tx_handlers_queued);
                return -1;
        }

        return 0;
}

/*
 * Late handlers can be called while the sta lock is held. Handlers that can
 * cause packets to be generated will cause deadlock!
 */
static int invoke_tx_handlers_late(struct ieee80211_tx_data *tx)
{
        struct ieee80211_tx_info *info = IEEE80211_SKB_CB(tx->skb);
        ieee80211_tx_result res = TX_CONTINUE;

        if (!ieee80211_hw_check(&tx->local->hw, HAS_RATE_CONTROL))
                CALL_TXH(ieee80211_tx_h_rate_ctrl);

        if (unlikely(info->flags & IEEE80211_TX_INTFL_RETRANSMISSION)) {
                __skb_queue_tail(&tx->skbs, tx->skb);
                tx->skb = NULL;
                goto txh_done;
        }

        CALL_TXH(ieee80211_tx_h_michael_mic_add);
        CALL_TXH(ieee80211_tx_h_sequence);
        CALL_TXH(ieee80211_tx_h_fragment);
        /* handlers after fragment must be aware of tx info fragmentation! */
        CALL_TXH(ieee80211_tx_h_stats);
        CALL_TXH(ieee80211_tx_h_encrypt);
        if (!ieee80211_hw_check(&tx->local->hw, HAS_RATE_CONTROL))
                CALL_TXH(ieee80211_tx_h_calculate_duration);
#undef CALL_TXH

 txh_done:
        if (unlikely(res == TX_DROP)) {
                I802_DEBUG_INC(tx->local->tx_handlers_drop);
                if (tx->skb)
                        ieee80211_free_txskb(&tx->local->hw, tx->skb);
                else
                        ieee80211_purge_tx_queue(&tx->local->hw, &tx->skbs);
                return -1;
        } else if (unlikely(res == TX_QUEUED)) {
                I802_DEBUG_INC(tx->local->tx_handlers_queued);
                return -1;
        }

        return 0;
}

static int invoke_tx_handlers(struct ieee80211_tx_data *tx)
{
        int r = invoke_tx_handlers_early(tx);

        if (r)
                return r;
        return invoke_tx_handlers_late(tx);
}

bool ieee80211_tx_prepare_skb(struct ieee80211_hw *hw,
                              struct ieee80211_vif *vif, struct sk_buff *skb,
                              int band, struct ieee80211_sta **sta)
{
        struct ieee80211_sub_if_data *sdata = vif_to_sdata(vif);
        struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb);
        struct ieee80211_tx_data tx;
        struct sk_buff *skb2;

        if (ieee80211_tx_prepare(sdata, &tx, NULL, skb) == TX_DROP)
                return false;

        info->band = band;
        info->control.vif = vif;
        info->hw_queue = vif->hw_queue[skb_get_queue_mapping(skb)];

        if (invoke_tx_handlers(&tx))
                return false;

        if (sta) {
                if (tx.sta)
                        *sta = &tx.sta->sta;
                else
                        *sta = NULL;
        }

        /* this function isn't suitable for fragmented data frames */
        skb2 = __skb_dequeue(&tx.skbs);
        if (WARN_ON(skb2 != skb || !skb_queue_empty(&tx.skbs))) {
                ieee80211_free_txskb(hw, skb2);
                ieee80211_purge_tx_queue(hw, &tx.skbs);
                return false;
        }

        return true;
}
EXPORT_SYMBOL(ieee80211_tx_prepare_skb);

/*
 * Returns false if the frame couldn't be transmitted but was queued instead.
 */
static bool ieee80211_tx(struct ieee80211_sub_if_data *sdata,
                         struct sta_info *sta, struct sk_buff *skb,
                         bool txpending)
{
        struct ieee80211_local *local = sdata->local;
        struct ieee80211_tx_data tx;
        ieee80211_tx_result res_prepare;
        struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb);
        bool result = true;

        if (unlikely(skb->len < 10)) {
                dev_kfree_skb(skb);
                return true;
        }

        /* initialises tx */
        res_prepare = ieee80211_tx_prepare(sdata, &tx, sta, skb);

        if (unlikely(res_prepare == TX_DROP)) {
                ieee80211_free_txskb(&local->hw, skb);
                return true;
        } else if (unlikely(res_prepare == TX_QUEUED)) {
                return true;
        }

        /* set up hw_queue value early */
        if (!(info->flags & IEEE80211_TX_CTL_TX_OFFCHAN) ||
            !ieee80211_hw_check(&local->hw, QUEUE_CONTROL))
                info->hw_queue =
                        sdata->vif.hw_queue[skb_get_queue_mapping(skb)];

        if (invoke_tx_handlers_early(&tx))
                return true;

        if (ieee80211_queue_skb(local, sdata, tx.sta, tx.skb))
                return true;

        if (!invoke_tx_handlers_late(&tx))
                result = __ieee80211_tx(local, &tx.skbs, tx.sta, txpending);

        return result;
}

/* device xmit handlers */

enum ieee80211_encrypt {
        ENCRYPT_NO,
        ENCRYPT_MGMT,
        ENCRYPT_DATA,
};

static int ieee80211_skb_resize(struct ieee80211_sub_if_data *sdata,
                                struct sk_buff *skb,
                                int head_need,
                                enum ieee80211_encrypt encrypt)
{
        struct ieee80211_local *local = sdata->local;
        bool enc_tailroom;
        int tail_need = 0;

        enc_tailroom = encrypt == ENCRYPT_MGMT ||
                       (encrypt == ENCRYPT_DATA &&
                        sdata->crypto_tx_tailroom_needed_cnt);

        if (enc_tailroom) {
                tail_need = IEEE80211_ENCRYPT_TAILROOM;
                tail_need -= skb_tailroom(skb);
                tail_need = max_t(int, tail_need, 0);
        }

        if (skb_cloned(skb) &&
            (!ieee80211_hw_check(&local->hw, SUPPORTS_CLONED_SKBS) ||
             !skb_clone_writable(skb, ETH_HLEN) || enc_tailroom))
                I802_DEBUG_INC(local->tx_expand_skb_head_cloned);
        else if (head_need || tail_need)
                I802_DEBUG_INC(local->tx_expand_skb_head);
        else
                return 0;

        if (pskb_expand_head(skb, head_need, tail_need, GFP_ATOMIC)) {
                wiphy_debug(local->hw.wiphy,
                            "failed to reallocate TX buffer\n");
                return -ENOMEM;
        }

        return 0;
}

void ieee80211_xmit(struct ieee80211_sub_if_data *sdata,
                    struct sta_info *sta, struct sk_buff *skb)
{
        struct ieee80211_local *local = sdata->local;
        struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb);
        struct ieee80211_hdr *hdr = (struct ieee80211_hdr *) skb->data;
        int headroom;
        enum ieee80211_encrypt encrypt;

        if (info->flags & IEEE80211_TX_INTFL_DONT_ENCRYPT)
                encrypt = ENCRYPT_NO;
        else if (ieee80211_is_mgmt(hdr->frame_control))
                encrypt = ENCRYPT_MGMT;
        else
                encrypt = ENCRYPT_DATA;

        headroom = local->tx_headroom;
        if (encrypt != ENCRYPT_NO)
                headroom += IEEE80211_ENCRYPT_HEADROOM;
        headroom -= skb_headroom(skb);
        headroom = max_t(int, 0, headroom);

        if (ieee80211_skb_resize(sdata, skb, headroom, encrypt)) {
                ieee80211_free_txskb(&local->hw, skb);
                return;
        }

        /* reload after potential resize */
        hdr = (struct ieee80211_hdr *) skb->data;
        info->control.vif = &sdata->vif;

        if (ieee80211_vif_is_mesh(&sdata->vif)) {
                if (ieee80211_is_data(hdr->frame_control) &&
                    is_unicast_ether_addr(hdr->addr1)) {
                        if (mesh_nexthop_resolve(sdata, skb))
                                return; /* skb queued: don't free */
                } else {
                        ieee80211_mps_set_frame_flags(sdata, NULL, hdr);
                }
        }

        ieee80211_set_qos_hdr(sdata, skb);
        ieee80211_tx(sdata, sta, skb, false);
}

static bool ieee80211_validate_radiotap_len(struct sk_buff *skb)
{
        struct ieee80211_radiotap_header *rthdr =
                (struct ieee80211_radiotap_header *)skb->data;

        /* check for not even having the fixed radiotap header part */
        if (unlikely(skb->len < sizeof(struct ieee80211_radiotap_header)))
                return false; /* too short to be possibly valid */

        /* is it a header version we can trust to find length from? */
        if (unlikely(rthdr->it_version))
                return false; /* only version 0 is supported */

        /* does the skb contain enough to deliver on the alleged length? */
        if (unlikely(skb->len < ieee80211_get_radiotap_len(skb->data)))
                return false; /* skb too short for claimed rt header extent */

        return true;
}

bool ieee80211_parse_tx_radiotap(struct sk_buff *skb,
                                 struct net_device *dev)
{
        struct ieee80211_local *local = wdev_priv(dev->ieee80211_ptr);
        struct ieee80211_radiotap_iterator iterator;
        struct ieee80211_radiotap_header *rthdr =
                (struct ieee80211_radiotap_header *) skb->data;
        struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb);
        int ret = ieee80211_radiotap_iterator_init(&iterator, rthdr, skb->len,
                                                   NULL);
        u16 txflags;
        u16 rate = 0;
        bool rate_found = false;
        u8 rate_retries = 0;
        u16 rate_flags = 0;
        u8 mcs_known, mcs_flags, mcs_bw;
        u16 vht_known;
        u8 vht_mcs = 0, vht_nss = 0;
        int i;

        if (!ieee80211_validate_radiotap_len(skb))
                return false;

        info->flags |= IEEE80211_TX_INTFL_DONT_ENCRYPT |
                       IEEE80211_TX_CTL_DONTFRAG;

        /*
         * for every radiotap entry that is present
         * (ieee80211_radiotap_iterator_next returns -ENOENT when no more
         * entries present, or -EINVAL on error)
         */

        while (!ret) {
                ret = ieee80211_radiotap_iterator_next(&iterator);

                if (ret)
                        continue;

                /* see if this argument is something we can use */
                switch (iterator.this_arg_index) {
                /*
                 * You must take care when dereferencing iterator.this_arg
                 * for multibyte types... the pointer is not aligned.  Use
                 * get_unaligned((type *)iterator.this_arg) to dereference
                 * iterator.this_arg for type "type" safely on all arches.
                */
                case IEEE80211_RADIOTAP_FLAGS:
                        if (*iterator.this_arg & IEEE80211_RADIOTAP_F_FCS) {
                                /*
                                 * this indicates that the skb we have been
                                 * handed has the 32-bit FCS CRC at the end...
                                 * we should react to that by snipping it off
                                 * because it will be recomputed and added
                                 * on transmission
                                 */
                                if (skb->len < (iterator._max_length + FCS_LEN))
                                        return false;

                                skb_trim(skb, skb->len - FCS_LEN);
                        }
                        if (*iterator.this_arg & IEEE80211_RADIOTAP_F_WEP)
                                info->flags &= ~IEEE80211_TX_INTFL_DONT_ENCRYPT;
                        if (*iterator.this_arg & IEEE80211_RADIOTAP_F_FRAG)
                                info->flags &= ~IEEE80211_TX_CTL_DONTFRAG;
                        break;

                case IEEE80211_RADIOTAP_TX_FLAGS:
                        txflags = get_unaligned_le16(iterator.this_arg);
                        if (txflags & IEEE80211_RADIOTAP_F_TX_NOACK)
                                info->flags |= IEEE80211_TX_CTL_NO_ACK;
                        if (txflags & IEEE80211_RADIOTAP_F_TX_NOSEQNO)
                                info->control.flags |= IEEE80211_TX_CTRL_NO_SEQNO;
                        if (txflags & IEEE80211_RADIOTAP_F_TX_ORDER)
                                info->control.flags |=
                                        IEEE80211_TX_CTRL_DONT_REORDER;
                        break;

                case IEEE80211_RADIOTAP_RATE:
                        rate = *iterator.this_arg;
                        rate_flags = 0;
                        rate_found = true;
                        break;

                case IEEE80211_RADIOTAP_ANTENNA:
                        /* this can appear multiple times, keep a bitmap */
                        info->control.antennas |= BIT(*iterator.this_arg);
                        break;

                case IEEE80211_RADIOTAP_DATA_RETRIES:
                        rate_retries = *iterator.this_arg;
                        break;

                case IEEE80211_RADIOTAP_MCS:
                        mcs_known = iterator.this_arg[0];
                        mcs_flags = iterator.this_arg[1];
                        if (!(mcs_known & IEEE80211_RADIOTAP_MCS_HAVE_MCS))
                                break;

                        rate_found = true;
                        rate = iterator.this_arg[2];
                        rate_flags = IEEE80211_TX_RC_MCS;

                        if (mcs_known & IEEE80211_RADIOTAP_MCS_HAVE_GI &&
                            mcs_flags & IEEE80211_RADIOTAP_MCS_SGI)
                                rate_flags |= IEEE80211_TX_RC_SHORT_GI;

                        mcs_bw = mcs_flags & IEEE80211_RADIOTAP_MCS_BW_MASK;
                        if (mcs_known & IEEE80211_RADIOTAP_MCS_HAVE_BW &&
                            mcs_bw == IEEE80211_RADIOTAP_MCS_BW_40)
                                rate_flags |= IEEE80211_TX_RC_40_MHZ_WIDTH;

                        if (mcs_known & IEEE80211_RADIOTAP_MCS_HAVE_FEC &&
                            mcs_flags & IEEE80211_RADIOTAP_MCS_FEC_LDPC)
                                info->flags |= IEEE80211_TX_CTL_LDPC;

                        if (mcs_known & IEEE80211_RADIOTAP_MCS_HAVE_STBC) {
                                u8 stbc = u8_get_bits(mcs_flags,
                                                      IEEE80211_RADIOTAP_MCS_STBC_MASK);

                                info->flags |=
                                        u32_encode_bits(stbc,
                                                        IEEE80211_TX_CTL_STBC);
                        }
                        break;

                case IEEE80211_RADIOTAP_VHT:
                        vht_known = get_unaligned_le16(iterator.this_arg);
                        rate_found = true;

                        rate_flags = IEEE80211_TX_RC_VHT_MCS;
                        if ((vht_known & IEEE80211_RADIOTAP_VHT_KNOWN_GI) &&
                            (iterator.this_arg[2] &
                             IEEE80211_RADIOTAP_VHT_FLAG_SGI))
                                rate_flags |= IEEE80211_TX_RC_SHORT_GI;
                        if (vht_known &
                            IEEE80211_RADIOTAP_VHT_KNOWN_BANDWIDTH) {
                                if (iterator.this_arg[3] == 1)
                                        rate_flags |=
                                                IEEE80211_TX_RC_40_MHZ_WIDTH;
                                else if (iterator.this_arg[3] == 4)
                                        rate_flags |=
                                                IEEE80211_TX_RC_80_MHZ_WIDTH;
                                else if (iterator.this_arg[3] == 11)
                                        rate_flags |=
                                                IEEE80211_TX_RC_160_MHZ_WIDTH;
                        }

                        vht_mcs = iterator.this_arg[4] >> 4;
                        if (vht_mcs > 11)
                                vht_mcs = 0;
                        vht_nss = iterator.this_arg[4] & 0xF;
                        if (!vht_nss || vht_nss > 8)
                                vht_nss = 1;
                        break;

                /*
                 * Please update the file
                 * Documentation/networking/mac80211-injection.rst
                 * when parsing new fields here.
                 */

                default:
                        break;
                }
        }

        if (ret != -ENOENT) /* ie, if we didn't simply run out of fields */
                return false;

        if (rate_found) {
                struct ieee80211_supported_band *sband =
                        local->hw.wiphy->bands[info->band];

                info->control.flags |= IEEE80211_TX_CTRL_RATE_INJECT;

                for (i = 0; i < IEEE80211_TX_MAX_RATES; i++) {
                        info->control.rates[i].idx = -1;
                        info->control.rates[i].flags = 0;
                        info->control.rates[i].count = 0;
                }

                if (rate_flags & IEEE80211_TX_RC_MCS) {
                        /* reset antennas if not enough */
                        if (IEEE80211_HT_MCS_CHAINS(rate) >
                                        hweight8(info->control.antennas))
                                info->control.antennas = 0;

                        info->control.rates[0].idx = rate;
                } else if (rate_flags & IEEE80211_TX_RC_VHT_MCS) {
                        /* reset antennas if not enough */
                        if (vht_nss > hweight8(info->control.antennas))
                                info->control.antennas = 0;

                        ieee80211_rate_set_vht(info->control.rates, vht_mcs,
                                               vht_nss);
                } else if (sband) {
                        for (i = 0; i < sband->n_bitrates; i++) {
                                if (rate * 5 != sband->bitrates[i].bitrate)
                                        continue;

                                info->control.rates[0].idx = i;
                                break;
                        }
                }

                if (info->control.rates[0].idx < 0)
                        info->control.flags &= ~IEEE80211_TX_CTRL_RATE_INJECT;

                info->control.rates[0].flags = rate_flags;
                info->control.rates[0].count = min_t(u8, rate_retries + 1,
                                                     local->hw.max_rate_tries);
        }

        return true;
}

netdev_tx_t ieee80211_monitor_start_xmit(struct sk_buff *skb,
                                         struct net_device *dev)
{
        struct ieee80211_local *local = wdev_priv(dev->ieee80211_ptr);
        struct ieee80211_chanctx_conf *chanctx_conf;
        struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb);
        struct ieee80211_hdr *hdr;
        struct ieee80211_sub_if_data *tmp_sdata, *sdata;
        struct cfg80211_chan_def *chandef;
        u16 len_rthdr;
        int hdrlen;

        sdata = IEEE80211_DEV_TO_SUB_IF(dev);
        if (unlikely(!ieee80211_sdata_running(sdata)))
                goto fail;

        memset(info, 0, sizeof(*info));
        info->flags = IEEE80211_TX_CTL_REQ_TX_STATUS |
                      IEEE80211_TX_CTL_INJECTED;

        /* Sanity-check the length of the radiotap header */
        if (!ieee80211_validate_radiotap_len(skb))
                goto fail;

        /* we now know there is a radiotap header with a length we can use */
        len_rthdr = ieee80211_get_radiotap_len(skb->data);

        /*
         * fix up the pointers accounting for the radiotap
         * header still being in there.  We are being given
         * a precooked IEEE80211 header so no need for
         * normal processing
         */
        skb_set_mac_header(skb, len_rthdr);
        /*
         * these are just fixed to the end of the rt area since we
         * don't have any better information and at this point, nobody cares
         */
        skb_set_network_header(skb, len_rthdr);
        skb_set_transport_header(skb, len_rthdr);

        if (skb->len < len_rthdr + 2)
                goto fail;

        hdr = (struct ieee80211_hdr *)(skb->data + len_rthdr);
        hdrlen = ieee80211_hdrlen(hdr->frame_control);

        if (skb->len < len_rthdr + hdrlen)
                goto fail;

        /*
         * Initialize skb->protocol if the injected frame is a data frame
         * carrying a rfc1042 header
         */
        if (ieee80211_is_data(hdr->frame_control) &&
            skb->len >= len_rthdr + hdrlen + sizeof(rfc1042_header) + 2) {
                u8 *payload = (u8 *)hdr + hdrlen;

                if (ether_addr_equal(payload, rfc1042_header))
                        skb->protocol = cpu_to_be16((payload[6] << 8) |
                                                    payload[7]);
        }

        rcu_read_lock();

        /*
         * We process outgoing injected frames that have a local address
         * we handle as though they are non-injected frames.
         * This code here isn't entirely correct, the local MAC address
         * isn't always enough to find the interface to use; for proper
         * VLAN support we have an nl80211-based mechanism.
         *
         * This is necessary, for example, for old hostapd versions that
         * don't use nl80211-based management TX/RX.
         */
        list_for_each_entry_rcu(tmp_sdata, &local->interfaces, list) {
                if (!ieee80211_sdata_running(tmp_sdata))
                        continue;
                if (tmp_sdata->vif.type == NL80211_IFTYPE_MONITOR ||
                    tmp_sdata->vif.type == NL80211_IFTYPE_AP_VLAN)
                        continue;
                if (ether_addr_equal(tmp_sdata->vif.addr, hdr->addr2)) {
                        sdata = tmp_sdata;
                        break;
                }
        }

        chanctx_conf = rcu_dereference(sdata->vif.bss_conf.chanctx_conf);
        if (!chanctx_conf) {
                tmp_sdata = rcu_dereference(local->monitor_sdata);
                if (tmp_sdata)
                        chanctx_conf =
                                rcu_dereference(tmp_sdata->vif.bss_conf.chanctx_conf);
        }

        if (chanctx_conf)
                chandef = &chanctx_conf->def;
        else
                goto fail_rcu;

        /*
         * If driver/HW supports IEEE80211_CHAN_CAN_MONITOR we still
         * shouldn't transmit on disabled channels.
         */
        if (!cfg80211_chandef_usable(local->hw.wiphy, chandef,
                                     IEEE80211_CHAN_DISABLED))
                goto fail_rcu;

        /*
         * Frame injection is not allowed if beaconing is not allowed
         * or if we need radar detection. Beaconing is usually not allowed when
         * the mode or operation (Adhoc, AP, Mesh) does not support DFS.
         * Passive scan is also used in world regulatory domains where
         * your country is not known and as such it should be treated as
         * NO TX unless the channel is explicitly allowed in which case
         * your current regulatory domain would not have the passive scan
         * flag.
         *
         * Since AP mode uses monitor interfaces to inject/TX management
         * frames we can make AP mode the exception to this rule once it
         * supports radar detection as its implementation can deal with
         * radar detection by itself. We can do that later by adding a
         * monitor flag interfaces used for AP support.
         */
        if (!cfg80211_reg_can_beacon(local->hw.wiphy, chandef,
                                     sdata->vif.type))
                goto fail_rcu;

        info->band = chandef->chan->band;

        /* Initialize skb->priority according to frame type and TID class,
         * with respect to the sub interface that the frame will actually
         * be transmitted on. If the DONT_REORDER flag is set, the original
         * skb-priority is preserved to assure frames injected with this
         * flag are not reordered relative to each other.
         */
        ieee80211_select_queue_80211(sdata, skb, hdr);
        skb_set_queue_mapping(skb, ieee80211_ac_from_tid(skb->priority));

        /*
         * Process the radiotap header. This will now take into account the
         * selected chandef above to accurately set injection rates and
         * retransmissions.
         */
        if (!ieee80211_parse_tx_radiotap(skb, dev))
                goto fail_rcu;

        /* remove the injection radiotap header */
        skb_pull(skb, len_rthdr);

        ieee80211_xmit(sdata, NULL, skb);
        rcu_read_unlock();

        return NETDEV_TX_OK;

fail_rcu:
        rcu_read_unlock();
fail:
        dev_kfree_skb(skb);
        return NETDEV_TX_OK; /* meaning, we dealt with the skb */
}

static inline bool ieee80211_is_tdls_setup(struct sk_buff *skb)
{
        u16 ethertype = (skb->data[12] << 8) | skb->data[13];

        return ethertype == ETH_P_TDLS &&
               skb->len > 14 &&
               skb->data[14] == WLAN_TDLS_SNAP_RFTYPE;
}

int ieee80211_lookup_ra_sta(struct ieee80211_sub_if_data *sdata,
                            struct sk_buff *skb,
                            struct sta_info **sta_out)
{
        struct sta_info *sta;

        switch (sdata->vif.type) {
        case NL80211_IFTYPE_AP_VLAN:
                sta = rcu_dereference(sdata->u.vlan.sta);
                if (sta) {
                        *sta_out = sta;
                        return 0;
                } else if (sdata->wdev.use_4addr) {
                        return -ENOLINK;
                }
                fallthrough;
        case NL80211_IFTYPE_AP:
        case NL80211_IFTYPE_OCB:
        case NL80211_IFTYPE_ADHOC:
                if (is_multicast_ether_addr(skb->data)) {
                        *sta_out = ERR_PTR(-ENOENT);
                        return 0;
                }
                sta = sta_info_get_bss(sdata, skb->data);
                break;
#ifdef CONFIG_MAC80211_MESH
        case NL80211_IFTYPE_MESH_POINT:
                /* determined much later */
                *sta_out = NULL;
                return 0;
#endif
        case NL80211_IFTYPE_STATION:
                if (sdata->wdev.wiphy->flags & WIPHY_FLAG_SUPPORTS_TDLS) {
                        sta = sta_info_get(sdata, skb->data);
                        if (sta && test_sta_flag(sta, WLAN_STA_TDLS_PEER)) {
                                if (test_sta_flag(sta,
                                                  WLAN_STA_TDLS_PEER_AUTH)) {
                                        *sta_out = sta;
                                        return 0;
                                }

                                /*
                                 * TDLS link during setup - throw out frames to
                                 * peer. Allow TDLS-setup frames to unauthorized
                                 * peers for the special case of a link teardown
                                 * after a TDLS sta is removed due to being
                                 * unreachable.
                                 */
                                if (!ieee80211_is_tdls_setup(skb))
                                        return -EINVAL;
                        }

                }

                sta = sta_info_get(sdata, sdata->vif.cfg.ap_addr);
                if (!sta)
                        return -ENOLINK;
                break;
        default:
                return -EINVAL;
        }

        *sta_out = sta ?: ERR_PTR(-ENOENT);
        return 0;
}

static u16 ieee80211_store_ack_skb(struct ieee80211_local *local,
                                   struct sk_buff *skb,
                                   u32 *info_flags,
                                   u64 *cookie)
{
        struct sk_buff *ack_skb;
        u16 info_id = 0;

        if (skb->sk)
                ack_skb = skb_clone_sk(skb);
        else
                ack_skb = skb_clone(skb, GFP_ATOMIC);

        if (ack_skb) {
                unsigned long flags;
                int id;

                spin_lock_irqsave(&local->ack_status_lock, flags);
                id = idr_alloc(&local->ack_status_frames, ack_skb,
                               1, 0x2000, GFP_ATOMIC);
                spin_unlock_irqrestore(&local->ack_status_lock, flags);

                if (id >= 0) {
                        info_id = id;
                        *info_flags |= IEEE80211_TX_CTL_REQ_TX_STATUS;
                        if (cookie) {
                                *cookie = ieee80211_mgmt_tx_cookie(local);
                                IEEE80211_SKB_CB(ack_skb)->ack.cookie = *cookie;
                        }
                } else {
                        kfree_skb(ack_skb);
                }
        }

        return info_id;
}

/**
 * ieee80211_build_hdr - build 802.11 header in the given frame
 * @sdata: virtual interface to build the header for
 * @skb: the skb to build the header in
 * @info_flags: skb flags to set
 * @sta: the station pointer
 * @ctrl_flags: info control flags to set
 * @cookie: cookie pointer to fill (if not %NULL)
 *
 * This function takes the skb with 802.3 header and reformats the header to
 * the appropriate IEEE 802.11 header based on which interface the packet is
 * being transmitted on.
 *
 * Note that this function also takes care of the TX status request and
 * potential unsharing of the SKB - this needs to be interleaved with the
 * header building.
 *
 * The function requires the read-side RCU lock held
 *
 * Returns: the (possibly reallocated) skb or an ERR_PTR() code
 */
static struct sk_buff *ieee80211_build_hdr(struct ieee80211_sub_if_data *sdata,
                                           struct sk_buff *skb, u32 info_flags,
                                           struct sta_info *sta, u32 ctrl_flags,
                                           u64 *cookie)
{
        struct ieee80211_local *local = sdata->local;
        struct ieee80211_tx_info *info;
        int head_need;
        u16 ethertype, hdrlen,  meshhdrlen = 0;
        __le16 fc;
        struct ieee80211_hdr hdr;
        struct ieee80211s_hdr mesh_hdr __maybe_unused;
        struct mesh_path __maybe_unused *mppath = NULL, *mpath = NULL;
        const u8 *encaps_data;
        int encaps_len, skip_header_bytes;
        bool wme_sta = false, authorized = false;
        bool tdls_peer;
        bool multicast;
        u16 info_id = 0;
        struct ieee80211_chanctx_conf *chanctx_conf = NULL;
        enum nl80211_band band;
        int ret;
        u8 link_id = u32_get_bits(ctrl_flags, IEEE80211_TX_CTRL_MLO_LINK);

        if (IS_ERR(sta))
                sta = NULL;

#ifdef CONFIG_MAC80211_DEBUGFS
        if (local->force_tx_status)
                info_flags |= IEEE80211_TX_CTL_REQ_TX_STATUS;
#endif

        /* convert Ethernet header to proper 802.11 header (based on
         * operation mode) */
        ethertype = (skb->data[12] << 8) | skb->data[13];
        fc = cpu_to_le16(IEEE80211_FTYPE_DATA | IEEE80211_STYPE_DATA);

        if (!ieee80211_vif_is_mld(&sdata->vif))
                chanctx_conf =
                        rcu_dereference(sdata->vif.bss_conf.chanctx_conf);

        switch (sdata->vif.type) {
        case NL80211_IFTYPE_AP_VLAN:
                if (sdata->wdev.use_4addr) {
                        fc |= cpu_to_le16(IEEE80211_FCTL_FROMDS | IEEE80211_FCTL_TODS);
                        /* RA TA DA SA */
                        memcpy(hdr.addr1, sta->sta.addr, ETH_ALEN);
                        memcpy(hdr.addr2, sdata->vif.addr, ETH_ALEN);
                        memcpy(hdr.addr3, skb->data, ETH_ALEN);
                        memcpy(hdr.addr4, skb->data + ETH_ALEN, ETH_ALEN);
                        hdrlen = 30;
                        authorized = test_sta_flag(sta, WLAN_STA_AUTHORIZED);
                        wme_sta = sta->sta.wme;
                }
                if (!ieee80211_vif_is_mld(&sdata->vif)) {
                        struct ieee80211_sub_if_data *ap_sdata;

                        /* override chanctx_conf from AP (we don't have one) */
                        ap_sdata = container_of(sdata->bss,
                                                struct ieee80211_sub_if_data,
                                                u.ap);
                        chanctx_conf =
                                rcu_dereference(ap_sdata->vif.bss_conf.chanctx_conf);
                }
                if (sdata->wdev.use_4addr)
                        break;
                fallthrough;
        case NL80211_IFTYPE_AP:
                fc |= cpu_to_le16(IEEE80211_FCTL_FROMDS);
                /* DA BSSID SA */
                memcpy(hdr.addr1, skb->data, ETH_ALEN);

                if (ieee80211_vif_is_mld(&sdata->vif) && sta && !sta->sta.mlo) {
                        struct ieee80211_link_data *link;

                        link_id = sta->deflink.link_id;
                        link = rcu_dereference(sdata->link[link_id]);
                        if (WARN_ON(!link)) {
                                ret = -ENOLINK;
                                goto free;
                        }
                        memcpy(hdr.addr2, link->conf->addr, ETH_ALEN);
                } else if (link_id == IEEE80211_LINK_UNSPECIFIED ||
                           (sta && sta->sta.mlo)) {
                        memcpy(hdr.addr2, sdata->vif.addr, ETH_ALEN);
                } else {
                        struct ieee80211_bss_conf *conf;

                        conf = rcu_dereference(sdata->vif.link_conf[link_id]);
                        if (unlikely(!conf)) {
                                ret = -ENOLINK;
                                goto free;
                        }

                        memcpy(hdr.addr2, conf->addr, ETH_ALEN);
                }

                memcpy(hdr.addr3, skb->data + ETH_ALEN, ETH_ALEN);
                hdrlen = 24;
                break;
#ifdef CONFIG_MAC80211_MESH
        case NL80211_IFTYPE_MESH_POINT:
                if (!is_multicast_ether_addr(skb->data)) {
                        struct sta_info *next_hop;
                        bool mpp_lookup = true;

                        mpath = mesh_path_lookup(sdata, skb->data);
                        if (mpath) {
                                mpp_lookup = false;
                                next_hop = rcu_dereference(mpath->next_hop);
                                if (!next_hop ||
                                    !(mpath->flags & (MESH_PATH_ACTIVE |
                                                      MESH_PATH_RESOLVING)))
                                        mpp_lookup = true;
                        }

                        if (mpp_lookup) {
                                mppath = mpp_path_lookup(sdata, skb->data);
                                if (mppath)
                                        mppath->exp_time = jiffies;
                        }

                        if (mppath && mpath)
                                mesh_path_del(sdata, mpath->dst);
                }

                /*
                 * Use address extension if it is a packet from
                 * another interface or if we know the destination
                 * is being proxied by a portal (i.e. portal address
                 * differs from proxied address)
                 */
                if (ether_addr_equal(sdata->vif.addr, skb->data + ETH_ALEN) &&
                    !(mppath && !ether_addr_equal(mppath->mpp, skb->data))) {
                        hdrlen = ieee80211_fill_mesh_addresses(&hdr, &fc,
                                        skb->data, skb->data + ETH_ALEN);
                        meshhdrlen = ieee80211_new_mesh_header(sdata, &mesh_hdr,
                                                               NULL, NULL);
                } else {
                        /* DS -> MBSS (802.11-2012 13.11.3.3).
                         * For unicast with unknown forwarding information,
                         * destination might be in the MBSS or if that fails
                         * forwarded to another mesh gate. In either case
                         * resolution will be handled in ieee80211_xmit(), so
                         * leave the original DA. This also works for mcast */
                        const u8 *mesh_da = skb->data;

                        if (mppath)
                                mesh_da = mppath->mpp;
                        else if (mpath)
                                mesh_da = mpath->dst;

                        hdrlen = ieee80211_fill_mesh_addresses(&hdr, &fc,
                                        mesh_da, sdata->vif.addr);
                        if (is_multicast_ether_addr(mesh_da))
                                /* DA TA mSA AE:SA */
                                meshhdrlen = ieee80211_new_mesh_header(
                                                sdata, &mesh_hdr,
                                                skb->data + ETH_ALEN, NULL);
                        else
                                /* RA TA mDA mSA AE:DA SA */
                                meshhdrlen = ieee80211_new_mesh_header(
                                                sdata, &mesh_hdr, skb->data,
                                                skb->data + ETH_ALEN);

                }

                /* For injected frames, fill RA right away as nexthop lookup
                 * will be skipped.
                 */
                if ((ctrl_flags & IEEE80211_TX_CTRL_SKIP_MPATH_LOOKUP) &&
                    is_zero_ether_addr(hdr.addr1))
                        memcpy(hdr.addr1, skb->data, ETH_ALEN);
                break;
#endif
        case NL80211_IFTYPE_STATION:
                /* we already did checks when looking up the RA STA */
                tdls_peer = test_sta_flag(sta, WLAN_STA_TDLS_PEER);

                if (tdls_peer) {
                        /* For TDLS only one link can be valid with peer STA */
                        int tdls_link_id = ieee80211_tdls_sta_link_id(sta);
                        struct ieee80211_link_data *link;

                        /* DA SA BSSID */
                        memcpy(hdr.addr1, skb->data, ETH_ALEN);
                        memcpy(hdr.addr2, skb->data + ETH_ALEN, ETH_ALEN);
                        link = rcu_dereference(sdata->link[tdls_link_id]);
                        if (WARN_ON_ONCE(!link)) {
                                ret = -EINVAL;
                                goto free;
                        }
                        memcpy(hdr.addr3, link->u.mgd.bssid, ETH_ALEN);
                        hdrlen = 24;
                }  else if (sdata->u.mgd.use_4addr &&
                            cpu_to_be16(ethertype) != sdata->control_port_protocol) {
                        fc |= cpu_to_le16(IEEE80211_FCTL_FROMDS |
                                          IEEE80211_FCTL_TODS);
                        /* RA TA DA SA */
                        memcpy(hdr.addr1, sdata->deflink.u.mgd.bssid, ETH_ALEN);
                        memcpy(hdr.addr2, sdata->vif.addr, ETH_ALEN);
                        memcpy(hdr.addr3, skb->data, ETH_ALEN);
                        memcpy(hdr.addr4, skb->data + ETH_ALEN, ETH_ALEN);
                        hdrlen = 30;
                } else {
                        fc |= cpu_to_le16(IEEE80211_FCTL_TODS);
                        /* BSSID SA DA */
                        memcpy(hdr.addr1, sdata->vif.cfg.ap_addr, ETH_ALEN);
                        memcpy(hdr.addr2, skb->data + ETH_ALEN, ETH_ALEN);
                        memcpy(hdr.addr3, skb->data, ETH_ALEN);
                        hdrlen = 24;
                }
                break;
        case NL80211_IFTYPE_OCB:
                /* DA SA BSSID */
                memcpy(hdr.addr1, skb->data, ETH_ALEN);
                memcpy(hdr.addr2, skb->data + ETH_ALEN, ETH_ALEN);
                eth_broadcast_addr(hdr.addr3);
                hdrlen = 24;
                break;
        case NL80211_IFTYPE_ADHOC:
                /* DA SA BSSID */
                memcpy(hdr.addr1, skb->data, ETH_ALEN);
                memcpy(hdr.addr2, skb->data + ETH_ALEN, ETH_ALEN);
                memcpy(hdr.addr3, sdata->u.ibss.bssid, ETH_ALEN);
                hdrlen = 24;
                break;
        default:
                ret = -EINVAL;
                goto free;
        }

        if (!chanctx_conf) {
                if (!ieee80211_vif_is_mld(&sdata->vif)) {
                        ret = -ENOTCONN;
                        goto free;
                }
                /* MLD transmissions must not rely on the band */
                band = 0;
        } else {
                band = chanctx_conf->def.chan->band;
        }

        multicast = is_multicast_ether_addr(hdr.addr1);

        /* sta is always NULL for mesh */
        if (sta) {
                authorized = test_sta_flag(sta, WLAN_STA_AUTHORIZED);
                wme_sta = sta->sta.wme;
        } else if (ieee80211_vif_is_mesh(&sdata->vif)) {
                /* For mesh, the use of the QoS header is mandatory */
                wme_sta = true;
        }

        /* receiver does QoS (which also means we do) use it */
        if (wme_sta) {
                fc |= cpu_to_le16(IEEE80211_STYPE_QOS_DATA);
                hdrlen += 2;
        }

        /*
         * Drop unicast frames to unauthorised stations unless they are
         * EAPOL frames from the local station.
         */
        if (unlikely(!ieee80211_vif_is_mesh(&sdata->vif) &&
                     (sdata->vif.type != NL80211_IFTYPE_OCB) &&
                     !multicast && !authorized &&
                     (cpu_to_be16(ethertype) != sdata->control_port_protocol ||
                      !ieee80211_is_our_addr(sdata, skb->data + ETH_ALEN, NULL)))) {
#ifdef CONFIG_MAC80211_VERBOSE_DEBUG
                net_info_ratelimited("%s: dropped frame to %pM (unauthorized port)\n",
                                    sdata->name, hdr.addr1);
#endif

                I802_DEBUG_INC(local->tx_handlers_drop_unauth_port);

                ret = -EPERM;
                goto free;
        }

        if (unlikely(!multicast &&
                     ((skb->sk &&
                       skb_shinfo(skb)->tx_flags & SKBTX_WIFI_STATUS) ||
                      ctrl_flags & IEEE80211_TX_CTL_REQ_TX_STATUS)))
                info_id = ieee80211_store_ack_skb(local, skb, &info_flags,
                                                  cookie);

        /*
         * If the skb is shared we need to obtain our own copy.
         */
        skb = skb_share_check(skb, GFP_ATOMIC);
        if (unlikely(!skb)) {
                ret = -ENOMEM;
                goto free;
        }

        hdr.frame_control = fc;
        hdr.duration_id = 0;
        hdr.seq_ctrl = 0;

        skip_header_bytes = ETH_HLEN;
        if (ethertype == ETH_P_AARP || ethertype == ETH_P_IPX) {
                encaps_data = bridge_tunnel_header;
                encaps_len = sizeof(bridge_tunnel_header);
                skip_header_bytes -= 2;
        } else if (ethertype >= ETH_P_802_3_MIN) {
                encaps_data = rfc1042_header;
                encaps_len = sizeof(rfc1042_header);
                skip_header_bytes -= 2;
        } else {
                encaps_data = NULL;
                encaps_len = 0;
        }

        skb_pull(skb, skip_header_bytes);
        head_need = hdrlen + encaps_len + meshhdrlen - skb_headroom(skb);

        /*
         * So we need to modify the skb header and hence need a copy of
         * that. The head_need variable above doesn't, so far, include
         * the needed header space that we don't need right away. If we
         * can, then we don't reallocate right now but only after the
         * frame arrives at the master device (if it does...)
         *
         * If we cannot, however, then we will reallocate to include all
         * the ever needed space. Also, if we need to reallocate it anyway,
         * make it big enough for everything we may ever need.
         */

        if (head_need > 0 || skb_cloned(skb)) {
                head_need += IEEE80211_ENCRYPT_HEADROOM;
                head_need += local->tx_headroom;
                head_need = max_t(int, 0, head_need);
                if (ieee80211_skb_resize(sdata, skb, head_need, ENCRYPT_DATA)) {
                        ieee80211_free_txskb(&local->hw, skb);
                        skb = NULL;
                        return ERR_PTR(-ENOMEM);
                }
        }

        if (encaps_data)
                memcpy(skb_push(skb, encaps_len), encaps_data, encaps_len);

#ifdef CONFIG_MAC80211_MESH
        if (meshhdrlen > 0)
                memcpy(skb_push(skb, meshhdrlen), &mesh_hdr, meshhdrlen);
#endif

        if (ieee80211_is_data_qos(fc)) {
                __le16 *qos_control;

                qos_control = skb_push(skb, 2);
                memcpy(skb_push(skb, hdrlen - 2), &hdr, hdrlen - 2);
                /*
                 * Maybe we could actually set some fields here, for now just
                 * initialise to zero to indicate no special operation.
                 */
                *qos_control = 0;
        } else
                memcpy(skb_push(skb, hdrlen), &hdr, hdrlen);

        skb_reset_mac_header(skb);

        info = IEEE80211_SKB_CB(skb);
        memset(info, 0, sizeof(*info));

        info->flags = info_flags;
        if (info_id) {
                info->status_data = info_id;
                info->status_data_idr = 1;
        }
        info->band = band;

        if (likely(!cookie)) {
                ctrl_flags |= u32_encode_bits(link_id,
                                              IEEE80211_TX_CTRL_MLO_LINK);
        } else {
                unsigned int pre_conf_link_id;

                /*
                 * ctrl_flags already have been set by
                 * ieee80211_tx_control_port(), here
                 * we just sanity check that
                 */

                pre_conf_link_id = u32_get_bits(ctrl_flags,
                                                IEEE80211_TX_CTRL_MLO_LINK);

                if (pre_conf_link_id != link_id &&
                    link_id != IEEE80211_LINK_UNSPECIFIED) {
#ifdef CONFIG_MAC80211_VERBOSE_DEBUG
                        net_info_ratelimited("%s: dropped frame to %pM with bad link ID request (%d vs. %d)\n",
                                             sdata->name, hdr.addr1,
                                             pre_conf_link_id, link_id);
#endif
                        ret = -EINVAL;
                        goto free;
                }
        }

        info->control.flags = ctrl_flags;

        return skb;
 free:
        kfree_skb(skb);
        return ERR_PTR(ret);
}

/*
 * fast-xmit overview
 *
 * The core idea of this fast-xmit is to remove per-packet checks by checking
 * them out of band. ieee80211_check_fast_xmit() implements the out-of-band
 * checks that are needed to get the sta->fast_tx pointer assigned, after which
 * much less work can be done per packet. For example, fragmentation must be
 * disabled or the fast_tx pointer will not be set. All the conditions are seen
 * in the code here.
 *
 * Once assigned, the fast_tx data structure also caches the per-packet 802.11
 * header and other data to aid packet processing in ieee80211_xmit_fast().
 *
 * The most difficult part of this is that when any of these assumptions
 * change, an external trigger (i.e. a call to ieee80211_clear_fast_xmit(),
 * ieee80211_check_fast_xmit() or friends) is required to reset the data,
 * since the per-packet code no longer checks the conditions. This is reflected
 * by the calls to these functions throughout the rest of the code, and must be
 * maintained if any of the TX path checks change.
 */

void ieee80211_check_fast_xmit(struct sta_info *sta)
{
        struct ieee80211_fast_tx build = {}, *fast_tx = NULL, *old;
        struct ieee80211_local *local = sta->local;
        struct ieee80211_sub_if_data *sdata = sta->sdata;
        struct ieee80211_hdr *hdr = (void *)build.hdr;
        struct ieee80211_chanctx_conf *chanctx_conf;
        __le16 fc;

        if (!ieee80211_hw_check(&local->hw, SUPPORT_FAST_XMIT))
                return;

        if (ieee80211_vif_is_mesh(&sdata->vif))
                mesh_fast_tx_flush_sta(sdata, sta);

        /* Locking here protects both the pointer itself, and against concurrent
         * invocations winning data access races to, e.g., the key pointer that
         * is used.
         * Without it, the invocation of this function right after the key
         * pointer changes wouldn't be sufficient, as another CPU could access
         * the pointer, then stall, and then do the cache update after the CPU
         * that invalidated the key.
         * With the locking, such scenarios cannot happen as the check for the
         * key and the fast-tx assignment are done atomically, so the CPU that
         * modifies the key will either wait or other one will see the key
         * cleared/changed already.
         */
        spin_lock_bh(&sta->lock);
        if (ieee80211_hw_check(&local->hw, SUPPORTS_PS) &&
            !ieee80211_hw_check(&local->hw, SUPPORTS_DYNAMIC_PS) &&
            sdata->vif.type == NL80211_IFTYPE_STATION)
                goto out;

        if (!test_sta_flag(sta, WLAN_STA_AUTHORIZED) || !sta->uploaded)
                goto out;

        if (test_sta_flag(sta, WLAN_STA_PS_STA) ||
            test_sta_flag(sta, WLAN_STA_PS_DRIVER) ||
            test_sta_flag(sta, WLAN_STA_PS_DELIVER) ||
            test_sta_flag(sta, WLAN_STA_CLEAR_PS_FILT))
                goto out;

        if (sdata->noack_map)
                goto out;

        /* fast-xmit doesn't handle fragmentation at all */
        if (local->hw.wiphy->frag_threshold != (u32)-1 &&
            !ieee80211_hw_check(&local->hw, SUPPORTS_TX_FRAG))
                goto out;

        if (!ieee80211_vif_is_mld(&sdata->vif)) {
                rcu_read_lock();
                chanctx_conf =
                        rcu_dereference(sdata->vif.bss_conf.chanctx_conf);
                if (!chanctx_conf) {
                        rcu_read_unlock();
                        goto out;
                }
                build.band = chanctx_conf->def.chan->band;
                rcu_read_unlock();
        } else {
                /* MLD transmissions must not rely on the band */
                build.band = 0;
        }

        fc = cpu_to_le16(IEEE80211_FTYPE_DATA | IEEE80211_STYPE_DATA);

        switch (sdata->vif.type) {
        case NL80211_IFTYPE_ADHOC:
                /* DA SA BSSID */
                build.da_offs = offsetof(struct ieee80211_hdr, addr1);
                build.sa_offs = offsetof(struct ieee80211_hdr, addr2);
                memcpy(hdr->addr3, sdata->u.ibss.bssid, ETH_ALEN);
                build.hdr_len = 24;
                break;
        case NL80211_IFTYPE_STATION:
                if (test_sta_flag(sta, WLAN_STA_TDLS_PEER)) {
                        /* For TDLS only one link can be valid with peer STA */
                        int tdls_link_id = ieee80211_tdls_sta_link_id(sta);
                        struct ieee80211_link_data *link;

                        /* DA SA BSSID */
                        build.da_offs = offsetof(struct ieee80211_hdr, addr1);
                        build.sa_offs = offsetof(struct ieee80211_hdr, addr2);
                        rcu_read_lock();
                        link = rcu_dereference(sdata->link[tdls_link_id]);
                        if (!WARN_ON_ONCE(!link))
                                memcpy(hdr->addr3, link->u.mgd.bssid, ETH_ALEN);
                        rcu_read_unlock();
                        build.hdr_len = 24;
                        break;
                }

                if (sdata->u.mgd.use_4addr) {
                        /* non-regular ethertype cannot use the fastpath */
                        fc |= cpu_to_le16(IEEE80211_FCTL_FROMDS |
                                          IEEE80211_FCTL_TODS);
                        /* RA TA DA SA */
                        memcpy(hdr->addr1, sdata->deflink.u.mgd.bssid, ETH_ALEN);
                        memcpy(hdr->addr2, sdata->vif.addr, ETH_ALEN);
                        build.da_offs = offsetof(struct ieee80211_hdr, addr3);
                        build.sa_offs = offsetof(struct ieee80211_hdr, addr4);
                        build.hdr_len = 30;
                        break;
                }
                fc |= cpu_to_le16(IEEE80211_FCTL_TODS);
                /* BSSID SA DA */
                memcpy(hdr->addr1, sdata->vif.cfg.ap_addr, ETH_ALEN);
                build.da_offs = offsetof(struct ieee80211_hdr, addr3);
                build.sa_offs = offsetof(struct ieee80211_hdr, addr2);
                build.hdr_len = 24;
                break;
        case NL80211_IFTYPE_AP_VLAN:
                if (sdata->wdev.use_4addr) {
                        fc |= cpu_to_le16(IEEE80211_FCTL_FROMDS |
                                          IEEE80211_FCTL_TODS);
                        /* RA TA DA SA */
                        memcpy(hdr->addr1, sta->sta.addr, ETH_ALEN);
                        memcpy(hdr->addr2, sdata->vif.addr, ETH_ALEN);
                        build.da_offs = offsetof(struct ieee80211_hdr, addr3);
                        build.sa_offs = offsetof(struct ieee80211_hdr, addr4);
                        build.hdr_len = 30;
                        break;
                }
                fallthrough;
        case NL80211_IFTYPE_AP:
                fc |= cpu_to_le16(IEEE80211_FCTL_FROMDS);
                /* DA BSSID SA */
                build.da_offs = offsetof(struct ieee80211_hdr, addr1);
                if (sta->sta.mlo || !ieee80211_vif_is_mld(&sdata->vif)) {
                        memcpy(hdr->addr2, sdata->vif.addr, ETH_ALEN);
                } else {
                        unsigned int link_id = sta->deflink.link_id;
                        struct ieee80211_link_data *link;

                        rcu_read_lock();
                        link = rcu_dereference(sdata->link[link_id]);
                        if (WARN_ON(!link)) {
                                rcu_read_unlock();
                                goto out;
                        }
                        memcpy(hdr->addr2, link->conf->addr, ETH_ALEN);
                        rcu_read_unlock();
                }
                build.sa_offs = offsetof(struct ieee80211_hdr, addr3);
                build.hdr_len = 24;
                break;
        default:
                /* not handled on fast-xmit */
                goto out;
        }

        if (sta->sta.wme) {
                build.hdr_len += 2;
                fc |= cpu_to_le16(IEEE80211_STYPE_QOS_DATA);
        }

        /* We store the key here so there's no point in using rcu_dereference()
         * but that's fine because the code that changes the pointers will call
         * this function after doing so. For a single CPU that would be enough,
         * for multiple see the comment above.
         */
        build.key = rcu_access_pointer(sta->ptk[sta->ptk_idx]);
        if (!build.key)
                build.key = rcu_access_pointer(sdata->default_unicast_key);
        if (build.key) {
                bool gen_iv, iv_spc, mmic;

                gen_iv = build.key->conf.flags & IEEE80211_KEY_FLAG_GENERATE_IV;
                iv_spc = build.key->conf.flags & IEEE80211_KEY_FLAG_PUT_IV_SPACE;
                mmic = build.key->conf.flags &
                        (IEEE80211_KEY_FLAG_GENERATE_MMIC |
                         IEEE80211_KEY_FLAG_PUT_MIC_SPACE);

                /* don't handle software crypto */
                if (!(build.key->flags & KEY_FLAG_UPLOADED_TO_HARDWARE))
                        goto out;

                /* Key is being removed */
                if (build.key->flags & KEY_FLAG_TAINTED)
                        goto out;

                switch (build.key->conf.cipher) {
                case WLAN_CIPHER_SUITE_CCMP:
                case WLAN_CIPHER_SUITE_CCMP_256:
                        if (gen_iv)
                                build.pn_offs = build.hdr_len;
                        if (gen_iv || iv_spc)
                                build.hdr_len += IEEE80211_CCMP_HDR_LEN;
                        break;
                case WLAN_CIPHER_SUITE_GCMP:
                case WLAN_CIPHER_SUITE_GCMP_256:
                        if (gen_iv)
                                build.pn_offs = build.hdr_len;
                        if (gen_iv || iv_spc)
                                build.hdr_len += IEEE80211_GCMP_HDR_LEN;
                        break;
                case WLAN_CIPHER_SUITE_TKIP:
                        /* cannot handle MMIC or IV generation in xmit-fast */
                        if (mmic || gen_iv)
                                goto out;
                        if (iv_spc)
                                build.hdr_len += IEEE80211_TKIP_IV_LEN;
                        break;
                case WLAN_CIPHER_SUITE_WEP40:
                case WLAN_CIPHER_SUITE_WEP104:
                        /* cannot handle IV generation in fast-xmit */
                        if (gen_iv)
                                goto out;
                        if (iv_spc)
                                build.hdr_len += IEEE80211_WEP_IV_LEN;
                        break;
                case WLAN_CIPHER_SUITE_AES_CMAC:
                case WLAN_CIPHER_SUITE_BIP_CMAC_256:
                case WLAN_CIPHER_SUITE_BIP_GMAC_128:
                case WLAN_CIPHER_SUITE_BIP_GMAC_256:
                        WARN(1,
                             "management cipher suite 0x%x enabled for data\n",
                             build.key->conf.cipher);
                        goto out;
                default:
                        /* we don't know how to generate IVs for this at all */
                        if (WARN_ON(gen_iv))
                                goto out;
                }

                fc |= cpu_to_le16(IEEE80211_FCTL_PROTECTED);
        }

        hdr->frame_control = fc;

        memcpy(build.hdr + build.hdr_len,
               rfc1042_header,  sizeof(rfc1042_header));
        build.hdr_len += sizeof(rfc1042_header);

        fast_tx = kmemdup(&build, sizeof(build), GFP_ATOMIC);
        /* if the kmemdup fails, continue w/o fast_tx */

 out:
        /* we might have raced against another call to this function */
        old = rcu_dereference_protected(sta->fast_tx,
                                        lockdep_is_held(&sta->lock));
        rcu_assign_pointer(sta->fast_tx, fast_tx);
        if (old)
                kfree_rcu(old, rcu_head);
        spin_unlock_bh(&sta->lock);
}

void ieee80211_check_fast_xmit_all(struct ieee80211_local *local)
{
        struct sta_info *sta;

        rcu_read_lock();
        list_for_each_entry_rcu(sta, &local->sta_list, list)
                ieee80211_check_fast_xmit(sta);
        rcu_read_unlock();
}

void ieee80211_check_fast_xmit_iface(struct ieee80211_sub_if_data *sdata)
{
        struct ieee80211_local *local = sdata->local;
        struct sta_info *sta;

        rcu_read_lock();

        list_for_each_entry_rcu(sta, &local->sta_list, list) {
                if (sdata != sta->sdata &&
                    (!sta->sdata->bss || sta->sdata->bss != sdata->bss))
                        continue;
                ieee80211_check_fast_xmit(sta);
        }

        rcu_read_unlock();
}

void ieee80211_clear_fast_xmit(struct sta_info *sta)
{
        struct ieee80211_fast_tx *fast_tx;

        spin_lock_bh(&sta->lock);
        fast_tx = rcu_dereference_protected(sta->fast_tx,
                                            lockdep_is_held(&sta->lock));
        RCU_INIT_POINTER(sta->fast_tx, NULL);
        spin_unlock_bh(&sta->lock);

        if (fast_tx)
                kfree_rcu(fast_tx, rcu_head);
}

static bool ieee80211_amsdu_realloc_pad(struct ieee80211_local *local,
                                        struct sk_buff *skb, int headroom)
{
        if (skb_headroom(skb) < headroom) {
                I802_DEBUG_INC(local->tx_expand_skb_head);

                if (pskb_expand_head(skb, headroom, 0, GFP_ATOMIC)) {
                        wiphy_debug(local->hw.wiphy,
                                    "failed to reallocate TX buffer\n");
                        return false;
                }
        }

        return true;
}

static bool ieee80211_amsdu_prepare_head(struct ieee80211_sub_if_data *sdata,
                                         struct ieee80211_fast_tx *fast_tx,
                                         struct sk_buff *skb)
{
        struct ieee80211_local *local = sdata->local;
        struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb);
        struct ieee80211_hdr *hdr;
        struct ethhdr *amsdu_hdr;
        int hdr_len = fast_tx->hdr_len - sizeof(rfc1042_header);
        int subframe_len = skb->len - hdr_len;
        void *data;
        u8 *qc, *h_80211_src, *h_80211_dst;
        const u8 *bssid;

        if (info->flags & IEEE80211_TX_CTL_RATE_CTRL_PROBE)
                return false;

        if (info->control.flags & IEEE80211_TX_CTRL_AMSDU)
                return true;

        if (!ieee80211_amsdu_realloc_pad(local, skb,
                                         sizeof(*amsdu_hdr) +
                                         local->hw.extra_tx_headroom))
                return false;

        data = skb_push(skb, sizeof(*amsdu_hdr));
        memmove(data, data + sizeof(*amsdu_hdr), hdr_len);
        hdr = data;
        amsdu_hdr = data + hdr_len;
        /* h_80211_src/dst is addr* field within hdr */
        h_80211_src = data + fast_tx->sa_offs;
        h_80211_dst = data + fast_tx->da_offs;

        amsdu_hdr->h_proto = cpu_to_be16(subframe_len);
        ether_addr_copy(amsdu_hdr->h_source, h_80211_src);
        ether_addr_copy(amsdu_hdr->h_dest, h_80211_dst);

        /* according to IEEE 802.11-2012 8.3.2 table 8-19, the outer SA/DA
         * fields needs to be changed to BSSID for A-MSDU frames depending
         * on FromDS/ToDS values.
         */
        switch (sdata->vif.type) {
        case NL80211_IFTYPE_STATION:
                bssid = sdata->vif.cfg.ap_addr;
                break;
        case NL80211_IFTYPE_AP:
        case NL80211_IFTYPE_AP_VLAN:
                bssid = sdata->vif.addr;
                break;
        default:
                bssid = NULL;
        }

        if (bssid && ieee80211_has_fromds(hdr->frame_control))
                ether_addr_copy(h_80211_src, bssid);

        if (bssid && ieee80211_has_tods(hdr->frame_control))
                ether_addr_copy(h_80211_dst, bssid);

        qc = ieee80211_get_qos_ctl(hdr);
        *qc |= IEEE80211_QOS_CTL_A_MSDU_PRESENT;

        info->control.flags |= IEEE80211_TX_CTRL_AMSDU;

        return true;
}

static bool ieee80211_amsdu_aggregate(struct ieee80211_sub_if_data *sdata,
                                      struct sta_info *sta,
                                      struct ieee80211_fast_tx *fast_tx,
                                      struct sk_buff *skb,
                                      const u8 *da, const u8 *sa)
{
        struct ieee80211_local *local = sdata->local;
        struct fq *fq = &local->fq;
        struct fq_tin *tin;
        struct fq_flow *flow;
        u8 tid = skb->priority & IEEE80211_QOS_CTL_TAG1D_MASK;
        struct ieee80211_txq *txq = sta->sta.txq[tid];
        struct txq_info *txqi;
        struct sk_buff **frag_tail, *head;
        int subframe_len = skb->len - ETH_ALEN;
        u8 max_subframes = sta->sta.max_amsdu_subframes;
        int max_frags = local->hw.max_tx_fragments;
        int max_amsdu_len = sta->sta.cur->max_amsdu_len;
        int orig_truesize;
        u32 flow_idx;
        __be16 len;
        void *data;
        bool ret = false;
        unsigned int orig_len;
        int n = 2, nfrags, pad = 0;
        u16 hdrlen;

        if (!ieee80211_hw_check(&local->hw, TX_AMSDU))
                return false;

        if (sdata->vif.offload_flags & IEEE80211_OFFLOAD_ENCAP_ENABLED)
                return false;

        if (ieee80211_vif_is_mesh(&sdata->vif))
                return false;

        if (skb_is_gso(skb))
                return false;

        if (!txq)
                return false;

        txqi = to_txq_info(txq);
        if (test_bit(IEEE80211_TXQ_NO_AMSDU, &txqi->flags))
                return false;

        if (sta->sta.cur->max_rc_amsdu_len)
                max_amsdu_len = min_t(int, max_amsdu_len,
                                      sta->sta.cur->max_rc_amsdu_len);

        if (sta->sta.cur->max_tid_amsdu_len[tid])
                max_amsdu_len = min_t(int, max_amsdu_len,
                                      sta->sta.cur->max_tid_amsdu_len[tid]);

        flow_idx = fq_flow_idx(fq, skb);

        spin_lock_bh(&fq->lock);

        /* TODO: Ideally aggregation should be done on dequeue to remain
         * responsive to environment changes.
         */

        tin = &txqi->tin;
        flow = fq_flow_classify(fq, tin, flow_idx, skb);
        head = skb_peek_tail(&flow->queue);
        if (!head || skb_is_gso(head))
                goto out;

        orig_truesize = head->truesize;
        orig_len = head->len;

        if (skb->len + head->len > max_amsdu_len)
                goto out;

        nfrags = 1 + skb_shinfo(skb)->nr_frags;
        nfrags += 1 + skb_shinfo(head)->nr_frags;
        frag_tail = &skb_shinfo(head)->frag_list;
        while (*frag_tail) {
                nfrags += 1 + skb_shinfo(*frag_tail)->nr_frags;
                frag_tail = &(*frag_tail)->next;
                n++;
        }

        if (max_subframes && n > max_subframes)
                goto out;

        if (max_frags && nfrags > max_frags)
                goto out;

        if (!drv_can_aggregate_in_amsdu(local, head, skb))
                goto out;

        if (!ieee80211_amsdu_prepare_head(sdata, fast_tx, head))
                goto out;

        /* If n == 2, the "while (*frag_tail)" loop above didn't execute
         * and  frag_tail should be &skb_shinfo(head)->frag_list.
         * However, ieee80211_amsdu_prepare_head() can reallocate it.
         * Reload frag_tail to have it pointing to the correct place.
         */
        if (n == 2)
                frag_tail = &skb_shinfo(head)->frag_list;

        /*
         * Pad out the previous subframe to a multiple of 4 by adding the
         * padding to the next one, that's being added. Note that head->len
         * is the length of the full A-MSDU, but that works since each time
         * we add a new subframe we pad out the previous one to a multiple
         * of 4 and thus it no longer matters in the next round.
         */
        hdrlen = fast_tx->hdr_len - sizeof(rfc1042_header);
        if ((head->len - hdrlen) & 3)
                pad = 4 - ((head->len - hdrlen) & 3);

        if (!ieee80211_amsdu_realloc_pad(local, skb, sizeof(rfc1042_header) +
                                                     2 + pad))
                goto out_recalc;

        ret = true;
        data = skb_push(skb, ETH_ALEN + 2);
        ether_addr_copy(data, da);
        ether_addr_copy(data + ETH_ALEN, sa);

        data += 2 * ETH_ALEN;
        len = cpu_to_be16(subframe_len);
        memcpy(data, &len, 2);
        memcpy(data + 2, rfc1042_header, sizeof(rfc1042_header));

        memset(skb_push(skb, pad), 0, pad);

        head->len += skb->len;
        head->data_len += skb->len;
        *frag_tail = skb;

out_recalc:
        fq->memory_usage += head->truesize - orig_truesize;
        if (head->len != orig_len) {
                flow->backlog += head->len - orig_len;
                tin->backlog_bytes += head->len - orig_len;
        }
out:
        spin_unlock_bh(&fq->lock);

        return ret;
}

/*
 * Can be called while the sta lock is held. Anything that can cause packets to
 * be generated will cause deadlock!
 */
static ieee80211_tx_result
ieee80211_xmit_fast_finish(struct ieee80211_sub_if_data *sdata,
                           struct sta_info *sta, u8 pn_offs,
                           struct ieee80211_key *key,
                           struct ieee80211_tx_data *tx)
{
        struct sk_buff *skb = tx->skb;
        struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb);
        struct ieee80211_hdr *hdr = (void *)skb->data;
        u8 tid = IEEE80211_NUM_TIDS;

        if (!ieee80211_hw_check(&tx->local->hw, HAS_RATE_CONTROL) &&
            ieee80211_tx_h_rate_ctrl(tx) != TX_CONTINUE)
                return TX_DROP;

        if (key)
                info->control.hw_key = &key->conf;

        dev_sw_netstats_tx_add(skb->dev, 1, skb->len);

        if (hdr->frame_control & cpu_to_le16(IEEE80211_STYPE_QOS_DATA)) {
                tid = skb->priority & IEEE80211_QOS_CTL_TAG1D_MASK;
                hdr->seq_ctrl = ieee80211_tx_next_seq(sta, tid);
        } else {
                info->flags |= IEEE80211_TX_CTL_ASSIGN_SEQ;
                hdr->seq_ctrl = cpu_to_le16(sdata->sequence_number);
                sdata->sequence_number += 0x10;
        }

        if (skb_shinfo(skb)->gso_size)
                sta->deflink.tx_stats.msdu[tid] +=
                        DIV_ROUND_UP(skb->len, skb_shinfo(skb)->gso_size);
        else
                sta->deflink.tx_stats.msdu[tid]++;

        info->hw_queue = sdata->vif.hw_queue[skb_get_queue_mapping(skb)];

        /* statistics normally done by ieee80211_tx_h_stats (but that
         * has to consider fragmentation, so is more complex)
         */
        sta->deflink.tx_stats.bytes[skb_get_queue_mapping(skb)] += skb->len;
        sta->deflink.tx_stats.packets[skb_get_queue_mapping(skb)]++;

        if (pn_offs) {
                u64 pn;
                u8 *crypto_hdr = skb->data + pn_offs;

                switch (key->conf.cipher) {
                case WLAN_CIPHER_SUITE_CCMP:
                case WLAN_CIPHER_SUITE_CCMP_256:
                case WLAN_CIPHER_SUITE_GCMP:
                case WLAN_CIPHER_SUITE_GCMP_256:
                        pn = atomic64_inc_return(&key->conf.tx_pn);
                        crypto_hdr[0] = pn;
                        crypto_hdr[1] = pn >> 8;
                        crypto_hdr[3] = 0x20 | (key->conf.keyidx << 6);
                        crypto_hdr[4] = pn >> 16;
                        crypto_hdr[5] = pn >> 24;
                        crypto_hdr[6] = pn >> 32;
                        crypto_hdr[7] = pn >> 40;
                        break;
                }
        }

        return TX_CONTINUE;
}

static netdev_features_t
ieee80211_sdata_netdev_features(struct ieee80211_sub_if_data *sdata)
{
        if (sdata->vif.type != NL80211_IFTYPE_AP_VLAN)
                return sdata->vif.netdev_features;

        if (!sdata->bss)
                return 0;

        sdata = container_of(sdata->bss, struct ieee80211_sub_if_data, u.ap);
        return sdata->vif.netdev_features;
}

static struct sk_buff *
ieee80211_tx_skb_fixup(struct sk_buff *skb, netdev_features_t features)
{
        if (skb_is_gso(skb)) {
                struct sk_buff *segs;

                segs = skb_gso_segment(skb, features);
                if (!segs)
                        return skb;
                if (IS_ERR(segs))
                        goto free;

                consume_skb(skb);
                return segs;
        }

        if (skb_needs_linearize(skb, features) && __skb_linearize(skb))
                goto free;

        if (skb->ip_summed == CHECKSUM_PARTIAL) {
                int ofs = skb_checksum_start_offset(skb);

                if (skb->encapsulation)
                        skb_set_inner_transport_header(skb, ofs);
                else
                        skb_set_transport_header(skb, ofs);

                if (skb_csum_hwoffload_help(skb, features))
                        goto free;
        }

        skb_mark_not_on_list(skb);
        return skb;

free:
        kfree_skb(skb);
        return NULL;
}

void __ieee80211_xmit_fast(struct ieee80211_sub_if_data *sdata,
                           struct sta_info *sta,
                           struct ieee80211_fast_tx *fast_tx,
                           struct sk_buff *skb, bool ampdu,
                           const u8 *da, const u8 *sa)
{
        struct ieee80211_local *local = sdata->local;
        struct ieee80211_hdr *hdr = (void *)fast_tx->hdr;
        struct ieee80211_tx_info *info;
        struct ieee80211_tx_data tx;
        ieee80211_tx_result r;
        int hw_headroom = sdata->local->hw.extra_tx_headroom;
        int extra_head = fast_tx->hdr_len - (ETH_HLEN - 2);

        skb = skb_share_check(skb, GFP_ATOMIC);
        if (unlikely(!skb))
                return;

        if ((hdr->frame_control & cpu_to_le16(IEEE80211_STYPE_QOS_DATA)) &&
            ieee80211_amsdu_aggregate(sdata, sta, fast_tx, skb, da, sa))
                return;

        /* will not be crypto-handled beyond what we do here, so use false
         * as the may-encrypt argument for the resize to not account for
         * more room than we already have in 'extra_head'
         */
        if (unlikely(ieee80211_skb_resize(sdata, skb,
                                          max_t(int, extra_head + hw_headroom -
                                                     skb_headroom(skb), 0),
                                          ENCRYPT_NO)))
                goto free;

        hdr = skb_push(skb, extra_head);
        memcpy(skb->data, fast_tx->hdr, fast_tx->hdr_len);
        memcpy(skb->data + fast_tx->da_offs, da, ETH_ALEN);
        memcpy(skb->data + fast_tx->sa_offs, sa, ETH_ALEN);

        info = IEEE80211_SKB_CB(skb);
        memset(info, 0, sizeof(*info));
        info->band = fast_tx->band;
        info->control.vif = &sdata->vif;
        info->flags = IEEE80211_TX_CTL_FIRST_FRAGMENT |
                      IEEE80211_TX_CTL_DONTFRAG;
        info->control.flags = IEEE80211_TX_CTRL_FAST_XMIT |
                              u32_encode_bits(IEEE80211_LINK_UNSPECIFIED,
                                              IEEE80211_TX_CTRL_MLO_LINK);

#ifdef CONFIG_MAC80211_DEBUGFS
        if (local->force_tx_status)
                info->flags |= IEEE80211_TX_CTL_REQ_TX_STATUS;
#endif

        if (hdr->frame_control & cpu_to_le16(IEEE80211_STYPE_QOS_DATA)) {
                u8 tid = skb->priority & IEEE80211_QOS_CTL_TAG1D_MASK;

                *ieee80211_get_qos_ctl(hdr) = tid;
        }

        __skb_queue_head_init(&tx.skbs);

        tx.flags = IEEE80211_TX_UNICAST;
        tx.local = local;
        tx.sdata = sdata;
        tx.sta = sta;
        tx.key = fast_tx->key;

        if (ieee80211_queue_skb(local, sdata, sta, skb))
                return;

        tx.skb = skb;
        r = ieee80211_xmit_fast_finish(sdata, sta, fast_tx->pn_offs,
                                       fast_tx->key, &tx);
        tx.skb = NULL;
        if (r == TX_DROP)
                goto free;

        if (sdata->vif.type == NL80211_IFTYPE_AP_VLAN)
                sdata = container_of(sdata->bss,
                                     struct ieee80211_sub_if_data, u.ap);

        __skb_queue_tail(&tx.skbs, skb);
        ieee80211_tx_frags(local, &sdata->vif, sta, &tx.skbs, false);
        return;

free:
        kfree_skb(skb);
}

static bool ieee80211_xmit_fast(struct ieee80211_sub_if_data *sdata,
                                struct sta_info *sta,
                                struct ieee80211_fast_tx *fast_tx,
                                struct sk_buff *skb)
{
        u16 ethertype = (skb->data[12] << 8) | skb->data[13];
        struct ieee80211_hdr *hdr = (void *)fast_tx->hdr;
        struct tid_ampdu_tx *tid_tx = NULL;
        struct sk_buff *next;
        struct ethhdr eth;
        u8 tid = IEEE80211_NUM_TIDS;

        /* control port protocol needs a lot of special handling */
        if (cpu_to_be16(ethertype) == sdata->control_port_protocol)
                return false;

        /* only RFC 1042 SNAP */
        if (ethertype < ETH_P_802_3_MIN)
                return false;

        /* don't handle TX status request here either */
        if (skb->sk && skb_shinfo(skb)->tx_flags & SKBTX_WIFI_STATUS)
                return false;

        if (hdr->frame_control & cpu_to_le16(IEEE80211_STYPE_QOS_DATA)) {
                tid = skb->priority & IEEE80211_QOS_CTL_TAG1D_MASK;
                tid_tx = rcu_dereference(sta->ampdu_mlme.tid_tx[tid]);
                if (tid_tx) {
                        if (!test_bit(HT_AGG_STATE_OPERATIONAL, &tid_tx->state))
                                return false;
                        if (tid_tx->timeout)
                                tid_tx->last_tx = jiffies;
                }
        }

        memcpy(&eth, skb->data, ETH_HLEN - 2);

        /* after this point (skb is modified) we cannot return false */
        skb = ieee80211_tx_skb_fixup(skb, ieee80211_sdata_netdev_features(sdata));
        if (!skb)
                return true;

        skb_list_walk_safe(skb, skb, next) {
                skb_mark_not_on_list(skb);
                __ieee80211_xmit_fast(sdata, sta, fast_tx, skb, tid_tx,
                                      eth.h_dest, eth.h_source);
        }

        return true;
}

struct sk_buff *ieee80211_tx_dequeue(struct ieee80211_hw *hw,
                                     struct ieee80211_txq *txq)
{
        struct ieee80211_local *local = hw_to_local(hw);
        struct txq_info *txqi = container_of(txq, struct txq_info, txq);
        struct ieee80211_hdr *hdr;
        struct sk_buff *skb = NULL;
        struct fq *fq = &local->fq;
        struct fq_tin *tin = &txqi->tin;
        struct ieee80211_tx_info *info;
        struct ieee80211_tx_data tx;
        ieee80211_tx_result r;
        struct ieee80211_vif *vif = txq->vif;
        int q = vif->hw_queue[txq->ac];
        unsigned long flags;
        bool q_stopped;

        WARN_ON_ONCE(softirq_count() == 0);

        if (!ieee80211_txq_airtime_check(hw, txq))
                return NULL;

begin:
        spin_lock_irqsave(&local->queue_stop_reason_lock, flags);
        q_stopped = local->queue_stop_reasons[q];
        spin_unlock_irqrestore(&local->queue_stop_reason_lock, flags);

        if (unlikely(q_stopped)) {
                /* mark for waking later */
                set_bit(IEEE80211_TXQ_DIRTY, &txqi->flags);
                return NULL;
        }

        spin_lock_bh(&fq->lock);

        /* Make sure fragments stay together. */
        skb = __skb_dequeue(&txqi->frags);
        if (unlikely(skb)) {
                if (!(IEEE80211_SKB_CB(skb)->control.flags &
                                IEEE80211_TX_INTCFL_NEED_TXPROCESSING))
                        goto out;
                IEEE80211_SKB_CB(skb)->control.flags &=
                        ~IEEE80211_TX_INTCFL_NEED_TXPROCESSING;
        } else {
                if (unlikely(test_bit(IEEE80211_TXQ_STOP, &txqi->flags)))
                        goto out;

                skb = fq_tin_dequeue(fq, tin, fq_tin_dequeue_func);
        }

        if (!skb)
                goto out;

        spin_unlock_bh(&fq->lock);

        hdr = (struct ieee80211_hdr *)skb->data;
        info = IEEE80211_SKB_CB(skb);

        memset(&tx, 0, sizeof(tx));
        __skb_queue_head_init(&tx.skbs);
        tx.local = local;
        tx.skb = skb;
        tx.sdata = vif_to_sdata(info->control.vif);

        if (txq->sta) {
                tx.sta = container_of(txq->sta, struct sta_info, sta);
                /*
                 * Drop unicast frames to unauthorised stations unless they are
                 * injected frames or EAPOL frames from the local station.
                 */
                if (unlikely(!(info->flags & IEEE80211_TX_CTL_INJECTED) &&
                             ieee80211_is_data(hdr->frame_control) &&
                             !ieee80211_vif_is_mesh(&tx.sdata->vif) &&
                             tx.sdata->vif.type != NL80211_IFTYPE_OCB &&
                             !is_multicast_ether_addr(hdr->addr1) &&
                             !test_sta_flag(tx.sta, WLAN_STA_AUTHORIZED) &&
                             (!(info->control.flags &
                                IEEE80211_TX_CTRL_PORT_CTRL_PROTO) ||
                              !ieee80211_is_our_addr(tx.sdata, hdr->addr2,
                                                     NULL)))) {
                        I802_DEBUG_INC(local->tx_handlers_drop_unauth_port);
                        ieee80211_free_txskb(&local->hw, skb);
                        goto begin;
                }
        }

        /*
         * The key can be removed while the packet was queued, so need to call
         * this here to get the current key.
         */
        r = ieee80211_tx_h_select_key(&tx);
        if (r != TX_CONTINUE) {
                ieee80211_free_txskb(&local->hw, skb);
                goto begin;
        }

        if (test_bit(IEEE80211_TXQ_AMPDU, &txqi->flags))
                info->flags |= (IEEE80211_TX_CTL_AMPDU |
                                IEEE80211_TX_CTL_DONTFRAG);

        if (info->flags & IEEE80211_TX_CTL_HW_80211_ENCAP) {
                if (!ieee80211_hw_check(&local->hw, HAS_RATE_CONTROL)) {
                        r = ieee80211_tx_h_rate_ctrl(&tx);
                        if (r != TX_CONTINUE) {
                                ieee80211_free_txskb(&local->hw, skb);
                                goto begin;
                        }
                }
                goto encap_out;
        }

        if (info->control.flags & IEEE80211_TX_CTRL_FAST_XMIT) {
                struct sta_info *sta = container_of(txq->sta, struct sta_info,
                                                    sta);
                u8 pn_offs = 0;

                if (tx.key &&
                    (tx.key->conf.flags & IEEE80211_KEY_FLAG_GENERATE_IV))
                        pn_offs = ieee80211_hdrlen(hdr->frame_control);

                r = ieee80211_xmit_fast_finish(sta->sdata, sta, pn_offs,
                                               tx.key, &tx);
                if (r != TX_CONTINUE) {
                        ieee80211_free_txskb(&local->hw, skb);
                        goto begin;
                }
        } else {
                if (invoke_tx_handlers_late(&tx))
                        goto begin;

                skb = __skb_dequeue(&tx.skbs);
                info = IEEE80211_SKB_CB(skb);

                if (!skb_queue_empty(&tx.skbs)) {
                        spin_lock_bh(&fq->lock);
                        skb_queue_splice_tail(&tx.skbs, &txqi->frags);
                        spin_unlock_bh(&fq->lock);
                }
        }

        if (skb_has_frag_list(skb) &&
            !ieee80211_hw_check(&local->hw, TX_FRAG_LIST)) {
                if (skb_linearize(skb)) {
                        ieee80211_free_txskb(&local->hw, skb);
                        goto begin;
                }
        }

        switch (tx.sdata->vif.type) {
        case NL80211_IFTYPE_MONITOR:
                if ((tx.sdata->u.mntr.flags & MONITOR_FLAG_ACTIVE) ||
                    ieee80211_hw_check(&local->hw, NO_VIRTUAL_MONITOR)) {
                        vif = &tx.sdata->vif;
                        break;
                }
                tx.sdata = rcu_dereference(local->monitor_sdata);
                if (tx.sdata &&
                    ieee80211_hw_check(&local->hw, WANT_MONITOR_VIF)) {
                        vif = &tx.sdata->vif;
                        info->hw_queue =
                                vif->hw_queue[skb_get_queue_mapping(skb)];
                } else if (ieee80211_hw_check(&local->hw, QUEUE_CONTROL)) {
                        ieee80211_free_txskb(&local->hw, skb);
                        goto begin;
                } else {
                        info->control.vif = NULL;
                        return skb;
                }
                break;
        case NL80211_IFTYPE_AP_VLAN:
                tx.sdata = container_of(tx.sdata->bss,
                                        struct ieee80211_sub_if_data, u.ap);
                fallthrough;
        default:
                vif = &tx.sdata->vif;
                break;
        }

encap_out:
        info->control.vif = vif;

        if (tx.sta &&
            wiphy_ext_feature_isset(local->hw.wiphy, NL80211_EXT_FEATURE_AQL)) {
                bool ampdu = txq->ac != IEEE80211_AC_VO;
                u32 airtime;

                airtime = ieee80211_calc_expected_tx_airtime(hw, vif, txq->sta,
                                                             skb->len, ampdu);
                if (airtime) {
                        airtime = ieee80211_info_set_tx_time_est(info, airtime);
                        ieee80211_sta_update_pending_airtime(local, tx.sta,
                                                             txq->ac,
                                                             airtime,
                                                             false);
                }
        }

        return skb;

out:
        spin_unlock_bh(&fq->lock);

        return skb;
}
EXPORT_SYMBOL(ieee80211_tx_dequeue);

static inline s32 ieee80211_sta_deficit(struct sta_info *sta, u8 ac)
{
        struct airtime_info *air_info = &sta->airtime[ac];

        return air_info->deficit - atomic_read(&air_info->aql_tx_pending);
}

static void
ieee80211_txq_set_active(struct txq_info *txqi)
{
        struct sta_info *sta;

        if (!txqi->txq.sta)
                return;

        sta = container_of(txqi->txq.sta, struct sta_info, sta);
        sta->airtime[txqi->txq.ac].last_active = jiffies;
}

static bool
ieee80211_txq_keep_active(struct txq_info *txqi)
{
        struct sta_info *sta;

        if (!txqi->txq.sta)
                return false;

        sta = container_of(txqi->txq.sta, struct sta_info, sta);
        if (ieee80211_sta_deficit(sta, txqi->txq.ac) >= 0)
                return false;

        return ieee80211_sta_keep_active(sta, txqi->txq.ac);
}

struct ieee80211_txq *ieee80211_next_txq(struct ieee80211_hw *hw, u8 ac)
{
        struct ieee80211_local *local = hw_to_local(hw);
        struct ieee80211_txq *ret = NULL;
        struct txq_info *txqi = NULL, *head = NULL;
        bool found_eligible_txq = false;

        spin_lock_bh(&local->active_txq_lock[ac]);

        if (!local->schedule_round[ac])
                goto out;

 begin:
        txqi = list_first_entry_or_null(&local->active_txqs[ac],
                                        struct txq_info,
                                        schedule_order);
        if (!txqi)
                goto out;

        if (txqi == head) {
                if (!found_eligible_txq)
                        goto out;
                else
                        found_eligible_txq = false;
        }

        if (!head)
                head = txqi;

        if (txqi->txq.sta) {
                struct sta_info *sta = container_of(txqi->txq.sta,
                                                    struct sta_info, sta);
                bool aql_check = ieee80211_txq_airtime_check(hw, &txqi->txq);
                s32 deficit = ieee80211_sta_deficit(sta, txqi->txq.ac);

                if (aql_check)
                        found_eligible_txq = true;

                if (deficit < 0)
                        sta->airtime[txqi->txq.ac].deficit +=
                                sta->airtime_weight;

                if (deficit < 0 || !aql_check) {
                        list_move_tail(&txqi->schedule_order,
                                       &local->active_txqs[txqi->txq.ac]);
                        goto begin;
                }
        }

        if (txqi->schedule_round == local->schedule_round[ac])
                goto out;

        list_del_init(&txqi->schedule_order);
        txqi->schedule_round = local->schedule_round[ac];
        ret = &txqi->txq;

out:
        spin_unlock_bh(&local->active_txq_lock[ac]);
        return ret;
}
EXPORT_SYMBOL(ieee80211_next_txq);

void __ieee80211_schedule_txq(struct ieee80211_hw *hw,
                              struct ieee80211_txq *txq,
                              bool force)
{
        struct ieee80211_local *local = hw_to_local(hw);
        struct txq_info *txqi = to_txq_info(txq);
        bool has_queue;

        spin_lock_bh(&local->active_txq_lock[txq->ac]);

        has_queue = force || txq_has_queue(txq);
        if (list_empty(&txqi->schedule_order) &&
            (has_queue || ieee80211_txq_keep_active(txqi))) {
                /* If airtime accounting is active, always enqueue STAs at the
                 * head of the list to ensure that they only get moved to the
                 * back by the airtime DRR scheduler once they have a negative
                 * deficit. A station that already has a negative deficit will
                 * get immediately moved to the back of the list on the next
                 * call to ieee80211_next_txq().
                 */
                if (txqi->txq.sta && local->airtime_flags && has_queue &&
                    wiphy_ext_feature_isset(local->hw.wiphy,
                                            NL80211_EXT_FEATURE_AIRTIME_FAIRNESS))
                        list_add(&txqi->schedule_order,
                                 &local->active_txqs[txq->ac]);
                else
                        list_add_tail(&txqi->schedule_order,
                                      &local->active_txqs[txq->ac]);
                if (has_queue)
                        ieee80211_txq_set_active(txqi);
        }

        spin_unlock_bh(&local->active_txq_lock[txq->ac]);
}
EXPORT_SYMBOL(__ieee80211_schedule_txq);

DEFINE_STATIC_KEY_FALSE(aql_disable);

bool ieee80211_txq_airtime_check(struct ieee80211_hw *hw,
                                 struct ieee80211_txq *txq)
{
        struct sta_info *sta;
        struct ieee80211_local *local = hw_to_local(hw);

        if (!wiphy_ext_feature_isset(local->hw.wiphy, NL80211_EXT_FEATURE_AQL))
                return true;

        if (static_branch_unlikely(&aql_disable))
                return true;

        if (!txq->sta)
                return true;

        if (unlikely(txq->tid == IEEE80211_NUM_TIDS))
                return true;

        sta = container_of(txq->sta, struct sta_info, sta);
        if (atomic_read(&sta->airtime[txq->ac].aql_tx_pending) <
            sta->airtime[txq->ac].aql_limit_low)
                return true;

        if (atomic_read(&local->aql_total_pending_airtime) <
            local->aql_threshold &&
            atomic_read(&sta->airtime[txq->ac].aql_tx_pending) <
            sta->airtime[txq->ac].aql_limit_high)
                return true;

        return false;
}
EXPORT_SYMBOL(ieee80211_txq_airtime_check);

static bool
ieee80211_txq_schedule_airtime_check(struct ieee80211_local *local, u8 ac)
{
        unsigned int num_txq = 0;
        struct txq_info *txq;
        u32 aql_limit;

        if (!wiphy_ext_feature_isset(local->hw.wiphy, NL80211_EXT_FEATURE_AQL))
                return true;

        list_for_each_entry(txq, &local->active_txqs[ac], schedule_order)
                num_txq++;

        aql_limit = (num_txq - 1) * local->aql_txq_limit_low[ac] / 2 +
                    local->aql_txq_limit_high[ac];

        return atomic_read(&local->aql_ac_pending_airtime[ac]) < aql_limit;
}

bool ieee80211_txq_may_transmit(struct ieee80211_hw *hw,
                                struct ieee80211_txq *txq)
{
        struct ieee80211_local *local = hw_to_local(hw);
        struct txq_info *iter, *tmp, *txqi = to_txq_info(txq);
        struct sta_info *sta;
        u8 ac = txq->ac;

        spin_lock_bh(&local->active_txq_lock[ac]);

        if (!txqi->txq.sta)
                goto out;

        if (list_empty(&txqi->schedule_order))
                goto out;

        if (!ieee80211_txq_schedule_airtime_check(local, ac))
                goto out;

        list_for_each_entry_safe(iter, tmp, &local->active_txqs[ac],
                                 schedule_order) {
                if (iter == txqi)
                        break;

                if (!iter->txq.sta) {
                        list_move_tail(&iter->schedule_order,
                                       &local->active_txqs[ac]);
                        continue;
                }
                sta = container_of(iter->txq.sta, struct sta_info, sta);
                if (ieee80211_sta_deficit(sta, ac) < 0)
                        sta->airtime[ac].deficit += sta->airtime_weight;
                list_move_tail(&iter->schedule_order, &local->active_txqs[ac]);
        }

        sta = container_of(txqi->txq.sta, struct sta_info, sta);
        if (sta->airtime[ac].deficit >= 0)
                goto out;

        sta->airtime[ac].deficit += sta->airtime_weight;
        list_move_tail(&txqi->schedule_order, &local->active_txqs[ac]);
        spin_unlock_bh(&local->active_txq_lock[ac]);

        return false;
out:
        if (!list_empty(&txqi->schedule_order))
                list_del_init(&txqi->schedule_order);
        spin_unlock_bh(&local->active_txq_lock[ac]);

        return true;
}
EXPORT_SYMBOL(ieee80211_txq_may_transmit);

void ieee80211_txq_schedule_start(struct ieee80211_hw *hw, u8 ac)
{
        struct ieee80211_local *local = hw_to_local(hw);

        spin_lock_bh(&local->active_txq_lock[ac]);

        if (ieee80211_txq_schedule_airtime_check(local, ac)) {
                local->schedule_round[ac]++;
                if (!local->schedule_round[ac])
                        local->schedule_round[ac]++;
        } else {
                local->schedule_round[ac] = 0;
        }

        spin_unlock_bh(&local->active_txq_lock[ac]);
}
EXPORT_SYMBOL(ieee80211_txq_schedule_start);

void __ieee80211_subif_start_xmit(struct sk_buff *skb,
                                  struct net_device *dev,
                                  u32 info_flags,
                                  u32 ctrl_flags,
                                  u64 *cookie)
{
        struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev);
        struct ieee80211_local *local = sdata->local;
        struct sta_info *sta;
        struct sk_buff *next;
        int len = skb->len;

        if (unlikely(!ieee80211_sdata_running(sdata) || skb->len < ETH_HLEN)) {
                kfree_skb(skb);
                return;
        }

        sk_pacing_shift_update(skb->sk, sdata->local->hw.tx_sk_pacing_shift);

        rcu_read_lock();

        if (ieee80211_vif_is_mesh(&sdata->vif) &&
            ieee80211_hw_check(&local->hw, SUPPORT_FAST_XMIT) &&
            ieee80211_mesh_xmit_fast(sdata, skb, ctrl_flags))
                goto out;

        if (ieee80211_lookup_ra_sta(sdata, skb, &sta))
                goto out_free;

        if (IS_ERR(sta))
                sta = NULL;

        skb_set_queue_mapping(skb, ieee80211_select_queue(sdata, sta, skb));
        ieee80211_aggr_check(sdata, sta, skb);

        if (sta) {
                struct ieee80211_fast_tx *fast_tx;

                fast_tx = rcu_dereference(sta->fast_tx);

                if (fast_tx &&
                    ieee80211_xmit_fast(sdata, sta, fast_tx, skb))
                        goto out;
        }

        /* the frame could be fragmented, software-encrypted, and other
         * things so we cannot really handle checksum or GSO offload.
         * fix it up in software before we handle anything else.
         */
        skb = ieee80211_tx_skb_fixup(skb, 0);
        if (!skb) {
                len = 0;
                goto out;
        }

        skb_list_walk_safe(skb, skb, next) {
                skb_mark_not_on_list(skb);

                if (skb->protocol == sdata->control_port_protocol)
                        ctrl_flags |= IEEE80211_TX_CTRL_SKIP_MPATH_LOOKUP;

                skb = ieee80211_build_hdr(sdata, skb, info_flags,
                                          sta, ctrl_flags, cookie);
                if (IS_ERR(skb)) {
                        kfree_skb_list(next);
                        goto out;
                }

                dev_sw_netstats_tx_add(dev, 1, skb->len);

                ieee80211_xmit(sdata, sta, skb);
        }
        goto out;
 out_free:
        kfree_skb(skb);
        len = 0;
 out:
        if (len)
                ieee80211_tpt_led_trig_tx(local, len);
        rcu_read_unlock();
}

static int ieee80211_change_da(struct sk_buff *skb, struct sta_info *sta)
{
        struct ethhdr *eth;
        int err;

        err = skb_ensure_writable(skb, ETH_HLEN);
        if (unlikely(err))
                return err;

        eth = (void *)skb->data;
        ether_addr_copy(eth->h_dest, sta->sta.addr);

        return 0;
}

static bool ieee80211_multicast_to_unicast(struct sk_buff *skb,
                                           struct net_device *dev)
{
        struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev);
        const struct ethhdr *eth = (void *)skb->data;
        const struct vlan_ethhdr *ethvlan = (void *)skb->data;
        __be16 ethertype;

        switch (sdata->vif.type) {
        case NL80211_IFTYPE_AP_VLAN:
                if (sdata->u.vlan.sta)
                        return false;
                if (sdata->wdev.use_4addr)
                        return false;
                fallthrough;
        case NL80211_IFTYPE_AP:
                /* check runtime toggle for this bss */
                if (!sdata->bss->multicast_to_unicast)
                        return false;
                break;
        default:
                return false;
        }

        /* multicast to unicast conversion only for some payload */
        ethertype = eth->h_proto;
        if (ethertype == htons(ETH_P_8021Q) && skb->len >= VLAN_ETH_HLEN)
                ethertype = ethvlan->h_vlan_encapsulated_proto;
        switch (ethertype) {
        case htons(ETH_P_ARP):
        case htons(ETH_P_IP):
        case htons(ETH_P_IPV6):
                break;
        default:
                return false;
        }

        return true;
}

static void
ieee80211_convert_to_unicast(struct sk_buff *skb, struct net_device *dev,
                             struct sk_buff_head *queue)
{
        struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev);
        struct ieee80211_local *local = sdata->local;
        const struct ethhdr *eth = (struct ethhdr *)skb->data;
        struct sta_info *sta, *first = NULL;
        struct sk_buff *cloned_skb;

        rcu_read_lock();

        list_for_each_entry_rcu(sta, &local->sta_list, list) {
                if (sdata != sta->sdata)
                        /* AP-VLAN mismatch */
                        continue;
                if (unlikely(ether_addr_equal(eth->h_source, sta->sta.addr)))
                        /* do not send back to source */
                        continue;
                if (!first) {
                        first = sta;
                        continue;
                }
                cloned_skb = skb_clone(skb, GFP_ATOMIC);
                if (!cloned_skb)
                        goto multicast;
                if (unlikely(ieee80211_change_da(cloned_skb, sta))) {
                        dev_kfree_skb(cloned_skb);
                        goto multicast;
                }
                __skb_queue_tail(queue, cloned_skb);
        }

        if (likely(first)) {
                if (unlikely(ieee80211_change_da(skb, first)))
                        goto multicast;
                __skb_queue_tail(queue, skb);
        } else {
                /* no STA connected, drop */
                kfree_skb(skb);
                skb = NULL;
        }

        goto out;
multicast:
        __skb_queue_purge(queue);
        __skb_queue_tail(queue, skb);
out:
        rcu_read_unlock();
}

static void ieee80211_mlo_multicast_tx_one(struct ieee80211_sub_if_data *sdata,
                                           struct sk_buff *skb, u32 ctrl_flags,
                                           unsigned int link_id)
{
        struct sk_buff *out;

        out = skb_copy(skb, GFP_ATOMIC);
        if (!out)
                return;

        ctrl_flags |= u32_encode_bits(link_id, IEEE80211_TX_CTRL_MLO_LINK);
        __ieee80211_subif_start_xmit(out, sdata->dev, 0, ctrl_flags, NULL);
}

static void ieee80211_mlo_multicast_tx(struct net_device *dev,
                                       struct sk_buff *skb)
{
        struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev);
        unsigned long links = sdata->vif.active_links;
        unsigned int link;
        u32 ctrl_flags = IEEE80211_TX_CTRL_MCAST_MLO_FIRST_TX;

        if (hweight16(links) == 1) {
                ctrl_flags |= u32_encode_bits(__ffs(links),
                                              IEEE80211_TX_CTRL_MLO_LINK);

                __ieee80211_subif_start_xmit(skb, sdata->dev, 0, ctrl_flags,
                                             NULL);
                return;
        }

        for_each_set_bit(link, &links, IEEE80211_MLD_MAX_NUM_LINKS) {
                ieee80211_mlo_multicast_tx_one(sdata, skb, ctrl_flags, link);
                ctrl_flags = 0;
        }
        kfree_skb(skb);
}

/**
 * ieee80211_subif_start_xmit - netif start_xmit function for 802.3 vifs
 * @skb: packet to be sent
 * @dev: incoming interface
 *
 * On failure skb will be freed.
 *
 * Returns: the netdev TX status (but really only %NETDEV_TX_OK)
 */
netdev_tx_t ieee80211_subif_start_xmit(struct sk_buff *skb,
                                       struct net_device *dev)
{
        struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev);
        const struct ethhdr *eth = (void *)skb->data;

        if (likely(!is_multicast_ether_addr(eth->h_dest)))
                goto normal;

        if (unlikely(!ieee80211_sdata_running(sdata))) {
                kfree_skb(skb);
                return NETDEV_TX_OK;
        }

        if (unlikely(ieee80211_multicast_to_unicast(skb, dev))) {
                struct sk_buff_head queue;

                __skb_queue_head_init(&queue);
                ieee80211_convert_to_unicast(skb, dev, &queue);
                while ((skb = __skb_dequeue(&queue)))
                        __ieee80211_subif_start_xmit(skb, dev, 0,
                                                     IEEE80211_TX_CTRL_MLO_LINK_UNSPEC,
                                                     NULL);
        } else if (ieee80211_vif_is_mld(&sdata->vif) &&
                   sdata->vif.type == NL80211_IFTYPE_AP &&
                   !ieee80211_hw_check(&sdata->local->hw, MLO_MCAST_MULTI_LINK_TX)) {
                ieee80211_mlo_multicast_tx(dev, skb);
        } else {
normal:
                __ieee80211_subif_start_xmit(skb, dev, 0,
                                             IEEE80211_TX_CTRL_MLO_LINK_UNSPEC,
                                             NULL);
        }

        return NETDEV_TX_OK;
}



static bool __ieee80211_tx_8023(struct ieee80211_sub_if_data *sdata,
                                struct sk_buff *skb, struct sta_info *sta,
                                bool txpending)
{
        struct ieee80211_local *local = sdata->local;
        struct ieee80211_tx_control control = {};
        struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb);
        struct ieee80211_sta *pubsta = NULL;
        unsigned long flags;
        int q = info->hw_queue;

        spin_lock_irqsave(&local->queue_stop_reason_lock, flags);

        if (local->queue_stop_reasons[q] ||
            (!txpending && !skb_queue_empty(&local->pending[q]))) {
                if (txpending)
                        skb_queue_head(&local->pending[q], skb);
                else
                        skb_queue_tail(&local->pending[q], skb);

                spin_unlock_irqrestore(&local->queue_stop_reason_lock, flags);

                return false;
        }

        spin_unlock_irqrestore(&local->queue_stop_reason_lock, flags);

        if (sta && sta->uploaded)
                pubsta = &sta->sta;

        control.sta = pubsta;

        drv_tx(local, &control, skb);

        return true;
}

static bool ieee80211_tx_8023(struct ieee80211_sub_if_data *sdata,
                              struct sk_buff *skb, struct sta_info *sta,
                              bool txpending)
{
        struct ieee80211_local *local = sdata->local;
        struct sk_buff *next;
        bool ret = true;

        if (ieee80211_queue_skb(local, sdata, sta, skb))
                return true;

        skb_list_walk_safe(skb, skb, next) {
                skb_mark_not_on_list(skb);
                if (!__ieee80211_tx_8023(sdata, skb, sta, txpending))
                        ret = false;
        }

        return ret;
}

static void ieee80211_8023_xmit(struct ieee80211_sub_if_data *sdata,
                                struct net_device *dev, struct sta_info *sta,
                                struct ieee80211_key *key, struct sk_buff *skb)
{
        struct ieee80211_tx_info *info;
        struct ieee80211_local *local = sdata->local;
        struct tid_ampdu_tx *tid_tx;
        struct sk_buff *seg, *next;
        unsigned int skbs = 0, len = 0;
        u16 queue;
        u8 tid;

        queue = ieee80211_select_queue(sdata, sta, skb);
        skb_set_queue_mapping(skb, queue);

        if (unlikely(test_bit(SCAN_SW_SCANNING, &local->scanning)) &&
            test_bit(SDATA_STATE_OFFCHANNEL, &sdata->state))
                goto out_free;

        skb = skb_share_check(skb, GFP_ATOMIC);
        if (unlikely(!skb))
                return;

        ieee80211_aggr_check(sdata, sta, skb);

        tid = skb->priority & IEEE80211_QOS_CTL_TAG1D_MASK;
        tid_tx = rcu_dereference(sta->ampdu_mlme.tid_tx[tid]);
        if (tid_tx) {
                if (!test_bit(HT_AGG_STATE_OPERATIONAL, &tid_tx->state)) {
                        /* fall back to non-offload slow path */
                        __ieee80211_subif_start_xmit(skb, dev, 0,
                                                     IEEE80211_TX_CTRL_MLO_LINK_UNSPEC,
                                                     NULL);
                        return;
                }

                if (tid_tx->timeout)
                        tid_tx->last_tx = jiffies;
        }

        skb = ieee80211_tx_skb_fixup(skb, ieee80211_sdata_netdev_features(sdata));
        if (!skb)
                return;

        info = IEEE80211_SKB_CB(skb);
        memset(info, 0, sizeof(*info));

        info->hw_queue = sdata->vif.hw_queue[queue];

        if (sdata->vif.type == NL80211_IFTYPE_AP_VLAN)
                sdata = container_of(sdata->bss,
                                     struct ieee80211_sub_if_data, u.ap);

        info->flags |= IEEE80211_TX_CTL_HW_80211_ENCAP;
        info->control.vif = &sdata->vif;

        if (key)
                info->control.hw_key = &key->conf;

        skb_list_walk_safe(skb, seg, next) {
                skbs++;
                len += seg->len;
                if (seg != skb)
                        memcpy(IEEE80211_SKB_CB(seg), info, sizeof(*info));
        }

        if (unlikely(skb->sk &&
                     skb_shinfo(skb)->tx_flags & SKBTX_WIFI_STATUS)) {
                info->status_data = ieee80211_store_ack_skb(local, skb,
                                                            &info->flags, NULL);
                if (info->status_data)
                        info->status_data_idr = 1;
        }

        dev_sw_netstats_tx_add(dev, skbs, len);
        sta->deflink.tx_stats.packets[queue] += skbs;
        sta->deflink.tx_stats.bytes[queue] += len;

        ieee80211_tpt_led_trig_tx(local, len);

        ieee80211_tx_8023(sdata, skb, sta, false);

        return;

out_free:
        kfree_skb(skb);
}

netdev_tx_t ieee80211_subif_start_xmit_8023(struct sk_buff *skb,
                                            struct net_device *dev)
{
        struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev);
        struct ethhdr *ehdr = (struct ethhdr *)skb->data;
        struct ieee80211_key *key;
        struct sta_info *sta;

        if (unlikely(!ieee80211_sdata_running(sdata) || skb->len < ETH_HLEN)) {
                kfree_skb(skb);
                return NETDEV_TX_OK;
        }

        rcu_read_lock();

        if (ieee80211_lookup_ra_sta(sdata, skb, &sta)) {
                kfree_skb(skb);
                goto out;
        }

        if (unlikely(IS_ERR_OR_NULL(sta) || !sta->uploaded ||
            !test_sta_flag(sta, WLAN_STA_AUTHORIZED) ||
            sdata->control_port_protocol == ehdr->h_proto))
                goto skip_offload;

        key = rcu_dereference(sta->ptk[sta->ptk_idx]);
        if (!key)
                key = rcu_dereference(sdata->default_unicast_key);

        if (key && (!(key->flags & KEY_FLAG_UPLOADED_TO_HARDWARE) ||
                    key->conf.cipher == WLAN_CIPHER_SUITE_TKIP))
                goto skip_offload;

        sk_pacing_shift_update(skb->sk, sdata->local->hw.tx_sk_pacing_shift);
        ieee80211_8023_xmit(sdata, dev, sta, key, skb);
        goto out;

skip_offload:
        ieee80211_subif_start_xmit(skb, dev);
out:
        rcu_read_unlock();

        return NETDEV_TX_OK;
}

struct sk_buff *
ieee80211_build_data_template(struct ieee80211_sub_if_data *sdata,
                              struct sk_buff *skb, u32 info_flags)
{
        struct ieee80211_hdr *hdr;
        struct ieee80211_tx_data tx = {
                .local = sdata->local,
                .sdata = sdata,
        };
        struct sta_info *sta;

        rcu_read_lock();

        if (ieee80211_lookup_ra_sta(sdata, skb, &sta)) {
                kfree_skb(skb);
                skb = ERR_PTR(-EINVAL);
                goto out;
        }

        skb = ieee80211_build_hdr(sdata, skb, info_flags, sta,
                                  IEEE80211_TX_CTRL_MLO_LINK_UNSPEC, NULL);
        if (IS_ERR(skb))
                goto out;

        hdr = (void *)skb->data;
        tx.sta = sta_info_get(sdata, hdr->addr1);
        tx.skb = skb;

        if (ieee80211_tx_h_select_key(&tx) != TX_CONTINUE) {
                rcu_read_unlock();
                kfree_skb(skb);
                return ERR_PTR(-EINVAL);
        }

out:
        rcu_read_unlock();
        return skb;
}

/*
 * ieee80211_clear_tx_pending may not be called in a context where
 * it is possible that it packets could come in again.
 */
void ieee80211_clear_tx_pending(struct ieee80211_local *local)
{
        struct sk_buff *skb;
        int i;

        for (i = 0; i < local->hw.queues; i++) {
                while ((skb = skb_dequeue(&local->pending[i])) != NULL)
                        ieee80211_free_txskb(&local->hw, skb);
        }
}

/*
 * Returns false if the frame couldn't be transmitted but was queued instead,
 * which in this case means re-queued -- take as an indication to stop sending
 * more pending frames.
 */
static bool ieee80211_tx_pending_skb(struct ieee80211_local *local,
                                     struct sk_buff *skb)
{
        struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb);
        struct ieee80211_sub_if_data *sdata;
        struct sta_info *sta;
        struct ieee80211_hdr *hdr;
        bool result;
        struct ieee80211_chanctx_conf *chanctx_conf;

        sdata = vif_to_sdata(info->control.vif);

        if (info->control.flags & IEEE80211_TX_INTCFL_NEED_TXPROCESSING) {
                /* update band only for non-MLD */
                if (!ieee80211_vif_is_mld(&sdata->vif)) {
                        chanctx_conf =
                                rcu_dereference(sdata->vif.bss_conf.chanctx_conf);
                        if (unlikely(!chanctx_conf)) {
                                dev_kfree_skb(skb);
                                return true;
                        }
                        info->band = chanctx_conf->def.chan->band;
                }
                result = ieee80211_tx(sdata, NULL, skb, true);
        } else if (info->flags & IEEE80211_TX_CTL_HW_80211_ENCAP) {
                if (ieee80211_lookup_ra_sta(sdata, skb, &sta)) {
                        dev_kfree_skb(skb);
                        return true;
                }

                if (IS_ERR(sta) || (sta && !sta->uploaded))
                        sta = NULL;

                result = ieee80211_tx_8023(sdata, skb, sta, true);
        } else {
                struct sk_buff_head skbs;

                __skb_queue_head_init(&skbs);
                __skb_queue_tail(&skbs, skb);

                hdr = (struct ieee80211_hdr *)skb->data;
                sta = sta_info_get(sdata, hdr->addr1);

                result = __ieee80211_tx(local, &skbs, sta, true);
        }

        return result;
}

/*
 * Transmit all pending packets. Called from tasklet.
 */
void ieee80211_tx_pending(struct tasklet_struct *t)
{
        struct ieee80211_local *local = from_tasklet(local, t,
                                                     tx_pending_tasklet);
        unsigned long flags;
        int i;
        bool txok;

        rcu_read_lock();

        spin_lock_irqsave(&local->queue_stop_reason_lock, flags);
        for (i = 0; i < local->hw.queues; i++) {
                /*
                 * If queue is stopped by something other than due to pending
                 * frames, or we have no pending frames, proceed to next queue.
                 */
                if (local->queue_stop_reasons[i] ||
                    skb_queue_empty(&local->pending[i]))
                        continue;

                while (!skb_queue_empty(&local->pending[i])) {
                        struct sk_buff *skb = __skb_dequeue(&local->pending[i]);
                        struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb);

                        if (WARN_ON(!info->control.vif)) {
                                ieee80211_free_txskb(&local->hw, skb);
                                continue;
                        }

                        spin_unlock_irqrestore(&local->queue_stop_reason_lock,
                                                flags);

                        txok = ieee80211_tx_pending_skb(local, skb);
                        spin_lock_irqsave(&local->queue_stop_reason_lock,
                                          flags);
                        if (!txok)
                                break;
                }
        }
        spin_unlock_irqrestore(&local->queue_stop_reason_lock, flags);

        rcu_read_unlock();
}

/* functions for drivers to get certain frames */

static void __ieee80211_beacon_add_tim(struct ieee80211_sub_if_data *sdata,
                                       struct ieee80211_link_data *link,
                                       struct ps_data *ps, struct sk_buff *skb,
                                       bool is_template)
{
        u8 *pos, *tim;
        int aid0 = 0;
        int i, have_bits = 0, n1, n2;
        struct ieee80211_bss_conf *link_conf = link->conf;

        /* Generate bitmap for TIM only if there are any STAs in power save
         * mode. */
        if (atomic_read(&ps->num_sta_ps) > 0)
                /* in the hope that this is faster than
                 * checking byte-for-byte */
                have_bits = !bitmap_empty((unsigned long *)ps->tim,
                                          IEEE80211_MAX_AID+1);
        if (!is_template) {
                if (ps->dtim_count == 0)
                        ps->dtim_count = link_conf->dtim_period - 1;
                else
                        ps->dtim_count--;
        }

        tim = pos = skb_put(skb, 5);
        *pos++ = WLAN_EID_TIM;
        *pos++ = 3;
        *pos++ = ps->dtim_count;
        *pos++ = link_conf->dtim_period;

        if (ps->dtim_count == 0 && !skb_queue_empty(&ps->bc_buf))
                aid0 = 1;

        ps->dtim_bc_mc = aid0 == 1;

        if (have_bits) {
                /* Find largest even number N1 so that bits numbered 1 through
                 * (N1 x 8) - 1 in the bitmap are 0 and number N2 so that bits
                 * (N2 + 1) x 8 through 2007 are 0. */
                n1 = 0;
                for (i = 0; i < IEEE80211_MAX_TIM_LEN; i++) {
                        if (ps->tim[i]) {
                                n1 = i & 0xfe;
                                break;
                        }
                }
                n2 = n1;
                for (i = IEEE80211_MAX_TIM_LEN - 1; i >= n1; i--) {
                        if (ps->tim[i]) {
                                n2 = i;
                                break;
                        }
                }

                /* Bitmap control */
                *pos++ = n1 | aid0;
                /* Part Virt Bitmap */
                skb_put_data(skb, ps->tim + n1, n2 - n1 + 1);

                tim[1] = n2 - n1 + 4;
        } else {
                *pos++ = aid0; /* Bitmap control */

                if (ieee80211_get_link_sband(link)->band != NL80211_BAND_S1GHZ) {
                        tim[1] = 4;
                        /* Part Virt Bitmap */
                        skb_put_u8(skb, 0);
                }
        }
}

static int ieee80211_beacon_add_tim(struct ieee80211_sub_if_data *sdata,
                                    struct ieee80211_link_data *link,
                                    struct ps_data *ps, struct sk_buff *skb,
                                    bool is_template)
{
        struct ieee80211_local *local = sdata->local;

        /*
         * Not very nice, but we want to allow the driver to call
         * ieee80211_beacon_get() as a response to the set_tim()
         * callback. That, however, is already invoked under the
         * sta_lock to guarantee consistent and race-free update
         * of the tim bitmap in mac80211 and the driver.
         */
        if (local->tim_in_locked_section) {
                __ieee80211_beacon_add_tim(sdata, link, ps, skb, is_template);
        } else {
                spin_lock_bh(&local->tim_lock);
                __ieee80211_beacon_add_tim(sdata, link, ps, skb, is_template);
                spin_unlock_bh(&local->tim_lock);
        }

        return 0;
}

static void ieee80211_set_beacon_cntdwn(struct ieee80211_sub_if_data *sdata,
                                        struct beacon_data *beacon,
                                        struct ieee80211_link_data *link)
{
        u8 *beacon_data, count, max_count = 1;
        struct probe_resp *resp;
        size_t beacon_data_len;
        u16 *bcn_offsets;
        int i;

        switch (sdata->vif.type) {
        case NL80211_IFTYPE_AP:
                beacon_data = beacon->tail;
                beacon_data_len = beacon->tail_len;
                break;
        case NL80211_IFTYPE_ADHOC:
                beacon_data = beacon->head;
                beacon_data_len = beacon->head_len;
                break;
        case NL80211_IFTYPE_MESH_POINT:
                beacon_data = beacon->head;
                beacon_data_len = beacon->head_len;
                break;
        default:
                return;
        }

        resp = rcu_dereference(link->u.ap.probe_resp);

        bcn_offsets = beacon->cntdwn_counter_offsets;
        count = beacon->cntdwn_current_counter;
        if (link->conf->csa_active)
                max_count = IEEE80211_MAX_CNTDWN_COUNTERS_NUM;

        for (i = 0; i < max_count; ++i) {
                if (bcn_offsets[i]) {
                        if (WARN_ON_ONCE(bcn_offsets[i] >= beacon_data_len))
                                return;
                        beacon_data[bcn_offsets[i]] = count;
                }

                if (sdata->vif.type == NL80211_IFTYPE_AP && resp) {
                        u16 *resp_offsets = resp->cntdwn_counter_offsets;

                        resp->data[resp_offsets[i]] = count;
                }
        }
}

static u8 __ieee80211_beacon_update_cntdwn(struct beacon_data *beacon)
{
        beacon->cntdwn_current_counter--;

        /* the counter should never reach 0 */
        WARN_ON_ONCE(!beacon->cntdwn_current_counter);

        return beacon->cntdwn_current_counter;
}

u8 ieee80211_beacon_update_cntdwn(struct ieee80211_vif *vif, unsigned int link_id)
{
        struct ieee80211_sub_if_data *sdata = vif_to_sdata(vif);
        struct ieee80211_link_data *link;
        struct beacon_data *beacon = NULL;
        u8 count = 0;

        if (WARN_ON(link_id >= IEEE80211_MLD_MAX_NUM_LINKS))
                return 0;

        rcu_read_lock();

        link = rcu_dereference(sdata->link[link_id]);
        if (!link)
                goto unlock;

        if (sdata->vif.type == NL80211_IFTYPE_AP)
                beacon = rcu_dereference(link->u.ap.beacon);
        else if (sdata->vif.type == NL80211_IFTYPE_ADHOC)
                beacon = rcu_dereference(sdata->u.ibss.presp);
        else if (ieee80211_vif_is_mesh(&sdata->vif))
                beacon = rcu_dereference(sdata->u.mesh.beacon);

        if (!beacon)
                goto unlock;

        count = __ieee80211_beacon_update_cntdwn(beacon);

unlock:
        rcu_read_unlock();
        return count;
}
EXPORT_SYMBOL(ieee80211_beacon_update_cntdwn);

void ieee80211_beacon_set_cntdwn(struct ieee80211_vif *vif, u8 counter)
{
        struct ieee80211_sub_if_data *sdata = vif_to_sdata(vif);
        struct beacon_data *beacon = NULL;

        rcu_read_lock();

        if (sdata->vif.type == NL80211_IFTYPE_AP)
                beacon = rcu_dereference(sdata->deflink.u.ap.beacon);
        else if (sdata->vif.type == NL80211_IFTYPE_ADHOC)
                beacon = rcu_dereference(sdata->u.ibss.presp);
        else if (ieee80211_vif_is_mesh(&sdata->vif))
                beacon = rcu_dereference(sdata->u.mesh.beacon);

        if (!beacon)
                goto unlock;

        if (counter < beacon->cntdwn_current_counter)
                beacon->cntdwn_current_counter = counter;

unlock:
        rcu_read_unlock();
}
EXPORT_SYMBOL(ieee80211_beacon_set_cntdwn);

bool ieee80211_beacon_cntdwn_is_complete(struct ieee80211_vif *vif,
                                         unsigned int link_id)
{
        struct ieee80211_sub_if_data *sdata = vif_to_sdata(vif);
        struct ieee80211_link_data *link;
        struct beacon_data *beacon = NULL;
        u8 *beacon_data;
        size_t beacon_data_len;
        int ret = false;

        if (!ieee80211_sdata_running(sdata))
                return false;

        if (WARN_ON(link_id >= IEEE80211_MLD_MAX_NUM_LINKS))
                return 0;

        rcu_read_lock();

        link = rcu_dereference(sdata->link[link_id]);
        if (!link)
                goto out;

        if (vif->type == NL80211_IFTYPE_AP) {
                beacon = rcu_dereference(link->u.ap.beacon);
                if (WARN_ON(!beacon || !beacon->tail))
                        goto out;
                beacon_data = beacon->tail;
                beacon_data_len = beacon->tail_len;
        } else if (vif->type == NL80211_IFTYPE_ADHOC) {
                struct ieee80211_if_ibss *ifibss = &sdata->u.ibss;

                beacon = rcu_dereference(ifibss->presp);
                if (!beacon)
                        goto out;

                beacon_data = beacon->head;
                beacon_data_len = beacon->head_len;
        } else if (vif->type == NL80211_IFTYPE_MESH_POINT) {
                struct ieee80211_if_mesh *ifmsh = &sdata->u.mesh;

                beacon = rcu_dereference(ifmsh->beacon);
                if (!beacon)
                        goto out;

                beacon_data = beacon->head;
                beacon_data_len = beacon->head_len;
        } else {
                WARN_ON(1);
                goto out;
        }

        if (!beacon->cntdwn_counter_offsets[0])
                goto out;

        if (WARN_ON_ONCE(beacon->cntdwn_counter_offsets[0] > beacon_data_len))
                goto out;

        if (beacon_data[beacon->cntdwn_counter_offsets[0]] == 1)
                ret = true;

 out:
        rcu_read_unlock();

        return ret;
}
EXPORT_SYMBOL(ieee80211_beacon_cntdwn_is_complete);

static int ieee80211_beacon_protect(struct sk_buff *skb,
                                    struct ieee80211_local *local,
                                    struct ieee80211_sub_if_data *sdata,
                                    struct ieee80211_link_data *link)
{
        ieee80211_tx_result res;
        struct ieee80211_tx_data tx;
        struct sk_buff *check_skb;

        memset(&tx, 0, sizeof(tx));
        tx.key = rcu_dereference(link->default_beacon_key);
        if (!tx.key)
                return 0;

        if (unlikely(tx.key->flags & KEY_FLAG_TAINTED)) {
                tx.key = NULL;
                return -EINVAL;
        }

        if (!(tx.key->conf.flags & IEEE80211_KEY_FLAG_SW_MGMT_TX) &&
            tx.key->flags & KEY_FLAG_UPLOADED_TO_HARDWARE)
                IEEE80211_SKB_CB(skb)->control.hw_key = &tx.key->conf;

        tx.local = local;
        tx.sdata = sdata;
        __skb_queue_head_init(&tx.skbs);
        __skb_queue_tail(&tx.skbs, skb);
        res = ieee80211_tx_h_encrypt(&tx);
        check_skb = __skb_dequeue(&tx.skbs);
        /* we may crash after this, but it'd be a bug in crypto */
        WARN_ON(check_skb != skb);
        if (WARN_ON_ONCE(res != TX_CONTINUE))
                return -EINVAL;

        return 0;
}

static void
ieee80211_beacon_get_finish(struct ieee80211_hw *hw,
                            struct ieee80211_vif *vif,
                            struct ieee80211_link_data *link,
                            struct ieee80211_mutable_offsets *offs,
                            struct beacon_data *beacon,
                            struct sk_buff *skb,
                            struct ieee80211_chanctx_conf *chanctx_conf,
                            u16 csa_off_base)
{
        struct ieee80211_local *local = hw_to_local(hw);
        struct ieee80211_sub_if_data *sdata = vif_to_sdata(vif);
        struct ieee80211_tx_info *info;
        enum nl80211_band band;
        struct ieee80211_tx_rate_control txrc;

        /* CSA offsets */
        if (offs && beacon) {
                u16 i;

                for (i = 0; i < IEEE80211_MAX_CNTDWN_COUNTERS_NUM; i++) {
                        u16 csa_off = beacon->cntdwn_counter_offsets[i];

                        if (!csa_off)
                                continue;

                        offs->cntdwn_counter_offs[i] = csa_off_base + csa_off;
                }
        }

        band = chanctx_conf->def.chan->band;
        info = IEEE80211_SKB_CB(skb);
        info->flags |= IEEE80211_TX_INTFL_DONT_ENCRYPT;
        info->flags |= IEEE80211_TX_CTL_NO_ACK;
        info->band = band;

        memset(&txrc, 0, sizeof(txrc));
        txrc.hw = hw;
        txrc.sband = local->hw.wiphy->bands[band];
        txrc.bss_conf = link->conf;
        txrc.skb = skb;
        txrc.reported_rate.idx = -1;
        if (sdata->beacon_rate_set && sdata->beacon_rateidx_mask[band])
                txrc.rate_idx_mask = sdata->beacon_rateidx_mask[band];
        else
                txrc.rate_idx_mask = sdata->rc_rateidx_mask[band];
        txrc.bss = true;
        rate_control_get_rate(sdata, NULL, &txrc);

        info->control.vif = vif;
        info->control.flags |= u32_encode_bits(link->link_id,
                                               IEEE80211_TX_CTRL_MLO_LINK);
        info->flags |= IEEE80211_TX_CTL_CLEAR_PS_FILT |
                       IEEE80211_TX_CTL_ASSIGN_SEQ |
                       IEEE80211_TX_CTL_FIRST_FRAGMENT;
}

static void
ieee80211_beacon_add_mbssid(struct sk_buff *skb, struct beacon_data *beacon,
                            u8 i)
{
        if (!beacon->mbssid_ies || !beacon->mbssid_ies->cnt ||
            i > beacon->mbssid_ies->cnt)
                return;

        if (i < beacon->mbssid_ies->cnt) {
                skb_put_data(skb, beacon->mbssid_ies->elem[i].data,
                             beacon->mbssid_ies->elem[i].len);

                if (beacon->rnr_ies && beacon->rnr_ies->cnt) {
                        skb_put_data(skb, beacon->rnr_ies->elem[i].data,
                                     beacon->rnr_ies->elem[i].len);

                        for (i = beacon->mbssid_ies->cnt; i < beacon->rnr_ies->cnt; i++)
                                skb_put_data(skb, beacon->rnr_ies->elem[i].data,
                                             beacon->rnr_ies->elem[i].len);
                }
                return;
        }

        /* i == beacon->mbssid_ies->cnt, include all MBSSID elements */
        for (i = 0; i < beacon->mbssid_ies->cnt; i++)
                skb_put_data(skb, beacon->mbssid_ies->elem[i].data,
                             beacon->mbssid_ies->elem[i].len);
}

static struct sk_buff *
ieee80211_beacon_get_ap(struct ieee80211_hw *hw,
                        struct ieee80211_vif *vif,
                        struct ieee80211_link_data *link,
                        struct ieee80211_mutable_offsets *offs,
                        bool is_template,
                        struct beacon_data *beacon,
                        struct ieee80211_chanctx_conf *chanctx_conf,
                        u8 ema_index)
{
        struct ieee80211_local *local = hw_to_local(hw);
        struct ieee80211_sub_if_data *sdata = vif_to_sdata(vif);
        struct ieee80211_if_ap *ap = &sdata->u.ap;
        struct sk_buff *skb = NULL;
        u16 csa_off_base = 0;
        int mbssid_len;

        if (beacon->cntdwn_counter_offsets[0]) {
                if (!is_template)
                        ieee80211_beacon_update_cntdwn(vif, link->link_id);

                ieee80211_set_beacon_cntdwn(sdata, beacon, link);
        }

        /* headroom, head length,
         * tail length, maximum TIM length and multiple BSSID length
         */
        mbssid_len = ieee80211_get_mbssid_beacon_len(beacon->mbssid_ies,
                                                     beacon->rnr_ies,
                                                     ema_index);

        skb = dev_alloc_skb(local->tx_headroom + beacon->head_len +
                            beacon->tail_len + 256 +
                            local->hw.extra_beacon_tailroom + mbssid_len);
        if (!skb)
                return NULL;

        skb_reserve(skb, local->tx_headroom);
        skb_put_data(skb, beacon->head, beacon->head_len);

        ieee80211_beacon_add_tim(sdata, link, &ap->ps, skb, is_template);

        if (offs) {
                offs->tim_offset = beacon->head_len;
                offs->tim_length = skb->len - beacon->head_len;
                offs->cntdwn_counter_offs[0] = beacon->cntdwn_counter_offsets[0];

                if (mbssid_len) {
                        ieee80211_beacon_add_mbssid(skb, beacon, ema_index);
                        offs->mbssid_off = skb->len - mbssid_len;
                }

                /* for AP the csa offsets are from tail */
                csa_off_base = skb->len;
        }

        if (beacon->tail)
                skb_put_data(skb, beacon->tail, beacon->tail_len);

        if (ieee80211_beacon_protect(skb, local, sdata, link) < 0) {
                dev_kfree_skb(skb);
                return NULL;
        }

        ieee80211_beacon_get_finish(hw, vif, link, offs, beacon, skb,
                                    chanctx_conf, csa_off_base);
        return skb;
}

static struct ieee80211_ema_beacons *
ieee80211_beacon_get_ap_ema_list(struct ieee80211_hw *hw,
                                 struct ieee80211_vif *vif,
                                 struct ieee80211_link_data *link,
                                 struct ieee80211_mutable_offsets *offs,
                                 bool is_template, struct beacon_data *beacon,
                                 struct ieee80211_chanctx_conf *chanctx_conf)
{
        struct ieee80211_ema_beacons *ema = NULL;

        if (!beacon->mbssid_ies || !beacon->mbssid_ies->cnt)
                return NULL;

        ema = kzalloc(struct_size(ema, bcn, beacon->mbssid_ies->cnt),
                      GFP_ATOMIC);
        if (!ema)
                return NULL;

        for (ema->cnt = 0; ema->cnt < beacon->mbssid_ies->cnt; ema->cnt++) {
                ema->bcn[ema->cnt].skb =
                        ieee80211_beacon_get_ap(hw, vif, link,
                                                &ema->bcn[ema->cnt].offs,
                                                is_template, beacon,
                                                chanctx_conf, ema->cnt);
                if (!ema->bcn[ema->cnt].skb)
                        break;
        }

        if (ema->cnt == beacon->mbssid_ies->cnt)
                return ema;

        ieee80211_beacon_free_ema_list(ema);
        return NULL;
}

#define IEEE80211_INCLUDE_ALL_MBSSID_ELEMS -1

static struct sk_buff *
__ieee80211_beacon_get(struct ieee80211_hw *hw,
                       struct ieee80211_vif *vif,
                       struct ieee80211_mutable_offsets *offs,
                       bool is_template,
                       unsigned int link_id,
                       int ema_index,
                       struct ieee80211_ema_beacons **ema_beacons)
{
        struct ieee80211_local *local = hw_to_local(hw);
        struct beacon_data *beacon = NULL;
        struct sk_buff *skb = NULL;
        struct ieee80211_sub_if_data *sdata = NULL;
        struct ieee80211_chanctx_conf *chanctx_conf;
        struct ieee80211_link_data *link;

        rcu_read_lock();

        sdata = vif_to_sdata(vif);
        link = rcu_dereference(sdata->link[link_id]);
        if (!link)
                goto out;
        chanctx_conf =
                rcu_dereference(link->conf->chanctx_conf);

        if (!ieee80211_sdata_running(sdata) || !chanctx_conf)
                goto out;

        if (offs)
                memset(offs, 0, sizeof(*offs));

        if (sdata->vif.type == NL80211_IFTYPE_AP) {
                beacon = rcu_dereference(link->u.ap.beacon);
                if (!beacon)
                        goto out;

                if (ema_beacons) {
                        *ema_beacons =
                                ieee80211_beacon_get_ap_ema_list(hw, vif, link,
                                                                 offs,
                                                                 is_template,
                                                                 beacon,
                                                                 chanctx_conf);
                } else {
                        if (beacon->mbssid_ies && beacon->mbssid_ies->cnt) {
                                if (ema_index >= beacon->mbssid_ies->cnt)
                                        goto out; /* End of MBSSID elements */

                                if (ema_index <= IEEE80211_INCLUDE_ALL_MBSSID_ELEMS)
                                        ema_index = beacon->mbssid_ies->cnt;
                        } else {
                                ema_index = 0;
                        }

                        skb = ieee80211_beacon_get_ap(hw, vif, link, offs,
                                                      is_template, beacon,
                                                      chanctx_conf,
                                                      ema_index);
                }
        } else if (sdata->vif.type == NL80211_IFTYPE_ADHOC) {
                struct ieee80211_if_ibss *ifibss = &sdata->u.ibss;
                struct ieee80211_hdr *hdr;

                beacon = rcu_dereference(ifibss->presp);
                if (!beacon)
                        goto out;

                if (beacon->cntdwn_counter_offsets[0]) {
                        if (!is_template)
                                __ieee80211_beacon_update_cntdwn(beacon);

                        ieee80211_set_beacon_cntdwn(sdata, beacon, link);
                }

                skb = dev_alloc_skb(local->tx_headroom + beacon->head_len +
                                    local->hw.extra_beacon_tailroom);
                if (!skb)
                        goto out;
                skb_reserve(skb, local->tx_headroom);
                skb_put_data(skb, beacon->head, beacon->head_len);

                hdr = (struct ieee80211_hdr *) skb->data;
                hdr->frame_control = cpu_to_le16(IEEE80211_FTYPE_MGMT |
                                                 IEEE80211_STYPE_BEACON);

                ieee80211_beacon_get_finish(hw, vif, link, offs, beacon, skb,
                                            chanctx_conf, 0);
        } else if (ieee80211_vif_is_mesh(&sdata->vif)) {
                struct ieee80211_if_mesh *ifmsh = &sdata->u.mesh;

                beacon = rcu_dereference(ifmsh->beacon);
                if (!beacon)
                        goto out;

                if (beacon->cntdwn_counter_offsets[0]) {
                        if (!is_template)
                                /* TODO: For mesh csa_counter is in TU, so
                                 * decrementing it by one isn't correct, but
                                 * for now we leave it consistent with overall
                                 * mac80211's behavior.
                                 */
                                __ieee80211_beacon_update_cntdwn(beacon);

                        ieee80211_set_beacon_cntdwn(sdata, beacon, link);
                }

                if (ifmsh->sync_ops)
                        ifmsh->sync_ops->adjust_tsf(sdata, beacon);

                skb = dev_alloc_skb(local->tx_headroom +
                                    beacon->head_len +
                                    256 + /* TIM IE */
                                    beacon->tail_len +
                                    local->hw.extra_beacon_tailroom);
                if (!skb)
                        goto out;
                skb_reserve(skb, local->tx_headroom);
                skb_put_data(skb, beacon->head, beacon->head_len);
                ieee80211_beacon_add_tim(sdata, link, &ifmsh->ps, skb,
                                         is_template);

                if (offs) {
                        offs->tim_offset = beacon->head_len;
                        offs->tim_length = skb->len - beacon->head_len;
                }

                skb_put_data(skb, beacon->tail, beacon->tail_len);
                ieee80211_beacon_get_finish(hw, vif, link, offs, beacon, skb,
                                            chanctx_conf, 0);
        } else {
                WARN_ON(1);
                goto out;
        }

 out:
        rcu_read_unlock();
        return skb;

}

struct sk_buff *
ieee80211_beacon_get_template(struct ieee80211_hw *hw,
                              struct ieee80211_vif *vif,
                              struct ieee80211_mutable_offsets *offs,
                              unsigned int link_id)
{
        return __ieee80211_beacon_get(hw, vif, offs, true, link_id,
                                      IEEE80211_INCLUDE_ALL_MBSSID_ELEMS, NULL);
}
EXPORT_SYMBOL(ieee80211_beacon_get_template);

struct sk_buff *
ieee80211_beacon_get_template_ema_index(struct ieee80211_hw *hw,
                                        struct ieee80211_vif *vif,
                                        struct ieee80211_mutable_offsets *offs,
                                        unsigned int link_id, u8 ema_index)
{
        return __ieee80211_beacon_get(hw, vif, offs, true, link_id, ema_index,
                                      NULL);
}
EXPORT_SYMBOL(ieee80211_beacon_get_template_ema_index);

void ieee80211_beacon_free_ema_list(struct ieee80211_ema_beacons *ema_beacons)
{
        u8 i;

        if (!ema_beacons)
                return;

        for (i = 0; i < ema_beacons->cnt; i++)
                kfree_skb(ema_beacons->bcn[i].skb);

        kfree(ema_beacons);
}
EXPORT_SYMBOL(ieee80211_beacon_free_ema_list);

struct ieee80211_ema_beacons *
ieee80211_beacon_get_template_ema_list(struct ieee80211_hw *hw,
                                       struct ieee80211_vif *vif,
                                       unsigned int link_id)
{
        struct ieee80211_ema_beacons *ema_beacons = NULL;

        WARN_ON(__ieee80211_beacon_get(hw, vif, NULL, true, link_id, 0,
                                       &ema_beacons));

        return ema_beacons;
}
EXPORT_SYMBOL(ieee80211_beacon_get_template_ema_list);

struct sk_buff *ieee80211_beacon_get_tim(struct ieee80211_hw *hw,
                                         struct ieee80211_vif *vif,
                                         u16 *tim_offset, u16 *tim_length,
                                         unsigned int link_id)
{
        struct ieee80211_mutable_offsets offs = {};
        struct sk_buff *bcn = __ieee80211_beacon_get(hw, vif, &offs, false,
                                                     link_id,
                                                     IEEE80211_INCLUDE_ALL_MBSSID_ELEMS,
                                                     NULL);
        struct sk_buff *copy;

        if (!bcn)
                return bcn;

        if (tim_offset)
                *tim_offset = offs.tim_offset;

        if (tim_length)
                *tim_length = offs.tim_length;

        if (ieee80211_hw_check(hw, BEACON_TX_STATUS) ||
            !hw_to_local(hw)->monitors)
                return bcn;

        /* send a copy to monitor interfaces */
        copy = skb_copy(bcn, GFP_ATOMIC);
        if (!copy)
                return bcn;

        ieee80211_tx_monitor(hw_to_local(hw), copy, 1, false, NULL);

        return bcn;
}
EXPORT_SYMBOL(ieee80211_beacon_get_tim);

struct sk_buff *ieee80211_proberesp_get(struct ieee80211_hw *hw,
                                        struct ieee80211_vif *vif)
{
        struct sk_buff *skb = NULL;
        struct probe_resp *presp = NULL;
        struct ieee80211_hdr *hdr;
        struct ieee80211_sub_if_data *sdata = vif_to_sdata(vif);

        if (sdata->vif.type != NL80211_IFTYPE_AP)
                return NULL;

        rcu_read_lock();
        presp = rcu_dereference(sdata->deflink.u.ap.probe_resp);
        if (!presp)
                goto out;

        skb = dev_alloc_skb(presp->len);
        if (!skb)
                goto out;

        skb_put_data(skb, presp->data, presp->len);

        hdr = (struct ieee80211_hdr *) skb->data;
        memset(hdr->addr1, 0, sizeof(hdr->addr1));

out:
        rcu_read_unlock();
        return skb;
}
EXPORT_SYMBOL(ieee80211_proberesp_get);

struct sk_buff *ieee80211_get_fils_discovery_tmpl(struct ieee80211_hw *hw,
                                                  struct ieee80211_vif *vif)
{
        struct sk_buff *skb = NULL;
        struct fils_discovery_data *tmpl = NULL;
        struct ieee80211_sub_if_data *sdata = vif_to_sdata(vif);

        if (sdata->vif.type != NL80211_IFTYPE_AP)
                return NULL;

        rcu_read_lock();
        tmpl = rcu_dereference(sdata->deflink.u.ap.fils_discovery);
        if (!tmpl) {
                rcu_read_unlock();
                return NULL;
        }

        skb = dev_alloc_skb(sdata->local->hw.extra_tx_headroom + tmpl->len);
        if (skb) {
                skb_reserve(skb, sdata->local->hw.extra_tx_headroom);
                skb_put_data(skb, tmpl->data, tmpl->len);
        }

        rcu_read_unlock();
        return skb;
}
EXPORT_SYMBOL(ieee80211_get_fils_discovery_tmpl);

struct sk_buff *
ieee80211_get_unsol_bcast_probe_resp_tmpl(struct ieee80211_hw *hw,
                                          struct ieee80211_vif *vif)
{
        struct sk_buff *skb = NULL;
        struct unsol_bcast_probe_resp_data *tmpl = NULL;
        struct ieee80211_sub_if_data *sdata = vif_to_sdata(vif);

        if (sdata->vif.type != NL80211_IFTYPE_AP)
                return NULL;

        rcu_read_lock();
        tmpl = rcu_dereference(sdata->deflink.u.ap.unsol_bcast_probe_resp);
        if (!tmpl) {
                rcu_read_unlock();
                return NULL;
        }

        skb = dev_alloc_skb(sdata->local->hw.extra_tx_headroom + tmpl->len);
        if (skb) {
                skb_reserve(skb, sdata->local->hw.extra_tx_headroom);
                skb_put_data(skb, tmpl->data, tmpl->len);
        }

        rcu_read_unlock();
        return skb;
}
EXPORT_SYMBOL(ieee80211_get_unsol_bcast_probe_resp_tmpl);

struct sk_buff *ieee80211_pspoll_get(struct ieee80211_hw *hw,
                                     struct ieee80211_vif *vif)
{
        struct ieee80211_sub_if_data *sdata;
        struct ieee80211_pspoll *pspoll;
        struct ieee80211_local *local;
        struct sk_buff *skb;

        if (WARN_ON(vif->type != NL80211_IFTYPE_STATION))
                return NULL;

        sdata = vif_to_sdata(vif);
        local = sdata->local;

        skb = dev_alloc_skb(local->hw.extra_tx_headroom + sizeof(*pspoll));
        if (!skb)
                return NULL;

        skb_reserve(skb, local->hw.extra_tx_headroom);

        pspoll = skb_put_zero(skb, sizeof(*pspoll));
        pspoll->frame_control = cpu_to_le16(IEEE80211_FTYPE_CTL |
                                            IEEE80211_STYPE_PSPOLL);
        pspoll->aid = cpu_to_le16(sdata->vif.cfg.aid);

        /* aid in PS-Poll has its two MSBs each set to 1 */
        pspoll->aid |= cpu_to_le16(1 << 15 | 1 << 14);

        memcpy(pspoll->bssid, sdata->deflink.u.mgd.bssid, ETH_ALEN);
        memcpy(pspoll->ta, vif->addr, ETH_ALEN);

        return skb;
}
EXPORT_SYMBOL(ieee80211_pspoll_get);

struct sk_buff *ieee80211_nullfunc_get(struct ieee80211_hw *hw,
                                       struct ieee80211_vif *vif,
                                       int link_id, bool qos_ok)
{
        struct ieee80211_sub_if_data *sdata = vif_to_sdata(vif);
        struct ieee80211_local *local = sdata->local;
        struct ieee80211_link_data *link = NULL;
        struct ieee80211_hdr_3addr *nullfunc;
        struct sk_buff *skb;
        bool qos = false;

        if (WARN_ON(vif->type != NL80211_IFTYPE_STATION))
                return NULL;

        skb = dev_alloc_skb(local->hw.extra_tx_headroom +
                            sizeof(*nullfunc) + 2);
        if (!skb)
                return NULL;

        rcu_read_lock();
        if (qos_ok) {
                struct sta_info *sta;

                sta = sta_info_get(sdata, vif->cfg.ap_addr);
                qos = sta && sta->sta.wme;
        }

        if (link_id >= 0) {
                link = rcu_dereference(sdata->link[link_id]);
                if (WARN_ON_ONCE(!link)) {
                        rcu_read_unlock();
                        kfree_skb(skb);
                        return NULL;
                }
        }

        skb_reserve(skb, local->hw.extra_tx_headroom);

        nullfunc = skb_put_zero(skb, sizeof(*nullfunc));
        nullfunc->frame_control = cpu_to_le16(IEEE80211_FTYPE_DATA |
                                              IEEE80211_STYPE_NULLFUNC |
                                              IEEE80211_FCTL_TODS);
        if (qos) {
                __le16 qoshdr = cpu_to_le16(7);

                BUILD_BUG_ON((IEEE80211_STYPE_QOS_NULLFUNC |
                              IEEE80211_STYPE_NULLFUNC) !=
                             IEEE80211_STYPE_QOS_NULLFUNC);
                nullfunc->frame_control |=
                        cpu_to_le16(IEEE80211_STYPE_QOS_NULLFUNC);
                skb->priority = 7;
                skb_set_queue_mapping(skb, IEEE80211_AC_VO);
                skb_put_data(skb, &qoshdr, sizeof(qoshdr));
        }

        if (link) {
                memcpy(nullfunc->addr1, link->conf->bssid, ETH_ALEN);
                memcpy(nullfunc->addr2, link->conf->addr, ETH_ALEN);
                memcpy(nullfunc->addr3, link->conf->bssid, ETH_ALEN);
        } else {
                memcpy(nullfunc->addr1, vif->cfg.ap_addr, ETH_ALEN);
                memcpy(nullfunc->addr2, vif->addr, ETH_ALEN);
                memcpy(nullfunc->addr3, vif->cfg.ap_addr, ETH_ALEN);
        }
        rcu_read_unlock();

        return skb;
}
EXPORT_SYMBOL(ieee80211_nullfunc_get);

struct sk_buff *ieee80211_probereq_get(struct ieee80211_hw *hw,
                                       const u8 *src_addr,
                                       const u8 *ssid, size_t ssid_len,
                                       size_t tailroom)
{
        struct ieee80211_local *local = hw_to_local(hw);
        struct ieee80211_hdr_3addr *hdr;
        struct sk_buff *skb;
        size_t ie_ssid_len;
        u8 *pos;

        ie_ssid_len = 2 + ssid_len;

        skb = dev_alloc_skb(local->hw.extra_tx_headroom + sizeof(*hdr) +
                            ie_ssid_len + tailroom);
        if (!skb)
                return NULL;

        skb_reserve(skb, local->hw.extra_tx_headroom);

        hdr = skb_put_zero(skb, sizeof(*hdr));
        hdr->frame_control = cpu_to_le16(IEEE80211_FTYPE_MGMT |
                                         IEEE80211_STYPE_PROBE_REQ);
        eth_broadcast_addr(hdr->addr1);
        memcpy(hdr->addr2, src_addr, ETH_ALEN);
        eth_broadcast_addr(hdr->addr3);

        pos = skb_put(skb, ie_ssid_len);
        *pos++ = WLAN_EID_SSID;
        *pos++ = ssid_len;
        if (ssid_len)
                memcpy(pos, ssid, ssid_len);
        pos += ssid_len;

        return skb;
}
EXPORT_SYMBOL(ieee80211_probereq_get);

void ieee80211_rts_get(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
                       const void *frame, size_t frame_len,
                       const struct ieee80211_tx_info *frame_txctl,
                       struct ieee80211_rts *rts)
{
        const struct ieee80211_hdr *hdr = frame;

        rts->frame_control =
            cpu_to_le16(IEEE80211_FTYPE_CTL | IEEE80211_STYPE_RTS);
        rts->duration = ieee80211_rts_duration(hw, vif, frame_len,
                                               frame_txctl);
        memcpy(rts->ra, hdr->addr1, sizeof(rts->ra));
        memcpy(rts->ta, hdr->addr2, sizeof(rts->ta));
}
EXPORT_SYMBOL(ieee80211_rts_get);

void ieee80211_ctstoself_get(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
                             const void *frame, size_t frame_len,
                             const struct ieee80211_tx_info *frame_txctl,
                             struct ieee80211_cts *cts)
{
        const struct ieee80211_hdr *hdr = frame;

        cts->frame_control =
            cpu_to_le16(IEEE80211_FTYPE_CTL | IEEE80211_STYPE_CTS);
        cts->duration = ieee80211_ctstoself_duration(hw, vif,
                                                     frame_len, frame_txctl);
        memcpy(cts->ra, hdr->addr1, sizeof(cts->ra));
}
EXPORT_SYMBOL(ieee80211_ctstoself_get);

struct sk_buff *
ieee80211_get_buffered_bc(struct ieee80211_hw *hw,
                          struct ieee80211_vif *vif)
{
        struct ieee80211_local *local = hw_to_local(hw);
        struct sk_buff *skb = NULL;
        struct ieee80211_tx_data tx;
        struct ieee80211_sub_if_data *sdata;
        struct ps_data *ps;
        struct ieee80211_tx_info *info;
        struct ieee80211_chanctx_conf *chanctx_conf;

        sdata = vif_to_sdata(vif);

        rcu_read_lock();
        chanctx_conf = rcu_dereference(sdata->vif.bss_conf.chanctx_conf);

        if (!chanctx_conf)
                goto out;

        if (sdata->vif.type == NL80211_IFTYPE_AP) {
                struct beacon_data *beacon =
                                rcu_dereference(sdata->deflink.u.ap.beacon);

                if (!beacon || !beacon->head)
                        goto out;

                ps = &sdata->u.ap.ps;
        } else if (ieee80211_vif_is_mesh(&sdata->vif)) {
                ps = &sdata->u.mesh.ps;
        } else {
                goto out;
        }

        if (ps->dtim_count != 0 || !ps->dtim_bc_mc)
                goto out; /* send buffered bc/mc only after DTIM beacon */

        while (1) {
                skb = skb_dequeue(&ps->bc_buf);
                if (!skb)
                        goto out;
                local->total_ps_buffered--;

                if (!skb_queue_empty(&ps->bc_buf) && skb->len >= 2) {
                        struct ieee80211_hdr *hdr =
                                (struct ieee80211_hdr *) skb->data;
                        /* more buffered multicast/broadcast frames ==> set
                         * MoreData flag in IEEE 802.11 header to inform PS
                         * STAs */
                        hdr->frame_control |=
                                cpu_to_le16(IEEE80211_FCTL_MOREDATA);
                }

                if (sdata->vif.type == NL80211_IFTYPE_AP)
                        sdata = IEEE80211_DEV_TO_SUB_IF(skb->dev);
                if (!ieee80211_tx_prepare(sdata, &tx, NULL, skb))
                        break;
                ieee80211_free_txskb(hw, skb);
        }

        info = IEEE80211_SKB_CB(skb);

        tx.flags |= IEEE80211_TX_PS_BUFFERED;
        info->band = chanctx_conf->def.chan->band;

        if (invoke_tx_handlers(&tx))
                skb = NULL;
 out:
        rcu_read_unlock();

        return skb;
}
EXPORT_SYMBOL(ieee80211_get_buffered_bc);

int ieee80211_reserve_tid(struct ieee80211_sta *pubsta, u8 tid)
{
        struct sta_info *sta = container_of(pubsta, struct sta_info, sta);
        struct ieee80211_sub_if_data *sdata = sta->sdata;
        struct ieee80211_local *local = sdata->local;
        int ret;
        u32 queues;

        lockdep_assert_wiphy(local->hw.wiphy);

        /* only some cases are supported right now */
        switch (sdata->vif.type) {
        case NL80211_IFTYPE_STATION:
        case NL80211_IFTYPE_AP:
        case NL80211_IFTYPE_AP_VLAN:
                break;
        default:
                WARN_ON(1);
                return -EINVAL;
        }

        if (WARN_ON(tid >= IEEE80211_NUM_UPS))
                return -EINVAL;

        if (sta->reserved_tid == tid) {
                ret = 0;
                goto out;
        }

        if (sta->reserved_tid != IEEE80211_TID_UNRESERVED) {
                sdata_err(sdata, "TID reservation already active\n");
                ret = -EALREADY;
                goto out;
        }

        ieee80211_stop_vif_queues(sdata->local, sdata,
                                  IEEE80211_QUEUE_STOP_REASON_RESERVE_TID);

        synchronize_net();

        /* Tear down BA sessions so we stop aggregating on this TID */
        if (ieee80211_hw_check(&local->hw, AMPDU_AGGREGATION)) {
                set_sta_flag(sta, WLAN_STA_BLOCK_BA);
                __ieee80211_stop_tx_ba_session(sta, tid,
                                               AGG_STOP_LOCAL_REQUEST);
        }

        queues = BIT(sdata->vif.hw_queue[ieee802_1d_to_ac[tid]]);
        __ieee80211_flush_queues(local, sdata, queues, false);

        sta->reserved_tid = tid;

        ieee80211_wake_vif_queues(local, sdata,
                                  IEEE80211_QUEUE_STOP_REASON_RESERVE_TID);

        if (ieee80211_hw_check(&local->hw, AMPDU_AGGREGATION))
                clear_sta_flag(sta, WLAN_STA_BLOCK_BA);

        ret = 0;
 out:
        return ret;
}
EXPORT_SYMBOL(ieee80211_reserve_tid);

void ieee80211_unreserve_tid(struct ieee80211_sta *pubsta, u8 tid)
{
        struct sta_info *sta = container_of(pubsta, struct sta_info, sta);
        struct ieee80211_sub_if_data *sdata = sta->sdata;

        lockdep_assert_wiphy(sdata->local->hw.wiphy);

        /* only some cases are supported right now */
        switch (sdata->vif.type) {
        case NL80211_IFTYPE_STATION:
        case NL80211_IFTYPE_AP:
        case NL80211_IFTYPE_AP_VLAN:
                break;
        default:
                WARN_ON(1);
                return;
        }

        if (tid != sta->reserved_tid) {
                sdata_err(sdata, "TID to unreserve (%d) isn't reserved\n", tid);
                return;
        }

        sta->reserved_tid = IEEE80211_TID_UNRESERVED;
}
EXPORT_SYMBOL(ieee80211_unreserve_tid);

void __ieee80211_tx_skb_tid_band(struct ieee80211_sub_if_data *sdata,
                                 struct sk_buff *skb, int tid, int link_id,
                                 enum nl80211_band band)
{
        const struct ieee80211_hdr *hdr = (void *)skb->data;
        int ac = ieee80211_ac_from_tid(tid);
        unsigned int link;

        skb_reset_mac_header(skb);
        skb_set_queue_mapping(skb, ac);
        skb->priority = tid;

        skb->dev = sdata->dev;

        BUILD_BUG_ON(IEEE80211_LINK_UNSPECIFIED < IEEE80211_MLD_MAX_NUM_LINKS);
        BUILD_BUG_ON(!FIELD_FIT(IEEE80211_TX_CTRL_MLO_LINK,
                                IEEE80211_LINK_UNSPECIFIED));

        if (!ieee80211_vif_is_mld(&sdata->vif)) {
                link = 0;
        } else if (link_id >= 0) {
                link = link_id;
        } else if (memcmp(sdata->vif.addr, hdr->addr2, ETH_ALEN) == 0) {
                /* address from the MLD */
                link = IEEE80211_LINK_UNSPECIFIED;
        } else {
                /* otherwise must be addressed from a link */
                rcu_read_lock();
                for (link = 0; link < ARRAY_SIZE(sdata->vif.link_conf); link++) {
                        struct ieee80211_bss_conf *link_conf;

                        link_conf = rcu_dereference(sdata->vif.link_conf[link]);
                        if (!link_conf)
                                continue;
                        if (memcmp(link_conf->addr, hdr->addr2, ETH_ALEN) == 0)
                                break;
                }
                rcu_read_unlock();

                if (WARN_ON_ONCE(link == ARRAY_SIZE(sdata->vif.link_conf)))
                        link = ffs(sdata->vif.active_links) - 1;
        }

        IEEE80211_SKB_CB(skb)->control.flags |=
                u32_encode_bits(link, IEEE80211_TX_CTRL_MLO_LINK);

        /*
         * The other path calling ieee80211_xmit is from the tasklet,
         * and while we can handle concurrent transmissions locking
         * requirements are that we do not come into tx with bhs on.
         */
        local_bh_disable();
        IEEE80211_SKB_CB(skb)->band = band;
        ieee80211_xmit(sdata, NULL, skb);
        local_bh_enable();
}

void ieee80211_tx_skb_tid(struct ieee80211_sub_if_data *sdata,
                          struct sk_buff *skb, int tid, int link_id)
{
        struct ieee80211_chanctx_conf *chanctx_conf;
        enum nl80211_band band;

        rcu_read_lock();
        if (!ieee80211_vif_is_mld(&sdata->vif)) {
                WARN_ON(link_id >= 0);
                chanctx_conf =
                        rcu_dereference(sdata->vif.bss_conf.chanctx_conf);
                if (WARN_ON(!chanctx_conf)) {
                        rcu_read_unlock();
                        kfree_skb(skb);
                        return;
                }
                band = chanctx_conf->def.chan->band;
        } else {
                WARN_ON(link_id >= 0 &&
                        !(sdata->vif.active_links & BIT(link_id)));
                /* MLD transmissions must not rely on the band */
                band = 0;
        }

        __ieee80211_tx_skb_tid_band(sdata, skb, tid, link_id, band);
        rcu_read_unlock();
}

int ieee80211_tx_control_port(struct wiphy *wiphy, struct net_device *dev,
                              const u8 *buf, size_t len,
                              const u8 *dest, __be16 proto, bool unencrypted,
                              int link_id, u64 *cookie)
{
        struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev);
        struct ieee80211_local *local = sdata->local;
        struct sta_info *sta;
        struct sk_buff *skb;
        struct ethhdr *ehdr;
        u32 ctrl_flags = 0;
        u32 flags = 0;
        int err;

        /* mutex lock is only needed for incrementing the cookie counter */
        lockdep_assert_wiphy(local->hw.wiphy);

        /* Only accept CONTROL_PORT_PROTOCOL configured in CONNECT/ASSOCIATE
         * or Pre-Authentication
         */
        if (proto != sdata->control_port_protocol &&
            proto != cpu_to_be16(ETH_P_PREAUTH))
                return -EINVAL;

        if (proto == sdata->control_port_protocol)
                ctrl_flags |= IEEE80211_TX_CTRL_PORT_CTRL_PROTO |
                              IEEE80211_TX_CTRL_SKIP_MPATH_LOOKUP;

        if (unencrypted)
                flags |= IEEE80211_TX_INTFL_DONT_ENCRYPT;

        if (cookie)
                ctrl_flags |= IEEE80211_TX_CTL_REQ_TX_STATUS;

        flags |= IEEE80211_TX_INTFL_NL80211_FRAME_TX;

        skb = dev_alloc_skb(local->hw.extra_tx_headroom +
                            sizeof(struct ethhdr) + len);
        if (!skb)
                return -ENOMEM;

        skb_reserve(skb, local->hw.extra_tx_headroom + sizeof(struct ethhdr));

        skb_put_data(skb, buf, len);

        ehdr = skb_push(skb, sizeof(struct ethhdr));
        memcpy(ehdr->h_dest, dest, ETH_ALEN);

        /* we may override the SA for MLO STA later */
        if (link_id < 0) {
                ctrl_flags |= u32_encode_bits(IEEE80211_LINK_UNSPECIFIED,
                                              IEEE80211_TX_CTRL_MLO_LINK);
                memcpy(ehdr->h_source, sdata->vif.addr, ETH_ALEN);
        } else {
                struct ieee80211_bss_conf *link_conf;

                ctrl_flags |= u32_encode_bits(link_id,
                                              IEEE80211_TX_CTRL_MLO_LINK);

                rcu_read_lock();
                link_conf = rcu_dereference(sdata->vif.link_conf[link_id]);
                if (!link_conf) {
                        dev_kfree_skb(skb);
                        rcu_read_unlock();
                        return -ENOLINK;
                }
                memcpy(ehdr->h_source, link_conf->addr, ETH_ALEN);
                rcu_read_unlock();
        }

        ehdr->h_proto = proto;

        skb->dev = dev;
        skb->protocol = proto;
        skb_reset_network_header(skb);
        skb_reset_mac_header(skb);

        if (local->hw.queues < IEEE80211_NUM_ACS)
                goto start_xmit;

        /* update QoS header to prioritize control port frames if possible,
         * prioritization also happens for control port frames send over
         * AF_PACKET
         */
        rcu_read_lock();
        err = ieee80211_lookup_ra_sta(sdata, skb, &sta);
        if (err) {
                dev_kfree_skb(skb);
                rcu_read_unlock();
                return err;
        }

        if (!IS_ERR(sta)) {
                u16 queue = ieee80211_select_queue(sdata, sta, skb);

                skb_set_queue_mapping(skb, queue);

                /*
                 * for MLO STA, the SA should be the AP MLD address, but
                 * the link ID has been selected already
                 */
                if (sta && sta->sta.mlo)
                        memcpy(ehdr->h_source, sdata->vif.addr, ETH_ALEN);
        }
        rcu_read_unlock();

start_xmit:
        local_bh_disable();
        __ieee80211_subif_start_xmit(skb, skb->dev, flags, ctrl_flags, cookie);
        local_bh_enable();

        return 0;
}

int ieee80211_probe_mesh_link(struct wiphy *wiphy, struct net_device *dev,
                              const u8 *buf, size_t len)
{
        struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev);
        struct ieee80211_local *local = sdata->local;
        struct sk_buff *skb;

        skb = dev_alloc_skb(local->hw.extra_tx_headroom + len +
                            30 + /* header size */
                            18); /* 11s header size */
        if (!skb)
                return -ENOMEM;

        skb_reserve(skb, local->hw.extra_tx_headroom);
        skb_put_data(skb, buf, len);

        skb->dev = dev;
        skb->protocol = htons(ETH_P_802_3);
        skb_reset_network_header(skb);
        skb_reset_mac_header(skb);

        local_bh_disable();
        __ieee80211_subif_start_xmit(skb, skb->dev, 0,
                                     IEEE80211_TX_CTRL_SKIP_MPATH_LOOKUP,
                                     NULL);
        local_bh_enable();

        return 0;
}















































  172 













    2 




















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
/* SPDX-License-Identifier: GPL-2.0 */
#ifndef _BCACHEFS_JOURNAL_RECLAIM_H
#define _BCACHEFS_JOURNAL_RECLAIM_H

#define JOURNAL_PIN        (32 * 1024)

static inline void journal_reclaim_kick(struct journal *j)
{
        struct task_struct *p = READ_ONCE(j->reclaim_thread);

        j->reclaim_kicked = true;
        if (p)
                wake_up_process(p);
}

unsigned bch2_journal_dev_buckets_available(struct journal *,
                                            struct journal_device *,
                                            enum journal_space_from);
void bch2_journal_set_watermark(struct journal *);
void bch2_journal_space_available(struct journal *);

static inline bool journal_pin_active(struct journal_entry_pin *pin)
{
        return pin->seq != 0;
}

static inline struct journal_entry_pin_list *
journal_seq_pin(struct journal *j, u64 seq)
{
        EBUG_ON(seq < j->pin.front || seq >= j->pin.back);

        return &j->pin.data[seq & j->pin.mask];
}

void bch2_journal_reclaim_fast(struct journal *);
bool __bch2_journal_pin_put(struct journal *, u64);
void bch2_journal_pin_put(struct journal *, u64);
void bch2_journal_pin_drop(struct journal *, struct journal_entry_pin *);

void bch2_journal_pin_set(struct journal *, u64, struct journal_entry_pin *,
                          journal_pin_flush_fn);

static inline void bch2_journal_pin_add(struct journal *j, u64 seq,
                                        struct journal_entry_pin *pin,
                                        journal_pin_flush_fn flush_fn)
{
        if (unlikely(!journal_pin_active(pin) || pin->seq > seq))
                bch2_journal_pin_set(j, seq, pin, flush_fn);
}

void bch2_journal_pin_copy(struct journal *,
                           struct journal_entry_pin *,
                           struct journal_entry_pin *,
                           journal_pin_flush_fn);

static inline void bch2_journal_pin_update(struct journal *j, u64 seq,
                                           struct journal_entry_pin *pin,
                                           journal_pin_flush_fn flush_fn)
{
        if (unlikely(!journal_pin_active(pin) || pin->seq < seq))
                bch2_journal_pin_set(j, seq, pin, flush_fn);
}

void bch2_journal_pin_flush(struct journal *, struct journal_entry_pin *);

void bch2_journal_do_discards(struct journal *);
int bch2_journal_reclaim(struct journal *);

void bch2_journal_reclaim_stop(struct journal *);
int bch2_journal_reclaim_start(struct journal *);

bool bch2_journal_flush_pins(struct journal *, u64);

static inline bool bch2_journal_flush_all_pins(struct journal *j)
{
        return bch2_journal_flush_pins(j, U64_MAX);
}

int bch2_journal_flush_device_pins(struct journal *, int);

#endif /* _BCACHEFS_JOURNAL_RECLAIM_H */























































































































































































  172 



























































































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
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
/* SPDX-License-Identifier: GPL-2.0-or-later */
/*
 * Cryptographic API for algorithms (i.e., low-level API).
 *
 * Copyright (c) 2006 Herbert Xu <herbert@gondor.apana.org.au>
 */
#ifndef _CRYPTO_ALGAPI_H
#define _CRYPTO_ALGAPI_H

#include <crypto/utils.h>
#include <linux/align.h>
#include <linux/cache.h>
#include <linux/crypto.h>
#include <linux/types.h>
#include <linux/workqueue.h>

/*
 * Maximum values for blocksize and alignmask, used to allocate
 * static buffers that are big enough for any combination of
 * algs and architectures. Ciphers have a lower maximum size.
 */
#define MAX_ALGAPI_BLOCKSIZE                160
#define MAX_ALGAPI_ALIGNMASK                127
#define MAX_CIPHER_BLOCKSIZE                16
#define MAX_CIPHER_ALIGNMASK                15

#ifdef ARCH_DMA_MINALIGN
#define CRYPTO_DMA_ALIGN ARCH_DMA_MINALIGN
#else
#define CRYPTO_DMA_ALIGN CRYPTO_MINALIGN
#endif

#define CRYPTO_DMA_PADDING ((CRYPTO_DMA_ALIGN - 1) & ~(CRYPTO_MINALIGN - 1))

/*
 * Autoloaded crypto modules should only use a prefixed name to avoid allowing
 * arbitrary modules to be loaded. Loading from userspace may still need the
 * unprefixed names, so retains those aliases as well.
 * This uses __MODULE_INFO directly instead of MODULE_ALIAS because pre-4.3
 * gcc (e.g. avr32 toolchain) uses __LINE__ for uniqueness, and this macro
 * expands twice on the same line. Instead, use a separate base name for the
 * alias.
 */
#define MODULE_ALIAS_CRYPTO(name)        \
                __MODULE_INFO(alias, alias_userspace, name);        \
                __MODULE_INFO(alias, alias_crypto, "crypto-" name)

struct crypto_aead;
struct crypto_instance;
struct module;
struct notifier_block;
struct rtattr;
struct scatterlist;
struct seq_file;
struct sk_buff;

struct crypto_type {
        unsigned int (*ctxsize)(struct crypto_alg *alg, u32 type, u32 mask);
        unsigned int (*extsize)(struct crypto_alg *alg);
        int (*init_tfm)(struct crypto_tfm *tfm);
        void (*show)(struct seq_file *m, struct crypto_alg *alg);
        int (*report)(struct sk_buff *skb, struct crypto_alg *alg);
        void (*free)(struct crypto_instance *inst);

        unsigned int type;
        unsigned int maskclear;
        unsigned int maskset;
        unsigned int tfmsize;
};

struct crypto_instance {
        struct crypto_alg alg;

        struct crypto_template *tmpl;

        union {
                /* Node in list of instances after registration. */
                struct hlist_node list;
                /* List of attached spawns before registration. */
                struct crypto_spawn *spawns;
        };

        struct work_struct free_work;

        void *__ctx[] CRYPTO_MINALIGN_ATTR;
};

struct crypto_template {
        struct list_head list;
        struct hlist_head instances;
        struct module *module;

        int (*create)(struct crypto_template *tmpl, struct rtattr **tb);

        char name[CRYPTO_MAX_ALG_NAME];
};

struct crypto_spawn {
        struct list_head list;
        struct crypto_alg *alg;
        union {
                /* Back pointer to instance after registration.*/
                struct crypto_instance *inst;
                /* Spawn list pointer prior to registration. */
                struct crypto_spawn *next;
        };
        const struct crypto_type *frontend;
        u32 mask;
        bool dead;
        bool registered;
};

struct crypto_queue {
        struct list_head list;
        struct list_head *backlog;

        unsigned int qlen;
        unsigned int max_qlen;
};

struct scatter_walk {
        struct scatterlist *sg;
        unsigned int offset;
};

struct crypto_attr_alg {
        char name[CRYPTO_MAX_ALG_NAME];
};

struct crypto_attr_type {
        u32 type;
        u32 mask;
};

/*
 * Algorithm registration interface.
 */
int crypto_register_alg(struct crypto_alg *alg);
void crypto_unregister_alg(struct crypto_alg *alg);
int crypto_register_algs(struct crypto_alg *algs, int count);
void crypto_unregister_algs(struct crypto_alg *algs, int count);

void crypto_mod_put(struct crypto_alg *alg);

int crypto_register_template(struct crypto_template *tmpl);
int crypto_register_templates(struct crypto_template *tmpls, int count);
void crypto_unregister_template(struct crypto_template *tmpl);
void crypto_unregister_templates(struct crypto_template *tmpls, int count);
struct crypto_template *crypto_lookup_template(const char *name);

int crypto_register_instance(struct crypto_template *tmpl,
                             struct crypto_instance *inst);
void crypto_unregister_instance(struct crypto_instance *inst);

int crypto_grab_spawn(struct crypto_spawn *spawn, struct crypto_instance *inst,
                      const char *name, u32 type, u32 mask);
void crypto_drop_spawn(struct crypto_spawn *spawn);
struct crypto_tfm *crypto_spawn_tfm(struct crypto_spawn *spawn, u32 type,
                                    u32 mask);
void *crypto_spawn_tfm2(struct crypto_spawn *spawn);

struct crypto_attr_type *crypto_get_attr_type(struct rtattr **tb);
int crypto_check_attr_type(struct rtattr **tb, u32 type, u32 *mask_ret);
const char *crypto_attr_alg_name(struct rtattr *rta);
int crypto_inst_setname(struct crypto_instance *inst, const char *name,
                        struct crypto_alg *alg);

void crypto_init_queue(struct crypto_queue *queue, unsigned int max_qlen);
int crypto_enqueue_request(struct crypto_queue *queue,
                           struct crypto_async_request *request);
void crypto_enqueue_request_head(struct crypto_queue *queue,
                                 struct crypto_async_request *request);
struct crypto_async_request *crypto_dequeue_request(struct crypto_queue *queue);
static inline unsigned int crypto_queue_len(struct crypto_queue *queue)
{
        return queue->qlen;
}

void crypto_inc(u8 *a, unsigned int size);

static inline void *crypto_tfm_ctx(struct crypto_tfm *tfm)
{
        return tfm->__crt_ctx;
}

static inline void *crypto_tfm_ctx_align(struct crypto_tfm *tfm,
                                         unsigned int align)
{
        if (align <= crypto_tfm_ctx_alignment())
                align = 1;

        return PTR_ALIGN(crypto_tfm_ctx(tfm), align);
}

static inline unsigned int crypto_dma_align(void)
{
        return CRYPTO_DMA_ALIGN;
}

static inline unsigned int crypto_dma_padding(void)
{
        return (crypto_dma_align() - 1) & ~(crypto_tfm_ctx_alignment() - 1);
}

static inline void *crypto_tfm_ctx_dma(struct crypto_tfm *tfm)
{
        return crypto_tfm_ctx_align(tfm, crypto_dma_align());
}

static inline struct crypto_instance *crypto_tfm_alg_instance(
        struct crypto_tfm *tfm)
{
        return container_of(tfm->__crt_alg, struct crypto_instance, alg);
}

static inline void *crypto_instance_ctx(struct crypto_instance *inst)
{
        return inst->__ctx;
}

static inline struct crypto_async_request *crypto_get_backlog(
        struct crypto_queue *queue)
{
        return queue->backlog == &queue->list ? NULL :
               container_of(queue->backlog, struct crypto_async_request, list);
}

static inline u32 crypto_requires_off(struct crypto_attr_type *algt, u32 off)
{
        return (algt->type ^ off) & algt->mask & off;
}

/*
 * When an algorithm uses another algorithm (e.g., if it's an instance of a
 * template), these are the flags that should always be set on the "outer"
 * algorithm if any "inner" algorithm has them set.
 */
#define CRYPTO_ALG_INHERITED_FLAGS        \
        (CRYPTO_ALG_ASYNC | CRYPTO_ALG_NEED_FALLBACK |        \
         CRYPTO_ALG_ALLOCATES_MEMORY)

/*
 * Given the type and mask that specify the flags restrictions on a template
 * instance being created, return the mask that should be passed to
 * crypto_grab_*() (along with type=0) to honor any request the user made to
 * have any of the CRYPTO_ALG_INHERITED_FLAGS clear.
 */
static inline u32 crypto_algt_inherited_mask(struct crypto_attr_type *algt)
{
        return crypto_requires_off(algt, CRYPTO_ALG_INHERITED_FLAGS);
}

int crypto_register_notifier(struct notifier_block *nb);
int crypto_unregister_notifier(struct notifier_block *nb);

/* Crypto notification events. */
enum {
        CRYPTO_MSG_ALG_REQUEST,
        CRYPTO_MSG_ALG_REGISTER,
        CRYPTO_MSG_ALG_LOADED,
};

static inline void crypto_request_complete(struct crypto_async_request *req,
                                           int err)
{
        req->complete(req->data, err);
}

static inline u32 crypto_tfm_alg_type(struct crypto_tfm *tfm)
{
        return tfm->__crt_alg->cra_flags & CRYPTO_ALG_TYPE_MASK;
}

#endif        /* _CRYPTO_ALGAPI_H */























  189 













  178 




   10 

















  147 









  185 






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
/*
 * linux/drivers/video/console/softcursor.c
 *
 * Generic software cursor for frame buffer devices
 *
 *  Created 14 Nov 2002 by James Simmons
 *
 * This file is subject to the terms and conditions of the GNU General
 * Public License.  See the file COPYING in the main directory of this
 * archive for more details.
 */

#include <linux/module.h>
#include <linux/string.h>
#include <linux/fb.h>
#include <linux/slab.h>

#include <asm/io.h>

#include "fbcon.h"

int soft_cursor(struct fb_info *info, struct fb_cursor *cursor)
{
        struct fbcon_ops *ops = info->fbcon_par;
        unsigned int scan_align = info->pixmap.scan_align - 1;
        unsigned int buf_align = info->pixmap.buf_align - 1;
        unsigned int i, size, dsize, s_pitch, d_pitch;
        struct fb_image *image;
        u8 *src, *dst;

        if (info->state != FBINFO_STATE_RUNNING)
                return 0;

        s_pitch = (cursor->image.width + 7) >> 3;
        dsize = s_pitch * cursor->image.height;

        if (dsize + sizeof(struct fb_image) != ops->cursor_size) {
                kfree(ops->cursor_src);
                ops->cursor_size = dsize + sizeof(struct fb_image);

                ops->cursor_src = kmalloc(ops->cursor_size, GFP_ATOMIC);
                if (!ops->cursor_src) {
                        ops->cursor_size = 0;
                        return -ENOMEM;
                }
        }

        src = ops->cursor_src + sizeof(struct fb_image);
        image = (struct fb_image *)ops->cursor_src;
        *image = cursor->image;
        d_pitch = (s_pitch + scan_align) & ~scan_align;

        size = d_pitch * image->height + buf_align;
        size &= ~buf_align;
        dst = fb_get_buffer_offset(info, &info->pixmap, size);

        if (cursor->enable) {
                switch (cursor->rop) {
                case ROP_XOR:
                        for (i = 0; i < dsize; i++)
                                src[i] = image->data[i] ^ cursor->mask[i];
                        break;
                case ROP_COPY:
                default:
                        for (i = 0; i < dsize; i++)
                                src[i] = image->data[i] & cursor->mask[i];
                        break;
                }
        } else
                memcpy(src, image->data, dsize);

        fb_pad_aligned_buffer(dst, d_pitch, src, s_pitch, image->height);
        image->data = dst;
        info->fbops->fb_imageblit(info, image);
        return 0;
}




































































































































































































































   23 







   17 


    8 




   23 
   23 
   11 

   18 













   17 


    8 




   23 

   23 

   23 

   23 

   23 

   23 
   23 






  179 
  179 
  179 










   26 











    3 


   19 


    5 
    4 







   15 



   15 
   15 


   15 

   15 



   15 










    7 




    4 
    7 




    4 







    7 





    7 

    7 




    7 



   14 


   14 


   11 







    5 






    5 
















    4 


    1 
    3 

    4 

    4 


















    5 



   40 


    5 

    2 




    8 



    8 
    8 


    8 

    1 


    1 



    1 
    1 



    3 






    2 


















    7 


    7 





    7 





    7 





















    1 









    1 
    1 

    1 






    1 


    1 























    6 



    6 



    6 



    6 



    6 
    6 





    6 















   11 




    1 




    2 











    6 
    6 



    1 
    2 





    2 
    8 







    1 




    8 












































































   40 






   40 















    5 

















    5 

    5 


    5 

    5 


    5 
    5 

    2 
    4 








    5 

    5 

















    1 





    4 

    4 
    4 






  173 




    3 

  162 

   20 







   36 






   84 



  134 


  171 
   21 




















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
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
// SPDX-License-Identifier: GPL-2.0
/*
 * consolemap.c
 *
 * Mapping from internal code (such as Latin-1 or Unicode or IBM PC code)
 * to font positions.
 *
 * aeb, 950210
 *
 * Support for multiple unimaps by Jakub Jelinek <jj@ultra.linux.cz>, July 1998
 *
 * Fix bug in inverse translation. Stanislav Voronyi <stas@cnti.uanet.kharkov.ua>, Dec 1998
 *
 * In order to prevent the following circular lock dependency:
 *   &mm->mmap_lock --> cpu_hotplug.lock --> console_lock --> &mm->mmap_lock
 *
 * We cannot allow page fault to happen while holding the console_lock.
 * Therefore, all the userspace copy operations have to be done outside
 * the console_lock critical sections.
 *
 * As all the affected functions are all called directly from vt_ioctl(), we
 * can allocate some small buffers directly on stack without worrying about
 * stack overflow.
 */

#include <linux/bitfield.h>
#include <linux/bits.h>
#include <linux/module.h>
#include <linux/kd.h>
#include <linux/errno.h>
#include <linux/mm.h>
#include <linux/slab.h>
#include <linux/init.h>
#include <linux/tty.h>
#include <linux/uaccess.h>
#include <linux/console.h>
#include <linux/consolemap.h>
#include <linux/vt_kern.h>
#include <linux/string.h>

static unsigned short translations[][E_TABSZ] = {
  /* 8-bit Latin-1 mapped to Unicode -- trivial mapping */
  [LAT1_MAP] = {
    0x0000, 0x0001, 0x0002, 0x0003, 0x0004, 0x0005, 0x0006, 0x0007,
    0x0008, 0x0009, 0x000a, 0x000b, 0x000c, 0x000d, 0x000e, 0x000f,
    0x0010, 0x0011, 0x0012, 0x0013, 0x0014, 0x0015, 0x0016, 0x0017,
    0x0018, 0x0019, 0x001a, 0x001b, 0x001c, 0x001d, 0x001e, 0x001f,
    0x0020, 0x0021, 0x0022, 0x0023, 0x0024, 0x0025, 0x0026, 0x0027,
    0x0028, 0x0029, 0x002a, 0x002b, 0x002c, 0x002d, 0x002e, 0x002f,
    0x0030, 0x0031, 0x0032, 0x0033, 0x0034, 0x0035, 0x0036, 0x0037,
    0x0038, 0x0039, 0x003a, 0x003b, 0x003c, 0x003d, 0x003e, 0x003f,
    0x0040, 0x0041, 0x0042, 0x0043, 0x0044, 0x0045, 0x0046, 0x0047,
    0x0048, 0x0049, 0x004a, 0x004b, 0x004c, 0x004d, 0x004e, 0x004f,
    0x0050, 0x0051, 0x0052, 0x0053, 0x0054, 0x0055, 0x0056, 0x0057,
    0x0058, 0x0059, 0x005a, 0x005b, 0x005c, 0x005d, 0x005e, 0x005f,
    0x0060, 0x0061, 0x0062, 0x0063, 0x0064, 0x0065, 0x0066, 0x0067,
    0x0068, 0x0069, 0x006a, 0x006b, 0x006c, 0x006d, 0x006e, 0x006f,
    0x0070, 0x0071, 0x0072, 0x0073, 0x0074, 0x0075, 0x0076, 0x0077,
    0x0078, 0x0079, 0x007a, 0x007b, 0x007c, 0x007d, 0x007e, 0x007f,
    0x0080, 0x0081, 0x0082, 0x0083, 0x0084, 0x0085, 0x0086, 0x0087,
    0x0088, 0x0089, 0x008a, 0x008b, 0x008c, 0x008d, 0x008e, 0x008f,
    0x0090, 0x0091, 0x0092, 0x0093, 0x0094, 0x0095, 0x0096, 0x0097,
    0x0098, 0x0099, 0x009a, 0x009b, 0x009c, 0x009d, 0x009e, 0x009f,
    0x00a0, 0x00a1, 0x00a2, 0x00a3, 0x00a4, 0x00a5, 0x00a6, 0x00a7,
    0x00a8, 0x00a9, 0x00aa, 0x00ab, 0x00ac, 0x00ad, 0x00ae, 0x00af,
    0x00b0, 0x00b1, 0x00b2, 0x00b3, 0x00b4, 0x00b5, 0x00b6, 0x00b7,
    0x00b8, 0x00b9, 0x00ba, 0x00bb, 0x00bc, 0x00bd, 0x00be, 0x00bf,
    0x00c0, 0x00c1, 0x00c2, 0x00c3, 0x00c4, 0x00c5, 0x00c6, 0x00c7,
    0x00c8, 0x00c9, 0x00ca, 0x00cb, 0x00cc, 0x00cd, 0x00ce, 0x00cf,
    0x00d0, 0x00d1, 0x00d2, 0x00d3, 0x00d4, 0x00d5, 0x00d6, 0x00d7,
    0x00d8, 0x00d9, 0x00da, 0x00db, 0x00dc, 0x00dd, 0x00de, 0x00df,
    0x00e0, 0x00e1, 0x00e2, 0x00e3, 0x00e4, 0x00e5, 0x00e6, 0x00e7,
    0x00e8, 0x00e9, 0x00ea, 0x00eb, 0x00ec, 0x00ed, 0x00ee, 0x00ef,
    0x00f0, 0x00f1, 0x00f2, 0x00f3, 0x00f4, 0x00f5, 0x00f6, 0x00f7,
    0x00f8, 0x00f9, 0x00fa, 0x00fb, 0x00fc, 0x00fd, 0x00fe, 0x00ff
  },
  /* VT100 graphics mapped to Unicode */
  [GRAF_MAP] = {
    0x0000, 0x0001, 0x0002, 0x0003, 0x0004, 0x0005, 0x0006, 0x0007,
    0x0008, 0x0009, 0x000a, 0x000b, 0x000c, 0x000d, 0x000e, 0x000f,
    0x0010, 0x0011, 0x0012, 0x0013, 0x0014, 0x0015, 0x0016, 0x0017,
    0x0018, 0x0019, 0x001a, 0x001b, 0x001c, 0x001d, 0x001e, 0x001f,
    0x0020, 0x0021, 0x0022, 0x0023, 0x0024, 0x0025, 0x0026, 0x0027,
    0x0028, 0x0029, 0x002a, 0x2192, 0x2190, 0x2191, 0x2193, 0x002f,
    0x2588, 0x0031, 0x0032, 0x0033, 0x0034, 0x0035, 0x0036, 0x0037,
    0x0038, 0x0039, 0x003a, 0x003b, 0x003c, 0x003d, 0x003e, 0x003f,
    0x0040, 0x0041, 0x0042, 0x0043, 0x0044, 0x0045, 0x0046, 0x0047,
    0x0048, 0x0049, 0x004a, 0x004b, 0x004c, 0x004d, 0x004e, 0x004f,
    0x0050, 0x0051, 0x0052, 0x0053, 0x0054, 0x0055, 0x0056, 0x0057,
    0x0058, 0x0059, 0x005a, 0x005b, 0x005c, 0x005d, 0x005e, 0x00a0,
    0x25c6, 0x2592, 0x2409, 0x240c, 0x240d, 0x240a, 0x00b0, 0x00b1,
    0x2591, 0x240b, 0x2518, 0x2510, 0x250c, 0x2514, 0x253c, 0x23ba,
    0x23bb, 0x2500, 0x23bc, 0x23bd, 0x251c, 0x2524, 0x2534, 0x252c,
    0x2502, 0x2264, 0x2265, 0x03c0, 0x2260, 0x00a3, 0x00b7, 0x007f,
    0x0080, 0x0081, 0x0082, 0x0083, 0x0084, 0x0085, 0x0086, 0x0087,
    0x0088, 0x0089, 0x008a, 0x008b, 0x008c, 0x008d, 0x008e, 0x008f,
    0x0090, 0x0091, 0x0092, 0x0093, 0x0094, 0x0095, 0x0096, 0x0097,
    0x0098, 0x0099, 0x009a, 0x009b, 0x009c, 0x009d, 0x009e, 0x009f,
    0x00a0, 0x00a1, 0x00a2, 0x00a3, 0x00a4, 0x00a5, 0x00a6, 0x00a7,
    0x00a8, 0x00a9, 0x00aa, 0x00ab, 0x00ac, 0x00ad, 0x00ae, 0x00af,
    0x00b0, 0x00b1, 0x00b2, 0x00b3, 0x00b4, 0x00b5, 0x00b6, 0x00b7,
    0x00b8, 0x00b9, 0x00ba, 0x00bb, 0x00bc, 0x00bd, 0x00be, 0x00bf,
    0x00c0, 0x00c1, 0x00c2, 0x00c3, 0x00c4, 0x00c5, 0x00c6, 0x00c7,
    0x00c8, 0x00c9, 0x00ca, 0x00cb, 0x00cc, 0x00cd, 0x00ce, 0x00cf,
    0x00d0, 0x00d1, 0x00d2, 0x00d3, 0x00d4, 0x00d5, 0x00d6, 0x00d7,
    0x00d8, 0x00d9, 0x00da, 0x00db, 0x00dc, 0x00dd, 0x00de, 0x00df,
    0x00e0, 0x00e1, 0x00e2, 0x00e3, 0x00e4, 0x00e5, 0x00e6, 0x00e7,
    0x00e8, 0x00e9, 0x00ea, 0x00eb, 0x00ec, 0x00ed, 0x00ee, 0x00ef,
    0x00f0, 0x00f1, 0x00f2, 0x00f3, 0x00f4, 0x00f5, 0x00f6, 0x00f7,
    0x00f8, 0x00f9, 0x00fa, 0x00fb, 0x00fc, 0x00fd, 0x00fe, 0x00ff
  },
  /* IBM Codepage 437 mapped to Unicode */
  [IBMPC_MAP] = {
    0x0000, 0x263a, 0x263b, 0x2665, 0x2666, 0x2663, 0x2660, 0x2022,
    0x25d8, 0x25cb, 0x25d9, 0x2642, 0x2640, 0x266a, 0x266b, 0x263c,
    0x25b6, 0x25c0, 0x2195, 0x203c, 0x00b6, 0x00a7, 0x25ac, 0x21a8,
    0x2191, 0x2193, 0x2192, 0x2190, 0x221f, 0x2194, 0x25b2, 0x25bc,
    0x0020, 0x0021, 0x0022, 0x0023, 0x0024, 0x0025, 0x0026, 0x0027,
    0x0028, 0x0029, 0x002a, 0x002b, 0x002c, 0x002d, 0x002e, 0x002f,
    0x0030, 0x0031, 0x0032, 0x0033, 0x0034, 0x0035, 0x0036, 0x0037,
    0x0038, 0x0039, 0x003a, 0x003b, 0x003c, 0x003d, 0x003e, 0x003f,
    0x0040, 0x0041, 0x0042, 0x0043, 0x0044, 0x0045, 0x0046, 0x0047,
    0x0048, 0x0049, 0x004a, 0x004b, 0x004c, 0x004d, 0x004e, 0x004f,
    0x0050, 0x0051, 0x0052, 0x0053, 0x0054, 0x0055, 0x0056, 0x0057,
    0x0058, 0x0059, 0x005a, 0x005b, 0x005c, 0x005d, 0x005e, 0x005f,
    0x0060, 0x0061, 0x0062, 0x0063, 0x0064, 0x0065, 0x0066, 0x0067,
    0x0068, 0x0069, 0x006a, 0x006b, 0x006c, 0x006d, 0x006e, 0x006f,
    0x0070, 0x0071, 0x0072, 0x0073, 0x0074, 0x0075, 0x0076, 0x0077,
    0x0078, 0x0079, 0x007a, 0x007b, 0x007c, 0x007d, 0x007e, 0x2302,
    0x00c7, 0x00fc, 0x00e9, 0x00e2, 0x00e4, 0x00e0, 0x00e5, 0x00e7,
    0x00ea, 0x00eb, 0x00e8, 0x00ef, 0x00ee, 0x00ec, 0x00c4, 0x00c5,
    0x00c9, 0x00e6, 0x00c6, 0x00f4, 0x00f6, 0x00f2, 0x00fb, 0x00f9,
    0x00ff, 0x00d6, 0x00dc, 0x00a2, 0x00a3, 0x00a5, 0x20a7, 0x0192,
    0x00e1, 0x00ed, 0x00f3, 0x00fa, 0x00f1, 0x00d1, 0x00aa, 0x00ba,
    0x00bf, 0x2310, 0x00ac, 0x00bd, 0x00bc, 0x00a1, 0x00ab, 0x00bb,
    0x2591, 0x2592, 0x2593, 0x2502, 0x2524, 0x2561, 0x2562, 0x2556,
    0x2555, 0x2563, 0x2551, 0x2557, 0x255d, 0x255c, 0x255b, 0x2510,
    0x2514, 0x2534, 0x252c, 0x251c, 0x2500, 0x253c, 0x255e, 0x255f,
    0x255a, 0x2554, 0x2569, 0x2566, 0x2560, 0x2550, 0x256c, 0x2567,
    0x2568, 0x2564, 0x2565, 0x2559, 0x2558, 0x2552, 0x2553, 0x256b,
    0x256a, 0x2518, 0x250c, 0x2588, 0x2584, 0x258c, 0x2590, 0x2580,
    0x03b1, 0x00df, 0x0393, 0x03c0, 0x03a3, 0x03c3, 0x00b5, 0x03c4,
    0x03a6, 0x0398, 0x03a9, 0x03b4, 0x221e, 0x03c6, 0x03b5, 0x2229,
    0x2261, 0x00b1, 0x2265, 0x2264, 0x2320, 0x2321, 0x00f7, 0x2248,
    0x00b0, 0x2219, 0x00b7, 0x221a, 0x207f, 0x00b2, 0x25a0, 0x00a0
  },
  /* User mapping -- default to codes for direct font mapping */
  [USER_MAP] = {
    0xf000, 0xf001, 0xf002, 0xf003, 0xf004, 0xf005, 0xf006, 0xf007,
    0xf008, 0xf009, 0xf00a, 0xf00b, 0xf00c, 0xf00d, 0xf00e, 0xf00f,
    0xf010, 0xf011, 0xf012, 0xf013, 0xf014, 0xf015, 0xf016, 0xf017,
    0xf018, 0xf019, 0xf01a, 0xf01b, 0xf01c, 0xf01d, 0xf01e, 0xf01f,
    0xf020, 0xf021, 0xf022, 0xf023, 0xf024, 0xf025, 0xf026, 0xf027,
    0xf028, 0xf029, 0xf02a, 0xf02b, 0xf02c, 0xf02d, 0xf02e, 0xf02f,
    0xf030, 0xf031, 0xf032, 0xf033, 0xf034, 0xf035, 0xf036, 0xf037,
    0xf038, 0xf039, 0xf03a, 0xf03b, 0xf03c, 0xf03d, 0xf03e, 0xf03f,
    0xf040, 0xf041, 0xf042, 0xf043, 0xf044, 0xf045, 0xf046, 0xf047,
    0xf048, 0xf049, 0xf04a, 0xf04b, 0xf04c, 0xf04d, 0xf04e, 0xf04f,
    0xf050, 0xf051, 0xf052, 0xf053, 0xf054, 0xf055, 0xf056, 0xf057,
    0xf058, 0xf059, 0xf05a, 0xf05b, 0xf05c, 0xf05d, 0xf05e, 0xf05f,
    0xf060, 0xf061, 0xf062, 0xf063, 0xf064, 0xf065, 0xf066, 0xf067,
    0xf068, 0xf069, 0xf06a, 0xf06b, 0xf06c, 0xf06d, 0xf06e, 0xf06f,
    0xf070, 0xf071, 0xf072, 0xf073, 0xf074, 0xf075, 0xf076, 0xf077,
    0xf078, 0xf079, 0xf07a, 0xf07b, 0xf07c, 0xf07d, 0xf07e, 0xf07f,
    0xf080, 0xf081, 0xf082, 0xf083, 0xf084, 0xf085, 0xf086, 0xf087,
    0xf088, 0xf089, 0xf08a, 0xf08b, 0xf08c, 0xf08d, 0xf08e, 0xf08f,
    0xf090, 0xf091, 0xf092, 0xf093, 0xf094, 0xf095, 0xf096, 0xf097,
    0xf098, 0xf099, 0xf09a, 0xf09b, 0xf09c, 0xf09d, 0xf09e, 0xf09f,
    0xf0a0, 0xf0a1, 0xf0a2, 0xf0a3, 0xf0a4, 0xf0a5, 0xf0a6, 0xf0a7,
    0xf0a8, 0xf0a9, 0xf0aa, 0xf0ab, 0xf0ac, 0xf0ad, 0xf0ae, 0xf0af,
    0xf0b0, 0xf0b1, 0xf0b2, 0xf0b3, 0xf0b4, 0xf0b5, 0xf0b6, 0xf0b7,
    0xf0b8, 0xf0b9, 0xf0ba, 0xf0bb, 0xf0bc, 0xf0bd, 0xf0be, 0xf0bf,
    0xf0c0, 0xf0c1, 0xf0c2, 0xf0c3, 0xf0c4, 0xf0c5, 0xf0c6, 0xf0c7,
    0xf0c8, 0xf0c9, 0xf0ca, 0xf0cb, 0xf0cc, 0xf0cd, 0xf0ce, 0xf0cf,
    0xf0d0, 0xf0d1, 0xf0d2, 0xf0d3, 0xf0d4, 0xf0d5, 0xf0d6, 0xf0d7,
    0xf0d8, 0xf0d9, 0xf0da, 0xf0db, 0xf0dc, 0xf0dd, 0xf0de, 0xf0df,
    0xf0e0, 0xf0e1, 0xf0e2, 0xf0e3, 0xf0e4, 0xf0e5, 0xf0e6, 0xf0e7,
    0xf0e8, 0xf0e9, 0xf0ea, 0xf0eb, 0xf0ec, 0xf0ed, 0xf0ee, 0xf0ef,
    0xf0f0, 0xf0f1, 0xf0f2, 0xf0f3, 0xf0f4, 0xf0f5, 0xf0f6, 0xf0f7,
    0xf0f8, 0xf0f9, 0xf0fa, 0xf0fb, 0xf0fc, 0xf0fd, 0xf0fe, 0xf0ff
  }
};

/* The standard kernel character-to-font mappings are not invertible
   -- this is just a best effort. */

#define MAX_GLYPH 512                /* Max possible glyph value */

static enum translation_map inv_translate[MAX_NR_CONSOLES];

#define UNI_DIRS        32U
#define UNI_DIR_ROWS        32U
#define UNI_ROW_GLYPHS        64U

#define UNI_DIR_BITS                GENMASK(15, 11)
#define UNI_ROW_BITS                GENMASK(10,  6)
#define UNI_GLYPH_BITS                GENMASK( 5,  0)

#define UNI_DIR(uni)                FIELD_GET(UNI_DIR_BITS, (uni))
#define UNI_ROW(uni)                FIELD_GET(UNI_ROW_BITS, (uni))
#define UNI_GLYPH(uni)                FIELD_GET(UNI_GLYPH_BITS, (uni))

#define UNI(dir, row, glyph)        (FIELD_PREP(UNI_DIR_BITS, (dir)) | \
                                 FIELD_PREP(UNI_ROW_BITS, (row)) | \
                                 FIELD_PREP(UNI_GLYPH_BITS, (glyph)))

/**
 * struct uni_pagedict - unicode directory
 *
 * @uni_pgdir: 32*32*64 table with glyphs
 * @refcount: reference count of this structure
 * @sum: checksum
 * @inverse_translations: best-effort inverse mapping
 * @inverse_trans_unicode: best-effort inverse mapping to unicode
 */
struct uni_pagedict {
        u16                **uni_pgdir[UNI_DIRS];
        unsigned long        refcount;
        unsigned long        sum;
        unsigned char        *inverse_translations[LAST_MAP + 1];
        u16                *inverse_trans_unicode;
};

static struct uni_pagedict *dflt;

static void set_inverse_transl(struct vc_data *conp, struct uni_pagedict *dict,
               enum translation_map m)
{
        unsigned short *t = translations[m];
        unsigned char *inv;

        if (!dict)
                return;
        inv = dict->inverse_translations[m];

        if (!inv) {
                inv = dict->inverse_translations[m] = kmalloc(MAX_GLYPH,
                                GFP_KERNEL);
                if (!inv)
                        return;
        }
        memset(inv, 0, MAX_GLYPH);

        for (unsigned int ch = 0; ch < ARRAY_SIZE(translations[m]); ch++) {
                int glyph = conv_uni_to_pc(conp, t[ch]);
                if (glyph >= 0 && glyph < MAX_GLYPH && inv[glyph] < 32) {
                        /* prefer '-' above SHY etc. */
                        inv[glyph] = ch;
                }
        }
}

static void set_inverse_trans_unicode(struct uni_pagedict *dict)
{
        unsigned int d, r, g;
        u16 *inv;

        if (!dict)
                return;

        inv = dict->inverse_trans_unicode;
        if (!inv) {
                inv = dict->inverse_trans_unicode = kmalloc_array(MAX_GLYPH,
                                sizeof(*inv), GFP_KERNEL);
                if (!inv)
                        return;
        }
        memset(inv, 0, MAX_GLYPH * sizeof(*inv));

        for (d = 0; d < UNI_DIRS; d++) {
                u16 **dir = dict->uni_pgdir[d];
                if (!dir)
                        continue;
                for (r = 0; r < UNI_DIR_ROWS; r++) {
                        u16 *row = dir[r];
                        if (!row)
                                continue;
                        for (g = 0; g < UNI_ROW_GLYPHS; g++) {
                                u16 glyph = row[g];
                                if (glyph < MAX_GLYPH && inv[glyph] < 32)
                                        inv[glyph] = UNI(d, r, g);
                        }
                }
        }
}

unsigned short *set_translate(enum translation_map m, struct vc_data *vc)
{
        inv_translate[vc->vc_num] = m;
        return translations[m];
}

/*
 * Inverse translation is impossible for several reasons:
 * 1. The font<->character maps are not 1-1.
 * 2. The text may have been written while a different translation map
 *    was active.
 * Still, it is now possible to a certain extent to cut and paste non-ASCII.
 */
u16 inverse_translate(const struct vc_data *conp, u16 glyph, bool use_unicode)
{
        struct uni_pagedict *p;
        enum translation_map m;

        if (glyph >= MAX_GLYPH)
                return 0;

        p = *conp->uni_pagedict_loc;
        if (!p)
                return glyph;

        if (use_unicode) {
                if (!p->inverse_trans_unicode)
                        return glyph;

                return p->inverse_trans_unicode[glyph];
        }

        m = inv_translate[conp->vc_num];
        if (!p->inverse_translations[m])
                return glyph;

        return p->inverse_translations[m][glyph];
}
EXPORT_SYMBOL_GPL(inverse_translate);

static void update_user_maps(void)
{
        int i;
        struct uni_pagedict *p, *q = NULL;

        for (i = 0; i < MAX_NR_CONSOLES; i++) {
                if (!vc_cons_allocated(i))
                        continue;
                p = *vc_cons[i].d->uni_pagedict_loc;
                if (p && p != q) {
                        set_inverse_transl(vc_cons[i].d, p, USER_MAP);
                        set_inverse_trans_unicode(p);
                        q = p;
                }
        }
}

/*
 * Load customizable translation table
 * arg points to a 256 byte translation table.
 *
 * The "old" variants are for translation directly to font (using the
 * 0xf000-0xf0ff "transparent" Unicodes) whereas the "new" variants set
 * Unicodes explicitly.
 */
int con_set_trans_old(unsigned char __user * arg)
{
        unsigned short inbuf[E_TABSZ];
        unsigned int i;
        unsigned char ch;

        for (i = 0; i < ARRAY_SIZE(inbuf); i++) {
                if (get_user(ch, &arg[i]))
                        return -EFAULT;
                inbuf[i] = UNI_DIRECT_BASE | ch;
        }

        console_lock();
        memcpy(translations[USER_MAP], inbuf, sizeof(inbuf));
        update_user_maps();
        console_unlock();
        return 0;
}

int con_get_trans_old(unsigned char __user * arg)
{
        int i, ch;
        unsigned short *p = translations[USER_MAP];
        unsigned char outbuf[E_TABSZ];

        console_lock();
        for (i = 0; i < ARRAY_SIZE(outbuf); i++)
        {
                ch = conv_uni_to_pc(vc_cons[fg_console].d, p[i]);
                outbuf[i] = (ch & ~0xff) ? 0 : ch;
        }
        console_unlock();

        return copy_to_user(arg, outbuf, sizeof(outbuf)) ? -EFAULT : 0;
}

int con_set_trans_new(ushort __user * arg)
{
        unsigned short inbuf[E_TABSZ];

        if (copy_from_user(inbuf, arg, sizeof(inbuf)))
                return -EFAULT;

        console_lock();
        memcpy(translations[USER_MAP], inbuf, sizeof(inbuf));
        update_user_maps();
        console_unlock();
        return 0;
}

int con_get_trans_new(ushort __user * arg)
{
        unsigned short outbuf[E_TABSZ];

        console_lock();
        memcpy(outbuf, translations[USER_MAP], sizeof(outbuf));
        console_unlock();

        return copy_to_user(arg, outbuf, sizeof(outbuf)) ? -EFAULT : 0;
}

/*
 * Unicode -> current font conversion
 *
 * A font has at most 512 chars, usually 256.
 * But one font position may represent several Unicode chars.
 * A hashtable is somewhat of a pain to deal with, so use a
 * "paged table" instead.  Simulation has shown the memory cost of
 * this 3-level paged table scheme to be comparable to a hash table.
 */

extern u8 dfont_unicount[];        /* Defined in console_defmap.c */
extern u16 dfont_unitable[];

static void con_release_unimap(struct uni_pagedict *dict)
{
        unsigned int d, r;

        if (dict == dflt)
                dflt = NULL;

        for (d = 0; d < UNI_DIRS; d++) {
                u16 **dir = dict->uni_pgdir[d];
                if (dir != NULL) {
                        for (r = 0; r < UNI_DIR_ROWS; r++)
                                kfree(dir[r]);
                        kfree(dir);
                }
                dict->uni_pgdir[d] = NULL;
        }

        for (r = 0; r < ARRAY_SIZE(dict->inverse_translations); r++) {
                kfree(dict->inverse_translations[r]);
                dict->inverse_translations[r] = NULL;
        }

        kfree(dict->inverse_trans_unicode);
        dict->inverse_trans_unicode = NULL;
}

/* Caller must hold the console lock */
void con_free_unimap(struct vc_data *vc)
{
        struct uni_pagedict *p;

        p = *vc->uni_pagedict_loc;
        if (!p)
                return;
        *vc->uni_pagedict_loc = NULL;
        if (--p->refcount)
                return;
        con_release_unimap(p);
        kfree(p);
}

static int con_unify_unimap(struct vc_data *conp, struct uni_pagedict *dict1)
{
        struct uni_pagedict *dict2;
        unsigned int cons, d, r;

        for (cons = 0; cons < MAX_NR_CONSOLES; cons++) {
                if (!vc_cons_allocated(cons))
                        continue;
                dict2 = *vc_cons[cons].d->uni_pagedict_loc;
                if (!dict2 || dict2 == dict1 || dict2->sum != dict1->sum)
                        continue;
                for (d = 0; d < UNI_DIRS; d++) {
                        u16 **dir1 = dict1->uni_pgdir[d];
                        u16 **dir2 = dict2->uni_pgdir[d];
                        if (!dir1 && !dir2)
                                continue;
                        if (!dir1 || !dir2)
                                break;
                        for (r = 0; r < UNI_DIR_ROWS; r++) {
                                if (!dir1[r] && !dir2[r])
                                        continue;
                                if (!dir1[r] || !dir2[r])
                                        break;
                                if (memcmp(dir1[r], dir2[r], UNI_ROW_GLYPHS *
                                                        sizeof(*dir1[r])))
                                        break;
                        }
                        if (r < UNI_DIR_ROWS)
                                break;
                }
                if (d == UNI_DIRS) {
                        dict2->refcount++;
                        *conp->uni_pagedict_loc = dict2;
                        con_release_unimap(dict1);
                        kfree(dict1);
                        return 1;
                }
        }
        return 0;
}

static int
con_insert_unipair(struct uni_pagedict *p, u_short unicode, u_short fontpos)
{
        u16 **dir, *row;
        unsigned int n;

        n = UNI_DIR(unicode);
        dir = p->uni_pgdir[n];
        if (!dir) {
                dir = p->uni_pgdir[n] = kcalloc(UNI_DIR_ROWS, sizeof(*dir),
                                GFP_KERNEL);
                if (!dir)
                        return -ENOMEM;
        }

        n = UNI_ROW(unicode);
        row = dir[n];
        if (!row) {
                row = dir[n] = kmalloc_array(UNI_ROW_GLYPHS, sizeof(*row),
                                GFP_KERNEL);
                if (!row)
                        return -ENOMEM;
                /* No glyphs for the characters (yet) */
                memset(row, 0xff, UNI_ROW_GLYPHS * sizeof(*row));
        }

        row[UNI_GLYPH(unicode)] = fontpos;

        p->sum += (fontpos << 20U) + unicode;

        return 0;
}

static int con_allocate_new(struct vc_data *vc)
{
        struct uni_pagedict *new, *old = *vc->uni_pagedict_loc;

        new = kzalloc(sizeof(*new), GFP_KERNEL);
        if (!new)
                return -ENOMEM;

        new->refcount = 1;
        *vc->uni_pagedict_loc = new;

        if (old)
                old->refcount--;

        return 0;
}

/* Caller must hold the lock */
static int con_do_clear_unimap(struct vc_data *vc)
{
        struct uni_pagedict *old = *vc->uni_pagedict_loc;

        if (!old || old->refcount > 1)
                return con_allocate_new(vc);

        old->sum = 0;
        con_release_unimap(old);

        return 0;
}

int con_clear_unimap(struct vc_data *vc)
{
        int ret;
        console_lock();
        ret = con_do_clear_unimap(vc);
        console_unlock();
        return ret;
}

static struct uni_pagedict *con_unshare_unimap(struct vc_data *vc,
                struct uni_pagedict *old)
{
        struct uni_pagedict *new;
        unsigned int d, r, g;
        int ret;
        u16 uni = 0;

        ret = con_allocate_new(vc);
        if (ret)
                return ERR_PTR(ret);

        new = *vc->uni_pagedict_loc;

        /*
         * uni_pgdir is a 32*32*64 table with rows allocated when its first
         * entry is added. The unicode value must still be incremented for
         * empty rows. We are copying entries from "old" to "new".
         */
        for (d = 0; d < UNI_DIRS; d++) {
                u16 **dir = old->uni_pgdir[d];
                if (!dir) {
                        /* Account for empty table */
                        uni += UNI_DIR_ROWS * UNI_ROW_GLYPHS;
                        continue;
                }

                for (r = 0; r < UNI_DIR_ROWS; r++) {
                        u16 *row = dir[r];
                        if (!row) {
                                /* Account for row of 64 empty entries */
                                uni += UNI_ROW_GLYPHS;
                                continue;
                        }

                        for (g = 0; g < UNI_ROW_GLYPHS; g++, uni++) {
                                if (row[g] == 0xffff)
                                        continue;
                                /*
                                 * Found one, copy entry for unicode uni with
                                 * fontpos value row[g].
                                 */
                                ret = con_insert_unipair(new, uni, row[g]);
                                if (ret) {
                                        old->refcount++;
                                        *vc->uni_pagedict_loc = old;
                                        con_release_unimap(new);
                                        kfree(new);
                                        return ERR_PTR(ret);
                                }
                        }
                }
        }

        return new;
}

int con_set_unimap(struct vc_data *vc, ushort ct, struct unipair __user *list)
{
        int err = 0, err1;
        struct uni_pagedict *dict;
        struct unipair *unilist, *plist;

        if (!ct)
                return 0;

        unilist = vmemdup_array_user(list, ct, sizeof(*unilist));
        if (IS_ERR(unilist))
                return PTR_ERR(unilist);

        console_lock();

        /* Save original vc_unipagdir_loc in case we allocate a new one */
        dict = *vc->uni_pagedict_loc;
        if (!dict) {
                err = -EINVAL;
                goto out_unlock;
        }

        if (dict->refcount > 1) {
                dict = con_unshare_unimap(vc, dict);
                if (IS_ERR(dict)) {
                        err = PTR_ERR(dict);
                        goto out_unlock;
                }
        } else if (dict == dflt) {
                dflt = NULL;
        }

        /*
         * Insert user specified unicode pairs into new table.
         */
        for (plist = unilist; ct; ct--, plist++) {
                err1 = con_insert_unipair(dict, plist->unicode, plist->fontpos);
                if (err1)
                        err = err1;
        }

        /*
         * Merge with fontmaps of any other virtual consoles.
         */
        if (con_unify_unimap(vc, dict))
                goto out_unlock;

        for (enum translation_map m = FIRST_MAP; m <= LAST_MAP; m++)
                set_inverse_transl(vc, dict, m);
        set_inverse_trans_unicode(dict);

out_unlock:
        console_unlock();
        kvfree(unilist);
        return err;
}

/**
 *        con_set_default_unimap        -        set default unicode map
 *        @vc: the console we are updating
 *
 *        Loads the unimap for the hardware font, as defined in uni_hash.tbl.
 *        The representation used was the most compact I could come up
 *        with.  This routine is executed at video setup, and when the
 *        PIO_FONTRESET ioctl is called.
 *
 *        The caller must hold the console lock
 */
int con_set_default_unimap(struct vc_data *vc)
{
        struct uni_pagedict *dict;
        unsigned int fontpos, count;
        int err = 0, err1;
        u16 *dfont;

        if (dflt) {
                dict = *vc->uni_pagedict_loc;
                if (dict == dflt)
                        return 0;

                dflt->refcount++;
                *vc->uni_pagedict_loc = dflt;
                if (dict && !--dict->refcount) {
                        con_release_unimap(dict);
                        kfree(dict);
                }
                return 0;
        }

        /* The default font is always 256 characters */

        err = con_do_clear_unimap(vc);
        if (err)
                return err;

        dict = *vc->uni_pagedict_loc;
        dfont = dfont_unitable;

        for (fontpos = 0; fontpos < 256U; fontpos++)
                for (count = dfont_unicount[fontpos]; count; count--) {
                        err1 = con_insert_unipair(dict, *(dfont++), fontpos);
                        if (err1)
                                err = err1;
                }

        if (con_unify_unimap(vc, dict)) {
                dflt = *vc->uni_pagedict_loc;
                return err;
        }

        for (enum translation_map m = FIRST_MAP; m <= LAST_MAP; m++)
                set_inverse_transl(vc, dict, m);
        set_inverse_trans_unicode(dict);
        dflt = dict;
        return err;
}
EXPORT_SYMBOL(con_set_default_unimap);

/**
 *        con_copy_unimap                -        copy unimap between two vts
 *        @dst_vc: target
 *        @src_vc: source
 *
 *        The caller must hold the console lock when invoking this method
 */
int con_copy_unimap(struct vc_data *dst_vc, struct vc_data *src_vc)
{
        struct uni_pagedict *src;

        if (!*src_vc->uni_pagedict_loc)
                return -EINVAL;
        if (*dst_vc->uni_pagedict_loc == *src_vc->uni_pagedict_loc)
                return 0;
        con_free_unimap(dst_vc);
        src = *src_vc->uni_pagedict_loc;
        src->refcount++;
        *dst_vc->uni_pagedict_loc = src;
        return 0;
}
EXPORT_SYMBOL(con_copy_unimap);

/*
 *        con_get_unimap                -        get the unicode map
 *
 *        Read the console unicode data for this console. Called from the ioctl
 *        handlers.
 */
int con_get_unimap(struct vc_data *vc, ushort ct, ushort __user *uct,
                struct unipair __user *list)
{
        ushort ect;
        struct uni_pagedict *dict;
        struct unipair *unilist;
        unsigned int d, r, g;
        int ret = 0;

        unilist = kvmalloc_array(ct, sizeof(*unilist), GFP_KERNEL);
        if (!unilist)
                return -ENOMEM;

        console_lock();

        ect = 0;
        dict = *vc->uni_pagedict_loc;
        if (!dict)
                goto unlock;

        for (d = 0; d < UNI_DIRS; d++) {
                u16 **dir = dict->uni_pgdir[d];
                if (!dir)
                        continue;

                for (r = 0; r < UNI_DIR_ROWS; r++) {
                        u16 *row = dir[r];
                        if (!row)
                                continue;

                        for (g = 0; g < UNI_ROW_GLYPHS; g++, row++) {
                                if (*row >= MAX_GLYPH)
                                        continue;
                                if (ect < ct) {
                                        unilist[ect].unicode = UNI(d, r, g);
                                        unilist[ect].fontpos = *row;
                                }
                                ect++;
                        }
                }
        }
unlock:
        console_unlock();
        if (copy_to_user(list, unilist, min(ect, ct) * sizeof(*unilist)))
                ret = -EFAULT;
        if (put_user(ect, uct))
                ret = -EFAULT;
        kvfree(unilist);
        return ret ? ret : (ect <= ct) ? 0 : -ENOMEM;
}

/*
 * Always use USER_MAP. These functions are used by the keyboard,
 * which shouldn't be affected by G0/G1 switching, etc.
 * If the user map still contains default values, i.e. the
 * direct-to-font mapping, then assume user is using Latin1.
 *
 * FIXME: at some point we need to decide if we want to lock the table
 * update element itself via the keyboard_event_lock for consistency with the
 * keyboard driver as well as the consoles
 */
/* may be called during an interrupt */
u32 conv_8bit_to_uni(unsigned char c)
{
        unsigned short uni = translations[USER_MAP][c];
        return uni == (0xf000 | c) ? c : uni;
}

int conv_uni_to_8bit(u32 uni)
{
        int c;
        for (c = 0; c < ARRAY_SIZE(translations[USER_MAP]); c++)
                if (translations[USER_MAP][c] == uni ||
                   (translations[USER_MAP][c] == (c | 0xf000) && uni == c))
                        return c;
        return -1;
}

int conv_uni_to_pc(struct vc_data *conp, long ucs)
{
        struct uni_pagedict *dict;
        u16 **dir, *row, glyph;

        /* Only 16-bit codes supported at this time */
        if (ucs > 0xffff)
                return -4;                /* Not found */
        else if (ucs < 0x20)
                return -1;                /* Not a printable character */
        else if (ucs == 0xfeff || (ucs >= 0x200b && ucs <= 0x200f))
                return -2;                        /* Zero-width space */
        /*
         * UNI_DIRECT_BASE indicates the start of the region in the User Zone
         * which always has a 1:1 mapping to the currently loaded font.  The
         * UNI_DIRECT_MASK indicates the bit span of the region.
         */
        else if ((ucs & ~UNI_DIRECT_MASK) == UNI_DIRECT_BASE)
                return ucs & UNI_DIRECT_MASK;

        dict = *conp->uni_pagedict_loc;
        if (!dict)
                return -3;

        dir = dict->uni_pgdir[UNI_DIR(ucs)];
        if (!dir)
                return -4;

        row = dir[UNI_ROW(ucs)];
        if (!row)
                return -4;

        glyph = row[UNI_GLYPH(ucs)];
        if (glyph >= MAX_GLYPH)
                return -4;

        return glyph;
}

/*
 * This is called at sys_setup time, after memory and the console are
 * initialized.  It must be possible to call kmalloc(..., GFP_KERNEL)
 * from this function, hence the call from sys_setup.
 */
void __init
console_map_init(void)
{
        int i;

        for (i = 0; i < MAX_NR_CONSOLES; i++)
                if (vc_cons_allocated(i) && !*vc_cons[i].d->uni_pagedict_loc)
                        con_set_default_unimap(vc_cons[i].d);
}































  231 























  302 





  303 























  132 
  132 



  131 
















  131 









  132 














  245 














  112 


  245 




































































  256 

  257 




  257 














  243 


  112 















  256 

  257 



  256 



  140 
  183 













  257 
























  257 

















  256 




  258 
    2 








  260 









  303 






  302 


  255 
















    5 





























    5 













    5 




























    5 
    5 
































    5 




    5 













    2 






    5 



    5 








  223 







  223 

  144 

  173 
  172 

















  223 



  223 


  223 






  132 








  132 






























































































    2 

















   28 












   28 






















   28 










   28 








  131 



  131 



















  131 









































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
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
// SPDX-License-Identifier: GPL-2.0

#include "bcachefs.h"
#include "btree_cache.h"
#include "btree_iter.h"
#include "btree_key_cache.h"
#include "btree_locking.h"
#include "btree_update.h"
#include "errcode.h"
#include "error.h"
#include "journal.h"
#include "journal_reclaim.h"
#include "trace.h"

#include <linux/sched/mm.h>

static inline bool btree_uses_pcpu_readers(enum btree_id id)
{
        return id == BTREE_ID_subvolumes;
}

static struct kmem_cache *bch2_key_cache;

static int bch2_btree_key_cache_cmp_fn(struct rhashtable_compare_arg *arg,
                                       const void *obj)
{
        const struct bkey_cached *ck = obj;
        const struct bkey_cached_key *key = arg->key;

        return ck->key.btree_id != key->btree_id ||
                !bpos_eq(ck->key.pos, key->pos);
}

static const struct rhashtable_params bch2_btree_key_cache_params = {
        .head_offset                = offsetof(struct bkey_cached, hash),
        .key_offset                = offsetof(struct bkey_cached, key),
        .key_len                = sizeof(struct bkey_cached_key),
        .obj_cmpfn                = bch2_btree_key_cache_cmp_fn,
        .automatic_shrinking        = true,
};

static inline void btree_path_cached_set(struct btree_trans *trans, struct btree_path *path,
                                         struct bkey_cached *ck,
                                         enum btree_node_locked_type lock_held)
{
        path->l[0].lock_seq        = six_lock_seq(&ck->c.lock);
        path->l[0].b                = (void *) ck;
        mark_btree_node_locked(trans, path, 0, lock_held);
}

__flatten
inline struct bkey_cached *
bch2_btree_key_cache_find(struct bch_fs *c, enum btree_id btree_id, struct bpos pos)
{
        struct bkey_cached_key key = {
                .btree_id        = btree_id,
                .pos                = pos,
        };

        return rhashtable_lookup_fast(&c->btree_key_cache.table, &key,
                                      bch2_btree_key_cache_params);
}

static bool bkey_cached_lock_for_evict(struct bkey_cached *ck)
{
        if (!six_trylock_intent(&ck->c.lock))
                return false;

        if (test_bit(BKEY_CACHED_DIRTY, &ck->flags)) {
                six_unlock_intent(&ck->c.lock);
                return false;
        }

        if (!six_trylock_write(&ck->c.lock)) {
                six_unlock_intent(&ck->c.lock);
                return false;
        }

        return true;
}

static bool bkey_cached_evict(struct btree_key_cache *c,
                              struct bkey_cached *ck)
{
        bool ret = !rhashtable_remove_fast(&c->table, &ck->hash,
                                      bch2_btree_key_cache_params);
        if (ret) {
                memset(&ck->key, ~0, sizeof(ck->key));
                atomic_long_dec(&c->nr_keys);
        }

        return ret;
}

static void __bkey_cached_free(struct rcu_pending *pending, struct rcu_head *rcu)
{
        struct bch_fs *c = container_of(pending->srcu, struct bch_fs, btree_trans_barrier);
        struct bkey_cached *ck = container_of(rcu, struct bkey_cached, rcu);

        this_cpu_dec(*c->btree_key_cache.nr_pending);
        kmem_cache_free(bch2_key_cache, ck);
}

static void bkey_cached_free(struct btree_key_cache *bc,
                             struct bkey_cached *ck)
{
        kfree(ck->k);
        ck->k                = NULL;
        ck->u64s        = 0;

        six_unlock_write(&ck->c.lock);
        six_unlock_intent(&ck->c.lock);

        bool pcpu_readers = ck->c.lock.readers != NULL;
        rcu_pending_enqueue(&bc->pending[pcpu_readers], &ck->rcu);
        this_cpu_inc(*bc->nr_pending);
}

static struct bkey_cached *__bkey_cached_alloc(unsigned key_u64s, gfp_t gfp)
{
        gfp |= __GFP_ACCOUNT|__GFP_RECLAIMABLE;

        struct bkey_cached *ck = kmem_cache_zalloc(bch2_key_cache, gfp);
        if (unlikely(!ck))
                return NULL;
        ck->k = kmalloc(key_u64s * sizeof(u64), gfp);
        if (unlikely(!ck->k)) {
                kmem_cache_free(bch2_key_cache, ck);
                return NULL;
        }
        ck->u64s = key_u64s;
        return ck;
}

static struct bkey_cached *
bkey_cached_alloc(struct btree_trans *trans, struct btree_path *path, unsigned key_u64s)
{
        struct bch_fs *c = trans->c;
        struct btree_key_cache *bc = &c->btree_key_cache;
        bool pcpu_readers = btree_uses_pcpu_readers(path->btree_id);
        int ret;

        struct bkey_cached *ck = container_of_or_null(
                                rcu_pending_dequeue(&bc->pending[pcpu_readers]),
                                struct bkey_cached, rcu);
        if (ck)
                goto lock;

        ck = allocate_dropping_locks(trans, ret,
                                     __bkey_cached_alloc(key_u64s, _gfp));
        if (ret) {
                if (ck)
                        kfree(ck->k);
                kmem_cache_free(bch2_key_cache, ck);
                return ERR_PTR(ret);
        }

        if (ck) {
                bch2_btree_lock_init(&ck->c, pcpu_readers ? SIX_LOCK_INIT_PCPU : 0);
                ck->c.cached = true;
                goto lock;
        }

        ck = container_of_or_null(rcu_pending_dequeue_from_all(&bc->pending[pcpu_readers]),
                                  struct bkey_cached, rcu);
        if (ck)
                goto lock;
lock:
        six_lock_intent(&ck->c.lock, NULL, NULL);
        six_lock_write(&ck->c.lock, NULL, NULL);
        return ck;
}

static struct bkey_cached *
bkey_cached_reuse(struct btree_key_cache *c)
{
        struct bucket_table *tbl;
        struct rhash_head *pos;
        struct bkey_cached *ck;
        unsigned i;

        rcu_read_lock();
        tbl = rht_dereference_rcu(c->table.tbl, &c->table);
        for (i = 0; i < tbl->size; i++)
                rht_for_each_entry_rcu(ck, pos, tbl, i, hash) {
                        if (!test_bit(BKEY_CACHED_DIRTY, &ck->flags) &&
                            bkey_cached_lock_for_evict(ck)) {
                                if (bkey_cached_evict(c, ck))
                                        goto out;
                                six_unlock_write(&ck->c.lock);
                                six_unlock_intent(&ck->c.lock);
                        }
                }
        ck = NULL;
out:
        rcu_read_unlock();
        return ck;
}

static int btree_key_cache_create(struct btree_trans *trans, struct btree_path *path,
                                  struct bkey_s_c k)
{
        struct bch_fs *c = trans->c;
        struct btree_key_cache *bc = &c->btree_key_cache;

        /*
         * bch2_varint_decode can read past the end of the buffer by at
         * most 7 bytes (it won't be used):
         */
        unsigned key_u64s = k.k->u64s + 1;

        /*
         * Allocate some extra space so that the transaction commit path is less
         * likely to have to reallocate, since that requires a transaction
         * restart:
         */
        key_u64s = min(256U, (key_u64s * 3) / 2);
        key_u64s = roundup_pow_of_two(key_u64s);

        struct bkey_cached *ck = bkey_cached_alloc(trans, path, key_u64s);
        int ret = PTR_ERR_OR_ZERO(ck);
        if (ret)
                return ret;

        if (unlikely(!ck)) {
                ck = bkey_cached_reuse(bc);
                if (unlikely(!ck)) {
                        bch_err(c, "error allocating memory for key cache item, btree %s",
                                bch2_btree_id_str(path->btree_id));
                        return -BCH_ERR_ENOMEM_btree_key_cache_create;
                }
        }

        ck->c.level                = 0;
        ck->c.btree_id                = path->btree_id;
        ck->key.btree_id        = path->btree_id;
        ck->key.pos                = path->pos;
        ck->flags                = 1U << BKEY_CACHED_ACCESSED;

        if (unlikely(key_u64s > ck->u64s)) {
                mark_btree_node_locked_noreset(path, 0, BTREE_NODE_UNLOCKED);

                struct bkey_i *new_k = allocate_dropping_locks(trans, ret,
                                kmalloc(key_u64s * sizeof(u64), _gfp));
                if (unlikely(!new_k)) {
                        bch_err(trans->c, "error allocating memory for key cache key, btree %s u64s %u",
                                bch2_btree_id_str(ck->key.btree_id), key_u64s);
                        ret = -BCH_ERR_ENOMEM_btree_key_cache_fill;
                } else if (ret) {
                        kfree(new_k);
                        goto err;
                }

                kfree(ck->k);
                ck->k = new_k;
                ck->u64s = key_u64s;
        }

        bkey_reassemble(ck->k, k);

        ret = rhashtable_lookup_insert_fast(&bc->table, &ck->hash, bch2_btree_key_cache_params);
        if (unlikely(ret)) /* raced with another fill? */
                goto err;

        atomic_long_inc(&bc->nr_keys);
        six_unlock_write(&ck->c.lock);

        enum six_lock_type lock_want = __btree_lock_want(path, 0);
        if (lock_want == SIX_LOCK_read)
                six_lock_downgrade(&ck->c.lock);
        btree_path_cached_set(trans, path, ck, (enum btree_node_locked_type) lock_want);
        path->uptodate = BTREE_ITER_UPTODATE;
        return 0;
err:
        bkey_cached_free(bc, ck);
        mark_btree_node_locked_noreset(path, 0, BTREE_NODE_UNLOCKED);

        return ret;
}

static noinline int btree_key_cache_fill(struct btree_trans *trans,
                                         struct btree_path *ck_path,
                                         unsigned flags)
{
        if (flags & BTREE_ITER_cached_nofill) {
                ck_path->uptodate = BTREE_ITER_UPTODATE;
                return 0;
        }

        struct bch_fs *c = trans->c;
        struct btree_iter iter;
        struct bkey_s_c k;
        int ret;

        bch2_trans_iter_init(trans, &iter, ck_path->btree_id, ck_path->pos,
                             BTREE_ITER_key_cache_fill|
                             BTREE_ITER_cached_nofill);
        iter.flags &= ~BTREE_ITER_with_journal;
        k = bch2_btree_iter_peek_slot(&iter);
        ret = bkey_err(k);
        if (ret)
                goto err;

        /* Recheck after btree lookup, before allocating: */
        ret = bch2_btree_key_cache_find(c, ck_path->btree_id, ck_path->pos) ? -EEXIST : 0;
        if (unlikely(ret))
                goto out;

        ret = btree_key_cache_create(trans, ck_path, k);
        if (ret)
                goto err;
out:
        /* We're not likely to need this iterator again: */
        bch2_set_btree_iter_dontneed(&iter);
err:
        bch2_trans_iter_exit(trans, &iter);
        return ret;
}

static inline int btree_path_traverse_cached_fast(struct btree_trans *trans,
                                                  struct btree_path *path)
{
        struct bch_fs *c = trans->c;
        struct bkey_cached *ck;
retry:
        ck = bch2_btree_key_cache_find(c, path->btree_id, path->pos);
        if (!ck)
                return -ENOENT;

        enum six_lock_type lock_want = __btree_lock_want(path, 0);

        int ret = btree_node_lock(trans, path, (void *) ck, 0, lock_want, _THIS_IP_);
        if (ret)
                return ret;

        if (ck->key.btree_id != path->btree_id ||
            !bpos_eq(ck->key.pos, path->pos)) {
                six_unlock_type(&ck->c.lock, lock_want);
                goto retry;
        }

        if (!test_bit(BKEY_CACHED_ACCESSED, &ck->flags))
                set_bit(BKEY_CACHED_ACCESSED, &ck->flags);

        btree_path_cached_set(trans, path, ck, (enum btree_node_locked_type) lock_want);
        path->uptodate = BTREE_ITER_UPTODATE;
        return 0;
}

int bch2_btree_path_traverse_cached(struct btree_trans *trans, struct btree_path *path,
                                    unsigned flags)
{
        EBUG_ON(path->level);

        path->l[1].b = NULL;

        int ret;
        do {
                ret = btree_path_traverse_cached_fast(trans, path);
                if (unlikely(ret == -ENOENT))
                        ret = btree_key_cache_fill(trans, path, flags);
        } while (ret == -EEXIST);

        if (unlikely(ret)) {
                path->uptodate = BTREE_ITER_NEED_TRAVERSE;
                if (!bch2_err_matches(ret, BCH_ERR_transaction_restart)) {
                        btree_node_unlock(trans, path, 0);
                        path->l[0].b = ERR_PTR(ret);
                }
        }
        return ret;
}

static int btree_key_cache_flush_pos(struct btree_trans *trans,
                                     struct bkey_cached_key key,
                                     u64 journal_seq,
                                     unsigned commit_flags,
                                     bool evict)
{
        struct bch_fs *c = trans->c;
        struct journal *j = &c->journal;
        struct btree_iter c_iter, b_iter;
        struct bkey_cached *ck = NULL;
        int ret;

        bch2_trans_iter_init(trans, &b_iter, key.btree_id, key.pos,
                             BTREE_ITER_slots|
                             BTREE_ITER_intent|
                             BTREE_ITER_all_snapshots);
        bch2_trans_iter_init(trans, &c_iter, key.btree_id, key.pos,
                             BTREE_ITER_cached|
                             BTREE_ITER_intent);
        b_iter.flags &= ~BTREE_ITER_with_key_cache;

        ret = bch2_btree_iter_traverse(&c_iter);
        if (ret)
                goto out;

        ck = (void *) btree_iter_path(trans, &c_iter)->l[0].b;
        if (!ck)
                goto out;

        if (!test_bit(BKEY_CACHED_DIRTY, &ck->flags)) {
                if (evict)
                        goto evict;
                goto out;
        }

        if (journal_seq && ck->journal.seq != journal_seq)
                goto out;

        trans->journal_res.seq = ck->journal.seq;

        /*
         * If we're at the end of the journal, we really want to free up space
         * in the journal right away - we don't want to pin that old journal
         * sequence number with a new btree node write, we want to re-journal
         * the update
         */
        if (ck->journal.seq == journal_last_seq(j))
                commit_flags |= BCH_WATERMARK_reclaim;

        if (ck->journal.seq != journal_last_seq(j) ||
            !test_bit(JOURNAL_space_low, &c->journal.flags))
                commit_flags |= BCH_TRANS_COMMIT_no_journal_res;

        ret   = bch2_btree_iter_traverse(&b_iter) ?:
                bch2_trans_update(trans, &b_iter, ck->k,
                                  BTREE_UPDATE_key_cache_reclaim|
                                  BTREE_UPDATE_internal_snapshot_node|
                                  BTREE_TRIGGER_norun) ?:
                bch2_trans_commit(trans, NULL, NULL,
                                  BCH_TRANS_COMMIT_no_check_rw|
                                  BCH_TRANS_COMMIT_no_enospc|
                                  commit_flags);

        bch2_fs_fatal_err_on(ret &&
                             !bch2_err_matches(ret, BCH_ERR_transaction_restart) &&
                             !bch2_err_matches(ret, BCH_ERR_journal_reclaim_would_deadlock) &&
                             !bch2_journal_error(j), c,
                             "flushing key cache: %s", bch2_err_str(ret));
        if (ret)
                goto out;

        bch2_journal_pin_drop(j, &ck->journal);

        struct btree_path *path = btree_iter_path(trans, &c_iter);
        BUG_ON(!btree_node_locked(path, 0));

        if (!evict) {
                if (test_bit(BKEY_CACHED_DIRTY, &ck->flags)) {
                        clear_bit(BKEY_CACHED_DIRTY, &ck->flags);
                        atomic_long_dec(&c->btree_key_cache.nr_dirty);
                }
        } else {
                struct btree_path *path2;
                unsigned i;
evict:
                trans_for_each_path(trans, path2, i)
                        if (path2 != path)
                                __bch2_btree_path_unlock(trans, path2);

                bch2_btree_node_lock_write_nofail(trans, path, &ck->c);

                if (test_bit(BKEY_CACHED_DIRTY, &ck->flags)) {
                        clear_bit(BKEY_CACHED_DIRTY, &ck->flags);
                        atomic_long_dec(&c->btree_key_cache.nr_dirty);
                }

                mark_btree_node_locked_noreset(path, 0, BTREE_NODE_UNLOCKED);
                if (bkey_cached_evict(&c->btree_key_cache, ck)) {
                        bkey_cached_free(&c->btree_key_cache, ck);
                } else {
                        six_unlock_write(&ck->c.lock);
                        six_unlock_intent(&ck->c.lock);
                }
        }
out:
        bch2_trans_iter_exit(trans, &b_iter);
        bch2_trans_iter_exit(trans, &c_iter);
        return ret;
}

int bch2_btree_key_cache_journal_flush(struct journal *j,
                                struct journal_entry_pin *pin, u64 seq)
{
        struct bch_fs *c = container_of(j, struct bch_fs, journal);
        struct bkey_cached *ck =
                container_of(pin, struct bkey_cached, journal);
        struct bkey_cached_key key;
        struct btree_trans *trans = bch2_trans_get(c);
        int srcu_idx = srcu_read_lock(&c->btree_trans_barrier);
        int ret = 0;

        btree_node_lock_nopath_nofail(trans, &ck->c, SIX_LOCK_read);
        key = ck->key;

        if (ck->journal.seq != seq ||
            !test_bit(BKEY_CACHED_DIRTY, &ck->flags)) {
                six_unlock_read(&ck->c.lock);
                goto unlock;
        }

        if (ck->seq != seq) {
                bch2_journal_pin_update(&c->journal, ck->seq, &ck->journal,
                                        bch2_btree_key_cache_journal_flush);
                six_unlock_read(&ck->c.lock);
                goto unlock;
        }
        six_unlock_read(&ck->c.lock);

        ret = lockrestart_do(trans,
                btree_key_cache_flush_pos(trans, key, seq,
                                BCH_TRANS_COMMIT_journal_reclaim, false));
unlock:
        srcu_read_unlock(&c->btree_trans_barrier, srcu_idx);

        bch2_trans_put(trans);
        return ret;
}

bool bch2_btree_insert_key_cached(struct btree_trans *trans,
                                  unsigned flags,
                                  struct btree_insert_entry *insert_entry)
{
        struct bch_fs *c = trans->c;
        struct bkey_cached *ck = (void *) (trans->paths + insert_entry->path)->l[0].b;
        struct bkey_i *insert = insert_entry->k;
        bool kick_reclaim = false;

        BUG_ON(insert->k.u64s > ck->u64s);

        bkey_copy(ck->k, insert);

        if (!test_bit(BKEY_CACHED_DIRTY, &ck->flags)) {
                EBUG_ON(test_bit(BCH_FS_clean_shutdown, &c->flags));
                set_bit(BKEY_CACHED_DIRTY, &ck->flags);
                atomic_long_inc(&c->btree_key_cache.nr_dirty);

                if (bch2_nr_btree_keys_need_flush(c))
                        kick_reclaim = true;
        }

        /*
         * To minimize lock contention, we only add the journal pin here and
         * defer pin updates to the flush callback via ->seq. Be careful not to
         * update ->seq on nojournal commits because we don't want to update the
         * pin to a seq that doesn't include journal updates on disk. Otherwise
         * we risk losing the update after a crash.
         *
         * The only exception is if the pin is not active in the first place. We
         * have to add the pin because journal reclaim drives key cache
         * flushing. The flush callback will not proceed unless ->seq matches
         * the latest pin, so make sure it starts with a consistent value.
         */
        if (!(insert_entry->flags & BTREE_UPDATE_nojournal) ||
            !journal_pin_active(&ck->journal)) {
                ck->seq = trans->journal_res.seq;
        }
        bch2_journal_pin_add(&c->journal, trans->journal_res.seq,
                             &ck->journal, bch2_btree_key_cache_journal_flush);

        if (kick_reclaim)
                journal_reclaim_kick(&c->journal);
        return true;
}

void bch2_btree_key_cache_drop(struct btree_trans *trans,
                               struct btree_path *path)
{
        struct bch_fs *c = trans->c;
        struct btree_key_cache *bc = &c->btree_key_cache;
        struct bkey_cached *ck = (void *) path->l[0].b;

        /*
         * We just did an update to the btree, bypassing the key cache: the key
         * cache key is now stale and must be dropped, even if dirty:
         */
        if (test_bit(BKEY_CACHED_DIRTY, &ck->flags)) {
                clear_bit(BKEY_CACHED_DIRTY, &ck->flags);
                atomic_long_dec(&c->btree_key_cache.nr_dirty);
                bch2_journal_pin_drop(&c->journal, &ck->journal);
        }

        bkey_cached_evict(bc, ck);
        bkey_cached_free(bc, ck);

        mark_btree_node_locked(trans, path, 0, BTREE_NODE_UNLOCKED);
        btree_path_set_dirty(path, BTREE_ITER_NEED_TRAVERSE);
        path->should_be_locked = false;
}

static unsigned long bch2_btree_key_cache_scan(struct shrinker *shrink,
                                           struct shrink_control *sc)
{
        struct bch_fs *c = shrink->private_data;
        struct btree_key_cache *bc = &c->btree_key_cache;
        struct bucket_table *tbl;
        struct bkey_cached *ck;
        size_t scanned = 0, freed = 0, nr = sc->nr_to_scan;
        unsigned iter, start;
        int srcu_idx;

        srcu_idx = srcu_read_lock(&c->btree_trans_barrier);
        rcu_read_lock();

        tbl = rht_dereference_rcu(bc->table.tbl, &bc->table);

        /*
         * Scanning is expensive while a rehash is in progress - most elements
         * will be on the new hashtable, if it's in progress
         *
         * A rehash could still start while we're scanning - that's ok, we'll
         * still see most elements.
         */
        if (unlikely(tbl->nest)) {
                rcu_read_unlock();
                srcu_read_unlock(&c->btree_trans_barrier, srcu_idx);
                return SHRINK_STOP;
        }

        iter = bc->shrink_iter;
        if (iter >= tbl->size)
                iter = 0;
        start = iter;

        do {
                struct rhash_head *pos, *next;

                pos = rht_ptr_rcu(&tbl->buckets[iter]);

                while (!rht_is_a_nulls(pos)) {
                        next = rht_dereference_bucket_rcu(pos->next, tbl, iter);
                        ck = container_of(pos, struct bkey_cached, hash);

                        if (test_bit(BKEY_CACHED_DIRTY, &ck->flags)) {
                                bc->skipped_dirty++;
                        } else if (test_bit(BKEY_CACHED_ACCESSED, &ck->flags)) {
                                clear_bit(BKEY_CACHED_ACCESSED, &ck->flags);
                                bc->skipped_accessed++;
                        } else if (!bkey_cached_lock_for_evict(ck)) {
                                bc->skipped_lock_fail++;
                        } else if (bkey_cached_evict(bc, ck)) {
                                bkey_cached_free(bc, ck);
                                bc->freed++;
                                freed++;
                        } else {
                                six_unlock_write(&ck->c.lock);
                                six_unlock_intent(&ck->c.lock);
                        }

                        scanned++;
                        if (scanned >= nr)
                                goto out;

                        pos = next;
                }

                iter++;
                if (iter >= tbl->size)
                        iter = 0;
        } while (scanned < nr && iter != start);
out:
        bc->shrink_iter = iter;

        rcu_read_unlock();
        srcu_read_unlock(&c->btree_trans_barrier, srcu_idx);

        return freed;
}

static unsigned long bch2_btree_key_cache_count(struct shrinker *shrink,
                                            struct shrink_control *sc)
{
        struct bch_fs *c = shrink->private_data;
        struct btree_key_cache *bc = &c->btree_key_cache;
        long nr = atomic_long_read(&bc->nr_keys) -
                atomic_long_read(&bc->nr_dirty);

        /*
         * Avoid hammering our shrinker too much if it's nearly empty - the
         * shrinker code doesn't take into account how big our cache is, if it's
         * mostly empty but the system is under memory pressure it causes nasty
         * lock contention:
         */
        nr -= 128;

        return max(0L, nr);
}

void bch2_fs_btree_key_cache_exit(struct btree_key_cache *bc)
{
        struct bch_fs *c = container_of(bc, struct bch_fs, btree_key_cache);
        struct bucket_table *tbl;
        struct bkey_cached *ck;
        struct rhash_head *pos;
        LIST_HEAD(items);
        unsigned i;

        shrinker_free(bc->shrink);

        /*
         * The loop is needed to guard against racing with rehash:
         */
        while (atomic_long_read(&bc->nr_keys)) {
                rcu_read_lock();
                tbl = rht_dereference_rcu(bc->table.tbl, &bc->table);
                if (tbl) {
                        if (tbl->nest) {
                                /* wait for in progress rehash */
                                rcu_read_unlock();
                                mutex_lock(&bc->table.mutex);
                                mutex_unlock(&bc->table.mutex);
                                rcu_read_lock();
                                continue;
                        }
                        for (i = 0; i < tbl->size; i++)
                                while (pos = rht_ptr_rcu(&tbl->buckets[i]), !rht_is_a_nulls(pos)) {
                                        ck = container_of(pos, struct bkey_cached, hash);
                                        BUG_ON(!bkey_cached_evict(bc, ck));
                                        kfree(ck->k);
                                        kmem_cache_free(bch2_key_cache, ck);
                                }
                }
                rcu_read_unlock();
        }

        if (atomic_long_read(&bc->nr_dirty) &&
            !bch2_journal_error(&c->journal) &&
            test_bit(BCH_FS_was_rw, &c->flags))
                panic("btree key cache shutdown error: nr_dirty nonzero (%li)\n",
                      atomic_long_read(&bc->nr_dirty));

        if (atomic_long_read(&bc->nr_keys))
                panic("btree key cache shutdown error: nr_keys nonzero (%li)\n",
                      atomic_long_read(&bc->nr_keys));

        if (bc->table_init_done)
                rhashtable_destroy(&bc->table);

        rcu_pending_exit(&bc->pending[0]);
        rcu_pending_exit(&bc->pending[1]);

        free_percpu(bc->nr_pending);
}

void bch2_fs_btree_key_cache_init_early(struct btree_key_cache *c)
{
}

int bch2_fs_btree_key_cache_init(struct btree_key_cache *bc)
{
        struct bch_fs *c = container_of(bc, struct bch_fs, btree_key_cache);
        struct shrinker *shrink;

        bc->nr_pending = alloc_percpu(size_t);
        if (!bc->nr_pending)
                return -BCH_ERR_ENOMEM_fs_btree_cache_init;

        if (rcu_pending_init(&bc->pending[0], &c->btree_trans_barrier, __bkey_cached_free) ||
            rcu_pending_init(&bc->pending[1], &c->btree_trans_barrier, __bkey_cached_free))
                return -BCH_ERR_ENOMEM_fs_btree_cache_init;

        if (rhashtable_init(&bc->table, &bch2_btree_key_cache_params))
                return -BCH_ERR_ENOMEM_fs_btree_cache_init;

        bc->table_init_done = true;

        shrink = shrinker_alloc(0, "%s-btree_key_cache", c->name);
        if (!shrink)
                return -BCH_ERR_ENOMEM_fs_btree_cache_init;
        bc->shrink = shrink;
        shrink->count_objects        = bch2_btree_key_cache_count;
        shrink->scan_objects        = bch2_btree_key_cache_scan;
        shrink->batch                = 1 << 14;
        shrink->seeks                = 0;
        shrink->private_data        = c;
        shrinker_register(shrink);
        return 0;
}

void bch2_btree_key_cache_to_text(struct printbuf *out, struct btree_key_cache *bc)
{
        printbuf_tabstop_push(out, 24);
        printbuf_tabstop_push(out, 12);

        prt_printf(out, "keys:\t%lu\r\n",                atomic_long_read(&bc->nr_keys));
        prt_printf(out, "dirty:\t%lu\r\n",                atomic_long_read(&bc->nr_dirty));
        prt_printf(out, "table size:\t%u\r\n",                bc->table.tbl->size);
        prt_newline(out);
        prt_printf(out, "shrinker:\n");
        prt_printf(out, "requested_to_free:\t%lu\r\n",        bc->requested_to_free);
        prt_printf(out, "freed:\t%lu\r\n",                bc->freed);
        prt_printf(out, "skipped_dirty:\t%lu\r\n",        bc->skipped_dirty);
        prt_printf(out, "skipped_accessed:\t%lu\r\n",        bc->skipped_accessed);
        prt_printf(out, "skipped_lock_fail:\t%lu\r\n",        bc->skipped_lock_fail);
        prt_newline(out);
        prt_printf(out, "pending:\t%zu\r\n",                per_cpu_sum(bc->nr_pending));
}

void bch2_btree_key_cache_exit(void)
{
        kmem_cache_destroy(bch2_key_cache);
}

int __init bch2_btree_key_cache_init(void)
{
        bch2_key_cache = KMEM_CACHE(bkey_cached, SLAB_RECLAIM_ACCOUNT);
        if (!bch2_key_cache)
                return -ENOMEM;

        return 0;
}























   11 



    9 






   11 

    3 













   57 

   58 

   58 














   58 





   38 




   39 


















   38 



   39 



   28 








    3 










   32 





















   19 










   19 































   19 




























   15 








   18 














   38 





















   15 

    9 






   14 







    3 





























    4 


    3 

    6 

    3 










    3 












   57 









































































   17 











   17 


   17 















   17 






























   58 



   58 




















   75 























   65 
   32 

   76 








   53 







   82 




   83 


   13 










   57 


   50 
   17 




   84 





   84 
   19 


   83 





















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
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
// SPDX-License-Identifier: GPL-2.0-or-later
/*
 *  net/dccp/options.c
 *
 *  An implementation of the DCCP protocol
 *  Copyright (c) 2005 Aristeu Sergio Rozanski Filho <aris@cathedrallabs.org>
 *  Copyright (c) 2005 Arnaldo Carvalho de Melo <acme@ghostprotocols.net>
 *  Copyright (c) 2005 Ian McDonald <ian.mcdonald@jandi.co.nz>
 */
#include <linux/dccp.h>
#include <linux/module.h>
#include <linux/types.h>
#include <linux/unaligned.h>
#include <linux/kernel.h>
#include <linux/skbuff.h>

#include "ackvec.h"
#include "ccid.h"
#include "dccp.h"
#include "feat.h"

u64 dccp_decode_value_var(const u8 *bf, const u8 len)
{
        u64 value = 0;

        if (len >= DCCP_OPTVAL_MAXLEN)
                value += ((u64)*bf++) << 40;
        if (len > 4)
                value += ((u64)*bf++) << 32;
        if (len > 3)
                value += ((u64)*bf++) << 24;
        if (len > 2)
                value += ((u64)*bf++) << 16;
        if (len > 1)
                value += ((u64)*bf++) << 8;
        if (len > 0)
                value += *bf;

        return value;
}

/**
 * dccp_parse_options  -  Parse DCCP options present in @skb
 * @sk: client|server|listening dccp socket (when @dreq != NULL)
 * @dreq: request socket to use during connection setup, or NULL
 * @skb: frame to parse
 */
int dccp_parse_options(struct sock *sk, struct dccp_request_sock *dreq,
                       struct sk_buff *skb)
{
        struct dccp_sock *dp = dccp_sk(sk);
        const struct dccp_hdr *dh = dccp_hdr(skb);
        const u8 pkt_type = DCCP_SKB_CB(skb)->dccpd_type;
        unsigned char *options = (unsigned char *)dh + dccp_hdr_len(skb);
        unsigned char *opt_ptr = options;
        const unsigned char *opt_end = (unsigned char *)dh +
                                        (dh->dccph_doff * 4);
        struct dccp_options_received *opt_recv = &dp->dccps_options_received;
        unsigned char opt, len;
        unsigned char *value;
        u32 elapsed_time;
        __be32 opt_val;
        int rc;
        int mandatory = 0;

        memset(opt_recv, 0, sizeof(*opt_recv));

        opt = len = 0;
        while (opt_ptr != opt_end) {
                opt   = *opt_ptr++;
                len   = 0;
                value = NULL;

                /* Check if this isn't a single byte option */
                if (opt > DCCPO_MAX_RESERVED) {
                        if (opt_ptr == opt_end)
                                goto out_nonsensical_length;

                        len = *opt_ptr++;
                        if (len < 2)
                                goto out_nonsensical_length;
                        /*
                         * Remove the type and len fields, leaving
                         * just the value size
                         */
                        len        -= 2;
                        value        = opt_ptr;
                        opt_ptr += len;

                        if (opt_ptr > opt_end)
                                goto out_nonsensical_length;
                }

                /*
                 * CCID-specific options are ignored during connection setup, as
                 * negotiation may still be in progress (see RFC 4340, 10.3).
                 * The same applies to Ack Vectors, as these depend on the CCID.
                 */
                if (dreq != NULL && (opt >= DCCPO_MIN_RX_CCID_SPECIFIC ||
                    opt == DCCPO_ACK_VECTOR_0 || opt == DCCPO_ACK_VECTOR_1))
                        goto ignore_option;

                switch (opt) {
                case DCCPO_PADDING:
                        break;
                case DCCPO_MANDATORY:
                        if (mandatory)
                                goto out_invalid_option;
                        if (pkt_type != DCCP_PKT_DATA)
                                mandatory = 1;
                        break;
                case DCCPO_NDP_COUNT:
                        if (len > 6)
                                goto out_invalid_option;

                        opt_recv->dccpor_ndp = dccp_decode_value_var(value, len);
                        dccp_pr_debug("%s opt: NDP count=%llu\n", dccp_role(sk),
                                      (unsigned long long)opt_recv->dccpor_ndp);
                        break;
                case DCCPO_CHANGE_L ... DCCPO_CONFIRM_R:
                        if (pkt_type == DCCP_PKT_DATA)      /* RFC 4340, 6 */
                                break;
                        if (len == 0)
                                goto out_invalid_option;
                        rc = dccp_feat_parse_options(sk, dreq, mandatory, opt,
                                                    *value, value + 1, len - 1);
                        if (rc)
                                goto out_featneg_failed;
                        break;
                case DCCPO_TIMESTAMP:
                        if (len != 4)
                                goto out_invalid_option;
                        /*
                         * RFC 4340 13.1: "The precise time corresponding to
                         * Timestamp Value zero is not specified". We use
                         * zero to indicate absence of a meaningful timestamp.
                         */
                        opt_val = get_unaligned((__be32 *)value);
                        if (unlikely(opt_val == 0)) {
                                DCCP_WARN("Timestamp with zero value\n");
                                break;
                        }

                        if (dreq != NULL) {
                                dreq->dreq_timestamp_echo = ntohl(opt_val);
                                dreq->dreq_timestamp_time = dccp_timestamp();
                        } else {
                                opt_recv->dccpor_timestamp =
                                        dp->dccps_timestamp_echo = ntohl(opt_val);
                                dp->dccps_timestamp_time = dccp_timestamp();
                        }
                        dccp_pr_debug("%s rx opt: TIMESTAMP=%u, ackno=%llu\n",
                                      dccp_role(sk), ntohl(opt_val),
                                      (unsigned long long)
                                      DCCP_SKB_CB(skb)->dccpd_ack_seq);
                        /* schedule an Ack in case this sender is quiescent */
                        inet_csk_schedule_ack(sk);
                        break;
                case DCCPO_TIMESTAMP_ECHO:
                        if (len != 4 && len != 6 && len != 8)
                                goto out_invalid_option;

                        opt_val = get_unaligned((__be32 *)value);
                        opt_recv->dccpor_timestamp_echo = ntohl(opt_val);

                        dccp_pr_debug("%s rx opt: TIMESTAMP_ECHO=%u, len=%d, "
                                      "ackno=%llu", dccp_role(sk),
                                      opt_recv->dccpor_timestamp_echo,
                                      len + 2,
                                      (unsigned long long)
                                      DCCP_SKB_CB(skb)->dccpd_ack_seq);

                        value += 4;

                        if (len == 4) {                /* no elapsed time included */
                                dccp_pr_debug_cat("\n");
                                break;
                        }

                        if (len == 6) {                /* 2-byte elapsed time */
                                __be16 opt_val2 = get_unaligned((__be16 *)value);
                                elapsed_time = ntohs(opt_val2);
                        } else {                /* 4-byte elapsed time */
                                opt_val = get_unaligned((__be32 *)value);
                                elapsed_time = ntohl(opt_val);
                        }

                        dccp_pr_debug_cat(", ELAPSED_TIME=%u\n", elapsed_time);

                        /* Give precedence to the biggest ELAPSED_TIME */
                        if (elapsed_time > opt_recv->dccpor_elapsed_time)
                                opt_recv->dccpor_elapsed_time = elapsed_time;
                        break;
                case DCCPO_ELAPSED_TIME:
                        if (dccp_packet_without_ack(skb))   /* RFC 4340, 13.2 */
                                break;

                        if (len == 2) {
                                __be16 opt_val2 = get_unaligned((__be16 *)value);
                                elapsed_time = ntohs(opt_val2);
                        } else if (len == 4) {
                                opt_val = get_unaligned((__be32 *)value);
                                elapsed_time = ntohl(opt_val);
                        } else {
                                goto out_invalid_option;
                        }

                        if (elapsed_time > opt_recv->dccpor_elapsed_time)
                                opt_recv->dccpor_elapsed_time = elapsed_time;

                        dccp_pr_debug("%s rx opt: ELAPSED_TIME=%d\n",
                                      dccp_role(sk), elapsed_time);
                        break;
                case DCCPO_MIN_RX_CCID_SPECIFIC ... DCCPO_MAX_RX_CCID_SPECIFIC:
                        if (ccid_hc_rx_parse_options(dp->dccps_hc_rx_ccid, sk,
                                                     pkt_type, opt, value, len))
                                goto out_invalid_option;
                        break;
                case DCCPO_ACK_VECTOR_0:
                case DCCPO_ACK_VECTOR_1:
                        if (dccp_packet_without_ack(skb))   /* RFC 4340, 11.4 */
                                break;
                        /*
                         * Ack vectors are processed by the TX CCID if it is
                         * interested. The RX CCID need not parse Ack Vectors,
                         * since it is only interested in clearing old state.
                         */
                        fallthrough;
                case DCCPO_MIN_TX_CCID_SPECIFIC ... DCCPO_MAX_TX_CCID_SPECIFIC:
                        if (ccid_hc_tx_parse_options(dp->dccps_hc_tx_ccid, sk,
                                                     pkt_type, opt, value, len))
                                goto out_invalid_option;
                        break;
                default:
                        DCCP_CRIT("DCCP(%p): option %d(len=%d) not "
                                  "implemented, ignoring", sk, opt, len);
                        break;
                }
ignore_option:
                if (opt != DCCPO_MANDATORY)
                        mandatory = 0;
        }

        /* mandatory was the last byte in option list -> reset connection */
        if (mandatory)
                goto out_invalid_option;

out_nonsensical_length:
        /* RFC 4340, 5.8: ignore option and all remaining option space */
        return 0;

out_invalid_option:
        DCCP_INC_STATS(DCCP_MIB_INVALIDOPT);
        rc = DCCP_RESET_CODE_OPTION_ERROR;
out_featneg_failed:
        DCCP_WARN("DCCP(%p): Option %d (len=%d) error=%u\n", sk, opt, len, rc);
        DCCP_SKB_CB(skb)->dccpd_reset_code = rc;
        DCCP_SKB_CB(skb)->dccpd_reset_data[0] = opt;
        DCCP_SKB_CB(skb)->dccpd_reset_data[1] = len > 0 ? value[0] : 0;
        DCCP_SKB_CB(skb)->dccpd_reset_data[2] = len > 1 ? value[1] : 0;
        return -1;
}

EXPORT_SYMBOL_GPL(dccp_parse_options);

void dccp_encode_value_var(const u64 value, u8 *to, const u8 len)
{
        if (len >= DCCP_OPTVAL_MAXLEN)
                *to++ = (value & 0xFF0000000000ull) >> 40;
        if (len > 4)
                *to++ = (value & 0xFF00000000ull) >> 32;
        if (len > 3)
                *to++ = (value & 0xFF000000) >> 24;
        if (len > 2)
                *to++ = (value & 0xFF0000) >> 16;
        if (len > 1)
                *to++ = (value & 0xFF00) >> 8;
        if (len > 0)
                *to++ = (value & 0xFF);
}

static inline u8 dccp_ndp_len(const u64 ndp)
{
        if (likely(ndp <= 0xFF))
                return 1;
        return likely(ndp <= USHRT_MAX) ? 2 : (ndp <= UINT_MAX ? 4 : 6);
}

int dccp_insert_option(struct sk_buff *skb, const unsigned char option,
                       const void *value, const unsigned char len)
{
        unsigned char *to;

        if (DCCP_SKB_CB(skb)->dccpd_opt_len + len + 2 > DCCP_MAX_OPT_LEN)
                return -1;

        DCCP_SKB_CB(skb)->dccpd_opt_len += len + 2;

        to    = skb_push(skb, len + 2);
        *to++ = option;
        *to++ = len + 2;

        memcpy(to, value, len);
        return 0;
}

EXPORT_SYMBOL_GPL(dccp_insert_option);

static int dccp_insert_option_ndp(struct sock *sk, struct sk_buff *skb)
{
        struct dccp_sock *dp = dccp_sk(sk);
        u64 ndp = dp->dccps_ndp_count;

        if (dccp_non_data_packet(skb))
                ++dp->dccps_ndp_count;
        else
                dp->dccps_ndp_count = 0;

        if (ndp > 0) {
                unsigned char *ptr;
                const int ndp_len = dccp_ndp_len(ndp);
                const int len = ndp_len + 2;

                if (DCCP_SKB_CB(skb)->dccpd_opt_len + len > DCCP_MAX_OPT_LEN)
                        return -1;

                DCCP_SKB_CB(skb)->dccpd_opt_len += len;

                ptr = skb_push(skb, len);
                *ptr++ = DCCPO_NDP_COUNT;
                *ptr++ = len;
                dccp_encode_value_var(ndp, ptr, ndp_len);
        }

        return 0;
}

static inline int dccp_elapsed_time_len(const u32 elapsed_time)
{
        return elapsed_time == 0 ? 0 : elapsed_time <= 0xFFFF ? 2 : 4;
}

static int dccp_insert_option_timestamp(struct sk_buff *skb)
{
        __be32 now = htonl(dccp_timestamp());
        /* yes this will overflow but that is the point as we want a
         * 10 usec 32 bit timer which mean it wraps every 11.9 hours */

        return dccp_insert_option(skb, DCCPO_TIMESTAMP, &now, sizeof(now));
}

static int dccp_insert_option_timestamp_echo(struct dccp_sock *dp,
                                             struct dccp_request_sock *dreq,
                                             struct sk_buff *skb)
{
        __be32 tstamp_echo;
        unsigned char *to;
        u32 elapsed_time, elapsed_time_len, len;

        if (dreq != NULL) {
                elapsed_time = dccp_timestamp() - dreq->dreq_timestamp_time;
                tstamp_echo  = htonl(dreq->dreq_timestamp_echo);
                dreq->dreq_timestamp_echo = 0;
        } else {
                elapsed_time = dccp_timestamp() - dp->dccps_timestamp_time;
                tstamp_echo  = htonl(dp->dccps_timestamp_echo);
                dp->dccps_timestamp_echo = 0;
        }

        elapsed_time_len = dccp_elapsed_time_len(elapsed_time);
        len = 6 + elapsed_time_len;

        if (DCCP_SKB_CB(skb)->dccpd_opt_len + len > DCCP_MAX_OPT_LEN)
                return -1;

        DCCP_SKB_CB(skb)->dccpd_opt_len += len;

        to    = skb_push(skb, len);
        *to++ = DCCPO_TIMESTAMP_ECHO;
        *to++ = len;

        memcpy(to, &tstamp_echo, 4);
        to += 4;

        if (elapsed_time_len == 2) {
                const __be16 var16 = htons((u16)elapsed_time);
                memcpy(to, &var16, 2);
        } else if (elapsed_time_len == 4) {
                const __be32 var32 = htonl(elapsed_time);
                memcpy(to, &var32, 4);
        }

        return 0;
}

static int dccp_insert_option_ackvec(struct sock *sk, struct sk_buff *skb)
{
        struct dccp_sock *dp = dccp_sk(sk);
        struct dccp_ackvec *av = dp->dccps_hc_rx_ackvec;
        struct dccp_skb_cb *dcb = DCCP_SKB_CB(skb);
        const u16 buflen = dccp_ackvec_buflen(av);
        /* Figure out how many options do we need to represent the ackvec */
        const u8 nr_opts = DIV_ROUND_UP(buflen, DCCP_SINGLE_OPT_MAXLEN);
        u16 len = buflen + 2 * nr_opts;
        u8 i, nonce = 0;
        const unsigned char *tail, *from;
        unsigned char *to;

        if (dcb->dccpd_opt_len + len > DCCP_MAX_OPT_LEN) {
                DCCP_WARN("Lacking space for %u bytes on %s packet\n", len,
                          dccp_packet_name(dcb->dccpd_type));
                return -1;
        }
        /*
         * Since Ack Vectors are variable-length, we can not always predict
         * their size. To catch exception cases where the space is running out
         * on the skb, a separate Sync is scheduled to carry the Ack Vector.
         */
        if (len > DCCPAV_MIN_OPTLEN &&
            len + dcb->dccpd_opt_len + skb->len > dp->dccps_mss_cache) {
                DCCP_WARN("No space left for Ack Vector (%u) on skb (%u+%u), "
                          "MPS=%u ==> reduce payload size?\n", len, skb->len,
                          dcb->dccpd_opt_len, dp->dccps_mss_cache);
                dp->dccps_sync_scheduled = 1;
                return 0;
        }
        dcb->dccpd_opt_len += len;

        to   = skb_push(skb, len);
        len  = buflen;
        from = av->av_buf + av->av_buf_head;
        tail = av->av_buf + DCCPAV_MAX_ACKVEC_LEN;

        for (i = 0; i < nr_opts; ++i) {
                int copylen = len;

                if (len > DCCP_SINGLE_OPT_MAXLEN)
                        copylen = DCCP_SINGLE_OPT_MAXLEN;

                /*
                 * RFC 4340, 12.2: Encode the Nonce Echo for this Ack Vector via
                 * its type; ack_nonce is the sum of all individual buf_nonce's.
                 */
                nonce ^= av->av_buf_nonce[i];

                *to++ = DCCPO_ACK_VECTOR_0 + av->av_buf_nonce[i];
                *to++ = copylen + 2;

                /* Check if buf_head wraps */
                if (from + copylen > tail) {
                        const u16 tailsize = tail - from;

                        memcpy(to, from, tailsize);
                        to        += tailsize;
                        len        -= tailsize;
                        copylen        -= tailsize;
                        from        = av->av_buf;
                }

                memcpy(to, from, copylen);
                from += copylen;
                to   += copylen;
                len  -= copylen;
        }
        /*
         * Each sent Ack Vector is recorded in the list, as per A.2 of RFC 4340.
         */
        if (dccp_ackvec_update_records(av, dcb->dccpd_seq, nonce))
                return -ENOBUFS;
        return 0;
}

/**
 * dccp_insert_option_mandatory  -  Mandatory option (5.8.2)
 * @skb: frame into which to insert option
 *
 * Note that since we are using skb_push, this function needs to be called
 * _after_ inserting the option it is supposed to influence (stack order).
 */
int dccp_insert_option_mandatory(struct sk_buff *skb)
{
        if (DCCP_SKB_CB(skb)->dccpd_opt_len >= DCCP_MAX_OPT_LEN)
                return -1;

        DCCP_SKB_CB(skb)->dccpd_opt_len++;
        *(u8 *)skb_push(skb, 1) = DCCPO_MANDATORY;
        return 0;
}

/**
 * dccp_insert_fn_opt  -  Insert single Feature-Negotiation option into @skb
 * @skb: frame to insert feature negotiation option into
 * @type: %DCCPO_CHANGE_L, %DCCPO_CHANGE_R, %DCCPO_CONFIRM_L, %DCCPO_CONFIRM_R
 * @feat: one out of %dccp_feature_numbers
 * @val: NN value or SP array (preferred element first) to copy
 * @len: true length of @val in bytes (excluding first element repetition)
 * @repeat_first: whether to copy the first element of @val twice
 *
 * The last argument is used to construct Confirm options, where the preferred
 * value and the preference list appear separately (RFC 4340, 6.3.1). Preference
 * lists are kept such that the preferred entry is always first, so we only need
 * to copy twice, and avoid the overhead of cloning into a bigger array.
 */
int dccp_insert_fn_opt(struct sk_buff *skb, u8 type, u8 feat,
                       u8 *val, u8 len, bool repeat_first)
{
        u8 tot_len, *to;

        /* take the `Feature' field and possible repetition into account */
        if (len > (DCCP_SINGLE_OPT_MAXLEN - 2)) {
                DCCP_WARN("length %u for feature %u too large\n", len, feat);
                return -1;
        }

        if (unlikely(val == NULL || len == 0))
                len = repeat_first = false;
        tot_len = 3 + repeat_first + len;

        if (DCCP_SKB_CB(skb)->dccpd_opt_len + tot_len > DCCP_MAX_OPT_LEN) {
                DCCP_WARN("packet too small for feature %d option!\n", feat);
                return -1;
        }
        DCCP_SKB_CB(skb)->dccpd_opt_len += tot_len;

        to    = skb_push(skb, tot_len);
        *to++ = type;
        *to++ = tot_len;
        *to++ = feat;

        if (repeat_first)
                *to++ = *val;
        if (len)
                memcpy(to, val, len);
        return 0;
}

/* The length of all options needs to be a multiple of 4 (5.8) */
static void dccp_insert_option_padding(struct sk_buff *skb)
{
        int padding = DCCP_SKB_CB(skb)->dccpd_opt_len % 4;

        if (padding != 0) {
                padding = 4 - padding;
                memset(skb_push(skb, padding), 0, padding);
                DCCP_SKB_CB(skb)->dccpd_opt_len += padding;
        }
}

int dccp_insert_options(struct sock *sk, struct sk_buff *skb)
{
        struct dccp_sock *dp = dccp_sk(sk);

        DCCP_SKB_CB(skb)->dccpd_opt_len = 0;

        if (dp->dccps_send_ndp_count && dccp_insert_option_ndp(sk, skb))
                return -1;

        if (DCCP_SKB_CB(skb)->dccpd_type != DCCP_PKT_DATA) {

                /* Feature Negotiation */
                if (dccp_feat_insert_opts(dp, NULL, skb))
                        return -1;

                if (DCCP_SKB_CB(skb)->dccpd_type == DCCP_PKT_REQUEST) {
                        /*
                         * Obtain RTT sample from Request/Response exchange.
                         * This is currently used for TFRC initialisation.
                         */
                        if (dccp_insert_option_timestamp(skb))
                                return -1;

                } else if (dccp_ackvec_pending(sk) &&
                           dccp_insert_option_ackvec(sk, skb)) {
                                return -1;
                }
        }

        if (dp->dccps_hc_rx_insert_options) {
                if (ccid_hc_rx_insert_options(dp->dccps_hc_rx_ccid, sk, skb))
                        return -1;
                dp->dccps_hc_rx_insert_options = 0;
        }

        if (dp->dccps_timestamp_echo != 0 &&
            dccp_insert_option_timestamp_echo(dp, NULL, skb))
                return -1;

        dccp_insert_option_padding(skb);
        return 0;
}

int dccp_insert_options_rsk(struct dccp_request_sock *dreq, struct sk_buff *skb)
{
        DCCP_SKB_CB(skb)->dccpd_opt_len = 0;

        if (dccp_feat_insert_opts(NULL, dreq, skb))
                return -1;

        /* Obtain RTT sample from Response/Ack exchange (used by TFRC). */
        if (dccp_insert_option_timestamp(skb))
                return -1;

        if (dreq->dreq_timestamp_echo != 0 &&
            dccp_insert_option_timestamp_echo(NULL, dreq, skb))
                return -1;

        dccp_insert_option_padding(skb);
        return 0;
}





























































    9 
    7 


    1 









    6 







    6 



    2 


















   20 


    1 














   18 






    3 



   14 










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
// SPDX-License-Identifier: GPL-2.0
/*
 * linux/fs/jfs/ioctl.c
 *
 * Copyright (C) 2006 Herbert Poetzl
 * adapted from Remy Card's ext2/ioctl.c
 */

#include <linux/fs.h>
#include <linux/ctype.h>
#include <linux/capability.h>
#include <linux/mount.h>
#include <linux/time.h>
#include <linux/sched.h>
#include <linux/blkdev.h>
#include <asm/current.h>
#include <linux/uaccess.h>
#include <linux/fileattr.h>

#include "jfs_filsys.h"
#include "jfs_debug.h"
#include "jfs_incore.h"
#include "jfs_dinode.h"
#include "jfs_inode.h"
#include "jfs_dmap.h"
#include "jfs_discard.h"

static struct {
        long jfs_flag;
        long ext2_flag;
} jfs_map[] = {
        {JFS_NOATIME_FL,        FS_NOATIME_FL},
        {JFS_DIRSYNC_FL,        FS_DIRSYNC_FL},
        {JFS_SYNC_FL,                FS_SYNC_FL},
        {JFS_SECRM_FL,                FS_SECRM_FL},
        {JFS_UNRM_FL,                FS_UNRM_FL},
        {JFS_APPEND_FL,                FS_APPEND_FL},
        {JFS_IMMUTABLE_FL,        FS_IMMUTABLE_FL},
        {0, 0},
};

static long jfs_map_ext2(unsigned long flags, int from)
{
        int index=0;
        long mapped=0;

        while (jfs_map[index].jfs_flag) {
                if (from) {
                        if (jfs_map[index].ext2_flag & flags)
                                mapped |= jfs_map[index].jfs_flag;
                } else {
                        if (jfs_map[index].jfs_flag & flags)
                                mapped |= jfs_map[index].ext2_flag;
                }
                index++;
        }
        return mapped;
}

int jfs_fileattr_get(struct dentry *dentry, struct fileattr *fa)
{
        struct jfs_inode_info *jfs_inode = JFS_IP(d_inode(dentry));
        unsigned int flags = jfs_inode->mode2 & JFS_FL_USER_VISIBLE;

        if (d_is_special(dentry))
                return -ENOTTY;

        fileattr_fill_flags(fa, jfs_map_ext2(flags, 0));

        return 0;
}

int jfs_fileattr_set(struct mnt_idmap *idmap,
                     struct dentry *dentry, struct fileattr *fa)
{
        struct inode *inode = d_inode(dentry);
        struct jfs_inode_info *jfs_inode = JFS_IP(inode);
        unsigned int flags;

        if (d_is_special(dentry))
                return -ENOTTY;

        if (fileattr_has_fsx(fa))
                return -EOPNOTSUPP;

        flags = jfs_map_ext2(fa->flags, 1);
        if (!S_ISDIR(inode->i_mode))
                flags &= ~JFS_DIRSYNC_FL;

        /* Is it quota file? Do not allow user to mess with it */
        if (IS_NOQUOTA(inode))
                return -EPERM;

        flags = flags & JFS_FL_USER_MODIFIABLE;
        flags |= jfs_inode->mode2 & ~JFS_FL_USER_MODIFIABLE;
        jfs_inode->mode2 = flags;

        jfs_set_inode_flags(inode);
        inode_set_ctime_current(inode);
        mark_inode_dirty(inode);

        return 0;
}

long jfs_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
{
        struct inode *inode = file_inode(filp);

        switch (cmd) {
        case FITRIM:
        {
                struct super_block *sb = inode->i_sb;
                struct fstrim_range range;
                s64 ret = 0;

                if (!capable(CAP_SYS_ADMIN))
                        return -EPERM;

                if (!bdev_max_discard_sectors(sb->s_bdev)) {
                        jfs_warn("FITRIM not supported on device");
                        return -EOPNOTSUPP;
                }

                if (copy_from_user(&range, (struct fstrim_range __user *)arg,
                    sizeof(range)))
                        return -EFAULT;

                range.minlen = max_t(unsigned int, range.minlen,
                                     bdev_discard_granularity(sb->s_bdev));

                ret = jfs_ioc_trim(inode, &range);
                if (ret < 0)
                        return ret;

                if (copy_to_user((struct fstrim_range __user *)arg, &range,
                    sizeof(range)))
                        return -EFAULT;

                return 0;
        }

        default:
                return -ENOTTY;
        }
}













































































































































































































































































































































































































































































































































































































































































































































































































































































































































































































































   19 



    1 


    1 






   12 
   12 
    1 




    2 
    1 






    1 













    3 












    5 
    5 













































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
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
// SPDX-License-Identifier: GPL-2.0-or-later
/*
 * Copyright (c) International Business Machines Corp., 2006
 *
 * Author: Artem Bityutskiy (Битюцкий Артём)
 */

/*
 * This file includes implementation of UBI character device operations.
 *
 * There are two kinds of character devices in UBI: UBI character devices and
 * UBI volume character devices. UBI character devices allow users to
 * manipulate whole volumes: create, remove, and re-size them. Volume character
 * devices provide volume I/O capabilities.
 *
 * Major and minor numbers are assigned dynamically to both UBI and volume
 * character devices.
 *
 * Well, there is the third kind of character devices - the UBI control
 * character device, which allows to manipulate by UBI devices - create and
 * delete them. In other words, it is used for attaching and detaching MTD
 * devices.
 */

#include <linux/module.h>
#include <linux/stat.h>
#include <linux/slab.h>
#include <linux/ioctl.h>
#include <linux/capability.h>
#include <linux/uaccess.h>
#include <linux/compat.h>
#include <linux/math64.h>
#include <mtd/ubi-user.h>
#include "ubi.h"

/**
 * get_exclusive - get exclusive access to an UBI volume.
 * @desc: volume descriptor
 *
 * This function changes UBI volume open mode to "exclusive". Returns previous
 * mode value (positive integer) in case of success and a negative error code
 * in case of failure.
 */
static int get_exclusive(struct ubi_volume_desc *desc)
{
        int users, err;
        struct ubi_volume *vol = desc->vol;

        spin_lock(&vol->ubi->volumes_lock);
        users = vol->readers + vol->writers + vol->exclusive + vol->metaonly;
        ubi_assert(users > 0);
        if (users > 1) {
                ubi_err(vol->ubi, "%d users for volume %d", users, vol->vol_id);
                err = -EBUSY;
        } else {
                vol->readers = vol->writers = vol->metaonly = 0;
                vol->exclusive = 1;
                err = desc->mode;
                desc->mode = UBI_EXCLUSIVE;
        }
        spin_unlock(&vol->ubi->volumes_lock);

        return err;
}

/**
 * revoke_exclusive - revoke exclusive mode.
 * @desc: volume descriptor
 * @mode: new mode to switch to
 */
static void revoke_exclusive(struct ubi_volume_desc *desc, int mode)
{
        struct ubi_volume *vol = desc->vol;

        spin_lock(&vol->ubi->volumes_lock);
        ubi_assert(vol->readers == 0 && vol->writers == 0 && vol->metaonly == 0);
        ubi_assert(vol->exclusive == 1 && desc->mode == UBI_EXCLUSIVE);
        vol->exclusive = 0;
        if (mode == UBI_READONLY)
                vol->readers = 1;
        else if (mode == UBI_READWRITE)
                vol->writers = 1;
        else if (mode == UBI_METAONLY)
                vol->metaonly = 1;
        else
                vol->exclusive = 1;
        spin_unlock(&vol->ubi->volumes_lock);

        desc->mode = mode;
}

static int vol_cdev_open(struct inode *inode, struct file *file)
{
        struct ubi_volume_desc *desc;
        int vol_id = iminor(inode) - 1, mode, ubi_num;

        ubi_num = ubi_major2num(imajor(inode));
        if (ubi_num < 0)
                return ubi_num;

        if (file->f_mode & FMODE_WRITE)
                mode = UBI_READWRITE;
        else
                mode = UBI_READONLY;

        dbg_gen("open device %d, volume %d, mode %d",
                ubi_num, vol_id, mode);

        desc = ubi_open_volume(ubi_num, vol_id, mode);
        if (IS_ERR(desc))
                return PTR_ERR(desc);

        file->private_data = desc;
        return 0;
}

static int vol_cdev_release(struct inode *inode, struct file *file)
{
        struct ubi_volume_desc *desc = file->private_data;
        struct ubi_volume *vol = desc->vol;

        dbg_gen("release device %d, volume %d, mode %d",
                vol->ubi->ubi_num, vol->vol_id, desc->mode);

        if (vol->updating) {
                ubi_warn(vol->ubi, "update of volume %d not finished, volume is damaged",
                         vol->vol_id);
                ubi_assert(!vol->changing_leb);
                vol->updating = 0;
                vfree(vol->upd_buf);
        } else if (vol->changing_leb) {
                dbg_gen("only %lld of %lld bytes received for atomic LEB change for volume %d:%d, cancel",
                        vol->upd_received, vol->upd_bytes, vol->ubi->ubi_num,
                        vol->vol_id);
                vol->changing_leb = 0;
                vfree(vol->upd_buf);
        }

        ubi_close_volume(desc);
        return 0;
}

static loff_t vol_cdev_llseek(struct file *file, loff_t offset, int origin)
{
        struct ubi_volume_desc *desc = file->private_data;
        struct ubi_volume *vol = desc->vol;

        if (vol->updating) {
                /* Update is in progress, seeking is prohibited */
                ubi_err(vol->ubi, "updating");
                return -EBUSY;
        }

        return fixed_size_llseek(file, offset, origin, vol->used_bytes);
}

static int vol_cdev_fsync(struct file *file, loff_t start, loff_t end,
                          int datasync)
{
        struct ubi_volume_desc *desc = file->private_data;
        struct ubi_device *ubi = desc->vol->ubi;
        struct inode *inode = file_inode(file);
        int err;
        inode_lock(inode);
        err = ubi_sync(ubi->ubi_num);
        inode_unlock(inode);
        return err;
}


static ssize_t vol_cdev_read(struct file *file, __user char *buf, size_t count,
                             loff_t *offp)
{
        struct ubi_volume_desc *desc = file->private_data;
        struct ubi_volume *vol = desc->vol;
        struct ubi_device *ubi = vol->ubi;
        int err, lnum, off, len,  tbuf_size;
        size_t count_save = count;
        void *tbuf;

        dbg_gen("read %zd bytes from offset %lld of volume %d",
                count, *offp, vol->vol_id);

        if (vol->updating) {
                ubi_err(vol->ubi, "updating");
                return -EBUSY;
        }
        if (vol->upd_marker) {
                ubi_err(vol->ubi, "damaged volume, update marker is set");
                return -EBADF;
        }
        if (*offp == vol->used_bytes || count == 0)
                return 0;

        if (vol->corrupted)
                dbg_gen("read from corrupted volume %d", vol->vol_id);

        if (*offp + count > vol->used_bytes)
                count_save = count = vol->used_bytes - *offp;

        tbuf_size = vol->usable_leb_size;
        if (count < tbuf_size)
                tbuf_size = ALIGN(count, ubi->min_io_size);
        tbuf = vmalloc(tbuf_size);
        if (!tbuf)
                return -ENOMEM;

        len = count > tbuf_size ? tbuf_size : count;
        lnum = div_u64_rem(*offp, vol->usable_leb_size, &off);

        do {
                cond_resched();

                if (off + len >= vol->usable_leb_size)
                        len = vol->usable_leb_size - off;

                err = ubi_eba_read_leb(ubi, vol, lnum, tbuf, off, len, 0);
                if (err)
                        break;

                off += len;
                if (off == vol->usable_leb_size) {
                        lnum += 1;
                        off -= vol->usable_leb_size;
                }

                count -= len;
                *offp += len;

                err = copy_to_user(buf, tbuf, len);
                if (err) {
                        err = -EFAULT;
                        break;
                }

                buf += len;
                len = count > tbuf_size ? tbuf_size : count;
        } while (count);

        vfree(tbuf);
        return err ? err : count_save - count;
}

/*
 * This function allows to directly write to dynamic UBI volumes, without
 * issuing the volume update operation.
 */
static ssize_t vol_cdev_direct_write(struct file *file, const char __user *buf,
                                     size_t count, loff_t *offp)
{
        struct ubi_volume_desc *desc = file->private_data;
        struct ubi_volume *vol = desc->vol;
        struct ubi_device *ubi = vol->ubi;
        int lnum, off, len, tbuf_size, err = 0;
        size_t count_save = count;
        char *tbuf;

        if (!vol->direct_writes)
                return -EPERM;

        dbg_gen("requested: write %zd bytes to offset %lld of volume %u",
                count, *offp, vol->vol_id);

        if (vol->vol_type == UBI_STATIC_VOLUME)
                return -EROFS;

        lnum = div_u64_rem(*offp, vol->usable_leb_size, &off);
        if (off & (ubi->min_io_size - 1)) {
                ubi_err(ubi, "unaligned position");
                return -EINVAL;
        }

        if (*offp + count > vol->used_bytes)
                count_save = count = vol->used_bytes - *offp;

        /* We can write only in fractions of the minimum I/O unit */
        if (count & (ubi->min_io_size - 1)) {
                ubi_err(ubi, "unaligned write length");
                return -EINVAL;
        }

        tbuf_size = vol->usable_leb_size;
        if (count < tbuf_size)
                tbuf_size = ALIGN(count, ubi->min_io_size);
        tbuf = vmalloc(tbuf_size);
        if (!tbuf)
                return -ENOMEM;

        len = count > tbuf_size ? tbuf_size : count;

        while (count) {
                cond_resched();

                if (off + len >= vol->usable_leb_size)
                        len = vol->usable_leb_size - off;

                err = copy_from_user(tbuf, buf, len);
                if (err) {
                        err = -EFAULT;
                        break;
                }

                err = ubi_eba_write_leb(ubi, vol, lnum, tbuf, off, len);
                if (err)
                        break;

                off += len;
                if (off == vol->usable_leb_size) {
                        lnum += 1;
                        off -= vol->usable_leb_size;
                }

                count -= len;
                *offp += len;
                buf += len;
                len = count > tbuf_size ? tbuf_size : count;
        }

        vfree(tbuf);
        return err ? err : count_save - count;
}

static ssize_t vol_cdev_write(struct file *file, const char __user *buf,
                              size_t count, loff_t *offp)
{
        int err = 0;
        struct ubi_volume_desc *desc = file->private_data;
        struct ubi_volume *vol = desc->vol;
        struct ubi_device *ubi = vol->ubi;

        if (!vol->updating && !vol->changing_leb)
                return vol_cdev_direct_write(file, buf, count, offp);

        if (vol->updating)
                err = ubi_more_update_data(ubi, vol, buf, count);
        else
                err = ubi_more_leb_change_data(ubi, vol, buf, count);

        if (err < 0) {
                ubi_err(ubi, "cannot accept more %zd bytes of data, error %d",
                        count, err);
                return err;
        }

        if (err) {
                /*
                 * The operation is finished, @err contains number of actually
                 * written bytes.
                 */
                count = err;

                if (vol->changing_leb) {
                        revoke_exclusive(desc, UBI_READWRITE);
                        return count;
                }

                /*
                 * We voluntarily do not take into account the skip_check flag
                 * as we want to make sure what we wrote was correctly written.
                 */
                err = ubi_check_volume(ubi, vol->vol_id);
                if (err < 0)
                        return err;

                if (err) {
                        ubi_warn(ubi, "volume %d on UBI device %d is corrupted",
                                 vol->vol_id, ubi->ubi_num);
                        vol->corrupted = 1;
                }
                vol->checked = 1;
                ubi_volume_notify(ubi, vol, UBI_VOLUME_UPDATED);
                revoke_exclusive(desc, UBI_READWRITE);
        }

        return count;
}

static long vol_cdev_ioctl(struct file *file, unsigned int cmd,
                           unsigned long arg)
{
        int err = 0;
        struct ubi_volume_desc *desc = file->private_data;
        struct ubi_volume *vol = desc->vol;
        struct ubi_device *ubi = vol->ubi;
        void __user *argp = (void __user *)arg;

        switch (cmd) {
        /* Volume update command */
        case UBI_IOCVOLUP:
        {
                int64_t bytes, rsvd_bytes;

                if (!capable(CAP_SYS_RESOURCE)) {
                        err = -EPERM;
                        break;
                }

                err = copy_from_user(&bytes, argp, sizeof(int64_t));
                if (err) {
                        err = -EFAULT;
                        break;
                }

                if (desc->mode == UBI_READONLY) {
                        err = -EROFS;
                        break;
                }

                rsvd_bytes = (long long)vol->reserved_pebs *
                                        vol->usable_leb_size;
                if (bytes < 0 || bytes > rsvd_bytes) {
                        err = -EINVAL;
                        break;
                }

                err = get_exclusive(desc);
                if (err < 0)
                        break;

                err = ubi_start_update(ubi, vol, bytes);
                if (bytes == 0) {
                        ubi_volume_notify(ubi, vol, UBI_VOLUME_UPDATED);
                        revoke_exclusive(desc, UBI_READWRITE);
                }
                break;
        }

        /* Atomic logical eraseblock change command */
        case UBI_IOCEBCH:
        {
                struct ubi_leb_change_req req;

                err = copy_from_user(&req, argp,
                                     sizeof(struct ubi_leb_change_req));
                if (err) {
                        err = -EFAULT;
                        break;
                }

                if (desc->mode == UBI_READONLY ||
                    vol->vol_type == UBI_STATIC_VOLUME) {
                        err = -EROFS;
                        break;
                }

                /* Validate the request */
                err = -EINVAL;
                if (!ubi_leb_valid(vol, req.lnum) ||
                    req.bytes < 0 || req.bytes > vol->usable_leb_size)
                        break;

                err = get_exclusive(desc);
                if (err < 0)
                        break;

                err = ubi_start_leb_change(ubi, vol, &req);
                if (req.bytes == 0)
                        revoke_exclusive(desc, UBI_READWRITE);
                break;
        }

        /* Logical eraseblock erasure command */
        case UBI_IOCEBER:
        {
                int32_t lnum;

                err = get_user(lnum, (__user int32_t *)argp);
                if (err) {
                        err = -EFAULT;
                        break;
                }

                if (desc->mode == UBI_READONLY ||
                    vol->vol_type == UBI_STATIC_VOLUME) {
                        err = -EROFS;
                        break;
                }

                if (!ubi_leb_valid(vol, lnum)) {
                        err = -EINVAL;
                        break;
                }

                dbg_gen("erase LEB %d:%d", vol->vol_id, lnum);
                err = ubi_eba_unmap_leb(ubi, vol, lnum);
                if (err)
                        break;

                err = ubi_wl_flush(ubi, UBI_ALL, UBI_ALL);
                break;
        }

        /* Logical eraseblock map command */
        case UBI_IOCEBMAP:
        {
                struct ubi_map_req req;

                err = copy_from_user(&req, argp, sizeof(struct ubi_map_req));
                if (err) {
                        err = -EFAULT;
                        break;
                }
                err = ubi_leb_map(desc, req.lnum);
                break;
        }

        /* Logical eraseblock un-map command */
        case UBI_IOCEBUNMAP:
        {
                int32_t lnum;

                err = get_user(lnum, (__user int32_t *)argp);
                if (err) {
                        err = -EFAULT;
                        break;
                }
                err = ubi_leb_unmap(desc, lnum);
                break;
        }

        /* Check if logical eraseblock is mapped command */
        case UBI_IOCEBISMAP:
        {
                int32_t lnum;

                err = get_user(lnum, (__user int32_t *)argp);
                if (err) {
                        err = -EFAULT;
                        break;
                }
                err = ubi_is_mapped(desc, lnum);
                break;
        }

        /* Set volume property command */
        case UBI_IOCSETVOLPROP:
        {
                struct ubi_set_vol_prop_req req;

                err = copy_from_user(&req, argp,
                                     sizeof(struct ubi_set_vol_prop_req));
                if (err) {
                        err = -EFAULT;
                        break;
                }
                switch (req.property) {
                case UBI_VOL_PROP_DIRECT_WRITE:
                        mutex_lock(&ubi->device_mutex);
                        desc->vol->direct_writes = !!req.value;
                        mutex_unlock(&ubi->device_mutex);
                        break;
                default:
                        err = -EINVAL;
                        break;
                }
                break;
        }

        /* Create a R/O block device on top of the UBI volume */
        case UBI_IOCVOLCRBLK:
        {
                struct ubi_volume_info vi;

                ubi_get_volume_info(desc, &vi);
                err = ubiblock_create(&vi);
                break;
        }

        /* Remove the R/O block device */
        case UBI_IOCVOLRMBLK:
        {
                struct ubi_volume_info vi;

                ubi_get_volume_info(desc, &vi);
                err = ubiblock_remove(&vi);
                break;
        }

        default:
                err = -ENOTTY;
                break;
        }
        return err;
}

/**
 * verify_mkvol_req - verify volume creation request.
 * @ubi: UBI device description object
 * @req: the request to check
 *
 * This function zero if the request is correct, and %-EINVAL if not.
 */
static int verify_mkvol_req(const struct ubi_device *ubi,
                            const struct ubi_mkvol_req *req)
{
        int n, err = -EINVAL;

        if (req->bytes < 0 || req->alignment < 0 || req->vol_type < 0 ||
            req->name_len < 0)
                goto bad;

        if ((req->vol_id < 0 || req->vol_id >= ubi->vtbl_slots) &&
            req->vol_id != UBI_VOL_NUM_AUTO)
                goto bad;

        if (req->alignment == 0)
                goto bad;

        if (req->bytes == 0)
                goto bad;

        if (req->vol_type != UBI_DYNAMIC_VOLUME &&
            req->vol_type != UBI_STATIC_VOLUME)
                goto bad;

        if (req->flags & ~UBI_VOL_VALID_FLGS)
                goto bad;

        if (req->flags & UBI_VOL_SKIP_CRC_CHECK_FLG &&
            req->vol_type != UBI_STATIC_VOLUME)
                goto bad;

        if (req->alignment > ubi->leb_size)
                goto bad;

        n = req->alignment & (ubi->min_io_size - 1);
        if (req->alignment != 1 && n)
                goto bad;

        if (!req->name[0] || !req->name_len)
                goto bad;

        if (req->name_len > UBI_VOL_NAME_MAX) {
                err = -ENAMETOOLONG;
                goto bad;
        }

        n = strnlen(req->name, req->name_len + 1);
        if (n != req->name_len)
                goto bad;

        return 0;

bad:
        ubi_err(ubi, "bad volume creation request");
        ubi_dump_mkvol_req(req);
        return err;
}

/**
 * verify_rsvol_req - verify volume re-size request.
 * @ubi: UBI device description object
 * @req: the request to check
 *
 * This function returns zero if the request is correct, and %-EINVAL if not.
 */
static int verify_rsvol_req(const struct ubi_device *ubi,
                            const struct ubi_rsvol_req *req)
{
        if (req->bytes <= 0)
                return -EINVAL;

        if (req->vol_id < 0 || req->vol_id >= ubi->vtbl_slots)
                return -EINVAL;

        return 0;
}

/**
 * rename_volumes - rename UBI volumes.
 * @ubi: UBI device description object
 * @req: volumes re-name request
 *
 * This is a helper function for the volume re-name IOCTL which validates the
 * request, opens the volume and calls corresponding volumes management
 * function. Returns zero in case of success and a negative error code in case
 * of failure.
 */
static int rename_volumes(struct ubi_device *ubi,
                          struct ubi_rnvol_req *req)
{
        int i, n, err;
        struct list_head rename_list;
        struct ubi_rename_entry *re, *re1;

        if (req->count < 0 || req->count > UBI_MAX_RNVOL)
                return -EINVAL;

        if (req->count == 0)
                return 0;

        /* Validate volume IDs and names in the request */
        for (i = 0; i < req->count; i++) {
                if (req->ents[i].vol_id < 0 ||
                    req->ents[i].vol_id >= ubi->vtbl_slots)
                        return -EINVAL;
                if (req->ents[i].name_len < 0)
                        return -EINVAL;
                if (req->ents[i].name_len > UBI_VOL_NAME_MAX)
                        return -ENAMETOOLONG;
                req->ents[i].name[req->ents[i].name_len] = '\0';
                n = strlen(req->ents[i].name);
                if (n != req->ents[i].name_len)
                        return -EINVAL;
        }

        /* Make sure volume IDs and names are unique */
        for (i = 0; i < req->count - 1; i++) {
                for (n = i + 1; n < req->count; n++) {
                        if (req->ents[i].vol_id == req->ents[n].vol_id) {
                                ubi_err(ubi, "duplicated volume id %d",
                                        req->ents[i].vol_id);
                                return -EINVAL;
                        }
                        if (!strcmp(req->ents[i].name, req->ents[n].name)) {
                                ubi_err(ubi, "duplicated volume name \"%s\"",
                                        req->ents[i].name);
                                return -EINVAL;
                        }
                }
        }

        /* Create the re-name list */
        INIT_LIST_HEAD(&rename_list);
        for (i = 0; i < req->count; i++) {
                int vol_id = req->ents[i].vol_id;
                int name_len = req->ents[i].name_len;
                const char *name = req->ents[i].name;

                re = kzalloc(sizeof(struct ubi_rename_entry), GFP_KERNEL);
                if (!re) {
                        err = -ENOMEM;
                        goto out_free;
                }

                re->desc = ubi_open_volume(ubi->ubi_num, vol_id, UBI_METAONLY);
                if (IS_ERR(re->desc)) {
                        err = PTR_ERR(re->desc);
                        ubi_err(ubi, "cannot open volume %d, error %d",
                                vol_id, err);
                        kfree(re);
                        goto out_free;
                }

                /* Skip this re-naming if the name does not really change */
                if (re->desc->vol->name_len == name_len &&
                    !memcmp(re->desc->vol->name, name, name_len)) {
                        ubi_close_volume(re->desc);
                        kfree(re);
                        continue;
                }

                re->new_name_len = name_len;
                memcpy(re->new_name, name, name_len);
                list_add_tail(&re->list, &rename_list);
                dbg_gen("will rename volume %d from \"%s\" to \"%s\"",
                        vol_id, re->desc->vol->name, name);
        }

        if (list_empty(&rename_list))
                return 0;

        /* Find out the volumes which have to be removed */
        list_for_each_entry(re, &rename_list, list) {
                struct ubi_volume_desc *desc;
                int no_remove_needed = 0;

                /*
                 * Volume @re->vol_id is going to be re-named to
                 * @re->new_name, while its current name is @name. If a volume
                 * with name @re->new_name currently exists, it has to be
                 * removed, unless it is also re-named in the request (@req).
                 */
                list_for_each_entry(re1, &rename_list, list) {
                        if (re->new_name_len == re1->desc->vol->name_len &&
                            !memcmp(re->new_name, re1->desc->vol->name,
                                    re1->desc->vol->name_len)) {
                                no_remove_needed = 1;
                                break;
                        }
                }

                if (no_remove_needed)
                        continue;

                /*
                 * It seems we need to remove volume with name @re->new_name,
                 * if it exists.
                 */
                desc = ubi_open_volume_nm(ubi->ubi_num, re->new_name,
                                          UBI_EXCLUSIVE);
                if (IS_ERR(desc)) {
                        err = PTR_ERR(desc);
                        if (err == -ENODEV)
                                /* Re-naming into a non-existing volume name */
                                continue;

                        /* The volume exists but busy, or an error occurred */
                        ubi_err(ubi, "cannot open volume \"%s\", error %d",
                                re->new_name, err);
                        goto out_free;
                }

                re1 = kzalloc(sizeof(struct ubi_rename_entry), GFP_KERNEL);
                if (!re1) {
                        err = -ENOMEM;
                        ubi_close_volume(desc);
                        goto out_free;
                }

                re1->remove = 1;
                re1->desc = desc;
                list_add(&re1->list, &rename_list);
                dbg_gen("will remove volume %d, name \"%s\"",
                        re1->desc->vol->vol_id, re1->desc->vol->name);
        }

        mutex_lock(&ubi->device_mutex);
        err = ubi_rename_volumes(ubi, &rename_list);
        mutex_unlock(&ubi->device_mutex);

out_free:
        list_for_each_entry_safe(re, re1, &rename_list, list) {
                ubi_close_volume(re->desc);
                list_del(&re->list);
                kfree(re);
        }
        return err;
}

static long ubi_cdev_ioctl(struct file *file, unsigned int cmd,
                           unsigned long arg)
{
        int err = 0;
        struct ubi_device *ubi;
        struct ubi_volume_desc *desc;
        void __user *argp = (void __user *)arg;

        if (!capable(CAP_SYS_RESOURCE))
                return -EPERM;

        ubi = ubi_get_by_major(imajor(file->f_mapping->host));
        if (!ubi)
                return -ENODEV;

        switch (cmd) {
        /* Create volume command */
        case UBI_IOCMKVOL:
        {
                struct ubi_mkvol_req req;

                dbg_gen("create volume");
                err = copy_from_user(&req, argp, sizeof(struct ubi_mkvol_req));
                if (err) {
                        err = -EFAULT;
                        break;
                }

                err = verify_mkvol_req(ubi, &req);
                if (err)
                        break;

                mutex_lock(&ubi->device_mutex);
                err = ubi_create_volume(ubi, &req);
                mutex_unlock(&ubi->device_mutex);
                if (err)
                        break;

                err = put_user(req.vol_id, (__user int32_t *)argp);
                if (err)
                        err = -EFAULT;

                break;
        }

        /* Remove volume command */
        case UBI_IOCRMVOL:
        {
                int vol_id;

                dbg_gen("remove volume");
                err = get_user(vol_id, (__user int32_t *)argp);
                if (err) {
                        err = -EFAULT;
                        break;
                }

                desc = ubi_open_volume(ubi->ubi_num, vol_id, UBI_EXCLUSIVE);
                if (IS_ERR(desc)) {
                        err = PTR_ERR(desc);
                        break;
                }

                mutex_lock(&ubi->device_mutex);
                err = ubi_remove_volume(desc, 0);
                mutex_unlock(&ubi->device_mutex);

                /*
                 * The volume is deleted (unless an error occurred), and the
                 * 'struct ubi_volume' object will be freed when
                 * 'ubi_close_volume()' will call 'put_device()'.
                 */
                ubi_close_volume(desc);
                break;
        }

        /* Re-size volume command */
        case UBI_IOCRSVOL:
        {
                int pebs;
                struct ubi_rsvol_req req;

                dbg_gen("re-size volume");
                err = copy_from_user(&req, argp, sizeof(struct ubi_rsvol_req));
                if (err) {
                        err = -EFAULT;
                        break;
                }

                err = verify_rsvol_req(ubi, &req);
                if (err)
                        break;

                desc = ubi_open_volume(ubi->ubi_num, req.vol_id, UBI_EXCLUSIVE);
                if (IS_ERR(desc)) {
                        err = PTR_ERR(desc);
                        break;
                }

                pebs = div_u64(req.bytes + desc->vol->usable_leb_size - 1,
                               desc->vol->usable_leb_size);

                mutex_lock(&ubi->device_mutex);
                err = ubi_resize_volume(desc, pebs);
                mutex_unlock(&ubi->device_mutex);
                ubi_close_volume(desc);
                break;
        }

        /* Re-name volumes command */
        case UBI_IOCRNVOL:
        {
                struct ubi_rnvol_req *req;

                dbg_gen("re-name volumes");
                req = kmalloc(sizeof(struct ubi_rnvol_req), GFP_KERNEL);
                if (!req) {
                        err = -ENOMEM;
                        break;
                }

                err = copy_from_user(req, argp, sizeof(struct ubi_rnvol_req));
                if (err) {
                        err = -EFAULT;
                        kfree(req);
                        break;
                }

                err = rename_volumes(ubi, req);
                kfree(req);
                break;
        }

        /* Check a specific PEB for bitflips and scrub it if needed */
        case UBI_IOCRPEB:
        {
                int pnum;

                err = get_user(pnum, (__user int32_t *)argp);
                if (err) {
                        err = -EFAULT;
                        break;
                }

                err = ubi_bitflip_check(ubi, pnum, 0);
                break;
        }

        /* Force scrubbing for a specific PEB */
        case UBI_IOCSPEB:
        {
                int pnum;

                err = get_user(pnum, (__user int32_t *)argp);
                if (err) {
                        err = -EFAULT;
                        break;
                }

                err = ubi_bitflip_check(ubi, pnum, 1);
                break;
        }

        default:
                err = -ENOTTY;
                break;
        }

        ubi_put_device(ubi);
        return err;
}

static long ctrl_cdev_ioctl(struct file *file, unsigned int cmd,
                            unsigned long arg)
{
        int err = 0;
        void __user *argp = (void __user *)arg;

        if (!capable(CAP_SYS_RESOURCE))
                return -EPERM;

        switch (cmd) {
        /* Attach an MTD device command */
        case UBI_IOCATT:
        {
                struct ubi_attach_req req;
                struct mtd_info *mtd;

                dbg_gen("attach MTD device");
                err = copy_from_user(&req, argp, sizeof(struct ubi_attach_req));
                if (err) {
                        err = -EFAULT;
                        break;
                }

                if (req.mtd_num < 0 ||
                    (req.ubi_num < 0 && req.ubi_num != UBI_DEV_NUM_AUTO)) {
                        err = -EINVAL;
                        break;
                }

                mtd = get_mtd_device(NULL, req.mtd_num);
                if (IS_ERR(mtd)) {
                        err = PTR_ERR(mtd);
                        break;
                }

                /*
                 * Note, further request verification is done by
                 * 'ubi_attach_mtd_dev()'.
                 */
                mutex_lock(&ubi_devices_mutex);
                err = ubi_attach_mtd_dev(mtd, req.ubi_num, req.vid_hdr_offset,
                                         req.max_beb_per1024, !!req.disable_fm,
                                         !!req.need_resv_pool);
                mutex_unlock(&ubi_devices_mutex);
                if (err < 0)
                        put_mtd_device(mtd);
                else
                        /* @err contains UBI device number */
                        err = put_user(err, (__user int32_t *)argp);

                break;
        }

        /* Detach an MTD device command */
        case UBI_IOCDET:
        {
                int ubi_num;

                dbg_gen("detach MTD device");
                err = get_user(ubi_num, (__user int32_t *)argp);
                if (err) {
                        err = -EFAULT;
                        break;
                }

                mutex_lock(&ubi_devices_mutex);
                err = ubi_detach_mtd_dev(ubi_num, 0);
                mutex_unlock(&ubi_devices_mutex);
                break;
        }

        default:
                err = -ENOTTY;
                break;
        }

        return err;
}

/* UBI volume character device operations */
const struct file_operations ubi_vol_cdev_operations = {
        .owner          = THIS_MODULE,
        .open           = vol_cdev_open,
        .release        = vol_cdev_release,
        .llseek         = vol_cdev_llseek,
        .read           = vol_cdev_read,
        .write          = vol_cdev_write,
        .fsync                = vol_cdev_fsync,
        .unlocked_ioctl = vol_cdev_ioctl,
        .compat_ioctl   = compat_ptr_ioctl,
};

/* UBI character device operations */
const struct file_operations ubi_cdev_operations = {
        .owner          = THIS_MODULE,
        .unlocked_ioctl = ubi_cdev_ioctl,
        .compat_ioctl   = compat_ptr_ioctl,
};

/* UBI control character device operations */
const struct file_operations ubi_ctrl_cdev_operations = {
        .owner          = THIS_MODULE,
        .unlocked_ioctl = ctrl_cdev_ioctl,
        .compat_ioctl   = compat_ptr_ioctl,
};















































































































































































































































































































































































































































































    3 







   58 















































































































































































































































































































































































































































   35 






   33 





   10 

































































































































































































































































































































































































































































































































































































































































































































































































































































































































































































  587 


   26 


  230 
  226 
  114 














































































   66 

















   66 














  181 









  673 









  307 
  306 


  307 









  663 
  663 



  391 
  483 




  246 




  140 




   59 




























   71 
  611 



   22 
  294 














































































































    8 










































   81 





























































  354 





















  354 


  305 
   49 











  253 




  256 



  258 












  255 


  246 









    3 
    9 







  244 
    3 


  249 





   21 






























   61 


  424 
   41 
   12 
   16 

  121 
  183 
  207 
  132 





















  121 




  107 
  121 
  121 
  121 
  121 
  121 


  107 




   78 





   78 





    1 






   77 




  696 

  179 




  393 




  279 
  280 

  278 




    1 
  330 



  163 
  196 



  195 
  196 

  195 










   14 

    2 
   12 







   26 




   17 
   88 









    4 















































  273 






  255 








  189 
   20 







   26 
   60 
















  251 








  204 



  161 
  161 



  251 





  250 


    6 















  204 

  160 








    3 

    6 






   51 









   50 



   51 






   38 


    3 





   21 

























  802 









  776 


  610 




  286 

   49 










    4 






  796 
  359 


  213 
  796 
  745 

  809 



  465 
  271 
  465 
  445 
  164 
















  406 








  406 

  473 






   63 







   63 



   63 










































  235 














    1 












  168 


  551 
    1 






  570 





  450 



    2 
  450 
































































































   64 


  151 

   44 





  316 















  309 
  519 
  309 








   42 
  477 
   32 











   34 




    2 

    2 

    2 












  279 

    6 

   94 



  169 
  182 





   34 



   13 




   18 



  135 
  148 































   26 
   62 
   60 
   31 
   64 
   28 
   62 
   30 
   59 
   27 
   85 
    3 
   84 
    3 






  108 
  216 
  168 
  167 
  261 
   72 
  257 
   68 
  263 
   22 
  283 
    2 
  283 
    1 














  296 
  151 






  159 













   55 
  213 


  479 





  309 
  310 

  310 





  216 
  325 







































  199 
















   42 

   92 





  151 

   22 







   11 


   99 



















   51 




    4 






















  482 




















   74 
  464 





  254 








  254 





































  206 
    1 





  431 





















































































































   27 


   27 































































































































































































































































































































































































































































































































































































































































































  360 



   20 

   20 










  365 
  246 




   20 




  248 



































































































































































   18 




   18 









































































  349 







  349 








   11 
  279 




  219 



  220 









    1 










   12 












































  109 








   99 

















    6 

    5 
    3 












    1 
    1 





    3 


    1 



    1 


    7 






    3 




  137 












  138 





















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
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
1187
1188
1189
1190
1191
1192
1193
1194
1195
1196
1197
1198
1199
1200
1201
1202
1203
1204
1205
1206
1207
1208
1209
1210
1211
1212
1213
1214
1215
1216
1217
1218
1219
1220
1221
1222
1223
1224
1225
1226
1227
1228
1229
1230
1231
1232
1233
1234
1235
1236
1237
1238
1239
1240
1241
1242
1243
1244
1245
1246
1247
1248
1249
1250
1251
1252
1253
1254
1255
1256
1257
1258
1259
1260
1261
1262
1263
1264
1265
1266
1267
1268
1269
1270
1271
1272
1273
1274
1275
1276
1277
1278
1279
1280
1281
1282
1283
1284
1285
1286
1287
1288
1289
1290
1291
1292
1293
1294
1295
1296
1297
1298
1299
1300
1301
1302
1303
1304
1305
1306
1307
1308
1309
1310
1311
1312
1313
1314
1315
1316
1317
1318
1319
1320
1321
1322
1323
1324
1325
1326
1327
1328
1329
1330
1331
1332
1333
1334
1335
1336
1337
1338
1339
1340
1341
1342
1343
1344
1345
1346
1347
1348
1349
1350
1351
1352
1353
1354
1355
1356
1357
1358
1359
1360
1361
1362
1363
1364
1365
1366
1367
1368
1369
1370
1371
1372
1373
1374
1375
1376
1377
1378
1379
1380
1381
1382
1383
1384
1385
1386
1387
1388
1389
1390
1391
1392
1393
1394
1395
1396
1397
1398
1399
1400
1401
1402
1403
1404
1405
1406
1407
1408
1409
1410
1411
1412
1413
1414
1415
1416
1417
1418
1419
1420
1421
1422
1423
1424
1425
1426
1427
1428
1429
1430
1431
1432
1433
1434
1435
1436
1437
1438
1439
1440
1441
1442
1443
1444
1445
1446
1447
1448
1449
1450
1451
1452
1453
1454
1455
1456
1457
1458
1459
1460
1461
1462
1463
1464
1465
1466
1467
1468
1469
1470
1471
1472
1473
1474
1475
1476
1477
1478
1479
1480
1481
1482
1483
1484
1485
1486
1487
1488
1489
1490
1491
1492
1493
1494
1495
1496
1497
1498
1499
1500
1501
1502
1503
1504
1505
1506
1507
1508
1509
1510
1511
1512
1513
1514
1515
1516
1517
1518
1519
1520
1521
1522
1523
1524
1525
1526
1527
1528
1529
1530
1531
1532
1533
1534
1535
1536
1537
1538
1539
1540
1541
1542
1543
1544
1545
1546
1547
1548
1549
1550
1551
1552
1553
1554
1555
1556
1557
1558
1559
1560
1561
1562
1563
1564
1565
1566
1567
1568
1569
1570
1571
1572
1573
1574
1575
1576
1577
1578
1579
1580
1581
1582
1583
1584
1585
1586
1587
1588
1589
1590
1591
1592
1593
1594
1595
1596
1597
1598
1599
1600
1601
1602
1603
1604
1605
1606
1607
1608
1609
1610
1611
1612
1613
1614
1615
1616
1617
1618
1619
1620
1621
1622
1623
1624
1625
1626
1627
1628
1629
1630
1631
1632
1633
1634
1635
1636
1637
1638
1639
1640
1641
1642
1643
1644
1645
1646
1647
1648
1649
1650
1651
1652
1653
1654
1655
1656
1657
1658
1659
1660
1661
1662
1663
1664
1665
1666
1667
1668
1669
1670
1671
1672
1673
1674
1675
1676
1677
1678
1679
1680
1681
1682
1683
1684
1685
1686
1687
1688
1689
1690
1691
1692
1693
1694
1695
1696
1697
1698
1699
1700
1701
1702
1703
1704
1705
1706
1707
1708
1709
1710
1711
1712
1713
1714
1715
1716
1717
1718
1719
1720
1721
1722
1723
1724
1725
1726
1727
1728
1729
1730
1731
1732
1733
1734
1735
1736
1737
1738
1739
1740
1741
1742
1743
1744
1745
1746
1747
1748
1749
1750
1751
1752
1753
1754
1755
1756
1757
1758
1759
1760
1761
1762
1763
1764
1765
1766
1767
1768
1769
1770
1771
1772
1773
1774
1775
1776
1777
1778
1779
1780
1781
1782
1783
1784
1785
1786
1787
1788
1789
1790
1791
1792
1793
1794
1795
1796
1797
1798
1799
1800
1801
1802
1803
1804
1805
1806
1807
1808
1809
1810
1811
1812
1813
1814
1815
1816
1817
1818
1819
1820
1821
1822
1823
1824
1825
1826
1827
1828
1829
1830
1831
1832
1833
1834
1835
1836
1837
1838
1839
1840
1841
1842
1843
1844
1845
1846
1847
1848
1849
1850
1851
1852
1853
1854
1855
1856
1857
1858
1859
1860
1861
1862
1863
1864
1865
1866
1867
1868
1869
1870
1871
1872
1873
1874
1875
1876
1877
1878
1879
1880
1881
1882
1883
1884
1885
1886
1887
1888
1889
1890
1891
1892
1893
1894
1895
1896
1897
1898
1899
1900
1901
1902
1903
1904
1905
1906
1907
1908
1909
1910
1911
1912
1913
1914
1915
1916
1917
1918
1919
1920
1921
1922
1923
1924
1925
1926
1927
1928
1929
1930
1931
1932
1933
1934
1935
1936
1937
1938
1939
1940
1941
1942
1943
1944
1945
1946
1947
1948
1949
1950
1951
1952
1953
1954
1955
1956
1957
1958
1959
1960
1961
1962
1963
1964
1965
1966
1967
1968
1969
1970
1971
1972
1973
1974
1975
1976
1977
1978
1979
1980
1981
1982
1983
1984
1985
1986
1987
1988
1989
1990
1991
1992
1993
1994
1995
1996
1997
1998
1999
2000
2001
2002
2003
2004
2005
2006
2007
2008
2009
2010
2011
2012
2013
2014
2015
2016
2017
2018
2019
2020
2021
2022
2023
2024
2025
2026
2027
2028
2029
2030
2031
2032
2033
2034
2035
2036
2037
2038
2039
2040
2041
2042
2043
2044
2045
2046
2047
2048
2049
2050
2051
2052
2053
2054
2055
2056
2057
2058
2059
2060
2061
2062
2063
2064
2065
2066
2067
2068
2069
2070
2071
2072
2073
2074
2075
2076
2077
2078
2079
2080
2081
2082
2083
2084
2085
2086
2087
2088
2089
2090
2091
2092
2093
2094
2095
2096
2097
2098
2099
2100
2101
2102
2103
2104
2105
2106
2107
2108
2109
2110
2111
2112
2113
2114
2115
2116
2117
2118
2119
2120
2121
2122
2123
2124
2125
2126
2127
2128
2129
2130
2131
2132
2133
2134
2135
2136
2137
2138
2139
2140
2141
2142
2143
2144
2145
2146
2147
2148
2149
2150
2151
2152
2153
2154
2155
2156
2157
2158
2159
2160
2161
2162
2163
2164
2165
2166
2167
2168
2169
2170
2171
2172
2173
2174
2175
2176
2177
2178
2179
2180
2181
2182
2183
2184
2185
2186
2187
2188
2189
2190
2191
2192
2193
2194
2195
2196
2197
2198
2199
2200
2201
2202
2203
2204
2205
2206
2207
2208
2209
2210
2211
2212
2213
2214
2215
2216
2217
2218
2219
2220
2221
2222
2223
2224
2225
2226
2227
2228
2229
2230
2231
2232
2233
2234
2235
2236
2237
2238
2239
2240
2241
2242
2243
2244
2245
2246
2247
2248
2249
2250
2251
2252
2253
2254
2255
2256
2257
2258
2259
2260
2261
2262
2263
2264
2265
2266
2267
2268
2269
2270
2271
2272
2273
2274
2275
2276
2277
2278
2279
2280
2281
2282
2283
2284
2285
2286
2287
2288
2289
2290
2291
2292
2293
2294
2295
2296
2297
2298
2299
2300
2301
2302
2303
2304
2305
2306
2307
2308
2309
2310
2311
2312
2313
2314
2315
2316
2317
2318
2319
2320
2321
2322
2323
2324
2325
2326
2327
2328
2329
2330
2331
2332
2333
2334
2335
2336
2337
2338
2339
2340
2341
2342
2343
2344
2345
2346
2347
2348
2349
2350
2351
2352
2353
2354
2355
2356
2357
2358
2359
2360
2361
2362
2363
2364
2365
2366
2367
2368
2369
2370
2371
2372
2373
2374
2375
2376
2377
2378
2379
2380
2381
2382
2383
2384
2385
2386
2387
2388
2389
2390
2391
2392
2393
2394
2395
2396
2397
2398
2399
2400
2401
2402
2403
2404
2405
2406
2407
2408
2409
2410
2411
2412
2413
2414
2415
2416
2417
2418
2419
2420
2421
2422
2423
2424
2425
2426
2427
2428
2429
2430
2431
2432
2433
2434
2435
2436
2437
2438
2439
2440
2441
2442
2443
2444
2445
2446
2447
2448
2449
2450
2451
2452
2453
2454
2455
2456
2457
2458
2459
2460
2461
2462
2463
2464
2465
2466
2467
2468
2469
2470
2471
2472
2473
2474
2475
2476
2477
2478
2479
2480
2481
2482
2483
2484
2485
2486
2487
2488
2489
2490
2491
2492
2493
2494
2495
2496
2497
2498
2499
2500
2501
2502
2503
2504
2505
2506
2507
2508
2509
2510
2511
2512
2513
2514
2515
2516
2517
2518
2519
2520
2521
2522
2523
2524
2525
2526
2527
2528
2529
2530
2531
2532
2533
2534
2535
2536
2537
2538
2539
2540
2541
2542
2543
2544
2545
2546
2547
2548
2549
2550
2551
2552
2553
2554
2555
2556
2557
2558
2559
2560
2561
2562
2563
2564
2565
2566
2567
2568
2569
2570
2571
2572
2573
2574
2575
2576
2577
2578
2579
2580
2581
2582
2583
2584
2585
2586
2587
2588
2589
2590
2591
2592
2593
2594
2595
2596
2597
2598
2599
2600
2601
2602
2603
2604
2605
2606
2607
2608
2609
2610
2611
2612
2613
2614
2615
2616
2617
2618
2619
2620
2621
2622
2623
2624
2625
2626
2627
2628
2629
2630
2631
2632
2633
2634
2635
2636
2637
2638
2639
2640
2641
2642
2643
2644
2645
2646
2647
2648
2649
2650
2651
2652
2653
2654
2655
2656
2657
2658
2659
2660
2661
2662
2663
2664
2665
2666
2667
2668
2669
2670
2671
2672
2673
2674
2675
2676
2677
2678
2679
2680
2681
2682
2683
2684
2685
2686
2687
2688
2689
2690
2691
2692
2693
2694
2695
2696
2697
2698
2699
2700
2701
2702
2703
2704
2705
2706
2707
2708
2709
2710
2711
2712
2713
2714
2715
2716
2717
2718
2719
2720
2721
2722
2723
2724
2725
2726
2727
2728
2729
2730
2731
2732
2733
2734
2735
2736
2737
2738
2739
2740
2741
2742
2743
2744
2745
2746
2747
2748
2749
2750
2751
2752
2753
2754
2755
2756
2757
2758
2759
2760
2761
2762
2763
2764
2765
2766
2767
2768
2769
2770
2771
2772
2773
2774
2775
2776
2777
2778
2779
2780
2781
2782
2783
2784
2785
2786
2787
2788
2789
2790
2791
2792
2793
2794
2795
2796
2797
2798
2799
2800
2801
2802
2803
2804
2805
2806
2807
2808
2809
2810
2811
2812
2813
2814
2815
2816
2817
2818
2819
2820
2821
2822
2823
2824
2825
2826
2827
2828
2829
2830
2831
2832
2833
2834
2835
2836
2837
2838
2839
2840
2841
2842
2843
2844
2845
2846
2847
2848
2849
2850
2851
2852
2853
2854
2855
2856
2857
2858
2859
2860
2861
2862
2863
2864
2865
2866
2867
2868
2869
2870
2871
2872
2873
2874
2875
2876
2877
2878
2879
2880
2881
2882
2883
2884
2885
2886
2887
2888
2889
2890
2891
2892
2893
2894
2895
2896
2897
2898
2899
2900
2901
2902
2903
2904
2905
2906
2907
2908
2909
2910
2911
2912
2913
2914
2915
2916
2917
2918
2919
2920
2921
2922
2923
2924
2925
2926
2927
2928
2929
2930
2931
2932
2933
2934
2935
2936
2937
2938
2939
2940
2941
2942
2943
2944
2945
2946
2947
2948
2949
2950
2951
2952
2953
2954
2955
2956
2957
2958
2959
2960
2961
2962
2963
2964
2965
2966
2967
2968
2969
2970
2971
2972
2973
2974
2975
2976
2977
2978
2979
2980
2981
2982
2983
2984
2985
2986
2987
2988
2989
2990
2991
2992
2993
2994
2995
2996
2997
2998
2999
3000
3001
3002
3003
3004
3005
3006
3007
3008
3009
3010
3011
3012
3013
3014
3015
3016
3017
3018
3019
3020
3021
3022
3023
3024
3025
3026
3027
3028
3029
3030
3031
3032
3033
3034
3035
3036
3037
3038
3039
3040
3041
3042
3043
3044
3045
3046
3047
3048
3049
3050
3051
3052
3053
3054
3055
3056
3057
3058
3059
3060
3061
3062
3063
3064
3065
3066
3067
3068
3069
3070
3071
3072
3073
3074
3075
3076
3077
3078
3079
3080
3081
3082
3083
3084
3085
3086
3087
3088
3089
3090
3091
3092
3093
3094
3095
3096
3097
3098
3099
3100
3101
3102
3103
3104
3105
3106
3107
3108
3109
3110
3111
3112
3113
3114
3115
3116
3117
3118
3119
3120
3121
3122
3123
3124
3125
3126
3127
3128
3129
3130
3131
3132
3133
3134
3135
3136
3137
3138
3139
3140
3141
3142
3143
3144
3145
3146
3147
3148
3149
3150
3151
3152
3153
3154
3155
3156
3157
3158
3159
3160
3161
3162
3163
3164
3165
3166
3167
3168
3169
3170
3171
3172
3173
3174
3175
3176
3177
3178
3179
3180
3181
3182
3183
3184
3185
3186
3187
3188
3189
3190
3191
3192
3193
3194
3195
3196
3197
3198
3199
3200
3201
3202
3203
3204
3205
3206
3207
3208
3209
3210
3211
3212
3213
3214
3215
3216
3217
3218
3219
3220
3221
3222
3223
3224
3225
3226
3227
3228
3229
3230
3231
3232
3233
3234
3235
3236
3237
3238
3239
3240
3241
3242
3243
3244
3245
3246
3247
3248
3249
3250
3251
3252
3253
3254
3255
3256
3257
3258
3259
3260
3261
3262
3263
3264
3265
3266
3267
3268
3269
3270
3271
3272
3273
3274
3275
3276
3277
3278
3279
3280
3281
3282
3283
3284
3285
3286
3287
3288
3289
3290
3291
3292
3293
3294
3295
3296
3297
3298
3299
3300
3301
3302
3303
3304
3305
3306
3307
3308
3309
3310
3311
3312
3313
3314
3315
3316
3317
3318
3319
3320
3321
3322
3323
3324
3325
3326
3327
3328
3329
3330
3331
3332
3333
3334
3335
3336
3337
3338
3339
3340
3341
3342
3343
3344
3345
3346
3347
3348
3349
3350
3351
3352
3353
3354
3355
3356
3357
3358
3359
3360
3361
3362
3363
3364
3365
3366
3367
3368
3369
3370
3371
3372
3373
3374
3375
3376
3377
3378
3379
3380
3381
3382
3383
3384
3385
3386
3387
3388
3389
3390
3391
3392
3393
3394
3395
3396
3397
3398
3399
3400
3401
3402
3403
3404
3405
3406
3407
3408
3409
3410
3411
3412
3413
3414
3415
3416
3417
3418
3419
3420
3421
3422
3423
3424
3425
3426
3427
3428
3429
3430
3431
3432
3433
3434
3435
3436
3437
3438
3439
3440
3441
3442
3443
3444
3445
3446
3447
3448
3449
3450
3451
3452
3453
3454
3455
3456
3457
3458
3459
3460
3461
3462
3463
3464
3465
3466
3467
3468
3469
3470
3471
3472
3473
3474
3475
3476
3477
3478
3479
3480
3481
3482
3483
3484
3485
3486
3487
3488
3489
3490
3491
3492
3493
3494
3495
3496
3497
3498
3499
3500
3501
3502
3503
3504
3505
3506
3507
3508
3509
3510
3511
3512
3513
3514
3515
3516
3517
3518
3519
3520
3521
3522
3523
3524
3525
3526
3527
3528
3529
3530
3531
3532
3533
3534
3535
3536
3537
3538
3539
3540
3541
3542
3543
3544
3545
3546
3547
3548
3549
3550
3551
3552
3553
3554
3555
3556
3557
3558
3559
3560
3561
3562
3563
3564
3565
3566
3567
3568
3569
3570
3571
3572
3573
3574
3575
3576
3577
3578
3579
3580
3581
3582
3583
3584
3585
3586
3587
3588
3589
3590
3591
3592
3593
3594
3595
3596
3597
3598
3599
3600
3601
3602
3603
3604
3605
3606
3607
3608
3609
3610
3611
3612
3613
3614
3615
3616
3617
3618
3619
3620
3621
3622
3623
3624
3625
3626
3627
3628
3629
3630
3631
3632
3633
3634
3635
3636
3637
3638
3639
3640
3641
3642
3643
3644
3645
3646
3647
3648
3649
3650
3651
3652
3653
3654
3655
3656
3657
3658
3659
3660
3661
3662
3663
3664
3665
3666
3667
3668
3669
3670
3671
3672
3673
3674
3675
3676
3677
3678
3679
3680
3681
3682
3683
3684
3685
3686
3687
3688
3689
3690
3691
3692
3693
3694
3695
3696
3697
3698
3699
3700
3701
3702
3703
3704
3705
3706
3707
3708
3709
3710
3711
3712
3713
3714
3715
3716
3717
3718
3719
3720
3721
3722
3723
3724
3725
3726
3727
3728
3729
3730
3731
3732
3733
3734
3735
3736
3737
3738
3739
3740
3741
3742
3743
3744
3745
3746
3747
3748
3749
3750
3751
3752
3753
3754
3755
3756
3757
3758
3759
3760
3761
3762
3763
3764
3765
3766
3767
3768
3769
3770
3771
3772
3773
3774
3775
3776
3777
3778
3779
3780
3781
3782
3783
3784
3785
3786
3787
3788
3789
3790
3791
3792
3793
3794
3795
3796
3797
3798
3799
3800
3801
3802
3803
3804
3805
3806
3807
3808
3809
3810
3811
3812
3813
3814
3815
3816
3817
3818
3819
3820
3821
3822
3823
3824
3825
3826
3827
3828
3829
3830
3831
3832
3833
3834
3835
3836
3837
3838
3839
3840
3841
3842
3843
3844
3845
3846
3847
3848
3849
3850
3851
3852
3853
3854
3855
3856
3857
3858
3859
3860
3861
3862
3863
3864
3865
3866
3867
3868
3869
3870
3871
3872
3873
3874
3875
3876
3877
3878
3879
3880
3881
3882
3883
3884
3885
3886
3887
3888
3889
3890
3891
3892
3893
3894
3895
3896
3897
3898
3899
3900
3901
3902
3903
3904
3905
3906
3907
3908
3909
3910
3911
3912
3913
3914
3915
3916
3917
3918
3919
3920
3921
3922
3923
3924
3925
3926
3927
3928
3929
3930
3931
3932
3933
3934
3935
3936
3937
3938
3939
3940
3941
3942
3943
3944
3945
3946
3947
3948
3949
3950
3951
3952
3953
3954
3955
3956
3957
3958
3959
3960
3961
3962
3963
3964
3965
3966
3967
3968
3969
3970
3971
3972
3973
3974
3975
3976
3977
3978
3979
3980
3981
3982
3983
3984
3985
3986
3987
3988
3989
3990
3991
3992
3993
3994
3995
3996
3997
3998
3999
4000
4001
4002
4003
4004
4005
4006
4007
4008
4009
4010
4011
4012
4013
4014
4015
4016
4017
4018
4019
4020
4021
4022
4023
4024
4025
4026
4027
4028
4029
4030
4031
4032
4033
4034
4035
4036
4037
4038
4039
4040
4041
4042
4043
4044
4045
4046
4047
4048
4049
4050
4051
4052
4053
4054
4055
4056
4057
4058
4059
4060
4061
4062
4063
4064
4065
4066
4067
4068
4069
4070
4071
4072
4073
4074
4075
4076
4077
4078
4079
4080
4081
4082
4083
4084
4085
4086
4087
4088
4089
4090
4091
4092
4093
4094
4095
4096
4097
4098
4099
4100
4101
4102
4103
4104
4105
4106
4107
4108
4109
4110
4111
4112
4113
4114
4115
4116
4117
4118
4119
4120
4121
4122
4123
4124
4125
4126
4127
4128
4129
4130
4131
4132
4133
4134
4135
4136
4137
4138
4139
4140
4141
4142
4143
4144
4145
4146
4147
4148
4149
4150
4151
4152
4153
4154
4155
4156
4157
4158
4159
4160
4161
4162
4163
4164
4165
4166
4167
4168
4169
4170
4171
4172
4173
4174
4175
4176
4177
4178
4179
4180
4181
4182
4183
4184
4185
4186
4187
4188
4189
4190
4191
4192
4193
4194
4195
4196
4197
4198
4199
4200
4201
4202
4203
4204
4205
4206
4207
4208
4209
4210
4211
4212
4213
4214
4215
4216
4217
4218
4219
4220
4221
4222
4223
4224
4225
4226
4227
4228
4229
4230
4231
4232
4233
4234
4235
4236
4237
4238
4239
4240
4241
4242
4243
4244
4245
4246
4247
4248
4249
4250
4251
4252
4253
4254
4255
4256
4257
4258
4259
4260
4261
4262
4263
4264
4265
4266
4267
4268
4269
4270
4271
4272
4273
4274
4275
4276
4277
4278
4279
4280
4281
4282
4283
4284
4285
4286
4287
4288
4289
4290
4291
4292
4293
4294
4295
4296
4297
4298
4299
4300
4301
4302
4303
4304
4305
4306
4307
4308
4309
4310
4311
4312
4313
4314
4315
4316
4317
4318
4319
4320
4321
4322
4323
4324
4325
4326
4327
4328
4329
4330
4331
4332
4333
4334
4335
4336
4337
4338
4339
4340
4341
4342
4343
4344
4345
4346
4347
4348
4349
4350
4351
4352
4353
4354
4355
4356
4357
4358
4359
4360
4361
4362
4363
4364
4365
4366
4367
4368
4369
4370
4371
4372
4373
4374
4375
4376
4377
4378
4379
4380
4381
4382
4383
4384
4385
4386
4387
4388
4389
4390
4391
4392
4393
4394
4395
4396
4397
4398
4399
4400
4401
4402
4403
4404
4405
4406
4407
4408
4409
4410
4411
4412
4413
4414
4415
4416
4417
4418
4419
4420
4421
4422
4423
4424
4425
4426
4427
4428
4429
4430
4431
4432
4433
4434
4435
4436
4437
4438
4439
4440
4441
4442
4443
4444
4445
4446
4447
4448
4449
4450
4451
4452
4453
4454
4455
4456
4457
4458
4459
4460
4461
4462
4463
4464
4465
4466
4467
4468
4469
4470
4471
4472
4473
4474
4475
4476
4477
4478
4479
4480
4481
4482
4483
4484
4485
4486
4487
4488
4489
4490
4491
4492
4493
4494
4495
4496
4497
4498
4499
4500
4501
4502
4503
4504
4505
4506
4507
4508
4509
4510
4511
4512
4513
4514
4515
4516
4517
4518
4519
4520
4521
4522
4523
4524
4525
4526
4527
4528
4529
4530
4531
4532
4533
4534
4535
4536
4537
4538
4539
4540
4541
4542
4543
4544
4545
4546
4547
4548
4549
4550
4551
4552
4553
4554
4555
4556
4557
4558
4559
4560
4561
4562
4563
4564
4565
4566
4567
4568
4569
4570
4571
4572
4573
4574
4575
4576
4577
4578
4579
4580
4581
4582
4583
4584
4585
4586
4587
4588
4589
4590
4591
4592
4593
4594
4595
4596
4597
4598
4599
4600
4601
4602
4603
4604
4605
4606
4607
4608
4609
4610
4611
4612
4613
4614
4615
4616
4617
4618
4619
4620
4621
4622
4623
4624
4625
4626
4627
4628
4629
4630
4631
4632
4633
4634
4635
4636
4637
4638
4639
4640
4641
4642
4643
4644
4645
4646
4647
4648
4649
4650
4651
4652
4653
4654
4655
4656
4657
4658
4659
4660
4661
4662
4663
4664
4665
4666
4667
4668
4669
4670
4671
4672
4673
4674
4675
4676
4677
4678
4679
4680
4681
4682
4683
4684
4685
4686
4687
4688
4689
4690
4691
4692
4693
4694
4695
4696
4697
4698
4699
4700
4701
4702
4703
4704
4705
4706
4707
4708
4709
4710
4711
4712
4713
4714
4715
4716
4717
4718
4719
4720
4721
4722
4723
4724
4725
4726
4727
4728
4729
4730
4731
4732
4733
4734
4735
4736
4737
4738
4739
4740
4741
4742
4743
4744
4745
4746
4747
4748
4749
4750
4751
4752
4753
4754
4755
4756
4757
4758
4759
4760
4761
4762
4763
4764
4765
4766
4767
4768
4769
4770
/* SPDX-License-Identifier: GPL-2.0 */
/*
 * fs/f2fs/f2fs.h
 *
 * Copyright (c) 2012 Samsung Electronics Co., Ltd.
 *             http://www.samsung.com/
 */
#ifndef _LINUX_F2FS_H
#define _LINUX_F2FS_H

#include <linux/uio.h>
#include <linux/types.h>
#include <linux/page-flags.h>
#include <linux/slab.h>
#include <linux/crc32.h>
#include <linux/magic.h>
#include <linux/kobject.h>
#include <linux/sched.h>
#include <linux/cred.h>
#include <linux/sched/mm.h>
#include <linux/vmalloc.h>
#include <linux/bio.h>
#include <linux/blkdev.h>
#include <linux/quotaops.h>
#include <linux/part_stat.h>
#include <linux/rw_hint.h>
#include <crypto/hash.h>

#include <linux/fscrypt.h>
#include <linux/fsverity.h>

struct pagevec;

#ifdef CONFIG_F2FS_CHECK_FS
#define f2fs_bug_on(sbi, condition)        BUG_ON(condition)
#else
#define f2fs_bug_on(sbi, condition)                                        \
        do {                                                                \
                if (WARN_ON(condition))                                        \
                        set_sbi_flag(sbi, SBI_NEED_FSCK);                \
        } while (0)
#endif

enum {
        FAULT_KMALLOC,
        FAULT_KVMALLOC,
        FAULT_PAGE_ALLOC,
        FAULT_PAGE_GET,
        FAULT_ALLOC_BIO,        /* it's obsolete due to bio_alloc() will never fail */
        FAULT_ALLOC_NID,
        FAULT_ORPHAN,
        FAULT_BLOCK,
        FAULT_DIR_DEPTH,
        FAULT_EVICT_INODE,
        FAULT_TRUNCATE,
        FAULT_READ_IO,
        FAULT_CHECKPOINT,
        FAULT_DISCARD,
        FAULT_WRITE_IO,
        FAULT_SLAB_ALLOC,
        FAULT_DQUOT_INIT,
        FAULT_LOCK_OP,
        FAULT_BLKADDR_VALIDITY,
        FAULT_BLKADDR_CONSISTENCE,
        FAULT_NO_SEGMENT,
        FAULT_MAX,
};

#ifdef CONFIG_F2FS_FAULT_INJECTION
#define F2FS_ALL_FAULT_TYPE                (GENMASK(FAULT_MAX - 1, 0))

struct f2fs_fault_info {
        atomic_t inject_ops;
        int inject_rate;
        unsigned int inject_type;
};

extern const char *f2fs_fault_name[FAULT_MAX];
#define IS_FAULT_SET(fi, type) ((fi)->inject_type & BIT(type))

/* maximum retry count for injected failure */
#define DEFAULT_FAILURE_RETRY_COUNT                8
#else
#define DEFAULT_FAILURE_RETRY_COUNT                1
#endif

/*
 * For mount options
 */
#define F2FS_MOUNT_DISABLE_ROLL_FORWARD        0x00000001
#define F2FS_MOUNT_DISCARD                0x00000002
#define F2FS_MOUNT_NOHEAP                0x00000004
#define F2FS_MOUNT_XATTR_USER                0x00000008
#define F2FS_MOUNT_POSIX_ACL                0x00000010
#define F2FS_MOUNT_DISABLE_EXT_IDENTIFY        0x00000020
#define F2FS_MOUNT_INLINE_XATTR                0x00000040
#define F2FS_MOUNT_INLINE_DATA                0x00000080
#define F2FS_MOUNT_INLINE_DENTRY        0x00000100
#define F2FS_MOUNT_FLUSH_MERGE                0x00000200
#define F2FS_MOUNT_NOBARRIER                0x00000400
#define F2FS_MOUNT_FASTBOOT                0x00000800
#define F2FS_MOUNT_READ_EXTENT_CACHE        0x00001000
#define F2FS_MOUNT_DATA_FLUSH                0x00002000
#define F2FS_MOUNT_FAULT_INJECTION        0x00004000
#define F2FS_MOUNT_USRQUOTA                0x00008000
#define F2FS_MOUNT_GRPQUOTA                0x00010000
#define F2FS_MOUNT_PRJQUOTA                0x00020000
#define F2FS_MOUNT_QUOTA                0x00040000
#define F2FS_MOUNT_INLINE_XATTR_SIZE        0x00080000
#define F2FS_MOUNT_RESERVE_ROOT                0x00100000
#define F2FS_MOUNT_DISABLE_CHECKPOINT        0x00200000
#define F2FS_MOUNT_NORECOVERY                0x00400000
#define F2FS_MOUNT_ATGC                        0x00800000
#define F2FS_MOUNT_MERGE_CHECKPOINT        0x01000000
#define        F2FS_MOUNT_GC_MERGE                0x02000000
#define F2FS_MOUNT_COMPRESS_CACHE        0x04000000
#define F2FS_MOUNT_AGE_EXTENT_CACHE        0x08000000

#define F2FS_OPTION(sbi)        ((sbi)->mount_opt)
#define clear_opt(sbi, option)        (F2FS_OPTION(sbi).opt &= ~F2FS_MOUNT_##option)
#define set_opt(sbi, option)        (F2FS_OPTION(sbi).opt |= F2FS_MOUNT_##option)
#define test_opt(sbi, option)        (F2FS_OPTION(sbi).opt & F2FS_MOUNT_##option)

#define ver_after(a, b)        (typecheck(unsigned long long, a) &&                \
                typecheck(unsigned long long, b) &&                        \
                ((long long)((a) - (b)) > 0))

typedef u32 block_t;        /*
                         * should not change u32, since it is the on-disk block
                         * address format, __le32.
                         */
typedef u32 nid_t;

#define COMPRESS_EXT_NUM                16

enum blkzone_allocation_policy {
        BLKZONE_ALLOC_PRIOR_SEQ,        /* Prioritize writing to sequential zones */
        BLKZONE_ALLOC_ONLY_SEQ,                /* Only allow writing to sequential zones */
        BLKZONE_ALLOC_PRIOR_CONV,        /* Prioritize writing to conventional zones */
};

/*
 * An implementation of an rwsem that is explicitly unfair to readers. This
 * prevents priority inversion when a low-priority reader acquires the read lock
 * while sleeping on the write lock but the write lock is needed by
 * higher-priority clients.
 */

struct f2fs_rwsem {
        struct rw_semaphore internal_rwsem;
#ifdef CONFIG_F2FS_UNFAIR_RWSEM
        wait_queue_head_t read_waiters;
#endif
};

struct f2fs_mount_info {
        unsigned int opt;
        block_t root_reserved_blocks;        /* root reserved blocks */
        kuid_t s_resuid;                /* reserved blocks for uid */
        kgid_t s_resgid;                /* reserved blocks for gid */
        int active_logs;                /* # of active logs */
        int inline_xattr_size;                /* inline xattr size */
#ifdef CONFIG_F2FS_FAULT_INJECTION
        struct f2fs_fault_info fault_info;        /* For fault injection */
#endif
#ifdef CONFIG_QUOTA
        /* Names of quota files with journalled quota */
        char *s_qf_names[MAXQUOTAS];
        int s_jquota_fmt;                        /* Format of quota to use */
#endif
        /* For which write hints are passed down to block layer */
        int alloc_mode;                        /* segment allocation policy */
        int fsync_mode;                        /* fsync policy */
        int fs_mode;                        /* fs mode: LFS or ADAPTIVE */
        int bggc_mode;                        /* bggc mode: off, on or sync */
        int memory_mode;                /* memory mode */
        int errors;                        /* errors parameter */
        int discard_unit;                /*
                                         * discard command's offset/size should
                                         * be aligned to this unit: block,
                                         * segment or section
                                         */
        struct fscrypt_dummy_policy dummy_enc_policy; /* test dummy encryption */
        block_t unusable_cap_perc;        /* percentage for cap */
        block_t unusable_cap;                /* Amount of space allowed to be
                                         * unusable when disabling checkpoint
                                         */

        /* For compression */
        unsigned char compress_algorithm;        /* algorithm type */
        unsigned char compress_log_size;        /* cluster log size */
        unsigned char compress_level;                /* compress level */
        bool compress_chksum;                        /* compressed data chksum */
        unsigned char compress_ext_cnt;                /* extension count */
        unsigned char nocompress_ext_cnt;                /* nocompress extension count */
        int compress_mode;                        /* compression mode */
        unsigned char extensions[COMPRESS_EXT_NUM][F2FS_EXTENSION_LEN];        /* extensions */
        unsigned char noextensions[COMPRESS_EXT_NUM][F2FS_EXTENSION_LEN]; /* extensions */
};

#define F2FS_FEATURE_ENCRYPT                        0x00000001
#define F2FS_FEATURE_BLKZONED                        0x00000002
#define F2FS_FEATURE_ATOMIC_WRITE                0x00000004
#define F2FS_FEATURE_EXTRA_ATTR                        0x00000008
#define F2FS_FEATURE_PRJQUOTA                        0x00000010
#define F2FS_FEATURE_INODE_CHKSUM                0x00000020
#define F2FS_FEATURE_FLEXIBLE_INLINE_XATTR        0x00000040
#define F2FS_FEATURE_QUOTA_INO                        0x00000080
#define F2FS_FEATURE_INODE_CRTIME                0x00000100
#define F2FS_FEATURE_LOST_FOUND                        0x00000200
#define F2FS_FEATURE_VERITY                        0x00000400
#define F2FS_FEATURE_SB_CHKSUM                        0x00000800
#define F2FS_FEATURE_CASEFOLD                        0x00001000
#define F2FS_FEATURE_COMPRESSION                0x00002000
#define F2FS_FEATURE_RO                                0x00004000
#define F2FS_FEATURE_DEVICE_ALIAS                0x00008000

#define __F2FS_HAS_FEATURE(raw_super, mask)                                \
        ((raw_super->feature & cpu_to_le32(mask)) != 0)
#define F2FS_HAS_FEATURE(sbi, mask)        __F2FS_HAS_FEATURE(sbi->raw_super, mask)

/*
 * Default values for user and/or group using reserved blocks
 */
#define        F2FS_DEF_RESUID                0
#define        F2FS_DEF_RESGID                0

/*
 * For checkpoint manager
 */
enum {
        NAT_BITMAP,
        SIT_BITMAP
};

#define        CP_UMOUNT        0x00000001
#define        CP_FASTBOOT        0x00000002
#define        CP_SYNC                0x00000004
#define        CP_RECOVERY        0x00000008
#define        CP_DISCARD        0x00000010
#define CP_TRIMMED        0x00000020
#define CP_PAUSE        0x00000040
#define CP_RESIZE         0x00000080

#define DEF_MAX_DISCARD_REQUEST                8        /* issue 8 discards per round */
#define DEF_MIN_DISCARD_ISSUE_TIME        50        /* 50 ms, if exists */
#define DEF_MID_DISCARD_ISSUE_TIME        500        /* 500 ms, if device busy */
#define DEF_MAX_DISCARD_ISSUE_TIME        60000        /* 60 s, if no candidates */
#define DEF_DISCARD_URGENT_UTIL                80        /* do more discard over 80% */
#define DEF_CP_INTERVAL                        60        /* 60 secs */
#define DEF_IDLE_INTERVAL                5        /* 5 secs */
#define DEF_DISABLE_INTERVAL                5        /* 5 secs */
#define DEF_DISABLE_QUICK_INTERVAL        1        /* 1 secs */
#define DEF_UMOUNT_DISCARD_TIMEOUT        5        /* 5 secs */

struct cp_control {
        int reason;
        __u64 trim_start;
        __u64 trim_end;
        __u64 trim_minlen;
};

/*
 * indicate meta/data type
 */
enum {
        META_CP,
        META_NAT,
        META_SIT,
        META_SSA,
        META_MAX,
        META_POR,
        DATA_GENERIC,                /* check range only */
        DATA_GENERIC_ENHANCE,        /* strong check on range and segment bitmap */
        DATA_GENERIC_ENHANCE_READ,        /*
                                         * strong check on range and segment
                                         * bitmap but no warning due to race
                                         * condition of read on truncated area
                                         * by extent_cache
                                         */
        DATA_GENERIC_ENHANCE_UPDATE,        /*
                                         * strong check on range and segment
                                         * bitmap for update case
                                         */
        META_GENERIC,
};

/* for the list of ino */
enum {
        ORPHAN_INO,                /* for orphan ino list */
        APPEND_INO,                /* for append ino list */
        UPDATE_INO,                /* for update ino list */
        TRANS_DIR_INO,                /* for transactions dir ino list */
        XATTR_DIR_INO,                /* for xattr updated dir ino list */
        FLUSH_INO,                /* for multiple device flushing */
        MAX_INO_ENTRY,                /* max. list */
};

struct ino_entry {
        struct list_head list;                /* list head */
        nid_t ino;                        /* inode number */
        unsigned int dirty_device;        /* dirty device bitmap */
};

/* for the list of inodes to be GCed */
struct inode_entry {
        struct list_head list;        /* list head */
        struct inode *inode;        /* vfs inode pointer */
};

struct fsync_node_entry {
        struct list_head list;        /* list head */
        struct page *page;        /* warm node page pointer */
        unsigned int seq_id;        /* sequence id */
};

struct ckpt_req {
        struct completion wait;                /* completion for checkpoint done */
        struct llist_node llnode;        /* llist_node to be linked in wait queue */
        int ret;                        /* return code of checkpoint */
        ktime_t queue_time;                /* request queued time */
};

struct ckpt_req_control {
        struct task_struct *f2fs_issue_ckpt;        /* checkpoint task */
        int ckpt_thread_ioprio;                        /* checkpoint merge thread ioprio */
        wait_queue_head_t ckpt_wait_queue;        /* waiting queue for wake-up */
        atomic_t issued_ckpt;                /* # of actually issued ckpts */
        atomic_t total_ckpt;                /* # of total ckpts */
        atomic_t queued_ckpt;                /* # of queued ckpts */
        struct llist_head issue_list;        /* list for command issue */
        spinlock_t stat_lock;                /* lock for below checkpoint time stats */
        unsigned int cur_time;                /* cur wait time in msec for currently issued checkpoint */
        unsigned int peak_time;                /* peak wait time in msec until now */
};

/* for the bitmap indicate blocks to be discarded */
struct discard_entry {
        struct list_head list;        /* list head */
        block_t start_blkaddr;        /* start blockaddr of current segment */
        unsigned char discard_map[SIT_VBLOCK_MAP_SIZE];        /* segment discard bitmap */
};

/* minimum discard granularity, unit: block count */
#define MIN_DISCARD_GRANULARITY                1
/* default discard granularity of inner discard thread, unit: block count */
#define DEFAULT_DISCARD_GRANULARITY                16
/* default maximum discard granularity of ordered discard, unit: block count */
#define DEFAULT_MAX_ORDERED_DISCARD_GRANULARITY        16

/* max discard pend list number */
#define MAX_PLIST_NUM                512
#define plist_idx(blk_num)        ((blk_num) >= MAX_PLIST_NUM ?                \
                                        (MAX_PLIST_NUM - 1) : ((blk_num) - 1))

enum {
        D_PREP,                        /* initial */
        D_PARTIAL,                /* partially submitted */
        D_SUBMIT,                /* all submitted */
        D_DONE,                        /* finished */
};

struct discard_info {
        block_t lstart;                        /* logical start address */
        block_t len;                        /* length */
        block_t start;                        /* actual start address in dev */
};

struct discard_cmd {
        struct rb_node rb_node;                /* rb node located in rb-tree */
        struct discard_info di;                /* discard info */
        struct list_head list;                /* command list */
        struct completion wait;                /* compleation */
        struct block_device *bdev;        /* bdev */
        unsigned short ref;                /* reference count */
        unsigned char state;                /* state */
        unsigned char queued;                /* queued discard */
        int error;                        /* bio error */
        spinlock_t lock;                /* for state/bio_ref updating */
        unsigned short bio_ref;                /* bio reference count */
};

enum {
        DPOLICY_BG,
        DPOLICY_FORCE,
        DPOLICY_FSTRIM,
        DPOLICY_UMOUNT,
        MAX_DPOLICY,
};

enum {
        DPOLICY_IO_AWARE_DISABLE,        /* force to not be aware of IO */
        DPOLICY_IO_AWARE_ENABLE,        /* force to be aware of IO */
        DPOLICY_IO_AWARE_MAX,
};

struct discard_policy {
        int type;                        /* type of discard */
        unsigned int min_interval;        /* used for candidates exist */
        unsigned int mid_interval;        /* used for device busy */
        unsigned int max_interval;        /* used for candidates not exist */
        unsigned int max_requests;        /* # of discards issued per round */
        unsigned int io_aware_gran;        /* minimum granularity discard not be aware of I/O */
        bool io_aware;                        /* issue discard in idle time */
        bool sync;                        /* submit discard with REQ_SYNC flag */
        bool ordered;                        /* issue discard by lba order */
        bool timeout;                        /* discard timeout for put_super */
        unsigned int granularity;        /* discard granularity */
};

struct discard_cmd_control {
        struct task_struct *f2fs_issue_discard;        /* discard thread */
        struct list_head entry_list;                /* 4KB discard entry list */
        struct list_head pend_list[MAX_PLIST_NUM];/* store pending entries */
        struct list_head wait_list;                /* store on-flushing entries */
        struct list_head fstrim_list;                /* in-flight discard from fstrim */
        wait_queue_head_t discard_wait_queue;        /* waiting queue for wake-up */
        struct mutex cmd_lock;
        unsigned int nr_discards;                /* # of discards in the list */
        unsigned int max_discards;                /* max. discards to be issued */
        unsigned int max_discard_request;        /* max. discard request per round */
        unsigned int min_discard_issue_time;        /* min. interval between discard issue */
        unsigned int mid_discard_issue_time;        /* mid. interval between discard issue */
        unsigned int max_discard_issue_time;        /* max. interval between discard issue */
        unsigned int discard_io_aware_gran; /* minimum discard granularity not be aware of I/O */
        unsigned int discard_urgent_util;        /* utilization which issue discard proactively */
        unsigned int discard_granularity;        /* discard granularity */
        unsigned int max_ordered_discard;        /* maximum discard granularity issued by lba order */
        unsigned int discard_io_aware;                /* io_aware policy */
        unsigned int undiscard_blks;                /* # of undiscard blocks */
        unsigned int next_pos;                        /* next discard position */
        atomic_t issued_discard;                /* # of issued discard */
        atomic_t queued_discard;                /* # of queued discard */
        atomic_t discard_cmd_cnt;                /* # of cached cmd count */
        struct rb_root_cached root;                /* root of discard rb-tree */
        bool rbtree_check;                        /* config for consistence check */
        bool discard_wake;                        /* to wake up discard thread */
};

/* for the list of fsync inodes, used only during recovery */
struct fsync_inode_entry {
        struct list_head list;        /* list head */
        struct inode *inode;        /* vfs inode pointer */
        block_t blkaddr;        /* block address locating the last fsync */
        block_t last_dentry;        /* block address locating the last dentry */
};

#define nats_in_cursum(jnl)                (le16_to_cpu((jnl)->n_nats))
#define sits_in_cursum(jnl)                (le16_to_cpu((jnl)->n_sits))

#define nat_in_journal(jnl, i)                ((jnl)->nat_j.entries[i].ne)
#define nid_in_journal(jnl, i)                ((jnl)->nat_j.entries[i].nid)
#define sit_in_journal(jnl, i)                ((jnl)->sit_j.entries[i].se)
#define segno_in_journal(jnl, i)        ((jnl)->sit_j.entries[i].segno)

#define MAX_NAT_JENTRIES(jnl)        (NAT_JOURNAL_ENTRIES - nats_in_cursum(jnl))
#define MAX_SIT_JENTRIES(jnl)        (SIT_JOURNAL_ENTRIES - sits_in_cursum(jnl))

static inline int update_nats_in_cursum(struct f2fs_journal *journal, int i)
{
        int before = nats_in_cursum(journal);

        journal->n_nats = cpu_to_le16(before + i);
        return before;
}

static inline int update_sits_in_cursum(struct f2fs_journal *journal, int i)
{
        int before = sits_in_cursum(journal);

        journal->n_sits = cpu_to_le16(before + i);
        return before;
}

static inline bool __has_cursum_space(struct f2fs_journal *journal,
                                                        int size, int type)
{
        if (type == NAT_JOURNAL)
                return size <= MAX_NAT_JENTRIES(journal);
        return size <= MAX_SIT_JENTRIES(journal);
}

/* for inline stuff */
#define DEF_INLINE_RESERVED_SIZE        1
static inline int get_extra_isize(struct inode *inode);
static inline int get_inline_xattr_addrs(struct inode *inode);
#define MAX_INLINE_DATA(inode)        (sizeof(__le32) *                        \
                                (CUR_ADDRS_PER_INODE(inode) -                \
                                get_inline_xattr_addrs(inode) -        \
                                DEF_INLINE_RESERVED_SIZE))

/* for inline dir */
#define NR_INLINE_DENTRY(inode)        (MAX_INLINE_DATA(inode) * BITS_PER_BYTE / \
                                ((SIZE_OF_DIR_ENTRY + F2FS_SLOT_LEN) * \
                                BITS_PER_BYTE + 1))
#define INLINE_DENTRY_BITMAP_SIZE(inode) \
        DIV_ROUND_UP(NR_INLINE_DENTRY(inode), BITS_PER_BYTE)
#define INLINE_RESERVED_SIZE(inode)        (MAX_INLINE_DATA(inode) - \
                                ((SIZE_OF_DIR_ENTRY + F2FS_SLOT_LEN) * \
                                NR_INLINE_DENTRY(inode) + \
                                INLINE_DENTRY_BITMAP_SIZE(inode)))

/*
 * For INODE and NODE manager
 */
/* for directory operations */

struct f2fs_filename {
        /*
         * The filename the user specified.  This is NULL for some
         * filesystem-internal operations, e.g. converting an inline directory
         * to a non-inline one, or roll-forward recovering an encrypted dentry.
         */
        const struct qstr *usr_fname;

        /*
         * The on-disk filename.  For encrypted directories, this is encrypted.
         * This may be NULL for lookups in an encrypted dir without the key.
         */
        struct fscrypt_str disk_name;

        /* The dirhash of this filename */
        f2fs_hash_t hash;

#ifdef CONFIG_FS_ENCRYPTION
        /*
         * For lookups in encrypted directories: either the buffer backing
         * disk_name, or a buffer that holds the decoded no-key name.
         */
        struct fscrypt_str crypto_buf;
#endif
#if IS_ENABLED(CONFIG_UNICODE)
        /*
         * For casefolded directories: the casefolded name, but it's left NULL
         * if the original name is not valid Unicode, if the original name is
         * "." or "..", if the directory is both casefolded and encrypted and
         * its encryption key is unavailable, or if the filesystem is doing an
         * internal operation where usr_fname is also NULL.  In all these cases
         * we fall back to treating the name as an opaque byte sequence.
         */
        struct qstr cf_name;
#endif
};

struct f2fs_dentry_ptr {
        struct inode *inode;
        void *bitmap;
        struct f2fs_dir_entry *dentry;
        __u8 (*filename)[F2FS_SLOT_LEN];
        int max;
        int nr_bitmap;
};

static inline void make_dentry_ptr_block(struct inode *inode,
                struct f2fs_dentry_ptr *d, struct f2fs_dentry_block *t)
{
        d->inode = inode;
        d->max = NR_DENTRY_IN_BLOCK;
        d->nr_bitmap = SIZE_OF_DENTRY_BITMAP;
        d->bitmap = t->dentry_bitmap;
        d->dentry = t->dentry;
        d->filename = t->filename;
}

static inline void make_dentry_ptr_inline(struct inode *inode,
                                        struct f2fs_dentry_ptr *d, void *t)
{
        int entry_cnt = NR_INLINE_DENTRY(inode);
        int bitmap_size = INLINE_DENTRY_BITMAP_SIZE(inode);
        int reserved_size = INLINE_RESERVED_SIZE(inode);

        d->inode = inode;
        d->max = entry_cnt;
        d->nr_bitmap = bitmap_size;
        d->bitmap = t;
        d->dentry = t + bitmap_size + reserved_size;
        d->filename = t + bitmap_size + reserved_size +
                                        SIZE_OF_DIR_ENTRY * entry_cnt;
}

/*
 * XATTR_NODE_OFFSET stores xattrs to one node block per file keeping -1
 * as its node offset to distinguish from index node blocks.
 * But some bits are used to mark the node block.
 */
#define XATTR_NODE_OFFSET        ((((unsigned int)-1) << OFFSET_BIT_SHIFT) \
                                >> OFFSET_BIT_SHIFT)
enum {
        ALLOC_NODE,                        /* allocate a new node page if needed */
        LOOKUP_NODE,                        /* look up a node without readahead */
        LOOKUP_NODE_RA,                        /*
                                         * look up a node with readahead called
                                         * by get_data_block.
                                         */
};

#define DEFAULT_RETRY_IO_COUNT        8        /* maximum retry read IO or flush count */

/* congestion wait timeout value, default: 20ms */
#define        DEFAULT_IO_TIMEOUT        (msecs_to_jiffies(20))

/* maximum retry quota flush count */
#define DEFAULT_RETRY_QUOTA_FLUSH_COUNT                8

/* maximum retry of EIO'ed page */
#define MAX_RETRY_PAGE_EIO                        100

#define F2FS_LINK_MAX        0xffffffff        /* maximum link count per file */

#define MAX_DIR_RA_PAGES        4        /* maximum ra pages of dir */

/* dirty segments threshold for triggering CP */
#define DEFAULT_DIRTY_THRESHOLD                4

#define RECOVERY_MAX_RA_BLOCKS                BIO_MAX_VECS
#define RECOVERY_MIN_RA_BLOCKS                1

#define F2FS_ONSTACK_PAGES        16        /* nr of onstack pages */

/* for in-memory extent cache entry */
#define F2FS_MIN_EXTENT_LEN        64        /* minimum extent length */

/* number of extent info in extent cache we try to shrink */
#define READ_EXTENT_CACHE_SHRINK_NUMBER        128

/* number of age extent info in extent cache we try to shrink */
#define AGE_EXTENT_CACHE_SHRINK_NUMBER        128
#define LAST_AGE_WEIGHT                        30
#define SAME_AGE_REGION                        1024

/*
 * Define data block with age less than 1GB as hot data
 * define data block with age less than 10GB but more than 1GB as warm data
 */
#define DEF_HOT_DATA_AGE_THRESHOLD        262144
#define DEF_WARM_DATA_AGE_THRESHOLD        2621440

/* default max read extent count per inode */
#define DEF_MAX_READ_EXTENT_COUNT        10240

/* extent cache type */
enum extent_type {
        EX_READ,
        EX_BLOCK_AGE,
        NR_EXTENT_CACHES,
};

struct extent_info {
        unsigned int fofs;                /* start offset in a file */
        unsigned int len;                /* length of the extent */
        union {
                /* read extent_cache */
                struct {
                        /* start block address of the extent */
                        block_t blk;
#ifdef CONFIG_F2FS_FS_COMPRESSION
                        /* physical extent length of compressed blocks */
                        unsigned int c_len;
#endif
                };
                /* block age extent_cache */
                struct {
                        /* block age of the extent */
                        unsigned long long age;
                        /* last total blocks allocated */
                        unsigned long long last_blocks;
                };
        };
};

struct extent_node {
        struct rb_node rb_node;                /* rb node located in rb-tree */
        struct extent_info ei;                /* extent info */
        struct list_head list;                /* node in global extent list of sbi */
        struct extent_tree *et;                /* extent tree pointer */
};

struct extent_tree {
        nid_t ino;                        /* inode number */
        enum extent_type type;                /* keep the extent tree type */
        struct rb_root_cached root;        /* root of extent info rb-tree */
        struct extent_node *cached_en;        /* recently accessed extent node */
        struct list_head list;                /* to be used by sbi->zombie_list */
        rwlock_t lock;                        /* protect extent info rb-tree */
        atomic_t node_cnt;                /* # of extent node in rb-tree*/
        bool largest_updated;                /* largest extent updated */
        struct extent_info largest;        /* largest cached extent for EX_READ */
};

struct extent_tree_info {
        struct radix_tree_root extent_tree_root;/* cache extent cache entries */
        struct mutex extent_tree_lock;        /* locking extent radix tree */
        struct list_head extent_list;                /* lru list for shrinker */
        spinlock_t extent_lock;                        /* locking extent lru list */
        atomic_t total_ext_tree;                /* extent tree count */
        struct list_head zombie_list;                /* extent zombie tree list */
        atomic_t total_zombie_tree;                /* extent zombie tree count */
        atomic_t total_ext_node;                /* extent info count */
};

/*
 * State of block returned by f2fs_map_blocks.
 */
#define F2FS_MAP_NEW                (1U << 0)
#define F2FS_MAP_MAPPED                (1U << 1)
#define F2FS_MAP_DELALLOC        (1U << 2)
#define F2FS_MAP_FLAGS                (F2FS_MAP_NEW | F2FS_MAP_MAPPED |\
                                F2FS_MAP_DELALLOC)

struct f2fs_map_blocks {
        struct block_device *m_bdev;        /* for multi-device dio */
        block_t m_pblk;
        block_t m_lblk;
        unsigned int m_len;
        unsigned int m_flags;
        pgoff_t *m_next_pgofs;                /* point next possible non-hole pgofs */
        pgoff_t *m_next_extent;                /* point to next possible extent */
        int m_seg_type;
        bool m_may_create;                /* indicate it is from write path */
        bool m_multidev_dio;                /* indicate it allows multi-device dio */
};

/* for flag in get_data_block */
enum {
        F2FS_GET_BLOCK_DEFAULT,
        F2FS_GET_BLOCK_FIEMAP,
        F2FS_GET_BLOCK_BMAP,
        F2FS_GET_BLOCK_DIO,
        F2FS_GET_BLOCK_PRE_DIO,
        F2FS_GET_BLOCK_PRE_AIO,
        F2FS_GET_BLOCK_PRECACHE,
};

/*
 * i_advise uses FADVISE_XXX_BIT. We can add additional hints later.
 */
#define FADVISE_COLD_BIT        0x01
#define FADVISE_LOST_PINO_BIT        0x02
#define FADVISE_ENCRYPT_BIT        0x04
#define FADVISE_ENC_NAME_BIT        0x08
#define FADVISE_KEEP_SIZE_BIT        0x10
#define FADVISE_HOT_BIT                0x20
#define FADVISE_VERITY_BIT        0x40
#define FADVISE_TRUNC_BIT        0x80

#define FADVISE_MODIFIABLE_BITS        (FADVISE_COLD_BIT | FADVISE_HOT_BIT)

#define file_is_cold(inode)        is_file(inode, FADVISE_COLD_BIT)
#define file_set_cold(inode)        set_file(inode, FADVISE_COLD_BIT)
#define file_clear_cold(inode)        clear_file(inode, FADVISE_COLD_BIT)

#define file_wrong_pino(inode)        is_file(inode, FADVISE_LOST_PINO_BIT)
#define file_lost_pino(inode)        set_file(inode, FADVISE_LOST_PINO_BIT)
#define file_got_pino(inode)        clear_file(inode, FADVISE_LOST_PINO_BIT)

#define file_is_encrypt(inode)        is_file(inode, FADVISE_ENCRYPT_BIT)
#define file_set_encrypt(inode)        set_file(inode, FADVISE_ENCRYPT_BIT)

#define file_enc_name(inode)        is_file(inode, FADVISE_ENC_NAME_BIT)
#define file_set_enc_name(inode) set_file(inode, FADVISE_ENC_NAME_BIT)

#define file_keep_isize(inode)        is_file(inode, FADVISE_KEEP_SIZE_BIT)
#define file_set_keep_isize(inode) set_file(inode, FADVISE_KEEP_SIZE_BIT)

#define file_is_hot(inode)        is_file(inode, FADVISE_HOT_BIT)
#define file_set_hot(inode)        set_file(inode, FADVISE_HOT_BIT)
#define file_clear_hot(inode)        clear_file(inode, FADVISE_HOT_BIT)

#define file_is_verity(inode)        is_file(inode, FADVISE_VERITY_BIT)
#define file_set_verity(inode)        set_file(inode, FADVISE_VERITY_BIT)

#define file_should_truncate(inode)        is_file(inode, FADVISE_TRUNC_BIT)
#define file_need_truncate(inode)        set_file(inode, FADVISE_TRUNC_BIT)
#define file_dont_truncate(inode)        clear_file(inode, FADVISE_TRUNC_BIT)

#define DEF_DIR_LEVEL                0

/* used for f2fs_inode_info->flags */
enum {
        FI_NEW_INODE,                /* indicate newly allocated inode */
        FI_DIRTY_INODE,                /* indicate inode is dirty or not */
        FI_AUTO_RECOVER,        /* indicate inode is recoverable */
        FI_DIRTY_DIR,                /* indicate directory has dirty pages */
        FI_INC_LINK,                /* need to increment i_nlink */
        FI_ACL_MODE,                /* indicate acl mode */
        FI_NO_ALLOC,                /* should not allocate any blocks */
        FI_FREE_NID,                /* free allocated nide */
        FI_NO_EXTENT,                /* not to use the extent cache */
        FI_INLINE_XATTR,        /* used for inline xattr */
        FI_INLINE_DATA,                /* used for inline data*/
        FI_INLINE_DENTRY,        /* used for inline dentry */
        FI_APPEND_WRITE,        /* inode has appended data */
        FI_UPDATE_WRITE,        /* inode has in-place-update data */
        FI_NEED_IPU,                /* used for ipu per file */
        FI_ATOMIC_FILE,                /* indicate atomic file */
        FI_DATA_EXIST,                /* indicate data exists */
        FI_SKIP_WRITES,                /* should skip data page writeback */
        FI_OPU_WRITE,                /* used for opu per file */
        FI_DIRTY_FILE,                /* indicate regular/symlink has dirty pages */
        FI_PREALLOCATED_ALL,        /* all blocks for write were preallocated */
        FI_HOT_DATA,                /* indicate file is hot */
        FI_EXTRA_ATTR,                /* indicate file has extra attribute */
        FI_PROJ_INHERIT,        /* indicate file inherits projectid */
        FI_PIN_FILE,                /* indicate file should not be gced */
        FI_VERITY_IN_PROGRESS,        /* building fs-verity Merkle tree */
        FI_COMPRESSED_FILE,        /* indicate file's data can be compressed */
        FI_COMPRESS_CORRUPT,        /* indicate compressed cluster is corrupted */
        FI_MMAP_FILE,                /* indicate file was mmapped */
        FI_ENABLE_COMPRESS,        /* enable compression in "user" compression mode */
        FI_COMPRESS_RELEASED,        /* compressed blocks were released */
        FI_ALIGNED_WRITE,        /* enable aligned write */
        FI_COW_FILE,                /* indicate COW file */
        FI_ATOMIC_COMMITTED,        /* indicate atomic commit completed except disk sync */
        FI_ATOMIC_DIRTIED,        /* indicate atomic file is dirtied */
        FI_ATOMIC_REPLACE,        /* indicate atomic replace */
        FI_OPENED_FILE,                /* indicate file has been opened */
        FI_MAX,                        /* max flag, never be used */
};

struct f2fs_inode_info {
        struct inode vfs_inode;                /* serve a vfs inode */
        unsigned long i_flags;                /* keep an inode flags for ioctl */
        unsigned char i_advise;                /* use to give file attribute hints */
        unsigned char i_dir_level;        /* use for dentry level for large dir */
        union {
                unsigned int i_current_depth;        /* only for directory depth */
                unsigned short i_gc_failures;        /* for gc failure statistic */
        };
        unsigned int i_pino;                /* parent inode number */
        umode_t i_acl_mode;                /* keep file acl mode temporarily */

        /* Use below internally in f2fs*/
        unsigned long flags[BITS_TO_LONGS(FI_MAX)];        /* use to pass per-file flags */
        struct f2fs_rwsem i_sem;        /* protect fi info */
        atomic_t dirty_pages;                /* # of dirty pages */
        f2fs_hash_t chash;                /* hash value of given file name */
        unsigned int clevel;                /* maximum level of given file name */
        struct task_struct *task;        /* lookup and create consistency */
        struct task_struct *cp_task;        /* separate cp/wb IO stats*/
        struct task_struct *wb_task;        /* indicate inode is in context of writeback */
        nid_t i_xattr_nid;                /* node id that contains xattrs */
        loff_t        last_disk_size;                /* lastly written file size */
        spinlock_t i_size_lock;                /* protect last_disk_size */

#ifdef CONFIG_QUOTA
        struct dquot __rcu *i_dquot[MAXQUOTAS];

        /* quota space reservation, managed internally by quota code */
        qsize_t i_reserved_quota;
#endif
        struct list_head dirty_list;        /* dirty list for dirs and files */
        struct list_head gdirty_list;        /* linked in global dirty list */
        struct task_struct *atomic_write_task;        /* store atomic write task */
        struct extent_tree *extent_tree[NR_EXTENT_CACHES];
                                        /* cached extent_tree entry */
        union {
                struct inode *cow_inode;        /* copy-on-write inode for atomic write */
                struct inode *atomic_inode;
                                        /* point to atomic_inode, available only for cow_inode */
        };

        /* avoid racing between foreground op and gc */
        struct f2fs_rwsem i_gc_rwsem[2];
        struct f2fs_rwsem i_xattr_sem; /* avoid racing between reading and changing EAs */

        int i_extra_isize;                /* size of extra space located in i_addr */
        kprojid_t i_projid;                /* id for project quota */
        int i_inline_xattr_size;        /* inline xattr size */
        struct timespec64 i_crtime;        /* inode creation time */
        struct timespec64 i_disk_time[3];/* inode disk times */

        /* for file compress */
        atomic_t i_compr_blocks;                /* # of compressed blocks */
        unsigned char i_compress_algorithm;        /* algorithm type */
        unsigned char i_log_cluster_size;        /* log of cluster size */
        unsigned char i_compress_level;                /* compress level (lz4hc,zstd) */
        unsigned char i_compress_flag;                /* compress flag */
        unsigned int i_cluster_size;                /* cluster size */

        unsigned int atomic_write_cnt;
        loff_t original_i_size;                /* original i_size before atomic write */
};

static inline void get_read_extent_info(struct extent_info *ext,
                                        struct f2fs_extent *i_ext)
{
        ext->fofs = le32_to_cpu(i_ext->fofs);
        ext->blk = le32_to_cpu(i_ext->blk);
        ext->len = le32_to_cpu(i_ext->len);
}

static inline void set_raw_read_extent(struct extent_info *ext,
                                        struct f2fs_extent *i_ext)
{
        i_ext->fofs = cpu_to_le32(ext->fofs);
        i_ext->blk = cpu_to_le32(ext->blk);
        i_ext->len = cpu_to_le32(ext->len);
}

static inline bool __is_discard_mergeable(struct discard_info *back,
                        struct discard_info *front, unsigned int max_len)
{
        return (back->lstart + back->len == front->lstart) &&
                (back->len + front->len <= max_len);
}

static inline bool __is_discard_back_mergeable(struct discard_info *cur,
                        struct discard_info *back, unsigned int max_len)
{
        return __is_discard_mergeable(back, cur, max_len);
}

static inline bool __is_discard_front_mergeable(struct discard_info *cur,
                        struct discard_info *front, unsigned int max_len)
{
        return __is_discard_mergeable(cur, front, max_len);
}

/*
 * For free nid management
 */
enum nid_state {
        FREE_NID,                /* newly added to free nid list */
        PREALLOC_NID,                /* it is preallocated */
        MAX_NID_STATE,
};

enum nat_state {
        TOTAL_NAT,
        DIRTY_NAT,
        RECLAIMABLE_NAT,
        MAX_NAT_STATE,
};

struct f2fs_nm_info {
        block_t nat_blkaddr;                /* base disk address of NAT */
        nid_t max_nid;                        /* maximum possible node ids */
        nid_t available_nids;                /* # of available node ids */
        nid_t next_scan_nid;                /* the next nid to be scanned */
        nid_t max_rf_node_blocks;        /* max # of nodes for recovery */
        unsigned int ram_thresh;        /* control the memory footprint */
        unsigned int ra_nid_pages;        /* # of nid pages to be readaheaded */
        unsigned int dirty_nats_ratio;        /* control dirty nats ratio threshold */

        /* NAT cache management */
        struct radix_tree_root nat_root;/* root of the nat entry cache */
        struct radix_tree_root nat_set_root;/* root of the nat set cache */
        struct f2fs_rwsem nat_tree_lock;        /* protect nat entry tree */
        struct list_head nat_entries;        /* cached nat entry list (clean) */
        spinlock_t nat_list_lock;        /* protect clean nat entry list */
        unsigned int nat_cnt[MAX_NAT_STATE]; /* the # of cached nat entries */
        unsigned int nat_blocks;        /* # of nat blocks */

        /* free node ids management */
        struct radix_tree_root free_nid_root;/* root of the free_nid cache */
        struct list_head free_nid_list;                /* list for free nids excluding preallocated nids */
        unsigned int nid_cnt[MAX_NID_STATE];        /* the number of free node id */
        spinlock_t nid_list_lock;        /* protect nid lists ops */
        struct mutex build_lock;        /* lock for build free nids */
        unsigned char **free_nid_bitmap;
        unsigned char *nat_block_bitmap;
        unsigned short *free_nid_count;        /* free nid count of NAT block */

        /* for checkpoint */
        char *nat_bitmap;                /* NAT bitmap pointer */

        unsigned int nat_bits_blocks;        /* # of nat bits blocks */
        unsigned char *nat_bits;        /* NAT bits blocks */
        unsigned char *full_nat_bits;        /* full NAT pages */
        unsigned char *empty_nat_bits;        /* empty NAT pages */
#ifdef CONFIG_F2FS_CHECK_FS
        char *nat_bitmap_mir;                /* NAT bitmap mirror */
#endif
        int bitmap_size;                /* bitmap size */
};

/*
 * this structure is used as one of function parameters.
 * all the information are dedicated to a given direct node block determined
 * by the data offset in a file.
 */
struct dnode_of_data {
        struct inode *inode;                /* vfs inode pointer */
        struct page *inode_page;        /* its inode page, NULL is possible */
        struct page *node_page;                /* cached direct node page */
        nid_t nid;                        /* node id of the direct node block */
        unsigned int ofs_in_node;        /* data offset in the node page */
        bool inode_page_locked;                /* inode page is locked or not */
        bool node_changed;                /* is node block changed */
        char cur_level;                        /* level of hole node page */
        char max_level;                        /* level of current page located */
        block_t        data_blkaddr;                /* block address of the node block */
};

static inline void set_new_dnode(struct dnode_of_data *dn, struct inode *inode,
                struct page *ipage, struct page *npage, nid_t nid)
{
        memset(dn, 0, sizeof(*dn));
        dn->inode = inode;
        dn->inode_page = ipage;
        dn->node_page = npage;
        dn->nid = nid;
}

/*
 * For SIT manager
 *
 * By default, there are 6 active log areas across the whole main area.
 * When considering hot and cold data separation to reduce cleaning overhead,
 * we split 3 for data logs and 3 for node logs as hot, warm, and cold types,
 * respectively.
 * In the current design, you should not change the numbers intentionally.
 * Instead, as a mount option such as active_logs=x, you can use 2, 4, and 6
 * logs individually according to the underlying devices. (default: 6)
 * Just in case, on-disk layout covers maximum 16 logs that consist of 8 for
 * data and 8 for node logs.
 */
#define        NR_CURSEG_DATA_TYPE        (3)
#define NR_CURSEG_NODE_TYPE        (3)
#define NR_CURSEG_INMEM_TYPE        (2)
#define NR_CURSEG_RO_TYPE        (2)
#define NR_CURSEG_PERSIST_TYPE        (NR_CURSEG_DATA_TYPE + NR_CURSEG_NODE_TYPE)
#define NR_CURSEG_TYPE                (NR_CURSEG_INMEM_TYPE + NR_CURSEG_PERSIST_TYPE)

enum log_type {
        CURSEG_HOT_DATA        = 0,        /* directory entry blocks */
        CURSEG_WARM_DATA,        /* data blocks */
        CURSEG_COLD_DATA,        /* multimedia or GCed data blocks */
        CURSEG_HOT_NODE,        /* direct node blocks of directory files */
        CURSEG_WARM_NODE,        /* direct node blocks of normal files */
        CURSEG_COLD_NODE,        /* indirect node blocks */
        NR_PERSISTENT_LOG,        /* number of persistent log */
        CURSEG_COLD_DATA_PINNED = NR_PERSISTENT_LOG,
                                /* pinned file that needs consecutive block address */
        CURSEG_ALL_DATA_ATGC,        /* SSR alloctor in hot/warm/cold data area */
        NO_CHECK_TYPE,                /* number of persistent & inmem log */
};

struct flush_cmd {
        struct completion wait;
        struct llist_node llnode;
        nid_t ino;
        int ret;
};

struct flush_cmd_control {
        struct task_struct *f2fs_issue_flush;        /* flush thread */
        wait_queue_head_t flush_wait_queue;        /* waiting queue for wake-up */
        atomic_t issued_flush;                        /* # of issued flushes */
        atomic_t queued_flush;                        /* # of queued flushes */
        struct llist_head issue_list;                /* list for command issue */
        struct llist_node *dispatch_list;        /* list for command dispatch */
};

struct f2fs_sm_info {
        struct sit_info *sit_info;                /* whole segment information */
        struct free_segmap_info *free_info;        /* free segment information */
        struct dirty_seglist_info *dirty_info;        /* dirty segment information */
        struct curseg_info *curseg_array;        /* active segment information */

        struct f2fs_rwsem curseg_lock;        /* for preventing curseg change */

        block_t seg0_blkaddr;                /* block address of 0'th segment */
        block_t main_blkaddr;                /* start block address of main area */
        block_t ssa_blkaddr;                /* start block address of SSA area */

        unsigned int segment_count;        /* total # of segments */
        unsigned int main_segments;        /* # of segments in main area */
        unsigned int reserved_segments;        /* # of reserved segments */
        unsigned int ovp_segments;        /* # of overprovision segments */

        /* a threshold to reclaim prefree segments */
        unsigned int rec_prefree_segments;

        struct list_head sit_entry_set;        /* sit entry set list */

        unsigned int ipu_policy;        /* in-place-update policy */
        unsigned int min_ipu_util;        /* in-place-update threshold */
        unsigned int min_fsync_blocks;        /* threshold for fsync */
        unsigned int min_seq_blocks;        /* threshold for sequential blocks */
        unsigned int min_hot_blocks;        /* threshold for hot block allocation */
        unsigned int min_ssr_sections;        /* threshold to trigger SSR allocation */

        /* for flush command control */
        struct flush_cmd_control *fcc_info;

        /* for discard command control */
        struct discard_cmd_control *dcc_info;
};

/*
 * For superblock
 */
/*
 * COUNT_TYPE for monitoring
 *
 * f2fs monitors the number of several block types such as on-writeback,
 * dirty dentry blocks, dirty node blocks, and dirty meta blocks.
 */
#define WB_DATA_TYPE(p, f)                        \
        (f || f2fs_is_cp_guaranteed(p) ? F2FS_WB_CP_DATA : F2FS_WB_DATA)
enum count_type {
        F2FS_DIRTY_DENTS,
        F2FS_DIRTY_DATA,
        F2FS_DIRTY_QDATA,
        F2FS_DIRTY_NODES,
        F2FS_DIRTY_META,
        F2FS_DIRTY_IMETA,
        F2FS_WB_CP_DATA,
        F2FS_WB_DATA,
        F2FS_RD_DATA,
        F2FS_RD_NODE,
        F2FS_RD_META,
        F2FS_DIO_WRITE,
        F2FS_DIO_READ,
        NR_COUNT_TYPE,
};

/*
 * The below are the page types of bios used in submit_bio().
 * The available types are:
 * DATA                        User data pages. It operates as async mode.
 * NODE                        Node pages. It operates as async mode.
 * META                        FS metadata pages such as SIT, NAT, CP.
 * NR_PAGE_TYPE                The number of page types.
 * META_FLUSH                Make sure the previous pages are written
 *                        with waiting the bio's completion
 * ...                        Only can be used with META.
 */
#define PAGE_TYPE_OF_BIO(type)        ((type) > META ? META : (type))
#define PAGE_TYPE_ON_MAIN(type)        ((type) == DATA || (type) == NODE)
enum page_type {
        DATA = 0,
        NODE = 1,        /* should not change this */
        META,
        NR_PAGE_TYPE,
        META_FLUSH,
        IPU,                /* the below types are used by tracepoints only. */
        OPU,
};

enum temp_type {
        HOT = 0,        /* must be zero for meta bio */
        WARM,
        COLD,
        NR_TEMP_TYPE,
};

enum need_lock_type {
        LOCK_REQ = 0,
        LOCK_DONE,
        LOCK_RETRY,
};

enum cp_reason_type {
        CP_NO_NEEDED,
        CP_NON_REGULAR,
        CP_COMPRESSED,
        CP_HARDLINK,
        CP_SB_NEED_CP,
        CP_WRONG_PINO,
        CP_NO_SPC_ROLL,
        CP_NODE_NEED_CP,
        CP_FASTBOOT_MODE,
        CP_SPEC_LOG_NUM,
        CP_RECOVER_DIR,
        CP_XATTR_DIR,
};

enum iostat_type {
        /* WRITE IO */
        APP_DIRECT_IO,                        /* app direct write IOs */
        APP_BUFFERED_IO,                /* app buffered write IOs */
        APP_WRITE_IO,                        /* app write IOs */
        APP_MAPPED_IO,                        /* app mapped IOs */
        APP_BUFFERED_CDATA_IO,                /* app buffered write IOs on compressed file */
        APP_MAPPED_CDATA_IO,                /* app mapped write IOs on compressed file */
        FS_DATA_IO,                        /* data IOs from kworker/fsync/reclaimer */
        FS_CDATA_IO,                        /* data IOs from kworker/fsync/reclaimer on compressed file */
        FS_NODE_IO,                        /* node IOs from kworker/fsync/reclaimer */
        FS_META_IO,                        /* meta IOs from kworker/reclaimer */
        FS_GC_DATA_IO,                        /* data IOs from forground gc */
        FS_GC_NODE_IO,                        /* node IOs from forground gc */
        FS_CP_DATA_IO,                        /* data IOs from checkpoint */
        FS_CP_NODE_IO,                        /* node IOs from checkpoint */
        FS_CP_META_IO,                        /* meta IOs from checkpoint */

        /* READ IO */
        APP_DIRECT_READ_IO,                /* app direct read IOs */
        APP_BUFFERED_READ_IO,                /* app buffered read IOs */
        APP_READ_IO,                        /* app read IOs */
        APP_MAPPED_READ_IO,                /* app mapped read IOs */
        APP_BUFFERED_CDATA_READ_IO,        /* app buffered read IOs on compressed file  */
        APP_MAPPED_CDATA_READ_IO,        /* app mapped read IOs on compressed file  */
        FS_DATA_READ_IO,                /* data read IOs */
        FS_GDATA_READ_IO,                /* data read IOs from background gc */
        FS_CDATA_READ_IO,                /* compressed data read IOs */
        FS_NODE_READ_IO,                /* node read IOs */
        FS_META_READ_IO,                /* meta read IOs */

        /* other */
        FS_DISCARD_IO,                        /* discard */
        FS_FLUSH_IO,                        /* flush */
        FS_ZONE_RESET_IO,                /* zone reset */
        NR_IO_TYPE,
};

struct f2fs_io_info {
        struct f2fs_sb_info *sbi;        /* f2fs_sb_info pointer */
        nid_t ino;                /* inode number */
        enum page_type type;        /* contains DATA/NODE/META/META_FLUSH */
        enum temp_type temp;        /* contains HOT/WARM/COLD */
        enum req_op op;                /* contains REQ_OP_ */
        blk_opf_t op_flags;        /* req_flag_bits */
        block_t new_blkaddr;        /* new block address to be written */
        block_t old_blkaddr;        /* old block address before Cow */
        struct page *page;        /* page to be written */
        struct page *encrypted_page;        /* encrypted page */
        struct page *compressed_page;        /* compressed page */
        struct list_head list;                /* serialize IOs */
        unsigned int compr_blocks;        /* # of compressed block addresses */
        unsigned int need_lock:8;        /* indicate we need to lock cp_rwsem */
        unsigned int version:8;                /* version of the node */
        unsigned int submitted:1;        /* indicate IO submission */
        unsigned int in_list:1;                /* indicate fio is in io_list */
        unsigned int is_por:1;                /* indicate IO is from recovery or not */
        unsigned int encrypted:1;        /* indicate file is encrypted */
        unsigned int meta_gc:1;                /* require meta inode GC */
        enum iostat_type io_type;        /* io type */
        struct writeback_control *io_wbc; /* writeback control */
        struct bio **bio;                /* bio for ipu */
        sector_t *last_block;                /* last block number in bio */
};

struct bio_entry {
        struct bio *bio;
        struct list_head list;
};

#define is_read_io(rw) ((rw) == READ)
struct f2fs_bio_info {
        struct f2fs_sb_info *sbi;        /* f2fs superblock */
        struct bio *bio;                /* bios to merge */
        sector_t last_block_in_bio;        /* last block number */
        struct f2fs_io_info fio;        /* store buffered io info. */
#ifdef CONFIG_BLK_DEV_ZONED
        struct completion zone_wait;        /* condition value for the previous open zone to close */
        struct bio *zone_pending_bio;        /* pending bio for the previous zone */
        void *bi_private;                /* previous bi_private for pending bio */
#endif
        struct f2fs_rwsem io_rwsem;        /* blocking op for bio */
        spinlock_t io_lock;                /* serialize DATA/NODE IOs */
        struct list_head io_list;        /* track fios */
        struct list_head bio_list;        /* bio entry list head */
        struct f2fs_rwsem bio_list_lock;        /* lock to protect bio entry list */
};

#define FDEV(i)                                (sbi->devs[i])
#define RDEV(i)                                (raw_super->devs[i])
struct f2fs_dev_info {
        struct file *bdev_file;
        struct block_device *bdev;
        char path[MAX_PATH_LEN];
        unsigned int total_segments;
        block_t start_blk;
        block_t end_blk;
#ifdef CONFIG_BLK_DEV_ZONED
        unsigned int nr_blkz;                /* Total number of zones */
        unsigned long *blkz_seq;        /* Bitmap indicating sequential zones */
#endif
};

enum inode_type {
        DIR_INODE,                        /* for dirty dir inode */
        FILE_INODE,                        /* for dirty regular/symlink inode */
        DIRTY_META,                        /* for all dirtied inode metadata */
        NR_INODE_TYPE,
};

/* for inner inode cache management */
struct inode_management {
        struct radix_tree_root ino_root;        /* ino entry array */
        spinlock_t ino_lock;                        /* for ino entry lock */
        struct list_head ino_list;                /* inode list head */
        unsigned long ino_num;                        /* number of entries */
};

/* for GC_AT */
struct atgc_management {
        bool atgc_enabled;                        /* ATGC is enabled or not */
        struct rb_root_cached root;                /* root of victim rb-tree */
        struct list_head victim_list;                /* linked with all victim entries */
        unsigned int victim_count;                /* victim count in rb-tree */
        unsigned int candidate_ratio;                /* candidate ratio */
        unsigned int max_candidate_count;        /* max candidate count */
        unsigned int age_weight;                /* age weight, vblock_weight = 100 - age_weight */
        unsigned long long age_threshold;        /* age threshold */
};

struct f2fs_gc_control {
        unsigned int victim_segno;        /* target victim segment number */
        int init_gc_type;                /* FG_GC or BG_GC */
        bool no_bg_gc;                        /* check the space and stop bg_gc */
        bool should_migrate_blocks;        /* should migrate blocks */
        bool err_gc_skipped;                /* return EAGAIN if GC skipped */
        bool one_time;                        /* require one time GC in one migration unit */
        unsigned int nr_free_secs;        /* # of free sections to do GC */
};

/*
 * For s_flag in struct f2fs_sb_info
 * Modification on enum should be synchronized with s_flag array
 */
enum {
        SBI_IS_DIRTY,                                /* dirty flag for checkpoint */
        SBI_IS_CLOSE,                                /* specify unmounting */
        SBI_NEED_FSCK,                                /* need fsck.f2fs to fix */
        SBI_POR_DOING,                                /* recovery is doing or not */
        SBI_NEED_SB_WRITE,                        /* need to recover superblock */
        SBI_NEED_CP,                                /* need to checkpoint */
        SBI_IS_SHUTDOWN,                        /* shutdown by ioctl */
        SBI_IS_RECOVERED,                        /* recovered orphan/data */
        SBI_CP_DISABLED,                        /* CP was disabled last mount */
        SBI_CP_DISABLED_QUICK,                        /* CP was disabled quickly */
        SBI_QUOTA_NEED_FLUSH,                        /* need to flush quota info in CP */
        SBI_QUOTA_SKIP_FLUSH,                        /* skip flushing quota in current CP */
        SBI_QUOTA_NEED_REPAIR,                        /* quota file may be corrupted */
        SBI_IS_RESIZEFS,                        /* resizefs is in process */
        SBI_IS_FREEZING,                        /* freezefs is in process */
        SBI_IS_WRITABLE,                        /* remove ro mountoption transiently */
        MAX_SBI_FLAG,
};

enum {
        CP_TIME,
        REQ_TIME,
        DISCARD_TIME,
        GC_TIME,
        DISABLE_TIME,
        UMOUNT_DISCARD_TIMEOUT,
        MAX_TIME,
};

/* Note that you need to keep synchronization with this gc_mode_names array */
enum {
        GC_NORMAL,
        GC_IDLE_CB,
        GC_IDLE_GREEDY,
        GC_IDLE_AT,
        GC_URGENT_HIGH,
        GC_URGENT_LOW,
        GC_URGENT_MID,
        MAX_GC_MODE,
};

enum {
        BGGC_MODE_ON,                /* background gc is on */
        BGGC_MODE_OFF,                /* background gc is off */
        BGGC_MODE_SYNC,                /*
                                 * background gc is on, migrating blocks
                                 * like foreground gc
                                 */
};

enum {
        FS_MODE_ADAPTIVE,                /* use both lfs/ssr allocation */
        FS_MODE_LFS,                        /* use lfs allocation only */
        FS_MODE_FRAGMENT_SEG,                /* segment fragmentation mode */
        FS_MODE_FRAGMENT_BLK,                /* block fragmentation mode */
};

enum {
        ALLOC_MODE_DEFAULT,        /* stay default */
        ALLOC_MODE_REUSE,        /* reuse segments as much as possible */
};

enum fsync_mode {
        FSYNC_MODE_POSIX,        /* fsync follows posix semantics */
        FSYNC_MODE_STRICT,        /* fsync behaves in line with ext4 */
        FSYNC_MODE_NOBARRIER,        /* fsync behaves nobarrier based on posix */
};

enum {
        COMPR_MODE_FS,                /*
                                 * automatically compress compression
                                 * enabled files
                                 */
        COMPR_MODE_USER,        /*
                                 * automatical compression is disabled.
                                 * user can control the file compression
                                 * using ioctls
                                 */
};

enum {
        DISCARD_UNIT_BLOCK,        /* basic discard unit is block */
        DISCARD_UNIT_SEGMENT,        /* basic discard unit is segment */
        DISCARD_UNIT_SECTION,        /* basic discard unit is section */
};

enum {
        MEMORY_MODE_NORMAL,        /* memory mode for normal devices */
        MEMORY_MODE_LOW,        /* memory mode for low memry devices */
};

enum errors_option {
        MOUNT_ERRORS_READONLY,        /* remount fs ro on errors */
        MOUNT_ERRORS_CONTINUE,        /* continue on errors */
        MOUNT_ERRORS_PANIC,        /* panic on errors */
};

enum {
        BACKGROUND,
        FOREGROUND,
        MAX_CALL_TYPE,
        TOTAL_CALL = FOREGROUND,
};

static inline int f2fs_test_bit(unsigned int nr, char *addr);
static inline void f2fs_set_bit(unsigned int nr, char *addr);
static inline void f2fs_clear_bit(unsigned int nr, char *addr);

/*
 * Layout of f2fs page.private:
 *
 * Layout A: lowest bit should be 1
 * | bit0 = 1 | bit1 | bit2 | ... | bit MAX | private data .... |
 * bit 0        PAGE_PRIVATE_NOT_POINTER
 * bit 1        PAGE_PRIVATE_ONGOING_MIGRATION
 * bit 2        PAGE_PRIVATE_INLINE_INODE
 * bit 3        PAGE_PRIVATE_REF_RESOURCE
 * bit 4        PAGE_PRIVATE_ATOMIC_WRITE
 * bit 5-        f2fs private data
 *
 * Layout B: lowest bit should be 0
 * page.private is a wrapped pointer.
 */
enum {
        PAGE_PRIVATE_NOT_POINTER,                /* private contains non-pointer data */
        PAGE_PRIVATE_ONGOING_MIGRATION,                /* data page which is on-going migrating */
        PAGE_PRIVATE_INLINE_INODE,                /* inode page contains inline data */
        PAGE_PRIVATE_REF_RESOURCE,                /* dirty page has referenced resources */
        PAGE_PRIVATE_ATOMIC_WRITE,                /* data page from atomic write path */
        PAGE_PRIVATE_MAX
};

/* For compression */
enum compress_algorithm_type {
        COMPRESS_LZO,
        COMPRESS_LZ4,
        COMPRESS_ZSTD,
        COMPRESS_LZORLE,
        COMPRESS_MAX,
};

enum compress_flag {
        COMPRESS_CHKSUM,
        COMPRESS_MAX_FLAG,
};

#define        COMPRESS_WATERMARK                        20
#define        COMPRESS_PERCENT                        20

#define COMPRESS_DATA_RESERVED_SIZE                4
struct compress_data {
        __le32 clen;                        /* compressed data size */
        __le32 chksum;                        /* compressed data chksum */
        __le32 reserved[COMPRESS_DATA_RESERVED_SIZE];        /* reserved */
        u8 cdata[];                        /* compressed data */
};

#define COMPRESS_HEADER_SIZE        (sizeof(struct compress_data))

#define F2FS_COMPRESSED_PAGE_MAGIC        0xF5F2C000

#define F2FS_ZSTD_DEFAULT_CLEVEL        1

#define        COMPRESS_LEVEL_OFFSET        8

/* compress context */
struct compress_ctx {
        struct inode *inode;                /* inode the context belong to */
        pgoff_t cluster_idx;                /* cluster index number */
        unsigned int cluster_size;        /* page count in cluster */
        unsigned int log_cluster_size;        /* log of cluster size */
        struct page **rpages;                /* pages store raw data in cluster */
        unsigned int nr_rpages;                /* total page number in rpages */
        struct page **cpages;                /* pages store compressed data in cluster */
        unsigned int nr_cpages;                /* total page number in cpages */
        unsigned int valid_nr_cpages;        /* valid page number in cpages */
        void *rbuf;                        /* virtual mapped address on rpages */
        struct compress_data *cbuf;        /* virtual mapped address on cpages */
        size_t rlen;                        /* valid data length in rbuf */
        size_t clen;                        /* valid data length in cbuf */
        void *private;                        /* payload buffer for specified compression algorithm */
        void *private2;                        /* extra payload buffer */
};

/* compress context for write IO path */
struct compress_io_ctx {
        u32 magic;                        /* magic number to indicate page is compressed */
        struct inode *inode;                /* inode the context belong to */
        struct page **rpages;                /* pages store raw data in cluster */
        unsigned int nr_rpages;                /* total page number in rpages */
        atomic_t pending_pages;                /* in-flight compressed page count */
};

/* Context for decompressing one cluster on the read IO path */
struct decompress_io_ctx {
        u32 magic;                        /* magic number to indicate page is compressed */
        struct inode *inode;                /* inode the context belong to */
        pgoff_t cluster_idx;                /* cluster index number */
        unsigned int cluster_size;        /* page count in cluster */
        unsigned int log_cluster_size;        /* log of cluster size */
        struct page **rpages;                /* pages store raw data in cluster */
        unsigned int nr_rpages;                /* total page number in rpages */
        struct page **cpages;                /* pages store compressed data in cluster */
        unsigned int nr_cpages;                /* total page number in cpages */
        struct page **tpages;                /* temp pages to pad holes in cluster */
        void *rbuf;                        /* virtual mapped address on rpages */
        struct compress_data *cbuf;        /* virtual mapped address on cpages */
        size_t rlen;                        /* valid data length in rbuf */
        size_t clen;                        /* valid data length in cbuf */

        /*
         * The number of compressed pages remaining to be read in this cluster.
         * This is initially nr_cpages.  It is decremented by 1 each time a page
         * has been read (or failed to be read).  When it reaches 0, the cluster
         * is decompressed (or an error is reported).
         *
         * If an error occurs before all the pages have been submitted for I/O,
         * then this will never reach 0.  In this case the I/O submitter is
         * responsible for calling f2fs_decompress_end_io() instead.
         */
        atomic_t remaining_pages;

        /*
         * Number of references to this decompress_io_ctx.
         *
         * One reference is held for I/O completion.  This reference is dropped
         * after the pagecache pages are updated and unlocked -- either after
         * decompression (and verity if enabled), or after an error.
         *
         * In addition, each compressed page holds a reference while it is in a
         * bio.  These references are necessary prevent compressed pages from
         * being freed while they are still in a bio.
         */
        refcount_t refcnt;

        bool failed;                        /* IO error occurred before decompression? */
        bool need_verity;                /* need fs-verity verification after decompression? */
        void *private;                        /* payload buffer for specified decompression algorithm */
        void *private2;                        /* extra payload buffer */
        struct work_struct verity_work;        /* work to verify the decompressed pages */
        struct work_struct free_work;        /* work for late free this structure itself */
};

#define NULL_CLUSTER                        ((unsigned int)(~0))
#define MIN_COMPRESS_LOG_SIZE                2
#define MAX_COMPRESS_LOG_SIZE                8
#define MAX_COMPRESS_WINDOW_SIZE(log_size)        ((PAGE_SIZE) << (log_size))

struct f2fs_sb_info {
        struct super_block *sb;                        /* pointer to VFS super block */
        struct proc_dir_entry *s_proc;                /* proc entry */
        struct f2fs_super_block *raw_super;        /* raw super block pointer */
        struct f2fs_rwsem sb_lock;                /* lock for raw super block */
        int valid_super_block;                        /* valid super block no */
        unsigned long s_flag;                                /* flags for sbi */
        struct mutex writepages;                /* mutex for writepages() */

#ifdef CONFIG_BLK_DEV_ZONED
        unsigned int blocks_per_blkz;                /* F2FS blocks per zone */
        unsigned int max_open_zones;                /* max open zone resources of the zoned device */
        /* For adjust the priority writing position of data in zone UFS */
        unsigned int blkzone_alloc_policy;
#endif

        /* for node-related operations */
        struct f2fs_nm_info *nm_info;                /* node manager */
        struct inode *node_inode;                /* cache node blocks */

        /* for segment-related operations */
        struct f2fs_sm_info *sm_info;                /* segment manager */

        /* for bio operations */
        struct f2fs_bio_info *write_io[NR_PAGE_TYPE];        /* for write bios */
        /* keep migration IO order for LFS mode */
        struct f2fs_rwsem io_order_lock;
        pgoff_t page_eio_ofs[NR_PAGE_TYPE];        /* EIO page offset */
        int page_eio_cnt[NR_PAGE_TYPE];                /* EIO count */

        /* for checkpoint */
        struct f2fs_checkpoint *ckpt;                /* raw checkpoint pointer */
        int cur_cp_pack;                        /* remain current cp pack */
        spinlock_t cp_lock;                        /* for flag in ckpt */
        struct inode *meta_inode;                /* cache meta blocks */
        struct f2fs_rwsem cp_global_sem;        /* checkpoint procedure lock */
        struct f2fs_rwsem cp_rwsem;                /* blocking FS operations */
        struct f2fs_rwsem node_write;                /* locking node writes */
        struct f2fs_rwsem node_change;        /* locking node change */
        wait_queue_head_t cp_wait;
        unsigned long last_time[MAX_TIME];        /* to store time in jiffies */
        long interval_time[MAX_TIME];                /* to store thresholds */
        struct ckpt_req_control cprc_info;        /* for checkpoint request control */

        struct inode_management im[MAX_INO_ENTRY];        /* manage inode cache */

        spinlock_t fsync_node_lock;                /* for node entry lock */
        struct list_head fsync_node_list;        /* node list head */
        unsigned int fsync_seg_id;                /* sequence id */
        unsigned int fsync_node_num;                /* number of node entries */

        /* for orphan inode, use 0'th array */
        unsigned int max_orphans;                /* max orphan inodes */

        /* for inode management */
        struct list_head inode_list[NR_INODE_TYPE];        /* dirty inode list */
        spinlock_t inode_lock[NR_INODE_TYPE];        /* for dirty inode list lock */
        struct mutex flush_lock;                /* for flush exclusion */

        /* for extent tree cache */
        struct extent_tree_info extent_tree[NR_EXTENT_CACHES];
        atomic64_t allocated_data_blocks;        /* for block age extent_cache */
        unsigned int max_read_extent_count;        /* max read extent count per inode */

        /* The threshold used for hot and warm data seperation*/
        unsigned int hot_data_age_threshold;
        unsigned int warm_data_age_threshold;
        unsigned int last_age_weight;

        /* basic filesystem units */
        unsigned int log_sectors_per_block;        /* log2 sectors per block */
        unsigned int log_blocksize;                /* log2 block size */
        unsigned int blocksize;                        /* block size */
        unsigned int root_ino_num;                /* root inode number*/
        unsigned int node_ino_num;                /* node inode number*/
        unsigned int meta_ino_num;                /* meta inode number*/
        unsigned int log_blocks_per_seg;        /* log2 blocks per segment */
        unsigned int blocks_per_seg;                /* blocks per segment */
        unsigned int unusable_blocks_per_sec;        /* unusable blocks per section */
        unsigned int segs_per_sec;                /* segments per section */
        unsigned int secs_per_zone;                /* sections per zone */
        unsigned int total_sections;                /* total section count */
        unsigned int total_node_count;                /* total node block count */
        unsigned int total_valid_node_count;        /* valid node block count */
        int dir_level;                                /* directory level */
        bool readdir_ra;                        /* readahead inode in readdir */
        u64 max_io_bytes;                        /* max io bytes to merge IOs */

        block_t user_block_count;                /* # of user blocks */
        block_t total_valid_block_count;        /* # of valid blocks */
        block_t discard_blks;                        /* discard command candidats */
        block_t last_valid_block_count;                /* for recovery */
        block_t reserved_blocks;                /* configurable reserved blocks */
        block_t current_reserved_blocks;        /* current reserved blocks */

        /* Additional tracking for no checkpoint mode */
        block_t unusable_block_count;                /* # of blocks saved by last cp */

        unsigned int nquota_files;                /* # of quota sysfile */
        struct f2fs_rwsem quota_sem;                /* blocking cp for flags */

        /* # of pages, see count_type */
        atomic_t nr_pages[NR_COUNT_TYPE];
        /* # of allocated blocks */
        struct percpu_counter alloc_valid_block_count;
        /* # of node block writes as roll forward recovery */
        struct percpu_counter rf_node_block_count;

        /* writeback control */
        atomic_t wb_sync_req[META];        /* count # of WB_SYNC threads */

        /* valid inode count */
        struct percpu_counter total_valid_inode_count;

        struct f2fs_mount_info mount_opt;        /* mount options */

        /* for cleaning operations */
        struct f2fs_rwsem gc_lock;                /*
                                                 * semaphore for GC, avoid
                                                 * race between GC and GC or CP
                                                 */
        struct f2fs_gc_kthread        *gc_thread;        /* GC thread */
        struct atgc_management am;                /* atgc management */
        unsigned int cur_victim_sec;                /* current victim section num */
        unsigned int gc_mode;                        /* current GC state */
        unsigned int next_victim_seg[2];        /* next segment in victim section */
        spinlock_t gc_remaining_trials_lock;
        /* remaining trial count for GC_URGENT_* and GC_IDLE_* */
        unsigned int gc_remaining_trials;

        /* for skip statistic */
        unsigned long long skipped_gc_rwsem;                /* FG_GC only */

        /* threshold for gc trials on pinned files */
        unsigned short gc_pin_file_threshold;
        struct f2fs_rwsem pin_sem;

        /* maximum # of trials to find a victim segment for SSR and GC */
        unsigned int max_victim_search;
        /* migration granularity of garbage collection, unit: segment */
        unsigned int migration_granularity;
        /* migration window granularity of garbage collection, unit: segment */
        unsigned int migration_window_granularity;

        /*
         * for stat information.
         * one is for the LFS mode, and the other is for the SSR mode.
         */
#ifdef CONFIG_F2FS_STAT_FS
        struct f2fs_stat_info *stat_info;        /* FS status information */
        atomic_t meta_count[META_MAX];                /* # of meta blocks */
        unsigned int segment_count[2];                /* # of allocated segments */
        unsigned int block_count[2];                /* # of allocated blocks */
        atomic_t inplace_count;                /* # of inplace update */
        /* # of lookup extent cache */
        atomic64_t total_hit_ext[NR_EXTENT_CACHES];
        /* # of hit rbtree extent node */
        atomic64_t read_hit_rbtree[NR_EXTENT_CACHES];
        /* # of hit cached extent node */
        atomic64_t read_hit_cached[NR_EXTENT_CACHES];
        /* # of hit largest extent node in read extent cache */
        atomic64_t read_hit_largest;
        atomic_t inline_xattr;                        /* # of inline_xattr inodes */
        atomic_t inline_inode;                        /* # of inline_data inodes */
        atomic_t inline_dir;                        /* # of inline_dentry inodes */
        atomic_t compr_inode;                        /* # of compressed inodes */
        atomic64_t compr_blocks;                /* # of compressed blocks */
        atomic_t swapfile_inode;                /* # of swapfile inodes */
        atomic_t atomic_files;                        /* # of opened atomic file */
        atomic_t max_aw_cnt;                        /* max # of atomic writes */
        unsigned int io_skip_bggc;                /* skip background gc for in-flight IO */
        unsigned int other_skip_bggc;                /* skip background gc for other reasons */
        unsigned int ndirty_inode[NR_INODE_TYPE];        /* # of dirty inodes */
        atomic_t cp_call_count[MAX_CALL_TYPE];        /* # of cp call */
#endif
        spinlock_t stat_lock;                        /* lock for stat operations */

        /* to attach REQ_META|REQ_FUA flags */
        unsigned int data_io_flag;
        unsigned int node_io_flag;

        /* For sysfs support */
        struct kobject s_kobj;                        /* /sys/fs/f2fs/<devname> */
        struct completion s_kobj_unregister;

        struct kobject s_stat_kobj;                /* /sys/fs/f2fs/<devname>/stat */
        struct completion s_stat_kobj_unregister;

        struct kobject s_feature_list_kobj;                /* /sys/fs/f2fs/<devname>/feature_list */
        struct completion s_feature_list_kobj_unregister;

        /* For shrinker support */
        struct list_head s_list;
        struct mutex umount_mutex;
        unsigned int shrinker_run_no;

        /* For multi devices */
        int s_ndevs;                                /* number of devices */
        struct f2fs_dev_info *devs;                /* for device list */
        unsigned int dirty_device;                /* for checkpoint data flush */
        spinlock_t dev_lock;                        /* protect dirty_device */
        bool aligned_blksize;                        /* all devices has the same logical blksize */
        unsigned int first_zoned_segno;                /* first zoned segno */

        /* For write statistics */
        u64 sectors_written_start;
        u64 kbytes_written;

        /* Reference to checksum algorithm driver via cryptoapi */
        struct crypto_shash *s_chksum_driver;

        /* Precomputed FS UUID checksum for seeding other checksums */
        __u32 s_chksum_seed;

        struct workqueue_struct *post_read_wq;        /* post read workqueue */

        /*
         * If we are in irq context, let's update error information into
         * on-disk superblock in the work.
         */
        struct work_struct s_error_work;
        unsigned char errors[MAX_F2FS_ERRORS];                /* error flags */
        unsigned char stop_reason[MAX_STOP_REASON];        /* stop reason */
        spinlock_t error_lock;                        /* protect errors/stop_reason array */
        bool error_dirty;                        /* errors of sb is dirty */

        struct kmem_cache *inline_xattr_slab;        /* inline xattr entry */
        unsigned int inline_xattr_slab_size;        /* default inline xattr slab size */

        /* For reclaimed segs statistics per each GC mode */
        unsigned int gc_segment_mode;                /* GC state for reclaimed segments */
        unsigned int gc_reclaimed_segs[MAX_GC_MODE];        /* Reclaimed segs for each mode */

        unsigned long seq_file_ra_mul;                /* multiplier for ra_pages of seq. files in fadvise */

        int max_fragment_chunk;                        /* max chunk size for block fragmentation mode */
        int max_fragment_hole;                        /* max hole size for block fragmentation mode */

        /* For atomic write statistics */
        atomic64_t current_atomic_write;
        s64 peak_atomic_write;
        u64 committed_atomic_block;
        u64 revoked_atomic_block;

#ifdef CONFIG_F2FS_FS_COMPRESSION
        struct kmem_cache *page_array_slab;        /* page array entry */
        unsigned int page_array_slab_size;        /* default page array slab size */

        /* For runtime compression statistics */
        u64 compr_written_block;
        u64 compr_saved_block;
        u32 compr_new_inode;

        /* For compressed block cache */
        struct inode *compress_inode;                /* cache compressed blocks */
        unsigned int compress_percent;                /* cache page percentage */
        unsigned int compress_watermark;        /* cache page watermark */
        atomic_t compress_page_hit;                /* cache hit count */
#endif

#ifdef CONFIG_F2FS_IOSTAT
        /* For app/fs IO statistics */
        spinlock_t iostat_lock;
        unsigned long long iostat_count[NR_IO_TYPE];
        unsigned long long iostat_bytes[NR_IO_TYPE];
        unsigned long long prev_iostat_bytes[NR_IO_TYPE];
        bool iostat_enable;
        unsigned long iostat_next_period;
        unsigned int iostat_period_ms;

        /* For io latency related statistics info in one iostat period */
        spinlock_t iostat_lat_lock;
        struct iostat_lat_info *iostat_io_lat;
#endif
};

/* Definitions to access f2fs_sb_info */
#define SEGS_TO_BLKS(sbi, segs)                                        \
                ((segs) << (sbi)->log_blocks_per_seg)
#define BLKS_TO_SEGS(sbi, blks)                                        \
                ((blks) >> (sbi)->log_blocks_per_seg)

#define BLKS_PER_SEG(sbi)        ((sbi)->blocks_per_seg)
#define BLKS_PER_SEC(sbi)        (SEGS_TO_BLKS(sbi, (sbi)->segs_per_sec))
#define SEGS_PER_SEC(sbi)        ((sbi)->segs_per_sec)

__printf(3, 4)
void f2fs_printk(struct f2fs_sb_info *sbi, bool limit_rate, const char *fmt, ...);

#define f2fs_err(sbi, fmt, ...)                                                \
        f2fs_printk(sbi, false, KERN_ERR fmt, ##__VA_ARGS__)
#define f2fs_warn(sbi, fmt, ...)                                        \
        f2fs_printk(sbi, false, KERN_WARNING fmt, ##__VA_ARGS__)
#define f2fs_notice(sbi, fmt, ...)                                        \
        f2fs_printk(sbi, false, KERN_NOTICE fmt, ##__VA_ARGS__)
#define f2fs_info(sbi, fmt, ...)                                        \
        f2fs_printk(sbi, false, KERN_INFO fmt, ##__VA_ARGS__)
#define f2fs_debug(sbi, fmt, ...)                                        \
        f2fs_printk(sbi, false, KERN_DEBUG fmt, ##__VA_ARGS__)

#define f2fs_err_ratelimited(sbi, fmt, ...)                                \
        f2fs_printk(sbi, true, KERN_ERR fmt, ##__VA_ARGS__)
#define f2fs_warn_ratelimited(sbi, fmt, ...)                                \
        f2fs_printk(sbi, true, KERN_WARNING fmt, ##__VA_ARGS__)
#define f2fs_info_ratelimited(sbi, fmt, ...)                                \
        f2fs_printk(sbi, true, KERN_INFO fmt, ##__VA_ARGS__)

#ifdef CONFIG_F2FS_FAULT_INJECTION
#define time_to_inject(sbi, type) __time_to_inject(sbi, type, __func__,        \
                                                                        __builtin_return_address(0))
static inline bool __time_to_inject(struct f2fs_sb_info *sbi, int type,
                                const char *func, const char *parent_func)
{
        struct f2fs_fault_info *ffi = &F2FS_OPTION(sbi).fault_info;

        if (!ffi->inject_rate)
                return false;

        if (!IS_FAULT_SET(ffi, type))
                return false;

        atomic_inc(&ffi->inject_ops);
        if (atomic_read(&ffi->inject_ops) >= ffi->inject_rate) {
                atomic_set(&ffi->inject_ops, 0);
                f2fs_info_ratelimited(sbi, "inject %s in %s of %pS",
                                f2fs_fault_name[type], func, parent_func);
                return true;
        }
        return false;
}
#else
static inline bool time_to_inject(struct f2fs_sb_info *sbi, int type)
{
        return false;
}
#endif

/*
 * Test if the mounted volume is a multi-device volume.
 *   - For a single regular disk volume, sbi->s_ndevs is 0.
 *   - For a single zoned disk volume, sbi->s_ndevs is 1.
 *   - For a multi-device volume, sbi->s_ndevs is always 2 or more.
 */
static inline bool f2fs_is_multi_device(struct f2fs_sb_info *sbi)
{
        return sbi->s_ndevs > 1;
}

static inline void f2fs_update_time(struct f2fs_sb_info *sbi, int type)
{
        unsigned long now = jiffies;

        sbi->last_time[type] = now;

        /* DISCARD_TIME and GC_TIME are based on REQ_TIME */
        if (type == REQ_TIME) {
                sbi->last_time[DISCARD_TIME] = now;
                sbi->last_time[GC_TIME] = now;
        }
}

static inline bool f2fs_time_over(struct f2fs_sb_info *sbi, int type)
{
        unsigned long interval = sbi->interval_time[type] * HZ;

        return time_after(jiffies, sbi->last_time[type] + interval);
}

static inline unsigned int f2fs_time_to_wait(struct f2fs_sb_info *sbi,
                                                int type)
{
        unsigned long interval = sbi->interval_time[type] * HZ;
        unsigned int wait_ms = 0;
        long delta;

        delta = (sbi->last_time[type] + interval) - jiffies;
        if (delta > 0)
                wait_ms = jiffies_to_msecs(delta);

        return wait_ms;
}

/*
 * Inline functions
 */
static inline u32 __f2fs_crc32(struct f2fs_sb_info *sbi, u32 crc,
                              const void *address, unsigned int length)
{
        struct {
                struct shash_desc shash;
                char ctx[4];
        } desc;
        int err;

        BUG_ON(crypto_shash_descsize(sbi->s_chksum_driver) != sizeof(desc.ctx));

        desc.shash.tfm = sbi->s_chksum_driver;
        *(u32 *)desc.ctx = crc;

        err = crypto_shash_update(&desc.shash, address, length);
        BUG_ON(err);

        return *(u32 *)desc.ctx;
}

static inline u32 f2fs_crc32(struct f2fs_sb_info *sbi, const void *address,
                           unsigned int length)
{
        return __f2fs_crc32(sbi, F2FS_SUPER_MAGIC, address, length);
}

static inline bool f2fs_crc_valid(struct f2fs_sb_info *sbi, __u32 blk_crc,
                                  void *buf, size_t buf_size)
{
        return f2fs_crc32(sbi, buf, buf_size) == blk_crc;
}

static inline u32 f2fs_chksum(struct f2fs_sb_info *sbi, u32 crc,
                              const void *address, unsigned int length)
{
        return __f2fs_crc32(sbi, crc, address, length);
}

static inline struct f2fs_inode_info *F2FS_I(struct inode *inode)
{
        return container_of(inode, struct f2fs_inode_info, vfs_inode);
}

static inline struct f2fs_sb_info *F2FS_SB(struct super_block *sb)
{
        return sb->s_fs_info;
}

static inline struct f2fs_sb_info *F2FS_I_SB(struct inode *inode)
{
        return F2FS_SB(inode->i_sb);
}

static inline struct f2fs_sb_info *F2FS_M_SB(struct address_space *mapping)
{
        return F2FS_I_SB(mapping->host);
}

static inline struct f2fs_sb_info *F2FS_P_SB(struct page *page)
{
        return F2FS_M_SB(page_file_mapping(page));
}

static inline struct f2fs_super_block *F2FS_RAW_SUPER(struct f2fs_sb_info *sbi)
{
        return (struct f2fs_super_block *)(sbi->raw_super);
}

static inline struct f2fs_super_block *F2FS_SUPER_BLOCK(struct folio *folio,
                                                                pgoff_t index)
{
        pgoff_t idx_in_folio = index % (1 << folio_order(folio));

        return (struct f2fs_super_block *)
                (page_address(folio_page(folio, idx_in_folio)) +
                                                F2FS_SUPER_OFFSET);
}

static inline struct f2fs_checkpoint *F2FS_CKPT(struct f2fs_sb_info *sbi)
{
        return (struct f2fs_checkpoint *)(sbi->ckpt);
}

static inline struct f2fs_node *F2FS_NODE(struct page *page)
{
        return (struct f2fs_node *)page_address(page);
}

static inline struct f2fs_inode *F2FS_INODE(struct page *page)
{
        return &((struct f2fs_node *)page_address(page))->i;
}

static inline struct f2fs_nm_info *NM_I(struct f2fs_sb_info *sbi)
{
        return (struct f2fs_nm_info *)(sbi->nm_info);
}

static inline struct f2fs_sm_info *SM_I(struct f2fs_sb_info *sbi)
{
        return (struct f2fs_sm_info *)(sbi->sm_info);
}

static inline struct sit_info *SIT_I(struct f2fs_sb_info *sbi)
{
        return (struct sit_info *)(SM_I(sbi)->sit_info);
}

static inline struct free_segmap_info *FREE_I(struct f2fs_sb_info *sbi)
{
        return (struct free_segmap_info *)(SM_I(sbi)->free_info);
}

static inline struct dirty_seglist_info *DIRTY_I(struct f2fs_sb_info *sbi)
{
        return (struct dirty_seglist_info *)(SM_I(sbi)->dirty_info);
}

static inline struct address_space *META_MAPPING(struct f2fs_sb_info *sbi)
{
        return sbi->meta_inode->i_mapping;
}

static inline struct address_space *NODE_MAPPING(struct f2fs_sb_info *sbi)
{
        return sbi->node_inode->i_mapping;
}

static inline bool is_sbi_flag_set(struct f2fs_sb_info *sbi, unsigned int type)
{
        return test_bit(type, &sbi->s_flag);
}

static inline void set_sbi_flag(struct f2fs_sb_info *sbi, unsigned int type)
{
        set_bit(type, &sbi->s_flag);
}

static inline void clear_sbi_flag(struct f2fs_sb_info *sbi, unsigned int type)
{
        clear_bit(type, &sbi->s_flag);
}

static inline unsigned long long cur_cp_version(struct f2fs_checkpoint *cp)
{
        return le64_to_cpu(cp->checkpoint_ver);
}

static inline unsigned long f2fs_qf_ino(struct super_block *sb, int type)
{
        if (type < F2FS_MAX_QUOTAS)
                return le32_to_cpu(F2FS_SB(sb)->raw_super->qf_ino[type]);
        return 0;
}

static inline __u64 cur_cp_crc(struct f2fs_checkpoint *cp)
{
        size_t crc_offset = le32_to_cpu(cp->checksum_offset);
        return le32_to_cpu(*((__le32 *)((unsigned char *)cp + crc_offset)));
}

static inline bool __is_set_ckpt_flags(struct f2fs_checkpoint *cp, unsigned int f)
{
        unsigned int ckpt_flags = le32_to_cpu(cp->ckpt_flags);

        return ckpt_flags & f;
}

static inline bool is_set_ckpt_flags(struct f2fs_sb_info *sbi, unsigned int f)
{
        return __is_set_ckpt_flags(F2FS_CKPT(sbi), f);
}

static inline void __set_ckpt_flags(struct f2fs_checkpoint *cp, unsigned int f)
{
        unsigned int ckpt_flags;

        ckpt_flags = le32_to_cpu(cp->ckpt_flags);
        ckpt_flags |= f;
        cp->ckpt_flags = cpu_to_le32(ckpt_flags);
}

static inline void set_ckpt_flags(struct f2fs_sb_info *sbi, unsigned int f)
{
        unsigned long flags;

        spin_lock_irqsave(&sbi->cp_lock, flags);
        __set_ckpt_flags(F2FS_CKPT(sbi), f);
        spin_unlock_irqrestore(&sbi->cp_lock, flags);
}

static inline void __clear_ckpt_flags(struct f2fs_checkpoint *cp, unsigned int f)
{
        unsigned int ckpt_flags;

        ckpt_flags = le32_to_cpu(cp->ckpt_flags);
        ckpt_flags &= (~f);
        cp->ckpt_flags = cpu_to_le32(ckpt_flags);
}

static inline void clear_ckpt_flags(struct f2fs_sb_info *sbi, unsigned int f)
{
        unsigned long flags;

        spin_lock_irqsave(&sbi->cp_lock, flags);
        __clear_ckpt_flags(F2FS_CKPT(sbi), f);
        spin_unlock_irqrestore(&sbi->cp_lock, flags);
}

#define init_f2fs_rwsem(sem)                                        \
do {                                                                \
        static struct lock_class_key __key;                        \
                                                                \
        __init_f2fs_rwsem((sem), #sem, &__key);                        \
} while (0)

static inline void __init_f2fs_rwsem(struct f2fs_rwsem *sem,
                const char *sem_name, struct lock_class_key *key)
{
        __init_rwsem(&sem->internal_rwsem, sem_name, key);
#ifdef CONFIG_F2FS_UNFAIR_RWSEM
        init_waitqueue_head(&sem->read_waiters);
#endif
}

static inline int f2fs_rwsem_is_locked(struct f2fs_rwsem *sem)
{
        return rwsem_is_locked(&sem->internal_rwsem);
}

static inline int f2fs_rwsem_is_contended(struct f2fs_rwsem *sem)
{
        return rwsem_is_contended(&sem->internal_rwsem);
}

static inline void f2fs_down_read(struct f2fs_rwsem *sem)
{
#ifdef CONFIG_F2FS_UNFAIR_RWSEM
        wait_event(sem->read_waiters, down_read_trylock(&sem->internal_rwsem));
#else
        down_read(&sem->internal_rwsem);
#endif
}

static inline int f2fs_down_read_trylock(struct f2fs_rwsem *sem)
{
        return down_read_trylock(&sem->internal_rwsem);
}

static inline void f2fs_up_read(struct f2fs_rwsem *sem)
{
        up_read(&sem->internal_rwsem);
}

static inline void f2fs_down_write(struct f2fs_rwsem *sem)
{
        down_write(&sem->internal_rwsem);
}

#ifdef CONFIG_DEBUG_LOCK_ALLOC
static inline void f2fs_down_read_nested(struct f2fs_rwsem *sem, int subclass)
{
        down_read_nested(&sem->internal_rwsem, subclass);
}

static inline void f2fs_down_write_nested(struct f2fs_rwsem *sem, int subclass)
{
        down_write_nested(&sem->internal_rwsem, subclass);
}
#else
#define f2fs_down_read_nested(sem, subclass) f2fs_down_read(sem)
#define f2fs_down_write_nested(sem, subclass) f2fs_down_write(sem)
#endif

static inline int f2fs_down_write_trylock(struct f2fs_rwsem *sem)
{
        return down_write_trylock(&sem->internal_rwsem);
}

static inline void f2fs_up_write(struct f2fs_rwsem *sem)
{
        up_write(&sem->internal_rwsem);
#ifdef CONFIG_F2FS_UNFAIR_RWSEM
        wake_up_all(&sem->read_waiters);
#endif
}

static inline void f2fs_lock_op(struct f2fs_sb_info *sbi)
{
        f2fs_down_read(&sbi->cp_rwsem);
}

static inline int f2fs_trylock_op(struct f2fs_sb_info *sbi)
{
        if (time_to_inject(sbi, FAULT_LOCK_OP))
                return 0;
        return f2fs_down_read_trylock(&sbi->cp_rwsem);
}

static inline void f2fs_unlock_op(struct f2fs_sb_info *sbi)
{
        f2fs_up_read(&sbi->cp_rwsem);
}

static inline void f2fs_lock_all(struct f2fs_sb_info *sbi)
{
        f2fs_down_write(&sbi->cp_rwsem);
}

static inline void f2fs_unlock_all(struct f2fs_sb_info *sbi)
{
        f2fs_up_write(&sbi->cp_rwsem);
}

static inline int __get_cp_reason(struct f2fs_sb_info *sbi)
{
        int reason = CP_SYNC;

        if (test_opt(sbi, FASTBOOT))
                reason = CP_FASTBOOT;
        if (is_sbi_flag_set(sbi, SBI_IS_CLOSE))
                reason = CP_UMOUNT;
        return reason;
}

static inline bool __remain_node_summaries(int reason)
{
        return (reason & (CP_UMOUNT | CP_FASTBOOT));
}

static inline bool __exist_node_summaries(struct f2fs_sb_info *sbi)
{
        return (is_set_ckpt_flags(sbi, CP_UMOUNT_FLAG) ||
                        is_set_ckpt_flags(sbi, CP_FASTBOOT_FLAG));
}

/*
 * Check whether the inode has blocks or not
 */
static inline int F2FS_HAS_BLOCKS(struct inode *inode)
{
        block_t xattr_block = F2FS_I(inode)->i_xattr_nid ? 1 : 0;

        return (inode->i_blocks >> F2FS_LOG_SECTORS_PER_BLOCK) > xattr_block;
}

static inline bool f2fs_has_xattr_block(unsigned int ofs)
{
        return ofs == XATTR_NODE_OFFSET;
}

static inline bool __allow_reserved_blocks(struct f2fs_sb_info *sbi,
                                        struct inode *inode, bool cap)
{
        if (!inode)
                return true;
        if (!test_opt(sbi, RESERVE_ROOT))
                return false;
        if (IS_NOQUOTA(inode))
                return true;
        if (uid_eq(F2FS_OPTION(sbi).s_resuid, current_fsuid()))
                return true;
        if (!gid_eq(F2FS_OPTION(sbi).s_resgid, GLOBAL_ROOT_GID) &&
                                        in_group_p(F2FS_OPTION(sbi).s_resgid))
                return true;
        if (cap && capable(CAP_SYS_RESOURCE))
                return true;
        return false;
}

static inline unsigned int get_available_block_count(struct f2fs_sb_info *sbi,
                                                struct inode *inode, bool cap)
{
        block_t avail_user_block_count;

        avail_user_block_count = sbi->user_block_count -
                                        sbi->current_reserved_blocks;

        if (!__allow_reserved_blocks(sbi, inode, cap))
                avail_user_block_count -= F2FS_OPTION(sbi).root_reserved_blocks;

        if (unlikely(is_sbi_flag_set(sbi, SBI_CP_DISABLED))) {
                if (avail_user_block_count > sbi->unusable_block_count)
                        avail_user_block_count -= sbi->unusable_block_count;
                else
                        avail_user_block_count = 0;
        }

        return avail_user_block_count;
}

static inline void f2fs_i_blocks_write(struct inode *, block_t, bool, bool);
static inline int inc_valid_block_count(struct f2fs_sb_info *sbi,
                                 struct inode *inode, blkcnt_t *count, bool partial)
{
        long long diff = 0, release = 0;
        block_t avail_user_block_count;
        int ret;

        ret = dquot_reserve_block(inode, *count);
        if (ret)
                return ret;

        if (time_to_inject(sbi, FAULT_BLOCK)) {
                release = *count;
                goto release_quota;
        }

        /*
         * let's increase this in prior to actual block count change in order
         * for f2fs_sync_file to avoid data races when deciding checkpoint.
         */
        percpu_counter_add(&sbi->alloc_valid_block_count, (*count));

        spin_lock(&sbi->stat_lock);

        avail_user_block_count = get_available_block_count(sbi, inode, true);
        diff = (long long)sbi->total_valid_block_count + *count -
                                                avail_user_block_count;
        if (unlikely(diff > 0)) {
                if (!partial) {
                        spin_unlock(&sbi->stat_lock);
                        release = *count;
                        goto enospc;
                }
                if (diff > *count)
                        diff = *count;
                *count -= diff;
                release = diff;
                if (!*count) {
                        spin_unlock(&sbi->stat_lock);
                        goto enospc;
                }
        }
        sbi->total_valid_block_count += (block_t)(*count);

        spin_unlock(&sbi->stat_lock);

        if (unlikely(release)) {
                percpu_counter_sub(&sbi->alloc_valid_block_count, release);
                dquot_release_reservation_block(inode, release);
        }
        f2fs_i_blocks_write(inode, *count, true, true);
        return 0;

enospc:
        percpu_counter_sub(&sbi->alloc_valid_block_count, release);
release_quota:
        dquot_release_reservation_block(inode, release);
        return -ENOSPC;
}

#define PAGE_PRIVATE_GET_FUNC(name, flagname) \
static inline bool page_private_##name(struct page *page) \
{ \
        return PagePrivate(page) && \
                test_bit(PAGE_PRIVATE_NOT_POINTER, &page_private(page)) && \
                test_bit(PAGE_PRIVATE_##flagname, &page_private(page)); \
}

#define PAGE_PRIVATE_SET_FUNC(name, flagname) \
static inline void set_page_private_##name(struct page *page) \
{ \
        if (!PagePrivate(page)) \
                attach_page_private(page, (void *)0); \
        set_bit(PAGE_PRIVATE_NOT_POINTER, &page_private(page)); \
        set_bit(PAGE_PRIVATE_##flagname, &page_private(page)); \
}

#define PAGE_PRIVATE_CLEAR_FUNC(name, flagname) \
static inline void clear_page_private_##name(struct page *page) \
{ \
        clear_bit(PAGE_PRIVATE_##flagname, &page_private(page)); \
        if (page_private(page) == BIT(PAGE_PRIVATE_NOT_POINTER)) \
                detach_page_private(page); \
}

PAGE_PRIVATE_GET_FUNC(nonpointer, NOT_POINTER);
PAGE_PRIVATE_GET_FUNC(inline, INLINE_INODE);
PAGE_PRIVATE_GET_FUNC(gcing, ONGOING_MIGRATION);
PAGE_PRIVATE_GET_FUNC(atomic, ATOMIC_WRITE);

PAGE_PRIVATE_SET_FUNC(reference, REF_RESOURCE);
PAGE_PRIVATE_SET_FUNC(inline, INLINE_INODE);
PAGE_PRIVATE_SET_FUNC(gcing, ONGOING_MIGRATION);
PAGE_PRIVATE_SET_FUNC(atomic, ATOMIC_WRITE);

PAGE_PRIVATE_CLEAR_FUNC(reference, REF_RESOURCE);
PAGE_PRIVATE_CLEAR_FUNC(inline, INLINE_INODE);
PAGE_PRIVATE_CLEAR_FUNC(gcing, ONGOING_MIGRATION);
PAGE_PRIVATE_CLEAR_FUNC(atomic, ATOMIC_WRITE);

static inline unsigned long get_page_private_data(struct page *page)
{
        unsigned long data = page_private(page);

        if (!test_bit(PAGE_PRIVATE_NOT_POINTER, &data))
                return 0;
        return data >> PAGE_PRIVATE_MAX;
}

static inline void set_page_private_data(struct page *page, unsigned long data)
{
        if (!PagePrivate(page))
                attach_page_private(page, (void *)0);
        set_bit(PAGE_PRIVATE_NOT_POINTER, &page_private(page));
        page_private(page) |= data << PAGE_PRIVATE_MAX;
}

static inline void clear_page_private_data(struct page *page)
{
        page_private(page) &= GENMASK(PAGE_PRIVATE_MAX - 1, 0);
        if (page_private(page) == BIT(PAGE_PRIVATE_NOT_POINTER))
                detach_page_private(page);
}

static inline void clear_page_private_all(struct page *page)
{
        clear_page_private_data(page);
        clear_page_private_reference(page);
        clear_page_private_gcing(page);
        clear_page_private_inline(page);
        clear_page_private_atomic(page);

        f2fs_bug_on(F2FS_P_SB(page), page_private(page));
}

static inline void dec_valid_block_count(struct f2fs_sb_info *sbi,
                                                struct inode *inode,
                                                block_t count)
{
        blkcnt_t sectors = count << F2FS_LOG_SECTORS_PER_BLOCK;

        spin_lock(&sbi->stat_lock);
        f2fs_bug_on(sbi, sbi->total_valid_block_count < (block_t) count);
        sbi->total_valid_block_count -= (block_t)count;
        if (sbi->reserved_blocks &&
                sbi->current_reserved_blocks < sbi->reserved_blocks)
                sbi->current_reserved_blocks = min(sbi->reserved_blocks,
                                        sbi->current_reserved_blocks + count);
        spin_unlock(&sbi->stat_lock);
        if (unlikely(inode->i_blocks < sectors)) {
                f2fs_warn(sbi, "Inconsistent i_blocks, ino:%lu, iblocks:%llu, sectors:%llu",
                          inode->i_ino,
                          (unsigned long long)inode->i_blocks,
                          (unsigned long long)sectors);
                set_sbi_flag(sbi, SBI_NEED_FSCK);
                return;
        }
        f2fs_i_blocks_write(inode, count, false, true);
}

static inline void inc_page_count(struct f2fs_sb_info *sbi, int count_type)
{
        atomic_inc(&sbi->nr_pages[count_type]);

        if (count_type == F2FS_DIRTY_DENTS ||
                        count_type == F2FS_DIRTY_NODES ||
                        count_type == F2FS_DIRTY_META ||
                        count_type == F2FS_DIRTY_QDATA ||
                        count_type == F2FS_DIRTY_IMETA)
                set_sbi_flag(sbi, SBI_IS_DIRTY);
}

static inline void inode_inc_dirty_pages(struct inode *inode)
{
        atomic_inc(&F2FS_I(inode)->dirty_pages);
        inc_page_count(F2FS_I_SB(inode), S_ISDIR(inode->i_mode) ?
                                F2FS_DIRTY_DENTS : F2FS_DIRTY_DATA);
        if (IS_NOQUOTA(inode))
                inc_page_count(F2FS_I_SB(inode), F2FS_DIRTY_QDATA);
}

static inline void dec_page_count(struct f2fs_sb_info *sbi, int count_type)
{
        atomic_dec(&sbi->nr_pages[count_type]);
}

static inline void inode_dec_dirty_pages(struct inode *inode)
{
        if (!S_ISDIR(inode->i_mode) && !S_ISREG(inode->i_mode) &&
                        !S_ISLNK(inode->i_mode))
                return;

        atomic_dec(&F2FS_I(inode)->dirty_pages);
        dec_page_count(F2FS_I_SB(inode), S_ISDIR(inode->i_mode) ?
                                F2FS_DIRTY_DENTS : F2FS_DIRTY_DATA);
        if (IS_NOQUOTA(inode))
                dec_page_count(F2FS_I_SB(inode), F2FS_DIRTY_QDATA);
}

static inline void inc_atomic_write_cnt(struct inode *inode)
{
        struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
        struct f2fs_inode_info *fi = F2FS_I(inode);
        u64 current_write;

        fi->atomic_write_cnt++;
        atomic64_inc(&sbi->current_atomic_write);
        current_write = atomic64_read(&sbi->current_atomic_write);
        if (current_write > sbi->peak_atomic_write)
                sbi->peak_atomic_write = current_write;
}

static inline void release_atomic_write_cnt(struct inode *inode)
{
        struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
        struct f2fs_inode_info *fi = F2FS_I(inode);

        atomic64_sub(fi->atomic_write_cnt, &sbi->current_atomic_write);
        fi->atomic_write_cnt = 0;
}

static inline s64 get_pages(struct f2fs_sb_info *sbi, int count_type)
{
        return atomic_read(&sbi->nr_pages[count_type]);
}

static inline int get_dirty_pages(struct inode *inode)
{
        return atomic_read(&F2FS_I(inode)->dirty_pages);
}

static inline int get_blocktype_secs(struct f2fs_sb_info *sbi, int block_type)
{
        return div_u64(get_pages(sbi, block_type) + BLKS_PER_SEC(sbi) - 1,
                                                        BLKS_PER_SEC(sbi));
}

static inline block_t valid_user_blocks(struct f2fs_sb_info *sbi)
{
        return sbi->total_valid_block_count;
}

static inline block_t discard_blocks(struct f2fs_sb_info *sbi)
{
        return sbi->discard_blks;
}

static inline unsigned long __bitmap_size(struct f2fs_sb_info *sbi, int flag)
{
        struct f2fs_checkpoint *ckpt = F2FS_CKPT(sbi);

        /* return NAT or SIT bitmap */
        if (flag == NAT_BITMAP)
                return le32_to_cpu(ckpt->nat_ver_bitmap_bytesize);
        else if (flag == SIT_BITMAP)
                return le32_to_cpu(ckpt->sit_ver_bitmap_bytesize);

        return 0;
}

static inline block_t __cp_payload(struct f2fs_sb_info *sbi)
{
        return le32_to_cpu(F2FS_RAW_SUPER(sbi)->cp_payload);
}

static inline void *__bitmap_ptr(struct f2fs_sb_info *sbi, int flag)
{
        struct f2fs_checkpoint *ckpt = F2FS_CKPT(sbi);
        void *tmp_ptr = &ckpt->sit_nat_version_bitmap;
        int offset;

        if (is_set_ckpt_flags(sbi, CP_LARGE_NAT_BITMAP_FLAG)) {
                offset = (flag == SIT_BITMAP) ?
                        le32_to_cpu(ckpt->nat_ver_bitmap_bytesize) : 0;
                /*
                 * if large_nat_bitmap feature is enabled, leave checksum
                 * protection for all nat/sit bitmaps.
                 */
                return tmp_ptr + offset + sizeof(__le32);
        }

        if (__cp_payload(sbi) > 0) {
                if (flag == NAT_BITMAP)
                        return tmp_ptr;
                else
                        return (unsigned char *)ckpt + F2FS_BLKSIZE;
        } else {
                offset = (flag == NAT_BITMAP) ?
                        le32_to_cpu(ckpt->sit_ver_bitmap_bytesize) : 0;
                return tmp_ptr + offset;
        }
}

static inline block_t __start_cp_addr(struct f2fs_sb_info *sbi)
{
        block_t start_addr = le32_to_cpu(F2FS_RAW_SUPER(sbi)->cp_blkaddr);

        if (sbi->cur_cp_pack == 2)
                start_addr += BLKS_PER_SEG(sbi);
        return start_addr;
}

static inline block_t __start_cp_next_addr(struct f2fs_sb_info *sbi)
{
        block_t start_addr = le32_to_cpu(F2FS_RAW_SUPER(sbi)->cp_blkaddr);

        if (sbi->cur_cp_pack == 1)
                start_addr += BLKS_PER_SEG(sbi);
        return start_addr;
}

static inline void __set_cp_next_pack(struct f2fs_sb_info *sbi)
{
        sbi->cur_cp_pack = (sbi->cur_cp_pack == 1) ? 2 : 1;
}

static inline block_t __start_sum_addr(struct f2fs_sb_info *sbi)
{
        return le32_to_cpu(F2FS_CKPT(sbi)->cp_pack_start_sum);
}

extern void f2fs_mark_inode_dirty_sync(struct inode *inode, bool sync);
static inline int inc_valid_node_count(struct f2fs_sb_info *sbi,
                                        struct inode *inode, bool is_inode)
{
        block_t        valid_block_count;
        unsigned int valid_node_count;
        unsigned int avail_user_block_count;
        int err;

        if (is_inode) {
                if (inode) {
                        err = dquot_alloc_inode(inode);
                        if (err)
                                return err;
                }
        } else {
                err = dquot_reserve_block(inode, 1);
                if (err)
                        return err;
        }

        if (time_to_inject(sbi, FAULT_BLOCK))
                goto enospc;

        spin_lock(&sbi->stat_lock);

        valid_block_count = sbi->total_valid_block_count + 1;
        avail_user_block_count = get_available_block_count(sbi, inode, false);

        if (unlikely(valid_block_count > avail_user_block_count)) {
                spin_unlock(&sbi->stat_lock);
                goto enospc;
        }

        valid_node_count = sbi->total_valid_node_count + 1;
        if (unlikely(valid_node_count > sbi->total_node_count)) {
                spin_unlock(&sbi->stat_lock);
                goto enospc;
        }

        sbi->total_valid_node_count++;
        sbi->total_valid_block_count++;
        spin_unlock(&sbi->stat_lock);

        if (inode) {
                if (is_inode)
                        f2fs_mark_inode_dirty_sync(inode, true);
                else
                        f2fs_i_blocks_write(inode, 1, true, true);
        }

        percpu_counter_inc(&sbi->alloc_valid_block_count);
        return 0;

enospc:
        if (is_inode) {
                if (inode)
                        dquot_free_inode(inode);
        } else {
                dquot_release_reservation_block(inode, 1);
        }
        return -ENOSPC;
}

static inline void dec_valid_node_count(struct f2fs_sb_info *sbi,
                                        struct inode *inode, bool is_inode)
{
        spin_lock(&sbi->stat_lock);

        if (unlikely(!sbi->total_valid_block_count ||
                        !sbi->total_valid_node_count)) {
                f2fs_warn(sbi, "dec_valid_node_count: inconsistent block counts, total_valid_block:%u, total_valid_node:%u",
                          sbi->total_valid_block_count,
                          sbi->total_valid_node_count);
                set_sbi_flag(sbi, SBI_NEED_FSCK);
        } else {
                sbi->total_valid_block_count--;
                sbi->total_valid_node_count--;
        }

        if (sbi->reserved_blocks &&
                sbi->current_reserved_blocks < sbi->reserved_blocks)
                sbi->current_reserved_blocks++;

        spin_unlock(&sbi->stat_lock);

        if (is_inode) {
                dquot_free_inode(inode);
        } else {
                if (unlikely(inode->i_blocks == 0)) {
                        f2fs_warn(sbi, "dec_valid_node_count: inconsistent i_blocks, ino:%lu, iblocks:%llu",
                                  inode->i_ino,
                                  (unsigned long long)inode->i_blocks);
                        set_sbi_flag(sbi, SBI_NEED_FSCK);
                        return;
                }
                f2fs_i_blocks_write(inode, 1, false, true);
        }
}

static inline unsigned int valid_node_count(struct f2fs_sb_info *sbi)
{
        return sbi->total_valid_node_count;
}

static inline void inc_valid_inode_count(struct f2fs_sb_info *sbi)
{
        percpu_counter_inc(&sbi->total_valid_inode_count);
}

static inline void dec_valid_inode_count(struct f2fs_sb_info *sbi)
{
        percpu_counter_dec(&sbi->total_valid_inode_count);
}

static inline s64 valid_inode_count(struct f2fs_sb_info *sbi)
{
        return percpu_counter_sum_positive(&sbi->total_valid_inode_count);
}

static inline struct page *f2fs_grab_cache_page(struct address_space *mapping,
                                                pgoff_t index, bool for_write)
{
        struct page *page;
        unsigned int flags;

        if (IS_ENABLED(CONFIG_F2FS_FAULT_INJECTION)) {
                if (!for_write)
                        page = find_get_page_flags(mapping, index,
                                                        FGP_LOCK | FGP_ACCESSED);
                else
                        page = find_lock_page(mapping, index);
                if (page)
                        return page;

                if (time_to_inject(F2FS_M_SB(mapping), FAULT_PAGE_ALLOC))
                        return NULL;
        }

        if (!for_write)
                return grab_cache_page(mapping, index);

        flags = memalloc_nofs_save();
        page = grab_cache_page_write_begin(mapping, index);
        memalloc_nofs_restore(flags);

        return page;
}

static inline struct page *f2fs_pagecache_get_page(
                                struct address_space *mapping, pgoff_t index,
                                fgf_t fgp_flags, gfp_t gfp_mask)
{
        if (time_to_inject(F2FS_M_SB(mapping), FAULT_PAGE_GET))
                return NULL;

        return pagecache_get_page(mapping, index, fgp_flags, gfp_mask);
}

static inline void f2fs_put_page(struct page *page, int unlock)
{
        if (!page)
                return;

        if (unlock) {
                f2fs_bug_on(F2FS_P_SB(page), !PageLocked(page));
                unlock_page(page);
        }
        put_page(page);
}

static inline void f2fs_put_dnode(struct dnode_of_data *dn)
{
        if (dn->node_page)
                f2fs_put_page(dn->node_page, 1);
        if (dn->inode_page && dn->node_page != dn->inode_page)
                f2fs_put_page(dn->inode_page, 0);
        dn->node_page = NULL;
        dn->inode_page = NULL;
}

static inline struct kmem_cache *f2fs_kmem_cache_create(const char *name,
                                        size_t size)
{
        return kmem_cache_create(name, size, 0, SLAB_RECLAIM_ACCOUNT, NULL);
}

static inline void *f2fs_kmem_cache_alloc_nofail(struct kmem_cache *cachep,
                                                gfp_t flags)
{
        void *entry;

        entry = kmem_cache_alloc(cachep, flags);
        if (!entry)
                entry = kmem_cache_alloc(cachep, flags | __GFP_NOFAIL);
        return entry;
}

static inline void *f2fs_kmem_cache_alloc(struct kmem_cache *cachep,
                        gfp_t flags, bool nofail, struct f2fs_sb_info *sbi)
{
        if (nofail)
                return f2fs_kmem_cache_alloc_nofail(cachep, flags);

        if (time_to_inject(sbi, FAULT_SLAB_ALLOC))
                return NULL;

        return kmem_cache_alloc(cachep, flags);
}

static inline bool is_inflight_io(struct f2fs_sb_info *sbi, int type)
{
        if (get_pages(sbi, F2FS_RD_DATA) || get_pages(sbi, F2FS_RD_NODE) ||
                get_pages(sbi, F2FS_RD_META) || get_pages(sbi, F2FS_WB_DATA) ||
                get_pages(sbi, F2FS_WB_CP_DATA) ||
                get_pages(sbi, F2FS_DIO_READ) ||
                get_pages(sbi, F2FS_DIO_WRITE))
                return true;

        if (type != DISCARD_TIME && SM_I(sbi) && SM_I(sbi)->dcc_info &&
                        atomic_read(&SM_I(sbi)->dcc_info->queued_discard))
                return true;

        if (SM_I(sbi) && SM_I(sbi)->fcc_info &&
                        atomic_read(&SM_I(sbi)->fcc_info->queued_flush))
                return true;
        return false;
}

static inline bool is_inflight_read_io(struct f2fs_sb_info *sbi)
{
        return get_pages(sbi, F2FS_RD_DATA) || get_pages(sbi, F2FS_DIO_READ);
}

static inline bool is_idle(struct f2fs_sb_info *sbi, int type)
{
        bool zoned_gc = (type == GC_TIME &&
                        F2FS_HAS_FEATURE(sbi, F2FS_FEATURE_BLKZONED));

        if (sbi->gc_mode == GC_URGENT_HIGH)
                return true;

        if (zoned_gc) {
                if (is_inflight_read_io(sbi))
                        return false;
        } else {
                if (is_inflight_io(sbi, type))
                        return false;
        }

        if (sbi->gc_mode == GC_URGENT_MID)
                return true;

        if (sbi->gc_mode == GC_URGENT_LOW &&
                        (type == DISCARD_TIME || type == GC_TIME))
                return true;

        if (zoned_gc)
                return true;

        return f2fs_time_over(sbi, type);
}

static inline void f2fs_radix_tree_insert(struct radix_tree_root *root,
                                unsigned long index, void *item)
{
        while (radix_tree_insert(root, index, item))
                cond_resched();
}

#define RAW_IS_INODE(p)        ((p)->footer.nid == (p)->footer.ino)

static inline bool IS_INODE(struct page *page)
{
        struct f2fs_node *p = F2FS_NODE(page);

        return RAW_IS_INODE(p);
}

static inline int offset_in_addr(struct f2fs_inode *i)
{
        return (i->i_inline & F2FS_EXTRA_ATTR) ?
                        (le16_to_cpu(i->i_extra_isize) / sizeof(__le32)) : 0;
}

static inline __le32 *blkaddr_in_node(struct f2fs_node *node)
{
        return RAW_IS_INODE(node) ? node->i.i_addr : node->dn.addr;
}

static inline int f2fs_has_extra_attr(struct inode *inode);
static inline unsigned int get_dnode_base(struct inode *inode,
                                        struct page *node_page)
{
        if (!IS_INODE(node_page))
                return 0;

        return inode ? get_extra_isize(inode) :
                        offset_in_addr(&F2FS_NODE(node_page)->i);
}

static inline __le32 *get_dnode_addr(struct inode *inode,
                                        struct page *node_page)
{
        return blkaddr_in_node(F2FS_NODE(node_page)) +
                        get_dnode_base(inode, node_page);
}

static inline block_t data_blkaddr(struct inode *inode,
                        struct page *node_page, unsigned int offset)
{
        return le32_to_cpu(*(get_dnode_addr(inode, node_page) + offset));
}

static inline block_t f2fs_data_blkaddr(struct dnode_of_data *dn)
{
        return data_blkaddr(dn->inode, dn->node_page, dn->ofs_in_node);
}

static inline int f2fs_test_bit(unsigned int nr, char *addr)
{
        int mask;

        addr += (nr >> 3);
        mask = BIT(7 - (nr & 0x07));
        return mask & *addr;
}

static inline void f2fs_set_bit(unsigned int nr, char *addr)
{
        int mask;

        addr += (nr >> 3);
        mask = BIT(7 - (nr & 0x07));
        *addr |= mask;
}

static inline void f2fs_clear_bit(unsigned int nr, char *addr)
{
        int mask;

        addr += (nr >> 3);
        mask = BIT(7 - (nr & 0x07));
        *addr &= ~mask;
}

static inline int f2fs_test_and_set_bit(unsigned int nr, char *addr)
{
        int mask;
        int ret;

        addr += (nr >> 3);
        mask = BIT(7 - (nr & 0x07));
        ret = mask & *addr;
        *addr |= mask;
        return ret;
}

static inline int f2fs_test_and_clear_bit(unsigned int nr, char *addr)
{
        int mask;
        int ret;

        addr += (nr >> 3);
        mask = BIT(7 - (nr & 0x07));
        ret = mask & *addr;
        *addr &= ~mask;
        return ret;
}

static inline void f2fs_change_bit(unsigned int nr, char *addr)
{
        int mask;

        addr += (nr >> 3);
        mask = BIT(7 - (nr & 0x07));
        *addr ^= mask;
}

/*
 * On-disk inode flags (f2fs_inode::i_flags)
 */
#define F2FS_COMPR_FL                        0x00000004 /* Compress file */
#define F2FS_SYNC_FL                        0x00000008 /* Synchronous updates */
#define F2FS_IMMUTABLE_FL                0x00000010 /* Immutable file */
#define F2FS_APPEND_FL                        0x00000020 /* writes to file may only append */
#define F2FS_NODUMP_FL                        0x00000040 /* do not dump file */
#define F2FS_NOATIME_FL                        0x00000080 /* do not update atime */
#define F2FS_NOCOMP_FL                        0x00000400 /* Don't compress */
#define F2FS_INDEX_FL                        0x00001000 /* hash-indexed directory */
#define F2FS_DIRSYNC_FL                        0x00010000 /* dirsync behaviour (directories only) */
#define F2FS_PROJINHERIT_FL                0x20000000 /* Create with parents projid */
#define F2FS_CASEFOLD_FL                0x40000000 /* Casefolded file */
#define F2FS_DEVICE_ALIAS_FL                0x80000000 /* File for aliasing a device */

#define F2FS_QUOTA_DEFAULT_FL                (F2FS_NOATIME_FL | F2FS_IMMUTABLE_FL)

/* Flags that should be inherited by new inodes from their parent. */
#define F2FS_FL_INHERITED (F2FS_SYNC_FL | F2FS_NODUMP_FL | F2FS_NOATIME_FL | \
                           F2FS_DIRSYNC_FL | F2FS_PROJINHERIT_FL | \
                           F2FS_CASEFOLD_FL)

/* Flags that are appropriate for regular files (all but dir-specific ones). */
#define F2FS_REG_FLMASK                (~(F2FS_DIRSYNC_FL | F2FS_PROJINHERIT_FL | \
                                F2FS_CASEFOLD_FL))

/* Flags that are appropriate for non-directories/regular files. */
#define F2FS_OTHER_FLMASK        (F2FS_NODUMP_FL | F2FS_NOATIME_FL)

#define IS_DEVICE_ALIASING(inode)        (F2FS_I(inode)->i_flags & F2FS_DEVICE_ALIAS_FL)

static inline __u32 f2fs_mask_flags(umode_t mode, __u32 flags)
{
        if (S_ISDIR(mode))
                return flags;
        else if (S_ISREG(mode))
                return flags & F2FS_REG_FLMASK;
        else
                return flags & F2FS_OTHER_FLMASK;
}

static inline void __mark_inode_dirty_flag(struct inode *inode,
                                                int flag, bool set)
{
        switch (flag) {
        case FI_INLINE_XATTR:
        case FI_INLINE_DATA:
        case FI_INLINE_DENTRY:
        case FI_NEW_INODE:
                if (set)
                        return;
                fallthrough;
        case FI_DATA_EXIST:
        case FI_PIN_FILE:
        case FI_COMPRESS_RELEASED:
                f2fs_mark_inode_dirty_sync(inode, true);
        }
}

static inline void set_inode_flag(struct inode *inode, int flag)
{
        set_bit(flag, F2FS_I(inode)->flags);
        __mark_inode_dirty_flag(inode, flag, true);
}

static inline int is_inode_flag_set(struct inode *inode, int flag)
{
        return test_bit(flag, F2FS_I(inode)->flags);
}

static inline void clear_inode_flag(struct inode *inode, int flag)
{
        clear_bit(flag, F2FS_I(inode)->flags);
        __mark_inode_dirty_flag(inode, flag, false);
}

static inline bool f2fs_verity_in_progress(struct inode *inode)
{
        return IS_ENABLED(CONFIG_FS_VERITY) &&
               is_inode_flag_set(inode, FI_VERITY_IN_PROGRESS);
}

static inline void set_acl_inode(struct inode *inode, umode_t mode)
{
        F2FS_I(inode)->i_acl_mode = mode;
        set_inode_flag(inode, FI_ACL_MODE);
        f2fs_mark_inode_dirty_sync(inode, false);
}

static inline void f2fs_i_links_write(struct inode *inode, bool inc)
{
        if (inc)
                inc_nlink(inode);
        else
                drop_nlink(inode);
        f2fs_mark_inode_dirty_sync(inode, true);
}

static inline void f2fs_i_blocks_write(struct inode *inode,
                                        block_t diff, bool add, bool claim)
{
        bool clean = !is_inode_flag_set(inode, FI_DIRTY_INODE);
        bool recover = is_inode_flag_set(inode, FI_AUTO_RECOVER);

        /* add = 1, claim = 1 should be dquot_reserve_block in pair */
        if (add) {
                if (claim)
                        dquot_claim_block(inode, diff);
                else
                        dquot_alloc_block_nofail(inode, diff);
        } else {
                dquot_free_block(inode, diff);
        }

        f2fs_mark_inode_dirty_sync(inode, true);
        if (clean || recover)
                set_inode_flag(inode, FI_AUTO_RECOVER);
}

static inline bool f2fs_is_atomic_file(struct inode *inode);

static inline void f2fs_i_size_write(struct inode *inode, loff_t i_size)
{
        bool clean = !is_inode_flag_set(inode, FI_DIRTY_INODE);
        bool recover = is_inode_flag_set(inode, FI_AUTO_RECOVER);

        if (i_size_read(inode) == i_size)
                return;

        i_size_write(inode, i_size);

        if (f2fs_is_atomic_file(inode))
                return;

        f2fs_mark_inode_dirty_sync(inode, true);
        if (clean || recover)
                set_inode_flag(inode, FI_AUTO_RECOVER);
}

static inline void f2fs_i_depth_write(struct inode *inode, unsigned int depth)
{
        F2FS_I(inode)->i_current_depth = depth;
        f2fs_mark_inode_dirty_sync(inode, true);
}

static inline void f2fs_i_gc_failures_write(struct inode *inode,
                                        unsigned int count)
{
        F2FS_I(inode)->i_gc_failures = count;
        f2fs_mark_inode_dirty_sync(inode, true);
}

static inline void f2fs_i_xnid_write(struct inode *inode, nid_t xnid)
{
        F2FS_I(inode)->i_xattr_nid = xnid;
        f2fs_mark_inode_dirty_sync(inode, true);
}

static inline void f2fs_i_pino_write(struct inode *inode, nid_t pino)
{
        F2FS_I(inode)->i_pino = pino;
        f2fs_mark_inode_dirty_sync(inode, true);
}

static inline void get_inline_info(struct inode *inode, struct f2fs_inode *ri)
{
        struct f2fs_inode_info *fi = F2FS_I(inode);

        if (ri->i_inline & F2FS_INLINE_XATTR)
                set_bit(FI_INLINE_XATTR, fi->flags);
        if (ri->i_inline & F2FS_INLINE_DATA)
                set_bit(FI_INLINE_DATA, fi->flags);
        if (ri->i_inline & F2FS_INLINE_DENTRY)
                set_bit(FI_INLINE_DENTRY, fi->flags);
        if (ri->i_inline & F2FS_DATA_EXIST)
                set_bit(FI_DATA_EXIST, fi->flags);
        if (ri->i_inline & F2FS_EXTRA_ATTR)
                set_bit(FI_EXTRA_ATTR, fi->flags);
        if (ri->i_inline & F2FS_PIN_FILE)
                set_bit(FI_PIN_FILE, fi->flags);
        if (ri->i_inline & F2FS_COMPRESS_RELEASED)
                set_bit(FI_COMPRESS_RELEASED, fi->flags);
}

static inline void set_raw_inline(struct inode *inode, struct f2fs_inode *ri)
{
        ri->i_inline = 0;

        if (is_inode_flag_set(inode, FI_INLINE_XATTR))
                ri->i_inline |= F2FS_INLINE_XATTR;
        if (is_inode_flag_set(inode, FI_INLINE_DATA))
                ri->i_inline |= F2FS_INLINE_DATA;
        if (is_inode_flag_set(inode, FI_INLINE_DENTRY))
                ri->i_inline |= F2FS_INLINE_DENTRY;
        if (is_inode_flag_set(inode, FI_DATA_EXIST))
                ri->i_inline |= F2FS_DATA_EXIST;
        if (is_inode_flag_set(inode, FI_EXTRA_ATTR))
                ri->i_inline |= F2FS_EXTRA_ATTR;
        if (is_inode_flag_set(inode, FI_PIN_FILE))
                ri->i_inline |= F2FS_PIN_FILE;
        if (is_inode_flag_set(inode, FI_COMPRESS_RELEASED))
                ri->i_inline |= F2FS_COMPRESS_RELEASED;
}

static inline int f2fs_has_extra_attr(struct inode *inode)
{
        return is_inode_flag_set(inode, FI_EXTRA_ATTR);
}

static inline int f2fs_has_inline_xattr(struct inode *inode)
{
        return is_inode_flag_set(inode, FI_INLINE_XATTR);
}

static inline int f2fs_compressed_file(struct inode *inode)
{
        return S_ISREG(inode->i_mode) &&
                is_inode_flag_set(inode, FI_COMPRESSED_FILE);
}

static inline bool f2fs_need_compress_data(struct inode *inode)
{
        int compress_mode = F2FS_OPTION(F2FS_I_SB(inode)).compress_mode;

        if (!f2fs_compressed_file(inode))
                return false;

        if (compress_mode == COMPR_MODE_FS)
                return true;
        else if (compress_mode == COMPR_MODE_USER &&
                        is_inode_flag_set(inode, FI_ENABLE_COMPRESS))
                return true;

        return false;
}

static inline unsigned int addrs_per_page(struct inode *inode,
                                                        bool is_inode)
{
        unsigned int addrs = is_inode ? (CUR_ADDRS_PER_INODE(inode) -
                        get_inline_xattr_addrs(inode)) : DEF_ADDRS_PER_BLOCK;

        if (f2fs_compressed_file(inode))
                return ALIGN_DOWN(addrs, F2FS_I(inode)->i_cluster_size);
        return addrs;
}

static inline void *inline_xattr_addr(struct inode *inode, struct page *page)
{
        struct f2fs_inode *ri = F2FS_INODE(page);

        return (void *)&(ri->i_addr[DEF_ADDRS_PER_INODE -
                                        get_inline_xattr_addrs(inode)]);
}

static inline int inline_xattr_size(struct inode *inode)
{
        if (f2fs_has_inline_xattr(inode))
                return get_inline_xattr_addrs(inode) * sizeof(__le32);
        return 0;
}

/*
 * Notice: check inline_data flag without inode page lock is unsafe.
 * It could change at any time by f2fs_convert_inline_page().
 */
static inline int f2fs_has_inline_data(struct inode *inode)
{
        return is_inode_flag_set(inode, FI_INLINE_DATA);
}

static inline int f2fs_exist_data(struct inode *inode)
{
        return is_inode_flag_set(inode, FI_DATA_EXIST);
}

static inline int f2fs_is_mmap_file(struct inode *inode)
{
        return is_inode_flag_set(inode, FI_MMAP_FILE);
}

static inline bool f2fs_is_pinned_file(struct inode *inode)
{
        return is_inode_flag_set(inode, FI_PIN_FILE);
}

static inline bool f2fs_is_atomic_file(struct inode *inode)
{
        return is_inode_flag_set(inode, FI_ATOMIC_FILE);
}

static inline bool f2fs_is_cow_file(struct inode *inode)
{
        return is_inode_flag_set(inode, FI_COW_FILE);
}

static inline void *inline_data_addr(struct inode *inode, struct page *page)
{
        __le32 *addr = get_dnode_addr(inode, page);

        return (void *)(addr + DEF_INLINE_RESERVED_SIZE);
}

static inline int f2fs_has_inline_dentry(struct inode *inode)
{
        return is_inode_flag_set(inode, FI_INLINE_DENTRY);
}

static inline int is_file(struct inode *inode, int type)
{
        return F2FS_I(inode)->i_advise & type;
}

static inline void set_file(struct inode *inode, int type)
{
        if (is_file(inode, type))
                return;
        F2FS_I(inode)->i_advise |= type;
        f2fs_mark_inode_dirty_sync(inode, true);
}

static inline void clear_file(struct inode *inode, int type)
{
        if (!is_file(inode, type))
                return;
        F2FS_I(inode)->i_advise &= ~type;
        f2fs_mark_inode_dirty_sync(inode, true);
}

static inline bool f2fs_is_time_consistent(struct inode *inode)
{
        struct timespec64 ts = inode_get_atime(inode);

        if (!timespec64_equal(F2FS_I(inode)->i_disk_time, &ts))
                return false;
        ts = inode_get_ctime(inode);
        if (!timespec64_equal(F2FS_I(inode)->i_disk_time + 1, &ts))
                return false;
        ts = inode_get_mtime(inode);
        if (!timespec64_equal(F2FS_I(inode)->i_disk_time + 2, &ts))
                return false;
        return true;
}

static inline bool f2fs_skip_inode_update(struct inode *inode, int dsync)
{
        bool ret;

        if (dsync) {
                struct f2fs_sb_info *sbi = F2FS_I_SB(inode);

                spin_lock(&sbi->inode_lock[DIRTY_META]);
                ret = list_empty(&F2FS_I(inode)->gdirty_list);
                spin_unlock(&sbi->inode_lock[DIRTY_META]);
                return ret;
        }
        if (!is_inode_flag_set(inode, FI_AUTO_RECOVER) ||
                        file_keep_isize(inode) ||
                        i_size_read(inode) & ~PAGE_MASK)
                return false;

        if (!f2fs_is_time_consistent(inode))
                return false;

        spin_lock(&F2FS_I(inode)->i_size_lock);
        ret = F2FS_I(inode)->last_disk_size == i_size_read(inode);
        spin_unlock(&F2FS_I(inode)->i_size_lock);

        return ret;
}

static inline bool f2fs_readonly(struct super_block *sb)
{
        return sb_rdonly(sb);
}

static inline bool f2fs_cp_error(struct f2fs_sb_info *sbi)
{
        return is_set_ckpt_flags(sbi, CP_ERROR_FLAG);
}

static inline void *f2fs_kmalloc(struct f2fs_sb_info *sbi,
                                        size_t size, gfp_t flags)
{
        if (time_to_inject(sbi, FAULT_KMALLOC))
                return NULL;

        return kmalloc(size, flags);
}

static inline void *f2fs_getname(struct f2fs_sb_info *sbi)
{
        if (time_to_inject(sbi, FAULT_KMALLOC))
                return NULL;

        return __getname();
}

static inline void f2fs_putname(char *buf)
{
        __putname(buf);
}

static inline void *f2fs_kzalloc(struct f2fs_sb_info *sbi,
                                        size_t size, gfp_t flags)
{
        return f2fs_kmalloc(sbi, size, flags | __GFP_ZERO);
}

static inline void *f2fs_kvmalloc(struct f2fs_sb_info *sbi,
                                        size_t size, gfp_t flags)
{
        if (time_to_inject(sbi, FAULT_KVMALLOC))
                return NULL;

        return kvmalloc(size, flags);
}

static inline void *f2fs_kvzalloc(struct f2fs_sb_info *sbi,
                                        size_t size, gfp_t flags)
{
        return f2fs_kvmalloc(sbi, size, flags | __GFP_ZERO);
}

static inline int get_extra_isize(struct inode *inode)
{
        return F2FS_I(inode)->i_extra_isize / sizeof(__le32);
}

static inline int get_inline_xattr_addrs(struct inode *inode)
{
        return F2FS_I(inode)->i_inline_xattr_size;
}

#define f2fs_get_inode_mode(i) \
        ((is_inode_flag_set(i, FI_ACL_MODE)) ? \
         (F2FS_I(i)->i_acl_mode) : ((i)->i_mode))

#define F2FS_MIN_EXTRA_ATTR_SIZE                (sizeof(__le32))

#define F2FS_TOTAL_EXTRA_ATTR_SIZE                        \
        (offsetof(struct f2fs_inode, i_extra_end) -        \
        offsetof(struct f2fs_inode, i_extra_isize))        \

#define F2FS_OLD_ATTRIBUTE_SIZE        (offsetof(struct f2fs_inode, i_addr))
#define F2FS_FITS_IN_INODE(f2fs_inode, extra_isize, field)                \
                ((offsetof(typeof(*(f2fs_inode)), field) +        \
                sizeof((f2fs_inode)->field))                        \
                <= (F2FS_OLD_ATTRIBUTE_SIZE + (extra_isize)))        \

#define __is_large_section(sbi)                (SEGS_PER_SEC(sbi) > 1)

#define __is_meta_io(fio) (PAGE_TYPE_OF_BIO((fio)->type) == META)

bool f2fs_is_valid_blkaddr(struct f2fs_sb_info *sbi,
                                        block_t blkaddr, int type);
static inline void verify_blkaddr(struct f2fs_sb_info *sbi,
                                        block_t blkaddr, int type)
{
        if (!f2fs_is_valid_blkaddr(sbi, blkaddr, type))
                f2fs_err(sbi, "invalid blkaddr: %u, type: %d, run fsck to fix.",
                         blkaddr, type);
}

static inline bool __is_valid_data_blkaddr(block_t blkaddr)
{
        if (blkaddr == NEW_ADDR || blkaddr == NULL_ADDR ||
                        blkaddr == COMPRESS_ADDR)
                return false;
        return true;
}

/*
 * file.c
 */
int f2fs_sync_file(struct file *file, loff_t start, loff_t end, int datasync);
int f2fs_do_truncate_blocks(struct inode *inode, u64 from, bool lock);
int f2fs_truncate_blocks(struct inode *inode, u64 from, bool lock);
int f2fs_truncate(struct inode *inode);
int f2fs_getattr(struct mnt_idmap *idmap, const struct path *path,
                 struct kstat *stat, u32 request_mask, unsigned int flags);
int f2fs_setattr(struct mnt_idmap *idmap, struct dentry *dentry,
                 struct iattr *attr);
int f2fs_truncate_hole(struct inode *inode, pgoff_t pg_start, pgoff_t pg_end);
void f2fs_truncate_data_blocks_range(struct dnode_of_data *dn, int count);
int f2fs_do_shutdown(struct f2fs_sb_info *sbi, unsigned int flag,
                                                bool readonly, bool need_lock);
int f2fs_precache_extents(struct inode *inode);
int f2fs_fileattr_get(struct dentry *dentry, struct fileattr *fa);
int f2fs_fileattr_set(struct mnt_idmap *idmap,
                      struct dentry *dentry, struct fileattr *fa);
long f2fs_ioctl(struct file *filp, unsigned int cmd, unsigned long arg);
long f2fs_compat_ioctl(struct file *file, unsigned int cmd, unsigned long arg);
int f2fs_transfer_project_quota(struct inode *inode, kprojid_t kprojid);
int f2fs_pin_file_control(struct inode *inode, bool inc);

/*
 * inode.c
 */
void f2fs_set_inode_flags(struct inode *inode);
bool f2fs_inode_chksum_verify(struct f2fs_sb_info *sbi, struct page *page);
void f2fs_inode_chksum_set(struct f2fs_sb_info *sbi, struct page *page);
struct inode *f2fs_iget(struct super_block *sb, unsigned long ino);
struct inode *f2fs_iget_retry(struct super_block *sb, unsigned long ino);
int f2fs_try_to_free_nats(struct f2fs_sb_info *sbi, int nr_shrink);
void f2fs_update_inode(struct inode *inode, struct page *node_page);
void f2fs_update_inode_page(struct inode *inode);
int f2fs_write_inode(struct inode *inode, struct writeback_control *wbc);
void f2fs_evict_inode(struct inode *inode);
void f2fs_handle_failed_inode(struct inode *inode);

/*
 * namei.c
 */
int f2fs_update_extension_list(struct f2fs_sb_info *sbi, const char *name,
                                                        bool hot, bool set);
struct dentry *f2fs_get_parent(struct dentry *child);
int f2fs_get_tmpfile(struct mnt_idmap *idmap, struct inode *dir,
                     struct inode **new_inode);

/*
 * dir.c
 */
#if IS_ENABLED(CONFIG_UNICODE)
int f2fs_init_casefolded_name(const struct inode *dir,
                              struct f2fs_filename *fname);
void f2fs_free_casefolded_name(struct f2fs_filename *fname);
#else
static inline int f2fs_init_casefolded_name(const struct inode *dir,
                                            struct f2fs_filename *fname)
{
        return 0;
}

static inline void f2fs_free_casefolded_name(struct f2fs_filename *fname)
{
}
#endif /* CONFIG_UNICODE */

int f2fs_setup_filename(struct inode *dir, const struct qstr *iname,
                        int lookup, struct f2fs_filename *fname);
int f2fs_prepare_lookup(struct inode *dir, struct dentry *dentry,
                        struct f2fs_filename *fname);
void f2fs_free_filename(struct f2fs_filename *fname);
struct f2fs_dir_entry *f2fs_find_target_dentry(const struct f2fs_dentry_ptr *d,
                        const struct f2fs_filename *fname, int *max_slots);
int f2fs_fill_dentries(struct dir_context *ctx, struct f2fs_dentry_ptr *d,
                        unsigned int start_pos, struct fscrypt_str *fstr);
void f2fs_do_make_empty_dir(struct inode *inode, struct inode *parent,
                        struct f2fs_dentry_ptr *d);
struct page *f2fs_init_inode_metadata(struct inode *inode, struct inode *dir,
                        const struct f2fs_filename *fname, struct page *dpage);
void f2fs_update_parent_metadata(struct inode *dir, struct inode *inode,
                        unsigned int current_depth);
int f2fs_room_for_filename(const void *bitmap, int slots, int max_slots);
void f2fs_drop_nlink(struct inode *dir, struct inode *inode);
struct f2fs_dir_entry *__f2fs_find_entry(struct inode *dir,
                                         const struct f2fs_filename *fname,
                                         struct page **res_page);
struct f2fs_dir_entry *f2fs_find_entry(struct inode *dir,
                        const struct qstr *child, struct page **res_page);
struct f2fs_dir_entry *f2fs_parent_dir(struct inode *dir, struct page **p);
ino_t f2fs_inode_by_name(struct inode *dir, const struct qstr *qstr,
                        struct page **page);
void f2fs_set_link(struct inode *dir, struct f2fs_dir_entry *de,
                        struct page *page, struct inode *inode);
bool f2fs_has_enough_room(struct inode *dir, struct page *ipage,
                          const struct f2fs_filename *fname);
void f2fs_update_dentry(nid_t ino, umode_t mode, struct f2fs_dentry_ptr *d,
                        const struct fscrypt_str *name, f2fs_hash_t name_hash,
                        unsigned int bit_pos);
int f2fs_add_regular_entry(struct inode *dir, const struct f2fs_filename *fname,
                        struct inode *inode, nid_t ino, umode_t mode);
int f2fs_add_dentry(struct inode *dir, const struct f2fs_filename *fname,
                        struct inode *inode, nid_t ino, umode_t mode);
int f2fs_do_add_link(struct inode *dir, const struct qstr *name,
                        struct inode *inode, nid_t ino, umode_t mode);
void f2fs_delete_entry(struct f2fs_dir_entry *dentry, struct page *page,
                        struct inode *dir, struct inode *inode);
int f2fs_do_tmpfile(struct inode *inode, struct inode *dir,
                                        struct f2fs_filename *fname);
bool f2fs_empty_dir(struct inode *dir);

static inline int f2fs_add_link(struct dentry *dentry, struct inode *inode)
{
        if (fscrypt_is_nokey_name(dentry))
                return -ENOKEY;
        return f2fs_do_add_link(d_inode(dentry->d_parent), &dentry->d_name,
                                inode, inode->i_ino, inode->i_mode);
}

/*
 * super.c
 */
int f2fs_inode_dirtied(struct inode *inode, bool sync);
void f2fs_inode_synced(struct inode *inode);
int f2fs_dquot_initialize(struct inode *inode);
int f2fs_enable_quota_files(struct f2fs_sb_info *sbi, bool rdonly);
int f2fs_quota_sync(struct super_block *sb, int type);
loff_t max_file_blocks(struct inode *inode);
void f2fs_quota_off_umount(struct super_block *sb);
void f2fs_save_errors(struct f2fs_sb_info *sbi, unsigned char flag);
void f2fs_handle_critical_error(struct f2fs_sb_info *sbi, unsigned char reason);
void f2fs_handle_error(struct f2fs_sb_info *sbi, unsigned char error);
void f2fs_handle_error_async(struct f2fs_sb_info *sbi, unsigned char error);
int f2fs_commit_super(struct f2fs_sb_info *sbi, bool recover);
int f2fs_sync_fs(struct super_block *sb, int sync);
int f2fs_sanity_check_ckpt(struct f2fs_sb_info *sbi);

/*
 * hash.c
 */
void f2fs_hash_filename(const struct inode *dir, struct f2fs_filename *fname);

/*
 * node.c
 */
struct node_info;

int f2fs_check_nid_range(struct f2fs_sb_info *sbi, nid_t nid);
bool f2fs_available_free_memory(struct f2fs_sb_info *sbi, int type);
bool f2fs_in_warm_node_list(struct f2fs_sb_info *sbi, struct page *page);
void f2fs_init_fsync_node_info(struct f2fs_sb_info *sbi);
void f2fs_del_fsync_node_entry(struct f2fs_sb_info *sbi, struct page *page);
void f2fs_reset_fsync_node_info(struct f2fs_sb_info *sbi);
int f2fs_need_dentry_mark(struct f2fs_sb_info *sbi, nid_t nid);
bool f2fs_is_checkpointed_node(struct f2fs_sb_info *sbi, nid_t nid);
bool f2fs_need_inode_block_update(struct f2fs_sb_info *sbi, nid_t ino);
int f2fs_get_node_info(struct f2fs_sb_info *sbi, nid_t nid,
                                struct node_info *ni, bool checkpoint_context);
pgoff_t f2fs_get_next_page_offset(struct dnode_of_data *dn, pgoff_t pgofs);
int f2fs_get_dnode_of_data(struct dnode_of_data *dn, pgoff_t index, int mode);
int f2fs_truncate_inode_blocks(struct inode *inode, pgoff_t from);
int f2fs_truncate_xattr_node(struct inode *inode);
int f2fs_wait_on_node_pages_writeback(struct f2fs_sb_info *sbi,
                                        unsigned int seq_id);
bool f2fs_nat_bitmap_enabled(struct f2fs_sb_info *sbi);
int f2fs_remove_inode_page(struct inode *inode);
struct page *f2fs_new_inode_page(struct inode *inode);
struct page *f2fs_new_node_page(struct dnode_of_data *dn, unsigned int ofs);
void f2fs_ra_node_page(struct f2fs_sb_info *sbi, nid_t nid);
struct page *f2fs_get_node_page(struct f2fs_sb_info *sbi, pgoff_t nid);
struct page *f2fs_get_node_page_ra(struct page *parent, int start);
int f2fs_move_node_page(struct page *node_page, int gc_type);
void f2fs_flush_inline_data(struct f2fs_sb_info *sbi);
int f2fs_fsync_node_pages(struct f2fs_sb_info *sbi, struct inode *inode,
                        struct writeback_control *wbc, bool atomic,
                        unsigned int *seq_id);
int f2fs_sync_node_pages(struct f2fs_sb_info *sbi,
                        struct writeback_control *wbc,
                        bool do_balance, enum iostat_type io_type);
int f2fs_build_free_nids(struct f2fs_sb_info *sbi, bool sync, bool mount);
bool f2fs_alloc_nid(struct f2fs_sb_info *sbi, nid_t *nid);
void f2fs_alloc_nid_done(struct f2fs_sb_info *sbi, nid_t nid);
void f2fs_alloc_nid_failed(struct f2fs_sb_info *sbi, nid_t nid);
int f2fs_try_to_free_nids(struct f2fs_sb_info *sbi, int nr_shrink);
int f2fs_recover_inline_xattr(struct inode *inode, struct page *page);
int f2fs_recover_xattr_data(struct inode *inode, struct page *page);
int f2fs_recover_inode_page(struct f2fs_sb_info *sbi, struct page *page);
int f2fs_restore_node_summary(struct f2fs_sb_info *sbi,
                        unsigned int segno, struct f2fs_summary_block *sum);
void f2fs_enable_nat_bits(struct f2fs_sb_info *sbi);
int f2fs_flush_nat_entries(struct f2fs_sb_info *sbi, struct cp_control *cpc);
int f2fs_build_node_manager(struct f2fs_sb_info *sbi);
void f2fs_destroy_node_manager(struct f2fs_sb_info *sbi);
int __init f2fs_create_node_manager_caches(void);
void f2fs_destroy_node_manager_caches(void);

/*
 * segment.c
 */
bool f2fs_need_SSR(struct f2fs_sb_info *sbi);
int f2fs_commit_atomic_write(struct inode *inode);
void f2fs_abort_atomic_write(struct inode *inode, bool clean);
void f2fs_balance_fs(struct f2fs_sb_info *sbi, bool need);
void f2fs_balance_fs_bg(struct f2fs_sb_info *sbi, bool from_bg);
int f2fs_issue_flush(struct f2fs_sb_info *sbi, nid_t ino);
int f2fs_create_flush_cmd_control(struct f2fs_sb_info *sbi);
int f2fs_flush_device_cache(struct f2fs_sb_info *sbi);
void f2fs_destroy_flush_cmd_control(struct f2fs_sb_info *sbi, bool free);
void f2fs_invalidate_blocks(struct f2fs_sb_info *sbi, block_t addr);
bool f2fs_is_checkpointed_data(struct f2fs_sb_info *sbi, block_t blkaddr);
int f2fs_start_discard_thread(struct f2fs_sb_info *sbi);
void f2fs_drop_discard_cmd(struct f2fs_sb_info *sbi);
void f2fs_stop_discard_thread(struct f2fs_sb_info *sbi);
bool f2fs_issue_discard_timeout(struct f2fs_sb_info *sbi);
void f2fs_clear_prefree_segments(struct f2fs_sb_info *sbi,
                                        struct cp_control *cpc);
void f2fs_dirty_to_prefree(struct f2fs_sb_info *sbi);
block_t f2fs_get_unusable_blocks(struct f2fs_sb_info *sbi);
int f2fs_disable_cp_again(struct f2fs_sb_info *sbi, block_t unusable);
void f2fs_release_discard_addrs(struct f2fs_sb_info *sbi);
int f2fs_npages_for_summary_flush(struct f2fs_sb_info *sbi, bool for_ra);
bool f2fs_segment_has_free_slot(struct f2fs_sb_info *sbi, int segno);
int f2fs_init_inmem_curseg(struct f2fs_sb_info *sbi);
int f2fs_reinit_atgc_curseg(struct f2fs_sb_info *sbi);
void f2fs_save_inmem_curseg(struct f2fs_sb_info *sbi);
void f2fs_restore_inmem_curseg(struct f2fs_sb_info *sbi);
int f2fs_allocate_segment_for_resize(struct f2fs_sb_info *sbi, int type,
                                        unsigned int start, unsigned int end);
int f2fs_allocate_new_section(struct f2fs_sb_info *sbi, int type, bool force);
int f2fs_allocate_pinning_section(struct f2fs_sb_info *sbi);
int f2fs_allocate_new_segments(struct f2fs_sb_info *sbi);
int f2fs_trim_fs(struct f2fs_sb_info *sbi, struct fstrim_range *range);
bool f2fs_exist_trim_candidates(struct f2fs_sb_info *sbi,
                                        struct cp_control *cpc);
struct page *f2fs_get_sum_page(struct f2fs_sb_info *sbi, unsigned int segno);
void f2fs_update_meta_page(struct f2fs_sb_info *sbi, void *src,
                                        block_t blk_addr);
void f2fs_do_write_meta_page(struct f2fs_sb_info *sbi, struct folio *folio,
                                                enum iostat_type io_type);
void f2fs_do_write_node_page(unsigned int nid, struct f2fs_io_info *fio);
void f2fs_outplace_write_data(struct dnode_of_data *dn,
                        struct f2fs_io_info *fio);
int f2fs_inplace_write_data(struct f2fs_io_info *fio);
void f2fs_do_replace_block(struct f2fs_sb_info *sbi, struct f2fs_summary *sum,
                        block_t old_blkaddr, block_t new_blkaddr,
                        bool recover_curseg, bool recover_newaddr,
                        bool from_gc);
void f2fs_replace_block(struct f2fs_sb_info *sbi, struct dnode_of_data *dn,
                        block_t old_addr, block_t new_addr,
                        unsigned char version, bool recover_curseg,
                        bool recover_newaddr);
enum temp_type f2fs_get_segment_temp(struct f2fs_sb_info *sbi,
                                                enum log_type seg_type);
int f2fs_allocate_data_block(struct f2fs_sb_info *sbi, struct page *page,
                        block_t old_blkaddr, block_t *new_blkaddr,
                        struct f2fs_summary *sum, int type,
                        struct f2fs_io_info *fio);
void f2fs_update_device_state(struct f2fs_sb_info *sbi, nid_t ino,
                                        block_t blkaddr, unsigned int blkcnt);
void f2fs_wait_on_page_writeback(struct page *page,
                        enum page_type type, bool ordered, bool locked);
void f2fs_wait_on_block_writeback(struct inode *inode, block_t blkaddr);
void f2fs_wait_on_block_writeback_range(struct inode *inode, block_t blkaddr,
                                                                block_t len);
void f2fs_write_data_summaries(struct f2fs_sb_info *sbi, block_t start_blk);
void f2fs_write_node_summaries(struct f2fs_sb_info *sbi, block_t start_blk);
int f2fs_lookup_journal_in_cursum(struct f2fs_journal *journal, int type,
                        unsigned int val, int alloc);
void f2fs_flush_sit_entries(struct f2fs_sb_info *sbi, struct cp_control *cpc);
int f2fs_check_and_fix_write_pointer(struct f2fs_sb_info *sbi);
int f2fs_build_segment_manager(struct f2fs_sb_info *sbi);
void f2fs_destroy_segment_manager(struct f2fs_sb_info *sbi);
int __init f2fs_create_segment_manager_caches(void);
void f2fs_destroy_segment_manager_caches(void);
int f2fs_rw_hint_to_seg_type(struct f2fs_sb_info *sbi, enum rw_hint hint);
enum rw_hint f2fs_io_type_to_rw_hint(struct f2fs_sb_info *sbi,
                        enum page_type type, enum temp_type temp);
unsigned int f2fs_usable_segs_in_sec(struct f2fs_sb_info *sbi);
unsigned int f2fs_usable_blks_in_seg(struct f2fs_sb_info *sbi,
                        unsigned int segno);
unsigned long long f2fs_get_section_mtime(struct f2fs_sb_info *sbi,
                        unsigned int segno);

#define DEF_FRAGMENT_SIZE        4
#define MIN_FRAGMENT_SIZE        1
#define MAX_FRAGMENT_SIZE        512

static inline bool f2fs_need_rand_seg(struct f2fs_sb_info *sbi)
{
        return F2FS_OPTION(sbi).fs_mode == FS_MODE_FRAGMENT_SEG ||
                F2FS_OPTION(sbi).fs_mode == FS_MODE_FRAGMENT_BLK;
}

/*
 * checkpoint.c
 */
void f2fs_stop_checkpoint(struct f2fs_sb_info *sbi, bool end_io,
                                                        unsigned char reason);
void f2fs_flush_ckpt_thread(struct f2fs_sb_info *sbi);
struct page *f2fs_grab_meta_page(struct f2fs_sb_info *sbi, pgoff_t index);
struct page *f2fs_get_meta_page(struct f2fs_sb_info *sbi, pgoff_t index);
struct page *f2fs_get_meta_page_retry(struct f2fs_sb_info *sbi, pgoff_t index);
struct page *f2fs_get_tmp_page(struct f2fs_sb_info *sbi, pgoff_t index);
bool f2fs_is_valid_blkaddr(struct f2fs_sb_info *sbi,
                                        block_t blkaddr, int type);
bool f2fs_is_valid_blkaddr_raw(struct f2fs_sb_info *sbi,
                                        block_t blkaddr, int type);
int f2fs_ra_meta_pages(struct f2fs_sb_info *sbi, block_t start, int nrpages,
                        int type, bool sync);
void f2fs_ra_meta_pages_cond(struct f2fs_sb_info *sbi, pgoff_t index,
                                                        unsigned int ra_blocks);
long f2fs_sync_meta_pages(struct f2fs_sb_info *sbi, enum page_type type,
                        long nr_to_write, enum iostat_type io_type);
void f2fs_add_ino_entry(struct f2fs_sb_info *sbi, nid_t ino, int type);
void f2fs_remove_ino_entry(struct f2fs_sb_info *sbi, nid_t ino, int type);
void f2fs_release_ino_entry(struct f2fs_sb_info *sbi, bool all);
bool f2fs_exist_written_data(struct f2fs_sb_info *sbi, nid_t ino, int mode);
void f2fs_set_dirty_device(struct f2fs_sb_info *sbi, nid_t ino,
                                        unsigned int devidx, int type);
bool f2fs_is_dirty_device(struct f2fs_sb_info *sbi, nid_t ino,
                                        unsigned int devidx, int type);
int f2fs_acquire_orphan_inode(struct f2fs_sb_info *sbi);
void f2fs_release_orphan_inode(struct f2fs_sb_info *sbi);
void f2fs_add_orphan_inode(struct inode *inode);
void f2fs_remove_orphan_inode(struct f2fs_sb_info *sbi, nid_t ino);
int f2fs_recover_orphan_inodes(struct f2fs_sb_info *sbi);
int f2fs_get_valid_checkpoint(struct f2fs_sb_info *sbi);
void f2fs_update_dirty_folio(struct inode *inode, struct folio *folio);
void f2fs_remove_dirty_inode(struct inode *inode);
int f2fs_sync_dirty_inodes(struct f2fs_sb_info *sbi, enum inode_type type,
                                                                bool from_cp);
void f2fs_wait_on_all_pages(struct f2fs_sb_info *sbi, int type);
u64 f2fs_get_sectors_written(struct f2fs_sb_info *sbi);
int f2fs_write_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc);
void f2fs_init_ino_entry_info(struct f2fs_sb_info *sbi);
int __init f2fs_create_checkpoint_caches(void);
void f2fs_destroy_checkpoint_caches(void);
int f2fs_issue_checkpoint(struct f2fs_sb_info *sbi);
int f2fs_start_ckpt_thread(struct f2fs_sb_info *sbi);
void f2fs_stop_ckpt_thread(struct f2fs_sb_info *sbi);
void f2fs_init_ckpt_req_control(struct f2fs_sb_info *sbi);

/*
 * data.c
 */
int __init f2fs_init_bioset(void);
void f2fs_destroy_bioset(void);
bool f2fs_is_cp_guaranteed(struct page *page);
int f2fs_init_bio_entry_cache(void);
void f2fs_destroy_bio_entry_cache(void);
void f2fs_submit_read_bio(struct f2fs_sb_info *sbi, struct bio *bio,
                          enum page_type type);
int f2fs_init_write_merge_io(struct f2fs_sb_info *sbi);
void f2fs_submit_merged_write(struct f2fs_sb_info *sbi, enum page_type type);
void f2fs_submit_merged_write_cond(struct f2fs_sb_info *sbi,
                                struct inode *inode, struct page *page,
                                nid_t ino, enum page_type type);
void f2fs_submit_merged_ipu_write(struct f2fs_sb_info *sbi,
                                        struct bio **bio, struct page *page);
void f2fs_flush_merged_writes(struct f2fs_sb_info *sbi);
int f2fs_submit_page_bio(struct f2fs_io_info *fio);
int f2fs_merge_page_bio(struct f2fs_io_info *fio);
void f2fs_submit_page_write(struct f2fs_io_info *fio);
struct block_device *f2fs_target_device(struct f2fs_sb_info *sbi,
                block_t blk_addr, sector_t *sector);
int f2fs_target_device_index(struct f2fs_sb_info *sbi, block_t blkaddr);
void f2fs_set_data_blkaddr(struct dnode_of_data *dn, block_t blkaddr);
void f2fs_update_data_blkaddr(struct dnode_of_data *dn, block_t blkaddr);
int f2fs_reserve_new_blocks(struct dnode_of_data *dn, blkcnt_t count);
int f2fs_reserve_new_block(struct dnode_of_data *dn);
int f2fs_get_block_locked(struct dnode_of_data *dn, pgoff_t index);
int f2fs_reserve_block(struct dnode_of_data *dn, pgoff_t index);
struct page *f2fs_get_read_data_page(struct inode *inode, pgoff_t index,
                        blk_opf_t op_flags, bool for_write, pgoff_t *next_pgofs);
struct page *f2fs_find_data_page(struct inode *inode, pgoff_t index,
                                                        pgoff_t *next_pgofs);
struct page *f2fs_get_lock_data_page(struct inode *inode, pgoff_t index,
                        bool for_write);
struct page *f2fs_get_new_data_page(struct inode *inode,
                        struct page *ipage, pgoff_t index, bool new_i_size);
int f2fs_do_write_data_page(struct f2fs_io_info *fio);
int f2fs_map_blocks(struct inode *inode, struct f2fs_map_blocks *map, int flag);
int f2fs_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
                        u64 start, u64 len);
int f2fs_encrypt_one_page(struct f2fs_io_info *fio);
bool f2fs_should_update_inplace(struct inode *inode, struct f2fs_io_info *fio);
bool f2fs_should_update_outplace(struct inode *inode, struct f2fs_io_info *fio);
int f2fs_write_single_data_page(struct folio *folio, int *submitted,
                                struct bio **bio, sector_t *last_block,
                                struct writeback_control *wbc,
                                enum iostat_type io_type,
                                int compr_blocks, bool allow_balance);
void f2fs_write_failed(struct inode *inode, loff_t to);
void f2fs_invalidate_folio(struct folio *folio, size_t offset, size_t length);
bool f2fs_release_folio(struct folio *folio, gfp_t wait);
bool f2fs_overwrite_io(struct inode *inode, loff_t pos, size_t len);
void f2fs_clear_page_cache_dirty_tag(struct folio *folio);
int f2fs_init_post_read_processing(void);
void f2fs_destroy_post_read_processing(void);
int f2fs_init_post_read_wq(struct f2fs_sb_info *sbi);
void f2fs_destroy_post_read_wq(struct f2fs_sb_info *sbi);
extern const struct iomap_ops f2fs_iomap_ops;

/*
 * gc.c
 */
int f2fs_start_gc_thread(struct f2fs_sb_info *sbi);
void f2fs_stop_gc_thread(struct f2fs_sb_info *sbi);
block_t f2fs_start_bidx_of_node(unsigned int node_ofs, struct inode *inode);
int f2fs_gc(struct f2fs_sb_info *sbi, struct f2fs_gc_control *gc_control);
void f2fs_build_gc_manager(struct f2fs_sb_info *sbi);
int f2fs_gc_range(struct f2fs_sb_info *sbi,
                unsigned int start_seg, unsigned int end_seg,
                bool dry_run, unsigned int dry_run_sections);
int f2fs_resize_fs(struct file *filp, __u64 block_count);
int __init f2fs_create_garbage_collection_cache(void);
void f2fs_destroy_garbage_collection_cache(void);
/* victim selection function for cleaning and SSR */
int f2fs_get_victim(struct f2fs_sb_info *sbi, unsigned int *result,
                        int gc_type, int type, char alloc_mode,
                        unsigned long long age, bool one_time);

/*
 * recovery.c
 */
int f2fs_recover_fsync_data(struct f2fs_sb_info *sbi, bool check_only);
bool f2fs_space_for_roll_forward(struct f2fs_sb_info *sbi);
int __init f2fs_create_recovery_cache(void);
void f2fs_destroy_recovery_cache(void);

/*
 * debug.c
 */
#ifdef CONFIG_F2FS_STAT_FS
enum {
        DEVSTAT_INUSE,
        DEVSTAT_DIRTY,
        DEVSTAT_FULL,
        DEVSTAT_FREE,
        DEVSTAT_PREFREE,
        DEVSTAT_MAX,
};

struct f2fs_dev_stats {
        unsigned int devstats[2][DEVSTAT_MAX];                /* 0: segs, 1: secs */
};

struct f2fs_stat_info {
        struct list_head stat_list;
        struct f2fs_sb_info *sbi;
        int all_area_segs, sit_area_segs, nat_area_segs, ssa_area_segs;
        int main_area_segs, main_area_sections, main_area_zones;
        unsigned long long hit_cached[NR_EXTENT_CACHES];
        unsigned long long hit_rbtree[NR_EXTENT_CACHES];
        unsigned long long total_ext[NR_EXTENT_CACHES];
        unsigned long long hit_total[NR_EXTENT_CACHES];
        int ext_tree[NR_EXTENT_CACHES];
        int zombie_tree[NR_EXTENT_CACHES];
        int ext_node[NR_EXTENT_CACHES];
        /* to count memory footprint */
        unsigned long long ext_mem[NR_EXTENT_CACHES];
        /* for read extent cache */
        unsigned long long hit_largest;
        /* for block age extent cache */
        unsigned long long allocated_data_blocks;
        int ndirty_node, ndirty_dent, ndirty_meta, ndirty_imeta;
        int ndirty_data, ndirty_qdata;
        unsigned int ndirty_dirs, ndirty_files, nquota_files, ndirty_all;
        int nats, dirty_nats, sits, dirty_sits;
        int free_nids, avail_nids, alloc_nids;
        int total_count, utilization;
        int nr_wb_cp_data, nr_wb_data;
        int nr_rd_data, nr_rd_node, nr_rd_meta;
        int nr_dio_read, nr_dio_write;
        unsigned int io_skip_bggc, other_skip_bggc;
        int nr_flushing, nr_flushed, flush_list_empty;
        int nr_discarding, nr_discarded;
        int nr_discard_cmd;
        unsigned int undiscard_blks;
        int nr_issued_ckpt, nr_total_ckpt, nr_queued_ckpt;
        unsigned int cur_ckpt_time, peak_ckpt_time;
        int inline_xattr, inline_inode, inline_dir, append, update, orphans;
        int compr_inode, swapfile_inode;
        unsigned long long compr_blocks;
        int aw_cnt, max_aw_cnt;
        unsigned int valid_count, valid_node_count, valid_inode_count, discard_blks;
        unsigned int bimodal, avg_vblocks;
        int util_free, util_valid, util_invalid;
        int rsvd_segs, overp_segs;
        int dirty_count, node_pages, meta_pages, compress_pages;
        int compress_page_hit;
        int prefree_count, free_segs, free_secs;
        int cp_call_count[MAX_CALL_TYPE], cp_count;
        int gc_call_count[MAX_CALL_TYPE];
        int gc_segs[2][2];
        int gc_secs[2][2];
        int tot_blks, data_blks, node_blks;
        int bg_data_blks, bg_node_blks;
        int curseg[NR_CURSEG_TYPE];
        int cursec[NR_CURSEG_TYPE];
        int curzone[NR_CURSEG_TYPE];
        unsigned int dirty_seg[NR_CURSEG_TYPE];
        unsigned int full_seg[NR_CURSEG_TYPE];
        unsigned int valid_blks[NR_CURSEG_TYPE];

        unsigned int meta_count[META_MAX];
        unsigned int segment_count[2];
        unsigned int block_count[2];
        unsigned int inplace_count;
        unsigned long long base_mem, cache_mem, page_mem;
        struct f2fs_dev_stats *dev_stats;
};

static inline struct f2fs_stat_info *F2FS_STAT(struct f2fs_sb_info *sbi)
{
        return (struct f2fs_stat_info *)sbi->stat_info;
}

#define stat_inc_cp_call_count(sbi, foreground)                                \
                atomic_inc(&sbi->cp_call_count[(foreground)])
#define stat_inc_cp_count(sbi)                (F2FS_STAT(sbi)->cp_count++)
#define stat_io_skip_bggc_count(sbi)        ((sbi)->io_skip_bggc++)
#define stat_other_skip_bggc_count(sbi)        ((sbi)->other_skip_bggc++)
#define stat_inc_dirty_inode(sbi, type)        ((sbi)->ndirty_inode[type]++)
#define stat_dec_dirty_inode(sbi, type)        ((sbi)->ndirty_inode[type]--)
#define stat_inc_total_hit(sbi, type)                (atomic64_inc(&(sbi)->total_hit_ext[type]))
#define stat_inc_rbtree_node_hit(sbi, type)        (atomic64_inc(&(sbi)->read_hit_rbtree[type]))
#define stat_inc_largest_node_hit(sbi)        (atomic64_inc(&(sbi)->read_hit_largest))
#define stat_inc_cached_node_hit(sbi, type)        (atomic64_inc(&(sbi)->read_hit_cached[type]))
#define stat_inc_inline_xattr(inode)                                        \
        do {                                                                \
                if (f2fs_has_inline_xattr(inode))                        \
                        (atomic_inc(&F2FS_I_SB(inode)->inline_xattr));        \
        } while (0)
#define stat_dec_inline_xattr(inode)                                        \
        do {                                                                \
                if (f2fs_has_inline_xattr(inode))                        \
                        (atomic_dec(&F2FS_I_SB(inode)->inline_xattr));        \
        } while (0)
#define stat_inc_inline_inode(inode)                                        \
        do {                                                                \
                if (f2fs_has_inline_data(inode))                        \
                        (atomic_inc(&F2FS_I_SB(inode)->inline_inode));        \
        } while (0)
#define stat_dec_inline_inode(inode)                                        \
        do {                                                                \
                if (f2fs_has_inline_data(inode))                        \
                        (atomic_dec(&F2FS_I_SB(inode)->inline_inode));        \
        } while (0)
#define stat_inc_inline_dir(inode)                                        \
        do {                                                                \
                if (f2fs_has_inline_dentry(inode))                        \
                        (atomic_inc(&F2FS_I_SB(inode)->inline_dir));        \
        } while (0)
#define stat_dec_inline_dir(inode)                                        \
        do {                                                                \
                if (f2fs_has_inline_dentry(inode))                        \
                        (atomic_dec(&F2FS_I_SB(inode)->inline_dir));        \
        } while (0)
#define stat_inc_compr_inode(inode)                                        \
        do {                                                                \
                if (f2fs_compressed_file(inode))                        \
                        (atomic_inc(&F2FS_I_SB(inode)->compr_inode));        \
        } while (0)
#define stat_dec_compr_inode(inode)                                        \
        do {                                                                \
                if (f2fs_compressed_file(inode))                        \
                        (atomic_dec(&F2FS_I_SB(inode)->compr_inode));        \
        } while (0)
#define stat_add_compr_blocks(inode, blocks)                                \
                (atomic64_add(blocks, &F2FS_I_SB(inode)->compr_blocks))
#define stat_sub_compr_blocks(inode, blocks)                                \
                (atomic64_sub(blocks, &F2FS_I_SB(inode)->compr_blocks))
#define stat_inc_swapfile_inode(inode)                                        \
                (atomic_inc(&F2FS_I_SB(inode)->swapfile_inode))
#define stat_dec_swapfile_inode(inode)                                        \
                (atomic_dec(&F2FS_I_SB(inode)->swapfile_inode))
#define stat_inc_atomic_inode(inode)                                        \
                        (atomic_inc(&F2FS_I_SB(inode)->atomic_files))
#define stat_dec_atomic_inode(inode)                                        \
                        (atomic_dec(&F2FS_I_SB(inode)->atomic_files))
#define stat_inc_meta_count(sbi, blkaddr)                                \
        do {                                                                \
                if (blkaddr < SIT_I(sbi)->sit_base_addr)                \
                        atomic_inc(&(sbi)->meta_count[META_CP]);        \
                else if (blkaddr < NM_I(sbi)->nat_blkaddr)                \
                        atomic_inc(&(sbi)->meta_count[META_SIT]);        \
                else if (blkaddr < SM_I(sbi)->ssa_blkaddr)                \
                        atomic_inc(&(sbi)->meta_count[META_NAT]);        \
                else if (blkaddr < SM_I(sbi)->main_blkaddr)                \
                        atomic_inc(&(sbi)->meta_count[META_SSA]);        \
        } while (0)
#define stat_inc_seg_type(sbi, curseg)                                        \
                ((sbi)->segment_count[(curseg)->alloc_type]++)
#define stat_inc_block_count(sbi, curseg)                                \
                ((sbi)->block_count[(curseg)->alloc_type]++)
#define stat_inc_inplace_blocks(sbi)                                        \
                (atomic_inc(&(sbi)->inplace_count))
#define stat_update_max_atomic_write(inode)                                \
        do {                                                                \
                int cur = atomic_read(&F2FS_I_SB(inode)->atomic_files);        \
                int max = atomic_read(&F2FS_I_SB(inode)->max_aw_cnt);        \
                if (cur > max)                                                \
                        atomic_set(&F2FS_I_SB(inode)->max_aw_cnt, cur);        \
        } while (0)
#define stat_inc_gc_call_count(sbi, foreground)                                \
                (F2FS_STAT(sbi)->gc_call_count[(foreground)]++)
#define stat_inc_gc_sec_count(sbi, type, gc_type)                        \
                (F2FS_STAT(sbi)->gc_secs[(type)][(gc_type)]++)
#define stat_inc_gc_seg_count(sbi, type, gc_type)                        \
                (F2FS_STAT(sbi)->gc_segs[(type)][(gc_type)]++)

#define stat_inc_tot_blk_count(si, blks)                                \
        ((si)->tot_blks += (blks))

#define stat_inc_data_blk_count(sbi, blks, gc_type)                        \
        do {                                                                \
                struct f2fs_stat_info *si = F2FS_STAT(sbi);                \
                stat_inc_tot_blk_count(si, blks);                        \
                si->data_blks += (blks);                                \
                si->bg_data_blks += ((gc_type) == BG_GC) ? (blks) : 0;        \
        } while (0)

#define stat_inc_node_blk_count(sbi, blks, gc_type)                        \
        do {                                                                \
                struct f2fs_stat_info *si = F2FS_STAT(sbi);                \
                stat_inc_tot_blk_count(si, blks);                        \
                si->node_blks += (blks);                                \
                si->bg_node_blks += ((gc_type) == BG_GC) ? (blks) : 0;        \
        } while (0)

int f2fs_build_stats(struct f2fs_sb_info *sbi);
void f2fs_destroy_stats(struct f2fs_sb_info *sbi);
void __init f2fs_create_root_stats(void);
void f2fs_destroy_root_stats(void);
void f2fs_update_sit_info(struct f2fs_sb_info *sbi);
#else
#define stat_inc_cp_call_count(sbi, foreground)                do { } while (0)
#define stat_inc_cp_count(sbi)                                do { } while (0)
#define stat_io_skip_bggc_count(sbi)                        do { } while (0)
#define stat_other_skip_bggc_count(sbi)                        do { } while (0)
#define stat_inc_dirty_inode(sbi, type)                        do { } while (0)
#define stat_dec_dirty_inode(sbi, type)                        do { } while (0)
#define stat_inc_total_hit(sbi, type)                        do { } while (0)
#define stat_inc_rbtree_node_hit(sbi, type)                do { } while (0)
#define stat_inc_largest_node_hit(sbi)                        do { } while (0)
#define stat_inc_cached_node_hit(sbi, type)                do { } while (0)
#define stat_inc_inline_xattr(inode)                        do { } while (0)
#define stat_dec_inline_xattr(inode)                        do { } while (0)
#define stat_inc_inline_inode(inode)                        do { } while (0)
#define stat_dec_inline_inode(inode)                        do { } while (0)
#define stat_inc_inline_dir(inode)                        do { } while (0)
#define stat_dec_inline_dir(inode)                        do { } while (0)
#define stat_inc_compr_inode(inode)                        do { } while (0)
#define stat_dec_compr_inode(inode)                        do { } while (0)
#define stat_add_compr_blocks(inode, blocks)                do { } while (0)
#define stat_sub_compr_blocks(inode, blocks)                do { } while (0)
#define stat_inc_swapfile_inode(inode)                        do { } while (0)
#define stat_dec_swapfile_inode(inode)                        do { } while (0)
#define stat_inc_atomic_inode(inode)                        do { } while (0)
#define stat_dec_atomic_inode(inode)                        do { } while (0)
#define stat_update_max_atomic_write(inode)                do { } while (0)
#define stat_inc_meta_count(sbi, blkaddr)                do { } while (0)
#define stat_inc_seg_type(sbi, curseg)                        do { } while (0)
#define stat_inc_block_count(sbi, curseg)                do { } while (0)
#define stat_inc_inplace_blocks(sbi)                        do { } while (0)
#define stat_inc_gc_call_count(sbi, foreground)                do { } while (0)
#define stat_inc_gc_sec_count(sbi, type, gc_type)        do { } while (0)
#define stat_inc_gc_seg_count(sbi, type, gc_type)        do { } while (0)
#define stat_inc_tot_blk_count(si, blks)                do { } while (0)
#define stat_inc_data_blk_count(sbi, blks, gc_type)        do { } while (0)
#define stat_inc_node_blk_count(sbi, blks, gc_type)        do { } while (0)

static inline int f2fs_build_stats(struct f2fs_sb_info *sbi) { return 0; }
static inline void f2fs_destroy_stats(struct f2fs_sb_info *sbi) { }
static inline void __init f2fs_create_root_stats(void) { }
static inline void f2fs_destroy_root_stats(void) { }
static inline void f2fs_update_sit_info(struct f2fs_sb_info *sbi) {}
#endif

extern const struct file_operations f2fs_dir_operations;
extern const struct file_operations f2fs_file_operations;
extern const struct inode_operations f2fs_file_inode_operations;
extern const struct address_space_operations f2fs_dblock_aops;
extern const struct address_space_operations f2fs_node_aops;
extern const struct address_space_operations f2fs_meta_aops;
extern const struct inode_operations f2fs_dir_inode_operations;
extern const struct inode_operations f2fs_symlink_inode_operations;
extern const struct inode_operations f2fs_encrypted_symlink_inode_operations;
extern const struct inode_operations f2fs_special_inode_operations;
extern struct kmem_cache *f2fs_inode_entry_slab;

/*
 * inline.c
 */
bool f2fs_may_inline_data(struct inode *inode);
bool f2fs_sanity_check_inline_data(struct inode *inode, struct page *ipage);
bool f2fs_may_inline_dentry(struct inode *inode);
void f2fs_do_read_inline_data(struct folio *folio, struct page *ipage);
void f2fs_truncate_inline_inode(struct inode *inode,
                                                struct page *ipage, u64 from);
int f2fs_read_inline_data(struct inode *inode, struct folio *folio);
int f2fs_convert_inline_page(struct dnode_of_data *dn, struct page *page);
int f2fs_convert_inline_inode(struct inode *inode);
int f2fs_try_convert_inline_dir(struct inode *dir, struct dentry *dentry);
int f2fs_write_inline_data(struct inode *inode, struct folio *folio);
int f2fs_recover_inline_data(struct inode *inode, struct page *npage);
struct f2fs_dir_entry *f2fs_find_in_inline_dir(struct inode *dir,
                                        const struct f2fs_filename *fname,
                                        struct page **res_page);
int f2fs_make_empty_inline_dir(struct inode *inode, struct inode *parent,
                        struct page *ipage);
int f2fs_add_inline_entry(struct inode *dir, const struct f2fs_filename *fname,
                        struct inode *inode, nid_t ino, umode_t mode);
void f2fs_delete_inline_entry(struct f2fs_dir_entry *dentry,
                                struct page *page, struct inode *dir,
                                struct inode *inode);
bool f2fs_empty_inline_dir(struct inode *dir);
int f2fs_read_inline_dir(struct file *file, struct dir_context *ctx,
                        struct fscrypt_str *fstr);
int f2fs_inline_data_fiemap(struct inode *inode,
                        struct fiemap_extent_info *fieinfo,
                        __u64 start, __u64 len);

/*
 * shrinker.c
 */
unsigned long f2fs_shrink_count(struct shrinker *shrink,
                        struct shrink_control *sc);
unsigned long f2fs_shrink_scan(struct shrinker *shrink,
                        struct shrink_control *sc);
void f2fs_join_shrinker(struct f2fs_sb_info *sbi);
void f2fs_leave_shrinker(struct f2fs_sb_info *sbi);

/*
 * extent_cache.c
 */
bool sanity_check_extent_cache(struct inode *inode, struct page *ipage);
void f2fs_init_extent_tree(struct inode *inode);
void f2fs_drop_extent_tree(struct inode *inode);
void f2fs_destroy_extent_node(struct inode *inode);
void f2fs_destroy_extent_tree(struct inode *inode);
void f2fs_init_extent_cache_info(struct f2fs_sb_info *sbi);
int __init f2fs_create_extent_cache(void);
void f2fs_destroy_extent_cache(void);

/* read extent cache ops */
void f2fs_init_read_extent_tree(struct inode *inode, struct page *ipage);
bool f2fs_lookup_read_extent_cache(struct inode *inode, pgoff_t pgofs,
                        struct extent_info *ei);
bool f2fs_lookup_read_extent_cache_block(struct inode *inode, pgoff_t index,
                        block_t *blkaddr);
void f2fs_update_read_extent_cache(struct dnode_of_data *dn);
void f2fs_update_read_extent_cache_range(struct dnode_of_data *dn,
                        pgoff_t fofs, block_t blkaddr, unsigned int len);
unsigned int f2fs_shrink_read_extent_tree(struct f2fs_sb_info *sbi,
                        int nr_shrink);

/* block age extent cache ops */
void f2fs_init_age_extent_tree(struct inode *inode);
bool f2fs_lookup_age_extent_cache(struct inode *inode, pgoff_t pgofs,
                        struct extent_info *ei);
void f2fs_update_age_extent_cache(struct dnode_of_data *dn);
void f2fs_update_age_extent_cache_range(struct dnode_of_data *dn,
                        pgoff_t fofs, unsigned int len);
unsigned int f2fs_shrink_age_extent_tree(struct f2fs_sb_info *sbi,
                        int nr_shrink);

/*
 * sysfs.c
 */
#define MIN_RA_MUL        2
#define MAX_RA_MUL        256

int __init f2fs_init_sysfs(void);
void f2fs_exit_sysfs(void);
int f2fs_register_sysfs(struct f2fs_sb_info *sbi);
void f2fs_unregister_sysfs(struct f2fs_sb_info *sbi);

/* verity.c */
extern const struct fsverity_operations f2fs_verityops;

/*
 * crypto support
 */
static inline bool f2fs_encrypted_file(struct inode *inode)
{
        return IS_ENCRYPTED(inode) && S_ISREG(inode->i_mode);
}

static inline void f2fs_set_encrypted_inode(struct inode *inode)
{
#ifdef CONFIG_FS_ENCRYPTION
        file_set_encrypt(inode);
        f2fs_set_inode_flags(inode);
#endif
}

/*
 * Returns true if the reads of the inode's data need to undergo some
 * postprocessing step, like decryption or authenticity verification.
 */
static inline bool f2fs_post_read_required(struct inode *inode)
{
        return f2fs_encrypted_file(inode) || fsverity_active(inode) ||
                f2fs_compressed_file(inode);
}

static inline bool f2fs_used_in_atomic_write(struct inode *inode)
{
        return f2fs_is_atomic_file(inode) || f2fs_is_cow_file(inode);
}

static inline bool f2fs_meta_inode_gc_required(struct inode *inode)
{
        return f2fs_post_read_required(inode) || f2fs_used_in_atomic_write(inode);
}

/*
 * compress.c
 */
#ifdef CONFIG_F2FS_FS_COMPRESSION
enum cluster_check_type {
        CLUSTER_IS_COMPR,   /* check only if compressed cluster */
        CLUSTER_COMPR_BLKS, /* return # of compressed blocks in a cluster */
        CLUSTER_RAW_BLKS    /* return # of raw blocks in a cluster */
};
bool f2fs_is_compressed_page(struct page *page);
struct page *f2fs_compress_control_page(struct page *page);
int f2fs_prepare_compress_overwrite(struct inode *inode,
                        struct page **pagep, pgoff_t index, void **fsdata);
bool f2fs_compress_write_end(struct inode *inode, void *fsdata,
                                        pgoff_t index, unsigned copied);
int f2fs_truncate_partial_cluster(struct inode *inode, u64 from, bool lock);
void f2fs_compress_write_end_io(struct bio *bio, struct page *page);
bool f2fs_is_compress_backend_ready(struct inode *inode);
bool f2fs_is_compress_level_valid(int alg, int lvl);
int __init f2fs_init_compress_mempool(void);
void f2fs_destroy_compress_mempool(void);
void f2fs_decompress_cluster(struct decompress_io_ctx *dic, bool in_task);
void f2fs_end_read_compressed_page(struct page *page, bool failed,
                                block_t blkaddr, bool in_task);
bool f2fs_cluster_is_empty(struct compress_ctx *cc);
bool f2fs_cluster_can_merge_page(struct compress_ctx *cc, pgoff_t index);
bool f2fs_all_cluster_page_ready(struct compress_ctx *cc, struct page **pages,
                                int index, int nr_pages, bool uptodate);
bool f2fs_sanity_check_cluster(struct dnode_of_data *dn);
void f2fs_compress_ctx_add_page(struct compress_ctx *cc, struct folio *folio);
int f2fs_write_multi_pages(struct compress_ctx *cc,
                                                int *submitted,
                                                struct writeback_control *wbc,
                                                enum iostat_type io_type);
int f2fs_is_compressed_cluster(struct inode *inode, pgoff_t index);
bool f2fs_is_sparse_cluster(struct inode *inode, pgoff_t index);
void f2fs_update_read_extent_tree_range_compressed(struct inode *inode,
                                pgoff_t fofs, block_t blkaddr,
                                unsigned int llen, unsigned int c_len);
int f2fs_read_multi_pages(struct compress_ctx *cc, struct bio **bio_ret,
                                unsigned nr_pages, sector_t *last_block_in_bio,
                                struct readahead_control *rac, bool for_write);
struct decompress_io_ctx *f2fs_alloc_dic(struct compress_ctx *cc);
void f2fs_decompress_end_io(struct decompress_io_ctx *dic, bool failed,
                                bool in_task);
void f2fs_put_page_dic(struct page *page, bool in_task);
unsigned int f2fs_cluster_blocks_are_contiguous(struct dnode_of_data *dn,
                                                unsigned int ofs_in_node);
int f2fs_init_compress_ctx(struct compress_ctx *cc);
void f2fs_destroy_compress_ctx(struct compress_ctx *cc, bool reuse);
void f2fs_init_compress_info(struct f2fs_sb_info *sbi);
int f2fs_init_compress_inode(struct f2fs_sb_info *sbi);
void f2fs_destroy_compress_inode(struct f2fs_sb_info *sbi);
int f2fs_init_page_array_cache(struct f2fs_sb_info *sbi);
void f2fs_destroy_page_array_cache(struct f2fs_sb_info *sbi);
int __init f2fs_init_compress_cache(void);
void f2fs_destroy_compress_cache(void);
struct address_space *COMPRESS_MAPPING(struct f2fs_sb_info *sbi);
void f2fs_invalidate_compress_page(struct f2fs_sb_info *sbi, block_t blkaddr);
void f2fs_cache_compressed_page(struct f2fs_sb_info *sbi, struct page *page,
                                                nid_t ino, block_t blkaddr);
bool f2fs_load_compressed_page(struct f2fs_sb_info *sbi, struct page *page,
                                                                block_t blkaddr);
void f2fs_invalidate_compress_pages(struct f2fs_sb_info *sbi, nid_t ino);
#define inc_compr_inode_stat(inode)                                        \
        do {                                                                \
                struct f2fs_sb_info *sbi = F2FS_I_SB(inode);                \
                sbi->compr_new_inode++;                                        \
        } while (0)
#define add_compr_block_stat(inode, blocks)                                \
        do {                                                                \
                struct f2fs_sb_info *sbi = F2FS_I_SB(inode);                \
                int diff = F2FS_I(inode)->i_cluster_size - blocks;        \
                sbi->compr_written_block += blocks;                        \
                sbi->compr_saved_block += diff;                                \
        } while (0)
#else
static inline bool f2fs_is_compressed_page(struct page *page) { return false; }
static inline bool f2fs_is_compress_backend_ready(struct inode *inode)
{
        if (!f2fs_compressed_file(inode))
                return true;
        /* not support compression */
        return false;
}
static inline bool f2fs_is_compress_level_valid(int alg, int lvl) { return false; }
static inline struct page *f2fs_compress_control_page(struct page *page)
{
        WARN_ON_ONCE(1);
        return ERR_PTR(-EINVAL);
}
static inline int __init f2fs_init_compress_mempool(void) { return 0; }
static inline void f2fs_destroy_compress_mempool(void) { }
static inline void f2fs_decompress_cluster(struct decompress_io_ctx *dic,
                                bool in_task) { }
static inline void f2fs_end_read_compressed_page(struct page *page,
                                bool failed, block_t blkaddr, bool in_task)
{
        WARN_ON_ONCE(1);
}
static inline void f2fs_put_page_dic(struct page *page, bool in_task)
{
        WARN_ON_ONCE(1);
}
static inline unsigned int f2fs_cluster_blocks_are_contiguous(
                        struct dnode_of_data *dn, unsigned int ofs_in_node) { return 0; }
static inline bool f2fs_sanity_check_cluster(struct dnode_of_data *dn) { return false; }
static inline int f2fs_init_compress_inode(struct f2fs_sb_info *sbi) { return 0; }
static inline void f2fs_destroy_compress_inode(struct f2fs_sb_info *sbi) { }
static inline int f2fs_init_page_array_cache(struct f2fs_sb_info *sbi) { return 0; }
static inline void f2fs_destroy_page_array_cache(struct f2fs_sb_info *sbi) { }
static inline int __init f2fs_init_compress_cache(void) { return 0; }
static inline void f2fs_destroy_compress_cache(void) { }
static inline void f2fs_invalidate_compress_page(struct f2fs_sb_info *sbi,
                                block_t blkaddr) { }
static inline void f2fs_cache_compressed_page(struct f2fs_sb_info *sbi,
                                struct page *page, nid_t ino, block_t blkaddr) { }
static inline bool f2fs_load_compressed_page(struct f2fs_sb_info *sbi,
                                struct page *page, block_t blkaddr) { return false; }
static inline void f2fs_invalidate_compress_pages(struct f2fs_sb_info *sbi,
                                                        nid_t ino) { }
#define inc_compr_inode_stat(inode)                do { } while (0)
static inline int f2fs_is_compressed_cluster(
                                struct inode *inode,
                                pgoff_t index) { return 0; }
static inline bool f2fs_is_sparse_cluster(
                                struct inode *inode,
                                pgoff_t index) { return true; }
static inline void f2fs_update_read_extent_tree_range_compressed(
                                struct inode *inode,
                                pgoff_t fofs, block_t blkaddr,
                                unsigned int llen, unsigned int c_len) { }
#endif

static inline int set_compress_context(struct inode *inode)
{
#ifdef CONFIG_F2FS_FS_COMPRESSION
        struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
        struct f2fs_inode_info *fi = F2FS_I(inode);

        fi->i_compress_algorithm = F2FS_OPTION(sbi).compress_algorithm;
        fi->i_log_cluster_size = F2FS_OPTION(sbi).compress_log_size;
        fi->i_compress_flag = F2FS_OPTION(sbi).compress_chksum ?
                                        BIT(COMPRESS_CHKSUM) : 0;
        fi->i_cluster_size = BIT(fi->i_log_cluster_size);
        if ((fi->i_compress_algorithm == COMPRESS_LZ4 ||
                fi->i_compress_algorithm == COMPRESS_ZSTD) &&
                        F2FS_OPTION(sbi).compress_level)
                fi->i_compress_level = F2FS_OPTION(sbi).compress_level;
        fi->i_flags |= F2FS_COMPR_FL;
        set_inode_flag(inode, FI_COMPRESSED_FILE);
        stat_inc_compr_inode(inode);
        inc_compr_inode_stat(inode);
        f2fs_mark_inode_dirty_sync(inode, true);
        return 0;
#else
        return -EOPNOTSUPP;
#endif
}

static inline bool f2fs_disable_compressed_file(struct inode *inode)
{
        struct f2fs_inode_info *fi = F2FS_I(inode);

        f2fs_down_write(&fi->i_sem);

        if (!f2fs_compressed_file(inode)) {
                f2fs_up_write(&fi->i_sem);
                return true;
        }
        if (f2fs_is_mmap_file(inode) ||
                (S_ISREG(inode->i_mode) && F2FS_HAS_BLOCKS(inode))) {
                f2fs_up_write(&fi->i_sem);
                return false;
        }

        fi->i_flags &= ~F2FS_COMPR_FL;
        stat_dec_compr_inode(inode);
        clear_inode_flag(inode, FI_COMPRESSED_FILE);
        f2fs_mark_inode_dirty_sync(inode, true);

        f2fs_up_write(&fi->i_sem);
        return true;
}

#define F2FS_FEATURE_FUNCS(name, flagname) \
static inline bool f2fs_sb_has_##name(struct f2fs_sb_info *sbi) \
{ \
        return F2FS_HAS_FEATURE(sbi, F2FS_FEATURE_##flagname); \
}

F2FS_FEATURE_FUNCS(encrypt, ENCRYPT);
F2FS_FEATURE_FUNCS(blkzoned, BLKZONED);
F2FS_FEATURE_FUNCS(extra_attr, EXTRA_ATTR);
F2FS_FEATURE_FUNCS(project_quota, PRJQUOTA);
F2FS_FEATURE_FUNCS(inode_chksum, INODE_CHKSUM);
F2FS_FEATURE_FUNCS(flexible_inline_xattr, FLEXIBLE_INLINE_XATTR);
F2FS_FEATURE_FUNCS(quota_ino, QUOTA_INO);
F2FS_FEATURE_FUNCS(inode_crtime, INODE_CRTIME);
F2FS_FEATURE_FUNCS(lost_found, LOST_FOUND);
F2FS_FEATURE_FUNCS(verity, VERITY);
F2FS_FEATURE_FUNCS(sb_chksum, SB_CHKSUM);
F2FS_FEATURE_FUNCS(casefold, CASEFOLD);
F2FS_FEATURE_FUNCS(compression, COMPRESSION);
F2FS_FEATURE_FUNCS(readonly, RO);
F2FS_FEATURE_FUNCS(device_alias, DEVICE_ALIAS);

#ifdef CONFIG_BLK_DEV_ZONED
static inline bool f2fs_blkz_is_seq(struct f2fs_sb_info *sbi, int devi,
                                    block_t blkaddr)
{
        unsigned int zno = blkaddr / sbi->blocks_per_blkz;

        return test_bit(zno, FDEV(devi).blkz_seq);
}
#endif

static inline int f2fs_bdev_index(struct f2fs_sb_info *sbi,
                                  struct block_device *bdev)
{
        int i;

        if (!f2fs_is_multi_device(sbi))
                return 0;

        for (i = 0; i < sbi->s_ndevs; i++)
                if (FDEV(i).bdev == bdev)
                        return i;

        WARN_ON(1);
        return -1;
}

static inline bool f2fs_hw_should_discard(struct f2fs_sb_info *sbi)
{
        return f2fs_sb_has_blkzoned(sbi);
}

static inline bool f2fs_bdev_support_discard(struct block_device *bdev)
{
        return bdev_max_discard_sectors(bdev) || bdev_is_zoned(bdev);
}

static inline bool f2fs_hw_support_discard(struct f2fs_sb_info *sbi)
{
        int i;

        if (!f2fs_is_multi_device(sbi))
                return f2fs_bdev_support_discard(sbi->sb->s_bdev);

        for (i = 0; i < sbi->s_ndevs; i++)
                if (f2fs_bdev_support_discard(FDEV(i).bdev))
                        return true;
        return false;
}

static inline bool f2fs_realtime_discard_enable(struct f2fs_sb_info *sbi)
{
        return (test_opt(sbi, DISCARD) && f2fs_hw_support_discard(sbi)) ||
                                        f2fs_hw_should_discard(sbi);
}

static inline bool f2fs_hw_is_readonly(struct f2fs_sb_info *sbi)
{
        int i;

        if (!f2fs_is_multi_device(sbi))
                return bdev_read_only(sbi->sb->s_bdev);

        for (i = 0; i < sbi->s_ndevs; i++)
                if (bdev_read_only(FDEV(i).bdev))
                        return true;
        return false;
}

static inline bool f2fs_dev_is_readonly(struct f2fs_sb_info *sbi)
{
        return f2fs_sb_has_readonly(sbi) || f2fs_hw_is_readonly(sbi);
}

static inline bool f2fs_lfs_mode(struct f2fs_sb_info *sbi)
{
        return F2FS_OPTION(sbi).fs_mode == FS_MODE_LFS;
}

static inline bool f2fs_valid_pinned_area(struct f2fs_sb_info *sbi,
                                          block_t blkaddr)
{
        if (f2fs_sb_has_blkzoned(sbi)) {
                int devi = f2fs_target_device_index(sbi, blkaddr);

                return !bdev_is_zoned(FDEV(devi).bdev);
        }
        return true;
}

static inline bool f2fs_low_mem_mode(struct f2fs_sb_info *sbi)
{
        return F2FS_OPTION(sbi).memory_mode == MEMORY_MODE_LOW;
}

static inline bool f2fs_may_compress(struct inode *inode)
{
        if (IS_SWAPFILE(inode) || f2fs_is_pinned_file(inode) ||
                f2fs_is_atomic_file(inode) || f2fs_has_inline_data(inode) ||
                f2fs_is_mmap_file(inode))
                return false;
        return S_ISREG(inode->i_mode) || S_ISDIR(inode->i_mode);
}

static inline void f2fs_i_compr_blocks_update(struct inode *inode,
                                                u64 blocks, bool add)
{
        struct f2fs_inode_info *fi = F2FS_I(inode);
        int diff = fi->i_cluster_size - blocks;

        /* don't update i_compr_blocks if saved blocks were released */
        if (!add && !atomic_read(&fi->i_compr_blocks))
                return;

        if (add) {
                atomic_add(diff, &fi->i_compr_blocks);
                stat_add_compr_blocks(inode, diff);
        } else {
                atomic_sub(diff, &fi->i_compr_blocks);
                stat_sub_compr_blocks(inode, diff);
        }
        f2fs_mark_inode_dirty_sync(inode, true);
}

static inline bool f2fs_allow_multi_device_dio(struct f2fs_sb_info *sbi,
                                                                int flag)
{
        if (!f2fs_is_multi_device(sbi))
                return false;
        if (flag != F2FS_GET_BLOCK_DIO)
                return false;
        return sbi->aligned_blksize;
}

static inline bool f2fs_need_verity(const struct inode *inode, pgoff_t idx)
{
        return fsverity_active(inode) &&
               idx < DIV_ROUND_UP(inode->i_size, PAGE_SIZE);
}

#ifdef CONFIG_F2FS_FAULT_INJECTION
extern int f2fs_build_fault_attr(struct f2fs_sb_info *sbi, unsigned long rate,
                                                        unsigned long type);
#else
static inline int f2fs_build_fault_attr(struct f2fs_sb_info *sbi,
                                        unsigned long rate, unsigned long type)
{
        return 0;
}
#endif

static inline bool is_journalled_quota(struct f2fs_sb_info *sbi)
{
#ifdef CONFIG_QUOTA
        if (f2fs_sb_has_quota_ino(sbi))
                return true;
        if (F2FS_OPTION(sbi).s_qf_names[USRQUOTA] ||
                F2FS_OPTION(sbi).s_qf_names[GRPQUOTA] ||
                F2FS_OPTION(sbi).s_qf_names[PRJQUOTA])
                return true;
#endif
        return false;
}

static inline bool f2fs_block_unit_discard(struct f2fs_sb_info *sbi)
{
        return F2FS_OPTION(sbi).discard_unit == DISCARD_UNIT_BLOCK;
}

static inline void f2fs_io_schedule_timeout(long timeout)
{
        set_current_state(TASK_UNINTERRUPTIBLE);
        io_schedule_timeout(timeout);
}

static inline void f2fs_handle_page_eio(struct f2fs_sb_info *sbi,
                                struct folio *folio, enum page_type type)
{
        pgoff_t ofs = folio->index;

        if (unlikely(f2fs_cp_error(sbi)))
                return;

        if (ofs == sbi->page_eio_ofs[type]) {
                if (sbi->page_eio_cnt[type]++ == MAX_RETRY_PAGE_EIO)
                        set_ckpt_flags(sbi, CP_ERROR_FLAG);
        } else {
                sbi->page_eio_ofs[type] = ofs;
                sbi->page_eio_cnt[type] = 0;
        }
}

static inline bool f2fs_is_readonly(struct f2fs_sb_info *sbi)
{
        return f2fs_sb_has_readonly(sbi) || f2fs_readonly(sbi->sb);
}

static inline void f2fs_truncate_meta_inode_pages(struct f2fs_sb_info *sbi,
                                        block_t blkaddr, unsigned int cnt)
{
        bool need_submit = false;
        int i = 0;

        do {
                struct page *page;

                page = find_get_page(META_MAPPING(sbi), blkaddr + i);
                if (page) {
                        if (folio_test_writeback(page_folio(page)))
                                need_submit = true;
                        f2fs_put_page(page, 0);
                }
        } while (++i < cnt && !need_submit);

        if (need_submit)
                f2fs_submit_merged_write_cond(sbi, sbi->meta_inode,
                                                        NULL, 0, DATA);

        truncate_inode_pages_range(META_MAPPING(sbi),
                        F2FS_BLK_TO_BYTES((loff_t)blkaddr),
                        F2FS_BLK_END_BYTES((loff_t)(blkaddr + cnt - 1)));
}

static inline void f2fs_invalidate_internal_cache(struct f2fs_sb_info *sbi,
                                                                block_t blkaddr)
{
        f2fs_truncate_meta_inode_pages(sbi, blkaddr, 1);
        f2fs_invalidate_compress_page(sbi, blkaddr);
}

#define EFSBADCRC        EBADMSG                /* Bad CRC detected */
#define EFSCORRUPTED        EUCLEAN                /* Filesystem is corrupted */

#endif /* _LINUX_F2FS_H */




















































































   11 

















































 7401 










 7401 

















































   50 







 7337 





    8 
























 7138 

































 6961 









 6962 









































    3 





 7336 












  125 





























 6966 
















    6 
















 7338 



















































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
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
/* SPDX-License-Identifier: GPL-2.0 */
#ifndef INT_BLK_MQ_H
#define INT_BLK_MQ_H

#include <linux/blk-mq.h>
#include "blk-stat.h"

struct blk_mq_tag_set;

struct blk_mq_ctxs {
        struct kobject kobj;
        struct blk_mq_ctx __percpu        *queue_ctx;
};

/**
 * struct blk_mq_ctx - State for a software queue facing the submitting CPUs
 */
struct blk_mq_ctx {
        struct {
                spinlock_t                lock;
                struct list_head        rq_lists[HCTX_MAX_TYPES];
        } ____cacheline_aligned_in_smp;

        unsigned int                cpu;
        unsigned short                index_hw[HCTX_MAX_TYPES];
        struct blk_mq_hw_ctx         *hctxs[HCTX_MAX_TYPES];

        struct request_queue        *queue;
        struct blk_mq_ctxs      *ctxs;
        struct kobject                kobj;
} ____cacheline_aligned_in_smp;

enum {
        BLK_MQ_NO_TAG                = -1U,
        BLK_MQ_TAG_MIN                = 1,
        BLK_MQ_TAG_MAX                = BLK_MQ_NO_TAG - 1,
};

#define BLK_MQ_CPU_WORK_BATCH        (8)

typedef unsigned int __bitwise blk_insert_t;
#define BLK_MQ_INSERT_AT_HEAD                ((__force blk_insert_t)0x01)

void blk_mq_submit_bio(struct bio *bio);
int blk_mq_poll(struct request_queue *q, blk_qc_t cookie, struct io_comp_batch *iob,
                unsigned int flags);
void blk_mq_exit_queue(struct request_queue *q);
int blk_mq_update_nr_requests(struct request_queue *q, unsigned int nr);
void blk_mq_wake_waiters(struct request_queue *q);
bool blk_mq_dispatch_rq_list(struct blk_mq_hw_ctx *hctx, struct list_head *,
                             unsigned int);
void blk_mq_flush_busy_ctxs(struct blk_mq_hw_ctx *hctx, struct list_head *list);
struct request *blk_mq_dequeue_from_ctx(struct blk_mq_hw_ctx *hctx,
                                        struct blk_mq_ctx *start);
void blk_mq_put_rq_ref(struct request *rq);

/*
 * Internal helpers for allocating/freeing the request map
 */
void blk_mq_free_rqs(struct blk_mq_tag_set *set, struct blk_mq_tags *tags,
                     unsigned int hctx_idx);
void blk_mq_free_rq_map(struct blk_mq_tags *tags);
struct blk_mq_tags *blk_mq_alloc_map_and_rqs(struct blk_mq_tag_set *set,
                                unsigned int hctx_idx, unsigned int depth);
void blk_mq_free_map_and_rqs(struct blk_mq_tag_set *set,
                             struct blk_mq_tags *tags,
                             unsigned int hctx_idx);

/*
 * CPU -> queue mappings
 */
extern int blk_mq_hw_queue_to_node(struct blk_mq_queue_map *qmap, unsigned int);

/*
 * blk_mq_map_queue_type() - map (hctx_type,cpu) to hardware queue
 * @q: request queue
 * @type: the hctx type index
 * @cpu: CPU
 */
static inline struct blk_mq_hw_ctx *blk_mq_map_queue_type(struct request_queue *q,
                                                          enum hctx_type type,
                                                          unsigned int cpu)
{
        return xa_load(&q->hctx_table, q->tag_set->map[type].mq_map[cpu]);
}

static inline enum hctx_type blk_mq_get_hctx_type(blk_opf_t opf)
{
        enum hctx_type type = HCTX_TYPE_DEFAULT;

        /*
         * The caller ensure that if REQ_POLLED, poll must be enabled.
         */
        if (opf & REQ_POLLED)
                type = HCTX_TYPE_POLL;
        else if ((opf & REQ_OP_MASK) == REQ_OP_READ)
                type = HCTX_TYPE_READ;
        return type;
}

/*
 * blk_mq_map_queue() - map (cmd_flags,type) to hardware queue
 * @q: request queue
 * @opf: operation type (REQ_OP_*) and flags (e.g. REQ_POLLED).
 * @ctx: software queue cpu ctx
 */
static inline struct blk_mq_hw_ctx *blk_mq_map_queue(struct request_queue *q,
                                                     blk_opf_t opf,
                                                     struct blk_mq_ctx *ctx)
{
        return ctx->hctxs[blk_mq_get_hctx_type(opf)];
}

/*
 * sysfs helpers
 */
extern void blk_mq_sysfs_init(struct request_queue *q);
extern void blk_mq_sysfs_deinit(struct request_queue *q);
int blk_mq_sysfs_register(struct gendisk *disk);
void blk_mq_sysfs_unregister(struct gendisk *disk);
int blk_mq_sysfs_register_hctxs(struct request_queue *q);
void blk_mq_sysfs_unregister_hctxs(struct request_queue *q);
extern void blk_mq_hctx_kobj_init(struct blk_mq_hw_ctx *hctx);
void blk_mq_free_plug_rqs(struct blk_plug *plug);
void blk_mq_flush_plug_list(struct blk_plug *plug, bool from_schedule);

void blk_mq_cancel_work_sync(struct request_queue *q);

void blk_mq_release(struct request_queue *q);

static inline struct blk_mq_ctx *__blk_mq_get_ctx(struct request_queue *q,
                                           unsigned int cpu)
{
        return per_cpu_ptr(q->queue_ctx, cpu);
}

/*
 * This assumes per-cpu software queueing queues. They could be per-node
 * as well, for instance. For now this is hardcoded as-is. Note that we don't
 * care about preemption, since we know the ctx's are persistent. This does
 * mean that we can't rely on ctx always matching the currently running CPU.
 */
static inline struct blk_mq_ctx *blk_mq_get_ctx(struct request_queue *q)
{
        return __blk_mq_get_ctx(q, raw_smp_processor_id());
}

struct blk_mq_alloc_data {
        /* input parameter */
        struct request_queue *q;
        blk_mq_req_flags_t flags;
        unsigned int shallow_depth;
        blk_opf_t cmd_flags;
        req_flags_t rq_flags;

        /* allocate multiple requests/tags in one go */
        unsigned int nr_tags;
        struct rq_list *cached_rqs;

        /* input & output parameter */
        struct blk_mq_ctx *ctx;
        struct blk_mq_hw_ctx *hctx;
};

struct blk_mq_tags *blk_mq_init_tags(unsigned int nr_tags,
                unsigned int reserved_tags, int node, int alloc_policy);
void blk_mq_free_tags(struct blk_mq_tags *tags);
int blk_mq_init_bitmaps(struct sbitmap_queue *bitmap_tags,
                struct sbitmap_queue *breserved_tags, unsigned int queue_depth,
                unsigned int reserved, int node, int alloc_policy);

unsigned int blk_mq_get_tag(struct blk_mq_alloc_data *data);
unsigned long blk_mq_get_tags(struct blk_mq_alloc_data *data, int nr_tags,
                unsigned int *offset);
void blk_mq_put_tag(struct blk_mq_tags *tags, struct blk_mq_ctx *ctx,
                unsigned int tag);
void blk_mq_put_tags(struct blk_mq_tags *tags, int *tag_array, int nr_tags);
int blk_mq_tag_update_depth(struct blk_mq_hw_ctx *hctx,
                struct blk_mq_tags **tags, unsigned int depth, bool can_grow);
void blk_mq_tag_resize_shared_tags(struct blk_mq_tag_set *set,
                unsigned int size);
void blk_mq_tag_update_sched_shared_tags(struct request_queue *q);

void blk_mq_tag_wakeup_all(struct blk_mq_tags *tags, bool);
void blk_mq_queue_tag_busy_iter(struct request_queue *q, busy_tag_iter_fn *fn,
                void *priv);
void blk_mq_all_tag_iter(struct blk_mq_tags *tags, busy_tag_iter_fn *fn,
                void *priv);

static inline struct sbq_wait_state *bt_wait_ptr(struct sbitmap_queue *bt,
                                                 struct blk_mq_hw_ctx *hctx)
{
        if (!hctx)
                return &bt->ws[0];
        return sbq_wait_ptr(bt, &hctx->wait_index);
}

void __blk_mq_tag_busy(struct blk_mq_hw_ctx *);
void __blk_mq_tag_idle(struct blk_mq_hw_ctx *);

static inline void blk_mq_tag_busy(struct blk_mq_hw_ctx *hctx)
{
        if (hctx->flags & BLK_MQ_F_TAG_QUEUE_SHARED)
                __blk_mq_tag_busy(hctx);
}

static inline void blk_mq_tag_idle(struct blk_mq_hw_ctx *hctx)
{
        if (hctx->flags & BLK_MQ_F_TAG_QUEUE_SHARED)
                __blk_mq_tag_idle(hctx);
}

static inline bool blk_mq_tag_is_reserved(struct blk_mq_tags *tags,
                                          unsigned int tag)
{
        return tag < tags->nr_reserved_tags;
}

static inline bool blk_mq_is_shared_tags(unsigned int flags)
{
        return flags & BLK_MQ_F_TAG_HCTX_SHARED;
}

static inline struct blk_mq_tags *blk_mq_tags_from_data(struct blk_mq_alloc_data *data)
{
        if (data->rq_flags & RQF_SCHED_TAGS)
                return data->hctx->sched_tags;
        return data->hctx->tags;
}

static inline bool blk_mq_hctx_stopped(struct blk_mq_hw_ctx *hctx)
{
        /* Fast path: hardware queue is not stopped most of the time. */
        if (likely(!test_bit(BLK_MQ_S_STOPPED, &hctx->state)))
                return false;

        /*
         * This barrier is used to order adding of dispatch list before and
         * the test of BLK_MQ_S_STOPPED below. Pairs with the memory barrier
         * in blk_mq_start_stopped_hw_queue() so that dispatch code could
         * either see BLK_MQ_S_STOPPED is cleared or dispatch list is not
         * empty to avoid missing dispatching requests.
         */
        smp_mb();

        return test_bit(BLK_MQ_S_STOPPED, &hctx->state);
}

static inline bool blk_mq_hw_queue_mapped(struct blk_mq_hw_ctx *hctx)
{
        return hctx->nr_ctx && hctx->tags;
}

unsigned int blk_mq_in_flight(struct request_queue *q,
                struct block_device *part);
void blk_mq_in_flight_rw(struct request_queue *q, struct block_device *part,
                unsigned int inflight[2]);

static inline void blk_mq_put_dispatch_budget(struct request_queue *q,
                                              int budget_token)
{
        if (q->mq_ops->put_budget)
                q->mq_ops->put_budget(q, budget_token);
}

static inline int blk_mq_get_dispatch_budget(struct request_queue *q)
{
        if (q->mq_ops->get_budget)
                return q->mq_ops->get_budget(q);
        return 0;
}

static inline void blk_mq_set_rq_budget_token(struct request *rq, int token)
{
        if (token < 0)
                return;

        if (rq->q->mq_ops->set_rq_budget_token)
                rq->q->mq_ops->set_rq_budget_token(rq, token);
}

static inline int blk_mq_get_rq_budget_token(struct request *rq)
{
        if (rq->q->mq_ops->get_rq_budget_token)
                return rq->q->mq_ops->get_rq_budget_token(rq);
        return -1;
}

static inline void __blk_mq_add_active_requests(struct blk_mq_hw_ctx *hctx,
                                                int val)
{
        if (blk_mq_is_shared_tags(hctx->flags))
                atomic_add(val, &hctx->queue->nr_active_requests_shared_tags);
        else
                atomic_add(val, &hctx->nr_active);
}

static inline void __blk_mq_inc_active_requests(struct blk_mq_hw_ctx *hctx)
{
        __blk_mq_add_active_requests(hctx, 1);
}

static inline void __blk_mq_sub_active_requests(struct blk_mq_hw_ctx *hctx,
                int val)
{
        if (blk_mq_is_shared_tags(hctx->flags))
                atomic_sub(val, &hctx->queue->nr_active_requests_shared_tags);
        else
                atomic_sub(val, &hctx->nr_active);
}

static inline void __blk_mq_dec_active_requests(struct blk_mq_hw_ctx *hctx)
{
        __blk_mq_sub_active_requests(hctx, 1);
}

static inline void blk_mq_add_active_requests(struct blk_mq_hw_ctx *hctx,
                                              int val)
{
        if (hctx->flags & BLK_MQ_F_TAG_QUEUE_SHARED)
                __blk_mq_add_active_requests(hctx, val);
}

static inline void blk_mq_inc_active_requests(struct blk_mq_hw_ctx *hctx)
{
        if (hctx->flags & BLK_MQ_F_TAG_QUEUE_SHARED)
                __blk_mq_inc_active_requests(hctx);
}

static inline void blk_mq_sub_active_requests(struct blk_mq_hw_ctx *hctx,
                                              int val)
{
        if (hctx->flags & BLK_MQ_F_TAG_QUEUE_SHARED)
                __blk_mq_sub_active_requests(hctx, val);
}

static inline void blk_mq_dec_active_requests(struct blk_mq_hw_ctx *hctx)
{
        if (hctx->flags & BLK_MQ_F_TAG_QUEUE_SHARED)
                __blk_mq_dec_active_requests(hctx);
}

static inline int __blk_mq_active_requests(struct blk_mq_hw_ctx *hctx)
{
        if (blk_mq_is_shared_tags(hctx->flags))
                return atomic_read(&hctx->queue->nr_active_requests_shared_tags);
        return atomic_read(&hctx->nr_active);
}
static inline void __blk_mq_put_driver_tag(struct blk_mq_hw_ctx *hctx,
                                           struct request *rq)
{
        blk_mq_dec_active_requests(hctx);
        blk_mq_put_tag(hctx->tags, rq->mq_ctx, rq->tag);
        rq->tag = BLK_MQ_NO_TAG;
}

static inline void blk_mq_put_driver_tag(struct request *rq)
{
        if (rq->tag == BLK_MQ_NO_TAG || rq->internal_tag == BLK_MQ_NO_TAG)
                return;

        __blk_mq_put_driver_tag(rq->mq_hctx, rq);
}

bool __blk_mq_alloc_driver_tag(struct request *rq);

static inline bool blk_mq_get_driver_tag(struct request *rq)
{
        if (rq->tag == BLK_MQ_NO_TAG && !__blk_mq_alloc_driver_tag(rq))
                return false;

        return true;
}

static inline void blk_mq_clear_mq_map(struct blk_mq_queue_map *qmap)
{
        int cpu;

        for_each_possible_cpu(cpu)
                qmap->mq_map[cpu] = 0;
}

/* Free all requests on the list */
static inline void blk_mq_free_requests(struct list_head *list)
{
        while (!list_empty(list)) {
                struct request *rq = list_entry_rq(list->next);

                list_del_init(&rq->queuelist);
                blk_mq_free_request(rq);
        }
}

/*
 * For shared tag users, we track the number of currently active users
 * and attempt to provide a fair share of the tag depth for each of them.
 */
static inline bool hctx_may_queue(struct blk_mq_hw_ctx *hctx,
                                  struct sbitmap_queue *bt)
{
        unsigned int depth, users;

        if (!hctx || !(hctx->flags & BLK_MQ_F_TAG_QUEUE_SHARED))
                return true;

        /*
         * Don't try dividing an ant
         */
        if (bt->sb.depth == 1)
                return true;

        if (blk_mq_is_shared_tags(hctx->flags)) {
                struct request_queue *q = hctx->queue;

                if (!test_bit(QUEUE_FLAG_HCTX_ACTIVE, &q->queue_flags))
                        return true;
        } else {
                if (!test_bit(BLK_MQ_S_TAG_ACTIVE, &hctx->state))
                        return true;
        }

        users = READ_ONCE(hctx->tags->active_queues);
        if (!users)
                return true;

        /*
         * Allow at least some tags
         */
        depth = max((bt->sb.depth + users - 1) / users, 4U);
        return __blk_mq_active_requests(hctx) < depth;
}

/* run the code block in @dispatch_ops with rcu/srcu read lock held */
#define __blk_mq_run_dispatch_ops(q, check_sleep, dispatch_ops)        \
do {                                                                \
        if ((q)->tag_set->flags & BLK_MQ_F_BLOCKING) {                \
                struct blk_mq_tag_set *__tag_set = (q)->tag_set; \
                int srcu_idx;                                        \
                                                                \
                might_sleep_if(check_sleep);                        \
                srcu_idx = srcu_read_lock(__tag_set->srcu);        \
                (dispatch_ops);                                        \
                srcu_read_unlock(__tag_set->srcu, srcu_idx);        \
        } else {                                                \
                rcu_read_lock();                                \
                (dispatch_ops);                                        \
                rcu_read_unlock();                                \
        }                                                        \
} while (0)

#define blk_mq_run_dispatch_ops(q, dispatch_ops)                \
        __blk_mq_run_dispatch_ops(q, true, dispatch_ops)        \

#endif








































































































































































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
/* SPDX-License-Identifier: GPL-2.0-only */
/*
 * Copyright (C) 1999-2002 Vojtech Pavlik
 */
#ifndef _SERIO_H
#define _SERIO_H


#include <linux/cleanup.h>
#include <linux/types.h>
#include <linux/interrupt.h>
#include <linux/list.h>
#include <linux/spinlock.h>
#include <linux/mutex.h>
#include <linux/device.h>
#include <linux/mod_devicetable.h>
#include <uapi/linux/serio.h>

extern const struct bus_type serio_bus;

struct serio {
        void *port_data;

        char name[32];
        char phys[32];
        char firmware_id[128];

        bool manual_bind;

        struct serio_device_id id;

        /* Protects critical sections from port's interrupt handler */
        spinlock_t lock;

        int (*write)(struct serio *, unsigned char);
        int (*open)(struct serio *);
        void (*close)(struct serio *);
        int (*start)(struct serio *);
        void (*stop)(struct serio *);

        struct serio *parent;
        /* Entry in parent->children list */
        struct list_head child_node;
        struct list_head children;
        /* Level of nesting in serio hierarchy */
        unsigned int depth;

        /*
         * serio->drv is accessed from interrupt handlers; when modifying
         * caller should acquire serio->drv_mutex and serio->lock.
         */
        struct serio_driver *drv;
        /* Protects serio->drv so attributes can pin current driver */
        struct mutex drv_mutex;

        struct device dev;

        struct list_head node;

        /*
         * For use by PS/2 layer when several ports share hardware and
         * may get indigestion when exposed to concurrent access (i8042).
         */
        struct mutex *ps2_cmd_mutex;
};
#define to_serio_port(d)        container_of(d, struct serio, dev)

struct serio_driver {
        const char *description;

        const struct serio_device_id *id_table;
        bool manual_bind;

        void (*write_wakeup)(struct serio *);
        irqreturn_t (*interrupt)(struct serio *, unsigned char, unsigned int);
        int  (*connect)(struct serio *, struct serio_driver *drv);
        int  (*reconnect)(struct serio *);
        int  (*fast_reconnect)(struct serio *);
        void (*disconnect)(struct serio *);
        void (*cleanup)(struct serio *);

        struct device_driver driver;
};
#define to_serio_driver(d)        container_of_const(d, struct serio_driver, driver)

int serio_open(struct serio *serio, struct serio_driver *drv);
void serio_close(struct serio *serio);
void serio_rescan(struct serio *serio);
void serio_reconnect(struct serio *serio);
irqreturn_t serio_interrupt(struct serio *serio, unsigned char data, unsigned int flags);

void __serio_register_port(struct serio *serio, struct module *owner);

/* use a define to avoid include chaining to get THIS_MODULE */
#define serio_register_port(serio) \
        __serio_register_port(serio, THIS_MODULE)

void serio_unregister_port(struct serio *serio);
void serio_unregister_child_port(struct serio *serio);

int __must_check __serio_register_driver(struct serio_driver *drv,
                                struct module *owner, const char *mod_name);

/* use a define to avoid include chaining to get THIS_MODULE & friends */
#define serio_register_driver(drv) \
        __serio_register_driver(drv, THIS_MODULE, KBUILD_MODNAME)

void serio_unregister_driver(struct serio_driver *drv);

/**
 * module_serio_driver() - Helper macro for registering a serio driver
 * @__serio_driver: serio_driver struct
 *
 * Helper macro for serio drivers which do not do anything special in
 * module init/exit. This eliminates a lot of boilerplate. Each module
 * may only use this macro once, and calling it replaces module_init()
 * and module_exit().
 */
#define module_serio_driver(__serio_driver) \
        module_driver(__serio_driver, serio_register_driver, \
                       serio_unregister_driver)

static inline int serio_write(struct serio *serio, unsigned char data)
{
        if (serio->write)
                return serio->write(serio, data);
        else
                return -1;
}

static inline void serio_drv_write_wakeup(struct serio *serio)
{
        if (serio->drv && serio->drv->write_wakeup)
                serio->drv->write_wakeup(serio);
}

/*
 * Use the following functions to manipulate serio's per-port
 * driver-specific data.
 */
static inline void *serio_get_drvdata(struct serio *serio)
{
        return dev_get_drvdata(&serio->dev);
}

static inline void serio_set_drvdata(struct serio *serio, void *data)
{
        dev_set_drvdata(&serio->dev, data);
}

/*
 * Use the following functions to protect critical sections in
 * driver code from port's interrupt handler
 */
static inline void serio_pause_rx(struct serio *serio)
{
        spin_lock_irq(&serio->lock);
}

static inline void serio_continue_rx(struct serio *serio)
{
        spin_unlock_irq(&serio->lock);
}

DEFINE_GUARD(serio_pause_rx, struct serio *, serio_pause_rx(_T), serio_continue_rx(_T))

#endif


























    1 















    1 











   10 










    1 


    1 

    1 



    2 


    2 



    3 



    1 




    1 

    1 

    2 

    1 
    1 






    1 















    1 








    3 








    3 
    3 























    3 





































































   13 












    1 


    1 

    1 



    4 

    3 


    1 




    2 



    1 













    1 










   18 




   18 
   18 


   18 








   18 
























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
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
// SPDX-License-Identifier: GPL-2.0-only
/*
 * File: pn_netlink.c
 *
 * Phonet netlink interface
 *
 * Copyright (C) 2008 Nokia Corporation.
 *
 * Authors: Sakari Ailus <sakari.ailus@nokia.com>
 *          Remi Denis-Courmont
 */

#include <linux/kernel.h>
#include <linux/netlink.h>
#include <linux/phonet.h>
#include <linux/slab.h>
#include <net/sock.h>
#include <net/phonet/pn_dev.h>

/* Device address handling */

static int fill_addr(struct sk_buff *skb, u32 ifindex, u8 addr,
                     u32 portid, u32 seq, int event);

void phonet_address_notify(struct net *net, int event, u32 ifindex, u8 addr)
{
        struct sk_buff *skb;
        int err = -ENOBUFS;

        skb = nlmsg_new(NLMSG_ALIGN(sizeof(struct ifaddrmsg)) +
                        nla_total_size(1), GFP_KERNEL);
        if (skb == NULL)
                goto errout;

        err = fill_addr(skb, ifindex, addr, 0, 0, event);
        if (err < 0) {
                WARN_ON(err == -EMSGSIZE);
                kfree_skb(skb);
                goto errout;
        }

        rtnl_notify(skb, net, 0, RTNLGRP_PHONET_IFADDR, NULL, GFP_KERNEL);
        return;
errout:
        rtnl_set_sk_err(net, RTNLGRP_PHONET_IFADDR, err);
}

static const struct nla_policy ifa_phonet_policy[IFA_MAX+1] = {
        [IFA_LOCAL] = { .type = NLA_U8 },
};

static int addr_doit(struct sk_buff *skb, struct nlmsghdr *nlh,
                     struct netlink_ext_ack *extack)
{
        struct net *net = sock_net(skb->sk);
        struct nlattr *tb[IFA_MAX+1];
        struct net_device *dev;
        struct ifaddrmsg *ifm;
        int err;
        u8 pnaddr;

        if (!netlink_capable(skb, CAP_NET_ADMIN))
                return -EPERM;

        if (!netlink_capable(skb, CAP_SYS_ADMIN))
                return -EPERM;

        err = nlmsg_parse_deprecated(nlh, sizeof(*ifm), tb, IFA_MAX,
                                     ifa_phonet_policy, extack);
        if (err < 0)
                return err;

        ifm = nlmsg_data(nlh);
        if (tb[IFA_LOCAL] == NULL)
                return -EINVAL;
        pnaddr = nla_get_u8(tb[IFA_LOCAL]);
        if (pnaddr & 3)
                /* Phonet addresses only have 6 high-order bits */
                return -EINVAL;

        rcu_read_lock();

        dev = dev_get_by_index_rcu(net, ifm->ifa_index);
        if (!dev) {
                rcu_read_unlock();
                return -ENODEV;
        }

        if (nlh->nlmsg_type == RTM_NEWADDR)
                err = phonet_address_add(dev, pnaddr);
        else
                err = phonet_address_del(dev, pnaddr);

        rcu_read_unlock();

        if (!err)
                phonet_address_notify(net, nlh->nlmsg_type, ifm->ifa_index, pnaddr);

        return err;
}

static int fill_addr(struct sk_buff *skb, u32 ifindex, u8 addr,
                     u32 portid, u32 seq, int event)
{
        struct ifaddrmsg *ifm;
        struct nlmsghdr *nlh;

        nlh = nlmsg_put(skb, portid, seq, event, sizeof(*ifm), 0);
        if (nlh == NULL)
                return -EMSGSIZE;

        ifm = nlmsg_data(nlh);
        ifm->ifa_family = AF_PHONET;
        ifm->ifa_prefixlen = 0;
        ifm->ifa_flags = IFA_F_PERMANENT;
        ifm->ifa_scope = RT_SCOPE_LINK;
        ifm->ifa_index = ifindex;
        if (nla_put_u8(skb, IFA_LOCAL, addr))
                goto nla_put_failure;
        nlmsg_end(skb, nlh);
        return 0;

nla_put_failure:
        nlmsg_cancel(skb, nlh);
        return -EMSGSIZE;
}

static int getaddr_dumpit(struct sk_buff *skb, struct netlink_callback *cb)
{
        int addr_idx = 0, addr_start_idx = cb->args[1];
        int dev_idx = 0, dev_start_idx = cb->args[0];
        struct phonet_device_list *pndevs;
        struct phonet_device *pnd;
        int err = 0;

        pndevs = phonet_device_list(sock_net(skb->sk));

        rcu_read_lock();
        list_for_each_entry_rcu(pnd, &pndevs->list, list) {
                DECLARE_BITMAP(addrs, 64);
                u8 addr;

                if (dev_idx > dev_start_idx)
                        addr_start_idx = 0;
                if (dev_idx++ < dev_start_idx)
                        continue;

                addr_idx = 0;
                memcpy(addrs, pnd->addrs, sizeof(pnd->addrs));

                for_each_set_bit(addr, addrs, 64) {
                        if (addr_idx++ < addr_start_idx)
                                continue;

                        err = fill_addr(skb, READ_ONCE(pnd->netdev->ifindex),
                                        addr << 2, NETLINK_CB(cb->skb).portid,
                                        cb->nlh->nlmsg_seq, RTM_NEWADDR);
                        if (err < 0)
                                goto out;
                }
        }
out:
        rcu_read_unlock();

        cb->args[0] = dev_idx;
        cb->args[1] = addr_idx;

        return err;
}

/* Routes handling */

static int fill_route(struct sk_buff *skb, u32 ifindex, u8 dst,
                      u32 portid, u32 seq, int event)
{
        struct rtmsg *rtm;
        struct nlmsghdr *nlh;

        nlh = nlmsg_put(skb, portid, seq, event, sizeof(*rtm), 0);
        if (nlh == NULL)
                return -EMSGSIZE;

        rtm = nlmsg_data(nlh);
        rtm->rtm_family = AF_PHONET;
        rtm->rtm_dst_len = 6;
        rtm->rtm_src_len = 0;
        rtm->rtm_tos = 0;
        rtm->rtm_table = RT_TABLE_MAIN;
        rtm->rtm_protocol = RTPROT_STATIC;
        rtm->rtm_scope = RT_SCOPE_UNIVERSE;
        rtm->rtm_type = RTN_UNICAST;
        rtm->rtm_flags = 0;
        if (nla_put_u8(skb, RTA_DST, dst) || nla_put_u32(skb, RTA_OIF, ifindex))
                goto nla_put_failure;
        nlmsg_end(skb, nlh);
        return 0;

nla_put_failure:
        nlmsg_cancel(skb, nlh);
        return -EMSGSIZE;
}

void rtm_phonet_notify(struct net *net, int event, u32 ifindex, u8 dst)
{
        struct sk_buff *skb;
        int err = -ENOBUFS;

        skb = nlmsg_new(NLMSG_ALIGN(sizeof(struct rtmsg)) +
                        nla_total_size(1) + nla_total_size(4), GFP_KERNEL);
        if (skb == NULL)
                goto errout;

        err = fill_route(skb, ifindex, dst, 0, 0, event);
        if (err < 0) {
                WARN_ON(err == -EMSGSIZE);
                kfree_skb(skb);
                goto errout;
        }

        rtnl_notify(skb, net, 0, RTNLGRP_PHONET_ROUTE, NULL, GFP_KERNEL);
        return;
errout:
        rtnl_set_sk_err(net, RTNLGRP_PHONET_ROUTE, err);
}

static const struct nla_policy rtm_phonet_policy[RTA_MAX+1] = {
        [RTA_DST] = { .type = NLA_U8 },
        [RTA_OIF] = { .type = NLA_U32 },
};

static int route_doit(struct sk_buff *skb, struct nlmsghdr *nlh,
                      struct netlink_ext_ack *extack)
{
        struct net *net = sock_net(skb->sk);
        struct nlattr *tb[RTA_MAX+1];
        bool sync_needed = false;
        struct net_device *dev;
        struct rtmsg *rtm;
        u32 ifindex;
        int err;
        u8 dst;

        if (!netlink_capable(skb, CAP_NET_ADMIN))
                return -EPERM;

        if (!netlink_capable(skb, CAP_SYS_ADMIN))
                return -EPERM;

        err = nlmsg_parse_deprecated(nlh, sizeof(*rtm), tb, RTA_MAX,
                                     rtm_phonet_policy, extack);
        if (err < 0)
                return err;

        rtm = nlmsg_data(nlh);
        if (rtm->rtm_table != RT_TABLE_MAIN || rtm->rtm_type != RTN_UNICAST)
                return -EINVAL;
        if (tb[RTA_DST] == NULL || tb[RTA_OIF] == NULL)
                return -EINVAL;
        dst = nla_get_u8(tb[RTA_DST]);
        if (dst & 3) /* Phonet addresses only have 6 high-order bits */
                return -EINVAL;

        ifindex = nla_get_u32(tb[RTA_OIF]);

        rcu_read_lock();

        dev = dev_get_by_index_rcu(net, ifindex);
        if (!dev) {
                rcu_read_unlock();
                return -ENODEV;
        }

        if (nlh->nlmsg_type == RTM_NEWROUTE) {
                err = phonet_route_add(dev, dst);
        } else {
                err = phonet_route_del(dev, dst);
                if (!err)
                        sync_needed = true;
        }

        rcu_read_unlock();

        if (sync_needed) {
                synchronize_rcu();
                dev_put(dev);
        }
        if (!err)
                rtm_phonet_notify(net, nlh->nlmsg_type, ifindex, dst);

        return err;
}

static int route_dumpit(struct sk_buff *skb, struct netlink_callback *cb)
{
        struct net *net = sock_net(skb->sk);
        int err = 0;
        u8 addr;

        rcu_read_lock();
        for (addr = cb->args[0]; addr < 64; addr++) {
                struct net_device *dev = phonet_route_get_rcu(net, addr << 2);

                if (!dev)
                        continue;

                err = fill_route(skb, READ_ONCE(dev->ifindex), addr << 2,
                                 NETLINK_CB(cb->skb).portid,
                                 cb->nlh->nlmsg_seq, RTM_NEWROUTE);
                if (err < 0)
                        break;
        }
        rcu_read_unlock();
        cb->args[0] = addr;

        return err;
}

static const struct rtnl_msg_handler phonet_rtnl_msg_handlers[] __initdata_or_module = {
        {.owner = THIS_MODULE, .protocol = PF_PHONET, .msgtype = RTM_NEWADDR,
         .doit = addr_doit, .flags = RTNL_FLAG_DOIT_UNLOCKED},
        {.owner = THIS_MODULE, .protocol = PF_PHONET, .msgtype = RTM_DELADDR,
         .doit = addr_doit, .flags = RTNL_FLAG_DOIT_UNLOCKED},
        {.owner = THIS_MODULE, .protocol = PF_PHONET, .msgtype = RTM_GETADDR,
         .dumpit = getaddr_dumpit, .flags = RTNL_FLAG_DUMP_UNLOCKED},
        {.owner = THIS_MODULE, .protocol = PF_PHONET, .msgtype = RTM_NEWROUTE,
         .doit = route_doit, .flags = RTNL_FLAG_DOIT_UNLOCKED},
        {.owner = THIS_MODULE, .protocol = PF_PHONET, .msgtype = RTM_DELROUTE,
         .doit = route_doit, .flags = RTNL_FLAG_DOIT_UNLOCKED},
        {.owner = THIS_MODULE, .protocol = PF_PHONET, .msgtype = RTM_GETROUTE,
         .dumpit = route_dumpit, .flags = RTNL_FLAG_DUMP_UNLOCKED},
};

int __init phonet_netlink_register(void)
{
        return rtnl_register_many(phonet_rtnl_msg_handlers);
}








































   13 




   13 




    9 



    9 
   13 
    2 



    6 


    9 

   13 



    6 




    6 


    1 
   13 










    5 
    6 






   13 






















   41 















































   60 

   60 








   13 

   10 
   47 


   47 




   44 





   47 
















   41 
   41 































   60 








   60 








   13 



   13 
   49 
    3 















   49 
    3 














































 23997 






 23977 


























 23982 




 24083 















































   91 


























































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
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
// SPDX-License-Identifier: GPL-2.0
/*
 * security/tomoyo/audit.c
 *
 * Copyright (C) 2005-2011  NTT DATA CORPORATION
 */

#include "common.h"
#include <linux/slab.h>

/**
 * tomoyo_print_bprm - Print "struct linux_binprm" for auditing.
 *
 * @bprm: Pointer to "struct linux_binprm".
 * @dump: Pointer to "struct tomoyo_page_dump".
 *
 * Returns the contents of @bprm on success, NULL otherwise.
 *
 * This function uses kzalloc(), so caller must kfree() if this function
 * didn't return NULL.
 */
static char *tomoyo_print_bprm(struct linux_binprm *bprm,
                               struct tomoyo_page_dump *dump)
{
        static const int tomoyo_buffer_len = 4096 * 2;
        char *buffer = kzalloc(tomoyo_buffer_len, GFP_NOFS);
        char *cp;
        char *last_start;
        int len;
        unsigned long pos = bprm->p;
        int offset = pos % PAGE_SIZE;
        int argv_count = bprm->argc;
        int envp_count = bprm->envc;
        bool truncated = false;

        if (!buffer)
                return NULL;
        len = snprintf(buffer, tomoyo_buffer_len - 1, "argv[]={ ");
        cp = buffer + len;
        if (!argv_count) {
                memmove(cp, "} envp[]={ ", 11);
                cp += 11;
        }
        last_start = cp;
        while (argv_count || envp_count) {
                if (!tomoyo_dump_page(bprm, pos, dump))
                        goto out;
                pos += PAGE_SIZE - offset;
                /* Read. */
                while (offset < PAGE_SIZE) {
                        const char *kaddr = dump->data;
                        const unsigned char c = kaddr[offset++];

                        if (cp == last_start)
                                *cp++ = '"';
                        if (cp >= buffer + tomoyo_buffer_len - 32) {
                                /* Reserve some room for "..." string. */
                                truncated = true;
                        } else if (c == '\\') {
                                *cp++ = '\\';
                                *cp++ = '\\';
                        } else if (c > ' ' && c < 127) {
                                *cp++ = c;
                        } else if (!c) {
                                *cp++ = '"';
                                *cp++ = ' ';
                                last_start = cp;
                        } else {
                                *cp++ = '\\';
                                *cp++ = (c >> 6) + '0';
                                *cp++ = ((c >> 3) & 7) + '0';
                                *cp++ = (c & 7) + '0';
                        }
                        if (c)
                                continue;
                        if (argv_count) {
                                if (--argv_count == 0) {
                                        if (truncated) {
                                                cp = last_start;
                                                memmove(cp, "... ", 4);
                                                cp += 4;
                                        }
                                        memmove(cp, "} envp[]={ ", 11);
                                        cp += 11;
                                        last_start = cp;
                                        truncated = false;
                                }
                        } else if (envp_count) {
                                if (--envp_count == 0) {
                                        if (truncated) {
                                                cp = last_start;
                                                memmove(cp, "... ", 4);
                                                cp += 4;
                                        }
                                }
                        }
                        if (!argv_count && !envp_count)
                                break;
                }
                offset = 0;
        }
        *cp++ = '}';
        *cp = '\0';
        return buffer;
out:
        snprintf(buffer, tomoyo_buffer_len - 1,
                 "argv[]={ ... } envp[]= { ... }");
        return buffer;
}

/**
 * tomoyo_filetype - Get string representation of file type.
 *
 * @mode: Mode value for stat().
 *
 * Returns file type string.
 */
static inline const char *tomoyo_filetype(const umode_t mode)
{
        switch (mode & S_IFMT) {
        case S_IFREG:
        case 0:
                return tomoyo_condition_keyword[TOMOYO_TYPE_IS_FILE];
        case S_IFDIR:
                return tomoyo_condition_keyword[TOMOYO_TYPE_IS_DIRECTORY];
        case S_IFLNK:
                return tomoyo_condition_keyword[TOMOYO_TYPE_IS_SYMLINK];
        case S_IFIFO:
                return tomoyo_condition_keyword[TOMOYO_TYPE_IS_FIFO];
        case S_IFSOCK:
                return tomoyo_condition_keyword[TOMOYO_TYPE_IS_SOCKET];
        case S_IFBLK:
                return tomoyo_condition_keyword[TOMOYO_TYPE_IS_BLOCK_DEV];
        case S_IFCHR:
                return tomoyo_condition_keyword[TOMOYO_TYPE_IS_CHAR_DEV];
        }
        return "unknown"; /* This should not happen. */
}

/**
 * tomoyo_print_header - Get header line of audit log.
 *
 * @r: Pointer to "struct tomoyo_request_info".
 *
 * Returns string representation.
 *
 * This function uses kmalloc(), so caller must kfree() if this function
 * didn't return NULL.
 */
static char *tomoyo_print_header(struct tomoyo_request_info *r)
{
        struct tomoyo_time stamp;
        const pid_t gpid = task_pid_nr(current);
        struct tomoyo_obj_info *obj = r->obj;
        static const int tomoyo_buffer_len = 4096;
        char *buffer = kmalloc(tomoyo_buffer_len, GFP_NOFS);
        int pos;
        u8 i;

        if (!buffer)
                return NULL;

        tomoyo_convert_time(ktime_get_real_seconds(), &stamp);

        pos = snprintf(buffer, tomoyo_buffer_len - 1,
                       "#%04u/%02u/%02u %02u:%02u:%02u# profile=%u mode=%s granted=%s (global-pid=%u) task={ pid=%u ppid=%u uid=%u gid=%u euid=%u egid=%u suid=%u sgid=%u fsuid=%u fsgid=%u }",
                       stamp.year, stamp.month, stamp.day, stamp.hour,
                       stamp.min, stamp.sec, r->profile, tomoyo_mode[r->mode],
                       str_yes_no(r->granted), gpid, tomoyo_sys_getpid(),
                       tomoyo_sys_getppid(),
                       from_kuid(&init_user_ns, current_uid()),
                       from_kgid(&init_user_ns, current_gid()),
                       from_kuid(&init_user_ns, current_euid()),
                       from_kgid(&init_user_ns, current_egid()),
                       from_kuid(&init_user_ns, current_suid()),
                       from_kgid(&init_user_ns, current_sgid()),
                       from_kuid(&init_user_ns, current_fsuid()),
                       from_kgid(&init_user_ns, current_fsgid()));
        if (!obj)
                goto no_obj_info;
        if (!obj->validate_done) {
                tomoyo_get_attributes(obj);
                obj->validate_done = true;
        }
        for (i = 0; i < TOMOYO_MAX_PATH_STAT; i++) {
                struct tomoyo_mini_stat *stat;
                unsigned int dev;
                umode_t mode;

                if (!obj->stat_valid[i])
                        continue;
                stat = &obj->stat[i];
                dev = stat->dev;
                mode = stat->mode;
                if (i & 1) {
                        pos += snprintf(buffer + pos,
                                        tomoyo_buffer_len - 1 - pos,
                                        " path%u.parent={ uid=%u gid=%u ino=%lu perm=0%o }",
                                        (i >> 1) + 1,
                                        from_kuid(&init_user_ns, stat->uid),
                                        from_kgid(&init_user_ns, stat->gid),
                                        (unsigned long)stat->ino,
                                        stat->mode & S_IALLUGO);
                        continue;
                }
                pos += snprintf(buffer + pos, tomoyo_buffer_len - 1 - pos,
                                " path%u={ uid=%u gid=%u ino=%lu major=%u minor=%u perm=0%o type=%s",
                                (i >> 1) + 1,
                                from_kuid(&init_user_ns, stat->uid),
                                from_kgid(&init_user_ns, stat->gid),
                                (unsigned long)stat->ino,
                                MAJOR(dev), MINOR(dev),
                                mode & S_IALLUGO, tomoyo_filetype(mode));
                if (S_ISCHR(mode) || S_ISBLK(mode)) {
                        dev = stat->rdev;
                        pos += snprintf(buffer + pos,
                                        tomoyo_buffer_len - 1 - pos,
                                        " dev_major=%u dev_minor=%u",
                                        MAJOR(dev), MINOR(dev));
                }
                pos += snprintf(buffer + pos, tomoyo_buffer_len - 1 - pos,
                                " }");
        }
no_obj_info:
        if (pos < tomoyo_buffer_len - 1)
                return buffer;
        kfree(buffer);
        return NULL;
}

/**
 * tomoyo_init_log - Allocate buffer for audit logs.
 *
 * @r:    Pointer to "struct tomoyo_request_info".
 * @len:  Buffer size needed for @fmt and @args.
 * @fmt:  The printf()'s format string.
 * @args: va_list structure for @fmt.
 *
 * Returns pointer to allocated memory.
 *
 * This function uses kzalloc(), so caller must kfree() if this function
 * didn't return NULL.
 */
char *tomoyo_init_log(struct tomoyo_request_info *r, int len, const char *fmt,
                      va_list args)
{
        char *buf = NULL;
        char *bprm_info = NULL;
        const char *header = NULL;
        char *realpath = NULL;
        const char *symlink = NULL;
        int pos;
        const char *domainname = r->domain->domainname->name;

        header = tomoyo_print_header(r);
        if (!header)
                return NULL;
        /* +10 is for '\n' etc. and '\0'. */
        len += strlen(domainname) + strlen(header) + 10;
        if (r->ee) {
                struct file *file = r->ee->bprm->file;

                realpath = tomoyo_realpath_from_path(&file->f_path);
                bprm_info = tomoyo_print_bprm(r->ee->bprm, &r->ee->dump);
                if (!realpath || !bprm_info)
                        goto out;
                /* +80 is for " exec={ realpath=\"%s\" argc=%d envc=%d %s }" */
                len += strlen(realpath) + 80 + strlen(bprm_info);
        } else if (r->obj && r->obj->symlink_target) {
                symlink = r->obj->symlink_target->name;
                /* +18 is for " symlink.target=\"%s\"" */
                len += 18 + strlen(symlink);
        }
        len = kmalloc_size_roundup(len);
        buf = kzalloc(len, GFP_NOFS);
        if (!buf)
                goto out;
        len--;
        pos = snprintf(buf, len, "%s", header);
        if (realpath) {
                struct linux_binprm *bprm = r->ee->bprm;

                pos += snprintf(buf + pos, len - pos,
                                " exec={ realpath=\"%s\" argc=%d envc=%d %s }",
                                realpath, bprm->argc, bprm->envc, bprm_info);
        } else if (symlink)
                pos += snprintf(buf + pos, len - pos, " symlink.target=\"%s\"",
                                symlink);
        pos += snprintf(buf + pos, len - pos, "\n%s\n", domainname);
        vsnprintf(buf + pos, len - pos, fmt, args);
out:
        kfree(realpath);
        kfree(bprm_info);
        kfree(header);
        return buf;
}

/* Wait queue for /sys/kernel/security/tomoyo/audit. */
static DECLARE_WAIT_QUEUE_HEAD(tomoyo_log_wait);

/* Structure for audit log. */
struct tomoyo_log {
        struct list_head list;
        char *log;
        int size;
};

/* The list for "struct tomoyo_log". */
static LIST_HEAD(tomoyo_log);

/* Lock for "struct list_head tomoyo_log". */
static DEFINE_SPINLOCK(tomoyo_log_lock);

/* Length of "struct list_head tomoyo_log". */
static unsigned int tomoyo_log_count;

/**
 * tomoyo_get_audit - Get audit mode.
 *
 * @ns:          Pointer to "struct tomoyo_policy_namespace".
 * @profile:     Profile number.
 * @index:       Index number of functionality.
 * @matched_acl: Pointer to "struct tomoyo_acl_info".
 * @is_granted:  True if granted log, false otherwise.
 *
 * Returns true if this request should be audited, false otherwise.
 */
static bool tomoyo_get_audit(const struct tomoyo_policy_namespace *ns,
                             const u8 profile, const u8 index,
                             const struct tomoyo_acl_info *matched_acl,
                             const bool is_granted)
{
        u8 mode;
        const u8 category = tomoyo_index2category[index] +
                TOMOYO_MAX_MAC_INDEX;
        struct tomoyo_profile *p;

        if (!tomoyo_policy_loaded)
                return false;
        p = tomoyo_profile(ns, profile);
        if (tomoyo_log_count >= p->pref[TOMOYO_PREF_MAX_AUDIT_LOG])
                return false;
        if (is_granted && matched_acl && matched_acl->cond &&
            matched_acl->cond->grant_log != TOMOYO_GRANTLOG_AUTO)
                return matched_acl->cond->grant_log == TOMOYO_GRANTLOG_YES;
        mode = p->config[index];
        if (mode == TOMOYO_CONFIG_USE_DEFAULT)
                mode = p->config[category];
        if (mode == TOMOYO_CONFIG_USE_DEFAULT)
                mode = p->default_config;
        if (is_granted)
                return mode & TOMOYO_CONFIG_WANT_GRANT_LOG;
        return mode & TOMOYO_CONFIG_WANT_REJECT_LOG;
}

/**
 * tomoyo_write_log2 - Write an audit log.
 *
 * @r:    Pointer to "struct tomoyo_request_info".
 * @len:  Buffer size needed for @fmt and @args.
 * @fmt:  The printf()'s format string.
 * @args: va_list structure for @fmt.
 *
 * Returns nothing.
 */
void tomoyo_write_log2(struct tomoyo_request_info *r, int len, const char *fmt,
                       va_list args)
{
        char *buf;
        struct tomoyo_log *entry;
        bool quota_exceeded = false;

        if (!tomoyo_get_audit(r->domain->ns, r->profile, r->type,
                              r->matched_acl, r->granted))
                goto out;
        buf = tomoyo_init_log(r, len, fmt, args);
        if (!buf)
                goto out;
        entry = kzalloc(sizeof(*entry), GFP_NOFS);
        if (!entry) {
                kfree(buf);
                goto out;
        }
        entry->log = buf;
        len = kmalloc_size_roundup(strlen(buf) + 1);
        /*
         * The entry->size is used for memory quota checks.
         * Don't go beyond strlen(entry->log).
         */
        entry->size = len + kmalloc_size_roundup(sizeof(*entry));
        spin_lock(&tomoyo_log_lock);
        if (tomoyo_memory_quota[TOMOYO_MEMORY_AUDIT] &&
            tomoyo_memory_used[TOMOYO_MEMORY_AUDIT] + entry->size >=
            tomoyo_memory_quota[TOMOYO_MEMORY_AUDIT]) {
                quota_exceeded = true;
        } else {
                tomoyo_memory_used[TOMOYO_MEMORY_AUDIT] += entry->size;
                list_add_tail(&entry->list, &tomoyo_log);
                tomoyo_log_count++;
        }
        spin_unlock(&tomoyo_log_lock);
        if (quota_exceeded) {
                kfree(buf);
                kfree(entry);
                goto out;
        }
        wake_up(&tomoyo_log_wait);
out:
        return;
}

/**
 * tomoyo_write_log - Write an audit log.
 *
 * @r:   Pointer to "struct tomoyo_request_info".
 * @fmt: The printf()'s format string, followed by parameters.
 *
 * Returns nothing.
 */
void tomoyo_write_log(struct tomoyo_request_info *r, const char *fmt, ...)
{
        va_list args;
        int len;

        va_start(args, fmt);
        len = vsnprintf(NULL, 0, fmt, args) + 1;
        va_end(args);
        va_start(args, fmt);
        tomoyo_write_log2(r, len, fmt, args);
        va_end(args);
}

/**
 * tomoyo_read_log - Read an audit log.
 *
 * @head: Pointer to "struct tomoyo_io_buffer".
 *
 * Returns nothing.
 */
void tomoyo_read_log(struct tomoyo_io_buffer *head)
{
        struct tomoyo_log *ptr = NULL;

        if (head->r.w_pos)
                return;
        kfree(head->read_buf);
        head->read_buf = NULL;
        spin_lock(&tomoyo_log_lock);
        if (!list_empty(&tomoyo_log)) {
                ptr = list_entry(tomoyo_log.next, typeof(*ptr), list);
                list_del(&ptr->list);
                tomoyo_log_count--;
                tomoyo_memory_used[TOMOYO_MEMORY_AUDIT] -= ptr->size;
        }
        spin_unlock(&tomoyo_log_lock);
        if (ptr) {
                head->read_buf = ptr->log;
                head->r.w[head->r.w_pos++] = head->read_buf;
                kfree(ptr);
        }
}

/**
 * tomoyo_poll_log - Wait for an audit log.
 *
 * @file: Pointer to "struct file".
 * @wait: Pointer to "poll_table". Maybe NULL.
 *
 * Returns EPOLLIN | EPOLLRDNORM when ready to read an audit log.
 */
__poll_t tomoyo_poll_log(struct file *file, poll_table *wait)
{
        if (tomoyo_log_count)
                return EPOLLIN | EPOLLRDNORM;
        poll_wait(file, &tomoyo_log_wait, wait);
        if (tomoyo_log_count)
                return EPOLLIN | EPOLLRDNORM;
        return 0;
}








































    4 
    4 












    4 
    4 












    4 







    4 



































    4 



















    4 
    4 


















    4 


    4 
    4 











    4 









    4 
    4 






    4 



    4 













    4 






    4 

















    4 











    4 












































































































































































































































































































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
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
// SPDX-License-Identifier: GPL-2.0-or-later
/*
 * Interface to Linux block layer for MTD 'translation layers'.
 *
 * Copyright © 2003-2010 David Woodhouse <dwmw2@infradead.org>
 */

#include <linux/kernel.h>
#include <linux/slab.h>
#include <linux/module.h>
#include <linux/list.h>
#include <linux/fs.h>
#include <linux/mtd/blktrans.h>
#include <linux/mtd/mtd.h>
#include <linux/blkdev.h>
#include <linux/blk-mq.h>
#include <linux/blkpg.h>
#include <linux/spinlock.h>
#include <linux/hdreg.h>
#include <linux/mutex.h>
#include <linux/uaccess.h>

#include "mtdcore.h"

static LIST_HEAD(blktrans_majors);

static void blktrans_dev_release(struct kref *kref)
{
        struct mtd_blktrans_dev *dev =
                container_of(kref, struct mtd_blktrans_dev, ref);

        put_disk(dev->disk);
        blk_mq_free_tag_set(dev->tag_set);
        kfree(dev->tag_set);
        list_del(&dev->list);
        kfree(dev);
}

static void blktrans_dev_put(struct mtd_blktrans_dev *dev)
{
        kref_put(&dev->ref, blktrans_dev_release);
}


static blk_status_t do_blktrans_request(struct mtd_blktrans_ops *tr,
                               struct mtd_blktrans_dev *dev,
                               struct request *req)
{
        struct req_iterator iter;
        struct bio_vec bvec;
        unsigned long block, nsect;
        char *buf;

        block = blk_rq_pos(req) << 9 >> tr->blkshift;
        nsect = blk_rq_cur_bytes(req) >> tr->blkshift;

        switch (req_op(req)) {
        case REQ_OP_FLUSH:
                if (tr->flush(dev))
                        return BLK_STS_IOERR;
                return BLK_STS_OK;
        case REQ_OP_DISCARD:
                if (tr->discard(dev, block, nsect))
                        return BLK_STS_IOERR;
                return BLK_STS_OK;
        case REQ_OP_READ:
                buf = kmap(bio_page(req->bio)) + bio_offset(req->bio);
                for (; nsect > 0; nsect--, block++, buf += tr->blksize) {
                        if (tr->readsect(dev, block, buf)) {
                                kunmap(bio_page(req->bio));
                                return BLK_STS_IOERR;
                        }
                }
                kunmap(bio_page(req->bio));

                rq_for_each_segment(bvec, req, iter)
                        flush_dcache_page(bvec.bv_page);
                return BLK_STS_OK;
        case REQ_OP_WRITE:
                if (!tr->writesect)
                        return BLK_STS_IOERR;

                rq_for_each_segment(bvec, req, iter)
                        flush_dcache_page(bvec.bv_page);

                buf = kmap(bio_page(req->bio)) + bio_offset(req->bio);
                for (; nsect > 0; nsect--, block++, buf += tr->blksize) {
                        if (tr->writesect(dev, block, buf)) {
                                kunmap(bio_page(req->bio));
                                return BLK_STS_IOERR;
                        }
                }
                kunmap(bio_page(req->bio));
                return BLK_STS_OK;
        default:
                return BLK_STS_IOERR;
        }
}

int mtd_blktrans_cease_background(struct mtd_blktrans_dev *dev)
{
        return dev->bg_stop;
}
EXPORT_SYMBOL_GPL(mtd_blktrans_cease_background);

static struct request *mtd_next_request(struct mtd_blktrans_dev *dev)
{
        struct request *rq;

        rq = list_first_entry_or_null(&dev->rq_list, struct request, queuelist);
        if (rq) {
                list_del_init(&rq->queuelist);
                blk_mq_start_request(rq);
                return rq;
        }

        return NULL;
}

static void mtd_blktrans_work(struct mtd_blktrans_dev *dev)
        __releases(&dev->queue_lock)
        __acquires(&dev->queue_lock)
{
        struct mtd_blktrans_ops *tr = dev->tr;
        struct request *req = NULL;
        int background_done = 0;

        while (1) {
                blk_status_t res;

                dev->bg_stop = false;
                if (!req && !(req = mtd_next_request(dev))) {
                        if (tr->background && !background_done) {
                                spin_unlock_irq(&dev->queue_lock);
                                mutex_lock(&dev->lock);
                                tr->background(dev);
                                mutex_unlock(&dev->lock);
                                spin_lock_irq(&dev->queue_lock);
                                /*
                                 * Do background processing just once per idle
                                 * period.
                                 */
                                background_done = !dev->bg_stop;
                                continue;
                        }
                        break;
                }

                spin_unlock_irq(&dev->queue_lock);

                mutex_lock(&dev->lock);
                res = do_blktrans_request(dev->tr, dev, req);
                mutex_unlock(&dev->lock);

                if (!blk_update_request(req, res, blk_rq_cur_bytes(req))) {
                        __blk_mq_end_request(req, res);
                        req = NULL;
                }

                background_done = 0;
                cond_resched();
                spin_lock_irq(&dev->queue_lock);
        }
}

static blk_status_t mtd_queue_rq(struct blk_mq_hw_ctx *hctx,
                                 const struct blk_mq_queue_data *bd)
{
        struct mtd_blktrans_dev *dev;

        dev = hctx->queue->queuedata;
        if (!dev) {
                blk_mq_start_request(bd->rq);
                return BLK_STS_IOERR;
        }

        spin_lock_irq(&dev->queue_lock);
        list_add_tail(&bd->rq->queuelist, &dev->rq_list);
        mtd_blktrans_work(dev);
        spin_unlock_irq(&dev->queue_lock);

        return BLK_STS_OK;
}

static int blktrans_open(struct gendisk *disk, blk_mode_t mode)
{
        struct mtd_blktrans_dev *dev = disk->private_data;
        int ret = 0;

        kref_get(&dev->ref);

        mutex_lock(&dev->lock);

        if (dev->open)
                goto unlock;

        __module_get(dev->tr->owner);

        if (!dev->mtd)
                goto unlock;

        if (dev->tr->open) {
                ret = dev->tr->open(dev);
                if (ret)
                        goto error_put;
        }

        ret = __get_mtd_device(dev->mtd);
        if (ret)
                goto error_release;
        dev->writable = mode & BLK_OPEN_WRITE;

unlock:
        dev->open++;
        mutex_unlock(&dev->lock);
        return ret;

error_release:
        if (dev->tr->release)
                dev->tr->release(dev);
error_put:
        module_put(dev->tr->owner);
        mutex_unlock(&dev->lock);
        blktrans_dev_put(dev);
        return ret;
}

static void blktrans_release(struct gendisk *disk)
{
        struct mtd_blktrans_dev *dev = disk->private_data;

        mutex_lock(&dev->lock);

        if (--dev->open)
                goto unlock;

        module_put(dev->tr->owner);

        if (dev->mtd) {
                if (dev->tr->release)
                        dev->tr->release(dev);
                __put_mtd_device(dev->mtd);
        }
unlock:
        mutex_unlock(&dev->lock);
        blktrans_dev_put(dev);
}

static int blktrans_getgeo(struct block_device *bdev, struct hd_geometry *geo)
{
        struct mtd_blktrans_dev *dev = bdev->bd_disk->private_data;
        int ret = -ENXIO;

        mutex_lock(&dev->lock);

        if (!dev->mtd)
                goto unlock;

        ret = dev->tr->getgeo ? dev->tr->getgeo(dev, geo) : -ENOTTY;
unlock:
        mutex_unlock(&dev->lock);
        return ret;
}

static const struct block_device_operations mtd_block_ops = {
        .owner                = THIS_MODULE,
        .open                = blktrans_open,
        .release        = blktrans_release,
        .getgeo                = blktrans_getgeo,
};

static const struct blk_mq_ops mtd_mq_ops = {
        .queue_rq        = mtd_queue_rq,
};

int add_mtd_blktrans_dev(struct mtd_blktrans_dev *new)
{
        struct mtd_blktrans_ops *tr = new->tr;
        struct mtd_blktrans_dev *d;
        struct queue_limits lim = { };
        int last_devnum = -1;
        struct gendisk *gd;
        int ret;

        lockdep_assert_held(&mtd_table_mutex);

        list_for_each_entry(d, &tr->devs, list) {
                if (new->devnum == -1) {
                        /* Use first free number */
                        if (d->devnum != last_devnum+1) {
                                /* Found a free devnum. Plug it in here */
                                new->devnum = last_devnum+1;
                                list_add_tail(&new->list, &d->list);
                                goto added;
                        }
                } else if (d->devnum == new->devnum) {
                        /* Required number taken */
                        return -EBUSY;
                } else if (d->devnum > new->devnum) {
                        /* Required number was free */
                        list_add_tail(&new->list, &d->list);
                        goto added;
                }
                last_devnum = d->devnum;
        }

        ret = -EBUSY;
        if (new->devnum == -1)
                new->devnum = last_devnum+1;

        /* Check that the device and any partitions will get valid
         * minor numbers and that the disk naming code below can cope
         * with this number. */
        if (new->devnum > (MINORMASK >> tr->part_bits) ||
            (tr->part_bits && new->devnum >= 27 * 26))
                return ret;

        list_add_tail(&new->list, &tr->devs);
 added:

        mutex_init(&new->lock);
        kref_init(&new->ref);
        if (!tr->writesect)
                new->readonly = 1;

        ret = -ENOMEM;
        new->tag_set = kzalloc(sizeof(*new->tag_set), GFP_KERNEL);
        if (!new->tag_set)
                goto out_list_del;

        ret = blk_mq_alloc_sq_tag_set(new->tag_set, &mtd_mq_ops, 2,
                        BLK_MQ_F_SHOULD_MERGE | BLK_MQ_F_BLOCKING);
        if (ret)
                goto out_kfree_tag_set;
        
        lim.logical_block_size = tr->blksize;
        if (tr->discard)
                lim.max_hw_discard_sectors = UINT_MAX;
        if (tr->flush)
                lim.features |= BLK_FEAT_WRITE_CACHE;

        /* Create gendisk */
        gd = blk_mq_alloc_disk(new->tag_set, &lim, new);
        if (IS_ERR(gd)) {
                ret = PTR_ERR(gd);
                goto out_free_tag_set;
        }

        new->disk = gd;
        new->rq = new->disk->queue;
        gd->private_data = new;
        gd->major = tr->major;
        gd->first_minor = (new->devnum) << tr->part_bits;
        gd->minors = 1 << tr->part_bits;
        gd->fops = &mtd_block_ops;

        if (tr->part_bits) {
                if (new->devnum < 26)
                        snprintf(gd->disk_name, sizeof(gd->disk_name),
                                 "%s%c", tr->name, 'a' + new->devnum);
                else
                        snprintf(gd->disk_name, sizeof(gd->disk_name),
                                 "%s%c%c", tr->name,
                                 'a' - 1 + new->devnum / 26,
                                 'a' + new->devnum % 26);
        } else {
                snprintf(gd->disk_name, sizeof(gd->disk_name),
                         "%s%d", tr->name, new->devnum);
                gd->flags |= GENHD_FL_NO_PART;
        }

        set_capacity(gd, ((u64)new->size * tr->blksize) >> 9);

        /* Create the request queue */
        spin_lock_init(&new->queue_lock);
        INIT_LIST_HEAD(&new->rq_list);
        gd->queue = new->rq;

        if (new->readonly)
                set_disk_ro(gd, 1);

        ret = device_add_disk(&new->mtd->dev, gd, NULL);
        if (ret)
                goto out_cleanup_disk;

        if (new->disk_attributes) {
                ret = sysfs_create_group(&disk_to_dev(gd)->kobj,
                                        new->disk_attributes);
                WARN_ON(ret);
        }
        return 0;

out_cleanup_disk:
        put_disk(new->disk);
out_free_tag_set:
        blk_mq_free_tag_set(new->tag_set);
out_kfree_tag_set:
        kfree(new->tag_set);
out_list_del:
        list_del(&new->list);
        return ret;
}

int del_mtd_blktrans_dev(struct mtd_blktrans_dev *old)
{
        unsigned long flags;

        lockdep_assert_held(&mtd_table_mutex);

        if (old->disk_attributes)
                sysfs_remove_group(&disk_to_dev(old->disk)->kobj,
                                                old->disk_attributes);

        /* Stop new requests to arrive */
        del_gendisk(old->disk);

        /* Kill current requests */
        spin_lock_irqsave(&old->queue_lock, flags);
        old->rq->queuedata = NULL;
        spin_unlock_irqrestore(&old->queue_lock, flags);

        /* freeze+quiesce queue to ensure all requests are flushed */
        blk_mq_freeze_queue(old->rq);
        blk_mq_quiesce_queue(old->rq);
        blk_mq_unquiesce_queue(old->rq);
        blk_mq_unfreeze_queue(old->rq);

        /* If the device is currently open, tell trans driver to close it,
                then put mtd device, and don't touch it again */
        mutex_lock(&old->lock);
        if (old->open) {
                if (old->tr->release)
                        old->tr->release(old);
                __put_mtd_device(old->mtd);
        }

        old->mtd = NULL;

        mutex_unlock(&old->lock);
        blktrans_dev_put(old);
        return 0;
}

static void blktrans_notify_remove(struct mtd_info *mtd)
{
        struct mtd_blktrans_ops *tr;
        struct mtd_blktrans_dev *dev, *next;

        list_for_each_entry(tr, &blktrans_majors, list)
                list_for_each_entry_safe(dev, next, &tr->devs, list)
                        if (dev->mtd == mtd)
                                tr->remove_dev(dev);
}

static void blktrans_notify_add(struct mtd_info *mtd)
{
        struct mtd_blktrans_ops *tr;

        if (mtd->type == MTD_ABSENT || mtd->type == MTD_UBIVOLUME)
                return;

        list_for_each_entry(tr, &blktrans_majors, list)
                tr->add_mtd(tr, mtd);
}

static struct mtd_notifier blktrans_notifier = {
        .add = blktrans_notify_add,
        .remove = blktrans_notify_remove,
};

int register_mtd_blktrans(struct mtd_blktrans_ops *tr)
{
        struct mtd_info *mtd;
        int ret;

        /* Register the notifier if/when the first device type is
           registered, to prevent the link/init ordering from fucking
           us over. */
        if (!blktrans_notifier.list.next)
                register_mtd_user(&blktrans_notifier);

        ret = register_blkdev(tr->major, tr->name);
        if (ret < 0) {
                printk(KERN_WARNING "Unable to register %s block device on major %d: %d\n",
                       tr->name, tr->major, ret);
                return ret;
        }

        if (ret)
                tr->major = ret;

        tr->blkshift = ffs(tr->blksize) - 1;

        INIT_LIST_HEAD(&tr->devs);

        mutex_lock(&mtd_table_mutex);
        list_add(&tr->list, &blktrans_majors);
        mtd_for_each_device(mtd)
                if (mtd->type != MTD_ABSENT && mtd->type != MTD_UBIVOLUME)
                        tr->add_mtd(tr, mtd);
        mutex_unlock(&mtd_table_mutex);
        return 0;
}

int deregister_mtd_blktrans(struct mtd_blktrans_ops *tr)
{
        struct mtd_blktrans_dev *dev, *next;

        mutex_lock(&mtd_table_mutex);

        /* Remove it from the list of active majors */
        list_del(&tr->list);

        list_for_each_entry_safe(dev, next, &tr->devs, list)
                tr->remove_dev(dev);

        mutex_unlock(&mtd_table_mutex);
        unregister_blkdev(tr->major, tr->name);

        BUG_ON(!list_empty(&tr->devs));
        return 0;
}

static void __exit mtd_blktrans_exit(void)
{
        /* No race here -- if someone's currently in register_mtd_blktrans
           we're screwed anyway. */
        if (blktrans_notifier.list.next)
                unregister_mtd_user(&blktrans_notifier);
}

module_exit(mtd_blktrans_exit);

EXPORT_SYMBOL_GPL(register_mtd_blktrans);
EXPORT_SYMBOL_GPL(deregister_mtd_blktrans);
EXPORT_SYMBOL_GPL(add_mtd_blktrans_dev);
EXPORT_SYMBOL_GPL(del_mtd_blktrans_dev);

MODULE_AUTHOR("David Woodhouse <dwmw2@infradead.org>");
MODULE_LICENSE("GPL");
MODULE_DESCRIPTION("Common interface to block layer for MTD 'translation layers'");

























































































































   23 
















    1 




    2 


    1 










   17 








    2 







    2 



    2 

    4 







    1 







    3 
    3 




    1 



    1 







    1 







   12 






    1 




    2 
















   10 








   10 


   10 

   10 












    3 




    2 





    3 












    3 




    2 




    1 



    3 








    3 


    3 




















   10 









   10 





    3 





    2 


    3 





    2 















    3 


    2 


    3 


    2 




























   27 


   27 






























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
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
// SPDX-License-Identifier: GPL-2.0-or-later
/*
 * Copyright (c) 2014 Jiri Pirko <jiri@resnulli.us>
 */

#include <linux/module.h>
#include <linux/init.h>
#include <linux/kernel.h>
#include <linux/skbuff.h>
#include <linux/rtnetlink.h>
#include <linux/if_vlan.h>
#include <net/netlink.h>
#include <net/pkt_sched.h>
#include <net/pkt_cls.h>
#include <net/tc_wrapper.h>

#include <linux/tc_act/tc_vlan.h>
#include <net/tc_act/tc_vlan.h>

static struct tc_action_ops act_vlan_ops;

TC_INDIRECT_SCOPE int tcf_vlan_act(struct sk_buff *skb,
                                   const struct tc_action *a,
                                   struct tcf_result *res)
{
        struct tcf_vlan *v = to_vlan(a);
        struct tcf_vlan_params *p;
        int action;
        int err;
        u16 tci;

        tcf_lastuse_update(&v->tcf_tm);
        tcf_action_update_bstats(&v->common, skb);

        /* Ensure 'data' points at mac_header prior calling vlan manipulating
         * functions.
         */
        if (skb_at_tc_ingress(skb))
                skb_push_rcsum(skb, skb->mac_len);

        action = READ_ONCE(v->tcf_action);

        p = rcu_dereference_bh(v->vlan_p);

        switch (p->tcfv_action) {
        case TCA_VLAN_ACT_POP:
                err = skb_vlan_pop(skb);
                if (err)
                        goto drop;
                break;
        case TCA_VLAN_ACT_PUSH:
                err = skb_vlan_push(skb, p->tcfv_push_proto, p->tcfv_push_vid |
                                    (p->tcfv_push_prio << VLAN_PRIO_SHIFT));
                if (err)
                        goto drop;
                break;
        case TCA_VLAN_ACT_MODIFY:
                /* No-op if no vlan tag (either hw-accel or in-payload) */
                if (!skb_vlan_tagged(skb))
                        goto out;
                /* extract existing tag (and guarantee no hw-accel tag) */
                if (skb_vlan_tag_present(skb)) {
                        tci = skb_vlan_tag_get(skb);
                        __vlan_hwaccel_clear_tag(skb);
                } else {
                        /* in-payload vlan tag, pop it */
                        err = __skb_vlan_pop(skb, &tci);
                        if (err)
                                goto drop;
                }
                /* replace the vid */
                tci = (tci & ~VLAN_VID_MASK) | p->tcfv_push_vid;
                /* replace prio bits, if tcfv_push_prio specified */
                if (p->tcfv_push_prio_exists) {
                        tci &= ~VLAN_PRIO_MASK;
                        tci |= p->tcfv_push_prio << VLAN_PRIO_SHIFT;
                }
                /* put updated tci as hwaccel tag */
                __vlan_hwaccel_put_tag(skb, p->tcfv_push_proto, tci);
                break;
        case TCA_VLAN_ACT_POP_ETH:
                err = skb_eth_pop(skb);
                if (err)
                        goto drop;
                break;
        case TCA_VLAN_ACT_PUSH_ETH:
                err = skb_eth_push(skb, p->tcfv_push_dst, p->tcfv_push_src);
                if (err)
                        goto drop;
                break;
        default:
                BUG();
        }

out:
        if (skb_at_tc_ingress(skb))
                skb_pull_rcsum(skb, skb->mac_len);

        skb_reset_mac_len(skb);
        return action;

drop:
        tcf_action_inc_drop_qstats(&v->common);
        return TC_ACT_SHOT;
}

static const struct nla_policy vlan_policy[TCA_VLAN_MAX + 1] = {
        [TCA_VLAN_UNSPEC]                = { .strict_start_type = TCA_VLAN_PUSH_ETH_DST },
        [TCA_VLAN_PARMS]                = { .len = sizeof(struct tc_vlan) },
        [TCA_VLAN_PUSH_VLAN_ID]                = { .type = NLA_U16 },
        [TCA_VLAN_PUSH_VLAN_PROTOCOL]        = { .type = NLA_U16 },
        [TCA_VLAN_PUSH_VLAN_PRIORITY]        = { .type = NLA_U8 },
        [TCA_VLAN_PUSH_ETH_DST]                = NLA_POLICY_ETH_ADDR,
        [TCA_VLAN_PUSH_ETH_SRC]                = NLA_POLICY_ETH_ADDR,
};

static int tcf_vlan_init(struct net *net, struct nlattr *nla,
                         struct nlattr *est, struct tc_action **a,
                         struct tcf_proto *tp, u32 flags,
                         struct netlink_ext_ack *extack)
{
        struct tc_action_net *tn = net_generic(net, act_vlan_ops.net_id);
        bool bind = flags & TCA_ACT_FLAGS_BIND;
        struct nlattr *tb[TCA_VLAN_MAX + 1];
        struct tcf_chain *goto_ch = NULL;
        bool push_prio_exists = false;
        struct tcf_vlan_params *p;
        struct tc_vlan *parm;
        struct tcf_vlan *v;
        int action;
        u16 push_vid = 0;
        __be16 push_proto = 0;
        u8 push_prio = 0;
        bool exists = false;
        int ret = 0, err;
        u32 index;

        if (!nla)
                return -EINVAL;

        err = nla_parse_nested_deprecated(tb, TCA_VLAN_MAX, nla, vlan_policy,
                                          NULL);
        if (err < 0)
                return err;

        if (!tb[TCA_VLAN_PARMS])
                return -EINVAL;
        parm = nla_data(tb[TCA_VLAN_PARMS]);
        index = parm->index;
        err = tcf_idr_check_alloc(tn, &index, a, bind);
        if (err < 0)
                return err;
        exists = err;
        if (exists && bind)
                return ACT_P_BOUND;

        switch (parm->v_action) {
        case TCA_VLAN_ACT_POP:
                break;
        case TCA_VLAN_ACT_PUSH:
        case TCA_VLAN_ACT_MODIFY:
                if (!tb[TCA_VLAN_PUSH_VLAN_ID]) {
                        if (exists)
                                tcf_idr_release(*a, bind);
                        else
                                tcf_idr_cleanup(tn, index);
                        return -EINVAL;
                }
                push_vid = nla_get_u16(tb[TCA_VLAN_PUSH_VLAN_ID]);
                if (push_vid >= VLAN_VID_MASK) {
                        if (exists)
                                tcf_idr_release(*a, bind);
                        else
                                tcf_idr_cleanup(tn, index);
                        return -ERANGE;
                }

                if (tb[TCA_VLAN_PUSH_VLAN_PROTOCOL]) {
                        push_proto = nla_get_be16(tb[TCA_VLAN_PUSH_VLAN_PROTOCOL]);
                        switch (push_proto) {
                        case htons(ETH_P_8021Q):
                        case htons(ETH_P_8021AD):
                                break;
                        default:
                                if (exists)
                                        tcf_idr_release(*a, bind);
                                else
                                        tcf_idr_cleanup(tn, index);
                                return -EPROTONOSUPPORT;
                        }
                } else {
                        push_proto = htons(ETH_P_8021Q);
                }

                push_prio_exists = !!tb[TCA_VLAN_PUSH_VLAN_PRIORITY];
                if (push_prio_exists)
                        push_prio = nla_get_u8(tb[TCA_VLAN_PUSH_VLAN_PRIORITY]);
                break;
        case TCA_VLAN_ACT_POP_ETH:
                break;
        case TCA_VLAN_ACT_PUSH_ETH:
                if (!tb[TCA_VLAN_PUSH_ETH_DST] || !tb[TCA_VLAN_PUSH_ETH_SRC]) {
                        if (exists)
                                tcf_idr_release(*a, bind);
                        else
                                tcf_idr_cleanup(tn, index);
                        return -EINVAL;
                }
                break;
        default:
                if (exists)
                        tcf_idr_release(*a, bind);
                else
                        tcf_idr_cleanup(tn, index);
                return -EINVAL;
        }
        action = parm->v_action;

        if (!exists) {
                ret = tcf_idr_create_from_flags(tn, index, est, a,
                                                &act_vlan_ops, bind, flags);
                if (ret) {
                        tcf_idr_cleanup(tn, index);
                        return ret;
                }

                ret = ACT_P_CREATED;
        } else if (!(flags & TCA_ACT_FLAGS_REPLACE)) {
                tcf_idr_release(*a, bind);
                return -EEXIST;
        }

        err = tcf_action_check_ctrlact(parm->action, tp, &goto_ch, extack);
        if (err < 0)
                goto release_idr;

        v = to_vlan(*a);

        p = kzalloc(sizeof(*p), GFP_KERNEL);
        if (!p) {
                err = -ENOMEM;
                goto put_chain;
        }

        p->tcfv_action = action;
        p->tcfv_push_vid = push_vid;
        p->tcfv_push_prio = push_prio;
        p->tcfv_push_prio_exists = push_prio_exists || action == TCA_VLAN_ACT_PUSH;
        p->tcfv_push_proto = push_proto;

        if (action == TCA_VLAN_ACT_PUSH_ETH) {
                nla_memcpy(&p->tcfv_push_dst, tb[TCA_VLAN_PUSH_ETH_DST],
                           ETH_ALEN);
                nla_memcpy(&p->tcfv_push_src, tb[TCA_VLAN_PUSH_ETH_SRC],
                           ETH_ALEN);
        }

        spin_lock_bh(&v->tcf_lock);
        goto_ch = tcf_action_set_ctrlact(*a, parm->action, goto_ch);
        p = rcu_replace_pointer(v->vlan_p, p, lockdep_is_held(&v->tcf_lock));
        spin_unlock_bh(&v->tcf_lock);

        if (goto_ch)
                tcf_chain_put_by_act(goto_ch);
        if (p)
                kfree_rcu(p, rcu);

        return ret;
put_chain:
        if (goto_ch)
                tcf_chain_put_by_act(goto_ch);
release_idr:
        tcf_idr_release(*a, bind);
        return err;
}

static void tcf_vlan_cleanup(struct tc_action *a)
{
        struct tcf_vlan *v = to_vlan(a);
        struct tcf_vlan_params *p;

        p = rcu_dereference_protected(v->vlan_p, 1);
        if (p)
                kfree_rcu(p, rcu);
}

static int tcf_vlan_dump(struct sk_buff *skb, struct tc_action *a,
                         int bind, int ref)
{
        unsigned char *b = skb_tail_pointer(skb);
        struct tcf_vlan *v = to_vlan(a);
        struct tcf_vlan_params *p;
        struct tc_vlan opt = {
                .index    = v->tcf_index,
                .refcnt   = refcount_read(&v->tcf_refcnt) - ref,
                .bindcnt  = atomic_read(&v->tcf_bindcnt) - bind,
        };
        struct tcf_t t;

        spin_lock_bh(&v->tcf_lock);
        opt.action = v->tcf_action;
        p = rcu_dereference_protected(v->vlan_p, lockdep_is_held(&v->tcf_lock));
        opt.v_action = p->tcfv_action;
        if (nla_put(skb, TCA_VLAN_PARMS, sizeof(opt), &opt))
                goto nla_put_failure;

        if ((p->tcfv_action == TCA_VLAN_ACT_PUSH ||
             p->tcfv_action == TCA_VLAN_ACT_MODIFY) &&
            (nla_put_u16(skb, TCA_VLAN_PUSH_VLAN_ID, p->tcfv_push_vid) ||
             nla_put_be16(skb, TCA_VLAN_PUSH_VLAN_PROTOCOL,
                          p->tcfv_push_proto) ||
             (p->tcfv_push_prio_exists &&
              nla_put_u8(skb, TCA_VLAN_PUSH_VLAN_PRIORITY, p->tcfv_push_prio))))
                goto nla_put_failure;

        if (p->tcfv_action == TCA_VLAN_ACT_PUSH_ETH) {
                if (nla_put(skb, TCA_VLAN_PUSH_ETH_DST, ETH_ALEN,
                            p->tcfv_push_dst))
                        goto nla_put_failure;
                if (nla_put(skb, TCA_VLAN_PUSH_ETH_SRC, ETH_ALEN,
                            p->tcfv_push_src))
                        goto nla_put_failure;
        }

        tcf_tm_dump(&t, &v->tcf_tm);
        if (nla_put_64bit(skb, TCA_VLAN_TM, sizeof(t), &t, TCA_VLAN_PAD))
                goto nla_put_failure;
        spin_unlock_bh(&v->tcf_lock);

        return skb->len;

nla_put_failure:
        spin_unlock_bh(&v->tcf_lock);
        nlmsg_trim(skb, b);
        return -1;
}

static void tcf_vlan_stats_update(struct tc_action *a, u64 bytes, u64 packets,
                                  u64 drops, u64 lastuse, bool hw)
{
        struct tcf_vlan *v = to_vlan(a);
        struct tcf_t *tm = &v->tcf_tm;

        tcf_action_update_stats(a, bytes, packets, drops, hw);
        tm->lastuse = max_t(u64, tm->lastuse, lastuse);
}

static size_t tcf_vlan_get_fill_size(const struct tc_action *act)
{
        return nla_total_size(sizeof(struct tc_vlan))
                + nla_total_size(sizeof(u16)) /* TCA_VLAN_PUSH_VLAN_ID */
                + nla_total_size(sizeof(u16)) /* TCA_VLAN_PUSH_VLAN_PROTOCOL */
                + nla_total_size(sizeof(u8)); /* TCA_VLAN_PUSH_VLAN_PRIORITY */
}

static int tcf_vlan_offload_act_setup(struct tc_action *act, void *entry_data,
                                      u32 *index_inc, bool bind,
                                      struct netlink_ext_ack *extack)
{
        if (bind) {
                struct flow_action_entry *entry = entry_data;

                switch (tcf_vlan_action(act)) {
                case TCA_VLAN_ACT_PUSH:
                        entry->id = FLOW_ACTION_VLAN_PUSH;
                        entry->vlan.vid = tcf_vlan_push_vid(act);
                        entry->vlan.proto = tcf_vlan_push_proto(act);
                        entry->vlan.prio = tcf_vlan_push_prio(act);
                        break;
                case TCA_VLAN_ACT_POP:
                        entry->id = FLOW_ACTION_VLAN_POP;
                        break;
                case TCA_VLAN_ACT_MODIFY:
                        entry->id = FLOW_ACTION_VLAN_MANGLE;
                        entry->vlan.vid = tcf_vlan_push_vid(act);
                        entry->vlan.proto = tcf_vlan_push_proto(act);
                        entry->vlan.prio = tcf_vlan_push_prio(act);
                        break;
                case TCA_VLAN_ACT_POP_ETH:
                        entry->id = FLOW_ACTION_VLAN_POP_ETH;
                        break;
                case TCA_VLAN_ACT_PUSH_ETH:
                        entry->id = FLOW_ACTION_VLAN_PUSH_ETH;
                        tcf_vlan_push_eth(entry->vlan_push_eth.src, entry->vlan_push_eth.dst, act);
                        break;
                default:
                        NL_SET_ERR_MSG_MOD(extack, "Unsupported vlan action mode offload");
                        return -EOPNOTSUPP;
                }
                *index_inc = 1;
        } else {
                struct flow_offload_action *fl_action = entry_data;

                switch (tcf_vlan_action(act)) {
                case TCA_VLAN_ACT_PUSH:
                        fl_action->id = FLOW_ACTION_VLAN_PUSH;
                        break;
                case TCA_VLAN_ACT_POP:
                        fl_action->id = FLOW_ACTION_VLAN_POP;
                        break;
                case TCA_VLAN_ACT_MODIFY:
                        fl_action->id = FLOW_ACTION_VLAN_MANGLE;
                        break;
                case TCA_VLAN_ACT_POP_ETH:
                        fl_action->id = FLOW_ACTION_VLAN_POP_ETH;
                        break;
                case TCA_VLAN_ACT_PUSH_ETH:
                        fl_action->id = FLOW_ACTION_VLAN_PUSH_ETH;
                        break;
                default:
                        return -EOPNOTSUPP;
                }
        }

        return 0;
}

static struct tc_action_ops act_vlan_ops = {
        .kind                =        "vlan",
        .id                =        TCA_ID_VLAN,
        .owner                =        THIS_MODULE,
        .act                =        tcf_vlan_act,
        .dump                =        tcf_vlan_dump,
        .init                =        tcf_vlan_init,
        .cleanup        =        tcf_vlan_cleanup,
        .stats_update        =        tcf_vlan_stats_update,
        .get_fill_size        =        tcf_vlan_get_fill_size,
        .offload_act_setup =        tcf_vlan_offload_act_setup,
        .size                =        sizeof(struct tcf_vlan),
};
MODULE_ALIAS_NET_ACT("vlan");

static __net_init int vlan_init_net(struct net *net)
{
        struct tc_action_net *tn = net_generic(net, act_vlan_ops.net_id);

        return tc_action_net_init(net, tn, &act_vlan_ops);
}

static void __net_exit vlan_exit_net(struct list_head *net_list)
{
        tc_action_net_exit(net_list, act_vlan_ops.net_id);
}

static struct pernet_operations vlan_net_ops = {
        .init = vlan_init_net,
        .exit_batch = vlan_exit_net,
        .id   = &act_vlan_ops.net_id,
        .size = sizeof(struct tc_action_net),
};

static int __init vlan_init_module(void)
{
        return tcf_register_action(&act_vlan_ops, &vlan_net_ops);
}

static void __exit vlan_cleanup_module(void)
{
        tcf_unregister_action(&act_vlan_ops, &vlan_net_ops);
}

module_init(vlan_init_module);
module_exit(vlan_cleanup_module);

MODULE_AUTHOR("Jiri Pirko <jiri@resnulli.us>");
MODULE_DESCRIPTION("vlan manipulation actions");
MODULE_LICENSE("GPL v2");












































   10 









   41 










    6 





    1 


    1 



    4 
    4 



    3 
    1 



    3 
    2 



    3 




    2 

















    6 















   19 

    1 


























    6 


    6 

















   24 





   24 










   10 


   20 


   15 

































































































   70 




    1 


   28 

   43 





   66 




   65 




    6 





   61 

















   24 

   43 



















   13 










   41 














   41 


























   40 






    3 










   41 








   41 

























    6 

   12 




















    7 



   55 













    7 

    7 


   55 















   21 










































   28 
















   13 

   13 
   13 
   13 
   13 
   13 



















    1 


   13 

    8 


    6 

    6 


    7 

    1 
   13 


    8 
    6 




   13 



    8 
    6 






















































   61 

   61 









   43 




   18 































   12 


















    1 

    6 
















   61 






   47 
   13 


   28 

   21 






   18 

   43 







   61 













   41 



    4 
   37 












   52 









   52 


   52 







   70 






























   70 

    3 


   61 


   61 








   21 
   41 

   61 

















   15 




   52 




   15 






   21 


   20 


   21 



















   12 



















   45 






   14 





   12 


    6 


   21 











   21 
    3 
   18 



    2 










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
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
// SPDX-License-Identifier: GPL-2.0
#include <linux/fanotify.h>
#include <linux/fsnotify_backend.h>
#include <linux/init.h>
#include <linux/jiffies.h>
#include <linux/kernel.h> /* UINT_MAX */
#include <linux/mount.h>
#include <linux/sched.h>
#include <linux/sched/user.h>
#include <linux/sched/signal.h>
#include <linux/types.h>
#include <linux/wait.h>
#include <linux/audit.h>
#include <linux/sched/mm.h>
#include <linux/statfs.h>
#include <linux/stringhash.h>

#include "fanotify.h"

static bool fanotify_path_equal(const struct path *p1, const struct path *p2)
{
        return p1->mnt == p2->mnt && p1->dentry == p2->dentry;
}

static unsigned int fanotify_hash_path(const struct path *path)
{
        return hash_ptr(path->dentry, FANOTIFY_EVENT_HASH_BITS) ^
                hash_ptr(path->mnt, FANOTIFY_EVENT_HASH_BITS);
}

static unsigned int fanotify_hash_fsid(__kernel_fsid_t *fsid)
{
        return hash_32(fsid->val[0], FANOTIFY_EVENT_HASH_BITS) ^
                hash_32(fsid->val[1], FANOTIFY_EVENT_HASH_BITS);
}

static bool fanotify_fh_equal(struct fanotify_fh *fh1,
                              struct fanotify_fh *fh2)
{
        if (fh1->type != fh2->type || fh1->len != fh2->len)
                return false;

        return !fh1->len ||
                !memcmp(fanotify_fh_buf(fh1), fanotify_fh_buf(fh2), fh1->len);
}

static unsigned int fanotify_hash_fh(struct fanotify_fh *fh)
{
        long salt = (long)fh->type | (long)fh->len << 8;

        /*
         * full_name_hash() works long by long, so it handles fh buf optimally.
         */
        return full_name_hash((void *)salt, fanotify_fh_buf(fh), fh->len);
}

static bool fanotify_fid_event_equal(struct fanotify_fid_event *ffe1,
                                     struct fanotify_fid_event *ffe2)
{
        /* Do not merge fid events without object fh */
        if (!ffe1->object_fh.len)
                return false;

        return fanotify_fsid_equal(&ffe1->fsid, &ffe2->fsid) &&
                fanotify_fh_equal(&ffe1->object_fh, &ffe2->object_fh);
}

static bool fanotify_info_equal(struct fanotify_info *info1,
                                struct fanotify_info *info2)
{
        if (info1->dir_fh_totlen != info2->dir_fh_totlen ||
            info1->dir2_fh_totlen != info2->dir2_fh_totlen ||
            info1->file_fh_totlen != info2->file_fh_totlen ||
            info1->name_len != info2->name_len ||
            info1->name2_len != info2->name2_len)
                return false;

        if (info1->dir_fh_totlen &&
            !fanotify_fh_equal(fanotify_info_dir_fh(info1),
                               fanotify_info_dir_fh(info2)))
                return false;

        if (info1->dir2_fh_totlen &&
            !fanotify_fh_equal(fanotify_info_dir2_fh(info1),
                               fanotify_info_dir2_fh(info2)))
                return false;

        if (info1->file_fh_totlen &&
            !fanotify_fh_equal(fanotify_info_file_fh(info1),
                               fanotify_info_file_fh(info2)))
                return false;

        if (info1->name_len &&
            memcmp(fanotify_info_name(info1), fanotify_info_name(info2),
                   info1->name_len))
                return false;

        return !info1->name2_len ||
                !memcmp(fanotify_info_name2(info1), fanotify_info_name2(info2),
                        info1->name2_len);
}

static bool fanotify_name_event_equal(struct fanotify_name_event *fne1,
                                      struct fanotify_name_event *fne2)
{
        struct fanotify_info *info1 = &fne1->info;
        struct fanotify_info *info2 = &fne2->info;

        /* Do not merge name events without dir fh */
        if (!info1->dir_fh_totlen)
                return false;

        if (!fanotify_fsid_equal(&fne1->fsid, &fne2->fsid))
                return false;

        return fanotify_info_equal(info1, info2);
}

static bool fanotify_error_event_equal(struct fanotify_error_event *fee1,
                                       struct fanotify_error_event *fee2)
{
        /* Error events against the same file system are always merged. */
        if (!fanotify_fsid_equal(&fee1->fsid, &fee2->fsid))
                return false;

        return true;
}

static bool fanotify_should_merge(struct fanotify_event *old,
                                  struct fanotify_event *new)
{
        pr_debug("%s: old=%p new=%p\n", __func__, old, new);

        if (old->hash != new->hash ||
            old->type != new->type || old->pid != new->pid)
                return false;

        /*
         * We want to merge many dirent events in the same dir (i.e.
         * creates/unlinks/renames), but we do not want to merge dirent
         * events referring to subdirs with dirent events referring to
         * non subdirs, otherwise, user won't be able to tell from a
         * mask FAN_CREATE|FAN_DELETE|FAN_ONDIR if it describes mkdir+
         * unlink pair or rmdir+create pair of events.
         */
        if ((old->mask & FS_ISDIR) != (new->mask & FS_ISDIR))
                return false;

        /*
         * FAN_RENAME event is reported with special info record types,
         * so we cannot merge it with other events.
         */
        if ((old->mask & FAN_RENAME) != (new->mask & FAN_RENAME))
                return false;

        switch (old->type) {
        case FANOTIFY_EVENT_TYPE_PATH:
                return fanotify_path_equal(fanotify_event_path(old),
                                           fanotify_event_path(new));
        case FANOTIFY_EVENT_TYPE_FID:
                return fanotify_fid_event_equal(FANOTIFY_FE(old),
                                                FANOTIFY_FE(new));
        case FANOTIFY_EVENT_TYPE_FID_NAME:
                return fanotify_name_event_equal(FANOTIFY_NE(old),
                                                 FANOTIFY_NE(new));
        case FANOTIFY_EVENT_TYPE_FS_ERROR:
                return fanotify_error_event_equal(FANOTIFY_EE(old),
                                                  FANOTIFY_EE(new));
        default:
                WARN_ON_ONCE(1);
        }

        return false;
}

/* Limit event merges to limit CPU overhead per event */
#define FANOTIFY_MAX_MERGE_EVENTS 128

/* and the list better be locked by something too! */
static int fanotify_merge(struct fsnotify_group *group,
                          struct fsnotify_event *event)
{
        struct fanotify_event *old, *new = FANOTIFY_E(event);
        unsigned int bucket = fanotify_event_hash_bucket(group, new);
        struct hlist_head *hlist = &group->fanotify_data.merge_hash[bucket];
        int i = 0;

        pr_debug("%s: group=%p event=%p bucket=%u\n", __func__,
                 group, event, bucket);

        /*
         * Don't merge a permission event with any other event so that we know
         * the event structure we have created in fanotify_handle_event() is the
         * one we should check for permission response.
         */
        if (fanotify_is_perm_event(new->mask))
                return 0;

        hlist_for_each_entry(old, hlist, merge_list) {
                if (++i > FANOTIFY_MAX_MERGE_EVENTS)
                        break;
                if (fanotify_should_merge(old, new)) {
                        old->mask |= new->mask;

                        if (fanotify_is_error_event(old->mask))
                                FANOTIFY_EE(old)->err_count++;

                        return 1;
                }
        }

        return 0;
}

/*
 * Wait for response to permission event. The function also takes care of
 * freeing the permission event (or offloads that in case the wait is canceled
 * by a signal). The function returns 0 in case access got allowed by userspace,
 * -EPERM in case userspace disallowed the access, and -ERESTARTSYS in case
 * the wait got interrupted by a signal.
 */
static int fanotify_get_response(struct fsnotify_group *group,
                                 struct fanotify_perm_event *event,
                                 struct fsnotify_iter_info *iter_info)
{
        int ret;

        pr_debug("%s: group=%p event=%p\n", __func__, group, event);

        ret = wait_event_state(group->fanotify_data.access_waitq,
                                  event->state == FAN_EVENT_ANSWERED,
                                  (TASK_KILLABLE|TASK_FREEZABLE));

        /* Signal pending? */
        if (ret < 0) {
                spin_lock(&group->notification_lock);
                /* Event reported to userspace and no answer yet? */
                if (event->state == FAN_EVENT_REPORTED) {
                        /* Event will get freed once userspace answers to it */
                        event->state = FAN_EVENT_CANCELED;
                        spin_unlock(&group->notification_lock);
                        return ret;
                }
                /* Event not yet reported? Just remove it. */
                if (event->state == FAN_EVENT_INIT) {
                        fsnotify_remove_queued_event(group, &event->fae.fse);
                        /* Permission events are not supposed to be hashed */
                        WARN_ON_ONCE(!hlist_unhashed(&event->fae.merge_list));
                }
                /*
                 * Event may be also answered in case signal delivery raced
                 * with wakeup. In that case we have nothing to do besides
                 * freeing the event and reporting error.
                 */
                spin_unlock(&group->notification_lock);
                goto out;
        }

        /* userspace responded, convert to something usable */
        switch (event->response & FANOTIFY_RESPONSE_ACCESS) {
        case FAN_ALLOW:
                ret = 0;
                break;
        case FAN_DENY:
        default:
                ret = -EPERM;
        }

        /* Check if the response should be audited */
        if (event->response & FAN_AUDIT)
                audit_fanotify(event->response & ~FAN_AUDIT,
                               &event->audit_rule);

        pr_debug("%s: group=%p event=%p about to return ret=%d\n", __func__,
                 group, event, ret);
out:
        fsnotify_destroy_event(group, &event->fae.fse);

        return ret;
}

/*
 * This function returns a mask for an event that only contains the flags
 * that have been specifically requested by the user. Flags that may have
 * been included within the event mask, but have not been explicitly
 * requested by the user, will not be present in the returned mask.
 */
static u32 fanotify_group_event_mask(struct fsnotify_group *group,
                                     struct fsnotify_iter_info *iter_info,
                                     u32 *match_mask, u32 event_mask,
                                     const void *data, int data_type,
                                     struct inode *dir)
{
        __u32 marks_mask = 0, marks_ignore_mask = 0;
        __u32 test_mask, user_mask = FANOTIFY_OUTGOING_EVENTS |
                                     FANOTIFY_EVENT_FLAGS;
        const struct path *path = fsnotify_data_path(data, data_type);
        unsigned int fid_mode = FAN_GROUP_FLAG(group, FANOTIFY_FID_BITS);
        struct fsnotify_mark *mark;
        bool ondir = event_mask & FAN_ONDIR;
        int type;

        pr_debug("%s: report_mask=%x mask=%x data=%p data_type=%d\n",
                 __func__, iter_info->report_mask, event_mask, data, data_type);

        if (!fid_mode) {
                /* Do we have path to open a file descriptor? */
                if (!path)
                        return 0;
                /* Path type events are only relevant for files and dirs */
                if (!d_is_reg(path->dentry) && !d_can_lookup(path->dentry))
                        return 0;
        } else if (!(fid_mode & FAN_REPORT_FID)) {
                /* Do we have a directory inode to report? */
                if (!dir && !ondir)
                        return 0;
        }

        fsnotify_foreach_iter_mark_type(iter_info, mark, type) {
                /*
                 * Apply ignore mask depending on event flags in ignore mask.
                 */
                marks_ignore_mask |=
                        fsnotify_effective_ignore_mask(mark, ondir, type);

                /*
                 * Send the event depending on event flags in mark mask.
                 */
                if (!fsnotify_mask_applicable(mark->mask, ondir, type))
                        continue;

                marks_mask |= mark->mask;

                /* Record the mark types of this group that matched the event */
                *match_mask |= 1U << type;
        }

        test_mask = event_mask & marks_mask & ~marks_ignore_mask;

        /*
         * For dirent modification events (create/delete/move) that do not carry
         * the child entry name information, we report FAN_ONDIR for mkdir/rmdir
         * so user can differentiate them from creat/unlink.
         *
         * For backward compatibility and consistency, do not report FAN_ONDIR
         * to user in legacy fanotify mode (reporting fd) and report FAN_ONDIR
         * to user in fid mode for all event types.
         *
         * We never report FAN_EVENT_ON_CHILD to user, but we do pass it in to
         * fanotify_alloc_event() when group is reporting fid as indication
         * that event happened on child.
         */
        if (fid_mode) {
                /* Do not report event flags without any event */
                if (!(test_mask & ~FANOTIFY_EVENT_FLAGS))
                        return 0;
        } else {
                user_mask &= ~FANOTIFY_EVENT_FLAGS;
        }

        return test_mask & user_mask;
}

/*
 * Check size needed to encode fanotify_fh.
 *
 * Return size of encoded fh without fanotify_fh header.
 * Return 0 on failure to encode.
 */
static int fanotify_encode_fh_len(struct inode *inode)
{
        int dwords = 0;
        int fh_len;

        if (!inode)
                return 0;

        exportfs_encode_fid(inode, NULL, &dwords);
        fh_len = dwords << 2;

        /*
         * struct fanotify_error_event might be preallocated and is
         * limited to MAX_HANDLE_SZ.  This should never happen, but
         * safeguard by forcing an invalid file handle.
         */
        if (WARN_ON_ONCE(fh_len > MAX_HANDLE_SZ))
                return 0;

        return fh_len;
}

/*
 * Encode fanotify_fh.
 *
 * Return total size of encoded fh including fanotify_fh header.
 * Return 0 on failure to encode.
 */
static int fanotify_encode_fh(struct fanotify_fh *fh, struct inode *inode,
                              unsigned int fh_len, unsigned int *hash,
                              gfp_t gfp)
{
        int dwords, type = 0;
        char *ext_buf = NULL;
        void *buf = fh->buf;
        int err;

        fh->type = FILEID_ROOT;
        fh->len = 0;
        fh->flags = 0;

        /*
         * Invalid FHs are used by FAN_FS_ERROR for errors not
         * linked to any inode. The f_handle won't be reported
         * back to userspace.
         */
        if (!inode)
                goto out;

        /*
         * !gpf means preallocated variable size fh, but fh_len could
         * be zero in that case if encoding fh len failed.
         */
        err = -ENOENT;
        if (fh_len < 4 || WARN_ON_ONCE(fh_len % 4) || fh_len > MAX_HANDLE_SZ)
                goto out_err;

        /* No external buffer in a variable size allocated fh */
        if (gfp && fh_len > FANOTIFY_INLINE_FH_LEN) {
                /* Treat failure to allocate fh as failure to encode fh */
                err = -ENOMEM;
                ext_buf = kmalloc(fh_len, gfp);
                if (!ext_buf)
                        goto out_err;

                *fanotify_fh_ext_buf_ptr(fh) = ext_buf;
                buf = ext_buf;
                fh->flags |= FANOTIFY_FH_FLAG_EXT_BUF;
        }

        dwords = fh_len >> 2;
        type = exportfs_encode_fid(inode, buf, &dwords);
        err = -EINVAL;
        if (type <= 0 || type == FILEID_INVALID || fh_len != dwords << 2)
                goto out_err;

        fh->type = type;
        fh->len = fh_len;

out:
        /*
         * Mix fh into event merge key.  Hash might be NULL in case of
         * unhashed FID events (i.e. FAN_FS_ERROR).
         */
        if (hash)
                *hash ^= fanotify_hash_fh(fh);

        return FANOTIFY_FH_HDR_LEN + fh_len;

out_err:
        pr_warn_ratelimited("fanotify: failed to encode fid (type=%d, len=%d, err=%i)\n",
                            type, fh_len, err);
        kfree(ext_buf);
        *fanotify_fh_ext_buf_ptr(fh) = NULL;
        /* Report the event without a file identifier on encode error */
        fh->type = FILEID_INVALID;
        fh->len = 0;
        return 0;
}

/*
 * FAN_REPORT_FID is ambiguous in that it reports the fid of the child for
 * some events and the fid of the parent for create/delete/move events.
 *
 * With the FAN_REPORT_TARGET_FID flag, the fid of the child is reported
 * also in create/delete/move events in addition to the fid of the parent
 * and the name of the child.
 */
static inline bool fanotify_report_child_fid(unsigned int fid_mode, u32 mask)
{
        if (mask & ALL_FSNOTIFY_DIRENT_EVENTS)
                return (fid_mode & FAN_REPORT_TARGET_FID);

        return (fid_mode & FAN_REPORT_FID) && !(mask & FAN_ONDIR);
}

/*
 * The inode to use as identifier when reporting fid depends on the event
 * and the group flags.
 *
 * With the group flag FAN_REPORT_TARGET_FID, always report the child fid.
 *
 * Without the group flag FAN_REPORT_TARGET_FID, report the modified directory
 * fid on dirent events and the child fid otherwise.
 *
 * For example:
 * FS_ATTRIB reports the child fid even if reported on a watched parent.
 * FS_CREATE reports the modified dir fid without FAN_REPORT_TARGET_FID.
 *       and reports the created child fid with FAN_REPORT_TARGET_FID.
 */
static struct inode *fanotify_fid_inode(u32 event_mask, const void *data,
                                        int data_type, struct inode *dir,
                                        unsigned int fid_mode)
{
        if ((event_mask & ALL_FSNOTIFY_DIRENT_EVENTS) &&
            !(fid_mode & FAN_REPORT_TARGET_FID))
                return dir;

        return fsnotify_data_inode(data, data_type);
}

/*
 * The inode to use as identifier when reporting dir fid depends on the event.
 * Report the modified directory inode on dirent modification events.
 * Report the "victim" inode if "victim" is a directory.
 * Report the parent inode if "victim" is not a directory and event is
 * reported to parent.
 * Otherwise, do not report dir fid.
 */
static struct inode *fanotify_dfid_inode(u32 event_mask, const void *data,
                                         int data_type, struct inode *dir)
{
        struct inode *inode = fsnotify_data_inode(data, data_type);

        if (event_mask & ALL_FSNOTIFY_DIRENT_EVENTS)
                return dir;

        if (inode && S_ISDIR(inode->i_mode))
                return inode;

        return dir;
}

static struct fanotify_event *fanotify_alloc_path_event(const struct path *path,
                                                        unsigned int *hash,
                                                        gfp_t gfp)
{
        struct fanotify_path_event *pevent;

        pevent = kmem_cache_alloc(fanotify_path_event_cachep, gfp);
        if (!pevent)
                return NULL;

        pevent->fae.type = FANOTIFY_EVENT_TYPE_PATH;
        pevent->path = *path;
        *hash ^= fanotify_hash_path(path);
        path_get(path);

        return &pevent->fae;
}

static struct fanotify_event *fanotify_alloc_perm_event(const struct path *path,
                                                        gfp_t gfp)
{
        struct fanotify_perm_event *pevent;

        pevent = kmem_cache_alloc(fanotify_perm_event_cachep, gfp);
        if (!pevent)
                return NULL;

        pevent->fae.type = FANOTIFY_EVENT_TYPE_PATH_PERM;
        pevent->response = 0;
        pevent->hdr.type = FAN_RESPONSE_INFO_NONE;
        pevent->hdr.pad = 0;
        pevent->hdr.len = 0;
        pevent->state = FAN_EVENT_INIT;
        pevent->path = *path;
        path_get(path);

        return &pevent->fae;
}

static struct fanotify_event *fanotify_alloc_fid_event(struct inode *id,
                                                       __kernel_fsid_t *fsid,
                                                       unsigned int *hash,
                                                       gfp_t gfp)
{
        struct fanotify_fid_event *ffe;

        ffe = kmem_cache_alloc(fanotify_fid_event_cachep, gfp);
        if (!ffe)
                return NULL;

        ffe->fae.type = FANOTIFY_EVENT_TYPE_FID;
        ffe->fsid = *fsid;
        *hash ^= fanotify_hash_fsid(fsid);
        fanotify_encode_fh(&ffe->object_fh, id, fanotify_encode_fh_len(id),
                           hash, gfp);

        return &ffe->fae;
}

static struct fanotify_event *fanotify_alloc_name_event(struct inode *dir,
                                                        __kernel_fsid_t *fsid,
                                                        const struct qstr *name,
                                                        struct inode *child,
                                                        struct dentry *moved,
                                                        unsigned int *hash,
                                                        gfp_t gfp)
{
        struct fanotify_name_event *fne;
        struct fanotify_info *info;
        struct fanotify_fh *dfh, *ffh;
        struct inode *dir2 = moved ? d_inode(moved->d_parent) : NULL;
        const struct qstr *name2 = moved ? &moved->d_name : NULL;
        unsigned int dir_fh_len = fanotify_encode_fh_len(dir);
        unsigned int dir2_fh_len = fanotify_encode_fh_len(dir2);
        unsigned int child_fh_len = fanotify_encode_fh_len(child);
        unsigned long name_len = name ? name->len : 0;
        unsigned long name2_len = name2 ? name2->len : 0;
        unsigned int len, size;

        /* Reserve terminating null byte even for empty name */
        size = sizeof(*fne) + name_len + name2_len + 2;
        if (dir_fh_len)
                size += FANOTIFY_FH_HDR_LEN + dir_fh_len;
        if (dir2_fh_len)
                size += FANOTIFY_FH_HDR_LEN + dir2_fh_len;
        if (child_fh_len)
                size += FANOTIFY_FH_HDR_LEN + child_fh_len;
        fne = kmalloc(size, gfp);
        if (!fne)
                return NULL;

        fne->fae.type = FANOTIFY_EVENT_TYPE_FID_NAME;
        fne->fsid = *fsid;
        *hash ^= fanotify_hash_fsid(fsid);
        info = &fne->info;
        fanotify_info_init(info);
        if (dir_fh_len) {
                dfh = fanotify_info_dir_fh(info);
                len = fanotify_encode_fh(dfh, dir, dir_fh_len, hash, 0);
                fanotify_info_set_dir_fh(info, len);
        }
        if (dir2_fh_len) {
                dfh = fanotify_info_dir2_fh(info);
                len = fanotify_encode_fh(dfh, dir2, dir2_fh_len, hash, 0);
                fanotify_info_set_dir2_fh(info, len);
        }
        if (child_fh_len) {
                ffh = fanotify_info_file_fh(info);
                len = fanotify_encode_fh(ffh, child, child_fh_len, hash, 0);
                fanotify_info_set_file_fh(info, len);
        }
        if (name_len) {
                fanotify_info_copy_name(info, name);
                *hash ^= full_name_hash((void *)name_len, name->name, name_len);
        }
        if (name2_len) {
                fanotify_info_copy_name2(info, name2);
                *hash ^= full_name_hash((void *)name2_len, name2->name,
                                        name2_len);
        }

        pr_debug("%s: size=%u dir_fh_len=%u child_fh_len=%u name_len=%u name='%.*s'\n",
                 __func__, size, dir_fh_len, child_fh_len,
                 info->name_len, info->name_len, fanotify_info_name(info));

        if (dir2_fh_len) {
                pr_debug("%s: dir2_fh_len=%u name2_len=%u name2='%.*s'\n",
                         __func__, dir2_fh_len, info->name2_len,
                         info->name2_len, fanotify_info_name2(info));
        }

        return &fne->fae;
}

static struct fanotify_event *fanotify_alloc_error_event(
                                                struct fsnotify_group *group,
                                                __kernel_fsid_t *fsid,
                                                const void *data, int data_type,
                                                unsigned int *hash)
{
        struct fs_error_report *report =
                        fsnotify_data_error_report(data, data_type);
        struct inode *inode;
        struct fanotify_error_event *fee;
        int fh_len;

        if (WARN_ON_ONCE(!report))
                return NULL;

        fee = mempool_alloc(&group->fanotify_data.error_events_pool, GFP_NOFS);
        if (!fee)
                return NULL;

        fee->fae.type = FANOTIFY_EVENT_TYPE_FS_ERROR;
        fee->error = report->error;
        fee->err_count = 1;
        fee->fsid = *fsid;

        inode = report->inode;
        fh_len = fanotify_encode_fh_len(inode);

        /* Bad fh_len. Fallback to using an invalid fh. Should never happen. */
        if (!fh_len && inode)
                inode = NULL;

        fanotify_encode_fh(&fee->object_fh, inode, fh_len, NULL, 0);

        *hash ^= fanotify_hash_fsid(fsid);

        return &fee->fae;
}

static struct fanotify_event *fanotify_alloc_event(
                                struct fsnotify_group *group,
                                u32 mask, const void *data, int data_type,
                                struct inode *dir, const struct qstr *file_name,
                                __kernel_fsid_t *fsid, u32 match_mask)
{
        struct fanotify_event *event = NULL;
        gfp_t gfp = GFP_KERNEL_ACCOUNT;
        unsigned int fid_mode = FAN_GROUP_FLAG(group, FANOTIFY_FID_BITS);
        struct inode *id = fanotify_fid_inode(mask, data, data_type, dir,
                                              fid_mode);
        struct inode *dirid = fanotify_dfid_inode(mask, data, data_type, dir);
        const struct path *path = fsnotify_data_path(data, data_type);
        struct mem_cgroup *old_memcg;
        struct dentry *moved = NULL;
        struct inode *child = NULL;
        bool name_event = false;
        unsigned int hash = 0;
        bool ondir = mask & FAN_ONDIR;
        struct pid *pid;

        if ((fid_mode & FAN_REPORT_DIR_FID) && dirid) {
                /*
                 * For certain events and group flags, report the child fid
                 * in addition to reporting the parent fid and maybe child name.
                 */
                if (fanotify_report_child_fid(fid_mode, mask) && id != dirid)
                        child = id;

                id = dirid;

                /*
                 * We record file name only in a group with FAN_REPORT_NAME
                 * and when we have a directory inode to report.
                 *
                 * For directory entry modification event, we record the fid of
                 * the directory and the name of the modified entry.
                 *
                 * For event on non-directory that is reported to parent, we
                 * record the fid of the parent and the name of the child.
                 *
                 * Even if not reporting name, we need a variable length
                 * fanotify_name_event if reporting both parent and child fids.
                 */
                if (!(fid_mode & FAN_REPORT_NAME)) {
                        name_event = !!child;
                        file_name = NULL;
                } else if ((mask & ALL_FSNOTIFY_DIRENT_EVENTS) || !ondir) {
                        name_event = true;
                }

                /*
                 * In the special case of FAN_RENAME event, use the match_mask
                 * to determine if we need to report only the old parent+name,
                 * only the new parent+name or both.
                 * 'dirid' and 'file_name' are the old parent+name and
                 * 'moved' has the new parent+name.
                 */
                if (mask & FAN_RENAME) {
                        bool report_old, report_new;

                        if (WARN_ON_ONCE(!match_mask))
                                return NULL;

                        /* Report both old and new parent+name if sb watching */
                        report_old = report_new =
                                match_mask & (1U << FSNOTIFY_ITER_TYPE_SB);
                        report_old |=
                                match_mask & (1U << FSNOTIFY_ITER_TYPE_INODE);
                        report_new |=
                                match_mask & (1U << FSNOTIFY_ITER_TYPE_INODE2);

                        if (!report_old) {
                                /* Do not report old parent+name */
                                dirid = NULL;
                                file_name = NULL;
                        }
                        if (report_new) {
                                /* Report new parent+name */
                                moved = fsnotify_data_dentry(data, data_type);
                        }
                }
        }

        /*
         * For queues with unlimited length lost events are not expected and
         * can possibly have security implications. Avoid losing events when
         * memory is short. For the limited size queues, avoid OOM killer in the
         * target monitoring memcg as it may have security repercussion.
         */
        if (group->max_events == UINT_MAX)
                gfp |= __GFP_NOFAIL;
        else
                gfp |= __GFP_RETRY_MAYFAIL;

        /* Whoever is interested in the event, pays for the allocation. */
        old_memcg = set_active_memcg(group->memcg);

        if (fanotify_is_perm_event(mask)) {
                event = fanotify_alloc_perm_event(path, gfp);
        } else if (fanotify_is_error_event(mask)) {
                event = fanotify_alloc_error_event(group, fsid, data,
                                                   data_type, &hash);
        } else if (name_event && (file_name || moved || child)) {
                event = fanotify_alloc_name_event(dirid, fsid, file_name, child,
                                                  moved, &hash, gfp);
        } else if (fid_mode) {
                event = fanotify_alloc_fid_event(id, fsid, &hash, gfp);
        } else {
                event = fanotify_alloc_path_event(path, &hash, gfp);
        }

        if (!event)
                goto out;

        if (FAN_GROUP_FLAG(group, FAN_REPORT_TID))
                pid = get_pid(task_pid(current));
        else
                pid = get_pid(task_tgid(current));

        /* Mix event info, FAN_ONDIR flag and pid into event merge key */
        hash ^= hash_long((unsigned long)pid | ondir, FANOTIFY_EVENT_HASH_BITS);
        fanotify_init_event(event, hash, mask);
        event->pid = pid;

out:
        set_active_memcg(old_memcg);
        return event;
}

/*
 * Get cached fsid of the filesystem containing the object from any mark.
 * All marks are supposed to have the same fsid, but we do not verify that here.
 */
static __kernel_fsid_t fanotify_get_fsid(struct fsnotify_iter_info *iter_info)
{
        struct fsnotify_mark *mark;
        int type;
        __kernel_fsid_t fsid = {};

        fsnotify_foreach_iter_mark_type(iter_info, mark, type) {
                if (!(mark->flags & FSNOTIFY_MARK_FLAG_HAS_FSID))
                        continue;
                fsid = FANOTIFY_MARK(mark)->fsid;
                if (!(mark->flags & FSNOTIFY_MARK_FLAG_WEAK_FSID) &&
                    WARN_ON_ONCE(!fsid.val[0] && !fsid.val[1]))
                        continue;
                return fsid;
        }

        return fsid;
}

/*
 * Add an event to hash table for faster merge.
 */
static void fanotify_insert_event(struct fsnotify_group *group,
                                  struct fsnotify_event *fsn_event)
{
        struct fanotify_event *event = FANOTIFY_E(fsn_event);
        unsigned int bucket = fanotify_event_hash_bucket(group, event);
        struct hlist_head *hlist = &group->fanotify_data.merge_hash[bucket];

        assert_spin_locked(&group->notification_lock);

        if (!fanotify_is_hashed_event(event->mask))
                return;

        pr_debug("%s: group=%p event=%p bucket=%u\n", __func__,
                 group, event, bucket);

        hlist_add_head(&event->merge_list, hlist);
}

static int fanotify_handle_event(struct fsnotify_group *group, u32 mask,
                                 const void *data, int data_type,
                                 struct inode *dir,
                                 const struct qstr *file_name, u32 cookie,
                                 struct fsnotify_iter_info *iter_info)
{
        int ret = 0;
        struct fanotify_event *event;
        struct fsnotify_event *fsn_event;
        __kernel_fsid_t fsid = {};
        u32 match_mask = 0;

        BUILD_BUG_ON(FAN_ACCESS != FS_ACCESS);
        BUILD_BUG_ON(FAN_MODIFY != FS_MODIFY);
        BUILD_BUG_ON(FAN_ATTRIB != FS_ATTRIB);
        BUILD_BUG_ON(FAN_CLOSE_NOWRITE != FS_CLOSE_NOWRITE);
        BUILD_BUG_ON(FAN_CLOSE_WRITE != FS_CLOSE_WRITE);
        BUILD_BUG_ON(FAN_OPEN != FS_OPEN);
        BUILD_BUG_ON(FAN_MOVED_TO != FS_MOVED_TO);
        BUILD_BUG_ON(FAN_MOVED_FROM != FS_MOVED_FROM);
        BUILD_BUG_ON(FAN_CREATE != FS_CREATE);
        BUILD_BUG_ON(FAN_DELETE != FS_DELETE);
        BUILD_BUG_ON(FAN_DELETE_SELF != FS_DELETE_SELF);
        BUILD_BUG_ON(FAN_MOVE_SELF != FS_MOVE_SELF);
        BUILD_BUG_ON(FAN_EVENT_ON_CHILD != FS_EVENT_ON_CHILD);
        BUILD_BUG_ON(FAN_Q_OVERFLOW != FS_Q_OVERFLOW);
        BUILD_BUG_ON(FAN_OPEN_PERM != FS_OPEN_PERM);
        BUILD_BUG_ON(FAN_ACCESS_PERM != FS_ACCESS_PERM);
        BUILD_BUG_ON(FAN_ONDIR != FS_ISDIR);
        BUILD_BUG_ON(FAN_OPEN_EXEC != FS_OPEN_EXEC);
        BUILD_BUG_ON(FAN_OPEN_EXEC_PERM != FS_OPEN_EXEC_PERM);
        BUILD_BUG_ON(FAN_FS_ERROR != FS_ERROR);
        BUILD_BUG_ON(FAN_RENAME != FS_RENAME);

        BUILD_BUG_ON(HWEIGHT32(ALL_FANOTIFY_EVENT_BITS) != 21);

        mask = fanotify_group_event_mask(group, iter_info, &match_mask,
                                         mask, data, data_type, dir);
        if (!mask)
                return 0;

        pr_debug("%s: group=%p mask=%x report_mask=%x\n", __func__,
                 group, mask, match_mask);

        if (fanotify_is_perm_event(mask)) {
                /*
                 * fsnotify_prepare_user_wait() fails if we race with mark
                 * deletion.  Just let the operation pass in that case.
                 */
                if (!fsnotify_prepare_user_wait(iter_info))
                        return 0;
        }

        if (FAN_GROUP_FLAG(group, FANOTIFY_FID_BITS))
                fsid = fanotify_get_fsid(iter_info);

        event = fanotify_alloc_event(group, mask, data, data_type, dir,
                                     file_name, &fsid, match_mask);
        ret = -ENOMEM;
        if (unlikely(!event)) {
                /*
                 * We don't queue overflow events for permission events as
                 * there the access is denied and so no event is in fact lost.
                 */
                if (!fanotify_is_perm_event(mask))
                        fsnotify_queue_overflow(group);
                goto finish;
        }

        fsn_event = &event->fse;
        ret = fsnotify_insert_event(group, fsn_event, fanotify_merge,
                                    fanotify_insert_event);
        if (ret) {
                /* Permission events shouldn't be merged */
                BUG_ON(ret == 1 && mask & FANOTIFY_PERM_EVENTS);
                /* Our event wasn't used in the end. Free it. */
                fsnotify_destroy_event(group, fsn_event);

                ret = 0;
        } else if (fanotify_is_perm_event(mask)) {
                ret = fanotify_get_response(group, FANOTIFY_PERM(event),
                                            iter_info);
        }
finish:
        if (fanotify_is_perm_event(mask))
                fsnotify_finish_user_wait(iter_info);

        return ret;
}

static void fanotify_free_group_priv(struct fsnotify_group *group)
{
        kfree(group->fanotify_data.merge_hash);
        if (group->fanotify_data.ucounts)
                dec_ucount(group->fanotify_data.ucounts,
                           UCOUNT_FANOTIFY_GROUPS);

        if (mempool_initialized(&group->fanotify_data.error_events_pool))
                mempool_exit(&group->fanotify_data.error_events_pool);
}

static void fanotify_free_path_event(struct fanotify_event *event)
{
        path_put(fanotify_event_path(event));
        kmem_cache_free(fanotify_path_event_cachep, FANOTIFY_PE(event));
}

static void fanotify_free_perm_event(struct fanotify_event *event)
{
        path_put(fanotify_event_path(event));
        kmem_cache_free(fanotify_perm_event_cachep, FANOTIFY_PERM(event));
}

static void fanotify_free_fid_event(struct fanotify_event *event)
{
        struct fanotify_fid_event *ffe = FANOTIFY_FE(event);

        if (fanotify_fh_has_ext_buf(&ffe->object_fh))
                kfree(fanotify_fh_ext_buf(&ffe->object_fh));
        kmem_cache_free(fanotify_fid_event_cachep, ffe);
}

static void fanotify_free_name_event(struct fanotify_event *event)
{
        kfree(FANOTIFY_NE(event));
}

static void fanotify_free_error_event(struct fsnotify_group *group,
                                      struct fanotify_event *event)
{
        struct fanotify_error_event *fee = FANOTIFY_EE(event);

        mempool_free(fee, &group->fanotify_data.error_events_pool);
}

static void fanotify_free_event(struct fsnotify_group *group,
                                struct fsnotify_event *fsn_event)
{
        struct fanotify_event *event;

        event = FANOTIFY_E(fsn_event);
        put_pid(event->pid);
        switch (event->type) {
        case FANOTIFY_EVENT_TYPE_PATH:
                fanotify_free_path_event(event);
                break;
        case FANOTIFY_EVENT_TYPE_PATH_PERM:
                fanotify_free_perm_event(event);
                break;
        case FANOTIFY_EVENT_TYPE_FID:
                fanotify_free_fid_event(event);
                break;
        case FANOTIFY_EVENT_TYPE_FID_NAME:
                fanotify_free_name_event(event);
                break;
        case FANOTIFY_EVENT_TYPE_OVERFLOW:
                kfree(event);
                break;
        case FANOTIFY_EVENT_TYPE_FS_ERROR:
                fanotify_free_error_event(group, event);
                break;
        default:
                WARN_ON_ONCE(1);
        }
}

static void fanotify_freeing_mark(struct fsnotify_mark *mark,
                                  struct fsnotify_group *group)
{
        if (!FAN_GROUP_FLAG(group, FAN_UNLIMITED_MARKS))
                dec_ucount(group->fanotify_data.ucounts, UCOUNT_FANOTIFY_MARKS);
}

static void fanotify_free_mark(struct fsnotify_mark *fsn_mark)
{
        kmem_cache_free(fanotify_mark_cache, FANOTIFY_MARK(fsn_mark));
}

const struct fsnotify_ops fanotify_fsnotify_ops = {
        .handle_event = fanotify_handle_event,
        .free_group_priv = fanotify_free_group_priv,
        .free_event = fanotify_free_event,
        .freeing_mark = fanotify_freeing_mark,
        .free_mark = fanotify_free_mark,
};







































   10 


















   10 


    7 






    5 

    3 

    4 


    2 






    5 



















    1 










    1 


    1 


























    7 


    1 

    5 




    1 



    1 







    1 


   38 



    1 





















    2 









































    2 










    8 





    6 


















    3 






    4 






    1 





    3 
    3 































    4 

    4 














    4 
    4 





















   12 






   12 





    4 



    5 







    1 





    4 





















    3 


    3 











    2 









    2 






    1 









    1 








    5 

   14 












   13 

  394 











    1 














  586 





   28 




  441 

   41 






   28 




   10 


    1 

    2 






    1 


    1 




    1 


    2 




    1 







   15 



    1 





    1 









  407 


   12 


    4 




    9 







   19 



















 1264 



 1263 

 1262 


 1218 

  116 
  103 
























  949 




  953 

    3 




  920 
   28 





  233 



    4 
    1 















   47 
   47 
   47 
   44 
    4 





  289 
    2 












    1 




   21 
    3 










   10 
























  141 









  149 

















  416 










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
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
// SPDX-License-Identifier: GPL-2.0
#include <linux/kmod.h>
#include <linux/netdevice.h>
#include <linux/inetdevice.h>
#include <linux/etherdevice.h>
#include <linux/rtnetlink.h>
#include <linux/net_tstamp.h>
#include <linux/phylib_stubs.h>
#include <linux/wireless.h>
#include <linux/if_bridge.h>
#include <net/dsa_stubs.h>
#include <net/wext.h>

#include "dev.h"

/*
 *        Map an interface index to its name (SIOCGIFNAME)
 */

/*
 *        We need this ioctl for efficient implementation of the
 *        if_indextoname() function required by the IPv6 API.  Without
 *        it, we would have to search all the interfaces to find a
 *        match.  --pb
 */

static int dev_ifname(struct net *net, struct ifreq *ifr)
{
        ifr->ifr_name[IFNAMSIZ-1] = 0;
        return netdev_get_name(net, ifr->ifr_name, ifr->ifr_ifindex);
}

/*
 *        Perform a SIOCGIFCONF call. This structure will change
 *        size eventually, and there is nothing I can do about it.
 *        Thus we will need a 'compatibility mode'.
 */
int dev_ifconf(struct net *net, struct ifconf __user *uifc)
{
        struct net_device *dev;
        void __user *pos;
        size_t size;
        int len, total = 0, done;

        /* both the ifconf and the ifreq structures are slightly different */
        if (in_compat_syscall()) {
                struct compat_ifconf ifc32;

                if (copy_from_user(&ifc32, uifc, sizeof(struct compat_ifconf)))
                        return -EFAULT;

                pos = compat_ptr(ifc32.ifcbuf);
                len = ifc32.ifc_len;
                size = sizeof(struct compat_ifreq);
        } else {
                struct ifconf ifc;

                if (copy_from_user(&ifc, uifc, sizeof(struct ifconf)))
                        return -EFAULT;

                pos = ifc.ifc_buf;
                len = ifc.ifc_len;
                size = sizeof(struct ifreq);
        }

        /* Loop over the interfaces, and write an info block for each. */
        rtnl_net_lock(net);
        for_each_netdev(net, dev) {
                if (!pos)
                        done = inet_gifconf(dev, NULL, 0, size);
                else
                        done = inet_gifconf(dev, pos + total,
                                            len - total, size);
                if (done < 0) {
                        rtnl_net_unlock(net);
                        return -EFAULT;
                }
                total += done;
        }
        rtnl_net_unlock(net);

        return put_user(total, &uifc->ifc_len);
}

static int dev_getifmap(struct net_device *dev, struct ifreq *ifr)
{
        struct ifmap *ifmap = &ifr->ifr_map;

        if (in_compat_syscall()) {
                struct compat_ifmap *cifmap = (struct compat_ifmap *)ifmap;

                cifmap->mem_start = dev->mem_start;
                cifmap->mem_end   = dev->mem_end;
                cifmap->base_addr = dev->base_addr;
                cifmap->irq       = dev->irq;
                cifmap->dma       = dev->dma;
                cifmap->port      = dev->if_port;

                return 0;
        }

        ifmap->mem_start  = dev->mem_start;
        ifmap->mem_end    = dev->mem_end;
        ifmap->base_addr  = dev->base_addr;
        ifmap->irq        = dev->irq;
        ifmap->dma        = dev->dma;
        ifmap->port       = dev->if_port;

        return 0;
}

static int dev_setifmap(struct net_device *dev, struct ifreq *ifr)
{
        struct compat_ifmap *cifmap = (struct compat_ifmap *)&ifr->ifr_map;

        if (!dev->netdev_ops->ndo_set_config)
                return -EOPNOTSUPP;

        if (in_compat_syscall()) {
                struct ifmap ifmap = {
                        .mem_start  = cifmap->mem_start,
                        .mem_end    = cifmap->mem_end,
                        .base_addr  = cifmap->base_addr,
                        .irq        = cifmap->irq,
                        .dma        = cifmap->dma,
                        .port       = cifmap->port,
                };

                return dev->netdev_ops->ndo_set_config(dev, &ifmap);
        }

        return dev->netdev_ops->ndo_set_config(dev, &ifr->ifr_map);
}

/*
 *        Perform the SIOCxIFxxx calls, inside rcu_read_lock()
 */
static int dev_ifsioc_locked(struct net *net, struct ifreq *ifr, unsigned int cmd)
{
        int err;
        struct net_device *dev = dev_get_by_name_rcu(net, ifr->ifr_name);

        if (!dev)
                return -ENODEV;

        switch (cmd) {
        case SIOCGIFFLAGS:        /* Get interface flags */
                ifr->ifr_flags = (short) dev_get_flags(dev);
                return 0;

        case SIOCGIFMETRIC:        /* Get the metric on the interface
                                   (currently unused) */
                ifr->ifr_metric = 0;
                return 0;

        case SIOCGIFMTU:        /* Get the MTU of a device */
                ifr->ifr_mtu = dev->mtu;
                return 0;

        case SIOCGIFSLAVE:
                err = -EINVAL;
                break;

        case SIOCGIFMAP:
                return dev_getifmap(dev, ifr);

        case SIOCGIFINDEX:
                ifr->ifr_ifindex = dev->ifindex;
                return 0;

        case SIOCGIFTXQLEN:
                ifr->ifr_qlen = dev->tx_queue_len;
                return 0;

        default:
                /* dev_ioctl() should ensure this case
                 * is never reached
                 */
                WARN_ON(1);
                err = -ENOTTY;
                break;

        }
        return err;
}

static int net_hwtstamp_validate(const struct kernel_hwtstamp_config *cfg)
{
        enum hwtstamp_tx_types tx_type;
        enum hwtstamp_rx_filters rx_filter;
        int tx_type_valid = 0;
        int rx_filter_valid = 0;

        if (cfg->flags & ~HWTSTAMP_FLAG_MASK)
                return -EINVAL;

        tx_type = cfg->tx_type;
        rx_filter = cfg->rx_filter;

        switch (tx_type) {
        case HWTSTAMP_TX_OFF:
        case HWTSTAMP_TX_ON:
        case HWTSTAMP_TX_ONESTEP_SYNC:
        case HWTSTAMP_TX_ONESTEP_P2P:
                tx_type_valid = 1;
                break;
        case __HWTSTAMP_TX_CNT:
                /* not a real value */
                break;
        }

        switch (rx_filter) {
        case HWTSTAMP_FILTER_NONE:
        case HWTSTAMP_FILTER_ALL:
        case HWTSTAMP_FILTER_SOME:
        case HWTSTAMP_FILTER_PTP_V1_L4_EVENT:
        case HWTSTAMP_FILTER_PTP_V1_L4_SYNC:
        case HWTSTAMP_FILTER_PTP_V1_L4_DELAY_REQ:
        case HWTSTAMP_FILTER_PTP_V2_L4_EVENT:
        case HWTSTAMP_FILTER_PTP_V2_L4_SYNC:
        case HWTSTAMP_FILTER_PTP_V2_L4_DELAY_REQ:
        case HWTSTAMP_FILTER_PTP_V2_L2_EVENT:
        case HWTSTAMP_FILTER_PTP_V2_L2_SYNC:
        case HWTSTAMP_FILTER_PTP_V2_L2_DELAY_REQ:
        case HWTSTAMP_FILTER_PTP_V2_EVENT:
        case HWTSTAMP_FILTER_PTP_V2_SYNC:
        case HWTSTAMP_FILTER_PTP_V2_DELAY_REQ:
        case HWTSTAMP_FILTER_NTP_ALL:
                rx_filter_valid = 1;
                break;
        case __HWTSTAMP_FILTER_CNT:
                /* not a real value */
                break;
        }

        if (!tx_type_valid || !rx_filter_valid)
                return -ERANGE;

        return 0;
}

static int dev_eth_ioctl(struct net_device *dev,
                         struct ifreq *ifr, unsigned int cmd)
{
        const struct net_device_ops *ops = dev->netdev_ops;

        if (!ops->ndo_eth_ioctl)
                return -EOPNOTSUPP;

        if (!netif_device_present(dev))
                return -ENODEV;

        return ops->ndo_eth_ioctl(dev, ifr, cmd);
}

/**
 * dev_get_hwtstamp_phylib() - Get hardware timestamping settings of NIC
 *        or of attached phylib PHY
 * @dev: Network device
 * @cfg: Timestamping configuration structure
 *
 * Helper for calling the default hardware provider timestamping.
 *
 * Note: phy_mii_ioctl() only handles SIOCSHWTSTAMP (not SIOCGHWTSTAMP), and
 * there only exists a phydev->mii_ts->hwtstamp() method. So this will return
 * -EOPNOTSUPP for phylib for now, which is still more accurate than letting
 * the netdev handle the GET request.
 */
static int dev_get_hwtstamp_phylib(struct net_device *dev,
                                   struct kernel_hwtstamp_config *cfg)
{
        if (phy_is_default_hwtstamp(dev->phydev))
                return phy_hwtstamp_get(dev->phydev, cfg);

        return dev->netdev_ops->ndo_hwtstamp_get(dev, cfg);
}

static int dev_get_hwtstamp(struct net_device *dev, struct ifreq *ifr)
{
        const struct net_device_ops *ops = dev->netdev_ops;
        struct kernel_hwtstamp_config kernel_cfg = {};
        struct hwtstamp_config cfg;
        int err;

        if (!ops->ndo_hwtstamp_get)
                return dev_eth_ioctl(dev, ifr, SIOCGHWTSTAMP); /* legacy */

        if (!netif_device_present(dev))
                return -ENODEV;

        kernel_cfg.ifr = ifr;
        err = dev_get_hwtstamp_phylib(dev, &kernel_cfg);
        if (err)
                return err;

        /* If the request was resolved through an unconverted driver, omit
         * the copy_to_user(), since the implementation has already done that
         */
        if (!kernel_cfg.copied_to_user) {
                hwtstamp_config_from_kernel(&cfg, &kernel_cfg);

                if (copy_to_user(ifr->ifr_data, &cfg, sizeof(cfg)))
                        return -EFAULT;
        }

        return 0;
}

/**
 * dev_set_hwtstamp_phylib() - Change hardware timestamping of NIC
 *        or of attached phylib PHY
 * @dev: Network device
 * @cfg: Timestamping configuration structure
 * @extack: Netlink extended ack message structure, for error reporting
 *
 * Helper for enforcing a common policy that phylib timestamping, if available,
 * should take precedence in front of hardware timestamping provided by the
 * netdev. If the netdev driver needs to perform specific actions even for PHY
 * timestamping to work properly (a switch port must trap the timestamped
 * frames and not forward them), it must set dev->see_all_hwtstamp_requests.
 */
int dev_set_hwtstamp_phylib(struct net_device *dev,
                            struct kernel_hwtstamp_config *cfg,
                            struct netlink_ext_ack *extack)
{
        const struct net_device_ops *ops = dev->netdev_ops;
        bool phy_ts = phy_is_default_hwtstamp(dev->phydev);
        struct kernel_hwtstamp_config old_cfg = {};
        bool changed = false;
        int err;

        cfg->source = phy_ts ? HWTSTAMP_SOURCE_PHYLIB : HWTSTAMP_SOURCE_NETDEV;

        if (phy_ts && dev->see_all_hwtstamp_requests) {
                err = ops->ndo_hwtstamp_get(dev, &old_cfg);
                if (err)
                        return err;
        }

        if (!phy_ts || dev->see_all_hwtstamp_requests) {
                err = ops->ndo_hwtstamp_set(dev, cfg, extack);
                if (err) {
                        if (extack->_msg)
                                netdev_err(dev, "%s\n", extack->_msg);
                        return err;
                }
        }

        if (phy_ts && dev->see_all_hwtstamp_requests)
                changed = kernel_hwtstamp_config_changed(&old_cfg, cfg);

        if (phy_ts) {
                err = phy_hwtstamp_set(dev->phydev, cfg, extack);
                if (err) {
                        if (changed)
                                ops->ndo_hwtstamp_set(dev, &old_cfg, NULL);
                        return err;
                }
        }

        return 0;
}

static int dev_set_hwtstamp(struct net_device *dev, struct ifreq *ifr)
{
        const struct net_device_ops *ops = dev->netdev_ops;
        struct kernel_hwtstamp_config kernel_cfg = {};
        struct netlink_ext_ack extack = {};
        struct hwtstamp_config cfg;
        int err;

        if (copy_from_user(&cfg, ifr->ifr_data, sizeof(cfg)))
                return -EFAULT;

        hwtstamp_config_to_kernel(&kernel_cfg, &cfg);
        kernel_cfg.ifr = ifr;

        err = net_hwtstamp_validate(&kernel_cfg);
        if (err)
                return err;

        err = dsa_conduit_hwtstamp_validate(dev, &kernel_cfg, &extack);
        if (err) {
                if (extack._msg)
                        netdev_err(dev, "%s\n", extack._msg);
                return err;
        }

        if (!ops->ndo_hwtstamp_set)
                return dev_eth_ioctl(dev, ifr, SIOCSHWTSTAMP); /* legacy */

        if (!netif_device_present(dev))
                return -ENODEV;

        err = dev_set_hwtstamp_phylib(dev, &kernel_cfg, &extack);
        if (err)
                return err;

        /* The driver may have modified the configuration, so copy the
         * updated version of it back to user space
         */
        if (!kernel_cfg.copied_to_user) {
                hwtstamp_config_from_kernel(&cfg, &kernel_cfg);

                if (copy_to_user(ifr->ifr_data, &cfg, sizeof(cfg)))
                        return -EFAULT;
        }

        return 0;
}

static int generic_hwtstamp_ioctl_lower(struct net_device *dev, int cmd,
                                        struct kernel_hwtstamp_config *kernel_cfg)
{
        struct ifreq ifrr;
        int err;

        strscpy_pad(ifrr.ifr_name, dev->name, IFNAMSIZ);
        ifrr.ifr_ifru = kernel_cfg->ifr->ifr_ifru;

        err = dev_eth_ioctl(dev, &ifrr, cmd);
        if (err)
                return err;

        kernel_cfg->ifr->ifr_ifru = ifrr.ifr_ifru;
        kernel_cfg->copied_to_user = true;

        return 0;
}

int generic_hwtstamp_get_lower(struct net_device *dev,
                               struct kernel_hwtstamp_config *kernel_cfg)
{
        const struct net_device_ops *ops = dev->netdev_ops;

        if (!netif_device_present(dev))
                return -ENODEV;

        if (ops->ndo_hwtstamp_get)
                return dev_get_hwtstamp_phylib(dev, kernel_cfg);

        /* Legacy path: unconverted lower driver */
        return generic_hwtstamp_ioctl_lower(dev, SIOCGHWTSTAMP, kernel_cfg);
}
EXPORT_SYMBOL(generic_hwtstamp_get_lower);

int generic_hwtstamp_set_lower(struct net_device *dev,
                               struct kernel_hwtstamp_config *kernel_cfg,
                               struct netlink_ext_ack *extack)
{
        const struct net_device_ops *ops = dev->netdev_ops;

        if (!netif_device_present(dev))
                return -ENODEV;

        if (ops->ndo_hwtstamp_set)
                return dev_set_hwtstamp_phylib(dev, kernel_cfg, extack);

        /* Legacy path: unconverted lower driver */
        return generic_hwtstamp_ioctl_lower(dev, SIOCSHWTSTAMP, kernel_cfg);
}
EXPORT_SYMBOL(generic_hwtstamp_set_lower);

static int dev_siocbond(struct net_device *dev,
                        struct ifreq *ifr, unsigned int cmd)
{
        const struct net_device_ops *ops = dev->netdev_ops;

        if (ops->ndo_siocbond) {
                if (netif_device_present(dev))
                        return ops->ndo_siocbond(dev, ifr, cmd);
                else
                        return -ENODEV;
        }

        return -EOPNOTSUPP;
}

static int dev_siocdevprivate(struct net_device *dev, struct ifreq *ifr,
                              void __user *data, unsigned int cmd)
{
        const struct net_device_ops *ops = dev->netdev_ops;

        if (ops->ndo_siocdevprivate) {
                if (netif_device_present(dev))
                        return ops->ndo_siocdevprivate(dev, ifr, data, cmd);
                else
                        return -ENODEV;
        }

        return -EOPNOTSUPP;
}

static int dev_siocwandev(struct net_device *dev, struct if_settings *ifs)
{
        const struct net_device_ops *ops = dev->netdev_ops;

        if (ops->ndo_siocwandev) {
                if (netif_device_present(dev))
                        return ops->ndo_siocwandev(dev, ifs);
                else
                        return -ENODEV;
        }

        return -EOPNOTSUPP;
}

/*
 *        Perform the SIOCxIFxxx calls, inside rtnl_lock()
 */
static int dev_ifsioc(struct net *net, struct ifreq *ifr, void __user *data,
                      unsigned int cmd)
{
        int err;
        struct net_device *dev = __dev_get_by_name(net, ifr->ifr_name);
        const struct net_device_ops *ops;
        netdevice_tracker dev_tracker;

        if (!dev)
                return -ENODEV;

        ops = dev->netdev_ops;

        switch (cmd) {
        case SIOCSIFFLAGS:        /* Set interface flags */
                return dev_change_flags(dev, ifr->ifr_flags, NULL);

        case SIOCSIFMETRIC:        /* Set the metric on the interface
                                   (currently unused) */
                return -EOPNOTSUPP;

        case SIOCSIFMTU:        /* Set the MTU of a device */
                return dev_set_mtu(dev, ifr->ifr_mtu);

        case SIOCSIFHWADDR:
                if (dev->addr_len > sizeof(struct sockaddr))
                        return -EINVAL;
                return dev_set_mac_address_user(dev, &ifr->ifr_hwaddr, NULL);

        case SIOCSIFHWBROADCAST:
                if (ifr->ifr_hwaddr.sa_family != dev->type)
                        return -EINVAL;
                memcpy(dev->broadcast, ifr->ifr_hwaddr.sa_data,
                       min(sizeof(ifr->ifr_hwaddr.sa_data_min),
                           (size_t)dev->addr_len));
                call_netdevice_notifiers(NETDEV_CHANGEADDR, dev);
                return 0;

        case SIOCSIFMAP:
                return dev_setifmap(dev, ifr);

        case SIOCADDMULTI:
                if (!ops->ndo_set_rx_mode ||
                    ifr->ifr_hwaddr.sa_family != AF_UNSPEC)
                        return -EINVAL;
                if (!netif_device_present(dev))
                        return -ENODEV;
                return dev_mc_add_global(dev, ifr->ifr_hwaddr.sa_data);

        case SIOCDELMULTI:
                if (!ops->ndo_set_rx_mode ||
                    ifr->ifr_hwaddr.sa_family != AF_UNSPEC)
                        return -EINVAL;
                if (!netif_device_present(dev))
                        return -ENODEV;
                return dev_mc_del_global(dev, ifr->ifr_hwaddr.sa_data);

        case SIOCSIFTXQLEN:
                if (ifr->ifr_qlen < 0)
                        return -EINVAL;
                return dev_change_tx_queue_len(dev, ifr->ifr_qlen);

        case SIOCSIFNAME:
                ifr->ifr_newname[IFNAMSIZ-1] = '\0';
                return dev_change_name(dev, ifr->ifr_newname);

        case SIOCWANDEV:
                return dev_siocwandev(dev, &ifr->ifr_settings);

        case SIOCBRADDIF:
        case SIOCBRDELIF:
                if (!netif_device_present(dev))
                        return -ENODEV;
                if (!netif_is_bridge_master(dev))
                        return -EOPNOTSUPP;
                netdev_hold(dev, &dev_tracker, GFP_KERNEL);
                rtnl_unlock();
                err = br_ioctl_call(net, netdev_priv(dev), cmd, ifr, NULL);
                netdev_put(dev, &dev_tracker);
                rtnl_lock();
                return err;

        case SIOCDEVPRIVATE ... SIOCDEVPRIVATE + 15:
                return dev_siocdevprivate(dev, ifr, data, cmd);

        case SIOCSHWTSTAMP:
                return dev_set_hwtstamp(dev, ifr);

        case SIOCGHWTSTAMP:
                return dev_get_hwtstamp(dev, ifr);

        case SIOCGMIIPHY:
        case SIOCGMIIREG:
        case SIOCSMIIREG:
                return dev_eth_ioctl(dev, ifr, cmd);

        case SIOCBONDENSLAVE:
        case SIOCBONDRELEASE:
        case SIOCBONDSETHWADDR:
        case SIOCBONDSLAVEINFOQUERY:
        case SIOCBONDINFOQUERY:
        case SIOCBONDCHANGEACTIVE:
                return dev_siocbond(dev, ifr, cmd);

        /* Unknown ioctl */
        default:
                err = -EINVAL;
        }
        return err;
}

/**
 *        dev_load         - load a network module
 *        @net: the applicable net namespace
 *        @name: name of interface
 *
 *        If a network interface is not present and the process has suitable
 *        privileges this function loads the module. If module loading is not
 *        available in this kernel then it becomes a nop.
 */

void dev_load(struct net *net, const char *name)
{
        struct net_device *dev;
        int no_module;

        rcu_read_lock();
        dev = dev_get_by_name_rcu(net, name);
        rcu_read_unlock();

        no_module = !dev;
        if (no_module && capable(CAP_NET_ADMIN))
                no_module = request_module("netdev-%s", name);
        if (no_module && capable(CAP_SYS_MODULE))
                request_module("%s", name);
}
EXPORT_SYMBOL(dev_load);

/*
 *        This function handles all "interface"-type I/O control requests. The actual
 *        'doing' part of this is dev_ifsioc above.
 */

/**
 *        dev_ioctl        -        network device ioctl
 *        @net: the applicable net namespace
 *        @cmd: command to issue
 *        @ifr: pointer to a struct ifreq in user space
 *        @data: data exchanged with userspace
 *        @need_copyout: whether or not copy_to_user() should be called
 *
 *        Issue ioctl functions to devices. This is normally called by the
 *        user space syscall interfaces but can sometimes be useful for
 *        other purposes. The return value is the return from the syscall if
 *        positive or a negative errno code on error.
 */

int dev_ioctl(struct net *net, unsigned int cmd, struct ifreq *ifr,
              void __user *data, bool *need_copyout)
{
        int ret;
        char *colon;

        if (need_copyout)
                *need_copyout = true;
        if (cmd == SIOCGIFNAME)
                return dev_ifname(net, ifr);

        ifr->ifr_name[IFNAMSIZ-1] = 0;

        colon = strchr(ifr->ifr_name, ':');
        if (colon)
                *colon = 0;

        /*
         *        See which interface the caller is talking about.
         */

        switch (cmd) {
        case SIOCGIFHWADDR:
                dev_load(net, ifr->ifr_name);
                ret = dev_get_mac_address(&ifr->ifr_hwaddr, net, ifr->ifr_name);
                if (colon)
                        *colon = ':';
                return ret;
        /*
         *        These ioctl calls:
         *        - can be done by all.
         *        - atomic and do not require locking.
         *        - return a value
         */
        case SIOCGIFFLAGS:
        case SIOCGIFMETRIC:
        case SIOCGIFMTU:
        case SIOCGIFSLAVE:
        case SIOCGIFMAP:
        case SIOCGIFINDEX:
        case SIOCGIFTXQLEN:
                dev_load(net, ifr->ifr_name);
                rcu_read_lock();
                ret = dev_ifsioc_locked(net, ifr, cmd);
                rcu_read_unlock();
                if (colon)
                        *colon = ':';
                return ret;

        case SIOCETHTOOL:
                dev_load(net, ifr->ifr_name);
                ret = dev_ethtool(net, ifr, data);
                if (colon)
                        *colon = ':';
                return ret;

        /*
         *        These ioctl calls:
         *        - require superuser power.
         *        - require strict serialization.
         *        - return a value
         */
        case SIOCGMIIPHY:
        case SIOCGMIIREG:
        case SIOCSIFNAME:
                dev_load(net, ifr->ifr_name);
                if (!ns_capable(net->user_ns, CAP_NET_ADMIN))
                        return -EPERM;
                rtnl_lock();
                ret = dev_ifsioc(net, ifr, data, cmd);
                rtnl_unlock();
                if (colon)
                        *colon = ':';
                return ret;

        /*
         *        These ioctl calls:
         *        - require superuser power.
         *        - require strict serialization.
         *        - do not return a value
         */
        case SIOCSIFMAP:
        case SIOCSIFTXQLEN:
                if (!capable(CAP_NET_ADMIN))
                        return -EPERM;
                fallthrough;
        /*
         *        These ioctl calls:
         *        - require local superuser power.
         *        - require strict serialization.
         *        - do not return a value
         */
        case SIOCSIFFLAGS:
        case SIOCSIFMETRIC:
        case SIOCSIFMTU:
        case SIOCSIFHWADDR:
        case SIOCSIFSLAVE:
        case SIOCADDMULTI:
        case SIOCDELMULTI:
        case SIOCSIFHWBROADCAST:
        case SIOCSMIIREG:
        case SIOCBONDENSLAVE:
        case SIOCBONDRELEASE:
        case SIOCBONDSETHWADDR:
        case SIOCBONDCHANGEACTIVE:
        case SIOCBRADDIF:
        case SIOCBRDELIF:
        case SIOCSHWTSTAMP:
                if (!ns_capable(net->user_ns, CAP_NET_ADMIN))
                        return -EPERM;
                fallthrough;
        case SIOCBONDSLAVEINFOQUERY:
        case SIOCBONDINFOQUERY:
                dev_load(net, ifr->ifr_name);
                rtnl_lock();
                ret = dev_ifsioc(net, ifr, data, cmd);
                rtnl_unlock();
                if (need_copyout)
                        *need_copyout = false;
                return ret;

        case SIOCGIFMEM:
                /* Get the per device memory space. We can add this but
                 * currently do not support it */
        case SIOCSIFMEM:
                /* Set the per device memory buffer space.
                 * Not applicable in our case */
        case SIOCSIFLINK:
                return -ENOTTY;

        /*
         *        Unknown or private ioctl.
         */
        default:
                if (cmd == SIOCWANDEV ||
                    cmd == SIOCGHWTSTAMP ||
                    (cmd >= SIOCDEVPRIVATE &&
                     cmd <= SIOCDEVPRIVATE + 15)) {
                        dev_load(net, ifr->ifr_name);
                        rtnl_lock();
                        ret = dev_ifsioc(net, ifr, data, cmd);
                        rtnl_unlock();
                        return ret;
                }
                return -ENOTTY;
        }
}


























    7 

    7 




    6 

    6 




    7 
















    1 










    4 








    4 




    1 

    1 


    1 





















    1 





    1 










    4 




























   17 





    4 
























   20 



    3 




   17 



































































































   15 





   17 
   17 













    1 
    4 






















    8 










    2 










    6 



    6 








    5 


    4 

    2 



    2 



    1 






    1 

    1 







    6 






    9 


    1 
    8 



    2 



    1 




    1 





















    1 

































    5 



































    4 








    1 



























    8 
























    8 






















    8 




























    1 








    1 












































































































































































































































































































































































































































































































































































































































































































































































































































































































































































































    7 

















































    7 






    4 
    4 






    4 













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
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
1187
1188
1189
1190
1191
1192
1193
1194
1195
1196
1197
1198
1199
1200
1201
1202
1203
1204
1205
1206
1207
1208
1209
1210
1211
1212
1213
1214
1215
1216
1217
1218
1219
1220
1221
1222
1223
1224
1225
1226
1227
1228
1229
1230
1231
1232
1233
1234
1235
1236
1237
1238
1239
1240
1241
1242
1243
1244
1245
1246
1247
1248
1249
1250
1251
1252
1253
1254
1255
1256
1257
1258
1259
1260
1261
1262
1263
1264
1265
1266
1267
1268
1269
1270
1271
1272
1273
1274
1275
1276
1277
1278
1279
1280
1281
1282
1283
1284
1285
1286
1287
1288
1289
1290
1291
1292
1293
1294
1295
1296
1297
1298
1299
1300
1301
1302
1303
1304
1305
1306
1307
1308
1309
1310
1311
1312
1313
1314
1315
1316
1317
1318
1319
1320
1321
1322
1323
1324
1325
1326
1327
1328
1329
1330
1331
1332
1333
1334
1335
1336
1337
1338
1339
1340
1341
1342
1343
1344
1345
1346
1347
1348
1349
1350
1351
1352
1353
1354
1355
1356
1357
1358
1359
1360
1361
1362
1363
1364
1365
1366
1367
1368
1369
1370
1371
1372
1373
1374
1375
1376
1377
1378
1379
1380
1381
1382
1383
1384
1385
1386
1387
1388
1389
1390
1391
1392
1393
1394
1395
1396
1397
1398
1399
1400
1401
1402
1403
1404
1405
1406
1407
1408
1409
1410
1411
1412
1413
1414
1415
1416
1417
1418
1419
1420
1421
1422
1423
1424
1425
1426
1427
1428
1429
1430
1431
1432
1433
1434
1435
1436
1437
1438
1439
1440
1441
1442
1443
1444
1445
1446
1447
1448
1449
1450
1451
1452
1453
1454
1455
1456
1457
1458
1459
1460
1461
1462
1463
1464
1465
1466
1467
1468
1469
1470
1471
1472
1473
1474
1475
1476
1477
1478
1479
1480
1481
1482
1483
1484
1485
1486
1487
1488
1489
1490
1491
1492
1493
1494
1495
1496
1497
1498
1499
1500
1501
1502
1503
1504
1505
1506
1507
1508
1509
1510
1511
1512
1513
1514
1515
1516
1517
1518
1519
1520
1521
1522
1523
1524
1525
1526
1527
1528
1529
1530
1531
1532
1533
1534
1535
1536
1537
1538
1539
1540
1541
1542
1543
1544
1545
1546
1547
1548
1549
1550
1551
1552
1553
1554
1555
1556
1557
1558
1559
1560
1561
1562
1563
1564
1565
1566
1567
1568
1569
1570
1571
1572
1573
1574
1575
1576
1577
1578
1579
1580
1581
1582
1583
1584
1585
1586
1587
1588
1589
1590
1591
1592
1593
1594
1595
1596
1597
1598
1599
1600
1601
1602
1603
1604
1605
1606
1607
1608
1609
1610
1611
1612
1613
1614
1615
1616
1617
1618
1619
1620
1621
1622
1623
1624
1625
1626
1627
1628
1629
1630
1631
1632
1633
1634
1635
1636
1637
1638
1639
1640
1641
1642
1643
1644
1645
1646
1647
1648
1649
1650
1651
1652
1653
1654
1655
1656
1657
1658
1659
1660
1661
1662
1663
1664
1665
1666
1667
1668
1669
1670
1671
1672
1673
1674
1675
1676
1677
1678
1679
1680
1681
1682
1683
1684
1685
1686
1687
1688
1689
1690
1691
1692
1693
1694
1695
// SPDX-License-Identifier: GPL-2.0-or-later
/*
 * Copyright (C) 2011  Intel Corporation. All rights reserved.
 * Copyright (C) 2014 Marvell International Ltd.
 */

#define pr_fmt(fmt) "llcp: %s: " fmt, __func__

#include <linux/init.h>
#include <linux/kernel.h>
#include <linux/list.h>
#include <linux/nfc.h>

#include "nfc.h"
#include "llcp.h"

static u8 llcp_magic[3] = {0x46, 0x66, 0x6d};

static LIST_HEAD(llcp_devices);
/* Protects llcp_devices list */
static DEFINE_SPINLOCK(llcp_devices_lock);

static void nfc_llcp_rx_skb(struct nfc_llcp_local *local, struct sk_buff *skb);

void nfc_llcp_sock_link(struct llcp_sock_list *l, struct sock *sk)
{
        write_lock(&l->lock);
        sk_add_node(sk, &l->head);
        write_unlock(&l->lock);
}

void nfc_llcp_sock_unlink(struct llcp_sock_list *l, struct sock *sk)
{
        write_lock(&l->lock);
        sk_del_node_init(sk);
        write_unlock(&l->lock);
}

void nfc_llcp_socket_remote_param_init(struct nfc_llcp_sock *sock)
{
        sock->remote_rw = LLCP_DEFAULT_RW;
        sock->remote_miu = LLCP_MAX_MIU + 1;
}

static void nfc_llcp_socket_purge(struct nfc_llcp_sock *sock)
{
        struct nfc_llcp_local *local = sock->local;
        struct sk_buff *s, *tmp;

        skb_queue_purge(&sock->tx_queue);
        skb_queue_purge(&sock->tx_pending_queue);

        if (local == NULL)
                return;

        /* Search for local pending SKBs that are related to this socket */
        skb_queue_walk_safe(&local->tx_queue, s, tmp) {
                if (s->sk != &sock->sk)
                        continue;

                skb_unlink(s, &local->tx_queue);
                kfree_skb(s);
        }
}

static void nfc_llcp_socket_release(struct nfc_llcp_local *local, bool device,
                                    int err)
{
        struct sock *sk;
        struct hlist_node *tmp;
        struct nfc_llcp_sock *llcp_sock;

        skb_queue_purge(&local->tx_queue);

        write_lock(&local->sockets.lock);

        sk_for_each_safe(sk, tmp, &local->sockets.head) {
                llcp_sock = nfc_llcp_sock(sk);

                bh_lock_sock(sk);

                nfc_llcp_socket_purge(llcp_sock);

                if (sk->sk_state == LLCP_CONNECTED)
                        nfc_put_device(llcp_sock->dev);

                if (sk->sk_state == LLCP_LISTEN) {
                        struct nfc_llcp_sock *lsk, *n;
                        struct sock *accept_sk;

                        list_for_each_entry_safe(lsk, n,
                                                 &llcp_sock->accept_queue,
                                                 accept_queue) {
                                accept_sk = &lsk->sk;
                                bh_lock_sock(accept_sk);

                                nfc_llcp_accept_unlink(accept_sk);

                                if (err)
                                        accept_sk->sk_err = err;
                                accept_sk->sk_state = LLCP_CLOSED;
                                accept_sk->sk_state_change(sk);

                                bh_unlock_sock(accept_sk);
                        }
                }

                if (err)
                        sk->sk_err = err;
                sk->sk_state = LLCP_CLOSED;
                sk->sk_state_change(sk);

                bh_unlock_sock(sk);

                sk_del_node_init(sk);
        }

        write_unlock(&local->sockets.lock);

        /* If we still have a device, we keep the RAW sockets alive */
        if (device == true)
                return;

        write_lock(&local->raw_sockets.lock);

        sk_for_each_safe(sk, tmp, &local->raw_sockets.head) {
                llcp_sock = nfc_llcp_sock(sk);

                bh_lock_sock(sk);

                nfc_llcp_socket_purge(llcp_sock);

                if (err)
                        sk->sk_err = err;
                sk->sk_state = LLCP_CLOSED;
                sk->sk_state_change(sk);

                bh_unlock_sock(sk);

                sk_del_node_init(sk);
        }

        write_unlock(&local->raw_sockets.lock);
}

static struct nfc_llcp_local *nfc_llcp_local_get(struct nfc_llcp_local *local)
{
        /* Since using nfc_llcp_local may result in usage of nfc_dev, whenever
         * we hold a reference to local, we also need to hold a reference to
         * the device to avoid UAF.
         */
        if (!nfc_get_device(local->dev->idx))
                return NULL;

        kref_get(&local->ref);

        return local;
}

static void local_cleanup(struct nfc_llcp_local *local)
{
        nfc_llcp_socket_release(local, false, ENXIO);
        del_timer_sync(&local->link_timer);
        skb_queue_purge(&local->tx_queue);
        cancel_work_sync(&local->tx_work);
        cancel_work_sync(&local->rx_work);
        cancel_work_sync(&local->timeout_work);
        kfree_skb(local->rx_pending);
        local->rx_pending = NULL;
        del_timer_sync(&local->sdreq_timer);
        cancel_work_sync(&local->sdreq_timeout_work);
        nfc_llcp_free_sdp_tlv_list(&local->pending_sdreqs);
}

static void local_release(struct kref *ref)
{
        struct nfc_llcp_local *local;

        local = container_of(ref, struct nfc_llcp_local, ref);

        local_cleanup(local);
        kfree(local);
}

int nfc_llcp_local_put(struct nfc_llcp_local *local)
{
        struct nfc_dev *dev;
        int ret;

        if (local == NULL)
                return 0;

        dev = local->dev;

        ret = kref_put(&local->ref, local_release);
        nfc_put_device(dev);

        return ret;
}

static struct nfc_llcp_sock *nfc_llcp_sock_get(struct nfc_llcp_local *local,
                                               u8 ssap, u8 dsap)
{
        struct sock *sk;
        struct nfc_llcp_sock *llcp_sock, *tmp_sock;

        pr_debug("ssap dsap %d %d\n", ssap, dsap);

        if (ssap == 0 && dsap == 0)
                return NULL;

        read_lock(&local->sockets.lock);

        llcp_sock = NULL;

        sk_for_each(sk, &local->sockets.head) {
                tmp_sock = nfc_llcp_sock(sk);

                if (tmp_sock->ssap == ssap && tmp_sock->dsap == dsap) {
                        llcp_sock = tmp_sock;
                        sock_hold(&llcp_sock->sk);
                        break;
                }
        }

        read_unlock(&local->sockets.lock);

        return llcp_sock;
}

static void nfc_llcp_sock_put(struct nfc_llcp_sock *sock)
{
        sock_put(&sock->sk);
}

static void nfc_llcp_timeout_work(struct work_struct *work)
{
        struct nfc_llcp_local *local = container_of(work, struct nfc_llcp_local,
                                                    timeout_work);

        nfc_dep_link_down(local->dev);
}

static void nfc_llcp_symm_timer(struct timer_list *t)
{
        struct nfc_llcp_local *local = from_timer(local, t, link_timer);

        pr_err("SYMM timeout\n");

        schedule_work(&local->timeout_work);
}

static void nfc_llcp_sdreq_timeout_work(struct work_struct *work)
{
        unsigned long time;
        HLIST_HEAD(nl_sdres_list);
        struct hlist_node *n;
        struct nfc_llcp_sdp_tlv *sdp;
        struct nfc_llcp_local *local = container_of(work, struct nfc_llcp_local,
                                                    sdreq_timeout_work);

        mutex_lock(&local->sdreq_lock);

        time = jiffies - msecs_to_jiffies(3 * local->remote_lto);

        hlist_for_each_entry_safe(sdp, n, &local->pending_sdreqs, node) {
                if (time_after(sdp->time, time))
                        continue;

                sdp->sap = LLCP_SDP_UNBOUND;

                hlist_del(&sdp->node);

                hlist_add_head(&sdp->node, &nl_sdres_list);
        }

        if (!hlist_empty(&local->pending_sdreqs))
                mod_timer(&local->sdreq_timer,
                          jiffies + msecs_to_jiffies(3 * local->remote_lto));

        mutex_unlock(&local->sdreq_lock);

        if (!hlist_empty(&nl_sdres_list))
                nfc_genl_llc_send_sdres(local->dev, &nl_sdres_list);
}

static void nfc_llcp_sdreq_timer(struct timer_list *t)
{
        struct nfc_llcp_local *local = from_timer(local, t, sdreq_timer);

        schedule_work(&local->sdreq_timeout_work);
}

struct nfc_llcp_local *nfc_llcp_find_local(struct nfc_dev *dev)
{
        struct nfc_llcp_local *local;
        struct nfc_llcp_local *res = NULL;

        spin_lock(&llcp_devices_lock);
        list_for_each_entry(local, &llcp_devices, list)
                if (local->dev == dev) {
                        res = nfc_llcp_local_get(local);
                        break;
                }
        spin_unlock(&llcp_devices_lock);

        return res;
}

static struct nfc_llcp_local *nfc_llcp_remove_local(struct nfc_dev *dev)
{
        struct nfc_llcp_local *local, *tmp;

        spin_lock(&llcp_devices_lock);
        list_for_each_entry_safe(local, tmp, &llcp_devices, list)
                if (local->dev == dev) {
                        list_del(&local->list);
                        spin_unlock(&llcp_devices_lock);
                        return local;
                }
        spin_unlock(&llcp_devices_lock);

        pr_warn("Shutting down device not found\n");

        return NULL;
}

static char *wks[] = {
        NULL,
        NULL, /* SDP */
        "urn:nfc:sn:ip",
        "urn:nfc:sn:obex",
        "urn:nfc:sn:snep",
};

static int nfc_llcp_wks_sap(const char *service_name, size_t service_name_len)
{
        int sap, num_wks;

        pr_debug("%s\n", service_name);

        if (service_name == NULL)
                return -EINVAL;

        num_wks = ARRAY_SIZE(wks);

        for (sap = 0; sap < num_wks; sap++) {
                if (wks[sap] == NULL)
                        continue;

                if (strncmp(wks[sap], service_name, service_name_len) == 0)
                        return sap;
        }

        return -EINVAL;
}

static
struct nfc_llcp_sock *nfc_llcp_sock_from_sn(struct nfc_llcp_local *local,
                                            const u8 *sn, size_t sn_len,
                                            bool needref)
{
        struct sock *sk;
        struct nfc_llcp_sock *llcp_sock, *tmp_sock;

        pr_debug("sn %zd %p\n", sn_len, sn);

        if (sn == NULL || sn_len == 0)
                return NULL;

        read_lock(&local->sockets.lock);

        llcp_sock = NULL;

        sk_for_each(sk, &local->sockets.head) {
                tmp_sock = nfc_llcp_sock(sk);

                pr_debug("llcp sock %p\n", tmp_sock);

                if (tmp_sock->sk.sk_type == SOCK_STREAM &&
                    tmp_sock->sk.sk_state != LLCP_LISTEN)
                        continue;

                if (tmp_sock->sk.sk_type == SOCK_DGRAM &&
                    tmp_sock->sk.sk_state != LLCP_BOUND)
                        continue;

                if (tmp_sock->service_name == NULL ||
                    tmp_sock->service_name_len == 0)
                        continue;

                if (tmp_sock->service_name_len != sn_len)
                        continue;

                if (memcmp(sn, tmp_sock->service_name, sn_len) == 0) {
                        llcp_sock = tmp_sock;
                        if (needref)
                                sock_hold(&llcp_sock->sk);
                        break;
                }
        }

        read_unlock(&local->sockets.lock);

        pr_debug("Found llcp sock %p\n", llcp_sock);

        return llcp_sock;
}

u8 nfc_llcp_get_sdp_ssap(struct nfc_llcp_local *local,
                         struct nfc_llcp_sock *sock)
{
        mutex_lock(&local->sdp_lock);

        if (sock->service_name != NULL && sock->service_name_len > 0) {
                int ssap = nfc_llcp_wks_sap(sock->service_name,
                                            sock->service_name_len);

                if (ssap > 0) {
                        pr_debug("WKS %d\n", ssap);

                        /* This is a WKS, let's check if it's free */
                        if (test_bit(ssap, &local->local_wks)) {
                                mutex_unlock(&local->sdp_lock);

                                return LLCP_SAP_MAX;
                        }

                        set_bit(ssap, &local->local_wks);
                        mutex_unlock(&local->sdp_lock);

                        return ssap;
                }

                /*
                 * Check if there already is a non WKS socket bound
                 * to this service name.
                 */
                if (nfc_llcp_sock_from_sn(local, sock->service_name,
                                          sock->service_name_len,
                                          false) != NULL) {
                        mutex_unlock(&local->sdp_lock);

                        return LLCP_SAP_MAX;
                }

                mutex_unlock(&local->sdp_lock);

                return LLCP_SDP_UNBOUND;

        } else if (sock->ssap != 0 && sock->ssap < LLCP_WKS_NUM_SAP) {
                if (!test_bit(sock->ssap, &local->local_wks)) {
                        set_bit(sock->ssap, &local->local_wks);
                        mutex_unlock(&local->sdp_lock);

                        return sock->ssap;
                }
        }

        mutex_unlock(&local->sdp_lock);

        return LLCP_SAP_MAX;
}

u8 nfc_llcp_get_local_ssap(struct nfc_llcp_local *local)
{
        u8 local_ssap;

        mutex_lock(&local->sdp_lock);

        local_ssap = find_first_zero_bit(&local->local_sap, LLCP_LOCAL_NUM_SAP);
        if (local_ssap == LLCP_LOCAL_NUM_SAP) {
                mutex_unlock(&local->sdp_lock);
                return LLCP_SAP_MAX;
        }

        set_bit(local_ssap, &local->local_sap);

        mutex_unlock(&local->sdp_lock);

        return local_ssap + LLCP_LOCAL_SAP_OFFSET;
}

void nfc_llcp_put_ssap(struct nfc_llcp_local *local, u8 ssap)
{
        u8 local_ssap;
        unsigned long *sdp;

        if (ssap < LLCP_WKS_NUM_SAP) {
                local_ssap = ssap;
                sdp = &local->local_wks;
        } else if (ssap < LLCP_LOCAL_NUM_SAP) {
                atomic_t *client_cnt;

                local_ssap = ssap - LLCP_WKS_NUM_SAP;
                sdp = &local->local_sdp;
                client_cnt = &local->local_sdp_cnt[local_ssap];

                pr_debug("%d clients\n", atomic_read(client_cnt));

                mutex_lock(&local->sdp_lock);

                if (atomic_dec_and_test(client_cnt)) {
                        struct nfc_llcp_sock *l_sock;

                        pr_debug("No more clients for SAP %d\n", ssap);

                        clear_bit(local_ssap, sdp);

                        /* Find the listening sock and set it back to UNBOUND */
                        l_sock = nfc_llcp_sock_get(local, ssap, LLCP_SAP_SDP);
                        if (l_sock) {
                                l_sock->ssap = LLCP_SDP_UNBOUND;
                                nfc_llcp_sock_put(l_sock);
                        }
                }

                mutex_unlock(&local->sdp_lock);

                return;
        } else if (ssap < LLCP_MAX_SAP) {
                local_ssap = ssap - LLCP_LOCAL_NUM_SAP;
                sdp = &local->local_sap;
        } else {
                return;
        }

        mutex_lock(&local->sdp_lock);

        clear_bit(local_ssap, sdp);

        mutex_unlock(&local->sdp_lock);
}

static u8 nfc_llcp_reserve_sdp_ssap(struct nfc_llcp_local *local)
{
        u8 ssap;

        mutex_lock(&local->sdp_lock);

        ssap = find_first_zero_bit(&local->local_sdp, LLCP_SDP_NUM_SAP);
        if (ssap == LLCP_SDP_NUM_SAP) {
                mutex_unlock(&local->sdp_lock);

                return LLCP_SAP_MAX;
        }

        pr_debug("SDP ssap %d\n", LLCP_WKS_NUM_SAP + ssap);

        set_bit(ssap, &local->local_sdp);

        mutex_unlock(&local->sdp_lock);

        return LLCP_WKS_NUM_SAP + ssap;
}

static int nfc_llcp_build_gb(struct nfc_llcp_local *local)
{
        u8 *gb_cur, version, version_length;
        u8 lto_length, wks_length, miux_length;
        const u8 *version_tlv = NULL, *lto_tlv = NULL,
           *wks_tlv = NULL, *miux_tlv = NULL;
        __be16 wks = cpu_to_be16(local->local_wks);
        u8 gb_len = 0;
        int ret = 0;

        version = LLCP_VERSION_11;
        version_tlv = nfc_llcp_build_tlv(LLCP_TLV_VERSION, &version,
                                         1, &version_length);
        if (!version_tlv) {
                ret = -ENOMEM;
                goto out;
        }
        gb_len += version_length;

        lto_tlv = nfc_llcp_build_tlv(LLCP_TLV_LTO, &local->lto, 1, &lto_length);
        if (!lto_tlv) {
                ret = -ENOMEM;
                goto out;
        }
        gb_len += lto_length;

        pr_debug("Local wks 0x%lx\n", local->local_wks);
        wks_tlv = nfc_llcp_build_tlv(LLCP_TLV_WKS, (u8 *)&wks, 2, &wks_length);
        if (!wks_tlv) {
                ret = -ENOMEM;
                goto out;
        }
        gb_len += wks_length;

        miux_tlv = nfc_llcp_build_tlv(LLCP_TLV_MIUX, (u8 *)&local->miux, 0,
                                      &miux_length);
        if (!miux_tlv) {
                ret = -ENOMEM;
                goto out;
        }
        gb_len += miux_length;

        gb_len += ARRAY_SIZE(llcp_magic);

        if (gb_len > NFC_MAX_GT_LEN) {
                ret = -EINVAL;
                goto out;
        }

        gb_cur = local->gb;

        memcpy(gb_cur, llcp_magic, ARRAY_SIZE(llcp_magic));
        gb_cur += ARRAY_SIZE(llcp_magic);

        memcpy(gb_cur, version_tlv, version_length);
        gb_cur += version_length;

        memcpy(gb_cur, lto_tlv, lto_length);
        gb_cur += lto_length;

        memcpy(gb_cur, wks_tlv, wks_length);
        gb_cur += wks_length;

        memcpy(gb_cur, miux_tlv, miux_length);
        gb_cur += miux_length;

        local->gb_len = gb_len;

out:
        kfree(version_tlv);
        kfree(lto_tlv);
        kfree(wks_tlv);
        kfree(miux_tlv);

        return ret;
}

u8 *nfc_llcp_general_bytes(struct nfc_dev *dev, size_t *general_bytes_len)
{
        struct nfc_llcp_local *local;

        local = nfc_llcp_find_local(dev);
        if (local == NULL) {
                *general_bytes_len = 0;
                return NULL;
        }

        nfc_llcp_build_gb(local);

        *general_bytes_len = local->gb_len;

        nfc_llcp_local_put(local);

        return local->gb;
}

int nfc_llcp_set_remote_gb(struct nfc_dev *dev, const u8 *gb, u8 gb_len)
{
        struct nfc_llcp_local *local;
        int err;

        if (gb_len < 3 || gb_len > NFC_MAX_GT_LEN)
                return -EINVAL;

        local = nfc_llcp_find_local(dev);
        if (local == NULL) {
                pr_err("No LLCP device\n");
                return -ENODEV;
        }

        memset(local->remote_gb, 0, NFC_MAX_GT_LEN);
        memcpy(local->remote_gb, gb, gb_len);
        local->remote_gb_len = gb_len;

        if (memcmp(local->remote_gb, llcp_magic, 3)) {
                pr_err("MAC does not support LLCP\n");
                err = -EINVAL;
                goto out;
        }

        err = nfc_llcp_parse_gb_tlv(local,
                                     &local->remote_gb[3],
                                     local->remote_gb_len - 3);
out:
        nfc_llcp_local_put(local);
        return err;
}

static u8 nfc_llcp_dsap(const struct sk_buff *pdu)
{
        return (pdu->data[0] & 0xfc) >> 2;
}

static u8 nfc_llcp_ptype(const struct sk_buff *pdu)
{
        return ((pdu->data[0] & 0x03) << 2) | ((pdu->data[1] & 0xc0) >> 6);
}

static u8 nfc_llcp_ssap(const struct sk_buff *pdu)
{
        return pdu->data[1] & 0x3f;
}

static u8 nfc_llcp_ns(const struct sk_buff *pdu)
{
        return pdu->data[2] >> 4;
}

static u8 nfc_llcp_nr(const struct sk_buff *pdu)
{
        return pdu->data[2] & 0xf;
}

static void nfc_llcp_set_nrns(struct nfc_llcp_sock *sock, struct sk_buff *pdu)
{
        pdu->data[2] = (sock->send_n << 4) | (sock->recv_n);
        sock->send_n = (sock->send_n + 1) % 16;
        sock->recv_ack_n = (sock->recv_n - 1) % 16;
}

void nfc_llcp_send_to_raw_sock(struct nfc_llcp_local *local,
                               struct sk_buff *skb, u8 direction)
{
        struct sk_buff *skb_copy = NULL, *nskb;
        struct sock *sk;
        u8 *data;

        read_lock(&local->raw_sockets.lock);

        sk_for_each(sk, &local->raw_sockets.head) {
                if (sk->sk_state != LLCP_BOUND)
                        continue;

                if (skb_copy == NULL) {
                        skb_copy = __pskb_copy_fclone(skb, NFC_RAW_HEADER_SIZE,
                                                      GFP_ATOMIC, true);

                        if (skb_copy == NULL)
                                continue;

                        data = skb_push(skb_copy, NFC_RAW_HEADER_SIZE);

                        data[0] = local->dev ? local->dev->idx : 0xFF;
                        data[1] = direction & 0x01;
                        data[1] |= (RAW_PAYLOAD_LLCP << 1);
                }

                nskb = skb_clone(skb_copy, GFP_ATOMIC);
                if (!nskb)
                        continue;

                if (sock_queue_rcv_skb(sk, nskb))
                        kfree_skb(nskb);
        }

        read_unlock(&local->raw_sockets.lock);

        kfree_skb(skb_copy);
}

static void nfc_llcp_tx_work(struct work_struct *work)
{
        struct nfc_llcp_local *local = container_of(work, struct nfc_llcp_local,
                                                    tx_work);
        struct sk_buff *skb;
        struct sock *sk;
        struct nfc_llcp_sock *llcp_sock;

        skb = skb_dequeue(&local->tx_queue);
        if (skb != NULL) {
                sk = skb->sk;
                llcp_sock = nfc_llcp_sock(sk);

                if (llcp_sock == NULL && nfc_llcp_ptype(skb) == LLCP_PDU_I) {
                        kfree_skb(skb);
                        nfc_llcp_send_symm(local->dev);
                } else if (llcp_sock && !llcp_sock->remote_ready) {
                        skb_queue_head(&local->tx_queue, skb);
                        nfc_llcp_send_symm(local->dev);
                } else {
                        struct sk_buff *copy_skb = NULL;
                        u8 ptype = nfc_llcp_ptype(skb);
                        int ret;

                        pr_debug("Sending pending skb\n");
                        print_hex_dump_debug("LLCP Tx: ", DUMP_PREFIX_OFFSET,
                                             16, 1, skb->data, skb->len, true);

                        if (ptype == LLCP_PDU_I)
                                copy_skb = skb_copy(skb, GFP_ATOMIC);

                        __net_timestamp(skb);

                        nfc_llcp_send_to_raw_sock(local, skb,
                                                  NFC_DIRECTION_TX);

                        ret = nfc_data_exchange(local->dev, local->target_idx,
                                                skb, nfc_llcp_recv, local);

                        if (ret) {
                                kfree_skb(copy_skb);
                                goto out;
                        }

                        if (ptype == LLCP_PDU_I && copy_skb)
                                skb_queue_tail(&llcp_sock->tx_pending_queue,
                                               copy_skb);
                }
        } else {
                nfc_llcp_send_symm(local->dev);
        }

out:
        mod_timer(&local->link_timer,
                  jiffies + msecs_to_jiffies(2 * local->remote_lto));
}

static struct nfc_llcp_sock *nfc_llcp_connecting_sock_get(struct nfc_llcp_local *local,
                                                          u8 ssap)
{
        struct sock *sk;
        struct nfc_llcp_sock *llcp_sock;

        read_lock(&local->connecting_sockets.lock);

        sk_for_each(sk, &local->connecting_sockets.head) {
                llcp_sock = nfc_llcp_sock(sk);

                if (llcp_sock->ssap == ssap) {
                        sock_hold(&llcp_sock->sk);
                        goto out;
                }
        }

        llcp_sock = NULL;

out:
        read_unlock(&local->connecting_sockets.lock);

        return llcp_sock;
}

static struct nfc_llcp_sock *nfc_llcp_sock_get_sn(struct nfc_llcp_local *local,
                                                  const u8 *sn, size_t sn_len)
{
        return nfc_llcp_sock_from_sn(local, sn, sn_len, true);
}

static const u8 *nfc_llcp_connect_sn(const struct sk_buff *skb, size_t *sn_len)
{
        u8 type, length;
        const u8 *tlv = &skb->data[2];
        size_t tlv_array_len = skb->len - LLCP_HEADER_SIZE, offset = 0;

        while (offset < tlv_array_len) {
                type = tlv[0];
                length = tlv[1];

                pr_debug("type 0x%x length %d\n", type, length);

                if (type == LLCP_TLV_SN) {
                        *sn_len = length;
                        return &tlv[2];
                }

                offset += length + 2;
                tlv += length + 2;
        }

        return NULL;
}

static void nfc_llcp_recv_ui(struct nfc_llcp_local *local,
                             struct sk_buff *skb)
{
        struct nfc_llcp_sock *llcp_sock;
        struct nfc_llcp_ui_cb *ui_cb;
        u8 dsap, ssap;

        dsap = nfc_llcp_dsap(skb);
        ssap = nfc_llcp_ssap(skb);

        ui_cb = nfc_llcp_ui_skb_cb(skb);
        ui_cb->dsap = dsap;
        ui_cb->ssap = ssap;

        pr_debug("%d %d\n", dsap, ssap);

        /* We're looking for a bound socket, not a client one */
        llcp_sock = nfc_llcp_sock_get(local, dsap, LLCP_SAP_SDP);
        if (llcp_sock == NULL || llcp_sock->sk.sk_type != SOCK_DGRAM)
                return;

        /* There is no sequence with UI frames */
        skb_pull(skb, LLCP_HEADER_SIZE);
        if (!sock_queue_rcv_skb(&llcp_sock->sk, skb)) {
                /*
                 * UI frames will be freed from the socket layer, so we
                 * need to keep them alive until someone receives them.
                 */
                skb_get(skb);
        } else {
                pr_err("Receive queue is full\n");
        }

        nfc_llcp_sock_put(llcp_sock);
}

static void nfc_llcp_recv_connect(struct nfc_llcp_local *local,
                                  const struct sk_buff *skb)
{
        struct sock *new_sk, *parent;
        struct nfc_llcp_sock *sock, *new_sock;
        u8 dsap, ssap, reason;

        dsap = nfc_llcp_dsap(skb);
        ssap = nfc_llcp_ssap(skb);

        pr_debug("%d %d\n", dsap, ssap);

        if (dsap != LLCP_SAP_SDP) {
                sock = nfc_llcp_sock_get(local, dsap, LLCP_SAP_SDP);
                if (sock == NULL || sock->sk.sk_state != LLCP_LISTEN) {
                        reason = LLCP_DM_NOBOUND;
                        goto fail;
                }
        } else {
                const u8 *sn;
                size_t sn_len;

                sn = nfc_llcp_connect_sn(skb, &sn_len);
                if (sn == NULL) {
                        reason = LLCP_DM_NOBOUND;
                        goto fail;
                }

                pr_debug("Service name length %zu\n", sn_len);

                sock = nfc_llcp_sock_get_sn(local, sn, sn_len);
                if (sock == NULL) {
                        reason = LLCP_DM_NOBOUND;
                        goto fail;
                }
        }

        lock_sock(&sock->sk);

        parent = &sock->sk;

        if (sk_acceptq_is_full(parent)) {
                reason = LLCP_DM_REJ;
                release_sock(&sock->sk);
                sock_put(&sock->sk);
                goto fail;
        }

        if (sock->ssap == LLCP_SDP_UNBOUND) {
                u8 ssap = nfc_llcp_reserve_sdp_ssap(local);

                pr_debug("First client, reserving %d\n", ssap);

                if (ssap == LLCP_SAP_MAX) {
                        reason = LLCP_DM_REJ;
                        release_sock(&sock->sk);
                        sock_put(&sock->sk);
                        goto fail;
                }

                sock->ssap = ssap;
        }

        new_sk = nfc_llcp_sock_alloc(NULL, parent->sk_type, GFP_ATOMIC, 0);
        if (new_sk == NULL) {
                reason = LLCP_DM_REJ;
                release_sock(&sock->sk);
                sock_put(&sock->sk);
                goto fail;
        }

        new_sock = nfc_llcp_sock(new_sk);

        new_sock->local = nfc_llcp_local_get(local);
        if (!new_sock->local) {
                reason = LLCP_DM_REJ;
                sock_put(&new_sock->sk);
                release_sock(&sock->sk);
                sock_put(&sock->sk);
                goto fail;
        }

        new_sock->dev = local->dev;
        new_sock->rw = sock->rw;
        new_sock->miux = sock->miux;
        new_sock->nfc_protocol = sock->nfc_protocol;
        new_sock->dsap = ssap;
        new_sock->target_idx = local->target_idx;
        new_sock->parent = parent;
        new_sock->ssap = sock->ssap;
        if (sock->ssap < LLCP_LOCAL_NUM_SAP && sock->ssap >= LLCP_WKS_NUM_SAP) {
                atomic_t *client_count;

                pr_debug("reserved_ssap %d for %p\n", sock->ssap, new_sock);

                client_count =
                        &local->local_sdp_cnt[sock->ssap - LLCP_WKS_NUM_SAP];

                atomic_inc(client_count);
                new_sock->reserved_ssap = sock->ssap;
        }

        nfc_llcp_parse_connection_tlv(new_sock, &skb->data[LLCP_HEADER_SIZE],
                                      skb->len - LLCP_HEADER_SIZE);

        pr_debug("new sock %p sk %p\n", new_sock, &new_sock->sk);

        nfc_llcp_sock_link(&local->sockets, new_sk);

        nfc_llcp_accept_enqueue(&sock->sk, new_sk);

        nfc_get_device(local->dev->idx);

        new_sk->sk_state = LLCP_CONNECTED;

        /* Wake the listening processes */
        parent->sk_data_ready(parent);

        /* Send CC */
        nfc_llcp_send_cc(new_sock);

        release_sock(&sock->sk);
        sock_put(&sock->sk);

        return;

fail:
        /* Send DM */
        nfc_llcp_send_dm(local, dsap, ssap, reason);
}

int nfc_llcp_queue_i_frames(struct nfc_llcp_sock *sock)
{
        int nr_frames = 0;
        struct nfc_llcp_local *local = sock->local;

        pr_debug("Remote ready %d tx queue len %d remote rw %d",
                 sock->remote_ready, skb_queue_len(&sock->tx_pending_queue),
                 sock->remote_rw);

        /* Try to queue some I frames for transmission */
        while (sock->remote_ready &&
               skb_queue_len(&sock->tx_pending_queue) < sock->remote_rw) {
                struct sk_buff *pdu;

                pdu = skb_dequeue(&sock->tx_queue);
                if (pdu == NULL)
                        break;

                /* Update N(S)/N(R) */
                nfc_llcp_set_nrns(sock, pdu);

                skb_queue_tail(&local->tx_queue, pdu);
                nr_frames++;
        }

        return nr_frames;
}

static void nfc_llcp_recv_hdlc(struct nfc_llcp_local *local,
                               struct sk_buff *skb)
{
        struct nfc_llcp_sock *llcp_sock;
        struct sock *sk;
        u8 dsap, ssap, ptype, ns, nr;

        ptype = nfc_llcp_ptype(skb);
        dsap = nfc_llcp_dsap(skb);
        ssap = nfc_llcp_ssap(skb);
        ns = nfc_llcp_ns(skb);
        nr = nfc_llcp_nr(skb);

        pr_debug("%d %d R %d S %d\n", dsap, ssap, nr, ns);

        llcp_sock = nfc_llcp_sock_get(local, dsap, ssap);
        if (llcp_sock == NULL) {
                nfc_llcp_send_dm(local, dsap, ssap, LLCP_DM_NOCONN);
                return;
        }

        sk = &llcp_sock->sk;
        lock_sock(sk);
        if (sk->sk_state == LLCP_CLOSED) {
                release_sock(sk);
                nfc_llcp_sock_put(llcp_sock);
        }

        /* Pass the payload upstream */
        if (ptype == LLCP_PDU_I) {
                pr_debug("I frame, queueing on %p\n", &llcp_sock->sk);

                if (ns == llcp_sock->recv_n)
                        llcp_sock->recv_n = (llcp_sock->recv_n + 1) % 16;
                else
                        pr_err("Received out of sequence I PDU\n");

                skb_pull(skb, LLCP_HEADER_SIZE + LLCP_SEQUENCE_SIZE);
                if (!sock_queue_rcv_skb(&llcp_sock->sk, skb)) {
                        /*
                         * I frames will be freed from the socket layer, so we
                         * need to keep them alive until someone receives them.
                         */
                        skb_get(skb);
                } else {
                        pr_err("Receive queue is full\n");
                }
        }

        /* Remove skbs from the pending queue */
        if (llcp_sock->send_ack_n != nr) {
                struct sk_buff *s, *tmp;
                u8 n;

                llcp_sock->send_ack_n = nr;

                /* Remove and free all skbs until ns == nr */
                skb_queue_walk_safe(&llcp_sock->tx_pending_queue, s, tmp) {
                        n = nfc_llcp_ns(s);

                        skb_unlink(s, &llcp_sock->tx_pending_queue);
                        kfree_skb(s);

                        if (n == nr)
                                break;
                }

                /* Re-queue the remaining skbs for transmission */
                skb_queue_reverse_walk_safe(&llcp_sock->tx_pending_queue,
                                            s, tmp) {
                        skb_unlink(s, &llcp_sock->tx_pending_queue);
                        skb_queue_head(&local->tx_queue, s);
                }
        }

        if (ptype == LLCP_PDU_RR)
                llcp_sock->remote_ready = true;
        else if (ptype == LLCP_PDU_RNR)
                llcp_sock->remote_ready = false;

        if (nfc_llcp_queue_i_frames(llcp_sock) == 0 && ptype == LLCP_PDU_I)
                nfc_llcp_send_rr(llcp_sock);

        release_sock(sk);
        nfc_llcp_sock_put(llcp_sock);
}

static void nfc_llcp_recv_disc(struct nfc_llcp_local *local,
                               const struct sk_buff *skb)
{
        struct nfc_llcp_sock *llcp_sock;
        struct sock *sk;
        u8 dsap, ssap;

        dsap = nfc_llcp_dsap(skb);
        ssap = nfc_llcp_ssap(skb);

        if ((dsap == 0) && (ssap == 0)) {
                pr_debug("Connection termination");
                nfc_dep_link_down(local->dev);
                return;
        }

        llcp_sock = nfc_llcp_sock_get(local, dsap, ssap);
        if (llcp_sock == NULL) {
                nfc_llcp_send_dm(local, dsap, ssap, LLCP_DM_NOCONN);
                return;
        }

        sk = &llcp_sock->sk;
        lock_sock(sk);

        nfc_llcp_socket_purge(llcp_sock);

        if (sk->sk_state == LLCP_CLOSED) {
                release_sock(sk);
                nfc_llcp_sock_put(llcp_sock);
        }

        if (sk->sk_state == LLCP_CONNECTED) {
                nfc_put_device(local->dev);
                sk->sk_state = LLCP_CLOSED;
                sk->sk_state_change(sk);
        }

        nfc_llcp_send_dm(local, dsap, ssap, LLCP_DM_DISC);

        release_sock(sk);
        nfc_llcp_sock_put(llcp_sock);
}

static void nfc_llcp_recv_cc(struct nfc_llcp_local *local,
                             const struct sk_buff *skb)
{
        struct nfc_llcp_sock *llcp_sock;
        struct sock *sk;
        u8 dsap, ssap;

        dsap = nfc_llcp_dsap(skb);
        ssap = nfc_llcp_ssap(skb);

        llcp_sock = nfc_llcp_connecting_sock_get(local, dsap);
        if (llcp_sock == NULL) {
                pr_err("Invalid CC\n");
                nfc_llcp_send_dm(local, dsap, ssap, LLCP_DM_NOCONN);

                return;
        }

        sk = &llcp_sock->sk;

        /* Unlink from connecting and link to the client array */
        nfc_llcp_sock_unlink(&local->connecting_sockets, sk);
        nfc_llcp_sock_link(&local->sockets, sk);
        llcp_sock->dsap = ssap;

        nfc_llcp_parse_connection_tlv(llcp_sock, &skb->data[LLCP_HEADER_SIZE],
                                      skb->len - LLCP_HEADER_SIZE);

        sk->sk_state = LLCP_CONNECTED;
        sk->sk_state_change(sk);

        nfc_llcp_sock_put(llcp_sock);
}

static void nfc_llcp_recv_dm(struct nfc_llcp_local *local,
                             const struct sk_buff *skb)
{
        struct nfc_llcp_sock *llcp_sock;
        struct sock *sk;
        u8 dsap, ssap, reason;

        dsap = nfc_llcp_dsap(skb);
        ssap = nfc_llcp_ssap(skb);
        reason = skb->data[2];

        pr_debug("%d %d reason %d\n", ssap, dsap, reason);

        switch (reason) {
        case LLCP_DM_NOBOUND:
        case LLCP_DM_REJ:
                llcp_sock = nfc_llcp_connecting_sock_get(local, dsap);
                break;

        default:
                llcp_sock = nfc_llcp_sock_get(local, dsap, ssap);
                break;
        }

        if (llcp_sock == NULL) {
                pr_debug("Already closed\n");
                return;
        }

        sk = &llcp_sock->sk;

        sk->sk_err = ENXIO;
        sk->sk_state = LLCP_CLOSED;
        sk->sk_state_change(sk);

        nfc_llcp_sock_put(llcp_sock);
}

static void nfc_llcp_recv_snl(struct nfc_llcp_local *local,
                              const struct sk_buff *skb)
{
        struct nfc_llcp_sock *llcp_sock;
        u8 dsap, ssap, type, length, tid, sap;
        const u8 *tlv;
        u16 tlv_len, offset;
        const char *service_name;
        size_t service_name_len;
        struct nfc_llcp_sdp_tlv *sdp;
        HLIST_HEAD(llc_sdres_list);
        size_t sdres_tlvs_len;
        HLIST_HEAD(nl_sdres_list);

        dsap = nfc_llcp_dsap(skb);
        ssap = nfc_llcp_ssap(skb);

        pr_debug("%d %d\n", dsap, ssap);

        if (dsap != LLCP_SAP_SDP || ssap != LLCP_SAP_SDP) {
                pr_err("Wrong SNL SAP\n");
                return;
        }

        tlv = &skb->data[LLCP_HEADER_SIZE];
        tlv_len = skb->len - LLCP_HEADER_SIZE;
        offset = 0;
        sdres_tlvs_len = 0;

        while (offset < tlv_len) {
                type = tlv[0];
                length = tlv[1];

                switch (type) {
                case LLCP_TLV_SDREQ:
                        tid = tlv[2];
                        service_name = (char *) &tlv[3];
                        service_name_len = length - 1;

                        pr_debug("Looking for %.16s\n", service_name);

                        if (service_name_len == strlen("urn:nfc:sn:sdp") &&
                            !strncmp(service_name, "urn:nfc:sn:sdp",
                                     service_name_len)) {
                                sap = 1;
                                goto add_snl;
                        }

                        llcp_sock = nfc_llcp_sock_from_sn(local, service_name,
                                                          service_name_len,
                                                          true);
                        if (!llcp_sock) {
                                sap = 0;
                                goto add_snl;
                        }

                        /*
                         * We found a socket but its ssap has not been reserved
                         * yet. We need to assign it for good and send a reply.
                         * The ssap will be freed when the socket is closed.
                         */
                        if (llcp_sock->ssap == LLCP_SDP_UNBOUND) {
                                atomic_t *client_count;

                                sap = nfc_llcp_reserve_sdp_ssap(local);

                                pr_debug("Reserving %d\n", sap);

                                if (sap == LLCP_SAP_MAX) {
                                        sap = 0;
                                        nfc_llcp_sock_put(llcp_sock);
                                        goto add_snl;
                                }

                                client_count =
                                        &local->local_sdp_cnt[sap -
                                                              LLCP_WKS_NUM_SAP];

                                atomic_inc(client_count);

                                llcp_sock->ssap = sap;
                                llcp_sock->reserved_ssap = sap;
                        } else {
                                sap = llcp_sock->ssap;
                        }

                        pr_debug("%p %d\n", llcp_sock, sap);

                        nfc_llcp_sock_put(llcp_sock);
add_snl:
                        sdp = nfc_llcp_build_sdres_tlv(tid, sap);
                        if (sdp == NULL)
                                goto exit;

                        sdres_tlvs_len += sdp->tlv_len;
                        hlist_add_head(&sdp->node, &llc_sdres_list);
                        break;

                case LLCP_TLV_SDRES:
                        mutex_lock(&local->sdreq_lock);

                        pr_debug("LLCP_TLV_SDRES: searching tid %d\n", tlv[2]);

                        hlist_for_each_entry(sdp, &local->pending_sdreqs, node) {
                                if (sdp->tid != tlv[2])
                                        continue;

                                sdp->sap = tlv[3];

                                pr_debug("Found: uri=%s, sap=%d\n",
                                         sdp->uri, sdp->sap);

                                hlist_del(&sdp->node);

                                hlist_add_head(&sdp->node, &nl_sdres_list);

                                break;
                        }

                        mutex_unlock(&local->sdreq_lock);
                        break;

                default:
                        pr_err("Invalid SNL tlv value 0x%x\n", type);
                        break;
                }

                offset += length + 2;
                tlv += length + 2;
        }

exit:
        if (!hlist_empty(&nl_sdres_list))
                nfc_genl_llc_send_sdres(local->dev, &nl_sdres_list);

        if (!hlist_empty(&llc_sdres_list))
                nfc_llcp_send_snl_sdres(local, &llc_sdres_list, sdres_tlvs_len);
}

static void nfc_llcp_recv_agf(struct nfc_llcp_local *local, struct sk_buff *skb)
{
        u8 ptype;
        u16 pdu_len;
        struct sk_buff *new_skb;

        if (skb->len <= LLCP_HEADER_SIZE) {
                pr_err("Malformed AGF PDU\n");
                return;
        }

        skb_pull(skb, LLCP_HEADER_SIZE);

        while (skb->len > LLCP_AGF_PDU_HEADER_SIZE) {
                pdu_len = skb->data[0] << 8 | skb->data[1];

                skb_pull(skb, LLCP_AGF_PDU_HEADER_SIZE);

                if (pdu_len < LLCP_HEADER_SIZE || pdu_len > skb->len) {
                        pr_err("Malformed AGF PDU\n");
                        return;
                }

                ptype = nfc_llcp_ptype(skb);

                if (ptype == LLCP_PDU_SYMM || ptype == LLCP_PDU_AGF)
                        goto next;

                new_skb = nfc_alloc_recv_skb(pdu_len, GFP_KERNEL);
                if (new_skb == NULL) {
                        pr_err("Could not allocate PDU\n");
                        return;
                }

                skb_put_data(new_skb, skb->data, pdu_len);

                nfc_llcp_rx_skb(local, new_skb);

                kfree_skb(new_skb);
next:
                skb_pull(skb, pdu_len);
        }
}

static void nfc_llcp_rx_skb(struct nfc_llcp_local *local, struct sk_buff *skb)
{
        u8 dsap, ssap, ptype;

        ptype = nfc_llcp_ptype(skb);
        dsap = nfc_llcp_dsap(skb);
        ssap = nfc_llcp_ssap(skb);

        pr_debug("ptype 0x%x dsap 0x%x ssap 0x%x\n", ptype, dsap, ssap);

        if (ptype != LLCP_PDU_SYMM)
                print_hex_dump_debug("LLCP Rx: ", DUMP_PREFIX_OFFSET, 16, 1,
                                     skb->data, skb->len, true);

        switch (ptype) {
        case LLCP_PDU_SYMM:
                pr_debug("SYMM\n");
                break;

        case LLCP_PDU_UI:
                pr_debug("UI\n");
                nfc_llcp_recv_ui(local, skb);
                break;

        case LLCP_PDU_CONNECT:
                pr_debug("CONNECT\n");
                nfc_llcp_recv_connect(local, skb);
                break;

        case LLCP_PDU_DISC:
                pr_debug("DISC\n");
                nfc_llcp_recv_disc(local, skb);
                break;

        case LLCP_PDU_CC:
                pr_debug("CC\n");
                nfc_llcp_recv_cc(local, skb);
                break;

        case LLCP_PDU_DM:
                pr_debug("DM\n");
                nfc_llcp_recv_dm(local, skb);
                break;

        case LLCP_PDU_SNL:
                pr_debug("SNL\n");
                nfc_llcp_recv_snl(local, skb);
                break;

        case LLCP_PDU_I:
        case LLCP_PDU_RR:
        case LLCP_PDU_RNR:
                pr_debug("I frame\n");
                nfc_llcp_recv_hdlc(local, skb);
                break;

        case LLCP_PDU_AGF:
                pr_debug("AGF frame\n");
                nfc_llcp_recv_agf(local, skb);
                break;
        }
}

static void nfc_llcp_rx_work(struct work_struct *work)
{
        struct nfc_llcp_local *local = container_of(work, struct nfc_llcp_local,
                                                    rx_work);
        struct sk_buff *skb;

        skb = local->rx_pending;
        if (skb == NULL) {
                pr_debug("No pending SKB\n");
                return;
        }

        __net_timestamp(skb);

        nfc_llcp_send_to_raw_sock(local, skb, NFC_DIRECTION_RX);

        nfc_llcp_rx_skb(local, skb);

        schedule_work(&local->tx_work);
        kfree_skb(local->rx_pending);
        local->rx_pending = NULL;
}

static void __nfc_llcp_recv(struct nfc_llcp_local *local, struct sk_buff *skb)
{
        local->rx_pending = skb;
        del_timer(&local->link_timer);
        schedule_work(&local->rx_work);
}

void nfc_llcp_recv(void *data, struct sk_buff *skb, int err)
{
        struct nfc_llcp_local *local = (struct nfc_llcp_local *) data;

        if (err < 0) {
                pr_err("LLCP PDU receive err %d\n", err);
                return;
        }

        __nfc_llcp_recv(local, skb);
}

int nfc_llcp_data_received(struct nfc_dev *dev, struct sk_buff *skb)
{
        struct nfc_llcp_local *local;

        local = nfc_llcp_find_local(dev);
        if (local == NULL) {
                kfree_skb(skb);
                return -ENODEV;
        }

        __nfc_llcp_recv(local, skb);

        nfc_llcp_local_put(local);

        return 0;
}

void nfc_llcp_mac_is_down(struct nfc_dev *dev)
{
        struct nfc_llcp_local *local;

        local = nfc_llcp_find_local(dev);
        if (local == NULL)
                return;

        local->remote_miu = LLCP_DEFAULT_MIU;
        local->remote_lto = LLCP_DEFAULT_LTO;

        /* Close and purge all existing sockets */
        nfc_llcp_socket_release(local, true, 0);

        nfc_llcp_local_put(local);
}

void nfc_llcp_mac_is_up(struct nfc_dev *dev, u32 target_idx,
                        u8 comm_mode, u8 rf_mode)
{
        struct nfc_llcp_local *local;

        pr_debug("rf mode %d\n", rf_mode);

        local = nfc_llcp_find_local(dev);
        if (local == NULL)
                return;

        local->target_idx = target_idx;
        local->comm_mode = comm_mode;
        local->rf_mode = rf_mode;

        if (rf_mode == NFC_RF_INITIATOR) {
                pr_debug("Queueing Tx work\n");

                schedule_work(&local->tx_work);
        } else {
                mod_timer(&local->link_timer,
                          jiffies + msecs_to_jiffies(local->remote_lto));
        }

        nfc_llcp_local_put(local);
}

int nfc_llcp_register_device(struct nfc_dev *ndev)
{
        struct nfc_llcp_local *local;

        local = kzalloc(sizeof(struct nfc_llcp_local), GFP_KERNEL);
        if (local == NULL)
                return -ENOMEM;

        /* As we are going to initialize local's refcount, we need to get the
         * nfc_dev to avoid UAF, otherwise there is no point in continuing.
         * See nfc_llcp_local_get().
         */
        local->dev = nfc_get_device(ndev->idx);
        if (!local->dev) {
                kfree(local);
                return -ENODEV;
        }

        INIT_LIST_HEAD(&local->list);
        kref_init(&local->ref);
        mutex_init(&local->sdp_lock);
        timer_setup(&local->link_timer, nfc_llcp_symm_timer, 0);

        skb_queue_head_init(&local->tx_queue);
        INIT_WORK(&local->tx_work, nfc_llcp_tx_work);

        local->rx_pending = NULL;
        INIT_WORK(&local->rx_work, nfc_llcp_rx_work);

        INIT_WORK(&local->timeout_work, nfc_llcp_timeout_work);

        rwlock_init(&local->sockets.lock);
        rwlock_init(&local->connecting_sockets.lock);
        rwlock_init(&local->raw_sockets.lock);

        local->lto = 150; /* 1500 ms */
        local->rw = LLCP_MAX_RW;
        local->miux = cpu_to_be16(LLCP_MAX_MIUX);
        local->local_wks = 0x1; /* LLC Link Management */

        nfc_llcp_build_gb(local);

        local->remote_miu = LLCP_DEFAULT_MIU;
        local->remote_lto = LLCP_DEFAULT_LTO;

        mutex_init(&local->sdreq_lock);
        INIT_HLIST_HEAD(&local->pending_sdreqs);
        timer_setup(&local->sdreq_timer, nfc_llcp_sdreq_timer, 0);
        INIT_WORK(&local->sdreq_timeout_work, nfc_llcp_sdreq_timeout_work);

        spin_lock(&llcp_devices_lock);
        list_add(&local->list, &llcp_devices);
        spin_unlock(&llcp_devices_lock);

        return 0;
}

void nfc_llcp_unregister_device(struct nfc_dev *dev)
{
        struct nfc_llcp_local *local = nfc_llcp_remove_local(dev);

        if (local == NULL) {
                pr_debug("No such device\n");
                return;
        }

        local_cleanup(local);

        nfc_llcp_local_put(local);
}

int __init nfc_llcp_init(void)
{
        return nfc_llcp_sock_init();
}

void nfc_llcp_exit(void)
{
        nfc_llcp_sock_exit();
}




































































































































































































































































  144 














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
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
/*
 * Copyright (C) 2014 Red Hat
 * Copyright (C) 2014 Intel Corp.
 *
 * Permission is hereby granted, free of charge, to any person obtaining a
 * copy of this software and associated documentation files (the "Software"),
 * to deal in the Software without restriction, including without limitation
 * the rights to use, copy, modify, merge, publish, distribute, sublicense,
 * and/or sell copies of the Software, and to permit persons to whom the
 * Software is furnished to do so, subject to the following conditions:
 *
 * The above copyright notice and this permission notice shall be included in
 * all copies or substantial portions of the Software.
 *
 * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
 * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
 * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
 * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
 * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
 * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
 * OTHER DEALINGS IN THE SOFTWARE.
 *
 * Authors:
 * Rob Clark <robdclark@gmail.com>
 * Daniel Vetter <daniel.vetter@ffwll.ch>
 */

#ifndef DRM_ATOMIC_HELPER_H_
#define DRM_ATOMIC_HELPER_H_

#include <drm/drm_crtc.h>
#include <drm/drm_modeset_helper_vtables.h>
#include <drm/drm_modeset_helper.h>
#include <drm/drm_atomic_state_helper.h>
#include <drm/drm_util.h>

/*
 * Drivers that don't allow primary plane scaling may pass this macro in place
 * of the min/max scale parameters of the plane-state checker function.
 *
 * Due to src being in 16.16 fixed point and dest being in integer pixels,
 * 1<<16 represents no scaling.
 */
#define DRM_PLANE_NO_SCALING (1<<16)

struct drm_atomic_state;
struct drm_private_obj;
struct drm_private_state;

int drm_atomic_helper_check_modeset(struct drm_device *dev,
                                struct drm_atomic_state *state);
int drm_atomic_helper_check_wb_connector_state(struct drm_connector *connector,
                                               struct drm_atomic_state *state);
int drm_atomic_helper_check_plane_state(struct drm_plane_state *plane_state,
                                        const struct drm_crtc_state *crtc_state,
                                        int min_scale,
                                        int max_scale,
                                        bool can_position,
                                        bool can_update_disabled);
int drm_atomic_helper_check_planes(struct drm_device *dev,
                               struct drm_atomic_state *state);
int drm_atomic_helper_check_crtc_primary_plane(struct drm_crtc_state *crtc_state);
int drm_atomic_helper_check(struct drm_device *dev,
                            struct drm_atomic_state *state);
void drm_atomic_helper_commit_tail(struct drm_atomic_state *state);
void drm_atomic_helper_commit_tail_rpm(struct drm_atomic_state *state);
int drm_atomic_helper_commit(struct drm_device *dev,
                             struct drm_atomic_state *state,
                             bool nonblock);
int drm_atomic_helper_async_check(struct drm_device *dev,
                                  struct drm_atomic_state *state);
void drm_atomic_helper_async_commit(struct drm_device *dev,
                                    struct drm_atomic_state *state);

int drm_atomic_helper_wait_for_fences(struct drm_device *dev,
                                        struct drm_atomic_state *state,
                                        bool pre_swap);

void drm_atomic_helper_wait_for_vblanks(struct drm_device *dev,
                                        struct drm_atomic_state *old_state);

void drm_atomic_helper_wait_for_flip_done(struct drm_device *dev,
                                          struct drm_atomic_state *old_state);

void
drm_atomic_helper_update_legacy_modeset_state(struct drm_device *dev,
                                              struct drm_atomic_state *old_state);

void
drm_atomic_helper_calc_timestamping_constants(struct drm_atomic_state *state);

void drm_atomic_helper_commit_modeset_disables(struct drm_device *dev,
                                               struct drm_atomic_state *state);
void drm_atomic_helper_commit_modeset_enables(struct drm_device *dev,
                                          struct drm_atomic_state *old_state);

int drm_atomic_helper_prepare_planes(struct drm_device *dev,
                                     struct drm_atomic_state *state);
void drm_atomic_helper_unprepare_planes(struct drm_device *dev,
                                        struct drm_atomic_state *state);

#define DRM_PLANE_COMMIT_ACTIVE_ONLY                        BIT(0)
#define DRM_PLANE_COMMIT_NO_DISABLE_AFTER_MODESET        BIT(1)

void drm_atomic_helper_commit_planes(struct drm_device *dev,
                                     struct drm_atomic_state *state,
                                     uint32_t flags);
void drm_atomic_helper_cleanup_planes(struct drm_device *dev,
                                      struct drm_atomic_state *old_state);
void drm_atomic_helper_commit_planes_on_crtc(struct drm_crtc_state *old_crtc_state);
void
drm_atomic_helper_disable_planes_on_crtc(struct drm_crtc_state *old_crtc_state,
                                         bool atomic);

int __must_check drm_atomic_helper_swap_state(struct drm_atomic_state *state,
                                              bool stall);

/* nonblocking commit helpers */
int drm_atomic_helper_setup_commit(struct drm_atomic_state *state,
                                   bool nonblock);
void drm_atomic_helper_wait_for_dependencies(struct drm_atomic_state *state);
void drm_atomic_helper_fake_vblank(struct drm_atomic_state *state);
void drm_atomic_helper_commit_hw_done(struct drm_atomic_state *state);
void drm_atomic_helper_commit_cleanup_done(struct drm_atomic_state *state);

/* implementations for legacy interfaces */
int drm_atomic_helper_update_plane(struct drm_plane *plane,
                                   struct drm_crtc *crtc,
                                   struct drm_framebuffer *fb,
                                   int crtc_x, int crtc_y,
                                   unsigned int crtc_w, unsigned int crtc_h,
                                   uint32_t src_x, uint32_t src_y,
                                   uint32_t src_w, uint32_t src_h,
                                   struct drm_modeset_acquire_ctx *ctx);
int drm_atomic_helper_disable_plane(struct drm_plane *plane,
                                    struct drm_modeset_acquire_ctx *ctx);
int drm_atomic_helper_set_config(struct drm_mode_set *set,
                                 struct drm_modeset_acquire_ctx *ctx);

int drm_atomic_helper_disable_all(struct drm_device *dev,
                                  struct drm_modeset_acquire_ctx *ctx);
void drm_atomic_helper_shutdown(struct drm_device *dev);
struct drm_atomic_state *
drm_atomic_helper_duplicate_state(struct drm_device *dev,
                                  struct drm_modeset_acquire_ctx *ctx);
struct drm_atomic_state *drm_atomic_helper_suspend(struct drm_device *dev);
int drm_atomic_helper_commit_duplicated_state(struct drm_atomic_state *state,
                                              struct drm_modeset_acquire_ctx *ctx);
int drm_atomic_helper_resume(struct drm_device *dev,
                             struct drm_atomic_state *state);

int drm_atomic_helper_page_flip(struct drm_crtc *crtc,
                                struct drm_framebuffer *fb,
                                struct drm_pending_vblank_event *event,
                                uint32_t flags,
                                struct drm_modeset_acquire_ctx *ctx);
int drm_atomic_helper_page_flip_target(
                                struct drm_crtc *crtc,
                                struct drm_framebuffer *fb,
                                struct drm_pending_vblank_event *event,
                                uint32_t flags,
                                uint32_t target,
                                struct drm_modeset_acquire_ctx *ctx);

/**
 * drm_atomic_crtc_for_each_plane - iterate over planes currently attached to CRTC
 * @plane: the loop cursor
 * @crtc:  the CRTC whose planes are iterated
 *
 * This iterates over the current state, useful (for example) when applying
 * atomic state after it has been checked and swapped.  To iterate over the
 * planes which *will* be attached (more useful in code called from
 * &drm_mode_config_funcs.atomic_check) see
 * drm_atomic_crtc_state_for_each_plane().
 */
#define drm_atomic_crtc_for_each_plane(plane, crtc) \
        drm_for_each_plane_mask(plane, (crtc)->dev, (crtc)->state->plane_mask)

/**
 * drm_atomic_crtc_state_for_each_plane - iterate over attached planes in new state
 * @plane: the loop cursor
 * @crtc_state: the incoming CRTC state
 *
 * Similar to drm_crtc_for_each_plane(), but iterates the planes that will be
 * attached if the specified state is applied.  Useful during for example
 * in code called from &drm_mode_config_funcs.atomic_check operations, to
 * validate the incoming state.
 */
#define drm_atomic_crtc_state_for_each_plane(plane, crtc_state) \
        drm_for_each_plane_mask(plane, (crtc_state)->state->dev, (crtc_state)->plane_mask)

/**
 * drm_atomic_crtc_state_for_each_plane_state - iterate over attached planes in new state
 * @plane: the loop cursor
 * @plane_state: loop cursor for the plane's state, must be const
 * @crtc_state: the incoming CRTC state
 *
 * Similar to drm_crtc_for_each_plane(), but iterates the planes that will be
 * attached if the specified state is applied.  Useful during for example
 * in code called from &drm_mode_config_funcs.atomic_check operations, to
 * validate the incoming state.
 *
 * Compared to just drm_atomic_crtc_state_for_each_plane() this also fills in a
 * const plane_state. This is useful when a driver just wants to peek at other
 * active planes on this CRTC, but does not need to change it.
 */
#define drm_atomic_crtc_state_for_each_plane_state(plane, plane_state, crtc_state) \
        drm_for_each_plane_mask(plane, (crtc_state)->state->dev, (crtc_state)->plane_mask) \
                for_each_if ((plane_state = \
                              __drm_atomic_get_current_plane_state((crtc_state)->state, \
                                                                   plane)))

/**
 * drm_atomic_plane_enabling - check whether a plane is being enabled
 * @old_plane_state: old atomic plane state
 * @new_plane_state: new atomic plane state
 *
 * Checks the atomic state of a plane to determine whether it's being enabled
 * or not. This also WARNs if it detects an invalid state (both CRTC and FB
 * need to either both be NULL or both be non-NULL).
 *
 * RETURNS:
 * True if the plane is being enabled, false otherwise.
 */
static inline bool drm_atomic_plane_enabling(struct drm_plane_state *old_plane_state,
                                             struct drm_plane_state *new_plane_state)
{
        /*
         * When enabling a plane, CRTC and FB should always be set together.
         * Anything else should be considered a bug in the atomic core, so we
         * gently warn about it.
         */
        WARN_ON((!new_plane_state->crtc && new_plane_state->fb) ||
                (new_plane_state->crtc && !new_plane_state->fb));

        return !old_plane_state->crtc && new_plane_state->crtc;
}

/**
 * drm_atomic_plane_disabling - check whether a plane is being disabled
 * @old_plane_state: old atomic plane state
 * @new_plane_state: new atomic plane state
 *
 * Checks the atomic state of a plane to determine whether it's being disabled
 * or not. This also WARNs if it detects an invalid state (both CRTC and FB
 * need to either both be NULL or both be non-NULL).
 *
 * RETURNS:
 * True if the plane is being disabled, false otherwise.
 */
static inline bool
drm_atomic_plane_disabling(struct drm_plane_state *old_plane_state,
                           struct drm_plane_state *new_plane_state)
{
        /*
         * When disabling a plane, CRTC and FB should always be NULL together.
         * Anything else should be considered a bug in the atomic core, so we
         * gently warn about it.
         */
        WARN_ON((new_plane_state->crtc == NULL && new_plane_state->fb != NULL) ||
                (new_plane_state->crtc != NULL && new_plane_state->fb == NULL));

        return old_plane_state->crtc && !new_plane_state->crtc;
}

u32 *
drm_atomic_helper_bridge_propagate_bus_fmt(struct drm_bridge *bridge,
                                        struct drm_bridge_state *bridge_state,
                                        struct drm_crtc_state *crtc_state,
                                        struct drm_connector_state *conn_state,
                                        u32 output_fmt,
                                        unsigned int *num_input_fmts);

#endif /* DRM_ATOMIC_HELPER_H_ */










































































































































































































































































































































































   25 








   17 
   24 






   31 





























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
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
/*
 * linux/fs/nls/nls_cp864.c
 *
 * Charset cp864 translation tables.
 * Generated automatically from the Unicode and charset
 * tables from the Unicode Organization (www.unicode.org).
 * The Unicode to charset table has only exact mappings.
 */

#include <linux/module.h>
#include <linux/kernel.h>
#include <linux/string.h>
#include <linux/nls.h>
#include <linux/errno.h>

static const wchar_t charset2uni[256] = {
        /* 0x00*/
        0x0000, 0x0001, 0x0002, 0x0003,
        0x0004, 0x0005, 0x0006, 0x0007,
        0x0008, 0x0009, 0x000a, 0x000b,
        0x000c, 0x000d, 0x000e, 0x000f,
        /* 0x10*/
        0x0010, 0x0011, 0x0012, 0x0013,
        0x0014, 0x0015, 0x0016, 0x0017,
        0x0018, 0x0019, 0x001a, 0x001b,
        0x001c, 0x001d, 0x001e, 0x001f,
        /* 0x20*/
        0x0020, 0x0021, 0x0022, 0x0023,
        0x0024, 0x066a, 0x0026, 0x0027,
        0x0028, 0x0029, 0x002a, 0x002b,
        0x002c, 0x002d, 0x002e, 0x002f,
        /* 0x30*/
        0x0030, 0x0031, 0x0032, 0x0033,
        0x0034, 0x0035, 0x0036, 0x0037,
        0x0038, 0x0039, 0x003a, 0x003b,
        0x003c, 0x003d, 0x003e, 0x003f,
        /* 0x40*/
        0x0040, 0x0041, 0x0042, 0x0043,
        0x0044, 0x0045, 0x0046, 0x0047,
        0x0048, 0x0049, 0x004a, 0x004b,
        0x004c, 0x004d, 0x004e, 0x004f,
        /* 0x50*/
        0x0050, 0x0051, 0x0052, 0x0053,
        0x0054, 0x0055, 0x0056, 0x0057,
        0x0058, 0x0059, 0x005a, 0x005b,
        0x005c, 0x005d, 0x005e, 0x005f,
        /* 0x60*/
        0x0060, 0x0061, 0x0062, 0x0063,
        0x0064, 0x0065, 0x0066, 0x0067,
        0x0068, 0x0069, 0x006a, 0x006b,
        0x006c, 0x006d, 0x006e, 0x006f,
        /* 0x70*/
        0x0070, 0x0071, 0x0072, 0x0073,
        0x0074, 0x0075, 0x0076, 0x0077,
        0x0078, 0x0079, 0x007a, 0x007b,
        0x007c, 0x007d, 0x007e, 0x007f,
        /* 0x80*/
        0x00b0, 0x00b7, 0x2219, 0x221a,
        0x2592, 0x2500, 0x2502, 0x253c,
        0x2524, 0x252c, 0x251c, 0x2534,
        0x2510, 0x250c, 0x2514, 0x2518,
        /* 0x90*/
        0x03b2, 0x221e, 0x03c6, 0x00b1,
        0x00bd, 0x00bc, 0x2248, 0x00ab,
        0x00bb, 0xfef7, 0xfef8, 0x0000,
        0x0000, 0xfefb, 0xfefc, 0x0000,
        /* 0xa0*/
        0x00a0, 0x00ad, 0xfe82, 0x00a3,
        0x00a4, 0xfe84, 0x0000, 0x0000,
        0xfe8e, 0xfe8f, 0xfe95, 0xfe99,
        0x060c, 0xfe9d, 0xfea1, 0xfea5,
        /* 0xb0*/
        0x0660, 0x0661, 0x0662, 0x0663,
        0x0664, 0x0665, 0x0666, 0x0667,
        0x0668, 0x0669, 0xfed1, 0x061b,
        0xfeb1, 0xfeb5, 0xfeb9, 0x061f,
        /* 0xc0*/
        0x00a2, 0xfe80, 0xfe81, 0xfe83,
        0xfe85, 0xfeca, 0xfe8b, 0xfe8d,
        0xfe91, 0xfe93, 0xfe97, 0xfe9b,
        0xfe9f, 0xfea3, 0xfea7, 0xfea9,
        /* 0xd0*/
        0xfeab, 0xfead, 0xfeaf, 0xfeb3,
        0xfeb7, 0xfebb, 0xfebf, 0xfec1,
        0xfec5, 0xfecb, 0xfecf, 0x00a6,
        0x00ac, 0x00f7, 0x00d7, 0xfec9,
        /* 0xe0*/
        0x0640, 0xfed3, 0xfed7, 0xfedb,
        0xfedf, 0xfee3, 0xfee7, 0xfeeb,
        0xfeed, 0xfeef, 0xfef3, 0xfebd,
        0xfecc, 0xfece, 0xfecd, 0xfee1,
        /* 0xf0*/
        0xfe7d, 0x0651, 0xfee5, 0xfee9,
        0xfeec, 0xfef0, 0xfef2, 0xfed0,
        0xfed5, 0xfef5, 0xfef6, 0xfedd,
        0xfed9, 0xfef1, 0x25a0, 0x0000,
};

static const unsigned char page00[256] = {
        0x00, 0x01, 0x02, 0x03, 0x04, 0x05, 0x06, 0x07, /* 0x00-0x07 */
        0x08, 0x09, 0x0a, 0x0b, 0x0c, 0x0d, 0x0e, 0x0f, /* 0x08-0x0f */
        0x10, 0x11, 0x12, 0x13, 0x14, 0x15, 0x16, 0x17, /* 0x10-0x17 */
        0x18, 0x19, 0x1a, 0x1b, 0x1c, 0x1d, 0x1e, 0x1f, /* 0x18-0x1f */
        0x20, 0x21, 0x22, 0x23, 0x24, 0x00, 0x26, 0x27, /* 0x20-0x27 */
        0x28, 0x29, 0x2a, 0x2b, 0x2c, 0x2d, 0x2e, 0x2f, /* 0x28-0x2f */
        0x30, 0x31, 0x32, 0x33, 0x34, 0x35, 0x36, 0x37, /* 0x30-0x37 */
        0x38, 0x39, 0x3a, 0x3b, 0x3c, 0x3d, 0x3e, 0x3f, /* 0x38-0x3f */
        0x40, 0x41, 0x42, 0x43, 0x44, 0x45, 0x46, 0x47, /* 0x40-0x47 */
        0x48, 0x49, 0x4a, 0x4b, 0x4c, 0x4d, 0x4e, 0x4f, /* 0x48-0x4f */
        0x50, 0x51, 0x52, 0x53, 0x54, 0x55, 0x56, 0x57, /* 0x50-0x57 */
        0x58, 0x59, 0x5a, 0x5b, 0x5c, 0x5d, 0x5e, 0x5f, /* 0x58-0x5f */
        0x60, 0x61, 0x62, 0x63, 0x64, 0x65, 0x66, 0x67, /* 0x60-0x67 */
        0x68, 0x69, 0x6a, 0x6b, 0x6c, 0x6d, 0x6e, 0x6f, /* 0x68-0x6f */
        0x70, 0x71, 0x72, 0x73, 0x74, 0x75, 0x76, 0x77, /* 0x70-0x77 */
        0x78, 0x79, 0x7a, 0x7b, 0x7c, 0x7d, 0x7e, 0x7f, /* 0x78-0x7f */

        0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x80-0x87 */
        0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x88-0x8f */
        0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x90-0x97 */
        0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x98-0x9f */
        0xa0, 0x00, 0xc0, 0xa3, 0xa4, 0x00, 0xdb, 0x00, /* 0xa0-0xa7 */
        0x00, 0x00, 0x00, 0x97, 0xdc, 0xa1, 0x00, 0x00, /* 0xa8-0xaf */
        0x80, 0x93, 0x00, 0x00, 0x00, 0x00, 0x00, 0x81, /* 0xb0-0xb7 */
        0x00, 0x00, 0x00, 0x98, 0x95, 0x94, 0x00, 0x00, /* 0xb8-0xbf */
        0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xc0-0xc7 */
        0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xc8-0xcf */
        0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0xde, /* 0xd0-0xd7 */
        0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xd8-0xdf */
        0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xe0-0xe7 */
        0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xe8-0xef */
        0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0xdd, /* 0xf0-0xf7 */
};

static const unsigned char page03[256] = {
        0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x00-0x07 */
        0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x08-0x0f */
        0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x10-0x17 */
        0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x18-0x1f */
        0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x20-0x27 */
        0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x28-0x2f */
        0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x30-0x37 */
        0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x38-0x3f */
        0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x40-0x47 */
        0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x48-0x4f */
        0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x50-0x57 */
        0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x58-0x5f */
        0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x60-0x67 */
        0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x68-0x6f */
        0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x70-0x77 */
        0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x78-0x7f */

        0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x80-0x87 */
        0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x88-0x8f */
        0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x90-0x97 */
        0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x98-0x9f */
        0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xa0-0xa7 */
        0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xa8-0xaf */
        0x00, 0x00, 0x90, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xb0-0xb7 */
        0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xb8-0xbf */
        0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x92, 0x00, /* 0xc0-0xc7 */
};

static const unsigned char page06[256] = {
        0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x00-0x07 */
        0x00, 0x00, 0x00, 0x00, 0xac, 0x00, 0x00, 0x00, /* 0x08-0x0f */
        0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x10-0x17 */
        0x00, 0x00, 0x00, 0xbb, 0x00, 0x00, 0x00, 0xbf, /* 0x18-0x1f */
        0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x20-0x27 */
        0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x28-0x2f */
        0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x30-0x37 */
        0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x38-0x3f */
        0xe0, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x40-0x47 */
        0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x48-0x4f */
        0x00, 0xf1, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x50-0x57 */
        0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x58-0x5f */
        0xb0, 0xb1, 0xb2, 0xb3, 0xb4, 0xb5, 0xb6, 0xb7, /* 0x60-0x67 */
        0xb8, 0xb9, 0x25, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x68-0x6f */
};

static const unsigned char page22[256] = {
        0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x00-0x07 */
        0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x08-0x0f */
        0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x10-0x17 */
        0x00, 0x82, 0x83, 0x00, 0x00, 0x00, 0x91, 0x00, /* 0x18-0x1f */
        0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x20-0x27 */
        0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x28-0x2f */
        0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x30-0x37 */
        0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x38-0x3f */
        0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x40-0x47 */
        0x96, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x48-0x4f */
};

static const unsigned char page25[256] = {
        0x85, 0x00, 0x86, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x00-0x07 */
        0x00, 0x00, 0x00, 0x00, 0x8d, 0x00, 0x00, 0x00, /* 0x08-0x0f */
        0x8c, 0x00, 0x00, 0x00, 0x8e, 0x00, 0x00, 0x00, /* 0x10-0x17 */
        0x8f, 0x00, 0x00, 0x00, 0x8a, 0x00, 0x00, 0x00, /* 0x18-0x1f */
        0x00, 0x00, 0x00, 0x00, 0x88, 0x00, 0x00, 0x00, /* 0x20-0x27 */
        0x00, 0x00, 0x00, 0x00, 0x89, 0x00, 0x00, 0x00, /* 0x28-0x2f */
        0x00, 0x00, 0x00, 0x00, 0x8b, 0x00, 0x00, 0x00, /* 0x30-0x37 */
        0x00, 0x00, 0x00, 0x00, 0x87, 0x00, 0x00, 0x00, /* 0x38-0x3f */
        0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x40-0x47 */
        0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x48-0x4f */
        0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x50-0x57 */
        0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x58-0x5f */
        0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x60-0x67 */
        0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x68-0x6f */
        0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x70-0x77 */
        0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x78-0x7f */

        0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x80-0x87 */
        0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x88-0x8f */
        0x00, 0x00, 0x84, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x90-0x97 */
        0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x98-0x9f */
        0xfe, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xa0-0xa7 */
};

static const unsigned char pagefe[256] = {
        0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x00-0x07 */
        0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x08-0x0f */
        0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x10-0x17 */
        0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x18-0x1f */
        0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x20-0x27 */
        0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x28-0x2f */
        0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x30-0x37 */
        0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x38-0x3f */
        0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x40-0x47 */
        0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x48-0x4f */
        0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x50-0x57 */
        0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x58-0x5f */
        0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x60-0x67 */
        0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x68-0x6f */
        0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x70-0x77 */
        0x00, 0x00, 0x00, 0x00, 0x00, 0xf0, 0x00, 0x00, /* 0x78-0x7f */

        0xc1, 0xc2, 0xa2, 0xc3, 0xa5, 0xc4, 0x00, 0x00, /* 0x80-0x87 */
        0x00, 0x00, 0x00, 0xc6, 0x00, 0xc7, 0xa8, 0xa9, /* 0x88-0x8f */
        0x00, 0xc8, 0x00, 0xc9, 0x00, 0xaa, 0x00, 0xca, /* 0x90-0x97 */
        0x00, 0xab, 0x00, 0xcb, 0x00, 0xad, 0x00, 0xcc, /* 0x98-0x9f */
        0x00, 0xae, 0x00, 0xcd, 0x00, 0xaf, 0x00, 0xce, /* 0xa0-0xa7 */
        0x00, 0xcf, 0x00, 0xd0, 0x00, 0xd1, 0x00, 0xd2, /* 0xa8-0xaf */
        0x00, 0xbc, 0x00, 0xd3, 0x00, 0xbd, 0x00, 0xd4, /* 0xb0-0xb7 */
        0x00, 0xbe, 0x00, 0xd5, 0x00, 0xeb, 0x00, 0xd6, /* 0xb8-0xbf */
        0x00, 0xd7, 0x00, 0x00, 0x00, 0xd8, 0x00, 0x00, /* 0xc0-0xc7 */
        0x00, 0xdf, 0xc5, 0xd9, 0xec, 0xee, 0xed, 0xda, /* 0xc8-0xcf */
        0xf7, 0xba, 0x00, 0xe1, 0x00, 0xf8, 0x00, 0xe2, /* 0xd0-0xd7 */
        0x00, 0xfc, 0x00, 0xe3, 0x00, 0xfb, 0x00, 0xe4, /* 0xd8-0xdf */
        0x00, 0xef, 0x00, 0xe5, 0x00, 0xf2, 0x00, 0xe6, /* 0xe0-0xe7 */
        0x00, 0xf3, 0x00, 0xe7, 0xf4, 0xe8, 0x00, 0xe9, /* 0xe8-0xef */
        0xf5, 0xfd, 0xf6, 0xea, 0x00, 0xf9, 0xfa, 0x99, /* 0xf0-0xf7 */
        0x9a, 0x00, 0x00, 0x9d, 0x9e, 0x00, 0x00, 0x00, /* 0xf8-0xff */
};

static const unsigned char *const page_uni2charset[256] = {
        page00, NULL,   NULL,   page03, NULL,   NULL,   page06, NULL,   
        NULL,   NULL,   NULL,   NULL,   NULL,   NULL,   NULL,   NULL,   
        NULL,   NULL,   NULL,   NULL,   NULL,   NULL,   NULL,   NULL,   
        NULL,   NULL,   NULL,   NULL,   NULL,   NULL,   NULL,   NULL,   
        NULL,   NULL,   page22, NULL,   NULL,   page25, NULL,   NULL,   
        NULL,   NULL,   NULL,   NULL,   NULL,   NULL,   NULL,   NULL,   
        NULL,   NULL,   NULL,   NULL,   NULL,   NULL,   NULL,   NULL,   
        NULL,   NULL,   NULL,   NULL,   NULL,   NULL,   NULL,   NULL,   
        NULL,   NULL,   NULL,   NULL,   NULL,   NULL,   NULL,   NULL,   
        NULL,   NULL,   NULL,   NULL,   NULL,   NULL,   NULL,   NULL,   
        NULL,   NULL,   NULL,   NULL,   NULL,   NULL,   NULL,   NULL,   
        NULL,   NULL,   NULL,   NULL,   NULL,   NULL,   NULL,   NULL,   
        NULL,   NULL,   NULL,   NULL,   NULL,   NULL,   NULL,   NULL,   
        NULL,   NULL,   NULL,   NULL,   NULL,   NULL,   NULL,   NULL,   
        NULL,   NULL,   NULL,   NULL,   NULL,   NULL,   NULL,   NULL,   
        NULL,   NULL,   NULL,   NULL,   NULL,   NULL,   NULL,   NULL,   
        NULL,   NULL,   NULL,   NULL,   NULL,   NULL,   NULL,   NULL,   
        NULL,   NULL,   NULL,   NULL,   NULL,   NULL,   NULL,   NULL,   
        NULL,   NULL,   NULL,   NULL,   NULL,   NULL,   NULL,   NULL,   
        NULL,   NULL,   NULL,   NULL,   NULL,   NULL,   NULL,   NULL,   
        NULL,   NULL,   NULL,   NULL,   NULL,   NULL,   NULL,   NULL,   
        NULL,   NULL,   NULL,   NULL,   NULL,   NULL,   NULL,   NULL,   
        NULL,   NULL,   NULL,   NULL,   NULL,   NULL,   NULL,   NULL,   
        NULL,   NULL,   NULL,   NULL,   NULL,   NULL,   NULL,   NULL,   
        NULL,   NULL,   NULL,   NULL,   NULL,   NULL,   NULL,   NULL,   
        NULL,   NULL,   NULL,   NULL,   NULL,   NULL,   NULL,   NULL,   
        NULL,   NULL,   NULL,   NULL,   NULL,   NULL,   NULL,   NULL,   
        NULL,   NULL,   NULL,   NULL,   NULL,   NULL,   NULL,   NULL,   
        NULL,   NULL,   NULL,   NULL,   NULL,   NULL,   NULL,   NULL,   
        NULL,   NULL,   NULL,   NULL,   NULL,   NULL,   NULL,   NULL,   
        NULL,   NULL,   NULL,   NULL,   NULL,   NULL,   NULL,   NULL,   
        NULL,   NULL,   NULL,   NULL,   NULL,   NULL,   pagefe, NULL,   
};

static const unsigned char charset2lower[256] = {
        0x00, 0x01, 0x02, 0x03, 0x04, 0x05, 0x06, 0x07, /* 0x00-0x07 */
        0x08, 0x09, 0x0a, 0x0b, 0x0c, 0x0d, 0x0e, 0x0f, /* 0x08-0x0f */
        0x10, 0x11, 0x12, 0x13, 0x14, 0x15, 0x16, 0x17, /* 0x10-0x17 */
        0x18, 0x19, 0x1a, 0x1b, 0x1c, 0x1d, 0x1e, 0x1f, /* 0x18-0x1f */
        0x20, 0x21, 0x22, 0x23, 0x24, 0x25, 0x26, 0x27, /* 0x20-0x27 */
        0x28, 0x29, 0x2a, 0x2b, 0x2c, 0x2d, 0x2e, 0x2f, /* 0x28-0x2f */
        0x30, 0x31, 0x32, 0x33, 0x34, 0x35, 0x36, 0x37, /* 0x30-0x37 */
        0x38, 0x39, 0x3a, 0x3b, 0x3c, 0x3d, 0x3e, 0x3f, /* 0x38-0x3f */
        0x40, 0x61, 0x62, 0x63, 0x64, 0x65, 0x66, 0x67, /* 0x40-0x47 */
        0x68, 0x69, 0x6a, 0x6b, 0x6c, 0x6d, 0x6e, 0x6f, /* 0x48-0x4f */
        0x70, 0x71, 0x72, 0x73, 0x74, 0x75, 0x76, 0x77, /* 0x50-0x57 */
        0x78, 0x79, 0x7a, 0x5b, 0x5c, 0x5d, 0x5e, 0x5f, /* 0x58-0x5f */
        0x60, 0x61, 0x62, 0x63, 0x64, 0x65, 0x66, 0x67, /* 0x60-0x67 */
        0x68, 0x69, 0x6a, 0x6b, 0x6c, 0x6d, 0x6e, 0x6f, /* 0x68-0x6f */
        0x70, 0x71, 0x72, 0x73, 0x74, 0x75, 0x76, 0x77, /* 0x70-0x77 */
        0x78, 0x79, 0x7a, 0x7b, 0x7c, 0x7d, 0x7e, 0x7f, /* 0x78-0x7f */

        0x80, 0x81, 0x82, 0x83, 0x84, 0x85, 0x86, 0x87, /* 0x80-0x87 */
        0x88, 0x89, 0x8a, 0x8b, 0x8c, 0x8d, 0x8e, 0x8f, /* 0x88-0x8f */
        0x90, 0x91, 0x92, 0x93, 0x94, 0x95, 0x96, 0x97, /* 0x90-0x97 */
        0x98, 0x99, 0x9a, 0x00, 0x00, 0x9d, 0x9e, 0x00, /* 0x98-0x9f */
        0xa0, 0xa1, 0xa2, 0xa3, 0xa4, 0xa5, 0x00, 0x00, /* 0xa0-0xa7 */
        0xa8, 0xa9, 0xaa, 0xab, 0xac, 0xad, 0xae, 0xaf, /* 0xa8-0xaf */
        0xb0, 0xb1, 0xb2, 0xb3, 0xb4, 0xb5, 0xb6, 0xb7, /* 0xb0-0xb7 */
        0xb8, 0xb9, 0xba, 0xbb, 0xbc, 0xbd, 0xbe, 0xbf, /* 0xb8-0xbf */
        0xc0, 0xc1, 0xc2, 0xc3, 0xc4, 0xc5, 0xc6, 0xc7, /* 0xc0-0xc7 */
        0xc8, 0xc9, 0xca, 0xcb, 0xcc, 0xcd, 0xce, 0xcf, /* 0xc8-0xcf */
        0xd0, 0xd1, 0xd2, 0xd3, 0xd4, 0xd5, 0xd6, 0xd7, /* 0xd0-0xd7 */
        0xd8, 0xd9, 0xda, 0xdb, 0xdc, 0xdd, 0xde, 0xdf, /* 0xd8-0xdf */
        0xe0, 0xe1, 0xe2, 0xe3, 0xe4, 0xe5, 0xe6, 0xe7, /* 0xe0-0xe7 */
        0xe8, 0xe9, 0xea, 0xeb, 0xec, 0xed, 0xee, 0xef, /* 0xe8-0xef */
        0xf0, 0xf1, 0xf2, 0xf3, 0xf4, 0xf5, 0xf6, 0xf7, /* 0xf0-0xf7 */
        0xf8, 0xf9, 0xfa, 0xfb, 0xfc, 0xfd, 0xfe, 0x00, /* 0xf8-0xff */
};

static const unsigned char charset2upper[256] = {
        0x00, 0x01, 0x02, 0x03, 0x04, 0x05, 0x06, 0x07, /* 0x00-0x07 */
        0x08, 0x09, 0x0a, 0x0b, 0x0c, 0x0d, 0x0e, 0x0f, /* 0x08-0x0f */
        0x10, 0x11, 0x12, 0x13, 0x14, 0x15, 0x16, 0x17, /* 0x10-0x17 */
        0x18, 0x19, 0x1a, 0x1b, 0x1c, 0x1d, 0x1e, 0x1f, /* 0x18-0x1f */
        0x20, 0x21, 0x22, 0x23, 0x24, 0x25, 0x26, 0x27, /* 0x20-0x27 */
        0x28, 0x29, 0x2a, 0x2b, 0x2c, 0x2d, 0x2e, 0x2f, /* 0x28-0x2f */
        0x30, 0x31, 0x32, 0x33, 0x34, 0x35, 0x36, 0x37, /* 0x30-0x37 */
        0x38, 0x39, 0x3a, 0x3b, 0x3c, 0x3d, 0x3e, 0x3f, /* 0x38-0x3f */
        0x40, 0x41, 0x42, 0x43, 0x44, 0x45, 0x46, 0x47, /* 0x40-0x47 */
        0x48, 0x49, 0x4a, 0x4b, 0x4c, 0x4d, 0x4e, 0x4f, /* 0x48-0x4f */
        0x50, 0x51, 0x52, 0x53, 0x54, 0x55, 0x56, 0x57, /* 0x50-0x57 */
        0x58, 0x59, 0x5a, 0x5b, 0x5c, 0x5d, 0x5e, 0x5f, /* 0x58-0x5f */
        0x60, 0x41, 0x42, 0x43, 0x44, 0x45, 0x46, 0x47, /* 0x60-0x67 */
        0x48, 0x49, 0x4a, 0x4b, 0x4c, 0x4d, 0x4e, 0x4f, /* 0x68-0x6f */
        0x50, 0x51, 0x52, 0x53, 0x54, 0x55, 0x56, 0x57, /* 0x70-0x77 */
        0x58, 0x59, 0x5a, 0x7b, 0x7c, 0x7d, 0x7e, 0x7f, /* 0x78-0x7f */

        0x80, 0x81, 0x82, 0x83, 0x84, 0x85, 0x86, 0x87, /* 0x80-0x87 */
        0x88, 0x89, 0x8a, 0x8b, 0x8c, 0x8d, 0x8e, 0x8f, /* 0x88-0x8f */
        0x00, 0x91, 0x00, 0x93, 0x94, 0x95, 0x96, 0x97, /* 0x90-0x97 */
        0x98, 0x99, 0x9a, 0x00, 0x00, 0x9d, 0x9e, 0x00, /* 0x98-0x9f */
        0xa0, 0xa1, 0xa2, 0xa3, 0xa4, 0xa5, 0x00, 0x00, /* 0xa0-0xa7 */
        0xa8, 0xa9, 0xaa, 0xab, 0xac, 0xad, 0xae, 0xaf, /* 0xa8-0xaf */
        0xb0, 0xb1, 0xb2, 0xb3, 0xb4, 0xb5, 0xb6, 0xb7, /* 0xb0-0xb7 */
        0xb8, 0xb9, 0xba, 0xbb, 0xbc, 0xbd, 0xbe, 0xbf, /* 0xb8-0xbf */
        0xc0, 0xc1, 0xc2, 0xc3, 0xc4, 0xc5, 0xc6, 0xc7, /* 0xc0-0xc7 */
        0xc8, 0xc9, 0xca, 0xcb, 0xcc, 0xcd, 0xce, 0xcf, /* 0xc8-0xcf */
        0xd0, 0xd1, 0xd2, 0xd3, 0xd4, 0xd5, 0xd6, 0xd7, /* 0xd0-0xd7 */
        0xd8, 0xd9, 0xda, 0xdb, 0xdc, 0xdd, 0xde, 0xdf, /* 0xd8-0xdf */
        0xe0, 0xe1, 0xe2, 0xe3, 0xe4, 0xe5, 0xe6, 0xe7, /* 0xe0-0xe7 */
        0xe8, 0xe9, 0xea, 0xeb, 0xec, 0xed, 0xee, 0xef, /* 0xe8-0xef */
        0xf0, 0xf1, 0xf2, 0xf3, 0xf4, 0xf5, 0xf6, 0xf7, /* 0xf0-0xf7 */
        0xf8, 0xf9, 0xfa, 0xfb, 0xfc, 0xfd, 0xfe, 0x00, /* 0xf8-0xff */
};

static int uni2char(wchar_t uni, unsigned char *out, int boundlen)
{
        const unsigned char *uni2charset;
        unsigned char cl = uni & 0x00ff;
        unsigned char ch = (uni & 0xff00) >> 8;

        if (boundlen <= 0)
                return -ENAMETOOLONG;

        uni2charset = page_uni2charset[ch];
        if (uni2charset && uni2charset[cl])
                out[0] = uni2charset[cl];
        else
                return -EINVAL;
        return 1;
}

static int char2uni(const unsigned char *rawstring, int boundlen, wchar_t *uni)
{
        *uni = charset2uni[*rawstring];
        if (*uni == 0x0000)
                return -EINVAL;
        return 1;
}

static struct nls_table table = {
        .charset        = "cp864",
        .uni2char        = uni2char,
        .char2uni        = char2uni,
        .charset2lower        = charset2lower,
        .charset2upper        = charset2upper,
};

static int __init init_nls_cp864(void)
{
        return register_nls(&table);
}

static void __exit exit_nls_cp864(void)
{
        unregister_nls(&table);
}

module_init(init_nls_cp864)
module_exit(exit_nls_cp864)

MODULE_DESCRIPTION("NLS Codepage 864 (Arabic)");
MODULE_LICENSE("Dual BSD/GPL");








































































   17 




    7 
   17 


    6 
   17 
    9 
   17 


    6 
   17 
    4 
   17 
    5 
   17 




   18 

















   17 


   17 




   17 











   26 

   26 

   26 













   19 





   19 
    5 








   26 
   26 



   26 










   26 




   26 








    5 





   26 












   20 
   20 



   20 











   20 




   20 

    3 















   20 













   20 
    3 
    3 


   20 









   20 





   20 





   24 








   27 

    1 


   24 








   24 

   24 





   27 

    1 
   27 





    1 



    1 













    1 








    1 





















    1 

















    1 














    4 
    4 
















    4 









    1 


    1 







    1 









   19 












   19 







   11 



   11 


























   11 
   11 




    6 
    6 
    6 
    6 

    6 

    3 





    3 



    6 


   10 

    1 





    2 



   10 


















   11 


   11 












   11 
















































































    6 








    6 























































































































   23 





   23 




   23 


















    3 





   17 





    4 

    4 

    4 




   19 








   19 
    3 








    1 





   18 


   18 
    5 




    6 

    6 


    6 
    6 



    4 





    4 


    4 





    3 
    1 




   16 










   16 




   16 










    6 
    6 



















   11 







   16 






    1 


    1 










    1 




    1 





   23 









    1 













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
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
// SPDX-License-Identifier: GPL-2.0
/*
 *  Implementation of operations over global quota file
 */
#include <linux/spinlock.h>
#include <linux/fs.h>
#include <linux/slab.h>
#include <linux/quota.h>
#include <linux/quotaops.h>
#include <linux/dqblk_qtree.h>
#include <linux/jiffies.h>
#include <linux/writeback.h>
#include <linux/workqueue.h>
#include <linux/llist.h>
#include <linux/iversion.h>

#include <cluster/masklog.h>

#include "ocfs2_fs.h"
#include "ocfs2.h"
#include "alloc.h"
#include "blockcheck.h"
#include "inode.h"
#include "journal.h"
#include "file.h"
#include "sysfile.h"
#include "dlmglue.h"
#include "uptodate.h"
#include "super.h"
#include "buffer_head_io.h"
#include "quota.h"
#include "ocfs2_trace.h"

/*
 * Locking of quotas with OCFS2 is rather complex. Here are rules that
 * should be obeyed by all the functions:
 * - any write of quota structure (either to local or global file) is protected
 *   by dqio_sem or dquot->dq_lock.
 * - any modification of global quota file holds inode cluster lock, i_rwsem,
 *   and ip_alloc_sem of the global quota file (achieved by
 *   ocfs2_lock_global_qf). It also has to hold qinfo_lock.
 * - an allocation of new blocks for local quota file is protected by
 *   its ip_alloc_sem
 *
 * A rough sketch of locking dependencies (lf = local file, gf = global file):
 * Normal filesystem operation:
 *   start_trans -> dqio_sem -> write to lf
 * Syncing of local and global file:
 *   ocfs2_lock_global_qf -> start_trans -> dqio_sem -> qinfo_lock ->
 *     write to gf
 *                                                       -> write to lf
 * Acquire dquot for the first time:
 *   dq_lock -> ocfs2_lock_global_qf -> qinfo_lock -> read from gf
 *                                     -> alloc space for gf
 *                                     -> start_trans -> qinfo_lock -> write to gf
 *             -> ip_alloc_sem of lf -> alloc space for lf
 *             -> write to lf
 * Release last reference to dquot:
 *   dq_lock -> ocfs2_lock_global_qf -> start_trans -> qinfo_lock -> write to gf
 *             -> write to lf
 * Note that all the above operations also hold the inode cluster lock of lf.
 * Recovery:
 *   inode cluster lock of recovered lf
 *     -> read bitmaps -> ip_alloc_sem of lf
 *     -> ocfs2_lock_global_qf -> start_trans -> dqio_sem -> qinfo_lock ->
 *        write to gf
 */

static void qsync_work_fn(struct work_struct *work);

static void ocfs2_global_disk2memdqb(struct dquot *dquot, void *dp)
{
        struct ocfs2_global_disk_dqblk *d = dp;
        struct mem_dqblk *m = &dquot->dq_dqb;

        /* Update from disk only entries not set by the admin */
        if (!test_bit(DQ_LASTSET_B + QIF_ILIMITS_B, &dquot->dq_flags)) {
                m->dqb_ihardlimit = le64_to_cpu(d->dqb_ihardlimit);
                m->dqb_isoftlimit = le64_to_cpu(d->dqb_isoftlimit);
        }
        if (!test_bit(DQ_LASTSET_B + QIF_INODES_B, &dquot->dq_flags))
                m->dqb_curinodes = le64_to_cpu(d->dqb_curinodes);
        if (!test_bit(DQ_LASTSET_B + QIF_BLIMITS_B, &dquot->dq_flags)) {
                m->dqb_bhardlimit = le64_to_cpu(d->dqb_bhardlimit);
                m->dqb_bsoftlimit = le64_to_cpu(d->dqb_bsoftlimit);
        }
        if (!test_bit(DQ_LASTSET_B + QIF_SPACE_B, &dquot->dq_flags))
                m->dqb_curspace = le64_to_cpu(d->dqb_curspace);
        if (!test_bit(DQ_LASTSET_B + QIF_BTIME_B, &dquot->dq_flags))
                m->dqb_btime = le64_to_cpu(d->dqb_btime);
        if (!test_bit(DQ_LASTSET_B + QIF_ITIME_B, &dquot->dq_flags))
                m->dqb_itime = le64_to_cpu(d->dqb_itime);
        OCFS2_DQUOT(dquot)->dq_use_count = le32_to_cpu(d->dqb_use_count);
}

static void ocfs2_global_mem2diskdqb(void *dp, struct dquot *dquot)
{
        struct ocfs2_global_disk_dqblk *d = dp;
        struct mem_dqblk *m = &dquot->dq_dqb;

        d->dqb_id = cpu_to_le32(from_kqid(&init_user_ns, dquot->dq_id));
        d->dqb_use_count = cpu_to_le32(OCFS2_DQUOT(dquot)->dq_use_count);
        d->dqb_ihardlimit = cpu_to_le64(m->dqb_ihardlimit);
        d->dqb_isoftlimit = cpu_to_le64(m->dqb_isoftlimit);
        d->dqb_curinodes = cpu_to_le64(m->dqb_curinodes);
        d->dqb_bhardlimit = cpu_to_le64(m->dqb_bhardlimit);
        d->dqb_bsoftlimit = cpu_to_le64(m->dqb_bsoftlimit);
        d->dqb_curspace = cpu_to_le64(m->dqb_curspace);
        d->dqb_btime = cpu_to_le64(m->dqb_btime);
        d->dqb_itime = cpu_to_le64(m->dqb_itime);
        d->dqb_pad1 = d->dqb_pad2 = 0;
}

static int ocfs2_global_is_id(void *dp, struct dquot *dquot)
{
        struct ocfs2_global_disk_dqblk *d = dp;
        struct ocfs2_mem_dqinfo *oinfo =
                        sb_dqinfo(dquot->dq_sb, dquot->dq_id.type)->dqi_priv;

        if (qtree_entry_unused(&oinfo->dqi_gi, dp))
                return 0;

        return qid_eq(make_kqid(&init_user_ns, dquot->dq_id.type,
                                le32_to_cpu(d->dqb_id)),
                      dquot->dq_id);
}

const struct qtree_fmt_operations ocfs2_global_ops = {
        .mem2disk_dqblk = ocfs2_global_mem2diskdqb,
        .disk2mem_dqblk = ocfs2_global_disk2memdqb,
        .is_id = ocfs2_global_is_id,
};

int ocfs2_validate_quota_block(struct super_block *sb, struct buffer_head *bh)
{
        struct ocfs2_disk_dqtrailer *dqt =
                ocfs2_block_dqtrailer(sb->s_blocksize, bh->b_data);

        trace_ocfs2_validate_quota_block((unsigned long long)bh->b_blocknr);

        BUG_ON(!buffer_uptodate(bh));

        /*
         * If the ecc fails, we return the error but otherwise
         * leave the filesystem running.  We know any error is
         * local to this block.
         */
        return ocfs2_validate_meta_ecc(sb, bh->b_data, &dqt->dq_check);
}

int ocfs2_read_quota_phys_block(struct inode *inode, u64 p_block,
                                struct buffer_head **bhp)
{
        int rc;

        *bhp = NULL;
        rc = ocfs2_read_blocks(INODE_CACHE(inode), p_block, 1, bhp, 0,
                               ocfs2_validate_quota_block);
        if (rc)
                mlog_errno(rc);
        return rc;
}

/* Read data from global quotafile - avoid pagecache and such because we cannot
 * afford acquiring the locks... We use quota cluster lock to serialize
 * operations. Caller is responsible for acquiring it. */
ssize_t ocfs2_quota_read(struct super_block *sb, int type, char *data,
                         size_t len, loff_t off)
{
        struct ocfs2_mem_dqinfo *oinfo = sb_dqinfo(sb, type)->dqi_priv;
        struct inode *gqinode = oinfo->dqi_gqinode;
        loff_t i_size = i_size_read(gqinode);
        int offset = off & (sb->s_blocksize - 1);
        sector_t blk = off >> sb->s_blocksize_bits;
        int err = 0;
        struct buffer_head *bh;
        size_t toread, tocopy;
        u64 pblock = 0, pcount = 0;

        if (off > i_size)
                return 0;
        if (off + len > i_size)
                len = i_size - off;
        toread = len;
        while (toread > 0) {
                tocopy = min_t(size_t, (sb->s_blocksize - offset), toread);
                if (!pcount) {
                        err = ocfs2_extent_map_get_blocks(gqinode, blk, &pblock,
                                                          &pcount, NULL);
                        if (err) {
                                mlog_errno(err);
                                return err;
                        }
                } else {
                        pcount--;
                        pblock++;
                }
                bh = NULL;
                err = ocfs2_read_quota_phys_block(gqinode, pblock, &bh);
                if (err) {
                        mlog_errno(err);
                        return err;
                }
                memcpy(data, bh->b_data + offset, tocopy);
                brelse(bh);
                offset = 0;
                toread -= tocopy;
                data += tocopy;
                blk++;
        }
        return len;
}

/* Write to quotafile (we know the transaction is already started and has
 * enough credits) */
ssize_t ocfs2_quota_write(struct super_block *sb, int type,
                          const char *data, size_t len, loff_t off)
{
        struct mem_dqinfo *info = sb_dqinfo(sb, type);
        struct ocfs2_mem_dqinfo *oinfo = info->dqi_priv;
        struct inode *gqinode = oinfo->dqi_gqinode;
        int offset = off & (sb->s_blocksize - 1);
        sector_t blk = off >> sb->s_blocksize_bits;
        int err = 0, new = 0, ja_type;
        struct buffer_head *bh = NULL;
        handle_t *handle = journal_current_handle();
        u64 pblock, pcount;

        if (!handle) {
                mlog(ML_ERROR, "Quota write (off=%llu, len=%llu) cancelled "
                     "because transaction was not started.\n",
                     (unsigned long long)off, (unsigned long long)len);
                return -EIO;
        }
        if (len > sb->s_blocksize - OCFS2_QBLK_RESERVED_SPACE - offset) {
                WARN_ON(1);
                len = sb->s_blocksize - OCFS2_QBLK_RESERVED_SPACE - offset;
        }

        if (i_size_read(gqinode) < off + len) {
                loff_t rounded_end =
                                ocfs2_align_bytes_to_blocks(sb, off + len);

                /* Space is already allocated in ocfs2_acquire_dquot() */
                err = ocfs2_simple_size_update(gqinode,
                                               oinfo->dqi_gqi_bh,
                                               rounded_end);
                if (err < 0)
                        goto out;
                new = 1;
        }
        err = ocfs2_extent_map_get_blocks(gqinode, blk, &pblock, &pcount, NULL);
        if (err) {
                mlog_errno(err);
                goto out;
        }
        /* Not rewriting whole block? */
        if ((offset || len < sb->s_blocksize - OCFS2_QBLK_RESERVED_SPACE) &&
            !new) {
                err = ocfs2_read_quota_phys_block(gqinode, pblock, &bh);
                ja_type = OCFS2_JOURNAL_ACCESS_WRITE;
        } else {
                bh = sb_getblk(sb, pblock);
                if (!bh)
                        err = -ENOMEM;
                ja_type = OCFS2_JOURNAL_ACCESS_CREATE;
        }
        if (err) {
                mlog_errno(err);
                goto out;
        }
        lock_buffer(bh);
        if (new)
                memset(bh->b_data, 0, sb->s_blocksize);
        memcpy(bh->b_data + offset, data, len);
        flush_dcache_page(bh->b_page);
        set_buffer_uptodate(bh);
        unlock_buffer(bh);
        ocfs2_set_buffer_uptodate(INODE_CACHE(gqinode), bh);
        err = ocfs2_journal_access_dq(handle, INODE_CACHE(gqinode), bh,
                                      ja_type);
        if (err < 0) {
                brelse(bh);
                goto out;
        }
        ocfs2_journal_dirty(handle, bh);
        brelse(bh);
out:
        if (err) {
                mlog_errno(err);
                return err;
        }
        inode_inc_iversion(gqinode);
        ocfs2_mark_inode_dirty(handle, gqinode, oinfo->dqi_gqi_bh);
        return len;
}

int ocfs2_lock_global_qf(struct ocfs2_mem_dqinfo *oinfo, int ex)
{
        int status;
        struct buffer_head *bh = NULL;

        status = ocfs2_inode_lock(oinfo->dqi_gqinode, &bh, ex);
        if (status < 0)
                return status;
        spin_lock(&dq_data_lock);
        if (!oinfo->dqi_gqi_count++)
                oinfo->dqi_gqi_bh = bh;
        else
                WARN_ON(bh != oinfo->dqi_gqi_bh);
        spin_unlock(&dq_data_lock);
        if (ex) {
                inode_lock(oinfo->dqi_gqinode);
                down_write(&OCFS2_I(oinfo->dqi_gqinode)->ip_alloc_sem);
        } else {
                down_read(&OCFS2_I(oinfo->dqi_gqinode)->ip_alloc_sem);
        }
        return 0;
}

void ocfs2_unlock_global_qf(struct ocfs2_mem_dqinfo *oinfo, int ex)
{
        if (ex) {
                up_write(&OCFS2_I(oinfo->dqi_gqinode)->ip_alloc_sem);
                inode_unlock(oinfo->dqi_gqinode);
        } else {
                up_read(&OCFS2_I(oinfo->dqi_gqinode)->ip_alloc_sem);
        }
        ocfs2_inode_unlock(oinfo->dqi_gqinode, ex);
        brelse(oinfo->dqi_gqi_bh);
        spin_lock(&dq_data_lock);
        if (!--oinfo->dqi_gqi_count)
                oinfo->dqi_gqi_bh = NULL;
        spin_unlock(&dq_data_lock);
}

/* Read information header from global quota file */
int ocfs2_global_read_info(struct super_block *sb, int type)
{
        unsigned int ino[OCFS2_MAXQUOTAS] = { USER_QUOTA_SYSTEM_INODE,
                                              GROUP_QUOTA_SYSTEM_INODE };
        struct ocfs2_global_disk_dqinfo dinfo;
        struct mem_dqinfo *info = sb_dqinfo(sb, type);
        struct ocfs2_mem_dqinfo *oinfo = info->dqi_priv;
        u64 pcount;
        int status;

        oinfo->dqi_gi.dqi_sb = sb;
        oinfo->dqi_gi.dqi_type = type;
        ocfs2_qinfo_lock_res_init(&oinfo->dqi_gqlock, oinfo);
        oinfo->dqi_gi.dqi_entry_size = sizeof(struct ocfs2_global_disk_dqblk);
        oinfo->dqi_gi.dqi_ops = &ocfs2_global_ops;
        oinfo->dqi_gqi_bh = NULL;
        oinfo->dqi_gqi_count = 0;

        /* Read global header */
        oinfo->dqi_gqinode = ocfs2_get_system_file_inode(OCFS2_SB(sb), ino[type],
                        OCFS2_INVALID_SLOT);
        if (!oinfo->dqi_gqinode) {
                mlog(ML_ERROR, "failed to get global quota inode (type=%d)\n",
                        type);
                status = -EINVAL;
                goto out_err;
        }

        status = ocfs2_lock_global_qf(oinfo, 0);
        if (status < 0) {
                mlog_errno(status);
                goto out_err;
        }

        status = ocfs2_extent_map_get_blocks(oinfo->dqi_gqinode, 0, &oinfo->dqi_giblk,
                                             &pcount, NULL);
        if (status < 0) {
                mlog_errno(status);
                goto out_unlock;
        }

        status = ocfs2_qinfo_lock(oinfo, 0);
        if (status < 0) {
                mlog_errno(status);
                goto out_unlock;
        }
        status = sb->s_op->quota_read(sb, type, (char *)&dinfo,
                                      sizeof(struct ocfs2_global_disk_dqinfo),
                                      OCFS2_GLOBAL_INFO_OFF);
        ocfs2_qinfo_unlock(oinfo, 0);
        ocfs2_unlock_global_qf(oinfo, 0);
        if (status != sizeof(struct ocfs2_global_disk_dqinfo)) {
                mlog(ML_ERROR, "Cannot read global quota info (%d).\n",
                     status);
                if (status >= 0)
                        status = -EIO;
                mlog_errno(status);
                goto out_err;
        }
        info->dqi_bgrace = le32_to_cpu(dinfo.dqi_bgrace);
        info->dqi_igrace = le32_to_cpu(dinfo.dqi_igrace);
        oinfo->dqi_syncms = le32_to_cpu(dinfo.dqi_syncms);
        oinfo->dqi_gi.dqi_blocks = le32_to_cpu(dinfo.dqi_blocks);
        oinfo->dqi_gi.dqi_free_blk = le32_to_cpu(dinfo.dqi_free_blk);
        oinfo->dqi_gi.dqi_free_entry = le32_to_cpu(dinfo.dqi_free_entry);
        oinfo->dqi_gi.dqi_blocksize_bits = sb->s_blocksize_bits;
        oinfo->dqi_gi.dqi_usable_bs = sb->s_blocksize -
                                                OCFS2_QBLK_RESERVED_SPACE;
        oinfo->dqi_gi.dqi_qtree_depth = qtree_depth(&oinfo->dqi_gi);
        INIT_DELAYED_WORK(&oinfo->dqi_sync_work, qsync_work_fn);
        schedule_delayed_work(&oinfo->dqi_sync_work,
                              msecs_to_jiffies(oinfo->dqi_syncms));

        return 0;
out_unlock:
        ocfs2_unlock_global_qf(oinfo, 0);
out_err:
        return status;
}

/* Write information to global quota file. Expects exclusive lock on quota
 * file inode and quota info */
static int __ocfs2_global_write_info(struct super_block *sb, int type)
{
        struct mem_dqinfo *info = sb_dqinfo(sb, type);
        struct ocfs2_mem_dqinfo *oinfo = info->dqi_priv;
        struct ocfs2_global_disk_dqinfo dinfo;
        ssize_t size;

        spin_lock(&dq_data_lock);
        info->dqi_flags &= ~DQF_INFO_DIRTY;
        dinfo.dqi_bgrace = cpu_to_le32(info->dqi_bgrace);
        dinfo.dqi_igrace = cpu_to_le32(info->dqi_igrace);
        spin_unlock(&dq_data_lock);
        dinfo.dqi_syncms = cpu_to_le32(oinfo->dqi_syncms);
        dinfo.dqi_blocks = cpu_to_le32(oinfo->dqi_gi.dqi_blocks);
        dinfo.dqi_free_blk = cpu_to_le32(oinfo->dqi_gi.dqi_free_blk);
        dinfo.dqi_free_entry = cpu_to_le32(oinfo->dqi_gi.dqi_free_entry);
        size = sb->s_op->quota_write(sb, type, (char *)&dinfo,
                                     sizeof(struct ocfs2_global_disk_dqinfo),
                                     OCFS2_GLOBAL_INFO_OFF);
        if (size != sizeof(struct ocfs2_global_disk_dqinfo)) {
                mlog(ML_ERROR, "Cannot write global quota info structure\n");
                if (size >= 0)
                        size = -EIO;
                return size;
        }
        return 0;
}

int ocfs2_global_write_info(struct super_block *sb, int type)
{
        int err;
        struct quota_info *dqopt = sb_dqopt(sb);
        struct ocfs2_mem_dqinfo *info = dqopt->info[type].dqi_priv;
        unsigned int memalloc;

        down_write(&dqopt->dqio_sem);
        memalloc = memalloc_nofs_save();
        err = ocfs2_qinfo_lock(info, 1);
        if (err < 0)
                goto out_sem;
        err = __ocfs2_global_write_info(sb, type);
        ocfs2_qinfo_unlock(info, 1);
out_sem:
        memalloc_nofs_restore(memalloc);
        up_write(&dqopt->dqio_sem);
        return err;
}

static int ocfs2_global_qinit_alloc(struct super_block *sb, int type)
{
        struct ocfs2_mem_dqinfo *oinfo = sb_dqinfo(sb, type)->dqi_priv;

        /*
         * We may need to allocate tree blocks and a leaf block but not the
         * root block
         */
        return oinfo->dqi_gi.dqi_qtree_depth;
}

static int ocfs2_calc_global_qinit_credits(struct super_block *sb, int type)
{
        /* We modify all the allocated blocks, tree root, info block and
         * the inode */
        return (ocfs2_global_qinit_alloc(sb, type) + 2) *
                        OCFS2_QUOTA_BLOCK_UPDATE_CREDITS + 1;
}

/* Sync local information about quota modifications with global quota file.
 * Caller must have started the transaction and obtained exclusive lock for
 * global quota file inode */
int __ocfs2_sync_dquot(struct dquot *dquot, int freeing)
{
        int err, err2;
        struct super_block *sb = dquot->dq_sb;
        int type = dquot->dq_id.type;
        struct ocfs2_mem_dqinfo *info = sb_dqinfo(sb, type)->dqi_priv;
        struct ocfs2_global_disk_dqblk dqblk;
        s64 spacechange, inodechange;
        time64_t olditime, oldbtime;

        err = sb->s_op->quota_read(sb, type, (char *)&dqblk,
                                   sizeof(struct ocfs2_global_disk_dqblk),
                                   dquot->dq_off);
        if (err != sizeof(struct ocfs2_global_disk_dqblk)) {
                if (err >= 0) {
                        mlog(ML_ERROR, "Short read from global quota file "
                                       "(%u read)\n", err);
                        err = -EIO;
                }
                goto out;
        }

        /* Update space and inode usage. Get also other information from
         * global quota file so that we don't overwrite any changes there.
         * We are */
        spin_lock(&dquot->dq_dqb_lock);
        spacechange = dquot->dq_dqb.dqb_curspace -
                                        OCFS2_DQUOT(dquot)->dq_origspace;
        inodechange = dquot->dq_dqb.dqb_curinodes -
                                        OCFS2_DQUOT(dquot)->dq_originodes;
        olditime = dquot->dq_dqb.dqb_itime;
        oldbtime = dquot->dq_dqb.dqb_btime;
        ocfs2_global_disk2memdqb(dquot, &dqblk);
        trace_ocfs2_sync_dquot(from_kqid(&init_user_ns, dquot->dq_id),
                               dquot->dq_dqb.dqb_curspace,
                               (long long)spacechange,
                               dquot->dq_dqb.dqb_curinodes,
                               (long long)inodechange);
        if (!test_bit(DQ_LASTSET_B + QIF_SPACE_B, &dquot->dq_flags))
                dquot->dq_dqb.dqb_curspace += spacechange;
        if (!test_bit(DQ_LASTSET_B + QIF_INODES_B, &dquot->dq_flags))
                dquot->dq_dqb.dqb_curinodes += inodechange;
        /* Set properly space grace time... */
        if (dquot->dq_dqb.dqb_bsoftlimit &&
            dquot->dq_dqb.dqb_curspace > dquot->dq_dqb.dqb_bsoftlimit) {
                if (!test_bit(DQ_LASTSET_B + QIF_BTIME_B, &dquot->dq_flags) &&
                    oldbtime > 0) {
                        if (dquot->dq_dqb.dqb_btime > 0)
                                dquot->dq_dqb.dqb_btime =
                                        min(dquot->dq_dqb.dqb_btime, oldbtime);
                        else
                                dquot->dq_dqb.dqb_btime = oldbtime;
                }
        } else {
                dquot->dq_dqb.dqb_btime = 0;
                clear_bit(DQ_BLKS_B, &dquot->dq_flags);
        }
        /* Set properly inode grace time... */
        if (dquot->dq_dqb.dqb_isoftlimit &&
            dquot->dq_dqb.dqb_curinodes > dquot->dq_dqb.dqb_isoftlimit) {
                if (!test_bit(DQ_LASTSET_B + QIF_ITIME_B, &dquot->dq_flags) &&
                    olditime > 0) {
                        if (dquot->dq_dqb.dqb_itime > 0)
                                dquot->dq_dqb.dqb_itime =
                                        min(dquot->dq_dqb.dqb_itime, olditime);
                        else
                                dquot->dq_dqb.dqb_itime = olditime;
                }
        } else {
                dquot->dq_dqb.dqb_itime = 0;
                clear_bit(DQ_INODES_B, &dquot->dq_flags);
        }
        /* All information is properly updated, clear the flags */
        __clear_bit(DQ_LASTSET_B + QIF_SPACE_B, &dquot->dq_flags);
        __clear_bit(DQ_LASTSET_B + QIF_INODES_B, &dquot->dq_flags);
        __clear_bit(DQ_LASTSET_B + QIF_BLIMITS_B, &dquot->dq_flags);
        __clear_bit(DQ_LASTSET_B + QIF_ILIMITS_B, &dquot->dq_flags);
        __clear_bit(DQ_LASTSET_B + QIF_BTIME_B, &dquot->dq_flags);
        __clear_bit(DQ_LASTSET_B + QIF_ITIME_B, &dquot->dq_flags);
        OCFS2_DQUOT(dquot)->dq_origspace = dquot->dq_dqb.dqb_curspace;
        OCFS2_DQUOT(dquot)->dq_originodes = dquot->dq_dqb.dqb_curinodes;
        spin_unlock(&dquot->dq_dqb_lock);
        err = ocfs2_qinfo_lock(info, freeing);
        if (err < 0) {
                mlog(ML_ERROR, "Failed to lock quota info, losing quota write"
                               " (type=%d, id=%u)\n", dquot->dq_id.type,
                               (unsigned)from_kqid(&init_user_ns, dquot->dq_id));
                goto out;
        }
        if (freeing)
                OCFS2_DQUOT(dquot)->dq_use_count--;
        err = qtree_write_dquot(&info->dqi_gi, dquot);
        if (err < 0)
                goto out_qlock;
        if (freeing && !OCFS2_DQUOT(dquot)->dq_use_count) {
                err = qtree_release_dquot(&info->dqi_gi, dquot);
                if (info_dirty(sb_dqinfo(sb, type))) {
                        err2 = __ocfs2_global_write_info(sb, type);
                        if (!err)
                                err = err2;
                }
        }
out_qlock:
        ocfs2_qinfo_unlock(info, freeing);
out:
        if (err < 0)
                mlog_errno(err);
        return err;
}

/*
 *  Functions for periodic syncing of dquots with global file
 */
static int ocfs2_sync_dquot_helper(struct dquot *dquot, unsigned long type)
{
        handle_t *handle;
        struct super_block *sb = dquot->dq_sb;
        struct ocfs2_mem_dqinfo *oinfo = sb_dqinfo(sb, type)->dqi_priv;
        struct ocfs2_super *osb = OCFS2_SB(sb);
        int status = 0;
        unsigned int memalloc;

        trace_ocfs2_sync_dquot_helper(from_kqid(&init_user_ns, dquot->dq_id),
                                      dquot->dq_id.type,
                                      type, sb->s_id);
        if (type != dquot->dq_id.type)
                goto out;
        status = ocfs2_lock_global_qf(oinfo, 1);
        if (status < 0)
                goto out;

        handle = ocfs2_start_trans(osb, OCFS2_QSYNC_CREDITS);
        if (IS_ERR(handle)) {
                status = PTR_ERR(handle);
                mlog_errno(status);
                goto out_ilock;
        }
        down_write(&sb_dqopt(sb)->dqio_sem);
        memalloc = memalloc_nofs_save();
        status = ocfs2_sync_dquot(dquot);
        if (status < 0)
                mlog_errno(status);
        /* We have to write local structure as well... */
        status = ocfs2_local_write_dquot(dquot);
        if (status < 0)
                mlog_errno(status);
        memalloc_nofs_restore(memalloc);
        up_write(&sb_dqopt(sb)->dqio_sem);
        ocfs2_commit_trans(osb, handle);
out_ilock:
        ocfs2_unlock_global_qf(oinfo, 1);
out:
        return status;
}

static void qsync_work_fn(struct work_struct *work)
{
        struct ocfs2_mem_dqinfo *oinfo = container_of(work,
                                                      struct ocfs2_mem_dqinfo,
                                                      dqi_sync_work.work);
        struct super_block *sb = oinfo->dqi_gqinode->i_sb;

        /*
         * We have to be careful here not to deadlock on s_umount as umount
         * disabling quotas may be in progress and it waits for this work to
         * complete. If trylock fails, we'll do the sync next time...
         */
        if (down_read_trylock(&sb->s_umount)) {
                dquot_scan_active(sb, ocfs2_sync_dquot_helper, oinfo->dqi_type);
                up_read(&sb->s_umount);
        }
        schedule_delayed_work(&oinfo->dqi_sync_work,
                              msecs_to_jiffies(oinfo->dqi_syncms));
}

/*
 *  Wrappers for generic quota functions
 */

static int ocfs2_write_dquot(struct dquot *dquot)
{
        handle_t *handle;
        struct ocfs2_super *osb = OCFS2_SB(dquot->dq_sb);
        int status = 0;
        unsigned int memalloc;

        trace_ocfs2_write_dquot(from_kqid(&init_user_ns, dquot->dq_id),
                                dquot->dq_id.type);

        handle = ocfs2_start_trans(osb, OCFS2_QWRITE_CREDITS);
        if (IS_ERR(handle)) {
                status = PTR_ERR(handle);
                mlog_errno(status);
                goto out;
        }
        down_write(&sb_dqopt(dquot->dq_sb)->dqio_sem);
        memalloc = memalloc_nofs_save();
        status = ocfs2_local_write_dquot(dquot);
        memalloc_nofs_restore(memalloc);
        up_write(&sb_dqopt(dquot->dq_sb)->dqio_sem);
        ocfs2_commit_trans(osb, handle);
out:
        return status;
}

static int ocfs2_calc_qdel_credits(struct super_block *sb, int type)
{
        struct ocfs2_mem_dqinfo *oinfo = sb_dqinfo(sb, type)->dqi_priv;
        /*
         * We modify tree, leaf block, global info, local chunk header,
         * global and local inode; OCFS2_QINFO_WRITE_CREDITS already
         * accounts for inode update
         */
        return (oinfo->dqi_gi.dqi_qtree_depth + 2) *
               OCFS2_QUOTA_BLOCK_UPDATE_CREDITS +
               OCFS2_QINFO_WRITE_CREDITS +
               OCFS2_INODE_UPDATE_CREDITS;
}

void ocfs2_drop_dquot_refs(struct work_struct *work)
{
        struct ocfs2_super *osb = container_of(work, struct ocfs2_super,
                                               dquot_drop_work);
        struct llist_node *list;
        struct ocfs2_dquot *odquot, *next_odquot;

        list = llist_del_all(&osb->dquot_drop_list);
        llist_for_each_entry_safe(odquot, next_odquot, list, list) {
                /* Drop the reference we acquired in ocfs2_dquot_release() */
                dqput(&odquot->dq_dquot);
        }
}

/*
 * Called when the last reference to dquot is dropped. If we are called from
 * downconvert thread, we cannot do all the handling here because grabbing
 * quota lock could deadlock (the node holding the quota lock could need some
 * other cluster lock to proceed but with blocked downconvert thread we cannot
 * release any lock).
 */
static int ocfs2_release_dquot(struct dquot *dquot)
{
        handle_t *handle;
        struct ocfs2_mem_dqinfo *oinfo =
                        sb_dqinfo(dquot->dq_sb, dquot->dq_id.type)->dqi_priv;
        struct ocfs2_super *osb = OCFS2_SB(dquot->dq_sb);
        int status = 0;

        trace_ocfs2_release_dquot(from_kqid(&init_user_ns, dquot->dq_id),
                                  dquot->dq_id.type);

        mutex_lock(&dquot->dq_lock);
        /* Check whether we are not racing with some other dqget() */
        if (dquot_is_busy(dquot))
                goto out;
        /* Running from downconvert thread? Postpone quota processing to wq */
        if (current == osb->dc_task) {
                /*
                 * Grab our own reference to dquot and queue it for delayed
                 * dropping.  Quota code rechecks after calling
                 * ->release_dquot() and won't free dquot structure.
                 */
                dqgrab(dquot);
                /* First entry on list -> queue work */
                if (llist_add(&OCFS2_DQUOT(dquot)->list, &osb->dquot_drop_list))
                        queue_work(osb->ocfs2_wq, &osb->dquot_drop_work);
                goto out;
        }
        status = ocfs2_lock_global_qf(oinfo, 1);
        if (status < 0)
                goto out;
        handle = ocfs2_start_trans(osb,
                ocfs2_calc_qdel_credits(dquot->dq_sb, dquot->dq_id.type));
        if (IS_ERR(handle)) {
                status = PTR_ERR(handle);
                mlog_errno(status);
                goto out_ilock;
        }

        status = ocfs2_global_release_dquot(dquot);
        if (status < 0) {
                mlog_errno(status);
                goto out_trans;
        }
        status = ocfs2_local_release_dquot(handle, dquot);
        /*
         * If we fail here, we cannot do much as global structure is
         * already released. So just complain...
         */
        if (status < 0)
                mlog_errno(status);
        /*
         * Clear dq_off so that we search for the structure in quota file next
         * time we acquire it. The structure might be deleted and reallocated
         * elsewhere by another node while our dquot structure is on freelist.
         */
        dquot->dq_off = 0;
        clear_bit(DQ_ACTIVE_B, &dquot->dq_flags);
out_trans:
        ocfs2_commit_trans(osb, handle);
out_ilock:
        ocfs2_unlock_global_qf(oinfo, 1);
out:
        mutex_unlock(&dquot->dq_lock);
        if (status)
                mlog_errno(status);
        return status;
}

/*
 * Read global dquot structure from disk or create it if it does
 * not exist. Also update use count of the global structure and
 * create structure in node-local quota file.
 */
static int ocfs2_acquire_dquot(struct dquot *dquot)
{
        int status = 0, err;
        int ex = 0;
        struct super_block *sb = dquot->dq_sb;
        struct ocfs2_super *osb = OCFS2_SB(sb);
        int type = dquot->dq_id.type;
        struct ocfs2_mem_dqinfo *info = sb_dqinfo(sb, type)->dqi_priv;
        struct inode *gqinode = info->dqi_gqinode;
        int need_alloc = ocfs2_global_qinit_alloc(sb, type);
        handle_t *handle;

        trace_ocfs2_acquire_dquot(from_kqid(&init_user_ns, dquot->dq_id),
                                  type);
        mutex_lock(&dquot->dq_lock);
        /*
         * We need an exclusive lock, because we're going to update use count
         * and instantiate possibly new dquot structure
         */
        status = ocfs2_lock_global_qf(info, 1);
        if (status < 0)
                goto out;
        status = ocfs2_qinfo_lock(info, 0);
        if (status < 0)
                goto out_dq;
        /*
         * We always want to read dquot structure from disk because we don't
         * know what happened with it while it was on freelist.
         */
        status = qtree_read_dquot(&info->dqi_gi, dquot);
        ocfs2_qinfo_unlock(info, 0);
        if (status < 0)
                goto out_dq;

        OCFS2_DQUOT(dquot)->dq_use_count++;
        OCFS2_DQUOT(dquot)->dq_origspace = dquot->dq_dqb.dqb_curspace;
        OCFS2_DQUOT(dquot)->dq_originodes = dquot->dq_dqb.dqb_curinodes;
        if (!dquot->dq_off) {        /* No real quota entry? */
                ex = 1;
                /*
                 * Add blocks to quota file before we start a transaction since
                 * locking allocators ranks above a transaction start
                 */
                WARN_ON(journal_current_handle());
                status = ocfs2_extend_no_holes(gqinode, NULL,
                        i_size_read(gqinode) + (need_alloc << sb->s_blocksize_bits),
                        i_size_read(gqinode));
                if (status < 0)
                        goto out_dq;
        }

        handle = ocfs2_start_trans(osb,
                                   ocfs2_calc_global_qinit_credits(sb, type));
        if (IS_ERR(handle)) {
                status = PTR_ERR(handle);
                goto out_dq;
        }
        status = ocfs2_qinfo_lock(info, ex);
        if (status < 0)
                goto out_trans;
        status = qtree_write_dquot(&info->dqi_gi, dquot);
        if (ex && info_dirty(sb_dqinfo(sb, type))) {
                err = __ocfs2_global_write_info(sb, type);
                if (!status)
                        status = err;
        }
        ocfs2_qinfo_unlock(info, ex);
out_trans:
        ocfs2_commit_trans(osb, handle);
out_dq:
        ocfs2_unlock_global_qf(info, 1);
        if (status < 0)
                goto out;

        status = ocfs2_create_local_dquot(dquot);
        if (status < 0)
                goto out;
        set_bit(DQ_ACTIVE_B, &dquot->dq_flags);
out:
        mutex_unlock(&dquot->dq_lock);
        if (status)
                mlog_errno(status);
        return status;
}

static int ocfs2_get_next_id(struct super_block *sb, struct kqid *qid)
{
        int type = qid->type;
        struct ocfs2_mem_dqinfo *info = sb_dqinfo(sb, type)->dqi_priv;
        int status = 0;

        trace_ocfs2_get_next_id(from_kqid(&init_user_ns, *qid), type);
        if (!sb_has_quota_active(sb, type)) {
                status = -ESRCH;
                goto out;
        }
        status = ocfs2_lock_global_qf(info, 0);
        if (status < 0)
                goto out;
        status = ocfs2_qinfo_lock(info, 0);
        if (status < 0)
                goto out_global;
        status = qtree_get_next_id(&info->dqi_gi, qid);
        ocfs2_qinfo_unlock(info, 0);
out_global:
        ocfs2_unlock_global_qf(info, 0);
out:
        /*
         * Avoid logging ENOENT since it just means there isn't next ID and
         * ESRCH which means quota isn't enabled for the filesystem.
         */
        if (status && status != -ENOENT && status != -ESRCH)
                mlog_errno(status);
        return status;
}

static int ocfs2_mark_dquot_dirty(struct dquot *dquot)
{
        unsigned long mask = (1 << (DQ_LASTSET_B + QIF_ILIMITS_B)) |
                             (1 << (DQ_LASTSET_B + QIF_BLIMITS_B)) |
                             (1 << (DQ_LASTSET_B + QIF_INODES_B)) |
                             (1 << (DQ_LASTSET_B + QIF_SPACE_B)) |
                             (1 << (DQ_LASTSET_B + QIF_BTIME_B)) |
                             (1 << (DQ_LASTSET_B + QIF_ITIME_B));
        int sync = 0;
        int status;
        struct super_block *sb = dquot->dq_sb;
        int type = dquot->dq_id.type;
        struct ocfs2_mem_dqinfo *oinfo = sb_dqinfo(sb, type)->dqi_priv;
        handle_t *handle;
        struct ocfs2_super *osb = OCFS2_SB(sb);
        unsigned int memalloc;

        trace_ocfs2_mark_dquot_dirty(from_kqid(&init_user_ns, dquot->dq_id),
                                     type);

        /* In case user set some limits, sync dquot immediately to global
         * quota file so that information propagates quicker */
        spin_lock(&dquot->dq_dqb_lock);
        if (dquot->dq_flags & mask)
                sync = 1;
        spin_unlock(&dquot->dq_dqb_lock);
        /* This is a slight hack but we can't afford getting global quota
         * lock if we already have a transaction started. */
        if (!sync || journal_current_handle()) {
                status = ocfs2_write_dquot(dquot);
                goto out;
        }
        status = ocfs2_lock_global_qf(oinfo, 1);
        if (status < 0)
                goto out;
        handle = ocfs2_start_trans(osb, OCFS2_QSYNC_CREDITS);
        if (IS_ERR(handle)) {
                status = PTR_ERR(handle);
                mlog_errno(status);
                goto out_ilock;
        }
        down_write(&sb_dqopt(sb)->dqio_sem);
        memalloc = memalloc_nofs_save();
        status = ocfs2_sync_dquot(dquot);
        if (status < 0) {
                mlog_errno(status);
                goto out_dlock;
        }
        /* Now write updated local dquot structure */
        status = ocfs2_local_write_dquot(dquot);
out_dlock:
        memalloc_nofs_restore(memalloc);
        up_write(&sb_dqopt(sb)->dqio_sem);
        ocfs2_commit_trans(osb, handle);
out_ilock:
        ocfs2_unlock_global_qf(oinfo, 1);
out:
        if (status)
                mlog_errno(status);
        return status;
}

/* This should happen only after set_dqinfo(). */
static int ocfs2_write_info(struct super_block *sb, int type)
{
        handle_t *handle;
        int status = 0;
        struct ocfs2_mem_dqinfo *oinfo = sb_dqinfo(sb, type)->dqi_priv;

        status = ocfs2_lock_global_qf(oinfo, 1);
        if (status < 0)
                goto out;
        handle = ocfs2_start_trans(OCFS2_SB(sb), OCFS2_QINFO_WRITE_CREDITS);
        if (IS_ERR(handle)) {
                status = PTR_ERR(handle);
                mlog_errno(status);
                goto out_ilock;
        }
        status = dquot_commit_info(sb, type);
        ocfs2_commit_trans(OCFS2_SB(sb), handle);
out_ilock:
        ocfs2_unlock_global_qf(oinfo, 1);
out:
        if (status)
                mlog_errno(status);
        return status;
}

static struct dquot *ocfs2_alloc_dquot(struct super_block *sb, int type)
{
        struct ocfs2_dquot *dquot =
                                kmem_cache_zalloc(ocfs2_dquot_cachep, GFP_NOFS);

        if (!dquot)
                return NULL;
        return &dquot->dq_dquot;
}

static void ocfs2_destroy_dquot(struct dquot *dquot)
{
        kmem_cache_free(ocfs2_dquot_cachep, dquot);
}

const struct dquot_operations ocfs2_quota_operations = {
        /* We never make dquot dirty so .write_dquot is never called */
        .acquire_dquot        = ocfs2_acquire_dquot,
        .release_dquot        = ocfs2_release_dquot,
        .mark_dirty        = ocfs2_mark_dquot_dirty,
        .write_info        = ocfs2_write_info,
        .alloc_dquot        = ocfs2_alloc_dquot,
        .destroy_dquot        = ocfs2_destroy_dquot,
        .get_next_id        = ocfs2_get_next_id,
};
























































































































































































































































  153 















































































































































































































































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
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
/*
 * Header file for reservations for dma-buf and ttm
 *
 * Copyright(C) 2011 Linaro Limited. All rights reserved.
 * Copyright (C) 2012-2013 Canonical Ltd
 * Copyright (C) 2012 Texas Instruments
 *
 * Authors:
 * Rob Clark <robdclark@gmail.com>
 * Maarten Lankhorst <maarten.lankhorst@canonical.com>
 * Thomas Hellstrom <thellstrom-at-vmware-dot-com>
 *
 * Based on bo.c which bears the following copyright notice,
 * but is dual licensed:
 *
 * Copyright (c) 2006-2009 VMware, Inc., Palo Alto, CA., USA
 * All Rights Reserved.
 *
 * Permission is hereby granted, free of charge, to any person obtaining a
 * copy of this software and associated documentation files (the
 * "Software"), to deal in the Software without restriction, including
 * without limitation the rights to use, copy, modify, merge, publish,
 * distribute, sub license, and/or sell copies of the Software, and to
 * permit persons to whom the Software is furnished to do so, subject to
 * the following conditions:
 *
 * The above copyright notice and this permission notice (including the
 * next paragraph) shall be included in all copies or substantial portions
 * of the Software.
 *
 * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
 * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
 * FITNESS FOR A PARTICULAR PURPOSE AND NON-INFRINGEMENT. IN NO EVENT SHALL
 * THE COPYRIGHT HOLDERS, AUTHORS AND/OR ITS SUPPLIERS BE LIABLE FOR ANY CLAIM,
 * DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR
 * OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE
 * USE OR OTHER DEALINGS IN THE SOFTWARE.
 */
#ifndef _LINUX_RESERVATION_H
#define _LINUX_RESERVATION_H

#include <linux/ww_mutex.h>
#include <linux/dma-fence.h>
#include <linux/slab.h>
#include <linux/seqlock.h>
#include <linux/rcupdate.h>

extern struct ww_class reservation_ww_class;

struct dma_resv_list;

/**
 * enum dma_resv_usage - how the fences from a dma_resv obj are used
 *
 * This enum describes the different use cases for a dma_resv object and
 * controls which fences are returned when queried.
 *
 * An important fact is that there is the order KERNEL<WRITE<READ<BOOKKEEP and
 * when the dma_resv object is asked for fences for one use case the fences
 * for the lower use case are returned as well.
 *
 * For example when asking for WRITE fences then the KERNEL fences are returned
 * as well. Similar when asked for READ fences then both WRITE and KERNEL
 * fences are returned as well.
 *
 * Already used fences can be promoted in the sense that a fence with
 * DMA_RESV_USAGE_BOOKKEEP could become DMA_RESV_USAGE_READ by adding it again
 * with this usage. But fences can never be degraded in the sense that a fence
 * with DMA_RESV_USAGE_WRITE could become DMA_RESV_USAGE_READ.
 */
enum dma_resv_usage {
        /**
         * @DMA_RESV_USAGE_KERNEL: For in kernel memory management only.
         *
         * This should only be used for things like copying or clearing memory
         * with a DMA hardware engine for the purpose of kernel memory
         * management.
         *
         * Drivers *always* must wait for those fences before accessing the
         * resource protected by the dma_resv object. The only exception for
         * that is when the resource is known to be locked down in place by
         * pinning it previously.
         */
        DMA_RESV_USAGE_KERNEL,

        /**
         * @DMA_RESV_USAGE_WRITE: Implicit write synchronization.
         *
         * This should only be used for userspace command submissions which add
         * an implicit write dependency.
         */
        DMA_RESV_USAGE_WRITE,

        /**
         * @DMA_RESV_USAGE_READ: Implicit read synchronization.
         *
         * This should only be used for userspace command submissions which add
         * an implicit read dependency.
         */
        DMA_RESV_USAGE_READ,

        /**
         * @DMA_RESV_USAGE_BOOKKEEP: No implicit sync.
         *
         * This should be used by submissions which don't want to participate in
         * any implicit synchronization.
         *
         * The most common cases are preemption fences, page table updates, TLB
         * flushes as well as explicitly synced user submissions.
         *
         * Explicitly synced user submissions can be promoted to
         * DMA_RESV_USAGE_READ or DMA_RESV_USAGE_WRITE as needed using
         * dma_buf_import_sync_file() when implicit synchronization should
         * become necessary after initial adding of the fence.
         */
        DMA_RESV_USAGE_BOOKKEEP
};

/**
 * dma_resv_usage_rw - helper for implicit sync
 * @write: true if we create a new implicit sync write
 *
 * This returns the implicit synchronization usage for write or read accesses,
 * see enum dma_resv_usage and &dma_buf.resv.
 */
static inline enum dma_resv_usage dma_resv_usage_rw(bool write)
{
        /* This looks confusing at first sight, but is indeed correct.
         *
         * The rational is that new write operations needs to wait for the
         * existing read and write operations to finish.
         * But a new read operation only needs to wait for the existing write
         * operations to finish.
         */
        return write ? DMA_RESV_USAGE_READ : DMA_RESV_USAGE_WRITE;
}

/**
 * struct dma_resv - a reservation object manages fences for a buffer
 *
 * This is a container for dma_fence objects which needs to handle multiple use
 * cases.
 *
 * One use is to synchronize cross-driver access to a struct dma_buf, either for
 * dynamic buffer management or just to handle implicit synchronization between
 * different users of the buffer in userspace. See &dma_buf.resv for a more
 * in-depth discussion.
 *
 * The other major use is to manage access and locking within a driver in a
 * buffer based memory manager. struct ttm_buffer_object is the canonical
 * example here, since this is where reservation objects originated from. But
 * use in drivers is spreading and some drivers also manage struct
 * drm_gem_object with the same scheme.
 */
struct dma_resv {
        /**
         * @lock:
         *
         * Update side lock. Don't use directly, instead use the wrapper
         * functions like dma_resv_lock() and dma_resv_unlock().
         *
         * Drivers which use the reservation object to manage memory dynamically
         * also use this lock to protect buffer object state like placement,
         * allocation policies or throughout command submission.
         */
        struct ww_mutex lock;

        /**
         * @fences:
         *
         * Array of fences which where added to the dma_resv object
         *
         * A new fence is added by calling dma_resv_add_fence(). Since this
         * often needs to be done past the point of no return in command
         * submission it cannot fail, and therefore sufficient slots need to be
         * reserved by calling dma_resv_reserve_fences().
         */
        struct dma_resv_list __rcu *fences;
};

/**
 * struct dma_resv_iter - current position into the dma_resv fences
 *
 * Don't touch this directly in the driver, use the accessor function instead.
 *
 * IMPORTANT
 *
 * When using the lockless iterators like dma_resv_iter_next_unlocked() or
 * dma_resv_for_each_fence_unlocked() beware that the iterator can be restarted.
 * Code which accumulates statistics or similar needs to check for this with
 * dma_resv_iter_is_restarted().
 */
struct dma_resv_iter {
        /** @obj: The dma_resv object we iterate over */
        struct dma_resv *obj;

        /** @usage: Return fences with this usage or lower. */
        enum dma_resv_usage usage;

        /** @fence: the currently handled fence */
        struct dma_fence *fence;

        /** @fence_usage: the usage of the current fence */
        enum dma_resv_usage fence_usage;

        /** @index: index into the shared fences */
        unsigned int index;

        /** @fences: the shared fences; private, *MUST* not dereference  */
        struct dma_resv_list *fences;

        /** @num_fences: number of fences */
        unsigned int num_fences;

        /** @is_restarted: true if this is the first returned fence */
        bool is_restarted;
};

struct dma_fence *dma_resv_iter_first_unlocked(struct dma_resv_iter *cursor);
struct dma_fence *dma_resv_iter_next_unlocked(struct dma_resv_iter *cursor);
struct dma_fence *dma_resv_iter_first(struct dma_resv_iter *cursor);
struct dma_fence *dma_resv_iter_next(struct dma_resv_iter *cursor);

/**
 * dma_resv_iter_begin - initialize a dma_resv_iter object
 * @cursor: The dma_resv_iter object to initialize
 * @obj: The dma_resv object which we want to iterate over
 * @usage: controls which fences to include, see enum dma_resv_usage.
 */
static inline void dma_resv_iter_begin(struct dma_resv_iter *cursor,
                                       struct dma_resv *obj,
                                       enum dma_resv_usage usage)
{
        cursor->obj = obj;
        cursor->usage = usage;
        cursor->fence = NULL;
}

/**
 * dma_resv_iter_end - cleanup a dma_resv_iter object
 * @cursor: the dma_resv_iter object which should be cleaned up
 *
 * Make sure that the reference to the fence in the cursor is properly
 * dropped.
 */
static inline void dma_resv_iter_end(struct dma_resv_iter *cursor)
{
        dma_fence_put(cursor->fence);
}

/**
 * dma_resv_iter_usage - Return the usage of the current fence
 * @cursor: the cursor of the current position
 *
 * Returns the usage of the currently processed fence.
 */
static inline enum dma_resv_usage
dma_resv_iter_usage(struct dma_resv_iter *cursor)
{
        return cursor->fence_usage;
}

/**
 * dma_resv_iter_is_restarted - test if this is the first fence after a restart
 * @cursor: the cursor with the current position
 *
 * Return true if this is the first fence in an iteration after a restart.
 */
static inline bool dma_resv_iter_is_restarted(struct dma_resv_iter *cursor)
{
        return cursor->is_restarted;
}

/**
 * dma_resv_for_each_fence_unlocked - unlocked fence iterator
 * @cursor: a struct dma_resv_iter pointer
 * @fence: the current fence
 *
 * Iterate over the fences in a struct dma_resv object without holding the
 * &dma_resv.lock and using RCU instead. The cursor needs to be initialized
 * with dma_resv_iter_begin() and cleaned up with dma_resv_iter_end(). Inside
 * the iterator a reference to the dma_fence is held and the RCU lock dropped.
 *
 * Beware that the iterator can be restarted when the struct dma_resv for
 * @cursor is modified. Code which accumulates statistics or similar needs to
 * check for this with dma_resv_iter_is_restarted(). For this reason prefer the
 * lock iterator dma_resv_for_each_fence() whenever possible.
 */
#define dma_resv_for_each_fence_unlocked(cursor, fence)                        \
        for (fence = dma_resv_iter_first_unlocked(cursor);                \
             fence; fence = dma_resv_iter_next_unlocked(cursor))

/**
 * dma_resv_for_each_fence - fence iterator
 * @cursor: a struct dma_resv_iter pointer
 * @obj: a dma_resv object pointer
 * @usage: controls which fences to return
 * @fence: the current fence
 *
 * Iterate over the fences in a struct dma_resv object while holding the
 * &dma_resv.lock. @all_fences controls if the shared fences are returned as
 * well. The cursor initialisation is part of the iterator and the fence stays
 * valid as long as the lock is held and so no extra reference to the fence is
 * taken.
 */
#define dma_resv_for_each_fence(cursor, obj, usage, fence)        \
        for (dma_resv_iter_begin(cursor, obj, usage),        \
             fence = dma_resv_iter_first(cursor); fence;        \
             fence = dma_resv_iter_next(cursor))

#define dma_resv_held(obj) lockdep_is_held(&(obj)->lock.base)
#define dma_resv_assert_held(obj) lockdep_assert_held(&(obj)->lock.base)

#ifdef CONFIG_DEBUG_MUTEXES
void dma_resv_reset_max_fences(struct dma_resv *obj);
#else
static inline void dma_resv_reset_max_fences(struct dma_resv *obj) {}
#endif

/**
 * dma_resv_lock - lock the reservation object
 * @obj: the reservation object
 * @ctx: the locking context
 *
 * Locks the reservation object for exclusive access and modification. Note,
 * that the lock is only against other writers, readers will run concurrently
 * with a writer under RCU. The seqlock is used to notify readers if they
 * overlap with a writer.
 *
 * As the reservation object may be locked by multiple parties in an
 * undefined order, a #ww_acquire_ctx is passed to unwind if a cycle
 * is detected. See ww_mutex_lock() and ww_acquire_init(). A reservation
 * object may be locked by itself by passing NULL as @ctx.
 *
 * When a die situation is indicated by returning -EDEADLK all locks held by
 * @ctx must be unlocked and then dma_resv_lock_slow() called on @obj.
 *
 * Unlocked by calling dma_resv_unlock().
 *
 * See also dma_resv_lock_interruptible() for the interruptible variant.
 */
static inline int dma_resv_lock(struct dma_resv *obj,
                                struct ww_acquire_ctx *ctx)
{
        return ww_mutex_lock(&obj->lock, ctx);
}

/**
 * dma_resv_lock_interruptible - lock the reservation object
 * @obj: the reservation object
 * @ctx: the locking context
 *
 * Locks the reservation object interruptible for exclusive access and
 * modification. Note, that the lock is only against other writers, readers
 * will run concurrently with a writer under RCU. The seqlock is used to
 * notify readers if they overlap with a writer.
 *
 * As the reservation object may be locked by multiple parties in an
 * undefined order, a #ww_acquire_ctx is passed to unwind if a cycle
 * is detected. See ww_mutex_lock() and ww_acquire_init(). A reservation
 * object may be locked by itself by passing NULL as @ctx.
 *
 * When a die situation is indicated by returning -EDEADLK all locks held by
 * @ctx must be unlocked and then dma_resv_lock_slow_interruptible() called on
 * @obj.
 *
 * Unlocked by calling dma_resv_unlock().
 */
static inline int dma_resv_lock_interruptible(struct dma_resv *obj,
                                              struct ww_acquire_ctx *ctx)
{
        return ww_mutex_lock_interruptible(&obj->lock, ctx);
}

/**
 * dma_resv_lock_slow - slowpath lock the reservation object
 * @obj: the reservation object
 * @ctx: the locking context
 *
 * Acquires the reservation object after a die case. This function
 * will sleep until the lock becomes available. See dma_resv_lock() as
 * well.
 *
 * See also dma_resv_lock_slow_interruptible() for the interruptible variant.
 */
static inline void dma_resv_lock_slow(struct dma_resv *obj,
                                      struct ww_acquire_ctx *ctx)
{
        ww_mutex_lock_slow(&obj->lock, ctx);
}

/**
 * dma_resv_lock_slow_interruptible - slowpath lock the reservation
 * object, interruptible
 * @obj: the reservation object
 * @ctx: the locking context
 *
 * Acquires the reservation object interruptible after a die case. This function
 * will sleep until the lock becomes available. See
 * dma_resv_lock_interruptible() as well.
 */
static inline int dma_resv_lock_slow_interruptible(struct dma_resv *obj,
                                                   struct ww_acquire_ctx *ctx)
{
        return ww_mutex_lock_slow_interruptible(&obj->lock, ctx);
}

/**
 * dma_resv_trylock - trylock the reservation object
 * @obj: the reservation object
 *
 * Tries to lock the reservation object for exclusive access and modification.
 * Note, that the lock is only against other writers, readers will run
 * concurrently with a writer under RCU. The seqlock is used to notify readers
 * if they overlap with a writer.
 *
 * Also note that since no context is provided, no deadlock protection is
 * possible, which is also not needed for a trylock.
 *
 * Returns true if the lock was acquired, false otherwise.
 */
static inline bool __must_check dma_resv_trylock(struct dma_resv *obj)
{
        return ww_mutex_trylock(&obj->lock, NULL);
}

/**
 * dma_resv_is_locked - is the reservation object locked
 * @obj: the reservation object
 *
 * Returns true if the mutex is locked, false if unlocked.
 */
static inline bool dma_resv_is_locked(struct dma_resv *obj)
{
        return ww_mutex_is_locked(&obj->lock);
}

/**
 * dma_resv_locking_ctx - returns the context used to lock the object
 * @obj: the reservation object
 *
 * Returns the context used to lock a reservation object or NULL if no context
 * was used or the object is not locked at all.
 *
 * WARNING: This interface is pretty horrible, but TTM needs it because it
 * doesn't pass the struct ww_acquire_ctx around in some very long callchains.
 * Everyone else just uses it to check whether they're holding a reservation or
 * not.
 */
static inline struct ww_acquire_ctx *dma_resv_locking_ctx(struct dma_resv *obj)
{
        return READ_ONCE(obj->lock.ctx);
}

/**
 * dma_resv_unlock - unlock the reservation object
 * @obj: the reservation object
 *
 * Unlocks the reservation object following exclusive access.
 */
static inline void dma_resv_unlock(struct dma_resv *obj)
{
        dma_resv_reset_max_fences(obj);
        ww_mutex_unlock(&obj->lock);
}

void dma_resv_init(struct dma_resv *obj);
void dma_resv_fini(struct dma_resv *obj);
int dma_resv_reserve_fences(struct dma_resv *obj, unsigned int num_fences);
void dma_resv_add_fence(struct dma_resv *obj, struct dma_fence *fence,
                        enum dma_resv_usage usage);
void dma_resv_replace_fences(struct dma_resv *obj, uint64_t context,
                             struct dma_fence *fence,
                             enum dma_resv_usage usage);
int dma_resv_get_fences(struct dma_resv *obj, enum dma_resv_usage usage,
                        unsigned int *num_fences, struct dma_fence ***fences);
int dma_resv_get_singleton(struct dma_resv *obj, enum dma_resv_usage usage,
                           struct dma_fence **fence);
int dma_resv_copy_fences(struct dma_resv *dst, struct dma_resv *src);
long dma_resv_wait_timeout(struct dma_resv *obj, enum dma_resv_usage usage,
                           bool intr, unsigned long timeout);
void dma_resv_set_deadline(struct dma_resv *obj, enum dma_resv_usage usage,
                           ktime_t deadline);
bool dma_resv_test_signaled(struct dma_resv *obj, enum dma_resv_usage usage);
void dma_resv_describe(struct dma_resv *obj, struct seq_file *seq);

#endif /* _LINUX_RESERVATION_H */



































































  150 







  150 



  129 













  115 

  114 















   14 
   12 






    5 

    1 




  126 


  125 
  126 

  126 



















   10 


   10 

   10 


    3 







   21 
   21 





    7 
    7 
    7 




   14 
   14 






   19 


    7 
    1 


    1 












    5 




    5 








    4 



















   11 








   11 







    6 
    5 

   11 
    6 


    5 
    4 


    1 






    5 





    4 
    4 

    4 




























    2 


   21 




   16 


    6 





   11 


    1 








    2 


    1 


   22 




   22 




   16 


    3 
    2 




    8 

    1 
    2 





   11 

   12 




    2 









    1 






    8 











   48 





   48 






    1 






    3 


   17 

   17 




    9 


    8 



    6 
   11 





    9 
    8 





   21 










    8 
    1 










   24 












   18 




    6 








   24 


    8 





    8 





















































































   14 


    3 








    7 
    5 











   27 


    4 




   23 






   56 


    4 



    4 







    3 






    5 














    5 







   65 













   66 

   15 














   41 


   12 







   22 


   13 


   14 





   27 
   27 
   24 

    3 


   27 


    9 


   33 
    1 



    4 

   35 
   35 


   10 

    4 
    6 
    6 
   19 


   34 










    2 
    3 




   31 



   27 



   25 
    5 
















    3 

   27 





   26 
    9 
   11 
   27 






    3 








   19 





   19 


    1 



    1 


    3 



    4 
   12 





    1 


   15 





    2 
    2 






    2 
    2 






    2 




    8 
    1 

    9 




   11 
    4 


    4 
    7 












   18 









    3 



    1 



    2 













   13 



   13 



   13 






   10 


    3 

    3 




    1 
   11 




































   11 



   11 

   11 


    3 
    9 










    8 





    2 


    8 




    9 
   11 


    7 






    6 






   11 




    5 
    5 



   11 



   11 

    8 








   11 


























    5 


    5 



















   27 




































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
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
1187
1188
1189
1190
1191
1192
1193
1194
1195
// SPDX-License-Identifier: GPL-2.0-or-later
/*
 * INET                An implementation of the TCP/IP protocol suite for the LINUX
 *                operating system.  INET is implemented using the  BSD Socket
 *                interface as the means of communication with the user level.
 *
 *                "Ping" sockets
 *
 * Based on ipv4/udp.c code.
 *
 * Authors:        Vasiliy Kulikov / Openwall (for Linux 2.6),
 *                Pavel Kankovsky (for Linux 2.4.32)
 *
 * Pavel gave all rights to bugs to Vasiliy,
 * none of the bugs are Pavel's now.
 */

#include <linux/uaccess.h>
#include <linux/types.h>
#include <linux/fcntl.h>
#include <linux/socket.h>
#include <linux/sockios.h>
#include <linux/in.h>
#include <linux/errno.h>
#include <linux/timer.h>
#include <linux/mm.h>
#include <linux/inet.h>
#include <linux/netdevice.h>
#include <net/snmp.h>
#include <net/ip.h>
#include <net/icmp.h>
#include <net/protocol.h>
#include <linux/skbuff.h>
#include <linux/proc_fs.h>
#include <linux/export.h>
#include <linux/bpf-cgroup.h>
#include <net/sock.h>
#include <net/ping.h>
#include <net/udp.h>
#include <net/route.h>
#include <net/inet_common.h>
#include <net/checksum.h>

#if IS_ENABLED(CONFIG_IPV6)
#include <linux/in6.h>
#include <linux/icmpv6.h>
#include <net/addrconf.h>
#include <net/ipv6.h>
#include <net/transp_v6.h>
#endif

struct ping_table {
        struct hlist_head        hash[PING_HTABLE_SIZE];
        spinlock_t                lock;
};

static struct ping_table ping_table;
struct pingv6_ops pingv6_ops;
EXPORT_SYMBOL_GPL(pingv6_ops);

static u16 ping_port_rover;

static inline u32 ping_hashfn(const struct net *net, u32 num, u32 mask)
{
        u32 res = (num + net_hash_mix(net)) & mask;

        pr_debug("hash(%u) = %u\n", num, res);
        return res;
}
EXPORT_SYMBOL_GPL(ping_hash);

static inline struct hlist_head *ping_hashslot(struct ping_table *table,
                                               struct net *net, unsigned int num)
{
        return &table->hash[ping_hashfn(net, num, PING_HTABLE_MASK)];
}

int ping_get_port(struct sock *sk, unsigned short ident)
{
        struct inet_sock *isk, *isk2;
        struct hlist_head *hlist;
        struct sock *sk2 = NULL;

        isk = inet_sk(sk);
        spin_lock(&ping_table.lock);
        if (ident == 0) {
                u32 i;
                u16 result = ping_port_rover + 1;

                for (i = 0; i < (1L << 16); i++, result++) {
                        if (!result)
                                result++; /* avoid zero */
                        hlist = ping_hashslot(&ping_table, sock_net(sk),
                                            result);
                        sk_for_each(sk2, hlist) {
                                isk2 = inet_sk(sk2);

                                if (isk2->inet_num == result)
                                        goto next_port;
                        }

                        /* found */
                        ping_port_rover = ident = result;
                        break;
next_port:
                        ;
                }
                if (i >= (1L << 16))
                        goto fail;
        } else {
                hlist = ping_hashslot(&ping_table, sock_net(sk), ident);
                sk_for_each(sk2, hlist) {
                        isk2 = inet_sk(sk2);

                        /* BUG? Why is this reuse and not reuseaddr? ping.c
                         * doesn't turn off SO_REUSEADDR, and it doesn't expect
                         * that other ping processes can steal its packets.
                         */
                        if ((isk2->inet_num == ident) &&
                            (sk2 != sk) &&
                            (!sk2->sk_reuse || !sk->sk_reuse))
                                goto fail;
                }
        }

        pr_debug("found port/ident = %d\n", ident);
        isk->inet_num = ident;
        if (sk_unhashed(sk)) {
                pr_debug("was not hashed\n");
                sk_add_node_rcu(sk, hlist);
                sock_set_flag(sk, SOCK_RCU_FREE);
                sock_prot_inuse_add(sock_net(sk), sk->sk_prot, 1);
        }
        spin_unlock(&ping_table.lock);
        return 0;

fail:
        spin_unlock(&ping_table.lock);
        return -EADDRINUSE;
}
EXPORT_SYMBOL_GPL(ping_get_port);

int ping_hash(struct sock *sk)
{
        pr_debug("ping_hash(sk->port=%u)\n", inet_sk(sk)->inet_num);
        BUG(); /* "Please do not press this button again." */

        return 0;
}

void ping_unhash(struct sock *sk)
{
        struct inet_sock *isk = inet_sk(sk);

        pr_debug("ping_unhash(isk=%p,isk->num=%u)\n", isk, isk->inet_num);
        spin_lock(&ping_table.lock);
        if (sk_del_node_init_rcu(sk)) {
                isk->inet_num = 0;
                isk->inet_sport = 0;
                sock_prot_inuse_add(sock_net(sk), sk->sk_prot, -1);
        }
        spin_unlock(&ping_table.lock);
}
EXPORT_SYMBOL_GPL(ping_unhash);

/* Called under rcu_read_lock() */
static struct sock *ping_lookup(struct net *net, struct sk_buff *skb, u16 ident)
{
        struct hlist_head *hslot = ping_hashslot(&ping_table, net, ident);
        struct sock *sk = NULL;
        struct inet_sock *isk;
        int dif, sdif;

        if (skb->protocol == htons(ETH_P_IP)) {
                dif = inet_iif(skb);
                sdif = inet_sdif(skb);
                pr_debug("try to find: num = %d, daddr = %pI4, dif = %d\n",
                         (int)ident, &ip_hdr(skb)->daddr, dif);
#if IS_ENABLED(CONFIG_IPV6)
        } else if (skb->protocol == htons(ETH_P_IPV6)) {
                dif = inet6_iif(skb);
                sdif = inet6_sdif(skb);
                pr_debug("try to find: num = %d, daddr = %pI6c, dif = %d\n",
                         (int)ident, &ipv6_hdr(skb)->daddr, dif);
#endif
        } else {
                return NULL;
        }

        sk_for_each_rcu(sk, hslot) {
                isk = inet_sk(sk);

                pr_debug("iterate\n");
                if (isk->inet_num != ident)
                        continue;

                if (skb->protocol == htons(ETH_P_IP) &&
                    sk->sk_family == AF_INET) {
                        pr_debug("found: %p: num=%d, daddr=%pI4, dif=%d\n", sk,
                                 (int) isk->inet_num, &isk->inet_rcv_saddr,
                                 sk->sk_bound_dev_if);

                        if (isk->inet_rcv_saddr &&
                            isk->inet_rcv_saddr != ip_hdr(skb)->daddr)
                                continue;
#if IS_ENABLED(CONFIG_IPV6)
                } else if (skb->protocol == htons(ETH_P_IPV6) &&
                           sk->sk_family == AF_INET6) {

                        pr_debug("found: %p: num=%d, daddr=%pI6c, dif=%d\n", sk,
                                 (int) isk->inet_num,
                                 &sk->sk_v6_rcv_saddr,
                                 sk->sk_bound_dev_if);

                        if (!ipv6_addr_any(&sk->sk_v6_rcv_saddr) &&
                            !ipv6_addr_equal(&sk->sk_v6_rcv_saddr,
                                             &ipv6_hdr(skb)->daddr))
                                continue;
#endif
                } else {
                        continue;
                }

                if (sk->sk_bound_dev_if && sk->sk_bound_dev_if != dif &&
                    sk->sk_bound_dev_if != sdif)
                        continue;

                goto exit;
        }

        sk = NULL;
exit:

        return sk;
}

static void inet_get_ping_group_range_net(struct net *net, kgid_t *low,
                                          kgid_t *high)
{
        kgid_t *data = net->ipv4.ping_group_range.range;
        unsigned int seq;

        do {
                seq = read_seqbegin(&net->ipv4.ping_group_range.lock);

                *low = data[0];
                *high = data[1];
        } while (read_seqretry(&net->ipv4.ping_group_range.lock, seq));
}


int ping_init_sock(struct sock *sk)
{
        struct net *net = sock_net(sk);
        kgid_t group = current_egid();
        struct group_info *group_info;
        int i;
        kgid_t low, high;
        int ret = 0;

        if (sk->sk_family == AF_INET6)
                sk->sk_ipv6only = 1;

        inet_get_ping_group_range_net(net, &low, &high);
        if (gid_lte(low, group) && gid_lte(group, high))
                return 0;

        group_info = get_current_groups();
        for (i = 0; i < group_info->ngroups; i++) {
                kgid_t gid = group_info->gid[i];

                if (gid_lte(low, gid) && gid_lte(gid, high))
                        goto out_release_group;
        }

        ret = -EACCES;

out_release_group:
        put_group_info(group_info);
        return ret;
}
EXPORT_SYMBOL_GPL(ping_init_sock);

void ping_close(struct sock *sk, long timeout)
{
        pr_debug("ping_close(sk=%p,sk->num=%u)\n",
                 inet_sk(sk), inet_sk(sk)->inet_num);
        pr_debug("isk->refcnt = %d\n", refcount_read(&sk->sk_refcnt));

        sk_common_release(sk);
}
EXPORT_SYMBOL_GPL(ping_close);

static int ping_pre_connect(struct sock *sk, struct sockaddr *uaddr,
                            int addr_len)
{
        /* This check is replicated from __ip4_datagram_connect() and
         * intended to prevent BPF program called below from accessing bytes
         * that are out of the bound specified by user in addr_len.
         */
        if (addr_len < sizeof(struct sockaddr_in))
                return -EINVAL;

        return BPF_CGROUP_RUN_PROG_INET4_CONNECT_LOCK(sk, uaddr, &addr_len);
}

/* Checks the bind address and possibly modifies sk->sk_bound_dev_if. */
static int ping_check_bind_addr(struct sock *sk, struct inet_sock *isk,
                                struct sockaddr *uaddr, int addr_len)
{
        struct net *net = sock_net(sk);
        if (sk->sk_family == AF_INET) {
                struct sockaddr_in *addr = (struct sockaddr_in *) uaddr;
                u32 tb_id = RT_TABLE_LOCAL;
                int chk_addr_ret;

                if (addr_len < sizeof(*addr))
                        return -EINVAL;

                if (addr->sin_family != AF_INET &&
                    !(addr->sin_family == AF_UNSPEC &&
                      addr->sin_addr.s_addr == htonl(INADDR_ANY)))
                        return -EAFNOSUPPORT;

                pr_debug("ping_check_bind_addr(sk=%p,addr=%pI4,port=%d)\n",
                         sk, &addr->sin_addr.s_addr, ntohs(addr->sin_port));

                if (addr->sin_addr.s_addr == htonl(INADDR_ANY))
                        return 0;

                tb_id = l3mdev_fib_table_by_index(net, sk->sk_bound_dev_if) ? : tb_id;
                chk_addr_ret = inet_addr_type_table(net, addr->sin_addr.s_addr, tb_id);

                if (chk_addr_ret == RTN_MULTICAST ||
                    chk_addr_ret == RTN_BROADCAST ||
                    (chk_addr_ret != RTN_LOCAL &&
                     !inet_can_nonlocal_bind(net, isk)))
                        return -EADDRNOTAVAIL;

#if IS_ENABLED(CONFIG_IPV6)
        } else if (sk->sk_family == AF_INET6) {
                struct sockaddr_in6 *addr = (struct sockaddr_in6 *) uaddr;
                int addr_type, scoped, has_addr;
                struct net_device *dev = NULL;

                if (addr_len < sizeof(*addr))
                        return -EINVAL;

                if (addr->sin6_family != AF_INET6)
                        return -EAFNOSUPPORT;

                pr_debug("ping_check_bind_addr(sk=%p,addr=%pI6c,port=%d)\n",
                         sk, addr->sin6_addr.s6_addr, ntohs(addr->sin6_port));

                addr_type = ipv6_addr_type(&addr->sin6_addr);
                scoped = __ipv6_addr_needs_scope_id(addr_type);
                if ((addr_type != IPV6_ADDR_ANY &&
                     !(addr_type & IPV6_ADDR_UNICAST)) ||
                    (scoped && !addr->sin6_scope_id))
                        return -EINVAL;

                rcu_read_lock();
                if (addr->sin6_scope_id) {
                        dev = dev_get_by_index_rcu(net, addr->sin6_scope_id);
                        if (!dev) {
                                rcu_read_unlock();
                                return -ENODEV;
                        }
                }

                if (!dev && sk->sk_bound_dev_if) {
                        dev = dev_get_by_index_rcu(net, sk->sk_bound_dev_if);
                        if (!dev) {
                                rcu_read_unlock();
                                return -ENODEV;
                        }
                }
                has_addr = pingv6_ops.ipv6_chk_addr(net, &addr->sin6_addr, dev,
                                                    scoped);
                rcu_read_unlock();

                if (!(ipv6_can_nonlocal_bind(net, isk) || has_addr ||
                      addr_type == IPV6_ADDR_ANY))
                        return -EADDRNOTAVAIL;

                if (scoped)
                        sk->sk_bound_dev_if = addr->sin6_scope_id;
#endif
        } else {
                return -EAFNOSUPPORT;
        }
        return 0;
}

static void ping_set_saddr(struct sock *sk, struct sockaddr *saddr)
{
        if (saddr->sa_family == AF_INET) {
                struct inet_sock *isk = inet_sk(sk);
                struct sockaddr_in *addr = (struct sockaddr_in *) saddr;
                isk->inet_rcv_saddr = isk->inet_saddr = addr->sin_addr.s_addr;
#if IS_ENABLED(CONFIG_IPV6)
        } else if (saddr->sa_family == AF_INET6) {
                struct sockaddr_in6 *addr = (struct sockaddr_in6 *) saddr;
                struct ipv6_pinfo *np = inet6_sk(sk);
                sk->sk_v6_rcv_saddr = np->saddr = addr->sin6_addr;
#endif
        }
}

/*
 * We need our own bind because there are no privileged id's == local ports.
 * Moreover, we don't allow binding to multi- and broadcast addresses.
 */

int ping_bind(struct sock *sk, struct sockaddr *uaddr, int addr_len)
{
        struct inet_sock *isk = inet_sk(sk);
        unsigned short snum;
        int err;
        int dif = sk->sk_bound_dev_if;

        err = ping_check_bind_addr(sk, isk, uaddr, addr_len);
        if (err)
                return err;

        lock_sock(sk);

        err = -EINVAL;
        if (isk->inet_num != 0)
                goto out;

        err = -EADDRINUSE;
        snum = ntohs(((struct sockaddr_in *)uaddr)->sin_port);
        if (ping_get_port(sk, snum) != 0) {
                /* Restore possibly modified sk->sk_bound_dev_if by ping_check_bind_addr(). */
                sk->sk_bound_dev_if = dif;
                goto out;
        }
        ping_set_saddr(sk, uaddr);

        pr_debug("after bind(): num = %hu, dif = %d\n",
                 isk->inet_num,
                 sk->sk_bound_dev_if);

        err = 0;
        if (sk->sk_family == AF_INET && isk->inet_rcv_saddr)
                sk->sk_userlocks |= SOCK_BINDADDR_LOCK;
#if IS_ENABLED(CONFIG_IPV6)
        if (sk->sk_family == AF_INET6 && !ipv6_addr_any(&sk->sk_v6_rcv_saddr))
                sk->sk_userlocks |= SOCK_BINDADDR_LOCK;
#endif

        if (snum)
                sk->sk_userlocks |= SOCK_BINDPORT_LOCK;
        isk->inet_sport = htons(isk->inet_num);
        isk->inet_daddr = 0;
        isk->inet_dport = 0;

#if IS_ENABLED(CONFIG_IPV6)
        if (sk->sk_family == AF_INET6)
                memset(&sk->sk_v6_daddr, 0, sizeof(sk->sk_v6_daddr));
#endif

        sk_dst_reset(sk);
out:
        release_sock(sk);
        pr_debug("ping_v4_bind -> %d\n", err);
        return err;
}
EXPORT_SYMBOL_GPL(ping_bind);

/*
 * Is this a supported type of ICMP message?
 */

static inline int ping_supported(int family, int type, int code)
{
        return (family == AF_INET && type == ICMP_ECHO && code == 0) ||
               (family == AF_INET && type == ICMP_EXT_ECHO && code == 0) ||
               (family == AF_INET6 && type == ICMPV6_ECHO_REQUEST && code == 0) ||
               (family == AF_INET6 && type == ICMPV6_EXT_ECHO_REQUEST && code == 0);
}

/*
 * This routine is called by the ICMP module when it gets some
 * sort of error condition.
 */

void ping_err(struct sk_buff *skb, int offset, u32 info)
{
        int family;
        struct icmphdr *icmph;
        struct inet_sock *inet_sock;
        int type;
        int code;
        struct net *net = dev_net(skb->dev);
        struct sock *sk;
        int harderr;
        int err;

        if (skb->protocol == htons(ETH_P_IP)) {
                family = AF_INET;
                type = icmp_hdr(skb)->type;
                code = icmp_hdr(skb)->code;
                icmph = (struct icmphdr *)(skb->data + offset);
        } else if (skb->protocol == htons(ETH_P_IPV6)) {
                family = AF_INET6;
                type = icmp6_hdr(skb)->icmp6_type;
                code = icmp6_hdr(skb)->icmp6_code;
                icmph = (struct icmphdr *) (skb->data + offset);
        } else {
                BUG();
        }

        /* We assume the packet has already been checked by icmp_unreach */

        if (!ping_supported(family, icmph->type, icmph->code))
                return;

        pr_debug("ping_err(proto=0x%x,type=%d,code=%d,id=%04x,seq=%04x)\n",
                 skb->protocol, type, code, ntohs(icmph->un.echo.id),
                 ntohs(icmph->un.echo.sequence));

        sk = ping_lookup(net, skb, ntohs(icmph->un.echo.id));
        if (!sk) {
                pr_debug("no socket, dropping\n");
                return;        /* No socket for error */
        }
        pr_debug("err on socket %p\n", sk);

        err = 0;
        harderr = 0;
        inet_sock = inet_sk(sk);

        if (skb->protocol == htons(ETH_P_IP)) {
                switch (type) {
                default:
                case ICMP_TIME_EXCEEDED:
                        err = EHOSTUNREACH;
                        break;
                case ICMP_SOURCE_QUENCH:
                        /* This is not a real error but ping wants to see it.
                         * Report it with some fake errno.
                         */
                        err = EREMOTEIO;
                        break;
                case ICMP_PARAMETERPROB:
                        err = EPROTO;
                        harderr = 1;
                        break;
                case ICMP_DEST_UNREACH:
                        if (code == ICMP_FRAG_NEEDED) { /* Path MTU discovery */
                                ipv4_sk_update_pmtu(skb, sk, info);
                                if (READ_ONCE(inet_sock->pmtudisc) != IP_PMTUDISC_DONT) {
                                        err = EMSGSIZE;
                                        harderr = 1;
                                        break;
                                }
                                goto out;
                        }
                        err = EHOSTUNREACH;
                        if (code <= NR_ICMP_UNREACH) {
                                harderr = icmp_err_convert[code].fatal;
                                err = icmp_err_convert[code].errno;
                        }
                        break;
                case ICMP_REDIRECT:
                        /* See ICMP_SOURCE_QUENCH */
                        ipv4_sk_redirect(skb, sk);
                        err = EREMOTEIO;
                        break;
                }
#if IS_ENABLED(CONFIG_IPV6)
        } else if (skb->protocol == htons(ETH_P_IPV6)) {
                harderr = pingv6_ops.icmpv6_err_convert(type, code, &err);
#endif
        }

        /*
         *      RFC1122: OK.  Passes ICMP errors back to application, as per
         *        4.1.3.3.
         */
        if ((family == AF_INET && !inet_test_bit(RECVERR, sk)) ||
            (family == AF_INET6 && !inet6_test_bit(RECVERR6, sk))) {
                if (!harderr || sk->sk_state != TCP_ESTABLISHED)
                        goto out;
        } else {
                if (family == AF_INET) {
                        ip_icmp_error(sk, skb, err, 0 /* no remote port */,
                                      info, (u8 *)icmph);
#if IS_ENABLED(CONFIG_IPV6)
                } else if (family == AF_INET6) {
                        pingv6_ops.ipv6_icmp_error(sk, skb, err, 0,
                                                   info, (u8 *)icmph);
#endif
                }
        }
        sk->sk_err = err;
        sk_error_report(sk);
out:
        return;
}
EXPORT_SYMBOL_GPL(ping_err);

/*
 *        Copy and checksum an ICMP Echo packet from user space into a buffer
 *        starting from the payload.
 */

int ping_getfrag(void *from, char *to,
                 int offset, int fraglen, int odd, struct sk_buff *skb)
{
        struct pingfakehdr *pfh = from;

        if (!csum_and_copy_from_iter_full(to, fraglen, &pfh->wcheck,
                                          &pfh->msg->msg_iter))
                return -EFAULT;

#if IS_ENABLED(CONFIG_IPV6)
        /* For IPv6, checksum each skb as we go along, as expected by
         * icmpv6_push_pending_frames. For IPv4, accumulate the checksum in
         * wcheck, it will be finalized in ping_v4_push_pending_frames.
         */
        if (pfh->family == AF_INET6) {
                skb->csum = csum_block_add(skb->csum, pfh->wcheck, odd);
                skb->ip_summed = CHECKSUM_NONE;
                pfh->wcheck = 0;
        }
#endif

        return 0;
}
EXPORT_SYMBOL_GPL(ping_getfrag);

static int ping_v4_push_pending_frames(struct sock *sk, struct pingfakehdr *pfh,
                                       struct flowi4 *fl4)
{
        struct sk_buff *skb = skb_peek(&sk->sk_write_queue);

        if (!skb)
                return 0;
        pfh->wcheck = csum_partial((char *)&pfh->icmph,
                sizeof(struct icmphdr), pfh->wcheck);
        pfh->icmph.checksum = csum_fold(pfh->wcheck);
        memcpy(icmp_hdr(skb), &pfh->icmph, sizeof(struct icmphdr));
        skb->ip_summed = CHECKSUM_NONE;
        return ip_push_pending_frames(sk, fl4);
}

int ping_common_sendmsg(int family, struct msghdr *msg, size_t len,
                        void *user_icmph, size_t icmph_len)
{
        u8 type, code;

        if (len > 0xFFFF)
                return -EMSGSIZE;

        /* Must have at least a full ICMP header. */
        if (len < icmph_len)
                return -EINVAL;

        /*
         *        Check the flags.
         */

        /* Mirror BSD error message compatibility */
        if (msg->msg_flags & MSG_OOB)
                return -EOPNOTSUPP;

        /*
         *        Fetch the ICMP header provided by the userland.
         *        iovec is modified! The ICMP header is consumed.
         */
        if (memcpy_from_msg(user_icmph, msg, icmph_len))
                return -EFAULT;

        if (family == AF_INET) {
                type = ((struct icmphdr *) user_icmph)->type;
                code = ((struct icmphdr *) user_icmph)->code;
#if IS_ENABLED(CONFIG_IPV6)
        } else if (family == AF_INET6) {
                type = ((struct icmp6hdr *) user_icmph)->icmp6_type;
                code = ((struct icmp6hdr *) user_icmph)->icmp6_code;
#endif
        } else {
                BUG();
        }

        if (!ping_supported(family, type, code))
                return -EINVAL;

        return 0;
}
EXPORT_SYMBOL_GPL(ping_common_sendmsg);

static int ping_v4_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
{
        struct net *net = sock_net(sk);
        struct flowi4 fl4;
        struct inet_sock *inet = inet_sk(sk);
        struct ipcm_cookie ipc;
        struct icmphdr user_icmph;
        struct pingfakehdr pfh;
        struct rtable *rt = NULL;
        struct ip_options_data opt_copy;
        int free = 0;
        __be32 saddr, daddr, faddr;
        u8 tos, scope;
        int err;

        pr_debug("ping_v4_sendmsg(sk=%p,sk->num=%u)\n", inet, inet->inet_num);

        err = ping_common_sendmsg(AF_INET, msg, len, &user_icmph,
                                  sizeof(user_icmph));
        if (err)
                return err;

        /*
         *        Get and verify the address.
         */

        if (msg->msg_name) {
                DECLARE_SOCKADDR(struct sockaddr_in *, usin, msg->msg_name);
                if (msg->msg_namelen < sizeof(*usin))
                        return -EINVAL;
                if (usin->sin_family != AF_INET)
                        return -EAFNOSUPPORT;
                daddr = usin->sin_addr.s_addr;
                /* no remote port */
        } else {
                if (sk->sk_state != TCP_ESTABLISHED)
                        return -EDESTADDRREQ;
                daddr = inet->inet_daddr;
                /* no remote port */
        }

        ipcm_init_sk(&ipc, inet);

        if (msg->msg_controllen) {
                err = ip_cmsg_send(sk, msg, &ipc, false);
                if (unlikely(err)) {
                        kfree(ipc.opt);
                        return err;
                }
                if (ipc.opt)
                        free = 1;
        }
        if (!ipc.opt) {
                struct ip_options_rcu *inet_opt;

                rcu_read_lock();
                inet_opt = rcu_dereference(inet->inet_opt);
                if (inet_opt) {
                        memcpy(&opt_copy, inet_opt,
                               sizeof(*inet_opt) + inet_opt->opt.optlen);
                        ipc.opt = &opt_copy.opt;
                }
                rcu_read_unlock();
        }

        saddr = ipc.addr;
        ipc.addr = faddr = daddr;

        if (ipc.opt && ipc.opt->opt.srr) {
                if (!daddr) {
                        err = -EINVAL;
                        goto out_free;
                }
                faddr = ipc.opt->opt.faddr;
        }
        tos = get_rttos(&ipc, inet);
        scope = ip_sendmsg_scope(inet, &ipc, msg);

        if (ipv4_is_multicast(daddr)) {
                if (!ipc.oif || netif_index_is_l3_master(sock_net(sk), ipc.oif))
                        ipc.oif = READ_ONCE(inet->mc_index);
                if (!saddr)
                        saddr = READ_ONCE(inet->mc_addr);
        } else if (!ipc.oif)
                ipc.oif = READ_ONCE(inet->uc_index);

        flowi4_init_output(&fl4, ipc.oif, ipc.sockc.mark, tos, scope,
                           sk->sk_protocol, inet_sk_flowi_flags(sk), faddr,
                           saddr, 0, 0, sk->sk_uid);

        fl4.fl4_icmp_type = user_icmph.type;
        fl4.fl4_icmp_code = user_icmph.code;

        security_sk_classify_flow(sk, flowi4_to_flowi_common(&fl4));
        rt = ip_route_output_flow(net, &fl4, sk);
        if (IS_ERR(rt)) {
                err = PTR_ERR(rt);
                rt = NULL;
                if (err == -ENETUNREACH)
                        IP_INC_STATS(net, IPSTATS_MIB_OUTNOROUTES);
                goto out;
        }

        err = -EACCES;
        if ((rt->rt_flags & RTCF_BROADCAST) &&
            !sock_flag(sk, SOCK_BROADCAST))
                goto out;

        if (msg->msg_flags & MSG_CONFIRM)
                goto do_confirm;
back_from_confirm:

        if (!ipc.addr)
                ipc.addr = fl4.daddr;

        lock_sock(sk);

        pfh.icmph.type = user_icmph.type; /* already checked */
        pfh.icmph.code = user_icmph.code; /* ditto */
        pfh.icmph.checksum = 0;
        pfh.icmph.un.echo.id = inet->inet_sport;
        pfh.icmph.un.echo.sequence = user_icmph.un.echo.sequence;
        pfh.msg = msg;
        pfh.wcheck = 0;
        pfh.family = AF_INET;

        err = ip_append_data(sk, &fl4, ping_getfrag, &pfh, len,
                             sizeof(struct icmphdr), &ipc, &rt,
                             msg->msg_flags);
        if (err)
                ip_flush_pending_frames(sk);
        else
                err = ping_v4_push_pending_frames(sk, &pfh, &fl4);
        release_sock(sk);

out:
        ip_rt_put(rt);
out_free:
        if (free)
                kfree(ipc.opt);
        if (!err) {
                icmp_out_count(sock_net(sk), user_icmph.type);
                return len;
        }
        return err;

do_confirm:
        if (msg->msg_flags & MSG_PROBE)
                dst_confirm_neigh(&rt->dst, &fl4.daddr);
        if (!(msg->msg_flags & MSG_PROBE) || len)
                goto back_from_confirm;
        err = 0;
        goto out;
}

int ping_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int flags,
                 int *addr_len)
{
        struct inet_sock *isk = inet_sk(sk);
        int family = sk->sk_family;
        struct sk_buff *skb;
        int copied, err;

        pr_debug("ping_recvmsg(sk=%p,sk->num=%u)\n", isk, isk->inet_num);

        err = -EOPNOTSUPP;
        if (flags & MSG_OOB)
                goto out;

        if (flags & MSG_ERRQUEUE)
                return inet_recv_error(sk, msg, len, addr_len);

        skb = skb_recv_datagram(sk, flags, &err);
        if (!skb)
                goto out;

        copied = skb->len;
        if (copied > len) {
                msg->msg_flags |= MSG_TRUNC;
                copied = len;
        }

        /* Don't bother checking the checksum */
        err = skb_copy_datagram_msg(skb, 0, msg, copied);
        if (err)
                goto done;

        sock_recv_timestamp(msg, sk, skb);

        /* Copy the address and add cmsg data. */
        if (family == AF_INET) {
                DECLARE_SOCKADDR(struct sockaddr_in *, sin, msg->msg_name);

                if (sin) {
                        sin->sin_family = AF_INET;
                        sin->sin_port = 0 /* skb->h.uh->source */;
                        sin->sin_addr.s_addr = ip_hdr(skb)->saddr;
                        memset(sin->sin_zero, 0, sizeof(sin->sin_zero));
                        *addr_len = sizeof(*sin);
                }

                if (inet_cmsg_flags(isk))
                        ip_cmsg_recv(msg, skb);

#if IS_ENABLED(CONFIG_IPV6)
        } else if (family == AF_INET6) {
                struct ipv6hdr *ip6 = ipv6_hdr(skb);
                DECLARE_SOCKADDR(struct sockaddr_in6 *, sin6, msg->msg_name);

                if (sin6) {
                        sin6->sin6_family = AF_INET6;
                        sin6->sin6_port = 0;
                        sin6->sin6_addr = ip6->saddr;
                        sin6->sin6_flowinfo = 0;
                        if (inet6_test_bit(SNDFLOW, sk))
                                sin6->sin6_flowinfo = ip6_flowinfo(ip6);
                        sin6->sin6_scope_id =
                                ipv6_iface_scope_id(&sin6->sin6_addr,
                                                    inet6_iif(skb));
                        *addr_len = sizeof(*sin6);
                }

                if (inet6_sk(sk)->rxopt.all)
                        pingv6_ops.ip6_datagram_recv_common_ctl(sk, msg, skb);
                if (skb->protocol == htons(ETH_P_IPV6) &&
                    inet6_sk(sk)->rxopt.all)
                        pingv6_ops.ip6_datagram_recv_specific_ctl(sk, msg, skb);
                else if (skb->protocol == htons(ETH_P_IP) &&
                         inet_cmsg_flags(isk))
                        ip_cmsg_recv(msg, skb);
#endif
        } else {
                BUG();
        }

        err = copied;

done:
        skb_free_datagram(sk, skb);
out:
        pr_debug("ping_recvmsg -> %d\n", err);
        return err;
}
EXPORT_SYMBOL_GPL(ping_recvmsg);

static enum skb_drop_reason __ping_queue_rcv_skb(struct sock *sk,
                                                 struct sk_buff *skb)
{
        enum skb_drop_reason reason;

        pr_debug("ping_queue_rcv_skb(sk=%p,sk->num=%d,skb=%p)\n",
                 inet_sk(sk), inet_sk(sk)->inet_num, skb);
        if (sock_queue_rcv_skb_reason(sk, skb, &reason) < 0) {
                sk_skb_reason_drop(sk, skb, reason);
                pr_debug("ping_queue_rcv_skb -> failed\n");
                return reason;
        }
        return SKB_NOT_DROPPED_YET;
}

int ping_queue_rcv_skb(struct sock *sk, struct sk_buff *skb)
{
        return __ping_queue_rcv_skb(sk, skb) ? -1 : 0;
}
EXPORT_SYMBOL_GPL(ping_queue_rcv_skb);


/*
 *        All we need to do is get the socket.
 */

enum skb_drop_reason ping_rcv(struct sk_buff *skb)
{
        enum skb_drop_reason reason = SKB_DROP_REASON_NO_SOCKET;
        struct sock *sk;
        struct net *net = dev_net(skb->dev);
        struct icmphdr *icmph = icmp_hdr(skb);

        /* We assume the packet has already been checked by icmp_rcv */

        pr_debug("ping_rcv(skb=%p,id=%04x,seq=%04x)\n",
                 skb, ntohs(icmph->un.echo.id), ntohs(icmph->un.echo.sequence));

        /* Push ICMP header back */
        skb_push(skb, skb->data - (u8 *)icmph);

        sk = ping_lookup(net, skb, ntohs(icmph->un.echo.id));
        if (sk) {
                struct sk_buff *skb2 = skb_clone(skb, GFP_ATOMIC);

                pr_debug("rcv on socket %p\n", sk);
                if (skb2)
                        reason = __ping_queue_rcv_skb(sk, skb2);
                else
                        reason = SKB_DROP_REASON_NOMEM;
        }

        if (reason)
                pr_debug("no socket, dropping\n");

        return reason;
}
EXPORT_SYMBOL_GPL(ping_rcv);

struct proto ping_prot = {
        .name =                "PING",
        .owner =        THIS_MODULE,
        .init =                ping_init_sock,
        .close =        ping_close,
        .pre_connect =        ping_pre_connect,
        .connect =        ip4_datagram_connect,
        .disconnect =        __udp_disconnect,
        .setsockopt =        ip_setsockopt,
        .getsockopt =        ip_getsockopt,
        .sendmsg =        ping_v4_sendmsg,
        .recvmsg =        ping_recvmsg,
        .bind =                ping_bind,
        .backlog_rcv =        ping_queue_rcv_skb,
        .release_cb =        ip4_datagram_release_cb,
        .hash =                ping_hash,
        .unhash =        ping_unhash,
        .get_port =        ping_get_port,
        .put_port =        ping_unhash,
        .obj_size =        sizeof(struct inet_sock),
};
EXPORT_SYMBOL(ping_prot);

#ifdef CONFIG_PROC_FS

static struct sock *ping_get_first(struct seq_file *seq, int start)
{
        struct sock *sk;
        struct ping_iter_state *state = seq->private;
        struct net *net = seq_file_net(seq);

        for (state->bucket = start; state->bucket < PING_HTABLE_SIZE;
             ++state->bucket) {
                struct hlist_head *hslot;

                hslot = &ping_table.hash[state->bucket];

                if (hlist_empty(hslot))
                        continue;

                sk_for_each(sk, hslot) {
                        if (net_eq(sock_net(sk), net) &&
                            sk->sk_family == state->family)
                                goto found;
                }
        }
        sk = NULL;
found:
        return sk;
}

static struct sock *ping_get_next(struct seq_file *seq, struct sock *sk)
{
        struct ping_iter_state *state = seq->private;
        struct net *net = seq_file_net(seq);

        do {
                sk = sk_next(sk);
        } while (sk && (!net_eq(sock_net(sk), net)));

        if (!sk)
                return ping_get_first(seq, state->bucket + 1);
        return sk;
}

static struct sock *ping_get_idx(struct seq_file *seq, loff_t pos)
{
        struct sock *sk = ping_get_first(seq, 0);

        if (sk)
                while (pos && (sk = ping_get_next(seq, sk)) != NULL)
                        --pos;
        return pos ? NULL : sk;
}

void *ping_seq_start(struct seq_file *seq, loff_t *pos, sa_family_t family)
        __acquires(ping_table.lock)
{
        struct ping_iter_state *state = seq->private;
        state->bucket = 0;
        state->family = family;

        spin_lock(&ping_table.lock);

        return *pos ? ping_get_idx(seq, *pos-1) : SEQ_START_TOKEN;
}
EXPORT_SYMBOL_GPL(ping_seq_start);

static void *ping_v4_seq_start(struct seq_file *seq, loff_t *pos)
{
        return ping_seq_start(seq, pos, AF_INET);
}

void *ping_seq_next(struct seq_file *seq, void *v, loff_t *pos)
{
        struct sock *sk;

        if (v == SEQ_START_TOKEN)
                sk = ping_get_idx(seq, 0);
        else
                sk = ping_get_next(seq, v);

        ++*pos;
        return sk;
}
EXPORT_SYMBOL_GPL(ping_seq_next);

void ping_seq_stop(struct seq_file *seq, void *v)
        __releases(ping_table.lock)
{
        spin_unlock(&ping_table.lock);
}
EXPORT_SYMBOL_GPL(ping_seq_stop);

static void ping_v4_format_sock(struct sock *sp, struct seq_file *f,
                int bucket)
{
        struct inet_sock *inet = inet_sk(sp);
        __be32 dest = inet->inet_daddr;
        __be32 src = inet->inet_rcv_saddr;
        __u16 destp = ntohs(inet->inet_dport);
        __u16 srcp = ntohs(inet->inet_sport);

        seq_printf(f, "%5d: %08X:%04X %08X:%04X"
                " %02X %08X:%08X %02X:%08lX %08X %5u %8d %lu %d %pK %u",
                bucket, src, srcp, dest, destp, sp->sk_state,
                sk_wmem_alloc_get(sp),
                sk_rmem_alloc_get(sp),
                0, 0L, 0,
                from_kuid_munged(seq_user_ns(f), sock_i_uid(sp)),
                0, sock_i_ino(sp),
                refcount_read(&sp->sk_refcnt), sp,
                atomic_read(&sp->sk_drops));
}

static int ping_v4_seq_show(struct seq_file *seq, void *v)
{
        seq_setwidth(seq, 127);
        if (v == SEQ_START_TOKEN)
                seq_puts(seq, "  sl  local_address rem_address   st tx_queue "
                           "rx_queue tr tm->when retrnsmt   uid  timeout "
                           "inode ref pointer drops");
        else {
                struct ping_iter_state *state = seq->private;

                ping_v4_format_sock(v, seq, state->bucket);
        }
        seq_pad(seq, '\n');
        return 0;
}

static const struct seq_operations ping_v4_seq_ops = {
        .start                = ping_v4_seq_start,
        .show                = ping_v4_seq_show,
        .next                = ping_seq_next,
        .stop                = ping_seq_stop,
};

static int __net_init ping_v4_proc_init_net(struct net *net)
{
        if (!proc_create_net("icmp", 0444, net->proc_net, &ping_v4_seq_ops,
                        sizeof(struct ping_iter_state)))
                return -ENOMEM;
        return 0;
}

static void __net_exit ping_v4_proc_exit_net(struct net *net)
{
        remove_proc_entry("icmp", net->proc_net);
}

static struct pernet_operations ping_v4_net_ops = {
        .init = ping_v4_proc_init_net,
        .exit = ping_v4_proc_exit_net,
};

int __init ping_proc_init(void)
{
        return register_pernet_subsys(&ping_v4_net_ops);
}

void ping_proc_exit(void)
{
        unregister_pernet_subsys(&ping_v4_net_ops);
}

#endif

void __init ping_init(void)
{
        int i;

        for (i = 0; i < PING_HTABLE_SIZE; i++)
                INIT_HLIST_HEAD(&ping_table.hash[i]);
        spin_lock_init(&ping_table.lock);
}









































































































































































































































































































































    1 





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
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
// SPDX-License-Identifier: GPL-2.0-only
/*
 * Copyright (C) 2010 Felix Fietkau <nbd@openwrt.org>
 */
#include <linux/netdevice.h>
#include <linux/types.h>
#include <linux/skbuff.h>
#include <linux/debugfs.h>
#include <linux/ieee80211.h>
#include <linux/export.h>
#include <net/mac80211.h>
#include "rc80211_minstrel_ht.h"

struct minstrel_debugfs_info {
        size_t len;
        char buf[];
};

static ssize_t
minstrel_stats_read(struct file *file, char __user *buf, size_t len, loff_t *ppos)
{
        struct minstrel_debugfs_info *ms;

        ms = file->private_data;
        return simple_read_from_buffer(buf, len, ppos, ms->buf, ms->len);
}

static int
minstrel_stats_release(struct inode *inode, struct file *file)
{
        kfree(file->private_data);
        return 0;
}

static bool
minstrel_ht_is_sample_rate(struct minstrel_ht_sta *mi, int idx)
{
        int type, i;

        for (type = 0; type < ARRAY_SIZE(mi->sample); type++)
                for (i = 0; i < MINSTREL_SAMPLE_RATES; i++)
                        if (mi->sample[type].cur_sample_rates[i] == idx)
                                return true;
        return false;
}

static char *
minstrel_ht_stats_dump(struct minstrel_ht_sta *mi, int i, char *p)
{
        const struct mcs_group *mg;
        unsigned int j, tp_max, tp_avg, eprob, tx_time;
        char htmode = '2';
        char gimode = 'L';
        u32 gflags;

        if (!mi->supported[i])
                return p;

        mg = &minstrel_mcs_groups[i];
        gflags = mg->flags;

        if (gflags & IEEE80211_TX_RC_40_MHZ_WIDTH)
                htmode = '4';
        else if (gflags & IEEE80211_TX_RC_80_MHZ_WIDTH)
                htmode = '8';
        if (gflags & IEEE80211_TX_RC_SHORT_GI)
                gimode = 'S';

        for (j = 0; j < MCS_GROUP_RATES; j++) {
                struct minstrel_rate_stats *mrs = &mi->groups[i].rates[j];
                int idx = MI_RATE(i, j);
                unsigned int duration;

                if (!(mi->supported[i] & BIT(j)))
                        continue;

                if (gflags & IEEE80211_TX_RC_MCS) {
                        p += sprintf(p, "HT%c0  ", htmode);
                        p += sprintf(p, "%cGI  ", gimode);
                        p += sprintf(p, "%d  ", mg->streams);
                } else if (gflags & IEEE80211_TX_RC_VHT_MCS) {
                        p += sprintf(p, "VHT%c0 ", htmode);
                        p += sprintf(p, "%cGI ", gimode);
                        p += sprintf(p, "%d  ", mg->streams);
                } else if (i == MINSTREL_OFDM_GROUP) {
                        p += sprintf(p, "OFDM       ");
                        p += sprintf(p, "1 ");
                } else {
                        p += sprintf(p, "CCK    ");
                        p += sprintf(p, "%cP  ", j < 4 ? 'L' : 'S');
                        p += sprintf(p, "1 ");
                }

                *(p++) = (idx == mi->max_tp_rate[0]) ? 'A' : ' ';
                *(p++) = (idx == mi->max_tp_rate[1]) ? 'B' : ' ';
                *(p++) = (idx == mi->max_tp_rate[2]) ? 'C' : ' ';
                *(p++) = (idx == mi->max_tp_rate[3]) ? 'D' : ' ';
                *(p++) = (idx == mi->max_prob_rate) ? 'P' : ' ';
                *(p++) = minstrel_ht_is_sample_rate(mi, idx) ? 'S' : ' ';

                if (gflags & IEEE80211_TX_RC_MCS) {
                        p += sprintf(p, "  MCS%-2u", (mg->streams - 1) * 8 + j);
                } else if (gflags & IEEE80211_TX_RC_VHT_MCS) {
                        p += sprintf(p, "  MCS%-1u/%1u", j, mg->streams);
                } else {
                        int r;

                        if (i == MINSTREL_OFDM_GROUP)
                                r = minstrel_ofdm_bitrates[j % 8];
                        else
                                r = minstrel_cck_bitrates[j % 4];

                        p += sprintf(p, "   %2u.%1uM", r / 10, r % 10);
                }

                p += sprintf(p, "  %3u  ", idx);

                /* tx_time[rate(i)] in usec */
                duration = mg->duration[j];
                duration <<= mg->shift;
                tx_time = DIV_ROUND_CLOSEST(duration, 1000);
                p += sprintf(p, "%6u  ", tx_time);

                tp_max = minstrel_ht_get_tp_avg(mi, i, j, MINSTREL_FRAC(100, 100));
                tp_avg = minstrel_ht_get_tp_avg(mi, i, j, mrs->prob_avg);
                eprob = MINSTREL_TRUNC(mrs->prob_avg * 1000);

                p += sprintf(p, "%4u.%1u    %4u.%1u     %3u.%1u"
                                "     %3u   %3u %-3u   "
                                "%9llu   %-9llu\n",
                                tp_max / 10, tp_max % 10,
                                tp_avg / 10, tp_avg % 10,
                                eprob / 10, eprob % 10,
                                mrs->retry_count,
                                mrs->last_success,
                                mrs->last_attempts,
                                (unsigned long long)mrs->succ_hist,
                                (unsigned long long)mrs->att_hist);
        }

        return p;
}

static int
minstrel_ht_stats_open(struct inode *inode, struct file *file)
{
        struct minstrel_ht_sta *mi = inode->i_private;
        struct minstrel_debugfs_info *ms;
        unsigned int i;
        char *p;

        ms = kmalloc(32768, GFP_KERNEL);
        if (!ms)
                return -ENOMEM;

        file->private_data = ms;
        p = ms->buf;

        p += sprintf(p, "\n");
        p += sprintf(p,
                     "              best    ____________rate__________    ____statistics___    _____last____    ______sum-of________\n");
        p += sprintf(p,
                     "mode guard #  rate   [name   idx airtime  max_tp]  [avg(tp) avg(prob)]  [retry|suc|att]  [#success | #attempts]\n");

        p = minstrel_ht_stats_dump(mi, MINSTREL_CCK_GROUP, p);
        for (i = 0; i < MINSTREL_CCK_GROUP; i++)
                p = minstrel_ht_stats_dump(mi, i, p);
        for (i++; i < ARRAY_SIZE(mi->groups); i++)
                p = minstrel_ht_stats_dump(mi, i, p);

        p += sprintf(p, "\nTotal packet count::    ideal %d      "
                        "lookaround %d\n",
                        max(0, (int) mi->total_packets - (int) mi->sample_packets),
                        mi->sample_packets);
        if (mi->avg_ampdu_len)
                p += sprintf(p, "Average # of aggregated frames per A-MPDU: %d.%d\n",
                        MINSTREL_TRUNC(mi->avg_ampdu_len),
                        MINSTREL_TRUNC(mi->avg_ampdu_len * 10) % 10);
        ms->len = p - ms->buf;
        WARN_ON(ms->len + sizeof(*ms) > 32768);

        return nonseekable_open(inode, file);
}

static const struct file_operations minstrel_ht_stat_fops = {
        .owner = THIS_MODULE,
        .open = minstrel_ht_stats_open,
        .read = minstrel_stats_read,
        .release = minstrel_stats_release,
};

static char *
minstrel_ht_stats_csv_dump(struct minstrel_ht_sta *mi, int i, char *p)
{
        const struct mcs_group *mg;
        unsigned int j, tp_max, tp_avg, eprob, tx_time;
        char htmode = '2';
        char gimode = 'L';
        u32 gflags;

        if (!mi->supported[i])
                return p;

        mg = &minstrel_mcs_groups[i];
        gflags = mg->flags;

        if (gflags & IEEE80211_TX_RC_40_MHZ_WIDTH)
                htmode = '4';
        else if (gflags & IEEE80211_TX_RC_80_MHZ_WIDTH)
                htmode = '8';
        if (gflags & IEEE80211_TX_RC_SHORT_GI)
                gimode = 'S';

        for (j = 0; j < MCS_GROUP_RATES; j++) {
                struct minstrel_rate_stats *mrs = &mi->groups[i].rates[j];
                int idx = MI_RATE(i, j);
                unsigned int duration;

                if (!(mi->supported[i] & BIT(j)))
                        continue;

                if (gflags & IEEE80211_TX_RC_MCS) {
                        p += sprintf(p, "HT%c0,", htmode);
                        p += sprintf(p, "%cGI,", gimode);
                        p += sprintf(p, "%d,", mg->streams);
                } else if (gflags & IEEE80211_TX_RC_VHT_MCS) {
                        p += sprintf(p, "VHT%c0,", htmode);
                        p += sprintf(p, "%cGI,", gimode);
                        p += sprintf(p, "%d,", mg->streams);
                } else if (i == MINSTREL_OFDM_GROUP) {
                        p += sprintf(p, "OFDM,,1,");
                } else {
                        p += sprintf(p, "CCK,");
                        p += sprintf(p, "%cP,", j < 4 ? 'L' : 'S');
                        p += sprintf(p, "1,");
                }

                p += sprintf(p, "%s" ,((idx == mi->max_tp_rate[0]) ? "A" : ""));
                p += sprintf(p, "%s" ,((idx == mi->max_tp_rate[1]) ? "B" : ""));
                p += sprintf(p, "%s" ,((idx == mi->max_tp_rate[2]) ? "C" : ""));
                p += sprintf(p, "%s" ,((idx == mi->max_tp_rate[3]) ? "D" : ""));
                p += sprintf(p, "%s" ,((idx == mi->max_prob_rate) ? "P" : ""));
                p += sprintf(p, "%s", (minstrel_ht_is_sample_rate(mi, idx) ? "S" : ""));

                if (gflags & IEEE80211_TX_RC_MCS) {
                        p += sprintf(p, ",MCS%-2u,", (mg->streams - 1) * 8 + j);
                } else if (gflags & IEEE80211_TX_RC_VHT_MCS) {
                        p += sprintf(p, ",MCS%-1u/%1u,", j, mg->streams);
                } else {
                        int r;

                        if (i == MINSTREL_OFDM_GROUP)
                                r = minstrel_ofdm_bitrates[j % 8];
                        else
                                r = minstrel_cck_bitrates[j % 4];

                        p += sprintf(p, ",%2u.%1uM,", r / 10, r % 10);
                }

                p += sprintf(p, "%u,", idx);

                duration = mg->duration[j];
                duration <<= mg->shift;
                tx_time = DIV_ROUND_CLOSEST(duration, 1000);
                p += sprintf(p, "%u,", tx_time);

                tp_max = minstrel_ht_get_tp_avg(mi, i, j, MINSTREL_FRAC(100, 100));
                tp_avg = minstrel_ht_get_tp_avg(mi, i, j, mrs->prob_avg);
                eprob = MINSTREL_TRUNC(mrs->prob_avg * 1000);

                p += sprintf(p, "%u.%u,%u.%u,%u.%u,%u,%u,"
                                "%u,%llu,%llu,",
                                tp_max / 10, tp_max % 10,
                                tp_avg / 10, tp_avg % 10,
                                eprob / 10, eprob % 10,
                                mrs->retry_count,
                                mrs->last_success,
                                mrs->last_attempts,
                                (unsigned long long)mrs->succ_hist,
                                (unsigned long long)mrs->att_hist);
                p += sprintf(p, "%d,%d,%d.%d\n",
                                max(0, (int) mi->total_packets -
                                (int) mi->sample_packets),
                                mi->sample_packets,
                                MINSTREL_TRUNC(mi->avg_ampdu_len),
                                MINSTREL_TRUNC(mi->avg_ampdu_len * 10) % 10);
        }

        return p;
}

static int
minstrel_ht_stats_csv_open(struct inode *inode, struct file *file)
{
        struct minstrel_ht_sta *mi = inode->i_private;
        struct minstrel_debugfs_info *ms;
        unsigned int i;
        char *p;

        ms = kmalloc(32768, GFP_KERNEL);
        if (!ms)
                return -ENOMEM;

        file->private_data = ms;

        p = ms->buf;

        p = minstrel_ht_stats_csv_dump(mi, MINSTREL_CCK_GROUP, p);
        for (i = 0; i < MINSTREL_CCK_GROUP; i++)
                p = minstrel_ht_stats_csv_dump(mi, i, p);
        for (i++; i < ARRAY_SIZE(mi->groups); i++)
                p = minstrel_ht_stats_csv_dump(mi, i, p);

        ms->len = p - ms->buf;
        WARN_ON(ms->len + sizeof(*ms) > 32768);

        return nonseekable_open(inode, file);
}

static const struct file_operations minstrel_ht_stat_csv_fops = {
        .owner = THIS_MODULE,
        .open = minstrel_ht_stats_csv_open,
        .read = minstrel_stats_read,
        .release = minstrel_stats_release,
};

void
minstrel_ht_add_sta_debugfs(void *priv, void *priv_sta, struct dentry *dir)
{
        debugfs_create_file("rc_stats", 0444, dir, priv_sta,
                            &minstrel_ht_stat_fops);
        debugfs_create_file("rc_stats_csv", 0444, dir, priv_sta,
                            &minstrel_ht_stat_csv_fops);
}


















































    3 



    1 



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
// SPDX-License-Identifier: GPL-2.0

#include <linux/net.h>
#include <linux/uio.h>
#include <net/sock.h>
#include <linux/nospec.h>

#include "rsrc.h"

#define IO_NOTIF_UBUF_FLAGS        (SKBFL_ZEROCOPY_FRAG | SKBFL_DONT_ORPHAN)
#define IO_NOTIF_SPLICE_BATCH        32

struct io_notif_data {
        struct file                *file;
        struct ubuf_info        uarg;

        struct io_notif_data        *next;
        struct io_notif_data        *head;

        unsigned                account_pages;
        bool                        zc_report;
        bool                        zc_used;
        bool                        zc_copied;
};

struct io_kiocb *io_alloc_notif(struct io_ring_ctx *ctx);
void io_tx_ubuf_complete(struct sk_buff *skb, struct ubuf_info *uarg,
                         bool success);

static inline struct io_notif_data *io_notif_to_data(struct io_kiocb *notif)
{
        return io_kiocb_to_cmd(notif, struct io_notif_data);
}

static inline void io_notif_flush(struct io_kiocb *notif)
        __must_hold(&notif->ctx->uring_lock)
{
        struct io_notif_data *nd = io_notif_to_data(notif);

        io_tx_ubuf_complete(NULL, &nd->uarg, true);
}

static inline int io_notif_account_mem(struct io_kiocb *notif, unsigned len)
{
        struct io_ring_ctx *ctx = notif->ctx;
        struct io_notif_data *nd = io_notif_to_data(notif);
        unsigned nr_pages = (len >> PAGE_SHIFT) + 2;
        int ret;

        if (ctx->user) {
                ret = __io_account_mem(ctx->user, nr_pages);
                if (ret)
                        return ret;
                nd->account_pages += nr_pages;
        }
        return 0;
}























 1159 







  194 






  192 





   94 
    3 
   96 


    7 
    1 




















 2326 





 2183 




 2186 




 1288 
 1288 





  156 
  157 





   90 
   90 




 1987 
 1989 
 1989 


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
// SPDX-License-Identifier: GPL-2.0-only
/*
 * mm/interval_tree.c - interval tree for mapping->i_mmap
 *
 * Copyright (C) 2012, Michel Lespinasse <walken@google.com>
 */

#include <linux/mm.h>
#include <linux/fs.h>
#include <linux/rmap.h>
#include <linux/interval_tree_generic.h>

static inline unsigned long vma_start_pgoff(struct vm_area_struct *v)
{
        return v->vm_pgoff;
}

static inline unsigned long vma_last_pgoff(struct vm_area_struct *v)
{
        return v->vm_pgoff + vma_pages(v) - 1;
}

INTERVAL_TREE_DEFINE(struct vm_area_struct, shared.rb,
                     unsigned long, shared.rb_subtree_last,
                     vma_start_pgoff, vma_last_pgoff, /* empty */, vma_interval_tree)

/* Insert node immediately after prev in the interval tree */
void vma_interval_tree_insert_after(struct vm_area_struct *node,
                                    struct vm_area_struct *prev,
                                    struct rb_root_cached *root)
{
        struct rb_node **link;
        struct vm_area_struct *parent;
        unsigned long last = vma_last_pgoff(node);

        VM_BUG_ON_VMA(vma_start_pgoff(node) != vma_start_pgoff(prev), node);

        if (!prev->shared.rb.rb_right) {
                parent = prev;
                link = &prev->shared.rb.rb_right;
        } else {
                parent = rb_entry(prev->shared.rb.rb_right,
                                  struct vm_area_struct, shared.rb);
                if (parent->shared.rb_subtree_last < last)
                        parent->shared.rb_subtree_last = last;
                while (parent->shared.rb.rb_left) {
                        parent = rb_entry(parent->shared.rb.rb_left,
                                struct vm_area_struct, shared.rb);
                        if (parent->shared.rb_subtree_last < last)
                                parent->shared.rb_subtree_last = last;
                }
                link = &parent->shared.rb.rb_left;
        }

        node->shared.rb_subtree_last = last;
        rb_link_node(&node->shared.rb, &parent->shared.rb, link);
        rb_insert_augmented(&node->shared.rb, &root->rb_root,
                            &vma_interval_tree_augment);
}

static inline unsigned long avc_start_pgoff(struct anon_vma_chain *avc)
{
        return vma_start_pgoff(avc->vma);
}

static inline unsigned long avc_last_pgoff(struct anon_vma_chain *avc)
{
        return vma_last_pgoff(avc->vma);
}

INTERVAL_TREE_DEFINE(struct anon_vma_chain, rb, unsigned long, rb_subtree_last,
                     avc_start_pgoff, avc_last_pgoff,
                     static inline, __anon_vma_interval_tree)

void anon_vma_interval_tree_insert(struct anon_vma_chain *node,
                                   struct rb_root_cached *root)
{
#ifdef CONFIG_DEBUG_VM_RB
        node->cached_vma_start = avc_start_pgoff(node);
        node->cached_vma_last = avc_last_pgoff(node);
#endif
        __anon_vma_interval_tree_insert(node, root);
}

void anon_vma_interval_tree_remove(struct anon_vma_chain *node,
                                   struct rb_root_cached *root)
{
        __anon_vma_interval_tree_remove(node, root);
}

struct anon_vma_chain *
anon_vma_interval_tree_iter_first(struct rb_root_cached *root,
                                  unsigned long first, unsigned long last)
{
        return __anon_vma_interval_tree_iter_first(root, first, last);
}

struct anon_vma_chain *
anon_vma_interval_tree_iter_next(struct anon_vma_chain *node,
                                 unsigned long first, unsigned long last)
{
        return __anon_vma_interval_tree_iter_next(node, first, last);
}

#ifdef CONFIG_DEBUG_VM_RB
void anon_vma_interval_tree_verify(struct anon_vma_chain *node)
{
        WARN_ON_ONCE(node->cached_vma_start != avc_start_pgoff(node));
        WARN_ON_ONCE(node->cached_vma_last != avc_last_pgoff(node));
}
#endif




























































































































































































    2 


































   22 







   22 







    4 


    4 


































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
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
// SPDX-License-Identifier: GPL-2.0-or-later
/*
 * Copyright (C), 2008-2021, OPPO Mobile Comm Corp., Ltd.
 *             https://www.oppo.com/
 */
#include <linux/sysfs.h>
#include <linux/kobject.h>

#include "internal.h"

enum {
        attr_feature,
        attr_drop_caches,
        attr_pointer_ui,
        attr_pointer_bool,
};

enum {
        struct_erofs_sb_info,
        struct_erofs_mount_opts,
};

struct erofs_attr {
        struct attribute attr;
        short attr_id;
        int struct_type, offset;
};

#define EROFS_ATTR(_name, _mode, _id)                                        \
static struct erofs_attr erofs_attr_##_name = {                                \
        .attr = {.name = __stringify(_name), .mode = _mode },                \
        .attr_id = attr_##_id,                                                \
}
#define EROFS_ATTR_FUNC(_name, _mode)        EROFS_ATTR(_name, _mode, _name)
#define EROFS_ATTR_FEATURE(_name)        EROFS_ATTR(_name, 0444, feature)

#define EROFS_ATTR_OFFSET(_name, _mode, _id, _struct)        \
static struct erofs_attr erofs_attr_##_name = {                        \
        .attr = {.name = __stringify(_name), .mode = _mode },        \
        .attr_id = attr_##_id,                                        \
        .struct_type = struct_##_struct,                        \
        .offset = offsetof(struct _struct, _name),\
}

#define EROFS_ATTR_RW(_name, _id, _struct)        \
        EROFS_ATTR_OFFSET(_name, 0644, _id, _struct)

#define EROFS_RO_ATTR(_name, _id, _struct)        \
        EROFS_ATTR_OFFSET(_name, 0444, _id, _struct)

#define EROFS_ATTR_RW_UI(_name, _struct)        \
        EROFS_ATTR_RW(_name, pointer_ui, _struct)

#define EROFS_ATTR_RW_BOOL(_name, _struct)        \
        EROFS_ATTR_RW(_name, pointer_bool, _struct)

#define ATTR_LIST(name) (&erofs_attr_##name.attr)

#ifdef CONFIG_EROFS_FS_ZIP
EROFS_ATTR_RW_UI(sync_decompress, erofs_mount_opts);
EROFS_ATTR_FUNC(drop_caches, 0200);
#endif

static struct attribute *erofs_attrs[] = {
#ifdef CONFIG_EROFS_FS_ZIP
        ATTR_LIST(sync_decompress),
        ATTR_LIST(drop_caches),
#endif
        NULL,
};
ATTRIBUTE_GROUPS(erofs);

/* Features this copy of erofs supports */
EROFS_ATTR_FEATURE(zero_padding);
EROFS_ATTR_FEATURE(compr_cfgs);
EROFS_ATTR_FEATURE(big_pcluster);
EROFS_ATTR_FEATURE(chunked_file);
EROFS_ATTR_FEATURE(device_table);
EROFS_ATTR_FEATURE(compr_head2);
EROFS_ATTR_FEATURE(sb_chksum);
EROFS_ATTR_FEATURE(ztailpacking);
EROFS_ATTR_FEATURE(fragments);
EROFS_ATTR_FEATURE(dedupe);

static struct attribute *erofs_feat_attrs[] = {
        ATTR_LIST(zero_padding),
        ATTR_LIST(compr_cfgs),
        ATTR_LIST(big_pcluster),
        ATTR_LIST(chunked_file),
        ATTR_LIST(device_table),
        ATTR_LIST(compr_head2),
        ATTR_LIST(sb_chksum),
        ATTR_LIST(ztailpacking),
        ATTR_LIST(fragments),
        ATTR_LIST(dedupe),
        NULL,
};
ATTRIBUTE_GROUPS(erofs_feat);

static unsigned char *__struct_ptr(struct erofs_sb_info *sbi,
                                          int struct_type, int offset)
{
        if (struct_type == struct_erofs_sb_info)
                return (unsigned char *)sbi + offset;
        if (struct_type == struct_erofs_mount_opts)
                return (unsigned char *)&sbi->opt + offset;
        return NULL;
}

static ssize_t erofs_attr_show(struct kobject *kobj,
                                struct attribute *attr, char *buf)
{
        struct erofs_sb_info *sbi = container_of(kobj, struct erofs_sb_info,
                                                s_kobj);
        struct erofs_attr *a = container_of(attr, struct erofs_attr, attr);
        unsigned char *ptr = __struct_ptr(sbi, a->struct_type, a->offset);

        switch (a->attr_id) {
        case attr_feature:
                return sysfs_emit(buf, "supported\n");
        case attr_pointer_ui:
                if (!ptr)
                        return 0;
                return sysfs_emit(buf, "%u\n", *(unsigned int *)ptr);
        case attr_pointer_bool:
                if (!ptr)
                        return 0;
                return sysfs_emit(buf, "%d\n", *(bool *)ptr);
        }
        return 0;
}

static ssize_t erofs_attr_store(struct kobject *kobj, struct attribute *attr,
                                                const char *buf, size_t len)
{
        struct erofs_sb_info *sbi = container_of(kobj, struct erofs_sb_info,
                                                s_kobj);
        struct erofs_attr *a = container_of(attr, struct erofs_attr, attr);
        unsigned char *ptr = __struct_ptr(sbi, a->struct_type, a->offset);
        unsigned long t;
        int ret;

        switch (a->attr_id) {
        case attr_pointer_ui:
                if (!ptr)
                        return 0;
                ret = kstrtoul(skip_spaces(buf), 0, &t);
                if (ret)
                        return ret;
                if (t != (unsigned int)t)
                        return -ERANGE;
#ifdef CONFIG_EROFS_FS_ZIP
                if (!strcmp(a->attr.name, "sync_decompress") &&
                    (t > EROFS_SYNC_DECOMPRESS_FORCE_OFF))
                        return -EINVAL;
#endif
                *(unsigned int *)ptr = t;
                return len;
        case attr_pointer_bool:
                if (!ptr)
                        return 0;
                ret = kstrtoul(skip_spaces(buf), 0, &t);
                if (ret)
                        return ret;
                if (t != 0 && t != 1)
                        return -EINVAL;
                *(bool *)ptr = !!t;
                return len;
#ifdef CONFIG_EROFS_FS_ZIP
        case attr_drop_caches:
                ret = kstrtoul(skip_spaces(buf), 0, &t);
                if (ret)
                        return ret;
                if (t < 1 || t > 3)
                        return -EINVAL;

                if (t & 2)
                        z_erofs_shrink_scan(sbi, ~0UL);
                if (t & 1)
                        invalidate_mapping_pages(MNGD_MAPPING(sbi), 0, -1);
                return len;
#endif
        }
        return 0;
}

static void erofs_sb_release(struct kobject *kobj)
{
        struct erofs_sb_info *sbi = container_of(kobj, struct erofs_sb_info,
                                                 s_kobj);
        complete(&sbi->s_kobj_unregister);
}

static const struct sysfs_ops erofs_attr_ops = {
        .show        = erofs_attr_show,
        .store        = erofs_attr_store,
};

static const struct kobj_type erofs_sb_ktype = {
        .default_groups = erofs_groups,
        .sysfs_ops        = &erofs_attr_ops,
        .release        = erofs_sb_release,
};

static const struct kobj_type erofs_ktype = {
        .sysfs_ops        = &erofs_attr_ops,
};

static struct kset erofs_root = {
        .kobj        = {.ktype = &erofs_ktype},
};

static const struct kobj_type erofs_feat_ktype = {
        .default_groups = erofs_feat_groups,
        .sysfs_ops        = &erofs_attr_ops,
};

static struct kobject erofs_feat = {
        .kset        = &erofs_root,
};

int erofs_register_sysfs(struct super_block *sb)
{
        struct erofs_sb_info *sbi = EROFS_SB(sb);
        int err;

        sbi->s_kobj.kset = &erofs_root;
        init_completion(&sbi->s_kobj_unregister);
        err = kobject_init_and_add(&sbi->s_kobj, &erofs_sb_ktype, NULL, "%s",
                                   sb->s_sysfs_name);
        if (err) {
                kobject_put(&sbi->s_kobj);
                wait_for_completion(&sbi->s_kobj_unregister);
        }
        return err;
}

void erofs_unregister_sysfs(struct super_block *sb)
{
        struct erofs_sb_info *sbi = EROFS_SB(sb);

        if (sbi->s_kobj.state_in_sysfs) {
                kobject_del(&sbi->s_kobj);
                kobject_put(&sbi->s_kobj);
                wait_for_completion(&sbi->s_kobj_unregister);
        }
}

int __init erofs_init_sysfs(void)
{
        int ret;

        kobject_set_name(&erofs_root.kobj, "erofs");
        erofs_root.kobj.parent = fs_kobj;
        ret = kset_register(&erofs_root);
        if (ret)
                goto root_err;

        ret = kobject_init_and_add(&erofs_feat, &erofs_feat_ktype,
                                   NULL, "features");
        if (ret)
                goto feat_err;
        return ret;

feat_err:
        kobject_put(&erofs_feat);
        kset_unregister(&erofs_root);
root_err:
        return ret;
}

void erofs_exit_sysfs(void)
{
        kobject_put(&erofs_feat);
        kset_unregister(&erofs_root);
}



























   11 
















































































   14 







   14 







    5 







    5 



   65 










   65 

   65 
   43 




    6 
   65 
   65 




   32 










   32 

   32 
   26 




    3 
   32 
   32 


















  112 

















  112 






   65 

   14 


    5 






   84 













   11 

   11 








































  112 






  112 




















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
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
// SPDX-License-Identifier: GPL-2.0
/*
 *  linux/fs/ext4/hash.c
 *
 * Copyright (C) 2002 by Theodore Ts'o
 */

#include <linux/fs.h>
#include <linux/unicode.h>
#include <linux/compiler.h>
#include <linux/bitops.h>
#include "ext4.h"

#define DELTA 0x9E3779B9

static void TEA_transform(__u32 buf[4], __u32 const in[])
{
        __u32        sum = 0;
        __u32        b0 = buf[0], b1 = buf[1];
        __u32        a = in[0], b = in[1], c = in[2], d = in[3];
        int        n = 16;

        do {
                sum += DELTA;
                b0 += ((b1 << 4)+a) ^ (b1+sum) ^ ((b1 >> 5)+b);
                b1 += ((b0 << 4)+c) ^ (b0+sum) ^ ((b0 >> 5)+d);
        } while (--n);

        buf[0] += b0;
        buf[1] += b1;
}

/* F, G and H are basic MD4 functions: selection, majority, parity */
#define F(x, y, z) ((z) ^ ((x) & ((y) ^ (z))))
#define G(x, y, z) (((x) & (y)) + (((x) ^ (y)) & (z)))
#define H(x, y, z) ((x) ^ (y) ^ (z))

/*
 * The generic round function.  The application is so specific that
 * we don't bother protecting all